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 05:58:51.899468: step: 4/526, loss: 0.011542052030563354
2023-01-24 05:58:52.972977: step: 8/526, loss: 0.02023157849907875
2023-01-24 05:58:54.021486: step: 12/526, loss: 0.06262841820716858
2023-01-24 05:58:55.082968: step: 16/526, loss: 0.05780504643917084
2023-01-24 05:58:56.139526: step: 20/526, loss: 0.020506612956523895
2023-01-24 05:58:57.203669: step: 24/526, loss: 0.01437404379248619
2023-01-24 05:58:58.275907: step: 28/526, loss: 0.020581595599651337
2023-01-24 05:58:59.331902: step: 32/526, loss: 0.027495669201016426
2023-01-24 05:59:00.386499: step: 36/526, loss: 0.020445631816983223
2023-01-24 05:59:01.459522: step: 40/526, loss: 0.017695395275950432
2023-01-24 05:59:02.523070: step: 44/526, loss: 0.031221332028508186
2023-01-24 05:59:03.597505: step: 48/526, loss: 0.02319531887769699
2023-01-24 05:59:04.666000: step: 52/526, loss: 0.01580868847668171
2023-01-24 05:59:05.730926: step: 56/526, loss: 0.012067344039678574
2023-01-24 05:59:06.794856: step: 60/526, loss: 0.01946335658431053
2023-01-24 05:59:07.869014: step: 64/526, loss: 0.025493476539850235
2023-01-24 05:59:08.929497: step: 68/526, loss: 0.01326130423694849
2023-01-24 05:59:09.994947: step: 72/526, loss: 0.028966855257749557
2023-01-24 05:59:11.063949: step: 76/526, loss: 0.015298008918762207
2023-01-24 05:59:12.130205: step: 80/526, loss: 0.008636180311441422
2023-01-24 05:59:13.203453: step: 84/526, loss: 0.061954278498888016
2023-01-24 05:59:14.263486: step: 88/526, loss: 0.03162294626235962
2023-01-24 05:59:15.314990: step: 92/526, loss: 0.006181944161653519
2023-01-24 05:59:16.401535: step: 96/526, loss: 0.014761177822947502
2023-01-24 05:59:17.463331: step: 100/526, loss: 0.009932223707437515
2023-01-24 05:59:18.529573: step: 104/526, loss: 0.014439082704484463
2023-01-24 05:59:19.602629: step: 108/526, loss: 0.012355302460491657
2023-01-24 05:59:20.675552: step: 112/526, loss: 0.014503220096230507
2023-01-24 05:59:21.748658: step: 116/526, loss: 0.011955962516367435
2023-01-24 05:59:22.806033: step: 120/526, loss: 0.009412375278770924
2023-01-24 05:59:23.897366: step: 124/526, loss: 0.010395512916147709
2023-01-24 05:59:24.972697: step: 128/526, loss: 0.019374214112758636
2023-01-24 05:59:26.030257: step: 132/526, loss: 0.014935505576431751
2023-01-24 05:59:27.092536: step: 136/526, loss: 0.009510563686490059
2023-01-24 05:59:28.159720: step: 140/526, loss: 0.01242282334715128
2023-01-24 05:59:29.217489: step: 144/526, loss: 0.02149650827050209
2023-01-24 05:59:30.298484: step: 148/526, loss: 0.014446397311985493
2023-01-24 05:59:31.378703: step: 152/526, loss: 0.020998205989599228
2023-01-24 05:59:32.461825: step: 156/526, loss: 0.017171582207083702
2023-01-24 05:59:33.546616: step: 160/526, loss: 0.05841045081615448
2023-01-24 05:59:34.619690: step: 164/526, loss: 0.04393700510263443
2023-01-24 05:59:35.701447: step: 168/526, loss: 0.0171918086707592
2023-01-24 05:59:36.773848: step: 172/526, loss: 0.012977737002074718
2023-01-24 05:59:37.841217: step: 176/526, loss: 0.019465535879135132
2023-01-24 05:59:38.899474: step: 180/526, loss: 0.04735732451081276
2023-01-24 05:59:39.962606: step: 184/526, loss: 0.011476998217403889
2023-01-24 05:59:41.028584: step: 188/526, loss: 0.02026982232928276
2023-01-24 05:59:42.095454: step: 192/526, loss: 0.02624250203371048
2023-01-24 05:59:43.160356: step: 196/526, loss: 0.03472770005464554
2023-01-24 05:59:44.240417: step: 200/526, loss: 0.015562203712761402
2023-01-24 05:59:45.303259: step: 204/526, loss: 0.024400711059570312
2023-01-24 05:59:46.364907: step: 208/526, loss: 0.018951723352074623
2023-01-24 05:59:47.427692: step: 212/526, loss: 0.01060152892023325
2023-01-24 05:59:48.494655: step: 216/526, loss: 0.006733638234436512
2023-01-24 05:59:49.554265: step: 220/526, loss: 0.015451989136636257
2023-01-24 05:59:50.623616: step: 224/526, loss: 0.023213978856801987
2023-01-24 05:59:51.696874: step: 228/526, loss: 0.010583912953734398
2023-01-24 05:59:52.771123: step: 232/526, loss: 0.031098660081624985
2023-01-24 05:59:53.856706: step: 236/526, loss: 0.01834714412689209
2023-01-24 05:59:54.947042: step: 240/526, loss: 0.07209409773349762
2023-01-24 05:59:56.018647: step: 244/526, loss: 0.011912657879292965
2023-01-24 05:59:57.098982: step: 248/526, loss: 0.06079801544547081
2023-01-24 05:59:58.198666: step: 252/526, loss: 0.02100806124508381
2023-01-24 05:59:59.291151: step: 256/526, loss: 0.048354655504226685
2023-01-24 06:00:00.369772: step: 260/526, loss: 0.003983271773904562
2023-01-24 06:00:01.444651: step: 264/526, loss: 0.028111929073929787
2023-01-24 06:00:02.517854: step: 268/526, loss: 0.012731669470667839
2023-01-24 06:00:03.632736: step: 272/526, loss: 0.013230368494987488
2023-01-24 06:00:04.702842: step: 276/526, loss: 0.04263673722743988
2023-01-24 06:00:05.780611: step: 280/526, loss: 0.014705047011375427
2023-01-24 06:00:06.851423: step: 284/526, loss: 0.005776818376034498
2023-01-24 06:00:07.929965: step: 288/526, loss: 0.041990526020526886
2023-01-24 06:00:09.006899: step: 292/526, loss: 0.009674874134361744
2023-01-24 06:00:10.074391: step: 296/526, loss: 0.06541553139686584
2023-01-24 06:00:11.146819: step: 300/526, loss: 0.011652745306491852
2023-01-24 06:00:12.217851: step: 304/526, loss: 0.021124111488461494
2023-01-24 06:00:13.306247: step: 308/526, loss: 0.032830338925123215
2023-01-24 06:00:14.408513: step: 312/526, loss: 0.055567238479852676
2023-01-24 06:00:15.482498: step: 316/526, loss: 0.008490262553095818
2023-01-24 06:00:16.558296: step: 320/526, loss: 0.03531695902347565
2023-01-24 06:00:17.629212: step: 324/526, loss: 0.039421889930963516
2023-01-24 06:00:18.716084: step: 328/526, loss: 0.038977764546871185
2023-01-24 06:00:19.805686: step: 332/526, loss: 0.07475990056991577
2023-01-24 06:00:20.876738: step: 336/526, loss: 0.012722814455628395
2023-01-24 06:00:21.931897: step: 340/526, loss: 0.006297828629612923
2023-01-24 06:00:23.006568: step: 344/526, loss: 0.014703561551868916
2023-01-24 06:00:24.093053: step: 348/526, loss: 0.04576403275132179
2023-01-24 06:00:25.174543: step: 352/526, loss: 0.030041227117180824
2023-01-24 06:00:26.247617: step: 356/526, loss: 0.013157275505363941
2023-01-24 06:00:27.317886: step: 360/526, loss: 0.01257038302719593
2023-01-24 06:00:28.411206: step: 364/526, loss: 0.011035998351871967
2023-01-24 06:00:29.505556: step: 368/526, loss: 0.06662046909332275
2023-01-24 06:00:30.580154: step: 372/526, loss: 0.00764904310926795
2023-01-24 06:00:31.668398: step: 376/526, loss: 0.012579564936459064
2023-01-24 06:00:32.766078: step: 380/526, loss: 0.0183241069316864
2023-01-24 06:00:33.826502: step: 384/526, loss: 0.011891600675880909
2023-01-24 06:00:34.923318: step: 388/526, loss: 0.009133614599704742
2023-01-24 06:00:36.015971: step: 392/526, loss: 0.00827095378190279
2023-01-24 06:00:37.089985: step: 396/526, loss: 0.07623982429504395
2023-01-24 06:00:38.169137: step: 400/526, loss: 0.07408555597066879
2023-01-24 06:00:39.249974: step: 404/526, loss: 0.01287064142525196
2023-01-24 06:00:40.315441: step: 408/526, loss: 0.04000311717391014
2023-01-24 06:00:41.392766: step: 412/526, loss: 0.014216827228665352
2023-01-24 06:00:42.459908: step: 416/526, loss: 0.028156902641057968
2023-01-24 06:00:43.544093: step: 420/526, loss: 0.012215754948556423
2023-01-24 06:00:44.623158: step: 424/526, loss: 0.010989603586494923
2023-01-24 06:00:45.702679: step: 428/526, loss: 0.039528124034404755
2023-01-24 06:00:46.769313: step: 432/526, loss: 0.010094551369547844
2023-01-24 06:00:47.853319: step: 436/526, loss: 0.01602562516927719
2023-01-24 06:00:48.922273: step: 440/526, loss: 0.02160622365772724
2023-01-24 06:00:49.985028: step: 444/526, loss: 0.012479305267333984
2023-01-24 06:00:51.054861: step: 448/526, loss: 0.009602426551282406
2023-01-24 06:00:52.127437: step: 452/526, loss: 0.014257905073463917
2023-01-24 06:00:53.183017: step: 456/526, loss: 0.016463544219732285
2023-01-24 06:00:54.251066: step: 460/526, loss: 0.040781211107969284
2023-01-24 06:00:55.335008: step: 464/526, loss: 0.05287405103445053
2023-01-24 06:00:56.410779: step: 468/526, loss: 0.04636642709374428
2023-01-24 06:00:57.495939: step: 472/526, loss: 0.012500831857323647
2023-01-24 06:00:58.572435: step: 476/526, loss: 0.022106660529971123
2023-01-24 06:00:59.633541: step: 480/526, loss: 0.011811993084847927
2023-01-24 06:01:00.689177: step: 484/526, loss: 0.012277712114155293
2023-01-24 06:01:01.746527: step: 488/526, loss: 0.017902759835124016
2023-01-24 06:01:02.824560: step: 492/526, loss: 0.007290765643119812
2023-01-24 06:01:03.896300: step: 496/526, loss: 0.022858478128910065
2023-01-24 06:01:04.969808: step: 500/526, loss: 0.08065126836299896
2023-01-24 06:01:06.042165: step: 504/526, loss: 0.03802528232336044
2023-01-24 06:01:07.093346: step: 508/526, loss: 0.005456075072288513
2023-01-24 06:01:08.168275: step: 512/526, loss: 0.005667749792337418
2023-01-24 06:01:09.246833: step: 516/526, loss: 0.017475707456469536
2023-01-24 06:01:10.341450: step: 520/526, loss: 0.01729508861899376
2023-01-24 06:01:11.415910: step: 524/526, loss: 0.011713293381035328
2023-01-24 06:01:12.469157: step: 528/526, loss: 0.00553947314620018
2023-01-24 06:01:13.555124: step: 532/526, loss: 0.0069784484803676605
2023-01-24 06:01:14.621557: step: 536/526, loss: 0.03892875835299492
2023-01-24 06:01:15.698725: step: 540/526, loss: 0.04607051610946655
2023-01-24 06:01:16.759999: step: 544/526, loss: 0.01426483504474163
2023-01-24 06:01:17.823040: step: 548/526, loss: 0.017066525295376778
2023-01-24 06:01:18.886389: step: 552/526, loss: 0.007925783284008503
2023-01-24 06:01:19.962319: step: 556/526, loss: 0.02163388766348362
2023-01-24 06:01:21.019709: step: 560/526, loss: 0.04421288147568703
2023-01-24 06:01:22.075241: step: 564/526, loss: 0.012516318820416927
2023-01-24 06:01:23.139152: step: 568/526, loss: 0.049236468970775604
2023-01-24 06:01:24.215676: step: 572/526, loss: 0.023150749504566193
2023-01-24 06:01:25.301559: step: 576/526, loss: 0.009522246196866035
2023-01-24 06:01:26.383955: step: 580/526, loss: 0.016963254660367966
2023-01-24 06:01:27.468767: step: 584/526, loss: 0.01820969767868519
2023-01-24 06:01:28.547497: step: 588/526, loss: 0.07111315429210663
2023-01-24 06:01:29.608084: step: 592/526, loss: 0.007916552014648914
2023-01-24 06:01:30.661190: step: 596/526, loss: 0.007605835795402527
2023-01-24 06:01:31.715100: step: 600/526, loss: 0.012078801169991493
2023-01-24 06:01:32.785393: step: 604/526, loss: 0.019069718196988106
2023-01-24 06:01:33.839316: step: 608/526, loss: 0.010963761247694492
2023-01-24 06:01:34.910260: step: 612/526, loss: 0.013945738784968853
2023-01-24 06:01:35.963969: step: 616/526, loss: 0.011986438184976578
2023-01-24 06:01:37.029176: step: 620/526, loss: 0.013496545143425465
2023-01-24 06:01:38.112560: step: 624/526, loss: 0.0414331816136837
2023-01-24 06:01:39.170550: step: 628/526, loss: 0.02690134197473526
2023-01-24 06:01:40.234547: step: 632/526, loss: 0.015718039125204086
2023-01-24 06:01:41.309247: step: 636/526, loss: 0.010147477500140667
2023-01-24 06:01:42.384799: step: 640/526, loss: 0.03716598451137543
2023-01-24 06:01:43.456888: step: 644/526, loss: 0.015070073306560516
2023-01-24 06:01:44.514115: step: 648/526, loss: 0.04377167299389839
2023-01-24 06:01:45.597905: step: 652/526, loss: 0.02360081672668457
2023-01-24 06:01:46.671992: step: 656/526, loss: 0.0687611922621727
2023-01-24 06:01:47.736376: step: 660/526, loss: 0.01847033202648163
2023-01-24 06:01:48.785283: step: 664/526, loss: 0.006497836206108332
2023-01-24 06:01:49.842984: step: 668/526, loss: 0.025193439796566963
2023-01-24 06:01:50.905252: step: 672/526, loss: 0.042160212993621826
2023-01-24 06:01:51.980468: step: 676/526, loss: 0.018554389476776123
2023-01-24 06:01:53.044854: step: 680/526, loss: 0.01312668714672327
2023-01-24 06:01:54.119869: step: 684/526, loss: 0.010146260261535645
2023-01-24 06:01:55.185915: step: 688/526, loss: 0.034670326858758926
2023-01-24 06:01:56.260629: step: 692/526, loss: 0.03556656092405319
2023-01-24 06:01:57.332614: step: 696/526, loss: 0.01568073406815529
2023-01-24 06:01:58.405718: step: 700/526, loss: 0.0177853275090456
2023-01-24 06:01:59.483610: step: 704/526, loss: 0.00870177149772644
2023-01-24 06:02:00.538240: step: 708/526, loss: 0.014387092553079128
2023-01-24 06:02:01.612240: step: 712/526, loss: 0.005565970204770565
2023-01-24 06:02:02.683480: step: 716/526, loss: 0.0475313663482666
2023-01-24 06:02:03.752489: step: 720/526, loss: 0.012597961351275444
2023-01-24 06:02:04.819594: step: 724/526, loss: 0.005450345575809479
2023-01-24 06:02:05.882899: step: 728/526, loss: 0.007392000872641802
2023-01-24 06:02:06.945916: step: 732/526, loss: 0.019318392500281334
2023-01-24 06:02:08.015517: step: 736/526, loss: 0.013643491081893444
2023-01-24 06:02:09.082885: step: 740/526, loss: 0.010704146698117256
2023-01-24 06:02:10.152671: step: 744/526, loss: 0.015467265620827675
2023-01-24 06:02:11.210870: step: 748/526, loss: 0.0532383993268013
2023-01-24 06:02:12.281152: step: 752/526, loss: 0.03352460265159607
2023-01-24 06:02:13.355520: step: 756/526, loss: 0.010013245046138763
2023-01-24 06:02:14.425711: step: 760/526, loss: 0.029759852215647697
2023-01-24 06:02:15.476208: step: 764/526, loss: 0.0007408804376609623
2023-01-24 06:02:16.542527: step: 768/526, loss: 0.010924393311142921
2023-01-24 06:02:17.623724: step: 772/526, loss: 0.04788918420672417
2023-01-24 06:02:18.684858: step: 776/526, loss: 0.011204993352293968
2023-01-24 06:02:19.754186: step: 780/526, loss: 0.011356550268828869
2023-01-24 06:02:20.830267: step: 784/526, loss: 0.02712724357843399
2023-01-24 06:02:21.907469: step: 788/526, loss: 0.010598118416965008
2023-01-24 06:02:22.966478: step: 792/526, loss: 0.014653448946774006
2023-01-24 06:02:24.019081: step: 796/526, loss: 0.011020460166037083
2023-01-24 06:02:25.107158: step: 800/526, loss: 0.011566013097763062
2023-01-24 06:02:26.187187: step: 804/526, loss: 0.013965641148388386
2023-01-24 06:02:27.251926: step: 808/526, loss: 0.011844201944768429
2023-01-24 06:02:28.308909: step: 812/526, loss: 0.030684705823659897
2023-01-24 06:02:29.394981: step: 816/526, loss: 0.010975209064781666
2023-01-24 06:02:30.465661: step: 820/526, loss: 0.004901180975139141
2023-01-24 06:02:31.536904: step: 824/526, loss: 0.00804068986326456
2023-01-24 06:02:32.587881: step: 828/526, loss: 0.0274370014667511
2023-01-24 06:02:33.649310: step: 832/526, loss: 0.028265872970223427
2023-01-24 06:02:34.719913: step: 836/526, loss: 0.007112360559403896
2023-01-24 06:02:35.781866: step: 840/526, loss: 0.030012423172593117
2023-01-24 06:02:36.847895: step: 844/526, loss: 0.062013957649469376
2023-01-24 06:02:37.902225: step: 848/526, loss: 0.0032820170745253563
2023-01-24 06:02:38.962861: step: 852/526, loss: 0.014663055539131165
2023-01-24 06:02:40.015396: step: 856/526, loss: 0.013649990782141685
2023-01-24 06:02:41.107099: step: 860/526, loss: 0.01548759825527668
2023-01-24 06:02:42.164088: step: 864/526, loss: 0.015864748507738113
2023-01-24 06:02:43.220640: step: 868/526, loss: 0.016371339559555054
2023-01-24 06:02:44.279145: step: 872/526, loss: 0.014859255403280258
2023-01-24 06:02:45.357388: step: 876/526, loss: 0.011524135246872902
2023-01-24 06:02:46.410142: step: 880/526, loss: 0.032405126839876175
2023-01-24 06:02:47.491917: step: 884/526, loss: 0.0398188941180706
2023-01-24 06:02:48.557905: step: 888/526, loss: 0.00956823118031025
2023-01-24 06:02:49.609042: step: 892/526, loss: 0.012285396456718445
2023-01-24 06:02:50.669943: step: 896/526, loss: 0.017864594236016273
2023-01-24 06:02:51.734984: step: 900/526, loss: 0.026145169511437416
2023-01-24 06:02:52.797141: step: 904/526, loss: 0.008185205049812794
2023-01-24 06:02:53.861679: step: 908/526, loss: 0.03489832207560539
2023-01-24 06:02:54.931082: step: 912/526, loss: 0.012369459494948387
2023-01-24 06:02:55.998996: step: 916/526, loss: 0.012742091901600361
2023-01-24 06:02:57.061903: step: 920/526, loss: 0.0014365314273163676
2023-01-24 06:02:58.142339: step: 924/526, loss: 0.011076916940510273
2023-01-24 06:02:59.190424: step: 928/526, loss: 0.02785377763211727
2023-01-24 06:03:00.250806: step: 932/526, loss: 0.01068216934800148
2023-01-24 06:03:01.314442: step: 936/526, loss: 0.011536781676113605
2023-01-24 06:03:02.391407: step: 940/526, loss: 0.012976781465113163
2023-01-24 06:03:03.456978: step: 944/526, loss: 0.008641269989311695
2023-01-24 06:03:04.528646: step: 948/526, loss: 0.008370699360966682
2023-01-24 06:03:05.593974: step: 952/526, loss: 0.009716982953250408
2023-01-24 06:03:06.682992: step: 956/526, loss: 0.015492056496441364
2023-01-24 06:03:07.729432: step: 960/526, loss: 0.004958414006978273
2023-01-24 06:03:08.786009: step: 964/526, loss: 0.03704093396663666
2023-01-24 06:03:09.858173: step: 968/526, loss: 0.008817754685878754
2023-01-24 06:03:10.945049: step: 972/526, loss: 0.00804503820836544
2023-01-24 06:03:12.014291: step: 976/526, loss: 0.007515077944844961
2023-01-24 06:03:13.065149: step: 980/526, loss: 0.02187001146376133
2023-01-24 06:03:14.121844: step: 984/526, loss: 0.013517889194190502
2023-01-24 06:03:15.183970: step: 988/526, loss: 0.0042789471335709095
2023-01-24 06:03:16.237230: step: 992/526, loss: 0.013299938291311264
2023-01-24 06:03:17.291051: step: 996/526, loss: 0.011831467039883137
