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 07:14:50.523807: step: 4/530, loss: 0.011467501521110535
2023-01-24 07:14:51.602251: step: 8/530, loss: 0.014485727064311504
2023-01-24 07:14:52.667057: step: 12/530, loss: 0.02021254412829876
2023-01-24 07:14:53.738434: step: 16/530, loss: 0.014981972053647041
2023-01-24 07:14:54.817861: step: 20/530, loss: 0.013090364634990692
2023-01-24 07:14:55.881413: step: 24/530, loss: 0.021329078823328018
2023-01-24 07:14:56.963243: step: 28/530, loss: 0.015183400362730026
2023-01-24 07:14:58.092896: step: 32/530, loss: 0.03845686465501785
2023-01-24 07:14:59.174594: step: 36/530, loss: 0.04434531182050705
2023-01-24 07:15:00.274968: step: 40/530, loss: 0.03982289880514145
2023-01-24 07:15:01.375316: step: 44/530, loss: 0.015156283974647522
2023-01-24 07:15:02.471347: step: 48/530, loss: 0.03714491426944733
2023-01-24 07:15:03.559708: step: 52/530, loss: 0.04233403503894806
2023-01-24 07:15:04.645218: step: 56/530, loss: 0.08096525073051453
2023-01-24 07:15:05.731415: step: 60/530, loss: 0.027153439819812775
2023-01-24 07:15:06.841576: step: 64/530, loss: 0.04382731020450592
2023-01-24 07:15:07.952260: step: 68/530, loss: 0.025821052491664886
2023-01-24 07:15:09.017823: step: 72/530, loss: 0.05722580477595329
2023-01-24 07:15:10.082145: step: 76/530, loss: 0.014848173595964909
2023-01-24 07:15:11.205191: step: 80/530, loss: 0.03056863322854042
2023-01-24 07:15:12.299563: step: 84/530, loss: 0.02284967713057995
2023-01-24 07:15:13.382042: step: 88/530, loss: 0.01969929039478302
2023-01-24 07:15:14.469785: step: 92/530, loss: 0.027563055977225304
2023-01-24 07:15:15.549540: step: 96/530, loss: 0.04755375534296036
2023-01-24 07:15:16.627764: step: 100/530, loss: 0.017107253894209862
2023-01-24 07:15:17.705829: step: 104/530, loss: 0.01470103021711111
2023-01-24 07:15:18.801916: step: 108/530, loss: 0.05741553008556366
2023-01-24 07:15:19.877667: step: 112/530, loss: 0.05990713834762573
2023-01-24 07:15:20.937137: step: 116/530, loss: 0.010556021705269814
2023-01-24 07:15:22.028373: step: 120/530, loss: 0.022959887981414795
2023-01-24 07:15:23.114640: step: 124/530, loss: 0.01252189464867115
2023-01-24 07:15:24.194013: step: 128/530, loss: 0.019330689683556557
2023-01-24 07:15:25.252709: step: 132/530, loss: 0.0162226390093565
2023-01-24 07:15:26.332174: step: 136/530, loss: 0.061574190855026245
2023-01-24 07:15:27.438432: step: 140/530, loss: 0.027933664619922638
2023-01-24 07:15:28.562435: step: 144/530, loss: 0.015939706936478615
2023-01-24 07:15:29.658429: step: 148/530, loss: 0.08044497668743134
2023-01-24 07:15:30.739252: step: 152/530, loss: 0.03180399909615517
2023-01-24 07:15:31.816568: step: 156/530, loss: 0.016494816169142723
2023-01-24 07:15:32.886864: step: 160/530, loss: 0.01672021672129631
2023-01-24 07:15:33.970988: step: 164/530, loss: 0.023755937814712524
2023-01-24 07:15:35.047372: step: 168/530, loss: 0.014235143549740314
2023-01-24 07:15:36.129198: step: 172/530, loss: 0.018145011737942696
2023-01-24 07:15:37.228002: step: 176/530, loss: 0.019230917096138
2023-01-24 07:15:38.305242: step: 180/530, loss: 0.032779112458229065
2023-01-24 07:15:39.377265: step: 184/530, loss: 0.0101863332092762
2023-01-24 07:15:40.451508: step: 188/530, loss: 0.0157422237098217
2023-01-24 07:15:41.546831: step: 192/530, loss: 0.006937301717698574
2023-01-24 07:15:42.641773: step: 196/530, loss: 0.05183155834674835
2023-01-24 07:15:43.707352: step: 200/530, loss: 0.05829997733235359
2023-01-24 07:15:44.803808: step: 204/530, loss: 0.010822414420545101
2023-01-24 07:15:45.880686: step: 208/530, loss: 0.05365070700645447
2023-01-24 07:15:46.965405: step: 212/530, loss: 0.011589542962610722
2023-01-24 07:15:48.052790: step: 216/530, loss: 0.018661417067050934
2023-01-24 07:15:49.131073: step: 220/530, loss: 0.0364769771695137
2023-01-24 07:15:50.207786: step: 224/530, loss: 0.05967678129673004
2023-01-24 07:15:51.288505: step: 228/530, loss: 0.02332700416445732
2023-01-24 07:15:52.359329: step: 232/530, loss: 0.01643318310379982
2023-01-24 07:15:53.426120: step: 236/530, loss: 0.01622905768454075
2023-01-24 07:15:54.500424: step: 240/530, loss: 0.014846382662653923
2023-01-24 07:15:55.587460: step: 244/530, loss: 0.021980928257107735
2023-01-24 07:15:56.670092: step: 248/530, loss: 0.04995280131697655
2023-01-24 07:15:57.757027: step: 252/530, loss: 0.008162538520991802
2023-01-24 07:15:58.849998: step: 256/530, loss: 0.013937925919890404
2023-01-24 07:15:59.915648: step: 260/530, loss: 0.021493133157491684
2023-01-24 07:16:01.014967: step: 264/530, loss: 0.011338409967720509
2023-01-24 07:16:02.116749: step: 268/530, loss: 0.012696531601250172
2023-01-24 07:16:03.256418: step: 272/530, loss: 0.011421488597989082
2023-01-24 07:16:04.354022: step: 276/530, loss: 0.03716360032558441
2023-01-24 07:16:05.436736: step: 280/530, loss: 0.014100338332355022
2023-01-24 07:16:06.551260: step: 284/530, loss: 0.011375023052096367
2023-01-24 07:16:07.615735: step: 288/530, loss: 0.008520003408193588
2023-01-24 07:16:08.728094: step: 292/530, loss: 0.010339656844735146
2023-01-24 07:16:09.791596: step: 296/530, loss: 0.012516725808382034
2023-01-24 07:16:10.858076: step: 300/530, loss: 0.009284278377890587
2023-01-24 07:16:11.950383: step: 304/530, loss: 0.013679335825145245
2023-01-24 07:16:13.032064: step: 308/530, loss: 0.013499300926923752
2023-01-24 07:16:14.157425: step: 312/530, loss: 0.02213696762919426
2023-01-24 07:16:15.225872: step: 316/530, loss: 0.0557267889380455
2023-01-24 07:16:16.319797: step: 320/530, loss: 0.016188064590096474
2023-01-24 07:16:17.395874: step: 324/530, loss: 0.010495403781533241
2023-01-24 07:16:18.515594: step: 328/530, loss: 0.05542273446917534
2023-01-24 07:16:19.587209: step: 332/530, loss: 0.018293123692274094
2023-01-24 07:16:20.667463: step: 336/530, loss: 0.047707267105579376
2023-01-24 07:16:21.752055: step: 340/530, loss: 0.04012608528137207
2023-01-24 07:16:22.839583: step: 344/530, loss: 0.010144260711967945
2023-01-24 07:16:23.948042: step: 348/530, loss: 0.0537719689309597
2023-01-24 07:16:25.051187: step: 352/530, loss: 0.030783772468566895
2023-01-24 07:16:26.143989: step: 356/530, loss: 0.013567428104579449
2023-01-24 07:16:27.217372: step: 360/530, loss: 0.015386553481221199
2023-01-24 07:16:28.296297: step: 364/530, loss: 0.048650193959474564
2023-01-24 07:16:29.379907: step: 368/530, loss: 0.05116035416722298
2023-01-24 07:16:30.447884: step: 372/530, loss: 0.040121253579854965
2023-01-24 07:16:31.533760: step: 376/530, loss: 0.003961693029850721
2023-01-24 07:16:32.601438: step: 380/530, loss: 0.024890054017305374
2023-01-24 07:16:33.696738: step: 384/530, loss: 0.009636261500418186
2023-01-24 07:16:34.802827: step: 388/530, loss: 0.050982046872377396
2023-01-24 07:16:35.883060: step: 392/530, loss: 0.010965893976390362
2023-01-24 07:16:36.972857: step: 396/530, loss: 0.018137114122509956
2023-01-24 07:16:38.041184: step: 400/530, loss: 0.03513287007808685
2023-01-24 07:16:39.116776: step: 404/530, loss: 0.009723388589918613
2023-01-24 07:16:40.221867: step: 408/530, loss: 0.009628687053918839
2023-01-24 07:16:41.326975: step: 412/530, loss: 0.011322302743792534
2023-01-24 07:16:42.447334: step: 416/530, loss: 0.015155560337007046
2023-01-24 07:16:43.531491: step: 420/530, loss: 0.05574380233883858
2023-01-24 07:16:44.598555: step: 424/530, loss: 0.031009312719106674
2023-01-24 07:16:45.687271: step: 428/530, loss: 0.009676420129835606
2023-01-24 07:16:46.771431: step: 432/530, loss: 0.01221969723701477
2023-01-24 07:16:47.875499: step: 436/530, loss: 0.017525238916277885
2023-01-24 07:16:48.949421: step: 440/530, loss: 0.021521715447306633
2023-01-24 07:16:50.006181: step: 444/530, loss: 0.05986635386943817
2023-01-24 07:16:51.084231: step: 448/530, loss: 0.012541204690933228
2023-01-24 07:16:52.162059: step: 452/530, loss: 0.020448947325348854
2023-01-24 07:16:53.250930: step: 456/530, loss: 0.009558239951729774
2023-01-24 07:16:54.360991: step: 460/530, loss: 0.05682926997542381
2023-01-24 07:16:55.442039: step: 464/530, loss: 0.01390343252569437
2023-01-24 07:16:56.552466: step: 468/530, loss: 0.011025974527001381
2023-01-24 07:16:57.613497: step: 472/530, loss: 0.01932631805539131
2023-01-24 07:16:58.695003: step: 476/530, loss: 0.035168226808309555
2023-01-24 07:16:59.778421: step: 480/530, loss: 0.015916112810373306
2023-01-24 07:17:00.870237: step: 484/530, loss: 0.033374249935150146
2023-01-24 07:17:01.943129: step: 488/530, loss: 0.07296033948659897
2023-01-24 07:17:03.051783: step: 492/530, loss: 0.037825677543878555
2023-01-24 07:17:04.124569: step: 496/530, loss: 0.014952165074646473
2023-01-24 07:17:05.241465: step: 500/530, loss: 0.005028252024203539
2023-01-24 07:17:06.328997: step: 504/530, loss: 0.07204002141952515
2023-01-24 07:17:07.406810: step: 508/530, loss: 0.0398731455206871
2023-01-24 07:17:08.474959: step: 512/530, loss: 0.025840265676379204
2023-01-24 07:17:09.547612: step: 516/530, loss: 0.018875647336244583
2023-01-24 07:17:10.622664: step: 520/530, loss: 0.008626456372439861
2023-01-24 07:17:11.688143: step: 524/530, loss: 0.021149303764104843
2023-01-24 07:17:12.798997: step: 528/530, loss: 0.062265027314424515
2023-01-24 07:17:13.889062: step: 532/530, loss: 0.01840990222990513
2023-01-24 07:17:14.987086: step: 536/530, loss: 0.008780206553637981
2023-01-24 07:17:16.068720: step: 540/530, loss: 0.03259558603167534
2023-01-24 07:17:17.146016: step: 544/530, loss: 0.051471538841724396
2023-01-24 07:17:18.220126: step: 548/530, loss: 0.014503030106425285
2023-01-24 07:17:19.309890: step: 552/530, loss: 0.01766877993941307
2023-01-24 07:17:20.392005: step: 556/530, loss: 0.011895626783370972
2023-01-24 07:17:21.487423: step: 560/530, loss: 0.01722758449614048
2023-01-24 07:17:22.570510: step: 564/530, loss: 0.047568801790475845
2023-01-24 07:17:23.657858: step: 568/530, loss: 0.02621176652610302
2023-01-24 07:17:24.742692: step: 572/530, loss: 0.04431449621915817
2023-01-24 07:17:25.829396: step: 576/530, loss: 0.007582752034068108
2023-01-24 07:17:26.876618: step: 580/530, loss: 0.009157495573163033
2023-01-24 07:17:27.959432: step: 584/530, loss: 0.023113993927836418
2023-01-24 07:17:29.062430: step: 588/530, loss: 0.014447697438299656
2023-01-24 07:17:30.163020: step: 592/530, loss: 0.010446269996464252
2023-01-24 07:17:31.259652: step: 596/530, loss: 0.053101733326911926
2023-01-24 07:17:32.344419: step: 600/530, loss: 0.02219861000776291
2023-01-24 07:17:33.448730: step: 604/530, loss: 0.00992828793823719
2023-01-24 07:17:34.533708: step: 608/530, loss: 0.04490850865840912
2023-01-24 07:17:35.645872: step: 612/530, loss: 0.011792284436523914
2023-01-24 07:17:36.724828: step: 616/530, loss: 0.009993292391300201
2023-01-24 07:17:37.820080: step: 620/530, loss: 0.010060536675155163
2023-01-24 07:17:38.870438: step: 624/530, loss: 0.050234872847795486
2023-01-24 07:17:39.971791: step: 628/530, loss: 0.019075261428952217
2023-01-24 07:17:41.029330: step: 632/530, loss: 0.016102146357297897
2023-01-24 07:17:42.122712: step: 636/530, loss: 0.010150427930057049
2023-01-24 07:17:43.217896: step: 640/530, loss: 0.009431491605937481
2023-01-24 07:17:44.298933: step: 644/530, loss: 0.009330429136753082
2023-01-24 07:17:45.394661: step: 648/530, loss: 0.013603986240923405
2023-01-24 07:17:46.483993: step: 652/530, loss: 0.007064360659569502
2023-01-24 07:17:47.553415: step: 656/530, loss: 0.010857746005058289
2023-01-24 07:17:48.620986: step: 660/530, loss: 0.010749378241598606
2023-01-24 07:17:49.695485: step: 664/530, loss: 0.03511538356542587
2023-01-24 07:17:50.785484: step: 668/530, loss: 0.00687797786667943
2023-01-24 07:17:51.884201: step: 672/530, loss: 0.016551679000258446
2023-01-24 07:17:52.984145: step: 676/530, loss: 0.008278360590338707
2023-01-24 07:17:54.088069: step: 680/530, loss: 0.013280468992888927
2023-01-24 07:17:55.173288: step: 684/530, loss: 0.052824780344963074
2023-01-24 07:17:56.275473: step: 688/530, loss: 0.04155043512582779
2023-01-24 07:17:57.351825: step: 692/530, loss: 0.009191321209073067
2023-01-24 07:17:58.425719: step: 696/530, loss: 0.00856541283428669
2023-01-24 07:17:59.502395: step: 700/530, loss: 0.007178144529461861
2023-01-24 07:18:00.579533: step: 704/530, loss: 0.005115367006510496
2023-01-24 07:18:01.654167: step: 708/530, loss: 0.011410994455218315
2023-01-24 07:18:02.731030: step: 712/530, loss: 0.017877524718642235
2023-01-24 07:18:03.829585: step: 716/530, loss: 0.03520526736974716
2023-01-24 07:18:04.905496: step: 720/530, loss: 0.001963396556675434
2023-01-24 07:18:05.975172: step: 724/530, loss: 0.0020664336625486612
2023-01-24 07:18:07.043373: step: 728/530, loss: 0.017566706985235214
2023-01-24 07:18:08.134667: step: 732/530, loss: 0.029703212901949883
2023-01-24 07:18:09.223720: step: 736/530, loss: 0.015074805356562138
2023-01-24 07:18:10.300410: step: 740/530, loss: 0.05114130303263664
2023-01-24 07:18:11.367874: step: 744/530, loss: 0.06399284303188324
2023-01-24 07:18:12.454586: step: 748/530, loss: 0.018372777849435806
2023-01-24 07:18:13.516950: step: 752/530, loss: 0.010410459712147713
2023-01-24 07:18:14.612779: step: 756/530, loss: 0.06911301612854004
2023-01-24 07:18:15.690578: step: 760/530, loss: 0.004994244780391455
2023-01-24 07:18:16.775261: step: 764/530, loss: 0.03868423029780388
2023-01-24 07:18:17.855845: step: 768/530, loss: 0.008029693737626076
2023-01-24 07:18:18.925643: step: 772/530, loss: 0.01988298073410988
2023-01-24 07:18:20.018910: step: 776/530, loss: 0.018982091918587685
2023-01-24 07:18:21.102009: step: 780/530, loss: 0.035353220999240875
2023-01-24 07:18:22.174044: step: 784/530, loss: 0.006461441516876221
2023-01-24 07:18:23.263048: step: 788/530, loss: 0.008811785839498043
2023-01-24 07:18:24.345069: step: 792/530, loss: 0.049760594964027405
2023-01-24 07:18:25.436516: step: 796/530, loss: 0.011513302102684975
2023-01-24 07:18:26.522497: step: 800/530, loss: 0.007470728363841772
2023-01-24 07:18:27.619792: step: 804/530, loss: 0.03038622811436653
2023-01-24 07:18:28.716792: step: 808/530, loss: 0.02139291912317276
2023-01-24 07:18:29.812604: step: 812/530, loss: 0.039839550852775574
2023-01-24 07:18:30.904641: step: 816/530, loss: 0.007161576300859451
2023-01-24 07:18:31.984699: step: 820/530, loss: 0.014159068465232849
2023-01-24 07:18:33.072645: step: 824/530, loss: 0.019974643364548683
2023-01-24 07:18:34.155356: step: 828/530, loss: 0.013316066935658455
2023-01-24 07:18:35.241708: step: 832/530, loss: 0.022347649559378624
2023-01-24 07:18:36.330585: step: 836/530, loss: 0.03583676740527153
2023-01-24 07:18:37.418503: step: 840/530, loss: 0.012776310555636883
2023-01-24 07:18:38.500437: step: 844/530, loss: 0.012068641372025013
2023-01-24 07:18:39.607753: step: 848/530, loss: 0.013448876328766346
2023-01-24 07:18:40.734346: step: 852/530, loss: 0.018185192719101906
2023-01-24 07:18:41.832586: step: 856/530, loss: 0.01383522991091013
2023-01-24 07:18:42.925186: step: 860/530, loss: 0.04743143916130066
2023-01-24 07:18:44.000596: step: 864/530, loss: 0.01881537400186062
2023-01-24 07:18:45.092692: step: 868/530, loss: 0.013506807386875153
2023-01-24 07:18:46.176168: step: 872/530, loss: 0.007484327536076307
2023-01-24 07:18:47.266640: step: 876/530, loss: 0.007950818166136742
2023-01-24 07:18:48.339631: step: 880/530, loss: 0.009719445370137691
2023-01-24 07:18:49.438522: step: 884/530, loss: 0.014991038478910923
2023-01-24 07:18:50.535656: step: 888/530, loss: 0.008596524596214294
2023-01-24 07:18:51.620743: step: 892/530, loss: 0.013084711506962776
2023-01-24 07:18:52.699813: step: 896/530, loss: 0.014744004234671593
2023-01-24 07:18:53.800263: step: 900/530, loss: 0.023029623553156853
2023-01-24 07:18:54.875395: step: 904/530, loss: 0.019510850310325623
2023-01-24 07:18:55.970599: step: 908/530, loss: 0.009823204018175602
2023-01-24 07:18:57.049357: step: 912/530, loss: 0.009708911180496216
2023-01-24 07:18:58.128706: step: 916/530, loss: 0.004477589391171932
2023-01-24 07:18:59.228346: step: 920/530, loss: 0.017420802265405655
2023-01-24 07:19:00.309293: step: 924/530, loss: 0.008795643225312233
2023-01-24 07:19:01.401015: step: 928/530, loss: 0.02314850687980652
2023-01-24 07:19:02.469474: step: 932/530, loss: 0.028379026800394058
2023-01-24 07:19:03.555199: step: 936/530, loss: 0.01130882278084755
2023-01-24 07:19:04.644143: step: 940/530, loss: 0.007444203831255436
2023-01-24 07:19:05.733843: step: 944/530, loss: 0.012078704312443733
2023-01-24 07:19:06.819762: step: 948/530, loss: 0.013832642696797848
2023-01-24 07:19:07.913391: step: 952/530, loss: 0.008240267634391785
2023-01-24 07:19:09.009333: step: 956/530, loss: 0.007556191645562649
2023-01-24 07:19:10.098663: step: 960/530, loss: 0.025990257039666176
2023-01-24 07:19:11.201287: step: 964/530, loss: 0.014192350208759308
2023-01-24 07:19:12.292532: step: 968/530, loss: 0.011100104078650475
2023-01-24 07:19:13.390166: step: 972/530, loss: 0.006428951863199472
2023-01-24 07:19:14.456947: step: 976/530, loss: 0.05296020209789276
2023-01-24 07:19:15.543864: step: 980/530, loss: 0.009439952671527863
2023-01-24 07:19:16.672582: step: 984/530, loss: 0.009728724136948586
2023-01-24 07:19:17.740831: step: 988/530, loss: 0.04730822518467903
2023-01-24 07:19:18.850662: step: 992/530, loss: 0.052044834941625595
2023-01-24 07:19:19.929361: step: 996/530, loss: 0.02639291062951088
2023-01-24 07:19:20.999447: step: 1000/530, loss: 0.008362848311662674
2023-01-24 07:19:22.076807: step: 1004/530, loss: 0.013744687661528587
2023-01-24 07:19:23.138127: step: 1008/530, loss: 0.005262541584670544
2023-01-24 07:19:24.245203: step: 1012/530, loss: 0.011320390738546848
2023-01-24 07:19:25.301202: step: 1016/530, loss: 0.02581048011779785
2023-01-24 07:19:26.388058: step: 1020/530, loss: 0.011062169447541237
2023-01-24 07:19:27.461001: step: 1024/530, loss: 0.026677079498767853
2023-01-24 07:19:28.554798: step: 1028/530, loss: 0.0048840949311852455
2023-01-24 07:19:29.659966: step: 1032/530, loss: 0.011815915815532207
2023-01-24 07:19:30.727379: step: 1036/530, loss: 0.01807076670229435
2023-01-24 07:19:31.826036: step: 1040/530, loss: 0.041602972894907
2023-01-24 07:19:32.909752: step: 1044/530, loss: 0.05111640691757202
2023-01-24 07:19:33.988300: step: 1048/530, loss: 0.007702759001404047
2023-01-24 07:19:35.097315: step: 1052/530, loss: 0.04642478749155998
2023-01-24 07:19:36.184271: step: 1056/530, loss: 0.009657839313149452
2023-01-24 07:19:37.265157: step: 1060/530, loss: 0.008408733643591404
2023-01-24 07:19:38.353388: step: 1064/530, loss: 0.02986236847937107
2023-01-24 07:19:39.439895: step: 1068/530, loss: 0.009164144285023212
2023-01-24 07:19:40.522245: step: 1072/530, loss: 0.009531466290354729
2023-01-24 07:19:41.611355: step: 1076/530, loss: 0.006760431919246912
2023-01-24 07:19:42.702592: step: 1080/530, loss: 0.010862594470381737
2023-01-24 07:19:43.797548: step: 1084/530, loss: 0.011358842253684998
2023-01-24 07:19:44.879955: step: 1088/530, loss: 0.015605390071868896
2023-01-24 07:19:45.958426: step: 1092/530, loss: 0.025138139724731445
2023-01-24 07:19:47.060519: step: 1096/530, loss: 0.06401416659355164
2023-01-24 07:19:48.154592: step: 1100/530, loss: 0.009003587998449802
2023-01-24 07:19:49.210219: step: 1104/530, loss: 0.018553756177425385
2023-01-24 07:19:50.284889: step: 1108/530, loss: 0.009399579837918282
2023-01-24 07:19:51.353662: step: 1112/530, loss: 0.010055833496153355
2023-01-24 07:19:52.428481: step: 1116/530, loss: 0.007202986627817154
2023-01-24 07:19:53.516320: step: 1120/530, loss: 0.018063019961118698
2023-01-24 07:19:54.605910: step: 1124/530, loss: 0.005566895008087158
2023-01-24 07:19:55.693566: step: 1128/530, loss: 0.013489291071891785
2023-01-24 07:19:56.781024: step: 1132/530, loss: 0.018932178616523743
2023-01-24 07:19:57.868156: step: 1136/530, loss: 0.0192992202937603
2023-01-24 07:19:58.958754: step: 1140/530, loss: 0.06442520022392273
2023-01-24 07:20:00.043567: step: 1144/530, loss: 0.017229406163096428
2023-01-24 07:20:01.132380: step: 1148/530, loss: 0.023317674174904823
2023-01-24 07:20:02.223083: step: 1152/530, loss: 0.009954470209777355
2023-01-24 07:20:03.310918: step: 1156/530, loss: 0.015561471693217754
2023-01-24 07:20:04.394899: step: 1160/530, loss: 0.008471912704408169
2023-01-24 07:20:05.496771: step: 1164/530, loss: 0.006097727920860052
2023-01-24 07:20:06.578939: step: 1168/530, loss: 0.02479659393429756
2023-01-24 07:20:07.662342: step: 1172/530, loss: 0.021039575338363647
2023-01-24 07:20:08.743416: step: 1176/530, loss: 0.008313262835144997
2023-01-24 07:20:09.822342: step: 1180/530, loss: 0.014532352797687054
2023-01-24 07:20:10.907266: step: 1184/530, loss: 0.010721875354647636
2023-01-24 07:20:12.024678: step: 1188/530, loss: 0.0011187108466401696
2023-01-24 07:20:13.110941: step: 1192/530, loss: 0.008913950994610786
2023-01-24 07:20:14.196996: step: 1196/530, loss: 0.013864309526979923
2023-01-24 07:20:15.275359: step: 1200/530, loss: 0.021943002939224243
2023-01-24 07:20:16.360438: step: 1204/530, loss: 0.046534888446331024
2023-01-24 07:20:17.456405: step: 1208/530, loss: 0.003053515451028943
2023-01-24 07:20:18.542480: step: 1212/530, loss: 0.027452979236841202
2023-01-24 07:20:19.619386: step: 1216/530, loss: 0.03662760183215141
2023-01-24 07:20:20.719948: step: 1220/530, loss: 0.007847432047128677
2023-01-24 07:20:21.816217: step: 1224/530, loss: 0.04117194935679436
2023-01-24 07:20:22.910321: step: 1228/530, loss: 0.014644318260252476
2023-01-24 07:20:24.000753: step: 1232/530, loss: 0.01593797095119953
2023-01-24 07:20:25.091963: step: 1236/530, loss: 0.014883672818541527
2023-01-24 07:20:26.169445: step: 1240/530, loss: 0.007079263683408499
2023-01-24 07:20:27.256348: step: 1244/530, loss: 0.008620164357125759
2023-01-24 07:20:28.334099: step: 1248/530, loss: 0.01168068964034319
2023-01-24 07:20:29.440193: step: 1252/530, loss: 0.012292832136154175
2023-01-24 07:20:30.525337: step: 1256/530, loss: 0.009831907227635384
2023-01-24 07:20:31.639606: step: 1260/530, loss: 0.0096824262291193
2023-01-24 07:20:32.733376: step: 1264/530, loss: 0.008983486331999302
2023-01-24 07:20:33.821487: step: 1268/530, loss: 0.051251497119665146
2023-01-24 07:20:34.905589: step: 1272/530, loss: 0.015889881178736687
2023-01-24 07:20:36.016261: step: 1276/530, loss: 0.013440173119306564
2023-01-24 07:20:37.093942: step: 1280/530, loss: 0.010372988879680634
2023-01-24 07:20:38.168261: step: 1284/530, loss: 0.03607025742530823
2023-01-24 07:20:39.266221: step: 1288/530, loss: 0.013582274317741394
2023-01-24 07:20:40.377218: step: 1292/530, loss: 0.04075070098042488
2023-01-24 07:20:41.453126: step: 1296/530, loss: 0.004589695017784834
2023-01-24 07:20:42.545891: step: 1300/530, loss: 0.011066440492868423
2023-01-24 07:20:43.615399: step: 1304/530, loss: 0.012043549679219723
2023-01-24 07:20:44.705210: step: 1308/530, loss: 0.001740098581649363
2023-01-24 07:20:45.794396: step: 1312/530, loss: 0.013796101324260235
2023-01-24 07:20:46.865736: step: 1316/530, loss: 0.052267950028181076
2023-01-24 07:20:47.949401: step: 1320/530, loss: 0.0011448016157373786
2023-01-24 07:20:49.025612: step: 1324/530, loss: 0.013321767561137676
2023-01-24 07:20:50.117671: step: 1328/530, loss: 0.0713484063744545
2023-01-24 07:20:51.202922: step: 1332/530, loss: 0.014469791203737259
2023-01-24 07:20:52.284658: step: 1336/530, loss: 0.011115959845483303
2023-01-24 07:20:53.385340: step: 1340/530, loss: 0.034775689244270325
2023-01-24 07:20:54.481098: step: 1344/530, loss: 0.03947098180651665
2023-01-24 07:20:55.569630: step: 1348/530, loss: 0.033898014575242996
2023-01-24 07:20:56.644624: step: 1352/530, loss: 0.02264307253062725
2023-01-24 07:20:57.730321: step: 1356/530, loss: 0.011270228773355484
2023-01-24 07:20:58.831222: step: 1360/530, loss: 0.009110105223953724
2023-01-24 07:20:59.912922: step: 1364/530, loss: 0.004825693555176258
2023-01-24 07:21:01.006504: step: 1368/530, loss: 0.00863538309931755
2023-01-24 07:21:02.098543: step: 1372/530, loss: 0.08705249428749084
2023-01-24 07:21:03.178410: step: 1376/530, loss: 0.036806944757699966
2023-01-24 07:21:04.296468: step: 1380/530, loss: 0.016920851543545723
2023-01-24 07:21:05.368778: step: 1384/530, loss: 0.013329208828508854
2023-01-24 07:21:06.434095: step: 1388/530, loss: 0.014396107755601406
2023-01-24 07:21:07.520399: step: 1392/530, loss: 0.05370703712105751
2023-01-24 07:21:08.603563: step: 1396/530, loss: 0.015506411902606487
2023-01-24 07:21:09.705702: step: 1400/530, loss: 0.016293397173285484
2023-01-24 07:21:10.785982: step: 1404/530, loss: 0.008619780652225018
2023-01-24 07:21:11.875148: step: 1408/530, loss: 0.017172975465655327
2023-01-24 07:21:12.968303: step: 1412/530, loss: 0.017536213621497154
2023-01-24 07:21:14.043280: step: 1416/530, loss: 0.013121065683662891
2023-01-24 07:21:15.117003: step: 1420/530, loss: 0.009021638892591
2023-01-24 07:21:16.215860: step: 1424/530, loss: 0.019467992708086967
2023-01-24 07:21:17.294546: step: 1428/530, loss: 0.0451773963868618
2023-01-24 07:21:18.398425: step: 1432/530, loss: 0.0163405891507864
2023-01-24 07:21:19.491754: step: 1436/530, loss: 0.006332543212920427
2023-01-24 07:21:20.581009: step: 1440/530, loss: 0.013158321380615234
2023-01-24 07:21:21.666797: step: 1444/530, loss: 0.010919002816081047
2023-01-24 07:21:22.762675: step: 1448/530, loss: 0.005222956649959087
2023-01-24 07:21:23.850501: step: 1452/530, loss: 0.007199855521321297
2023-01-24 07:21:24.949306: step: 1456/530, loss: 0.0466931015253067
2023-01-24 07:21:26.053625: step: 1460/530, loss: 0.02764984965324402
2023-01-24 07:21:27.138639: step: 1464/530, loss: 0.015452233143150806
2023-01-24 07:21:28.212299: step: 1468/530, loss: 0.013781887479126453
2023-01-24 07:21:29.284419: step: 1472/530, loss: 0.008006605319678783
2023-01-24 07:21:30.377411: step: 1476/530, loss: 0.009298715740442276
2023-01-24 07:21:31.487909: step: 1480/530, loss: 0.017962105572223663
2023-01-24 07:21:32.579093: step: 1484/530, loss: 0.04525889456272125
2023-01-24 07:21:33.661503: step: 1488/530, loss: 0.0073051913641393185
2023-01-24 07:21:34.761565: step: 1492/530, loss: 0.006594618316739798
2023-01-24 07:21:35.865030: step: 1496/530, loss: 0.03404797613620758
2023-01-24 07:21:36.935653: step: 1500/530, loss: 0.006146298721432686
2023-01-24 07:21:38.020316: step: 1504/530, loss: 0.0053114937618374825
2023-01-24 07:21:39.102468: step: 1508/530, loss: 0.007468213327229023
2023-01-24 07:21:40.191122: step: 1512/530, loss: 0.016199523583054543
2023-01-24 07:21:41.261195: step: 1516/530, loss: 0.009386864490807056
2023-01-24 07:21:42.363021: step: 1520/530, loss: 0.040742166340351105
2023-01-24 07:21:43.430227: step: 1524/530, loss: 0.01466831099241972
2023-01-24 07:21:44.518714: step: 1528/530, loss: 0.06471836566925049
2023-01-24 07:21:45.607117: step: 1532/530, loss: 0.06189916282892227
2023-01-24 07:21:46.688017: step: 1536/530, loss: 0.005648388527333736
2023-01-24 07:21:47.763428: step: 1540/530, loss: 0.005295681767165661
2023-01-24 07:21:48.834416: step: 1544/530, loss: 0.038363661617040634
2023-01-24 07:21:49.923158: step: 1548/530, loss: 0.01912683993577957
2023-01-24 07:21:51.035951: step: 1552/530, loss: 0.02115822024643421
2023-01-24 07:21:52.114673: step: 1556/530, loss: 0.006661378778517246
2023-01-24 07:21:53.194518: step: 1560/530, loss: 0.0025027559604495764
2023-01-24 07:21:54.283654: step: 1564/530, loss: 0.028140855953097343
2023-01-24 07:21:55.379933: step: 1568/530, loss: 0.05170895904302597
2023-01-24 07:21:56.463682: step: 1572/530, loss: 0.015366709791123867
2023-01-24 07:21:57.546881: step: 1576/530, loss: 0.0493619404733181
2023-01-24 07:21:58.638168: step: 1580/530, loss: 0.006609445903450251
2023-01-24 07:21:59.729723: step: 1584/530, loss: 0.086870476603508
2023-01-24 07:22:00.810262: step: 1588/530, loss: 0.004183044657111168
2023-01-24 07:22:01.933113: step: 1592/530, loss: 0.02441703900694847
2023-01-24 07:22:03.005897: step: 1596/530, loss: 0.005866901483386755
2023-01-24 07:22:04.102453: step: 1600/530, loss: 0.006879615597426891
2023-01-24 07:22:05.182289: step: 1604/530, loss: 0.011241494677960873
2023-01-24 07:22:06.283895: step: 1608/530, loss: 0.006326948292553425
2023-01-24 07:22:07.390678: step: 1612/530, loss: 0.08572746813297272
2023-01-24 07:22:08.485361: step: 1616/530, loss: 0.04401139169931412
2023-01-24 07:22:09.562349: step: 1620/530, loss: 0.010090016759932041
2023-01-24 07:22:10.635769: step: 1624/530, loss: 0.027341250330209732
2023-01-24 07:22:11.714530: step: 1628/530, loss: 0.05105701833963394
2023-01-24 07:22:12.780490: step: 1632/530, loss: 0.0067165750078856945
2023-01-24 07:22:13.888672: step: 1636/530, loss: 0.008871729485690594
2023-01-24 07:22:14.988083: step: 1640/530, loss: 0.010072163306176662
2023-01-24 07:22:16.071965: step: 1644/530, loss: 0.017721718177199364
2023-01-24 07:22:17.188182: step: 1648/530, loss: 0.014519420452415943
2023-01-24 07:22:18.260379: step: 1652/530, loss: 0.003179592080414295
2023-01-24 07:22:19.347438: step: 1656/530, loss: 0.0170866921544075
2023-01-24 07:22:20.421402: step: 1660/530, loss: 0.004248795565217733
2023-01-24 07:22:21.518164: step: 1664/530, loss: 0.041401106864213943
2023-01-24 07:22:22.642178: step: 1668/530, loss: 0.010224878787994385
2023-01-24 07:22:23.726510: step: 1672/530, loss: 0.005794689524918795
2023-01-24 07:22:24.803202: step: 1676/530, loss: 0.004830840975046158
2023-01-24 07:22:25.878535: step: 1680/530, loss: 0.046073660254478455
2023-01-24 07:22:26.947447: step: 1684/530, loss: 0.02316979132592678
2023-01-24 07:22:28.037032: step: 1688/530, loss: 0.011960898526012897
2023-01-24 07:22:29.127979: step: 1692/530, loss: 0.005457218736410141
2023-01-24 07:22:30.228429: step: 1696/530, loss: 0.023861417546868324
2023-01-24 07:22:31.306244: step: 1700/530, loss: 0.007934191264212132
2023-01-24 07:22:32.402752: step: 1704/530, loss: 0.0192751195281744
2023-01-24 07:22:33.493586: step: 1708/530, loss: 0.009477551095187664
2023-01-24 07:22:34.575311: step: 1712/530, loss: 0.011693878099322319
2023-01-24 07:22:35.680460: step: 1716/530, loss: 0.012986032292246819
2023-01-24 07:22:36.758006: step: 1720/530, loss: 0.04070911556482315
2023-01-24 07:22:37.837445: step: 1724/530, loss: 0.04441099613904953
2023-01-24 07:22:38.931421: step: 1728/530, loss: 0.03590861335396767
2023-01-24 07:22:40.031788: step: 1732/530, loss: 0.007922603748738766
2023-01-24 07:22:41.115215: step: 1736/530, loss: 0.015488187782466412
2023-01-24 07:22:42.191279: step: 1740/530, loss: 0.05255468189716339
2023-01-24 07:22:43.286560: step: 1744/530, loss: 0.05340617895126343
2023-01-24 07:22:44.366606: step: 1748/530, loss: 0.016160784289240837
2023-01-24 07:22:45.453623: step: 1752/530, loss: 0.011097296141088009
2023-01-24 07:22:46.529634: step: 1756/530, loss: 0.04077597334980965
2023-01-24 07:22:47.618959: step: 1760/530, loss: 0.02521529048681259
2023-01-24 07:22:48.713396: step: 1764/530, loss: 0.016891025006771088
2023-01-24 07:22:49.791403: step: 1768/530, loss: 0.021420054137706757
2023-01-24 07:22:50.871910: step: 1772/530, loss: 0.014504202641546726
2023-01-24 07:22:51.967826: step: 1776/530, loss: 0.013056584633886814
2023-01-24 07:22:53.058117: step: 1780/530, loss: 0.008672324940562248
2023-01-24 07:22:54.168522: step: 1784/530, loss: 0.05655907839536667
2023-01-24 07:22:55.250145: step: 1788/530, loss: 0.011442478746175766
2023-01-24 07:22:56.312673: step: 1792/530, loss: 0.023429814726114273
2023-01-24 07:22:57.393678: step: 1796/530, loss: 0.006677787285298109
2023-01-24 07:22:58.479006: step: 1800/530, loss: 0.02389880083501339
2023-01-24 07:22:59.553216: step: 1804/530, loss: 0.014673844911158085
2023-01-24 07:23:00.641989: step: 1808/530, loss: 0.011427624151110649
2023-01-24 07:23:01.723398: step: 1812/530, loss: 0.017208192497491837
2023-01-24 07:23:02.817824: step: 1816/530, loss: 0.009373791515827179
2023-01-24 07:23:03.889204: step: 1820/530, loss: 0.010688582435250282
2023-01-24 07:23:04.971632: step: 1824/530, loss: 0.011597719043493271
2023-01-24 07:23:06.052993: step: 1828/530, loss: 0.011483196169137955
2023-01-24 07:23:07.132691: step: 1832/530, loss: 0.0057946061715483665
2023-01-24 07:23:08.213957: step: 1836/530, loss: 0.016938593238592148
2023-01-24 07:23:09.297615: step: 1840/530, loss: 0.021978773176670074
2023-01-24 07:23:10.362610: step: 1844/530, loss: 0.011688240803778172
2023-01-24 07:23:11.464328: step: 1848/530, loss: 0.020980799570679665
2023-01-24 07:23:12.541468: step: 1852/530, loss: 0.005678862798959017
2023-01-24 07:23:13.614302: step: 1856/530, loss: 0.007353747729212046
2023-01-24 07:23:14.715666: step: 1860/530, loss: 0.016599297523498535
2023-01-24 07:23:15.787178: step: 1864/530, loss: 0.011584038846194744
2023-01-24 07:23:16.891467: step: 1868/530, loss: 0.011547436937689781
2023-01-24 07:23:17.968383: step: 1872/530, loss: 0.011611199006438255
2023-01-24 07:23:19.051800: step: 1876/530, loss: 0.005899867508560419
2023-01-24 07:23:20.132898: step: 1880/530, loss: 0.020347844809293747
2023-01-24 07:23:21.231332: step: 1884/530, loss: 0.041970983147621155
2023-01-24 07:23:22.322225: step: 1888/530, loss: 0.023819850757718086
2023-01-24 07:23:23.410979: step: 1892/530, loss: 0.021984515711665154
2023-01-24 07:23:24.520179: step: 1896/530, loss: 0.006055832374840975
2023-01-24 07:23:25.638709: step: 1900/530, loss: 0.002389435190707445
2023-01-24 07:23:26.721602: step: 1904/530, loss: 0.02583673968911171
2023-01-24 07:23:27.795601: step: 1908/530, loss: 0.013413617387413979
2023-01-24 07:23:28.881845: step: 1912/530, loss: 0.005588800646364689
2023-01-24 07:23:29.952074: step: 1916/530, loss: 0.015275241807103157
2023-01-24 07:23:31.022725: step: 1920/530, loss: 0.007640031632035971
2023-01-24 07:23:32.141604: step: 1924/530, loss: 0.008493843488395214
2023-01-24 07:23:33.231036: step: 1928/530, loss: 0.014558842405676842
2023-01-24 07:23:34.329635: step: 1932/530, loss: 0.015088051557540894
2023-01-24 07:23:35.407007: step: 1936/530, loss: 0.01971045881509781
2023-01-24 07:23:36.490850: step: 1940/530, loss: 0.007974453270435333
2023-01-24 07:23:37.589055: step: 1944/530, loss: 0.031929511576890945
2023-01-24 07:23:38.698038: step: 1948/530, loss: 0.03817980736494064
2023-01-24 07:23:39.763942: step: 1952/530, loss: 0.014736795797944069
2023-01-24 07:23:40.868712: step: 1956/530, loss: 0.01946777105331421
2023-01-24 07:23:42.011662: step: 1960/530, loss: 0.04873862862586975
2023-01-24 07:23:43.126866: step: 1964/530, loss: 0.04807610437273979
2023-01-24 07:23:44.206329: step: 1968/530, loss: 0.005408183671534061
2023-01-24 07:23:45.280544: step: 1972/530, loss: 0.003873688168823719
2023-01-24 07:23:46.365305: step: 1976/530, loss: 0.007736499886959791
2023-01-24 07:23:47.462311: step: 1980/530, loss: 0.00979442335665226
2023-01-24 07:23:48.554246: step: 1984/530, loss: 0.005270025227218866
2023-01-24 07:23:49.638351: step: 1988/530, loss: 0.0016902843490242958
2023-01-24 07:23:50.731524: step: 1992/530, loss: 0.016470305621623993
2023-01-24 07:23:51.815104: step: 1996/530, loss: 0.016909243538975716
2023-01-24 07:23:52.922669: step: 2000/530, loss: 0.01853897050023079
2023-01-24 07:23:54.032729: step: 2004/530, loss: 0.042839545756578445
2023-01-24 07:23:55.133887: step: 2008/530, loss: 0.007836148142814636
2023-01-24 07:23:56.223298: step: 2012/530, loss: 0.04640832543373108
2023-01-24 07:23:57.342733: step: 2016/530, loss: 0.007148121017962694
2023-01-24 07:23:58.443682: step: 2020/530, loss: 0.04487069696187973
2023-01-24 07:23:59.545017: step: 2024/530, loss: 0.014467395842075348
2023-01-24 07:24:00.636811: step: 2028/530, loss: 0.01731143891811371
2023-01-24 07:24:01.718242: step: 2032/530, loss: 0.01316429115831852
2023-01-24 07:24:02.809166: step: 2036/530, loss: 0.04857649281620979
2023-01-24 07:24:03.899493: step: 2040/530, loss: 0.013822689652442932
2023-01-24 07:24:04.977638: step: 2044/530, loss: 0.05104544386267662
2023-01-24 07:24:06.063061: step: 2048/530, loss: 0.06270679086446762
2023-01-24 07:24:07.147295: step: 2052/530, loss: 0.010346686467528343
2023-01-24 07:24:08.268159: step: 2056/530, loss: 0.007750852964818478
2023-01-24 07:24:09.362156: step: 2060/530, loss: 0.008350764401257038
2023-01-24 07:24:10.451078: step: 2064/530, loss: 0.008360866457223892
2023-01-24 07:24:11.521418: step: 2068/530, loss: 0.04624565690755844
2023-01-24 07:24:12.600791: step: 2072/530, loss: 0.030611254274845123
2023-01-24 07:24:13.691870: step: 2076/530, loss: 0.02276519685983658
2023-01-24 07:24:14.755837: step: 2080/530, loss: 0.010013825260102749
2023-01-24 07:24:15.844842: step: 2084/530, loss: 0.03413398936390877
2023-01-24 07:24:16.919934: step: 2088/530, loss: 0.01107659749686718
2023-01-24 07:24:18.008804: step: 2092/530, loss: 0.008314614184200764
2023-01-24 07:24:19.090388: step: 2096/530, loss: 0.009954916313290596
2023-01-24 07:24:20.189297: step: 2100/530, loss: 0.04503287002444267
2023-01-24 07:24:21.278990: step: 2104/530, loss: 0.012182024307549
2023-01-24 07:24:22.353341: step: 2108/530, loss: 0.0066059851087629795
2023-01-24 07:24:23.421856: step: 2112/530, loss: 0.003165996866300702
2023-01-24 07:24:24.500625: step: 2116/530, loss: 0.02666446566581726
2023-01-24 07:24:25.602790: step: 2120/530, loss: 0.010328611359000206
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3435334598538886, 'r': 0.3448371921493493, 'f1': 0.34418409140664213}, 'combined': 0.2536093305101573, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3235237651064796, 'r': 0.2678981375091205, 'f1': 0.2930950434153837}, 'combined': 0.1820274480158699, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38162598689856403, 'r': 0.32876318415929423, 'f1': 0.3532277228378146}, 'combined': 0.2602730589331265, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.32121575042699824, 'r': 0.25874832413467974, 'f1': 0.286617881190192}, 'combined': 0.17800478937075082, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37179763683225536, 'r': 0.323118249846628, 'f1': 0.34575292927750856}, 'combined': 0.25476531630974314, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.32867544366786683, 'r': 0.26378394442445774, 'f1': 0.2926759427184838}, 'combined': 0.18176716442516364, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.37, 'r': 0.40217391304347827, 'f1': 0.38541666666666663}, 'combined': 0.19270833333333331, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, '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': 0.3435334598538886, 'r': 0.3448371921493493, 'f1': 0.34418409140664213}, 'combined': 0.2536093305101573, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3235237651064796, 'r': 0.2678981375091205, 'f1': 0.2930950434153837}, 'combined': 0.1820274480158699, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38162598689856403, 'r': 0.32876318415929423, 'f1': 0.3532277228378146}, 'combined': 0.2602730589331265, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.32121575042699824, 'r': 0.25874832413467974, 'f1': 0.286617881190192}, 'combined': 0.17800478937075082, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.37, 'r': 0.40217391304347827, 'f1': 0.38541666666666663}, 'combined': 0.19270833333333331, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37179763683225536, 'r': 0.323118249846628, 'f1': 0.34575292927750856}, 'combined': 0.25476531630974314, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.32867544366786683, 'r': 0.26378394442445774, 'f1': 0.2926759427184838}, 'combined': 0.18176716442516364, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, '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 07:27:18.465462: step: 4/530, loss: 0.005641673691570759
2023-01-24 07:27:19.543461: step: 8/530, loss: 0.02767476812005043
2023-01-24 07:27:20.610731: step: 12/530, loss: 0.006464339327067137
2023-01-24 07:27:21.709103: step: 16/530, loss: 0.006023034919053316
2023-01-24 07:27:22.770278: step: 20/530, loss: 0.002565554343163967
2023-01-24 07:27:23.839370: step: 24/530, loss: 0.007445499766618013
2023-01-24 07:27:24.904428: step: 28/530, loss: 0.03772822394967079
2023-01-24 07:27:25.980787: step: 32/530, loss: 0.012982611544430256
2023-01-24 07:27:27.067217: step: 36/530, loss: 0.009248163551092148
2023-01-24 07:27:28.149069: step: 40/530, loss: 0.013611535541713238
2023-01-24 07:27:29.215621: step: 44/530, loss: 0.0074456194415688515
2023-01-24 07:27:30.306835: step: 48/530, loss: 0.01183254737406969
2023-01-24 07:27:31.372625: step: 52/530, loss: 0.00836742203682661
2023-01-24 07:27:32.456484: step: 56/530, loss: 0.029643826186656952
2023-01-24 07:27:33.530710: step: 60/530, loss: 0.0018335202476009727
2023-01-24 07:27:34.622031: step: 64/530, loss: 0.009220931679010391
2023-01-24 07:27:35.700476: step: 68/530, loss: 0.0027676185127347708
2023-01-24 07:27:36.767518: step: 72/530, loss: 0.045051395893096924
2023-01-24 07:27:37.843609: step: 76/530, loss: 0.024673137813806534
2023-01-24 07:27:38.924499: step: 80/530, loss: 0.015320098027586937
2023-01-24 07:27:40.010528: step: 84/530, loss: 0.012221215292811394
2023-01-24 07:27:41.078462: step: 88/530, loss: 0.031142128631472588
2023-01-24 07:27:42.160933: step: 92/530, loss: 0.012339354492723942
2023-01-24 07:27:43.241776: step: 96/530, loss: 0.03250077739357948
2023-01-24 07:27:44.331279: step: 100/530, loss: 0.013919645920395851
2023-01-24 07:27:45.421142: step: 104/530, loss: 0.011967160739004612
2023-01-24 07:27:46.506110: step: 108/530, loss: 0.009652109816670418
2023-01-24 07:27:47.591682: step: 112/530, loss: 0.008104892447590828
2023-01-24 07:27:48.682827: step: 116/530, loss: 0.023436369374394417
2023-01-24 07:27:49.780325: step: 120/530, loss: 0.007483702152967453
2023-01-24 07:27:50.879746: step: 124/530, loss: 0.011638524010777473
2023-01-24 07:27:51.971840: step: 128/530, loss: 0.011519819498062134
2023-01-24 07:27:53.055712: step: 132/530, loss: 0.02385181561112404
2023-01-24 07:27:54.140709: step: 136/530, loss: 0.018908152356743813
2023-01-24 07:27:55.252295: step: 140/530, loss: 0.010773095302283764
2023-01-24 07:27:56.334916: step: 144/530, loss: 0.013346029445528984
2023-01-24 07:27:57.399012: step: 148/530, loss: 0.004396419040858746
2023-01-24 07:27:58.486639: step: 152/530, loss: 0.024951230734586716
2023-01-24 07:27:59.579521: step: 156/530, loss: 0.039059292525053024
2023-01-24 07:28:00.658134: step: 160/530, loss: 0.00906367413699627
2023-01-24 07:28:01.747150: step: 164/530, loss: 0.006897334475070238
2023-01-24 07:28:02.850791: step: 168/530, loss: 0.04623740538954735
2023-01-24 07:28:03.931277: step: 172/530, loss: 0.01330616045743227
2023-01-24 07:28:04.991386: step: 176/530, loss: 0.020469974726438522
2023-01-24 07:28:06.058890: step: 180/530, loss: 0.016315195709466934
2023-01-24 07:28:07.144983: step: 184/530, loss: 0.009510687552392483
2023-01-24 07:28:08.253203: step: 188/530, loss: 0.030139977112412453
2023-01-24 07:28:09.324490: step: 192/530, loss: 0.03469419106841087
2023-01-24 07:28:10.408334: step: 196/530, loss: 0.011470895260572433
2023-01-24 07:28:11.482131: step: 200/530, loss: 0.004861598368734121
2023-01-24 07:28:12.571158: step: 204/530, loss: 0.02003544010221958
2023-01-24 07:28:13.669368: step: 208/530, loss: 0.013560621067881584
2023-01-24 07:28:14.791432: step: 212/530, loss: 0.021602347493171692
2023-01-24 07:28:15.884385: step: 216/530, loss: 0.03374919667840004
2023-01-24 07:28:16.966235: step: 220/530, loss: 0.033289119601249695
2023-01-24 07:28:18.030701: step: 224/530, loss: 0.04721187427639961
2023-01-24 07:28:19.140963: step: 228/530, loss: 0.013874021358788013
2023-01-24 07:28:20.223046: step: 232/530, loss: 0.010972077958285809
2023-01-24 07:28:21.291563: step: 236/530, loss: 0.010974066331982613
2023-01-24 07:28:22.370130: step: 240/530, loss: 0.021125182509422302
2023-01-24 07:28:23.459234: step: 244/530, loss: 0.008498281240463257
2023-01-24 07:28:24.527621: step: 248/530, loss: 0.00769105413928628
2023-01-24 07:28:25.607989: step: 252/530, loss: 0.012197794392704964
2023-01-24 07:28:26.676267: step: 256/530, loss: 0.011553655378520489
2023-01-24 07:28:27.752864: step: 260/530, loss: 0.012967188842594624
2023-01-24 07:28:28.822245: step: 264/530, loss: 0.009487172588706017
2023-01-24 07:28:29.900006: step: 268/530, loss: 0.003814895171672106
2023-01-24 07:28:30.975736: step: 272/530, loss: 0.0024984669871628284
2023-01-24 07:28:32.050144: step: 276/530, loss: 0.010408744215965271
2023-01-24 07:28:33.126226: step: 280/530, loss: 0.006640077568590641
2023-01-24 07:28:34.218355: step: 284/530, loss: 0.0037364831659942865
2023-01-24 07:28:35.308476: step: 288/530, loss: 0.02296803705394268
2023-01-24 07:28:36.373961: step: 292/530, loss: 0.005384999327361584
2023-01-24 07:28:37.452160: step: 296/530, loss: 0.004077731631696224
2023-01-24 07:28:38.514757: step: 300/530, loss: 0.006421379745006561
2023-01-24 07:28:39.581179: step: 304/530, loss: 0.006202185992151499
2023-01-24 07:28:40.666887: step: 308/530, loss: 0.026412248611450195
2023-01-24 07:28:41.812610: step: 312/530, loss: 0.060694605112075806
2023-01-24 07:28:42.899643: step: 316/530, loss: 0.020239736884832382
2023-01-24 07:28:43.989134: step: 320/530, loss: 0.005850775167346001
2023-01-24 07:28:45.083998: step: 324/530, loss: 0.005612388718873262
2023-01-24 07:28:46.169715: step: 328/530, loss: 0.040948543697595596
2023-01-24 07:28:47.267499: step: 332/530, loss: 0.006373019888997078
2023-01-24 07:28:48.329871: step: 336/530, loss: 0.02074727974832058
2023-01-24 07:28:49.404478: step: 340/530, loss: 0.01446513645350933
2023-01-24 07:28:50.514922: step: 344/530, loss: 0.03704356774687767
2023-01-24 07:28:51.616311: step: 348/530, loss: 0.016241004690527916
2023-01-24 07:28:52.688008: step: 352/530, loss: 0.014843384735286236
2023-01-24 07:28:53.780017: step: 356/530, loss: 0.005968667101114988
2023-01-24 07:28:54.856068: step: 360/530, loss: 0.021548090502619743
2023-01-24 07:28:55.949110: step: 364/530, loss: 0.010564169846475124
2023-01-24 07:28:57.035536: step: 368/530, loss: 0.008715122006833553
2023-01-24 07:28:58.118823: step: 372/530, loss: 0.044845305383205414
2023-01-24 07:28:59.210408: step: 376/530, loss: 0.005612906068563461
2023-01-24 07:29:00.305044: step: 380/530, loss: 0.015625333413481712
2023-01-24 07:29:01.391593: step: 384/530, loss: 0.003909599035978317
2023-01-24 07:29:02.467003: step: 388/530, loss: 0.007939442060887814
2023-01-24 07:29:03.546185: step: 392/530, loss: 0.012792473658919334
2023-01-24 07:29:04.645428: step: 396/530, loss: 0.004712843336164951
2023-01-24 07:29:05.716831: step: 400/530, loss: 0.046316131949424744
2023-01-24 07:29:06.821576: step: 404/530, loss: 0.019022682681679726
2023-01-24 07:29:07.898140: step: 408/530, loss: 0.06996455043554306
2023-01-24 07:29:08.989060: step: 412/530, loss: 0.00816689059138298
2023-01-24 07:29:10.079268: step: 416/530, loss: 0.003402122063562274
2023-01-24 07:29:11.177184: step: 420/530, loss: 0.022883590310811996
2023-01-24 07:29:12.283155: step: 424/530, loss: 0.006130310241132975
2023-01-24 07:29:13.382250: step: 428/530, loss: 0.020629115402698517
2023-01-24 07:29:14.480442: step: 432/530, loss: 0.10651036351919174
2023-01-24 07:29:15.586814: step: 436/530, loss: 0.002941350219771266
2023-01-24 07:29:16.672228: step: 440/530, loss: 0.03869142010807991
2023-01-24 07:29:17.772082: step: 444/530, loss: 0.015508608892560005
2023-01-24 07:29:18.864960: step: 448/530, loss: 0.013619472272694111
2023-01-24 07:29:19.972241: step: 452/530, loss: 0.006740827113389969
2023-01-24 07:29:21.031407: step: 456/530, loss: 0.00532924197614193
2023-01-24 07:29:22.127746: step: 460/530, loss: 0.024177664890885353
2023-01-24 07:29:23.190010: step: 464/530, loss: 0.001887515769340098
2023-01-24 07:29:24.249673: step: 468/530, loss: 0.015710581094026566
2023-01-24 07:29:25.325393: step: 472/530, loss: 0.005297767464071512
2023-01-24 07:29:26.403507: step: 476/530, loss: 0.024334866553544998
2023-01-24 07:29:27.493232: step: 480/530, loss: 0.004942451138049364
2023-01-24 07:29:28.584013: step: 484/530, loss: 0.026859039440751076
2023-01-24 07:29:29.661029: step: 488/530, loss: 0.005093375686556101
2023-01-24 07:29:30.734103: step: 492/530, loss: 0.03999800980091095
2023-01-24 07:29:31.794856: step: 496/530, loss: 0.00826770719140768
2023-01-24 07:29:32.894344: step: 500/530, loss: 0.005403068382292986
2023-01-24 07:29:33.979148: step: 504/530, loss: 0.04293103888630867
2023-01-24 07:29:35.047968: step: 508/530, loss: 0.010611155070364475
2023-01-24 07:29:36.139868: step: 512/530, loss: 0.020945990458130836
2023-01-24 07:29:37.247644: step: 516/530, loss: 0.01142231747508049
2023-01-24 07:29:38.341600: step: 520/530, loss: 0.01530852634459734
2023-01-24 07:29:39.426521: step: 524/530, loss: 0.01927567832171917
2023-01-24 07:29:40.500936: step: 528/530, loss: 0.01029086671769619
2023-01-24 07:29:41.595015: step: 532/530, loss: 0.05991935729980469
2023-01-24 07:29:42.664053: step: 536/530, loss: 0.00935330055654049
2023-01-24 07:29:43.754781: step: 540/530, loss: 0.012328356504440308
2023-01-24 07:29:44.831401: step: 544/530, loss: 0.008024824783205986
2023-01-24 07:29:45.895764: step: 548/530, loss: 0.007618793286383152
2023-01-24 07:29:46.972396: step: 552/530, loss: 0.0005801370134577155
2023-01-24 07:29:48.061904: step: 556/530, loss: 0.020705144852399826
2023-01-24 07:29:49.133372: step: 560/530, loss: 0.05678887292742729
2023-01-24 07:29:50.226187: step: 564/530, loss: 0.004876886494457722
2023-01-24 07:29:51.319364: step: 568/530, loss: 0.03397480398416519
2023-01-24 07:29:52.422365: step: 572/530, loss: 0.01163378357887268
2023-01-24 07:29:53.480708: step: 576/530, loss: 0.02361510507762432
2023-01-24 07:29:54.592491: step: 580/530, loss: 0.030911602079868317
2023-01-24 07:29:55.691816: step: 584/530, loss: 0.000158442446263507
2023-01-24 07:29:56.770371: step: 588/530, loss: 0.005778936203569174
2023-01-24 07:29:57.861712: step: 592/530, loss: 0.004600215703248978
2023-01-24 07:29:58.918124: step: 596/530, loss: 0.004718068987131119
2023-01-24 07:29:59.996475: step: 600/530, loss: 0.004555044695734978
2023-01-24 07:30:01.086959: step: 604/530, loss: 0.013402585871517658
2023-01-24 07:30:02.175177: step: 608/530, loss: 0.009843009524047375
2023-01-24 07:30:03.246694: step: 612/530, loss: 0.00898763444274664
2023-01-24 07:30:04.338313: step: 616/530, loss: 0.008238019421696663
2023-01-24 07:30:05.431610: step: 620/530, loss: 0.03368796408176422
2023-01-24 07:30:06.510283: step: 624/530, loss: 0.008473996073007584
2023-01-24 07:30:07.563864: step: 628/530, loss: 0.007081137038767338
2023-01-24 07:30:08.659958: step: 632/530, loss: 0.011353718116879463
2023-01-24 07:30:09.734776: step: 636/530, loss: 0.030242454260587692
2023-01-24 07:30:10.832674: step: 640/530, loss: 0.008260573260486126
2023-01-24 07:30:11.912213: step: 644/530, loss: 0.015393915586173534
2023-01-24 07:30:13.007292: step: 648/530, loss: 0.0032675284892320633
2023-01-24 07:30:14.086869: step: 652/530, loss: 0.012374993413686752
2023-01-24 07:30:15.172902: step: 656/530, loss: 0.00668248301371932
2023-01-24 07:30:16.266602: step: 660/530, loss: 0.0027193506248295307
2023-01-24 07:30:17.331378: step: 664/530, loss: 0.007382545154541731
2023-01-24 07:30:18.391186: step: 668/530, loss: 0.0024907432962208986
2023-01-24 07:30:19.479467: step: 672/530, loss: 0.00687566539272666
2023-01-24 07:30:20.560836: step: 676/530, loss: 0.012593916617333889
2023-01-24 07:30:21.636152: step: 680/530, loss: 0.023399043828248978
2023-01-24 07:30:22.724175: step: 684/530, loss: 0.009080097079277039
2023-01-24 07:30:23.811348: step: 688/530, loss: 0.006220946088433266
2023-01-24 07:30:24.917102: step: 692/530, loss: 0.09992773830890656
2023-01-24 07:30:26.004698: step: 696/530, loss: 0.005490303970873356
2023-01-24 07:30:27.087969: step: 700/530, loss: 0.02275363728404045
2023-01-24 07:30:28.185343: step: 704/530, loss: 0.00788944959640503
2023-01-24 07:30:29.290836: step: 708/530, loss: 0.08822882920503616
2023-01-24 07:30:30.389467: step: 712/530, loss: 0.05410638451576233
2023-01-24 07:30:31.460608: step: 716/530, loss: 0.00497577665373683
2023-01-24 07:30:32.531853: step: 720/530, loss: 0.04873286560177803
2023-01-24 07:30:33.620338: step: 724/530, loss: 0.004274641629308462
2023-01-24 07:30:34.698494: step: 728/530, loss: 0.005349225830286741
2023-01-24 07:30:35.785811: step: 732/530, loss: 0.009203272871673107
2023-01-24 07:30:36.846026: step: 736/530, loss: 0.011367706581950188
2023-01-24 07:30:37.927600: step: 740/530, loss: 0.03039545565843582
2023-01-24 07:30:39.025743: step: 744/530, loss: 0.0032586485613137484
2023-01-24 07:30:40.121320: step: 748/530, loss: 0.02519851364195347
2023-01-24 07:30:41.213847: step: 752/530, loss: 0.014162487350404263
2023-01-24 07:30:42.313762: step: 756/530, loss: 0.0062086861580610275
2023-01-24 07:30:43.382887: step: 760/530, loss: 0.007211018819361925
2023-01-24 07:30:44.463383: step: 764/530, loss: 0.0024865069426596165
2023-01-24 07:30:45.537097: step: 768/530, loss: 0.0297025665640831
2023-01-24 07:30:46.602825: step: 772/530, loss: 0.009920384734869003
2023-01-24 07:30:47.686363: step: 776/530, loss: 0.011691642925143242
2023-01-24 07:30:48.778169: step: 780/530, loss: 0.004452267196029425
2023-01-24 07:30:49.879212: step: 784/530, loss: 0.027387509122490883
2023-01-24 07:30:50.967870: step: 788/530, loss: 0.010054368525743484
2023-01-24 07:30:52.051926: step: 792/530, loss: 0.005780488718301058
2023-01-24 07:30:53.139720: step: 796/530, loss: 0.009561055339872837
2023-01-24 07:30:54.241655: step: 800/530, loss: 0.0407571941614151
2023-01-24 07:30:55.326686: step: 804/530, loss: 0.012976707890629768
2023-01-24 07:30:56.409673: step: 808/530, loss: 0.041171710938215256
2023-01-24 07:30:57.513696: step: 812/530, loss: 0.006434359587728977
2023-01-24 07:30:58.614802: step: 816/530, loss: 0.019613947719335556
2023-01-24 07:30:59.701715: step: 820/530, loss: 0.01882244274020195
2023-01-24 07:31:00.826652: step: 824/530, loss: 0.04118381068110466
2023-01-24 07:31:01.901618: step: 828/530, loss: 0.04458343982696533
2023-01-24 07:31:02.975698: step: 832/530, loss: 0.009364611469209194
2023-01-24 07:31:04.075535: step: 836/530, loss: 0.003201334970071912
2023-01-24 07:31:05.183759: step: 840/530, loss: 0.012826669961214066
2023-01-24 07:31:06.254357: step: 844/530, loss: 0.007696354761719704
2023-01-24 07:31:07.330379: step: 848/530, loss: 0.013038534671068192
2023-01-24 07:31:08.425241: step: 852/530, loss: 0.0034489654935896397
2023-01-24 07:31:09.511440: step: 856/530, loss: 0.019957341253757477
2023-01-24 07:31:10.602331: step: 860/530, loss: 0.04034833982586861
2023-01-24 07:31:11.687149: step: 864/530, loss: 0.005544763058423996
2023-01-24 07:31:12.824972: step: 868/530, loss: 0.011408579535782337
2023-01-24 07:31:13.895503: step: 872/530, loss: 0.0009432925726287067
2023-01-24 07:31:14.979901: step: 876/530, loss: 0.02067532017827034
2023-01-24 07:31:16.044681: step: 880/530, loss: 0.03105892613530159
2023-01-24 07:31:17.121402: step: 884/530, loss: 0.0001108178767026402
2023-01-24 07:31:18.237749: step: 888/530, loss: 0.0308159701526165
2023-01-24 07:31:19.319821: step: 892/530, loss: 0.010535906068980694
2023-01-24 07:31:20.403451: step: 896/530, loss: 0.03460075333714485
2023-01-24 07:31:21.484253: step: 900/530, loss: 0.004548558034002781
2023-01-24 07:31:22.559032: step: 904/530, loss: 0.003941976930946112
2023-01-24 07:31:23.652868: step: 908/530, loss: 0.04560186341404915
2023-01-24 07:31:24.766448: step: 912/530, loss: 0.053826577961444855
2023-01-24 07:31:25.868067: step: 916/530, loss: 0.020927051082253456
2023-01-24 07:31:26.917387: step: 920/530, loss: 0.008506862446665764
2023-01-24 07:31:28.025359: step: 924/530, loss: 0.0068391673266887665
2023-01-24 07:31:29.121834: step: 928/530, loss: 0.006463491357862949
2023-01-24 07:31:30.185859: step: 932/530, loss: 0.020972708240151405
2023-01-24 07:31:31.262534: step: 936/530, loss: 0.0030379327945411205
2023-01-24 07:31:32.335227: step: 940/530, loss: 0.01844375766813755
2023-01-24 07:31:33.402327: step: 944/530, loss: 0.00045030046021565795
2023-01-24 07:31:34.494836: step: 948/530, loss: 0.013975881040096283
2023-01-24 07:31:35.565541: step: 952/530, loss: 0.015563739463686943
2023-01-24 07:31:36.643778: step: 956/530, loss: 0.0052184234373271465
2023-01-24 07:31:37.719138: step: 960/530, loss: 0.04436177387833595
2023-01-24 07:31:38.813960: step: 964/530, loss: 0.005312021821737289
2023-01-24 07:31:39.883703: step: 968/530, loss: 0.0015295686898753047
2023-01-24 07:31:40.983410: step: 972/530, loss: 0.010709281079471111
2023-01-24 07:31:42.036827: step: 976/530, loss: 0.00014532609202433378
2023-01-24 07:31:43.127831: step: 980/530, loss: 0.01103973388671875
2023-01-24 07:31:44.213921: step: 984/530, loss: 0.0076539963483810425
2023-01-24 07:31:45.287364: step: 988/530, loss: 0.004451177082955837
2023-01-24 07:31:46.404993: step: 992/530, loss: 0.035717714577913284
2023-01-24 07:31:47.481259: step: 996/530, loss: 0.05799010768532753
2023-01-24 07:31:48.559292: step: 1000/530, loss: 0.010364919900894165
2023-01-24 07:31:49.645955: step: 1004/530, loss: 0.004060240462422371
2023-01-24 07:31:50.723221: step: 1008/530, loss: 0.035794422030448914
2023-01-24 07:31:51.806064: step: 1012/530, loss: 0.005741428583860397
2023-01-24 07:31:52.914720: step: 1016/530, loss: 0.005371949169784784
2023-01-24 07:31:54.004362: step: 1020/530, loss: 0.008296807296574116
2023-01-24 07:31:55.082274: step: 1024/530, loss: 0.0060907816514372826
2023-01-24 07:31:56.172726: step: 1028/530, loss: 0.003747503738850355
2023-01-24 07:31:57.250770: step: 1032/530, loss: 0.032581131905317307
2023-01-24 07:31:58.352249: step: 1036/530, loss: 0.006987593602389097
2023-01-24 07:31:59.410636: step: 1040/530, loss: 0.02342052012681961
2023-01-24 07:32:00.466966: step: 1044/530, loss: 0.0023827464319765568
2023-01-24 07:32:01.585044: step: 1048/530, loss: 0.04525222256779671
2023-01-24 07:32:02.673552: step: 1052/530, loss: 0.007199571933597326
2023-01-24 07:32:03.766078: step: 1056/530, loss: 0.01801137812435627
2023-01-24 07:32:04.861074: step: 1060/530, loss: 0.03630020469427109
2023-01-24 07:32:05.935354: step: 1064/530, loss: 0.0016164183616638184
2023-01-24 07:32:07.026679: step: 1068/530, loss: 0.0035438472405076027
2023-01-24 07:32:08.099851: step: 1072/530, loss: 0.010327319614589214
2023-01-24 07:32:09.189093: step: 1076/530, loss: 0.006465037353336811
2023-01-24 07:32:10.284824: step: 1080/530, loss: 0.0003414069360587746
2023-01-24 07:32:11.370546: step: 1084/530, loss: 0.006829671561717987
2023-01-24 07:32:12.443311: step: 1088/530, loss: 0.04112397879362106
2023-01-24 07:32:13.510470: step: 1092/530, loss: 0.007807550020515919
2023-01-24 07:32:14.595663: step: 1096/530, loss: 0.022542793303728104
2023-01-24 07:32:15.660107: step: 1100/530, loss: 0.006746973842382431
2023-01-24 07:32:16.758786: step: 1104/530, loss: 0.00983869656920433
2023-01-24 07:32:17.829221: step: 1108/530, loss: 0.049351684749126434
2023-01-24 07:32:18.912977: step: 1112/530, loss: 0.023587143048644066
2023-01-24 07:32:20.009935: step: 1116/530, loss: 0.00761682353913784
2023-01-24 07:32:21.089694: step: 1120/530, loss: 0.004863751120865345
2023-01-24 07:32:22.201856: step: 1124/530, loss: 0.007675236091017723
2023-01-24 07:32:23.273620: step: 1128/530, loss: 0.007254406344145536
2023-01-24 07:32:24.366401: step: 1132/530, loss: 0.032132767140865326
2023-01-24 07:32:25.434974: step: 1136/530, loss: 0.0
2023-01-24 07:32:26.500155: step: 1140/530, loss: 0.013009486719965935
2023-01-24 07:32:27.575629: step: 1144/530, loss: 0.009483582340180874
2023-01-24 07:32:28.676461: step: 1148/530, loss: 0.008291544392704964
2023-01-24 07:32:29.757286: step: 1152/530, loss: 0.07039010524749756
2023-01-24 07:32:30.844412: step: 1156/530, loss: 0.006580561399459839
2023-01-24 07:32:31.936877: step: 1160/530, loss: 0.011134467087686062
2023-01-24 07:32:33.016308: step: 1164/530, loss: 0.005670149344950914
2023-01-24 07:32:34.097921: step: 1168/530, loss: 0.007107221055775881
2023-01-24 07:32:35.187193: step: 1172/530, loss: 0.008636192418634892
2023-01-24 07:32:36.268114: step: 1176/530, loss: 0.007439135108143091
2023-01-24 07:32:37.354446: step: 1180/530, loss: 0.014782206155359745
2023-01-24 07:32:38.449335: step: 1184/530, loss: 0.010683221742510796
2023-01-24 07:32:39.548873: step: 1188/530, loss: 0.006635103840380907
2023-01-24 07:32:40.626486: step: 1192/530, loss: 0.006144394166767597
2023-01-24 07:32:41.721034: step: 1196/530, loss: 0.0116724893450737
2023-01-24 07:32:42.812822: step: 1200/530, loss: 0.008740604855120182
2023-01-24 07:32:43.892413: step: 1204/530, loss: 0.003188355825841427
2023-01-24 07:32:44.980790: step: 1208/530, loss: 0.026846351101994514
2023-01-24 07:32:46.053268: step: 1212/530, loss: 0.009961804375052452
2023-01-24 07:32:47.129604: step: 1216/530, loss: 0.012602888979017735
2023-01-24 07:32:48.200814: step: 1220/530, loss: 0.00370414718054235
2023-01-24 07:32:49.272009: step: 1224/530, loss: 0.0043518319725990295
2023-01-24 07:32:50.373813: step: 1228/530, loss: 0.003109956393018365
2023-01-24 07:32:51.488002: step: 1232/530, loss: 0.012438689358532429
2023-01-24 07:32:52.583077: step: 1236/530, loss: 0.02567046508193016
2023-01-24 07:32:53.657706: step: 1240/530, loss: 0.004578316118568182
2023-01-24 07:32:54.748729: step: 1244/530, loss: 0.00847189873456955
2023-01-24 07:32:55.823927: step: 1248/530, loss: 0.012865513563156128
2023-01-24 07:32:56.910394: step: 1252/530, loss: 0.005565828178077936
2023-01-24 07:32:58.010998: step: 1256/530, loss: 0.08082952350378036
2023-01-24 07:32:59.067403: step: 1260/530, loss: 0.007097425404936075
2023-01-24 07:33:00.156972: step: 1264/530, loss: 0.053296253085136414
2023-01-24 07:33:01.264599: step: 1268/530, loss: 0.05518532544374466
2023-01-24 07:33:02.348437: step: 1272/530, loss: 0.0029264793265610933
2023-01-24 07:33:03.405173: step: 1276/530, loss: 0.0028281453996896744
2023-01-24 07:33:04.519905: step: 1280/530, loss: 0.06469020992517471
2023-01-24 07:33:05.587906: step: 1284/530, loss: 0.002533006016165018
2023-01-24 07:33:06.651220: step: 1288/530, loss: 0.02022383362054825
2023-01-24 07:33:07.715232: step: 1292/530, loss: 0.012499403208494186
2023-01-24 07:33:08.808626: step: 1296/530, loss: 0.00623535830527544
2023-01-24 07:33:09.897479: step: 1300/530, loss: 0.0021335294004529715
2023-01-24 07:33:10.995396: step: 1304/530, loss: 0.04678473621606827
2023-01-24 07:33:12.087977: step: 1308/530, loss: 0.023786287754774094
2023-01-24 07:33:13.168164: step: 1312/530, loss: 0.01839214190840721
2023-01-24 07:33:14.263512: step: 1316/530, loss: 0.00917195063084364
2023-01-24 07:33:15.350634: step: 1320/530, loss: 0.011823109351098537
2023-01-24 07:33:16.463967: step: 1324/530, loss: 0.007667298428714275
2023-01-24 07:33:17.541329: step: 1328/530, loss: 0.06011826545000076
2023-01-24 07:33:18.639372: step: 1332/530, loss: 0.04796822369098663
2023-01-24 07:33:19.717319: step: 1336/530, loss: 0.006836344953626394
2023-01-24 07:33:20.808666: step: 1340/530, loss: 0.00395851070061326
2023-01-24 07:33:21.867317: step: 1344/530, loss: 0.006227710284292698
2023-01-24 07:33:22.946632: step: 1348/530, loss: 0.02330593764781952
2023-01-24 07:33:24.028915: step: 1352/530, loss: 0.00745026022195816
2023-01-24 07:33:25.114944: step: 1356/530, loss: 0.004284335300326347
2023-01-24 07:33:26.183807: step: 1360/530, loss: 0.003827574197202921
2023-01-24 07:33:27.238970: step: 1364/530, loss: 0.0037481170147657394
2023-01-24 07:33:28.350530: step: 1368/530, loss: 0.012344997376203537
2023-01-24 07:33:29.433372: step: 1372/530, loss: 0.012376873753964901
2023-01-24 07:33:30.516447: step: 1376/530, loss: 0.004207395017147064
2023-01-24 07:33:31.603079: step: 1380/530, loss: 0.004015093669295311
2023-01-24 07:33:32.678273: step: 1384/530, loss: 0.00776244979351759
2023-01-24 07:33:33.750259: step: 1388/530, loss: 0.006806132383644581
2023-01-24 07:33:34.850612: step: 1392/530, loss: 0.012347176671028137
2023-01-24 07:33:35.945290: step: 1396/530, loss: 0.04131225496530533
2023-01-24 07:33:37.026994: step: 1400/530, loss: 0.005150005221366882
2023-01-24 07:33:38.107344: step: 1404/530, loss: 0.026020819321274757
2023-01-24 07:33:39.175114: step: 1408/530, loss: 0.009125958196818829
2023-01-24 07:33:40.282079: step: 1412/530, loss: 0.010478360578417778
2023-01-24 07:33:41.368269: step: 1416/530, loss: 0.012633388862013817
2023-01-24 07:33:42.463684: step: 1420/530, loss: 0.011061619967222214
2023-01-24 07:33:43.550556: step: 1424/530, loss: 0.005792701151221991
2023-01-24 07:33:44.640800: step: 1428/530, loss: 0.011377145536243916
2023-01-24 07:33:45.740770: step: 1432/530, loss: 0.024892304092645645
2023-01-24 07:33:46.834450: step: 1436/530, loss: 0.006165762897580862
2023-01-24 07:33:47.941803: step: 1440/530, loss: 0.03086588717997074
2023-01-24 07:33:49.024653: step: 1444/530, loss: 0.010979481041431427
2023-01-24 07:33:50.121643: step: 1448/530, loss: 0.02529328502714634
2023-01-24 07:33:51.176931: step: 1452/530, loss: 0.006963388528674841
2023-01-24 07:33:52.306074: step: 1456/530, loss: 0.051081933081150055
2023-01-24 07:33:53.398892: step: 1460/530, loss: 0.017252610996365547
2023-01-24 07:33:54.469361: step: 1464/530, loss: 0.00937830563634634
2023-01-24 07:33:55.548002: step: 1468/530, loss: 0.03347708657383919
2023-01-24 07:33:56.616877: step: 1472/530, loss: 0.0019538993947207928
2023-01-24 07:33:57.683992: step: 1476/530, loss: 0.0055658030323684216
2023-01-24 07:33:58.786386: step: 1480/530, loss: 0.016274578869342804
2023-01-24 07:33:59.889473: step: 1484/530, loss: 0.012164952233433723
2023-01-24 07:34:00.978459: step: 1488/530, loss: 0.0
2023-01-24 07:34:02.069399: step: 1492/530, loss: 0.04196206480264664
2023-01-24 07:34:03.167173: step: 1496/530, loss: 0.011771033518016338
2023-01-24 07:34:04.270421: step: 1500/530, loss: 0.011590060777962208
2023-01-24 07:34:05.339287: step: 1504/530, loss: 0.01295036356896162
2023-01-24 07:34:06.426929: step: 1508/530, loss: 0.034659143537282944
2023-01-24 07:34:07.494675: step: 1512/530, loss: 0.002883182605728507
2023-01-24 07:34:08.579839: step: 1516/530, loss: 0.0041257720440626144
2023-01-24 07:34:09.688506: step: 1520/530, loss: 0.026274969801306725
2023-01-24 07:34:10.757170: step: 1524/530, loss: 0.03965918719768524
2023-01-24 07:34:11.863684: step: 1528/530, loss: 0.009315415285527706
2023-01-24 07:34:12.936426: step: 1532/530, loss: 0.01658005639910698
2023-01-24 07:34:13.994068: step: 1536/530, loss: 0.005782548803836107
2023-01-24 07:34:15.071969: step: 1540/530, loss: 0.010098210535943508
2023-01-24 07:34:16.166785: step: 1544/530, loss: 0.044509027153253555
2023-01-24 07:34:17.218070: step: 1548/530, loss: 0.004450908862054348
2023-01-24 07:34:18.320846: step: 1552/530, loss: 0.0024891409557312727
2023-01-24 07:34:19.434826: step: 1556/530, loss: 0.006433618720620871
2023-01-24 07:34:20.518902: step: 1560/530, loss: 0.01959502324461937
2023-01-24 07:34:21.589068: step: 1564/530, loss: 0.005832815542817116
2023-01-24 07:34:22.699948: step: 1568/530, loss: 0.00603628670796752
2023-01-24 07:34:23.798043: step: 1572/530, loss: 0.008451227098703384
2023-01-24 07:34:24.904966: step: 1576/530, loss: 0.0048043313436210155
2023-01-24 07:34:25.995552: step: 1580/530, loss: 0.024757657200098038
2023-01-24 07:34:27.088072: step: 1584/530, loss: 0.04192760959267616
2023-01-24 07:34:28.183524: step: 1588/530, loss: 0.008118299767374992
2023-01-24 07:34:29.272221: step: 1592/530, loss: 0.005396769382059574
2023-01-24 07:34:30.356820: step: 1596/530, loss: 0.041538264602422714
2023-01-24 07:34:31.443177: step: 1600/530, loss: 0.007196536287665367
2023-01-24 07:34:32.531439: step: 1604/530, loss: 0.00934265274554491
2023-01-24 07:34:33.610963: step: 1608/530, loss: 0.009051230736076832
2023-01-24 07:34:34.690864: step: 1612/530, loss: 0.004858491476625204
2023-01-24 07:34:35.770556: step: 1616/530, loss: 0.002977528842166066
2023-01-24 07:34:36.861250: step: 1620/530, loss: 0.037747953087091446
2023-01-24 07:34:37.947156: step: 1624/530, loss: 0.03636101260781288
2023-01-24 07:34:39.025357: step: 1628/530, loss: 0.006396973505616188
2023-01-24 07:34:40.116442: step: 1632/530, loss: 0.02565055340528488
2023-01-24 07:34:41.189759: step: 1636/530, loss: 0.0019030816620215774
2023-01-24 07:34:42.287111: step: 1640/530, loss: 0.013001527637243271
2023-01-24 07:34:43.393552: step: 1644/530, loss: 0.054762933403253555
2023-01-24 07:34:44.500472: step: 1648/530, loss: 0.00581360375508666
2023-01-24 07:34:45.564359: step: 1652/530, loss: 0.005165275186300278
2023-01-24 07:34:46.655470: step: 1656/530, loss: 0.0051534841768443584
2023-01-24 07:34:47.738761: step: 1660/530, loss: 0.040944743901491165
2023-01-24 07:34:48.815731: step: 1664/530, loss: 0.012922110967338085
2023-01-24 07:34:49.904449: step: 1668/530, loss: 0.01060144416987896
2023-01-24 07:34:50.980257: step: 1672/530, loss: 0.009440352208912373
2023-01-24 07:34:52.044670: step: 1676/530, loss: 0.006665647029876709
2023-01-24 07:34:53.136849: step: 1680/530, loss: 0.04775189608335495
2023-01-24 07:34:54.222357: step: 1684/530, loss: 0.01774897426366806
2023-01-24 07:34:55.304198: step: 1688/530, loss: 0.03745989128947258
2023-01-24 07:34:56.389093: step: 1692/530, loss: 0.011849308386445045
2023-01-24 07:34:57.461389: step: 1696/530, loss: 0.006372003350406885
2023-01-24 07:34:58.543799: step: 1700/530, loss: 0.007675140164792538
2023-01-24 07:34:59.638316: step: 1704/530, loss: 0.014992504380643368
2023-01-24 07:35:00.728534: step: 1708/530, loss: 0.006380526348948479
2023-01-24 07:35:01.824223: step: 1712/530, loss: 0.017169829457998276
2023-01-24 07:35:02.887526: step: 1716/530, loss: 0.024744641035795212
2023-01-24 07:35:03.988257: step: 1720/530, loss: 0.048928651958703995
2023-01-24 07:35:05.065668: step: 1724/530, loss: 0.005339645780622959
2023-01-24 07:35:06.152519: step: 1728/530, loss: 0.004798244684934616
2023-01-24 07:35:07.234537: step: 1732/530, loss: 0.021579215303063393
2023-01-24 07:35:08.326449: step: 1736/530, loss: 0.028703859075903893
2023-01-24 07:35:09.414450: step: 1740/530, loss: 0.0072754002176225185
2023-01-24 07:35:10.524326: step: 1744/530, loss: 0.04253525286912918
2023-01-24 07:35:11.613342: step: 1748/530, loss: 0.003510440466925502
2023-01-24 07:35:12.735587: step: 1752/530, loss: 0.005049799103289843
2023-01-24 07:35:13.821545: step: 1756/530, loss: 0.018389668315649033
2023-01-24 07:35:14.911997: step: 1760/530, loss: 0.0036845372524112463
2023-01-24 07:35:15.982094: step: 1764/530, loss: 0.0026990945916622877
2023-01-24 07:35:17.073566: step: 1768/530, loss: 0.03512921556830406
2023-01-24 07:35:18.173875: step: 1772/530, loss: 0.005441419780254364
2023-01-24 07:35:19.257223: step: 1776/530, loss: 0.006914149038493633
2023-01-24 07:35:20.347869: step: 1780/530, loss: 0.004507198929786682
2023-01-24 07:35:21.427252: step: 1784/530, loss: 0.01564428210258484
2023-01-24 07:35:22.504338: step: 1788/530, loss: 0.0042689889669418335
2023-01-24 07:35:23.580085: step: 1792/530, loss: 0.004463187884539366
2023-01-24 07:35:24.657479: step: 1796/530, loss: 0.009166345000267029
2023-01-24 07:35:25.743395: step: 1800/530, loss: 0.004761158023029566
2023-01-24 07:35:26.820305: step: 1804/530, loss: 0.009483604691922665
2023-01-24 07:35:27.918162: step: 1808/530, loss: 0.008102762512862682
2023-01-24 07:35:29.000609: step: 1812/530, loss: 0.0076997848227620125
2023-01-24 07:35:30.087377: step: 1816/530, loss: 0.010463826358318329
2023-01-24 07:35:31.176094: step: 1820/530, loss: 0.0031284149736166
2023-01-24 07:35:32.240906: step: 1824/530, loss: 0.004331889096647501
2023-01-24 07:35:33.317233: step: 1828/530, loss: 0.009172449819743633
2023-01-24 07:35:34.413344: step: 1832/530, loss: 0.06897719949483871
2023-01-24 07:35:35.490070: step: 1836/530, loss: 0.0036861842963844538
2023-01-24 07:35:36.589395: step: 1840/530, loss: 0.0324915274977684
2023-01-24 07:35:37.676605: step: 1844/530, loss: 0.03383469209074974
2023-01-24 07:35:38.765466: step: 1848/530, loss: 0.00970512069761753
2023-01-24 07:35:39.855129: step: 1852/530, loss: 0.011853737756609917
2023-01-24 07:35:40.961150: step: 1856/530, loss: 0.0028102637734264135
2023-01-24 07:35:42.034919: step: 1860/530, loss: 0.1190100684762001
2023-01-24 07:35:43.111613: step: 1864/530, loss: 0.019448217004537582
2023-01-24 07:35:44.188009: step: 1868/530, loss: 0.010541149415075779
2023-01-24 07:35:45.277940: step: 1872/530, loss: 0.004271318670362234
2023-01-24 07:35:46.371059: step: 1876/530, loss: 0.007992695085704327
2023-01-24 07:35:47.464596: step: 1880/530, loss: 0.0023088206071406603
2023-01-24 07:35:48.570209: step: 1884/530, loss: 0.01651832088828087
2023-01-24 07:35:49.677825: step: 1888/530, loss: 0.014331793412566185
2023-01-24 07:35:50.763779: step: 1892/530, loss: 0.0037648214492946863
2023-01-24 07:35:51.878129: step: 1896/530, loss: 0.009419191628694534
2023-01-24 07:35:52.999027: step: 1900/530, loss: 0.00566993560642004
2023-01-24 07:35:54.111684: step: 1904/530, loss: 0.010001144371926785
2023-01-24 07:35:55.182984: step: 1908/530, loss: 0.00864218920469284
2023-01-24 07:35:56.285147: step: 1912/530, loss: 0.010635146871209145
2023-01-24 07:35:57.378069: step: 1916/530, loss: 0.012258029542863369
2023-01-24 07:35:58.452171: step: 1920/530, loss: 0.004968596156686544
2023-01-24 07:35:59.541152: step: 1924/530, loss: 0.04668574780225754
2023-01-24 07:36:00.627756: step: 1928/530, loss: 0.034046854823827744
2023-01-24 07:36:01.730029: step: 1932/530, loss: 0.03584835305809975
2023-01-24 07:36:02.813976: step: 1936/530, loss: 0.04924082010984421
2023-01-24 07:36:03.878513: step: 1940/530, loss: 0.008164254017174244
2023-01-24 07:36:04.960082: step: 1944/530, loss: 0.011303422041237354
2023-01-24 07:36:06.074682: step: 1948/530, loss: 0.009488912299275398
2023-01-24 07:36:07.146999: step: 1952/530, loss: 0.003806962864473462
2023-01-24 07:36:08.244830: step: 1956/530, loss: 0.027558019384741783
2023-01-24 07:36:09.348410: step: 1960/530, loss: 0.007914615795016289
2023-01-24 07:36:10.418791: step: 1964/530, loss: 0.0032007251866161823
2023-01-24 07:36:11.527414: step: 1968/530, loss: 0.03232016786932945
2023-01-24 07:36:12.606718: step: 1972/530, loss: 0.0053441342897713184
2023-01-24 07:36:13.689562: step: 1976/530, loss: 0.01302309799939394
2023-01-24 07:36:14.770212: step: 1980/530, loss: 0.022190343588590622
2023-01-24 07:36:15.860443: step: 1984/530, loss: 0.006786705460399389
2023-01-24 07:36:16.967469: step: 1988/530, loss: 0.012712826021015644
2023-01-24 07:36:18.049757: step: 1992/530, loss: 0.007025027181953192
2023-01-24 07:36:19.128796: step: 1996/530, loss: 0.0010213572531938553
2023-01-24 07:36:20.224748: step: 2000/530, loss: 0.01323331892490387
2023-01-24 07:36:21.324917: step: 2004/530, loss: 0.017328208312392235
2023-01-24 07:36:22.406480: step: 2008/530, loss: 0.019475113600492477
2023-01-24 07:36:23.475579: step: 2012/530, loss: 0.04903915524482727
2023-01-24 07:36:24.561193: step: 2016/530, loss: 0.006896850187331438
2023-01-24 07:36:25.638507: step: 2020/530, loss: 0.024892330169677734
2023-01-24 07:36:26.721804: step: 2024/530, loss: 0.01610695756971836
2023-01-24 07:36:27.813703: step: 2028/530, loss: 0.03003283403813839
2023-01-24 07:36:28.894785: step: 2032/530, loss: 0.0017887263093143702
2023-01-24 07:36:29.993406: step: 2036/530, loss: 0.008579340763390064
2023-01-24 07:36:31.085594: step: 2040/530, loss: 0.035815708339214325
2023-01-24 07:36:32.171346: step: 2044/530, loss: 0.007980084046721458
2023-01-24 07:36:33.290313: step: 2048/530, loss: 0.044137533754110336
2023-01-24 07:36:34.367381: step: 2052/530, loss: 0.0021754472982138395
2023-01-24 07:36:35.463219: step: 2056/530, loss: 0.0056371125392615795
2023-01-24 07:36:36.547804: step: 2060/530, loss: 0.00535947410389781
2023-01-24 07:36:37.633369: step: 2064/530, loss: 0.03193186968564987
2023-01-24 07:36:38.741022: step: 2068/530, loss: 0.0052633220329880714
2023-01-24 07:36:39.822177: step: 2072/530, loss: 0.022842828184366226
2023-01-24 07:36:40.903923: step: 2076/530, loss: 0.01033526286482811
2023-01-24 07:36:42.010268: step: 2080/530, loss: 0.0030002822168171406
2023-01-24 07:36:43.108269: step: 2084/530, loss: 0.010663585737347603
2023-01-24 07:36:44.192733: step: 2088/530, loss: 0.0029286956414580345
2023-01-24 07:36:45.287710: step: 2092/530, loss: 0.010178258642554283
2023-01-24 07:36:46.386188: step: 2096/530, loss: 0.019944066181778908
2023-01-24 07:36:47.470662: step: 2100/530, loss: 0.007491804659366608
2023-01-24 07:36:48.552997: step: 2104/530, loss: 0.004933681804686785
2023-01-24 07:36:49.638608: step: 2108/530, loss: 0.006967674940824509
2023-01-24 07:36:50.733537: step: 2112/530, loss: 0.01465792115777731
2023-01-24 07:36:51.814227: step: 2116/530, loss: 0.004928010981529951
2023-01-24 07:36:52.897302: step: 2120/530, loss: 0.012756621465086937
==================================================
Loss: 0.016
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35384310730622737, 'r': 0.34578595875276485, 'f1': 0.3497681387000136}, 'combined': 0.25772389167369425, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34016676933404005, 'r': 0.26816312083009886, 'f1': 0.2999036672115375}, 'combined': 0.18625596174190226, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3906081588479548, 'r': 0.3268656509524631, 'f1': 0.3559053678759258}, 'combined': 0.26224606054015587, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3365587402403451, 'r': 0.2607332533087258, 'f1': 0.2938330204325507}, 'combined': 0.18248577058442625, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3818011606932129, 'r': 0.323118249846628, 'f1': 0.35001709695616234}, 'combined': 0.2579073345992775, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34522140115342165, 'r': 0.2664986532102426, 'f1': 0.30079458016933225}, 'combined': 0.18680926557884847, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, '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': 0.35384310730622737, 'r': 0.34578595875276485, 'f1': 0.3497681387000136}, 'combined': 0.25772389167369425, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34016676933404005, 'r': 0.26816312083009886, 'f1': 0.2999036672115375}, 'combined': 0.18625596174190226, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3906081588479548, 'r': 0.3268656509524631, 'f1': 0.3559053678759258}, 'combined': 0.26224606054015587, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3365587402403451, 'r': 0.2607332533087258, 'f1': 0.2938330204325507}, 'combined': 0.18248577058442625, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3818011606932129, 'r': 0.323118249846628, 'f1': 0.35001709695616234}, 'combined': 0.2579073345992775, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34522140115342165, 'r': 0.2664986532102426, 'f1': 0.30079458016933225}, 'combined': 0.18680926557884847, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, '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 07:39:38.081046: step: 4/530, loss: 0.012391503900289536
2023-01-24 07:39:39.157083: step: 8/530, loss: 0.007634381297975779
2023-01-24 07:39:40.242540: step: 12/530, loss: 0.0344882532954216
2023-01-24 07:39:41.331706: step: 16/530, loss: 0.008949057199060917
2023-01-24 07:39:42.418013: step: 20/530, loss: 0.014058766886591911
2023-01-24 07:39:43.501027: step: 24/530, loss: 0.01798669435083866
2023-01-24 07:39:44.581869: step: 28/530, loss: 0.03188132122159004
2023-01-24 07:39:45.685152: step: 32/530, loss: 0.017498953267931938
2023-01-24 07:39:46.763599: step: 36/530, loss: 0.004909016191959381
2023-01-24 07:39:47.839532: step: 40/530, loss: 0.005497514270246029
2023-01-24 07:39:48.918169: step: 44/530, loss: 0.014802170917391777
2023-01-24 07:39:50.018192: step: 48/530, loss: 0.0059297094121575356
2023-01-24 07:39:51.108659: step: 52/530, loss: 0.006121484097093344
2023-01-24 07:39:52.215303: step: 56/530, loss: 0.033066362142562866
2023-01-24 07:39:53.311958: step: 60/530, loss: 0.017747612670063972
2023-01-24 07:39:54.395585: step: 64/530, loss: 0.003740782616659999
2023-01-24 07:39:55.473797: step: 68/530, loss: 0.0008440447854809463
2023-01-24 07:39:56.533415: step: 72/530, loss: 0.044839028269052505
2023-01-24 07:39:57.642327: step: 76/530, loss: 0.0036292097065597773
2023-01-24 07:39:58.732391: step: 80/530, loss: 0.0031144428066909313
2023-01-24 07:39:59.810843: step: 84/530, loss: 0.003786178771406412
2023-01-24 07:40:00.878902: step: 88/530, loss: 0.06664510071277618
2023-01-24 07:40:01.948529: step: 92/530, loss: 0.010051997378468513
2023-01-24 07:40:03.048579: step: 96/530, loss: 0.005361826159060001
2023-01-24 07:40:04.116061: step: 100/530, loss: 0.004370855167508125
2023-01-24 07:40:05.184010: step: 104/530, loss: 0.009892871603369713
2023-01-24 07:40:06.255400: step: 108/530, loss: 0.006972011178731918
2023-01-24 07:40:07.342026: step: 112/530, loss: 0.049745917320251465
2023-01-24 07:40:08.436161: step: 116/530, loss: 0.005181717686355114
2023-01-24 07:40:09.510232: step: 120/530, loss: 0.04260662570595741
2023-01-24 07:40:10.580487: step: 124/530, loss: 0.019936926662921906
2023-01-24 07:40:11.639606: step: 128/530, loss: 0.009502381086349487
2023-01-24 07:40:12.732038: step: 132/530, loss: 0.0027861290145665407
2023-01-24 07:40:13.805333: step: 136/530, loss: 0.007031664252281189
2023-01-24 07:40:14.875929: step: 140/530, loss: 0.00249624066054821
2023-01-24 07:40:15.958375: step: 144/530, loss: 0.008162613026797771
2023-01-24 07:40:17.056054: step: 148/530, loss: 0.006209488958120346
2023-01-24 07:40:18.147324: step: 152/530, loss: 0.014237584546208382
2023-01-24 07:40:19.220892: step: 156/530, loss: 0.005376539193093777
2023-01-24 07:40:20.291661: step: 160/530, loss: 0.005726292729377747
2023-01-24 07:40:21.364964: step: 164/530, loss: 0.045714814215898514
2023-01-24 07:40:22.431066: step: 168/530, loss: 0.004599275533109903
2023-01-24 07:40:23.520766: step: 172/530, loss: 0.019371014088392258
2023-01-24 07:40:24.615173: step: 176/530, loss: 0.00452074920758605
2023-01-24 07:40:25.693419: step: 180/530, loss: 0.00240876991301775
2023-01-24 07:40:26.758270: step: 184/530, loss: 0.009490301832556725
2023-01-24 07:40:27.827356: step: 188/530, loss: 0.015913814306259155
2023-01-24 07:40:28.894202: step: 192/530, loss: 0.003869971027597785
2023-01-24 07:40:29.991187: step: 196/530, loss: 0.005710897035896778
2023-01-24 07:40:31.092320: step: 200/530, loss: 0.009119526483118534
2023-01-24 07:40:32.158138: step: 204/530, loss: 0.00745429378002882
2023-01-24 07:40:33.263044: step: 208/530, loss: 0.011853475123643875
2023-01-24 07:40:34.335860: step: 212/530, loss: 0.013891429640352726
2023-01-24 07:40:35.421897: step: 216/530, loss: 0.0012209659907966852
2023-01-24 07:40:36.521554: step: 220/530, loss: 0.016997987404465675
2023-01-24 07:40:37.606464: step: 224/530, loss: 0.006589137949049473
2023-01-24 07:40:38.678965: step: 228/530, loss: 0.005170939024537802
2023-01-24 07:40:39.751566: step: 232/530, loss: 0.007014515344053507
2023-01-24 07:40:40.819371: step: 236/530, loss: 0.0014491764595732093
2023-01-24 07:40:41.924286: step: 240/530, loss: 0.017552219331264496
2023-01-24 07:40:43.024347: step: 244/530, loss: 0.0005964357405900955
2023-01-24 07:40:44.114206: step: 248/530, loss: 0.022998103871941566
2023-01-24 07:40:45.196507: step: 252/530, loss: 0.002045807894319296
2023-01-24 07:40:46.275352: step: 256/530, loss: 0.030318327248096466
2023-01-24 07:40:47.334807: step: 260/530, loss: 0.005669730249792337
2023-01-24 07:40:48.425776: step: 264/530, loss: 0.012015166692435741
2023-01-24 07:40:49.486962: step: 268/530, loss: 0.0019308619666844606
2023-01-24 07:40:50.554415: step: 272/530, loss: 0.02902081608772278
2023-01-24 07:40:51.634199: step: 276/530, loss: 0.0015481747686862946
2023-01-24 07:40:52.686223: step: 280/530, loss: 0.015439937822520733
2023-01-24 07:40:53.770181: step: 284/530, loss: 0.002557411091402173
2023-01-24 07:40:54.854397: step: 288/530, loss: 0.010464164428412914
2023-01-24 07:40:55.923325: step: 292/530, loss: 0.005846427753567696
2023-01-24 07:40:56.998624: step: 296/530, loss: 0.0033386549912393093
2023-01-24 07:40:58.070833: step: 300/530, loss: 0.004703700542449951
2023-01-24 07:40:59.172320: step: 304/530, loss: 0.0037038058508187532
2023-01-24 07:41:00.267454: step: 308/530, loss: 0.023519383743405342
2023-01-24 07:41:01.351094: step: 312/530, loss: 0.004581342451274395
2023-01-24 07:41:02.450435: step: 316/530, loss: 0.01667645014822483
2023-01-24 07:41:03.526393: step: 320/530, loss: 0.009866605512797832
2023-01-24 07:41:04.603551: step: 324/530, loss: 0.006697378121316433
2023-01-24 07:41:05.700380: step: 328/530, loss: 0.0029570343904197216
2023-01-24 07:41:06.798010: step: 332/530, loss: 0.00546490540727973
2023-01-24 07:41:07.865869: step: 336/530, loss: 0.010721621103584766
2023-01-24 07:41:08.963256: step: 340/530, loss: 0.01307881623506546
2023-01-24 07:41:10.056176: step: 344/530, loss: 0.0055169640108942986
2023-01-24 07:41:11.120632: step: 348/530, loss: 0.012309126555919647
2023-01-24 07:41:12.195965: step: 352/530, loss: 0.003929964732378721
2023-01-24 07:41:13.257553: step: 356/530, loss: 0.0027418392710387707
2023-01-24 07:41:14.362435: step: 360/530, loss: 0.004157582297921181
2023-01-24 07:41:15.463023: step: 364/530, loss: 0.002446571597829461
2023-01-24 07:41:16.538478: step: 368/530, loss: 0.007255947683006525
2023-01-24 07:41:17.611320: step: 372/530, loss: 0.004091478884220123
2023-01-24 07:41:18.691934: step: 376/530, loss: 0.0076437462121248245
2023-01-24 07:41:19.775167: step: 380/530, loss: 0.029653025791049004
2023-01-24 07:41:20.860397: step: 384/530, loss: 0.009166298434138298
2023-01-24 07:41:21.934081: step: 388/530, loss: 0.01233306247740984
2023-01-24 07:41:23.003837: step: 392/530, loss: 0.0054398709908127785
2023-01-24 07:41:24.106837: step: 396/530, loss: 0.010394660755991936
2023-01-24 07:41:25.181494: step: 400/530, loss: 0.01157502643764019
2023-01-24 07:41:26.258081: step: 404/530, loss: 0.004937803838402033
2023-01-24 07:41:27.352968: step: 408/530, loss: 0.041797030717134476
2023-01-24 07:41:28.426199: step: 412/530, loss: 0.006708246655762196
2023-01-24 07:41:29.498632: step: 416/530, loss: 0.022681649774312973
2023-01-24 07:41:30.589852: step: 420/530, loss: 0.011472459882497787
2023-01-24 07:41:31.669936: step: 424/530, loss: 0.003999972715973854
2023-01-24 07:41:32.744909: step: 428/530, loss: 0.006213391199707985
2023-01-24 07:41:33.838993: step: 432/530, loss: 0.008885979652404785
2023-01-24 07:41:34.919993: step: 436/530, loss: 0.03559815138578415
2023-01-24 07:41:35.991378: step: 440/530, loss: 0.0028997703921049833
2023-01-24 07:41:37.073938: step: 444/530, loss: 0.007490651682019234
2023-01-24 07:41:38.140006: step: 448/530, loss: 0.006587234791368246
2023-01-24 07:41:39.225112: step: 452/530, loss: 0.01258843019604683
2023-01-24 07:41:40.304436: step: 456/530, loss: 0.0022444056812673807
2023-01-24 07:41:41.387092: step: 460/530, loss: 0.004761658143252134
2023-01-24 07:41:42.478140: step: 464/530, loss: 0.005991101264953613
2023-01-24 07:41:43.533342: step: 468/530, loss: 0.011496379040181637
2023-01-24 07:41:44.636599: step: 472/530, loss: 0.0033064144663512707
2023-01-24 07:41:45.715077: step: 476/530, loss: 0.0015110295498743653
2023-01-24 07:41:46.778418: step: 480/530, loss: 0.002834895858541131
2023-01-24 07:41:47.866636: step: 484/530, loss: 0.04340868070721626
2023-01-24 07:41:48.951000: step: 488/530, loss: 0.026502616703510284
2023-01-24 07:41:50.056266: step: 492/530, loss: 0.03256915137171745
2023-01-24 07:41:51.125151: step: 496/530, loss: 0.042726702988147736
2023-01-24 07:41:52.221636: step: 500/530, loss: 0.03379477187991142
2023-01-24 07:41:53.319169: step: 504/530, loss: 0.0456722155213356
2023-01-24 07:41:54.421737: step: 508/530, loss: 0.008975841104984283
2023-01-24 07:41:55.501010: step: 512/530, loss: 0.010568582452833652
2023-01-24 07:41:56.586485: step: 516/530, loss: 0.004530169069766998
2023-01-24 07:41:57.654584: step: 520/530, loss: 0.0050271437503397465
2023-01-24 07:41:58.730848: step: 524/530, loss: 0.0059117465279996395
2023-01-24 07:41:59.784689: step: 528/530, loss: 0.007956920191645622
2023-01-24 07:42:00.859854: step: 532/530, loss: 0.00443342886865139
2023-01-24 07:42:01.956164: step: 536/530, loss: 0.0077603361569345
2023-01-24 07:42:03.042253: step: 540/530, loss: 0.04145801439881325
2023-01-24 07:42:04.114412: step: 544/530, loss: 0.0022467821836471558
2023-01-24 07:42:05.201913: step: 548/530, loss: 0.0038608901668339968
2023-01-24 07:42:06.312906: step: 552/530, loss: 0.012951676733791828
2023-01-24 07:42:07.403823: step: 556/530, loss: 0.00817587785422802
2023-01-24 07:42:08.489448: step: 560/530, loss: 0.018627174198627472
2023-01-24 07:42:09.582402: step: 564/530, loss: 0.054581452161073685
2023-01-24 07:42:10.669166: step: 568/530, loss: 0.006028099916875362
2023-01-24 07:42:11.751359: step: 572/530, loss: 0.007498130202293396
2023-01-24 07:42:12.864827: step: 576/530, loss: 0.0036621009930968285
2023-01-24 07:42:13.948791: step: 580/530, loss: 0.02529073692858219
2023-01-24 07:42:15.044038: step: 584/530, loss: 0.003978257533162832
2023-01-24 07:42:16.126766: step: 588/530, loss: 0.023453691974282265
2023-01-24 07:42:17.241569: step: 592/530, loss: 0.004406873136758804
2023-01-24 07:42:18.353650: step: 596/530, loss: 0.00697239488363266
2023-01-24 07:42:19.444989: step: 600/530, loss: 0.003588011721149087
2023-01-24 07:42:20.541441: step: 604/530, loss: 0.006585159804672003
2023-01-24 07:42:21.632441: step: 608/530, loss: 0.0055506532080471516
2023-01-24 07:42:22.719197: step: 612/530, loss: 0.006966990884393454
2023-01-24 07:42:23.807944: step: 616/530, loss: 0.006100517697632313
2023-01-24 07:42:24.907002: step: 620/530, loss: 0.009459367953240871
2023-01-24 07:42:25.989334: step: 624/530, loss: 0.005740609485656023
2023-01-24 07:42:27.067630: step: 628/530, loss: 0.005944130476564169
2023-01-24 07:42:28.145053: step: 632/530, loss: 0.042672835290431976
2023-01-24 07:42:29.231845: step: 636/530, loss: 0.0050724768079817295
2023-01-24 07:42:30.318401: step: 640/530, loss: 0.022977346554398537
2023-01-24 07:42:31.385145: step: 644/530, loss: 0.0024776621721684933
2023-01-24 07:42:32.476399: step: 648/530, loss: 0.00833917036652565
2023-01-24 07:42:33.545471: step: 652/530, loss: 0.003180461237207055
2023-01-24 07:42:34.663716: step: 656/530, loss: 0.009908239357173443
2023-01-24 07:42:35.763806: step: 660/530, loss: 0.010503917932510376
2023-01-24 07:42:36.836393: step: 664/530, loss: 0.0063460045494139194
2023-01-24 07:42:37.929196: step: 668/530, loss: 0.04455850273370743
2023-01-24 07:42:39.025389: step: 672/530, loss: 0.0043808892369270325
2023-01-24 07:42:40.093848: step: 676/530, loss: 0.007582313846796751
2023-01-24 07:42:41.182226: step: 680/530, loss: 0.009835908189415932
2023-01-24 07:42:42.298764: step: 684/530, loss: 0.005511335097253323
2023-01-24 07:42:43.384277: step: 688/530, loss: 0.008358702063560486
2023-01-24 07:42:44.477287: step: 692/530, loss: 0.0029729404486715794
2023-01-24 07:42:45.556397: step: 696/530, loss: 0.034365374594926834
2023-01-24 07:42:46.625807: step: 700/530, loss: 0.008347341790795326
2023-01-24 07:42:47.704291: step: 704/530, loss: 0.0070320009253919125
2023-01-24 07:42:48.774351: step: 708/530, loss: 0.004852325655519962
2023-01-24 07:42:49.875011: step: 712/530, loss: 0.004159483592957258
2023-01-24 07:42:50.943249: step: 716/530, loss: 0.05728793889284134
2023-01-24 07:42:52.019471: step: 720/530, loss: 0.014387681148946285
2023-01-24 07:42:53.074655: step: 724/530, loss: 0.0014776451280340552
2023-01-24 07:42:54.168883: step: 728/530, loss: 0.006308345589786768
2023-01-24 07:42:55.247097: step: 732/530, loss: 0.0032411569263786077
2023-01-24 07:42:56.335312: step: 736/530, loss: 0.022740010172128677
2023-01-24 07:42:57.451873: step: 740/530, loss: 0.0197331253439188
2023-01-24 07:42:58.523555: step: 744/530, loss: 0.004414266441017389
2023-01-24 07:42:59.592542: step: 748/530, loss: 0.00426337867975235
2023-01-24 07:43:00.685378: step: 752/530, loss: 0.006704048719257116
2023-01-24 07:43:01.752231: step: 756/530, loss: 0.002996407449245453
2023-01-24 07:43:02.836384: step: 760/530, loss: 0.02191072888672352
2023-01-24 07:43:03.905435: step: 764/530, loss: 0.008164918050169945
2023-01-24 07:43:04.980468: step: 768/530, loss: 0.0041312649846076965
2023-01-24 07:43:06.052817: step: 772/530, loss: 0.012271516025066376
2023-01-24 07:43:07.143197: step: 776/530, loss: 0.028820911422371864
2023-01-24 07:43:08.207814: step: 780/530, loss: 0.004298738669604063
2023-01-24 07:43:09.308527: step: 784/530, loss: 0.029807010665535927
2023-01-24 07:43:10.396968: step: 788/530, loss: 0.004857347346842289
2023-01-24 07:43:11.499214: step: 792/530, loss: 0.008187413215637207
2023-01-24 07:43:12.638127: step: 796/530, loss: 0.03593704476952553
2023-01-24 07:43:13.727722: step: 800/530, loss: 0.0028564122039824724
2023-01-24 07:43:14.808437: step: 804/530, loss: 0.006321623455733061
2023-01-24 07:43:15.890822: step: 808/530, loss: 0.031741488724946976
2023-01-24 07:43:16.968144: step: 812/530, loss: 0.02111353911459446
2023-01-24 07:43:18.054707: step: 816/530, loss: 0.013843242079019547
2023-01-24 07:43:19.155676: step: 820/530, loss: 0.009732394479215145
2023-01-24 07:43:20.255924: step: 824/530, loss: 0.00735677033662796
2023-01-24 07:43:21.338740: step: 828/530, loss: 0.014589892700314522
2023-01-24 07:43:22.426667: step: 832/530, loss: 0.0028226105496287346
2023-01-24 07:43:23.517803: step: 836/530, loss: 0.0016596870264038444
2023-01-24 07:43:24.599379: step: 840/530, loss: 0.003013663226738572
2023-01-24 07:43:25.668451: step: 844/530, loss: 0.008269528858363628
2023-01-24 07:43:26.750452: step: 848/530, loss: 0.0035748162772506475
2023-01-24 07:43:27.844711: step: 852/530, loss: 0.011307514272630215
2023-01-24 07:43:28.934396: step: 856/530, loss: 0.0037999527994543314
2023-01-24 07:43:30.028398: step: 860/530, loss: 0.005010879132896662
2023-01-24 07:43:31.116608: step: 864/530, loss: 0.030367949977517128
2023-01-24 07:43:32.226704: step: 868/530, loss: 0.005125672556459904
2023-01-24 07:43:33.310467: step: 872/530, loss: 0.005078231915831566
2023-01-24 07:43:34.396604: step: 876/530, loss: 0.0036739930510520935
2023-01-24 07:43:35.481318: step: 880/530, loss: 0.0037847235798835754
2023-01-24 07:43:36.545991: step: 884/530, loss: 0.032393958419561386
2023-01-24 07:43:37.641581: step: 888/530, loss: 0.04867049679160118
2023-01-24 07:43:38.739098: step: 892/530, loss: 0.017797769978642464
2023-01-24 07:43:39.842605: step: 896/530, loss: 0.02136847749352455
2023-01-24 07:43:40.928262: step: 900/530, loss: 0.03316077962517738
2023-01-24 07:43:42.012061: step: 904/530, loss: 0.0027223387733101845
2023-01-24 07:43:43.098634: step: 908/530, loss: 0.0022718573454767466
2023-01-24 07:43:44.188817: step: 912/530, loss: 0.01857251673936844
2023-01-24 07:43:45.256403: step: 916/530, loss: 0.00319062452763319
2023-01-24 07:43:46.335374: step: 920/530, loss: 0.008814864791929722
2023-01-24 07:43:47.418745: step: 924/530, loss: 0.022224988788366318
2023-01-24 07:43:48.515705: step: 928/530, loss: 0.021893490105867386
2023-01-24 07:43:49.595711: step: 932/530, loss: 0.007734906394034624
2023-01-24 07:43:50.699987: step: 936/530, loss: 0.0033426606096327305
2023-01-24 07:43:51.783263: step: 940/530, loss: 0.008457035757601261
2023-01-24 07:43:52.859605: step: 944/530, loss: 0.01598880998790264
2023-01-24 07:43:53.943323: step: 948/530, loss: 0.012407969683408737
2023-01-24 07:43:55.039407: step: 952/530, loss: 0.011005377396941185
2023-01-24 07:43:56.159309: step: 956/530, loss: 0.009087464772164822
2023-01-24 07:43:57.226146: step: 960/530, loss: 0.006762050092220306
2023-01-24 07:43:58.323878: step: 964/530, loss: 0.005455736070871353
2023-01-24 07:43:59.430398: step: 968/530, loss: 0.0029754224233329296
2023-01-24 07:44:00.505499: step: 972/530, loss: 0.013980239629745483
2023-01-24 07:44:01.588139: step: 976/530, loss: 0.010633447207510471
2023-01-24 07:44:02.663073: step: 980/530, loss: 0.009286978282034397
2023-01-24 07:44:03.738901: step: 984/530, loss: 0.005178204737603664
2023-01-24 07:44:04.820117: step: 988/530, loss: 0.01092336792498827
2023-01-24 07:44:05.914009: step: 992/530, loss: 0.005870092660188675
2023-01-24 07:44:06.990013: step: 996/530, loss: 0.004301386419683695
2023-01-24 07:44:08.077404: step: 1000/530, loss: 0.022751811891794205
2023-01-24 07:44:09.148628: step: 1004/530, loss: 0.006232579238712788
2023-01-24 07:44:10.226213: step: 1008/530, loss: 0.06963155418634415
2023-01-24 07:44:11.302142: step: 1012/530, loss: 0.004631880205124617
2023-01-24 07:44:12.405480: step: 1016/530, loss: 0.008173738606274128
2023-01-24 07:44:13.480348: step: 1020/530, loss: 0.0032272457610815763
2023-01-24 07:44:14.568407: step: 1024/530, loss: 0.004275115672498941
2023-01-24 07:44:15.644380: step: 1028/530, loss: 0.008450631983578205
2023-01-24 07:44:16.728360: step: 1032/530, loss: 0.0003325218567624688
2023-01-24 07:44:17.814666: step: 1036/530, loss: 0.011116856709122658
2023-01-24 07:44:18.879989: step: 1040/530, loss: 0.0034582875669002533
