Command that produces this log: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024])
>>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024])
>>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024])
>>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024])
>>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.pooler.dense.weight: torch.Size([1024, 1024])
>>> xlmr.pooler.dense.bias: torch.Size([1024])
>>> type_embedding.weight: torch.Size([123, 100])
>>> trans_rep.weight: torch.Size([1024, 1124])
>>> trans_rep.bias: torch.Size([1024])
>>> coref_type_ffn.weight: torch.Size([3, 4096])
>>> coref_type_ffn.bias: torch.Size([3])
n_trainable_params: 561067023, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:44:37.464267: step: 4/529, loss: 0.036906637251377106
2023-01-24 05:44:38.536055: step: 8/529, loss: 0.0621248222887516
2023-01-24 05:44:39.598398: step: 12/529, loss: 0.02300257608294487
2023-01-24 05:44:40.669024: step: 16/529, loss: 0.021292800083756447
2023-01-24 05:44:41.731688: step: 20/529, loss: 0.019287262111902237
2023-01-24 05:44:42.793431: step: 24/529, loss: 0.014699488878250122
2023-01-24 05:44:43.854614: step: 28/529, loss: 0.05607492849230766
2023-01-24 05:44:44.920997: step: 32/529, loss: 0.02246081829071045
2023-01-24 05:44:45.993613: step: 36/529, loss: 0.013310117647051811
2023-01-24 05:44:47.053503: step: 40/529, loss: 0.02030652016401291
2023-01-24 05:44:48.109323: step: 44/529, loss: 0.04427490010857582
2023-01-24 05:44:49.162840: step: 48/529, loss: 0.06931335479021072
2023-01-24 05:44:50.245570: step: 52/529, loss: 0.019074495881795883
2023-01-24 05:44:51.303141: step: 56/529, loss: 0.015496532432734966
2023-01-24 05:44:52.375465: step: 60/529, loss: 0.01601226255297661
2023-01-24 05:44:53.439284: step: 64/529, loss: 0.011658409610390663
2023-01-24 05:44:54.513152: step: 68/529, loss: 0.06258019059896469
2023-01-24 05:44:55.575127: step: 72/529, loss: 0.025525854900479317
2023-01-24 05:44:56.625617: step: 76/529, loss: 0.014389489777386189
2023-01-24 05:44:57.676073: step: 80/529, loss: 0.011208429001271725
2023-01-24 05:44:58.735812: step: 84/529, loss: 0.04706929996609688
2023-01-24 05:44:59.797056: step: 88/529, loss: 0.02508408948779106
2023-01-24 05:45:00.858875: step: 92/529, loss: 0.02566348947584629
2023-01-24 05:45:01.947949: step: 96/529, loss: 0.021056417375802994
2023-01-24 05:45:03.019769: step: 100/529, loss: 0.020041653886437416
2023-01-24 05:45:04.088556: step: 104/529, loss: 0.008005469106137753
2023-01-24 05:45:05.147974: step: 108/529, loss: 0.020515985786914825
2023-01-24 05:45:06.198265: step: 112/529, loss: 0.0
2023-01-24 05:45:07.275247: step: 116/529, loss: 0.020652977749705315
2023-01-24 05:45:08.358456: step: 120/529, loss: 0.01828337460756302
2023-01-24 05:45:09.418664: step: 124/529, loss: 0.018345335498452187
2023-01-24 05:45:10.495978: step: 128/529, loss: 0.01574639417231083
2023-01-24 05:45:11.554567: step: 132/529, loss: 0.05731136351823807
2023-01-24 05:45:12.637830: step: 136/529, loss: 0.011213736608624458
2023-01-24 05:45:13.702229: step: 140/529, loss: 0.013642799109220505
2023-01-24 05:45:14.766565: step: 144/529, loss: 0.02615521103143692
2023-01-24 05:45:15.833007: step: 148/529, loss: 0.028597723692655563
2023-01-24 05:45:16.900872: step: 152/529, loss: 0.07758909463882446
2023-01-24 05:45:17.957884: step: 156/529, loss: 0.032660774886608124
2023-01-24 05:45:19.016156: step: 160/529, loss: 0.010725762695074081
2023-01-24 05:45:20.099357: step: 164/529, loss: 0.08858466893434525
2023-01-24 05:45:21.167377: step: 168/529, loss: 0.015186084434390068
2023-01-24 05:45:22.227305: step: 172/529, loss: 0.04659134894609451
2023-01-24 05:45:23.294641: step: 176/529, loss: 0.024690069258213043
2023-01-24 05:45:24.380049: step: 180/529, loss: 0.04203398898243904
2023-01-24 05:45:25.443484: step: 184/529, loss: 0.014550302177667618
2023-01-24 05:45:26.532630: step: 188/529, loss: 0.021250847727060318
2023-01-24 05:45:27.612918: step: 192/529, loss: 0.008041131310164928
2023-01-24 05:45:28.686404: step: 196/529, loss: 0.017589721828699112
2023-01-24 05:45:29.771687: step: 200/529, loss: 0.05970647558569908
2023-01-24 05:45:30.846717: step: 204/529, loss: 0.010688910260796547
2023-01-24 05:45:31.931800: step: 208/529, loss: 0.05130859836935997
2023-01-24 05:45:33.006376: step: 212/529, loss: 0.008765791542828083
2023-01-24 05:45:34.073437: step: 216/529, loss: 0.014925209805369377
2023-01-24 05:45:35.138026: step: 220/529, loss: 0.04095502570271492
2023-01-24 05:45:36.196419: step: 224/529, loss: 0.006114865653216839
2023-01-24 05:45:37.273877: step: 228/529, loss: 0.01627984270453453
2023-01-24 05:45:38.345128: step: 232/529, loss: 0.017671987414360046
2023-01-24 05:45:39.428643: step: 236/529, loss: 0.015359263867139816
2023-01-24 05:45:40.487009: step: 240/529, loss: 0.05051518976688385
2023-01-24 05:45:41.562962: step: 244/529, loss: 0.023071138188242912
2023-01-24 05:45:42.633429: step: 248/529, loss: 0.014023618772625923
2023-01-24 05:45:43.717630: step: 252/529, loss: 0.009916102513670921
2023-01-24 05:45:44.813034: step: 256/529, loss: 0.04910624772310257
2023-01-24 05:45:45.871248: step: 260/529, loss: 0.01754813827574253
2023-01-24 05:45:46.954419: step: 264/529, loss: 0.009435590356588364
2023-01-24 05:45:48.040562: step: 268/529, loss: 0.013928825967013836
2023-01-24 05:45:49.109673: step: 272/529, loss: 0.011481163091957569
2023-01-24 05:45:50.181715: step: 276/529, loss: 0.10326572507619858
2023-01-24 05:45:51.259655: step: 280/529, loss: 0.04917379841208458
2023-01-24 05:45:52.327326: step: 284/529, loss: 0.021951744332909584
2023-01-24 05:45:53.409461: step: 288/529, loss: 0.021210145205259323
2023-01-24 05:45:54.483784: step: 292/529, loss: 0.016783222556114197
2023-01-24 05:45:55.575816: step: 296/529, loss: 0.01707283779978752
2023-01-24 05:45:56.658235: step: 300/529, loss: 0.01796027459204197
2023-01-24 05:45:57.725538: step: 304/529, loss: 0.036726683378219604
2023-01-24 05:45:58.786931: step: 308/529, loss: 0.00756659172475338
2023-01-24 05:45:59.869508: step: 312/529, loss: 0.010935730300843716
2023-01-24 05:46:00.934814: step: 316/529, loss: 0.004954290110617876
2023-01-24 05:46:02.023580: step: 320/529, loss: 0.012793033383786678
2023-01-24 05:46:03.093825: step: 324/529, loss: 0.021430062130093575
2023-01-24 05:46:04.176932: step: 328/529, loss: 0.0345136933028698
2023-01-24 05:46:05.262282: step: 332/529, loss: 0.007490217220038176
2023-01-24 05:46:06.323716: step: 336/529, loss: 0.024818042293190956
2023-01-24 05:46:07.414091: step: 340/529, loss: 0.04161607474088669
2023-01-24 05:46:08.487286: step: 344/529, loss: 0.06896219402551651
2023-01-24 05:46:09.564910: step: 348/529, loss: 0.04392163082957268
2023-01-24 05:46:10.648444: step: 352/529, loss: 0.006646931637078524
2023-01-24 05:46:11.708662: step: 356/529, loss: 0.0
2023-01-24 05:46:12.797134: step: 360/529, loss: 0.012845569290220737
2023-01-24 05:46:13.879836: step: 364/529, loss: 0.00917950738221407
2023-01-24 05:46:14.946188: step: 368/529, loss: 0.04632199555635452
2023-01-24 05:46:16.024808: step: 372/529, loss: 0.07200482487678528
2023-01-24 05:46:17.090623: step: 376/529, loss: 0.041902121156454086
2023-01-24 05:46:18.172926: step: 380/529, loss: 0.008073313161730766
2023-01-24 05:46:19.242133: step: 384/529, loss: 0.009958234615623951
2023-01-24 05:46:20.309592: step: 388/529, loss: 0.012584754265844822
2023-01-24 05:46:21.403698: step: 392/529, loss: 0.06030331179499626
2023-01-24 05:46:22.485392: step: 396/529, loss: 0.00962952058762312
2023-01-24 05:46:23.563867: step: 400/529, loss: 0.013606185093522072
2023-01-24 05:46:24.633553: step: 404/529, loss: 0.012179278768599033
2023-01-24 05:46:25.709289: step: 408/529, loss: 0.017199020832777023
2023-01-24 05:46:26.802844: step: 412/529, loss: 0.060847386717796326
2023-01-24 05:46:27.891492: step: 416/529, loss: 0.010868166573345661
2023-01-24 05:46:28.967168: step: 420/529, loss: 0.0400981530547142
2023-01-24 05:46:30.042074: step: 424/529, loss: 0.010132329538464546
2023-01-24 05:46:31.103214: step: 428/529, loss: 0.017198748886585236
2023-01-24 05:46:32.171160: step: 432/529, loss: 0.013414408080279827
2023-01-24 05:46:33.260780: step: 436/529, loss: 0.01622629351913929
2023-01-24 05:46:34.329227: step: 440/529, loss: 0.011021781712770462
2023-01-24 05:46:35.408814: step: 444/529, loss: 0.016030149534344673
2023-01-24 05:46:36.498375: step: 448/529, loss: 0.05198883265256882
2023-01-24 05:46:37.600211: step: 452/529, loss: 0.031469158828258514
2023-01-24 05:46:38.679322: step: 456/529, loss: 0.014572232030332088
2023-01-24 05:46:39.784320: step: 460/529, loss: 0.011517726816236973
2023-01-24 05:46:40.869297: step: 464/529, loss: 0.040690720081329346
2023-01-24 05:46:41.941712: step: 468/529, loss: 0.018083972856402397
2023-01-24 05:46:43.033755: step: 472/529, loss: 0.047869883477687836
2023-01-24 05:46:44.107490: step: 476/529, loss: 0.036852624267339706
2023-01-24 05:46:45.197680: step: 480/529, loss: 0.024334874004125595
2023-01-24 05:46:46.267621: step: 484/529, loss: 0.011195872910320759
2023-01-24 05:46:47.348073: step: 488/529, loss: 0.010092330165207386
2023-01-24 05:46:48.421732: step: 492/529, loss: 0.014725054614245892
2023-01-24 05:46:49.499506: step: 496/529, loss: 0.010978207923471928
2023-01-24 05:46:50.573022: step: 500/529, loss: 0.04949723556637764
2023-01-24 05:46:51.643563: step: 504/529, loss: 0.039471693336963654
2023-01-24 05:46:52.725979: step: 508/529, loss: 0.008636035025119781
2023-01-24 05:46:53.812511: step: 512/529, loss: 0.05558284372091293
2023-01-24 05:46:54.905936: step: 516/529, loss: 0.024330083280801773
2023-01-24 05:46:55.999164: step: 520/529, loss: 0.020511817187070847
2023-01-24 05:46:57.084458: step: 524/529, loss: 0.01563498005270958
2023-01-24 05:46:58.163440: step: 528/529, loss: 0.04201168939471245
2023-01-24 05:46:59.259514: step: 532/529, loss: 0.012389475479722023
2023-01-24 05:47:00.342253: step: 536/529, loss: 0.006306052673608065
2023-01-24 05:47:01.429586: step: 540/529, loss: 0.027361616492271423
2023-01-24 05:47:02.514868: step: 544/529, loss: 0.00941076036542654
2023-01-24 05:47:03.612375: step: 548/529, loss: 0.049970827996730804
2023-01-24 05:47:04.686999: step: 552/529, loss: 0.008651609532535076
2023-01-24 05:47:05.762210: step: 556/529, loss: 0.010524558834731579
2023-01-24 05:47:06.836777: step: 560/529, loss: 0.048365574330091476
2023-01-24 05:47:07.923806: step: 564/529, loss: 0.002411904511973262
2023-01-24 05:47:09.006812: step: 568/529, loss: 0.007765104994177818
2023-01-24 05:47:10.081517: step: 572/529, loss: 0.050128962844610214
2023-01-24 05:47:11.168429: step: 576/529, loss: 0.035054419189691544
2023-01-24 05:47:12.250361: step: 580/529, loss: 0.0769512727856636
2023-01-24 05:47:13.349292: step: 584/529, loss: 0.058283016085624695
2023-01-24 05:47:14.443309: step: 588/529, loss: 0.012656567618250847
2023-01-24 05:47:15.523969: step: 592/529, loss: 0.009634032845497131
2023-01-24 05:47:16.596105: step: 596/529, loss: 0.030522329732775688
2023-01-24 05:47:17.682045: step: 600/529, loss: 0.010691116563975811
2023-01-24 05:47:18.772140: step: 604/529, loss: 0.011345036327838898
2023-01-24 05:47:19.862988: step: 608/529, loss: 0.015001209452748299
2023-01-24 05:47:20.939255: step: 612/529, loss: 0.04308963567018509
2023-01-24 05:47:22.029864: step: 616/529, loss: 0.04435019567608833
2023-01-24 05:47:23.099309: step: 620/529, loss: 0.05402511730790138
2023-01-24 05:47:24.178585: step: 624/529, loss: 0.03840957209467888
2023-01-24 05:47:25.270328: step: 628/529, loss: 0.008532053790986538
2023-01-24 05:47:26.356022: step: 632/529, loss: 0.04640606790781021
2023-01-24 05:47:27.445789: step: 636/529, loss: 0.015516658313572407
2023-01-24 05:47:28.536408: step: 640/529, loss: 0.048128049820661545
2023-01-24 05:47:29.626466: step: 644/529, loss: 0.023092491552233696
2023-01-24 05:47:30.710403: step: 648/529, loss: 0.0109193604439497
2023-01-24 05:47:31.790502: step: 652/529, loss: 0.039670784026384354
2023-01-24 05:47:32.888009: step: 656/529, loss: 0.024215450510382652
2023-01-24 05:47:33.971345: step: 660/529, loss: 0.07807125896215439
2023-01-24 05:47:35.051380: step: 664/529, loss: 0.04490305855870247
2023-01-24 05:47:36.151205: step: 668/529, loss: 0.010400510393083096
2023-01-24 05:47:37.245279: step: 672/529, loss: 0.018645433709025383
2023-01-24 05:47:38.313124: step: 676/529, loss: 0.041870374232530594
2023-01-24 05:47:39.383069: step: 680/529, loss: 0.09524698555469513
2023-01-24 05:47:40.456083: step: 684/529, loss: 0.0345437191426754
2023-01-24 05:47:41.541572: step: 688/529, loss: 0.014123331755399704
2023-01-24 05:47:42.618685: step: 692/529, loss: 0.013536249287426472
2023-01-24 05:47:43.695610: step: 696/529, loss: 0.009395051747560501
2023-01-24 05:47:44.781142: step: 700/529, loss: 0.012241140939295292
2023-01-24 05:47:45.850442: step: 704/529, loss: 0.01093914732336998
2023-01-24 05:47:46.922858: step: 708/529, loss: 0.029698064550757408
2023-01-24 05:47:48.015690: step: 712/529, loss: 0.012869570404291153
2023-01-24 05:47:49.116819: step: 716/529, loss: 0.009240290150046349
2023-01-24 05:47:50.200133: step: 720/529, loss: 0.0075867632403969765
2023-01-24 05:47:51.288132: step: 724/529, loss: 0.01640930399298668
2023-01-24 05:47:52.374545: step: 728/529, loss: 0.00956727284938097
2023-01-24 05:47:53.471651: step: 732/529, loss: 0.007887667044997215
2023-01-24 05:47:54.560890: step: 736/529, loss: 0.01039630826562643
2023-01-24 05:47:55.643218: step: 740/529, loss: 0.013838459737598896
2023-01-24 05:47:56.725736: step: 744/529, loss: 0.05541898310184479
2023-01-24 05:47:57.800936: step: 748/529, loss: 0.013446134515106678
2023-01-24 05:47:58.890385: step: 752/529, loss: 0.048116616904735565
2023-01-24 05:47:59.980173: step: 756/529, loss: 0.006654263474047184
2023-01-24 05:48:01.068585: step: 760/529, loss: 0.014451884664595127
2023-01-24 05:48:02.135451: step: 764/529, loss: 0.0052962410263717175
2023-01-24 05:48:03.215217: step: 768/529, loss: 0.0028691133484244347
2023-01-24 05:48:04.306805: step: 772/529, loss: 0.010828969068825245
2023-01-24 05:48:05.395569: step: 776/529, loss: 0.01071922481060028
2023-01-24 05:48:06.474467: step: 780/529, loss: 0.012221409007906914
2023-01-24 05:48:07.560587: step: 784/529, loss: 0.03381427004933357
2023-01-24 05:48:08.650862: step: 788/529, loss: 0.013468189164996147
2023-01-24 05:48:09.729301: step: 792/529, loss: 0.02683264948427677
2023-01-24 05:48:10.816657: step: 796/529, loss: 0.014051465317606926
2023-01-24 05:48:11.915601: step: 800/529, loss: 0.008052659220993519
2023-01-24 05:48:13.012154: step: 804/529, loss: 0.02756400965154171
2023-01-24 05:48:14.100680: step: 808/529, loss: 0.011081838980317116
2023-01-24 05:48:15.198098: step: 812/529, loss: 0.030933188274502754
2023-01-24 05:48:16.286791: step: 816/529, loss: 0.04143639653921127
2023-01-24 05:48:17.364374: step: 820/529, loss: 0.04699551314115524
2023-01-24 05:48:18.470310: step: 824/529, loss: 0.009988164529204369
2023-01-24 05:48:19.568257: step: 828/529, loss: 0.04094613343477249
2023-01-24 05:48:20.662439: step: 832/529, loss: 0.008815049193799496
2023-01-24 05:48:21.743258: step: 836/529, loss: 0.0246005579829216
2023-01-24 05:48:22.833838: step: 840/529, loss: 0.008881958201527596
2023-01-24 05:48:23.912735: step: 844/529, loss: 0.005901203956454992
2023-01-24 05:48:24.991300: step: 848/529, loss: 0.009790322743356228
2023-01-24 05:48:26.068772: step: 852/529, loss: 0.0077022346667945385
2023-01-24 05:48:27.159448: step: 856/529, loss: 0.01971416361629963
2023-01-24 05:48:28.237120: step: 860/529, loss: 0.012111751362681389
2023-01-24 05:48:29.317984: step: 864/529, loss: 0.008319082669913769
2023-01-24 05:48:30.383610: step: 868/529, loss: 0.008041729219257832
2023-01-24 05:48:31.461267: step: 872/529, loss: 0.009349256753921509
2023-01-24 05:48:32.551438: step: 876/529, loss: 0.010881714522838593
2023-01-24 05:48:33.621654: step: 880/529, loss: 0.0036121136508882046
2023-01-24 05:48:34.735306: step: 884/529, loss: 0.04462500289082527
2023-01-24 05:48:35.816626: step: 888/529, loss: 0.014002700336277485
2023-01-24 05:48:36.900819: step: 892/529, loss: 0.009989199228584766
2023-01-24 05:48:37.992051: step: 896/529, loss: 0.008908821269869804
2023-01-24 05:48:39.085862: step: 900/529, loss: 0.011485452763736248
2023-01-24 05:48:40.156237: step: 904/529, loss: 0.01944391056895256
2023-01-24 05:48:41.223092: step: 908/529, loss: 0.03485608100891113
2023-01-24 05:48:42.303479: step: 912/529, loss: 0.03305096551775932
2023-01-24 05:48:43.385938: step: 916/529, loss: 0.007312651723623276
2023-01-24 05:48:44.461495: step: 920/529, loss: 0.013770959340035915
2023-01-24 05:48:45.552298: step: 924/529, loss: 0.05728096887469292
2023-01-24 05:48:46.660826: step: 928/529, loss: 0.020198343321681023
2023-01-24 05:48:47.731109: step: 932/529, loss: 0.01897631399333477
2023-01-24 05:48:48.810137: step: 936/529, loss: 0.010871518403291702
2023-01-24 05:48:49.900255: step: 940/529, loss: 0.03519846871495247
2023-01-24 05:48:51.002579: step: 944/529, loss: 0.01631801947951317
2023-01-24 05:48:52.078551: step: 948/529, loss: 0.006152381654828787
2023-01-24 05:48:53.151711: step: 952/529, loss: 0.006907373666763306
2023-01-24 05:48:54.246737: step: 956/529, loss: 0.007043652702122927
2023-01-24 05:48:55.333073: step: 960/529, loss: 0.025328710675239563
2023-01-24 05:48:56.413870: step: 964/529, loss: 0.020681828260421753
2023-01-24 05:48:57.488092: step: 968/529, loss: 0.03203994035720825
2023-01-24 05:48:58.557609: step: 972/529, loss: 0.004437461961060762
2023-01-24 05:48:59.635796: step: 976/529, loss: 0.007767890114337206
2023-01-24 05:49:00.720406: step: 980/529, loss: 0.03811563923954964
2023-01-24 05:49:01.788641: step: 984/529, loss: 0.014742046594619751
2023-01-24 05:49:02.857795: step: 988/529, loss: 0.00966726616024971
2023-01-24 05:49:03.938395: step: 992/529, loss: 0.011935340240597725
2023-01-24 05:49:05.024136: step: 996/529, loss: 0.033202216029167175
2023-01-24 05:49:06.115838: step: 1000/529, loss: 0.008478621952235699
2023-01-24 05:49:07.196304: step: 1004/529, loss: 0.023013152182102203
2023-01-24 05:49:08.298574: step: 1008/529, loss: 0.006438667420297861
2023-01-24 05:49:09.382715: step: 1012/529, loss: 0.03475933521986008
2023-01-24 05:49:10.468107: step: 1016/529, loss: 0.0068849120289087296
2023-01-24 05:49:11.563150: step: 1020/529, loss: 0.04339052364230156
2023-01-24 05:49:12.643734: step: 1024/529, loss: 0.010688281618058681
2023-01-24 05:49:13.719036: step: 1028/529, loss: 0.01973528042435646
2023-01-24 05:49:14.803172: step: 1032/529, loss: 0.01425983291119337
2023-01-24 05:49:15.885393: step: 1036/529, loss: 0.016061833128333092
2023-01-24 05:49:16.959209: step: 1040/529, loss: 0.010656836442649364
2023-01-24 05:49:18.029856: step: 1044/529, loss: 0.029521167278289795
2023-01-24 05:49:19.100608: step: 1048/529, loss: 0.018340887501835823
2023-01-24 05:49:20.169625: step: 1052/529, loss: 0.048236045986413956
2023-01-24 05:49:21.249344: step: 1056/529, loss: 0.004470358602702618
2023-01-24 05:49:22.332313: step: 1060/529, loss: 0.01605336181819439
2023-01-24 05:49:23.415182: step: 1064/529, loss: 0.014046620577573776
2023-01-24 05:49:24.482105: step: 1068/529, loss: 0.014131884090602398
2023-01-24 05:49:25.559689: step: 1072/529, loss: 0.02307000197470188
2023-01-24 05:49:26.638657: step: 1076/529, loss: 0.06608673185110092
2023-01-24 05:49:27.712541: step: 1080/529, loss: 0.007001555059105158
2023-01-24 05:49:28.817506: step: 1084/529, loss: 0.01940244808793068
2023-01-24 05:49:29.918479: step: 1088/529, loss: 0.010441668331623077
2023-01-24 05:49:31.005635: step: 1092/529, loss: 0.008033023215830326
2023-01-24 05:49:32.084084: step: 1096/529, loss: 0.03955061733722687
2023-01-24 05:49:33.179208: step: 1100/529, loss: 0.043457262217998505
2023-01-24 05:49:34.247995: step: 1104/529, loss: 0.04453654587268829
2023-01-24 05:49:35.330704: step: 1108/529, loss: 0.020859340205788612
2023-01-24 05:49:36.400266: step: 1112/529, loss: 0.009554127231240273
2023-01-24 05:49:37.464725: step: 1116/529, loss: 0.06352561712265015
2023-01-24 05:49:38.530974: step: 1120/529, loss: 0.012546413578093052
2023-01-24 05:49:39.604698: step: 1124/529, loss: 0.00781959481537342
2023-01-24 05:49:40.677622: step: 1128/529, loss: 0.018820233643054962
2023-01-24 05:49:41.745149: step: 1132/529, loss: 0.039390288293361664
2023-01-24 05:49:42.834139: step: 1136/529, loss: 0.03650328144431114
2023-01-24 05:49:43.932584: step: 1140/529, loss: 0.04654746130108833
2023-01-24 05:49:45.002306: step: 1144/529, loss: 0.019812630489468575
2023-01-24 05:49:46.062011: step: 1148/529, loss: 0.011509333737194538
2023-01-24 05:49:47.140474: step: 1152/529, loss: 0.007650483399629593
2023-01-24 05:49:48.208252: step: 1156/529, loss: 0.014886134304106236
2023-01-24 05:49:49.297638: step: 1160/529, loss: 0.05990464612841606
2023-01-24 05:49:50.382466: step: 1164/529, loss: 0.039350491017103195
2023-01-24 05:49:51.464308: step: 1168/529, loss: 0.00626153452321887
2023-01-24 05:49:52.547712: step: 1172/529, loss: 0.009320780634880066
2023-01-24 05:49:53.609356: step: 1176/529, loss: 0.0134690897539258
2023-01-24 05:49:54.688500: step: 1180/529, loss: 0.008416729979217052
2023-01-24 05:49:55.758256: step: 1184/529, loss: 0.04894373193383217
2023-01-24 05:49:56.840991: step: 1188/529, loss: 0.022580036893486977
2023-01-24 05:49:57.942130: step: 1192/529, loss: 0.0033554767724126577
2023-01-24 05:49:59.021276: step: 1196/529, loss: 0.0164506733417511
2023-01-24 05:50:00.120899: step: 1200/529, loss: 0.012273762375116348
2023-01-24 05:50:01.208632: step: 1204/529, loss: 0.06385210156440735
2023-01-24 05:50:02.279087: step: 1208/529, loss: 0.003882566699758172
2023-01-24 05:50:03.360638: step: 1212/529, loss: 0.03736743703484535
2023-01-24 05:50:04.443440: step: 1216/529, loss: 0.007969222031533718
2023-01-24 05:50:05.536054: step: 1220/529, loss: 0.030050775036215782
2023-01-24 05:50:06.619835: step: 1224/529, loss: 0.03377442806959152
2023-01-24 05:50:07.700636: step: 1228/529, loss: 0.008897541090846062
2023-01-24 05:50:08.770028: step: 1232/529, loss: 0.03691292926669121
2023-01-24 05:50:09.885582: step: 1236/529, loss: 0.01646624505519867
2023-01-24 05:50:10.983863: step: 1240/529, loss: 0.02995854802429676
2023-01-24 05:50:12.067202: step: 1244/529, loss: 0.03402078151702881
2023-01-24 05:50:13.134841: step: 1248/529, loss: 0.01780552603304386
2023-01-24 05:50:14.244856: step: 1252/529, loss: 0.009463814087212086
2023-01-24 05:50:15.321829: step: 1256/529, loss: 0.010619205422699451
2023-01-24 05:50:16.387956: step: 1260/529, loss: 0.012928532436490059
2023-01-24 05:50:17.477618: step: 1264/529, loss: 0.009818925522267818
2023-01-24 05:50:18.558642: step: 1268/529, loss: 0.0014176652766764164
2023-01-24 05:50:19.645060: step: 1272/529, loss: 0.01897534541785717
2023-01-24 05:50:20.728723: step: 1276/529, loss: 0.02581171877682209
2023-01-24 05:50:21.834647: step: 1280/529, loss: 0.009975031018257141
2023-01-24 05:50:22.907917: step: 1284/529, loss: 0.03988887742161751
2023-01-24 05:50:23.984184: step: 1288/529, loss: 0.003912187647074461
2023-01-24 05:50:25.081675: step: 1292/529, loss: 0.010445482097566128
2023-01-24 05:50:26.158613: step: 1296/529, loss: 0.016609974205493927
2023-01-24 05:50:27.229436: step: 1300/529, loss: 0.019434276968240738
2023-01-24 05:50:28.306123: step: 1304/529, loss: 0.030209345743060112
2023-01-24 05:50:29.389236: step: 1308/529, loss: 0.03816532343626022
2023-01-24 05:50:30.469982: step: 1312/529, loss: 0.02780003659427166
2023-01-24 05:50:31.541395: step: 1316/529, loss: 0.01622786931693554
2023-01-24 05:50:32.610784: step: 1320/529, loss: 0.011303656734526157
2023-01-24 05:50:33.683897: step: 1324/529, loss: 0.013496220111846924
2023-01-24 05:50:34.765883: step: 1328/529, loss: 0.05611635744571686
2023-01-24 05:50:35.852940: step: 1332/529, loss: 0.047016698867082596
2023-01-24 05:50:36.928843: step: 1336/529, loss: 0.014781685546040535
2023-01-24 05:50:38.005465: step: 1340/529, loss: 0.02529684081673622
2023-01-24 05:50:39.089469: step: 1344/529, loss: 0.04970370978116989
2023-01-24 05:50:40.177238: step: 1348/529, loss: 0.00895818043500185
2023-01-24 05:50:41.256489: step: 1352/529, loss: 0.013945626094937325
2023-01-24 05:50:42.339801: step: 1356/529, loss: 0.01091905776411295
2023-01-24 05:50:43.433936: step: 1360/529, loss: 0.009536290541291237
2023-01-24 05:50:44.511382: step: 1364/529, loss: 0.005469128023833036
2023-01-24 05:50:45.599071: step: 1368/529, loss: 0.013938400894403458
2023-01-24 05:50:46.687262: step: 1372/529, loss: 0.014763103798031807
2023-01-24 05:50:47.757674: step: 1376/529, loss: 0.014497095718979836
2023-01-24 05:50:48.844774: step: 1380/529, loss: 0.01092081144452095
2023-01-24 05:50:49.925650: step: 1384/529, loss: 0.024942563846707344
2023-01-24 05:50:50.995770: step: 1388/529, loss: 0.01457739807665348
2023-01-24 05:50:52.062074: step: 1392/529, loss: 0.004112505353987217
2023-01-24 05:50:53.134858: step: 1396/529, loss: 0.005271682515740395
2023-01-24 05:50:54.208792: step: 1400/529, loss: 0.009081680327653885
2023-01-24 05:50:55.292853: step: 1404/529, loss: 0.018123524263501167
2023-01-24 05:50:56.374277: step: 1408/529, loss: 0.06646265834569931
2023-01-24 05:50:57.463725: step: 1412/529, loss: 0.01829330250620842
2023-01-24 05:50:58.540520: step: 1416/529, loss: 0.014399976469576359
2023-01-24 05:50:59.609374: step: 1420/529, loss: 0.0422513484954834
2023-01-24 05:51:00.668576: step: 1424/529, loss: 0.014533104375004768
2023-01-24 05:51:01.748030: step: 1428/529, loss: 0.003955908119678497
2023-01-24 05:51:02.817332: step: 1432/529, loss: 0.019932806491851807
2023-01-24 05:51:03.918605: step: 1436/529, loss: 0.09128439426422119
2023-01-24 05:51:04.982503: step: 1440/529, loss: 0.009105724282562733
2023-01-24 05:51:06.043231: step: 1444/529, loss: 0.0064781541004776955
2023-01-24 05:51:07.147223: step: 1448/529, loss: 0.004979480989277363
2023-01-24 05:51:08.210670: step: 1452/529, loss: 0.022313237190246582
2023-01-24 05:51:09.278657: step: 1456/529, loss: 0.014171168208122253
2023-01-24 05:51:10.347331: step: 1460/529, loss: 0.012895352207124233
2023-01-24 05:51:11.429363: step: 1464/529, loss: 0.048164334148168564
2023-01-24 05:51:12.504125: step: 1468/529, loss: 0.0479486808180809
2023-01-24 05:51:13.604429: step: 1472/529, loss: 0.009772618301212788
2023-01-24 05:51:14.679038: step: 1476/529, loss: 0.014677603729069233
2023-01-24 05:51:15.771594: step: 1480/529, loss: 0.011042511090636253
2023-01-24 05:51:16.854844: step: 1484/529, loss: 0.02183568850159645
2023-01-24 05:51:17.946567: step: 1488/529, loss: 0.0098685622215271
2023-01-24 05:51:19.044118: step: 1492/529, loss: 0.04448552429676056
2023-01-24 05:51:20.124235: step: 1496/529, loss: 0.012356571853160858
2023-01-24 05:51:21.223605: step: 1500/529, loss: 0.008956319652497768
2023-01-24 05:51:22.308549: step: 1504/529, loss: 0.027506200596690178
2023-01-24 05:51:23.404031: step: 1508/529, loss: 0.03240431100130081
2023-01-24 05:51:24.479282: step: 1512/529, loss: 0.007043669931590557
2023-01-24 05:51:25.551886: step: 1516/529, loss: 0.014196484349668026
2023-01-24 05:51:26.630126: step: 1520/529, loss: 0.03495393320918083
2023-01-24 05:51:27.718927: step: 1524/529, loss: 0.012616559863090515
2023-01-24 05:51:28.791839: step: 1528/529, loss: 0.010927898809313774
2023-01-24 05:51:29.862987: step: 1532/529, loss: 0.015938246622681618
2023-01-24 05:51:30.932218: step: 1536/529, loss: 0.012138689868152142
2023-01-24 05:51:32.000590: step: 1540/529, loss: 0.020071323961019516
2023-01-24 05:51:33.081140: step: 1544/529, loss: 0.010562852025032043
2023-01-24 05:51:34.165857: step: 1548/529, loss: 0.015179213136434555
2023-01-24 05:51:35.244398: step: 1552/529, loss: 0.011046028696000576
2023-01-24 05:51:36.313306: step: 1556/529, loss: 0.023666206747293472
2023-01-24 05:51:37.393253: step: 1560/529, loss: 0.009827623143792152
2023-01-24 05:51:38.460571: step: 1564/529, loss: 0.013244322501122952
2023-01-24 05:51:39.539177: step: 1568/529, loss: 0.006782297044992447
2023-01-24 05:51:40.629420: step: 1572/529, loss: 0.016043927520513535
2023-01-24 05:51:41.707920: step: 1576/529, loss: 0.04864581301808357
2023-01-24 05:51:42.791155: step: 1580/529, loss: 0.011934645473957062
2023-01-24 05:51:43.871735: step: 1584/529, loss: 0.0119180828332901
2023-01-24 05:51:44.953500: step: 1588/529, loss: 0.014821691438555717
2023-01-24 05:51:46.026323: step: 1592/529, loss: 0.019581124186515808
2023-01-24 05:51:47.099676: step: 1596/529, loss: 0.038017239421606064
2023-01-24 05:51:48.187098: step: 1600/529, loss: 0.009091285057365894
2023-01-24 05:51:49.262107: step: 1604/529, loss: 0.010705037042498589
2023-01-24 05:51:50.337319: step: 1608/529, loss: 0.01161727961152792
2023-01-24 05:51:51.411052: step: 1612/529, loss: 0.012504544109106064
2023-01-24 05:51:52.480784: step: 1616/529, loss: 0.01929384469985962
2023-01-24 05:51:53.574864: step: 1620/529, loss: 0.005453450605273247
2023-01-24 05:51:54.682678: step: 1624/529, loss: 0.01647050678730011
2023-01-24 05:51:55.759216: step: 1628/529, loss: 0.02542250044643879
2023-01-24 05:51:56.844554: step: 1632/529, loss: 0.010703759267926216
2023-01-24 05:51:57.926857: step: 1636/529, loss: 0.024750564247369766
2023-01-24 05:51:58.990631: step: 1640/529, loss: 0.019360367208719254
2023-01-24 05:52:00.087504: step: 1644/529, loss: 0.030594654381275177
2023-01-24 05:52:01.176558: step: 1648/529, loss: 0.00952104851603508
2023-01-24 05:52:02.251879: step: 1652/529, loss: 0.008548855781555176
2023-01-24 05:52:03.333282: step: 1656/529, loss: 0.007255463860929012
2023-01-24 05:52:04.410393: step: 1660/529, loss: 0.005405239295214415
2023-01-24 05:52:05.498854: step: 1664/529, loss: 0.011535361409187317
2023-01-24 05:52:06.569600: step: 1668/529, loss: 0.01885666884481907
2023-01-24 05:52:07.654436: step: 1672/529, loss: 0.00498919328674674
2023-01-24 05:52:08.729995: step: 1676/529, loss: 0.014910454861819744
2023-01-24 05:52:09.799595: step: 1680/529, loss: 0.06842447072267532
2023-01-24 05:52:10.881563: step: 1684/529, loss: 0.004844325128942728
2023-01-24 05:52:11.973409: step: 1688/529, loss: 0.018356764689087868
2023-01-24 05:52:13.089072: step: 1692/529, loss: 0.017747139558196068
2023-01-24 05:52:14.169683: step: 1696/529, loss: 0.009090698324143887
2023-01-24 05:52:15.281396: step: 1700/529, loss: 0.008004606701433659
2023-01-24 05:52:16.347933: step: 1704/529, loss: 0.0038984352722764015
2023-01-24 05:52:17.418504: step: 1708/529, loss: 0.01213434524834156
2023-01-24 05:52:18.510287: step: 1712/529, loss: 0.018441416323184967
2023-01-24 05:52:19.586082: step: 1716/529, loss: 0.0013421541079878807
2023-01-24 05:52:20.660648: step: 1720/529, loss: 0.011830998584628105
2023-01-24 05:52:21.743141: step: 1724/529, loss: 0.019219642505049706
2023-01-24 05:52:22.820946: step: 1728/529, loss: 0.08307844400405884
2023-01-24 05:52:23.898399: step: 1732/529, loss: 0.027975892648100853
2023-01-24 05:52:24.986036: step: 1736/529, loss: 0.0045472909696400166
2023-01-24 05:52:26.063670: step: 1740/529, loss: 0.010373634286224842
2023-01-24 05:52:27.146044: step: 1744/529, loss: 0.011059076525270939
2023-01-24 05:52:28.234963: step: 1748/529, loss: 0.011523915454745293
2023-01-24 05:52:29.309366: step: 1752/529, loss: 0.006287896540015936
2023-01-24 05:52:30.377577: step: 1756/529, loss: 0.011118857190012932
2023-01-24 05:52:31.463389: step: 1760/529, loss: 0.013232304714620113
2023-01-24 05:52:32.530197: step: 1764/529, loss: 0.03782587870955467
2023-01-24 05:52:33.611266: step: 1768/529, loss: 0.04864799231290817
2023-01-24 05:52:34.688528: step: 1772/529, loss: 0.01754884421825409
2023-01-24 05:52:35.775966: step: 1776/529, loss: 0.004559441935271025
2023-01-24 05:52:36.860404: step: 1780/529, loss: 0.005559857003390789
2023-01-24 05:52:37.929918: step: 1784/529, loss: 0.00941484235227108
2023-01-24 05:52:39.021721: step: 1788/529, loss: 0.01203937642276287
2023-01-24 05:52:40.090339: step: 1792/529, loss: 0.02942446805536747
2023-01-24 05:52:41.172778: step: 1796/529, loss: 0.027867969125509262
2023-01-24 05:52:42.260350: step: 1800/529, loss: 0.01711081899702549
2023-01-24 05:52:43.351039: step: 1804/529, loss: 0.007564476225525141
2023-01-24 05:52:44.446371: step: 1808/529, loss: 0.0303249042481184
2023-01-24 05:52:45.517659: step: 1812/529, loss: 0.01560313068330288
2023-01-24 05:52:46.599130: step: 1816/529, loss: 0.01105155237019062
2023-01-24 05:52:47.686777: step: 1820/529, loss: 0.026142792776226997
2023-01-24 05:52:48.771354: step: 1824/529, loss: 0.022417457774281502
2023-01-24 05:52:49.839897: step: 1828/529, loss: 0.009239268489181995
2023-01-24 05:52:50.912989: step: 1832/529, loss: 0.016888830810785294
2023-01-24 05:52:51.990098: step: 1836/529, loss: 0.019255323335528374
2023-01-24 05:52:53.057960: step: 1840/529, loss: 0.00810487475246191
2023-01-24 05:52:54.129198: step: 1844/529, loss: 0.008998078294098377
2023-01-24 05:52:55.220889: step: 1848/529, loss: 0.014304356649518013
2023-01-24 05:52:56.299758: step: 1852/529, loss: 0.011611538007855415
2023-01-24 05:52:57.363026: step: 1856/529, loss: 0.015956824645400047
2023-01-24 05:52:58.430692: step: 1860/529, loss: 0.028270462527871132
2023-01-24 05:52:59.500015: step: 1864/529, loss: 0.026612134650349617
2023-01-24 05:53:00.565896: step: 1868/529, loss: 0.00843536015599966
2023-01-24 05:53:01.658577: step: 1872/529, loss: 0.008983597159385681
2023-01-24 05:53:02.729800: step: 1876/529, loss: 0.016142651438713074
2023-01-24 05:53:03.800019: step: 1880/529, loss: 0.03215731680393219
2023-01-24 05:53:04.864837: step: 1884/529, loss: 0.00981141161173582
2023-01-24 05:53:05.928532: step: 1888/529, loss: 0.02600226178765297
2023-01-24 05:53:07.009270: step: 1892/529, loss: 0.006307667586952448
2023-01-24 05:53:08.085843: step: 1896/529, loss: 0.015335206873714924
2023-01-24 05:53:09.190535: step: 1900/529, loss: 0.018125057220458984
2023-01-24 05:53:10.305477: step: 1904/529, loss: 0.0016812998801469803
2023-01-24 05:53:11.387280: step: 1908/529, loss: 0.04461795836687088
2023-01-24 05:53:12.454963: step: 1912/529, loss: 0.010300851427018642
2023-01-24 05:53:13.540334: step: 1916/529, loss: 0.005020210053771734
2023-01-24 05:53:14.631723: step: 1920/529, loss: 0.01172242034226656
2023-01-24 05:53:15.716679: step: 1924/529, loss: 0.012929745018482208
2023-01-24 05:53:16.792475: step: 1928/529, loss: 0.025406766682863235
2023-01-24 05:53:17.890305: step: 1932/529, loss: 0.025732429698109627
2023-01-24 05:53:18.983104: step: 1936/529, loss: 0.0036415972281247377
2023-01-24 05:53:20.049693: step: 1940/529, loss: 0.012167402543127537
2023-01-24 05:53:21.119587: step: 1944/529, loss: 0.0045298305340111256
2023-01-24 05:53:22.191648: step: 1948/529, loss: 0.028993822634220123
2023-01-24 05:53:23.265756: step: 1952/529, loss: 0.007412605918943882
2023-01-24 05:53:24.336139: step: 1956/529, loss: 0.014061648398637772
2023-01-24 05:53:25.404840: step: 1960/529, loss: 0.004360183607786894
2023-01-24 05:53:26.471248: step: 1964/529, loss: 0.021339930593967438
2023-01-24 05:53:27.550283: step: 1968/529, loss: 0.029146555811166763
2023-01-24 05:53:28.623228: step: 1972/529, loss: 0.022972330451011658
2023-01-24 05:53:29.691065: step: 1976/529, loss: 0.011870529502630234
2023-01-24 05:53:30.759951: step: 1980/529, loss: 0.012140263803303242
2023-01-24 05:53:31.831806: step: 1984/529, loss: 0.008505532518029213
2023-01-24 05:53:32.919561: step: 1988/529, loss: 0.01145215891301632
2023-01-24 05:53:33.979374: step: 1992/529, loss: 0.014780446887016296
2023-01-24 05:53:35.047789: step: 1996/529, loss: 0.018030371516942978
2023-01-24 05:53:36.128127: step: 2000/529, loss: 0.005312791559845209
2023-01-24 05:53:37.222188: step: 2004/529, loss: 0.013527121394872665
2023-01-24 05:53:38.297576: step: 2008/529, loss: 0.00816743541508913
2023-01-24 05:53:39.382046: step: 2012/529, loss: 0.009447246789932251
2023-01-24 05:53:40.474141: step: 2016/529, loss: 0.012655762955546379
2023-01-24 05:53:41.555455: step: 2020/529, loss: 0.012693057768046856
2023-01-24 05:53:42.621781: step: 2024/529, loss: 0.02072948031127453
2023-01-24 05:53:43.695617: step: 2028/529, loss: 0.009843254461884499
2023-01-24 05:53:44.776700: step: 2032/529, loss: 0.00949727650731802
2023-01-24 05:53:45.848279: step: 2036/529, loss: 0.007400128059089184
2023-01-24 05:53:46.938773: step: 2040/529, loss: 0.010082544758915901
2023-01-24 05:53:48.023521: step: 2044/529, loss: 0.012053323909640312
2023-01-24 05:53:49.112842: step: 2048/529, loss: 0.008179706521332264
2023-01-24 05:53:50.190829: step: 2052/529, loss: 0.013202308677136898
2023-01-24 05:53:51.274283: step: 2056/529, loss: 0.023810986429452896
2023-01-24 05:53:52.345020: step: 2060/529, loss: 0.010993927717208862
2023-01-24 05:53:53.423150: step: 2064/529, loss: 0.005121553782373667
2023-01-24 05:53:54.497708: step: 2068/529, loss: 0.04755368083715439
2023-01-24 05:53:55.579191: step: 2072/529, loss: 0.06176955997943878
2023-01-24 05:53:56.640345: step: 2076/529, loss: 0.00973560567945242
2023-01-24 05:53:57.745698: step: 2080/529, loss: 0.007067820988595486
2023-01-24 05:53:58.819314: step: 2084/529, loss: 0.011963969096541405
2023-01-24 05:53:59.889580: step: 2088/529, loss: 0.011447635479271412
2023-01-24 05:54:00.969964: step: 2092/529, loss: 0.056180067360401154
2023-01-24 05:54:02.039410: step: 2096/529, loss: 0.005715841893106699
2023-01-24 05:54:03.129973: step: 2100/529, loss: 0.006448804400861263
2023-01-24 05:54:04.211634: step: 2104/529, loss: 0.009625070728361607
2023-01-24 05:54:05.296491: step: 2108/529, loss: 0.012132695876061916
2023-01-24 05:54:06.370158: step: 2112/529, loss: 0.002576471772044897
2023-01-24 05:54:07.445034: step: 2116/529, loss: 0.04353349655866623
==================================================
Loss: 0.021
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3347340770689828, 'r': 0.3029756257341647, 'f1': 0.3180640533105673}, 'combined': 0.2343629866498917, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3210072671371102, 'r': 0.29120787928706593, 'f1': 0.3053823350981473}, 'combined': 0.19936877835423086, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3542050764655905, 'r': 0.35958200362256343, 'f1': 0.3568732879643897}, 'combined': 0.26295926481586607, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.345719725922165, 'r': 0.31013093060664804, 'f1': 0.32695974079460566}, 'combined': 0.21345558207316223, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36862724672657937, 'r': 0.3406479490623229, 'f1': 0.35408573797996873}, 'combined': 0.26090528061681906, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35513067799423575, 'r': 0.3025791714160446, 'f1': 0.3267554724572273}, 'combined': 0.21332222554202404, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3675213675213675, 'r': 0.4095238095238095, 'f1': 0.38738738738738737}, 'combined': 0.2582582582582582, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3620689655172414, 'r': 0.45652173913043476, 'f1': 0.4038461538461538}, 'combined': 0.2019230769230769, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, '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': 0.3347340770689828, 'r': 0.3029756257341647, 'f1': 0.3180640533105673}, 'combined': 0.2343629866498917, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3210072671371102, 'r': 0.29120787928706593, 'f1': 0.3053823350981473}, 'combined': 0.19936877835423086, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3675213675213675, 'r': 0.4095238095238095, 'f1': 0.38738738738738737}, 'combined': 0.2582582582582582, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3542050764655905, 'r': 0.35958200362256343, 'f1': 0.3568732879643897}, 'combined': 0.26295926481586607, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.345719725922165, 'r': 0.31013093060664804, 'f1': 0.32695974079460566}, 'combined': 0.21345558207316223, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3620689655172414, 'r': 0.45652173913043476, 'f1': 0.4038461538461538}, 'combined': 0.2019230769230769, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36862724672657937, 'r': 0.3406479490623229, 'f1': 0.35408573797996873}, 'combined': 0.26090528061681906, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35513067799423575, 'r': 0.3025791714160446, 'f1': 0.3267554724572273}, 'combined': 0.21332222554202404, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:57:05.922592: step: 4/529, loss: 0.006389554124325514
2023-01-24 05:57:06.973478: step: 8/529, loss: 0.03755481541156769
2023-01-24 05:57:08.052539: step: 12/529, loss: 0.007507758215069771
2023-01-24 05:57:09.097954: step: 16/529, loss: 0.027793176472187042
2023-01-24 05:57:10.161955: step: 20/529, loss: 0.014019597321748734
2023-01-24 05:57:11.237336: step: 24/529, loss: 0.025989636778831482
2023-01-24 05:57:12.298331: step: 28/529, loss: 0.0033279864583164454
2023-01-24 05:57:13.365351: step: 32/529, loss: 0.007357017602771521
2023-01-24 05:57:14.443343: step: 36/529, loss: 0.0425308533012867
2023-01-24 05:57:15.517260: step: 40/529, loss: 0.005761740263551474
2023-01-24 05:57:16.584281: step: 44/529, loss: 0.007748181466013193
2023-01-24 05:57:17.643662: step: 48/529, loss: 0.011610709130764008
2023-01-24 05:57:18.714701: step: 52/529, loss: 0.006128428038209677
2023-01-24 05:57:19.815118: step: 56/529, loss: 0.011070339009165764
2023-01-24 05:57:20.903506: step: 60/529, loss: 0.013912631198763847
2023-01-24 05:57:21.984119: step: 64/529, loss: 0.008094375021755695
2023-01-24 05:57:23.050890: step: 68/529, loss: 0.009871361777186394
2023-01-24 05:57:24.115549: step: 72/529, loss: 0.006932706106454134
2023-01-24 05:57:25.192319: step: 76/529, loss: 0.006453662179410458
2023-01-24 05:57:26.259871: step: 80/529, loss: 0.00603462615981698
2023-01-24 05:57:27.334318: step: 84/529, loss: 0.0460745170712471
2023-01-24 05:57:28.409275: step: 88/529, loss: 0.008818504400551319
2023-01-24 05:57:29.504690: step: 92/529, loss: 0.006742529571056366
2023-01-24 05:57:30.592560: step: 96/529, loss: 0.009727596305310726
2023-01-24 05:57:31.665828: step: 100/529, loss: 0.009798946790397167
2023-01-24 05:57:32.740715: step: 104/529, loss: 0.016682641580700874
2023-01-24 05:57:33.819777: step: 108/529, loss: 0.010820260271430016
2023-01-24 05:57:34.892286: step: 112/529, loss: 0.0023955171927809715
2023-01-24 05:57:35.962191: step: 116/529, loss: 0.005558701232075691
2023-01-24 05:57:37.035057: step: 120/529, loss: 0.002182362601161003
2023-01-24 05:57:38.104149: step: 124/529, loss: 0.02721530944108963
2023-01-24 05:57:39.187653: step: 128/529, loss: 0.03818333148956299
2023-01-24 05:57:40.258563: step: 132/529, loss: 0.014669663272798061
2023-01-24 05:57:41.319614: step: 136/529, loss: 0.009535056538879871
2023-01-24 05:57:42.409678: step: 140/529, loss: 0.018070055171847343
2023-01-24 05:57:43.470256: step: 144/529, loss: 0.0028326385654509068
2023-01-24 05:57:44.548742: step: 148/529, loss: 0.0418134406208992
2023-01-24 05:57:45.625939: step: 152/529, loss: 0.04009309038519859
2023-01-24 05:57:46.704276: step: 156/529, loss: 0.028574738651514053
2023-01-24 05:57:47.783341: step: 160/529, loss: 0.03564642742276192
2023-01-24 05:57:48.851176: step: 164/529, loss: 0.012470312416553497
2023-01-24 05:57:49.924717: step: 168/529, loss: 0.0017326278612017632
2023-01-24 05:57:51.001620: step: 172/529, loss: 0.005212576128542423
2023-01-24 05:57:52.078289: step: 176/529, loss: 0.012050974182784557
2023-01-24 05:57:53.150039: step: 180/529, loss: 0.00785812083631754
2023-01-24 05:57:54.224529: step: 184/529, loss: 0.06717624515295029
2023-01-24 05:57:55.304450: step: 188/529, loss: 0.008724033832550049
2023-01-24 05:57:56.381017: step: 192/529, loss: 0.019697142764925957
2023-01-24 05:57:57.476331: step: 196/529, loss: 0.006172453984618187
2023-01-24 05:57:58.560098: step: 200/529, loss: 0.014866306446492672
2023-01-24 05:57:59.660979: step: 204/529, loss: 0.052562814205884933
2023-01-24 05:58:00.746509: step: 208/529, loss: 0.00932515412569046
2023-01-24 05:58:01.832197: step: 212/529, loss: 0.011283752508461475
2023-01-24 05:58:02.925245: step: 216/529, loss: 0.007453024387359619
2023-01-24 05:58:04.010081: step: 220/529, loss: 0.007802099920809269
2023-01-24 05:58:05.077516: step: 224/529, loss: 0.008974428288638592
2023-01-24 05:58:06.151458: step: 228/529, loss: 0.014008049853146076
2023-01-24 05:58:07.232016: step: 232/529, loss: 0.032013390213251114
2023-01-24 05:58:08.336380: step: 236/529, loss: 0.007799850776791573
2023-01-24 05:58:09.400229: step: 240/529, loss: 0.006839349400252104
2023-01-24 05:58:10.474834: step: 244/529, loss: 0.01127974409610033
2023-01-24 05:58:11.572475: step: 248/529, loss: 0.005647597834467888
2023-01-24 05:58:12.648710: step: 252/529, loss: 0.007228284142911434
2023-01-24 05:58:13.729696: step: 256/529, loss: 0.008763637393712997
2023-01-24 05:58:14.798116: step: 260/529, loss: 0.009788310155272484
2023-01-24 05:58:15.894397: step: 264/529, loss: 0.009001868776977062
2023-01-24 05:58:16.983094: step: 268/529, loss: 0.01717890240252018
2023-01-24 05:58:18.061804: step: 272/529, loss: 0.011038258671760559
2023-01-24 05:58:19.133347: step: 276/529, loss: 0.04749833419919014
2023-01-24 05:58:20.211742: step: 280/529, loss: 0.0075602903962135315
2023-01-24 05:58:21.290926: step: 284/529, loss: 0.014721144922077656
2023-01-24 05:58:22.387170: step: 288/529, loss: 0.0094086192548275
2023-01-24 05:58:23.476829: step: 292/529, loss: 0.04242559149861336
2023-01-24 05:58:24.542716: step: 296/529, loss: 0.01724233664572239
2023-01-24 05:58:25.623605: step: 300/529, loss: 0.019524725154042244
2023-01-24 05:58:26.709885: step: 304/529, loss: 0.005104272160679102
2023-01-24 05:58:27.795391: step: 308/529, loss: 0.01220310851931572
2023-01-24 05:58:28.893967: step: 312/529, loss: 0.022783854976296425
2023-01-24 05:58:29.994834: step: 316/529, loss: 0.04930324852466583
2023-01-24 05:58:31.092713: step: 320/529, loss: 0.028871264308691025
2023-01-24 05:58:32.172984: step: 324/529, loss: 0.0047592404298484325
2023-01-24 05:58:33.289692: step: 328/529, loss: 0.031854189932346344
2023-01-24 05:58:34.382606: step: 332/529, loss: 0.003642053809016943
2023-01-24 05:58:35.473918: step: 336/529, loss: 0.005386331118643284
2023-01-24 05:58:36.559034: step: 340/529, loss: 0.013746044598519802
2023-01-24 05:58:37.669958: step: 344/529, loss: 0.04910745471715927
2023-01-24 05:58:38.746143: step: 348/529, loss: 0.02622928097844124
2023-01-24 05:58:39.843991: step: 352/529, loss: 0.00903019867837429
2023-01-24 05:58:40.949270: step: 356/529, loss: 0.005778355058282614
2023-01-24 05:58:42.031885: step: 360/529, loss: 0.024011900648474693
2023-01-24 05:58:43.128075: step: 364/529, loss: 0.014881373383104801
2023-01-24 05:58:44.228074: step: 368/529, loss: 0.007700710091739893
2023-01-24 05:58:45.314380: step: 372/529, loss: 0.011685631237924099
2023-01-24 05:58:46.389433: step: 376/529, loss: 0.03502241149544716
2023-01-24 05:58:47.486874: step: 380/529, loss: 0.014022661373019218
2023-01-24 05:58:48.573573: step: 384/529, loss: 0.008072962984442711
2023-01-24 05:58:49.641082: step: 388/529, loss: 0.015174179337918758
2023-01-24 05:58:50.721894: step: 392/529, loss: 0.014057688415050507
2023-01-24 05:58:51.797921: step: 396/529, loss: 0.006233478896319866
2023-01-24 05:58:52.887142: step: 400/529, loss: 0.033747125416994095
2023-01-24 05:58:53.974475: step: 404/529, loss: 0.01181731279939413
2023-01-24 05:58:55.065009: step: 408/529, loss: 0.009264535270631313
2023-01-24 05:58:56.139245: step: 412/529, loss: 0.0316186398267746
2023-01-24 05:58:57.252220: step: 416/529, loss: 0.017516102641820908
2023-01-24 05:58:58.325789: step: 420/529, loss: 0.0
2023-01-24 05:58:59.396431: step: 424/529, loss: 0.0067905536852777
2023-01-24 05:59:00.476926: step: 428/529, loss: 0.01274697482585907
2023-01-24 05:59:01.575920: step: 432/529, loss: 0.014057214371860027
2023-01-24 05:59:02.672932: step: 436/529, loss: 0.010879402048885822
2023-01-24 05:59:03.765564: step: 440/529, loss: 0.0435330756008625
2023-01-24 05:59:04.863622: step: 444/529, loss: 0.0361146405339241
2023-01-24 05:59:05.981994: step: 448/529, loss: 0.025848638266324997
2023-01-24 05:59:07.061172: step: 452/529, loss: 0.03951834514737129
2023-01-24 05:59:08.140496: step: 456/529, loss: 0.03723164275288582
2023-01-24 05:59:09.236984: step: 460/529, loss: 0.03215601295232773
2023-01-24 05:59:10.317960: step: 464/529, loss: 0.02577909082174301
2023-01-24 05:59:11.402058: step: 468/529, loss: 0.02198733203113079
2023-01-24 05:59:12.503214: step: 472/529, loss: 0.009233383461833
2023-01-24 05:59:13.596837: step: 476/529, loss: 0.008173203095793724
2023-01-24 05:59:14.701693: step: 480/529, loss: 0.006877875421196222
2023-01-24 05:59:15.789882: step: 484/529, loss: 0.021933211013674736
2023-01-24 05:59:16.879144: step: 488/529, loss: 0.0135538624599576
2023-01-24 05:59:17.977976: step: 492/529, loss: 0.007879468612372875
2023-01-24 05:59:19.065007: step: 496/529, loss: 0.015126294456422329
2023-01-24 05:59:20.168204: step: 500/529, loss: 0.029508234933018684
2023-01-24 05:59:21.239825: step: 504/529, loss: 0.0085877301171422
2023-01-24 05:59:22.317451: step: 508/529, loss: 0.002188845770433545
2023-01-24 05:59:23.406932: step: 512/529, loss: 0.015549305826425552
2023-01-24 05:59:24.471109: step: 516/529, loss: 0.0
2023-01-24 05:59:25.552290: step: 520/529, loss: 0.008136602118611336
2023-01-24 05:59:26.640718: step: 524/529, loss: 0.021008729934692383
2023-01-24 05:59:27.714396: step: 528/529, loss: 0.02992773801088333
2023-01-24 05:59:28.818012: step: 532/529, loss: 0.018168631941080093
2023-01-24 05:59:29.910710: step: 536/529, loss: 0.028462180867791176
2023-01-24 05:59:31.001798: step: 540/529, loss: 0.01713193953037262
2023-01-24 05:59:32.071772: step: 544/529, loss: 0.005905382800847292
2023-01-24 05:59:33.178466: step: 548/529, loss: 0.007970664650201797
2023-01-24 05:59:34.291948: step: 552/529, loss: 0.011371022090315819
2023-01-24 05:59:35.365561: step: 556/529, loss: 0.0017865701811388135
2023-01-24 05:59:36.447317: step: 560/529, loss: 0.025730127468705177
2023-01-24 05:59:37.531488: step: 564/529, loss: 0.011516742408275604
2023-01-24 05:59:38.622087: step: 568/529, loss: 0.0
2023-01-24 05:59:39.704369: step: 572/529, loss: 0.03642452508211136
2023-01-24 05:59:40.783742: step: 576/529, loss: 0.004339108243584633
2023-01-24 05:59:41.873243: step: 580/529, loss: 0.011853300034999847
2023-01-24 05:59:42.946397: step: 584/529, loss: 0.010838539339601994
2023-01-24 05:59:44.036942: step: 588/529, loss: 0.00917479395866394
2023-01-24 05:59:45.122607: step: 592/529, loss: 0.00919092632830143
2023-01-24 05:59:46.201904: step: 596/529, loss: 0.03562064841389656
2023-01-24 05:59:47.267926: step: 600/529, loss: 0.004526804201304913
2023-01-24 05:59:48.357046: step: 604/529, loss: 0.013805286958813667
2023-01-24 05:59:49.447109: step: 608/529, loss: 0.005685083568096161
2023-01-24 05:59:50.533447: step: 612/529, loss: 0.02160307951271534
2023-01-24 05:59:51.601730: step: 616/529, loss: 0.014341292902827263
2023-01-24 05:59:52.680706: step: 620/529, loss: 0.013234489597380161
2023-01-24 05:59:53.761725: step: 624/529, loss: 0.014834756962954998
2023-01-24 05:59:54.839158: step: 628/529, loss: 0.031487688422203064
2023-01-24 05:59:55.919482: step: 632/529, loss: 0.01619633287191391
2023-01-24 05:59:57.009144: step: 636/529, loss: 0.010047301650047302
2023-01-24 05:59:58.095298: step: 640/529, loss: 0.025032538920640945
2023-01-24 05:59:59.181050: step: 644/529, loss: 0.021785518154501915
2023-01-24 06:00:00.283535: step: 648/529, loss: 0.045387152582407
2023-01-24 06:00:01.416377: step: 652/529, loss: 0.01219183299690485
2023-01-24 06:00:02.512152: step: 656/529, loss: 0.005538894794881344
2023-01-24 06:00:03.610835: step: 660/529, loss: 0.05428878590464592
2023-01-24 06:00:04.695501: step: 664/529, loss: 0.043511323630809784
2023-01-24 06:00:05.825916: step: 668/529, loss: 0.006223185453563929
2023-01-24 06:00:06.899310: step: 672/529, loss: 0.0052870032377541065
2023-01-24 06:00:07.958159: step: 676/529, loss: 0.009733655489981174
2023-01-24 06:00:09.041326: step: 680/529, loss: 0.01350930705666542
2023-01-24 06:00:10.132013: step: 684/529, loss: 0.07173962891101837
2023-01-24 06:00:11.231265: step: 688/529, loss: 0.007063969038426876
2023-01-24 06:00:12.319591: step: 692/529, loss: 0.004214726388454437
2023-01-24 06:00:13.401199: step: 696/529, loss: 0.008578401058912277
2023-01-24 06:00:14.490042: step: 700/529, loss: 0.010689918883144855
2023-01-24 06:00:15.574852: step: 704/529, loss: 0.018659910187125206
2023-01-24 06:00:16.649633: step: 708/529, loss: 0.009841065853834152
2023-01-24 06:00:17.731982: step: 712/529, loss: 0.008847055025398731
2023-01-24 06:00:18.818723: step: 716/529, loss: 0.004942535422742367
2023-01-24 06:00:19.876181: step: 720/529, loss: 0.004865266848355532
2023-01-24 06:00:20.950765: step: 724/529, loss: 0.00932259950786829
2023-01-24 06:00:22.028761: step: 728/529, loss: 0.007701905444264412
2023-01-24 06:00:23.105792: step: 732/529, loss: 0.006199746858328581
2023-01-24 06:00:24.200233: step: 736/529, loss: 0.04192938283085823
2023-01-24 06:00:25.282093: step: 740/529, loss: 0.008602647110819817
2023-01-24 06:00:26.368111: step: 744/529, loss: 0.0036116524133831263
2023-01-24 06:00:27.469521: step: 748/529, loss: 0.005802961066365242
2023-01-24 06:00:28.564595: step: 752/529, loss: 0.03189490735530853
2023-01-24 06:00:29.631737: step: 756/529, loss: 0.010053660720586777
2023-01-24 06:00:30.719601: step: 760/529, loss: 0.02291499264538288
2023-01-24 06:00:31.803648: step: 764/529, loss: 0.019252410158514977
2023-01-24 06:00:32.896981: step: 768/529, loss: 0.027998756617307663
2023-01-24 06:00:33.988205: step: 772/529, loss: 0.01739143207669258
2023-01-24 06:00:35.074741: step: 776/529, loss: 0.058801185339689255
2023-01-24 06:00:36.150253: step: 780/529, loss: 0.0017137709073722363
2023-01-24 06:00:37.228791: step: 784/529, loss: 0.004182151053100824
2023-01-24 06:00:38.305916: step: 788/529, loss: 0.02712380699813366
2023-01-24 06:00:39.388479: step: 792/529, loss: 0.00687322486191988
2023-01-24 06:00:40.467993: step: 796/529, loss: 0.016469301655888557
2023-01-24 06:00:41.540937: step: 800/529, loss: 0.0029740245081484318
2023-01-24 06:00:42.637190: step: 804/529, loss: 0.003832004964351654
2023-01-24 06:00:43.713412: step: 808/529, loss: 0.02452721633017063
2023-01-24 06:00:44.813247: step: 812/529, loss: 0.0071546658873558044
2023-01-24 06:00:45.902763: step: 816/529, loss: 0.009976695291697979
2023-01-24 06:00:47.007601: step: 820/529, loss: 0.04803130775690079
2023-01-24 06:00:48.116355: step: 824/529, loss: 0.0054082116112113
2023-01-24 06:00:49.185398: step: 828/529, loss: 0.01031528227031231
2023-01-24 06:00:50.271203: step: 832/529, loss: 0.009105538949370384
2023-01-24 06:00:51.338682: step: 836/529, loss: 0.017155827954411507
2023-01-24 06:00:52.425492: step: 840/529, loss: 0.0072313230484724045
2023-01-24 06:00:53.523889: step: 844/529, loss: 0.005047089885920286
2023-01-24 06:00:54.589375: step: 848/529, loss: 0.003133185440674424
2023-01-24 06:00:55.675296: step: 852/529, loss: 0.024824628606438637
2023-01-24 06:00:56.749870: step: 856/529, loss: 0.002959504257887602
2023-01-24 06:00:57.830525: step: 860/529, loss: 0.023963922634720802
2023-01-24 06:00:58.925060: step: 864/529, loss: 0.011016862466931343
2023-01-24 06:00:59.994180: step: 868/529, loss: 0.009529675357043743
2023-01-24 06:01:01.066321: step: 872/529, loss: 0.019599657505750656
2023-01-24 06:01:02.138850: step: 876/529, loss: 0.006038099527359009
2023-01-24 06:01:03.206383: step: 880/529, loss: 0.010600242763757706
2023-01-24 06:01:04.293199: step: 884/529, loss: 0.011199026368558407
2023-01-24 06:01:05.372664: step: 888/529, loss: 0.021132322028279305
2023-01-24 06:01:06.432997: step: 892/529, loss: 0.0387236662209034
2023-01-24 06:01:07.517044: step: 896/529, loss: 0.006413321942090988
2023-01-24 06:01:08.595920: step: 900/529, loss: 0.04611104726791382
2023-01-24 06:01:09.671760: step: 904/529, loss: 0.007502878084778786
2023-01-24 06:01:10.747075: step: 908/529, loss: 0.0413038432598114
2023-01-24 06:01:11.827725: step: 912/529, loss: 0.006357306148856878
2023-01-24 06:01:12.936806: step: 916/529, loss: 0.004701308906078339
2023-01-24 06:01:14.022534: step: 920/529, loss: 0.011431719176471233
2023-01-24 06:01:15.086032: step: 924/529, loss: 0.008504052646458149
2023-01-24 06:01:16.145455: step: 928/529, loss: 0.005382700357586145
2023-01-24 06:01:17.215207: step: 932/529, loss: 0.012047774158418179
2023-01-24 06:01:18.287350: step: 936/529, loss: 0.006272532045841217
2023-01-24 06:01:19.364116: step: 940/529, loss: 0.0053003947250545025
2023-01-24 06:01:20.433418: step: 944/529, loss: 0.012830831110477448
2023-01-24 06:01:21.525297: step: 948/529, loss: 0.00279985461384058
2023-01-24 06:01:22.584723: step: 952/529, loss: 0.04484260454773903
2023-01-24 06:01:23.665077: step: 956/529, loss: 0.027535611763596535
2023-01-24 06:01:24.728103: step: 960/529, loss: 0.01332399994134903
2023-01-24 06:01:25.804304: step: 964/529, loss: 0.007254543714225292
2023-01-24 06:01:26.875893: step: 968/529, loss: 0.0031458751764148474
2023-01-24 06:01:27.954751: step: 972/529, loss: 0.006339004263281822
2023-01-24 06:01:29.019213: step: 976/529, loss: 0.019019586965441704
2023-01-24 06:01:30.095448: step: 980/529, loss: 0.004889925941824913
2023-01-24 06:01:31.175237: step: 984/529, loss: 0.02319488115608692
2023-01-24 06:01:32.248048: step: 988/529, loss: 0.011226978152990341
2023-01-24 06:01:33.321900: step: 992/529, loss: 0.0025775248650461435
2023-01-24 06:01:34.371137: step: 996/529, loss: 0.07843223214149475
2023-01-24 06:01:35.443059: step: 1000/529, loss: 0.004787592217326164
2023-01-24 06:01:36.520550: step: 1004/529, loss: 0.009302588179707527
2023-01-24 06:01:37.595958: step: 1008/529, loss: 0.005800108425319195
2023-01-24 06:01:38.676695: step: 1012/529, loss: 0.008581769652664661
2023-01-24 06:01:39.738250: step: 1016/529, loss: 0.011314456351101398
2023-01-24 06:01:40.797356: step: 1020/529, loss: 0.0028924960643053055
2023-01-24 06:01:41.873420: step: 1024/529, loss: 0.008326766081154346
2023-01-24 06:01:42.953001: step: 1028/529, loss: 0.015010037459433079
2023-01-24 06:01:44.023705: step: 1032/529, loss: 0.004664513282477856
2023-01-24 06:01:45.113482: step: 1036/529, loss: 0.009582985192537308
2023-01-24 06:01:46.183868: step: 1040/529, loss: 0.011315559037029743
2023-01-24 06:01:47.269124: step: 1044/529, loss: 0.02792517840862274
2023-01-24 06:01:48.344715: step: 1048/529, loss: 0.002590895164757967
2023-01-24 06:01:49.414812: step: 1052/529, loss: 0.0076039452105760574
2023-01-24 06:01:50.484745: step: 1056/529, loss: 0.01580253429710865
2023-01-24 06:01:51.557227: step: 1060/529, loss: 0.04356185719370842
2023-01-24 06:01:52.631429: step: 1064/529, loss: 0.0076228417456150055
2023-01-24 06:01:53.695881: step: 1068/529, loss: 0.007826216518878937
2023-01-24 06:01:54.758381: step: 1072/529, loss: 0.007501887157559395
2023-01-24 06:01:55.878598: step: 1076/529, loss: 0.018637852743268013
2023-01-24 06:01:56.952402: step: 1080/529, loss: 0.009781665168702602
2023-01-24 06:01:58.021544: step: 1084/529, loss: 0.002811392769217491
2023-01-24 06:01:59.105103: step: 1088/529, loss: 0.009726126678287983
2023-01-24 06:02:00.181015: step: 1092/529, loss: 0.011768890544772148
2023-01-24 06:02:01.253781: step: 1096/529, loss: 0.032852720469236374
2023-01-24 06:02:02.344124: step: 1100/529, loss: 0.004471438936889172
2023-01-24 06:02:03.417999: step: 1104/529, loss: 0.007103884592652321
2023-01-24 06:02:04.496178: step: 1108/529, loss: 0.016453972086310387
2023-01-24 06:02:05.561761: step: 1112/529, loss: 0.008063547313213348
2023-01-24 06:02:06.626627: step: 1116/529, loss: 0.02745014987885952
2023-01-24 06:02:07.707432: step: 1120/529, loss: 0.01557265967130661
2023-01-24 06:02:08.775410: step: 1124/529, loss: 0.013674561865627766
2023-01-24 06:02:09.832475: step: 1128/529, loss: 0.0029267645440995693
2023-01-24 06:02:10.913289: step: 1132/529, loss: 0.005986180156469345
2023-01-24 06:02:12.002260: step: 1136/529, loss: 0.009181891568005085
2023-01-24 06:02:13.101361: step: 1140/529, loss: 0.005270898342132568
2023-01-24 06:02:14.170952: step: 1144/529, loss: 0.039514750242233276
2023-01-24 06:02:15.242009: step: 1148/529, loss: 0.027101781219244003
2023-01-24 06:02:16.304561: step: 1152/529, loss: 0.011535374447703362
2023-01-24 06:02:17.384342: step: 1156/529, loss: 0.042968783527612686
2023-01-24 06:02:18.456656: step: 1160/529, loss: 0.006305822171270847
2023-01-24 06:02:19.530200: step: 1164/529, loss: 0.02580130472779274
2023-01-24 06:02:20.604722: step: 1168/529, loss: 0.009113805368542671
2023-01-24 06:02:21.682279: step: 1172/529, loss: 0.010318076238036156
2023-01-24 06:02:22.754871: step: 1176/529, loss: 0.004338184371590614
2023-01-24 06:02:23.824066: step: 1180/529, loss: 0.005512248259037733
2023-01-24 06:02:24.891233: step: 1184/529, loss: 0.02038363367319107
2023-01-24 06:02:25.964610: step: 1188/529, loss: 0.01213717833161354
2023-01-24 06:02:27.028285: step: 1192/529, loss: 0.010896789841353893
2023-01-24 06:02:28.112570: step: 1196/529, loss: 0.007011616602540016
2023-01-24 06:02:29.183235: step: 1200/529, loss: 0.011035246774554253
2023-01-24 06:02:30.238227: step: 1204/529, loss: 0.010063204914331436
2023-01-24 06:02:31.309675: step: 1208/529, loss: 0.027120720595121384
2023-01-24 06:02:32.393667: step: 1212/529, loss: 0.03099985048174858
2023-01-24 06:02:33.466911: step: 1216/529, loss: 0.03999115526676178
2023-01-24 06:02:34.529702: step: 1220/529, loss: 0.00536049110814929
2023-01-24 06:02:35.604572: step: 1224/529, loss: 0.02533509023487568
2023-01-24 06:02:36.684735: step: 1228/529, loss: 0.007261867169290781
2023-01-24 06:02:37.764432: step: 1232/529, loss: 0.021081771701574326
2023-01-24 06:02:38.860667: step: 1236/529, loss: 0.013951675035059452
2023-01-24 06:02:39.935963: step: 1240/529, loss: 0.0072111631743609905
2023-01-24 06:02:41.006271: step: 1244/529, loss: 0.011290324851870537
2023-01-24 06:02:42.064112: step: 1248/529, loss: 0.0023878600914031267
2023-01-24 06:02:43.131832: step: 1252/529, loss: 0.009116090834140778
2023-01-24 06:02:44.210748: step: 1256/529, loss: 0.013053000904619694
2023-01-24 06:02:45.278899: step: 1260/529, loss: 0.01214775163680315
2023-01-24 06:02:46.349294: step: 1264/529, loss: 0.005877509247511625
2023-01-24 06:02:47.428023: step: 1268/529, loss: 0.011246110312640667
2023-01-24 06:02:48.492463: step: 1272/529, loss: 0.016227534040808678
2023-01-24 06:02:49.560683: step: 1276/529, loss: 0.01072680950164795
2023-01-24 06:02:50.622377: step: 1280/529, loss: 0.008840692229568958
2023-01-24 06:02:51.681344: step: 1284/529, loss: 0.011864015832543373
2023-01-24 06:02:52.777542: step: 1288/529, loss: 0.014883642084896564
2023-01-24 06:02:53.838703: step: 1292/529, loss: 0.004966744687408209
2023-01-24 06:02:54.911658: step: 1296/529, loss: 0.04509740695357323
2023-01-24 06:02:55.976055: step: 1300/529, loss: 0.00328592280857265
2023-01-24 06:02:57.073617: step: 1304/529, loss: 0.00690871849656105
2023-01-24 06:02:58.129236: step: 1308/529, loss: 0.03959457948803902
2023-01-24 06:02:59.193554: step: 1312/529, loss: 0.04519904404878616
2023-01-24 06:03:00.253624: step: 1316/529, loss: 0.021984321996569633
2023-01-24 06:03:01.316980: step: 1320/529, loss: 0.006843100767582655
2023-01-24 06:03:02.395503: step: 1324/529, loss: 0.044762954115867615
2023-01-24 06:03:03.470707: step: 1328/529, loss: 0.014802508056163788
2023-01-24 06:03:04.543533: step: 1332/529, loss: 0.00244291708804667
2023-01-24 06:03:05.603823: step: 1336/529, loss: 0.009213568642735481
2023-01-24 06:03:06.676437: step: 1340/529, loss: 0.011801140382885933
2023-01-24 06:03:07.743312: step: 1344/529, loss: 0.012021483853459358
2023-01-24 06:03:08.816156: step: 1348/529, loss: 0.006623891647905111
2023-01-24 06:03:09.897659: step: 1352/529, loss: 0.005431486293673515
2023-01-24 06:03:10.976778: step: 1356/529, loss: 0.06648432463407516
2023-01-24 06:03:12.051120: step: 1360/529, loss: 0.010971464216709137
2023-01-24 06:03:13.133542: step: 1364/529, loss: 0.029019389301538467
2023-01-24 06:03:14.206648: step: 1368/529, loss: 0.018898412585258484
2023-01-24 06:03:15.294636: step: 1372/529, loss: 0.009463388472795486
2023-01-24 06:03:16.354975: step: 1376/529, loss: 0.006287693046033382
2023-01-24 06:03:17.423704: step: 1380/529, loss: 0.003187919734045863
2023-01-24 06:03:18.524783: step: 1384/529, loss: 0.003515623277053237
2023-01-24 06:03:19.610419: step: 1388/529, loss: 0.0026332989800721407
2023-01-24 06:03:20.687710: step: 1392/529, loss: 0.009394300170242786
2023-01-24 06:03:21.764257: step: 1396/529, loss: 0.004997484851628542
2023-01-24 06:03:22.829272: step: 1400/529, loss: 0.009509800933301449
2023-01-24 06:03:23.904699: step: 1404/529, loss: 0.00559243792667985
2023-01-24 06:03:24.983767: step: 1408/529, loss: 0.0076534803956747055
2023-01-24 06:03:26.055187: step: 1412/529, loss: 0.08146931231021881
2023-01-24 06:03:27.109758: step: 1416/529, loss: 0.010398810729384422
2023-01-24 06:03:28.184189: step: 1420/529, loss: 0.010525343008339405
2023-01-24 06:03:29.259192: step: 1424/529, loss: 0.05010334774851799
2023-01-24 06:03:30.322701: step: 1428/529, loss: 0.005588009022176266
2023-01-24 06:03:31.394607: step: 1432/529, loss: 0.00919264554977417
2023-01-24 06:03:32.460649: step: 1436/529, loss: 0.006516479421406984
2023-01-24 06:03:33.544182: step: 1440/529, loss: 0.013326709158718586
2023-01-24 06:03:34.609799: step: 1444/529, loss: 0.0029639750719070435
2023-01-24 06:03:35.673842: step: 1448/529, loss: 0.010421779938042164
2023-01-24 06:03:36.734048: step: 1452/529, loss: 0.007942502386868
2023-01-24 06:03:37.811677: step: 1456/529, loss: 0.035399384796619415
2023-01-24 06:03:38.888570: step: 1460/529, loss: 0.006975781638175249
2023-01-24 06:03:39.983248: step: 1464/529, loss: 0.05700681731104851
2023-01-24 06:03:41.048553: step: 1468/529, loss: 0.00598968006670475
2023-01-24 06:03:42.101285: step: 1472/529, loss: 0.010580715723335743
2023-01-24 06:03:43.181033: step: 1476/529, loss: 0.0077400836162269115
2023-01-24 06:03:44.252340: step: 1480/529, loss: 0.005843636114150286
2023-01-24 06:03:45.315904: step: 1484/529, loss: 0.03368179500102997
2023-01-24 06:03:46.386539: step: 1488/529, loss: 0.004991909023374319
2023-01-24 06:03:47.457120: step: 1492/529, loss: 0.039475228637456894
2023-01-24 06:03:48.539466: step: 1496/529, loss: 0.020836995914578438
2023-01-24 06:03:49.615464: step: 1500/529, loss: 0.017095476388931274
2023-01-24 06:03:50.688931: step: 1504/529, loss: 0.007995637133717537
2023-01-24 06:03:51.764470: step: 1508/529, loss: 0.03511830419301987
2023-01-24 06:03:52.846657: step: 1512/529, loss: 0.043007515370845795
2023-01-24 06:03:53.913675: step: 1516/529, loss: 0.003032101085409522
2023-01-24 06:03:54.966980: step: 1520/529, loss: 0.008619263768196106
2023-01-24 06:03:56.045202: step: 1524/529, loss: 0.005864525213837624
2023-01-24 06:03:57.121079: step: 1528/529, loss: 0.0013895228039473295
2023-01-24 06:03:58.198771: step: 1532/529, loss: 0.019807903096079826
2023-01-24 06:03:59.264778: step: 1536/529, loss: 0.007260092534124851
2023-01-24 06:04:00.333711: step: 1540/529, loss: 0.004646764136850834
2023-01-24 06:04:01.390013: step: 1544/529, loss: 0.0028868799563497305
2023-01-24 06:04:02.445398: step: 1548/529, loss: 0.006035225931555033
2023-01-24 06:04:03.514848: step: 1552/529, loss: 0.0023739205207675695
2023-01-24 06:04:04.609516: step: 1556/529, loss: 0.014841475524008274
2023-01-24 06:04:05.697029: step: 1560/529, loss: 0.003927040379494429
2023-01-24 06:04:06.754479: step: 1564/529, loss: 0.013967577368021011
2023-01-24 06:04:07.831751: step: 1568/529, loss: 0.01272412296384573
2023-01-24 06:04:08.896451: step: 1572/529, loss: 0.005824252963066101
2023-01-24 06:04:09.985271: step: 1576/529, loss: 0.007159653585404158
2023-01-24 06:04:11.058713: step: 1580/529, loss: 0.010241798125207424
2023-01-24 06:04:12.130503: step: 1584/529, loss: 0.0177440345287323
2023-01-24 06:04:13.205002: step: 1588/529, loss: 0.002803144045174122
2023-01-24 06:04:14.268690: step: 1592/529, loss: 0.0041565364226698875
2023-01-24 06:04:15.362786: step: 1596/529, loss: 0.04219739884138107
2023-01-24 06:04:16.434547: step: 1600/529, loss: 0.013250652700662613
2023-01-24 06:04:17.495215: step: 1604/529, loss: 0.0059806592762470245
2023-01-24 06:04:18.563569: step: 1608/529, loss: 0.010280859656631947
2023-01-24 06:04:19.628386: step: 1612/529, loss: 0.007436178158968687
2023-01-24 06:04:20.695885: step: 1616/529, loss: 0.009739872999489307
2023-01-24 06:04:21.751745: step: 1620/529, loss: 0.0055679879151284695
2023-01-24 06:04:22.818656: step: 1624/529, loss: 0.05519388988614082
2023-01-24 06:04:23.875824: step: 1628/529, loss: 0.0054127671755850315
2023-01-24 06:04:24.930771: step: 1632/529, loss: 0.03428838029503822
2023-01-24 06:04:26.019229: step: 1636/529, loss: 0.016511430963873863
2023-01-24 06:04:27.081785: step: 1640/529, loss: 0.013362477533519268
2023-01-24 06:04:28.162399: step: 1644/529, loss: 0.04664391279220581
2023-01-24 06:04:29.244295: step: 1648/529, loss: 0.005670679267495871
2023-01-24 06:04:30.312947: step: 1652/529, loss: 0.009138268418610096
2023-01-24 06:04:31.384605: step: 1656/529, loss: 0.018803101032972336
2023-01-24 06:04:32.449035: step: 1660/529, loss: 0.014966643415391445
2023-01-24 06:04:33.508327: step: 1664/529, loss: 0.0032274597324430943
2023-01-24 06:04:34.574380: step: 1668/529, loss: 0.016024164855480194
2023-01-24 06:04:35.652205: step: 1672/529, loss: 0.013423580676317215
2023-01-24 06:04:36.723743: step: 1676/529, loss: 0.0057151103392243385
2023-01-24 06:04:37.797547: step: 1680/529, loss: 0.012827717699110508
2023-01-24 06:04:38.875662: step: 1684/529, loss: 0.005884043872356415
2023-01-24 06:04:39.959329: step: 1688/529, loss: 0.0035296257119625807
2023-01-24 06:04:41.036037: step: 1692/529, loss: 0.02579759992659092
2023-01-24 06:04:42.095881: step: 1696/529, loss: 0.04146649315953255
2023-01-24 06:04:43.184501: step: 1700/529, loss: 0.025786763057112694
2023-01-24 06:04:44.247664: step: 1704/529, loss: 0.00027789032901637256
2023-01-24 06:04:45.317532: step: 1708/529, loss: 0.034782007336616516
2023-01-24 06:04:46.373734: step: 1712/529, loss: 0.008539574220776558
2023-01-24 06:04:47.430868: step: 1716/529, loss: 0.029483728110790253
2023-01-24 06:04:48.499331: step: 1720/529, loss: 0.007934585213661194
2023-01-24 06:04:49.567648: step: 1724/529, loss: 0.05138925090432167
2023-01-24 06:04:50.639275: step: 1728/529, loss: 0.011047548614442348
2023-01-24 06:04:51.712026: step: 1732/529, loss: 0.004193627741187811
2023-01-24 06:04:52.780892: step: 1736/529, loss: 0.005660828202962875
2023-01-24 06:04:53.869828: step: 1740/529, loss: 0.009986856020987034
2023-01-24 06:04:54.933206: step: 1744/529, loss: 0.008113296702504158
2023-01-24 06:04:56.001120: step: 1748/529, loss: 0.004208900034427643
2023-01-24 06:04:57.073364: step: 1752/529, loss: 0.005658932030200958
2023-01-24 06:04:58.138246: step: 1756/529, loss: 0.007513790391385555
2023-01-24 06:04:59.226456: step: 1760/529, loss: 0.006018828600645065
2023-01-24 06:05:00.297372: step: 1764/529, loss: 0.015406571328639984
2023-01-24 06:05:01.367410: step: 1768/529, loss: 0.006777746137231588
2023-01-24 06:05:02.450445: step: 1772/529, loss: 0.016631942242383957
2023-01-24 06:05:03.520963: step: 1776/529, loss: 0.05578795447945595
2023-01-24 06:05:04.586225: step: 1780/529, loss: 0.028491957113146782
2023-01-24 06:05:05.673212: step: 1784/529, loss: 0.009910641238093376
2023-01-24 06:05:06.743912: step: 1788/529, loss: 0.010287641547620296
2023-01-24 06:05:07.825014: step: 1792/529, loss: 0.009349336847662926
2023-01-24 06:05:08.903300: step: 1796/529, loss: 0.010252943262457848
2023-01-24 06:05:09.963934: step: 1800/529, loss: 0.008965574204921722
2023-01-24 06:05:11.025341: step: 1804/529, loss: 0.013064608909189701
2023-01-24 06:05:12.096431: step: 1808/529, loss: 0.0067008123733103275
2023-01-24 06:05:13.185086: step: 1812/529, loss: 0.034985847771167755
2023-01-24 06:05:14.245412: step: 1816/529, loss: 0.0029357224702835083
2023-01-24 06:05:15.320430: step: 1820/529, loss: 0.012511278502643108
2023-01-24 06:05:16.417578: step: 1824/529, loss: 0.014967227354645729
2023-01-24 06:05:17.488399: step: 1828/529, loss: 0.009885610081255436
2023-01-24 06:05:18.570446: step: 1832/529, loss: 0.00869726575911045
2023-01-24 06:05:19.634147: step: 1836/529, loss: 0.005111526697874069
2023-01-24 06:05:20.704152: step: 1840/529, loss: 0.026112454012036324
2023-01-24 06:05:21.778270: step: 1844/529, loss: 0.003226904897019267
2023-01-24 06:05:22.849223: step: 1848/529, loss: 0.006491770502179861
2023-01-24 06:05:23.919763: step: 1852/529, loss: 0.007665010169148445
2023-01-24 06:05:24.995754: step: 1856/529, loss: 0.00772461760789156
2023-01-24 06:05:26.058295: step: 1860/529, loss: 0.005196233280003071
2023-01-24 06:05:27.100869: step: 1864/529, loss: 0.009938716888427734
2023-01-24 06:05:28.179845: step: 1868/529, loss: 0.00214287918061018
2023-01-24 06:05:29.248672: step: 1872/529, loss: 0.023980073630809784
2023-01-24 06:05:30.321007: step: 1876/529, loss: 0.011643702164292336
2023-01-24 06:05:31.405785: step: 1880/529, loss: 0.006355784833431244
2023-01-24 06:05:32.476800: step: 1884/529, loss: 0.023815974593162537
2023-01-24 06:05:33.533187: step: 1888/529, loss: 0.04275970906019211
2023-01-24 06:05:34.594978: step: 1892/529, loss: 0.04026271030306816
2023-01-24 06:05:35.676555: step: 1896/529, loss: 0.005890017841011286
2023-01-24 06:05:36.737741: step: 1900/529, loss: 0.01739628054201603
2023-01-24 06:05:37.795381: step: 1904/529, loss: 0.008714761584997177
2023-01-24 06:05:38.851206: step: 1908/529, loss: 0.00838181097060442
2023-01-24 06:05:39.915038: step: 1912/529, loss: 0.010334637947380543
2023-01-24 06:05:40.985917: step: 1916/529, loss: 0.00658290134742856
2023-01-24 06:05:42.050235: step: 1920/529, loss: 0.05561702698469162
2023-01-24 06:05:43.135831: step: 1924/529, loss: 0.009740826673805714
2023-01-24 06:05:44.210203: step: 1928/529, loss: 0.019930532202124596
2023-01-24 06:05:45.281213: step: 1932/529, loss: 0.008057414554059505
2023-01-24 06:05:46.361975: step: 1936/529, loss: 0.058137282729148865
2023-01-24 06:05:47.419518: step: 1940/529, loss: 0.004486719612032175
2023-01-24 06:05:48.490329: step: 1944/529, loss: 0.01392204500734806
2023-01-24 06:05:49.556690: step: 1948/529, loss: 0.03284474089741707
2023-01-24 06:05:50.639313: step: 1952/529, loss: 0.015019644983112812
2023-01-24 06:05:51.717612: step: 1956/529, loss: 0.013032629154622555
2023-01-24 06:05:52.798478: step: 1960/529, loss: 0.005332757253199816
2023-01-24 06:05:53.857821: step: 1964/529, loss: 0.007482311688363552
2023-01-24 06:05:54.921165: step: 1968/529, loss: 0.01071746926754713
2023-01-24 06:05:55.994501: step: 1972/529, loss: 0.006644145119935274
2023-01-24 06:05:57.080461: step: 1976/529, loss: 0.012638228945434093
2023-01-24 06:05:58.155312: step: 1980/529, loss: 0.03407052159309387
2023-01-24 06:05:59.228016: step: 1984/529, loss: 0.0048530432395637035
2023-01-24 06:06:00.308958: step: 1988/529, loss: 0.05103858932852745
2023-01-24 06:06:01.388989: step: 1992/529, loss: 0.013925762847065926
2023-01-24 06:06:02.462739: step: 1996/529, loss: 0.0031792980153113604
2023-01-24 06:06:03.542284: step: 2000/529, loss: 0.1556052714586258
2023-01-24 06:06:04.608852: step: 2004/529, loss: 0.013302719220519066
2023-01-24 06:06:05.679681: step: 2008/529, loss: 0.018728191033005714
2023-01-24 06:06:06.740126: step: 2012/529, loss: 0.004508196841925383
2023-01-24 06:06:07.804546: step: 2016/529, loss: 0.02374061942100525
2023-01-24 06:06:08.870628: step: 2020/529, loss: 0.011305669322609901
2023-01-24 06:06:09.953369: step: 2024/529, loss: 0.01459311880171299
2023-01-24 06:06:11.028685: step: 2028/529, loss: 0.04293946921825409
2023-01-24 06:06:12.100472: step: 2032/529, loss: 0.009750621393322945
2023-01-24 06:06:13.187832: step: 2036/529, loss: 0.028861336410045624
2023-01-24 06:06:14.244260: step: 2040/529, loss: 0.009075273759663105
2023-01-24 06:06:15.316892: step: 2044/529, loss: 0.0069069270975887775
2023-01-24 06:06:16.392048: step: 2048/529, loss: 0.046794530004262924
2023-01-24 06:06:17.468458: step: 2052/529, loss: 0.004367154091596603
2023-01-24 06:06:18.543304: step: 2056/529, loss: 0.005833095870912075
2023-01-24 06:06:19.613655: step: 2060/529, loss: 0.04321917146444321
2023-01-24 06:06:20.686244: step: 2064/529, loss: 0.006839882116764784
2023-01-24 06:06:21.749335: step: 2068/529, loss: 0.0207469891756773
2023-01-24 06:06:22.829336: step: 2072/529, loss: 0.016233840957283974
2023-01-24 06:06:23.890505: step: 2076/529, loss: 0.0068873390555381775
2023-01-24 06:06:24.967985: step: 2080/529, loss: 0.007550279144197702
2023-01-24 06:06:26.050870: step: 2084/529, loss: 0.005358210299164057
2023-01-24 06:06:27.123513: step: 2088/529, loss: 0.0036425397265702486
2023-01-24 06:06:28.196814: step: 2092/529, loss: 0.0075703030452132225
2023-01-24 06:06:29.255439: step: 2096/529, loss: 0.005759506020694971
2023-01-24 06:06:30.325120: step: 2100/529, loss: 0.0191704872995615
2023-01-24 06:06:31.389344: step: 2104/529, loss: 0.010615777224302292
2023-01-24 06:06:32.451043: step: 2108/529, loss: 0.008621551096439362
2023-01-24 06:06:33.522600: step: 2112/529, loss: 0.006205690558999777
2023-01-24 06:06:34.572255: step: 2116/529, loss: 0.007107949815690517
==================================================
Loss: 0.016
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35673570381231673, 'r': 0.35673570381231673, 'f1': 0.35673570381231673}, 'combined': 0.2628578870196018, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.353761632917999, 'r': 0.3131180629595892, 'f1': 0.3322013188688767}, 'combined': 0.21687754496102832, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36808550341411167, 'r': 0.33875041585549176, 'f1': 0.3528092275807197}, 'combined': 0.2599646940068461, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3638376931950127, 'r': 0.304647186121927, 'f1': 0.33162194947539425}, 'combined': 0.216499303802589, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35673570381231673, 'r': 0.35673570381231673, 'f1': 0.35673570381231673}, 'combined': 0.2628578870196018, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.353761632917999, 'r': 0.3131180629595892, 'f1': 0.3322013188688767}, 'combined': 0.21687754496102832, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36862724672657937, 'r': 0.3406479490623229, 'f1': 0.35408573797996873}, 'combined': 0.26090528061681906, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35513067799423575, 'r': 0.3025791714160446, 'f1': 0.3267554724572273}, 'combined': 0.21332222554202404, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 0}
******************************
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 06:09:23.960816: step: 4/529, loss: 0.010113946162164211
2023-01-24 06:09:25.015000: step: 8/529, loss: 0.023191876709461212
2023-01-24 06:09:26.078798: step: 12/529, loss: 0.006596298422664404
2023-01-24 06:09:27.159555: step: 16/529, loss: 0.0040982491336762905
2023-01-24 06:09:28.236151: step: 20/529, loss: 0.00264414818957448
2023-01-24 06:09:29.287957: step: 24/529, loss: 0.024419303983449936
2023-01-24 06:09:30.358421: step: 28/529, loss: 0.005509079433977604
2023-01-24 06:09:31.416399: step: 32/529, loss: 0.006224116776138544
2023-01-24 06:09:32.478619: step: 36/529, loss: 0.01086567621678114
2023-01-24 06:09:33.551451: step: 40/529, loss: 0.009877790696918964
2023-01-24 06:09:34.612561: step: 44/529, loss: 0.028803030028939247
2023-01-24 06:09:35.690267: step: 48/529, loss: 0.0053496649488806725
2023-01-24 06:09:36.762552: step: 52/529, loss: 0.02631174772977829
2023-01-24 06:09:37.831915: step: 56/529, loss: 0.0009045038023032248
2023-01-24 06:09:38.912110: step: 60/529, loss: 0.007811385206878185
2023-01-24 06:09:39.965463: step: 64/529, loss: 0.011069833301007748
2023-01-24 06:09:41.038003: step: 68/529, loss: 0.01691410318017006
2023-01-24 06:09:42.101962: step: 72/529, loss: 0.017194414511322975
2023-01-24 06:09:43.181679: step: 76/529, loss: 0.009982526302337646
2023-01-24 06:09:44.228542: step: 80/529, loss: 0.022082049399614334
2023-01-24 06:09:45.312245: step: 84/529, loss: 0.005680608097463846
2023-01-24 06:09:46.370460: step: 88/529, loss: 0.00825822725892067
2023-01-24 06:09:47.422007: step: 92/529, loss: 0.005429005715996027
2023-01-24 06:09:48.480251: step: 96/529, loss: 0.0027572272811084986
2023-01-24 06:09:49.539238: step: 100/529, loss: 0.009466941468417645
2023-01-24 06:09:50.614458: step: 104/529, loss: 0.021326912567019463
2023-01-24 06:09:51.675541: step: 108/529, loss: 0.007840532809495926
2023-01-24 06:09:52.752395: step: 112/529, loss: 0.015168609097599983
2023-01-24 06:09:53.814384: step: 116/529, loss: 0.00839829258620739
2023-01-24 06:09:54.888256: step: 120/529, loss: 0.004541113972663879
2023-01-24 06:09:55.951292: step: 124/529, loss: 0.006309458054602146
2023-01-24 06:09:57.001405: step: 128/529, loss: 0.019247012212872505
2023-01-24 06:09:58.081677: step: 132/529, loss: 0.013402356766164303
2023-01-24 06:09:59.155239: step: 136/529, loss: 0.01287771388888359
2023-01-24 06:10:00.237961: step: 140/529, loss: 0.07247739285230637
2023-01-24 06:10:01.308219: step: 144/529, loss: 0.019719649106264114
2023-01-24 06:10:02.368320: step: 148/529, loss: 0.01630535162985325
2023-01-24 06:10:03.446366: step: 152/529, loss: 0.011462540365755558
2023-01-24 06:10:04.537047: step: 156/529, loss: 0.007881594821810722
2023-01-24 06:10:05.625240: step: 160/529, loss: 0.0306947510689497
2023-01-24 06:10:06.720527: step: 164/529, loss: 0.02132401429116726
2023-01-24 06:10:07.783978: step: 168/529, loss: 0.010975182987749577
2023-01-24 06:10:08.850338: step: 172/529, loss: 0.004137462470680475
2023-01-24 06:10:09.922538: step: 176/529, loss: 0.006465671584010124
2023-01-24 06:10:10.986987: step: 180/529, loss: 0.004132358357310295
2023-01-24 06:10:12.049434: step: 184/529, loss: 0.006023016758263111
2023-01-24 06:10:13.113483: step: 188/529, loss: 0.006676420569419861
2023-01-24 06:10:14.181892: step: 192/529, loss: 0.00285189226269722
2023-01-24 06:10:15.258616: step: 196/529, loss: 0.05700604245066643
2023-01-24 06:10:16.331709: step: 200/529, loss: 0.008522611111402512
2023-01-24 06:10:17.408893: step: 204/529, loss: 0.04799949750304222
2023-01-24 06:10:18.504762: step: 208/529, loss: 0.026255574077367783
2023-01-24 06:10:19.573511: step: 212/529, loss: 0.003190845949575305
2023-01-24 06:10:20.654584: step: 216/529, loss: 0.01589416153728962
2023-01-24 06:10:21.727750: step: 220/529, loss: 0.005084800999611616
2023-01-24 06:10:22.820305: step: 224/529, loss: 0.007687171455472708
2023-01-24 06:10:23.895320: step: 228/529, loss: 0.01149655319750309
2023-01-24 06:10:24.968067: step: 232/529, loss: 0.011149103753268719
2023-01-24 06:10:26.042065: step: 236/529, loss: 0.015421555377542973
2023-01-24 06:10:27.106600: step: 240/529, loss: 0.009221922606229782
2023-01-24 06:10:28.176209: step: 244/529, loss: 0.01107594184577465
2023-01-24 06:10:29.249010: step: 248/529, loss: 0.009078064002096653
2023-01-24 06:10:30.324373: step: 252/529, loss: 0.02102748118340969
2023-01-24 06:10:31.413067: step: 256/529, loss: 0.012334208935499191
2023-01-24 06:10:32.476547: step: 260/529, loss: 0.006269046105444431
2023-01-24 06:10:33.546647: step: 264/529, loss: 0.00042572588426992297
2023-01-24 06:10:34.630810: step: 268/529, loss: 0.015571920201182365
2023-01-24 06:10:35.706459: step: 272/529, loss: 0.0068322112783789635
2023-01-24 06:10:36.790305: step: 276/529, loss: 0.029863247647881508
2023-01-24 06:10:37.863060: step: 280/529, loss: 0.008220745250582695
2023-01-24 06:10:38.942191: step: 284/529, loss: 0.011505833826959133
2023-01-24 06:10:40.013651: step: 288/529, loss: 0.0034879117738455534
2023-01-24 06:10:41.084744: step: 292/529, loss: 0.011915769428014755
2023-01-24 06:10:42.163184: step: 296/529, loss: 0.02561418153345585
2023-01-24 06:10:43.248947: step: 300/529, loss: 0.006159918382763863
2023-01-24 06:10:44.315889: step: 304/529, loss: 0.005980865564197302
2023-01-24 06:10:45.399369: step: 308/529, loss: 0.03755580261349678
2023-01-24 06:10:46.474498: step: 312/529, loss: 0.004994974937289953
2023-01-24 06:10:47.563821: step: 316/529, loss: 0.01340450532734394
2023-01-24 06:10:48.643147: step: 320/529, loss: 0.005502969957888126
2023-01-24 06:10:49.721640: step: 324/529, loss: 0.006256521679461002
2023-01-24 06:10:50.795690: step: 328/529, loss: 0.03778060898184776
2023-01-24 06:10:51.875090: step: 332/529, loss: 0.007686616852879524
2023-01-24 06:10:52.966980: step: 336/529, loss: 0.002084204228594899
2023-01-24 06:10:54.046271: step: 340/529, loss: 0.009598198346793652
2023-01-24 06:10:55.135084: step: 344/529, loss: 0.010809702798724174
2023-01-24 06:10:56.205964: step: 348/529, loss: 0.01607486605644226
2023-01-24 06:10:57.296601: step: 352/529, loss: 0.008933251723647118
2023-01-24 06:10:58.378999: step: 356/529, loss: 0.01987755298614502
2023-01-24 06:10:59.448943: step: 360/529, loss: 0.0035100020468235016
2023-01-24 06:11:00.522169: step: 364/529, loss: 0.008190550841391087
2023-01-24 06:11:01.593145: step: 368/529, loss: 0.0072615742683410645
2023-01-24 06:11:02.673142: step: 372/529, loss: 0.039022739976644516
2023-01-24 06:11:03.755396: step: 376/529, loss: 0.007754258345812559
2023-01-24 06:11:04.831537: step: 380/529, loss: 0.00399549026042223
2023-01-24 06:11:05.909331: step: 384/529, loss: 0.008288799785077572
2023-01-24 06:11:06.994428: step: 388/529, loss: 0.006451813969761133
2023-01-24 06:11:08.066135: step: 392/529, loss: 0.007065907120704651
2023-01-24 06:11:09.170416: step: 396/529, loss: 0.05141688883304596
2023-01-24 06:11:10.238692: step: 400/529, loss: 0.00629222160205245
2023-01-24 06:11:11.309520: step: 404/529, loss: 0.012433497235178947
2023-01-24 06:11:12.394431: step: 408/529, loss: 0.01031239703297615
2023-01-24 06:11:13.465390: step: 412/529, loss: 0.008377622812986374
2023-01-24 06:11:14.536992: step: 416/529, loss: 0.0024060921277850866
2023-01-24 06:11:15.608055: step: 420/529, loss: 0.008515998721122742
2023-01-24 06:11:16.687835: step: 424/529, loss: 0.011796880513429642
2023-01-24 06:11:17.768342: step: 428/529, loss: 0.0015517441788688302
2023-01-24 06:11:18.871542: step: 432/529, loss: 0.005994210485368967
2023-01-24 06:11:19.970989: step: 436/529, loss: 0.006786423735320568
2023-01-24 06:11:21.044576: step: 440/529, loss: 0.014521707780659199
2023-01-24 06:11:22.129789: step: 444/529, loss: 0.006072856020182371
2023-01-24 06:11:23.210485: step: 448/529, loss: 0.014734000898897648
2023-01-24 06:11:24.303632: step: 452/529, loss: 0.012063873000442982
2023-01-24 06:11:25.388108: step: 456/529, loss: 0.010869873687624931
2023-01-24 06:11:26.474783: step: 460/529, loss: 0.0059290737845003605
2023-01-24 06:11:27.541400: step: 464/529, loss: 0.030661994591355324
2023-01-24 06:11:28.622113: step: 468/529, loss: 0.03214063495397568
2023-01-24 06:11:29.710209: step: 472/529, loss: 0.008816438727080822
2023-01-24 06:11:30.796854: step: 476/529, loss: 0.006373694632202387
2023-01-24 06:11:31.878299: step: 480/529, loss: 0.01191974338144064
2023-01-24 06:11:32.944836: step: 484/529, loss: 0.005648419726639986
2023-01-24 06:11:34.051368: step: 488/529, loss: 0.003929120488464832
2023-01-24 06:11:35.139214: step: 492/529, loss: 0.0074152275919914246
2023-01-24 06:11:36.209656: step: 496/529, loss: 0.002956545911729336
2023-01-24 06:11:37.290240: step: 500/529, loss: 0.03752194717526436
2023-01-24 06:11:38.352687: step: 504/529, loss: 0.0006859778659418225
2023-01-24 06:11:39.436890: step: 508/529, loss: 0.011561921797692776
2023-01-24 06:11:40.528220: step: 512/529, loss: 0.005353607703000307
2023-01-24 06:11:41.619556: step: 516/529, loss: 0.02221294306218624
2023-01-24 06:11:42.725029: step: 520/529, loss: 0.06545469909906387
2023-01-24 06:11:43.826155: step: 524/529, loss: 0.01264087576419115
2023-01-24 06:11:44.909059: step: 528/529, loss: 0.002884245477616787
2023-01-24 06:11:46.001247: step: 532/529, loss: 0.007786398287862539
2023-01-24 06:11:47.090614: step: 536/529, loss: 0.008083497174084187
2023-01-24 06:11:48.195436: step: 540/529, loss: 0.030045470222830772
2023-01-24 06:11:49.279922: step: 544/529, loss: 0.014178305864334106
2023-01-24 06:11:50.358133: step: 548/529, loss: 0.008849376812577248
2023-01-24 06:11:51.443234: step: 552/529, loss: 0.008732696995139122
2023-01-24 06:11:52.522209: step: 556/529, loss: 0.004410865716636181
2023-01-24 06:11:53.594925: step: 560/529, loss: 0.006997823249548674
2023-01-24 06:11:54.679589: step: 564/529, loss: 0.022372372448444366
2023-01-24 06:11:55.757229: step: 568/529, loss: 0.010571775026619434
2023-01-24 06:11:56.836346: step: 572/529, loss: 0.009789271280169487
2023-01-24 06:11:57.921574: step: 576/529, loss: 0.011386413127183914
2023-01-24 06:11:58.996227: step: 580/529, loss: 0.0026053423061966896
2023-01-24 06:12:00.113649: step: 584/529, loss: 0.006315314210951328
2023-01-24 06:12:01.187836: step: 588/529, loss: 0.006061123218387365
2023-01-24 06:12:02.273043: step: 592/529, loss: 0.012107725255191326
2023-01-24 06:12:03.360702: step: 596/529, loss: 0.010177775286138058
2023-01-24 06:12:04.425225: step: 600/529, loss: 0.0055756717920303345
2023-01-24 06:12:05.493784: step: 604/529, loss: 0.021189868450164795
2023-01-24 06:12:06.556537: step: 608/529, loss: 0.01046000700443983
2023-01-24 06:12:07.642917: step: 612/529, loss: 0.005971742793917656
2023-01-24 06:12:08.723934: step: 616/529, loss: 0.05866464972496033
2023-01-24 06:12:09.805023: step: 620/529, loss: 0.0023554451763629913
2023-01-24 06:12:10.896201: step: 624/529, loss: 0.0011644354090094566
2023-01-24 06:12:11.991700: step: 628/529, loss: 0.004025870468467474
2023-01-24 06:12:13.100853: step: 632/529, loss: 0.03125376999378204
2023-01-24 06:12:14.173387: step: 636/529, loss: 0.01074403990060091
2023-01-24 06:12:15.257096: step: 640/529, loss: 0.005771816708147526
2023-01-24 06:12:16.345025: step: 644/529, loss: 0.03079116903245449
2023-01-24 06:12:17.423478: step: 648/529, loss: 0.033063679933547974
2023-01-24 06:12:18.510160: step: 652/529, loss: 0.016354400664567947
2023-01-24 06:12:19.609098: step: 656/529, loss: 0.05970814451575279
2023-01-24 06:12:20.685674: step: 660/529, loss: 0.001444636844098568
2023-01-24 06:12:21.789629: step: 664/529, loss: 0.016184290871024132
2023-01-24 06:12:22.889396: step: 668/529, loss: 0.00477588502690196
2023-01-24 06:12:23.980431: step: 672/529, loss: 0.006206808146089315
2023-01-24 06:12:25.052234: step: 676/529, loss: 0.008227761834859848
2023-01-24 06:12:26.136629: step: 680/529, loss: 0.015279300510883331
2023-01-24 06:12:27.214012: step: 684/529, loss: 0.01271582767367363
2023-01-24 06:12:28.285953: step: 688/529, loss: 0.014392211101949215
2023-01-24 06:12:29.369583: step: 692/529, loss: 0.003943356219679117
2023-01-24 06:12:30.453254: step: 696/529, loss: 0.015789717435836792
2023-01-24 06:12:31.534815: step: 700/529, loss: 0.009603102691471577
2023-01-24 06:12:32.615589: step: 704/529, loss: 0.0014994575176388025
2023-01-24 06:12:33.702554: step: 708/529, loss: 0.04623842239379883
2023-01-24 06:12:34.767418: step: 712/529, loss: 0.009516654536128044
2023-01-24 06:12:35.842079: step: 716/529, loss: 0.01575472392141819
2023-01-24 06:12:36.929593: step: 720/529, loss: 0.013767393305897713
2023-01-24 06:12:38.003446: step: 724/529, loss: 0.003637568326666951
2023-01-24 06:12:39.107437: step: 728/529, loss: 0.0043344697915017605
2023-01-24 06:12:40.175379: step: 732/529, loss: 0.006537323351949453
2023-01-24 06:12:41.246607: step: 736/529, loss: 0.0033879082184284925
2023-01-24 06:12:42.326987: step: 740/529, loss: 0.02533634565770626
2023-01-24 06:12:43.428877: step: 744/529, loss: 0.017336128279566765
2023-01-24 06:12:44.505095: step: 748/529, loss: 0.004925339482724667
2023-01-24 06:12:45.568467: step: 752/529, loss: 0.007628203369677067
2023-01-24 06:12:46.650807: step: 756/529, loss: 0.008437758311629295
2023-01-24 06:12:47.744515: step: 760/529, loss: 0.024408672004938126
2023-01-24 06:12:48.829171: step: 764/529, loss: 0.0125978272408247
2023-01-24 06:12:49.926517: step: 768/529, loss: 0.005498663522303104
2023-01-24 06:12:51.018098: step: 772/529, loss: 0.011882169172167778
2023-01-24 06:12:52.099198: step: 776/529, loss: 0.011211286298930645
2023-01-24 06:12:53.186739: step: 780/529, loss: 0.02300315536558628
2023-01-24 06:12:54.277365: step: 784/529, loss: 0.003724579932168126
2023-01-24 06:12:55.338526: step: 788/529, loss: 0.028514083474874496
2023-01-24 06:12:56.427792: step: 792/529, loss: 0.006447245366871357
2023-01-24 06:12:57.500633: step: 796/529, loss: 0.006065033376216888
2023-01-24 06:12:58.572730: step: 800/529, loss: 0.005077395588159561
2023-01-24 06:12:59.679946: step: 804/529, loss: 0.010027355514466763
2023-01-24 06:13:00.759141: step: 808/529, loss: 0.02832377701997757
2023-01-24 06:13:01.844926: step: 812/529, loss: 0.043153002858161926
2023-01-24 06:13:02.910852: step: 816/529, loss: 0.025798605754971504
2023-01-24 06:13:04.005849: step: 820/529, loss: 0.015424206852912903
2023-01-24 06:13:05.088848: step: 824/529, loss: 0.0060752397403120995
2023-01-24 06:13:06.172881: step: 828/529, loss: 0.004287119023501873
2023-01-24 06:13:07.258101: step: 832/529, loss: 0.007462375797331333
2023-01-24 06:13:08.347288: step: 836/529, loss: 0.023030288517475128
2023-01-24 06:13:09.410253: step: 840/529, loss: 0.005865107756108046
2023-01-24 06:13:10.474615: step: 844/529, loss: 0.006104913540184498
2023-01-24 06:13:11.550747: step: 848/529, loss: 0.002652696566656232
2023-01-24 06:13:12.638015: step: 852/529, loss: 0.003942091483622789
2023-01-24 06:13:13.716102: step: 856/529, loss: 0.009529509581625462
2023-01-24 06:13:14.795695: step: 860/529, loss: 0.027600182220339775
2023-01-24 06:13:15.867383: step: 864/529, loss: 0.023900698870420456
2023-01-24 06:13:16.945124: step: 868/529, loss: 0.0259038507938385
2023-01-24 06:13:18.031396: step: 872/529, loss: 0.004927666392177343
2023-01-24 06:13:19.116271: step: 876/529, loss: 0.03155926987528801
2023-01-24 06:13:20.182558: step: 880/529, loss: 0.004801892675459385
2023-01-24 06:13:21.267093: step: 884/529, loss: 0.0028987738769501448
2023-01-24 06:13:22.332199: step: 888/529, loss: 0.011629470624029636
2023-01-24 06:13:23.409888: step: 892/529, loss: 0.011148552410304546
2023-01-24 06:13:24.483468: step: 896/529, loss: 0.13162261247634888
2023-01-24 06:13:25.581337: step: 900/529, loss: 0.008143724873661995
2023-01-24 06:13:26.662392: step: 904/529, loss: 0.03998962789773941
2023-01-24 06:13:27.749710: step: 908/529, loss: 0.0052235922776162624
2023-01-24 06:13:28.801572: step: 912/529, loss: 0.00394093943759799
2023-01-24 06:13:29.901375: step: 916/529, loss: 0.0072084455750882626
2023-01-24 06:13:30.973360: step: 920/529, loss: 0.009431025013327599
2023-01-24 06:13:32.062090: step: 924/529, loss: 0.0255372766405344
2023-01-24 06:13:33.144235: step: 928/529, loss: 0.01579502411186695
2023-01-24 06:13:34.208605: step: 932/529, loss: 0.004735572263598442
2023-01-24 06:13:35.297611: step: 936/529, loss: 0.019908593967556953
2023-01-24 06:13:36.366323: step: 940/529, loss: 0.02770416811108589
2023-01-24 06:13:37.441568: step: 944/529, loss: 0.006304669659584761
2023-01-24 06:13:38.506339: step: 948/529, loss: 0.0403580516576767
2023-01-24 06:13:39.574400: step: 952/529, loss: 0.007796632591634989
2023-01-24 06:13:40.633608: step: 956/529, loss: 0.0030209182295948267
2023-01-24 06:13:41.691343: step: 960/529, loss: 0.013146238401532173
2023-01-24 06:13:42.769894: step: 964/529, loss: 0.01584496907889843
2023-01-24 06:13:43.849955: step: 968/529, loss: 0.003359497059136629
2023-01-24 06:13:44.931319: step: 972/529, loss: 0.03896097093820572
2023-01-24 06:13:46.002333: step: 976/529, loss: 0.0074942875653505325
2023-01-24 06:13:47.068618: step: 980/529, loss: 0.009633627720177174
2023-01-24 06:13:48.156916: step: 984/529, loss: 0.010517396964132786
2023-01-24 06:13:49.228453: step: 988/529, loss: 0.004183989018201828
2023-01-24 06:13:50.304960: step: 992/529, loss: 0.025566834956407547
2023-01-24 06:13:51.365843: step: 996/529, loss: 0.0017568806651979685
2023-01-24 06:13:52.432685: step: 1000/529, loss: 0.003724064212292433
2023-01-24 06:13:53.515372: step: 1004/529, loss: 0.018226245418190956
2023-01-24 06:13:54.585039: step: 1008/529, loss: 0.002621798310428858
2023-01-24 06:13:55.670605: step: 1012/529, loss: 0.01233003567904234
2023-01-24 06:13:56.748189: step: 1016/529, loss: 0.0020173578523099422
2023-01-24 06:13:57.819408: step: 1020/529, loss: 0.055649321526288986
2023-01-24 06:13:58.887490: step: 1024/529, loss: 0.004484891425818205
2023-01-24 06:13:59.959885: step: 1028/529, loss: 0.015714703127741814
2023-01-24 06:14:01.034707: step: 1032/529, loss: 0.0038978324737399817
2023-01-24 06:14:02.130522: step: 1036/529, loss: 0.0031042390037328005