2023-01-24 06:03:18.358730: step: 1000/526, loss: 0.02314213663339615
2023-01-24 06:03:19.413861: step: 1004/526, loss: 0.011190442368388176
2023-01-24 06:03:20.467405: step: 1008/526, loss: 0.00815039873123169
2023-01-24 06:03:21.538553: step: 1012/526, loss: 0.008704792708158493
2023-01-24 06:03:22.598630: step: 1016/526, loss: 0.017575861886143684
2023-01-24 06:03:23.655880: step: 1020/526, loss: 0.010505554266273975
2023-01-24 06:03:24.722596: step: 1024/526, loss: 0.07492277026176453
2023-01-24 06:03:25.806702: step: 1028/526, loss: 0.02986185811460018
2023-01-24 06:03:26.877600: step: 1032/526, loss: 0.0039607989601790905
2023-01-24 06:03:27.925732: step: 1036/526, loss: 0.008863895200192928
2023-01-24 06:03:29.010962: step: 1040/526, loss: 0.009433879517018795
2023-01-24 06:03:30.072605: step: 1044/526, loss: 0.01492956280708313
2023-01-24 06:03:31.148395: step: 1048/526, loss: 0.0010975669138133526
2023-01-24 06:03:32.214584: step: 1052/526, loss: 0.006231072824448347
2023-01-24 06:03:33.279195: step: 1056/526, loss: 0.011758730746805668
2023-01-24 06:03:34.347658: step: 1060/526, loss: 0.00797701720148325
2023-01-24 06:03:35.447143: step: 1064/526, loss: 0.010580445639789104
2023-01-24 06:03:36.507162: step: 1068/526, loss: 0.014520341530442238
2023-01-24 06:03:37.589387: step: 1072/526, loss: 0.009447069838643074
2023-01-24 06:03:38.662918: step: 1076/526, loss: 0.04533913731575012
2023-01-24 06:03:39.736648: step: 1080/526, loss: 0.05336616933345795
2023-01-24 06:03:40.790850: step: 1084/526, loss: 0.017616352066397667
2023-01-24 06:03:41.849282: step: 1088/526, loss: 0.009178748354315758
2023-01-24 06:03:42.927940: step: 1092/526, loss: 0.03466084599494934
2023-01-24 06:03:44.025204: step: 1096/526, loss: 0.011660982854664326
2023-01-24 06:03:45.090587: step: 1100/526, loss: 0.009456636384129524
2023-01-24 06:03:46.156641: step: 1104/526, loss: 0.030066153034567833
2023-01-24 06:03:47.224396: step: 1108/526, loss: 0.004824388772249222
2023-01-24 06:03:48.279834: step: 1112/526, loss: 0.036501746624708176
2023-01-24 06:03:49.353446: step: 1116/526, loss: 0.01415973249822855
2023-01-24 06:03:50.419351: step: 1120/526, loss: 0.00685915956273675
2023-01-24 06:03:51.491310: step: 1124/526, loss: 0.008669904433190823
2023-01-24 06:03:52.576595: step: 1128/526, loss: 0.006808173377066851
2023-01-24 06:03:53.649525: step: 1132/526, loss: 0.009730562567710876
2023-01-24 06:03:54.720885: step: 1136/526, loss: 0.015168559737503529
2023-01-24 06:03:55.773071: step: 1140/526, loss: 0.006401766091585159
2023-01-24 06:03:56.841989: step: 1144/526, loss: 0.010507703758776188
2023-01-24 06:03:57.901329: step: 1148/526, loss: 0.016983985900878906
2023-01-24 06:03:58.983038: step: 1152/526, loss: 0.04353087767958641
2023-01-24 06:04:00.087611: step: 1156/526, loss: 0.012048405595123768
2023-01-24 06:04:01.137870: step: 1160/526, loss: 0.005415227264165878
2023-01-24 06:04:02.201041: step: 1164/526, loss: 0.010012845508754253
2023-01-24 06:04:03.254413: step: 1168/526, loss: 0.014785283245146275
2023-01-24 06:04:04.306774: step: 1172/526, loss: 0.01904195547103882
2023-01-24 06:04:05.371867: step: 1176/526, loss: 0.006536061409860849
2023-01-24 06:04:06.432311: step: 1180/526, loss: 0.05519216135144234
2023-01-24 06:04:07.501658: step: 1184/526, loss: 0.011332720518112183
2023-01-24 06:04:08.574507: step: 1188/526, loss: 0.00711508933454752
2023-01-24 06:04:09.652194: step: 1192/526, loss: 0.0708845853805542
2023-01-24 06:04:10.748008: step: 1196/526, loss: 0.004140944220125675
2023-01-24 06:04:11.810689: step: 1200/526, loss: 0.03137581795454025
2023-01-24 06:04:12.901796: step: 1204/526, loss: 0.04280191287398338
2023-01-24 06:04:13.956554: step: 1208/526, loss: 0.019610702991485596
2023-01-24 06:04:15.019480: step: 1212/526, loss: 0.019446009770035744
2023-01-24 06:04:16.063756: step: 1216/526, loss: 0.01401528250426054
2023-01-24 06:04:17.129963: step: 1220/526, loss: 0.005409129895269871
2023-01-24 06:04:18.212320: step: 1224/526, loss: 0.007175501901656389
2023-01-24 06:04:19.284669: step: 1228/526, loss: 0.008640944957733154
2023-01-24 06:04:20.343641: step: 1232/526, loss: 0.005673054605722427
2023-01-24 06:04:21.413189: step: 1236/526, loss: 0.02942793257534504
2023-01-24 06:04:22.472026: step: 1240/526, loss: 0.005041190888732672
2023-01-24 06:04:23.538029: step: 1244/526, loss: 0.041995421051979065
2023-01-24 06:04:24.605489: step: 1248/526, loss: 0.01346071157604456
2023-01-24 06:04:25.686380: step: 1252/526, loss: 0.01392744854092598
2023-01-24 06:04:26.770106: step: 1256/526, loss: 0.009032701142132282
2023-01-24 06:04:27.838929: step: 1260/526, loss: 0.026062192395329475
2023-01-24 06:04:28.889855: step: 1264/526, loss: 0.04490725323557854
2023-01-24 06:04:29.957420: step: 1268/526, loss: 0.00986095517873764
2023-01-24 06:04:31.044995: step: 1272/526, loss: 0.0012970336247235537
2023-01-24 06:04:32.128767: step: 1276/526, loss: 0.02037988230586052
2023-01-24 06:04:33.193995: step: 1280/526, loss: 0.02683100476861
2023-01-24 06:04:34.260770: step: 1284/526, loss: 0.007773365825414658
2023-01-24 06:04:35.324409: step: 1288/526, loss: 0.05968731641769409
2023-01-24 06:04:36.394762: step: 1292/526, loss: 0.03613681346178055
2023-01-24 06:04:37.462906: step: 1296/526, loss: 0.014471679925918579
2023-01-24 06:04:38.524136: step: 1300/526, loss: 0.05630014091730118
2023-01-24 06:04:39.599199: step: 1304/526, loss: 0.01242032554000616
2023-01-24 06:04:40.662694: step: 1308/526, loss: 0.014923516660928726
2023-01-24 06:04:41.731471: step: 1312/526, loss: 0.005437185056507587
2023-01-24 06:04:42.796684: step: 1316/526, loss: 0.026831425726413727
2023-01-24 06:04:43.884596: step: 1320/526, loss: 0.006485107820481062
2023-01-24 06:04:44.946068: step: 1324/526, loss: 0.0076478831470012665
2023-01-24 06:04:45.998147: step: 1328/526, loss: 0.012937773950397968
2023-01-24 06:04:47.069302: step: 1332/526, loss: 0.03799450397491455
2023-01-24 06:04:48.147013: step: 1336/526, loss: 0.04945323243737221
2023-01-24 06:04:49.222581: step: 1340/526, loss: 0.008653589524328709
2023-01-24 06:04:50.311086: step: 1344/526, loss: 0.011765801347792149
2023-01-24 06:04:51.375098: step: 1348/526, loss: 0.003939558286219835
2023-01-24 06:04:52.435683: step: 1352/526, loss: 0.010396410711109638
2023-01-24 06:04:53.502864: step: 1356/526, loss: 0.007071498781442642
2023-01-24 06:04:54.590150: step: 1360/526, loss: 0.02911684848368168
2023-01-24 06:04:55.653943: step: 1364/526, loss: 0.009999081492424011
2023-01-24 06:04:56.717196: step: 1368/526, loss: 0.01261632889509201
2023-01-24 06:04:57.775512: step: 1372/526, loss: 0.018445320427417755
2023-01-24 06:04:58.854215: step: 1376/526, loss: 0.029369182884693146
2023-01-24 06:04:59.923680: step: 1380/526, loss: 0.03203567489981651
2023-01-24 06:05:00.985109: step: 1384/526, loss: 0.01643977500498295
2023-01-24 06:05:02.053477: step: 1388/526, loss: 0.006959362421184778
2023-01-24 06:05:03.118553: step: 1392/526, loss: 0.009082360193133354
2023-01-24 06:05:04.179311: step: 1396/526, loss: 0.015994016081094742
2023-01-24 06:05:05.252057: step: 1400/526, loss: 0.007509440649300814
2023-01-24 06:05:06.348995: step: 1404/526, loss: 0.009382094256579876
2023-01-24 06:05:07.415269: step: 1408/526, loss: 0.06619424372911453
2023-01-24 06:05:08.473306: step: 1412/526, loss: 0.01072310097515583
2023-01-24 06:05:09.553338: step: 1416/526, loss: 0.011856546625494957
2023-01-24 06:05:10.618734: step: 1420/526, loss: 0.008005455136299133
2023-01-24 06:05:11.680758: step: 1424/526, loss: 0.029859593138098717
2023-01-24 06:05:12.755870: step: 1428/526, loss: 0.008419408462941647
2023-01-24 06:05:13.832454: step: 1432/526, loss: 0.00817930232733488
2023-01-24 06:05:14.900771: step: 1436/526, loss: 0.003652143059298396
2023-01-24 06:05:15.971866: step: 1440/526, loss: 0.02835831791162491
2023-01-24 06:05:17.034355: step: 1444/526, loss: 0.009940870106220245
2023-01-24 06:05:18.113912: step: 1448/526, loss: 0.009122544899582863
2023-01-24 06:05:19.172934: step: 1452/526, loss: 0.008882798254489899
2023-01-24 06:05:20.247694: step: 1456/526, loss: 0.002926712157204747
2023-01-24 06:05:21.315033: step: 1460/526, loss: 0.009402105584740639
2023-01-24 06:05:22.380121: step: 1464/526, loss: 0.008531627245247364
2023-01-24 06:05:23.443978: step: 1468/526, loss: 0.017533885315060616
2023-01-24 06:05:24.502639: step: 1472/526, loss: 0.01003988366574049
2023-01-24 06:05:25.575943: step: 1476/526, loss: 0.003773764008656144
2023-01-24 06:05:26.634386: step: 1480/526, loss: 0.03491215780377388
2023-01-24 06:05:27.711058: step: 1484/526, loss: 0.0
2023-01-24 06:05:28.775825: step: 1488/526, loss: 0.007994186133146286
2023-01-24 06:05:29.845018: step: 1492/526, loss: 0.005993510130792856
2023-01-24 06:05:30.904400: step: 1496/526, loss: 0.007079313043504953
2023-01-24 06:05:31.964192: step: 1500/526, loss: 0.0017002951353788376
2023-01-24 06:05:33.032055: step: 1504/526, loss: 0.015731265768408775
2023-01-24 06:05:34.107295: step: 1508/526, loss: 0.037618815898895264
2023-01-24 06:05:35.179537: step: 1512/526, loss: 0.012623411603271961
2023-01-24 06:05:36.250614: step: 1516/526, loss: 0.009160598739981651
2023-01-24 06:05:37.311746: step: 1520/526, loss: 0.006584780290722847
2023-01-24 06:05:38.366097: step: 1524/526, loss: 0.012651040218770504
2023-01-24 06:05:39.423335: step: 1528/526, loss: 0.008514382876455784
2023-01-24 06:05:40.495114: step: 1532/526, loss: 0.011343814432621002
2023-01-24 06:05:41.573339: step: 1536/526, loss: 0.0
2023-01-24 06:05:42.622020: step: 1540/526, loss: 0.026241444051265717
2023-01-24 06:05:43.683707: step: 1544/526, loss: 0.01048093568533659
2023-01-24 06:05:44.748017: step: 1548/526, loss: 0.019991302862763405
2023-01-24 06:05:45.831791: step: 1552/526, loss: 0.006727890577167273
2023-01-24 06:05:46.897856: step: 1556/526, loss: 0.008984006941318512
2023-01-24 06:05:47.982150: step: 1560/526, loss: 0.006317827384918928
2023-01-24 06:05:49.038899: step: 1564/526, loss: 0.028456710278987885
2023-01-24 06:05:50.099365: step: 1568/526, loss: 0.03435984626412392
2023-01-24 06:05:51.176790: step: 1572/526, loss: 0.008374986238777637
2023-01-24 06:05:52.244919: step: 1576/526, loss: 0.010556735098361969
2023-01-24 06:05:53.308320: step: 1580/526, loss: 0.007845778949558735
2023-01-24 06:05:54.359294: step: 1584/526, loss: 0.01241462491452694
2023-01-24 06:05:55.414917: step: 1588/526, loss: 0.008453438989818096
2023-01-24 06:05:56.473564: step: 1592/526, loss: 0.0023859762586653233
2023-01-24 06:05:57.527593: step: 1596/526, loss: 0.002180887386202812
2023-01-24 06:05:58.593528: step: 1600/526, loss: 0.055828213691711426
2023-01-24 06:05:59.666454: step: 1604/526, loss: 0.014245115220546722
2023-01-24 06:06:00.733492: step: 1608/526, loss: 0.0005981465801596642
2023-01-24 06:06:01.798363: step: 1612/526, loss: 0.01824469491839409
2023-01-24 06:06:02.882850: step: 1616/526, loss: 0.03601479157805443
2023-01-24 06:06:03.973735: step: 1620/526, loss: 0.010745086707174778
2023-01-24 06:06:05.053993: step: 1624/526, loss: 0.012959487736225128
2023-01-24 06:06:06.124879: step: 1628/526, loss: 0.031919367611408234
2023-01-24 06:06:07.198277: step: 1632/526, loss: 0.03662387281656265
2023-01-24 06:06:08.261754: step: 1636/526, loss: 0.014079691842198372
2023-01-24 06:06:09.322100: step: 1640/526, loss: 0.013199028559029102
2023-01-24 06:06:10.388437: step: 1644/526, loss: 0.005749897100031376
2023-01-24 06:06:11.472596: step: 1648/526, loss: 0.058484792709350586
2023-01-24 06:06:12.541764: step: 1652/526, loss: 0.009160355664789677
2023-01-24 06:06:13.623794: step: 1656/526, loss: 0.01271575503051281
2023-01-24 06:06:14.670271: step: 1660/526, loss: 0.005082838237285614
2023-01-24 06:06:15.746480: step: 1664/526, loss: 0.0063095358200371265
2023-01-24 06:06:16.828222: step: 1668/526, loss: 0.016301430761814117
2023-01-24 06:06:17.900862: step: 1672/526, loss: 0.01858590543270111
2023-01-24 06:06:18.994304: step: 1676/526, loss: 0.0562649667263031
2023-01-24 06:06:20.073953: step: 1680/526, loss: 0.03633774444460869
2023-01-24 06:06:21.138029: step: 1684/526, loss: 0.02037951350212097
2023-01-24 06:06:22.192947: step: 1688/526, loss: 0.009017981588840485
2023-01-24 06:06:23.254992: step: 1692/526, loss: 0.014851553365588188
2023-01-24 06:06:24.329381: step: 1696/526, loss: 0.03930414095520973
2023-01-24 06:06:25.383797: step: 1700/526, loss: 0.009732124395668507
2023-01-24 06:06:26.463411: step: 1704/526, loss: 0.03580033779144287
2023-01-24 06:06:27.527563: step: 1708/526, loss: 0.10349379479885101
2023-01-24 06:06:28.581793: step: 1712/526, loss: 0.02116229385137558
2023-01-24 06:06:29.628453: step: 1716/526, loss: 0.006866572890430689
2023-01-24 06:06:30.689712: step: 1720/526, loss: 0.004173388238996267
2023-01-24 06:06:31.763549: step: 1724/526, loss: 0.020609896630048752
2023-01-24 06:06:32.801387: step: 1728/526, loss: 0.008703921921551228
2023-01-24 06:06:33.872703: step: 1732/526, loss: 0.06990665942430496
2023-01-24 06:06:34.943838: step: 1736/526, loss: 0.05288764461874962
2023-01-24 06:06:36.038695: step: 1740/526, loss: 0.007890609093010426
2023-01-24 06:06:37.115311: step: 1744/526, loss: 0.01431087777018547
2023-01-24 06:06:38.173031: step: 1748/526, loss: 0.008707761764526367
2023-01-24 06:06:39.270967: step: 1752/526, loss: 0.024928338825702667
2023-01-24 06:06:40.346220: step: 1756/526, loss: 0.009167775511741638
2023-01-24 06:06:41.409770: step: 1760/526, loss: 0.012607909739017487
2023-01-24 06:06:42.475897: step: 1764/526, loss: 0.009761009365320206
2023-01-24 06:06:43.562369: step: 1768/526, loss: 0.040605463087558746
2023-01-24 06:06:44.644684: step: 1772/526, loss: 0.010327261872589588
2023-01-24 06:06:45.716731: step: 1776/526, loss: 0.00893464032560587
2023-01-24 06:06:46.810392: step: 1780/526, loss: 0.012258530594408512
2023-01-24 06:06:47.863772: step: 1784/526, loss: 0.011431992053985596
2023-01-24 06:06:48.960662: step: 1788/526, loss: 0.033019233494997025
2023-01-24 06:06:50.031733: step: 1792/526, loss: 0.011460560373961926
2023-01-24 06:06:51.108495: step: 1796/526, loss: 0.036431025713682175
2023-01-24 06:06:52.166497: step: 1800/526, loss: 0.01994819939136505
2023-01-24 06:06:53.232535: step: 1804/526, loss: 0.028628690168261528
2023-01-24 06:06:54.291016: step: 1808/526, loss: 0.03119327500462532
2023-01-24 06:06:55.361823: step: 1812/526, loss: 0.011507650837302208
2023-01-24 06:06:56.429244: step: 1816/526, loss: 0.020260179415345192
2023-01-24 06:06:57.495455: step: 1820/526, loss: 0.01271382998675108
2023-01-24 06:06:58.572318: step: 1824/526, loss: 0.007489434909075499
2023-01-24 06:06:59.641178: step: 1828/526, loss: 0.04710334166884422
2023-01-24 06:07:00.718988: step: 1832/526, loss: 0.00463204737752676
2023-01-24 06:07:01.790153: step: 1836/526, loss: 0.005719366483390331
2023-01-24 06:07:02.863389: step: 1840/526, loss: 0.0285815242677927
2023-01-24 06:07:03.942109: step: 1844/526, loss: 0.006801443640142679
2023-01-24 06:07:05.021562: step: 1848/526, loss: 0.03405589237809181
2023-01-24 06:07:06.100014: step: 1852/526, loss: 0.007955166511237621
2023-01-24 06:07:07.161179: step: 1856/526, loss: 0.03807443380355835
2023-01-24 06:07:08.231871: step: 1860/526, loss: 0.013254741206765175
2023-01-24 06:07:09.295413: step: 1864/526, loss: 0.03340696170926094
2023-01-24 06:07:10.380529: step: 1868/526, loss: 0.011111082509160042
2023-01-24 06:07:11.424281: step: 1872/526, loss: 0.028069892898201942
2023-01-24 06:07:12.493916: step: 1876/526, loss: 0.009006863459944725
2023-01-24 06:07:13.552801: step: 1880/526, loss: 0.0012652931036427617
2023-01-24 06:07:14.615447: step: 1884/526, loss: 0.011551257222890854
2023-01-24 06:07:15.687630: step: 1888/526, loss: 0.007737389300018549
2023-01-24 06:07:16.756395: step: 1892/526, loss: 0.013382695615291595
2023-01-24 06:07:17.833022: step: 1896/526, loss: 0.04424820840358734
2023-01-24 06:07:18.903635: step: 1900/526, loss: 0.009375272318720818
2023-01-24 06:07:19.969489: step: 1904/526, loss: 0.008670293726027012
2023-01-24 06:07:21.049452: step: 1908/526, loss: 0.02267920970916748
2023-01-24 06:07:22.118824: step: 1912/526, loss: 0.01814381405711174
2023-01-24 06:07:23.214715: step: 1916/526, loss: 0.016704678535461426
2023-01-24 06:07:24.283172: step: 1920/526, loss: 0.027080735191702843
2023-01-24 06:07:25.353756: step: 1924/526, loss: 0.008847378194332123
2023-01-24 06:07:26.441761: step: 1928/526, loss: 0.01489635743200779
2023-01-24 06:07:27.508980: step: 1932/526, loss: 0.00615769624710083
2023-01-24 06:07:28.574008: step: 1936/526, loss: 0.021490972489118576
2023-01-24 06:07:29.619743: step: 1940/526, loss: 0.0002509737969376147
2023-01-24 06:07:30.696602: step: 1944/526, loss: 0.008738047443330288
2023-01-24 06:07:31.776055: step: 1948/526, loss: 0.050118062645196915
2023-01-24 06:07:32.834032: step: 1952/526, loss: 0.06966641545295715
2023-01-24 06:07:33.912101: step: 1956/526, loss: 0.010268663987517357
2023-01-24 06:07:34.988413: step: 1960/526, loss: 0.04485553503036499
2023-01-24 06:07:36.069002: step: 1964/526, loss: 0.002371970796957612
2023-01-24 06:07:37.130827: step: 1968/526, loss: 0.008896823041141033
2023-01-24 06:07:38.206271: step: 1972/526, loss: 0.00835936889052391
2023-01-24 06:07:39.280147: step: 1976/526, loss: 0.015106378123164177