2023-01-24 07:44:19.959117: step: 1044/530, loss: 0.0018107590731233358
2023-01-24 07:44:21.046127: step: 1048/530, loss: 0.026982396841049194
2023-01-24 07:44:22.139848: step: 1052/530, loss: 0.002509910613298416
2023-01-24 07:44:23.203422: step: 1056/530, loss: 0.012826124206185341
2023-01-24 07:44:24.283347: step: 1060/530, loss: 0.031740766018629074
2023-01-24 07:44:25.359417: step: 1064/530, loss: 0.028774620965123177
2023-01-24 07:44:26.435070: step: 1068/530, loss: 0.0026212071534246206
2023-01-24 07:44:27.517055: step: 1072/530, loss: 0.0076530794613063335
2023-01-24 07:44:28.581207: step: 1076/530, loss: 0.06592535227537155
2023-01-24 07:44:29.681086: step: 1080/530, loss: 0.0094529427587986
2023-01-24 07:44:30.770118: step: 1084/530, loss: 0.005001086741685867
2023-01-24 07:44:31.855237: step: 1088/530, loss: 0.014370698481798172
2023-01-24 07:44:32.928302: step: 1092/530, loss: 0.0329345166683197
2023-01-24 07:44:34.017541: step: 1096/530, loss: 0.03442564979195595
2023-01-24 07:44:35.100002: step: 1100/530, loss: 0.03979559242725372
2023-01-24 07:44:36.195662: step: 1104/530, loss: 0.007194514852017164
2023-01-24 07:44:37.323168: step: 1108/530, loss: 0.020551208406686783
2023-01-24 07:44:38.428268: step: 1112/530, loss: 0.006106766872107983
2023-01-24 07:44:39.522723: step: 1116/530, loss: 0.003778885118663311
2023-01-24 07:44:40.625793: step: 1120/530, loss: 0.06535742431879044
2023-01-24 07:44:41.698701: step: 1124/530, loss: 0.04842514917254448
2023-01-24 07:44:42.786668: step: 1128/530, loss: 0.06867803633213043
2023-01-24 07:44:43.865124: step: 1132/530, loss: 0.00756215862929821
2023-01-24 07:44:44.957031: step: 1136/530, loss: 0.01421402208507061
2023-01-24 07:44:46.044149: step: 1140/530, loss: 0.034601762890815735
2023-01-24 07:44:47.129069: step: 1144/530, loss: 0.006792508997023106
2023-01-24 07:44:48.219777: step: 1148/530, loss: 0.010737613774836063
2023-01-24 07:44:49.293336: step: 1152/530, loss: 0.01484235655516386
2023-01-24 07:44:50.380318: step: 1156/530, loss: 0.024346277117729187
2023-01-24 07:44:51.467928: step: 1160/530, loss: 0.027085792273283005
2023-01-24 07:44:52.557340: step: 1164/530, loss: 0.0024853956419974566
2023-01-24 07:44:53.671532: step: 1168/530, loss: 0.08352573215961456
2023-01-24 07:44:54.759234: step: 1172/530, loss: 0.03397878259420395
2023-01-24 07:44:55.850420: step: 1176/530, loss: 0.00481100007891655
2023-01-24 07:44:56.972559: step: 1180/530, loss: 0.024954786524176598
2023-01-24 07:44:58.034977: step: 1184/530, loss: 0.03177491948008537
2023-01-24 07:44:59.123336: step: 1188/530, loss: 0.010879147797822952
2023-01-24 07:45:00.201853: step: 1192/530, loss: 0.004253412131220102
2023-01-24 07:45:01.290418: step: 1196/530, loss: 0.003874037181958556
2023-01-24 07:45:02.390139: step: 1200/530, loss: 0.030718030408024788
2023-01-24 07:45:03.474931: step: 1204/530, loss: 0.009647996164858341
2023-01-24 07:45:04.559027: step: 1208/530, loss: 0.013988994993269444
2023-01-24 07:45:05.653096: step: 1212/530, loss: 0.0038821506313979626
2023-01-24 07:45:06.774722: step: 1216/530, loss: 0.007743278983980417
2023-01-24 07:45:07.872019: step: 1220/530, loss: 0.010174600407481194
2023-01-24 07:45:08.937444: step: 1224/530, loss: 0.004546063952147961
2023-01-24 07:45:10.023113: step: 1228/530, loss: 0.03946392983198166
2023-01-24 07:45:11.124612: step: 1232/530, loss: 0.0052576204761862755
2023-01-24 07:45:12.208353: step: 1236/530, loss: 0.00017730020044837147
2023-01-24 07:45:13.290654: step: 1240/530, loss: 0.0027113768737763166
2023-01-24 07:45:14.369240: step: 1244/530, loss: 0.0044046686962246895
2023-01-24 07:45:15.437137: step: 1248/530, loss: 0.004420549608767033
2023-01-24 07:45:16.519234: step: 1252/530, loss: 0.025432948023080826
2023-01-24 07:45:17.618067: step: 1256/530, loss: 0.012925539165735245
2023-01-24 07:45:18.705703: step: 1260/530, loss: 0.004398446064442396
2023-01-24 07:45:19.799975: step: 1264/530, loss: 0.001315298955887556
2023-01-24 07:45:20.882667: step: 1268/530, loss: 0.017206929624080658
2023-01-24 07:45:21.982348: step: 1272/530, loss: 0.00601047370582819
2023-01-24 07:45:23.051425: step: 1276/530, loss: 0.006891086231917143
2023-01-24 07:45:24.106941: step: 1280/530, loss: 0.0047853486612439156
2023-01-24 07:45:25.219773: step: 1284/530, loss: 0.01606903038918972
2023-01-24 07:45:26.278667: step: 1288/530, loss: 0.0858551561832428
2023-01-24 07:45:27.364198: step: 1292/530, loss: 0.04245857521891594
2023-01-24 07:45:28.452200: step: 1296/530, loss: 0.006317073479294777
2023-01-24 07:45:29.551728: step: 1300/530, loss: 0.003843980608507991
2023-01-24 07:45:30.662789: step: 1304/530, loss: 0.004499596543610096
2023-01-24 07:45:31.749843: step: 1308/530, loss: 0.013047484681010246
2023-01-24 07:45:32.842775: step: 1312/530, loss: 0.014584006741642952
2023-01-24 07:45:33.918688: step: 1316/530, loss: 0.004421008750796318
2023-01-24 07:45:35.006023: step: 1320/530, loss: 0.006567663978785276
2023-01-24 07:45:36.095183: step: 1324/530, loss: 0.012001038528978825
2023-01-24 07:45:37.172251: step: 1328/530, loss: 0.006867594551295042
2023-01-24 07:45:38.247286: step: 1332/530, loss: 0.0037352575454860926
2023-01-24 07:45:39.308332: step: 1336/530, loss: 0.0037329038605093956
2023-01-24 07:45:40.391018: step: 1340/530, loss: 0.003762504318729043
2023-01-24 07:45:41.498096: step: 1344/530, loss: 0.011309497058391571
2023-01-24 07:45:42.577975: step: 1348/530, loss: 0.011775614693760872
2023-01-24 07:45:43.663900: step: 1352/530, loss: 0.01116671971976757
2023-01-24 07:45:44.738088: step: 1356/530, loss: 0.009452038444578648
2023-01-24 07:45:45.832938: step: 1360/530, loss: 0.0030575324781239033
2023-01-24 07:45:46.903344: step: 1364/530, loss: 0.006513847969472408
2023-01-24 07:45:47.964470: step: 1368/530, loss: 0.0021709268912672997
2023-01-24 07:45:49.036665: step: 1372/530, loss: 0.0028043787460774183
2023-01-24 07:45:50.135131: step: 1376/530, loss: 0.002050436334684491
2023-01-24 07:45:51.208158: step: 1380/530, loss: 0.007309226784855127
2023-01-24 07:45:52.294790: step: 1384/530, loss: 0.0631498470902443
2023-01-24 07:45:53.375909: step: 1388/530, loss: 0.009299755096435547
2023-01-24 07:45:54.456270: step: 1392/530, loss: 0.0006266501150093973
2023-01-24 07:45:55.516196: step: 1396/530, loss: 0.002885455032810569
2023-01-24 07:45:56.600710: step: 1400/530, loss: 0.027987513691186905
2023-01-24 07:45:57.676335: step: 1404/530, loss: 0.006226013880223036
2023-01-24 07:45:58.749769: step: 1408/530, loss: 0.003627366153523326
2023-01-24 07:45:59.864183: step: 1412/530, loss: 0.0046201786026358604
2023-01-24 07:46:00.962521: step: 1416/530, loss: 0.026542022824287415
2023-01-24 07:46:02.034377: step: 1420/530, loss: 0.006074593402445316
2023-01-24 07:46:03.101307: step: 1424/530, loss: 0.003745131194591522
2023-01-24 07:46:04.194637: step: 1428/530, loss: 0.038597483187913895
2023-01-24 07:46:05.286222: step: 1432/530, loss: 0.032367486506700516
2023-01-24 07:46:06.350801: step: 1436/530, loss: 0.005088086239993572
2023-01-24 07:46:07.415463: step: 1440/530, loss: 0.010617496445775032
2023-01-24 07:46:08.505789: step: 1444/530, loss: 0.010132071562111378
2023-01-24 07:46:09.596847: step: 1448/530, loss: 0.008153957314789295
2023-01-24 07:46:10.688796: step: 1452/530, loss: 0.00618277071043849
2023-01-24 07:46:11.783352: step: 1456/530, loss: 0.0038366348017007113
2023-01-24 07:46:12.893236: step: 1460/530, loss: 0.023068279027938843
2023-01-24 07:46:13.978962: step: 1464/530, loss: 0.008380578830838203
2023-01-24 07:46:15.061666: step: 1468/530, loss: 0.03498849272727966
2023-01-24 07:46:16.165315: step: 1472/530, loss: 0.004794488660991192
2023-01-24 07:46:17.239119: step: 1476/530, loss: 0.013601918704807758
2023-01-24 07:46:18.313175: step: 1480/530, loss: 0.03223627805709839
2023-01-24 07:46:19.403002: step: 1484/530, loss: 0.004585186019539833
2023-01-24 07:46:20.490737: step: 1488/530, loss: 0.012364663183689117
2023-01-24 07:46:21.564122: step: 1492/530, loss: 0.005103865638375282
2023-01-24 07:46:22.653432: step: 1496/530, loss: 0.014150340110063553
2023-01-24 07:46:23.722037: step: 1500/530, loss: 0.01660972833633423
2023-01-24 07:46:24.829397: step: 1504/530, loss: 0.004308665636926889
2023-01-24 07:46:25.916538: step: 1508/530, loss: 0.019259531050920486
2023-01-24 07:46:26.976163: step: 1512/530, loss: 0.0035142023116350174
2023-01-24 07:46:28.085023: step: 1516/530, loss: 0.008946807123720646
2023-01-24 07:46:29.176009: step: 1520/530, loss: 0.016206560656428337
2023-01-24 07:46:30.247512: step: 1524/530, loss: 0.01725117862224579
2023-01-24 07:46:31.321843: step: 1528/530, loss: 0.004326906520873308
2023-01-24 07:46:32.450892: step: 1532/530, loss: 0.0019213708583265543
2023-01-24 07:46:33.530178: step: 1536/530, loss: 0.008800514973700047
2023-01-24 07:46:34.605634: step: 1540/530, loss: 0.005787848029285669
2023-01-24 07:46:35.695994: step: 1544/530, loss: 0.007245591841638088
2023-01-24 07:46:36.779968: step: 1548/530, loss: 0.011111351661384106
2023-01-24 07:46:37.872790: step: 1552/530, loss: 0.002489902311936021
2023-01-24 07:46:38.964966: step: 1556/530, loss: 0.008993119932711124
2023-01-24 07:46:40.081505: step: 1560/530, loss: 0.010299931280314922
2023-01-24 07:46:41.159133: step: 1564/530, loss: 0.03347787633538246
2023-01-24 07:46:42.282050: step: 1568/530, loss: 0.02024606615304947
2023-01-24 07:46:43.367616: step: 1572/530, loss: 0.0033000423572957516
2023-01-24 07:46:44.475728: step: 1576/530, loss: 0.017095889896154404
2023-01-24 07:46:45.555590: step: 1580/530, loss: 0.09861433506011963
2023-01-24 07:46:46.647289: step: 1584/530, loss: 0.008935102261602879
2023-01-24 07:46:47.745570: step: 1588/530, loss: 0.008086437359452248
2023-01-24 07:46:48.831503: step: 1592/530, loss: 0.0017422897508367896
2023-01-24 07:46:49.897304: step: 1596/530, loss: 0.023042909801006317
2023-01-24 07:46:50.987577: step: 1600/530, loss: 0.008903463371098042
2023-01-24 07:46:52.082207: step: 1604/530, loss: 0.008396804332733154
2023-01-24 07:46:53.136694: step: 1608/530, loss: 0.005524285603314638
2023-01-24 07:46:54.228630: step: 1612/530, loss: 0.022530753165483475
2023-01-24 07:46:55.318912: step: 1616/530, loss: 0.016370324417948723
2023-01-24 07:46:56.404251: step: 1620/530, loss: 0.04579024389386177
2023-01-24 07:46:57.499932: step: 1624/530, loss: 0.007668602745980024
2023-01-24 07:46:58.600788: step: 1628/530, loss: 0.003944729920476675
2023-01-24 07:46:59.671256: step: 1632/530, loss: 0.0032784356735646725
2023-01-24 07:47:00.759661: step: 1636/530, loss: 0.005256242118775845
2023-01-24 07:47:01.865111: step: 1640/530, loss: 0.005322916433215141
2023-01-24 07:47:02.954405: step: 1644/530, loss: 0.0020510840695351362
2023-01-24 07:47:04.071684: step: 1648/530, loss: 0.004503228235989809
2023-01-24 07:47:05.153135: step: 1652/530, loss: 0.015600706450641155
2023-01-24 07:47:06.239286: step: 1656/530, loss: 0.008826656267046928
2023-01-24 07:47:07.311144: step: 1660/530, loss: 0.0005036370130255818
2023-01-24 07:47:08.407425: step: 1664/530, loss: 0.047386832535266876
2023-01-24 07:47:09.512493: step: 1668/530, loss: 0.023287741467356682
2023-01-24 07:47:10.632385: step: 1672/530, loss: 0.007491467986255884
2023-01-24 07:47:11.721327: step: 1676/530, loss: 0.004142443649470806
2023-01-24 07:47:12.804555: step: 1680/530, loss: 0.007098161615431309
2023-01-24 07:47:13.885157: step: 1684/530, loss: 0.002737255534157157
2023-01-24 07:47:14.988058: step: 1688/530, loss: 0.03544925898313522
2023-01-24 07:47:16.070795: step: 1692/530, loss: 0.03142731636762619
2023-01-24 07:47:17.166171: step: 1696/530, loss: 0.032398588955402374
2023-01-24 07:47:18.258465: step: 1700/530, loss: 0.0012969091767445207
2023-01-24 07:47:19.354490: step: 1704/530, loss: 0.002732472028583288
2023-01-24 07:47:20.438864: step: 1708/530, loss: 0.04723600298166275
2023-01-24 07:47:21.528522: step: 1712/530, loss: 0.00844617560505867
2023-01-24 07:47:22.621354: step: 1716/530, loss: 0.0008941101841628551
2023-01-24 07:47:23.737926: step: 1720/530, loss: 0.020552800968289375
2023-01-24 07:47:24.830161: step: 1724/530, loss: 0.009452478028833866
2023-01-24 07:47:25.940194: step: 1728/530, loss: 0.015093473717570305
2023-01-24 07:47:27.070222: step: 1732/530, loss: 0.029983708634972572
2023-01-24 07:47:28.173760: step: 1736/530, loss: 0.014131785370409489
2023-01-24 07:47:29.242903: step: 1740/530, loss: 0.009197235107421875
2023-01-24 07:47:30.345701: step: 1744/530, loss: 0.010480126366019249
2023-01-24 07:47:31.418560: step: 1748/530, loss: 0.009321744553744793
2023-01-24 07:47:32.523260: step: 1752/530, loss: 0.009413870051503181
2023-01-24 07:47:33.637506: step: 1756/530, loss: 0.01103140227496624
2023-01-24 07:47:34.717454: step: 1760/530, loss: 0.007739428896456957
2023-01-24 07:47:35.798840: step: 1764/530, loss: 0.01679868996143341
2023-01-24 07:47:36.895503: step: 1768/530, loss: 0.010832425206899643
2023-01-24 07:47:37.967969: step: 1772/530, loss: 0.0047462922520935535
2023-01-24 07:47:39.058152: step: 1776/530, loss: 0.004021686967462301
2023-01-24 07:47:40.134768: step: 1780/530, loss: 0.0
2023-01-24 07:47:41.214294: step: 1784/530, loss: 0.005754449404776096
2023-01-24 07:47:42.309471: step: 1788/530, loss: 0.030051853507757187
2023-01-24 07:47:43.417032: step: 1792/530, loss: 0.07881727069616318
2023-01-24 07:47:44.503422: step: 1796/530, loss: 0.006806483957916498
2023-01-24 07:47:45.620152: step: 1800/530, loss: 0.029210636392235756
2023-01-24 07:47:46.712464: step: 1804/530, loss: 0.0006344731664285064
2023-01-24 07:47:47.802825: step: 1808/530, loss: 0.005361342802643776
2023-01-24 07:47:48.883784: step: 1812/530, loss: 0.008182952180504799
2023-01-24 07:47:49.965874: step: 1816/530, loss: 0.004938941914588213
2023-01-24 07:47:51.065659: step: 1820/530, loss: 0.012819604948163033
2023-01-24 07:47:52.168282: step: 1824/530, loss: 0.049621012061834335
2023-01-24 07:47:53.265042: step: 1828/530, loss: 0.004920081701129675
2023-01-24 07:47:54.362618: step: 1832/530, loss: 0.04681029170751572
2023-01-24 07:47:55.485135: step: 1836/530, loss: 0.010457811877131462
2023-01-24 07:47:56.601882: step: 1840/530, loss: 0.004233458545058966
2023-01-24 07:47:57.680878: step: 1844/530, loss: 0.025596261024475098
2023-01-24 07:47:58.748496: step: 1848/530, loss: 0.00549063365906477
2023-01-24 07:47:59.834912: step: 1852/530, loss: 0.00705106183886528
2023-01-24 07:48:00.916860: step: 1856/530, loss: 0.0004364947963040322
2023-01-24 07:48:02.024161: step: 1860/530, loss: 0.01021557580679655
2023-01-24 07:48:03.111846: step: 1864/530, loss: 0.0017422246746718884
2023-01-24 07:48:04.193702: step: 1868/530, loss: 0.0041860612109303474
2023-01-24 07:48:05.264709: step: 1872/530, loss: 0.04310573637485504
2023-01-24 07:48:06.380487: step: 1876/530, loss: 0.020023928955197334
2023-01-24 07:48:07.473202: step: 1880/530, loss: 0.00489689689129591
2023-01-24 07:48:08.570485: step: 1884/530, loss: 0.027558067813515663
2023-01-24 07:48:09.673094: step: 1888/530, loss: 0.006431622430682182
2023-01-24 07:48:10.763455: step: 1892/530, loss: 0.021379824727773666
2023-01-24 07:48:11.863499: step: 1896/530, loss: 0.009161487221717834
2023-01-24 07:48:12.942012: step: 1900/530, loss: 0.008073671720921993
2023-01-24 07:48:14.017873: step: 1904/530, loss: 0.004906642250716686
2023-01-24 07:48:15.091939: step: 1908/530, loss: 0.0034442346077412367
2023-01-24 07:48:16.171627: step: 1912/530, loss: 0.0037114170845597982
2023-01-24 07:48:17.255689: step: 1916/530, loss: 0.0037614472676068544
2023-01-24 07:48:18.309719: step: 1920/530, loss: 0.029696006327867508
2023-01-24 07:48:19.402364: step: 1924/530, loss: 0.011749030090868473
2023-01-24 07:48:20.478265: step: 1928/530, loss: 0.011213784106075764
2023-01-24 07:48:21.561977: step: 1932/530, loss: 0.0029136526864022017
2023-01-24 07:48:22.681288: step: 1936/530, loss: 0.0045543755404651165
2023-01-24 07:48:23.756380: step: 1940/530, loss: 0.013390528038144112
2023-01-24 07:48:24.844849: step: 1944/530, loss: 0.017309991642832756
2023-01-24 07:48:25.984486: step: 1948/530, loss: 0.05734814703464508
2023-01-24 07:48:27.071807: step: 1952/530, loss: 0.01196904294192791
2023-01-24 07:48:28.133375: step: 1956/530, loss: 0.022607866674661636
2023-01-24 07:48:29.213674: step: 1960/530, loss: 0.018757633864879608
2023-01-24 07:48:30.310947: step: 1964/530, loss: 0.009620281867682934
2023-01-24 07:48:31.414860: step: 1968/530, loss: 0.005232736933976412
2023-01-24 07:48:32.537922: step: 1972/530, loss: 0.008973057381808758
2023-01-24 07:48:33.618835: step: 1976/530, loss: 0.0034213506150990725
2023-01-24 07:48:34.714441: step: 1980/530, loss: 0.006188738625496626
2023-01-24 07:48:35.805689: step: 1984/530, loss: 0.004274419974535704
2023-01-24 07:48:36.896715: step: 1988/530, loss: 0.0032662139274179935
2023-01-24 07:48:37.987070: step: 1992/530, loss: 0.003156520426273346
2023-01-24 07:48:39.062427: step: 1996/530, loss: 0.010001575574278831
2023-01-24 07:48:40.172783: step: 2000/530, loss: 0.010153896175324917
2023-01-24 07:48:41.253355: step: 2004/530, loss: 0.02358771115541458
2023-01-24 07:48:42.362888: step: 2008/530, loss: 0.006304414942860603
2023-01-24 07:48:43.455777: step: 2012/530, loss: 0.027232374995946884
2023-01-24 07:48:44.539163: step: 2016/530, loss: 0.0059166159480810165
2023-01-24 07:48:45.623635: step: 2020/530, loss: 0.002335348166525364
2023-01-24 07:48:46.707758: step: 2024/530, loss: 0.005618598777800798
2023-01-24 07:48:47.799301: step: 2028/530, loss: 0.008079351857304573
2023-01-24 07:48:48.896966: step: 2032/530, loss: 0.0045247129164636135
2023-01-24 07:48:49.973835: step: 2036/530, loss: 0.018133796751499176
2023-01-24 07:48:51.059127: step: 2040/530, loss: 0.007943114265799522
2023-01-24 07:48:52.131668: step: 2044/530, loss: 0.014843118377029896
2023-01-24 07:48:53.210837: step: 2048/530, loss: 0.0059630656614899635
2023-01-24 07:48:54.309308: step: 2052/530, loss: 0.006998266093432903
2023-01-24 07:48:55.393421: step: 2056/530, loss: 0.012137621641159058
2023-01-24 07:48:56.465568: step: 2060/530, loss: 0.002685179701074958
2023-01-24 07:48:57.569830: step: 2064/530, loss: 0.005768399219959974
2023-01-24 07:48:58.666840: step: 2068/530, loss: 0.019703621044754982
2023-01-24 07:48:59.779389: step: 2072/530, loss: 0.0068180011585354805
2023-01-24 07:49:00.870438: step: 2076/530, loss: 0.0011532928328961134
2023-01-24 07:49:01.955324: step: 2080/530, loss: 0.007384370546787977
2023-01-24 07:49:03.056066: step: 2084/530, loss: 0.00564651470631361
2023-01-24 07:49:04.124877: step: 2088/530, loss: 0.004955998156219721
2023-01-24 07:49:05.226561: step: 2092/530, loss: 0.006114862393587828
2023-01-24 07:49:06.309859: step: 2096/530, loss: 0.006418767850846052
2023-01-24 07:49:07.378135: step: 2100/530, loss: 0.003920678980648518
2023-01-24 07:49:08.458035: step: 2104/530, loss: 0.0072768740355968475
2023-01-24 07:49:09.549786: step: 2108/530, loss: 0.006788167636841536
2023-01-24 07:49:10.667285: step: 2112/530, loss: 0.0168886911123991
2023-01-24 07:49:11.753328: step: 2116/530, loss: 0.012799182906746864
2023-01-24 07:49:12.872429: step: 2120/530, loss: 0.089204341173172
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34585725240974635, 'r': 0.34388842554593374, 'f1': 0.3448700290441619}, 'combined': 0.2541147582430667, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3462225312925746, 'r': 0.27533423853534117, 'f1': 0.3067359946658181}, 'combined': 0.19049919668719228, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3850182178932179, 'r': 0.32876318415929423, 'f1': 0.3546738957051137}, 'combined': 0.2613386599932417, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3355763585730524, 'r': 0.2629565734668286, 'f1': 0.29486099983205605}, 'combined': 0.18312419989569798, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37727603010831046, 'r': 0.32501578305345913, 'f1': 0.3492014631379673}, 'combined': 0.2573063412595548, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34759940929004546, 'r': 0.2697069454116246, 'f1': 0.3037388946103121}, 'combined': 0.1886378398106149, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.38, 'r': 0.41304347826086957, 'f1': 0.39583333333333337}, 'combined': 0.19791666666666669, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 2}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35384310730622737, 'r': 0.34578595875276485, 'f1': 0.3497681387000136}, 'combined': 0.25772389167369425, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34016676933404005, 'r': 0.26816312083009886, 'f1': 0.2999036672115375}, 'combined': 0.18625596174190226, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3906081588479548, 'r': 0.3268656509524631, 'f1': 0.3559053678759258}, 'combined': 0.26224606054015587, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3365587402403451, 'r': 0.2607332533087258, 'f1': 0.2938330204325507}, 'combined': 0.18248577058442625, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3818011606932129, 'r': 0.323118249846628, 'f1': 0.35001709695616234}, 'combined': 0.2579073345992775, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34522140115342165, 'r': 0.2664986532102426, 'f1': 0.30079458016933225}, 'combined': 0.18680926557884847, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:51:39.584001: step: 4/530, loss: 0.002227536402642727
2023-01-24 07:51:40.657024: step: 8/530, loss: 0.016790607944130898
2023-01-24 07:51:41.720026: step: 12/530, loss: 0.004460806958377361
2023-01-24 07:51:42.803964: step: 16/530, loss: 0.0032792179845273495
2023-01-24 07:51:43.877634: step: 20/530, loss: 0.003597506321966648
2023-01-24 07:51:44.954859: step: 24/530, loss: 0.010008974000811577
2023-01-24 07:51:46.057669: step: 28/530, loss: 0.009772967547178268
2023-01-24 07:51:47.136301: step: 32/530, loss: 0.009915060363709927
2023-01-24 07:51:48.235715: step: 36/530, loss: 0.006194828078150749
2023-01-24 07:51:49.338469: step: 40/530, loss: 0.00501536438241601
2023-01-24 07:51:50.425734: step: 44/530, loss: 0.006514077540487051
2023-01-24 07:51:51.521518: step: 48/530, loss: 0.013056674972176552
2023-01-24 07:51:52.590222: step: 52/530, loss: 0.0034928987734019756
2023-01-24 07:51:53.666084: step: 56/530, loss: 0.01233162172138691
2023-01-24 07:51:54.726143: step: 60/530, loss: 0.00442137848585844
2023-01-24 07:51:55.778694: step: 64/530, loss: 0.002346806926652789
2023-01-24 07:51:56.871423: step: 68/530, loss: 0.030737319961190224
2023-01-24 07:51:57.950355: step: 72/530, loss: 0.009473285637795925
2023-01-24 07:51:59.062539: step: 76/530, loss: 0.029489140957593918
2023-01-24 07:52:00.138736: step: 80/530, loss: 0.006130874156951904
2023-01-24 07:52:01.219711: step: 84/530, loss: 0.00369679881259799
2023-01-24 07:52:02.296940: step: 88/530, loss: 0.04161631315946579
2023-01-24 07:52:03.382922: step: 92/530, loss: 0.057136762887239456
2023-01-24 07:52:04.481769: step: 96/530, loss: 0.0024038327392190695
2023-01-24 07:52:05.589742: step: 100/530, loss: 0.006832140497863293
2023-01-24 07:52:06.662918: step: 104/530, loss: 0.04319263994693756
2023-01-24 07:52:07.761709: step: 108/530, loss: 0.007719225715845823
2023-01-24 07:52:08.864736: step: 112/530, loss: 0.03820951282978058
2023-01-24 07:52:09.944221: step: 116/530, loss: 0.007090891245752573
2023-01-24 07:52:11.027508: step: 120/530, loss: 0.0029282455798238516
2023-01-24 07:52:12.128363: step: 124/530, loss: 0.0031002552714198828
2023-01-24 07:52:13.192737: step: 128/530, loss: 0.01766994036734104
2023-01-24 07:52:14.302939: step: 132/530, loss: 0.10048720985651016
2023-01-24 07:52:15.387338: step: 136/530, loss: 0.007003552280366421
2023-01-24 07:52:16.456133: step: 140/530, loss: 0.0016844915226101875
2023-01-24 07:52:17.521831: step: 144/530, loss: 0.0023643632885068655
2023-01-24 07:52:18.609511: step: 148/530, loss: 0.004746571183204651
2023-01-24 07:52:19.698617: step: 152/530, loss: 0.004188341088593006
2023-01-24 07:52:20.790814: step: 156/530, loss: 0.013090483844280243
2023-01-24 07:52:21.886955: step: 160/530, loss: 0.0031739817932248116
2023-01-24 07:52:22.960212: step: 164/530, loss: 0.005898940376937389
2023-01-24 07:52:24.029400: step: 168/530, loss: 0.02599339932203293
2023-01-24 07:52:25.136874: step: 172/530, loss: 0.010433711111545563
2023-01-24 07:52:26.225748: step: 176/530, loss: 0.016894489526748657
2023-01-24 07:52:27.311698: step: 180/530, loss: 0.0037484883796423674
2023-01-24 07:52:28.430467: step: 184/530, loss: 0.040714994072914124
2023-01-24 07:52:29.507072: step: 188/530, loss: 0.00013284954184200615
2023-01-24 07:52:30.597589: step: 192/530, loss: 0.009761529043316841
2023-01-24 07:52:31.671421: step: 196/530, loss: 0.0040414780378341675
2023-01-24 07:52:32.760970: step: 200/530, loss: 0.0032499758526682854
2023-01-24 07:52:33.855591: step: 204/530, loss: 0.006838515866547823
2023-01-24 07:52:34.940402: step: 208/530, loss: 0.0016300976276397705
2023-01-24 07:52:36.015885: step: 212/530, loss: 0.017263047397136688
2023-01-24 07:52:37.113700: step: 216/530, loss: 0.005723776761442423
2023-01-24 07:52:38.183585: step: 220/530, loss: 0.007065284997224808
2023-01-24 07:52:39.292950: step: 224/530, loss: 0.0019440948963165283
2023-01-24 07:52:40.379049: step: 228/530, loss: 0.0034122595097869635
2023-01-24 07:52:41.469484: step: 232/530, loss: 0.014555097557604313
2023-01-24 07:52:42.555250: step: 236/530, loss: 0.029644416645169258
2023-01-24 07:52:43.636290: step: 240/530, loss: 0.009609824046492577
2023-01-24 07:52:44.725420: step: 244/530, loss: 0.00654362328350544
2023-01-24 07:52:45.860183: step: 248/530, loss: 0.061627987772226334
2023-01-24 07:52:46.942054: step: 252/530, loss: 0.03641989454627037
2023-01-24 07:52:48.026925: step: 256/530, loss: 0.004374881274998188
2023-01-24 07:52:49.140897: step: 260/530, loss: 0.030204875394701958
2023-01-24 07:52:50.216562: step: 264/530, loss: 0.004012828227132559
2023-01-24 07:52:51.302160: step: 268/530, loss: 0.006058164872229099
2023-01-24 07:52:52.378931: step: 272/530, loss: 0.002543671755120158
2023-01-24 07:52:53.451941: step: 276/530, loss: 0.006091054528951645
2023-01-24 07:52:54.560101: step: 280/530, loss: 0.024719322100281715
2023-01-24 07:52:55.635477: step: 284/530, loss: 0.014802731573581696
2023-01-24 07:52:56.753969: step: 288/530, loss: 0.014300837181508541
2023-01-24 07:52:57.856694: step: 292/530, loss: 0.009814117103815079
2023-01-24 07:52:58.957818: step: 296/530, loss: 0.0059904539957642555
2023-01-24 07:53:00.044654: step: 300/530, loss: 0.023650934919714928
2023-01-24 07:53:01.116204: step: 304/530, loss: 0.009037637151777744
2023-01-24 07:53:02.213296: step: 308/530, loss: 0.014698131009936333
2023-01-24 07:53:03.285737: step: 312/530, loss: 0.00847918912768364
2023-01-24 07:53:04.357864: step: 316/530, loss: 0.01754039339721203
2023-01-24 07:53:05.410688: step: 320/530, loss: 0.00804224144667387
2023-01-24 07:53:06.494417: step: 324/530, loss: 0.005646221339702606
2023-01-24 07:53:07.578585: step: 328/530, loss: 0.004300011321902275
2023-01-24 07:53:08.684793: step: 332/530, loss: 0.005537185352295637
2023-01-24 07:53:09.752334: step: 336/530, loss: 0.012691509909927845
2023-01-24 07:53:10.825487: step: 340/530, loss: 0.009244035929441452
2023-01-24 07:53:11.896241: step: 344/530, loss: 0.003927251324057579
2023-01-24 07:53:12.973039: step: 348/530, loss: 0.011134376749396324
2023-01-24 07:53:14.058943: step: 352/530, loss: 0.009228087030351162
2023-01-24 07:53:15.132136: step: 356/530, loss: 0.005150577053427696
2023-01-24 07:53:16.232943: step: 360/530, loss: 0.006937472149729729
2023-01-24 07:53:17.315170: step: 364/530, loss: 0.0025320244021713734
2023-01-24 07:53:18.373267: step: 368/530, loss: 0.009534927085042
2023-01-24 07:53:19.476497: step: 372/530, loss: 0.00988983828574419
2023-01-24 07:53:20.566491: step: 376/530, loss: 0.004799413960427046
2023-01-24 07:53:21.636992: step: 380/530, loss: 0.004854446742683649
2023-01-24 07:53:22.712774: step: 384/530, loss: 0.0008865715935826302
2023-01-24 07:53:23.831522: step: 388/530, loss: 0.010974948294460773
2023-01-24 07:53:24.914169: step: 392/530, loss: 0.005058357026427984
2023-01-24 07:53:25.995019: step: 396/530, loss: 0.0010100967483595014
2023-01-24 07:53:27.076353: step: 400/530, loss: 0.019582092761993408
2023-01-24 07:53:28.156172: step: 404/530, loss: 0.0027957975398749113
2023-01-24 07:53:29.244277: step: 408/530, loss: 0.009675396606326103
2023-01-24 07:53:30.325807: step: 412/530, loss: 0.005329884588718414
2023-01-24 07:53:31.426403: step: 416/530, loss: 0.010127348825335503
2023-01-24 07:53:32.514284: step: 420/530, loss: 0.006457071285694838
2023-01-24 07:53:33.600658: step: 424/530, loss: 0.029611095786094666
2023-01-24 07:53:34.714379: step: 428/530, loss: 0.015631312504410744
2023-01-24 07:53:35.784143: step: 432/530, loss: 0.006112556904554367
2023-01-24 07:53:36.880220: step: 436/530, loss: 0.0060873571783304214
2023-01-24 07:53:37.955602: step: 440/530, loss: 0.002243014285340905
2023-01-24 07:53:39.033928: step: 444/530, loss: 0.01817476376891136
2023-01-24 07:53:40.114806: step: 448/530, loss: 0.00849417969584465
2023-01-24 07:53:41.203294: step: 452/530, loss: 0.005257307086139917
2023-01-24 07:53:42.289870: step: 456/530, loss: 0.005071935709565878
2023-01-24 07:53:43.369399: step: 460/530, loss: 0.007713960018008947
2023-01-24 07:53:44.462653: step: 464/530, loss: 0.0037115723825991154
2023-01-24 07:53:45.535330: step: 468/530, loss: 0.0075607746839523315
2023-01-24 07:53:46.610291: step: 472/530, loss: 0.008396073244512081
2023-01-24 07:53:47.705673: step: 476/530, loss: 0.003240798832848668
2023-01-24 07:53:48.763019: step: 480/530, loss: 0.0022829517256468534
2023-01-24 07:53:49.862158: step: 484/530, loss: 0.0071618156507611275
2023-01-24 07:53:50.958139: step: 488/530, loss: 0.0022120859939604998
2023-01-24 07:53:52.029676: step: 492/530, loss: 0.005249615292996168
2023-01-24 07:53:53.110493: step: 496/530, loss: 0.008912590332329273
2023-01-24 07:53:54.218693: step: 500/530, loss: 0.004269557073712349
2023-01-24 07:53:55.295781: step: 504/530, loss: 0.004679122939705849
2023-01-24 07:53:56.381065: step: 508/530, loss: 0.002990277949720621
2023-01-24 07:53:57.474661: step: 512/530, loss: 0.008443482220172882
2023-01-24 07:53:58.573055: step: 516/530, loss: 0.002614922821521759
2023-01-24 07:53:59.644368: step: 520/530, loss: 0.015633730217814445
2023-01-24 07:54:00.744649: step: 524/530, loss: 0.010473628528416157
2023-01-24 07:54:01.822093: step: 528/530, loss: 0.0025497088208794594
2023-01-24 07:54:02.895092: step: 532/530, loss: 0.0094808554276824
2023-01-24 07:54:03.982895: step: 536/530, loss: 0.03716466948390007
2023-01-24 07:54:05.069009: step: 540/530, loss: 0.00557212857529521
2023-01-24 07:54:06.167880: step: 544/530, loss: 0.009412577375769615
2023-01-24 07:54:07.234980: step: 548/530, loss: 0.013018887490034103
2023-01-24 07:54:08.328084: step: 552/530, loss: 0.008328845724463463
2023-01-24 07:54:09.386536: step: 556/530, loss: 0.005064348690211773
2023-01-24 07:54:10.465668: step: 560/530, loss: 0.006493042688816786
2023-01-24 07:54:11.567144: step: 564/530, loss: 0.013318916782736778
2023-01-24 07:54:12.666216: step: 568/530, loss: 0.005416987929493189
2023-01-24 07:54:13.739890: step: 572/530, loss: 0.006717041600495577
2023-01-24 07:54:14.826759: step: 576/530, loss: 0.0030994806438684464
2023-01-24 07:54:15.937455: step: 580/530, loss: 0.006757744122296572
2023-01-24 07:54:17.012043: step: 584/530, loss: 0.008027574978768826
2023-01-24 07:54:18.113467: step: 588/530, loss: 0.007547580637037754
2023-01-24 07:54:19.187226: step: 592/530, loss: 0.0038620911072939634
2023-01-24 07:54:20.292669: step: 596/530, loss: 0.006576234009116888
2023-01-24 07:54:21.357910: step: 600/530, loss: 0.009168741293251514
2023-01-24 07:54:22.436446: step: 604/530, loss: 0.008811403065919876
2023-01-24 07:54:23.521649: step: 608/530, loss: 0.006936532910913229
2023-01-24 07:54:24.603510: step: 612/530, loss: 0.011735818348824978
2023-01-24 07:54:25.688052: step: 616/530, loss: 0.04981715977191925
2023-01-24 07:54:26.777658: step: 620/530, loss: 0.016454385593533516
2023-01-24 07:54:27.850640: step: 624/530, loss: 0.030957506969571114
2023-01-24 07:54:28.958983: step: 628/530, loss: 0.0008294227300211787
2023-01-24 07:54:30.049971: step: 632/530, loss: 0.01704142801463604
2023-01-24 07:54:31.140488: step: 636/530, loss: 0.02974986471235752
2023-01-24 07:54:32.204206: step: 640/530, loss: 0.004496879409998655
2023-01-24 07:54:33.276219: step: 644/530, loss: 0.0016910843551158905
2023-01-24 07:54:34.343707: step: 648/530, loss: 0.008565268479287624
2023-01-24 07:54:35.446063: step: 652/530, loss: 0.01379690133035183
2023-01-24 07:54:36.522156: step: 656/530, loss: 0.010884171351790428
2023-01-24 07:54:37.602430: step: 660/530, loss: 0.009911797009408474
2023-01-24 07:54:38.686046: step: 664/530, loss: 0.0036713872104883194
2023-01-24 07:54:39.752740: step: 668/530, loss: 0.015017013065516949
2023-01-24 07:54:40.832301: step: 672/530, loss: 0.01850060746073723
2023-01-24 07:54:41.909132: step: 676/530, loss: 0.028786921873688698
2023-01-24 07:54:42.989509: step: 680/530, loss: 0.004183605313301086
2023-01-24 07:54:44.078179: step: 684/530, loss: 0.0015425084857270122
2023-01-24 07:54:45.184795: step: 688/530, loss: 0.006054719444364309
2023-01-24 07:54:46.301900: step: 692/530, loss: 0.0034743899013847113
2023-01-24 07:54:47.389869: step: 696/530, loss: 0.00018592907872516662
2023-01-24 07:54:48.486610: step: 700/530, loss: 0.007415073923766613
2023-01-24 07:54:49.587319: step: 704/530, loss: 0.006361925508826971
2023-01-24 07:54:50.667853: step: 708/530, loss: 0.0045522344298660755
2023-01-24 07:54:51.752831: step: 712/530, loss: 0.005137616768479347
2023-01-24 07:54:52.805203: step: 716/530, loss: 0.003768669441342354
2023-01-24 07:54:53.880549: step: 720/530, loss: 0.0023649167269468307
2023-01-24 07:54:54.947406: step: 724/530, loss: 0.0017330496339127421
2023-01-24 07:54:56.017833: step: 728/530, loss: 0.0021172247361391783
2023-01-24 07:54:57.107119: step: 732/530, loss: 0.00999140739440918
2023-01-24 07:54:58.179648: step: 736/530, loss: 0.0037728685420006514
2023-01-24 07:54:59.263974: step: 740/530, loss: 0.009008875116705894
2023-01-24 07:55:00.379299: step: 744/530, loss: 0.003614150919020176
2023-01-24 07:55:01.455383: step: 748/530, loss: 0.013678636401891708
2023-01-24 07:55:02.544084: step: 752/530, loss: 0.0148874931037426
2023-01-24 07:55:03.640543: step: 756/530, loss: 0.011193053796887398
2023-01-24 07:55:04.721266: step: 760/530, loss: 0.007567123509943485
2023-01-24 07:55:05.814178: step: 764/530, loss: 0.0033964584581553936
2023-01-24 07:55:06.878974: step: 768/530, loss: 0.013261942192912102
2023-01-24 07:55:07.971445: step: 772/530, loss: 0.00231935759074986
2023-01-24 07:55:09.052953: step: 776/530, loss: 0.00519409216940403
2023-01-24 07:55:10.155210: step: 780/530, loss: 0.007931515574455261
2023-01-24 07:55:11.241782: step: 784/530, loss: 0.005752062890678644
2023-01-24 07:55:12.311204: step: 788/530, loss: 0.0019751957152038813
2023-01-24 07:55:13.392159: step: 792/530, loss: 0.008055678568780422
2023-01-24 07:55:14.475777: step: 796/530, loss: 0.008411243557929993
2023-01-24 07:55:15.584966: step: 800/530, loss: 0.003742727916687727
2023-01-24 07:55:16.652805: step: 804/530, loss: 0.004822937306016684
2023-01-24 07:55:17.714086: step: 808/530, loss: 0.0022399635054171085
2023-01-24 07:55:18.802569: step: 812/530, loss: 0.019668443128466606
2023-01-24 07:55:19.869000: step: 816/530, loss: 0.0051964991725981236
2023-01-24 07:55:20.963060: step: 820/530, loss: 0.018342772498726845
2023-01-24 07:55:22.048142: step: 824/530, loss: 0.0077751497738063335
2023-01-24 07:55:23.143814: step: 828/530, loss: 0.006631223019212484
2023-01-24 07:55:24.217024: step: 832/530, loss: 0.0105736143887043
2023-01-24 07:55:25.303485: step: 836/530, loss: 0.0051844073459506035
2023-01-24 07:55:26.377275: step: 840/530, loss: 0.007381302770227194
2023-01-24 07:55:27.458002: step: 844/530, loss: 0.0031810072250664234
2023-01-24 07:55:28.532039: step: 848/530, loss: 0.008050918579101562
2023-01-24 07:55:29.620411: step: 852/530, loss: 0.013539256528019905
2023-01-24 07:55:30.693528: step: 856/530, loss: 0.013206942938268185
2023-01-24 07:55:31.779702: step: 860/530, loss: 0.0062510352581739426
2023-01-24 07:55:32.855926: step: 864/530, loss: 0.008488173596560955
2023-01-24 07:55:33.960588: step: 868/530, loss: 0.008705228567123413
2023-01-24 07:55:35.065571: step: 872/530, loss: 0.020819269120693207
2023-01-24 07:55:36.156809: step: 876/530, loss: 0.0020449236035346985
2023-01-24 07:55:37.236820: step: 880/530, loss: 0.014308874495327473
2023-01-24 07:55:38.318863: step: 884/530, loss: 0.0024342637043446302
2023-01-24 07:55:39.389516: step: 888/530, loss: 0.008903756737709045
2023-01-24 07:55:40.445054: step: 892/530, loss: 0.02250978909432888
2023-01-24 07:55:41.553845: step: 896/530, loss: 0.003295569447800517
2023-01-24 07:55:42.652525: step: 900/530, loss: 0.007382961921393871
2023-01-24 07:55:43.725374: step: 904/530, loss: 0.003065861063078046
2023-01-24 07:55:44.796613: step: 908/530, loss: 0.010868741199374199
2023-01-24 07:55:45.892979: step: 912/530, loss: 0.004745489917695522
2023-01-24 07:55:46.974274: step: 916/530, loss: 0.01935676485300064
2023-01-24 07:55:48.053883: step: 920/530, loss: 0.011972932144999504
2023-01-24 07:55:49.128134: step: 924/530, loss: 0.00022512185387313366
2023-01-24 07:55:50.220403: step: 928/530, loss: 0.010233130306005478
2023-01-24 07:55:51.283428: step: 932/530, loss: 0.0018110991222783923
2023-01-24 07:55:52.359736: step: 936/530, loss: 0.007435475941747427
2023-01-24 07:55:53.427856: step: 940/530, loss: 0.002791812876239419
2023-01-24 07:55:54.522660: step: 944/530, loss: 0.004688797052949667
2023-01-24 07:55:55.601573: step: 948/530, loss: 0.005692686419934034
2023-01-24 07:55:56.690194: step: 952/530, loss: 0.018047353252768517
2023-01-24 07:55:57.774414: step: 956/530, loss: 0.0005185452173464
2023-01-24 07:55:58.882238: step: 960/530, loss: 0.04479311406612396
2023-01-24 07:55:59.959241: step: 964/530, loss: 0.038241881877183914
2023-01-24 07:56:01.050928: step: 968/530, loss: 0.009267397224903107
2023-01-24 07:56:02.116063: step: 972/530, loss: 0.0055338190868496895
2023-01-24 07:56:03.180014: step: 976/530, loss: 0.003924527671188116
2023-01-24 07:56:04.260825: step: 980/530, loss: 0.004754830151796341
2023-01-24 07:56:05.341719: step: 984/530, loss: 0.03573412075638771
2023-01-24 07:56:06.423415: step: 988/530, loss: 0.008589028380811214
2023-01-24 07:56:07.490098: step: 992/530, loss: 0.006674485746771097
2023-01-24 07:56:08.570725: step: 996/530, loss: 0.0007309062057174742
2023-01-24 07:56:09.685980: step: 1000/530, loss: 0.013067721389234066
2023-01-24 07:56:10.766746: step: 1004/530, loss: 0.012321450747549534
2023-01-24 07:56:11.862013: step: 1008/530, loss: 0.011038108728826046
2023-01-24 07:56:12.934489: step: 1012/530, loss: 0.015308350324630737
2023-01-24 07:56:14.023185: step: 1016/530, loss: 0.00011961118434555829
2023-01-24 07:56:15.117845: step: 1020/530, loss: 0.006224613171070814
2023-01-24 07:56:16.211253: step: 1024/530, loss: 0.006144258659332991
2023-01-24 07:56:17.319377: step: 1028/530, loss: 0.004497601184993982
2023-01-24 07:56:18.393505: step: 1032/530, loss: 0.007542679086327553
2023-01-24 07:56:19.480994: step: 1036/530, loss: 0.0030587154906243086
2023-01-24 07:56:20.561051: step: 1040/530, loss: 0.00018483679741621017
2023-01-24 07:56:21.648014: step: 1044/530, loss: 0.007949182763695717
2023-01-24 07:56:22.745566: step: 1048/530, loss: 0.04049225151538849
2023-01-24 07:56:23.818457: step: 1052/530, loss: 0.035482801496982574
2023-01-24 07:56:24.903583: step: 1056/530, loss: 0.0017006665002554655
2023-01-24 07:56:25.986756: step: 1060/530, loss: 0.05259407311677933
2023-01-24 07:56:27.072445: step: 1064/530, loss: 0.010258263908326626
2023-01-24 07:56:28.176128: step: 1068/530, loss: 0.004466751124709845
2023-01-24 07:56:29.245229: step: 1072/530, loss: 0.01392581406980753
2023-01-24 07:56:30.319805: step: 1076/530, loss: 0.0017227617790922523
2023-01-24 07:56:31.419987: step: 1080/530, loss: 0.004666168242692947
2023-01-24 07:56:32.508873: step: 1084/530, loss: 0.010201828554272652
2023-01-24 07:56:33.602516: step: 1088/530, loss: 0.0020840181969106197
2023-01-24 07:56:34.666430: step: 1092/530, loss: 0.005235451273620129
2023-01-24 07:56:35.746171: step: 1096/530, loss: 0.013133256696164608
2023-01-24 07:56:36.837492: step: 1100/530, loss: 0.020084798336029053
2023-01-24 07:56:37.927741: step: 1104/530, loss: 0.009468114003539085
2023-01-24 07:56:39.025214: step: 1108/530, loss: 0.00959616620093584
2023-01-24 07:56:40.130657: step: 1112/530, loss: 0.007817719131708145
2023-01-24 07:56:41.219852: step: 1116/530, loss: 0.011656277813017368
2023-01-24 07:56:42.314677: step: 1120/530, loss: 0.03768749535083771
2023-01-24 07:56:43.408351: step: 1124/530, loss: 0.0026087763253599405
2023-01-24 07:56:44.505432: step: 1128/530, loss: 0.024585768580436707
2023-01-24 07:56:45.570111: step: 1132/530, loss: 0.010689685121178627
2023-01-24 07:56:46.668192: step: 1136/530, loss: 0.010371686890721321
2023-01-24 07:56:47.756972: step: 1140/530, loss: 0.011005585081875324
2023-01-24 07:56:48.834295: step: 1144/530, loss: 0.005857882089912891
2023-01-24 07:56:49.912054: step: 1148/530, loss: 0.004124849569052458
2023-01-24 07:56:51.012338: step: 1152/530, loss: 1.5140353752940428e-06
2023-01-24 07:56:52.094099: step: 1156/530, loss: 0.012998753227293491
2023-01-24 07:56:53.177198: step: 1160/530, loss: 0.003946313168853521
2023-01-24 07:56:54.277596: step: 1164/530, loss: 0.029805080965161324
2023-01-24 07:56:55.376716: step: 1168/530, loss: 0.006880226545035839
2023-01-24 07:56:56.476764: step: 1172/530, loss: 0.08833377063274384
2023-01-24 07:56:57.554617: step: 1176/530, loss: 0.004376439843326807
2023-01-24 07:56:58.644540: step: 1180/530, loss: 0.02380470745265484
2023-01-24 07:56:59.717156: step: 1184/530, loss: 0.012658650055527687
2023-01-24 07:57:00.810108: step: 1188/530, loss: 0.008989873342216015
2023-01-24 07:57:01.877043: step: 1192/530, loss: 0.0018720749067142606
2023-01-24 07:57:02.960196: step: 1196/530, loss: 0.004735585767775774
2023-01-24 07:57:04.056299: step: 1200/530, loss: 0.02861524559557438
2023-01-24 07:57:05.139817: step: 1204/530, loss: 0.006515833083540201
2023-01-24 07:57:06.209350: step: 1208/530, loss: 0.0020132747013121843
2023-01-24 07:57:07.301268: step: 1212/530, loss: 0.0008755850722081959
2023-01-24 07:57:08.381906: step: 1216/530, loss: 7.4505797087454084e-09
2023-01-24 07:57:09.450854: step: 1220/530, loss: 0.06438211351633072
2023-01-24 07:57:10.526974: step: 1224/530, loss: 0.04198005422949791
2023-01-24 07:57:11.593591: step: 1228/530, loss: 0.0
2023-01-24 07:57:12.682828: step: 1232/530, loss: 0.00632608262822032
2023-01-24 07:57:13.771235: step: 1236/530, loss: 0.02386266179382801
2023-01-24 07:57:14.832888: step: 1240/530, loss: 0.005555871408432722
2023-01-24 07:57:15.921106: step: 1244/530, loss: 0.014315348118543625
2023-01-24 07:57:16.992098: step: 1248/530, loss: 0.02399740181863308
2023-01-24 07:57:18.077441: step: 1252/530, loss: 0.003911165986210108
2023-01-24 07:57:19.195206: step: 1256/530, loss: 0.00886138528585434
2023-01-24 07:57:20.279970: step: 1260/530, loss: 0.011854602955281734
2023-01-24 07:57:21.363539: step: 1264/530, loss: 0.02003047801554203
2023-01-24 07:57:22.451850: step: 1268/530, loss: 0.0033985127229243517
2023-01-24 07:57:23.536406: step: 1272/530, loss: 0.027946490794420242
2023-01-24 07:57:24.620733: step: 1276/530, loss: 0.0068738083355128765
2023-01-24 07:57:25.696700: step: 1280/530, loss: 0.004011850338429213
2023-01-24 07:57:26.791411: step: 1284/530, loss: 0.02610250562429428
2023-01-24 07:57:27.891947: step: 1288/530, loss: 0.01805303804576397
2023-01-24 07:57:28.958797: step: 1292/530, loss: 0.009144733659923077
2023-01-24 07:57:30.054699: step: 1296/530, loss: 0.004507117904722691
2023-01-24 07:57:31.175848: step: 1300/530, loss: 0.03221559897065163
2023-01-24 07:57:32.245419: step: 1304/530, loss: 0.0018386135343462229
2023-01-24 07:57:33.310501: step: 1308/530, loss: 0.006673126481473446
2023-01-24 07:57:34.395838: step: 1312/530, loss: 0.009045238606631756
2023-01-24 07:57:35.479668: step: 1316/530, loss: 0.0011634668335318565
2023-01-24 07:57:36.564687: step: 1320/530, loss: 0.004658046644181013
2023-01-24 07:57:37.652105: step: 1324/530, loss: 0.0025051843840628862
2023-01-24 07:57:38.736051: step: 1328/530, loss: 0.002556690014898777
2023-01-24 07:57:39.811971: step: 1332/530, loss: 0.0105762779712677
2023-01-24 07:57:40.900078: step: 1336/530, loss: 0.03093128465116024
2023-01-24 07:57:41.999068: step: 1340/530, loss: 0.006454716436564922
2023-01-24 07:57:43.075019: step: 1344/530, loss: 0.0022223638370633125
2023-01-24 07:57:44.150411: step: 1348/530, loss: 0.014794566668570042
2023-01-24 07:57:45.234022: step: 1352/530, loss: 0.006150797475129366
2023-01-24 07:57:46.315866: step: 1356/530, loss: 0.047473419457674026
2023-01-24 07:57:47.421005: step: 1360/530, loss: 0.009126752614974976
2023-01-24 07:57:48.512334: step: 1364/530, loss: 0.005281102377921343
2023-01-24 07:57:49.599324: step: 1368/530, loss: 0.03255490958690643
2023-01-24 07:57:50.709104: step: 1372/530, loss: 0.004429229535162449
2023-01-24 07:57:51.809981: step: 1376/530, loss: 0.030390240252017975
2023-01-24 07:57:52.906973: step: 1380/530, loss: 0.011396808549761772
2023-01-24 07:57:53.991328: step: 1384/530, loss: 0.02816726453602314
2023-01-24 07:57:55.082422: step: 1388/530, loss: 0.010108868591487408
2023-01-24 07:57:56.159655: step: 1392/530, loss: 0.0
2023-01-24 07:57:57.252797: step: 1396/530, loss: 0.0062020099721848965
2023-01-24 07:57:58.342706: step: 1400/530, loss: 0.03659898787736893
2023-01-24 07:57:59.410007: step: 1404/530, loss: 0.024742981418967247
2023-01-24 07:58:00.492495: step: 1408/530, loss: 0.0029463020619004965
2023-01-24 07:58:01.610876: step: 1412/530, loss: 0.055403999984264374
2023-01-24 07:58:02.709026: step: 1416/530, loss: 0.014414084143936634
2023-01-24 07:58:03.775454: step: 1420/530, loss: 4.377431469038129e-05
2023-01-24 07:58:04.867691: step: 1424/530, loss: 0.00045292737195268273
2023-01-24 07:58:05.935128: step: 1428/530, loss: 0.0013491526478901505
2023-01-24 07:58:07.023490: step: 1432/530, loss: 0.01840001344680786
2023-01-24 07:58:08.137901: step: 1436/530, loss: 0.009388620965182781
2023-01-24 07:58:09.217527: step: 1440/530, loss: 0.001821655547246337
2023-01-24 07:58:10.310103: step: 1444/530, loss: 0.008030835539102554
2023-01-24 07:58:11.400682: step: 1448/530, loss: 0.003816197859123349
2023-01-24 07:58:12.501383: step: 1452/530, loss: 0.009518238715827465
2023-01-24 07:58:13.561621: step: 1456/530, loss: 0.0078024608083069324
2023-01-24 07:58:14.637034: step: 1460/530, loss: 0.005686014890670776
2023-01-24 07:58:15.729739: step: 1464/530, loss: 0.008159623481333256
2023-01-24 07:58:16.822924: step: 1468/530, loss: 0.005434315651655197
2023-01-24 07:58:17.896779: step: 1472/530, loss: 0.00561576196923852
2023-01-24 07:58:18.980548: step: 1476/530, loss: 0.0095906313508749
2023-01-24 07:58:20.077283: step: 1480/530, loss: 0.017152147367596626
2023-01-24 07:58:21.147374: step: 1484/530, loss: 0.004590487573295832
2023-01-24 07:58:22.238293: step: 1488/530, loss: 0.0005239572492428124
2023-01-24 07:58:23.312351: step: 1492/530, loss: 0.004447967745363712
2023-01-24 07:58:24.390585: step: 1496/530, loss: 0.015526765026152134
2023-01-24 07:58:25.483193: step: 1500/530, loss: 0.051587581634521484
2023-01-24 07:58:26.565512: step: 1504/530, loss: 0.006166251376271248
2023-01-24 07:58:27.644586: step: 1508/530, loss: 0.005185808055102825
2023-01-24 07:58:28.746326: step: 1512/530, loss: 0.018353205174207687
2023-01-24 07:58:29.842330: step: 1516/530, loss: 0.029015248641371727
2023-01-24 07:58:30.909106: step: 1520/530, loss: 0.004135618451982737
2023-01-24 07:58:31.980622: step: 1524/530, loss: 0.0033073234371840954
2023-01-24 07:58:33.074805: step: 1528/530, loss: 0.002053049160167575
2023-01-24 07:58:34.169457: step: 1532/530, loss: 0.0036400973331183195
2023-01-24 07:58:35.266157: step: 1536/530, loss: 0.003317296039313078
2023-01-24 07:58:36.377149: step: 1540/530, loss: 0.004234801512211561
2023-01-24 07:58:37.454235: step: 1544/530, loss: 0.017313288524746895
2023-01-24 07:58:38.528902: step: 1548/530, loss: 0.012317666783928871
2023-01-24 07:58:39.620169: step: 1552/530, loss: 0.005927101708948612
2023-01-24 07:58:40.721285: step: 1556/530, loss: 0.0037845014594495296
2023-01-24 07:58:41.843904: step: 1560/530, loss: 0.008884548209607601
2023-01-24 07:58:42.935236: step: 1564/530, loss: 0.022238239645957947
2023-01-24 07:58:44.036435: step: 1568/530, loss: 0.012891136109828949
2023-01-24 07:58:45.113397: step: 1572/530, loss: 0.030476849526166916
2023-01-24 07:58:46.218293: step: 1576/530, loss: 0.0029098056256771088
2023-01-24 07:58:47.319313: step: 1580/530, loss: 0.01052937377244234
2023-01-24 07:58:48.417499: step: 1584/530, loss: 0.04979405179619789
2023-01-24 07:58:49.523380: step: 1588/530, loss: 0.0023765319492667913
2023-01-24 07:58:50.612472: step: 1592/530, loss: 0.004143412224948406
2023-01-24 07:58:51.702899: step: 1596/530, loss: 0.006798804271966219
2023-01-24 07:58:52.796606: step: 1600/530, loss: 0.009213268756866455
2023-01-24 07:58:53.879027: step: 1604/530, loss: 0.0126715749502182
2023-01-24 07:58:54.976308: step: 1608/530, loss: 0.05339021980762482
2023-01-24 07:58:56.062837: step: 1612/530, loss: 0.011374258436262608
2023-01-24 07:58:57.147585: step: 1616/530, loss: 0.005303275305777788
2023-01-24 07:58:58.237350: step: 1620/530, loss: 0.008439534343779087
2023-01-24 07:58:59.309372: step: 1624/530, loss: 0.003532485105097294
2023-01-24 07:59:00.380987: step: 1628/530, loss: 0.007714767009019852
2023-01-24 07:59:01.464808: step: 1632/530, loss: 0.005036373157054186
2023-01-24 07:59:02.563482: step: 1636/530, loss: 0.010950824245810509
2023-01-24 07:59:03.654039: step: 1640/530, loss: 0.0017168091144412756
2023-01-24 07:59:04.714448: step: 1644/530, loss: 0.019485170021653175
2023-01-24 07:59:05.796319: step: 1648/530, loss: 0.009485960006713867
2023-01-24 07:59:06.872007: step: 1652/530, loss: 0.005088926292955875
2023-01-24 07:59:07.955329: step: 1656/530, loss: 0.031124968081712723
2023-01-24 07:59:09.040697: step: 1660/530, loss: 0.028705941513180733
2023-01-24 07:59:10.127002: step: 1664/530, loss: 0.00893686804920435
2023-01-24 07:59:11.191315: step: 1668/530, loss: 0.002964981598779559
2023-01-24 07:59:12.286071: step: 1672/530, loss: 0.0036536783445626497
2023-01-24 07:59:13.369384: step: 1676/530, loss: 0.005702549125999212
2023-01-24 07:59:14.433049: step: 1680/530, loss: 0.012292525731027126
2023-01-24 07:59:15.535574: step: 1684/530, loss: 0.004351802170276642
2023-01-24 07:59:16.629569: step: 1688/530, loss: 0.006031625904142857
2023-01-24 07:59:17.703172: step: 1692/530, loss: 0.006322294473648071
2023-01-24 07:59:18.796784: step: 1696/530, loss: 0.007334110792726278
2023-01-24 07:59:19.901004: step: 1700/530, loss: 0.008161856792867184
2023-01-24 07:59:21.006645: step: 1704/530, loss: 0.01021916326135397
2023-01-24 07:59:22.098841: step: 1708/530, loss: 0.0014939174288883805
2023-01-24 07:59:23.170724: step: 1712/530, loss: 0.002128892345353961
2023-01-24 07:59:24.265838: step: 1716/530, loss: 0.01101960614323616
2023-01-24 07:59:25.352849: step: 1720/530, loss: 0.025418000295758247
2023-01-24 07:59:26.448451: step: 1724/530, loss: 0.013953392393887043
2023-01-24 07:59:27.541998: step: 1728/530, loss: 0.005516911391168833
2023-01-24 07:59:28.622734: step: 1732/530, loss: 0.005705171264708042
2023-01-24 07:59:29.701765: step: 1736/530, loss: 0.006698850076645613
2023-01-24 07:59:30.824055: step: 1740/530, loss: 0.0030481084249913692
2023-01-24 07:59:31.912217: step: 1744/530, loss: 0.014505933038890362
2023-01-24 07:59:32.982672: step: 1748/530, loss: 0.039191834628582
2023-01-24 07:59:34.071893: step: 1752/530, loss: 0.022778907790780067
2023-01-24 07:59:35.169987: step: 1756/530, loss: 0.00712298508733511
2023-01-24 07:59:36.249552: step: 1760/530, loss: 0.010292649269104004
2023-01-24 07:59:37.321582: step: 1764/530, loss: 0.004079221282154322
2023-01-24 07:59:38.415501: step: 1768/530, loss: 0.01893676444888115
2023-01-24 07:59:39.507523: step: 1772/530, loss: 0.0
2023-01-24 07:59:40.580274: step: 1776/530, loss: 0.005525399465113878
2023-01-24 07:59:41.688807: step: 1780/530, loss: 0.007351726293563843
2023-01-24 07:59:42.804434: step: 1784/530, loss: 0.0016253157518804073
2023-01-24 07:59:43.892077: step: 1788/530, loss: 0.004539277404546738
2023-01-24 07:59:45.014239: step: 1792/530, loss: 0.01693624258041382
2023-01-24 07:59:46.093812: step: 1796/530, loss: 0.0058190119452774525
2023-01-24 07:59:47.169627: step: 1800/530, loss: 0.009923038072884083
2023-01-24 07:59:48.244620: step: 1804/530, loss: 0.03290071710944176
2023-01-24 07:59:49.324505: step: 1808/530, loss: 0.003919346258044243
2023-01-24 07:59:50.403808: step: 1812/530, loss: 0.005124642513692379
2023-01-24 07:59:51.486528: step: 1816/530, loss: 0.0020729973912239075
2023-01-24 07:59:52.571999: step: 1820/530, loss: 0.005176374223083258
2023-01-24 07:59:53.655670: step: 1824/530, loss: 0.003863455494865775
2023-01-24 07:59:54.764544: step: 1828/530, loss: 0.0201641246676445
2023-01-24 07:59:55.887564: step: 1832/530, loss: 0.03788105025887489
2023-01-24 07:59:56.969319: step: 1836/530, loss: 0.0016798643628135324
2023-01-24 07:59:58.075366: step: 1840/530, loss: 0.016978899016976357
2023-01-24 07:59:59.184643: step: 1844/530, loss: 0.01821254752576351
2023-01-24 08:00:00.258561: step: 1848/530, loss: 0.0035666811745613813
2023-01-24 08:00:01.370627: step: 1852/530, loss: 0.1473417729139328
2023-01-24 08:00:02.451254: step: 1856/530, loss: 0.022895826026797295
2023-01-24 08:00:03.529825: step: 1860/530, loss: 0.004063081461936235
2023-01-24 08:00:04.600844: step: 1864/530, loss: 0.039851684123277664
2023-01-24 08:00:05.677752: step: 1868/530, loss: 0.013828875496983528
2023-01-24 08:00:06.753004: step: 1872/530, loss: 0.0001568260049680248
2023-01-24 08:00:07.828907: step: 1876/530, loss: 0.0032759520690888166
2023-01-24 08:00:08.924480: step: 1880/530, loss: 0.001493890886195004
2023-01-24 08:00:10.004620: step: 1884/530, loss: 0.0003120404726359993
2023-01-24 08:00:11.080127: step: 1888/530, loss: 0.00673631951212883
2023-01-24 08:00:12.189697: step: 1892/530, loss: 0.010273081250488758
2023-01-24 08:00:13.270863: step: 1896/530, loss: 0.0015573864802718163
2023-01-24 08:00:14.353811: step: 1900/530, loss: 0.010385089553892612
2023-01-24 08:00:15.428071: step: 1904/530, loss: 0.002454180736094713
2023-01-24 08:00:16.503498: step: 1908/530, loss: 0.002259141532704234
2023-01-24 08:00:17.578376: step: 1912/530, loss: 0.009372632019221783
2023-01-24 08:00:18.675216: step: 1916/530, loss: 0.01044060941785574
2023-01-24 08:00:19.763087: step: 1920/530, loss: 0.009234768338501453
2023-01-24 08:00:20.838893: step: 1924/530, loss: 0.0029348856769502163
2023-01-24 08:00:21.925996: step: 1928/530, loss: 0.0034264831338077784
2023-01-24 08:00:22.999427: step: 1932/530, loss: 0.018970796838402748
2023-01-24 08:00:24.085734: step: 1936/530, loss: 0.005571961402893066
2023-01-24 08:00:25.171308: step: 1940/530, loss: 0.002216230146586895
2023-01-24 08:00:26.284263: step: 1944/530, loss: 0.01605202630162239
2023-01-24 08:00:27.355724: step: 1948/530, loss: 0.005035205744206905
2023-01-24 08:00:28.434683: step: 1952/530, loss: 0.005195165518671274
2023-01-24 08:00:29.523918: step: 1956/530, loss: 0.004524275194853544
2023-01-24 08:00:30.618444: step: 1960/530, loss: 0.003987927455455065
2023-01-24 08:00:31.703249: step: 1964/530, loss: 0.010138333775103092
2023-01-24 08:00:32.777664: step: 1968/530, loss: 0.01195729710161686
2023-01-24 08:00:33.876339: step: 1972/530, loss: 0.03733308985829353
2023-01-24 08:00:34.976984: step: 1976/530, loss: 0.01076783612370491
2023-01-24 08:00:36.082187: step: 1980/530, loss: 0.020792188122868538
2023-01-24 08:00:37.165173: step: 1984/530, loss: 0.0
2023-01-24 08:00:38.284772: step: 1988/530, loss: 0.004448098596185446
2023-01-24 08:00:39.381448: step: 1992/530, loss: 0.007634727284312248
2023-01-24 08:00:40.461314: step: 1996/530, loss: 0.003218783298507333
2023-01-24 08:00:41.552735: step: 2000/530, loss: 0.0037025760393589735
2023-01-24 08:00:42.646216: step: 2004/530, loss: 0.005660674534738064
2023-01-24 08:00:43.700793: step: 2008/530, loss: 0.03520983085036278
2023-01-24 08:00:44.795837: step: 2012/530, loss: 0.012717806734144688
2023-01-24 08:00:45.895636: step: 2016/530, loss: 0.005978054832667112
2023-01-24 08:00:46.985013: step: 2020/530, loss: 0.004329439718276262
2023-01-24 08:00:48.070739: step: 2024/530, loss: 0.014939241111278534
2023-01-24 08:00:49.141760: step: 2028/530, loss: 0.027365699410438538
2023-01-24 08:00:50.230352: step: 2032/530, loss: 0.0020701545290648937
2023-01-24 08:00:51.316888: step: 2036/530, loss: 0.02141907624900341
2023-01-24 08:00:52.398993: step: 2040/530, loss: 0.011363283731043339
2023-01-24 08:00:53.472171: step: 2044/530, loss: 0.007223441265523434
2023-01-24 08:00:54.566562: step: 2048/530, loss: 0.012013864703476429
2023-01-24 08:00:55.653428: step: 2052/530, loss: 0.0017661800375208259
2023-01-24 08:00:56.717625: step: 2056/530, loss: 0.012152872048318386
2023-01-24 08:00:57.810347: step: 2060/530, loss: 0.004492082633078098
2023-01-24 08:00:58.890886: step: 2064/530, loss: 0.011100994423031807
2023-01-24 08:00:59.971669: step: 2068/530, loss: 0.01058836281299591
2023-01-24 08:01:01.061458: step: 2072/530, loss: 0.004957281518727541
2023-01-24 08:01:02.128794: step: 2076/530, loss: 0.0019252515630796552
2023-01-24 08:01:03.203897: step: 2080/530, loss: 0.01359036099165678
2023-01-24 08:01:04.284115: step: 2084/530, loss: 0.003083687974140048
2023-01-24 08:01:05.369533: step: 2088/530, loss: 0.013326723128557205
2023-01-24 08:01:06.471045: step: 2092/530, loss: 0.004173072054982185
2023-01-24 08:01:07.580925: step: 2096/530, loss: 0.055387236177921295
2023-01-24 08:01:08.669918: step: 2100/530, loss: 0.0202984306961298
2023-01-24 08:01:09.742123: step: 2104/530, loss: 0.0010682246647775173
2023-01-24 08:01:10.838594: step: 2108/530, loss: 0.02901669405400753
2023-01-24 08:01:11.940761: step: 2112/530, loss: 0.006395253352820873
2023-01-24 08:01:13.012647: step: 2116/530, loss: 0.0033668573014438152
2023-01-24 08:01:14.103689: step: 2120/530, loss: 0.010745705105364323
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3920004410956527, 'r': 0.3339814004780798, 'f1': 0.3606725369916968}, 'combined': 0.2657587114675661, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3304633279557043, 'r': 0.26221546674746105, 'f1': 0.292409975039593}, 'combined': 0.18160198449827356, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38333329883077744, 'r': 0.3302339993722447, 'f1': 0.35480798709311506}, 'combined': 0.26143746417387426, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34574514535424083, 'r': 0.27194973883594437, 'f1': 0.3044393094048404}, 'combined': 0.1890728342619535, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 3}
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': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3920004410956527, 'r': 0.3339814004780798, 'f1': 0.3606725369916968}, 'combined': 0.2657587114675661, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3304633279557043, 'r': 0.26221546674746105, 'f1': 0.292409975039593}, 'combined': 0.18160198449827356, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38333329883077744, 'r': 0.3302339993722447, 'f1': 0.35480798709311506}, 'combined': 0.26143746417387426, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34574514535424083, 'r': 0.27194973883594437, 'f1': 0.3044393094048404}, 'combined': 0.1890728342619535, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 3}
******************************
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 08:04:11.401496: step: 4/530, loss: 0.09927669167518616
2023-01-24 08:04:12.530739: step: 8/530, loss: 0.005641601979732513
2023-01-24 08:04:13.593799: step: 12/530, loss: 0.0013777896529063582
2023-01-24 08:04:14.663474: step: 16/530, loss: 0.00665803300216794
2023-01-24 08:04:15.742895: step: 20/530, loss: 0.006408526562154293
2023-01-24 08:04:16.820860: step: 24/530, loss: 0.00570447975769639
2023-01-24 08:04:17.906646: step: 28/530, loss: 0.008242086507380009
2023-01-24 08:04:18.981152: step: 32/530, loss: 0.013434949330985546
2023-01-24 08:04:20.058598: step: 36/530, loss: 0.007572309114038944
2023-01-24 08:04:21.135165: step: 40/530, loss: 0.006733869668096304
2023-01-24 08:04:22.233528: step: 44/530, loss: 0.011334957554936409
2023-01-24 08:04:23.322496: step: 48/530, loss: 0.0306736771017313
2023-01-24 08:04:24.408733: step: 52/530, loss: 0.004868673160672188
2023-01-24 08:04:25.492342: step: 56/530, loss: 0.0037384810857474804
2023-01-24 08:04:26.590188: step: 60/530, loss: 0.01926356367766857
2023-01-24 08:04:27.675336: step: 64/530, loss: 0.025363925844430923
2023-01-24 08:04:28.755533: step: 68/530, loss: 0.004237812478095293
2023-01-24 08:04:29.835338: step: 72/530, loss: 0.0004058255290146917
2023-01-24 08:04:30.911742: step: 76/530, loss: 0.017811616882681847
2023-01-24 08:04:31.995086: step: 80/530, loss: 0.004367070738226175
2023-01-24 08:04:33.090813: step: 84/530, loss: 0.031310077756643295
2023-01-24 08:04:34.190184: step: 88/530, loss: 0.003796903882175684
2023-01-24 08:04:35.257690: step: 92/530, loss: 0.0005739496555179358
2023-01-24 08:04:36.328896: step: 96/530, loss: 0.004304783884435892
2023-01-24 08:04:37.406977: step: 100/530, loss: 0.004899375140666962
2023-01-24 08:04:38.506733: step: 104/530, loss: 0.008823595941066742
2023-01-24 08:04:39.587610: step: 108/530, loss: 0.0031449312809854746
2023-01-24 08:04:40.679826: step: 112/530, loss: 0.02087133377790451
2023-01-24 08:04:41.782615: step: 116/530, loss: 0.0010118724312633276
2023-01-24 08:04:42.881766: step: 120/530, loss: 0.030991574749350548
2023-01-24 08:04:43.959105: step: 124/530, loss: 0.002826171461492777
2023-01-24 08:04:45.023291: step: 128/530, loss: 0.03895251825451851
2023-01-24 08:04:46.103632: step: 132/530, loss: 0.04373853653669357
2023-01-24 08:04:47.178842: step: 136/530, loss: 0.006357408128678799
2023-01-24 08:04:48.251223: step: 140/530, loss: 0.011653343215584755
2023-01-24 08:04:49.321328: step: 144/530, loss: 0.004880918189883232
2023-01-24 08:04:50.392004: step: 148/530, loss: 0.00032929336884990335
2023-01-24 08:04:51.465917: step: 152/530, loss: 0.0033075911924242973
2023-01-24 08:04:52.545200: step: 156/530, loss: 0.002118311822414398
2023-01-24 08:04:53.629101: step: 160/530, loss: 0.008454743772745132
2023-01-24 08:04:54.709561: step: 164/530, loss: 0.0018689573043957353
2023-01-24 08:04:55.805126: step: 168/530, loss: 0.0064310599118471146
2023-01-24 08:04:56.880998: step: 172/530, loss: 0.004264505580067635
2023-01-24 08:04:57.979704: step: 176/530, loss: 0.002996481489390135
2023-01-24 08:04:59.048835: step: 180/530, loss: 0.010713724419474602
2023-01-24 08:05:00.126501: step: 184/530, loss: 0.04462990537285805
2023-01-24 08:05:01.225839: step: 188/530, loss: 0.0010316789848729968
2023-01-24 08:05:02.324039: step: 192/530, loss: 0.007205520290881395
2023-01-24 08:05:03.398140: step: 196/530, loss: 0.017558736726641655
2023-01-24 08:05:04.477941: step: 200/530, loss: 0.005804868880659342
2023-01-24 08:05:05.556300: step: 204/530, loss: 0.004413038957864046
2023-01-24 08:05:06.638931: step: 208/530, loss: 0.00911199115216732
2023-01-24 08:05:07.716682: step: 212/530, loss: 0.0032672162633389235
2023-01-24 08:05:08.825475: step: 216/530, loss: 0.00288008782081306
2023-01-24 08:05:09.931995: step: 220/530, loss: 0.0027356515638530254
2023-01-24 08:05:11.017335: step: 224/530, loss: 0.01759803667664528
2023-01-24 08:05:12.117612: step: 228/530, loss: 0.014631424099206924
2023-01-24 08:05:13.197139: step: 232/530, loss: 0.001528739696368575
2023-01-24 08:05:14.307949: step: 236/530, loss: 0.021075492724776268
2023-01-24 08:05:15.397328: step: 240/530, loss: 0.014439521357417107
2023-01-24 08:05:16.476566: step: 244/530, loss: 0.005400847643613815
2023-01-24 08:05:17.555304: step: 248/530, loss: 0.0009490182274021208
2023-01-24 08:05:18.661439: step: 252/530, loss: 0.007926997728645802
2023-01-24 08:05:19.763155: step: 256/530, loss: 0.0022545952815562487
2023-01-24 08:05:20.852879: step: 260/530, loss: 0.0029541002586483955
2023-01-24 08:05:21.941719: step: 264/530, loss: 0.008275289088487625
2023-01-24 08:05:23.019531: step: 268/530, loss: 0.0017798682674765587
2023-01-24 08:05:24.101063: step: 272/530, loss: 0.00442288164049387
2023-01-24 08:05:25.184338: step: 276/530, loss: 0.04807819053530693
2023-01-24 08:05:26.280410: step: 280/530, loss: 0.0024885369930416346
2023-01-24 08:05:27.376116: step: 284/530, loss: 0.0008520008996129036
2023-01-24 08:05:28.463239: step: 288/530, loss: 0.013537491671741009
2023-01-24 08:05:29.542270: step: 292/530, loss: 0.0036641217302531004
2023-01-24 08:05:30.616322: step: 296/530, loss: 0.07835936546325684
2023-01-24 08:05:31.715540: step: 300/530, loss: 0.006127417553216219
2023-01-24 08:05:32.823924: step: 304/530, loss: 0.014236005954444408
2023-01-24 08:05:33.901199: step: 308/530, loss: 0.001819130266085267
2023-01-24 08:05:34.976059: step: 312/530, loss: 0.006281946785748005
2023-01-24 08:05:36.105729: step: 316/530, loss: 0.0028561612125486135
2023-01-24 08:05:37.215261: step: 320/530, loss: 0.06220261752605438
2023-01-24 08:05:38.293057: step: 324/530, loss: 0.018125133588910103
2023-01-24 08:05:39.363733: step: 328/530, loss: 0.014507114887237549
2023-01-24 08:05:40.457086: step: 332/530, loss: 0.006403418257832527
2023-01-24 08:05:41.564513: step: 336/530, loss: 0.0008241086034104228
2023-01-24 08:05:42.650489: step: 340/530, loss: 0.012522955425083637
2023-01-24 08:05:43.737327: step: 344/530, loss: 0.028947046026587486
2023-01-24 08:05:44.823695: step: 348/530, loss: 0.0012344359420239925
2023-01-24 08:05:45.901813: step: 352/530, loss: 0.008961455896496773
2023-01-24 08:05:46.985453: step: 356/530, loss: 0.005826309788972139
2023-01-24 08:05:48.077794: step: 360/530, loss: 0.0023722576443105936
2023-01-24 08:05:49.178485: step: 364/530, loss: 0.001849903492256999
2023-01-24 08:05:50.262250: step: 368/530, loss: 0.010201117023825645
2023-01-24 08:05:51.338234: step: 372/530, loss: 0.007875319570302963
2023-01-24 08:05:52.425788: step: 376/530, loss: 0.014172296971082687
2023-01-24 08:05:53.491106: step: 380/530, loss: 0.009425021708011627
2023-01-24 08:05:54.579238: step: 384/530, loss: 0.004893010947853327
2023-01-24 08:05:55.648247: step: 388/530, loss: 0.0035306529607623816
2023-01-24 08:05:56.715748: step: 392/530, loss: 0.00699588842689991
2023-01-24 08:05:57.814880: step: 396/530, loss: 0.026883775368332863
2023-01-24 08:05:58.883107: step: 400/530, loss: 0.0
2023-01-24 08:05:59.966721: step: 404/530, loss: 0.003555327421054244
2023-01-24 08:06:01.061160: step: 408/530, loss: 0.001621041912585497
2023-01-24 08:06:02.162387: step: 412/530, loss: 0.0054182508029043674
2023-01-24 08:06:03.234431: step: 416/530, loss: 0.013784663751721382
2023-01-24 08:06:04.306617: step: 420/530, loss: 0.04009197652339935
2023-01-24 08:06:05.390520: step: 424/530, loss: 0.007577024400234222
2023-01-24 08:06:06.468674: step: 428/530, loss: 0.006525625940412283
2023-01-24 08:06:07.547970: step: 432/530, loss: 0.018196502700448036
2023-01-24 08:06:08.629670: step: 436/530, loss: 0.0001607575686648488
2023-01-24 08:06:09.740565: step: 440/530, loss: 0.002720220945775509
2023-01-24 08:06:10.838507: step: 444/530, loss: 0.014555196277797222
2023-01-24 08:06:11.903799: step: 448/530, loss: 0.0005303258076310158
2023-01-24 08:06:12.986312: step: 452/530, loss: 0.005635303445160389
2023-01-24 08:06:14.072523: step: 456/530, loss: 0.0011091685155406594
2023-01-24 08:06:15.163314: step: 460/530, loss: 0.006827346049249172
2023-01-24 08:06:16.264550: step: 464/530, loss: 0.008032244630157948
2023-01-24 08:06:17.355953: step: 468/530, loss: 0.006095521152019501
2023-01-24 08:06:18.439823: step: 472/530, loss: 0.028219925239682198
2023-01-24 08:06:19.503374: step: 476/530, loss: 0.002821669215336442
2023-01-24 08:06:20.623231: step: 480/530, loss: 0.0032214473467320204
2023-01-24 08:06:21.717162: step: 484/530, loss: 0.0027135361451655626
2023-01-24 08:06:22.817766: step: 488/530, loss: 0.010229124687612057
2023-01-24 08:06:23.924625: step: 492/530, loss: 0.012760784476995468
2023-01-24 08:06:25.007103: step: 496/530, loss: 0.01200017798691988
2023-01-24 08:06:26.078902: step: 500/530, loss: 0.00775990542024374
2023-01-24 08:06:27.165160: step: 504/530, loss: 0.004292254336178303
2023-01-24 08:06:28.264547: step: 508/530, loss: 0.005923712160438299
2023-01-24 08:06:29.380470: step: 512/530, loss: 0.04941634461283684
2023-01-24 08:06:30.461151: step: 516/530, loss: 0.06716771423816681
2023-01-24 08:06:31.554094: step: 520/530, loss: 0.005379937589168549
2023-01-24 08:06:32.630595: step: 524/530, loss: 0.002120907884091139
2023-01-24 08:06:33.718989: step: 528/530, loss: 0.009625289589166641
2023-01-24 08:06:34.782682: step: 532/530, loss: 0.0009129293612204492
2023-01-24 08:06:35.868769: step: 536/530, loss: 0.010262400843203068
2023-01-24 08:06:36.959141: step: 540/530, loss: 0.007930413819849491
2023-01-24 08:06:38.038079: step: 544/530, loss: 0.004497353918850422
2023-01-24 08:06:39.124024: step: 548/530, loss: 0.004900988657027483
2023-01-24 08:06:40.210909: step: 552/530, loss: 0.002976667834445834
2023-01-24 08:06:41.294773: step: 556/530, loss: 0.005632808431982994
2023-01-24 08:06:42.375332: step: 560/530, loss: 0.004273197613656521
2023-01-24 08:06:43.469216: step: 564/530, loss: 0.005485229194164276
2023-01-24 08:06:44.570318: step: 568/530, loss: 0.005553442519158125
2023-01-24 08:06:45.658654: step: 572/530, loss: 0.006116292905062437
2023-01-24 08:06:46.742764: step: 576/530, loss: 0.019503524526953697
2023-01-24 08:06:47.830252: step: 580/530, loss: 0.0014874463668093085
2023-01-24 08:06:48.941265: step: 584/530, loss: 0.0029542213305830956
2023-01-24 08:06:50.010765: step: 588/530, loss: 0.008017477579414845
2023-01-24 08:06:51.091686: step: 592/530, loss: 0.01405017077922821
2023-01-24 08:06:52.164134: step: 596/530, loss: 0.009267565794289112
2023-01-24 08:06:53.249787: step: 600/530, loss: 0.005587130319327116
2023-01-24 08:06:54.338338: step: 604/530, loss: 0.005893026012927294
2023-01-24 08:06:55.408880: step: 608/530, loss: 0.05462037771940231
2023-01-24 08:06:56.469459: step: 612/530, loss: 0.014503302052617073
2023-01-24 08:06:57.550104: step: 616/530, loss: 0.0021572366822510958
2023-01-24 08:06:58.643339: step: 620/530, loss: 0.030603861436247826
2023-01-24 08:06:59.741105: step: 624/530, loss: 0.025606010109186172
2023-01-24 08:07:00.819498: step: 628/530, loss: 0.012202084064483643
2023-01-24 08:07:01.902250: step: 632/530, loss: 0.006320464424788952
2023-01-24 08:07:02.994888: step: 636/530, loss: 0.01756983809173107
2023-01-24 08:07:04.078188: step: 640/530, loss: 0.013302707113325596
2023-01-24 08:07:05.138535: step: 644/530, loss: 0.0051459018141031265
2023-01-24 08:07:06.228693: step: 648/530, loss: 0.018608955666422844
2023-01-24 08:07:07.354019: step: 652/530, loss: 0.051968496292829514
2023-01-24 08:07:08.445915: step: 656/530, loss: 0.002816385356709361
2023-01-24 08:07:09.519489: step: 660/530, loss: 0.0011777845211327076
2023-01-24 08:07:10.603260: step: 664/530, loss: 0.05226266756653786
2023-01-24 08:07:11.675852: step: 668/530, loss: 0.0022365900222212076
2023-01-24 08:07:12.763937: step: 672/530, loss: 0.0017457716166973114
2023-01-24 08:07:13.853717: step: 676/530, loss: 0.004118798766285181
2023-01-24 08:07:14.958856: step: 680/530, loss: 0.007175061386078596
2023-01-24 08:07:16.050070: step: 684/530, loss: 0.0065866210497915745
2023-01-24 08:07:17.136778: step: 688/530, loss: 0.0046526906080543995
2023-01-24 08:07:18.232719: step: 692/530, loss: 0.013096659444272518
2023-01-24 08:07:19.308261: step: 696/530, loss: 0.0021525996271520853
2023-01-24 08:07:20.399496: step: 700/530, loss: 0.010530092753469944
2023-01-24 08:07:21.477715: step: 704/530, loss: 0.01911844126880169
2023-01-24 08:07:22.545929: step: 708/530, loss: 0.005516392178833485
2023-01-24 08:07:23.662050: step: 712/530, loss: 0.0376371368765831
2023-01-24 08:07:24.730346: step: 716/530, loss: 0.008230074308812618
2023-01-24 08:07:25.808912: step: 720/530, loss: 0.0011314211878925562
2023-01-24 08:07:26.905076: step: 724/530, loss: 0.005857103504240513
2023-01-24 08:07:27.978135: step: 728/530, loss: 0.006830296479165554
2023-01-24 08:07:29.058855: step: 732/530, loss: 0.037676043808460236
2023-01-24 08:07:30.159325: step: 736/530, loss: 0.00492482166737318
2023-01-24 08:07:31.261861: step: 740/530, loss: 0.006314415019005537
2023-01-24 08:07:32.332445: step: 744/530, loss: 0.0011559833073988557
2023-01-24 08:07:33.413428: step: 748/530, loss: 0.019396888092160225
2023-01-24 08:07:34.477118: step: 752/530, loss: 0.0035427967086434364
2023-01-24 08:07:35.553235: step: 756/530, loss: 0.004653621930629015
2023-01-24 08:07:36.623959: step: 760/530, loss: 0.04286370053887367
2023-01-24 08:07:37.710770: step: 764/530, loss: 0.004473235923796892
2023-01-24 08:07:38.806738: step: 768/530, loss: 0.0014295750297605991
2023-01-24 08:07:39.897768: step: 772/530, loss: 0.009321562945842743
2023-01-24 08:07:40.981544: step: 776/530, loss: 0.001998191000893712
2023-01-24 08:07:42.067272: step: 780/530, loss: 0.010920494794845581
2023-01-24 08:07:43.167343: step: 784/530, loss: 0.005064839031547308
2023-01-24 08:07:44.212962: step: 788/530, loss: 0.0026471298187971115
2023-01-24 08:07:45.287720: step: 792/530, loss: 0.007634473033249378
2023-01-24 08:07:46.374286: step: 796/530, loss: 0.0054195537231862545
2023-01-24 08:07:47.448309: step: 800/530, loss: 2.5632723918533884e-05
2023-01-24 08:07:48.514319: step: 804/530, loss: 0.0015481067821383476
2023-01-24 08:07:49.588473: step: 808/530, loss: 0.0013678346294909716
2023-01-24 08:07:50.649536: step: 812/530, loss: 3.655743785202503e-05
2023-01-24 08:07:51.735579: step: 816/530, loss: 0.0007711700745858252
2023-01-24 08:07:52.832687: step: 820/530, loss: 0.002734269481152296
2023-01-24 08:07:53.929288: step: 824/530, loss: 0.007342600263655186
2023-01-24 08:07:55.007458: step: 828/530, loss: 0.008949954062700272
2023-01-24 08:07:56.079915: step: 832/530, loss: 0.01913045346736908
2023-01-24 08:07:57.156145: step: 836/530, loss: 0.0058847409673035145
2023-01-24 08:07:58.231672: step: 840/530, loss: 0.0016242398414760828
2023-01-24 08:07:59.320898: step: 844/530, loss: 0.0
2023-01-24 08:08:00.388069: step: 848/530, loss: 0.003999742213636637
2023-01-24 08:08:01.473939: step: 852/530, loss: 0.010109375230967999
2023-01-24 08:08:02.558624: step: 856/530, loss: 0.00460029998794198
2023-01-24 08:08:03.649538: step: 860/530, loss: 0.0004871089186053723
2023-01-24 08:08:04.761389: step: 864/530, loss: 0.009708979167044163
2023-01-24 08:08:05.853994: step: 868/530, loss: 0.018177898600697517
2023-01-24 08:08:06.920448: step: 872/530, loss: 0.014271182008087635
2023-01-24 08:08:07.987288: step: 876/530, loss: 0.016332503408193588
2023-01-24 08:08:09.062060: step: 880/530, loss: 0.028696853667497635
2023-01-24 08:08:10.131202: step: 884/530, loss: 0.0019225645810365677
2023-01-24 08:08:11.204636: step: 888/530, loss: 0.006583839189261198
2023-01-24 08:08:12.294361: step: 892/530, loss: 0.01813540793955326
2023-01-24 08:08:13.396331: step: 896/530, loss: 0.002659044461324811
2023-01-24 08:08:14.500478: step: 900/530, loss: 0.007973596453666687
2023-01-24 08:08:15.571285: step: 904/530, loss: 0.000344327709171921
2023-01-24 08:08:16.637114: step: 908/530, loss: 0.0005181411979719996
2023-01-24 08:08:17.737218: step: 912/530, loss: 0.006515146233141422
2023-01-24 08:08:18.836561: step: 916/530, loss: 0.04089716821908951
2023-01-24 08:08:19.915966: step: 920/530, loss: 0.012362835928797722
2023-01-24 08:08:20.977129: step: 924/530, loss: 0.0032248373609036207
2023-01-24 08:08:22.060879: step: 928/530, loss: 0.0052716550417244434
2023-01-24 08:08:23.163999: step: 932/530, loss: 0.008960737846791744
2023-01-24 08:08:24.245410: step: 936/530, loss: 0.007722099777311087
2023-01-24 08:08:25.324471: step: 940/530, loss: 0.005386774893850088
2023-01-24 08:08:26.370362: step: 944/530, loss: 0.02466478943824768
2023-01-24 08:08:27.464630: step: 948/530, loss: 0.000699700671248138
2023-01-24 08:08:28.530249: step: 952/530, loss: 0.010090579278767109
2023-01-24 08:08:29.621170: step: 956/530, loss: 0.032206565141677856
2023-01-24 08:08:30.705311: step: 960/530, loss: 0.004933027550578117
2023-01-24 08:08:31.780730: step: 964/530, loss: 0.005204321350902319
2023-01-24 08:08:32.861230: step: 968/530, loss: 0.007158435881137848
2023-01-24 08:08:33.948108: step: 972/530, loss: 0.0004781386232934892
2023-01-24 08:08:35.026853: step: 976/530, loss: 0.007539019919931889
2023-01-24 08:08:36.118223: step: 980/530, loss: 0.028663285076618195
2023-01-24 08:08:37.194906: step: 984/530, loss: 0.0062734270468354225
2023-01-24 08:08:38.274942: step: 988/530, loss: 0.003907158505171537
2023-01-24 08:08:39.344778: step: 992/530, loss: 0.009708663448691368
2023-01-24 08:08:40.410600: step: 996/530, loss: 0.0015299940714612603
2023-01-24 08:08:41.507856: step: 1000/530, loss: 0.027635866776108742
2023-01-24 08:08:42.619863: step: 1004/530, loss: 0.019229024648666382
2023-01-24 08:08:43.720147: step: 1008/530, loss: 0.0019254639046266675
2023-01-24 08:08:44.805209: step: 1012/530, loss: 0.006283264607191086
2023-01-24 08:08:45.892162: step: 1016/530, loss: 0.010211851447820663
2023-01-24 08:08:46.960673: step: 1020/530, loss: 0.02226889505982399
2023-01-24 08:08:48.062253: step: 1024/530, loss: 0.011547621339559555
2023-01-24 08:08:49.147171: step: 1028/530, loss: 0.028978381305933
2023-01-24 08:08:50.237892: step: 1032/530, loss: 0.009371335618197918
2023-01-24 08:08:51.305168: step: 1036/530, loss: 0.004516514949500561
2023-01-24 08:08:52.389234: step: 1040/530, loss: 0.004802541807293892
2023-01-24 08:08:53.472961: step: 1044/530, loss: 0.004046474117785692
2023-01-24 08:08:54.548239: step: 1048/530, loss: 0.01412553247064352
2023-01-24 08:08:55.642127: step: 1052/530, loss: 0.031771283596754074
2023-01-24 08:08:56.713442: step: 1056/530, loss: 0.016401346772909164
2023-01-24 08:08:57.788687: step: 1060/530, loss: 0.005149469245225191
2023-01-24 08:08:58.884755: step: 1064/530, loss: 0.0051411353051662445
2023-01-24 08:08:59.991948: step: 1068/530, loss: 0.006421458441764116
2023-01-24 08:09:01.093254: step: 1072/530, loss: 0.005479373969137669
2023-01-24 08:09:02.189260: step: 1076/530, loss: 0.01687074452638626
2023-01-24 08:09:03.261359: step: 1080/530, loss: 0.01837819442152977
2023-01-24 08:09:04.340223: step: 1084/530, loss: 0.006419012788683176
2023-01-24 08:09:05.441530: step: 1088/530, loss: 0.21443110704421997
2023-01-24 08:09:06.539502: step: 1092/530, loss: 0.00515205692499876
2023-01-24 08:09:07.605126: step: 1096/530, loss: 0.014464744366705418
2023-01-24 08:09:08.691277: step: 1100/530, loss: 0.010988007299602032
2023-01-24 08:09:09.772434: step: 1104/530, loss: 0.012415298260748386
2023-01-24 08:09:10.843537: step: 1108/530, loss: 0.006238764151930809
2023-01-24 08:09:11.942964: step: 1112/530, loss: 0.006947832182049751
2023-01-24 08:09:13.005048: step: 1116/530, loss: 0.03296361863613129
2023-01-24 08:09:14.118164: step: 1120/530, loss: 0.04336675629019737
2023-01-24 08:09:15.170955: step: 1124/530, loss: 0.005384029820561409
2023-01-24 08:09:16.257303: step: 1128/530, loss: 0.001848328742198646
2023-01-24 08:09:17.343118: step: 1132/530, loss: 0.005821629893034697
2023-01-24 08:09:18.428225: step: 1136/530, loss: 0.0011691212421283126
2023-01-24 08:09:19.501350: step: 1140/530, loss: 0.0023401067592203617
2023-01-24 08:09:20.580686: step: 1144/530, loss: 0.011342565529048443
2023-01-24 08:09:21.690309: step: 1148/530, loss: 0.03706418722867966
2023-01-24 08:09:22.761133: step: 1152/530, loss: 0.008639579638838768
2023-01-24 08:09:23.834341: step: 1156/530, loss: 0.00441003916785121
2023-01-24 08:09:24.912631: step: 1160/530, loss: 0.015135018154978752
2023-01-24 08:09:26.013666: step: 1164/530, loss: 0.003957340959459543
2023-01-24 08:09:27.076346: step: 1168/530, loss: 0.010271869599819183
2023-01-24 08:09:28.169166: step: 1172/530, loss: 0.007644107099622488
2023-01-24 08:09:29.249975: step: 1176/530, loss: 0.04006931558251381
2023-01-24 08:09:30.332841: step: 1180/530, loss: 0.02148464135825634
2023-01-24 08:09:31.403671: step: 1184/530, loss: 0.006408920977264643
2023-01-24 08:09:32.492668: step: 1188/530, loss: 0.00384511798620224
2023-01-24 08:09:33.595042: step: 1192/530, loss: 0.03347256779670715
2023-01-24 08:09:34.684606: step: 1196/530, loss: 0.005603414494544268
2023-01-24 08:09:35.765760: step: 1200/530, loss: 0.007562906481325626
2023-01-24 08:09:36.859622: step: 1204/530, loss: 0.0015090858796611428
2023-01-24 08:09:37.950501: step: 1208/530, loss: 0.017365990206599236
2023-01-24 08:09:39.039239: step: 1212/530, loss: 0.008800257928669453
2023-01-24 08:09:40.124258: step: 1216/530, loss: 0.005413127597421408
2023-01-24 08:09:41.222652: step: 1220/530, loss: 0.0047996509820222855
2023-01-24 08:09:42.303395: step: 1224/530, loss: 0.022756759077310562
2023-01-24 08:09:43.366569: step: 1228/530, loss: 0.006855475716292858
2023-01-24 08:09:44.426972: step: 1232/530, loss: 0.020436810329556465
2023-01-24 08:09:45.505757: step: 1236/530, loss: 0.04669833183288574
2023-01-24 08:09:46.598132: step: 1240/530, loss: 0.011487391777336597
2023-01-24 08:09:47.695594: step: 1244/530, loss: 0.01739269308745861
2023-01-24 08:09:48.758567: step: 1248/530, loss: 0.031075118109583855
2023-01-24 08:09:49.833021: step: 1252/530, loss: 0.010184599086642265
2023-01-24 08:09:50.915304: step: 1256/530, loss: 0.007033254485577345
2023-01-24 08:09:52.005543: step: 1260/530, loss: 0.005699960980564356
2023-01-24 08:09:53.095774: step: 1264/530, loss: 0.007377345114946365
2023-01-24 08:09:54.198977: step: 1268/530, loss: 0.01987394690513611
2023-01-24 08:09:55.292020: step: 1272/530, loss: 0.0006842540460638702
2023-01-24 08:09:56.371859: step: 1276/530, loss: 0.07761415094137192
2023-01-24 08:09:57.453882: step: 1280/530, loss: 0.0015428510960191488
2023-01-24 08:09:58.541005: step: 1284/530, loss: 0.002973944880068302
2023-01-24 08:09:59.660869: step: 1288/530, loss: 0.015504645183682442
2023-01-24 08:10:00.776946: step: 1292/530, loss: 0.0063639418222010136
2023-01-24 08:10:01.867020: step: 1296/530, loss: 0.008862471207976341
2023-01-24 08:10:02.973521: step: 1300/530, loss: 0.0045169140212237835
2023-01-24 08:10:04.056151: step: 1304/530, loss: 0.004776623100042343
2023-01-24 08:10:05.140394: step: 1308/530, loss: 0.006416270975023508
2023-01-24 08:10:06.230432: step: 1312/530, loss: 0.027517270296812057
2023-01-24 08:10:07.352897: step: 1316/530, loss: 0.013181486167013645
2023-01-24 08:10:08.423521: step: 1320/530, loss: 0.012903379276394844
2023-01-24 08:10:09.508553: step: 1324/530, loss: 0.0036061087157577276
2023-01-24 08:10:10.578401: step: 1328/530, loss: 0.012627535499632359
2023-01-24 08:10:11.675634: step: 1332/530, loss: 0.00782503467053175
2023-01-24 08:10:12.778505: step: 1336/530, loss: 0.020762721076607704
2023-01-24 08:10:13.864776: step: 1340/530, loss: 0.03078097105026245
2023-01-24 08:10:14.935869: step: 1344/530, loss: 0.01978605054318905
2023-01-24 08:10:16.043977: step: 1348/530, loss: 0.024528084322810173
2023-01-24 08:10:17.132363: step: 1352/530, loss: 0.0026921741664409637
2023-01-24 08:10:18.190558: step: 1356/530, loss: 0.008660894818603992
2023-01-24 08:10:19.272871: step: 1360/530, loss: 0.009936562739312649
2023-01-24 08:10:20.347763: step: 1364/530, loss: 0.009195527993142605
2023-01-24 08:10:21.447762: step: 1368/530, loss: 0.005268219392746687
2023-01-24 08:10:22.522635: step: 1372/530, loss: 0.00024246703833341599
2023-01-24 08:10:23.590791: step: 1376/530, loss: 0.008973626419901848
2023-01-24 08:10:24.663425: step: 1380/530, loss: 0.0010981213999912143
2023-01-24 08:10:25.750598: step: 1384/530, loss: 0.0008329460397362709
2023-01-24 08:10:26.823533: step: 1388/530, loss: 0.013117737136781216
2023-01-24 08:10:27.900085: step: 1392/530, loss: 0.0015662973746657372
2023-01-24 08:10:29.008954: step: 1396/530, loss: 0.0262934397906065
2023-01-24 08:10:30.077468: step: 1400/530, loss: 0.0017349009867757559
2023-01-24 08:10:31.196628: step: 1404/530, loss: 0.043029069900512695
2023-01-24 08:10:32.287904: step: 1408/530, loss: 0.02065475657582283
2023-01-24 08:10:33.382868: step: 1412/530, loss: 0.010066530667245388
2023-01-24 08:10:34.476829: step: 1416/530, loss: 0.0075648087076842785
2023-01-24 08:10:35.542512: step: 1420/530, loss: 0.006466331426054239
2023-01-24 08:10:36.631500: step: 1424/530, loss: 0.010740979574620724
2023-01-24 08:10:37.723918: step: 1428/530, loss: 0.008851229213178158
2023-01-24 08:10:38.801802: step: 1432/530, loss: 0.004348272457718849
2023-01-24 08:10:39.915652: step: 1436/530, loss: 0.009712323546409607
2023-01-24 08:10:40.988727: step: 1440/530, loss: 0.00931523647159338
2023-01-24 08:10:42.081095: step: 1444/530, loss: 0.008745982311666012
2023-01-24 08:10:43.161452: step: 1448/530, loss: 0.004645561799407005
2023-01-24 08:10:44.231047: step: 1452/530, loss: 0.006835793145000935
2023-01-24 08:10:45.331527: step: 1456/530, loss: 0.005716282874345779
2023-01-24 08:10:46.433534: step: 1460/530, loss: 0.002697772579267621
2023-01-24 08:10:47.523887: step: 1464/530, loss: 0.017428727820515633
2023-01-24 08:10:48.633384: step: 1468/530, loss: 0.00808794517070055
2023-01-24 08:10:49.737267: step: 1472/530, loss: 0.004085040185600519
2023-01-24 08:10:50.827551: step: 1476/530, loss: 0.007563811726868153
2023-01-24 08:10:51.895726: step: 1480/530, loss: 0.015021136961877346
2023-01-24 08:10:52.973577: step: 1484/530, loss: 0.03507441654801369
2023-01-24 08:10:54.064145: step: 1488/530, loss: 0.022063041105866432
2023-01-24 08:10:55.162950: step: 1492/530, loss: 0.0016781722661107779
2023-01-24 08:10:56.245973: step: 1496/530, loss: 0.0037427227944135666
2023-01-24 08:10:57.331904: step: 1500/530, loss: 0.0059233796782791615
2023-01-24 08:10:58.407117: step: 1504/530, loss: 0.001936563989147544
2023-01-24 08:10:59.507546: step: 1508/530, loss: 0.005255910102277994
2023-01-24 08:11:00.598134: step: 1512/530, loss: 0.05116692930459976
2023-01-24 08:11:01.679844: step: 1516/530, loss: 0.002298779087141156
2023-01-24 08:11:02.761897: step: 1520/530, loss: 0.005176724400371313
2023-01-24 08:11:03.840744: step: 1524/530, loss: 0.00435676658526063
2023-01-24 08:11:04.926287: step: 1528/530, loss: 0.00561439897865057
2023-01-24 08:11:06.022362: step: 1532/530, loss: 0.027845002710819244
2023-01-24 08:11:07.108183: step: 1536/530, loss: 0.01168154552578926
2023-01-24 08:11:08.197999: step: 1540/530, loss: 0.0070859710685908794
2023-01-24 08:11:09.293975: step: 1544/530, loss: 0.008946003392338753
2023-01-24 08:11:10.338991: step: 1548/530, loss: 0.016834719106554985
2023-01-24 08:11:11.407823: step: 1552/530, loss: 0.009201685898005962
2023-01-24 08:11:12.555453: step: 1556/530, loss: 0.0068786353804171085
2023-01-24 08:11:13.613178: step: 1560/530, loss: 0.0142699358984828
2023-01-24 08:11:14.702181: step: 1564/530, loss: 0.008466634899377823
2023-01-24 08:11:15.796336: step: 1568/530, loss: 0.0026678431313484907
2023-01-24 08:11:16.882151: step: 1572/530, loss: 0.0048872740007936954
2023-01-24 08:11:17.980814: step: 1576/530, loss: 0.008471204899251461
2023-01-24 08:11:19.068052: step: 1580/530, loss: 0.00534965842962265
2023-01-24 08:11:20.180340: step: 1584/530, loss: 0.025050774216651917
2023-01-24 08:11:21.259958: step: 1588/530, loss: 0.0031647684518247843
2023-01-24 08:11:22.336896: step: 1592/530, loss: 0.006447574123740196
2023-01-24 08:11:23.422383: step: 1596/530, loss: 0.019744012504816055
2023-01-24 08:11:24.513720: step: 1600/530, loss: 0.012958145700395107
2023-01-24 08:11:25.610561: step: 1604/530, loss: 0.008241388015449047
2023-01-24 08:11:26.686495: step: 1608/530, loss: 0.003305027959868312
2023-01-24 08:11:27.767433: step: 1612/530, loss: 0.01975034549832344
2023-01-24 08:11:28.872229: step: 1616/530, loss: 0.014768530614674091
2023-01-24 08:11:29.924803: step: 1620/530, loss: 0.03643510118126869
2023-01-24 08:11:30.996911: step: 1624/530, loss: 0.0020543818827718496
2023-01-24 08:11:32.081729: step: 1628/530, loss: 0.003917388617992401
2023-01-24 08:11:33.168277: step: 1632/530, loss: 8.823875396046788e-05
2023-01-24 08:11:34.254978: step: 1636/530, loss: 0.003380486276000738
2023-01-24 08:11:35.323788: step: 1640/530, loss: 0.0044584074057638645
2023-01-24 08:11:36.418772: step: 1644/530, loss: 0.036464858800172806
2023-01-24 08:11:37.503682: step: 1648/530, loss: 0.004702022764831781
2023-01-24 08:11:38.621469: step: 1652/530, loss: 0.017135631293058395
2023-01-24 08:11:39.709633: step: 1656/530, loss: 0.0071953521110117435
2023-01-24 08:11:40.804381: step: 1660/530, loss: 0.00426038634032011
2023-01-24 08:11:41.903303: step: 1664/530, loss: 0.007563033606857061
2023-01-24 08:11:42.993077: step: 1668/530, loss: 0.0027075540274381638
2023-01-24 08:11:44.082195: step: 1672/530, loss: 0.015235417522490025
2023-01-24 08:11:45.174127: step: 1676/530, loss: 0.1320732980966568
2023-01-24 08:11:46.261268: step: 1680/530, loss: 0.003960240166634321
2023-01-24 08:11:47.362236: step: 1684/530, loss: 0.0065732491202652454
2023-01-24 08:11:48.458286: step: 1688/530, loss: 0.05801035463809967
2023-01-24 08:11:49.560702: step: 1692/530, loss: 0.0005680571775883436
2023-01-24 08:11:50.645859: step: 1696/530, loss: 0.00609312579035759
2023-01-24 08:11:51.736886: step: 1700/530, loss: 0.00030032210634090006
2023-01-24 08:11:52.834762: step: 1704/530, loss: 0.007867347449064255
2023-01-24 08:11:53.911344: step: 1708/530, loss: 0.015998782590031624
2023-01-24 08:11:55.014001: step: 1712/530, loss: 0.011615244671702385
2023-01-24 08:11:56.122454: step: 1716/530, loss: 0.027224913239479065
2023-01-24 08:11:57.213349: step: 1720/530, loss: 0.007757535204291344
2023-01-24 08:11:58.303238: step: 1724/530, loss: 0.005203958600759506
2023-01-24 08:11:59.392595: step: 1728/530, loss: 0.007733961101621389
2023-01-24 08:12:00.478273: step: 1732/530, loss: 0.0973784476518631
2023-01-24 08:12:01.572018: step: 1736/530, loss: 0.007953282445669174
2023-01-24 08:12:02.662823: step: 1740/530, loss: 0.0162724070250988
2023-01-24 08:12:03.767743: step: 1744/530, loss: 0.006409160792827606
2023-01-24 08:12:04.838009: step: 1748/530, loss: 0.0072939214296638966
2023-01-24 08:12:05.928690: step: 1752/530, loss: 0.006528573110699654
2023-01-24 08:12:07.021204: step: 1756/530, loss: 0.0005678427987731993
2023-01-24 08:12:08.103263: step: 1760/530, loss: 0.0056610689498484135
2023-01-24 08:12:09.178131: step: 1764/530, loss: 0.03463749587535858
2023-01-24 08:12:10.254002: step: 1768/530, loss: 0.001118711894378066
2023-01-24 08:12:11.365718: step: 1772/530, loss: 0.008784106932580471
2023-01-24 08:12:12.449749: step: 1776/530, loss: 0.00478857709094882
2023-01-24 08:12:13.524313: step: 1780/530, loss: 0.00412032101303339
2023-01-24 08:12:14.615691: step: 1784/530, loss: 0.006077309604734182
2023-01-24 08:12:15.699490: step: 1788/530, loss: 0.007692502345889807
2023-01-24 08:12:16.787877: step: 1792/530, loss: 0.005792549811303616
2023-01-24 08:12:17.872567: step: 1796/530, loss: 0.0033693709410727024
2023-01-24 08:12:18.953671: step: 1800/530, loss: 0.0012090852251276374
2023-01-24 08:12:20.035347: step: 1804/530, loss: 0.020762303844094276
2023-01-24 08:12:21.127868: step: 1808/530, loss: 0.00416500074788928
2023-01-24 08:12:22.234898: step: 1812/530, loss: 0.02418254129588604
2023-01-24 08:12:23.316105: step: 1816/530, loss: 0.012921021319925785
2023-01-24 08:12:24.407635: step: 1820/530, loss: 0.004524185787886381
2023-01-24 08:12:25.507121: step: 1824/530, loss: 0.003047233447432518
2023-01-24 08:12:26.603724: step: 1828/530, loss: 0.013662545010447502
2023-01-24 08:12:27.678576: step: 1832/530, loss: 0.0187588632106781
2023-01-24 08:12:28.774046: step: 1836/530, loss: 0.005499811843037605
2023-01-24 08:12:29.885494: step: 1840/530, loss: 0.02362939529120922
2023-01-24 08:12:30.975989: step: 1844/530, loss: 0.004111357033252716
2023-01-24 08:12:32.070434: step: 1848/530, loss: 0.010315585881471634
2023-01-24 08:12:33.165026: step: 1852/530, loss: 0.0072876568883657455
2023-01-24 08:12:34.244896: step: 1856/530, loss: 0.010600189678370953
2023-01-24 08:12:35.337898: step: 1860/530, loss: 0.01006628479808569
2023-01-24 08:12:36.421629: step: 1864/530, loss: 0.004517877474427223
2023-01-24 08:12:37.505631: step: 1868/530, loss: 0.010671298950910568
2023-01-24 08:12:38.559704: step: 1872/530, loss: 0.0008903589914552867
2023-01-24 08:12:39.639315: step: 1876/530, loss: 0.06083684042096138
2023-01-24 08:12:40.723261: step: 1880/530, loss: 0.037631455808877945
2023-01-24 08:12:41.823503: step: 1884/530, loss: 0.0668218582868576
2023-01-24 08:12:42.892022: step: 1888/530, loss: 0.026623815298080444
2023-01-24 08:12:43.986699: step: 1892/530, loss: 0.033049069344997406
2023-01-24 08:12:45.055386: step: 1896/530, loss: 0.01622823253273964
2023-01-24 08:12:46.138322: step: 1900/530, loss: 0.0043643200770020485
2023-01-24 08:12:47.232043: step: 1904/530, loss: 0.009135270491242409
2023-01-24 08:12:48.300231: step: 1908/530, loss: 0.01555678527802229
2023-01-24 08:12:49.412138: step: 1912/530, loss: 0.010884417220950127
2023-01-24 08:12:50.494288: step: 1916/530, loss: 0.011741231195628643
2023-01-24 08:12:51.584449: step: 1920/530, loss: 0.006384402513504028
2023-01-24 08:12:52.649626: step: 1924/530, loss: 0.023064740002155304
2023-01-24 08:12:53.721954: step: 1928/530, loss: 0.007335499860346317
2023-01-24 08:12:54.833134: step: 1932/530, loss: 0.002174460794776678
2023-01-24 08:12:55.920996: step: 1936/530, loss: 0.0009123747004196048
2023-01-24 08:12:57.008367: step: 1940/530, loss: 0.03267615661025047
2023-01-24 08:12:58.088733: step: 1944/530, loss: 0.01721155270934105
2023-01-24 08:12:59.159217: step: 1948/530, loss: 0.00958101637661457
2023-01-24 08:13:00.252604: step: 1952/530, loss: 0.00603700103238225
2023-01-24 08:13:01.341763: step: 1956/530, loss: 0.002537440275773406
2023-01-24 08:13:02.411348: step: 1960/530, loss: 0.0025301428977400064
2023-01-24 08:13:03.503288: step: 1964/530, loss: 0.012461566366255283
2023-01-24 08:13:04.584609: step: 1968/530, loss: 0.023656077682971954
2023-01-24 08:13:05.669711: step: 1972/530, loss: 0.007463125512003899
2023-01-24 08:13:06.741094: step: 1976/530, loss: 0.003984319977462292
2023-01-24 08:13:07.829668: step: 1980/530, loss: 0.018382729962468147
2023-01-24 08:13:08.924245: step: 1984/530, loss: 0.0034127768594771624
2023-01-24 08:13:10.017963: step: 1988/530, loss: 0.01551706250756979
2023-01-24 08:13:11.118361: step: 1992/530, loss: 0.020493097603321075
2023-01-24 08:13:12.195731: step: 1996/530, loss: 0.05537712201476097
2023-01-24 08:13:13.270779: step: 2000/530, loss: 0.004812260624021292
2023-01-24 08:13:14.361069: step: 2004/530, loss: 0.004523058421909809
2023-01-24 08:13:15.450756: step: 2008/530, loss: 0.009608150459825993
2023-01-24 08:13:16.540457: step: 2012/530, loss: 0.004829746205359697
2023-01-24 08:13:17.632251: step: 2016/530, loss: 0.004766157828271389
2023-01-24 08:13:18.719873: step: 2020/530, loss: 0.006347528658807278
2023-01-24 08:13:19.793423: step: 2024/530, loss: 0.022239279001951218
2023-01-24 08:13:20.862221: step: 2028/530, loss: 0.0022849151864647865
2023-01-24 08:13:21.944430: step: 2032/530, loss: 0.01862087845802307
2023-01-24 08:13:23.017573: step: 2036/530, loss: 0.006219734437763691
2023-01-24 08:13:24.115115: step: 2040/530, loss: 0.006357923150062561
2023-01-24 08:13:25.215593: step: 2044/530, loss: 0.004786049947142601
2023-01-24 08:13:26.298295: step: 2048/530, loss: 0.003965491894632578
2023-01-24 08:13:27.368197: step: 2052/530, loss: 0.007487200200557709
2023-01-24 08:13:28.450186: step: 2056/530, loss: 0.014578355476260185
2023-01-24 08:13:29.533029: step: 2060/530, loss: 0.0032622357830405235
2023-01-24 08:13:30.623479: step: 2064/530, loss: 0.008332009427249432
2023-01-24 08:13:31.719601: step: 2068/530, loss: 0.01456921361386776
2023-01-24 08:13:32.807308: step: 2072/530, loss: 0.008971704170107841
2023-01-24 08:13:33.890279: step: 2076/530, loss: 0.008645850233733654
2023-01-24 08:13:34.980276: step: 2080/530, loss: 0.012069402262568474
2023-01-24 08:13:36.068798: step: 2084/530, loss: 0.002603366272523999
2023-01-24 08:13:37.145297: step: 2088/530, loss: 0.0016511273570358753
2023-01-24 08:13:38.242487: step: 2092/530, loss: 0.011426740325987339
2023-01-24 08:13:39.320990: step: 2096/530, loss: 0.0041406708769500256
2023-01-24 08:13:40.382359: step: 2100/530, loss: 0.005497670266777277
2023-01-24 08:13:41.471900: step: 2104/530, loss: 0.0884915366768837