2023-01-24 06:14:03.214640: step: 1040/529, loss: 0.007391402497887611
2023-01-24 06:14:04.281760: step: 1044/529, loss: 0.029405970126390457
2023-01-24 06:14:05.359915: step: 1048/529, loss: 0.018559670075774193
2023-01-24 06:14:06.399787: step: 1052/529, loss: 0.0049636485055089
2023-01-24 06:14:07.474903: step: 1056/529, loss: 0.004320602398365736
2023-01-24 06:14:08.535888: step: 1060/529, loss: 0.010983044281601906
2023-01-24 06:14:09.603506: step: 1064/529, loss: 0.011514020152390003
2023-01-24 06:14:10.679055: step: 1068/529, loss: 0.009376381523907185
2023-01-24 06:14:11.735555: step: 1072/529, loss: 0.008348432369530201
2023-01-24 06:14:12.798766: step: 1076/529, loss: 0.017761917784810066
2023-01-24 06:14:13.875538: step: 1080/529, loss: 0.008414589799940586
2023-01-24 06:14:14.958279: step: 1084/529, loss: 0.005496625322848558
2023-01-24 06:14:16.024770: step: 1088/529, loss: 0.04644312337040901
2023-01-24 06:14:17.094700: step: 1092/529, loss: 0.004304953385144472
2023-01-24 06:14:18.178897: step: 1096/529, loss: 0.005510158836841583
2023-01-24 06:14:19.267841: step: 1100/529, loss: 0.005772853270173073
2023-01-24 06:14:20.331120: step: 1104/529, loss: 0.012061094865202904
2023-01-24 06:14:21.398299: step: 1108/529, loss: 0.0017688010120764375
2023-01-24 06:14:22.486818: step: 1112/529, loss: 0.017434442415833473
2023-01-24 06:14:23.569456: step: 1116/529, loss: 0.014594674110412598
2023-01-24 06:14:24.653811: step: 1120/529, loss: 0.0023712334223091602
2023-01-24 06:14:25.715594: step: 1124/529, loss: 0.006871682126075029
2023-01-24 06:14:26.799870: step: 1128/529, loss: 0.03983144089579582
2023-01-24 06:14:27.884214: step: 1132/529, loss: 0.028394797816872597
2023-01-24 06:14:28.959611: step: 1136/529, loss: 0.007608314510434866
2023-01-24 06:14:30.039045: step: 1140/529, loss: 0.013981778174638748
2023-01-24 06:14:31.112825: step: 1144/529, loss: 0.018365658819675446
2023-01-24 06:14:32.172126: step: 1148/529, loss: 0.008952243253588676
2023-01-24 06:14:33.246736: step: 1152/529, loss: 0.0017094701761379838
2023-01-24 06:14:34.329205: step: 1156/529, loss: 0.004046187736093998
2023-01-24 06:14:35.398535: step: 1160/529, loss: 0.013640028424561024
2023-01-24 06:14:36.456613: step: 1164/529, loss: 0.008996560238301754
2023-01-24 06:14:37.535411: step: 1168/529, loss: 0.02026931196451187
2023-01-24 06:14:38.598774: step: 1172/529, loss: 0.005805299151688814
2023-01-24 06:14:39.658521: step: 1176/529, loss: 0.002212170511484146
2023-01-24 06:14:40.726051: step: 1180/529, loss: 0.02477906085550785
2023-01-24 06:14:41.807639: step: 1184/529, loss: 0.02762446366250515
2023-01-24 06:14:42.887760: step: 1188/529, loss: 0.006099613383412361
2023-01-24 06:14:43.955193: step: 1192/529, loss: 0.012876187451183796
2023-01-24 06:14:45.020387: step: 1196/529, loss: 0.0063935755752027035
2023-01-24 06:14:46.087620: step: 1200/529, loss: 0.003878252115100622
2023-01-24 06:14:47.172822: step: 1204/529, loss: 0.039350178092718124
2023-01-24 06:14:48.253550: step: 1208/529, loss: 0.02139635756611824
2023-01-24 06:14:49.329201: step: 1212/529, loss: 0.00921793095767498
2023-01-24 06:14:50.408876: step: 1216/529, loss: 0.06087804585695267
2023-01-24 06:14:51.483217: step: 1220/529, loss: 0.028340278193354607
2023-01-24 06:14:52.553669: step: 1224/529, loss: 0.055563412606716156
2023-01-24 06:14:53.604966: step: 1228/529, loss: 0.02344418317079544
2023-01-24 06:14:54.665897: step: 1232/529, loss: 0.05165579915046692
2023-01-24 06:14:55.753497: step: 1236/529, loss: 0.001859421725384891
2023-01-24 06:14:56.828766: step: 1240/529, loss: 0.006139685865491629
2023-01-24 06:14:57.894863: step: 1244/529, loss: 0.0014655182603746653
2023-01-24 06:14:58.946380: step: 1248/529, loss: 0.0164926890283823
2023-01-24 06:15:00.044363: step: 1252/529, loss: 0.004378945101052523
2023-01-24 06:15:01.108960: step: 1256/529, loss: 0.024394448846578598
2023-01-24 06:15:02.187632: step: 1260/529, loss: 0.0026625245809555054
2023-01-24 06:15:03.248334: step: 1264/529, loss: 0.0066239298321306705
2023-01-24 06:15:04.318550: step: 1268/529, loss: 0.00588213000446558
2023-01-24 06:15:05.404022: step: 1272/529, loss: 0.00279621547088027
2023-01-24 06:15:06.500498: step: 1276/529, loss: 0.0028513562865555286
2023-01-24 06:15:07.580702: step: 1280/529, loss: 0.025714419782161713
2023-01-24 06:15:08.654694: step: 1284/529, loss: 0.008050620555877686
2023-01-24 06:15:09.717914: step: 1288/529, loss: 0.004834986291825771
2023-01-24 06:15:10.800166: step: 1292/529, loss: 0.0075737726874649525
2023-01-24 06:15:11.856023: step: 1296/529, loss: 0.0038207576144486666
2023-01-24 06:15:12.933297: step: 1300/529, loss: 0.02046213299036026
2023-01-24 06:15:14.004218: step: 1304/529, loss: 0.002661511767655611
2023-01-24 06:15:15.074071: step: 1308/529, loss: 0.0029636435210704803
2023-01-24 06:15:16.151057: step: 1312/529, loss: 0.007103527896106243
2023-01-24 06:15:17.211927: step: 1316/529, loss: 0.015374016016721725
2023-01-24 06:15:18.279773: step: 1320/529, loss: 0.005588351748883724
2023-01-24 06:15:19.351898: step: 1324/529, loss: 0.010644293390214443
2023-01-24 06:15:20.440984: step: 1328/529, loss: 0.013514773920178413
2023-01-24 06:15:21.523653: step: 1332/529, loss: 0.023189803585410118
2023-01-24 06:15:22.591094: step: 1336/529, loss: 0.016200147569179535
2023-01-24 06:15:23.654879: step: 1340/529, loss: 0.005605983082205057
2023-01-24 06:15:24.728616: step: 1344/529, loss: 0.005158822052180767
2023-01-24 06:15:25.831108: step: 1348/529, loss: 0.015752919018268585
2023-01-24 06:15:26.896854: step: 1352/529, loss: 0.007457233965396881
2023-01-24 06:15:27.968336: step: 1356/529, loss: 0.002733898349106312
2023-01-24 06:15:29.036994: step: 1360/529, loss: 0.00803408958017826
2023-01-24 06:15:30.121461: step: 1364/529, loss: 0.012401004321873188
2023-01-24 06:15:31.188530: step: 1368/529, loss: 0.012529886327683926
2023-01-24 06:15:32.264164: step: 1372/529, loss: 0.008226102218031883
2023-01-24 06:15:33.329280: step: 1376/529, loss: 0.003408262971788645
2023-01-24 06:15:34.395011: step: 1380/529, loss: 0.022067299112677574
2023-01-24 06:15:35.482234: step: 1384/529, loss: 0.029023773968219757
2023-01-24 06:15:36.565561: step: 1388/529, loss: 0.00243426114320755
2023-01-24 06:15:37.644815: step: 1392/529, loss: 0.02284083142876625
2023-01-24 06:15:38.717446: step: 1396/529, loss: 0.03285153955221176
2023-01-24 06:15:39.780183: step: 1400/529, loss: 0.0036283060908317566
2023-01-24 06:15:40.839610: step: 1404/529, loss: 0.004334451165050268
2023-01-24 06:15:41.925629: step: 1408/529, loss: 0.00718021159991622
2023-01-24 06:15:43.015684: step: 1412/529, loss: 0.0029661478474736214
2023-01-24 06:15:44.095695: step: 1416/529, loss: 0.008175135590136051
2023-01-24 06:15:45.161200: step: 1420/529, loss: 0.01993684098124504
2023-01-24 06:15:46.232447: step: 1424/529, loss: 0.016457246616482735
2023-01-24 06:15:47.293760: step: 1428/529, loss: 0.002410030923783779
2023-01-24 06:15:48.374766: step: 1432/529, loss: 0.003478674218058586
2023-01-24 06:15:49.445337: step: 1436/529, loss: 0.02772131934762001
2023-01-24 06:15:50.523451: step: 1440/529, loss: 0.04534738510847092
2023-01-24 06:15:51.597020: step: 1444/529, loss: 0.030017990618944168
2023-01-24 06:15:52.682373: step: 1448/529, loss: 0.03938787803053856
2023-01-24 06:15:53.778511: step: 1452/529, loss: 0.01088863518089056
2023-01-24 06:15:54.868967: step: 1456/529, loss: 0.034394435584545135
2023-01-24 06:15:55.943059: step: 1460/529, loss: 0.029155105352401733
2023-01-24 06:15:57.040532: step: 1464/529, loss: 0.008115858770906925
2023-01-24 06:15:58.125824: step: 1468/529, loss: 0.005686505232006311
2023-01-24 06:15:59.208460: step: 1472/529, loss: 0.018737081438302994
2023-01-24 06:16:00.285696: step: 1476/529, loss: 0.04900810867547989
2023-01-24 06:16:01.359973: step: 1480/529, loss: 0.016080887988209724
2023-01-24 06:16:02.425112: step: 1484/529, loss: 0.0045938449911773205
2023-01-24 06:16:03.497282: step: 1488/529, loss: 0.0033197340089827776
2023-01-24 06:16:04.586845: step: 1492/529, loss: 0.0010473380098119378
2023-01-24 06:16:05.687477: step: 1496/529, loss: 0.0172530859708786
2023-01-24 06:16:06.753532: step: 1500/529, loss: 0.007884933613240719
2023-01-24 06:16:07.827923: step: 1504/529, loss: 0.016385843977332115
2023-01-24 06:16:08.916257: step: 1508/529, loss: 0.015001671388745308
2023-01-24 06:16:09.982819: step: 1512/529, loss: 0.0015640354249626398
2023-01-24 06:16:11.056306: step: 1516/529, loss: 0.01059502549469471
2023-01-24 06:16:12.134413: step: 1520/529, loss: 0.006004739552736282
2023-01-24 06:16:13.218669: step: 1524/529, loss: 0.02500385232269764
2023-01-24 06:16:14.301190: step: 1528/529, loss: 0.002497711917385459
2023-01-24 06:16:15.364880: step: 1532/529, loss: 0.0026351953856647015
2023-01-24 06:16:16.442782: step: 1536/529, loss: 0.02436256594955921
2023-01-24 06:16:17.512547: step: 1540/529, loss: 0.004375166725367308
2023-01-24 06:16:18.596358: step: 1544/529, loss: 0.013552402146160603
2023-01-24 06:16:19.677791: step: 1548/529, loss: 0.023637469857931137
2023-01-24 06:16:20.735395: step: 1552/529, loss: 0.005161425564438105
2023-01-24 06:16:21.806811: step: 1556/529, loss: 0.003004640806466341
2023-01-24 06:16:22.892543: step: 1560/529, loss: 0.001522923936136067
2023-01-24 06:16:23.961004: step: 1564/529, loss: 0.0152517044916749
2023-01-24 06:16:25.021686: step: 1568/529, loss: 0.038275524973869324
2023-01-24 06:16:26.104378: step: 1572/529, loss: 0.005669040139764547
2023-01-24 06:16:27.194415: step: 1576/529, loss: 0.03416592627763748
2023-01-24 06:16:28.277000: step: 1580/529, loss: 0.012744205072522163
2023-01-24 06:16:29.354155: step: 1584/529, loss: 0.00821915827691555
2023-01-24 06:16:30.429358: step: 1588/529, loss: 0.01181462500244379
2023-01-24 06:16:31.509891: step: 1592/529, loss: 0.0055070677772164345
2023-01-24 06:16:32.586599: step: 1596/529, loss: 0.0008309081895276904
2023-01-24 06:16:33.664787: step: 1600/529, loss: 0.004739423282444477
2023-01-24 06:16:34.764858: step: 1604/529, loss: 0.006184678990393877
2023-01-24 06:16:35.854804: step: 1608/529, loss: 0.029379019513726234
2023-01-24 06:16:36.945445: step: 1612/529, loss: 0.0038327632937580347
2023-01-24 06:16:38.019599: step: 1616/529, loss: 0.007538485806435347
2023-01-24 06:16:39.099622: step: 1620/529, loss: 0.05112817883491516
2023-01-24 06:16:40.180013: step: 1624/529, loss: 0.007354019675403833
2023-01-24 06:16:41.244517: step: 1628/529, loss: 0.009731377474963665
2023-01-24 06:16:42.334625: step: 1632/529, loss: 0.004311395809054375
2023-01-24 06:16:43.418845: step: 1636/529, loss: 0.010484105907380581
2023-01-24 06:16:44.487626: step: 1640/529, loss: 0.04261666163802147
2023-01-24 06:16:45.563082: step: 1644/529, loss: 0.008501452393829823
2023-01-24 06:16:46.618244: step: 1648/529, loss: 0.03699615225195885
2023-01-24 06:16:47.702650: step: 1652/529, loss: 0.053415074944496155
2023-01-24 06:16:48.783419: step: 1656/529, loss: 0.007597135845571756
2023-01-24 06:16:49.873271: step: 1660/529, loss: 0.01577094942331314
2023-01-24 06:16:50.946565: step: 1664/529, loss: 0.03706006705760956
2023-01-24 06:16:52.013274: step: 1668/529, loss: 0.00483612809330225
2023-01-24 06:16:53.091816: step: 1672/529, loss: 0.01426513772457838
2023-01-24 06:16:54.179045: step: 1676/529, loss: 0.007214435841888189
2023-01-24 06:16:55.250789: step: 1680/529, loss: 0.025714347139000893
2023-01-24 06:16:56.328888: step: 1684/529, loss: 0.009176847524940968
2023-01-24 06:16:57.395292: step: 1688/529, loss: 0.044139422476291656
2023-01-24 06:16:58.468571: step: 1692/529, loss: 0.00020565024169627577
2023-01-24 06:16:59.535125: step: 1696/529, loss: 0.033236853778362274
2023-01-24 06:17:00.612204: step: 1700/529, loss: 0.02413833886384964
2023-01-24 06:17:01.688587: step: 1704/529, loss: 0.014737321063876152
2023-01-24 06:17:02.763056: step: 1708/529, loss: 0.006017411593347788
2023-01-24 06:17:03.828563: step: 1712/529, loss: 0.00570539478212595
2023-01-24 06:17:04.898883: step: 1716/529, loss: 0.01466822437942028
2023-01-24 06:17:06.006985: step: 1720/529, loss: 0.018773669376969337
2023-01-24 06:17:07.087166: step: 1724/529, loss: 0.008616812527179718
2023-01-24 06:17:08.162901: step: 1728/529, loss: 0.0018309402512386441
2023-01-24 06:17:09.240541: step: 1732/529, loss: 0.0016914657317101955
2023-01-24 06:17:10.317493: step: 1736/529, loss: 0.0016465247608721256
2023-01-24 06:17:11.387082: step: 1740/529, loss: 0.00797338504344225
2023-01-24 06:17:12.461588: step: 1744/529, loss: 0.030192503705620766
2023-01-24 06:17:13.552897: step: 1748/529, loss: 0.01001956406980753
2023-01-24 06:17:14.628963: step: 1752/529, loss: 0.006117544136941433
2023-01-24 06:17:15.717941: step: 1756/529, loss: 0.007491874508559704
2023-01-24 06:17:16.810356: step: 1760/529, loss: 0.02282862365245819
2023-01-24 06:17:17.893523: step: 1764/529, loss: 0.004685061983764172
2023-01-24 06:17:18.976263: step: 1768/529, loss: 0.005918607115745544
2023-01-24 06:17:20.026832: step: 1772/529, loss: 0.008445680141448975
2023-01-24 06:17:21.123277: step: 1776/529, loss: 0.00673102680593729
2023-01-24 06:17:22.207334: step: 1780/529, loss: 0.013594028539955616
2023-01-24 06:17:23.298708: step: 1784/529, loss: 0.010501289740204811
2023-01-24 06:17:24.378454: step: 1788/529, loss: 0.005844305269420147
2023-01-24 06:17:25.453060: step: 1792/529, loss: 0.003535617608577013
2023-01-24 06:17:26.528969: step: 1796/529, loss: 0.008703017607331276
2023-01-24 06:17:27.601159: step: 1800/529, loss: 0.03647451475262642
2023-01-24 06:17:28.678789: step: 1804/529, loss: 0.0032347142696380615
2023-01-24 06:17:29.762247: step: 1808/529, loss: 0.0056460085324943066
2023-01-24 06:17:30.837217: step: 1812/529, loss: 0.02136342041194439
2023-01-24 06:17:31.911868: step: 1816/529, loss: 0.026320243254303932
2023-01-24 06:17:32.990969: step: 1820/529, loss: 0.0029856255277991295
2023-01-24 06:17:34.079543: step: 1824/529, loss: 0.07196203619241714
2023-01-24 06:17:35.161872: step: 1828/529, loss: 0.028125401586294174
2023-01-24 06:17:36.221407: step: 1832/529, loss: 0.037703514099121094
2023-01-24 06:17:37.293766: step: 1836/529, loss: 0.008615609258413315
2023-01-24 06:17:38.364764: step: 1840/529, loss: 0.0136657003313303
2023-01-24 06:17:39.437829: step: 1844/529, loss: 0.004803077783435583
2023-01-24 06:17:40.520966: step: 1848/529, loss: 0.005082200281322002
2023-01-24 06:17:41.592287: step: 1852/529, loss: 0.0
2023-01-24 06:17:42.684151: step: 1856/529, loss: 0.01590595580637455
2023-01-24 06:17:43.758438: step: 1860/529, loss: 0.029346419498324394
2023-01-24 06:17:44.840279: step: 1864/529, loss: 0.0018871879437938333
2023-01-24 06:17:45.923538: step: 1868/529, loss: 0.0
2023-01-24 06:17:46.995327: step: 1872/529, loss: 0.003660541260614991
2023-01-24 06:17:48.072027: step: 1876/529, loss: 0.006462095770984888
2023-01-24 06:17:49.141999: step: 1880/529, loss: 0.011465365998446941
2023-01-24 06:17:50.220512: step: 1884/529, loss: 0.010310271754860878
2023-01-24 06:17:51.290741: step: 1888/529, loss: 0.006486890837550163
2023-01-24 06:17:52.391457: step: 1892/529, loss: 0.009188487194478512
2023-01-24 06:17:53.484034: step: 1896/529, loss: 0.009915893897414207
2023-01-24 06:17:54.567389: step: 1900/529, loss: 0.002734539331868291
2023-01-24 06:17:55.644991: step: 1904/529, loss: 0.005615149158984423
2023-01-24 06:17:56.748335: step: 1908/529, loss: 0.05137315392494202
2023-01-24 06:17:57.831181: step: 1912/529, loss: 0.002599590690806508
2023-01-24 06:17:58.894130: step: 1916/529, loss: 0.00834757648408413
2023-01-24 06:17:59.981540: step: 1920/529, loss: 0.049918632954359055
2023-01-24 06:18:01.056914: step: 1924/529, loss: 0.0056789773516356945
2023-01-24 06:18:02.124897: step: 1928/529, loss: 0.004025747999548912
2023-01-24 06:18:03.201867: step: 1932/529, loss: 0.0026592707727104425
2023-01-24 06:18:04.298685: step: 1936/529, loss: 0.003504074178636074
2023-01-24 06:18:05.378584: step: 1940/529, loss: 0.012685788795351982
2023-01-24 06:18:06.461867: step: 1944/529, loss: 0.01997111178934574
2023-01-24 06:18:07.529268: step: 1948/529, loss: 0.0035657461266964674
2023-01-24 06:18:08.614161: step: 1952/529, loss: 0.003932040184736252
2023-01-24 06:18:09.705673: step: 1956/529, loss: 0.0186584684997797
2023-01-24 06:18:10.783534: step: 1960/529, loss: 0.0054773613810539246
2023-01-24 06:18:11.860117: step: 1964/529, loss: 0.010664473287761211
2023-01-24 06:18:12.938209: step: 1968/529, loss: 0.031069811433553696
2023-01-24 06:18:14.014487: step: 1972/529, loss: 0.023229114711284637
2023-01-24 06:18:15.084333: step: 1976/529, loss: 0.007274959702044725
2023-01-24 06:18:16.160870: step: 1980/529, loss: 0.029007315635681152
2023-01-24 06:18:17.230695: step: 1984/529, loss: 0.0015267595881596208
2023-01-24 06:18:18.308539: step: 1988/529, loss: 0.004608352668583393
2023-01-24 06:18:19.400600: step: 1992/529, loss: 0.004273242317140102
2023-01-24 06:18:20.493410: step: 1996/529, loss: 0.004014894366264343
2023-01-24 06:18:21.577389: step: 2000/529, loss: 0.038474246859550476
2023-01-24 06:18:22.662742: step: 2004/529, loss: 0.014269506558775902
2023-01-24 06:18:23.731201: step: 2008/529, loss: 0.006851397920399904
2023-01-24 06:18:24.799020: step: 2012/529, loss: 0.005348716396838427
2023-01-24 06:18:25.867496: step: 2016/529, loss: 0.01597530022263527
2023-01-24 06:18:26.944518: step: 2020/529, loss: 0.011576604098081589
2023-01-24 06:18:28.017562: step: 2024/529, loss: 0.011374489404261112
2023-01-24 06:18:29.090104: step: 2028/529, loss: 0.020817169919610023
2023-01-24 06:18:30.155647: step: 2032/529, loss: 0.049827978014945984
2023-01-24 06:18:31.233260: step: 2036/529, loss: 0.038883961737155914
2023-01-24 06:18:32.309086: step: 2040/529, loss: 0.056108780205249786
2023-01-24 06:18:33.382247: step: 2044/529, loss: 0.015199577435851097
2023-01-24 06:18:34.455326: step: 2048/529, loss: 0.009123128838837147
2023-01-24 06:18:35.519396: step: 2052/529, loss: 0.017961569130420685
2023-01-24 06:18:36.605697: step: 2056/529, loss: 0.009053281508386135
2023-01-24 06:18:37.678338: step: 2060/529, loss: 0.0076627591624855995
2023-01-24 06:18:38.760236: step: 2064/529, loss: 0.010079356841742992
2023-01-24 06:18:39.821250: step: 2068/529, loss: 0.0019372139358893037
2023-01-24 06:18:40.881978: step: 2072/529, loss: 0.0047211721539497375
2023-01-24 06:18:41.962434: step: 2076/529, loss: 0.004959276877343655
2023-01-24 06:18:43.032779: step: 2080/529, loss: 0.006662295665591955
2023-01-24 06:18:44.103606: step: 2084/529, loss: 0.0018974773120135069
2023-01-24 06:18:45.190340: step: 2088/529, loss: 0.005917488597333431
2023-01-24 06:18:46.251174: step: 2092/529, loss: 0.0018383333226665854
2023-01-24 06:18:47.316356: step: 2096/529, loss: 0.036907970905303955
2023-01-24 06:18:48.383044: step: 2100/529, loss: 0.04326321557164192
2023-01-24 06:18:49.457194: step: 2104/529, loss: 0.004703995771706104
2023-01-24 06:18:50.532074: step: 2108/529, loss: 0.0034996713511645794
2023-01-24 06:18:51.617861: step: 2112/529, loss: 0.00457699503749609
2023-01-24 06:18:52.692571: step: 2116/529, loss: 0.006359584629535675
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3324701762201763, 'r': 0.30345000903587244, 'f1': 0.31729792611489044}, 'combined': 0.23379847187412978, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33333421221395576, 'r': 0.2925865557576542, 'f1': 0.3116340407873987}, 'combined': 0.2034502027938458, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.358222525347998, 'r': 0.35958200362256343, 'f1': 0.35890097710055097}, 'combined': 0.2644533515477744, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3570613996849087, 'r': 0.31242872472429506, 'f1': 0.3332573063725814}, 'combined': 0.21756694612925, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36688054929764113, 'r': 0.34112233236403067, 'f1': 0.3535328793625254}, 'combined': 0.26049791110922926, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3712138853827869, 'r': 0.30809387729839754, 'f1': 0.3367213847319503}, 'combined': 0.21982846878873438, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 2}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.358222525347998, 'r': 0.35958200362256343, 'f1': 0.35890097710055097}, 'combined': 0.2644533515477744, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3570613996849087, 'r': 0.31242872472429506, 'f1': 0.3332573063725814}, 'combined': 0.21756694612925, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36862724672657937, 'r': 0.3406479490623229, 'f1': 0.35408573797996873}, 'combined': 0.26090528061681906, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35513067799423575, 'r': 0.3025791714160446, 'f1': 0.3267554724572273}, 'combined': 0.21332222554202404, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 0}
******************************
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 06:21:34.996579: step: 4/529, loss: 0.0024898829869925976
2023-01-24 06:21:36.051575: step: 8/529, loss: 0.009998486377298832
2023-01-24 06:21:37.111177: step: 12/529, loss: 0.009323058649897575
2023-01-24 06:21:38.200458: step: 16/529, loss: 0.011328169144690037
2023-01-24 06:21:39.263202: step: 20/529, loss: 0.0009869153145700693
2023-01-24 06:21:40.327172: step: 24/529, loss: 0.030980706214904785
2023-01-24 06:21:41.387035: step: 28/529, loss: 0.05104508623480797
2023-01-24 06:21:42.467686: step: 32/529, loss: 0.0055313920602202415
2023-01-24 06:21:43.536154: step: 36/529, loss: 0.004372811410576105
2023-01-24 06:21:44.599573: step: 40/529, loss: 0.011180211789906025
2023-01-24 06:21:45.675295: step: 44/529, loss: 0.009532887488603592
2023-01-24 06:21:46.748607: step: 48/529, loss: 0.015362439677119255
2023-01-24 06:21:47.824184: step: 52/529, loss: 0.006224817596375942
2023-01-24 06:21:48.874464: step: 56/529, loss: 0.0025285992305725813
2023-01-24 06:21:49.928249: step: 60/529, loss: 0.013974323868751526
2023-01-24 06:21:51.008708: step: 64/529, loss: 0.013623700477182865
2023-01-24 06:21:52.060563: step: 68/529, loss: 0.019874049350619316
2023-01-24 06:21:53.114139: step: 72/529, loss: 0.002674778923392296
2023-01-24 06:21:54.168119: step: 76/529, loss: 0.006196442525833845
2023-01-24 06:21:55.239071: step: 80/529, loss: 0.0
2023-01-24 06:21:56.328310: step: 84/529, loss: 0.0028121531940996647
2023-01-24 06:21:57.425250: step: 88/529, loss: 0.03950012847781181
2023-01-24 06:21:58.480461: step: 92/529, loss: 0.0011263397755101323
2023-01-24 06:21:59.550493: step: 96/529, loss: 0.00035015030880458653
2023-01-24 06:22:00.611048: step: 100/529, loss: 0.013024108484387398
2023-01-24 06:22:01.691058: step: 104/529, loss: 0.002154993126168847
2023-01-24 06:22:02.755840: step: 108/529, loss: 0.004968708846718073
2023-01-24 06:22:03.808724: step: 112/529, loss: 0.010217132978141308
2023-01-24 06:22:04.910143: step: 116/529, loss: 0.02586781233549118
2023-01-24 06:22:05.982292: step: 120/529, loss: 0.0017980748089030385
2023-01-24 06:22:07.054869: step: 124/529, loss: 0.007088362239301205
2023-01-24 06:22:08.145815: step: 128/529, loss: 0.014599244110286236
2023-01-24 06:22:09.216938: step: 132/529, loss: 0.00649668462574482
2023-01-24 06:22:10.285713: step: 136/529, loss: 0.009308228269219398
2023-01-24 06:22:11.357884: step: 140/529, loss: 0.004525244235992432
2023-01-24 06:22:12.435796: step: 144/529, loss: 0.02284422516822815
2023-01-24 06:22:13.529957: step: 148/529, loss: 0.00675962632521987
2023-01-24 06:22:14.603283: step: 152/529, loss: 0.04700329899787903
2023-01-24 06:22:15.689029: step: 156/529, loss: 0.0022611855529248714
2023-01-24 06:22:16.783278: step: 160/529, loss: 0.00609878683462739
2023-01-24 06:22:17.870368: step: 164/529, loss: 0.0028452607803046703
2023-01-24 06:22:18.942751: step: 168/529, loss: 0.007472863886505365
2023-01-24 06:22:20.013441: step: 172/529, loss: 0.014165637083351612
2023-01-24 06:22:21.097140: step: 176/529, loss: 0.018322885036468506
2023-01-24 06:22:22.183903: step: 180/529, loss: 0.005257230717688799
2023-01-24 06:22:23.249260: step: 184/529, loss: 0.0034080655314028263
2023-01-24 06:22:24.315168: step: 188/529, loss: 0.009067095816135406
2023-01-24 06:22:25.385055: step: 192/529, loss: 0.014662901870906353
2023-01-24 06:22:26.468330: step: 196/529, loss: 0.006641920655965805
2023-01-24 06:22:27.559406: step: 200/529, loss: 0.003498903475701809
2023-01-24 06:22:28.635856: step: 204/529, loss: 0.0022364268079400063
2023-01-24 06:22:29.735589: step: 208/529, loss: 0.006371054332703352
2023-01-24 06:22:30.816930: step: 212/529, loss: 0.011325756087899208
2023-01-24 06:22:31.901760: step: 216/529, loss: 0.011798487044870853
2023-01-24 06:22:32.985803: step: 220/529, loss: 0.016787752509117126
2023-01-24 06:22:34.089460: step: 224/529, loss: 0.005627484060823917
2023-01-24 06:22:35.166996: step: 228/529, loss: 0.004370959475636482
2023-01-24 06:22:36.241519: step: 232/529, loss: 0.020324936136603355
2023-01-24 06:22:37.324221: step: 236/529, loss: 0.008290110155940056
2023-01-24 06:22:38.395794: step: 240/529, loss: 0.0093317162245512
2023-01-24 06:22:39.466536: step: 244/529, loss: 0.005572185385972261
2023-01-24 06:22:40.542237: step: 248/529, loss: 0.0072760507464408875
2023-01-24 06:22:41.625129: step: 252/529, loss: 0.002409134991466999
2023-01-24 06:22:42.703530: step: 256/529, loss: 0.0033105802722275257
2023-01-24 06:22:43.791411: step: 260/529, loss: 0.002645289059728384
2023-01-24 06:22:44.866875: step: 264/529, loss: 0.0036009822506457567
2023-01-24 06:22:45.942629: step: 268/529, loss: 0.014621791429817677
2023-01-24 06:22:47.030420: step: 272/529, loss: 0.004520943388342857
2023-01-24 06:22:48.102220: step: 276/529, loss: 0.03241395205259323
2023-01-24 06:22:49.189105: step: 280/529, loss: 0.0014357933541759849
2023-01-24 06:22:50.266615: step: 284/529, loss: 0.016433486714959145
2023-01-24 06:22:51.331496: step: 288/529, loss: 0.00847969762980938
2023-01-24 06:22:52.415027: step: 292/529, loss: 0.005534472409635782
2023-01-24 06:22:53.508291: step: 296/529, loss: 0.009325714781880379
2023-01-24 06:22:54.581573: step: 300/529, loss: 0.0035875560715794563
2023-01-24 06:22:55.665722: step: 304/529, loss: 0.0061773560009896755
2023-01-24 06:22:56.735822: step: 308/529, loss: 0.003879481228068471
2023-01-24 06:22:57.820692: step: 312/529, loss: 0.02109449729323387
2023-01-24 06:22:58.889360: step: 316/529, loss: 0.006028865929692984
2023-01-24 06:22:59.961308: step: 320/529, loss: 0.0077999047935009
2023-01-24 06:23:01.042872: step: 324/529, loss: 0.005089559126645327
2023-01-24 06:23:02.118492: step: 328/529, loss: 0.012071740813553333
2023-01-24 06:23:03.196038: step: 332/529, loss: 0.0156533382833004
2023-01-24 06:23:04.283521: step: 336/529, loss: 0.0017831578152254224
2023-01-24 06:23:05.361395: step: 340/529, loss: 0.02241969108581543
2023-01-24 06:23:06.419196: step: 344/529, loss: 0.014348461292684078
2023-01-24 06:23:07.479662: step: 348/529, loss: 0.013777585700154305
2023-01-24 06:23:08.568010: step: 352/529, loss: 0.004657554905861616
2023-01-24 06:23:09.631665: step: 356/529, loss: 0.010508907958865166
2023-01-24 06:23:10.698018: step: 360/529, loss: 0.0047691757790744305
2023-01-24 06:23:11.754326: step: 364/529, loss: 0.023700784891843796
2023-01-24 06:23:12.827737: step: 368/529, loss: 0.08743604272603989
2023-01-24 06:23:13.917855: step: 372/529, loss: 0.0010982062667608261
2023-01-24 06:23:14.993636: step: 376/529, loss: 0.060454998165369034
2023-01-24 06:23:16.066771: step: 380/529, loss: 0.003574472852051258
2023-01-24 06:23:17.142731: step: 384/529, loss: 0.011014697141945362
2023-01-24 06:23:18.211002: step: 388/529, loss: 0.007280935533344746
2023-01-24 06:23:19.283706: step: 392/529, loss: 0.045963287353515625
2023-01-24 06:23:20.345613: step: 396/529, loss: 0.002156640635803342
2023-01-24 06:23:21.412277: step: 400/529, loss: 0.005824054591357708
2023-01-24 06:23:22.474553: step: 404/529, loss: 0.009582431986927986
2023-01-24 06:23:23.549080: step: 408/529, loss: 0.004311279859393835
2023-01-24 06:23:24.618987: step: 412/529, loss: 0.010646672919392586
2023-01-24 06:23:25.687370: step: 416/529, loss: 0.0013396181166172028
2023-01-24 06:23:26.760575: step: 420/529, loss: 0.02017797902226448
2023-01-24 06:23:27.834214: step: 424/529, loss: 0.011507540941238403
2023-01-24 06:23:28.914272: step: 428/529, loss: 0.0056877946481108665
2023-01-24 06:23:29.997257: step: 432/529, loss: 0.035469356924295425
2023-01-24 06:23:31.084521: step: 436/529, loss: 0.0041465251706540585
2023-01-24 06:23:32.140420: step: 440/529, loss: 0.010650979354977608
2023-01-24 06:23:33.213797: step: 444/529, loss: 0.00836743600666523
2023-01-24 06:23:34.282213: step: 448/529, loss: 0.006790465675294399
2023-01-24 06:23:35.352697: step: 452/529, loss: 0.0030433835927397013
2023-01-24 06:23:36.411025: step: 456/529, loss: 0.005927408114075661
2023-01-24 06:23:37.489095: step: 460/529, loss: 0.001353300060145557
2023-01-24 06:23:38.560299: step: 464/529, loss: 0.0038225119933485985
2023-01-24 06:23:39.617413: step: 468/529, loss: 0.00865098275244236
2023-01-24 06:23:40.689079: step: 472/529, loss: 0.04484766721725464
2023-01-24 06:23:41.758429: step: 476/529, loss: 0.0029634395614266396
2023-01-24 06:23:42.829918: step: 480/529, loss: 0.021705979481339455
2023-01-24 06:23:43.902038: step: 484/529, loss: 0.006049150601029396
2023-01-24 06:23:44.958493: step: 488/529, loss: 0.09693079441785812
2023-01-24 06:23:46.040235: step: 492/529, loss: 0.006209753453731537
2023-01-24 06:23:47.110162: step: 496/529, loss: 0.006873418111354113
2023-01-24 06:23:48.169135: step: 500/529, loss: 0.002736093942075968
2023-01-24 06:23:49.256986: step: 504/529, loss: 0.010693483985960484
2023-01-24 06:23:50.325697: step: 508/529, loss: 0.009600749239325523
2023-01-24 06:23:51.403842: step: 512/529, loss: 0.017675578594207764
2023-01-24 06:23:52.468555: step: 516/529, loss: 0.007996274158358574
2023-01-24 06:23:53.531508: step: 520/529, loss: 0.005945304408669472
2023-01-24 06:23:54.600912: step: 524/529, loss: 0.0015728590078651905
2023-01-24 06:23:55.677580: step: 528/529, loss: 0.0032930667512118816
2023-01-24 06:23:56.732945: step: 532/529, loss: 0.009243723936378956
2023-01-24 06:23:57.797443: step: 536/529, loss: 0.02138587459921837
2023-01-24 06:23:58.861539: step: 540/529, loss: 0.009292421862483025
2023-01-24 06:23:59.927304: step: 544/529, loss: 0.0050464109517633915
2023-01-24 06:24:00.996641: step: 548/529, loss: 0.008963420987129211
2023-01-24 06:24:02.058508: step: 552/529, loss: 0.00029907815041951835
2023-01-24 06:24:03.144654: step: 556/529, loss: 0.004303612280637026
2023-01-24 06:24:04.205486: step: 560/529, loss: 0.014759157784283161
2023-01-24 06:24:05.267234: step: 564/529, loss: 0.004573407582938671
2023-01-24 06:24:06.344852: step: 568/529, loss: 0.016875358298420906
2023-01-24 06:24:07.403952: step: 572/529, loss: 0.051509033888578415
2023-01-24 06:24:08.477359: step: 576/529, loss: 0.0021495213732123375
2023-01-24 06:24:09.522087: step: 580/529, loss: 0.016047941520810127
2023-01-24 06:24:10.582384: step: 584/529, loss: 0.013519387692213058
2023-01-24 06:24:11.659776: step: 588/529, loss: 0.016106870025396347
2023-01-24 06:24:12.739091: step: 592/529, loss: 0.00716715632006526
2023-01-24 06:24:13.841198: step: 596/529, loss: 0.008574715815484524
2023-01-24 06:24:14.919501: step: 600/529, loss: 0.006716846022754908
2023-01-24 06:24:15.992677: step: 604/529, loss: 0.0076522547751665115
2023-01-24 06:24:17.070421: step: 608/529, loss: 0.00690355384722352
2023-01-24 06:24:18.145743: step: 612/529, loss: 0.0062452019192278385
2023-01-24 06:24:19.212978: step: 616/529, loss: 0.0038067682180553675
2023-01-24 06:24:20.280964: step: 620/529, loss: 0.009516894817352295
2023-01-24 06:24:21.350955: step: 624/529, loss: 0.010676353238523006
2023-01-24 06:24:22.416932: step: 628/529, loss: 0.021904734894633293
2023-01-24 06:24:23.489806: step: 632/529, loss: 0.0028012630064040422
2023-01-24 06:24:24.569229: step: 636/529, loss: 0.007320138160139322
2023-01-24 06:24:25.633173: step: 640/529, loss: 0.0008662366308271885
2023-01-24 06:24:26.714115: step: 644/529, loss: 0.0037315881345421076
2023-01-24 06:24:27.790286: step: 648/529, loss: 0.003295026021078229
2023-01-24 06:24:28.862952: step: 652/529, loss: 0.05796245485544205
2023-01-24 06:24:29.930750: step: 656/529, loss: 0.0062024155631661415
2023-01-24 06:24:31.000465: step: 660/529, loss: 0.005118315573781729
2023-01-24 06:24:32.064744: step: 664/529, loss: 0.012726697139441967
2023-01-24 06:24:33.149198: step: 668/529, loss: 0.012336802668869495
2023-01-24 06:24:34.220067: step: 672/529, loss: 0.006135644856840372
2023-01-24 06:24:35.301532: step: 676/529, loss: 0.00828030239790678
2023-01-24 06:24:36.380392: step: 680/529, loss: 0.004346923902630806
2023-01-24 06:24:37.447180: step: 684/529, loss: 0.0007528209243901074
2023-01-24 06:24:38.542153: step: 688/529, loss: 0.0027078480925410986
2023-01-24 06:24:39.611131: step: 692/529, loss: 8.653145778225735e-05
2023-01-24 06:24:40.697293: step: 696/529, loss: 0.0047794790007174015
2023-01-24 06:24:41.765469: step: 700/529, loss: 0.020407507196068764
2023-01-24 06:24:42.871209: step: 704/529, loss: 0.005711992736905813
2023-01-24 06:24:43.959313: step: 708/529, loss: 0.026463540270924568
2023-01-24 06:24:45.016596: step: 712/529, loss: 0.005868465639650822
2023-01-24 06:24:46.070356: step: 716/529, loss: 0.0018788294401019812
2023-01-24 06:24:47.133683: step: 720/529, loss: 0.0010879709152504802
2023-01-24 06:24:48.206899: step: 724/529, loss: 0.009109952487051487
2023-01-24 06:24:49.280238: step: 728/529, loss: 0.003531214315444231
2023-01-24 06:24:50.368763: step: 732/529, loss: 0.015216343104839325
2023-01-24 06:24:51.425133: step: 736/529, loss: 0.015219041146337986
2023-01-24 06:24:52.498316: step: 740/529, loss: 0.0019862083718180656
2023-01-24 06:24:53.570314: step: 744/529, loss: 0.00816744938492775
2023-01-24 06:24:54.631294: step: 748/529, loss: 0.010270909406244755
2023-01-24 06:24:55.703862: step: 752/529, loss: 0.0005229077069088817
2023-01-24 06:24:56.773227: step: 756/529, loss: 0.008877737447619438
2023-01-24 06:24:57.845202: step: 760/529, loss: 0.012867475859820843
2023-01-24 06:24:58.921809: step: 764/529, loss: 0.004842827096581459
2023-01-24 06:24:59.999242: step: 768/529, loss: 0.03432096540927887
2023-01-24 06:25:01.078818: step: 772/529, loss: 0.005269247107207775
2023-01-24 06:25:02.170802: step: 776/529, loss: 0.013661100529134274
2023-01-24 06:25:03.255912: step: 780/529, loss: 0.0031797976698726416
2023-01-24 06:25:04.320508: step: 784/529, loss: 0.022498922422528267
2023-01-24 06:25:05.393241: step: 788/529, loss: 0.0077417767606675625
2023-01-24 06:25:06.476766: step: 792/529, loss: 0.00687831174582243
2023-01-24 06:25:07.581057: step: 796/529, loss: 0.015061895363032818
2023-01-24 06:25:08.654523: step: 800/529, loss: 0.006087824702262878
2023-01-24 06:25:09.721598: step: 804/529, loss: 0.019029002636671066
2023-01-24 06:25:10.811371: step: 808/529, loss: 0.02404755726456642
2023-01-24 06:25:11.891904: step: 812/529, loss: 0.012975217774510384
2023-01-24 06:25:12.966302: step: 816/529, loss: 0.07651344686746597
2023-01-24 06:25:14.027279: step: 820/529, loss: 0.006077010650187731
2023-01-24 06:25:15.100399: step: 824/529, loss: 0.03473775088787079
2023-01-24 06:25:16.162737: step: 828/529, loss: 0.027194304391741753
2023-01-24 06:25:17.238786: step: 832/529, loss: 0.007897722534835339
2023-01-24 06:25:18.314359: step: 836/529, loss: 0.00758944870904088
2023-01-24 06:25:19.396226: step: 840/529, loss: 0.0044963182881474495
2023-01-24 06:25:20.475032: step: 844/529, loss: 0.001894872635602951
2023-01-24 06:25:21.538357: step: 848/529, loss: 0.0027859548572450876
2023-01-24 06:25:22.616401: step: 852/529, loss: 0.010159488767385483
2023-01-24 06:25:23.680688: step: 856/529, loss: 0.00764209870249033
2023-01-24 06:25:24.756473: step: 860/529, loss: 0.009537285193800926
2023-01-24 06:25:25.845194: step: 864/529, loss: 0.007376695517450571
2023-01-24 06:25:26.923366: step: 868/529, loss: 0.013290522620081902
2023-01-24 06:25:28.000307: step: 872/529, loss: 0.0003908459038939327
2023-01-24 06:25:29.052413: step: 876/529, loss: 0.019253509119153023
2023-01-24 06:25:30.150852: step: 880/529, loss: 0.0057402984239161015
2023-01-24 06:25:31.218445: step: 884/529, loss: 0.012292454950511456
2023-01-24 06:25:32.295443: step: 888/529, loss: 0.022274423390626907
2023-01-24 06:25:33.352532: step: 892/529, loss: 0.001244120649062097
2023-01-24 06:25:34.429125: step: 896/529, loss: 0.007655525114387274
2023-01-24 06:25:35.486225: step: 900/529, loss: 0.004843244794756174
2023-01-24 06:25:36.568268: step: 904/529, loss: 0.05078835412859917
2023-01-24 06:25:37.640498: step: 908/529, loss: 0.014287375845015049
2023-01-24 06:25:38.737857: step: 912/529, loss: 0.00481020612642169
2023-01-24 06:25:39.811282: step: 916/529, loss: 0.0033847445156425238
2023-01-24 06:25:40.874350: step: 920/529, loss: 0.0026354873552918434
2023-01-24 06:25:41.947980: step: 924/529, loss: 0.001621701754629612
2023-01-24 06:25:43.017044: step: 928/529, loss: 0.0041492353193461895
2023-01-24 06:25:44.091738: step: 932/529, loss: 0.0052189333364367485
2023-01-24 06:25:45.179454: step: 936/529, loss: 0.007679773028939962
2023-01-24 06:25:46.248996: step: 940/529, loss: 0.00989400502294302
2023-01-24 06:25:47.306874: step: 944/529, loss: 0.016143208369612694
2023-01-24 06:25:48.379411: step: 948/529, loss: 0.007086863741278648
2023-01-24 06:25:49.453438: step: 952/529, loss: 0.003801848040893674
2023-01-24 06:25:50.548838: step: 956/529, loss: 0.008233774453401566
2023-01-24 06:25:51.612408: step: 960/529, loss: 0.02469220571219921
2023-01-24 06:25:52.687190: step: 964/529, loss: 0.027191689237952232
2023-01-24 06:25:53.777713: step: 968/529, loss: 0.028196467086672783
2023-01-24 06:25:54.860704: step: 972/529, loss: 0.0027674532029777765
2023-01-24 06:25:55.942548: step: 976/529, loss: 0.002779850736260414
2023-01-24 06:25:57.019423: step: 980/529, loss: 0.0036088430788367987
2023-01-24 06:25:58.096994: step: 984/529, loss: 0.004137295763939619
2023-01-24 06:25:59.184498: step: 988/529, loss: 0.00014658411964774132
2023-01-24 06:26:00.253742: step: 992/529, loss: 0.003567516803741455
2023-01-24 06:26:01.330777: step: 996/529, loss: 0.007545940112322569
2023-01-24 06:26:02.408317: step: 1000/529, loss: 0.03780417516827583
2023-01-24 06:26:03.473647: step: 1004/529, loss: 0.004817961249500513
2023-01-24 06:26:04.533495: step: 1008/529, loss: 0.004160279408097267
2023-01-24 06:26:05.602499: step: 1012/529, loss: 0.0052159070037305355
2023-01-24 06:26:06.672222: step: 1016/529, loss: 0.003921581897884607
2023-01-24 06:26:07.718498: step: 1020/529, loss: 0.014333940111100674
2023-01-24 06:26:08.803285: step: 1024/529, loss: 0.005078762304037809
2023-01-24 06:26:09.876705: step: 1028/529, loss: 0.004200531169772148
2023-01-24 06:26:10.948526: step: 1032/529, loss: 0.025001676753163338
2023-01-24 06:26:12.021071: step: 1036/529, loss: 0.01375879067927599
2023-01-24 06:26:13.109175: step: 1040/529, loss: 0.011037852615118027
2023-01-24 06:26:14.166077: step: 1044/529, loss: 0.0011660035233944654
2023-01-24 06:26:15.230360: step: 1048/529, loss: 0.04122757911682129
2023-01-24 06:26:16.291509: step: 1052/529, loss: 0.008421225473284721
2023-01-24 06:26:17.356545: step: 1056/529, loss: 0.013406566344201565
2023-01-24 06:26:18.425939: step: 1060/529, loss: 0.0048745060339570045
2023-01-24 06:26:19.507110: step: 1064/529, loss: 0.003069806145504117
2023-01-24 06:26:20.576268: step: 1068/529, loss: 0.001798956305719912
2023-01-24 06:26:21.671240: step: 1072/529, loss: 0.014165295287966728
2023-01-24 06:26:22.745318: step: 1076/529, loss: 0.013126375153660774
2023-01-24 06:26:23.854024: step: 1080/529, loss: 0.010651309043169022
2023-01-24 06:26:24.935807: step: 1084/529, loss: 0.009359825402498245
2023-01-24 06:26:26.009478: step: 1088/529, loss: 0.00133776746224612
2023-01-24 06:26:27.078531: step: 1092/529, loss: 0.006887001916766167
2023-01-24 06:26:28.161049: step: 1096/529, loss: 0.005140291526913643
2023-01-24 06:26:29.253056: step: 1100/529, loss: 0.012525931932032108
2023-01-24 06:26:30.353068: step: 1104/529, loss: 0.002243511378765106
2023-01-24 06:26:31.433609: step: 1108/529, loss: 0.009197882376611233
2023-01-24 06:26:32.521430: step: 1112/529, loss: 0.007377720903605223
2023-01-24 06:26:33.596425: step: 1116/529, loss: 0.012514114379882812
2023-01-24 06:26:34.668550: step: 1120/529, loss: 0.011046313680708408
2023-01-24 06:26:35.735269: step: 1124/529, loss: 0.008019635453820229
2023-01-24 06:26:36.823873: step: 1128/529, loss: 0.004647758789360523
2023-01-24 06:26:37.894836: step: 1132/529, loss: 0.010757249779999256
2023-01-24 06:26:38.963268: step: 1136/529, loss: 0.0026242982130497694
2023-01-24 06:26:40.027177: step: 1140/529, loss: 0.002294326201081276
2023-01-24 06:26:41.101155: step: 1144/529, loss: 0.0063705043867230415
2023-01-24 06:26:42.172251: step: 1148/529, loss: 0.023698003962635994
2023-01-24 06:26:43.268777: step: 1152/529, loss: 0.0035925637930631638
2023-01-24 06:26:44.330072: step: 1156/529, loss: 0.003907541744410992
2023-01-24 06:26:45.410195: step: 1160/529, loss: 0.01026979461312294
2023-01-24 06:26:46.486304: step: 1164/529, loss: 0.046339161694049835
2023-01-24 06:26:47.556233: step: 1168/529, loss: 0.0009419429115951061
2023-01-24 06:26:48.619828: step: 1172/529, loss: 0.008353786543011665
2023-01-24 06:26:49.705741: step: 1176/529, loss: 0.0013033384457230568
2023-01-24 06:26:50.792579: step: 1180/529, loss: 0.017704816535115242
2023-01-24 06:26:51.886485: step: 1184/529, loss: 0.009403382427990437
2023-01-24 06:26:52.962736: step: 1188/529, loss: 0.0026736774016171694
2023-01-24 06:26:54.034460: step: 1192/529, loss: 0.018443763256072998
2023-01-24 06:26:55.103140: step: 1196/529, loss: 0.012267779558897018
2023-01-24 06:26:56.189412: step: 1200/529, loss: 0.007556559517979622
2023-01-24 06:26:57.292327: step: 1204/529, loss: 0.01756388694047928
2023-01-24 06:26:58.376364: step: 1208/529, loss: 0.006873392499983311
2023-01-24 06:26:59.468649: step: 1212/529, loss: 0.001942845294252038
2023-01-24 06:27:00.547414: step: 1216/529, loss: 0.020934734493494034
2023-01-24 06:27:01.637851: step: 1220/529, loss: 0.04420597851276398
2023-01-24 06:27:02.724798: step: 1224/529, loss: 0.012765571475028992
2023-01-24 06:27:03.799259: step: 1228/529, loss: 0.013465002179145813
2023-01-24 06:27:04.901647: step: 1232/529, loss: 0.006584836170077324
2023-01-24 06:27:05.979542: step: 1236/529, loss: 0.01110995002090931
2023-01-24 06:27:07.046922: step: 1240/529, loss: 0.0009530002134852111
2023-01-24 06:27:08.136165: step: 1244/529, loss: 0.0005308607942424715
2023-01-24 06:27:09.214250: step: 1248/529, loss: 0.011963690631091595
2023-01-24 06:27:10.281107: step: 1252/529, loss: 0.028013112023472786
2023-01-24 06:27:11.353366: step: 1256/529, loss: 0.0014048839220777154
2023-01-24 06:27:12.431935: step: 1260/529, loss: 0.022144142538309097
2023-01-24 06:27:13.501996: step: 1264/529, loss: 0.010153418406844139
2023-01-24 06:27:14.567145: step: 1268/529, loss: 0.0351460836827755
2023-01-24 06:27:15.630907: step: 1272/529, loss: 0.01911328360438347
2023-01-24 06:27:16.707507: step: 1276/529, loss: 0.0035000531934201717
2023-01-24 06:27:17.776668: step: 1280/529, loss: 0.014711982570588589
2023-01-24 06:27:18.858700: step: 1284/529, loss: 0.020019857212901115
2023-01-24 06:27:19.920641: step: 1288/529, loss: 0.0009073346736840904
2023-01-24 06:27:21.005693: step: 1292/529, loss: 0.006496801041066647
2023-01-24 06:27:22.070241: step: 1296/529, loss: 0.005249849054962397
2023-01-24 06:27:23.153505: step: 1300/529, loss: 0.09730228781700134
2023-01-24 06:27:24.226198: step: 1304/529, loss: 0.00010446640953887254
2023-01-24 06:27:25.307804: step: 1308/529, loss: 0.0018612323328852654
2023-01-24 06:27:26.386967: step: 1312/529, loss: 0.0047396095469594
2023-01-24 06:27:27.459239: step: 1316/529, loss: 0.003213820978999138
2023-01-24 06:27:28.541640: step: 1320/529, loss: 0.0008751116110943258
2023-01-24 06:27:29.615864: step: 1324/529, loss: 0.011827266775071621
2023-01-24 06:27:30.686712: step: 1328/529, loss: 0.014146394096314907
2023-01-24 06:27:31.790139: step: 1332/529, loss: 0.0036795600317418575
2023-01-24 06:27:32.877372: step: 1336/529, loss: 0.011944161728024483
2023-01-24 06:27:33.956914: step: 1340/529, loss: 0.04109463095664978
2023-01-24 06:27:35.052101: step: 1344/529, loss: 0.009228614158928394
2023-01-24 06:27:36.120410: step: 1348/529, loss: 0.0016489842673763633
2023-01-24 06:27:37.199753: step: 1352/529, loss: 0.01078275591135025
2023-01-24 06:27:38.296175: step: 1356/529, loss: 0.0020169378258287907
2023-01-24 06:27:39.371615: step: 1360/529, loss: 0.013365722261369228
2023-01-24 06:27:40.465884: step: 1364/529, loss: 0.034779567271471024
2023-01-24 06:27:41.546673: step: 1368/529, loss: 0.011920524761080742
2023-01-24 06:27:42.637446: step: 1372/529, loss: 0.005875522270798683
2023-01-24 06:27:43.722833: step: 1376/529, loss: 0.00880617368966341
2023-01-24 06:27:44.800595: step: 1380/529, loss: 0.008332458324730396
2023-01-24 06:27:45.887388: step: 1384/529, loss: 0.013337942771613598
2023-01-24 06:27:46.990511: step: 1388/529, loss: 0.009446166455745697
2023-01-24 06:27:48.068091: step: 1392/529, loss: 0.016431570053100586
2023-01-24 06:27:49.154330: step: 1396/529, loss: 0.021695852279663086
2023-01-24 06:27:50.253194: step: 1400/529, loss: 0.0033575354609638453
2023-01-24 06:27:51.345747: step: 1404/529, loss: 0.037024397403001785
2023-01-24 06:27:52.426397: step: 1408/529, loss: 0.021687215194106102
2023-01-24 06:27:53.512738: step: 1412/529, loss: 0.0077699655666947365
2023-01-24 06:27:54.600200: step: 1416/529, loss: 0.0004141340032219887
2023-01-24 06:27:55.685780: step: 1420/529, loss: 0.003890436142683029
2023-01-24 06:27:56.754669: step: 1424/529, loss: 0.0012461403384804726
2023-01-24 06:27:57.830940: step: 1428/529, loss: 0.0058377389796078205
2023-01-24 06:27:58.910620: step: 1432/529, loss: 0.009935363195836544
2023-01-24 06:27:59.987672: step: 1436/529, loss: 0.01389356330037117
2023-01-24 06:28:01.073787: step: 1440/529, loss: 0.008554589003324509
2023-01-24 06:28:02.158581: step: 1444/529, loss: 0.065959133207798
2023-01-24 06:28:03.264336: step: 1448/529, loss: 0.037170734256505966
2023-01-24 06:28:04.325340: step: 1452/529, loss: 0.004982625599950552
2023-01-24 06:28:05.412039: step: 1456/529, loss: 0.0029572409112006426
2023-01-24 06:28:06.469573: step: 1460/529, loss: 1.1880091733473819e-05
2023-01-24 06:28:07.562171: step: 1464/529, loss: 0.011264627799391747
2023-01-24 06:28:08.645470: step: 1468/529, loss: 0.0030728185083717108
2023-01-24 06:28:09.724897: step: 1472/529, loss: 0.007966026663780212
2023-01-24 06:28:10.806640: step: 1476/529, loss: 0.024318084120750427
2023-01-24 06:28:11.882832: step: 1480/529, loss: 0.0017617353005334735
2023-01-24 06:28:12.971337: step: 1484/529, loss: 0.034694306552410126
2023-01-24 06:28:14.089666: step: 1488/529, loss: 0.08897338062524796
2023-01-24 06:28:15.167166: step: 1492/529, loss: 0.013717732392251492
2023-01-24 06:28:16.265429: step: 1496/529, loss: 0.0101424315944314
2023-01-24 06:28:17.343562: step: 1500/529, loss: 0.0019414408598095179
2023-01-24 06:28:18.427535: step: 1504/529, loss: 0.002259514993056655
2023-01-24 06:28:19.483725: step: 1508/529, loss: 0.0036597619764506817
2023-01-24 06:28:20.566467: step: 1512/529, loss: 0.04667592793703079
2023-01-24 06:28:21.653992: step: 1516/529, loss: 0.017591072246432304
2023-01-24 06:28:22.719154: step: 1520/529, loss: 0.0001521392841823399
2023-01-24 06:28:23.795530: step: 1524/529, loss: 0.013777170330286026
2023-01-24 06:28:24.862035: step: 1528/529, loss: 0.004690087866038084
2023-01-24 06:28:25.936904: step: 1532/529, loss: 0.003948920406401157
2023-01-24 06:28:27.029515: step: 1536/529, loss: 0.07563547044992447
2023-01-24 06:28:28.093798: step: 1540/529, loss: 0.016616258770227432
2023-01-24 06:28:29.148244: step: 1544/529, loss: 0.005448971409350634
2023-01-24 06:28:30.221243: step: 1548/529, loss: 0.009977582842111588
2023-01-24 06:28:31.286975: step: 1552/529, loss: 0.0061608958058059216
2023-01-24 06:28:32.371147: step: 1556/529, loss: 0.002114545786753297
2023-01-24 06:28:33.440160: step: 1560/529, loss: 0.008750095963478088
2023-01-24 06:28:34.510324: step: 1564/529, loss: 0.004472228232771158
2023-01-24 06:28:35.594661: step: 1568/529, loss: 0.008842178620398045
2023-01-24 06:28:36.658780: step: 1572/529, loss: 0.003872595727443695
2023-01-24 06:28:37.727025: step: 1576/529, loss: 0.0160906333476305
2023-01-24 06:28:38.795685: step: 1580/529, loss: 0.012151301838457584
2023-01-24 06:28:39.869715: step: 1584/529, loss: 0.008990393951535225
2023-01-24 06:28:40.951787: step: 1588/529, loss: 0.0468946248292923
2023-01-24 06:28:42.027865: step: 1592/529, loss: 0.0056581636890769005
2023-01-24 06:28:43.094222: step: 1596/529, loss: 0.009731780737638474
2023-01-24 06:28:44.171800: step: 1600/529, loss: 0.012729713693261147
2023-01-24 06:28:45.239676: step: 1604/529, loss: 0.055125731974840164
2023-01-24 06:28:46.310211: step: 1608/529, loss: 0.07322222739458084
2023-01-24 06:28:47.390412: step: 1612/529, loss: 0.05458943918347359
2023-01-24 06:28:48.494497: step: 1616/529, loss: 0.005859483499079943
2023-01-24 06:28:49.575437: step: 1620/529, loss: 0.017146673053503036
2023-01-24 06:28:50.651892: step: 1624/529, loss: 0.016247712075710297
2023-01-24 06:28:51.716566: step: 1628/529, loss: 0.008485060185194016
2023-01-24 06:28:52.798535: step: 1632/529, loss: 0.0033759544603526592
2023-01-24 06:28:53.873206: step: 1636/529, loss: 0.007815441116690636
2023-01-24 06:28:54.934245: step: 1640/529, loss: 0.003971477504819632
2023-01-24 06:28:56.013646: step: 1644/529, loss: 0.006523026153445244
2023-01-24 06:28:57.087220: step: 1648/529, loss: 0.0017680278979241848
2023-01-24 06:28:58.177392: step: 1652/529, loss: 0.0053138285875320435
2023-01-24 06:28:59.244428: step: 1656/529, loss: 0.03768530488014221
2023-01-24 06:29:00.322058: step: 1660/529, loss: 0.0081466194242239
2023-01-24 06:29:01.394498: step: 1664/529, loss: 0.007737896870821714
2023-01-24 06:29:02.470289: step: 1668/529, loss: 0.011441116221249104
2023-01-24 06:29:03.525902: step: 1672/529, loss: 0.01290665753185749
2023-01-24 06:29:04.589269: step: 1676/529, loss: 0.0031395989935845137
2023-01-24 06:29:05.649127: step: 1680/529, loss: 0.01727680116891861
2023-01-24 06:29:06.732138: step: 1684/529, loss: 0.003604139434173703
2023-01-24 06:29:07.805063: step: 1688/529, loss: 0.0049101728945970535
2023-01-24 06:29:08.880655: step: 1692/529, loss: 0.003701012348756194
2023-01-24 06:29:09.959928: step: 1696/529, loss: 0.02277238667011261
2023-01-24 06:29:11.022899: step: 1700/529, loss: 0.0006703791441395879
2023-01-24 06:29:12.087461: step: 1704/529, loss: 0.012263515032827854
2023-01-24 06:29:13.177035: step: 1708/529, loss: 0.003391839098185301
2023-01-24 06:29:14.249841: step: 1712/529, loss: 0.0024109166115522385
2023-01-24 06:29:15.330652: step: 1716/529, loss: 0.0038264933973550797
2023-01-24 06:29:16.407170: step: 1720/529, loss: 0.03251434490084648
2023-01-24 06:29:17.477639: step: 1724/529, loss: 0.002734135603532195
2023-01-24 06:29:18.538347: step: 1728/529, loss: 0.0023881003726273775
2023-01-24 06:29:19.610754: step: 1732/529, loss: 0.011680040508508682
2023-01-24 06:29:20.674001: step: 1736/529, loss: 0.0020366625394672155
2023-01-24 06:29:21.741986: step: 1740/529, loss: 0.00933763850480318
2023-01-24 06:29:22.807582: step: 1744/529, loss: 0.0062961638905107975
2023-01-24 06:29:23.892279: step: 1748/529, loss: 0.0038678504060953856
2023-01-24 06:29:24.964350: step: 1752/529, loss: 0.010100818239152431
2023-01-24 06:29:26.045675: step: 1756/529, loss: 0.010858502238988876
2023-01-24 06:29:27.120038: step: 1760/529, loss: 0.00944447424262762
2023-01-24 06:29:28.189784: step: 1764/529, loss: 0.017714692279696465
2023-01-24 06:29:29.251766: step: 1768/529, loss: 0.006214953027665615
2023-01-24 06:29:30.345150: step: 1772/529, loss: 0.0027611658442765474
2023-01-24 06:29:31.420954: step: 1776/529, loss: 0.037212248891592026
2023-01-24 06:29:32.476464: step: 1780/529, loss: 0.008566268719732761
2023-01-24 06:29:33.556058: step: 1784/529, loss: 0.01868366077542305
2023-01-24 06:29:34.614351: step: 1788/529, loss: 0.002395871328189969
2023-01-24 06:29:35.686281: step: 1792/529, loss: 0.005026060622185469
2023-01-24 06:29:36.759048: step: 1796/529, loss: 0.009730721823871136
2023-01-24 06:29:37.822235: step: 1800/529, loss: 0.019793130457401276
2023-01-24 06:29:38.905746: step: 1804/529, loss: 0.015989243984222412
2023-01-24 06:29:39.997515: step: 1808/529, loss: 0.06439851224422455
2023-01-24 06:29:41.045460: step: 1812/529, loss: 0.002367462031543255
2023-01-24 06:29:42.110915: step: 1816/529, loss: 0.006908094510436058
2023-01-24 06:29:43.187593: step: 1820/529, loss: 0.0035598762333393097
2023-01-24 06:29:44.253647: step: 1824/529, loss: 0.0004046270623803139
2023-01-24 06:29:45.338982: step: 1828/529, loss: 0.010219672694802284
2023-01-24 06:29:46.414742: step: 1832/529, loss: 0.056064531207084656
2023-01-24 06:29:47.479175: step: 1836/529, loss: 0.003887404687702656
2023-01-24 06:29:48.560261: step: 1840/529, loss: 0.010096265003085136
2023-01-24 06:29:49.620246: step: 1844/529, loss: 0.01793801039457321
2023-01-24 06:29:50.679874: step: 1848/529, loss: 0.0017579769482836127
2023-01-24 06:29:51.748148: step: 1852/529, loss: 0.032831039279699326
2023-01-24 06:29:52.825744: step: 1856/529, loss: 0.01784345507621765
2023-01-24 06:29:53.902889: step: 1860/529, loss: 0.008065914735198021
2023-01-24 06:29:54.970774: step: 1864/529, loss: 0.008744626305997372
2023-01-24 06:29:56.028593: step: 1868/529, loss: 0.006435508374124765
2023-01-24 06:29:57.101749: step: 1872/529, loss: 0.010720211081206799
2023-01-24 06:29:58.161693: step: 1876/529, loss: 0.01839168556034565
2023-01-24 06:29:59.239626: step: 1880/529, loss: 0.013671822845935822
2023-01-24 06:30:00.294577: step: 1884/529, loss: 0.0024428698234260082
2023-01-24 06:30:01.357445: step: 1888/529, loss: 0.019225915893912315
2023-01-24 06:30:02.417229: step: 1892/529, loss: 0.006163674872368574
2023-01-24 06:30:03.472170: step: 1896/529, loss: 0.0037699565291404724
2023-01-24 06:30:04.544905: step: 1900/529, loss: 0.013765586540102959
2023-01-24 06:30:05.602817: step: 1904/529, loss: 0.013111330568790436
2023-01-24 06:30:06.662316: step: 1908/529, loss: 0.0034677963703870773
2023-01-24 06:30:07.711685: step: 1912/529, loss: 0.010969200171530247
2023-01-24 06:30:08.777941: step: 1916/529, loss: 0.005650100763887167
2023-01-24 06:30:09.838963: step: 1920/529, loss: 0.007209569215774536
2023-01-24 06:30:10.904395: step: 1924/529, loss: 0.022459348663687706
2023-01-24 06:30:11.969321: step: 1928/529, loss: 0.018021751195192337
2023-01-24 06:30:13.042662: step: 1932/529, loss: 0.01943148858845234
2023-01-24 06:30:14.111845: step: 1936/529, loss: 0.003262628335505724
2023-01-24 06:30:15.165427: step: 1940/529, loss: 0.010799327865242958
2023-01-24 06:30:16.257085: step: 1944/529, loss: 0.004368732217699289
2023-01-24 06:30:17.324718: step: 1948/529, loss: 0.027089713141322136
2023-01-24 06:30:18.401330: step: 1952/529, loss: 0.028108585625886917
2023-01-24 06:30:19.460878: step: 1956/529, loss: 0.006967587396502495
2023-01-24 06:30:20.537449: step: 1960/529, loss: 0.000502319831866771
2023-01-24 06:30:21.600260: step: 1964/529, loss: 0.006585522089153528
2023-01-24 06:30:22.672963: step: 1968/529, loss: 0.006087393034249544
2023-01-24 06:30:23.731821: step: 1972/529, loss: 0.0020255688577890396
2023-01-24 06:30:24.783329: step: 1976/529, loss: 0.0011896903160959482
2023-01-24 06:30:25.870449: step: 1980/529, loss: 0.015363163314759731
2023-01-24 06:30:26.945994: step: 1984/529, loss: 0.004335400182753801
2023-01-24 06:30:28.027535: step: 1988/529, loss: 0.01175539568066597
2023-01-24 06:30:29.146039: step: 1992/529, loss: 0.011699249967932701
2023-01-24 06:30:30.233656: step: 1996/529, loss: 0.02545962482690811
2023-01-24 06:30:31.313767: step: 2000/529, loss: 0.0006460958393290639
2023-01-24 06:30:32.391012: step: 2004/529, loss: 0.009515242651104927
2023-01-24 06:30:33.446331: step: 2008/529, loss: 0.04111385717988014
2023-01-24 06:30:34.509366: step: 2012/529, loss: 0.005877222865819931
2023-01-24 06:30:35.585120: step: 2016/529, loss: 0.007505779154598713
2023-01-24 06:30:36.633971: step: 2020/529, loss: 0.008421323262155056
2023-01-24 06:30:37.700750: step: 2024/529, loss: 0.016268698498606682
2023-01-24 06:30:38.777239: step: 2028/529, loss: 0.012657465413212776
2023-01-24 06:30:39.836614: step: 2032/529, loss: 0.005319786258041859
2023-01-24 06:30:40.902914: step: 2036/529, loss: 0.023542700335383415
2023-01-24 06:30:41.982019: step: 2040/529, loss: 0.006941151339560747
2023-01-24 06:30:43.101402: step: 2044/529, loss: 0.0069933389313519
2023-01-24 06:30:44.168617: step: 2048/529, loss: 0.008115910924971104
2023-01-24 06:30:45.255778: step: 2052/529, loss: 0.0010779907461255789
2023-01-24 06:30:46.345343: step: 2056/529, loss: 0.020473960787057877
2023-01-24 06:30:47.408927: step: 2060/529, loss: 0.007803792133927345
2023-01-24 06:30:48.481205: step: 2064/529, loss: 0.0056096287444233894
2023-01-24 06:30:49.559621: step: 2068/529, loss: 0.02149871550500393
2023-01-24 06:30:50.627812: step: 2072/529, loss: 0.011949121952056885
2023-01-24 06:30:51.692759: step: 2076/529, loss: 0.011404074728488922
2023-01-24 06:30:52.750214: step: 2080/529, loss: 0.010310224257409573
2023-01-24 06:30:53.813315: step: 2084/529, loss: 0.013979884795844555
2023-01-24 06:30:54.894508: step: 2088/529, loss: 0.013739165849983692
2023-01-24 06:30:55.960211: step: 2092/529, loss: 0.0023008326534181833
2023-01-24 06:30:57.033452: step: 2096/529, loss: 0.012866536155343056
2023-01-24 06:30:58.107231: step: 2100/529, loss: 0.004443677142262459
2023-01-24 06:30:59.201658: step: 2104/529, loss: 0.045822624117136
2023-01-24 06:31:00.271253: step: 2108/529, loss: 0.009228694252669811
2023-01-24 06:31:01.344970: step: 2112/529, loss: 0.007563404273241758
2023-01-24 06:31:02.428645: step: 2116/529, loss: 0.009492633864283562
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3432444899403499, 'r': 0.30677069214782693, 'f1': 0.32398427807996955}, 'combined': 0.23872525753260912, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32829423635487776, 'r': 0.2893696439929483, 'f1': 0.3076054447135591}, 'combined': 0.20082013489071734, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
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': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, '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 06:33:48.665327: step: 4/529, loss: 0.005306081846356392
2023-01-24 06:33:49.733174: step: 8/529, loss: 0.01165945827960968
2023-01-24 06:33:50.785618: step: 12/529, loss: 0.025551021099090576
2023-01-24 06:33:51.854243: step: 16/529, loss: 0.00669049471616745
2023-01-24 06:33:52.918883: step: 20/529, loss: 0.002775543835014105
2023-01-24 06:33:53.983807: step: 24/529, loss: 0.0016739120474085212
2023-01-24 06:33:55.038980: step: 28/529, loss: 0.004657388664782047
2023-01-24 06:33:56.106522: step: 32/529, loss: 0.0074105532839894295
2023-01-24 06:33:57.170576: step: 36/529, loss: 0.0015190700069069862
2023-01-24 06:33:58.231603: step: 40/529, loss: 0.04774459823966026
2023-01-24 06:33:59.298988: step: 44/529, loss: 0.007806417997926474
2023-01-24 06:34:00.365734: step: 48/529, loss: 0.006820150185376406
2023-01-24 06:34:01.418010: step: 52/529, loss: 0.0010121590457856655
2023-01-24 06:34:02.490406: step: 56/529, loss: 0.009199569001793861
2023-01-24 06:34:03.554475: step: 60/529, loss: 0.013597894459962845
2023-01-24 06:34:04.607056: step: 64/529, loss: 0.00033319779322482646
2023-01-24 06:34:05.680005: step: 68/529, loss: 0.0039946516044437885
2023-01-24 06:34:06.747253: step: 72/529, loss: 0.004073295276612043
2023-01-24 06:34:07.821460: step: 76/529, loss: 0.005464494228363037
2023-01-24 06:34:08.885889: step: 80/529, loss: 0.014722703024744987
2023-01-24 06:34:09.944527: step: 84/529, loss: 0.00970328040421009
2023-01-24 06:34:11.019814: step: 88/529, loss: 0.0037130180280655622
2023-01-24 06:34:12.090951: step: 92/529, loss: 0.004681583493947983
2023-01-24 06:34:13.164402: step: 96/529, loss: 0.00022668573365081102
2023-01-24 06:34:14.219816: step: 100/529, loss: 0.004565810784697533
2023-01-24 06:34:15.278424: step: 104/529, loss: 0.0077153155580163
2023-01-24 06:34:16.367195: step: 108/529, loss: 0.016666296869516373
2023-01-24 06:34:17.450268: step: 112/529, loss: 0.0030223659705370665
2023-01-24 06:34:18.497516: step: 116/529, loss: 0.006218838505446911
2023-01-24 06:34:19.582617: step: 120/529, loss: 0.012414630502462387
2023-01-24 06:34:20.646405: step: 124/529, loss: 0.0080726845189929
2023-01-24 06:34:21.698910: step: 128/529, loss: 0.0008169668144546449
2023-01-24 06:34:22.757654: step: 132/529, loss: 0.000573504192288965
2023-01-24 06:34:23.845668: step: 136/529, loss: 0.00733181880787015
2023-01-24 06:34:24.921876: step: 140/529, loss: 0.03185557201504707
2023-01-24 06:34:25.992271: step: 144/529, loss: 0.00632117735221982
2023-01-24 06:34:27.067630: step: 148/529, loss: 0.0017276605358347297
2023-01-24 06:34:28.119161: step: 152/529, loss: 0.035782888531684875
2023-01-24 06:34:29.185814: step: 156/529, loss: 0.009627927094697952
2023-01-24 06:34:30.252407: step: 160/529, loss: 0.04056047275662422
2023-01-24 06:34:31.322538: step: 164/529, loss: 0.006219907198101282
2023-01-24 06:34:32.382054: step: 168/529, loss: 0.0039070723578333855
2023-01-24 06:34:33.463474: step: 172/529, loss: 0.019929764792323112
2023-01-24 06:34:34.530963: step: 176/529, loss: 0.003329492174088955
2023-01-24 06:34:35.611790: step: 180/529, loss: 0.010492537170648575
2023-01-24 06:34:36.685770: step: 184/529, loss: 0.01743011362850666
2023-01-24 06:34:37.749940: step: 188/529, loss: 0.00692491140216589
2023-01-24 06:34:38.820045: step: 192/529, loss: 0.006524811498820782
2023-01-24 06:34:39.878881: step: 196/529, loss: 0.0078565813601017
2023-01-24 06:34:40.942893: step: 200/529, loss: 0.015842001885175705
2023-01-24 06:34:42.011697: step: 204/529, loss: 0.005076906643807888
2023-01-24 06:34:43.099243: step: 208/529, loss: 0.010431725531816483
2023-01-24 06:34:44.165194: step: 212/529, loss: 0.0067523508332669735
2023-01-24 06:34:45.248357: step: 216/529, loss: 0.005084163509309292
2023-01-24 06:34:46.314851: step: 220/529, loss: 0.0032661170698702335
2023-01-24 06:34:47.378340: step: 224/529, loss: 0.004277156665921211
2023-01-24 06:34:48.446213: step: 228/529, loss: 0.00416102260351181
2023-01-24 06:34:49.512484: step: 232/529, loss: 0.009883806109428406
2023-01-24 06:34:50.601157: step: 236/529, loss: 0.013675697147846222
2023-01-24 06:34:51.668507: step: 240/529, loss: 0.007257337681949139
2023-01-24 06:34:52.746694: step: 244/529, loss: 0.005144351627677679
2023-01-24 06:34:53.825242: step: 248/529, loss: 0.006191601511090994
2023-01-24 06:34:54.911653: step: 252/529, loss: 0.016674751415848732
2023-01-24 06:34:55.992428: step: 256/529, loss: 0.0012712310999631882
2023-01-24 06:34:57.073427: step: 260/529, loss: 0.006329537369310856
2023-01-24 06:34:58.159166: step: 264/529, loss: 0.004793352447450161
2023-01-24 06:34:59.227139: step: 268/529, loss: 0.01138306688517332
2023-01-24 06:35:00.282197: step: 272/529, loss: 0.004126550629734993
2023-01-24 06:35:01.350003: step: 276/529, loss: 0.0035139364190399647
2023-01-24 06:35:02.412189: step: 280/529, loss: 0.004335692152380943
2023-01-24 06:35:03.485051: step: 284/529, loss: 0.002115140203386545
2023-01-24 06:35:04.568208: step: 288/529, loss: 0.006532656494528055
2023-01-24 06:35:05.628881: step: 292/529, loss: 0.011361896991729736
2023-01-24 06:35:06.700135: step: 296/529, loss: 0.0011511738412082195
2023-01-24 06:35:07.771598: step: 300/529, loss: 0.0339822918176651
2023-01-24 06:35:08.853356: step: 304/529, loss: 0.02406451664865017
2023-01-24 06:35:09.923152: step: 308/529, loss: 0.027834169566631317
2023-01-24 06:35:10.982491: step: 312/529, loss: 0.0013004255015403032
2023-01-24 06:35:12.051059: step: 316/529, loss: 0.003725425573065877
2023-01-24 06:35:13.123230: step: 320/529, loss: 0.00986859854310751
2023-01-24 06:35:14.208354: step: 324/529, loss: 0.009932243265211582
2023-01-24 06:35:15.298155: step: 328/529, loss: 0.002096701180562377
2023-01-24 06:35:16.394775: step: 332/529, loss: 0.030377984046936035
2023-01-24 06:35:17.476568: step: 336/529, loss: 0.00202542869374156
2023-01-24 06:35:18.562600: step: 340/529, loss: 0.0004344083135947585
2023-01-24 06:35:19.624976: step: 344/529, loss: 0.0042776083573699
2023-01-24 06:35:20.703848: step: 348/529, loss: 0.031020637601614
2023-01-24 06:35:21.779188: step: 352/529, loss: 0.0013227768940851092
2023-01-24 06:35:22.867919: step: 356/529, loss: 0.010704068467020988
2023-01-24 06:35:23.958386: step: 360/529, loss: 0.008606866002082825
2023-01-24 06:35:25.027850: step: 364/529, loss: 0.00715230917558074
2023-01-24 06:35:26.093603: step: 368/529, loss: 0.0032142442651093006
2023-01-24 06:35:27.176439: step: 372/529, loss: 0.0022923434153199196
2023-01-24 06:35:28.237708: step: 376/529, loss: 0.02998194471001625
2023-01-24 06:35:29.293244: step: 380/529, loss: 0.004120546858757734
2023-01-24 06:35:30.370244: step: 384/529, loss: 0.007094264030456543
2023-01-24 06:35:31.448407: step: 388/529, loss: 0.014737040735781193
2023-01-24 06:35:32.523120: step: 392/529, loss: 0.010227232240140438
2023-01-24 06:35:33.600897: step: 396/529, loss: 0.018505224958062172
2023-01-24 06:35:34.671287: step: 400/529, loss: 0.0019069066038355231
2023-01-24 06:35:35.755093: step: 404/529, loss: 0.014191785827279091
2023-01-24 06:35:36.834414: step: 408/529, loss: 0.004034942481666803
2023-01-24 06:35:37.924717: step: 412/529, loss: 0.025709589943289757
2023-01-24 06:35:39.016534: step: 416/529, loss: 0.011058644391596317
2023-01-24 06:35:40.081697: step: 420/529, loss: 0.008795877918601036
2023-01-24 06:35:41.165068: step: 424/529, loss: 0.001207193243317306
2023-01-24 06:35:42.231895: step: 428/529, loss: 0.008448513224720955
2023-01-24 06:35:43.301826: step: 432/529, loss: 0.0015582371270284057
2023-01-24 06:35:44.390240: step: 436/529, loss: 0.006277194246649742
2023-01-24 06:35:45.467982: step: 440/529, loss: 0.002147891791537404
2023-01-24 06:35:46.558983: step: 444/529, loss: 0.0020357149187475443
2023-01-24 06:35:47.627663: step: 448/529, loss: 0.016439586877822876
2023-01-24 06:35:48.699426: step: 452/529, loss: 0.023635433986783028
2023-01-24 06:35:49.788321: step: 456/529, loss: 0.017845846712589264
2023-01-24 06:35:50.880210: step: 460/529, loss: 0.005339685827493668
2023-01-24 06:35:51.972398: step: 464/529, loss: 0.0032788454554975033
2023-01-24 06:35:53.044643: step: 468/529, loss: 0.0049303025007247925
2023-01-24 06:35:54.126591: step: 472/529, loss: 0.07946745306253433
2023-01-24 06:35:55.220287: step: 476/529, loss: 0.012931461445987225
2023-01-24 06:35:56.303730: step: 480/529, loss: 0.005204359069466591
2023-01-24 06:35:57.388943: step: 484/529, loss: 0.0033782885875552893
2023-01-24 06:35:58.474258: step: 488/529, loss: 0.0067017050459980965
2023-01-24 06:35:59.571341: step: 492/529, loss: 0.013821267522871494
2023-01-24 06:36:00.664813: step: 496/529, loss: 0.00670505641028285
2023-01-24 06:36:01.754356: step: 500/529, loss: 0.00608456926420331
2023-01-24 06:36:02.849867: step: 504/529, loss: 0.013473868370056152
2023-01-24 06:36:03.933896: step: 508/529, loss: 0.032499514520168304
2023-01-24 06:36:05.013306: step: 512/529, loss: 0.0009791419142857194
2023-01-24 06:36:06.097517: step: 516/529, loss: 0.0044460603967309
2023-01-24 06:36:07.183779: step: 520/529, loss: 0.00795968621969223
2023-01-24 06:36:08.241363: step: 524/529, loss: 0.006531299091875553
2023-01-24 06:36:09.317360: step: 528/529, loss: 0.006767368409782648
2023-01-24 06:36:10.414388: step: 532/529, loss: 0.0035915214102715254
2023-01-24 06:36:11.494381: step: 536/529, loss: 0.030227866023778915
2023-01-24 06:36:12.568876: step: 540/529, loss: 0.0029931794852018356
2023-01-24 06:36:13.652243: step: 544/529, loss: 0.011107520200312138
2023-01-24 06:36:14.725682: step: 548/529, loss: 0.006771856918931007
2023-01-24 06:36:15.823634: step: 552/529, loss: 0.008452314883470535
2023-01-24 06:36:16.912128: step: 556/529, loss: 0.006177971139550209
2023-01-24 06:36:17.994649: step: 560/529, loss: 0.03494871407747269
2023-01-24 06:36:19.080135: step: 564/529, loss: 0.00797675084322691
2023-01-24 06:36:20.163609: step: 568/529, loss: 0.015033339150249958
2023-01-24 06:36:21.265797: step: 572/529, loss: 0.0018735273042693734
2023-01-24 06:36:22.343258: step: 576/529, loss: 0.011242460459470749
2023-01-24 06:36:23.408646: step: 580/529, loss: 0.006593300029635429
2023-01-24 06:36:24.464745: step: 584/529, loss: 0.009311879053711891
2023-01-24 06:36:25.560364: step: 588/529, loss: 0.006556670647114515
2023-01-24 06:36:26.648879: step: 592/529, loss: 0.0021247942931950092
2023-01-24 06:36:27.733457: step: 596/529, loss: 0.0019866900984197855
2023-01-24 06:36:28.818012: step: 600/529, loss: 0.006030280143022537
2023-01-24 06:36:29.900949: step: 604/529, loss: 2.6696779968915507e-05
2023-01-24 06:36:31.001225: step: 608/529, loss: 0.04135812819004059
2023-01-24 06:36:32.094108: step: 612/529, loss: 0.007614175323396921
2023-01-24 06:36:33.184522: step: 616/529, loss: 0.0031433100812137127
2023-01-24 06:36:34.251961: step: 620/529, loss: 0.010717714205384254
2023-01-24 06:36:35.321177: step: 624/529, loss: 0.010698345489799976
2023-01-24 06:36:36.412027: step: 628/529, loss: 0.023886142298579216
2023-01-24 06:36:37.483194: step: 632/529, loss: 0.003928531892597675
2023-01-24 06:36:38.567421: step: 636/529, loss: 0.016103779897093773
2023-01-24 06:36:39.661320: step: 640/529, loss: 0.013525239191949368
2023-01-24 06:36:40.749932: step: 644/529, loss: 0.03457599878311157
2023-01-24 06:36:41.823165: step: 648/529, loss: 0.008419967256486416
2023-01-24 06:36:42.911989: step: 652/529, loss: 0.0049747442826628685
2023-01-24 06:36:44.030944: step: 656/529, loss: 0.008991905488073826
2023-01-24 06:36:45.131622: step: 660/529, loss: 0.0271906778216362
2023-01-24 06:36:46.213741: step: 664/529, loss: 0.018528439104557037
2023-01-24 06:36:47.300819: step: 668/529, loss: 0.007969571277499199
2023-01-24 06:36:48.394339: step: 672/529, loss: 0.024170290678739548
2023-01-24 06:36:49.466376: step: 676/529, loss: 0.019351670518517494
2023-01-24 06:36:50.546129: step: 680/529, loss: 0.004487547092139721
2023-01-24 06:36:51.623471: step: 684/529, loss: 0.006088240537792444
2023-01-24 06:36:52.705123: step: 688/529, loss: 0.002518126042559743
2023-01-24 06:36:53.782522: step: 692/529, loss: 0.00971476174890995
2023-01-24 06:36:54.866041: step: 696/529, loss: 0.004671934992074966
2023-01-24 06:36:55.945099: step: 700/529, loss: 0.004092163406312466
2023-01-24 06:36:57.044842: step: 704/529, loss: 0.023588519543409348
2023-01-24 06:36:58.137603: step: 708/529, loss: 0.012343088164925575
2023-01-24 06:36:59.207018: step: 712/529, loss: 0.0014462524559348822
2023-01-24 06:37:00.276308: step: 716/529, loss: 0.009823783300817013
2023-01-24 06:37:01.375588: step: 720/529, loss: 0.0078210374340415
2023-01-24 06:37:02.449456: step: 724/529, loss: 0.0024997733999043703
2023-01-24 06:37:03.529522: step: 728/529, loss: 0.015557827427983284
2023-01-24 06:37:04.601603: step: 732/529, loss: 0.009667051956057549
2023-01-24 06:37:05.691199: step: 736/529, loss: 0.0020753752905875444
2023-01-24 06:37:06.783009: step: 740/529, loss: 0.0031915053259581327
2023-01-24 06:37:07.856406: step: 744/529, loss: 0.017997652292251587
2023-01-24 06:37:08.938538: step: 748/529, loss: 0.0038397267926484346
2023-01-24 06:37:10.010010: step: 752/529, loss: 0.010845580138266087
2023-01-24 06:37:11.083122: step: 756/529, loss: 0.0056469980627298355
2023-01-24 06:37:12.162679: step: 760/529, loss: 0.024205049499869347
2023-01-24 06:37:13.256991: step: 764/529, loss: 0.009294592775404453
2023-01-24 06:37:14.328862: step: 768/529, loss: 0.005519056227058172
2023-01-24 06:37:15.413922: step: 772/529, loss: 0.0066510592587292194
2023-01-24 06:37:16.496171: step: 776/529, loss: 0.00451636454090476
2023-01-24 06:37:17.588686: step: 780/529, loss: 0.006918779108673334
2023-01-24 06:37:18.654186: step: 784/529, loss: 0.003937877714633942
2023-01-24 06:37:19.717708: step: 788/529, loss: 0.0034500632900744677
2023-01-24 06:37:20.788040: step: 792/529, loss: 0.015180250629782677
2023-01-24 06:37:21.861741: step: 796/529, loss: 0.005527715664356947
2023-01-24 06:37:22.944755: step: 800/529, loss: 0.0026738387532532215
2023-01-24 06:37:24.017059: step: 804/529, loss: 0.010368620976805687
2023-01-24 06:37:25.076216: step: 808/529, loss: 0.005900280084460974
2023-01-24 06:37:26.146110: step: 812/529, loss: 0.01362408697605133
2023-01-24 06:37:27.236815: step: 816/529, loss: 0.009619764983654022
2023-01-24 06:37:28.305451: step: 820/529, loss: 0.011690499261021614
2023-01-24 06:37:29.387855: step: 824/529, loss: 0.01570005528628826
2023-01-24 06:37:30.457208: step: 828/529, loss: 0.00252782111056149
2023-01-24 06:37:31.544680: step: 832/529, loss: 0.033378612250089645
2023-01-24 06:37:32.621894: step: 836/529, loss: 0.02463219128549099
2023-01-24 06:37:33.699175: step: 840/529, loss: 0.01371025387197733
2023-01-24 06:37:34.784457: step: 844/529, loss: 0.0005712570855394006
2023-01-24 06:37:35.860605: step: 848/529, loss: 0.0033849880564957857
2023-01-24 06:37:36.951343: step: 852/529, loss: 0.015501162968575954
2023-01-24 06:37:38.027991: step: 856/529, loss: 0.0033761262893676758
2023-01-24 06:37:39.104170: step: 860/529, loss: 0.003269011853262782
2023-01-24 06:37:40.180998: step: 864/529, loss: 0.005324568599462509
2023-01-24 06:37:41.250343: step: 868/529, loss: 0.015953127294778824
2023-01-24 06:37:42.315263: step: 872/529, loss: 0.011110708117485046
2023-01-24 06:37:43.426004: step: 876/529, loss: 0.009748917073011398
2023-01-24 06:37:44.501103: step: 880/529, loss: 0.030173728242516518
2023-01-24 06:37:45.577652: step: 884/529, loss: 0.009095161221921444
2023-01-24 06:37:46.651876: step: 888/529, loss: 0.007395054213702679
2023-01-24 06:37:47.717934: step: 892/529, loss: 0.001859817304648459
2023-01-24 06:37:48.800075: step: 896/529, loss: 0.015024775639176369
2023-01-24 06:37:49.887232: step: 900/529, loss: 0.036551643162965775
2023-01-24 06:37:50.964621: step: 904/529, loss: 0.004126851912587881
2023-01-24 06:37:52.031566: step: 908/529, loss: 0.0037501517217606306
2023-01-24 06:37:53.095333: step: 912/529, loss: 0.0016765149775892496
2023-01-24 06:37:54.162777: step: 916/529, loss: 0.00263429107144475
2023-01-24 06:37:55.225402: step: 920/529, loss: 0.010215152986347675
2023-01-24 06:37:56.286466: step: 924/529, loss: 0.01056759338825941
2023-01-24 06:37:57.390911: step: 928/529, loss: 0.006834817118942738
2023-01-24 06:37:58.477981: step: 932/529, loss: 0.003006510902196169
2023-01-24 06:37:59.555617: step: 936/529, loss: 0.02883508801460266
2023-01-24 06:38:00.652100: step: 940/529, loss: 0.022211819887161255
2023-01-24 06:38:01.728089: step: 944/529, loss: 0.010564801283180714
2023-01-24 06:38:02.803654: step: 948/529, loss: 0.004062940366566181
2023-01-24 06:38:03.885459: step: 952/529, loss: 0.002742258133366704
2023-01-24 06:38:04.955006: step: 956/529, loss: 0.006772853899747133
2023-01-24 06:38:06.040586: step: 960/529, loss: 0.00285226758569479
2023-01-24 06:38:07.108029: step: 964/529, loss: 0.007859828881919384
2023-01-24 06:38:08.178880: step: 968/529, loss: 0.004809211939573288
2023-01-24 06:38:09.273864: step: 972/529, loss: 0.005635186564177275
2023-01-24 06:38:10.343513: step: 976/529, loss: 0.03100399859249592
2023-01-24 06:38:11.425706: step: 980/529, loss: 0.04693903028964996
2023-01-24 06:38:12.476199: step: 984/529, loss: 0.007040327414870262
2023-01-24 06:38:13.537088: step: 988/529, loss: 0.0003511648974381387
2023-01-24 06:38:14.610858: step: 992/529, loss: 0.021587209776043892
2023-01-24 06:38:15.683505: step: 996/529, loss: 0.008670927956700325
2023-01-24 06:38:16.758032: step: 1000/529, loss: 0.00503647280856967
2023-01-24 06:38:17.827176: step: 1004/529, loss: 0.010647826828062534
2023-01-24 06:38:18.898632: step: 1008/529, loss: 0.004342544358223677
2023-01-24 06:38:19.981931: step: 1012/529, loss: 0.021491017192602158
2023-01-24 06:38:21.059503: step: 1016/529, loss: 0.007109408266842365
2023-01-24 06:38:22.128266: step: 1020/529, loss: 0.026232164353132248
2023-01-24 06:38:23.213815: step: 1024/529, loss: 0.026226766407489777
2023-01-24 06:38:24.295936: step: 1028/529, loss: 0.009091410785913467
2023-01-24 06:38:25.373411: step: 1032/529, loss: 0.013991279527544975
2023-01-24 06:38:26.436643: step: 1036/529, loss: 0.007567662745714188
2023-01-24 06:38:27.513280: step: 1040/529, loss: 0.003366368357092142
2023-01-24 06:38:28.589084: step: 1044/529, loss: 0.0064007192850112915
2023-01-24 06:38:29.664290: step: 1048/529, loss: 0.04431624710559845
2023-01-24 06:38:30.745407: step: 1052/529, loss: 0.02152891270816326
2023-01-24 06:38:31.826734: step: 1056/529, loss: 0.011203648522496223
2023-01-24 06:38:32.900453: step: 1060/529, loss: 0.009548647329211235
2023-01-24 06:38:33.968923: step: 1064/529, loss: 0.003137181745842099
2023-01-24 06:38:35.060144: step: 1068/529, loss: 0.0017036364879459143
2023-01-24 06:38:36.131090: step: 1072/529, loss: 0.022670309990644455
2023-01-24 06:38:37.200590: step: 1076/529, loss: 0.00296448334120214
2023-01-24 06:38:38.267799: step: 1080/529, loss: 0.0032868662383407354
2023-01-24 06:38:39.362305: step: 1084/529, loss: 0.00535968504846096
2023-01-24 06:38:40.432056: step: 1088/529, loss: 0.008010120131075382
2023-01-24 06:38:41.518743: step: 1092/529, loss: 0.0042228600941598415
2023-01-24 06:38:42.597734: step: 1096/529, loss: 0.04953213036060333
2023-01-24 06:38:43.681398: step: 1100/529, loss: 0.015964580699801445
2023-01-24 06:38:44.751240: step: 1104/529, loss: 0.0062031252309679985
2023-01-24 06:38:45.805567: step: 1108/529, loss: 0.01025872491300106
2023-01-24 06:38:46.867685: step: 1112/529, loss: 0.004633505363017321
2023-01-24 06:38:47.937887: step: 1116/529, loss: 0.003801979124546051
2023-01-24 06:38:49.013112: step: 1120/529, loss: 0.0025255049113184214
2023-01-24 06:38:50.086245: step: 1124/529, loss: 0.0019073954317718744
2023-01-24 06:38:51.174339: step: 1128/529, loss: 0.006439147517085075
2023-01-24 06:38:52.253514: step: 1132/529, loss: 0.005457963794469833
2023-01-24 06:38:53.330070: step: 1136/529, loss: 0.0097409188747406
2023-01-24 06:38:54.386071: step: 1140/529, loss: 0.0014348758850246668
2023-01-24 06:38:55.466534: step: 1144/529, loss: 0.004820538684725761
2023-01-24 06:38:56.540168: step: 1148/529, loss: 0.006507347337901592
2023-01-24 06:38:57.614021: step: 1152/529, loss: 0.0009271916933357716
2023-01-24 06:38:58.686450: step: 1156/529, loss: 0.004905874840915203
2023-01-24 06:38:59.765676: step: 1160/529, loss: 0.014403492212295532
2023-01-24 06:39:00.849306: step: 1164/529, loss: 0.01025901548564434
2023-01-24 06:39:01.935742: step: 1168/529, loss: 0.017725173383951187
2023-01-24 06:39:03.002068: step: 1172/529, loss: 0.003254067851230502
2023-01-24 06:39:04.073055: step: 1176/529, loss: 0.06489744037389755
2023-01-24 06:39:05.152642: step: 1180/529, loss: 0.006055659614503384
2023-01-24 06:39:06.220178: step: 1184/529, loss: 0.02200540527701378
2023-01-24 06:39:07.293310: step: 1188/529, loss: 0.01975547894835472
2023-01-24 06:39:08.373747: step: 1192/529, loss: 0.00919928029179573
2023-01-24 06:39:09.434046: step: 1196/529, loss: 0.00953410379588604
2023-01-24 06:39:10.502974: step: 1200/529, loss: 0.02829376608133316
2023-01-24 06:39:11.558127: step: 1204/529, loss: 0.003076962660998106
2023-01-24 06:39:12.630014: step: 1208/529, loss: 0.006185153499245644
2023-01-24 06:39:13.717610: step: 1212/529, loss: 0.001367044635117054
2023-01-24 06:39:14.784305: step: 1216/529, loss: 0.004037867300212383
2023-01-24 06:39:15.848308: step: 1220/529, loss: 0.005665189120918512
2023-01-24 06:39:16.920244: step: 1224/529, loss: 0.008640700951218605
2023-01-24 06:39:17.994610: step: 1228/529, loss: 0.005546838045120239
2023-01-24 06:39:19.075770: step: 1232/529, loss: 0.01690641976892948
2023-01-24 06:39:20.131893: step: 1236/529, loss: 0.004949650727212429
2023-01-24 06:39:21.220764: step: 1240/529, loss: 0.012577560730278492
2023-01-24 06:39:22.274493: step: 1244/529, loss: 0.002623192733153701
2023-01-24 06:39:23.338521: step: 1248/529, loss: 0.015778103843331337
2023-01-24 06:39:24.425196: step: 1252/529, loss: 0.0019661467522382736
2023-01-24 06:39:25.503246: step: 1256/529, loss: 0.005598688032478094
2023-01-24 06:39:26.570219: step: 1260/529, loss: 0.023746563121676445
2023-01-24 06:39:27.650566: step: 1264/529, loss: 0.02076910063624382
2023-01-24 06:39:28.714482: step: 1268/529, loss: 0.012793630361557007
2023-01-24 06:39:29.787045: step: 1272/529, loss: 0.007723736576735973
2023-01-24 06:39:30.875792: step: 1276/529, loss: 0.0028649610467255116
2023-01-24 06:39:31.964910: step: 1280/529, loss: 0.022496290504932404
2023-01-24 06:39:33.046526: step: 1284/529, loss: 0.00020430835138540715
2023-01-24 06:39:34.108918: step: 1288/529, loss: 0.06546629965305328
2023-01-24 06:39:35.183347: step: 1292/529, loss: 0.006132582668215036
2023-01-24 06:39:36.264973: step: 1296/529, loss: 0.031766265630722046
2023-01-24 06:39:37.333571: step: 1300/529, loss: 0.016393672674894333
2023-01-24 06:39:38.411421: step: 1304/529, loss: 0.009899788536131382
2023-01-24 06:39:39.464237: step: 1308/529, loss: 0.03336502984166145
2023-01-24 06:39:40.531499: step: 1312/529, loss: 0.02855636365711689
2023-01-24 06:39:41.624987: step: 1316/529, loss: 0.011804209090769291
2023-01-24 06:39:42.718429: step: 1320/529, loss: 0.04140903428196907
2023-01-24 06:39:43.788217: step: 1324/529, loss: 0.025253072381019592
2023-01-24 06:39:44.866158: step: 1328/529, loss: 0.004349129740148783
2023-01-24 06:39:45.946131: step: 1332/529, loss: 0.00424607377499342
2023-01-24 06:39:47.014149: step: 1336/529, loss: 0.05381146818399429
2023-01-24 06:39:48.091510: step: 1340/529, loss: 0.006734470371156931
2023-01-24 06:39:49.159652: step: 1344/529, loss: 0.0036293980665504932
2023-01-24 06:39:50.245333: step: 1348/529, loss: 0.008891493082046509
2023-01-24 06:39:51.326403: step: 1352/529, loss: 0.01908380538225174
2023-01-24 06:39:52.392711: step: 1356/529, loss: 0.016486801207065582
2023-01-24 06:39:53.454467: step: 1360/529, loss: 0.008257966488599777
2023-01-24 06:39:54.524264: step: 1364/529, loss: 0.03334486484527588
2023-01-24 06:39:55.614633: step: 1368/529, loss: 0.013955829665064812
2023-01-24 06:39:56.682874: step: 1372/529, loss: 9.377596143167466e-06
2023-01-24 06:39:57.750837: step: 1376/529, loss: 0.0063485875725746155
2023-01-24 06:39:58.812272: step: 1380/529, loss: 0.002045923611149192
2023-01-24 06:39:59.901902: step: 1384/529, loss: 0.01518089696764946
2023-01-24 06:40:00.969700: step: 1388/529, loss: 0.004115557298064232
2023-01-24 06:40:02.049854: step: 1392/529, loss: 0.0016862958436831832
2023-01-24 06:40:03.130065: step: 1396/529, loss: 0.025592461228370667
2023-01-24 06:40:04.208665: step: 1400/529, loss: 0.024935556575655937
2023-01-24 06:40:05.277784: step: 1404/529, loss: 0.012728538364171982
2023-01-24 06:40:06.337139: step: 1408/529, loss: 0.042654845863580704
2023-01-24 06:40:07.412912: step: 1412/529, loss: 0.010267243720591068
2023-01-24 06:40:08.463760: step: 1416/529, loss: 0.01058992836624384
2023-01-24 06:40:09.534142: step: 1420/529, loss: 0.0026905033737421036
2023-01-24 06:40:10.590631: step: 1424/529, loss: 0.0068442788906395435
2023-01-24 06:40:11.660500: step: 1428/529, loss: 0.003912247251719236
2023-01-24 06:40:12.735502: step: 1432/529, loss: 0.04170241206884384
2023-01-24 06:40:13.826202: step: 1436/529, loss: 0.006908444222062826
2023-01-24 06:40:14.900110: step: 1440/529, loss: 0.005204537883400917
2023-01-24 06:40:15.961824: step: 1444/529, loss: 0.004310019314289093
2023-01-24 06:40:17.033788: step: 1448/529, loss: 0.006490429397672415
2023-01-24 06:40:18.114775: step: 1452/529, loss: 0.005031294655054808
2023-01-24 06:40:19.213443: step: 1456/529, loss: 0.015018314123153687
2023-01-24 06:40:20.294125: step: 1460/529, loss: 0.012576140463352203
2023-01-24 06:40:21.375858: step: 1464/529, loss: 0.01709701679646969
2023-01-24 06:40:22.447099: step: 1468/529, loss: 0.02605600841343403
2023-01-24 06:40:23.507664: step: 1472/529, loss: 0.01831715553998947
2023-01-24 06:40:24.574373: step: 1476/529, loss: 0.0053050946444272995
2023-01-24 06:40:25.648594: step: 1480/529, loss: 0.00328476051799953
2023-01-24 06:40:26.741000: step: 1484/529, loss: 0.006424771621823311
2023-01-24 06:40:27.818451: step: 1488/529, loss: 0.001035862835124135
2023-01-24 06:40:28.881922: step: 1492/529, loss: 0.06115015223622322
2023-01-24 06:40:29.959628: step: 1496/529, loss: 0.027961784973740578
2023-01-24 06:40:31.017941: step: 1500/529, loss: 0.0010620169341564178
2023-01-24 06:40:32.088225: step: 1504/529, loss: 0.017797712236642838
2023-01-24 06:40:33.154025: step: 1508/529, loss: 0.0028727345634251833
2023-01-24 06:40:34.225272: step: 1512/529, loss: 0.003638346679508686
2023-01-24 06:40:35.298585: step: 1516/529, loss: 0.0059278919361531734
2023-01-24 06:40:36.356078: step: 1520/529, loss: 0.04296484962105751
2023-01-24 06:40:37.418753: step: 1524/529, loss: 0.0006260772934183478
2023-01-24 06:40:38.481197: step: 1528/529, loss: 0.0014787226682528853
2023-01-24 06:40:39.532994: step: 1532/529, loss: 0.001329754013568163
2023-01-24 06:40:40.606521: step: 1536/529, loss: 0.008486728183925152
2023-01-24 06:40:41.693603: step: 1540/529, loss: 0.0076823364943265915
2023-01-24 06:40:42.779197: step: 1544/529, loss: 0.014573008753359318
2023-01-24 06:40:43.862305: step: 1548/529, loss: 0.016743669286370277
2023-01-24 06:40:44.930947: step: 1552/529, loss: 0.0349496491253376
2023-01-24 06:40:45.989407: step: 1556/529, loss: 0.007348290644586086
2023-01-24 06:40:47.057674: step: 1560/529, loss: 0.0018828087486326694
2023-01-24 06:40:48.129335: step: 1564/529, loss: 0.022683776915073395
2023-01-24 06:40:49.188319: step: 1568/529, loss: 0.023825807496905327
2023-01-24 06:40:50.247036: step: 1572/529, loss: 0.011531732976436615
2023-01-24 06:40:51.325476: step: 1576/529, loss: 0.008588587865233421
2023-01-24 06:40:52.394781: step: 1580/529, loss: 0.005683989264070988
2023-01-24 06:40:53.458146: step: 1584/529, loss: 0.016850145533680916
2023-01-24 06:40:54.531698: step: 1588/529, loss: 0.005151068791747093
2023-01-24 06:40:55.604290: step: 1592/529, loss: 0.02597479708492756
2023-01-24 06:40:56.665754: step: 1596/529, loss: 0.0303542148321867
2023-01-24 06:40:57.741415: step: 1600/529, loss: 0.02412993647158146
2023-01-24 06:40:58.815598: step: 1604/529, loss: 0.00743184145539999
2023-01-24 06:40:59.886896: step: 1608/529, loss: 0.009544594213366508
2023-01-24 06:41:00.959689: step: 1612/529, loss: 0.015473476611077785
2023-01-24 06:41:02.026222: step: 1616/529, loss: 0.008911818265914917
2023-01-24 06:41:03.088551: step: 1620/529, loss: 0.01670347899198532
2023-01-24 06:41:04.154346: step: 1624/529, loss: 0.002616297686472535
2023-01-24 06:41:05.229310: step: 1628/529, loss: 0.0036034672521054745
2023-01-24 06:41:06.299182: step: 1632/529, loss: 0.006160416640341282
2023-01-24 06:41:07.358997: step: 1636/529, loss: 0.004200714640319347
2023-01-24 06:41:08.424643: step: 1640/529, loss: 0.00981410313397646
2023-01-24 06:41:09.502462: step: 1644/529, loss: 0.004251305479556322
2023-01-24 06:41:10.572789: step: 1648/529, loss: 0.015658719465136528
2023-01-24 06:41:11.648609: step: 1652/529, loss: 0.037121228873729706
2023-01-24 06:41:12.717637: step: 1656/529, loss: 0.09933902323246002
2023-01-24 06:41:13.782659: step: 1660/529, loss: 0.016771141439676285
2023-01-24 06:41:14.858254: step: 1664/529, loss: 0.01599819026887417
2023-01-24 06:41:15.907469: step: 1668/529, loss: 0.0014509749598801136
2023-01-24 06:41:16.968317: step: 1672/529, loss: 0.016085010021924973
2023-01-24 06:41:18.045394: step: 1676/529, loss: 0.025324085727334023
2023-01-24 06:41:19.120455: step: 1680/529, loss: 0.006123365834355354
2023-01-24 06:41:20.186210: step: 1684/529, loss: 0.019563492387533188
2023-01-24 06:41:21.255969: step: 1688/529, loss: 0.0075540728867053986
2023-01-24 06:41:22.339512: step: 1692/529, loss: 0.006424248218536377
2023-01-24 06:41:23.414484: step: 1696/529, loss: 0.007962196134030819
2023-01-24 06:41:24.477050: step: 1700/529, loss: 0.00419227872043848
2023-01-24 06:41:25.542125: step: 1704/529, loss: 0.005730568431317806
2023-01-24 06:41:26.601791: step: 1708/529, loss: 0.006074938923120499
2023-01-24 06:41:27.667763: step: 1712/529, loss: 0.008359881117939949
2023-01-24 06:41:28.717928: step: 1716/529, loss: 0.008949099108576775
2023-01-24 06:41:29.782545: step: 1720/529, loss: 0.0005189424846321344
2023-01-24 06:41:30.864877: step: 1724/529, loss: 0.001241878024302423
2023-01-24 06:41:31.936945: step: 1728/529, loss: 0.023316921666264534
2023-01-24 06:41:33.016771: step: 1732/529, loss: 0.005595780443400145
2023-01-24 06:41:34.087255: step: 1736/529, loss: 0.003928350750356913
2023-01-24 06:41:35.152181: step: 1740/529, loss: 0.025084983557462692
2023-01-24 06:41:36.227823: step: 1744/529, loss: 0.005941771436482668
2023-01-24 06:41:37.301252: step: 1748/529, loss: 0.005050054285675287
2023-01-24 06:41:38.385496: step: 1752/529, loss: 0.03062165156006813
2023-01-24 06:41:39.476156: step: 1756/529, loss: 0.013844349421560764
2023-01-24 06:41:40.541339: step: 1760/529, loss: 0.016237672418355942
2023-01-24 06:41:41.603248: step: 1764/529, loss: 0.004700832534581423
2023-01-24 06:41:42.696139: step: 1768/529, loss: 0.009221207350492477
2023-01-24 06:41:43.765961: step: 1772/529, loss: 0.01399283017963171
2023-01-24 06:41:44.845267: step: 1776/529, loss: 0.000554208701942116
2023-01-24 06:41:45.910507: step: 1780/529, loss: 0.004608966875821352
2023-01-24 06:41:47.001666: step: 1784/529, loss: 0.05405984818935394
2023-01-24 06:41:48.056788: step: 1788/529, loss: 0.00849241204559803
2023-01-24 06:41:49.132484: step: 1792/529, loss: 0.02150285430252552
2023-01-24 06:41:50.206643: step: 1796/529, loss: 0.005432683043181896
2023-01-24 06:41:51.286283: step: 1800/529, loss: 0.0023045307025313377
2023-01-24 06:41:52.362214: step: 1804/529, loss: 2.0657407731050625e-05
2023-01-24 06:41:53.413669: step: 1808/529, loss: 0.0038340457249432802
2023-01-24 06:41:54.494496: step: 1812/529, loss: 0.018187930807471275
2023-01-24 06:41:55.566537: step: 1816/529, loss: 0.012754458002746105
2023-01-24 06:41:56.637921: step: 1820/529, loss: 0.0018092350801452994
2023-01-24 06:41:57.706320: step: 1824/529, loss: 0.006038977764546871
2023-01-24 06:41:58.775729: step: 1828/529, loss: 0.04289066419005394
2023-01-24 06:41:59.850606: step: 1832/529, loss: 0.006066637113690376
2023-01-24 06:42:00.932549: step: 1836/529, loss: 0.019083892926573753
2023-01-24 06:42:02.006330: step: 1840/529, loss: 0.015402274206280708
2023-01-24 06:42:03.077503: step: 1844/529, loss: 0.008550545200705528
2023-01-24 06:42:04.151392: step: 1848/529, loss: 0.006068128161132336
2023-01-24 06:42:05.231271: step: 1852/529, loss: 0.002489842474460602
2023-01-24 06:42:06.318263: step: 1856/529, loss: 0.005711839534342289
2023-01-24 06:42:07.381515: step: 1860/529, loss: 0.011155230924487114
2023-01-24 06:42:08.461183: step: 1864/529, loss: 0.007385375443845987
2023-01-24 06:42:09.561619: step: 1868/529, loss: 0.005201231222599745
2023-01-24 06:42:10.640831: step: 1872/529, loss: 0.013216188177466393
2023-01-24 06:42:11.713854: step: 1876/529, loss: 0.01222376897931099
2023-01-24 06:42:12.785970: step: 1880/529, loss: 0.025436189025640488
2023-01-24 06:42:13.854367: step: 1884/529, loss: 0.004563449416309595
2023-01-24 06:42:14.933627: step: 1888/529, loss: 0.015077211894094944
2023-01-24 06:42:16.007183: step: 1892/529, loss: 0.0257384292781353
2023-01-24 06:42:17.079116: step: 1896/529, loss: 0.0045809973962605
2023-01-24 06:42:18.134863: step: 1900/529, loss: 0.0020767245441675186
2023-01-24 06:42:19.200229: step: 1904/529, loss: 0.009484152309596539
2023-01-24 06:42:20.273867: step: 1908/529, loss: 0.006550249177962542
2023-01-24 06:42:21.348043: step: 1912/529, loss: 0.00044212437933310866
2023-01-24 06:42:22.428812: step: 1916/529, loss: 0.02092244103550911
2023-01-24 06:42:23.490014: step: 1920/529, loss: 0.004801048897206783
2023-01-24 06:42:24.556603: step: 1924/529, loss: 0.003222655039280653
2023-01-24 06:42:25.624277: step: 1928/529, loss: 0.004944137297570705
2023-01-24 06:42:26.693001: step: 1932/529, loss: 0.030959121882915497
2023-01-24 06:42:27.760142: step: 1936/529, loss: 0.0003269213775638491
2023-01-24 06:42:28.853597: step: 1940/529, loss: 0.01522830780595541
2023-01-24 06:42:29.920915: step: 1944/529, loss: 0.003529431065544486
2023-01-24 06:42:30.974002: step: 1948/529, loss: 0.0031008790247142315
2023-01-24 06:42:32.046781: step: 1952/529, loss: 0.013878103345632553
2023-01-24 06:42:33.111280: step: 1956/529, loss: 0.00032939633820205927
2023-01-24 06:42:34.174605: step: 1960/529, loss: 0.00490737147629261
2023-01-24 06:42:35.253327: step: 1964/529, loss: 0.006270409096032381
2023-01-24 06:42:36.337201: step: 1968/529, loss: 0.0027163519989699125
2023-01-24 06:42:37.420695: step: 1972/529, loss: 0.001964374678209424
2023-01-24 06:42:38.495537: step: 1976/529, loss: 0.011277947574853897
2023-01-24 06:42:39.583372: step: 1980/529, loss: 0.03554533049464226
2023-01-24 06:42:40.672084: step: 1984/529, loss: 0.0776987224817276
2023-01-24 06:42:41.748042: step: 1988/529, loss: 0.001686428557150066
2023-01-24 06:42:42.828818: step: 1992/529, loss: 0.004262098576873541
2023-01-24 06:42:43.910002: step: 1996/529, loss: 0.001260052202269435
2023-01-24 06:42:44.962593: step: 2000/529, loss: 0.002083900850266218
2023-01-24 06:42:46.044466: step: 2004/529, loss: 0.022707713767886162
2023-01-24 06:42:47.100067: step: 2008/529, loss: 0.012377276085317135
2023-01-24 06:42:48.179938: step: 2012/529, loss: 0.014637023210525513
2023-01-24 06:42:49.246875: step: 2016/529, loss: 0.007896382361650467
2023-01-24 06:42:50.320388: step: 2020/529, loss: 0.03769185021519661
2023-01-24 06:42:51.396929: step: 2024/529, loss: 0.014995766803622246
2023-01-24 06:42:52.463258: step: 2028/529, loss: 0.01594899408519268
2023-01-24 06:42:53.533503: step: 2032/529, loss: 0.00520738773047924
2023-01-24 06:42:54.604221: step: 2036/529, loss: 0.0034832293167710304
2023-01-24 06:42:55.676287: step: 2040/529, loss: 0.013992756605148315
2023-01-24 06:42:56.754797: step: 2044/529, loss: 0.007770204450935125
2023-01-24 06:42:57.825806: step: 2048/529, loss: 0.000749800237827003
2023-01-24 06:42:58.903482: step: 2052/529, loss: 0.019051600247621536
2023-01-24 06:42:59.983817: step: 2056/529, loss: 0.015893064439296722
2023-01-24 06:43:01.115101: step: 2060/529, loss: 0.07714373618364334
2023-01-24 06:43:02.177515: step: 2064/529, loss: 0.051430750638246536
2023-01-24 06:43:03.249306: step: 2068/529, loss: 0.01454426534473896
2023-01-24 06:43:04.314577: step: 2072/529, loss: 0.029555466026067734
2023-01-24 06:43:05.382581: step: 2076/529, loss: 0.00812841858714819
2023-01-24 06:43:06.448311: step: 2080/529, loss: 0.007017475087195635
2023-01-24 06:43:07.522933: step: 2084/529, loss: 0.005045258905738592
2023-01-24 06:43:08.618993: step: 2088/529, loss: 0.004556868225336075
2023-01-24 06:43:09.692419: step: 2092/529, loss: 0.019676432013511658
2023-01-24 06:43:10.749061: step: 2096/529, loss: 0.0016599795781075954
2023-01-24 06:43:11.814725: step: 2100/529, loss: 0.005418145563453436
2023-01-24 06:43:12.912078: step: 2104/529, loss: 0.006692006718367338
2023-01-24 06:43:13.982136: step: 2108/529, loss: 0.05009535327553749
2023-01-24 06:43:15.055910: step: 2112/529, loss: 0.0026667662896215916
2023-01-24 06:43:16.116915: step: 2116/529, loss: 0.012330101802945137
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3383116306223983, 'r': 0.3010780925273336, 'f1': 0.3186107525339454}, 'combined': 0.23476581765659132, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33624119731958535, 'r': 0.29235677634588947, 'f1': 0.3127671314300175}, 'combined': 0.20418994072633267, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36077669726107225, 'r': 0.3559845969179461, 'f1': 0.35836462765187693}, 'combined': 0.2640581466908567, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3555852251059672, 'r': 0.30852247472429506, 'f1': 0.3303862721457018}, 'combined': 0.21569259217802295, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3763552812491492, 'r': 0.3406479490623229, 'f1': 0.3576124883582553}, 'combined': 0.2635039387902934, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36909167243376845, 'r': 0.3039578478866329, 'f1': 0.33337312348856507}, 'combined': 0.21764255730341553, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3888888888888889, 'r': 0.45652173913043476, 'f1': 0.42}, 'combined': 0.21, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, '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 06:45:49.690879: step: 4/529, loss: 0.0023591865319758654