2023-01-24 06:07:40.364241: step: 1980/526, loss: 0.00909444224089384
2023-01-24 06:07:41.438307: step: 1984/526, loss: 0.010535995475947857
2023-01-24 06:07:42.508577: step: 1988/526, loss: 0.006307290866971016
2023-01-24 06:07:43.562577: step: 1992/526, loss: 0.01878141425549984
2023-01-24 06:07:44.627348: step: 1996/526, loss: 0.038284849375486374
2023-01-24 06:07:45.712788: step: 2000/526, loss: 0.00795657467097044
2023-01-24 06:07:46.776384: step: 2004/526, loss: 0.011157316155731678
2023-01-24 06:07:47.863445: step: 2008/526, loss: 0.04704447463154793
2023-01-24 06:07:48.920999: step: 2012/526, loss: 0.0013298210687935352
2023-01-24 06:07:49.981734: step: 2016/526, loss: 0.01780594140291214
2023-01-24 06:07:51.061942: step: 2020/526, loss: 0.012109140865504742
2023-01-24 06:07:52.119358: step: 2024/526, loss: 0.004032840020954609
2023-01-24 06:07:53.183683: step: 2028/526, loss: 0.0509190671145916
2023-01-24 06:07:54.251960: step: 2032/526, loss: 0.008496547117829323
2023-01-24 06:07:55.325516: step: 2036/526, loss: 0.009023867547512054
2023-01-24 06:07:56.407077: step: 2040/526, loss: 0.01766207255423069
2023-01-24 06:07:57.495421: step: 2044/526, loss: 0.010823347605764866
2023-01-24 06:07:58.562337: step: 2048/526, loss: 0.009245182387530804
2023-01-24 06:07:59.619482: step: 2052/526, loss: 0.006597570609301329
2023-01-24 06:08:00.699636: step: 2056/526, loss: 0.0073024514131248
2023-01-24 06:08:01.766510: step: 2060/526, loss: 0.014326004311442375
2023-01-24 06:08:02.828719: step: 2064/526, loss: 0.002964144805446267
2023-01-24 06:08:03.899948: step: 2068/526, loss: 0.03649190813302994
2023-01-24 06:08:04.969185: step: 2072/526, loss: 0.009398775175213814
2023-01-24 06:08:06.032300: step: 2076/526, loss: 0.004718531854450703
2023-01-24 06:08:07.094730: step: 2080/526, loss: 0.010285005904734135
2023-01-24 06:08:08.160167: step: 2084/526, loss: 0.03717676177620888
2023-01-24 06:08:09.245057: step: 2088/526, loss: 0.008828303776681423
2023-01-24 06:08:10.311979: step: 2092/526, loss: 0.0037476096767932177
2023-01-24 06:08:11.387095: step: 2096/526, loss: 0.01692165620625019
2023-01-24 06:08:12.464920: step: 2100/526, loss: 0.006278595887124538
2023-01-24 06:08:13.564744: step: 2104/526, loss: 0.018769849091768265
==================================================
Loss: 0.020
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3653141952983725, 'r': 0.273812347519653, 'f1': 0.3130132475983886}, 'combined': 0.23064134033565475, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3481924145738987, 'r': 0.22108466213566852, 'f1': 0.27044827724038695}, 'combined': 0.14751724213112014, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3331596684226836, 'r': 0.29143568717809704, 'f1': 0.31090406304222096}, 'combined': 0.22908720434689964, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3509259061173678, 'r': 0.2560637433678328, 'f1': 0.29608215310219316}, 'combined': 0.1614993562375599, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3565282103692168, 'r': 0.3159367632683572, 'f1': 0.33500739284189984}, 'combined': 0.24684755262034724, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35195149061403846, 'r': 0.27209424480225297, 'f1': 0.3069133225684856}, 'combined': 0.16740726685553758, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, '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': 0.3653141952983725, 'r': 0.273812347519653, 'f1': 0.3130132475983886}, 'combined': 0.23064134033565475, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3481924145738987, 'r': 0.22108466213566852, 'f1': 0.27044827724038695}, 'combined': 0.14751724213112014, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3331596684226836, 'r': 0.29143568717809704, 'f1': 0.31090406304222096}, 'combined': 0.22908720434689964, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3509259061173678, 'r': 0.2560637433678328, 'f1': 0.29608215310219316}, 'combined': 0.1614993562375599, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3565282103692168, 'r': 0.3159367632683572, 'f1': 0.33500739284189984}, 'combined': 0.24684755262034724, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35195149061403846, 'r': 0.27209424480225297, 'f1': 0.3069133225684856}, 'combined': 0.16740726685553758, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, '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 06:11:11.052847: step: 4/526, loss: 0.03211181238293648
2023-01-24 06:11:12.113714: step: 8/526, loss: 0.015572511591017246
2023-01-24 06:11:13.169718: step: 12/526, loss: 0.008042541332542896
2023-01-24 06:11:14.275898: step: 16/526, loss: 0.004841309506446123
2023-01-24 06:11:15.361416: step: 20/526, loss: 0.007955636829137802
2023-01-24 06:11:16.435405: step: 24/526, loss: 0.00797360297292471
2023-01-24 06:11:17.514883: step: 28/526, loss: 0.033014778047800064
2023-01-24 06:11:18.584652: step: 32/526, loss: 0.05221322178840637
2023-01-24 06:11:19.668806: step: 36/526, loss: 0.030476940795779228
2023-01-24 06:11:20.742773: step: 40/526, loss: 0.0014396319165825844
2023-01-24 06:11:21.810223: step: 44/526, loss: 0.01805701106786728
2023-01-24 06:11:22.877202: step: 48/526, loss: 0.007719062734395266
2023-01-24 06:11:23.941000: step: 52/526, loss: 0.007864895276725292
2023-01-24 06:11:24.999627: step: 56/526, loss: 0.010750040411949158
2023-01-24 06:11:26.070049: step: 60/526, loss: 0.014993387274444103
2023-01-24 06:11:27.155338: step: 64/526, loss: 0.015512635000050068
2023-01-24 06:11:28.217171: step: 68/526, loss: 0.003549936693161726
2023-01-24 06:11:29.290997: step: 72/526, loss: 0.007248771842569113
2023-01-24 06:11:30.348037: step: 76/526, loss: 0.016969798132777214
2023-01-24 06:11:31.410514: step: 80/526, loss: 0.008019802160561085
2023-01-24 06:11:32.469278: step: 84/526, loss: 0.009370728395879269
2023-01-24 06:11:33.540694: step: 88/526, loss: 0.010859012603759766
2023-01-24 06:11:34.601384: step: 92/526, loss: 0.0011244139168411493
2023-01-24 06:11:35.659176: step: 96/526, loss: 0.0029502692632377148
2023-01-24 06:11:36.740653: step: 100/526, loss: 0.006351650692522526
2023-01-24 06:11:37.805027: step: 104/526, loss: 0.023949936032295227
2023-01-24 06:11:38.870119: step: 108/526, loss: 0.007888903841376305
2023-01-24 06:11:39.932211: step: 112/526, loss: 0.008125972002744675
2023-01-24 06:11:41.004497: step: 116/526, loss: 0.009863548912107944
2023-01-24 06:11:42.084911: step: 120/526, loss: 0.03601766377687454
2023-01-24 06:11:43.144768: step: 124/526, loss: 0.015775542706251144
2023-01-24 06:11:44.210312: step: 128/526, loss: 0.011705438606441021
2023-01-24 06:11:45.275456: step: 132/526, loss: 0.011139459908008575
2023-01-24 06:11:46.329251: step: 136/526, loss: 0.021827878430485725
2023-01-24 06:11:47.403767: step: 140/526, loss: 0.007847513072192669
2023-01-24 06:11:48.475061: step: 144/526, loss: 0.04689466953277588
2023-01-24 06:11:49.548861: step: 148/526, loss: 0.009505599737167358
2023-01-24 06:11:50.617556: step: 152/526, loss: 0.009732306934893131
2023-01-24 06:11:51.702798: step: 156/526, loss: 0.007876728661358356
2023-01-24 06:11:52.770097: step: 160/526, loss: 0.015592919662594795
2023-01-24 06:11:53.813214: step: 164/526, loss: 0.009664716199040413
2023-01-24 06:11:54.874938: step: 168/526, loss: 0.01496057491749525
2023-01-24 06:11:55.934205: step: 172/526, loss: 0.013952945359051228
2023-01-24 06:11:57.020794: step: 176/526, loss: 0.01393144205212593
2023-01-24 06:11:58.088050: step: 180/526, loss: 0.03488390892744064
2023-01-24 06:11:59.170272: step: 184/526, loss: 0.0152826476842165
2023-01-24 06:12:00.250655: step: 188/526, loss: 0.012214967980980873
2023-01-24 06:12:01.334609: step: 192/526, loss: 0.011353610083460808
2023-01-24 06:12:02.410966: step: 196/526, loss: 0.004587080795317888
2023-01-24 06:12:03.470173: step: 200/526, loss: 0.012474067509174347
2023-01-24 06:12:04.546160: step: 204/526, loss: 0.017332954332232475
2023-01-24 06:12:05.616267: step: 208/526, loss: 0.02854897268116474
2023-01-24 06:12:06.680218: step: 212/526, loss: 0.026937387883663177
2023-01-24 06:12:07.745603: step: 216/526, loss: 0.05181463807821274
2023-01-24 06:12:08.824651: step: 220/526, loss: 0.012530874460935593
2023-01-24 06:12:09.912429: step: 224/526, loss: 0.007335149683058262
2023-01-24 06:12:10.994311: step: 228/526, loss: 0.0031346820760518312
2023-01-24 06:12:12.074567: step: 232/526, loss: 0.015300611965358257
2023-01-24 06:12:13.154225: step: 236/526, loss: 0.011877749115228653
2023-01-24 06:12:14.229979: step: 240/526, loss: 0.00818359013646841
2023-01-24 06:12:15.292752: step: 244/526, loss: 0.005689065903425217
2023-01-24 06:12:16.354892: step: 248/526, loss: 0.014335880987346172
2023-01-24 06:12:17.438388: step: 252/526, loss: 0.030663516372442245
2023-01-24 06:12:18.513219: step: 256/526, loss: 0.029263811185956
2023-01-24 06:12:19.590880: step: 260/526, loss: 0.026315417140722275
2023-01-24 06:12:20.680715: step: 264/526, loss: 0.015756351873278618
2023-01-24 06:12:21.750347: step: 268/526, loss: 0.0010223337449133396
2023-01-24 06:12:22.822710: step: 272/526, loss: 0.02698124386370182
2023-01-24 06:12:23.906835: step: 276/526, loss: 0.007111274637281895
2023-01-24 06:12:24.984244: step: 280/526, loss: 0.011177325621247292
2023-01-24 06:12:26.062191: step: 284/526, loss: 0.030898889526724815
2023-01-24 06:12:27.132213: step: 288/526, loss: 0.009922806173563004
2023-01-24 06:12:28.196202: step: 292/526, loss: 0.01405404694378376
2023-01-24 06:12:29.276014: step: 296/526, loss: 0.038369640707969666
2023-01-24 06:12:30.348360: step: 300/526, loss: 0.02093619480729103
2023-01-24 06:12:31.421414: step: 304/526, loss: 0.007910237647593021
2023-01-24 06:12:32.484886: step: 308/526, loss: 0.005331913474947214
2023-01-24 06:12:33.572458: step: 312/526, loss: 0.02157352678477764
2023-01-24 06:12:34.650153: step: 316/526, loss: 0.009920264594256878
2023-01-24 06:12:35.727253: step: 320/526, loss: 0.06362996250391006
2023-01-24 06:12:36.806545: step: 324/526, loss: 0.006740234326571226
2023-01-24 06:12:37.866662: step: 328/526, loss: 0.01942634768784046
2023-01-24 06:12:38.963026: step: 332/526, loss: 0.01024128869175911
2023-01-24 06:12:40.031551: step: 336/526, loss: 0.018934722989797592
2023-01-24 06:12:41.095149: step: 340/526, loss: 0.025675050914287567
2023-01-24 06:12:42.164146: step: 344/526, loss: 0.002226931508630514
2023-01-24 06:12:43.242352: step: 348/526, loss: 0.025554940104484558
2023-01-24 06:12:44.310056: step: 352/526, loss: 0.04201820120215416
2023-01-24 06:12:45.396522: step: 356/526, loss: 0.006230425555258989
2023-01-24 06:12:46.462377: step: 360/526, loss: 0.007900257594883442
2023-01-24 06:12:47.539653: step: 364/526, loss: 0.0032039673533290625
2023-01-24 06:12:48.602309: step: 368/526, loss: 0.01583411544561386
2023-01-24 06:12:49.669554: step: 372/526, loss: 0.005878274794667959
2023-01-24 06:12:50.724203: step: 376/526, loss: 0.007089337334036827
2023-01-24 06:12:51.801807: step: 380/526, loss: 0.03770569711923599
2023-01-24 06:12:52.870301: step: 384/526, loss: 0.03550266474485397
2023-01-24 06:12:53.968915: step: 388/526, loss: 0.009625154547393322
2023-01-24 06:12:55.029768: step: 392/526, loss: 0.005954100284725428
2023-01-24 06:12:56.104332: step: 396/526, loss: 0.01914738304913044
2023-01-24 06:12:57.181539: step: 400/526, loss: 0.010117245838046074
2023-01-24 06:12:58.243906: step: 404/526, loss: 0.038790617138147354
2023-01-24 06:12:59.314441: step: 408/526, loss: 0.009354247711598873
2023-01-24 06:13:00.391211: step: 412/526, loss: 0.009561301209032536
2023-01-24 06:13:01.462105: step: 416/526, loss: 0.022464746609330177
2023-01-24 06:13:02.534468: step: 420/526, loss: 0.015408172272145748
2023-01-24 06:13:03.622890: step: 424/526, loss: 0.02869766391813755
2023-01-24 06:13:04.707705: step: 428/526, loss: 0.02420332096517086
2023-01-24 06:13:05.798520: step: 432/526, loss: 0.011934206821024418
2023-01-24 06:13:06.877050: step: 436/526, loss: 0.06720546633005142
2023-01-24 06:13:07.950664: step: 440/526, loss: 0.013508724048733711
2023-01-24 06:13:09.015920: step: 444/526, loss: 0.003344995202496648
2023-01-24 06:13:10.080996: step: 448/526, loss: 0.01771223545074463
2023-01-24 06:13:11.156643: step: 452/526, loss: 0.00806915108114481
2023-01-24 06:13:12.240682: step: 456/526, loss: 0.032121557742357254
2023-01-24 06:13:13.313753: step: 460/526, loss: 0.007599648088216782
2023-01-24 06:13:14.388507: step: 464/526, loss: 0.012127426452934742
2023-01-24 06:13:15.471500: step: 468/526, loss: 0.0073621622286736965
2023-01-24 06:13:16.535304: step: 472/526, loss: 0.024229129776358604
2023-01-24 06:13:17.619527: step: 476/526, loss: 0.008662429638206959
2023-01-24 06:13:18.710419: step: 480/526, loss: 0.015572981908917427
2023-01-24 06:13:19.793615: step: 484/526, loss: 0.03178900107741356
2023-01-24 06:13:20.872096: step: 488/526, loss: 0.04805722087621689
2023-01-24 06:13:21.958027: step: 492/526, loss: 0.00870773196220398
2023-01-24 06:13:23.027469: step: 496/526, loss: 0.021471833810210228
2023-01-24 06:13:24.095865: step: 500/526, loss: 0.03204527869820595
2023-01-24 06:13:25.169405: step: 504/526, loss: 0.012247931212186813
2023-01-24 06:13:26.243609: step: 508/526, loss: 0.00462923850864172
2023-01-24 06:13:27.358193: step: 512/526, loss: 0.0216665118932724
2023-01-24 06:13:28.437639: step: 516/526, loss: 0.0545852854847908
2023-01-24 06:13:29.504061: step: 520/526, loss: 0.009089004248380661
2023-01-24 06:13:30.580985: step: 524/526, loss: 0.04380949214100838
2023-01-24 06:13:31.650293: step: 528/526, loss: 0.010037143714725971
2023-01-24 06:13:32.733724: step: 532/526, loss: 0.011802319437265396
2023-01-24 06:13:33.807377: step: 536/526, loss: 0.007577423006296158
2023-01-24 06:13:34.872416: step: 540/526, loss: 0.012781643308699131
2023-01-24 06:13:35.946673: step: 544/526, loss: 0.005990928970277309
2023-01-24 06:13:37.009578: step: 548/526, loss: 0.020134612917900085
2023-01-24 06:13:38.079691: step: 552/526, loss: 0.01833156682550907
2023-01-24 06:13:39.136803: step: 556/526, loss: 0.012743410654366016
2023-01-24 06:13:40.218687: step: 560/526, loss: 0.0056757088750600815
2023-01-24 06:13:41.281575: step: 564/526, loss: 0.005099541507661343
2023-01-24 06:13:42.347638: step: 568/526, loss: 0.03215373679995537
2023-01-24 06:13:43.403236: step: 572/526, loss: 0.030809998512268066
2023-01-24 06:13:44.468282: step: 576/526, loss: 0.018042458221316338
2023-01-24 06:13:45.512191: step: 580/526, loss: 0.015842700377106667
2023-01-24 06:13:46.570754: step: 584/526, loss: 0.007151165511459112
2023-01-24 06:13:47.637928: step: 588/526, loss: 0.00645815534517169
2023-01-24 06:13:48.715423: step: 592/526, loss: 0.006514847278594971
2023-01-24 06:13:49.779458: step: 596/526, loss: 0.006465676706284285
2023-01-24 06:13:50.881363: step: 600/526, loss: 0.021039044484496117
2023-01-24 06:13:51.958049: step: 604/526, loss: 0.03174136206507683
2023-01-24 06:13:53.028067: step: 608/526, loss: 0.005157373379915953
2023-01-24 06:13:54.104132: step: 612/526, loss: 0.014290643855929375
2023-01-24 06:13:55.170103: step: 616/526, loss: 0.0008734349976293743
2023-01-24 06:13:56.253545: step: 620/526, loss: 0.006645748857408762
2023-01-24 06:13:57.310208: step: 624/526, loss: 0.00627474719658494
2023-01-24 06:13:58.370229: step: 628/526, loss: 0.039031971246004105
2023-01-24 06:13:59.429938: step: 632/526, loss: 0.0062651680782437325
2023-01-24 06:14:00.519809: step: 636/526, loss: 0.010329682379961014
2023-01-24 06:14:01.588789: step: 640/526, loss: 0.03935340419411659
2023-01-24 06:14:02.659955: step: 644/526, loss: 0.013947218656539917
2023-01-24 06:14:03.740583: step: 648/526, loss: 0.02123948559165001
2023-01-24 06:14:04.810929: step: 652/526, loss: 0.011712118983268738
2023-01-24 06:14:05.892553: step: 656/526, loss: 0.0040458738803863525
2023-01-24 06:14:06.954032: step: 660/526, loss: 0.00468495674431324
2023-01-24 06:14:08.014988: step: 664/526, loss: 0.02137726917862892
2023-01-24 06:14:09.074989: step: 668/526, loss: 0.006868351716548204
2023-01-24 06:14:10.135125: step: 672/526, loss: 0.054988425225019455
2023-01-24 06:14:11.230354: step: 676/526, loss: 0.022215574979782104
2023-01-24 06:14:12.302880: step: 680/526, loss: 0.007315394002944231
2023-01-24 06:14:13.398493: step: 684/526, loss: 0.009959024377167225
2023-01-24 06:14:14.451801: step: 688/526, loss: 0.003706212854012847
2023-01-24 06:14:15.523939: step: 692/526, loss: 0.0057921684347093105
2023-01-24 06:14:16.592349: step: 696/526, loss: 0.01116146519780159
2023-01-24 06:14:17.663666: step: 700/526, loss: 0.0040785176679492
2023-01-24 06:14:18.752180: step: 704/526, loss: 0.017844034358859062
2023-01-24 06:14:19.825360: step: 708/526, loss: 0.015944886952638626
2023-01-24 06:14:20.906867: step: 712/526, loss: 0.0108705535531044
2023-01-24 06:14:21.966192: step: 716/526, loss: 0.009291144087910652
2023-01-24 06:14:23.034112: step: 720/526, loss: 0.007601814344525337
2023-01-24 06:14:24.100282: step: 724/526, loss: 0.03549468517303467
2023-01-24 06:14:25.156809: step: 728/526, loss: 0.003963234834372997
2023-01-24 06:14:26.217022: step: 732/526, loss: 0.007039588876068592
2023-01-24 06:14:27.284370: step: 736/526, loss: 0.010890254750847816
2023-01-24 06:14:28.350814: step: 740/526, loss: 0.00566583639010787
2023-01-24 06:14:29.416030: step: 744/526, loss: 0.0019247246673330665
2023-01-24 06:14:30.473601: step: 748/526, loss: 0.008732607588171959