2023-01-24 08:13:42.569828: step: 2108/530, loss: 0.0007639945833943784
2023-01-24 08:13:43.647023: step: 2112/530, loss: 0.012787983752787113
2023-01-24 08:13:44.755384: step: 2116/530, loss: 0.00024670781567692757
2023-01-24 08:13:45.827926: step: 2120/530, loss: 0.02791227400302887
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35044076973597516, 'r': 0.34578595875276485, 'f1': 0.3480978037492017}, 'combined': 0.2564931185520433, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34025965263320723, 'r': 0.2757044616197924, 'f1': 0.3045992523572379}, 'combined': 0.1891721672534425, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3767330036928605, 'r': 0.323118249846628, 'f1': 0.34787194620872924}, 'combined': 0.2563266972064321, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34323258254017047, 'r': 0.26997345425096414, 'f1': 0.3022269200243094}, 'combined': 0.18769882401509744, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, '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': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 4}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.38333329883077744, 'r': 0.3302339993722447, 'f1': 0.35480798709311506}, 'combined': 0.26143746417387426, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34574514535424083, 'r': 0.27194973883594437, 'f1': 0.3044393094048404}, 'combined': 0.1890728342619535, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 3}
******************************
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 08:16:21.963976: step: 4/530, loss: 0.009927969425916672
2023-01-24 08:16:23.038254: step: 8/530, loss: 0.005128829274326563
2023-01-24 08:16:24.109399: step: 12/530, loss: 0.04475068673491478
2023-01-24 08:16:25.210483: step: 16/530, loss: 0.009328820742666721
2023-01-24 08:16:26.265335: step: 20/530, loss: 0.00403439300134778
2023-01-24 08:16:27.331863: step: 24/530, loss: 0.01125125028192997
2023-01-24 08:16:28.423470: step: 28/530, loss: 0.0048458450473845005
2023-01-24 08:16:29.497599: step: 32/530, loss: 0.013264902867376804
2023-01-24 08:16:30.591753: step: 36/530, loss: 0.018973875790834427
2023-01-24 08:16:31.676733: step: 40/530, loss: 0.016321133822202682
2023-01-24 08:16:32.759002: step: 44/530, loss: 0.010839315131306648
2023-01-24 08:16:33.832339: step: 48/530, loss: 0.006358737591654062
2023-01-24 08:16:34.892154: step: 52/530, loss: 0.008591302670538425
2023-01-24 08:16:35.980716: step: 56/530, loss: 0.0012758837547153234
2023-01-24 08:16:37.051187: step: 60/530, loss: 0.004210789687931538
2023-01-24 08:16:38.151489: step: 64/530, loss: 0.011850784532725811
2023-01-24 08:16:39.238905: step: 68/530, loss: 0.00352488667704165
2023-01-24 08:16:40.325829: step: 72/530, loss: 0.0006779723917134106
2023-01-24 08:16:41.418025: step: 76/530, loss: 0.019818367436528206
2023-01-24 08:16:42.512901: step: 80/530, loss: 0.002778246533125639
2023-01-24 08:16:43.606886: step: 84/530, loss: 0.01132697518914938
2023-01-24 08:16:44.701678: step: 88/530, loss: 0.02920081838965416
2023-01-24 08:16:45.832916: step: 92/530, loss: 0.06911709159612656
2023-01-24 08:16:46.940932: step: 96/530, loss: 0.006899694446474314
2023-01-24 08:16:48.022688: step: 100/530, loss: 0.01456447783857584
2023-01-24 08:16:49.106744: step: 104/530, loss: 0.006375570315867662
2023-01-24 08:16:50.197685: step: 108/530, loss: 0.0024532810784876347
2023-01-24 08:16:51.287849: step: 112/530, loss: 0.0017753717256709933
2023-01-24 08:16:52.362743: step: 116/530, loss: 0.011672258377075195
2023-01-24 08:16:53.481575: step: 120/530, loss: 0.00401636678725481
2023-01-24 08:16:54.608756: step: 124/530, loss: 0.01942227967083454
2023-01-24 08:16:55.687862: step: 128/530, loss: 0.005506512243300676
2023-01-24 08:16:56.785211: step: 132/530, loss: 0.0021414831280708313
2023-01-24 08:16:57.859496: step: 136/530, loss: 0.005920359864830971
2023-01-24 08:16:58.952723: step: 140/530, loss: 0.003510456532239914
2023-01-24 08:17:00.017006: step: 144/530, loss: 0.002353669609874487
2023-01-24 08:17:01.106843: step: 148/530, loss: 0.010640815831720829
2023-01-24 08:17:02.198246: step: 152/530, loss: 0.03576274216175079
2023-01-24 08:17:03.267803: step: 156/530, loss: 0.008341441862285137
2023-01-24 08:17:04.357343: step: 160/530, loss: 0.003986270632594824
2023-01-24 08:17:05.425944: step: 164/530, loss: 0.001406124560162425
2023-01-24 08:17:06.500924: step: 168/530, loss: 0.009706404060125351
2023-01-24 08:17:07.571983: step: 172/530, loss: 0.004061954095959663
2023-01-24 08:17:08.659499: step: 176/530, loss: 0.005667248275130987
2023-01-24 08:17:09.747295: step: 180/530, loss: 0.005562384147197008
2023-01-24 08:17:10.853224: step: 184/530, loss: 0.008082667365670204
2023-01-24 08:17:11.932667: step: 188/530, loss: 0.007437993306666613
2023-01-24 08:17:12.989604: step: 192/530, loss: 0.004453169647604227
2023-01-24 08:17:14.072033: step: 196/530, loss: 5.284436701913364e-05
2023-01-24 08:17:15.174190: step: 200/530, loss: 0.03970012813806534
2023-01-24 08:17:16.276010: step: 204/530, loss: 0.0004708790220320225
2023-01-24 08:17:17.345253: step: 208/530, loss: 0.01243553962558508
2023-01-24 08:17:18.431280: step: 212/530, loss: 0.014587502926588058
2023-01-24 08:17:19.500917: step: 216/530, loss: 0.00047801644541323185
2023-01-24 08:17:20.568194: step: 220/530, loss: 0.01798751763999462
2023-01-24 08:17:21.643642: step: 224/530, loss: 0.002520455978810787
2023-01-24 08:17:22.731667: step: 228/530, loss: 0.006364905741065741
2023-01-24 08:17:23.805485: step: 232/530, loss: 0.028661977499723434
2023-01-24 08:17:24.902530: step: 236/530, loss: 0.004739727824926376
2023-01-24 08:17:25.985267: step: 240/530, loss: 0.0007106245029717684
2023-01-24 08:17:27.074166: step: 244/530, loss: 0.0038836118765175343
2023-01-24 08:17:28.143533: step: 248/530, loss: 0.0033591161482036114
2023-01-24 08:17:29.213311: step: 252/530, loss: 0.01268624048680067
2023-01-24 08:17:30.292819: step: 256/530, loss: 0.0034052045084536076
2023-01-24 08:17:31.370911: step: 260/530, loss: 0.004034136421978474
2023-01-24 08:17:32.458082: step: 264/530, loss: 0.004076881799846888
2023-01-24 08:17:33.530860: step: 268/530, loss: 0.0006219844799488783
2023-01-24 08:17:34.602873: step: 272/530, loss: 0.0031220486853271723
2023-01-24 08:17:35.705951: step: 276/530, loss: 0.00915757566690445
2023-01-24 08:17:36.796254: step: 280/530, loss: 0.0012872337829321623
2023-01-24 08:17:37.882795: step: 284/530, loss: 0.002386258915066719
2023-01-24 08:17:38.967936: step: 288/530, loss: 0.004436228424310684
2023-01-24 08:17:40.052492: step: 292/530, loss: 0.006758742965757847
2023-01-24 08:17:41.138861: step: 296/530, loss: 0.007563683204352856
2023-01-24 08:17:42.246080: step: 300/530, loss: 0.005827596411108971
2023-01-24 08:17:43.333797: step: 304/530, loss: 0.0043299635872244835
2023-01-24 08:17:44.432243: step: 308/530, loss: 0.00750034861266613
2023-01-24 08:17:45.513337: step: 312/530, loss: 0.005572655238211155
2023-01-24 08:17:46.599742: step: 316/530, loss: 0.003433826146647334
2023-01-24 08:17:47.670138: step: 320/530, loss: 0.00217996072024107
2023-01-24 08:17:48.760930: step: 324/530, loss: 0.012475233525037766
2023-01-24 08:17:49.843070: step: 328/530, loss: 0.0126360934227705
2023-01-24 08:17:50.948574: step: 332/530, loss: 0.006459742784500122
2023-01-24 08:17:52.035997: step: 336/530, loss: 0.006656565237790346
2023-01-24 08:17:53.116019: step: 340/530, loss: 0.01680254004895687
2023-01-24 08:17:54.183078: step: 344/530, loss: 0.003458525286987424
2023-01-24 08:17:55.273673: step: 348/530, loss: 0.007182309869676828
2023-01-24 08:17:56.371771: step: 352/530, loss: 0.0039078895933926105
2023-01-24 08:17:57.440285: step: 356/530, loss: 0.0017451149178668857
2023-01-24 08:17:58.495705: step: 360/530, loss: 3.626816032920033e-05
2023-01-24 08:17:59.584937: step: 364/530, loss: 0.005791897885501385
2023-01-24 08:18:00.673041: step: 368/530, loss: 0.005260811187326908
2023-01-24 08:18:01.743880: step: 372/530, loss: 0.0026299997698515654
2023-01-24 08:18:02.837865: step: 376/530, loss: 0.029537083581089973
2023-01-24 08:18:03.939466: step: 380/530, loss: 0.02752068266272545
2023-01-24 08:18:05.009407: step: 384/530, loss: 0.005755385383963585
2023-01-24 08:18:06.098541: step: 388/530, loss: 0.005558202508836985
2023-01-24 08:18:07.173259: step: 392/530, loss: 0.047580499202013016
2023-01-24 08:18:08.250062: step: 396/530, loss: 0.035065244883298874
2023-01-24 08:18:09.347098: step: 400/530, loss: 0.0002280263288412243
2023-01-24 08:18:10.429533: step: 404/530, loss: 0.0006840199930593371
2023-01-24 08:18:11.492322: step: 408/530, loss: 0.0070375413633883
2023-01-24 08:18:12.557420: step: 412/530, loss: 0.013827987015247345
2023-01-24 08:18:13.640292: step: 416/530, loss: 0.008810057304799557
2023-01-24 08:18:14.725822: step: 420/530, loss: 0.0017100953264161944
2023-01-24 08:18:15.823632: step: 424/530, loss: 0.005180246662348509
2023-01-24 08:18:16.918772: step: 428/530, loss: 0.02431401051580906
2023-01-24 08:18:17.985252: step: 432/530, loss: 0.01683223247528076
2023-01-24 08:18:19.084313: step: 436/530, loss: 0.030931025743484497
2023-01-24 08:18:20.196836: step: 440/530, loss: 0.00038184644654393196
2023-01-24 08:18:21.307924: step: 444/530, loss: 0.003955648746341467
2023-01-24 08:18:22.394101: step: 448/530, loss: 0.03574395924806595
2023-01-24 08:18:23.464624: step: 452/530, loss: 0.007264542859047651
2023-01-24 08:18:24.581411: step: 456/530, loss: 0.015016872435808182
2023-01-24 08:18:25.675040: step: 460/530, loss: 0.0055486224591732025
2023-01-24 08:18:26.746627: step: 464/530, loss: 0.007629780564457178
2023-01-24 08:18:27.834592: step: 468/530, loss: 0.005283321253955364
2023-01-24 08:18:28.905171: step: 472/530, loss: 0.0037030719686299562
2023-01-24 08:18:29.990780: step: 476/530, loss: 0.009584475308656693
2023-01-24 08:18:31.075574: step: 480/530, loss: 0.10841675102710724
2023-01-24 08:18:32.162478: step: 484/530, loss: 0.007172941230237484
2023-01-24 08:18:33.262124: step: 488/530, loss: 0.007054260466247797
2023-01-24 08:18:34.332634: step: 492/530, loss: 0.0069967638701200485
2023-01-24 08:18:35.417824: step: 496/530, loss: 0.007977736182510853
2023-01-24 08:18:36.486941: step: 500/530, loss: 0.005747297313064337
2023-01-24 08:18:37.574610: step: 504/530, loss: 0.014383424073457718
2023-01-24 08:18:38.640581: step: 508/530, loss: 0.006413948722183704
2023-01-24 08:18:39.716922: step: 512/530, loss: 0.021535467356443405
2023-01-24 08:18:40.800414: step: 516/530, loss: 0.013873053714632988
2023-01-24 08:18:41.885014: step: 520/530, loss: 0.0021121506579220295
2023-01-24 08:18:42.983408: step: 524/530, loss: 0.007193238474428654
2023-01-24 08:18:44.076363: step: 528/530, loss: 0.005421261768788099
2023-01-24 08:18:45.155398: step: 532/530, loss: 0.02269272319972515
2023-01-24 08:18:46.248287: step: 536/530, loss: 0.020114630460739136
2023-01-24 08:18:47.334547: step: 540/530, loss: 0.028823966160416603
2023-01-24 08:18:48.395273: step: 544/530, loss: 0.005062198266386986
2023-01-24 08:18:49.504048: step: 548/530, loss: 0.004133230075240135
2023-01-24 08:18:50.602330: step: 552/530, loss: 0.004652720410376787
2023-01-24 08:18:51.698662: step: 556/530, loss: 0.0068655614741146564
2023-01-24 08:18:52.790038: step: 560/530, loss: 0.01430361345410347
2023-01-24 08:18:53.882332: step: 564/530, loss: 0.005681750364601612
2023-01-24 08:18:54.952304: step: 568/530, loss: 0.0023478225339204073
2023-01-24 08:18:56.046643: step: 572/530, loss: 0.0022609184961766005
2023-01-24 08:18:57.150613: step: 576/530, loss: 0.006015228573232889
2023-01-24 08:18:58.233257: step: 580/530, loss: 0.004941890016198158
2023-01-24 08:18:59.308164: step: 584/530, loss: 0.017170375213027
2023-01-24 08:19:00.420661: step: 588/530, loss: 0.02504393830895424
2023-01-24 08:19:01.501797: step: 592/530, loss: 0.012134358286857605
2023-01-24 08:19:02.591092: step: 596/530, loss: 0.031021377071738243
2023-01-24 08:19:03.658566: step: 600/530, loss: 0.0015711723826825619
2023-01-24 08:19:04.711043: step: 604/530, loss: 0.0014493025373667479
2023-01-24 08:19:05.809891: step: 608/530, loss: 0.020252171903848648
2023-01-24 08:19:06.904319: step: 612/530, loss: 0.0039865863509476185
2023-01-24 08:19:07.978979: step: 616/530, loss: 0.016128981485962868
2023-01-24 08:19:09.036167: step: 620/530, loss: 0.038906656205654144
2023-01-24 08:19:10.148073: step: 624/530, loss: 0.010242643766105175
2023-01-24 08:19:11.205314: step: 628/530, loss: 0.010289092548191547
2023-01-24 08:19:12.293049: step: 632/530, loss: 0.0020376669708639383
2023-01-24 08:19:13.359507: step: 636/530, loss: 0.04130535572767258
2023-01-24 08:19:14.431441: step: 640/530, loss: 0.008746541105210781
2023-01-24 08:19:15.525106: step: 644/530, loss: 0.009842237457633018
2023-01-24 08:19:16.618466: step: 648/530, loss: 0.022690266370773315
2023-01-24 08:19:17.695262: step: 652/530, loss: 0.017371635884046555
2023-01-24 08:19:18.780313: step: 656/530, loss: 0.004394746385514736
2023-01-24 08:19:19.855329: step: 660/530, loss: 0.005064487922936678
2023-01-24 08:19:20.927251: step: 664/530, loss: 0.0037051455583423376
2023-01-24 08:19:21.994114: step: 668/530, loss: 0.0002648273075465113
2023-01-24 08:19:23.069643: step: 672/530, loss: 0.0028208144940435886
2023-01-24 08:19:24.167120: step: 676/530, loss: 0.01486341655254364
2023-01-24 08:19:25.250126: step: 680/530, loss: 0.013482906855642796
2023-01-24 08:19:26.318333: step: 684/530, loss: 0.0019089989364147186
2023-01-24 08:19:27.395662: step: 688/530, loss: 0.025296710431575775
2023-01-24 08:19:28.487491: step: 692/530, loss: 0.0018094453262165189
2023-01-24 08:19:29.592846: step: 696/530, loss: 0.005951243452727795
2023-01-24 08:19:30.659942: step: 700/530, loss: 0.002945193089544773
2023-01-24 08:19:31.756111: step: 704/530, loss: 0.004906233865767717
2023-01-24 08:19:32.832751: step: 708/530, loss: 0.0020124120637774467
2023-01-24 08:19:33.902467: step: 712/530, loss: 0.004250792786478996
2023-01-24 08:19:35.013675: step: 716/530, loss: 0.06334321945905685
2023-01-24 08:19:36.102546: step: 720/530, loss: 0.012508920393884182
2023-01-24 08:19:37.175831: step: 724/530, loss: 0.0014923866838216782
2023-01-24 08:19:38.278596: step: 728/530, loss: 0.00275184097699821
2023-01-24 08:19:39.369201: step: 732/530, loss: 0.008599773980677128
2023-01-24 08:19:40.483044: step: 736/530, loss: 0.0076149520464241505
2023-01-24 08:19:41.574472: step: 740/530, loss: 0.02288990281522274
2023-01-24 08:19:42.668724: step: 744/530, loss: 0.006646342575550079
2023-01-24 08:19:43.757338: step: 748/530, loss: 0.0033843473065644503
2023-01-24 08:19:44.835288: step: 752/530, loss: 0.0006627660477533937
2023-01-24 08:19:45.927394: step: 756/530, loss: 0.003157450584694743
2023-01-24 08:19:47.015361: step: 760/530, loss: 0.028473051264882088
2023-01-24 08:19:48.122253: step: 764/530, loss: 0.004545000847429037
2023-01-24 08:19:49.221495: step: 768/530, loss: 0.0012491007801145315
2023-01-24 08:19:50.303397: step: 772/530, loss: 0.005975918844342232
2023-01-24 08:19:51.401882: step: 776/530, loss: 0.03943159058690071
2023-01-24 08:19:52.535363: step: 780/530, loss: 0.01770174689590931
2023-01-24 08:19:53.628410: step: 784/530, loss: 0.008249512873589993
2023-01-24 08:19:54.704834: step: 788/530, loss: 0.011769704520702362
2023-01-24 08:19:55.784809: step: 792/530, loss: 0.008093920536339283
2023-01-24 08:19:56.869057: step: 796/530, loss: 0.009733738377690315
2023-01-24 08:19:57.963230: step: 800/530, loss: 0.0033110210206359625
2023-01-24 08:19:59.052322: step: 804/530, loss: 0.006189823616296053
2023-01-24 08:20:00.167165: step: 808/530, loss: 0.018803108483552933
2023-01-24 08:20:01.253237: step: 812/530, loss: 0.05368834733963013
2023-01-24 08:20:02.345006: step: 816/530, loss: 0.014654400758445263
2023-01-24 08:20:03.423842: step: 820/530, loss: 0.015123249962925911
2023-01-24 08:20:04.536680: step: 824/530, loss: 0.02406453527510166
2023-01-24 08:20:05.624726: step: 828/530, loss: 0.0017264683265239
2023-01-24 08:20:06.735158: step: 832/530, loss: 0.006244051735848188
2023-01-24 08:20:07.804243: step: 836/530, loss: 0.0006846334435977042
2023-01-24 08:20:08.883772: step: 840/530, loss: 0.013209469616413116
2023-01-24 08:20:09.993466: step: 844/530, loss: 0.004798524081707001
2023-01-24 08:20:11.069132: step: 848/530, loss: 0.016030339524149895
2023-01-24 08:20:12.151247: step: 852/530, loss: 0.0027581085450947285
2023-01-24 08:20:13.248497: step: 856/530, loss: 0.0014344928786158562
2023-01-24 08:20:14.324813: step: 860/530, loss: 0.01735539920628071
2023-01-24 08:20:15.426366: step: 864/530, loss: 0.006705708801746368
2023-01-24 08:20:16.514311: step: 868/530, loss: 0.01609933376312256
2023-01-24 08:20:17.595658: step: 872/530, loss: 0.034301504492759705
2023-01-24 08:20:18.668312: step: 876/530, loss: 0.005869516171514988
2023-01-24 08:20:19.739878: step: 880/530, loss: 0.008199592120945454
2023-01-24 08:20:20.822890: step: 884/530, loss: 0.003910835832357407
2023-01-24 08:20:21.931033: step: 888/530, loss: 0.02594786509871483
2023-01-24 08:20:23.027818: step: 892/530, loss: 0.0013578069629147649
2023-01-24 08:20:24.102109: step: 896/530, loss: 0.006081853527575731
2023-01-24 08:20:25.201673: step: 900/530, loss: 0.004724468570202589
2023-01-24 08:20:26.253321: step: 904/530, loss: 0.005373109132051468
2023-01-24 08:20:27.343941: step: 908/530, loss: 0.011944221332669258
2023-01-24 08:20:28.449917: step: 912/530, loss: 0.015439932234585285
2023-01-24 08:20:29.541042: step: 916/530, loss: 0.004212393891066313
2023-01-24 08:20:30.609372: step: 920/530, loss: 0.005986310075968504
2023-01-24 08:20:31.717664: step: 924/530, loss: 0.017463088035583496
2023-01-24 08:20:32.840857: step: 928/530, loss: 0.010621001943945885
2023-01-24 08:20:33.905778: step: 932/530, loss: 0.0020706690847873688
2023-01-24 08:20:35.028855: step: 936/530, loss: 0.017201585695147514
2023-01-24 08:20:36.121148: step: 940/530, loss: 0.0015285331755876541
2023-01-24 08:20:37.207732: step: 944/530, loss: 0.004085628781467676
2023-01-24 08:20:38.277487: step: 948/530, loss: 0.0055943639017641544
2023-01-24 08:20:39.398636: step: 952/530, loss: 0.0012125269277021289
2023-01-24 08:20:40.497971: step: 956/530, loss: 0.03324398770928383
2023-01-24 08:20:41.573222: step: 960/530, loss: 0.036107923835515976
2023-01-24 08:20:42.644998: step: 964/530, loss: 0.010087436996400356
2023-01-24 08:20:43.758966: step: 968/530, loss: 0.021248996257781982
2023-01-24 08:20:44.887946: step: 972/530, loss: 0.010942698456346989
2023-01-24 08:20:45.988135: step: 976/530, loss: 0.009958078153431416
2023-01-24 08:20:47.081863: step: 980/530, loss: 0.008440959267318249
2023-01-24 08:20:48.172652: step: 984/530, loss: 0.0015444383025169373
2023-01-24 08:20:49.264632: step: 988/530, loss: 0.011825080029666424
2023-01-24 08:20:50.345537: step: 992/530, loss: 0.042501576244831085
2023-01-24 08:20:51.435741: step: 996/530, loss: 0.022968651726841927
2023-01-24 08:20:52.518753: step: 1000/530, loss: 0.00941373035311699
2023-01-24 08:20:53.638994: step: 1004/530, loss: 0.003551363479346037
2023-01-24 08:20:54.712971: step: 1008/530, loss: 0.0031270224135369062
2023-01-24 08:20:55.786952: step: 1012/530, loss: 0.0016350416699424386
2023-01-24 08:20:56.896467: step: 1016/530, loss: 0.014712892472743988
2023-01-24 08:20:57.966669: step: 1020/530, loss: 0.006596389692276716
2023-01-24 08:20:59.041374: step: 1024/530, loss: 0.012117584235966206
2023-01-24 08:21:00.131599: step: 1028/530, loss: 0.004741362761706114
2023-01-24 08:21:01.217221: step: 1032/530, loss: 0.00014142485451884568
2023-01-24 08:21:02.317229: step: 1036/530, loss: 0.005007429048418999
2023-01-24 08:21:03.405449: step: 1040/530, loss: 0.02516634203493595
2023-01-24 08:21:04.504466: step: 1044/530, loss: 0.016056302934885025
2023-01-24 08:21:05.582189: step: 1048/530, loss: 0.003571026958525181
2023-01-24 08:21:06.678103: step: 1052/530, loss: 0.005324543919414282
2023-01-24 08:21:07.778541: step: 1056/530, loss: 0.009494753554463387
2023-01-24 08:21:08.852834: step: 1060/530, loss: 0.007454304024577141
2023-01-24 08:21:09.964815: step: 1064/530, loss: 0.003984508570283651
2023-01-24 08:21:11.058112: step: 1068/530, loss: 0.007783366832882166
2023-01-24 08:21:12.152327: step: 1072/530, loss: 0.0051447865553200245
2023-01-24 08:21:13.253083: step: 1076/530, loss: 0.024477636441588402
2023-01-24 08:21:14.355065: step: 1080/530, loss: 0.027586881071329117
2023-01-24 08:21:15.444911: step: 1084/530, loss: 0.0050377678126096725
2023-01-24 08:21:16.535507: step: 1088/530, loss: 0.0016665261937305331
2023-01-24 08:21:17.600816: step: 1092/530, loss: 0.022634021937847137
2023-01-24 08:21:18.695742: step: 1096/530, loss: 0.008211866952478886
2023-01-24 08:21:19.760376: step: 1100/530, loss: 0.007138671353459358
2023-01-24 08:21:20.847711: step: 1104/530, loss: 0.03303040564060211
2023-01-24 08:21:21.976141: step: 1108/530, loss: 0.006315619219094515
2023-01-24 08:21:23.045586: step: 1112/530, loss: 0.006362857297062874
2023-01-24 08:21:24.140402: step: 1116/530, loss: 0.003907065838575363
2023-01-24 08:21:25.243325: step: 1120/530, loss: 0.00701772328466177
2023-01-24 08:21:26.321489: step: 1124/530, loss: 0.0060411663725972176
2023-01-24 08:21:27.423933: step: 1128/530, loss: 0.0063125137239694595
2023-01-24 08:21:28.511480: step: 1132/530, loss: 0.0009099377784878016
2023-01-24 08:21:29.598576: step: 1136/530, loss: 0.00436819763854146
2023-01-24 08:21:30.692399: step: 1140/530, loss: 0.006643245927989483
2023-01-24 08:21:31.788659: step: 1144/530, loss: 0.05079443007707596
2023-01-24 08:21:32.883397: step: 1148/530, loss: 0.004961497150361538
2023-01-24 08:21:33.980458: step: 1152/530, loss: 0.004648693837225437
2023-01-24 08:21:35.062254: step: 1156/530, loss: 0.009455114603042603
2023-01-24 08:21:36.140581: step: 1160/530, loss: 0.003025786718353629
2023-01-24 08:21:37.222011: step: 1164/530, loss: 0.002651132410392165
2023-01-24 08:21:38.296390: step: 1168/530, loss: 0.006034562364220619
2023-01-24 08:21:39.392384: step: 1172/530, loss: 0.055347051471471786
2023-01-24 08:21:40.495372: step: 1176/530, loss: 0.04707120358943939
2023-01-24 08:21:41.550361: step: 1180/530, loss: 0.00532685499638319
2023-01-24 08:21:42.633225: step: 1184/530, loss: 0.03385983780026436
2023-01-24 08:21:43.720922: step: 1188/530, loss: 0.006398843601346016
2023-01-24 08:21:44.818404: step: 1192/530, loss: 0.004570150747895241
2023-01-24 08:21:45.910585: step: 1196/530, loss: 0.0069955140352249146
2023-01-24 08:21:46.975555: step: 1200/530, loss: 0.016269484534859657
2023-01-24 08:21:48.041320: step: 1204/530, loss: 0.008860309608280659
2023-01-24 08:21:49.130607: step: 1208/530, loss: 0.001976356143131852
2023-01-24 08:21:50.221366: step: 1212/530, loss: 0.0010373091790825129
2023-01-24 08:21:51.322204: step: 1216/530, loss: 0.005320926196873188
2023-01-24 08:21:52.413875: step: 1220/530, loss: 0.02453349344432354
2023-01-24 08:21:53.484041: step: 1224/530, loss: 0.02141612395644188
2023-01-24 08:21:54.563510: step: 1228/530, loss: 0.0006792772328481078
2023-01-24 08:21:55.672540: step: 1232/530, loss: 0.004519452340900898
2023-01-24 08:21:56.752418: step: 1236/530, loss: 0.03056146204471588
2023-01-24 08:21:57.828007: step: 1240/530, loss: 0.004883999936282635
2023-01-24 08:21:58.932545: step: 1244/530, loss: 0.005924487952142954
2023-01-24 08:22:00.043456: step: 1248/530, loss: 0.02378247119486332
2023-01-24 08:22:01.129251: step: 1252/530, loss: 0.01055564358830452
2023-01-24 08:22:02.216681: step: 1256/530, loss: 0.007359538692981005
2023-01-24 08:22:03.303098: step: 1260/530, loss: 0.008896327577531338
2023-01-24 08:22:04.427316: step: 1264/530, loss: 0.0075872051529586315
2023-01-24 08:22:05.514642: step: 1268/530, loss: 0.004266760777682066
2023-01-24 08:22:06.617905: step: 1272/530, loss: 0.038588110357522964
2023-01-24 08:22:07.708632: step: 1276/530, loss: 0.008576435036957264
2023-01-24 08:22:08.798359: step: 1280/530, loss: 0.028927817940711975
2023-01-24 08:22:09.915665: step: 1284/530, loss: 0.0011064070276916027
2023-01-24 08:22:10.999417: step: 1288/530, loss: 0.024422533810138702
2023-01-24 08:22:12.085652: step: 1292/530, loss: 0.04459747299551964
2023-01-24 08:22:13.150156: step: 1296/530, loss: 0.00013573789328802377
2023-01-24 08:22:14.223618: step: 1300/530, loss: 0.03848407417535782
2023-01-24 08:22:15.338269: step: 1304/530, loss: 0.01567724347114563
2023-01-24 08:22:16.455444: step: 1308/530, loss: 0.07717403769493103
2023-01-24 08:22:17.539268: step: 1312/530, loss: 0.0018159148748964071
2023-01-24 08:22:18.637236: step: 1316/530, loss: 0.031898293644189835
2023-01-24 08:22:19.728202: step: 1320/530, loss: 0.0041343942284584045
2023-01-24 08:22:20.830175: step: 1324/530, loss: 0.0022816993296146393
2023-01-24 08:22:21.920418: step: 1328/530, loss: 0.0031828333158046007
2023-01-24 08:22:22.997309: step: 1332/530, loss: 0.00687678437680006
2023-01-24 08:22:24.079438: step: 1336/530, loss: 0.005433598533272743
2023-01-24 08:22:25.162563: step: 1340/530, loss: 0.00604582391679287
2023-01-24 08:22:26.257095: step: 1344/530, loss: 0.0007604804704897106
2023-01-24 08:22:27.406034: step: 1348/530, loss: 0.042319100350141525
2023-01-24 08:22:28.481009: step: 1352/530, loss: 0.0055596185848116875
2023-01-24 08:22:29.560379: step: 1356/530, loss: 0.006614349782466888
2023-01-24 08:22:30.656003: step: 1360/530, loss: 0.002728455699980259
2023-01-24 08:22:31.733754: step: 1364/530, loss: 0.0019447727827355266
2023-01-24 08:22:32.814906: step: 1368/530, loss: 0.03412714973092079
2023-01-24 08:22:33.901525: step: 1372/530, loss: 0.008057081140577793
2023-01-24 08:22:34.990217: step: 1376/530, loss: 0.009723569266498089
2023-01-24 08:22:36.058566: step: 1380/530, loss: 0.0020942145492881536
2023-01-24 08:22:37.144376: step: 1384/530, loss: 0.037779707461595535
2023-01-24 08:22:38.240120: step: 1388/530, loss: 0.004162820987403393
2023-01-24 08:22:39.356891: step: 1392/530, loss: 0.0030314435716718435
2023-01-24 08:22:40.454894: step: 1396/530, loss: 0.008005054667592049
2023-01-24 08:22:41.535330: step: 1400/530, loss: 0.015445479191839695
2023-01-24 08:22:42.634497: step: 1404/530, loss: 0.0054588885977864265
2023-01-24 08:22:43.726105: step: 1408/530, loss: 0.0009541259496472776
2023-01-24 08:22:44.811557: step: 1412/530, loss: 3.309938983875327e-05
2023-01-24 08:22:45.928219: step: 1416/530, loss: 0.0037648354191333055
2023-01-24 08:22:47.036038: step: 1420/530, loss: 0.009427951648831367
2023-01-24 08:22:48.134756: step: 1424/530, loss: 0.00912496168166399
2023-01-24 08:22:49.201590: step: 1428/530, loss: 0.0034798718988895416
2023-01-24 08:22:50.295515: step: 1432/530, loss: 0.0017370186978951097
2023-01-24 08:22:51.373634: step: 1436/530, loss: 0.00719187268987298
2023-01-24 08:22:52.453481: step: 1440/530, loss: 0.012083577923476696
2023-01-24 08:22:53.531698: step: 1444/530, loss: 0.029020706191658974
2023-01-24 08:22:54.635549: step: 1448/530, loss: 0.019146781414747238
2023-01-24 08:22:55.734357: step: 1452/530, loss: 0.004539281129837036
2023-01-24 08:22:56.812120: step: 1456/530, loss: 0.0032251356169581413
2023-01-24 08:22:57.913234: step: 1460/530, loss: 0.005161783192306757
2023-01-24 08:22:59.001190: step: 1464/530, loss: 0.002296453109011054
2023-01-24 08:23:00.076600: step: 1468/530, loss: 0.014328506775200367
2023-01-24 08:23:01.183404: step: 1472/530, loss: 0.025557201355695724
2023-01-24 08:23:02.275898: step: 1476/530, loss: 0.024794891476631165
2023-01-24 08:23:03.355257: step: 1480/530, loss: 0.003375542815774679
2023-01-24 08:23:04.469907: step: 1484/530, loss: 0.039767853915691376
2023-01-24 08:23:05.572604: step: 1488/530, loss: 0.005468260031193495
2023-01-24 08:23:06.664344: step: 1492/530, loss: 0.008726963773369789
2023-01-24 08:23:07.758615: step: 1496/530, loss: 0.005459923762828112
2023-01-24 08:23:08.860856: step: 1500/530, loss: 0.0030650740955024958
2023-01-24 08:23:09.958120: step: 1504/530, loss: 0.0014649203512817621
2023-01-24 08:23:11.059681: step: 1508/530, loss: 0.005837735719978809
2023-01-24 08:23:12.135939: step: 1512/530, loss: 0.0023033074103295803
2023-01-24 08:23:13.234396: step: 1516/530, loss: 0.008538995869457722
2023-01-24 08:23:14.321770: step: 1520/530, loss: 0.02530035749077797
2023-01-24 08:23:15.401418: step: 1524/530, loss: 0.0003509093075990677
2023-01-24 08:23:16.512597: step: 1528/530, loss: 0.0025637757498770952
2023-01-24 08:23:17.599778: step: 1532/530, loss: 0.023431751877069473
2023-01-24 08:23:18.687969: step: 1536/530, loss: 0.02613828144967556
2023-01-24 08:23:19.780712: step: 1540/530, loss: 0.02312270551919937
2023-01-24 08:23:20.887405: step: 1544/530, loss: 0.012337801046669483
2023-01-24 08:23:21.989572: step: 1548/530, loss: 0.00269088102504611
2023-01-24 08:23:23.083442: step: 1552/530, loss: 0.04785211756825447
2023-01-24 08:23:24.157605: step: 1556/530, loss: 0.005905095022171736
2023-01-24 08:23:25.249513: step: 1560/530, loss: 0.002391225891187787
2023-01-24 08:23:26.350018: step: 1564/530, loss: 0.0015557766892015934
2023-01-24 08:23:27.436434: step: 1568/530, loss: 0.004008970223367214
2023-01-24 08:23:28.533685: step: 1572/530, loss: 0.01488753966987133
2023-01-24 08:23:29.622205: step: 1576/530, loss: 0.005019379314035177
2023-01-24 08:23:30.706804: step: 1580/530, loss: 0.013527367264032364
2023-01-24 08:23:31.793579: step: 1584/530, loss: 0.0021498952992260456
2023-01-24 08:23:32.901701: step: 1588/530, loss: 0.0205497145652771
2023-01-24 08:23:33.986672: step: 1592/530, loss: 0.0015079585136845708
2023-01-24 08:23:35.092784: step: 1596/530, loss: 0.020550483837723732
2023-01-24 08:23:36.182451: step: 1600/530, loss: 0.014292348176240921
2023-01-24 08:23:37.273850: step: 1604/530, loss: 0.000968808657489717
2023-01-24 08:23:38.375215: step: 1608/530, loss: 0.014684724621474743
2023-01-24 08:23:39.467799: step: 1612/530, loss: 0.011075002141296864
2023-01-24 08:23:40.579351: step: 1616/530, loss: 0.06649428606033325
2023-01-24 08:23:41.654431: step: 1620/530, loss: 0.00946545135229826
2023-01-24 08:23:42.763592: step: 1624/530, loss: 0.008289055898785591
2023-01-24 08:23:43.875848: step: 1628/530, loss: 0.0059280553832650185
2023-01-24 08:23:44.981789: step: 1632/530, loss: 0.008240843191742897
2023-01-24 08:23:46.106831: step: 1636/530, loss: 0.033979691565036774
2023-01-24 08:23:47.212579: step: 1640/530, loss: 0.007574205752462149
2023-01-24 08:23:48.287153: step: 1644/530, loss: 0.03126741573214531
2023-01-24 08:23:49.367102: step: 1648/530, loss: 0.028560157865285873
2023-01-24 08:23:50.454571: step: 1652/530, loss: 0.009541143663227558
2023-01-24 08:23:51.537813: step: 1656/530, loss: 0.0100101288408041
2023-01-24 08:23:52.625795: step: 1660/530, loss: 0.0022494872100651264
2023-01-24 08:23:53.703927: step: 1664/530, loss: 0.00710147712379694
2023-01-24 08:23:54.797494: step: 1668/530, loss: 0.03679417818784714
2023-01-24 08:23:55.908644: step: 1672/530, loss: 0.00597589323297143
2023-01-24 08:23:57.042645: step: 1676/530, loss: 0.012171313166618347
2023-01-24 08:23:58.129725: step: 1680/530, loss: 0.008749675005674362
2023-01-24 08:23:59.228492: step: 1684/530, loss: 0.026481980457901955
2023-01-24 08:24:00.327344: step: 1688/530, loss: 0.00019856475410051644
2023-01-24 08:24:01.415409: step: 1692/530, loss: 0.011157437227666378
2023-01-24 08:24:02.504652: step: 1696/530, loss: 0.025775246322155
2023-01-24 08:24:03.597466: step: 1700/530, loss: 0.0011197603307664394
2023-01-24 08:24:04.683355: step: 1704/530, loss: 0.0034876095596700907
2023-01-24 08:24:05.767371: step: 1708/530, loss: 0.04879726469516754
2023-01-24 08:24:06.839849: step: 1712/530, loss: 0.013412362895905972
2023-01-24 08:24:07.909520: step: 1716/530, loss: 0.007574820425361395
2023-01-24 08:24:08.997924: step: 1720/530, loss: 0.0028674439527094364
2023-01-24 08:24:10.109783: step: 1724/530, loss: 0.029380347579717636
2023-01-24 08:24:11.199686: step: 1728/530, loss: 0.005109013058245182
2023-01-24 08:24:12.295356: step: 1732/530, loss: 0.03197004273533821
2023-01-24 08:24:13.378742: step: 1736/530, loss: 0.007782723754644394
2023-01-24 08:24:14.453438: step: 1740/530, loss: 0.003919995855540037
2023-01-24 08:24:15.561984: step: 1744/530, loss: 0.0074639832600951195
2023-01-24 08:24:16.659493: step: 1748/530, loss: 0.008496605791151524
2023-01-24 08:24:17.750365: step: 1752/530, loss: 0.01595201902091503
2023-01-24 08:24:18.854300: step: 1756/530, loss: 0.008883570320904255
2023-01-24 08:24:19.940523: step: 1760/530, loss: 0.005591331049799919
2023-01-24 08:24:21.045493: step: 1764/530, loss: 0.005617531016469002
2023-01-24 08:24:22.134752: step: 1768/530, loss: 0.004801840055733919
2023-01-24 08:24:23.215684: step: 1772/530, loss: 0.0046240827068686485
2023-01-24 08:24:24.286281: step: 1776/530, loss: 0.0027022850699722767
2023-01-24 08:24:25.382881: step: 1780/530, loss: 0.003939067013561726
2023-01-24 08:24:26.463731: step: 1784/530, loss: 0.0007597700459882617
2023-01-24 08:24:27.566470: step: 1788/530, loss: 0.03544655442237854
2023-01-24 08:24:28.651823: step: 1792/530, loss: 0.01583850011229515
2023-01-24 08:24:29.716918: step: 1796/530, loss: 0.023905564099550247
2023-01-24 08:24:30.809649: step: 1800/530, loss: 0.012000749818980694
2023-01-24 08:24:31.916621: step: 1804/530, loss: 0.014172019436955452
2023-01-24 08:24:33.003689: step: 1808/530, loss: 0.009804642759263515
2023-01-24 08:24:34.099517: step: 1812/530, loss: 0.011192088015377522
2023-01-24 08:24:35.173265: step: 1816/530, loss: 0.009174440056085587
2023-01-24 08:24:36.283004: step: 1820/530, loss: 0.0028696416411548853
2023-01-24 08:24:37.381756: step: 1824/530, loss: 0.0006159775657579303
2023-01-24 08:24:38.479081: step: 1828/530, loss: 0.007845573127269745
2023-01-24 08:24:39.549452: step: 1832/530, loss: 0.006900114007294178
2023-01-24 08:24:40.620358: step: 1836/530, loss: 0.000597308506257832
2023-01-24 08:24:41.681494: step: 1840/530, loss: 0.0013562479289248586
2023-01-24 08:24:42.803838: step: 1844/530, loss: 0.018411412835121155
2023-01-24 08:24:43.889450: step: 1848/530, loss: 0.02957063913345337
2023-01-24 08:24:44.976862: step: 1852/530, loss: 0.004262606613337994
2023-01-24 08:24:46.046982: step: 1856/530, loss: 0.0008446556748822331
2023-01-24 08:24:47.125053: step: 1860/530, loss: 0.003785383189097047
2023-01-24 08:24:48.208485: step: 1864/530, loss: 0.017457813024520874
2023-01-24 08:24:49.321033: step: 1868/530, loss: 0.016903871670365334
2023-01-24 08:24:50.422899: step: 1872/530, loss: 0.00910563487559557
2023-01-24 08:24:51.514779: step: 1876/530, loss: 0.0024856175296008587
2023-01-24 08:24:52.621976: step: 1880/530, loss: 0.01771523617208004
2023-01-24 08:24:53.731031: step: 1884/530, loss: 0.0037364992313086987
2023-01-24 08:24:54.813403: step: 1888/530, loss: 0.007870021276175976
2023-01-24 08:24:55.890321: step: 1892/530, loss: 0.006785782054066658
2023-01-24 08:24:56.964559: step: 1896/530, loss: 0.004140164237469435
2023-01-24 08:24:58.067616: step: 1900/530, loss: 0.011881887912750244
2023-01-24 08:24:59.172969: step: 1904/530, loss: 0.01027042604982853
2023-01-24 08:25:00.247520: step: 1908/530, loss: 0.0076409000903368
2023-01-24 08:25:01.327893: step: 1912/530, loss: 0.00034652548492886126
2023-01-24 08:25:02.403566: step: 1916/530, loss: 0.023433564230799675
2023-01-24 08:25:03.480416: step: 1920/530, loss: 0.005476299673318863
2023-01-24 08:25:04.595487: step: 1924/530, loss: 0.0087105268612504
2023-01-24 08:25:05.676040: step: 1928/530, loss: 0.003965376410633326
2023-01-24 08:25:06.777115: step: 1932/530, loss: 0.014118590392172337
2023-01-24 08:25:07.872527: step: 1936/530, loss: 0.007075015921145678
2023-01-24 08:25:08.944075: step: 1940/530, loss: 0.003730004420503974
2023-01-24 08:25:10.021646: step: 1944/530, loss: 0.010544252581894398
2023-01-24 08:25:11.112862: step: 1948/530, loss: 0.003539704019203782
2023-01-24 08:25:12.207390: step: 1952/530, loss: 0.02847655676305294
2023-01-24 08:25:13.314958: step: 1956/530, loss: 0.008167409338057041
2023-01-24 08:25:14.401898: step: 1960/530, loss: 0.00765496538951993
2023-01-24 08:25:15.478846: step: 1964/530, loss: 0.009911566972732544
2023-01-24 08:25:16.581323: step: 1968/530, loss: 0.004691366571933031
2023-01-24 08:25:17.651018: step: 1972/530, loss: 0.004511936567723751
2023-01-24 08:25:18.735521: step: 1976/530, loss: 0.003240075660869479
2023-01-24 08:25:19.828151: step: 1980/530, loss: 0.0009990454418584704
2023-01-24 08:25:20.914270: step: 1984/530, loss: 0.0037197726778686047
2023-01-24 08:25:22.001812: step: 1988/530, loss: 0.010630200617015362
2023-01-24 08:25:23.105056: step: 1992/530, loss: 0.03566709905862808
2023-01-24 08:25:24.169670: step: 1996/530, loss: 0.030046110972762108
2023-01-24 08:25:25.288713: step: 2000/530, loss: 0.043111298233270645
2023-01-24 08:25:26.373066: step: 2004/530, loss: 0.0023429833818227053
2023-01-24 08:25:27.481737: step: 2008/530, loss: 0.004607904702425003
2023-01-24 08:25:28.578738: step: 2012/530, loss: 0.017392003908753395
2023-01-24 08:25:29.669743: step: 2016/530, loss: 0.002853038487955928
2023-01-24 08:25:30.753062: step: 2020/530, loss: 0.020979465916752815
2023-01-24 08:25:31.830873: step: 2024/530, loss: 0.00715996976941824
2023-01-24 08:25:32.905486: step: 2028/530, loss: 0.0042402432300150394
2023-01-24 08:25:33.972796: step: 2032/530, loss: 0.002821543486788869
2023-01-24 08:25:35.064364: step: 2036/530, loss: 0.0031747843604534864
2023-01-24 08:25:36.143696: step: 2040/530, loss: 0.010959334671497345
2023-01-24 08:25:37.222977: step: 2044/530, loss: 0.00917725171893835
2023-01-24 08:25:38.313549: step: 2048/530, loss: 0.039017170667648315
2023-01-24 08:25:39.400586: step: 2052/530, loss: 0.0003101283800788224
2023-01-24 08:25:40.499475: step: 2056/530, loss: 0.002798594068735838
2023-01-24 08:25:41.575979: step: 2060/530, loss: 0.005760581232607365
2023-01-24 08:25:42.646898: step: 2064/530, loss: 0.016744490712881088
2023-01-24 08:25:43.726703: step: 2068/530, loss: 0.010294698178768158
2023-01-24 08:25:44.814800: step: 2072/530, loss: 0.024722643196582794
2023-01-24 08:25:45.897045: step: 2076/530, loss: 0.003681193571537733
2023-01-24 08:25:46.972693: step: 2080/530, loss: 0.0052399770356714725
2023-01-24 08:25:48.048064: step: 2084/530, loss: 0.00033079757122322917
2023-01-24 08:25:49.117271: step: 2088/530, loss: 0.002503804164007306
2023-01-24 08:25:50.206361: step: 2092/530, loss: 0.015386294573545456
2023-01-24 08:25:51.284407: step: 2096/530, loss: 0.006947911344468594
2023-01-24 08:25:52.371942: step: 2100/530, loss: 0.0018436722457408905
2023-01-24 08:25:53.455882: step: 2104/530, loss: 0.038152843713760376
2023-01-24 08:25:54.524436: step: 2108/530, loss: 0.006926866713911295
2023-01-24 08:25:55.616642: step: 2112/530, loss: 0.01697811484336853
2023-01-24 08:25:56.720953: step: 2116/530, loss: 0.01982099376618862
2023-01-24 08:25:57.815612: step: 2120/530, loss: 0.007340516895055771
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35216737094569495, 'r': 0.34815787526130376, 'f1': 0.35015114553951737}, 'combined': 0.25800610723964434, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3435023761280768, 'r': 0.2738505590101186, 'f1': 0.3047472924152228}, 'combined': 0.18926410792103313, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3902211667836668, 'r': 0.32876318415929423, 'f1': 0.35686549547260155}, 'combined': 0.26295352297981167, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33347427968356047, 'r': 0.2619684311743385, 'f1': 0.2934278387918434}, 'combined': 0.1822341314601975, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38174070593149545, 'r': 0.32596454965687466, 'f1': 0.35165469328387505}, 'combined': 0.25911398452496054, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34556942274711017, 'r': 0.2684729868726315, 'f1': 0.30218126189108413}, 'combined': 0.1876704679113049, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.38333329883077744, 'r': 0.3302339993722447, 'f1': 0.35480798709311506}, 'combined': 0.26143746417387426, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34574514535424083, 'r': 0.27194973883594437, 'f1': 0.3044393094048404}, 'combined': 0.1890728342619535, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 3}
******************************
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 08:28:27.070273: step: 4/530, loss: 0.013390426523983479
2023-01-24 08:28:28.158084: step: 8/530, loss: 0.003913471940904856
2023-01-24 08:28:29.249448: step: 12/530, loss: 0.014675590209662914
2023-01-24 08:28:30.325719: step: 16/530, loss: 0.0025220257230103016
2023-01-24 08:28:31.444650: step: 20/530, loss: 0.0057050203904509544
2023-01-24 08:28:32.513025: step: 24/530, loss: 0.019459763541817665
2023-01-24 08:28:33.600839: step: 28/530, loss: 0.06323400139808655
2023-01-24 08:28:34.712564: step: 32/530, loss: 0.019175894558429718
2023-01-24 08:28:35.799845: step: 36/530, loss: 0.0103736761957407
2023-01-24 08:28:36.882017: step: 40/530, loss: 0.0025775940157473087
2023-01-24 08:28:37.998188: step: 44/530, loss: 0.001016054768115282
2023-01-24 08:28:39.080351: step: 48/530, loss: 0.01773722842335701
2023-01-24 08:28:40.160618: step: 52/530, loss: 0.005342042539268732
2023-01-24 08:28:41.231372: step: 56/530, loss: 0.01565561257302761
2023-01-24 08:28:42.307780: step: 60/530, loss: 0.004726297687739134
2023-01-24 08:28:43.388120: step: 64/530, loss: 0.016036001965403557
2023-01-24 08:28:44.478929: step: 68/530, loss: 0.004280498716980219
2023-01-24 08:28:45.579102: step: 72/530, loss: 0.016028283163905144
2023-01-24 08:28:46.698518: step: 76/530, loss: 0.0032032765448093414
2023-01-24 08:28:47.785511: step: 80/530, loss: 0.0050194598734378815
2023-01-24 08:28:48.857488: step: 84/530, loss: 0.0064005437307059765
2023-01-24 08:28:49.960696: step: 88/530, loss: 0.002755015389993787
2023-01-24 08:28:51.064477: step: 92/530, loss: 0.006801757495850325
2023-01-24 08:28:52.161300: step: 96/530, loss: 0.004431865178048611
2023-01-24 08:28:53.245696: step: 100/530, loss: 0.006601641420274973
2023-01-24 08:28:54.349221: step: 104/530, loss: 0.014659630134701729
2023-01-24 08:28:55.451463: step: 108/530, loss: 0.013820094987750053
2023-01-24 08:28:56.515493: step: 112/530, loss: 0.0010037426836788654
2023-01-24 08:28:57.575150: step: 116/530, loss: 0.008951479569077492
2023-01-24 08:28:58.668191: step: 120/530, loss: 0.007594216149300337
2023-01-24 08:28:59.750036: step: 124/530, loss: 0.004729499574750662
2023-01-24 08:29:00.825726: step: 128/530, loss: 0.022528061643242836
2023-01-24 08:29:01.911000: step: 132/530, loss: 0.005706608761101961
2023-01-24 08:29:03.007974: step: 136/530, loss: 0.01574314758181572
2023-01-24 08:29:04.097110: step: 140/530, loss: 0.002276085317134857
2023-01-24 08:29:05.201622: step: 144/530, loss: 0.018506066873669624
2023-01-24 08:29:06.282690: step: 148/530, loss: 0.01409124955534935
2023-01-24 08:29:07.362925: step: 152/530, loss: 0.009515224024653435
2023-01-24 08:29:08.433854: step: 156/530, loss: 0.014751598238945007
2023-01-24 08:29:09.513634: step: 160/530, loss: 0.004073361866176128
2023-01-24 08:29:10.576140: step: 164/530, loss: 0.001871665590442717
2023-01-24 08:29:11.665671: step: 168/530, loss: 0.005623673088848591
2023-01-24 08:29:12.766747: step: 172/530, loss: 0.006894161459058523
2023-01-24 08:29:13.832888: step: 176/530, loss: 0.0040574087761342525
2023-01-24 08:29:14.922035: step: 180/530, loss: 0.0001293703098781407
2023-01-24 08:29:16.001260: step: 184/530, loss: 0.009348595514893532
2023-01-24 08:29:17.110752: step: 188/530, loss: 0.0010552923195064068
2023-01-24 08:29:18.191931: step: 192/530, loss: 0.00040406209882348776
2023-01-24 08:29:19.273706: step: 196/530, loss: 0.013306169770658016
2023-01-24 08:29:20.359549: step: 200/530, loss: 0.02009774185717106
2023-01-24 08:29:21.445241: step: 204/530, loss: 0.012250389903783798
2023-01-24 08:29:22.545394: step: 208/530, loss: 0.003727343864738941
2023-01-24 08:29:23.650937: step: 212/530, loss: 0.004510779399424791
2023-01-24 08:29:24.750661: step: 216/530, loss: 0.008073188364505768
2023-01-24 08:29:25.818672: step: 220/530, loss: 0.06214343011379242
2023-01-24 08:29:26.892677: step: 224/530, loss: 0.005105390213429928
2023-01-24 08:29:27.977884: step: 228/530, loss: 0.0036071166396141052
2023-01-24 08:29:29.048141: step: 232/530, loss: 0.004965350031852722
2023-01-24 08:29:30.115291: step: 236/530, loss: 0.008593683131039143
2023-01-24 08:29:31.213609: step: 240/530, loss: 0.0011923352722078562
2023-01-24 08:29:32.299040: step: 244/530, loss: 0.009273329749703407
2023-01-24 08:29:33.383395: step: 248/530, loss: 0.015437302179634571
2023-01-24 08:29:34.454580: step: 252/530, loss: 0.0029063429683446884
2023-01-24 08:29:35.562918: step: 256/530, loss: 0.0029965871945023537
2023-01-24 08:29:36.656150: step: 260/530, loss: 0.015377046540379524
2023-01-24 08:29:37.728215: step: 264/530, loss: 0.00244529964402318
2023-01-24 08:29:38.834205: step: 268/530, loss: 0.008787153288722038
2023-01-24 08:29:39.926764: step: 272/530, loss: 0.011790621094405651
2023-01-24 08:29:41.023306: step: 276/530, loss: 0.00617571035400033
2023-01-24 08:29:42.146509: step: 280/530, loss: 0.01603359915316105
2023-01-24 08:29:43.230798: step: 284/530, loss: 0.003708968637511134
2023-01-24 08:29:44.347196: step: 288/530, loss: 0.0037179531063884497
2023-01-24 08:29:45.433074: step: 292/530, loss: 0.0053726742044091225
2023-01-24 08:29:46.518741: step: 296/530, loss: 0.006987280212342739
2023-01-24 08:29:47.627652: step: 300/530, loss: 0.05322657898068428
2023-01-24 08:29:48.708666: step: 304/530, loss: 0.00358753465116024
2023-01-24 08:29:49.782839: step: 308/530, loss: 0.0012447584886103868
2023-01-24 08:29:50.864213: step: 312/530, loss: 0.012272996827960014
2023-01-24 08:29:51.965206: step: 316/530, loss: 0.024080568924546242
2023-01-24 08:29:53.040164: step: 320/530, loss: 0.0021521628368645906
2023-01-24 08:29:54.135132: step: 324/530, loss: 0.0011233440600335598
2023-01-24 08:29:55.246371: step: 328/530, loss: 0.016007384285330772
2023-01-24 08:29:56.348128: step: 332/530, loss: 0.006393632385879755
2023-01-24 08:29:57.456209: step: 336/530, loss: 0.008048313669860363
2023-01-24 08:29:58.555225: step: 340/530, loss: 0.0035647025797516108
2023-01-24 08:29:59.664301: step: 344/530, loss: 0.01215900294482708
2023-01-24 08:30:00.725491: step: 348/530, loss: 0.004934570752084255
2023-01-24 08:30:01.825766: step: 352/530, loss: 0.0035738968290388584
2023-01-24 08:30:02.899711: step: 356/530, loss: 0.005652283318340778
2023-01-24 08:30:03.998096: step: 360/530, loss: 0.02595125138759613
2023-01-24 08:30:05.092883: step: 364/530, loss: 0.009565915912389755
2023-01-24 08:30:06.174351: step: 368/530, loss: 0.0006659716018475592
2023-01-24 08:30:07.242035: step: 372/530, loss: 0.004813600331544876
2023-01-24 08:30:08.360703: step: 376/530, loss: 0.003479395294561982
2023-01-24 08:30:09.451258: step: 380/530, loss: 0.002324026543647051
2023-01-24 08:30:10.556874: step: 384/530, loss: 0.005483194720000029
2023-01-24 08:30:11.652112: step: 388/530, loss: 0.004847073927521706
2023-01-24 08:30:12.742655: step: 392/530, loss: 0.007429624442011118
2023-01-24 08:30:13.844676: step: 396/530, loss: 0.008476309478282928
2023-01-24 08:30:14.931081: step: 400/530, loss: 0.0029982924461364746
2023-01-24 08:30:16.009901: step: 404/530, loss: 0.00288561312481761
2023-01-24 08:30:17.094935: step: 408/530, loss: 0.014835940673947334
2023-01-24 08:30:18.182029: step: 412/530, loss: 0.019096961244940758
2023-01-24 08:30:19.266422: step: 416/530, loss: 0.009492441080510616
2023-01-24 08:30:20.337789: step: 420/530, loss: 0.006955127697438002
2023-01-24 08:30:21.415616: step: 424/530, loss: 0.005792070180177689
2023-01-24 08:30:22.487756: step: 428/530, loss: 0.0008928178576752543
2023-01-24 08:30:23.609621: step: 432/530, loss: 0.01803162321448326
2023-01-24 08:30:24.700552: step: 436/530, loss: 0.0005017681396566331
2023-01-24 08:30:25.790048: step: 440/530, loss: 0.02273922599852085
2023-01-24 08:30:26.874272: step: 444/530, loss: 0.008860909380018711
2023-01-24 08:30:27.948800: step: 448/530, loss: 0.006418897304683924
2023-01-24 08:30:29.061272: step: 452/530, loss: 0.006321071647107601
2023-01-24 08:30:30.148356: step: 456/530, loss: 0.0008852732717059553
2023-01-24 08:30:31.235290: step: 460/530, loss: 0.06455767154693604
2023-01-24 08:30:32.345319: step: 464/530, loss: 0.011337414383888245
2023-01-24 08:30:33.444202: step: 468/530, loss: 0.03129412606358528
2023-01-24 08:30:34.534178: step: 472/530, loss: 0.005267268046736717
2023-01-24 08:30:35.607303: step: 476/530, loss: 0.005748947616666555
2023-01-24 08:30:36.675620: step: 480/530, loss: 0.016402380540966988
2023-01-24 08:30:37.751350: step: 484/530, loss: 0.0032799935434013605
2023-01-24 08:30:38.844340: step: 488/530, loss: 0.012513834051787853
2023-01-24 08:30:39.939550: step: 492/530, loss: 0.0026917611248791218
2023-01-24 08:30:41.027734: step: 496/530, loss: 0.0060631581582129
2023-01-24 08:30:42.121161: step: 500/530, loss: 0.0032556792721152306
2023-01-24 08:30:43.217809: step: 504/530, loss: 0.0029229968786239624
2023-01-24 08:30:44.295327: step: 508/530, loss: 0.00792235229164362
2023-01-24 08:30:45.389556: step: 512/530, loss: 0.014967920258641243
2023-01-24 08:30:46.506854: step: 516/530, loss: 0.006878642365336418
2023-01-24 08:30:47.608258: step: 520/530, loss: 0.004619373008608818
2023-01-24 08:30:48.680664: step: 524/530, loss: 0.002735935617238283
2023-01-24 08:30:49.764907: step: 528/530, loss: 0.007665351964533329
2023-01-24 08:30:50.856658: step: 532/530, loss: 0.013482710346579552
2023-01-24 08:30:51.933016: step: 536/530, loss: 0.024530954658985138
2023-01-24 08:30:53.020356: step: 540/530, loss: 0.0028515001758933067
2023-01-24 08:30:54.116106: step: 544/530, loss: 0.00530988909304142
2023-01-24 08:30:55.203795: step: 548/530, loss: 0.000554635189473629
2023-01-24 08:30:56.293813: step: 552/530, loss: 0.013563115149736404
2023-01-24 08:30:57.366169: step: 556/530, loss: 0.0022188678849488497
2023-01-24 08:30:58.467983: step: 560/530, loss: 0.022701134905219078
2023-01-24 08:30:59.561380: step: 564/530, loss: 0.00687677226960659
2023-01-24 08:31:00.661455: step: 568/530, loss: 0.007060638628900051
2023-01-24 08:31:01.768883: step: 572/530, loss: 0.0007632538327015936
2023-01-24 08:31:02.879266: step: 576/530, loss: 0.0009229238494299352
2023-01-24 08:31:03.967909: step: 580/530, loss: 0.018368715420365334
2023-01-24 08:31:05.098738: step: 584/530, loss: 0.006042899563908577
2023-01-24 08:31:06.205274: step: 588/530, loss: 0.01982397586107254
2023-01-24 08:31:07.286437: step: 592/530, loss: 0.0013868712121620774
2023-01-24 08:31:08.369509: step: 596/530, loss: 0.0015452922089025378
2023-01-24 08:31:09.460406: step: 600/530, loss: 0.0050039151683449745
2023-01-24 08:31:10.541181: step: 604/530, loss: 0.002873511053621769
2023-01-24 08:31:11.652654: step: 608/530, loss: 0.01189162116497755
2023-01-24 08:31:12.738445: step: 612/530, loss: 0.010051965713500977
2023-01-24 08:31:13.827842: step: 616/530, loss: 0.006220933981239796
2023-01-24 08:31:14.926737: step: 620/530, loss: 0.007419348694384098
2023-01-24 08:31:16.005506: step: 624/530, loss: 0.014715871773660183
2023-01-24 08:31:17.086496: step: 628/530, loss: 0.0012297948123887181
2023-01-24 08:31:18.182447: step: 632/530, loss: 0.014310983009636402
2023-01-24 08:31:19.280148: step: 636/530, loss: 0.008859928697347641
2023-01-24 08:31:20.371924: step: 640/530, loss: 0.009216432459652424
2023-01-24 08:31:21.451858: step: 644/530, loss: 0.004318630788475275
2023-01-24 08:31:22.550157: step: 648/530, loss: 0.05318840593099594
2023-01-24 08:31:23.647138: step: 652/530, loss: 0.0028300799895077944
2023-01-24 08:31:24.731440: step: 656/530, loss: 0.0064165182411670685
2023-01-24 08:31:25.854345: step: 660/530, loss: 0.013577465899288654
2023-01-24 08:31:26.935256: step: 664/530, loss: 0.02669849991798401
2023-01-24 08:31:27.999084: step: 668/530, loss: 0.0
2023-01-24 08:31:29.101658: step: 672/530, loss: 0.005146565847098827
2023-01-24 08:31:30.189944: step: 676/530, loss: 0.003153915284201503
2023-01-24 08:31:31.286389: step: 680/530, loss: 0.0021724035032093525
2023-01-24 08:31:32.389070: step: 684/530, loss: 0.008481604047119617
2023-01-24 08:31:33.474419: step: 688/530, loss: 0.014910262078046799
2023-01-24 08:31:34.575463: step: 692/530, loss: 0.0002634353586472571
2023-01-24 08:31:35.651262: step: 696/530, loss: 0.0005372039158828557
2023-01-24 08:31:36.741540: step: 700/530, loss: 0.002919894177466631
2023-01-24 08:31:37.832735: step: 704/530, loss: 0.016136229038238525
2023-01-24 08:31:38.913330: step: 708/530, loss: 0.007952974177896976
2023-01-24 08:31:39.993990: step: 712/530, loss: 0.0016320603899657726
2023-01-24 08:31:41.074249: step: 716/530, loss: 0.0067335935309529305
2023-01-24 08:31:42.152057: step: 720/530, loss: 0.020796235650777817
2023-01-24 08:31:43.256596: step: 724/530, loss: 0.010603051632642746
2023-01-24 08:31:44.379940: step: 728/530, loss: 0.0035867670085281134
2023-01-24 08:31:45.456347: step: 732/530, loss: 0.038410037755966187
2023-01-24 08:31:46.543036: step: 736/530, loss: 0.01595931313931942
2023-01-24 08:31:47.639600: step: 740/530, loss: 0.01142870169132948
2023-01-24 08:31:48.705179: step: 744/530, loss: 0.0003212083538528532
2023-01-24 08:31:49.801514: step: 748/530, loss: 0.006775077432394028
2023-01-24 08:31:50.884322: step: 752/530, loss: 0.004188289400190115
2023-01-24 08:31:51.967901: step: 756/530, loss: 0.009298007003962994
2023-01-24 08:31:53.051501: step: 760/530, loss: 0.01912320964038372
2023-01-24 08:31:54.137468: step: 764/530, loss: 0.012271419167518616
2023-01-24 08:31:55.245947: step: 768/530, loss: 0.00332202878780663
2023-01-24 08:31:56.311884: step: 772/530, loss: 0.0029262148309499025
2023-01-24 08:31:57.416873: step: 776/530, loss: 0.0008892411715351045
2023-01-24 08:31:58.492684: step: 780/530, loss: 0.011919665150344372
2023-01-24 08:31:59.579841: step: 784/530, loss: 0.01851597987115383
2023-01-24 08:32:00.641462: step: 788/530, loss: 0.0030852241907268763
2023-01-24 08:32:01.717612: step: 792/530, loss: 0.0036761611700057983
2023-01-24 08:32:02.804232: step: 796/530, loss: 0.003399947192519903
2023-01-24 08:32:03.899075: step: 800/530, loss: 0.006142581347376108
2023-01-24 08:32:04.980257: step: 804/530, loss: 0.023061295971274376
2023-01-24 08:32:06.094002: step: 808/530, loss: 0.008395311422646046
2023-01-24 08:32:07.192101: step: 812/530, loss: 0.026986798271536827
2023-01-24 08:32:08.296825: step: 816/530, loss: 0.01530088298022747
2023-01-24 08:32:09.399675: step: 820/530, loss: 0.07895203679800034
2023-01-24 08:32:10.473505: step: 824/530, loss: 0.007875069975852966
2023-01-24 08:32:11.566286: step: 828/530, loss: 0.022428033873438835
2023-01-24 08:32:12.657822: step: 832/530, loss: 0.00685987900942564
2023-01-24 08:32:13.755937: step: 836/530, loss: 0.005061048083007336
2023-01-24 08:32:14.843793: step: 840/530, loss: 0.005881423130631447
2023-01-24 08:32:15.922822: step: 844/530, loss: 0.0023010517470538616
2023-01-24 08:32:17.002669: step: 848/530, loss: 0.009259999729692936
2023-01-24 08:32:18.083678: step: 852/530, loss: 0.023595279082655907
2023-01-24 08:32:19.172368: step: 856/530, loss: 0.007073951885104179
2023-01-24 08:32:20.267906: step: 860/530, loss: 0.012977248057723045
2023-01-24 08:32:21.348123: step: 864/530, loss: 0.002038983628153801
2023-01-24 08:32:22.418193: step: 868/530, loss: 0.021646853536367416
2023-01-24 08:32:23.503903: step: 872/530, loss: 0.0034775726962834597
2023-01-24 08:32:24.596600: step: 876/530, loss: 0.002575481543317437
2023-01-24 08:32:25.695401: step: 880/530, loss: 0.016511347144842148
2023-01-24 08:32:26.773616: step: 884/530, loss: 0.007966233417391777
2023-01-24 08:32:27.885289: step: 888/530, loss: 0.0036477355752140284
2023-01-24 08:32:28.997809: step: 892/530, loss: 0.023912986740469933
2023-01-24 08:32:30.108323: step: 896/530, loss: 0.005340574309229851
2023-01-24 08:32:31.215265: step: 900/530, loss: 0.012384876608848572
2023-01-24 08:32:32.293459: step: 904/530, loss: 0.0006822962313890457
2023-01-24 08:32:33.352491: step: 908/530, loss: 0.02468578703701496
2023-01-24 08:32:34.432417: step: 912/530, loss: 0.01933750882744789
2023-01-24 08:32:35.506239: step: 916/530, loss: 0.008372031152248383
2023-01-24 08:32:36.606375: step: 920/530, loss: 0.015360166318714619
2023-01-24 08:32:37.724742: step: 924/530, loss: 0.014099378138780594
2023-01-24 08:32:38.798214: step: 928/530, loss: 0.004104915075004101
2023-01-24 08:32:39.889875: step: 932/530, loss: 0.004274293314665556
2023-01-24 08:32:40.967246: step: 936/530, loss: 0.013796493411064148
2023-01-24 08:32:42.066892: step: 940/530, loss: 0.004015969578176737
2023-01-24 08:32:43.152418: step: 944/530, loss: 0.029437707737088203
2023-01-24 08:32:44.243749: step: 948/530, loss: 0.06338165700435638
2023-01-24 08:32:45.347004: step: 952/530, loss: 0.006039412692189217
2023-01-24 08:32:46.427237: step: 956/530, loss: 0.004642699845135212
2023-01-24 08:32:47.512624: step: 960/530, loss: 0.001632447587326169
2023-01-24 08:32:48.614703: step: 964/530, loss: 0.0092964768409729
2023-01-24 08:32:49.699464: step: 968/530, loss: 0.003565976396203041
2023-01-24 08:32:50.788394: step: 972/530, loss: 0.0037259955424815416
2023-01-24 08:32:51.877363: step: 976/530, loss: 0.007760280277580023
2023-01-24 08:32:52.951825: step: 980/530, loss: 0.00566880265250802
2023-01-24 08:32:54.044663: step: 984/530, loss: 0.0024378288071602583
2023-01-24 08:32:55.163580: step: 988/530, loss: 0.006020046770572662
2023-01-24 08:32:56.283894: step: 992/530, loss: 0.02705455757677555
2023-01-24 08:32:57.369668: step: 996/530, loss: 0.0018895254470407963
2023-01-24 08:32:58.457170: step: 1000/530, loss: 0.0025461469776928425
2023-01-24 08:32:59.562986: step: 1004/530, loss: 0.0010933129815384746
2023-01-24 08:33:00.652794: step: 1008/530, loss: 0.010913295671343803
2023-01-24 08:33:01.758458: step: 1012/530, loss: 0.009694751352071762
2023-01-24 08:33:02.859443: step: 1016/530, loss: 0.027088673785328865
2023-01-24 08:33:03.938253: step: 1020/530, loss: 0.007128599099814892
2023-01-24 08:33:05.026485: step: 1024/530, loss: 0.043904609978199005
2023-01-24 08:33:06.129029: step: 1028/530, loss: 0.005110875703394413
2023-01-24 08:33:07.206550: step: 1032/530, loss: 0.005126473028212786
2023-01-24 08:33:08.293167: step: 1036/530, loss: 0.0054137264378368855
2023-01-24 08:33:09.367288: step: 1040/530, loss: 0.01349830161780119
2023-01-24 08:33:10.489622: step: 1044/530, loss: 0.005182754714041948
2023-01-24 08:33:11.575987: step: 1048/530, loss: 0.0028157818596810102
2023-01-24 08:33:12.674063: step: 1052/530, loss: 0.000210175960091874
2023-01-24 08:33:13.777538: step: 1056/530, loss: 0.01893300563097
2023-01-24 08:33:14.865005: step: 1060/530, loss: 0.013074495829641819
2023-01-24 08:33:15.960095: step: 1064/530, loss: 0.026199353858828545
2023-01-24 08:33:17.031485: step: 1068/530, loss: 0.0012763570994138718
2023-01-24 08:33:18.112672: step: 1072/530, loss: 0.000747830024920404
2023-01-24 08:33:19.196725: step: 1076/530, loss: 0.004875941667705774
2023-01-24 08:33:20.267541: step: 1080/530, loss: 0.02152143232524395
2023-01-24 08:33:21.356126: step: 1084/530, loss: 0.003370596095919609
2023-01-24 08:33:22.431314: step: 1088/530, loss: 0.0016149122966453433
2023-01-24 08:33:23.524277: step: 1092/530, loss: 0.02816551923751831
2023-01-24 08:33:24.615710: step: 1096/530, loss: 0.0006070274976082146
2023-01-24 08:33:25.681010: step: 1100/530, loss: 0.00011186282790731639
2023-01-24 08:33:26.811785: step: 1104/530, loss: 0.008155712857842445
2023-01-24 08:33:27.882701: step: 1108/530, loss: 0.0005338452174328268
2023-01-24 08:33:28.963373: step: 1112/530, loss: 0.006027278024703264
2023-01-24 08:33:30.072831: step: 1116/530, loss: 0.03878793120384216
2023-01-24 08:33:31.163488: step: 1120/530, loss: 0.00042224457138217986
2023-01-24 08:33:32.250393: step: 1124/530, loss: 0.0031638885848224163
2023-01-24 08:33:33.342268: step: 1128/530, loss: 0.007403148803859949
2023-01-24 08:33:34.415784: step: 1132/530, loss: 0.00174345588311553
2023-01-24 08:33:35.522534: step: 1136/530, loss: 0.014343636110424995
2023-01-24 08:33:36.608681: step: 1140/530, loss: 0.0018404264701530337
2023-01-24 08:33:37.685825: step: 1144/530, loss: 0.020351599901914597
2023-01-24 08:33:38.775972: step: 1148/530, loss: 0.008296698331832886
2023-01-24 08:33:39.888148: step: 1152/530, loss: 0.06742016226053238
2023-01-24 08:33:40.983248: step: 1156/530, loss: 0.0034034899435937405
2023-01-24 08:33:42.078970: step: 1160/530, loss: 0.010913080535829067
2023-01-24 08:33:43.175466: step: 1164/530, loss: 0.004154646303504705
2023-01-24 08:33:44.243378: step: 1168/530, loss: 0.01610121876001358
2023-01-24 08:33:45.344679: step: 1172/530, loss: 0.0050384271889925
2023-01-24 08:33:46.436798: step: 1176/530, loss: 0.004915058612823486
2023-01-24 08:33:47.552958: step: 1180/530, loss: 0.015269331634044647
2023-01-24 08:33:48.652688: step: 1184/530, loss: 0.029997672885656357
2023-01-24 08:33:49.749864: step: 1188/530, loss: 0.009049919433891773
2023-01-24 08:33:50.850714: step: 1192/530, loss: 0.018555831164121628
2023-01-24 08:33:51.931383: step: 1196/530, loss: 0.005224880296736956
2023-01-24 08:33:53.061711: step: 1200/530, loss: 0.0039734807796776295
2023-01-24 08:33:54.144621: step: 1204/530, loss: 0.006240292452275753
2023-01-24 08:33:55.244526: step: 1208/530, loss: 0.00665348069742322
2023-01-24 08:33:56.388190: step: 1212/530, loss: 0.03361654281616211
2023-01-24 08:33:57.464095: step: 1216/530, loss: 0.008245476521551609
2023-01-24 08:33:58.579945: step: 1220/530, loss: 0.022018421441316605
2023-01-24 08:33:59.712162: step: 1224/530, loss: 0.004142383113503456
2023-01-24 08:34:00.814237: step: 1228/530, loss: 0.007273348048329353
2023-01-24 08:34:01.906434: step: 1232/530, loss: 0.008193165995180607
2023-01-24 08:34:03.012173: step: 1236/530, loss: 0.005689043086022139
2023-01-24 08:34:04.112306: step: 1240/530, loss: 0.0005889005260542035
2023-01-24 08:34:05.212241: step: 1244/530, loss: 0.0018694591708481312
2023-01-24 08:34:06.295216: step: 1248/530, loss: 0.008512190543115139
2023-01-24 08:34:07.379759: step: 1252/530, loss: 0.00022736986284144223
2023-01-24 08:34:08.487307: step: 1256/530, loss: 0.007735078223049641
2023-01-24 08:34:09.586768: step: 1260/530, loss: 0.010479175485670567
2023-01-24 08:34:10.679954: step: 1264/530, loss: 0.004068239126354456
2023-01-24 08:34:11.793838: step: 1268/530, loss: 0.002515255706384778
2023-01-24 08:34:12.912153: step: 1272/530, loss: 0.0074677979573607445
2023-01-24 08:34:14.025510: step: 1276/530, loss: 0.00739635806530714
2023-01-24 08:34:15.093732: step: 1280/530, loss: 0.019201155751943588
2023-01-24 08:34:16.180699: step: 1284/530, loss: 0.0022439199965447187
2023-01-24 08:34:17.281131: step: 1288/530, loss: 0.003761469852179289
2023-01-24 08:34:18.368272: step: 1292/530, loss: 0.006268573924899101
2023-01-24 08:34:19.456399: step: 1296/530, loss: 0.0005840518279001117
2023-01-24 08:34:20.550632: step: 1300/530, loss: 0.06176234036684036
2023-01-24 08:34:21.658703: step: 1304/530, loss: 0.010002519004046917
2023-01-24 08:34:22.738597: step: 1308/530, loss: 0.0046221488155424595
2023-01-24 08:34:23.840830: step: 1312/530, loss: 0.006704976782202721
2023-01-24 08:34:24.942812: step: 1316/530, loss: 0.0013584103435277939
2023-01-24 08:34:26.035250: step: 1320/530, loss: 0.006341882050037384
2023-01-24 08:34:27.132158: step: 1324/530, loss: 0.017576860263943672
2023-01-24 08:34:28.251475: step: 1328/530, loss: 0.0009096225840039551
2023-01-24 08:34:29.349740: step: 1332/530, loss: 0.013372194953262806
2023-01-24 08:34:30.426859: step: 1336/530, loss: 0.006615982856601477
2023-01-24 08:34:31.522425: step: 1340/530, loss: 0.00839964859187603
2023-01-24 08:34:32.598105: step: 1344/530, loss: 0.019094789400696754
2023-01-24 08:34:33.689611: step: 1348/530, loss: 4.0409677239949815e-06
2023-01-24 08:34:34.781918: step: 1352/530, loss: 0.0063874367624521255
2023-01-24 08:34:35.877777: step: 1356/530, loss: 0.033885207027196884
2023-01-24 08:34:36.962028: step: 1360/530, loss: 0.004803528543561697
2023-01-24 08:34:38.034416: step: 1364/530, loss: 0.001461849664337933
2023-01-24 08:34:39.114926: step: 1368/530, loss: 0.004812730010598898
2023-01-24 08:34:40.182001: step: 1372/530, loss: 0.005526599008589983
2023-01-24 08:34:41.241218: step: 1376/530, loss: 6.95694106980227e-05
2023-01-24 08:34:42.347165: step: 1380/530, loss: 0.00903487578034401
2023-01-24 08:34:43.447812: step: 1384/530, loss: 0.006801504176110029
2023-01-24 08:34:44.515286: step: 1388/530, loss: 0.00288062053732574
2023-01-24 08:34:45.618331: step: 1392/530, loss: 0.03670917823910713
2023-01-24 08:34:46.703741: step: 1396/530, loss: 0.015249194577336311
2023-01-24 08:34:47.769228: step: 1400/530, loss: 0.0034498574677854776
2023-01-24 08:34:48.871037: step: 1404/530, loss: 0.009832950308918953
2023-01-24 08:34:49.984217: step: 1408/530, loss: 0.004163734614849091
2023-01-24 08:34:51.063440: step: 1412/530, loss: 0.008080611005425453
2023-01-24 08:34:52.149987: step: 1416/530, loss: 0.025228403508663177
2023-01-24 08:34:53.235426: step: 1420/530, loss: 0.007757321931421757
2023-01-24 08:34:54.347622: step: 1424/530, loss: 0.007283371407538652
2023-01-24 08:34:55.416787: step: 1428/530, loss: 0.0010529693681746721
2023-01-24 08:34:56.520891: step: 1432/530, loss: 0.010803609155118465
2023-01-24 08:34:57.615053: step: 1436/530, loss: 0.013553500175476074
2023-01-24 08:34:58.705915: step: 1440/530, loss: 0.006621817592531443
2023-01-24 08:34:59.796525: step: 1444/530, loss: 0.00014562037540599704
2023-01-24 08:35:00.896713: step: 1448/530, loss: 0.005476659629493952
2023-01-24 08:35:01.999631: step: 1452/530, loss: 0.018918126821517944
2023-01-24 08:35:03.077714: step: 1456/530, loss: 0.002413890790194273
2023-01-24 08:35:04.155599: step: 1460/530, loss: 0.008535767905414104
2023-01-24 08:35:05.229720: step: 1464/530, loss: 0.007015233859419823
2023-01-24 08:35:06.339250: step: 1468/530, loss: 0.018064122647047043
2023-01-24 08:35:07.462876: step: 1472/530, loss: 0.0024961926974356174
2023-01-24 08:35:08.542967: step: 1476/530, loss: 0.0014636997366324067
2023-01-24 08:35:09.631347: step: 1480/530, loss: 0.008846471086144447
2023-01-24 08:35:10.742966: step: 1484/530, loss: 0.0021048174239695072
2023-01-24 08:35:11.868617: step: 1488/530, loss: 0.0012592453276738524
2023-01-24 08:35:12.986661: step: 1492/530, loss: 0.002622247440740466
2023-01-24 08:35:14.099800: step: 1496/530, loss: 0.019220324233174324
2023-01-24 08:35:15.192891: step: 1500/530, loss: 0.018160155043005943
2023-01-24 08:35:16.299928: step: 1504/530, loss: 0.02214130386710167
2023-01-24 08:35:17.394707: step: 1508/530, loss: 0.004736586473882198
2023-01-24 08:35:18.501877: step: 1512/530, loss: 0.009976362809538841
2023-01-24 08:35:19.591158: step: 1516/530, loss: 0.04310748353600502
2023-01-24 08:35:20.686148: step: 1520/530, loss: 0.007466264069080353
2023-01-24 08:35:21.779569: step: 1524/530, loss: 0.002315219957381487
2023-01-24 08:35:22.861659: step: 1528/530, loss: 0.008697858080267906
2023-01-24 08:35:23.949011: step: 1532/530, loss: 0.0
2023-01-24 08:35:25.029402: step: 1536/530, loss: 0.00947598461061716
2023-01-24 08:35:26.102900: step: 1540/530, loss: 0.0004582456895150244
2023-01-24 08:35:27.192042: step: 1544/530, loss: 0.006739595904946327
2023-01-24 08:35:28.322423: step: 1548/530, loss: 0.012601654976606369
2023-01-24 08:35:29.394596: step: 1552/530, loss: 3.860785000142641e-06
2023-01-24 08:35:30.478181: step: 1556/530, loss: 0.05636851117014885
2023-01-24 08:35:31.559744: step: 1560/530, loss: 2.1893432858632877e-05
2023-01-24 08:35:32.659062: step: 1564/530, loss: 0.0017861186061054468
2023-01-24 08:35:33.738981: step: 1568/530, loss: 0.006397359538823366
2023-01-24 08:35:34.808944: step: 1572/530, loss: 0.003253550035879016
2023-01-24 08:35:35.899743: step: 1576/530, loss: 0.00168312294408679
2023-01-24 08:35:36.994977: step: 1580/530, loss: 0.004595127422362566
2023-01-24 08:35:38.083082: step: 1584/530, loss: 0.012165140360593796
2023-01-24 08:35:39.162436: step: 1588/530, loss: 0.006841971538960934
2023-01-24 08:35:40.238521: step: 1592/530, loss: 0.01632261648774147
2023-01-24 08:35:41.321191: step: 1596/530, loss: 7.958279456943274e-05
2023-01-24 08:35:42.405281: step: 1600/530, loss: 0.0028296750970184803
2023-01-24 08:35:43.521993: step: 1604/530, loss: 0.04016222804784775
2023-01-24 08:35:44.625684: step: 1608/530, loss: 0.004369673784822226
2023-01-24 08:35:45.725716: step: 1612/530, loss: 0.0026291189715266228
2023-01-24 08:35:46.813837: step: 1616/530, loss: 0.03938344120979309
2023-01-24 08:35:47.889989: step: 1620/530, loss: 0.0002474721986800432
2023-01-24 08:35:48.984818: step: 1624/530, loss: 0.015566072426736355
2023-01-24 08:35:50.077679: step: 1628/530, loss: 0.005241157487034798
2023-01-24 08:35:51.154838: step: 1632/530, loss: 0.012914786115288734
2023-01-24 08:35:52.242764: step: 1636/530, loss: 0.008136267773807049
2023-01-24 08:35:53.331897: step: 1640/530, loss: 0.007448459975421429
2023-01-24 08:35:54.433700: step: 1644/530, loss: 0.002437054179608822
2023-01-24 08:35:55.530561: step: 1648/530, loss: 0.0241682268679142
2023-01-24 08:35:56.608216: step: 1652/530, loss: 0.000406511127948761
2023-01-24 08:35:57.707461: step: 1656/530, loss: 0.0033410938922315836
2023-01-24 08:35:58.797785: step: 1660/530, loss: 0.0011541829444468021
2023-01-24 08:35:59.881302: step: 1664/530, loss: 0.0020975994411855936
2023-01-24 08:36:00.960661: step: 1668/530, loss: 0.013906214386224747
2023-01-24 08:36:02.033471: step: 1672/530, loss: 0.0036015575751662254
2023-01-24 08:36:03.155840: step: 1676/530, loss: 0.0009082278702408075
2023-01-24 08:36:04.262207: step: 1680/530, loss: 0.019838446751236916
2023-01-24 08:36:05.348948: step: 1684/530, loss: 0.0005814454052597284
2023-01-24 08:36:06.448295: step: 1688/530, loss: 0.004982032813131809
2023-01-24 08:36:07.510164: step: 1692/530, loss: 0.007635097019374371
2023-01-24 08:36:08.590959: step: 1696/530, loss: 0.004282320383936167
2023-01-24 08:36:09.663802: step: 1700/530, loss: 0.0013093005400151014
2023-01-24 08:36:10.747524: step: 1704/530, loss: 6.666172703262419e-05
2023-01-24 08:36:11.877110: step: 1708/530, loss: 0.0033410987816751003
2023-01-24 08:36:12.975957: step: 1712/530, loss: 0.014055160805583
2023-01-24 08:36:14.065203: step: 1716/530, loss: 0.0067917462438344955
2023-01-24 08:36:15.161980: step: 1720/530, loss: 0.006169333588331938
2023-01-24 08:36:16.253261: step: 1724/530, loss: 0.01123003475368023
2023-01-24 08:36:17.338736: step: 1728/530, loss: 0.00014782797370571643
2023-01-24 08:36:18.450592: step: 1732/530, loss: 0.005444451235234737
2023-01-24 08:36:19.547761: step: 1736/530, loss: 0.006503126583993435
2023-01-24 08:36:20.658027: step: 1740/530, loss: 0.01831994205713272
2023-01-24 08:36:21.743374: step: 1744/530, loss: 0.0007748312200419605
2023-01-24 08:36:22.833304: step: 1748/530, loss: 0.034647706896066666
2023-01-24 08:36:23.895413: step: 1752/530, loss: 0.0018340562237426639
2023-01-24 08:36:24.978981: step: 1756/530, loss: 0.0011087298626080155
2023-01-24 08:36:26.079898: step: 1760/530, loss: 0.0002733748988248408
2023-01-24 08:36:27.169034: step: 1764/530, loss: 0.0025841135066002607
2023-01-24 08:36:28.270404: step: 1768/530, loss: 0.0015732855536043644
2023-01-24 08:36:29.376626: step: 1772/530, loss: 0.0037623767275363207
2023-01-24 08:36:30.466821: step: 1776/530, loss: 0.0034943281207233667
2023-01-24 08:36:31.560343: step: 1780/530, loss: 0.024733854457736015
2023-01-24 08:36:32.653952: step: 1784/530, loss: 0.0025741488207131624
2023-01-24 08:36:33.755088: step: 1788/530, loss: 0.020954806357622147
2023-01-24 08:36:34.852184: step: 1792/530, loss: 0.012817895971238613
2023-01-24 08:36:35.929753: step: 1796/530, loss: 0.012562660500407219
2023-01-24 08:36:37.005861: step: 1800/530, loss: 0.00377222360111773
2023-01-24 08:36:38.116668: step: 1804/530, loss: 0.0007697981200180948
2023-01-24 08:36:39.211507: step: 1808/530, loss: 0.02762249857187271
2023-01-24 08:36:40.301464: step: 1812/530, loss: 0.03712872788310051
2023-01-24 08:36:41.381616: step: 1816/530, loss: 0.0036480992566794157
2023-01-24 08:36:42.468810: step: 1820/530, loss: 0.004068395588546991
2023-01-24 08:36:43.547446: step: 1824/530, loss: 0.005120148882269859
2023-01-24 08:36:44.639863: step: 1828/530, loss: 0.004024632275104523
2023-01-24 08:36:45.728047: step: 1832/530, loss: 0.029572544619441032
2023-01-24 08:36:46.824220: step: 1836/530, loss: 0.06368596106767654
2023-01-24 08:36:47.913504: step: 1840/530, loss: 0.020419303327798843
2023-01-24 08:36:48.992420: step: 1844/530, loss: 0.006639654282480478
2023-01-24 08:36:50.084775: step: 1848/530, loss: 0.010417046956717968
2023-01-24 08:36:51.172661: step: 1852/530, loss: 0.011444559320807457
2023-01-24 08:36:52.257582: step: 1856/530, loss: 0.0020195627585053444
2023-01-24 08:36:53.365148: step: 1860/530, loss: 0.005016625858843327
2023-01-24 08:36:54.484018: step: 1864/530, loss: 0.008337307721376419
2023-01-24 08:36:55.585529: step: 1868/530, loss: 0.003666571108624339
2023-01-24 08:36:56.662935: step: 1872/530, loss: 0.0020980502013117075
2023-01-24 08:36:57.757050: step: 1876/530, loss: 0.0034470376558601856
2023-01-24 08:36:58.855494: step: 1880/530, loss: 0.005727291107177734
2023-01-24 08:36:59.940115: step: 1884/530, loss: 0.0020817650947719812
2023-01-24 08:37:01.022683: step: 1888/530, loss: 0.004460801370441914
2023-01-24 08:37:02.117812: step: 1892/530, loss: 0.0016281689750030637
2023-01-24 08:37:03.204181: step: 1896/530, loss: 0.006343192420899868
2023-01-24 08:37:04.311112: step: 1900/530, loss: 0.009423536248505116
2023-01-24 08:37:05.398857: step: 1904/530, loss: 0.008155460469424725
2023-01-24 08:37:06.487868: step: 1908/530, loss: 0.003949078265577555
2023-01-24 08:37:07.594583: step: 1912/530, loss: 0.0037763582076877356
2023-01-24 08:37:08.718606: step: 1916/530, loss: 0.0035387608222663403
2023-01-24 08:37:09.842262: step: 1920/530, loss: 0.013976875692605972
2023-01-24 08:37:10.919315: step: 1924/530, loss: 0.0010418662568554282
2023-01-24 08:37:12.028449: step: 1928/530, loss: 0.002441958524286747
2023-01-24 08:37:13.121076: step: 1932/530, loss: 0.013802547939121723
2023-01-24 08:37:14.201977: step: 1936/530, loss: 0.00454210489988327
2023-01-24 08:37:15.276174: step: 1940/530, loss: 0.00550570385530591
2023-01-24 08:37:16.379275: step: 1944/530, loss: 0.002162436256185174
2023-01-24 08:37:17.486860: step: 1948/530, loss: 0.0331319198012352
2023-01-24 08:37:18.595299: step: 1952/530, loss: 0.004887016490101814
2023-01-24 08:37:19.679034: step: 1956/530, loss: 0.0003119751636404544
2023-01-24 08:37:20.789012: step: 1960/530, loss: 0.0023202712181955576
2023-01-24 08:37:21.859569: step: 1964/530, loss: 0.007336675655096769
2023-01-24 08:37:22.964592: step: 1968/530, loss: 0.0025362251326441765
2023-01-24 08:37:24.047913: step: 1972/530, loss: 0.0023483028635382652
2023-01-24 08:37:25.137906: step: 1976/530, loss: 0.007916290313005447
2023-01-24 08:37:26.225539: step: 1980/530, loss: 0.010539408773183823
2023-01-24 08:37:27.309519: step: 1984/530, loss: 0.005473783705383539
2023-01-24 08:37:28.411455: step: 1988/530, loss: 0.010434496216475964
2023-01-24 08:37:29.504613: step: 1992/530, loss: 0.010954899713397026
2023-01-24 08:37:30.586515: step: 1996/530, loss: 0.00786043331027031
2023-01-24 08:37:31.683157: step: 2000/530, loss: 0.004296116065233946
2023-01-24 08:37:32.772963: step: 2004/530, loss: 0.01646469719707966
2023-01-24 08:37:33.871681: step: 2008/530, loss: 0.0014695404097437859
2023-01-24 08:37:34.961776: step: 2012/530, loss: 0.0015034498646855354
2023-01-24 08:37:36.047050: step: 2016/530, loss: 0.01275192853063345
2023-01-24 08:37:37.126422: step: 2020/530, loss: 0.007414584513753653
2023-01-24 08:37:38.224199: step: 2024/530, loss: 0.007664314471185207
2023-01-24 08:37:39.316905: step: 2028/530, loss: 0.007140903268009424
2023-01-24 08:37:40.384988: step: 2032/530, loss: 0.0014236748684197664
2023-01-24 08:37:41.479899: step: 2036/530, loss: 0.0063665746711194515
2023-01-24 08:37:42.587392: step: 2040/530, loss: 0.0027392064221203327
2023-01-24 08:37:43.712383: step: 2044/530, loss: 0.005666750017553568
2023-01-24 08:37:44.798113: step: 2048/530, loss: 0.004224306438118219
2023-01-24 08:37:45.891811: step: 2052/530, loss: 0.0022075639571994543
2023-01-24 08:37:46.968380: step: 2056/530, loss: 0.006415753159672022
2023-01-24 08:37:48.052127: step: 2060/530, loss: 0.0028477220330387354
2023-01-24 08:37:49.149130: step: 2064/530, loss: 0.0012268719729036093
2023-01-24 08:37:50.231613: step: 2068/530, loss: 0.004640631843358278
2023-01-24 08:37:51.331198: step: 2072/530, loss: 0.007370230741798878
2023-01-24 08:37:52.433756: step: 2076/530, loss: 0.003632717300206423
2023-01-24 08:37:53.526481: step: 2080/530, loss: 0.0007659295806661248
2023-01-24 08:37:54.613171: step: 2084/530, loss: 0.0017630505608394742
2023-01-24 08:37:55.697714: step: 2088/530, loss: 0.011211691424250603
2023-01-24 08:37:56.797114: step: 2092/530, loss: 0.006302114110440016
2023-01-24 08:37:57.865547: step: 2096/530, loss: 0.0025455388240516186
2023-01-24 08:37:58.953778: step: 2100/530, loss: 0.008401133120059967
2023-01-24 08:38:00.013899: step: 2104/530, loss: 0.007786688860505819
2023-01-24 08:38:01.105385: step: 2108/530, loss: 0.002886673668399453
2023-01-24 08:38:02.193418: step: 2112/530, loss: 0.0017836429178714752
2023-01-24 08:38:03.274822: step: 2116/530, loss: 0.0034210775047540665
2023-01-24 08:38:04.343377: step: 2120/530, loss: 0.008159960620105267
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3511961982180743, 'r': 0.35052979176984267, 'f1': 0.3508626785616469}, 'combined': 0.2585303947296345, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34692952488793816, 'r': 0.2779554056965677, 'f1': 0.3086358211523667}, 'combined': 0.1916790889262067, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3939071067821068, 'r': 0.3363533169866187, 'f1': 0.36286222733254464}, 'combined': 0.26737216750819076, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3369333991804158, 'r': 0.26468582247868633, 'f1': 0.2964715576629005}, 'combined': 0.184124441074854, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 08:40:41.199262: step: 4/530, loss: 0.00463224807754159
2023-01-24 08:40:42.287764: step: 8/530, loss: 0.001683820621110499
2023-01-24 08:40:43.370594: step: 12/530, loss: 0.003381364746019244
2023-01-24 08:40:44.451580: step: 16/530, loss: 0.0009808320319280028
2023-01-24 08:40:45.524485: step: 20/530, loss: 0.0026922153774648905
2023-01-24 08:40:46.613547: step: 24/530, loss: 0.036002252250909805
2023-01-24 08:40:47.683450: step: 28/530, loss: 0.006942289415746927
2023-01-24 08:40:48.757704: step: 32/530, loss: 0.004761753138154745
2023-01-24 08:40:49.842385: step: 36/530, loss: 0.002646166365593672
2023-01-24 08:40:50.933618: step: 40/530, loss: 0.0012257886119186878
2023-01-24 08:40:52.014703: step: 44/530, loss: 0.005338764283806086
2023-01-24 08:40:53.081892: step: 48/530, loss: 0.0012871178332716227
2023-01-24 08:40:54.180695: step: 52/530, loss: 0.02203054539859295
2023-01-24 08:40:55.291159: step: 56/530, loss: 0.03155577927827835
2023-01-24 08:40:56.390334: step: 60/530, loss: 0.010559890419244766
2023-01-24 08:40:57.473262: step: 64/530, loss: 0.01051109004765749
2023-01-24 08:40:58.571072: step: 68/530, loss: 0.006899889092892408
2023-01-24 08:40:59.665150: step: 72/530, loss: 0.01590123400092125
2023-01-24 08:41:00.776409: step: 76/530, loss: 0.006657039280980825
2023-01-24 08:41:01.890373: step: 80/530, loss: 0.006138589233160019
2023-01-24 08:41:02.975382: step: 84/530, loss: 0.03596678748726845
2023-01-24 08:41:04.057684: step: 88/530, loss: 0.006385402288287878
2023-01-24 08:41:05.126240: step: 92/530, loss: 0.006057546474039555
2023-01-24 08:41:06.216179: step: 96/530, loss: 0.0010628706077113748
2023-01-24 08:41:07.290720: step: 100/530, loss: 0.0029035129118710756
2023-01-24 08:41:08.372313: step: 104/530, loss: 0.0005100720445625484
2023-01-24 08:41:09.486238: step: 108/530, loss: 0.0023102881386876106
2023-01-24 08:41:10.580263: step: 112/530, loss: 0.0041152178309857845
2023-01-24 08:41:11.666942: step: 116/530, loss: 0.007752481382340193
2023-01-24 08:41:12.784612: step: 120/530, loss: 0.0008607989875599742
2023-01-24 08:41:13.854234: step: 124/530, loss: 0.014354175888001919
2023-01-24 08:41:14.951652: step: 128/530, loss: 0.026126377284526825
2023-01-24 08:41:16.017261: step: 132/530, loss: 0.07373518496751785
2023-01-24 08:41:17.097933: step: 136/530, loss: 0.0076378206722438335
2023-01-24 08:41:18.188060: step: 140/530, loss: 0.005049635656177998
2023-01-24 08:41:19.289714: step: 144/530, loss: 0.005359150003641844
2023-01-24 08:41:20.367486: step: 148/530, loss: 0.021733876317739487
2023-01-24 08:41:21.441644: step: 152/530, loss: 0.0019560488872230053
2023-01-24 08:41:22.542316: step: 156/530, loss: 0.022906986996531487
2023-01-24 08:41:23.627268: step: 160/530, loss: 0.00881852675229311
2023-01-24 08:41:24.706182: step: 164/530, loss: 0.002233170671388507
2023-01-24 08:41:25.783377: step: 168/530, loss: 0.0030977248679846525
2023-01-24 08:41:26.876320: step: 172/530, loss: 0.009406842291355133
2023-01-24 08:41:27.955199: step: 176/530, loss: 9.771555050974712e-05
2023-01-24 08:41:29.043867: step: 180/530, loss: 0.0023808307014405727
2023-01-24 08:41:30.163665: step: 184/530, loss: 0.004987532738596201
2023-01-24 08:41:31.240709: step: 188/530, loss: 0.0067310575395822525
2023-01-24 08:41:32.326057: step: 192/530, loss: 0.00045536665129475296
2023-01-24 08:41:33.400970: step: 196/530, loss: 0.010355474427342415
2023-01-24 08:41:34.492813: step: 200/530, loss: 0.008715576492249966
2023-01-24 08:41:35.590106: step: 204/530, loss: 0.008107380010187626
2023-01-24 08:41:36.674877: step: 208/530, loss: 0.0026640372816473246
2023-01-24 08:41:37.778115: step: 212/530, loss: 0.003948599100112915
2023-01-24 08:41:38.866606: step: 216/530, loss: 0.016453798860311508
2023-01-24 08:41:39.951653: step: 220/530, loss: 0.008649768307805061
2023-01-24 08:41:41.021807: step: 224/530, loss: 0.006488385144621134
2023-01-24 08:41:42.125206: step: 228/530, loss: 0.009495281614363194
2023-01-24 08:41:43.211385: step: 232/530, loss: 0.0019276264356449246
2023-01-24 08:41:44.306284: step: 236/530, loss: 0.004236297681927681
2023-01-24 08:41:45.413653: step: 240/530, loss: 0.0031727757304906845
2023-01-24 08:41:46.531608: step: 244/530, loss: 0.009979244321584702
2023-01-24 08:41:47.616249: step: 248/530, loss: 0.008907273411750793
2023-01-24 08:41:48.707137: step: 252/530, loss: 0.008175627328455448
2023-01-24 08:41:49.786184: step: 256/530, loss: 0.003716078121215105
2023-01-24 08:41:50.881176: step: 260/530, loss: 0.0030617089942097664
2023-01-24 08:41:51.968653: step: 264/530, loss: 0.0064925262704491615
2023-01-24 08:41:53.033197: step: 268/530, loss: 0.004499923903495073
2023-01-24 08:41:54.143777: step: 272/530, loss: 0.0027902901638299227
2023-01-24 08:41:55.242356: step: 276/530, loss: 0.0049284156411886215
2023-01-24 08:41:56.328362: step: 280/530, loss: 0.10972261428833008
2023-01-24 08:41:57.407483: step: 284/530, loss: 0.003794509917497635
2023-01-24 08:41:58.500003: step: 288/530, loss: 0.0058370851911604404
2023-01-24 08:41:59.594273: step: 292/530, loss: 0.002325585577636957
2023-01-24 08:42:00.683318: step: 296/530, loss: 0.016462258994579315
2023-01-24 08:42:01.780395: step: 300/530, loss: 0.0026082347612828016
2023-01-24 08:42:02.855739: step: 304/530, loss: 0.0001077714332495816
2023-01-24 08:42:03.963218: step: 308/530, loss: 0.00916716642677784
2023-01-24 08:42:05.044117: step: 312/530, loss: 0.0018658683402463794
2023-01-24 08:42:06.138681: step: 316/530, loss: 0.008952973410487175
2023-01-24 08:42:07.244533: step: 320/530, loss: 0.0031925092916935682
2023-01-24 08:42:08.320645: step: 324/530, loss: 0.002578672720119357
2023-01-24 08:42:09.419892: step: 328/530, loss: 0.012113017030060291
2023-01-24 08:42:10.510975: step: 332/530, loss: 0.015871243551373482
2023-01-24 08:42:11.600595: step: 336/530, loss: 0.003200849983841181
2023-01-24 08:42:12.674235: step: 340/530, loss: 0.0035453704185783863
2023-01-24 08:42:13.768561: step: 344/530, loss: 0.006059712264686823
2023-01-24 08:42:14.851282: step: 348/530, loss: 0.0014549053739756346
2023-01-24 08:42:15.923872: step: 352/530, loss: 0.0005033534835092723
2023-01-24 08:42:17.018954: step: 356/530, loss: 0.010503847151994705
2023-01-24 08:42:18.103817: step: 360/530, loss: 0.0006020868895575404
2023-01-24 08:42:19.200654: step: 364/530, loss: 0.025041157379746437
2023-01-24 08:42:20.278831: step: 368/530, loss: 0.00463578337803483
2023-01-24 08:42:21.360672: step: 372/530, loss: 0.00018186590750701725
2023-01-24 08:42:22.465725: step: 376/530, loss: 0.010330156423151493
2023-01-24 08:42:23.606713: step: 380/530, loss: 0.042303700000047684
2023-01-24 08:42:24.696971: step: 384/530, loss: 0.005308076739311218
2023-01-24 08:42:25.830384: step: 388/530, loss: 0.003753856522962451
2023-01-24 08:42:26.923501: step: 392/530, loss: 0.005373753607273102
2023-01-24 08:42:28.004657: step: 396/530, loss: 0.004915583413094282
2023-01-24 08:42:29.076341: step: 400/530, loss: 0.005431151483207941
2023-01-24 08:42:30.164217: step: 404/530, loss: 0.034240443259477615
2023-01-24 08:42:31.256831: step: 408/530, loss: 0.004481774754822254
2023-01-24 08:42:32.350863: step: 412/530, loss: 0.004229320213198662
2023-01-24 08:42:33.429929: step: 416/530, loss: 0.027343405410647392
2023-01-24 08:42:34.521512: step: 420/530, loss: 0.009248564019799232
2023-01-24 08:42:35.625766: step: 424/530, loss: 0.005732208490371704
2023-01-24 08:42:36.716942: step: 428/530, loss: 0.00029404659289866686
2023-01-24 08:42:37.812972: step: 432/530, loss: 0.012223182246088982
2023-01-24 08:42:38.887751: step: 436/530, loss: 0.0030045306775718927
2023-01-24 08:42:39.972248: step: 440/530, loss: 0.004541632253676653
2023-01-24 08:42:41.079440: step: 444/530, loss: 0.025317862629890442
2023-01-24 08:42:42.179668: step: 448/530, loss: 0.006078396458178759
2023-01-24 08:42:43.267559: step: 452/530, loss: 0.005915583577007055
2023-01-24 08:42:44.367782: step: 456/530, loss: 0.008833033964037895
2023-01-24 08:42:45.455773: step: 460/530, loss: 0.001243118429556489
2023-01-24 08:42:46.523857: step: 464/530, loss: 0.0015866317553445697
2023-01-24 08:42:47.600519: step: 468/530, loss: 0.00038922682870179415
2023-01-24 08:42:48.680512: step: 472/530, loss: 2.3639402570552193e-05
2023-01-24 08:42:49.767373: step: 476/530, loss: 0.01827951893210411
2023-01-24 08:42:50.845361: step: 480/530, loss: 0.002740520052611828
2023-01-24 08:42:51.923359: step: 484/530, loss: 0.012980856001377106
2023-01-24 08:42:53.011550: step: 488/530, loss: 0.003744292538613081
2023-01-24 08:42:54.101341: step: 492/530, loss: 0.008897952735424042
2023-01-24 08:42:55.182418: step: 496/530, loss: 0.017438406124711037
2023-01-24 08:42:56.269547: step: 500/530, loss: 0.015113581903278828
2023-01-24 08:42:57.359227: step: 504/530, loss: 0.0201431754976511
2023-01-24 08:42:58.449834: step: 508/530, loss: 0.0005575797986239195
2023-01-24 08:42:59.549476: step: 512/530, loss: 0.004977009259164333
2023-01-24 08:43:00.675732: step: 516/530, loss: 0.00013052007125224918
2023-01-24 08:43:01.768278: step: 520/530, loss: 0.010828935541212559
2023-01-24 08:43:02.848506: step: 524/530, loss: 0.003017609706148505
2023-01-24 08:43:03.940082: step: 528/530, loss: 0.11536585539579391
2023-01-24 08:43:05.037223: step: 532/530, loss: 0.0012215098831802607
2023-01-24 08:43:06.141420: step: 536/530, loss: 0.004368349444121122
2023-01-24 08:43:07.226404: step: 540/530, loss: 0.00455597136169672
2023-01-24 08:43:08.339020: step: 544/530, loss: 0.015852967277169228
2023-01-24 08:43:09.442572: step: 548/530, loss: 0.0013160236412659287
2023-01-24 08:43:10.532964: step: 552/530, loss: 0.008815168403089046
2023-01-24 08:43:11.632348: step: 556/530, loss: 0.04347842186689377
2023-01-24 08:43:12.726265: step: 560/530, loss: 0.06092775613069534
2023-01-24 08:43:13.799328: step: 564/530, loss: 0.0027884505689144135
2023-01-24 08:43:14.900620: step: 568/530, loss: 0.0013436584267765284
2023-01-24 08:43:15.979773: step: 572/530, loss: 0.0016177746001631021
2023-01-24 08:43:17.061272: step: 576/530, loss: 0.026669178158044815
2023-01-24 08:43:18.142666: step: 580/530, loss: 0.00439387047663331
2023-01-24 08:43:19.246340: step: 584/530, loss: 0.002781476126983762
2023-01-24 08:43:20.317600: step: 588/530, loss: 0.009298130869865417
2023-01-24 08:43:21.416325: step: 592/530, loss: 0.0022303471341729164
2023-01-24 08:43:22.496797: step: 596/530, loss: 0.01920304261147976
2023-01-24 08:43:23.593865: step: 600/530, loss: 0.01152800489217043
2023-01-24 08:43:24.677178: step: 604/530, loss: 0.0010703217703849077
2023-01-24 08:43:25.774415: step: 608/530, loss: 0.006187962368130684
2023-01-24 08:43:26.866873: step: 612/530, loss: 0.025365499779582024
2023-01-24 08:43:27.956294: step: 616/530, loss: 0.001042837044224143
2023-01-24 08:43:29.033107: step: 620/530, loss: 0.018153347074985504
2023-01-24 08:43:30.128321: step: 624/530, loss: 0.0028189036529511213
2023-01-24 08:43:31.216327: step: 628/530, loss: 0.031228696927428246
2023-01-24 08:43:32.297244: step: 632/530, loss: 0.004321316722780466
2023-01-24 08:43:33.384682: step: 636/530, loss: 0.0039545269683003426
2023-01-24 08:43:34.492387: step: 640/530, loss: 0.008419704623520374
2023-01-24 08:43:35.598132: step: 644/530, loss: 0.023659128695726395
2023-01-24 08:43:36.673049: step: 648/530, loss: 0.006105189677327871
2023-01-24 08:43:37.736409: step: 652/530, loss: 0.004462653771042824
2023-01-24 08:43:38.833391: step: 656/530, loss: 0.014436847530305386
2023-01-24 08:43:39.933106: step: 660/530, loss: 0.0004893246805295348
2023-01-24 08:43:41.044284: step: 664/530, loss: 0.011037465184926987
2023-01-24 08:43:42.114204: step: 668/530, loss: 0.007631612475961447
2023-01-24 08:43:43.205274: step: 672/530, loss: 0.0025377729907631874
2023-01-24 08:43:44.305363: step: 676/530, loss: 0.007415556348860264
2023-01-24 08:43:45.370540: step: 680/530, loss: 0.00011127939069410786
2023-01-24 08:43:46.439015: step: 684/530, loss: 0.003199041122570634
2023-01-24 08:43:47.514129: step: 688/530, loss: 0.007297462783753872
2023-01-24 08:43:48.582263: step: 692/530, loss: 0.002811875194311142
2023-01-24 08:43:49.663639: step: 696/530, loss: 0.01668676547706127
2023-01-24 08:43:50.744725: step: 700/530, loss: 0.00025425234343856573
2023-01-24 08:43:51.818551: step: 704/530, loss: 0.00702581275254488
2023-01-24 08:43:52.915625: step: 708/530, loss: 0.00665396498516202
2023-01-24 08:43:54.028261: step: 712/530, loss: 0.004290307871997356
2023-01-24 08:43:55.122301: step: 716/530, loss: 0.006105480715632439
2023-01-24 08:43:56.207937: step: 720/530, loss: 0.0017243979964405298
2023-01-24 08:43:57.300899: step: 724/530, loss: 0.00618281913921237
2023-01-24 08:43:58.378701: step: 728/530, loss: 0.00036540484870783985
2023-01-24 08:43:59.452832: step: 732/530, loss: 0.018587326630949974
2023-01-24 08:44:00.547509: step: 736/530, loss: 0.01968672312796116
2023-01-24 08:44:01.664226: step: 740/530, loss: 0.00969591736793518
2023-01-24 08:44:02.756888: step: 744/530, loss: 0.018504971638321877
2023-01-24 08:44:03.853394: step: 748/530, loss: 0.003154666628688574
2023-01-24 08:44:04.938301: step: 752/530, loss: 0.0071092708967626095
2023-01-24 08:44:06.029893: step: 756/530, loss: 0.010406233370304108
2023-01-24 08:44:07.123710: step: 760/530, loss: 0.004511485807597637
2023-01-24 08:44:08.207578: step: 764/530, loss: 0.007421662099659443
2023-01-24 08:44:09.284190: step: 768/530, loss: 0.0016526951221749187
2023-01-24 08:44:10.363310: step: 772/530, loss: 0.0009398804395459592
2023-01-24 08:44:11.467896: step: 776/530, loss: 0.002562194596976042
2023-01-24 08:44:12.564907: step: 780/530, loss: 0.0023031991440802813
2023-01-24 08:44:13.635567: step: 784/530, loss: 0.00508621521294117
2023-01-24 08:44:14.721164: step: 788/530, loss: 0.017179515212774277
2023-01-24 08:44:15.820614: step: 792/530, loss: 0.004915738943964243
2023-01-24 08:44:16.914686: step: 796/530, loss: 0.0069856238551437855
2023-01-24 08:44:17.992506: step: 800/530, loss: 0.004629735369235277
2023-01-24 08:44:19.094270: step: 804/530, loss: 0.009691477753221989
2023-01-24 08:44:20.173246: step: 808/530, loss: 0.0017027984140440822
2023-01-24 08:44:21.256000: step: 812/530, loss: 0.002548523712903261
2023-01-24 08:44:22.341781: step: 816/530, loss: 0.005001395009458065
2023-01-24 08:44:23.453458: step: 820/530, loss: 0.006331135518848896
2023-01-24 08:44:24.552645: step: 824/530, loss: 0.010274523869156837
2023-01-24 08:44:25.639287: step: 828/530, loss: 0.009996467269957066
2023-01-24 08:44:26.717721: step: 832/530, loss: 0.0075516668148338795
2023-01-24 08:44:27.829972: step: 836/530, loss: 0.03111538477241993
2023-01-24 08:44:28.907489: step: 840/530, loss: 0.011280653066933155
2023-01-24 08:44:30.014742: step: 844/530, loss: 0.0026294696144759655
2023-01-24 08:44:31.141669: step: 848/530, loss: 0.003596894210204482
2023-01-24 08:44:32.231154: step: 852/530, loss: 0.022199522703886032
2023-01-24 08:44:33.298904: step: 856/530, loss: 0.005757243372499943
2023-01-24 08:44:34.397437: step: 860/530, loss: 0.012366288341581821
2023-01-24 08:44:35.503845: step: 864/530, loss: 0.0072590867057442665
2023-01-24 08:44:36.581643: step: 868/530, loss: 0.005211768206208944
2023-01-24 08:44:37.662181: step: 872/530, loss: 0.0007780153537169099
2023-01-24 08:44:38.762393: step: 876/530, loss: 0.006579045671969652
2023-01-24 08:44:39.837222: step: 880/530, loss: 0.00034035538556054235
2023-01-24 08:44:40.945257: step: 884/530, loss: 0.020639551803469658
2023-01-24 08:44:42.044130: step: 888/530, loss: 0.009564299136400223
2023-01-24 08:44:43.147885: step: 892/530, loss: 0.012995216995477676
2023-01-24 08:44:44.248868: step: 896/530, loss: 0.0038737058639526367
2023-01-24 08:44:45.329098: step: 900/530, loss: 0.004532379563897848
2023-01-24 08:44:46.423750: step: 904/530, loss: 0.009280158206820488
2023-01-24 08:44:47.514824: step: 908/530, loss: 0.0004263847367838025
2023-01-24 08:44:48.612501: step: 912/530, loss: 0.009736970998346806
2023-01-24 08:44:49.692987: step: 916/530, loss: 0.004490819294005632
2023-01-24 08:44:50.774066: step: 920/530, loss: 0.004912327975034714
2023-01-24 08:44:51.901262: step: 924/530, loss: 0.005350144580006599
2023-01-24 08:44:52.967027: step: 928/530, loss: 0.016704106703400612
2023-01-24 08:44:54.048887: step: 932/530, loss: 0.002201124094426632
2023-01-24 08:44:55.143026: step: 936/530, loss: 0.005016628187149763
2023-01-24 08:44:56.224929: step: 940/530, loss: 0.003153557190671563
2023-01-24 08:44:57.270459: step: 944/530, loss: 0.02185557782649994
2023-01-24 08:44:58.372902: step: 948/530, loss: 0.004187334794551134
2023-01-24 08:44:59.477535: step: 952/530, loss: 0.008498439565300941
2023-01-24 08:45:00.564715: step: 956/530, loss: 0.016587520018219948
2023-01-24 08:45:01.663857: step: 960/530, loss: 0.008890247903764248
2023-01-24 08:45:02.786363: step: 964/530, loss: 0.03038751147687435
2023-01-24 08:45:03.856781: step: 968/530, loss: 0.009932409040629864
2023-01-24 08:45:04.942958: step: 972/530, loss: 9.147833225142676e-06
2023-01-24 08:45:06.027370: step: 976/530, loss: 0.001971217803657055
2023-01-24 08:45:07.104972: step: 980/530, loss: 0.002326179528608918
2023-01-24 08:45:08.194745: step: 984/530, loss: 0.005505596753209829
2023-01-24 08:45:09.289388: step: 988/530, loss: 0.02590414695441723
2023-01-24 08:45:10.385379: step: 992/530, loss: 0.00020978087559342384
2023-01-24 08:45:11.473624: step: 996/530, loss: 0.011213100515305996
2023-01-24 08:45:12.581035: step: 1000/530, loss: 0.026498788967728615
2023-01-24 08:45:13.672750: step: 1004/530, loss: 0.003575400449335575
2023-01-24 08:45:14.794094: step: 1008/530, loss: 0.00878897961229086
2023-01-24 08:45:15.877073: step: 1012/530, loss: 0.004244158510118723
2023-01-24 08:45:16.968116: step: 1016/530, loss: 0.0026787789538502693
2023-01-24 08:45:18.053497: step: 1020/530, loss: 0.007764363661408424
2023-01-24 08:45:19.133865: step: 1024/530, loss: 0.0011498505482450128
2023-01-24 08:45:20.237613: step: 1028/530, loss: 0.002127460204064846
2023-01-24 08:45:21.327821: step: 1032/530, loss: 0.0024901870638132095
2023-01-24 08:45:22.414792: step: 1036/530, loss: 0.0077363974414765835
2023-01-24 08:45:23.487903: step: 1040/530, loss: 0.004087755922228098
2023-01-24 08:45:24.577844: step: 1044/530, loss: 0.010710582137107849
2023-01-24 08:45:25.659864: step: 1048/530, loss: 0.000266395159997046
2023-01-24 08:45:26.771875: step: 1052/530, loss: 0.005906963255256414
2023-01-24 08:45:27.862178: step: 1056/530, loss: 0.003952084109187126
2023-01-24 08:45:28.939976: step: 1060/530, loss: 0.0019199763191863894
2023-01-24 08:45:30.028048: step: 1064/530, loss: 0.004333644639700651
2023-01-24 08:45:31.115886: step: 1068/530, loss: 0.0038385805673897266
2023-01-24 08:45:32.211266: step: 1072/530, loss: 0.002833553357049823