2023-01-24 06:45:50.756463: step: 8/529, loss: 0.022934990003705025
2023-01-24 06:45:51.823257: step: 12/529, loss: 0.00520970206707716
2023-01-24 06:45:52.877445: step: 16/529, loss: 0.02341693826019764
2023-01-24 06:45:53.944280: step: 20/529, loss: 9.770537144504488e-05
2023-01-24 06:45:55.011835: step: 24/529, loss: 0.00018030313367489725
2023-01-24 06:45:56.073121: step: 28/529, loss: 0.02539955824613571
2023-01-24 06:45:57.144407: step: 32/529, loss: 0.03564148768782616
2023-01-24 06:45:58.205984: step: 36/529, loss: 0.0038195543456822634
2023-01-24 06:45:59.266763: step: 40/529, loss: 0.00010295725223841146
2023-01-24 06:46:00.333666: step: 44/529, loss: 0.010775351896882057
2023-01-24 06:46:01.403857: step: 48/529, loss: 0.00821895431727171
2023-01-24 06:46:02.463012: step: 52/529, loss: 0.01877855509519577
2023-01-24 06:46:03.531834: step: 56/529, loss: 0.005858547519892454
2023-01-24 06:46:04.603992: step: 60/529, loss: 0.0328177772462368
2023-01-24 06:46:05.651059: step: 64/529, loss: 0.014643720351159573
2023-01-24 06:46:06.716034: step: 68/529, loss: 0.032504670321941376
2023-01-24 06:46:07.796649: step: 72/529, loss: 0.006147871259599924
2023-01-24 06:46:08.856254: step: 76/529, loss: 0.0531005933880806
2023-01-24 06:46:09.927280: step: 80/529, loss: 0.031548935920000076
2023-01-24 06:46:11.002148: step: 84/529, loss: 0.007868846878409386
2023-01-24 06:46:12.064096: step: 88/529, loss: 0.005373908672481775
2023-01-24 06:46:13.141687: step: 92/529, loss: 0.009822044521570206
2023-01-24 06:46:14.199081: step: 96/529, loss: 0.004009397700428963
2023-01-24 06:46:15.262622: step: 100/529, loss: 0.003939324989914894
2023-01-24 06:46:16.321630: step: 104/529, loss: 0.030637217685580254
2023-01-24 06:46:17.385363: step: 108/529, loss: 0.001025114906951785
2023-01-24 06:46:18.452828: step: 112/529, loss: 0.007835193537175655
2023-01-24 06:46:19.531177: step: 116/529, loss: 0.011833150871098042
2023-01-24 06:46:20.594202: step: 120/529, loss: 0.03219558671116829
2023-01-24 06:46:21.656673: step: 124/529, loss: 0.0002794024767354131
2023-01-24 06:46:22.738753: step: 128/529, loss: 0.0097324438393116
2023-01-24 06:46:23.808619: step: 132/529, loss: 0.024913547560572624
2023-01-24 06:46:24.875725: step: 136/529, loss: 0.017749769613146782
2023-01-24 06:46:25.945948: step: 140/529, loss: 0.0036395140923559666
2023-01-24 06:46:27.018581: step: 144/529, loss: 0.0023946850560605526
2023-01-24 06:46:28.084582: step: 148/529, loss: 0.03142841160297394
2023-01-24 06:46:29.167265: step: 152/529, loss: 0.007366228383034468
2023-01-24 06:46:30.225854: step: 156/529, loss: 0.007933779619634151
2023-01-24 06:46:31.303095: step: 160/529, loss: 0.028447827324271202
2023-01-24 06:46:32.382850: step: 164/529, loss: 0.0027678715996444225
2023-01-24 06:46:33.455391: step: 168/529, loss: 0.01275789923965931
2023-01-24 06:46:34.527357: step: 172/529, loss: 0.0009689267026260495
2023-01-24 06:46:35.583599: step: 176/529, loss: 0.002439645351842046
2023-01-24 06:46:36.642381: step: 180/529, loss: 0.023513024672865868
2023-01-24 06:46:37.731284: step: 184/529, loss: 0.0024362525437027216
2023-01-24 06:46:38.807111: step: 188/529, loss: 0.001983602764084935
2023-01-24 06:46:39.848309: step: 192/529, loss: 0.00682625500485301
2023-01-24 06:46:40.919087: step: 196/529, loss: 0.004751925822347403
2023-01-24 06:46:42.000304: step: 200/529, loss: 0.0021734184119850397
2023-01-24 06:46:43.078877: step: 204/529, loss: 0.0025329540949314833
2023-01-24 06:46:44.150832: step: 208/529, loss: 0.005129461642354727
2023-01-24 06:46:45.217806: step: 212/529, loss: 0.005169543903321028
2023-01-24 06:46:46.311286: step: 216/529, loss: 0.004711352754384279
2023-01-24 06:46:47.375437: step: 220/529, loss: 0.008054588921368122
2023-01-24 06:46:48.443146: step: 224/529, loss: 0.003451740136370063
2023-01-24 06:46:49.517703: step: 228/529, loss: 0.004340517334640026
2023-01-24 06:46:50.590003: step: 232/529, loss: 0.03223850205540657
2023-01-24 06:46:51.679192: step: 236/529, loss: 0.0011079449905082583
2023-01-24 06:46:52.737674: step: 240/529, loss: 0.0015037362463772297
2023-01-24 06:46:53.812052: step: 244/529, loss: 0.020707331597805023
2023-01-24 06:46:54.870902: step: 248/529, loss: 0.020134232938289642
2023-01-24 06:46:55.955088: step: 252/529, loss: 0.009122924879193306
2023-01-24 06:46:57.035717: step: 256/529, loss: 0.00728244986385107
2023-01-24 06:46:58.148913: step: 260/529, loss: 0.0028491420671343803
2023-01-24 06:46:59.202054: step: 264/529, loss: 0.000450416118837893
2023-01-24 06:47:00.281715: step: 268/529, loss: 0.007179692853242159
2023-01-24 06:47:01.381439: step: 272/529, loss: 0.01157737709581852
2023-01-24 06:47:02.441304: step: 276/529, loss: 0.0009326613508164883
2023-01-24 06:47:03.511470: step: 280/529, loss: 0.01036171056330204
2023-01-24 06:47:04.604576: step: 284/529, loss: 0.09236515313386917
2023-01-24 06:47:05.686423: step: 288/529, loss: 0.013139292597770691
2023-01-24 06:47:06.765900: step: 292/529, loss: 0.014926465228199959
2023-01-24 06:47:07.851297: step: 296/529, loss: 0.0029992233030498028
2023-01-24 06:47:08.932079: step: 300/529, loss: 0.0025662067346274853
2023-01-24 06:47:10.024039: step: 304/529, loss: 0.005319194868206978
2023-01-24 06:47:11.101352: step: 308/529, loss: 0.01083306223154068
2023-01-24 06:47:12.186249: step: 312/529, loss: 0.003545610001310706
2023-01-24 06:47:13.256881: step: 316/529, loss: 0.01508993562310934
2023-01-24 06:47:14.325689: step: 320/529, loss: 0.006574643775820732
2023-01-24 06:47:15.414172: step: 324/529, loss: 0.02904742956161499
2023-01-24 06:47:16.485386: step: 328/529, loss: 0.0019047949463129044
2023-01-24 06:47:17.575944: step: 332/529, loss: 0.005265311803668737
2023-01-24 06:47:18.650767: step: 336/529, loss: 0.003619307419285178
2023-01-24 06:47:19.734298: step: 340/529, loss: 0.016096679493784904
2023-01-24 06:47:20.793818: step: 344/529, loss: 0.021636826917529106
2023-01-24 06:47:21.871743: step: 348/529, loss: 0.007235253229737282
2023-01-24 06:47:22.944218: step: 352/529, loss: 0.015154299326241016
2023-01-24 06:47:24.031556: step: 356/529, loss: 0.006073358468711376
2023-01-24 06:47:25.115044: step: 360/529, loss: 0.008909916505217552
2023-01-24 06:47:26.190103: step: 364/529, loss: 0.007834630087018013
2023-01-24 06:47:27.267071: step: 368/529, loss: 2.194949956901837e-06
2023-01-24 06:47:28.342842: step: 372/529, loss: 0.007482160814106464
2023-01-24 06:47:29.423509: step: 376/529, loss: 0.030774014070630074
2023-01-24 06:47:30.511683: step: 380/529, loss: 0.007288197986781597
2023-01-24 06:47:31.601294: step: 384/529, loss: 0.012908224016427994
2023-01-24 06:47:32.685024: step: 388/529, loss: 0.01493560429662466
2023-01-24 06:47:33.751869: step: 392/529, loss: 0.000726421712897718
2023-01-24 06:47:34.825196: step: 396/529, loss: 0.0035562561824917793
2023-01-24 06:47:35.905120: step: 400/529, loss: 0.006127411033958197
2023-01-24 06:47:36.997948: step: 404/529, loss: 0.0435500368475914
2023-01-24 06:47:38.077492: step: 408/529, loss: 0.012825858779251575
2023-01-24 06:47:39.166027: step: 412/529, loss: 0.006627162452787161
2023-01-24 06:47:40.247207: step: 416/529, loss: 0.00868252944201231
2023-01-24 06:47:41.323215: step: 420/529, loss: 0.004846430849283934
2023-01-24 06:47:42.419948: step: 424/529, loss: 0.03135371580719948
2023-01-24 06:47:43.512517: step: 428/529, loss: 0.024940218776464462
2023-01-24 06:47:44.592537: step: 432/529, loss: 0.0085542481392622
2023-01-24 06:47:45.669378: step: 436/529, loss: 0.009447372518479824
2023-01-24 06:47:46.750660: step: 440/529, loss: 0.0028872983530163765
2023-01-24 06:47:47.854243: step: 444/529, loss: 0.01761099323630333
2023-01-24 06:47:48.928645: step: 448/529, loss: 0.009838612750172615
2023-01-24 06:47:50.005954: step: 452/529, loss: 0.0074104429222643375
2023-01-24 06:47:51.095927: step: 456/529, loss: 0.026121564209461212
2023-01-24 06:47:52.168615: step: 460/529, loss: 0.003765722969546914
2023-01-24 06:47:53.244865: step: 464/529, loss: 0.005026004742830992
2023-01-24 06:47:54.322050: step: 468/529, loss: 0.019378002732992172
2023-01-24 06:47:55.421194: step: 472/529, loss: 0.007816677913069725
2023-01-24 06:47:56.507110: step: 476/529, loss: 0.008424460887908936
2023-01-24 06:47:57.591443: step: 480/529, loss: 0.0035309477243572474
2023-01-24 06:47:58.660716: step: 484/529, loss: 0.013482525013387203
2023-01-24 06:47:59.738236: step: 488/529, loss: 0.003127522999420762
2023-01-24 06:48:00.816233: step: 492/529, loss: 0.007443585433065891
2023-01-24 06:48:01.893903: step: 496/529, loss: 0.0033241277560591698
2023-01-24 06:48:02.977664: step: 500/529, loss: 0.005822707433253527
2023-01-24 06:48:04.057895: step: 504/529, loss: 0.00861866120249033
2023-01-24 06:48:05.140939: step: 508/529, loss: 0.030997419729828835
2023-01-24 06:48:06.225231: step: 512/529, loss: 0.012883225455880165
2023-01-24 06:48:07.313434: step: 516/529, loss: 0.026715340092778206
2023-01-24 06:48:08.412708: step: 520/529, loss: 0.01364895235747099
2023-01-24 06:48:09.495041: step: 524/529, loss: 0.0031265225261449814
2023-01-24 06:48:10.582717: step: 528/529, loss: 0.0015215002931654453
2023-01-24 06:48:11.678263: step: 532/529, loss: 0.007553800940513611
2023-01-24 06:48:12.770713: step: 536/529, loss: 0.012286574579775333
2023-01-24 06:48:13.857044: step: 540/529, loss: 0.007760470267385244
2023-01-24 06:48:14.930519: step: 544/529, loss: 0.004370789974927902
2023-01-24 06:48:16.001693: step: 548/529, loss: 0.014047746546566486
2023-01-24 06:48:17.102239: step: 552/529, loss: 0.019543102011084557
2023-01-24 06:48:18.188810: step: 556/529, loss: 0.0006572658894583583
2023-01-24 06:48:19.268599: step: 560/529, loss: 0.009009703062474728
2023-01-24 06:48:20.351346: step: 564/529, loss: 0.0008789764251559973
2023-01-24 06:48:21.438087: step: 568/529, loss: 0.036441605538129807
2023-01-24 06:48:22.512655: step: 572/529, loss: 0.00891857873648405
2023-01-24 06:48:23.608230: step: 576/529, loss: 0.012162557803094387
2023-01-24 06:48:24.676674: step: 580/529, loss: 0.003688802244141698
2023-01-24 06:48:25.753915: step: 584/529, loss: 0.006818746216595173
2023-01-24 06:48:26.835236: step: 588/529, loss: 0.003726058639585972
2023-01-24 06:48:27.949186: step: 592/529, loss: 0.007386893033981323
2023-01-24 06:48:29.034338: step: 596/529, loss: 0.0018032968509942293
2023-01-24 06:48:30.106522: step: 600/529, loss: 0.0017450537998229265
2023-01-24 06:48:31.178082: step: 604/529, loss: 0.013055171817541122
2023-01-24 06:48:32.257878: step: 608/529, loss: 0.0046906559728085995
2023-01-24 06:48:33.332639: step: 612/529, loss: 0.0012650399003177881
2023-01-24 06:48:34.418852: step: 616/529, loss: 0.03179369494318962
2023-01-24 06:48:35.485399: step: 620/529, loss: 0.005403509363532066
2023-01-24 06:48:36.572672: step: 624/529, loss: 0.008115163072943687
2023-01-24 06:48:37.670789: step: 628/529, loss: 0.005907402839511633
2023-01-24 06:48:38.769536: step: 632/529, loss: 0.007011353969573975
2023-01-24 06:48:39.850707: step: 636/529, loss: 0.0007654178771190345
2023-01-24 06:48:40.939366: step: 640/529, loss: 0.014596791937947273
2023-01-24 06:48:42.035503: step: 644/529, loss: 0.01081467792391777
2023-01-24 06:48:43.129224: step: 648/529, loss: 0.012734362855553627
2023-01-24 06:48:44.206956: step: 652/529, loss: 0.008981704711914062
2023-01-24 06:48:45.295302: step: 656/529, loss: 0.0048651322722435
2023-01-24 06:48:46.372082: step: 660/529, loss: 0.0018407233292236924
2023-01-24 06:48:47.445984: step: 664/529, loss: 0.0213095024228096
2023-01-24 06:48:48.512760: step: 668/529, loss: 0.02741035260260105
2023-01-24 06:48:49.608373: step: 672/529, loss: 0.016823599115014076
2023-01-24 06:48:50.688474: step: 676/529, loss: 0.020916426554322243
2023-01-24 06:48:51.789188: step: 680/529, loss: 0.007137995678931475
2023-01-24 06:48:52.865356: step: 684/529, loss: 0.005267574451863766
2023-01-24 06:48:53.952461: step: 688/529, loss: 0.0027815639041364193
2023-01-24 06:48:55.022351: step: 692/529, loss: 0.0036561554297804832
2023-01-24 06:48:56.093354: step: 696/529, loss: 0.007523233070969582
2023-01-24 06:48:57.176337: step: 700/529, loss: 0.0038603900466114283
2023-01-24 06:48:58.259021: step: 704/529, loss: 0.024964014068245888
2023-01-24 06:48:59.350232: step: 708/529, loss: 0.002301727421581745
2023-01-24 06:49:00.436412: step: 712/529, loss: 0.013016752898693085
2023-01-24 06:49:01.509565: step: 716/529, loss: 0.03989667445421219
2023-01-24 06:49:02.598219: step: 720/529, loss: 0.014000875875353813
2023-01-24 06:49:03.686713: step: 724/529, loss: 0.014962454326450825
2023-01-24 06:49:04.777107: step: 728/529, loss: 0.025587832555174828
2023-01-24 06:49:05.843437: step: 732/529, loss: 0.012081263586878777
2023-01-24 06:49:06.930362: step: 736/529, loss: 0.014643527567386627
2023-01-24 06:49:08.010853: step: 740/529, loss: 0.0076567307114601135
2023-01-24 06:49:09.093338: step: 744/529, loss: 0.010932404547929764
2023-01-24 06:49:10.165473: step: 748/529, loss: 0.006697780452668667
2023-01-24 06:49:11.253133: step: 752/529, loss: 0.034995365887880325
2023-01-24 06:49:12.326718: step: 756/529, loss: 0.007777332328259945
2023-01-24 06:49:13.400191: step: 760/529, loss: 0.004732560832053423
2023-01-24 06:49:14.485640: step: 764/529, loss: 0.005508625414222479
2023-01-24 06:49:15.577008: step: 768/529, loss: 0.00552033819258213
2023-01-24 06:49:16.654644: step: 772/529, loss: 0.01584731601178646
2023-01-24 06:49:17.740607: step: 776/529, loss: 0.005111855920404196
2023-01-24 06:49:18.830805: step: 780/529, loss: 0.007852288894355297
2023-01-24 06:49:19.898970: step: 784/529, loss: 0.0010208550374954939
2023-01-24 06:49:20.972411: step: 788/529, loss: 0.0024359177332371473
2023-01-24 06:49:22.049512: step: 792/529, loss: 0.009936979971826077
2023-01-24 06:49:23.120868: step: 796/529, loss: 0.004408544860780239
2023-01-24 06:49:24.199174: step: 800/529, loss: 0.05775133892893791
2023-01-24 06:49:25.274354: step: 804/529, loss: 0.0019695491064339876
2023-01-24 06:49:26.362197: step: 808/529, loss: 0.00781511515378952
2023-01-24 06:49:27.431997: step: 812/529, loss: 0.0046793632209300995
2023-01-24 06:49:28.489660: step: 816/529, loss: 0.0
2023-01-24 06:49:29.581648: step: 820/529, loss: 0.008469846099615097
2023-01-24 06:49:30.661184: step: 824/529, loss: 0.00775155471637845
2023-01-24 06:49:31.740528: step: 828/529, loss: 0.009959186427295208
2023-01-24 06:49:32.809605: step: 832/529, loss: 0.01913496106863022
2023-01-24 06:49:33.888889: step: 836/529, loss: 0.00519212894141674
2023-01-24 06:49:34.957238: step: 840/529, loss: 0.0020829234272241592
2023-01-24 06:49:36.040332: step: 844/529, loss: 0.006178383715450764
2023-01-24 06:49:37.114598: step: 848/529, loss: 0.16761167347431183
2023-01-24 06:49:38.179066: step: 852/529, loss: 0.014773697592318058
2023-01-24 06:49:39.247398: step: 856/529, loss: 0.0010599122615531087
2023-01-24 06:49:40.319748: step: 860/529, loss: 0.011026586405932903
2023-01-24 06:49:41.402040: step: 864/529, loss: 0.014187859371304512
2023-01-24 06:49:42.483306: step: 868/529, loss: 0.004979118704795837
2023-01-24 06:49:43.594488: step: 872/529, loss: 0.005366618279367685
2023-01-24 06:49:44.672165: step: 876/529, loss: 0.00425998168066144
2023-01-24 06:49:45.726833: step: 880/529, loss: 0.0014896979555487633
2023-01-24 06:49:46.797409: step: 884/529, loss: 0.002451414940878749
2023-01-24 06:49:47.899289: step: 888/529, loss: 0.0630563497543335
2023-01-24 06:49:48.971815: step: 892/529, loss: 0.002949623391032219
2023-01-24 06:49:50.052843: step: 896/529, loss: 0.00682945316657424
2023-01-24 06:49:51.124866: step: 900/529, loss: 0.00905640795826912
2023-01-24 06:49:52.207708: step: 904/529, loss: 0.006573675200343132
2023-01-24 06:49:53.294428: step: 908/529, loss: 0.01280137151479721
2023-01-24 06:49:54.369468: step: 912/529, loss: 0.006114022806286812
2023-01-24 06:49:55.424173: step: 916/529, loss: 0.006355506833642721
2023-01-24 06:49:56.509421: step: 920/529, loss: 0.0063613951206207275
2023-01-24 06:49:57.570517: step: 924/529, loss: 0.005754409357905388
2023-01-24 06:49:58.651852: step: 928/529, loss: 0.028570882976055145
2023-01-24 06:49:59.725176: step: 932/529, loss: 0.00022434037236962467
2023-01-24 06:50:00.790056: step: 936/529, loss: 0.020676080137491226
2023-01-24 06:50:01.861221: step: 940/529, loss: 0.004602524451911449
2023-01-24 06:50:02.951395: step: 944/529, loss: 0.009075782261788845
2023-01-24 06:50:04.017851: step: 948/529, loss: 0.007831712253391743
2023-01-24 06:50:05.103284: step: 952/529, loss: 0.006078928709030151
2023-01-24 06:50:06.196384: step: 956/529, loss: 0.003775586374104023
2023-01-24 06:50:07.291477: step: 960/529, loss: 0.01066896878182888
2023-01-24 06:50:08.372349: step: 964/529, loss: 0.007163495756685734
2023-01-24 06:50:09.434214: step: 968/529, loss: 0.015286673791706562
2023-01-24 06:50:10.505203: step: 972/529, loss: 0.0055341958068311214
2023-01-24 06:50:11.575024: step: 976/529, loss: 0.004220864269882441
2023-01-24 06:50:12.664242: step: 980/529, loss: 0.04802757129073143
2023-01-24 06:50:13.732519: step: 984/529, loss: 0.008909719064831734
2023-01-24 06:50:14.795035: step: 988/529, loss: 0.016143960878252983
2023-01-24 06:50:15.871880: step: 992/529, loss: 0.002123722108080983
2023-01-24 06:50:16.943911: step: 996/529, loss: 0.06090731918811798
2023-01-24 06:50:18.013541: step: 1000/529, loss: 0.03460565209388733
2023-01-24 06:50:19.065696: step: 1004/529, loss: 0.003564713755622506
2023-01-24 06:50:20.140846: step: 1008/529, loss: 0.003454942721873522
2023-01-24 06:50:21.210180: step: 1012/529, loss: 0.006876189727336168
2023-01-24 06:50:22.279721: step: 1016/529, loss: 0.020064184442162514
2023-01-24 06:50:23.372296: step: 1020/529, loss: 0.041294246912002563
2023-01-24 06:50:24.437942: step: 1024/529, loss: 0.0030531559605151415
2023-01-24 06:50:25.498413: step: 1028/529, loss: 0.005201972089707851
2023-01-24 06:50:26.592872: step: 1032/529, loss: 0.013871893286705017
2023-01-24 06:50:27.645332: step: 1036/529, loss: 0.016921035945415497
2023-01-24 06:50:28.715715: step: 1040/529, loss: 0.00787028856575489
2023-01-24 06:50:29.804462: step: 1044/529, loss: 0.013744481839239597
2023-01-24 06:50:30.872347: step: 1048/529, loss: 0.0007722425507381558
2023-01-24 06:50:31.958684: step: 1052/529, loss: 0.00881260633468628
2023-01-24 06:50:33.035375: step: 1056/529, loss: 0.007405300159007311
2023-01-24 06:50:34.097347: step: 1060/529, loss: 0.01694301888346672
2023-01-24 06:50:35.167330: step: 1064/529, loss: 0.014890308491885662
2023-01-24 06:50:36.250311: step: 1068/529, loss: 0.008977736346423626
2023-01-24 06:50:37.321346: step: 1072/529, loss: 0.007859176956117153
2023-01-24 06:50:38.374797: step: 1076/529, loss: 0.0032545970752835274
2023-01-24 06:50:39.445745: step: 1080/529, loss: 0.0027104350738227367
2023-01-24 06:50:40.507301: step: 1084/529, loss: 0.00029562684358097613
2023-01-24 06:50:41.625959: step: 1088/529, loss: 0.027976777404546738
2023-01-24 06:50:42.699791: step: 1092/529, loss: 0.0002920544648077339
2023-01-24 06:50:43.765874: step: 1096/529, loss: 0.005539219360798597
2023-01-24 06:50:44.829266: step: 1100/529, loss: 0.017816459760069847
2023-01-24 06:50:45.897222: step: 1104/529, loss: 0.02801329828798771
2023-01-24 06:50:46.959512: step: 1108/529, loss: 0.037525489926338196
2023-01-24 06:50:48.034734: step: 1112/529, loss: 0.007232323754578829
2023-01-24 06:50:49.099087: step: 1116/529, loss: 0.03849571943283081
2023-01-24 06:50:50.182025: step: 1120/529, loss: 0.004483949393033981
2023-01-24 06:50:51.240798: step: 1124/529, loss: 0.0031455166172236204
2023-01-24 06:50:52.305439: step: 1128/529, loss: 0.01355654001235962
2023-01-24 06:50:53.382366: step: 1132/529, loss: 0.0014939901884645224
2023-01-24 06:50:54.467835: step: 1136/529, loss: 0.006358602549880743
2023-01-24 06:50:55.552126: step: 1140/529, loss: 0.010074728168547153
2023-01-24 06:50:56.626426: step: 1144/529, loss: 0.0
2023-01-24 06:50:57.692104: step: 1148/529, loss: 0.004920216277241707
2023-01-24 06:50:58.779064: step: 1152/529, loss: 0.007155633065849543
2023-01-24 06:50:59.840770: step: 1156/529, loss: 0.07974962890148163
2023-01-24 06:51:00.929125: step: 1160/529, loss: 0.0029482811223715544
2023-01-24 06:51:01.993072: step: 1164/529, loss: 0.01466186624020338
2023-01-24 06:51:03.083614: step: 1168/529, loss: 0.011331798508763313
2023-01-24 06:51:04.178600: step: 1172/529, loss: 0.02274644747376442
2023-01-24 06:51:05.258415: step: 1176/529, loss: 0.013689613901078701
2023-01-24 06:51:06.337412: step: 1180/529, loss: 0.03239350765943527
2023-01-24 06:51:07.405857: step: 1184/529, loss: 0.004444632213562727
2023-01-24 06:51:08.461693: step: 1188/529, loss: 0.004769716411828995
2023-01-24 06:51:09.518904: step: 1192/529, loss: 0.0013277638936415315
2023-01-24 06:51:10.578747: step: 1196/529, loss: 0.05235392972826958
2023-01-24 06:51:11.655261: step: 1200/529, loss: 0.024671632796525955
2023-01-24 06:51:12.723744: step: 1204/529, loss: 0.0057119401171803474
2023-01-24 06:51:13.824462: step: 1208/529, loss: 0.0023117177188396454
2023-01-24 06:51:14.888896: step: 1212/529, loss: 0.006331521086394787
2023-01-24 06:51:15.946112: step: 1216/529, loss: 0.01428559236228466
2023-01-24 06:51:17.021093: step: 1220/529, loss: 0.0023710555396974087
2023-01-24 06:51:18.084719: step: 1224/529, loss: 0.004345199093222618
2023-01-24 06:51:19.170573: step: 1228/529, loss: 0.019951367750763893
2023-01-24 06:51:20.238813: step: 1232/529, loss: 0.007890959270298481
2023-01-24 06:51:21.296334: step: 1236/529, loss: 0.07620669901371002
2023-01-24 06:51:22.367684: step: 1240/529, loss: 0.0011335468152537942
2023-01-24 06:51:23.425821: step: 1244/529, loss: 0.009308500215411186
2023-01-24 06:51:24.514312: step: 1248/529, loss: 0.004264793824404478
2023-01-24 06:51:25.580178: step: 1252/529, loss: 0.006576917599886656
2023-01-24 06:51:26.659090: step: 1256/529, loss: 0.013798649422824383
2023-01-24 06:51:27.728735: step: 1260/529, loss: 0.009273541159927845
2023-01-24 06:51:28.790713: step: 1264/529, loss: 0.0014964672736823559
2023-01-24 06:51:29.848000: step: 1268/529, loss: 0.04203373193740845
2023-01-24 06:51:30.916519: step: 1272/529, loss: 0.0029081483371555805
2023-01-24 06:51:31.992286: step: 1276/529, loss: 0.01879449561238289
2023-01-24 06:51:33.054005: step: 1280/529, loss: 0.013544732704758644
2023-01-24 06:51:34.135691: step: 1284/529, loss: 0.005477940663695335
2023-01-24 06:51:35.214700: step: 1288/529, loss: 0.018900319933891296
2023-01-24 06:51:36.266029: step: 1292/529, loss: 0.023639418184757233
2023-01-24 06:51:37.334917: step: 1296/529, loss: 0.007221922278404236
2023-01-24 06:51:38.405364: step: 1300/529, loss: 0.009306453168392181
2023-01-24 06:51:39.484889: step: 1304/529, loss: 0.0028487478848546743
2023-01-24 06:51:40.561233: step: 1308/529, loss: 0.012331938371062279
2023-01-24 06:51:41.635938: step: 1312/529, loss: 0.013492444530129433
2023-01-24 06:51:42.689958: step: 1316/529, loss: 0.0
2023-01-24 06:51:43.766245: step: 1320/529, loss: 0.002121965866535902
2023-01-24 06:51:44.850870: step: 1324/529, loss: 0.004902695305645466
2023-01-24 06:51:45.924120: step: 1328/529, loss: 0.025261392816901207
2023-01-24 06:51:47.012599: step: 1332/529, loss: 0.004776181653141975
2023-01-24 06:51:48.097665: step: 1336/529, loss: 0.017266785725951195
2023-01-24 06:51:49.189029: step: 1340/529, loss: 0.012460139580070972
2023-01-24 06:51:50.266922: step: 1344/529, loss: 0.008990156464278698
2023-01-24 06:51:51.358975: step: 1348/529, loss: 0.04393523931503296
2023-01-24 06:51:52.427439: step: 1352/529, loss: 0.010298765264451504
2023-01-24 06:51:53.526853: step: 1356/529, loss: 0.0396031029522419
2023-01-24 06:51:54.615055: step: 1360/529, loss: 0.03492884337902069
2023-01-24 06:51:55.701246: step: 1364/529, loss: 0.009422865696251392
2023-01-24 06:51:56.774582: step: 1368/529, loss: 0.005993964616209269
2023-01-24 06:51:57.838774: step: 1372/529, loss: 0.010289964266121387
2023-01-24 06:51:58.925413: step: 1376/529, loss: 0.02454109489917755
2023-01-24 06:52:00.007037: step: 1380/529, loss: 0.003755053738132119
2023-01-24 06:52:01.075743: step: 1384/529, loss: 0.005654075648635626
2023-01-24 06:52:02.180216: step: 1388/529, loss: 0.02863590605556965
2023-01-24 06:52:03.250582: step: 1392/529, loss: 0.0035188167821615934
2023-01-24 06:52:04.321917: step: 1396/529, loss: 0.005578240845352411
2023-01-24 06:52:05.397521: step: 1400/529, loss: 0.009057060815393925
2023-01-24 06:52:06.473426: step: 1404/529, loss: 0.005759712308645248
2023-01-24 06:52:07.537988: step: 1408/529, loss: 0.003830369096249342
2023-01-24 06:52:08.609015: step: 1412/529, loss: 0.040804117918014526
2023-01-24 06:52:09.694609: step: 1416/529, loss: 0.004583555273711681
2023-01-24 06:52:10.778296: step: 1420/529, loss: 0.03579489514231682
2023-01-24 06:52:11.841680: step: 1424/529, loss: 0.008261672221124172
2023-01-24 06:52:12.933102: step: 1428/529, loss: 0.00042252615094184875
2023-01-24 06:52:14.004531: step: 1432/529, loss: 0.005859615281224251
2023-01-24 06:52:15.068046: step: 1436/529, loss: 0.00278661772608757
2023-01-24 06:52:16.128533: step: 1440/529, loss: 0.017631590366363525
2023-01-24 06:52:17.211519: step: 1444/529, loss: 0.004680880811065435
2023-01-24 06:52:18.278102: step: 1448/529, loss: 0.010311641730368137
2023-01-24 06:52:19.342937: step: 1452/529, loss: 0.021048827096819878
2023-01-24 06:52:20.412267: step: 1456/529, loss: 0.010116723366081715
2023-01-24 06:52:21.477187: step: 1460/529, loss: 0.03891179710626602
2023-01-24 06:52:22.544912: step: 1464/529, loss: 0.0024544892366975546
2023-01-24 06:52:23.614573: step: 1468/529, loss: 0.009924131445586681
2023-01-24 06:52:24.687092: step: 1472/529, loss: 0.00858625303953886
2023-01-24 06:52:25.768931: step: 1476/529, loss: 0.0024726493284106255
2023-01-24 06:52:26.839636: step: 1480/529, loss: 0.0013446114026010036
2023-01-24 06:52:27.906092: step: 1484/529, loss: 0.004836790729314089
2023-01-24 06:52:28.974767: step: 1488/529, loss: 0.006040053442120552
2023-01-24 06:52:30.057676: step: 1492/529, loss: 0.04293355718255043
2023-01-24 06:52:31.128562: step: 1496/529, loss: 0.008027631789445877
2023-01-24 06:52:32.199362: step: 1500/529, loss: 0.003630795981734991
2023-01-24 06:52:33.268508: step: 1504/529, loss: 0.032587241381406784
2023-01-24 06:52:34.332589: step: 1508/529, loss: 0.0020075689535588026
2023-01-24 06:52:35.411567: step: 1512/529, loss: 0.022222377359867096
2023-01-24 06:52:36.492585: step: 1516/529, loss: 0.0221629049628973
2023-01-24 06:52:37.565046: step: 1520/529, loss: 0.02755477838218212
2023-01-24 06:52:38.638263: step: 1524/529, loss: 0.00889334175735712
2023-01-24 06:52:39.722910: step: 1528/529, loss: 0.026414886116981506
2023-01-24 06:52:40.777251: step: 1532/529, loss: 0.0030905883759260178
2023-01-24 06:52:41.836322: step: 1536/529, loss: 0.0008331799763254821
2023-01-24 06:52:42.932981: step: 1540/529, loss: 0.012762368656694889
2023-01-24 06:52:44.015532: step: 1544/529, loss: 0.013532751239836216
2023-01-24 06:52:45.082779: step: 1548/529, loss: 0.004549093544483185
2023-01-24 06:52:46.181119: step: 1552/529, loss: 0.005234023090451956
2023-01-24 06:52:47.272265: step: 1556/529, loss: 0.006097541190683842
2023-01-24 06:52:48.359844: step: 1560/529, loss: 0.01614624634385109
2023-01-24 06:52:49.432253: step: 1564/529, loss: 0.021045619621872902
2023-01-24 06:52:50.499136: step: 1568/529, loss: 0.007534326054155827
2023-01-24 06:52:51.563888: step: 1572/529, loss: 0.02432713471353054
2023-01-24 06:52:52.627533: step: 1576/529, loss: 0.0026261243037879467
2023-01-24 06:52:53.717401: step: 1580/529, loss: 0.04308377951383591
2023-01-24 06:52:54.793333: step: 1584/529, loss: 0.010176918469369411
2023-01-24 06:52:55.854505: step: 1588/529, loss: 0.005328764673322439
2023-01-24 06:52:56.924297: step: 1592/529, loss: 0.07903500646352768
2023-01-24 06:52:58.001867: step: 1596/529, loss: 0.004221309907734394
2023-01-24 06:52:59.089076: step: 1600/529, loss: 0.015687737613916397
2023-01-24 06:53:00.165764: step: 1604/529, loss: 0.00549752963706851
2023-01-24 06:53:01.229419: step: 1608/529, loss: 0.011800880543887615
2023-01-24 06:53:02.319738: step: 1612/529, loss: 0.027584398165345192
2023-01-24 06:53:03.379458: step: 1616/529, loss: 0.013747325167059898
2023-01-24 06:53:04.459260: step: 1620/529, loss: 0.037530671805143356
2023-01-24 06:53:05.539688: step: 1624/529, loss: 0.005068168509751558
2023-01-24 06:53:06.621369: step: 1628/529, loss: 0.006172776222229004
2023-01-24 06:53:07.688901: step: 1632/529, loss: 0.007974918000400066
2023-01-24 06:53:08.743958: step: 1636/529, loss: 0.006738297641277313
2023-01-24 06:53:09.806773: step: 1640/529, loss: 0.0034984492231160402
2023-01-24 06:53:10.868772: step: 1644/529, loss: 0.014918613247573376
2023-01-24 06:53:11.949764: step: 1648/529, loss: 0.006512226536870003
2023-01-24 06:53:12.999167: step: 1652/529, loss: 0.00737723708152771
2023-01-24 06:53:14.075236: step: 1656/529, loss: 0.0573233962059021
2023-01-24 06:53:15.133878: step: 1660/529, loss: 0.0069577330723404884
2023-01-24 06:53:16.191369: step: 1664/529, loss: 0.019377263262867928
2023-01-24 06:53:17.274010: step: 1668/529, loss: 0.03078649938106537
2023-01-24 06:53:18.341214: step: 1672/529, loss: 0.003216062905266881
2023-01-24 06:53:19.419966: step: 1676/529, loss: 0.0037748897448182106
2023-01-24 06:53:20.472569: step: 1680/529, loss: 0.002429459011182189
2023-01-24 06:53:21.551566: step: 1684/529, loss: 0.004633056931197643
2023-01-24 06:53:22.622017: step: 1688/529, loss: 0.030605506151914597
2023-01-24 06:53:23.723358: step: 1692/529, loss: 0.016295254230499268
2023-01-24 06:53:24.797496: step: 1696/529, loss: 0.01034608669579029
2023-01-24 06:53:25.878449: step: 1700/529, loss: 0.004735305439680815
2023-01-24 06:53:26.966213: step: 1704/529, loss: 0.015845278277993202
2023-01-24 06:53:28.040906: step: 1708/529, loss: 0.007071654312312603
2023-01-24 06:53:29.106285: step: 1712/529, loss: 0.004461943171918392
2023-01-24 06:53:30.186874: step: 1716/529, loss: 0.03569343313574791
2023-01-24 06:53:31.280584: step: 1720/529, loss: 0.01444600522518158
2023-01-24 06:53:32.363906: step: 1724/529, loss: 0.010641595348715782
2023-01-24 06:53:33.435147: step: 1728/529, loss: 0.008447544649243355
2023-01-24 06:53:34.526251: step: 1732/529, loss: 0.0072909072041511536
2023-01-24 06:53:35.603768: step: 1736/529, loss: 0.002131541259586811
2023-01-24 06:53:36.682081: step: 1740/529, loss: 0.02337382733821869
2023-01-24 06:53:37.777154: step: 1744/529, loss: 0.012673169374465942
2023-01-24 06:53:38.856427: step: 1748/529, loss: 0.00959248747676611
2023-01-24 06:53:39.938818: step: 1752/529, loss: 0.026055578142404556
2023-01-24 06:53:41.002537: step: 1756/529, loss: 0.01532035693526268
2023-01-24 06:53:42.059254: step: 1760/529, loss: 0.0015387131134048104
2023-01-24 06:53:43.124190: step: 1764/529, loss: 0.0063927313312888145
2023-01-24 06:53:44.203802: step: 1768/529, loss: 0.025243641808629036
2023-01-24 06:53:45.278100: step: 1772/529, loss: 0.003757145255804062
2023-01-24 06:53:46.354369: step: 1776/529, loss: 0.0054232217371463776
2023-01-24 06:53:47.413546: step: 1780/529, loss: 0.007150574587285519
2023-01-24 06:53:48.488359: step: 1784/529, loss: 0.006214563734829426
2023-01-24 06:53:49.546807: step: 1788/529, loss: 0.003573064459487796
2023-01-24 06:53:50.608071: step: 1792/529, loss: 0.01645597256720066
2023-01-24 06:53:51.669914: step: 1796/529, loss: 0.009686240926384926
2023-01-24 06:53:52.732434: step: 1800/529, loss: 0.013272601179778576
2023-01-24 06:53:53.789216: step: 1804/529, loss: 0.026154495775699615
2023-01-24 06:53:54.866882: step: 1808/529, loss: 0.003204566426575184
2023-01-24 06:53:55.949266: step: 1812/529, loss: 0.014051277190446854
2023-01-24 06:53:57.010239: step: 1816/529, loss: 0.0031279672402888536
2023-01-24 06:53:58.078863: step: 1820/529, loss: 0.006006308831274509
2023-01-24 06:53:59.157335: step: 1824/529, loss: 0.008006137795746326
2023-01-24 06:54:00.231661: step: 1828/529, loss: 0.03570302203297615
2023-01-24 06:54:01.316707: step: 1832/529, loss: 0.008539380505681038
2023-01-24 06:54:02.369100: step: 1836/529, loss: 0.01007886417210102
2023-01-24 06:54:03.430156: step: 1840/529, loss: 0.0075442977249622345
2023-01-24 06:54:04.489599: step: 1844/529, loss: 0.0066248951479792595
2023-01-24 06:54:05.546387: step: 1848/529, loss: 0.0005288355168886483
2023-01-24 06:54:06.619596: step: 1852/529, loss: 0.0009223928791470826
2023-01-24 06:54:07.689641: step: 1856/529, loss: 0.012264363467693329
2023-01-24 06:54:08.774908: step: 1860/529, loss: 0.02287827990949154
2023-01-24 06:54:09.840825: step: 1864/529, loss: 0.017279639840126038
2023-01-24 06:54:10.900410: step: 1868/529, loss: 0.018276898190379143
2023-01-24 06:54:11.956413: step: 1872/529, loss: 0.005971214268356562
2023-01-24 06:54:13.023914: step: 1876/529, loss: 0.01321127824485302
2023-01-24 06:54:14.092954: step: 1880/529, loss: 0.021702038124203682
2023-01-24 06:54:15.168048: step: 1884/529, loss: 0.014448175206780434
2023-01-24 06:54:16.244921: step: 1888/529, loss: 0.010672574862837791
2023-01-24 06:54:17.313228: step: 1892/529, loss: 0.006881430745124817
2023-01-24 06:54:18.369825: step: 1896/529, loss: 0.01842563971877098
2023-01-24 06:54:19.439708: step: 1900/529, loss: 0.00330442120321095
2023-01-24 06:54:20.500209: step: 1904/529, loss: 0.0029181467834860086
2023-01-24 06:54:21.583306: step: 1908/529, loss: 0.01516847312450409
2023-01-24 06:54:22.666605: step: 1912/529, loss: 0.014981931075453758
2023-01-24 06:54:23.722453: step: 1916/529, loss: 0.009225535206496716
2023-01-24 06:54:24.803962: step: 1920/529, loss: 0.0028526494279503822
2023-01-24 06:54:25.895016: step: 1924/529, loss: 0.011153114959597588
2023-01-24 06:54:26.976946: step: 1928/529, loss: 0.013986228033900261
2023-01-24 06:54:28.051622: step: 1932/529, loss: 0.005642796866595745
2023-01-24 06:54:29.107871: step: 1936/529, loss: 0.0047327009961009026
2023-01-24 06:54:30.179186: step: 1940/529, loss: 0.004789605736732483
2023-01-24 06:54:31.239830: step: 1944/529, loss: 0.0016605491982772946
2023-01-24 06:54:32.334783: step: 1948/529, loss: 0.006903086788952351
2023-01-24 06:54:33.414751: step: 1952/529, loss: 0.017687933519482613
2023-01-24 06:54:34.499206: step: 1956/529, loss: 0.01979789510369301
2023-01-24 06:54:35.569715: step: 1960/529, loss: 0.03956262022256851
2023-01-24 06:54:36.653743: step: 1964/529, loss: 0.005671752616763115
2023-01-24 06:54:37.740938: step: 1968/529, loss: 0.0045891073532402515
2023-01-24 06:54:38.807240: step: 1972/529, loss: 0.027699964120984077
2023-01-24 06:54:39.870267: step: 1976/529, loss: 0.0183024350553751
2023-01-24 06:54:40.945568: step: 1980/529, loss: 0.007530553266406059
2023-01-24 06:54:42.007856: step: 1984/529, loss: 0.01620594412088394
2023-01-24 06:54:43.100110: step: 1988/529, loss: 0.014276370406150818
2023-01-24 06:54:44.174518: step: 1992/529, loss: 0.021116022020578384
2023-01-24 06:54:45.260660: step: 1996/529, loss: 0.007424824871122837
2023-01-24 06:54:46.335058: step: 2000/529, loss: 0.006106334272772074
2023-01-24 06:54:47.392952: step: 2004/529, loss: 0.005225195083767176
2023-01-24 06:54:48.467589: step: 2008/529, loss: 0.023255614563822746
2023-01-24 06:54:49.534247: step: 2012/529, loss: 0.016700133681297302
2023-01-24 06:54:50.605856: step: 2016/529, loss: 0.00023159108241088688
2023-01-24 06:54:51.706174: step: 2020/529, loss: 0.004689238965511322
2023-01-24 06:54:52.763603: step: 2024/529, loss: 0.01314149796962738
2023-01-24 06:54:53.835033: step: 2028/529, loss: 0.010646788403391838
2023-01-24 06:54:54.914373: step: 2032/529, loss: 0.005147057585418224
2023-01-24 06:54:56.000852: step: 2036/529, loss: 0.003516519907861948
2023-01-24 06:54:57.066807: step: 2040/529, loss: 0.004199287388473749
2023-01-24 06:54:58.154449: step: 2044/529, loss: 0.010551740415394306
2023-01-24 06:54:59.224429: step: 2048/529, loss: 0.0009885496692731977
2023-01-24 06:55:00.303814: step: 2052/529, loss: 0.006307472940534353
2023-01-24 06:55:01.375872: step: 2056/529, loss: 0.009027451276779175
2023-01-24 06:55:02.448455: step: 2060/529, loss: 0.0068636201322078705
2023-01-24 06:55:03.537098: step: 2064/529, loss: 0.0673711970448494
2023-01-24 06:55:04.596887: step: 2068/529, loss: 0.009444445371627808
2023-01-24 06:55:05.674072: step: 2072/529, loss: 0.004476535599678755
2023-01-24 06:55:06.750160: step: 2076/529, loss: 0.0030442506540566683
2023-01-24 06:55:07.821168: step: 2080/529, loss: 0.001577819581143558
2023-01-24 06:55:08.891736: step: 2084/529, loss: 0.0071356333792209625
2023-01-24 06:55:09.962959: step: 2088/529, loss: 0.00712616927921772
2023-01-24 06:55:11.039721: step: 2092/529, loss: 0.01787043735384941
2023-01-24 06:55:12.105453: step: 2096/529, loss: 0.002402389654889703
2023-01-24 06:55:13.185224: step: 2100/529, loss: 0.010706400498747826
2023-01-24 06:55:14.256210: step: 2104/529, loss: 0.003975633531808853
2023-01-24 06:55:15.330767: step: 2108/529, loss: 0.007619303185492754
2023-01-24 06:55:16.410067: step: 2112/529, loss: 0.04413328319787979
2023-01-24 06:55:17.468282: step: 2116/529, loss: 0.006672995164990425
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3324537177159, 'r': 0.2977574094153791, 'f1': 0.3141504599837933}, 'combined': 0.2314792863038477, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.331608874393714, 'r': 0.29442479105177183, 'f1': 0.3119125342398517}, 'combined': 0.20363201717213117, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35456219754580026, 'r': 0.3538894040020701, 'f1': 0.3542254813088147}, 'combined': 0.2610082493854424, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3567632732497733, 'r': 0.3138074011948833, 'f1': 0.3339094889975873}, 'combined': 0.2179927233870259, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37012726533301066, 'r': 0.33922479915719955, 'f1': 0.35400290921949334}, 'combined': 0.26084424889857405, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3655278697346525, 'r': 0.30303873023957406, 'f1': 0.33136295326699156}, 'combined': 0.21633021819503076, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35, 'r': 0.45652173913043476, 'f1': 0.39622641509433965}, 'combined': 0.19811320754716982, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, '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 06:57:50.930935: step: 4/529, loss: 0.004251775797456503
2023-01-24 06:57:51.990204: step: 8/529, loss: 0.009208057075738907
2023-01-24 06:57:53.049701: step: 12/529, loss: 0.0011367305414751172
2023-01-24 06:57:54.126133: step: 16/529, loss: 0.006010278128087521
2023-01-24 06:57:55.203601: step: 20/529, loss: 0.014736865647137165
2023-01-24 06:57:56.266811: step: 24/529, loss: 0.012458905577659607
2023-01-24 06:57:57.341370: step: 28/529, loss: 0.008214066736400127
2023-01-24 06:57:58.382905: step: 32/529, loss: 0.04549988731741905
2023-01-24 06:57:59.465180: step: 36/529, loss: 0.02159840054810047
2023-01-24 06:58:00.527701: step: 40/529, loss: 0.00996602512896061
2023-01-24 06:58:01.596260: step: 44/529, loss: 0.0031831255182623863
2023-01-24 06:58:02.673756: step: 48/529, loss: 0.00453998101875186
2023-01-24 06:58:03.734045: step: 52/529, loss: 0.00900235679000616
2023-01-24 06:58:04.796095: step: 56/529, loss: 0.0026426673866808414
2023-01-24 06:58:05.860677: step: 60/529, loss: 0.014532829634845257
2023-01-24 06:58:06.932790: step: 64/529, loss: 0.0028687419835478067
2023-01-24 06:58:08.013305: step: 68/529, loss: 0.003404824063181877
2023-01-24 06:58:09.079516: step: 72/529, loss: 0.01833401247859001
2023-01-24 06:58:10.143009: step: 76/529, loss: 0.012656144797801971
2023-01-24 06:58:11.203184: step: 80/529, loss: 0.0019174279877915978
2023-01-24 06:58:12.264740: step: 84/529, loss: 0.009247859008610249
2023-01-24 06:58:13.352500: step: 88/529, loss: 0.011272904463112354
2023-01-24 06:58:14.406071: step: 92/529, loss: 0.023677509278059006
2023-01-24 06:58:15.478853: step: 96/529, loss: 0.009600764140486717
2023-01-24 06:58:16.554491: step: 100/529, loss: 0.0031745238229632378
2023-01-24 06:58:17.625105: step: 104/529, loss: 0.012265895493328571
2023-01-24 06:58:18.694181: step: 108/529, loss: 0.00886599812656641
2023-01-24 06:58:19.764202: step: 112/529, loss: 0.0038776546716690063
2023-01-24 06:58:20.809692: step: 116/529, loss: 0.0036289007402956486
2023-01-24 06:58:21.866033: step: 120/529, loss: 0.0011353361187502742
2023-01-24 06:58:22.925835: step: 124/529, loss: 0.01882966049015522
2023-01-24 06:58:23.986818: step: 128/529, loss: 0.019013207405805588
2023-01-24 06:58:25.063228: step: 132/529, loss: 0.0036519926507025957
2023-01-24 06:58:26.134710: step: 136/529, loss: 0.005039970390498638
2023-01-24 06:58:27.192301: step: 140/529, loss: 0.025404075160622597
2023-01-24 06:58:28.257909: step: 144/529, loss: 0.019541069865226746
2023-01-24 06:58:29.314841: step: 148/529, loss: 0.0047492715530097485
2023-01-24 06:58:30.382185: step: 152/529, loss: 0.007716539781540632
2023-01-24 06:58:31.471478: step: 156/529, loss: 0.004348834976553917
2023-01-24 06:58:32.543568: step: 160/529, loss: 0.013202686794102192
2023-01-24 06:58:33.600237: step: 164/529, loss: 0.0019087671535089612
2023-01-24 06:58:34.662319: step: 168/529, loss: 0.018394405022263527
2023-01-24 06:58:35.733399: step: 172/529, loss: 0.019277531653642654
2023-01-24 06:58:36.799861: step: 176/529, loss: 0.006570256315171719
2023-01-24 06:58:37.859293: step: 180/529, loss: 0.0041452497243881226
2023-01-24 06:58:38.946883: step: 184/529, loss: 0.0023679640144109726
2023-01-24 06:58:40.023363: step: 188/529, loss: 0.008945180103182793
2023-01-24 06:58:41.080982: step: 192/529, loss: 0.0006713150069117546
2023-01-24 06:58:42.142971: step: 196/529, loss: 0.04765382409095764
2023-01-24 06:58:43.224912: step: 200/529, loss: 0.0017833278980106115
2023-01-24 06:58:44.292130: step: 204/529, loss: 0.011787833645939827
2023-01-24 06:58:45.355606: step: 208/529, loss: 0.004820005968213081
2023-01-24 06:58:46.429638: step: 212/529, loss: 0.009184892289340496
2023-01-24 06:58:47.517159: step: 216/529, loss: 0.004535608924925327
2023-01-24 06:58:48.597045: step: 220/529, loss: 0.003341608913615346
2023-01-24 06:58:49.684228: step: 224/529, loss: 0.005843697115778923
2023-01-24 06:58:50.751365: step: 228/529, loss: 8.227876969613135e-05
2023-01-24 06:58:51.824457: step: 232/529, loss: 0.011046051979064941
2023-01-24 06:58:52.894650: step: 236/529, loss: 0.009204757399857044
2023-01-24 06:58:53.973355: step: 240/529, loss: 0.004128958098590374
2023-01-24 06:58:55.051361: step: 244/529, loss: 0.005831011105328798
2023-01-24 06:58:56.133007: step: 248/529, loss: 0.0016641899710521102
2023-01-24 06:58:57.205115: step: 252/529, loss: 0.04585116729140282
2023-01-24 06:58:58.296796: step: 256/529, loss: 0.0307149700820446
2023-01-24 06:58:59.381963: step: 260/529, loss: 0.0036291461437940598
2023-01-24 06:59:00.445349: step: 264/529, loss: 0.00504803191870451
2023-01-24 06:59:01.529860: step: 268/529, loss: 0.0035000613424926996
2023-01-24 06:59:02.602358: step: 272/529, loss: 0.003666242817416787
2023-01-24 06:59:03.659415: step: 276/529, loss: 0.021791420876979828
2023-01-24 06:59:04.738756: step: 280/529, loss: 0.01919335126876831
2023-01-24 06:59:05.823470: step: 284/529, loss: 0.0043715969659388065
2023-01-24 06:59:06.893713: step: 288/529, loss: 0.0025412060786038637
2023-01-24 06:59:07.974770: step: 292/529, loss: 0.00961506087332964
2023-01-24 06:59:09.029613: step: 296/529, loss: 0.00323112728074193
2023-01-24 06:59:10.119610: step: 300/529, loss: 0.012194921262562275
2023-01-24 06:59:11.173003: step: 304/529, loss: 0.005448506213724613
2023-01-24 06:59:12.231863: step: 308/529, loss: 0.006082399748265743
2023-01-24 06:59:13.333709: step: 312/529, loss: 0.006452085915952921
2023-01-24 06:59:14.409928: step: 316/529, loss: 0.0034442876931279898
2023-01-24 06:59:15.480396: step: 320/529, loss: 0.0011805604444816709
2023-01-24 06:59:16.552635: step: 324/529, loss: 0.021573780104517937
2023-01-24 06:59:17.646689: step: 328/529, loss: 0.0031904454808682203
2023-01-24 06:59:18.746941: step: 332/529, loss: 0.008264061994850636
2023-01-24 06:59:19.821544: step: 336/529, loss: 0.015552588738501072
2023-01-24 06:59:20.890402: step: 340/529, loss: 0.0662967711687088
2023-01-24 06:59:21.967609: step: 344/529, loss: 0.010384410619735718
2023-01-24 06:59:23.040959: step: 348/529, loss: 0.0021233269944787025
2023-01-24 06:59:24.107691: step: 352/529, loss: 0.006720137782394886
2023-01-24 06:59:25.169654: step: 356/529, loss: 0.002918441779911518
2023-01-24 06:59:26.252177: step: 360/529, loss: 0.009702460840344429
2023-01-24 06:59:27.340358: step: 364/529, loss: 0.0004309820360504091
2023-01-24 06:59:28.439365: step: 368/529, loss: 0.004881261847913265
2023-01-24 06:59:29.516539: step: 372/529, loss: 0.003993060439825058
2023-01-24 06:59:30.601472: step: 376/529, loss: 0.03987521305680275
2023-01-24 06:59:31.670741: step: 380/529, loss: 0.03511584550142288
2023-01-24 06:59:32.765648: step: 384/529, loss: 0.004193971864879131
2023-01-24 06:59:33.852386: step: 388/529, loss: 0.005980449728667736
2023-01-24 06:59:34.924592: step: 392/529, loss: 0.02889382094144821
2023-01-24 06:59:36.002334: step: 396/529, loss: 0.0008592014200985432
2023-01-24 06:59:37.070094: step: 400/529, loss: 0.01188697200268507
2023-01-24 06:59:38.134044: step: 404/529, loss: 0.000858179060742259
2023-01-24 06:59:39.211076: step: 408/529, loss: 0.0073442463763058186
2023-01-24 06:59:40.274616: step: 412/529, loss: 0.04937830567359924
2023-01-24 06:59:41.358269: step: 416/529, loss: 0.000712226377800107
2023-01-24 06:59:42.450067: step: 420/529, loss: 0.0019556868355721235
2023-01-24 06:59:43.535677: step: 424/529, loss: 0.004297799430787563
2023-01-24 06:59:44.621891: step: 428/529, loss: 0.015537970699369907
2023-01-24 06:59:45.717038: step: 432/529, loss: 0.005229091737419367
2023-01-24 06:59:46.810523: step: 436/529, loss: 0.0068436795845627785
2023-01-24 06:59:47.904050: step: 440/529, loss: 0.010124222375452518
2023-01-24 06:59:48.985797: step: 444/529, loss: 0.003377160057425499
2023-01-24 06:59:50.050621: step: 448/529, loss: 0.005254809744656086
2023-01-24 06:59:51.159952: step: 452/529, loss: 0.002338831778615713
2023-01-24 06:59:52.235422: step: 456/529, loss: 0.001920098438858986
2023-01-24 06:59:53.319860: step: 460/529, loss: 0.0073715196922421455
2023-01-24 06:59:54.414254: step: 464/529, loss: 0.0053662885911762714
2023-01-24 06:59:55.502190: step: 468/529, loss: 0.0035072308965027332
2023-01-24 06:59:56.593223: step: 472/529, loss: 0.002970685251057148
2023-01-24 06:59:57.679106: step: 476/529, loss: 0.00894078053534031
2023-01-24 06:59:58.756131: step: 480/529, loss: 0.0008381872903555632
2023-01-24 06:59:59.842479: step: 484/529, loss: 0.015279687009751797
2023-01-24 07:00:00.922950: step: 488/529, loss: 0.012683913111686707
2023-01-24 07:00:02.005819: step: 492/529, loss: 0.004614950157701969
2023-01-24 07:00:03.082188: step: 496/529, loss: 0.009267103858292103
2023-01-24 07:00:04.158257: step: 500/529, loss: 0.0001331931125605479
2023-01-24 07:00:05.239034: step: 504/529, loss: 0.0029978761449456215
2023-01-24 07:00:06.314413: step: 508/529, loss: 0.0020075913053005934
2023-01-24 07:00:07.396159: step: 512/529, loss: 0.0045829410664737225
2023-01-24 07:00:08.483153: step: 516/529, loss: 0.017840543761849403
2023-01-24 07:00:09.554276: step: 520/529, loss: 0.0050712707452476025
2023-01-24 07:00:10.632308: step: 524/529, loss: 0.003671597223728895
2023-01-24 07:00:11.719385: step: 528/529, loss: 0.029142843559384346
2023-01-24 07:00:12.801319: step: 532/529, loss: 0.007382141891866922
2023-01-24 07:00:13.888375: step: 536/529, loss: 0.009816615842282772
2023-01-24 07:00:14.962841: step: 540/529, loss: 0.0009239738574251533
2023-01-24 07:00:16.052294: step: 544/529, loss: 0.01686771586537361
2023-01-24 07:00:17.135304: step: 548/529, loss: 0.014569797553122044
2023-01-24 07:00:18.223125: step: 552/529, loss: 0.025281637907028198
2023-01-24 07:00:19.314760: step: 556/529, loss: 0.0022701232228428125
2023-01-24 07:00:20.386719: step: 560/529, loss: 0.00023636706464458257
2023-01-24 07:00:21.464403: step: 564/529, loss: 0.002500031143426895
2023-01-24 07:00:22.573113: step: 568/529, loss: 0.005576382856816053
2023-01-24 07:00:23.659839: step: 572/529, loss: 0.023954322561621666
2023-01-24 07:00:24.748319: step: 576/529, loss: 0.007249325513839722
2023-01-24 07:00:25.837078: step: 580/529, loss: 0.03558175638318062
2023-01-24 07:00:26.923835: step: 584/529, loss: 0.0035528670996427536
2023-01-24 07:00:28.008239: step: 588/529, loss: 0.003556488547474146
2023-01-24 07:00:29.111420: step: 592/529, loss: 0.004361058585345745
2023-01-24 07:00:30.192389: step: 596/529, loss: 0.002490002429112792
2023-01-24 07:00:31.272180: step: 600/529, loss: 0.003968839533627033
2023-01-24 07:00:32.362475: step: 604/529, loss: 0.007614034693688154
2023-01-24 07:00:33.447310: step: 608/529, loss: 0.057831019163131714
2023-01-24 07:00:34.527178: step: 612/529, loss: 0.008671285584568977
2023-01-24 07:00:35.602866: step: 616/529, loss: 0.0005794924218207598
2023-01-24 07:00:36.680215: step: 620/529, loss: 0.010089150629937649
2023-01-24 07:00:37.764473: step: 624/529, loss: 0.01467905379831791
2023-01-24 07:00:38.830572: step: 628/529, loss: 0.004232405219227076
2023-01-24 07:00:39.925992: step: 632/529, loss: 0.001756802899762988
2023-01-24 07:00:40.996706: step: 636/529, loss: 4.07196166634094e-05
2023-01-24 07:00:42.076749: step: 640/529, loss: 0.00585485203191638
2023-01-24 07:00:43.187722: step: 644/529, loss: 0.002673714654520154
2023-01-24 07:00:44.281346: step: 648/529, loss: 0.004026413895189762
2023-01-24 07:00:45.373419: step: 652/529, loss: 0.07536202669143677
2023-01-24 07:00:46.451489: step: 656/529, loss: 0.030667327344417572
2023-01-24 07:00:47.537499: step: 660/529, loss: 0.0031212777830660343
2023-01-24 07:00:48.616759: step: 664/529, loss: 0.002480089897289872
2023-01-24 07:00:49.688194: step: 668/529, loss: 0.0024589565582573414
2023-01-24 07:00:50.757644: step: 672/529, loss: 0.0010578534565865993
2023-01-24 07:00:51.853233: step: 676/529, loss: 0.008302543312311172
2023-01-24 07:00:52.924914: step: 680/529, loss: 0.006249351426959038
2023-01-24 07:00:54.001430: step: 684/529, loss: 0.007828416302800179
2023-01-24 07:00:55.084911: step: 688/529, loss: 0.004356584046036005
2023-01-24 07:00:56.161290: step: 692/529, loss: 0.008816482499241829
2023-01-24 07:00:57.234613: step: 696/529, loss: 0.008845777250826359
2023-01-24 07:00:58.314106: step: 700/529, loss: 0.005275289993733168
2023-01-24 07:00:59.398071: step: 704/529, loss: 0.01827814057469368
2023-01-24 07:01:00.487451: step: 708/529, loss: 0.013627135194838047
2023-01-24 07:01:01.563695: step: 712/529, loss: 0.012442792765796185
2023-01-24 07:01:02.634903: step: 716/529, loss: 0.0058509670197963715
2023-01-24 07:01:03.733149: step: 720/529, loss: 0.018941203132271767
2023-01-24 07:01:04.837300: step: 724/529, loss: 0.05661045387387276
2023-01-24 07:01:05.926712: step: 728/529, loss: 0.018146302551031113
2023-01-24 07:01:07.028113: step: 732/529, loss: 0.0035150747280567884
2023-01-24 07:01:08.109568: step: 736/529, loss: 0.002940249862149358
2023-01-24 07:01:09.172695: step: 740/529, loss: 0.00035843192017637193
2023-01-24 07:01:10.261009: step: 744/529, loss: 0.04068102315068245
2023-01-24 07:01:11.348031: step: 748/529, loss: 0.009319968521595001
2023-01-24 07:01:12.424170: step: 752/529, loss: 0.013870734721422195
2023-01-24 07:01:13.531734: step: 756/529, loss: 0.0040064407512545586
2023-01-24 07:01:14.614332: step: 760/529, loss: 0.01702064834535122
2023-01-24 07:01:15.717524: step: 764/529, loss: 0.006673571188002825
2023-01-24 07:01:16.803279: step: 768/529, loss: 0.0037315767258405685
2023-01-24 07:01:17.877627: step: 772/529, loss: 0.01851697266101837
2023-01-24 07:01:18.953632: step: 776/529, loss: 0.0077040973119437695
2023-01-24 07:01:20.046556: step: 780/529, loss: 0.004212753847241402
2023-01-24 07:01:21.133004: step: 784/529, loss: 0.009366575628519058
2023-01-24 07:01:22.218871: step: 788/529, loss: 0.029224945232272148
2023-01-24 07:01:23.297197: step: 792/529, loss: 0.037477053701877594
2023-01-24 07:01:24.386687: step: 796/529, loss: 0.014138245023787022
2023-01-24 07:01:25.455311: step: 800/529, loss: 0.0012153461575508118
2023-01-24 07:01:26.533763: step: 804/529, loss: 0.005523739382624626
2023-01-24 07:01:27.624755: step: 808/529, loss: 0.0036886618472635746
2023-01-24 07:01:28.717391: step: 812/529, loss: 0.0006245935219340026
2023-01-24 07:01:29.816157: step: 816/529, loss: 0.0061524417251348495
2023-01-24 07:01:30.891335: step: 820/529, loss: 0.0014282549964264035
2023-01-24 07:01:31.990815: step: 824/529, loss: 0.00044671798241324723
2023-01-24 07:01:33.062332: step: 828/529, loss: 0.014413303695619106
2023-01-24 07:01:34.143330: step: 832/529, loss: 0.007666704710572958
2023-01-24 07:01:35.229793: step: 836/529, loss: 0.0023659660946577787
2023-01-24 07:01:36.304376: step: 840/529, loss: 0.006354359909892082
2023-01-24 07:01:37.376294: step: 844/529, loss: 0.003157402155920863
2023-01-24 07:01:38.462677: step: 848/529, loss: 0.0024600059259682894
2023-01-24 07:01:39.530922: step: 852/529, loss: 0.00858303438872099
2023-01-24 07:01:40.624870: step: 856/529, loss: 0.005679039750248194
2023-01-24 07:01:41.709825: step: 860/529, loss: 0.010664182715117931
2023-01-24 07:01:42.791811: step: 864/529, loss: 0.010316543281078339
2023-01-24 07:01:43.874256: step: 868/529, loss: 0.01099282968789339
2023-01-24 07:01:44.939897: step: 872/529, loss: 0.002407555002719164
2023-01-24 07:01:46.017711: step: 876/529, loss: 0.006599427200853825
2023-01-24 07:01:47.094402: step: 880/529, loss: 0.0012035934487357736
2023-01-24 07:01:48.163135: step: 884/529, loss: 0.006955781485885382
2023-01-24 07:01:49.246565: step: 888/529, loss: 0.006533194798976183
2023-01-24 07:01:50.333210: step: 892/529, loss: 0.01938214898109436
2023-01-24 07:01:51.415689: step: 896/529, loss: 0.011880344711244106
2023-01-24 07:01:52.475838: step: 900/529, loss: 0.010847535915672779
2023-01-24 07:01:53.542522: step: 904/529, loss: 0.0011242233449593186
2023-01-24 07:01:54.621867: step: 908/529, loss: 0.006665481254458427
2023-01-24 07:01:55.703688: step: 912/529, loss: 0.004542097914963961
2023-01-24 07:01:56.792340: step: 916/529, loss: 0.01959998533129692
2023-01-24 07:01:57.877045: step: 920/529, loss: 0.009096367284655571
2023-01-24 07:01:58.949659: step: 924/529, loss: 0.01188227254897356
2023-01-24 07:02:00.010691: step: 928/529, loss: 0.007576973643153906
2023-01-24 07:02:01.106425: step: 932/529, loss: 0.002881244057789445
2023-01-24 07:02:02.195895: step: 936/529, loss: 0.008614256978034973
2023-01-24 07:02:03.267555: step: 940/529, loss: 0.0070563205517828465
2023-01-24 07:02:04.336709: step: 944/529, loss: 0.0027562417089939117
2023-01-24 07:02:05.399435: step: 948/529, loss: 0.003601611126214266
2023-01-24 07:02:06.472365: step: 952/529, loss: 0.008946127258241177
2023-01-24 07:02:07.547408: step: 956/529, loss: 0.006065301597118378
2023-01-24 07:02:08.614829: step: 960/529, loss: 0.007183948066085577
2023-01-24 07:02:09.679184: step: 964/529, loss: 0.0026896835770457983
2023-01-24 07:02:10.780531: step: 968/529, loss: 0.014979854226112366
2023-01-24 07:02:11.837129: step: 972/529, loss: 0.00674881786108017
2023-01-24 07:02:12.928708: step: 976/529, loss: 0.008472763933241367
2023-01-24 07:02:13.992526: step: 980/529, loss: 0.015505709685385227
2023-01-24 07:02:15.067416: step: 984/529, loss: 0.01022348552942276
2023-01-24 07:02:16.140749: step: 988/529, loss: 0.05629247799515724
2023-01-24 07:02:17.216268: step: 992/529, loss: 0.011514423415064812
2023-01-24 07:02:18.293362: step: 996/529, loss: 0.0020439212676137686
2023-01-24 07:02:19.349906: step: 1000/529, loss: 0.008712699636816978
2023-01-24 07:02:20.420755: step: 1004/529, loss: 0.008198211900889874
2023-01-24 07:02:21.497121: step: 1008/529, loss: 0.003807215951383114
2023-01-24 07:02:22.575828: step: 1012/529, loss: 0.015538888052105904
2023-01-24 07:02:23.649593: step: 1016/529, loss: 0.0028870285023003817
2023-01-24 07:02:24.725915: step: 1020/529, loss: 0.007703030481934547
2023-01-24 07:02:25.806102: step: 1024/529, loss: 0.002175495494157076
2023-01-24 07:02:26.889510: step: 1028/529, loss: 0.00846147257834673
2023-01-24 07:02:27.973832: step: 1032/529, loss: 0.003329416736960411
2023-01-24 07:02:29.037792: step: 1036/529, loss: 0.0047632367350161076
2023-01-24 07:02:30.128744: step: 1040/529, loss: 0.009274058975279331
2023-01-24 07:02:31.206299: step: 1044/529, loss: 0.002075947355479002
2023-01-24 07:02:32.261836: step: 1048/529, loss: 0.0035732085816562176
2023-01-24 07:02:33.340261: step: 1052/529, loss: 0.015886353328824043
2023-01-24 07:02:34.403036: step: 1056/529, loss: 0.0028083750512450933
2023-01-24 07:02:35.476202: step: 1060/529, loss: 0.00417746277526021
2023-01-24 07:02:36.547393: step: 1064/529, loss: 0.0009289412992075086
2023-01-24 07:02:37.636794: step: 1068/529, loss: 0.004043098539113998
2023-01-24 07:02:38.697592: step: 1072/529, loss: 0.0025499416515231133
2023-01-24 07:02:39.768632: step: 1076/529, loss: 0.009742177091538906
2023-01-24 07:02:40.833084: step: 1080/529, loss: 0.01728571392595768
2023-01-24 07:02:41.922614: step: 1084/529, loss: 0.007542267441749573
2023-01-24 07:02:42.988464: step: 1088/529, loss: 0.0013810511445626616
2023-01-24 07:02:44.047083: step: 1092/529, loss: 0.0022976386826485395
2023-01-24 07:02:45.119231: step: 1096/529, loss: 0.0036816869396716356
2023-01-24 07:02:46.199462: step: 1100/529, loss: 0.004171743523329496
2023-01-24 07:02:47.261810: step: 1104/529, loss: 0.005522042512893677
2023-01-24 07:02:48.335448: step: 1108/529, loss: 0.006198076531291008
2023-01-24 07:02:49.409836: step: 1112/529, loss: 0.0028345489408820868
2023-01-24 07:02:50.476225: step: 1116/529, loss: 0.0005563206505030394
2023-01-24 07:02:51.528891: step: 1120/529, loss: 0.0041571143083274364
2023-01-24 07:02:52.600153: step: 1124/529, loss: 0.0032633799128234386
2023-01-24 07:02:53.668128: step: 1128/529, loss: 0.00960410013794899
2023-01-24 07:02:54.745276: step: 1132/529, loss: 0.004124002065509558
2023-01-24 07:02:55.805132: step: 1136/529, loss: 5.40231440027128e-06
2023-01-24 07:02:56.886213: step: 1140/529, loss: 0.003400008426979184
2023-01-24 07:02:57.980102: step: 1144/529, loss: 0.015203959308564663
2023-01-24 07:02:59.047647: step: 1148/529, loss: 0.012904616072773933
2023-01-24 07:03:00.139228: step: 1152/529, loss: 0.003881575772538781
2023-01-24 07:03:01.213313: step: 1156/529, loss: 0.07048137485980988
2023-01-24 07:03:02.296190: step: 1160/529, loss: 0.005223456304520369
2023-01-24 07:03:03.363393: step: 1164/529, loss: 0.008334493264555931
2023-01-24 07:03:04.456059: step: 1168/529, loss: 0.01136496290564537
2023-01-24 07:03:05.539831: step: 1172/529, loss: 0.005291508976370096
2023-01-24 07:03:06.608086: step: 1176/529, loss: 0.013276208192110062
2023-01-24 07:03:07.674980: step: 1180/529, loss: 0.008856615982949734
2023-01-24 07:03:08.757913: step: 1184/529, loss: 0.00530351884663105
2023-01-24 07:03:09.843994: step: 1188/529, loss: 0.001901112962514162
2023-01-24 07:03:10.929333: step: 1192/529, loss: 0.004477955866605043
2023-01-24 07:03:11.980681: step: 1196/529, loss: 0.010055916383862495
2023-01-24 07:03:13.043718: step: 1200/529, loss: 0.0047800056636333466
2023-01-24 07:03:14.099094: step: 1204/529, loss: 0.0027272680308669806
2023-01-24 07:03:15.162923: step: 1208/529, loss: 0.008661479689180851
2023-01-24 07:03:16.241601: step: 1212/529, loss: 0.0013380871387198567
2023-01-24 07:03:17.305605: step: 1216/529, loss: 0.007114128675311804
2023-01-24 07:03:18.392699: step: 1220/529, loss: 0.011884539388120174
2023-01-24 07:03:19.484543: step: 1224/529, loss: 0.02450762689113617
2023-01-24 07:03:20.551595: step: 1228/529, loss: 0.002024158602580428
2023-01-24 07:03:21.631471: step: 1232/529, loss: 0.008725673891603947
2023-01-24 07:03:22.705010: step: 1236/529, loss: 0.002557213883846998
2023-01-24 07:03:23.779592: step: 1240/529, loss: 0.002870753640308976
2023-01-24 07:03:24.845069: step: 1244/529, loss: 0.00911586731672287
2023-01-24 07:03:25.909619: step: 1248/529, loss: 0.0038410075940191746
2023-01-24 07:03:26.972818: step: 1252/529, loss: 0.029661059379577637
2023-01-24 07:03:28.042423: step: 1256/529, loss: 0.003212140640243888
2023-01-24 07:03:29.112305: step: 1260/529, loss: 0.005618896801024675
2023-01-24 07:03:30.168351: step: 1264/529, loss: 0.008286651223897934
2023-01-24 07:03:31.244283: step: 1268/529, loss: 0.01274032611399889
2023-01-24 07:03:32.309125: step: 1272/529, loss: 0.0037362687289714813
2023-01-24 07:03:33.362951: step: 1276/529, loss: 0.00804054457694292
2023-01-24 07:03:34.428093: step: 1280/529, loss: 0.0012157114688307047
2023-01-24 07:03:35.485570: step: 1284/529, loss: 0.0015416594687849283
2023-01-24 07:03:36.555252: step: 1288/529, loss: 0.004680857062339783
2023-01-24 07:03:37.609431: step: 1292/529, loss: 0.0028292019851505756
2023-01-24 07:03:38.695636: step: 1296/529, loss: 0.08718092739582062
2023-01-24 07:03:39.761322: step: 1300/529, loss: 0.009938710369169712
2023-01-24 07:03:40.849236: step: 1304/529, loss: 0.04332110658288002
2023-01-24 07:03:41.912543: step: 1308/529, loss: 0.006968655623495579
2023-01-24 07:03:42.985963: step: 1312/529, loss: 0.004150428343564272
2023-01-24 07:03:44.067572: step: 1316/529, loss: 0.02297881245613098
2023-01-24 07:03:45.162688: step: 1320/529, loss: 0.014645163901150227
2023-01-24 07:03:46.252141: step: 1324/529, loss: 0.005532841198146343
2023-01-24 07:03:47.329275: step: 1328/529, loss: 0.034226030111312866
2023-01-24 07:03:48.408544: step: 1332/529, loss: 0.01838810183107853
2023-01-24 07:03:49.502082: step: 1336/529, loss: 0.0212626364082098
2023-01-24 07:03:50.582952: step: 1340/529, loss: 0.011266743764281273
2023-01-24 07:03:51.638689: step: 1344/529, loss: 0.0025158508215099573
2023-01-24 07:03:52.714412: step: 1348/529, loss: 0.022542087361216545
2023-01-24 07:03:53.785216: step: 1352/529, loss: 0.0013686477905139327
2023-01-24 07:03:54.861296: step: 1356/529, loss: 0.007258938159793615
2023-01-24 07:03:55.935089: step: 1360/529, loss: 0.009761031717061996
2023-01-24 07:03:56.994786: step: 1364/529, loss: 0.0041913497261703014
2023-01-24 07:03:58.081530: step: 1368/529, loss: 0.008142043836414814
2023-01-24 07:03:59.161793: step: 1372/529, loss: 0.0440276637673378
2023-01-24 07:04:00.232716: step: 1376/529, loss: 0.006626906339079142
2023-01-24 07:04:01.317591: step: 1380/529, loss: 0.01024853065609932
2023-01-24 07:04:02.378436: step: 1384/529, loss: 0.003399195149540901
2023-01-24 07:04:03.469246: step: 1388/529, loss: 0.0031623761169612408
2023-01-24 07:04:04.522781: step: 1392/529, loss: 0.00807243399322033
2023-01-24 07:04:05.596480: step: 1396/529, loss: 0.010173263028264046
2023-01-24 07:04:06.671327: step: 1400/529, loss: 0.0015340005047619343
2023-01-24 07:04:07.746139: step: 1404/529, loss: 0.004942870698869228
2023-01-24 07:04:08.828506: step: 1408/529, loss: 0.0024159541353583336
2023-01-24 07:04:09.901884: step: 1412/529, loss: 0.001312845153734088
2023-01-24 07:04:10.965961: step: 1416/529, loss: 0.012278782203793526
2023-01-24 07:04:12.030320: step: 1420/529, loss: 0.005591663997620344
2023-01-24 07:04:13.117720: step: 1424/529, loss: 0.02819264680147171
2023-01-24 07:04:14.195053: step: 1428/529, loss: 0.007811288814991713
2023-01-24 07:04:15.272450: step: 1432/529, loss: 0.00844008382409811
2023-01-24 07:04:16.363563: step: 1436/529, loss: 0.005512373987585306
2023-01-24 07:04:17.463551: step: 1440/529, loss: 0.0018055766122415662
2023-01-24 07:04:18.543040: step: 1444/529, loss: 0.04203746095299721
2023-01-24 07:04:19.638186: step: 1448/529, loss: 0.007252662442624569
2023-01-24 07:04:20.701471: step: 1452/529, loss: 0.03764216601848602
2023-01-24 07:04:21.756926: step: 1456/529, loss: 0.0005199461593292654
2023-01-24 07:04:22.817367: step: 1460/529, loss: 0.005638635251671076
2023-01-24 07:04:23.878489: step: 1464/529, loss: 0.0021217751782387495
2023-01-24 07:04:24.958269: step: 1468/529, loss: 0.01366223581135273
2023-01-24 07:04:26.025532: step: 1472/529, loss: 0.008197786286473274
2023-01-24 07:04:27.089047: step: 1476/529, loss: 0.043221522122621536
2023-01-24 07:04:28.171811: step: 1480/529, loss: 0.007423872593790293
2023-01-24 07:04:29.247954: step: 1484/529, loss: 0.02055491879582405
2023-01-24 07:04:30.305122: step: 1488/529, loss: 0.003961401991546154
2023-01-24 07:04:31.376178: step: 1492/529, loss: 0.003747825277969241
2023-01-24 07:04:32.442664: step: 1496/529, loss: 0.0010228921892121434
2023-01-24 07:04:33.519920: step: 1500/529, loss: 0.009438322857022285
2023-01-24 07:04:34.595800: step: 1504/529, loss: 0.012222778983414173
2023-01-24 07:04:35.679488: step: 1508/529, loss: 0.009745476767420769
2023-01-24 07:04:36.759304: step: 1512/529, loss: 0.0026218045968562365
2023-01-24 07:04:37.831075: step: 1516/529, loss: 0.0007571568130515516
2023-01-24 07:04:38.903288: step: 1520/529, loss: 0.003980558831244707
2023-01-24 07:04:39.997999: step: 1524/529, loss: 0.01007144432514906
2023-01-24 07:04:41.078905: step: 1528/529, loss: 0.0024592960253357887
2023-01-24 07:04:42.183618: step: 1532/529, loss: 0.0179671049118042
2023-01-24 07:04:43.261025: step: 1536/529, loss: 0.0014771640999242663
2023-01-24 07:04:44.365657: step: 1540/529, loss: 0.013780679553747177
2023-01-24 07:04:45.435211: step: 1544/529, loss: 0.0036924942396581173
2023-01-24 07:04:46.505256: step: 1548/529, loss: 0.007804648019373417
2023-01-24 07:04:47.588769: step: 1552/529, loss: 0.02368420548737049
2023-01-24 07:04:48.644564: step: 1556/529, loss: 0.03424181789159775
2023-01-24 07:04:49.744030: step: 1560/529, loss: 0.005288993939757347
2023-01-24 07:04:50.814295: step: 1564/529, loss: 0.02749105915427208
2023-01-24 07:04:51.900397: step: 1568/529, loss: 0.01094154641032219
2023-01-24 07:04:52.982197: step: 1572/529, loss: 0.0087797362357378
2023-01-24 07:04:54.052993: step: 1576/529, loss: 0.002545113442465663
2023-01-24 07:04:55.140761: step: 1580/529, loss: 0.0016076716128736734
2023-01-24 07:04:56.220937: step: 1584/529, loss: 0.0088021419942379
2023-01-24 07:04:57.295414: step: 1588/529, loss: 0.001380827627144754
2023-01-24 07:04:58.374387: step: 1592/529, loss: 0.0028225325513631105
2023-01-24 07:04:59.457321: step: 1596/529, loss: 0.011315269395709038
2023-01-24 07:05:00.522237: step: 1600/529, loss: 0.006238800007849932
2023-01-24 07:05:01.599203: step: 1604/529, loss: 0.0032620918937027454
2023-01-24 07:05:02.670336: step: 1608/529, loss: 0.0069154370576143265
2023-01-24 07:05:03.748320: step: 1612/529, loss: 0.034226495772600174
2023-01-24 07:05:04.837071: step: 1616/529, loss: 0.004367852117866278
2023-01-24 07:05:05.935205: step: 1620/529, loss: 0.00941659975796938
2023-01-24 07:05:07.043178: step: 1624/529, loss: 0.008812328800559044
2023-01-24 07:05:08.126044: step: 1628/529, loss: 0.0028780994471162558
2023-01-24 07:05:09.205604: step: 1632/529, loss: 0.026409205049276352
2023-01-24 07:05:10.272770: step: 1636/529, loss: 0.004808820318430662
2023-01-24 07:05:11.319880: step: 1640/529, loss: 0.0022123989183455706
2023-01-24 07:05:12.412759: step: 1644/529, loss: 0.09495656937360764
2023-01-24 07:05:13.473498: step: 1648/529, loss: 0.006485449615865946
2023-01-24 07:05:14.560220: step: 1652/529, loss: 0.010328743606805801
2023-01-24 07:05:15.627876: step: 1656/529, loss: 0.010405809618532658
2023-01-24 07:05:16.701715: step: 1660/529, loss: 0.07516153156757355
2023-01-24 07:05:17.786189: step: 1664/529, loss: 0.01170724630355835
2023-01-24 07:05:18.863906: step: 1668/529, loss: 0.0043946923688054085
2023-01-24 07:05:19.952094: step: 1672/529, loss: 0.014025701209902763
2023-01-24 07:05:21.036278: step: 1676/529, loss: 0.005781049374490976
2023-01-24 07:05:22.107596: step: 1680/529, loss: 0.0035958215594291687
2023-01-24 07:05:23.188037: step: 1684/529, loss: 0.019465569406747818
2023-01-24 07:05:24.254467: step: 1688/529, loss: 0.0025285258889198303
2023-01-24 07:05:25.316560: step: 1692/529, loss: 0.003045066259801388
2023-01-24 07:05:26.387068: step: 1696/529, loss: 0.009937570430338383
2023-01-24 07:05:27.456444: step: 1700/529, loss: 0.003986789379268885
2023-01-24 07:05:28.528740: step: 1704/529, loss: 0.00230491254478693
2023-01-24 07:05:29.625084: step: 1708/529, loss: 0.001607365207746625
2023-01-24 07:05:30.706702: step: 1712/529, loss: 0.009701140224933624
2023-01-24 07:05:31.798529: step: 1716/529, loss: 0.022345921024680138
2023-01-24 07:05:32.874820: step: 1720/529, loss: 0.006601015571504831
2023-01-24 07:05:33.951494: step: 1724/529, loss: 0.01697540283203125
2023-01-24 07:05:35.066982: step: 1728/529, loss: 0.006874631159007549
2023-01-24 07:05:36.144346: step: 1732/529, loss: 0.03952629119157791
2023-01-24 07:05:37.215281: step: 1736/529, loss: 0.002731254091486335
2023-01-24 07:05:38.294072: step: 1740/529, loss: 0.00044692287337966263
2023-01-24 07:05:39.357029: step: 1744/529, loss: 0.013179549016058445
2023-01-24 07:05:40.429978: step: 1748/529, loss: 0.0005687236553058028
2023-01-24 07:05:41.508683: step: 1752/529, loss: 0.004726551938802004
2023-01-24 07:05:42.577209: step: 1756/529, loss: 0.02497788332402706
2023-01-24 07:05:43.689074: step: 1760/529, loss: 0.02773934230208397
2023-01-24 07:05:44.764029: step: 1764/529, loss: 0.004229980520904064
2023-01-24 07:05:45.852555: step: 1768/529, loss: 0.008047755807638168
2023-01-24 07:05:46.925540: step: 1772/529, loss: 0.0022551477886736393
2023-01-24 07:05:47.997604: step: 1776/529, loss: 0.0018247365951538086
2023-01-24 07:05:49.084670: step: 1780/529, loss: 0.010773323476314545
2023-01-24 07:05:50.176798: step: 1784/529, loss: 0.04095825180411339
2023-01-24 07:05:51.242556: step: 1788/529, loss: 0.012872646562755108
2023-01-24 07:05:52.321798: step: 1792/529, loss: 0.004160088486969471
2023-01-24 07:05:53.404902: step: 1796/529, loss: 0.0038366459775716066
2023-01-24 07:05:54.476016: step: 1800/529, loss: 0.005891278386116028
2023-01-24 07:05:55.569476: step: 1804/529, loss: 1.0860945621971041e-05
2023-01-24 07:05:56.643698: step: 1808/529, loss: 0.00873658712953329
2023-01-24 07:05:57.713993: step: 1812/529, loss: 0.0007788158836774528
2023-01-24 07:05:58.806741: step: 1816/529, loss: 0.03033316507935524
2023-01-24 07:05:59.889984: step: 1820/529, loss: 0.0031953095458447933
2023-01-24 07:06:00.975471: step: 1824/529, loss: 0.0026121840346604586
2023-01-24 07:06:02.047842: step: 1828/529, loss: 0.011429809965193272
2023-01-24 07:06:03.150665: step: 1832/529, loss: 0.005580891389399767
2023-01-24 07:06:04.236154: step: 1836/529, loss: 0.009507030248641968
2023-01-24 07:06:05.319387: step: 1840/529, loss: 0.008096694946289062
2023-01-24 07:06:06.412969: step: 1844/529, loss: 0.00789687130600214
2023-01-24 07:06:07.504841: step: 1848/529, loss: 0.04057244583964348
2023-01-24 07:06:08.582747: step: 1852/529, loss: 0.005006532184779644
2023-01-24 07:06:09.675085: step: 1856/529, loss: 0.003552117384970188
2023-01-24 07:06:10.771805: step: 1860/529, loss: 0.00452266214415431
2023-01-24 07:06:11.855383: step: 1864/529, loss: 0.00851934403181076
2023-01-24 07:06:12.953656: step: 1868/529, loss: 0.010997751727700233
2023-01-24 07:06:14.026104: step: 1872/529, loss: 0.009946765378117561
2023-01-24 07:06:15.112305: step: 1876/529, loss: 0.01137964241206646
2023-01-24 07:06:16.180219: step: 1880/529, loss: 0.0005444071139208972
2023-01-24 07:06:17.250527: step: 1884/529, loss: 0.003657351015135646
2023-01-24 07:06:18.336228: step: 1888/529, loss: 0.0023001153022050858
2023-01-24 07:06:19.426088: step: 1892/529, loss: 0.0052753109484910965
2023-01-24 07:06:20.516193: step: 1896/529, loss: 0.005844618659466505
2023-01-24 07:06:21.591513: step: 1900/529, loss: 0.005758931860327721
2023-01-24 07:06:22.656995: step: 1904/529, loss: 0.008736329153180122
2023-01-24 07:06:23.719605: step: 1908/529, loss: 0.01070530153810978
2023-01-24 07:06:24.794053: step: 1912/529, loss: 0.004352023359388113
2023-01-24 07:06:25.890563: step: 1916/529, loss: 0.013666080310940742
2023-01-24 07:06:26.957245: step: 1920/529, loss: 0.009677940048277378
2023-01-24 07:06:28.026838: step: 1924/529, loss: 0.005825961474329233
2023-01-24 07:06:29.091132: step: 1928/529, loss: 0.005881572142243385
2023-01-24 07:06:30.162330: step: 1932/529, loss: 0.004065447486937046
2023-01-24 07:06:31.225280: step: 1936/529, loss: 0.004868187475949526
2023-01-24 07:06:32.300087: step: 1940/529, loss: 0.020822836086153984
2023-01-24 07:06:33.386943: step: 1944/529, loss: 0.003358823712915182
2023-01-24 07:06:34.466439: step: 1948/529, loss: 0.03390880674123764
2023-01-24 07:06:35.553214: step: 1952/529, loss: 0.003090057522058487
2023-01-24 07:06:36.631544: step: 1956/529, loss: 0.01908806897699833
2023-01-24 07:06:37.712991: step: 1960/529, loss: 0.004665096290409565
2023-01-24 07:06:38.788951: step: 1964/529, loss: 0.01134908851236105
2023-01-24 07:06:39.867238: step: 1968/529, loss: 0.008327435702085495
2023-01-24 07:06:40.946424: step: 1972/529, loss: 0.005929056089371443
2023-01-24 07:06:42.023517: step: 1976/529, loss: 0.006328521762043238
2023-01-24 07:06:43.104886: step: 1980/529, loss: 0.006182138342410326
2023-01-24 07:06:44.191254: step: 1984/529, loss: 0.004397683311253786
2023-01-24 07:06:45.280234: step: 1988/529, loss: 0.03543352708220482
2023-01-24 07:06:46.343961: step: 1992/529, loss: 0.008861798793077469
2023-01-24 07:06:47.444301: step: 1996/529, loss: 0.009600820019841194
2023-01-24 07:06:48.531935: step: 2000/529, loss: 0.032085221260786057
2023-01-24 07:06:49.596847: step: 2004/529, loss: 0.011869809590280056
2023-01-24 07:06:50.674243: step: 2008/529, loss: 0.0226276908069849
2023-01-24 07:06:51.745383: step: 2012/529, loss: 0.00026266343775205314
2023-01-24 07:06:52.817845: step: 2016/529, loss: 0.002348813693970442
2023-01-24 07:06:53.897563: step: 2020/529, loss: 0.020276904106140137
2023-01-24 07:06:54.960396: step: 2024/529, loss: 0.004203373566269875
2023-01-24 07:06:56.013491: step: 2028/529, loss: 0.01897486485540867
2023-01-24 07:06:57.102078: step: 2032/529, loss: 0.02406066283583641
2023-01-24 07:06:58.163160: step: 2036/529, loss: 0.0016599440714344382
2023-01-24 07:06:59.247067: step: 2040/529, loss: 0.007167106494307518
2023-01-24 07:07:00.313554: step: 2044/529, loss: 0.010923652909696102
2023-01-24 07:07:01.402951: step: 2048/529, loss: 0.0004048360569868237
2023-01-24 07:07:02.484430: step: 2052/529, loss: 0.004154149442911148
2023-01-24 07:07:03.564942: step: 2056/529, loss: 0.009003751911222935
2023-01-24 07:07:04.633392: step: 2060/529, loss: 0.004973648581653833
2023-01-24 07:07:05.722229: step: 2064/529, loss: 0.024084147065877914
2023-01-24 07:07:06.791881: step: 2068/529, loss: 0.00817825272679329
2023-01-24 07:07:07.867695: step: 2072/529, loss: 0.00335396034643054
2023-01-24 07:07:08.936996: step: 2076/529, loss: 0.0033416247460991144
2023-01-24 07:07:10.009942: step: 2080/529, loss: 0.006267180200666189
2023-01-24 07:07:11.082320: step: 2084/529, loss: 0.007855514995753765
2023-01-24 07:07:12.144477: step: 2088/529, loss: 0.003910467494279146
2023-01-24 07:07:13.223134: step: 2092/529, loss: 0.03349063917994499
2023-01-24 07:07:14.313707: step: 2096/529, loss: 0.007858878001570702
2023-01-24 07:07:15.374046: step: 2100/529, loss: 0.006541946437209845
2023-01-24 07:07:16.457980: step: 2104/529, loss: 0.02803930640220642
2023-01-24 07:07:17.528543: step: 2108/529, loss: 0.006639318540692329
2023-01-24 07:07:18.606517: step: 2112/529, loss: 0.01448830496519804
2023-01-24 07:07:19.690409: step: 2116/529, loss: 0.010935690253973007
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33264198908730164, 'r': 0.3029756257341647, 'f1': 0.31711649406535214}, 'combined': 0.23366478510078578, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3376010163681586, 'r': 0.29695236458118357, 'f1': 0.3159747409920075}, 'combined': 0.2062840277978909, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36147953682939454, 'r': 0.36147953682939454, 'f1': 0.36147953682939454}, 'combined': 0.26635334292692225, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3588996349790263, 'r': 0.31403718060664804, 'f1': 0.3349729926470913}, 'combined': 0.2186870314690855, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37222067588469027, 'r': 0.34396863217427737, 'f1': 0.3575374145085684}, 'combined': 0.2634486212168399, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3710970688333222, 'r': 0.3097023331807505, 'f1': 0.3376314013032631}, 'combined': 0.22042257287156033, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
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 07:09:52.762175: step: 4/529, loss: 0.00568016991019249
2023-01-24 07:09:53.815677: step: 8/529, loss: 0.0037791873328387737
2023-01-24 07:09:54.893354: step: 12/529, loss: 0.015430057421326637
2023-01-24 07:09:55.951449: step: 16/529, loss: 0.00036626451765187085
2023-01-24 07:09:57.026663: step: 20/529, loss: 0.009316004812717438
2023-01-24 07:09:58.099084: step: 24/529, loss: 0.00023781387426424772
2023-01-24 07:09:59.158117: step: 28/529, loss: 0.0019802323076874018
2023-01-24 07:10:00.235107: step: 32/529, loss: 0.02349786087870598
2023-01-24 07:10:01.307963: step: 36/529, loss: 0.009819498285651207
2023-01-24 07:10:02.365112: step: 40/529, loss: 0.002291661687195301
2023-01-24 07:10:03.428454: step: 44/529, loss: 0.002832529367879033
2023-01-24 07:10:04.495549: step: 48/529, loss: 0.007768876384943724
2023-01-24 07:10:05.555789: step: 52/529, loss: 0.0015841801650822163
2023-01-24 07:10:06.635749: step: 56/529, loss: 0.00557374581694603
2023-01-24 07:10:07.704749: step: 60/529, loss: 0.004808449186384678
2023-01-24 07:10:08.771247: step: 64/529, loss: 0.005983045790344477
2023-01-24 07:10:09.836341: step: 68/529, loss: 0.041461579501628876
2023-01-24 07:10:10.904619: step: 72/529, loss: 0.0038062836974859238
2023-01-24 07:10:11.969783: step: 76/529, loss: 0.005338095128536224
2023-01-24 07:10:13.045850: step: 80/529, loss: 0.0025962344370782375
2023-01-24 07:10:14.103458: step: 84/529, loss: 0.0005924426950514317
2023-01-24 07:10:15.175753: step: 88/529, loss: 0.005933774169534445
2023-01-24 07:10:16.247030: step: 92/529, loss: 0.0009836549870669842
2023-01-24 07:10:17.311486: step: 96/529, loss: 0.025895144790410995
2023-01-24 07:10:18.376886: step: 100/529, loss: 0.0028382393065840006
2023-01-24 07:10:19.450588: step: 104/529, loss: 0.00791685190051794
2023-01-24 07:10:20.521324: step: 108/529, loss: 0.002369657391682267
2023-01-24 07:10:21.575603: step: 112/529, loss: 0.003230104921385646
2023-01-24 07:10:22.678453: step: 116/529, loss: 0.002270039636641741
2023-01-24 07:10:23.749349: step: 120/529, loss: 0.0024864375591278076
2023-01-24 07:10:24.806564: step: 124/529, loss: 0.004147215746343136
2023-01-24 07:10:25.865336: step: 128/529, loss: 0.007507805246859789
2023-01-24 07:10:26.933143: step: 132/529, loss: 0.0028371461667120457
2023-01-24 07:10:27.989240: step: 136/529, loss: 0.04736693948507309
2023-01-24 07:10:29.055110: step: 140/529, loss: 0.00560291251167655
2023-01-24 07:10:30.127215: step: 144/529, loss: 0.0023508346639573574
2023-01-24 07:10:31.223393: step: 148/529, loss: 0.005191101226955652
2023-01-24 07:10:32.286621: step: 152/529, loss: 0.013244339264929295
2023-01-24 07:10:33.340552: step: 156/529, loss: 0.003391327103599906
2023-01-24 07:10:34.393367: step: 160/529, loss: 0.09651968628168106
2023-01-24 07:10:35.442813: step: 164/529, loss: 0.002731872024014592
2023-01-24 07:10:36.523109: step: 168/529, loss: 0.06937011331319809
2023-01-24 07:10:37.588918: step: 172/529, loss: 0.0050599537789821625
2023-01-24 07:10:38.650147: step: 176/529, loss: 0.004609157331287861
2023-01-24 07:10:39.715742: step: 180/529, loss: 0.008236760273575783
2023-01-24 07:10:40.777936: step: 184/529, loss: 0.008219015784561634
2023-01-24 07:10:41.845423: step: 188/529, loss: 0.012265676632523537
2023-01-24 07:10:42.933045: step: 192/529, loss: 0.007208076771348715
2023-01-24 07:10:44.013388: step: 196/529, loss: 0.011508278548717499
2023-01-24 07:10:45.099107: step: 200/529, loss: 0.010133801028132439
2023-01-24 07:10:46.166409: step: 204/529, loss: 0.024479715153574944
2023-01-24 07:10:47.240091: step: 208/529, loss: 0.011863814666867256
2023-01-24 07:10:48.296903: step: 212/529, loss: 0.03410855680704117
2023-01-24 07:10:49.355364: step: 216/529, loss: 0.003080726834014058
2023-01-24 07:10:50.439164: step: 220/529, loss: 0.011270204558968544
2023-01-24 07:10:51.523882: step: 224/529, loss: 0.0021524641197174788
2023-01-24 07:10:52.606129: step: 228/529, loss: 0.003030849387869239
2023-01-24 07:10:53.677554: step: 232/529, loss: 0.012466098181903362
2023-01-24 07:10:54.751002: step: 236/529, loss: 0.005734369158744812
2023-01-24 07:10:55.815920: step: 240/529, loss: 0.0007453287253156304
2023-01-24 07:10:56.883640: step: 244/529, loss: 0.004105732310563326
2023-01-24 07:10:57.948628: step: 248/529, loss: 0.008348530158400536
2023-01-24 07:10:59.010227: step: 252/529, loss: 0.003066055942326784
2023-01-24 07:11:00.079668: step: 256/529, loss: 0.013963768258690834
2023-01-24 07:11:01.148255: step: 260/529, loss: 0.0021843169815838337
2023-01-24 07:11:02.222605: step: 264/529, loss: 0.009637662209570408
2023-01-24 07:11:03.298247: step: 268/529, loss: 0.0020488786976784468
2023-01-24 07:11:04.356931: step: 272/529, loss: 0.002763220341876149
2023-01-24 07:11:05.427678: step: 276/529, loss: 0.004496428184211254
2023-01-24 07:11:06.488366: step: 280/529, loss: 0.009399174712598324
2023-01-24 07:11:07.559524: step: 284/529, loss: 0.011515219695866108
2023-01-24 07:11:08.630105: step: 288/529, loss: 0.019486650824546814
2023-01-24 07:11:09.688586: step: 292/529, loss: 0.010760155506432056
2023-01-24 07:11:10.765819: step: 296/529, loss: 0.007388952653855085
2023-01-24 07:11:11.853438: step: 300/529, loss: 0.001067520584911108
2023-01-24 07:11:12.933017: step: 304/529, loss: 0.013397138565778732
2023-01-24 07:11:14.017653: step: 308/529, loss: 0.0052513135597109795
2023-01-24 07:11:15.084573: step: 312/529, loss: 0.016393117606639862
2023-01-24 07:11:16.148494: step: 316/529, loss: 0.0031123885419219732
2023-01-24 07:11:17.222335: step: 320/529, loss: 0.0034190292935818434
2023-01-24 07:11:18.315549: step: 324/529, loss: 0.005750210955739021
2023-01-24 07:11:19.387186: step: 328/529, loss: 0.041475702077150345
2023-01-24 07:11:20.469483: step: 332/529, loss: 0.0017468280857428908
2023-01-24 07:11:21.550700: step: 336/529, loss: 0.0007696906686760485
2023-01-24 07:11:22.618643: step: 340/529, loss: 0.01678144372999668
2023-01-24 07:11:23.693453: step: 344/529, loss: 0.005581000354140997
2023-01-24 07:11:24.765837: step: 348/529, loss: 0.005104969721287489
2023-01-24 07:11:25.837215: step: 352/529, loss: 0.009868049994111061
2023-01-24 07:11:26.939779: step: 356/529, loss: 0.004311675671488047
2023-01-24 07:11:28.001150: step: 360/529, loss: 0.0024313824251294136
2023-01-24 07:11:29.080247: step: 364/529, loss: 0.00486027542501688
2023-01-24 07:11:30.154901: step: 368/529, loss: 0.003816516138613224
2023-01-24 07:11:31.214621: step: 372/529, loss: 0.0021876327227801085
2023-01-24 07:11:32.285627: step: 376/529, loss: 0.005908139981329441
2023-01-24 07:11:33.358601: step: 380/529, loss: 0.00656081223860383
2023-01-24 07:11:34.439674: step: 384/529, loss: 0.023145845159888268
2023-01-24 07:11:35.518928: step: 388/529, loss: 0.013495726510882378
2023-01-24 07:11:36.591405: step: 392/529, loss: 0.0008799554198049009
2023-01-24 07:11:37.655209: step: 396/529, loss: 0.012078013271093369
2023-01-24 07:11:38.744812: step: 400/529, loss: 0.00843176431953907
2023-01-24 07:11:39.818026: step: 404/529, loss: 0.0032087743747979403
2023-01-24 07:11:40.905601: step: 408/529, loss: 0.013576321303844452
2023-01-24 07:11:42.002415: step: 412/529, loss: 0.0016561581287533045
2023-01-24 07:11:43.099882: step: 416/529, loss: 0.015348426066339016
2023-01-24 07:11:44.168099: step: 420/529, loss: 0.005162274930626154
2023-01-24 07:11:45.250468: step: 424/529, loss: 0.010190640576183796
2023-01-24 07:11:46.314359: step: 428/529, loss: 0.0005091220373287797
2023-01-24 07:11:47.384267: step: 432/529, loss: 0.0019746189936995506
2023-01-24 07:11:48.457702: step: 436/529, loss: 0.021828433498740196
2023-01-24 07:11:49.535508: step: 440/529, loss: 0.005172313190996647
2023-01-24 07:11:50.619126: step: 444/529, loss: 0.0010447107488289475
2023-01-24 07:11:51.705927: step: 448/529, loss: 0.007668701000511646
2023-01-24 07:11:52.776059: step: 452/529, loss: 0.01001465693116188
2023-01-24 07:11:53.824811: step: 456/529, loss: 0.014296041801571846
2023-01-24 07:11:54.917792: step: 460/529, loss: 0.012382669374346733
2023-01-24 07:11:56.001126: step: 464/529, loss: 0.0018333930056542158
2023-01-24 07:11:57.069109: step: 468/529, loss: 0.00012185341620352119
2023-01-24 07:11:58.131199: step: 472/529, loss: 0.010263880714774132
2023-01-24 07:11:59.221394: step: 476/529, loss: 0.029986437410116196
2023-01-24 07:12:00.303377: step: 480/529, loss: 0.003973283804953098
2023-01-24 07:12:01.375380: step: 484/529, loss: 0.02596515417098999
2023-01-24 07:12:02.469636: step: 488/529, loss: 0.005611129105091095
2023-01-24 07:12:03.540512: step: 492/529, loss: 0.004910180810838938
2023-01-24 07:12:04.624248: step: 496/529, loss: 0.022428816184401512
2023-01-24 07:12:05.713915: step: 500/529, loss: 0.029541783034801483
2023-01-24 07:12:06.774385: step: 504/529, loss: 0.0011173203820362687
2023-01-24 07:12:07.845302: step: 508/529, loss: 0.005091271363198757
2023-01-24 07:12:08.919746: step: 512/529, loss: 0.0012395735830068588
2023-01-24 07:12:09.999332: step: 516/529, loss: 0.003120470093563199
2023-01-24 07:12:11.081858: step: 520/529, loss: 0.009806467220187187
2023-01-24 07:12:12.157385: step: 524/529, loss: 0.01977851800620556
2023-01-24 07:12:13.243845: step: 528/529, loss: 0.0020553497597575188
2023-01-24 07:12:14.356520: step: 532/529, loss: 0.005043101031333208
2023-01-24 07:12:15.445956: step: 536/529, loss: 0.001568490406498313
2023-01-24 07:12:16.515834: step: 540/529, loss: 0.009771560318768024
2023-01-24 07:12:17.595034: step: 544/529, loss: 0.0005327824037522078
2023-01-24 07:12:18.665823: step: 548/529, loss: 0.00030661284108646214
2023-01-24 07:12:19.753587: step: 552/529, loss: 0.005557921249419451
2023-01-24 07:12:20.829705: step: 556/529, loss: 0.027158109471201897
2023-01-24 07:12:21.915926: step: 560/529, loss: 0.007757531013339758
2023-01-24 07:12:23.009817: step: 564/529, loss: 4.151556368015008e-06
2023-01-24 07:12:24.092228: step: 568/529, loss: 0.002892021555453539
2023-01-24 07:12:25.165619: step: 572/529, loss: 0.019166069105267525
2023-01-24 07:12:26.237752: step: 576/529, loss: 0.00070958212018013
2023-01-24 07:12:27.314582: step: 580/529, loss: 0.0032791781704872847
2023-01-24 07:12:28.398564: step: 584/529, loss: 0.03315307945013046
2023-01-24 07:12:29.485007: step: 588/529, loss: 0.027390863746404648
2023-01-24 07:12:30.572845: step: 592/529, loss: 0.0028754703234881163
2023-01-24 07:12:31.665873: step: 596/529, loss: 0.018367497250437737
2023-01-24 07:12:32.748673: step: 600/529, loss: 0.007619834970682859
2023-01-24 07:12:33.838565: step: 604/529, loss: 0.027885867282748222
2023-01-24 07:12:34.905427: step: 608/529, loss: 0.0044440398924052715
2023-01-24 07:12:35.973868: step: 612/529, loss: 0.007782158441841602
2023-01-24 07:12:37.055299: step: 616/529, loss: 0.012843900360167027
2023-01-24 07:12:38.160960: step: 620/529, loss: 0.008705461397767067
2023-01-24 07:12:39.239092: step: 624/529, loss: 0.011032906360924244
2023-01-24 07:12:40.311114: step: 628/529, loss: 0.002136365044862032
2023-01-24 07:12:41.403466: step: 632/529, loss: 0.004624108783900738
2023-01-24 07:12:42.486784: step: 636/529, loss: 0.0007290123030543327
2023-01-24 07:12:43.586161: step: 640/529, loss: 0.05365367233753204
2023-01-24 07:12:44.669517: step: 644/529, loss: 0.01255691796541214
2023-01-24 07:12:45.759735: step: 648/529, loss: 0.0006463015452027321
2023-01-24 07:12:46.853422: step: 652/529, loss: 0.006273298058658838
2023-01-24 07:12:47.935494: step: 656/529, loss: 0.0043082935735583305
2023-01-24 07:12:49.032709: step: 660/529, loss: 0.009441153146326542
2023-01-24 07:12:50.100999: step: 664/529, loss: 0.01002568006515503
2023-01-24 07:12:51.179353: step: 668/529, loss: 0.006818255875259638
2023-01-24 07:12:52.280210: step: 672/529, loss: 0.012039298191666603
2023-01-24 07:12:53.361232: step: 676/529, loss: 0.0032885251566767693
2023-01-24 07:12:54.447648: step: 680/529, loss: 0.00021989028027746826
2023-01-24 07:12:55.525890: step: 684/529, loss: 0.003094775602221489
2023-01-24 07:12:56.596671: step: 688/529, loss: 0.004029995761811733
2023-01-24 07:12:57.674002: step: 692/529, loss: 0.021245555952191353
2023-01-24 07:12:58.761160: step: 696/529, loss: 0.004962686914950609
2023-01-24 07:12:59.867965: step: 700/529, loss: 0.008309044875204563
2023-01-24 07:13:00.949632: step: 704/529, loss: 0.009739680215716362
2023-01-24 07:13:02.039526: step: 708/529, loss: 0.0043122423812747
2023-01-24 07:13:03.117716: step: 712/529, loss: 0.0180693157017231
2023-01-24 07:13:04.202887: step: 716/529, loss: 0.0024974641855806112
2023-01-24 07:13:05.283096: step: 720/529, loss: 0.010176624171435833
2023-01-24 07:13:06.370343: step: 724/529, loss: 0.001968876225873828
2023-01-24 07:13:07.443349: step: 728/529, loss: 0.006001739297062159
2023-01-24 07:13:08.524339: step: 732/529, loss: 0.0044102114625275135
2023-01-24 07:13:09.617481: step: 736/529, loss: 0.0091475248336792
2023-01-24 07:13:10.698792: step: 740/529, loss: 0.015723884105682373
2023-01-24 07:13:11.783866: step: 744/529, loss: 0.012495236471295357
2023-01-24 07:13:12.887759: step: 748/529, loss: 0.006256813183426857
2023-01-24 07:13:13.952766: step: 752/529, loss: 0.004281683824956417
2023-01-24 07:13:15.032361: step: 756/529, loss: 0.016755009070038795
2023-01-24 07:13:16.105400: step: 760/529, loss: 0.010574867017567158
2023-01-24 07:13:17.189800: step: 764/529, loss: 0.005176052916795015
2023-01-24 07:13:18.269348: step: 768/529, loss: 0.006731318309903145
2023-01-24 07:13:19.364009: step: 772/529, loss: 0.008975555188953876
2023-01-24 07:13:20.443326: step: 776/529, loss: 0.0026803144719451666
2023-01-24 07:13:21.519703: step: 780/529, loss: 0.01217376347631216
2023-01-24 07:13:22.597930: step: 784/529, loss: 0.006609021220356226
2023-01-24 07:13:23.668899: step: 788/529, loss: 0.0013147088466212153
2023-01-24 07:13:24.765284: step: 792/529, loss: 0.0032262145541608334
2023-01-24 07:13:25.843536: step: 796/529, loss: 0.0058262962847948074
2023-01-24 07:13:26.920998: step: 800/529, loss: 0.001048209727741778
2023-01-24 07:13:27.989148: step: 804/529, loss: 0.00857475120574236
2023-01-24 07:13:29.077423: step: 808/529, loss: 0.02058105729520321
2023-01-24 07:13:30.152147: step: 812/529, loss: 0.009505290538072586
2023-01-24 07:13:31.251229: step: 816/529, loss: 0.000214135114219971
2023-01-24 07:13:32.331804: step: 820/529, loss: 0.017492523416876793
2023-01-24 07:13:33.407986: step: 824/529, loss: 0.0019358092686161399
2023-01-24 07:13:34.478817: step: 828/529, loss: 0.0013326627667993307
2023-01-24 07:13:35.565150: step: 832/529, loss: 0.005512428004294634
2023-01-24 07:13:36.642599: step: 836/529, loss: 0.0008948629256337881
2023-01-24 07:13:37.740547: step: 840/529, loss: 0.02665616013109684
2023-01-24 07:13:38.799808: step: 844/529, loss: 0.00874472688883543
2023-01-24 07:13:39.891191: step: 848/529, loss: 0.005078576970845461
2023-01-24 07:13:40.980958: step: 852/529, loss: 0.015749715268611908
2023-01-24 07:13:42.055049: step: 856/529, loss: 0.003927599173039198
2023-01-24 07:13:43.131066: step: 860/529, loss: 0.0026331909466534853
2023-01-24 07:13:44.211071: step: 864/529, loss: 0.0033662368077784777
2023-01-24 07:13:45.288996: step: 868/529, loss: 0.0042876508086919785
2023-01-24 07:13:46.377017: step: 872/529, loss: 0.013326133601367474
2023-01-24 07:13:47.464299: step: 876/529, loss: 0.02533111348748207
2023-01-24 07:13:48.546851: step: 880/529, loss: 0.004523855168372393
2023-01-24 07:13:49.628614: step: 884/529, loss: 0.0015018930425867438
2023-01-24 07:13:50.721838: step: 888/529, loss: 0.004736669827252626
2023-01-24 07:13:51.806234: step: 892/529, loss: 0.004544378258287907
2023-01-24 07:13:52.892016: step: 896/529, loss: 0.0035141941625624895
2023-01-24 07:13:53.972184: step: 900/529, loss: 0.014882017858326435
2023-01-24 07:13:55.047787: step: 904/529, loss: 0.027485407888889313
2023-01-24 07:13:56.120502: step: 908/529, loss: 0.0007455486920662224
2023-01-24 07:13:57.196221: step: 912/529, loss: 0.014828327111899853
2023-01-24 07:13:58.283993: step: 916/529, loss: 0.024159684777259827
2023-01-24 07:13:59.376317: step: 920/529, loss: 0.0006692619062960148
2023-01-24 07:14:00.467726: step: 924/529, loss: 0.006813994143158197
2023-01-24 07:14:01.567734: step: 928/529, loss: 0.002748151309788227
2023-01-24 07:14:02.630773: step: 932/529, loss: 0.003093400038778782
2023-01-24 07:14:03.721660: step: 936/529, loss: 0.011748131364583969
2023-01-24 07:14:04.799708: step: 940/529, loss: 0.016738710924983025
2023-01-24 07:14:05.878298: step: 944/529, loss: 0.0034232211764901876
2023-01-24 07:14:06.957590: step: 948/529, loss: 0.017535418272018433
2023-01-24 07:14:08.032092: step: 952/529, loss: 0.020190685987472534
2023-01-24 07:14:09.109889: step: 956/529, loss: 0.00412218039855361
2023-01-24 07:14:10.199961: step: 960/529, loss: 0.0016655544750392437
2023-01-24 07:14:11.283075: step: 964/529, loss: 0.023878321051597595
2023-01-24 07:14:12.342244: step: 968/529, loss: 0.0038219469133764505
2023-01-24 07:14:13.443522: step: 972/529, loss: 0.0014707164373248816
2023-01-24 07:14:14.544122: step: 976/529, loss: 0.016964400187134743
2023-01-24 07:14:15.621200: step: 980/529, loss: 0.005282182712107897
2023-01-24 07:14:16.701133: step: 984/529, loss: 0.0019000746542587876
2023-01-24 07:14:17.775601: step: 988/529, loss: 0.016119830310344696
2023-01-24 07:14:18.857211: step: 992/529, loss: 0.0033304672688245773
2023-01-24 07:14:19.931462: step: 996/529, loss: 0.0003596344031393528
2023-01-24 07:14:21.006150: step: 1000/529, loss: 0.014452248811721802
2023-01-24 07:14:22.078010: step: 1004/529, loss: 0.00019113316375296563
2023-01-24 07:14:23.147967: step: 1008/529, loss: 0.0005143745802342892
2023-01-24 07:14:24.222740: step: 1012/529, loss: 0.006043735425919294
2023-01-24 07:14:25.299837: step: 1016/529, loss: 0.010864400304853916
2023-01-24 07:14:26.402410: step: 1020/529, loss: 0.003958025481551886
2023-01-24 07:14:27.504063: step: 1024/529, loss: 0.0020520146936178207
2023-01-24 07:14:28.588608: step: 1028/529, loss: 0.0029882951639592648
2023-01-24 07:14:29.673379: step: 1032/529, loss: 0.002661942271515727
2023-01-24 07:14:30.758925: step: 1036/529, loss: 0.00633154297247529
2023-01-24 07:14:31.836017: step: 1040/529, loss: 0.002098259748890996
2023-01-24 07:14:32.896036: step: 1044/529, loss: 0.008438413962721825
2023-01-24 07:14:33.956077: step: 1048/529, loss: 0.007111316546797752
2023-01-24 07:14:35.044300: step: 1052/529, loss: 0.0058357128873467445
2023-01-24 07:14:36.131021: step: 1056/529, loss: 0.00228347210213542
2023-01-24 07:14:37.200179: step: 1060/529, loss: 0.0008982159197330475
2023-01-24 07:14:38.283435: step: 1064/529, loss: 0.008492826484143734
2023-01-24 07:14:39.344068: step: 1068/529, loss: 0.006082760635763407
2023-01-24 07:14:40.425876: step: 1072/529, loss: 0.004790329374372959
2023-01-24 07:14:41.502163: step: 1076/529, loss: 0.009013747796416283
2023-01-24 07:14:42.577243: step: 1080/529, loss: 0.003286935854703188
2023-01-24 07:14:43.685710: step: 1084/529, loss: 0.0022279697004705667
2023-01-24 07:14:44.764225: step: 1088/529, loss: 0.005761610809713602
2023-01-24 07:14:45.836579: step: 1092/529, loss: 0.005899119656533003
2023-01-24 07:14:46.916204: step: 1096/529, loss: 0.0059688580222427845
2023-01-24 07:14:47.986332: step: 1100/529, loss: 0.003196155186742544
2023-01-24 07:14:49.066575: step: 1104/529, loss: 0.0008680655155330896
2023-01-24 07:14:50.137572: step: 1108/529, loss: 0.0014954046346247196
2023-01-24 07:14:51.233841: step: 1112/529, loss: 0.01368359848856926
2023-01-24 07:14:52.309282: step: 1116/529, loss: 0.007206558249890804
2023-01-24 07:14:53.384281: step: 1120/529, loss: 0.004152627661824226
2023-01-24 07:14:54.448652: step: 1124/529, loss: 0.011732162907719612
2023-01-24 07:14:55.529300: step: 1128/529, loss: 0.009585341438651085
2023-01-24 07:14:56.596453: step: 1132/529, loss: 0.01096218079328537
2023-01-24 07:14:57.681230: step: 1136/529, loss: 0.0029368819668889046
2023-01-24 07:14:58.760794: step: 1140/529, loss: 0.008652622811496258
2023-01-24 07:14:59.824370: step: 1144/529, loss: 0.0013932700967416167
2023-01-24 07:15:00.901652: step: 1148/529, loss: 0.009043017402291298
2023-01-24 07:15:01.972834: step: 1152/529, loss: 0.012237952090799809
2023-01-24 07:15:03.064971: step: 1156/529, loss: 0.0013904266525059938
2023-01-24 07:15:04.157739: step: 1160/529, loss: 0.0032105050049722195
2023-01-24 07:15:05.225089: step: 1164/529, loss: 0.007998811081051826