2023-01-24 06:14:31.532851: step: 752/526, loss: 0.008327975869178772
2023-01-24 06:14:32.583776: step: 756/526, loss: 0.007925166748464108
2023-01-24 06:14:33.635036: step: 760/526, loss: 0.013754901476204395
2023-01-24 06:14:34.707736: step: 764/526, loss: 0.01145532913506031
2023-01-24 06:14:35.774629: step: 768/526, loss: 0.004006172064691782
2023-01-24 06:14:36.825572: step: 772/526, loss: 0.012019657529890537
2023-01-24 06:14:37.891402: step: 776/526, loss: 0.012505311518907547
2023-01-24 06:14:38.951144: step: 780/526, loss: 0.0036865200381726027
2023-01-24 06:14:40.011120: step: 784/526, loss: 0.0048268320970237255
2023-01-24 06:14:41.069007: step: 788/526, loss: 0.000239708082517609
2023-01-24 06:14:42.127554: step: 792/526, loss: 0.0015891763614490628
2023-01-24 06:14:43.193519: step: 796/526, loss: 0.010582678951323032
2023-01-24 06:14:44.250093: step: 800/526, loss: 0.05896751210093498
2023-01-24 06:14:45.333615: step: 804/526, loss: 0.011327753774821758
2023-01-24 06:14:46.406588: step: 808/526, loss: 0.046806029975414276
2023-01-24 06:14:47.463022: step: 812/526, loss: 0.048858143389225006
2023-01-24 06:14:48.516202: step: 816/526, loss: 0.01034831814467907
2023-01-24 06:14:49.565817: step: 820/526, loss: 0.02128666639328003
2023-01-24 06:14:50.636137: step: 824/526, loss: 0.013094465248286724
2023-01-24 06:14:51.698259: step: 828/526, loss: 0.0029561948031187057
2023-01-24 06:14:52.764481: step: 832/526, loss: 0.019411412999033928
2023-01-24 06:14:53.829278: step: 836/526, loss: 0.032024700194597244
2023-01-24 06:14:54.902710: step: 840/526, loss: 0.005607653874903917
2023-01-24 06:14:55.975235: step: 844/526, loss: 0.01002599485218525
2023-01-24 06:14:57.030112: step: 848/526, loss: 0.029176589101552963
2023-01-24 06:14:58.077536: step: 852/526, loss: 0.02625167742371559
2023-01-24 06:14:59.141965: step: 856/526, loss: 0.006641499698162079
2023-01-24 06:15:00.205118: step: 860/526, loss: 0.038459356874227524
2023-01-24 06:15:01.261042: step: 864/526, loss: 0.00858103483915329
2023-01-24 06:15:02.325996: step: 868/526, loss: 0.025573449209332466
2023-01-24 06:15:03.406801: step: 872/526, loss: 0.011654009111225605
2023-01-24 06:15:04.487645: step: 876/526, loss: 0.02767193876206875
2023-01-24 06:15:05.560189: step: 880/526, loss: 0.008378477767109871
2023-01-24 06:15:06.618273: step: 884/526, loss: 0.024453088641166687
2023-01-24 06:15:07.690098: step: 888/526, loss: 0.02721349149942398
2023-01-24 06:15:08.741205: step: 892/526, loss: 0.013855252414941788
2023-01-24 06:15:09.811898: step: 896/526, loss: 0.004693435505032539
2023-01-24 06:15:10.889708: step: 900/526, loss: 0.015292895957827568
2023-01-24 06:15:11.959675: step: 904/526, loss: 0.020867938175797462
2023-01-24 06:15:13.055212: step: 908/526, loss: 0.039456333965063095
2023-01-24 06:15:14.148516: step: 912/526, loss: 0.007400562521070242
2023-01-24 06:15:15.238518: step: 916/526, loss: 0.04387707635760307
2023-01-24 06:15:16.297273: step: 920/526, loss: 0.009956590831279755
2023-01-24 06:15:17.351420: step: 924/526, loss: 0.005391793791204691
2023-01-24 06:15:18.409990: step: 928/526, loss: 0.0059174406342208385
2023-01-24 06:15:19.459932: step: 932/526, loss: 0.008824181742966175
2023-01-24 06:15:20.529603: step: 936/526, loss: 0.013592577539384365
2023-01-24 06:15:21.602336: step: 940/526, loss: 0.011900778859853745
2023-01-24 06:15:22.661784: step: 944/526, loss: 0.009875464253127575
2023-01-24 06:15:23.745571: step: 948/526, loss: 0.0007198238163255155
2023-01-24 06:15:24.806784: step: 952/526, loss: 0.002723206765949726
2023-01-24 06:15:25.882250: step: 956/526, loss: 0.04314401000738144
2023-01-24 06:15:26.954668: step: 960/526, loss: 0.01172436773777008
2023-01-24 06:15:28.012072: step: 964/526, loss: 0.01210050005465746
2023-01-24 06:15:29.056188: step: 968/526, loss: 0.009707611054182053
2023-01-24 06:15:30.111069: step: 972/526, loss: 0.00920557975769043
2023-01-24 06:15:31.181122: step: 976/526, loss: 0.0039517320692539215
2023-01-24 06:15:32.247694: step: 980/526, loss: 0.035349588841199875
2023-01-24 06:15:33.320878: step: 984/526, loss: 0.05844910442829132
2023-01-24 06:15:34.398542: step: 988/526, loss: 0.008539840579032898
2023-01-24 06:15:35.469276: step: 992/526, loss: 0.0036421450786292553
2023-01-24 06:15:36.534380: step: 996/526, loss: 0.006346558686345816
2023-01-24 06:15:37.604651: step: 1000/526, loss: 0.020023275166749954
2023-01-24 06:15:38.672352: step: 1004/526, loss: 0.023386115208268166
2023-01-24 06:15:39.731004: step: 1008/526, loss: 0.012384321540594101
2023-01-24 06:15:40.810178: step: 1012/526, loss: 0.07021833956241608
2023-01-24 06:15:41.882993: step: 1016/526, loss: 0.020438725128769875
2023-01-24 06:15:42.959304: step: 1020/526, loss: 0.04313286393880844
2023-01-24 06:15:44.020151: step: 1024/526, loss: 0.011168815195560455
2023-01-24 06:15:45.084747: step: 1028/526, loss: 0.005922115407884121
2023-01-24 06:15:46.147653: step: 1032/526, loss: 0.010224668309092522
2023-01-24 06:15:47.228368: step: 1036/526, loss: 0.06196172907948494
2023-01-24 06:15:48.303524: step: 1040/526, loss: 0.021300524473190308
2023-01-24 06:15:49.386512: step: 1044/526, loss: 0.009970474056899548
2023-01-24 06:15:50.441418: step: 1048/526, loss: 0.014697756618261337
2023-01-24 06:15:51.506093: step: 1052/526, loss: 0.008854944258928299
2023-01-24 06:15:52.584523: step: 1056/526, loss: 0.014498366974294186
2023-01-24 06:15:53.666126: step: 1060/526, loss: 0.006762553472071886
2023-01-24 06:15:54.744872: step: 1064/526, loss: 0.04316618666052818
2023-01-24 06:15:55.804601: step: 1068/526, loss: 0.00620792293921113
2023-01-24 06:15:56.863603: step: 1072/526, loss: 0.005949460435658693
2023-01-24 06:15:57.937736: step: 1076/526, loss: 0.02700575813651085
2023-01-24 06:15:59.005951: step: 1080/526, loss: 0.02261035330593586
2023-01-24 06:16:00.082741: step: 1084/526, loss: 0.012013763189315796
2023-01-24 06:16:01.156694: step: 1088/526, loss: 0.015156416222453117
2023-01-24 06:16:02.239103: step: 1092/526, loss: 0.007228700909763575
2023-01-24 06:16:03.286139: step: 1096/526, loss: 0.011648271232843399
2023-01-24 06:16:04.369174: step: 1100/526, loss: 0.008078822866082191
2023-01-24 06:16:05.452073: step: 1104/526, loss: 0.005949000362306833
2023-01-24 06:16:06.523201: step: 1108/526, loss: 0.010286852717399597
2023-01-24 06:16:07.612172: step: 1112/526, loss: 0.031086308881640434
2023-01-24 06:16:08.692379: step: 1116/526, loss: 0.011280796490609646
2023-01-24 06:16:09.782741: step: 1120/526, loss: 0.004612576682120562
2023-01-24 06:16:10.858825: step: 1124/526, loss: 0.05066349729895592
2023-01-24 06:16:11.934034: step: 1128/526, loss: 0.004325521644204855
2023-01-24 06:16:12.991524: step: 1132/526, loss: 0.022121351212263107
2023-01-24 06:16:14.057036: step: 1136/526, loss: 0.0010887769749388099
2023-01-24 06:16:15.125705: step: 1140/526, loss: 0.018265364691615105
2023-01-24 06:16:16.186545: step: 1144/526, loss: 0.02968595176935196
2023-01-24 06:16:17.258587: step: 1148/526, loss: 0.03147466853260994
2023-01-24 06:16:18.330468: step: 1152/526, loss: 0.02486201375722885
2023-01-24 06:16:19.413895: step: 1156/526, loss: 0.01647029258310795
2023-01-24 06:16:20.473968: step: 1160/526, loss: 0.029502950608730316
2023-01-24 06:16:21.530083: step: 1164/526, loss: 0.02906990610063076
2023-01-24 06:16:22.607028: step: 1168/526, loss: 0.04194151982665062
2023-01-24 06:16:23.682301: step: 1172/526, loss: 0.00660712132230401
2023-01-24 06:16:24.767850: step: 1176/526, loss: 0.011205222457647324
2023-01-24 06:16:25.844943: step: 1180/526, loss: 0.011131997220218182
2023-01-24 06:16:26.898226: step: 1184/526, loss: 0.01965154893696308
2023-01-24 06:16:27.976179: step: 1188/526, loss: 0.01701144129037857
2023-01-24 06:16:29.037902: step: 1192/526, loss: 0.008872097358107567
2023-01-24 06:16:30.106682: step: 1196/526, loss: 0.021640565246343613
2023-01-24 06:16:31.170817: step: 1200/526, loss: 0.005938517861068249
2023-01-24 06:16:32.231176: step: 1204/526, loss: 0.007166590075939894
2023-01-24 06:16:33.302213: step: 1208/526, loss: 0.07776742428541183
2023-01-24 06:16:34.371233: step: 1212/526, loss: 0.005381354130804539
2023-01-24 06:16:35.433651: step: 1216/526, loss: 0.029926860705018044
2023-01-24 06:16:36.505565: step: 1220/526, loss: 0.00538078136742115
2023-01-24 06:16:37.602577: step: 1224/526, loss: 0.005435564089566469
2023-01-24 06:16:38.673844: step: 1228/526, loss: 0.04002247005701065
2023-01-24 06:16:39.736944: step: 1232/526, loss: 0.0023748199455440044
2023-01-24 06:16:40.808944: step: 1236/526, loss: 0.02900881879031658
2023-01-24 06:16:41.886592: step: 1240/526, loss: 0.01200336217880249
2023-01-24 06:16:42.953861: step: 1244/526, loss: 0.03268972411751747
2023-01-24 06:16:44.042765: step: 1248/526, loss: 0.00803168024867773
2023-01-24 06:16:45.101487: step: 1252/526, loss: 0.01995820552110672
2023-01-24 06:16:46.171088: step: 1256/526, loss: 0.048296958208084106
2023-01-24 06:16:47.257154: step: 1260/526, loss: 0.0035812933929264545
2023-01-24 06:16:48.332001: step: 1264/526, loss: 0.005360682960599661
2023-01-24 06:16:49.399052: step: 1268/526, loss: 0.0019773298408836126
2023-01-24 06:16:50.472786: step: 1272/526, loss: 0.008220542222261429
2023-01-24 06:16:51.542970: step: 1276/526, loss: 0.007411687169224024
2023-01-24 06:16:52.626539: step: 1280/526, loss: 0.009043864905834198
2023-01-24 06:16:53.699692: step: 1284/526, loss: 0.013929463922977448
2023-01-24 06:16:54.780688: step: 1288/526, loss: 0.0
2023-01-24 06:16:55.857469: step: 1292/526, loss: 0.005940048024058342
2023-01-24 06:16:56.935747: step: 1296/526, loss: 0.09276102483272552
2023-01-24 06:16:58.019252: step: 1300/526, loss: 0.008096638135612011
2023-01-24 06:16:59.105845: step: 1304/526, loss: 0.012664354406297207
2023-01-24 06:17:00.168192: step: 1308/526, loss: 0.006375948898494244
2023-01-24 06:17:01.237938: step: 1312/526, loss: 0.06691757589578629
2023-01-24 06:17:02.319174: step: 1316/526, loss: 0.04357099160552025
2023-01-24 06:17:03.409532: step: 1320/526, loss: 0.01275489293038845
2023-01-24 06:17:04.485799: step: 1324/526, loss: 0.007187874987721443
2023-01-24 06:17:05.561471: step: 1328/526, loss: 0.0026793908327817917
2023-01-24 06:17:06.630333: step: 1332/526, loss: 0.013523890636861324
2023-01-24 06:17:07.698903: step: 1336/526, loss: 0.005205713678151369
2023-01-24 06:17:08.772372: step: 1340/526, loss: 0.05279330536723137
2023-01-24 06:17:09.849138: step: 1344/526, loss: 0.006751976907253265
2023-01-24 06:17:10.918595: step: 1348/526, loss: 0.00653742766007781
2023-01-24 06:17:12.000508: step: 1352/526, loss: 0.009395278058946133
2023-01-24 06:17:13.088776: step: 1356/526, loss: 0.008364694193005562
2023-01-24 06:17:14.159368: step: 1360/526, loss: 0.009754997678101063
2023-01-24 06:17:15.260023: step: 1364/526, loss: 0.017432140186429024
2023-01-24 06:17:16.317026: step: 1368/526, loss: 0.010237367823719978
2023-01-24 06:17:17.398989: step: 1372/526, loss: 0.006789594888687134
2023-01-24 06:17:18.480768: step: 1376/526, loss: 0.007290634326636791
2023-01-24 06:17:19.565712: step: 1380/526, loss: 0.02280835248529911
2023-01-24 06:17:20.653492: step: 1384/526, loss: 0.02002943493425846
2023-01-24 06:17:21.730081: step: 1388/526, loss: 0.007367415819317102
2023-01-24 06:17:22.803766: step: 1392/526, loss: 0.02557818405330181
2023-01-24 06:17:23.878823: step: 1396/526, loss: 0.00872527901083231
2023-01-24 06:17:24.950836: step: 1400/526, loss: 0.009468142874538898
2023-01-24 06:17:26.026544: step: 1404/526, loss: 0.006287826225161552
2023-01-24 06:17:27.087292: step: 1408/526, loss: 0.0003901036689057946
2023-01-24 06:17:28.148606: step: 1412/526, loss: 0.022159673273563385
2023-01-24 06:17:29.236349: step: 1416/526, loss: 0.010757877491414547
2023-01-24 06:17:30.311917: step: 1420/526, loss: 0.004200148396193981
2023-01-24 06:17:31.388704: step: 1424/526, loss: 0.003942762967199087
2023-01-24 06:17:32.446121: step: 1428/526, loss: 0.002182086231186986
2023-01-24 06:17:33.518510: step: 1432/526, loss: 0.005723259411752224
2023-01-24 06:17:34.603612: step: 1436/526, loss: 0.004808911122381687
2023-01-24 06:17:35.685031: step: 1440/526, loss: 0.022685237228870392
2023-01-24 06:17:36.764566: step: 1444/526, loss: 0.027270250022411346
2023-01-24 06:17:37.858539: step: 1448/526, loss: 0.008733347989618778
2023-01-24 06:17:38.929355: step: 1452/526, loss: 0.008996464312076569
2023-01-24 06:17:40.008424: step: 1456/526, loss: 0.010059132240712643
2023-01-24 06:17:41.082057: step: 1460/526, loss: 0.04958635941147804
2023-01-24 06:17:42.173658: step: 1464/526, loss: 0.007838988676667213
2023-01-24 06:17:43.245772: step: 1468/526, loss: 0.014982925727963448
2023-01-24 06:17:44.333386: step: 1472/526, loss: 0.02857663668692112
2023-01-24 06:17:45.428919: step: 1476/526, loss: 0.03424534201622009
2023-01-24 06:17:46.508969: step: 1480/526, loss: 0.005225681234151125
2023-01-24 06:17:47.590953: step: 1484/526, loss: 0.006253308150917292
2023-01-24 06:17:48.673859: step: 1488/526, loss: 0.006416618824005127
2023-01-24 06:17:49.751467: step: 1492/526, loss: 0.005713945254683495
2023-01-24 06:17:50.817979: step: 1496/526, loss: 0.007323291152715683
2023-01-24 06:17:51.896857: step: 1500/526, loss: 0.0054649063386023045
2023-01-24 06:17:52.971913: step: 1504/526, loss: 0.0751451775431633
2023-01-24 06:17:54.041248: step: 1508/526, loss: 0.007875404320657253
2023-01-24 06:17:55.110421: step: 1512/526, loss: 0.016096655279397964
2023-01-24 06:17:56.200765: step: 1516/526, loss: 0.013204229064285755
2023-01-24 06:17:57.272335: step: 1520/526, loss: 0.0037331937346607447
2023-01-24 06:17:58.354484: step: 1524/526, loss: 0.047402508556842804
2023-01-24 06:17:59.441535: step: 1528/526, loss: 0.008372505195438862
2023-01-24 06:18:00.520573: step: 1532/526, loss: 0.0040089040994644165
2023-01-24 06:18:01.606445: step: 1536/526, loss: 0.003782615065574646
2023-01-24 06:18:02.683075: step: 1540/526, loss: 0.0023831261787563562
2023-01-24 06:18:03.757279: step: 1544/526, loss: 0.004488678649067879
2023-01-24 06:18:04.830774: step: 1548/526, loss: 0.0026706543285399675
2023-01-24 06:18:05.923628: step: 1552/526, loss: 0.016022304072976112
2023-01-24 06:18:06.995618: step: 1556/526, loss: 0.016195174306631088
2023-01-24 06:18:08.075434: step: 1560/526, loss: 0.015752162784337997
2023-01-24 06:18:09.154891: step: 1564/526, loss: 0.00617462582886219
2023-01-24 06:18:10.224339: step: 1568/526, loss: 0.00824673194438219
2023-01-24 06:18:11.295023: step: 1572/526, loss: 0.04886094108223915
2023-01-24 06:18:12.364948: step: 1576/526, loss: 0.016282636672258377
2023-01-24 06:18:13.441450: step: 1580/526, loss: 0.005639585200697184
2023-01-24 06:18:14.526293: step: 1584/526, loss: 0.009086117148399353
2023-01-24 06:18:15.604202: step: 1588/526, loss: 0.007528063375502825
2023-01-24 06:18:16.673496: step: 1592/526, loss: 0.0
2023-01-24 06:18:17.738501: step: 1596/526, loss: 0.0008297221502289176
2023-01-24 06:18:18.808402: step: 1600/526, loss: 0.015622070990502834
2023-01-24 06:18:19.877133: step: 1604/526, loss: 0.0505061000585556
2023-01-24 06:18:20.941934: step: 1608/526, loss: 0.029565712437033653
2023-01-24 06:18:22.013475: step: 1612/526, loss: 0.00864845234900713
2023-01-24 06:18:23.092417: step: 1616/526, loss: 0.002517703687772155
2023-01-24 06:18:24.156175: step: 1620/526, loss: 0.009909183718264103
2023-01-24 06:18:25.233477: step: 1624/526, loss: 0.011386432684957981
2023-01-24 06:18:26.302610: step: 1628/526, loss: 0.030048370361328125
2023-01-24 06:18:27.373433: step: 1632/526, loss: 0.011784379370510578
2023-01-24 06:18:28.428573: step: 1636/526, loss: 0.005533888470381498
2023-01-24 06:18:29.490296: step: 1640/526, loss: 0.009105381555855274
2023-01-24 06:18:30.543698: step: 1644/526, loss: 0.005557889584451914
2023-01-24 06:18:31.620226: step: 1648/526, loss: 0.011499984189867973
2023-01-24 06:18:32.691298: step: 1652/526, loss: 0.013947533443570137
2023-01-24 06:18:33.752338: step: 1656/526, loss: 0.0017300623003393412
2023-01-24 06:18:34.834993: step: 1660/526, loss: 0.0029353441204875708
2023-01-24 06:18:35.911444: step: 1664/526, loss: 0.005586166866123676
2023-01-24 06:18:37.009593: step: 1668/526, loss: 0.06570611894130707
2023-01-24 06:18:38.077386: step: 1672/526, loss: 0.0074541871435940266
2023-01-24 06:18:39.164555: step: 1676/526, loss: 0.003746382426470518
2023-01-24 06:18:40.223974: step: 1680/526, loss: 0.004787694662809372
2023-01-24 06:18:41.297299: step: 1684/526, loss: 0.007458502892404795
2023-01-24 06:18:42.378829: step: 1688/526, loss: 0.029496192932128906
2023-01-24 06:18:43.440322: step: 1692/526, loss: 0.012440165504813194
2023-01-24 06:18:44.513920: step: 1696/526, loss: 0.0144155602902174
2023-01-24 06:18:45.594656: step: 1700/526, loss: 0.008919878862798214
2023-01-24 06:18:46.670945: step: 1704/526, loss: 0.0047838035970926285
2023-01-24 06:18:47.747617: step: 1708/526, loss: 0.015375535003840923
2023-01-24 06:18:48.830479: step: 1712/526, loss: 0.052577659487724304
2023-01-24 06:18:49.894176: step: 1716/526, loss: 0.013651976361870766
2023-01-24 06:18:50.954469: step: 1720/526, loss: 0.018864955753087997
2023-01-24 06:18:52.028164: step: 1724/526, loss: 0.00418910151347518
2023-01-24 06:18:53.088940: step: 1728/526, loss: 0.017243286594748497
2023-01-24 06:18:54.158611: step: 1732/526, loss: 0.010998336598277092