2023-01-24 08:45:33.321259: step: 1076/530, loss: 0.005803776439279318
2023-01-24 08:45:34.417878: step: 1080/530, loss: 0.006797958631068468
2023-01-24 08:45:35.548569: step: 1084/530, loss: 0.008882487192749977
2023-01-24 08:45:36.680367: step: 1088/530, loss: 0.005546614062041044
2023-01-24 08:45:37.771679: step: 1092/530, loss: 0.007498566061258316
2023-01-24 08:45:38.858469: step: 1096/530, loss: 0.005331460852175951
2023-01-24 08:45:39.943712: step: 1100/530, loss: 0.004108885303139687
2023-01-24 08:45:41.033539: step: 1104/530, loss: 0.013274230994284153
2023-01-24 08:45:42.118391: step: 1108/530, loss: 0.001495203236117959
2023-01-24 08:45:43.245094: step: 1112/530, loss: 0.0014030119637027383
2023-01-24 08:45:44.326244: step: 1116/530, loss: 0.0009595714509487152
2023-01-24 08:45:45.404188: step: 1120/530, loss: 0.004312857985496521
2023-01-24 08:45:46.488919: step: 1124/530, loss: 0.002902315929532051
2023-01-24 08:45:47.563656: step: 1128/530, loss: 0.0015837440732866526
2023-01-24 08:45:48.644661: step: 1132/530, loss: 0.0006025604670867324
2023-01-24 08:45:49.705543: step: 1136/530, loss: 0.008249369449913502
2023-01-24 08:45:50.792108: step: 1140/530, loss: 0.008096471428871155
2023-01-24 08:45:51.886413: step: 1144/530, loss: 0.007233277428895235
2023-01-24 08:45:52.991130: step: 1148/530, loss: 0.0013244193978607655
2023-01-24 08:45:54.097440: step: 1152/530, loss: 0.003945418167859316
2023-01-24 08:45:55.215552: step: 1156/530, loss: 0.010840107686817646
2023-01-24 08:45:56.314803: step: 1160/530, loss: 0.0009566234075464308
2023-01-24 08:45:57.422182: step: 1164/530, loss: 0.004920309409499168
2023-01-24 08:45:58.516602: step: 1168/530, loss: 0.0018896886613219976
2023-01-24 08:45:59.614706: step: 1172/530, loss: 0.0015820706030353904
2023-01-24 08:46:00.724207: step: 1176/530, loss: 0.0010488731786608696
2023-01-24 08:46:01.810188: step: 1180/530, loss: 0.0010845185024663806
2023-01-24 08:46:02.905385: step: 1184/530, loss: 0.0032175439409911633
2023-01-24 08:46:04.003732: step: 1188/530, loss: 0.024632660672068596
2023-01-24 08:46:05.098820: step: 1192/530, loss: 0.0041234660893678665
2023-01-24 08:46:06.184428: step: 1196/530, loss: 0.0017406868282705545
2023-01-24 08:46:07.288392: step: 1200/530, loss: 0.0026537885423749685
2023-01-24 08:46:08.390580: step: 1204/530, loss: 0.01513298787176609
2023-01-24 08:46:09.481445: step: 1208/530, loss: 0.008798873983323574
2023-01-24 08:46:10.638437: step: 1212/530, loss: 0.004736314062029123
2023-01-24 08:46:11.725534: step: 1216/530, loss: 0.005063324701040983
2023-01-24 08:46:12.805364: step: 1220/530, loss: 0.001203644904308021
2023-01-24 08:46:13.920807: step: 1224/530, loss: 0.004585994407534599
2023-01-24 08:46:15.012704: step: 1228/530, loss: 0.005031667649745941
2023-01-24 08:46:16.091931: step: 1232/530, loss: 0.00317892013117671
2023-01-24 08:46:17.162507: step: 1236/530, loss: 0.0048159826546907425
2023-01-24 08:46:18.246583: step: 1240/530, loss: 0.002159917028620839
2023-01-24 08:46:19.316731: step: 1244/530, loss: 0.0027185932267457247
2023-01-24 08:46:20.419088: step: 1248/530, loss: 0.0073392740450799465
2023-01-24 08:46:21.493793: step: 1252/530, loss: 0.0010658196406438947
2023-01-24 08:46:22.583840: step: 1256/530, loss: 7.896054012235254e-05
2023-01-24 08:46:23.686941: step: 1260/530, loss: 0.010328765027225018
2023-01-24 08:46:24.752083: step: 1264/530, loss: 0.0020433415193110704
2023-01-24 08:46:25.846936: step: 1268/530, loss: 0.006494658067822456
2023-01-24 08:46:26.944653: step: 1272/530, loss: 0.004773708060383797
2023-01-24 08:46:28.014306: step: 1276/530, loss: 0.003112129168584943
2023-01-24 08:46:29.107732: step: 1280/530, loss: 0.0249512679874897
2023-01-24 08:46:30.196833: step: 1284/530, loss: 0.0022350058425217867
2023-01-24 08:46:31.293291: step: 1288/530, loss: 0.007941442541778088
2023-01-24 08:46:32.379918: step: 1292/530, loss: 0.004541994538158178
2023-01-24 08:46:33.489263: step: 1296/530, loss: 0.013734852895140648
2023-01-24 08:46:34.620195: step: 1300/530, loss: 0.008403218351304531
2023-01-24 08:46:35.715745: step: 1304/530, loss: 0.004030571319162846
2023-01-24 08:46:36.817293: step: 1308/530, loss: 0.00379652320407331
2023-01-24 08:46:37.906880: step: 1312/530, loss: 0.00011982818250544369
2023-01-24 08:46:38.998913: step: 1316/530, loss: 0.007124029099941254
2023-01-24 08:46:40.090549: step: 1320/530, loss: 0.0036713359877467155
2023-01-24 08:46:41.172371: step: 1324/530, loss: 0.0042560407891869545
2023-01-24 08:46:42.292121: step: 1328/530, loss: 0.0016115898033604026
2023-01-24 08:46:43.365880: step: 1332/530, loss: 0.00369810382835567
2023-01-24 08:46:44.462538: step: 1336/530, loss: 5.417061038315296e-05
2023-01-24 08:46:45.541033: step: 1340/530, loss: 0.013022118248045444
2023-01-24 08:46:46.624247: step: 1344/530, loss: 0.008205000311136246
2023-01-24 08:46:47.708942: step: 1348/530, loss: 0.0024616713635623455
2023-01-24 08:46:48.785139: step: 1352/530, loss: 0.015581676736474037
2023-01-24 08:46:49.880783: step: 1356/530, loss: 0.005608633626252413
2023-01-24 08:46:50.988825: step: 1360/530, loss: 0.0017849968280643225
2023-01-24 08:46:52.059768: step: 1364/530, loss: 0.001441963016986847
2023-01-24 08:46:53.138539: step: 1368/530, loss: 0.0038278549909591675
2023-01-24 08:46:54.228448: step: 1372/530, loss: 0.01854427345097065
2023-01-24 08:46:55.308578: step: 1376/530, loss: 0.002111167646944523
2023-01-24 08:46:56.426821: step: 1380/530, loss: 0.017942290753126144
2023-01-24 08:46:57.531018: step: 1384/530, loss: 0.004350887145847082
2023-01-24 08:46:58.629648: step: 1388/530, loss: 0.001139622530899942
2023-01-24 08:46:59.712384: step: 1392/530, loss: 0.0
2023-01-24 08:47:00.795175: step: 1396/530, loss: 0.00782643910497427
2023-01-24 08:47:01.884159: step: 1400/530, loss: 0.003277075942605734
2023-01-24 08:47:02.964163: step: 1404/530, loss: 0.006889357231557369
2023-01-24 08:47:04.050237: step: 1408/530, loss: 0.0027386583387851715
2023-01-24 08:47:05.158939: step: 1412/530, loss: 0.006297572050243616
2023-01-24 08:47:06.250788: step: 1416/530, loss: 0.0002503152936697006
2023-01-24 08:47:07.364655: step: 1420/530, loss: 0.007495633326470852
2023-01-24 08:47:08.448927: step: 1424/530, loss: 0.0046742577105760574
2023-01-24 08:47:09.552428: step: 1428/530, loss: 0.00758227938786149
2023-01-24 08:47:10.637112: step: 1432/530, loss: 0.003613221226260066
2023-01-24 08:47:11.781170: step: 1436/530, loss: 0.016247134655714035
2023-01-24 08:47:12.891321: step: 1440/530, loss: 0.003686268115416169
2023-01-24 08:47:13.962633: step: 1444/530, loss: 0.004092773888260126
2023-01-24 08:47:15.065611: step: 1448/530, loss: 0.0029255282133817673
2023-01-24 08:47:16.185105: step: 1452/530, loss: 0.026645731180906296
2023-01-24 08:47:17.296117: step: 1456/530, loss: 0.010394490323960781
2023-01-24 08:47:18.400796: step: 1460/530, loss: 0.004966864828020334
2023-01-24 08:47:19.475918: step: 1464/530, loss: 0.006544764619320631
2023-01-24 08:47:20.567752: step: 1468/530, loss: 0.02776217833161354
2023-01-24 08:47:21.665873: step: 1472/530, loss: 0.0045127058401703835
2023-01-24 08:47:22.761512: step: 1476/530, loss: 0.0007814022828824818
2023-01-24 08:47:23.847261: step: 1480/530, loss: 0.0019984205719083548
2023-01-24 08:47:24.938144: step: 1484/530, loss: 0.03594312071800232
2023-01-24 08:47:26.028692: step: 1488/530, loss: 0.0011367242550477386
2023-01-24 08:47:27.123679: step: 1492/530, loss: 0.01858605444431305
2023-01-24 08:47:28.196306: step: 1496/530, loss: 0.012442837469279766
2023-01-24 08:47:29.280170: step: 1500/530, loss: 0.054779428988695145
2023-01-24 08:47:30.385228: step: 1504/530, loss: 0.004249508958309889
2023-01-24 08:47:31.502431: step: 1508/530, loss: 0.006845967844128609
2023-01-24 08:47:32.601759: step: 1512/530, loss: 0.021029451861977577
2023-01-24 08:47:33.692506: step: 1516/530, loss: 0.002162677003070712
2023-01-24 08:47:34.785346: step: 1520/530, loss: 0.004090449772775173
2023-01-24 08:47:35.871318: step: 1524/530, loss: 0.006330376490950584
2023-01-24 08:47:36.948118: step: 1528/530, loss: 0.0016081409994512796
2023-01-24 08:47:38.045611: step: 1532/530, loss: 0.0043511539697647095
2023-01-24 08:47:39.127408: step: 1536/530, loss: 0.005677711218595505
2023-01-24 08:47:40.230928: step: 1540/530, loss: 0.036507170647382736
2023-01-24 08:47:41.303984: step: 1544/530, loss: 0.0038570270407944918
2023-01-24 08:47:42.372650: step: 1548/530, loss: 0.006900971755385399
2023-01-24 08:47:43.480526: step: 1552/530, loss: 0.008843934163451195
2023-01-24 08:47:44.600624: step: 1556/530, loss: 0.0018246282124891877
2023-01-24 08:47:45.695436: step: 1560/530, loss: 0.001417941297404468
2023-01-24 08:47:46.781085: step: 1564/530, loss: 0.03741540387272835
2023-01-24 08:47:47.862109: step: 1568/530, loss: 0.0013847595546394587
2023-01-24 08:47:48.950778: step: 1572/530, loss: 0.002411586930975318
2023-01-24 08:47:50.058831: step: 1576/530, loss: 0.008746135048568249
2023-01-24 08:47:51.142771: step: 1580/530, loss: 0.004413927439600229
2023-01-24 08:47:52.198245: step: 1584/530, loss: 0.005375355947762728
2023-01-24 08:47:53.281448: step: 1588/530, loss: 0.003987058997154236
2023-01-24 08:47:54.360162: step: 1592/530, loss: 0.0022512220311909914
2023-01-24 08:47:55.466542: step: 1596/530, loss: 0.00216246978379786
2023-01-24 08:47:56.561937: step: 1600/530, loss: 0.008033680729568005
2023-01-24 08:47:57.650851: step: 1604/530, loss: 0.00646651815623045
2023-01-24 08:47:58.735766: step: 1608/530, loss: 0.00499124638736248
2023-01-24 08:47:59.833110: step: 1612/530, loss: 0.00862337090075016
2023-01-24 08:48:00.907562: step: 1616/530, loss: 0.00017277048027608544
2023-01-24 08:48:02.006540: step: 1620/530, loss: 0.0036424994468688965
2023-01-24 08:48:03.092371: step: 1624/530, loss: 0.002481953240931034
2023-01-24 08:48:04.173307: step: 1628/530, loss: 0.000285786809399724
2023-01-24 08:48:05.257574: step: 1632/530, loss: 0.0014721582410857081
2023-01-24 08:48:06.342609: step: 1636/530, loss: 0.003251965157687664
2023-01-24 08:48:07.432985: step: 1640/530, loss: 0.03291851654648781
2023-01-24 08:48:08.503644: step: 1644/530, loss: 0.015224786475300789
2023-01-24 08:48:09.581768: step: 1648/530, loss: 0.002789664315059781
2023-01-24 08:48:10.679687: step: 1652/530, loss: 0.024261346086859703
2023-01-24 08:48:11.806157: step: 1656/530, loss: 0.0007601691759191453
2023-01-24 08:48:12.905418: step: 1660/530, loss: 0.0020782810170203447
2023-01-24 08:48:14.000329: step: 1664/530, loss: 0.005972633603960276
2023-01-24 08:48:15.089937: step: 1668/530, loss: 0.007904973812401295
2023-01-24 08:48:16.177610: step: 1672/530, loss: 0.004683814011514187
2023-01-24 08:48:17.270328: step: 1676/530, loss: 0.009097536094486713
2023-01-24 08:48:18.357735: step: 1680/530, loss: 0.004008658230304718
2023-01-24 08:48:19.430370: step: 1684/530, loss: 0.010705480352044106
2023-01-24 08:48:20.516167: step: 1688/530, loss: 0.0031620340887457132
2023-01-24 08:48:21.599804: step: 1692/530, loss: 0.002292171586304903
2023-01-24 08:48:22.680945: step: 1696/530, loss: 0.0029696908313781023
2023-01-24 08:48:23.752758: step: 1700/530, loss: 9.170618432108313e-05
2023-01-24 08:48:24.839117: step: 1704/530, loss: 0.006824272219091654
2023-01-24 08:48:25.945212: step: 1708/530, loss: 0.002788491314277053
2023-01-24 08:48:27.040412: step: 1712/530, loss: 0.00028299755649641156
2023-01-24 08:48:28.129104: step: 1716/530, loss: 0.004729172680526972
2023-01-24 08:48:29.199539: step: 1720/530, loss: 0.00674403365701437
2023-01-24 08:48:30.282586: step: 1724/530, loss: 0.0005443753907456994
2023-01-24 08:48:31.348147: step: 1728/530, loss: 0.004042500630021095
2023-01-24 08:48:32.445061: step: 1732/530, loss: 0.004739298485219479
2023-01-24 08:48:33.556941: step: 1736/530, loss: 0.016698963940143585
2023-01-24 08:48:34.653631: step: 1740/530, loss: 0.004124755505472422
2023-01-24 08:48:35.762318: step: 1744/530, loss: 0.00602650735527277
2023-01-24 08:48:36.849755: step: 1748/530, loss: 0.0001949649304151535
2023-01-24 08:48:37.933974: step: 1752/530, loss: 0.00897810235619545
2023-01-24 08:48:38.994359: step: 1756/530, loss: 0.0002865359710995108
2023-01-24 08:48:40.068303: step: 1760/530, loss: 0.00449963565915823
2023-01-24 08:48:41.168340: step: 1764/530, loss: 0.0045041609555482864
2023-01-24 08:48:42.286898: step: 1768/530, loss: 0.0038851157296448946
2023-01-24 08:48:43.366329: step: 1772/530, loss: 0.001119268243201077
2023-01-24 08:48:44.462332: step: 1776/530, loss: 0.014574144035577774
2023-01-24 08:48:45.544702: step: 1780/530, loss: 0.004657109268009663
2023-01-24 08:48:46.629915: step: 1784/530, loss: 0.0025860783644020557
2023-01-24 08:48:47.744609: step: 1788/530, loss: 0.005173766054213047
2023-01-24 08:48:48.829968: step: 1792/530, loss: 0.006994450464844704
2023-01-24 08:48:49.914226: step: 1796/530, loss: 0.0030993837863206863
2023-01-24 08:48:50.994761: step: 1800/530, loss: 0.0024590729735791683
2023-01-24 08:48:52.081713: step: 1804/530, loss: 0.010682656429708004
2023-01-24 08:48:53.174696: step: 1808/530, loss: 0.06118054315447807
2023-01-24 08:48:54.284527: step: 1812/530, loss: 0.0007971552549861372
2023-01-24 08:48:55.376705: step: 1816/530, loss: 0.005168508272618055
2023-01-24 08:48:56.478886: step: 1820/530, loss: 0.0006055228295736015
2023-01-24 08:48:57.569102: step: 1824/530, loss: 0.007847760803997517
2023-01-24 08:48:58.649387: step: 1828/530, loss: 0.0027650182601064444
2023-01-24 08:48:59.718421: step: 1832/530, loss: 0.00246259942650795
2023-01-24 08:49:00.813138: step: 1836/530, loss: 0.0003299112431704998
2023-01-24 08:49:01.896389: step: 1840/530, loss: 0.00890478678047657
2023-01-24 08:49:02.969781: step: 1844/530, loss: 0.0010243532015010715
2023-01-24 08:49:04.051061: step: 1848/530, loss: 0.00031048664823174477
2023-01-24 08:49:05.133617: step: 1852/530, loss: 0.003606498474255204
2023-01-24 08:49:06.201488: step: 1856/530, loss: 0.004054786171764135
2023-01-24 08:49:07.272609: step: 1860/530, loss: 0.0001850359549280256
2023-01-24 08:49:08.354677: step: 1864/530, loss: 0.0033533195964992046
2023-01-24 08:49:09.438685: step: 1868/530, loss: 0.0033644381910562515
2023-01-24 08:49:10.546940: step: 1872/530, loss: 0.0031397216953337193
2023-01-24 08:49:11.622467: step: 1876/530, loss: 0.0056030941195786
2023-01-24 08:49:12.704651: step: 1880/530, loss: 0.008420975878834724
2023-01-24 08:49:13.819981: step: 1884/530, loss: 0.0031390476506203413
2023-01-24 08:49:14.898896: step: 1888/530, loss: 0.004058401565998793
2023-01-24 08:49:15.989792: step: 1892/530, loss: 0.018810905516147614
2023-01-24 08:49:17.059034: step: 1896/530, loss: 0.0017225093906745315
2023-01-24 08:49:18.126457: step: 1900/530, loss: 0.00015182253264356405
2023-01-24 08:49:19.231938: step: 1904/530, loss: 0.014628239907324314
2023-01-24 08:49:20.332386: step: 1908/530, loss: 0.007030069828033447
2023-01-24 08:49:21.440561: step: 1912/530, loss: 0.0039815884083509445
2023-01-24 08:49:22.512573: step: 1916/530, loss: 0.0031995372846722603
2023-01-24 08:49:23.601248: step: 1920/530, loss: 0.0021978002041578293
2023-01-24 08:49:24.691404: step: 1924/530, loss: 0.011598794721066952
2023-01-24 08:49:25.747751: step: 1928/530, loss: 1.3859623322787229e-05
2023-01-24 08:49:26.832344: step: 1932/530, loss: 0.005122246686369181
2023-01-24 08:49:27.925155: step: 1936/530, loss: 0.000861929205711931
2023-01-24 08:49:29.015416: step: 1940/530, loss: 0.0037842500023543835
2023-01-24 08:49:30.112611: step: 1944/530, loss: 0.024135509505867958
2023-01-24 08:49:31.227846: step: 1948/530, loss: 0.004512297920882702
2023-01-24 08:49:32.306864: step: 1952/530, loss: 0.007814999669790268
2023-01-24 08:49:33.398250: step: 1956/530, loss: 0.0035329656675457954
2023-01-24 08:49:34.494584: step: 1960/530, loss: 0.007976973429322243
2023-01-24 08:49:35.613643: step: 1964/530, loss: 0.0010328668868169188
2023-01-24 08:49:36.683729: step: 1968/530, loss: 0.005584979895502329
2023-01-24 08:49:37.777040: step: 1972/530, loss: 0.0035292149987071753
2023-01-24 08:49:38.853961: step: 1976/530, loss: 0.013540218584239483
2023-01-24 08:49:39.956404: step: 1980/530, loss: 0.053867876529693604
2023-01-24 08:49:41.041561: step: 1984/530, loss: 0.007585104554891586
2023-01-24 08:49:42.133124: step: 1988/530, loss: 0.00833124853670597
2023-01-24 08:49:43.222445: step: 1992/530, loss: 0.01000333670526743
2023-01-24 08:49:44.310780: step: 1996/530, loss: 0.009707452729344368
2023-01-24 08:49:45.400518: step: 2000/530, loss: 0.0010923369554802775
2023-01-24 08:49:46.493146: step: 2004/530, loss: 0.01993182860314846
2023-01-24 08:49:47.581486: step: 2008/530, loss: 0.005449749529361725
2023-01-24 08:49:48.678143: step: 2012/530, loss: 0.002692443085834384
2023-01-24 08:49:49.785435: step: 2016/530, loss: 0.004566051997244358
2023-01-24 08:49:50.854527: step: 2020/530, loss: 0.005283520091325045
2023-01-24 08:49:51.949683: step: 2024/530, loss: 0.013108435086905956
2023-01-24 08:49:53.051339: step: 2028/530, loss: 0.006936965975910425
2023-01-24 08:49:54.116590: step: 2032/530, loss: 5.192582466406748e-05
2023-01-24 08:49:55.221724: step: 2036/530, loss: 0.007226844783872366
2023-01-24 08:49:56.311050: step: 2040/530, loss: 0.0064369551837444305
2023-01-24 08:49:57.415524: step: 2044/530, loss: 0.0069593158550560474
2023-01-24 08:49:58.508029: step: 2048/530, loss: 0.00316441198810935
2023-01-24 08:49:59.588352: step: 2052/530, loss: 0.006536487024277449
2023-01-24 08:50:00.675621: step: 2056/530, loss: 0.007403606548905373
2023-01-24 08:50:01.756597: step: 2060/530, loss: 0.008399543352425098
2023-01-24 08:50:02.873292: step: 2064/530, loss: 0.0011779998894780874
2023-01-24 08:50:03.973694: step: 2068/530, loss: 0.0026249131187796593
2023-01-24 08:50:05.070052: step: 2072/530, loss: 0.012515190988779068
2023-01-24 08:50:06.154814: step: 2076/530, loss: 0.0011450749589130282
2023-01-24 08:50:07.247454: step: 2080/530, loss: 0.0004367369692772627
2023-01-24 08:50:08.340303: step: 2084/530, loss: 0.01260147150605917
2023-01-24 08:50:09.441970: step: 2088/530, loss: 0.0008949777111411095
2023-01-24 08:50:10.545988: step: 2092/530, loss: 0.002702175173908472
2023-01-24 08:50:11.617754: step: 2096/530, loss: 0.0007663618307560682
2023-01-24 08:50:12.720992: step: 2100/530, loss: 0.0
2023-01-24 08:50:13.792234: step: 2104/530, loss: 0.008782296441495419
2023-01-24 08:50:14.898344: step: 2108/530, loss: 0.00501541281118989
2023-01-24 08:50:15.978328: step: 2112/530, loss: 0.020943904295563698
2023-01-24 08:50:17.059627: step: 2116/530, loss: 0.0034575266763567924
2023-01-24 08:50:18.157607: step: 2120/530, loss: 0.0016149027505889535
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35324169934885535, 'r': 0.3472091086578882, 'f1': 0.3501994263401092}, 'combined': 0.25804168256639626, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34399865404370955, 'r': 0.2739752126079347, 'f1': 0.3050197086460175}, 'combined': 0.189433292738053, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38934426528527655, 'r': 0.32876318415929423, 'f1': 0.3564983499011277}, 'combined': 0.2626829946639888, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3372626923591295, 'r': 0.2639447157593187, 'f1': 0.2961330957299674}, 'combined': 0.1839142384007166, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3837044936952627, 'r': 0.32691331626029024, 'f1': 0.35303958538764957}, 'combined': 0.2601344313382681, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34632714465900216, 'r': 0.2687197785804301, 'f1': 0.3026271658721242}, 'combined': 0.18794739775216135, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 08:52:45.928727: step: 4/530, loss: 0.007388156373053789
2023-01-24 08:52:47.008162: step: 8/530, loss: 0.0015344498679041862
2023-01-24 08:52:48.101745: step: 12/530, loss: 0.0018128934316337109
2023-01-24 08:52:49.185253: step: 16/530, loss: 0.009831286035478115
2023-01-24 08:52:50.299381: step: 20/530, loss: 0.007215637248009443
2023-01-24 08:52:51.387763: step: 24/530, loss: 0.014350504614412785
2023-01-24 08:52:52.496482: step: 28/530, loss: 0.0031574484892189503
2023-01-24 08:52:53.609028: step: 32/530, loss: 0.006929425522685051
2023-01-24 08:52:54.697244: step: 36/530, loss: 0.008028604090213776
2023-01-24 08:52:55.767628: step: 40/530, loss: 0.00025584796094335616
2023-01-24 08:52:56.819688: step: 44/530, loss: 0.00564237218350172
2023-01-24 08:52:57.899156: step: 48/530, loss: 0.007395686581730843
2023-01-24 08:52:59.009771: step: 52/530, loss: 0.008263861760497093
2023-01-24 08:53:00.117940: step: 56/530, loss: 0.004996147938072681
2023-01-24 08:53:01.187964: step: 60/530, loss: 0.0030164753552526236
2023-01-24 08:53:02.278995: step: 64/530, loss: 0.008622347377240658
2023-01-24 08:53:03.355404: step: 68/530, loss: 0.019499190151691437
2023-01-24 08:53:04.441129: step: 72/530, loss: 0.005495051387697458
2023-01-24 08:53:05.530890: step: 76/530, loss: 0.007131422404199839
2023-01-24 08:53:06.654211: step: 80/530, loss: 0.03309730067849159
2023-01-24 08:53:07.743274: step: 84/530, loss: 0.004485478159040213
2023-01-24 08:53:08.812245: step: 88/530, loss: 0.0018139644525945187
2023-01-24 08:53:09.891066: step: 92/530, loss: 0.0038743652403354645
2023-01-24 08:53:10.960309: step: 96/530, loss: 0.005034653469920158
2023-01-24 08:53:12.050673: step: 100/530, loss: 0.003150301519781351
2023-01-24 08:53:13.146774: step: 104/530, loss: 0.002994616748765111
2023-01-24 08:53:14.226910: step: 108/530, loss: 0.0015131353866308928
2023-01-24 08:53:15.317867: step: 112/530, loss: 0.016307523474097252
2023-01-24 08:53:16.414428: step: 116/530, loss: 0.0059173088520765305
2023-01-24 08:53:17.537038: step: 120/530, loss: 0.010499164462089539
2023-01-24 08:53:18.623004: step: 124/530, loss: 0.005338155198842287
2023-01-24 08:53:19.709696: step: 128/530, loss: 0.008071066811680794
2023-01-24 08:53:20.793586: step: 132/530, loss: 0.003561959834769368
2023-01-24 08:53:21.897313: step: 136/530, loss: 0.007174029015004635
2023-01-24 08:53:22.984674: step: 140/530, loss: 0.005008305888622999
2023-01-24 08:53:24.073472: step: 144/530, loss: 0.0001466915273340419
2023-01-24 08:53:25.173696: step: 148/530, loss: 0.008366018533706665
2023-01-24 08:53:26.253843: step: 152/530, loss: 0.026283252984285355
2023-01-24 08:53:27.360232: step: 156/530, loss: 0.009043721482157707
2023-01-24 08:53:28.469270: step: 160/530, loss: 0.008177349343895912
2023-01-24 08:53:29.570952: step: 164/530, loss: 0.0040166606195271015
2023-01-24 08:53:30.643568: step: 168/530, loss: 0.004817122593522072
2023-01-24 08:53:31.727168: step: 172/530, loss: 0.00043714369530789554
2023-01-24 08:53:32.808158: step: 176/530, loss: 0.0114826001226902
2023-01-24 08:53:33.917078: step: 180/530, loss: 0.0040775928646326065
2023-01-24 08:53:35.010745: step: 184/530, loss: 0.011558112688362598
2023-01-24 08:53:36.088649: step: 188/530, loss: 0.0068406532518565655
2023-01-24 08:53:37.167307: step: 192/530, loss: 0.020551558583974838
2023-01-24 08:53:38.250111: step: 196/530, loss: 0.001693563535809517
2023-01-24 08:53:39.333713: step: 200/530, loss: 0.06349463015794754
2023-01-24 08:53:40.415550: step: 204/530, loss: 0.01125803217291832
2023-01-24 08:53:41.504529: step: 208/530, loss: 0.0010764760663732886
2023-01-24 08:53:42.590510: step: 212/530, loss: 0.0006107440567575395
2023-01-24 08:53:43.658244: step: 216/530, loss: 0.0032729203812777996
2023-01-24 08:53:44.737223: step: 220/530, loss: 0.004097287077456713
2023-01-24 08:53:45.812656: step: 224/530, loss: 0.003067636862397194
2023-01-24 08:53:46.933035: step: 228/530, loss: 0.007797864731401205
2023-01-24 08:53:48.035845: step: 232/530, loss: 0.0007214655051939189
2023-01-24 08:53:49.110786: step: 236/530, loss: 0.0006559145986102521
2023-01-24 08:53:50.209388: step: 240/530, loss: 0.003197344485670328
2023-01-24 08:53:51.306483: step: 244/530, loss: 0.00365530326962471
2023-01-24 08:53:52.393791: step: 248/530, loss: 0.008429373614490032
2023-01-24 08:53:53.494591: step: 252/530, loss: 0.004971066489815712
2023-01-24 08:53:54.584287: step: 256/530, loss: 0.0021796892397105694
2023-01-24 08:53:55.686495: step: 260/530, loss: 0.004744360689073801
2023-01-24 08:53:56.785060: step: 264/530, loss: 0.0015998062444850802
2023-01-24 08:53:57.872061: step: 268/530, loss: 0.004553547594696283
2023-01-24 08:53:58.948296: step: 272/530, loss: 0.0014314936706796288
2023-01-24 08:54:00.045162: step: 276/530, loss: 0.004400314763188362
2023-01-24 08:54:01.161927: step: 280/530, loss: 0.012932044453918934
2023-01-24 08:54:02.266861: step: 284/530, loss: 0.0004229581099934876
2023-01-24 08:54:03.361096: step: 288/530, loss: 0.05883161351084709
2023-01-24 08:54:04.449971: step: 292/530, loss: 0.005640116985887289
2023-01-24 08:54:05.534713: step: 296/530, loss: 0.0003104460774920881
2023-01-24 08:54:06.616136: step: 300/530, loss: 0.0044784098863601685
2023-01-24 08:54:07.710399: step: 304/530, loss: 0.005911798216402531
2023-01-24 08:54:08.793720: step: 308/530, loss: 0.0025081285275518894
2023-01-24 08:54:09.855710: step: 312/530, loss: 0.0013118191855028272
2023-01-24 08:54:10.931661: step: 316/530, loss: 0.016062332317233086
2023-01-24 08:54:12.046349: step: 320/530, loss: 0.0030639884062111378
2023-01-24 08:54:13.170518: step: 324/530, loss: 0.005788047332316637
2023-01-24 08:54:14.278692: step: 328/530, loss: 0.003149400232359767
2023-01-24 08:54:15.359828: step: 332/530, loss: 0.005945851560682058
2023-01-24 08:54:16.470905: step: 336/530, loss: 0.002734619891270995
2023-01-24 08:54:17.536233: step: 340/530, loss: 0.0068957204930484295
2023-01-24 08:54:18.616693: step: 344/530, loss: 0.0010261823190376163
2023-01-24 08:54:19.685016: step: 348/530, loss: 0.0073088607750833035
2023-01-24 08:54:20.773688: step: 352/530, loss: 0.002897347556427121
2023-01-24 08:54:21.872469: step: 356/530, loss: 0.10373104363679886
2023-01-24 08:54:22.997188: step: 360/530, loss: 0.0011780316708609462
2023-01-24 08:54:24.077869: step: 364/530, loss: 0.00012777314987033606
2023-01-24 08:54:25.156034: step: 368/530, loss: 0.0021382318809628487
2023-01-24 08:54:26.251849: step: 372/530, loss: 0.003371322061866522
2023-01-24 08:54:27.345170: step: 376/530, loss: 0.0054047973826527596
2023-01-24 08:54:28.440330: step: 380/530, loss: 0.00026519360835663974
2023-01-24 08:54:29.531930: step: 384/530, loss: 0.006048600655049086
2023-01-24 08:54:30.600789: step: 388/530, loss: 0.0013884049840271473
2023-01-24 08:54:31.687560: step: 392/530, loss: 0.012104946188628674
2023-01-24 08:54:32.779818: step: 396/530, loss: 0.0038868628907948732
2023-01-24 08:54:33.864827: step: 400/530, loss: 0.005234112497419119
2023-01-24 08:54:34.949717: step: 404/530, loss: 0.008141560479998589
2023-01-24 08:54:36.009532: step: 408/530, loss: 4.81834695165162e-06
2023-01-24 08:54:37.079483: step: 412/530, loss: 0.0002958564436994493
2023-01-24 08:54:38.161288: step: 416/530, loss: 0.008125375024974346
2023-01-24 08:54:39.244124: step: 420/530, loss: 0.002929950598627329
2023-01-24 08:54:40.314064: step: 424/530, loss: 0.008882114663720131
2023-01-24 08:54:41.395637: step: 428/530, loss: 0.0013432524865493178
2023-01-24 08:54:42.526166: step: 432/530, loss: 0.0036510159261524677
2023-01-24 08:54:43.588859: step: 436/530, loss: 0.002689539222046733
2023-01-24 08:54:44.692062: step: 440/530, loss: 0.0008996232063509524
2023-01-24 08:54:45.796165: step: 444/530, loss: 0.0025219181552529335
2023-01-24 08:54:46.888570: step: 448/530, loss: 0.003783931490033865
2023-01-24 08:54:47.972747: step: 452/530, loss: 0.009089943952858448
2023-01-24 08:54:49.051388: step: 456/530, loss: 0.05749931186437607
2023-01-24 08:54:50.120957: step: 460/530, loss: 0.002829259494319558
2023-01-24 08:54:51.198165: step: 464/530, loss: 0.0046712858602404594
2023-01-24 08:54:52.282228: step: 468/530, loss: 0.03202364593744278
2023-01-24 08:54:53.372973: step: 472/530, loss: 0.003799722297117114
2023-01-24 08:54:54.460950: step: 476/530, loss: 0.007668789941817522
2023-01-24 08:54:55.538856: step: 480/530, loss: 0.014642185531556606
2023-01-24 08:54:56.632506: step: 484/530, loss: 0.0238353181630373
2023-01-24 08:54:57.735519: step: 488/530, loss: 0.006100240629166365
2023-01-24 08:54:58.814036: step: 492/530, loss: 0.0009572201524861157
2023-01-24 08:54:59.909518: step: 496/530, loss: 0.0013079307973384857
2023-01-24 08:55:01.002853: step: 500/530, loss: 0.020869150757789612
2023-01-24 08:55:02.082358: step: 504/530, loss: 0.009384731762111187
2023-01-24 08:55:03.146160: step: 508/530, loss: 0.009377263486385345
2023-01-24 08:55:04.214911: step: 512/530, loss: 0.001966709503903985
2023-01-24 08:55:05.285247: step: 516/530, loss: 0.002783228876069188
2023-01-24 08:55:06.356459: step: 520/530, loss: 0.002126112813130021
2023-01-24 08:55:07.453166: step: 524/530, loss: 0.001104741240851581
2023-01-24 08:55:08.561842: step: 528/530, loss: 0.006545455195009708
2023-01-24 08:55:09.652144: step: 532/530, loss: 0.009132733568549156
2023-01-24 08:55:10.741435: step: 536/530, loss: 1.1474792700028047e-05
2023-01-24 08:55:11.824405: step: 540/530, loss: 0.02148590050637722
2023-01-24 08:55:12.921596: step: 544/530, loss: 0.003492011921480298
2023-01-24 08:55:14.023923: step: 548/530, loss: 0.0037010449450463057
2023-01-24 08:55:15.106529: step: 552/530, loss: 0.003186080139130354
2023-01-24 08:55:16.191992: step: 556/530, loss: 0.012086662463843822
2023-01-24 08:55:17.283631: step: 560/530, loss: 0.004258180037140846
2023-01-24 08:55:18.398229: step: 564/530, loss: 0.0064422027207911015
2023-01-24 08:55:19.498192: step: 568/530, loss: 0.010450919158756733
2023-01-24 08:55:20.560196: step: 572/530, loss: 0.00021632964489981532
2023-01-24 08:55:21.649472: step: 576/530, loss: 0.0028493760619312525
2023-01-24 08:55:22.727626: step: 580/530, loss: 0.0034244342241436243
2023-01-24 08:55:23.814164: step: 584/530, loss: 0.008110796101391315
2023-01-24 08:55:24.929609: step: 588/530, loss: 0.0013099772622808814
2023-01-24 08:55:26.016629: step: 592/530, loss: 0.00390882370993495
2023-01-24 08:55:27.109886: step: 596/530, loss: 0.006104831583797932
2023-01-24 08:55:28.179930: step: 600/530, loss: 0.003616774221882224
2023-01-24 08:55:29.270662: step: 604/530, loss: 0.00127408467233181
2023-01-24 08:55:30.357940: step: 608/530, loss: 0.0002809033030644059
2023-01-24 08:55:31.455693: step: 612/530, loss: 0.0034628703724592924
2023-01-24 08:55:32.537044: step: 616/530, loss: 0.001268115476705134
2023-01-24 08:55:33.619565: step: 620/530, loss: 0.007326859049499035
2023-01-24 08:55:34.719361: step: 624/530, loss: 0.003486846573650837
2023-01-24 08:55:35.820737: step: 628/530, loss: 0.0013649256434291601
2023-01-24 08:55:36.909130: step: 632/530, loss: 0.003663488896563649
2023-01-24 08:55:38.027589: step: 636/530, loss: 0.003642222611233592
2023-01-24 08:55:39.132236: step: 640/530, loss: 0.014086704701185226
2023-01-24 08:55:40.224979: step: 644/530, loss: 0.011483301408588886
2023-01-24 08:55:41.332341: step: 648/530, loss: 0.014000587165355682
2023-01-24 08:55:42.412837: step: 652/530, loss: 0.0019541641231626272
2023-01-24 08:55:43.500053: step: 656/530, loss: 0.003688916563987732
2023-01-24 08:55:44.544131: step: 660/530, loss: 0.004820521920919418
2023-01-24 08:55:45.616007: step: 664/530, loss: 0.0037048442754894495
2023-01-24 08:55:46.707503: step: 668/530, loss: 0.00088413868797943
2023-01-24 08:55:47.805813: step: 672/530, loss: 0.008120663464069366
2023-01-24 08:55:48.878575: step: 676/530, loss: 0.0010722496081143618
2023-01-24 08:55:49.948048: step: 680/530, loss: 0.0059935906901955605
2023-01-24 08:55:51.046815: step: 684/530, loss: 0.004710780922323465
2023-01-24 08:55:52.142372: step: 688/530, loss: 0.002258643275126815
2023-01-24 08:55:53.218531: step: 692/530, loss: 0.010286723263561726
2023-01-24 08:55:54.325258: step: 696/530, loss: 0.0005337955080904067
2023-01-24 08:55:55.433020: step: 700/530, loss: 0.0029301673639565706
2023-01-24 08:55:56.510214: step: 704/530, loss: 0.0010197005467489362
2023-01-24 08:55:57.586773: step: 708/530, loss: 0.00235172500833869
2023-01-24 08:55:58.677563: step: 712/530, loss: 4.155106125836028e-06
2023-01-24 08:55:59.777467: step: 716/530, loss: 0.0037140788044780493
2023-01-24 08:56:00.898555: step: 720/530, loss: 0.016127701848745346
2023-01-24 08:56:01.969434: step: 724/530, loss: 0.0005109111662022769
2023-01-24 08:56:03.033601: step: 728/530, loss: 0.006089877337217331
2023-01-24 08:56:04.140528: step: 732/530, loss: 0.005313365254551172
2023-01-24 08:56:05.228949: step: 736/530, loss: 0.0014886532444506884
2023-01-24 08:56:06.316306: step: 740/530, loss: 0.00926622562110424
2023-01-24 08:56:07.419804: step: 744/530, loss: 0.0006086198263801634
2023-01-24 08:56:08.534425: step: 748/530, loss: 0.010885899886488914
2023-01-24 08:56:09.645685: step: 752/530, loss: 0.0059586940333247185
2023-01-24 08:56:10.762501: step: 756/530, loss: 0.005535410717129707
2023-01-24 08:56:11.875350: step: 760/530, loss: 0.007350731175392866
2023-01-24 08:56:12.964382: step: 764/530, loss: 0.0009643484372645617
2023-01-24 08:56:14.060108: step: 768/530, loss: 0.006084567867219448
2023-01-24 08:56:15.147721: step: 772/530, loss: 0.01721637323498726
2023-01-24 08:56:16.243391: step: 776/530, loss: 0.007361912168562412
2023-01-24 08:56:17.330443: step: 780/530, loss: 0.00501954136416316
2023-01-24 08:56:18.398067: step: 784/530, loss: 0.017124975100159645
2023-01-24 08:56:19.472034: step: 788/530, loss: 0.0024047335609793663
2023-01-24 08:56:20.564191: step: 792/530, loss: 0.008885848335921764
2023-01-24 08:56:21.636557: step: 796/530, loss: 0.00019390931993257254
2023-01-24 08:56:22.729062: step: 800/530, loss: 0.0064721559174358845
2023-01-24 08:56:23.821991: step: 804/530, loss: 0.00936433020979166
2023-01-24 08:56:24.895446: step: 808/530, loss: 0.008190997876226902
2023-01-24 08:56:25.983739: step: 812/530, loss: 0.00391278974711895
2023-01-24 08:56:27.076191: step: 816/530, loss: 0.005585444159805775
2023-01-24 08:56:28.160764: step: 820/530, loss: 0.0018051897641271353
2023-01-24 08:56:29.274639: step: 824/530, loss: 0.00956685934215784
2023-01-24 08:56:30.370415: step: 828/530, loss: 0.004708088468760252
2023-01-24 08:56:31.481220: step: 832/530, loss: 0.012936240062117577
2023-01-24 08:56:32.579464: step: 836/530, loss: 0.00329538993537426
2023-01-24 08:56:33.641992: step: 840/530, loss: 0.01207366306334734
2023-01-24 08:56:34.731458: step: 844/530, loss: 0.004577316343784332
2023-01-24 08:56:35.824310: step: 848/530, loss: 0.006770789623260498
2023-01-24 08:56:36.915115: step: 852/530, loss: 1.0023153436122811e-06
2023-01-24 08:56:38.008084: step: 856/530, loss: 0.0012699918588623405
2023-01-24 08:56:39.099070: step: 860/530, loss: 0.0027047626208513975
2023-01-24 08:56:40.226861: step: 864/530, loss: 0.00703151011839509
2023-01-24 08:56:41.322239: step: 868/530, loss: 0.00563738401979208
2023-01-24 08:56:42.417080: step: 872/530, loss: 0.014759116806089878
2023-01-24 08:56:43.558143: step: 876/530, loss: 0.004694843199104071
2023-01-24 08:56:44.637756: step: 880/530, loss: 0.0023958419915288687
2023-01-24 08:56:45.737647: step: 884/530, loss: 0.0009593351278454065
2023-01-24 08:56:46.812751: step: 888/530, loss: 0.005466763861477375
2023-01-24 08:56:47.903482: step: 892/530, loss: 0.007187244016677141
2023-01-24 08:56:49.013434: step: 896/530, loss: 0.0025142570957541466
2023-01-24 08:56:50.113462: step: 900/530, loss: 0.004243083298206329
2023-01-24 08:56:51.193621: step: 904/530, loss: 0.0016123928362503648
2023-01-24 08:56:52.274617: step: 908/530, loss: 0.0074295299127697945
2023-01-24 08:56:53.386195: step: 912/530, loss: 0.007709177676588297
2023-01-24 08:56:54.475632: step: 916/530, loss: 0.01350318267941475
2023-01-24 08:56:55.571878: step: 920/530, loss: 0.002081478713080287
2023-01-24 08:56:56.659845: step: 924/530, loss: 0.006151957903057337
2023-01-24 08:56:57.741601: step: 928/530, loss: 0.0008753815782256424
2023-01-24 08:56:58.837733: step: 932/530, loss: 0.010530886240303516
2023-01-24 08:56:59.919113: step: 936/530, loss: 0.0027114395052194595
2023-01-24 08:57:01.022601: step: 940/530, loss: 0.002038032514974475
2023-01-24 08:57:02.132165: step: 944/530, loss: 0.0014491023030132055
2023-01-24 08:57:03.229172: step: 948/530, loss: 0.04799647256731987
2023-01-24 08:57:04.314589: step: 952/530, loss: 0.011955811642110348
2023-01-24 08:57:05.427310: step: 956/530, loss: 0.003184965346008539
2023-01-24 08:57:06.491057: step: 960/530, loss: 0.00422566756606102
2023-01-24 08:57:07.570039: step: 964/530, loss: 0.007717070635408163
2023-01-24 08:57:08.653565: step: 968/530, loss: 0.0023763130884617567
2023-01-24 08:57:09.750136: step: 972/530, loss: 0.008148809894919395
2023-01-24 08:57:10.841380: step: 976/530, loss: 0.0048790560103952885
2023-01-24 08:57:11.929869: step: 980/530, loss: 0.0020296794828027487
2023-01-24 08:57:13.029239: step: 984/530, loss: 0.0063913497142493725
2023-01-24 08:57:14.108617: step: 988/530, loss: 0.0021754205226898193
2023-01-24 08:57:15.205224: step: 992/530, loss: 0.0029841738287359476
2023-01-24 08:57:16.309246: step: 996/530, loss: 0.00038652989314869046
2023-01-24 08:57:17.378532: step: 1000/530, loss: 0.004347706213593483
2023-01-24 08:57:18.476714: step: 1004/530, loss: 0.011413280852138996
2023-01-24 08:57:19.568226: step: 1008/530, loss: 0.005719151347875595
2023-01-24 08:57:20.661202: step: 1012/530, loss: 0.02083134651184082
2023-01-24 08:57:21.747828: step: 1016/530, loss: 0.00015534705016762018
2023-01-24 08:57:22.824080: step: 1020/530, loss: 0.010990736074745655
2023-01-24 08:57:23.922836: step: 1024/530, loss: 0.003862551413476467
2023-01-24 08:57:25.020496: step: 1028/530, loss: 0.007739650085568428
2023-01-24 08:57:26.109900: step: 1032/530, loss: 0.003504781750962138
2023-01-24 08:57:27.210785: step: 1036/530, loss: 0.008097977377474308
2023-01-24 08:57:28.325564: step: 1040/530, loss: 0.0045357379131019115
2023-01-24 08:57:29.438790: step: 1044/530, loss: 0.009852608665823936
2023-01-24 08:57:30.523756: step: 1048/530, loss: 0.0010357053251937032
2023-01-24 08:57:31.615882: step: 1052/530, loss: 0.0044439793564379215
2023-01-24 08:57:32.687247: step: 1056/530, loss: 1.589901694387663e-05
2023-01-24 08:57:33.793392: step: 1060/530, loss: 0.011970419436693192
2023-01-24 08:57:34.878530: step: 1064/530, loss: 0.0026482355315238237
2023-01-24 08:57:35.984484: step: 1068/530, loss: 0.00543260108679533
2023-01-24 08:57:37.075702: step: 1072/530, loss: 0.004344042856246233
2023-01-24 08:57:38.166120: step: 1076/530, loss: 0.001634949236176908
2023-01-24 08:57:39.271156: step: 1080/530, loss: 0.010718392208218575
2023-01-24 08:57:40.372808: step: 1084/530, loss: 0.00682159373536706
2023-01-24 08:57:41.463291: step: 1088/530, loss: 0.00335360923781991
2023-01-24 08:57:42.553321: step: 1092/530, loss: 0.006648879498243332
2023-01-24 08:57:43.633206: step: 1096/530, loss: 0.0009464729228056967
2023-01-24 08:57:44.735842: step: 1100/530, loss: 0.05777476727962494
2023-01-24 08:57:45.820600: step: 1104/530, loss: 0.0010224033612757921
2023-01-24 08:57:46.928870: step: 1108/530, loss: 0.010388949885964394
2023-01-24 08:57:48.014384: step: 1112/530, loss: 0.01638748124241829
2023-01-24 08:57:49.112005: step: 1116/530, loss: 0.00656832056120038
2023-01-24 08:57:50.180361: step: 1120/530, loss: 0.001014142413623631
2023-01-24 08:57:51.244279: step: 1124/530, loss: 0.002948155626654625
2023-01-24 08:57:52.329075: step: 1128/530, loss: 0.0008527644677087665
2023-01-24 08:57:53.417511: step: 1132/530, loss: 0.004900769796222448
2023-01-24 08:57:54.515673: step: 1136/530, loss: 0.0004243611474521458
2023-01-24 08:57:55.605524: step: 1140/530, loss: 0.002492793370038271
2023-01-24 08:57:56.706164: step: 1144/530, loss: 0.005905480124056339
2023-01-24 08:57:57.817324: step: 1148/530, loss: 0.011737021617591381
2023-01-24 08:57:58.913929: step: 1152/530, loss: 0.010104364715516567
2023-01-24 08:58:00.009795: step: 1156/530, loss: 0.0032714896369725466
2023-01-24 08:58:01.095794: step: 1160/530, loss: 0.004936861339956522
2023-01-24 08:58:02.192559: step: 1164/530, loss: 0.00797466840595007
2023-01-24 08:58:03.262731: step: 1168/530, loss: 0.0021329522132873535
2023-01-24 08:58:04.367152: step: 1172/530, loss: 0.00536087341606617
2023-01-24 08:58:05.476701: step: 1176/530, loss: 0.003951833583414555
2023-01-24 08:58:06.563635: step: 1180/530, loss: 0.008810511790215969
2023-01-24 08:58:07.643352: step: 1184/530, loss: 0.04611946642398834
2023-01-24 08:58:08.736621: step: 1188/530, loss: 0.022184358909726143
2023-01-24 08:58:09.823159: step: 1192/530, loss: 0.004205614328384399
2023-01-24 08:58:10.911050: step: 1196/530, loss: 0.0005284690414555371
2023-01-24 08:58:12.024781: step: 1200/530, loss: 0.004280883818864822
2023-01-24 08:58:13.137249: step: 1204/530, loss: 0.003171307034790516
2023-01-24 08:58:14.237130: step: 1208/530, loss: 0.007054960820823908
2023-01-24 08:58:15.325384: step: 1212/530, loss: 0.005159756634384394
2023-01-24 08:58:16.425175: step: 1216/530, loss: 0.0030938643030822277
2023-01-24 08:58:17.521456: step: 1220/530, loss: 0.01114040520042181
2023-01-24 08:58:18.627053: step: 1224/530, loss: 0.020213384181261063
2023-01-24 08:58:19.728650: step: 1228/530, loss: 0.007830311544239521
2023-01-24 08:58:20.815361: step: 1232/530, loss: 0.006653353571891785
2023-01-24 08:58:21.918376: step: 1236/530, loss: 0.010676193051040173
2023-01-24 08:58:23.040725: step: 1240/530, loss: 0.007289595436304808
2023-01-24 08:58:24.123706: step: 1244/530, loss: 0.0049084085039794445
2023-01-24 08:58:25.219995: step: 1248/530, loss: 0.029946664348244667
2023-01-24 08:58:26.301901: step: 1252/530, loss: 0.006143920123577118
2023-01-24 08:58:27.384306: step: 1256/530, loss: 0.0018259295029565692
2023-01-24 08:58:28.474144: step: 1260/530, loss: 0.009663070552051067
2023-01-24 08:58:29.557748: step: 1264/530, loss: 0.0010316005209460855
2023-01-24 08:58:30.655941: step: 1268/530, loss: 0.003054466098546982
2023-01-24 08:58:31.761635: step: 1272/530, loss: 0.005911185871809721
2023-01-24 08:58:32.887838: step: 1276/530, loss: 0.0035121699329465628
2023-01-24 08:58:33.977711: step: 1280/530, loss: 0.030863603577017784
2023-01-24 08:58:35.077426: step: 1284/530, loss: 0.02290409430861473
2023-01-24 08:58:36.186516: step: 1288/530, loss: 0.004529096651822329
2023-01-24 08:58:37.277723: step: 1292/530, loss: 0.010354121215641499
2023-01-24 08:58:38.373242: step: 1296/530, loss: 0.00481444364413619
2023-01-24 08:58:39.465368: step: 1300/530, loss: 0.007985670119524002
2023-01-24 08:58:40.561276: step: 1304/530, loss: 0.03664156794548035
2023-01-24 08:58:41.680307: step: 1308/530, loss: 0.002835296094417572
2023-01-24 08:58:42.811863: step: 1312/530, loss: 0.00440608337521553
2023-01-24 08:58:43.909272: step: 1316/530, loss: 0.004514886066317558
2023-01-24 08:58:44.991288: step: 1320/530, loss: 0.003778372658416629
2023-01-24 08:58:46.084162: step: 1324/530, loss: 0.0034132925793528557
2023-01-24 08:58:47.169174: step: 1328/530, loss: 0.002136263297870755
2023-01-24 08:58:48.251041: step: 1332/530, loss: 0.002274127444252372
2023-01-24 08:58:49.321761: step: 1336/530, loss: 0.0010393350385129452
2023-01-24 08:58:50.411279: step: 1340/530, loss: 0.019602840766310692
2023-01-24 08:58:51.520382: step: 1344/530, loss: 0.0013386289356276393
2023-01-24 08:58:52.611362: step: 1348/530, loss: 0.006865911651402712
2023-01-24 08:58:53.698057: step: 1352/530, loss: 0.005287148989737034
2023-01-24 08:58:54.781142: step: 1356/530, loss: 0.00351408077403903
2023-01-24 08:58:55.894011: step: 1360/530, loss: 0.016778897494077682
2023-01-24 08:58:56.990012: step: 1364/530, loss: 0.009416652843356133
2023-01-24 08:58:58.079733: step: 1368/530, loss: 0.0018788962624967098
2023-01-24 08:58:59.184747: step: 1372/530, loss: 0.007068673148751259
2023-01-24 08:59:00.278025: step: 1376/530, loss: 0.003668523859232664
2023-01-24 08:59:01.364236: step: 1380/530, loss: 0.0065972814336419106
2023-01-24 08:59:02.447682: step: 1384/530, loss: 0.004082637373358011
2023-01-24 08:59:03.520692: step: 1388/530, loss: 0.0013107869308441877
2023-01-24 08:59:04.610216: step: 1392/530, loss: 0.017675383016467094
2023-01-24 08:59:05.719731: step: 1396/530, loss: 0.004469520412385464
2023-01-24 08:59:06.795457: step: 1400/530, loss: 0.004404785577207804
2023-01-24 08:59:07.893035: step: 1404/530, loss: 0.005567232612520456
2023-01-24 08:59:08.985497: step: 1408/530, loss: 0.004682925529778004
2023-01-24 08:59:10.068836: step: 1412/530, loss: 0.02175498753786087
2023-01-24 08:59:11.173793: step: 1416/530, loss: 0.012862207368016243
2023-01-24 08:59:12.278179: step: 1420/530, loss: 0.0
2023-01-24 08:59:13.390229: step: 1424/530, loss: 0.0008108131005428731
2023-01-24 08:59:14.480041: step: 1428/530, loss: 0.0012629760894924402
2023-01-24 08:59:15.576385: step: 1432/530, loss: 0.005576068535447121
2023-01-24 08:59:16.677224: step: 1436/530, loss: 0.015617192722856998
2023-01-24 08:59:17.753367: step: 1440/530, loss: 0.00028293757350184023
2023-01-24 08:59:18.834265: step: 1444/530, loss: 0.007297741714864969
2023-01-24 08:59:19.929550: step: 1448/530, loss: 0.0019038491882383823
2023-01-24 08:59:21.034944: step: 1452/530, loss: 0.0021815032232552767
2023-01-24 08:59:22.136889: step: 1456/530, loss: 0.0028231716714799404
2023-01-24 08:59:23.257348: step: 1460/530, loss: 0.0028600329533219337
2023-01-24 08:59:24.333608: step: 1464/530, loss: 0.0017172808293253183
2023-01-24 08:59:25.434397: step: 1468/530, loss: 0.002904909197241068
2023-01-24 08:59:26.525785: step: 1472/530, loss: 0.006400510668754578
2023-01-24 08:59:27.610784: step: 1476/530, loss: 0.005666607525199652
2023-01-24 08:59:28.703837: step: 1480/530, loss: 0.013713116757571697
2023-01-24 08:59:29.787638: step: 1484/530, loss: 0.005708231590688229
2023-01-24 08:59:30.885488: step: 1488/530, loss: 0.005585353821516037
2023-01-24 08:59:31.984368: step: 1492/530, loss: 0.00759673397988081
2023-01-24 08:59:33.081019: step: 1496/530, loss: 0.003911247942596674
2023-01-24 08:59:34.168611: step: 1500/530, loss: 0.0010523127857595682
2023-01-24 08:59:35.242672: step: 1504/530, loss: 0.005459906999021769
2023-01-24 08:59:36.352153: step: 1508/530, loss: 0.0017450046725571156
2023-01-24 08:59:37.458800: step: 1512/530, loss: 0.004098229110240936
2023-01-24 08:59:38.565830: step: 1516/530, loss: 0.009447664953768253
2023-01-24 08:59:39.649603: step: 1520/530, loss: 0.0018781708786264062
2023-01-24 08:59:40.763161: step: 1524/530, loss: 0.003473359625786543
2023-01-24 08:59:41.905453: step: 1528/530, loss: 0.01289084181189537
2023-01-24 08:59:42.990577: step: 1532/530, loss: 0.0019815952982753515
2023-01-24 08:59:44.093093: step: 1536/530, loss: 0.003952621947973967
2023-01-24 08:59:45.187236: step: 1540/530, loss: 0.027720943093299866
2023-01-24 08:59:46.267814: step: 1544/530, loss: 0.0006244656979106367
2023-01-24 08:59:47.346865: step: 1548/530, loss: 0.0027780826203525066
2023-01-24 08:59:48.442220: step: 1552/530, loss: 0.014304236508905888
2023-01-24 08:59:49.537645: step: 1556/530, loss: 0.005743764340877533
2023-01-24 08:59:50.627150: step: 1560/530, loss: 0.004498668015003204
2023-01-24 08:59:51.727719: step: 1564/530, loss: 0.0001885459787445143
2023-01-24 08:59:52.820434: step: 1568/530, loss: 0.03931552171707153
2023-01-24 08:59:53.924999: step: 1572/530, loss: 0.0117438193410635
2023-01-24 08:59:55.010827: step: 1576/530, loss: 0.008759861811995506
2023-01-24 08:59:56.091350: step: 1580/530, loss: 0.004414891358464956
2023-01-24 08:59:57.187363: step: 1584/530, loss: 0.015773741528391838
2023-01-24 08:59:58.312095: step: 1588/530, loss: 0.014878548681735992
2023-01-24 08:59:59.405712: step: 1592/530, loss: 0.022531064227223396
2023-01-24 09:00:00.499968: step: 1596/530, loss: 0.00883167702704668
2023-01-24 09:00:01.599708: step: 1600/530, loss: 0.0033920041751116514
2023-01-24 09:00:02.703707: step: 1604/530, loss: 0.0026087721344083548
2023-01-24 09:00:03.780121: step: 1608/530, loss: 0.013353990390896797
2023-01-24 09:00:04.851164: step: 1612/530, loss: 0.009016508236527443
2023-01-24 09:00:05.953146: step: 1616/530, loss: 0.01207042671740055
2023-01-24 09:00:07.091956: step: 1620/530, loss: 0.007473519071936607
2023-01-24 09:00:08.176458: step: 1624/530, loss: 0.00028923607897013426
2023-01-24 09:00:09.275735: step: 1628/530, loss: 0.008898764848709106
2023-01-24 09:00:10.344930: step: 1632/530, loss: 0.005579464137554169
2023-01-24 09:00:11.467800: step: 1636/530, loss: 0.003116974839940667
2023-01-24 09:00:12.556848: step: 1640/530, loss: 0.000852027500513941
2023-01-24 09:00:13.647070: step: 1644/530, loss: 0.0015090826200321317
2023-01-24 09:00:14.757775: step: 1648/530, loss: 0.001047214725986123
2023-01-24 09:00:15.853235: step: 1652/530, loss: 0.004282757639884949
2023-01-24 09:00:16.928340: step: 1656/530, loss: 0.0025495090521872044
2023-01-24 09:00:18.033733: step: 1660/530, loss: 0.00820249319076538
2023-01-24 09:00:19.128575: step: 1664/530, loss: 0.0005332635482773185
2023-01-24 09:00:20.224516: step: 1668/530, loss: 0.0013903120998293161
2023-01-24 09:00:21.316432: step: 1672/530, loss: 0.007464383263140917
2023-01-24 09:00:22.429978: step: 1676/530, loss: 0.007312059868127108
2023-01-24 09:00:23.547475: step: 1680/530, loss: 0.006925118621438742
2023-01-24 09:00:24.633047: step: 1684/530, loss: 0.00024333904730156064
2023-01-24 09:00:25.732836: step: 1688/530, loss: 0.0006623081862926483
2023-01-24 09:00:26.816569: step: 1692/530, loss: 0.00014406631817109883
2023-01-24 09:00:27.912283: step: 1696/530, loss: 0.005367347039282322
2023-01-24 09:00:28.999711: step: 1700/530, loss: 0.01579924114048481
2023-01-24 09:00:30.097400: step: 1704/530, loss: 0.0027582456823438406
2023-01-24 09:00:31.221211: step: 1708/530, loss: 0.027939584106206894
2023-01-24 09:00:32.307628: step: 1712/530, loss: 0.0029140375554561615
2023-01-24 09:00:33.389832: step: 1716/530, loss: 0.0007726530893705785
2023-01-24 09:00:34.472362: step: 1720/530, loss: 0.008381947875022888
2023-01-24 09:00:35.558544: step: 1724/530, loss: 0.005194207187741995
2023-01-24 09:00:36.662255: step: 1728/530, loss: 2.8067463063052855e-05
2023-01-24 09:00:37.768838: step: 1732/530, loss: 0.004748601000756025
2023-01-24 09:00:38.864194: step: 1736/530, loss: 0.004202454816550016
2023-01-24 09:00:39.949940: step: 1740/530, loss: 0.005364618264138699
2023-01-24 09:00:41.048097: step: 1744/530, loss: 0.0045860521495342255
2023-01-24 09:00:42.133229: step: 1748/530, loss: 0.0003562755009625107
2023-01-24 09:00:43.220762: step: 1752/530, loss: 0.002667174907401204
2023-01-24 09:00:44.320435: step: 1756/530, loss: 0.017062919214367867
2023-01-24 09:00:45.415301: step: 1760/530, loss: 0.0016122220549732447
2023-01-24 09:00:46.509704: step: 1764/530, loss: 0.0038395128212869167
2023-01-24 09:00:47.595248: step: 1768/530, loss: 0.0067592100240290165
2023-01-24 09:00:48.666749: step: 1772/530, loss: 0.005635429173707962
2023-01-24 09:00:49.762541: step: 1776/530, loss: 0.0037499871104955673
2023-01-24 09:00:50.873864: step: 1780/530, loss: 0.009561735205352306
2023-01-24 09:00:51.964825: step: 1784/530, loss: 0.009552452713251114
2023-01-24 09:00:53.053431: step: 1788/530, loss: 0.0048697213642299175
2023-01-24 09:00:54.129687: step: 1792/530, loss: 0.005792495794594288
2023-01-24 09:00:55.220143: step: 1796/530, loss: 0.001262329868040979
2023-01-24 09:00:56.350775: step: 1800/530, loss: 0.008863368071615696
2023-01-24 09:00:57.442682: step: 1804/530, loss: 0.0012546515790745616
2023-01-24 09:00:58.533510: step: 1808/530, loss: 0.0063784136436879635
2023-01-24 09:00:59.641857: step: 1812/530, loss: 0.00655109528452158
2023-01-24 09:01:00.735536: step: 1816/530, loss: 0.005710633937269449
2023-01-24 09:01:01.821619: step: 1820/530, loss: 0.0023225401528179646
2023-01-24 09:01:02.918101: step: 1824/530, loss: 0.002122816164046526
2023-01-24 09:01:04.039756: step: 1828/530, loss: 0.012034503743052483
2023-01-24 09:01:05.133114: step: 1832/530, loss: 0.005654426291584969
2023-01-24 09:01:06.230687: step: 1836/530, loss: 0.05996264889836311
2023-01-24 09:01:07.318442: step: 1840/530, loss: 0.0023963332641869783
2023-01-24 09:01:08.419808: step: 1844/530, loss: 0.004057222977280617
2023-01-24 09:01:09.505161: step: 1848/530, loss: 0.004797052592039108
2023-01-24 09:01:10.616767: step: 1852/530, loss: 0.018800226971507072
2023-01-24 09:01:11.697138: step: 1856/530, loss: 0.012684672139585018
2023-01-24 09:01:12.799773: step: 1860/530, loss: 0.005445479415357113
2023-01-24 09:01:13.903393: step: 1864/530, loss: 0.006310692522674799
2023-01-24 09:01:14.989981: step: 1868/530, loss: 0.0058257682248950005
2023-01-24 09:01:16.075968: step: 1872/530, loss: 0.007973291911184788
2023-01-24 09:01:17.172866: step: 1876/530, loss: 0.00021161425684113055
2023-01-24 09:01:18.266876: step: 1880/530, loss: 0.003784623695537448
2023-01-24 09:01:19.358662: step: 1884/530, loss: 0.003617755603045225
2023-01-24 09:01:20.440149: step: 1888/530, loss: 0.005014495924115181
2023-01-24 09:01:21.542282: step: 1892/530, loss: 0.007986443117260933
2023-01-24 09:01:22.637631: step: 1896/530, loss: 0.0638704001903534
2023-01-24 09:01:23.744164: step: 1900/530, loss: 0.01315513625741005
2023-01-24 09:01:24.824796: step: 1904/530, loss: 0.003585227532312274
2023-01-24 09:01:25.915366: step: 1908/530, loss: 0.010146183893084526
2023-01-24 09:01:26.981251: step: 1912/530, loss: 0.0002532742510084063
2023-01-24 09:01:28.062903: step: 1916/530, loss: 0.008187280967831612
2023-01-24 09:01:29.182685: step: 1920/530, loss: 0.004738227464258671
2023-01-24 09:01:30.270439: step: 1924/530, loss: 0.0065395706333220005
2023-01-24 09:01:31.374414: step: 1928/530, loss: 0.002547272713854909
2023-01-24 09:01:32.464775: step: 1932/530, loss: 0.03828773647546768
2023-01-24 09:01:33.555831: step: 1936/530, loss: 0.026910273358225822
2023-01-24 09:01:34.637103: step: 1940/530, loss: 0.016570253297686577
2023-01-24 09:01:35.733316: step: 1944/530, loss: 0.0017694535199552774
2023-01-24 09:01:36.844181: step: 1948/530, loss: 0.0058820126578211784
2023-01-24 09:01:37.954713: step: 1952/530, loss: 0.0047866362147033215
2023-01-24 09:01:39.033851: step: 1956/530, loss: 0.0031540365889668465
2023-01-24 09:01:40.137668: step: 1960/530, loss: 0.009054695256054401
2023-01-24 09:01:41.226117: step: 1964/530, loss: 0.00031283817952498794
2023-01-24 09:01:42.302802: step: 1968/530, loss: 0.011626465246081352
2023-01-24 09:01:43.394250: step: 1972/530, loss: 0.004292723257094622
2023-01-24 09:01:44.485189: step: 1976/530, loss: 0.0026255559641867876
2023-01-24 09:01:45.621708: step: 1980/530, loss: 0.014015048742294312
2023-01-24 09:01:46.736044: step: 1984/530, loss: 0.01889391802251339
2023-01-24 09:01:47.836287: step: 1988/530, loss: 0.0008177540730684996
2023-01-24 09:01:48.917912: step: 1992/530, loss: 0.0025048761162906885
2023-01-24 09:01:50.015519: step: 1996/530, loss: 0.006152528803795576
2023-01-24 09:01:51.120200: step: 2000/530, loss: 0.02581629902124405
2023-01-24 09:01:52.229377: step: 2004/530, loss: 0.0019788651261478662
2023-01-24 09:01:53.321928: step: 2008/530, loss: 0.004808387719094753
2023-01-24 09:01:54.415777: step: 2012/530, loss: 0.0006217002519406378
2023-01-24 09:01:55.509030: step: 2016/530, loss: 0.01565537042915821
2023-01-24 09:01:56.621750: step: 2020/530, loss: 0.004735218361020088
2023-01-24 09:01:57.696599: step: 2024/530, loss: 0.0012645252281799912
2023-01-24 09:01:58.783993: step: 2028/530, loss: 0.004584374371916056
2023-01-24 09:01:59.879350: step: 2032/530, loss: 0.011293581686913967
2023-01-24 09:02:00.964157: step: 2036/530, loss: 0.004231262020766735
2023-01-24 09:02:02.041088: step: 2040/530, loss: 0.007557030767202377
2023-01-24 09:02:03.145743: step: 2044/530, loss: 0.0001206692832056433
2023-01-24 09:02:04.215387: step: 2048/530, loss: 0.006060923915356398
2023-01-24 09:02:05.300257: step: 2052/530, loss: 0.020609134808182716
2023-01-24 09:02:06.399740: step: 2056/530, loss: 0.011785211972892284
2023-01-24 09:02:07.517831: step: 2060/530, loss: 0.000952857022639364
2023-01-24 09:02:08.593543: step: 2064/530, loss: 0.0046133059076964855
2023-01-24 09:02:09.691257: step: 2068/530, loss: 0.0043978020548820496
2023-01-24 09:02:10.797555: step: 2072/530, loss: 0.00933991838246584
2023-01-24 09:02:11.897814: step: 2076/530, loss: 0.004743628203868866
2023-01-24 09:02:12.992532: step: 2080/530, loss: 0.18316756188869476
2023-01-24 09:02:14.069677: step: 2084/530, loss: 0.009476578794419765
2023-01-24 09:02:15.165502: step: 2088/530, loss: 0.011847156099975109
2023-01-24 09:02:16.234934: step: 2092/530, loss: 0.006440174765884876
2023-01-24 09:02:17.341988: step: 2096/530, loss: 0.010593869723379612
2023-01-24 09:02:18.417050: step: 2100/530, loss: 0.0010112167801707983
2023-01-24 09:02:19.496645: step: 2104/530, loss: 0.0010628459276631474
2023-01-24 09:02:20.581102: step: 2108/530, loss: 0.004539801739156246
2023-01-24 09:02:21.703375: step: 2112/530, loss: 0.008094402961432934
2023-01-24 09:02:22.794848: step: 2116/530, loss: 0.002351432805880904
2023-01-24 09:02:23.863000: step: 2120/530, loss: 0.011183440685272217
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35005648019865976, 'r': 0.34341404224422595, 'f1': 0.3467034487791324}, 'combined': 0.25546569910041333, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34228543037310466, 'r': 0.27152612775393664, 'f1': 0.302827264378632}, 'combined': 0.18807166945620304, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3330532308207982, 'r': 0.25999214658935826, 'f1': 0.29202225565863543}, 'combined': 0.1813611903564157, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3800740392648288, 'r': 0.32454139975175134, 'f1': 0.3501193811037317}, 'combined': 0.25798270186590755, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3473347837828553, 'r': 0.2684729868726315, 'f1': 0.3028542713830465}, 'combined': 0.18808844222736573, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6047570850202428, 'r': 0.27109800362976405, 'f1': 0.3743734335839598}, 'combined': 0.24958228905597318, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 09:04:48.898227: step: 4/530, loss: 0.012852641753852367
2023-01-24 09:04:49.984953: step: 8/530, loss: 0.002417398849502206
2023-01-24 09:04:51.048113: step: 12/530, loss: 0.0011995211243629456
2023-01-24 09:04:52.158543: step: 16/530, loss: 0.0010039876215159893
2023-01-24 09:04:53.244677: step: 20/530, loss: 0.00017232468235306442
2023-01-24 09:04:54.337644: step: 24/530, loss: 0.007264132145792246
2023-01-24 09:04:55.401610: step: 28/530, loss: 0.0036720209755003452
2023-01-24 09:04:56.475353: step: 32/530, loss: 0.0048157824203372
2023-01-24 09:04:57.540890: step: 36/530, loss: 0.0034320226404815912
2023-01-24 09:04:58.624488: step: 40/530, loss: 0.003279099939391017
2023-01-24 09:04:59.717817: step: 44/530, loss: 0.0028031456749886274
2023-01-24 09:05:00.804371: step: 48/530, loss: 0.002326064743101597
2023-01-24 09:05:01.897593: step: 52/530, loss: 0.008965677581727505
2023-01-24 09:05:02.972198: step: 56/530, loss: 0.010192080400884151
2023-01-24 09:05:04.058922: step: 60/530, loss: 0.0023942210245877504
2023-01-24 09:05:05.147048: step: 64/530, loss: 0.007135374005883932
2023-01-24 09:05:06.229093: step: 68/530, loss: 4.353479380370118e-05
2023-01-24 09:05:07.324487: step: 72/530, loss: 0.0021611973643302917
2023-01-24 09:05:08.397430: step: 76/530, loss: 0.004792075138539076
2023-01-24 09:05:09.480939: step: 80/530, loss: 0.01676429808139801
2023-01-24 09:05:10.541079: step: 84/530, loss: 0.005350546911358833
2023-01-24 09:05:11.655543: step: 88/530, loss: 0.006298549007624388
2023-01-24 09:05:12.770867: step: 92/530, loss: 0.0003452624077908695
2023-01-24 09:05:13.857173: step: 96/530, loss: 0.0034581469371914864
2023-01-24 09:05:14.947783: step: 100/530, loss: 0.0016276293899863958
2023-01-24 09:05:16.048402: step: 104/530, loss: 0.00324163306504488
2023-01-24 09:05:17.141522: step: 108/530, loss: 0.0009973623091354966
2023-01-24 09:05:18.211488: step: 112/530, loss: 0.0018076226115226746
2023-01-24 09:05:19.282677: step: 116/530, loss: 0.006380291655659676
2023-01-24 09:05:20.365578: step: 120/530, loss: 0.0030232977587729692
2023-01-24 09:05:21.442611: step: 124/530, loss: 0.006191682536154985
2023-01-24 09:05:22.523001: step: 128/530, loss: 0.009679173119366169
2023-01-24 09:05:23.635138: step: 132/530, loss: 0.0016814138507470489
2023-01-24 09:05:24.719123: step: 136/530, loss: 0.000629706250037998
2023-01-24 09:05:25.833695: step: 140/530, loss: 0.006482336670160294
2023-01-24 09:05:26.912860: step: 144/530, loss: 0.003738175146281719
2023-01-24 09:05:27.978570: step: 148/530, loss: 0.0007629310712218285
2023-01-24 09:05:29.066688: step: 152/530, loss: 0.0030066377948969603
2023-01-24 09:05:30.161622: step: 156/530, loss: 0.0031846221536397934
2023-01-24 09:05:31.258656: step: 160/530, loss: 0.004700453020632267
2023-01-24 09:05:32.339530: step: 164/530, loss: 0.0013999439543113112
2023-01-24 09:05:33.430473: step: 168/530, loss: 0.03358696028590202
2023-01-24 09:05:34.528943: step: 172/530, loss: 0.008787048980593681
2023-01-24 09:05:35.620027: step: 176/530, loss: 0.004170938394963741
2023-01-24 09:05:36.708825: step: 180/530, loss: 0.002950782887637615
2023-01-24 09:05:37.780578: step: 184/530, loss: 0.0009335349895991385
2023-01-24 09:05:38.886159: step: 188/530, loss: 0.018743734806776047
2023-01-24 09:05:39.962496: step: 192/530, loss: 0.006596866529434919
2023-01-24 09:05:41.032544: step: 196/530, loss: 0.006678693927824497
2023-01-24 09:05:42.116590: step: 200/530, loss: 0.0031592408195137978
2023-01-24 09:05:43.208664: step: 204/530, loss: 0.002463296055793762
2023-01-24 09:05:44.298085: step: 208/530, loss: 0.003427669405937195
2023-01-24 09:05:45.380732: step: 212/530, loss: 0.011702906340360641
2023-01-24 09:05:46.501977: step: 216/530, loss: 0.008907417766749859
2023-01-24 09:05:47.586738: step: 220/530, loss: 0.008853808045387268
2023-01-24 09:05:48.680294: step: 224/530, loss: 0.010829031467437744
2023-01-24 09:05:49.765682: step: 228/530, loss: 0.0035358441527932882
2023-01-24 09:05:50.875167: step: 232/530, loss: 0.018984684720635414
2023-01-24 09:05:51.954126: step: 236/530, loss: 0.0011065416038036346
2023-01-24 09:05:53.040984: step: 240/530, loss: 0.0008059915853664279
2023-01-24 09:05:54.138605: step: 244/530, loss: 0.0029619589913636446
2023-01-24 09:05:55.233451: step: 248/530, loss: 0.004144147504121065
2023-01-24 09:05:56.318866: step: 252/530, loss: 0.00027097263955511153
2023-01-24 09:05:57.412605: step: 256/530, loss: 0.028288258239626884
2023-01-24 09:05:58.518492: step: 260/530, loss: 0.004978305194526911
2023-01-24 09:05:59.620080: step: 264/530, loss: 0.009526673704385757
2023-01-24 09:06:00.683160: step: 268/530, loss: 0.0008316404419019818
2023-01-24 09:06:01.805470: step: 272/530, loss: 0.0075862654484808445
2023-01-24 09:06:02.883699: step: 276/530, loss: 0.012735490687191486
2023-01-24 09:06:03.952150: step: 280/530, loss: 0.0005930901970714331
2023-01-24 09:06:05.042977: step: 284/530, loss: 0.008498327806591988
2023-01-24 09:06:06.136250: step: 288/530, loss: 0.003878409741446376
2023-01-24 09:06:07.257280: step: 292/530, loss: 0.002927615772932768
2023-01-24 09:06:08.360896: step: 296/530, loss: 0.006158793810755014
2023-01-24 09:06:09.472933: step: 300/530, loss: 0.006205850280821323
2023-01-24 09:06:10.550065: step: 304/530, loss: 0.009309251792728901
2023-01-24 09:06:11.632212: step: 308/530, loss: 0.009339329786598682
2023-01-24 09:06:12.708208: step: 312/530, loss: 0.004272827412933111
2023-01-24 09:06:13.790271: step: 316/530, loss: 0.0005239882739260793
2023-01-24 09:06:14.916796: step: 320/530, loss: 0.0031910634133964777
2023-01-24 09:06:16.003680: step: 324/530, loss: 0.0017521815607324243
2023-01-24 09:06:17.069557: step: 328/530, loss: 0.0010132597526535392
2023-01-24 09:06:18.168844: step: 332/530, loss: 0.002245164243504405
2023-01-24 09:06:19.267253: step: 336/530, loss: 0.001676232204772532
2023-01-24 09:06:20.341815: step: 340/530, loss: 0.0036706961691379547
2023-01-24 09:06:21.428218: step: 344/530, loss: 0.003087942488491535
2023-01-24 09:06:22.511360: step: 348/530, loss: 0.006789413746446371
2023-01-24 09:06:23.589508: step: 352/530, loss: 0.0005472687189467251
2023-01-24 09:06:24.684760: step: 356/530, loss: 0.005121403839439154
2023-01-24 09:06:25.791358: step: 360/530, loss: 0.0042812940664589405
2023-01-24 09:06:26.862515: step: 364/530, loss: 0.003609717357903719
2023-01-24 09:06:27.974859: step: 368/530, loss: 0.0018349169986322522
2023-01-24 09:06:29.071488: step: 372/530, loss: 0.014606616459786892
2023-01-24 09:06:30.145351: step: 376/530, loss: 0.0020804009400308132
2023-01-24 09:06:31.242198: step: 380/530, loss: 0.0035718935541808605
2023-01-24 09:06:32.328755: step: 384/530, loss: 0.006819744128733873
2023-01-24 09:06:33.431541: step: 388/530, loss: 0.00019025173969566822
2023-01-24 09:06:34.517717: step: 392/530, loss: 0.008957646787166595
2023-01-24 09:06:35.592268: step: 396/530, loss: 0.0007106844568625093
2023-01-24 09:06:36.700164: step: 400/530, loss: 0.008181637153029442
2023-01-24 09:06:37.803654: step: 404/530, loss: 0.0022422587499022484
2023-01-24 09:06:38.893690: step: 408/530, loss: 0.008068078197538853
2023-01-24 09:06:39.979820: step: 412/530, loss: 0.004556990694254637
2023-01-24 09:06:41.082126: step: 416/530, loss: 0.0008272951235994697
2023-01-24 09:06:42.150841: step: 420/530, loss: 0.006012100726366043
2023-01-24 09:06:43.218886: step: 424/530, loss: 0.001314446097239852
2023-01-24 09:06:44.308796: step: 428/530, loss: 0.0052610342390835285
2023-01-24 09:06:45.390804: step: 432/530, loss: 0.0009571047849021852
2023-01-24 09:06:46.466401: step: 436/530, loss: 0.0076738083735108376
2023-01-24 09:06:47.543222: step: 440/530, loss: 0.0029224767349660397
2023-01-24 09:06:48.658892: step: 444/530, loss: 0.02174765057861805
2023-01-24 09:06:49.738166: step: 448/530, loss: 0.0008959988481365144
2023-01-24 09:06:50.836975: step: 452/530, loss: 0.015675559639930725
2023-01-24 09:06:51.939857: step: 456/530, loss: 0.008674388751387596
2023-01-24 09:06:53.045003: step: 460/530, loss: 0.01830499991774559
2023-01-24 09:06:54.128531: step: 464/530, loss: 0.0009909734362736344
2023-01-24 09:06:55.193235: step: 468/530, loss: 0.0015118962619453669
2023-01-24 09:06:56.286082: step: 472/530, loss: 0.007263553328812122
2023-01-24 09:06:57.392219: step: 476/530, loss: 0.0
2023-01-24 09:06:58.478207: step: 480/530, loss: 0.0020446141716092825
2023-01-24 09:06:59.587252: step: 484/530, loss: 0.02304811030626297
2023-01-24 09:07:00.685213: step: 488/530, loss: 0.005052995402365923
2023-01-24 09:07:01.763684: step: 492/530, loss: 0.0004195969959255308
2023-01-24 09:07:02.858170: step: 496/530, loss: 0.06983699649572372
2023-01-24 09:07:03.944020: step: 500/530, loss: 0.0017783496296033263
2023-01-24 09:07:05.042356: step: 504/530, loss: 0.0007300215656869113
2023-01-24 09:07:06.143151: step: 508/530, loss: 0.005889096297323704
2023-01-24 09:07:07.249680: step: 512/530, loss: 0.011448380537331104
2023-01-24 09:07:08.329654: step: 516/530, loss: 1.6626150681986474e-05
2023-01-24 09:07:09.406333: step: 520/530, loss: 0.0055013555102050304
2023-01-24 09:07:10.510027: step: 524/530, loss: 0.005656551104038954
2023-01-24 09:07:11.616235: step: 528/530, loss: 0.00023554236395284534
2023-01-24 09:07:12.694369: step: 532/530, loss: 0.005936426110565662
2023-01-24 09:07:13.792106: step: 536/530, loss: 0.005324170924723148
2023-01-24 09:07:14.880256: step: 540/530, loss: 0.005824314896017313
2023-01-24 09:07:15.963502: step: 544/530, loss: 0.0023509550374001265
2023-01-24 09:07:17.047525: step: 548/530, loss: 0.030468204990029335
2023-01-24 09:07:18.127397: step: 552/530, loss: 0.0035597807727754116
2023-01-24 09:07:19.211232: step: 556/530, loss: 0.010581757873296738
2023-01-24 09:07:20.266487: step: 560/530, loss: 0.010156725533306599
2023-01-24 09:07:21.346457: step: 564/530, loss: 0.0016914489679038525
2023-01-24 09:07:22.419663: step: 568/530, loss: 0.0007650958141312003
2023-01-24 09:07:23.498288: step: 572/530, loss: 0.0035633896477520466
2023-01-24 09:07:24.577429: step: 576/530, loss: 0.0007015399751253426
2023-01-24 09:07:25.645822: step: 580/530, loss: 0.0006578704342246056
2023-01-24 09:07:26.717567: step: 584/530, loss: 0.005710997153073549
2023-01-24 09:07:27.794614: step: 588/530, loss: 0.009510494768619537
2023-01-24 09:07:28.881733: step: 592/530, loss: 0.028136061504483223
2023-01-24 09:07:29.978353: step: 596/530, loss: 0.014152660965919495
2023-01-24 09:07:31.065211: step: 600/530, loss: 0.008041109889745712
2023-01-24 09:07:32.147656: step: 604/530, loss: 0.0031933574937283993
2023-01-24 09:07:33.232964: step: 608/530, loss: 0.0004951993469148874
2023-01-24 09:07:34.353827: step: 612/530, loss: 0.007825084961950779
2023-01-24 09:07:35.442859: step: 616/530, loss: 0.0038491194136440754
2023-01-24 09:07:36.520297: step: 620/530, loss: 0.0062204692512750626
2023-01-24 09:07:37.606292: step: 624/530, loss: 0.0022343993186950684
2023-01-24 09:07:38.687439: step: 628/530, loss: 0.0030720075592398643
2023-01-24 09:07:39.780814: step: 632/530, loss: 0.005884266458451748
2023-01-24 09:07:40.866011: step: 636/530, loss: 0.003556633833795786
2023-01-24 09:07:41.961032: step: 640/530, loss: 0.004114823415875435
2023-01-24 09:07:43.052843: step: 644/530, loss: 0.011077985167503357
2023-01-24 09:07:44.129686: step: 648/530, loss: 0.00010280668357154354
2023-01-24 09:07:45.230269: step: 652/530, loss: 0.0008016469073481858
2023-01-24 09:07:46.323596: step: 656/530, loss: 0.005742603912949562
2023-01-24 09:07:47.422372: step: 660/530, loss: 0.008505282923579216
2023-01-24 09:07:48.518717: step: 664/530, loss: 0.00211735931225121
2023-01-24 09:07:49.598655: step: 668/530, loss: 0.0036868590395897627
2023-01-24 09:07:50.690893: step: 672/530, loss: 0.033049263060092926
2023-01-24 09:07:51.775422: step: 676/530, loss: 0.0032268972136080265
2023-01-24 09:07:52.843951: step: 680/530, loss: 0.0022875515278428793
2023-01-24 09:07:53.908374: step: 684/530, loss: 0.0013293405063450336
2023-01-24 09:07:55.000879: step: 688/530, loss: 0.006347678601741791
2023-01-24 09:07:56.096204: step: 692/530, loss: 0.007853042334318161
2023-01-24 09:07:57.162835: step: 696/530, loss: 0.0017268542433157563
2023-01-24 09:07:58.258640: step: 700/530, loss: 0.006198188289999962
2023-01-24 09:07:59.335969: step: 704/530, loss: 0.010438612662255764
2023-01-24 09:08:00.402471: step: 708/530, loss: 0.00693716062232852
2023-01-24 09:08:01.487772: step: 712/530, loss: 0.0028866783250123262
2023-01-24 09:08:02.565540: step: 716/530, loss: 0.00014014098269399256
2023-01-24 09:08:03.655583: step: 720/530, loss: 0.013577362522482872
2023-01-24 09:08:04.731867: step: 724/530, loss: 5.0817641749745235e-05
2023-01-24 09:08:05.819901: step: 728/530, loss: 0.00023314656573347747
2023-01-24 09:08:06.899300: step: 732/530, loss: 0.001911955769173801
2023-01-24 09:08:07.984735: step: 736/530, loss: 0.012397710233926773
2023-01-24 09:08:09.070703: step: 740/530, loss: 0.005772104486823082
2023-01-24 09:08:10.161774: step: 744/530, loss: 0.001831976929679513
2023-01-24 09:08:11.242169: step: 748/530, loss: 0.013668297789990902
2023-01-24 09:08:12.369165: step: 752/530, loss: 0.008609876036643982
2023-01-24 09:08:13.462361: step: 756/530, loss: 0.013752492144703865
2023-01-24 09:08:14.555715: step: 760/530, loss: 0.004622215870767832
2023-01-24 09:08:15.639678: step: 764/530, loss: 0.009318478405475616
2023-01-24 09:08:16.718188: step: 768/530, loss: 0.0001981892273761332
2023-01-24 09:08:17.783518: step: 772/530, loss: 0.005856137257069349
2023-01-24 09:08:18.887209: step: 776/530, loss: 0.0010913341538980603
2023-01-24 09:08:19.960453: step: 780/530, loss: 0.007248550653457642
2023-01-24 09:08:21.039845: step: 784/530, loss: 0.0026998359244316816
2023-01-24 09:08:22.118243: step: 788/530, loss: 0.00705366488546133
2023-01-24 09:08:23.194972: step: 792/530, loss: 0.00720044132322073
2023-01-24 09:08:24.282783: step: 796/530, loss: 0.0012210009153932333
2023-01-24 09:08:25.375462: step: 800/530, loss: 0.002764006843790412
2023-01-24 09:08:26.457130: step: 804/530, loss: 0.00411082711070776
2023-01-24 09:08:27.524865: step: 808/530, loss: 0.006338645238429308
2023-01-24 09:08:28.612454: step: 812/530, loss: 0.001269435859285295
2023-01-24 09:08:29.713765: step: 816/530, loss: 0.010235443711280823
2023-01-24 09:08:30.812409: step: 820/530, loss: 0.0014181012520566583
2023-01-24 09:08:31.906445: step: 824/530, loss: 0.0034648084547370672
2023-01-24 09:08:33.026786: step: 828/530, loss: 0.0005349619896151125
2023-01-24 09:08:34.104854: step: 832/530, loss: 0.025860896334052086
2023-01-24 09:08:35.180163: step: 836/530, loss: 0.009158861823379993
2023-01-24 09:08:36.266251: step: 840/530, loss: 0.012786809355020523
2023-01-24 09:08:37.355839: step: 844/530, loss: 0.0050424253568053246
2023-01-24 09:08:38.433724: step: 848/530, loss: 0.0037137819454073906
2023-01-24 09:08:39.519225: step: 852/530, loss: 0.006844476331025362
2023-01-24 09:08:40.605464: step: 856/530, loss: 0.003874870715662837
2023-01-24 09:08:41.692919: step: 860/530, loss: 0.0028753934893757105
2023-01-24 09:08:42.791685: step: 864/530, loss: 0.0017035690834745765
2023-01-24 09:08:43.861943: step: 868/530, loss: 0.0001334802946075797
2023-01-24 09:08:44.977986: step: 872/530, loss: 0.014125794172286987
2023-01-24 09:08:46.077070: step: 876/530, loss: 0.023393521085381508
2023-01-24 09:08:47.136647: step: 880/530, loss: 0.0006625691312365234
2023-01-24 09:08:48.221398: step: 884/530, loss: 0.012671408243477345
2023-01-24 09:08:49.318936: step: 888/530, loss: 0.002146540442481637
2023-01-24 09:08:50.395130: step: 892/530, loss: 0.007133450359106064
2023-01-24 09:08:51.469911: step: 896/530, loss: 0.004140970762819052
2023-01-24 09:08:52.569301: step: 900/530, loss: 0.0025890804827213287
2023-01-24 09:08:53.661645: step: 904/530, loss: 0.00036826045834459364
2023-01-24 09:08:54.742637: step: 908/530, loss: 0.0014974417863413692
2023-01-24 09:08:55.825068: step: 912/530, loss: 0.004251014441251755
2023-01-24 09:08:56.903694: step: 916/530, loss: 0.010467146523296833
2023-01-24 09:08:57.993088: step: 920/530, loss: 0.0064591895788908005
2023-01-24 09:08:59.105200: step: 924/530, loss: 0.005451238714158535
2023-01-24 09:09:00.213928: step: 928/530, loss: 0.0015243480447679758
2023-01-24 09:09:01.282919: step: 932/530, loss: 0.0034614023752510548
2023-01-24 09:09:02.366407: step: 936/530, loss: 0.00016352557577192783
2023-01-24 09:09:03.464658: step: 940/530, loss: 0.005220635328441858
2023-01-24 09:09:04.572470: step: 944/530, loss: 0.013248939998447895
2023-01-24 09:09:05.637967: step: 948/530, loss: 2.4616736027383013e-06
2023-01-24 09:09:06.742579: step: 952/530, loss: 0.008181281387805939
2023-01-24 09:09:07.825047: step: 956/530, loss: 0.0008815866895020008
2023-01-24 09:09:08.933796: step: 960/530, loss: 0.03313359245657921
2023-01-24 09:09:10.040718: step: 964/530, loss: 0.012474209070205688
2023-01-24 09:09:11.126181: step: 968/530, loss: 0.004883915651589632
2023-01-24 09:09:12.227589: step: 972/530, loss: 0.017077939584851265
2023-01-24 09:09:13.307562: step: 976/530, loss: 0.001611165120266378
2023-01-24 09:09:14.426562: step: 980/530, loss: 0.019696753472089767
2023-01-24 09:09:15.532615: step: 984/530, loss: 0.0008806691621430218
2023-01-24 09:09:16.618076: step: 988/530, loss: 0.012325761839747429
2023-01-24 09:09:17.723287: step: 992/530, loss: 0.009970033541321754
2023-01-24 09:09:18.828839: step: 996/530, loss: 0.0021491264924407005
2023-01-24 09:09:19.907135: step: 1000/530, loss: 0.0018775860080495477
2023-01-24 09:09:20.987864: step: 1004/530, loss: 0.010070179589092731
2023-01-24 09:09:22.086762: step: 1008/530, loss: 0.0173482745885849
2023-01-24 09:09:23.200422: step: 1012/530, loss: 0.004282968118786812
2023-01-24 09:09:24.290588: step: 1016/530, loss: 0.010686510242521763
2023-01-24 09:09:25.383812: step: 1020/530, loss: 0.015376301482319832
2023-01-24 09:09:26.478970: step: 1024/530, loss: 0.003207979490980506
2023-01-24 09:09:27.585132: step: 1028/530, loss: 0.004286313429474831
2023-01-24 09:09:28.667641: step: 1032/530, loss: 0.0025914551224559546
2023-01-24 09:09:29.769552: step: 1036/530, loss: 0.002869923133403063
2023-01-24 09:09:30.855873: step: 1040/530, loss: 0.0005609919899143279
2023-01-24 09:09:31.944337: step: 1044/530, loss: 0.007180202752351761
2023-01-24 09:09:33.044943: step: 1048/530, loss: 0.023522144183516502
2023-01-24 09:09:34.135391: step: 1052/530, loss: 0.004931448958814144
2023-01-24 09:09:35.240876: step: 1056/530, loss: 0.003753190627321601
2023-01-24 09:09:36.364474: step: 1060/530, loss: 0.04350333288311958
2023-01-24 09:09:37.482193: step: 1064/530, loss: 0.006681147031486034
2023-01-24 09:09:38.570293: step: 1068/530, loss: 0.013521349057555199
2023-01-24 09:09:39.663480: step: 1072/530, loss: 0.002822374925017357
2023-01-24 09:09:40.768568: step: 1076/530, loss: 0.002605520188808441
2023-01-24 09:09:41.873535: step: 1080/530, loss: 0.0033892544452100992
2023-01-24 09:09:42.968771: step: 1084/530, loss: 0.014805257320404053
2023-01-24 09:09:44.068813: step: 1088/530, loss: 0.003605550853535533
2023-01-24 09:09:45.163734: step: 1092/530, loss: 0.001872859662398696
2023-01-24 09:09:46.258257: step: 1096/530, loss: 0.01707622967660427
2023-01-24 09:09:47.362455: step: 1100/530, loss: 0.016445960849523544
2023-01-24 09:09:48.434178: step: 1104/530, loss: 0.002510062651708722
2023-01-24 09:09:49.536668: step: 1108/530, loss: 0.006677572149783373
2023-01-24 09:09:50.606642: step: 1112/530, loss: 0.006370050832629204
2023-01-24 09:09:51.739155: step: 1116/530, loss: 0.0012825154699385166
2023-01-24 09:09:52.830482: step: 1120/530, loss: 0.003444019006565213
2023-01-24 09:09:53.918913: step: 1124/530, loss: 0.025100549682974815
2023-01-24 09:09:55.010131: step: 1128/530, loss: 0.0029362936038523912
2023-01-24 09:09:56.101839: step: 1132/530, loss: 0.0027295027393847704
2023-01-24 09:09:57.186655: step: 1136/530, loss: 0.00018789245223160833
2023-01-24 09:09:58.281165: step: 1140/530, loss: 0.0003588128893170506
2023-01-24 09:09:59.341503: step: 1144/530, loss: 0.005856632255017757
2023-01-24 09:10:00.440497: step: 1148/530, loss: 0.020307840779423714
2023-01-24 09:10:01.544983: step: 1152/530, loss: 0.00271012750454247
2023-01-24 09:10:02.641940: step: 1156/530, loss: 0.010237624868750572
2023-01-24 09:10:03.730278: step: 1160/530, loss: 0.005984066519886255
2023-01-24 09:10:04.828852: step: 1164/530, loss: 0.004605032969266176
2023-01-24 09:10:05.892893: step: 1168/530, loss: 0.00023817337932996452
2023-01-24 09:10:07.007093: step: 1172/530, loss: 0.008438789285719395
2023-01-24 09:10:08.110290: step: 1176/530, loss: 0.0009418681729584932
2023-01-24 09:10:09.211552: step: 1180/530, loss: 0.00288075627759099
2023-01-24 09:10:10.284609: step: 1184/530, loss: 0.0006417831173166633
2023-01-24 09:10:11.389992: step: 1188/530, loss: 0.019675668329000473
2023-01-24 09:10:12.494260: step: 1192/530, loss: 0.0006893801037222147
2023-01-24 09:10:13.594403: step: 1196/530, loss: 0.00027176938601769507
2023-01-24 09:10:14.696296: step: 1200/530, loss: 0.0002283220674144104
2023-01-24 09:10:15.796293: step: 1204/530, loss: 0.0033687877003103495
2023-01-24 09:10:16.894591: step: 1208/530, loss: 0.0009588535176590085
2023-01-24 09:10:17.994108: step: 1212/530, loss: 0.007998911663889885
2023-01-24 09:10:19.066752: step: 1216/530, loss: 0.004501916468143463
2023-01-24 09:10:20.165028: step: 1220/530, loss: 0.0006718040094710886
2023-01-24 09:10:21.246786: step: 1224/530, loss: 0.04154327139258385
2023-01-24 09:10:22.340957: step: 1228/530, loss: 0.0036498745903372765
2023-01-24 09:10:23.420695: step: 1232/530, loss: 0.0016898217145353556
2023-01-24 09:10:24.502890: step: 1236/530, loss: 0.0019241824047639966
2023-01-24 09:10:25.594349: step: 1240/530, loss: 0.0027863839641213417
2023-01-24 09:10:26.684512: step: 1244/530, loss: 0.0050810822285711765
2023-01-24 09:10:27.809114: step: 1248/530, loss: 0.0037873501423746347
2023-01-24 09:10:28.913865: step: 1252/530, loss: 0.0018542238976806402
2023-01-24 09:10:29.999411: step: 1256/530, loss: 0.006123093888163567
2023-01-24 09:10:31.112454: step: 1260/530, loss: 0.002410774352028966
2023-01-24 09:10:32.207972: step: 1264/530, loss: 0.0034158991184085608
2023-01-24 09:10:33.300984: step: 1268/530, loss: 0.0017858152277767658
2023-01-24 09:10:34.406826: step: 1272/530, loss: 0.0061688050627708435
2023-01-24 09:10:35.489390: step: 1276/530, loss: 0.00449812738224864
2023-01-24 09:10:36.600428: step: 1280/530, loss: 0.0034192863386124372
2023-01-24 09:10:37.689582: step: 1284/530, loss: 0.0036674761213362217
2023-01-24 09:10:38.788831: step: 1288/530, loss: 0.011822589673101902
2023-01-24 09:10:39.907857: step: 1292/530, loss: 0.016700327396392822
2023-01-24 09:10:40.973753: step: 1296/530, loss: 0.0001120849046856165
2023-01-24 09:10:42.114289: step: 1300/530, loss: 0.005160850007086992
2023-01-24 09:10:43.205082: step: 1304/530, loss: 0.0035220228601247072
2023-01-24 09:10:44.286589: step: 1308/530, loss: 0.009390189312398434
2023-01-24 09:10:45.366076: step: 1312/530, loss: 0.001900652889162302
2023-01-24 09:10:46.481627: step: 1316/530, loss: 0.005975495558232069
2023-01-24 09:10:47.561944: step: 1320/530, loss: 0.00012547499500215054
2023-01-24 09:10:48.657543: step: 1324/530, loss: 0.007042139768600464
2023-01-24 09:10:49.754981: step: 1328/530, loss: 0.013127412647008896
2023-01-24 09:10:50.849920: step: 1332/530, loss: 0.0012310559395700693
2023-01-24 09:10:51.931819: step: 1336/530, loss: 0.00017637229757383466
2023-01-24 09:10:53.023449: step: 1340/530, loss: 0.0002910773328039795
2023-01-24 09:10:54.125244: step: 1344/530, loss: 0.050613563507795334
2023-01-24 09:10:55.200545: step: 1348/530, loss: 8.155624527717009e-05
2023-01-24 09:10:56.291512: step: 1352/530, loss: 0.003610956249758601
2023-01-24 09:10:57.389055: step: 1356/530, loss: 0.011948911473155022
2023-01-24 09:10:58.485578: step: 1360/530, loss: 0.006423926446586847
2023-01-24 09:10:59.583301: step: 1364/530, loss: 0.004793121479451656
2023-01-24 09:11:00.699665: step: 1368/530, loss: 0.027611060068011284
2023-01-24 09:11:01.795968: step: 1372/530, loss: 0.0010081022046506405
2023-01-24 09:11:02.900024: step: 1376/530, loss: 0.007629277650266886
2023-01-24 09:11:03.993200: step: 1380/530, loss: 4.365411768958438e-06
2023-01-24 09:11:05.091143: step: 1384/530, loss: 0.002638371894136071
2023-01-24 09:11:06.171013: step: 1388/530, loss: 0.015869446098804474
2023-01-24 09:11:07.286921: step: 1392/530, loss: 0.00021729881700593978
2023-01-24 09:11:08.385887: step: 1396/530, loss: 0.0028890392277389765
2023-01-24 09:11:09.466683: step: 1400/530, loss: 0.0009449466015212238
2023-01-24 09:11:10.571449: step: 1404/530, loss: 0.000890866038389504
2023-01-24 09:11:11.661426: step: 1408/530, loss: 0.02000340074300766
2023-01-24 09:11:12.775365: step: 1412/530, loss: 0.017198355868458748
2023-01-24 09:11:13.875366: step: 1416/530, loss: 0.0026251724921166897
2023-01-24 09:11:14.964160: step: 1420/530, loss: 0.011111374013125896
2023-01-24 09:11:16.037544: step: 1424/530, loss: 0.0008446262800134718
2023-01-24 09:11:17.150176: step: 1428/530, loss: 0.0004870123811997473
2023-01-24 09:11:18.253605: step: 1432/530, loss: 0.008600347675383091
2023-01-24 09:11:19.340430: step: 1436/530, loss: 0.002035481622442603
2023-01-24 09:11:20.449905: step: 1440/530, loss: 0.007148706819862127
2023-01-24 09:11:21.549579: step: 1444/530, loss: 0.005883886478841305
2023-01-24 09:11:22.646929: step: 1448/530, loss: 0.0025332090444862843
2023-01-24 09:11:23.715543: step: 1452/530, loss: 0.003139760810881853
2023-01-24 09:11:24.797771: step: 1456/530, loss: 0.00416307058185339
2023-01-24 09:11:25.887042: step: 1460/530, loss: 0.005314046982675791
2023-01-24 09:11:26.978973: step: 1464/530, loss: 0.008616367354989052
2023-01-24 09:11:28.059358: step: 1468/530, loss: 0.005100147798657417
2023-01-24 09:11:29.145975: step: 1472/530, loss: 0.0039847660809755325
2023-01-24 09:11:30.245649: step: 1476/530, loss: 0.0003103814960923046
2023-01-24 09:11:31.309675: step: 1480/530, loss: 0.00010832703992491588
2023-01-24 09:11:32.410534: step: 1484/530, loss: 0.019363101571798325
2023-01-24 09:11:33.485284: step: 1488/530, loss: 0.0038264915347099304
2023-01-24 09:11:34.558481: step: 1492/530, loss: 0.005332478322088718
2023-01-24 09:11:35.628847: step: 1496/530, loss: 0.0026007560081779957
2023-01-24 09:11:36.718609: step: 1500/530, loss: 0.006084011867642403
2023-01-24 09:11:37.808483: step: 1504/530, loss: 0.018632173538208008
2023-01-24 09:11:38.934019: step: 1508/530, loss: 0.0025714419316500425
2023-01-24 09:11:40.027538: step: 1512/530, loss: 0.0012076179264113307
2023-01-24 09:11:41.099113: step: 1516/530, loss: 0.0006937332800589502
2023-01-24 09:11:42.191675: step: 1520/530, loss: 0.00013510914868675172
2023-01-24 09:11:43.289481: step: 1524/530, loss: 0.019041750580072403
2023-01-24 09:11:44.378393: step: 1528/530, loss: 0.01660768687725067
2023-01-24 09:11:45.461872: step: 1532/530, loss: 0.0
2023-01-24 09:11:46.555946: step: 1536/530, loss: 0.00801519863307476
2023-01-24 09:11:47.673028: step: 1540/530, loss: 0.0038964995183050632
2023-01-24 09:11:48.757467: step: 1544/530, loss: 0.011827089823782444
2023-01-24 09:11:49.834870: step: 1548/530, loss: 0.0007869135588407516
2023-01-24 09:11:50.932128: step: 1552/530, loss: 0.010387184098362923
2023-01-24 09:11:52.020220: step: 1556/530, loss: 0.021088551729917526
2023-01-24 09:11:53.122410: step: 1560/530, loss: 0.0002866918803192675
2023-01-24 09:11:54.206883: step: 1564/530, loss: 0.004804663360118866
2023-01-24 09:11:55.299701: step: 1568/530, loss: 0.0076960292644798756
2023-01-24 09:11:56.383922: step: 1572/530, loss: 0.00040203926619142294
2023-01-24 09:11:57.485853: step: 1576/530, loss: 0.002767186611890793
2023-01-24 09:11:58.582543: step: 1580/530, loss: 0.0070724464021623135
2023-01-24 09:11:59.674860: step: 1584/530, loss: 0.006301302928477526
2023-01-24 09:12:00.758726: step: 1588/530, loss: 0.0021566362120211124
2023-01-24 09:12:01.860771: step: 1592/530, loss: 0.0001665118761593476
2023-01-24 09:12:02.980562: step: 1596/530, loss: 0.00469922972843051
2023-01-24 09:12:04.082563: step: 1600/530, loss: 0.01255431491881609
2023-01-24 09:12:05.170125: step: 1604/530, loss: 0.008955096825957298
2023-01-24 09:12:06.249310: step: 1608/530, loss: 0.0024435240775346756
2023-01-24 09:12:07.329372: step: 1612/530, loss: 0.0035248163621872663
2023-01-24 09:12:08.402074: step: 1616/530, loss: 0.0060799927450716496
2023-01-24 09:12:09.511701: step: 1620/530, loss: 0.0015154475113376975
2023-01-24 09:12:10.581121: step: 1624/530, loss: 0.002236857544630766
2023-01-24 09:12:11.689873: step: 1628/530, loss: 0.003611978143453598
2023-01-24 09:12:12.820254: step: 1632/530, loss: 0.004215634427964687
2023-01-24 09:12:13.922329: step: 1636/530, loss: 0.0055053094401955605
2023-01-24 09:12:15.029890: step: 1640/530, loss: 0.003384184557944536
2023-01-24 09:12:16.122750: step: 1644/530, loss: 0.007361925207078457
2023-01-24 09:12:17.195961: step: 1648/530, loss: 0.006534917745739222
2023-01-24 09:12:18.270260: step: 1652/530, loss: 0.030968040227890015
2023-01-24 09:12:19.374824: step: 1656/530, loss: 0.003852076129987836
2023-01-24 09:12:20.457010: step: 1660/530, loss: 0.002589681651443243
2023-01-24 09:12:21.553064: step: 1664/530, loss: 0.0044108061119914055
2023-01-24 09:12:22.645065: step: 1668/530, loss: 0.037874381989240646
2023-01-24 09:12:23.739296: step: 1672/530, loss: 0.005340332165360451
2023-01-24 09:12:24.822870: step: 1676/530, loss: 0.001252803485840559
2023-01-24 09:12:25.896327: step: 1680/530, loss: 0.0023055358324199915
2023-01-24 09:12:26.975427: step: 1684/530, loss: 0.005429337732493877
2023-01-24 09:12:28.083774: step: 1688/530, loss: 0.001402071793563664
2023-01-24 09:12:29.175438: step: 1692/530, loss: 0.003628536593168974
2023-01-24 09:12:30.260019: step: 1696/530, loss: 0.0034396806731820107
2023-01-24 09:12:31.345184: step: 1700/530, loss: 0.012472940608859062
2023-01-24 09:12:32.424848: step: 1704/530, loss: 0.017810627818107605
2023-01-24 09:12:33.511772: step: 1708/530, loss: 0.00910043716430664
2023-01-24 09:12:34.573459: step: 1712/530, loss: 0.012113492004573345
2023-01-24 09:12:35.650216: step: 1716/530, loss: 0.027594799175858498
2023-01-24 09:12:36.733998: step: 1720/530, loss: 0.007864712737500668
2023-01-24 09:12:37.820007: step: 1724/530, loss: 0.010359127074480057
2023-01-24 09:12:38.910135: step: 1728/530, loss: 0.004951147828251123
2023-01-24 09:12:39.995066: step: 1732/530, loss: 0.010661778971552849
2023-01-24 09:12:41.102492: step: 1736/530, loss: 0.04660448431968689
2023-01-24 09:12:42.218032: step: 1740/530, loss: 0.023057512938976288
2023-01-24 09:12:43.321797: step: 1744/530, loss: 0.0026987886521965265
2023-01-24 09:12:44.439964: step: 1748/530, loss: 0.008165402337908745
2023-01-24 09:12:45.561017: step: 1752/530, loss: 0.008982207626104355
2023-01-24 09:12:46.650972: step: 1756/530, loss: 0.002726080594584346
2023-01-24 09:12:47.748719: step: 1760/530, loss: 0.003132391953840852
2023-01-24 09:12:48.829171: step: 1764/530, loss: 0.0003318925737403333
2023-01-24 09:12:49.911201: step: 1768/530, loss: 0.0010938697960227728
2023-01-24 09:12:50.993876: step: 1772/530, loss: 0.016663808375597
2023-01-24 09:12:52.093589: step: 1776/530, loss: 0.007776834536343813
2023-01-24 09:12:53.162490: step: 1780/530, loss: 0.001584175624884665
2023-01-24 09:12:54.243403: step: 1784/530, loss: 0.00040965297375805676
2023-01-24 09:12:55.311805: step: 1788/530, loss: 0.009385798126459122
2023-01-24 09:12:56.402010: step: 1792/530, loss: 0.0006889718351885676
2023-01-24 09:12:57.496014: step: 1796/530, loss: 0.018294749781489372
2023-01-24 09:12:58.581133: step: 1800/530, loss: 0.0026774355210363865
2023-01-24 09:12:59.639661: step: 1804/530, loss: 0.015958787873387337
2023-01-24 09:13:00.740637: step: 1808/530, loss: 0.0016962961526587605
2023-01-24 09:13:01.844654: step: 1812/530, loss: 0.005244984291493893
2023-01-24 09:13:02.940380: step: 1816/530, loss: 0.0008689347305335104
2023-01-24 09:13:04.039986: step: 1820/530, loss: 0.003296517301350832
2023-01-24 09:13:05.123379: step: 1824/530, loss: 0.0016393533442169428
2023-01-24 09:13:06.213372: step: 1828/530, loss: 0.0016171283787116408
2023-01-24 09:13:07.298739: step: 1832/530, loss: 0.01213243417441845
2023-01-24 09:13:08.366420: step: 1836/530, loss: 5.0799677410395816e-05
2023-01-24 09:13:09.447355: step: 1840/530, loss: 0.00038332241820171475
2023-01-24 09:13:10.521962: step: 1844/530, loss: 0.008795974776148796
2023-01-24 09:13:11.595375: step: 1848/530, loss: 0.0019124295795336366
2023-01-24 09:13:12.716491: step: 1852/530, loss: 0.006140131037682295
2023-01-24 09:13:13.801930: step: 1856/530, loss: 0.002668975852429867
2023-01-24 09:13:14.891402: step: 1860/530, loss: 0.007928646169602871
2023-01-24 09:13:16.006434: step: 1864/530, loss: 0.005748241674154997
2023-01-24 09:13:17.100951: step: 1868/530, loss: 0.00027306514675728977
2023-01-24 09:13:18.187129: step: 1872/530, loss: 0.001409861957654357
2023-01-24 09:13:19.292457: step: 1876/530, loss: 0.008886498399078846
2023-01-24 09:13:20.374452: step: 1880/530, loss: 0.0022387877106666565
2023-01-24 09:13:21.453791: step: 1884/530, loss: 0.0016016238369047642
2023-01-24 09:13:22.554172: step: 1888/530, loss: 0.001985857030376792
2023-01-24 09:13:23.666378: step: 1892/530, loss: 0.0008222759934142232
2023-01-24 09:13:24.746672: step: 1896/530, loss: 0.002720050048083067
2023-01-24 09:13:25.843014: step: 1900/530, loss: 0.012504915706813335
2023-01-24 09:13:26.930480: step: 1904/530, loss: 0.004875602200627327
2023-01-24 09:13:28.006786: step: 1908/530, loss: 0.0031856712885200977
2023-01-24 09:13:29.098431: step: 1912/530, loss: 0.002739051589742303
2023-01-24 09:13:30.175678: step: 1916/530, loss: 0.022072207182645798
2023-01-24 09:13:31.259706: step: 1920/530, loss: 0.004854911006987095
2023-01-24 09:13:32.331343: step: 1924/530, loss: 0.0002982405130751431
2023-01-24 09:13:33.402208: step: 1928/530, loss: 0.0053671193309128284
2023-01-24 09:13:34.491154: step: 1932/530, loss: 0.007114367559552193
2023-01-24 09:13:35.563146: step: 1936/530, loss: 0.0012457175180315971
2023-01-24 09:13:36.641173: step: 1940/530, loss: 0.006959805730730295
2023-01-24 09:13:37.732873: step: 1944/530, loss: 0.001081329770386219
2023-01-24 09:13:38.845187: step: 1948/530, loss: 0.0066568139009177685
2023-01-24 09:13:39.957579: step: 1952/530, loss: 0.01788986846804619
2023-01-24 09:13:41.029297: step: 1956/530, loss: 0.007602077443152666
2023-01-24 09:13:42.126755: step: 1960/530, loss: 0.011420664377510548
2023-01-24 09:13:43.198796: step: 1964/530, loss: 0.003076155437156558
2023-01-24 09:13:44.281485: step: 1968/530, loss: 0.0017775805899873376
2023-01-24 09:13:45.366858: step: 1972/530, loss: 0.0011716056615114212
2023-01-24 09:13:46.427451: step: 1976/530, loss: 0.0007368326769210398
2023-01-24 09:13:47.517670: step: 1980/530, loss: 0.013338204473257065
2023-01-24 09:13:48.594984: step: 1984/530, loss: 0.00042962783481925726
2023-01-24 09:13:49.677369: step: 1988/530, loss: 0.00039271271089091897
2023-01-24 09:13:50.766721: step: 1992/530, loss: 0.0011719658505171537
2023-01-24 09:13:51.856071: step: 1996/530, loss: 0.003937747795134783
2023-01-24 09:13:52.958806: step: 2000/530, loss: 0.004414998460561037
2023-01-24 09:13:54.037603: step: 2004/530, loss: 0.00075063097756356
2023-01-24 09:13:55.129011: step: 2008/530, loss: 0.007871423847973347
2023-01-24 09:13:56.248251: step: 2012/530, loss: 0.01167930755764246
2023-01-24 09:13:57.336899: step: 2016/530, loss: 0.009887666441500187
2023-01-24 09:13:58.428143: step: 2020/530, loss: 0.0049647558480501175
2023-01-24 09:13:59.522383: step: 2024/530, loss: 0.0007859620964154601
2023-01-24 09:14:00.609591: step: 2028/530, loss: 0.014205127954483032
2023-01-24 09:14:01.685710: step: 2032/530, loss: 0.004115665331482887
2023-01-24 09:14:02.780582: step: 2036/530, loss: 0.0032271044328808784
2023-01-24 09:14:03.859454: step: 2040/530, loss: 0.004548276774585247
2023-01-24 09:14:04.952568: step: 2044/530, loss: 0.004282260313630104
2023-01-24 09:14:06.034515: step: 2048/530, loss: 0.0037071609403938055
2023-01-24 09:14:07.107581: step: 2052/530, loss: 0.0003640760842245072
2023-01-24 09:14:08.207817: step: 2056/530, loss: 0.0005618956638500094
2023-01-24 09:14:09.329002: step: 2060/530, loss: 0.0018802088452503085
2023-01-24 09:14:10.412718: step: 2064/530, loss: 0.0008161062141880393
2023-01-24 09:14:11.475157: step: 2068/530, loss: 0.0023067700676620007
2023-01-24 09:14:12.552074: step: 2072/530, loss: 0.005230557173490524
2023-01-24 09:14:13.627912: step: 2076/530, loss: 0.009671683423221111
2023-01-24 09:14:14.721996: step: 2080/530, loss: 0.00613103061914444
2023-01-24 09:14:15.800720: step: 2084/530, loss: 0.011765551753342152
2023-01-24 09:14:16.905688: step: 2088/530, loss: 0.0006902336026541889
2023-01-24 09:14:17.980888: step: 2092/530, loss: 0.009412631392478943
2023-01-24 09:14:19.073517: step: 2096/530, loss: 0.0038881096988916397
2023-01-24 09:14:20.193739: step: 2100/530, loss: 0.005062987562268972
2023-01-24 09:14:21.287104: step: 2104/530, loss: 0.005288320127874613
2023-01-24 09:14:22.381060: step: 2108/530, loss: 0.001456351368688047
2023-01-24 09:14:23.464038: step: 2112/530, loss: 0.006281753536313772
2023-01-24 09:14:24.541520: step: 2116/530, loss: 0.03574305772781372
2023-01-24 09:14:25.616142: step: 2120/530, loss: 0.001871609129011631
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34436280884764153, 'r': 0.34436280884764153, 'f1': 0.34436280884764153}, 'combined': 0.25374101704563057, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34519519797185405, 'r': 0.2762244462504747, 'f1': 0.3068823243508021}, 'combined': 0.19059007512312973, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3872404401154401, 'r': 0.33066071736612535, 'f1': 0.35672097861197144}, 'combined': 0.26284703687197897, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3377831681569112, 'r': 0.26468582247868633, 'f1': 0.29680005800380116}, 'combined': 0.18432845707604495, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3769875660156958, 'r': 0.32691331626029024, 'f1': 0.3501693448560426}, 'combined': 0.2580195172623472, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3515453957986952, 'r': 0.2724216541974094, 'f1': 0.30696678053612425}, 'combined': 0.19064252685927718, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36538461538461536, 'r': 0.41304347826086957, 'f1': 0.3877551020408163}, 'combined': 0.19387755102040816, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 09:16:51.933918: step: 4/530, loss: 0.0034415009431540966
2023-01-24 09:16:53.034773: step: 8/530, loss: 0.0018855099333450198
2023-01-24 09:16:54.114470: step: 12/530, loss: 0.0025820701848715544
2023-01-24 09:16:55.205607: step: 16/530, loss: 0.005389011465013027
2023-01-24 09:16:56.273521: step: 20/530, loss: 0.0017314772121608257