2023-01-24 07:15:06.302337: step: 1168/529, loss: 0.002177305519580841
2023-01-24 07:15:07.360903: step: 1172/529, loss: 0.0014117809478193521
2023-01-24 07:15:08.432956: step: 1176/529, loss: 0.02790038473904133
2023-01-24 07:15:09.501572: step: 1180/529, loss: 0.0012378093088045716
2023-01-24 07:15:10.574664: step: 1184/529, loss: 0.0012186041567474604
2023-01-24 07:15:11.644106: step: 1188/529, loss: 0.006064120680093765
2023-01-24 07:15:12.704921: step: 1192/529, loss: 0.0009852745570242405
2023-01-24 07:15:13.769771: step: 1196/529, loss: 0.006969446316361427
2023-01-24 07:15:14.844886: step: 1200/529, loss: 0.006442433223128319
2023-01-24 07:15:15.902834: step: 1204/529, loss: 0.013939647004008293
2023-01-24 07:15:16.971364: step: 1208/529, loss: 0.0012466382468119264
2023-01-24 07:15:18.043653: step: 1212/529, loss: 0.006464638747274876
2023-01-24 07:15:19.110416: step: 1216/529, loss: 0.010552704334259033
2023-01-24 07:15:20.198455: step: 1220/529, loss: 0.01777702011168003
2023-01-24 07:15:21.282645: step: 1224/529, loss: 0.0006012205849401653
2023-01-24 07:15:22.353751: step: 1228/529, loss: 0.0002604760811664164
2023-01-24 07:15:23.434219: step: 1232/529, loss: 0.000569429190363735
2023-01-24 07:15:24.505642: step: 1236/529, loss: 0.01760999858379364
2023-01-24 07:15:25.579673: step: 1240/529, loss: 0.0448414571583271
2023-01-24 07:15:26.649734: step: 1244/529, loss: 0.002511577680706978
2023-01-24 07:15:27.733834: step: 1248/529, loss: 0.002938677091151476
2023-01-24 07:15:28.829032: step: 1252/529, loss: 0.016430296003818512
2023-01-24 07:15:29.920555: step: 1256/529, loss: 0.00340069318190217
2023-01-24 07:15:30.986348: step: 1260/529, loss: 0.009581729769706726
2023-01-24 07:15:32.071002: step: 1264/529, loss: 0.00018196339078713208
2023-01-24 07:15:33.146058: step: 1268/529, loss: 0.00011938531679334119
2023-01-24 07:15:34.223367: step: 1272/529, loss: 0.0028011722024530172
2023-01-24 07:15:35.286594: step: 1276/529, loss: 0.011804710142314434
2023-01-24 07:15:36.353204: step: 1280/529, loss: 0.004475636873394251
2023-01-24 07:15:37.426946: step: 1284/529, loss: 0.007032283581793308
2023-01-24 07:15:38.517034: step: 1288/529, loss: 0.000515773834194988
2023-01-24 07:15:39.591935: step: 1292/529, loss: 0.019129138439893723
2023-01-24 07:15:40.674722: step: 1296/529, loss: 0.006546602584421635
2023-01-24 07:15:41.755567: step: 1300/529, loss: 0.015814706683158875
2023-01-24 07:15:42.856850: step: 1304/529, loss: 0.0037350074853748083
2023-01-24 07:15:43.921457: step: 1308/529, loss: 0.012844981625676155
2023-01-24 07:15:44.989580: step: 1312/529, loss: 0.015001154504716396
2023-01-24 07:15:46.062632: step: 1316/529, loss: 0.0049246507696807384
2023-01-24 07:15:47.131898: step: 1320/529, loss: 0.002503888914361596
2023-01-24 07:15:48.196666: step: 1324/529, loss: 0.0045127859339118
2023-01-24 07:15:49.266902: step: 1328/529, loss: 0.009251574985682964
2023-01-24 07:15:50.329228: step: 1332/529, loss: 0.00950449239462614
2023-01-24 07:15:51.384592: step: 1336/529, loss: 0.007390092592686415
2023-01-24 07:15:52.456935: step: 1340/529, loss: 0.009491657838225365
2023-01-24 07:15:53.522160: step: 1344/529, loss: 0.023269934579730034
2023-01-24 07:15:54.582997: step: 1348/529, loss: 0.002573844976723194
2023-01-24 07:15:55.661903: step: 1352/529, loss: 0.02060754783451557
2023-01-24 07:15:56.748427: step: 1356/529, loss: 0.004539800342172384
2023-01-24 07:15:57.841182: step: 1360/529, loss: 0.007307715248316526
2023-01-24 07:15:58.912073: step: 1364/529, loss: 0.0040616742335259914
2023-01-24 07:15:59.984216: step: 1368/529, loss: 0.0008702565683051944
2023-01-24 07:16:01.049217: step: 1372/529, loss: 0.0022693159990012646
2023-01-24 07:16:02.118486: step: 1376/529, loss: 0.015980953350663185
2023-01-24 07:16:03.184931: step: 1380/529, loss: 0.04366021603345871
2023-01-24 07:16:04.249198: step: 1384/529, loss: 0.00546699995175004
2023-01-24 07:16:05.305515: step: 1388/529, loss: 0.006896627135574818
2023-01-24 07:16:06.404173: step: 1392/529, loss: 0.01586287096142769
2023-01-24 07:16:07.459261: step: 1396/529, loss: 0.0013543320819735527
2023-01-24 07:16:08.508441: step: 1400/529, loss: 0.003794848918914795
2023-01-24 07:16:09.573304: step: 1404/529, loss: 0.005269336514174938
2023-01-24 07:16:10.640059: step: 1408/529, loss: 0.0042932601645588875
2023-01-24 07:16:11.689749: step: 1412/529, loss: 0.004138121381402016
2023-01-24 07:16:12.763387: step: 1416/529, loss: 0.0054690176621079445
2023-01-24 07:16:13.852352: step: 1420/529, loss: 0.022345731034874916
2023-01-24 07:16:14.929322: step: 1424/529, loss: 0.0009192422730848193
2023-01-24 07:16:15.972693: step: 1428/529, loss: 0.002709059277549386
2023-01-24 07:16:17.054974: step: 1432/529, loss: 0.007847032509744167
2023-01-24 07:16:18.140149: step: 1436/529, loss: 0.032989751547575
2023-01-24 07:16:19.227427: step: 1440/529, loss: 0.007617088500410318
2023-01-24 07:16:20.304611: step: 1444/529, loss: 0.006016429979354143
2023-01-24 07:16:21.369546: step: 1448/529, loss: 0.004423749167472124
2023-01-24 07:16:22.429574: step: 1452/529, loss: 0.0006823095609433949
2023-01-24 07:16:23.500515: step: 1456/529, loss: 0.0030739593785256147
2023-01-24 07:16:24.563836: step: 1460/529, loss: 0.0021899263374507427
2023-01-24 07:16:25.645495: step: 1464/529, loss: 0.005480119958519936
2023-01-24 07:16:26.720402: step: 1468/529, loss: 0.02652132697403431
2023-01-24 07:16:27.798339: step: 1472/529, loss: 0.005870181601494551
2023-01-24 07:16:28.861643: step: 1476/529, loss: 0.0050626457668840885
2023-01-24 07:16:29.948372: step: 1480/529, loss: 0.008457575924694538
2023-01-24 07:16:31.019188: step: 1484/529, loss: 0.02206493727862835
2023-01-24 07:16:32.079961: step: 1488/529, loss: 0.011269577778875828
2023-01-24 07:16:33.159243: step: 1492/529, loss: 0.0010914630256593227
2023-01-24 07:16:34.239741: step: 1496/529, loss: 0.007932956330478191
2023-01-24 07:16:35.305600: step: 1500/529, loss: 0.0023037916980683804
2023-01-24 07:16:36.397742: step: 1504/529, loss: 0.006315466947853565
2023-01-24 07:16:37.471179: step: 1508/529, loss: 0.005262590479105711
2023-01-24 07:16:38.529821: step: 1512/529, loss: 0.0
2023-01-24 07:16:39.598832: step: 1516/529, loss: 0.00033349369186908007
2023-01-24 07:16:40.672154: step: 1520/529, loss: 0.005749932955950499
2023-01-24 07:16:41.756926: step: 1524/529, loss: 0.002397337928414345
2023-01-24 07:16:42.874645: step: 1528/529, loss: 0.00247242022305727
2023-01-24 07:16:43.924102: step: 1532/529, loss: 0.012600021436810493
2023-01-24 07:16:44.997132: step: 1536/529, loss: 0.018075793981552124
2023-01-24 07:16:46.083484: step: 1540/529, loss: 0.006383591331541538
2023-01-24 07:16:47.152535: step: 1544/529, loss: 0.002323059132322669
2023-01-24 07:16:48.227896: step: 1548/529, loss: 0.014821457676589489
2023-01-24 07:16:49.294344: step: 1552/529, loss: 0.00607643648982048
2023-01-24 07:16:50.375753: step: 1556/529, loss: 0.003533856011927128
2023-01-24 07:16:51.430010: step: 1560/529, loss: 0.04687945917248726
2023-01-24 07:16:52.510231: step: 1564/529, loss: 0.03262916952371597
2023-01-24 07:16:53.585260: step: 1568/529, loss: 0.004752876702696085
2023-01-24 07:16:54.644197: step: 1572/529, loss: 0.0013683937722817063
2023-01-24 07:16:55.704332: step: 1576/529, loss: 0.006566714495420456
2023-01-24 07:16:56.777505: step: 1580/529, loss: 0.01917283982038498
2023-01-24 07:16:57.869023: step: 1584/529, loss: 0.003517351346090436
2023-01-24 07:16:58.942549: step: 1588/529, loss: 0.00024256319738924503
2023-01-24 07:16:59.998408: step: 1592/529, loss: 0.0010324452305212617
2023-01-24 07:17:01.071527: step: 1596/529, loss: 0.0018782115075737238
2023-01-24 07:17:02.164217: step: 1600/529, loss: 0.07054159790277481
2023-01-24 07:17:03.234877: step: 1604/529, loss: 0.011130588129162788
2023-01-24 07:17:04.308108: step: 1608/529, loss: 0.0020678380969911814
2023-01-24 07:17:05.372931: step: 1612/529, loss: 0.005637689493596554
2023-01-24 07:17:06.452662: step: 1616/529, loss: 0.004181877709925175
2023-01-24 07:17:07.530133: step: 1620/529, loss: 0.006981275975704193
2023-01-24 07:17:08.596185: step: 1624/529, loss: 0.004725219216197729
2023-01-24 07:17:09.645725: step: 1628/529, loss: 0.006260905880481005
2023-01-24 07:17:10.710332: step: 1632/529, loss: 0.0015165150398388505
2023-01-24 07:17:11.795312: step: 1636/529, loss: 0.0038289874792099
2023-01-24 07:17:12.887738: step: 1640/529, loss: 0.004182036500424147
2023-01-24 07:17:13.952987: step: 1644/529, loss: 0.004378526005893946
2023-01-24 07:17:15.022289: step: 1648/529, loss: 0.004563461989164352
2023-01-24 07:17:16.095011: step: 1652/529, loss: 0.005700966808944941
2023-01-24 07:17:17.184298: step: 1656/529, loss: 0.009548171423375607
2023-01-24 07:17:18.259355: step: 1660/529, loss: 0.0041475142352283
2023-01-24 07:17:19.325806: step: 1664/529, loss: 0.05564342439174652
2023-01-24 07:17:20.379011: step: 1668/529, loss: 0.00832329224795103
2023-01-24 07:17:21.446400: step: 1672/529, loss: 0.004141243640333414
2023-01-24 07:17:22.526588: step: 1676/529, loss: 0.0066801016218960285
2023-01-24 07:17:23.613757: step: 1680/529, loss: 0.0024728206917643547
2023-01-24 07:17:24.700858: step: 1684/529, loss: 0.006450298707932234
2023-01-24 07:17:25.770402: step: 1688/529, loss: 0.006854694336652756
2023-01-24 07:17:26.849621: step: 1692/529, loss: 0.006273137405514717
2023-01-24 07:17:27.937866: step: 1696/529, loss: 0.002281331457197666
2023-01-24 07:17:29.000022: step: 1700/529, loss: 0.0009556938894093037
2023-01-24 07:17:30.077682: step: 1704/529, loss: 0.012507337145507336
2023-01-24 07:17:31.152124: step: 1708/529, loss: 0.0009623004589229822
2023-01-24 07:17:32.243394: step: 1712/529, loss: 0.0036687704268842936
2023-01-24 07:17:33.341687: step: 1716/529, loss: 0.00023484372650273144
2023-01-24 07:17:34.407572: step: 1720/529, loss: 0.0043158261105418205
2023-01-24 07:17:35.471670: step: 1724/529, loss: 0.010423144325613976
2023-01-24 07:17:36.541265: step: 1728/529, loss: 0.009649207815527916
2023-01-24 07:17:37.614646: step: 1732/529, loss: 0.015450162813067436
2023-01-24 07:17:38.668384: step: 1736/529, loss: 0.0005176262930035591
2023-01-24 07:17:39.740073: step: 1740/529, loss: 0.004055425059050322
2023-01-24 07:17:40.809996: step: 1744/529, loss: 0.009960419498383999
2023-01-24 07:17:41.891955: step: 1748/529, loss: 0.026089394465088844
2023-01-24 07:17:42.959964: step: 1752/529, loss: 0.016885975375771523
2023-01-24 07:17:44.034980: step: 1756/529, loss: 0.004090787842869759
2023-01-24 07:17:45.099686: step: 1760/529, loss: 0.0048917243257164955
2023-01-24 07:17:46.175528: step: 1764/529, loss: 0.010180746205151081
2023-01-24 07:17:47.250317: step: 1768/529, loss: 0.003251784946769476
2023-01-24 07:17:48.314225: step: 1772/529, loss: 0.0033885561861097813
2023-01-24 07:17:49.392989: step: 1776/529, loss: 0.006806801538914442
2023-01-24 07:17:50.476193: step: 1780/529, loss: 0.010073409415781498
2023-01-24 07:17:51.551542: step: 1784/529, loss: 0.009834295138716698
2023-01-24 07:17:52.641416: step: 1788/529, loss: 0.006426077801734209
2023-01-24 07:17:53.728287: step: 1792/529, loss: 0.027749070897698402
2023-01-24 07:17:54.807719: step: 1796/529, loss: 0.02370607480406761
2023-01-24 07:17:55.907863: step: 1800/529, loss: 0.005324054043740034
2023-01-24 07:17:56.989869: step: 1804/529, loss: 0.0025302397552877665
2023-01-24 07:17:58.085702: step: 1808/529, loss: 0.0009093704866245389
2023-01-24 07:17:59.172792: step: 1812/529, loss: 0.0007821667823009193
2023-01-24 07:18:00.243249: step: 1816/529, loss: 0.006052022334188223
2023-01-24 07:18:01.301466: step: 1820/529, loss: 0.00571755226701498
2023-01-24 07:18:02.368305: step: 1824/529, loss: 0.00827968493103981
2023-01-24 07:18:03.438463: step: 1828/529, loss: 0.006284003611654043
2023-01-24 07:18:04.517274: step: 1832/529, loss: 0.002431155415251851
2023-01-24 07:18:05.587753: step: 1836/529, loss: 0.008903119713068008
2023-01-24 07:18:06.647376: step: 1840/529, loss: 0.001334880362264812
2023-01-24 07:18:07.742312: step: 1844/529, loss: 0.006673356983810663
2023-01-24 07:18:08.819003: step: 1848/529, loss: 0.0008704556967131793
2023-01-24 07:18:09.903805: step: 1852/529, loss: 0.009662069380283356
2023-01-24 07:18:10.982311: step: 1856/529, loss: 0.010032053105533123
2023-01-24 07:18:12.046189: step: 1860/529, loss: 0.006116312928497791
2023-01-24 07:18:13.139266: step: 1864/529, loss: 0.002026266884058714
2023-01-24 07:18:14.225232: step: 1868/529, loss: 0.04767926037311554
2023-01-24 07:18:15.301951: step: 1872/529, loss: 0.0015611908165737987
2023-01-24 07:18:16.386791: step: 1876/529, loss: 0.0031267593149095774
2023-01-24 07:18:17.469527: step: 1880/529, loss: 0.005828710738569498
2023-01-24 07:18:18.539252: step: 1884/529, loss: 0.003626617370173335
2023-01-24 07:18:19.613137: step: 1888/529, loss: 0.004030480049550533
2023-01-24 07:18:20.704861: step: 1892/529, loss: 0.010975723154842854
2023-01-24 07:18:21.769098: step: 1896/529, loss: 0.0027940827421844006
2023-01-24 07:18:22.842763: step: 1900/529, loss: 0.0009849475463852286
2023-01-24 07:18:23.914190: step: 1904/529, loss: 0.007541480008512735
2023-01-24 07:18:24.986453: step: 1908/529, loss: 0.005235531833022833
2023-01-24 07:18:26.067331: step: 1912/529, loss: 0.003981713205575943
2023-01-24 07:18:27.125230: step: 1916/529, loss: 0.05958854779601097
2023-01-24 07:18:28.190765: step: 1920/529, loss: 0.007360525894910097
2023-01-24 07:18:29.258959: step: 1924/529, loss: 0.013344666920602322
2023-01-24 07:18:30.335629: step: 1928/529, loss: 0.0014688002411276102
2023-01-24 07:18:31.406170: step: 1932/529, loss: 0.0036034630611538887
2023-01-24 07:18:32.467582: step: 1936/529, loss: 0.009805344976484776
2023-01-24 07:18:33.543260: step: 1940/529, loss: 0.002524876967072487
2023-01-24 07:18:34.604996: step: 1944/529, loss: 0.004475317429751158
2023-01-24 07:18:35.671450: step: 1948/529, loss: 0.0008972417563199997
2023-01-24 07:18:36.758281: step: 1952/529, loss: 0.004966420587152243
2023-01-24 07:18:37.836992: step: 1956/529, loss: 0.006108081433922052
2023-01-24 07:18:38.911771: step: 1960/529, loss: 0.01398506760597229
2023-01-24 07:18:39.985283: step: 1964/529, loss: 0.009954427368938923
2023-01-24 07:18:41.054859: step: 1968/529, loss: 0.004458195064216852
2023-01-24 07:18:42.126945: step: 1972/529, loss: 0.0044325548224151134
2023-01-24 07:18:43.207641: step: 1976/529, loss: 0.011509330943226814
2023-01-24 07:18:44.289099: step: 1980/529, loss: 0.017971521243453026
2023-01-24 07:18:45.370836: step: 1984/529, loss: 0.005178586579859257
2023-01-24 07:18:46.445033: step: 1988/529, loss: 0.0030492593068629503
2023-01-24 07:18:47.513801: step: 1992/529, loss: 0.003938610199838877
2023-01-24 07:18:48.580949: step: 1996/529, loss: 0.010159165598452091
2023-01-24 07:18:49.683874: step: 2000/529, loss: 0.0029523978009819984
2023-01-24 07:18:50.760102: step: 2004/529, loss: 0.005174259189516306
2023-01-24 07:18:51.833270: step: 2008/529, loss: 0.027476996183395386
2023-01-24 07:18:52.900697: step: 2012/529, loss: 0.024513723328709602
2023-01-24 07:18:53.966188: step: 2016/529, loss: 0.0024818151723593473
2023-01-24 07:18:55.030534: step: 2020/529, loss: 0.0431428998708725
2023-01-24 07:18:56.103366: step: 2024/529, loss: 0.02708708494901657
2023-01-24 07:18:57.178144: step: 2028/529, loss: 0.004642784595489502
2023-01-24 07:18:58.249973: step: 2032/529, loss: 0.01315707340836525
2023-01-24 07:18:59.317662: step: 2036/529, loss: 0.003880305215716362
2023-01-24 07:19:00.374473: step: 2040/529, loss: 0.00948945339769125
2023-01-24 07:19:01.412820: step: 2044/529, loss: 0.025201668962836266
2023-01-24 07:19:02.485505: step: 2048/529, loss: 0.006676464341580868
2023-01-24 07:19:03.547021: step: 2052/529, loss: 0.0044360230676829815
2023-01-24 07:19:04.617612: step: 2056/529, loss: 0.008129360154271126
2023-01-24 07:19:05.681723: step: 2060/529, loss: 0.016363075003027916
2023-01-24 07:19:06.760470: step: 2064/529, loss: 0.009301436133682728
2023-01-24 07:19:07.824362: step: 2068/529, loss: 0.0007248249021358788
2023-01-24 07:19:08.897278: step: 2072/529, loss: 0.0004125684790778905
2023-01-24 07:19:09.963229: step: 2076/529, loss: 0.0022369003854691982
2023-01-24 07:19:11.041877: step: 2080/529, loss: 0.00980714987963438
2023-01-24 07:19:12.117357: step: 2084/529, loss: 0.01985403709113598
2023-01-24 07:19:13.204126: step: 2088/529, loss: 0.014631159603595734
2023-01-24 07:19:14.278358: step: 2092/529, loss: 0.005297543480992317
2023-01-24 07:19:15.355160: step: 2096/529, loss: 0.006698545068502426
2023-01-24 07:19:16.435871: step: 2100/529, loss: 0.0017708899686113
2023-01-24 07:19:17.499740: step: 2104/529, loss: 0.0005140889552421868
2023-01-24 07:19:18.582399: step: 2108/529, loss: 0.03649412468075752
2023-01-24 07:19:19.658999: step: 2112/529, loss: 0.004563836380839348
2023-01-24 07:19:20.726495: step: 2116/529, loss: 0.010992822237312794
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3312356192476991, 'r': 0.29918055932050247, 'f1': 0.31439313013340936}, 'combined': 0.2316580958877753, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3256497670741063, 'r': 0.29212699693412475, 'f1': 0.30797884948093773}, 'combined': 0.20106391209636348, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3561142797247282, 'r': 0.354087063711115, 'f1': 0.35509777845053775}, 'combined': 0.26165099464776465, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35400046745871183, 'r': 0.31495629825370686, 'f1': 0.33333896157590764}, 'combined': 0.21762025470758736, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3740153686334242, 'r': 0.3449173987776929, 'f1': 0.35887753041627674}, 'combined': 0.2644360750435723, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3617649873633588, 'r': 0.3025791714160446, 'f1': 0.3295356741748314}, 'combined': 0.21513727951310235, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3675213675213675, 'r': 0.4095238095238095, 'f1': 0.38738738738738737}, 'combined': 0.2582582582582582, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.4891304347826087, 'f1': 0.4245283018867925}, 'combined': 0.21226415094339626, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
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 07:21:58.131819: step: 4/529, loss: 0.009747476316988468
2023-01-24 07:21:59.200511: step: 8/529, loss: 0.003275158815085888
2023-01-24 07:22:00.269451: step: 12/529, loss: 0.008259285241365433
2023-01-24 07:22:01.330936: step: 16/529, loss: 0.006497662048786879
2023-01-24 07:22:02.388188: step: 20/529, loss: 0.00302662281319499
2023-01-24 07:22:03.451794: step: 24/529, loss: 0.0007791048265062273
2023-01-24 07:22:04.522076: step: 28/529, loss: 0.0020304741337895393
2023-01-24 07:22:05.582698: step: 32/529, loss: 0.014636431820690632
2023-01-24 07:22:06.643067: step: 36/529, loss: 0.004981345497071743
2023-01-24 07:22:07.710229: step: 40/529, loss: 0.004502154886722565
2023-01-24 07:22:08.775917: step: 44/529, loss: 0.0039527141489088535
2023-01-24 07:22:09.836122: step: 48/529, loss: 0.0004062947991769761
2023-01-24 07:22:10.905102: step: 52/529, loss: 0.01000632531940937
2023-01-24 07:22:11.971036: step: 56/529, loss: 0.0010569922160357237
2023-01-24 07:22:13.036384: step: 60/529, loss: 0.009578239172697067
2023-01-24 07:22:14.096253: step: 64/529, loss: 0.0055840169079601765
2023-01-24 07:22:15.151428: step: 68/529, loss: 0.027266722172498703
2023-01-24 07:22:16.219368: step: 72/529, loss: 0.005511911120265722
2023-01-24 07:22:17.300090: step: 76/529, loss: 0.028164569288492203
2023-01-24 07:22:18.368435: step: 80/529, loss: 0.01114873681217432
2023-01-24 07:22:19.435602: step: 84/529, loss: 0.010442463681101799
2023-01-24 07:22:20.516657: step: 88/529, loss: 0.0019789354410022497
2023-01-24 07:22:21.583150: step: 92/529, loss: 0.002176770241931081
2023-01-24 07:22:22.643604: step: 96/529, loss: 0.011197119019925594
2023-01-24 07:22:23.721306: step: 100/529, loss: 0.021637076511979103
2023-01-24 07:22:24.791232: step: 104/529, loss: 0.009540221653878689
2023-01-24 07:22:25.867154: step: 108/529, loss: 0.0026357679162174463
2023-01-24 07:22:26.942324: step: 112/529, loss: 0.0039633531123399734
2023-01-24 07:22:28.021038: step: 116/529, loss: 0.006209233775734901
2023-01-24 07:22:29.092153: step: 120/529, loss: 0.002560943365097046
2023-01-24 07:22:30.148025: step: 124/529, loss: 0.029506143182516098
2023-01-24 07:22:31.233734: step: 128/529, loss: 0.004663768224418163
2023-01-24 07:22:32.296375: step: 132/529, loss: 0.00984466727823019
2023-01-24 07:22:33.366344: step: 136/529, loss: 0.00023562906426377594
2023-01-24 07:22:34.420160: step: 140/529, loss: 0.006864276714622974
2023-01-24 07:22:35.511350: step: 144/529, loss: 0.0011946257436648011
2023-01-24 07:22:36.605074: step: 148/529, loss: 0.004430925939232111
2023-01-24 07:22:37.671540: step: 152/529, loss: 0.0136809591203928
2023-01-24 07:22:38.751710: step: 156/529, loss: 0.007057512644678354
2023-01-24 07:22:39.823917: step: 160/529, loss: 0.05233162268996239
2023-01-24 07:22:40.884149: step: 164/529, loss: 0.00047828099923208356
2023-01-24 07:22:41.955922: step: 168/529, loss: 0.012809165753424168
2023-01-24 07:22:43.024968: step: 172/529, loss: 0.004256012849509716
2023-01-24 07:22:44.102040: step: 176/529, loss: 0.008155967108905315
2023-01-24 07:22:45.177109: step: 180/529, loss: 0.0017409624997526407
2023-01-24 07:22:46.233002: step: 184/529, loss: 0.006880775094032288
2023-01-24 07:22:47.315586: step: 188/529, loss: 0.002150752581655979
2023-01-24 07:22:48.400729: step: 192/529, loss: 0.015141529031097889
2023-01-24 07:22:49.476161: step: 196/529, loss: 0.0011681936448439956
2023-01-24 07:22:50.554823: step: 200/529, loss: 0.002449402352795005
2023-01-24 07:22:51.621335: step: 204/529, loss: 0.000558110827114433
2023-01-24 07:22:52.700111: step: 208/529, loss: 0.0391618013381958
2023-01-24 07:22:53.781584: step: 212/529, loss: 0.005045281257480383
2023-01-24 07:22:54.838641: step: 216/529, loss: 0.0044939653016626835
2023-01-24 07:22:55.886214: step: 220/529, loss: 3.725290076417309e-09
2023-01-24 07:22:56.976750: step: 224/529, loss: 0.005099854897707701
2023-01-24 07:22:58.049453: step: 228/529, loss: 0.015604529529809952
2023-01-24 07:22:59.143121: step: 232/529, loss: 0.011787890456616879
2023-01-24 07:23:00.212079: step: 236/529, loss: 0.0003547786909621209
2023-01-24 07:23:01.294291: step: 240/529, loss: 0.00912325270473957
2023-01-24 07:23:02.370456: step: 244/529, loss: 0.020363986492156982
2023-01-24 07:23:03.443255: step: 248/529, loss: 0.00735419662669301
2023-01-24 07:23:04.519008: step: 252/529, loss: 0.004128073807805777
2023-01-24 07:23:05.605370: step: 256/529, loss: 0.006799825932830572
2023-01-24 07:23:06.681976: step: 260/529, loss: 0.005110451020300388
2023-01-24 07:23:07.736028: step: 264/529, loss: 0.016539715230464935
2023-01-24 07:23:08.805624: step: 268/529, loss: 0.002039081184193492
2023-01-24 07:23:09.897098: step: 272/529, loss: 0.0021473790984600782
2023-01-24 07:23:10.981600: step: 276/529, loss: 0.0007715190295130014
2023-01-24 07:23:12.063104: step: 280/529, loss: 0.00780539819970727
2023-01-24 07:23:13.128337: step: 284/529, loss: 0.000981232151389122
2023-01-24 07:23:14.206419: step: 288/529, loss: 0.004279303830116987
2023-01-24 07:23:15.256447: step: 292/529, loss: 0.0026296470314264297
2023-01-24 07:23:16.338113: step: 296/529, loss: 0.016560344025492668
2023-01-24 07:23:17.418347: step: 300/529, loss: 0.02972700074315071
2023-01-24 07:23:18.504584: step: 304/529, loss: 0.034799423068761826
2023-01-24 07:23:19.566436: step: 308/529, loss: 0.013093378394842148
2023-01-24 07:23:20.654660: step: 312/529, loss: 0.048066381365060806
2023-01-24 07:23:21.741345: step: 316/529, loss: 0.0057670907117426395
2023-01-24 07:23:22.813632: step: 320/529, loss: 0.017366575077176094
2023-01-24 07:23:23.880299: step: 324/529, loss: 0.0006468056235462427
2023-01-24 07:23:24.953303: step: 328/529, loss: 0.001152149634435773
2023-01-24 07:23:26.036570: step: 332/529, loss: 0.00032867054687812924
2023-01-24 07:23:27.121391: step: 336/529, loss: 0.012116515077650547
2023-01-24 07:23:28.195068: step: 340/529, loss: 0.006163491867482662
2023-01-24 07:23:29.268755: step: 344/529, loss: 0.0011839959770441055
2023-01-24 07:23:30.369003: step: 348/529, loss: 0.009106863290071487
2023-01-24 07:23:31.463305: step: 352/529, loss: 0.003912312909960747
2023-01-24 07:23:32.547768: step: 356/529, loss: 0.012659174390137196
2023-01-24 07:23:33.609835: step: 360/529, loss: 0.010551778599619865
2023-01-24 07:23:34.685243: step: 364/529, loss: 0.004434017464518547
2023-01-24 07:23:35.762035: step: 368/529, loss: 0.02366974763572216
2023-01-24 07:23:36.852567: step: 372/529, loss: 0.006800464820116758
2023-01-24 07:23:37.925973: step: 376/529, loss: 0.0008074561483226717
2023-01-24 07:23:39.012187: step: 380/529, loss: 0.006059197708964348
2023-01-24 07:23:40.087182: step: 384/529, loss: 0.001420728163793683
2023-01-24 07:23:41.170705: step: 388/529, loss: 0.03265802189707756
2023-01-24 07:23:42.249055: step: 392/529, loss: 0.011451431550085545
2023-01-24 07:23:43.359798: step: 396/529, loss: 0.0022584048565477133
2023-01-24 07:23:44.436530: step: 400/529, loss: 0.013998680748045444
2023-01-24 07:23:45.524082: step: 404/529, loss: 0.010839652270078659
2023-01-24 07:23:46.615217: step: 408/529, loss: 0.024989547207951546
2023-01-24 07:23:47.717008: step: 412/529, loss: 0.0008449184824712574
2023-01-24 07:23:48.802808: step: 416/529, loss: 0.015925172716379166
2023-01-24 07:23:49.878373: step: 420/529, loss: 0.008344486355781555
2023-01-24 07:23:50.945286: step: 424/529, loss: 0.006443290039896965
2023-01-24 07:23:52.020854: step: 428/529, loss: 0.0034994876477867365
2023-01-24 07:23:53.104627: step: 432/529, loss: 0.006240661721676588
2023-01-24 07:23:54.182262: step: 436/529, loss: 0.026115959510207176
2023-01-24 07:23:55.279190: step: 440/529, loss: 0.002189795020967722
2023-01-24 07:23:56.371572: step: 444/529, loss: 0.001292856759391725
2023-01-24 07:23:57.477877: step: 448/529, loss: 0.021675340831279755
2023-01-24 07:23:58.582165: step: 452/529, loss: 0.020170198753476143
2023-01-24 07:23:59.664294: step: 456/529, loss: 0.0038539739325642586
2023-01-24 07:24:00.726671: step: 460/529, loss: 0.003045107237994671
2023-01-24 07:24:01.828934: step: 464/529, loss: 0.0020149783231317997
2023-01-24 07:24:02.917247: step: 468/529, loss: 0.0035974527709186077
2023-01-24 07:24:04.012141: step: 472/529, loss: 0.004982856567949057
2023-01-24 07:24:05.106000: step: 476/529, loss: 0.015442381612956524
2023-01-24 07:24:06.185235: step: 480/529, loss: 0.0036645352374762297
2023-01-24 07:24:07.271470: step: 484/529, loss: 0.021050328388810158
2023-01-24 07:24:08.363056: step: 488/529, loss: 0.007365392986685038
2023-01-24 07:24:09.433485: step: 492/529, loss: 7.890837878221646e-05
2023-01-24 07:24:10.523848: step: 496/529, loss: 0.0021499230060726404
2023-01-24 07:24:11.606402: step: 500/529, loss: 0.013126959092915058
2023-01-24 07:24:12.690013: step: 504/529, loss: 0.00651155598461628
2023-01-24 07:24:13.767392: step: 508/529, loss: 0.0042288885451853275
2023-01-24 07:24:14.838910: step: 512/529, loss: 0.010497361421585083
2023-01-24 07:24:15.924167: step: 516/529, loss: 0.0032536915969103575
2023-01-24 07:24:17.024751: step: 520/529, loss: 0.006407783832401037
2023-01-24 07:24:18.115029: step: 524/529, loss: 0.030243633314967155
2023-01-24 07:24:19.198756: step: 528/529, loss: 0.008385750465095043
2023-01-24 07:24:20.289296: step: 532/529, loss: 0.00030342568061314523
2023-01-24 07:24:21.382710: step: 536/529, loss: 0.006019508931785822
2023-01-24 07:24:22.468680: step: 540/529, loss: 0.0023384622763842344
2023-01-24 07:24:23.563890: step: 544/529, loss: 0.007905756123363972
2023-01-24 07:24:24.662161: step: 548/529, loss: 0.008231570944190025
2023-01-24 07:24:25.758726: step: 552/529, loss: 0.0026338002644479275
2023-01-24 07:24:26.842830: step: 556/529, loss: 0.02624349854886532
2023-01-24 07:24:27.920736: step: 560/529, loss: 0.020095830783247948
2023-01-24 07:24:29.016408: step: 564/529, loss: 0.007856771349906921
2023-01-24 07:24:30.090092: step: 568/529, loss: 0.00978147890418768
2023-01-24 07:24:31.175332: step: 572/529, loss: 0.006413714028894901
2023-01-24 07:24:32.275859: step: 576/529, loss: 0.008696607314050198
2023-01-24 07:24:33.371741: step: 580/529, loss: 0.005394941661506891
2023-01-24 07:24:34.455937: step: 584/529, loss: 0.00240964419208467
2023-01-24 07:24:35.549759: step: 588/529, loss: 0.01084339153021574
2023-01-24 07:24:36.634696: step: 592/529, loss: 0.0008681678446009755
2023-01-24 07:24:37.720221: step: 596/529, loss: 0.002573717152699828
2023-01-24 07:24:38.807674: step: 600/529, loss: 0.001686137286014855
2023-01-24 07:24:39.882772: step: 604/529, loss: 0.0002229427482234314
2023-01-24 07:24:40.976704: step: 608/529, loss: 0.0033347313292324543
2023-01-24 07:24:42.066748: step: 612/529, loss: 0.006069518160074949
2023-01-24 07:24:43.180000: step: 616/529, loss: 0.005314069800078869
2023-01-24 07:24:44.289332: step: 620/529, loss: 0.011619308963418007
2023-01-24 07:24:45.369180: step: 624/529, loss: 0.007463936693966389
2023-01-24 07:24:46.448958: step: 628/529, loss: 0.005212721414864063
2023-01-24 07:24:47.554667: step: 632/529, loss: 0.011492015793919563
2023-01-24 07:24:48.638858: step: 636/529, loss: 0.00473751500248909
2023-01-24 07:24:49.714508: step: 640/529, loss: 0.008172940462827682
2023-01-24 07:24:50.803171: step: 644/529, loss: 0.011758987791836262
2023-01-24 07:24:51.879290: step: 648/529, loss: 0.005540257785469294
2023-01-24 07:24:52.961699: step: 652/529, loss: 0.002190530067309737
2023-01-24 07:24:54.046689: step: 656/529, loss: 0.02387157827615738
2023-01-24 07:24:55.145647: step: 660/529, loss: 0.0012084796326234937
2023-01-24 07:24:56.224081: step: 664/529, loss: 0.00021252931037452072
2023-01-24 07:24:57.290266: step: 668/529, loss: 0.005288487765938044
2023-01-24 07:24:58.382178: step: 672/529, loss: 0.011240778490900993
2023-01-24 07:24:59.476961: step: 676/529, loss: 0.00876892264932394
2023-01-24 07:25:00.565464: step: 680/529, loss: 0.015661615878343582
2023-01-24 07:25:01.638738: step: 684/529, loss: 0.0001873767760116607
2023-01-24 07:25:02.725368: step: 688/529, loss: 0.005850032437592745
2023-01-24 07:25:03.819781: step: 692/529, loss: 0.002547177951782942
2023-01-24 07:25:04.914824: step: 696/529, loss: 0.00028295861557126045
2023-01-24 07:25:05.995184: step: 700/529, loss: 0.009461583569645882
2023-01-24 07:25:07.096719: step: 704/529, loss: 0.0023425337858498096
2023-01-24 07:25:08.187606: step: 708/529, loss: 0.0020930746104568243
2023-01-24 07:25:09.285429: step: 712/529, loss: 0.009239100851118565
2023-01-24 07:25:10.395339: step: 716/529, loss: 0.012814832851290703
2023-01-24 07:25:11.468506: step: 720/529, loss: 0.004613940604031086
2023-01-24 07:25:12.546303: step: 724/529, loss: 0.0029280786402523518
2023-01-24 07:25:13.636920: step: 728/529, loss: 0.003943185321986675
2023-01-24 07:25:14.717887: step: 732/529, loss: 0.0027340154629200697
2023-01-24 07:25:15.787611: step: 736/529, loss: 0.0015234225429594517
2023-01-24 07:25:16.861542: step: 740/529, loss: 0.0005853785551153123
2023-01-24 07:25:17.949009: step: 744/529, loss: 0.005643903277814388
2023-01-24 07:25:19.038991: step: 748/529, loss: 0.002172401174902916
2023-01-24 07:25:20.121653: step: 752/529, loss: 0.005956471897661686
2023-01-24 07:25:21.203848: step: 756/529, loss: 0.0038132721092551947
2023-01-24 07:25:22.288665: step: 760/529, loss: 0.0018798239761963487
2023-01-24 07:25:23.365888: step: 764/529, loss: 0.008477110415697098
2023-01-24 07:25:24.449058: step: 768/529, loss: 0.005096436943858862
2023-01-24 07:25:25.541777: step: 772/529, loss: 0.005197742488235235
2023-01-24 07:25:26.627063: step: 776/529, loss: 0.00404119910672307
2023-01-24 07:25:27.715131: step: 780/529, loss: 0.0014957330422475934
2023-01-24 07:25:28.809513: step: 784/529, loss: 0.0028175227344036102
2023-01-24 07:25:29.883009: step: 788/529, loss: 0.010531235486268997
2023-01-24 07:25:30.984811: step: 792/529, loss: 0.006592996418476105
2023-01-24 07:25:32.067282: step: 796/529, loss: 0.001529913512058556
2023-01-24 07:25:33.147243: step: 800/529, loss: 0.0017347006360068917
2023-01-24 07:25:34.230194: step: 804/529, loss: 0.0017265999922528863
2023-01-24 07:25:35.321037: step: 808/529, loss: 0.0023738956078886986
2023-01-24 07:25:36.415918: step: 812/529, loss: 0.006240862421691418
2023-01-24 07:25:37.505689: step: 816/529, loss: 0.0026183349546045065
2023-01-24 07:25:38.584715: step: 820/529, loss: 0.0003096178697887808
2023-01-24 07:25:39.670386: step: 824/529, loss: 0.0034289476461708546
2023-01-24 07:25:40.745236: step: 828/529, loss: 0.0017801757203415036
2023-01-24 07:25:41.829887: step: 832/529, loss: 0.004398096352815628
2023-01-24 07:25:42.923431: step: 836/529, loss: 0.0010579280788078904
2023-01-24 07:25:44.004770: step: 840/529, loss: 0.0036922418512403965
2023-01-24 07:25:45.083052: step: 844/529, loss: 0.013683700934052467
2023-01-24 07:25:46.174421: step: 848/529, loss: 8.35388564155437e-05
2023-01-24 07:25:47.254649: step: 852/529, loss: 0.006110694725066423
2023-01-24 07:25:48.338743: step: 856/529, loss: 0.00912535097450018
2023-01-24 07:25:49.410218: step: 860/529, loss: 0.002674727002158761
2023-01-24 07:25:50.491182: step: 864/529, loss: 0.004322531633079052
2023-01-24 07:25:51.567183: step: 868/529, loss: 0.006016689818352461
2023-01-24 07:25:52.647334: step: 872/529, loss: 0.001576276496052742
2023-01-24 07:25:53.724919: step: 876/529, loss: 0.0008923484710976481
2023-01-24 07:25:54.812132: step: 880/529, loss: 0.013937306590378284
2023-01-24 07:25:55.895227: step: 884/529, loss: 0.004354747943580151
2023-01-24 07:25:56.966945: step: 888/529, loss: 0.001541958306916058
2023-01-24 07:25:58.051681: step: 892/529, loss: 0.00795665942132473
2023-01-24 07:25:59.113657: step: 896/529, loss: 0.0005363939562812448
2023-01-24 07:26:00.194614: step: 900/529, loss: 0.0035471252631396055
2023-01-24 07:26:01.280984: step: 904/529, loss: 0.05340811610221863
2023-01-24 07:26:02.350060: step: 908/529, loss: 0.0034446301870048046
2023-01-24 07:26:03.437054: step: 912/529, loss: 0.00645345076918602
2023-01-24 07:26:04.520424: step: 916/529, loss: 0.0036342365201562643
2023-01-24 07:26:05.614723: step: 920/529, loss: 0.04230709746479988
2023-01-24 07:26:06.688721: step: 924/529, loss: 0.003863136749714613
2023-01-24 07:26:07.783253: step: 928/529, loss: 0.003635154804214835
2023-01-24 07:26:08.860147: step: 932/529, loss: 0.004086005967110395
2023-01-24 07:26:09.942332: step: 936/529, loss: 0.019329141825437546
2023-01-24 07:26:11.014392: step: 940/529, loss: 0.00680341012775898
2023-01-24 07:26:12.100014: step: 944/529, loss: 0.004597218707203865
2023-01-24 07:26:13.191075: step: 948/529, loss: 0.0036511612124741077
2023-01-24 07:26:14.292991: step: 952/529, loss: 0.004385803826153278
2023-01-24 07:26:15.377075: step: 956/529, loss: 0.0045221904292702675
2023-01-24 07:26:16.434143: step: 960/529, loss: 0.0031598364003002644
2023-01-24 07:26:17.519786: step: 964/529, loss: 0.010563013143837452
2023-01-24 07:26:18.594817: step: 968/529, loss: 0.009025481529533863
2023-01-24 07:26:19.701923: step: 972/529, loss: 0.0034501042682677507
2023-01-24 07:26:20.786463: step: 976/529, loss: 0.01031646691262722
2023-01-24 07:26:21.869401: step: 980/529, loss: 0.005332152359187603
2023-01-24 07:26:22.942642: step: 984/529, loss: 8.416222408413887e-05
2023-01-24 07:26:24.012281: step: 988/529, loss: 0.0008549308986403048
2023-01-24 07:26:25.090287: step: 992/529, loss: 0.033310480415821075
2023-01-24 07:26:26.166102: step: 996/529, loss: 0.008810398168861866
2023-01-24 07:26:27.251504: step: 1000/529, loss: 0.006010415498167276
2023-01-24 07:26:28.334134: step: 1004/529, loss: 0.004055732861161232
2023-01-24 07:26:29.422539: step: 1008/529, loss: 0.0
2023-01-24 07:26:30.502396: step: 1012/529, loss: 0.003681538626551628
2023-01-24 07:26:31.590959: step: 1016/529, loss: 0.005241389386355877
2023-01-24 07:26:32.655899: step: 1020/529, loss: 0.013020191341638565
2023-01-24 07:26:33.726855: step: 1024/529, loss: 0.001995422411710024
2023-01-24 07:26:34.813896: step: 1028/529, loss: 0.024140600115060806
2023-01-24 07:26:35.901200: step: 1032/529, loss: 0.007250323425978422
2023-01-24 07:26:36.976123: step: 1036/529, loss: 0.004806543234735727
2023-01-24 07:26:38.054335: step: 1040/529, loss: 0.01244381070137024
2023-01-24 07:26:39.128706: step: 1044/529, loss: 0.0025910362601280212
2023-01-24 07:26:40.232814: step: 1048/529, loss: 0.00502138352021575
2023-01-24 07:26:41.314681: step: 1052/529, loss: 0.028342485427856445
2023-01-24 07:26:42.401791: step: 1056/529, loss: 0.0007401079055853188
2023-01-24 07:26:43.484212: step: 1060/529, loss: 0.019049426540732384
2023-01-24 07:26:44.559693: step: 1064/529, loss: 0.007588242646306753
2023-01-24 07:26:45.649115: step: 1068/529, loss: 0.013227601535618305
2023-01-24 07:26:46.729743: step: 1072/529, loss: 0.004317444283515215
2023-01-24 07:26:47.809098: step: 1076/529, loss: 0.00983927957713604
2023-01-24 07:26:48.887151: step: 1080/529, loss: 0.01683719828724861
2023-01-24 07:26:49.965059: step: 1084/529, loss: 8.491049084113911e-05
2023-01-24 07:26:51.051804: step: 1088/529, loss: 0.005881684832274914
2023-01-24 07:26:52.127413: step: 1092/529, loss: 0.006691095884889364
2023-01-24 07:26:53.216759: step: 1096/529, loss: 0.003454263089224696
2023-01-24 07:26:54.296705: step: 1100/529, loss: 0.015649283304810524
2023-01-24 07:26:55.379603: step: 1104/529, loss: 0.011050356552004814
2023-01-24 07:26:56.453909: step: 1108/529, loss: 0.0032142456620931625
2023-01-24 07:26:57.522706: step: 1112/529, loss: 0.007386663928627968
2023-01-24 07:26:58.615961: step: 1116/529, loss: 0.02004830911755562
2023-01-24 07:26:59.685661: step: 1120/529, loss: 0.009723396971821785
2023-01-24 07:27:00.752056: step: 1124/529, loss: 0.004837788641452789
2023-01-24 07:27:01.837719: step: 1128/529, loss: 0.003017564071342349
2023-01-24 07:27:02.909038: step: 1132/529, loss: 0.00225435639731586
2023-01-24 07:27:03.975054: step: 1136/529, loss: 0.007492497097700834
2023-01-24 07:27:05.063955: step: 1140/529, loss: 0.003741239197552204
2023-01-24 07:27:06.152083: step: 1144/529, loss: 0.03487576171755791
2023-01-24 07:27:07.225153: step: 1148/529, loss: 0.0014335340820252895
2023-01-24 07:27:08.301462: step: 1152/529, loss: 0.0029061236418783665
2023-01-24 07:27:09.378686: step: 1156/529, loss: 0.001039195922203362
2023-01-24 07:27:10.463414: step: 1160/529, loss: 0.0022364326287060976
2023-01-24 07:27:11.538443: step: 1164/529, loss: 0.002948314417153597
2023-01-24 07:27:12.626932: step: 1168/529, loss: 0.0034942475613206625
2023-01-24 07:27:13.717000: step: 1172/529, loss: 0.006814890541136265
2023-01-24 07:27:14.796089: step: 1176/529, loss: 0.004032635595649481
2023-01-24 07:27:15.881420: step: 1180/529, loss: 0.017857084050774574
2023-01-24 07:27:16.951889: step: 1184/529, loss: 0.006571384612470865
2023-01-24 07:27:18.039778: step: 1188/529, loss: 0.02706005796790123
2023-01-24 07:27:19.106129: step: 1192/529, loss: 0.0017993083456531167
2023-01-24 07:27:20.195071: step: 1196/529, loss: 0.010335346683859825
2023-01-24 07:27:21.275316: step: 1200/529, loss: 0.005582628771662712
2023-01-24 07:27:22.348252: step: 1204/529, loss: 0.01272439956665039
2023-01-24 07:27:23.441651: step: 1208/529, loss: 0.004503973294049501
2023-01-24 07:27:24.520217: step: 1212/529, loss: 0.001502827974036336
2023-01-24 07:27:25.615433: step: 1216/529, loss: 0.004217275884002447
2023-01-24 07:27:26.693306: step: 1220/529, loss: 0.018099181354045868
2023-01-24 07:27:27.768066: step: 1224/529, loss: 0.0038011951837688684
2023-01-24 07:27:28.837823: step: 1228/529, loss: 0.006562451366335154
2023-01-24 07:27:29.918248: step: 1232/529, loss: 0.004566310439258814
2023-01-24 07:27:31.010825: step: 1236/529, loss: 0.005925430450588465
2023-01-24 07:27:32.080750: step: 1240/529, loss: 0.0001502680970588699
2023-01-24 07:27:33.163142: step: 1244/529, loss: 0.0070723495446145535
2023-01-24 07:27:34.234656: step: 1248/529, loss: 0.011896009556949139
2023-01-24 07:27:35.316223: step: 1252/529, loss: 0.0024085433688014746
2023-01-24 07:27:36.387273: step: 1256/529, loss: 0.004441781900823116
2023-01-24 07:27:37.486136: step: 1260/529, loss: 0.005776817444711924
2023-01-24 07:27:38.564971: step: 1264/529, loss: 0.03551269322633743
2023-01-24 07:27:39.671215: step: 1268/529, loss: 0.008740313351154327
2023-01-24 07:27:40.767069: step: 1272/529, loss: 0.011169994249939919
2023-01-24 07:27:41.859461: step: 1276/529, loss: 0.01391005888581276
2023-01-24 07:27:42.940793: step: 1280/529, loss: 0.006699708756059408
2023-01-24 07:27:44.010403: step: 1284/529, loss: 0.0006082784966565669
2023-01-24 07:27:45.089507: step: 1288/529, loss: 0.008528091013431549
2023-01-24 07:27:46.155221: step: 1292/529, loss: 0.001084450981579721
2023-01-24 07:27:47.235725: step: 1296/529, loss: 0.004320644773542881
2023-01-24 07:27:48.302146: step: 1300/529, loss: 0.0035094122868031263
2023-01-24 07:27:49.376989: step: 1304/529, loss: 0.0010691630886867642
2023-01-24 07:27:50.460685: step: 1308/529, loss: 0.0007240056293085217
2023-01-24 07:27:51.547509: step: 1312/529, loss: 0.002161764306947589
2023-01-24 07:27:52.633971: step: 1316/529, loss: 0.012812407687306404
2023-01-24 07:27:53.715321: step: 1320/529, loss: 0.010177544318139553
2023-01-24 07:27:54.780199: step: 1324/529, loss: 0.001555904047563672
2023-01-24 07:27:55.872053: step: 1328/529, loss: 0.003890685271471739
2023-01-24 07:27:56.947187: step: 1332/529, loss: 0.023090403527021408
2023-01-24 07:27:58.037122: step: 1336/529, loss: 0.00614022184163332
2023-01-24 07:27:59.116412: step: 1340/529, loss: 0.006378744263201952
2023-01-24 07:28:00.209582: step: 1344/529, loss: 0.008394118398427963
2023-01-24 07:28:01.293459: step: 1348/529, loss: 0.0032654814422130585
2023-01-24 07:28:02.372022: step: 1352/529, loss: 0.007110281381756067
2023-01-24 07:28:03.453347: step: 1356/529, loss: 0.006826352793723345
2023-01-24 07:28:04.535856: step: 1360/529, loss: 0.0021168761886656284
2023-01-24 07:28:05.623779: step: 1364/529, loss: 0.022711405530571938
2023-01-24 07:28:06.707741: step: 1368/529, loss: 0.004626799374818802
2023-01-24 07:28:07.787378: step: 1372/529, loss: 0.003447539871558547
2023-01-24 07:28:08.855596: step: 1376/529, loss: 0.019592512398958206
2023-01-24 07:28:09.947247: step: 1380/529, loss: 0.009044213220477104
2023-01-24 07:28:11.007711: step: 1384/529, loss: 0.005241322796791792
2023-01-24 07:28:12.103088: step: 1388/529, loss: 0.00176662253215909
2023-01-24 07:28:13.202123: step: 1392/529, loss: 0.00025052446289919317
2023-01-24 07:28:14.267950: step: 1396/529, loss: 0.006436891388148069
2023-01-24 07:28:15.354376: step: 1400/529, loss: 0.0014382406370714307
2023-01-24 07:28:16.428930: step: 1404/529, loss: 0.002375274430960417
2023-01-24 07:28:17.502742: step: 1408/529, loss: 0.006078909616917372
2023-01-24 07:28:18.594166: step: 1412/529, loss: 0.01394870225340128
2023-01-24 07:28:19.660419: step: 1416/529, loss: 0.003460199572145939
2023-01-24 07:28:20.739990: step: 1420/529, loss: 0.01040552370250225
2023-01-24 07:28:21.831688: step: 1424/529, loss: 0.0015089769149199128
2023-01-24 07:28:22.907708: step: 1428/529, loss: 0.002916331635788083
2023-01-24 07:28:23.984852: step: 1432/529, loss: 0.007505747955292463
2023-01-24 07:28:25.074941: step: 1436/529, loss: 0.00466849934309721
2023-01-24 07:28:26.147060: step: 1440/529, loss: 0.00920061394572258
2023-01-24 07:28:27.224501: step: 1444/529, loss: 0.0057571628130972385
2023-01-24 07:28:28.303062: step: 1448/529, loss: 0.008626052178442478
2023-01-24 07:28:29.397875: step: 1452/529, loss: 0.014985253103077412
2023-01-24 07:28:30.482407: step: 1456/529, loss: 0.002016692655161023
2023-01-24 07:28:31.550684: step: 1460/529, loss: 0.000815091363620013
2023-01-24 07:28:32.625559: step: 1464/529, loss: 0.007801668718457222
2023-01-24 07:28:33.693770: step: 1468/529, loss: 0.00866541638970375
2023-01-24 07:28:34.767831: step: 1472/529, loss: 0.0009801725391298532
2023-01-24 07:28:35.847395: step: 1476/529, loss: 0.008660559542477131
2023-01-24 07:28:36.929042: step: 1480/529, loss: 0.014192376285791397
2023-01-24 07:28:38.024482: step: 1484/529, loss: 0.0026923012919723988
2023-01-24 07:28:39.104439: step: 1488/529, loss: 0.0075814565643668175
2023-01-24 07:28:40.191854: step: 1492/529, loss: 0.029399165883660316
2023-01-24 07:28:41.268674: step: 1496/529, loss: 0.00834119226783514
2023-01-24 07:28:42.330749: step: 1500/529, loss: 0.006017880514264107
2023-01-24 07:28:43.424040: step: 1504/529, loss: 0.008777924813330173
2023-01-24 07:28:44.490756: step: 1508/529, loss: 0.0019894454162567854
2023-01-24 07:28:45.570677: step: 1512/529, loss: 0.014763196930289268
2023-01-24 07:28:46.638289: step: 1516/529, loss: 0.003023806493729353
2023-01-24 07:28:47.720550: step: 1520/529, loss: 0.014696680940687656
2023-01-24 07:28:48.818096: step: 1524/529, loss: 0.003669432597234845
2023-01-24 07:28:49.903432: step: 1528/529, loss: 0.009443075396120548
2023-01-24 07:28:50.976815: step: 1532/529, loss: 0.01387085858732462
2023-01-24 07:28:52.074899: step: 1536/529, loss: 0.0026909341104328632
2023-01-24 07:28:53.166492: step: 1540/529, loss: 0.07674626260995865
2023-01-24 07:28:54.241881: step: 1544/529, loss: 0.0061227441765367985
2023-01-24 07:28:55.333188: step: 1548/529, loss: 0.008370391093194485
2023-01-24 07:28:56.409479: step: 1552/529, loss: 0.0032957694493234158
2023-01-24 07:28:57.494235: step: 1556/529, loss: 0.001369014149531722
2023-01-24 07:28:58.581817: step: 1560/529, loss: 0.01644028164446354
2023-01-24 07:28:59.644689: step: 1564/529, loss: 0.009593049995601177
2023-01-24 07:29:00.722811: step: 1568/529, loss: 0.004544573370367289
2023-01-24 07:29:01.798783: step: 1572/529, loss: 0.008603706024587154
2023-01-24 07:29:02.895575: step: 1576/529, loss: 0.0034662429243326187
2023-01-24 07:29:03.977842: step: 1580/529, loss: 0.008092181757092476
2023-01-24 07:29:05.071559: step: 1584/529, loss: 0.007533358875662088
2023-01-24 07:29:06.136309: step: 1588/529, loss: 0.0005055989022366703
2023-01-24 07:29:07.225113: step: 1592/529, loss: 0.004422774072736502
2023-01-24 07:29:08.292935: step: 1596/529, loss: 0.0016019812319427729
2023-01-24 07:29:09.375720: step: 1600/529, loss: 0.019868889823555946
2023-01-24 07:29:10.440166: step: 1604/529, loss: 0.003041674615815282
2023-01-24 07:29:11.501661: step: 1608/529, loss: 0.0029272520914673805
2023-01-24 07:29:12.576627: step: 1612/529, loss: 0.006823974195867777
2023-01-24 07:29:13.681166: step: 1616/529, loss: 0.01577920652925968
2023-01-24 07:29:14.763170: step: 1620/529, loss: 0.004937442485243082
2023-01-24 07:29:15.839840: step: 1624/529, loss: 0.01993417553603649
2023-01-24 07:29:16.915504: step: 1628/529, loss: 0.01570660062134266
2023-01-24 07:29:17.997445: step: 1632/529, loss: 0.009924609214067459
2023-01-24 07:29:19.065661: step: 1636/529, loss: 0.016979781910777092
2023-01-24 07:29:20.145937: step: 1640/529, loss: 0.007434999104589224
2023-01-24 07:29:21.218148: step: 1644/529, loss: 0.0029545214492827654
2023-01-24 07:29:22.303760: step: 1648/529, loss: 0.010606428608298302
2023-01-24 07:29:23.388582: step: 1652/529, loss: 0.00034419671283103526
2023-01-24 07:29:24.466752: step: 1656/529, loss: 0.0035986558068543673
2023-01-24 07:29:25.555110: step: 1660/529, loss: 0.0022976382169872522
2023-01-24 07:29:26.628366: step: 1664/529, loss: 0.001503913663327694
2023-01-24 07:29:27.716313: step: 1668/529, loss: 0.004559915047138929
2023-01-24 07:29:28.795084: step: 1672/529, loss: 0.0005347795085981488
2023-01-24 07:29:29.880270: step: 1676/529, loss: 0.03257714956998825
2023-01-24 07:29:30.966328: step: 1680/529, loss: 0.008291545324027538
2023-01-24 07:29:32.037722: step: 1684/529, loss: 0.005107128992676735
2023-01-24 07:29:33.104000: step: 1688/529, loss: 0.005116648972034454
2023-01-24 07:29:34.211653: step: 1692/529, loss: 0.007378586567938328
2023-01-24 07:29:35.298570: step: 1696/529, loss: 0.012093840166926384
2023-01-24 07:29:36.368612: step: 1700/529, loss: 0.007946373894810677
2023-01-24 07:29:37.454908: step: 1704/529, loss: 0.012926735915243626
2023-01-24 07:29:38.523636: step: 1708/529, loss: 0.0031895963475108147
2023-01-24 07:29:39.605461: step: 1712/529, loss: 0.028509464114904404
2023-01-24 07:29:40.675550: step: 1716/529, loss: 0.0009545735665597022
2023-01-24 07:29:41.746893: step: 1720/529, loss: 0.015718529000878334
2023-01-24 07:29:42.819455: step: 1724/529, loss: 0.007813684642314911
2023-01-24 07:29:43.887054: step: 1728/529, loss: 0.012756199575960636
2023-01-24 07:29:44.973941: step: 1732/529, loss: 0.010427942499518394
2023-01-24 07:29:46.048909: step: 1736/529, loss: 0.0031596841290593147
2023-01-24 07:29:47.120296: step: 1740/529, loss: 0.02043180912733078
2023-01-24 07:29:48.209541: step: 1744/529, loss: 0.0011438081273809075
2023-01-24 07:29:49.305964: step: 1748/529, loss: 0.004946943372488022
2023-01-24 07:29:50.369769: step: 1752/529, loss: 0.005224988795816898
2023-01-24 07:29:51.441032: step: 1756/529, loss: 0.007633446715772152
2023-01-24 07:29:52.522499: step: 1760/529, loss: 0.008096297271549702
2023-01-24 07:29:53.620875: step: 1764/529, loss: 0.007603825069963932
2023-01-24 07:29:54.706830: step: 1768/529, loss: 0.006806579418480396
2023-01-24 07:29:55.779773: step: 1772/529, loss: 0.005438607186079025
2023-01-24 07:29:56.878545: step: 1776/529, loss: 0.01815561205148697
2023-01-24 07:29:57.958841: step: 1780/529, loss: 0.020348792895674706
2023-01-24 07:29:59.032243: step: 1784/529, loss: 0.00146417785435915
2023-01-24 07:30:00.112785: step: 1788/529, loss: 0.006973433308303356
2023-01-24 07:30:01.202085: step: 1792/529, loss: 0.007061352953314781
2023-01-24 07:30:02.288683: step: 1796/529, loss: 0.018406858667731285
2023-01-24 07:30:03.378076: step: 1800/529, loss: 0.017630452290177345
2023-01-24 07:30:04.457222: step: 1804/529, loss: 0.009714137762784958
2023-01-24 07:30:05.542961: step: 1808/529, loss: 0.014081901870667934
2023-01-24 07:30:06.611754: step: 1812/529, loss: 0.005558694247156382
2023-01-24 07:30:07.681831: step: 1816/529, loss: 0.006522204261273146
2023-01-24 07:30:08.758076: step: 1820/529, loss: 0.025125302374362946
2023-01-24 07:30:09.844343: step: 1824/529, loss: 0.0002913131029345095
2023-01-24 07:30:10.897874: step: 1828/529, loss: 0.0019964517559856176
2023-01-24 07:30:11.983822: step: 1832/529, loss: 0.0007465678500011563
2023-01-24 07:30:13.090324: step: 1836/529, loss: 0.004286186303943396
2023-01-24 07:30:14.172157: step: 1840/529, loss: 0.00113116845022887
2023-01-24 07:30:15.240202: step: 1844/529, loss: 0.00785467866808176
2023-01-24 07:30:16.317681: step: 1848/529, loss: 0.002037757309153676
2023-01-24 07:30:17.392594: step: 1852/529, loss: 0.0041639553382992744
2023-01-24 07:30:18.469537: step: 1856/529, loss: 0.005991968791931868
2023-01-24 07:30:19.539248: step: 1860/529, loss: 0.0028306187596172094
2023-01-24 07:30:20.603928: step: 1864/529, loss: 0.0008542510913684964
2023-01-24 07:30:21.695971: step: 1868/529, loss: 0.007124752271920443
2023-01-24 07:30:22.769297: step: 1872/529, loss: 0.017392653971910477
2023-01-24 07:30:23.843397: step: 1876/529, loss: 0.0059369513764977455
2023-01-24 07:30:24.916938: step: 1880/529, loss: 0.012182307429611683
2023-01-24 07:30:26.003590: step: 1884/529, loss: 0.012995271943509579
2023-01-24 07:30:27.068353: step: 1888/529, loss: 0.00014857731002848595
2023-01-24 07:30:28.141694: step: 1892/529, loss: 0.0010416853474453092
2023-01-24 07:30:29.218946: step: 1896/529, loss: 0.007235480938106775
2023-01-24 07:30:30.327428: step: 1900/529, loss: 0.005913544446229935
2023-01-24 07:30:31.413420: step: 1904/529, loss: 0.033664945513010025
2023-01-24 07:30:32.481076: step: 1908/529, loss: 0.0007438280154019594
2023-01-24 07:30:33.574337: step: 1912/529, loss: 0.0006379848346114159
2023-01-24 07:30:34.643786: step: 1916/529, loss: 0.07692140340805054
2023-01-24 07:30:35.731749: step: 1920/529, loss: 0.008052946999669075
2023-01-24 07:30:36.802283: step: 1924/529, loss: 0.0034659206867218018
2023-01-24 07:30:37.891917: step: 1928/529, loss: 0.015730535611510277
2023-01-24 07:30:38.973313: step: 1932/529, loss: 0.0060439263470470905
2023-01-24 07:30:40.042423: step: 1936/529, loss: 0.007294867653399706
2023-01-24 07:30:41.120955: step: 1940/529, loss: 0.002797638764604926
2023-01-24 07:30:42.198493: step: 1944/529, loss: 0.01025779265910387
2023-01-24 07:30:43.296376: step: 1948/529, loss: 0.0030402876436710358
2023-01-24 07:30:44.372595: step: 1952/529, loss: 0.0061142644844949245
2023-01-24 07:30:45.465241: step: 1956/529, loss: 0.007880199700593948
2023-01-24 07:30:46.551168: step: 1960/529, loss: 0.01784527488052845
2023-01-24 07:30:47.613731: step: 1964/529, loss: 0.01850874349474907
2023-01-24 07:30:48.677294: step: 1968/529, loss: 0.010088245384395123
2023-01-24 07:30:49.752975: step: 1972/529, loss: 0.003554239869117737
2023-01-24 07:30:50.829281: step: 1976/529, loss: 0.0010395313147455454
2023-01-24 07:30:51.914866: step: 1980/529, loss: 0.008423163555562496
2023-01-24 07:30:52.996639: step: 1984/529, loss: 0.01008532289415598
2023-01-24 07:30:54.067493: step: 1988/529, loss: 0.003578011877834797
2023-01-24 07:30:55.134437: step: 1992/529, loss: 0.02857138030230999
2023-01-24 07:30:56.200170: step: 1996/529, loss: 0.003955631051212549
2023-01-24 07:30:57.282221: step: 2000/529, loss: 0.01996195688843727
2023-01-24 07:30:58.356519: step: 2004/529, loss: 0.02355371229350567
2023-01-24 07:30:59.421206: step: 2008/529, loss: 0.00039478030521422625
2023-01-24 07:31:00.500646: step: 2012/529, loss: 0.0021190063562244177
2023-01-24 07:31:01.581292: step: 2016/529, loss: 0.0034552859142422676
2023-01-24 07:31:02.670190: step: 2020/529, loss: 0.005363295320421457
2023-01-24 07:31:03.773148: step: 2024/529, loss: 0.011911021545529366
2023-01-24 07:31:04.853607: step: 2028/529, loss: 0.011462458409368992
2023-01-24 07:31:05.942301: step: 2032/529, loss: 0.0093986289575696
2023-01-24 07:31:07.024973: step: 2036/529, loss: 0.0017564240843057632
2023-01-24 07:31:08.113097: step: 2040/529, loss: 0.005043210927397013
2023-01-24 07:31:09.191256: step: 2044/529, loss: 0.0028536366298794746
2023-01-24 07:31:10.265954: step: 2048/529, loss: 0.007279288489371538
2023-01-24 07:31:11.356193: step: 2052/529, loss: 0.007180248852819204
2023-01-24 07:31:12.431845: step: 2056/529, loss: 0.025156911462545395
2023-01-24 07:31:13.502624: step: 2060/529, loss: 0.0007034644950181246
2023-01-24 07:31:14.588736: step: 2064/529, loss: 0.0034645809791982174
2023-01-24 07:31:15.650013: step: 2068/529, loss: 0.0022970237769186497
2023-01-24 07:31:16.724854: step: 2072/529, loss: 0.002476394409313798
2023-01-24 07:31:17.814158: step: 2076/529, loss: 0.002615951234474778
2023-01-24 07:31:18.901329: step: 2080/529, loss: 0.0074923718348145485
2023-01-24 07:31:19.978546: step: 2084/529, loss: 0.005540072917938232
2023-01-24 07:31:21.030113: step: 2088/529, loss: 0.009539883583784103
2023-01-24 07:31:22.105214: step: 2092/529, loss: 0.013932091183960438
2023-01-24 07:31:23.179431: step: 2096/529, loss: 0.004204911645501852
2023-01-24 07:31:24.279453: step: 2100/529, loss: 0.017170259729027748
2023-01-24 07:31:25.373638: step: 2104/529, loss: 0.01165766455233097
2023-01-24 07:31:26.460231: step: 2108/529, loss: 0.013586471788585186
2023-01-24 07:31:27.558936: step: 2112/529, loss: 0.038044918328523636
2023-01-24 07:31:28.646459: step: 2116/529, loss: 0.0002362493542023003
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3368750631887575, 'r': 0.3010780925273336, 'f1': 0.3179722540318733}, 'combined': 0.23429534507611716, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32627497176066916, 'r': 0.2902887616400071, 'f1': 0.30723168547113594}, 'combined': 0.2005761262661302, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36008422759262493, 'r': 0.3559845969179461, 'f1': 0.35802267667129306}, 'combined': 0.26380618281042645, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3532593449895961, 'r': 0.31105004825370686, 'f1': 0.3308137365591721}, 'combined': 0.21597166220961495, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3797719940248827, 'r': 0.3430198655708618, 'f1': 0.3604615536507361}, 'combined': 0.2656032500584371, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36951631939872526, 'r': 0.304647186121927, 'f1': 0.33396084483693356}, 'combined': 0.21802625103343848, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:34:04.346161: step: 4/529, loss: 0.0076475683599710464
2023-01-24 07:34:05.396457: step: 8/529, loss: 0.0013952614972367883
2023-01-24 07:34:06.460797: step: 12/529, loss: 0.009745420888066292
2023-01-24 07:34:07.535486: step: 16/529, loss: 0.007470333017408848
2023-01-24 07:34:08.589160: step: 20/529, loss: 0.0030291101429611444
2023-01-24 07:34:09.667211: step: 24/529, loss: 0.0055459002032876015
2023-01-24 07:34:10.724632: step: 28/529, loss: 0.007540428079664707
2023-01-24 07:34:11.810292: step: 32/529, loss: 0.0014579800190404058
2023-01-24 07:34:12.887821: step: 36/529, loss: 0.006648776587098837
2023-01-24 07:34:13.955683: step: 40/529, loss: 0.011146008968353271
2023-01-24 07:34:15.014257: step: 44/529, loss: 0.0004218129615765065
2023-01-24 07:34:16.071936: step: 48/529, loss: 0.0022697325330227613
2023-01-24 07:34:17.151613: step: 52/529, loss: 0.006932941731065512
2023-01-24 07:34:18.220303: step: 56/529, loss: 0.001632420695386827
2023-01-24 07:34:19.292875: step: 60/529, loss: 0.0058930376544594765
2023-01-24 07:34:20.357007: step: 64/529, loss: 0.003020771313458681
2023-01-24 07:34:21.417845: step: 68/529, loss: 0.0036091350484639406
2023-01-24 07:34:22.508368: step: 72/529, loss: 0.008187517523765564
2023-01-24 07:34:23.572407: step: 76/529, loss: 0.0021265442483127117
2023-01-24 07:34:24.641913: step: 80/529, loss: 0.003632922889664769
2023-01-24 07:34:25.713676: step: 84/529, loss: 0.0029451590962707996
2023-01-24 07:34:26.792153: step: 88/529, loss: 0.001857382827438414
2023-01-24 07:34:27.865844: step: 92/529, loss: 0.0010842308402061462
2023-01-24 07:34:28.956152: step: 96/529, loss: 0.0808914303779602
2023-01-24 07:34:30.037338: step: 100/529, loss: 0.011222359724342823
2023-01-24 07:34:31.109935: step: 104/529, loss: 0.002562921494245529
2023-01-24 07:34:32.184932: step: 108/529, loss: 0.006626314949244261
2023-01-24 07:34:33.275371: step: 112/529, loss: 1.3431079423753545e-05
2023-01-24 07:34:34.343270: step: 116/529, loss: 0.002375928685069084
2023-01-24 07:34:35.418918: step: 120/529, loss: 0.004076572600752115
2023-01-24 07:34:36.488988: step: 124/529, loss: 0.004171817097812891
2023-01-24 07:34:37.572543: step: 128/529, loss: 0.006225327495485544
2023-01-24 07:34:38.648379: step: 132/529, loss: 0.005350849125534296
2023-01-24 07:34:39.716610: step: 136/529, loss: 0.005230417009443045
2023-01-24 07:34:40.803214: step: 140/529, loss: 0.00936820451170206
2023-01-24 07:34:41.874949: step: 144/529, loss: 0.002336789621040225
2023-01-24 07:34:42.954979: step: 148/529, loss: 0.02020631544291973
2023-01-24 07:34:44.071606: step: 152/529, loss: 0.011263777501881123
2023-01-24 07:34:45.142898: step: 156/529, loss: 0.006566526833921671
2023-01-24 07:34:46.219209: step: 160/529, loss: 0.00023341966152656823
2023-01-24 07:34:47.301254: step: 164/529, loss: 3.326933801872656e-05
2023-01-24 07:34:48.372879: step: 168/529, loss: 0.000817728927358985
2023-01-24 07:34:49.463930: step: 172/529, loss: 0.004214529413729906
2023-01-24 07:34:50.526858: step: 176/529, loss: 0.0034627956338226795
2023-01-24 07:34:51.621604: step: 180/529, loss: 0.015495163388550282
2023-01-24 07:34:52.715867: step: 184/529, loss: 0.004431141074746847
2023-01-24 07:34:53.790180: step: 188/529, loss: 0.004249555058777332
2023-01-24 07:34:54.867757: step: 192/529, loss: 0.0011924149002879858
2023-01-24 07:34:55.940319: step: 196/529, loss: 0.00422682287171483
2023-01-24 07:34:57.010039: step: 200/529, loss: 0.0014853612519800663
2023-01-24 07:34:58.077999: step: 204/529, loss: 0.007872479036450386
2023-01-24 07:34:59.156782: step: 208/529, loss: 0.005835859104990959
2023-01-24 07:35:00.235455: step: 212/529, loss: 0.0021257756743580103
2023-01-24 07:35:01.292836: step: 216/529, loss: 0.0007697069668211043
2023-01-24 07:35:02.373183: step: 220/529, loss: 0.003168319119140506
2023-01-24 07:35:03.451271: step: 224/529, loss: 0.004536579828709364
2023-01-24 07:35:04.516850: step: 228/529, loss: 0.0032074071932584047
2023-01-24 07:35:05.581708: step: 232/529, loss: 0.0037514548748731613
2023-01-24 07:35:06.664750: step: 236/529, loss: 0.004225895740091801
2023-01-24 07:35:07.736366: step: 240/529, loss: 0.002993042813614011
2023-01-24 07:35:08.842372: step: 244/529, loss: 0.0032093417830765247
2023-01-24 07:35:09.917339: step: 248/529, loss: 0.0036520243156701326
2023-01-24 07:35:10.993821: step: 252/529, loss: 0.007269485387951136
2023-01-24 07:35:12.065020: step: 256/529, loss: 0.009392387233674526
2023-01-24 07:35:13.139295: step: 260/529, loss: 0.0012123326305299997
2023-01-24 07:35:14.209139: step: 264/529, loss: 0.004999190103262663
2023-01-24 07:35:15.302769: step: 268/529, loss: 0.006076238118112087
2023-01-24 07:35:16.394974: step: 272/529, loss: 0.016086755320429802
2023-01-24 07:35:17.449298: step: 276/529, loss: 0.0019808385986834764
2023-01-24 07:35:18.519236: step: 280/529, loss: 0.016098368912935257
2023-01-24 07:35:19.579118: step: 284/529, loss: 2.1055468096164986e-05
2023-01-24 07:35:20.652075: step: 288/529, loss: 0.018915528431534767
2023-01-24 07:35:21.716137: step: 292/529, loss: 0.0068099042400717735
2023-01-24 07:35:22.782674: step: 296/529, loss: 0.0003205329994671047
2023-01-24 07:35:23.858757: step: 300/529, loss: 0.002356010489165783
2023-01-24 07:35:24.934638: step: 304/529, loss: 0.013506465591490269
2023-01-24 07:35:26.000123: step: 308/529, loss: 0.010100096464157104
2023-01-24 07:35:27.058441: step: 312/529, loss: 0.0048659429885447025
2023-01-24 07:35:28.126827: step: 316/529, loss: 0.014681518077850342
2023-01-24 07:35:29.199072: step: 320/529, loss: 0.0005140863941051066
2023-01-24 07:35:30.281588: step: 324/529, loss: 0.010165358893573284
2023-01-24 07:35:31.370322: step: 328/529, loss: 0.008363066241145134
2023-01-24 07:35:32.429336: step: 332/529, loss: 0.0028446551878005266
2023-01-24 07:35:33.497024: step: 336/529, loss: 0.00018585480574984103
2023-01-24 07:35:34.569722: step: 340/529, loss: 0.0018784565618261695
2023-01-24 07:35:35.656757: step: 344/529, loss: 0.006612745113670826
2023-01-24 07:35:36.733535: step: 348/529, loss: 0.020105058327317238
2023-01-24 07:35:37.806183: step: 352/529, loss: 0.013487892225384712
2023-01-24 07:35:38.872971: step: 356/529, loss: 0.01829264685511589
2023-01-24 07:35:39.954998: step: 360/529, loss: 0.0006016806000843644
2023-01-24 07:35:41.023925: step: 364/529, loss: 0.004490015562623739
2023-01-24 07:35:42.113130: step: 368/529, loss: 0.0030565359629690647
2023-01-24 07:35:43.193199: step: 372/529, loss: 0.0021017531398683786
2023-01-24 07:35:44.281825: step: 376/529, loss: 0.0114333126693964
2023-01-24 07:35:45.349882: step: 380/529, loss: 0.005322054028511047
2023-01-24 07:35:46.429224: step: 384/529, loss: 0.021088669076561928
2023-01-24 07:35:47.493641: step: 388/529, loss: 4.0491329855285585e-05
2023-01-24 07:35:48.578469: step: 392/529, loss: 0.003996938467025757
2023-01-24 07:35:49.643534: step: 396/529, loss: 0.006614970974624157
2023-01-24 07:35:50.714017: step: 400/529, loss: 0.004860007669776678
2023-01-24 07:35:51.781296: step: 404/529, loss: 0.0049461605958640575
2023-01-24 07:35:52.860660: step: 408/529, loss: 0.0018996495055034757
2023-01-24 07:35:53.943380: step: 412/529, loss: 0.007716783322393894
2023-01-24 07:35:55.028828: step: 416/529, loss: 0.004638045560568571
2023-01-24 07:35:56.103386: step: 420/529, loss: 0.007567286491394043
2023-01-24 07:35:57.160126: step: 424/529, loss: 0.0034006128553301096
2023-01-24 07:35:58.227731: step: 428/529, loss: 0.0025180901866406202
2023-01-24 07:35:59.290065: step: 432/529, loss: 0.001276357565075159
2023-01-24 07:36:00.367370: step: 436/529, loss: 0.001452281721867621
2023-01-24 07:36:01.437949: step: 440/529, loss: 0.007344067096710205
2023-01-24 07:36:02.503175: step: 444/529, loss: 0.003009831765666604
2023-01-24 07:36:03.599554: step: 448/529, loss: 0.009160235524177551
2023-01-24 07:36:04.679015: step: 452/529, loss: 0.014338766224682331
2023-01-24 07:36:05.744954: step: 456/529, loss: 0.006339029408991337
2023-01-24 07:36:06.813287: step: 460/529, loss: 0.007201789412647486
2023-01-24 07:36:07.881238: step: 464/529, loss: 0.005167341325432062
2023-01-24 07:36:08.950430: step: 468/529, loss: 0.029966171830892563
2023-01-24 07:36:10.021407: step: 472/529, loss: 0.0005870857276022434
2023-01-24 07:36:11.104506: step: 476/529, loss: 0.0003639193018898368
2023-01-24 07:36:12.165292: step: 480/529, loss: 0.0014165329048410058
2023-01-24 07:36:13.233361: step: 484/529, loss: 0.0006119013414718211
2023-01-24 07:36:14.326992: step: 488/529, loss: 0.0005429352750070393
2023-01-24 07:36:15.406713: step: 492/529, loss: 0.005061294883489609
2023-01-24 07:36:16.487224: step: 496/529, loss: 0.013761462643742561
2023-01-24 07:36:17.563330: step: 500/529, loss: 0.016085518524050713
2023-01-24 07:36:18.632107: step: 504/529, loss: 0.0008053927449509501
2023-01-24 07:36:19.702657: step: 508/529, loss: 0.016597095876932144
2023-01-24 07:36:20.769870: step: 512/529, loss: 0.004336851183325052
2023-01-24 07:36:21.842729: step: 516/529, loss: 0.0038900349754840136
2023-01-24 07:36:22.927780: step: 520/529, loss: 0.004234934691339731
2023-01-24 07:36:24.025924: step: 524/529, loss: 0.005054661072790623
2023-01-24 07:36:25.102058: step: 528/529, loss: 0.012339567765593529
2023-01-24 07:36:26.162681: step: 532/529, loss: 0.025672173127532005
2023-01-24 07:36:27.257808: step: 536/529, loss: 0.009109568782150745
2023-01-24 07:36:28.324705: step: 540/529, loss: 0.002947914879769087
2023-01-24 07:36:29.409296: step: 544/529, loss: 0.001444044173695147
2023-01-24 07:36:30.471517: step: 548/529, loss: 0.015618451870977879
2023-01-24 07:36:31.541782: step: 552/529, loss: 0.008262096904218197
2023-01-24 07:36:32.632383: step: 556/529, loss: 0.011409304104745388
2023-01-24 07:36:33.709941: step: 560/529, loss: 0.005359118338674307
2023-01-24 07:36:34.789204: step: 564/529, loss: 0.000634010648354888
2023-01-24 07:36:35.876951: step: 568/529, loss: 0.002230749698355794
2023-01-24 07:36:36.944823: step: 572/529, loss: 0.0030680911149829626
2023-01-24 07:36:38.014891: step: 576/529, loss: 0.007307857740670443
2023-01-24 07:36:39.082657: step: 580/529, loss: 0.0031003218609839678
2023-01-24 07:36:40.162439: step: 584/529, loss: 0.002819253597408533
2023-01-24 07:36:41.230033: step: 588/529, loss: 0.0015863453736528754
2023-01-24 07:36:42.297998: step: 592/529, loss: 0.001516444026492536
2023-01-24 07:36:43.373635: step: 596/529, loss: 0.0012560886098071933
2023-01-24 07:36:44.451741: step: 600/529, loss: 0.002046899637207389
2023-01-24 07:36:45.528256: step: 604/529, loss: 0.0015403830911964178
2023-01-24 07:36:46.613292: step: 608/529, loss: 0.004180640447884798
2023-01-24 07:36:47.686754: step: 612/529, loss: 0.005670543294399977
2023-01-24 07:36:48.767684: step: 616/529, loss: 0.010511565953493118
2023-01-24 07:36:49.824771: step: 620/529, loss: 0.004360548686236143
2023-01-24 07:36:50.905716: step: 624/529, loss: 0.00293146725744009
2023-01-24 07:36:51.963442: step: 628/529, loss: 0.013130432926118374
2023-01-24 07:36:53.025265: step: 632/529, loss: 0.006084002088755369
2023-01-24 07:36:54.098649: step: 636/529, loss: 0.003935667686164379
2023-01-24 07:36:55.168017: step: 640/529, loss: 0.006984036415815353
2023-01-24 07:36:56.234041: step: 644/529, loss: 0.004299352411180735
2023-01-24 07:36:57.295879: step: 648/529, loss: 0.002253611572086811
2023-01-24 07:36:58.363792: step: 652/529, loss: 0.004824842792004347
2023-01-24 07:36:59.431677: step: 656/529, loss: 0.003846768755465746
2023-01-24 07:37:00.512782: step: 660/529, loss: 0.006501362659037113
2023-01-24 07:37:01.567906: step: 664/529, loss: 0.015127809718251228
2023-01-24 07:37:02.633148: step: 668/529, loss: 0.008387857116758823
2023-01-24 07:37:03.702778: step: 672/529, loss: 0.02491394616663456
2023-01-24 07:37:04.774012: step: 676/529, loss: 0.0008256888249889016
2023-01-24 07:37:05.832493: step: 680/529, loss: 0.022070206701755524
2023-01-24 07:37:06.900021: step: 684/529, loss: 0.0008302762289531529
2023-01-24 07:37:07.969589: step: 688/529, loss: 0.004053502809256315
2023-01-24 07:37:09.041566: step: 692/529, loss: 0.0028657459188252687
2023-01-24 07:37:10.122212: step: 696/529, loss: 0.007253702264279127
2023-01-24 07:37:11.197446: step: 700/529, loss: 0.0233880877494812
2023-01-24 07:37:12.272311: step: 704/529, loss: 0.011055349372327328
2023-01-24 07:37:13.359108: step: 708/529, loss: 0.00232279347255826
2023-01-24 07:37:14.429536: step: 712/529, loss: 0.0035306140780448914
2023-01-24 07:37:15.493960: step: 716/529, loss: 0.008902845904231071
2023-01-24 07:37:16.553003: step: 720/529, loss: 0.0016613632906228304
2023-01-24 07:37:17.624445: step: 724/529, loss: 0.0030670773703604937
2023-01-24 07:37:18.686795: step: 728/529, loss: 0.008626404218375683
2023-01-24 07:37:19.765772: step: 732/529, loss: 0.012124470435082912
2023-01-24 07:37:20.853493: step: 736/529, loss: 0.014640077948570251
2023-01-24 07:37:21.938928: step: 740/529, loss: 0.0023502048570662737
2023-01-24 07:37:22.994908: step: 744/529, loss: 0.02139144204556942
2023-01-24 07:37:24.066443: step: 748/529, loss: 0.0
2023-01-24 07:37:25.153802: step: 752/529, loss: 0.0029019841458648443
2023-01-24 07:37:26.220950: step: 756/529, loss: 0.016864478588104248
2023-01-24 07:37:27.293275: step: 760/529, loss: 0.0011493735946714878
2023-01-24 07:37:28.381154: step: 764/529, loss: 0.013748283497989178
2023-01-24 07:37:29.463810: step: 768/529, loss: 0.0035685438197106123
2023-01-24 07:37:30.536147: step: 772/529, loss: 0.0010443481151014566
2023-01-24 07:37:31.629212: step: 776/529, loss: 0.01635405793786049
2023-01-24 07:37:32.701782: step: 780/529, loss: 0.006745730992406607
2023-01-24 07:37:33.773954: step: 784/529, loss: 0.0051277135498821735
2023-01-24 07:37:34.847089: step: 788/529, loss: 0.002445952733978629
2023-01-24 07:37:35.900588: step: 792/529, loss: 0.004199530929327011
2023-01-24 07:37:36.957143: step: 796/529, loss: 0.0009448050404898822
2023-01-24 07:37:38.032406: step: 800/529, loss: 0.011746187694370747
2023-01-24 07:37:39.108419: step: 804/529, loss: 0.0009272314491681755
2023-01-24 07:37:40.167171: step: 808/529, loss: 0.02234543487429619
2023-01-24 07:37:41.235650: step: 812/529, loss: 0.0027863499708473682
2023-01-24 07:37:42.303591: step: 816/529, loss: 0.01994817517697811
2023-01-24 07:37:43.375123: step: 820/529, loss: 0.0022010498214513063
2023-01-24 07:37:44.436564: step: 824/529, loss: 0.023616492748260498
2023-01-24 07:37:45.515017: step: 828/529, loss: 0.004976135212928057
2023-01-24 07:37:46.578699: step: 832/529, loss: 0.004065125714987516
2023-01-24 07:37:47.641066: step: 836/529, loss: 0.0029577077366411686
2023-01-24 07:37:48.702388: step: 840/529, loss: 0.004215072840452194
2023-01-24 07:37:49.780590: step: 844/529, loss: 0.003447695402428508
2023-01-24 07:37:50.867899: step: 848/529, loss: 0.005496373865753412
2023-01-24 07:37:51.942654: step: 852/529, loss: 0.007129501551389694
2023-01-24 07:37:53.017413: step: 856/529, loss: 0.004603737033903599
2023-01-24 07:37:54.108621: step: 860/529, loss: 0.0175398588180542
2023-01-24 07:37:55.179152: step: 864/529, loss: 0.010939725674688816
2023-01-24 07:37:56.269380: step: 868/529, loss: 0.008177352137863636
2023-01-24 07:37:57.354090: step: 872/529, loss: 0.006134300492703915
2023-01-24 07:37:58.421374: step: 876/529, loss: 0.0037835538387298584
2023-01-24 07:37:59.531483: step: 880/529, loss: 0.011444897390902042
2023-01-24 07:38:00.596914: step: 884/529, loss: 0.019874265417456627
2023-01-24 07:38:01.686881: step: 888/529, loss: 0.0016192832263186574
2023-01-24 07:38:02.749812: step: 892/529, loss: 0.014175825752317905
2023-01-24 07:38:03.816606: step: 896/529, loss: 0.0023495086934417486
2023-01-24 07:38:04.881359: step: 900/529, loss: 0.006926489993929863
2023-01-24 07:38:05.938997: step: 904/529, loss: 0.01937299594283104
2023-01-24 07:38:07.014588: step: 908/529, loss: 0.010852350853383541
2023-01-24 07:38:08.088249: step: 912/529, loss: 0.02044033631682396
2023-01-24 07:38:09.156912: step: 916/529, loss: 0.01225733757019043
2023-01-24 07:38:10.239934: step: 920/529, loss: 0.010902819223701954
2023-01-24 07:38:11.305994: step: 924/529, loss: 0.0006711737369187176
2023-01-24 07:38:12.388027: step: 928/529, loss: 0.012211877852678299
2023-01-24 07:38:13.487014: step: 932/529, loss: 0.002037275116890669
2023-01-24 07:38:14.568480: step: 936/529, loss: 0.0019138348288834095
2023-01-24 07:38:15.654305: step: 940/529, loss: 0.0034044641070067883
2023-01-24 07:38:16.752877: step: 944/529, loss: 0.002331846859306097
2023-01-24 07:38:17.829989: step: 948/529, loss: 0.001319916220381856
2023-01-24 07:38:18.892576: step: 952/529, loss: 0.009768449701368809
2023-01-24 07:38:19.974418: step: 956/529, loss: 0.008089636452496052
2023-01-24 07:38:21.081851: step: 960/529, loss: 0.00013672596833202988
2023-01-24 07:38:22.160783: step: 964/529, loss: 0.007477053441107273
2023-01-24 07:38:23.225006: step: 968/529, loss: 0.0013338353019207716
2023-01-24 07:38:24.307143: step: 972/529, loss: 0.0058829886838793755
2023-01-24 07:38:25.384685: step: 976/529, loss: 0.005059738643467426
2023-01-24 07:38:26.450787: step: 980/529, loss: 0.0023297767620533705
2023-01-24 07:38:27.525390: step: 984/529, loss: 0.006030438467860222
2023-01-24 07:38:28.596948: step: 988/529, loss: 0.010914365760982037
2023-01-24 07:38:29.679870: step: 992/529, loss: 0.006999350618571043
2023-01-24 07:38:30.745919: step: 996/529, loss: 0.0009580472833476961
2023-01-24 07:38:31.809208: step: 1000/529, loss: 0.012078394182026386
2023-01-24 07:38:32.882546: step: 1004/529, loss: 0.0022896553855389357
2023-01-24 07:38:33.940974: step: 1008/529, loss: 0.00154294993262738
2023-01-24 07:38:35.022134: step: 1012/529, loss: 0.005238499026745558
2023-01-24 07:38:36.095362: step: 1016/529, loss: 0.005048517603427172
2023-01-24 07:38:37.173882: step: 1020/529, loss: 0.005287530366331339
2023-01-24 07:38:38.254944: step: 1024/529, loss: 0.012809209525585175
2023-01-24 07:38:39.354759: step: 1028/529, loss: 0.005282236263155937
2023-01-24 07:38:40.430515: step: 1032/529, loss: 0.007225828245282173
2023-01-24 07:38:41.503637: step: 1036/529, loss: 0.0038605937734246254
2023-01-24 07:38:42.581305: step: 1040/529, loss: 0.008390206843614578
2023-01-24 07:38:43.707102: step: 1044/529, loss: 0.0072082532569766045
2023-01-24 07:38:44.779362: step: 1048/529, loss: 0.0012835939414799213
2023-01-24 07:38:45.884023: step: 1052/529, loss: 0.010899576358497143
2023-01-24 07:38:46.968386: step: 1056/529, loss: 0.004053235985338688
2023-01-24 07:38:48.046257: step: 1060/529, loss: 0.002784229116514325
2023-01-24 07:38:49.114433: step: 1064/529, loss: 0.00917440839111805
2023-01-24 07:38:50.187153: step: 1068/529, loss: 0.008142219856381416
2023-01-24 07:38:51.265823: step: 1072/529, loss: 0.00158506294246763
2023-01-24 07:38:52.354839: step: 1076/529, loss: 0.014603233896195889
2023-01-24 07:38:53.423202: step: 1080/529, loss: 0.001800975645892322
2023-01-24 07:38:54.501588: step: 1084/529, loss: 0.0008096672245301306
2023-01-24 07:38:55.565454: step: 1088/529, loss: 0.0008882347028702497
2023-01-24 07:38:56.639546: step: 1092/529, loss: 5.980853529763408e-05
2023-01-24 07:38:57.716009: step: 1096/529, loss: 0.0019555939361453056
2023-01-24 07:38:58.806145: step: 1100/529, loss: 0.010712580755352974
2023-01-24 07:38:59.882179: step: 1104/529, loss: 0.00031959067564457655
2023-01-24 07:39:00.969035: step: 1108/529, loss: 0.0001488373236497864
2023-01-24 07:39:02.052210: step: 1112/529, loss: 0.0009048609645105898
2023-01-24 07:39:03.146745: step: 1116/529, loss: 0.0010535198962315917
2023-01-24 07:39:04.224392: step: 1120/529, loss: 0.0004017679311800748
2023-01-24 07:39:05.302077: step: 1124/529, loss: 0.002266225405037403
2023-01-24 07:39:06.378426: step: 1128/529, loss: 0.0054472372867167
2023-01-24 07:39:07.467123: step: 1132/529, loss: 0.0006995557341724634
2023-01-24 07:39:08.546051: step: 1136/529, loss: 0.03537345305085182
2023-01-24 07:39:09.618543: step: 1140/529, loss: 0.015552092343568802
2023-01-24 07:39:10.697946: step: 1144/529, loss: 0.00044780928874388337
2023-01-24 07:39:11.772752: step: 1148/529, loss: 0.008493904955685139
2023-01-24 07:39:12.875428: step: 1152/529, loss: 0.01671547442674637
2023-01-24 07:39:13.937231: step: 1156/529, loss: 0.0052228085696697235
2023-01-24 07:39:15.014913: step: 1160/529, loss: 0.019558357074856758
2023-01-24 07:39:16.085018: step: 1164/529, loss: 2.258449785585981e-05
2023-01-24 07:39:17.179132: step: 1168/529, loss: 0.007621017284691334
2023-01-24 07:39:18.252054: step: 1172/529, loss: 0.001624539028853178
2023-01-24 07:39:19.351548: step: 1176/529, loss: 0.005067102145403624
2023-01-24 07:39:20.445676: step: 1180/529, loss: 0.03003064915537834
2023-01-24 07:39:21.526613: step: 1184/529, loss: 0.0074188909493386745
2023-01-24 07:39:22.594886: step: 1188/529, loss: 0.0017773497384041548
2023-01-24 07:39:23.671962: step: 1192/529, loss: 0.004770188592374325
2023-01-24 07:39:24.751636: step: 1196/529, loss: 0.0003078423033002764
2023-01-24 07:39:25.844354: step: 1200/529, loss: 0.01505332812666893
2023-01-24 07:39:26.916743: step: 1204/529, loss: 0.012690840288996696
2023-01-24 07:39:27.994137: step: 1208/529, loss: 0.0045699733309447765
2023-01-24 07:39:29.067318: step: 1212/529, loss: 0.012958314269781113
2023-01-24 07:39:30.137344: step: 1216/529, loss: 0.018212882801890373
2023-01-24 07:39:31.225244: step: 1220/529, loss: 0.0046076057478785515
2023-01-24 07:39:32.319752: step: 1224/529, loss: 0.002567409072071314
2023-01-24 07:39:33.391654: step: 1228/529, loss: 0.0002043575223069638
2023-01-24 07:39:34.469521: step: 1232/529, loss: 0.002568405820056796
2023-01-24 07:39:35.555121: step: 1236/529, loss: 4.1959297959692776e-05
2023-01-24 07:39:36.634757: step: 1240/529, loss: 0.0026478685904294252
2023-01-24 07:39:37.713450: step: 1244/529, loss: 0.0012978308368474245
2023-01-24 07:39:38.810732: step: 1248/529, loss: 0.005010705441236496
2023-01-24 07:39:39.896005: step: 1252/529, loss: 0.015009735710918903
2023-01-24 07:39:40.972772: step: 1256/529, loss: 0.0007904329104349017
2023-01-24 07:39:42.037908: step: 1260/529, loss: 0.0034027108922600746
2023-01-24 07:39:43.130254: step: 1264/529, loss: 0.0326940156519413
2023-01-24 07:39:44.191927: step: 1268/529, loss: 0.00028689843020401895
2023-01-24 07:39:45.270860: step: 1272/529, loss: 0.011139270849525928
2023-01-24 07:39:46.366467: step: 1276/529, loss: 0.0010533812455832958
2023-01-24 07:39:47.445779: step: 1280/529, loss: 0.007056094706058502
2023-01-24 07:39:48.540133: step: 1284/529, loss: 0.0038725589402019978
2023-01-24 07:39:49.617278: step: 1288/529, loss: 0.00634577963501215
2023-01-24 07:39:50.700337: step: 1292/529, loss: 0.009059863165020943
2023-01-24 07:39:51.785609: step: 1296/529, loss: 0.00016235487419180572
2023-01-24 07:39:52.866348: step: 1300/529, loss: 0.005849065724760294
2023-01-24 07:39:53.932841: step: 1304/529, loss: 0.006454144138842821
2023-01-24 07:39:55.013636: step: 1308/529, loss: 0.000713278423063457
2023-01-24 07:39:56.121643: step: 1312/529, loss: 0.0006331218173727393
2023-01-24 07:39:57.188699: step: 1316/529, loss: 0.0023495752830058336
2023-01-24 07:39:58.277176: step: 1320/529, loss: 0.005079804453998804
2023-01-24 07:39:59.363271: step: 1324/529, loss: 0.0034808525815606117
2023-01-24 07:40:00.449597: step: 1328/529, loss: 0.003095766296610236
2023-01-24 07:40:01.525100: step: 1332/529, loss: 0.00925816223025322
2023-01-24 07:40:02.599198: step: 1336/529, loss: 0.008485754020512104
2023-01-24 07:40:03.687105: step: 1340/529, loss: 0.010287277400493622
2023-01-24 07:40:04.774655: step: 1344/529, loss: 0.003547879634425044
2023-01-24 07:40:05.864394: step: 1348/529, loss: 0.007376531604677439
2023-01-24 07:40:06.941988: step: 1352/529, loss: 0.00036150572123005986
2023-01-24 07:40:08.022044: step: 1356/529, loss: 0.01189280953258276
2023-01-24 07:40:09.082178: step: 1360/529, loss: 0.016222845762968063
2023-01-24 07:40:10.143862: step: 1364/529, loss: 0.007536229211837053
2023-01-24 07:40:11.239648: step: 1368/529, loss: 0.004005281254649162
2023-01-24 07:40:12.313206: step: 1372/529, loss: 0.012071509845554829
2023-01-24 07:40:13.409671: step: 1376/529, loss: 0.00499314209446311
2023-01-24 07:40:14.499152: step: 1380/529, loss: 0.00555872917175293
2023-01-24 07:40:15.574187: step: 1384/529, loss: 0.008989017456769943
2023-01-24 07:40:16.653800: step: 1388/529, loss: 0.0023135317023843527
2023-01-24 07:40:17.727830: step: 1392/529, loss: 0.0020052785985171795
2023-01-24 07:40:18.804574: step: 1396/529, loss: 0.0018481879960745573
2023-01-24 07:40:19.878523: step: 1400/529, loss: 0.005316754337400198
2023-01-24 07:40:20.954248: step: 1404/529, loss: 0.005384465213865042
2023-01-24 07:40:22.024547: step: 1408/529, loss: 0.0035632906947284937
2023-01-24 07:40:23.104624: step: 1412/529, loss: 0.007418631576001644
2023-01-24 07:40:24.192887: step: 1416/529, loss: 0.00488336430862546
2023-01-24 07:40:25.279806: step: 1420/529, loss: 0.0015416296664625406
2023-01-24 07:40:26.373906: step: 1424/529, loss: 0.006803611759096384
2023-01-24 07:40:27.461332: step: 1428/529, loss: 0.003949249163269997
2023-01-24 07:40:28.549299: step: 1432/529, loss: 0.006798784248530865
2023-01-24 07:40:29.633173: step: 1436/529, loss: 0.012535007670521736
2023-01-24 07:40:30.699965: step: 1440/529, loss: 0.00040682428516447544
2023-01-24 07:40:31.784184: step: 1444/529, loss: 0.003597379894927144
2023-01-24 07:40:32.854806: step: 1448/529, loss: 0.005746961571276188
2023-01-24 07:40:33.936447: step: 1452/529, loss: 0.0025634882040321827
2023-01-24 07:40:35.024989: step: 1456/529, loss: 0.012677955441176891
2023-01-24 07:40:36.100537: step: 1460/529, loss: 0.009069709107279778
2023-01-24 07:40:37.192500: step: 1464/529, loss: 0.012745595537126064
2023-01-24 07:40:38.255688: step: 1468/529, loss: 0.009782114066183567
2023-01-24 07:40:39.333091: step: 1472/529, loss: 0.0004659111727960408
2023-01-24 07:40:40.409357: step: 1476/529, loss: 0.003835623385384679
2023-01-24 07:40:41.487556: step: 1480/529, loss: 0.0060687074437737465
2023-01-24 07:40:42.573752: step: 1484/529, loss: 0.0006159237818792462
2023-01-24 07:40:43.644326: step: 1488/529, loss: 0.013183645904064178
2023-01-24 07:40:44.749931: step: 1492/529, loss: 0.005801281426101923
2023-01-24 07:40:45.831112: step: 1496/529, loss: 0.016578853130340576
2023-01-24 07:40:46.907504: step: 1500/529, loss: 0.0008852445753291249
2023-01-24 07:40:47.993176: step: 1504/529, loss: 0.02838902361690998
2023-01-24 07:40:49.075465: step: 1508/529, loss: 0.0008083205320872366
2023-01-24 07:40:50.171586: step: 1512/529, loss: 0.005692531354725361
2023-01-24 07:40:51.248009: step: 1516/529, loss: 0.003928464837372303
2023-01-24 07:40:52.317404: step: 1520/529, loss: 0.009461517445743084
2023-01-24 07:40:53.399234: step: 1524/529, loss: 0.0095612658187747
2023-01-24 07:40:54.456248: step: 1528/529, loss: 0.0062532140873372555
2023-01-24 07:40:55.534725: step: 1532/529, loss: 0.005272820126265287
2023-01-24 07:40:56.612042: step: 1536/529, loss: 0.003997983876615763
2023-01-24 07:40:57.695432: step: 1540/529, loss: 0.0035730230156332254
2023-01-24 07:40:58.784421: step: 1544/529, loss: 0.0037694217171519995
2023-01-24 07:40:59.870508: step: 1548/529, loss: 0.007433673366904259
2023-01-24 07:41:00.957654: step: 1552/529, loss: 0.002951303729787469
2023-01-24 07:41:02.050658: step: 1556/529, loss: 0.000823546084575355
2023-01-24 07:41:03.147569: step: 1560/529, loss: 0.0019693535286933184
2023-01-24 07:41:04.218992: step: 1564/529, loss: 0.0001680671120993793
2023-01-24 07:41:05.301422: step: 1568/529, loss: 0.004970727022737265
2023-01-24 07:41:06.390931: step: 1572/529, loss: 0.004377331584692001
2023-01-24 07:41:07.447675: step: 1576/529, loss: 0.009058392606675625
2023-01-24 07:41:08.520549: step: 1580/529, loss: 0.0016375655541196465
2023-01-24 07:41:09.601750: step: 1584/529, loss: 0.00201908010058105
2023-01-24 07:41:10.694119: step: 1588/529, loss: 0.0015947859501466155
2023-01-24 07:41:11.774390: step: 1592/529, loss: 0.00842420943081379
2023-01-24 07:41:12.887856: step: 1596/529, loss: 0.006397983990609646
2023-01-24 07:41:13.970555: step: 1600/529, loss: 0.006083968561142683
2023-01-24 07:41:15.069501: step: 1604/529, loss: 0.006729488261044025
2023-01-24 07:41:16.152046: step: 1608/529, loss: 0.02505103312432766
2023-01-24 07:41:17.223311: step: 1612/529, loss: 0.00016586524725425988
2023-01-24 07:41:18.295383: step: 1616/529, loss: 0.008201044984161854
2023-01-24 07:41:19.379415: step: 1620/529, loss: 0.00033281039213761687
2023-01-24 07:41:20.460465: step: 1624/529, loss: 0.0005419896915555
2023-01-24 07:41:21.538726: step: 1628/529, loss: 0.008269484154880047
2023-01-24 07:41:22.616216: step: 1632/529, loss: 0.0017122018616646528
2023-01-24 07:41:23.687757: step: 1636/529, loss: 0.06922311335802078
2023-01-24 07:41:24.771491: step: 1640/529, loss: 0.004820461850613356
2023-01-24 07:41:25.838072: step: 1644/529, loss: 0.012144972570240498
2023-01-24 07:41:26.919312: step: 1648/529, loss: 0.003677899017930031
2023-01-24 07:41:28.009747: step: 1652/529, loss: 0.01788925565779209
2023-01-24 07:41:29.094375: step: 1656/529, loss: 0.0032273477409034967
2023-01-24 07:41:30.166278: step: 1660/529, loss: 0.0028945133090019226
2023-01-24 07:41:31.244814: step: 1664/529, loss: 0.009249512106180191
2023-01-24 07:41:32.336435: step: 1668/529, loss: 0.004640126135200262
2023-01-24 07:41:33.405123: step: 1672/529, loss: 0.0012480197474360466
2023-01-24 07:41:34.477707: step: 1676/529, loss: 0.0064326198771595955
2023-01-24 07:41:35.535905: step: 1680/529, loss: 0.004940737504512072
2023-01-24 07:41:36.615310: step: 1684/529, loss: 0.011697688139975071
2023-01-24 07:41:37.685774: step: 1688/529, loss: 0.0
2023-01-24 07:41:38.765394: step: 1692/529, loss: 0.009908830747008324
2023-01-24 07:41:39.842950: step: 1696/529, loss: 0.006016677711158991
2023-01-24 07:41:40.910208: step: 1700/529, loss: 0.004238234832882881
2023-01-24 07:41:41.976155: step: 1704/529, loss: 0.007609625346958637
2023-01-24 07:41:43.038073: step: 1708/529, loss: 0.00047207679017446935
2023-01-24 07:41:44.095509: step: 1712/529, loss: 0.006124584935605526
2023-01-24 07:41:45.172351: step: 1716/529, loss: 0.019933952018618584
2023-01-24 07:41:46.233076: step: 1720/529, loss: 0.007246662862598896
2023-01-24 07:41:47.307741: step: 1724/529, loss: 0.00900278426706791
2023-01-24 07:41:48.372916: step: 1728/529, loss: 0.01211378164589405
2023-01-24 07:41:49.462845: step: 1732/529, loss: 0.00901151541620493
2023-01-24 07:41:50.532753: step: 1736/529, loss: 0.01022647600620985
2023-01-24 07:41:51.602515: step: 1740/529, loss: 0.0
2023-01-24 07:41:52.680403: step: 1744/529, loss: 0.007156314328312874
2023-01-24 07:41:53.736531: step: 1748/529, loss: 0.002353959484025836
2023-01-24 07:41:54.810690: step: 1752/529, loss: 0.016793211922049522
2023-01-24 07:41:55.882263: step: 1756/529, loss: 0.00508834095671773
2023-01-24 07:41:56.953209: step: 1760/529, loss: 0.0017321131890639663
2023-01-24 07:41:58.034536: step: 1764/529, loss: 0.00010371057578595355
2023-01-24 07:41:59.103986: step: 1768/529, loss: 0.030849751085042953
2023-01-24 07:42:00.182042: step: 1772/529, loss: 0.006752902641892433
2023-01-24 07:42:01.251224: step: 1776/529, loss: 0.004435475450009108
2023-01-24 07:42:02.333745: step: 1780/529, loss: 0.0037832336965948343
2023-01-24 07:42:03.402731: step: 1784/529, loss: 0.005638766568154097
2023-01-24 07:42:04.459118: step: 1788/529, loss: 0.007061276119202375
2023-01-24 07:42:05.532095: step: 1792/529, loss: 0.00024603374185971916
2023-01-24 07:42:06.618426: step: 1796/529, loss: 0.003160672727972269
2023-01-24 07:42:07.712199: step: 1800/529, loss: 0.013142304494976997
2023-01-24 07:42:08.803502: step: 1804/529, loss: 0.005885056219995022
2023-01-24 07:42:09.889121: step: 1808/529, loss: 0.009415185078978539
2023-01-24 07:42:10.949047: step: 1812/529, loss: 0.0065564364194869995
2023-01-24 07:42:12.016627: step: 1816/529, loss: 0.0025281747803092003
2023-01-24 07:42:13.103310: step: 1820/529, loss: 5.0830625696107745e-05
2023-01-24 07:42:14.188376: step: 1824/529, loss: 0.0009516460704617202
2023-01-24 07:42:15.259452: step: 1828/529, loss: 0.05348248407244682
2023-01-24 07:42:16.333560: step: 1832/529, loss: 0.007529357448220253
2023-01-24 07:42:17.400572: step: 1836/529, loss: 0.0030437230598181486
2023-01-24 07:42:18.477241: step: 1840/529, loss: 0.001966297160834074
2023-01-24 07:42:19.558798: step: 1844/529, loss: 0.038521189242601395
2023-01-24 07:42:20.634612: step: 1848/529, loss: 0.0017159967683255672
2023-01-24 07:42:21.718091: step: 1852/529, loss: 0.0024291304871439934
2023-01-24 07:42:22.798864: step: 1856/529, loss: 0.002658829092979431
2023-01-24 07:42:23.873647: step: 1860/529, loss: 0.0121042151004076
2023-01-24 07:42:24.951109: step: 1864/529, loss: 0.002069308655336499
2023-01-24 07:42:26.024473: step: 1868/529, loss: 0.029283249750733376
2023-01-24 07:42:27.124609: step: 1872/529, loss: 0.0024235681630671024
2023-01-24 07:42:28.198965: step: 1876/529, loss: 0.004316000267863274
2023-01-24 07:42:29.278490: step: 1880/529, loss: 0.005460443906486034
2023-01-24 07:42:30.370641: step: 1884/529, loss: 0.006304616574198008
2023-01-24 07:42:31.441470: step: 1888/529, loss: 0.02929220162332058
2023-01-24 07:42:32.537084: step: 1892/529, loss: 0.005456773564219475
2023-01-24 07:42:33.610383: step: 1896/529, loss: 0.001716810860671103
2023-01-24 07:42:34.674990: step: 1900/529, loss: 0.0020062385592609644
2023-01-24 07:42:35.767199: step: 1904/529, loss: 0.00724907498806715
2023-01-24 07:42:36.836270: step: 1908/529, loss: 0.005905916914343834
2023-01-24 07:42:37.925768: step: 1912/529, loss: 0.021696487441658974
2023-01-24 07:42:39.003677: step: 1916/529, loss: 0.005390317644923925
2023-01-24 07:42:40.087170: step: 1920/529, loss: 0.005775989964604378
2023-01-24 07:42:41.139834: step: 1924/529, loss: 0.010800627991557121
2023-01-24 07:42:42.205969: step: 1928/529, loss: 0.0019488058751448989
2023-01-24 07:42:43.284661: step: 1932/529, loss: 0.0028403939213603735
2023-01-24 07:42:44.347298: step: 1936/529, loss: 0.016468241810798645
2023-01-24 07:42:45.406433: step: 1940/529, loss: 0.008032802492380142
2023-01-24 07:42:46.478646: step: 1944/529, loss: 0.0039010082837194204
2023-01-24 07:42:47.554114: step: 1948/529, loss: 0.0011157785775139928
2023-01-24 07:42:48.632592: step: 1952/529, loss: 0.019286809489130974
2023-01-24 07:42:49.713453: step: 1956/529, loss: 0.009672509506344795
2023-01-24 07:42:50.775712: step: 1960/529, loss: 0.00016585277626290917
2023-01-24 07:42:51.834657: step: 1964/529, loss: 0.0013886081287637353
2023-01-24 07:42:52.925209: step: 1968/529, loss: 0.0017637466080486774
2023-01-24 07:42:54.009513: step: 1972/529, loss: 0.012323351576924324
2023-01-24 07:42:55.089359: step: 1976/529, loss: 0.007403888739645481
2023-01-24 07:42:56.159788: step: 1980/529, loss: 0.011588135734200478
2023-01-24 07:42:57.231559: step: 1984/529, loss: 0.02019616961479187
2023-01-24 07:42:58.300876: step: 1988/529, loss: 0.008840294554829597
2023-01-24 07:42:59.371071: step: 1992/529, loss: 0.0026347257662564516
2023-01-24 07:43:00.431753: step: 1996/529, loss: 0.00047466118121519685
2023-01-24 07:43:01.495458: step: 2000/529, loss: 0.0005630180821754038
2023-01-24 07:43:02.579921: step: 2004/529, loss: 0.005905618891119957
2023-01-24 07:43:03.656555: step: 2008/529, loss: 0.0031517362222075462
2023-01-24 07:43:04.708810: step: 2012/529, loss: 0.0063653071410954
2023-01-24 07:43:05.803656: step: 2016/529, loss: 0.006680846214294434
2023-01-24 07:43:06.883388: step: 2020/529, loss: 0.003968801815062761
2023-01-24 07:43:07.941801: step: 2024/529, loss: 0.00036190554965287447
2023-01-24 07:43:09.000607: step: 2028/529, loss: 0.006771177984774113
2023-01-24 07:43:10.060175: step: 2032/529, loss: 0.00410230690613389
2023-01-24 07:43:11.128310: step: 2036/529, loss: 0.011110005900263786
2023-01-24 07:43:12.192255: step: 2040/529, loss: 0.004130862187594175
2023-01-24 07:43:13.269800: step: 2044/529, loss: 0.0013060435885563493
2023-01-24 07:43:14.348414: step: 2048/529, loss: 0.010264605283737183
2023-01-24 07:43:15.439227: step: 2052/529, loss: 0.0068694911897182465
2023-01-24 07:43:16.532433: step: 2056/529, loss: 0.008920758962631226
2023-01-24 07:43:17.598018: step: 2060/529, loss: 0.0025634404737502337
2023-01-24 07:43:18.688457: step: 2064/529, loss: 0.013335098512470722
2023-01-24 07:43:19.767975: step: 2068/529, loss: 0.003870293963700533
2023-01-24 07:43:20.842017: step: 2072/529, loss: 0.015538040548563004
2023-01-24 07:43:21.926787: step: 2076/529, loss: 0.007456211838871241
2023-01-24 07:43:22.993935: step: 2080/529, loss: 0.001130507211200893
2023-01-24 07:43:24.063358: step: 2084/529, loss: 0.01031955424696207
2023-01-24 07:43:25.134496: step: 2088/529, loss: 0.02968425303697586
2023-01-24 07:43:26.224998: step: 2092/529, loss: 0.005661926697939634
2023-01-24 07:43:27.292827: step: 2096/529, loss: 0.0027986892964690924
2023-01-24 07:43:28.369890: step: 2100/529, loss: 0.012736142612993717
2023-01-24 07:43:29.443751: step: 2104/529, loss: 0.01918371580541134
2023-01-24 07:43:30.542547: step: 2108/529, loss: 0.06171911209821701
2023-01-24 07:43:31.622483: step: 2112/529, loss: 0.014033549465239048
2023-01-24 07:43:32.692069: step: 2116/529, loss: 0.005055828019976616
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33617943446035137, 'r': 0.29918055932050247, 'f1': 0.3166027204054313}, 'combined': 0.23328621503558095, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33048150691320305, 'r': 0.2928163351694189, 'f1': 0.31051088953638184}, 'combined': 0.20271695379059124, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3594640839561968, 'r': 0.35673570381231673, 'f1': 0.3580946969696969}, 'combined': 0.26385925039872404, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3571364565899927, 'r': 0.3138074011948833, 'f1': 0.3340728498043376}, 'combined': 0.2180993734473914, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3755679271042765, 'r': 0.3406479490623229, 'f1': 0.35725665503650583}, 'combined': 0.2632417458163727, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3674680027723465, 'r': 0.304647186121927, 'f1': 0.33312174723684074}, 'combined': 0.2174784463826007, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3888888888888889, 'r': 0.45652173913043476, 'f1': 0.42}, 'combined': 0.21, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36685769331243473, 'r': 0.36337707003622566, 'f1': 0.36510908657595986}, 'combined': 0.26902774800333884, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3573610613207894, 'r': 0.3133478423713539, 'f1': 0.3339103354554682}, 'combined': 0.21799327599683418, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:46:07.249601: step: 4/529, loss: 0.009177212603390217
2023-01-24 07:46:08.302037: step: 8/529, loss: 0.006231806706637144
2023-01-24 07:46:09.358353: step: 12/529, loss: 0.013157458044588566
2023-01-24 07:46:10.427219: step: 16/529, loss: 0.023935312405228615
2023-01-24 07:46:11.481917: step: 20/529, loss: 0.0008759293123148382
2023-01-24 07:46:12.556499: step: 24/529, loss: 0.0045522525906562805
2023-01-24 07:46:13.632774: step: 28/529, loss: 2.7001295165973715e-05
2023-01-24 07:46:14.688917: step: 32/529, loss: 0.019330311566591263
2023-01-24 07:46:15.782061: step: 36/529, loss: 0.010645509697496891
2023-01-24 07:46:16.848125: step: 40/529, loss: 0.0075593567453324795
2023-01-24 07:46:17.920788: step: 44/529, loss: 0.004905917681753635
2023-01-24 07:46:18.976911: step: 48/529, loss: 0.0021308085415512323
2023-01-24 07:46:20.048583: step: 52/529, loss: 0.005914323031902313
2023-01-24 07:46:21.119923: step: 56/529, loss: 0.005613838322460651
2023-01-24 07:46:22.177443: step: 60/529, loss: 0.009431330487132072
2023-01-24 07:46:23.249596: step: 64/529, loss: 0.005296084098517895
2023-01-24 07:46:24.323069: step: 68/529, loss: 0.003205634653568268
2023-01-24 07:46:25.405568: step: 72/529, loss: 0.006710636895149946
2023-01-24 07:46:26.471915: step: 76/529, loss: 0.019852634519338608
2023-01-24 07:46:27.523081: step: 80/529, loss: 0.0004563805996440351
2023-01-24 07:46:28.605007: step: 84/529, loss: 0.008617057465016842
2023-01-24 07:46:29.669433: step: 88/529, loss: 0.0058946493081748486
2023-01-24 07:46:30.731663: step: 92/529, loss: 0.003905066754668951
2023-01-24 07:46:31.799613: step: 96/529, loss: 0.0009366964222863317
2023-01-24 07:46:32.854345: step: 100/529, loss: 0.03207209333777428
2023-01-24 07:46:33.926245: step: 104/529, loss: 0.001331940060481429