2023-01-24 06:18:55.215980: step: 1736/526, loss: 0.007787647657096386
2023-01-24 06:18:56.296410: step: 1740/526, loss: 0.012227986939251423
2023-01-24 06:18:57.346247: step: 1744/526, loss: 0.031399860978126526
2023-01-24 06:18:58.456076: step: 1748/526, loss: 0.0052993446588516235
2023-01-24 06:18:59.525386: step: 1752/526, loss: 0.022675102576613426
2023-01-24 06:19:00.594656: step: 1756/526, loss: 0.008326425217092037
2023-01-24 06:19:01.656096: step: 1760/526, loss: 0.0073272292502224445
2023-01-24 06:19:02.731466: step: 1764/526, loss: 0.01987486705183983
2023-01-24 06:19:03.787199: step: 1768/526, loss: 0.04475490748882294
2023-01-24 06:19:04.854464: step: 1772/526, loss: 0.004304112400859594
2023-01-24 06:19:05.938384: step: 1776/526, loss: 0.02367010898888111
2023-01-24 06:19:06.998053: step: 1780/526, loss: 0.006102908868342638
2023-01-24 06:19:08.062278: step: 1784/526, loss: 0.0031300713308155537
2023-01-24 06:19:09.138563: step: 1788/526, loss: 0.030115678906440735
2023-01-24 06:19:10.214694: step: 1792/526, loss: 0.05035819113254547
2023-01-24 06:19:11.278788: step: 1796/526, loss: 0.016981353983283043
2023-01-24 06:19:12.357650: step: 1800/526, loss: 0.007648933213204145
2023-01-24 06:19:13.417086: step: 1804/526, loss: 0.007050811313092709
2023-01-24 06:19:14.490219: step: 1808/526, loss: 0.007111803628504276
2023-01-24 06:19:15.554320: step: 1812/526, loss: 0.049223240464925766
2023-01-24 06:19:16.619784: step: 1816/526, loss: 0.011343998834490776
2023-01-24 06:19:17.692433: step: 1820/526, loss: 0.011715702712535858
2023-01-24 06:19:18.771974: step: 1824/526, loss: 0.0065694102086126804
2023-01-24 06:19:19.830316: step: 1828/526, loss: 0.004104414954781532
2023-01-24 06:19:20.907154: step: 1832/526, loss: 0.05072854459285736
2023-01-24 06:19:21.983447: step: 1836/526, loss: 0.0064126052893698215
2023-01-24 06:19:23.054643: step: 1840/526, loss: 0.004947653040289879
2023-01-24 06:19:24.116663: step: 1844/526, loss: 0.005876810755580664
2023-01-24 06:19:25.183379: step: 1848/526, loss: 0.007638882379978895
2023-01-24 06:19:26.235444: step: 1852/526, loss: 0.026459213346242905
2023-01-24 06:19:27.308546: step: 1856/526, loss: 0.01469198614358902
2023-01-24 06:19:28.386232: step: 1860/526, loss: 0.01027812622487545
2023-01-24 06:19:29.472166: step: 1864/526, loss: 0.01965285837650299
2023-01-24 06:19:30.528988: step: 1868/526, loss: 0.02159073017537594
2023-01-24 06:19:31.599736: step: 1872/526, loss: 0.005820313468575478
2023-01-24 06:19:32.667902: step: 1876/526, loss: 0.0221233032643795
2023-01-24 06:19:33.749318: step: 1880/526, loss: 0.0033949408680200577
2023-01-24 06:19:34.821996: step: 1884/526, loss: 0.050316862761974335
2023-01-24 06:19:35.886066: step: 1888/526, loss: 0.05392443761229515
2023-01-24 06:19:36.963888: step: 1892/526, loss: 0.010367084294557571
2023-01-24 06:19:38.027834: step: 1896/526, loss: 0.012242653407156467
2023-01-24 06:19:39.082047: step: 1900/526, loss: 0.02093501016497612
2023-01-24 06:19:40.155469: step: 1904/526, loss: 0.008596562780439854
2023-01-24 06:19:41.226138: step: 1908/526, loss: 0.00320019805803895
2023-01-24 06:19:42.290820: step: 1912/526, loss: 0.005016467534005642
2023-01-24 06:19:43.354508: step: 1916/526, loss: 0.06825742870569229
2023-01-24 06:19:44.413360: step: 1920/526, loss: 0.004963371902704239
2023-01-24 06:19:45.507825: step: 1924/526, loss: 0.01704205945134163
2023-01-24 06:19:46.569197: step: 1928/526, loss: 0.007099714130163193
2023-01-24 06:19:47.629797: step: 1932/526, loss: 0.012352654710412025
2023-01-24 06:19:48.695139: step: 1936/526, loss: 0.03212769702076912
2023-01-24 06:19:49.759708: step: 1940/526, loss: 0.017122428864240646
2023-01-24 06:19:50.827750: step: 1944/526, loss: 0.009441671893000603
2023-01-24 06:19:51.911797: step: 1948/526, loss: 0.011189322918653488
2023-01-24 06:19:52.986751: step: 1952/526, loss: 0.008775146678090096
2023-01-24 06:19:54.050272: step: 1956/526, loss: 0.004551365040242672
2023-01-24 06:19:55.124796: step: 1960/526, loss: 0.01498501654714346
2023-01-24 06:19:56.199287: step: 1964/526, loss: 0.026638157665729523
2023-01-24 06:19:57.264817: step: 1968/526, loss: 0.01696990244090557
2023-01-24 06:19:58.341625: step: 1972/526, loss: 0.005672011990100145
2023-01-24 06:19:59.407519: step: 1976/526, loss: 0.011845101602375507
2023-01-24 06:20:00.484620: step: 1980/526, loss: 0.006821760442107916
2023-01-24 06:20:01.568562: step: 1984/526, loss: 0.02255084179341793
2023-01-24 06:20:02.638119: step: 1988/526, loss: 6.998753815423697e-05
2023-01-24 06:20:03.716054: step: 1992/526, loss: 0.0037554940208792686
2023-01-24 06:20:04.784942: step: 1996/526, loss: 0.0038460008800029755
2023-01-24 06:20:05.867915: step: 2000/526, loss: 0.004586793016642332
2023-01-24 06:20:06.962132: step: 2004/526, loss: 0.009389428421854973
2023-01-24 06:20:08.025139: step: 2008/526, loss: 0.009711971506476402
2023-01-24 06:20:09.087968: step: 2012/526, loss: 0.005631749983876944
2023-01-24 06:20:10.163458: step: 2016/526, loss: 0.00222161877900362
2023-01-24 06:20:11.222517: step: 2020/526, loss: 0.00375740067102015
2023-01-24 06:20:12.276925: step: 2024/526, loss: 0.0015059334691613913
2023-01-24 06:20:13.347922: step: 2028/526, loss: 0.0029861547518521547
2023-01-24 06:20:14.435678: step: 2032/526, loss: 0.021876122802495956
2023-01-24 06:20:15.481289: step: 2036/526, loss: 0.004218714311718941
2023-01-24 06:20:16.554310: step: 2040/526, loss: 0.07000627368688583
2023-01-24 06:20:17.618743: step: 2044/526, loss: 0.004202850162982941
2023-01-24 06:20:18.685735: step: 2048/526, loss: 0.0029538043309003115
2023-01-24 06:20:19.784828: step: 2052/526, loss: 0.040568865835666656
2023-01-24 06:20:20.847414: step: 2056/526, loss: 0.010062962770462036
2023-01-24 06:20:21.905159: step: 2060/526, loss: 0.007632994093000889
2023-01-24 06:20:22.969350: step: 2064/526, loss: 0.01092681847512722
2023-01-24 06:20:24.017030: step: 2068/526, loss: 0.023032061755657196
2023-01-24 06:20:25.083469: step: 2072/526, loss: 0.03470155596733093
2023-01-24 06:20:26.179260: step: 2076/526, loss: 0.05821975693106651
2023-01-24 06:20:27.249353: step: 2080/526, loss: 0.04016618803143501
2023-01-24 06:20:28.315335: step: 2084/526, loss: 0.03075486421585083
2023-01-24 06:20:29.367290: step: 2088/526, loss: 0.03850513696670532
2023-01-24 06:20:30.427194: step: 2092/526, loss: 0.00623524934053421
2023-01-24 06:20:31.522573: step: 2096/526, loss: 0.003364350413903594
2023-01-24 06:20:32.599212: step: 2100/526, loss: 0.01366267167031765
2023-01-24 06:20:33.670455: step: 2104/526, loss: 0.01837616041302681
==================================================
Loss: 0.016
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336995843596059, 'r': 0.29380760368663594, 'f1': 0.31248558454663394}, 'combined': 0.23025253598173026, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597710279387254, 'r': 0.2590483064846998, 'f1': 0.30121255211465625}, 'combined': 0.1642977556989034, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3597402018039063, 'r': 0.3187830630786039, 'f1': 0.3380255014938114}, 'combined': 0.2490714221533347, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3626348362380441, 'r': 0.2743815275103957, 'f1': 0.3123948016342317}, 'combined': 0.17039716452776274, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336995843596059, 'r': 0.29380760368663594, 'f1': 0.31248558454663394}, 'combined': 0.23025253598173026, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597710279387254, 'r': 0.2590483064846998, 'f1': 0.30121255211465625}, 'combined': 0.1642977556989034, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3597402018039063, 'r': 0.3187830630786039, 'f1': 0.3380255014938114}, 'combined': 0.2490714221533347, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3626348362380441, 'r': 0.2743815275103957, 'f1': 0.3123948016342317}, 'combined': 0.17039716452776274, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:23:33.572006: step: 4/526, loss: 0.009650016203522682
2023-01-24 06:23:34.619182: step: 8/526, loss: 0.010013791732490063
2023-01-24 06:23:35.679384: step: 12/526, loss: 0.03347144275903702
2023-01-24 06:23:36.724463: step: 16/526, loss: 0.013068323954939842
2023-01-24 06:23:37.786694: step: 20/526, loss: 0.01097600907087326
2023-01-24 06:23:38.832632: step: 24/526, loss: 0.019244518131017685
2023-01-24 06:23:39.888311: step: 28/526, loss: 0.012354213744401932
2023-01-24 06:23:40.948878: step: 32/526, loss: 0.014527775347232819
2023-01-24 06:23:42.012619: step: 36/526, loss: 0.0045250277034938335
2023-01-24 06:23:43.091672: step: 40/526, loss: 0.008542371913790703
2023-01-24 06:23:44.138093: step: 44/526, loss: 0.006913589779287577
2023-01-24 06:23:45.197571: step: 48/526, loss: 0.007144640665501356
2023-01-24 06:23:46.223603: step: 52/526, loss: 0.011766207404434681
2023-01-24 06:23:47.297491: step: 56/526, loss: 0.0032600248232483864
2023-01-24 06:23:48.362455: step: 60/526, loss: 0.03873160853981972
2023-01-24 06:23:49.436834: step: 64/526, loss: 0.020658886060118675
2023-01-24 06:23:50.489390: step: 68/526, loss: 0.0038150351028889418
2023-01-24 06:23:51.540814: step: 72/526, loss: 0.008012867532670498
2023-01-24 06:23:52.589936: step: 76/526, loss: 0.008683625608682632
2023-01-24 06:23:53.654543: step: 80/526, loss: 0.007013949099928141
2023-01-24 06:23:54.733303: step: 84/526, loss: 0.004606140777468681
2023-01-24 06:23:55.793261: step: 88/526, loss: 0.01227221917361021
2023-01-24 06:23:56.862046: step: 92/526, loss: 0.007199561223387718
2023-01-24 06:23:57.925653: step: 96/526, loss: 0.057429712265729904
2023-01-24 06:23:59.000274: step: 100/526, loss: 0.00389100331813097
2023-01-24 06:24:00.061075: step: 104/526, loss: 0.00589369423687458
2023-01-24 06:24:01.108246: step: 108/526, loss: 0.012208799831569195
2023-01-24 06:24:02.165845: step: 112/526, loss: 0.034113410860300064
2023-01-24 06:24:03.245529: step: 116/526, loss: 0.005686573684215546
2023-01-24 06:24:04.299802: step: 120/526, loss: 0.00732325529679656
2023-01-24 06:24:05.357359: step: 124/526, loss: 0.06855107843875885
2023-01-24 06:24:06.438133: step: 128/526, loss: 0.008350858464837074
2023-01-24 06:24:07.494130: step: 132/526, loss: 0.0071120294742286205
2023-01-24 06:24:08.560255: step: 136/526, loss: 0.010930932126939297
2023-01-24 06:24:09.630500: step: 140/526, loss: 0.01904200203716755
2023-01-24 06:24:10.691475: step: 144/526, loss: 0.030828766524791718
2023-01-24 06:24:11.765551: step: 148/526, loss: 0.004793122410774231
2023-01-24 06:24:12.855737: step: 152/526, loss: 0.010236724279820919
2023-01-24 06:24:13.917821: step: 156/526, loss: 0.030238352715969086
2023-01-24 06:24:15.007836: step: 160/526, loss: 0.006312841083854437
2023-01-24 06:24:16.061906: step: 164/526, loss: 0.01839604042470455
2023-01-24 06:24:17.130198: step: 168/526, loss: 0.0034752930514514446
2023-01-24 06:24:18.192883: step: 172/526, loss: 0.006147360894829035
2023-01-24 06:24:19.252074: step: 176/526, loss: 0.01481261570006609
2023-01-24 06:24:20.320635: step: 180/526, loss: 0.011082170531153679
2023-01-24 06:24:21.385418: step: 184/526, loss: 0.010606542229652405
2023-01-24 06:24:22.453479: step: 188/526, loss: 0.026972047984600067
2023-01-24 06:24:23.507962: step: 192/526, loss: 0.009704423137009144
2023-01-24 06:24:24.578128: step: 196/526, loss: 0.04423944279551506
2023-01-24 06:24:25.646724: step: 200/526, loss: 0.001866355654783547
2023-01-24 06:24:26.732248: step: 204/526, loss: 0.025922570377588272
2023-01-24 06:24:27.804403: step: 208/526, loss: 0.011625106446444988
2023-01-24 06:24:28.869025: step: 212/526, loss: 0.012148432433605194
2023-01-24 06:24:29.941886: step: 216/526, loss: 0.03693895414471626
2023-01-24 06:24:31.014716: step: 220/526, loss: 0.027484169229865074
2023-01-24 06:24:32.091457: step: 224/526, loss: 0.007740234490483999
2023-01-24 06:24:33.149570: step: 228/526, loss: 0.004102836828678846
2023-01-24 06:24:34.226175: step: 232/526, loss: 0.004029305651783943
2023-01-24 06:24:35.294128: step: 236/526, loss: 0.005516399163752794
2023-01-24 06:24:36.383425: step: 240/526, loss: 0.013329179026186466
2023-01-24 06:24:37.441693: step: 244/526, loss: 0.021181335672736168
2023-01-24 06:24:38.496825: step: 248/526, loss: 0.02165023237466812
2023-01-24 06:24:39.571766: step: 252/526, loss: 0.004780726041644812
2023-01-24 06:24:40.645433: step: 256/526, loss: 0.003291594795882702
2023-01-24 06:24:41.713415: step: 260/526, loss: 0.02164202742278576
2023-01-24 06:24:42.781892: step: 264/526, loss: 0.007455023936927319
2023-01-24 06:24:43.832670: step: 268/526, loss: 0.012338540516793728
2023-01-24 06:24:44.904169: step: 272/526, loss: 0.022265000268816948
2023-01-24 06:24:45.970170: step: 276/526, loss: 0.0051247356459498405
2023-01-24 06:24:47.041899: step: 280/526, loss: 0.004940933547914028
2023-01-24 06:24:48.112168: step: 284/526, loss: 0.010958746075630188
2023-01-24 06:24:49.196868: step: 288/526, loss: 0.01980961114168167
2023-01-24 06:24:50.261260: step: 292/526, loss: 0.010513312183320522
2023-01-24 06:24:51.339674: step: 296/526, loss: 0.029352642595767975
2023-01-24 06:24:52.390296: step: 300/526, loss: 0.005348069127649069
2023-01-24 06:24:53.446737: step: 304/526, loss: 0.006212959531694651
2023-01-24 06:24:54.526355: step: 308/526, loss: 0.005067212041467428
2023-01-24 06:24:55.611871: step: 312/526, loss: 0.006340665742754936
2023-01-24 06:24:56.686738: step: 316/526, loss: 0.006352726370096207
2023-01-24 06:24:57.754980: step: 320/526, loss: 0.004037776030600071
2023-01-24 06:24:58.817366: step: 324/526, loss: 0.004941687453538179
2023-01-24 06:24:59.910155: step: 328/526, loss: 0.005619700998067856
2023-01-24 06:25:00.989217: step: 332/526, loss: 0.026720736175775528
2023-01-24 06:25:02.062865: step: 336/526, loss: 0.018055040389299393
2023-01-24 06:25:03.117174: step: 340/526, loss: 0.00468561053276062
2023-01-24 06:25:04.166301: step: 344/526, loss: 0.005450468976050615
2023-01-24 06:25:05.241033: step: 348/526, loss: 0.006480196490883827
2023-01-24 06:25:06.312199: step: 352/526, loss: 0.0015610882546752691
2023-01-24 06:25:07.369667: step: 356/526, loss: 0.0013867387315258384
2023-01-24 06:25:08.425891: step: 360/526, loss: 0.025500910356640816
2023-01-24 06:25:09.489784: step: 364/526, loss: 0.0005921070696786046
2023-01-24 06:25:10.561214: step: 368/526, loss: 0.004796150140464306
2023-01-24 06:25:11.629821: step: 372/526, loss: 0.013667273335158825
2023-01-24 06:25:12.701592: step: 376/526, loss: 0.008390936069190502
2023-01-24 06:25:13.803306: step: 380/526, loss: 0.007209073752164841
2023-01-24 06:25:14.869303: step: 384/526, loss: 0.004153812769800425
2023-01-24 06:25:15.953636: step: 388/526, loss: 0.004443436861038208
2023-01-24 06:25:17.024676: step: 392/526, loss: 0.008662360720336437
2023-01-24 06:25:18.098133: step: 396/526, loss: 0.010088438168168068
2023-01-24 06:25:19.183415: step: 400/526, loss: 0.02405945584177971
2023-01-24 06:25:20.252359: step: 404/526, loss: 0.012908042408525944
2023-01-24 06:25:21.311306: step: 408/526, loss: 0.004260818473994732
2023-01-24 06:25:22.372948: step: 412/526, loss: 0.03877304866909981
2023-01-24 06:25:23.453111: step: 416/526, loss: 0.0057965912856161594
2023-01-24 06:25:24.529156: step: 420/526, loss: 0.00363843678496778
2023-01-24 06:25:25.597150: step: 424/526, loss: 0.0026531137991696596
2023-01-24 06:25:26.664007: step: 428/526, loss: 0.023729026317596436
2023-01-24 06:25:27.737696: step: 432/526, loss: 0.0037401465233415365
2023-01-24 06:25:28.802688: step: 436/526, loss: 0.001971272751688957
2023-01-24 06:25:29.855837: step: 440/526, loss: 0.014780450612306595
2023-01-24 06:25:30.924584: step: 444/526, loss: 0.008082711137831211
2023-01-24 06:25:32.006760: step: 448/526, loss: 0.013978217728435993
2023-01-24 06:25:33.078460: step: 452/526, loss: 0.0030507894698530436
2023-01-24 06:25:34.137893: step: 456/526, loss: 0.005185616668313742
2023-01-24 06:25:35.200979: step: 460/526, loss: 0.012244999408721924
2023-01-24 06:25:36.257198: step: 464/526, loss: 0.018588056787848473
2023-01-24 06:25:37.322625: step: 468/526, loss: 0.010285770520567894
2023-01-24 06:25:38.404573: step: 472/526, loss: 0.008559764362871647
2023-01-24 06:25:39.492026: step: 476/526, loss: 0.05094970762729645
2023-01-24 06:25:40.552467: step: 480/526, loss: 0.015446318313479424
2023-01-24 06:25:41.601010: step: 484/526, loss: 0.008355128578841686
2023-01-24 06:25:42.674091: step: 488/526, loss: 0.007788226939737797
2023-01-24 06:25:43.745740: step: 492/526, loss: 0.04156165570020676
2023-01-24 06:25:44.824476: step: 496/526, loss: 0.02522088587284088
2023-01-24 06:25:45.890350: step: 500/526, loss: 0.011526042595505714
2023-01-24 06:25:46.958053: step: 504/526, loss: 0.002771098632365465
2023-01-24 06:25:48.033606: step: 508/526, loss: 0.007668028119951487
2023-01-24 06:25:49.105875: step: 512/526, loss: 0.00046785661834292114
2023-01-24 06:25:50.164200: step: 516/526, loss: 0.008059462532401085
2023-01-24 06:25:51.234783: step: 520/526, loss: 0.006946189794689417
2023-01-24 06:25:52.310481: step: 524/526, loss: 0.007862059399485588
2023-01-24 06:25:53.378996: step: 528/526, loss: 0.013094890862703323
2023-01-24 06:25:54.454590: step: 532/526, loss: 0.0
2023-01-24 06:25:55.527702: step: 536/526, loss: 0.0189999807626009
2023-01-24 06:25:56.601439: step: 540/526, loss: 0.006072042975574732