2023-01-24 09:16:57.360917: step: 24/530, loss: 0.001437419094145298
2023-01-24 09:16:58.418192: step: 28/530, loss: 0.004753878340125084
2023-01-24 09:16:59.505219: step: 32/530, loss: 0.0023134828079491854
2023-01-24 09:17:00.583006: step: 36/530, loss: 0.0013290735660120845
2023-01-24 09:17:01.669530: step: 40/530, loss: 0.0027263276278972626
2023-01-24 09:17:02.760199: step: 44/530, loss: 0.009244153276085854
2023-01-24 09:17:03.847297: step: 48/530, loss: 0.0011075136717408895
2023-01-24 09:17:04.921569: step: 52/530, loss: 0.0011879028752446175
2023-01-24 09:17:05.993631: step: 56/530, loss: 0.011863050051033497
2023-01-24 09:17:07.066491: step: 60/530, loss: 0.0016303241718560457
2023-01-24 09:17:08.151700: step: 64/530, loss: 0.002244720235466957
2023-01-24 09:17:09.236131: step: 68/530, loss: 0.00011352369619999081
2023-01-24 09:17:10.309049: step: 72/530, loss: 0.00046751886839047074
2023-01-24 09:17:11.384914: step: 76/530, loss: 0.004899282474070787
2023-01-24 09:17:12.447990: step: 80/530, loss: 0.0033934323582798243
2023-01-24 09:17:13.553366: step: 84/530, loss: 0.005008421838283539
2023-01-24 09:17:14.615254: step: 88/530, loss: 0.0002878271334338933
2023-01-24 09:17:15.705885: step: 92/530, loss: 0.00558737525716424
2023-01-24 09:17:16.804133: step: 96/530, loss: 0.0093363206833601
2023-01-24 09:17:17.909772: step: 100/530, loss: 0.0032868129201233387
2023-01-24 09:17:18.966134: step: 104/530, loss: 0.004269672092050314
2023-01-24 09:17:20.048447: step: 108/530, loss: 0.012570032849907875
2023-01-24 09:17:21.132599: step: 112/530, loss: 0.0158297847956419
2023-01-24 09:17:22.233211: step: 116/530, loss: 0.0010067452676594257
2023-01-24 09:17:23.311193: step: 120/530, loss: 0.0024046064354479313
2023-01-24 09:17:24.387088: step: 124/530, loss: 0.00044459145283326507
2023-01-24 09:17:25.471550: step: 128/530, loss: 0.010600504465401173
2023-01-24 09:17:26.559329: step: 132/530, loss: 0.00039859768003225327
2023-01-24 09:17:27.661627: step: 136/530, loss: 0.003415749641135335
2023-01-24 09:17:28.758405: step: 140/530, loss: 0.028947310522198677
2023-01-24 09:17:29.824583: step: 144/530, loss: 0.0018326163990423083
2023-01-24 09:17:30.918392: step: 148/530, loss: 0.004080368671566248
2023-01-24 09:17:31.992259: step: 152/530, loss: 0.0005264051724225283
2023-01-24 09:17:33.068452: step: 156/530, loss: 0.0029352109413594007
2023-01-24 09:17:34.161559: step: 160/530, loss: 0.008986947126686573
2023-01-24 09:17:35.241273: step: 164/530, loss: 0.0053579979576170444
2023-01-24 09:17:36.351290: step: 168/530, loss: 0.0034974587615579367
2023-01-24 09:17:37.442452: step: 172/530, loss: 0.009433495812118053
2023-01-24 09:17:38.518180: step: 176/530, loss: 0.0007090445724315941
2023-01-24 09:17:39.609454: step: 180/530, loss: 0.00040775485103949904
2023-01-24 09:17:40.688014: step: 184/530, loss: 0.0025965918321162462
2023-01-24 09:17:41.807176: step: 188/530, loss: 0.0002931267081294209
2023-01-24 09:17:42.900486: step: 192/530, loss: 0.005676877684891224
2023-01-24 09:17:44.003642: step: 196/530, loss: 0.010167280212044716
2023-01-24 09:17:45.091082: step: 200/530, loss: 0.0068588582798838615
2023-01-24 09:17:46.164934: step: 204/530, loss: 0.0009279776131734252
2023-01-24 09:17:47.244112: step: 208/530, loss: 0.003876051167026162
2023-01-24 09:17:48.319389: step: 212/530, loss: 0.0012742475373670459
2023-01-24 09:17:49.418633: step: 216/530, loss: 0.007744040340185165
2023-01-24 09:17:50.496249: step: 220/530, loss: 0.006425646599382162
2023-01-24 09:17:51.589863: step: 224/530, loss: 0.00498602818697691
2023-01-24 09:17:52.685359: step: 228/530, loss: 0.0026386925019323826
2023-01-24 09:17:53.789479: step: 232/530, loss: 0.007540892343968153
2023-01-24 09:17:54.863020: step: 236/530, loss: 0.011274152435362339
2023-01-24 09:17:55.931663: step: 240/530, loss: 0.028672195971012115
2023-01-24 09:17:57.015483: step: 244/530, loss: 0.01065274141728878
2023-01-24 09:17:58.097868: step: 248/530, loss: 0.002114612376317382
2023-01-24 09:17:59.187137: step: 252/530, loss: 0.0017169505590572953
2023-01-24 09:18:00.272894: step: 256/530, loss: 0.006198923569172621
2023-01-24 09:18:01.341648: step: 260/530, loss: 0.0001791394461179152
2023-01-24 09:18:02.398537: step: 264/530, loss: 0.011137833818793297
2023-01-24 09:18:03.483438: step: 268/530, loss: 0.0015613245777785778
2023-01-24 09:18:04.554175: step: 272/530, loss: 0.0019488499965518713
2023-01-24 09:18:05.648010: step: 276/530, loss: 0.0012817097594961524
2023-01-24 09:18:06.742153: step: 280/530, loss: 0.0018022364238277078
2023-01-24 09:18:07.822225: step: 284/530, loss: 0.0019409205997362733
2023-01-24 09:18:08.903240: step: 288/530, loss: 0.002587040653452277
2023-01-24 09:18:10.009523: step: 292/530, loss: 0.004167493898421526
2023-01-24 09:18:11.091891: step: 296/530, loss: 0.004530603066086769
2023-01-24 09:18:12.166452: step: 300/530, loss: 0.000620887556578964
2023-01-24 09:18:13.272537: step: 304/530, loss: 0.0154774384573102
2023-01-24 09:18:14.364888: step: 308/530, loss: 0.00944730918854475
2023-01-24 09:18:15.462846: step: 312/530, loss: 0.0012708025751635432
2023-01-24 09:18:16.567092: step: 316/530, loss: 0.008497222326695919
2023-01-24 09:18:17.633706: step: 320/530, loss: 0.014150462113320827
2023-01-24 09:18:18.709563: step: 324/530, loss: 0.0027164421044290066
2023-01-24 09:18:19.786447: step: 328/530, loss: 0.008109225891530514
2023-01-24 09:18:20.867682: step: 332/530, loss: 0.0010222382843494415
2023-01-24 09:18:21.941128: step: 336/530, loss: 0.004857663996517658
2023-01-24 09:18:23.025944: step: 340/530, loss: 0.005858488846570253
2023-01-24 09:18:24.102695: step: 344/530, loss: 0.003807384055107832
2023-01-24 09:18:25.182552: step: 348/530, loss: 0.0032293195836246014
2023-01-24 09:18:26.256150: step: 352/530, loss: 0.003018673975020647
2023-01-24 09:18:27.335810: step: 356/530, loss: 0.029335839673876762
2023-01-24 09:18:28.422459: step: 360/530, loss: 0.01103054266422987
2023-01-24 09:18:29.493312: step: 364/530, loss: 0.0027374725323170424
2023-01-24 09:18:30.575721: step: 368/530, loss: 0.0012658733176067472
2023-01-24 09:18:31.659609: step: 372/530, loss: 0.004912860691547394
2023-01-24 09:18:32.740860: step: 376/530, loss: 0.002985097002238035
2023-01-24 09:18:33.831986: step: 380/530, loss: 0.005533963441848755
2023-01-24 09:18:34.929373: step: 384/530, loss: 0.0036693972069770098
2023-01-24 09:18:35.998300: step: 388/530, loss: 0.0030343160033226013
2023-01-24 09:18:37.070670: step: 392/530, loss: 0.0002340084611205384
2023-01-24 09:18:38.172245: step: 396/530, loss: 0.002366960048675537
2023-01-24 09:18:39.255924: step: 400/530, loss: 0.0045024738647043705
2023-01-24 09:18:40.327498: step: 404/530, loss: 0.0006814567022956908
2023-01-24 09:18:41.415615: step: 408/530, loss: 0.001246783067472279
2023-01-24 09:18:42.504662: step: 412/530, loss: 0.0031921551562845707
2023-01-24 09:18:43.597933: step: 416/530, loss: 0.0038193792570382357
2023-01-24 09:18:44.697493: step: 420/530, loss: 0.0016046573873609304
2023-01-24 09:18:45.794664: step: 424/530, loss: 0.004700668156147003
2023-01-24 09:18:46.899135: step: 428/530, loss: 0.008702094666659832
2023-01-24 09:18:47.989318: step: 432/530, loss: 0.01003299094736576
2023-01-24 09:18:49.086554: step: 436/530, loss: 0.018044637516140938
2023-01-24 09:18:50.181797: step: 440/530, loss: 9.396607492817566e-05
2023-01-24 09:18:51.275124: step: 444/530, loss: 0.012194762006402016
2023-01-24 09:18:52.347807: step: 448/530, loss: 0.00013641318946611136
2023-01-24 09:18:53.453676: step: 452/530, loss: 0.004846340976655483
2023-01-24 09:18:54.537187: step: 456/530, loss: 9.918484283844009e-05
2023-01-24 09:18:55.615429: step: 460/530, loss: 0.00012301348033361137
2023-01-24 09:18:56.702317: step: 464/530, loss: 0.0019925881642848253
2023-01-24 09:18:57.776335: step: 468/530, loss: 0.004436699207872152
2023-01-24 09:18:58.848754: step: 472/530, loss: 0.0027862873394042253
2023-01-24 09:18:59.942139: step: 476/530, loss: 0.008916843682527542
2023-01-24 09:19:01.026408: step: 480/530, loss: 0.002100105630233884
2023-01-24 09:19:02.120699: step: 484/530, loss: 0.003695284016430378
2023-01-24 09:19:03.207751: step: 488/530, loss: 0.00017014855984598398
2023-01-24 09:19:04.314360: step: 492/530, loss: 0.0018134398851543665
2023-01-24 09:19:05.416087: step: 496/530, loss: 0.0025519183836877346
2023-01-24 09:19:06.494182: step: 500/530, loss: 0.00042375936754979193
2023-01-24 09:19:07.610477: step: 504/530, loss: 0.01567401923239231
2023-01-24 09:19:08.691832: step: 508/530, loss: 0.0005772035801783204
2023-01-24 09:19:09.788085: step: 512/530, loss: 0.0016135585028678179
2023-01-24 09:19:10.869275: step: 516/530, loss: 0.002485134871676564
2023-01-24 09:19:11.966827: step: 520/530, loss: 0.012817529030144215
2023-01-24 09:19:13.053453: step: 524/530, loss: 0.004903607070446014
2023-01-24 09:19:14.144062: step: 528/530, loss: 0.007648189552128315
2023-01-24 09:19:15.257412: step: 532/530, loss: 0.003112268866971135
2023-01-24 09:19:16.376945: step: 536/530, loss: 0.017006365582346916
2023-01-24 09:19:17.459821: step: 540/530, loss: 0.00040519481990486383
2023-01-24 09:19:18.536550: step: 544/530, loss: 0.004090775735676289
2023-01-24 09:19:19.629361: step: 548/530, loss: 0.0016456767916679382
2023-01-24 09:19:20.697902: step: 552/530, loss: 0.01644858345389366
2023-01-24 09:19:21.782387: step: 556/530, loss: 0.002307191025465727
2023-01-24 09:19:22.859336: step: 560/530, loss: 0.006284062750637531
2023-01-24 09:19:23.947530: step: 564/530, loss: 0.0027016112580895424
2023-01-24 09:19:25.033317: step: 568/530, loss: 0.005701027810573578
2023-01-24 09:19:26.134569: step: 572/530, loss: 0.00931558758020401
2023-01-24 09:19:27.217672: step: 576/530, loss: 0.0020256154239177704
2023-01-24 09:19:28.300318: step: 580/530, loss: 0.023163888603448868
2023-01-24 09:19:29.361710: step: 584/530, loss: 0.0002538264961913228
2023-01-24 09:19:30.448381: step: 588/530, loss: 0.008892915211617947
2023-01-24 09:19:31.526802: step: 592/530, loss: 0.007267594803124666
2023-01-24 09:19:32.604953: step: 596/530, loss: 0.000707216328009963
2023-01-24 09:19:33.690018: step: 600/530, loss: 0.0036801721435040236
2023-01-24 09:19:34.778751: step: 604/530, loss: 0.004926749505102634
2023-01-24 09:19:35.884355: step: 608/530, loss: 0.0033411975018680096
2023-01-24 09:19:36.963276: step: 612/530, loss: 0.0029005182441323996
2023-01-24 09:19:38.048218: step: 616/530, loss: 0.0014471672475337982
2023-01-24 09:19:39.132395: step: 620/530, loss: 0.00519148726016283
2023-01-24 09:19:40.229780: step: 624/530, loss: 0.004915914963930845
2023-01-24 09:19:41.347342: step: 628/530, loss: 0.0110006770119071
2023-01-24 09:19:42.430118: step: 632/530, loss: 0.0012852144427597523
2023-01-24 09:19:43.504958: step: 636/530, loss: 0.00438058702275157
2023-01-24 09:19:44.573434: step: 640/530, loss: 0.00918579287827015
2023-01-24 09:19:45.674094: step: 644/530, loss: 0.0017917025834321976
2023-01-24 09:19:46.772303: step: 648/530, loss: 0.001813714043237269
2023-01-24 09:19:47.854795: step: 652/530, loss: 0.0052543762139976025
2023-01-24 09:19:48.953081: step: 656/530, loss: 0.0009003058657981455
2023-01-24 09:19:50.039069: step: 660/530, loss: 0.004665522836148739
2023-01-24 09:19:51.126325: step: 664/530, loss: 0.0020169091876596212
2023-01-24 09:19:52.209562: step: 668/530, loss: 0.0054077086970210075
2023-01-24 09:19:53.288865: step: 672/530, loss: 0.0017569754272699356
2023-01-24 09:19:54.372179: step: 676/530, loss: 0.0008131520007736981
2023-01-24 09:19:55.450805: step: 680/530, loss: 0.00010416947770863771
2023-01-24 09:19:56.535719: step: 684/530, loss: 0.0018142632907256484
2023-01-24 09:19:57.647976: step: 688/530, loss: 0.006656542420387268
2023-01-24 09:19:58.748992: step: 692/530, loss: 0.0005797837511636317
2023-01-24 09:19:59.831994: step: 696/530, loss: 0.0007885689847171307
2023-01-24 09:20:00.938473: step: 700/530, loss: 0.052023597061634064
2023-01-24 09:20:02.020160: step: 704/530, loss: 0.005453550722450018
2023-01-24 09:20:03.113796: step: 708/530, loss: 0.007839587517082691
2023-01-24 09:20:04.185652: step: 712/530, loss: 0.0009000131394714117
2023-01-24 09:20:05.252988: step: 716/530, loss: 0.00037429857184179127
2023-01-24 09:20:06.336929: step: 720/530, loss: 0.004768033046275377
2023-01-24 09:20:07.444546: step: 724/530, loss: 0.0070826830342411995
2023-01-24 09:20:08.536547: step: 728/530, loss: 0.0048217205330729485
2023-01-24 09:20:09.638368: step: 732/530, loss: 0.0013208432355895638
2023-01-24 09:20:10.721509: step: 736/530, loss: 0.00471006752923131
2023-01-24 09:20:11.833720: step: 740/530, loss: 0.0016549668507650495
2023-01-24 09:20:12.917804: step: 744/530, loss: 0.004077339079231024
2023-01-24 09:20:13.994730: step: 748/530, loss: 0.003988637588918209
2023-01-24 09:20:15.065024: step: 752/530, loss: 0.002860607346519828
2023-01-24 09:20:16.140673: step: 756/530, loss: 0.00011697473382810131
2023-01-24 09:20:17.229209: step: 760/530, loss: 0.0002914362703450024
2023-01-24 09:20:18.337044: step: 764/530, loss: 0.005991601850837469
2023-01-24 09:20:19.409508: step: 768/530, loss: 0.0004237417597323656
2023-01-24 09:20:20.478011: step: 772/530, loss: 0.0021470848005264997
2023-01-24 09:20:21.542290: step: 776/530, loss: 0.002884796354919672
2023-01-24 09:20:22.620031: step: 780/530, loss: 0.004891611635684967
2023-01-24 09:20:23.698776: step: 784/530, loss: 0.01020373497158289
2023-01-24 09:20:24.808667: step: 788/530, loss: 0.004425450228154659
2023-01-24 09:20:25.896288: step: 792/530, loss: 0.007049204781651497
2023-01-24 09:20:26.974952: step: 796/530, loss: 0.010170838795602322
2023-01-24 09:20:28.069419: step: 800/530, loss: 0.0035678057465702295
2023-01-24 09:20:29.168938: step: 804/530, loss: 0.010326921939849854
2023-01-24 09:20:30.238897: step: 808/530, loss: 0.04217381402850151
2023-01-24 09:20:31.325188: step: 812/530, loss: 0.0013110467698425055
2023-01-24 09:20:32.424475: step: 816/530, loss: 0.014697118662297726
2023-01-24 09:20:33.516901: step: 820/530, loss: 0.0015910804504528642
2023-01-24 09:20:34.605364: step: 824/530, loss: 0.006394257768988609
2023-01-24 09:20:35.709873: step: 828/530, loss: 0.004869935568422079
2023-01-24 09:20:36.782502: step: 832/530, loss: 0.01354996394366026
2023-01-24 09:20:37.878492: step: 836/530, loss: 0.01052496675401926
2023-01-24 09:20:38.959334: step: 840/530, loss: 0.003269155975431204
2023-01-24 09:20:40.057314: step: 844/530, loss: 0.018886715173721313
2023-01-24 09:20:41.159493: step: 848/530, loss: 0.00438551465049386
2023-01-24 09:20:42.277495: step: 852/530, loss: 0.006867893505841494
2023-01-24 09:20:43.366930: step: 856/530, loss: 0.001360465888865292
2023-01-24 09:20:44.459618: step: 860/530, loss: 0.007910734042525291
2023-01-24 09:20:45.552336: step: 864/530, loss: 7.721110159764066e-05
2023-01-24 09:20:46.651961: step: 868/530, loss: 0.0023887630086392164
2023-01-24 09:20:47.758193: step: 872/530, loss: 0.00022753450321033597
2023-01-24 09:20:48.860442: step: 876/530, loss: 0.006508971098810434
2023-01-24 09:20:49.947094: step: 880/530, loss: 0.0015781933907419443
2023-01-24 09:20:51.048268: step: 884/530, loss: 0.009550977498292923
2023-01-24 09:20:52.133658: step: 888/530, loss: 0.0021734812762588263
2023-01-24 09:20:53.215027: step: 892/530, loss: 0.006952111143618822
2023-01-24 09:20:54.307065: step: 896/530, loss: 0.0006070664385333657
2023-01-24 09:20:55.401315: step: 900/530, loss: 0.001960593508556485
2023-01-24 09:20:56.495957: step: 904/530, loss: 0.00942571833729744
2023-01-24 09:20:57.598186: step: 908/530, loss: 0.004294681828469038
2023-01-24 09:20:58.670698: step: 912/530, loss: 0.007583240978419781
2023-01-24 09:20:59.755972: step: 916/530, loss: 0.0031840302981436253
2023-01-24 09:21:00.852515: step: 920/530, loss: 0.0025073098950088024
2023-01-24 09:21:01.958595: step: 924/530, loss: 0.0033496415708214045
2023-01-24 09:21:03.070136: step: 928/530, loss: 0.004370107315480709
2023-01-24 09:21:04.177177: step: 932/530, loss: 0.000515086343511939
2023-01-24 09:21:05.306248: step: 936/530, loss: 0.010644691064953804
2023-01-24 09:21:06.388465: step: 940/530, loss: 0.0015098314033821225
2023-01-24 09:21:07.501234: step: 944/530, loss: 0.00036256806924939156
2023-01-24 09:21:08.602761: step: 948/530, loss: 0.005524048116058111
2023-01-24 09:21:09.688069: step: 952/530, loss: 0.0008494430803693831
2023-01-24 09:21:10.809380: step: 956/530, loss: 0.006233882158994675
2023-01-24 09:21:11.887444: step: 960/530, loss: 0.003864891128614545
2023-01-24 09:21:12.963040: step: 964/530, loss: 0.0045983027666807175
2023-01-24 09:21:14.045137: step: 968/530, loss: 0.0032973329070955515
2023-01-24 09:21:15.153487: step: 972/530, loss: 0.0009336351067759097
2023-01-24 09:21:16.265542: step: 976/530, loss: 0.002526262542232871
2023-01-24 09:21:17.337376: step: 980/530, loss: 0.006512057967483997
2023-01-24 09:21:18.449185: step: 984/530, loss: 7.263862789841369e-05
2023-01-24 09:21:19.543718: step: 988/530, loss: 0.004556652624160051
2023-01-24 09:21:20.622854: step: 992/530, loss: 0.003534437622874975
2023-01-24 09:21:21.744455: step: 996/530, loss: 0.004351919516921043
2023-01-24 09:21:22.814063: step: 1000/530, loss: 0.0018057613633573055
2023-01-24 09:21:23.879867: step: 1004/530, loss: 0.003542422316968441
2023-01-24 09:21:24.990744: step: 1008/530, loss: 0.0035890303552150726
2023-01-24 09:21:26.076384: step: 1012/530, loss: 0.005569561384618282
2023-01-24 09:21:27.171363: step: 1016/530, loss: 0.0074818190187215805
2023-01-24 09:21:28.234621: step: 1020/530, loss: 0.0006150158005766571
2023-01-24 09:21:29.357565: step: 1024/530, loss: 0.00553083885461092
2023-01-24 09:21:30.464830: step: 1028/530, loss: 0.00024989820667542517
2023-01-24 09:21:31.573477: step: 1032/530, loss: 0.00281052989885211
2023-01-24 09:21:32.679707: step: 1036/530, loss: 0.006160425953567028
2023-01-24 09:21:33.771967: step: 1040/530, loss: 0.006961078383028507
2023-01-24 09:21:34.858579: step: 1044/530, loss: 0.022290097549557686
2023-01-24 09:21:35.931569: step: 1048/530, loss: 0.0015631720889359713
2023-01-24 09:21:37.031364: step: 1052/530, loss: 0.00197742972522974
2023-01-24 09:21:38.120446: step: 1056/530, loss: 0.0014348529512062669
2023-01-24 09:21:39.217917: step: 1060/530, loss: 0.004474959336221218
2023-01-24 09:21:40.315382: step: 1064/530, loss: 0.00034423902980051935
2023-01-24 09:21:41.402688: step: 1068/530, loss: 0.0015322730178013444
2023-01-24 09:21:42.525747: step: 1072/530, loss: 0.002828197320923209
2023-01-24 09:21:43.609858: step: 1076/530, loss: 0.006610402371734381
2023-01-24 09:21:44.741473: step: 1080/530, loss: 0.0006098880548961461
2023-01-24 09:21:45.864860: step: 1084/530, loss: 0.0016893999418243766
2023-01-24 09:21:46.966662: step: 1088/530, loss: 0.015406097285449505
2023-01-24 09:21:48.042398: step: 1092/530, loss: 0.0007497449987567961
2023-01-24 09:21:49.111508: step: 1096/530, loss: 0.0034004985354840755
2023-01-24 09:21:50.192118: step: 1100/530, loss: 0.006882116198539734
2023-01-24 09:21:51.276360: step: 1104/530, loss: 0.00790882483124733
2023-01-24 09:21:52.393371: step: 1108/530, loss: 0.005721793510019779
2023-01-24 09:21:53.477404: step: 1112/530, loss: 0.011735101230442524
2023-01-24 09:21:54.569669: step: 1116/530, loss: 0.0008561141439713538
2023-01-24 09:21:55.670662: step: 1120/530, loss: 0.006097300909459591
2023-01-24 09:21:56.791429: step: 1124/530, loss: 0.006091817282140255
2023-01-24 09:21:57.884512: step: 1128/530, loss: 0.00031029951060190797
2023-01-24 09:21:58.999715: step: 1132/530, loss: 0.0028116947505623102
2023-01-24 09:22:00.116918: step: 1136/530, loss: 0.0028461655601859093
2023-01-24 09:22:01.213043: step: 1140/530, loss: 0.0017151185311377048
2023-01-24 09:22:02.290995: step: 1144/530, loss: 0.0021916173864156008
2023-01-24 09:22:03.375911: step: 1148/530, loss: 0.0028402898460626602
2023-01-24 09:22:04.458545: step: 1152/530, loss: 0.008344939909875393
2023-01-24 09:22:05.556455: step: 1156/530, loss: 0.0025396314449608326
2023-01-24 09:22:06.642437: step: 1160/530, loss: 0.0022760778665542603
2023-01-24 09:22:07.748324: step: 1164/530, loss: 0.0015138674061745405
2023-01-24 09:22:08.845734: step: 1168/530, loss: 0.0048512788489460945
2023-01-24 09:22:09.971549: step: 1172/530, loss: 0.0025135655887424946
2023-01-24 09:22:11.063790: step: 1176/530, loss: 0.0012192686554044485
2023-01-24 09:22:12.133555: step: 1180/530, loss: 0.003668656339868903
2023-01-24 09:22:13.222965: step: 1184/530, loss: 0.0010577113134786487
2023-01-24 09:22:14.308562: step: 1188/530, loss: 0.0037559799384325743
2023-01-24 09:22:15.400309: step: 1192/530, loss: 0.006520634517073631
2023-01-24 09:22:16.499307: step: 1196/530, loss: 0.005236170720309019
2023-01-24 09:22:17.607938: step: 1200/530, loss: 0.0003623549418989569
2023-01-24 09:22:18.692956: step: 1204/530, loss: 0.0013735555112361908
2023-01-24 09:22:19.788148: step: 1208/530, loss: 0.0009886849438771605
2023-01-24 09:22:20.865777: step: 1212/530, loss: 0.0024561192840337753
2023-01-24 09:22:22.006258: step: 1216/530, loss: 0.004731297492980957
2023-01-24 09:22:23.126229: step: 1220/530, loss: 0.0025116626638919115
2023-01-24 09:22:24.195440: step: 1224/530, loss: 0.003190577495843172
2023-01-24 09:22:25.285523: step: 1228/530, loss: 0.009936847724020481
2023-01-24 09:22:26.368351: step: 1232/530, loss: 0.0006460713921114802
2023-01-24 09:22:27.443954: step: 1236/530, loss: 0.00035688711795955896
2023-01-24 09:22:28.518397: step: 1240/530, loss: 0.002589360112324357
2023-01-24 09:22:29.627563: step: 1244/530, loss: 0.002872176468372345
2023-01-24 09:22:30.720618: step: 1248/530, loss: 0.005783560685813427
2023-01-24 09:22:31.812852: step: 1252/530, loss: 0.009352799504995346
2023-01-24 09:22:32.904877: step: 1256/530, loss: 0.0019772867672145367
2023-01-24 09:22:33.992575: step: 1260/530, loss: 0.01452991459518671
2023-01-24 09:22:35.093563: step: 1264/530, loss: 0.0008392550516873598
2023-01-24 09:22:36.191981: step: 1268/530, loss: 0.002110585570335388
2023-01-24 09:22:37.281224: step: 1272/530, loss: 0.0
2023-01-24 09:22:38.393376: step: 1276/530, loss: 0.0009411110077053308
2023-01-24 09:22:39.492551: step: 1280/530, loss: 0.0019496346358209848
2023-01-24 09:22:40.572672: step: 1284/530, loss: 0.0007129334844648838
2023-01-24 09:22:41.673729: step: 1288/530, loss: 5.188986961002229e-06
2023-01-24 09:22:42.799874: step: 1292/530, loss: 3.364436634001322e-05
2023-01-24 09:22:43.886352: step: 1296/530, loss: 3.258133074268699e-05
2023-01-24 09:22:44.971068: step: 1300/530, loss: 0.014258338138461113
2023-01-24 09:22:46.068128: step: 1304/530, loss: 0.008571045473217964
2023-01-24 09:22:47.184180: step: 1308/530, loss: 0.0028334816452115774
2023-01-24 09:22:48.282306: step: 1312/530, loss: 0.0011947295861318707
2023-01-24 09:22:49.360975: step: 1316/530, loss: 0.01433481927961111
2023-01-24 09:22:50.462441: step: 1320/530, loss: 0.01468334998935461
2023-01-24 09:22:51.563326: step: 1324/530, loss: 0.004220316186547279
2023-01-24 09:22:52.658143: step: 1328/530, loss: 0.0023487682919949293
2023-01-24 09:22:53.765099: step: 1332/530, loss: 0.0037937385495752096
2023-01-24 09:22:54.854421: step: 1336/530, loss: 0.005685847718268633
2023-01-24 09:22:55.955281: step: 1340/530, loss: 0.0036236243322491646
2023-01-24 09:22:57.043592: step: 1344/530, loss: 0.0037714182399213314
2023-01-24 09:22:58.126275: step: 1348/530, loss: 0.0027703167870640755
2023-01-24 09:22:59.222584: step: 1352/530, loss: 0.0034639134537428617
2023-01-24 09:23:00.328478: step: 1356/530, loss: 0.0013512304285541177
2023-01-24 09:23:01.425568: step: 1360/530, loss: 0.0038040808867663145
2023-01-24 09:23:02.514230: step: 1364/530, loss: 0.003248954890295863
2023-01-24 09:23:03.610309: step: 1368/530, loss: 0.0013664424186572433
2023-01-24 09:23:04.683296: step: 1372/530, loss: 0.0016001887852326035
2023-01-24 09:23:05.786571: step: 1376/530, loss: 0.0051473951898515224
2023-01-24 09:23:06.884390: step: 1380/530, loss: 0.029464716091752052
2023-01-24 09:23:07.985494: step: 1384/530, loss: 0.00023289750970434397
2023-01-24 09:23:09.095132: step: 1388/530, loss: 0.04877311363816261
2023-01-24 09:23:10.195131: step: 1392/530, loss: 0.005440156906843185
2023-01-24 09:23:11.278545: step: 1396/530, loss: 0.0007012205896899104
2023-01-24 09:23:12.387037: step: 1400/530, loss: 0.0007147606229409575
2023-01-24 09:23:13.469342: step: 1404/530, loss: 0.0024747319985181093
2023-01-24 09:23:14.573342: step: 1408/530, loss: 0.0021012744400650263
2023-01-24 09:23:15.676346: step: 1412/530, loss: 0.003056436777114868
2023-01-24 09:23:16.779475: step: 1416/530, loss: 0.007285845000296831
2023-01-24 09:23:17.868973: step: 1420/530, loss: 0.006533654872328043
2023-01-24 09:23:18.956202: step: 1424/530, loss: 0.0011564880842342973
2023-01-24 09:23:20.063569: step: 1428/530, loss: 0.0038760975003242493
2023-01-24 09:23:21.158619: step: 1432/530, loss: 0.00046560607734136283
2023-01-24 09:23:22.262954: step: 1436/530, loss: 0.007719695568084717
2023-01-24 09:23:23.357646: step: 1440/530, loss: 0.000948564033024013
2023-01-24 09:23:24.422409: step: 1444/530, loss: 0.012988336384296417
2023-01-24 09:23:25.509709: step: 1448/530, loss: 0.0023189648054540157
2023-01-24 09:23:26.591525: step: 1452/530, loss: 0.0009147964883595705
2023-01-24 09:23:27.676534: step: 1456/530, loss: 0.0035243304446339607
2023-01-24 09:23:28.763489: step: 1460/530, loss: 0.003154285717755556
2023-01-24 09:23:29.860480: step: 1464/530, loss: 0.017779337242245674
2023-01-24 09:23:30.939964: step: 1468/530, loss: 0.002096073003485799
2023-01-24 09:23:32.034243: step: 1472/530, loss: 0.011108839884400368
2023-01-24 09:23:33.120544: step: 1476/530, loss: 0.000411507033277303
2023-01-24 09:23:34.237111: step: 1480/530, loss: 0.0070840464904904366
2023-01-24 09:23:35.333371: step: 1484/530, loss: 0.0040029967203736305
2023-01-24 09:23:36.429434: step: 1488/530, loss: 0.018261317163705826
2023-01-24 09:23:37.511659: step: 1492/530, loss: 0.022633962333202362
2023-01-24 09:23:38.587006: step: 1496/530, loss: 0.0007916140602901578
2023-01-24 09:23:39.676160: step: 1500/530, loss: 0.001371148508042097
2023-01-24 09:23:40.810655: step: 1504/530, loss: 0.020567800849676132
2023-01-24 09:23:41.892999: step: 1508/530, loss: 0.008351309224963188
2023-01-24 09:23:42.976352: step: 1512/530, loss: 0.0036118722055107355
2023-01-24 09:23:44.074503: step: 1516/530, loss: 0.024894297122955322
2023-01-24 09:23:45.139723: step: 1520/530, loss: 0.00034612778108567
2023-01-24 09:23:46.223919: step: 1524/530, loss: 0.0061981286853551865
2023-01-24 09:23:47.333384: step: 1528/530, loss: 0.016763020306825638
2023-01-24 09:23:48.401328: step: 1532/530, loss: 0.0008295041043311357
2023-01-24 09:23:49.476485: step: 1536/530, loss: 0.010216237045824528
2023-01-24 09:23:50.577246: step: 1540/530, loss: 0.0017834630561992526
2023-01-24 09:23:51.671327: step: 1544/530, loss: 0.012036183848977089
2023-01-24 09:23:52.744165: step: 1548/530, loss: 0.0027237434405833483
2023-01-24 09:23:53.834502: step: 1552/530, loss: 0.007208657916635275
2023-01-24 09:23:54.945248: step: 1556/530, loss: 0.009769456461071968
2023-01-24 09:23:56.020160: step: 1560/530, loss: 0.0007078879280015826
2023-01-24 09:23:57.109604: step: 1564/530, loss: 0.002872936427593231
2023-01-24 09:23:58.190111: step: 1568/530, loss: 0.005300926975905895
2023-01-24 09:23:59.270350: step: 1572/530, loss: 0.0014098727842792869
2023-01-24 09:24:00.363662: step: 1576/530, loss: 0.006817088462412357
2023-01-24 09:24:01.464673: step: 1580/530, loss: 0.0013497865293174982
2023-01-24 09:24:02.558538: step: 1584/530, loss: 0.00028876421856693923
2023-01-24 09:24:03.675241: step: 1588/530, loss: 0.004325491841882467
2023-01-24 09:24:04.761588: step: 1592/530, loss: 0.011348665691912174
2023-01-24 09:24:05.848480: step: 1596/530, loss: 0.0035355770960450172
2023-01-24 09:24:06.917944: step: 1600/530, loss: 0.00013748608762398362
2023-01-24 09:24:08.015067: step: 1604/530, loss: 0.002196061657741666
2023-01-24 09:24:09.098039: step: 1608/530, loss: 0.0021907149348407984
2023-01-24 09:24:10.192428: step: 1612/530, loss: 0.0043025934137403965
2023-01-24 09:24:11.284672: step: 1616/530, loss: 0.004991177003830671
2023-01-24 09:24:12.374737: step: 1620/530, loss: 0.0009854704840108752
2023-01-24 09:24:13.462302: step: 1624/530, loss: 0.0009910885710269213
2023-01-24 09:24:14.580511: step: 1628/530, loss: 0.013235753402113914
2023-01-24 09:24:15.668120: step: 1632/530, loss: 0.002808724297210574
2023-01-24 09:24:16.766662: step: 1636/530, loss: 0.002283906564116478
2023-01-24 09:24:17.857726: step: 1640/530, loss: 0.005316497758030891
2023-01-24 09:24:18.944655: step: 1644/530, loss: 0.004256706219166517
2023-01-24 09:24:20.046460: step: 1648/530, loss: 0.0075982981361448765
2023-01-24 09:24:21.156000: step: 1652/530, loss: 0.006811073049902916
2023-01-24 09:24:22.249211: step: 1656/530, loss: 0.0011994980741292238
2023-01-24 09:24:23.333842: step: 1660/530, loss: 0.001670225989073515
2023-01-24 09:24:24.412682: step: 1664/530, loss: 0.0027181445620954037
2023-01-24 09:24:25.517896: step: 1668/530, loss: 0.0022412072867155075
2023-01-24 09:24:26.600648: step: 1672/530, loss: 0.002797999419271946
2023-01-24 09:24:27.707049: step: 1676/530, loss: 0.00272500142455101
2023-01-24 09:24:28.795152: step: 1680/530, loss: 0.0052646188996732235
2023-01-24 09:24:29.882872: step: 1684/530, loss: 2.53915750363376e-05
2023-01-24 09:24:30.975459: step: 1688/530, loss: 0.00134277471806854
2023-01-24 09:24:32.080195: step: 1692/530, loss: 0.013469576835632324
2023-01-24 09:24:33.168871: step: 1696/530, loss: 0.008590266108512878
2023-01-24 09:24:34.262059: step: 1700/530, loss: 0.0021843782160431147
2023-01-24 09:24:35.358082: step: 1704/530, loss: 0.007513238582760096
2023-01-24 09:24:36.447453: step: 1708/530, loss: 0.0145924286916852
2023-01-24 09:24:37.545137: step: 1712/530, loss: 0.002340807346627116
2023-01-24 09:24:38.642713: step: 1716/530, loss: 0.01064359862357378
2023-01-24 09:24:39.729895: step: 1720/530, loss: 0.007667229976505041
2023-01-24 09:24:40.809669: step: 1724/530, loss: 0.006118538789451122
2023-01-24 09:24:41.896556: step: 1728/530, loss: 0.004504764452576637
2023-01-24 09:24:42.989713: step: 1732/530, loss: 0.006519198417663574
2023-01-24 09:24:44.085790: step: 1736/530, loss: 0.0039019996766000986
2023-01-24 09:24:45.178066: step: 1740/530, loss: 0.003268276108428836
2023-01-24 09:24:46.267554: step: 1744/530, loss: 0.0038736071437597275
2023-01-24 09:24:47.369484: step: 1748/530, loss: 0.010874832980334759
2023-01-24 09:24:48.457485: step: 1752/530, loss: 0.003607241902500391
2023-01-24 09:24:49.543575: step: 1756/530, loss: 0.0023108585737645626
2023-01-24 09:24:50.622622: step: 1760/530, loss: 0.0
2023-01-24 09:24:51.708610: step: 1764/530, loss: 0.003200850449502468
2023-01-24 09:24:52.807020: step: 1768/530, loss: 0.009596412070095539
2023-01-24 09:24:53.891460: step: 1772/530, loss: 0.002132405759766698
2023-01-24 09:24:54.969547: step: 1776/530, loss: 0.00011658322910079733
2023-01-24 09:24:56.064904: step: 1780/530, loss: 0.001403294038027525
2023-01-24 09:24:57.158415: step: 1784/530, loss: 0.0010689322371035814
2023-01-24 09:24:58.244750: step: 1788/530, loss: 0.00023162271827459335
2023-01-24 09:24:59.330508: step: 1792/530, loss: 0.00031199815566651523
2023-01-24 09:25:00.414119: step: 1796/530, loss: 0.011649326421320438
2023-01-24 09:25:01.483363: step: 1800/530, loss: 0.0030095886904746294
2023-01-24 09:25:02.600857: step: 1804/530, loss: 0.0045340885408222675
2023-01-24 09:25:03.684170: step: 1808/530, loss: 0.004164821468293667
2023-01-24 09:25:04.765663: step: 1812/530, loss: 0.0030954324174672365
2023-01-24 09:25:05.854333: step: 1816/530, loss: 0.004995994735509157
2023-01-24 09:25:06.961491: step: 1820/530, loss: 0.00032775578438304365
2023-01-24 09:25:08.067990: step: 1824/530, loss: 0.0033056489191949368
2023-01-24 09:25:09.167919: step: 1828/530, loss: 0.0016626243013888597
2023-01-24 09:25:10.258573: step: 1832/530, loss: 1.0593716979201417e-05
2023-01-24 09:25:11.339482: step: 1836/530, loss: 0.006667034700512886
2023-01-24 09:25:12.441106: step: 1840/530, loss: 0.009982477873563766
2023-01-24 09:25:13.538593: step: 1844/530, loss: 0.01013704389333725
2023-01-24 09:25:14.665648: step: 1848/530, loss: 0.00021069031208753586
2023-01-24 09:25:15.739882: step: 1852/530, loss: 0.002714292611926794
2023-01-24 09:25:16.831591: step: 1856/530, loss: 0.0003858456911984831
2023-01-24 09:25:17.920977: step: 1860/530, loss: 0.014455663971602917
2023-01-24 09:25:19.004230: step: 1864/530, loss: 0.003604452358558774
2023-01-24 09:25:20.105764: step: 1868/530, loss: 0.012609553523361683
2023-01-24 09:25:21.184591: step: 1872/530, loss: 0.0004549937439151108
2023-01-24 09:25:22.252313: step: 1876/530, loss: 0.0034798739943653345
2023-01-24 09:25:23.350837: step: 1880/530, loss: 0.005634340923279524
2023-01-24 09:25:24.446827: step: 1884/530, loss: 8.543483272660524e-05
2023-01-24 09:25:25.527825: step: 1888/530, loss: 0.008969456888735294
2023-01-24 09:25:26.603895: step: 1892/530, loss: 0.008344369940459728
2023-01-24 09:25:27.717160: step: 1896/530, loss: 0.0026686647906899452
2023-01-24 09:25:28.803278: step: 1900/530, loss: 0.01765001378953457
2023-01-24 09:25:29.893405: step: 1904/530, loss: 0.00037060148315504193
2023-01-24 09:25:30.974161: step: 1908/530, loss: 0.003669881261885166
2023-01-24 09:25:32.080115: step: 1912/530, loss: 0.0032493583858013153
2023-01-24 09:25:33.179516: step: 1916/530, loss: 0.005560439079999924
2023-01-24 09:25:34.277893: step: 1920/530, loss: 0.015126613900065422
2023-01-24 09:25:35.403382: step: 1924/530, loss: 0.03719492256641388
2023-01-24 09:25:36.494754: step: 1928/530, loss: 0.0004608245217241347
2023-01-24 09:25:37.580669: step: 1932/530, loss: 0.0004902182263322175
2023-01-24 09:25:38.671244: step: 1936/530, loss: 0.00780758960172534
2023-01-24 09:25:39.764198: step: 1940/530, loss: 0.0021297961939126253
2023-01-24 09:25:40.850900: step: 1944/530, loss: 0.010691937990486622
2023-01-24 09:25:41.931875: step: 1948/530, loss: 0.004143524449318647
2023-01-24 09:25:43.011245: step: 1952/530, loss: 0.005331322085112333
2023-01-24 09:25:44.113429: step: 1956/530, loss: 0.03961164876818657
2023-01-24 09:25:45.197562: step: 1960/530, loss: 0.008898531086742878
2023-01-24 09:25:46.287345: step: 1964/530, loss: 0.002609647111967206
2023-01-24 09:25:47.405728: step: 1968/530, loss: 0.004613959696143866
2023-01-24 09:25:48.492942: step: 1972/530, loss: 0.002736974973231554
2023-01-24 09:25:49.580488: step: 1976/530, loss: 0.0058308071456849575
2023-01-24 09:25:50.681000: step: 1980/530, loss: 0.008194469846785069
2023-01-24 09:25:51.790243: step: 1984/530, loss: 0.001225427258759737
2023-01-24 09:25:52.868009: step: 1988/530, loss: 0.00017375429160892963
2023-01-24 09:25:53.956382: step: 1992/530, loss: 0.004000471904873848
2023-01-24 09:25:55.040375: step: 1996/530, loss: 0.0037554746959358454
2023-01-24 09:25:56.170696: step: 2000/530, loss: 0.0032068383879959583
2023-01-24 09:25:57.258591: step: 2004/530, loss: 0.007411566097289324
2023-01-24 09:25:58.367391: step: 2008/530, loss: 0.015719568356871605
2023-01-24 09:25:59.455203: step: 2012/530, loss: 0.004038520157337189
2023-01-24 09:26:00.557838: step: 2016/530, loss: 0.0015511835226789117
2023-01-24 09:26:01.636946: step: 2020/530, loss: 0.001353686093352735
2023-01-24 09:26:02.770499: step: 2024/530, loss: 0.0034951341804116964
2023-01-24 09:26:03.862656: step: 2028/530, loss: 0.0031962350476533175
2023-01-24 09:26:04.945866: step: 2032/530, loss: 0.003692465601488948
2023-01-24 09:26:06.045964: step: 2036/530, loss: 0.0018718288047239184
2023-01-24 09:26:07.135471: step: 2040/530, loss: 0.0010259640403091908
2023-01-24 09:26:08.225894: step: 2044/530, loss: 0.011069604195654392
2023-01-24 09:26:09.323937: step: 2048/530, loss: 0.009898328222334385
2023-01-24 09:26:10.422233: step: 2052/530, loss: 0.002545662224292755
2023-01-24 09:26:11.512517: step: 2056/530, loss: 0.004568136762827635
2023-01-24 09:26:12.624400: step: 2060/530, loss: 0.004701043479144573
2023-01-24 09:26:13.692291: step: 2064/530, loss: 0.005160473752766848
2023-01-24 09:26:14.775280: step: 2068/530, loss: 0.0006103627383708954
2023-01-24 09:26:15.854130: step: 2072/530, loss: 8.681625331519172e-05
2023-01-24 09:26:16.950758: step: 2076/530, loss: 0.0011636678827926517
2023-01-24 09:26:18.062599: step: 2080/530, loss: 0.002393764676526189
2023-01-24 09:26:19.144192: step: 2084/530, loss: 0.0002670777903404087
2023-01-24 09:26:20.219706: step: 2088/530, loss: 0.0063750711269676685
2023-01-24 09:26:21.305826: step: 2092/530, loss: 0.00611089589074254
2023-01-24 09:26:22.386960: step: 2096/530, loss: 0.013167677447199821
2023-01-24 09:26:23.473767: step: 2100/530, loss: 0.007116015534847975
2023-01-24 09:26:24.562992: step: 2104/530, loss: 0.002222956158220768
2023-01-24 09:26:25.646193: step: 2108/530, loss: 0.006987978704273701
2023-01-24 09:26:26.747578: step: 2112/530, loss: 0.002270687837153673
2023-01-24 09:26:27.839997: step: 2116/530, loss: 0.02031017281115055
2023-01-24 09:26:28.931849: step: 2120/530, loss: 0.002151333726942539
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34967404630287613, 'r': 0.34768349195959597, 'f1': 0.3486759281878346}, 'combined': 0.2569191049805097, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3430406359990493, 'r': 0.2748396786936003, 'f1': 0.3051761835905875}, 'combined': 0.18953047191415437, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38442079215032754, 'r': 0.32971195076270976, 'f1': 0.3549707825371768}, 'combined': 0.26155741871160393, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3348388568620032, 'r': 0.2627095378937061, 'f1': 0.29442087746227086}, 'combined': 0.18285086073972612, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3857875113608197, 'r': 0.3330802991824914, 'f1': 0.35750166531399785}, 'combined': 0.26342227970505105, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3464498543974213, 'r': 0.2684729868726315, 'f1': 0.30251739232700303}, 'combined': 0.1878792226030861, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6047570850202428, 'r': 0.27109800362976405, 'f1': 0.3743734335839598}, 'combined': 0.24958228905597318, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 09:28:53.216461: step: 4/530, loss: 0.00239155744202435
2023-01-24 09:28:54.300166: step: 8/530, loss: 0.0024033032823354006
2023-01-24 09:28:55.401818: step: 12/530, loss: 0.00449529429897666
2023-01-24 09:28:56.499952: step: 16/530, loss: 0.0058736661449074745
2023-01-24 09:28:57.617662: step: 20/530, loss: 0.00034863376640714705
2023-01-24 09:28:58.697729: step: 24/530, loss: 0.015756824985146523
2023-01-24 09:28:59.773852: step: 28/530, loss: 0.00029133513453416526
2023-01-24 09:29:00.862615: step: 32/530, loss: 0.0010171124013140798
2023-01-24 09:29:01.950027: step: 36/530, loss: 0.005919092800468206
2023-01-24 09:29:03.030477: step: 40/530, loss: 0.0014844770776107907
2023-01-24 09:29:04.108934: step: 44/530, loss: 0.0005742798093706369
2023-01-24 09:29:05.194467: step: 48/530, loss: 0.001526810578070581
2023-01-24 09:29:06.281508: step: 52/530, loss: 0.017103327438235283
2023-01-24 09:29:07.369062: step: 56/530, loss: 0.004896756261587143
2023-01-24 09:29:08.454930: step: 60/530, loss: 0.003529720474034548
2023-01-24 09:29:09.556263: step: 64/530, loss: 0.003721288638189435
2023-01-24 09:29:10.638463: step: 68/530, loss: 0.013919164426624775
2023-01-24 09:29:11.743939: step: 72/530, loss: 0.009428983554244041
2023-01-24 09:29:12.821708: step: 76/530, loss: 0.0020549967885017395
2023-01-24 09:29:13.903442: step: 80/530, loss: 0.0005727734533138573
2023-01-24 09:29:14.991615: step: 84/530, loss: 0.029020557180047035
2023-01-24 09:29:16.096968: step: 88/530, loss: 0.0009710404556244612
2023-01-24 09:29:17.172030: step: 92/530, loss: 0.0140199214220047
2023-01-24 09:29:18.244801: step: 96/530, loss: 0.0027598401065915823
2023-01-24 09:29:19.355506: step: 100/530, loss: 0.002796739572659135
2023-01-24 09:29:20.424486: step: 104/530, loss: 0.0011954504298046231
2023-01-24 09:29:21.528344: step: 108/530, loss: 0.024249127134680748
2023-01-24 09:29:22.653738: step: 112/530, loss: 0.005792188923805952
2023-01-24 09:29:23.723749: step: 116/530, loss: 0.006264966446906328
2023-01-24 09:29:24.798604: step: 120/530, loss: 0.003406588453799486
2023-01-24 09:29:25.876299: step: 124/530, loss: 0.0008385282126255333
2023-01-24 09:29:26.948979: step: 128/530, loss: 0.006097255740314722
2023-01-24 09:29:28.044196: step: 132/530, loss: 0.004822678864002228
2023-01-24 09:29:29.119990: step: 136/530, loss: 0.009024323895573616
2023-01-24 09:29:30.207100: step: 140/530, loss: 0.004446942359209061
2023-01-24 09:29:31.283392: step: 144/530, loss: 0.006993423216044903
2023-01-24 09:29:32.383553: step: 148/530, loss: 0.0014891955070197582
2023-01-24 09:29:33.475065: step: 152/530, loss: 0.0013069381238892674
2023-01-24 09:29:34.579820: step: 156/530, loss: 0.007261795457452536
2023-01-24 09:29:35.647340: step: 160/530, loss: 0.003443314926698804
2023-01-24 09:29:36.764076: step: 164/530, loss: 0.027477990835905075
2023-01-24 09:29:37.861152: step: 168/530, loss: 0.015958357602357864
2023-01-24 09:29:38.948663: step: 172/530, loss: 6.025932634656783e-06
2023-01-24 09:29:40.033819: step: 176/530, loss: 0.0012165606021881104
2023-01-24 09:29:41.120177: step: 180/530, loss: 0.006017171777784824
2023-01-24 09:29:42.188438: step: 184/530, loss: 0.0029329550452530384
2023-01-24 09:29:43.292510: step: 188/530, loss: 0.006054393015801907
2023-01-24 09:29:44.387463: step: 192/530, loss: 0.00127957493532449
2023-01-24 09:29:45.459444: step: 196/530, loss: 0.008293425664305687
2023-01-24 09:29:46.591407: step: 200/530, loss: 0.00937639269977808
2023-01-24 09:29:47.686241: step: 204/530, loss: 0.0019085989333689213
2023-01-24 09:29:48.767194: step: 208/530, loss: 0.001609591068699956
2023-01-24 09:29:49.824166: step: 212/530, loss: 0.0010371814714744687
2023-01-24 09:29:50.906354: step: 216/530, loss: 0.0026844250969588757
2023-01-24 09:29:52.002771: step: 220/530, loss: 0.0048226360231637955
2023-01-24 09:29:53.099023: step: 224/530, loss: 0.04717119038105011
2023-01-24 09:29:54.186096: step: 228/530, loss: 0.007930617779493332
2023-01-24 09:29:55.290394: step: 232/530, loss: 0.00222823116928339
2023-01-24 09:29:56.373782: step: 236/530, loss: 0.004855830688029528
2023-01-24 09:29:57.476321: step: 240/530, loss: 0.023386413231492043
2023-01-24 09:29:58.563909: step: 244/530, loss: 0.008373802527785301
2023-01-24 09:29:59.664660: step: 248/530, loss: 0.00043708784505724907
2023-01-24 09:30:00.743850: step: 252/530, loss: 0.01068387646228075
2023-01-24 09:30:01.829212: step: 256/530, loss: 0.0005089847836643457
2023-01-24 09:30:02.911041: step: 260/530, loss: 0.0026610034983605146
2023-01-24 09:30:04.028644: step: 264/530, loss: 0.00679350271821022
2023-01-24 09:30:05.104054: step: 268/530, loss: 0.00031216413481161
2023-01-24 09:30:06.201428: step: 272/530, loss: 1.621147930563893e-05
2023-01-24 09:30:07.290044: step: 276/530, loss: 0.037259966135025024
2023-01-24 09:30:08.364361: step: 280/530, loss: 0.0030288512352854013
2023-01-24 09:30:09.465096: step: 284/530, loss: 0.003950710874050856
2023-01-24 09:30:10.553650: step: 288/530, loss: 0.006789867766201496
2023-01-24 09:30:11.641117: step: 292/530, loss: 0.009791080839931965
2023-01-24 09:30:12.751666: step: 296/530, loss: 0.010872495360672474
2023-01-24 09:30:13.841137: step: 300/530, loss: 0.0014845393598079681
2023-01-24 09:30:14.919424: step: 304/530, loss: 0.0048056114464998245
2023-01-24 09:30:15.998470: step: 308/530, loss: 0.02465643733739853
2023-01-24 09:30:17.084910: step: 312/530, loss: 0.0028367226477712393
2023-01-24 09:30:18.168737: step: 316/530, loss: 0.0005825771950185299
2023-01-24 09:30:19.262127: step: 320/530, loss: 0.010419790633022785
2023-01-24 09:30:20.355543: step: 324/530, loss: 0.0012331544421613216
2023-01-24 09:30:21.433560: step: 328/530, loss: 0.008323131129145622
2023-01-24 09:30:22.523760: step: 332/530, loss: 0.022704927250742912
2023-01-24 09:30:23.635595: step: 336/530, loss: 0.02240392379462719
2023-01-24 09:30:24.738672: step: 340/530, loss: 0.021398130804300308
2023-01-24 09:30:25.830944: step: 344/530, loss: 0.0019201998366042972
2023-01-24 09:30:26.905709: step: 348/530, loss: 7.556645141448826e-05
2023-01-24 09:30:27.999806: step: 352/530, loss: 0.0010268030455335975
2023-01-24 09:30:29.085366: step: 356/530, loss: 0.001753143034875393
2023-01-24 09:30:30.178645: step: 360/530, loss: 0.001639651134610176
2023-01-24 09:30:31.280491: step: 364/530, loss: 0.0070901173166930676
2023-01-24 09:30:32.369184: step: 368/530, loss: 0.0034733866341412067
2023-01-24 09:30:33.466459: step: 372/530, loss: 0.005018951371312141
2023-01-24 09:30:34.562544: step: 376/530, loss: 0.006167082116007805
2023-01-24 09:30:35.650248: step: 380/530, loss: 0.0006437755655497313
2023-01-24 09:30:36.753950: step: 384/530, loss: 0.01264442503452301
2023-01-24 09:30:37.851208: step: 388/530, loss: 0.004485584329813719
2023-01-24 09:30:38.938455: step: 392/530, loss: 0.0028374779503792524
2023-01-24 09:30:40.024042: step: 396/530, loss: 0.008006450720131397
2023-01-24 09:30:41.117813: step: 400/530, loss: 0.0039567346684634686
2023-01-24 09:30:42.198353: step: 404/530, loss: 0.003176835598424077
2023-01-24 09:30:43.309051: step: 408/530, loss: 0.009895380586385727
2023-01-24 09:30:44.415137: step: 412/530, loss: 0.004642541985958815
2023-01-24 09:30:45.518511: step: 416/530, loss: 0.0030829578172415495
2023-01-24 09:30:46.638046: step: 420/530, loss: 0.0018799740355461836
2023-01-24 09:30:47.724698: step: 424/530, loss: 0.001895493478514254
2023-01-24 09:30:48.810415: step: 428/530, loss: 0.0014667012728750706
2023-01-24 09:30:49.888038: step: 432/530, loss: 0.004194389097392559
2023-01-24 09:30:50.978804: step: 436/530, loss: 0.003689173609018326
2023-01-24 09:30:52.087931: step: 440/530, loss: 0.0014013617765158415
2023-01-24 09:30:53.159675: step: 444/530, loss: 0.00045999078429304063
2023-01-24 09:30:54.251470: step: 448/530, loss: 0.004100313875824213
2023-01-24 09:30:55.340110: step: 452/530, loss: 0.0009114727145060897
2023-01-24 09:30:56.441699: step: 456/530, loss: 0.00012237658665981144
2023-01-24 09:30:57.520354: step: 460/530, loss: 6.0865801060572267e-05
2023-01-24 09:30:58.621310: step: 464/530, loss: 0.0012575997970998287
2023-01-24 09:30:59.727959: step: 468/530, loss: 0.0057510011829435825
2023-01-24 09:31:00.840908: step: 472/530, loss: 0.003288004081696272
2023-01-24 09:31:01.957816: step: 476/530, loss: 0.0033185333013534546
2023-01-24 09:31:03.034118: step: 480/530, loss: 0.015662487596273422
2023-01-24 09:31:04.115487: step: 484/530, loss: 0.043038032948970795
2023-01-24 09:31:05.212205: step: 488/530, loss: 2.1868934709345922e-05
2023-01-24 09:31:06.314223: step: 492/530, loss: 0.004520669113844633
2023-01-24 09:31:07.398603: step: 496/530, loss: 0.016593074426054955
2023-01-24 09:31:08.498681: step: 500/530, loss: 0.007728383876383305
2023-01-24 09:31:09.574030: step: 504/530, loss: 0.003346404992043972
2023-01-24 09:31:10.662965: step: 508/530, loss: 0.003778420854359865
2023-01-24 09:31:11.750416: step: 512/530, loss: 0.0028398719150573015
2023-01-24 09:31:12.841711: step: 516/530, loss: 0.005659664981067181
2023-01-24 09:31:13.951028: step: 520/530, loss: 0.006070531904697418
2023-01-24 09:31:15.042209: step: 524/530, loss: 0.02036793902516365
2023-01-24 09:31:16.123730: step: 528/530, loss: 0.004326016176491976
2023-01-24 09:31:17.190428: step: 532/530, loss: 0.0004810047394130379
2023-01-24 09:31:18.290873: step: 536/530, loss: 0.0028727876488119364
2023-01-24 09:31:19.351340: step: 540/530, loss: 0.0032594348303973675
2023-01-24 09:31:20.429303: step: 544/530, loss: 0.0006257977220229805
2023-01-24 09:31:21.513125: step: 548/530, loss: 0.00021563086193054914
2023-01-24 09:31:22.607310: step: 552/530, loss: 0.013127956539392471
2023-01-24 09:31:23.707449: step: 556/530, loss: 0.008440916426479816
2023-01-24 09:31:24.795897: step: 560/530, loss: 0.005489332601428032
2023-01-24 09:31:25.898159: step: 564/530, loss: 0.0028305230662226677
2023-01-24 09:31:26.968845: step: 568/530, loss: 0.0012131185503676534
2023-01-24 09:31:28.086707: step: 572/530, loss: 0.010537172667682171
2023-01-24 09:31:29.195445: step: 576/530, loss: 0.01680556684732437
2023-01-24 09:31:30.291856: step: 580/530, loss: 0.006243174895644188
2023-01-24 09:31:31.380334: step: 584/530, loss: 4.402376362122595e-05
2023-01-24 09:31:32.491507: step: 588/530, loss: 0.005905324127525091
2023-01-24 09:31:33.592061: step: 592/530, loss: 0.008308203890919685
2023-01-24 09:31:34.696961: step: 596/530, loss: 0.00039306472172029316
2023-01-24 09:31:35.795676: step: 600/530, loss: 0.00035865072277374566
2023-01-24 09:31:36.893690: step: 604/530, loss: 0.006062301807105541
2023-01-24 09:31:37.989123: step: 608/530, loss: 0.0010942736407741904
2023-01-24 09:31:39.089348: step: 612/530, loss: 0.009786644019186497
2023-01-24 09:31:40.178846: step: 616/530, loss: 0.0025595512706786394
2023-01-24 09:31:41.263596: step: 620/530, loss: 0.0029115111101418734
2023-01-24 09:31:42.388681: step: 624/530, loss: 0.018040794879198074
2023-01-24 09:31:43.503996: step: 628/530, loss: 0.003304567653685808
2023-01-24 09:31:44.591084: step: 632/530, loss: 0.001293787150643766
2023-01-24 09:31:45.678643: step: 636/530, loss: 0.06879562884569168
2023-01-24 09:31:46.782190: step: 640/530, loss: 0.013498660176992416
2023-01-24 09:31:47.892558: step: 644/530, loss: 0.010204283520579338
2023-01-24 09:31:48.999028: step: 648/530, loss: 0.0028150181751698256
2023-01-24 09:31:50.086717: step: 652/530, loss: 0.004815452732145786
2023-01-24 09:31:51.209426: step: 656/530, loss: 0.00303437327966094
2023-01-24 09:31:52.300661: step: 660/530, loss: 0.0077403211034834385
2023-01-24 09:31:53.401003: step: 664/530, loss: 0.0003952081024181098
2023-01-24 09:31:54.497752: step: 668/530, loss: 0.017567165195941925
2023-01-24 09:31:55.589578: step: 672/530, loss: 0.0014099651016294956
2023-01-24 09:31:56.705253: step: 676/530, loss: 0.03357509896159172
2023-01-24 09:31:57.817941: step: 680/530, loss: 0.013304296880960464
2023-01-24 09:31:58.924644: step: 684/530, loss: 0.005183124914765358
2023-01-24 09:32:00.032246: step: 688/530, loss: 7.820197060937062e-05
2023-01-24 09:32:01.121797: step: 692/530, loss: 0.009638318791985512
2023-01-24 09:32:02.217406: step: 696/530, loss: 0.0012962538748979568
2023-01-24 09:32:03.286629: step: 700/530, loss: 0.0040832869708538055
2023-01-24 09:32:04.369174: step: 704/530, loss: 0.004653675947338343
2023-01-24 09:32:05.452172: step: 708/530, loss: 0.029797863215208054
2023-01-24 09:32:06.523773: step: 712/530, loss: 0.0036987420171499252
2023-01-24 09:32:07.585749: step: 716/530, loss: 0.003255095798522234
2023-01-24 09:32:08.672332: step: 720/530, loss: 0.0021511369850486517
2023-01-24 09:32:09.727042: step: 724/530, loss: 3.745911817532033e-05
2023-01-24 09:32:10.831575: step: 728/530, loss: 0.00893073808401823
2023-01-24 09:32:11.937593: step: 732/530, loss: 0.004155294504016638
2023-01-24 09:32:13.048694: step: 736/530, loss: 0.004102346021682024
2023-01-24 09:32:14.132638: step: 740/530, loss: 0.013285879977047443
2023-01-24 09:32:15.238351: step: 744/530, loss: 0.0017888894071802497
2023-01-24 09:32:16.308647: step: 748/530, loss: 1.5603556676069275e-05
2023-01-24 09:32:17.385368: step: 752/530, loss: 0.009007218293845654
2023-01-24 09:32:18.517561: step: 756/530, loss: 0.0008521409472450614
2023-01-24 09:32:19.614878: step: 760/530, loss: 0.006173994857817888
2023-01-24 09:32:20.701720: step: 764/530, loss: 0.024529192596673965
2023-01-24 09:32:21.776274: step: 768/530, loss: 0.0004677910765167326
2023-01-24 09:32:22.853955: step: 772/530, loss: 0.014223648235201836
2023-01-24 09:32:23.942566: step: 776/530, loss: 0.03586577996611595
2023-01-24 09:32:25.042585: step: 780/530, loss: 0.005227996036410332
2023-01-24 09:32:26.155328: step: 784/530, loss: 0.005863068159669638
2023-01-24 09:32:27.248225: step: 788/530, loss: 0.010787401348352432
2023-01-24 09:32:28.360928: step: 792/530, loss: 0.0038701503071933985
2023-01-24 09:32:29.457669: step: 796/530, loss: 0.0016628074226900935
2023-01-24 09:32:30.537385: step: 800/530, loss: 5.918848910368979e-05
2023-01-24 09:32:31.664889: step: 804/530, loss: 0.012087317183613777
2023-01-24 09:32:32.748674: step: 808/530, loss: 2.4346105419681408e-05
2023-01-24 09:32:33.827201: step: 812/530, loss: 0.01186387799680233
2023-01-24 09:32:34.928386: step: 816/530, loss: 0.0028141469229012728
2023-01-24 09:32:36.027337: step: 820/530, loss: 0.0012036864645779133
2023-01-24 09:32:37.167826: step: 824/530, loss: 0.006622304208576679
2023-01-24 09:32:38.256655: step: 828/530, loss: 0.0068290564231574535
2023-01-24 09:32:39.352693: step: 832/530, loss: 0.006145627237856388
2023-01-24 09:32:40.416478: step: 836/530, loss: 0.0054101282730698586
2023-01-24 09:32:41.517500: step: 840/530, loss: 0.0026045117992907763
2023-01-24 09:32:42.611348: step: 844/530, loss: 0.0038952401373535395
2023-01-24 09:32:43.704692: step: 848/530, loss: 0.010366232134401798
2023-01-24 09:32:44.779020: step: 852/530, loss: 9.185209637507796e-05
2023-01-24 09:32:45.844942: step: 856/530, loss: 0.009231075644493103
2023-01-24 09:32:46.930326: step: 860/530, loss: 0.004903125576674938
2023-01-24 09:32:48.028958: step: 864/530, loss: 0.006773474160581827
2023-01-24 09:32:49.098145: step: 868/530, loss: 0.0013201372930780053
2023-01-24 09:32:50.209354: step: 872/530, loss: 0.006256154738366604
2023-01-24 09:32:51.305714: step: 876/530, loss: 0.0016541752265766263
2023-01-24 09:32:52.378070: step: 880/530, loss: 6.33298791186121e-09
2023-01-24 09:32:53.461986: step: 884/530, loss: 0.00031882431358098984
2023-01-24 09:32:54.554555: step: 888/530, loss: 0.00876542367041111
2023-01-24 09:32:55.643502: step: 892/530, loss: 0.001780482823960483
2023-01-24 09:32:56.740057: step: 896/530, loss: 0.0004626884183380753
2023-01-24 09:32:57.821956: step: 900/530, loss: 0.003102170303463936
2023-01-24 09:32:58.920958: step: 904/530, loss: 0.012953349389135838
2023-01-24 09:33:00.012038: step: 908/530, loss: 0.0037548686377704144
2023-01-24 09:33:01.114576: step: 912/530, loss: 0.00599473062902689
2023-01-24 09:33:02.192686: step: 916/530, loss: 0.008263442665338516
2023-01-24 09:33:03.304737: step: 920/530, loss: 0.009791245684027672
2023-01-24 09:33:04.401873: step: 924/530, loss: 0.0007159954402595758
2023-01-24 09:33:05.519696: step: 928/530, loss: 0.0031552892178297043
2023-01-24 09:33:06.612177: step: 932/530, loss: 0.010926619172096252
2023-01-24 09:33:07.698793: step: 936/530, loss: 0.00016466010129079223
2023-01-24 09:33:08.776989: step: 940/530, loss: 0.004548830445855856
2023-01-24 09:33:09.854675: step: 944/530, loss: 1.2120547580707353e-05
2023-01-24 09:33:10.941156: step: 948/530, loss: 0.00046599801862612367
2023-01-24 09:33:12.031802: step: 952/530, loss: 0.02845151536166668
2023-01-24 09:33:13.107121: step: 956/530, loss: 0.005994254723191261
2023-01-24 09:33:14.180041: step: 960/530, loss: 0.006463390309363604
2023-01-24 09:33:15.293982: step: 964/530, loss: 8.653848453832325e-06
2023-01-24 09:33:16.380676: step: 968/530, loss: 0.004255854059010744
2023-01-24 09:33:17.504079: step: 972/530, loss: 0.00019908220565412194
2023-01-24 09:33:18.598834: step: 976/530, loss: 0.0021408952306956053
2023-01-24 09:33:19.687306: step: 980/530, loss: 0.0042573981918394566
2023-01-24 09:33:20.786844: step: 984/530, loss: 0.001045731594786048
2023-01-24 09:33:21.900648: step: 988/530, loss: 0.018463417887687683
2023-01-24 09:33:22.980575: step: 992/530, loss: 0.004368930123746395
2023-01-24 09:33:24.078233: step: 996/530, loss: 0.009772378951311111
2023-01-24 09:33:25.146427: step: 1000/530, loss: 1.3300714272190817e-06
2023-01-24 09:33:26.234051: step: 1004/530, loss: 0.007684438023716211
2023-01-24 09:33:27.330862: step: 1008/530, loss: 0.005854856222867966
2023-01-24 09:33:28.421395: step: 1012/530, loss: 0.0027198675088584423
2023-01-24 09:33:29.509536: step: 1016/530, loss: 0.0006460316362790763
2023-01-24 09:33:30.604130: step: 1020/530, loss: 0.010666060261428356
2023-01-24 09:33:31.712995: step: 1024/530, loss: 0.0020747161470353603
2023-01-24 09:33:32.813848: step: 1028/530, loss: 0.0006734076887369156
2023-01-24 09:33:33.904158: step: 1032/530, loss: 0.0025935957673937082
2023-01-24 09:33:34.988603: step: 1036/530, loss: 0.00029823408112861216
2023-01-24 09:33:36.074762: step: 1040/530, loss: 0.00022185847046785057
2023-01-24 09:33:37.156562: step: 1044/530, loss: 0.004975500516593456
2023-01-24 09:33:38.254783: step: 1048/530, loss: 0.0009544325876049697
2023-01-24 09:33:39.345229: step: 1052/530, loss: 0.0026594416704028845
2023-01-24 09:33:40.432422: step: 1056/530, loss: 0.0046880594454705715
2023-01-24 09:33:41.508304: step: 1060/530, loss: 0.0034318624529987574
2023-01-24 09:33:42.613619: step: 1064/530, loss: 0.004394009709358215
2023-01-24 09:33:43.718082: step: 1068/530, loss: 0.0017150972271338105
2023-01-24 09:33:44.798326: step: 1072/530, loss: 0.003705520648509264
2023-01-24 09:33:45.891549: step: 1076/530, loss: 0.00025791017105802894
2023-01-24 09:33:46.958615: step: 1080/530, loss: 0.008437520824372768
2023-01-24 09:33:48.043408: step: 1084/530, loss: 0.0018043089658021927
2023-01-24 09:33:49.149567: step: 1088/530, loss: 0.0013199786189943552
2023-01-24 09:33:50.248505: step: 1092/530, loss: 0.00043355507659725845
2023-01-24 09:33:51.332471: step: 1096/530, loss: 0.000349196809111163
2023-01-24 09:33:52.426467: step: 1100/530, loss: 0.009282906539738178
2023-01-24 09:33:53.508756: step: 1104/530, loss: 0.004893858451396227
2023-01-24 09:33:54.601918: step: 1108/530, loss: 0.0033122492022812366
2023-01-24 09:33:55.690681: step: 1112/530, loss: 0.002883948851376772
2023-01-24 09:33:56.766444: step: 1116/530, loss: 0.0036363275721669197
2023-01-24 09:33:57.878577: step: 1120/530, loss: 0.008871153928339481
2023-01-24 09:33:58.969746: step: 1124/530, loss: 7.155339699238539e-05
2023-01-24 09:34:00.037837: step: 1128/530, loss: 0.005794833414256573
2023-01-24 09:34:01.124730: step: 1132/530, loss: 0.005077144131064415
2023-01-24 09:34:02.219315: step: 1136/530, loss: 0.010705525986850262
2023-01-24 09:34:03.306417: step: 1140/530, loss: 0.009555460885167122
2023-01-24 09:34:04.392511: step: 1144/530, loss: 0.005552574992179871
2023-01-24 09:34:05.499746: step: 1148/530, loss: 0.0025734449736773968
2023-01-24 09:34:06.587408: step: 1152/530, loss: 0.0015987020451575518
2023-01-24 09:34:07.697969: step: 1156/530, loss: 0.00010630020551616326
2023-01-24 09:34:08.808132: step: 1160/530, loss: 0.0025307191535830498
2023-01-24 09:34:09.892157: step: 1164/530, loss: 0.0008618913707323372
2023-01-24 09:34:10.992168: step: 1168/530, loss: 0.006099597085267305
2023-01-24 09:34:12.069926: step: 1172/530, loss: 0.007948421873152256
2023-01-24 09:34:13.126481: step: 1176/530, loss: 0.0004808121011592448
2023-01-24 09:34:14.231078: step: 1180/530, loss: 0.0010332210222259164
2023-01-24 09:34:15.316648: step: 1184/530, loss: 0.0008535869419574738
2023-01-24 09:34:16.408642: step: 1188/530, loss: 0.006233790423721075
2023-01-24 09:34:17.512921: step: 1192/530, loss: 0.02192133106291294
2023-01-24 09:34:18.612605: step: 1196/530, loss: 0.011391752399504185
2023-01-24 09:34:19.696064: step: 1200/530, loss: 0.003326660254970193
2023-01-24 09:34:20.803067: step: 1204/530, loss: 0.000734316126909107
2023-01-24 09:34:21.907310: step: 1208/530, loss: 0.02097994275391102
2023-01-24 09:34:23.022027: step: 1212/530, loss: 0.00789344310760498
2023-01-24 09:34:24.105132: step: 1216/530, loss: 0.0050422088243067265
2023-01-24 09:34:25.229669: step: 1220/530, loss: 0.004294767510145903
2023-01-24 09:34:26.338580: step: 1224/530, loss: 0.006191391032189131
2023-01-24 09:34:27.421995: step: 1228/530, loss: 0.005577748641371727
2023-01-24 09:34:28.555482: step: 1232/530, loss: 0.004371450282633305
2023-01-24 09:34:29.661125: step: 1236/530, loss: 0.011765412986278534
2023-01-24 09:34:30.773016: step: 1240/530, loss: 0.000831493700388819
2023-01-24 09:34:31.867299: step: 1244/530, loss: 0.01249920204281807
2023-01-24 09:34:32.947561: step: 1248/530, loss: 0.019663171842694283
2023-01-24 09:34:34.024751: step: 1252/530, loss: 0.0018935668049380183
2023-01-24 09:34:35.097989: step: 1256/530, loss: 0.006387850269675255
2023-01-24 09:34:36.192920: step: 1260/530, loss: 0.0015770683530718088
2023-01-24 09:34:37.273575: step: 1264/530, loss: 0.005411600228399038
2023-01-24 09:34:38.354884: step: 1268/530, loss: 4.197704765829258e-05
2023-01-24 09:34:39.457040: step: 1272/530, loss: 0.01857392117381096
2023-01-24 09:34:40.522512: step: 1276/530, loss: 0.0004069058923050761
2023-01-24 09:34:41.603675: step: 1280/530, loss: 0.0006431051297113299
2023-01-24 09:34:42.696608: step: 1284/530, loss: 0.0032634944655001163
2023-01-24 09:34:43.774720: step: 1288/530, loss: 0.0011680993484333158
2023-01-24 09:34:44.843550: step: 1292/530, loss: 0.005447241012006998
2023-01-24 09:34:45.940952: step: 1296/530, loss: 0.005970741622149944
2023-01-24 09:34:47.032836: step: 1300/530, loss: 0.00038607389433309436
2023-01-24 09:34:48.150296: step: 1304/530, loss: 0.00487444456666708
2023-01-24 09:34:49.240432: step: 1308/530, loss: 0.005848734173923731
2023-01-24 09:34:50.326847: step: 1312/530, loss: 5.818076169816777e-05
2023-01-24 09:34:51.432063: step: 1316/530, loss: 0.0035178440157324076
2023-01-24 09:34:52.531445: step: 1320/530, loss: 0.0018739523366093636
2023-01-24 09:34:53.606703: step: 1324/530, loss: 0.0007567688589915633
2023-01-24 09:34:54.679119: step: 1328/530, loss: 0.006811899598687887
2023-01-24 09:34:55.742656: step: 1332/530, loss: 0.004004851449280977
2023-01-24 09:34:56.840133: step: 1336/530, loss: 0.004442003555595875
2023-01-24 09:34:57.951234: step: 1340/530, loss: 0.015975134447216988
2023-01-24 09:34:59.038350: step: 1344/530, loss: 0.0005995518295094371
2023-01-24 09:35:00.140376: step: 1348/530, loss: 0.0031597898341715336
2023-01-24 09:35:01.238131: step: 1352/530, loss: 0.004254691768437624
2023-01-24 09:35:02.344077: step: 1356/530, loss: 0.00034919148311018944
2023-01-24 09:35:03.435233: step: 1360/530, loss: 0.011843032203614712
2023-01-24 09:35:04.508297: step: 1364/530, loss: 0.0016121385851874948
2023-01-24 09:35:05.596851: step: 1368/530, loss: 0.0023107873275876045
2023-01-24 09:35:06.682777: step: 1372/530, loss: 0.0034817068371921778
2023-01-24 09:35:07.781797: step: 1376/530, loss: 0.002137373900040984
2023-01-24 09:35:08.865803: step: 1380/530, loss: 7.509499846491963e-05
2023-01-24 09:35:09.956235: step: 1384/530, loss: 0.004698347765952349
2023-01-24 09:35:11.044154: step: 1388/530, loss: 0.00018029357306659222
2023-01-24 09:35:12.131622: step: 1392/530, loss: 1.0746311090770178e-05
2023-01-24 09:35:13.200374: step: 1396/530, loss: 0.0019366234773769975
2023-01-24 09:35:14.285422: step: 1400/530, loss: 0.0004704426391981542
2023-01-24 09:35:15.365717: step: 1404/530, loss: 0.00199788436293602
2023-01-24 09:35:16.465714: step: 1408/530, loss: 0.0003137617895845324
2023-01-24 09:35:17.531380: step: 1412/530, loss: 0.0022457896266132593
2023-01-24 09:35:18.634437: step: 1416/530, loss: 0.00045267504174262285
2023-01-24 09:35:19.724783: step: 1420/530, loss: 0.0009092573309317231
2023-01-24 09:35:20.814057: step: 1424/530, loss: 0.0020866524428129196
2023-01-24 09:35:21.904814: step: 1428/530, loss: 0.0017698314040899277
2023-01-24 09:35:22.979064: step: 1432/530, loss: 0.013435174711048603
2023-01-24 09:35:24.079675: step: 1436/530, loss: 0.001993982819840312
2023-01-24 09:35:25.173760: step: 1440/530, loss: 0.011218621395528316
2023-01-24 09:35:26.274754: step: 1444/530, loss: 0.0002953499788418412
2023-01-24 09:35:27.382852: step: 1448/530, loss: 0.011713948100805283
2023-01-24 09:35:28.456586: step: 1452/530, loss: 0.0015478963032364845
2023-01-24 09:35:29.553827: step: 1456/530, loss: 0.0025427218060940504
2023-01-24 09:35:30.650904: step: 1460/530, loss: 0.0034042673651129007
2023-01-24 09:35:31.753542: step: 1464/530, loss: 0.0023622673470526934
2023-01-24 09:35:32.831013: step: 1468/530, loss: 0.0025987448170781136
2023-01-24 09:35:33.958881: step: 1472/530, loss: 0.0009625330567359924
2023-01-24 09:35:35.043507: step: 1476/530, loss: 0.002376854419708252
2023-01-24 09:35:36.128408: step: 1480/530, loss: 0.012599444016814232
2023-01-24 09:35:37.214634: step: 1484/530, loss: 0.00047750273370184004
2023-01-24 09:35:38.314800: step: 1488/530, loss: 0.001846915460191667
2023-01-24 09:35:39.395537: step: 1492/530, loss: 0.006273969076573849
2023-01-24 09:35:40.497265: step: 1496/530, loss: 0.001010268577374518
2023-01-24 09:35:41.598910: step: 1500/530, loss: 0.006716223433613777
2023-01-24 09:35:42.670805: step: 1504/530, loss: 0.008409428410232067
2023-01-24 09:35:43.762496: step: 1508/530, loss: 0.004951608367264271
2023-01-24 09:35:44.860234: step: 1512/530, loss: 0.000355736498022452
2023-01-24 09:35:45.942916: step: 1516/530, loss: 0.0029275112319737673
2023-01-24 09:35:47.029969: step: 1520/530, loss: 0.005963629111647606
2023-01-24 09:35:48.134377: step: 1524/530, loss: 0.0038211403880268335
2023-01-24 09:35:49.218744: step: 1528/530, loss: 0.001565816579386592
2023-01-24 09:35:50.310825: step: 1532/530, loss: 0.012257400900125504
2023-01-24 09:35:51.405527: step: 1536/530, loss: 0.01185611356049776
2023-01-24 09:35:52.476554: step: 1540/530, loss: 0.0008904370479285717
2023-01-24 09:35:53.547215: step: 1544/530, loss: 0.00985379982739687
2023-01-24 09:35:54.598204: step: 1548/530, loss: 0.0004087619890924543
2023-01-24 09:35:55.696213: step: 1552/530, loss: 0.005597870796918869
2023-01-24 09:35:56.772140: step: 1556/530, loss: 0.015355966053903103
2023-01-24 09:35:57.892523: step: 1560/530, loss: 0.0043082330375909805
2023-01-24 09:35:58.985252: step: 1564/530, loss: 0.004766838625073433
2023-01-24 09:36:00.063274: step: 1568/530, loss: 0.00024223816581070423
2023-01-24 09:36:01.158958: step: 1572/530, loss: 0.006220538634806871
2023-01-24 09:36:02.254936: step: 1576/530, loss: 0.00019033053831662983
2023-01-24 09:36:03.337255: step: 1580/530, loss: 0.0019313825760036707
2023-01-24 09:36:04.408271: step: 1584/530, loss: 0.01158900000154972
2023-01-24 09:36:05.502966: step: 1588/530, loss: 0.009623370133340359
2023-01-24 09:36:06.586388: step: 1592/530, loss: 0.006437897682189941
2023-01-24 09:36:07.669513: step: 1596/530, loss: 0.0010151652386412024
2023-01-24 09:36:08.753899: step: 1600/530, loss: 0.004753860179334879
2023-01-24 09:36:09.837768: step: 1604/530, loss: 0.01348473783582449
2023-01-24 09:36:10.950738: step: 1608/530, loss: 0.002250124467536807
2023-01-24 09:36:12.047102: step: 1612/530, loss: 0.007330153603106737
2023-01-24 09:36:13.153805: step: 1616/530, loss: 0.007058130577206612
2023-01-24 09:36:14.250655: step: 1620/530, loss: 0.0014252610271796584
2023-01-24 09:36:15.327741: step: 1624/530, loss: 0.007356412708759308
2023-01-24 09:36:16.412748: step: 1628/530, loss: 0.00017888860020320863
2023-01-24 09:36:17.499851: step: 1632/530, loss: 0.0006667135166935623
2023-01-24 09:36:18.577352: step: 1636/530, loss: 0.011095312424004078
2023-01-24 09:36:19.670224: step: 1640/530, loss: 0.002226361073553562
2023-01-24 09:36:20.772324: step: 1644/530, loss: 0.01689758151769638
2023-01-24 09:36:21.856631: step: 1648/530, loss: 0.0012102712644264102
2023-01-24 09:36:22.946100: step: 1652/530, loss: 8.18850749055855e-05
2023-01-24 09:36:24.037376: step: 1656/530, loss: 1.2423811313055921e-05
2023-01-24 09:36:25.123501: step: 1660/530, loss: 0.003003004938364029
2023-01-24 09:36:26.234732: step: 1664/530, loss: 0.005219044629484415
2023-01-24 09:36:27.330227: step: 1668/530, loss: 0.020767422392964363
2023-01-24 09:36:28.420734: step: 1672/530, loss: 0.003036527195945382
2023-01-24 09:36:29.494270: step: 1676/530, loss: 1.7686797946225852e-06
2023-01-24 09:36:30.584569: step: 1680/530, loss: 0.007433051709085703
2023-01-24 09:36:31.664158: step: 1684/530, loss: 0.029139313846826553
2023-01-24 09:36:32.804891: step: 1688/530, loss: 0.0010811605025082827
2023-01-24 09:36:33.933053: step: 1692/530, loss: 0.011061285622417927
2023-01-24 09:36:35.018796: step: 1696/530, loss: 0.02029518224298954
2023-01-24 09:36:36.127382: step: 1700/530, loss: 0.00505274161696434
2023-01-24 09:36:37.242304: step: 1704/530, loss: 0.00032734230626374483
2023-01-24 09:36:38.336615: step: 1708/530, loss: 0.009157164953649044
2023-01-24 09:36:39.448682: step: 1712/530, loss: 0.0028398402500897646
2023-01-24 09:36:40.530753: step: 1716/530, loss: 0.017813021317124367
2023-01-24 09:36:41.621938: step: 1720/530, loss: 0.002479216083884239
2023-01-24 09:36:42.727475: step: 1724/530, loss: 0.01330887246876955
2023-01-24 09:36:43.810146: step: 1728/530, loss: 0.019950294867157936
2023-01-24 09:36:44.928000: step: 1732/530, loss: 0.006393796298652887
2023-01-24 09:36:46.011657: step: 1736/530, loss: 0.0022322724107652903
2023-01-24 09:36:47.115454: step: 1740/530, loss: 0.008349602110683918
2023-01-24 09:36:48.203818: step: 1744/530, loss: 0.006456011440604925
2023-01-24 09:36:49.311556: step: 1748/530, loss: 0.005218730308115482
2023-01-24 09:36:50.417945: step: 1752/530, loss: 0.0004118007782381028
2023-01-24 09:36:51.513598: step: 1756/530, loss: 7.621573604410514e-05
2023-01-24 09:36:52.616598: step: 1760/530, loss: 4.565552080748603e-05
2023-01-24 09:36:53.700308: step: 1764/530, loss: 0.002926686080172658
2023-01-24 09:36:54.798479: step: 1768/530, loss: 0.015068943612277508
2023-01-24 09:36:55.887581: step: 1772/530, loss: 0.0015271228039637208
2023-01-24 09:36:56.966600: step: 1776/530, loss: 0.0038208412006497383
2023-01-24 09:36:58.052491: step: 1780/530, loss: 0.004268140997737646
2023-01-24 09:36:59.140379: step: 1784/530, loss: 0.0007785434718243778
2023-01-24 09:37:00.220183: step: 1788/530, loss: 0.0037303471472114325
2023-01-24 09:37:01.319756: step: 1792/530, loss: 0.005979621782898903
2023-01-24 09:37:02.430048: step: 1796/530, loss: 0.002793046645820141
2023-01-24 09:37:03.522232: step: 1800/530, loss: 0.012062052264809608
2023-01-24 09:37:04.607524: step: 1804/530, loss: 0.0011541249696165323
2023-01-24 09:37:05.725006: step: 1808/530, loss: 0.007963895797729492
2023-01-24 09:37:06.822146: step: 1812/530, loss: 0.0011873121839016676
2023-01-24 09:37:07.918262: step: 1816/530, loss: 0.007192743010818958
2023-01-24 09:37:09.007987: step: 1820/530, loss: 0.0008395753684453666
2023-01-24 09:37:10.081016: step: 1824/530, loss: 0.00234224577434361
2023-01-24 09:37:11.170541: step: 1828/530, loss: 0.0017208369681611657
2023-01-24 09:37:12.298110: step: 1832/530, loss: 0.002837186912074685
2023-01-24 09:37:13.404686: step: 1836/530, loss: 0.0008313122089020908
2023-01-24 09:37:14.488258: step: 1840/530, loss: 0.00895564816892147
2023-01-24 09:37:15.612875: step: 1844/530, loss: 0.0036113779060542583
2023-01-24 09:37:16.701300: step: 1848/530, loss: 0.007410169579088688
2023-01-24 09:37:17.789887: step: 1852/530, loss: 0.007057948503643274
2023-01-24 09:37:18.883239: step: 1856/530, loss: 0.007463072892278433
2023-01-24 09:37:19.972078: step: 1860/530, loss: 0.00016262877034023404
2023-01-24 09:37:21.067779: step: 1864/530, loss: 0.0015687368577346206
2023-01-24 09:37:22.151452: step: 1868/530, loss: 0.0016334542306140065
2023-01-24 09:37:23.219699: step: 1872/530, loss: 0.016074128448963165
2023-01-24 09:37:24.329567: step: 1876/530, loss: 0.00044986631837673485
2023-01-24 09:37:25.411227: step: 1880/530, loss: 0.019057132303714752
2023-01-24 09:37:26.505987: step: 1884/530, loss: 0.012813219800591469
2023-01-24 09:37:27.566287: step: 1888/530, loss: 0.0030455824453383684
2023-01-24 09:37:28.665791: step: 1892/530, loss: 0.003639615373685956
2023-01-24 09:37:29.752420: step: 1896/530, loss: 0.010136867873370647
2023-01-24 09:37:30.841681: step: 1900/530, loss: 0.0009270050213672221
2023-01-24 09:37:31.954209: step: 1904/530, loss: 0.0039407857693731785
2023-01-24 09:37:33.038840: step: 1908/530, loss: 0.007624221034348011
2023-01-24 09:37:34.107092: step: 1912/530, loss: 0.00032158478279598057
2023-01-24 09:37:35.199319: step: 1916/530, loss: 0.001729368232190609
2023-01-24 09:37:36.287476: step: 1920/530, loss: 0.0038076473865658045
2023-01-24 09:37:37.368284: step: 1924/530, loss: 0.014754346571862698
2023-01-24 09:37:38.443607: step: 1928/530, loss: 0.001312493928708136
2023-01-24 09:37:39.525172: step: 1932/530, loss: 0.0017326330998912454
2023-01-24 09:37:40.620758: step: 1936/530, loss: 0.0005827595014125109
2023-01-24 09:37:41.706916: step: 1940/530, loss: 0.023289987817406654
2023-01-24 09:37:42.819252: step: 1944/530, loss: 0.005664709024131298
2023-01-24 09:37:43.917550: step: 1948/530, loss: 0.003145907074213028
2023-01-24 09:37:45.004855: step: 1952/530, loss: 0.002479083836078644
2023-01-24 09:37:46.097566: step: 1956/530, loss: 0.0008014517952688038
2023-01-24 09:37:47.189861: step: 1960/530, loss: 0.004337603226304054
2023-01-24 09:37:48.291661: step: 1964/530, loss: 0.00604652613401413
2023-01-24 09:37:49.387249: step: 1968/530, loss: 0.003832897637039423
2023-01-24 09:37:50.493658: step: 1972/530, loss: 0.0075946287252008915
2023-01-24 09:37:51.564503: step: 1976/530, loss: 0.009812133386731148
2023-01-24 09:37:52.695980: step: 1980/530, loss: 0.007179032079875469
2023-01-24 09:37:53.786719: step: 1984/530, loss: 0.0017271579708904028
2023-01-24 09:37:54.905130: step: 1988/530, loss: 0.0038227015174925327
2023-01-24 09:37:56.000389: step: 1992/530, loss: 7.549358997493982e-05
2023-01-24 09:37:57.102937: step: 1996/530, loss: 6.163866714814503e-07
2023-01-24 09:37:58.191298: step: 2000/530, loss: 0.010236179456114769
2023-01-24 09:37:59.285556: step: 2004/530, loss: 0.005936293862760067
2023-01-24 09:38:00.371956: step: 2008/530, loss: 0.0025672833435237408
2023-01-24 09:38:01.462425: step: 2012/530, loss: 0.0037847773637622595
2023-01-24 09:38:02.544409: step: 2016/530, loss: 0.00466605881229043
2023-01-24 09:38:03.633131: step: 2020/530, loss: 0.0016953644808381796
2023-01-24 09:38:04.728919: step: 2024/530, loss: 0.014948712661862373
2023-01-24 09:38:05.810661: step: 2028/530, loss: 0.0059296446852386
2023-01-24 09:38:06.887407: step: 2032/530, loss: 0.001659872941672802
2023-01-24 09:38:07.995495: step: 2036/530, loss: 0.0009222202352248132
2023-01-24 09:38:09.074731: step: 2040/530, loss: 0.006768266204744577
2023-01-24 09:38:10.172146: step: 2044/530, loss: 0.003870441345497966
2023-01-24 09:38:11.288665: step: 2048/530, loss: 0.0004518051282502711
2023-01-24 09:38:12.415485: step: 2052/530, loss: 0.0002215412532677874
2023-01-24 09:38:13.498585: step: 2056/530, loss: 0.004906861577183008
2023-01-24 09:38:14.582845: step: 2060/530, loss: 0.0025891445111483335
2023-01-24 09:38:15.644844: step: 2064/530, loss: 0.012634353712201118
2023-01-24 09:38:16.726808: step: 2068/530, loss: 0.009332558140158653
2023-01-24 09:38:17.802102: step: 2072/530, loss: 0.004877055063843727
2023-01-24 09:38:18.895816: step: 2076/530, loss: 0.002650513779371977
2023-01-24 09:38:19.986613: step: 2080/530, loss: 0.0016186363063752651
2023-01-24 09:38:21.075012: step: 2084/530, loss: 0.07312414795160294
2023-01-24 09:38:22.173857: step: 2088/530, loss: 0.003823396749794483
2023-01-24 09:38:23.258447: step: 2092/530, loss: 0.00966161023825407
2023-01-24 09:38:24.350185: step: 2096/530, loss: 0.002313487231731415
2023-01-24 09:38:25.429265: step: 2100/530, loss: 0.0001693515368970111
2023-01-24 09:38:26.519713: step: 2104/530, loss: 0.010704522021114826
2023-01-24 09:38:27.606304: step: 2108/530, loss: 0.00025611446471884847
2023-01-24 09:38:28.712534: step: 2112/530, loss: 0.004219945054501295
2023-01-24 09:38:29.805723: step: 2116/530, loss: 0.0009405352175235748
2023-01-24 09:38:30.884568: step: 2120/530, loss: 0.004256460350006819
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35149272080978367, 'r': 0.34815787526130376, 'f1': 0.3498173503578781}, 'combined': 0.2577601528952786, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.347652879551281, 'r': 0.27647172617134513, 'f1': 0.30800321229667205}, 'combined': 0.19128620553161738, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3858757194920892, 'r': 0.32876318415929423, 'f1': 0.3550372910900575}, 'combined': 0.26160642501372655, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3369470357934729, 'r': 0.2636976801861962, 'f1': 0.29585593386743964}, 'combined': 0.1837421062966204, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37727603010831046, 'r': 0.32501578305345913, 'f1': 0.3492014631379673}, 'combined': 0.2573063412595548, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34798621281976616, 'r': 0.2706941122428191, 'f1': 0.3045120885085794}, 'combined': 0.1891180339158546, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 09:40:57.886466: step: 4/530, loss: 0.0013282769359648228
2023-01-24 09:40:58.992310: step: 8/530, loss: 0.0007166077848523855
2023-01-24 09:41:00.083836: step: 12/530, loss: 0.0026112738996744156
2023-01-24 09:41:01.151807: step: 16/530, loss: 0.002682651858776808
2023-01-24 09:41:02.229384: step: 20/530, loss: 0.011102957651019096
2023-01-24 09:41:03.328692: step: 24/530, loss: 0.006892113015055656
2023-01-24 09:41:04.436503: step: 28/530, loss: 0.012931205332279205
2023-01-24 09:41:05.510370: step: 32/530, loss: 0.0017117051174864173
2023-01-24 09:41:06.574820: step: 36/530, loss: 0.004092513117939234
2023-01-24 09:41:07.644489: step: 40/530, loss: 0.009882969781756401
2023-01-24 09:41:08.746867: step: 44/530, loss: 0.0014846251579001546
2023-01-24 09:41:09.822981: step: 48/530, loss: 0.00927084218710661
2023-01-24 09:41:10.928338: step: 52/530, loss: 0.004552260506898165
2023-01-24 09:41:12.037269: step: 56/530, loss: 0.0007692054496146739
2023-01-24 09:41:13.134848: step: 60/530, loss: 0.00425350246950984
2023-01-24 09:41:14.237523: step: 64/530, loss: 0.0004158757801633328
2023-01-24 09:41:15.330468: step: 68/530, loss: 0.022751739248633385
2023-01-24 09:41:16.443339: step: 72/530, loss: 0.008947727270424366
2023-01-24 09:41:17.524435: step: 76/530, loss: 0.0019416005816310644
2023-01-24 09:41:18.610794: step: 80/530, loss: 0.004187324084341526
2023-01-24 09:41:19.694939: step: 84/530, loss: 0.004844694398343563
2023-01-24 09:41:20.784219: step: 88/530, loss: 0.0013403381453827024
2023-01-24 09:41:21.887331: step: 92/530, loss: 0.003545124549418688
2023-01-24 09:41:22.961586: step: 96/530, loss: 0.003108375705778599
2023-01-24 09:41:24.059628: step: 100/530, loss: 0.0016596417408436537
2023-01-24 09:41:25.156458: step: 104/530, loss: 0.007822801358997822
2023-01-24 09:41:26.287174: step: 108/530, loss: 0.00777782266959548
2023-01-24 09:41:27.369177: step: 112/530, loss: 0.0015431058127433062
2023-01-24 09:41:28.459435: step: 116/530, loss: 0.0021872520446777344
2023-01-24 09:41:29.529864: step: 120/530, loss: 0.0036428936291486025
2023-01-24 09:41:30.628564: step: 124/530, loss: 0.005377375520765781
2023-01-24 09:41:31.711937: step: 128/530, loss: 0.0025357420090585947
2023-01-24 09:41:32.807301: step: 132/530, loss: 0.02607816830277443
2023-01-24 09:41:33.892277: step: 136/530, loss: 0.013520168140530586
2023-01-24 09:41:34.982941: step: 140/530, loss: 0.004857353866100311
2023-01-24 09:41:36.057455: step: 144/530, loss: 0.008640473708510399
2023-01-24 09:41:37.144716: step: 148/530, loss: 0.00011588572670007125
2023-01-24 09:41:38.214387: step: 152/530, loss: 0.02487765997648239
2023-01-24 09:41:39.309043: step: 156/530, loss: 0.0005496989469975233
2023-01-24 09:41:40.416279: step: 160/530, loss: 0.1543724536895752
2023-01-24 09:41:41.496114: step: 164/530, loss: 0.03956758230924606
2023-01-24 09:41:42.572174: step: 168/530, loss: 0.0032563696149736643
2023-01-24 09:41:43.644541: step: 172/530, loss: 0.0015266978880390525
2023-01-24 09:41:44.740569: step: 176/530, loss: 0.0021048292983323336
2023-01-24 09:41:45.821631: step: 180/530, loss: 0.004921151790767908
2023-01-24 09:41:46.932027: step: 184/530, loss: 0.005682270508259535
2023-01-24 09:41:48.021339: step: 188/530, loss: 0.0022502427455037832
2023-01-24 09:41:49.107685: step: 192/530, loss: 1.6228532331297174e-05
2023-01-24 09:41:50.214894: step: 196/530, loss: 0.0027154642157256603
2023-01-24 09:41:51.313065: step: 200/530, loss: 0.002484674099832773
2023-01-24 09:41:52.402030: step: 204/530, loss: 0.0002948844921775162
2023-01-24 09:41:53.515477: step: 208/530, loss: 0.0031943190842866898
2023-01-24 09:41:54.591123: step: 212/530, loss: 8.710770634934306e-05
2023-01-24 09:41:55.690429: step: 216/530, loss: 0.0020512444898486137
2023-01-24 09:41:56.775759: step: 220/530, loss: 0.017200758680701256
2023-01-24 09:41:57.854065: step: 224/530, loss: 0.01049842406064272
2023-01-24 09:41:58.956693: step: 228/530, loss: 0.0007387291407212615
2023-01-24 09:42:00.056719: step: 232/530, loss: 0.000985565478913486
2023-01-24 09:42:01.141608: step: 236/530, loss: 0.0007848618552088737
2023-01-24 09:42:02.245330: step: 240/530, loss: 0.001021631876938045
2023-01-24 09:42:03.321430: step: 244/530, loss: 0.000648330373223871
2023-01-24 09:42:04.384748: step: 248/530, loss: 0.004050981253385544
2023-01-24 09:42:05.447333: step: 252/530, loss: 0.0004885526141151786
2023-01-24 09:42:06.531297: step: 256/530, loss: 0.0004767110222019255
2023-01-24 09:42:07.614053: step: 260/530, loss: 0.0030144068878144026
2023-01-24 09:42:08.701204: step: 264/530, loss: 0.004344135522842407
2023-01-24 09:42:09.809311: step: 268/530, loss: 0.008200027979910374
2023-01-24 09:42:10.874271: step: 272/530, loss: 0.001755343982949853
2023-01-24 09:42:11.976626: step: 276/530, loss: 0.010060666128993034
2023-01-24 09:42:13.090374: step: 280/530, loss: 0.003028949024155736
2023-01-24 09:42:14.169257: step: 284/530, loss: 0.0060416641645133495
2023-01-24 09:42:15.257347: step: 288/530, loss: 0.000583796645514667
2023-01-24 09:42:16.348018: step: 292/530, loss: 0.005627032835036516
2023-01-24 09:42:17.427830: step: 296/530, loss: 0.0018009231425821781
2023-01-24 09:42:18.521062: step: 300/530, loss: 0.0006026829360052943
2023-01-24 09:42:19.610674: step: 304/530, loss: 0.001971691381186247
2023-01-24 09:42:20.727721: step: 308/530, loss: 0.0015901505248621106
2023-01-24 09:42:21.816056: step: 312/530, loss: 0.005434457678347826
2023-01-24 09:42:22.906200: step: 316/530, loss: 0.003684228053316474
2023-01-24 09:42:24.013781: step: 320/530, loss: 0.0007053037988953292
2023-01-24 09:42:25.102060: step: 324/530, loss: 0.004026405513286591
2023-01-24 09:42:26.199572: step: 328/530, loss: 0.008272100239992142
2023-01-24 09:42:27.289467: step: 332/530, loss: 0.0007523755193687975
2023-01-24 09:42:28.391851: step: 336/530, loss: 0.0008887725416570902
2023-01-24 09:42:29.478417: step: 340/530, loss: 0.0002869265154004097
2023-01-24 09:42:30.551450: step: 344/530, loss: 0.001409532269462943
2023-01-24 09:42:31.638870: step: 348/530, loss: 0.0014691234100610018
2023-01-24 09:42:32.722682: step: 352/530, loss: 0.003308819606900215
2023-01-24 09:42:33.806508: step: 356/530, loss: 0.0070055099204182625
2023-01-24 09:42:34.896079: step: 360/530, loss: 0.003059013281017542
2023-01-24 09:42:36.003017: step: 364/530, loss: 0.007416489068418741
2023-01-24 09:42:37.077792: step: 368/530, loss: 0.0035310243256390095
2023-01-24 09:42:38.170490: step: 372/530, loss: 0.0044801486656069756
2023-01-24 09:42:39.261771: step: 376/530, loss: 0.005069028586149216
2023-01-24 09:42:40.358060: step: 380/530, loss: 0.002067211549729109
2023-01-24 09:42:41.443754: step: 384/530, loss: 0.003478986443951726
2023-01-24 09:42:42.542227: step: 388/530, loss: 0.01598384976387024
2023-01-24 09:42:43.634877: step: 392/530, loss: 0.00575635302811861
2023-01-24 09:42:44.726918: step: 396/530, loss: 0.002196107292547822
2023-01-24 09:42:45.842740: step: 400/530, loss: 0.0021438344847410917
2023-01-24 09:42:46.951663: step: 404/530, loss: 0.006238223053514957
2023-01-24 09:42:48.067718: step: 408/530, loss: 0.007764538284391165
2023-01-24 09:42:49.172771: step: 412/530, loss: 0.0026912125758826733
2023-01-24 09:42:50.274314: step: 416/530, loss: 0.010484520345926285
2023-01-24 09:42:51.372762: step: 420/530, loss: 5.424030314316042e-05
2023-01-24 09:42:52.463621: step: 424/530, loss: 0.0010154732735827565
2023-01-24 09:42:53.547934: step: 428/530, loss: 0.002305225934833288
2023-01-24 09:42:54.658642: step: 432/530, loss: 0.0016883363714441657
2023-01-24 09:42:55.739645: step: 436/530, loss: 0.0029265927150845528
2023-01-24 09:42:56.823069: step: 440/530, loss: 0.0022073877044022083
2023-01-24 09:42:57.908213: step: 444/530, loss: 0.0016494240844622254
2023-01-24 09:42:58.981827: step: 448/530, loss: 0.0059205531142652035
2023-01-24 09:43:00.100934: step: 452/530, loss: 0.00023701814643573016
2023-01-24 09:43:01.178909: step: 456/530, loss: 0.0005892252665944397
2023-01-24 09:43:02.264453: step: 460/530, loss: 0.006177544128149748
2023-01-24 09:43:03.369455: step: 464/530, loss: 0.0038924363907426596
2023-01-24 09:43:04.472290: step: 468/530, loss: 0.005065560340881348
2023-01-24 09:43:05.584868: step: 472/530, loss: 0.007990981452167034
2023-01-24 09:43:06.665341: step: 476/530, loss: 0.0005420101806521416
2023-01-24 09:43:07.744068: step: 480/530, loss: 0.0004488943668548018
2023-01-24 09:43:08.800438: step: 484/530, loss: 0.003811345435678959
2023-01-24 09:43:09.901130: step: 488/530, loss: 0.00531365629285574
2023-01-24 09:43:11.030842: step: 492/530, loss: 0.004253334831446409
2023-01-24 09:43:12.172931: step: 496/530, loss: 0.0015755154890939593
2023-01-24 09:43:13.279572: step: 500/530, loss: 0.003367781639099121
2023-01-24 09:43:14.381214: step: 504/530, loss: 0.006671552546322346
2023-01-24 09:43:15.480968: step: 508/530, loss: 0.005226884502917528
2023-01-24 09:43:16.600668: step: 512/530, loss: 0.024795377627015114
2023-01-24 09:43:17.694056: step: 516/530, loss: 2.29196803047671e-06
2023-01-24 09:43:18.799593: step: 520/530, loss: 0.011250624433159828
2023-01-24 09:43:19.898735: step: 524/530, loss: 0.003432190278545022
2023-01-24 09:43:21.002097: step: 528/530, loss: 0.009041900746524334
2023-01-24 09:43:22.091590: step: 532/530, loss: 3.596556416596286e-05
2023-01-24 09:43:23.171696: step: 536/530, loss: 0.011411798186600208
2023-01-24 09:43:24.287697: step: 540/530, loss: 0.004180583171546459
2023-01-24 09:43:25.349139: step: 544/530, loss: 5.783369124401361e-05
2023-01-24 09:43:26.439475: step: 548/530, loss: 0.011810092255473137
2023-01-24 09:43:27.550660: step: 552/530, loss: 0.0012022400042042136
2023-01-24 09:43:28.652122: step: 556/530, loss: 0.0031371568329632282
2023-01-24 09:43:29.766226: step: 560/530, loss: 0.0029107872396707535
2023-01-24 09:43:30.865809: step: 564/530, loss: 0.00022597539646085352
2023-01-24 09:43:31.964059: step: 568/530, loss: 0.0030135330744087696
2023-01-24 09:43:33.046323: step: 572/530, loss: 0.00741279823705554
2023-01-24 09:43:34.151953: step: 576/530, loss: 0.007068963255733252
2023-01-24 09:43:35.252901: step: 580/530, loss: 0.00439951429143548
2023-01-24 09:43:36.349661: step: 584/530, loss: 0.0007739784196019173
2023-01-24 09:43:37.451136: step: 588/530, loss: 0.009545059874653816
2023-01-24 09:43:38.532466: step: 592/530, loss: 0.02392938733100891
2023-01-24 09:43:39.615686: step: 596/530, loss: 0.0012618659529834986
2023-01-24 09:43:40.715062: step: 600/530, loss: 0.002825401956215501
2023-01-24 09:43:41.825214: step: 604/530, loss: 0.003480615559965372
2023-01-24 09:43:42.917877: step: 608/530, loss: 0.011056671850383282
2023-01-24 09:43:44.003285: step: 612/530, loss: 5.0333917897660285e-05
2023-01-24 09:43:45.095304: step: 616/530, loss: 0.012612312100827694
2023-01-24 09:43:46.185908: step: 620/530, loss: 0.0015372501220554113
2023-01-24 09:43:47.285356: step: 624/530, loss: 0.0004818023007828742
2023-01-24 09:43:48.362047: step: 628/530, loss: 0.012534980662167072
2023-01-24 09:43:49.489727: step: 632/530, loss: 0.0032857495825737715
2023-01-24 09:43:50.577443: step: 636/530, loss: 0.0020048515871167183
2023-01-24 09:43:51.658396: step: 640/530, loss: 0.0015880591236054897
2023-01-24 09:43:52.750701: step: 644/530, loss: 0.001628233352676034
2023-01-24 09:43:53.845923: step: 648/530, loss: 0.008483968675136566
2023-01-24 09:43:54.936467: step: 652/530, loss: 0.0010150448651984334
2023-01-24 09:43:56.018763: step: 656/530, loss: 0.0006647915579378605
2023-01-24 09:43:57.106222: step: 660/530, loss: 0.004456573165953159
2023-01-24 09:43:58.185316: step: 664/530, loss: 0.0014632751699537039
2023-01-24 09:43:59.268217: step: 668/530, loss: 0.00010278318222844973
2023-01-24 09:44:00.353461: step: 672/530, loss: 0.0002867642615456134
2023-01-24 09:44:01.429932: step: 676/530, loss: 0.0008807194535620511
2023-01-24 09:44:02.518754: step: 680/530, loss: 0.006089372094720602
2023-01-24 09:44:03.600826: step: 684/530, loss: 0.012407553382217884
2023-01-24 09:44:04.675445: step: 688/530, loss: 0.0006447809282690287
2023-01-24 09:44:05.748758: step: 692/530, loss: 0.0009658485651016235
2023-01-24 09:44:06.809523: step: 696/530, loss: 0.00035205602762289345
2023-01-24 09:44:07.904481: step: 700/530, loss: 0.001657846150919795
2023-01-24 09:44:09.012748: step: 704/530, loss: 3.839066994260065e-05
2023-01-24 09:44:10.113500: step: 708/530, loss: 0.002620797138661146
2023-01-24 09:44:11.193938: step: 712/530, loss: 0.01476196013391018
2023-01-24 09:44:12.279602: step: 716/530, loss: 0.014402851462364197
2023-01-24 09:44:13.377569: step: 720/530, loss: 0.00914725847542286
2023-01-24 09:44:14.500778: step: 724/530, loss: 0.0015775400679558516
2023-01-24 09:44:15.579338: step: 728/530, loss: 0.011741344816982746
2023-01-24 09:44:16.676838: step: 732/530, loss: 0.008535072207450867
2023-01-24 09:44:17.744990: step: 736/530, loss: 0.00040210349834524095
2023-01-24 09:44:18.858437: step: 740/530, loss: 0.01881117932498455
2023-01-24 09:44:19.947915: step: 744/530, loss: 0.0036962665617465973
2023-01-24 09:44:21.052060: step: 748/530, loss: 0.0022431055549532175
2023-01-24 09:44:22.160477: step: 752/530, loss: 0.002346399240195751
2023-01-24 09:44:23.263394: step: 756/530, loss: 3.1254390364665596e-07
2023-01-24 09:44:24.352792: step: 760/530, loss: 0.000602013140451163
2023-01-24 09:44:25.431457: step: 764/530, loss: 0.008635367266833782
2023-01-24 09:44:26.524386: step: 768/530, loss: 0.0007458119071088731
2023-01-24 09:44:27.616271: step: 772/530, loss: 0.019908368587493896
2023-01-24 09:44:28.720573: step: 776/530, loss: 0.005076912697404623
2023-01-24 09:44:29.799004: step: 780/530, loss: 0.005201888270676136
2023-01-24 09:44:30.905687: step: 784/530, loss: 0.023236414417624474
2023-01-24 09:44:32.003409: step: 788/530, loss: 0.005887606181204319
2023-01-24 09:44:33.111282: step: 792/530, loss: 0.00021235259191598743
2023-01-24 09:44:34.206987: step: 796/530, loss: 0.00024718864005990326
2023-01-24 09:44:35.320251: step: 800/530, loss: 0.0196321252733469
2023-01-24 09:44:36.405845: step: 804/530, loss: 0.0012177644530311227
2023-01-24 09:44:37.499479: step: 808/530, loss: 0.0032924406696110964
2023-01-24 09:44:38.572151: step: 812/530, loss: 0.00010472331632627174
2023-01-24 09:44:39.678525: step: 816/530, loss: 0.003384908428415656
2023-01-24 09:44:40.766213: step: 820/530, loss: 0.006923796609044075
2023-01-24 09:44:41.870928: step: 824/530, loss: 0.0029404230881482363
2023-01-24 09:44:42.962559: step: 828/530, loss: 0.003901845309883356
2023-01-24 09:44:44.062511: step: 832/530, loss: 0.0022908365353941917
2023-01-24 09:44:45.152298: step: 836/530, loss: 0.004797129426151514
2023-01-24 09:44:46.243152: step: 840/530, loss: 0.004384325817227364
2023-01-24 09:44:47.331645: step: 844/530, loss: 0.00028739136178046465
2023-01-24 09:44:48.435260: step: 848/530, loss: 0.00015839732077438384
2023-01-24 09:44:49.531460: step: 852/530, loss: 0.003454955294728279
2023-01-24 09:44:50.642281: step: 856/530, loss: 0.01841742917895317
2023-01-24 09:44:51.726654: step: 860/530, loss: 0.0020822861697524786
2023-01-24 09:44:52.825321: step: 864/530, loss: 0.007027497049421072
2023-01-24 09:44:53.932794: step: 868/530, loss: 0.0006082684849388897
2023-01-24 09:44:55.016667: step: 872/530, loss: 0.0018352603074163198
2023-01-24 09:44:56.120097: step: 876/530, loss: 0.004127270542085171
2023-01-24 09:44:57.215973: step: 880/530, loss: 0.001196317607536912
2023-01-24 09:44:58.312918: step: 884/530, loss: 0.005441926419734955
2023-01-24 09:44:59.390218: step: 888/530, loss: 0.005609191954135895
2023-01-24 09:45:00.473014: step: 892/530, loss: 0.0005249209934845567
2023-01-24 09:45:01.570096: step: 896/530, loss: 0.0036400395911186934
2023-01-24 09:45:02.682715: step: 900/530, loss: 0.008705930784344673
2023-01-24 09:45:03.772839: step: 904/530, loss: 9.220934771292377e-06
2023-01-24 09:45:04.859256: step: 908/530, loss: 9.59230019361712e-05
2023-01-24 09:45:05.951694: step: 912/530, loss: 0.000316394871333614
2023-01-24 09:45:07.043355: step: 916/530, loss: 0.007739558815956116
2023-01-24 09:45:08.137597: step: 920/530, loss: 0.0030269413255155087
2023-01-24 09:45:09.224642: step: 924/530, loss: 0.0014082634588703513
2023-01-24 09:45:10.323983: step: 928/530, loss: 0.0033085395116358995
2023-01-24 09:45:11.392282: step: 932/530, loss: 4.4718261051457375e-05
2023-01-24 09:45:12.477180: step: 936/530, loss: 0.0029728920198976994
2023-01-24 09:45:13.567328: step: 940/530, loss: 0.00013389321975409985
2023-01-24 09:45:14.663019: step: 944/530, loss: 0.0038787336088716984
2023-01-24 09:45:15.763416: step: 948/530, loss: 0.024764133617281914
2023-01-24 09:45:16.867036: step: 952/530, loss: 0.002442519413307309
2023-01-24 09:45:17.940773: step: 956/530, loss: 0.00785348005592823
2023-01-24 09:45:19.039554: step: 960/530, loss: 0.00306137977167964
2023-01-24 09:45:20.130264: step: 964/530, loss: 0.0036833484191447496
2023-01-24 09:45:21.223175: step: 968/530, loss: 0.0027110674418509007
2023-01-24 09:45:22.314324: step: 972/530, loss: 0.0007943974924273789
2023-01-24 09:45:23.403208: step: 976/530, loss: 0.00847509317100048
2023-01-24 09:45:24.496059: step: 980/530, loss: 0.000861790613271296
2023-01-24 09:45:25.590093: step: 984/530, loss: 0.008168418891727924
2023-01-24 09:45:26.662482: step: 988/530, loss: 0.0033762722741812468
2023-01-24 09:45:27.733249: step: 992/530, loss: 0.0015345296123996377
2023-01-24 09:45:28.812987: step: 996/530, loss: 0.0008810081635601819
2023-01-24 09:45:29.893490: step: 1000/530, loss: 0.0014387140981853008
2023-01-24 09:45:30.973453: step: 1004/530, loss: 0.003929978236556053
2023-01-24 09:45:32.055085: step: 1008/530, loss: 0.0015910568181425333
2023-01-24 09:45:33.137570: step: 1012/530, loss: 5.263879575068131e-05
2023-01-24 09:45:34.234519: step: 1016/530, loss: 0.0036562897730618715
2023-01-24 09:45:35.329933: step: 1020/530, loss: 0.004044460132718086
2023-01-24 09:45:36.429360: step: 1024/530, loss: 0.0004481390060391277
2023-01-24 09:45:37.556052: step: 1028/530, loss: 0.005939308553934097
2023-01-24 09:45:38.640437: step: 1032/530, loss: 0.0025205567944794893
2023-01-24 09:45:39.763085: step: 1036/530, loss: 0.0003851708024740219
2023-01-24 09:45:40.859790: step: 1040/530, loss: 0.00394230242818594
2023-01-24 09:45:41.932453: step: 1044/530, loss: 0.000790725345723331
2023-01-24 09:45:43.019449: step: 1048/530, loss: 0.0006547352531924844
2023-01-24 09:45:44.113920: step: 1052/530, loss: 0.0002145062608178705
2023-01-24 09:45:45.202061: step: 1056/530, loss: 0.0035680169239640236
2023-01-24 09:45:46.284797: step: 1060/530, loss: 0.005521649960428476
2023-01-24 09:45:47.363223: step: 1064/530, loss: 0.006090599112212658
2023-01-24 09:45:48.455464: step: 1068/530, loss: 0.003495714860036969
2023-01-24 09:45:49.562802: step: 1072/530, loss: 0.0023991423659026623
2023-01-24 09:45:50.661485: step: 1076/530, loss: 0.011029968038201332
2023-01-24 09:45:51.747675: step: 1080/530, loss: 0.01628875732421875
2023-01-24 09:45:52.826310: step: 1084/530, loss: 0.0026841729413717985
2023-01-24 09:45:53.903265: step: 1088/530, loss: 0.004322941415011883
2023-01-24 09:45:54.993314: step: 1092/530, loss: 0.0005825699190609157
2023-01-24 09:45:56.081831: step: 1096/530, loss: 0.004924403969198465
2023-01-24 09:45:57.157410: step: 1100/530, loss: 0.0009734384948387742
2023-01-24 09:45:58.236039: step: 1104/530, loss: 0.003486888948827982
2023-01-24 09:45:59.302539: step: 1108/530, loss: 0.0007589052547700703
2023-01-24 09:46:00.384475: step: 1112/530, loss: 0.0017122741555795074
2023-01-24 09:46:01.457114: step: 1116/530, loss: 0.005499228835105896
2023-01-24 09:46:02.538388: step: 1120/530, loss: 0.0005945372977294028
2023-01-24 09:46:03.633444: step: 1124/530, loss: 0.01989840343594551
2023-01-24 09:46:04.722069: step: 1128/530, loss: 0.0009664539247751236
2023-01-24 09:46:05.796224: step: 1132/530, loss: 3.013615810232295e-07
2023-01-24 09:46:06.888230: step: 1136/530, loss: 0.025590527802705765
2023-01-24 09:46:07.989477: step: 1140/530, loss: 0.01024713832885027
2023-01-24 09:46:09.075299: step: 1144/530, loss: 0.004431177396327257