2023-01-24 07:46:34.999155: step: 108/529, loss: 0.009211969561874866
2023-01-24 07:46:36.090964: step: 112/529, loss: 0.011316678486764431
2023-01-24 07:46:37.160163: step: 116/529, loss: 0.010628294199705124
2023-01-24 07:46:38.231165: step: 120/529, loss: 0.020939765498042107
2023-01-24 07:46:39.301399: step: 124/529, loss: 0.0007465697126463056
2023-01-24 07:46:40.371269: step: 128/529, loss: 0.002736742841079831
2023-01-24 07:46:41.428583: step: 132/529, loss: 0.0066178226843476295
2023-01-24 07:46:42.505883: step: 136/529, loss: 0.004855653736740351
2023-01-24 07:46:43.591433: step: 140/529, loss: 0.000464532058686018
2023-01-24 07:46:44.666439: step: 144/529, loss: 0.0036000816617161036
2023-01-24 07:46:45.749503: step: 148/529, loss: 0.009008240886032581
2023-01-24 07:46:46.816780: step: 152/529, loss: 0.002022910863161087
2023-01-24 07:46:47.899379: step: 156/529, loss: 0.01034573744982481
2023-01-24 07:46:48.967955: step: 160/529, loss: 0.01814563199877739
2023-01-24 07:46:50.045004: step: 164/529, loss: 0.00302757415920496
2023-01-24 07:46:51.125482: step: 168/529, loss: 0.010049357078969479
2023-01-24 07:46:52.203422: step: 172/529, loss: 0.011032577604055405
2023-01-24 07:46:53.295381: step: 176/529, loss: 0.006926556583493948
2023-01-24 07:46:54.378024: step: 180/529, loss: 0.004254165105521679
2023-01-24 07:46:55.454144: step: 184/529, loss: 0.0022481554187834263
2023-01-24 07:46:56.514303: step: 188/529, loss: 0.002917242469266057
2023-01-24 07:46:57.585268: step: 192/529, loss: 0.0072310976684093475
2023-01-24 07:46:58.665735: step: 196/529, loss: 0.007072195410728455
2023-01-24 07:46:59.744739: step: 200/529, loss: 0.005174529273062944
2023-01-24 07:47:00.825166: step: 204/529, loss: 0.02271167002618313
2023-01-24 07:47:01.909121: step: 208/529, loss: 0.0003428247000556439
2023-01-24 07:47:02.993907: step: 212/529, loss: 0.004607544280588627
2023-01-24 07:47:04.060556: step: 216/529, loss: 0.008299225009977818
2023-01-24 07:47:05.129305: step: 220/529, loss: 0.017638826742768288
2023-01-24 07:47:06.191201: step: 224/529, loss: 0.001121660228818655
2023-01-24 07:47:07.263246: step: 228/529, loss: 0.0048792557790875435
2023-01-24 07:47:08.324681: step: 232/529, loss: 0.005989342927932739
2023-01-24 07:47:09.395332: step: 236/529, loss: 0.008433006703853607
2023-01-24 07:47:10.458450: step: 240/529, loss: 0.0029687266796827316
2023-01-24 07:47:11.533254: step: 244/529, loss: 0.008188113570213318
2023-01-24 07:47:12.600413: step: 248/529, loss: 0.009621746838092804
2023-01-24 07:47:13.664148: step: 252/529, loss: 0.0005770410061813891
2023-01-24 07:47:14.736797: step: 256/529, loss: 0.0002183005417464301
2023-01-24 07:47:15.831641: step: 260/529, loss: 0.005462479777634144
2023-01-24 07:47:16.907869: step: 264/529, loss: 0.0034609134308993816
2023-01-24 07:47:17.976482: step: 268/529, loss: 0.010720867663621902
2023-01-24 07:47:19.041799: step: 272/529, loss: 0.00046243920223787427
2023-01-24 07:47:20.123031: step: 276/529, loss: 0.0012837282847613096
2023-01-24 07:47:21.198351: step: 280/529, loss: 0.002034065779298544
2023-01-24 07:47:22.260516: step: 284/529, loss: 0.0012776763178408146
2023-01-24 07:47:23.343937: step: 288/529, loss: 0.022065186873078346
2023-01-24 07:47:24.413937: step: 292/529, loss: 0.015671178698539734
2023-01-24 07:47:25.490839: step: 296/529, loss: 0.020309926941990852
2023-01-24 07:47:26.568715: step: 300/529, loss: 0.00212185550481081
2023-01-24 07:47:27.649502: step: 304/529, loss: 0.007124459370970726
2023-01-24 07:47:28.727820: step: 308/529, loss: 0.0035402572248131037
2023-01-24 07:47:29.794563: step: 312/529, loss: 0.0006490561063401401
2023-01-24 07:47:30.864697: step: 316/529, loss: 0.007779272738844156
2023-01-24 07:47:31.922757: step: 320/529, loss: 0.004670790396630764
2023-01-24 07:47:32.999010: step: 324/529, loss: 0.007918543182313442
2023-01-24 07:47:34.080853: step: 328/529, loss: 0.007585111539810896
2023-01-24 07:47:35.151072: step: 332/529, loss: 0.0010087236296385527
2023-01-24 07:47:36.220807: step: 336/529, loss: 0.017342330887913704
2023-01-24 07:47:37.315702: step: 340/529, loss: 0.0034432823304086924
2023-01-24 07:47:38.397242: step: 344/529, loss: 8.939124381868169e-05
2023-01-24 07:47:39.488264: step: 348/529, loss: 0.008808866143226624
2023-01-24 07:47:40.571930: step: 352/529, loss: 0.006594873033463955
2023-01-24 07:47:41.647098: step: 356/529, loss: 0.008746516890823841
2023-01-24 07:47:42.726859: step: 360/529, loss: 0.004234047140926123
2023-01-24 07:47:43.805548: step: 364/529, loss: 0.0005237410077825189
2023-01-24 07:47:44.871651: step: 368/529, loss: 0.001920199254527688
2023-01-24 07:47:45.953704: step: 372/529, loss: 0.013653873465955257
2023-01-24 07:47:47.018784: step: 376/529, loss: 0.0020227963104844093
2023-01-24 07:47:48.106074: step: 380/529, loss: 0.004719252232462168
2023-01-24 07:47:49.193901: step: 384/529, loss: 0.000996257527731359
2023-01-24 07:47:50.275542: step: 388/529, loss: 0.0007212611963041127
2023-01-24 07:47:51.342658: step: 392/529, loss: 0.0006773895001970232
2023-01-24 07:47:52.415964: step: 396/529, loss: 0.0007422130438499153
2023-01-24 07:47:53.496344: step: 400/529, loss: 0.0011392846936360002
2023-01-24 07:47:54.595731: step: 404/529, loss: 0.0002601121086627245
2023-01-24 07:47:55.684748: step: 408/529, loss: 0.0012339414097368717
2023-01-24 07:47:56.766524: step: 412/529, loss: 0.003740661544725299
2023-01-24 07:47:57.854182: step: 416/529, loss: 0.0035948576405644417
2023-01-24 07:47:58.928936: step: 420/529, loss: 0.000956323929131031
2023-01-24 07:48:00.017567: step: 424/529, loss: 0.0931340679526329
2023-01-24 07:48:01.092248: step: 428/529, loss: 0.0009822794236242771
2023-01-24 07:48:02.182599: step: 432/529, loss: 0.00559822004288435
2023-01-24 07:48:03.242757: step: 436/529, loss: 0.00013511610450223088
2023-01-24 07:48:04.314210: step: 440/529, loss: 0.027110062539577484
2023-01-24 07:48:05.388991: step: 444/529, loss: 0.0018125197384506464
2023-01-24 07:48:06.460976: step: 448/529, loss: 0.003616165369749069
2023-01-24 07:48:07.532791: step: 452/529, loss: 0.0017639797879382968
2023-01-24 07:48:08.623223: step: 456/529, loss: 0.0021489739883691072
2023-01-24 07:48:09.715362: step: 460/529, loss: 0.004466381389647722
2023-01-24 07:48:10.804810: step: 464/529, loss: 0.0029205146711319685
2023-01-24 07:48:11.891777: step: 468/529, loss: 0.0064828842878341675
2023-01-24 07:48:12.975515: step: 472/529, loss: 0.008500788360834122
2023-01-24 07:48:14.065009: step: 476/529, loss: 0.008972913958132267
2023-01-24 07:48:15.165758: step: 480/529, loss: 0.002545770490542054
2023-01-24 07:48:16.241064: step: 484/529, loss: 0.0036424424033612013
2023-01-24 07:48:17.343562: step: 488/529, loss: 0.019571540877223015
2023-01-24 07:48:18.430463: step: 492/529, loss: 0.0022102324292063713
2023-01-24 07:48:19.510391: step: 496/529, loss: 0.00277679692953825
2023-01-24 07:48:20.598953: step: 500/529, loss: 0.00978800654411316
2023-01-24 07:48:21.707358: step: 504/529, loss: 0.00016021693591028452
2023-01-24 07:48:22.801988: step: 508/529, loss: 0.0010758526623249054
2023-01-24 07:48:23.890608: step: 512/529, loss: 0.001040567411109805
2023-01-24 07:48:24.981131: step: 516/529, loss: 0.004138750955462456
2023-01-24 07:48:26.073455: step: 520/529, loss: 0.0023467293940484524
2023-01-24 07:48:27.156741: step: 524/529, loss: 0.005997047759592533
2023-01-24 07:48:28.258755: step: 528/529, loss: 0.012271576561033726
2023-01-24 07:48:29.359303: step: 532/529, loss: 0.0021466920152306557
2023-01-24 07:48:30.439324: step: 536/529, loss: 0.0004516357439570129
2023-01-24 07:48:31.536397: step: 540/529, loss: 0.004927820526063442
2023-01-24 07:48:32.620180: step: 544/529, loss: 0.0055756038054823875
2023-01-24 07:48:33.707816: step: 548/529, loss: 0.031241467222571373
2023-01-24 07:48:34.816373: step: 552/529, loss: 0.045850787311792374
2023-01-24 07:48:35.907829: step: 556/529, loss: 0.004398068878799677
2023-01-24 07:48:36.995643: step: 560/529, loss: 0.008083287626504898
2023-01-24 07:48:38.093474: step: 564/529, loss: 0.05309683457016945
2023-01-24 07:48:39.182525: step: 568/529, loss: 0.013529249466955662
2023-01-24 07:48:40.255724: step: 572/529, loss: 0.006030323449522257
2023-01-24 07:48:41.338284: step: 576/529, loss: 0.00357049866579473
2023-01-24 07:48:42.421281: step: 580/529, loss: 0.0033912579528987408
2023-01-24 07:48:43.498085: step: 584/529, loss: 0.0008257452282123268
2023-01-24 07:48:44.589435: step: 588/529, loss: 0.0028539581689983606
2023-01-24 07:48:45.672379: step: 592/529, loss: 0.007156797684729099
2023-01-24 07:48:46.743385: step: 596/529, loss: 0.00024271325673907995
2023-01-24 07:48:47.841061: step: 600/529, loss: 0.0028622762765735388
2023-01-24 07:48:48.920886: step: 604/529, loss: 0.007389379665255547
2023-01-24 07:48:49.993452: step: 608/529, loss: 0.004982942249625921
2023-01-24 07:48:51.066127: step: 612/529, loss: 0.008847521618008614
2023-01-24 07:48:52.148358: step: 616/529, loss: 0.0016525331884622574
2023-01-24 07:48:53.217738: step: 620/529, loss: 0.00505827646702528
2023-01-24 07:48:54.290687: step: 624/529, loss: 0.0021099450532346964
2023-01-24 07:48:55.386497: step: 628/529, loss: 0.004570155870169401
2023-01-24 07:48:56.471566: step: 632/529, loss: 0.00020336614397820085
2023-01-24 07:48:57.556957: step: 636/529, loss: 0.0035085943527519703
2023-01-24 07:48:58.652339: step: 640/529, loss: 0.005054764449596405
2023-01-24 07:48:59.749923: step: 644/529, loss: 0.0014001630479469895
2023-01-24 07:49:00.838072: step: 648/529, loss: 0.00033254941808991134
2023-01-24 07:49:01.924415: step: 652/529, loss: 0.0017622694140300155
2023-01-24 07:49:02.999898: step: 656/529, loss: 0.00035268146893940866
2023-01-24 07:49:04.092228: step: 660/529, loss: 0.010863285511732101
2023-01-24 07:49:05.184399: step: 664/529, loss: 0.0032234960235655308
2023-01-24 07:49:06.276095: step: 668/529, loss: 0.003366815857589245
2023-01-24 07:49:07.355434: step: 672/529, loss: 0.0008061127737164497
2023-01-24 07:49:08.438873: step: 676/529, loss: 0.0006125570507720113
2023-01-24 07:49:09.524223: step: 680/529, loss: 0.023458849638700485
2023-01-24 07:49:10.605785: step: 684/529, loss: 0.0019004769856110215
2023-01-24 07:49:11.702002: step: 688/529, loss: 0.0068727293983101845
2023-01-24 07:49:12.818472: step: 692/529, loss: 0.005446384195238352
2023-01-24 07:49:13.902720: step: 696/529, loss: 0.015116190537810326
2023-01-24 07:49:14.977230: step: 700/529, loss: 0.006550222635269165
2023-01-24 07:49:16.062577: step: 704/529, loss: 0.006168141029775143
2023-01-24 07:49:17.134346: step: 708/529, loss: 0.0056921085342764854
2023-01-24 07:49:18.209089: step: 712/529, loss: 0.010966421104967594
2023-01-24 07:49:19.307378: step: 716/529, loss: 0.003927030600607395
2023-01-24 07:49:20.372066: step: 720/529, loss: 3.948249650420621e-05
2023-01-24 07:49:21.462928: step: 724/529, loss: 0.00038617607788182795
2023-01-24 07:49:22.550877: step: 728/529, loss: 0.011211150325834751
2023-01-24 07:49:23.632304: step: 732/529, loss: 0.006522752344608307
2023-01-24 07:49:24.706192: step: 736/529, loss: 0.006303978152573109
2023-01-24 07:49:25.798166: step: 740/529, loss: 0.0022232637275010347
2023-01-24 07:49:26.892415: step: 744/529, loss: 0.0018562698969617486
2023-01-24 07:49:27.977068: step: 748/529, loss: 0.008830190636217594
2023-01-24 07:49:29.058887: step: 752/529, loss: 0.011314819566905499
2023-01-24 07:49:30.139123: step: 756/529, loss: 0.0017902416875585914
2023-01-24 07:49:31.210697: step: 760/529, loss: 0.0021212357096374035
2023-01-24 07:49:32.289650: step: 764/529, loss: 0.0058141001500189304
2023-01-24 07:49:33.368425: step: 768/529, loss: 0.0006642450462095439
2023-01-24 07:49:34.466759: step: 772/529, loss: 0.042035046964883804
2023-01-24 07:49:35.552703: step: 776/529, loss: 0.003217842895537615
2023-01-24 07:49:36.654475: step: 780/529, loss: 0.0028717005625367165
2023-01-24 07:49:37.741232: step: 784/529, loss: 0.0011830341536551714
2023-01-24 07:49:38.835228: step: 788/529, loss: 0.0028628401923924685
2023-01-24 07:49:39.913283: step: 792/529, loss: 0.0034351679496467113
2023-01-24 07:49:41.003288: step: 796/529, loss: 0.032102711498737335
2023-01-24 07:49:42.082655: step: 800/529, loss: 0.005031494423747063
2023-01-24 07:49:43.181299: step: 804/529, loss: 0.007227532099932432
2023-01-24 07:49:44.278336: step: 808/529, loss: 0.019073989242315292
2023-01-24 07:49:45.363179: step: 812/529, loss: 0.008997561410069466
2023-01-24 07:49:46.431592: step: 816/529, loss: 0.000582393491640687
2023-01-24 07:49:47.506079: step: 820/529, loss: 0.012501739896833897
2023-01-24 07:49:48.603904: step: 824/529, loss: 0.004014948848634958
2023-01-24 07:49:49.681833: step: 828/529, loss: 0.022581838071346283
2023-01-24 07:49:50.784116: step: 832/529, loss: 0.0025139066856354475
2023-01-24 07:49:51.872511: step: 836/529, loss: 0.0029055378399789333
2023-01-24 07:49:52.933277: step: 840/529, loss: 0.009847921319305897
2023-01-24 07:49:54.019323: step: 844/529, loss: 0.004913387354463339
2023-01-24 07:49:55.114690: step: 848/529, loss: 0.010944134555757046
2023-01-24 07:49:56.196398: step: 852/529, loss: 0.01431617233902216
2023-01-24 07:49:57.275190: step: 856/529, loss: 0.006244725547730923
2023-01-24 07:49:58.338015: step: 860/529, loss: 0.003779197810217738
2023-01-24 07:49:59.403469: step: 864/529, loss: 0.01293051429092884
2023-01-24 07:50:00.482466: step: 868/529, loss: 0.008084164932370186
2023-01-24 07:50:01.563788: step: 872/529, loss: 0.0003463590401224792
2023-01-24 07:50:02.651325: step: 876/529, loss: 0.0012960982276126742
2023-01-24 07:50:03.720153: step: 880/529, loss: 0.0007494304445572197
2023-01-24 07:50:04.808082: step: 884/529, loss: 0.012735312804579735
2023-01-24 07:50:05.886343: step: 888/529, loss: 0.00246731610968709
2023-01-24 07:50:06.966644: step: 892/529, loss: 0.0024457420222461224
2023-01-24 07:50:08.045293: step: 896/529, loss: 0.005838751792907715
2023-01-24 07:50:09.154476: step: 900/529, loss: 0.0006208329577930272
2023-01-24 07:50:10.251307: step: 904/529, loss: 0.008349798619747162
2023-01-24 07:50:11.366390: step: 908/529, loss: 0.0015658786287531257
2023-01-24 07:50:12.449387: step: 912/529, loss: 0.0029360074549913406
2023-01-24 07:50:13.536427: step: 916/529, loss: 0.0030074878595769405
2023-01-24 07:50:14.621718: step: 920/529, loss: 0.008125103078782558
2023-01-24 07:50:15.699330: step: 924/529, loss: 0.0003534247516654432
2023-01-24 07:50:16.789783: step: 928/529, loss: 0.005403808783739805
2023-01-24 07:50:17.854655: step: 932/529, loss: 0.0034687230363488197
2023-01-24 07:50:18.935601: step: 936/529, loss: 0.003291774308308959
2023-01-24 07:50:20.031391: step: 940/529, loss: 0.0038656878750771284
2023-01-24 07:50:21.102784: step: 944/529, loss: 0.00010822190961334854
2023-01-24 07:50:22.192127: step: 948/529, loss: 0.0027201964985579252
2023-01-24 07:50:23.281536: step: 952/529, loss: 0.014513666741549969
2023-01-24 07:50:24.370143: step: 956/529, loss: 0.0007798672304488719
2023-01-24 07:50:25.451347: step: 960/529, loss: 0.023821255192160606
2023-01-24 07:50:26.573985: step: 964/529, loss: 0.004256630316376686
2023-01-24 07:50:27.659686: step: 968/529, loss: 0.004839982837438583
2023-01-24 07:50:28.727662: step: 972/529, loss: 0.00023812487779650837
2023-01-24 07:50:29.816165: step: 976/529, loss: 0.005690691061317921
2023-01-24 07:50:30.894071: step: 980/529, loss: 0.0017980728298425674
2023-01-24 07:50:31.987413: step: 984/529, loss: 0.003909555729478598
2023-01-24 07:50:33.060632: step: 988/529, loss: 0.006293295416980982
2023-01-24 07:50:34.142645: step: 992/529, loss: 0.005559058859944344
2023-01-24 07:50:35.230248: step: 996/529, loss: 0.003048380371183157
2023-01-24 07:50:36.304364: step: 1000/529, loss: 0.003193227807059884
2023-01-24 07:50:37.382631: step: 1004/529, loss: 0.00016463841893710196
2023-01-24 07:50:38.465233: step: 1008/529, loss: 0.010374438017606735
2023-01-24 07:50:39.565008: step: 1012/529, loss: 0.0008038009400479496
2023-01-24 07:50:40.641237: step: 1016/529, loss: 0.0033988088835030794
2023-01-24 07:50:41.720387: step: 1020/529, loss: 0.0026192169170826674
2023-01-24 07:50:42.789704: step: 1024/529, loss: 0.016734879463911057
2023-01-24 07:50:43.846654: step: 1028/529, loss: 0.0007094732718542218
2023-01-24 07:50:44.926461: step: 1032/529, loss: 0.0018715693149715662
2023-01-24 07:50:46.022993: step: 1036/529, loss: 0.003840759629383683
2023-01-24 07:50:47.123422: step: 1040/529, loss: 0.009966296143829823
2023-01-24 07:50:48.217272: step: 1044/529, loss: 0.015022620558738708
2023-01-24 07:50:49.293153: step: 1048/529, loss: 0.002781221177428961
2023-01-24 07:50:50.377549: step: 1052/529, loss: 0.007517424877732992
2023-01-24 07:50:51.451950: step: 1056/529, loss: 0.000453771383035928
2023-01-24 07:50:52.528110: step: 1060/529, loss: 0.004217195324599743
2023-01-24 07:50:53.603672: step: 1064/529, loss: 0.002011943841353059
2023-01-24 07:50:54.686640: step: 1068/529, loss: 0.002803136594593525
2023-01-24 07:50:55.749738: step: 1072/529, loss: 0.0002057022211374715
2023-01-24 07:50:56.834412: step: 1076/529, loss: 0.008079002611339092
2023-01-24 07:50:57.903062: step: 1080/529, loss: 0.004181064199656248
2023-01-24 07:50:58.980184: step: 1084/529, loss: 0.00019540874927770346
2023-01-24 07:51:00.064809: step: 1088/529, loss: 0.00459140632301569
2023-01-24 07:51:01.138608: step: 1092/529, loss: 0.0012845245655626059
2023-01-24 07:51:02.221231: step: 1096/529, loss: 0.0027654164005070925
2023-01-24 07:51:03.295460: step: 1100/529, loss: 0.004545701202005148
2023-01-24 07:51:04.359774: step: 1104/529, loss: 0.0
2023-01-24 07:51:05.450288: step: 1108/529, loss: 0.006438740994781256
2023-01-24 07:51:06.526286: step: 1112/529, loss: 0.012592857703566551
2023-01-24 07:51:07.600105: step: 1116/529, loss: 0.001085448544472456
2023-01-24 07:51:08.670419: step: 1120/529, loss: 9.162333299173042e-05
2023-01-24 07:51:09.770815: step: 1124/529, loss: 0.001993956044316292
2023-01-24 07:51:10.833876: step: 1128/529, loss: 0.014985653571784496
2023-01-24 07:51:11.924027: step: 1132/529, loss: 0.007238594349473715
2023-01-24 07:51:13.016901: step: 1136/529, loss: 0.0006948950467631221
2023-01-24 07:51:14.091385: step: 1140/529, loss: 0.0012186398962512612
2023-01-24 07:51:15.172643: step: 1144/529, loss: 0.0074728853069245815
2023-01-24 07:51:16.255161: step: 1148/529, loss: 0.005998431704938412
2023-01-24 07:51:17.326850: step: 1152/529, loss: 0.017919017001986504
2023-01-24 07:51:18.413298: step: 1156/529, loss: 0.0010136482305824757
2023-01-24 07:51:19.484836: step: 1160/529, loss: 0.00255751283839345
2023-01-24 07:51:20.567481: step: 1164/529, loss: 0.00038443991797976196
2023-01-24 07:51:21.670936: step: 1168/529, loss: 0.0010660532861948013
2023-01-24 07:51:22.743370: step: 1172/529, loss: 0.004924565088003874
2023-01-24 07:51:23.831023: step: 1176/529, loss: 0.001071522245183587
2023-01-24 07:51:24.911173: step: 1180/529, loss: 0.0015187327517196536
2023-01-24 07:51:25.989832: step: 1184/529, loss: 0.00300554558634758
2023-01-24 07:51:27.069232: step: 1188/529, loss: 0.000765617354772985
2023-01-24 07:51:28.135971: step: 1192/529, loss: 0.0062858047895133495
2023-01-24 07:51:29.212091: step: 1196/529, loss: 1.7848709831014276e-05
2023-01-24 07:51:30.281679: step: 1200/529, loss: 0.013907291926443577
2023-01-24 07:51:31.354840: step: 1204/529, loss: 0.009092290885746479
2023-01-24 07:51:32.437261: step: 1208/529, loss: 0.008984521962702274
2023-01-24 07:51:33.517909: step: 1212/529, loss: 0.0009734661434777081
2023-01-24 07:51:34.599682: step: 1216/529, loss: 0.0009463827009312809
2023-01-24 07:51:35.673997: step: 1220/529, loss: 0.0012541133910417557
2023-01-24 07:51:36.752762: step: 1224/529, loss: 0.0026158480904996395
2023-01-24 07:51:37.826204: step: 1228/529, loss: 0.003346783807501197
2023-01-24 07:51:38.903197: step: 1232/529, loss: 0.002754059387370944
2023-01-24 07:51:39.982387: step: 1236/529, loss: 0.0016162253450602293
2023-01-24 07:51:41.068923: step: 1240/529, loss: 0.012374963611364365
2023-01-24 07:51:42.153538: step: 1244/529, loss: 0.00817466527223587
2023-01-24 07:51:43.245561: step: 1248/529, loss: 0.009739483706653118
2023-01-24 07:51:44.321408: step: 1252/529, loss: 0.002772791311144829
2023-01-24 07:51:45.388210: step: 1256/529, loss: 0.004882731940597296
2023-01-24 07:51:46.455861: step: 1260/529, loss: 0.0003424373862799257
2023-01-24 07:51:47.537396: step: 1264/529, loss: 0.002785620978102088
2023-01-24 07:51:48.623020: step: 1268/529, loss: 0.01190499309450388
2023-01-24 07:51:49.714657: step: 1272/529, loss: 0.0028960874769836664
2023-01-24 07:51:50.801051: step: 1276/529, loss: 0.001876495429314673
2023-01-24 07:51:51.893635: step: 1280/529, loss: 0.0038968604058027267
2023-01-24 07:51:52.966221: step: 1284/529, loss: 0.0014473608462139964
2023-01-24 07:51:54.055265: step: 1288/529, loss: 0.003630367573350668
2023-01-24 07:51:55.131631: step: 1292/529, loss: 0.0012406966416165233
2023-01-24 07:51:56.202440: step: 1296/529, loss: 0.0013465335359796882
2023-01-24 07:51:57.276216: step: 1300/529, loss: 0.006871648132801056
2023-01-24 07:51:58.360998: step: 1304/529, loss: 0.0028659726958721876
2023-01-24 07:51:59.450068: step: 1308/529, loss: 0.004046380519866943
2023-01-24 07:52:00.541179: step: 1312/529, loss: 0.025357460603117943
2023-01-24 07:52:01.618157: step: 1316/529, loss: 0.004396599717438221
2023-01-24 07:52:02.694041: step: 1320/529, loss: 0.006586793344467878
2023-01-24 07:52:03.773589: step: 1324/529, loss: 0.00811008084565401
2023-01-24 07:52:04.855639: step: 1328/529, loss: 0.002518047345802188
2023-01-24 07:52:05.915284: step: 1332/529, loss: 0.0019351443042978644
2023-01-24 07:52:06.988774: step: 1336/529, loss: 0.0009093194385059178
2023-01-24 07:52:08.069439: step: 1340/529, loss: 0.004282132722437382
2023-01-24 07:52:09.146569: step: 1344/529, loss: 0.0003690617741085589
2023-01-24 07:52:10.239310: step: 1348/529, loss: 0.003928898833692074
2023-01-24 07:52:11.313308: step: 1352/529, loss: 0.003199152648448944
2023-01-24 07:52:12.402162: step: 1356/529, loss: 0.003624142147600651
2023-01-24 07:52:13.468626: step: 1360/529, loss: 0.0029232895467430353
2023-01-24 07:52:14.561568: step: 1364/529, loss: 0.003160163527354598
2023-01-24 07:52:15.649472: step: 1368/529, loss: 0.018363306298851967
2023-01-24 07:52:16.736178: step: 1372/529, loss: 0.014122958295047283
2023-01-24 07:52:17.802054: step: 1376/529, loss: 0.0013863503700122237
2023-01-24 07:52:18.882249: step: 1380/529, loss: 0.005783788859844208
2023-01-24 07:52:19.972097: step: 1384/529, loss: 0.007065037731081247
2023-01-24 07:52:21.026555: step: 1388/529, loss: 0.0008020845707505941
2023-01-24 07:52:22.094905: step: 1392/529, loss: 0.000981620978564024
2023-01-24 07:52:23.171282: step: 1396/529, loss: 0.0009956590365618467
2023-01-24 07:52:24.255464: step: 1400/529, loss: 0.003136741230264306
2023-01-24 07:52:25.343658: step: 1404/529, loss: 0.0014253241242840886
2023-01-24 07:52:26.412459: step: 1408/529, loss: 0.0011652220273390412
2023-01-24 07:52:27.485965: step: 1412/529, loss: 0.001703666872344911
2023-01-24 07:52:28.551048: step: 1416/529, loss: 0.006479042582213879
2023-01-24 07:52:29.631693: step: 1420/529, loss: 0.004729365464299917
2023-01-24 07:52:30.722593: step: 1424/529, loss: 0.002865213667973876
2023-01-24 07:52:31.835294: step: 1428/529, loss: 0.0038078895304352045
2023-01-24 07:52:32.916522: step: 1432/529, loss: 0.001645090989768505
2023-01-24 07:52:33.982134: step: 1436/529, loss: 0.0028535800520330667
2023-01-24 07:52:35.075838: step: 1440/529, loss: 0.001665384159423411
2023-01-24 07:52:36.145589: step: 1444/529, loss: 0.018140381202101707
2023-01-24 07:52:37.211527: step: 1448/529, loss: 0.0005168024217709899
2023-01-24 07:52:38.292735: step: 1452/529, loss: 0.001085174735635519
2023-01-24 07:52:39.360959: step: 1456/529, loss: 0.0014501296682283282
2023-01-24 07:52:40.418429: step: 1460/529, loss: 0.027862543240189552
2023-01-24 07:52:41.500738: step: 1464/529, loss: 0.011404496617615223
2023-01-24 07:52:42.568390: step: 1468/529, loss: 0.0020065598655492067
2023-01-24 07:52:43.671812: step: 1472/529, loss: 0.001588613260537386
2023-01-24 07:52:44.752616: step: 1476/529, loss: 0.0068007418885827065
2023-01-24 07:52:45.838559: step: 1480/529, loss: 8.738425822230056e-05
2023-01-24 07:52:46.913958: step: 1484/529, loss: 0.013928217813372612
2023-01-24 07:52:47.980399: step: 1488/529, loss: 0.0001934495521709323
2023-01-24 07:52:49.057574: step: 1492/529, loss: 0.008348044008016586
2023-01-24 07:52:50.142158: step: 1496/529, loss: 0.013856679201126099
2023-01-24 07:52:51.226036: step: 1500/529, loss: 0.0014986825408414006
2023-01-24 07:52:52.300609: step: 1504/529, loss: 0.00015405072190333158
2023-01-24 07:52:53.368321: step: 1508/529, loss: 0.007739780005067587
2023-01-24 07:52:54.436850: step: 1512/529, loss: 0.0028329347260296345
2023-01-24 07:52:55.509156: step: 1516/529, loss: 0.0051941354759037495
2023-01-24 07:52:56.593240: step: 1520/529, loss: 0.010268112644553185
2023-01-24 07:52:57.677289: step: 1524/529, loss: 0.006983105558902025
2023-01-24 07:52:58.758592: step: 1528/529, loss: 0.0009511972893960774
2023-01-24 07:52:59.843904: step: 1532/529, loss: 0.0038837611209601164
2023-01-24 07:53:00.931542: step: 1536/529, loss: 0.002611966570839286
2023-01-24 07:53:02.014910: step: 1540/529, loss: 0.02525462582707405
2023-01-24 07:53:03.108761: step: 1544/529, loss: 0.005396829452365637
2023-01-24 07:53:04.181902: step: 1548/529, loss: 0.010904856957495213
2023-01-24 07:53:05.258247: step: 1552/529, loss: 0.007915393449366093
2023-01-24 07:53:06.333780: step: 1556/529, loss: 0.002802344737574458
2023-01-24 07:53:07.415971: step: 1560/529, loss: 0.006745410617440939
2023-01-24 07:53:08.506184: step: 1564/529, loss: 0.0031769820488989353
2023-01-24 07:53:09.567914: step: 1568/529, loss: 0.0
2023-01-24 07:53:10.634614: step: 1572/529, loss: 0.0027002287097275257
2023-01-24 07:53:11.724466: step: 1576/529, loss: 5.949012847850099e-05
2023-01-24 07:53:12.790637: step: 1580/529, loss: 0.012963945977389812
2023-01-24 07:53:13.858995: step: 1584/529, loss: 0.006360412575304508
2023-01-24 07:53:14.937220: step: 1588/529, loss: 0.002343586878851056
2023-01-24 07:53:16.017750: step: 1592/529, loss: 0.002032279735431075
2023-01-24 07:53:17.092920: step: 1596/529, loss: 0.0016265364829450846
2023-01-24 07:53:18.173595: step: 1600/529, loss: 0.011014615185558796
2023-01-24 07:53:19.247811: step: 1604/529, loss: 0.0033035501837730408
2023-01-24 07:53:20.324846: step: 1608/529, loss: 0.0005296764429658651
2023-01-24 07:53:21.406961: step: 1612/529, loss: 0.008404571563005447
2023-01-24 07:53:22.472277: step: 1616/529, loss: 0.011015924625098705
2023-01-24 07:53:23.534857: step: 1620/529, loss: 0.0012217392213642597
2023-01-24 07:53:24.613980: step: 1624/529, loss: 0.00406935578212142
2023-01-24 07:53:25.675160: step: 1628/529, loss: 0.006565426010638475
2023-01-24 07:53:26.744117: step: 1632/529, loss: 0.0009572013514116406
2023-01-24 07:53:27.833319: step: 1636/529, loss: 0.009375134482979774
2023-01-24 07:53:28.904601: step: 1640/529, loss: 0.015614711679518223
2023-01-24 07:53:29.997172: step: 1644/529, loss: 0.002346860943362117
2023-01-24 07:53:31.073570: step: 1648/529, loss: 0.0029121439438313246
2023-01-24 07:53:32.167749: step: 1652/529, loss: 0.001958949724212289
2023-01-24 07:53:33.250645: step: 1656/529, loss: 0.0004589745949488133
2023-01-24 07:53:34.323436: step: 1660/529, loss: 0.0029409106355160475
2023-01-24 07:53:35.399729: step: 1664/529, loss: 0.014715256169438362
2023-01-24 07:53:36.481268: step: 1668/529, loss: 0.00866536982357502
2023-01-24 07:53:37.571350: step: 1672/529, loss: 0.0025762272998690605
2023-01-24 07:53:38.668388: step: 1676/529, loss: 0.004894184414297342
2023-01-24 07:53:39.751006: step: 1680/529, loss: 0.01025621872395277
2023-01-24 07:53:40.812763: step: 1684/529, loss: 0.0006695187767036259
2023-01-24 07:53:41.887209: step: 1688/529, loss: 0.004675024189054966
2023-01-24 07:53:42.974089: step: 1692/529, loss: 0.00014494657807517797
2023-01-24 07:53:44.044283: step: 1696/529, loss: 0.000748831604141742
2023-01-24 07:53:45.128164: step: 1700/529, loss: 0.017094817012548447
2023-01-24 07:53:46.200184: step: 1704/529, loss: 0.01809392310678959
2023-01-24 07:53:47.273544: step: 1708/529, loss: 0.006069628056138754
2023-01-24 07:53:48.345829: step: 1712/529, loss: 0.003959669265896082
2023-01-24 07:53:49.435839: step: 1716/529, loss: 0.0005402990500442684
2023-01-24 07:53:50.536388: step: 1720/529, loss: 0.0004691762151196599
2023-01-24 07:53:51.615380: step: 1724/529, loss: 0.00016597381909377873
2023-01-24 07:53:52.722372: step: 1728/529, loss: 0.0009870573412626982
2023-01-24 07:53:53.814369: step: 1732/529, loss: 0.005165559239685535
2023-01-24 07:53:54.898763: step: 1736/529, loss: 0.002001678105443716
2023-01-24 07:53:55.994541: step: 1740/529, loss: 0.002589354757219553
2023-01-24 07:53:57.073971: step: 1744/529, loss: 0.001608711900189519
2023-01-24 07:53:58.168070: step: 1748/529, loss: 0.007137427106499672
2023-01-24 07:53:59.247260: step: 1752/529, loss: 0.012139768339693546
2023-01-24 07:54:00.330898: step: 1756/529, loss: 0.0017902354011312127
2023-01-24 07:54:01.397490: step: 1760/529, loss: 0.007811323739588261
2023-01-24 07:54:02.470253: step: 1764/529, loss: 0.013736235909163952
2023-01-24 07:54:03.547673: step: 1768/529, loss: 0.0160172488540411
2023-01-24 07:54:04.640638: step: 1772/529, loss: 0.009667756035923958
2023-01-24 07:54:05.720175: step: 1776/529, loss: 0.001788889872841537
2023-01-24 07:54:06.805167: step: 1780/529, loss: 0.0008035851642489433
2023-01-24 07:54:07.895276: step: 1784/529, loss: 0.00268270680680871
2023-01-24 07:54:08.970744: step: 1788/529, loss: 0.0014193312963470817
2023-01-24 07:54:10.049945: step: 1792/529, loss: 0.007340143900364637
2023-01-24 07:54:11.131946: step: 1796/529, loss: 0.0005057966918684542
2023-01-24 07:54:12.197764: step: 1800/529, loss: 0.004738260991871357
2023-01-24 07:54:13.294129: step: 1804/529, loss: 0.0031953398138284683
2023-01-24 07:54:14.368746: step: 1808/529, loss: 0.00093284179456532
2023-01-24 07:54:15.457527: step: 1812/529, loss: 0.0005930204642936587
2023-01-24 07:54:16.534176: step: 1816/529, loss: 0.008809304796159267
2023-01-24 07:54:17.612902: step: 1820/529, loss: 0.013269947841763496
2023-01-24 07:54:18.698666: step: 1824/529, loss: 0.0014831337612122297
2023-01-24 07:54:19.775209: step: 1828/529, loss: 0.0037388396449387074
2023-01-24 07:54:20.847350: step: 1832/529, loss: 0.003756570862606168
2023-01-24 07:54:21.919635: step: 1836/529, loss: 0.008058917708694935
2023-01-24 07:54:22.988584: step: 1840/529, loss: 0.006774854380637407
2023-01-24 07:54:24.083358: step: 1844/529, loss: 0.0005413430044427514
2023-01-24 07:54:25.173477: step: 1848/529, loss: 0.009238917380571365
2023-01-24 07:54:26.278239: step: 1852/529, loss: 0.005848722532391548
2023-01-24 07:54:27.343196: step: 1856/529, loss: 0.004729467444121838
2023-01-24 07:54:28.413043: step: 1860/529, loss: 0.016204742714762688
2023-01-24 07:54:29.480124: step: 1864/529, loss: 0.008855198509991169
2023-01-24 07:54:30.573499: step: 1868/529, loss: 0.11497065424919128
2023-01-24 07:54:31.653309: step: 1872/529, loss: 0.006695417687296867
2023-01-24 07:54:32.727434: step: 1876/529, loss: 0.0015388191677629948
2023-01-24 07:54:33.790120: step: 1880/529, loss: 0.003265910316258669
2023-01-24 07:54:34.871443: step: 1884/529, loss: 0.007440519984811544
2023-01-24 07:54:35.948005: step: 1888/529, loss: 0.006220884621143341
2023-01-24 07:54:37.040921: step: 1892/529, loss: 0.005961087066680193
2023-01-24 07:54:38.130196: step: 1896/529, loss: 0.0016540618380531669
2023-01-24 07:54:39.219044: step: 1900/529, loss: 0.0011557937832549214
2023-01-24 07:54:40.301456: step: 1904/529, loss: 0.00114920805208385
2023-01-24 07:54:41.387146: step: 1908/529, loss: 0.0007330832304432988
2023-01-24 07:54:42.454364: step: 1912/529, loss: 0.0055529153905808926
2023-01-24 07:54:43.545912: step: 1916/529, loss: 0.002856532344594598
2023-01-24 07:54:44.628695: step: 1920/529, loss: 0.0001175344514194876
2023-01-24 07:54:45.720613: step: 1924/529, loss: 0.003297254675999284
2023-01-24 07:54:46.796291: step: 1928/529, loss: 0.006175698712468147
2023-01-24 07:54:47.865551: step: 1932/529, loss: 0.00023109393077902496
2023-01-24 07:54:48.960026: step: 1936/529, loss: 0.002368801971897483
2023-01-24 07:54:50.046997: step: 1940/529, loss: 0.009190341457724571
2023-01-24 07:54:51.132704: step: 1944/529, loss: 0.0017559340922161937
2023-01-24 07:54:52.212914: step: 1948/529, loss: 0.033422596752643585
2023-01-24 07:54:53.310775: step: 1952/529, loss: 0.00014490677858702838
2023-01-24 07:54:54.383289: step: 1956/529, loss: 0.002352301497012377
2023-01-24 07:54:55.455897: step: 1960/529, loss: 0.010715760290622711
2023-01-24 07:54:56.530968: step: 1964/529, loss: 0.0015514919068664312
2023-01-24 07:54:57.623973: step: 1968/529, loss: 0.007033297326415777
2023-01-24 07:54:58.698622: step: 1972/529, loss: 0.00013565286644734442
2023-01-24 07:54:59.779826: step: 1976/529, loss: 0.0035234945826232433
2023-01-24 07:55:00.850799: step: 1980/529, loss: 0.010246050544083118
2023-01-24 07:55:01.937345: step: 1984/529, loss: 0.004345087334513664
2023-01-24 07:55:03.010878: step: 1988/529, loss: 0.0008381556835956872
2023-01-24 07:55:04.084310: step: 1992/529, loss: 0.0020852491725236177
2023-01-24 07:55:05.152772: step: 1996/529, loss: 0.007938524708151817
2023-01-24 07:55:06.222640: step: 2000/529, loss: 0.008011175319552422
2023-01-24 07:55:07.283603: step: 2004/529, loss: 0.02062593586742878
2023-01-24 07:55:08.374671: step: 2008/529, loss: 1.4936611478333361e-05
2023-01-24 07:55:09.458146: step: 2012/529, loss: 0.016349783167243004
2023-01-24 07:55:10.527321: step: 2016/529, loss: 0.00047937972703948617
2023-01-24 07:55:11.607967: step: 2020/529, loss: 0.008948408998548985
2023-01-24 07:55:12.689733: step: 2024/529, loss: 0.007444143295288086
2023-01-24 07:55:13.756028: step: 2028/529, loss: 0.0017338474281132221
2023-01-24 07:55:14.827702: step: 2032/529, loss: 0.0037951997946947813
2023-01-24 07:55:15.908036: step: 2036/529, loss: 0.007294212002307177
2023-01-24 07:55:17.000266: step: 2040/529, loss: 0.010114915668964386
2023-01-24 07:55:18.084293: step: 2044/529, loss: 0.007748943753540516
2023-01-24 07:55:19.160164: step: 2048/529, loss: 0.0004019513726234436
2023-01-24 07:55:20.239389: step: 2052/529, loss: 0.0006413411465473473
2023-01-24 07:55:21.309438: step: 2056/529, loss: 0.010674230754375458
2023-01-24 07:55:22.402499: step: 2060/529, loss: 0.016643160954117775
2023-01-24 07:55:23.472491: step: 2064/529, loss: 0.007731199264526367
2023-01-24 07:55:24.551135: step: 2068/529, loss: 0.00734926201403141
2023-01-24 07:55:25.630937: step: 2072/529, loss: 0.0012264309916645288
2023-01-24 07:55:26.708545: step: 2076/529, loss: 0.00308642047457397
2023-01-24 07:55:27.789190: step: 2080/529, loss: 4.6565954647803665e-08
2023-01-24 07:55:28.868916: step: 2084/529, loss: 0.001504861400462687
2023-01-24 07:55:29.959572: step: 2088/529, loss: 0.0007517228950746357
2023-01-24 07:55:31.039176: step: 2092/529, loss: 0.006435941904783249
2023-01-24 07:55:32.099986: step: 2096/529, loss: 0.00358761684037745
2023-01-24 07:55:33.162902: step: 2100/529, loss: 0.005381579510867596
2023-01-24 07:55:34.255435: step: 2104/529, loss: 0.013732613995671272
2023-01-24 07:55:35.320178: step: 2108/529, loss: 0.0004469332052394748
2023-01-24 07:55:36.378780: step: 2112/529, loss: 0.003604160388931632
2023-01-24 07:55:37.446290: step: 2116/529, loss: 0.0002558234555181116
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3397194782168187, 'r': 0.3029756257341647, 'f1': 0.3202972011271912}, 'combined': 0.23600846398845665, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33083247687818607, 'r': 0.2937354528164777, 'f1': 0.3111822518639998}, 'combined': 0.20315525251224856, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3581648417960798, 'r': 0.354087063711115, 'f1': 0.35611427972472826}, 'combined': 0.26239999558664184, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3578082053291881, 'r': 0.31472651884194214, 'f1': 0.33488748410761177}, 'combined': 0.21863120724123877, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38107226238122466, 'r': 0.3449173987776929, 'f1': 0.36209456007140267}, 'combined': 0.26680651794734933, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.37049681347511865, 'r': 0.3057960831807505, 'f1': 0.3350514989936118}, 'combined': 0.21873828431707298, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3581648417960798, 'r': 0.354087063711115, 'f1': 0.35611427972472826}, 'combined': 0.26239999558664184, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3578082053291881, 'r': 0.31472651884194214, 'f1': 0.33488748410761177}, 'combined': 0.21863120724123877, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:58:16.808655: step: 4/529, loss: 0.002799802692607045
2023-01-24 07:58:17.850225: step: 8/529, loss: 0.00098445825278759
2023-01-24 07:58:18.950217: step: 12/529, loss: 0.0031236563809216022
2023-01-24 07:58:20.023536: step: 16/529, loss: 0.003714518388733268
2023-01-24 07:58:21.093315: step: 20/529, loss: 0.004137910436838865
2023-01-24 07:58:22.178228: step: 24/529, loss: 0.001822648337110877
2023-01-24 07:58:23.232970: step: 28/529, loss: 0.0005741449422203004
2023-01-24 07:58:24.297090: step: 32/529, loss: 0.022738302126526833
2023-01-24 07:58:25.371074: step: 36/529, loss: 0.0022163265384733677
2023-01-24 07:58:26.445039: step: 40/529, loss: 0.005905527621507645
2023-01-24 07:58:27.515206: step: 44/529, loss: 0.007161538116633892
2023-01-24 07:58:28.594091: step: 48/529, loss: 0.001817191019654274
2023-01-24 07:58:29.681436: step: 52/529, loss: 0.005079301539808512
2023-01-24 07:58:30.757583: step: 56/529, loss: 0.014951029792428017
2023-01-24 07:58:31.823588: step: 60/529, loss: 0.01486099325120449
2023-01-24 07:58:32.890732: step: 64/529, loss: 0.004643063992261887
2023-01-24 07:58:33.978834: step: 68/529, loss: 0.001184926019050181
2023-01-24 07:58:35.037725: step: 72/529, loss: 0.0004509768623393029
2023-01-24 07:58:36.095513: step: 76/529, loss: 0.0016595391789451241
2023-01-24 07:58:37.167101: step: 80/529, loss: 0.0037661821115761995
2023-01-24 07:58:38.237868: step: 84/529, loss: 0.010828875005245209
2023-01-24 07:58:39.314162: step: 88/529, loss: 0.004606639500707388
2023-01-24 07:58:40.400082: step: 92/529, loss: 0.00365068344399333
2023-01-24 07:58:41.474155: step: 96/529, loss: 0.007801222149282694
2023-01-24 07:58:42.530801: step: 100/529, loss: 0.0074273813515901566
2023-01-24 07:58:43.620654: step: 104/529, loss: 0.0007517495541833341
2023-01-24 07:58:44.685032: step: 108/529, loss: 0.006015571765601635
2023-01-24 07:58:45.748054: step: 112/529, loss: 0.0025424775667488575
2023-01-24 07:58:46.817953: step: 116/529, loss: 0.0035228494089096785
2023-01-24 07:58:47.899547: step: 120/529, loss: 0.0049491506069898605
2023-01-24 07:58:48.956348: step: 124/529, loss: 0.0036107334308326244
2023-01-24 07:58:50.032620: step: 128/529, loss: 0.0030216840095818043
2023-01-24 07:58:51.100448: step: 132/529, loss: 0.002300210762768984
2023-01-24 07:58:52.164548: step: 136/529, loss: 0.004470197018235922
2023-01-24 07:58:53.246781: step: 140/529, loss: 0.0037267478182911873
2023-01-24 07:58:54.314607: step: 144/529, loss: 0.0051951101049780846
2023-01-24 07:58:55.374037: step: 148/529, loss: 0.004832123871892691
2023-01-24 07:58:56.430926: step: 152/529, loss: 0.0027162693440914154
2023-01-24 07:58:57.502440: step: 156/529, loss: 0.00048536615213379264
2023-01-24 07:58:58.570677: step: 160/529, loss: 0.003793970914557576
2023-01-24 07:58:59.655641: step: 164/529, loss: 0.006952115800231695
2023-01-24 07:59:00.751578: step: 168/529, loss: 0.0019066323293372989
2023-01-24 07:59:01.825859: step: 172/529, loss: 9.22923645703122e-05
2023-01-24 07:59:02.895013: step: 176/529, loss: 0.003931107930839062
2023-01-24 07:59:03.969127: step: 180/529, loss: 0.006486900616437197
2023-01-24 07:59:05.039833: step: 184/529, loss: 0.0009289022418670356
2023-01-24 07:59:06.109151: step: 188/529, loss: 0.0030753996688872576
2023-01-24 07:59:07.181077: step: 192/529, loss: 0.0028130351565778255
2023-01-24 07:59:08.272159: step: 196/529, loss: 0.006381553132086992
2023-01-24 07:59:09.347510: step: 200/529, loss: 4.228491889080033e-05
2023-01-24 07:59:10.425459: step: 204/529, loss: 0.01762462593615055
2023-01-24 07:59:11.508575: step: 208/529, loss: 3.691194433486089e-05
2023-01-24 07:59:12.568983: step: 212/529, loss: 0.0
2023-01-24 07:59:13.630497: step: 216/529, loss: 0.0024418069515377283
2023-01-24 07:59:14.706564: step: 220/529, loss: 0.003514789044857025
2023-01-24 07:59:15.779014: step: 224/529, loss: 0.0004902156651951373
2023-01-24 07:59:16.841912: step: 228/529, loss: 0.006283532362431288
2023-01-24 07:59:17.902632: step: 232/529, loss: 0.0024360523093491793
2023-01-24 07:59:18.983158: step: 236/529, loss: 0.003864196129143238
2023-01-24 07:59:20.057807: step: 240/529, loss: 0.00010936384205706418
2023-01-24 07:59:21.137053: step: 244/529, loss: 0.004691033158451319
2023-01-24 07:59:22.216358: step: 248/529, loss: 0.0032178163528442383
2023-01-24 07:59:23.289586: step: 252/529, loss: 0.003401032416149974
2023-01-24 07:59:24.368418: step: 256/529, loss: 0.013381686992943287
2023-01-24 07:59:25.436047: step: 260/529, loss: 0.002689080312848091
2023-01-24 07:59:26.508561: step: 264/529, loss: 0.0006650852737948298
2023-01-24 07:59:27.577435: step: 268/529, loss: 0.0049430374056100845
2023-01-24 07:59:28.651415: step: 272/529, loss: 0.005930429790169001
2023-01-24 07:59:29.750794: step: 276/529, loss: 0.0051653701812028885
2023-01-24 07:59:30.823709: step: 280/529, loss: 0.00038762151962146163
2023-01-24 07:59:31.897124: step: 284/529, loss: 0.00020901841344311833
2023-01-24 07:59:32.985535: step: 288/529, loss: 0.01706971600651741
2023-01-24 07:59:34.061967: step: 292/529, loss: 0.0012292361352592707
2023-01-24 07:59:35.151383: step: 296/529, loss: 0.006169318687170744
2023-01-24 07:59:36.209954: step: 300/529, loss: 0.000375593634089455
2023-01-24 07:59:37.288486: step: 304/529, loss: 0.0010701855644583702
2023-01-24 07:59:38.371636: step: 308/529, loss: 0.0005013360059820116
2023-01-24 07:59:39.429822: step: 312/529, loss: 0.0016539142234250903
2023-01-24 07:59:40.518490: step: 316/529, loss: 0.0019989381544291973
2023-01-24 07:59:41.590529: step: 320/529, loss: 0.0036413585767149925
2023-01-24 07:59:42.669877: step: 324/529, loss: 0.0043944972567260265
2023-01-24 07:59:43.744641: step: 328/529, loss: 0.0036881607957184315
2023-01-24 07:59:44.833346: step: 332/529, loss: 0.0032382241915911436
2023-01-24 07:59:45.912798: step: 336/529, loss: 0.0032929531298577785
2023-01-24 07:59:46.983305: step: 340/529, loss: 0.0062603517435491085
2023-01-24 07:59:48.055988: step: 344/529, loss: 0.006787760648876429
2023-01-24 07:59:49.127000: step: 348/529, loss: 0.0015887313056737185
2023-01-24 07:59:50.215643: step: 352/529, loss: 0.003251665737479925
2023-01-24 07:59:51.311631: step: 356/529, loss: 0.005710741505026817
2023-01-24 07:59:52.377646: step: 360/529, loss: 0.011052190326154232
2023-01-24 07:59:53.444797: step: 364/529, loss: 0.0020662425085902214
2023-01-24 07:59:54.528620: step: 368/529, loss: 0.008903606794774532
2023-01-24 07:59:55.616835: step: 372/529, loss: 0.004032880067825317
2023-01-24 07:59:56.686736: step: 376/529, loss: 0.002282926347106695
2023-01-24 07:59:57.765071: step: 380/529, loss: 0.003698973450809717
2023-01-24 07:59:58.840293: step: 384/529, loss: 0.0038311092648655176
2023-01-24 07:59:59.911132: step: 388/529, loss: 0.004132179077714682
2023-01-24 08:00:00.985960: step: 392/529, loss: 0.0023199536371976137
2023-01-24 08:00:02.067590: step: 396/529, loss: 0.002862815512344241
2023-01-24 08:00:03.128949: step: 400/529, loss: 0.010286512784659863
2023-01-24 08:00:04.196470: step: 404/529, loss: 0.0030006521847099066
2023-01-24 08:00:05.264374: step: 408/529, loss: 0.039712563157081604
2023-01-24 08:00:06.341556: step: 412/529, loss: 0.009774887003004551
2023-01-24 08:00:07.417591: step: 416/529, loss: 0.0008259558235295117
2023-01-24 08:00:08.484103: step: 420/529, loss: 0.0074269408360123634
2023-01-24 08:00:09.553783: step: 424/529, loss: 0.006902003660798073
2023-01-24 08:00:10.629305: step: 428/529, loss: 0.00027348060393705964
2023-01-24 08:00:11.689657: step: 432/529, loss: 0.0012583623174577951
2023-01-24 08:00:12.764930: step: 436/529, loss: 0.0007712326478213072
2023-01-24 08:00:13.853299: step: 440/529, loss: 0.01883554644882679
2023-01-24 08:00:14.923495: step: 444/529, loss: 0.00024521685554645956
2023-01-24 08:00:16.007559: step: 448/529, loss: 0.01075885258615017
2023-01-24 08:00:17.086632: step: 452/529, loss: 0.004799680318683386
2023-01-24 08:00:18.164653: step: 456/529, loss: 0.0005024845013394952
2023-01-24 08:00:19.248679: step: 460/529, loss: 0.0016516101313754916
2023-01-24 08:00:20.332106: step: 464/529, loss: 0.005199144594371319
2023-01-24 08:00:21.430495: step: 468/529, loss: 0.014054781757295132
2023-01-24 08:00:22.505401: step: 472/529, loss: 0.006899752654135227
2023-01-24 08:00:23.593770: step: 476/529, loss: 0.006904142908751965
2023-01-24 08:00:24.666293: step: 480/529, loss: 0.0005460199317894876
2023-01-24 08:00:25.739099: step: 484/529, loss: 0.003620860865339637
2023-01-24 08:00:26.822325: step: 488/529, loss: 0.009071952663362026
2023-01-24 08:00:27.892017: step: 492/529, loss: 3.001012373715639e-05
2023-01-24 08:00:28.961305: step: 496/529, loss: 0.013208171352744102
2023-01-24 08:00:30.052014: step: 500/529, loss: 0.002930690301582217
2023-01-24 08:00:31.131490: step: 504/529, loss: 0.00794550497084856
2023-01-24 08:00:32.208343: step: 508/529, loss: 0.005965706426650286
2023-01-24 08:00:33.282836: step: 512/529, loss: 0.0070600989274680614
2023-01-24 08:00:34.357365: step: 516/529, loss: 0.005748335737735033
2023-01-24 08:00:35.415736: step: 520/529, loss: 0.010124134831130505
2023-01-24 08:00:36.487003: step: 524/529, loss: 0.0030858267564326525
2023-01-24 08:00:37.548606: step: 528/529, loss: 1.776937779141008e-07
2023-01-24 08:00:38.614592: step: 532/529, loss: 0.008894138038158417
2023-01-24 08:00:39.685236: step: 536/529, loss: 0.0003888040955644101
2023-01-24 08:00:40.763348: step: 540/529, loss: 0.00016863054770510644
2023-01-24 08:00:41.824498: step: 544/529, loss: 0.01236016396433115
2023-01-24 08:00:42.891052: step: 548/529, loss: 0.0007682872237637639
2023-01-24 08:00:43.960548: step: 552/529, loss: 0.006971367169171572
2023-01-24 08:00:45.035216: step: 556/529, loss: 0.0015935538103803992
2023-01-24 08:00:46.142491: step: 560/529, loss: 0.002298989798873663
2023-01-24 08:00:47.218069: step: 564/529, loss: 0.0033600274473428726
2023-01-24 08:00:48.280994: step: 568/529, loss: 0.004706053528934717
2023-01-24 08:00:49.337779: step: 572/529, loss: 0.009068414568901062
2023-01-24 08:00:50.431478: step: 576/529, loss: 0.009056344628334045
2023-01-24 08:00:51.523133: step: 580/529, loss: 0.005143926944583654
2023-01-24 08:00:52.589717: step: 584/529, loss: 0.004690610803663731
2023-01-24 08:00:53.662065: step: 588/529, loss: 0.00041718213469721377
2023-01-24 08:00:54.726331: step: 592/529, loss: 0.0032455853652209044
2023-01-24 08:00:55.815331: step: 596/529, loss: 0.002281383378431201
2023-01-24 08:00:56.890937: step: 600/529, loss: 0.0002451192995067686
2023-01-24 08:00:57.957471: step: 604/529, loss: 0.007181620225310326
2023-01-24 08:00:59.008440: step: 608/529, loss: 0.005475702229887247
2023-01-24 08:01:00.101216: step: 612/529, loss: 0.0027037349063903093
2023-01-24 08:01:01.183132: step: 616/529, loss: 0.004738654475659132
2023-01-24 08:01:02.267319: step: 620/529, loss: 0.022524306550621986
2023-01-24 08:01:03.324189: step: 624/529, loss: 0.0028218678198754787
2023-01-24 08:01:04.394498: step: 628/529, loss: 0.0009046487975865602
2023-01-24 08:01:05.453611: step: 632/529, loss: 0.0018516629934310913
2023-01-24 08:01:06.526409: step: 636/529, loss: 0.0008893645135685802
2023-01-24 08:01:07.595663: step: 640/529, loss: 0.006917968392372131
2023-01-24 08:01:08.664731: step: 644/529, loss: 0.002134098904207349
2023-01-24 08:01:09.748141: step: 648/529, loss: 0.0018686726689338684
2023-01-24 08:01:10.840460: step: 652/529, loss: 0.0024751045275479555
2023-01-24 08:01:11.908219: step: 656/529, loss: 0.005321783944964409
2023-01-24 08:01:12.998495: step: 660/529, loss: 0.002583594061434269
2023-01-24 08:01:14.066170: step: 664/529, loss: 0.0026916086208075285
2023-01-24 08:01:15.134549: step: 668/529, loss: 0.004706230945885181
2023-01-24 08:01:16.224577: step: 672/529, loss: 0.0021738982759416103
2023-01-24 08:01:17.286606: step: 676/529, loss: 0.0013355562696233392
2023-01-24 08:01:18.359360: step: 680/529, loss: 0.006208792794495821
2023-01-24 08:01:19.421549: step: 684/529, loss: 0.001460074563510716
2023-01-24 08:01:20.509143: step: 688/529, loss: 0.0035437317565083504
2023-01-24 08:01:21.574100: step: 692/529, loss: 0.0006643783999606967
2023-01-24 08:01:22.658079: step: 696/529, loss: 0.004758054856210947
2023-01-24 08:01:23.726504: step: 700/529, loss: 0.012687666341662407
2023-01-24 08:01:24.780630: step: 704/529, loss: 0.0017439179355278611
2023-01-24 08:01:25.864963: step: 708/529, loss: 0.001834993134252727
2023-01-24 08:01:26.936164: step: 712/529, loss: 0.01399508211761713
2023-01-24 08:01:27.997693: step: 716/529, loss: 0.008070344105362892
2023-01-24 08:01:29.075786: step: 720/529, loss: 0.006971363443881273
2023-01-24 08:01:30.130694: step: 724/529, loss: 0.0007292046793736517
2023-01-24 08:01:31.201220: step: 728/529, loss: 0.0017946661682799459
2023-01-24 08:01:32.266621: step: 732/529, loss: 0.0030234334990382195
2023-01-24 08:01:33.334610: step: 736/529, loss: 0.0008042494300752878
2023-01-24 08:01:34.390754: step: 740/529, loss: 0.0010378105798736215
2023-01-24 08:01:35.478255: step: 744/529, loss: 0.012843229807913303
2023-01-24 08:01:36.544910: step: 748/529, loss: 0.021408304572105408
2023-01-24 08:01:37.627013: step: 752/529, loss: 0.00567891588434577
2023-01-24 08:01:38.682907: step: 756/529, loss: 0.0003825603344012052
2023-01-24 08:01:39.748433: step: 760/529, loss: 6.123925413703546e-05
2023-01-24 08:01:40.809780: step: 764/529, loss: 0.008799569681286812
2023-01-24 08:01:41.881019: step: 768/529, loss: 0.00476152403280139
2023-01-24 08:01:42.950636: step: 772/529, loss: 0.006334402598440647
2023-01-24 08:01:44.023790: step: 776/529, loss: 3.610803832998499e-05
2023-01-24 08:01:45.119497: step: 780/529, loss: 0.00034002639586105943
2023-01-24 08:01:46.191500: step: 784/529, loss: 0.012935356236994267
2023-01-24 08:01:47.257455: step: 788/529, loss: 0.0005749124102294445
2023-01-24 08:01:48.335328: step: 792/529, loss: 0.011290821246802807
2023-01-24 08:01:49.414705: step: 796/529, loss: 0.004592223558574915
2023-01-24 08:01:50.493917: step: 800/529, loss: 0.005901220254600048
2023-01-24 08:01:51.567778: step: 804/529, loss: 0.0009286381537094712
2023-01-24 08:01:52.641734: step: 808/529, loss: 0.004681146237999201
2023-01-24 08:01:53.704051: step: 812/529, loss: 0.0048268684186041355
2023-01-24 08:01:54.775204: step: 816/529, loss: 0.007325382903218269
2023-01-24 08:01:55.873113: step: 820/529, loss: 0.005948640406131744
2023-01-24 08:01:56.941463: step: 824/529, loss: 0.0006674726610071957
2023-01-24 08:01:58.009238: step: 828/529, loss: 0.007661811076104641
2023-01-24 08:01:59.077453: step: 832/529, loss: 0.018102621659636497
2023-01-24 08:02:00.165923: step: 836/529, loss: 0.0024864375591278076
2023-01-24 08:02:01.226799: step: 840/529, loss: 0.00022554029419552535
2023-01-24 08:02:02.298058: step: 844/529, loss: 0.0061652869917452335
2023-01-24 08:02:03.348969: step: 848/529, loss: 0.004371496848762035
2023-01-24 08:02:04.432040: step: 852/529, loss: 0.0037744506262242794
2023-01-24 08:02:05.499534: step: 856/529, loss: 0.0003453693352639675
2023-01-24 08:02:06.576127: step: 860/529, loss: 0.00436187582090497
2023-01-24 08:02:07.650355: step: 864/529, loss: 0.003474610624834895
2023-01-24 08:02:08.718085: step: 868/529, loss: 0.13750362396240234
2023-01-24 08:02:09.789764: step: 872/529, loss: 0.017220474779605865
2023-01-24 08:02:10.872522: step: 876/529, loss: 0.004889114759862423
2023-01-24 08:02:11.948382: step: 880/529, loss: 0.002652924507856369
2023-01-24 08:02:13.026632: step: 884/529, loss: 0.0029058349318802357
2023-01-24 08:02:14.097568: step: 888/529, loss: 0.002441678661853075
2023-01-24 08:02:15.174326: step: 892/529, loss: 0.0016899965703487396
2023-01-24 08:02:16.237176: step: 896/529, loss: 0.0053136046044528484
2023-01-24 08:02:17.304031: step: 900/529, loss: 0.03263198211789131
2023-01-24 08:02:18.366270: step: 904/529, loss: 0.0006510126986540854
2023-01-24 08:02:19.458525: step: 908/529, loss: 0.006777654867619276
2023-01-24 08:02:20.537310: step: 912/529, loss: 0.00010978826321661472
2023-01-24 08:02:21.609401: step: 916/529, loss: 0.0034061321057379246
2023-01-24 08:02:22.680470: step: 920/529, loss: 0.00019502728537190706
2023-01-24 08:02:23.749324: step: 924/529, loss: 0.0017094011418521404
2023-01-24 08:02:24.807458: step: 928/529, loss: 0.006432528607547283
2023-01-24 08:02:25.878735: step: 932/529, loss: 0.0008155680843628943
2023-01-24 08:02:26.944283: step: 936/529, loss: 0.0102853337302804
2023-01-24 08:02:28.015915: step: 940/529, loss: 0.006996444892138243
2023-01-24 08:02:29.095859: step: 944/529, loss: 0.0017697897274047136
2023-01-24 08:02:30.174687: step: 948/529, loss: 0.008571169339120388
2023-01-24 08:02:31.232349: step: 952/529, loss: 0.0005437851068563759
2023-01-24 08:02:32.288228: step: 956/529, loss: 0.016357216984033585
2023-01-24 08:02:33.353091: step: 960/529, loss: 0.004743458703160286
2023-01-24 08:02:34.435781: step: 964/529, loss: 0.05050304904580116
2023-01-24 08:02:35.513962: step: 968/529, loss: 0.00031291492632590234
2023-01-24 08:02:36.589591: step: 972/529, loss: 0.0016435356810688972
2023-01-24 08:02:37.656819: step: 976/529, loss: 2.594915531517472e-05
2023-01-24 08:02:38.736204: step: 980/529, loss: 0.001903029391542077
2023-01-24 08:02:39.823213: step: 984/529, loss: 0.0030033248476684093
2023-01-24 08:02:40.889336: step: 988/529, loss: 0.0005427224677987397
2023-01-24 08:02:41.952377: step: 992/529, loss: 0.000672551803290844
2023-01-24 08:02:43.028259: step: 996/529, loss: 0.002496907953172922
2023-01-24 08:02:44.107908: step: 1000/529, loss: 0.0018266845727339387
2023-01-24 08:02:45.185160: step: 1004/529, loss: 0.012097865343093872
2023-01-24 08:02:46.242672: step: 1008/529, loss: 0.008147796615958214
2023-01-24 08:02:47.319107: step: 1012/529, loss: 0.0016766826156526804
2023-01-24 08:02:48.382663: step: 1016/529, loss: 0.005306873004883528
2023-01-24 08:02:49.439834: step: 1020/529, loss: 0.005997353233397007
2023-01-24 08:02:50.497693: step: 1024/529, loss: 0.00370508199557662
2023-01-24 08:02:51.565204: step: 1028/529, loss: 0.011876273900270462
2023-01-24 08:02:52.638180: step: 1032/529, loss: 0.004483404103666544
2023-01-24 08:02:53.720623: step: 1036/529, loss: 0.0014186983462423086
2023-01-24 08:02:54.786281: step: 1040/529, loss: 7.65753211453557e-05
2023-01-24 08:02:55.846050: step: 1044/529, loss: 0.0012655870523303747
2023-01-24 08:02:56.928752: step: 1048/529, loss: 0.0026184390299022198
2023-01-24 08:02:57.996616: step: 1052/529, loss: 0.004399022553116083
2023-01-24 08:02:59.074891: step: 1056/529, loss: 0.0017807999392971396
2023-01-24 08:03:00.157857: step: 1060/529, loss: 0.008361397311091423
2023-01-24 08:03:01.221681: step: 1064/529, loss: 0.015588500536978245
2023-01-24 08:03:02.286245: step: 1068/529, loss: 0.005209534429013729
2023-01-24 08:03:03.362068: step: 1072/529, loss: 0.01267347950488329
2023-01-24 08:03:04.449588: step: 1076/529, loss: 0.00047251611249521375
2023-01-24 08:03:05.521101: step: 1080/529, loss: 0.0013504591770470142
2023-01-24 08:03:06.582741: step: 1084/529, loss: 0.01155027374625206
2023-01-24 08:03:07.653451: step: 1088/529, loss: 0.0006555234431289136
2023-01-24 08:03:08.725587: step: 1092/529, loss: 0.001129095209762454
2023-01-24 08:03:09.799619: step: 1096/529, loss: 0.009894326329231262
2023-01-24 08:03:10.867237: step: 1100/529, loss: 6.452338129747659e-05
2023-01-24 08:03:11.948187: step: 1104/529, loss: 0.005296661984175444
2023-01-24 08:03:13.027746: step: 1108/529, loss: 0.0045640189200639725
2023-01-24 08:03:14.094773: step: 1112/529, loss: 0.0005523888976313174
2023-01-24 08:03:15.154367: step: 1116/529, loss: 0.007128852419555187
2023-01-24 08:03:16.231973: step: 1120/529, loss: 0.006258789449930191
2023-01-24 08:03:17.300678: step: 1124/529, loss: 0.0005953112849965692
2023-01-24 08:03:18.386459: step: 1128/529, loss: 6.748545274604112e-05
2023-01-24 08:03:19.445191: step: 1132/529, loss: 0.0044932314194738865
2023-01-24 08:03:20.503981: step: 1136/529, loss: 0.009857969358563423
2023-01-24 08:03:21.573706: step: 1140/529, loss: 0.0021883067674934864
2023-01-24 08:03:22.661869: step: 1144/529, loss: 0.0003860625147353858
2023-01-24 08:03:23.725484: step: 1148/529, loss: 0.005602306220680475
2023-01-24 08:03:24.795106: step: 1152/529, loss: 0.016554484143853188
2023-01-24 08:03:25.871542: step: 1156/529, loss: 0.0034943840000778437
2023-01-24 08:03:26.931662: step: 1160/529, loss: 0.0005029496969655156
2023-01-24 08:03:28.004093: step: 1164/529, loss: 0.0033986091148108244
2023-01-24 08:03:29.095780: step: 1168/529, loss: 0.0015404887963086367
2023-01-24 08:03:30.173418: step: 1172/529, loss: 0.0011166732292622328
2023-01-24 08:03:31.256595: step: 1176/529, loss: 0.0002667238295543939
2023-01-24 08:03:32.328782: step: 1180/529, loss: 0.002281706314533949
2023-01-24 08:03:33.436844: step: 1184/529, loss: 0.002955926116555929
2023-01-24 08:03:34.503363: step: 1188/529, loss: 0.009445217438042164
2023-01-24 08:03:35.577760: step: 1192/529, loss: 0.0018050877843052149
2023-01-24 08:03:36.627650: step: 1196/529, loss: 0.0003661549126263708
2023-01-24 08:03:37.705356: step: 1200/529, loss: 0.003146685427054763
2023-01-24 08:03:38.766467: step: 1204/529, loss: 0.0028313391376286745
2023-01-24 08:03:39.830495: step: 1208/529, loss: 0.022725306451320648
2023-01-24 08:03:40.908988: step: 1212/529, loss: 0.011618991382420063
2023-01-24 08:03:41.987365: step: 1216/529, loss: 0.007653260137885809
2023-01-24 08:03:43.089669: step: 1220/529, loss: 0.013248827308416367
2023-01-24 08:03:44.148934: step: 1224/529, loss: 0.0005917140515521169
2023-01-24 08:03:45.227763: step: 1228/529, loss: 0.007229936774820089
2023-01-24 08:03:46.300483: step: 1232/529, loss: 0.003560977755114436
2023-01-24 08:03:47.381641: step: 1236/529, loss: 0.002076733158901334
2023-01-24 08:03:48.473057: step: 1240/529, loss: 0.0009652223670855165
2023-01-24 08:03:49.539695: step: 1244/529, loss: 0.0056844064965844154
2023-01-24 08:03:50.608530: step: 1248/529, loss: 0.00021671729336958379
2023-01-24 08:03:51.687034: step: 1252/529, loss: 0.0025617831852287054
2023-01-24 08:03:52.757395: step: 1256/529, loss: 0.000589905132073909
2023-01-24 08:03:53.828056: step: 1260/529, loss: 0.009309370070695877
2023-01-24 08:03:54.896447: step: 1264/529, loss: 0.0037129605188965797
2023-01-24 08:03:55.976204: step: 1268/529, loss: 0.0019228963647037745
2023-01-24 08:03:57.068598: step: 1272/529, loss: 0.0028096914757043123
2023-01-24 08:03:58.129708: step: 1276/529, loss: 0.004148928448557854
2023-01-24 08:03:59.177982: step: 1280/529, loss: 0.0018817471573129296
2023-01-24 08:04:00.261211: step: 1284/529, loss: 0.00251255976036191
2023-01-24 08:04:01.344535: step: 1288/529, loss: 0.0020330878905951977
2023-01-24 08:04:02.421690: step: 1292/529, loss: 0.001012020860798657
2023-01-24 08:04:03.502441: step: 1296/529, loss: 0.0066626910120248795
2023-01-24 08:04:04.573474: step: 1300/529, loss: 0.0016276236856356263
2023-01-24 08:04:05.635626: step: 1304/529, loss: 0.001064040930941701
2023-01-24 08:04:06.695616: step: 1308/529, loss: 0.0023552991915494204
2023-01-24 08:04:07.763371: step: 1312/529, loss: 0.0011800406500697136
2023-01-24 08:04:08.836902: step: 1316/529, loss: 0.0010205378057435155
2023-01-24 08:04:09.914942: step: 1320/529, loss: 0.0043399096466600895
2023-01-24 08:04:10.996340: step: 1324/529, loss: 0.0019996531773358583
2023-01-24 08:04:12.075140: step: 1328/529, loss: 0.0013175040949136019
2023-01-24 08:04:13.162835: step: 1332/529, loss: 0.008157377131283283
2023-01-24 08:04:14.238182: step: 1336/529, loss: 1.0361813110648654e-05
2023-01-24 08:04:15.313431: step: 1340/529, loss: 0.010931240394711494
2023-01-24 08:04:16.393443: step: 1344/529, loss: 0.004290084820240736
2023-01-24 08:04:17.460000: step: 1348/529, loss: 0.001613378175534308
2023-01-24 08:04:18.534195: step: 1352/529, loss: 0.005706457886844873
2023-01-24 08:04:19.618817: step: 1356/529, loss: 0.0011905826395377517
2023-01-24 08:04:20.689945: step: 1360/529, loss: 0.0011665733763948083
2023-01-24 08:04:21.765140: step: 1364/529, loss: 0.002651187125593424
2023-01-24 08:04:22.825375: step: 1368/529, loss: 0.002460924908518791
2023-01-24 08:04:23.888772: step: 1372/529, loss: 0.0012857065303251147
2023-01-24 08:04:24.981148: step: 1376/529, loss: 0.000723969773389399
2023-01-24 08:04:26.054675: step: 1380/529, loss: 0.005783837754279375
2023-01-24 08:04:27.118675: step: 1384/529, loss: 0.0018851591739803553
2023-01-24 08:04:28.183171: step: 1388/529, loss: 0.0002665466454345733
2023-01-24 08:04:29.248575: step: 1392/529, loss: 0.003083331510424614
2023-01-24 08:04:30.315094: step: 1396/529, loss: 0.00038746505742892623
2023-01-24 08:04:31.390293: step: 1400/529, loss: 0.004574262537062168
2023-01-24 08:04:32.466964: step: 1404/529, loss: 0.00023623576271347702
2023-01-24 08:04:33.544176: step: 1408/529, loss: 0.013189992867410183
2023-01-24 08:04:34.622224: step: 1412/529, loss: 0.0001180979234050028
2023-01-24 08:04:35.704887: step: 1416/529, loss: 0.0003545752842910588
2023-01-24 08:04:36.776377: step: 1420/529, loss: 0.002352015348151326
2023-01-24 08:04:37.857438: step: 1424/529, loss: 0.0014859104994684458
2023-01-24 08:04:38.922651: step: 1428/529, loss: 3.6385048588272184e-05
2023-01-24 08:04:40.008399: step: 1432/529, loss: 0.004082232713699341
2023-01-24 08:04:41.071585: step: 1436/529, loss: 0.005047069396823645
2023-01-24 08:04:42.132778: step: 1440/529, loss: 0.0016998436767607927
2023-01-24 08:04:43.208397: step: 1444/529, loss: 0.017887288704514503
2023-01-24 08:04:44.289653: step: 1448/529, loss: 0.0119456322863698
2023-01-24 08:04:45.356356: step: 1452/529, loss: 0.0003369227342773229
2023-01-24 08:04:46.439820: step: 1456/529, loss: 0.0014498044038191438
2023-01-24 08:04:47.529121: step: 1460/529, loss: 0.001330201979726553
2023-01-24 08:04:48.611414: step: 1464/529, loss: 0.03399517014622688
2023-01-24 08:04:49.698968: step: 1468/529, loss: 0.0009036113042384386
2023-01-24 08:04:50.758525: step: 1472/529, loss: 0.009424423798918724
2023-01-24 08:04:51.831797: step: 1476/529, loss: 0.0045033469796180725
2023-01-24 08:04:52.905363: step: 1480/529, loss: 0.006226568948477507
2023-01-24 08:04:53.979922: step: 1484/529, loss: 0.005201412830501795
2023-01-24 08:04:55.046121: step: 1488/529, loss: 0.0070693036541342735
2023-01-24 08:04:56.125271: step: 1492/529, loss: 0.004682602360844612
2023-01-24 08:04:57.206206: step: 1496/529, loss: 0.007212301250547171
2023-01-24 08:04:58.284148: step: 1500/529, loss: 0.00461286585777998
2023-01-24 08:04:59.365655: step: 1504/529, loss: 0.0016360811423510313
2023-01-24 08:05:00.438387: step: 1508/529, loss: 0.0006825494929216802
2023-01-24 08:05:01.497073: step: 1512/529, loss: 0.0022835417184978724
2023-01-24 08:05:02.571276: step: 1516/529, loss: 0.005479033105075359
2023-01-24 08:05:03.658481: step: 1520/529, loss: 0.030284978449344635
2023-01-24 08:05:04.731904: step: 1524/529, loss: 0.00014283962082117796
2023-01-24 08:05:05.809502: step: 1528/529, loss: 0.0026233394164592028
2023-01-24 08:05:06.873767: step: 1532/529, loss: 0.0020527131855487823
2023-01-24 08:05:07.955605: step: 1536/529, loss: 0.0002474638749845326
2023-01-24 08:05:09.021528: step: 1540/529, loss: 0.0013742984738200903
2023-01-24 08:05:10.113607: step: 1544/529, loss: 0.008978042751550674
2023-01-24 08:05:11.191528: step: 1548/529, loss: 0.00020447769202291965
2023-01-24 08:05:12.263006: step: 1552/529, loss: 0.002034167991951108
2023-01-24 08:05:13.356283: step: 1556/529, loss: 0.00557552557438612
2023-01-24 08:05:14.438268: step: 1560/529, loss: 0.0009481045417487621
2023-01-24 08:05:15.494346: step: 1564/529, loss: 0.0010191145120188594
2023-01-24 08:05:16.578712: step: 1568/529, loss: 0.001281422097235918
2023-01-24 08:05:17.691679: step: 1572/529, loss: 0.0063865589909255505
2023-01-24 08:05:18.764560: step: 1576/529, loss: 0.00016970594879239798
2023-01-24 08:05:19.832761: step: 1580/529, loss: 0.007933572866022587
2023-01-24 08:05:20.917281: step: 1584/529, loss: 0.0042253597639501095
2023-01-24 08:05:21.991000: step: 1588/529, loss: 0.0011132482904940844
2023-01-24 08:05:23.055542: step: 1592/529, loss: 0.0014076882507652044
2023-01-24 08:05:24.134313: step: 1596/529, loss: 0.024389734491705894
2023-01-24 08:05:25.224314: step: 1600/529, loss: 0.0030206141527742147
2023-01-24 08:05:26.303941: step: 1604/529, loss: 0.001388438744470477
2023-01-24 08:05:27.361435: step: 1608/529, loss: 0.012383831664919853
2023-01-24 08:05:28.430765: step: 1612/529, loss: 0.002930454211309552
2023-01-24 08:05:29.524225: step: 1616/529, loss: 0.007121201604604721
2023-01-24 08:05:30.599991: step: 1620/529, loss: 0.0420500710606575
2023-01-24 08:05:31.673522: step: 1624/529, loss: 0.006728779058903456
2023-01-24 08:05:32.750507: step: 1628/529, loss: 0.0018686304101720452
2023-01-24 08:05:33.841540: step: 1632/529, loss: 0.0014674749691039324
2023-01-24 08:05:34.913240: step: 1636/529, loss: 0.0005261803744360805
2023-01-24 08:05:35.981804: step: 1640/529, loss: 0.007460297085344791
2023-01-24 08:05:37.068860: step: 1644/529, loss: 0.006846974138170481
2023-01-24 08:05:38.157581: step: 1648/529, loss: 0.00816772785037756
2023-01-24 08:05:39.251281: step: 1652/529, loss: 0.0028012238908559084
2023-01-24 08:05:40.345092: step: 1656/529, loss: 0.005947655066847801
2023-01-24 08:05:41.441341: step: 1660/529, loss: 0.0053372434340417385
2023-01-24 08:05:42.533278: step: 1664/529, loss: 0.006887024734169245
2023-01-24 08:05:43.628548: step: 1668/529, loss: 0.0029607245232909918
2023-01-24 08:05:44.695164: step: 1672/529, loss: 0.0027111347299069166
2023-01-24 08:05:45.769588: step: 1676/529, loss: 0.0035719876177608967
2023-01-24 08:05:46.846549: step: 1680/529, loss: 0.0029191048815846443
2023-01-24 08:05:47.919488: step: 1684/529, loss: 0.00319719803519547
2023-01-24 08:05:49.018060: step: 1688/529, loss: 0.00456938985735178
2023-01-24 08:05:50.094907: step: 1692/529, loss: 0.006604470312595367
2023-01-24 08:05:51.179675: step: 1696/529, loss: 0.0044240802526474
2023-01-24 08:05:52.265105: step: 1700/529, loss: 0.00014695030404254794
2023-01-24 08:05:53.357200: step: 1704/529, loss: 0.004230601713061333
2023-01-24 08:05:54.439754: step: 1708/529, loss: 0.0005656823632307351
2023-01-24 08:05:55.516191: step: 1712/529, loss: 0.00022217545483727008
2023-01-24 08:05:56.593518: step: 1716/529, loss: 0.0009813887299969792
2023-01-24 08:05:57.675169: step: 1720/529, loss: 0.0016360919689759612
2023-01-24 08:05:58.747634: step: 1724/529, loss: 0.003637816058471799
2023-01-24 08:05:59.817563: step: 1728/529, loss: 0.004927363246679306
2023-01-24 08:06:00.885626: step: 1732/529, loss: 0.00621325708925724
2023-01-24 08:06:01.955900: step: 1736/529, loss: 0.003051426261663437
2023-01-24 08:06:03.029822: step: 1740/529, loss: 0.005948478356003761
2023-01-24 08:06:04.110797: step: 1744/529, loss: 0.003967400640249252
2023-01-24 08:06:05.179496: step: 1748/529, loss: 0.001984755042940378
2023-01-24 08:06:06.252016: step: 1752/529, loss: 0.0008297549211420119
2023-01-24 08:06:07.319050: step: 1756/529, loss: 0.008170767687261105
2023-01-24 08:06:08.394581: step: 1760/529, loss: 0.00993902888149023
2023-01-24 08:06:09.461564: step: 1764/529, loss: 0.0014071790501475334
2023-01-24 08:06:10.523916: step: 1768/529, loss: 0.0007235452649183571
2023-01-24 08:06:11.617639: step: 1772/529, loss: 0.003635557135567069
2023-01-24 08:06:12.689395: step: 1776/529, loss: 0.0019865641370415688
2023-01-24 08:06:13.754173: step: 1780/529, loss: 0.004577450919896364
2023-01-24 08:06:14.823862: step: 1784/529, loss: 0.00024526112247258425
2023-01-24 08:06:15.894113: step: 1788/529, loss: 0.0027508193161338568
2023-01-24 08:06:16.985903: step: 1792/529, loss: 0.007453067693859339
2023-01-24 08:06:18.076657: step: 1796/529, loss: 0.0007248448091559112
2023-01-24 08:06:19.144965: step: 1800/529, loss: 5.425360086519504e-06
2023-01-24 08:06:20.210274: step: 1804/529, loss: 0.0028575537726283073
2023-01-24 08:06:21.287330: step: 1808/529, loss: 0.015212181955575943
2023-01-24 08:06:22.365711: step: 1812/529, loss: 0.011936192400753498
2023-01-24 08:06:23.433820: step: 1816/529, loss: 0.0012568295933306217
2023-01-24 08:06:24.510502: step: 1820/529, loss: 0.004838570021092892
2023-01-24 08:06:25.587193: step: 1824/529, loss: 0.01585705764591694
2023-01-24 08:06:26.650025: step: 1828/529, loss: 0.004867205861955881
2023-01-24 08:06:27.731194: step: 1832/529, loss: 0.006079098209738731
2023-01-24 08:06:28.814844: step: 1836/529, loss: 0.0017804085509851575
2023-01-24 08:06:29.891308: step: 1840/529, loss: 0.0005418629734776914
2023-01-24 08:06:30.970095: step: 1844/529, loss: 0.013174304738640785
2023-01-24 08:06:32.049647: step: 1848/529, loss: 0.015392934903502464
2023-01-24 08:06:33.126255: step: 1852/529, loss: 0.009023748338222504
2023-01-24 08:06:34.205838: step: 1856/529, loss: 0.004224275704473257
2023-01-24 08:06:35.282481: step: 1860/529, loss: 0.0006300094537436962
2023-01-24 08:06:36.354885: step: 1864/529, loss: 0.00799323059618473
2023-01-24 08:06:37.441421: step: 1868/529, loss: 0.0032703541219234467
2023-01-24 08:06:38.495187: step: 1872/529, loss: 0.005142878741025925
2023-01-24 08:06:39.560706: step: 1876/529, loss: 0.0030077104456722736
2023-01-24 08:06:40.633918: step: 1880/529, loss: 2.8942829430889105e-06
2023-01-24 08:06:41.706863: step: 1884/529, loss: 0.0034233068581670523
2023-01-24 08:06:42.783716: step: 1888/529, loss: 0.0021873395889997482
2023-01-24 08:06:43.866071: step: 1892/529, loss: 0.0045728785917162895
2023-01-24 08:06:44.937029: step: 1896/529, loss: 0.00026265758788213134
2023-01-24 08:06:46.026281: step: 1900/529, loss: 0.005356815177947283
2023-01-24 08:06:47.112787: step: 1904/529, loss: 0.0034824293106794357
2023-01-24 08:06:48.198979: step: 1908/529, loss: 0.0072312550619244576
2023-01-24 08:06:49.267098: step: 1912/529, loss: 0.0005669582751579583
2023-01-24 08:06:50.336875: step: 1916/529, loss: 0.008275214582681656
2023-01-24 08:06:51.406820: step: 1920/529, loss: 0.009792604483664036
2023-01-24 08:06:52.500015: step: 1924/529, loss: 0.0022169151343405247
2023-01-24 08:06:53.571663: step: 1928/529, loss: 0.00634088134393096
2023-01-24 08:06:54.649968: step: 1932/529, loss: 0.0030979879666119814
2023-01-24 08:06:55.727672: step: 1936/529, loss: 0.009384188801050186
2023-01-24 08:06:56.818095: step: 1940/529, loss: 0.010857371613383293
2023-01-24 08:06:57.894293: step: 1944/529, loss: 0.00020369526464492083
2023-01-24 08:06:58.964334: step: 1948/529, loss: 0.004388144239783287
2023-01-24 08:07:00.024012: step: 1952/529, loss: 0.005341329611837864
2023-01-24 08:07:01.107874: step: 1956/529, loss: 0.003869568230584264
2023-01-24 08:07:02.174835: step: 1960/529, loss: 0.005754523910582066
2023-01-24 08:07:03.244195: step: 1964/529, loss: 0.02395222708582878
2023-01-24 08:07:04.322216: step: 1968/529, loss: 0.004579734988510609
2023-01-24 08:07:05.396158: step: 1972/529, loss: 0.006186152342706919
2023-01-24 08:07:06.478800: step: 1976/529, loss: 0.024824978783726692
2023-01-24 08:07:07.562922: step: 1980/529, loss: 0.03843974322080612
2023-01-24 08:07:08.635500: step: 1984/529, loss: 0.002381526865065098
2023-01-24 08:07:09.707083: step: 1988/529, loss: 0.00890548899769783
2023-01-24 08:07:10.783815: step: 1992/529, loss: 0.0004151340981479734
2023-01-24 08:07:11.887100: step: 1996/529, loss: 0.00864302646368742
2023-01-24 08:07:12.954112: step: 2000/529, loss: 0.00403991062194109
2023-01-24 08:07:14.028866: step: 2004/529, loss: 0.0007158780936151743
2023-01-24 08:07:15.110651: step: 2008/529, loss: 0.007027340121567249
2023-01-24 08:07:16.189117: step: 2012/529, loss: 0.012439608573913574
2023-01-24 08:07:17.246433: step: 2016/529, loss: 0.004067345056682825
2023-01-24 08:07:18.330007: step: 2020/529, loss: 0.0021914695389568806
2023-01-24 08:07:19.397176: step: 2024/529, loss: 0.011593271978199482
2023-01-24 08:07:20.488454: step: 2028/529, loss: 0.002958855824545026
2023-01-24 08:07:21.565126: step: 2032/529, loss: 0.009319811128079891
2023-01-24 08:07:22.634819: step: 2036/529, loss: 0.0007707621552981436
2023-01-24 08:07:23.705292: step: 2040/529, loss: 0.0005363363306969404
2023-01-24 08:07:24.784068: step: 2044/529, loss: 0.01899806223809719
2023-01-24 08:07:25.862975: step: 2048/529, loss: 0.004605645313858986
2023-01-24 08:07:26.933645: step: 2052/529, loss: 0.009063088335096836
2023-01-24 08:07:28.000098: step: 2056/529, loss: 0.002710837172344327
2023-01-24 08:07:29.062570: step: 2060/529, loss: 0.002295162295922637
2023-01-24 08:07:30.133695: step: 2064/529, loss: 0.0017400173237547278
2023-01-24 08:07:31.224916: step: 2068/529, loss: 0.009092207998037338
2023-01-24 08:07:32.328897: step: 2072/529, loss: 0.006157895550131798
2023-01-24 08:07:33.406654: step: 2076/529, loss: 0.003863296704366803
2023-01-24 08:07:34.480120: step: 2080/529, loss: 0.0002572887751739472
2023-01-24 08:07:35.547382: step: 2084/529, loss: 0.006474801804870367
2023-01-24 08:07:36.621378: step: 2088/529, loss: 6.854459115857026e-07
2023-01-24 08:07:37.681790: step: 2092/529, loss: 0.023611361160874367
2023-01-24 08:07:38.744811: step: 2096/529, loss: 0.006375241558998823
2023-01-24 08:07:39.810306: step: 2100/529, loss: 0.0008411225280724466
2023-01-24 08:07:40.881680: step: 2104/529, loss: 0.002858164021745324
2023-01-24 08:07:41.947121: step: 2108/529, loss: 0.004075914155691862
2023-01-24 08:07:43.022115: step: 2112/529, loss: 0.0010750771034508944
2023-01-24 08:07:44.107004: step: 2116/529, loss: 0.0012862237635999918
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3347519209382267, 'r': 0.29918055932050247, 'f1': 0.3159682460158413}, 'combined': 0.23281870759061987, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3346390111318661, 'r': 0.29465457046353655, 'f1': 0.3133765128683556}, 'combined': 0.20458777524048086, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580872292314783, 'r': 0.3574077468230694, 'f1': 0.3577471653860543}, 'combined': 0.2636031744949873, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36065178272254766, 'r': 0.3165647541360598, 'f1': 0.3371732280959697}, 'combined': 0.2201234546118766, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3784517173078494, 'r': 0.342545482269154, 'f1': 0.3596045202307652}, 'combined': 0.2649717517489849, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3706505421760894, 'r': 0.30694498023957406, 'f1': 0.3358030553048332}, 'combined': 0.21922893766015014, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 11}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580872292314783, 'r': 0.3574077468230694, 'f1': 0.3577471653860543}, 'combined': 0.2636031744949873, 'stategy': 1, 'epoch': 11}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36065178272254766, 'r': 0.3165647541360598, 'f1': 0.3371732280959697}, 'combined': 0.2201234546118766, 'stategy': 1, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
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 08:10:28.339866: step: 4/529, loss: 0.000361921323928982
2023-01-24 08:10:29.402399: step: 8/529, loss: 0.0027543329633772373
2023-01-24 08:10:30.469584: step: 12/529, loss: 0.007630254607647657
2023-01-24 08:10:31.534877: step: 16/529, loss: 0.0007343032048083842
2023-01-24 08:10:32.617194: step: 20/529, loss: 0.0012807133607566357
2023-01-24 08:10:33.693918: step: 24/529, loss: 0.00038759689778089523
2023-01-24 08:10:34.756855: step: 28/529, loss: 0.004231306724250317
2023-01-24 08:10:35.816113: step: 32/529, loss: 0.0023894808255136013
2023-01-24 08:10:36.892508: step: 36/529, loss: 0.1705983281135559
2023-01-24 08:10:37.957003: step: 40/529, loss: 0.007521615829318762
2023-01-24 08:10:39.035249: step: 44/529, loss: 0.0022974121384322643
2023-01-24 08:10:40.103031: step: 48/529, loss: 0.007646316662430763
2023-01-24 08:10:41.182048: step: 52/529, loss: 0.010570627637207508
2023-01-24 08:10:42.243086: step: 56/529, loss: 0.006622339133173227
2023-01-24 08:10:43.349573: step: 60/529, loss: 0.0018222443759441376
2023-01-24 08:10:44.423530: step: 64/529, loss: 0.002226763404905796
2023-01-24 08:10:45.502077: step: 68/529, loss: 4.19920907006599e-05
2023-01-24 08:10:46.566308: step: 72/529, loss: 0.0016830101376399398
2023-01-24 08:10:47.628792: step: 76/529, loss: 0.0011862420942634344
2023-01-24 08:10:48.693477: step: 80/529, loss: 0.002153007546439767
2023-01-24 08:10:49.759069: step: 84/529, loss: 0.00904899276793003
2023-01-24 08:10:50.829937: step: 88/529, loss: 0.0022940707858651876
2023-01-24 08:10:51.919935: step: 92/529, loss: 0.0007194042555056512
2023-01-24 08:10:53.005246: step: 96/529, loss: 0.002703003818169236
2023-01-24 08:10:54.090832: step: 100/529, loss: 0.006100880913436413
2023-01-24 08:10:55.184639: step: 104/529, loss: 0.004942405503243208
2023-01-24 08:10:56.258198: step: 108/529, loss: 0.0005690957768820226
2023-01-24 08:10:57.331505: step: 112/529, loss: 0.002523837611079216
2023-01-24 08:10:58.425310: step: 116/529, loss: 0.0018693087622523308
2023-01-24 08:10:59.479794: step: 120/529, loss: 0.0010828442173078656
2023-01-24 08:11:00.553585: step: 124/529, loss: 0.02824726700782776
2023-01-24 08:11:01.623105: step: 128/529, loss: 0.005307256244122982
2023-01-24 08:11:02.706709: step: 132/529, loss: 0.0017831261502578855
2023-01-24 08:11:03.771193: step: 136/529, loss: 0.001563708414323628
2023-01-24 08:11:04.828279: step: 140/529, loss: 0.00043457504943944514
2023-01-24 08:11:05.908435: step: 144/529, loss: 0.005051839165389538
2023-01-24 08:11:07.009595: step: 148/529, loss: 0.0040791817009449005
2023-01-24 08:11:08.076041: step: 152/529, loss: 0.00046497126459144056
2023-01-24 08:11:09.164842: step: 156/529, loss: 0.006744929123669863
2023-01-24 08:11:10.228850: step: 160/529, loss: 0.05362081900238991
2023-01-24 08:11:11.299142: step: 164/529, loss: 0.0012575376313179731
2023-01-24 08:11:12.370651: step: 168/529, loss: 0.001310107414610684
2023-01-24 08:11:13.440348: step: 172/529, loss: 0.00033167380024679005
2023-01-24 08:11:14.503620: step: 176/529, loss: 0.004193542059510946
2023-01-24 08:11:15.573939: step: 180/529, loss: 0.014545802026987076
2023-01-24 08:11:16.638080: step: 184/529, loss: 0.0028726791497319937
2023-01-24 08:11:17.726068: step: 188/529, loss: 0.020510900765657425
2023-01-24 08:11:18.786777: step: 192/529, loss: 0.0010077552869915962
2023-01-24 08:11:19.874925: step: 196/529, loss: 0.004950291942805052
2023-01-24 08:11:20.941638: step: 200/529, loss: 5.701499503629748e-06
2023-01-24 08:11:22.005462: step: 204/529, loss: 0.0034605127293616533
2023-01-24 08:11:23.097901: step: 208/529, loss: 0.003968795295804739
2023-01-24 08:11:24.174998: step: 212/529, loss: 0.006312464829534292
2023-01-24 08:11:25.235562: step: 216/529, loss: 5.8979509049095213e-05
2023-01-24 08:11:26.308312: step: 220/529, loss: 0.016386644914746284
2023-01-24 08:11:27.379290: step: 224/529, loss: 0.003938872367143631
2023-01-24 08:11:28.444075: step: 228/529, loss: 0.0004759289731737226
2023-01-24 08:11:29.492214: step: 232/529, loss: 0.02547384425997734
2023-01-24 08:11:30.569739: step: 236/529, loss: 0.025544393807649612
2023-01-24 08:11:31.632693: step: 240/529, loss: 0.007377654779702425
2023-01-24 08:11:32.704962: step: 244/529, loss: 0.00414050230756402
2023-01-24 08:11:33.786978: step: 248/529, loss: 0.00026615633396431804
2023-01-24 08:11:34.860269: step: 252/529, loss: 0.0008698086603544652
2023-01-24 08:11:35.920132: step: 256/529, loss: 0.008049258030951023
2023-01-24 08:11:36.983712: step: 260/529, loss: 0.003497631289064884
2023-01-24 08:11:38.052524: step: 264/529, loss: 0.006201254203915596
2023-01-24 08:11:39.158164: step: 268/529, loss: 0.017417285591363907
2023-01-24 08:11:40.240199: step: 272/529, loss: 0.007253679446876049
2023-01-24 08:11:41.313143: step: 276/529, loss: 0.001215081661939621
2023-01-24 08:11:42.395023: step: 280/529, loss: 0.001447502989321947
2023-01-24 08:11:43.461014: step: 284/529, loss: 0.00040332681965082884
2023-01-24 08:11:44.538029: step: 288/529, loss: 0.0032110409811139107
2023-01-24 08:11:45.602472: step: 292/529, loss: 0.0030246665701270103
2023-01-24 08:11:46.691716: step: 296/529, loss: 0.00448493892326951
2023-01-24 08:11:47.766338: step: 300/529, loss: 0.0059451148845255375
2023-01-24 08:11:48.833001: step: 304/529, loss: 0.0013365116901695728
2023-01-24 08:11:49.898526: step: 308/529, loss: 0.00784012209624052
2023-01-24 08:11:50.970881: step: 312/529, loss: 0.006504009012132883
2023-01-24 08:11:52.044297: step: 316/529, loss: 0.000388285203371197
2023-01-24 08:11:53.110145: step: 320/529, loss: 0.0023971241898834705
2023-01-24 08:11:54.179375: step: 324/529, loss: 5.8770178839040454e-06
2023-01-24 08:11:55.237970: step: 328/529, loss: 0.003277328098192811
2023-01-24 08:11:56.306266: step: 332/529, loss: 0.007359951734542847
2023-01-24 08:11:57.397180: step: 336/529, loss: 0.0012199666816741228
2023-01-24 08:11:58.477283: step: 340/529, loss: 0.010876295156776905
2023-01-24 08:11:59.557919: step: 344/529, loss: 0.0017492666374891996
2023-01-24 08:12:00.618517: step: 348/529, loss: 0.0031481008045375347
2023-01-24 08:12:01.683880: step: 352/529, loss: 0.012958996929228306
2023-01-24 08:12:02.757289: step: 356/529, loss: 0.0045308503322303295
2023-01-24 08:12:03.826108: step: 360/529, loss: 0.005091175436973572
2023-01-24 08:12:04.885370: step: 364/529, loss: 0.0011031769681721926
2023-01-24 08:12:05.955337: step: 368/529, loss: 0.014993158169090748
2023-01-24 08:12:07.012763: step: 372/529, loss: 0.0015691436128690839
2023-01-24 08:12:08.098467: step: 376/529, loss: 0.0060926880687475204
2023-01-24 08:12:09.184888: step: 380/529, loss: 0.001660754787735641
2023-01-24 08:12:10.265513: step: 384/529, loss: 0.004047817550599575
2023-01-24 08:12:11.344387: step: 388/529, loss: 0.0015079942531883717
2023-01-24 08:12:12.423036: step: 392/529, loss: 0.0041028582490980625
2023-01-24 08:12:13.499053: step: 396/529, loss: 0.003120981389656663
2023-01-24 08:12:14.565006: step: 400/529, loss: 0.010635006241500378
2023-01-24 08:12:15.645420: step: 404/529, loss: 0.00629972480237484
2023-01-24 08:12:16.711722: step: 408/529, loss: 3.9860097444943676e-07
2023-01-24 08:12:17.799626: step: 412/529, loss: 0.009384317323565483
2023-01-24 08:12:18.858917: step: 416/529, loss: 0.004853838123381138
2023-01-24 08:12:19.933743: step: 420/529, loss: 0.002183604519814253
2023-01-24 08:12:21.005818: step: 424/529, loss: 0.015336764045059681
2023-01-24 08:12:22.085007: step: 428/529, loss: 0.025337018072605133
2023-01-24 08:12:23.156508: step: 432/529, loss: 0.0003656052576843649
2023-01-24 08:12:24.236995: step: 436/529, loss: 0.0012341223191469908
2023-01-24 08:12:25.304662: step: 440/529, loss: 0.004322833381593227
2023-01-24 08:12:26.384088: step: 444/529, loss: 0.007125149946659803
2023-01-24 08:12:27.455392: step: 448/529, loss: 0.017365621402859688
2023-01-24 08:12:28.523182: step: 452/529, loss: 2.6152900318265893e-05
2023-01-24 08:12:29.605932: step: 456/529, loss: 0.0036615203134715557
2023-01-24 08:12:30.689262: step: 460/529, loss: 0.0035374825820326805
2023-01-24 08:12:31.765645: step: 464/529, loss: 0.01242318656295538
2023-01-24 08:12:32.841223: step: 468/529, loss: 0.004052699543535709
2023-01-24 08:12:33.923429: step: 472/529, loss: 0.007320075761526823
2023-01-24 08:12:35.009652: step: 476/529, loss: 0.003266759216785431
2023-01-24 08:12:36.079275: step: 480/529, loss: 0.004201654810458422
2023-01-24 08:12:37.151846: step: 484/529, loss: 0.0026862011291086674
2023-01-24 08:12:38.228356: step: 488/529, loss: 0.002474110806360841
2023-01-24 08:12:39.296077: step: 492/529, loss: 0.006022781133651733
2023-01-24 08:12:40.360874: step: 496/529, loss: 0.005296438001096249
2023-01-24 08:12:41.428196: step: 500/529, loss: 0.002801610389724374
2023-01-24 08:12:42.493194: step: 504/529, loss: 0.0014753537252545357
2023-01-24 08:12:43.580941: step: 508/529, loss: 0.008723734878003597
2023-01-24 08:12:44.664547: step: 512/529, loss: 0.016350971534848213
2023-01-24 08:12:45.750233: step: 516/529, loss: 0.01831996440887451
2023-01-24 08:12:46.814127: step: 520/529, loss: 0.005710884928703308
2023-01-24 08:12:47.890286: step: 524/529, loss: 0.006975293159484863
2023-01-24 08:12:48.949440: step: 528/529, loss: 0.00898286048322916
2023-01-24 08:12:50.025799: step: 532/529, loss: 0.0007190429023467004
2023-01-24 08:12:51.094367: step: 536/529, loss: 0.0038729894440621138
2023-01-24 08:12:52.165908: step: 540/529, loss: 0.016032736748456955
2023-01-24 08:12:53.219948: step: 544/529, loss: 0.0020117787644267082
2023-01-24 08:12:54.309663: step: 548/529, loss: 0.00921130832284689
2023-01-24 08:12:55.379221: step: 552/529, loss: 0.0028724046424031258
2023-01-24 08:12:56.464376: step: 556/529, loss: 0.000245564995566383
2023-01-24 08:12:57.534171: step: 560/529, loss: 0.0024213865399360657
2023-01-24 08:12:58.597681: step: 564/529, loss: 0.003219675738364458
2023-01-24 08:12:59.665333: step: 568/529, loss: 0.002193629974499345
2023-01-24 08:13:00.733740: step: 572/529, loss: 0.005870449356734753
2023-01-24 08:13:01.794873: step: 576/529, loss: 0.014043132774531841
2023-01-24 08:13:02.879150: step: 580/529, loss: 0.0056515890173614025
2023-01-24 08:13:03.963343: step: 584/529, loss: 0.0042397934012115
2023-01-24 08:13:05.042703: step: 588/529, loss: 0.0008258468005806208
2023-01-24 08:13:06.117605: step: 592/529, loss: 0.0009125696960836649
2023-01-24 08:13:07.181081: step: 596/529, loss: 0.0019172930624336004
2023-01-24 08:13:08.255333: step: 600/529, loss: 0.004650169983506203
2023-01-24 08:13:09.333907: step: 604/529, loss: 0.049236856400966644
2023-01-24 08:13:10.410270: step: 608/529, loss: 0.0018092230893671513
2023-01-24 08:13:11.477374: step: 612/529, loss: 0.006917131599038839
2023-01-24 08:13:12.537486: step: 616/529, loss: 0.002702345373108983
2023-01-24 08:13:13.621387: step: 620/529, loss: 0.009933579713106155
2023-01-24 08:13:14.692501: step: 624/529, loss: 0.02553955465555191
2023-01-24 08:13:15.785070: step: 628/529, loss: 0.01620328798890114
2023-01-24 08:13:16.848535: step: 632/529, loss: 0.0029310528188943863
2023-01-24 08:13:17.919256: step: 636/529, loss: 0.008869489654898643
2023-01-24 08:13:18.992173: step: 640/529, loss: 0.0023660664446651936
2023-01-24 08:13:20.062348: step: 644/529, loss: 0.0003124453069176525
2023-01-24 08:13:21.147870: step: 648/529, loss: 0.001961875008419156
2023-01-24 08:13:22.238940: step: 652/529, loss: 0.040871672332286835
2023-01-24 08:13:23.303385: step: 656/529, loss: 0.002327162539586425
2023-01-24 08:13:24.377058: step: 660/529, loss: 0.0022622430697083473
2023-01-24 08:13:25.442614: step: 664/529, loss: 0.0035075093619525433
2023-01-24 08:13:26.522383: step: 668/529, loss: 0.0006215961766429245
2023-01-24 08:13:27.599158: step: 672/529, loss: 0.002107851207256317
2023-01-24 08:13:28.648348: step: 676/529, loss: 0.003571446519345045
2023-01-24 08:13:29.731220: step: 680/529, loss: 0.0031601879745721817
2023-01-24 08:13:30.813356: step: 684/529, loss: 0.006430068053305149
2023-01-24 08:13:31.876073: step: 688/529, loss: 0.006697945296764374
2023-01-24 08:13:32.951969: step: 692/529, loss: 0.012313859537243843
2023-01-24 08:13:34.044247: step: 696/529, loss: 0.006500555202364922
2023-01-24 08:13:35.114787: step: 700/529, loss: 0.004255449865013361
2023-01-24 08:13:36.183724: step: 704/529, loss: 0.010104414075613022
2023-01-24 08:13:37.265010: step: 708/529, loss: 0.006870902143418789
2023-01-24 08:13:38.339327: step: 712/529, loss: 0.0004085441760253161
2023-01-24 08:13:39.394645: step: 716/529, loss: 2.9241049560368992e-05
2023-01-24 08:13:40.468115: step: 720/529, loss: 0.01358101237565279
2023-01-24 08:13:41.554753: step: 724/529, loss: 0.0013228950556367636
2023-01-24 08:13:42.636617: step: 728/529, loss: 0.008493266999721527
2023-01-24 08:13:43.697528: step: 732/529, loss: 0.00284643960185349
2023-01-24 08:13:44.782945: step: 736/529, loss: 0.00036593960248865187
2023-01-24 08:13:45.863207: step: 740/529, loss: 0.004394339397549629
2023-01-24 08:13:46.951211: step: 744/529, loss: 0.0003114200080744922
2023-01-24 08:13:48.010358: step: 748/529, loss: 0.018969858065247536
2023-01-24 08:13:49.094397: step: 752/529, loss: 0.0021657058969140053
2023-01-24 08:13:50.175140: step: 756/529, loss: 0.01967126876115799
2023-01-24 08:13:51.247397: step: 760/529, loss: 0.01050269603729248
2023-01-24 08:13:52.319552: step: 764/529, loss: 0.001448205322958529
2023-01-24 08:13:53.386974: step: 768/529, loss: 0.010337715968489647
2023-01-24 08:13:54.462607: step: 772/529, loss: 0.0022648551966995
2023-01-24 08:13:55.532410: step: 776/529, loss: 0.003120388835668564
2023-01-24 08:13:56.598330: step: 780/529, loss: 0.004174788948148489
2023-01-24 08:13:57.675159: step: 784/529, loss: 0.023587878793478012
2023-01-24 08:13:58.748948: step: 788/529, loss: 0.0042237709276378155
2023-01-24 08:13:59.824074: step: 792/529, loss: 0.0021804224234074354
2023-01-24 08:14:00.897560: step: 796/529, loss: 0.0009366533486172557
2023-01-24 08:14:01.966951: step: 800/529, loss: 0.001944833085872233
2023-01-24 08:14:03.062572: step: 804/529, loss: 0.0083340248093009
2023-01-24 08:14:04.139552: step: 808/529, loss: 0.008067324757575989
2023-01-24 08:14:05.208971: step: 812/529, loss: 0.000578813545871526
2023-01-24 08:14:06.285887: step: 816/529, loss: 0.004300620872527361
2023-01-24 08:14:07.368120: step: 820/529, loss: 0.0051774862222373486
2023-01-24 08:14:08.429800: step: 824/529, loss: 0.0012338312808424234
2023-01-24 08:14:09.512678: step: 828/529, loss: 0.0034790572244673967
2023-01-24 08:14:10.598421: step: 832/529, loss: 0.001092011807486415
2023-01-24 08:14:11.671988: step: 836/529, loss: 0.009042570367455482
2023-01-24 08:14:12.739863: step: 840/529, loss: 0.0023971109185367823
2023-01-24 08:14:13.829825: step: 844/529, loss: 0.004049123730510473
2023-01-24 08:14:14.927044: step: 848/529, loss: 0.009170043282210827
2023-01-24 08:14:16.015656: step: 852/529, loss: 0.0012786417501047254
2023-01-24 08:14:17.092689: step: 856/529, loss: 0.021059595048427582
2023-01-24 08:14:18.176198: step: 860/529, loss: 0.004077080637216568
2023-01-24 08:14:19.249779: step: 864/529, loss: 0.0037740645930171013
2023-01-24 08:14:20.327722: step: 868/529, loss: 0.00802623201161623
2023-01-24 08:14:21.403341: step: 872/529, loss: 0.0048888931050896645
2023-01-24 08:14:22.481746: step: 876/529, loss: 0.000670494104269892
2023-01-24 08:14:23.568428: step: 880/529, loss: 0.006875012535601854
2023-01-24 08:14:24.670241: step: 884/529, loss: 0.0015024887397885323
2023-01-24 08:14:25.759452: step: 888/529, loss: 0.007486126851290464
2023-01-24 08:14:26.840749: step: 892/529, loss: 0.005453349556773901
2023-01-24 08:14:27.921258: step: 896/529, loss: 1.5941181118250825e-05
2023-01-24 08:14:29.038730: step: 900/529, loss: 0.013964889571070671
2023-01-24 08:14:30.131982: step: 904/529, loss: 0.0007833112613297999
2023-01-24 08:14:31.198786: step: 908/529, loss: 0.0020404993556439877
2023-01-24 08:14:32.283009: step: 912/529, loss: 0.024872416630387306
2023-01-24 08:14:33.373710: step: 916/529, loss: 0.0018921869341284037
2023-01-24 08:14:34.441521: step: 920/529, loss: 0.007095129694789648
2023-01-24 08:14:35.529815: step: 924/529, loss: 0.007776946760714054
2023-01-24 08:14:36.588131: step: 928/529, loss: 8.95168795977952e-06
2023-01-24 08:14:37.678786: step: 932/529, loss: 0.0028668097220361233
2023-01-24 08:14:38.749859: step: 936/529, loss: 0.0028234587516635656
2023-01-24 08:14:39.820494: step: 940/529, loss: 0.004628787748515606
2023-01-24 08:14:40.884947: step: 944/529, loss: 0.0007252873620018363
2023-01-24 08:14:41.977055: step: 948/529, loss: 0.0024532407987862825
2023-01-24 08:14:43.046527: step: 952/529, loss: 0.0006805064040236175
2023-01-24 08:14:44.132519: step: 956/529, loss: 0.006331130396574736
2023-01-24 08:14:45.217143: step: 960/529, loss: 0.000772796745877713
2023-01-24 08:14:46.324325: step: 964/529, loss: 0.0010961184743791819
2023-01-24 08:14:47.428304: step: 968/529, loss: 0.005595693364739418
2023-01-24 08:14:48.533288: step: 972/529, loss: 0.00617518974468112
2023-01-24 08:14:49.604980: step: 976/529, loss: 0.002138980431482196
2023-01-24 08:14:50.704142: step: 980/529, loss: 0.00802935566753149
2023-01-24 08:14:51.787270: step: 984/529, loss: 0.00715281255543232
2023-01-24 08:14:52.912864: step: 988/529, loss: 0.002921774983406067
2023-01-24 08:14:53.979131: step: 992/529, loss: 0.0065352581441402435
2023-01-24 08:14:55.060408: step: 996/529, loss: 0.004722020588815212
2023-01-24 08:14:56.135680: step: 1000/529, loss: 0.009458709508180618
2023-01-24 08:14:57.197289: step: 1004/529, loss: 0.005019423086196184
2023-01-24 08:14:58.296337: step: 1008/529, loss: 0.0004274088714737445
2023-01-24 08:14:59.386487: step: 1012/529, loss: 0.0066294982098042965
2023-01-24 08:15:00.475281: step: 1016/529, loss: 0.0027282305527478456
2023-01-24 08:15:01.556532: step: 1020/529, loss: 0.0020150088239461184
2023-01-24 08:15:02.641392: step: 1024/529, loss: 0.007532848045229912
2023-01-24 08:15:03.721191: step: 1028/529, loss: 9.887239139061421e-05
2023-01-24 08:15:04.797971: step: 1032/529, loss: 0.002379458397626877
2023-01-24 08:15:05.880243: step: 1036/529, loss: 0.0005518639227375388
2023-01-24 08:15:06.950271: step: 1040/529, loss: 0.008010240271687508
2023-01-24 08:15:08.022068: step: 1044/529, loss: 0.002007808769121766
2023-01-24 08:15:09.113783: step: 1048/529, loss: 0.0017985260346904397
2023-01-24 08:15:10.186091: step: 1052/529, loss: 0.00574650801718235
2023-01-24 08:15:11.276075: step: 1056/529, loss: 0.00014476251089945436
2023-01-24 08:15:12.343255: step: 1060/529, loss: 0.0032546704169362783
2023-01-24 08:15:13.436650: step: 1064/529, loss: 0.004099247511476278
2023-01-24 08:15:14.505178: step: 1068/529, loss: 0.0032230836804956198
2023-01-24 08:15:15.592094: step: 1072/529, loss: 0.007470614276826382
2023-01-24 08:15:16.686375: step: 1076/529, loss: 0.0032864778768271208
2023-01-24 08:15:17.767851: step: 1080/529, loss: 0.005386980250477791
2023-01-24 08:15:18.862128: step: 1084/529, loss: 0.005451235454529524
2023-01-24 08:15:19.936166: step: 1088/529, loss: 0.006932253483682871
2023-01-24 08:15:21.014759: step: 1092/529, loss: 0.002052298281341791
2023-01-24 08:15:22.085620: step: 1096/529, loss: 0.007956176996231079
2023-01-24 08:15:23.162338: step: 1100/529, loss: 0.010404829867184162
2023-01-24 08:15:24.218869: step: 1104/529, loss: 0.00186672352720052
2023-01-24 08:15:25.334792: step: 1108/529, loss: 0.006265898235142231
2023-01-24 08:15:26.416614: step: 1112/529, loss: 0.006293782033026218
2023-01-24 08:15:27.490181: step: 1116/529, loss: 0.000141568758408539
2023-01-24 08:15:28.574058: step: 1120/529, loss: 0.00019353433162905276
2023-01-24 08:15:29.646589: step: 1124/529, loss: 0.001994740217924118
2023-01-24 08:15:30.707030: step: 1128/529, loss: 0.0038161971606314182
2023-01-24 08:15:31.789548: step: 1132/529, loss: 0.004771463107317686
2023-01-24 08:15:32.876245: step: 1136/529, loss: 0.009334413334727287
2023-01-24 08:15:33.946218: step: 1140/529, loss: 0.002802507719025016
2023-01-24 08:15:35.033267: step: 1144/529, loss: 0.004227387253195047
2023-01-24 08:15:36.133108: step: 1148/529, loss: 0.002585578477010131
2023-01-24 08:15:37.221270: step: 1152/529, loss: 0.005385723430663347
2023-01-24 08:15:38.288283: step: 1156/529, loss: 4.5131346837479214e-07
2023-01-24 08:15:39.353385: step: 1160/529, loss: 0.02335977926850319
2023-01-24 08:15:40.451711: step: 1164/529, loss: 0.001962715294212103
2023-01-24 08:15:41.520905: step: 1168/529, loss: 0.011584354564547539
2023-01-24 08:15:42.589444: step: 1172/529, loss: 0.0030808988958597183
2023-01-24 08:15:43.689606: step: 1176/529, loss: 0.00456633185967803
2023-01-24 08:15:44.763603: step: 1180/529, loss: 0.028549674898386
2023-01-24 08:15:45.832995: step: 1184/529, loss: 0.0036442154087126255
2023-01-24 08:15:46.904373: step: 1188/529, loss: 0.00785110704600811
2023-01-24 08:15:47.983866: step: 1192/529, loss: 0.013239417225122452
2023-01-24 08:15:49.054863: step: 1196/529, loss: 0.0076675256714224815
2023-01-24 08:15:50.166863: step: 1200/529, loss: 0.001430810079909861
2023-01-24 08:15:51.226980: step: 1204/529, loss: 0.008416172116994858
2023-01-24 08:15:52.297452: step: 1208/529, loss: 0.001066521625034511