2023-01-24 06:25:57.675753: step: 544/526, loss: 0.004083544015884399
2023-01-24 06:25:58.752465: step: 548/526, loss: 0.027086535468697548
2023-01-24 06:25:59.823490: step: 552/526, loss: 0.05943413823843002
2023-01-24 06:26:00.889243: step: 556/526, loss: 0.006296733859926462
2023-01-24 06:26:01.941544: step: 560/526, loss: 0.004672641400247812
2023-01-24 06:26:03.018011: step: 564/526, loss: 0.0034309227485209703
2023-01-24 06:26:04.090553: step: 568/526, loss: 0.01013965904712677
2023-01-24 06:26:05.146323: step: 572/526, loss: 0.004993991460651159
2023-01-24 06:26:06.210306: step: 576/526, loss: 0.003762580454349518
2023-01-24 06:26:07.261093: step: 580/526, loss: 0.006700827274471521
2023-01-24 06:26:08.363146: step: 584/526, loss: 0.0065978216007351875
2023-01-24 06:26:09.438432: step: 588/526, loss: 0.0027285825926810503
2023-01-24 06:26:10.496186: step: 592/526, loss: 0.0026484897825866938
2023-01-24 06:26:11.559723: step: 596/526, loss: 0.008796604350209236
2023-01-24 06:26:12.639646: step: 600/526, loss: 0.02042219042778015
2023-01-24 06:26:13.701158: step: 604/526, loss: 0.008733711205422878
2023-01-24 06:26:14.778044: step: 608/526, loss: 0.0034685188438743353
2023-01-24 06:26:15.861160: step: 612/526, loss: 0.058398570865392685
2023-01-24 06:26:16.921184: step: 616/526, loss: 0.007216060534119606
2023-01-24 06:26:17.990864: step: 620/526, loss: 0.0075833601877093315
2023-01-24 06:26:19.053568: step: 624/526, loss: 0.01524543296545744
2023-01-24 06:26:20.118446: step: 628/526, loss: 0.008459759876132011
2023-01-24 06:26:21.189225: step: 632/526, loss: 0.019246211275458336
2023-01-24 06:26:22.263540: step: 636/526, loss: 0.01280898880213499
2023-01-24 06:26:23.339267: step: 640/526, loss: 0.010272116400301456
2023-01-24 06:26:24.430110: step: 644/526, loss: 0.004532577469944954
2023-01-24 06:26:25.514786: step: 648/526, loss: 0.04452493414282799
2023-01-24 06:26:26.593268: step: 652/526, loss: 0.025648871436715126
2023-01-24 06:26:27.667960: step: 656/526, loss: 0.004953925032168627
2023-01-24 06:26:28.747578: step: 660/526, loss: 0.007000575307756662
2023-01-24 06:26:29.818684: step: 664/526, loss: 0.0065264273434877396
2023-01-24 06:26:30.902713: step: 668/526, loss: 0.006868980824947357
2023-01-24 06:26:31.970551: step: 672/526, loss: 0.0071555995382368565
2023-01-24 06:26:33.041903: step: 676/526, loss: 0.00946854893118143
2023-01-24 06:26:34.134118: step: 680/526, loss: 0.01051437109708786
2023-01-24 06:26:35.205067: step: 684/526, loss: 0.004051868803799152
2023-01-24 06:26:36.290031: step: 688/526, loss: 0.010793021880090237
2023-01-24 06:26:37.365689: step: 692/526, loss: 0.0088266646489501
2023-01-24 06:26:38.429854: step: 696/526, loss: 0.005774748045951128
2023-01-24 06:26:39.501287: step: 700/526, loss: 0.018759895116090775
2023-01-24 06:26:40.574579: step: 704/526, loss: 0.010701971128582954
2023-01-24 06:26:41.649893: step: 708/526, loss: 0.005979751702398062
2023-01-24 06:26:42.744364: step: 712/526, loss: 0.007589823566377163
2023-01-24 06:26:43.826537: step: 716/526, loss: 0.08392458409070969
2023-01-24 06:26:44.904951: step: 720/526, loss: 0.0021874525118619204
2023-01-24 06:26:45.966521: step: 724/526, loss: 0.016090866178274155
2023-01-24 06:26:47.051031: step: 728/526, loss: 0.018652459606528282
2023-01-24 06:26:48.109974: step: 732/526, loss: 0.007374058477580547
2023-01-24 06:26:49.180711: step: 736/526, loss: 0.004847398493438959
2023-01-24 06:26:50.253149: step: 740/526, loss: 0.004190844018012285
2023-01-24 06:26:51.330881: step: 744/526, loss: 0.004264814779162407
2023-01-24 06:26:52.411843: step: 748/526, loss: 0.023278141394257545
2023-01-24 06:26:53.477527: step: 752/526, loss: 0.005648747552186251
2023-01-24 06:26:54.564680: step: 756/526, loss: 0.007402417249977589
2023-01-24 06:26:55.644278: step: 760/526, loss: 0.002384051214903593
2023-01-24 06:26:56.725648: step: 764/526, loss: 0.013636879622936249
2023-01-24 06:26:57.793106: step: 768/526, loss: 0.0011240590829402208
2023-01-24 06:26:58.913710: step: 772/526, loss: 0.007019934244453907
2023-01-24 06:27:00.002127: step: 776/526, loss: 0.014455851167440414
2023-01-24 06:27:01.076437: step: 780/526, loss: 0.014101763255894184
2023-01-24 06:27:02.149044: step: 784/526, loss: 0.005727006122469902
2023-01-24 06:27:03.221149: step: 788/526, loss: 0.011075682938098907
2023-01-24 06:27:04.296535: step: 792/526, loss: 0.0020008953288197517
2023-01-24 06:27:05.369774: step: 796/526, loss: 0.020557090640068054
2023-01-24 06:27:06.442096: step: 800/526, loss: 0.02410268783569336
2023-01-24 06:27:07.521009: step: 804/526, loss: 0.0063035693019628525
2023-01-24 06:27:08.580367: step: 808/526, loss: 0.004689145367592573
2023-01-24 06:27:09.658090: step: 812/526, loss: 0.01358272135257721
2023-01-24 06:27:10.745692: step: 816/526, loss: 0.003380807815119624
2023-01-24 06:27:11.838006: step: 820/526, loss: 0.011991090141236782
2023-01-24 06:27:12.916987: step: 824/526, loss: 0.0027609998360276222
2023-01-24 06:27:14.003038: step: 828/526, loss: 0.009906318038702011
2023-01-24 06:27:15.096275: step: 832/526, loss: 0.004464716650545597
2023-01-24 06:27:16.189099: step: 836/526, loss: 0.030358489602804184
2023-01-24 06:27:17.280182: step: 840/526, loss: 0.0034298240207135677
2023-01-24 06:27:18.371507: step: 844/526, loss: 0.0026594619266688824
2023-01-24 06:27:19.453441: step: 848/526, loss: 0.008309874683618546
2023-01-24 06:27:20.533866: step: 852/526, loss: 0.010560836642980576
2023-01-24 06:27:21.620189: step: 856/526, loss: 0.012410067953169346
2023-01-24 06:27:22.701338: step: 860/526, loss: 0.0041047558188438416
2023-01-24 06:27:23.778774: step: 864/526, loss: 0.0036047259345650673
2023-01-24 06:27:24.870312: step: 868/526, loss: 0.08083193004131317
2023-01-24 06:27:25.945145: step: 872/526, loss: 0.004556929226964712
2023-01-24 06:27:27.012193: step: 876/526, loss: 0.007955954410135746
2023-01-24 06:27:28.104175: step: 880/526, loss: 0.04868384078145027
2023-01-24 06:27:29.184642: step: 884/526, loss: 0.003371535800397396
2023-01-24 06:27:30.250360: step: 888/526, loss: 0.006219801492989063
2023-01-24 06:27:31.320182: step: 892/526, loss: 0.007122638635337353
2023-01-24 06:27:32.401212: step: 896/526, loss: 0.0032529502641409636
2023-01-24 06:27:33.477077: step: 900/526, loss: 0.02301887236535549
2023-01-24 06:27:34.551634: step: 904/526, loss: 0.0051975552923977375
2023-01-24 06:27:35.624119: step: 908/526, loss: 0.043318770825862885
2023-01-24 06:27:36.694959: step: 912/526, loss: 0.003209874499589205
2023-01-24 06:27:37.777299: step: 916/526, loss: 0.02868613414466381
2023-01-24 06:27:38.873522: step: 920/526, loss: 0.004495481960475445
2023-01-24 06:27:39.942020: step: 924/526, loss: 0.03996625542640686
2023-01-24 06:27:41.024917: step: 928/526, loss: 0.027455996721982956
2023-01-24 06:27:42.100936: step: 932/526, loss: 0.004166061989963055
2023-01-24 06:27:43.190550: step: 936/526, loss: 0.005743321031332016
2023-01-24 06:27:44.271296: step: 940/526, loss: 0.010885016992688179
2023-01-24 06:27:45.341550: step: 944/526, loss: 0.010835173539817333
2023-01-24 06:27:46.418846: step: 948/526, loss: 0.011836973018944263
2023-01-24 06:27:47.507029: step: 952/526, loss: 0.016941901296377182
2023-01-24 06:27:48.575437: step: 956/526, loss: 0.0031142006628215313
2023-01-24 06:27:49.659096: step: 960/526, loss: 0.010438790544867516
2023-01-24 06:27:50.744965: step: 964/526, loss: 0.01830361969769001
2023-01-24 06:27:51.840870: step: 968/526, loss: 0.008257209323346615
2023-01-24 06:27:52.920092: step: 972/526, loss: 0.005571051966398954
2023-01-24 06:27:54.015283: step: 976/526, loss: 0.005304281134158373
2023-01-24 06:27:55.113175: step: 980/526, loss: 0.01096657570451498
2023-01-24 06:27:56.219492: step: 984/526, loss: 0.027911212295293808
2023-01-24 06:27:57.301606: step: 988/526, loss: 0.011240304447710514
2023-01-24 06:27:58.382904: step: 992/526, loss: 0.06038908660411835
2023-01-24 06:27:59.454724: step: 996/526, loss: 0.01339729130268097
2023-01-24 06:28:00.538687: step: 1000/526, loss: 0.00668367138132453
2023-01-24 06:28:01.617308: step: 1004/526, loss: 0.018606390804052353
2023-01-24 06:28:02.680053: step: 1008/526, loss: 0.0033643865026533604
2023-01-24 06:28:03.751069: step: 1012/526, loss: 0.01883353292942047
2023-01-24 06:28:04.845740: step: 1016/526, loss: 0.006229817867279053
2023-01-24 06:28:05.927840: step: 1020/526, loss: 0.029786109924316406
2023-01-24 06:28:06.995385: step: 1024/526, loss: 0.0017382865771651268
2023-01-24 06:28:08.068928: step: 1028/526, loss: 0.013280978426337242
2023-01-24 06:28:09.150827: step: 1032/526, loss: 0.011007885448634624
2023-01-24 06:28:10.233703: step: 1036/526, loss: 0.0034824381582438946
2023-01-24 06:28:11.310798: step: 1040/526, loss: 0.005445824004709721
2023-01-24 06:28:12.400962: step: 1044/526, loss: 0.007069554645568132
2023-01-24 06:28:13.468925: step: 1048/526, loss: 0.0007817599689587951
2023-01-24 06:28:14.530021: step: 1052/526, loss: 0.08426336944103241
2023-01-24 06:28:15.607809: step: 1056/526, loss: 0.012588013894855976
2023-01-24 06:28:16.688450: step: 1060/526, loss: 0.00295455870218575
2023-01-24 06:28:17.763528: step: 1064/526, loss: 0.007516203913837671
2023-01-24 06:28:18.836209: step: 1068/526, loss: 0.02468854747712612
2023-01-24 06:28:19.904839: step: 1072/526, loss: 0.0390239879488945
2023-01-24 06:28:20.985802: step: 1076/526, loss: 0.0055543649941682816
2023-01-24 06:28:22.059759: step: 1080/526, loss: 0.030798103660345078
2023-01-24 06:28:23.126784: step: 1084/526, loss: 0.01350131630897522
2023-01-24 06:28:24.198893: step: 1088/526, loss: 0.009989018552005291
2023-01-24 06:28:25.267015: step: 1092/526, loss: 0.006031517405062914
2023-01-24 06:28:26.347027: step: 1096/526, loss: 0.034877825528383255
2023-01-24 06:28:27.421562: step: 1100/526, loss: 0.01338210143148899
2023-01-24 06:28:28.490471: step: 1104/526, loss: 0.011179731227457523
2023-01-24 06:28:29.567795: step: 1108/526, loss: 0.0026474054902791977
2023-01-24 06:28:30.639203: step: 1112/526, loss: 0.00873781368136406
2023-01-24 06:28:31.713950: step: 1116/526, loss: 0.0117159029468894
2023-01-24 06:28:32.783498: step: 1120/526, loss: 0.0076748887076973915
2023-01-24 06:28:33.856343: step: 1124/526, loss: 0.007969887927174568
2023-01-24 06:28:34.924452: step: 1128/526, loss: 0.004495459608733654
2023-01-24 06:28:35.989198: step: 1132/526, loss: 0.019307535141706467
2023-01-24 06:28:37.058473: step: 1136/526, loss: 0.0219793189316988
2023-01-24 06:28:38.135684: step: 1140/526, loss: 0.008263111114501953
2023-01-24 06:28:39.232867: step: 1144/526, loss: 0.015542508102953434
2023-01-24 06:28:40.310337: step: 1148/526, loss: 0.03168462589383125
2023-01-24 06:28:41.374493: step: 1152/526, loss: 0.0023571166675537825
2023-01-24 06:28:42.445091: step: 1156/526, loss: 0.05652833729982376
2023-01-24 06:28:43.501860: step: 1160/526, loss: 0.01070844754576683
2023-01-24 06:28:44.570479: step: 1164/526, loss: 0.0044338093139231205
2023-01-24 06:28:45.651333: step: 1168/526, loss: 0.003867821302264929
2023-01-24 06:28:46.720568: step: 1172/526, loss: 0.024858953431248665
2023-01-24 06:28:47.771428: step: 1176/526, loss: 0.01870400458574295
2023-01-24 06:28:48.855142: step: 1180/526, loss: 0.007217070087790489
2023-01-24 06:28:49.928835: step: 1184/526, loss: 0.00820702500641346
2023-01-24 06:28:51.011495: step: 1188/526, loss: 0.009867927059531212
2023-01-24 06:28:52.071913: step: 1192/526, loss: 0.04338536411523819
2023-01-24 06:28:53.135405: step: 1196/526, loss: 0.01646721176803112
2023-01-24 06:28:54.199683: step: 1200/526, loss: 0.030806325376033783
2023-01-24 06:28:55.267121: step: 1204/526, loss: 0.009647082537412643
2023-01-24 06:28:56.348899: step: 1208/526, loss: 0.025725239887833595
2023-01-24 06:28:57.412238: step: 1212/526, loss: 0.025477230548858643
2023-01-24 06:28:58.485203: step: 1216/526, loss: 0.011215124279260635
2023-01-24 06:28:59.553318: step: 1220/526, loss: 0.02604593336582184
2023-01-24 06:29:00.623358: step: 1224/526, loss: 0.047443535178899765
2023-01-24 06:29:01.684295: step: 1228/526, loss: 0.022466301918029785
2023-01-24 06:29:02.756549: step: 1232/526, loss: 0.005243474151939154
2023-01-24 06:29:03.824205: step: 1236/526, loss: 0.017764508724212646
2023-01-24 06:29:04.880290: step: 1240/526, loss: 0.0067218998447060585
2023-01-24 06:29:05.945126: step: 1244/526, loss: 0.03833760693669319
2023-01-24 06:29:07.027980: step: 1248/526, loss: 0.00447751535102725
2023-01-24 06:29:08.099473: step: 1252/526, loss: 0.006492044311016798
2023-01-24 06:29:09.167659: step: 1256/526, loss: 0.021420910954475403
2023-01-24 06:29:10.228633: step: 1260/526, loss: 0.011233736760914326
2023-01-24 06:29:11.286045: step: 1264/526, loss: 0.010537364520132542
2023-01-24 06:29:12.351201: step: 1268/526, loss: 0.01400777418166399
2023-01-24 06:29:13.414555: step: 1272/526, loss: 0.0026878828648477793
2023-01-24 06:29:14.473245: step: 1276/526, loss: 0.03409126028418541
2023-01-24 06:29:15.550129: step: 1280/526, loss: 0.012045320123434067
2023-01-24 06:29:16.614664: step: 1284/526, loss: 0.00646931491792202
2023-01-24 06:29:17.675552: step: 1288/526, loss: 0.0
2023-01-24 06:29:18.752149: step: 1292/526, loss: 0.035632483661174774
2023-01-24 06:29:19.810640: step: 1296/526, loss: 0.009531461633741856
2023-01-24 06:29:20.881775: step: 1300/526, loss: 0.008342907764017582
2023-01-24 06:29:21.938693: step: 1304/526, loss: 0.016757989302277565
2023-01-24 06:29:23.000034: step: 1308/526, loss: 0.003976346459239721
2023-01-24 06:29:24.059754: step: 1312/526, loss: 0.010344144888222218
2023-01-24 06:29:25.144640: step: 1316/526, loss: 0.005565538536757231
2023-01-24 06:29:26.203921: step: 1320/526, loss: 0.0057592978700995445
2023-01-24 06:29:27.270535: step: 1324/526, loss: 0.010162352584302425
2023-01-24 06:29:28.343907: step: 1328/526, loss: 0.0221356600522995
2023-01-24 06:29:29.423208: step: 1332/526, loss: 0.017170565202832222
2023-01-24 06:29:30.481326: step: 1336/526, loss: 0.00286900089122355
2023-01-24 06:29:31.557269: step: 1340/526, loss: 0.00820174254477024
2023-01-24 06:29:32.610014: step: 1344/526, loss: 0.014971645548939705
2023-01-24 06:29:33.709164: step: 1348/526, loss: 0.0065859099850058556
2023-01-24 06:29:34.787824: step: 1352/526, loss: 0.0292165819555521
2023-01-24 06:29:35.844779: step: 1356/526, loss: 0.022404586896300316
2023-01-24 06:29:36.923352: step: 1360/526, loss: 0.0029354114085435867
2023-01-24 06:29:37.989665: step: 1364/526, loss: 0.012884167023003101
2023-01-24 06:29:39.047567: step: 1368/526, loss: 0.0014245564816519618
2023-01-24 06:29:40.127598: step: 1372/526, loss: 0.026715008541941643
2023-01-24 06:29:41.185024: step: 1376/526, loss: 0.04357811436057091
2023-01-24 06:29:42.249687: step: 1380/526, loss: 0.004910048563033342
2023-01-24 06:29:43.314294: step: 1384/526, loss: 0.011042262427508831
2023-01-24 06:29:44.384118: step: 1388/526, loss: 0.0014828643761575222
2023-01-24 06:29:45.448441: step: 1392/526, loss: 0.018773356452584267
2023-01-24 06:29:46.511589: step: 1396/526, loss: 0.011864673346281052
2023-01-24 06:29:47.567064: step: 1400/526, loss: 0.00803462602198124
2023-01-24 06:29:48.616042: step: 1404/526, loss: 0.002856550505384803
2023-01-24 06:29:49.686085: step: 1408/526, loss: 0.0033457232639193535
2023-01-24 06:29:50.753981: step: 1412/526, loss: 0.01171930506825447
2023-01-24 06:29:51.808123: step: 1416/526, loss: 0.020162900909781456
2023-01-24 06:29:52.877701: step: 1420/526, loss: 0.01573345437645912
2023-01-24 06:29:53.951138: step: 1424/526, loss: 0.008854788728058338
2023-01-24 06:29:55.004959: step: 1428/526, loss: 0.006366438698023558
2023-01-24 06:29:56.068533: step: 1432/526, loss: 0.04270756617188454
2023-01-24 06:29:57.130178: step: 1436/526, loss: 0.02801160328090191
2023-01-24 06:29:58.182385: step: 1440/526, loss: 0.00948960892856121
2023-01-24 06:29:59.247697: step: 1444/526, loss: 0.009206300601363182
2023-01-24 06:30:00.319769: step: 1448/526, loss: 0.009319613687694073
2023-01-24 06:30:01.395988: step: 1452/526, loss: 0.008261908777058125
2023-01-24 06:30:02.451448: step: 1456/526, loss: 0.004989591892808676
2023-01-24 06:30:03.512537: step: 1460/526, loss: 0.03424499183893204
2023-01-24 06:30:04.572086: step: 1464/526, loss: 0.006096519995480776
2023-01-24 06:30:05.642138: step: 1468/526, loss: 0.010850897990167141
2023-01-24 06:30:06.703276: step: 1472/526, loss: 0.010049943812191486
2023-01-24 06:30:07.773690: step: 1476/526, loss: 0.004420015029609203
2023-01-24 06:30:08.854575: step: 1480/526, loss: 0.007550597190856934
2023-01-24 06:30:09.922790: step: 1484/526, loss: 0.0037027643993496895
2023-01-24 06:30:11.008534: step: 1488/526, loss: 0.02450309507548809
2023-01-24 06:30:12.074659: step: 1492/526, loss: 0.004156967159360647
2023-01-24 06:30:13.148502: step: 1496/526, loss: 0.0030682943761348724
2023-01-24 06:30:14.231004: step: 1500/526, loss: 0.006102921906858683
2023-01-24 06:30:15.291144: step: 1504/526, loss: 0.004751682281494141
2023-01-24 06:30:16.342777: step: 1508/526, loss: 0.002415277063846588
2023-01-24 06:30:17.408476: step: 1512/526, loss: 0.016951916739344597
2023-01-24 06:30:18.482808: step: 1516/526, loss: 0.012345204129815102
2023-01-24 06:30:19.554120: step: 1520/526, loss: 0.018035629764199257
2023-01-24 06:30:20.610394: step: 1524/526, loss: 0.007199098821729422
2023-01-24 06:30:21.669889: step: 1528/526, loss: 0.04139915481209755