2023-01-24 09:46:10.158723: step: 1148/530, loss: 0.006881935056298971
2023-01-24 09:46:11.209067: step: 1152/530, loss: 0.0009120499598793685
2023-01-24 09:46:12.318758: step: 1156/530, loss: 0.007891872897744179
2023-01-24 09:46:13.407181: step: 1160/530, loss: 0.006422643084079027
2023-01-24 09:46:14.481059: step: 1164/530, loss: 0.0015579741448163986
2023-01-24 09:46:15.562172: step: 1168/530, loss: 0.0005016556242480874
2023-01-24 09:46:16.632823: step: 1172/530, loss: 0.002956017618998885
2023-01-24 09:46:17.735924: step: 1176/530, loss: 0.0021321908570826054
2023-01-24 09:46:18.822117: step: 1180/530, loss: 0.000456401874544099
2023-01-24 09:46:19.914221: step: 1184/530, loss: 0.0027978145517408848
2023-01-24 09:46:21.030755: step: 1188/530, loss: 0.006141733843833208
2023-01-24 09:46:22.107628: step: 1192/530, loss: 0.00030454795341938734
2023-01-24 09:46:23.183477: step: 1196/530, loss: 0.0036493183579295874
2023-01-24 09:46:24.267757: step: 1200/530, loss: 0.005128855351358652
2023-01-24 09:46:25.349947: step: 1204/530, loss: 5.0108679715776816e-05
2023-01-24 09:46:26.494215: step: 1208/530, loss: 0.007080928888171911
2023-01-24 09:46:27.574053: step: 1212/530, loss: 0.0006423405138775706
2023-01-24 09:46:28.662833: step: 1216/530, loss: 0.006253702566027641
2023-01-24 09:46:29.754646: step: 1220/530, loss: 0.0038436076138168573
2023-01-24 09:46:30.849959: step: 1224/530, loss: 0.0012389343464747071
2023-01-24 09:46:31.948802: step: 1228/530, loss: 0.0011327725369483232
2023-01-24 09:46:33.035970: step: 1232/530, loss: 0.005476536229252815
2023-01-24 09:46:34.109029: step: 1236/530, loss: 0.0015993707347661257
2023-01-24 09:46:35.199866: step: 1240/530, loss: 0.0023863338865339756
2023-01-24 09:46:36.276003: step: 1244/530, loss: 0.00957927294075489
2023-01-24 09:46:37.362357: step: 1248/530, loss: 0.022871652618050575
2023-01-24 09:46:38.474528: step: 1252/530, loss: 0.0021960516460239887
2023-01-24 09:46:39.552574: step: 1256/530, loss: 0.00020496989600360394
2023-01-24 09:46:40.642086: step: 1260/530, loss: 0.000734953791834414
2023-01-24 09:46:41.799378: step: 1264/530, loss: 0.003913666121661663
2023-01-24 09:46:42.926149: step: 1268/530, loss: 0.017393719404935837
2023-01-24 09:46:44.050172: step: 1272/530, loss: 0.0032708507496863604
2023-01-24 09:46:45.145686: step: 1276/530, loss: 0.01114897895604372
2023-01-24 09:46:46.269979: step: 1280/530, loss: 0.002834647661074996
2023-01-24 09:46:47.381298: step: 1284/530, loss: 0.00044656184036284685
2023-01-24 09:46:48.451729: step: 1288/530, loss: 0.011877741664648056
2023-01-24 09:46:49.540698: step: 1292/530, loss: 0.0023644077591598034
2023-01-24 09:46:50.626223: step: 1296/530, loss: 0.015803668648004532
2023-01-24 09:46:51.714771: step: 1300/530, loss: 0.0004333755059633404
2023-01-24 09:46:52.822890: step: 1304/530, loss: 0.008682974614202976
2023-01-24 09:46:53.937898: step: 1308/530, loss: 0.0015222133370116353
2023-01-24 09:46:55.028045: step: 1312/530, loss: 0.0018281691009178758
2023-01-24 09:46:56.132945: step: 1316/530, loss: 0.0005714896251447499
2023-01-24 09:46:57.220397: step: 1320/530, loss: 0.05201597511768341
2023-01-24 09:46:58.333958: step: 1324/530, loss: 8.254409476649016e-05
2023-01-24 09:46:59.423054: step: 1328/530, loss: 0.003138340078294277
2023-01-24 09:47:00.508586: step: 1332/530, loss: 0.0019122665980830789
2023-01-24 09:47:01.586863: step: 1336/530, loss: 0.00042591485544107854
2023-01-24 09:47:02.683480: step: 1340/530, loss: 0.00829241331666708
2023-01-24 09:47:03.782533: step: 1344/530, loss: 0.003200522856786847
2023-01-24 09:47:04.885568: step: 1348/530, loss: 0.0108566889539361
2023-01-24 09:47:05.995518: step: 1352/530, loss: 0.007357567548751831
2023-01-24 09:47:07.068429: step: 1356/530, loss: 0.005130159668624401
2023-01-24 09:47:08.167978: step: 1360/530, loss: 0.002784601878374815
2023-01-24 09:47:09.278783: step: 1364/530, loss: 0.0018567726947367191
2023-01-24 09:47:10.385910: step: 1368/530, loss: 0.001946165575645864
2023-01-24 09:47:11.472798: step: 1372/530, loss: 0.0021874376107007265
2023-01-24 09:47:12.566128: step: 1376/530, loss: 0.007368598598986864
2023-01-24 09:47:13.642894: step: 1380/530, loss: 0.007469009142369032
2023-01-24 09:47:14.740088: step: 1384/530, loss: 0.003102353308349848
2023-01-24 09:47:15.831565: step: 1388/530, loss: 0.0004759367147926241
2023-01-24 09:47:16.923993: step: 1392/530, loss: 0.0029485838022083044
2023-01-24 09:47:18.015941: step: 1396/530, loss: 0.003538076998665929
2023-01-24 09:47:19.124754: step: 1400/530, loss: 0.00025586719857528806
2023-01-24 09:47:20.217350: step: 1404/530, loss: 0.005292871966958046
2023-01-24 09:47:21.298405: step: 1408/530, loss: 0.0009659806964918971
2023-01-24 09:47:22.390481: step: 1412/530, loss: 0.007447524461895227
2023-01-24 09:47:23.491615: step: 1416/530, loss: 0.001783325569704175
2023-01-24 09:47:24.575860: step: 1420/530, loss: 0.00785510428249836
2023-01-24 09:47:25.675658: step: 1424/530, loss: 0.003746903734281659
2023-01-24 09:47:26.769533: step: 1428/530, loss: 0.0013054126175120473
2023-01-24 09:47:27.863619: step: 1432/530, loss: 0.008335101418197155
2023-01-24 09:47:28.955508: step: 1436/530, loss: 0.03604024276137352
2023-01-24 09:47:30.050786: step: 1440/530, loss: 0.003660415532067418
2023-01-24 09:47:31.150625: step: 1444/530, loss: 0.0074257622472941875
2023-01-24 09:47:32.220534: step: 1448/530, loss: 0.007867055013775826
2023-01-24 09:47:33.304402: step: 1452/530, loss: 0.015310634858906269
2023-01-24 09:47:34.384686: step: 1456/530, loss: 0.013803989626467228
2023-01-24 09:47:35.475650: step: 1460/530, loss: 0.006369090173393488
2023-01-24 09:47:36.572762: step: 1464/530, loss: 0.0008969185873866081
2023-01-24 09:47:37.667209: step: 1468/530, loss: 0.004128504544496536
2023-01-24 09:47:38.749541: step: 1472/530, loss: 0.008057482540607452
2023-01-24 09:47:39.837273: step: 1476/530, loss: 0.0013072536094114184
2023-01-24 09:47:40.904757: step: 1480/530, loss: 0.014017199166119099
2023-01-24 09:47:42.034397: step: 1484/530, loss: 0.05971527844667435
2023-01-24 09:47:43.123757: step: 1488/530, loss: 0.005062997341156006
2023-01-24 09:47:44.221102: step: 1492/530, loss: 0.0024659796617925167
2023-01-24 09:47:45.289028: step: 1496/530, loss: 9.569990879754187e-07
2023-01-24 09:47:46.377019: step: 1500/530, loss: 0.006207902915775776
2023-01-24 09:47:47.493387: step: 1504/530, loss: 0.002065556589514017
2023-01-24 09:47:48.602299: step: 1508/530, loss: 0.001768824178725481
2023-01-24 09:47:49.700251: step: 1512/530, loss: 0.002064608968794346
2023-01-24 09:47:50.789694: step: 1516/530, loss: 0.0009590198751538992
2023-01-24 09:47:51.862349: step: 1520/530, loss: 0.0027619139291346073
2023-01-24 09:47:52.963648: step: 1524/530, loss: 0.005965469870716333
2023-01-24 09:47:54.044293: step: 1528/530, loss: 0.0005408466677181423
2023-01-24 09:47:55.149609: step: 1532/530, loss: 0.004232795909047127
2023-01-24 09:47:56.248661: step: 1536/530, loss: 0.029255446046590805
2023-01-24 09:47:57.334928: step: 1540/530, loss: 0.001512959599494934
2023-01-24 09:47:58.428524: step: 1544/530, loss: 0.004193993750959635
2023-01-24 09:47:59.517253: step: 1548/530, loss: 0.01655593328177929
2023-01-24 09:48:00.597825: step: 1552/530, loss: 0.004010556731373072
2023-01-24 09:48:01.698897: step: 1556/530, loss: 0.00477555999532342
2023-01-24 09:48:02.791126: step: 1560/530, loss: 0.0030332282185554504
2023-01-24 09:48:03.869335: step: 1564/530, loss: 0.004279244691133499
2023-01-24 09:48:04.934991: step: 1568/530, loss: 0.002007303759455681
2023-01-24 09:48:06.027900: step: 1572/530, loss: 0.0029593987856060266
2023-01-24 09:48:07.131953: step: 1576/530, loss: 0.0020100378897041082
2023-01-24 09:48:08.224104: step: 1580/530, loss: 0.009585062973201275
2023-01-24 09:48:09.345897: step: 1584/530, loss: 0.010612668469548225
2023-01-24 09:48:10.426254: step: 1588/530, loss: 0.003532403614372015
2023-01-24 09:48:11.546647: step: 1592/530, loss: 0.004616458900272846
2023-01-24 09:48:12.630339: step: 1596/530, loss: 0.00012834652443416417
2023-01-24 09:48:13.700438: step: 1600/530, loss: 0.008451024070382118
2023-01-24 09:48:14.789283: step: 1604/530, loss: 0.003901928663253784
2023-01-24 09:48:15.891947: step: 1608/530, loss: 0.0076681217178702354
2023-01-24 09:48:16.962269: step: 1612/530, loss: 0.0027105221524834633
2023-01-24 09:48:18.060412: step: 1616/530, loss: 0.0029793232679367065
2023-01-24 09:48:19.131372: step: 1620/530, loss: 0.002083100378513336
2023-01-24 09:48:20.235000: step: 1624/530, loss: 0.0014758487232029438
2023-01-24 09:48:21.323438: step: 1628/530, loss: 0.018433067947626114
2023-01-24 09:48:22.437415: step: 1632/530, loss: 0.0008275517611764371
2023-01-24 09:48:23.524714: step: 1636/530, loss: 0.004098664037883282
2023-01-24 09:48:24.612042: step: 1640/530, loss: 4.538245775620453e-06
2023-01-24 09:48:25.734446: step: 1644/530, loss: 0.004451615270227194
2023-01-24 09:48:26.817188: step: 1648/530, loss: 0.009558179415762424
2023-01-24 09:48:27.879002: step: 1652/530, loss: 0.0010312829399481416
2023-01-24 09:48:28.956862: step: 1656/530, loss: 0.00029791021370328963
2023-01-24 09:48:30.025726: step: 1660/530, loss: 0.0012415312230587006
2023-01-24 09:48:31.096092: step: 1664/530, loss: 0.00031093659345060587
2023-01-24 09:48:32.201549: step: 1668/530, loss: 0.006347445771098137
2023-01-24 09:48:33.285175: step: 1672/530, loss: 0.010725405067205429
2023-01-24 09:48:34.366376: step: 1676/530, loss: 0.0025757949333637953
2023-01-24 09:48:35.456269: step: 1680/530, loss: 1.4211590496415738e-05
2023-01-24 09:48:36.551309: step: 1684/530, loss: 0.004520696122199297
2023-01-24 09:48:37.656328: step: 1688/530, loss: 0.008326796814799309
2023-01-24 09:48:38.751990: step: 1692/530, loss: 9.182773646898568e-05
2023-01-24 09:48:39.828949: step: 1696/530, loss: 0.002773266052827239
2023-01-24 09:48:40.900955: step: 1700/530, loss: 0.001968016382306814
2023-01-24 09:48:42.039661: step: 1704/530, loss: 0.004385901615023613
2023-01-24 09:48:43.129723: step: 1708/530, loss: 0.011045076884329319
2023-01-24 09:48:44.219951: step: 1712/530, loss: 0.0030012561473995447
2023-01-24 09:48:45.308801: step: 1716/530, loss: 0.002662105718627572
2023-01-24 09:48:46.385727: step: 1720/530, loss: 0.004749532323330641
2023-01-24 09:48:47.483603: step: 1724/530, loss: 0.0022050482220947742
2023-01-24 09:48:48.577898: step: 1728/530, loss: 0.007212100084871054
2023-01-24 09:48:49.660094: step: 1732/530, loss: 0.013577912002801895
2023-01-24 09:48:50.759414: step: 1736/530, loss: 0.008280695416033268
2023-01-24 09:48:51.846658: step: 1740/530, loss: 0.002290676813572645
2023-01-24 09:48:52.937570: step: 1744/530, loss: 0.001719155116006732
2023-01-24 09:48:54.025606: step: 1748/530, loss: 0.006506065838038921
2023-01-24 09:48:55.151539: step: 1752/530, loss: 0.0069944956339895725
2023-01-24 09:48:56.241553: step: 1756/530, loss: 0.0027302296366542578
2023-01-24 09:48:57.335997: step: 1760/530, loss: 0.004053385928273201
2023-01-24 09:48:58.437687: step: 1764/530, loss: 0.0018323834519833326
2023-01-24 09:48:59.535930: step: 1768/530, loss: 0.00046504868078045547
2023-01-24 09:49:00.621423: step: 1772/530, loss: 0.0003045002813450992
2023-01-24 09:49:01.716742: step: 1776/530, loss: 0.0041580963879823685
2023-01-24 09:49:02.833137: step: 1780/530, loss: 0.0015695146284997463
2023-01-24 09:49:03.921530: step: 1784/530, loss: 0.0016330681974068284
2023-01-24 09:49:05.027991: step: 1788/530, loss: 0.0005462969420477748
2023-01-24 09:49:06.119168: step: 1792/530, loss: 0.0029472154565155506
2023-01-24 09:49:07.189478: step: 1796/530, loss: 0.005171945318579674
2023-01-24 09:49:08.300183: step: 1800/530, loss: 0.008737027645111084
2023-01-24 09:49:09.395897: step: 1804/530, loss: 0.004143659025430679
2023-01-24 09:49:10.495516: step: 1808/530, loss: 0.004884339869022369
2023-01-24 09:49:11.589179: step: 1812/530, loss: 0.007590312045067549
2023-01-24 09:49:12.700509: step: 1816/530, loss: 0.0003040601732209325
2023-01-24 09:49:13.807195: step: 1820/530, loss: 0.0021880995482206345
2023-01-24 09:49:14.897600: step: 1824/530, loss: 0.05034518241882324
2023-01-24 09:49:15.975315: step: 1828/530, loss: 0.0027692888397723436
2023-01-24 09:49:17.072779: step: 1832/530, loss: 0.007986345328390598
2023-01-24 09:49:18.162576: step: 1836/530, loss: 0.005478563718497753
2023-01-24 09:49:19.264119: step: 1840/530, loss: 0.008761007338762283
2023-01-24 09:49:20.344530: step: 1844/530, loss: 0.0007668921607546508
2023-01-24 09:49:21.454839: step: 1848/530, loss: 1.3191502148401923e-05
2023-01-24 09:49:22.535381: step: 1852/530, loss: 0.0008549068588763475
2023-01-24 09:49:23.635811: step: 1856/530, loss: 0.00013868896348867565
2023-01-24 09:49:24.728748: step: 1860/530, loss: 0.012111968360841274
2023-01-24 09:49:25.821932: step: 1864/530, loss: 0.002229460049420595
2023-01-24 09:49:26.933166: step: 1868/530, loss: 0.005779405124485493
2023-01-24 09:49:28.005808: step: 1872/530, loss: 0.0007654499495401978
2023-01-24 09:49:29.082899: step: 1876/530, loss: 0.0004401237238198519
2023-01-24 09:49:30.180124: step: 1880/530, loss: 0.01065981574356556
2023-01-24 09:49:31.261222: step: 1884/530, loss: 0.012769266963005066
2023-01-24 09:49:32.354906: step: 1888/530, loss: 0.001921915914863348
2023-01-24 09:49:33.448329: step: 1892/530, loss: 0.01803373172879219
2023-01-24 09:49:34.554596: step: 1896/530, loss: 0.011836661025881767
2023-01-24 09:49:35.649628: step: 1900/530, loss: 0.013509376905858517
2023-01-24 09:49:36.714589: step: 1904/530, loss: 0.013414420187473297
2023-01-24 09:49:37.834905: step: 1908/530, loss: 0.00331012811511755
2023-01-24 09:49:38.905832: step: 1912/530, loss: 0.0012118967715650797
2023-01-24 09:49:39.993788: step: 1916/530, loss: 0.0028175697661936283
2023-01-24 09:49:41.072663: step: 1920/530, loss: 0.0021286497358232737
2023-01-24 09:49:42.177747: step: 1924/530, loss: 0.00033343781251460314
2023-01-24 09:49:43.279843: step: 1928/530, loss: 0.006572900805622339
2023-01-24 09:49:44.372535: step: 1932/530, loss: 0.003769731381908059
2023-01-24 09:49:45.472680: step: 1936/530, loss: 0.010479830205440521
2023-01-24 09:49:46.581053: step: 1940/530, loss: 0.004546172916889191
2023-01-24 09:49:47.659203: step: 1944/530, loss: 0.0014573668595403433
2023-01-24 09:49:48.732678: step: 1948/530, loss: 0.001883357996121049
2023-01-24 09:49:49.811459: step: 1952/530, loss: 0.023197341710329056
2023-01-24 09:49:50.908550: step: 1956/530, loss: 0.0
2023-01-24 09:49:51.999761: step: 1960/530, loss: 0.004750645253807306
2023-01-24 09:49:53.087547: step: 1964/530, loss: 0.0015845161397010088
2023-01-24 09:49:54.159705: step: 1968/530, loss: 0.014294756576418877
2023-01-24 09:49:55.281019: step: 1972/530, loss: 0.0022179039660841227
2023-01-24 09:49:56.378638: step: 1976/530, loss: 0.0037082417402416468
2023-01-24 09:49:57.453506: step: 1980/530, loss: 0.005503215827047825
2023-01-24 09:49:58.570784: step: 1984/530, loss: 0.0035996742080897093
2023-01-24 09:49:59.668833: step: 1988/530, loss: 0.009086393751204014
2023-01-24 09:50:00.778824: step: 1992/530, loss: 0.0027807424776256084
2023-01-24 09:50:01.863067: step: 1996/530, loss: 0.0007474375306628644
2023-01-24 09:50:02.975658: step: 2000/530, loss: 0.00048265905934385955
2023-01-24 09:50:04.068769: step: 2004/530, loss: 0.0018520974554121494
2023-01-24 09:50:05.157179: step: 2008/530, loss: 0.0010032663121819496
2023-01-24 09:50:06.262254: step: 2012/530, loss: 0.005230959039181471
2023-01-24 09:50:07.345185: step: 2016/530, loss: 0.003999687731266022
2023-01-24 09:50:08.437830: step: 2020/530, loss: 0.00028858802397735417
2023-01-24 09:50:09.536684: step: 2024/530, loss: 0.003560730954632163
2023-01-24 09:50:10.619806: step: 2028/530, loss: 0.010231171734631062
2023-01-24 09:50:11.702700: step: 2032/530, loss: 0.0019173513865098357
2023-01-24 09:50:12.790236: step: 2036/530, loss: 0.007335932459682226
2023-01-24 09:50:13.875505: step: 2040/530, loss: 0.010403071530163288
2023-01-24 09:50:14.974337: step: 2044/530, loss: 0.00016546566621400416
2023-01-24 09:50:16.046642: step: 2048/530, loss: 0.003771527437493205
2023-01-24 09:50:17.153843: step: 2052/530, loss: 0.006769419647753239
2023-01-24 09:50:18.258687: step: 2056/530, loss: 0.04177527502179146
2023-01-24 09:50:19.347855: step: 2060/530, loss: 0.002998405834659934
2023-01-24 09:50:20.451904: step: 2064/530, loss: 0.0029434487223625183
2023-01-24 09:50:21.532521: step: 2068/530, loss: 0.0033542837481945753
2023-01-24 09:50:22.628669: step: 2072/530, loss: 0.010070827789604664
2023-01-24 09:50:23.732768: step: 2076/530, loss: 0.004673119634389877
2023-01-24 09:50:24.829458: step: 2080/530, loss: 0.009197418577969074
2023-01-24 09:50:25.923043: step: 2084/530, loss: 0.0038647225592285395
2023-01-24 09:50:27.002338: step: 2088/530, loss: 0.003918979782611132
2023-01-24 09:50:28.078952: step: 2092/530, loss: 0.004716282710433006
2023-01-24 09:50:29.174743: step: 2096/530, loss: 0.003306119702756405
2023-01-24 09:50:30.265484: step: 2100/530, loss: 0.003941201604902744
2023-01-24 09:50:31.366493: step: 2104/530, loss: 0.0023030757438391447
2023-01-24 09:50:32.448773: step: 2108/530, loss: 0.01321802195161581
2023-01-24 09:50:33.530865: step: 2112/530, loss: 0.006373906508088112
2023-01-24 09:50:34.635385: step: 2116/530, loss: 0.007655682973563671
2023-01-24 09:50:35.717821: step: 2120/530, loss: 0.005693155340850353
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3442460957384897, 'r': 0.34293965894251816, 'f1': 0.3435916354804317}, 'combined': 0.2531727840382128, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34361196448181025, 'r': 0.2759771663296043, 'f1': 0.3061030336360175}, 'combined': 0.19010609457394773, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38638181386241255, 'r': 0.33066071736612535, 'f1': 0.3563562332350676}, 'combined': 0.26257827712057613, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3335784847533633, 'r': 0.2627095378937061, 'f1': 0.29393261730064185}, 'combined': 0.18254762548145126, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3767330036928605, 'r': 0.323118249846628, 'f1': 0.34787194620872924}, 'combined': 0.2563266972064321, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34798621281976616, 'r': 0.27096159654345425, 'f1': 0.30468126189108413}, 'combined': 0.18922309949025226, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36538461538461536, 'r': 0.41304347826086957, 'f1': 0.3877551020408163}, 'combined': 0.19387755102040816, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 09:53:03.164296: step: 4/530, loss: 0.0009382517891936004
2023-01-24 09:53:04.242608: step: 8/530, loss: 0.0007458329200744629
2023-01-24 09:53:05.319630: step: 12/530, loss: 0.020100224763154984
2023-01-24 09:53:06.402675: step: 16/530, loss: 0.00603818753734231
2023-01-24 09:53:07.464204: step: 20/530, loss: 0.0023992632050067186
2023-01-24 09:53:08.550273: step: 24/530, loss: 8.95670018508099e-05
2023-01-24 09:53:09.610440: step: 28/530, loss: 0.00046150924754329026
2023-01-24 09:53:10.683920: step: 32/530, loss: 0.0008870534948073328
2023-01-24 09:53:11.773635: step: 36/530, loss: 0.005683777388185263
2023-01-24 09:53:12.873003: step: 40/530, loss: 0.0015970487147569656
2023-01-24 09:53:13.953450: step: 44/530, loss: 0.001628810539841652
2023-01-24 09:53:15.043518: step: 48/530, loss: 0.004171023610979319
2023-01-24 09:53:16.135887: step: 52/530, loss: 5.571292422246188e-05
2023-01-24 09:53:17.226363: step: 56/530, loss: 5.181822780286893e-05
2023-01-24 09:53:18.323236: step: 60/530, loss: 2.9268907383084297e-05
2023-01-24 09:53:19.397369: step: 64/530, loss: 0.0008482362609356642
2023-01-24 09:53:20.472865: step: 68/530, loss: 0.00347668188624084
2023-01-24 09:53:21.548523: step: 72/530, loss: 7.646776793990284e-05
2023-01-24 09:53:22.614076: step: 76/530, loss: 0.000637854915112257
2023-01-24 09:53:23.694484: step: 80/530, loss: 0.0012868506601080298
2023-01-24 09:53:24.795877: step: 84/530, loss: 0.0014965353766456246
2023-01-24 09:53:25.861651: step: 88/530, loss: 0.00263797864317894
2023-01-24 09:53:26.947021: step: 92/530, loss: 0.0011093398788943887
2023-01-24 09:53:28.074560: step: 96/530, loss: 0.005608233157545328
2023-01-24 09:53:29.157078: step: 100/530, loss: 0.00014191395894158632
2023-01-24 09:53:30.244366: step: 104/530, loss: 0.0009764271671883762
2023-01-24 09:53:31.329842: step: 108/530, loss: 0.004163474775850773
2023-01-24 09:53:32.394920: step: 112/530, loss: 0.00037535608862526715
2023-01-24 09:53:33.517680: step: 116/530, loss: 0.0032862084917724133
2023-01-24 09:53:34.611627: step: 120/530, loss: 0.009096729569137096
2023-01-24 09:53:35.722684: step: 124/530, loss: 0.0022512138821184635
2023-01-24 09:53:36.802964: step: 128/530, loss: 0.002169341314584017
2023-01-24 09:53:37.937568: step: 132/530, loss: 0.005965308286249638
2023-01-24 09:53:39.026251: step: 136/530, loss: 0.011858509853482246
2023-01-24 09:53:40.105152: step: 140/530, loss: 0.0008963411673903465
2023-01-24 09:53:41.189457: step: 144/530, loss: 0.02409239299595356
2023-01-24 09:53:42.291461: step: 148/530, loss: 0.0042005423456430435
2023-01-24 09:53:43.383543: step: 152/530, loss: 0.020239807665348053
2023-01-24 09:53:44.462736: step: 156/530, loss: 0.003998726140707731
2023-01-24 09:53:45.565174: step: 160/530, loss: 0.005496561992913485
2023-01-24 09:53:46.640767: step: 164/530, loss: 0.005694527644664049
2023-01-24 09:53:47.730386: step: 168/530, loss: 0.001840868266299367
2023-01-24 09:53:48.801295: step: 172/530, loss: 0.002671318594366312
2023-01-24 09:53:49.886524: step: 176/530, loss: 0.0020116078667342663
2023-01-24 09:53:50.953804: step: 180/530, loss: 0.0010723109589889646
2023-01-24 09:53:52.040657: step: 184/530, loss: 0.008998713456094265
2023-01-24 09:53:53.127597: step: 188/530, loss: 0.002764201257377863
2023-01-24 09:53:54.218560: step: 192/530, loss: 0.00342775066383183
2023-01-24 09:53:55.292833: step: 196/530, loss: 0.006084446795284748
2023-01-24 09:53:56.374779: step: 200/530, loss: 0.0020574626978486776
2023-01-24 09:53:57.462510: step: 204/530, loss: 0.0004493702726904303
2023-01-24 09:53:58.546775: step: 208/530, loss: 0.009899861179292202
2023-01-24 09:53:59.635786: step: 212/530, loss: 0.0011038478696718812
2023-01-24 09:54:00.724074: step: 216/530, loss: 0.00041425848030485213
2023-01-24 09:54:01.799751: step: 220/530, loss: 0.007660370785742998
2023-01-24 09:54:02.895380: step: 224/530, loss: 0.008085745386779308
2023-01-24 09:54:04.001261: step: 228/530, loss: 0.005541825667023659
2023-01-24 09:54:05.094420: step: 232/530, loss: 0.0016924977535381913
2023-01-24 09:54:06.179938: step: 236/530, loss: 0.008505958132445812
2023-01-24 09:54:07.271444: step: 240/530, loss: 0.006898310501128435
2023-01-24 09:54:08.350611: step: 244/530, loss: 0.004474983084946871
2023-01-24 09:54:09.446086: step: 248/530, loss: 0.0010577687062323093
2023-01-24 09:54:10.540734: step: 252/530, loss: 0.0039393361657857895
2023-01-24 09:54:11.642861: step: 256/530, loss: 0.007406703196465969
2023-01-24 09:54:12.715830: step: 260/530, loss: 3.003341362273204e-07
2023-01-24 09:54:13.808562: step: 264/530, loss: 0.012480025179684162
2023-01-24 09:54:14.883892: step: 268/530, loss: 4.777618869411526e-06
2023-01-24 09:54:15.995014: step: 272/530, loss: 0.006687567103654146
2023-01-24 09:54:17.101069: step: 276/530, loss: 0.00017694816051516682
2023-01-24 09:54:18.186915: step: 280/530, loss: 0.0003960226022172719
2023-01-24 09:54:19.294897: step: 284/530, loss: 0.0006106164655648172
2023-01-24 09:54:20.380558: step: 288/530, loss: 0.0008020658860914409
2023-01-24 09:54:21.472953: step: 292/530, loss: 0.004469539970159531
2023-01-24 09:54:22.568888: step: 296/530, loss: 0.005460104439407587
2023-01-24 09:54:23.689162: step: 300/530, loss: 0.001034132787026465
2023-01-24 09:54:24.793954: step: 304/530, loss: 0.0002937859098892659
2023-01-24 09:54:25.889897: step: 308/530, loss: 0.007251308765262365
2023-01-24 09:54:26.967108: step: 312/530, loss: 0.00323469121940434
2023-01-24 09:54:28.069769: step: 316/530, loss: 0.011491605080664158
2023-01-24 09:54:29.156665: step: 320/530, loss: 0.0007970802835188806
2023-01-24 09:54:30.259202: step: 324/530, loss: 0.003871447406709194
2023-01-24 09:54:31.392536: step: 328/530, loss: 0.03132467716932297
2023-01-24 09:54:32.476381: step: 332/530, loss: 0.00546283321455121
2023-01-24 09:54:33.567932: step: 336/530, loss: 0.0006811360362917185
2023-01-24 09:54:34.652847: step: 340/530, loss: 0.009633843787014484
2023-01-24 09:54:35.738644: step: 344/530, loss: 0.0019323276355862617
2023-01-24 09:54:36.826939: step: 348/530, loss: 0.0005890722968615592
2023-01-24 09:54:37.909148: step: 352/530, loss: 0.011600606143474579
2023-01-24 09:54:39.008229: step: 356/530, loss: 0.0029137167148292065
2023-01-24 09:54:40.076620: step: 360/530, loss: 0.002526012249290943
2023-01-24 09:54:41.182145: step: 364/530, loss: 0.0022561270743608475
2023-01-24 09:54:42.302562: step: 368/530, loss: 0.0003573104622773826
2023-01-24 09:54:43.388501: step: 372/530, loss: 0.0012719127116724849
2023-01-24 09:54:44.509695: step: 376/530, loss: 0.0047092377208173275
2023-01-24 09:54:45.614377: step: 380/530, loss: 0.0037850087974220514
2023-01-24 09:54:46.719389: step: 384/530, loss: 0.0009696660563349724
2023-01-24 09:54:47.835382: step: 388/530, loss: 0.00386227760463953
2023-01-24 09:54:48.926520: step: 392/530, loss: 0.004639643710106611
2023-01-24 09:54:50.026528: step: 396/530, loss: 0.002485678531229496
2023-01-24 09:54:51.100049: step: 400/530, loss: 0.00032548923627473414
2023-01-24 09:54:52.198620: step: 404/530, loss: 0.002456765156239271
2023-01-24 09:54:53.265730: step: 408/530, loss: 9.76178671407979e-06
2023-01-24 09:54:54.363464: step: 412/530, loss: 0.006419209763407707
2023-01-24 09:54:55.437014: step: 416/530, loss: 0.009708626195788383
2023-01-24 09:54:56.533756: step: 420/530, loss: 0.00022630620514973998
2023-01-24 09:54:57.630792: step: 424/530, loss: 0.0035180081613361835
2023-01-24 09:54:58.736105: step: 428/530, loss: 0.0023558405227959156
2023-01-24 09:54:59.820475: step: 432/530, loss: 0.0030372757464647293
2023-01-24 09:55:00.912839: step: 436/530, loss: 0.002196301007643342
2023-01-24 09:55:02.017589: step: 440/530, loss: 0.004221763927489519
2023-01-24 09:55:03.105492: step: 444/530, loss: 0.001984473317861557
2023-01-24 09:55:04.201648: step: 448/530, loss: 0.00038633798249065876
2023-01-24 09:55:05.302403: step: 452/530, loss: 0.003452147589996457
2023-01-24 09:55:06.398613: step: 456/530, loss: 0.007510800380259752
2023-01-24 09:55:07.497083: step: 460/530, loss: 0.0007514133467338979
2023-01-24 09:55:08.588253: step: 464/530, loss: 0.000614840944763273
2023-01-24 09:55:09.678760: step: 468/530, loss: 0.009482195600867271
2023-01-24 09:55:10.766939: step: 472/530, loss: 0.0007676169043406844
2023-01-24 09:55:11.863165: step: 476/530, loss: 0.0026391278952360153
2023-01-24 09:55:12.950487: step: 480/530, loss: 0.006811762228608131
2023-01-24 09:55:14.036499: step: 484/530, loss: 0.006468001753091812
2023-01-24 09:55:15.128195: step: 488/530, loss: 0.00397089496254921
2023-01-24 09:55:16.214654: step: 492/530, loss: 0.002719681477174163
2023-01-24 09:55:17.309683: step: 496/530, loss: 0.0020633763633668423
2023-01-24 09:55:18.424698: step: 500/530, loss: 9.77211311692372e-05
2023-01-24 09:55:19.500933: step: 504/530, loss: 0.0008222581236623228
2023-01-24 09:55:20.577381: step: 508/530, loss: 0.0006518136360682547
2023-01-24 09:55:21.661451: step: 512/530, loss: 0.014863686636090279
2023-01-24 09:55:22.749964: step: 516/530, loss: 0.0010331552475690842
2023-01-24 09:55:23.840373: step: 520/530, loss: 0.00015811574121471494
2023-01-24 09:55:24.935243: step: 524/530, loss: 0.0014177013654261827
2023-01-24 09:55:26.029758: step: 528/530, loss: 0.0011622320162132382
2023-01-24 09:55:27.126681: step: 532/530, loss: 0.0053962827660143375
2023-01-24 09:55:28.214457: step: 536/530, loss: 0.0025527379475533962
2023-01-24 09:55:29.293287: step: 540/530, loss: 7.70887709222734e-05
2023-01-24 09:55:30.398362: step: 544/530, loss: 0.0022577052004635334
2023-01-24 09:55:31.491289: step: 548/530, loss: 8.863598850439303e-06
2023-01-24 09:55:32.592783: step: 552/530, loss: 0.004121160134673119
2023-01-24 09:55:33.679421: step: 556/530, loss: 0.005839852150529623
2023-01-24 09:55:34.772348: step: 560/530, loss: 4.106546384718968e-06
2023-01-24 09:55:35.840235: step: 564/530, loss: 6.0821498664154205e-06
2023-01-24 09:55:36.934292: step: 568/530, loss: 0.013007650151848793
2023-01-24 09:55:38.037409: step: 572/530, loss: 0.002608954207971692
2023-01-24 09:55:39.132022: step: 576/530, loss: 0.0001987192954402417
2023-01-24 09:55:40.236242: step: 580/530, loss: 0.0020917458459734917
2023-01-24 09:55:41.340299: step: 584/530, loss: 0.0034687542356550694
2023-01-24 09:55:42.446118: step: 588/530, loss: 0.0047590541653335094
2023-01-24 09:55:43.550776: step: 592/530, loss: 0.0007282274309545755
2023-01-24 09:55:44.621912: step: 596/530, loss: 1.887783764686901e-05
2023-01-24 09:55:45.742196: step: 600/530, loss: 0.006157950032502413
2023-01-24 09:55:46.834372: step: 604/530, loss: 0.0009968391386792064
2023-01-24 09:55:47.929810: step: 608/530, loss: 0.0010159407975152135
2023-01-24 09:55:48.997452: step: 612/530, loss: 0.00309828226454556
2023-01-24 09:55:50.086647: step: 616/530, loss: 0.003981821238994598
2023-01-24 09:55:51.186808: step: 620/530, loss: 0.0018538751173764467
2023-01-24 09:55:52.273653: step: 624/530, loss: 0.005044296383857727
2023-01-24 09:55:53.369440: step: 628/530, loss: 0.004188151098787785
2023-01-24 09:55:54.439655: step: 632/530, loss: 0.0024080753792077303
2023-01-24 09:55:55.542145: step: 636/530, loss: 0.00557094719260931
2023-01-24 09:55:56.645473: step: 640/530, loss: 0.004846950527280569
2023-01-24 09:55:57.750891: step: 644/530, loss: 0.002767184516415
2023-01-24 09:55:58.822667: step: 648/530, loss: 0.0003927384677808732
2023-01-24 09:55:59.907631: step: 652/530, loss: 0.004269721452146769
2023-01-24 09:56:01.019856: step: 656/530, loss: 0.008520129136741161
2023-01-24 09:56:02.098973: step: 660/530, loss: 0.005950061604380608
2023-01-24 09:56:03.185851: step: 664/530, loss: 7.245476444950327e-05
2023-01-24 09:56:04.272653: step: 668/530, loss: 0.0027762348763644695
2023-01-24 09:56:05.370363: step: 672/530, loss: 9.943183977156878e-05
2023-01-24 09:56:06.457140: step: 676/530, loss: 0.004367906600236893
2023-01-24 09:56:07.572199: step: 680/530, loss: 0.00047338640433736145
2023-01-24 09:56:08.671623: step: 684/530, loss: 0.0011735564330592752
2023-01-24 09:56:09.765179: step: 688/530, loss: 2.893675809900742e-05
2023-01-24 09:56:10.850314: step: 692/530, loss: 0.0009245704859495163
2023-01-24 09:56:11.947703: step: 696/530, loss: 0.0037451686803251505
2023-01-24 09:56:13.033736: step: 700/530, loss: 0.021765418350696564
2023-01-24 09:56:14.127320: step: 704/530, loss: 0.002269482472911477
2023-01-24 09:56:15.210127: step: 708/530, loss: 0.0
2023-01-24 09:56:16.292044: step: 712/530, loss: 0.0010808603838086128
2023-01-24 09:56:17.387751: step: 716/530, loss: 0.005610091611742973
2023-01-24 09:56:18.502930: step: 720/530, loss: 0.001090293750166893
2023-01-24 09:56:19.599681: step: 724/530, loss: 0.0022586656268686056
2023-01-24 09:56:20.705034: step: 728/530, loss: 0.030740924179553986
2023-01-24 09:56:21.806169: step: 732/530, loss: 0.001200369093567133
2023-01-24 09:56:22.899901: step: 736/530, loss: 0.004841573536396027
2023-01-24 09:56:23.989133: step: 740/530, loss: 0.0008445832063443959
2023-01-24 09:56:25.095166: step: 744/530, loss: 0.004193236585706472
2023-01-24 09:56:26.186478: step: 748/530, loss: 0.0038601115811616182
2023-01-24 09:56:27.273692: step: 752/530, loss: 0.0032526650466024876
2023-01-24 09:56:28.357751: step: 756/530, loss: 0.0018296608468517661
2023-01-24 09:56:29.441075: step: 760/530, loss: 3.840676072286442e-05
2023-01-24 09:56:30.543492: step: 764/530, loss: 0.0003374102816451341
2023-01-24 09:56:31.646463: step: 768/530, loss: 0.00048198073636740446
2023-01-24 09:56:32.737316: step: 772/530, loss: 0.007557819131761789
2023-01-24 09:56:33.847354: step: 776/530, loss: 0.0006743691628798842
2023-01-24 09:56:34.937482: step: 780/530, loss: 0.0028557456098496914
2023-01-24 09:56:36.036217: step: 784/530, loss: 0.0003291918837931007
2023-01-24 09:56:37.120450: step: 788/530, loss: 0.010044308379292488
2023-01-24 09:56:38.212850: step: 792/530, loss: 0.0012281634844839573
2023-01-24 09:56:39.313374: step: 796/530, loss: 0.007754568476229906
2023-01-24 09:56:40.390923: step: 800/530, loss: 0.004021527711302042
2023-01-24 09:56:41.472989: step: 804/530, loss: 0.0003520576865412295
2023-01-24 09:56:42.577985: step: 808/530, loss: 0.0032094307243824005
2023-01-24 09:56:43.690732: step: 812/530, loss: 0.0008712415001355112
2023-01-24 09:56:44.777361: step: 816/530, loss: 0.007400264963507652
2023-01-24 09:56:45.864101: step: 820/530, loss: 0.005930343642830849
2023-01-24 09:56:46.952384: step: 824/530, loss: 0.006092222407460213
2023-01-24 09:56:48.045468: step: 828/530, loss: 0.007556985132396221
2023-01-24 09:56:49.132339: step: 832/530, loss: 0.0025327824987471104
2023-01-24 09:56:50.227223: step: 836/530, loss: 0.011381884105503559
2023-01-24 09:56:51.334805: step: 840/530, loss: 0.0039446656592190266
2023-01-24 09:56:52.446403: step: 844/530, loss: 0.008466324768960476
2023-01-24 09:56:53.534160: step: 848/530, loss: 6.4050109358504415e-06
2023-01-24 09:56:54.622960: step: 852/530, loss: 0.007452858611941338
2023-01-24 09:56:55.726057: step: 856/530, loss: 0.01534226629883051
2023-01-24 09:56:56.809268: step: 860/530, loss: 6.664237844233867e-06
2023-01-24 09:56:57.897158: step: 864/530, loss: 5.0291376396671694e-08
2023-01-24 09:56:58.993050: step: 868/530, loss: 0.019897237420082092
2023-01-24 09:57:00.071457: step: 872/530, loss: 0.0039535523392260075
2023-01-24 09:57:01.149112: step: 876/530, loss: 0.012000597082078457
2023-01-24 09:57:02.256540: step: 880/530, loss: 0.039778389036655426
2023-01-24 09:57:03.336665: step: 884/530, loss: 0.002352713607251644
2023-01-24 09:57:04.425255: step: 888/530, loss: 0.0013583969557657838
2023-01-24 09:57:05.514334: step: 892/530, loss: 0.0005925582372583449
2023-01-24 09:57:06.611438: step: 896/530, loss: 0.0014661260647699237
2023-01-24 09:57:07.683563: step: 900/530, loss: 0.0003891157975886017
2023-01-24 09:57:08.774409: step: 904/530, loss: 0.001099692191928625
2023-01-24 09:57:09.872679: step: 908/530, loss: 0.0011839447543025017
2023-01-24 09:57:10.969871: step: 912/530, loss: 0.0001947626005858183
2023-01-24 09:57:12.073202: step: 916/530, loss: 0.017845891416072845
2023-01-24 09:57:13.189564: step: 920/530, loss: 0.0017318632453680038
2023-01-24 09:57:14.274442: step: 924/530, loss: 0.0030967986676841974
2023-01-24 09:57:15.349837: step: 928/530, loss: 0.006518544163554907
2023-01-24 09:57:16.443497: step: 932/530, loss: 0.004933425225317478
2023-01-24 09:57:17.536666: step: 936/530, loss: 0.021260403096675873
2023-01-24 09:57:18.629476: step: 940/530, loss: 0.006665264256298542
2023-01-24 09:57:19.741906: step: 944/530, loss: 0.0007224353612400591
2023-01-24 09:57:20.827099: step: 948/530, loss: 0.004189273342490196
2023-01-24 09:57:21.934687: step: 952/530, loss: 0.0008263826020993292
2023-01-24 09:57:23.042686: step: 956/530, loss: 0.00208522891625762
2023-01-24 09:57:24.140167: step: 960/530, loss: 0.0052817403338849545
2023-01-24 09:57:25.225743: step: 964/530, loss: 0.0019786537159234285
2023-01-24 09:57:26.331576: step: 968/530, loss: 0.0011980137787759304
2023-01-24 09:57:27.419319: step: 972/530, loss: 0.003914820495992899
2023-01-24 09:57:28.516903: step: 976/530, loss: 0.0023069828748703003
2023-01-24 09:57:29.608792: step: 980/530, loss: 0.004015594255179167
2023-01-24 09:57:30.705006: step: 984/530, loss: 0.004730938468128443
2023-01-24 09:57:31.792178: step: 988/530, loss: 0.004416345153003931
2023-01-24 09:57:32.881409: step: 992/530, loss: 0.00339575856924057
2023-01-24 09:57:33.998980: step: 996/530, loss: 0.0026151412166655064
2023-01-24 09:57:35.079635: step: 1000/530, loss: 0.0025615852791815996
2023-01-24 09:57:36.192120: step: 1004/530, loss: 0.002780602080747485
2023-01-24 09:57:37.274491: step: 1008/530, loss: 0.0024323835968971252
2023-01-24 09:57:38.368075: step: 1012/530, loss: 0.0017398330383002758
2023-01-24 09:57:39.459514: step: 1016/530, loss: 0.0017514735227450728
2023-01-24 09:57:40.530899: step: 1020/530, loss: 0.0011801804648712277
2023-01-24 09:57:41.629247: step: 1024/530, loss: 0.010364910587668419
2023-01-24 09:57:42.754079: step: 1028/530, loss: 0.0030158699955791235
2023-01-24 09:57:43.839189: step: 1032/530, loss: 0.000503338931594044
2023-01-24 09:57:44.944299: step: 1036/530, loss: 0.003913387656211853
2023-01-24 09:57:46.052436: step: 1040/530, loss: 0.0008146704640239477
2023-01-24 09:57:47.138585: step: 1044/530, loss: 0.002618949394673109
2023-01-24 09:57:48.241488: step: 1048/530, loss: 5.17438274982851e-05
2023-01-24 09:57:49.341151: step: 1052/530, loss: 0.00746112409979105
2023-01-24 09:57:50.443008: step: 1056/530, loss: 0.05978460982441902
2023-01-24 09:57:51.541727: step: 1060/530, loss: 0.01746443286538124
2023-01-24 09:57:52.662958: step: 1064/530, loss: 0.0065761590376496315
2023-01-24 09:57:53.777861: step: 1068/530, loss: 0.00971446093171835
2023-01-24 09:57:54.851130: step: 1072/530, loss: 0.004888199269771576
2023-01-24 09:57:55.961097: step: 1076/530, loss: 0.0019925145898014307
2023-01-24 09:57:57.027055: step: 1080/530, loss: 0.0013363719917833805
2023-01-24 09:57:58.128607: step: 1084/530, loss: 0.009254733100533485
2023-01-24 09:57:59.207173: step: 1088/530, loss: 0.0003369998885318637
2023-01-24 09:58:00.320086: step: 1092/530, loss: 0.006268787197768688
2023-01-24 09:58:01.406010: step: 1096/530, loss: 0.008753328584134579
2023-01-24 09:58:02.507027: step: 1100/530, loss: 0.0003484312037471682
2023-01-24 09:58:03.595343: step: 1104/530, loss: 0.006100955884903669
2023-01-24 09:58:04.675264: step: 1108/530, loss: 0.00019000712200067937
2023-01-24 09:58:05.766936: step: 1112/530, loss: 0.011058731004595757
2023-01-24 09:58:06.846070: step: 1116/530, loss: 0.0030486814212054014
2023-01-24 09:58:07.919844: step: 1120/530, loss: 0.005386482924222946
2023-01-24 09:58:08.994003: step: 1124/530, loss: 0.00038144763675518334
2023-01-24 09:58:10.078341: step: 1128/530, loss: 0.003398491069674492
2023-01-24 09:58:11.154654: step: 1132/530, loss: 0.0002537529217079282
2023-01-24 09:58:12.247977: step: 1136/530, loss: 0.002493631560355425
2023-01-24 09:58:13.338968: step: 1140/530, loss: 0.002667548367753625
2023-01-24 09:58:14.411985: step: 1144/530, loss: 0.019800031557679176
2023-01-24 09:58:15.488067: step: 1148/530, loss: 0.009160289540886879
2023-01-24 09:58:16.585785: step: 1152/530, loss: 0.0018552790861576796
2023-01-24 09:58:17.691113: step: 1156/530, loss: 0.0043502552434802055
2023-01-24 09:58:18.792744: step: 1160/530, loss: 0.0003805956512223929
2023-01-24 09:58:19.868408: step: 1164/530, loss: 0.000876463542226702
2023-01-24 09:58:20.944433: step: 1168/530, loss: 2.4589211534475908e-05
2023-01-24 09:58:22.067469: step: 1172/530, loss: 0.0008695876458659768
2023-01-24 09:58:23.147097: step: 1176/530, loss: 0.0009143345523625612
2023-01-24 09:58:24.247916: step: 1180/530, loss: 0.0020415079779922962
2023-01-24 09:58:25.340420: step: 1184/530, loss: 0.002801405033096671
2023-01-24 09:58:26.421163: step: 1188/530, loss: 0.0018937858985736966
2023-01-24 09:58:27.512529: step: 1192/530, loss: 0.00959955994039774
2023-01-24 09:58:28.593174: step: 1196/530, loss: 0.004226675722748041
2023-01-24 09:58:29.669030: step: 1200/530, loss: 2.4448534531984478e-05
2023-01-24 09:58:30.749908: step: 1204/530, loss: 0.011197513900697231
2023-01-24 09:58:31.840124: step: 1208/530, loss: 0.013362959958612919
2023-01-24 09:58:32.912001: step: 1212/530, loss: 0.0010965893743559718
2023-01-24 09:58:34.007711: step: 1216/530, loss: 0.0026229280047118664
2023-01-24 09:58:35.106795: step: 1220/530, loss: 0.005070118233561516
2023-01-24 09:58:36.200594: step: 1224/530, loss: 0.0026583687867969275
2023-01-24 09:58:37.285818: step: 1228/530, loss: 0.003312967484816909
2023-01-24 09:58:38.377538: step: 1232/530, loss: 0.0008142516599036753
2023-01-24 09:58:39.490069: step: 1236/530, loss: 0.0021133790723979473
2023-01-24 09:58:40.569499: step: 1240/530, loss: 0.0034803026355803013
2023-01-24 09:58:41.661139: step: 1244/530, loss: 0.0067142341285943985
2023-01-24 09:58:42.743838: step: 1248/530, loss: 0.008614704012870789
2023-01-24 09:58:43.824199: step: 1252/530, loss: 0.0012909629149362445
2023-01-24 09:58:44.892312: step: 1256/530, loss: 0.0015210537239909172
2023-01-24 09:58:45.987319: step: 1260/530, loss: 0.00339047540910542
2023-01-24 09:58:47.076742: step: 1264/530, loss: 0.0027066462207585573
2023-01-24 09:58:48.156834: step: 1268/530, loss: 0.000420679192757234
2023-01-24 09:58:49.243944: step: 1272/530, loss: 0.02238692343235016
2023-01-24 09:58:50.349922: step: 1276/530, loss: 0.0003682363894768059
2023-01-24 09:58:51.462121: step: 1280/530, loss: 0.007898399606347084
2023-01-24 09:58:52.549392: step: 1284/530, loss: 4.020193046017084e-06
2023-01-24 09:58:53.648359: step: 1288/530, loss: 0.0008638929575681686
2023-01-24 09:58:54.768016: step: 1292/530, loss: 0.008006955496966839
2023-01-24 09:58:55.881634: step: 1296/530, loss: 0.00043161181383766234
2023-01-24 09:58:56.963395: step: 1300/530, loss: 0.0001510414876975119
2023-01-24 09:58:58.067064: step: 1304/530, loss: 0.0007518358179368079
2023-01-24 09:58:59.160852: step: 1308/530, loss: 0.0006505374331027269
2023-01-24 09:59:00.244686: step: 1312/530, loss: 0.004661477170884609
2023-01-24 09:59:01.333000: step: 1316/530, loss: 0.0009284016559831798
2023-01-24 09:59:02.430730: step: 1320/530, loss: 0.012900302186608315
2023-01-24 09:59:03.495126: step: 1324/530, loss: 0.005833383649587631
2023-01-24 09:59:04.579131: step: 1328/530, loss: 1.515905387350358e-05
2023-01-24 09:59:05.650706: step: 1332/530, loss: 0.0018105567432940006
2023-01-24 09:59:06.750337: step: 1336/530, loss: 0.002501973882317543
2023-01-24 09:59:07.830420: step: 1340/530, loss: 0.003806342603638768
2023-01-24 09:59:08.919540: step: 1344/530, loss: 0.011848351918160915
2023-01-24 09:59:10.010540: step: 1348/530, loss: 0.0026647765189409256
2023-01-24 09:59:11.132013: step: 1352/530, loss: 0.010918958112597466
2023-01-24 09:59:12.218808: step: 1356/530, loss: 0.0034258549567312002
2023-01-24 09:59:13.311757: step: 1360/530, loss: 0.02496151439845562
2023-01-24 09:59:14.386911: step: 1364/530, loss: 0.0033963769674301147
2023-01-24 09:59:15.465355: step: 1368/530, loss: 0.0012569841928780079
2023-01-24 09:59:16.554157: step: 1372/530, loss: 0.014646589756011963
2023-01-24 09:59:17.682920: step: 1376/530, loss: 0.00520023750141263
2023-01-24 09:59:18.765470: step: 1380/530, loss: 0.008949876762926579
2023-01-24 09:59:19.847865: step: 1384/530, loss: 0.014099440537393093
2023-01-24 09:59:20.928062: step: 1388/530, loss: 0.0017189332284033298
2023-01-24 09:59:22.026816: step: 1392/530, loss: 0.009262565523386002
2023-01-24 09:59:23.112703: step: 1396/530, loss: 0.0012344110291451216
2023-01-24 09:59:24.200492: step: 1400/530, loss: 0.0008225159836001694
2023-01-24 09:59:25.319197: step: 1404/530, loss: 0.0014936174266040325
2023-01-24 09:59:26.427508: step: 1408/530, loss: 0.003664296120405197
2023-01-24 09:59:27.535100: step: 1412/530, loss: 0.00030481244903057814
2023-01-24 09:59:28.637557: step: 1416/530, loss: 0.002614325378090143
2023-01-24 09:59:29.730519: step: 1420/530, loss: 0.007549910340458155
2023-01-24 09:59:30.837113: step: 1424/530, loss: 0.038141150027513504
2023-01-24 09:59:31.922598: step: 1428/530, loss: 0.004947444889694452
2023-01-24 09:59:33.048983: step: 1432/530, loss: 0.00578342517837882
2023-01-24 09:59:34.128644: step: 1436/530, loss: 0.005597495473921299
2023-01-24 09:59:35.208584: step: 1440/530, loss: 0.0017578318947926164
2023-01-24 09:59:36.293115: step: 1444/530, loss: 0.003772624535486102
2023-01-24 09:59:37.387858: step: 1448/530, loss: 0.008857645094394684
2023-01-24 09:59:38.469469: step: 1452/530, loss: 0.00011549842020031065
2023-01-24 09:59:39.579649: step: 1456/530, loss: 0.004917779937386513
2023-01-24 09:59:40.671857: step: 1460/530, loss: 0.0004713029193226248
2023-01-24 09:59:41.758575: step: 1464/530, loss: 3.580367410904728e-05
2023-01-24 09:59:42.856590: step: 1468/530, loss: 0.024880684912204742
2023-01-24 09:59:43.966996: step: 1472/530, loss: 0.015539719723165035
2023-01-24 09:59:45.056505: step: 1476/530, loss: 0.0030423651915043592
2023-01-24 09:59:46.140608: step: 1480/530, loss: 0.0005326632526703179
2023-01-24 09:59:47.275188: step: 1484/530, loss: 0.00669434666633606
2023-01-24 09:59:48.355644: step: 1488/530, loss: 0.006360972300171852
2023-01-24 09:59:49.462000: step: 1492/530, loss: 0.004966961685568094
2023-01-24 09:59:50.571197: step: 1496/530, loss: 7.674341031815857e-05
2023-01-24 09:59:51.673405: step: 1500/530, loss: 0.000766607525292784
2023-01-24 09:59:52.747161: step: 1504/530, loss: 0.002515893429517746
2023-01-24 09:59:53.844475: step: 1508/530, loss: 0.007046996150165796
2023-01-24 09:59:54.949320: step: 1512/530, loss: 0.0013534441823139787
2023-01-24 09:59:56.020615: step: 1516/530, loss: 0.002146252663806081
2023-01-24 09:59:57.093687: step: 1520/530, loss: 0.0004873658763244748
2023-01-24 09:59:58.185450: step: 1524/530, loss: 0.004555124323815107
2023-01-24 09:59:59.280037: step: 1528/530, loss: 0.0035639917477965355
2023-01-24 10:00:00.351315: step: 1532/530, loss: 0.007021291647106409
2023-01-24 10:00:01.432728: step: 1536/530, loss: 0.007638323120772839
2023-01-24 10:00:02.522100: step: 1540/530, loss: 0.00022224440181162208
2023-01-24 10:00:03.621306: step: 1544/530, loss: 0.001797450939193368
2023-01-24 10:00:04.717478: step: 1548/530, loss: 0.004820940550416708
2023-01-24 10:00:05.817954: step: 1552/530, loss: 0.00698222778737545
2023-01-24 10:00:06.920985: step: 1556/530, loss: 0.0018218755722045898
2023-01-24 10:00:08.011631: step: 1560/530, loss: 0.0015776666114106774
2023-01-24 10:00:09.099648: step: 1564/530, loss: 0.0002898024977184832
2023-01-24 10:00:10.191259: step: 1568/530, loss: 0.0038671568036079407
2023-01-24 10:00:11.281541: step: 1572/530, loss: 0.018185589462518692
2023-01-24 10:00:12.393232: step: 1576/530, loss: 0.005456727463752031
2023-01-24 10:00:13.483657: step: 1580/530, loss: 0.009965651668608189
2023-01-24 10:00:14.586836: step: 1584/530, loss: 0.0066036018542945385
2023-01-24 10:00:15.686059: step: 1588/530, loss: 0.00564106460660696
2023-01-24 10:00:16.760313: step: 1592/530, loss: 0.002011688658967614
2023-01-24 10:00:17.841043: step: 1596/530, loss: 0.0003201515937689692
2023-01-24 10:00:18.954292: step: 1600/530, loss: 0.002538562985137105
2023-01-24 10:00:20.047109: step: 1604/530, loss: 0.017771240323781967
2023-01-24 10:00:21.129270: step: 1608/530, loss: 0.00866878405213356
2023-01-24 10:00:22.227623: step: 1612/530, loss: 0.003042306285351515
2023-01-24 10:00:23.323476: step: 1616/530, loss: 0.005300478078424931
2023-01-24 10:00:24.395563: step: 1620/530, loss: 0.005812700837850571
2023-01-24 10:00:25.512188: step: 1624/530, loss: 0.002968069165945053
2023-01-24 10:00:26.593999: step: 1628/530, loss: 0.004015675280243158
2023-01-24 10:00:27.685543: step: 1632/530, loss: 0.007417803164571524
2023-01-24 10:00:28.793274: step: 1636/530, loss: 0.00010906918032560498
2023-01-24 10:00:29.907976: step: 1640/530, loss: 0.0008300939225591719
2023-01-24 10:00:31.013350: step: 1644/530, loss: 0.03929116204380989
2023-01-24 10:00:32.106790: step: 1648/530, loss: 0.003633128711953759
2023-01-24 10:00:33.210590: step: 1652/530, loss: 0.0004056805628351867
2023-01-24 10:00:34.312931: step: 1656/530, loss: 0.00047271084622479975
2023-01-24 10:00:35.401400: step: 1660/530, loss: 0.00017324018699582666
2023-01-24 10:00:36.496485: step: 1664/530, loss: 0.0009093162370845675
2023-01-24 10:00:37.598607: step: 1668/530, loss: 0.0016274412628263235
2023-01-24 10:00:38.679727: step: 1672/530, loss: 2.1692556401831098e-05
2023-01-24 10:00:39.769809: step: 1676/530, loss: 0.002160932868719101
2023-01-24 10:00:40.859413: step: 1680/530, loss: 0.002776879584416747
2023-01-24 10:00:41.934931: step: 1684/530, loss: 0.0
2023-01-24 10:00:43.029305: step: 1688/530, loss: 0.001768921036273241
2023-01-24 10:00:44.120629: step: 1692/530, loss: 8.10049386927858e-05
2023-01-24 10:00:45.203398: step: 1696/530, loss: 0.0010290194768458605
2023-01-24 10:00:46.316377: step: 1700/530, loss: 0.004831664729863405
2023-01-24 10:00:47.403671: step: 1704/530, loss: 0.004273466765880585
2023-01-24 10:00:48.505975: step: 1708/530, loss: 0.003378627821803093
2023-01-24 10:00:49.582027: step: 1712/530, loss: 0.004147721920162439
2023-01-24 10:00:50.681727: step: 1716/530, loss: 0.004268621560186148
2023-01-24 10:00:51.781721: step: 1720/530, loss: 0.004693754017353058
2023-01-24 10:00:52.889396: step: 1724/530, loss: 0.004603015258908272
2023-01-24 10:00:53.988680: step: 1728/530, loss: 0.08938749134540558
2023-01-24 10:00:55.074201: step: 1732/530, loss: 0.005390554666519165
2023-01-24 10:00:56.172430: step: 1736/530, loss: 0.0003526887157931924
2023-01-24 10:00:57.272358: step: 1740/530, loss: 0.010446108877658844
2023-01-24 10:00:58.359654: step: 1744/530, loss: 0.00035366369411349297
2023-01-24 10:00:59.456490: step: 1748/530, loss: 0.002506296383216977
2023-01-24 10:01:00.531311: step: 1752/530, loss: 0.0028603640384972095
2023-01-24 10:01:01.625345: step: 1756/530, loss: 0.0045945653691887856
2023-01-24 10:01:02.735151: step: 1760/530, loss: 0.004601327236741781
2023-01-24 10:01:03.837656: step: 1764/530, loss: 0.013493113219738007
2023-01-24 10:01:04.915692: step: 1768/530, loss: 0.0003100834437645972
2023-01-24 10:01:06.012374: step: 1772/530, loss: 0.013857807964086533
2023-01-24 10:01:07.116825: step: 1776/530, loss: 0.003310558618977666
2023-01-24 10:01:08.188188: step: 1780/530, loss: 0.002016305923461914
2023-01-24 10:01:09.306923: step: 1784/530, loss: 0.004242977127432823
2023-01-24 10:01:10.416231: step: 1788/530, loss: 0.004578152671456337
2023-01-24 10:01:11.513519: step: 1792/530, loss: 0.0019369639921933413
2023-01-24 10:01:12.620870: step: 1796/530, loss: 7.450491921190405e-07
2023-01-24 10:01:13.719716: step: 1800/530, loss: 0.0041890013962984085
2023-01-24 10:01:14.808926: step: 1804/530, loss: 0.0003966613730881363
2023-01-24 10:01:15.895356: step: 1808/530, loss: 0.0009504702175036073
2023-01-24 10:01:16.981294: step: 1812/530, loss: 0.0070826588198542595
2023-01-24 10:01:18.092619: step: 1816/530, loss: 0.00793431419879198
2023-01-24 10:01:19.165442: step: 1820/530, loss: 0.0007111338200047612
2023-01-24 10:01:20.283927: step: 1824/530, loss: 0.02384822629392147
2023-01-24 10:01:21.397529: step: 1828/530, loss: 0.011601111851632595
2023-01-24 10:01:22.488406: step: 1832/530, loss: 0.000378284981707111
2023-01-24 10:01:23.572721: step: 1836/530, loss: 0.004807294346392155
2023-01-24 10:01:24.658186: step: 1840/530, loss: 0.0010158069198951125
2023-01-24 10:01:25.741730: step: 1844/530, loss: 0.004164641257375479
2023-01-24 10:01:26.816496: step: 1848/530, loss: 0.0009046039776876569
2023-01-24 10:01:27.895433: step: 1852/530, loss: 6.486716756626265e-06
2023-01-24 10:01:28.985478: step: 1856/530, loss: 0.003988295793533325
2023-01-24 10:01:30.087609: step: 1860/530, loss: 0.002295270562171936
2023-01-24 10:01:31.171145: step: 1864/530, loss: 0.0038218514528125525
2023-01-24 10:01:32.246958: step: 1868/530, loss: 0.0015781333204358816
2023-01-24 10:01:33.324318: step: 1872/530, loss: 0.008558275178074837
2023-01-24 10:01:34.442607: step: 1876/530, loss: 0.005718821659684181
2023-01-24 10:01:35.549866: step: 1880/530, loss: 0.0019060020567849278
2023-01-24 10:01:36.642989: step: 1884/530, loss: 0.011836216785013676
2023-01-24 10:01:37.727745: step: 1888/530, loss: 0.0028520463965833187
2023-01-24 10:01:38.834426: step: 1892/530, loss: 0.011126195080578327
2023-01-24 10:01:39.944056: step: 1896/530, loss: 0.005881585646420717
2023-01-24 10:01:41.036041: step: 1900/530, loss: 0.0021082295570522547
2023-01-24 10:01:42.138745: step: 1904/530, loss: 0.0027009572368115187
2023-01-24 10:01:43.241019: step: 1908/530, loss: 0.006047988776117563
2023-01-24 10:01:44.344605: step: 1912/530, loss: 0.0039531332440674305
2023-01-24 10:01:45.437510: step: 1916/530, loss: 0.005742067936807871
2023-01-24 10:01:46.511738: step: 1920/530, loss: 0.0011928094318136573
2023-01-24 10:01:47.598584: step: 1924/530, loss: 0.0011774139711633325
2023-01-24 10:01:48.692063: step: 1928/530, loss: 0.0015301486710086465
2023-01-24 10:01:49.783762: step: 1932/530, loss: 0.003928130026906729
2023-01-24 10:01:50.879287: step: 1936/530, loss: 0.0003547614032868296
2023-01-24 10:01:51.975697: step: 1940/530, loss: 0.0043481444008648396
2023-01-24 10:01:53.059324: step: 1944/530, loss: 0.003280860371887684
2023-01-24 10:01:54.166835: step: 1948/530, loss: 0.0063994633965194225
2023-01-24 10:01:55.273060: step: 1952/530, loss: 0.0040566879324615
2023-01-24 10:01:56.356435: step: 1956/530, loss: 1.2758776392729487e-05
2023-01-24 10:01:57.464055: step: 1960/530, loss: 0.002702544443309307
2023-01-24 10:01:58.552721: step: 1964/530, loss: 0.004193741362541914
2023-01-24 10:01:59.618406: step: 1968/530, loss: 0.003984420094639063
2023-01-24 10:02:00.716651: step: 1972/530, loss: 0.003577832132577896
2023-01-24 10:02:01.806591: step: 1976/530, loss: 0.004695831798017025
2023-01-24 10:02:02.890133: step: 1980/530, loss: 0.00024278204364236444
2023-01-24 10:02:03.985889: step: 1984/530, loss: 0.00016520480858162045
2023-01-24 10:02:05.079056: step: 1988/530, loss: 0.0004756670678034425
2023-01-24 10:02:06.191049: step: 1992/530, loss: 0.005009965039789677
2023-01-24 10:02:07.264024: step: 1996/530, loss: 0.00016160421364475042
2023-01-24 10:02:08.359880: step: 2000/530, loss: 0.002480706898495555
2023-01-24 10:02:09.470429: step: 2004/530, loss: 0.00024894674425013363
2023-01-24 10:02:10.576664: step: 2008/530, loss: 0.006939046084880829
2023-01-24 10:02:11.662263: step: 2012/530, loss: 0.02630123309791088
2023-01-24 10:02:12.759707: step: 2016/530, loss: 0.001474782358855009
2023-01-24 10:02:13.839519: step: 2020/530, loss: 0.004352755844593048
2023-01-24 10:02:14.933746: step: 2024/530, loss: 0.013139724731445312
2023-01-24 10:02:16.019591: step: 2028/530, loss: 4.3009305954910815e-05
2023-01-24 10:02:17.119224: step: 2032/530, loss: 0.0018679157365113497
2023-01-24 10:02:18.218047: step: 2036/530, loss: 0.0032187236938625574
2023-01-24 10:02:19.325801: step: 2040/530, loss: 0.0013946050312370062
2023-01-24 10:02:20.402503: step: 2044/530, loss: 0.004480474628508091
2023-01-24 10:02:21.496937: step: 2048/530, loss: 0.00010630625183694065
2023-01-24 10:02:22.620004: step: 2052/530, loss: 0.02964196354150772
2023-01-24 10:02:23.704530: step: 2056/530, loss: 0.006195282097905874
2023-01-24 10:02:24.789278: step: 2060/530, loss: 0.005950705148279667
2023-01-24 10:02:25.884300: step: 2064/530, loss: 0.006208291742950678
2023-01-24 10:02:26.963590: step: 2068/530, loss: 0.0176533255726099
2023-01-24 10:02:28.053179: step: 2072/530, loss: 0.0007111184531822801
2023-01-24 10:02:29.134540: step: 2076/530, loss: 0.0028486649971455336
2023-01-24 10:02:30.223047: step: 2080/530, loss: 0.0017024489352479577
2023-01-24 10:02:31.296995: step: 2084/530, loss: 0.00044607679592445493
2023-01-24 10:02:32.367257: step: 2088/530, loss: 0.005664762109518051
2023-01-24 10:02:33.459472: step: 2092/530, loss: 0.011150743812322617
2023-01-24 10:02:34.547615: step: 2096/530, loss: 0.0023099160753190517
2023-01-24 10:02:35.634618: step: 2100/530, loss: 0.007214162033051252
2023-01-24 10:02:36.728237: step: 2104/530, loss: 0.001990193733945489
2023-01-24 10:02:37.816521: step: 2108/530, loss: 0.003204174805432558
2023-01-24 10:02:38.900311: step: 2112/530, loss: 0.002190495142713189
2023-01-24 10:02:39.982322: step: 2116/530, loss: 0.0008908937452360988
2023-01-24 10:02:41.084662: step: 2120/530, loss: 0.004174768924713135
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3471032385956325, 'r': 0.34578595875276485, 'f1': 0.34644334650704767}, 'combined': 0.2552740447946667, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34648004362187335, 'r': 0.2762244462504747, 'f1': 0.3073890095313483}, 'combined': 0.19090475328789, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38602906240101365, 'r': 0.3303588370832204, 'f1': 0.35603089395267307}, 'combined': 0.26233855343881174, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33620687559701207, 'r': 0.26345064461307366, 'f1': 0.29541501645255464}, 'combined': 0.1834682733757971, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37754575311906147, 'r': 0.32596454965687466, 'f1': 0.3498641907722463}, 'combined': 0.25779466688481306, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3493160964356379, 'r': 0.27096159654345425, 'f1': 0.30518991174399085}, 'combined': 0.18953899781995223, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 10:05:08.599713: step: 4/530, loss: 0.00041957953362725675
2023-01-24 10:05:09.677224: step: 8/530, loss: 0.0012305567506700754
2023-01-24 10:05:10.741147: step: 12/530, loss: 0.0003846187610179186
2023-01-24 10:05:11.864249: step: 16/530, loss: 0.0017954891081899405
2023-01-24 10:05:12.935924: step: 20/530, loss: 0.005422938149422407
2023-01-24 10:05:14.017619: step: 24/530, loss: 0.002643261570483446
2023-01-24 10:05:15.103285: step: 28/530, loss: 0.0018135977443307638
2023-01-24 10:05:16.181416: step: 32/530, loss: 0.00037464252091012895
2023-01-24 10:05:17.253886: step: 36/530, loss: 0.0020497890654951334
2023-01-24 10:05:18.329775: step: 40/530, loss: 0.006587619427591562
2023-01-24 10:05:19.408383: step: 44/530, loss: 0.0009700774680823088
2023-01-24 10:05:20.515714: step: 48/530, loss: 0.0007794132689014077
2023-01-24 10:05:21.597823: step: 52/530, loss: 0.009133766405284405
2023-01-24 10:05:22.663317: step: 56/530, loss: 0.0033496320247650146
2023-01-24 10:05:23.762030: step: 60/530, loss: 0.011073989793658257
2023-01-24 10:05:24.837607: step: 64/530, loss: 0.004006025847047567
2023-01-24 10:05:25.928751: step: 68/530, loss: 0.0008794956956990063
2023-01-24 10:05:27.038968: step: 72/530, loss: 0.005165646784007549
2023-01-24 10:05:28.122153: step: 76/530, loss: 0.011668819934129715
2023-01-24 10:05:29.191095: step: 80/530, loss: 0.0006029019132256508
2023-01-24 10:05:30.271574: step: 84/530, loss: 0.0005558215198107064
2023-01-24 10:05:31.377518: step: 88/530, loss: 0.0032922138925641775
2023-01-24 10:05:32.474691: step: 92/530, loss: 0.0003902245662175119
2023-01-24 10:05:33.573041: step: 96/530, loss: 0.005438562016934156
2023-01-24 10:05:34.661086: step: 100/530, loss: 0.0003223950625397265
2023-01-24 10:05:35.748818: step: 104/530, loss: 0.0024952334351837635
2023-01-24 10:05:36.851832: step: 108/530, loss: 0.0030183882918208838
2023-01-24 10:05:37.941058: step: 112/530, loss: 0.0002886571455746889
2023-01-24 10:05:39.017965: step: 116/530, loss: 0.007234872318804264
2023-01-24 10:05:40.118035: step: 120/530, loss: 0.0008107398170977831
2023-01-24 10:05:41.206205: step: 124/530, loss: 0.0011682487092912197
2023-01-24 10:05:42.290238: step: 128/530, loss: 0.00020595089881680906
2023-01-24 10:05:43.374516: step: 132/530, loss: 0.00039724650559946895
2023-01-24 10:05:44.451100: step: 136/530, loss: 0.007038023788481951
2023-01-24 10:05:45.542043: step: 140/530, loss: 0.0032320325262844563
2023-01-24 10:05:46.652405: step: 144/530, loss: 0.009678706526756287
2023-01-24 10:05:47.732666: step: 148/530, loss: 0.003409762866795063
2023-01-24 10:05:48.829728: step: 152/530, loss: 0.0020736628212034702
2023-01-24 10:05:49.907715: step: 156/530, loss: 0.001371394144371152
2023-01-24 10:05:50.984047: step: 160/530, loss: 0.0038567499723285437
2023-01-24 10:05:52.070209: step: 164/530, loss: 0.003594342153519392
2023-01-24 10:05:53.160342: step: 168/530, loss: 0.002544281305745244
2023-01-24 10:05:54.244367: step: 172/530, loss: 0.0010763269383460283
2023-01-24 10:05:55.319544: step: 176/530, loss: 0.00584668293595314
2023-01-24 10:05:56.397750: step: 180/530, loss: 0.005828606430441141
2023-01-24 10:05:57.479645: step: 184/530, loss: 6.124362698756158e-06
2023-01-24 10:05:58.560956: step: 188/530, loss: 0.0013317487901076674
2023-01-24 10:05:59.641838: step: 192/530, loss: 0.0005292042624205351
2023-01-24 10:06:00.743887: step: 196/530, loss: 0.0014115390367805958
2023-01-24 10:06:01.830525: step: 200/530, loss: 0.0025520212948322296
2023-01-24 10:06:02.929919: step: 204/530, loss: 0.005806716158986092
2023-01-24 10:06:04.028485: step: 208/530, loss: 0.0013863842468708754
2023-01-24 10:06:05.115130: step: 212/530, loss: 2.3006439732853323e-05
2023-01-24 10:06:06.203007: step: 216/530, loss: 0.0016012545675039291
2023-01-24 10:06:07.285615: step: 220/530, loss: 0.0009532867697998881
2023-01-24 10:06:08.402137: step: 224/530, loss: 0.0001585626305313781
2023-01-24 10:06:09.518430: step: 228/530, loss: 0.0008216666174121201
2023-01-24 10:06:10.593923: step: 232/530, loss: 0.0181658286601305
2023-01-24 10:06:11.685265: step: 236/530, loss: 0.0004386380023788661
2023-01-24 10:06:12.797367: step: 240/530, loss: 0.0039194850251078606
2023-01-24 10:06:13.885757: step: 244/530, loss: 0.0023481573443859816
2023-01-24 10:06:14.956226: step: 248/530, loss: 0.00583037082105875
2023-01-24 10:06:16.070789: step: 252/530, loss: 0.00710871908813715
2023-01-24 10:06:17.160576: step: 256/530, loss: 0.012729004956781864
2023-01-24 10:06:18.249838: step: 260/530, loss: 0.026176651939749718
2023-01-24 10:06:19.338977: step: 264/530, loss: 4.958019781042822e-05
2023-01-24 10:06:20.427561: step: 268/530, loss: 0.027267776429653168
2023-01-24 10:06:21.556809: step: 272/530, loss: 0.0014167454792186618
2023-01-24 10:06:22.668857: step: 276/530, loss: 0.006288043223321438
2023-01-24 10:06:23.763396: step: 280/530, loss: 0.0007312045199796557
2023-01-24 10:06:24.876506: step: 284/530, loss: 0.00029566502780653536
2023-01-24 10:06:25.978271: step: 288/530, loss: 0.0020559243857860565
2023-01-24 10:06:27.067679: step: 292/530, loss: 0.00029819586779922247
2023-01-24 10:06:28.161549: step: 296/530, loss: 0.0036456305533647537
2023-01-24 10:06:29.223015: step: 300/530, loss: 8.203275683626998e-06
2023-01-24 10:06:30.302835: step: 304/530, loss: 0.0025169288273900747
2023-01-24 10:06:31.411246: step: 308/530, loss: 0.005093428771942854
2023-01-24 10:06:32.501940: step: 312/530, loss: 0.0043222238309681416
2023-01-24 10:06:33.622698: step: 316/530, loss: 0.007977612316608429
2023-01-24 10:06:34.708690: step: 320/530, loss: 0.0004820974136237055
2023-01-24 10:06:35.787043: step: 324/530, loss: 0.002975445007905364
2023-01-24 10:06:36.860370: step: 328/530, loss: 0.002435133093968034
2023-01-24 10:06:37.985816: step: 332/530, loss: 0.0035984329879283905
2023-01-24 10:06:39.089445: step: 336/530, loss: 0.0008130475180223584
2023-01-24 10:06:40.182972: step: 340/530, loss: 0.0005286601954139769
2023-01-24 10:06:41.289291: step: 344/530, loss: 0.03124627098441124
2023-01-24 10:06:42.402343: step: 348/530, loss: 0.004316762555390596
2023-01-24 10:06:43.534217: step: 352/530, loss: 0.002753043081611395
2023-01-24 10:06:44.629806: step: 356/530, loss: 0.004522338975220919
2023-01-24 10:06:45.705994: step: 360/530, loss: 4.239913323544897e-06
2023-01-24 10:06:46.834266: step: 364/530, loss: 0.002400033175945282
2023-01-24 10:06:47.911950: step: 368/530, loss: 0.0008092439966276288
2023-01-24 10:06:49.011022: step: 372/530, loss: 0.006402950268238783
2023-01-24 10:06:50.097638: step: 376/530, loss: 0.0034164160024374723
2023-01-24 10:06:51.206308: step: 380/530, loss: 0.00027832461637444794
2023-01-24 10:06:52.276765: step: 384/530, loss: 0.0016440374311059713
2023-01-24 10:06:53.367642: step: 388/530, loss: 0.0007841635379008949
2023-01-24 10:06:54.459213: step: 392/530, loss: 0.0018719471991062164
2023-01-24 10:06:55.546511: step: 396/530, loss: 0.0010516648180782795
2023-01-24 10:06:56.632373: step: 400/530, loss: 0.00862325169146061
2023-01-24 10:06:57.732886: step: 404/530, loss: 0.006379847414791584
2023-01-24 10:06:58.829757: step: 408/530, loss: 0.0010357204591855407
2023-01-24 10:06:59.932220: step: 412/530, loss: 0.008124977350234985
2023-01-24 10:07:01.051831: step: 416/530, loss: 0.0010897415922954679
2023-01-24 10:07:02.144593: step: 420/530, loss: 0.007163804490119219
2023-01-24 10:07:03.246196: step: 424/530, loss: 0.0009442644077353179
2023-01-24 10:07:04.347227: step: 428/530, loss: 0.0017286279471591115
2023-01-24 10:07:05.416600: step: 432/530, loss: 0.007969128899276257
2023-01-24 10:07:06.493014: step: 436/530, loss: 0.0007324569160118699
2023-01-24 10:07:07.576903: step: 440/530, loss: 0.00875879917293787
2023-01-24 10:07:08.666683: step: 444/530, loss: 0.007760476320981979
2023-01-24 10:07:09.762066: step: 448/530, loss: 0.0014678913867101073
2023-01-24 10:07:10.861197: step: 452/530, loss: 1.8849799744202755e-05
2023-01-24 10:07:11.934576: step: 456/530, loss: 0.01136686559766531
2023-01-24 10:07:13.032637: step: 460/530, loss: 0.0040018693543970585
2023-01-24 10:07:14.140488: step: 464/530, loss: 0.003364595817402005
2023-01-24 10:07:15.220099: step: 468/530, loss: 0.001970995217561722
2023-01-24 10:07:16.296516: step: 472/530, loss: 0.0007398941088467836
2023-01-24 10:07:17.395746: step: 476/530, loss: 0.004584888927638531
2023-01-24 10:07:18.467653: step: 480/530, loss: 0.0002695714065339416
2023-01-24 10:07:19.555549: step: 484/530, loss: 0.0005539420526474714
2023-01-24 10:07:20.638864: step: 488/530, loss: 0.025037281215190887
2023-01-24 10:07:21.722594: step: 492/530, loss: 0.0032129879109561443
2023-01-24 10:07:22.806706: step: 496/530, loss: 0.00039441286935471
2023-01-24 10:07:23.912748: step: 500/530, loss: 0.004720891825854778
2023-01-24 10:07:25.004167: step: 504/530, loss: 0.0011298924218863249
2023-01-24 10:07:26.093450: step: 508/530, loss: 0.00041900365613400936
2023-01-24 10:07:27.194626: step: 512/530, loss: 4.196471854811534e-05
2023-01-24 10:07:28.326706: step: 516/530, loss: 0.013871035538613796
2023-01-24 10:07:29.412494: step: 520/530, loss: 0.00013691623462364078
2023-01-24 10:07:30.518055: step: 524/530, loss: 0.008406477980315685
2023-01-24 10:07:31.608799: step: 528/530, loss: 0.003086388809606433
2023-01-24 10:07:32.693844: step: 532/530, loss: 0.006190589163452387
2023-01-24 10:07:33.775160: step: 536/530, loss: 0.007421389222145081
2023-01-24 10:07:34.872718: step: 540/530, loss: 0.002495412714779377
2023-01-24 10:07:35.972295: step: 544/530, loss: 0.007445516996085644
2023-01-24 10:07:37.077409: step: 548/530, loss: 0.0011785250389948487
2023-01-24 10:07:38.164228: step: 552/530, loss: 0.0008654675912111998
2023-01-24 10:07:39.267895: step: 556/530, loss: 0.00025137377087958157
2023-01-24 10:07:40.341834: step: 560/530, loss: 0.00017511122860014439
2023-01-24 10:07:41.438921: step: 564/530, loss: 5.7159009884344414e-05
2023-01-24 10:07:42.546886: step: 568/530, loss: 0.016914788633584976
2023-01-24 10:07:43.622617: step: 572/530, loss: 0.0009976305300369859
2023-01-24 10:07:44.721575: step: 576/530, loss: 0.0006685921689495444
2023-01-24 10:07:45.822373: step: 580/530, loss: 0.0037347576580941677
2023-01-24 10:07:46.904179: step: 584/530, loss: 0.0013946848921477795
2023-01-24 10:07:47.998706: step: 588/530, loss: 0.003970451653003693
2023-01-24 10:07:49.081005: step: 592/530, loss: 0.0001628063910175115
2023-01-24 10:07:50.172064: step: 596/530, loss: 0.0008422298706136644
2023-01-24 10:07:51.248628: step: 600/530, loss: 0.00029587431345134974
2023-01-24 10:07:52.337461: step: 604/530, loss: 0.0006361801060847938
2023-01-24 10:07:53.430897: step: 608/530, loss: 0.0034885662607848644
2023-01-24 10:07:54.507367: step: 612/530, loss: 0.0003585990925785154
2023-01-24 10:07:55.568627: step: 616/530, loss: 2.5604125767131336e-05
2023-01-24 10:07:56.669944: step: 620/530, loss: 0.0016611746978014708
2023-01-24 10:07:57.757181: step: 624/530, loss: 0.002439285861328244
2023-01-24 10:07:58.845872: step: 628/530, loss: 3.925748387700878e-05
2023-01-24 10:07:59.940778: step: 632/530, loss: 0.0038144635036587715
2023-01-24 10:08:01.047145: step: 636/530, loss: 0.01120692491531372
2023-01-24 10:08:02.116216: step: 640/530, loss: 2.340239916520659e-05
2023-01-24 10:08:03.212817: step: 644/530, loss: 0.0017313751159235835
2023-01-24 10:08:04.311414: step: 648/530, loss: 0.0017275534337386489
2023-01-24 10:08:05.401853: step: 652/530, loss: 2.3065988443704555e-06
2023-01-24 10:08:06.501702: step: 656/530, loss: 0.0029233889654278755
2023-01-24 10:08:07.596147: step: 660/530, loss: 0.0032414367888122797
2023-01-24 10:08:08.685475: step: 664/530, loss: 0.006235004402697086
2023-01-24 10:08:09.779308: step: 668/530, loss: 0.0024263113737106323
2023-01-24 10:08:10.873156: step: 672/530, loss: 0.0033212851267307997
2023-01-24 10:08:11.976076: step: 676/530, loss: 7.125129195628688e-05
2023-01-24 10:08:13.063796: step: 680/530, loss: 0.0008174025570042431
2023-01-24 10:08:14.166728: step: 684/530, loss: 0.006060808897018433
2023-01-24 10:08:15.227673: step: 688/530, loss: 0.0027228742837905884
2023-01-24 10:08:16.317870: step: 692/530, loss: 0.002320940140634775
2023-01-24 10:08:17.405544: step: 696/530, loss: 0.0010438866447657347
2023-01-24 10:08:18.474386: step: 700/530, loss: 0.004476509522646666
2023-01-24 10:08:19.586865: step: 704/530, loss: 0.0029681925661861897
2023-01-24 10:08:20.675906: step: 708/530, loss: 0.00013709232734981924
2023-01-24 10:08:21.758889: step: 712/530, loss: 0.006894290912896395
2023-01-24 10:08:22.846628: step: 716/530, loss: 0.0019235251238569617
2023-01-24 10:08:23.936312: step: 720/530, loss: 0.0003483947948552668
2023-01-24 10:08:25.013833: step: 724/530, loss: 0.0012323943665251136
2023-01-24 10:08:26.117101: step: 728/530, loss: 0.0049696979112923145
2023-01-24 10:08:27.191613: step: 732/530, loss: 0.00313419452868402
2023-01-24 10:08:28.283491: step: 736/530, loss: 0.0002585958573035896
2023-01-24 10:08:29.359200: step: 740/530, loss: 0.002907141810283065
2023-01-24 10:08:30.436394: step: 744/530, loss: 0.0005720037734135985
2023-01-24 10:08:31.539316: step: 748/530, loss: 0.09205687046051025
2023-01-24 10:08:32.643968: step: 752/530, loss: 0.0011814923491328955
2023-01-24 10:08:33.721630: step: 756/530, loss: 0.0026381819043308496
2023-01-24 10:08:34.813917: step: 760/530, loss: 4.626006193575449e-05
2023-01-24 10:08:35.885338: step: 764/530, loss: 0.015169908292591572
2023-01-24 10:08:36.975826: step: 768/530, loss: 0.005272774491459131
2023-01-24 10:08:38.063747: step: 772/530, loss: 0.003081422531977296
2023-01-24 10:08:39.170817: step: 776/530, loss: 0.0010419772006571293
2023-01-24 10:08:40.288444: step: 780/530, loss: 0.0028410006780177355
2023-01-24 10:08:41.401999: step: 784/530, loss: 0.010967368260025978
2023-01-24 10:08:42.481934: step: 788/530, loss: 0.008490442298352718
2023-01-24 10:08:43.563718: step: 792/530, loss: 0.004188038408756256
2023-01-24 10:08:44.674279: step: 796/530, loss: 0.00353723275475204
2023-01-24 10:08:45.787233: step: 800/530, loss: 0.008835950866341591
2023-01-24 10:08:46.885216: step: 804/530, loss: 0.014122353866696358
2023-01-24 10:08:47.959338: step: 808/530, loss: 0.0019575064070522785
2023-01-24 10:08:49.057299: step: 812/530, loss: 0.0001283080637222156
2023-01-24 10:08:50.159073: step: 816/530, loss: 0.006627049762755632
2023-01-24 10:08:51.225814: step: 820/530, loss: 0.0010814443230628967
2023-01-24 10:08:52.300869: step: 824/530, loss: 0.0007403788040392101
2023-01-24 10:08:53.396401: step: 828/530, loss: 0.002512782346457243
2023-01-24 10:08:54.523581: step: 832/530, loss: 0.00648350128903985
2023-01-24 10:08:55.633125: step: 836/530, loss: 0.006590052507817745
2023-01-24 10:08:56.723623: step: 840/530, loss: 0.00013365535414777696
2023-01-24 10:08:57.821046: step: 844/530, loss: 0.005512470379471779
2023-01-24 10:08:58.909646: step: 848/530, loss: 0.0005471798358485103
2023-01-24 10:09:00.020775: step: 852/530, loss: 0.006437006406486034
2023-01-24 10:09:01.098031: step: 856/530, loss: 0.0017111505148932338
2023-01-24 10:09:02.173588: step: 860/530, loss: 0.0020091054029762745
2023-01-24 10:09:03.266883: step: 864/530, loss: 0.0004005547962151468
2023-01-24 10:09:04.358392: step: 868/530, loss: 0.002750362968072295
2023-01-24 10:09:05.444998: step: 872/530, loss: 0.005676696542650461
2023-01-24 10:09:06.551992: step: 876/530, loss: 0.0051183272153139114
2023-01-24 10:09:07.637604: step: 880/530, loss: 0.0007667641621083021
2023-01-24 10:09:08.720724: step: 884/530, loss: 0.0025634237099438906
2023-01-24 10:09:09.789950: step: 888/530, loss: 0.0021997729782015085
2023-01-24 10:09:10.898177: step: 892/530, loss: 0.00013588348519988358
2023-01-24 10:09:12.005540: step: 896/530, loss: 0.01640518195927143
2023-01-24 10:09:13.090745: step: 900/530, loss: 0.0008989162743091583
2023-01-24 10:09:14.193166: step: 904/530, loss: 0.001824555336497724
2023-01-24 10:09:15.281015: step: 908/530, loss: 0.0010768282227218151
2023-01-24 10:09:16.381557: step: 912/530, loss: 0.004957268945872784
2023-01-24 10:09:17.471368: step: 916/530, loss: 0.00736016733571887
2023-01-24 10:09:18.585401: step: 920/530, loss: 0.004380638711154461
2023-01-24 10:09:19.662023: step: 924/530, loss: 0.002497141482308507
2023-01-24 10:09:20.734840: step: 928/530, loss: 0.001268291613087058
2023-01-24 10:09:21.829330: step: 932/530, loss: 0.0005254681454971433
2023-01-24 10:09:22.936546: step: 936/530, loss: 0.002369712106883526
2023-01-24 10:09:24.027726: step: 940/530, loss: 0.0008978047408163548
2023-01-24 10:09:25.123948: step: 944/530, loss: 0.04146760702133179
2023-01-24 10:09:26.192700: step: 948/530, loss: 0.0008567434852011502
2023-01-24 10:09:27.283987: step: 952/530, loss: 0.00290684518404305
2023-01-24 10:09:28.353673: step: 956/530, loss: 0.00016746077744755894
2023-01-24 10:09:29.437495: step: 960/530, loss: 0.0019771752413362265
2023-01-24 10:09:30.538467: step: 964/530, loss: 0.0019547496922314167
2023-01-24 10:09:31.646880: step: 968/530, loss: 0.006751535460352898
2023-01-24 10:09:32.741361: step: 972/530, loss: 2.4312272216775455e-05
2023-01-24 10:09:33.829434: step: 976/530, loss: 0.004235660657286644
2023-01-24 10:09:34.921634: step: 980/530, loss: 0.011990902945399284
2023-01-24 10:09:36.037753: step: 984/530, loss: 0.001053488813340664
2023-01-24 10:09:37.151721: step: 988/530, loss: 0.0004209255857858807
2023-01-24 10:09:38.244476: step: 992/530, loss: 5.6086522818077356e-05
2023-01-24 10:09:39.331795: step: 996/530, loss: 0.0005520488484762609
2023-01-24 10:09:40.413131: step: 1000/530, loss: 0.00023184662859421223
2023-01-24 10:09:41.503257: step: 1004/530, loss: 2.11595477139781e-07
2023-01-24 10:09:42.615340: step: 1008/530, loss: 0.013235863298177719
2023-01-24 10:09:43.707636: step: 1012/530, loss: 0.010187349282205105
2023-01-24 10:09:44.798064: step: 1016/530, loss: 0.005687339697033167
2023-01-24 10:09:45.890954: step: 1020/530, loss: 0.0017560739070177078
2023-01-24 10:09:46.981420: step: 1024/530, loss: 0.0026939495000988245
2023-01-24 10:09:48.108267: step: 1028/530, loss: 0.007238706108182669
2023-01-24 10:09:49.194217: step: 1032/530, loss: 0.00013601387036032975
2023-01-24 10:09:50.283544: step: 1036/530, loss: 0.00045989060890860856
2023-01-24 10:09:51.374657: step: 1040/530, loss: 0.0032810233533382416
2023-01-24 10:09:52.465384: step: 1044/530, loss: 0.0004015865852124989
2023-01-24 10:09:53.579119: step: 1048/530, loss: 0.013448178768157959
2023-01-24 10:09:54.659808: step: 1052/530, loss: 0.003856315743178129
2023-01-24 10:09:55.816275: step: 1056/530, loss: 0.0005450118915177882
2023-01-24 10:09:56.890818: step: 1060/530, loss: 0.0
2023-01-24 10:09:57.977414: step: 1064/530, loss: 0.0008792424923740327
2023-01-24 10:09:59.071484: step: 1068/530, loss: 0.00823802500963211
2023-01-24 10:10:00.161301: step: 1072/530, loss: 2.6319603421143256e-06
2023-01-24 10:10:01.233496: step: 1076/530, loss: 0.0008064648136496544
2023-01-24 10:10:02.342838: step: 1080/530, loss: 0.006718065589666367
2023-01-24 10:10:03.449276: step: 1084/530, loss: 0.00017420953372493386
2023-01-24 10:10:04.569133: step: 1088/530, loss: 0.002185078337788582
2023-01-24 10:10:05.661805: step: 1092/530, loss: 0.00019640305254142731
2023-01-24 10:10:06.747545: step: 1096/530, loss: 0.006831278093159199
2023-01-24 10:10:07.828361: step: 1100/530, loss: 4.614041972672567e-05
2023-01-24 10:10:08.932242: step: 1104/530, loss: 0.0032910217996686697
2023-01-24 10:10:10.017334: step: 1108/530, loss: 0.0009668187703937292
2023-01-24 10:10:11.106860: step: 1112/530, loss: 0.0004408480308484286
2023-01-24 10:10:12.173347: step: 1116/530, loss: 0.0020132348872721195
2023-01-24 10:10:13.250644: step: 1120/530, loss: 0.005592492874711752
2023-01-24 10:10:14.337505: step: 1124/530, loss: 0.0005681593902409077
2023-01-24 10:10:15.417813: step: 1128/530, loss: 0.03897804021835327
2023-01-24 10:10:16.501632: step: 1132/530, loss: 0.014552135951817036
2023-01-24 10:10:17.599628: step: 1136/530, loss: 0.007389168720692396
2023-01-24 10:10:18.708111: step: 1140/530, loss: 0.0010538259521126747
2023-01-24 10:10:19.837875: step: 1144/530, loss: 0.0072760749608278275
2023-01-24 10:10:20.918478: step: 1148/530, loss: 0.001881799311377108
2023-01-24 10:10:21.992380: step: 1152/530, loss: 0.0050290850922465324
2023-01-24 10:10:23.087613: step: 1156/530, loss: 0.009101685136556625
2023-01-24 10:10:24.159385: step: 1160/530, loss: 0.0004510745930019766
2023-01-24 10:10:25.241722: step: 1164/530, loss: 0.0022820280864834785
2023-01-24 10:10:26.338486: step: 1168/530, loss: 0.0004817323060706258
2023-01-24 10:10:27.431427: step: 1172/530, loss: 0.017603395506739616
2023-01-24 10:10:28.504556: step: 1176/530, loss: 0.0006317555671557784
2023-01-24 10:10:29.589161: step: 1180/530, loss: 0.0017889713635668159
2023-01-24 10:10:30.676823: step: 1184/530, loss: 0.010875473730266094
2023-01-24 10:10:31.779606: step: 1188/530, loss: 0.004709660075604916
2023-01-24 10:10:32.860854: step: 1192/530, loss: 0.0010572028113529086
2023-01-24 10:10:33.927299: step: 1196/530, loss: 0.0007839778554625809
2023-01-24 10:10:35.020714: step: 1200/530, loss: 0.004494942259043455
2023-01-24 10:10:36.106433: step: 1204/530, loss: 0.0024047312326729298
2023-01-24 10:10:37.197420: step: 1208/530, loss: 0.0023907735012471676
2023-01-24 10:10:38.290152: step: 1212/530, loss: 5.270205747365253e-06
2023-01-24 10:10:39.415986: step: 1216/530, loss: 0.003890441497787833
2023-01-24 10:10:40.507580: step: 1220/530, loss: 0.001387719064950943
2023-01-24 10:10:41.599462: step: 1224/530, loss: 0.0012261300580576062
2023-01-24 10:10:42.695274: step: 1228/530, loss: 0.009833861142396927
2023-01-24 10:10:43.797072: step: 1232/530, loss: 0.010457347147166729
2023-01-24 10:10:44.897743: step: 1236/530, loss: 0.0009336344082839787
2023-01-24 10:10:45.963748: step: 1240/530, loss: 0.003212392795830965
2023-01-24 10:10:47.063908: step: 1244/530, loss: 0.0008669504313729703
2023-01-24 10:10:48.156476: step: 1248/530, loss: 0.00018693390302360058
2023-01-24 10:10:49.235880: step: 1252/530, loss: 0.0009722743998281658
2023-01-24 10:10:50.358215: step: 1256/530, loss: 0.006682408507913351
2023-01-24 10:10:51.446965: step: 1260/530, loss: 0.004756182432174683
2023-01-24 10:10:52.525570: step: 1264/530, loss: 0.0004418453900143504
2023-01-24 10:10:53.617251: step: 1268/530, loss: 0.012299046851694584
2023-01-24 10:10:54.737420: step: 1272/530, loss: 0.0004543860559351742
2023-01-24 10:10:55.835732: step: 1276/530, loss: 0.004451368935406208
2023-01-24 10:10:56.912785: step: 1280/530, loss: 0.0016371669480577111
2023-01-24 10:10:58.014755: step: 1284/530, loss: 0.001994268735870719
2023-01-24 10:10:59.087465: step: 1288/530, loss: 0.0020643984898924828
2023-01-24 10:11:00.153757: step: 1292/530, loss: 0.0007742835441604257
2023-01-24 10:11:01.229329: step: 1296/530, loss: 0.00020217744167894125
2023-01-24 10:11:02.318092: step: 1300/530, loss: 0.001714938087388873
2023-01-24 10:11:03.394682: step: 1304/530, loss: 0.00015804576105438173
2023-01-24 10:11:04.476987: step: 1308/530, loss: 3.625944009399973e-05
2023-01-24 10:11:05.558044: step: 1312/530, loss: 0.009256994351744652
2023-01-24 10:11:06.627316: step: 1316/530, loss: 6.166958337416872e-05
2023-01-24 10:11:07.700522: step: 1320/530, loss: 0.00343429041095078
2023-01-24 10:11:08.797352: step: 1324/530, loss: 0.00027316107298247516
2023-01-24 10:11:09.895452: step: 1328/530, loss: 0.0020564028527587652
2023-01-24 10:11:10.981686: step: 1332/530, loss: 0.004720047581940889
2023-01-24 10:11:12.065404: step: 1336/530, loss: 8.517401874996722e-05
2023-01-24 10:11:13.155661: step: 1340/530, loss: 0.0013121734373271465
2023-01-24 10:11:14.279209: step: 1344/530, loss: 0.005484965164214373
2023-01-24 10:11:15.358921: step: 1348/530, loss: 0.00012013780360575765
2023-01-24 10:11:16.480832: step: 1352/530, loss: 0.023909686133265495
2023-01-24 10:11:17.550527: step: 1356/530, loss: 0.0004580010718200356
2023-01-24 10:11:18.645047: step: 1360/530, loss: 8.234806045948062e-06
2023-01-24 10:11:19.759067: step: 1364/530, loss: 0.001918577472679317
2023-01-24 10:11:20.856379: step: 1368/530, loss: 0.003393137827515602
2023-01-24 10:11:21.919723: step: 1372/530, loss: 0.00019939703634008765
2023-01-24 10:11:23.031861: step: 1376/530, loss: 0.00010725236643338576
2023-01-24 10:11:24.123185: step: 1380/530, loss: 0.00024035417300183326
2023-01-24 10:11:25.203416: step: 1384/530, loss: 0.028011364862322807
2023-01-24 10:11:26.309022: step: 1388/530, loss: 0.0021849924232810736
2023-01-24 10:11:27.394302: step: 1392/530, loss: 0.0009893151000142097
2023-01-24 10:11:28.482971: step: 1396/530, loss: 0.002132462104782462
2023-01-24 10:11:29.570083: step: 1400/530, loss: 7.176028884714469e-05
2023-01-24 10:11:30.651713: step: 1404/530, loss: 0.022018464282155037
2023-01-24 10:11:31.736707: step: 1408/530, loss: 0.007787796203047037
2023-01-24 10:11:32.829624: step: 1412/530, loss: 0.002511626807972789
2023-01-24 10:11:33.928412: step: 1416/530, loss: 0.009674613364040852
2023-01-24 10:11:35.016368: step: 1420/530, loss: 2.9385002562776208e-05
2023-01-24 10:11:36.113851: step: 1424/530, loss: 0.0014973906800150871
2023-01-24 10:11:37.198469: step: 1428/530, loss: 0.07004883885383606
2023-01-24 10:11:38.293928: step: 1432/530, loss: 1.74994274857454e-05
2023-01-24 10:11:39.381363: step: 1436/530, loss: 0.0010433431016281247
2023-01-24 10:11:40.457035: step: 1440/530, loss: 0.0004845707444474101
2023-01-24 10:11:41.531391: step: 1444/530, loss: 0.0019190305611118674
2023-01-24 10:11:42.644956: step: 1448/530, loss: 0.003605431178584695
2023-01-24 10:11:43.741597: step: 1452/530, loss: 0.0008017189684323967
2023-01-24 10:11:44.837746: step: 1456/530, loss: 0.004502593539655209
2023-01-24 10:11:45.922947: step: 1460/530, loss: 0.00550076412037015
2023-01-24 10:11:47.010768: step: 1464/530, loss: 0.0018752755131572485
2023-01-24 10:11:48.129827: step: 1468/530, loss: 0.005419633816927671
2023-01-24 10:11:49.202537: step: 1472/530, loss: 0.0027900550048798323
2023-01-24 10:11:50.294801: step: 1476/530, loss: 0.005146119277924299
2023-01-24 10:11:51.391087: step: 1480/530, loss: 0.00032300723250955343
2023-01-24 10:11:52.490535: step: 1484/530, loss: 0.0007106717675924301
2023-01-24 10:11:53.559375: step: 1488/530, loss: 5.9772269196400885e-06
2023-01-24 10:11:54.644487: step: 1492/530, loss: 0.005116772372275591
2023-01-24 10:11:55.768692: step: 1496/530, loss: 0.006594047416001558
2023-01-24 10:11:56.850614: step: 1500/530, loss: 0.0037953134160488844
2023-01-24 10:11:57.945597: step: 1504/530, loss: 0.012371010147035122
2023-01-24 10:11:59.052854: step: 1508/530, loss: 0.004237303975969553
2023-01-24 10:12:00.159557: step: 1512/530, loss: 2.643659354362171e-05
2023-01-24 10:12:01.258754: step: 1516/530, loss: 0.015276732854545116
2023-01-24 10:12:02.358514: step: 1520/530, loss: 0.0010161424288526177
2023-01-24 10:12:03.441811: step: 1524/530, loss: 1.3737771041633096e-05
2023-01-24 10:12:04.524432: step: 1528/530, loss: 0.001201915554702282
2023-01-24 10:12:05.606695: step: 1532/530, loss: 0.025990746915340424
2023-01-24 10:12:06.703582: step: 1536/530, loss: 0.001058524358086288
2023-01-24 10:12:07.785274: step: 1540/530, loss: 0.0003789604816120118
2023-01-24 10:12:08.878168: step: 1544/530, loss: 0.0069553544744849205
2023-01-24 10:12:09.957038: step: 1548/530, loss: 0.00045877540833316743
2023-01-24 10:12:11.043806: step: 1552/530, loss: 0.0001989740558201447
2023-01-24 10:12:12.132534: step: 1556/530, loss: 0.0026985194999724627
2023-01-24 10:12:13.225217: step: 1560/530, loss: 0.0009219951462000608
2023-01-24 10:12:14.300863: step: 1564/530, loss: 0.0033113141544163227
2023-01-24 10:12:15.397174: step: 1568/530, loss: 0.0035611242055892944
2023-01-24 10:12:16.526216: step: 1572/530, loss: 0.004538318142294884
2023-01-24 10:12:17.598380: step: 1576/530, loss: 0.004159430041909218
2023-01-24 10:12:18.702914: step: 1580/530, loss: 0.0006233225576579571
2023-01-24 10:12:19.812071: step: 1584/530, loss: 0.0005770657444372773
2023-01-24 10:12:20.904262: step: 1588/530, loss: 0.0011998669942840934
2023-01-24 10:12:22.000631: step: 1592/530, loss: 0.006901716813445091
2023-01-24 10:12:23.101949: step: 1596/530, loss: 0.02905910648405552
2023-01-24 10:12:24.190701: step: 1600/530, loss: 0.0024881402496248484
2023-01-24 10:12:25.293521: step: 1604/530, loss: 0.003927901852875948
2023-01-24 10:12:26.364805: step: 1608/530, loss: 0.0007349054212681949
2023-01-24 10:12:27.461616: step: 1612/530, loss: 0.0011800610227510333
2023-01-24 10:12:28.567247: step: 1616/530, loss: 0.02105814591050148
2023-01-24 10:12:29.632623: step: 1620/530, loss: 0.0015395227819681168
2023-01-24 10:12:30.742124: step: 1624/530, loss: 0.010922984220087528
2023-01-24 10:12:31.822360: step: 1628/530, loss: 0.008248801343142986
2023-01-24 10:12:32.927708: step: 1632/530, loss: 0.01618781127035618
2023-01-24 10:12:34.005941: step: 1636/530, loss: 0.02958204410970211
2023-01-24 10:12:35.107610: step: 1640/530, loss: 4.399966564960778e-05
2023-01-24 10:12:36.180428: step: 1644/530, loss: 0.001968149794265628
2023-01-24 10:12:37.282960: step: 1648/530, loss: 0.0005820642109028995
2023-01-24 10:12:38.347086: step: 1652/530, loss: 0.005752319935709238
2023-01-24 10:12:39.434598: step: 1656/530, loss: 0.0050523472018539906
2023-01-24 10:12:40.538801: step: 1660/530, loss: 0.001452722353860736
2023-01-24 10:12:41.622393: step: 1664/530, loss: 0.005445309914648533
2023-01-24 10:12:42.700961: step: 1668/530, loss: 1.1548379141856913e-08
2023-01-24 10:12:43.786569: step: 1672/530, loss: 0.00011109039769507945
2023-01-24 10:12:44.883435: step: 1676/530, loss: 0.0018030399223789573
2023-01-24 10:12:45.970116: step: 1680/530, loss: 0.005194325931370258
2023-01-24 10:12:47.087444: step: 1684/530, loss: 0.00385474250651896
2023-01-24 10:12:48.182732: step: 1688/530, loss: 0.007741323672235012
2023-01-24 10:12:49.281835: step: 1692/530, loss: 0.01495644822716713
2023-01-24 10:12:50.398373: step: 1696/530, loss: 0.01685008406639099
2023-01-24 10:12:51.491202: step: 1700/530, loss: 0.0055544120259583
2023-01-24 10:12:52.617095: step: 1704/530, loss: 0.010248808190226555
2023-01-24 10:12:53.716210: step: 1708/530, loss: 0.011854437179863453
2023-01-24 10:12:54.807100: step: 1712/530, loss: 0.03471222519874573
2023-01-24 10:12:55.871191: step: 1716/530, loss: 0.0008398064528591931
2023-01-24 10:12:56.950192: step: 1720/530, loss: 0.0001746997149894014
2023-01-24 10:12:58.056800: step: 1724/530, loss: 0.0005755234742537141
2023-01-24 10:12:59.157332: step: 1728/530, loss: 0.0034256817307323217
2023-01-24 10:13:00.247663: step: 1732/530, loss: 0.021520541980862617
2023-01-24 10:13:01.347576: step: 1736/530, loss: 0.007916544564068317
2023-01-24 10:13:02.461289: step: 1740/530, loss: 0.0022996366024017334
2023-01-24 10:13:03.542056: step: 1744/530, loss: 0.0005643433541990817
2023-01-24 10:13:04.633431: step: 1748/530, loss: 0.0034838926512748003
2023-01-24 10:13:05.741718: step: 1752/530, loss: 0.03036956675350666
2023-01-24 10:13:06.823444: step: 1756/530, loss: 0.0007215047953650355
2023-01-24 10:13:07.904148: step: 1760/530, loss: 0.0019453135319054127
2023-01-24 10:13:08.983868: step: 1764/530, loss: 0.001330358674749732
2023-01-24 10:13:10.062683: step: 1768/530, loss: 0.007806940004229546
2023-01-24 10:13:11.161714: step: 1772/530, loss: 0.003456848906353116
2023-01-24 10:13:12.237313: step: 1776/530, loss: 0.005057643633335829
2023-01-24 10:13:13.324707: step: 1780/530, loss: 0.011384502053260803
2023-01-24 10:13:14.421300: step: 1784/530, loss: 0.011234925128519535
2023-01-24 10:13:15.492378: step: 1788/530, loss: 0.0047269645147025585
2023-01-24 10:13:16.593501: step: 1792/530, loss: 0.0001232069917023182
2023-01-24 10:13:17.683704: step: 1796/530, loss: 0.0016339218709617853
2023-01-24 10:13:18.792364: step: 1800/530, loss: 0.0014323396608233452
2023-01-24 10:13:19.890142: step: 1804/530, loss: 0.001967453630641103
2023-01-24 10:13:20.997162: step: 1808/530, loss: 0.009709027595818043
2023-01-24 10:13:22.071501: step: 1812/530, loss: 0.0005732905119657516
2023-01-24 10:13:23.173618: step: 1816/530, loss: 0.004624378867447376
2023-01-24 10:13:24.269165: step: 1820/530, loss: 0.0017234840197488666
2023-01-24 10:13:25.358159: step: 1824/530, loss: 6.280279194470495e-05
2023-01-24 10:13:26.458374: step: 1828/530, loss: 0.00363940536044538
2023-01-24 10:13:27.531429: step: 1832/530, loss: 0.0027547746431082487
2023-01-24 10:13:28.622101: step: 1836/530, loss: 0.006162369158118963
2023-01-24 10:13:29.717782: step: 1840/530, loss: 0.00149850535672158
2023-01-24 10:13:30.826479: step: 1844/530, loss: 0.004718123469501734
2023-01-24 10:13:31.916624: step: 1848/530, loss: 0.003149504540488124
2023-01-24 10:13:32.990734: step: 1852/530, loss: 0.00022196733334567398
2023-01-24 10:13:34.075585: step: 1856/530, loss: 0.006669645197689533
2023-01-24 10:13:35.211381: step: 1860/530, loss: 0.004956276621669531
2023-01-24 10:13:36.294604: step: 1864/530, loss: 0.002093520015478134
2023-01-24 10:13:37.384943: step: 1868/530, loss: 0.0007709778728894889
2023-01-24 10:13:38.477532: step: 1872/530, loss: 0.00627837935462594
2023-01-24 10:13:39.578518: step: 1876/530, loss: 0.005650392267853022
2023-01-24 10:13:40.678819: step: 1880/530, loss: 0.010585335083305836
2023-01-24 10:13:41.743319: step: 1884/530, loss: 6.372926691255998e-06
2023-01-24 10:13:42.841174: step: 1888/530, loss: 4.653074938687496e-05
2023-01-24 10:13:43.924789: step: 1892/530, loss: 0.010358398780226707
2023-01-24 10:13:45.015823: step: 1896/530, loss: 0.0019476724555715919
2023-01-24 10:13:46.110109: step: 1900/530, loss: 0.002111525274813175
2023-01-24 10:13:47.200838: step: 1904/530, loss: 0.001851673237979412
2023-01-24 10:13:48.288793: step: 1908/530, loss: 0.003778306767344475
2023-01-24 10:13:49.357439: step: 1912/530, loss: 0.0008608328062109649
2023-01-24 10:13:50.449933: step: 1916/530, loss: 0.0008358883787877858
2023-01-24 10:13:51.540979: step: 1920/530, loss: 0.002286526607349515
2023-01-24 10:13:52.613341: step: 1924/530, loss: 0.0006502037867903709
2023-01-24 10:13:53.697251: step: 1928/530, loss: 0.0028706425800919533
2023-01-24 10:13:54.780323: step: 1932/530, loss: 0.0030464837327599525
2023-01-24 10:13:55.905957: step: 1936/530, loss: 0.009233983233571053
2023-01-24 10:13:57.003933: step: 1940/530, loss: 0.024344248697161674
2023-01-24 10:13:58.102948: step: 1944/530, loss: 0.00017233123071491718
2023-01-24 10:13:59.159753: step: 1948/530, loss: 8.85099871084094e-05
2023-01-24 10:14:00.261961: step: 1952/530, loss: 0.015052702277898788
2023-01-24 10:14:01.361816: step: 1956/530, loss: 0.002015867503359914
2023-01-24 10:14:02.464332: step: 1960/530, loss: 0.009345891885459423
2023-01-24 10:14:03.554856: step: 1964/530, loss: 1.1462586371635552e-05
2023-01-24 10:14:04.645659: step: 1968/530, loss: 0.0023738304153084755
2023-01-24 10:14:05.724520: step: 1972/530, loss: 0.006011987570673227
2023-01-24 10:14:06.813838: step: 1976/530, loss: 0.0035228943452239037
2023-01-24 10:14:07.926694: step: 1980/530, loss: 0.006211179308593273
2023-01-24 10:14:09.003129: step: 1984/530, loss: 0.0008161471923813224
2023-01-24 10:14:10.070754: step: 1988/530, loss: 0.004560565575957298
2023-01-24 10:14:11.141477: step: 1992/530, loss: 0.000625628512352705
2023-01-24 10:14:12.256060: step: 1996/530, loss: 0.00011095472291344777
2023-01-24 10:14:13.337515: step: 2000/530, loss: 0.001555387512780726
2023-01-24 10:14:14.427314: step: 2004/530, loss: 0.00889945961534977
2023-01-24 10:14:15.507803: step: 2008/530, loss: 0.0014049547025933862
2023-01-24 10:14:16.595116: step: 2012/530, loss: 0.00033359084045514464
2023-01-24 10:14:17.695957: step: 2016/530, loss: 0.002479431452229619
2023-01-24 10:14:18.767532: step: 2020/530, loss: 0.00129645224660635
2023-01-24 10:14:19.862322: step: 2024/530, loss: 0.01016774121671915
2023-01-24 10:14:20.957624: step: 2028/530, loss: 0.004030562937259674
2023-01-24 10:14:22.055734: step: 2032/530, loss: 0.0014632843667641282
2023-01-24 10:14:23.129418: step: 2036/530, loss: 0.00033714438905008137
2023-01-24 10:14:24.222400: step: 2040/530, loss: 0.009767036885023117
2023-01-24 10:14:25.339566: step: 2044/530, loss: 0.012330167926847935
2023-01-24 10:14:26.429833: step: 2048/530, loss: 0.007674699183553457
2023-01-24 10:14:27.509930: step: 2052/530, loss: 0.005123947747051716
2023-01-24 10:14:28.585496: step: 2056/530, loss: 0.0001182538690045476
2023-01-24 10:14:29.663731: step: 2060/530, loss: 0.0014430314768105745
2023-01-24 10:14:30.757114: step: 2064/530, loss: 0.00013447781384456903
2023-01-24 10:14:31.853293: step: 2068/530, loss: 0.0013207438169047236
2023-01-24 10:14:32.942915: step: 2072/530, loss: 0.0016460088081657887
2023-01-24 10:14:34.006883: step: 2076/530, loss: 0.0016261229757219553
2023-01-24 10:14:35.090612: step: 2080/530, loss: 0.0006282105459831655
2023-01-24 10:14:36.200868: step: 2084/530, loss: 0.0004141568497288972
2023-01-24 10:14:37.289182: step: 2088/530, loss: 0.0039739953354001045
2023-01-24 10:14:38.378877: step: 2092/530, loss: 0.002581220120191574
2023-01-24 10:14:39.478386: step: 2096/530, loss: 0.006727252621203661
2023-01-24 10:14:40.577784: step: 2100/530, loss: 0.0035481418017297983
2023-01-24 10:14:41.654643: step: 2104/530, loss: 0.0016609999584034085
2023-01-24 10:14:42.760364: step: 2108/530, loss: 0.006071708630770445
2023-01-24 10:14:43.846326: step: 2112/530, loss: 0.00026346012600697577
2023-01-24 10:14:44.933923: step: 2116/530, loss: 8.357186743523926e-05
2023-01-24 10:14:46.010768: step: 2120/530, loss: 0.002504725707694888
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3477656493563112, 'r': 0.34578595875276485, 'f1': 0.34677297861599826}, 'combined': 0.2555169316117882, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34679021731914383, 'r': 0.27619853276603745, 'f1': 0.30749495617077}, 'combined': 0.1909705517271098, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3830203047504372, 'r': 0.329237567461002, 'f1': 0.35409836337132256}, 'combined': 0.260914583536764, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3346305830371129, 'r': 0.26221546674746105, 'f1': 0.29402997490130806}, 'combined': 0.18260808967554923, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37670286449820206, 'r': 0.32881084946712136, 'f1': 0.3511313427946767}, 'combined': 0.2587283578487092, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34703443617001994, 'r': 0.2699537371194232, 'f1': 0.30367921788115015}, 'combined': 0.18860077742092485, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 10:17:14.438273: step: 4/530, loss: 0.0005603269091807306
2023-01-24 10:17:15.521047: step: 8/530, loss: 0.0033836020156741142
2023-01-24 10:17:16.575829: step: 12/530, loss: 2.748173756117467e-05
2023-01-24 10:17:17.669542: step: 16/530, loss: 0.02031107433140278
2023-01-24 10:17:18.763131: step: 20/530, loss: 0.0024168984964489937
2023-01-24 10:17:19.831051: step: 24/530, loss: 0.0001324393815593794
2023-01-24 10:17:20.923230: step: 28/530, loss: 0.000845213420689106
2023-01-24 10:17:22.019029: step: 32/530, loss: 0.0005316843162290752
2023-01-24 10:17:23.082709: step: 36/530, loss: 1.4628681128669996e-05
2023-01-24 10:17:24.168018: step: 40/530, loss: 0.015268100425601006
2023-01-24 10:17:25.252213: step: 44/530, loss: 0.005782716907560825
2023-01-24 10:17:26.353148: step: 48/530, loss: 0.008466568775475025
2023-01-24 10:17:27.463350: step: 52/530, loss: 0.0008337254985235631
2023-01-24 10:17:28.573193: step: 56/530, loss: 0.010610067285597324
2023-01-24 10:17:29.657103: step: 60/530, loss: 0.002079881029203534
2023-01-24 10:17:30.742254: step: 64/530, loss: 0.0009238152415491641
2023-01-24 10:17:31.841787: step: 68/530, loss: 0.000500765978358686
2023-01-24 10:17:32.939033: step: 72/530, loss: 0.03360120952129364
2023-01-24 10:17:34.037701: step: 76/530, loss: 0.0009136134758591652
2023-01-24 10:17:35.126397: step: 80/530, loss: 0.003076310269534588