2023-01-24 08:15:53.387741: step: 1212/529, loss: 0.007978377863764763
2023-01-24 08:15:54.458072: step: 1216/529, loss: 0.007027463987469673
2023-01-24 08:15:55.543054: step: 1220/529, loss: 0.013067848980426788
2023-01-24 08:15:56.611813: step: 1224/529, loss: 0.00699908472597599
2023-01-24 08:15:57.693560: step: 1228/529, loss: 0.035781923681497574
2023-01-24 08:15:58.758676: step: 1232/529, loss: 0.009348358027637005
2023-01-24 08:15:59.853206: step: 1236/529, loss: 0.00537651963531971
2023-01-24 08:16:00.939796: step: 1240/529, loss: 0.03756602853536606
2023-01-24 08:16:02.016543: step: 1244/529, loss: 0.008057399652898312
2023-01-24 08:16:03.088969: step: 1248/529, loss: 0.0017485424177721143
2023-01-24 08:16:04.161353: step: 1252/529, loss: 0.005797643214464188
2023-01-24 08:16:05.232598: step: 1256/529, loss: 0.00043898308649659157
2023-01-24 08:16:06.300668: step: 1260/529, loss: 0.0001829609536798671
2023-01-24 08:16:07.385666: step: 1264/529, loss: 0.001816952251829207
2023-01-24 08:16:08.485778: step: 1268/529, loss: 0.002002737717702985
2023-01-24 08:16:09.561422: step: 1272/529, loss: 0.004937693476676941
2023-01-24 08:16:10.630094: step: 1276/529, loss: 0.008246760815382004
2023-01-24 08:16:11.710063: step: 1280/529, loss: 0.004174930974841118
2023-01-24 08:16:12.801556: step: 1284/529, loss: 0.007025341037660837
2023-01-24 08:16:13.886478: step: 1288/529, loss: 0.00136400549672544
2023-01-24 08:16:14.960193: step: 1292/529, loss: 0.004458239767700434
2023-01-24 08:16:16.026861: step: 1296/529, loss: 0.002784284995868802
2023-01-24 08:16:17.113856: step: 1300/529, loss: 0.008618834428489208
2023-01-24 08:16:18.189830: step: 1304/529, loss: 2.4947779820649885e-05
2023-01-24 08:16:19.265895: step: 1308/529, loss: 0.013042942620813847
2023-01-24 08:16:20.340515: step: 1312/529, loss: 0.000932298949919641
2023-01-24 08:16:21.416977: step: 1316/529, loss: 0.00020931493781972677
2023-01-24 08:16:22.484641: step: 1320/529, loss: 0.005391411483287811
2023-01-24 08:16:23.581439: step: 1324/529, loss: 0.0030733859166502953
2023-01-24 08:16:24.659025: step: 1328/529, loss: 0.0014090086333453655
2023-01-24 08:16:25.732472: step: 1332/529, loss: 0.001266465405933559
2023-01-24 08:16:26.809548: step: 1336/529, loss: 0.011990770697593689
2023-01-24 08:16:27.889478: step: 1340/529, loss: 0.0025625831913203
2023-01-24 08:16:28.959568: step: 1344/529, loss: 0.0024642636999487877
2023-01-24 08:16:30.026997: step: 1348/529, loss: 0.0011555214878171682
2023-01-24 08:16:31.099410: step: 1352/529, loss: 0.005239961203187704
2023-01-24 08:16:32.175947: step: 1356/529, loss: 0.0005212591495364904
2023-01-24 08:16:33.294282: step: 1360/529, loss: 0.0033456392120569944
2023-01-24 08:16:34.380372: step: 1364/529, loss: 0.0008974817465059459
2023-01-24 08:16:35.461552: step: 1368/529, loss: 0.0036943599116057158
2023-01-24 08:16:36.544771: step: 1372/529, loss: 0.004358185920864344
2023-01-24 08:16:37.616549: step: 1376/529, loss: 0.01866780035197735
2023-01-24 08:16:38.682356: step: 1380/529, loss: 0.009757593274116516
2023-01-24 08:16:39.766438: step: 1384/529, loss: 0.003262993646785617
2023-01-24 08:16:40.856856: step: 1388/529, loss: 0.0009631969733163714
2023-01-24 08:16:41.926582: step: 1392/529, loss: 0.00368310185149312
2023-01-24 08:16:43.027242: step: 1396/529, loss: 4.6427554480032995e-05
2023-01-24 08:16:44.108642: step: 1400/529, loss: 0.0003410500066820532
2023-01-24 08:16:45.204200: step: 1404/529, loss: 0.028717441484332085
2023-01-24 08:16:46.293674: step: 1408/529, loss: 0.005228606518357992
2023-01-24 08:16:47.377233: step: 1412/529, loss: 0.001336421468295157
2023-01-24 08:16:48.463771: step: 1416/529, loss: 0.00861088652163744
2023-01-24 08:16:49.533852: step: 1420/529, loss: 0.0001997453800868243
2023-01-24 08:16:50.619998: step: 1424/529, loss: 0.013761427253484726
2023-01-24 08:16:51.727304: step: 1428/529, loss: 0.004547123331576586
2023-01-24 08:16:52.806628: step: 1432/529, loss: 0.001521176309324801
2023-01-24 08:16:53.883918: step: 1436/529, loss: 0.0013128601713106036
2023-01-24 08:16:54.964246: step: 1440/529, loss: 0.00041359514580108225
2023-01-24 08:16:56.038776: step: 1444/529, loss: 0.0028874811250716448
2023-01-24 08:16:57.098015: step: 1448/529, loss: 0.00205975491553545
2023-01-24 08:16:58.200665: step: 1452/529, loss: 0.04599124938249588
2023-01-24 08:16:59.289635: step: 1456/529, loss: 0.0007727158372290432
2023-01-24 08:17:00.368124: step: 1460/529, loss: 5.3414946705743205e-06
2023-01-24 08:17:01.435215: step: 1464/529, loss: 0.002363678067922592
2023-01-24 08:17:02.522197: step: 1468/529, loss: 0.004923494067043066
2023-01-24 08:17:03.603647: step: 1472/529, loss: 0.0018438565311953425
2023-01-24 08:17:04.696182: step: 1476/529, loss: 0.0019986480474472046
2023-01-24 08:17:05.775685: step: 1480/529, loss: 0.010694275610148907
2023-01-24 08:17:06.856862: step: 1484/529, loss: 0.002109937369823456
2023-01-24 08:17:07.943607: step: 1488/529, loss: 0.011114335618913174
2023-01-24 08:17:09.038102: step: 1492/529, loss: 0.0011281033512204885
2023-01-24 08:17:10.110130: step: 1496/529, loss: 0.006920067593455315
2023-01-24 08:17:11.190031: step: 1500/529, loss: 0.0074417442083358765
2023-01-24 08:17:12.292188: step: 1504/529, loss: 0.010387626476585865
2023-01-24 08:17:13.374045: step: 1508/529, loss: 0.0024306965060532093
2023-01-24 08:17:14.463707: step: 1512/529, loss: 0.012259759940207005
2023-01-24 08:17:15.545438: step: 1516/529, loss: 0.05915343761444092
2023-01-24 08:17:16.634017: step: 1520/529, loss: 0.012260396033525467
2023-01-24 08:17:17.726777: step: 1524/529, loss: 0.005930379033088684
2023-01-24 08:17:18.808779: step: 1528/529, loss: 0.0002930450427811593
2023-01-24 08:17:19.906901: step: 1532/529, loss: 0.011883622966706753
2023-01-24 08:17:20.991768: step: 1536/529, loss: 0.01701703481376171
2023-01-24 08:17:22.069398: step: 1540/529, loss: 0.0023777985479682684
2023-01-24 08:17:23.148448: step: 1544/529, loss: 0.0089075593277812
2023-01-24 08:17:24.215293: step: 1548/529, loss: 0.003510445822030306
2023-01-24 08:17:25.291021: step: 1552/529, loss: 0.007700522430241108
2023-01-24 08:17:26.363188: step: 1556/529, loss: 0.004346936475485563
2023-01-24 08:17:27.434704: step: 1560/529, loss: 0.004421493969857693
2023-01-24 08:17:28.513914: step: 1564/529, loss: 0.007850480265915394
2023-01-24 08:17:29.599087: step: 1568/529, loss: 0.03238620236515999
2023-01-24 08:17:30.684518: step: 1572/529, loss: 0.003119183937087655
2023-01-24 08:17:31.759523: step: 1576/529, loss: 0.032034046947956085
2023-01-24 08:17:32.828474: step: 1580/529, loss: 0.0058512696996331215
2023-01-24 08:17:33.906303: step: 1584/529, loss: 0.0043077231384813786
2023-01-24 08:17:34.977901: step: 1588/529, loss: 0.0018022634321823716
2023-01-24 08:17:36.037942: step: 1592/529, loss: 0.005876576527953148
2023-01-24 08:17:37.116712: step: 1596/529, loss: 0.0017832991434261203
2023-01-24 08:17:38.187629: step: 1600/529, loss: 0.010564473457634449
2023-01-24 08:17:39.284977: step: 1604/529, loss: 0.0007911696447990835
2023-01-24 08:17:40.363991: step: 1608/529, loss: 0.0024978939909487963
2023-01-24 08:17:41.437626: step: 1612/529, loss: 0.0014426166890189052
2023-01-24 08:17:42.504010: step: 1616/529, loss: 0.0007707003387622535
2023-01-24 08:17:43.600216: step: 1620/529, loss: 0.0016293848166242242
2023-01-24 08:17:44.669402: step: 1624/529, loss: 0.0015996628208085895
2023-01-24 08:17:45.735142: step: 1628/529, loss: 0.005285800434648991
2023-01-24 08:17:46.811868: step: 1632/529, loss: 0.0022937017492949963
2023-01-24 08:17:47.901370: step: 1636/529, loss: 0.01592060923576355
2023-01-24 08:17:48.964835: step: 1640/529, loss: 0.002437553135678172
2023-01-24 08:17:50.018857: step: 1644/529, loss: 0.016958992928266525
2023-01-24 08:17:51.101441: step: 1648/529, loss: 0.000696833711117506
2023-01-24 08:17:52.175824: step: 1652/529, loss: 0.00597717147320509
2023-01-24 08:17:53.250259: step: 1656/529, loss: 0.0001052335646818392
2023-01-24 08:17:54.343029: step: 1660/529, loss: 0.00012823617726098746
2023-01-24 08:17:55.417859: step: 1664/529, loss: 0.005667322780936956
2023-01-24 08:17:56.496126: step: 1668/529, loss: 0.0011264043860137463
2023-01-24 08:17:57.549961: step: 1672/529, loss: 0.005253660026937723
2023-01-24 08:17:58.620414: step: 1676/529, loss: 0.001289410749450326
2023-01-24 08:17:59.698308: step: 1680/529, loss: 0.0010281333234161139
2023-01-24 08:18:00.783460: step: 1684/529, loss: 0.00605596462264657
2023-01-24 08:18:01.864769: step: 1688/529, loss: 0.012970738112926483
2023-01-24 08:18:02.939643: step: 1692/529, loss: 0.005011787638068199
2023-01-24 08:18:04.033276: step: 1696/529, loss: 0.003135734237730503
2023-01-24 08:18:05.091492: step: 1700/529, loss: 0.00018702501256484538
2023-01-24 08:18:06.190519: step: 1704/529, loss: 0.0030305900145322084
2023-01-24 08:18:07.274662: step: 1708/529, loss: 0.02004946395754814
2023-01-24 08:18:08.351805: step: 1712/529, loss: 0.006373633164912462
2023-01-24 08:18:09.436888: step: 1716/529, loss: 0.0026312260888516903
2023-01-24 08:18:10.516171: step: 1720/529, loss: 0.006205298472195864
2023-01-24 08:18:11.573175: step: 1724/529, loss: 0.004602530039846897
2023-01-24 08:18:12.633115: step: 1728/529, loss: 0.006025823298841715
2023-01-24 08:18:13.690211: step: 1732/529, loss: 0.013049333356320858
2023-01-24 08:18:14.755833: step: 1736/529, loss: 0.006153861526399851
2023-01-24 08:18:15.827317: step: 1740/529, loss: 0.005557524040341377
2023-01-24 08:18:16.900495: step: 1744/529, loss: 0.007490483112633228
2023-01-24 08:18:17.958086: step: 1748/529, loss: 0.008488928899168968
2023-01-24 08:18:19.038797: step: 1752/529, loss: 0.0064591411501169205
2023-01-24 08:18:20.116200: step: 1756/529, loss: 0.0013906044187024236
2023-01-24 08:18:21.182974: step: 1760/529, loss: 0.005087839439511299
2023-01-24 08:18:22.255513: step: 1764/529, loss: 0.0013060927158221602
2023-01-24 08:18:23.337635: step: 1768/529, loss: 0.005546437576413155
2023-01-24 08:18:24.412229: step: 1772/529, loss: 0.0034699239768087864
2023-01-24 08:18:25.496257: step: 1776/529, loss: 0.0005160251748748124
2023-01-24 08:18:26.573266: step: 1780/529, loss: 3.356958768563345e-05
2023-01-24 08:18:27.639402: step: 1784/529, loss: 0.006278616841882467
2023-01-24 08:18:28.714934: step: 1788/529, loss: 0.005382593255490065
2023-01-24 08:18:29.800329: step: 1792/529, loss: 0.0037666133139282465
2023-01-24 08:18:30.881685: step: 1796/529, loss: 0.0072418502531945705
2023-01-24 08:18:31.960772: step: 1800/529, loss: 0.00019383685139473528
2023-01-24 08:18:33.038252: step: 1804/529, loss: 0.001018869923427701
2023-01-24 08:18:34.103110: step: 1808/529, loss: 0.003560728393495083
2023-01-24 08:18:35.167484: step: 1812/529, loss: 0.0006448279600590467
2023-01-24 08:18:36.240400: step: 1816/529, loss: 0.002446823287755251
2023-01-24 08:18:37.302610: step: 1820/529, loss: 0.0024071810767054558
2023-01-24 08:18:38.385690: step: 1824/529, loss: 0.0051125031895935535
2023-01-24 08:18:39.449368: step: 1828/529, loss: 0.00031027488876134157
2023-01-24 08:18:40.521746: step: 1832/529, loss: 0.009204480797052383
2023-01-24 08:18:41.610468: step: 1836/529, loss: 0.0008500593830831349
2023-01-24 08:18:42.688349: step: 1840/529, loss: 0.0037134967278689146
2023-01-24 08:18:43.772835: step: 1844/529, loss: 0.0012093615951016545
2023-01-24 08:18:44.839318: step: 1848/529, loss: 0.005602362100034952
2023-01-24 08:18:45.907830: step: 1852/529, loss: 0.005232165567576885
2023-01-24 08:18:46.975421: step: 1856/529, loss: 0.018830273300409317
2023-01-24 08:18:48.057831: step: 1860/529, loss: 0.011606309562921524
2023-01-24 08:18:49.140082: step: 1864/529, loss: 0.001993372105062008
2023-01-24 08:18:50.211992: step: 1868/529, loss: 0.007100284099578857
2023-01-24 08:18:51.288370: step: 1872/529, loss: 0.0010416858131065965
2023-01-24 08:18:52.354006: step: 1876/529, loss: 0.002694792114198208
2023-01-24 08:18:53.423421: step: 1880/529, loss: 0.002246998017653823
2023-01-24 08:18:54.483156: step: 1884/529, loss: 0.005340383853763342
2023-01-24 08:18:55.559985: step: 1888/529, loss: 0.0008305404917337
2023-01-24 08:18:56.643919: step: 1892/529, loss: 0.004039315041154623
2023-01-24 08:18:57.715321: step: 1896/529, loss: 0.007692957296967506
2023-01-24 08:18:58.776532: step: 1900/529, loss: 0.0009001350263133645
2023-01-24 08:18:59.859259: step: 1904/529, loss: 0.008609401993453503
2023-01-24 08:19:00.938790: step: 1908/529, loss: 0.0026894821785390377
2023-01-24 08:19:02.013843: step: 1912/529, loss: 0.00699479877948761
2023-01-24 08:19:03.097520: step: 1916/529, loss: 0.0025947594549506903
2023-01-24 08:19:04.168345: step: 1920/529, loss: 0.00038627785397693515
2023-01-24 08:19:05.229248: step: 1924/529, loss: 0.0004348678921815008
2023-01-24 08:19:06.302286: step: 1928/529, loss: 0.00037938178866170347
2023-01-24 08:19:07.360891: step: 1932/529, loss: 0.0001086424381355755
2023-01-24 08:19:08.414258: step: 1936/529, loss: 0.008144153282046318
2023-01-24 08:19:09.506458: step: 1940/529, loss: 0.0013748578494414687
2023-01-24 08:19:10.582123: step: 1944/529, loss: 0.000560526445042342
2023-01-24 08:19:11.657999: step: 1948/529, loss: 0.0007381871691904962
2023-01-24 08:19:12.729350: step: 1952/529, loss: 0.0025683450512588024
2023-01-24 08:19:13.831395: step: 1956/529, loss: 0.005808547139167786
2023-01-24 08:19:14.919737: step: 1960/529, loss: 0.0010733160888776183
2023-01-24 08:19:15.973342: step: 1964/529, loss: 0.0008478582021780312
2023-01-24 08:19:17.034761: step: 1968/529, loss: 0.000983109581284225
2023-01-24 08:19:18.105666: step: 1972/529, loss: 0.0032325664069503546
2023-01-24 08:19:19.181446: step: 1976/529, loss: 0.007949438877403736
2023-01-24 08:19:20.257154: step: 1980/529, loss: 0.0005663922638632357
2023-01-24 08:19:21.338479: step: 1984/529, loss: 0.0006114203715696931
2023-01-24 08:19:22.412833: step: 1988/529, loss: 0.0003220208454877138
2023-01-24 08:19:23.475393: step: 1992/529, loss: 0.0018726433627307415
2023-01-24 08:19:24.554480: step: 1996/529, loss: 0.010423687286674976
2023-01-24 08:19:25.629122: step: 2000/529, loss: 0.002392818219959736
2023-01-24 08:19:26.714564: step: 2004/529, loss: 0.0071152630262076855
2023-01-24 08:19:27.779255: step: 2008/529, loss: 0.014891195110976696
2023-01-24 08:19:28.849730: step: 2012/529, loss: 0.004344492219388485
2023-01-24 08:19:29.942098: step: 2016/529, loss: 0.0036844457499682903
2023-01-24 08:19:31.014585: step: 2020/529, loss: 0.003806793363764882
2023-01-24 08:19:32.076399: step: 2024/529, loss: 0.009753200225532055
2023-01-24 08:19:33.153982: step: 2028/529, loss: 0.002347629750147462
2023-01-24 08:19:34.238301: step: 2032/529, loss: 0.0012171134585514665
2023-01-24 08:19:35.332872: step: 2036/529, loss: 0.0045912074856460094
2023-01-24 08:19:36.394305: step: 2040/529, loss: 0.004901139065623283
2023-01-24 08:19:37.457064: step: 2044/529, loss: 0.0003906798083335161
2023-01-24 08:19:38.534010: step: 2048/529, loss: 0.0021583319175988436
2023-01-24 08:19:39.619100: step: 2052/529, loss: 0.004819855559617281
2023-01-24 08:19:40.685093: step: 2056/529, loss: 0.0005273776478134096
2023-01-24 08:19:41.751369: step: 2060/529, loss: 0.005431292578577995
2023-01-24 08:19:42.857700: step: 2064/529, loss: 0.011450282298028469
2023-01-24 08:19:43.921339: step: 2068/529, loss: 0.004794581793248653
2023-01-24 08:19:44.990748: step: 2072/529, loss: 0.0031150751747190952
2023-01-24 08:19:46.056311: step: 2076/529, loss: 0.016725575551390648
2023-01-24 08:19:47.125672: step: 2080/529, loss: 0.0034163992386311293
2023-01-24 08:19:48.218619: step: 2084/529, loss: 0.0029623941518366337
2023-01-24 08:19:49.305071: step: 2088/529, loss: 0.0058944872580468655
2023-01-24 08:19:50.372581: step: 2092/529, loss: 0.0022327504120767117
2023-01-24 08:19:51.438304: step: 2096/529, loss: 0.0022764084860682487
2023-01-24 08:19:52.508676: step: 2100/529, loss: 0.0009543506312184036
2023-01-24 08:19:53.602168: step: 2104/529, loss: 0.026266003027558327
2023-01-24 08:19:54.685143: step: 2108/529, loss: 0.004046869929879904
2023-01-24 08:19:55.763635: step: 2112/529, loss: 0.005345308221876621
2023-01-24 08:19:56.844553: step: 2116/529, loss: 0.011642795987427235
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3411712708587709, 'r': 0.3029756257341647, 'f1': 0.3209410145967936}, 'combined': 0.23648285286079526, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32891173013977915, 'r': 0.29051854105177183, 'f1': 0.30852530274702566}, 'combined': 0.2014206639695608, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3569305434149184, 'r': 0.3521895305042838, 'f1': 0.3545441883013516}, 'combined': 0.2612430861167854, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3575104214660032, 'r': 0.3138074011948833, 'f1': 0.33423637053356153}, 'combined': 0.21820612791310234, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3813744075017809, 'r': 0.3430198655708618, 'f1': 0.3611817565551332}, 'combined': 0.2661339258827297, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3676965831480542, 'r': 0.30280895082780934, 'f1': 0.33211304284340376}, 'combined': 0.21681991398066774, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580872292314783, 'r': 0.3574077468230694, 'f1': 0.3577471653860543}, 'combined': 0.2636031744949873, 'stategy': 1, 'epoch': 11}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36065178272254766, 'r': 0.3165647541360598, 'f1': 0.3371732280959697}, 'combined': 0.2201234546118766, 'stategy': 1, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
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 08:22:28.786396: step: 4/529, loss: 0.00824214518070221
2023-01-24 08:22:29.857852: step: 8/529, loss: 0.0006485304911620915
2023-01-24 08:22:30.927650: step: 12/529, loss: 0.004493335727602243
2023-01-24 08:22:31.995595: step: 16/529, loss: 0.007203877437859774
2023-01-24 08:22:33.059057: step: 20/529, loss: 0.009456831030547619
2023-01-24 08:22:34.120565: step: 24/529, loss: 0.0017443131655454636
2023-01-24 08:22:35.183948: step: 28/529, loss: 0.01108352281153202
2023-01-24 08:22:36.245971: step: 32/529, loss: 0.01880197413265705
2023-01-24 08:22:37.317739: step: 36/529, loss: 0.0032266222406178713
2023-01-24 08:22:38.382601: step: 40/529, loss: 0.00032905503758229315
2023-01-24 08:22:39.453348: step: 44/529, loss: 2.7835616492666304e-05
2023-01-24 08:22:40.521644: step: 48/529, loss: 0.000580169667955488
2023-01-24 08:22:41.579407: step: 52/529, loss: 0.006601984612643719
2023-01-24 08:22:42.636468: step: 56/529, loss: 0.006240781396627426
2023-01-24 08:22:43.706913: step: 60/529, loss: 0.0003889532817993313
2023-01-24 08:22:44.770409: step: 64/529, loss: 0.009685706347227097
2023-01-24 08:22:45.838791: step: 68/529, loss: 0.005073095206171274
2023-01-24 08:22:46.902671: step: 72/529, loss: 0.0002205546188633889
2023-01-24 08:22:47.982184: step: 76/529, loss: 0.0005509615293703973
2023-01-24 08:22:49.037926: step: 80/529, loss: 3.432148787396727e-06
2023-01-24 08:22:50.119269: step: 84/529, loss: 0.0003260619705542922
2023-01-24 08:22:51.178938: step: 88/529, loss: 0.00610450329259038
2023-01-24 08:22:52.254908: step: 92/529, loss: 0.010843431577086449
2023-01-24 08:22:53.334902: step: 96/529, loss: 0.0023373360745608807
2023-01-24 08:22:54.422614: step: 100/529, loss: 0.0012215864844620228
2023-01-24 08:22:55.502443: step: 104/529, loss: 0.0003956040018238127
2023-01-24 08:22:56.564212: step: 108/529, loss: 0.006970307789742947
2023-01-24 08:22:57.623924: step: 112/529, loss: 0.00034082215279340744
2023-01-24 08:22:58.693163: step: 116/529, loss: 0.0028653612826019526
2023-01-24 08:22:59.760259: step: 120/529, loss: 0.0023257178254425526
2023-01-24 08:23:00.821794: step: 124/529, loss: 0.0014433900360018015
2023-01-24 08:23:01.911331: step: 128/529, loss: 0.0045508709736168385
2023-01-24 08:23:02.979152: step: 132/529, loss: 4.12813933508005e-05
2023-01-24 08:23:04.048678: step: 136/529, loss: 0.000526791496668011
2023-01-24 08:23:05.121410: step: 140/529, loss: 0.011098070070147514
2023-01-24 08:23:06.178360: step: 144/529, loss: 0.0017983197467401624
2023-01-24 08:23:07.240926: step: 148/529, loss: 0.001859365263953805
2023-01-24 08:23:08.322714: step: 152/529, loss: 0.013218419626355171
2023-01-24 08:23:09.393138: step: 156/529, loss: 0.007587966043502092
2023-01-24 08:23:10.451884: step: 160/529, loss: 0.0051147788763046265
2023-01-24 08:23:11.525253: step: 164/529, loss: 0.00010762804595287889
2023-01-24 08:23:12.597291: step: 168/529, loss: 0.00015817872190382332
2023-01-24 08:23:13.679050: step: 172/529, loss: 0.019348064437508583
2023-01-24 08:23:14.740755: step: 176/529, loss: 0.0064213513396680355
2023-01-24 08:23:15.817450: step: 180/529, loss: 0.00465433718636632
2023-01-24 08:23:16.904949: step: 184/529, loss: 0.0021932865492999554
2023-01-24 08:23:17.995777: step: 188/529, loss: 0.005030844826251268
2023-01-24 08:23:19.057974: step: 192/529, loss: 0.004534582607448101
2023-01-24 08:23:20.118065: step: 196/529, loss: 0.0021553875412791967
2023-01-24 08:23:21.180836: step: 200/529, loss: 0.004790895618498325
2023-01-24 08:23:22.261933: step: 204/529, loss: 0.0001650998747209087
2023-01-24 08:23:23.323250: step: 208/529, loss: 0.0021575833670794964
2023-01-24 08:23:24.396821: step: 212/529, loss: 0.005316279362887144
2023-01-24 08:23:25.462034: step: 216/529, loss: 0.0034932380076497793
2023-01-24 08:23:26.534385: step: 220/529, loss: 0.004438444040715694
2023-01-24 08:23:27.608099: step: 224/529, loss: 0.00034117026370950043
2023-01-24 08:23:28.675849: step: 228/529, loss: 0.011383119970560074
2023-01-24 08:23:29.751712: step: 232/529, loss: 0.001447061775252223
2023-01-24 08:23:30.825845: step: 236/529, loss: 0.0009878063574433327
2023-01-24 08:23:31.905484: step: 240/529, loss: 0.0016755458200350404
2023-01-24 08:23:32.977122: step: 244/529, loss: 0.0026080089155584574
2023-01-24 08:23:34.069721: step: 248/529, loss: 0.0010913778096437454
2023-01-24 08:23:35.156439: step: 252/529, loss: 0.0028230883181095123
2023-01-24 08:23:36.218283: step: 256/529, loss: 0.001103143789805472
2023-01-24 08:23:37.287626: step: 260/529, loss: 0.00041276152478531003
2023-01-24 08:23:38.356311: step: 264/529, loss: 0.025269627571105957
2023-01-24 08:23:39.417470: step: 268/529, loss: 0.015226365998387337
2023-01-24 08:23:40.478681: step: 272/529, loss: 8.569552301196381e-05
2023-01-24 08:23:41.544071: step: 276/529, loss: 0.0
2023-01-24 08:23:42.610384: step: 280/529, loss: 0.006448135245591402
2023-01-24 08:23:43.668994: step: 284/529, loss: 0.0026999583933502436
2023-01-24 08:23:44.743532: step: 288/529, loss: 0.00784483551979065
2023-01-24 08:23:45.822844: step: 292/529, loss: 0.0004777391441166401
2023-01-24 08:23:46.904715: step: 296/529, loss: 0.0008279381436295807
2023-01-24 08:23:47.981630: step: 300/529, loss: 0.006379679776728153
2023-01-24 08:23:49.046016: step: 304/529, loss: 0.0020584098529070616
2023-01-24 08:23:50.121018: step: 308/529, loss: 0.006110067013651133
2023-01-24 08:23:51.184003: step: 312/529, loss: 0.03464924544095993
2023-01-24 08:23:52.255368: step: 316/529, loss: 0.0020083491690456867
2023-01-24 08:23:53.309522: step: 320/529, loss: 0.00013349168875720352
2023-01-24 08:23:54.378365: step: 324/529, loss: 0.007500241044908762
2023-01-24 08:23:55.438263: step: 328/529, loss: 0.0023305623326450586
2023-01-24 08:23:56.510481: step: 332/529, loss: 0.005106762051582336
2023-01-24 08:23:57.576758: step: 336/529, loss: 0.004585073795169592
2023-01-24 08:23:58.656822: step: 340/529, loss: 0.00680381478741765
2023-01-24 08:23:59.728928: step: 344/529, loss: 0.001004521851427853
2023-01-24 08:24:00.796998: step: 348/529, loss: 0.008059404790401459
2023-01-24 08:24:01.861495: step: 352/529, loss: 0.008250962011516094
2023-01-24 08:24:02.928322: step: 356/529, loss: 0.001658450230024755
2023-01-24 08:24:04.006399: step: 360/529, loss: 0.0024763462133705616
2023-01-24 08:24:05.066813: step: 364/529, loss: 0.0008286912343464792
2023-01-24 08:24:06.137741: step: 368/529, loss: 0.00506360549479723
2023-01-24 08:24:07.221852: step: 372/529, loss: 0.0002563508751336485
2023-01-24 08:24:08.308273: step: 376/529, loss: 0.0045692203566432
2023-01-24 08:24:09.385480: step: 380/529, loss: 0.0001046157703967765
2023-01-24 08:24:10.450044: step: 384/529, loss: 0.004003176931291819
2023-01-24 08:24:11.507710: step: 388/529, loss: 0.012683391571044922
2023-01-24 08:24:12.596678: step: 392/529, loss: 0.009644143283367157
2023-01-24 08:24:13.677672: step: 396/529, loss: 0.0026218497660011053
2023-01-24 08:24:14.770200: step: 400/529, loss: 0.0028819614090025425
2023-01-24 08:24:15.839763: step: 404/529, loss: 0.00339402980171144
2023-01-24 08:24:16.933018: step: 408/529, loss: 0.0032723492477089167
2023-01-24 08:24:18.001368: step: 412/529, loss: 0.000563874957151711
2023-01-24 08:24:19.069554: step: 416/529, loss: 0.0002562661247793585
2023-01-24 08:24:20.127962: step: 420/529, loss: 6.370181893089466e-08
2023-01-24 08:24:21.192328: step: 424/529, loss: 0.0011810840805992484
2023-01-24 08:24:22.255165: step: 428/529, loss: 0.005647722166031599
2023-01-24 08:24:23.328659: step: 432/529, loss: 0.008015875704586506
2023-01-24 08:24:24.414746: step: 436/529, loss: 0.0013981559313833714
2023-01-24 08:24:25.488226: step: 440/529, loss: 0.006221064832061529
2023-01-24 08:24:26.562230: step: 444/529, loss: 0.005132558289915323
2023-01-24 08:24:27.622478: step: 448/529, loss: 0.00134725880343467
2023-01-24 08:24:28.692953: step: 452/529, loss: 0.015525266528129578
2023-01-24 08:24:29.759303: step: 456/529, loss: 0.0005615393165498972
2023-01-24 08:24:30.833944: step: 460/529, loss: 0.0008262925548478961
2023-01-24 08:24:31.905862: step: 464/529, loss: 0.0009931253734976053
2023-01-24 08:24:32.980340: step: 468/529, loss: 0.00593172712251544
2023-01-24 08:24:34.054801: step: 472/529, loss: 0.004466334357857704
2023-01-24 08:24:35.116554: step: 476/529, loss: 0.0019491706043481827
2023-01-24 08:24:36.195314: step: 480/529, loss: 0.0001354796695522964
2023-01-24 08:24:37.273332: step: 484/529, loss: 0.0017280488973483443
2023-01-24 08:24:38.346365: step: 488/529, loss: 0.0015871248906478286
2023-01-24 08:24:39.413356: step: 492/529, loss: 0.00016232201596722007
2023-01-24 08:24:40.482449: step: 496/529, loss: 0.004697137512266636
2023-01-24 08:24:41.556736: step: 500/529, loss: 0.0025716538075357676
2023-01-24 08:24:42.621405: step: 504/529, loss: 0.001128175645135343
2023-01-24 08:24:43.708478: step: 508/529, loss: 0.0031883204355835915
2023-01-24 08:24:44.775896: step: 512/529, loss: 0.00993662141263485
2023-01-24 08:24:45.840824: step: 516/529, loss: 0.0029723665211349726
2023-01-24 08:24:46.900221: step: 520/529, loss: 0.0053993407636880875
2023-01-24 08:24:47.970445: step: 524/529, loss: 0.0024499623104929924
2023-01-24 08:24:49.042227: step: 528/529, loss: 0.001859718351624906
2023-01-24 08:24:50.125533: step: 532/529, loss: 0.006356637459248304
2023-01-24 08:24:51.212332: step: 536/529, loss: 0.020191717892885208
2023-01-24 08:24:52.287659: step: 540/529, loss: 0.0018192763673141599
2023-01-24 08:24:53.371888: step: 544/529, loss: 0.00022298246040008962
2023-01-24 08:24:54.443641: step: 548/529, loss: 0.0011389312567189336
2023-01-24 08:24:55.516722: step: 552/529, loss: 0.0046478998847305775
2023-01-24 08:24:56.593045: step: 556/529, loss: 0.011164539493620396
2023-01-24 08:24:57.670321: step: 560/529, loss: 0.000698400370310992
2023-01-24 08:24:58.736213: step: 564/529, loss: 0.0031681659165769815
2023-01-24 08:24:59.822044: step: 568/529, loss: 0.0033868071623146534
2023-01-24 08:25:00.890682: step: 572/529, loss: 0.00022426863142754883
2023-01-24 08:25:01.974599: step: 576/529, loss: 0.006263082381337881
2023-01-24 08:25:03.049684: step: 580/529, loss: 0.0009689821163192391
2023-01-24 08:25:04.138876: step: 584/529, loss: 0.003132249228656292
2023-01-24 08:25:05.222180: step: 588/529, loss: 0.005541677121073008
2023-01-24 08:25:06.283656: step: 592/529, loss: 0.0068025351502001286
2023-01-24 08:25:07.349401: step: 596/529, loss: 0.0005151866935193539
2023-01-24 08:25:08.412617: step: 600/529, loss: 0.005062904674559832
2023-01-24 08:25:09.475575: step: 604/529, loss: 0.0010287613840773702
2023-01-24 08:25:10.549270: step: 608/529, loss: 0.010212545283138752
2023-01-24 08:25:11.614917: step: 612/529, loss: 0.0031777014955878258
2023-01-24 08:25:12.667586: step: 616/529, loss: 0.0008616489940322936
2023-01-24 08:25:13.752502: step: 620/529, loss: 0.003417890053242445
2023-01-24 08:25:14.834145: step: 624/529, loss: 0.002632226562127471
2023-01-24 08:25:15.905918: step: 628/529, loss: 3.271413879701868e-05
2023-01-24 08:25:16.998167: step: 632/529, loss: 0.0071709370240569115
2023-01-24 08:25:18.063645: step: 636/529, loss: 0.001597222755663097
2023-01-24 08:25:19.132521: step: 640/529, loss: 0.00589072797447443
2023-01-24 08:25:20.210776: step: 644/529, loss: 0.001144689624197781
2023-01-24 08:25:21.274920: step: 648/529, loss: 0.003911987412720919
2023-01-24 08:25:22.361406: step: 652/529, loss: 0.0004588759911712259
2023-01-24 08:25:23.426874: step: 656/529, loss: 0.00029177276883274317
2023-01-24 08:25:24.479975: step: 660/529, loss: 0.0014887326397001743
2023-01-24 08:25:25.562681: step: 664/529, loss: 0.004669911228120327
2023-01-24 08:25:26.618907: step: 668/529, loss: 0.007444572169333696
2023-01-24 08:25:27.692800: step: 672/529, loss: 0.0008700828766450286
2023-01-24 08:25:28.759215: step: 676/529, loss: 0.0003717791405506432
2023-01-24 08:25:29.870843: step: 680/529, loss: 0.0018614951986819506
2023-01-24 08:25:30.943449: step: 684/529, loss: 0.0014391134027391672
2023-01-24 08:25:32.025614: step: 688/529, loss: 1.0803304206774555e-07
2023-01-24 08:25:33.095323: step: 692/529, loss: 0.005155359860509634
2023-01-24 08:25:34.177158: step: 696/529, loss: 0.003998635336756706
2023-01-24 08:25:35.291976: step: 700/529, loss: 0.0009432635270059109
2023-01-24 08:25:36.359311: step: 704/529, loss: 0.0010925807291641831
2023-01-24 08:25:37.424264: step: 708/529, loss: 0.004977728705853224
2023-01-24 08:25:38.489742: step: 712/529, loss: 0.028033442795276642
2023-01-24 08:25:39.543309: step: 716/529, loss: 0.0008672356489114463
2023-01-24 08:25:40.627299: step: 720/529, loss: 0.0010278065456077456
2023-01-24 08:25:41.682578: step: 724/529, loss: 0.0009569845860823989
2023-01-24 08:25:42.756910: step: 728/529, loss: 0.006153136491775513
2023-01-24 08:25:43.848536: step: 732/529, loss: 0.0005688882665708661
2023-01-24 08:25:44.915468: step: 736/529, loss: 0.006432798225432634
2023-01-24 08:25:45.993014: step: 740/529, loss: 0.0031695724464952946
2023-01-24 08:25:47.046196: step: 744/529, loss: 0.002205257536843419
2023-01-24 08:25:48.122172: step: 748/529, loss: 0.001660765497945249
2023-01-24 08:25:49.201240: step: 752/529, loss: 0.000290944502921775
2023-01-24 08:25:50.264226: step: 756/529, loss: 0.004038677550852299
2023-01-24 08:25:51.331828: step: 760/529, loss: 0.018525337800383568
2023-01-24 08:25:52.412888: step: 764/529, loss: 0.004912679083645344
2023-01-24 08:25:53.476540: step: 768/529, loss: 0.037664324045181274
2023-01-24 08:25:54.550829: step: 772/529, loss: 0.03377256169915199
2023-01-24 08:25:55.620430: step: 776/529, loss: 0.001526806503534317
2023-01-24 08:25:56.687889: step: 780/529, loss: 0.0018826342420652509
2023-01-24 08:25:57.766014: step: 784/529, loss: 0.0022028882522135973
2023-01-24 08:25:58.824318: step: 788/529, loss: 0.0059320661239326
2023-01-24 08:25:59.892124: step: 792/529, loss: 1.5464382158825174e-05
2023-01-24 08:26:00.959013: step: 796/529, loss: 0.0032495378982275724
2023-01-24 08:26:02.023360: step: 800/529, loss: 0.0006169435800984502
2023-01-24 08:26:03.099320: step: 804/529, loss: 0.004915500525385141
2023-01-24 08:26:04.158568: step: 808/529, loss: 0.013608753681182861
2023-01-24 08:26:05.240218: step: 812/529, loss: 0.0049199918285012245
2023-01-24 08:26:06.317091: step: 816/529, loss: 0.006587619427591562
2023-01-24 08:26:07.372358: step: 820/529, loss: 0.0015551808755844831
2023-01-24 08:26:08.431836: step: 824/529, loss: 0.008166050538420677
2023-01-24 08:26:09.509691: step: 828/529, loss: 0.00920891109853983
2023-01-24 08:26:10.588697: step: 832/529, loss: 0.0018128411611542106
2023-01-24 08:26:11.652495: step: 836/529, loss: 0.0006175698363222182
2023-01-24 08:26:12.731569: step: 840/529, loss: 0.004237494897097349
2023-01-24 08:26:13.833937: step: 844/529, loss: 0.003978268709033728
2023-01-24 08:26:14.910690: step: 848/529, loss: 0.0027342909015715122
2023-01-24 08:26:15.959494: step: 852/529, loss: 0.010389260947704315
2023-01-24 08:26:17.029662: step: 856/529, loss: 0.005601401440799236
2023-01-24 08:26:18.101709: step: 860/529, loss: 0.0001558121875859797
2023-01-24 08:26:19.177415: step: 864/529, loss: 0.0004491571744438261
2023-01-24 08:26:20.251482: step: 868/529, loss: 0.0035772596020251513
2023-01-24 08:26:21.341682: step: 872/529, loss: 0.003511154092848301
2023-01-24 08:26:22.416780: step: 876/529, loss: 0.021909328177571297
2023-01-24 08:26:23.502650: step: 880/529, loss: 0.012795479036867619
2023-01-24 08:26:24.580714: step: 884/529, loss: 0.00991862639784813
2023-01-24 08:26:25.648905: step: 888/529, loss: 0.012951732613146305
2023-01-24 08:26:26.724126: step: 892/529, loss: 0.0009472208912484348
2023-01-24 08:26:27.801254: step: 896/529, loss: 0.000470205006422475
2023-01-24 08:26:28.872282: step: 900/529, loss: 0.0038967649452388287
2023-01-24 08:26:29.937553: step: 904/529, loss: 0.00014454267511609942
2023-01-24 08:26:30.998619: step: 908/529, loss: 0.00037391152000054717
2023-01-24 08:26:32.082341: step: 912/529, loss: 0.005236899945884943
2023-01-24 08:26:33.144253: step: 916/529, loss: 0.0035261260345578194
2023-01-24 08:26:34.219747: step: 920/529, loss: 0.0012421862920746207
2023-01-24 08:26:35.309974: step: 924/529, loss: 0.0034080306068062782
2023-01-24 08:26:36.377652: step: 928/529, loss: 0.0020261327736079693
2023-01-24 08:26:37.442563: step: 932/529, loss: 0.0039024525322020054
2023-01-24 08:26:38.529905: step: 936/529, loss: 0.0027381600812077522
2023-01-24 08:26:39.589388: step: 940/529, loss: 6.02755208092276e-05
2023-01-24 08:26:40.650662: step: 944/529, loss: 0.008762603625655174
2023-01-24 08:26:41.719915: step: 948/529, loss: 0.00030116699053905904
2023-01-24 08:26:42.792756: step: 952/529, loss: 0.0014694355195388198
2023-01-24 08:26:43.852752: step: 956/529, loss: 0.008344966918230057
2023-01-24 08:26:44.911038: step: 960/529, loss: 0.00015417247777804732
2023-01-24 08:26:45.980513: step: 964/529, loss: 0.004995978437364101
2023-01-24 08:26:47.056549: step: 968/529, loss: 0.0005209104856476188
2023-01-24 08:26:48.119812: step: 972/529, loss: 0.005219424609094858
2023-01-24 08:26:49.196389: step: 976/529, loss: 0.00030140328453853726
2023-01-24 08:26:50.277106: step: 980/529, loss: 0.004988627973943949
2023-01-24 08:26:51.352975: step: 984/529, loss: 0.0004941115621477365
2023-01-24 08:26:52.415435: step: 988/529, loss: 0.004638523794710636
2023-01-24 08:26:53.485511: step: 992/529, loss: 0.001124656293541193
2023-01-24 08:26:54.559373: step: 996/529, loss: 0.00223352387547493
2023-01-24 08:26:55.644695: step: 1000/529, loss: 0.001285680802538991
2023-01-24 08:26:56.730795: step: 1004/529, loss: 0.0013634903589263558
2023-01-24 08:26:57.793884: step: 1008/529, loss: 0.001708086347207427
2023-01-24 08:26:58.860617: step: 1012/529, loss: 0.004962691105902195
2023-01-24 08:26:59.925379: step: 1016/529, loss: 0.0010700155980885029
2023-01-24 08:27:01.014104: step: 1020/529, loss: 0.00023641200095880777
2023-01-24 08:27:02.094313: step: 1024/529, loss: 0.00754582742229104
2023-01-24 08:27:03.160412: step: 1028/529, loss: 0.005813295021653175
2023-01-24 08:27:04.217037: step: 1032/529, loss: 4.928624184685759e-05
2023-01-24 08:27:05.295573: step: 1036/529, loss: 0.0032214426901191473
2023-01-24 08:27:06.359511: step: 1040/529, loss: 0.006151001434773207
2023-01-24 08:27:07.429652: step: 1044/529, loss: 0.010917824693024158
2023-01-24 08:27:08.503633: step: 1048/529, loss: 0.005020971409976482
2023-01-24 08:27:09.578599: step: 1052/529, loss: 0.009902467019855976
2023-01-24 08:27:10.652010: step: 1056/529, loss: 0.0022045476362109184
2023-01-24 08:27:11.716611: step: 1060/529, loss: 0.007249363698065281
2023-01-24 08:27:12.804796: step: 1064/529, loss: 0.006000439636409283
2023-01-24 08:27:13.887064: step: 1068/529, loss: 0.011353102512657642
2023-01-24 08:27:14.978715: step: 1072/529, loss: 0.005109582561999559
2023-01-24 08:27:16.063572: step: 1076/529, loss: 0.0061624315567314625
2023-01-24 08:27:17.131681: step: 1080/529, loss: 0.00034367028274573386
2023-01-24 08:27:18.201610: step: 1084/529, loss: 0.0003387421602383256
2023-01-24 08:27:19.276438: step: 1088/529, loss: 0.006283136084675789
2023-01-24 08:27:20.374523: step: 1092/529, loss: 0.008878123946487904
2023-01-24 08:27:21.433080: step: 1096/529, loss: 6.844523886684328e-05
2023-01-24 08:27:22.499830: step: 1100/529, loss: 0.0013711864594370127
2023-01-24 08:27:23.575537: step: 1104/529, loss: 0.0066091218031942844
2023-01-24 08:27:24.647262: step: 1108/529, loss: 0.0019864237401634455
2023-01-24 08:27:25.729417: step: 1112/529, loss: 0.000602297717705369
2023-01-24 08:27:26.792182: step: 1116/529, loss: 0.002463366137817502
2023-01-24 08:27:27.875049: step: 1120/529, loss: 0.003219776088371873
2023-01-24 08:27:28.956023: step: 1124/529, loss: 0.02767278254032135
2023-01-24 08:27:30.032574: step: 1128/529, loss: 0.0003260983503423631
2023-01-24 08:27:31.099396: step: 1132/529, loss: 0.012269899249076843
2023-01-24 08:27:32.153882: step: 1136/529, loss: 8.498618990415707e-05
2023-01-24 08:27:33.218624: step: 1140/529, loss: 0.0058839088305830956
2023-01-24 08:27:34.285548: step: 1144/529, loss: 0.01344376616179943
2023-01-24 08:27:35.352711: step: 1148/529, loss: 0.0014127636095508933
2023-01-24 08:27:36.430348: step: 1152/529, loss: 0.0172192994505167
2023-01-24 08:27:37.531879: step: 1156/529, loss: 0.012244591489434242
2023-01-24 08:27:38.595250: step: 1160/529, loss: 0.006438829470425844
2023-01-24 08:27:39.671526: step: 1164/529, loss: 0.0033560418523848057
2023-01-24 08:27:40.762757: step: 1168/529, loss: 0.03704174607992172
2023-01-24 08:27:41.856535: step: 1172/529, loss: 0.001134713413193822
2023-01-24 08:27:42.938687: step: 1176/529, loss: 8.293869177578017e-05
2023-01-24 08:27:44.017532: step: 1180/529, loss: 0.007193255238234997
2023-01-24 08:27:45.081087: step: 1184/529, loss: 0.0035913093015551567
2023-01-24 08:27:46.152646: step: 1188/529, loss: 0.005067116115242243
2023-01-24 08:27:47.243545: step: 1192/529, loss: 0.03776457905769348
2023-01-24 08:27:48.317774: step: 1196/529, loss: 0.0029532411135733128
2023-01-24 08:27:49.392008: step: 1200/529, loss: 0.009159223176538944
2023-01-24 08:27:50.488721: step: 1204/529, loss: 0.003995794337242842
2023-01-24 08:27:51.560361: step: 1208/529, loss: 0.002940747421234846
2023-01-24 08:27:52.610753: step: 1212/529, loss: 0.005281684920191765
2023-01-24 08:27:53.722933: step: 1216/529, loss: 0.003792811883613467
2023-01-24 08:27:54.800918: step: 1220/529, loss: 7.246151653816923e-05
2023-01-24 08:27:55.874222: step: 1224/529, loss: 0.00017703989578876644
2023-01-24 08:27:56.956073: step: 1228/529, loss: 0.0006702755927108228
2023-01-24 08:27:58.052162: step: 1232/529, loss: 0.0014314763247966766
2023-01-24 08:27:59.114968: step: 1236/529, loss: 0.0014320998452603817
2023-01-24 08:28:00.191725: step: 1240/529, loss: 0.022254856303334236
2023-01-24 08:28:01.294475: step: 1244/529, loss: 0.011834208853542805
2023-01-24 08:28:02.375115: step: 1248/529, loss: 0.00435211043804884
2023-01-24 08:28:03.439577: step: 1252/529, loss: 0.006410572212189436
2023-01-24 08:28:04.509102: step: 1256/529, loss: 0.0004829451791010797
2023-01-24 08:28:05.582307: step: 1260/529, loss: 0.0005952382343821228
2023-01-24 08:28:06.649806: step: 1264/529, loss: 0.0013238408137112856
2023-01-24 08:28:07.742879: step: 1268/529, loss: 0.007921346463263035
2023-01-24 08:28:08.824005: step: 1272/529, loss: 0.00043858870049007237
2023-01-24 08:28:09.905304: step: 1276/529, loss: 0.00159892113879323
2023-01-24 08:28:10.993335: step: 1280/529, loss: 0.0639544203877449
2023-01-24 08:28:12.070705: step: 1284/529, loss: 0.0013967757113277912
2023-01-24 08:28:13.169377: step: 1288/529, loss: 3.5319928429089487e-05
2023-01-24 08:28:14.240601: step: 1292/529, loss: 0.010427518747746944
2023-01-24 08:28:15.303169: step: 1296/529, loss: 0.00037475820863619447
2023-01-24 08:28:16.380808: step: 1300/529, loss: 0.00021107254724483937
2023-01-24 08:28:17.437808: step: 1304/529, loss: 0.060003846883773804
2023-01-24 08:28:18.517589: step: 1308/529, loss: 0.02229604870080948
2023-01-24 08:28:19.590677: step: 1312/529, loss: 0.0038752174004912376
2023-01-24 08:28:20.669652: step: 1316/529, loss: 0.0001930451689986512
2023-01-24 08:28:21.741573: step: 1320/529, loss: 0.0027876130770891905
2023-01-24 08:28:22.828724: step: 1324/529, loss: 0.003849061904475093
2023-01-24 08:28:23.897656: step: 1328/529, loss: 0.005554105620831251
2023-01-24 08:28:24.977253: step: 1332/529, loss: 0.0014325926313176751
2023-01-24 08:28:26.058960: step: 1336/529, loss: 0.00343710882589221
2023-01-24 08:28:27.147075: step: 1340/529, loss: 0.03830718249082565
2023-01-24 08:28:28.217519: step: 1344/529, loss: 0.00295704766176641
2023-01-24 08:28:29.291103: step: 1348/529, loss: 0.002468763617798686
2023-01-24 08:28:30.358522: step: 1352/529, loss: 0.0012411042116582394
2023-01-24 08:28:31.414930: step: 1356/529, loss: 0.008442936465144157
2023-01-24 08:28:32.508112: step: 1360/529, loss: 0.0016720404382795095
2023-01-24 08:28:33.583939: step: 1364/529, loss: 0.000936595257371664
2023-01-24 08:28:34.660938: step: 1368/529, loss: 0.010597063228487968
2023-01-24 08:28:35.742156: step: 1372/529, loss: 0.003616020316258073
2023-01-24 08:28:36.811128: step: 1376/529, loss: 0.001012818538583815
2023-01-24 08:28:37.889873: step: 1380/529, loss: 0.0013415602734312415
2023-01-24 08:28:38.967864: step: 1384/529, loss: 0.0027728863060474396
2023-01-24 08:28:40.057118: step: 1388/529, loss: 0.00444216001778841
2023-01-24 08:28:41.132267: step: 1392/529, loss: 0.00015794373757671565
2023-01-24 08:28:42.201036: step: 1396/529, loss: 0.002407039748504758
2023-01-24 08:28:43.287615: step: 1400/529, loss: 0.0016656331717967987
2023-01-24 08:28:44.354707: step: 1404/529, loss: 0.0021918434649705887
2023-01-24 08:28:45.434161: step: 1408/529, loss: 0.002362446393817663
2023-01-24 08:28:46.501816: step: 1412/529, loss: 0.004766460508108139
2023-01-24 08:28:47.564834: step: 1416/529, loss: 0.005630891770124435
2023-01-24 08:28:48.637877: step: 1420/529, loss: 0.0015056979609653354
2023-01-24 08:28:49.709754: step: 1424/529, loss: 0.013482719659805298
2023-01-24 08:28:50.791295: step: 1428/529, loss: 0.005831719841808081
2023-01-24 08:28:51.853786: step: 1432/529, loss: 0.0019798949360847473
2023-01-24 08:28:52.925786: step: 1436/529, loss: 0.002944647567346692
2023-01-24 08:28:53.994657: step: 1440/529, loss: 0.0016318289563059807
2023-01-24 08:28:55.058360: step: 1444/529, loss: 0.007818658836185932
2023-01-24 08:28:56.124882: step: 1448/529, loss: 0.00045890428009442985
2023-01-24 08:28:57.187063: step: 1452/529, loss: 0.010443691164255142
2023-01-24 08:28:58.269899: step: 1456/529, loss: 0.006630977150052786
2023-01-24 08:28:59.359853: step: 1460/529, loss: 0.0072214072570204735
2023-01-24 08:29:00.436601: step: 1464/529, loss: 0.002359408885240555
2023-01-24 08:29:01.513074: step: 1468/529, loss: 0.00011643358448054641
2023-01-24 08:29:02.571942: step: 1472/529, loss: 0.010804359801113605
2023-01-24 08:29:03.650734: step: 1476/529, loss: 0.003163361456245184
2023-01-24 08:29:04.739619: step: 1480/529, loss: 0.0021558557637035847
2023-01-24 08:29:05.831200: step: 1484/529, loss: 0.0018655690364539623
2023-01-24 08:29:06.898306: step: 1488/529, loss: 0.001293476321734488
2023-01-24 08:29:07.992114: step: 1492/529, loss: 0.0015365119324997067
2023-01-24 08:29:09.083064: step: 1496/529, loss: 0.0004397197044454515
2023-01-24 08:29:10.160724: step: 1500/529, loss: 0.00013709231279790401
2023-01-24 08:29:11.231613: step: 1504/529, loss: 0.003821911755949259
2023-01-24 08:29:12.328421: step: 1508/529, loss: 7.101294613676146e-05
2023-01-24 08:29:13.428687: step: 1512/529, loss: 0.0037749484181404114
2023-01-24 08:29:14.511369: step: 1516/529, loss: 0.0071118841879069805
2023-01-24 08:29:15.583996: step: 1520/529, loss: 0.0004207525053061545
2023-01-24 08:29:16.643450: step: 1524/529, loss: 0.0030081754084676504
2023-01-24 08:29:17.750630: step: 1528/529, loss: 0.000305487570585683
2023-01-24 08:29:18.830042: step: 1532/529, loss: 0.004214287269860506
2023-01-24 08:29:19.917107: step: 1536/529, loss: 0.011443152092397213
2023-01-24 08:29:20.994097: step: 1540/529, loss: 0.010332275182008743
2023-01-24 08:29:22.067108: step: 1544/529, loss: 0.0007756793638691306
2023-01-24 08:29:23.135509: step: 1548/529, loss: 0.003838974516838789
2023-01-24 08:29:24.208225: step: 1552/529, loss: 0.004816325381398201
2023-01-24 08:29:25.267502: step: 1556/529, loss: 0.0028927952516824007
2023-01-24 08:29:26.336633: step: 1560/529, loss: 0.002183598931878805
2023-01-24 08:29:27.393358: step: 1564/529, loss: 0.004798260051757097
2023-01-24 08:29:28.462513: step: 1568/529, loss: 0.0064127701334655285
2023-01-24 08:29:29.535888: step: 1572/529, loss: 0.002084509702399373
2023-01-24 08:29:30.624115: step: 1576/529, loss: 0.006421895697712898
2023-01-24 08:29:31.692015: step: 1580/529, loss: 0.002261742250993848
2023-01-24 08:29:32.751008: step: 1584/529, loss: 0.00420528557151556
2023-01-24 08:29:33.827169: step: 1588/529, loss: 0.0011106288293376565
2023-01-24 08:29:34.918388: step: 1592/529, loss: 0.006521884817630053
2023-01-24 08:29:36.003532: step: 1596/529, loss: 0.013600890524685383
2023-01-24 08:29:37.073773: step: 1600/529, loss: 0.0025971289724111557
2023-01-24 08:29:38.153328: step: 1604/529, loss: 0.00014028883015271276
2023-01-24 08:29:39.221234: step: 1608/529, loss: 2.604587461974006e-05
2023-01-24 08:29:40.285844: step: 1612/529, loss: 4.4563814299181104e-05
2023-01-24 08:29:41.367989: step: 1616/529, loss: 0.0001973005710169673
2023-01-24 08:29:42.435606: step: 1620/529, loss: 0.001374994171783328
2023-01-24 08:29:43.529477: step: 1624/529, loss: 0.004968054126948118
2023-01-24 08:29:44.600645: step: 1628/529, loss: 0.0001699640997685492
2023-01-24 08:29:45.697856: step: 1632/529, loss: 0.0012247348204255104
2023-01-24 08:29:46.771780: step: 1636/529, loss: 0.0005153222009539604
2023-01-24 08:29:47.855802: step: 1640/529, loss: 0.009150661528110504
2023-01-24 08:29:48.921526: step: 1644/529, loss: 0.004539622459560633
2023-01-24 08:29:49.997289: step: 1648/529, loss: 0.0024223339278250933
2023-01-24 08:29:51.060518: step: 1652/529, loss: 0.005861751735210419
2023-01-24 08:29:52.129623: step: 1656/529, loss: 0.0034328049514442682
2023-01-24 08:29:53.197994: step: 1660/529, loss: 0.0067036347463727
2023-01-24 08:29:54.267301: step: 1664/529, loss: 0.0046232049353420734
2023-01-24 08:29:55.331792: step: 1668/529, loss: 0.008543912321329117
2023-01-24 08:29:56.412322: step: 1672/529, loss: 0.0013973599998280406
2023-01-24 08:29:57.510440: step: 1676/529, loss: 0.0075758653692901134
2023-01-24 08:29:58.582397: step: 1680/529, loss: 0.002628772985190153
2023-01-24 08:29:59.652113: step: 1684/529, loss: 3.391894279047847e-05
2023-01-24 08:30:00.720069: step: 1688/529, loss: 0.00017970365297514945
2023-01-24 08:30:01.797976: step: 1692/529, loss: 0.01029476709663868
2023-01-24 08:30:02.879922: step: 1696/529, loss: 0.005078609567135572
2023-01-24 08:30:03.965989: step: 1700/529, loss: 0.0010321841109544039
2023-01-24 08:30:05.026736: step: 1704/529, loss: 6.0735295846825466e-05
2023-01-24 08:30:06.101067: step: 1708/529, loss: 0.0003616898611653596
2023-01-24 08:30:07.166867: step: 1712/529, loss: 0.0001613723288755864
2023-01-24 08:30:08.257044: step: 1716/529, loss: 0.006900268141180277
2023-01-24 08:30:09.319068: step: 1720/529, loss: 0.00038855645107105374
2023-01-24 08:30:10.392987: step: 1724/529, loss: 4.684772648033686e-06
2023-01-24 08:30:11.468119: step: 1728/529, loss: 0.0012728418223559856
2023-01-24 08:30:12.542615: step: 1732/529, loss: 0.003334173932671547
2023-01-24 08:30:13.617040: step: 1736/529, loss: 0.002552600111812353
2023-01-24 08:30:14.690121: step: 1740/529, loss: 2.339587990718428e-05
2023-01-24 08:30:15.745652: step: 1744/529, loss: 0.0003956110740546137
2023-01-24 08:30:16.815619: step: 1748/529, loss: 0.005057722795754671
2023-01-24 08:30:17.874707: step: 1752/529, loss: 7.605341670569032e-05
2023-01-24 08:30:18.942283: step: 1756/529, loss: 0.0003037995775230229
2023-01-24 08:30:20.018731: step: 1760/529, loss: 0.012842925265431404
2023-01-24 08:30:21.092302: step: 1764/529, loss: 0.004501067101955414
2023-01-24 08:30:22.161631: step: 1768/529, loss: 0.001360322698019445
2023-01-24 08:30:23.228981: step: 1772/529, loss: 0.0017796738538891077
2023-01-24 08:30:24.330033: step: 1776/529, loss: 0.0035017579793930054
2023-01-24 08:30:25.395343: step: 1780/529, loss: 0.00018301911768503487
2023-01-24 08:30:26.469286: step: 1784/529, loss: 0.003364932257682085
2023-01-24 08:30:27.552082: step: 1788/529, loss: 0.0018085100455209613
2023-01-24 08:30:28.617258: step: 1792/529, loss: 0.0044455151073634624
2023-01-24 08:30:29.702536: step: 1796/529, loss: 0.0035848882980644703
2023-01-24 08:30:30.775930: step: 1800/529, loss: 0.002089511835947633
2023-01-24 08:30:31.838351: step: 1804/529, loss: 0.0010881441412493587
2023-01-24 08:30:32.920877: step: 1808/529, loss: 0.003012422239407897
2023-01-24 08:30:33.978872: step: 1812/529, loss: 0.0023543399292975664
2023-01-24 08:30:35.064322: step: 1816/529, loss: 0.00046483860933221877
2023-01-24 08:30:36.142155: step: 1820/529, loss: 0.0051916842348873615
2023-01-24 08:30:37.219813: step: 1824/529, loss: 0.0004477714537642896
2023-01-24 08:30:38.274345: step: 1828/529, loss: 0.0026559936814010143
2023-01-24 08:30:39.352910: step: 1832/529, loss: 0.039945535361766815
2023-01-24 08:30:40.411313: step: 1836/529, loss: 0.0017794484738260508
2023-01-24 08:30:41.491221: step: 1840/529, loss: 0.006043660920113325
2023-01-24 08:30:42.552946: step: 1844/529, loss: 0.0010697685647755861
2023-01-24 08:30:43.630917: step: 1848/529, loss: 0.00010163659317186102
2023-01-24 08:30:44.707706: step: 1852/529, loss: 0.005914970766752958
2023-01-24 08:30:45.780329: step: 1856/529, loss: 0.0015464090975001454
2023-01-24 08:30:46.856893: step: 1860/529, loss: 0.0026120194233953953
2023-01-24 08:30:47.931136: step: 1864/529, loss: 0.004273236729204655
2023-01-24 08:30:49.024259: step: 1868/529, loss: 0.015176031738519669
2023-01-24 08:30:50.094163: step: 1872/529, loss: 0.0030267895199358463
2023-01-24 08:30:51.163651: step: 1876/529, loss: 7.87690169090638e-06
2023-01-24 08:30:52.264026: step: 1880/529, loss: 0.0015675147296860814
2023-01-24 08:30:53.343309: step: 1884/529, loss: 0.0002008663141168654
2023-01-24 08:30:54.408185: step: 1888/529, loss: 0.003913629800081253
2023-01-24 08:30:55.471175: step: 1892/529, loss: 0.003583942074328661
2023-01-24 08:30:56.553784: step: 1896/529, loss: 0.0017871442250907421
2023-01-24 08:30:57.636737: step: 1900/529, loss: 0.001158599043264985
2023-01-24 08:30:58.725446: step: 1904/529, loss: 0.008377348072826862
2023-01-24 08:30:59.806422: step: 1908/529, loss: 0.007920026779174805
2023-01-24 08:31:00.891471: step: 1912/529, loss: 0.025390343740582466
2023-01-24 08:31:01.972289: step: 1916/529, loss: 0.006896121893078089
2023-01-24 08:31:03.041520: step: 1920/529, loss: 0.005686902441084385
2023-01-24 08:31:04.140271: step: 1924/529, loss: 0.016825594007968903
2023-01-24 08:31:05.206362: step: 1928/529, loss: 0.000193691739696078
2023-01-24 08:31:06.269555: step: 1932/529, loss: 0.0020622049923986197
2023-01-24 08:31:07.343271: step: 1936/529, loss: 0.01039885450154543
2023-01-24 08:31:08.427299: step: 1940/529, loss: 0.012124961242079735
2023-01-24 08:31:09.486995: step: 1944/529, loss: 0.00048159074503928423
2023-01-24 08:31:10.567601: step: 1948/529, loss: 0.00028677258524112403
2023-01-24 08:31:11.655629: step: 1952/529, loss: 0.010880428366363049
2023-01-24 08:31:12.729033: step: 1956/529, loss: 0.0038385135121643543
2023-01-24 08:31:13.822674: step: 1960/529, loss: 0.009883001446723938
2023-01-24 08:31:14.892330: step: 1964/529, loss: 0.000713395478669554
2023-01-24 08:31:15.975542: step: 1968/529, loss: 0.006667461711913347
2023-01-24 08:31:17.047667: step: 1972/529, loss: 0.0034269497264176607
2023-01-24 08:31:18.126636: step: 1976/529, loss: 0.0015176531160250306
2023-01-24 08:31:19.202439: step: 1980/529, loss: 0.006744371727108955
2023-01-24 08:31:20.278771: step: 1984/529, loss: 0.0022800147999078035
2023-01-24 08:31:21.351142: step: 1988/529, loss: 0.0009745724964886904
2023-01-24 08:31:22.427129: step: 1992/529, loss: 0.002331268973648548
2023-01-24 08:31:23.491610: step: 1996/529, loss: 0.007197085302323103
2023-01-24 08:31:24.573952: step: 2000/529, loss: 0.0016320046270266175
2023-01-24 08:31:25.642839: step: 2004/529, loss: 0.005486673209816217
2023-01-24 08:31:26.703998: step: 2008/529, loss: 0.0042807552963495255
2023-01-24 08:31:27.777384: step: 2012/529, loss: 0.0007030915003269911
2023-01-24 08:31:28.845204: step: 2016/529, loss: 0.003387653036043048
2023-01-24 08:31:29.913204: step: 2020/529, loss: 5.706393494619988e-05
2023-01-24 08:31:30.992510: step: 2024/529, loss: 0.027386324480175972
2023-01-24 08:31:32.062456: step: 2028/529, loss: 0.0034047963563352823
2023-01-24 08:31:33.147067: step: 2032/529, loss: 0.001972943777218461
2023-01-24 08:31:34.234543: step: 2036/529, loss: 0.0009757645893841982
2023-01-24 08:31:35.306892: step: 2040/529, loss: 0.00035479560028761625
2023-01-24 08:31:36.368416: step: 2044/529, loss: 0.0056922584772109985
2023-01-24 08:31:37.442403: step: 2048/529, loss: 0.0015625410014763474
2023-01-24 08:31:38.528900: step: 2052/529, loss: 0.007033843081444502
2023-01-24 08:31:39.598140: step: 2056/529, loss: 0.000552872137632221
2023-01-24 08:31:40.674788: step: 2060/529, loss: 0.004987975582480431
2023-01-24 08:31:41.767000: step: 2064/529, loss: 0.0005516937817446887
2023-01-24 08:31:42.880807: step: 2068/529, loss: 0.0039209662936627865
2023-01-24 08:31:43.950007: step: 2072/529, loss: 0.0013764798641204834
2023-01-24 08:31:45.042468: step: 2076/529, loss: 0.005496394354850054
2023-01-24 08:31:46.129163: step: 2080/529, loss: 0.0033817782532423735
2023-01-24 08:31:47.210982: step: 2084/529, loss: 0.0036234098952263594
2023-01-24 08:31:48.298870: step: 2088/529, loss: 0.0008921523112803698
2023-01-24 08:31:49.380441: step: 2092/529, loss: 0.005154572427272797
2023-01-24 08:31:50.471095: step: 2096/529, loss: 0.003025319427251816
2023-01-24 08:31:51.540127: step: 2100/529, loss: 0.0009227404370903969
2023-01-24 08:31:52.614072: step: 2104/529, loss: 0.0005347715341486037
2023-01-24 08:31:53.680435: step: 2108/529, loss: 0.008064485155045986
2023-01-24 08:31:54.758544: step: 2112/529, loss: 0.005259071476757526
2023-01-24 08:31:55.848648: step: 2116/529, loss: 0.00626530172303319
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34112134768981905, 'r': 0.3048731589409958, 'f1': 0.3219802700639375}, 'combined': 0.2372486200471118, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33133142389166953, 'r': 0.29143765869883065, 'f1': 0.3101067703318609}, 'combined': 0.20245312467261384, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36200361338917003, 'r': 0.3578821301247772, 'f1': 0.35993107361785803}, 'combined': 0.26521237003421116, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35480804679288436, 'r': 0.31013093060664804, 'f1': 0.3309685654733036}, 'combined': 0.21607274222609457, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3784517173078494, 'r': 0.342545482269154, 'f1': 0.3596045202307652}, 'combined': 0.2649717517489849, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36922473575492354, 'r': 0.30372806847486816, 'f1': 0.3332890958150848}, 'combined': 0.21758769985855278, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3620689655172414, 'r': 0.45652173913043476, 'f1': 0.4038461538461538}, 'combined': 0.2019230769230769, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580872292314783, 'r': 0.3574077468230694, 'f1': 0.3577471653860543}, 'combined': 0.2636031744949873, 'stategy': 1, 'epoch': 11}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36065178272254766, 'r': 0.3165647541360598, 'f1': 0.3371732280959697}, 'combined': 0.2201234546118766, 'stategy': 1, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:34:28.510229: step: 4/529, loss: 0.0013083918020129204
2023-01-24 08:34:29.583390: step: 8/529, loss: 0.001629989710636437
2023-01-24 08:34:30.637007: step: 12/529, loss: 0.00506221130490303
2023-01-24 08:34:31.709226: step: 16/529, loss: 0.00011804777022916824
2023-01-24 08:34:32.773609: step: 20/529, loss: 0.02768115885555744
2023-01-24 08:34:33.845842: step: 24/529, loss: 0.00039927702164277434
2023-01-24 08:34:34.922346: step: 28/529, loss: 0.002878830535337329
2023-01-24 08:34:35.974901: step: 32/529, loss: 0.0067565483041107655
2023-01-24 08:34:37.041109: step: 36/529, loss: 0.001153373857960105
2023-01-24 08:34:38.093322: step: 40/529, loss: 1.8734412151388824e-05
2023-01-24 08:34:39.172172: step: 44/529, loss: 0.0002706583763938397
2023-01-24 08:34:40.234386: step: 48/529, loss: 0.002159199910238385
2023-01-24 08:34:41.319707: step: 52/529, loss: 0.00034504308132454753
2023-01-24 08:34:42.381048: step: 56/529, loss: 0.00022985381656326354
2023-01-24 08:34:43.444258: step: 60/529, loss: 0.0035387659445405006
2023-01-24 08:34:44.492298: step: 64/529, loss: 0.0025859409943223
2023-01-24 08:34:45.561253: step: 68/529, loss: 0.00022430610260926187
2023-01-24 08:34:46.640345: step: 72/529, loss: 0.003941799979656935
2023-01-24 08:34:47.716157: step: 76/529, loss: 0.001380683621391654
2023-01-24 08:34:48.787134: step: 80/529, loss: 0.0023522034753113985
2023-01-24 08:34:49.857546: step: 84/529, loss: 0.00308869406580925
2023-01-24 08:34:50.921294: step: 88/529, loss: 0.006730386987328529
2023-01-24 08:34:51.999356: step: 92/529, loss: 0.00849398598074913
2023-01-24 08:34:53.079457: step: 96/529, loss: 0.008255600929260254
2023-01-24 08:34:54.171474: step: 100/529, loss: 0.002060904400423169
2023-01-24 08:34:55.272356: step: 104/529, loss: 0.0008200475131161511
2023-01-24 08:34:56.336776: step: 108/529, loss: 0.004485452547669411
2023-01-24 08:34:57.412580: step: 112/529, loss: 0.006593985483050346
2023-01-24 08:34:58.478202: step: 116/529, loss: 0.0028539884369820356
2023-01-24 08:34:59.560223: step: 120/529, loss: 0.0012559586903080344
2023-01-24 08:35:00.622548: step: 124/529, loss: 0.0001731273514451459
2023-01-24 08:35:01.700559: step: 128/529, loss: 0.003500661114230752
2023-01-24 08:35:02.773602: step: 132/529, loss: 0.0027256000321358442
2023-01-24 08:35:03.852152: step: 136/529, loss: 0.001709451200440526
2023-01-24 08:35:04.944297: step: 140/529, loss: 0.004447990097105503
2023-01-24 08:35:06.024151: step: 144/529, loss: 0.011341128498315811
2023-01-24 08:35:07.115530: step: 148/529, loss: 3.96544965042267e-06
2023-01-24 08:35:08.181137: step: 152/529, loss: 0.0001453894074074924
2023-01-24 08:35:09.250619: step: 156/529, loss: 9.502104512648657e-05
2023-01-24 08:35:10.315237: step: 160/529, loss: 0.002916882745921612
2023-01-24 08:35:11.380109: step: 164/529, loss: 0.0022351504303514957
2023-01-24 08:35:12.465361: step: 168/529, loss: 0.006104897707700729
2023-01-24 08:35:13.575062: step: 172/529, loss: 0.002474898938089609
2023-01-24 08:35:14.646696: step: 176/529, loss: 0.0005531220231205225
2023-01-24 08:35:15.719582: step: 180/529, loss: 0.0026697826106101274
2023-01-24 08:35:16.820628: step: 184/529, loss: 0.0064180525951087475
2023-01-24 08:35:17.898420: step: 188/529, loss: 0.002999653108417988
2023-01-24 08:35:19.004858: step: 192/529, loss: 0.025464113801717758
2023-01-24 08:35:20.085239: step: 196/529, loss: 0.009232824668288231
2023-01-24 08:35:21.159537: step: 200/529, loss: 0.00032653496600687504
2023-01-24 08:35:22.239710: step: 204/529, loss: 0.0027034401427954435
2023-01-24 08:35:23.321721: step: 208/529, loss: 0.003960411064326763
2023-01-24 08:35:24.392546: step: 212/529, loss: 0.003326426725834608
2023-01-24 08:35:25.470261: step: 216/529, loss: 0.010160683654248714
2023-01-24 08:35:26.556717: step: 220/529, loss: 0.0036211484111845493
2023-01-24 08:35:27.636360: step: 224/529, loss: 0.0005328348488546908
2023-01-24 08:35:28.719637: step: 228/529, loss: 0.004893571604043245
2023-01-24 08:35:29.794002: step: 232/529, loss: 0.0014357338659465313
2023-01-24 08:35:30.873458: step: 236/529, loss: 0.006993093993514776
2023-01-24 08:35:31.948195: step: 240/529, loss: 0.0041709295473992825
2023-01-24 08:35:33.023257: step: 244/529, loss: 0.0023953274358063936
2023-01-24 08:35:34.110724: step: 248/529, loss: 0.005794886499643326
2023-01-24 08:35:35.198685: step: 252/529, loss: 3.386481694178656e-05
2023-01-24 08:35:36.275970: step: 256/529, loss: 0.0032592457719147205
2023-01-24 08:35:37.366323: step: 260/529, loss: 0.00032845191890373826
2023-01-24 08:35:38.450744: step: 264/529, loss: 8.309235272463411e-05
2023-01-24 08:35:39.519043: step: 268/529, loss: 0.004330434370785952
2023-01-24 08:35:40.590629: step: 272/529, loss: 0.00031662671244703233
2023-01-24 08:35:41.668383: step: 276/529, loss: 0.009323946200311184
2023-01-24 08:35:42.730998: step: 280/529, loss: 0.000254539045272395
2023-01-24 08:35:43.835397: step: 284/529, loss: 0.0436927005648613
2023-01-24 08:35:44.903213: step: 288/529, loss: 0.006670475006103516
2023-01-24 08:35:45.973281: step: 292/529, loss: 0.00038110025343485177
2023-01-24 08:35:47.050741: step: 296/529, loss: 0.010616067796945572
2023-01-24 08:35:48.113859: step: 300/529, loss: 0.0001866883394541219
2023-01-24 08:35:49.179197: step: 304/529, loss: 0.0013444084906950593
2023-01-24 08:35:50.236736: step: 308/529, loss: 0.0041800630278885365
2023-01-24 08:35:51.311892: step: 312/529, loss: 0.008285368792712688
2023-01-24 08:35:52.386088: step: 316/529, loss: 0.0015832665376365185
2023-01-24 08:35:53.468986: step: 320/529, loss: 0.0008135446696542203
2023-01-24 08:35:54.556197: step: 324/529, loss: 6.871490768389776e-05
2023-01-24 08:35:55.642580: step: 328/529, loss: 0.004307453986257315
2023-01-24 08:35:56.714606: step: 332/529, loss: 0.00017551037308294326
2023-01-24 08:35:57.789793: step: 336/529, loss: 0.0010425669606775045
2023-01-24 08:35:58.864885: step: 340/529, loss: 0.0002904363500420004
2023-01-24 08:35:59.936321: step: 344/529, loss: 0.009340458549559116
2023-01-24 08:36:01.009846: step: 348/529, loss: 0.0013986770063638687
2023-01-24 08:36:02.079135: step: 352/529, loss: 0.002482094569131732
2023-01-24 08:36:03.142959: step: 356/529, loss: 0.0004495203902479261
2023-01-24 08:36:04.228499: step: 360/529, loss: 0.0010811351239681244
2023-01-24 08:36:05.306300: step: 364/529, loss: 0.04078175500035286
2023-01-24 08:36:06.393569: step: 368/529, loss: 0.0013570310547947884
2023-01-24 08:36:07.472013: step: 372/529, loss: 0.002462711650878191
2023-01-24 08:36:08.545442: step: 376/529, loss: 0.001508450717665255
2023-01-24 08:36:09.623655: step: 380/529, loss: 0.007940758019685745
2023-01-24 08:36:10.720139: step: 384/529, loss: 0.005111399106681347
2023-01-24 08:36:11.795202: step: 388/529, loss: 0.00037518609315156937
2023-01-24 08:36:12.887822: step: 392/529, loss: 0.0051468126475811005
2023-01-24 08:36:13.960500: step: 396/529, loss: 0.008642208762466908
2023-01-24 08:36:15.039843: step: 400/529, loss: 0.01035205740481615
2023-01-24 08:36:16.104779: step: 404/529, loss: 0.006263865157961845
2023-01-24 08:36:17.165060: step: 408/529, loss: 3.7809741115779616e-06
2023-01-24 08:36:18.229404: step: 412/529, loss: 0.002615247620269656
2023-01-24 08:36:19.302705: step: 416/529, loss: 0.01604885421693325
2023-01-24 08:36:20.370297: step: 420/529, loss: 0.003055088222026825
2023-01-24 08:36:21.437747: step: 424/529, loss: 0.001945036114193499
2023-01-24 08:36:22.497971: step: 428/529, loss: 0.0010235343361273408
2023-01-24 08:36:23.572640: step: 432/529, loss: 6.6673992478172295e-06
2023-01-24 08:36:24.660898: step: 436/529, loss: 0.0022046423982828856
2023-01-24 08:36:25.737372: step: 440/529, loss: 0.0015066710766404867
2023-01-24 08:36:26.833402: step: 444/529, loss: 0.005969975609332323
2023-01-24 08:36:27.904959: step: 448/529, loss: 0.0009364045108668506
2023-01-24 08:36:28.987843: step: 452/529, loss: 0.00505894236266613
2023-01-24 08:36:30.078063: step: 456/529, loss: 0.0006616225582547486
2023-01-24 08:36:31.152725: step: 460/529, loss: 0.008182837627828121
2023-01-24 08:36:32.208909: step: 464/529, loss: 0.00038651531212963164
2023-01-24 08:36:33.276346: step: 468/529, loss: 0.0025241547264158726
2023-01-24 08:36:34.353132: step: 472/529, loss: 0.0015358327655121684
2023-01-24 08:36:35.407487: step: 476/529, loss: 0.0007262724684551358
2023-01-24 08:36:36.488595: step: 480/529, loss: 0.00014446189743466675
2023-01-24 08:36:37.567485: step: 484/529, loss: 0.020341655239462852
2023-01-24 08:36:38.639663: step: 488/529, loss: 0.014740174636244774
2023-01-24 08:36:39.715676: step: 492/529, loss: 0.002303437562659383
2023-01-24 08:36:40.781571: step: 496/529, loss: 0.000746925245039165
2023-01-24 08:36:41.864563: step: 500/529, loss: 0.012227782048285007
2023-01-24 08:36:42.936847: step: 504/529, loss: 0.00623081810772419
2023-01-24 08:36:44.003354: step: 508/529, loss: 0.005031298846006393
2023-01-24 08:36:45.086297: step: 512/529, loss: 0.00010093992023030296
2023-01-24 08:36:46.165778: step: 516/529, loss: 0.002336269710212946
2023-01-24 08:36:47.224876: step: 520/529, loss: 0.006468994077295065
2023-01-24 08:36:48.303799: step: 524/529, loss: 0.00030392836197279394
2023-01-24 08:36:49.374896: step: 528/529, loss: 0.002299483399838209
2023-01-24 08:36:50.452569: step: 532/529, loss: 0.004743121098726988
2023-01-24 08:36:51.513722: step: 536/529, loss: 0.0024499150458723307
2023-01-24 08:36:52.588550: step: 540/529, loss: 0.0019470476545393467
2023-01-24 08:36:53.665450: step: 544/529, loss: 0.00031268014572560787
2023-01-24 08:36:54.754929: step: 548/529, loss: 0.0016287235775962472
2023-01-24 08:36:55.834619: step: 552/529, loss: 0.003286950755864382
2023-01-24 08:36:56.921296: step: 556/529, loss: 0.006994290743023157
2023-01-24 08:36:57.997461: step: 560/529, loss: 4.9108646635431796e-05
2023-01-24 08:36:59.075366: step: 564/529, loss: 0.0017090942710638046
2023-01-24 08:37:00.163685: step: 568/529, loss: 0.004771821200847626
2023-01-24 08:37:01.234257: step: 572/529, loss: 0.0027980839367955923
2023-01-24 08:37:02.299300: step: 576/529, loss: 0.007625539321452379
2023-01-24 08:37:03.369776: step: 580/529, loss: 0.0020463312976062298
2023-01-24 08:37:04.445327: step: 584/529, loss: 0.0023525923024863005
2023-01-24 08:37:05.517675: step: 588/529, loss: 0.00694476580247283
2023-01-24 08:37:06.585838: step: 592/529, loss: 0.002207657555118203
2023-01-24 08:37:07.646941: step: 596/529, loss: 0.008983233943581581
2023-01-24 08:37:08.709324: step: 600/529, loss: 0.0001583544653840363
2023-01-24 08:37:09.790803: step: 604/529, loss: 0.011797570623457432
2023-01-24 08:37:10.851299: step: 608/529, loss: 0.0018957924330607057
2023-01-24 08:37:11.927661: step: 612/529, loss: 0.0031891940161585808
2023-01-24 08:37:13.018435: step: 616/529, loss: 0.057069331407547
2023-01-24 08:37:14.103953: step: 620/529, loss: 0.0033412936609238386
2023-01-24 08:37:15.179113: step: 624/529, loss: 0.005603430327028036
2023-01-24 08:37:16.257064: step: 628/529, loss: 0.00172527099493891
2023-01-24 08:37:17.339101: step: 632/529, loss: 0.0023448984138667583
2023-01-24 08:37:18.412955: step: 636/529, loss: 0.00036707372055388987
2023-01-24 08:37:19.481929: step: 640/529, loss: 0.003940449096262455
2023-01-24 08:37:20.546994: step: 644/529, loss: 0.011811473406851292
2023-01-24 08:37:21.617318: step: 648/529, loss: 0.0009290999732911587
2023-01-24 08:37:22.678120: step: 652/529, loss: 0.0040426068007946014
2023-01-24 08:37:23.742353: step: 656/529, loss: 0.00016602044343017042
2023-01-24 08:37:24.808407: step: 660/529, loss: 0.000490012695081532
2023-01-24 08:37:25.884035: step: 664/529, loss: 0.013274741359055042
2023-01-24 08:37:26.950715: step: 668/529, loss: 0.004442111123353243
2023-01-24 08:37:28.012528: step: 672/529, loss: 0.004331009928137064
2023-01-24 08:37:29.094065: step: 676/529, loss: 0.006994915660470724
2023-01-24 08:37:30.152446: step: 680/529, loss: 0.007527124602347612
2023-01-24 08:37:31.213386: step: 684/529, loss: 0.00945842731744051
2023-01-24 08:37:32.295822: step: 688/529, loss: 0.0007517659105360508
2023-01-24 08:37:33.360190: step: 692/529, loss: 0.004018715582787991
2023-01-24 08:37:34.424507: step: 696/529, loss: 0.0004807522054761648
2023-01-24 08:37:35.499297: step: 700/529, loss: 0.0001125754788517952
2023-01-24 08:37:36.589649: step: 704/529, loss: 0.0015589147806167603
2023-01-24 08:37:37.670738: step: 708/529, loss: 0.0030514593236148357
2023-01-24 08:37:38.753228: step: 712/529, loss: 0.00042455235961824656
2023-01-24 08:37:39.842328: step: 716/529, loss: 0.0030508958734571934
2023-01-24 08:37:40.912719: step: 720/529, loss: 0.0029742801561951637
2023-01-24 08:37:41.993051: step: 724/529, loss: 0.028850683942437172
2023-01-24 08:37:43.104167: step: 728/529, loss: 0.0040900311432778835
2023-01-24 08:37:44.181535: step: 732/529, loss: 0.00011467358126537874
2023-01-24 08:37:45.251434: step: 736/529, loss: 1.7049587768269703e-05
2023-01-24 08:37:46.310540: step: 740/529, loss: 0.004052354954183102
2023-01-24 08:37:47.394265: step: 744/529, loss: 0.007852279581129551
2023-01-24 08:37:48.465796: step: 748/529, loss: 0.00012509440421126783
2023-01-24 08:37:49.530729: step: 752/529, loss: 0.004132823087275028
2023-01-24 08:37:50.606077: step: 756/529, loss: 0.0019473739666864276
2023-01-24 08:37:51.689971: step: 760/529, loss: 0.003840666264295578
2023-01-24 08:37:52.754931: step: 764/529, loss: 0.0057149589993059635
2023-01-24 08:37:53.826027: step: 768/529, loss: 0.0009152949205599725
2023-01-24 08:37:54.904394: step: 772/529, loss: 0.005389711819589138
2023-01-24 08:37:55.988923: step: 776/529, loss: 0.005897090770304203
2023-01-24 08:37:57.053736: step: 780/529, loss: 0.0005674312124028802
2023-01-24 08:37:58.112971: step: 784/529, loss: 0.0024358986411243677
2023-01-24 08:37:59.167476: step: 788/529, loss: 0.007085789460688829
2023-01-24 08:38:00.231207: step: 792/529, loss: 0.004392254166305065
2023-01-24 08:38:01.301702: step: 796/529, loss: 0.005781763698905706
2023-01-24 08:38:02.368711: step: 800/529, loss: 0.003665948286652565
2023-01-24 08:38:03.445701: step: 804/529, loss: 0.00012799628893844783
2023-01-24 08:38:04.512919: step: 808/529, loss: 0.010023016482591629
2023-01-24 08:38:05.585504: step: 812/529, loss: 0.0021820273250341415
2023-01-24 08:38:06.668834: step: 816/529, loss: 0.009777463972568512
2023-01-24 08:38:07.733608: step: 820/529, loss: 0.010205371305346489
2023-01-24 08:38:08.790078: step: 824/529, loss: 2.6652109227143228e-05
2023-01-24 08:38:09.869835: step: 828/529, loss: 0.003344296244904399
2023-01-24 08:38:10.945438: step: 832/529, loss: 0.004322676919400692
2023-01-24 08:38:12.024942: step: 836/529, loss: 0.00082737288903445
2023-01-24 08:38:13.111525: step: 840/529, loss: 0.002806248376145959
2023-01-24 08:38:14.177074: step: 844/529, loss: 0.0003043327888008207
2023-01-24 08:38:15.250524: step: 848/529, loss: 2.696049341466278e-05
2023-01-24 08:38:16.318777: step: 852/529, loss: 0.0008913210476748645
2023-01-24 08:38:17.386843: step: 856/529, loss: 0.0047568706795573235
2023-01-24 08:38:18.463968: step: 860/529, loss: 0.0006697503849864006
2023-01-24 08:38:19.535822: step: 864/529, loss: 0.0017113873036578298
2023-01-24 08:38:20.603350: step: 868/529, loss: 0.0037341443821787834
2023-01-24 08:38:21.686358: step: 872/529, loss: 0.005166519898921251
2023-01-24 08:38:22.755229: step: 876/529, loss: 0.006426224019378424
2023-01-24 08:38:23.821770: step: 880/529, loss: 0.0006184052326716483
2023-01-24 08:38:24.888030: step: 884/529, loss: 0.003161293687298894
2023-01-24 08:38:25.951474: step: 888/529, loss: 0.010034614242613316
2023-01-24 08:38:27.002979: step: 892/529, loss: 0.026789799332618713
2023-01-24 08:38:28.086416: step: 896/529, loss: 0.001929200254380703
2023-01-24 08:38:29.158966: step: 900/529, loss: 0.0145545220002532
2023-01-24 08:38:30.237397: step: 904/529, loss: 0.0032731760293245316
2023-01-24 08:38:31.314654: step: 908/529, loss: 0.0053643579594790936
2023-01-24 08:38:32.386427: step: 912/529, loss: 0.00484539195895195
2023-01-24 08:38:33.458428: step: 916/529, loss: 0.006907839793711901
2023-01-24 08:38:34.527325: step: 920/529, loss: 3.603533696150407e-05
2023-01-24 08:38:35.604047: step: 924/529, loss: 0.009192566387355328
2023-01-24 08:38:36.674846: step: 928/529, loss: 0.006187533028423786
2023-01-24 08:38:37.746322: step: 932/529, loss: 0.0001257225958397612
2023-01-24 08:38:38.816591: step: 936/529, loss: 0.010146988555788994
2023-01-24 08:38:39.873769: step: 940/529, loss: 0.02705325372517109
2023-01-24 08:38:40.959903: step: 944/529, loss: 0.04710602015256882
2023-01-24 08:38:42.028942: step: 948/529, loss: 0.0009438158595003188
2023-01-24 08:38:43.129635: step: 952/529, loss: 0.004957647528499365
2023-01-24 08:38:44.198085: step: 956/529, loss: 0.003248073160648346
2023-01-24 08:38:45.263256: step: 960/529, loss: 0.0031586489640176296
2023-01-24 08:38:46.350673: step: 964/529, loss: 0.006837042514234781
2023-01-24 08:38:47.427951: step: 968/529, loss: 0.0024759764783084393
2023-01-24 08:38:48.500895: step: 972/529, loss: 0.002118160715326667
2023-01-24 08:38:49.580437: step: 976/529, loss: 0.002055953722447157
2023-01-24 08:38:50.670075: step: 980/529, loss: 0.004124574363231659
2023-01-24 08:38:51.749344: step: 984/529, loss: 0.016004513949155807
2023-01-24 08:38:52.821289: step: 988/529, loss: 0.003560491371899843
2023-01-24 08:38:53.912701: step: 992/529, loss: 0.005313785281032324
2023-01-24 08:38:54.976291: step: 996/529, loss: 0.0032371787820011377
2023-01-24 08:38:56.038536: step: 1000/529, loss: 1.7462771211285144e-05
2023-01-24 08:38:57.111302: step: 1004/529, loss: 0.0001582477561896667
2023-01-24 08:38:58.176069: step: 1008/529, loss: 0.0023180777207016945
2023-01-24 08:38:59.266653: step: 1012/529, loss: 0.001344939460977912
2023-01-24 08:39:00.326281: step: 1016/529, loss: 0.0004612569173332304
2023-01-24 08:39:01.408568: step: 1020/529, loss: 0.0031566154211759567
2023-01-24 08:39:02.496921: step: 1024/529, loss: 0.00035195861710235476
2023-01-24 08:39:03.565775: step: 1028/529, loss: 0.008639510720968246
2023-01-24 08:39:04.647294: step: 1032/529, loss: 0.00013106749975122511
2023-01-24 08:39:05.722136: step: 1036/529, loss: 0.0049845874309539795
2023-01-24 08:39:06.770232: step: 1040/529, loss: 0.00024464441230520606
2023-01-24 08:39:07.839718: step: 1044/529, loss: 0.008739300072193146
2023-01-24 08:39:08.917613: step: 1048/529, loss: 0.00521880853921175
2023-01-24 08:39:09.986168: step: 1052/529, loss: 0.0008859842200763524
2023-01-24 08:39:11.066773: step: 1056/529, loss: 0.009324532002210617
2023-01-24 08:39:12.147465: step: 1060/529, loss: 0.023509660735726357
2023-01-24 08:39:13.224120: step: 1064/529, loss: 0.010008524172008038
2023-01-24 08:39:14.287842: step: 1068/529, loss: 1.1678504961309955e-05
2023-01-24 08:39:15.360685: step: 1072/529, loss: 0.002534510102123022
2023-01-24 08:39:16.430117: step: 1076/529, loss: 0.00048508241889066994
2023-01-24 08:39:17.504748: step: 1080/529, loss: 0.00174156844150275
2023-01-24 08:39:18.572163: step: 1084/529, loss: 0.007203032728284597
2023-01-24 08:39:19.641459: step: 1088/529, loss: 0.0008048833697102964
2023-01-24 08:39:20.698847: step: 1092/529, loss: 0.0001464414526708424
2023-01-24 08:39:21.754359: step: 1096/529, loss: 0.003558980068191886
2023-01-24 08:39:22.815007: step: 1100/529, loss: 0.0011085179867222905
2023-01-24 08:39:23.874877: step: 1104/529, loss: 0.0015488055068999529
2023-01-24 08:39:24.934567: step: 1108/529, loss: 0.0027339491061866283
2023-01-24 08:39:26.013189: step: 1112/529, loss: 0.004658680874854326
2023-01-24 08:39:27.081779: step: 1116/529, loss: 0.004505416844040155
2023-01-24 08:39:28.151196: step: 1120/529, loss: 0.007795459590852261
2023-01-24 08:39:29.225572: step: 1124/529, loss: 0.0011100741103291512
2023-01-24 08:39:30.297365: step: 1128/529, loss: 0.0011100699193775654
2023-01-24 08:39:31.372546: step: 1132/529, loss: 0.0006393307121470571
2023-01-24 08:39:32.462854: step: 1136/529, loss: 0.01404570508748293
2023-01-24 08:39:33.538453: step: 1140/529, loss: 0.005572729744017124
2023-01-24 08:39:34.654033: step: 1144/529, loss: 0.006868306081742048
2023-01-24 08:39:35.733991: step: 1148/529, loss: 0.003913376480340958
2023-01-24 08:39:36.802561: step: 1152/529, loss: 0.004049277398735285
2023-01-24 08:39:37.872353: step: 1156/529, loss: 6.321066757664084e-05
2023-01-24 08:39:38.938816: step: 1160/529, loss: 0.0626671090722084
2023-01-24 08:39:40.015655: step: 1164/529, loss: 0.0026410934515297413
2023-01-24 08:39:41.078159: step: 1168/529, loss: 0.000755573040805757
2023-01-24 08:39:42.160954: step: 1172/529, loss: 0.0007078420021571219
2023-01-24 08:39:43.225117: step: 1176/529, loss: 0.000758122478146106
2023-01-24 08:39:44.305152: step: 1180/529, loss: 0.0005499935941770673
2023-01-24 08:39:45.393940: step: 1184/529, loss: 0.004979957826435566
2023-01-24 08:39:46.467496: step: 1188/529, loss: 0.004975061397999525
2023-01-24 08:39:47.534820: step: 1192/529, loss: 0.0061318762600421906
2023-01-24 08:39:48.599420: step: 1196/529, loss: 6.094748187024379e-06
2023-01-24 08:39:49.672050: step: 1200/529, loss: 0.008106323890388012
2023-01-24 08:39:50.738211: step: 1204/529, loss: 0.0008714957511983812
2023-01-24 08:39:51.822088: step: 1208/529, loss: 0.006702861282974482
2023-01-24 08:39:52.885688: step: 1212/529, loss: 0.0015920302830636501
2023-01-24 08:39:53.965741: step: 1216/529, loss: 0.0017727756639942527
2023-01-24 08:39:55.034126: step: 1220/529, loss: 0.004820380825549364
2023-01-24 08:39:56.116064: step: 1224/529, loss: 0.012969250790774822
2023-01-24 08:39:57.192944: step: 1228/529, loss: 0.004003622569143772
2023-01-24 08:39:58.260953: step: 1232/529, loss: 0.0011055308859795332
2023-01-24 08:39:59.323104: step: 1236/529, loss: 0.005733616184443235
2023-01-24 08:40:00.402889: step: 1240/529, loss: 0.00570191815495491
2023-01-24 08:40:01.488871: step: 1244/529, loss: 2.457704431435559e-05
2023-01-24 08:40:02.552096: step: 1248/529, loss: 0.00041102274553850293
2023-01-24 08:40:03.630703: step: 1252/529, loss: 0.0031053186394274235
2023-01-24 08:40:04.701256: step: 1256/529, loss: 0.012733005918562412
2023-01-24 08:40:05.780489: step: 1260/529, loss: 0.007202472072094679
2023-01-24 08:40:06.847781: step: 1264/529, loss: 0.004870354663580656
2023-01-24 08:40:07.928399: step: 1268/529, loss: 0.0022922626230865717
2023-01-24 08:40:08.997455: step: 1272/529, loss: 0.001979152439162135
2023-01-24 08:40:10.054095: step: 1276/529, loss: 0.010340387932956219
2023-01-24 08:40:11.129747: step: 1280/529, loss: 0.00019813135440927
2023-01-24 08:40:12.177189: step: 1284/529, loss: 0.009121579118072987
2023-01-24 08:40:13.269551: step: 1288/529, loss: 0.0026397088076919317
2023-01-24 08:40:14.345039: step: 1292/529, loss: 0.004600172862410545
2023-01-24 08:40:15.415276: step: 1296/529, loss: 2.715624577831477e-05
2023-01-24 08:40:16.498702: step: 1300/529, loss: 0.002242723712697625
2023-01-24 08:40:17.578474: step: 1304/529, loss: 0.02446291781961918
2023-01-24 08:40:18.643849: step: 1308/529, loss: 0.009032251313328743
2023-01-24 08:40:19.710062: step: 1312/529, loss: 0.007352314889431
2023-01-24 08:40:20.778539: step: 1316/529, loss: 0.0048003834672272205
2023-01-24 08:40:21.841111: step: 1320/529, loss: 0.019572388380765915
2023-01-24 08:40:22.917572: step: 1324/529, loss: 0.003064745804294944
2023-01-24 08:40:24.012816: step: 1328/529, loss: 0.0036644909996539354
2023-01-24 08:40:25.078243: step: 1332/529, loss: 0.012914334423840046
2023-01-24 08:40:26.150584: step: 1336/529, loss: 0.004564644303172827
2023-01-24 08:40:27.231976: step: 1340/529, loss: 0.0030346137937158346
2023-01-24 08:40:28.312011: step: 1344/529, loss: 0.0035736700519919395
2023-01-24 08:40:29.387955: step: 1348/529, loss: 0.006541269365698099
2023-01-24 08:40:30.438336: step: 1352/529, loss: 0.004591689445078373
2023-01-24 08:40:31.541440: step: 1356/529, loss: 0.024633893743157387
2023-01-24 08:40:32.613468: step: 1360/529, loss: 0.005393498111516237
2023-01-24 08:40:33.676999: step: 1364/529, loss: 0.010563160292804241
2023-01-24 08:40:34.748575: step: 1368/529, loss: 0.002505565993487835
2023-01-24 08:40:35.825561: step: 1372/529, loss: 0.000835604325402528
2023-01-24 08:40:36.899244: step: 1376/529, loss: 0.010811658576130867
2023-01-24 08:40:38.008459: step: 1380/529, loss: 0.008302316069602966
2023-01-24 08:40:39.069945: step: 1384/529, loss: 0.00036046322202309966
2023-01-24 08:40:40.136586: step: 1388/529, loss: 0.012536582536995411
2023-01-24 08:40:41.215122: step: 1392/529, loss: 0.005242150742560625
2023-01-24 08:40:42.277594: step: 1396/529, loss: 0.0044818841852247715
2023-01-24 08:40:43.375915: step: 1400/529, loss: 0.0029626083560287952
2023-01-24 08:40:44.440485: step: 1404/529, loss: 0.0069379303604364395
2023-01-24 08:40:45.518590: step: 1408/529, loss: 0.0056917727924883366
2023-01-24 08:40:46.602677: step: 1412/529, loss: 0.001560179516673088
2023-01-24 08:40:47.681846: step: 1416/529, loss: 0.0012899324065074325
2023-01-24 08:40:48.762780: step: 1420/529, loss: 0.0008623880567029119
2023-01-24 08:40:49.833169: step: 1424/529, loss: 0.005058376584202051
2023-01-24 08:40:50.898610: step: 1428/529, loss: 0.01329648494720459
2023-01-24 08:40:51.969326: step: 1432/529, loss: 0.0003696754574775696
2023-01-24 08:40:53.047196: step: 1436/529, loss: 0.0007314187241718173
2023-01-24 08:40:54.128204: step: 1440/529, loss: 0.0035408358089625835
2023-01-24 08:40:55.192411: step: 1444/529, loss: 0.0004966481938026845
2023-01-24 08:40:56.268504: step: 1448/529, loss: 0.005022390745580196
2023-01-24 08:40:57.334878: step: 1452/529, loss: 0.00841954629868269
2023-01-24 08:40:58.407733: step: 1456/529, loss: 0.0026678030844777822
2023-01-24 08:40:59.470475: step: 1460/529, loss: 0.0010666601592674851
2023-01-24 08:41:00.539737: step: 1464/529, loss: 0.0027653449214994907
2023-01-24 08:41:01.599576: step: 1468/529, loss: 0.005911482032388449
2023-01-24 08:41:02.665712: step: 1472/529, loss: 0.009020921774208546
2023-01-24 08:41:03.747513: step: 1476/529, loss: 0.0007216590456664562
2023-01-24 08:41:04.817357: step: 1480/529, loss: 0.0006418696139007807
2023-01-24 08:41:05.908944: step: 1484/529, loss: 0.0011347413528710604
2023-01-24 08:41:06.972300: step: 1488/529, loss: 0.004619520623236895
2023-01-24 08:41:08.059862: step: 1492/529, loss: 0.002761669224128127
2023-01-24 08:41:09.149909: step: 1496/529, loss: 0.0015018106205388904
2023-01-24 08:41:10.227343: step: 1500/529, loss: 0.0011983702424913645
2023-01-24 08:41:11.306744: step: 1504/529, loss: 3.712824036483653e-05
2023-01-24 08:41:12.397513: step: 1508/529, loss: 0.003035917179659009
2023-01-24 08:41:13.480905: step: 1512/529, loss: 0.002935249824076891
2023-01-24 08:41:14.567585: step: 1516/529, loss: 0.0005018645315431058
2023-01-24 08:41:15.633256: step: 1520/529, loss: 7.516053301515058e-05
2023-01-24 08:41:16.712563: step: 1524/529, loss: 0.0006252499297261238
2023-01-24 08:41:17.791556: step: 1528/529, loss: 0.00021914085664320737
2023-01-24 08:41:18.867882: step: 1532/529, loss: 0.00035210527130402625
2023-01-24 08:41:19.931426: step: 1536/529, loss: 0.0049569010734558105
2023-01-24 08:41:21.006903: step: 1540/529, loss: 0.0005235927528701723
2023-01-24 08:41:22.079983: step: 1544/529, loss: 0.0026279399171471596
2023-01-24 08:41:23.157362: step: 1548/529, loss: 0.00324541749432683
2023-01-24 08:41:24.219218: step: 1552/529, loss: 0.009012006223201752
2023-01-24 08:41:25.286369: step: 1556/529, loss: 0.0006068104994483292
2023-01-24 08:41:26.366124: step: 1560/529, loss: 0.0016141320811584592
2023-01-24 08:41:27.421172: step: 1564/529, loss: 0.00028360760188661516
2023-01-24 08:41:28.506591: step: 1568/529, loss: 0.003278398420661688
2023-01-24 08:41:29.567517: step: 1572/529, loss: 0.0009010664070956409
2023-01-24 08:41:30.638768: step: 1576/529, loss: 0.002551017329096794
2023-01-24 08:41:31.722230: step: 1580/529, loss: 0.0016217385418713093
2023-01-24 08:41:32.799003: step: 1584/529, loss: 0.0015589940594509244
2023-01-24 08:41:33.871195: step: 1588/529, loss: 0.0013086016988381743
2023-01-24 08:41:34.944683: step: 1592/529, loss: 0.013980780728161335
2023-01-24 08:41:36.021095: step: 1596/529, loss: 0.02320174314081669
2023-01-24 08:41:37.110783: step: 1600/529, loss: 0.0044688149355351925
2023-01-24 08:41:38.195629: step: 1604/529, loss: 0.03884219005703926
2023-01-24 08:41:39.256205: step: 1608/529, loss: 9.968772246793378e-06
2023-01-24 08:41:40.324951: step: 1612/529, loss: 0.003088307799771428
2023-01-24 08:41:41.395419: step: 1616/529, loss: 0.0023602466098964214
2023-01-24 08:41:42.476633: step: 1620/529, loss: 0.006536624860018492
2023-01-24 08:41:43.566731: step: 1624/529, loss: 0.0
2023-01-24 08:41:44.657554: step: 1628/529, loss: 0.003033406799659133
2023-01-24 08:41:45.719044: step: 1632/529, loss: 0.0013596320059150457
2023-01-24 08:41:46.783882: step: 1636/529, loss: 0.0023997037205845118
2023-01-24 08:41:47.864246: step: 1640/529, loss: 0.003005336970090866
2023-01-24 08:41:48.932456: step: 1644/529, loss: 0.002092453185468912
2023-01-24 08:41:49.993542: step: 1648/529, loss: 0.000312409974867478
2023-01-24 08:41:51.075571: step: 1652/529, loss: 0.0041015553288161755
2023-01-24 08:41:52.149086: step: 1656/529, loss: 0.0017991220811381936
2023-01-24 08:41:53.223386: step: 1660/529, loss: 0.0019315526587888598
2023-01-24 08:41:54.350348: step: 1664/529, loss: 0.004510460887104273
2023-01-24 08:41:55.424277: step: 1668/529, loss: 0.005529333371669054
2023-01-24 08:41:56.492858: step: 1672/529, loss: 0.003165849018841982
2023-01-24 08:41:57.565982: step: 1676/529, loss: 0.0006393567891791463
2023-01-24 08:41:58.635589: step: 1680/529, loss: 0.0023484984412789345
2023-01-24 08:41:59.686684: step: 1684/529, loss: 0.0003511063405312598
2023-01-24 08:42:00.762646: step: 1688/529, loss: 0.00018169709073845297
2023-01-24 08:42:01.815083: step: 1692/529, loss: 0.00715620955452323
2023-01-24 08:42:02.877568: step: 1696/529, loss: 8.939039253164083e-05
2023-01-24 08:42:03.942249: step: 1700/529, loss: 0.0057845208793878555
2023-01-24 08:42:05.012032: step: 1704/529, loss: 0.0036745222751051188
2023-01-24 08:42:06.108587: step: 1708/529, loss: 0.0041084326803684235
2023-01-24 08:42:07.186560: step: 1712/529, loss: 0.005269292276352644
2023-01-24 08:42:08.246351: step: 1716/529, loss: 0.003057217225432396
2023-01-24 08:42:09.335957: step: 1720/529, loss: 0.00042299754568375647
2023-01-24 08:42:10.390530: step: 1724/529, loss: 0.0015383093850687146
2023-01-24 08:42:11.480665: step: 1728/529, loss: 0.0008272006525658071
2023-01-24 08:42:12.549924: step: 1732/529, loss: 0.00575598469004035
2023-01-24 08:42:13.621335: step: 1736/529, loss: 0.000451031606644392
2023-01-24 08:42:14.699997: step: 1740/529, loss: 0.00012466817861422896
2023-01-24 08:42:15.778067: step: 1744/529, loss: 0.0038290719967335463
2023-01-24 08:42:16.855090: step: 1748/529, loss: 0.011712432838976383
2023-01-24 08:42:17.919362: step: 1752/529, loss: 2.7688449335983023e-05
2023-01-24 08:42:18.991145: step: 1756/529, loss: 0.0015026670880615711
2023-01-24 08:42:20.068165: step: 1760/529, loss: 0.003128649899736047
2023-01-24 08:42:21.136609: step: 1764/529, loss: 0.0017477100482210517
2023-01-24 08:42:22.210483: step: 1768/529, loss: 0.006452275440096855
2023-01-24 08:42:23.279329: step: 1772/529, loss: 0.0018919184803962708
2023-01-24 08:42:24.346765: step: 1776/529, loss: 0.001168661518022418
2023-01-24 08:42:25.416510: step: 1780/529, loss: 0.0013780271401628852
2023-01-24 08:42:26.518906: step: 1784/529, loss: 0.0091183390468359
2023-01-24 08:42:27.598379: step: 1788/529, loss: 0.0010438120225444436
2023-01-24 08:42:28.659195: step: 1792/529, loss: 0.002068291185423732
2023-01-24 08:42:29.729131: step: 1796/529, loss: 0.0006684469408355653
2023-01-24 08:42:30.788433: step: 1800/529, loss: 0.006883364636451006
2023-01-24 08:42:31.841676: step: 1804/529, loss: 6.186648533912376e-05
2023-01-24 08:42:32.921785: step: 1808/529, loss: 0.0005298329633660614
2023-01-24 08:42:33.983304: step: 1812/529, loss: 0.0002774820604827255
2023-01-24 08:42:35.067425: step: 1816/529, loss: 0.0002061830018647015
2023-01-24 08:42:36.131891: step: 1820/529, loss: 4.0665730921318755e-05
2023-01-24 08:42:37.195654: step: 1824/529, loss: 0.0008008748409338295
2023-01-24 08:42:38.271756: step: 1828/529, loss: 3.203128289896995e-05
2023-01-24 08:42:39.342654: step: 1832/529, loss: 0.004102792590856552
2023-01-24 08:42:40.423589: step: 1836/529, loss: 0.0005983141018077731
2023-01-24 08:42:41.482949: step: 1840/529, loss: 9.179474000120535e-05
2023-01-24 08:42:42.559864: step: 1844/529, loss: 0.002192548243328929
2023-01-24 08:42:43.642677: step: 1848/529, loss: 0.0021154964342713356
2023-01-24 08:42:44.710195: step: 1852/529, loss: 0.004692483227699995
2023-01-24 08:42:45.795872: step: 1856/529, loss: 0.002063579158857465
2023-01-24 08:42:46.877277: step: 1860/529, loss: 0.0034239974338561296
2023-01-24 08:42:47.966208: step: 1864/529, loss: 0.0017422258388251066
2023-01-24 08:42:49.038002: step: 1868/529, loss: 6.844824383733794e-06
2023-01-24 08:42:50.118934: step: 1872/529, loss: 3.4428646813466912e-06
2023-01-24 08:42:51.188360: step: 1876/529, loss: 0.0005339368362911046
2023-01-24 08:42:52.256951: step: 1880/529, loss: 0.010746901854872704
2023-01-24 08:42:53.324036: step: 1884/529, loss: 0.0029423637315630913
2023-01-24 08:42:54.395046: step: 1888/529, loss: 0.012396391481161118
2023-01-24 08:42:55.460242: step: 1892/529, loss: 2.0159728592261672e-05
2023-01-24 08:42:56.542559: step: 1896/529, loss: 0.0009077794966287911
2023-01-24 08:42:57.629680: step: 1900/529, loss: 0.00228919368237257
2023-01-24 08:42:58.699827: step: 1904/529, loss: 0.0007247887551784515
2023-01-24 08:42:59.767097: step: 1908/529, loss: 0.0069438316859304905
2023-01-24 08:43:00.830889: step: 1912/529, loss: 0.004304738715291023
2023-01-24 08:43:01.911777: step: 1916/529, loss: 0.0035784002393484116
2023-01-24 08:43:02.993845: step: 1920/529, loss: 0.011989950202405453
2023-01-24 08:43:04.065244: step: 1924/529, loss: 0.0019601411186158657
2023-01-24 08:43:05.148178: step: 1928/529, loss: 0.0013878459576517344
2023-01-24 08:43:06.216128: step: 1932/529, loss: 0.002206981647759676
2023-01-24 08:43:07.271796: step: 1936/529, loss: 2.1091598227940267e-06
2023-01-24 08:43:08.334411: step: 1940/529, loss: 0.0016788952052593231
2023-01-24 08:43:09.422232: step: 1944/529, loss: 0.018700117245316505
2023-01-24 08:43:10.500319: step: 1948/529, loss: 0.00289915781468153
2023-01-24 08:43:11.571934: step: 1952/529, loss: 0.006917925551533699
2023-01-24 08:43:12.651253: step: 1956/529, loss: 0.0002779752539936453
2023-01-24 08:43:13.726702: step: 1960/529, loss: 0.0005320819327607751
2023-01-24 08:43:14.802701: step: 1964/529, loss: 0.0
2023-01-24 08:43:15.881155: step: 1968/529, loss: 0.003783997381106019
2023-01-24 08:43:16.965894: step: 1972/529, loss: 0.008835915476083755
2023-01-24 08:43:18.031627: step: 1976/529, loss: 0.00048177296412177384
2023-01-24 08:43:19.103525: step: 1980/529, loss: 0.0069314478896558285
2023-01-24 08:43:20.164181: step: 1984/529, loss: 0.003239867277443409
2023-01-24 08:43:21.236607: step: 1988/529, loss: 0.0015226966934278607
2023-01-24 08:43:22.330753: step: 1992/529, loss: 0.0015954652335494757
2023-01-24 08:43:23.411281: step: 1996/529, loss: 0.0003833039663732052
2023-01-24 08:43:24.485259: step: 2000/529, loss: 0.0002944319858215749
2023-01-24 08:43:25.553640: step: 2004/529, loss: 0.005284524522721767
2023-01-24 08:43:26.628755: step: 2008/529, loss: 0.005018971860408783
2023-01-24 08:43:27.710556: step: 2012/529, loss: 0.0023734390269964933
2023-01-24 08:43:28.785553: step: 2016/529, loss: 0.0006474965484812856
2023-01-24 08:43:29.856575: step: 2020/529, loss: 0.0018509947694838047
2023-01-24 08:43:30.934399: step: 2024/529, loss: 0.008611795492470264
2023-01-24 08:43:32.006451: step: 2028/529, loss: 0.011392266489565372
2023-01-24 08:43:33.073565: step: 2032/529, loss: 0.00043303260463289917
2023-01-24 08:43:34.161671: step: 2036/529, loss: 4.455868838704191e-05
2023-01-24 08:43:35.239171: step: 2040/529, loss: 0.0022229517344385386
2023-01-24 08:43:36.337970: step: 2044/529, loss: 0.003587716957554221
2023-01-24 08:43:37.425238: step: 2048/529, loss: 0.004381757695227861
2023-01-24 08:43:38.511412: step: 2052/529, loss: 0.0020230996888130903
2023-01-24 08:43:39.603471: step: 2056/529, loss: 0.0034694720525294542
2023-01-24 08:43:40.687324: step: 2060/529, loss: 0.003932279068976641
2023-01-24 08:43:41.770444: step: 2064/529, loss: 0.0020144081208854914
2023-01-24 08:43:42.888033: step: 2068/529, loss: 0.0013614704366773367
2023-01-24 08:43:43.946577: step: 2072/529, loss: 0.004141340497881174
2023-01-24 08:43:45.022711: step: 2076/529, loss: 0.0019316418329253793
2023-01-24 08:43:46.101464: step: 2080/529, loss: 0.0006597943720407784
2023-01-24 08:43:47.176878: step: 2084/529, loss: 0.006309060379862785
2023-01-24 08:43:48.266835: step: 2088/529, loss: 0.0016341398004442453
2023-01-24 08:43:49.372430: step: 2092/529, loss: 0.006675537209957838
2023-01-24 08:43:50.456214: step: 2096/529, loss: 0.0009607902029529214
2023-01-24 08:43:51.543496: step: 2100/529, loss: 0.0047721462324261665
2023-01-24 08:43:52.620059: step: 2104/529, loss: 0.031034506857395172
2023-01-24 08:43:53.679295: step: 2108/529, loss: 0.0018453217344358563
2023-01-24 08:43:54.760544: step: 2112/529, loss: 0.011940338648855686
2023-01-24 08:43:55.838495: step: 2116/529, loss: 0.0018543225014582276
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3376191750790252, 'r': 0.29918055932050247, 'f1': 0.3172397480118809}, 'combined': 0.233755603798228, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33072460612142773, 'r': 0.29120787928706593, 'f1': 0.30971082371879544}, 'combined': 0.2021946310288509, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3581648417960798, 'r': 0.354087063711115, 'f1': 0.35611427972472826}, 'combined': 0.26239999558664184, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35893338836481453, 'r': 0.31472651884194214, 'f1': 0.3353794833496896}, 'combined': 0.21895240881896832, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3800451982228298, 'r': 0.342545482269154, 'f1': 0.36032229372423985}, 'combined': 0.2655006374810188, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3651932004846004, 'r': 0.3018125623839673, 'f1': 0.3304915841489597}, 'combined': 0.21576134509206693, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3620689655172414, 'r': 0.45652173913043476, 'f1': 0.4038461538461538}, 'combined': 0.2019230769230769, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580872292314783, 'r': 0.3574077468230694, 'f1': 0.3577471653860543}, 'combined': 0.2636031744949873, 'stategy': 1, 'epoch': 11}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36065178272254766, 'r': 0.3165647541360598, 'f1': 0.3371732280959697}, 'combined': 0.2201234546118766, 'stategy': 1, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:46:27.014542: step: 4/529, loss: 0.0014406029367819428
2023-01-24 08:46:28.072438: step: 8/529, loss: 0.0005166666815057397
2023-01-24 08:46:29.143559: step: 12/529, loss: 0.0055794198997318745
2023-01-24 08:46:30.222557: step: 16/529, loss: 0.0024013204965740442
2023-01-24 08:46:31.287997: step: 20/529, loss: 0.0009924215264618397
2023-01-24 08:46:32.363251: step: 24/529, loss: 0.052919644862413406
2023-01-24 08:46:33.447074: step: 28/529, loss: 0.0010007554665207863
2023-01-24 08:46:34.504438: step: 32/529, loss: 0.0035555881913751364
2023-01-24 08:46:35.572620: step: 36/529, loss: 0.00017612775263842195
2023-01-24 08:46:36.640951: step: 40/529, loss: 0.0013773787068203092
2023-01-24 08:46:37.711039: step: 44/529, loss: 0.00011239123705308884
2023-01-24 08:46:38.783074: step: 48/529, loss: 0.0119791179895401
2023-01-24 08:46:39.872148: step: 52/529, loss: 0.0032426011748611927
2023-01-24 08:46:40.938704: step: 56/529, loss: 0.0023406182881444693
2023-01-24 08:46:42.010545: step: 60/529, loss: 0.0007079282077029347
2023-01-24 08:46:43.093484: step: 64/529, loss: 0.029164807870984077
2023-01-24 08:46:44.158901: step: 68/529, loss: 0.006156122777611017
2023-01-24 08:46:45.233653: step: 72/529, loss: 0.0028103936929255724
2023-01-24 08:46:46.291213: step: 76/529, loss: 0.0008448417065665126
2023-01-24 08:46:47.364387: step: 80/529, loss: 0.006331016309559345
2023-01-24 08:46:48.432136: step: 84/529, loss: 0.0013154357438907027
2023-01-24 08:46:49.510298: step: 88/529, loss: 0.003233660012483597
2023-01-24 08:46:50.592407: step: 92/529, loss: 0.004117619711905718