2023-01-24 06:30:22.751975: step: 1532/526, loss: 0.005168642848730087
2023-01-24 06:30:23.811555: step: 1536/526, loss: 0.010584330186247826
2023-01-24 06:30:24.898444: step: 1540/526, loss: 0.006846735253930092
2023-01-24 06:30:25.971577: step: 1544/526, loss: 0.026852548122406006
2023-01-24 06:30:27.043516: step: 1548/526, loss: 0.002502594143152237
2023-01-24 06:30:28.121611: step: 1552/526, loss: 0.035872578620910645
2023-01-24 06:30:29.182542: step: 1556/526, loss: 0.005310544278472662
2023-01-24 06:30:30.241221: step: 1560/526, loss: 0.017590191215276718
2023-01-24 06:30:31.309189: step: 1564/526, loss: 0.0029978761449456215
2023-01-24 06:30:32.367972: step: 1568/526, loss: 0.01053419429808855
2023-01-24 06:30:33.431952: step: 1572/526, loss: 0.0053388746455311775
2023-01-24 06:30:34.495431: step: 1576/526, loss: 0.010215004906058311
2023-01-24 06:30:35.562881: step: 1580/526, loss: 0.023346543312072754
2023-01-24 06:30:36.622646: step: 1584/526, loss: 0.003912911284714937
2023-01-24 06:30:37.689585: step: 1588/526, loss: 0.00445833895355463
2023-01-24 06:30:38.760682: step: 1592/526, loss: 0.004861005581915379
2023-01-24 06:30:39.822863: step: 1596/526, loss: 0.00711582787334919
2023-01-24 06:30:40.900423: step: 1600/526, loss: 0.017639338970184326
2023-01-24 06:30:41.993151: step: 1604/526, loss: 0.004676608834415674
2023-01-24 06:30:43.074013: step: 1608/526, loss: 0.09627410024404526
2023-01-24 06:30:44.157425: step: 1612/526, loss: 0.007182906847447157
2023-01-24 06:30:45.233453: step: 1616/526, loss: 0.009184567257761955
2023-01-24 06:30:46.296781: step: 1620/526, loss: 0.0014865609118714929
2023-01-24 06:30:47.360630: step: 1624/526, loss: 0.005441845860332251
2023-01-24 06:30:48.409142: step: 1628/526, loss: 0.005753014702349901
2023-01-24 06:30:49.482809: step: 1632/526, loss: 0.005112130660563707
2023-01-24 06:30:50.567624: step: 1636/526, loss: 0.007921729236841202
2023-01-24 06:30:51.638281: step: 1640/526, loss: 0.0006049563526175916
2023-01-24 06:30:52.711034: step: 1644/526, loss: 0.021332260221242905
2023-01-24 06:30:53.780964: step: 1648/526, loss: 0.010541192255914211
2023-01-24 06:30:54.861297: step: 1652/526, loss: 0.002833027159795165
2023-01-24 06:30:55.923308: step: 1656/526, loss: 0.008171668276190758
2023-01-24 06:30:56.985637: step: 1660/526, loss: 0.027608271688222885
2023-01-24 06:30:58.044914: step: 1664/526, loss: 0.0032521956600248814
2023-01-24 06:30:59.094104: step: 1668/526, loss: 0.0023409565910696983
2023-01-24 06:31:00.169098: step: 1672/526, loss: 0.006066160276532173
2023-01-24 06:31:01.250419: step: 1676/526, loss: 0.023671183735132217
2023-01-24 06:31:02.316216: step: 1680/526, loss: 0.04049052298069
2023-01-24 06:31:03.379384: step: 1684/526, loss: 0.03451811522245407
2023-01-24 06:31:04.447231: step: 1688/526, loss: 0.02045125514268875
2023-01-24 06:31:05.506387: step: 1692/526, loss: 0.0036604974884539843
2023-01-24 06:31:06.577229: step: 1696/526, loss: 0.018069837242364883
2023-01-24 06:31:07.639859: step: 1700/526, loss: 0.03992658108472824
2023-01-24 06:31:08.725794: step: 1704/526, loss: 0.03465672582387924
2023-01-24 06:31:09.802045: step: 1708/526, loss: 0.018688617274165154
2023-01-24 06:31:10.882675: step: 1712/526, loss: 0.026766885071992874
2023-01-24 06:31:11.939352: step: 1716/526, loss: 0.02549033984541893
2023-01-24 06:31:12.993532: step: 1720/526, loss: 0.007111749611794949
2023-01-24 06:31:14.051096: step: 1724/526, loss: 0.014270732179284096
2023-01-24 06:31:15.122126: step: 1728/526, loss: 0.0008265099604614079
2023-01-24 06:31:16.172396: step: 1732/526, loss: 0.023535097017884254
2023-01-24 06:31:17.219307: step: 1736/526, loss: 0.012633095495402813
2023-01-24 06:31:18.282744: step: 1740/526, loss: 0.01793331652879715
2023-01-24 06:31:19.344881: step: 1744/526, loss: 0.00403120880946517
2023-01-24 06:31:20.402704: step: 1748/526, loss: 0.0001715904800221324
2023-01-24 06:31:21.476631: step: 1752/526, loss: 0.0037404517643153667
2023-01-24 06:31:22.528123: step: 1756/526, loss: 0.008556806482374668
2023-01-24 06:31:23.581932: step: 1760/526, loss: 0.07043598592281342
2023-01-24 06:31:24.658789: step: 1764/526, loss: 0.006439608987420797
2023-01-24 06:31:25.713716: step: 1768/526, loss: 0.02019934169948101
2023-01-24 06:31:26.767077: step: 1772/526, loss: 0.007826108485460281
2023-01-24 06:31:27.825062: step: 1776/526, loss: 0.01723911426961422
2023-01-24 06:31:28.902721: step: 1780/526, loss: 0.022307654842734337
2023-01-24 06:31:30.008949: step: 1784/526, loss: 0.010500245727598667
2023-01-24 06:31:31.072328: step: 1788/526, loss: 0.04364487901329994
2023-01-24 06:31:32.136701: step: 1792/526, loss: 0.0074179829098284245
2023-01-24 06:31:33.202325: step: 1796/526, loss: 0.010694097727537155
2023-01-24 06:31:34.275475: step: 1800/526, loss: 0.005141766741871834
2023-01-24 06:31:35.349696: step: 1804/526, loss: 0.023395854979753494
2023-01-24 06:31:36.419503: step: 1808/526, loss: 0.009554535150527954
2023-01-24 06:31:37.488281: step: 1812/526, loss: 0.006269097328186035
2023-01-24 06:31:38.572181: step: 1816/526, loss: 0.004594143014401197
2023-01-24 06:31:39.640033: step: 1820/526, loss: 0.02031327784061432
2023-01-24 06:31:40.717686: step: 1824/526, loss: 0.0019776553381234407
2023-01-24 06:31:41.793301: step: 1828/526, loss: 0.002862253226339817
2023-01-24 06:31:42.902671: step: 1832/526, loss: 0.010650093667209148
2023-01-24 06:31:43.966559: step: 1836/526, loss: 0.04844445735216141
2023-01-24 06:31:45.033010: step: 1840/526, loss: 0.02523704245686531
2023-01-24 06:31:46.105751: step: 1844/526, loss: 0.019803304225206375
2023-01-24 06:31:47.179453: step: 1848/526, loss: 0.04520859941840172
2023-01-24 06:31:48.251498: step: 1852/526, loss: 0.004723967052996159
2023-01-24 06:31:49.310550: step: 1856/526, loss: 0.01091139018535614
2023-01-24 06:31:50.385025: step: 1860/526, loss: 0.011228218674659729
2023-01-24 06:31:51.464846: step: 1864/526, loss: 0.007062103133648634
2023-01-24 06:31:52.525229: step: 1868/526, loss: 0.008993699215352535
2023-01-24 06:31:53.587605: step: 1872/526, loss: 0.013751370832324028
2023-01-24 06:31:54.655258: step: 1876/526, loss: 0.008922052569687366
2023-01-24 06:31:55.736313: step: 1880/526, loss: 0.0034748322796076536
2023-01-24 06:31:56.804042: step: 1884/526, loss: 0.013804436661303043
2023-01-24 06:31:57.869993: step: 1888/526, loss: 0.0052545093931257725
2023-01-24 06:31:58.941474: step: 1892/526, loss: 0.005114257801324129
2023-01-24 06:32:00.047586: step: 1896/526, loss: 0.006395290605723858
2023-01-24 06:32:01.111456: step: 1900/526, loss: 0.005421869922429323
2023-01-24 06:32:02.178603: step: 1904/526, loss: 0.0018781094113364816
2023-01-24 06:32:03.236309: step: 1908/526, loss: 0.011902541853487492
2023-01-24 06:32:04.294320: step: 1912/526, loss: 0.010770831257104874
2023-01-24 06:32:05.350796: step: 1916/526, loss: 0.02877545729279518
2023-01-24 06:32:06.426842: step: 1920/526, loss: 0.0035146879963576794
2023-01-24 06:32:07.478994: step: 1924/526, loss: 0.03203630819916725
2023-01-24 06:32:08.536248: step: 1928/526, loss: 0.0071519771590828896
2023-01-24 06:32:09.598220: step: 1932/526, loss: 0.005815187469124794
2023-01-24 06:32:10.681954: step: 1936/526, loss: 0.003906155237928033
2023-01-24 06:32:11.737570: step: 1940/526, loss: 0.0051356470212340355
2023-01-24 06:32:12.798292: step: 1944/526, loss: 0.005927410442382097
2023-01-24 06:32:13.909124: step: 1948/526, loss: 0.010274640284478664
2023-01-24 06:32:14.968788: step: 1952/526, loss: 0.0034792316146194935
2023-01-24 06:32:16.026357: step: 1956/526, loss: 0.0031065037474036217
2023-01-24 06:32:17.089370: step: 1960/526, loss: 0.03285900503396988
2023-01-24 06:32:18.158701: step: 1964/526, loss: 0.0037486539222300053
2023-01-24 06:32:19.221125: step: 1968/526, loss: 0.013327890075743198
2023-01-24 06:32:20.288832: step: 1972/526, loss: 0.003992380574345589
2023-01-24 06:32:21.356243: step: 1976/526, loss: 0.002244959818199277
2023-01-24 06:32:22.429375: step: 1980/526, loss: 0.07178151607513428
2023-01-24 06:32:23.515446: step: 1984/526, loss: 0.050462786108255386
2023-01-24 06:32:24.574049: step: 1988/526, loss: 0.007395831402391195
2023-01-24 06:32:25.650515: step: 1992/526, loss: 0.00534437969326973
2023-01-24 06:32:26.706469: step: 1996/526, loss: 0.011167893186211586
2023-01-24 06:32:27.774713: step: 2000/526, loss: 0.004772778134793043
2023-01-24 06:32:28.830875: step: 2004/526, loss: 0.006650469731539488
2023-01-24 06:32:29.895236: step: 2008/526, loss: 0.010275108739733696
2023-01-24 06:32:30.982993: step: 2012/526, loss: 0.010766251012682915
2023-01-24 06:32:32.050402: step: 2016/526, loss: 0.0193684883415699
2023-01-24 06:32:33.120145: step: 2020/526, loss: 0.008803722448647022
2023-01-24 06:32:34.193682: step: 2024/526, loss: 0.002253290032967925
2023-01-24 06:32:35.260328: step: 2028/526, loss: 0.010889406315982342
2023-01-24 06:32:36.319879: step: 2032/526, loss: 0.003997150808572769
2023-01-24 06:32:37.384560: step: 2036/526, loss: 0.006157516036182642
2023-01-24 06:32:38.451695: step: 2040/526, loss: 0.06259596347808838
2023-01-24 06:32:39.530369: step: 2044/526, loss: 0.0840030312538147
2023-01-24 06:32:40.608335: step: 2048/526, loss: 0.035455912351608276
2023-01-24 06:32:41.689895: step: 2052/526, loss: 0.02177589014172554
2023-01-24 06:32:42.760707: step: 2056/526, loss: 0.007078463677316904
2023-01-24 06:32:43.831564: step: 2060/526, loss: 0.007366360165178776
2023-01-24 06:32:44.917415: step: 2064/526, loss: 0.01395875308662653
2023-01-24 06:32:45.987232: step: 2068/526, loss: 0.013152029365301132
2023-01-24 06:32:47.082358: step: 2072/526, loss: 0.002955480944365263
2023-01-24 06:32:48.144828: step: 2076/526, loss: 0.0292070172727108
2023-01-24 06:32:49.228839: step: 2080/526, loss: 0.011541560292243958
2023-01-24 06:32:50.306988: step: 2084/526, loss: 0.010321681387722492
2023-01-24 06:32:51.393601: step: 2088/526, loss: 0.015211386606097221
2023-01-24 06:32:52.472132: step: 2092/526, loss: 0.004252570681273937
2023-01-24 06:32:53.532628: step: 2096/526, loss: 0.003494285512715578
2023-01-24 06:32:54.588171: step: 2100/526, loss: 0.030963025987148285
2023-01-24 06:32:55.651353: step: 2104/526, loss: 0.007188418880105019
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3568270905923345, 'r': 0.27760741393331523, 'f1': 0.31227130660161606}, 'combined': 0.23009464696961182, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3522047585082535, 'r': 0.22588795582276824, 'f1': 0.2752458592132505}, 'combined': 0.15013410502540936, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.331924855929633, 'r': 0.2966539034968826, 'f1': 0.3132998139135414}, 'combined': 0.23085249446260944, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35586985170070695, 'r': 0.2656814263383137, 'f1': 0.3042323719096667}, 'combined': 0.16594493013254544, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3489950933384478, 'r': 0.31389691507101375, 'f1': 0.3305168316531953}, 'combined': 0.24353871806024915, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3552698281535947, 'r': 0.2772599848261814, 'f1': 0.3114544331089582}, 'combined': 0.16988423624124993, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.42045454545454547, 'r': 0.40217391304347827, 'f1': 0.41111111111111115}, 'combined': 0.20555555555555557, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 2}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336995843596059, 'r': 0.29380760368663594, 'f1': 0.31248558454663394}, 'combined': 0.23025253598173026, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597710279387254, 'r': 0.2590483064846998, 'f1': 0.30121255211465625}, 'combined': 0.1642977556989034, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3597402018039063, 'r': 0.3187830630786039, 'f1': 0.3380255014938114}, 'combined': 0.2490714221533347, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3626348362380441, 'r': 0.2743815275103957, 'f1': 0.3123948016342317}, 'combined': 0.17039716452776274, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:35:43.601599: step: 4/526, loss: 0.01453336887061596
2023-01-24 06:35:44.659680: step: 8/526, loss: 0.00482061505317688
2023-01-24 06:35:45.706257: step: 12/526, loss: 0.019346054643392563
2023-01-24 06:35:46.772537: step: 16/526, loss: 0.0028248419985175133
2023-01-24 06:35:47.824457: step: 20/526, loss: 0.001616541645489633
2023-01-24 06:35:48.932251: step: 24/526, loss: 0.018345719203352928
2023-01-24 06:35:49.990027: step: 28/526, loss: 0.002214467851445079
2023-01-24 06:35:51.045762: step: 32/526, loss: 0.006031076889485121
2023-01-24 06:35:52.110413: step: 36/526, loss: 0.021169841289520264
2023-01-24 06:35:53.172809: step: 40/526, loss: 0.014332202263176441
2023-01-24 06:35:54.237139: step: 44/526, loss: 0.01166242454200983
2023-01-24 06:35:55.304809: step: 48/526, loss: 0.007443530485033989
2023-01-24 06:35:56.376002: step: 52/526, loss: 0.006939054466784
2023-01-24 06:35:57.427119: step: 56/526, loss: 0.00618600333109498
2023-01-24 06:35:58.493399: step: 60/526, loss: 0.049402832984924316
2023-01-24 06:35:59.545029: step: 64/526, loss: 0.003533771028742194
2023-01-24 06:36:00.622897: step: 68/526, loss: 0.006433280650526285
2023-01-24 06:36:01.699236: step: 72/526, loss: 0.015450327657163143
2023-01-24 06:36:02.776236: step: 76/526, loss: 0.013647615909576416
2023-01-24 06:36:03.874149: step: 80/526, loss: 0.01516517624258995
2023-01-24 06:36:04.947474: step: 84/526, loss: 0.009910054504871368
2023-01-24 06:36:06.005367: step: 88/526, loss: 0.0041787223890423775
2023-01-24 06:36:07.062479: step: 92/526, loss: 0.007803673390299082
2023-01-24 06:36:08.135582: step: 96/526, loss: 0.004188187420368195
2023-01-24 06:36:09.207565: step: 100/526, loss: 0.03430202230811119
2023-01-24 06:36:10.283613: step: 104/526, loss: 0.01833048276603222
2023-01-24 06:36:11.360824: step: 108/526, loss: 0.008701053448021412
2023-01-24 06:36:12.440771: step: 112/526, loss: 0.005170323420315981
2023-01-24 06:36:13.502769: step: 116/526, loss: 0.0031774239614605904
2023-01-24 06:36:14.577970: step: 120/526, loss: 0.014394068159162998
2023-01-24 06:36:15.659342: step: 124/526, loss: 0.007874553091824055
2023-01-24 06:36:16.726992: step: 128/526, loss: 0.05461150407791138
2023-01-24 06:36:17.784150: step: 132/526, loss: 0.006642511114478111
2023-01-24 06:36:18.862605: step: 136/526, loss: 0.013262495398521423
2023-01-24 06:36:19.932718: step: 140/526, loss: 0.008064507506787777
2023-01-24 06:36:21.009142: step: 144/526, loss: 0.007895958609879017
2023-01-24 06:36:22.090649: step: 148/526, loss: 6.85572813381441e-05
2023-01-24 06:36:23.149550: step: 152/526, loss: 0.0062192995101213455
2023-01-24 06:36:24.240460: step: 156/526, loss: 0.048363275825977325
2023-01-24 06:36:25.297689: step: 160/526, loss: 0.001769882976077497
2023-01-24 06:36:26.379974: step: 164/526, loss: 0.004625684581696987
2023-01-24 06:36:27.445144: step: 168/526, loss: 0.02058299072086811
2023-01-24 06:36:28.529533: step: 172/526, loss: 0.009122991003096104
2023-01-24 06:36:29.596070: step: 176/526, loss: 0.001211250782944262
2023-01-24 06:36:30.666049: step: 180/526, loss: 0.009969021193683147
2023-01-24 06:36:31.747028: step: 184/526, loss: 0.00723232189193368
2023-01-24 06:36:32.805344: step: 188/526, loss: 0.008864911273121834
2023-01-24 06:36:33.900700: step: 192/526, loss: 0.007698389235883951
2023-01-24 06:36:35.000711: step: 196/526, loss: 0.011442573741078377
2023-01-24 06:36:36.085625: step: 200/526, loss: 0.020363764837384224
2023-01-24 06:36:37.149037: step: 204/526, loss: 0.004419893492013216
2023-01-24 06:36:38.214360: step: 208/526, loss: 0.022030601277947426
2023-01-24 06:36:39.289569: step: 212/526, loss: 0.006434077396988869
2023-01-24 06:36:40.379292: step: 216/526, loss: 0.016334280371665955
2023-01-24 06:36:41.490499: step: 220/526, loss: 0.015567542053759098
2023-01-24 06:36:42.553801: step: 224/526, loss: 0.028035342693328857
2023-01-24 06:36:43.656693: step: 228/526, loss: 0.006301909685134888
2023-01-24 06:36:44.729360: step: 232/526, loss: 0.023465782403945923
2023-01-24 06:36:45.792847: step: 236/526, loss: 0.004896972328424454
2023-01-24 06:36:46.867021: step: 240/526, loss: 0.0032686295453459024
2023-01-24 06:36:47.940300: step: 244/526, loss: 0.0016423244960606098
2023-01-24 06:36:49.012280: step: 248/526, loss: 0.005847712513059378
2023-01-24 06:36:50.111282: step: 252/526, loss: 0.017023583874106407
2023-01-24 06:36:51.228646: step: 256/526, loss: 0.02328610047698021
2023-01-24 06:36:52.305198: step: 260/526, loss: 0.006989973597228527
2023-01-24 06:36:53.375313: step: 264/526, loss: 0.02049330808222294
2023-01-24 06:36:54.437733: step: 268/526, loss: 0.01033694576472044
2023-01-24 06:36:55.514706: step: 272/526, loss: 0.003345879027619958
2023-01-24 06:36:56.613597: step: 276/526, loss: 0.027556832879781723
2023-01-24 06:36:57.685597: step: 280/526, loss: 0.0013843950582668185
2023-01-24 06:36:58.758745: step: 284/526, loss: 0.00024239910999312997
2023-01-24 06:36:59.824806: step: 288/526, loss: 0.0097554512321949
2023-01-24 06:37:00.903430: step: 292/526, loss: 0.01125571969896555
2023-01-24 06:37:01.957612: step: 296/526, loss: 0.007423019502311945
2023-01-24 06:37:03.034119: step: 300/526, loss: 0.00855428259819746
2023-01-24 06:37:04.125953: step: 304/526, loss: 0.0006459562573581934