2023-01-24 10:17:36.204199: step: 84/530, loss: 0.001181140192784369
2023-01-24 10:17:37.283681: step: 88/530, loss: 0.00034104418591596186
2023-01-24 10:17:38.367346: step: 92/530, loss: 0.0012450501089915633
2023-01-24 10:17:39.447795: step: 96/530, loss: 0.0034340769052505493
2023-01-24 10:17:40.557197: step: 100/530, loss: 0.0008036938961595297
2023-01-24 10:17:41.633522: step: 104/530, loss: 7.929922139737755e-05
2023-01-24 10:17:42.722080: step: 108/530, loss: 0.0035339402966201305
2023-01-24 10:17:43.816753: step: 112/530, loss: 0.00012609059922397137
2023-01-24 10:17:44.905351: step: 116/530, loss: 0.0012745129643008113
2023-01-24 10:17:46.025341: step: 120/530, loss: 0.004408474545925856
2023-01-24 10:17:47.134782: step: 124/530, loss: 0.0007517550839111209
2023-01-24 10:17:48.229243: step: 128/530, loss: 0.00026374630397185683
2023-01-24 10:17:49.315915: step: 132/530, loss: 2.5531522624078207e-05
2023-01-24 10:17:50.412482: step: 136/530, loss: 0.001046914840117097
2023-01-24 10:17:51.488503: step: 140/530, loss: 0.003953760955482721
2023-01-24 10:17:52.571172: step: 144/530, loss: 0.0016117108752951026
2023-01-24 10:17:53.676233: step: 148/530, loss: 0.0038673526141792536
2023-01-24 10:17:54.763355: step: 152/530, loss: 0.0021993231493979692
2023-01-24 10:17:55.838477: step: 156/530, loss: 0.005202023778110743
2023-01-24 10:17:56.917754: step: 160/530, loss: 0.0026546542067080736
2023-01-24 10:17:58.009158: step: 164/530, loss: 0.012892602942883968
2023-01-24 10:17:59.117198: step: 168/530, loss: 0.0010452303104102612
2023-01-24 10:18:00.189213: step: 172/530, loss: 0.0026824157685041428
2023-01-24 10:18:01.286745: step: 176/530, loss: 0.0015785073628649116
2023-01-24 10:18:02.386315: step: 180/530, loss: 0.0007645704899914563
2023-01-24 10:18:03.477469: step: 184/530, loss: 0.002705469261854887
2023-01-24 10:18:04.556268: step: 188/530, loss: 0.005366666242480278
2023-01-24 10:18:05.635845: step: 192/530, loss: 0.0005622747703455389
2023-01-24 10:18:06.716383: step: 196/530, loss: 5.989646524540149e-06
2023-01-24 10:18:07.819115: step: 200/530, loss: 0.007668128702789545
2023-01-24 10:18:08.904503: step: 204/530, loss: 0.007374717853963375
2023-01-24 10:18:09.985557: step: 208/530, loss: 0.008534826338291168
2023-01-24 10:18:11.082451: step: 212/530, loss: 0.003811290254816413
2023-01-24 10:18:12.171586: step: 216/530, loss: 0.0015131818363443017
2023-01-24 10:18:13.281036: step: 220/530, loss: 0.00036347308196127415
2023-01-24 10:18:14.357084: step: 224/530, loss: 0.0031561492942273617
2023-01-24 10:18:15.434632: step: 228/530, loss: 0.0022700896952301264
2023-01-24 10:18:16.525670: step: 232/530, loss: 0.004300015978515148
2023-01-24 10:18:17.612180: step: 236/530, loss: 0.0002827040443662554
2023-01-24 10:18:18.721827: step: 240/530, loss: 0.0012241177028045058
2023-01-24 10:18:19.843994: step: 244/530, loss: 0.004503392614424229
2023-01-24 10:18:20.921886: step: 248/530, loss: 0.00039703870425000787
2023-01-24 10:18:22.028983: step: 252/530, loss: 0.0085066519677639
2023-01-24 10:18:23.125614: step: 256/530, loss: 0.0036142293829470873
2023-01-24 10:18:24.231973: step: 260/530, loss: 0.006109429989010096
2023-01-24 10:18:25.324676: step: 264/530, loss: 0.0015096550341695547
2023-01-24 10:18:26.429683: step: 268/530, loss: 0.0030760865192860365
2023-01-24 10:18:27.530799: step: 272/530, loss: 0.004289589822292328
2023-01-24 10:18:28.630477: step: 276/530, loss: 0.0021411217749118805
2023-01-24 10:18:29.724887: step: 280/530, loss: 4.426351370057091e-05
2023-01-24 10:18:30.801982: step: 284/530, loss: 9.423431038158014e-05
2023-01-24 10:18:31.868346: step: 288/530, loss: 0.004925564397126436
2023-01-24 10:18:32.962137: step: 292/530, loss: 0.0011611017398536205
2023-01-24 10:18:34.078095: step: 296/530, loss: 0.006216420326381922
2023-01-24 10:18:35.148335: step: 300/530, loss: 0.0058028195053339005
2023-01-24 10:18:36.264084: step: 304/530, loss: 0.00038804401992820203
2023-01-24 10:18:37.340236: step: 308/530, loss: 0.009510464034974575
2023-01-24 10:18:38.413348: step: 312/530, loss: 0.001831777160987258
2023-01-24 10:18:39.484675: step: 316/530, loss: 0.010432722046971321
2023-01-24 10:18:40.568768: step: 320/530, loss: 3.167520117131062e-05
2023-01-24 10:18:41.656642: step: 324/530, loss: 0.023967141285538673
2023-01-24 10:18:42.749257: step: 328/530, loss: 0.0031255523208528757
2023-01-24 10:18:43.875149: step: 332/530, loss: 0.0013823750196024776
2023-01-24 10:18:44.995390: step: 336/530, loss: 0.003276097821071744
2023-01-24 10:18:46.074203: step: 340/530, loss: 0.00030117094866000116
2023-01-24 10:18:47.170893: step: 344/530, loss: 0.004074622876942158
2023-01-24 10:18:48.273517: step: 348/530, loss: 0.00046580296475440264
2023-01-24 10:18:49.356253: step: 352/530, loss: 0.002189417602494359
2023-01-24 10:18:50.454908: step: 356/530, loss: 0.0030694399029016495
2023-01-24 10:18:51.574005: step: 360/530, loss: 0.017475778236985207
2023-01-24 10:18:52.664055: step: 364/530, loss: 0.003079014364629984
2023-01-24 10:18:53.766677: step: 368/530, loss: 0.0061907717026770115
2023-01-24 10:18:54.851167: step: 372/530, loss: 0.0037436443381011486
2023-01-24 10:18:55.948826: step: 376/530, loss: 0.0008974772645160556
2023-01-24 10:18:57.064021: step: 380/530, loss: 3.344173819641583e-05
2023-01-24 10:18:58.159392: step: 384/530, loss: 0.004639403894543648
2023-01-24 10:18:59.261902: step: 388/530, loss: 0.0012414584634825587
2023-01-24 10:19:00.359593: step: 392/530, loss: 0.0062952348962426186
2023-01-24 10:19:01.461274: step: 396/530, loss: 0.0005269868415780365
2023-01-24 10:19:02.540817: step: 400/530, loss: 0.0006903203902766109
2023-01-24 10:19:03.629756: step: 404/530, loss: 0.0017095323419198394
2023-01-24 10:19:04.693007: step: 408/530, loss: 0.009268923662602901
2023-01-24 10:19:05.753545: step: 412/530, loss: 1.6288953702314757e-05
2023-01-24 10:19:06.839521: step: 416/530, loss: 0.01433035172522068
2023-01-24 10:19:07.928317: step: 420/530, loss: 0.001576497801579535
2023-01-24 10:19:09.021503: step: 424/530, loss: 0.004388230852782726
2023-01-24 10:19:10.115881: step: 428/530, loss: 0.0004961317754350603
2023-01-24 10:19:11.203542: step: 432/530, loss: 0.003969933837652206
2023-01-24 10:19:12.300848: step: 436/530, loss: 0.0007683968869969249
2023-01-24 10:19:13.374302: step: 440/530, loss: 0.0010073124431073666
2023-01-24 10:19:14.457388: step: 444/530, loss: 0.0023505499120801687
2023-01-24 10:19:15.523483: step: 448/530, loss: 0.00015716916823294014
2023-01-24 10:19:16.614604: step: 452/530, loss: 0.0032290888484567404
2023-01-24 10:19:17.704139: step: 456/530, loss: 0.000613926153164357
2023-01-24 10:19:18.798150: step: 460/530, loss: 0.01097936648875475
2023-01-24 10:19:19.873006: step: 464/530, loss: 7.576760981464759e-05
2023-01-24 10:19:20.948237: step: 468/530, loss: 0.0012992059346288443
2023-01-24 10:19:22.037614: step: 472/530, loss: 0.004572598729282618
2023-01-24 10:19:23.118164: step: 476/530, loss: 0.0032610297203063965
2023-01-24 10:19:24.207956: step: 480/530, loss: 0.0022114189341664314
2023-01-24 10:19:25.299402: step: 484/530, loss: 0.0020829904824495316
2023-01-24 10:19:26.389218: step: 488/530, loss: 4.587047442328185e-05
2023-01-24 10:19:27.474539: step: 492/530, loss: 0.0026753153651952744
2023-01-24 10:19:28.575117: step: 496/530, loss: 0.0009746643481776118
2023-01-24 10:19:29.667574: step: 500/530, loss: 0.0019232332706451416
2023-01-24 10:19:30.745556: step: 504/530, loss: 0.005039873067289591
2023-01-24 10:19:31.838177: step: 508/530, loss: 0.01322495099157095
2023-01-24 10:19:32.928465: step: 512/530, loss: 0.008688376285135746
2023-01-24 10:19:34.019702: step: 516/530, loss: 0.04017927125096321
2023-01-24 10:19:35.119721: step: 520/530, loss: 0.0006335675716400146
2023-01-24 10:19:36.205017: step: 524/530, loss: 0.003151129698380828
2023-01-24 10:19:37.289789: step: 528/530, loss: 0.0003703125403262675
2023-01-24 10:19:38.378190: step: 532/530, loss: 0.013355312868952751
2023-01-24 10:19:39.490725: step: 536/530, loss: 8.864116534823552e-05
2023-01-24 10:19:40.594560: step: 540/530, loss: 0.0012442035367712379
2023-01-24 10:19:41.675063: step: 544/530, loss: 0.006936206016689539
2023-01-24 10:19:42.798468: step: 548/530, loss: 0.00932455062866211
2023-01-24 10:19:43.890613: step: 552/530, loss: 0.01208194438368082
2023-01-24 10:19:44.972433: step: 556/530, loss: 0.0007088372949510813
2023-01-24 10:19:46.083510: step: 560/530, loss: 0.000727538950741291
2023-01-24 10:19:47.183909: step: 564/530, loss: 0.0003795283264480531
2023-01-24 10:19:48.266597: step: 568/530, loss: 0.0003345249278936535
2023-01-24 10:19:49.345304: step: 572/530, loss: 3.2434752938570455e-05
2023-01-24 10:19:50.447017: step: 576/530, loss: 0.003163258545100689
2023-01-24 10:19:51.534934: step: 580/530, loss: 0.0026887848507612944
2023-01-24 10:19:52.652113: step: 584/530, loss: 0.003371400060132146
2023-01-24 10:19:53.756691: step: 588/530, loss: 5.6341796152992174e-05
2023-01-24 10:19:54.826841: step: 592/530, loss: 0.004009477328509092
2023-01-24 10:19:55.931984: step: 596/530, loss: 0.0024920590221881866
2023-01-24 10:19:57.028123: step: 600/530, loss: 0.00015841968706808984
2023-01-24 10:19:58.117239: step: 604/530, loss: 6.668202701121118e-08
2023-01-24 10:19:59.222907: step: 608/530, loss: 0.009033799171447754
2023-01-24 10:20:00.339972: step: 612/530, loss: 0.010294109582901001
2023-01-24 10:20:01.443489: step: 616/530, loss: 0.005923269782215357
2023-01-24 10:20:02.531144: step: 620/530, loss: 0.0005148897180333734
2023-01-24 10:20:03.620337: step: 624/530, loss: 0.004174213390797377
2023-01-24 10:20:04.688154: step: 628/530, loss: 4.9260168452747166e-05
2023-01-24 10:20:05.768004: step: 632/530, loss: 0.0013204978313297033
2023-01-24 10:20:06.855353: step: 636/530, loss: 0.00033934699604287744
2023-01-24 10:20:07.941204: step: 640/530, loss: 0.01224727276712656
2023-01-24 10:20:09.043221: step: 644/530, loss: 0.00040627815178595483
2023-01-24 10:20:10.162586: step: 648/530, loss: 0.003339530434459448
2023-01-24 10:20:11.276792: step: 652/530, loss: 0.008279840461909771
2023-01-24 10:20:12.372452: step: 656/530, loss: 0.0014663063921034336
2023-01-24 10:20:13.461860: step: 660/530, loss: 0.0018453781958669424
2023-01-24 10:20:14.565699: step: 664/530, loss: 0.004806226585060358
2023-01-24 10:20:15.655053: step: 668/530, loss: 0.008879673667252064
2023-01-24 10:20:16.752750: step: 672/530, loss: 0.0009397105895914137
2023-01-24 10:20:17.835929: step: 676/530, loss: 0.004249256569892168
2023-01-24 10:20:18.918694: step: 680/530, loss: 0.019687814638018608
2023-01-24 10:20:20.006893: step: 684/530, loss: 0.006677149794995785
2023-01-24 10:20:21.088414: step: 688/530, loss: 0.0019105913816019893
2023-01-24 10:20:22.173905: step: 692/530, loss: 0.001259146723896265
2023-01-24 10:20:23.263973: step: 696/530, loss: 4.184913632343523e-05
2023-01-24 10:20:24.356312: step: 700/530, loss: 0.0009217371698468924
2023-01-24 10:20:25.446059: step: 704/530, loss: 0.00031716443481855094
2023-01-24 10:20:26.526649: step: 708/530, loss: 0.012752840295433998
2023-01-24 10:20:27.613258: step: 712/530, loss: 0.005632590968161821
2023-01-24 10:20:28.719351: step: 716/530, loss: 6.445802227972308e-06
2023-01-24 10:20:29.804852: step: 720/530, loss: 0.0025948206894099712
2023-01-24 10:20:30.918120: step: 724/530, loss: 0.002619817154482007
2023-01-24 10:20:32.004502: step: 728/530, loss: 0.0004861385968979448
2023-01-24 10:20:33.101106: step: 732/530, loss: 0.0024453115183860064
2023-01-24 10:20:34.196655: step: 736/530, loss: 0.004731861874461174
2023-01-24 10:20:35.288237: step: 740/530, loss: 0.0013162607792764902
2023-01-24 10:20:36.389153: step: 744/530, loss: 0.000495178101118654
2023-01-24 10:20:37.453764: step: 748/530, loss: 2.0115919596719323e-07
2023-01-24 10:20:38.582785: step: 752/530, loss: 0.0007767449715174735
2023-01-24 10:20:39.685216: step: 756/530, loss: 0.0012465323088690639
2023-01-24 10:20:40.763060: step: 760/530, loss: 0.0005242686602286994
2023-01-24 10:20:41.863234: step: 764/530, loss: 0.0011807344853878021
2023-01-24 10:20:42.979043: step: 768/530, loss: 0.010948910377919674
2023-01-24 10:20:44.073613: step: 772/530, loss: 0.004480754490941763
2023-01-24 10:20:45.132179: step: 776/530, loss: 0.001311618136242032
2023-01-24 10:20:46.214633: step: 780/530, loss: 0.0002680454927030951
2023-01-24 10:20:47.306909: step: 784/530, loss: 0.0008214745903387666
2023-01-24 10:20:48.421806: step: 788/530, loss: 0.00015548574447166175
2023-01-24 10:20:49.534396: step: 792/530, loss: 0.000394105794839561
2023-01-24 10:20:50.634111: step: 796/530, loss: 0.004533532075583935
2023-01-24 10:20:51.727964: step: 800/530, loss: 0.0007221539854072034
2023-01-24 10:20:52.829885: step: 804/530, loss: 0.004022045060992241
2023-01-24 10:20:53.916921: step: 808/530, loss: 0.015345017425715923
2023-01-24 10:20:55.001829: step: 812/530, loss: 0.001496016513556242
2023-01-24 10:20:56.091990: step: 816/530, loss: 0.002786329947412014
2023-01-24 10:20:57.223495: step: 820/530, loss: 0.0059187584556639194
2023-01-24 10:20:58.303770: step: 824/530, loss: 0.0009018850978463888
2023-01-24 10:20:59.413029: step: 828/530, loss: 0.00019411362882237881
2023-01-24 10:21:00.496742: step: 832/530, loss: 0.0045598577708005905
2023-01-24 10:21:01.591813: step: 836/530, loss: 0.005649175029247999
2023-01-24 10:21:02.677354: step: 840/530, loss: 0.0059195104986429214
2023-01-24 10:21:03.755207: step: 844/530, loss: 0.00266664638184011
2023-01-24 10:21:04.850931: step: 848/530, loss: 0.006456125061959028
2023-01-24 10:21:05.922940: step: 852/530, loss: 0.0012606477830559015
2023-01-24 10:21:06.989001: step: 856/530, loss: 9.023839083965868e-05
2023-01-24 10:21:08.090104: step: 860/530, loss: 0.00177907501347363
2023-01-24 10:21:09.168428: step: 864/530, loss: 0.0024248322006314993
2023-01-24 10:21:10.262840: step: 868/530, loss: 0.0034812274388968945
2023-01-24 10:21:11.364330: step: 872/530, loss: 0.005492594558745623
2023-01-24 10:21:12.477817: step: 876/530, loss: 0.003532568458467722
2023-01-24 10:21:13.556828: step: 880/530, loss: 0.00010047259274870157
2023-01-24 10:21:14.652067: step: 884/530, loss: 0.0021263943053781986
2023-01-24 10:21:15.716341: step: 888/530, loss: 0.010426861234009266
2023-01-24 10:21:16.814103: step: 892/530, loss: 0.06476103514432907
2023-01-24 10:21:17.910523: step: 896/530, loss: 0.00402695732191205
2023-01-24 10:21:19.012790: step: 900/530, loss: 0.0034620303194969893
2023-01-24 10:21:20.124493: step: 904/530, loss: 0.0016567535931244493
2023-01-24 10:21:21.199779: step: 908/530, loss: 0.0008701797924004495
2023-01-24 10:21:22.299378: step: 912/530, loss: 0.0005422146059572697
2023-01-24 10:21:23.410512: step: 916/530, loss: 0.009410968981683254
2023-01-24 10:21:24.495030: step: 920/530, loss: 0.00418858602643013
2023-01-24 10:21:25.584389: step: 924/530, loss: 0.00023712597612757236
2023-01-24 10:21:26.675955: step: 928/530, loss: 0.00026911086752079427
2023-01-24 10:21:27.782730: step: 932/530, loss: 0.0010811963584274054
2023-01-24 10:21:28.882375: step: 936/530, loss: 0.005770714487880468
2023-01-24 10:21:29.952882: step: 940/530, loss: 0.0009019781136885285
2023-01-24 10:21:31.042480: step: 944/530, loss: 0.006315905135124922
2023-01-24 10:21:32.154943: step: 948/530, loss: 2.6591626010485925e-05
2023-01-24 10:21:33.249739: step: 952/530, loss: 0.003705458017066121
2023-01-24 10:21:34.347895: step: 956/530, loss: 0.0031867579091340303
2023-01-24 10:21:35.473186: step: 960/530, loss: 0.00012549081293400377
2023-01-24 10:21:36.562387: step: 964/530, loss: 0.00026949579478241503
2023-01-24 10:21:37.651562: step: 968/530, loss: 0.003759004408493638
2023-01-24 10:21:38.741860: step: 972/530, loss: 2.0215552467561793e-06
2023-01-24 10:21:39.814012: step: 976/530, loss: 0.001552699482999742
2023-01-24 10:21:40.916351: step: 980/530, loss: 1.6033138308557682e-05
2023-01-24 10:21:41.994618: step: 984/530, loss: 0.002237774431705475
2023-01-24 10:21:43.051113: step: 988/530, loss: 3.3042865652532782e-06
2023-01-24 10:21:44.147312: step: 992/530, loss: 0.010879520326852798
2023-01-24 10:21:45.224451: step: 996/530, loss: 0.010834017768502235
2023-01-24 10:21:46.309362: step: 1000/530, loss: 0.002442287979647517
2023-01-24 10:21:47.418047: step: 1004/530, loss: 0.011311542242765427
2023-01-24 10:21:48.500503: step: 1008/530, loss: 0.0002734313893597573
2023-01-24 10:21:49.595100: step: 1012/530, loss: 0.0036937897093594074
2023-01-24 10:21:50.672732: step: 1016/530, loss: 0.002512504579499364
2023-01-24 10:21:51.742282: step: 1020/530, loss: 0.0012993746204301715
2023-01-24 10:21:52.849829: step: 1024/530, loss: 0.002023993758484721
2023-01-24 10:21:53.926818: step: 1028/530, loss: 0.005852619186043739
2023-01-24 10:21:55.000690: step: 1032/530, loss: 4.5952849177410826e-05
2023-01-24 10:21:56.096921: step: 1036/530, loss: 0.0045895446091890335
2023-01-24 10:21:57.177803: step: 1040/530, loss: 0.0009423495503142476
2023-01-24 10:21:58.255114: step: 1044/530, loss: 0.0021403960417956114
2023-01-24 10:21:59.351046: step: 1048/530, loss: 0.005640462040901184
2023-01-24 10:22:00.448435: step: 1052/530, loss: 5.1703432291105855e-06
2023-01-24 10:22:01.539438: step: 1056/530, loss: 0.009345858357846737
2023-01-24 10:22:02.613571: step: 1060/530, loss: 0.0018892979715019464
2023-01-24 10:22:03.705467: step: 1064/530, loss: 0.005363785196095705
2023-01-24 10:22:04.798937: step: 1068/530, loss: 0.0011568197514861822
2023-01-24 10:22:05.896816: step: 1072/530, loss: 0.0003025837941095233
2023-01-24 10:22:07.021308: step: 1076/530, loss: 0.006940390449017286
2023-01-24 10:22:08.116941: step: 1080/530, loss: 2.688643871806562e-05
2023-01-24 10:22:09.193969: step: 1084/530, loss: 0.008109815418720245
2023-01-24 10:22:10.287702: step: 1088/530, loss: 0.0033530257642269135
2023-01-24 10:22:11.375877: step: 1092/530, loss: 0.0062082624062895775
2023-01-24 10:22:12.450848: step: 1096/530, loss: 0.0001378083397867158
2023-01-24 10:22:13.539877: step: 1100/530, loss: 0.0022450617980211973
2023-01-24 10:22:14.639677: step: 1104/530, loss: 0.002642890438437462
2023-01-24 10:22:15.761207: step: 1108/530, loss: 0.010595089755952358
2023-01-24 10:22:16.855868: step: 1112/530, loss: 0.0003634699387475848
2023-01-24 10:22:17.940287: step: 1116/530, loss: 0.006039982661604881
2023-01-24 10:22:19.046592: step: 1120/530, loss: 0.005501694045960903
2023-01-24 10:22:20.126675: step: 1124/530, loss: 0.00172157003544271
2023-01-24 10:22:21.214627: step: 1128/530, loss: 0.008069985546171665
2023-01-24 10:22:22.304262: step: 1132/530, loss: 0.003147716401144862
2023-01-24 10:22:23.385519: step: 1136/530, loss: 0.005004453007131815
2023-01-24 10:22:24.465848: step: 1140/530, loss: 0.002055081073194742
2023-01-24 10:22:25.544409: step: 1144/530, loss: 0.000731030770111829
2023-01-24 10:22:26.645579: step: 1148/530, loss: 9.636824688641354e-05
2023-01-24 10:22:27.718804: step: 1152/530, loss: 0.0017672054236754775
2023-01-24 10:22:28.831568: step: 1156/530, loss: 0.003239114535972476
2023-01-24 10:22:29.921616: step: 1160/530, loss: 0.02174297720193863
2023-01-24 10:22:30.990296: step: 1164/530, loss: 0.00011597121192608029
2023-01-24 10:22:32.087529: step: 1168/530, loss: 0.001182210398837924
2023-01-24 10:22:33.201236: step: 1172/530, loss: 0.0026390645653009415
2023-01-24 10:22:34.275610: step: 1176/530, loss: 0.0038202961441129446
2023-01-24 10:22:35.391201: step: 1180/530, loss: 0.0021490994840860367
2023-01-24 10:22:36.471767: step: 1184/530, loss: 0.001816555974073708
2023-01-24 10:22:37.556130: step: 1188/530, loss: 0.004720339085906744
2023-01-24 10:22:38.635837: step: 1192/530, loss: 0.0010220394469797611
2023-01-24 10:22:39.719486: step: 1196/530, loss: 0.0024166754446923733
2023-01-24 10:22:40.823045: step: 1200/530, loss: 0.004676496144384146
2023-01-24 10:22:41.908192: step: 1204/530, loss: 0.0033705593086779118
2023-01-24 10:22:42.993009: step: 1208/530, loss: 0.0032190699130296707
2023-01-24 10:22:44.084243: step: 1212/530, loss: 7.603576523251832e-05
2023-01-24 10:22:45.164351: step: 1216/530, loss: 0.010298809967935085
2023-01-24 10:22:46.263604: step: 1220/530, loss: 0.0012661231448873878
2023-01-24 10:22:47.360615: step: 1224/530, loss: 0.002544811926782131
2023-01-24 10:22:48.437573: step: 1228/530, loss: 0.0006274183979257941
2023-01-24 10:22:49.528709: step: 1232/530, loss: 0.0069658467546105385
2023-01-24 10:22:50.606662: step: 1236/530, loss: 0.00265141692943871
2023-01-24 10:22:51.708152: step: 1240/530, loss: 0.0022913615684956312
2023-01-24 10:22:52.805300: step: 1244/530, loss: 0.02095579355955124
2023-01-24 10:22:53.883478: step: 1248/530, loss: 0.0019135121256113052
2023-01-24 10:22:54.982006: step: 1252/530, loss: 0.0001453147706342861
2023-01-24 10:22:56.081565: step: 1256/530, loss: 0.005594421643763781
2023-01-24 10:22:57.192177: step: 1260/530, loss: 0.006734446622431278
2023-01-24 10:22:58.279907: step: 1264/530, loss: 0.0046421983279287815
2023-01-24 10:22:59.378362: step: 1268/530, loss: 0.007329718209803104
2023-01-24 10:23:00.467233: step: 1272/530, loss: 8.12764628790319e-05
2023-01-24 10:23:01.559160: step: 1276/530, loss: 5.270047768135555e-05
2023-01-24 10:23:02.651420: step: 1280/530, loss: 0.0004227318277116865
2023-01-24 10:23:03.737662: step: 1284/530, loss: 0.006260464433580637
2023-01-24 10:23:04.839026: step: 1288/530, loss: 0.005704643204808235
2023-01-24 10:23:05.928552: step: 1292/530, loss: 8.435212657786906e-05
2023-01-24 10:23:07.016901: step: 1296/530, loss: 0.0003714327176567167
2023-01-24 10:23:08.118321: step: 1300/530, loss: 0.004081703722476959
2023-01-24 10:23:09.203652: step: 1304/530, loss: 0.002183932112529874
2023-01-24 10:23:10.293259: step: 1308/530, loss: 0.002861962653696537
2023-01-24 10:23:11.368741: step: 1312/530, loss: 0.002355008153244853
2023-01-24 10:23:12.469240: step: 1316/530, loss: 0.0013220246182754636
2023-01-24 10:23:13.566445: step: 1320/530, loss: 0.0032330371905118227
2023-01-24 10:23:14.671033: step: 1324/530, loss: 0.009310531429946423
2023-01-24 10:23:15.773184: step: 1328/530, loss: 0.010981257073581219
2023-01-24 10:23:16.868925: step: 1332/530, loss: 0.013804920949041843
2023-01-24 10:23:17.928590: step: 1336/530, loss: 0.012152074836194515
2023-01-24 10:23:18.997866: step: 1340/530, loss: 0.0008176719420589507
2023-01-24 10:23:20.071678: step: 1344/530, loss: 2.639052581798751e-05
2023-01-24 10:23:21.174376: step: 1348/530, loss: 2.1447528979479102e-06
2023-01-24 10:23:22.248311: step: 1352/530, loss: 0.0005587259074673057
2023-01-24 10:23:23.331551: step: 1356/530, loss: 0.0034455277491360903
2023-01-24 10:23:24.430612: step: 1360/530, loss: 0.0007288409979082644
2023-01-24 10:23:25.518685: step: 1364/530, loss: 2.9353806894505396e-05
2023-01-24 10:23:26.619207: step: 1368/530, loss: 0.0013934716116636992
2023-01-24 10:23:27.686198: step: 1372/530, loss: 0.0023119293618947268
2023-01-24 10:23:28.768435: step: 1376/530, loss: 2.198658876295667e-05
2023-01-24 10:23:29.861494: step: 1380/530, loss: 0.006924602203071117
2023-01-24 10:23:30.951383: step: 1384/530, loss: 0.005602176766842604
2023-01-24 10:23:32.039611: step: 1388/530, loss: 1.759415135893505e-05
2023-01-24 10:23:33.109901: step: 1392/530, loss: 0.001758261932991445
2023-01-24 10:23:34.212105: step: 1396/530, loss: 0.001229122281074524
2023-01-24 10:23:35.302196: step: 1400/530, loss: 0.0002035643847193569
2023-01-24 10:23:36.413358: step: 1404/530, loss: 0.00043837804696522653
2023-01-24 10:23:37.511181: step: 1408/530, loss: 0.00032678412389941514
2023-01-24 10:23:38.627666: step: 1412/530, loss: 0.0036443667486310005
2023-01-24 10:23:39.696616: step: 1416/530, loss: 0.0004399028839543462
2023-01-24 10:23:40.778077: step: 1420/530, loss: 0.00015647706459276378
2023-01-24 10:23:41.876205: step: 1424/530, loss: 0.002332886680960655
2023-01-24 10:23:42.963476: step: 1428/530, loss: 0.00021565385395660996
2023-01-24 10:23:44.044426: step: 1432/530, loss: 0.007475203834474087
2023-01-24 10:23:45.147653: step: 1436/530, loss: 0.0044013927690684795
2023-01-24 10:23:46.232108: step: 1440/530, loss: 4.1806215449469164e-05
2023-01-24 10:23:47.332162: step: 1444/530, loss: 0.0011703333584591746
2023-01-24 10:23:48.425011: step: 1448/530, loss: 0.0015794051578268409
2023-01-24 10:23:49.528969: step: 1452/530, loss: 0.00033551757223904133
2023-01-24 10:23:50.645284: step: 1456/530, loss: 9.213612793246284e-05
2023-01-24 10:23:51.731327: step: 1460/530, loss: 0.012634302489459515
2023-01-24 10:23:52.820802: step: 1464/530, loss: 0.005126113537698984
2023-01-24 10:23:53.927850: step: 1468/530, loss: 9.689124271972105e-05
2023-01-24 10:23:55.020965: step: 1472/530, loss: 0.0019329937640577555
2023-01-24 10:23:56.092906: step: 1476/530, loss: 0.008387736976146698
2023-01-24 10:23:57.178401: step: 1480/530, loss: 0.0017540312837809324
2023-01-24 10:23:58.272397: step: 1484/530, loss: 0.0008437251090072095
2023-01-24 10:23:59.359855: step: 1488/530, loss: 0.003939060959964991
2023-01-24 10:24:00.436834: step: 1492/530, loss: 0.0045392257161438465
2023-01-24 10:24:01.545374: step: 1496/530, loss: 0.008384022861719131
2023-01-24 10:24:02.642002: step: 1500/530, loss: 0.00045957029215060174
2023-01-24 10:24:03.727765: step: 1504/530, loss: 9.275861521018669e-05
2023-01-24 10:24:04.818868: step: 1508/530, loss: 0.00700340885668993
2023-01-24 10:24:05.916583: step: 1512/530, loss: 0.0007242744322866201
2023-01-24 10:24:06.989380: step: 1516/530, loss: 0.0008526495075784624
2023-01-24 10:24:08.080666: step: 1520/530, loss: 0.006042341701686382
2023-01-24 10:24:09.202818: step: 1524/530, loss: 0.016548385843634605
2023-01-24 10:24:10.317628: step: 1528/530, loss: 0.00233745900914073
2023-01-24 10:24:11.399135: step: 1532/530, loss: 0.0005690492107532918
2023-01-24 10:24:12.514765: step: 1536/530, loss: 0.00019722001161426306
2023-01-24 10:24:13.611355: step: 1540/530, loss: 0.005244697909802198
2023-01-24 10:24:14.699038: step: 1544/530, loss: 0.0006843619630672038
2023-01-24 10:24:15.804047: step: 1548/530, loss: 0.0026567126624286175
2023-01-24 10:24:16.893962: step: 1552/530, loss: 0.007519073318690062
2023-01-24 10:24:17.974877: step: 1556/530, loss: 0.0020052820909768343
2023-01-24 10:24:19.102666: step: 1560/530, loss: 1.000175871013198e-06
2023-01-24 10:24:20.184372: step: 1564/530, loss: 0.0036371080204844475
2023-01-24 10:24:21.300450: step: 1568/530, loss: 0.0001614685170352459
2023-01-24 10:24:22.416974: step: 1572/530, loss: 0.003568487474694848
2023-01-24 10:24:23.493077: step: 1576/530, loss: 0.0001279938587686047
2023-01-24 10:24:24.611347: step: 1580/530, loss: 0.005685790907591581
2023-01-24 10:24:25.695286: step: 1584/530, loss: 0.00011141136201331392
2023-01-24 10:24:26.781471: step: 1588/530, loss: 0.0003209089918527752
2023-01-24 10:24:27.895834: step: 1592/530, loss: 0.00011579424608498812
2023-01-24 10:24:28.990723: step: 1596/530, loss: 0.005333163775503635
2023-01-24 10:24:30.080147: step: 1600/530, loss: 0.0013128520222380757
2023-01-24 10:24:31.191323: step: 1604/530, loss: 0.0004314040415920317
2023-01-24 10:24:32.298364: step: 1608/530, loss: 0.0031901539769023657
2023-01-24 10:24:33.410715: step: 1612/530, loss: 0.0036830303724855185
2023-01-24 10:24:34.496663: step: 1616/530, loss: 0.00030810883617959917
2023-01-24 10:24:35.587254: step: 1620/530, loss: 0.0025271351914852858
2023-01-24 10:24:36.678111: step: 1624/530, loss: 0.00015104500926099718
2023-01-24 10:24:37.754855: step: 1628/530, loss: 0.0009225932881236076
2023-01-24 10:24:38.840501: step: 1632/530, loss: 0.006921342574059963
2023-01-24 10:24:39.938076: step: 1636/530, loss: 0.012433944270014763
2023-01-24 10:24:41.020614: step: 1640/530, loss: 0.002472271677106619
2023-01-24 10:24:42.128626: step: 1644/530, loss: 0.01649395376443863
2023-01-24 10:24:43.204799: step: 1648/530, loss: 0.0005079595721326768
2023-01-24 10:24:44.281823: step: 1652/530, loss: 0.001471898751333356
2023-01-24 10:24:45.356109: step: 1656/530, loss: 0.0005140473367646337
2023-01-24 10:24:46.432029: step: 1660/530, loss: 7.484033267246559e-05
2023-01-24 10:24:47.505587: step: 1664/530, loss: 0.006606653332710266
2023-01-24 10:24:48.604532: step: 1668/530, loss: 0.0032492068130522966
2023-01-24 10:24:49.686087: step: 1672/530, loss: 7.73825649957871e-06
2023-01-24 10:24:50.788546: step: 1676/530, loss: 0.014332698658108711
2023-01-24 10:24:51.872276: step: 1680/530, loss: 0.015233784914016724
2023-01-24 10:24:52.956496: step: 1684/530, loss: 0.010254183784127235
2023-01-24 10:24:54.022941: step: 1688/530, loss: 0.00034514759317971766
2023-01-24 10:24:55.122017: step: 1692/530, loss: 0.00027492354274727404
2023-01-24 10:24:56.203255: step: 1696/530, loss: 0.0005268744425848126
2023-01-24 10:24:57.300184: step: 1700/530, loss: 3.061047027586028e-05
2023-01-24 10:24:58.393382: step: 1704/530, loss: 0.004546803887933493
2023-01-24 10:24:59.486014: step: 1708/530, loss: 0.0007081169751472771
2023-01-24 10:25:00.567449: step: 1712/530, loss: 0.000974190654233098
2023-01-24 10:25:01.664441: step: 1716/530, loss: 0.002233486855402589
2023-01-24 10:25:02.754991: step: 1720/530, loss: 0.00027596502332016826
2023-01-24 10:25:03.848881: step: 1724/530, loss: 0.0012686955742537975
2023-01-24 10:25:04.961813: step: 1728/530, loss: 0.011882033199071884
2023-01-24 10:25:06.063905: step: 1732/530, loss: 0.0016740866703912616
2023-01-24 10:25:07.172907: step: 1736/530, loss: 0.0036670188419520855
2023-01-24 10:25:08.266848: step: 1740/530, loss: 0.0006247829296626151
2023-01-24 10:25:09.366052: step: 1744/530, loss: 0.0002302930224686861
2023-01-24 10:25:10.448027: step: 1748/530, loss: 0.004521691240370274
2023-01-24 10:25:11.532570: step: 1752/530, loss: 6.992492853896692e-05
2023-01-24 10:25:12.633086: step: 1756/530, loss: 0.0025664132554084063
2023-01-24 10:25:13.714520: step: 1760/530, loss: 0.0001788092777132988
2023-01-24 10:25:14.809274: step: 1764/530, loss: 0.0027129855006933212
2023-01-24 10:25:15.899466: step: 1768/530, loss: 0.0022424794733524323
2023-01-24 10:25:16.990471: step: 1772/530, loss: 0.014447060413658619
2023-01-24 10:25:18.084298: step: 1776/530, loss: 0.015384789556264877
2023-01-24 10:25:19.201378: step: 1780/530, loss: 0.0037047071382403374
2023-01-24 10:25:20.305435: step: 1784/530, loss: 0.0019358344143256545
2023-01-24 10:25:21.375710: step: 1788/530, loss: 0.0011915653012692928
2023-01-24 10:25:22.472311: step: 1792/530, loss: 0.0050245351158082485
2023-01-24 10:25:23.550218: step: 1796/530, loss: 0.0036216562148183584
2023-01-24 10:25:24.624996: step: 1800/530, loss: 0.00040984529186971486
2023-01-24 10:25:25.714784: step: 1804/530, loss: 0.003871543100103736
2023-01-24 10:25:26.814829: step: 1808/530, loss: 0.001043385243974626
2023-01-24 10:25:27.881148: step: 1812/530, loss: 0.0014169103233143687
2023-01-24 10:25:28.972813: step: 1816/530, loss: 0.0010335597908124328
2023-01-24 10:25:30.072993: step: 1820/530, loss: 0.00853751227259636
2023-01-24 10:25:31.164083: step: 1824/530, loss: 0.001902538351714611
2023-01-24 10:25:32.272022: step: 1828/530, loss: 0.005769925657659769
2023-01-24 10:25:33.352951: step: 1832/530, loss: 0.00010788224608404562
2023-01-24 10:25:34.437337: step: 1836/530, loss: 0.0002556719118729234
2023-01-24 10:25:35.521286: step: 1840/530, loss: 0.0023373058065772057
2023-01-24 10:25:36.606833: step: 1844/530, loss: 0.0018819218967109919
2023-01-24 10:25:37.717919: step: 1848/530, loss: 0.0053341928869485855
2023-01-24 10:25:38.799883: step: 1852/530, loss: 0.0010817032307386398
2023-01-24 10:25:39.891760: step: 1856/530, loss: 0.004029288422316313
2023-01-24 10:25:40.986991: step: 1860/530, loss: 0.0005967693869024515
2023-01-24 10:25:42.065354: step: 1864/530, loss: 0.012114092707633972
2023-01-24 10:25:43.143988: step: 1868/530, loss: 0.00201412639580667
2023-01-24 10:25:44.222746: step: 1872/530, loss: 0.0019678636454045773
2023-01-24 10:25:45.287397: step: 1876/530, loss: 0.004111373797059059
2023-01-24 10:25:46.368094: step: 1880/530, loss: 0.007007824257016182
2023-01-24 10:25:47.441846: step: 1884/530, loss: 0.00036227283999323845
2023-01-24 10:25:48.527468: step: 1888/530, loss: 0.004348426591604948
2023-01-24 10:25:49.590170: step: 1892/530, loss: 0.001902793999761343
2023-01-24 10:25:50.697930: step: 1896/530, loss: 0.0016491325804963708
2023-01-24 10:25:51.763700: step: 1900/530, loss: 0.003511815331876278
2023-01-24 10:25:52.840318: step: 1904/530, loss: 0.002622359897941351
2023-01-24 10:25:53.928501: step: 1908/530, loss: 0.0013616224750876427
2023-01-24 10:25:55.008265: step: 1912/530, loss: 0.0017233459511771798
2023-01-24 10:25:56.106164: step: 1916/530, loss: 0.01039955485612154
2023-01-24 10:25:57.186776: step: 1920/530, loss: 0.003541199490427971
2023-01-24 10:25:58.277529: step: 1924/530, loss: 0.004119502380490303
2023-01-24 10:25:59.356853: step: 1928/530, loss: 0.00024195419973693788
2023-01-24 10:26:00.429434: step: 1932/530, loss: 0.01525817159563303
2023-01-24 10:26:01.506893: step: 1936/530, loss: 0.00019643902487587184
2023-01-24 10:26:02.602889: step: 1940/530, loss: 0.0038997665978968143
2023-01-24 10:26:03.680519: step: 1944/530, loss: 0.00576160941272974
2023-01-24 10:26:04.745473: step: 1948/530, loss: 5.638922448270023e-05
2023-01-24 10:26:05.841588: step: 1952/530, loss: 0.007332270033657551
2023-01-24 10:26:06.935603: step: 1956/530, loss: 0.001038927468471229
2023-01-24 10:26:08.042016: step: 1960/530, loss: 0.0007676129462197423
2023-01-24 10:26:09.132283: step: 1964/530, loss: 0.0017081722617149353
2023-01-24 10:26:10.213435: step: 1968/530, loss: 0.001446377718821168
2023-01-24 10:26:11.285982: step: 1972/530, loss: 7.40698233130388e-05
2023-01-24 10:26:12.393976: step: 1976/530, loss: 0.015186567790806293
2023-01-24 10:26:13.499241: step: 1980/530, loss: 0.004140587989240885
2023-01-24 10:26:14.581449: step: 1984/530, loss: 0.0013683964498341084
2023-01-24 10:26:15.676789: step: 1988/530, loss: 0.004019567742943764
2023-01-24 10:26:16.755838: step: 1992/530, loss: 0.00021876940445508808
2023-01-24 10:26:17.869503: step: 1996/530, loss: 0.0026058435905724764
2023-01-24 10:26:18.953347: step: 2000/530, loss: 3.5194450902054086e-05
2023-01-24 10:26:20.038406: step: 2004/530, loss: 0.0012629564153030515
2023-01-24 10:26:21.137589: step: 2008/530, loss: 0.003418681211769581
2023-01-24 10:26:22.221074: step: 2012/530, loss: 0.00518101267516613
2023-01-24 10:26:23.305643: step: 2016/530, loss: 0.001349366852082312
2023-01-24 10:26:24.395841: step: 2020/530, loss: 0.0004321894666645676
2023-01-24 10:26:25.476692: step: 2024/530, loss: 0.0030992792453616858
2023-01-24 10:26:26.578540: step: 2028/530, loss: 0.003331840503960848
2023-01-24 10:26:27.667243: step: 2032/530, loss: 0.000894597265869379
2023-01-24 10:26:28.736951: step: 2036/530, loss: 0.007164007984101772
2023-01-24 10:26:29.826988: step: 2040/530, loss: 0.009799154475331306
2023-01-24 10:26:30.924028: step: 2044/530, loss: 0.0047544799745082855
2023-01-24 10:26:32.040419: step: 2048/530, loss: 0.007946967147290707
2023-01-24 10:26:33.117251: step: 2052/530, loss: 0.0020527716260403395
2023-01-24 10:26:34.201192: step: 2056/530, loss: 0.0022000509779900312
2023-01-24 10:26:35.283465: step: 2060/530, loss: 5.367500762076816e-06
2023-01-24 10:26:36.369796: step: 2064/530, loss: 0.0034030878450721502
2023-01-24 10:26:37.454152: step: 2068/530, loss: 0.011891954578459263
2023-01-24 10:26:38.542577: step: 2072/530, loss: 0.0049121929332613945
2023-01-24 10:26:39.625696: step: 2076/530, loss: 0.00882336962968111
2023-01-24 10:26:40.700806: step: 2080/530, loss: 0.0031558808404952288
2023-01-24 10:26:41.806704: step: 2084/530, loss: 0.006491594482213259
2023-01-24 10:26:42.901509: step: 2088/530, loss: 0.0003341978008393198
2023-01-24 10:26:43.997775: step: 2092/530, loss: 0.008969110436737537
2023-01-24 10:26:45.099254: step: 2096/530, loss: 0.0
2023-01-24 10:26:46.176007: step: 2100/530, loss: 0.00013284842134453356
2023-01-24 10:26:47.248829: step: 2104/530, loss: 0.00024358122027479112
2023-01-24 10:26:48.355831: step: 2108/530, loss: 0.0021814615465700626
2023-01-24 10:26:49.451959: step: 2112/530, loss: 0.01966274343430996
2023-01-24 10:26:50.545639: step: 2116/530, loss: 0.006108695175498724
2023-01-24 10:26:51.637009: step: 2120/530, loss: 5.6259759730892256e-05
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3476613031852626, 'r': 0.34436280884764153, 'f1': 0.3460041949717962}, 'combined': 0.25495045945290246, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34694836215856434, 'r': 0.27968636514266065, 'f1': 0.30970746457746984}, 'combined': 0.1923446358954813, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38946266233766236, 'r': 0.33255825057295646, 'f1': 0.35876806151882923}, 'combined': 0.26435541375071625, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3351468661837272, 'r': 0.2639447157593187, 'f1': 0.29531459629456114}, 'combined': 0.18340590717241168, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37837735169421355, 'r': 0.32596454965687466, 'f1': 0.35022083112981234}, 'combined': 0.2580574545167038, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.35229801736625566, 'r': 0.2746671301402922, 'f1': 0.3086764416457254}, 'combined': 0.19170431639050314, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 10:29:19.566402: step: 4/530, loss: 0.002954723546281457
2023-01-24 10:29:20.632423: step: 8/530, loss: 0.00044845815864391625
2023-01-24 10:29:21.723243: step: 12/530, loss: 0.0005227226647548378
2023-01-24 10:29:22.810347: step: 16/530, loss: 2.8173930331831798e-05
2023-01-24 10:29:23.882934: step: 20/530, loss: 0.0005631744861602783
2023-01-24 10:29:24.979549: step: 24/530, loss: 0.007691206876188517
2023-01-24 10:29:26.083563: step: 28/530, loss: 0.0017431259620934725
2023-01-24 10:29:27.162046: step: 32/530, loss: 0.0006445638136938214
2023-01-24 10:29:28.236415: step: 36/530, loss: 0.0014654003316536546
2023-01-24 10:29:29.316997: step: 40/530, loss: 0.00032433445448987186
2023-01-24 10:29:30.405864: step: 44/530, loss: 0.0045589879155159
2023-01-24 10:29:31.501057: step: 48/530, loss: 0.004568952135741711
2023-01-24 10:29:32.577048: step: 52/530, loss: 0.0020693992264568806
2023-01-24 10:29:33.646596: step: 56/530, loss: 0.00017161820142064244
2023-01-24 10:29:34.713220: step: 60/530, loss: 0.001358807203359902
2023-01-24 10:29:35.810155: step: 64/530, loss: 0.001410193624906242
2023-01-24 10:29:36.892681: step: 68/530, loss: 0.00045735028106719255
2023-01-24 10:29:37.969897: step: 72/530, loss: 0.0002586637856438756
2023-01-24 10:29:39.059012: step: 76/530, loss: 0.000398591801058501
2023-01-24 10:29:40.153732: step: 80/530, loss: 0.02035372145473957
2023-01-24 10:29:41.240358: step: 84/530, loss: 0.013444044627249241
2023-01-24 10:29:42.338150: step: 88/530, loss: 3.883817043970339e-05
2023-01-24 10:29:43.433622: step: 92/530, loss: 0.007603918202221394
2023-01-24 10:29:44.514131: step: 96/530, loss: 0.0008910742471925914
2023-01-24 10:29:45.634395: step: 100/530, loss: 0.0016997241182252765
2023-01-24 10:29:46.728791: step: 104/530, loss: 0.001665754010900855
2023-01-24 10:29:47.798476: step: 108/530, loss: 0.0003134464204777032
2023-01-24 10:29:48.903183: step: 112/530, loss: 0.005385173484683037
2023-01-24 10:29:49.970343: step: 116/530, loss: 0.0028875747229903936
2023-01-24 10:29:51.053651: step: 120/530, loss: 0.022701019421219826
2023-01-24 10:29:52.174475: step: 124/530, loss: 0.002913362579420209
2023-01-24 10:29:53.261212: step: 128/530, loss: 0.0007831230759620667
2023-01-24 10:29:54.353353: step: 132/530, loss: 0.0004321267770137638
2023-01-24 10:29:55.448310: step: 136/530, loss: 0.001030613319016993
2023-01-24 10:29:56.544041: step: 140/530, loss: 0.002651211805641651
2023-01-24 10:29:57.667256: step: 144/530, loss: 1.0803332450848302e-08
2023-01-24 10:29:58.742893: step: 148/530, loss: 0.004252434242516756
2023-01-24 10:29:59.819215: step: 152/530, loss: 0.005296775139868259
2023-01-24 10:30:00.916045: step: 156/530, loss: 0.00017949669563677162
2023-01-24 10:30:02.000594: step: 160/530, loss: 6.435580417019082e-06
2023-01-24 10:30:03.098849: step: 164/530, loss: 0.00034122608485631645
2023-01-24 10:30:04.183280: step: 168/530, loss: 0.0010028555989265442
2023-01-24 10:30:05.263448: step: 172/530, loss: 0.0027353032492101192
2023-01-24 10:30:06.348538: step: 176/530, loss: 0.00256900442764163
2023-01-24 10:30:07.444070: step: 180/530, loss: 0.01153743639588356
2023-01-24 10:30:08.516294: step: 184/530, loss: 0.0011792861623689532
2023-01-24 10:30:09.601662: step: 188/530, loss: 0.0007198047824203968
2023-01-24 10:30:10.699981: step: 192/530, loss: 0.006728826556354761
2023-01-24 10:30:11.813845: step: 196/530, loss: 0.0003828633052762598
2023-01-24 10:30:12.889269: step: 200/530, loss: 0.002646331675350666
2023-01-24 10:30:13.975295: step: 204/530, loss: 0.001077571650967002
2023-01-24 10:30:15.063544: step: 208/530, loss: 0.000652323302347213
2023-01-24 10:30:16.181642: step: 212/530, loss: 0.0030014568474143744
2023-01-24 10:30:17.297030: step: 216/530, loss: 0.003260666271671653
2023-01-24 10:30:18.389556: step: 220/530, loss: 0.001680352259427309
2023-01-24 10:30:19.474330: step: 224/530, loss: 0.0008825248805806041
2023-01-24 10:30:20.542000: step: 228/530, loss: 0.0011361065553501248
2023-01-24 10:30:21.637904: step: 232/530, loss: 0.005784417502582073
2023-01-24 10:30:22.713792: step: 236/530, loss: 0.007462788838893175
2023-01-24 10:30:23.805208: step: 240/530, loss: 0.0007599100354127586
2023-01-24 10:30:24.910104: step: 244/530, loss: 0.004313374403864145
2023-01-24 10:30:25.981751: step: 248/530, loss: 6.927909453224856e-06
2023-01-24 10:30:27.090349: step: 252/530, loss: 0.0004326468624640256
2023-01-24 10:30:28.178640: step: 256/530, loss: 0.008995186537504196
2023-01-24 10:30:29.277585: step: 260/530, loss: 0.00029355150763876736
2023-01-24 10:30:30.383297: step: 264/530, loss: 0.00486218836158514
2023-01-24 10:30:31.465010: step: 268/530, loss: 0.0048637669533491135
2023-01-24 10:30:32.545710: step: 272/530, loss: 0.0021844892762601376
2023-01-24 10:30:33.646697: step: 276/530, loss: 0.002423346508294344
2023-01-24 10:30:34.734438: step: 280/530, loss: 0.0022170129232108593
2023-01-24 10:30:35.833226: step: 284/530, loss: 0.0038028659764677286
2023-01-24 10:30:36.930471: step: 288/530, loss: 0.00030519781284965575
2023-01-24 10:30:37.996313: step: 292/530, loss: 0.0012181508354842663
2023-01-24 10:30:39.097885: step: 296/530, loss: 0.0001642900169827044
2023-01-24 10:30:40.192215: step: 300/530, loss: 0.0016337765846401453
2023-01-24 10:30:41.280887: step: 304/530, loss: 2.640813727339264e-05
2023-01-24 10:30:42.387865: step: 308/530, loss: 0.005103096831589937
2023-01-24 10:30:43.478879: step: 312/530, loss: 4.338818325777538e-05
2023-01-24 10:30:44.568503: step: 316/530, loss: 0.007284747902303934
2023-01-24 10:30:45.657473: step: 320/530, loss: 0.01187017373740673
2023-01-24 10:30:46.754721: step: 324/530, loss: 0.003390074707567692
2023-01-24 10:30:47.865650: step: 328/530, loss: 0.007587057538330555
2023-01-24 10:30:48.946044: step: 332/530, loss: 0.005341880023479462
2023-01-24 10:30:50.029237: step: 336/530, loss: 0.0011350206332281232
2023-01-24 10:30:51.127103: step: 340/530, loss: 0.0025320881977677345
2023-01-24 10:30:52.251159: step: 344/530, loss: 0.0008874781779013574
2023-01-24 10:30:53.347866: step: 348/530, loss: 0.002052400493994355
2023-01-24 10:30:54.434936: step: 352/530, loss: 0.0024771452881395817
2023-01-24 10:30:55.548912: step: 356/530, loss: 0.00033059160341508687
2023-01-24 10:30:56.628684: step: 360/530, loss: 0.00028168834978714585
2023-01-24 10:30:57.703184: step: 364/530, loss: 0.0006801236886531115
2023-01-24 10:30:58.801774: step: 368/530, loss: 0.006793640088289976
2023-01-24 10:30:59.902234: step: 372/530, loss: 1.2780573342752177e-05
2023-01-24 10:31:00.993441: step: 376/530, loss: 0.0005107701290398836
2023-01-24 10:31:02.059716: step: 380/530, loss: 0.00029774016002193093
2023-01-24 10:31:03.143362: step: 384/530, loss: 0.00011703440395649523
2023-01-24 10:31:04.223989: step: 388/530, loss: 2.059024882328231e-05
2023-01-24 10:31:05.303244: step: 392/530, loss: 0.0007314326358027756
2023-01-24 10:31:06.387564: step: 396/530, loss: 0.0009269976289942861
2023-01-24 10:31:07.479416: step: 400/530, loss: 0.0008016666979528964
2023-01-24 10:31:08.559338: step: 404/530, loss: 0.00016452903219033033
2023-01-24 10:31:09.652464: step: 408/530, loss: 0.005205125547945499
2023-01-24 10:31:10.758237: step: 412/530, loss: 0.0025602970272302628
2023-01-24 10:31:11.863611: step: 416/530, loss: 0.0008605541661381721
2023-01-24 10:31:12.962332: step: 420/530, loss: 3.0510685974149965e-05
2023-01-24 10:31:14.050534: step: 424/530, loss: 0.006701792124658823
2023-01-24 10:31:15.144339: step: 428/530, loss: 0.0014641211600974202
2023-01-24 10:31:16.260506: step: 432/530, loss: 1.4339184417622164e-05
2023-01-24 10:31:17.362084: step: 436/530, loss: 0.0010109801078215241
2023-01-24 10:31:18.453233: step: 440/530, loss: 0.0006940175080671906
2023-01-24 10:31:19.542466: step: 444/530, loss: 0.00990916509181261
2023-01-24 10:31:20.639764: step: 448/530, loss: 0.0008067302405834198
2023-01-24 10:31:21.733265: step: 452/530, loss: 0.004962479695677757
2023-01-24 10:31:22.827741: step: 456/530, loss: 0.0002970180648844689
2023-01-24 10:31:23.906679: step: 460/530, loss: 0.009171870537102222
2023-01-24 10:31:25.009650: step: 464/530, loss: 0.00016788435459602624
2023-01-24 10:31:26.130650: step: 468/530, loss: 0.005036230199038982
2023-01-24 10:31:27.259354: step: 472/530, loss: 0.003540154080837965
2023-01-24 10:31:28.355829: step: 476/530, loss: 0.009947326965630054
2023-01-24 10:31:29.436668: step: 480/530, loss: 9.142982889898121e-06
2023-01-24 10:31:30.518986: step: 484/530, loss: 0.01023060828447342
2023-01-24 10:31:31.594951: step: 488/530, loss: 0.001469960785470903
2023-01-24 10:31:32.676401: step: 492/530, loss: 0.000816535553894937
2023-01-24 10:31:33.777756: step: 496/530, loss: 0.006719451863318682
2023-01-24 10:31:34.858770: step: 500/530, loss: 0.0034260135143995285
2023-01-24 10:31:35.938534: step: 504/530, loss: 0.0031876498833298683
2023-01-24 10:31:37.048140: step: 508/530, loss: 0.0005767729016952217
2023-01-24 10:31:38.139029: step: 512/530, loss: 0.0016765849431976676
2023-01-24 10:31:39.222709: step: 516/530, loss: 0.00012110883835703135
2023-01-24 10:31:40.336903: step: 520/530, loss: 0.0004973490140400827
2023-01-24 10:31:41.394119: step: 524/530, loss: 0.00018373607599642128
2023-01-24 10:31:42.494524: step: 528/530, loss: 0.004958410281687975
2023-01-24 10:31:43.584958: step: 532/530, loss: 0.0017065670108422637
2023-01-24 10:31:44.680867: step: 536/530, loss: 0.0040092021226882935
2023-01-24 10:31:45.760887: step: 540/530, loss: 0.03397200256586075
2023-01-24 10:31:46.847706: step: 544/530, loss: 0.0008486725273542106
2023-01-24 10:31:47.935971: step: 548/530, loss: 2.9967008231324144e-05
2023-01-24 10:31:49.035084: step: 552/530, loss: 0.0010432637063786387
2023-01-24 10:31:50.137138: step: 556/530, loss: 0.0027807482983917
2023-01-24 10:31:51.228162: step: 560/530, loss: 6.872442463645712e-05
2023-01-24 10:31:52.326765: step: 564/530, loss: 0.0013290123315528035
2023-01-24 10:31:53.402947: step: 568/530, loss: 0.006641450338065624
2023-01-24 10:31:54.496518: step: 572/530, loss: 0.003023469587787986
2023-01-24 10:31:55.594198: step: 576/530, loss: 0.002972981659695506
2023-01-24 10:31:56.695698: step: 580/530, loss: 3.284886770416051e-05
2023-01-24 10:31:57.792377: step: 584/530, loss: 0.0031865399796515703
2023-01-24 10:31:58.890093: step: 588/530, loss: 0.007889127358794212
2023-01-24 10:31:59.980038: step: 592/530, loss: 0.0038619008846580982
2023-01-24 10:32:01.045506: step: 596/530, loss: 0.0009821607964113355
2023-01-24 10:32:02.146681: step: 600/530, loss: 6.619410851271823e-05
2023-01-24 10:32:03.230741: step: 604/530, loss: 0.002822831505909562
2023-01-24 10:32:04.326071: step: 608/530, loss: 0.005496440455317497
2023-01-24 10:32:05.409158: step: 612/530, loss: 0.009657280519604683
2023-01-24 10:32:06.510030: step: 616/530, loss: 0.0016709959600120783
2023-01-24 10:32:07.615653: step: 620/530, loss: 0.0014983081491664052
2023-01-24 10:32:08.706114: step: 624/530, loss: 0.004068445414304733
2023-01-24 10:32:09.796020: step: 628/530, loss: 8.508070550306002e-07
2023-01-24 10:32:10.896789: step: 632/530, loss: 5.519353726413101e-05
2023-01-24 10:32:12.012741: step: 636/530, loss: 0.0001397411251673475
2023-01-24 10:32:13.103884: step: 640/530, loss: 0.0014539090916514397
2023-01-24 10:32:14.199702: step: 644/530, loss: 3.7332079955376685e-05
2023-01-24 10:32:15.275383: step: 648/530, loss: 0.00031373254023492336
2023-01-24 10:32:16.380270: step: 652/530, loss: 0.0017929950263351202
2023-01-24 10:32:17.465871: step: 656/530, loss: 1.528276357021241e-06
2023-01-24 10:32:18.576065: step: 660/530, loss: 1.6391229706869126e-08
2023-01-24 10:32:19.653883: step: 664/530, loss: 2.3388469344354235e-05
2023-01-24 10:32:20.733870: step: 668/530, loss: 0.0
2023-01-24 10:32:21.836156: step: 672/530, loss: 0.005200324580073357
2023-01-24 10:32:22.905984: step: 676/530, loss: 4.359983722679317e-05
2023-01-24 10:32:23.996479: step: 680/530, loss: 1.058614429894078e-06
2023-01-24 10:32:25.085645: step: 684/530, loss: 1.3914585679231095e-06
2023-01-24 10:32:26.174528: step: 688/530, loss: 0.001755238277837634
2023-01-24 10:32:27.262909: step: 692/530, loss: 5.841856818733504e-06
2023-01-24 10:32:28.357379: step: 696/530, loss: 0.00015238371270243078
2023-01-24 10:32:29.447291: step: 700/530, loss: 0.0034832616802304983
2023-01-24 10:32:30.552177: step: 704/530, loss: 0.0026851161383092403
2023-01-24 10:32:31.634799: step: 708/530, loss: 0.00034477890585549176
2023-01-24 10:32:32.720630: step: 712/530, loss: 0.0001400583132635802
2023-01-24 10:32:33.808714: step: 716/530, loss: 0.000933889125008136
2023-01-24 10:32:34.887869: step: 720/530, loss: 0.0009453259408473969
2023-01-24 10:32:35.989188: step: 724/530, loss: 0.0011413487372919917
2023-01-24 10:32:37.102636: step: 728/530, loss: 0.006688188295811415
2023-01-24 10:32:38.219905: step: 732/530, loss: 0.003394009545445442
2023-01-24 10:32:39.320062: step: 736/530, loss: 0.0033763854298740625
2023-01-24 10:32:40.433553: step: 740/530, loss: 0.0028470607940107584
2023-01-24 10:32:41.522155: step: 744/530, loss: 0.0010789900552481413
2023-01-24 10:32:42.643964: step: 748/530, loss: 0.0006434411625377834
2023-01-24 10:32:43.734186: step: 752/530, loss: 0.0030373719055205584
2023-01-24 10:32:44.815579: step: 756/530, loss: 0.0013517733896151185
2023-01-24 10:32:45.902033: step: 760/530, loss: 0.0007551456801593304
2023-01-24 10:32:47.004881: step: 764/530, loss: 0.011850315146148205
2023-01-24 10:32:48.096440: step: 768/530, loss: 0.0019961909856647253
2023-01-24 10:32:49.196477: step: 772/530, loss: 0.0007041761418804526
2023-01-24 10:32:50.303513: step: 776/530, loss: 0.00309159979224205
2023-01-24 10:32:51.412232: step: 780/530, loss: 0.0011339497286826372
2023-01-24 10:32:52.488639: step: 784/530, loss: 6.161235432955436e-06
2023-01-24 10:32:53.585858: step: 788/530, loss: 0.0005244814674369991
2023-01-24 10:32:54.678330: step: 792/530, loss: 0.005705093964934349
2023-01-24 10:32:55.756698: step: 796/530, loss: 0.0037209982983767986
2023-01-24 10:32:56.839305: step: 800/530, loss: 5.357477493816987e-05
2023-01-24 10:32:57.926994: step: 804/530, loss: 0.007990230806171894
2023-01-24 10:32:59.007021: step: 808/530, loss: 0.0004635354853235185
2023-01-24 10:33:00.107326: step: 812/530, loss: 0.002716107526794076
2023-01-24 10:33:01.181820: step: 816/530, loss: 0.005373099353164434
2023-01-24 10:33:02.291274: step: 820/530, loss: 0.0042391931638121605
2023-01-24 10:33:03.359634: step: 824/530, loss: 0.0003886620106641203
2023-01-24 10:33:04.475841: step: 828/530, loss: 0.0003630721475929022
2023-01-24 10:33:05.562356: step: 832/530, loss: 0.0016245156293734908
2023-01-24 10:33:06.645977: step: 836/530, loss: 0.0016663596034049988
2023-01-24 10:33:07.743741: step: 840/530, loss: 4.6407927584368736e-05
2023-01-24 10:33:08.845929: step: 844/530, loss: 0.03343836963176727
2023-01-24 10:33:09.933295: step: 848/530, loss: 0.0015235901810228825
2023-01-24 10:33:11.026841: step: 852/530, loss: 2.3184093151940033e-05
2023-01-24 10:33:12.130799: step: 856/530, loss: 0.000152737382450141
2023-01-24 10:33:13.233483: step: 860/530, loss: 0.008834323845803738
2023-01-24 10:33:14.338353: step: 864/530, loss: 0.0021855863742530346
2023-01-24 10:33:15.427750: step: 868/530, loss: 1.8849797925213352e-05
2023-01-24 10:33:16.542661: step: 872/530, loss: 4.739106589113362e-05
2023-01-24 10:33:17.625477: step: 876/530, loss: 4.2123956518480554e-05
2023-01-24 10:33:18.731093: step: 880/530, loss: 0.00017269035743083805
2023-01-24 10:33:19.816619: step: 884/530, loss: 0.000481678667711094
2023-01-24 10:33:20.890492: step: 888/530, loss: 0.0017502587288618088
2023-01-24 10:33:21.994478: step: 892/530, loss: 0.010046809911727905
2023-01-24 10:33:23.089630: step: 896/530, loss: 0.004912385251373053
2023-01-24 10:33:24.180812: step: 900/530, loss: 0.0021108752116560936
2023-01-24 10:33:25.254013: step: 904/530, loss: 0.00012018627603538334
2023-01-24 10:33:26.359338: step: 908/530, loss: 0.0019957348704338074
2023-01-24 10:33:27.444626: step: 912/530, loss: 0.0006939433515071869
2023-01-24 10:33:28.531660: step: 916/530, loss: 0.0043212249875068665
2023-01-24 10:33:29.644664: step: 920/530, loss: 0.006252510938793421
2023-01-24 10:33:30.734190: step: 924/530, loss: 0.0007723422022536397
2023-01-24 10:33:31.824916: step: 928/530, loss: 0.0011998937698081136
2023-01-24 10:33:32.903218: step: 932/530, loss: 0.006741023156791925
2023-01-24 10:33:33.990783: step: 936/530, loss: 3.805392043432221e-05
2023-01-24 10:33:35.088398: step: 940/530, loss: 0.00033521157456561923
2023-01-24 10:33:36.193042: step: 944/530, loss: 0.007296199444681406
2023-01-24 10:33:37.296205: step: 948/530, loss: 0.0022839608136564493
2023-01-24 10:33:38.371539: step: 952/530, loss: 0.0009386551682837307
2023-01-24 10:33:39.462586: step: 956/530, loss: 0.002275177976116538
2023-01-24 10:33:40.551621: step: 960/530, loss: 0.00646181171759963
2023-01-24 10:33:41.662385: step: 964/530, loss: 0.0026393351145088673
2023-01-24 10:33:42.757401: step: 968/530, loss: 0.0013786256313323975
2023-01-24 10:33:43.836087: step: 972/530, loss: 3.009774218298844e-06
2023-01-24 10:33:44.945575: step: 976/530, loss: 0.005927097983658314
2023-01-24 10:33:46.046926: step: 980/530, loss: 0.00010646599548636004
2023-01-24 10:33:47.130289: step: 984/530, loss: 0.0033073725644499063
2023-01-24 10:33:48.225196: step: 988/530, loss: 8.717246964806691e-05
2023-01-24 10:33:49.300371: step: 992/530, loss: 0.0015189225086942315
2023-01-24 10:33:50.383658: step: 996/530, loss: 0.0008218188886530697
2023-01-24 10:33:51.476797: step: 1000/530, loss: 0.01095456350594759
2023-01-24 10:33:52.555765: step: 1004/530, loss: 0.004398738499730825
2023-01-24 10:33:53.655168: step: 1008/530, loss: 0.004040711093693972
2023-01-24 10:33:54.742405: step: 1012/530, loss: 0.0013462050119414926
2023-01-24 10:33:55.834165: step: 1016/530, loss: 0.018077151849865913
2023-01-24 10:33:56.923001: step: 1020/530, loss: 0.0008204568293876946
2023-01-24 10:33:58.024689: step: 1024/530, loss: 0.008758884854614735
2023-01-24 10:33:59.113478: step: 1028/530, loss: 0.007381300907582045
2023-01-24 10:34:00.205143: step: 1032/530, loss: 0.0020989899057894945
2023-01-24 10:34:01.302518: step: 1036/530, loss: 0.005010779947042465
2023-01-24 10:34:02.386616: step: 1040/530, loss: 1.5025427273940295e-05
2023-01-24 10:34:03.472381: step: 1044/530, loss: 0.010882746428251266
2023-01-24 10:34:04.580493: step: 1048/530, loss: 0.0030730734579265118
2023-01-24 10:34:05.644381: step: 1052/530, loss: 1.9689518012455665e-05
2023-01-24 10:34:06.730250: step: 1056/530, loss: 1.5188254110398702e-05
2023-01-24 10:34:07.814352: step: 1060/530, loss: 0.0003083275514654815
2023-01-24 10:34:08.906828: step: 1064/530, loss: 0.005573458969593048
2023-01-24 10:34:10.022982: step: 1068/530, loss: 0.022893719375133514
2023-01-24 10:34:11.116399: step: 1072/530, loss: 0.0025528757832944393
2023-01-24 10:34:12.187509: step: 1076/530, loss: 0.00040614043246023357
2023-01-24 10:34:13.265322: step: 1080/530, loss: 0.0025634909979999065
2023-01-24 10:34:14.358837: step: 1084/530, loss: 0.0006221125368028879
2023-01-24 10:34:15.458455: step: 1088/530, loss: 0.006092137191444635
2023-01-24 10:34:16.538874: step: 1092/530, loss: 0.00023583446454722434
2023-01-24 10:34:17.620178: step: 1096/530, loss: 0.0018546071369200945
2023-01-24 10:34:18.722490: step: 1100/530, loss: 0.001455626799724996
2023-01-24 10:34:19.817646: step: 1104/530, loss: 0.0009344169520772994
2023-01-24 10:34:20.921935: step: 1108/530, loss: 0.001996472245082259
2023-01-24 10:34:22.018085: step: 1112/530, loss: 0.00409529497846961
2023-01-24 10:34:23.118622: step: 1116/530, loss: 0.011121563613414764
2023-01-24 10:34:24.214453: step: 1120/530, loss: 0.0013962743105366826
2023-01-24 10:34:25.316387: step: 1124/530, loss: 0.004220105707645416
2023-01-24 10:34:26.381786: step: 1128/530, loss: 0.0031265011057257652
2023-01-24 10:34:27.466343: step: 1132/530, loss: 0.006375927943736315
2023-01-24 10:34:28.544842: step: 1136/530, loss: 0.0009379417169839144
2023-01-24 10:34:29.606172: step: 1140/530, loss: 9.866567415883765e-05
2023-01-24 10:34:30.706128: step: 1144/530, loss: 0.0006635566824115813
2023-01-24 10:34:31.783032: step: 1148/530, loss: 0.003601459553465247
2023-01-24 10:34:32.851881: step: 1152/530, loss: 0.0013722165022045374
2023-01-24 10:34:33.933264: step: 1156/530, loss: 0.0333854965865612
2023-01-24 10:34:35.046887: step: 1160/530, loss: 0.0010874661384150386
2023-01-24 10:34:36.147417: step: 1164/530, loss: 0.00022803246974945068
2023-01-24 10:34:37.232319: step: 1168/530, loss: 5.935566605330678e-06
2023-01-24 10:34:38.320238: step: 1172/530, loss: 0.0023388874251395464
2023-01-24 10:34:39.411647: step: 1176/530, loss: 0.0008275939617305994
2023-01-24 10:34:40.512638: step: 1180/530, loss: 0.00235777092166245
2023-01-24 10:34:41.606184: step: 1184/530, loss: 0.003099546767771244
2023-01-24 10:34:42.695875: step: 1188/530, loss: 0.007683195639401674
2023-01-24 10:34:43.803240: step: 1192/530, loss: 0.01222831942141056
2023-01-24 10:34:44.903050: step: 1196/530, loss: 0.0015453894156962633
2023-01-24 10:34:45.991621: step: 1200/530, loss: 0.0022118159104138613
2023-01-24 10:34:47.081448: step: 1204/530, loss: 0.006718839053064585
2023-01-24 10:34:48.187383: step: 1208/530, loss: 0.002990497974678874
2023-01-24 10:34:49.279618: step: 1212/530, loss: 0.0012237633345648646
2023-01-24 10:34:50.377300: step: 1216/530, loss: 0.01069978903979063
2023-01-24 10:34:51.482990: step: 1220/530, loss: 0.0003575255977921188
2023-01-24 10:34:52.603758: step: 1224/530, loss: 0.0004864147340413183
2023-01-24 10:34:53.688081: step: 1228/530, loss: 0.0006158277974463999
2023-01-24 10:34:54.760901: step: 1232/530, loss: 0.008188759908080101
2023-01-24 10:34:55.851622: step: 1236/530, loss: 0.006146847270429134
2023-01-24 10:34:56.973083: step: 1240/530, loss: 0.0022965569514781237
2023-01-24 10:34:58.043294: step: 1244/530, loss: 0.001639484311453998
2023-01-24 10:34:59.123700: step: 1248/530, loss: 0.006271504797041416
2023-01-24 10:35:00.225640: step: 1252/530, loss: 0.0011681526666507125
2023-01-24 10:35:01.302916: step: 1256/530, loss: 0.007113034371286631
2023-01-24 10:35:02.415185: step: 1260/530, loss: 0.005143363960087299
2023-01-24 10:35:03.510297: step: 1264/530, loss: 0.0004639250983018428
2023-01-24 10:35:04.636256: step: 1268/530, loss: 0.0005338076734915376
2023-01-24 10:35:05.720701: step: 1272/530, loss: 8.12380385468714e-05
2023-01-24 10:35:06.820801: step: 1276/530, loss: 0.0009575830190442502
2023-01-24 10:35:07.907711: step: 1280/530, loss: 0.0010877613676711917
2023-01-24 10:35:09.001632: step: 1284/530, loss: 0.0023875616025179625
2023-01-24 10:35:10.093801: step: 1288/530, loss: 0.0004638465470634401
2023-01-24 10:35:11.200701: step: 1292/530, loss: 0.002524861367419362
2023-01-24 10:35:12.289597: step: 1296/530, loss: 7.034824375296012e-05
2023-01-24 10:35:13.387736: step: 1300/530, loss: 0.004284720867872238
2023-01-24 10:35:14.481829: step: 1304/530, loss: 0.012702934443950653
2023-01-24 10:35:15.577550: step: 1308/530, loss: 0.0013486533425748348
2023-01-24 10:35:16.648895: step: 1312/530, loss: 8.894842176232487e-05
2023-01-24 10:35:17.754608: step: 1316/530, loss: 0.004712602589279413
2023-01-24 10:35:18.827654: step: 1320/530, loss: 0.001283988356590271
2023-01-24 10:35:19.899903: step: 1324/530, loss: 2.7795958885690197e-05
2023-01-24 10:35:20.990907: step: 1328/530, loss: 0.0005046577425673604
2023-01-24 10:35:22.078781: step: 1332/530, loss: 0.0006284591509029269
2023-01-24 10:35:23.148186: step: 1336/530, loss: 0.003634740598499775
2023-01-24 10:35:24.238910: step: 1340/530, loss: 7.278336124727502e-05
2023-01-24 10:35:25.352277: step: 1344/530, loss: 0.0007392282132059336
2023-01-24 10:35:26.451765: step: 1348/530, loss: 0.000643865903839469
2023-01-24 10:35:27.520475: step: 1352/530, loss: 3.5265742326373584e-07
2023-01-24 10:35:28.599520: step: 1356/530, loss: 0.0022137747146189213
2023-01-24 10:35:29.704750: step: 1360/530, loss: 0.00041922854143194854
2023-01-24 10:35:30.790384: step: 1364/530, loss: 0.0040763677097857
2023-01-24 10:35:31.888331: step: 1368/530, loss: 0.009680839255452156
2023-01-24 10:35:32.977975: step: 1372/530, loss: 0.008086957037448883
2023-01-24 10:35:34.073786: step: 1376/530, loss: 0.004043171647936106
2023-01-24 10:35:35.152235: step: 1380/530, loss: 0.0018598099704831839
2023-01-24 10:35:36.241580: step: 1384/530, loss: 0.0006758856470696628
2023-01-24 10:35:37.351581: step: 1388/530, loss: 0.0037887301295995712
2023-01-24 10:35:38.424220: step: 1392/530, loss: 0.0052274675108492374
2023-01-24 10:35:39.522869: step: 1396/530, loss: 0.004116029478609562
2023-01-24 10:35:40.603264: step: 1400/530, loss: 9.88139581750147e-05
2023-01-24 10:35:41.686690: step: 1404/530, loss: 6.6203047026647255e-06
2023-01-24 10:35:42.793800: step: 1408/530, loss: 0.002617774996906519
2023-01-24 10:35:43.892179: step: 1412/530, loss: 0.001070051803253591
2023-01-24 10:35:44.974368: step: 1416/530, loss: 0.0008536711102351546
2023-01-24 10:35:46.044019: step: 1420/530, loss: 0.01228385791182518
2023-01-24 10:35:47.131584: step: 1424/530, loss: 0.0018940340960398316
2023-01-24 10:35:48.218754: step: 1428/530, loss: 6.663881504209712e-05
2023-01-24 10:35:49.308843: step: 1432/530, loss: 0.0033455672673881054
2023-01-24 10:35:50.384350: step: 1436/530, loss: 1.7605614630156197e-05
2023-01-24 10:35:51.493682: step: 1440/530, loss: 0.001410569646395743
2023-01-24 10:35:52.581268: step: 1444/530, loss: 0.006385213695466518
2023-01-24 10:35:53.643646: step: 1448/530, loss: 0.001963956281542778
2023-01-24 10:35:54.722681: step: 1452/530, loss: 0.0007068910053931177
2023-01-24 10:35:55.822077: step: 1456/530, loss: 0.0016609654994681478
2023-01-24 10:35:56.904981: step: 1460/530, loss: 0.002481671515852213
2023-01-24 10:35:58.009497: step: 1464/530, loss: 0.0023920934181660414
2023-01-24 10:35:59.083404: step: 1468/530, loss: 0.0003659272624645382
2023-01-24 10:36:00.153505: step: 1472/530, loss: 0.0005528698093257844
2023-01-24 10:36:01.235708: step: 1476/530, loss: 0.00032423148513771594
2023-01-24 10:36:02.320828: step: 1480/530, loss: 0.0002946548629552126
2023-01-24 10:36:03.402947: step: 1484/530, loss: 0.0008898377418518066
2023-01-24 10:36:04.476756: step: 1488/530, loss: 0.0024196216836571693
2023-01-24 10:36:05.577083: step: 1492/530, loss: 0.013456962071359158
2023-01-24 10:36:06.638097: step: 1496/530, loss: 0.0010293158702552319
2023-01-24 10:36:07.713483: step: 1500/530, loss: 0.0020077268127352
2023-01-24 10:36:08.793059: step: 1504/530, loss: 0.013075864873826504
2023-01-24 10:36:09.896489: step: 1508/530, loss: 5.658302325173281e-05
2023-01-24 10:36:10.991248: step: 1512/530, loss: 0.0009153262944892049
2023-01-24 10:36:12.107801: step: 1516/530, loss: 0.004963977262377739
2023-01-24 10:36:13.206398: step: 1520/530, loss: 0.0036875337827950716
2023-01-24 10:36:14.282456: step: 1524/530, loss: 0.002731300424784422
2023-01-24 10:36:15.363961: step: 1528/530, loss: 0.012656821869313717
2023-01-24 10:36:16.437208: step: 1532/530, loss: 0.0008387502748519182
2023-01-24 10:36:17.530227: step: 1536/530, loss: 0.0032218273263424635
2023-01-24 10:36:18.630604: step: 1540/530, loss: 0.00024911388754844666
2023-01-24 10:36:19.730994: step: 1544/530, loss: 0.023877687752246857
2023-01-24 10:36:20.809752: step: 1548/530, loss: 0.00823256280273199
2023-01-24 10:36:21.898078: step: 1552/530, loss: 0.02221542038023472
2023-01-24 10:36:22.992554: step: 1556/530, loss: 0.005809667985886335
2023-01-24 10:36:24.074280: step: 1560/530, loss: 0.0027239446062594652
2023-01-24 10:36:25.179968: step: 1564/530, loss: 0.022694837301969528
2023-01-24 10:36:26.270365: step: 1568/530, loss: 0.014259930700063705
2023-01-24 10:36:27.365025: step: 1572/530, loss: 0.00015027608606033027
2023-01-24 10:36:28.475718: step: 1576/530, loss: 0.005722373723983765
2023-01-24 10:36:29.553135: step: 1580/530, loss: 0.00357958790846169
2023-01-24 10:36:30.663461: step: 1584/530, loss: 0.0043758824467659
2023-01-24 10:36:31.753604: step: 1588/530, loss: 0.003674211213365197
2023-01-24 10:36:32.850321: step: 1592/530, loss: 2.4529456368327374e-06
2023-01-24 10:36:33.957012: step: 1596/530, loss: 0.0031450423412024975
2023-01-24 10:36:35.046348: step: 1600/530, loss: 0.003242489416152239
2023-01-24 10:36:36.166177: step: 1604/530, loss: 0.0006098906742408872
2023-01-24 10:36:37.266435: step: 1608/530, loss: 0.0019877140875905752
2023-01-24 10:36:38.355186: step: 1612/530, loss: 0.001345456694252789
2023-01-24 10:36:39.456779: step: 1616/530, loss: 0.002948288805782795
2023-01-24 10:36:40.533625: step: 1620/530, loss: 8.273212301901367e-07
2023-01-24 10:36:41.645101: step: 1624/530, loss: 0.0038146143779158592
2023-01-24 10:36:42.755841: step: 1628/530, loss: 0.00317201460711658
2023-01-24 10:36:43.846478: step: 1632/530, loss: 0.0015082353493198752
2023-01-24 10:36:44.948735: step: 1636/530, loss: 0.0003809299669228494
2023-01-24 10:36:46.041065: step: 1640/530, loss: 0.013876257464289665
2023-01-24 10:36:47.116430: step: 1644/530, loss: 0.00010343162284698337
2023-01-24 10:36:48.207476: step: 1648/530, loss: 0.0009813953656703234
2023-01-24 10:36:49.306883: step: 1652/530, loss: 2.960980054922402e-05
2023-01-24 10:36:50.407658: step: 1656/530, loss: 0.0052544656209647655
2023-01-24 10:36:51.498386: step: 1660/530, loss: 1.619407703401521e-05
2023-01-24 10:36:52.578902: step: 1664/530, loss: 0.001400230685248971
2023-01-24 10:36:53.682866: step: 1668/530, loss: 0.0016509218839928508
2023-01-24 10:36:54.766128: step: 1672/530, loss: 0.001079654903151095
2023-01-24 10:36:55.871045: step: 1676/530, loss: 0.004524801392108202
2023-01-24 10:36:56.949256: step: 1680/530, loss: 0.0010629636235535145
2023-01-24 10:36:58.040816: step: 1684/530, loss: 0.00010164112609345466
2023-01-24 10:36:59.140145: step: 1688/530, loss: 0.00247724587097764
2023-01-24 10:37:00.226616: step: 1692/530, loss: 0.005047983024269342
2023-01-24 10:37:01.303404: step: 1696/530, loss: 0.0013642992125824094
2023-01-24 10:37:02.387663: step: 1700/530, loss: 0.0004914554883725941
2023-01-24 10:37:03.521569: step: 1704/530, loss: 0.005199359729886055
2023-01-24 10:37:04.619415: step: 1708/530, loss: 0.0060662259347736835
2023-01-24 10:37:05.716925: step: 1712/530, loss: 0.0009265231783501804
2023-01-24 10:37:06.815235: step: 1716/530, loss: 0.0
2023-01-24 10:37:07.930975: step: 1720/530, loss: 0.0019822362810373306
2023-01-24 10:37:09.024136: step: 1724/530, loss: 3.788025787798688e-05
2023-01-24 10:37:10.133980: step: 1728/530, loss: 0.005469823721796274
2023-01-24 10:37:11.226419: step: 1732/530, loss: 0.004149814136326313
2023-01-24 10:37:12.319258: step: 1736/530, loss: 0.0017180907307192683
2023-01-24 10:37:13.399629: step: 1740/530, loss: 0.00011590938083827496
2023-01-24 10:37:14.501328: step: 1744/530, loss: 0.0024439338594675064
2023-01-24 10:37:15.596042: step: 1748/530, loss: 0.0024968907237052917
2023-01-24 10:37:16.704473: step: 1752/530, loss: 0.005898426752537489
2023-01-24 10:37:17.801290: step: 1756/530, loss: 0.002481900155544281
2023-01-24 10:37:18.892959: step: 1760/530, loss: 0.0011037297081202269
2023-01-24 10:37:20.002579: step: 1764/530, loss: 0.0024954553227871656
2023-01-24 10:37:21.074402: step: 1768/530, loss: 0.0024645228404551744
2023-01-24 10:37:22.179787: step: 1772/530, loss: 0.0009285281994380057
2023-01-24 10:37:23.258175: step: 1776/530, loss: 0.003900257172062993
2023-01-24 10:37:24.366202: step: 1780/530, loss: 0.003312863875180483
2023-01-24 10:37:25.466023: step: 1784/530, loss: 0.003721606684848666
2023-01-24 10:37:26.541700: step: 1788/530, loss: 3.9572481909999624e-05
2023-01-24 10:37:27.636654: step: 1792/530, loss: 0.014231804758310318
2023-01-24 10:37:28.721478: step: 1796/530, loss: 0.0001211568815051578
2023-01-24 10:37:29.824074: step: 1800/530, loss: 0.02522517926990986
2023-01-24 10:37:30.907570: step: 1804/530, loss: 0.0030734154861420393
2023-01-24 10:37:32.006036: step: 1808/530, loss: 0.0008686508517712355
2023-01-24 10:37:33.112221: step: 1812/530, loss: 0.0011809499701485038
2023-01-24 10:37:34.201976: step: 1816/530, loss: 0.0007994048064574599
2023-01-24 10:37:35.281341: step: 1820/530, loss: 0.002967127598822117
2023-01-24 10:37:36.374696: step: 1824/530, loss: 9.524337656330317e-06
2023-01-24 10:37:37.457850: step: 1828/530, loss: 0.004406691994518042
2023-01-24 10:37:38.556805: step: 1832/530, loss: 0.0013986529083922505
2023-01-24 10:37:39.672102: step: 1836/530, loss: 0.0016440274193882942
2023-01-24 10:37:40.754676: step: 1840/530, loss: 0.009066744707524776
2023-01-24 10:37:41.829591: step: 1844/530, loss: 0.0002761918876785785
2023-01-24 10:37:42.909225: step: 1848/530, loss: 0.0011494659120216966
2023-01-24 10:37:43.987243: step: 1852/530, loss: 0.0006082436884753406
2023-01-24 10:37:45.077829: step: 1856/530, loss: 0.005805442109704018
2023-01-24 10:37:46.195744: step: 1860/530, loss: 0.0016728354385122657
2023-01-24 10:37:47.260052: step: 1864/530, loss: 0.0005908252205699682
2023-01-24 10:37:48.348175: step: 1868/530, loss: 0.0031077589374035597
2023-01-24 10:37:49.435709: step: 1872/530, loss: 0.0036844387650489807
2023-01-24 10:37:50.519096: step: 1876/530, loss: 0.0021285268012434244
2023-01-24 10:37:51.601573: step: 1880/530, loss: 0.006949524860829115
2023-01-24 10:37:52.700825: step: 1884/530, loss: 0.002678863937035203
2023-01-24 10:37:53.793734: step: 1888/530, loss: 0.004842081572860479
2023-01-24 10:37:54.858417: step: 1892/530, loss: 0.0006235690088942647
2023-01-24 10:37:55.955987: step: 1896/530, loss: 0.0004585866117849946
2023-01-24 10:37:57.048595: step: 1900/530, loss: 0.008985369466245174
2023-01-24 10:37:58.122535: step: 1904/530, loss: 0.0001941321970662102
2023-01-24 10:37:59.193403: step: 1908/530, loss: 0.009316373616456985
2023-01-24 10:38:00.273269: step: 1912/530, loss: 0.0
2023-01-24 10:38:01.377674: step: 1916/530, loss: 0.006425163708627224
2023-01-24 10:38:02.471483: step: 1920/530, loss: 0.0010336049599573016
2023-01-24 10:38:03.567246: step: 1924/530, loss: 0.0001332381652900949
2023-01-24 10:38:04.647409: step: 1928/530, loss: 0.013687378726899624
2023-01-24 10:38:05.736724: step: 1932/530, loss: 0.0021381631959229708
2023-01-24 10:38:06.829864: step: 1936/530, loss: 0.00012012131628580391
2023-01-24 10:38:07.915774: step: 1940/530, loss: 0.00014436228957492858
2023-01-24 10:38:09.013399: step: 1944/530, loss: 0.015538678504526615
2023-01-24 10:38:10.092574: step: 1948/530, loss: 0.0001945592084666714
2023-01-24 10:38:11.192797: step: 1952/530, loss: 0.0036120894365012646
2023-01-24 10:38:12.296928: step: 1956/530, loss: 8.194353540602606e-06
2023-01-24 10:38:13.395603: step: 1960/530, loss: 0.005616932641714811
2023-01-24 10:38:14.507465: step: 1964/530, loss: 0.005948303733021021
2023-01-24 10:38:15.600920: step: 1968/530, loss: 0.00020649051293730736
2023-01-24 10:38:16.669844: step: 1972/530, loss: 0.0004324015462771058
2023-01-24 10:38:17.777462: step: 1976/530, loss: 8.814790635369718e-05
2023-01-24 10:38:18.858747: step: 1980/530, loss: 0.00025432216352783144
2023-01-24 10:38:19.955045: step: 1984/530, loss: 0.00011884964624186978
2023-01-24 10:38:21.038639: step: 1988/530, loss: 0.00917538907378912
2023-01-24 10:38:22.107190: step: 1992/530, loss: 0.0002176128327846527
2023-01-24 10:38:23.188467: step: 1996/530, loss: 0.004938729107379913
2023-01-24 10:38:24.290162: step: 2000/530, loss: 0.000126317361718975
2023-01-24 10:38:25.377980: step: 2004/530, loss: 0.017990481108427048
2023-01-24 10:38:26.468278: step: 2008/530, loss: 0.003084475640207529
2023-01-24 10:38:27.562627: step: 2012/530, loss: 0.005482024978846312
2023-01-24 10:38:28.655004: step: 2016/530, loss: 0.006015224382281303
2023-01-24 10:38:29.802507: step: 2020/530, loss: 0.001774609205313027
2023-01-24 10:38:30.882686: step: 2024/530, loss: 0.005875098519027233
2023-01-24 10:38:31.963464: step: 2028/530, loss: 0.0021836848463863134
2023-01-24 10:38:33.058275: step: 2032/530, loss: 0.002014268422499299
2023-01-24 10:38:34.125937: step: 2036/530, loss: 0.0021670558489859104
2023-01-24 10:38:35.225371: step: 2040/530, loss: 0.003708336967974901
2023-01-24 10:38:36.322525: step: 2044/530, loss: 0.0014673734549432993
2023-01-24 10:38:37.415715: step: 2048/530, loss: 0.0003642119700089097
2023-01-24 10:38:38.520936: step: 2052/530, loss: 0.008844273164868355
2023-01-24 10:38:39.629810: step: 2056/530, loss: 0.0008772752480581403
2023-01-24 10:38:40.728096: step: 2060/530, loss: 0.0020840431097894907
2023-01-24 10:38:41.848692: step: 2064/530, loss: 0.00027094673714600503
2023-01-24 10:38:42.936906: step: 2068/530, loss: 0.000147123821079731
2023-01-24 10:38:44.022917: step: 2072/530, loss: 0.006090828217566013
2023-01-24 10:38:45.128589: step: 2076/530, loss: 0.009165171533823013
2023-01-24 10:38:46.199133: step: 2080/530, loss: 0.0060962350107729435
2023-01-24 10:38:47.290822: step: 2084/530, loss: 5.152806352271e-06
2023-01-24 10:38:48.359008: step: 2088/530, loss: 0.007182287517935038
2023-01-24 10:38:49.441835: step: 2092/530, loss: 0.004165596794337034
2023-01-24 10:38:50.525748: step: 2096/530, loss: 0.001052184379659593
2023-01-24 10:38:51.610795: step: 2100/530, loss: 0.007389001548290253
2023-01-24 10:38:52.708287: step: 2104/530, loss: 0.0018403733847662807
2023-01-24 10:38:53.771831: step: 2108/530, loss: 1.4677470971946605e-07
2023-01-24 10:38:54.852036: step: 2112/530, loss: 0.00014616147382184863
2023-01-24 10:38:55.932413: step: 2116/530, loss: 0.000502644048538059
2023-01-24 10:38:57.006357: step: 2120/530, loss: 0.002124864375218749
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3515071571812516, 'r': 0.3448371921493493, 'f1': 0.3481402303883277}, 'combined': 0.25652438028613617, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3436884803464391, 'r': 0.2739989269626409, 'f1': 0.30491239973498063}, 'combined': 0.18936664825646166, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39207650570905606, 'r': 0.33255825057295646, 'f1': 0.35987309661590977}, 'combined': 0.2651696501380388, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33326428868322444, 'r': 0.2604862177356033, 'f1': 0.2924149221835059}, 'combined': 0.18160505693501947, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3792313030358602, 'r': 0.32454139975175134, 'f1': 0.3497613858265296}, 'combined': 0.2577189158721797, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3445390263719436, 'r': 0.2669922366258398, 'f1': 0.3008488717485826}, 'combined': 0.18684298350701448, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 10:41:22.120021: step: 4/530, loss: 0.0034808169584721327
2023-01-24 10:41:23.212943: step: 8/530, loss: 0.0018997406587004662
2023-01-24 10:41:24.295497: step: 12/530, loss: 0.002144439844414592
2023-01-24 10:41:25.367556: step: 16/530, loss: 3.552175985532813e-05
2023-01-24 10:41:26.461591: step: 20/530, loss: 0.015589152462780476
2023-01-24 10:41:27.551842: step: 24/530, loss: 0.0011679998133331537
2023-01-24 10:41:28.647430: step: 28/530, loss: 0.0056754183024168015
2023-01-24 10:41:29.764383: step: 32/530, loss: 0.0048375255428254604
2023-01-24 10:41:30.836867: step: 36/530, loss: 0.0049126893281936646
2023-01-24 10:41:31.931516: step: 40/530, loss: 0.008735156618058681
2023-01-24 10:41:33.043716: step: 44/530, loss: 0.000172492626006715
2023-01-24 10:41:34.142411: step: 48/530, loss: 0.0001775828714016825
2023-01-24 10:41:35.235627: step: 52/530, loss: 0.0001304171746596694
2023-01-24 10:41:36.332907: step: 56/530, loss: 6.779382965760306e-05
2023-01-24 10:41:37.455167: step: 60/530, loss: 0.0010022937785834074
2023-01-24 10:41:38.551390: step: 64/530, loss: 0.0010771224042400718
2023-01-24 10:41:39.634627: step: 68/530, loss: 1.5661638826713897e-05
2023-01-24 10:41:40.740160: step: 72/530, loss: 0.001393350656144321
2023-01-24 10:41:41.869913: step: 76/530, loss: 0.002266770461574197
2023-01-24 10:41:42.974771: step: 80/530, loss: 1.681139474385418e-05
2023-01-24 10:41:44.059274: step: 84/530, loss: 0.0007144093397073448
2023-01-24 10:41:45.139643: step: 88/530, loss: 0.001190351671539247
2023-01-24 10:41:46.222640: step: 92/530, loss: 0.0004423519130796194
2023-01-24 10:41:47.317562: step: 96/530, loss: 0.0002996137482114136
2023-01-24 10:41:48.396878: step: 100/530, loss: 0.010776826180517673
2023-01-24 10:41:49.482254: step: 104/530, loss: 0.0009892707457765937
2023-01-24 10:41:50.601644: step: 108/530, loss: 0.003703233553096652
2023-01-24 10:41:51.684211: step: 112/530, loss: 0.004948604851961136
2023-01-24 10:41:52.765440: step: 116/530, loss: 3.733527762506128e-07
2023-01-24 10:41:53.842955: step: 120/530, loss: 0.004020960070192814
2023-01-24 10:41:54.931458: step: 124/530, loss: 0.0008976784883998334
2023-01-24 10:41:56.019638: step: 128/530, loss: 0.0017104309517890215
2023-01-24 10:41:57.119193: step: 132/530, loss: 0.0011665651109069586
2023-01-24 10:41:58.201587: step: 136/530, loss: 7.510670548072085e-05
2023-01-24 10:41:59.300749: step: 140/530, loss: 0.006148394662886858
2023-01-24 10:42:00.387406: step: 144/530, loss: 0.003674423089250922
2023-01-24 10:42:01.455944: step: 148/530, loss: 0.005385248456150293
2023-01-24 10:42:02.558926: step: 152/530, loss: 0.006293687969446182
2023-01-24 10:42:03.642435: step: 156/530, loss: 0.0004134675255045295
2023-01-24 10:42:04.726067: step: 160/530, loss: 0.0027773447800427675
2023-01-24 10:42:05.815622: step: 164/530, loss: 0.03866887837648392
2023-01-24 10:42:06.922179: step: 168/530, loss: 0.0017375019378960133
2023-01-24 10:42:08.013597: step: 172/530, loss: 0.001592339831404388
2023-01-24 10:42:09.117764: step: 176/530, loss: 0.012710786424577236
2023-01-24 10:42:10.218598: step: 180/530, loss: 0.02182740904390812
2023-01-24 10:42:11.313242: step: 184/530, loss: 7.350520900217816e-05
2023-01-24 10:42:12.406897: step: 188/530, loss: 0.007247790694236755
2023-01-24 10:42:13.495132: step: 192/530, loss: 0.0032906096894294024
2023-01-24 10:42:14.588306: step: 196/530, loss: 0.0011998474365100265
2023-01-24 10:42:15.665719: step: 200/530, loss: 0.002117785392329097
2023-01-24 10:42:16.757747: step: 204/530, loss: 0.0002837668580468744
2023-01-24 10:42:17.872863: step: 208/530, loss: 0.0007688378682360053
2023-01-24 10:42:18.981316: step: 212/530, loss: 7.450579597723106e-10
2023-01-24 10:42:20.069390: step: 216/530, loss: 0.0013182366965338588
2023-01-24 10:42:21.134070: step: 220/530, loss: 0.0015739495866000652
2023-01-24 10:42:22.218802: step: 224/530, loss: 0.00012653223529923707
2023-01-24 10:42:23.321315: step: 228/530, loss: 0.0036604790948331356
2023-01-24 10:42:24.408933: step: 232/530, loss: 0.0034920531325042248
2023-01-24 10:42:25.485624: step: 236/530, loss: 0.00047044819802977145
2023-01-24 10:42:26.567821: step: 240/530, loss: 0.0003440014261286706
2023-01-24 10:42:27.644972: step: 244/530, loss: 0.006319877225905657
2023-01-24 10:42:28.741197: step: 248/530, loss: 0.0071740709245204926
2023-01-24 10:42:29.846499: step: 252/530, loss: 0.006342435721307993
2023-01-24 10:42:30.931826: step: 256/530, loss: 8.749008884478826e-06
2023-01-24 10:42:32.028372: step: 260/530, loss: 0.0001330746745225042
2023-01-24 10:42:33.101669: step: 264/530, loss: 0.001663908245973289
2023-01-24 10:42:34.222689: step: 268/530, loss: 0.0046469164080917835
2023-01-24 10:42:35.327840: step: 272/530, loss: 0.0023898312356323004
2023-01-24 10:42:36.420845: step: 276/530, loss: 0.0023684173356741667
2023-01-24 10:42:37.508948: step: 280/530, loss: 0.004610610194504261
2023-01-24 10:42:38.578527: step: 284/530, loss: 4.1727969801286235e-05
2023-01-24 10:42:39.676288: step: 288/530, loss: 0.0047868299297988415
2023-01-24 10:42:40.774357: step: 292/530, loss: 0.0014362818328663707
2023-01-24 10:42:41.889179: step: 296/530, loss: 0.013098294846713543
2023-01-24 10:42:42.988249: step: 300/530, loss: 0.000280734762782231
2023-01-24 10:42:44.091930: step: 304/530, loss: 0.0012219070922583342
2023-01-24 10:42:45.169558: step: 308/530, loss: 0.0007669119513593614
2023-01-24 10:42:46.276997: step: 312/530, loss: 1.3020689038967248e-05
2023-01-24 10:42:47.373118: step: 316/530, loss: 0.009945424273610115
2023-01-24 10:42:48.451178: step: 320/530, loss: 0.0043518198654055595
2023-01-24 10:42:49.542661: step: 324/530, loss: 0.00011538516264408827
2023-01-24 10:42:50.618856: step: 328/530, loss: 9.029215289046988e-05
2023-01-24 10:42:51.712790: step: 332/530, loss: 0.0002399556979071349
2023-01-24 10:42:52.799813: step: 336/530, loss: 0.007572166156023741
2023-01-24 10:42:53.865360: step: 340/530, loss: 0.0001940718648256734
2023-01-24 10:42:54.946972: step: 344/530, loss: 0.0036341894883662462
2023-01-24 10:42:56.034345: step: 348/530, loss: 0.000201019603991881
2023-01-24 10:42:57.129543: step: 352/530, loss: 0.0007032624562270939
2023-01-24 10:42:58.221208: step: 356/530, loss: 0.000679805816616863
2023-01-24 10:42:59.323702: step: 360/530, loss: 0.002421688986942172
2023-01-24 10:43:00.433830: step: 364/530, loss: 0.015139338560402393
2023-01-24 10:43:01.524575: step: 368/530, loss: 0.0007957784691825509
2023-01-24 10:43:02.610042: step: 372/530, loss: 0.0026553990319371223
2023-01-24 10:43:03.709227: step: 376/530, loss: 0.0024460679851472378
2023-01-24 10:43:04.827114: step: 380/530, loss: 0.0027359339874237776
2023-01-24 10:43:05.920796: step: 384/530, loss: 0.005867304280400276
2023-01-24 10:43:07.044781: step: 388/530, loss: 0.004757972899824381
2023-01-24 10:43:08.114319: step: 392/530, loss: 4.183263808954507e-05
2023-01-24 10:43:09.205738: step: 396/530, loss: 2.556456092861481e-05
2023-01-24 10:43:10.304013: step: 400/530, loss: 0.0015227266121655703
2023-01-24 10:43:11.414049: step: 404/530, loss: 6.342248525470495e-05
2023-01-24 10:43:12.519876: step: 408/530, loss: 0.0014097301755100489
2023-01-24 10:43:13.597256: step: 412/530, loss: 0.00048197878641076386
2023-01-24 10:43:14.686638: step: 416/530, loss: 0.002813866129145026
2023-01-24 10:43:15.794318: step: 420/530, loss: 2.2102161892689764e-05
2023-01-24 10:43:16.884624: step: 424/530, loss: 0.0030066766776144505
2023-01-24 10:43:17.967054: step: 428/530, loss: 0.00028449707315303385
2023-01-24 10:43:19.064802: step: 432/530, loss: 0.0026070221792906523
2023-01-24 10:43:20.155866: step: 436/530, loss: 0.0037741651758551598
2023-01-24 10:43:21.228667: step: 440/530, loss: 0.002109530149027705
2023-01-24 10:43:22.299721: step: 444/530, loss: 0.002431826665997505
2023-01-24 10:43:23.404077: step: 448/530, loss: 0.0010731664951890707
2023-01-24 10:43:24.479332: step: 452/530, loss: 0.0021129047963768244
2023-01-24 10:43:25.590234: step: 456/530, loss: 0.004795182030647993
2023-01-24 10:43:26.685629: step: 460/530, loss: 0.00022948479454498738
2023-01-24 10:43:27.795911: step: 464/530, loss: 0.0052319359965622425
2023-01-24 10:43:28.894056: step: 468/530, loss: 0.0003693769103847444
2023-01-24 10:43:29.995419: step: 472/530, loss: 0.017211947590112686
2023-01-24 10:43:31.082569: step: 476/530, loss: 0.01170080341398716
2023-01-24 10:43:32.203974: step: 480/530, loss: 0.0010586120188236237
2023-01-24 10:43:33.273936: step: 484/530, loss: 0.00043138189357705414
2023-01-24 10:43:34.339235: step: 488/530, loss: 0.003336365567520261
2023-01-24 10:43:35.460701: step: 492/530, loss: 0.0015763710252940655
2023-01-24 10:43:36.563907: step: 496/530, loss: 0.0006782274576835334
2023-01-24 10:43:37.646329: step: 500/530, loss: 2.6213465389446355e-05
2023-01-24 10:43:38.752686: step: 504/530, loss: 0.003002919489517808
2023-01-24 10:43:39.840406: step: 508/530, loss: 0.0065875910222530365
2023-01-24 10:43:40.922556: step: 512/530, loss: 0.0010819419985637069
2023-01-24 10:43:42.037527: step: 516/530, loss: 0.0004035773454234004
2023-01-24 10:43:43.129066: step: 520/530, loss: 0.0004645856097340584
2023-01-24 10:43:44.241257: step: 524/530, loss: 0.0009050294174812734
2023-01-24 10:43:45.330806: step: 528/530, loss: 3.505948552628979e-05
2023-01-24 10:43:46.413751: step: 532/530, loss: 0.0036793684121221304
2023-01-24 10:43:47.517662: step: 536/530, loss: 0.011716824024915695
2023-01-24 10:43:48.621369: step: 540/530, loss: 0.007206967566162348
2023-01-24 10:43:49.706659: step: 544/530, loss: 0.009051250293850899
2023-01-24 10:43:50.806276: step: 548/530, loss: 0.00013011842384003103
2023-01-24 10:43:51.906277: step: 552/530, loss: 5.353549113351619e-06
2023-01-24 10:43:52.994049: step: 556/530, loss: 0.0006024892209097743
2023-01-24 10:43:54.115073: step: 560/530, loss: 0.004242273513227701
2023-01-24 10:43:55.215195: step: 564/530, loss: 0.00017575321544427425
2023-01-24 10:43:56.304085: step: 568/530, loss: 0.00044714190880768
2023-01-24 10:43:57.402190: step: 572/530, loss: 0.0032757045701146126
2023-01-24 10:43:58.483536: step: 576/530, loss: 0.000928366556763649
2023-01-24 10:43:59.576672: step: 580/530, loss: 0.0011983714066445827
2023-01-24 10:44:00.660384: step: 584/530, loss: 0.0004430399276316166
2023-01-24 10:44:01.740093: step: 588/530, loss: 0.003928348422050476
2023-01-24 10:44:02.822493: step: 592/530, loss: 3.2033615298132645e-06
2023-01-24 10:44:03.894941: step: 596/530, loss: 0.0027793985791504383
2023-01-24 10:44:04.977712: step: 600/530, loss: 0.003533866023644805
2023-01-24 10:44:06.074851: step: 604/530, loss: 0.0006644558743573725
2023-01-24 10:44:07.153845: step: 608/530, loss: 0.00011873383482452482
2023-01-24 10:44:08.253342: step: 612/530, loss: 0.0005890467436984181
2023-01-24 10:44:09.368579: step: 616/530, loss: 0.004688585177063942
2023-01-24 10:44:10.473965: step: 620/530, loss: 0.0012207345571368933
2023-01-24 10:44:11.568269: step: 624/530, loss: 0.0003617858747020364
2023-01-24 10:44:12.663556: step: 628/530, loss: 0.0005774375167675316
2023-01-24 10:44:13.748640: step: 632/530, loss: 0.00032479382934980094
2023-01-24 10:44:14.834879: step: 636/530, loss: 0.00042347575072199106
2023-01-24 10:44:15.919165: step: 640/530, loss: 0.0021121923346072435
2023-01-24 10:44:16.992955: step: 644/530, loss: 2.1308244413376087e-06
2023-01-24 10:44:18.078817: step: 648/530, loss: 0.0008518691174685955
2023-01-24 10:44:19.174728: step: 652/530, loss: 0.006940099410712719
2023-01-24 10:44:20.282198: step: 656/530, loss: 0.0061613707803189754
2023-01-24 10:44:21.378537: step: 660/530, loss: 0.0011795359896495938
2023-01-24 10:44:22.451486: step: 664/530, loss: 0.0006289535667747259
2023-01-24 10:44:23.551227: step: 668/530, loss: 0.020524267107248306
2023-01-24 10:44:24.637805: step: 672/530, loss: 0.0005878504598513246
2023-01-24 10:44:25.713478: step: 676/530, loss: 0.00021731419838033617
2023-01-24 10:44:26.802327: step: 680/530, loss: 0.0005742923240177333
2023-01-24 10:44:27.881961: step: 684/530, loss: 0.0007030502310954034
2023-01-24 10:44:28.987849: step: 688/530, loss: 0.003954659681767225
2023-01-24 10:44:30.065945: step: 692/530, loss: 0.00017020836821757257
2023-01-24 10:44:31.142861: step: 696/530, loss: 0.0005727845709770918
2023-01-24 10:44:32.259295: step: 700/530, loss: 0.0015427382895722985
2023-01-24 10:44:33.351167: step: 704/530, loss: 0.0013018085155636072
2023-01-24 10:44:34.455945: step: 708/530, loss: 0.0025435348507016897
2023-01-24 10:44:35.562406: step: 712/530, loss: 0.001990637741982937
2023-01-24 10:44:36.664790: step: 716/530, loss: 0.0019166427664458752
2023-01-24 10:44:37.766461: step: 720/530, loss: 0.001076818909496069
2023-01-24 10:44:38.860950: step: 724/530, loss: 0.0005725253722630441
2023-01-24 10:44:39.952237: step: 728/530, loss: 0.0002605449699331075
2023-01-24 10:44:41.041207: step: 732/530, loss: 0.004124950151890516
2023-01-24 10:44:42.140588: step: 736/530, loss: 0.004425158724188805
2023-01-24 10:44:43.227815: step: 740/530, loss: 0.0020203827880322933
2023-01-24 10:44:44.326695: step: 744/530, loss: 0.0019976019393652678
2023-01-24 10:44:45.393054: step: 748/530, loss: 2.617143400129862e-05
2023-01-24 10:44:46.456129: step: 752/530, loss: 0.0009109968086704612
2023-01-24 10:44:47.551600: step: 756/530, loss: 0.007275097072124481
2023-01-24 10:44:48.664359: step: 760/530, loss: 0.005125010851770639
2023-01-24 10:44:49.786853: step: 764/530, loss: 0.010058313608169556
2023-01-24 10:44:50.869570: step: 768/530, loss: 0.0005352284642867744
2023-01-24 10:44:51.944468: step: 772/530, loss: 1.1774956874432974e-05
2023-01-24 10:44:53.050791: step: 776/530, loss: 0.012429129332304
2023-01-24 10:44:54.143870: step: 780/530, loss: 0.001796990865841508
2023-01-24 10:44:55.247357: step: 784/530, loss: 0.0007893404690548778
2023-01-24 10:44:56.345689: step: 788/530, loss: 0.00015968702791724354
2023-01-24 10:44:57.421487: step: 792/530, loss: 0.00026670395163819194
2023-01-24 10:44:58.536640: step: 796/530, loss: 3.1496165320277214e-05
2023-01-24 10:44:59.604264: step: 800/530, loss: 0.002667137887328863
2023-01-24 10:45:00.685662: step: 804/530, loss: 0.00022116818581707776
2023-01-24 10:45:01.775624: step: 808/530, loss: 0.0009400615817867219
2023-01-24 10:45:02.856208: step: 812/530, loss: 0.002219259273260832
2023-01-24 10:45:03.949910: step: 816/530, loss: 0.007406312972307205
2023-01-24 10:45:05.035821: step: 820/530, loss: 0.0002881985856220126
2023-01-24 10:45:06.118807: step: 824/530, loss: 0.0003620398638304323
2023-01-24 10:45:07.202597: step: 828/530, loss: 0.0003469117218628526
2023-01-24 10:45:08.307827: step: 832/530, loss: 0.0004634088254533708
2023-01-24 10:45:09.412657: step: 836/530, loss: 0.0006332676275633276
2023-01-24 10:45:10.488511: step: 840/530, loss: 0.0031147710978984833
2023-01-24 10:45:11.571769: step: 844/530, loss: 0.0006185956299304962
2023-01-24 10:45:12.656588: step: 848/530, loss: 0.0004379435849841684
2023-01-24 10:45:13.744661: step: 852/530, loss: 1.5504343537031673e-05
2023-01-24 10:45:14.825261: step: 856/530, loss: 0.00041991108446381986
2023-01-24 10:45:15.912895: step: 860/530, loss: 0.0004991637542843819
2023-01-24 10:45:17.022562: step: 864/530, loss: 0.006516980938613415
2023-01-24 10:45:18.098989: step: 868/530, loss: 0.0015845214948058128
2023-01-24 10:45:19.167187: step: 872/530, loss: 3.6916717363055795e-05
2023-01-24 10:45:20.262933: step: 876/530, loss: 0.001291735447011888
2023-01-24 10:45:21.362455: step: 880/530, loss: 0.0018934139516204596
2023-01-24 10:45:22.461186: step: 884/530, loss: 0.0011029306333512068
2023-01-24 10:45:23.573423: step: 888/530, loss: 0.00016446737572550774
2023-01-24 10:45:24.685312: step: 892/530, loss: 0.0022822474129498005
2023-01-24 10:45:25.783830: step: 896/530, loss: 0.0025672889314591885
2023-01-24 10:45:26.891556: step: 900/530, loss: 0.0005073066568002105
2023-01-24 10:45:27.980507: step: 904/530, loss: 0.002016980666667223
2023-01-24 10:45:29.053625: step: 908/530, loss: 0.0032625554595142603
2023-01-24 10:45:30.131282: step: 912/530, loss: 0.0012266021221876144
2023-01-24 10:45:31.220028: step: 916/530, loss: 0.010914864018559456
2023-01-24 10:45:32.311345: step: 920/530, loss: 0.005537052173167467
2023-01-24 10:45:33.429610: step: 924/530, loss: 0.0038829047698527575
2023-01-24 10:45:34.519823: step: 928/530, loss: 0.0007737540872767568
2023-01-24 10:45:35.605615: step: 932/530, loss: 0.0021450240164995193
2023-01-24 10:45:36.716186: step: 936/530, loss: 0.010253152810037136
2023-01-24 10:45:37.813039: step: 940/530, loss: 0.0017688992666080594
2023-01-24 10:45:38.896226: step: 944/530, loss: 0.00901026651263237
2023-01-24 10:45:39.984082: step: 948/530, loss: 0.001152405864559114
2023-01-24 10:45:41.085287: step: 952/530, loss: 0.0035532780457288027
2023-01-24 10:45:42.179975: step: 956/530, loss: 0.006383465602993965
2023-01-24 10:45:43.275368: step: 960/530, loss: 0.0009306279825977981
2023-01-24 10:45:44.340581: step: 964/530, loss: 0.00040455852285958827
2023-01-24 10:45:45.428803: step: 968/530, loss: 0.00017179954738821834
2023-01-24 10:45:46.524255: step: 972/530, loss: 0.0007859966717660427
2023-01-24 10:45:47.620835: step: 976/530, loss: 2.7183359634364024e-05
2023-01-24 10:45:48.705978: step: 980/530, loss: 8.094224540400319e-06
2023-01-24 10:45:49.791539: step: 984/530, loss: 0.007210175506770611
2023-01-24 10:45:50.875329: step: 988/530, loss: 0.0008191528613679111
2023-01-24 10:45:51.961050: step: 992/530, loss: 0.003515303134918213
2023-01-24 10:45:53.069531: step: 996/530, loss: 0.0017188818892464042
2023-01-24 10:45:54.182519: step: 1000/530, loss: 0.0029762466438114643
2023-01-24 10:45:55.281942: step: 1004/530, loss: 5.2656214393209666e-05
2023-01-24 10:45:56.374566: step: 1008/530, loss: 0.0002444193232804537
2023-01-24 10:45:57.470208: step: 1012/530, loss: 0.009162704460322857
2023-01-24 10:45:58.562675: step: 1016/530, loss: 0.005453592631965876
2023-01-24 10:45:59.656992: step: 1020/530, loss: 0.0015048424247652292
2023-01-24 10:46:00.733846: step: 1024/530, loss: 0.005734096746891737
2023-01-24 10:46:01.812348: step: 1028/530, loss: 0.017995981499552727
2023-01-24 10:46:02.894344: step: 1032/530, loss: 0.004703155253082514
2023-01-24 10:46:03.970882: step: 1036/530, loss: 0.005158161278814077
2023-01-24 10:46:05.072364: step: 1040/530, loss: 0.00500600878149271
2023-01-24 10:46:06.172772: step: 1044/530, loss: 0.0024152242112904787
2023-01-24 10:46:07.244517: step: 1048/530, loss: 0.01518117357045412
2023-01-24 10:46:08.332357: step: 1052/530, loss: 0.007749086711555719
2023-01-24 10:46:09.434397: step: 1056/530, loss: 0.0002087807224597782
2023-01-24 10:46:10.547188: step: 1060/530, loss: 0.00011596120020840317
2023-01-24 10:46:11.636001: step: 1064/530, loss: 0.014991536736488342
2023-01-24 10:46:12.739731: step: 1068/530, loss: 0.0021489278879016638
2023-01-24 10:46:13.813978: step: 1072/530, loss: 0.0007681234274059534
2023-01-24 10:46:14.887716: step: 1076/530, loss: 0.0020727748051285744
2023-01-24 10:46:15.970932: step: 1080/530, loss: 0.0010961415246129036
2023-01-24 10:46:17.052391: step: 1084/530, loss: 7.461431778210681e-06
2023-01-24 10:46:18.143240: step: 1088/530, loss: 0.00016314793901983649
2023-01-24 10:46:19.244098: step: 1092/530, loss: 0.007404114585369825
2023-01-24 10:46:20.327408: step: 1096/530, loss: 0.004782171454280615
2023-01-24 10:46:21.436993: step: 1100/530, loss: 1.4867505342408549e-05
2023-01-24 10:46:22.537007: step: 1104/530, loss: 0.0091378940269351
2023-01-24 10:46:23.639935: step: 1108/530, loss: 0.016494134441018105
2023-01-24 10:46:24.752959: step: 1112/530, loss: 0.006772821303457022
2023-01-24 10:46:25.845612: step: 1116/530, loss: 0.0002630894596222788
2023-01-24 10:46:26.922378: step: 1120/530, loss: 0.0004232735082041472
2023-01-24 10:46:28.017769: step: 1124/530, loss: 0.0010103174718096852
2023-01-24 10:46:29.091907: step: 1128/530, loss: 0.002713279565796256
2023-01-24 10:46:30.182757: step: 1132/530, loss: 0.006466195452958345
2023-01-24 10:46:31.286399: step: 1136/530, loss: 0.0029782913625240326
2023-01-24 10:46:32.362623: step: 1140/530, loss: 0.00022127982811070979
2023-01-24 10:46:33.456533: step: 1144/530, loss: 0.009942966513335705
2023-01-24 10:46:34.534899: step: 1148/530, loss: 0.012226640246808529
2023-01-24 10:46:35.635703: step: 1152/530, loss: 0.0041862293146550655
2023-01-24 10:46:36.714948: step: 1156/530, loss: 0.018717629835009575
2023-01-24 10:46:37.802075: step: 1160/530, loss: 0.001450053765438497
2023-01-24 10:46:38.886615: step: 1164/530, loss: 0.0034925302024930716
2023-01-24 10:46:39.974833: step: 1168/530, loss: 0.003703951369971037
2023-01-24 10:46:41.087710: step: 1172/530, loss: 0.0004603114794008434
2023-01-24 10:46:42.168613: step: 1176/530, loss: 5.0427173846401274e-05
2023-01-24 10:46:43.248774: step: 1180/530, loss: 0.003371449885889888
2023-01-24 10:46:44.342884: step: 1184/530, loss: 0.0032470007427036762
2023-01-24 10:46:45.455781: step: 1188/530, loss: 0.0021416267845779657
2023-01-24 10:46:46.524146: step: 1192/530, loss: 0.0005429533775895834
2023-01-24 10:46:47.607791: step: 1196/530, loss: 0.00465348968282342