2023-01-24 08:46:51.655817: step: 96/529, loss: 0.00036356100463308394
2023-01-24 08:46:52.740141: step: 100/529, loss: 0.0028379629366099834
2023-01-24 08:46:53.824724: step: 104/529, loss: 0.007633896078914404
2023-01-24 08:46:54.905488: step: 108/529, loss: 0.0003820745041593909
2023-01-24 08:46:55.986361: step: 112/529, loss: 0.0018571915570646524
2023-01-24 08:46:57.069144: step: 116/529, loss: 0.004072810057550669
2023-01-24 08:46:58.138436: step: 120/529, loss: 0.004594247322529554
2023-01-24 08:46:59.222409: step: 124/529, loss: 0.0029200438875705004
2023-01-24 08:47:00.294417: step: 128/529, loss: 0.0008496983209624887
2023-01-24 08:47:01.363395: step: 132/529, loss: 0.001706223003566265
2023-01-24 08:47:02.463572: step: 136/529, loss: 0.00247276877053082
2023-01-24 08:47:03.544311: step: 140/529, loss: 0.004223995376378298
2023-01-24 08:47:04.607224: step: 144/529, loss: 0.004998901393264532
2023-01-24 08:47:05.668828: step: 148/529, loss: 0.0010829686652868986
2023-01-24 08:47:06.740318: step: 152/529, loss: 0.004460414871573448
2023-01-24 08:47:07.828093: step: 156/529, loss: 0.00247690686956048
2023-01-24 08:47:08.902274: step: 160/529, loss: 0.0006109255482442677
2023-01-24 08:47:09.961682: step: 164/529, loss: 1.267790503334254e-05
2023-01-24 08:47:11.031344: step: 168/529, loss: 0.0027858333196491003
2023-01-24 08:47:12.121398: step: 172/529, loss: 0.005347960162907839
2023-01-24 08:47:13.205419: step: 176/529, loss: 0.0011582892620936036
2023-01-24 08:47:14.275865: step: 180/529, loss: 8.794327004579827e-05
2023-01-24 08:47:15.335673: step: 184/529, loss: 0.00025748019106686115
2023-01-24 08:47:16.403487: step: 188/529, loss: 1.555074231873732e-05
2023-01-24 08:47:17.466801: step: 192/529, loss: 0.0011577480472624302
2023-01-24 08:47:18.540725: step: 196/529, loss: 0.0011529306648299098
2023-01-24 08:47:19.616471: step: 200/529, loss: 0.0032238292042165995
2023-01-24 08:47:20.693893: step: 204/529, loss: 0.015989812090992928
2023-01-24 08:47:21.770870: step: 208/529, loss: 0.008752340450882912
2023-01-24 08:47:22.854091: step: 212/529, loss: 0.008068365044891834
2023-01-24 08:47:23.946676: step: 216/529, loss: 0.0016642805421724916
2023-01-24 08:47:25.010973: step: 220/529, loss: 0.0010034673614427447
2023-01-24 08:47:26.081958: step: 224/529, loss: 0.004248702432960272
2023-01-24 08:47:27.161762: step: 228/529, loss: 0.006841846741735935
2023-01-24 08:47:28.232625: step: 232/529, loss: 0.0008880904060788453
2023-01-24 08:47:29.302882: step: 236/529, loss: 0.0002831376332323998
2023-01-24 08:47:30.398420: step: 240/529, loss: 0.002143791178241372
2023-01-24 08:47:31.456770: step: 244/529, loss: 0.0009778562234714627
2023-01-24 08:47:32.521275: step: 248/529, loss: 0.00015718958457000554
2023-01-24 08:47:33.593087: step: 252/529, loss: 0.0006788586033508182
2023-01-24 08:47:34.665795: step: 256/529, loss: 0.0001369896490359679
2023-01-24 08:47:35.749499: step: 260/529, loss: 0.006800807546824217
2023-01-24 08:47:36.803931: step: 264/529, loss: 0.002131674438714981
2023-01-24 08:47:37.884148: step: 268/529, loss: 0.012378649786114693
2023-01-24 08:47:38.947421: step: 272/529, loss: 0.005594603717327118
2023-01-24 08:47:40.016807: step: 276/529, loss: 1.4710850564370048e-06
2023-01-24 08:47:41.117858: step: 280/529, loss: 0.00035618359106592834
2023-01-24 08:47:42.199604: step: 284/529, loss: 0.002371045295149088
2023-01-24 08:47:43.259231: step: 288/529, loss: 0.0014916997170075774
2023-01-24 08:47:44.334358: step: 292/529, loss: 0.003098335349932313
2023-01-24 08:47:45.399542: step: 296/529, loss: 0.0009281517122872174
2023-01-24 08:47:46.495098: step: 300/529, loss: 0.0231844000518322
2023-01-24 08:47:47.576816: step: 304/529, loss: 0.0037730697076767683
2023-01-24 08:47:48.650241: step: 308/529, loss: 0.0038550340104848146
2023-01-24 08:47:49.726224: step: 312/529, loss: 0.003156480845063925
2023-01-24 08:47:50.797026: step: 316/529, loss: 0.009825780056416988
2023-01-24 08:47:51.874850: step: 320/529, loss: 0.0002331018476979807
2023-01-24 08:47:52.938913: step: 324/529, loss: 1.4097027815296315e-05
2023-01-24 08:47:54.019776: step: 328/529, loss: 0.0008861885871738195
2023-01-24 08:47:55.083981: step: 332/529, loss: 0.0016851425170898438
2023-01-24 08:47:56.167809: step: 336/529, loss: 0.0005363310337997973
2023-01-24 08:47:57.234449: step: 340/529, loss: 0.0007374809356406331
2023-01-24 08:47:58.332311: step: 344/529, loss: 0.0009122372139245272
2023-01-24 08:47:59.401149: step: 348/529, loss: 0.0001343362091574818
2023-01-24 08:48:00.489952: step: 352/529, loss: 0.0014942878624424338
2023-01-24 08:48:01.570174: step: 356/529, loss: 4.1831168346107006e-05
2023-01-24 08:48:02.637461: step: 360/529, loss: 0.0076486216858029366
2023-01-24 08:48:03.716114: step: 364/529, loss: 0.0057144626043736935
2023-01-24 08:48:04.788399: step: 368/529, loss: 0.0014407701091840863
2023-01-24 08:48:05.858921: step: 372/529, loss: 0.004227327182888985
2023-01-24 08:48:06.946659: step: 376/529, loss: 0.004579753149300814
2023-01-24 08:48:08.023394: step: 380/529, loss: 0.0029917466454207897
2023-01-24 08:48:09.106439: step: 384/529, loss: 0.0003732573240995407
2023-01-24 08:48:10.179250: step: 388/529, loss: 0.0005306508392095566
2023-01-24 08:48:11.256603: step: 392/529, loss: 1.5595917375321733e-06
2023-01-24 08:48:12.321358: step: 396/529, loss: 0.014625673182308674
2023-01-24 08:48:13.385689: step: 400/529, loss: 0.001569255138747394
2023-01-24 08:48:14.461172: step: 404/529, loss: 0.002541843568906188
2023-01-24 08:48:15.527563: step: 408/529, loss: 0.009019548073410988
2023-01-24 08:48:16.625413: step: 412/529, loss: 0.0013536105398088694
2023-01-24 08:48:17.699756: step: 416/529, loss: 0.0003253206086810678
2023-01-24 08:48:18.776715: step: 420/529, loss: 0.0023956219665706158
2023-01-24 08:48:19.831216: step: 424/529, loss: 0.0036653790157288313
2023-01-24 08:48:20.893418: step: 428/529, loss: 0.036183107644319534
2023-01-24 08:48:21.958045: step: 432/529, loss: 0.0028086304664611816
2023-01-24 08:48:23.043048: step: 436/529, loss: 0.005541963502764702
2023-01-24 08:48:24.116675: step: 440/529, loss: 0.011829298920929432
2023-01-24 08:48:25.184354: step: 444/529, loss: 0.001492236857302487
2023-01-24 08:48:26.247223: step: 448/529, loss: 0.004675740376114845
2023-01-24 08:48:27.329578: step: 452/529, loss: 0.0012503373436629772
2023-01-24 08:48:28.400376: step: 456/529, loss: 0.0004541607340797782
2023-01-24 08:48:29.453540: step: 460/529, loss: 0.0011744523653760552
2023-01-24 08:48:30.525819: step: 464/529, loss: 0.0009027521009556949
2023-01-24 08:48:31.591220: step: 468/529, loss: 0.0018053650856018066
2023-01-24 08:48:32.667310: step: 472/529, loss: 0.004834257531911135
2023-01-24 08:48:33.725543: step: 476/529, loss: 1.590656211192254e-05
2023-01-24 08:48:34.804964: step: 480/529, loss: 0.0005579310236498713
2023-01-24 08:48:35.894710: step: 484/529, loss: 0.002521494636312127
2023-01-24 08:48:36.963620: step: 488/529, loss: 0.0009275380289182067
2023-01-24 08:48:38.055618: step: 492/529, loss: 8.145716856233776e-05
2023-01-24 08:48:39.147018: step: 496/529, loss: 0.0035063971299678087
2023-01-24 08:48:40.218490: step: 500/529, loss: 0.004410580266267061
2023-01-24 08:48:41.291289: step: 504/529, loss: 2.120953104167711e-05
2023-01-24 08:48:42.374198: step: 508/529, loss: 0.00011912729678442702
2023-01-24 08:48:43.467136: step: 512/529, loss: 0.0013176235370337963
2023-01-24 08:48:44.534796: step: 516/529, loss: 0.00691906176507473
2023-01-24 08:48:45.609563: step: 520/529, loss: 0.011709775775671005
2023-01-24 08:48:46.680240: step: 524/529, loss: 7.465539965778589e-05
2023-01-24 08:48:47.751210: step: 528/529, loss: 4.04789752792567e-05
2023-01-24 08:48:48.829957: step: 532/529, loss: 0.0036931922659277916
2023-01-24 08:48:49.911782: step: 536/529, loss: 0.0015838434919714928
2023-01-24 08:48:50.978414: step: 540/529, loss: 0.002325591165572405
2023-01-24 08:48:52.052833: step: 544/529, loss: 0.005759669467806816
2023-01-24 08:48:53.128208: step: 548/529, loss: 0.005209536291658878
2023-01-24 08:48:54.222027: step: 552/529, loss: 0.006583836395293474
2023-01-24 08:48:55.294515: step: 556/529, loss: 0.0037974235601723194
2023-01-24 08:48:56.357243: step: 560/529, loss: 0.002532810438424349
2023-01-24 08:48:57.412900: step: 564/529, loss: 0.003581755328923464
2023-01-24 08:48:58.474759: step: 568/529, loss: 0.0007503884844481945
2023-01-24 08:48:59.541640: step: 572/529, loss: 0.006548554636538029
2023-01-24 08:49:00.611959: step: 576/529, loss: 0.002439468400552869
2023-01-24 08:49:01.672793: step: 580/529, loss: 0.00270541338250041
2023-01-24 08:49:02.741417: step: 584/529, loss: 6.443067104555666e-05
2023-01-24 08:49:03.825680: step: 588/529, loss: 0.0006757031078450382
2023-01-24 08:49:04.886751: step: 592/529, loss: 0.0021824685391038656
2023-01-24 08:49:05.960381: step: 596/529, loss: 0.0005361948860809207
2023-01-24 08:49:07.034492: step: 600/529, loss: 0.004789344500750303
2023-01-24 08:49:08.109859: step: 604/529, loss: 0.001820781733840704
2023-01-24 08:49:09.203013: step: 608/529, loss: 0.009909247979521751
2023-01-24 08:49:10.280762: step: 612/529, loss: 0.0002098877594107762
2023-01-24 08:49:11.352062: step: 616/529, loss: 0.0003080358146689832
2023-01-24 08:49:12.424375: step: 620/529, loss: 0.002664165571331978
2023-01-24 08:49:13.498200: step: 624/529, loss: 0.0009047680650837719
2023-01-24 08:49:14.573093: step: 628/529, loss: 0.004044122528284788
2023-01-24 08:49:15.652483: step: 632/529, loss: 0.0039992681704461575
2023-01-24 08:49:16.743716: step: 636/529, loss: 0.0009118133457377553
2023-01-24 08:49:17.824633: step: 640/529, loss: 0.0008229080121964216
2023-01-24 08:49:18.891369: step: 644/529, loss: 0.0015035989927127957
2023-01-24 08:49:19.953340: step: 648/529, loss: 0.003242161124944687
2023-01-24 08:49:21.026815: step: 652/529, loss: 0.00345221278257668
2023-01-24 08:49:22.099318: step: 656/529, loss: 0.00026589020853862166
2023-01-24 08:49:23.184077: step: 660/529, loss: 0.012026051990687847
2023-01-24 08:49:24.254076: step: 664/529, loss: 0.0007402487099170685
2023-01-24 08:49:25.324423: step: 668/529, loss: 0.0045550731010735035
2023-01-24 08:49:26.399401: step: 672/529, loss: 0.003394849132746458
2023-01-24 08:49:27.484090: step: 676/529, loss: 0.004230661783367395
2023-01-24 08:49:28.563243: step: 680/529, loss: 0.0020529828034341335
2023-01-24 08:49:29.628731: step: 684/529, loss: 5.553709343075752e-05
2023-01-24 08:49:30.707914: step: 688/529, loss: 0.0007035293383523822
2023-01-24 08:49:31.784063: step: 692/529, loss: 0.0006701484089717269
2023-01-24 08:49:32.842069: step: 696/529, loss: 0.016399648040533066
2023-01-24 08:49:33.933117: step: 700/529, loss: 0.02274392358958721
2023-01-24 08:49:35.002128: step: 704/529, loss: 0.0034613735042512417
2023-01-24 08:49:36.088118: step: 708/529, loss: 0.01630670204758644
2023-01-24 08:49:37.158774: step: 712/529, loss: 0.004414531867951155
2023-01-24 08:49:38.238520: step: 716/529, loss: 0.00618187990039587
2023-01-24 08:49:39.310763: step: 720/529, loss: 0.012535316869616508
2023-01-24 08:49:40.388231: step: 724/529, loss: 0.025236256420612335
2023-01-24 08:49:41.452665: step: 728/529, loss: 0.0109225083142519
2023-01-24 08:49:42.520006: step: 732/529, loss: 0.0029832429718226194
2023-01-24 08:49:43.604847: step: 736/529, loss: 0.01108157355338335
2023-01-24 08:49:44.668854: step: 740/529, loss: 0.007448251359164715
2023-01-24 08:49:45.764210: step: 744/529, loss: 0.023523937910795212
2023-01-24 08:49:46.843451: step: 748/529, loss: 0.0038337353616952896
2023-01-24 08:49:47.928438: step: 752/529, loss: 0.008344761095941067
2023-01-24 08:49:49.037247: step: 756/529, loss: 0.019771428778767586
2023-01-24 08:49:50.120532: step: 760/529, loss: 0.00035001744981855154
2023-01-24 08:49:51.200184: step: 764/529, loss: 0.005875334143638611
2023-01-24 08:49:52.278214: step: 768/529, loss: 0.002457705792039633
2023-01-24 08:49:53.348768: step: 772/529, loss: 1.4393920537258964e-05
2023-01-24 08:49:54.424966: step: 776/529, loss: 0.006355027202516794
2023-01-24 08:49:55.495819: step: 780/529, loss: 0.00011113999062217772
2023-01-24 08:49:56.577179: step: 784/529, loss: 0.0014787557302042842
2023-01-24 08:49:57.662265: step: 788/529, loss: 0.00033515787799842656
2023-01-24 08:49:58.715482: step: 792/529, loss: 0.011279977858066559
2023-01-24 08:49:59.788868: step: 796/529, loss: 0.00278403889387846
2023-01-24 08:50:00.867697: step: 800/529, loss: 0.005266489926725626
2023-01-24 08:50:01.954872: step: 804/529, loss: 0.002984214574098587
2023-01-24 08:50:03.043238: step: 808/529, loss: 0.004232475534081459
2023-01-24 08:50:04.119281: step: 812/529, loss: 0.002166487742215395
2023-01-24 08:50:05.194021: step: 816/529, loss: 0.022144053131341934
2023-01-24 08:50:06.263445: step: 820/529, loss: 0.004441455472260714
2023-01-24 08:50:07.340870: step: 824/529, loss: 0.00011230283416807652
2023-01-24 08:50:08.417226: step: 828/529, loss: 0.0354902409017086
2023-01-24 08:50:09.486418: step: 832/529, loss: 0.004579294007271528
2023-01-24 08:50:10.557442: step: 836/529, loss: 0.002783134113997221
2023-01-24 08:50:11.620308: step: 840/529, loss: 0.004558006767183542
2023-01-24 08:50:12.696435: step: 844/529, loss: 0.0074923960492014885
2023-01-24 08:50:13.770160: step: 848/529, loss: 0.008867579512298107
2023-01-24 08:50:14.854185: step: 852/529, loss: 0.0037276153452694416
2023-01-24 08:50:15.953002: step: 856/529, loss: 0.002161223441362381
2023-01-24 08:50:17.030277: step: 860/529, loss: 0.00037463707849383354
2023-01-24 08:50:18.096852: step: 864/529, loss: 0.006098653189837933
2023-01-24 08:50:19.162368: step: 868/529, loss: 0.004756368231028318
2023-01-24 08:50:20.245559: step: 872/529, loss: 0.0020644301548600197
2023-01-24 08:50:21.314614: step: 876/529, loss: 0.0030793799087405205
2023-01-24 08:50:22.400529: step: 880/529, loss: 0.00506234634667635
2023-01-24 08:50:23.458420: step: 884/529, loss: 0.0021876669488847256
2023-01-24 08:50:24.554519: step: 888/529, loss: 0.0013469543773680925
2023-01-24 08:50:25.633739: step: 892/529, loss: 0.00020525470608845353
2023-01-24 08:50:26.693860: step: 896/529, loss: 0.00028438394656404853
2023-01-24 08:50:27.764535: step: 900/529, loss: 0.003786481451243162
2023-01-24 08:50:28.822906: step: 904/529, loss: 0.0038216193206608295
2023-01-24 08:50:29.896512: step: 908/529, loss: 8.71155771164922e-06
2023-01-24 08:50:30.971856: step: 912/529, loss: 0.019581666216254234
2023-01-24 08:50:32.028472: step: 916/529, loss: 0.001887670368887484
2023-01-24 08:50:33.096530: step: 920/529, loss: 0.003705795854330063
2023-01-24 08:50:34.189002: step: 924/529, loss: 0.007517037447541952
2023-01-24 08:50:35.256594: step: 928/529, loss: 4.0604254536447115e-07
2023-01-24 08:50:36.329848: step: 932/529, loss: 0.006292502395808697
2023-01-24 08:50:37.389585: step: 936/529, loss: 0.0008214179542846978
2023-01-24 08:50:38.477909: step: 940/529, loss: 0.0001273697562282905
2023-01-24 08:50:39.546622: step: 944/529, loss: 0.006866239011287689
2023-01-24 08:50:40.617846: step: 948/529, loss: 0.004648054949939251
2023-01-24 08:50:41.694192: step: 952/529, loss: 0.0018585880752652884
2023-01-24 08:50:42.745489: step: 956/529, loss: 0.00021947783534415066
2023-01-24 08:50:43.842913: step: 960/529, loss: 0.005518754944205284
2023-01-24 08:50:44.924253: step: 964/529, loss: 0.00654368381947279
2023-01-24 08:50:45.997648: step: 968/529, loss: 0.0060023777186870575
2023-01-24 08:50:47.069250: step: 972/529, loss: 0.000745442055631429
2023-01-24 08:50:48.135056: step: 976/529, loss: 0.0006995638832449913
2023-01-24 08:50:49.212013: step: 980/529, loss: 0.0002712214190978557
2023-01-24 08:50:50.292755: step: 984/529, loss: 4.598938176059164e-05
2023-01-24 08:50:51.374008: step: 988/529, loss: 0.00021073105745017529
2023-01-24 08:50:52.440340: step: 992/529, loss: 0.0026787295937538147
2023-01-24 08:50:53.527689: step: 996/529, loss: 0.004937823861837387
2023-01-24 08:50:54.605817: step: 1000/529, loss: 0.0035365531221032143
2023-01-24 08:50:55.681729: step: 1004/529, loss: 0.002807697979733348
2023-01-24 08:50:56.754772: step: 1008/529, loss: 0.005513792857527733
2023-01-24 08:50:57.830089: step: 1012/529, loss: 0.0002561243891250342
2023-01-24 08:50:58.916989: step: 1016/529, loss: 0.006081057246774435
2023-01-24 08:50:59.991663: step: 1020/529, loss: 0.005015847738832235
2023-01-24 08:51:01.078852: step: 1024/529, loss: 0.0024155641440302134
2023-01-24 08:51:02.158336: step: 1028/529, loss: 0.005686714313924313
2023-01-24 08:51:03.216161: step: 1032/529, loss: 0.0059417602606117725
2023-01-24 08:51:04.303063: step: 1036/529, loss: 0.009248845279216766
2023-01-24 08:51:05.367435: step: 1040/529, loss: 0.004371550865471363
2023-01-24 08:51:06.435589: step: 1044/529, loss: 0.0020127687603235245
2023-01-24 08:51:07.503582: step: 1048/529, loss: 0.001159345149062574
2023-01-24 08:51:08.571917: step: 1052/529, loss: 4.526906559476629e-05
2023-01-24 08:51:09.639582: step: 1056/529, loss: 0.003700123867020011
2023-01-24 08:51:10.699372: step: 1060/529, loss: 0.003462725318968296
2023-01-24 08:51:11.770285: step: 1064/529, loss: 0.005008205771446228
2023-01-24 08:51:12.859244: step: 1068/529, loss: 0.00031501176999881864
2023-01-24 08:51:13.938392: step: 1072/529, loss: 0.0027354652993381023
2023-01-24 08:51:15.015802: step: 1076/529, loss: 0.008873580023646355
2023-01-24 08:51:16.081524: step: 1080/529, loss: 8.971295028459281e-05
2023-01-24 08:51:17.150913: step: 1084/529, loss: 0.014573873020708561
2023-01-24 08:51:18.222345: step: 1088/529, loss: 0.004396980162709951
2023-01-24 08:51:19.285014: step: 1092/529, loss: 0.001197937992401421
2023-01-24 08:51:20.348617: step: 1096/529, loss: 0.00785503163933754
2023-01-24 08:51:21.407763: step: 1100/529, loss: 0.010189991444349289
2023-01-24 08:51:22.474136: step: 1104/529, loss: 0.002251886995509267
2023-01-24 08:51:23.547114: step: 1108/529, loss: 0.002838397864252329
2023-01-24 08:51:24.625845: step: 1112/529, loss: 0.00024347318685613573
2023-01-24 08:51:25.703310: step: 1116/529, loss: 0.0024957633577287197
2023-01-24 08:51:26.772408: step: 1120/529, loss: 0.0016599871451035142
2023-01-24 08:51:27.852835: step: 1124/529, loss: 0.0037962065543979406
2023-01-24 08:51:28.935636: step: 1128/529, loss: 0.0019828176591545343
2023-01-24 08:51:30.003018: step: 1132/529, loss: 0.0019687071908265352
2023-01-24 08:51:31.096582: step: 1136/529, loss: 0.011665153317153454
2023-01-24 08:51:32.165888: step: 1140/529, loss: 0.00034134433371946216
2023-01-24 08:51:33.243995: step: 1144/529, loss: 0.002435169881209731
2023-01-24 08:51:34.310420: step: 1148/529, loss: 0.0007438263855874538
2023-01-24 08:51:35.374125: step: 1152/529, loss: 0.007376573048532009
2023-01-24 08:51:36.445152: step: 1156/529, loss: 0.00010170307359658182
2023-01-24 08:51:37.523103: step: 1160/529, loss: 0.0053239623084664345
2023-01-24 08:51:38.587889: step: 1164/529, loss: 0.010280627757310867
2023-01-24 08:51:39.644105: step: 1168/529, loss: 0.010312197729945183
2023-01-24 08:51:40.725002: step: 1172/529, loss: 0.006687337998300791
2023-01-24 08:51:41.793655: step: 1176/529, loss: 0.0010680067352950573
2023-01-24 08:51:42.886851: step: 1180/529, loss: 0.00954980868846178
2023-01-24 08:51:43.967566: step: 1184/529, loss: 0.004383870866149664
2023-01-24 08:51:45.049797: step: 1188/529, loss: 0.0003942779148928821
2023-01-24 08:51:46.101601: step: 1192/529, loss: 0.001772363786585629
2023-01-24 08:51:47.189327: step: 1196/529, loss: 0.0011210321681573987
2023-01-24 08:51:48.271512: step: 1200/529, loss: 0.013752724044024944
2023-01-24 08:51:49.334102: step: 1204/529, loss: 0.0003787998575717211
2023-01-24 08:51:50.416247: step: 1208/529, loss: 0.011433050036430359
2023-01-24 08:51:51.492394: step: 1212/529, loss: 0.0009741354733705521
2023-01-24 08:51:52.568371: step: 1216/529, loss: 0.013240729458630085
2023-01-24 08:51:53.636097: step: 1220/529, loss: 0.005714384838938713
2023-01-24 08:51:54.721955: step: 1224/529, loss: 0.00011433459440013394
2023-01-24 08:51:55.794736: step: 1228/529, loss: 0.0015510107623413205
2023-01-24 08:51:56.875321: step: 1232/529, loss: 0.0036971797235310078
2023-01-24 08:51:57.963517: step: 1236/529, loss: 0.0013544723624363542
2023-01-24 08:51:59.023012: step: 1240/529, loss: 0.012556590139865875
2023-01-24 08:52:00.082293: step: 1244/529, loss: 0.0016521679935976863
2023-01-24 08:52:01.174693: step: 1248/529, loss: 0.0019292457727715373
2023-01-24 08:52:02.271197: step: 1252/529, loss: 0.0047577121295034885
2023-01-24 08:52:03.345150: step: 1256/529, loss: 0.013279648497700691
2023-01-24 08:52:04.414432: step: 1260/529, loss: 0.0020150321070104837
2023-01-24 08:52:05.485890: step: 1264/529, loss: 0.06822654604911804
2023-01-24 08:52:06.546821: step: 1268/529, loss: 0.00014766899403184652
2023-01-24 08:52:07.619730: step: 1272/529, loss: 0.004514533095061779
2023-01-24 08:52:08.686934: step: 1276/529, loss: 0.003707671305164695
2023-01-24 08:52:09.759375: step: 1280/529, loss: 0.0008800482610240579
2023-01-24 08:52:10.832945: step: 1284/529, loss: 0.0025320565328001976
2023-01-24 08:52:11.909136: step: 1288/529, loss: 0.0003295718925073743
2023-01-24 08:52:12.993120: step: 1292/529, loss: 0.009966210462152958
2023-01-24 08:52:14.065600: step: 1296/529, loss: 0.010593287646770477
2023-01-24 08:52:15.140099: step: 1300/529, loss: 0.01655689999461174
2023-01-24 08:52:16.203693: step: 1304/529, loss: 0.005912919994443655
2023-01-24 08:52:17.276795: step: 1308/529, loss: 0.0003717422659974545
2023-01-24 08:52:18.356826: step: 1312/529, loss: 0.00473179342225194
2023-01-24 08:52:19.425634: step: 1316/529, loss: 0.04951927065849304
2023-01-24 08:52:20.498089: step: 1320/529, loss: 0.0061185224913060665
2023-01-24 08:52:21.574338: step: 1324/529, loss: 0.0075952596962451935
2023-01-24 08:52:22.649388: step: 1328/529, loss: 0.00022339631686918437
2023-01-24 08:52:23.735683: step: 1332/529, loss: 0.003941317554563284
2023-01-24 08:52:24.827720: step: 1336/529, loss: 7.480735803255811e-05
2023-01-24 08:52:25.906571: step: 1340/529, loss: 0.011999009177088737
2023-01-24 08:52:26.989680: step: 1344/529, loss: 0.0013146221172064543
2023-01-24 08:52:28.048600: step: 1348/529, loss: 0.05926206335425377
2023-01-24 08:52:29.105399: step: 1352/529, loss: 0.00828623678535223
2023-01-24 08:52:30.191251: step: 1356/529, loss: 0.004431975074112415
2023-01-24 08:52:31.262894: step: 1360/529, loss: 0.004410061985254288
2023-01-24 08:52:32.327494: step: 1364/529, loss: 0.0013089042622596025
2023-01-24 08:52:33.404026: step: 1368/529, loss: 0.007834733463823795
2023-01-24 08:52:34.459083: step: 1372/529, loss: 0.003975994884967804
2023-01-24 08:52:35.519106: step: 1376/529, loss: 0.010506715625524521
2023-01-24 08:52:36.590966: step: 1380/529, loss: 0.001384251518175006
2023-01-24 08:52:37.679428: step: 1384/529, loss: 0.006658020429313183
2023-01-24 08:52:38.741984: step: 1388/529, loss: 0.0011319330660626292
2023-01-24 08:52:39.817566: step: 1392/529, loss: 0.001445335103198886
2023-01-24 08:52:40.874392: step: 1396/529, loss: 0.0019462514901533723
2023-01-24 08:52:41.974081: step: 1400/529, loss: 0.03967732563614845
2023-01-24 08:52:43.065360: step: 1404/529, loss: 0.022351933643221855
2023-01-24 08:52:44.133956: step: 1408/529, loss: 0.003850222798064351
2023-01-24 08:52:45.216583: step: 1412/529, loss: 0.00017581836436875165
2023-01-24 08:52:46.273349: step: 1416/529, loss: 0.008602466434240341
2023-01-24 08:52:47.361000: step: 1420/529, loss: 0.010391976684331894
2023-01-24 08:52:48.435711: step: 1424/529, loss: 0.0233137384057045
2023-01-24 08:52:49.502517: step: 1428/529, loss: 0.007026453968137503
2023-01-24 08:52:50.569342: step: 1432/529, loss: 0.0029631215147674084
2023-01-24 08:52:51.644704: step: 1436/529, loss: 0.002670511370524764
2023-01-24 08:52:52.713363: step: 1440/529, loss: 0.006047316826879978
2023-01-24 08:52:53.805564: step: 1444/529, loss: 0.02050812914967537
2023-01-24 08:52:54.864653: step: 1448/529, loss: 0.008940990082919598
2023-01-24 08:52:55.947517: step: 1452/529, loss: 0.007197519764304161
2023-01-24 08:52:57.035600: step: 1456/529, loss: 0.005508510861545801
2023-01-24 08:52:58.118963: step: 1460/529, loss: 0.06660294532775879
2023-01-24 08:52:59.200162: step: 1464/529, loss: 0.010147585533559322
2023-01-24 08:53:00.293415: step: 1468/529, loss: 0.0052138096652925014
2023-01-24 08:53:01.368626: step: 1472/529, loss: 0.003988031763583422
2023-01-24 08:53:02.443694: step: 1476/529, loss: 0.004229758400470018
2023-01-24 08:53:03.509408: step: 1480/529, loss: 0.003836695570498705
2023-01-24 08:53:04.583796: step: 1484/529, loss: 0.003095924388617277
2023-01-24 08:53:05.673397: step: 1488/529, loss: 0.0056379917077720165
2023-01-24 08:53:06.756776: step: 1492/529, loss: 0.019603027030825615
2023-01-24 08:53:07.812629: step: 1496/529, loss: 0.002713260240852833
2023-01-24 08:53:08.875096: step: 1500/529, loss: 0.01192429568618536
2023-01-24 08:53:09.949897: step: 1504/529, loss: 0.024023110046982765
2023-01-24 08:53:11.015844: step: 1508/529, loss: 0.02491852082312107
2023-01-24 08:53:12.087608: step: 1512/529, loss: 0.015108231455087662
2023-01-24 08:53:13.174159: step: 1516/529, loss: 0.00885758176445961
2023-01-24 08:53:14.264098: step: 1520/529, loss: 0.004531919956207275
2023-01-24 08:53:15.333489: step: 1524/529, loss: 0.07931800931692123
2023-01-24 08:53:16.417663: step: 1528/529, loss: 0.01182169932872057
2023-01-24 08:53:17.491718: step: 1532/529, loss: 0.004285391420125961
2023-01-24 08:53:18.563347: step: 1536/529, loss: 0.008243849501013756
2023-01-24 08:53:19.615583: step: 1540/529, loss: 0.01846648007631302
2023-01-24 08:53:20.692427: step: 1544/529, loss: 0.0836813822388649
2023-01-24 08:53:21.764962: step: 1548/529, loss: 0.04009845852851868
2023-01-24 08:53:22.843149: step: 1552/529, loss: 0.025475895032286644
2023-01-24 08:53:23.892685: step: 1556/529, loss: 0.002944002626463771
2023-01-24 08:53:24.973191: step: 1560/529, loss: 0.01520458422601223
2023-01-24 08:53:26.065437: step: 1564/529, loss: 0.016403669491410255
2023-01-24 08:53:27.145102: step: 1568/529, loss: 0.010399769991636276
2023-01-24 08:53:28.221626: step: 1572/529, loss: 0.02235635183751583
2023-01-24 08:53:29.304758: step: 1576/529, loss: 0.04166422411799431
2023-01-24 08:53:30.378036: step: 1580/529, loss: 0.006262169219553471
2023-01-24 08:53:31.452509: step: 1584/529, loss: 0.004788485821336508
2023-01-24 08:53:32.535479: step: 1588/529, loss: 0.0006601986242458224
2023-01-24 08:53:33.612791: step: 1592/529, loss: 0.010616461746394634
2023-01-24 08:53:34.678856: step: 1596/529, loss: 0.0005407176213338971
2023-01-24 08:53:35.764674: step: 1600/529, loss: 0.015413879416882992
2023-01-24 08:53:36.840758: step: 1604/529, loss: 0.0013394468696787953
2023-01-24 08:53:37.898020: step: 1608/529, loss: 0.005355029832571745
2023-01-24 08:53:38.969863: step: 1612/529, loss: 0.006717989221215248
2023-01-24 08:53:40.059825: step: 1616/529, loss: 0.009617160074412823
2023-01-24 08:53:41.125767: step: 1620/529, loss: 0.0011271152179688215
2023-01-24 08:53:42.203179: step: 1624/529, loss: 0.03819387033581734
2023-01-24 08:53:43.279522: step: 1628/529, loss: 0.00708995433524251
2023-01-24 08:53:44.359030: step: 1632/529, loss: 0.006487742532044649
2023-01-24 08:53:45.426528: step: 1636/529, loss: 2.0126548406551592e-05
2023-01-24 08:53:46.502133: step: 1640/529, loss: 0.020241333171725273
2023-01-24 08:53:47.594063: step: 1644/529, loss: 0.006108326371759176
2023-01-24 08:53:48.667928: step: 1648/529, loss: 0.0041269357316195965
2023-01-24 08:53:49.753963: step: 1652/529, loss: 0.007861895486712456
2023-01-24 08:53:50.833514: step: 1656/529, loss: 0.016316376626491547
2023-01-24 08:53:51.914581: step: 1660/529, loss: 0.010215459391474724
2023-01-24 08:53:52.981505: step: 1664/529, loss: 0.0442894883453846
2023-01-24 08:53:54.050768: step: 1668/529, loss: 0.003823575796559453
2023-01-24 08:53:55.127305: step: 1672/529, loss: 0.0047595868818461895
2023-01-24 08:53:56.217868: step: 1676/529, loss: 0.00584134366363287
2023-01-24 08:53:57.291558: step: 1680/529, loss: 0.006459423806518316
2023-01-24 08:53:58.370469: step: 1684/529, loss: 0.006974353455007076
2023-01-24 08:53:59.443819: step: 1688/529, loss: 0.008059553802013397
2023-01-24 08:54:00.532262: step: 1692/529, loss: 0.004898645915091038
2023-01-24 08:54:01.607366: step: 1696/529, loss: 0.025280611589550972
2023-01-24 08:54:02.695981: step: 1700/529, loss: 0.0001225828455062583
2023-01-24 08:54:03.763685: step: 1704/529, loss: 0.0002256205480080098
2023-01-24 08:54:04.846151: step: 1708/529, loss: 0.007077811285853386
2023-01-24 08:54:05.909609: step: 1712/529, loss: 0.011649307794868946
2023-01-24 08:54:06.998229: step: 1716/529, loss: 0.02036501280963421
2023-01-24 08:54:08.073317: step: 1720/529, loss: 0.004421024117618799
2023-01-24 08:54:09.133211: step: 1724/529, loss: 0.0001589000748936087
2023-01-24 08:54:10.224647: step: 1728/529, loss: 0.1147143691778183
2023-01-24 08:54:11.302667: step: 1732/529, loss: 0.00032137572998180985
2023-01-24 08:54:12.369953: step: 1736/529, loss: 0.012886990793049335
2023-01-24 08:54:13.449356: step: 1740/529, loss: 0.0007714257808402181
2023-01-24 08:54:14.526826: step: 1744/529, loss: 0.007499590050429106
2023-01-24 08:54:15.607972: step: 1748/529, loss: 0.0013658899115398526
2023-01-24 08:54:16.693523: step: 1752/529, loss: 0.012005806900560856
2023-01-24 08:54:17.755485: step: 1756/529, loss: 0.007383640389889479
2023-01-24 08:54:18.844832: step: 1760/529, loss: 0.012057912535965443
2023-01-24 08:54:19.926823: step: 1764/529, loss: 0.01914384961128235
2023-01-24 08:54:20.992970: step: 1768/529, loss: 0.004751065745949745
2023-01-24 08:54:22.062127: step: 1772/529, loss: 0.037016380578279495
2023-01-24 08:54:23.136274: step: 1776/529, loss: 1.788167173799593e-05
2023-01-24 08:54:24.224600: step: 1780/529, loss: 0.0023537336383014917
2023-01-24 08:54:25.295794: step: 1784/529, loss: 0.06649907678365707
2023-01-24 08:54:26.369275: step: 1788/529, loss: 0.00046867263154126704
2023-01-24 08:54:27.410178: step: 1792/529, loss: 0.0030611385591328144
2023-01-24 08:54:28.486330: step: 1796/529, loss: 0.0029054179321974516
2023-01-24 08:54:29.566611: step: 1800/529, loss: 0.0012938749277964234
2023-01-24 08:54:30.655186: step: 1804/529, loss: 0.019227538257837296
2023-01-24 08:54:31.738565: step: 1808/529, loss: 0.011588284745812416
2023-01-24 08:54:32.816897: step: 1812/529, loss: 0.0004917408805340528
2023-01-24 08:54:33.899991: step: 1816/529, loss: 0.002023714128881693
2023-01-24 08:54:34.983509: step: 1820/529, loss: 0.004464180674403906
2023-01-24 08:54:36.049003: step: 1824/529, loss: 0.003917478956282139
2023-01-24 08:54:37.119947: step: 1828/529, loss: 0.01375524327158928
2023-01-24 08:54:38.197834: step: 1832/529, loss: 0.0004942264058627188
2023-01-24 08:54:39.297440: step: 1836/529, loss: 0.0043309531174600124
2023-01-24 08:54:40.358197: step: 1840/529, loss: 0.004723868332803249
2023-01-24 08:54:41.425632: step: 1844/529, loss: 0.000695010123308748
2023-01-24 08:54:42.493777: step: 1848/529, loss: 0.016243886202573776
2023-01-24 08:54:43.617063: step: 1852/529, loss: 0.009934772737324238
2023-01-24 08:54:44.688395: step: 1856/529, loss: 0.004993104841560125
2023-01-24 08:54:45.763574: step: 1860/529, loss: 0.0043144216760993
2023-01-24 08:54:46.822628: step: 1864/529, loss: 0.002567149233072996
2023-01-24 08:54:47.878648: step: 1868/529, loss: 0.005471567623317242
2023-01-24 08:54:48.958092: step: 1872/529, loss: 0.0025861479807645082
2023-01-24 08:54:50.026461: step: 1876/529, loss: 0.00028775312239304185
2023-01-24 08:54:51.104788: step: 1880/529, loss: 0.014888478443026543
2023-01-24 08:54:52.167717: step: 1884/529, loss: 0.00999882910400629
2023-01-24 08:54:53.241536: step: 1888/529, loss: 0.0033422678243368864
2023-01-24 08:54:54.316968: step: 1892/529, loss: 0.045420411974191666
2023-01-24 08:54:55.383357: step: 1896/529, loss: 0.0019703619182109833
2023-01-24 08:54:56.447724: step: 1900/529, loss: 0.0038814619183540344
2023-01-24 08:54:57.534545: step: 1904/529, loss: 0.006972117815166712
2023-01-24 08:54:58.614384: step: 1908/529, loss: 0.00014306962839327753
2023-01-24 08:54:59.688100: step: 1912/529, loss: 8.572261322115082e-06
2023-01-24 08:55:00.748559: step: 1916/529, loss: 0.0010433811694383621
2023-01-24 08:55:01.821162: step: 1920/529, loss: 0.013767136260867119
2023-01-24 08:55:02.901181: step: 1924/529, loss: 0.018282251432538033
2023-01-24 08:55:03.987403: step: 1928/529, loss: 0.0023097163066267967
2023-01-24 08:55:05.076456: step: 1932/529, loss: 0.008481103926897049
2023-01-24 08:55:06.149796: step: 1936/529, loss: 0.00039895385270938277
2023-01-24 08:55:07.227387: step: 1940/529, loss: 0.006965293549001217
2023-01-24 08:55:08.301755: step: 1944/529, loss: 0.0018776124343276024
2023-01-24 08:55:09.372080: step: 1948/529, loss: 1.5175035514403135e-05
2023-01-24 08:55:10.442508: step: 1952/529, loss: 0.0023299106396734715
2023-01-24 08:55:11.517859: step: 1956/529, loss: 0.001219909405335784
2023-01-24 08:55:12.603267: step: 1960/529, loss: 1.7902691979543306e-05
2023-01-24 08:55:13.701924: step: 1964/529, loss: 0.011577676050364971
2023-01-24 08:55:14.792893: step: 1968/529, loss: 0.010660630650818348
2023-01-24 08:55:15.871993: step: 1972/529, loss: 0.0015880067367106676
2023-01-24 08:55:16.950308: step: 1976/529, loss: 0.0007982393726706505
2023-01-24 08:55:18.007520: step: 1980/529, loss: 0.005514700431376696
2023-01-24 08:55:19.084629: step: 1984/529, loss: 0.00013628712622448802
2023-01-24 08:55:20.176238: step: 1988/529, loss: 0.0029673371464014053
2023-01-24 08:55:21.235960: step: 1992/529, loss: 0.006338965147733688
2023-01-24 08:55:22.322435: step: 1996/529, loss: 0.0006737405201420188
2023-01-24 08:55:23.419721: step: 2000/529, loss: 0.0029726927168667316
2023-01-24 08:55:24.484604: step: 2004/529, loss: 0.0008707870147190988
2023-01-24 08:55:25.551084: step: 2008/529, loss: 0.002293345518410206
2023-01-24 08:55:26.620655: step: 2012/529, loss: 0.010868585668504238
2023-01-24 08:55:27.699047: step: 2016/529, loss: 0.001958066364750266
2023-01-24 08:55:28.757495: step: 2020/529, loss: 0.00029370779520832
2023-01-24 08:55:29.846513: step: 2024/529, loss: 0.002247725147753954
2023-01-24 08:55:30.917133: step: 2028/529, loss: 0.003144902177155018
2023-01-24 08:55:31.997937: step: 2032/529, loss: 0.002322837710380554
2023-01-24 08:55:33.061626: step: 2036/529, loss: 0.008072112686932087
2023-01-24 08:55:34.156756: step: 2040/529, loss: 0.05930409952998161
2023-01-24 08:55:35.239410: step: 2044/529, loss: 0.006734666880220175
2023-01-24 08:55:36.300759: step: 2048/529, loss: 0.0032757148146629333
2023-01-24 08:55:37.359568: step: 2052/529, loss: 0.0004420387267600745
2023-01-24 08:55:38.441946: step: 2056/529, loss: 0.001882361015304923
2023-01-24 08:55:39.524662: step: 2060/529, loss: 0.0025561205111443996
2023-01-24 08:55:40.594613: step: 2064/529, loss: 0.0038214854430407286
2023-01-24 08:55:41.664992: step: 2068/529, loss: 0.00022664254356641322
2023-01-24 08:55:42.745793: step: 2072/529, loss: 0.00832713395357132
2023-01-24 08:55:43.855391: step: 2076/529, loss: 0.0032956209033727646
2023-01-24 08:55:44.934715: step: 2080/529, loss: 0.0043381499126553535
2023-01-24 08:55:46.025591: step: 2084/529, loss: 0.005727696698158979
2023-01-24 08:55:47.112059: step: 2088/529, loss: 0.001343218027614057
2023-01-24 08:55:48.180223: step: 2092/529, loss: 0.0005521242856048048
2023-01-24 08:55:49.264780: step: 2096/529, loss: 0.0005589186330325902
2023-01-24 08:55:50.357581: step: 2100/529, loss: 0.011060362681746483
2023-01-24 08:55:51.414724: step: 2104/529, loss: 0.0019971111323684454
2023-01-24 08:55:52.494597: step: 2108/529, loss: 0.006012806203216314
2023-01-24 08:55:53.582053: step: 2112/529, loss: 0.00186148623470217
2023-01-24 08:55:54.666798: step: 2116/529, loss: 0.025643527507781982
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3404438267844452, 'r': 0.3029756257341647, 'f1': 0.3206187846624594}, 'combined': 0.23624542027760165, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33272402998360645, 'r': 0.29235677634588947, 'f1': 0.3112369595541367}, 'combined': 0.20319096841358147, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3636796067612542, 'r': 0.3581588537174401, 'f1': 0.3608981183730229}, 'combined': 0.2659249293274905, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35552667976942665, 'r': 0.31173938648900096, 'f1': 0.3321963295788767}, 'combined': 0.21687428770434436, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3809219426406926, 'r': 0.33827603255378397, 'f1': 0.35833461136853095}, 'combined': 0.2640360294294438, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.37157447710037905, 'r': 0.3064039306116992, 'f1': 0.3358569506151388}, 'combined': 0.21926412319952068, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3888888888888889, 'r': 0.45652173913043476, 'f1': 0.42}, 'combined': 0.21, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580872292314783, 'r': 0.3574077468230694, 'f1': 0.3577471653860543}, 'combined': 0.2636031744949873, 'stategy': 1, 'epoch': 11}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36065178272254766, 'r': 0.3165647541360598, 'f1': 0.3371732280959697}, 'combined': 0.2201234546118766, 'stategy': 1, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:58:25.651350: step: 4/529, loss: 0.0010954438475891948
2023-01-24 08:58:26.721479: step: 8/529, loss: 0.00014005853154230863
2023-01-24 08:58:27.782552: step: 12/529, loss: 0.0013785591581836343
2023-01-24 08:58:28.856956: step: 16/529, loss: 0.005142595618963242
2023-01-24 08:58:29.921153: step: 20/529, loss: 0.008900392800569534
2023-01-24 08:58:30.973925: step: 24/529, loss: 0.0006917696446180344
2023-01-24 08:58:32.047270: step: 28/529, loss: 0.004724801983684301
2023-01-24 08:58:33.102009: step: 32/529, loss: 0.009850116446614265
2023-01-24 08:58:34.158826: step: 36/529, loss: 0.0032707988284528255
2023-01-24 08:58:35.229027: step: 40/529, loss: 0.002567447954788804
2023-01-24 08:58:36.290139: step: 44/529, loss: 0.000650116999167949
2023-01-24 08:58:37.354922: step: 48/529, loss: 0.0013387176441028714
2023-01-24 08:58:38.418647: step: 52/529, loss: 0.006641398649662733
2023-01-24 08:58:39.455356: step: 56/529, loss: 0.0027483964804559946
2023-01-24 08:58:40.523719: step: 60/529, loss: 0.004357555881142616
2023-01-24 08:58:41.610651: step: 64/529, loss: 0.009028466418385506
2023-01-24 08:58:42.678662: step: 68/529, loss: 6.34523676126264e-05
2023-01-24 08:58:43.742834: step: 72/529, loss: 0.006409817840903997
2023-01-24 08:58:44.797391: step: 76/529, loss: 0.009009601548314095
2023-01-24 08:58:45.851795: step: 80/529, loss: 0.0050859469920396805
2023-01-24 08:58:46.900959: step: 84/529, loss: 0.0046436237171292305
2023-01-24 08:58:47.963587: step: 88/529, loss: 0.0021038404665887356
2023-01-24 08:58:49.022744: step: 92/529, loss: 0.0002085765008814633
2023-01-24 08:58:50.088552: step: 96/529, loss: 9.38282537390478e-05
2023-01-24 08:58:51.154063: step: 100/529, loss: 9.447576303500682e-06
2023-01-24 08:58:52.240093: step: 104/529, loss: 0.004167590290307999
2023-01-24 08:58:53.347601: step: 108/529, loss: 0.0044244155287742615
2023-01-24 08:58:54.405007: step: 112/529, loss: 0.0027735703624784946
2023-01-24 08:58:55.477465: step: 116/529, loss: 5.468056406243704e-05
2023-01-24 08:58:56.542110: step: 120/529, loss: 0.008275819011032581
2023-01-24 08:58:57.605452: step: 124/529, loss: 0.000756150926463306
2023-01-24 08:58:58.674186: step: 128/529, loss: 0.009803102351725101
2023-01-24 08:58:59.738292: step: 132/529, loss: 0.0065562487579882145
2023-01-24 08:59:00.811324: step: 136/529, loss: 0.0007596256909891963
2023-01-24 08:59:01.864971: step: 140/529, loss: 0.0006582309724763036
2023-01-24 08:59:02.930393: step: 144/529, loss: 0.0004294962855055928
2023-01-24 08:59:03.989809: step: 148/529, loss: 0.0011537284590303898
2023-01-24 08:59:05.077583: step: 152/529, loss: 0.00482360552996397
2023-01-24 08:59:06.152332: step: 156/529, loss: 0.00574611546471715
2023-01-24 08:59:07.196670: step: 160/529, loss: 0.0026020624209195375
2023-01-24 08:59:08.265878: step: 164/529, loss: 0.0018216570606455207
2023-01-24 08:59:09.355332: step: 168/529, loss: 0.00622558081522584
2023-01-24 08:59:10.403293: step: 172/529, loss: 0.000253814912866801
2023-01-24 08:59:11.469740: step: 176/529, loss: 0.007571086753159761
2023-01-24 08:59:12.535472: step: 180/529, loss: 0.02941497229039669
2023-01-24 08:59:13.594703: step: 184/529, loss: 0.005346913821995258
2023-01-24 08:59:14.674130: step: 188/529, loss: 0.0126403933390975
2023-01-24 08:59:15.742597: step: 192/529, loss: 0.014569035731256008
2023-01-24 08:59:16.802587: step: 196/529, loss: 0.000573804893065244
2023-01-24 08:59:17.859895: step: 200/529, loss: 0.0012837330577895045
2023-01-24 08:59:18.934320: step: 204/529, loss: 0.00323014915920794
2023-01-24 08:59:20.005241: step: 208/529, loss: 0.008282310329377651
2023-01-24 08:59:21.086273: step: 212/529, loss: 1.6132453311001882e-05
2023-01-24 08:59:22.142662: step: 216/529, loss: 0.0003099872265011072
2023-01-24 08:59:23.197871: step: 220/529, loss: 0.0011674208799377084
2023-01-24 08:59:24.273466: step: 224/529, loss: 0.0006898681749589741
2023-01-24 08:59:25.329282: step: 228/529, loss: 0.0030965341720730066
2023-01-24 08:59:26.385559: step: 232/529, loss: 0.0007291412330232561
2023-01-24 08:59:27.451345: step: 236/529, loss: 0.05628994479775429
2023-01-24 08:59:28.507675: step: 240/529, loss: 0.002138701267540455
2023-01-24 08:59:29.575671: step: 244/529, loss: 0.0026771645061671734
2023-01-24 08:59:30.649425: step: 248/529, loss: 0.003572388319298625
2023-01-24 08:59:31.708814: step: 252/529, loss: 0.013278273865580559
2023-01-24 08:59:32.787464: step: 256/529, loss: 0.005799334961920977
2023-01-24 08:59:33.881679: step: 260/529, loss: 0.0029618097469210625
2023-01-24 08:59:34.941542: step: 264/529, loss: 0.004178767558187246
2023-01-24 08:59:36.008270: step: 268/529, loss: 0.0004428937681950629
2023-01-24 08:59:37.081176: step: 272/529, loss: 0.0007823935011401772
2023-01-24 08:59:38.153077: step: 276/529, loss: 0.00128506391774863
2023-01-24 08:59:39.204543: step: 280/529, loss: 0.0005061851697973907
2023-01-24 08:59:40.268478: step: 284/529, loss: 0.0006799264228902757
2023-01-24 08:59:41.310145: step: 288/529, loss: 0.0068840160965919495
2023-01-24 08:59:42.384028: step: 292/529, loss: 0.01142135076224804
2023-01-24 08:59:43.466871: step: 296/529, loss: 0.008359819650650024
2023-01-24 08:59:44.509862: step: 300/529, loss: 0.007426922675222158
2023-01-24 08:59:45.578757: step: 304/529, loss: 0.003563546808436513
2023-01-24 08:59:46.657025: step: 308/529, loss: 0.004988022614270449
2023-01-24 08:59:47.718300: step: 312/529, loss: 0.0009332579211331904
2023-01-24 08:59:48.785197: step: 316/529, loss: 0.001709270873107016
2023-01-24 08:59:49.842922: step: 320/529, loss: 0.0003621365176513791
2023-01-24 08:59:50.906344: step: 324/529, loss: 0.0006478636641986668
2023-01-24 08:59:51.965725: step: 328/529, loss: 0.00011735512089217082
2023-01-24 08:59:53.022065: step: 332/529, loss: 0.000821030989754945
2023-01-24 08:59:54.093492: step: 336/529, loss: 0.0003936767461709678
2023-01-24 08:59:55.171007: step: 340/529, loss: 0.003962892107665539
2023-01-24 08:59:56.244310: step: 344/529, loss: 0.004729588981717825
2023-01-24 08:59:57.312082: step: 348/529, loss: 0.002129775006324053
2023-01-24 08:59:58.372558: step: 352/529, loss: 0.00276339054107666
2023-01-24 08:59:59.446340: step: 356/529, loss: 0.000782274641096592
2023-01-24 09:00:00.517002: step: 360/529, loss: 0.0009951724205166101
2023-01-24 09:00:01.592420: step: 364/529, loss: 0.0035933861508965492
2023-01-24 09:00:02.672677: step: 368/529, loss: 0.000625802029389888
2023-01-24 09:00:03.754795: step: 372/529, loss: 0.0025161586236208677
2023-01-24 09:00:04.806713: step: 376/529, loss: 0.0047616539523005486
2023-01-24 09:00:05.866750: step: 380/529, loss: 0.004277392290532589
2023-01-24 09:00:06.923869: step: 384/529, loss: 0.00019334277021698654
2023-01-24 09:00:07.987087: step: 388/529, loss: 0.001998462015762925
2023-01-24 09:00:09.052970: step: 392/529, loss: 0.0002462692209519446
2023-01-24 09:00:10.136867: step: 396/529, loss: 0.0010160517413169146
2023-01-24 09:00:11.209424: step: 400/529, loss: 0.001342215808108449
2023-01-24 09:00:12.286394: step: 404/529, loss: 0.00032033113529905677
2023-01-24 09:00:13.368341: step: 408/529, loss: 0.0003599270130507648
2023-01-24 09:00:14.444552: step: 412/529, loss: 0.010256094858050346
2023-01-24 09:00:15.516669: step: 416/529, loss: 0.0032527311705052853
2023-01-24 09:00:16.584837: step: 420/529, loss: 0.006540959235280752
2023-01-24 09:00:17.658054: step: 424/529, loss: 0.001434178906492889
2023-01-24 09:00:18.744711: step: 428/529, loss: 0.005891936831176281
2023-01-24 09:00:19.817219: step: 432/529, loss: 8.731216075830162e-05
2023-01-24 09:00:20.888518: step: 436/529, loss: 0.0020319747272878885
2023-01-24 09:00:21.954108: step: 440/529, loss: 0.0036512166261672974
2023-01-24 09:00:23.041932: step: 444/529, loss: 0.013736655935645103
2023-01-24 09:00:24.095318: step: 448/529, loss: 0.0002248917444376275
2023-01-24 09:00:25.174512: step: 452/529, loss: 0.0028420104645192623
2023-01-24 09:00:26.253525: step: 456/529, loss: 0.003367389552295208
2023-01-24 09:00:27.317579: step: 460/529, loss: 7.060422831273172e-06
2023-01-24 09:00:28.377237: step: 464/529, loss: 0.0004347244102973491
2023-01-24 09:00:29.454293: step: 468/529, loss: 0.009450795128941536
2023-01-24 09:00:30.523240: step: 472/529, loss: 0.0001558825751999393
2023-01-24 09:00:31.600045: step: 476/529, loss: 0.004345542285591364
2023-01-24 09:00:32.678684: step: 480/529, loss: 0.0019708226900547743
2023-01-24 09:00:33.744415: step: 484/529, loss: 0.010202948935329914
2023-01-24 09:00:34.823917: step: 488/529, loss: 0.023752881214022636
2023-01-24 09:00:35.910192: step: 492/529, loss: 0.0038924843538552523
2023-01-24 09:00:37.000508: step: 496/529, loss: 0.003336658701300621
2023-01-24 09:00:38.087771: step: 500/529, loss: 0.006687353830784559
2023-01-24 09:00:39.179796: step: 504/529, loss: 0.0003770515904761851
2023-01-24 09:00:40.260102: step: 508/529, loss: 0.00023633446835447103
2023-01-24 09:00:41.314296: step: 512/529, loss: 0.008220965974032879
2023-01-24 09:00:42.384817: step: 516/529, loss: 0.0034480062313377857
2023-01-24 09:00:43.454145: step: 520/529, loss: 0.012186998501420021
2023-01-24 09:00:44.545413: step: 524/529, loss: 0.006798294838517904
2023-01-24 09:00:45.623098: step: 528/529, loss: 0.0014652048703283072
2023-01-24 09:00:46.696646: step: 532/529, loss: 0.002841431647539139
2023-01-24 09:00:47.760407: step: 536/529, loss: 0.004340182989835739
2023-01-24 09:00:48.821990: step: 540/529, loss: 0.00031229222076945007
2023-01-24 09:00:49.890958: step: 544/529, loss: 0.002261245856061578
2023-01-24 09:00:50.969756: step: 548/529, loss: 0.00027513556415215135
2023-01-24 09:00:52.025015: step: 552/529, loss: 8.289164543384686e-05
2023-01-24 09:00:53.083568: step: 556/529, loss: 0.0006063411710783839
2023-01-24 09:00:54.152655: step: 560/529, loss: 0.002139572286978364
2023-01-24 09:00:55.206835: step: 564/529, loss: 0.004961965139955282
2023-01-24 09:00:56.274500: step: 568/529, loss: 0.004999150056391954
2023-01-24 09:00:57.335927: step: 572/529, loss: 0.0012909912038594484
2023-01-24 09:00:58.414040: step: 576/529, loss: 0.010782454162836075
2023-01-24 09:00:59.492510: step: 580/529, loss: 0.003144910791888833
2023-01-24 09:01:00.552183: step: 584/529, loss: 0.005620375741273165
2023-01-24 09:01:01.617458: step: 588/529, loss: 0.0032185467425733805
2023-01-24 09:01:02.680220: step: 592/529, loss: 0.004467971157282591
2023-01-24 09:01:03.755933: step: 596/529, loss: 0.0006425076862797141
2023-01-24 09:01:04.841361: step: 600/529, loss: 0.007304641418159008
2023-01-24 09:01:05.914621: step: 604/529, loss: 0.0007512957672588527
2023-01-24 09:01:06.997312: step: 608/529, loss: 0.00016295410750899464
2023-01-24 09:01:08.083463: step: 612/529, loss: 0.0036396945361047983
2023-01-24 09:01:09.142398: step: 616/529, loss: 3.9047754398779944e-05
2023-01-24 09:01:10.203842: step: 620/529, loss: 3.933031257474795e-05
2023-01-24 09:01:11.270436: step: 624/529, loss: 0.004212466534227133
2023-01-24 09:01:12.324668: step: 628/529, loss: 0.0002174114342778921
2023-01-24 09:01:13.383503: step: 632/529, loss: 0.0013432024279609323
2023-01-24 09:01:14.450020: step: 636/529, loss: 0.00417986698448658
2023-01-24 09:01:15.513360: step: 640/529, loss: 0.00021822468261234462
2023-01-24 09:01:16.580987: step: 644/529, loss: 0.0008427880238741636
2023-01-24 09:01:17.657911: step: 648/529, loss: 0.008065682835876942
2023-01-24 09:01:18.743950: step: 652/529, loss: 0.0015927249332889915
2023-01-24 09:01:19.809112: step: 656/529, loss: 0.00033644938957877457
2023-01-24 09:01:20.878356: step: 660/529, loss: 0.0022307627368718386
2023-01-24 09:01:21.969442: step: 664/529, loss: 0.002486559795215726
2023-01-24 09:01:23.058638: step: 668/529, loss: 0.0035985014401376247
2023-01-24 09:01:24.143321: step: 672/529, loss: 0.001727428869344294
2023-01-24 09:01:25.219751: step: 676/529, loss: 0.004708203487098217
2023-01-24 09:01:26.291483: step: 680/529, loss: 0.0029380577616393566
2023-01-24 09:01:27.367342: step: 684/529, loss: 0.004313901532441378
2023-01-24 09:01:28.443852: step: 688/529, loss: 0.002098947297781706
2023-01-24 09:01:29.504359: step: 692/529, loss: 0.0014363566879183054
2023-01-24 09:01:30.594333: step: 696/529, loss: 0.0016961208311840892
2023-01-24 09:01:31.683711: step: 700/529, loss: 0.011711465194821358
2023-01-24 09:01:32.741521: step: 704/529, loss: 0.023736581206321716
2023-01-24 09:01:33.794548: step: 708/529, loss: 0.003962870687246323
2023-01-24 09:01:34.856058: step: 712/529, loss: 0.0026871052104979753
2023-01-24 09:01:35.926834: step: 716/529, loss: 0.0044683245941996574
2023-01-24 09:01:36.996835: step: 720/529, loss: 0.0010794788831844926
2023-01-24 09:01:38.107083: step: 724/529, loss: 0.002859567292034626
2023-01-24 09:01:39.177636: step: 728/529, loss: 0.0028695364017039537
2023-01-24 09:01:40.266507: step: 732/529, loss: 0.0017105877632275224
2023-01-24 09:01:41.338824: step: 736/529, loss: 0.0015929468208923936
2023-01-24 09:01:42.418545: step: 740/529, loss: 0.0005045856814831495
2023-01-24 09:01:43.491138: step: 744/529, loss: 0.00014082345296628773
2023-01-24 09:01:44.579615: step: 748/529, loss: 0.0057590720243752
2023-01-24 09:01:45.654832: step: 752/529, loss: 0.003147656796500087
2023-01-24 09:01:46.732445: step: 756/529, loss: 0.01637602038681507
2023-01-24 09:01:47.801543: step: 760/529, loss: 0.0022980000358074903
2023-01-24 09:01:48.867385: step: 764/529, loss: 0.003147440729662776
2023-01-24 09:01:49.923282: step: 768/529, loss: 0.0005454433849081397
2023-01-24 09:01:50.986837: step: 772/529, loss: 0.007334181107580662
2023-01-24 09:01:52.066774: step: 776/529, loss: 0.0076117683202028275
2023-01-24 09:01:53.138188: step: 780/529, loss: 0.025856632739305496
2023-01-24 09:01:54.204550: step: 784/529, loss: 0.003416971303522587
2023-01-24 09:01:55.282925: step: 788/529, loss: 0.0033766631968319416
2023-01-24 09:01:56.372040: step: 792/529, loss: 0.002056500408798456
2023-01-24 09:01:57.439671: step: 796/529, loss: 5.327885446604341e-05
2023-01-24 09:01:58.525034: step: 800/529, loss: 0.0005987496115267277
2023-01-24 09:01:59.602794: step: 804/529, loss: 0.0027309113647788763
2023-01-24 09:02:00.676634: step: 808/529, loss: 0.0005045857396908104
2023-01-24 09:02:01.751068: step: 812/529, loss: 7.377019755949732e-06
2023-01-24 09:02:02.820353: step: 816/529, loss: 0.005275465548038483
2023-01-24 09:02:03.919209: step: 820/529, loss: 0.0006710027228109539
2023-01-24 09:02:04.995394: step: 824/529, loss: 0.011098587885499
2023-01-24 09:02:06.071684: step: 828/529, loss: 0.019840924069285393
2023-01-24 09:02:07.162626: step: 832/529, loss: 0.0003957364824600518
2023-01-24 09:02:08.234589: step: 836/529, loss: 0.007990744896233082
2023-01-24 09:02:09.303820: step: 840/529, loss: 0.00018548700609244406
2023-01-24 09:02:10.368494: step: 844/529, loss: 0.0005949554615654051
2023-01-24 09:02:11.457166: step: 848/529, loss: 0.002382143633440137
2023-01-24 09:02:12.529958: step: 852/529, loss: 0.013774306513369083
2023-01-24 09:02:13.612818: step: 856/529, loss: 0.0020129827316850424
2023-01-24 09:02:14.671005: step: 860/529, loss: 0.0001959400251507759
2023-01-24 09:02:15.739339: step: 864/529, loss: 0.002107658889144659
2023-01-24 09:02:16.837116: step: 868/529, loss: 0.014242433942854404
2023-01-24 09:02:17.914835: step: 872/529, loss: 0.0010067049879580736
2023-01-24 09:02:18.995035: step: 876/529, loss: 0.005846137180924416
2023-01-24 09:02:20.073686: step: 880/529, loss: 0.0004147252475377172
2023-01-24 09:02:21.147368: step: 884/529, loss: 0.004995714407414198
2023-01-24 09:02:22.200333: step: 888/529, loss: 0.001140714855864644
2023-01-24 09:02:23.278521: step: 892/529, loss: 0.0021672435104846954
2023-01-24 09:02:24.339786: step: 896/529, loss: 0.0013585336273536086
2023-01-24 09:02:25.425807: step: 900/529, loss: 0.003301621414721012
2023-01-24 09:02:26.509234: step: 904/529, loss: 0.002283631358295679
2023-01-24 09:02:27.572945: step: 908/529, loss: 0.004097479861229658
2023-01-24 09:02:28.644143: step: 912/529, loss: 0.0033491672948002815
2023-01-24 09:02:29.718220: step: 916/529, loss: 0.0006542227929458022
2023-01-24 09:02:30.789806: step: 920/529, loss: 0.0004434731090441346
2023-01-24 09:02:31.873324: step: 924/529, loss: 0.004721059463918209
2023-01-24 09:02:32.947838: step: 928/529, loss: 0.00035630050115287304
2023-01-24 09:02:34.037647: step: 932/529, loss: 0.002155991503968835
2023-01-24 09:02:35.116292: step: 936/529, loss: 0.0004280532302800566
2023-01-24 09:02:36.205398: step: 940/529, loss: 0.0010875569423660636
2023-01-24 09:02:37.288627: step: 944/529, loss: 0.0002769070561043918
2023-01-24 09:02:38.350319: step: 948/529, loss: 5.664702985086478e-05
2023-01-24 09:02:39.440072: step: 952/529, loss: 0.00240424950607121
2023-01-24 09:02:40.501782: step: 956/529, loss: 0.0035321670584380627
2023-01-24 09:02:41.582293: step: 960/529, loss: 0.010955289006233215
2023-01-24 09:02:42.651431: step: 964/529, loss: 0.001727513736113906
2023-01-24 09:02:43.736833: step: 968/529, loss: 0.0005645964411087334
2023-01-24 09:02:44.825497: step: 972/529, loss: 0.015866288915276527
2023-01-24 09:02:45.900263: step: 976/529, loss: 0.023438313975930214
2023-01-24 09:02:46.974514: step: 980/529, loss: 0.00012244908430147916
2023-01-24 09:02:48.048976: step: 984/529, loss: 0.00037967320531606674
2023-01-24 09:02:49.116228: step: 988/529, loss: 0.00013209758617449552
2023-01-24 09:02:50.191995: step: 992/529, loss: 0.0010998069774359465
2023-01-24 09:02:51.281989: step: 996/529, loss: 0.0041693770326673985
2023-01-24 09:02:52.347648: step: 1000/529, loss: 0.0016989033902063966
2023-01-24 09:02:53.444733: step: 1004/529, loss: 0.0012132319388911128
2023-01-24 09:02:54.492740: step: 1008/529, loss: 0.0008248412632383406
2023-01-24 09:02:55.563791: step: 1012/529, loss: 0.0007059279014356434
2023-01-24 09:02:56.640711: step: 1016/529, loss: 0.0009574407013133168
2023-01-24 09:02:57.708006: step: 1020/529, loss: 0.0033111919183284044
2023-01-24 09:02:58.784995: step: 1024/529, loss: 0.007435535080730915
2023-01-24 09:02:59.841929: step: 1028/529, loss: 0.0003497051075100899
2023-01-24 09:03:00.907194: step: 1032/529, loss: 0.0013905841624364257
2023-01-24 09:03:01.985776: step: 1036/529, loss: 0.006318611558526754
2023-01-24 09:03:03.055739: step: 1040/529, loss: 0.0017095108050853014
2023-01-24 09:03:04.133872: step: 1044/529, loss: 0.0034974359441548586
2023-01-24 09:03:05.212067: step: 1048/529, loss: 0.0019471794366836548
2023-01-24 09:03:06.305550: step: 1052/529, loss: 0.0007004099315963686
2023-01-24 09:03:07.384858: step: 1056/529, loss: 0.007734659127891064
2023-01-24 09:03:08.457445: step: 1060/529, loss: 0.004697005730122328
2023-01-24 09:03:09.523522: step: 1064/529, loss: 0.0010571939637884498
2023-01-24 09:03:10.601066: step: 1068/529, loss: 0.0003072860126849264
2023-01-24 09:03:11.670776: step: 1072/529, loss: 0.0023033826146274805
2023-01-24 09:03:12.742079: step: 1076/529, loss: 0.0007356511778198183
2023-01-24 09:03:13.844535: step: 1080/529, loss: 0.006206228863447905
2023-01-24 09:03:14.910749: step: 1084/529, loss: 1.8731745512923226e-05
2023-01-24 09:03:15.984033: step: 1088/529, loss: 0.0010727845365181565
2023-01-24 09:03:17.062899: step: 1092/529, loss: 0.0033734359312802553
2023-01-24 09:03:18.124425: step: 1096/529, loss: 0.014654737897217274
2023-01-24 09:03:19.207818: step: 1100/529, loss: 0.0009916258277371526
2023-01-24 09:03:20.267300: step: 1104/529, loss: 0.0013614826602861285
2023-01-24 09:03:21.353343: step: 1108/529, loss: 0.05653456971049309
2023-01-24 09:03:22.427909: step: 1112/529, loss: 0.012455425225198269
2023-01-24 09:03:23.492067: step: 1116/529, loss: 0.0074430773966014385
2023-01-24 09:03:24.557291: step: 1120/529, loss: 0.00229323236271739
2023-01-24 09:03:25.635385: step: 1124/529, loss: 0.005573911126703024
2023-01-24 09:03:26.732899: step: 1128/529, loss: 0.008381973020732403
2023-01-24 09:03:27.816686: step: 1132/529, loss: 0.0016428804956376553
2023-01-24 09:03:28.878486: step: 1136/529, loss: 0.000961322570219636
2023-01-24 09:03:29.951881: step: 1140/529, loss: 0.0028468400705605745
2023-01-24 09:03:31.033949: step: 1144/529, loss: 1.7321572158834897e-05
2023-01-24 09:03:32.104062: step: 1148/529, loss: 0.004201015457510948
2023-01-24 09:03:33.179949: step: 1152/529, loss: 0.006543593946844339
2023-01-24 09:03:34.268045: step: 1156/529, loss: 0.002083392348140478
2023-01-24 09:03:35.329765: step: 1160/529, loss: 0.0002069090260192752
2023-01-24 09:03:36.397942: step: 1164/529, loss: 0.0020632827654480934
2023-01-24 09:03:37.477026: step: 1168/529, loss: 0.0005716446321457624
2023-01-24 09:03:38.538607: step: 1172/529, loss: 0.008840794675052166
2023-01-24 09:03:39.631770: step: 1176/529, loss: 0.002881059655919671
2023-01-24 09:03:40.693767: step: 1180/529, loss: 0.0035947225987911224
2023-01-24 09:03:41.767627: step: 1184/529, loss: 0.00636895839124918
2023-01-24 09:03:42.835358: step: 1188/529, loss: 0.015454822219908237
2023-01-24 09:03:43.926811: step: 1192/529, loss: 5.2436520491028205e-05
2023-01-24 09:03:44.991638: step: 1196/529, loss: 0.0006554363062605262
2023-01-24 09:03:46.071732: step: 1200/529, loss: 0.0036376938223838806
2023-01-24 09:03:47.146626: step: 1204/529, loss: 0.0006328403833322227
2023-01-24 09:03:48.224563: step: 1208/529, loss: 0.00024968371144495904
2023-01-24 09:03:49.283806: step: 1212/529, loss: 6.73434478812851e-05
2023-01-24 09:03:50.344075: step: 1216/529, loss: 1.1594082025112584e-05
2023-01-24 09:03:51.415562: step: 1220/529, loss: 0.0025993227027356625
2023-01-24 09:03:52.490370: step: 1224/529, loss: 0.0008273287676274776
2023-01-24 09:03:53.568850: step: 1228/529, loss: 0.00030462435097433627
2023-01-24 09:03:54.642663: step: 1232/529, loss: 0.0008110857452265918
2023-01-24 09:03:55.717802: step: 1236/529, loss: 0.009415808133780956
2023-01-24 09:03:56.780846: step: 1240/529, loss: 0.00804172083735466
2023-01-24 09:03:57.851880: step: 1244/529, loss: 0.00652984669432044
2023-01-24 09:03:58.952114: step: 1248/529, loss: 6.674671749351546e-05
2023-01-24 09:04:00.016872: step: 1252/529, loss: 0.0021721862722188234
2023-01-24 09:04:01.105183: step: 1256/529, loss: 0.005228969734162092
2023-01-24 09:04:02.200675: step: 1260/529, loss: 0.0012572129489853978
2023-01-24 09:04:03.270456: step: 1264/529, loss: 0.007516874931752682
2023-01-24 09:04:04.374370: step: 1268/529, loss: 8.773025911068544e-05
2023-01-24 09:04:05.455180: step: 1272/529, loss: 3.598104740376584e-05
2023-01-24 09:04:06.542472: step: 1276/529, loss: 0.0027793648187071085
2023-01-24 09:04:07.612412: step: 1280/529, loss: 0.0015998753951862454
2023-01-24 09:04:08.690632: step: 1284/529, loss: 0.004523026756942272
2023-01-24 09:04:09.766941: step: 1288/529, loss: 0.0004491481522563845
2023-01-24 09:04:10.845536: step: 1292/529, loss: 0.004214296117424965
2023-01-24 09:04:11.925065: step: 1296/529, loss: 0.0004579112573992461
2023-01-24 09:04:12.988236: step: 1300/529, loss: 0.0010065702954307199
2023-01-24 09:04:14.094821: step: 1304/529, loss: 0.017643973231315613
2023-01-24 09:04:15.191991: step: 1308/529, loss: 0.006803768686950207
2023-01-24 09:04:16.267840: step: 1312/529, loss: 0.0012831541243940592
2023-01-24 09:04:17.343274: step: 1316/529, loss: 0.0032608886249363422
2023-01-24 09:04:18.403419: step: 1320/529, loss: 0.0017519196262583137
2023-01-24 09:04:19.468483: step: 1324/529, loss: 0.0032986635342240334
2023-01-24 09:04:20.523132: step: 1328/529, loss: 4.6117744204821065e-05
2023-01-24 09:04:21.599970: step: 1332/529, loss: 0.0014522559940814972
2023-01-24 09:04:22.672849: step: 1336/529, loss: 0.004566948860883713
2023-01-24 09:04:23.732788: step: 1340/529, loss: 0.0013769244542345405
2023-01-24 09:04:24.814708: step: 1344/529, loss: 0.002909476635977626
2023-01-24 09:04:25.890874: step: 1348/529, loss: 0.00917851272970438
2023-01-24 09:04:26.968947: step: 1352/529, loss: 0.003980763256549835
2023-01-24 09:04:28.047226: step: 1356/529, loss: 0.0024915789254009724
2023-01-24 09:04:29.115065: step: 1360/529, loss: 0.0012534555280581117
2023-01-24 09:04:30.207491: step: 1364/529, loss: 0.02174685150384903
2023-01-24 09:04:31.271614: step: 1368/529, loss: 0.010201332159340382
2023-01-24 09:04:32.378068: step: 1372/529, loss: 0.0005428955773822963
2023-01-24 09:04:33.447911: step: 1376/529, loss: 4.276012987247668e-05
2023-01-24 09:04:34.510916: step: 1380/529, loss: 0.00165741634555161
2023-01-24 09:04:35.591961: step: 1384/529, loss: 0.014200867153704166
2023-01-24 09:04:36.649242: step: 1388/529, loss: 8.947202877607197e-05
2023-01-24 09:04:37.719635: step: 1392/529, loss: 0.0011852295137941837
2023-01-24 09:04:38.790718: step: 1396/529, loss: 0.0006104173371568322
2023-01-24 09:04:39.852432: step: 1400/529, loss: 0.001817601383663714
2023-01-24 09:04:40.915815: step: 1404/529, loss: 0.005933358334004879
2023-01-24 09:04:41.994538: step: 1408/529, loss: 2.9284942684171256e-06
2023-01-24 09:04:43.090573: step: 1412/529, loss: 0.010107898153364658
2023-01-24 09:04:44.169127: step: 1416/529, loss: 0.009911715053021908
2023-01-24 09:04:45.262480: step: 1420/529, loss: 6.0493066484923474e-06
2023-01-24 09:04:46.329411: step: 1424/529, loss: 0.00022279111726675183
2023-01-24 09:04:47.401353: step: 1428/529, loss: 0.005169587209820747
2023-01-24 09:04:48.472491: step: 1432/529, loss: 6.311206379905343e-05
2023-01-24 09:04:49.547487: step: 1436/529, loss: 0.005723575595766306
2023-01-24 09:04:50.617414: step: 1440/529, loss: 1.195803491782499e-07
2023-01-24 09:04:51.681237: step: 1444/529, loss: 0.0015658182092010975
2023-01-24 09:04:52.764129: step: 1448/529, loss: 0.0014453926123678684
2023-01-24 09:04:53.855086: step: 1452/529, loss: 0.00023209606297314167
2023-01-24 09:04:54.930653: step: 1456/529, loss: 0.003008805913850665
2023-01-24 09:04:56.014402: step: 1460/529, loss: 0.002512269653379917
2023-01-24 09:04:57.078580: step: 1464/529, loss: 0.005969419609755278
2023-01-24 09:04:58.169504: step: 1468/529, loss: 0.0013168842997401953
2023-01-24 09:04:59.246362: step: 1472/529, loss: 0.013506489805877209
2023-01-24 09:05:00.320854: step: 1476/529, loss: 0.0159147996455431
2023-01-24 09:05:01.391343: step: 1480/529, loss: 0.0004716266121249646
2023-01-24 09:05:02.482297: step: 1484/529, loss: 0.0039177448488771915
2023-01-24 09:05:03.553907: step: 1488/529, loss: 0.001691853511147201
2023-01-24 09:05:04.627904: step: 1492/529, loss: 0.002796584041789174
2023-01-24 09:05:05.688368: step: 1496/529, loss: 0.0006318148225545883
2023-01-24 09:05:06.759592: step: 1500/529, loss: 0.001606442965567112
2023-01-24 09:05:07.854113: step: 1504/529, loss: 0.0017404399113729596
2023-01-24 09:05:08.922511: step: 1508/529, loss: 6.433537055272609e-05
2023-01-24 09:05:10.006781: step: 1512/529, loss: 0.000550813740119338
2023-01-24 09:05:11.087676: step: 1516/529, loss: 0.005006174556910992
2023-01-24 09:05:12.167920: step: 1520/529, loss: 0.0002731724816840142
2023-01-24 09:05:13.242523: step: 1524/529, loss: 0.008615589700639248
2023-01-24 09:05:14.310525: step: 1528/529, loss: 0.005340637639164925
2023-01-24 09:05:15.397495: step: 1532/529, loss: 0.002051289426162839
2023-01-24 09:05:16.480440: step: 1536/529, loss: 0.006582419387996197
2023-01-24 09:05:17.555554: step: 1540/529, loss: 8.828871500554669e-08
2023-01-24 09:05:18.628508: step: 1544/529, loss: 0.0024221024941653013
2023-01-24 09:05:19.692234: step: 1548/529, loss: 0.001180012826807797
2023-01-24 09:05:20.751638: step: 1552/529, loss: 0.0013095546746626496
2023-01-24 09:05:21.840793: step: 1556/529, loss: 0.0002072866482194513
2023-01-24 09:05:22.924021: step: 1560/529, loss: 0.0016030482947826385
2023-01-24 09:05:24.013352: step: 1564/529, loss: 0.015543331392109394
2023-01-24 09:05:25.094366: step: 1568/529, loss: 0.00036658262251876295
2023-01-24 09:05:26.184157: step: 1572/529, loss: 0.0024295509792864323
2023-01-24 09:05:27.277575: step: 1576/529, loss: 0.006785272154957056
2023-01-24 09:05:28.360635: step: 1580/529, loss: 0.004670398309826851
2023-01-24 09:05:29.431267: step: 1584/529, loss: 0.0018465934554114938
2023-01-24 09:05:30.508602: step: 1588/529, loss: 0.00019738740229513496
2023-01-24 09:05:31.587464: step: 1592/529, loss: 8.536456880392507e-05
2023-01-24 09:05:32.661439: step: 1596/529, loss: 0.00225271750241518
2023-01-24 09:05:33.750995: step: 1600/529, loss: 0.003619945840910077
2023-01-24 09:05:34.828765: step: 1604/529, loss: 0.0015065292827785015
2023-01-24 09:05:35.897862: step: 1608/529, loss: 0.0011722138151526451
2023-01-24 09:05:36.963504: step: 1612/529, loss: 0.004720865283161402
2023-01-24 09:05:38.040903: step: 1616/529, loss: 0.0004522582166828215
2023-01-24 09:05:39.130598: step: 1620/529, loss: 0.02775600738823414
2023-01-24 09:05:40.202032: step: 1624/529, loss: 0.0003340844705235213
2023-01-24 09:05:41.280389: step: 1628/529, loss: 0.00024691305588930845
2023-01-24 09:05:42.348585: step: 1632/529, loss: 0.00029908629949204624
2023-01-24 09:05:43.433182: step: 1636/529, loss: 0.0063592176884412766
2023-01-24 09:05:44.513524: step: 1640/529, loss: 0.002701652003452182
2023-01-24 09:05:45.597186: step: 1644/529, loss: 0.009289263747632504
2023-01-24 09:05:46.680769: step: 1648/529, loss: 0.0001726174814393744
2023-01-24 09:05:47.764584: step: 1652/529, loss: 0.0017450257437303662
2023-01-24 09:05:48.856649: step: 1656/529, loss: 0.004294929094612598
2023-01-24 09:05:49.928964: step: 1660/529, loss: 1.2603007235156838e-05
2023-01-24 09:05:51.001578: step: 1664/529, loss: 0.00244903308339417
2023-01-24 09:05:52.075306: step: 1668/529, loss: 0.0025717755779623985
2023-01-24 09:05:53.171160: step: 1672/529, loss: 0.008560407906770706
2023-01-24 09:05:54.242758: step: 1676/529, loss: 0.0027694785967469215
2023-01-24 09:05:55.316978: step: 1680/529, loss: 0.004802444484084845
2023-01-24 09:05:56.401645: step: 1684/529, loss: 0.003135088598355651
2023-01-24 09:05:57.475696: step: 1688/529, loss: 0.009954369626939297
2023-01-24 09:05:58.543641: step: 1692/529, loss: 0.010034805163741112
2023-01-24 09:05:59.625528: step: 1696/529, loss: 0.0026271215174347162
2023-01-24 09:06:00.710815: step: 1700/529, loss: 0.002825000789016485
2023-01-24 09:06:01.785013: step: 1704/529, loss: 0.00971689261496067
2023-01-24 09:06:02.879620: step: 1708/529, loss: 0.004913742188364267
2023-01-24 09:06:03.952968: step: 1712/529, loss: 0.00012328309821896255
2023-01-24 09:06:05.025687: step: 1716/529, loss: 0.005492243450134993
2023-01-24 09:06:06.099585: step: 1720/529, loss: 0.0016261449782177806
2023-01-24 09:06:07.182554: step: 1724/529, loss: 0.009109891019761562
2023-01-24 09:06:08.250584: step: 1728/529, loss: 0.0014789358247071505
2023-01-24 09:06:09.315098: step: 1732/529, loss: 0.0028209127485752106
2023-01-24 09:06:10.383569: step: 1736/529, loss: 0.0003853342786896974
2023-01-24 09:06:11.451289: step: 1740/529, loss: 0.00039297869079746306
2023-01-24 09:06:12.515818: step: 1744/529, loss: 6.063833643565886e-05
2023-01-24 09:06:13.603346: step: 1748/529, loss: 2.0009640138596296e-05
2023-01-24 09:06:14.675415: step: 1752/529, loss: 0.0022021473851054907
2023-01-24 09:06:15.751458: step: 1756/529, loss: 0.0009158815373666584
2023-01-24 09:06:16.813762: step: 1760/529, loss: 0.0018402691930532455
2023-01-24 09:06:17.897719: step: 1764/529, loss: 9.479855361860245e-05
2023-01-24 09:06:18.990688: step: 1768/529, loss: 0.002112946705892682
2023-01-24 09:06:20.067278: step: 1772/529, loss: 0.00384847866371274
2023-01-24 09:06:21.135866: step: 1776/529, loss: 0.0003655296750366688
2023-01-24 09:06:22.219655: step: 1780/529, loss: 0.0007998215733096004
2023-01-24 09:06:23.303079: step: 1784/529, loss: 0.0012237696209922433
2023-01-24 09:06:24.386633: step: 1788/529, loss: 0.0051121520809829235
2023-01-24 09:06:25.445400: step: 1792/529, loss: 0.0017046780558302999
2023-01-24 09:06:26.515389: step: 1796/529, loss: 0.0
2023-01-24 09:06:27.593353: step: 1800/529, loss: 0.0007969383150339127
2023-01-24 09:06:28.659782: step: 1804/529, loss: 0.004054985474795103
2023-01-24 09:06:29.727521: step: 1808/529, loss: 0.0022393804974853992
2023-01-24 09:06:30.800990: step: 1812/529, loss: 0.0010669297771528363
2023-01-24 09:06:31.881259: step: 1816/529, loss: 0.0006529333186335862
2023-01-24 09:06:32.958601: step: 1820/529, loss: 0.006599863525480032
2023-01-24 09:06:34.027147: step: 1824/529, loss: 0.0020184549503028393
2023-01-24 09:06:35.102785: step: 1828/529, loss: 0.002421551151201129
2023-01-24 09:06:36.167872: step: 1832/529, loss: 1.8109219581674552e-06
2023-01-24 09:06:37.249579: step: 1836/529, loss: 0.0013850892428308725
2023-01-24 09:06:38.319251: step: 1840/529, loss: 0.004276327323168516
2023-01-24 09:06:39.386922: step: 1844/529, loss: 0.004120286554098129
2023-01-24 09:06:40.465908: step: 1848/529, loss: 0.004482806660234928
2023-01-24 09:06:41.528689: step: 1852/529, loss: 1.4339137123897672e-05
2023-01-24 09:06:42.601679: step: 1856/529, loss: 0.007714579347521067
2023-01-24 09:06:43.701623: step: 1860/529, loss: 0.0035939589142799377
2023-01-24 09:06:44.783017: step: 1864/529, loss: 0.0004403050697874278
2023-01-24 09:06:45.834529: step: 1868/529, loss: 2.0488961638420733e-07
2023-01-24 09:06:46.931755: step: 1872/529, loss: 0.006935497280210257
2023-01-24 09:06:48.010355: step: 1876/529, loss: 0.001358131063170731
2023-01-24 09:06:49.096871: step: 1880/529, loss: 0.004059590399265289
2023-01-24 09:06:50.165493: step: 1884/529, loss: 0.0001957083004526794
2023-01-24 09:06:51.247475: step: 1888/529, loss: 0.003749070456251502
2023-01-24 09:06:52.316642: step: 1892/529, loss: 1.3325626241567079e-05
2023-01-24 09:06:53.371103: step: 1896/529, loss: 0.003497549332678318
2023-01-24 09:06:54.454106: step: 1900/529, loss: 0.009957300499081612
2023-01-24 09:06:55.543240: step: 1904/529, loss: 0.003748676972463727
2023-01-24 09:06:56.634278: step: 1908/529, loss: 0.002384974854066968
2023-01-24 09:06:57.714121: step: 1912/529, loss: 0.0043234494514763355
2023-01-24 09:06:58.807240: step: 1916/529, loss: 0.03477722406387329
2023-01-24 09:06:59.882148: step: 1920/529, loss: 0.010558787733316422
2023-01-24 09:07:00.953763: step: 1924/529, loss: 0.003296146634966135
2023-01-24 09:07:02.023181: step: 1928/529, loss: 0.003266238607466221
2023-01-24 09:07:03.093512: step: 1932/529, loss: 0.0004403567872941494
2023-01-24 09:07:04.176535: step: 1936/529, loss: 0.0021226985845714808
2023-01-24 09:07:05.260631: step: 1940/529, loss: 0.0006780982366763055
2023-01-24 09:07:06.342355: step: 1944/529, loss: 0.00035880677751265466
2023-01-24 09:07:07.410678: step: 1948/529, loss: 0.0006868747295811772
2023-01-24 09:07:08.481226: step: 1952/529, loss: 0.000473122694529593
2023-01-24 09:07:09.550059: step: 1956/529, loss: 0.0008916643564589322
2023-01-24 09:07:10.630944: step: 1960/529, loss: 0.00961329322308302
2023-01-24 09:07:11.710607: step: 1964/529, loss: 0.0009683585958555341
2023-01-24 09:07:12.781642: step: 1968/529, loss: 0.005597032606601715
2023-01-24 09:07:13.855342: step: 1972/529, loss: 0.0009607592946849763
2023-01-24 09:07:14.926689: step: 1976/529, loss: 0.0030667155515402555
2023-01-24 09:07:16.008919: step: 1980/529, loss: 0.00414391839876771
2023-01-24 09:07:17.090379: step: 1984/529, loss: 0.007180177606642246
2023-01-24 09:07:18.172732: step: 1988/529, loss: 0.0014331936836242676
2023-01-24 09:07:19.244402: step: 1992/529, loss: 0.0032149862963706255
2023-01-24 09:07:20.309339: step: 1996/529, loss: 0.0005135077517479658
2023-01-24 09:07:21.384457: step: 2000/529, loss: 0.0032334676943719387
2023-01-24 09:07:22.460477: step: 2004/529, loss: 0.0012933633988723159
2023-01-24 09:07:23.518016: step: 2008/529, loss: 0.002671900438144803
2023-01-24 09:07:24.603805: step: 2012/529, loss: 0.00028709357138723135
2023-01-24 09:07:25.676435: step: 2016/529, loss: 0.0008177050622180104
2023-01-24 09:07:26.768036: step: 2020/529, loss: 0.007460963446646929
2023-01-24 09:07:27.843692: step: 2024/529, loss: 0.006277134642004967
2023-01-24 09:07:28.922494: step: 2028/529, loss: 0.0037806753534823656
2023-01-24 09:07:30.004272: step: 2032/529, loss: 0.0009752631303854287
2023-01-24 09:07:31.085614: step: 2036/529, loss: 3.725290076417309e-10
2023-01-24 09:07:32.182187: step: 2040/529, loss: 0.002428225474432111
2023-01-24 09:07:33.259116: step: 2044/529, loss: 0.002150231972336769
2023-01-24 09:07:34.330559: step: 2048/529, loss: 0.00016201801190618426
2023-01-24 09:07:35.397959: step: 2052/529, loss: 0.0
2023-01-24 09:07:36.472627: step: 2056/529, loss: 0.014403726905584335
2023-01-24 09:07:37.547276: step: 2060/529, loss: 0.0003406417672522366
2023-01-24 09:07:38.631081: step: 2064/529, loss: 0.0076192887499928474
2023-01-24 09:07:39.719232: step: 2068/529, loss: 0.00010909307457040995
2023-01-24 09:07:40.791433: step: 2072/529, loss: 0.02076174132525921
2023-01-24 09:07:41.873614: step: 2076/529, loss: 0.003686367766931653
2023-01-24 09:07:42.944842: step: 2080/529, loss: 0.0005375833134166896
2023-01-24 09:07:44.012105: step: 2084/529, loss: 0.001783317537046969
2023-01-24 09:07:45.085256: step: 2088/529, loss: 0.00028340835706330836
2023-01-24 09:07:46.175401: step: 2092/529, loss: 0.00456823967397213
2023-01-24 09:07:47.235966: step: 2096/529, loss: 0.005551275797188282
2023-01-24 09:07:48.310669: step: 2100/529, loss: 0.009063190780580044
2023-01-24 09:07:49.400653: step: 2104/529, loss: 0.009672529064118862
2023-01-24 09:07:50.475715: step: 2108/529, loss: 0.004472561180591583
2023-01-24 09:07:51.556408: step: 2112/529, loss: 0.0003142780333291739
2023-01-24 09:07:52.634397: step: 2116/529, loss: 1.1137221918033902e-06
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3376191750790252, 'r': 0.29918055932050247, 'f1': 0.3172397480118809}, 'combined': 0.233755603798228, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3314224949575889, 'r': 0.29212699693412475, 'f1': 0.3105365634238668}, 'combined': 0.20273371498138454, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36228352381783285, 'r': 0.3581588537174401, 'f1': 0.3602093815058987}, 'combined': 0.2654174390043464, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35743685856996116, 'r': 0.31242872472429506, 'f1': 0.3334207479156774}, 'combined': 0.21767364889831786, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3813744075017809, 'r': 0.3430198655708618, 'f1': 0.3611817565551332}, 'combined': 0.2661339258827297, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.37147512625212076, 'r': 0.30694498023957406, 'f1': 0.3361410553604998}, 'combined': 0.21944960090892734, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 16}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36228352381783285, 'r': 0.3581588537174401, 'f1': 0.3602093815058987}, 'combined': 0.2654174390043464, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35743685856996116, 'r': 0.31242872472429506, 'f1': 0.3334207479156774}, 'combined': 0.21767364889831786, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
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 09:10:28.680100: step: 4/529, loss: 0.004774351604282856
2023-01-24 09:10:29.748315: step: 8/529, loss: 0.00011110320338048041
2023-01-24 09:10:30.812800: step: 12/529, loss: 0.00041783173219300807
2023-01-24 09:10:31.886325: step: 16/529, loss: 0.00014816332259215415
2023-01-24 09:10:32.959028: step: 20/529, loss: 0.002932025818154216
2023-01-24 09:10:34.021355: step: 24/529, loss: 0.00035048782592639327
2023-01-24 09:10:35.075490: step: 28/529, loss: 0.004982681013643742
2023-01-24 09:10:36.129480: step: 32/529, loss: 2.1233639927231707e-05
2023-01-24 09:10:37.186374: step: 36/529, loss: 0.00013713899534195662
2023-01-24 09:10:38.247283: step: 40/529, loss: 0.00028068991377949715
2023-01-24 09:10:39.300813: step: 44/529, loss: 0.0005943615105934441
2023-01-24 09:10:40.359526: step: 48/529, loss: 0.0031879248563200235
2023-01-24 09:10:41.407237: step: 52/529, loss: 8.189268555724993e-05
2023-01-24 09:10:42.465187: step: 56/529, loss: 0.0006212772568687797
2023-01-24 09:10:43.513949: step: 60/529, loss: 0.00011823880049632862
2023-01-24 09:10:44.572560: step: 64/529, loss: 0.0012236885959282517
2023-01-24 09:10:45.632494: step: 68/529, loss: 0.0004854573926422745
2023-01-24 09:10:46.692438: step: 72/529, loss: 0.007082747295498848
2023-01-24 09:10:47.753919: step: 76/529, loss: 0.0004908978589810431
2023-01-24 09:10:48.826235: step: 80/529, loss: 0.00037303700810298324
2023-01-24 09:10:49.887750: step: 84/529, loss: 0.0001519659417681396
2023-01-24 09:10:50.939143: step: 88/529, loss: 0.0024474391248077154
2023-01-24 09:10:51.994957: step: 92/529, loss: 3.118909080512822e-05
2023-01-24 09:10:53.055537: step: 96/529, loss: 0.010022071190178394
2023-01-24 09:10:54.141142: step: 100/529, loss: 0.0076587870717048645
2023-01-24 09:10:55.205015: step: 104/529, loss: 0.0016353769460693002
2023-01-24 09:10:56.271818: step: 108/529, loss: 7.432909478666261e-05
2023-01-24 09:10:57.317593: step: 112/529, loss: 0.0013143441174179316
2023-01-24 09:10:58.405453: step: 116/529, loss: 0.0016834146808832884
2023-01-24 09:10:59.469138: step: 120/529, loss: 0.0009339546086266637
2023-01-24 09:11:00.538077: step: 124/529, loss: 5.631415479001589e-05
2023-01-24 09:11:01.596998: step: 128/529, loss: 0.0022102429065853357
2023-01-24 09:11:02.667927: step: 132/529, loss: 0.002972292946651578
2023-01-24 09:11:03.721599: step: 136/529, loss: 0.0034958343021571636
2023-01-24 09:11:04.788708: step: 140/529, loss: 0.002566281706094742
2023-01-24 09:11:05.823923: step: 144/529, loss: 0.00019849218369927257
2023-01-24 09:11:06.914337: step: 148/529, loss: 0.005178583785891533
2023-01-24 09:11:07.981953: step: 152/529, loss: 0.002736426191404462
2023-01-24 09:11:09.052790: step: 156/529, loss: 0.007798114325851202
2023-01-24 09:11:10.132974: step: 160/529, loss: 0.0048319618217647076
2023-01-24 09:11:11.210208: step: 164/529, loss: 0.008279364556074142
2023-01-24 09:11:12.287179: step: 168/529, loss: 0.002521841088309884
2023-01-24 09:11:13.364461: step: 172/529, loss: 0.008925371803343296
2023-01-24 09:11:14.424032: step: 176/529, loss: 3.7435679587360937e-06
2023-01-24 09:11:15.501080: step: 180/529, loss: 0.0020514533389359713
2023-01-24 09:11:16.557934: step: 184/529, loss: 0.0038077435456216335
2023-01-24 09:11:17.633364: step: 188/529, loss: 0.000652316608466208
2023-01-24 09:11:18.688108: step: 192/529, loss: 2.0696195861091837e-05
2023-01-24 09:11:19.768942: step: 196/529, loss: 0.002564126392826438
2023-01-24 09:11:20.825362: step: 200/529, loss: 0.003402081085368991
2023-01-24 09:11:21.890599: step: 204/529, loss: 0.004479540046304464
2023-01-24 09:11:22.976510: step: 208/529, loss: 0.0018465116154402494
2023-01-24 09:11:24.042145: step: 212/529, loss: 0.0007151631289161742
2023-01-24 09:11:25.120853: step: 216/529, loss: 0.005244481842964888
2023-01-24 09:11:26.187110: step: 220/529, loss: 0.00010370021482231095
2023-01-24 09:11:27.257891: step: 224/529, loss: 7.456904131686315e-05
2023-01-24 09:11:28.326629: step: 228/529, loss: 0.0018638074398040771
2023-01-24 09:11:29.394987: step: 232/529, loss: 0.004323921166360378
2023-01-24 09:11:30.467282: step: 236/529, loss: 0.0007034416194073856
2023-01-24 09:11:31.559909: step: 240/529, loss: 0.0007420348119921982
2023-01-24 09:11:32.618797: step: 244/529, loss: 0.0023707980290055275
2023-01-24 09:11:33.701007: step: 248/529, loss: 0.0031798563431948423
2023-01-24 09:11:34.777255: step: 252/529, loss: 0.001064923359081149
2023-01-24 09:11:35.848212: step: 256/529, loss: 0.0013210728066042066
2023-01-24 09:11:36.927336: step: 260/529, loss: 4.597189672495006e-06
2023-01-24 09:11:37.994529: step: 264/529, loss: 0.00804111361503601
2023-01-24 09:11:39.048612: step: 268/529, loss: 4.8266265366692096e-05
2023-01-24 09:11:40.134374: step: 272/529, loss: 0.005466201342642307
2023-01-24 09:11:41.212581: step: 276/529, loss: 8.47073461045511e-05
2023-01-24 09:11:42.278574: step: 280/529, loss: 0.0015489307697862387
2023-01-24 09:11:43.350082: step: 284/529, loss: 0.0033976032864302397
2023-01-24 09:11:44.422165: step: 288/529, loss: 0.0016044657677412033
2023-01-24 09:11:45.489270: step: 292/529, loss: 6.452019442804158e-05
2023-01-24 09:11:46.557509: step: 296/529, loss: 0.0023355484008789062
2023-01-24 09:11:47.615442: step: 300/529, loss: 0.009125921875238419
2023-01-24 09:11:48.683179: step: 304/529, loss: 0.009663855656981468
2023-01-24 09:11:49.752324: step: 308/529, loss: 0.0005212817923165858
2023-01-24 09:11:50.809879: step: 312/529, loss: 0.00038913520984351635
2023-01-24 09:11:51.878544: step: 316/529, loss: 2.071810740744695e-06
2023-01-24 09:11:52.955359: step: 320/529, loss: 0.0015925494953989983
2023-01-24 09:11:54.028347: step: 324/529, loss: 6.970712274778634e-05
2023-01-24 09:11:55.098954: step: 328/529, loss: 0.004545920994132757
2023-01-24 09:11:56.171802: step: 332/529, loss: 2.40278552610107e-07
2023-01-24 09:11:57.238959: step: 336/529, loss: 0.00036701513454318047
2023-01-24 09:11:58.310513: step: 340/529, loss: 0.002165420213714242
2023-01-24 09:11:59.373781: step: 344/529, loss: 0.0015689270803704858
2023-01-24 09:12:00.451517: step: 348/529, loss: 0.0008598619024269283
2023-01-24 09:12:01.542608: step: 352/529, loss: 0.030548138543963432
2023-01-24 09:12:02.617888: step: 356/529, loss: 0.004977196920663118
2023-01-24 09:12:03.702822: step: 360/529, loss: 0.00011398706556065008
2023-01-24 09:12:04.791064: step: 364/529, loss: 0.004644823260605335
2023-01-24 09:12:05.864928: step: 368/529, loss: 0.013795222155749798
2023-01-24 09:12:06.959531: step: 372/529, loss: 0.00019335832621436566
2023-01-24 09:12:08.054677: step: 376/529, loss: 1.8577834453026298e-06
2023-01-24 09:12:09.124653: step: 380/529, loss: 0.009377739392220974
2023-01-24 09:12:10.195122: step: 384/529, loss: 0.00037509846151806414
2023-01-24 09:12:11.271831: step: 388/529, loss: 0.004540981724858284
2023-01-24 09:12:12.340377: step: 392/529, loss: 0.00012763110862579197
2023-01-24 09:12:13.434881: step: 396/529, loss: 0.009456207975745201
2023-01-24 09:12:14.503230: step: 400/529, loss: 0.0034424876794219017
2023-01-24 09:12:15.578794: step: 404/529, loss: 0.04370659962296486
2023-01-24 09:12:16.649576: step: 408/529, loss: 0.0003631363215390593
2023-01-24 09:12:17.721921: step: 412/529, loss: 0.0009669842547737062
2023-01-24 09:12:18.794845: step: 416/529, loss: 3.820407982857432e-06
2023-01-24 09:12:19.878916: step: 420/529, loss: 0.0017878817161545157
2023-01-24 09:12:20.950970: step: 424/529, loss: 0.004045877140015364
2023-01-24 09:12:22.027670: step: 428/529, loss: 0.005891798529773951
2023-01-24 09:12:23.098607: step: 432/529, loss: 0.0014330159174278378
2023-01-24 09:12:24.174434: step: 436/529, loss: 0.0009665749967098236
2023-01-24 09:12:25.236496: step: 440/529, loss: 0.002940972102805972
2023-01-24 09:12:26.333020: step: 444/529, loss: 0.0002214901032857597
2023-01-24 09:12:27.416806: step: 448/529, loss: 0.0012117965379729867
2023-01-24 09:12:28.494798: step: 452/529, loss: 0.0108401570469141
2023-01-24 09:12:29.565006: step: 456/529, loss: 0.010137693956494331
2023-01-24 09:12:30.644857: step: 460/529, loss: 0.00017200839647557586
2023-01-24 09:12:31.729084: step: 464/529, loss: 0.005317979026585817
2023-01-24 09:12:32.799594: step: 468/529, loss: 0.0014371046563610435
2023-01-24 09:12:33.889713: step: 472/529, loss: 0.001969830133020878
2023-01-24 09:12:34.977423: step: 476/529, loss: 0.0020322680938988924
2023-01-24 09:12:36.076937: step: 480/529, loss: 0.002301317173987627
2023-01-24 09:12:37.149801: step: 484/529, loss: 0.003000570461153984
2023-01-24 09:12:38.237029: step: 488/529, loss: 0.013125085271894932
2023-01-24 09:12:39.307467: step: 492/529, loss: 0.0026452532038092613
2023-01-24 09:12:40.390686: step: 496/529, loss: 0.003359744790941477
2023-01-24 09:12:41.489090: step: 500/529, loss: 0.012588279321789742
2023-01-24 09:12:42.561927: step: 504/529, loss: 0.0004936831537634134
2023-01-24 09:12:43.626577: step: 508/529, loss: 0.000453014305094257
2023-01-24 09:12:44.701802: step: 512/529, loss: 0.0014283152995631099
2023-01-24 09:12:45.773800: step: 516/529, loss: 6.273492908803746e-05
2023-01-24 09:12:46.835904: step: 520/529, loss: 0.0037453763652592897
2023-01-24 09:12:47.915676: step: 524/529, loss: 0.00708908773958683
2023-01-24 09:12:48.992579: step: 528/529, loss: 0.0003847303451038897
2023-01-24 09:12:50.062510: step: 532/529, loss: 0.0007803772459737957
2023-01-24 09:12:51.140035: step: 536/529, loss: 0.001063131378032267
2023-01-24 09:12:52.207978: step: 540/529, loss: 0.00014132454816717654
2023-01-24 09:12:53.309241: step: 544/529, loss: 0.0003259962541051209
2023-01-24 09:12:54.392508: step: 548/529, loss: 0.0010191089240834117
2023-01-24 09:12:55.476777: step: 552/529, loss: 0.0023419675417244434
2023-01-24 09:12:56.542502: step: 556/529, loss: 0.000528524920810014
2023-01-24 09:12:57.624101: step: 560/529, loss: 0.0004716124967671931
2023-01-24 09:12:58.687842: step: 564/529, loss: 0.0024010816123336554
2023-01-24 09:12:59.779167: step: 568/529, loss: 0.0007846885710023344
2023-01-24 09:13:00.875602: step: 572/529, loss: 0.002488890662789345
2023-01-24 09:13:01.972011: step: 576/529, loss: 0.00165373960044235
2023-01-24 09:13:03.049840: step: 580/529, loss: 0.008673086762428284
2023-01-24 09:13:04.133375: step: 584/529, loss: 0.0015404396690428257
2023-01-24 09:13:05.197270: step: 588/529, loss: 0.002522109542042017
2023-01-24 09:13:06.276019: step: 592/529, loss: 0.002636249642819166
2023-01-24 09:13:07.376390: step: 596/529, loss: 0.001112492405809462
2023-01-24 09:13:08.463523: step: 600/529, loss: 0.004458381794393063
2023-01-24 09:13:09.540707: step: 604/529, loss: 0.0014742023777216673
2023-01-24 09:13:10.595289: step: 608/529, loss: 0.0008885821443982422
2023-01-24 09:13:11.698314: step: 612/529, loss: 1.9904477085219696e-05
2023-01-24 09:13:12.761558: step: 616/529, loss: 0.0017006245907396078
2023-01-24 09:13:13.850276: step: 620/529, loss: 0.0014850731240585446
2023-01-24 09:13:14.918454: step: 624/529, loss: 0.00023758201859891415
2023-01-24 09:13:16.003578: step: 628/529, loss: 0.0010377351427450776
2023-01-24 09:13:17.077983: step: 632/529, loss: 0.0019140334334224463
2023-01-24 09:13:18.150083: step: 636/529, loss: 0.0023769692052155733
2023-01-24 09:13:19.222076: step: 640/529, loss: 0.000245902017923072
2023-01-24 09:13:20.298926: step: 644/529, loss: 0.002616342157125473
2023-01-24 09:13:21.378818: step: 648/529, loss: 0.0038746490608900785
2023-01-24 09:13:22.479187: step: 652/529, loss: 0.002077002776786685
2023-01-24 09:13:23.559006: step: 656/529, loss: 0.005881055723875761
2023-01-24 09:13:24.649883: step: 660/529, loss: 7.45057526785331e-09
2023-01-24 09:13:25.719433: step: 664/529, loss: 0.000414300593547523
2023-01-24 09:13:26.818226: step: 668/529, loss: 0.004773742984980345
2023-01-24 09:13:27.903601: step: 672/529, loss: 0.0036938427947461605
2023-01-24 09:13:28.989997: step: 676/529, loss: 0.0003341565898153931
2023-01-24 09:13:30.088164: step: 680/529, loss: 0.0009104507626034319
2023-01-24 09:13:31.152053: step: 684/529, loss: 5.523121217265725e-06
2023-01-24 09:13:32.223556: step: 688/529, loss: 1.7188789570354857e-05
2023-01-24 09:13:33.285595: step: 692/529, loss: 0.0007495395257137716
2023-01-24 09:13:34.355550: step: 696/529, loss: 0.0033264432568103075
2023-01-24 09:13:35.431832: step: 700/529, loss: 0.0068891653791069984
2023-01-24 09:13:36.523164: step: 704/529, loss: 0.009174483828246593
2023-01-24 09:13:37.616502: step: 708/529, loss: 0.0005347991827875376
2023-01-24 09:13:38.689033: step: 712/529, loss: 0.006793070584535599
2023-01-24 09:13:39.759252: step: 716/529, loss: 0.011829989962279797
2023-01-24 09:13:40.860468: step: 720/529, loss: 0.004367281682789326
2023-01-24 09:13:41.945846: step: 724/529, loss: 0.007348595652729273
2023-01-24 09:13:43.035408: step: 728/529, loss: 0.00039315730100497603
2023-01-24 09:13:44.115492: step: 732/529, loss: 0.009478211402893066
2023-01-24 09:13:45.203552: step: 736/529, loss: 0.0015816637314856052
2023-01-24 09:13:46.256583: step: 740/529, loss: 0.004561400506645441
2023-01-24 09:13:47.336198: step: 744/529, loss: 0.000998090603388846
2023-01-24 09:13:48.419873: step: 748/529, loss: 0.002690277760848403
2023-01-24 09:13:49.501306: step: 752/529, loss: 0.01983640529215336
2023-01-24 09:13:50.594650: step: 756/529, loss: 0.02866826020181179
2023-01-24 09:13:51.665708: step: 760/529, loss: 0.002755439840257168
2023-01-24 09:13:52.743702: step: 764/529, loss: 0.0013352558016777039
2023-01-24 09:13:53.816503: step: 768/529, loss: 0.0014271977124735713
2023-01-24 09:13:54.898677: step: 772/529, loss: 0.0022671674378216267
2023-01-24 09:13:55.992844: step: 776/529, loss: 0.0018875261303037405
2023-01-24 09:13:57.066692: step: 780/529, loss: 3.158912704748218e-06
2023-01-24 09:13:58.152358: step: 784/529, loss: 0.003514400916174054
2023-01-24 09:13:59.238100: step: 788/529, loss: 0.005634487606585026
2023-01-24 09:14:00.336082: step: 792/529, loss: 0.001252013840712607
2023-01-24 09:14:01.426123: step: 796/529, loss: 0.0008378030615858734
2023-01-24 09:14:02.495230: step: 800/529, loss: 0.00011768119293265045
2023-01-24 09:14:03.574329: step: 804/529, loss: 0.0313212051987648
2023-01-24 09:14:04.643697: step: 808/529, loss: 0.003424952272325754
2023-01-24 09:14:05.735880: step: 812/529, loss: 0.0003686647687572986
2023-01-24 09:14:06.813072: step: 816/529, loss: 0.017792463302612305
2023-01-24 09:14:07.874180: step: 820/529, loss: 0.007854940369725227
2023-01-24 09:14:08.952881: step: 824/529, loss: 0.00029206243925727904
2023-01-24 09:14:10.034909: step: 828/529, loss: 0.0015315775526687503
2023-01-24 09:14:11.141124: step: 832/529, loss: 0.00845752377063036
2023-01-24 09:14:12.231692: step: 836/529, loss: 0.00011560235725482926
2023-01-24 09:14:13.330070: step: 840/529, loss: 0.0011882432736456394
2023-01-24 09:14:14.422675: step: 844/529, loss: 0.003570557339116931
2023-01-24 09:14:15.513845: step: 848/529, loss: 7.160241511883214e-05
2023-01-24 09:14:16.599115: step: 852/529, loss: 0.0009545166394673288
2023-01-24 09:14:17.691546: step: 856/529, loss: 0.0002575825492385775
2023-01-24 09:14:18.755037: step: 860/529, loss: 0.0012334130005910993
2023-01-24 09:14:19.851713: step: 864/529, loss: 0.01737028732895851
2023-01-24 09:14:20.939086: step: 868/529, loss: 0.0054113599471747875
2023-01-24 09:14:22.003300: step: 872/529, loss: 7.68220161262434e-06
2023-01-24 09:14:23.089786: step: 876/529, loss: 0.001449385192245245
2023-01-24 09:14:24.164754: step: 880/529, loss: 0.0025277924723923206
2023-01-24 09:14:25.248987: step: 884/529, loss: 0.0007194819045253098
2023-01-24 09:14:26.336658: step: 888/529, loss: 0.006475755479186773
2023-01-24 09:14:27.414560: step: 892/529, loss: 0.0013373121619224548
2023-01-24 09:14:28.487318: step: 896/529, loss: 0.01022915355861187
2023-01-24 09:14:29.571395: step: 900/529, loss: 0.005136055406183004
2023-01-24 09:14:30.659562: step: 904/529, loss: 0.0022083797957748175
2023-01-24 09:14:31.724437: step: 908/529, loss: 0.0032370751723647118
2023-01-24 09:14:32.801525: step: 912/529, loss: 0.001199365477077663
2023-01-24 09:14:33.865992: step: 916/529, loss: 0.0008733494905754924
2023-01-24 09:14:34.950046: step: 920/529, loss: 0.0037629641592502594
2023-01-24 09:14:36.036320: step: 924/529, loss: 0.0030023385770618916
2023-01-24 09:14:37.110447: step: 928/529, loss: 7.729006028966978e-05
2023-01-24 09:14:38.206493: step: 932/529, loss: 0.006165419705212116
2023-01-24 09:14:39.296611: step: 936/529, loss: 0.002081350889056921
2023-01-24 09:14:40.371293: step: 940/529, loss: 0.0010776565177366138
2023-01-24 09:14:41.447982: step: 944/529, loss: 0.0012144746724516153
2023-01-24 09:14:42.513637: step: 948/529, loss: 0.0013656432274729013
2023-01-24 09:14:43.605700: step: 952/529, loss: 0.005908365361392498
2023-01-24 09:14:44.693959: step: 956/529, loss: 0.002732435939833522
2023-01-24 09:14:45.786463: step: 960/529, loss: 0.00545385992154479
2023-01-24 09:14:46.851423: step: 964/529, loss: 0.0019418157171458006
2023-01-24 09:14:47.920601: step: 968/529, loss: 0.001496769953519106
2023-01-24 09:14:49.002564: step: 972/529, loss: 0.0031646527349948883
2023-01-24 09:14:50.087745: step: 976/529, loss: 0.015380684286355972
2023-01-24 09:14:51.152289: step: 980/529, loss: 0.006559289991855621
2023-01-24 09:14:52.222985: step: 984/529, loss: 0.0011803609086200595
2023-01-24 09:14:53.303965: step: 988/529, loss: 0.0028026883956044912
2023-01-24 09:14:54.381055: step: 992/529, loss: 0.0018853460205718875
2023-01-24 09:14:55.453883: step: 996/529, loss: 0.00375824305228889
2023-01-24 09:14:56.542352: step: 1000/529, loss: 0.0008085378794930875
2023-01-24 09:14:57.621321: step: 1004/529, loss: 0.0020609023049473763
2023-01-24 09:14:58.687752: step: 1008/529, loss: 0.007779187988489866
2023-01-24 09:14:59.767772: step: 1012/529, loss: 0.002778386464342475
2023-01-24 09:15:00.861322: step: 1016/529, loss: 0.0001404272043146193
2023-01-24 09:15:01.941011: step: 1020/529, loss: 0.0052325366996228695
2023-01-24 09:15:03.042508: step: 1024/529, loss: 0.002829657169058919
2023-01-24 09:15:04.123222: step: 1028/529, loss: 9.075047273654491e-05
2023-01-24 09:15:05.215622: step: 1032/529, loss: 5.7433717302046716e-05
2023-01-24 09:15:06.290550: step: 1036/529, loss: 0.0005083115538582206
2023-01-24 09:15:07.365654: step: 1040/529, loss: 0.00039361463859677315
2023-01-24 09:15:08.442316: step: 1044/529, loss: 0.0006710219895467162
2023-01-24 09:15:09.508775: step: 1048/529, loss: 6.667277193628252e-05
2023-01-24 09:15:10.584858: step: 1052/529, loss: 7.658819231437519e-05
2023-01-24 09:15:11.649036: step: 1056/529, loss: 0.0006490605883300304
2023-01-24 09:15:12.754692: step: 1060/529, loss: 0.010827995836734772
2023-01-24 09:15:13.859999: step: 1064/529, loss: 0.00015219306806102395
2023-01-24 09:15:14.935267: step: 1068/529, loss: 0.0008494030334986746
2023-01-24 09:15:16.008648: step: 1072/529, loss: 0.0005586376646533608
2023-01-24 09:15:17.079493: step: 1076/529, loss: 0.0015351675683632493
2023-01-24 09:15:18.153551: step: 1080/529, loss: 0.0017223567701876163
2023-01-24 09:15:19.222527: step: 1084/529, loss: 4.26711849286221e-05
2023-01-24 09:15:20.298418: step: 1088/529, loss: 0.003707293886691332
2023-01-24 09:15:21.375306: step: 1092/529, loss: 0.002257500309497118
2023-01-24 09:15:22.457731: step: 1096/529, loss: 0.0008587195188738406
2023-01-24 09:15:23.546912: step: 1100/529, loss: 0.00748869962990284
2023-01-24 09:15:24.627855: step: 1104/529, loss: 0.0008730971603654325
2023-01-24 09:15:25.731583: step: 1108/529, loss: 0.0018483257154002786
2023-01-24 09:15:26.799366: step: 1112/529, loss: 0.0019268756732344627
2023-01-24 09:15:27.879900: step: 1116/529, loss: 0.0015258695930242538
2023-01-24 09:15:28.949948: step: 1120/529, loss: 0.0005209136288613081
2023-01-24 09:15:30.011742: step: 1124/529, loss: 0.0012028071796521544
2023-01-24 09:15:31.088607: step: 1128/529, loss: 0.0038608855102211237
2023-01-24 09:15:32.169833: step: 1132/529, loss: 0.0006154804141260684
2023-01-24 09:15:33.241552: step: 1136/529, loss: 0.003657440422102809
2023-01-24 09:15:34.327088: step: 1140/529, loss: 0.043205469846725464
2023-01-24 09:15:35.396923: step: 1144/529, loss: 6.276134809013456e-05
2023-01-24 09:15:36.476809: step: 1148/529, loss: 0.002498716115951538
2023-01-24 09:15:37.570435: step: 1152/529, loss: 0.004072152078151703
2023-01-24 09:15:38.659003: step: 1156/529, loss: 0.0003936043649446219
2023-01-24 09:15:39.726723: step: 1160/529, loss: 0.007063613273203373
2023-01-24 09:15:40.801881: step: 1164/529, loss: 0.0007550419541075826
2023-01-24 09:15:41.888154: step: 1168/529, loss: 0.004259921610355377
2023-01-24 09:15:42.978860: step: 1172/529, loss: 0.00039926229510456324
2023-01-24 09:15:44.033339: step: 1176/529, loss: 0.0011149825295433402