2023-01-24 10:46:48.707407: step: 1200/530, loss: 0.001009253435768187
2023-01-24 10:46:49.812358: step: 1204/530, loss: 0.030110033228993416
2023-01-24 10:46:50.897631: step: 1208/530, loss: 0.00037223813706077635
2023-01-24 10:46:51.969073: step: 1212/530, loss: 0.0025553249288350344
2023-01-24 10:46:53.065384: step: 1216/530, loss: 0.006032499950379133
2023-01-24 10:46:54.155467: step: 1220/530, loss: 4.047404581797309e-05
2023-01-24 10:46:55.253731: step: 1224/530, loss: 0.000852379307616502
2023-01-24 10:46:56.349353: step: 1228/530, loss: 7.200497930170968e-05
2023-01-24 10:46:57.461175: step: 1232/530, loss: 0.0014304049545899034
2023-01-24 10:46:58.543927: step: 1236/530, loss: 0.004008917603641748
2023-01-24 10:46:59.629906: step: 1240/530, loss: 0.007127148099243641
2023-01-24 10:47:00.729296: step: 1244/530, loss: 0.01821468025445938
2023-01-24 10:47:01.802690: step: 1248/530, loss: 1.0921195098489989e-05
2023-01-24 10:47:02.882304: step: 1252/530, loss: 0.028740478679537773
2023-01-24 10:47:03.975028: step: 1256/530, loss: 1.7588701666682027e-05
2023-01-24 10:47:05.065418: step: 1260/530, loss: 0.002110525267198682
2023-01-24 10:47:06.157682: step: 1264/530, loss: 0.001676070154644549
2023-01-24 10:47:07.258528: step: 1268/530, loss: 0.004911639727652073
2023-01-24 10:47:08.345956: step: 1272/530, loss: 0.001979612745344639
2023-01-24 10:47:09.425670: step: 1276/530, loss: 0.000550492259208113
2023-01-24 10:47:10.536079: step: 1280/530, loss: 0.004401945509016514
2023-01-24 10:47:11.620211: step: 1284/530, loss: 0.004540633875876665
2023-01-24 10:47:12.722565: step: 1288/530, loss: 0.0009680314688012004
2023-01-24 10:47:13.805368: step: 1292/530, loss: 0.003358195535838604
2023-01-24 10:47:14.870113: step: 1296/530, loss: 0.00045573891839012504
2023-01-24 10:47:15.987978: step: 1300/530, loss: 0.0012548742815852165
2023-01-24 10:47:17.074706: step: 1304/530, loss: 0.010721873492002487
2023-01-24 10:47:18.141920: step: 1308/530, loss: 0.00015493064711336046
2023-01-24 10:47:19.234651: step: 1312/530, loss: 0.0010917402105405927
2023-01-24 10:47:20.328353: step: 1316/530, loss: 0.0031570803839713335
2023-01-24 10:47:21.430697: step: 1320/530, loss: 0.008043994195759296
2023-01-24 10:47:22.512282: step: 1324/530, loss: 0.0012500904267653823
2023-01-24 10:47:23.592469: step: 1328/530, loss: 0.018676310777664185
2023-01-24 10:47:24.680353: step: 1332/530, loss: 4.9612197472015396e-05
2023-01-24 10:47:25.749613: step: 1336/530, loss: 0.006168786436319351
2023-01-24 10:47:26.837579: step: 1340/530, loss: 0.0004904735833406448
2023-01-24 10:47:27.925599: step: 1344/530, loss: 0.012654002755880356
2023-01-24 10:47:29.013952: step: 1348/530, loss: 0.0017332867719233036
2023-01-24 10:47:30.104512: step: 1352/530, loss: 0.005420266184955835
2023-01-24 10:47:31.189722: step: 1356/530, loss: 0.002804506104439497
2023-01-24 10:47:32.271319: step: 1360/530, loss: 0.005558534525334835
2023-01-24 10:47:33.382617: step: 1364/530, loss: 0.0014608752680942416
2023-01-24 10:47:34.464364: step: 1368/530, loss: 0.0015148414531722665
2023-01-24 10:47:35.553138: step: 1372/530, loss: 0.010762615129351616
2023-01-24 10:47:36.652285: step: 1376/530, loss: 0.002828380558639765
2023-01-24 10:47:37.748643: step: 1380/530, loss: 0.0029202981386333704
2023-01-24 10:47:38.823182: step: 1384/530, loss: 0.00023294426500797272
2023-01-24 10:47:39.926067: step: 1388/530, loss: 8.773962326813489e-05
2023-01-24 10:47:41.018662: step: 1392/530, loss: 0.003974469378590584
2023-01-24 10:47:42.111463: step: 1396/530, loss: 0.0005275339353829622
2023-01-24 10:47:43.202376: step: 1400/530, loss: 0.027599824592471123
2023-01-24 10:47:44.287374: step: 1404/530, loss: 0.0002456007932778448
2023-01-24 10:47:45.377225: step: 1408/530, loss: 0.00014337974425870925
2023-01-24 10:47:46.458370: step: 1412/530, loss: 0.0002336033940082416
2023-01-24 10:47:47.537843: step: 1416/530, loss: 3.7831738154636696e-05
2023-01-24 10:47:48.669273: step: 1420/530, loss: 0.005172450095415115
2023-01-24 10:47:49.752646: step: 1424/530, loss: 0.0027136385906487703
2023-01-24 10:47:50.858507: step: 1428/530, loss: 0.002548440359532833
2023-01-24 10:47:51.960459: step: 1432/530, loss: 0.04339786246418953
2023-01-24 10:47:53.043681: step: 1436/530, loss: 0.008410529233515263
2023-01-24 10:47:54.116923: step: 1440/530, loss: 0.008311120793223381
2023-01-24 10:47:55.208454: step: 1444/530, loss: 0.005648605991154909
2023-01-24 10:47:56.293641: step: 1448/530, loss: 0.00011642611934803426
2023-01-24 10:47:57.414413: step: 1452/530, loss: 0.0015221787616610527
2023-01-24 10:47:58.512298: step: 1456/530, loss: 0.002900173654779792
2023-01-24 10:47:59.618579: step: 1460/530, loss: 0.006394024472683668
2023-01-24 10:48:00.720085: step: 1464/530, loss: 0.0012230782303959131
2023-01-24 10:48:01.789219: step: 1468/530, loss: 0.001762936357408762
2023-01-24 10:48:02.876550: step: 1472/530, loss: 8.360754577552143e-07
2023-01-24 10:48:03.971196: step: 1476/530, loss: 0.002977677620947361
2023-01-24 10:48:05.052585: step: 1480/530, loss: 0.0016329261707141995
2023-01-24 10:48:06.138121: step: 1484/530, loss: 0.00017170999490190297
2023-01-24 10:48:07.220593: step: 1488/530, loss: 0.0024347316939383745
2023-01-24 10:48:08.284121: step: 1492/530, loss: 6.549506360897794e-05
2023-01-24 10:48:09.385909: step: 1496/530, loss: 0.0002729482657741755
2023-01-24 10:48:10.472407: step: 1500/530, loss: 0.012052626349031925
2023-01-24 10:48:11.561968: step: 1504/530, loss: 0.014203791506588459
2023-01-24 10:48:12.640050: step: 1508/530, loss: 0.0004855323350057006
2023-01-24 10:48:13.739139: step: 1512/530, loss: 8.177094423444942e-05
2023-01-24 10:48:14.831184: step: 1516/530, loss: 0.007196275983005762
2023-01-24 10:48:15.931605: step: 1520/530, loss: 0.0009334517526440322
2023-01-24 10:48:17.020596: step: 1524/530, loss: 0.0005425841081887484
2023-01-24 10:48:18.082721: step: 1528/530, loss: 0.0008515716763213277
2023-01-24 10:48:19.167475: step: 1532/530, loss: 0.0029152731876820326
2023-01-24 10:48:20.240350: step: 1536/530, loss: 0.0028622474055737257
2023-01-24 10:48:21.343658: step: 1540/530, loss: 0.0027356904465705156
2023-01-24 10:48:22.439849: step: 1544/530, loss: 0.0036398330703377724
2023-01-24 10:48:23.530254: step: 1548/530, loss: 0.00200962508097291
2023-01-24 10:48:24.615191: step: 1552/530, loss: 0.00031526293605566025
2023-01-24 10:48:25.713535: step: 1556/530, loss: 0.0007602398400194943
2023-01-24 10:48:26.804469: step: 1560/530, loss: 0.009113945998251438
2023-01-24 10:48:27.898086: step: 1564/530, loss: 0.004607424605637789
2023-01-24 10:48:28.993340: step: 1568/530, loss: 9.279806545237079e-05
2023-01-24 10:48:30.064231: step: 1572/530, loss: 0.0029641669243574142
2023-01-24 10:48:31.177424: step: 1576/530, loss: 0.00010851237311726436
2023-01-24 10:48:32.275823: step: 1580/530, loss: 0.003018486313521862
2023-01-24 10:48:33.349046: step: 1584/530, loss: 0.0002792272134684026
2023-01-24 10:48:34.473978: step: 1588/530, loss: 0.00010053430742118508
2023-01-24 10:48:35.567521: step: 1592/530, loss: 0.0003937681613024324
2023-01-24 10:48:36.650188: step: 1596/530, loss: 0.010704144835472107
2023-01-24 10:48:37.733120: step: 1600/530, loss: 5.881514880456962e-05
2023-01-24 10:48:38.837677: step: 1604/530, loss: 0.005205592606216669
2023-01-24 10:48:39.939676: step: 1608/530, loss: 0.0027847348246723413
2023-01-24 10:48:41.044244: step: 1612/530, loss: 0.00018132803961634636
2023-01-24 10:48:42.138065: step: 1616/530, loss: 0.009442429058253765
2023-01-24 10:48:43.221620: step: 1620/530, loss: 0.02821452170610428
2023-01-24 10:48:44.310875: step: 1624/530, loss: 0.00038336883881129324
2023-01-24 10:48:45.403226: step: 1628/530, loss: 1.556850111228414e-05
2023-01-24 10:48:46.488210: step: 1632/530, loss: 0.00011915427603526041
2023-01-24 10:48:47.597431: step: 1636/530, loss: 0.0033786995336413383
2023-01-24 10:48:48.678268: step: 1640/530, loss: 9.686307021183893e-05
2023-01-24 10:48:49.754727: step: 1644/530, loss: 0.0009107019286602736
2023-01-24 10:48:50.872265: step: 1648/530, loss: 0.010780328884720802
2023-01-24 10:48:51.971421: step: 1652/530, loss: 1.4698194718221202e-05
2023-01-24 10:48:53.071434: step: 1656/530, loss: 0.007394067943096161
2023-01-24 10:48:54.179029: step: 1660/530, loss: 0.0023417857009917498
2023-01-24 10:48:55.276208: step: 1664/530, loss: 0.004217495210468769
2023-01-24 10:48:56.366060: step: 1668/530, loss: 0.00412709079682827
2023-01-24 10:48:57.445176: step: 1672/530, loss: 0.0012540417956188321
2023-01-24 10:48:58.523001: step: 1676/530, loss: 0.0008241914911195636
2023-01-24 10:48:59.598395: step: 1680/530, loss: 0.0010481151985004544
2023-01-24 10:49:00.684938: step: 1684/530, loss: 0.0022604179102927446
2023-01-24 10:49:01.781319: step: 1688/530, loss: 0.0007706551696173847
2023-01-24 10:49:02.872401: step: 1692/530, loss: 0.001371414284221828
2023-01-24 10:49:03.993045: step: 1696/530, loss: 0.00046042041503824294
2023-01-24 10:49:05.070894: step: 1700/530, loss: 0.005168757401406765
2023-01-24 10:49:06.159715: step: 1704/530, loss: 4.6169079723767936e-05
2023-01-24 10:49:07.243237: step: 1708/530, loss: 0.0008091203635558486
2023-01-24 10:49:08.313150: step: 1712/530, loss: 0.001225824817083776
2023-01-24 10:49:09.412924: step: 1716/530, loss: 0.002943438710644841
2023-01-24 10:49:10.499721: step: 1720/530, loss: 0.0019306633621454239
2023-01-24 10:49:11.577626: step: 1724/530, loss: 0.0006289273151196539
2023-01-24 10:49:12.674201: step: 1728/530, loss: 0.0004547074204310775
2023-01-24 10:49:13.761871: step: 1732/530, loss: 0.003432940226048231
2023-01-24 10:49:14.840016: step: 1736/530, loss: 0.011345287784934044
2023-01-24 10:49:15.935553: step: 1740/530, loss: 0.0021766044665127993
2023-01-24 10:49:17.019694: step: 1744/530, loss: 0.0003303492267150432
2023-01-24 10:49:18.120524: step: 1748/530, loss: 0.00245128502137959
2023-01-24 10:49:19.216582: step: 1752/530, loss: 0.00047326594358310103
2023-01-24 10:49:20.312388: step: 1756/530, loss: 0.00010543585813138634
2023-01-24 10:49:21.391578: step: 1760/530, loss: 0.00010827576625160873
2023-01-24 10:49:22.478757: step: 1764/530, loss: 0.0006188526167534292
2023-01-24 10:49:23.559695: step: 1768/530, loss: 0.003043142845854163
2023-01-24 10:49:24.649896: step: 1772/530, loss: 0.0006010145880281925
2023-01-24 10:49:25.771667: step: 1776/530, loss: 0.006816300563514233
2023-01-24 10:49:26.854623: step: 1780/530, loss: 0.0022533806040883064
2023-01-24 10:49:27.942330: step: 1784/530, loss: 0.0029185237362980843
2023-01-24 10:49:29.020951: step: 1788/530, loss: 0.0009701751987449825
2023-01-24 10:49:30.105428: step: 1792/530, loss: 2.095879153785063e-06
2023-01-24 10:49:31.201523: step: 1796/530, loss: 0.0026495042257010937
2023-01-24 10:49:32.296122: step: 1800/530, loss: 0.001783812534995377
2023-01-24 10:49:33.377821: step: 1804/530, loss: 0.004000787157565355
2023-01-24 10:49:34.474516: step: 1808/530, loss: 0.02174878492951393
2023-01-24 10:49:35.542840: step: 1812/530, loss: 2.2332524167723022e-05
2023-01-24 10:49:36.645078: step: 1816/530, loss: 0.011863541789352894
2023-01-24 10:49:37.739728: step: 1820/530, loss: 0.005531518720090389
2023-01-24 10:49:38.825436: step: 1824/530, loss: 0.0023476574569940567
2023-01-24 10:49:39.938820: step: 1828/530, loss: 0.0008948675240390003
2023-01-24 10:49:41.027480: step: 1832/530, loss: 0.0019338495330885053
2023-01-24 10:49:42.096057: step: 1836/530, loss: 5.583491201832658e-06
2023-01-24 10:49:43.179270: step: 1840/530, loss: 0.00016705291636753827
2023-01-24 10:49:44.281548: step: 1844/530, loss: 0.0006547645898535848
2023-01-24 10:49:45.373791: step: 1848/530, loss: 7.919600466266274e-05
2023-01-24 10:49:46.468998: step: 1852/530, loss: 0.002055986085906625
2023-01-24 10:49:47.618600: step: 1856/530, loss: 0.0033276185858994722
2023-01-24 10:49:48.708476: step: 1860/530, loss: 9.616312308935449e-05
2023-01-24 10:49:49.811483: step: 1864/530, loss: 0.00048755662282928824
2023-01-24 10:49:50.892937: step: 1868/530, loss: 0.005983664188534021
2023-01-24 10:49:51.997425: step: 1872/530, loss: 0.002054516924545169
2023-01-24 10:49:53.107818: step: 1876/530, loss: 0.0007921885699033737
2023-01-24 10:49:54.191822: step: 1880/530, loss: 0.0007027360261417925
2023-01-24 10:49:55.278776: step: 1884/530, loss: 0.0013822525506839156
2023-01-24 10:49:56.387544: step: 1888/530, loss: 0.0022649893071502447
2023-01-24 10:49:57.471905: step: 1892/530, loss: 0.0004750127554871142
2023-01-24 10:49:58.554378: step: 1896/530, loss: 7.53599942981964e-06
2023-01-24 10:49:59.631289: step: 1900/530, loss: 0.0015178367029875517
2023-01-24 10:50:00.743781: step: 1904/530, loss: 0.00015136870206333697
2023-01-24 10:50:01.814495: step: 1908/530, loss: 4.3332940549589694e-05
2023-01-24 10:50:02.894165: step: 1912/530, loss: 7.711160492362978e-07
2023-01-24 10:50:03.964539: step: 1916/530, loss: 0.004623178858309984
2023-01-24 10:50:05.034043: step: 1920/530, loss: 1.5363431884907186e-05
2023-01-24 10:50:06.122375: step: 1924/530, loss: 0.0028751862701028585
2023-01-24 10:50:07.196722: step: 1928/530, loss: 0.00360312731936574
2023-01-24 10:50:08.297969: step: 1932/530, loss: 0.004539411514997482
2023-01-24 10:50:09.404033: step: 1936/530, loss: 0.0032826552633196115
2023-01-24 10:50:10.482137: step: 1940/530, loss: 0.0031021826434880495
2023-01-24 10:50:11.574594: step: 1944/530, loss: 0.003293985966593027
2023-01-24 10:50:12.664691: step: 1948/530, loss: 0.00023466760467272252
2023-01-24 10:50:13.767184: step: 1952/530, loss: 0.010962816886603832
2023-01-24 10:50:14.876616: step: 1956/530, loss: 0.003906755708158016
2023-01-24 10:50:15.955103: step: 1960/530, loss: 0.001585396472364664
2023-01-24 10:50:17.051028: step: 1964/530, loss: 0.0004932558513246477
2023-01-24 10:50:18.156767: step: 1968/530, loss: 0.00801409874111414
2023-01-24 10:50:19.248155: step: 1972/530, loss: 0.002754591405391693
2023-01-24 10:50:20.336879: step: 1976/530, loss: 0.003606868674978614
2023-01-24 10:50:21.452772: step: 1980/530, loss: 0.009220970794558525
2023-01-24 10:50:22.533099: step: 1984/530, loss: 0.0032213402446359396
2023-01-24 10:50:23.618659: step: 1988/530, loss: 0.0016332759987562895
2023-01-24 10:50:24.738513: step: 1992/530, loss: 0.0024386129807680845
2023-01-24 10:50:25.811996: step: 1996/530, loss: 0.006423316430300474
2023-01-24 10:50:26.904731: step: 2000/530, loss: 0.0009003261802718043
2023-01-24 10:50:27.982533: step: 2004/530, loss: 0.0006505006458610296
2023-01-24 10:50:29.083157: step: 2008/530, loss: 0.00021246673713903874
2023-01-24 10:50:30.177283: step: 2012/530, loss: 4.256839474692242e-06
2023-01-24 10:50:31.260396: step: 2016/530, loss: 0.0021003950387239456
2023-01-24 10:50:32.342596: step: 2020/530, loss: 0.011076259426772594
2023-01-24 10:50:33.419171: step: 2024/530, loss: 0.001986247021704912
2023-01-24 10:50:34.488929: step: 2028/530, loss: 2.125672608599416e-06
2023-01-24 10:50:35.579167: step: 2032/530, loss: 0.005149484146386385
2023-01-24 10:50:36.664926: step: 2036/530, loss: 0.004954056814312935
2023-01-24 10:50:37.743248: step: 2040/530, loss: 0.00020679004956036806
2023-01-24 10:50:38.814307: step: 2044/530, loss: 0.0014698265586048365
2023-01-24 10:50:39.897186: step: 2048/530, loss: 0.005000512581318617
2023-01-24 10:50:40.990291: step: 2052/530, loss: 0.002040943130850792
2023-01-24 10:50:42.094062: step: 2056/530, loss: 1.192059789900668e-05
2023-01-24 10:50:43.196441: step: 2060/530, loss: 0.0046931067481637
2023-01-24 10:50:44.276691: step: 2064/530, loss: 5.736005550716072e-05
2023-01-24 10:50:45.371441: step: 2068/530, loss: 0.005970245227217674
2023-01-24 10:50:46.465611: step: 2072/530, loss: 3.0284812964964658e-05
2023-01-24 10:50:47.554691: step: 2076/530, loss: 0.0031871541868895292
2023-01-24 10:50:48.644267: step: 2080/530, loss: 2.6468411306268536e-05
2023-01-24 10:50:49.749923: step: 2084/530, loss: 0.0038185175508260727
2023-01-24 10:50:50.835329: step: 2088/530, loss: 0.0015276194317266345
2023-01-24 10:50:51.930062: step: 2092/530, loss: 0.0023720518220216036
2023-01-24 10:50:53.036369: step: 2096/530, loss: 0.0031994623132050037
2023-01-24 10:50:54.123596: step: 2100/530, loss: 0.0008301698253490031
2023-01-24 10:50:55.231925: step: 2104/530, loss: 0.0036158226430416107
2023-01-24 10:50:56.305066: step: 2108/530, loss: 0.0019475846784189343
2023-01-24 10:50:57.395477: step: 2112/530, loss: 0.004567019175738096
2023-01-24 10:50:58.501536: step: 2116/530, loss: 3.7252898543727042e-09
2023-01-24 10:50:59.586395: step: 2120/530, loss: 0.009466171264648438
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3478487529034685, 'r': 0.34388842554593374, 'f1': 0.34585725240974635}, 'combined': 0.2548421859861289, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33936709321815167, 'r': 0.2742462068835113, 'f1': 0.30335111067749443}, 'combined': 0.18839700557865444, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3888455709113895, 'r': 0.33350701717637204, 'f1': 0.3590565843757877}, 'combined': 0.26456800954005405, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3332648084672905, 'r': 0.26246250232058355, 'f1': 0.293656221501858}, 'combined': 0.18237596914325918, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3808682509253266, 'r': 0.32738769956199804, 'f1': 0.3521088115697407}, 'combined': 0.2594485979987563, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34856275057139785, 'r': 0.2724438099821894, 'f1': 0.30583819822737185}, 'combined': 0.18994161784647307, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.38, 'r': 0.41304347826086957, 'f1': 0.39583333333333337}, 'combined': 0.19791666666666669, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 10:53:26.462287: step: 4/530, loss: 0.001717277686111629
2023-01-24 10:53:27.534150: step: 8/530, loss: 0.0006986533990129828
2023-01-24 10:53:28.608048: step: 12/530, loss: 0.0038119065575301647
2023-01-24 10:53:29.710309: step: 16/530, loss: 0.0023736669681966305
2023-01-24 10:53:30.800596: step: 20/530, loss: 0.001824354287236929
2023-01-24 10:53:31.889469: step: 24/530, loss: 0.0007617135415785015
2023-01-24 10:53:32.983530: step: 28/530, loss: 0.005846124608069658
2023-01-24 10:53:34.065578: step: 32/530, loss: 0.006003752816468477
2023-01-24 10:53:35.135888: step: 36/530, loss: 0.0019311968935653567
2023-01-24 10:53:36.210548: step: 40/530, loss: 0.004382942337542772
2023-01-24 10:53:37.327174: step: 44/530, loss: 0.02645988017320633
2023-01-24 10:53:38.389623: step: 48/530, loss: 0.0002333256124984473
2023-01-24 10:53:39.472847: step: 52/530, loss: 0.003416206454858184
2023-01-24 10:53:40.531762: step: 56/530, loss: 0.002360232174396515
2023-01-24 10:53:41.612452: step: 60/530, loss: 7.052139699226245e-05
2023-01-24 10:53:42.686172: step: 64/530, loss: 0.006199215538799763
2023-01-24 10:53:43.799199: step: 68/530, loss: 0.004202813375741243
2023-01-24 10:53:44.882098: step: 72/530, loss: 0.00518175819888711
2023-01-24 10:53:45.965657: step: 76/530, loss: 0.00010874445433728397
2023-01-24 10:53:47.034022: step: 80/530, loss: 4.146892752032727e-05
2023-01-24 10:53:48.146235: step: 84/530, loss: 0.014703149907290936
2023-01-24 10:53:49.214184: step: 88/530, loss: 8.461222023470327e-06
2023-01-24 10:53:50.304693: step: 92/530, loss: 0.004158864729106426
2023-01-24 10:53:51.383818: step: 96/530, loss: 0.0002442148106638342
2023-01-24 10:53:52.459310: step: 100/530, loss: 0.0004288915079087019
2023-01-24 10:53:53.572142: step: 104/530, loss: 0.00298251211643219
2023-01-24 10:53:54.687250: step: 108/530, loss: 0.01544266752898693
2023-01-24 10:53:55.773545: step: 112/530, loss: 0.0002007533039432019
2023-01-24 10:53:56.868719: step: 116/530, loss: 0.000407932122470811
2023-01-24 10:53:57.954218: step: 120/530, loss: 0.00021574630227405578
2023-01-24 10:53:59.038818: step: 124/530, loss: 0.005891435779631138
2023-01-24 10:54:00.142602: step: 128/530, loss: 0.0028573423624038696
2023-01-24 10:54:01.226060: step: 132/530, loss: 0.0019811580423265696
2023-01-24 10:54:02.313187: step: 136/530, loss: 0.0011197433341294527
2023-01-24 10:54:03.393046: step: 140/530, loss: 0.005254335701465607
2023-01-24 10:54:04.467070: step: 144/530, loss: 0.0018295374466106296
2023-01-24 10:54:05.551308: step: 148/530, loss: 0.0001792960101738572
2023-01-24 10:54:06.646686: step: 152/530, loss: 0.004178212024271488
2023-01-24 10:54:07.735425: step: 156/530, loss: 0.02185814082622528
2023-01-24 10:54:08.824250: step: 160/530, loss: 0.005147851537913084
2023-01-24 10:54:09.908984: step: 164/530, loss: 0.0003381682909093797
2023-01-24 10:54:10.995162: step: 168/530, loss: 0.005957733374089003
2023-01-24 10:54:12.081352: step: 172/530, loss: 0.00031117681646719575
2023-01-24 10:54:13.157540: step: 176/530, loss: 9.963851880456787e-06
2023-01-24 10:54:14.268637: step: 180/530, loss: 0.011955692432820797
2023-01-24 10:54:15.357764: step: 184/530, loss: 0.0002807419514283538
2023-01-24 10:54:16.410550: step: 188/530, loss: 0.0031959018670022488
2023-01-24 10:54:17.489645: step: 192/530, loss: 0.006584660150110722
2023-01-24 10:54:18.566703: step: 196/530, loss: 0.000583402463234961
2023-01-24 10:54:19.688671: step: 200/530, loss: 0.0044104475528001785
2023-01-24 10:54:20.796717: step: 204/530, loss: 0.0019759235437959433
2023-01-24 10:54:21.889003: step: 208/530, loss: 5.7586716138757765e-05
2023-01-24 10:54:22.983966: step: 212/530, loss: 7.456469029420987e-05
2023-01-24 10:54:24.096229: step: 216/530, loss: 0.004510125610977411
2023-01-24 10:54:25.164083: step: 220/530, loss: 1.1955972695432138e-05
2023-01-24 10:54:26.261199: step: 224/530, loss: 4.097818528947528e-09
2023-01-24 10:54:27.373035: step: 228/530, loss: 0.00011046500731026754
2023-01-24 10:54:28.443718: step: 232/530, loss: 0.0054216464050114155
2023-01-24 10:54:29.542785: step: 236/530, loss: 0.005629874300211668
2023-01-24 10:54:30.614546: step: 240/530, loss: 0.0001685080205788836
2023-01-24 10:54:31.715639: step: 244/530, loss: 0.0012813311768695712
2023-01-24 10:54:32.790551: step: 248/530, loss: 0.0017779003828763962
2023-01-24 10:54:33.899650: step: 252/530, loss: 1.4218800970411394e-05
2023-01-24 10:54:34.989998: step: 256/530, loss: 0.00031449217931367457
2023-01-24 10:54:36.071526: step: 260/530, loss: 0.000883161264937371
2023-01-24 10:54:37.144481: step: 264/530, loss: 0.004566379357129335
2023-01-24 10:54:38.265445: step: 268/530, loss: 0.00648776488378644
2023-01-24 10:54:39.334673: step: 272/530, loss: 0.00039646675577387214
2023-01-24 10:54:40.418115: step: 276/530, loss: 0.00014451795141212642
2023-01-24 10:54:41.529027: step: 280/530, loss: 0.0019416098948568106
2023-01-24 10:54:42.608891: step: 284/530, loss: 0.0011632838286459446
2023-01-24 10:54:43.708973: step: 288/530, loss: 0.0007095273467712104
2023-01-24 10:54:44.796300: step: 292/530, loss: 0.0007614679052494466
2023-01-24 10:54:45.880665: step: 296/530, loss: 0.0002598889986984432
2023-01-24 10:54:46.980822: step: 300/530, loss: 0.0002933721407316625
2023-01-24 10:54:48.060035: step: 304/530, loss: 0.002365187043324113
2023-01-24 10:54:49.180989: step: 308/530, loss: 0.00019210478058084846
2023-01-24 10:54:50.272567: step: 312/530, loss: 0.011270344257354736
2023-01-24 10:54:51.359795: step: 316/530, loss: 0.00019919799524359405
2023-01-24 10:54:52.427144: step: 320/530, loss: 0.001244648010469973
2023-01-24 10:54:53.535113: step: 324/530, loss: 0.00011213490506634116
2023-01-24 10:54:54.623887: step: 328/530, loss: 0.0009468088974244893
2023-01-24 10:54:55.702732: step: 332/530, loss: 2.9115508368704468e-05
2023-01-24 10:54:56.793846: step: 336/530, loss: 0.0029539279639720917
2023-01-24 10:54:57.898439: step: 340/530, loss: 0.0009108154918067157
2023-01-24 10:54:58.984319: step: 344/530, loss: 0.00022972917940933257
2023-01-24 10:55:00.075383: step: 348/530, loss: 2.0186087567708455e-05
2023-01-24 10:55:01.162519: step: 352/530, loss: 0.00953727774322033
2023-01-24 10:55:02.247625: step: 356/530, loss: 0.0020959770772606134
2023-01-24 10:55:03.316450: step: 360/530, loss: 0.001370947458781302
2023-01-24 10:55:04.410145: step: 364/530, loss: 7.094330794643611e-05
2023-01-24 10:55:05.512668: step: 368/530, loss: 0.005751086864620447
2023-01-24 10:55:06.604936: step: 372/530, loss: 0.0019651406910270452
2023-01-24 10:55:07.705408: step: 376/530, loss: 0.0029390938580036163
2023-01-24 10:55:08.796185: step: 380/530, loss: 0.0006309486925601959
2023-01-24 10:55:09.889777: step: 384/530, loss: 0.0006725346902385354
2023-01-24 10:55:10.983634: step: 388/530, loss: 0.000701945973560214
2023-01-24 10:55:12.095305: step: 392/530, loss: 0.0005636418936774135
2023-01-24 10:55:13.212107: step: 396/530, loss: 0.0036305224057286978
2023-01-24 10:55:14.328390: step: 400/530, loss: 0.0026129111647605896
2023-01-24 10:55:15.409357: step: 404/530, loss: 0.0016736896941438317
2023-01-24 10:55:16.508968: step: 408/530, loss: 0.0032366346567869186
2023-01-24 10:55:17.590693: step: 412/530, loss: 0.010163509286940098
2023-01-24 10:55:18.677184: step: 416/530, loss: 0.0008702895138412714
2023-01-24 10:55:19.763721: step: 420/530, loss: 0.01142034586519003
2023-01-24 10:55:20.850172: step: 424/530, loss: 0.00237711681984365
2023-01-24 10:55:21.961262: step: 428/530, loss: 0.00505759147927165
2023-01-24 10:55:23.038292: step: 432/530, loss: 0.006024437490850687
2023-01-24 10:55:24.116115: step: 436/530, loss: 0.008693150244653225
2023-01-24 10:55:25.212579: step: 440/530, loss: 0.00016724682063795626
2023-01-24 10:55:26.302530: step: 444/530, loss: 6.383230356732383e-05
2023-01-24 10:55:27.394182: step: 448/530, loss: 0.0015097310533747077
2023-01-24 10:55:28.499970: step: 452/530, loss: 0.011982501484453678
2023-01-24 10:55:29.584965: step: 456/530, loss: 2.5591793928469997e-07
2023-01-24 10:55:30.678318: step: 460/530, loss: 0.0001620101393200457
2023-01-24 10:55:31.766333: step: 464/530, loss: 8.83015600265935e-05
2023-01-24 10:55:32.858109: step: 468/530, loss: 0.004646714311093092
2023-01-24 10:55:33.956079: step: 472/530, loss: 0.000592630822211504
2023-01-24 10:55:35.047241: step: 476/530, loss: 0.005837602540850639
2023-01-24 10:55:36.141805: step: 480/530, loss: 0.004000914748758078
2023-01-24 10:55:37.229852: step: 484/530, loss: 0.012194002978503704
2023-01-24 10:55:38.307679: step: 488/530, loss: 0.008404335007071495
2023-01-24 10:55:39.400371: step: 492/530, loss: 0.00016589769802521914
2023-01-24 10:55:40.510582: step: 496/530, loss: 6.875131657579914e-05
2023-01-24 10:55:41.596446: step: 500/530, loss: 0.00075691775418818
2023-01-24 10:55:42.711864: step: 504/530, loss: 0.031414587050676346
2023-01-24 10:55:43.820449: step: 508/530, loss: 0.0012252414599061012
2023-01-24 10:55:44.902814: step: 512/530, loss: 0.020032024011015892
2023-01-24 10:55:45.989620: step: 516/530, loss: 0.012250245548784733
2023-01-24 10:55:47.092125: step: 520/530, loss: 0.004050903487950563
2023-01-24 10:55:48.193835: step: 524/530, loss: 0.004247687291353941
2023-01-24 10:55:49.297726: step: 528/530, loss: 0.0035304396878927946
2023-01-24 10:55:50.401821: step: 532/530, loss: 0.007886233739554882
2023-01-24 10:55:51.523750: step: 536/530, loss: 0.006331183947622776
2023-01-24 10:55:52.638456: step: 540/530, loss: 0.013163681142032146
2023-01-24 10:55:53.728148: step: 544/530, loss: 0.0005475817015394568
2023-01-24 10:55:54.801457: step: 548/530, loss: 0.0004599393578246236
2023-01-24 10:55:55.880167: step: 552/530, loss: 0.0010365445632487535
2023-01-24 10:55:56.960084: step: 556/530, loss: 1.4423936590901576e-05
2023-01-24 10:55:58.052664: step: 560/530, loss: 1.5923005776130594e-05
2023-01-24 10:55:59.134057: step: 564/530, loss: 0.0003931539540644735
2023-01-24 10:56:00.253767: step: 568/530, loss: 0.0009414428495801985
2023-01-24 10:56:01.361438: step: 572/530, loss: 4.491058007261017e-06
2023-01-24 10:56:02.511105: step: 576/530, loss: 0.0037829342763870955
2023-01-24 10:56:03.596324: step: 580/530, loss: 8.805045217741281e-05
2023-01-24 10:56:04.677457: step: 584/530, loss: 4.563278821478889e-07
2023-01-24 10:56:05.777052: step: 588/530, loss: 0.00023557775421068072
2023-01-24 10:56:06.888378: step: 592/530, loss: 0.004916893783956766
2023-01-24 10:56:07.978981: step: 596/530, loss: 0.00038089865120127797
2023-01-24 10:56:09.093816: step: 600/530, loss: 0.004265580326318741
2023-01-24 10:56:10.208966: step: 604/530, loss: 0.004831551108509302
2023-01-24 10:56:11.315906: step: 608/530, loss: 0.0020402439404278994
2023-01-24 10:56:12.427888: step: 612/530, loss: 0.0008778349729254842
2023-01-24 10:56:13.510808: step: 616/530, loss: 0.0028767564799636602
2023-01-24 10:56:14.628492: step: 620/530, loss: 0.0036349743604660034
2023-01-24 10:56:15.735015: step: 624/530, loss: 0.0032440037466585636
2023-01-24 10:56:16.823289: step: 628/530, loss: 0.0046727824956178665
2023-01-24 10:56:17.894726: step: 632/530, loss: 0.002169714542105794
2023-01-24 10:56:18.972997: step: 636/530, loss: 0.0023315646685659885
2023-01-24 10:56:20.067907: step: 640/530, loss: 0.0004691978101618588
2023-01-24 10:56:21.167850: step: 644/530, loss: 0.0013867220841348171
2023-01-24 10:56:22.244794: step: 648/530, loss: 3.5058568755630404e-05
2023-01-24 10:56:23.331196: step: 652/530, loss: 0.0002541353169362992
2023-01-24 10:56:24.434777: step: 656/530, loss: 0.0025046151131391525
2023-01-24 10:56:25.517624: step: 660/530, loss: 4.2849565943470225e-05
2023-01-24 10:56:26.628156: step: 664/530, loss: 0.00032935856143012643
2023-01-24 10:56:27.707109: step: 668/530, loss: 0.00035427865805104375
2023-01-24 10:56:28.806757: step: 672/530, loss: 0.007320267613977194
2023-01-24 10:56:29.892660: step: 676/530, loss: 0.0018458595732226968
2023-01-24 10:56:30.968266: step: 680/530, loss: 0.0025820601731538773
2023-01-24 10:56:32.058062: step: 684/530, loss: 0.0017484494019299746
2023-01-24 10:56:33.129019: step: 688/530, loss: 0.0017654402181506157
2023-01-24 10:56:34.211136: step: 692/530, loss: 0.004032533150166273
2023-01-24 10:56:35.272516: step: 696/530, loss: 0.00021393563656602055
2023-01-24 10:56:36.355648: step: 700/530, loss: 0.0020914871711283922
2023-01-24 10:56:37.429323: step: 704/530, loss: 0.0003192913136444986
2023-01-24 10:56:38.494257: step: 708/530, loss: 0.0001073602688848041
2023-01-24 10:56:39.567799: step: 712/530, loss: 0.0015706164995208383
2023-01-24 10:56:40.664550: step: 716/530, loss: 0.002007235074415803
2023-01-24 10:56:41.793457: step: 720/530, loss: 0.0016504325903952122
2023-01-24 10:56:42.902447: step: 724/530, loss: 0.0013440509792417288
2023-01-24 10:56:44.005788: step: 728/530, loss: 0.004388183355331421
2023-01-24 10:56:45.096335: step: 732/530, loss: 0.004481877200305462
2023-01-24 10:56:46.191401: step: 736/530, loss: 0.003275747410953045
2023-01-24 10:56:47.270864: step: 740/530, loss: 4.967485074303113e-05
2023-01-24 10:56:48.364339: step: 744/530, loss: 0.0021200755145400763
2023-01-24 10:56:49.453244: step: 748/530, loss: 5.9789403167087585e-05
2023-01-24 10:56:50.547957: step: 752/530, loss: 0.001000691088847816
2023-01-24 10:56:51.625221: step: 756/530, loss: 0.00037946488009765744
2023-01-24 10:56:52.747466: step: 760/530, loss: 0.000272397039225325
2023-01-24 10:56:53.860996: step: 764/530, loss: 0.005482069682329893
2023-01-24 10:56:54.956897: step: 768/530, loss: 0.0014439367223531008
2023-01-24 10:56:56.055595: step: 772/530, loss: 0.00023551311460323632
2023-01-24 10:56:57.153522: step: 776/530, loss: 0.00016074276936706156
2023-01-24 10:56:58.239592: step: 780/530, loss: 0.00014413455210160464
2023-01-24 10:56:59.322591: step: 784/530, loss: 0.006376531440764666
2023-01-24 10:57:00.413332: step: 788/530, loss: 0.0004619788669515401
2023-01-24 10:57:01.516231: step: 792/530, loss: 5.243196937954053e-05
2023-01-24 10:57:02.608173: step: 796/530, loss: 8.521234121872112e-05
2023-01-24 10:57:03.719715: step: 800/530, loss: 0.001080823945812881
2023-01-24 10:57:04.802161: step: 804/530, loss: 3.813042712863535e-05
2023-01-24 10:57:05.878739: step: 808/530, loss: 0.0030335320625454187
2023-01-24 10:57:06.968956: step: 812/530, loss: 0.0039006578736007214
2023-01-24 10:57:08.075813: step: 816/530, loss: 0.0016806074418127537
2023-01-24 10:57:09.174764: step: 820/530, loss: 0.01914094388484955
2023-01-24 10:57:10.274496: step: 824/530, loss: 0.003452296368777752
2023-01-24 10:57:11.356001: step: 828/530, loss: 0.0002554992097429931
2023-01-24 10:57:12.455300: step: 832/530, loss: 0.0012343236012384295
2023-01-24 10:57:13.533350: step: 836/530, loss: 0.0031420369632542133
2023-01-24 10:57:14.641186: step: 840/530, loss: 0.0022533959709107876
2023-01-24 10:57:15.743790: step: 844/530, loss: 0.0020250931847840548
2023-01-24 10:57:16.845026: step: 848/530, loss: 0.0014053195482119918
2023-01-24 10:57:17.935625: step: 852/530, loss: 0.0019668361637741327
2023-01-24 10:57:19.035573: step: 856/530, loss: 0.001912312232889235
2023-01-24 10:57:20.114907: step: 860/530, loss: 0.002343566855415702
2023-01-24 10:57:21.196732: step: 864/530, loss: 0.0036152235697954893
2023-01-24 10:57:22.273987: step: 868/530, loss: 0.003888618666678667
2023-01-24 10:57:23.357365: step: 872/530, loss: 0.0
2023-01-24 10:57:24.481098: step: 876/530, loss: 0.009707119315862656
2023-01-24 10:57:25.584208: step: 880/530, loss: 0.00782280694693327
2023-01-24 10:57:26.691085: step: 884/530, loss: 0.002724698279052973
2023-01-24 10:57:27.767842: step: 888/530, loss: 5.1082268328173086e-05
2023-01-24 10:57:28.852019: step: 892/530, loss: 0.0023005264811217785
2023-01-24 10:57:29.963239: step: 896/530, loss: 5.8825709857046604e-05
2023-01-24 10:57:31.057220: step: 900/530, loss: 0.0072162458673119545
2023-01-24 10:57:32.162734: step: 904/530, loss: 0.00029325688956305385
2023-01-24 10:57:33.248844: step: 908/530, loss: 0.0022310204803943634
2023-01-24 10:57:34.355046: step: 912/530, loss: 0.000991170178167522
2023-01-24 10:57:35.446693: step: 916/530, loss: 0.002493495587259531
2023-01-24 10:57:36.516354: step: 920/530, loss: 0.006371739786118269
2023-01-24 10:57:37.607512: step: 924/530, loss: 0.01080137025564909
2023-01-24 10:57:38.699819: step: 928/530, loss: 4.840054316446185e-06
2023-01-24 10:57:39.792858: step: 932/530, loss: 0.0035445194225758314
2023-01-24 10:57:40.872302: step: 936/530, loss: 0.0018409241456538439
2023-01-24 10:57:41.955393: step: 940/530, loss: 0.0011638402938842773
2023-01-24 10:57:43.032575: step: 944/530, loss: 0.004288491792976856
2023-01-24 10:57:44.109176: step: 948/530, loss: 0.0004601738473866135
2023-01-24 10:57:45.223634: step: 952/530, loss: 0.0036804615519940853
2023-01-24 10:57:46.304368: step: 956/530, loss: 0.001864671939983964
2023-01-24 10:57:47.397812: step: 960/530, loss: 0.007566457148641348
2023-01-24 10:57:48.491687: step: 964/530, loss: 3.502176332403906e-05
2023-01-24 10:57:49.585543: step: 968/530, loss: 0.011312774382531643
2023-01-24 10:57:50.659728: step: 972/530, loss: 0.006206408608704805
2023-01-24 10:57:51.743174: step: 976/530, loss: 0.0005008551524952054
2023-01-24 10:57:52.856173: step: 980/530, loss: 0.0017643271712586284
2023-01-24 10:57:53.972407: step: 984/530, loss: 0.0022599254734814167
2023-01-24 10:57:55.082135: step: 988/530, loss: 0.0014045790303498507
2023-01-24 10:57:56.149527: step: 992/530, loss: 0.0003754697390832007
2023-01-24 10:57:57.226832: step: 996/530, loss: 0.0025966197717934847
2023-01-24 10:57:58.334101: step: 1000/530, loss: 0.0059115388430655
2023-01-24 10:57:59.406782: step: 1004/530, loss: 0.004008471965789795
2023-01-24 10:58:00.505196: step: 1008/530, loss: 0.006558794528245926
2023-01-24 10:58:01.611025: step: 1012/530, loss: 0.0057535069063305855
2023-01-24 10:58:02.702835: step: 1016/530, loss: 0.0027343512047082186
2023-01-24 10:58:03.804294: step: 1020/530, loss: 0.00018126910435967147
2023-01-24 10:58:04.884186: step: 1024/530, loss: 0.010294582694768906
2023-01-24 10:58:05.964713: step: 1028/530, loss: 0.0003243729879613966
2023-01-24 10:58:07.083276: step: 1032/530, loss: 4.505300967139192e-05
2023-01-24 10:58:08.172586: step: 1036/530, loss: 0.0020992967765778303
2023-01-24 10:58:09.256001: step: 1040/530, loss: 0.001721567357890308
2023-01-24 10:58:10.346882: step: 1044/530, loss: 0.00028687919257208705
2023-01-24 10:58:11.460849: step: 1048/530, loss: 0.0028847442008554935
2023-01-24 10:58:12.568757: step: 1052/530, loss: 0.0002744919911492616
2023-01-24 10:58:13.647995: step: 1056/530, loss: 0.004789954517036676
2023-01-24 10:58:14.755122: step: 1060/530, loss: 0.0001996932114707306
2023-01-24 10:58:15.834309: step: 1064/530, loss: 0.002991387154906988
2023-01-24 10:58:16.927682: step: 1068/530, loss: 0.0013041590573266149
2023-01-24 10:58:18.042848: step: 1072/530, loss: 0.0009976651053875685
2023-01-24 10:58:19.126444: step: 1076/530, loss: 0.0003664449031930417
2023-01-24 10:58:20.217120: step: 1080/530, loss: 0.003211794886738062
2023-01-24 10:58:21.339954: step: 1084/530, loss: 0.0015634378651157022
2023-01-24 10:58:22.414751: step: 1088/530, loss: 0.00016998103819787502
2023-01-24 10:58:23.491959: step: 1092/530, loss: 0.00010231405030936003
2023-01-24 10:58:24.589275: step: 1096/530, loss: 2.615609992062673e-05
2023-01-24 10:58:25.672927: step: 1100/530, loss: 4.504331809584983e-05
2023-01-24 10:58:26.739441: step: 1104/530, loss: 0.00014758470933884382
2023-01-24 10:58:27.826999: step: 1108/530, loss: 0.00011001220991602167
2023-01-24 10:58:28.934241: step: 1112/530, loss: 0.01595516875386238
2023-01-24 10:58:30.013786: step: 1116/530, loss: 0.00031333856168203056
2023-01-24 10:58:31.101825: step: 1120/530, loss: 0.0019532975275069475
2023-01-24 10:58:32.202067: step: 1124/530, loss: 0.002874934347346425
2023-01-24 10:58:33.291927: step: 1128/530, loss: 0.0022516525350511074
2023-01-24 10:58:34.378849: step: 1132/530, loss: 0.0005060546100139618
2023-01-24 10:58:35.478955: step: 1136/530, loss: 0.0005739081534557045
2023-01-24 10:58:36.570329: step: 1140/530, loss: 0.0012365446891635656
2023-01-24 10:58:37.683952: step: 1144/530, loss: 0.019276412203907967
2023-01-24 10:58:38.753612: step: 1148/530, loss: 0.0014636055566370487
2023-01-24 10:58:39.868574: step: 1152/530, loss: 0.003789471462368965
2023-01-24 10:58:40.962971: step: 1156/530, loss: 0.0028425180353224277
2023-01-24 10:58:42.053556: step: 1160/530, loss: 0.0035149287432432175
2023-01-24 10:58:43.153705: step: 1164/530, loss: 0.0031245313584804535
2023-01-24 10:58:44.251183: step: 1168/530, loss: 0.00384851498529315
2023-01-24 10:58:45.351133: step: 1172/530, loss: 0.00021501992887351662
2023-01-24 10:58:46.448443: step: 1176/530, loss: 0.0034433945547789335
2023-01-24 10:58:47.537081: step: 1180/530, loss: 0.007750116754323244
2023-01-24 10:58:48.627215: step: 1184/530, loss: 0.000263664813246578
2023-01-24 10:58:49.744310: step: 1188/530, loss: 0.003954093437641859
2023-01-24 10:58:50.822540: step: 1192/530, loss: 2.8115797249483876e-05
2023-01-24 10:58:51.944206: step: 1196/530, loss: 0.00457800505682826
2023-01-24 10:58:53.010354: step: 1200/530, loss: 0.0010012646671384573
2023-01-24 10:58:54.104951: step: 1204/530, loss: 2.460063797116163e-06
2023-01-24 10:58:55.186445: step: 1208/530, loss: 1.3038495616513046e-08
2023-01-24 10:58:56.277043: step: 1212/530, loss: 8.966604218585417e-05
2023-01-24 10:58:57.354472: step: 1216/530, loss: 3.9777263737050816e-05
2023-01-24 10:58:58.441751: step: 1220/530, loss: 6.475103873526677e-05
2023-01-24 10:58:59.538541: step: 1224/530, loss: 0.003936760127544403
2023-01-24 10:59:00.632155: step: 1228/530, loss: 0.005309733096510172
2023-01-24 10:59:01.707181: step: 1232/530, loss: 3.902622847817838e-05
2023-01-24 10:59:02.805948: step: 1236/530, loss: 0.007171180564910173
2023-01-24 10:59:03.896700: step: 1240/530, loss: 0.0013217878295108676
2023-01-24 10:59:04.981641: step: 1244/530, loss: 0.0026664354372769594
2023-01-24 10:59:06.058348: step: 1248/530, loss: 5.535219679586589e-05
2023-01-24 10:59:07.149391: step: 1252/530, loss: 0.004173062276095152
2023-01-24 10:59:08.243833: step: 1256/530, loss: 0.000889939779881388
2023-01-24 10:59:09.322049: step: 1260/530, loss: 0.001878840266726911
2023-01-24 10:59:10.414596: step: 1264/530, loss: 0.00019303134467918426
2023-01-24 10:59:11.490161: step: 1268/530, loss: 0.0058050015941262245
2023-01-24 10:59:12.573816: step: 1272/530, loss: 0.0011189930373802781
2023-01-24 10:59:13.662342: step: 1276/530, loss: 0.0022181409876793623
2023-01-24 10:59:14.759472: step: 1280/530, loss: 0.0009613332222215831
2023-01-24 10:59:15.850154: step: 1284/530, loss: 0.0007159464876167476
2023-01-24 10:59:16.959257: step: 1288/530, loss: 0.0017143894219771028
2023-01-24 10:59:18.066809: step: 1292/530, loss: 0.006154817063361406
2023-01-24 10:59:19.157012: step: 1296/530, loss: 0.007152739446610212
2023-01-24 10:59:20.279481: step: 1300/530, loss: 0.0021627964451909065
2023-01-24 10:59:21.374945: step: 1304/530, loss: 0.001702772919088602
2023-01-24 10:59:22.458495: step: 1308/530, loss: 6.095332082622917e-06
2023-01-24 10:59:23.565347: step: 1312/530, loss: 0.0044060563668608665
2023-01-24 10:59:24.672887: step: 1316/530, loss: 0.00379826663993299
2023-01-24 10:59:25.759488: step: 1320/530, loss: 0.0015721842646598816
2023-01-24 10:59:26.844141: step: 1324/530, loss: 0.002565699862316251
2023-01-24 10:59:27.952398: step: 1328/530, loss: 0.0025266525335609913
2023-01-24 10:59:29.051266: step: 1332/530, loss: 0.0022809526417404413
2023-01-24 10:59:30.156735: step: 1336/530, loss: 0.0002023878914769739
2023-01-24 10:59:31.225937: step: 1340/530, loss: 0.00039393187034875154
2023-01-24 10:59:32.332163: step: 1344/530, loss: 8.490855179843493e-06
2023-01-24 10:59:33.455577: step: 1348/530, loss: 0.0012715040938928723
2023-01-24 10:59:34.534910: step: 1352/530, loss: 0.0033437812235206366
2023-01-24 10:59:35.670328: step: 1356/530, loss: 0.0026764723006635904
2023-01-24 10:59:36.783527: step: 1360/530, loss: 0.0018067383207380772
2023-01-24 10:59:37.893715: step: 1364/530, loss: 0.0024920664727687836
2023-01-24 10:59:38.986453: step: 1368/530, loss: 7.260068377945572e-05
2023-01-24 10:59:40.094012: step: 1372/530, loss: 0.004392989445477724
2023-01-24 10:59:41.177935: step: 1376/530, loss: 0.007284869905561209
2023-01-24 10:59:42.291152: step: 1380/530, loss: 0.0025853365659713745
2023-01-24 10:59:43.378918: step: 1384/530, loss: 0.0006087161600589752
2023-01-24 10:59:44.460798: step: 1388/530, loss: 2.4609207684989087e-05
2023-01-24 10:59:45.545688: step: 1392/530, loss: 1.7088406821130775e-05
2023-01-24 10:59:46.641310: step: 1396/530, loss: 0.00859412457793951
2023-01-24 10:59:47.726748: step: 1400/530, loss: 0.0019435868598520756
2023-01-24 10:59:48.812250: step: 1404/530, loss: 0.0019388190703466535
2023-01-24 10:59:49.909755: step: 1408/530, loss: 1.255468487215694e-05
2023-01-24 10:59:51.008776: step: 1412/530, loss: 0.00016437396698165685
2023-01-24 10:59:52.097471: step: 1416/530, loss: 0.0015550577081739902
2023-01-24 10:59:53.182272: step: 1420/530, loss: 0.00014448219735641032
2023-01-24 10:59:54.270963: step: 1424/530, loss: 0.0019296086393296719
2023-01-24 10:59:55.357751: step: 1428/530, loss: 0.0006081080064177513
2023-01-24 10:59:56.444871: step: 1432/530, loss: 0.0021067133639007807
2023-01-24 10:59:57.531417: step: 1436/530, loss: 0.002325301757082343
2023-01-24 10:59:58.606030: step: 1440/530, loss: 0.0014245351776480675
2023-01-24 10:59:59.697612: step: 1444/530, loss: 5.2530690481944475e-06
2023-01-24 11:00:00.776139: step: 1448/530, loss: 0.0013785141054540873
2023-01-24 11:00:01.866155: step: 1452/530, loss: 0.00266665150411427
2023-01-24 11:00:02.942950: step: 1456/530, loss: 0.00010153292532777414
2023-01-24 11:00:04.033837: step: 1460/530, loss: 0.010531317442655563
2023-01-24 11:00:05.144781: step: 1464/530, loss: 0.005117565393447876
2023-01-24 11:00:06.248592: step: 1468/530, loss: 0.0026795787271112204
2023-01-24 11:00:07.355596: step: 1472/530, loss: 0.004253399092704058
2023-01-24 11:00:08.456921: step: 1476/530, loss: 0.006138286553323269
2023-01-24 11:00:09.540196: step: 1480/530, loss: 0.001985726645216346
2023-01-24 11:00:10.621787: step: 1484/530, loss: 0.0009818169055506587
2023-01-24 11:00:11.719594: step: 1488/530, loss: 0.0020236035343259573
2023-01-24 11:00:12.811920: step: 1492/530, loss: 0.0019806043710559607
2023-01-24 11:00:13.905713: step: 1496/530, loss: 0.007451156619936228
2023-01-24 11:00:14.985980: step: 1500/530, loss: 0.0007054515881463885
2023-01-24 11:00:16.066782: step: 1504/530, loss: 0.0030755724292248487
2023-01-24 11:00:17.168934: step: 1508/530, loss: 0.005066622514277697
2023-01-24 11:00:18.271076: step: 1512/530, loss: 0.006008957978338003
2023-01-24 11:00:19.347160: step: 1516/530, loss: 0.013087806291878223
2023-01-24 11:00:20.433574: step: 1520/530, loss: 0.001419123844243586
2023-01-24 11:00:21.529725: step: 1524/530, loss: 0.0009964581113308668
2023-01-24 11:00:22.622940: step: 1528/530, loss: 0.00013537734048441052
2023-01-24 11:00:23.696153: step: 1532/530, loss: 0.0027017153333872557
2023-01-24 11:00:24.771475: step: 1536/530, loss: 0.0010289069032296538
2023-01-24 11:00:25.847609: step: 1540/530, loss: 4.0146969695342705e-05
2023-01-24 11:00:26.929597: step: 1544/530, loss: 0.0018527734791859984
2023-01-24 11:00:28.022475: step: 1548/530, loss: 0.00414172001183033
2023-01-24 11:00:29.107235: step: 1552/530, loss: 0.0004370535025373101
2023-01-24 11:00:30.218234: step: 1556/530, loss: 0.0009930988308042288
2023-01-24 11:00:31.320663: step: 1560/530, loss: 0.0015663818921893835
2023-01-24 11:00:32.397295: step: 1564/530, loss: 0.007728134747594595
2023-01-24 11:00:33.486843: step: 1568/530, loss: 0.009619293734431267
2023-01-24 11:00:34.576733: step: 1572/530, loss: 0.00032079138327389956
2023-01-24 11:00:35.645828: step: 1576/530, loss: 0.000599631923250854
2023-01-24 11:00:36.743913: step: 1580/530, loss: 0.005323352292180061
2023-01-24 11:00:37.850456: step: 1584/530, loss: 0.0011103095021098852
2023-01-24 11:00:38.923960: step: 1588/530, loss: 1.4017600733495783e-06
2023-01-24 11:00:40.032231: step: 1592/530, loss: 0.0024874003138393164
2023-01-24 11:00:41.175490: step: 1596/530, loss: 0.005891331937164068
2023-01-24 11:00:42.295065: step: 1600/530, loss: 0.005847080610692501
2023-01-24 11:00:43.366802: step: 1604/530, loss: 0.0019826064817607403
2023-01-24 11:00:44.448432: step: 1608/530, loss: 0.01145973801612854
2023-01-24 11:00:45.554764: step: 1612/530, loss: 0.001424646470695734
2023-01-24 11:00:46.655248: step: 1616/530, loss: 0.003142877947539091
2023-01-24 11:00:47.728290: step: 1620/530, loss: 3.783239299082197e-05
2023-01-24 11:00:48.820085: step: 1624/530, loss: 0.004596029408276081
2023-01-24 11:00:49.915297: step: 1628/530, loss: 0.003456001402810216
2023-01-24 11:00:50.984514: step: 1632/530, loss: 6.610665082007472e-07
2023-01-24 11:00:52.078680: step: 1636/530, loss: 0.0001403927308274433
2023-01-24 11:00:53.179526: step: 1640/530, loss: 0.003840002231299877
2023-01-24 11:00:54.280917: step: 1644/530, loss: 0.0008944791625253856
2023-01-24 11:00:55.375482: step: 1648/530, loss: 0.004717118572443724
2023-01-24 11:00:56.472809: step: 1652/530, loss: 0.00012440640421118587
2023-01-24 11:00:57.562173: step: 1656/530, loss: 0.0014180088182911277
2023-01-24 11:00:58.660060: step: 1660/530, loss: 0.004750819411128759
2023-01-24 11:00:59.757784: step: 1664/530, loss: 0.0017868034774437547
2023-01-24 11:01:00.856581: step: 1668/530, loss: 0.0012775957584381104
2023-01-24 11:01:01.952439: step: 1672/530, loss: 0.0031952436547726393
2023-01-24 11:01:03.023291: step: 1676/530, loss: 2.72011475317413e-05
2023-01-24 11:01:04.122836: step: 1680/530, loss: 0.003033621469512582
2023-01-24 11:01:05.206426: step: 1684/530, loss: 0.00031308206962421536
2023-01-24 11:01:06.266290: step: 1688/530, loss: 4.836493098991923e-05
2023-01-24 11:01:07.382348: step: 1692/530, loss: 7.271373033290729e-05
2023-01-24 11:01:08.472791: step: 1696/530, loss: 0.0001186248628073372
2023-01-24 11:01:09.570810: step: 1700/530, loss: 0.002530114259570837
2023-01-24 11:01:10.660732: step: 1704/530, loss: 0.0020812377333641052
2023-01-24 11:01:11.734716: step: 1708/530, loss: 0.010340622626245022
2023-01-24 11:01:12.821751: step: 1712/530, loss: 0.0002444394340272993
2023-01-24 11:01:13.900442: step: 1716/530, loss: 0.003982409369200468
2023-01-24 11:01:14.996025: step: 1720/530, loss: 3.0109549697954208e-05
2023-01-24 11:01:16.099556: step: 1724/530, loss: 0.0016302644507959485
2023-01-24 11:01:17.194743: step: 1728/530, loss: 0.0005931056221015751
2023-01-24 11:01:18.279519: step: 1732/530, loss: 2.019263547481387e-06
2023-01-24 11:01:19.351806: step: 1736/530, loss: 0.0008689704118296504
2023-01-24 11:01:20.446830: step: 1740/530, loss: 0.0008405217085964978
2023-01-24 11:01:21.520715: step: 1744/530, loss: 2.7922547815251164e-05
2023-01-24 11:01:22.589383: step: 1748/530, loss: 7.264497253345326e-05
2023-01-24 11:01:23.662678: step: 1752/530, loss: 0.00038379195029847324
2023-01-24 11:01:24.756345: step: 1756/530, loss: 0.0009625382372178137
2023-01-24 11:01:25.843832: step: 1760/530, loss: 0.0002641146711539477
2023-01-24 11:01:26.950059: step: 1764/530, loss: 0.009809155017137527
2023-01-24 11:01:28.019647: step: 1768/530, loss: 0.00038203957956284285
2023-01-24 11:01:29.105198: step: 1772/530, loss: 0.010345851071178913
2023-01-24 11:01:30.190887: step: 1776/530, loss: 0.0003978973545599729
2023-01-24 11:01:31.287310: step: 1780/530, loss: 0.003386878641322255
2023-01-24 11:01:32.366167: step: 1784/530, loss: 0.0001284680183744058
2023-01-24 11:01:33.464697: step: 1788/530, loss: 0.0014040580717846751
2023-01-24 11:01:34.546292: step: 1792/530, loss: 6.557555752806365e-05
2023-01-24 11:01:35.647383: step: 1796/530, loss: 0.0044130305759608746
2023-01-24 11:01:36.731753: step: 1800/530, loss: 0.0013103386154398322
2023-01-24 11:01:37.833050: step: 1804/530, loss: 0.0015345969004556537
2023-01-24 11:01:38.915501: step: 1808/530, loss: 0.004855201579630375
2023-01-24 11:01:40.007159: step: 1812/530, loss: 0.016004931181669235
2023-01-24 11:01:41.117523: step: 1816/530, loss: 0.001297872862778604
2023-01-24 11:01:42.221833: step: 1820/530, loss: 0.005055380053818226
2023-01-24 11:01:43.305299: step: 1824/530, loss: 0.00018071664089802653
2023-01-24 11:01:44.413633: step: 1828/530, loss: 0.0075599090196192265
2023-01-24 11:01:45.522937: step: 1832/530, loss: 0.0034981267526745796
2023-01-24 11:01:46.609912: step: 1836/530, loss: 0.0011073533678427339
2023-01-24 11:01:47.700326: step: 1840/530, loss: 0.0015231224242597818
2023-01-24 11:01:48.792241: step: 1844/530, loss: 0.0038231462240219116
2023-01-24 11:01:49.898754: step: 1848/530, loss: 0.0004272600053809583
2023-01-24 11:01:50.982284: step: 1852/530, loss: 0.0017785176169127226
2023-01-24 11:01:52.066115: step: 1856/530, loss: 2.09951735996583e-06
2023-01-24 11:01:53.153816: step: 1860/530, loss: 0.0006456903065554798
2023-01-24 11:01:54.248930: step: 1864/530, loss: 0.00011082401033490896
2023-01-24 11:01:55.350982: step: 1868/530, loss: 0.0009531215182505548
2023-01-24 11:01:56.437538: step: 1872/530, loss: 0.00011759912013076246
2023-01-24 11:01:57.523469: step: 1876/530, loss: 0.006264088209718466
2023-01-24 11:01:58.621440: step: 1880/530, loss: 0.012948942370712757
2023-01-24 11:01:59.700112: step: 1884/530, loss: 0.0030248446855694056
2023-01-24 11:02:00.785188: step: 1888/530, loss: 2.8554763048305176e-05
2023-01-24 11:02:01.865352: step: 1892/530, loss: 1.4335214473248925e-05
2023-01-24 11:02:02.955154: step: 1896/530, loss: 0.004100819118320942
2023-01-24 11:02:04.043304: step: 1900/530, loss: 0.0008017533691599965
2023-01-24 11:02:05.117484: step: 1904/530, loss: 0.0006815269589424133
2023-01-24 11:02:06.212449: step: 1908/530, loss: 0.003955672029405832
2023-01-24 11:02:07.302382: step: 1912/530, loss: 0.005318224895745516
2023-01-24 11:02:08.394100: step: 1916/530, loss: 0.00162272690795362
2023-01-24 11:02:09.477547: step: 1920/530, loss: 0.004056726116687059
2023-01-24 11:02:10.556853: step: 1924/530, loss: 0.005189417861402035
2023-01-24 11:02:11.653320: step: 1928/530, loss: 0.003656966844573617
2023-01-24 11:02:12.758441: step: 1932/530, loss: 0.0036018837708979845
2023-01-24 11:02:13.845905: step: 1936/530, loss: 0.02192796766757965
2023-01-24 11:02:14.919682: step: 1940/530, loss: 5.364325943446602e-07
2023-01-24 11:02:16.014982: step: 1944/530, loss: 0.003181676845997572
2023-01-24 11:02:17.105460: step: 1948/530, loss: 0.004406286869198084
2023-01-24 11:02:18.204455: step: 1952/530, loss: 0.008195783942937851
2023-01-24 11:02:19.309525: step: 1956/530, loss: 0.0002161364973289892
2023-01-24 11:02:20.402844: step: 1960/530, loss: 0.014707427471876144
2023-01-24 11:02:21.477959: step: 1964/530, loss: 0.0008810496656224132
2023-01-24 11:02:22.594459: step: 1968/530, loss: 0.004724032245576382
2023-01-24 11:02:23.678624: step: 1972/530, loss: 0.0021628988906741142
2023-01-24 11:02:24.784975: step: 1976/530, loss: 0.012636066414415836
2023-01-24 11:02:25.868757: step: 1980/530, loss: 0.0006995893199928105
2023-01-24 11:02:26.933048: step: 1984/530, loss: 0.0028340821154415607
2023-01-24 11:02:28.019255: step: 1988/530, loss: 0.0015111678512766957
2023-01-24 11:02:29.108289: step: 1992/530, loss: 0.003040769835934043
2023-01-24 11:02:30.198192: step: 1996/530, loss: 0.0021007449831813574
2023-01-24 11:02:31.265178: step: 2000/530, loss: 6.046826092642732e-05
2023-01-24 11:02:32.331881: step: 2004/530, loss: 0.011318760924041271
2023-01-24 11:02:33.416277: step: 2008/530, loss: 0.0008086036541499197
2023-01-24 11:02:34.519745: step: 2012/530, loss: 0.001626555691473186
2023-01-24 11:02:35.618559: step: 2016/530, loss: 0.0005122142611071467
2023-01-24 11:02:36.692425: step: 2020/530, loss: 0.006633398588746786
2023-01-24 11:02:37.797342: step: 2024/530, loss: 0.005307371262460947
2023-01-24 11:02:38.896325: step: 2028/530, loss: 0.006337102502584457
2023-01-24 11:02:40.011267: step: 2032/530, loss: 0.0022158240899443626
2023-01-24 11:02:41.113365: step: 2036/530, loss: 0.000360160309355706
2023-01-24 11:02:42.199924: step: 2040/530, loss: 0.006802905350923538
2023-01-24 11:02:43.319619: step: 2044/530, loss: 0.0004644159344024956
2023-01-24 11:02:44.416633: step: 2048/530, loss: 0.0007800815510563552
2023-01-24 11:02:45.508259: step: 2052/530, loss: 0.0002871396718546748
2023-01-24 11:02:46.611068: step: 2056/530, loss: 0.00527344923466444
2023-01-24 11:02:47.692561: step: 2060/530, loss: 3.128217485937057e-06
2023-01-24 11:02:48.809597: step: 2064/530, loss: 0.0019845294300466776
2023-01-24 11:02:49.900130: step: 2068/530, loss: 0.0024314215406775475
2023-01-24 11:02:51.001817: step: 2072/530, loss: 0.011278643272817135
2023-01-24 11:02:52.099179: step: 2076/530, loss: 0.014923572540283203
2023-01-24 11:02:53.187736: step: 2080/530, loss: 0.0012695260811597109
2023-01-24 11:02:54.275989: step: 2084/530, loss: 0.0048428867012262344
2023-01-24 11:02:55.361973: step: 2088/530, loss: 7.22408076399006e-05
2023-01-24 11:02:56.445938: step: 2092/530, loss: 1.5640538549632765e-05
2023-01-24 11:02:57.523547: step: 2096/530, loss: 0.000488990219309926
2023-01-24 11:02:58.606836: step: 2100/530, loss: 0.001418329426087439
2023-01-24 11:02:59.708378: step: 2104/530, loss: 9.549040260026231e-05
2023-01-24 11:03:00.799875: step: 2108/530, loss: 0.0009483927278779447
2023-01-24 11:03:01.896371: step: 2112/530, loss: 0.005046523176133633
2023-01-24 11:03:02.979987: step: 2116/530, loss: 0.006434328854084015
2023-01-24 11:03:04.074027: step: 2120/530, loss: 0.002885560505092144
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35301374095936466, 'r': 0.35100417507155046, 'f1': 0.3520060899385482}, 'combined': 0.25937290837577237, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34538631501139494, 'r': 0.27671900609221556, 'f1': 0.3072629491040416}, 'combined': 0.19082646312777324, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38835155122655124, 'r': 0.33160948396954093, 'f1': 0.3577445200654004}, 'combined': 0.26360122531134766, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33410321050117053, 'r': 0.26246250232058355, 'f1': 0.29398124222294475}, 'combined': 0.1825778241174078, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3830757564440904, 'r': 0.32928523276882915, 'f1': 0.35414962789627136}, 'combined': 0.2609523573972526, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34425713379996925, 'r': 0.2684729868726315, 'f1': 0.30167846445033353}, 'combined': 0.18735820423757557, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.38, 'r': 0.41304347826086957, 'f1': 0.39583333333333337}, 'combined': 0.19791666666666669, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.351567486318917, 'r': 0.3529017082783816, 'f1': 0.3522333338308847}, 'combined': 0.25954035124380975, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34136774075423865, 'r': 0.2772135659339564, 'f1': 0.30596388117819856}, 'combined': 0.1900196735738286, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}
******************************
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 11:05:30.311649: step: 4/530, loss: 0.00010612226469675079
2023-01-24 11:05:31.393146: step: 8/530, loss: 0.002795103471726179
2023-01-24 11:05:32.454674: step: 12/530, loss: 0.0012319920351728797
2023-01-24 11:05:33.547061: step: 16/530, loss: 0.0014200176810845733
2023-01-24 11:05:34.616608: step: 20/530, loss: 0.0016587760765105486
2023-01-24 11:05:35.751814: step: 24/530, loss: 0.0021934101823717356
2023-01-24 11:05:36.822656: step: 28/530, loss: 0.00047815864672884345
2023-01-24 11:05:37.887536: step: 32/530, loss: 0.0005557241966016591
2023-01-24 11:05:38.980856: step: 36/530, loss: 0.0001829547982197255
2023-01-24 11:05:40.043973: step: 40/530, loss: 0.000904804328456521
2023-01-24 11:05:41.132546: step: 44/530, loss: 0.0018636543536558747
2023-01-24 11:05:42.203938: step: 48/530, loss: 0.0014137588441371918
2023-01-24 11:05:43.288456: step: 52/530, loss: 0.000891570933163166
2023-01-24 11:05:44.339511: step: 56/530, loss: 0.004370993003249168
2023-01-24 11:05:45.418924: step: 60/530, loss: 0.0031751038040965796
2023-01-24 11:05:46.525872: step: 64/530, loss: 0.00010741830919869244
2023-01-24 11:05:47.613905: step: 68/530, loss: 4.526889824774116e-05
2023-01-24 11:05:48.705558: step: 72/530, loss: 0.001225336454808712
2023-01-24 11:05:49.786488: step: 76/530, loss: 0.00047454051673412323
2023-01-24 11:05:50.859329: step: 80/530, loss: 0.00041128124576061964
2023-01-24 11:05:51.944542: step: 84/530, loss: 0.006240918301045895
2023-01-24 11:05:53.013503: step: 88/530, loss: 0.0009851172799244523
2023-01-24 11:05:54.107819: step: 92/530, loss: 0.0006712054600939155
2023-01-24 11:05:55.206262: step: 96/530, loss: 0.0036751648876816034
2023-01-24 11:05:56.320853: step: 100/530, loss: 0.0008558948757126927
2023-01-24 11:05:57.411023: step: 104/530, loss: 6.694487819913775e-05
2023-01-24 11:05:58.495862: step: 108/530, loss: 0.0012892525410279632
2023-01-24 11:05:59.594929: step: 112/530, loss: 6.967418357817223e-06
2023-01-24 11:06:00.683669: step: 116/530, loss: 0.003482397645711899
2023-01-24 11:06:01.770318: step: 120/530, loss: 0.0016791452653706074
2023-01-24 11:06:02.855135: step: 124/530, loss: 0.00023542375129181892
2023-01-24 11:06:03.947761: step: 128/530, loss: 0.00030218009487725794
2023-01-24 11:06:05.013592: step: 132/530, loss: 0.0010352826211601496
2023-01-24 11:06:06.088141: step: 136/530, loss: 0.00018657285545486957
2023-01-24 11:06:07.189799: step: 140/530, loss: 0.00039744420791976154
2023-01-24 11:06:08.288166: step: 144/530, loss: 0.0014532171189785004
2023-01-24 11:06:09.385671: step: 148/530, loss: 0.000477830006275326
2023-01-24 11:06:10.468908: step: 152/530, loss: 0.001896329689770937
2023-01-24 11:06:11.562311: step: 156/530, loss: 0.0035541930701583624
2023-01-24 11:06:12.640127: step: 160/530, loss: 0.00035384896909818053
2023-01-24 11:06:13.753534: step: 164/530, loss: 0.00028528578695841134
2023-01-24 11:06:14.825454: step: 168/530, loss: 0.014234398491680622
2023-01-24 11:06:15.943909: step: 172/530, loss: 0.008148133754730225
2023-01-24 11:06:17.031366: step: 176/530, loss: 0.000363050407031551
2023-01-24 11:06:18.123881: step: 180/530, loss: 0.003651235718280077
2023-01-24 11:06:19.205660: step: 184/530, loss: 0.0013336684787645936
2023-01-24 11:06:20.300005: step: 188/530, loss: 6.017145642545074e-05
2023-01-24 11:06:21.405684: step: 192/530, loss: 0.000127437524497509
2023-01-24 11:06:22.511799: step: 196/530, loss: 9.177709580399096e-05
2023-01-24 11:06:23.596720: step: 200/530, loss: 0.0002827983407769352
2023-01-24 11:06:24.693955: step: 204/530, loss: 0.004648215137422085
2023-01-24 11:06:25.778023: step: 208/530, loss: 0.00022543530212715268
2023-01-24 11:06:26.863507: step: 212/530, loss: 0.007725493051111698
2023-01-24 11:06:27.952845: step: 216/530, loss: 2.5174347683787346e-05
2023-01-24 11:06:29.069148: step: 220/530, loss: 0.00765589065849781
2023-01-24 11:06:30.178361: step: 224/530, loss: 0.0007989535224623978
2023-01-24 11:06:31.273100: step: 228/530, loss: 0.0028176598716527224
2023-01-24 11:06:32.365170: step: 232/530, loss: 0.008448977954685688
2023-01-24 11:06:33.456276: step: 236/530, loss: 2.2463866116595455e-05
2023-01-24 11:06:34.528298: step: 240/530, loss: 0.002177407266572118
2023-01-24 11:06:35.630496: step: 244/530, loss: 0.00027448637410998344
2023-01-24 11:06:36.730448: step: 248/530, loss: 0.001832942827604711
2023-01-24 11:06:37.827406: step: 252/530, loss: 0.0022396331187337637
2023-01-24 11:06:38.921603: step: 256/530, loss: 6.207867409102619e-05
2023-01-24 11:06:40.044862: step: 260/530, loss: 0.0022227142471820116
2023-01-24 11:06:41.142584: step: 264/530, loss: 0.005615370813757181
2023-01-24 11:06:42.284737: step: 268/530, loss: 0.0014066529693081975
2023-01-24 11:06:43.368662: step: 272/530, loss: 0.0015630247071385384
2023-01-24 11:06:44.454476: step: 276/530, loss: 0.002412098227068782
2023-01-24 11:06:45.572266: step: 280/530, loss: 0.00030573393451049924
2023-01-24 11:06:46.672720: step: 284/530, loss: 0.0016775837866589427
2023-01-24 11:06:47.770120: step: 288/530, loss: 0.0005219071172177792
2023-01-24 11:06:48.861332: step: 292/530, loss: 0.00039185353671200573
2023-01-24 11:06:49.945828: step: 296/530, loss: 0.0001350231032120064
2023-01-24 11:06:51.038369: step: 300/530, loss: 4.602426542987814e-06
2023-01-24 11:06:52.146120: step: 304/530, loss: 0.002512165578082204
2023-01-24 11:06:53.225490: step: 308/530, loss: 0.01900053396821022
2023-01-24 11:06:54.306824: step: 312/530, loss: 0.0005610514199361205
2023-01-24 11:06:55.404946: step: 316/530, loss: 0.0025838708970695734
2023-01-24 11:06:56.486825: step: 320/530, loss: 0.007404142525047064
2023-01-24 11:06:57.615335: step: 324/530, loss: 7.23678749636747e-05
2023-01-24 11:06:58.718118: step: 328/530, loss: 0.0027387484442442656
2023-01-24 11:06:59.813196: step: 332/530, loss: 0.001112161437049508
2023-01-24 11:07:00.917483: step: 336/530, loss: 0.0007506462861783803
2023-01-24 11:07:02.026350: step: 340/530, loss: 0.0001530869340058416
2023-01-24 11:07:03.101635: step: 344/530, loss: 0.00020024762488901615
2023-01-24 11:07:04.179847: step: 348/530, loss: 0.0019760737195611
2023-01-24 11:07:05.283323: step: 352/530, loss: 0.0029700316954404116
2023-01-24 11:07:06.383586: step: 356/530, loss: 0.00216482556425035
2023-01-24 11:07:07.461771: step: 360/530, loss: 0.0017006483394652605
2023-01-24 11:07:08.567169: step: 364/530, loss: 6.0551388742169365e-05
2023-01-24 11:07:09.657352: step: 368/530, loss: 0.0011895173229277134
2023-01-24 11:07:10.743027: step: 372/530, loss: 0.00020171467622276396
2023-01-24 11:07:11.837807: step: 376/530, loss: 0.015934865921735764
2023-01-24 11:07:12.940064: step: 380/530, loss: 0.0032380190677940845
2023-01-24 11:07:14.028794: step: 384/530, loss: 0.0030422040726989508
2023-01-24 11:07:15.130725: step: 388/530, loss: 0.0017841702792793512
2023-01-24 11:07:16.246160: step: 392/530, loss: 9.812969801714644e-05
2023-01-24 11:07:17.330522: step: 396/530, loss: 0.019144121557474136
2023-01-24 11:07:18.413741: step: 400/530, loss: 2.2069940314395353e-05
2023-01-24 11:07:19.516438: step: 404/530, loss: 0.005186447408050299
2023-01-24 11:07:20.605745: step: 408/530, loss: 0.0006216090405359864
2023-01-24 11:07:21.690469: step: 412/530, loss: 0.0024480412248522043
2023-01-24 11:07:22.783162: step: 416/530, loss: 2.526305615901947e-05
2023-01-24 11:07:23.843229: step: 420/530, loss: 0.0002451435138937086
2023-01-24 11:07:24.923499: step: 424/530, loss: 0.00018999732856173068
2023-01-24 11:07:26.017697: step: 428/530, loss: 0.00024223285436164588
2023-01-24 11:07:27.097158: step: 432/530, loss: 0.00017848741845227778
2023-01-24 11:07:28.185678: step: 436/530, loss: 8.253068517660722e-05
2023-01-24 11:07:29.297133: step: 440/530, loss: 8.181794692063704e-05
2023-01-24 11:07:30.414302: step: 444/530, loss: 0.0002570562355685979
2023-01-24 11:07:31.517671: step: 448/530, loss: 0.006813338026404381
2023-01-24 11:07:32.610061: step: 452/530, loss: 0.0002035939833149314
2023-01-24 11:07:33.694915: step: 456/530, loss: 9.507857612334192e-05
2023-01-24 11:07:34.767514: step: 460/530, loss: 0.000119017917313613
2023-01-24 11:07:35.854355: step: 464/530, loss: 0.012260710820555687
2023-01-24 11:07:36.928795: step: 468/530, loss: 0.0008721818448975682
2023-01-24 11:07:38.015184: step: 472/530, loss: 0.003999961540102959
2023-01-24 11:07:39.095329: step: 476/530, loss: 0.0023704753257334232
2023-01-24 11:07:40.171876: step: 480/530, loss: 0.0006542131886817515
2023-01-24 11:07:41.262189: step: 484/530, loss: 0.0005305339582264423
2023-01-24 11:07:42.376369: step: 488/530, loss: 0.000548834796063602
2023-01-24 11:07:43.458400: step: 492/530, loss: 9.316128125647083e-05
2023-01-24 11:07:44.535206: step: 496/530, loss: 0.0001876260939752683
2023-01-24 11:07:45.638427: step: 500/530, loss: 0.00029482279205694795
2023-01-24 11:07:46.708444: step: 504/530, loss: 0.0027160996105521917
2023-01-24 11:07:47.814424: step: 508/530, loss: 0.004169796593487263
2023-01-24 11:07:48.920628: step: 512/530, loss: 0.00419542146846652
2023-01-24 11:07:50.024477: step: 516/530, loss: 0.001662172027863562
2023-01-24 11:07:51.109654: step: 520/530, loss: 0.005924543831497431
2023-01-24 11:07:52.201338: step: 524/530, loss: 0.0092924814671278
2023-01-24 11:07:53.289993: step: 528/530, loss: 0.0023686615750193596
2023-01-24 11:07:54.379902: step: 532/530, loss: 5.9015434089815244e-05
2023-01-24 11:07:55.518667: step: 536/530, loss: 0.0017717560986056924
2023-01-24 11:07:56.612777: step: 540/530, loss: 1.6681902707205154e-05
2023-01-24 11:07:57.720332: step: 544/530, loss: 0.00023030232114251703
2023-01-24 11:07:58.819079: step: 548/530, loss: 0.0010691189672797918
2023-01-24 11:07:59.913460: step: 552/530, loss: 7.2947092121467e-05
2023-01-24 11:08:01.018702: step: 556/530, loss: 2.7744817998609506e-06
2023-01-24 11:08:02.132585: step: 560/530, loss: 0.005825372412800789
2023-01-24 11:08:03.225891: step: 564/530, loss: 0.0008699214085936546
2023-01-24 11:08:04.307130: step: 568/530, loss: 0.001545156235806644
2023-01-24 11:08:05.410489: step: 572/530, loss: 0.0002815865445882082
2023-01-24 11:08:06.489903: step: 576/530, loss: 0.00023228765348903835
2023-01-24 11:08:07.566645: step: 580/530, loss: 0.0028442859183996916
2023-01-24 11:08:08.688471: step: 584/530, loss: 0.0023350215051323175
2023-01-24 11:08:09.780327: step: 588/530, loss: 0.0016820277087390423
2023-01-24 11:08:10.865800: step: 592/530, loss: 0.0029673816170543432
2023-01-24 11:08:11.976382: step: 596/530, loss: 0.007681077811866999
2023-01-24 11:08:13.085794: step: 600/530, loss: 0.0013397708535194397
2023-01-24 11:08:14.193932: step: 604/530, loss: 0.009949568659067154
2023-01-24 11:08:15.283916: step: 608/530, loss: 0.0012124726781621575
2023-01-24 11:08:16.377473: step: 612/530, loss: 0.0006463738391175866
2023-01-24 11:08:17.481664: step: 616/530, loss: 0.0006983615458011627
2023-01-24 11:08:18.572450: step: 620/530, loss: 0.0014640305889770389
2023-01-24 11:08:19.665143: step: 624/530, loss: 0.009332627058029175
2023-01-24 11:08:20.756796: step: 628/530, loss: 0.005885405000299215
2023-01-24 11:08:21.834685: step: 632/530, loss: 0.00014350692799780518
2023-01-24 11:08:22.914984: step: 636/530, loss: 0.008285566233098507
2023-01-24 11:08:24.000502: step: 640/530, loss: 0.0022046321537345648
2023-01-24 11:08:25.079707: step: 644/530, loss: 0.0009495335398241878
2023-01-24 11:08:26.154917: step: 648/530, loss: 0.0006517135188914835
2023-01-24 11:08:27.244978: step: 652/530, loss: 0.00010133364412467927
2023-01-24 11:08:28.342742: step: 656/530, loss: 0.0028543220832943916
2023-01-24 11:08:29.437475: step: 660/530, loss: 0.0031247297301888466
2023-01-24 11:08:30.521589: step: 664/530, loss: 0.003758001606911421
2023-01-24 11:08:31.635294: step: 668/530, loss: 0.0018406884046271443
2023-01-24 11:08:32.737950: step: 672/530, loss: 0.0063645802438259125
2023-01-24 11:08:33.827964: step: 676/530, loss: 0.0034332971554249525
2023-01-24 11:08:34.939307: step: 680/530, loss: 0.009605745784938335
2023-01-24 11:08:36.038242: step: 684/530, loss: 0.00012636395695153624
2023-01-24 11:08:37.139648: step: 688/530, loss: 0.0013792074751108885
2023-01-24 11:08:38.216634: step: 692/530, loss: 0.0034518863540142775
2023-01-24 11:08:39.334855: step: 696/530, loss: 0.0015571805415675044
2023-01-24 11:08:40.424528: step: 700/530, loss: 0.002138337818905711
2023-01-24 11:08:41.517018: step: 704/530, loss: 0.0003091080579906702
2023-01-24 11:08:42.614430: step: 708/530, loss: 0.0021379266399890184
2023-01-24 11:08:43.699791: step: 712/530, loss: 0.0001398646563757211
2023-01-24 11:08:44.781422: step: 716/530, loss: 0.0006683410611003637
2023-01-24 11:08:45.891424: step: 720/530, loss: 0.0028443525079637766
2023-01-24 11:08:46.975500: step: 724/530, loss: 0.014140930958092213
2023-01-24 11:08:48.049891: step: 728/530, loss: 6.861837755423039e-05
2023-01-24 11:08:49.149853: step: 732/530, loss: 0.006302974186837673
2023-01-24 11:08:50.238913: step: 736/530, loss: 8.41275614220649e-05
2023-01-24 11:08:51.332274: step: 740/530, loss: 0.0009295594063587487
2023-01-24 11:08:52.439635: step: 744/530, loss: 5.107237370793882e-07
2023-01-24 11:08:53.539295: step: 748/530, loss: 0.017124244943261147
2023-01-24 11:08:54.629267: step: 752/530, loss: 0.0032133159693330526
2023-01-24 11:08:55.724752: step: 756/530, loss: 0.000350703252479434
2023-01-24 11:08:56.841449: step: 760/530, loss: 0.0019325226312503219
2023-01-24 11:08:57.937686: step: 764/530, loss: 1.0375431884313002e-05
2023-01-24 11:08:59.042938: step: 768/530, loss: 0.003244813997298479
2023-01-24 11:09:00.121443: step: 772/530, loss: 0.0023170344065874815
2023-01-24 11:09:01.198356: step: 776/530, loss: 0.0005471422919072211
2023-01-24 11:09:02.268324: step: 780/530, loss: 1.1085880032624118e-05
2023-01-24 11:09:03.350292: step: 784/530, loss: 0.000662175239995122
2023-01-24 11:09:04.435002: step: 788/530, loss: 0.0012159064644947648
2023-01-24 11:09:05.514939: step: 792/530, loss: 0.0001026913887471892
2023-01-24 11:09:06.605205: step: 796/530, loss: 0.00013545122055802494
2023-01-24 11:09:07.693006: step: 800/530, loss: 0.00039481211570091546
2023-01-24 11:09:08.764668: step: 804/530, loss: 1.8506450942368247e-05
2023-01-24 11:09:09.849855: step: 808/530, loss: 0.0007518731872551143
2023-01-24 11:09:10.949535: step: 812/530, loss: 0.005355015397071838
2023-01-24 11:09:12.071911: step: 816/530, loss: 0.009262152016162872
2023-01-24 11:09:13.162242: step: 820/530, loss: 0.002548203570768237
2023-01-24 11:09:14.268770: step: 824/530, loss: 0.002876387210562825
2023-01-24 11:09:15.372589: step: 828/530, loss: 0.0020748015958815813
2023-01-24 11:09:16.459629: step: 832/530, loss: 0.0003181732026860118
2023-01-24 11:09:17.553855: step: 836/530, loss: 0.002926662564277649
2023-01-24 11:09:18.632130: step: 840/530, loss: 0.0003673312603496015
2023-01-24 11:09:19.708788: step: 844/530, loss: 0.0016110616270452738
2023-01-24 11:09:20.789866: step: 848/530, loss: 0.0030272037256509066
2023-01-24 11:09:21.885461: step: 852/530, loss: 0.003720643697306514
2023-01-24 11:09:23.009160: step: 856/530, loss: 0.003420489374548197
2023-01-24 11:09:24.116688: step: 860/530, loss: 0.000681612640619278
2023-01-24 11:09:25.192940: step: 864/530, loss: 0.0010235266527161002
2023-01-24 11:09:26.294661: step: 868/530, loss: 1.1331835594319273e-06
2023-01-24 11:09:27.372958: step: 872/530, loss: 0.008483139798045158
2023-01-24 11:09:28.461794: step: 876/530, loss: 0.0013104387326166034
2023-01-24 11:09:29.569436: step: 880/530, loss: 0.0011970880441367626
2023-01-24 11:09:30.648638: step: 884/530, loss: 6.7724345171882305e-06
2023-01-24 11:09:31.714508: step: 888/530, loss: 0.001854976057074964
2023-01-24 11:09:32.801838: step: 892/530, loss: 2.076085911539849e-05
2023-01-24 11:09:33.936192: step: 896/530, loss: 0.00039890181506052613
2023-01-24 11:09:35.018381: step: 900/530, loss: 0.0029576276428997517
2023-01-24 11:09:36.084349: step: 904/530, loss: 0.00693677319213748
2023-01-24 11:09:37.161480: step: 908/530, loss: 6.96541610523127e-05
2023-01-24 11:09:38.233406: step: 912/530, loss: 0.003066401928663254
2023-01-24 11:09:39.308687: step: 916/530, loss: 0.0022195763885974884
2023-01-24 11:09:40.403881: step: 920/530, loss: 0.006827932316809893
2023-01-24 11:09:41.503602: step: 924/530, loss: 0.0006443933816626668
2023-01-24 11:09:42.590500: step: 928/530, loss: 0.0010862374911084771
2023-01-24 11:09:43.674659: step: 932/530, loss: 0.001978747546672821
2023-01-24 11:09:44.767649: step: 936/530, loss: 0.0017067306907847524
2023-01-24 11:09:45.849270: step: 940/530, loss: 0.0002453155757393688
2023-01-24 11:09:46.949195: step: 944/530, loss: 0.0022631175816059113
2023-01-24 11:09:48.024130: step: 948/530, loss: 0.01073909830302
2023-01-24 11:09:49.103101: step: 952/530, loss: 2.1372539777075872e-05
2023-01-24 11:09:50.198065: step: 956/530, loss: 0.0018166899681091309
2023-01-24 11:09:51.305294: step: 960/530, loss: 0.0018802545964717865
2023-01-24 11:09:52.404566: step: 964/530, loss: 0.00030414227512665093
2023-01-24 11:09:53.495962: step: 968/530, loss: 0.049407340586185455
2023-01-24 11:09:54.594999: step: 972/530, loss: 0.002354665659368038
2023-01-24 11:09:55.673730: step: 976/530, loss: 0.0006467264611274004
2023-01-24 11:09:56.784805: step: 980/530, loss: 0.0002191751846112311
2023-01-24 11:09:57.868754: step: 984/530, loss: 1.0901581845246255e-05
2023-01-24 11:09:58.967112: step: 988/530, loss: 0.010003658942878246
2023-01-24 11:10:00.057667: step: 992/530, loss: 0.0028742491267621517
2023-01-24 11:10:01.168311: step: 996/530, loss: 0.003459608880802989
2023-01-24 11:10:02.265512: step: 1000/530, loss: 0.009734617546200752
2023-01-24 11:10:03.341655: step: 1004/530, loss: 0.004015708342194557
2023-01-24 11:10:04.429792: step: 1008/530, loss: 0.003532921662554145
2023-01-24 11:10:05.511657: step: 1012/530, loss: 0.005811508744955063
2023-01-24 11:10:06.611660: step: 1016/530, loss: 0.00032728290534578264
2023-01-24 11:10:07.710312: step: 1020/530, loss: 0.005041017197072506
2023-01-24 11:10:08.800245: step: 1024/530, loss: 0.000962086021900177
2023-01-24 11:10:09.900661: step: 1028/530, loss: 0.0015051723457872868
2023-01-24 11:10:10.994575: step: 1032/530, loss: 0.004779349081218243
2023-01-24 11:10:12.075888: step: 1036/530, loss: 0.0036869365721940994
2023-01-24 11:10:13.180074: step: 1040/530, loss: 0.004515713546425104
2023-01-24 11:10:14.277474: step: 1044/530, loss: 0.003777437610551715
2023-01-24 11:10:15.365943: step: 1048/530, loss: 0.033518899232149124
2023-01-24 11:10:16.425993: step: 1052/530, loss: 0.011628029868006706
2023-01-24 11:10:17.537347: step: 1056/530, loss: 0.0055001419968903065
2023-01-24 11:10:18.633390: step: 1060/530, loss: 0.00013690949708689004
2023-01-24 11:10:19.693581: step: 1064/530, loss: 0.00268448400311172
2023-01-24 11:10:20.772900: step: 1068/530, loss: 0.0015796461375430226
2023-01-24 11:10:21.870958: step: 1072/530, loss: 0.00010647771705407649
2023-01-24 11:10:22.968925: step: 1076/530, loss: 0.0041709779761731625
2023-01-24 11:10:24.068494: step: 1080/530, loss: 0.006433352828025818
2023-01-24 11:10:25.172171: step: 1084/530, loss: 0.007411969359964132
2023-01-24 11:10:26.271279: step: 1088/530, loss: 0.005055057816207409
2023-01-24 11:10:27.378327: step: 1092/530, loss: 0.0061180428601801395
2023-01-24 11:10:28.512780: step: 1096/530, loss: 0.0036884101573377848
2023-01-24 11:10:29.599120: step: 1100/530, loss: 0.003087639342993498
2023-01-24 11:10:30.718859: step: 1104/530, loss: 0.0006503356853500009
2023-01-24 11:10:31.794578: step: 1108/530, loss: 0.0012748206499963999
2023-01-24 11:10:32.879318: step: 1112/530, loss: 0.015659553930163383
2023-01-24 11:10:33.948296: step: 1116/530, loss: 0.00022522902872879058
2023-01-24 11:10:35.034712: step: 1120/530, loss: 0.00029547931626439095
2023-01-24 11:10:36.120591: step: 1124/530, loss: 0.00232200906611979
2023-01-24 11:10:37.207235: step: 1128/530, loss: 0.0037394037935882807
2023-01-24 11:10:38.288586: step: 1132/530, loss: 0.00022217437799554318
2023-01-24 11:10:39.380309: step: 1136/530, loss: 0.002667974680662155
2023-01-24 11:10:40.484767: step: 1140/530, loss: 6.199646304594353e-05
2023-01-24 11:10:41.570207: step: 1144/530, loss: 0.005206217523664236
2023-01-24 11:10:42.659409: step: 1148/530, loss: 0.0010839808965101838
2023-01-24 11:10:43.755520: step: 1152/530, loss: 0.0003359429829288274
2023-01-24 11:10:44.829534: step: 1156/530, loss: 0.0031326801981776953
2023-01-24 11:10:45.933004: step: 1160/530, loss: 0.0006840827991254628
2023-01-24 11:10:47.031755: step: 1164/530, loss: 5.298924588714726e-05
2023-01-24 11:10:48.102149: step: 1168/530, loss: 0.00036467472091317177
2023-01-24 11:10:49.186133: step: 1172/530, loss: 0.0008015702478587627
2023-01-24 11:10:50.280126: step: 1176/530, loss: 0.001813840470276773
2023-01-24 11:10:51.371518: step: 1180/530, loss: 0.004003350622951984
2023-01-24 11:10:52.463592: step: 1184/530, loss: 3.4948625398101285e-05
2023-01-24 11:10:53.560047: step: 1188/530, loss: 0.001791725168004632
2023-01-24 11:10:54.652376: step: 1192/530, loss: 0.0007922702352516353
2023-01-24 11:10:55.748838: step: 1196/530, loss: 0.15773484110832214
2023-01-24 11:10:56.833835: step: 1200/530, loss: 0.0003773942880798131
2023-01-24 11:10:57.905075: step: 1204/530, loss: 0.002099961508065462
2023-01-24 11:10:58.995081: step: 1208/530, loss: 9.61387122515589e-05
2023-01-24 11:11:00.103518: step: 1212/530, loss: 0.007378213107585907
2023-01-24 11:11:01.221177: step: 1216/530, loss: 0.012547855265438557
2023-01-24 11:11:02.310559: step: 1220/530, loss: 0.003913717810064554
2023-01-24 11:11:03.411970: step: 1224/530, loss: 0.0003519150777719915
2023-01-24 11:11:04.526229: step: 1228/530, loss: 0.005848758388310671
2023-01-24 11:11:05.627306: step: 1232/530, loss: 0.0011302847415208817
2023-01-24 11:11:06.707294: step: 1236/530, loss: 0.00032962014665827155
2023-01-24 11:11:07.812396: step: 1240/530, loss: 0.0030261704232543707
2023-01-24 11:11:08.905072: step: 1244/530, loss: 0.011049726977944374
2023-01-24 11:11:10.016258: step: 1248/530, loss: 0.00032516149803996086
2023-01-24 11:11:11.102787: step: 1252/530, loss: 0.0026952135376632214
2023-01-24 11:11:12.169348: step: 1256/530, loss: 0.004448683466762304
2023-01-24 11:11:13.256507: step: 1260/530, loss: 0.004877091385424137
2023-01-24 11:11:14.330823: step: 1264/530, loss: 0.0021662248764187098
2023-01-24 11:11:15.389222: step: 1268/530, loss: 5.9905862144660205e-05
2023-01-24 11:11:16.480453: step: 1272/530, loss: 9.155741764743652e-08
2023-01-24 11:11:17.582300: step: 1276/530, loss: 0.0010946731781587005
2023-01-24 11:11:18.667331: step: 1280/530, loss: 0.0028232859913259745
2023-01-24 11:11:19.759219: step: 1284/530, loss: 1.7036798453773372e-05
2023-01-24 11:11:20.842784: step: 1288/530, loss: 0.0023632789961993694
2023-01-24 11:11:21.915704: step: 1292/530, loss: 0.0003779674007091671
2023-01-24 11:11:23.021579: step: 1296/530, loss: 0.00283479574136436
2023-01-24 11:11:24.100617: step: 1300/530, loss: 0.0018201533239334822
2023-01-24 11:11:25.187350: step: 1304/530, loss: 0.0012148297391831875
2023-01-24 11:11:26.278422: step: 1308/530, loss: 0.002993691945448518
2023-01-24 11:11:27.378412: step: 1312/530, loss: 0.00023005179536994547
2023-01-24 11:11:28.452141: step: 1316/530, loss: 0.0011218771105632186
2023-01-24 11:11:29.572293: step: 1320/530, loss: 0.021919548511505127
2023-01-24 11:11:30.651527: step: 1324/530, loss: 0.004026548471301794
2023-01-24 11:11:31.734182: step: 1328/530, loss: 0.00016143418906722218
2023-01-24 11:11:32.832618: step: 1332/530, loss: 4.627986811556184e-07
2023-01-24 11:11:33.930204: step: 1336/530, loss: 0.0022843223996460438
2023-01-24 11:11:35.037807: step: 1340/530, loss: 1.7791131540434435e-05
2023-01-24 11:11:36.133110: step: 1344/530, loss: 0.00043966970406472683
2023-01-24 11:11:37.200314: step: 1348/530, loss: 2.274669668622664e-06
2023-01-24 11:11:38.304892: step: 1352/530, loss: 0.0002892041520681232
2023-01-24 11:11:39.401217: step: 1356/530, loss: 0.010213593952357769
2023-01-24 11:11:40.495411: step: 1360/530, loss: 0.0008568572229705751
2023-01-24 11:11:41.590956: step: 1364/530, loss: 0.0035403133369982243
2023-01-24 11:11:42.680168: step: 1368/530, loss: 3.521113467286341e-05
2023-01-24 11:11:43.753796: step: 1372/530, loss: 0.0009181509376503527
2023-01-24 11:11:44.847440: step: 1376/530, loss: 1.4798672054894269e-05
2023-01-24 11:11:45.924777: step: 1380/530, loss: 0.0009366365848109126
2023-01-24 11:11:47.030847: step: 1384/530, loss: 0.004516437649726868
2023-01-24 11:11:48.113058: step: 1388/530, loss: 4.533562605502084e-05
2023-01-24 11:11:49.205112: step: 1392/530, loss: 0.004407972097396851
2023-01-24 11:11:50.279224: step: 1396/530, loss: 0.0036491043865680695
2023-01-24 11:11:51.390980: step: 1400/530, loss: 0.0002919454127550125
2023-01-24 11:11:52.467898: step: 1404/530, loss: 7.566505519207567e-05
2023-01-24 11:11:53.570192: step: 1408/530, loss: 0.0027953805401921272
2023-01-24 11:11:54.657725: step: 1412/530, loss: 0.0008610638324171305
2023-01-24 11:11:55.740845: step: 1416/530, loss: 0.00381405814550817
2023-01-24 11:11:56.831738: step: 1420/530, loss: 0.0026882088277488947
2023-01-24 11:11:57.921306: step: 1424/530, loss: 0.0
2023-01-24 11:11:59.004410: step: 1428/530, loss: 0.0005442898836918175
2023-01-24 11:12:00.095759: step: 1432/530, loss: 6.463371391873807e-05
2023-01-24 11:12:01.186735: step: 1436/530, loss: 0.000184837932465598
2023-01-24 11:12:02.276858: step: 1440/530, loss: 0.009980302304029465
2023-01-24 11:12:03.364032: step: 1444/530, loss: 0.00011968673788942397
2023-01-24 11:12:04.454849: step: 1448/530, loss: 0.00013466255040839314
2023-01-24 11:12:05.553365: step: 1452/530, loss: 0.00279190088622272
2023-01-24 11:12:06.672106: step: 1456/530, loss: 0.006928619928658009
2023-01-24 11:12:07.736624: step: 1460/530, loss: 9.136817311627965e-07
2023-01-24 11:12:08.834739: step: 1464/530, loss: 0.0032755162101238966
2023-01-24 11:12:09.941331: step: 1468/530, loss: 0.0009578948956914246
2023-01-24 11:12:11.054859: step: 1472/530, loss: 0.004956020042300224
2023-01-24 11:12:12.141902: step: 1476/530, loss: 0.0014834189787507057
2023-01-24 11:12:13.221560: step: 1480/530, loss: 0.002009877236559987
2023-01-24 11:12:14.324719: step: 1484/530, loss: 0.0029133677016943693
2023-01-24 11:12:15.424286: step: 1488/530, loss: 0.020586330443620682
2023-01-24 11:12:16.503056: step: 1492/530, loss: 0.0013607380678877234
2023-01-24 11:12:17.588589: step: 1496/530, loss: 0.0030814907513558865
2023-01-24 11:12:18.668757: step: 1500/530, loss: 0.002972833812236786
2023-01-24 11:12:19.751119: step: 1504/530, loss: 0.0015024917665868998
2023-01-24 11:12:20.835469: step: 1508/530, loss: 0.0028529074043035507
2023-01-24 11:12:21.919335: step: 1512/530, loss: 0.002402563113719225
2023-01-24 11:12:22.986601: step: 1516/530, loss: 9.545624197926372e-05
2023-01-24 11:12:24.101685: step: 1520/530, loss: 0.0005605558399111032
2023-01-24 11:12:25.186411: step: 1524/530, loss: 0.002436092123389244
2023-01-24 11:12:26.286308: step: 1528/530, loss: 0.039780210703611374
2023-01-24 11:12:27.361129: step: 1532/530, loss: 0.0001810369867598638
2023-01-24 11:12:28.461618: step: 1536/530, loss: 0.0003175641468260437
2023-01-24 11:12:29.539029: step: 1540/530, loss: 8.467099519293697e-07
2023-01-24 11:12:30.641992: step: 1544/530, loss: 0.000988020095974207
2023-01-24 11:12:31.748724: step: 1548/530, loss: 0.004215283785015345
2023-01-24 11:12:32.822892: step: 1552/530, loss: 1.9923118088627234e-06
2023-01-24 11:12:33.913084: step: 1556/530, loss: 0.0009153741411864758
2023-01-24 11:12:35.004799: step: 1560/530, loss: 0.0030492425430566072
2023-01-24 11:12:36.101477: step: 1564/530, loss: 1.3904646039009094e-06
2023-01-24 11:12:37.206617: step: 1568/530, loss: 0.0020644599571824074
2023-01-24 11:12:38.292507: step: 1572/530, loss: 0.000401181896449998
2023-01-24 11:12:39.364544: step: 1576/530, loss: 0.0018996200524270535
2023-01-24 11:12:40.442630: step: 1580/530, loss: 0.003534716786816716
2023-01-24 11:12:41.523654: step: 1584/530, loss: 6.729322922183201e-05
2023-01-24 11:12:42.610324: step: 1588/530, loss: 0.003328819992020726
2023-01-24 11:12:43.687842: step: 1592/530, loss: 0.04004179313778877
2023-01-24 11:12:44.786245: step: 1596/530, loss: 0.010661550797522068
2023-01-24 11:12:45.860906: step: 1600/530, loss: 0.0017881629755720496
2023-01-24 11:12:46.923580: step: 1604/530, loss: 0.0039047240279614925
2023-01-24 11:12:48.034773: step: 1608/530, loss: 3.2011335861170664e-05
2023-01-24 11:12:49.150658: step: 1612/530, loss: 0.00015045386680867523
2023-01-24 11:12:50.240865: step: 1616/530, loss: 4.442041245056316e-05
2023-01-24 11:12:51.327657: step: 1620/530, loss: 5.109552603244083e-06
2023-01-24 11:12:52.416109: step: 1624/530, loss: 0.0009275132906623185
2023-01-24 11:12:53.507367: step: 1628/530, loss: 0.0034423477482050657
2023-01-24 11:12:54.585873: step: 1632/530, loss: 0.0028966316021978855
2023-01-24 11:12:55.665210: step: 1636/530, loss: 0.000514811894390732
2023-01-24 11:12:56.751333: step: 1640/530, loss: 0.0007470088894478977
2023-01-24 11:12:57.852880: step: 1644/530, loss: 0.008726184256374836
2023-01-24 11:12:58.924834: step: 1648/530, loss: 0.00019980079378001392
2023-01-24 11:13:00.036197: step: 1652/530, loss: 0.006958498619496822
2023-01-24 11:13:01.127737: step: 1656/530, loss: 0.002085222862660885
2023-01-24 11:13:02.219067: step: 1660/530, loss: 0.001445403671823442
2023-01-24 11:13:03.330476: step: 1664/530, loss: 0.0021974630653858185
2023-01-24 11:13:04.398598: step: 1668/530, loss: 0.0
2023-01-24 11:13:05.496336: step: 1672/530, loss: 0.012715769000351429
2023-01-24 11:13:06.601144: step: 1676/530, loss: 0.003582859179005027
2023-01-24 11:13:07.692033: step: 1680/530, loss: 0.005014185793697834
2023-01-24 11:13:08.762190: step: 1684/530, loss: 0.00012731069000437856
2023-01-24 11:13:09.844581: step: 1688/530, loss: 0.007671989034861326
2023-01-24 11:13:10.946849: step: 1692/530, loss: 3.5964432754553854e-05
2023-01-24 11:13:12.042409: step: 1696/530, loss: 2.128567393810954e-05
2023-01-24 11:13:13.166401: step: 1700/530, loss: 0.0025053133722394705
2023-01-24 11:13:14.270003: step: 1704/530, loss: 0.005780582781881094
2023-01-24 11:13:15.363211: step: 1708/530, loss: 0.001596905873157084
2023-01-24 11:13:16.442128: step: 1712/530, loss: 1.1687239748425782e-05
2023-01-24 11:13:17.561552: step: 1716/530, loss: 0.008107785135507584
2023-01-24 11:13:18.635343: step: 1720/530, loss: 0.0016066232929006219
2023-01-24 11:13:19.710826: step: 1724/530, loss: 6.309814125415869e-06
2023-01-24 11:13:20.805722: step: 1728/530, loss: 9.108841186389327e-05
2023-01-24 11:13:21.898739: step: 1732/530, loss: 1.4966180970077403e-05
2023-01-24 11:13:22.979770: step: 1736/530, loss: 0.00019453787535894662
2023-01-24 11:13:24.039801: step: 1740/530, loss: 0.0001246624015038833
2023-01-24 11:13:25.129605: step: 1744/530, loss: 0.005154330749064684
2023-01-24 11:13:26.226203: step: 1748/530, loss: 0.00010170163295697421
2023-01-24 11:13:27.313541: step: 1752/530, loss: 0.0018698968924582005
2023-01-24 11:13:28.385369: step: 1756/530, loss: 6.83599864714779e-05
2023-01-24 11:13:29.482482: step: 1760/530, loss: 0.008800136856734753
2023-01-24 11:13:30.571227: step: 1764/530, loss: 0.0049568661488592625
2023-01-24 11:13:31.657924: step: 1768/530, loss: 0.0018267015693709254
2023-01-24 11:13:32.761227: step: 1772/530, loss: 0.005369527265429497
2023-01-24 11:13:33.845158: step: 1776/530, loss: 0.00037364373565651476
2023-01-24 11:13:34.950177: step: 1780/530, loss: 0.0002443153935018927
2023-01-24 11:13:36.045304: step: 1784/530, loss: 0.0006877300911583006
2023-01-24 11:13:37.143353: step: 1788/530, loss: 0.018640106543898582
2023-01-24 11:13:38.255399: step: 1792/530, loss: 0.002196121495217085
2023-01-24 11:13:39.329624: step: 1796/530, loss: 2.3374448119284352e-06
2023-01-24 11:13:40.424325: step: 1800/530, loss: 0.0038667176850140095
2023-01-24 11:13:41.516843: step: 1804/530, loss: 0.0031091426499187946
2023-01-24 11:13:42.638697: step: 1808/530, loss: 0.0022826758213341236
2023-01-24 11:13:43.722368: step: 1812/530, loss: 0.009245526976883411
2023-01-24 11:13:44.808998: step: 1816/530, loss: 0.00012097950821043923
2023-01-24 11:13:45.897392: step: 1820/530, loss: 5.00375208503101e-05
2023-01-24 11:13:46.975368: step: 1824/530, loss: 0.00012188960681669414
2023-01-24 11:13:48.069639: step: 1828/530, loss: 0.00023899287043605
2023-01-24 11:13:49.174230: step: 1832/530, loss: 0.0010847916128113866
2023-01-24 11:13:50.257545: step: 1836/530, loss: 0.0029559554532170296
2023-01-24 11:13:51.355830: step: 1840/530, loss: 0.00029525961144827306
2023-01-24 11:13:52.477469: step: 1844/530, loss: 0.006062031257897615
2023-01-24 11:13:53.580736: step: 1848/530, loss: 0.0027633002027869225
2023-01-24 11:13:54.684931: step: 1852/530, loss: 0.005294295493513346
2023-01-24 11:13:55.788751: step: 1856/530, loss: 0.0035847793333232403
2023-01-24 11:13:56.897636: step: 1860/530, loss: 0.000911436160095036
2023-01-24 11:13:57.976256: step: 1864/530, loss: 5.170115036889911e-05
2023-01-24 11:13:59.070126: step: 1868/530, loss: 0.0066793388687074184
2023-01-24 11:14:00.140003: step: 1872/530, loss: 0.001877503120340407
2023-01-24 11:14:01.243853: step: 1876/530, loss: 0.002873568329960108
2023-01-24 11:14:02.310524: step: 1880/530, loss: 0.0007109367288649082
2023-01-24 11:14:03.382870: step: 1884/530, loss: 0.0017746200319379568
2023-01-24 11:14:04.465830: step: 1888/530, loss: 0.02019747719168663
2023-01-24 11:14:05.532608: step: 1892/530, loss: 0.004764596465975046
2023-01-24 11:14:06.640230: step: 1896/530, loss: 0.012391520664095879
2023-01-24 11:14:07.719164: step: 1900/530, loss: 0.0039004029240459204
2023-01-24 11:14:08.851367: step: 1904/530, loss: 0.010178638622164726
2023-01-24 11:14:09.915976: step: 1908/530, loss: 0.005706189200282097
2023-01-24 11:14:11.016412: step: 1912/530, loss: 0.006951368413865566
2023-01-24 11:14:12.107134: step: 1916/530, loss: 0.009065288119018078
2023-01-24 11:14:13.193541: step: 1920/530, loss: 2.1797888621222228e-05
2023-01-24 11:14:14.282621: step: 1924/530, loss: 0.005138007458299398
2023-01-24 11:14:15.384461: step: 1928/530, loss: 0.018205001950263977
2023-01-24 11:14:16.468385: step: 1932/530, loss: 0.0029143067076802254
2023-01-24 11:14:17.566410: step: 1936/530, loss: 0.0014819448115304112
2023-01-24 11:14:18.657680: step: 1940/530, loss: 0.00012170481204520911
2023-01-24 11:14:19.764025: step: 1944/530, loss: 0.013513009063899517
2023-01-24 11:14:20.835521: step: 1948/530, loss: 0.0028930676635354757
2023-01-24 11:14:21.906842: step: 1952/530, loss: 0.002232213271781802
2023-01-24 11:14:23.000661: step: 1956/530, loss: 0.004743141587823629
2023-01-24 11:14:24.096934: step: 1960/530, loss: 0.004425340332090855
2023-01-24 11:14:25.197236: step: 1964/530, loss: 0.00034303279244340956
2023-01-24 11:14:26.290631: step: 1968/530, loss: 0.008089178241789341
2023-01-24 11:14:27.400219: step: 1972/530, loss: 0.0010775779373943806
2023-01-24 11:14:28.488609: step: 1976/530, loss: 0.0030615869909524918
2023-01-24 11:14:29.567594: step: 1980/530, loss: 1.655684478407693e-10
2023-01-24 11:14:30.704791: step: 1984/530, loss: 3.54763978975825e-05
2023-01-24 11:14:31.806510: step: 1988/530, loss: 5.670629252563231e-05
2023-01-24 11:14:32.880098: step: 1992/530, loss: 0.006418494042009115
2023-01-24 11:14:33.965012: step: 1996/530, loss: 0.006443052552640438
2023-01-24 11:14:35.036233: step: 2000/530, loss: 0.00046917388681322336
2023-01-24 11:14:36.146328: step: 2004/530, loss: 0.010000565089285374
2023-01-24 11:14:37.253467: step: 2008/530, loss: 0.001778299454599619
2023-01-24 11:14:38.328083: step: 2012/530, loss: 0.0016366541385650635
2023-01-24 11:14:39.405179: step: 2016/530, loss: 0.0017698848387226462
2023-01-24 11:14:40.503754: step: 2020/530, loss: 5.0431299314368516e-05
2023-01-24 11:14:41.563523: step: 2024/530, loss: 1.473018892284017e-05
2023-01-24 11:14:42.660499: step: 2028/530, loss: 0.0054372879676520824
2023-01-24 11:14:43.747462: step: 2032/530, loss: 0.013245935551822186
2023-01-24 11:14:44.834345: step: 2036/530, loss: 0.008621656335890293
2023-01-24 11:14:45.917454: step: 2040/530, loss: 0.0005633449763990939
2023-01-24 11:14:47.003531: step: 2044/530, loss: 0.0005284935468807817
2023-01-24 11:14:48.105644: step: 2048/530, loss: 0.007640881463885307
2023-01-24 11:14:49.189741: step: 2052/530, loss: 0.0004758746363222599
2023-01-24 11:14:50.298516: step: 2056/530, loss: 0.0018036675173789263
2023-01-24 11:14:51.378823: step: 2060/530, loss: 0.001490497961640358
2023-01-24 11:14:52.463567: step: 2064/530, loss: 0.004089886322617531
2023-01-24 11:14:53.540577: step: 2068/530, loss: 0.005039777606725693
2023-01-24 11:14:54.637571: step: 2072/530, loss: 0.0077629066072404385
2023-01-24 11:14:55.709180: step: 2076/530, loss: 0.00040686584543436766
2023-01-24 11:14:56.824626: step: 2080/530, loss: 1.979967964871321e-05
2023-01-24 11:14:57.919214: step: 2084/530, loss: 0.0017287888331338763
2023-01-24 11:14:58.993490: step: 2088/530, loss: 7.450580152834618e-10
2023-01-24 11:15:00.072321: step: 2092/530, loss: 9.442597729503177e-06
2023-01-24 11:15:01.161240: step: 2096/530, loss: 0.0002690191613510251
2023-01-24 11:15:02.234430: step: 2100/530, loss: 0.00023467732535209507
2023-01-24 11:15:03.350668: step: 2104/530, loss: 0.0056996820494532585
2023-01-24 11:15:04.467622: step: 2108/530, loss: 0.003091799793764949
2023-01-24 11:15:05.535984: step: 2112/530, loss: 0.013210326433181763
2023-01-24 11:15:06.638981: step: 2116/530, loss: 0.002925982465967536
2023-01-24 11:15:07.734009: step: 2120/530, loss: 2.0695311775398295e-07
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35675572866545063, 'r': 0.34863225856301155, 'f1': 0.35264721739483124}, 'combined': 0.25984531808040195, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34403565371051775, 'r': 0.2759771663296043, 'f1': 0.30627103749641044}, 'combined': 0.19021043381356018, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3906081588479548, 'r': 0.3268656509524631, 'f1': 0.3559053678759258}, 'combined': 0.26224606054015587, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33452399540104605, 'r': 0.26246250232058355, 'f1': 0.2941440225342531}, 'combined': 0.18267891925811508, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38486200820844063, 'r': 0.32643893295858245, 'f1': 0.35325116564511905}, 'combined': 0.260290332580614, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3462287066944138, 'r': 0.27096159654345425, 'f1': 0.3040056936828999}, 'combined': 0.18880353607674838, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 19}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35675572866545063, 'r': 0.34863225856301155, 'f1': 0.35264721739483124}, 'combined': 0.25984531808040195, 'stategy': 1, 'epoch': 19}
Test for Chinese: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.34403565371051775, 'r': 0.2759771663296043, 'f1': 0.30627103749641044}, 'combined': 0.19021043381356018, 'stategy': 1, 'epoch': 19}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3715277777777778, 'r': 0.3821428571428571, 'f1': 0.37676056338028174}, 'combined': 0.2511737089201878, 'stategy': 1, 'epoch': 19}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3915914562965125, 'r': 0.33066071736612535, 'f1': 0.358555963069852}, 'combined': 0.26419913068304884, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.33294116835642923, 'r': 0.2622774455561999, 'f1': 0.2934147458292993}, 'combined': 0.1822260000413543, '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': 0.3838063704567095, 'r': 0.33355468248419917, 'f1': 0.3569204419678639}, 'combined': 0.2629940098710576, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9516129032258065, 'r': 0.4609375, 'f1': 0.6210526315789474}, 'slot': {'p': 0.3474753947928535, 'r': 0.2699537371194232, 'f1': 0.30384792855775083}, 'combined': 0.18870555563060315, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6551535087719298, 'r': 0.27109800362976405, 'f1': 0.3835044929396662}, 'combined': 0.25566966195977747, 'stategy': 1, 'epoch': 6}