2023-01-24 09:15:45.106800: step: 1180/529, loss: 0.002595897763967514
2023-01-24 09:15:46.174903: step: 1184/529, loss: 0.008593294769525528
2023-01-24 09:15:47.232652: step: 1188/529, loss: 0.000594412733335048
2023-01-24 09:15:48.287610: step: 1192/529, loss: 1.808378510759212e-05
2023-01-24 09:15:49.354025: step: 1196/529, loss: 0.0048291427083313465
2023-01-24 09:15:50.429315: step: 1200/529, loss: 0.0020109168253839016
2023-01-24 09:15:51.503237: step: 1204/529, loss: 0.0036780221853405237
2023-01-24 09:15:52.579360: step: 1208/529, loss: 0.0044897496700286865
2023-01-24 09:15:53.653946: step: 1212/529, loss: 0.0007382581825368106
2023-01-24 09:15:54.740069: step: 1216/529, loss: 0.010926084592938423
2023-01-24 09:15:55.802966: step: 1220/529, loss: 0.0039057754911482334
2023-01-24 09:15:56.865178: step: 1224/529, loss: 0.006962126586586237
2023-01-24 09:15:57.934415: step: 1228/529, loss: 0.0034068129025399685
2023-01-24 09:15:59.007075: step: 1232/529, loss: 0.00112510088365525
2023-01-24 09:16:00.102591: step: 1236/529, loss: 0.0007346238126046956
2023-01-24 09:16:01.202521: step: 1240/529, loss: 0.0019496228778734803
2023-01-24 09:16:02.282910: step: 1244/529, loss: 0.0038012738805264235
2023-01-24 09:16:03.352733: step: 1248/529, loss: 0.004894669633358717
2023-01-24 09:16:04.435293: step: 1252/529, loss: 0.0005669477395713329
2023-01-24 09:16:05.504404: step: 1256/529, loss: 0.0028599631041288376
2023-01-24 09:16:06.581749: step: 1260/529, loss: 0.00023831026919651777
2023-01-24 09:16:07.661629: step: 1264/529, loss: 0.0017782659269869328
2023-01-24 09:16:08.731353: step: 1268/529, loss: 0.003180332714691758
2023-01-24 09:16:09.797824: step: 1272/529, loss: 0.0005634871777147055
2023-01-24 09:16:10.872931: step: 1276/529, loss: 0.0005659122834913433
2023-01-24 09:16:11.945901: step: 1280/529, loss: 0.0012836528476327658
2023-01-24 09:16:13.005770: step: 1284/529, loss: 0.004379668273031712
2023-01-24 09:16:14.077127: step: 1288/529, loss: 0.009521793574094772
2023-01-24 09:16:15.155801: step: 1292/529, loss: 0.002475961111485958
2023-01-24 09:16:16.215960: step: 1296/529, loss: 0.0009779938263818622
2023-01-24 09:16:17.297065: step: 1300/529, loss: 0.00312836398370564
2023-01-24 09:16:18.369599: step: 1304/529, loss: 0.002582593122497201
2023-01-24 09:16:19.442124: step: 1308/529, loss: 0.00019374507246538997
2023-01-24 09:16:20.517062: step: 1312/529, loss: 0.0006239487556740642
2023-01-24 09:16:21.573232: step: 1316/529, loss: 0.0006423802697099745
2023-01-24 09:16:22.644932: step: 1320/529, loss: 0.001917838817462325
2023-01-24 09:16:23.713017: step: 1324/529, loss: 0.0001850782718975097
2023-01-24 09:16:24.777971: step: 1328/529, loss: 0.007231010589748621
2023-01-24 09:16:25.851587: step: 1332/529, loss: 0.0029431157745420933
2023-01-24 09:16:26.906387: step: 1336/529, loss: 0.007133177947252989
2023-01-24 09:16:27.964352: step: 1340/529, loss: 0.0046417731791734695
2023-01-24 09:16:29.032785: step: 1344/529, loss: 0.0001938982750289142
2023-01-24 09:16:30.104022: step: 1348/529, loss: 0.0010179791133850813
2023-01-24 09:16:31.168845: step: 1352/529, loss: 0.00048548419727012515
2023-01-24 09:16:32.249461: step: 1356/529, loss: 0.0033264486119151115
2023-01-24 09:16:33.327687: step: 1360/529, loss: 0.0009518049191683531
2023-01-24 09:16:34.393725: step: 1364/529, loss: 0.0022814397234469652
2023-01-24 09:16:35.451731: step: 1368/529, loss: 0.0005287769017741084
2023-01-24 09:16:36.518721: step: 1372/529, loss: 0.005225060973316431
2023-01-24 09:16:37.590778: step: 1376/529, loss: 0.00015767682634759694
2023-01-24 09:16:38.662963: step: 1380/529, loss: 0.0011445179115980864
2023-01-24 09:16:39.760966: step: 1384/529, loss: 0.0018238815246149898
2023-01-24 09:16:40.828208: step: 1388/529, loss: 0.007704332936555147
2023-01-24 09:16:41.892866: step: 1392/529, loss: 0.0011966499732807279
2023-01-24 09:16:42.952836: step: 1396/529, loss: 0.002158642979338765
2023-01-24 09:16:44.029904: step: 1400/529, loss: 0.006224733777344227
2023-01-24 09:16:45.095774: step: 1404/529, loss: 0.0010657889069989324
2023-01-24 09:16:46.178287: step: 1408/529, loss: 5.5490858358098194e-05
2023-01-24 09:16:47.243033: step: 1412/529, loss: 0.0014365941751748323
2023-01-24 09:16:48.304113: step: 1416/529, loss: 0.0013984849210828543
2023-01-24 09:16:49.371762: step: 1420/529, loss: 0.0036160035524517298
2023-01-24 09:16:50.447152: step: 1424/529, loss: 0.0035706888884305954
2023-01-24 09:16:51.522305: step: 1428/529, loss: 0.0009824762819334865
2023-01-24 09:16:52.586585: step: 1432/529, loss: 0.0005747652030549943
2023-01-24 09:16:53.653172: step: 1436/529, loss: 0.001848118263296783
2023-01-24 09:16:54.716267: step: 1440/529, loss: 0.0028743401635438204
2023-01-24 09:16:55.768190: step: 1444/529, loss: 0.00449009845033288
2023-01-24 09:16:56.845587: step: 1448/529, loss: 0.00325595261529088
2023-01-24 09:16:57.910698: step: 1452/529, loss: 0.0009442290756851435
2023-01-24 09:16:58.990948: step: 1456/529, loss: 0.0012102173641324043
2023-01-24 09:17:00.067555: step: 1460/529, loss: 0.0039881025440990925
2023-01-24 09:17:01.142639: step: 1464/529, loss: 0.00017110141925513744
2023-01-24 09:17:02.212232: step: 1468/529, loss: 0.0014555882662534714
2023-01-24 09:17:03.282001: step: 1472/529, loss: 0.0022690044716000557
2023-01-24 09:17:04.348450: step: 1476/529, loss: 0.00011602540325839072
2023-01-24 09:17:05.429075: step: 1480/529, loss: 7.570101297460496e-05
2023-01-24 09:17:06.496950: step: 1484/529, loss: 0.0007460275664925575
2023-01-24 09:17:07.568775: step: 1488/529, loss: 0.004927394911646843
2023-01-24 09:17:08.649062: step: 1492/529, loss: 0.00025014503626152873
2023-01-24 09:17:09.717960: step: 1496/529, loss: 0.002118960488587618
2023-01-24 09:17:10.787212: step: 1500/529, loss: 0.018409421667456627
2023-01-24 09:17:11.865909: step: 1504/529, loss: 0.0010395676363259554
2023-01-24 09:17:12.944354: step: 1508/529, loss: 0.0010848288657143712
2023-01-24 09:17:14.014515: step: 1512/529, loss: 7.273046776390402e-06
2023-01-24 09:17:15.082554: step: 1516/529, loss: 0.006037840619683266
2023-01-24 09:17:16.149874: step: 1520/529, loss: 8.223614713642746e-07
2023-01-24 09:17:17.218158: step: 1524/529, loss: 0.0028185120318084955
2023-01-24 09:17:18.280687: step: 1528/529, loss: 4.02489495172631e-05
2023-01-24 09:17:19.359990: step: 1532/529, loss: 0.0015066106570884585
2023-01-24 09:17:20.419679: step: 1536/529, loss: 0.0015155121218413115
2023-01-24 09:17:21.484860: step: 1540/529, loss: 0.0037343150470405817
2023-01-24 09:17:22.575441: step: 1544/529, loss: 3.739988869710942e-07
2023-01-24 09:17:23.647297: step: 1548/529, loss: 0.0009553920244798064
2023-01-24 09:17:24.710490: step: 1552/529, loss: 0.002387288026511669
2023-01-24 09:17:25.785428: step: 1556/529, loss: 0.0016599317314103246
2023-01-24 09:17:26.863993: step: 1560/529, loss: 0.0001930451689986512
2023-01-24 09:17:27.927852: step: 1564/529, loss: 0.0010668542236089706
2023-01-24 09:17:29.008702: step: 1568/529, loss: 0.0007465079543180764
2023-01-24 09:17:30.080619: step: 1572/529, loss: 0.0002625504566822201
2023-01-24 09:17:31.149280: step: 1576/529, loss: 0.0015640161000192165
2023-01-24 09:17:32.212815: step: 1580/529, loss: 0.0017872406169772148
2023-01-24 09:17:33.287954: step: 1584/529, loss: 9.835542005021125e-05
2023-01-24 09:17:34.356508: step: 1588/529, loss: 0.0007155194762162864
2023-01-24 09:17:35.428016: step: 1592/529, loss: 5.46418123121839e-05
2023-01-24 09:17:36.494869: step: 1596/529, loss: 0.00044310936937108636
2023-01-24 09:17:37.556545: step: 1600/529, loss: 0.0043274713680148125
2023-01-24 09:17:38.639045: step: 1604/529, loss: 0.002196304500102997
2023-01-24 09:17:39.720834: step: 1608/529, loss: 0.0061032394878566265
2023-01-24 09:17:40.803153: step: 1612/529, loss: 0.0019603732507675886
2023-01-24 09:17:41.877974: step: 1616/529, loss: 0.00047863248619250953
2023-01-24 09:17:42.952848: step: 1620/529, loss: 0.0017844531685113907
2023-01-24 09:17:44.020682: step: 1624/529, loss: 0.001975511433556676
2023-01-24 09:17:45.091503: step: 1628/529, loss: 0.005960141774266958
2023-01-24 09:17:46.163272: step: 1632/529, loss: 0.0029372964054346085
2023-01-24 09:17:47.244185: step: 1636/529, loss: 0.0025688691530376673
2023-01-24 09:17:48.321672: step: 1640/529, loss: 0.001015074783936143
2023-01-24 09:17:49.400744: step: 1644/529, loss: 2.1234066593933676e-07
2023-01-24 09:17:50.466376: step: 1648/529, loss: 0.0004801612230949104
2023-01-24 09:17:51.537105: step: 1652/529, loss: 0.003322687465697527
2023-01-24 09:17:52.592257: step: 1656/529, loss: 0.0011118465336039662
2023-01-24 09:17:53.664005: step: 1660/529, loss: 0.0073075732216238976
2023-01-24 09:17:54.734525: step: 1664/529, loss: 0.0004294175305403769
2023-01-24 09:17:55.792706: step: 1668/529, loss: 0.00015707006969023496
2023-01-24 09:17:56.862340: step: 1672/529, loss: 0.0001412837445968762
2023-01-24 09:17:57.935990: step: 1676/529, loss: 0.0003383977455087006
2023-01-24 09:17:59.019852: step: 1680/529, loss: 0.019864745438098907
2023-01-24 09:18:00.082359: step: 1684/529, loss: 0.00041160514228977263
2023-01-24 09:18:01.153887: step: 1688/529, loss: 0.002199660986661911
2023-01-24 09:18:02.228446: step: 1692/529, loss: 0.0013559951912611723
2023-01-24 09:18:03.308061: step: 1696/529, loss: 0.0010018300963565707
2023-01-24 09:18:04.362777: step: 1700/529, loss: 0.0021604576613754034
2023-01-24 09:18:05.435797: step: 1704/529, loss: 0.000719524803571403
2023-01-24 09:18:06.498289: step: 1708/529, loss: 0.003140198765322566
2023-01-24 09:18:07.552293: step: 1712/529, loss: 0.0006435253308154643
2023-01-24 09:18:08.608552: step: 1716/529, loss: 0.00011017225187970325
2023-01-24 09:18:09.699722: step: 1720/529, loss: 0.004275134298950434
2023-01-24 09:18:10.778111: step: 1724/529, loss: 0.0005691625992767513
2023-01-24 09:18:11.841923: step: 1728/529, loss: 0.0008874873165041208
2023-01-24 09:18:12.933426: step: 1732/529, loss: 0.005249090027064085
2023-01-24 09:18:14.000354: step: 1736/529, loss: 0.0027024808805435896
2023-01-24 09:18:15.084315: step: 1740/529, loss: 0.0022624663542956114
2023-01-24 09:18:16.172716: step: 1744/529, loss: 0.0131065733730793
2023-01-24 09:18:17.241942: step: 1748/529, loss: 5.179776781005785e-05
2023-01-24 09:18:18.310846: step: 1752/529, loss: 0.0001413149293512106
2023-01-24 09:18:19.376134: step: 1756/529, loss: 0.004212803672999144
2023-01-24 09:18:20.451476: step: 1760/529, loss: 0.0050727264024317265
2023-01-24 09:18:21.529313: step: 1764/529, loss: 0.007901964709162712
2023-01-24 09:18:22.598013: step: 1768/529, loss: 0.0018743944820016623
2023-01-24 09:18:23.658877: step: 1772/529, loss: 0.0020944548305124044
2023-01-24 09:18:24.728691: step: 1776/529, loss: 0.00019091676222160459
2023-01-24 09:18:25.791572: step: 1780/529, loss: 0.0018894568784162402
2023-01-24 09:18:26.847974: step: 1784/529, loss: 6.166517414385453e-05
2023-01-24 09:18:27.922770: step: 1788/529, loss: 0.001851622830145061
2023-01-24 09:18:28.993066: step: 1792/529, loss: 0.01644969917833805
2023-01-24 09:18:30.054885: step: 1796/529, loss: 0.002602136693894863
2023-01-24 09:18:31.136327: step: 1800/529, loss: 0.006712350994348526
2023-01-24 09:18:32.197891: step: 1804/529, loss: 5.161118679097854e-06
2023-01-24 09:18:33.242080: step: 1808/529, loss: 3.353336069267243e-06
2023-01-24 09:18:34.303621: step: 1812/529, loss: 0.0030756357591599226
2023-01-24 09:18:35.382057: step: 1816/529, loss: 0.002079861471429467
2023-01-24 09:18:36.464348: step: 1820/529, loss: 0.003998699132353067
2023-01-24 09:18:37.542945: step: 1824/529, loss: 0.007737547159194946
2023-01-24 09:18:38.613517: step: 1828/529, loss: 0.0038897807244211435
2023-01-24 09:18:39.684874: step: 1832/529, loss: 0.004534234758466482
2023-01-24 09:18:40.750317: step: 1836/529, loss: 0.0004959909711033106
2023-01-24 09:18:41.820022: step: 1840/529, loss: 0.0005378610221669078
2023-01-24 09:18:42.887003: step: 1844/529, loss: 0.002199208363890648
2023-01-24 09:18:43.945845: step: 1848/529, loss: 0.0008325819508172572
2023-01-24 09:18:45.011379: step: 1852/529, loss: 0.007355336099863052
2023-01-24 09:18:46.075056: step: 1856/529, loss: 0.0004597824008669704
2023-01-24 09:18:47.124236: step: 1860/529, loss: 0.0057330504059791565
2023-01-24 09:18:48.183617: step: 1864/529, loss: 0.0001159469029516913
2023-01-24 09:18:49.258762: step: 1868/529, loss: 1.6581265299464576e-05
2023-01-24 09:18:50.321692: step: 1872/529, loss: 0.0005634183180518448
2023-01-24 09:18:51.397805: step: 1876/529, loss: 0.011288592591881752
2023-01-24 09:18:52.454047: step: 1880/529, loss: 0.00043343662400729954
2023-01-24 09:18:53.515075: step: 1884/529, loss: 0.0006984006613492966
2023-01-24 09:18:54.588068: step: 1888/529, loss: 0.0046867490746080875
2023-01-24 09:18:55.654525: step: 1892/529, loss: 0.004059478174895048
2023-01-24 09:18:56.714452: step: 1896/529, loss: 0.0012924011098220944
2023-01-24 09:18:57.796986: step: 1900/529, loss: 0.002071784343570471
2023-01-24 09:18:58.899919: step: 1904/529, loss: 0.011372504755854607
2023-01-24 09:18:59.976536: step: 1908/529, loss: 0.003362776944413781
2023-01-24 09:19:01.039823: step: 1912/529, loss: 0.0023445303086191416
2023-01-24 09:19:02.097895: step: 1916/529, loss: 0.00017955811927095056
2023-01-24 09:19:03.165443: step: 1920/529, loss: 0.001524993684142828
2023-01-24 09:19:04.229809: step: 1924/529, loss: 0.0017600884893909097
2023-01-24 09:19:05.316784: step: 1928/529, loss: 0.0038016540929675102
2023-01-24 09:19:06.391221: step: 1932/529, loss: 2.8747370379278436e-05
2023-01-24 09:19:07.464780: step: 1936/529, loss: 0.0058314017951488495
2023-01-24 09:19:08.530584: step: 1940/529, loss: 0.005763298366218805
2023-01-24 09:19:09.591490: step: 1944/529, loss: 0.0028499593026936054
2023-01-24 09:19:10.660264: step: 1948/529, loss: 0.0020090679172426462
2023-01-24 09:19:11.729895: step: 1952/529, loss: 0.003981693182140589
2023-01-24 09:19:12.810228: step: 1956/529, loss: 0.002778051421046257
2023-01-24 09:19:13.867548: step: 1960/529, loss: 0.0007779460866004229
2023-01-24 09:19:14.954904: step: 1964/529, loss: 0.0042539192363619804
2023-01-24 09:19:16.011201: step: 1968/529, loss: 0.02666550502181053
2023-01-24 09:19:17.082712: step: 1972/529, loss: 4.753031680593267e-05
2023-01-24 09:19:18.144670: step: 1976/529, loss: 0.0035888017155230045
2023-01-24 09:19:19.232032: step: 1980/529, loss: 0.004086082801222801
2023-01-24 09:19:20.307532: step: 1984/529, loss: 0.0005060922121629119
2023-01-24 09:19:21.378206: step: 1988/529, loss: 0.0014637112617492676
2023-01-24 09:19:22.466497: step: 1992/529, loss: 0.004064515233039856
2023-01-24 09:19:23.556159: step: 1996/529, loss: 0.002950838999822736
2023-01-24 09:19:24.632178: step: 2000/529, loss: 0.0011641213204711676
2023-01-24 09:19:25.690800: step: 2004/529, loss: 0.0021604953799396753
2023-01-24 09:19:26.771585: step: 2008/529, loss: 0.0012989185051992536
2023-01-24 09:19:27.845981: step: 2012/529, loss: 0.0018135125283151865
2023-01-24 09:19:28.914355: step: 2016/529, loss: 1.6374669939978048e-05
2023-01-24 09:19:29.990188: step: 2020/529, loss: 0.005068726371973753
2023-01-24 09:19:31.065355: step: 2024/529, loss: 0.0004423893115017563
2023-01-24 09:19:32.137129: step: 2028/529, loss: 0.0006851354846730828
2023-01-24 09:19:33.200331: step: 2032/529, loss: 0.027675429359078407
2023-01-24 09:19:34.273942: step: 2036/529, loss: 0.0033681581262499094
2023-01-24 09:19:35.352808: step: 2040/529, loss: 0.01567409187555313
2023-01-24 09:19:36.409306: step: 2044/529, loss: 0.0022905180230736732
2023-01-24 09:19:37.487892: step: 2048/529, loss: 0.005376490764319897
2023-01-24 09:19:38.562066: step: 2052/529, loss: 0.0035738579463213682
2023-01-24 09:19:39.642198: step: 2056/529, loss: 0.0001299295254284516
2023-01-24 09:19:40.711163: step: 2060/529, loss: 5.431179488368798e-07
2023-01-24 09:19:41.770654: step: 2064/529, loss: 1.3345228353500715e-06
2023-01-24 09:19:42.874147: step: 2068/529, loss: 0.00254993699491024
2023-01-24 09:19:43.928872: step: 2072/529, loss: 0.0019837834406644106
2023-01-24 09:19:44.994298: step: 2076/529, loss: 0.011133707128465176
2023-01-24 09:19:46.064507: step: 2080/529, loss: 0.001869537984021008
2023-01-24 09:19:47.135611: step: 2084/529, loss: 0.0023477799259126186
2023-01-24 09:19:48.194957: step: 2088/529, loss: 0.001385086914524436
2023-01-24 09:19:49.264821: step: 2092/529, loss: 0.0007534649921581149
2023-01-24 09:19:50.340650: step: 2096/529, loss: 0.005786359775811434
2023-01-24 09:19:51.423663: step: 2100/529, loss: 0.008153497241437435
2023-01-24 09:19:52.492339: step: 2104/529, loss: 0.003495414275676012
2023-01-24 09:19:53.563090: step: 2108/529, loss: 3.7915068418215014e-08
2023-01-24 09:19:54.625983: step: 2112/529, loss: 0.0005296847084537148
2023-01-24 09:19:55.676432: step: 2116/529, loss: 0.0
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34025139311043573, 'r': 0.30345000903587244, 'f1': 0.32079870564073176}, 'combined': 0.23637799363001286, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3316831831744815, 'r': 0.29235677634588947, 'f1': 0.3107808233163925}, 'combined': 0.2028931799889402, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35652536642819754, 'r': 0.3524662540969467, 'f1': 0.354484190666204}, 'combined': 0.2611988773329924, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3587054942468965, 'r': 0.3151860776654716, 'f1': 0.3355405601761576}, 'combined': 0.21905756778339822, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37713696476118025, 'r': 0.3420710989674462, 'f1': 0.3587491923499386}, 'combined': 0.2643415101525863, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3696497081480542, 'r': 0.30441740671016226, 'f1': 0.3338771557466296}, 'combined': 0.21797161463251463, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36228352381783285, 'r': 0.3581588537174401, 'f1': 0.3602093815058987}, 'combined': 0.2654174390043464, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35743685856996116, 'r': 0.31242872472429506, 'f1': 0.3334207479156774}, 'combined': 0.21767364889831786, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
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 09:22:25.240427: step: 4/529, loss: 0.0005170427029952407
2023-01-24 09:22:26.300690: step: 8/529, loss: 0.003996998071670532
2023-01-24 09:22:27.348595: step: 12/529, loss: 2.510870217520278e-06
2023-01-24 09:22:28.397562: step: 16/529, loss: 1.3675046830030624e-05
2023-01-24 09:22:29.479605: step: 20/529, loss: 0.008300567977130413
2023-01-24 09:22:30.539704: step: 24/529, loss: 0.005986595526337624
2023-01-24 09:22:31.606595: step: 28/529, loss: 0.000947567168623209
2023-01-24 09:22:32.668226: step: 32/529, loss: 3.4728953323792666e-05
2023-01-24 09:22:33.738712: step: 36/529, loss: 0.0001365190400974825
2023-01-24 09:22:34.793312: step: 40/529, loss: 0.006958008278161287
2023-01-24 09:22:35.860539: step: 44/529, loss: 0.006734210532158613
2023-01-24 09:22:36.907417: step: 48/529, loss: 5.352754214982269e-06
2023-01-24 09:22:37.974031: step: 52/529, loss: 2.4183271307265386e-05
2023-01-24 09:22:39.050469: step: 56/529, loss: 0.0011040987446904182
2023-01-24 09:22:40.109300: step: 60/529, loss: 0.001783977379091084
2023-01-24 09:22:41.163624: step: 64/529, loss: 8.852654718793929e-05
2023-01-24 09:22:42.239233: step: 68/529, loss: 0.0026852956507354975
2023-01-24 09:22:43.336645: step: 72/529, loss: 1.2267275451449677e-05
2023-01-24 09:22:44.410270: step: 76/529, loss: 0.0011496621882542968
2023-01-24 09:22:45.490820: step: 80/529, loss: 0.001844880636781454
2023-01-24 09:22:46.566438: step: 84/529, loss: 0.0022491570562124252
2023-01-24 09:22:47.638255: step: 88/529, loss: 0.001819856115616858
2023-01-24 09:22:48.714561: step: 92/529, loss: 0.0009606943349353969
2023-01-24 09:22:49.789522: step: 96/529, loss: 0.0029981129337102175
2023-01-24 09:22:50.858145: step: 100/529, loss: 0.002628811402246356
2023-01-24 09:22:51.914577: step: 104/529, loss: 0.002487039193511009
2023-01-24 09:22:52.987589: step: 108/529, loss: 4.50752122560516e-05
2023-01-24 09:22:54.047449: step: 112/529, loss: 4.667012035497464e-06
2023-01-24 09:22:55.106060: step: 116/529, loss: 0.0
2023-01-24 09:22:56.170581: step: 120/529, loss: 2.5754681701073423e-05
2023-01-24 09:22:57.234666: step: 124/529, loss: 0.006827972363680601
2023-01-24 09:22:58.304372: step: 128/529, loss: 1.8251725123263896e-05
2023-01-24 09:22:59.370761: step: 132/529, loss: 0.0027503070887178183
2023-01-24 09:23:00.448892: step: 136/529, loss: 0.002401398029178381
2023-01-24 09:23:01.526192: step: 140/529, loss: 0.008718474768102169
2023-01-24 09:23:02.590188: step: 144/529, loss: 0.002033430617302656
2023-01-24 09:23:03.669870: step: 148/529, loss: 0.0009262897656299174
2023-01-24 09:23:04.745886: step: 152/529, loss: 0.00035648245830088854
2023-01-24 09:23:05.814338: step: 156/529, loss: 0.0025159530341625214
2023-01-24 09:23:06.889444: step: 160/529, loss: 0.006056359503418207
2023-01-24 09:23:07.958122: step: 164/529, loss: 0.000981770921498537
2023-01-24 09:23:09.032732: step: 168/529, loss: 0.005055608693510294
2023-01-24 09:23:10.120868: step: 172/529, loss: 2.6814668672159314e-05
2023-01-24 09:23:11.202480: step: 176/529, loss: 0.002276569837704301
2023-01-24 09:23:12.277268: step: 180/529, loss: 0.0003162195789627731
2023-01-24 09:23:13.370641: step: 184/529, loss: 9.143976785708219e-05
2023-01-24 09:23:14.441483: step: 188/529, loss: 0.0018073818646371365
2023-01-24 09:23:15.529976: step: 192/529, loss: 0.001006540609523654
2023-01-24 09:23:16.616051: step: 196/529, loss: 0.0051518515683710575
2023-01-24 09:23:17.684381: step: 200/529, loss: 0.0011647173669189215
2023-01-24 09:23:18.768755: step: 204/529, loss: 5.387639703258174e-07
2023-01-24 09:23:19.832979: step: 208/529, loss: 0.001833552261814475
2023-01-24 09:23:20.917810: step: 212/529, loss: 0.0014072679914534092
2023-01-24 09:23:21.989480: step: 216/529, loss: 9.867369226412848e-05
2023-01-24 09:23:23.075370: step: 220/529, loss: 0.00038242017035372555
2023-01-24 09:23:24.138028: step: 224/529, loss: 0.00014357497275341302
2023-01-24 09:23:25.231836: step: 228/529, loss: 0.005328443367034197
2023-01-24 09:23:26.304252: step: 232/529, loss: 0.0025594925973564386
2023-01-24 09:23:27.382560: step: 236/529, loss: 0.0001578389637870714
2023-01-24 09:23:28.455634: step: 240/529, loss: 0.002368208486586809
2023-01-24 09:23:29.531731: step: 244/529, loss: 0.0013675173977389932
2023-01-24 09:23:30.590221: step: 248/529, loss: 9.905160550260916e-05
2023-01-24 09:23:31.680358: step: 252/529, loss: 0.0038675423711538315
2023-01-24 09:23:32.768414: step: 256/529, loss: 0.003128435229882598
2023-01-24 09:23:33.847102: step: 260/529, loss: 0.0050405231304466724
2023-01-24 09:23:34.927364: step: 264/529, loss: 0.0034534321166574955
2023-01-24 09:23:35.985852: step: 268/529, loss: 3.246635606046766e-05
2023-01-24 09:23:37.060103: step: 272/529, loss: 0.0029384715016931295
2023-01-24 09:23:38.143430: step: 276/529, loss: 0.0010744519531726837
2023-01-24 09:23:39.204839: step: 280/529, loss: 0.0022833039984107018
2023-01-24 09:23:40.282860: step: 284/529, loss: 0.0008670688839629292
2023-01-24 09:23:41.408253: step: 288/529, loss: 0.003240938065573573
2023-01-24 09:23:42.486676: step: 292/529, loss: 5.8092631661565974e-05
2023-01-24 09:23:43.589799: step: 296/529, loss: 0.0010195011273026466
2023-01-24 09:23:44.679508: step: 300/529, loss: 0.012319865636527538
2023-01-24 09:23:45.762282: step: 304/529, loss: 0.00497813755646348
2023-01-24 09:23:46.856176: step: 308/529, loss: 0.000755386718083173
2023-01-24 09:23:47.938748: step: 312/529, loss: 0.0019269298063591123
2023-01-24 09:23:49.029685: step: 316/529, loss: 0.0027097086422145367
2023-01-24 09:23:50.103808: step: 320/529, loss: 0.002618101192638278
2023-01-24 09:23:51.182058: step: 324/529, loss: 0.0002074251533485949
2023-01-24 09:23:52.264671: step: 328/529, loss: 0.0022812895476818085
2023-01-24 09:23:53.326453: step: 332/529, loss: 0.0023774162400513887
2023-01-24 09:23:54.403124: step: 336/529, loss: 0.00025950890267267823
2023-01-24 09:23:55.473783: step: 340/529, loss: 0.022284623235464096
2023-01-24 09:23:56.570460: step: 344/529, loss: 0.0007858769386075437
2023-01-24 09:23:57.645328: step: 348/529, loss: 4.798209556611255e-05
2023-01-24 09:23:58.706806: step: 352/529, loss: 0.014714204706251621
2023-01-24 09:23:59.791742: step: 356/529, loss: 0.024418260902166367
2023-01-24 09:24:00.868173: step: 360/529, loss: 0.000383179314667359
2023-01-24 09:24:01.941238: step: 364/529, loss: 0.0006357360980473459
2023-01-24 09:24:03.025661: step: 368/529, loss: 0.000190254402696155
2023-01-24 09:24:04.123470: step: 372/529, loss: 0.00103954307269305
2023-01-24 09:24:05.200605: step: 376/529, loss: 0.0013072279980406165
2023-01-24 09:24:06.276802: step: 380/529, loss: 0.0028431143146008253
2023-01-24 09:24:07.335510: step: 384/529, loss: 0.0
2023-01-24 09:24:08.415241: step: 388/529, loss: 0.001187230576761067
2023-01-24 09:24:09.506934: step: 392/529, loss: 0.0004948079586029053
2023-01-24 09:24:10.586932: step: 396/529, loss: 0.00013973114255350083
2023-01-24 09:24:11.649096: step: 400/529, loss: 0.0002870879543479532
2023-01-24 09:24:12.722067: step: 404/529, loss: 0.00035541175748221576
2023-01-24 09:24:13.796931: step: 408/529, loss: 0.006057152524590492
2023-01-24 09:24:14.866485: step: 412/529, loss: 0.0008274091524071991
2023-01-24 09:24:15.938998: step: 416/529, loss: 0.00019476051966194063
2023-01-24 09:24:17.025572: step: 420/529, loss: 0.0036354619078338146
2023-01-24 09:24:18.113999: step: 424/529, loss: 0.004550225101411343
2023-01-24 09:24:19.190094: step: 428/529, loss: 0.0007033761939965189
2023-01-24 09:24:20.270186: step: 432/529, loss: 0.0021626714151352644
2023-01-24 09:24:21.327415: step: 436/529, loss: 0.00012795602378901094
2023-01-24 09:24:22.405297: step: 440/529, loss: 0.0035500184167176485
2023-01-24 09:24:23.478849: step: 444/529, loss: 0.00013778953871224076
2023-01-24 09:24:24.555589: step: 448/529, loss: 0.00013741859584115446
2023-01-24 09:24:25.628244: step: 452/529, loss: 0.0016091839643195271
2023-01-24 09:24:26.679550: step: 456/529, loss: 0.009337568655610085
2023-01-24 09:24:27.757943: step: 460/529, loss: 0.0006452303496189415
2023-01-24 09:24:28.824679: step: 464/529, loss: 0.0030323772225528955
2023-01-24 09:24:29.911747: step: 468/529, loss: 0.0006839603302069008
2023-01-24 09:24:30.969151: step: 472/529, loss: 0.0006726902793161571
2023-01-24 09:24:32.035465: step: 476/529, loss: 0.0020286915823817253
2023-01-24 09:24:33.114004: step: 480/529, loss: 0.0007536160410381854
2023-01-24 09:24:34.201066: step: 484/529, loss: 0.010548115707933903
2023-01-24 09:24:35.287868: step: 488/529, loss: 0.0012876685941591859
2023-01-24 09:24:36.362163: step: 492/529, loss: 8.220409654313698e-05
2023-01-24 09:24:37.451426: step: 496/529, loss: 0.0008663617190904915
2023-01-24 09:24:38.538545: step: 500/529, loss: 2.1060950530227274e-05
2023-01-24 09:24:39.607386: step: 504/529, loss: 0.0048391143791377544
2023-01-24 09:24:40.681796: step: 508/529, loss: 0.008487492799758911
2023-01-24 09:24:41.761644: step: 512/529, loss: 0.0006959937163628638
2023-01-24 09:24:42.871927: step: 516/529, loss: 0.003163679502904415
2023-01-24 09:24:43.944437: step: 520/529, loss: 0.016245556995272636
2023-01-24 09:24:45.034455: step: 524/529, loss: 0.004731496796011925
2023-01-24 09:24:46.116946: step: 528/529, loss: 0.0008546838071197271
2023-01-24 09:24:47.195664: step: 532/529, loss: 0.006097367964684963
2023-01-24 09:24:48.261853: step: 536/529, loss: 7.900789205450565e-05
2023-01-24 09:24:49.349250: step: 540/529, loss: 0.014645283110439777
2023-01-24 09:24:50.421094: step: 544/529, loss: 0.0045510525815188885
2023-01-24 09:24:51.526706: step: 548/529, loss: 0.0015728421276435256
2023-01-24 09:24:52.619227: step: 552/529, loss: 0.006241316441446543
2023-01-24 09:24:53.696736: step: 556/529, loss: 0.0008262254414148629
2023-01-24 09:24:54.765171: step: 560/529, loss: 0.0002901999687310308
2023-01-24 09:24:55.829642: step: 564/529, loss: 0.0009423245792277157
2023-01-24 09:24:56.904355: step: 568/529, loss: 0.004145944491028786
2023-01-24 09:24:57.982535: step: 572/529, loss: 0.0012021501315757632
2023-01-24 09:24:59.068456: step: 576/529, loss: 0.0011120678391307592
2023-01-24 09:25:00.144075: step: 580/529, loss: 0.005865253508090973
2023-01-24 09:25:01.202140: step: 584/529, loss: 0.0006417521508410573
2023-01-24 09:25:02.271794: step: 588/529, loss: 0.0008551164646632969
2023-01-24 09:25:03.352095: step: 592/529, loss: 0.0051851761527359486
2023-01-24 09:25:04.430857: step: 596/529, loss: 0.0010545669356361032
2023-01-24 09:25:05.497630: step: 600/529, loss: 0.002115735551342368
2023-01-24 09:25:06.563233: step: 604/529, loss: 0.001378060900606215
2023-01-24 09:25:07.633025: step: 608/529, loss: 0.0024605717044323683
2023-01-24 09:25:08.720859: step: 612/529, loss: 4.1022130972123705e-06
2023-01-24 09:25:09.815409: step: 616/529, loss: 0.0020249353256076574
2023-01-24 09:25:10.898706: step: 620/529, loss: 5.1120798161718994e-05
2023-01-24 09:25:11.971586: step: 624/529, loss: 0.0009625621605664492
2023-01-24 09:25:13.051390: step: 628/529, loss: 0.0024871586356312037
2023-01-24 09:25:14.117110: step: 632/529, loss: 0.0018476922996342182
2023-01-24 09:25:15.202558: step: 636/529, loss: 0.002248483942821622
2023-01-24 09:25:16.289809: step: 640/529, loss: 0.00010955056495731696
2023-01-24 09:25:17.358366: step: 644/529, loss: 0.0021941205486655235
2023-01-24 09:25:18.438641: step: 648/529, loss: 0.0007116594351828098
2023-01-24 09:25:19.505653: step: 652/529, loss: 3.0883711588103324e-05
2023-01-24 09:25:20.573403: step: 656/529, loss: 0.00012071282253600657
2023-01-24 09:25:21.639592: step: 660/529, loss: 0.00012231143773533404
2023-01-24 09:25:22.735659: step: 664/529, loss: 0.0038045060355216265
2023-01-24 09:25:23.810101: step: 668/529, loss: 0.0001801444450393319
2023-01-24 09:25:24.894070: step: 672/529, loss: 0.00021985379862599075
2023-01-24 09:25:25.972167: step: 676/529, loss: 0.00038099708035588264
2023-01-24 09:25:27.038162: step: 680/529, loss: 0.0011286812368780375
2023-01-24 09:25:28.116078: step: 684/529, loss: 0.00010883078357437626
2023-01-24 09:25:29.192481: step: 688/529, loss: 0.05610376596450806
2023-01-24 09:25:30.267801: step: 692/529, loss: 4.084552074345993e-06
2023-01-24 09:25:31.353364: step: 696/529, loss: 0.0006638095946982503
2023-01-24 09:25:32.428301: step: 700/529, loss: 0.00024273428425658494
2023-01-24 09:25:33.490895: step: 704/529, loss: 0.0002553915837779641
2023-01-24 09:25:34.581419: step: 708/529, loss: 0.0014193645911291242
2023-01-24 09:25:35.670010: step: 712/529, loss: 0.00038652695366181433
2023-01-24 09:25:36.760536: step: 716/529, loss: 0.0026721444446593523
2023-01-24 09:25:37.849808: step: 720/529, loss: 0.0003787715395446867
2023-01-24 09:25:38.923721: step: 724/529, loss: 0.007860297337174416
2023-01-24 09:25:40.002981: step: 728/529, loss: 0.00029570524930022657
2023-01-24 09:25:41.093996: step: 732/529, loss: 0.005589492153376341
2023-01-24 09:25:42.180955: step: 736/529, loss: 0.0013478923356160522
2023-01-24 09:25:43.279371: step: 740/529, loss: 0.000393137481296435
2023-01-24 09:25:44.361760: step: 744/529, loss: 0.0034523168578743935
2023-01-24 09:25:45.455436: step: 748/529, loss: 0.0018992506666108966
2023-01-24 09:25:46.529912: step: 752/529, loss: 0.0071465312503278255
2023-01-24 09:25:47.619309: step: 756/529, loss: 0.002539483131840825
2023-01-24 09:25:48.687509: step: 760/529, loss: 0.0005039104726165533
2023-01-24 09:25:49.766436: step: 764/529, loss: 1.7175478205899708e-05
2023-01-24 09:25:50.840861: step: 768/529, loss: 0.002322344807907939
2023-01-24 09:25:51.913155: step: 772/529, loss: 0.0006581287016160786
2023-01-24 09:25:52.989423: step: 776/529, loss: 0.0004342835454735905
2023-01-24 09:25:54.063530: step: 780/529, loss: 0.0038829061668366194
2023-01-24 09:25:55.129494: step: 784/529, loss: 0.0034522421192377806
2023-01-24 09:25:56.191447: step: 788/529, loss: 0.00038375702570192516
2023-01-24 09:25:57.248631: step: 792/529, loss: 4.385676948004402e-05
2023-01-24 09:25:58.334801: step: 796/529, loss: 0.006793093867599964
2023-01-24 09:25:59.407683: step: 800/529, loss: 2.044854682026198e-06
2023-01-24 09:26:00.478745: step: 804/529, loss: 0.009319250471889973
2023-01-24 09:26:01.563505: step: 808/529, loss: 0.005190895404666662
2023-01-24 09:26:02.641340: step: 812/529, loss: 0.0005878365482203662
2023-01-24 09:26:03.731296: step: 816/529, loss: 0.0057428255677223206
2023-01-24 09:26:04.830221: step: 820/529, loss: 0.0011091399937868118
2023-01-24 09:26:05.900067: step: 824/529, loss: 0.0009232126176357269
2023-01-24 09:26:06.959967: step: 828/529, loss: 0.0006929375231266022
2023-01-24 09:26:08.042787: step: 832/529, loss: 0.002562541514635086
2023-01-24 09:26:09.136177: step: 836/529, loss: 0.005218657664954662
2023-01-24 09:26:10.203172: step: 840/529, loss: 0.0015394786605611444
2023-01-24 09:26:11.281682: step: 844/529, loss: 0.0017984022852033377
2023-01-24 09:26:12.363433: step: 848/529, loss: 0.0008619173313491046
2023-01-24 09:26:13.436138: step: 852/529, loss: 0.00039507824112661183
2023-01-24 09:26:14.512571: step: 856/529, loss: 0.0033971716184169054
2023-01-24 09:26:15.583792: step: 860/529, loss: 0.0008975898963399231
2023-01-24 09:26:16.663186: step: 864/529, loss: 0.0003234376199543476
2023-01-24 09:26:17.721650: step: 868/529, loss: 0.0014752991264685988
2023-01-24 09:26:18.807585: step: 872/529, loss: 0.0017516027437523007
2023-01-24 09:26:19.908406: step: 876/529, loss: 6.583932554349303e-05
2023-01-24 09:26:20.990555: step: 880/529, loss: 0.0034900950267910957
2023-01-24 09:26:22.074417: step: 884/529, loss: 0.0010465745581313968
2023-01-24 09:26:23.157298: step: 888/529, loss: 0.005252181086689234
2023-01-24 09:26:24.243856: step: 892/529, loss: 0.007148124277591705
2023-01-24 09:26:25.329393: step: 896/529, loss: 3.0493527447106317e-05
2023-01-24 09:26:26.414488: step: 900/529, loss: 0.0016849299427121878
2023-01-24 09:26:27.483813: step: 904/529, loss: 0.0009735008352436125
2023-01-24 09:26:28.553731: step: 908/529, loss: 0.01325288601219654
2023-01-24 09:26:29.621685: step: 912/529, loss: 0.0015434680972248316
2023-01-24 09:26:30.697697: step: 916/529, loss: 0.0019753093365579844
2023-01-24 09:26:31.767503: step: 920/529, loss: 5.046111982665025e-05
2023-01-24 09:26:32.850121: step: 924/529, loss: 0.0026010717265307903
2023-01-24 09:26:33.922270: step: 928/529, loss: 0.001972249476239085
2023-01-24 09:26:34.995079: step: 932/529, loss: 0.00041918802889995277
2023-01-24 09:26:36.067771: step: 936/529, loss: 0.005304364487528801
2023-01-24 09:26:37.146054: step: 940/529, loss: 0.002736226422712207
2023-01-24 09:26:38.229734: step: 944/529, loss: 0.004888090770691633
2023-01-24 09:26:39.328545: step: 948/529, loss: 0.0028150822035968304
2023-01-24 09:26:40.408714: step: 952/529, loss: 0.003160664113238454
2023-01-24 09:26:41.483429: step: 956/529, loss: 0.00039712185389362276
2023-01-24 09:26:42.551947: step: 960/529, loss: 0.0016485154628753662
2023-01-24 09:26:43.619432: step: 964/529, loss: 0.0001912313891807571
2023-01-24 09:26:44.691573: step: 968/529, loss: 0.00421398738399148
2023-01-24 09:26:45.766165: step: 972/529, loss: 0.004482007119804621
2023-01-24 09:26:46.842555: step: 976/529, loss: 0.019088326022028923
2023-01-24 09:26:47.910667: step: 980/529, loss: 0.0032817998435348272
2023-01-24 09:26:48.978736: step: 984/529, loss: 1.5632689610356465e-05
2023-01-24 09:26:50.053455: step: 988/529, loss: 4.045343666803092e-05
2023-01-24 09:26:51.121690: step: 992/529, loss: 0.0042253234423696995
2023-01-24 09:26:52.187871: step: 996/529, loss: 0.002274387050420046
2023-01-24 09:26:53.279581: step: 1000/529, loss: 0.0015770719619467854
2023-01-24 09:26:54.353421: step: 1004/529, loss: 0.002691145520657301
2023-01-24 09:26:55.416477: step: 1008/529, loss: 0.0037738229148089886
2023-01-24 09:26:56.501483: step: 1012/529, loss: 0.0018977581057697535
2023-01-24 09:26:57.580066: step: 1016/529, loss: 0.0006461940356530249
2023-01-24 09:26:58.660608: step: 1020/529, loss: 0.004442417528480291
2023-01-24 09:26:59.733084: step: 1024/529, loss: 0.00022630376042798162
2023-01-24 09:27:00.802302: step: 1028/529, loss: 4.8760248319013044e-05
2023-01-24 09:27:01.890846: step: 1032/529, loss: 0.006847711279988289
2023-01-24 09:27:02.969520: step: 1036/529, loss: 0.0016026971861720085
2023-01-24 09:27:04.039579: step: 1040/529, loss: 2.7047412004321814e-05
2023-01-24 09:27:05.114116: step: 1044/529, loss: 2.033718146776664e-06
2023-01-24 09:27:06.203702: step: 1048/529, loss: 0.00478706369176507
2023-01-24 09:27:07.277564: step: 1052/529, loss: 0.0011160974390804768
2023-01-24 09:27:08.354983: step: 1056/529, loss: 0.0010749862994998693
2023-01-24 09:27:09.417832: step: 1060/529, loss: 0.0022716568782925606
2023-01-24 09:27:10.486814: step: 1064/529, loss: 0.0013149181613698602
2023-01-24 09:27:11.570185: step: 1068/529, loss: 0.0007107298006303608
2023-01-24 09:27:12.634715: step: 1072/529, loss: 4.153432746534236e-05
2023-01-24 09:27:13.712009: step: 1076/529, loss: 0.004577780142426491
2023-01-24 09:27:14.804945: step: 1080/529, loss: 0.0001739071449264884
2023-01-24 09:27:15.874564: step: 1084/529, loss: 0.003044232027605176
2023-01-24 09:27:16.939768: step: 1088/529, loss: 0.004600810818374157
2023-01-24 09:27:18.031478: step: 1092/529, loss: 0.002502787858247757
2023-01-24 09:27:19.122747: step: 1096/529, loss: 0.0013413004344329238
2023-01-24 09:27:20.200363: step: 1100/529, loss: 0.0039334469474852085
2023-01-24 09:27:21.279014: step: 1104/529, loss: 3.0470575438812375e-05
2023-01-24 09:27:22.361540: step: 1108/529, loss: 0.016193196177482605
2023-01-24 09:27:23.432219: step: 1112/529, loss: 0.000409727479564026
2023-01-24 09:27:24.515820: step: 1116/529, loss: 0.0011356855975463986
2023-01-24 09:27:25.591546: step: 1120/529, loss: 0.004081465769559145
2023-01-24 09:27:26.675080: step: 1124/529, loss: 0.00019597906793933362
2023-01-24 09:27:27.745279: step: 1128/529, loss: 0.00021422002464532852
2023-01-24 09:27:28.831026: step: 1132/529, loss: 0.0037924337666481733
2023-01-24 09:27:29.930706: step: 1136/529, loss: 5.8792022173292935e-05
2023-01-24 09:27:30.998059: step: 1140/529, loss: 0.00797716062515974
2023-01-24 09:27:32.078806: step: 1144/529, loss: 0.0022480101324617863
2023-01-24 09:27:33.156159: step: 1148/529, loss: 0.0005457639344967902
2023-01-24 09:27:34.233518: step: 1152/529, loss: 0.00022189089213497937
2023-01-24 09:27:35.316815: step: 1156/529, loss: 0.0033852746710181236
2023-01-24 09:27:36.396913: step: 1160/529, loss: 0.002605618443340063
2023-01-24 09:27:37.470077: step: 1164/529, loss: 1.1136330613226164e-05
2023-01-24 09:27:38.551505: step: 1168/529, loss: 0.0009035008843056858
2023-01-24 09:27:39.638732: step: 1172/529, loss: 0.0035224941093474627
2023-01-24 09:27:40.722533: step: 1176/529, loss: 0.004014801699668169
2023-01-24 09:27:41.799208: step: 1180/529, loss: 0.003338790265843272
2023-01-24 09:27:42.895428: step: 1184/529, loss: 0.0025712866336107254
2023-01-24 09:27:43.989596: step: 1188/529, loss: 0.005512366537004709
2023-01-24 09:27:45.070798: step: 1192/529, loss: 0.00788103323429823
2023-01-24 09:27:46.150167: step: 1196/529, loss: 0.004905066918581724
2023-01-24 09:27:47.219057: step: 1200/529, loss: 3.468736031209119e-05
2023-01-24 09:27:48.320650: step: 1204/529, loss: 0.0030592731200158596
2023-01-24 09:27:49.388549: step: 1208/529, loss: 0.0018325737910345197
2023-01-24 09:27:50.469368: step: 1212/529, loss: 0.0008709755493327975
2023-01-24 09:27:51.546731: step: 1216/529, loss: 0.01195499300956726
2023-01-24 09:27:52.608282: step: 1220/529, loss: 5.310764390742406e-05
2023-01-24 09:27:53.683290: step: 1224/529, loss: 3.789425682043657e-05
2023-01-24 09:27:54.811631: step: 1228/529, loss: 0.00246809353120625
2023-01-24 09:27:55.885426: step: 1232/529, loss: 0.00047421138151548803
2023-01-24 09:27:56.960994: step: 1236/529, loss: 0.001974575687199831
2023-01-24 09:27:58.036468: step: 1240/529, loss: 0.0009810103802010417
2023-01-24 09:27:59.103965: step: 1244/529, loss: 0.00886964425444603
2023-01-24 09:28:00.196231: step: 1248/529, loss: 0.00045228906674310565
2023-01-24 09:28:01.271878: step: 1252/529, loss: 0.004300416447222233
2023-01-24 09:28:02.351996: step: 1256/529, loss: 4.550609446596354e-05
2023-01-24 09:28:03.426786: step: 1260/529, loss: 0.0007722140871919692
2023-01-24 09:28:04.497651: step: 1264/529, loss: 0.0010265677701681852
2023-01-24 09:28:05.564805: step: 1268/529, loss: 0.0029264758341014385
2023-01-24 09:28:06.640819: step: 1272/529, loss: 0.005729811266064644
2023-01-24 09:28:07.732006: step: 1276/529, loss: 0.0037682722322642803
2023-01-24 09:28:08.804650: step: 1280/529, loss: 6.315475184237584e-05
2023-01-24 09:28:09.862000: step: 1284/529, loss: 0.0013305587926879525
2023-01-24 09:28:10.942272: step: 1288/529, loss: 0.0018673146842047572
2023-01-24 09:28:12.015955: step: 1292/529, loss: 7.157486106734723e-05
2023-01-24 09:28:13.093936: step: 1296/529, loss: 0.0017495786305516958
2023-01-24 09:28:14.174653: step: 1300/529, loss: 5.299753320286982e-05
2023-01-24 09:28:15.257702: step: 1304/529, loss: 0.016978254541754723
2023-01-24 09:28:16.326311: step: 1308/529, loss: 0.0028834324330091476
2023-01-24 09:28:17.405355: step: 1312/529, loss: 0.0011937894159927964
2023-01-24 09:28:18.500679: step: 1316/529, loss: 5.6245236919494346e-05
2023-01-24 09:28:19.565379: step: 1320/529, loss: 0.002781190210953355
2023-01-24 09:28:20.627415: step: 1324/529, loss: 0.0015717914793640375
2023-01-24 09:28:21.691785: step: 1328/529, loss: 2.8033493435941637e-05
2023-01-24 09:28:22.766449: step: 1332/529, loss: 0.0006443460588343441
2023-01-24 09:28:23.849322: step: 1336/529, loss: 0.0048844702541828156
2023-01-24 09:28:24.918730: step: 1340/529, loss: 0.0004202676354907453
2023-01-24 09:28:25.986371: step: 1344/529, loss: 0.0019861129112541676
2023-01-24 09:28:27.059130: step: 1348/529, loss: 0.004950982052832842
2023-01-24 09:28:28.120026: step: 1352/529, loss: 0.0005211990792304277
2023-01-24 09:28:29.183894: step: 1356/529, loss: 0.0002867472358047962
2023-01-24 09:28:30.249580: step: 1360/529, loss: 2.4214367400077208e-08
2023-01-24 09:28:31.338461: step: 1364/529, loss: 0.005261734127998352
2023-01-24 09:28:32.436085: step: 1368/529, loss: 0.0006633458542637527
2023-01-24 09:28:33.519222: step: 1372/529, loss: 0.00017273858247790486
2023-01-24 09:28:34.612041: step: 1376/529, loss: 4.366132088762242e-06
2023-01-24 09:28:35.673075: step: 1380/529, loss: 0.0009466444025747478
2023-01-24 09:28:36.743061: step: 1384/529, loss: 0.0013486393727362156
2023-01-24 09:28:37.817411: step: 1388/529, loss: 0.004097298253327608
2023-01-24 09:28:38.896455: step: 1392/529, loss: 0.0016938869375735521
2023-01-24 09:28:39.966077: step: 1396/529, loss: 0.0031844936311244965
2023-01-24 09:28:41.036298: step: 1400/529, loss: 0.0002008500596275553
2023-01-24 09:28:42.121016: step: 1404/529, loss: 0.00039893112261779606
2023-01-24 09:28:43.201750: step: 1408/529, loss: 0.00011707357043633237
2023-01-24 09:28:44.301457: step: 1412/529, loss: 0.002673372160643339
2023-01-24 09:28:45.359520: step: 1416/529, loss: 0.0014983529690653086
2023-01-24 09:28:46.438945: step: 1420/529, loss: 0.0009529491071589291
2023-01-24 09:28:47.516002: step: 1424/529, loss: 0.013765398412942886
2023-01-24 09:28:48.597896: step: 1428/529, loss: 0.0016339631984010339
2023-01-24 09:28:49.654909: step: 1432/529, loss: 0.00101010175421834
2023-01-24 09:28:50.711656: step: 1436/529, loss: 0.0013753349194303155
2023-01-24 09:28:51.801238: step: 1440/529, loss: 0.002998936688527465
2023-01-24 09:28:52.881389: step: 1444/529, loss: 0.001989042153581977
2023-01-24 09:28:53.969245: step: 1448/529, loss: 0.0057318322360515594
2023-01-24 09:28:55.048066: step: 1452/529, loss: 0.0011409578146412969
2023-01-24 09:28:56.106543: step: 1456/529, loss: 0.005625690333545208
2023-01-24 09:28:57.184371: step: 1460/529, loss: 0.00029265269404277205
2023-01-24 09:28:58.270135: step: 1464/529, loss: 0.0018152110278606415
2023-01-24 09:28:59.337774: step: 1468/529, loss: 0.0
2023-01-24 09:29:00.418271: step: 1472/529, loss: 0.0025686740409582853
2023-01-24 09:29:01.484833: step: 1476/529, loss: 0.001083427108824253
2023-01-24 09:29:02.578020: step: 1480/529, loss: 0.002301785396412015
2023-01-24 09:29:03.656698: step: 1484/529, loss: 0.00012055222759954631
2023-01-24 09:29:04.730930: step: 1488/529, loss: 0.006107552908360958
2023-01-24 09:29:05.803081: step: 1492/529, loss: 0.0025829130318015814
2023-01-24 09:29:06.872360: step: 1496/529, loss: 0.00010875325824599713
2023-01-24 09:29:07.945416: step: 1500/529, loss: 0.007653120439499617
2023-01-24 09:29:09.018530: step: 1504/529, loss: 8.807182894088328e-05
2023-01-24 09:29:10.093273: step: 1508/529, loss: 0.045848678797483444
2023-01-24 09:29:11.167949: step: 1512/529, loss: 0.001855504815466702
2023-01-24 09:29:12.247400: step: 1516/529, loss: 0.0022322640288621187
2023-01-24 09:29:13.337967: step: 1520/529, loss: 0.0007884801598265767
2023-01-24 09:29:14.419635: step: 1524/529, loss: 0.0018687976989895105
2023-01-24 09:29:15.489218: step: 1528/529, loss: 0.0019302616128697991
2023-01-24 09:29:16.557917: step: 1532/529, loss: 0.007825545035302639
2023-01-24 09:29:17.638503: step: 1536/529, loss: 0.003675041953101754
2023-01-24 09:29:18.705389: step: 1540/529, loss: 0.004312681034207344
2023-01-24 09:29:19.772667: step: 1544/529, loss: 0.0028086958918720484
2023-01-24 09:29:20.850899: step: 1548/529, loss: 0.003273728536441922
2023-01-24 09:29:21.921380: step: 1552/529, loss: 0.0014557080576196313
2023-01-24 09:29:23.001694: step: 1556/529, loss: 0.003620919305831194
2023-01-24 09:29:24.064222: step: 1560/529, loss: 0.0010540438815951347
2023-01-24 09:29:25.151511: step: 1564/529, loss: 0.0017262566834688187
2023-01-24 09:29:26.211616: step: 1568/529, loss: 0.0012436554534360766
2023-01-24 09:29:27.290395: step: 1572/529, loss: 0.0002291925484314561
2023-01-24 09:29:28.362770: step: 1576/529, loss: 0.0077019124291837215
2023-01-24 09:29:29.442212: step: 1580/529, loss: 0.003642189549282193
2023-01-24 09:29:30.495996: step: 1584/529, loss: 0.001956172287464142
2023-01-24 09:29:31.582832: step: 1588/529, loss: 0.004347768146544695
2023-01-24 09:29:32.660799: step: 1592/529, loss: 1.5669371578042046e-06
2023-01-24 09:29:33.751754: step: 1596/529, loss: 0.004435322713106871
2023-01-24 09:29:34.842300: step: 1600/529, loss: 0.0011272202245891094
2023-01-24 09:29:35.932949: step: 1604/529, loss: 1.7881353286952617e-08
2023-01-24 09:29:36.999081: step: 1608/529, loss: 0.0011762864887714386
2023-01-24 09:29:38.095530: step: 1612/529, loss: 0.003867711639031768
2023-01-24 09:29:39.187950: step: 1616/529, loss: 0.001478060963563621
2023-01-24 09:29:40.244123: step: 1620/529, loss: 0.000472315470688045
2023-01-24 09:29:41.302553: step: 1624/529, loss: 0.001271736458875239
2023-01-24 09:29:42.372609: step: 1628/529, loss: 0.0048606302589178085
2023-01-24 09:29:43.444989: step: 1632/529, loss: 0.0026488814037293196
2023-01-24 09:29:44.514753: step: 1636/529, loss: 0.002292864490300417
2023-01-24 09:29:45.588296: step: 1640/529, loss: 0.005180178210139275
2023-01-24 09:29:46.660723: step: 1644/529, loss: 0.00605470035225153
2023-01-24 09:29:47.744630: step: 1648/529, loss: 0.00026593913207761943
2023-01-24 09:29:48.821414: step: 1652/529, loss: 0.00044693052768707275
2023-01-24 09:29:49.891945: step: 1656/529, loss: 0.008743745274841785
2023-01-24 09:29:50.955795: step: 1660/529, loss: 0.001957723405212164
2023-01-24 09:29:52.049517: step: 1664/529, loss: 0.00011366964463377371
2023-01-24 09:29:53.139696: step: 1668/529, loss: 0.00282717845402658
2023-01-24 09:29:54.206876: step: 1672/529, loss: 0.0017495150677859783
2023-01-24 09:29:55.275745: step: 1676/529, loss: 0.014476480893790722
2023-01-24 09:29:56.351271: step: 1680/529, loss: 4.029765932500595e-06
2023-01-24 09:29:57.440325: step: 1684/529, loss: 0.0037144396919757128
2023-01-24 09:29:58.509321: step: 1688/529, loss: 0.0037353576626628637
2023-01-24 09:29:59.607056: step: 1692/529, loss: 0.0024860119447112083
2023-01-24 09:30:00.694521: step: 1696/529, loss: 0.017800122499465942
2023-01-24 09:30:01.776657: step: 1700/529, loss: 0.003148434916511178
2023-01-24 09:30:02.861184: step: 1704/529, loss: 0.00012700304796453565
2023-01-24 09:30:03.944764: step: 1708/529, loss: 0.0003432237426750362
2023-01-24 09:30:05.015250: step: 1712/529, loss: 0.015456571243703365
2023-01-24 09:30:06.096719: step: 1716/529, loss: 0.013328760862350464
2023-01-24 09:30:07.187975: step: 1720/529, loss: 0.021435288712382317
2023-01-24 09:30:08.248462: step: 1724/529, loss: 0.0032337489537894726
2023-01-24 09:30:09.331528: step: 1728/529, loss: 0.016377339139580727
2023-01-24 09:30:10.397222: step: 1732/529, loss: 1.6883181160665117e-05
2023-01-24 09:30:11.473688: step: 1736/529, loss: 0.002774052554741502
2023-01-24 09:30:12.557664: step: 1740/529, loss: 5.215403664493579e-09
2023-01-24 09:30:13.638843: step: 1744/529, loss: 0.0025115625467151403
2023-01-24 09:30:14.700284: step: 1748/529, loss: 9.311628673458472e-05
2023-01-24 09:30:15.781805: step: 1752/529, loss: 0.00018827612802851945
2023-01-24 09:30:16.854034: step: 1756/529, loss: 0.00016461798804812133
2023-01-24 09:30:17.926892: step: 1760/529, loss: 4.0593829908175394e-05
2023-01-24 09:30:19.011580: step: 1764/529, loss: 0.00020516736549325287
2023-01-24 09:30:20.096838: step: 1768/529, loss: 0.00025373511016368866
2023-01-24 09:30:21.169779: step: 1772/529, loss: 0.0007797826547175646
2023-01-24 09:30:22.238911: step: 1776/529, loss: 0.007685862015932798
2023-01-24 09:30:23.316666: step: 1780/529, loss: 0.003458377905189991
2023-01-24 09:30:24.410717: step: 1784/529, loss: 0.0002428066945867613
2023-01-24 09:30:25.491126: step: 1788/529, loss: 0.001367623801343143
2023-01-24 09:30:26.566843: step: 1792/529, loss: 0.0007303935708478093
2023-01-24 09:30:27.637665: step: 1796/529, loss: 0.0029274916741997004
2023-01-24 09:30:28.716376: step: 1800/529, loss: 0.005029785912483931
2023-01-24 09:30:29.791276: step: 1804/529, loss: 0.0007640636758878827
2023-01-24 09:30:30.859444: step: 1808/529, loss: 0.008094827644526958
2023-01-24 09:30:31.942806: step: 1812/529, loss: 0.0028483157511800528
2023-01-24 09:30:33.008714: step: 1816/529, loss: 0.003843510989099741
2023-01-24 09:30:34.072680: step: 1820/529, loss: 0.0028546745888888836
2023-01-24 09:30:35.154748: step: 1824/529, loss: 0.009414628148078918
2023-01-24 09:30:36.228252: step: 1828/529, loss: 0.000546939205378294
2023-01-24 09:30:37.320805: step: 1832/529, loss: 0.008302607573568821
2023-01-24 09:30:38.387456: step: 1836/529, loss: 0.0018023460870608687
2023-01-24 09:30:39.452510: step: 1840/529, loss: 0.0033640670590102673
2023-01-24 09:30:40.521971: step: 1844/529, loss: 0.00022593063476961106
2023-01-24 09:30:41.598545: step: 1848/529, loss: 0.0032788817770779133
2023-01-24 09:30:42.678919: step: 1852/529, loss: 0.0009824071312323213
2023-01-24 09:30:43.763866: step: 1856/529, loss: 0.0006703875842504203
2023-01-24 09:30:44.837477: step: 1860/529, loss: 4.0801351133268327e-05
2023-01-24 09:30:45.909798: step: 1864/529, loss: 0.005344883073121309
2023-01-24 09:30:46.994686: step: 1868/529, loss: 2.165043042623438e-05
2023-01-24 09:30:48.069819: step: 1872/529, loss: 0.001672480721026659
2023-01-24 09:30:49.131157: step: 1876/529, loss: 0.008345549926161766
2023-01-24 09:30:50.203777: step: 1880/529, loss: 0.004136687610298395
2023-01-24 09:30:51.301796: step: 1884/529, loss: 0.00020024561672471464
2023-01-24 09:30:52.364330: step: 1888/529, loss: 5.363531272450928e-06
2023-01-24 09:30:53.434127: step: 1892/529, loss: 0.0001777696015778929
2023-01-24 09:30:54.511055: step: 1896/529, loss: 0.0006320319953374565
2023-01-24 09:30:55.585590: step: 1900/529, loss: 0.005616499576717615
2023-01-24 09:30:56.650929: step: 1904/529, loss: 7.62258714530617e-05
2023-01-24 09:30:57.724514: step: 1908/529, loss: 0.001104343100450933
2023-01-24 09:30:58.783894: step: 1912/529, loss: 0.00019116631301585585
2023-01-24 09:30:59.850124: step: 1916/529, loss: 0.022298462688922882
2023-01-24 09:31:00.914404: step: 1920/529, loss: 3.74045739590656e-05
2023-01-24 09:31:02.002548: step: 1924/529, loss: 0.0010586337884888053
2023-01-24 09:31:03.094733: step: 1928/529, loss: 0.001114601967856288
2023-01-24 09:31:04.158656: step: 1932/529, loss: 0.0019243746064603329
2023-01-24 09:31:05.243157: step: 1936/529, loss: 0.0047816503793001175
2023-01-24 09:31:06.314767: step: 1940/529, loss: 6.0832117014797404e-05
2023-01-24 09:31:07.389529: step: 1944/529, loss: 0.007426185999065638
2023-01-24 09:31:08.485415: step: 1948/529, loss: 0.004662423860281706
2023-01-24 09:31:09.568554: step: 1952/529, loss: 0.00014836881018709391
2023-01-24 09:31:10.649156: step: 1956/529, loss: 0.037565406411886215
2023-01-24 09:31:11.730481: step: 1960/529, loss: 0.005257372744381428
2023-01-24 09:31:12.786960: step: 1964/529, loss: 0.004434757865965366
2023-01-24 09:31:13.857159: step: 1968/529, loss: 0.00023937605146784335
2023-01-24 09:31:14.944506: step: 1972/529, loss: 0.007027643732726574
2023-01-24 09:31:16.036181: step: 1976/529, loss: 0.0001306109334109351
2023-01-24 09:31:17.119805: step: 1980/529, loss: 0.004706720821559429
2023-01-24 09:31:18.204067: step: 1984/529, loss: 1.9174987755832262e-05
2023-01-24 09:31:19.272963: step: 1988/529, loss: 0.001869891188107431
2023-01-24 09:31:20.340712: step: 1992/529, loss: 0.04575552046298981
2023-01-24 09:31:21.429369: step: 1996/529, loss: 0.0015851868083700538
2023-01-24 09:31:22.499639: step: 2000/529, loss: 0.006763105280697346
2023-01-24 09:31:23.591736: step: 2004/529, loss: 0.00030633527785539627
2023-01-24 09:31:24.661603: step: 2008/529, loss: 0.010973074473440647
2023-01-24 09:31:25.721785: step: 2012/529, loss: 0.0033213645219802856
2023-01-24 09:31:26.776394: step: 2016/529, loss: 0.00019747317128349096
2023-01-24 09:31:27.847713: step: 2020/529, loss: 0.018144918605685234
2023-01-24 09:31:28.926916: step: 2024/529, loss: 0.00255021033808589
2023-01-24 09:31:29.971422: step: 2028/529, loss: 0.0002806618285831064
2023-01-24 09:31:31.037484: step: 2032/529, loss: 0.0019072286086156964
2023-01-24 09:31:32.109340: step: 2036/529, loss: 0.014130468480288982
2023-01-24 09:31:33.176607: step: 2040/529, loss: 0.0043364111334085464
2023-01-24 09:31:34.250417: step: 2044/529, loss: 0.0018080249428749084
2023-01-24 09:31:35.332602: step: 2048/529, loss: 0.0008840971859171987
2023-01-24 09:31:36.419863: step: 2052/529, loss: 0.007227852940559387
2023-01-24 09:31:37.514880: step: 2056/529, loss: 0.003201918676495552
2023-01-24 09:31:38.598315: step: 2060/529, loss: 0.001980405766516924
2023-01-24 09:31:39.668462: step: 2064/529, loss: 0.0018950875382870436
2023-01-24 09:31:40.740094: step: 2068/529, loss: 0.0025689273606985807
2023-01-24 09:31:41.813373: step: 2072/529, loss: 0.022754589095711708
2023-01-24 09:31:42.886534: step: 2076/529, loss: 0.00029317382723093033
2023-01-24 09:31:43.968298: step: 2080/529, loss: 0.0020040625240653753
2023-01-24 09:31:45.043532: step: 2084/529, loss: 0.003298926865682006
2023-01-24 09:31:46.122904: step: 2088/529, loss: 0.007333265617489815
2023-01-24 09:31:47.201029: step: 2092/529, loss: 0.0017135670641437173
2023-01-24 09:31:48.266726: step: 2096/529, loss: 0.004834538325667381
2023-01-24 09:31:49.353496: step: 2100/529, loss: 0.009966586716473103
2023-01-24 09:31:50.424881: step: 2104/529, loss: 0.0009601965430192649
2023-01-24 09:31:51.493359: step: 2108/529, loss: 0.0012738538207486272
2023-01-24 09:31:52.573121: step: 2112/529, loss: 0.002421914367005229
2023-01-24 09:31:53.632903: step: 2116/529, loss: 2.430733547953423e-05
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.336787069900424, 'r': 0.30866822535465804, 'f1': 0.32211515794436596}, 'combined': 0.2373480111169012, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33123997137625943, 'r': 0.29074832046353655, 'f1': 0.3096761357457932}, 'combined': 0.20217198499466293, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36079491649449036, 'r': 0.36147953682939454, 'f1': 0.36113690219732875}, 'combined': 0.26610087530329485, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3616709889821963, 'r': 0.3167945335478245, 'f1': 0.33774860607548557}, 'combined': 0.22049908997674186, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37866006023934745, 'r': 0.3477636985879396, 'f1': 0.36255483512530995}, 'combined': 0.26714566798707046, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3685121162985973, 'r': 0.30387867808644664, 'f1': 0.333088958667479}, 'combined': 0.21745704037358732, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36228352381783285, 'r': 0.3581588537174401, 'f1': 0.3602093815058987}, 'combined': 0.2654174390043464, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35743685856996116, 'r': 0.31242872472429506, 'f1': 0.3334207479156774}, 'combined': 0.21767364889831786, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:34:25.855416: step: 4/529, loss: 0.005550272762775421
2023-01-24 09:34:26.910358: step: 8/529, loss: 0.0007610549801029265
2023-01-24 09:34:27.962540: step: 12/529, loss: 0.0026525871362537146
2023-01-24 09:34:29.021268: step: 16/529, loss: 0.005220665596425533
2023-01-24 09:34:30.070525: step: 20/529, loss: 8.616345439804718e-05
2023-01-24 09:34:31.137700: step: 24/529, loss: 0.0083405626937747
2023-01-24 09:34:32.183908: step: 28/529, loss: 0.0013250771444290876
2023-01-24 09:34:33.265914: step: 32/529, loss: 0.0005602349410764873
2023-01-24 09:34:34.308882: step: 36/529, loss: 0.0012757163494825363
2023-01-24 09:34:35.356155: step: 40/529, loss: 0.0009365349542349577
2023-01-24 09:34:36.445849: step: 44/529, loss: 0.0006063762702979147
2023-01-24 09:34:37.510208: step: 48/529, loss: 0.006380933336913586
2023-01-24 09:34:38.562018: step: 52/529, loss: 0.005873164162039757
2023-01-24 09:34:39.639976: step: 56/529, loss: 5.03152523378958e-06
2023-01-24 09:34:40.696749: step: 60/529, loss: 0.001569485873915255
2023-01-24 09:34:41.762508: step: 64/529, loss: 0.0010876096785068512
2023-01-24 09:34:42.817963: step: 68/529, loss: 0.001101877074688673
2023-01-24 09:34:43.883057: step: 72/529, loss: 1.7718231902108528e-05
2023-01-24 09:34:44.955798: step: 76/529, loss: 0.0005937537644058466
2023-01-24 09:34:46.028062: step: 80/529, loss: 0.0003423927410040051
2023-01-24 09:34:47.090506: step: 84/529, loss: 0.0021822818089276552
2023-01-24 09:34:48.171324: step: 88/529, loss: 0.006153288297355175
2023-01-24 09:34:49.249646: step: 92/529, loss: 0.00023072838666848838
2023-01-24 09:34:50.311658: step: 96/529, loss: 0.0019809072837233543
2023-01-24 09:34:51.386857: step: 100/529, loss: 6.69790679239668e-05
2023-01-24 09:34:52.476538: step: 104/529, loss: 0.0020098222885280848
2023-01-24 09:34:53.556399: step: 108/529, loss: 0.0010741493897512555
2023-01-24 09:34:54.631014: step: 112/529, loss: 0.0008140694117173553
2023-01-24 09:34:55.714024: step: 116/529, loss: 5.615416739601642e-05
2023-01-24 09:34:56.794461: step: 120/529, loss: 0.00012135961151216179
2023-01-24 09:34:57.865978: step: 124/529, loss: 0.005974811967462301
2023-01-24 09:34:58.931976: step: 128/529, loss: 0.0013884353684261441
2023-01-24 09:35:00.002012: step: 132/529, loss: 0.00014729340909980237
2023-01-24 09:35:01.083176: step: 136/529, loss: 0.0027141727041453123
2023-01-24 09:35:02.140910: step: 140/529, loss: 0.05117199942469597
2023-01-24 09:35:03.203414: step: 144/529, loss: 0.0003811954229604453
2023-01-24 09:35:04.279942: step: 148/529, loss: 0.0009387718746438622
2023-01-24 09:35:05.357795: step: 152/529, loss: 0.0063337781466543674
2023-01-24 09:35:06.418136: step: 156/529, loss: 1.2615866751275462e-07
2023-01-24 09:35:07.485049: step: 160/529, loss: 0.0030080436263233423
2023-01-24 09:35:08.574150: step: 164/529, loss: 0.009680736809968948
2023-01-24 09:35:09.663232: step: 168/529, loss: 0.007572818081825972
2023-01-24 09:35:10.727641: step: 172/529, loss: 0.0037050042301416397
2023-01-24 09:35:11.809270: step: 176/529, loss: 0.0014902646653354168
2023-01-24 09:35:12.886262: step: 180/529, loss: 0.0034742115531116724
2023-01-24 09:35:13.954029: step: 184/529, loss: 0.010083647444844246
2023-01-24 09:35:15.035397: step: 188/529, loss: 0.005261592101305723
2023-01-24 09:35:16.116339: step: 192/529, loss: 0.009679010137915611
2023-01-24 09:35:17.191347: step: 196/529, loss: 0.0016269839834421873
2023-01-24 09:35:18.262610: step: 200/529, loss: 0.005767378956079483
2023-01-24 09:35:19.344099: step: 204/529, loss: 0.003280257573351264
2023-01-24 09:35:20.433582: step: 208/529, loss: 0.003496411256492138
2023-01-24 09:35:21.519606: step: 212/529, loss: 0.0013061660574749112
2023-01-24 09:35:22.590050: step: 216/529, loss: 0.005923225544393063
2023-01-24 09:35:23.655968: step: 220/529, loss: 0.004614126868546009
2023-01-24 09:35:24.746553: step: 224/529, loss: 0.007316398434340954
2023-01-24 09:35:25.807625: step: 228/529, loss: 0.002448020502924919
2023-01-24 09:35:26.888261: step: 232/529, loss: 0.014334214851260185
2023-01-24 09:35:27.950135: step: 236/529, loss: 0.0009581045596860349
2023-01-24 09:35:29.027891: step: 240/529, loss: 5.191339732846245e-05
2023-01-24 09:35:30.137917: step: 244/529, loss: 0.00016784474428277463
2023-01-24 09:35:31.217563: step: 248/529, loss: 0.0031329242046922445
2023-01-24 09:35:32.293818: step: 252/529, loss: 0.001772395451553166
2023-01-24 09:35:33.346708: step: 256/529, loss: 0.0015573803102597594
2023-01-24 09:35:34.412110: step: 260/529, loss: 0.00039358355570584536
2023-01-24 09:35:35.487248: step: 264/529, loss: 0.003650473663583398
2023-01-24 09:35:36.563292: step: 268/529, loss: 0.0006346809095703065
2023-01-24 09:35:37.658491: step: 272/529, loss: 1.9788350982707925e-05
2023-01-24 09:35:38.746554: step: 276/529, loss: 0.00807908084243536
2023-01-24 09:35:39.826735: step: 280/529, loss: 0.0016301866853609681
2023-01-24 09:35:40.916436: step: 284/529, loss: 0.004677473101764917
2023-01-24 09:35:41.997497: step: 288/529, loss: 0.0003901770105585456
2023-01-24 09:35:43.075957: step: 292/529, loss: 0.00012507506471592933
2023-01-24 09:35:44.152607: step: 296/529, loss: 0.008182822726666927
2023-01-24 09:35:45.240477: step: 300/529, loss: 0.0032544543500989676
2023-01-24 09:35:46.338375: step: 304/529, loss: 0.011036175303161144
2023-01-24 09:35:47.412556: step: 308/529, loss: 0.003701606299728155
2023-01-24 09:35:48.505735: step: 312/529, loss: 0.002165562007576227
2023-01-24 09:35:49.570339: step: 316/529, loss: 0.00017161211872007698
2023-01-24 09:35:50.643957: step: 320/529, loss: 0.0003640690993051976
2023-01-24 09:35:51.733185: step: 324/529, loss: 1.0542474626618059e-07
2023-01-24 09:35:52.815785: step: 328/529, loss: 0.0009929283987730742
2023-01-24 09:35:53.919692: step: 332/529, loss: 0.0060135601088404655
2023-01-24 09:35:55.016339: step: 336/529, loss: 1.0803737495734822e-05
2023-01-24 09:35:56.087223: step: 340/529, loss: 0.0031833513639867306
2023-01-24 09:35:57.171078: step: 344/529, loss: 0.0006615098100155592
2023-01-24 09:35:58.269427: step: 348/529, loss: 0.004738308489322662
2023-01-24 09:35:59.348496: step: 352/529, loss: 0.0011392160085961223
2023-01-24 09:36:00.445848: step: 356/529, loss: 6.718080840073526e-05
2023-01-24 09:36:01.540101: step: 360/529, loss: 5.5149335821624845e-05
2023-01-24 09:36:02.607608: step: 364/529, loss: 0.00018120997992809862
2023-01-24 09:36:03.696693: step: 368/529, loss: 0.0002326490357518196
2023-01-24 09:36:04.770580: step: 372/529, loss: 0.0011034633498638868
2023-01-24 09:36:05.857979: step: 376/529, loss: 0.012548612430691719
2023-01-24 09:36:06.928298: step: 380/529, loss: 0.00438894284889102
2023-01-24 09:36:07.985952: step: 384/529, loss: 0.0005325342644937336
2023-01-24 09:36:09.075077: step: 388/529, loss: 0.0005177184357307851
2023-01-24 09:36:10.162175: step: 392/529, loss: 0.00010126904089702293
2023-01-24 09:36:11.256955: step: 396/529, loss: 5.426102507044561e-05
2023-01-24 09:36:12.327736: step: 400/529, loss: 4.5438166125677526e-05
2023-01-24 09:36:13.393486: step: 404/529, loss: 0.001413967227563262
2023-01-24 09:36:14.477545: step: 408/529, loss: 1.5022586012491956e-05
2023-01-24 09:36:15.551828: step: 412/529, loss: 0.00252367090433836
2023-01-24 09:36:16.639634: step: 416/529, loss: 0.0029055026825517416
2023-01-24 09:36:17.734852: step: 420/529, loss: 0.003600257681682706
2023-01-24 09:36:18.819712: step: 424/529, loss: 0.003331037238240242
2023-01-24 09:36:19.909425: step: 428/529, loss: 0.0005742170033045113
2023-01-24 09:36:20.985296: step: 432/529, loss: 1.4974522855482064e-05
2023-01-24 09:36:22.065883: step: 436/529, loss: 0.0027157519944012165
2023-01-24 09:36:23.136240: step: 440/529, loss: 0.004017917905002832
2023-01-24 09:36:24.228473: step: 444/529, loss: 0.00242613791488111
2023-01-24 09:36:25.331055: step: 448/529, loss: 0.0020046711433678865
2023-01-24 09:36:26.429424: step: 452/529, loss: 0.0013640165561810136
2023-01-24 09:36:27.505811: step: 456/529, loss: 0.008201287128031254
2023-01-24 09:36:28.590072: step: 460/529, loss: 0.004405135754495859
2023-01-24 09:36:29.653653: step: 464/529, loss: 0.005086584482342005
2023-01-24 09:36:30.720382: step: 468/529, loss: 3.379970075911842e-05
2023-01-24 09:36:31.794771: step: 472/529, loss: 0.0019488012185320258
2023-01-24 09:36:32.888668: step: 476/529, loss: 0.0008598949643783271
2023-01-24 09:36:33.976403: step: 480/529, loss: 0.0041540260426700115
2023-01-24 09:36:35.049245: step: 484/529, loss: 0.0001484264066675678
2023-01-24 09:36:36.126390: step: 488/529, loss: 0.0028602289967238903
2023-01-24 09:36:37.195606: step: 492/529, loss: 0.0003589103580452502
2023-01-24 09:36:38.282663: step: 496/529, loss: 0.004425681196153164
2023-01-24 09:36:39.367716: step: 500/529, loss: 0.0037166171241551638
2023-01-24 09:36:40.439873: step: 504/529, loss: 0.0032905940897762775
2023-01-24 09:36:41.511484: step: 508/529, loss: 0.0026078030932694674
2023-01-24 09:36:42.578250: step: 512/529, loss: 0.0010439407778903842
2023-01-24 09:36:43.676416: step: 516/529, loss: 0.00939603429287672
2023-01-24 09:36:44.753022: step: 520/529, loss: 0.0077019608579576015
2023-01-24 09:36:45.846143: step: 524/529, loss: 0.0006680558435618877
2023-01-24 09:36:46.926411: step: 528/529, loss: 0.0001808326633181423
2023-01-24 09:36:48.008578: step: 532/529, loss: 0.0021404752042144537
2023-01-24 09:36:49.094438: step: 536/529, loss: 0.0001727363996906206
2023-01-24 09:36:50.174163: step: 540/529, loss: 0.0022375795524567366
2023-01-24 09:36:51.249048: step: 544/529, loss: 0.0009696347988210618
2023-01-24 09:36:52.333497: step: 548/529, loss: 0.00290606077760458
2023-01-24 09:36:53.411346: step: 552/529, loss: 0.003670124337077141
2023-01-24 09:36:54.489048: step: 556/529, loss: 0.00038866783143021166
2023-01-24 09:36:55.563485: step: 560/529, loss: 0.00025236618239432573
2023-01-24 09:36:56.648826: step: 564/529, loss: 0.007980805821716785
2023-01-24 09:36:57.724900: step: 568/529, loss: 2.9802293965985882e-08
2023-01-24 09:36:58.798918: step: 572/529, loss: 0.00014798915071878582
2023-01-24 09:36:59.876631: step: 576/529, loss: 0.0005282009369693696
2023-01-24 09:37:00.941923: step: 580/529, loss: 0.0007339513394981623
2023-01-24 09:37:02.019313: step: 584/529, loss: 0.00027704695821739733
2023-01-24 09:37:03.098367: step: 588/529, loss: 0.004597665276378393
2023-01-24 09:37:04.186991: step: 592/529, loss: 0.001893265056423843
2023-01-24 09:37:05.265612: step: 596/529, loss: 0.00017987325554713607
2023-01-24 09:37:06.356467: step: 600/529, loss: 0.0028877875301986933
2023-01-24 09:37:07.442451: step: 604/529, loss: 0.00735909678041935
2023-01-24 09:37:08.522980: step: 608/529, loss: 0.0003404644376132637
2023-01-24 09:37:09.588219: step: 612/529, loss: 0.008895325474441051
2023-01-24 09:37:10.663924: step: 616/529, loss: 5.1473551138769835e-05
2023-01-24 09:37:11.744989: step: 620/529, loss: 3.52718161593657e-05
2023-01-24 09:37:12.819084: step: 624/529, loss: 0.0007283874438144267
2023-01-24 09:37:13.914841: step: 628/529, loss: 0.0024800642859190702
2023-01-24 09:37:14.983985: step: 632/529, loss: 0.0035599025432020426
2023-01-24 09:37:16.055867: step: 636/529, loss: 0.0012787414016202092
2023-01-24 09:37:17.126651: step: 640/529, loss: 0.0066371182911098
2023-01-24 09:37:18.205968: step: 644/529, loss: 0.0006164282676763833
2023-01-24 09:37:19.282087: step: 648/529, loss: 0.0008739436743780971
2023-01-24 09:37:20.349083: step: 652/529, loss: 3.632759762695059e-05
2023-01-24 09:37:21.425730: step: 656/529, loss: 0.0008676178986206651
2023-01-24 09:37:22.497543: step: 660/529, loss: 0.0028725017327815294
2023-01-24 09:37:23.568479: step: 664/529, loss: 0.006448869127780199
2023-01-24 09:37:24.663170: step: 668/529, loss: 0.00020628042693715543
2023-01-24 09:37:25.734976: step: 672/529, loss: 0.0001328882935922593
2023-01-24 09:37:26.803471: step: 676/529, loss: 0.0027902175206691027
2023-01-24 09:37:27.901491: step: 680/529, loss: 2.019218982241e-06
2023-01-24 09:37:28.972803: step: 684/529, loss: 1.0821781870617997e-06
2023-01-24 09:37:30.060661: step: 688/529, loss: 5.632678949041292e-05
2023-01-24 09:37:31.125638: step: 692/529, loss: 0.0006660653743892908
2023-01-24 09:37:32.196170: step: 696/529, loss: 0.0005596240516752005
2023-01-24 09:37:33.272519: step: 700/529, loss: 9.715823398437351e-05
2023-01-24 09:37:34.336017: step: 704/529, loss: 0.0019281271379441023
2023-01-24 09:37:35.422491: step: 708/529, loss: 0.000764808792155236
2023-01-24 09:37:36.510711: step: 712/529, loss: 0.0011708365054801106
2023-01-24 09:37:37.586672: step: 716/529, loss: 0.0008129074121825397
2023-01-24 09:37:38.665779: step: 720/529, loss: 0.010915243066847324
2023-01-24 09:37:39.737246: step: 724/529, loss: 5.075321496406104e-06
2023-01-24 09:37:40.835643: step: 728/529, loss: 0.001940823276527226
2023-01-24 09:37:41.929323: step: 732/529, loss: 0.005649505648761988
2023-01-24 09:37:43.019487: step: 736/529, loss: 0.013434085063636303
2023-01-24 09:37:44.097520: step: 740/529, loss: 0.0003298694209661335
2023-01-24 09:37:45.179489: step: 744/529, loss: 0.007294130977243185
2023-01-24 09:37:46.258153: step: 748/529, loss: 1.9457265807432123e-06
2023-01-24 09:37:47.323093: step: 752/529, loss: 0.001068144221790135
2023-01-24 09:37:48.417279: step: 756/529, loss: 0.002726457780227065
2023-01-24 09:37:49.488303: step: 760/529, loss: 3.196978650521487e-05
2023-01-24 09:37:50.560983: step: 764/529, loss: 8.373675518669188e-05
2023-01-24 09:37:51.644889: step: 768/529, loss: 0.039239853620529175
2023-01-24 09:37:52.715219: step: 772/529, loss: 0.0013340356526896358
2023-01-24 09:37:53.792782: step: 776/529, loss: 0.011207184754312038
2023-01-24 09:37:54.889062: step: 780/529, loss: 0.003583451034501195
2023-01-24 09:37:55.974038: step: 784/529, loss: 0.007945828139781952
2023-01-24 09:37:57.065056: step: 788/529, loss: 0.018534524366259575
2023-01-24 09:37:58.128002: step: 792/529, loss: 1.5667070329072885e-05
2023-01-24 09:37:59.215385: step: 796/529, loss: 0.00035253335954621434
2023-01-24 09:38:00.299985: step: 800/529, loss: 0.0026388531550765038
2023-01-24 09:38:01.372554: step: 804/529, loss: 0.0035606969613581896
2023-01-24 09:38:02.468515: step: 808/529, loss: 0.00023287774820346385
2023-01-24 09:38:03.546547: step: 812/529, loss: 0.004454170353710651
2023-01-24 09:38:04.604612: step: 816/529, loss: 0.0
2023-01-24 09:38:05.687440: step: 820/529, loss: 2.568472837083391e-06
2023-01-24 09:38:06.780731: step: 824/529, loss: 7.068672130117193e-05
2023-01-24 09:38:07.856844: step: 828/529, loss: 0.00011554638331290334
2023-01-24 09:38:08.926810: step: 832/529, loss: 0.0009226802503690124
2023-01-24 09:38:09.989635: step: 836/529, loss: 7.057376205921173e-05
2023-01-24 09:38:11.060222: step: 840/529, loss: 0.008089513517916203
2023-01-24 09:38:12.138847: step: 844/529, loss: 0.0043051643297076225
2023-01-24 09:38:13.230567: step: 848/529, loss: 0.0011193244718015194
2023-01-24 09:38:14.312343: step: 852/529, loss: 0.002075742231681943
2023-01-24 09:38:15.397336: step: 856/529, loss: 0.004258294124156237
2023-01-24 09:38:16.495123: step: 860/529, loss: 0.01081676222383976
2023-01-24 09:38:17.593916: step: 864/529, loss: 0.0004502387309912592
2023-01-24 09:38:18.671389: step: 868/529, loss: 6.123903585830703e-05
2023-01-24 09:38:19.730988: step: 872/529, loss: 0.003467608941718936
2023-01-24 09:38:20.820495: step: 876/529, loss: 0.0009224391542375088
2023-01-24 09:38:21.898506: step: 880/529, loss: 9.106258858082583e-09
2023-01-24 09:38:22.974500: step: 884/529, loss: 0.001418363768607378
2023-01-24 09:38:24.061824: step: 888/529, loss: 0.0020852508023381233
2023-01-24 09:38:25.129922: step: 892/529, loss: 0.00016155694902408868
2023-01-24 09:38:26.202896: step: 896/529, loss: 0.0060864645056426525
2023-01-24 09:38:27.267366: step: 900/529, loss: 0.0028166677802801132
2023-01-24 09:38:28.346394: step: 904/529, loss: 0.00024000738631002605
2023-01-24 09:38:29.429074: step: 908/529, loss: 0.0015794719802215695
2023-01-24 09:38:30.491383: step: 912/529, loss: 1.4170055919748847e-06
2023-01-24 09:38:31.561080: step: 916/529, loss: 0.002193300984799862
2023-01-24 09:38:32.643609: step: 920/529, loss: 0.0037680587265640497
2023-01-24 09:38:33.717857: step: 924/529, loss: 0.0033980198204517365
2023-01-24 09:38:34.815682: step: 928/529, loss: 0.002662337850779295
2023-01-24 09:38:35.900673: step: 932/529, loss: 0.0006825101445429027
2023-01-24 09:38:36.975161: step: 936/529, loss: 0.004220837727189064
2023-01-24 09:38:38.091482: step: 940/529, loss: 0.000912040879484266
2023-01-24 09:38:39.163582: step: 944/529, loss: 0.00012912981037516147
2023-01-24 09:38:40.252948: step: 948/529, loss: 0.006432090420275927
2023-01-24 09:38:41.323508: step: 952/529, loss: 0.0020078851375728846
2023-01-24 09:38:42.412287: step: 956/529, loss: 0.00226851599290967
2023-01-24 09:38:43.487926: step: 960/529, loss: 0.0008618362480774522
2023-01-24 09:38:44.588323: step: 964/529, loss: 0.0027117962017655373
2023-01-24 09:38:45.675415: step: 968/529, loss: 0.000921405095141381
2023-01-24 09:38:46.739936: step: 972/529, loss: 0.0005355889443308115
2023-01-24 09:38:47.833557: step: 976/529, loss: 0.006245487369596958
2023-01-24 09:38:48.911067: step: 980/529, loss: 0.006575887091457844
2023-01-24 09:38:49.991441: step: 984/529, loss: 0.0007065368117764592
2023-01-24 09:38:51.068687: step: 988/529, loss: 0.004607339855283499
2023-01-24 09:38:52.131070: step: 992/529, loss: 0.005440534092485905
2023-01-24 09:38:53.189863: step: 996/529, loss: 0.002364398678764701
2023-01-24 09:38:54.261663: step: 1000/529, loss: 0.0004719163989648223
2023-01-24 09:38:55.341835: step: 1004/529, loss: 0.011130196042358875
2023-01-24 09:38:56.437430: step: 1008/529, loss: 0.0002421838289592415
2023-01-24 09:38:57.517269: step: 1012/529, loss: 0.0021815448999404907
2023-01-24 09:38:58.598412: step: 1016/529, loss: 0.0010663840221241117
2023-01-24 09:38:59.668406: step: 1020/529, loss: 9.196421888191253e-05
2023-01-24 09:39:00.756951: step: 1024/529, loss: 0.0016589164733886719
2023-01-24 09:39:01.826955: step: 1028/529, loss: 0.010646265931427479
2023-01-24 09:39:02.914565: step: 1032/529, loss: 0.0016196627402678132
2023-01-24 09:39:04.003268: step: 1036/529, loss: 0.001986629329621792
2023-01-24 09:39:05.069132: step: 1040/529, loss: 0.0003384593001101166
2023-01-24 09:39:06.142429: step: 1044/529, loss: 0.0003534338902682066
2023-01-24 09:39:07.234086: step: 1048/529, loss: 2.6854836505663116e-06
2023-01-24 09:39:08.315942: step: 1052/529, loss: 9.029432840179652e-05
2023-01-24 09:39:09.408604: step: 1056/529, loss: 2.8878250304842368e-05
2023-01-24 09:39:10.488659: step: 1060/529, loss: 0.005253805313259363
2023-01-24 09:39:11.562933: step: 1064/529, loss: 0.0022125833202153444
2023-01-24 09:39:12.639040: step: 1068/529, loss: 0.0007990999729372561
2023-01-24 09:39:13.721815: step: 1072/529, loss: 0.0017336050514131784
2023-01-24 09:39:14.791067: step: 1076/529, loss: 0.001977931708097458
2023-01-24 09:39:15.862740: step: 1080/529, loss: 0.0018157617887482047
2023-01-24 09:39:16.924821: step: 1084/529, loss: 6.831006612628698e-05
2023-01-24 09:39:18.002971: step: 1088/529, loss: 0.0008231173851527274
2023-01-24 09:39:19.061073: step: 1092/529, loss: 0.00012559779861476272
2023-01-24 09:39:20.139331: step: 1096/529, loss: 0.002117100404575467
2023-01-24 09:39:21.202024: step: 1100/529, loss: 0.00042675432632677257
2023-01-24 09:39:22.278761: step: 1104/529, loss: 2.101760037476197e-05
2023-01-24 09:39:23.358059: step: 1108/529, loss: 0.0029196669347584248
2023-01-24 09:39:24.422744: step: 1112/529, loss: 0.0001926364639075473
2023-01-24 09:39:25.508745: step: 1116/529, loss: 0.005537739954888821
2023-01-24 09:39:26.600526: step: 1120/529, loss: 0.0007231393246911466
2023-01-24 09:39:27.676308: step: 1124/529, loss: 0.0009354263311251998
2023-01-24 09:39:28.755874: step: 1128/529, loss: 0.0005767861730419099
2023-01-24 09:39:29.816975: step: 1132/529, loss: 0.0016078012995421886
2023-01-24 09:39:30.894055: step: 1136/529, loss: 0.0001219295445480384
2023-01-24 09:39:31.974798: step: 1140/529, loss: 0.002624856773763895
2023-01-24 09:39:33.057051: step: 1144/529, loss: 0.002847106661647558
2023-01-24 09:39:34.133447: step: 1148/529, loss: 0.004916645120829344
2023-01-24 09:39:35.242946: step: 1152/529, loss: 0.004542953800410032
2023-01-24 09:39:36.308268: step: 1156/529, loss: 0.00013412647240329534
2023-01-24 09:39:37.387267: step: 1160/529, loss: 0.0025263663846999407
2023-01-24 09:39:38.475578: step: 1164/529, loss: 0.0010383236221969128
2023-01-24 09:39:39.535149: step: 1168/529, loss: 0.0016580659430474043
2023-01-24 09:39:40.608878: step: 1172/529, loss: 0.005924290511757135
2023-01-24 09:39:41.683301: step: 1176/529, loss: 0.0013048473047092557
2023-01-24 09:39:42.777765: step: 1180/529, loss: 0.007904703728854656
2023-01-24 09:39:43.854113: step: 1184/529, loss: 0.00986100360751152
2023-01-24 09:39:44.939839: step: 1188/529, loss: 3.345069126226008e-05
2023-01-24 09:39:46.019302: step: 1192/529, loss: 0.004237491171807051
2023-01-24 09:39:47.107704: step: 1196/529, loss: 0.001981412759050727
2023-01-24 09:39:48.186425: step: 1200/529, loss: 0.0023590335622429848
2023-01-24 09:39:49.255433: step: 1204/529, loss: 0.013690161518752575
2023-01-24 09:39:50.336515: step: 1208/529, loss: 1.376276827613765e-06
2023-01-24 09:39:51.404475: step: 1212/529, loss: 0.00010868853860301897
2023-01-24 09:39:52.466656: step: 1216/529, loss: 0.002281750086694956
2023-01-24 09:39:53.546265: step: 1220/529, loss: 0.0008225697092711926
2023-01-24 09:39:54.617099: step: 1224/529, loss: 0.0002749623672571033
2023-01-24 09:39:55.701452: step: 1228/529, loss: 0.00037340051494538784
2023-01-24 09:39:56.771207: step: 1232/529, loss: 0.000289250718196854
2023-01-24 09:39:57.848382: step: 1236/529, loss: 0.0015886299079284072
2023-01-24 09:39:58.914026: step: 1240/529, loss: 0.0004179180832579732
2023-01-24 09:39:59.990806: step: 1244/529, loss: 8.27842128181544e-10
2023-01-24 09:40:01.075274: step: 1248/529, loss: 6.55414187349379e-05
2023-01-24 09:40:02.149592: step: 1252/529, loss: 0.0031209278386086226
2023-01-24 09:40:03.218609: step: 1256/529, loss: 0.0170805174857378
2023-01-24 09:40:04.308144: step: 1260/529, loss: 0.005246256478130817
2023-01-24 09:40:05.378935: step: 1264/529, loss: 0.000935079122427851
2023-01-24 09:40:06.449120: step: 1268/529, loss: 0.0010366657515987754
2023-01-24 09:40:07.519150: step: 1272/529, loss: 0.0015398615505546331
2023-01-24 09:40:08.635280: step: 1276/529, loss: 0.0023136036470532417
2023-01-24 09:40:09.712255: step: 1280/529, loss: 0.005282704718410969
2023-01-24 09:40:10.787853: step: 1284/529, loss: 0.0031433331314474344
2023-01-24 09:40:11.861895: step: 1288/529, loss: 0.004818292800337076
2023-01-24 09:40:12.953957: step: 1292/529, loss: 0.003580772550776601
2023-01-24 09:40:14.046372: step: 1296/529, loss: 0.000507801421917975
2023-01-24 09:40:15.114360: step: 1300/529, loss: 0.0007315064431168139
2023-01-24 09:40:16.186172: step: 1304/529, loss: 3.2765165087766945e-05
2023-01-24 09:40:17.257222: step: 1308/529, loss: 0.0001225455926032737
2023-01-24 09:40:18.339883: step: 1312/529, loss: 8.749850530875847e-05
2023-01-24 09:40:19.414951: step: 1316/529, loss: 0.0018611084669828415
2023-01-24 09:40:20.486884: step: 1320/529, loss: 0.006996247451752424
2023-01-24 09:40:21.568116: step: 1324/529, loss: 0.0002824230177793652
2023-01-24 09:40:22.641177: step: 1328/529, loss: 0.0020704646594822407
2023-01-24 09:40:23.708020: step: 1332/529, loss: 0.003465651534497738
2023-01-24 09:40:24.814778: step: 1336/529, loss: 0.0008402460371144116
2023-01-24 09:40:25.877271: step: 1340/529, loss: 0.0015167383244261146
2023-01-24 09:40:26.965497: step: 1344/529, loss: 0.0034511748235672712
2023-01-24 09:40:28.030734: step: 1348/529, loss: 0.00018992846889887005
2023-01-24 09:40:29.108878: step: 1352/529, loss: 0.0006809252081438899
2023-01-24 09:40:30.184460: step: 1356/529, loss: 0.00016157186473719776
2023-01-24 09:40:31.264159: step: 1360/529, loss: 0.006505895871669054
2023-01-24 09:40:32.350124: step: 1364/529, loss: 0.0003203966189175844
2023-01-24 09:40:33.415415: step: 1368/529, loss: 0.0004957928322255611
2023-01-24 09:40:34.478542: step: 1372/529, loss: 1.3241086890047882e-05
2023-01-24 09:40:35.559768: step: 1376/529, loss: 0.0001145578280556947
2023-01-24 09:40:36.627897: step: 1380/529, loss: 0.0009045111946761608
2023-01-24 09:40:37.719518: step: 1384/529, loss: 0.0012526812497526407
2023-01-24 09:40:38.791486: step: 1388/529, loss: 0.010926326736807823
2023-01-24 09:40:39.867763: step: 1392/529, loss: 0.0011335014132782817
2023-01-24 09:40:40.934707: step: 1396/529, loss: 0.0012295488268136978
2023-01-24 09:40:42.002955: step: 1400/529, loss: 0.0005643097683787346
2023-01-24 09:40:43.101423: step: 1404/529, loss: 0.0018103045877069235
2023-01-24 09:40:44.169161: step: 1408/529, loss: 0.00015527053619734943
2023-01-24 09:40:45.240739: step: 1412/529, loss: 0.0007706593023613095
2023-01-24 09:40:46.319418: step: 1416/529, loss: 0.0016050555277615786
2023-01-24 09:40:47.402579: step: 1420/529, loss: 0.0001577777584316209
2023-01-24 09:40:48.475750: step: 1424/529, loss: 0.004776421003043652
2023-01-24 09:40:49.578332: step: 1428/529, loss: 0.001445088186301291
2023-01-24 09:40:50.671236: step: 1432/529, loss: 0.00047005570377223194
2023-01-24 09:40:51.735941: step: 1436/529, loss: 0.00777039211243391
2023-01-24 09:40:52.817446: step: 1440/529, loss: 0.007142259739339352
2023-01-24 09:40:53.910023: step: 1444/529, loss: 0.006781228817999363
2023-01-24 09:40:54.971503: step: 1448/529, loss: 3.7252889661942845e-09
2023-01-24 09:40:56.060561: step: 1452/529, loss: 0.0027382178232073784
2023-01-24 09:40:57.145477: step: 1456/529, loss: 0.003530877409502864
2023-01-24 09:40:58.230785: step: 1460/529, loss: 0.0001910785649670288
2023-01-24 09:40:59.307072: step: 1464/529, loss: 0.0015563304768875241
2023-01-24 09:41:00.393300: step: 1468/529, loss: 0.003940044902265072
2023-01-24 09:41:01.467764: step: 1472/529, loss: 0.00015611646813340485
2023-01-24 09:41:02.541981: step: 1476/529, loss: 0.0033869983162730932
2023-01-24 09:41:03.623539: step: 1480/529, loss: 0.0012347704032436013
2023-01-24 09:41:04.698563: step: 1484/529, loss: 2.8247177397133783e-05
2023-01-24 09:41:05.782240: step: 1488/529, loss: 0.0005833734758198261
2023-01-24 09:41:06.840261: step: 1492/529, loss: 0.002017692429944873
2023-01-24 09:41:07.893467: step: 1496/529, loss: 0.013612544164061546
2023-01-24 09:41:08.998719: step: 1500/529, loss: 0.0019536535255610943
2023-01-24 09:41:10.111624: step: 1504/529, loss: 0.00017686377395875752
2023-01-24 09:41:11.185920: step: 1508/529, loss: 0.0031346355099231005
2023-01-24 09:41:12.270995: step: 1512/529, loss: 0.0034271629992872477
2023-01-24 09:41:13.355620: step: 1516/529, loss: 0.002846606308594346
2023-01-24 09:41:14.436114: step: 1520/529, loss: 6.15144963376224e-05
2023-01-24 09:41:15.514873: step: 1524/529, loss: 0.007690890692174435
2023-01-24 09:41:16.584474: step: 1528/529, loss: 0.0006451900117099285
2023-01-24 09:41:17.665164: step: 1532/529, loss: 0.0039938329719007015
2023-01-24 09:41:18.735154: step: 1536/529, loss: 0.008942309767007828
2023-01-24 09:41:19.803195: step: 1540/529, loss: 0.00010460113117005676
2023-01-24 09:41:20.863284: step: 1544/529, loss: 3.533124618115835e-05
2023-01-24 09:41:21.943963: step: 1548/529, loss: 0.0014272828120738268
2023-01-24 09:41:23.024569: step: 1552/529, loss: 0.0005007721483707428
2023-01-24 09:41:24.115659: step: 1556/529, loss: 0.00017079628014471382
2023-01-24 09:41:25.203724: step: 1560/529, loss: 0.0011937690433114767
2023-01-24 09:41:26.284723: step: 1564/529, loss: 0.0011961006093770266
2023-01-24 09:41:27.351882: step: 1568/529, loss: 0.0019001393811777234
2023-01-24 09:41:28.417148: step: 1572/529, loss: 0.011626417748630047
2023-01-24 09:41:29.485068: step: 1576/529, loss: 4.191290372546064e-06
2023-01-24 09:41:30.562527: step: 1580/529, loss: 0.0005881005199626088
2023-01-24 09:41:31.628170: step: 1584/529, loss: 0.0011072555789723992
2023-01-24 09:41:32.706326: step: 1588/529, loss: 0.00021221810311544687
2023-01-24 09:41:33.789306: step: 1592/529, loss: 0.0037836190313100815
2023-01-24 09:41:34.859036: step: 1596/529, loss: 0.0002930145710706711
2023-01-24 09:41:35.938373: step: 1600/529, loss: 0.00012631977733690292
2023-01-24 09:41:36.997740: step: 1604/529, loss: 0.006007087882608175
2023-01-24 09:41:38.062505: step: 1608/529, loss: 1.868352592282463e-05
2023-01-24 09:41:39.149566: step: 1612/529, loss: 0.0016673553036525846
2023-01-24 09:41:40.219697: step: 1616/529, loss: 0.00011032953625544906
2023-01-24 09:41:41.304334: step: 1620/529, loss: 0.0040433513931930065
2023-01-24 09:41:42.383212: step: 1624/529, loss: 0.0008833800093270838
2023-01-24 09:41:43.447649: step: 1628/529, loss: 0.00011601475853240117
2023-01-24 09:41:44.516362: step: 1632/529, loss: 6.98849034961313e-05
2023-01-24 09:41:45.593218: step: 1636/529, loss: 0.003080921247601509
2023-01-24 09:41:46.655792: step: 1640/529, loss: 0.008081153966486454
2023-01-24 09:41:47.738085: step: 1644/529, loss: 0.004066224675625563
2023-01-24 09:41:48.822079: step: 1648/529, loss: 7.912777800811455e-05
2023-01-24 09:41:49.888667: step: 1652/529, loss: 6.255049811443314e-05
2023-01-24 09:41:50.954684: step: 1656/529, loss: 0.0005993222002871335
2023-01-24 09:41:52.019774: step: 1660/529, loss: 0.00011411066225264221
2023-01-24 09:41:53.102526: step: 1664/529, loss: 0.0017574802041053772
2023-01-24 09:41:54.164447: step: 1668/529, loss: 0.006759719457477331
2023-01-24 09:41:55.265686: step: 1672/529, loss: 0.0006977932062000036
2023-01-24 09:41:56.353236: step: 1676/529, loss: 0.0015799521934241056
2023-01-24 09:41:57.420399: step: 1680/529, loss: 0.0006595553131774068
2023-01-24 09:41:58.483086: step: 1684/529, loss: 0.0002391458983765915
2023-01-24 09:41:59.553990: step: 1688/529, loss: 0.0008294139988720417
2023-01-24 09:42:00.648681: step: 1692/529, loss: 0.002560486551374197
2023-01-24 09:42:01.733107: step: 1696/529, loss: 0.01014238502830267
2023-01-24 09:42:02.823216: step: 1700/529, loss: 0.0023997356183826923
2023-01-24 09:42:03.913444: step: 1704/529, loss: 0.0002925774606410414
2023-01-24 09:42:04.988378: step: 1708/529, loss: 2.1410052795545198e-05
2023-01-24 09:42:06.065939: step: 1712/529, loss: 0.0041291615925729275
2023-01-24 09:42:07.136335: step: 1716/529, loss: 0.0033650079276412725
2023-01-24 09:42:08.207891: step: 1720/529, loss: 0.00014977413229644299
2023-01-24 09:42:09.297992: step: 1724/529, loss: 0.0005717944004572928
2023-01-24 09:42:10.362474: step: 1728/529, loss: 0.0017060530371963978
2023-01-24 09:42:11.445257: step: 1732/529, loss: 0.00021760266099590808
2023-01-24 09:42:12.514995: step: 1736/529, loss: 0.01043646689504385
2023-01-24 09:42:13.613630: step: 1740/529, loss: 0.00029296407592482865
2023-01-24 09:42:14.688671: step: 1744/529, loss: 9.995861910283566e-05
2023-01-24 09:42:15.753058: step: 1748/529, loss: 0.004003719426691532
2023-01-24 09:42:16.820033: step: 1752/529, loss: 0.0003494007105473429
2023-01-24 09:42:17.898261: step: 1756/529, loss: 0.017226722091436386
2023-01-24 09:42:18.986375: step: 1760/529, loss: 0.015792647376656532
2023-01-24 09:42:20.059163: step: 1764/529, loss: 0.0004726860497612506
2023-01-24 09:42:21.136346: step: 1768/529, loss: 0.000832783873192966
2023-01-24 09:42:22.206585: step: 1772/529, loss: 4.9931190005736426e-05
2023-01-24 09:42:23.279895: step: 1776/529, loss: 0.003307485254481435
2023-01-24 09:42:24.346306: step: 1780/529, loss: 0.00029952405020594597
2023-01-24 09:42:25.430750: step: 1784/529, loss: 0.0008505576406605542
2023-01-24 09:42:26.488772: step: 1788/529, loss: 8.7362015619874e-05
2023-01-24 09:42:27.553959: step: 1792/529, loss: 0.00031362142181023955
2023-01-24 09:42:28.631343: step: 1796/529, loss: 0.0051210420206189156
2023-01-24 09:42:29.701456: step: 1800/529, loss: 0.001576750073581934
2023-01-24 09:42:30.773803: step: 1804/529, loss: 0.0009034052491188049
2023-01-24 09:42:31.870084: step: 1808/529, loss: 0.008525361306965351
2023-01-24 09:42:32.940876: step: 1812/529, loss: 6.831515406702238e-07
2023-01-24 09:42:34.011077: step: 1816/529, loss: 9.70430119195953e-05
2023-01-24 09:42:35.068566: step: 1820/529, loss: 0.0005761044449172914
2023-01-24 09:42:36.148261: step: 1824/529, loss: 0.003197520272806287
2023-01-24 09:42:37.229437: step: 1828/529, loss: 0.0046645235270261765
2023-01-24 09:42:38.303187: step: 1832/529, loss: 0.003829003544524312
2023-01-24 09:42:39.382338: step: 1836/529, loss: 0.004863250534981489
2023-01-24 09:42:40.469197: step: 1840/529, loss: 0.0019632449839264154
2023-01-24 09:42:41.548240: step: 1844/529, loss: 4.454702138900757e-05
2023-01-24 09:42:42.631125: step: 1848/529, loss: 0.0008929175091907382
2023-01-24 09:42:43.693413: step: 1852/529, loss: 0.0005542693543247879
2023-01-24 09:42:44.772583: step: 1856/529, loss: 0.0023257785942405462
2023-01-24 09:42:45.864567: step: 1860/529, loss: 7.65239165048115e-05
2023-01-24 09:42:46.924986: step: 1864/529, loss: 1.213531504618004e-05
2023-01-24 09:42:47.970950: step: 1868/529, loss: 0.0008265121723525226
2023-01-24 09:42:49.043442: step: 1872/529, loss: 0.001287953113205731
2023-01-24 09:42:50.121624: step: 1876/529, loss: 4.980025187251158e-05
2023-01-24 09:42:51.201965: step: 1880/529, loss: 0.0007879058830440044
2023-01-24 09:42:52.282902: step: 1884/529, loss: 6.111104448791593e-05
2023-01-24 09:42:53.347877: step: 1888/529, loss: 0.0005668092053383589
2023-01-24 09:42:54.423423: step: 1892/529, loss: 3.9842714613769203e-05
2023-01-24 09:42:55.510146: step: 1896/529, loss: 0.00296900887042284
2023-01-24 09:42:56.577408: step: 1900/529, loss: 0.004442651756107807
2023-01-24 09:42:57.640181: step: 1904/529, loss: 0.0005830864538438618
2023-01-24 09:42:58.718199: step: 1908/529, loss: 0.004742756485939026
2023-01-24 09:42:59.808705: step: 1912/529, loss: 0.0048843384720385075
2023-01-24 09:43:00.883132: step: 1916/529, loss: 2.110856939907535e-06
2023-01-24 09:43:01.964510: step: 1920/529, loss: 0.010243343189358711
2023-01-24 09:43:03.029182: step: 1924/529, loss: 0.003939337562769651
2023-01-24 09:43:04.092305: step: 1928/529, loss: 5.353868800739292e-06
2023-01-24 09:43:05.158742: step: 1932/529, loss: 4.694567178376019e-05
2023-01-24 09:43:06.226348: step: 1936/529, loss: 0.0004204769793432206
2023-01-24 09:43:07.306933: step: 1940/529, loss: 0.0019293130608275533
2023-01-24 09:43:08.382857: step: 1944/529, loss: 0.004171682987362146
2023-01-24 09:43:09.474887: step: 1948/529, loss: 0.00016569948638789356
2023-01-24 09:43:10.552843: step: 1952/529, loss: 0.002988734282553196
2023-01-24 09:43:11.639357: step: 1956/529, loss: 0.0009037981508299708
2023-01-24 09:43:12.712684: step: 1960/529, loss: 0.0018470805371180177
2023-01-24 09:43:13.806402: step: 1964/529, loss: 0.011918551288545132
2023-01-24 09:43:14.875511: step: 1968/529, loss: 0.0007112628081813455
2023-01-24 09:43:15.958053: step: 1972/529, loss: 0.0018391464836895466
2023-01-24 09:43:17.042923: step: 1976/529, loss: 0.011291444301605225
2023-01-24 09:43:18.130707: step: 1980/529, loss: 0.0011909948661923409
2023-01-24 09:43:19.203931: step: 1984/529, loss: 0.006228840909898281
2023-01-24 09:43:20.267213: step: 1988/529, loss: 0.026630794629454613
2023-01-24 09:43:21.336609: step: 1992/529, loss: 0.0002000487584155053
2023-01-24 09:43:22.412357: step: 1996/529, loss: 0.002114376286044717
2023-01-24 09:43:23.495852: step: 2000/529, loss: 0.004504579585045576
2023-01-24 09:43:24.570194: step: 2004/529, loss: 0.010221246629953384
2023-01-24 09:43:25.639299: step: 2008/529, loss: 0.0012430810602381825
2023-01-24 09:43:26.725438: step: 2012/529, loss: 0.0018100414890795946
2023-01-24 09:43:27.802674: step: 2016/529, loss: 0.002091814298182726
2023-01-24 09:43:28.876719: step: 2020/529, loss: 0.0011974122608080506
2023-01-24 09:43:29.944180: step: 2024/529, loss: 0.005928805563598871
2023-01-24 09:43:31.043272: step: 2028/529, loss: 0.005593332927674055
2023-01-24 09:43:32.124089: step: 2032/529, loss: 0.0004174827190581709
2023-01-24 09:43:33.195883: step: 2036/529, loss: 0.014579106122255325
2023-01-24 09:43:34.261874: step: 2040/529, loss: 0.004975006449967623
2023-01-24 09:43:35.344829: step: 2044/529, loss: 0.0005144670139998198
2023-01-24 09:43:36.437655: step: 2048/529, loss: 0.007221609819680452
2023-01-24 09:43:37.522229: step: 2052/529, loss: 0.0027210204862058163
2023-01-24 09:43:38.591842: step: 2056/529, loss: 0.0006094719283282757
2023-01-24 09:43:39.668878: step: 2060/529, loss: 0.0035577979870140553
2023-01-24 09:43:40.739182: step: 2064/529, loss: 0.0004641000123228878
2023-01-24 09:43:41.791403: step: 2068/529, loss: 9.884611063171178e-05
2023-01-24 09:43:42.879491: step: 2072/529, loss: 0.0006773408968001604
2023-01-24 09:43:43.948718: step: 2076/529, loss: 6.177403702167794e-05
2023-01-24 09:43:45.030237: step: 2080/529, loss: 0.003080954309552908
2023-01-24 09:43:46.094556: step: 2084/529, loss: 0.01797344535589218
2023-01-24 09:43:47.168390: step: 2088/529, loss: 0.0004905228852294385
2023-01-24 09:43:48.234869: step: 2092/529, loss: 0.000253918522503227
2023-01-24 09:43:49.309003: step: 2096/529, loss: 0.0067605916410684586
2023-01-24 09:43:50.378393: step: 2100/529, loss: 0.003052406944334507
2023-01-24 09:43:51.447892: step: 2104/529, loss: 0.005314346868544817
2023-01-24 09:43:52.539429: step: 2108/529, loss: 0.0005654231645166874
2023-01-24 09:43:53.621950: step: 2112/529, loss: 0.005869102198630571
2023-01-24 09:43:54.690527: step: 2116/529, loss: 0.007144043687731028
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3374058487513902, 'r': 0.3015524758290413, 'f1': 0.3184732560358813}, 'combined': 0.23466450444749146, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3346349351345762, 'r': 0.29557368811059537, 'f1': 0.3138937751725991}, 'combined': 0.20492546980180043, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35830098455933385, 'r': 0.35626132051060894, 'f1': 0.3572782415016002}, 'combined': 0.26325765163275805, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3590476941238542, 'r': 0.3144967394301774, 'f1': 0.33529882655564236}, 'combined': 0.21889975205187015, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37452782883438873, 'r': 0.34396863217427737, 'f1': 0.3585983563913831}, 'combined': 0.2642303678673349, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.36939570944517397, 'r': 0.3055663037689858, 'f1': 0.33446291599663636}, 'combined': 0.21835402805998022, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.45652173913043476, 'f1': 0.41176470588235287}, 'combined': 0.20588235294117643, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34663437183384, 'r': 0.30914260865636584, 'f1': 0.3268167598032193}, 'combined': 0.2408123493286879, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247017155531567, 'r': 0.29097809987530127, 'f1': 0.30691630893294014}, 'combined': 0.20037023277487284, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3771929824561403, 'r': 0.4095238095238095, 'f1': 0.3926940639269406}, 'combined': 0.2617960426179604, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36228352381783285, 'r': 0.3581588537174401, 'f1': 0.3602093815058987}, 'combined': 0.2654174390043464, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.35743685856996116, 'r': 0.31242872472429506, 'f1': 0.3334207479156774}, 'combined': 0.21767364889831786, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4017857142857143, 'r': 0.4891304347826087, 'f1': 0.4411764705882353}, 'combined': 0.22058823529411764, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831345911395494, 'r': 0.34823808188964733, 'f1': 0.3648538154191733}, 'combined': 0.26883965346675925, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3725766910621861, 'r': 0.3064854214160446, 'f1': 0.33631481442325417}, 'combined': 0.2195630394680312, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}