2023-01-24 06:37:05.214783: step: 308/526, loss: 0.028279097750782967
2023-01-24 06:37:06.306952: step: 312/526, loss: 0.01437902171164751
2023-01-24 06:37:07.387712: step: 316/526, loss: 0.02789865992963314
2023-01-24 06:37:08.463228: step: 320/526, loss: 0.01503366231918335
2023-01-24 06:37:09.545865: step: 324/526, loss: 0.002005531219765544
2023-01-24 06:37:10.625660: step: 328/526, loss: 0.0030598067678511143
2023-01-24 06:37:11.699909: step: 332/526, loss: 0.018018824979662895
2023-01-24 06:37:12.773814: step: 336/526, loss: 0.006739713251590729
2023-01-24 06:37:13.846852: step: 340/526, loss: 0.024852771311998367
2023-01-24 06:37:14.919903: step: 344/526, loss: 0.004392530769109726
2023-01-24 06:37:15.992594: step: 348/526, loss: 0.017079133540391922
2023-01-24 06:37:17.081960: step: 352/526, loss: 0.013240063562989235
2023-01-24 06:37:18.158176: step: 356/526, loss: 0.006750912871211767
2023-01-24 06:37:19.237379: step: 360/526, loss: 0.0078098042868077755
2023-01-24 06:37:20.306662: step: 364/526, loss: 0.012694346718490124
2023-01-24 06:37:21.399893: step: 368/526, loss: 0.006354122888296843
2023-01-24 06:37:22.468997: step: 372/526, loss: 0.0067864893935620785
2023-01-24 06:37:23.536872: step: 376/526, loss: 0.0327744223177433
2023-01-24 06:37:24.591610: step: 380/526, loss: 0.016337445005774498
2023-01-24 06:37:25.675067: step: 384/526, loss: 0.0034072063863277435
2023-01-24 06:37:26.745221: step: 388/526, loss: 0.00803084671497345
2023-01-24 06:37:27.824940: step: 392/526, loss: 0.050930123776197433
2023-01-24 06:37:28.902322: step: 396/526, loss: 0.009968280792236328
2023-01-24 06:37:29.975857: step: 400/526, loss: 0.008098617196083069
2023-01-24 06:37:31.051141: step: 404/526, loss: 0.004890930373221636
2023-01-24 06:37:32.112059: step: 408/526, loss: 0.006930863484740257
2023-01-24 06:37:33.189399: step: 412/526, loss: 0.012169006280601025
2023-01-24 06:37:34.272838: step: 416/526, loss: 0.04285794496536255
2023-01-24 06:37:35.335624: step: 420/526, loss: 0.003666388802230358
2023-01-24 06:37:36.417240: step: 424/526, loss: 0.012774799950420856
2023-01-24 06:37:37.509900: step: 428/526, loss: 0.007495295722037554
2023-01-24 06:37:38.578029: step: 432/526, loss: 0.014199631288647652
2023-01-24 06:37:39.634343: step: 436/526, loss: 0.009778316132724285
2023-01-24 06:37:40.685110: step: 440/526, loss: 0.060826994478702545
2023-01-24 06:37:41.758530: step: 444/526, loss: 0.004873138852417469
2023-01-24 06:37:42.837019: step: 448/526, loss: 0.013729703612625599
2023-01-24 06:37:43.902107: step: 452/526, loss: 0.05647847056388855
2023-01-24 06:37:44.977782: step: 456/526, loss: 0.009778296574950218
2023-01-24 06:37:46.042978: step: 460/526, loss: 0.006020212080329657
2023-01-24 06:37:47.121614: step: 464/526, loss: 0.012150839902460575
2023-01-24 06:37:48.188170: step: 468/526, loss: 0.006403443403542042
2023-01-24 06:37:49.261641: step: 472/526, loss: 0.02598799578845501
2023-01-24 06:37:50.335112: step: 476/526, loss: 0.004478775896131992
2023-01-24 06:37:51.411944: step: 480/526, loss: 0.022910412400960922
2023-01-24 06:37:52.466312: step: 484/526, loss: 0.02777860499918461
2023-01-24 06:37:53.534453: step: 488/526, loss: 0.037520118057727814
2023-01-24 06:37:54.606914: step: 492/526, loss: 0.002860916079953313
2023-01-24 06:37:55.675950: step: 496/526, loss: 0.0039716255851089954
2023-01-24 06:37:56.755796: step: 500/526, loss: 0.03581337258219719
2023-01-24 06:37:57.822335: step: 504/526, loss: 0.0014725279761478305
2023-01-24 06:37:58.896400: step: 508/526, loss: 0.005930229555815458
2023-01-24 06:37:59.957477: step: 512/526, loss: 0.0031955912709236145
2023-01-24 06:38:01.018761: step: 516/526, loss: 0.006874459329992533
2023-01-24 06:38:02.111381: step: 520/526, loss: 0.008637451566755772
2023-01-24 06:38:03.177113: step: 524/526, loss: 0.03221502527594566
2023-01-24 06:38:04.240142: step: 528/526, loss: 0.01700977422297001
2023-01-24 06:38:05.323337: step: 532/526, loss: 0.007120462600141764
2023-01-24 06:38:06.368743: step: 536/526, loss: 0.005697491113096476
2023-01-24 06:38:07.436399: step: 540/526, loss: 0.013995268382132053
2023-01-24 06:38:08.499875: step: 544/526, loss: 0.043236516416072845
2023-01-24 06:38:09.562091: step: 548/526, loss: 0.0010032171849161386
2023-01-24 06:38:10.638156: step: 552/526, loss: 0.003636823734268546
2023-01-24 06:38:11.692434: step: 556/526, loss: 0.003714676247909665
2023-01-24 06:38:12.758315: step: 560/526, loss: 0.06154327467083931
2023-01-24 06:38:13.823972: step: 564/526, loss: 0.0006883384194225073
2023-01-24 06:38:14.887909: step: 568/526, loss: 0.016375605016946793
2023-01-24 06:38:15.956816: step: 572/526, loss: 0.006623808294534683
2023-01-24 06:38:17.016884: step: 576/526, loss: 0.0106643782928586
2023-01-24 06:38:18.076012: step: 580/526, loss: 0.011396318674087524
2023-01-24 06:38:19.141401: step: 584/526, loss: 0.044407010078430176
2023-01-24 06:38:20.201403: step: 588/526, loss: 0.05138601362705231
2023-01-24 06:38:21.259179: step: 592/526, loss: 0.013208644464612007
2023-01-24 06:38:22.318135: step: 596/526, loss: 0.009223378263413906
2023-01-24 06:38:23.399836: step: 600/526, loss: 0.003958255518227816
2023-01-24 06:38:24.465322: step: 604/526, loss: 0.020762505009770393
2023-01-24 06:38:25.519343: step: 608/526, loss: 0.02664206735789776
2023-01-24 06:38:26.583882: step: 612/526, loss: 0.01851213350892067
2023-01-24 06:38:27.655807: step: 616/526, loss: 0.01115064974874258
2023-01-24 06:38:28.725013: step: 620/526, loss: 0.009437215514481068
2023-01-24 06:38:29.792437: step: 624/526, loss: 0.015818025916814804
2023-01-24 06:38:30.856416: step: 628/526, loss: 0.022757917642593384
2023-01-24 06:38:31.923222: step: 632/526, loss: 0.004255269188433886
2023-01-24 06:38:32.989334: step: 636/526, loss: 0.007974151521921158
2023-01-24 06:38:34.063355: step: 640/526, loss: 0.03277970105409622
2023-01-24 06:38:35.135185: step: 644/526, loss: 0.00660000741481781
2023-01-24 06:38:36.181876: step: 648/526, loss: 0.00025135863688774407
2023-01-24 06:38:37.242634: step: 652/526, loss: 0.014811350964009762
2023-01-24 06:38:38.319517: step: 656/526, loss: 0.009015078656375408
2023-01-24 06:38:39.388917: step: 660/526, loss: 0.008203686214983463
2023-01-24 06:38:40.462007: step: 664/526, loss: 0.0030238081235438585
2023-01-24 06:38:41.523607: step: 668/526, loss: 0.027519404888153076
2023-01-24 06:38:42.594880: step: 672/526, loss: 0.009931741282343864
2023-01-24 06:38:43.660114: step: 676/526, loss: 0.00881365966051817
2023-01-24 06:38:44.725916: step: 680/526, loss: 0.0015198359033092856
2023-01-24 06:38:45.778187: step: 684/526, loss: 0.03769846633076668
2023-01-24 06:38:46.836179: step: 688/526, loss: 0.0
2023-01-24 06:38:47.894665: step: 692/526, loss: 0.01602693274617195
2023-01-24 06:38:48.963638: step: 696/526, loss: 0.01890532486140728
2023-01-24 06:38:50.027747: step: 700/526, loss: 0.05904241278767586
2023-01-24 06:38:51.086153: step: 704/526, loss: 0.0017161288997158408
2023-01-24 06:38:52.150183: step: 708/526, loss: 0.004789257887750864
2023-01-24 06:38:53.227676: step: 712/526, loss: 0.003328604158014059
2023-01-24 06:38:54.295039: step: 716/526, loss: 0.008297652006149292
2023-01-24 06:38:55.371445: step: 720/526, loss: 0.0026028358843177557
2023-01-24 06:38:56.446209: step: 724/526, loss: 0.01887928880751133
2023-01-24 06:38:57.532804: step: 728/526, loss: 0.0021802117116749287
2023-01-24 06:38:58.595740: step: 732/526, loss: 0.006900761742144823
2023-01-24 06:38:59.654048: step: 736/526, loss: 0.017902949824929237
2023-01-24 06:39:00.720194: step: 740/526, loss: 0.007469620555639267
2023-01-24 06:39:01.798692: step: 744/526, loss: 0.007927126251161098
2023-01-24 06:39:02.861709: step: 748/526, loss: 0.004104436840862036
2023-01-24 06:39:03.937260: step: 752/526, loss: 0.007140577770769596
2023-01-24 06:39:05.011690: step: 756/526, loss: 0.0020137031096965075
2023-01-24 06:39:06.085249: step: 760/526, loss: 0.022616535425186157
2023-01-24 06:39:07.159201: step: 764/526, loss: 0.01716579683125019
2023-01-24 06:39:08.241826: step: 768/526, loss: 0.006678692996501923
2023-01-24 06:39:09.309297: step: 772/526, loss: 0.010869510471820831
2023-01-24 06:39:10.368443: step: 776/526, loss: 0.002949516987428069
2023-01-24 06:39:11.423037: step: 780/526, loss: 0.006804764270782471
2023-01-24 06:39:12.493411: step: 784/526, loss: 0.0047178310342133045
2023-01-24 06:39:13.563261: step: 788/526, loss: 0.002043781103566289
2023-01-24 06:39:14.627804: step: 792/526, loss: 0.005039089825004339
2023-01-24 06:39:15.682601: step: 796/526, loss: 0.019487515091896057
2023-01-24 06:39:16.741027: step: 800/526, loss: 0.006454563234001398
2023-01-24 06:39:17.835010: step: 804/526, loss: 0.008772947825491428
2023-01-24 06:39:18.883775: step: 808/526, loss: 0.0012387357419356704
2023-01-24 06:39:19.978460: step: 812/526, loss: 0.019759926944971085
2023-01-24 06:39:21.052485: step: 816/526, loss: 0.011131839826703072
2023-01-24 06:39:22.113278: step: 820/526, loss: 0.0336940661072731
2023-01-24 06:39:23.166937: step: 824/526, loss: 0.0021152161061763763
2023-01-24 06:39:24.224497: step: 828/526, loss: 0.010587775148451328
2023-01-24 06:39:25.278705: step: 832/526, loss: 0.008336754515767097
2023-01-24 06:39:26.349651: step: 836/526, loss: 0.01640806719660759
2023-01-24 06:39:27.408133: step: 840/526, loss: 0.008297319523990154
2023-01-24 06:39:28.472040: step: 844/526, loss: 0.002325724344700575
2023-01-24 06:39:29.526533: step: 848/526, loss: 0.013057859614491463
2023-01-24 06:39:30.586300: step: 852/526, loss: 0.0060117305256426334
2023-01-24 06:39:31.660327: step: 856/526, loss: 0.006096655502915382
2023-01-24 06:39:32.728299: step: 860/526, loss: 0.01787818782031536
2023-01-24 06:39:33.781041: step: 864/526, loss: 0.009486567229032516
2023-01-24 06:39:34.847089: step: 868/526, loss: 0.0019624163396656513
2023-01-24 06:39:35.902730: step: 872/526, loss: 0.0045420927926898
2023-01-24 06:39:36.962833: step: 876/526, loss: 0.010387561284005642
2023-01-24 06:39:38.010450: step: 880/526, loss: 0.029061662033200264
2023-01-24 06:39:39.098241: step: 884/526, loss: 0.010791003704071045
2023-01-24 06:39:40.162815: step: 888/526, loss: 0.011274965479969978
2023-01-24 06:39:41.231497: step: 892/526, loss: 0.010358316823840141
2023-01-24 06:39:42.285254: step: 896/526, loss: 0.0020715061109513044
2023-01-24 06:39:43.343322: step: 900/526, loss: 0.014876225031912327
2023-01-24 06:39:44.422981: step: 904/526, loss: 0.0020804698579013348
2023-01-24 06:39:45.488793: step: 908/526, loss: 0.0026322698686271906
2023-01-24 06:39:46.571756: step: 912/526, loss: 0.0040582045912742615
2023-01-24 06:39:47.637747: step: 916/526, loss: 0.008920358493924141
2023-01-24 06:39:48.705335: step: 920/526, loss: 0.0029874430038034916
2023-01-24 06:39:49.773432: step: 924/526, loss: 0.009158621542155743
2023-01-24 06:39:50.829585: step: 928/526, loss: 0.00733718229457736
2023-01-24 06:39:51.897131: step: 932/526, loss: 0.007403201889246702
2023-01-24 06:39:52.976139: step: 936/526, loss: 0.03757746145129204
2023-01-24 06:39:54.039811: step: 940/526, loss: 0.018963400274515152
2023-01-24 06:39:55.092401: step: 944/526, loss: 0.054025933146476746
2023-01-24 06:39:56.156059: step: 948/526, loss: 0.006316265556961298
2023-01-24 06:39:57.216283: step: 952/526, loss: 0.040511757135391235
2023-01-24 06:39:58.302052: step: 956/526, loss: 0.02917717956006527
2023-01-24 06:39:59.367974: step: 960/526, loss: 0.0006092271069064736
2023-01-24 06:40:00.463871: step: 964/526, loss: 0.05069291964173317
2023-01-24 06:40:01.541392: step: 968/526, loss: 0.006297879386693239
2023-01-24 06:40:02.595043: step: 972/526, loss: 0.0001518265635240823
2023-01-24 06:40:03.660219: step: 976/526, loss: 0.0017175829270854592
2023-01-24 06:40:04.723084: step: 980/526, loss: 0.00459779379889369
2023-01-24 06:40:05.784915: step: 984/526, loss: 0.00311674945987761
2023-01-24 06:40:06.863181: step: 988/526, loss: 0.007379377260804176
2023-01-24 06:40:07.932228: step: 992/526, loss: 0.004725204780697823
2023-01-24 06:40:08.994855: step: 996/526, loss: 0.01223618071526289
2023-01-24 06:40:10.043552: step: 1000/526, loss: 0.0008432284812442958
2023-01-24 06:40:11.097750: step: 1004/526, loss: 0.0011946444865316153
2023-01-24 06:40:12.152988: step: 1008/526, loss: 0.013188197277486324
2023-01-24 06:40:13.224548: step: 1012/526, loss: 0.03502798080444336
2023-01-24 06:40:14.284157: step: 1016/526, loss: 0.006396422628313303
2023-01-24 06:40:15.357981: step: 1020/526, loss: 0.005777356680482626
2023-01-24 06:40:16.420941: step: 1024/526, loss: 0.02009611576795578
2023-01-24 06:40:17.489016: step: 1028/526, loss: 0.0015835731755942106
2023-01-24 06:40:18.539479: step: 1032/526, loss: 0.0016257904935628176
2023-01-24 06:40:19.626275: step: 1036/526, loss: 0.008096247911453247
2023-01-24 06:40:20.686742: step: 1040/526, loss: 0.00093059241771698
2023-01-24 06:40:21.761083: step: 1044/526, loss: 0.010792925953865051
2023-01-24 06:40:22.833115: step: 1048/526, loss: 0.0051745218224823475
2023-01-24 06:40:23.888482: step: 1052/526, loss: 0.009874873794615269
2023-01-24 06:40:24.960106: step: 1056/526, loss: 0.0026784767396748066
2023-01-24 06:40:26.021774: step: 1060/526, loss: 0.006505837198346853
2023-01-24 06:40:27.080255: step: 1064/526, loss: 0.023519212380051613
2023-01-24 06:40:28.141495: step: 1068/526, loss: 0.013372170738875866
2023-01-24 06:40:29.193465: step: 1072/526, loss: 0.008404867723584175
2023-01-24 06:40:30.248931: step: 1076/526, loss: 0.001452846685424447
2023-01-24 06:40:31.322018: step: 1080/526, loss: 0.014082156121730804
2023-01-24 06:40:32.390103: step: 1084/526, loss: 0.006291474215686321
2023-01-24 06:40:33.459192: step: 1088/526, loss: 0.011282151564955711
2023-01-24 06:40:34.530416: step: 1092/526, loss: 0.019947927445173264
2023-01-24 06:40:35.606141: step: 1096/526, loss: 0.0006907903007231653
2023-01-24 06:40:36.662964: step: 1100/526, loss: 0.030990425497293472
2023-01-24 06:40:37.722534: step: 1104/526, loss: 0.004109003581106663
2023-01-24 06:40:38.793210: step: 1108/526, loss: 0.009068459272384644
2023-01-24 06:40:39.845214: step: 1112/526, loss: 0.022836284711956978
2023-01-24 06:40:40.901428: step: 1116/526, loss: 0.014025052078068256
2023-01-24 06:40:41.963431: step: 1120/526, loss: 0.00168801739346236
2023-01-24 06:40:43.068322: step: 1124/526, loss: 0.02312871813774109
2023-01-24 06:40:44.144262: step: 1128/526, loss: 0.00856107845902443
2023-01-24 06:40:45.232144: step: 1132/526, loss: 0.03813363239169121
2023-01-24 06:40:46.311195: step: 1136/526, loss: 0.005415665917098522
2023-01-24 06:40:47.376075: step: 1140/526, loss: 0.005216538906097412
2023-01-24 06:40:48.430177: step: 1144/526, loss: 0.01107375044375658
2023-01-24 06:40:49.496763: step: 1148/526, loss: 0.002300586085766554
2023-01-24 06:40:50.568869: step: 1152/526, loss: 0.006091007962822914
2023-01-24 06:40:51.638974: step: 1156/526, loss: 0.006083650980144739
2023-01-24 06:40:52.712659: step: 1160/526, loss: 0.005855833645910025
2023-01-24 06:40:53.781656: step: 1164/526, loss: 0.0070433830842375755
2023-01-24 06:40:54.845299: step: 1168/526, loss: 0.002403890946879983
2023-01-24 06:40:55.914495: step: 1172/526, loss: 0.022314131259918213
2023-01-24 06:40:56.976739: step: 1176/526, loss: 0.0044588735327124596
2023-01-24 06:40:58.050312: step: 1180/526, loss: 0.005917669273912907
2023-01-24 06:40:59.100583: step: 1184/526, loss: 0.0057390546426177025
2023-01-24 06:41:00.176194: step: 1188/526, loss: 0.008226591162383556
2023-01-24 06:41:01.238344: step: 1192/526, loss: 0.010439438745379448
2023-01-24 06:41:02.322916: step: 1196/526, loss: 0.004426050931215286
2023-01-24 06:41:03.393662: step: 1200/526, loss: 0.038710419088602066
2023-01-24 06:41:04.451809: step: 1204/526, loss: 0.00555199570953846
2023-01-24 06:41:05.505600: step: 1208/526, loss: 0.010031957179307938
2023-01-24 06:41:06.581544: step: 1212/526, loss: 0.007387576159089804
2023-01-24 06:41:07.648369: step: 1216/526, loss: 0.003792413743212819
2023-01-24 06:41:08.711545: step: 1220/526, loss: 0.015015135519206524
2023-01-24 06:41:09.770429: step: 1224/526, loss: 0.0019042622298002243
2023-01-24 06:41:10.850894: step: 1228/526, loss: 0.009735428728163242
2023-01-24 06:41:11.920653: step: 1232/526, loss: 0.020870467647910118
2023-01-24 06:41:12.984593: step: 1236/526, loss: 0.008933988399803638
2023-01-24 06:41:14.037942: step: 1240/526, loss: 0.009933794848620892
2023-01-24 06:41:15.103475: step: 1244/526, loss: 0.015355129726231098
2023-01-24 06:41:16.167898: step: 1248/526, loss: 0.002939500380307436
2023-01-24 06:41:17.240182: step: 1252/526, loss: 0.017817232757806778
2023-01-24 06:41:18.302829: step: 1256/526, loss: 0.03595886379480362
2023-01-24 06:41:19.366207: step: 1260/526, loss: 0.0031141669023782015
2023-01-24 06:41:20.439739: step: 1264/526, loss: 0.06592642515897751
2023-01-24 06:41:21.498667: step: 1268/526, loss: 0.0035397219471633434
2023-01-24 06:41:22.582076: step: 1272/526, loss: 0.017418434843420982
2023-01-24 06:41:23.657315: step: 1276/526, loss: 0.005319727584719658
2023-01-24 06:41:24.727515: step: 1280/526, loss: 0.0031767389737069607
2023-01-24 06:41:25.799122: step: 1284/526, loss: 0.05969233810901642
2023-01-24 06:41:26.870031: step: 1288/526, loss: 0.004849054850637913
2023-01-24 06:41:27.934901: step: 1292/526, loss: 0.013007866218686104
2023-01-24 06:41:29.007943: step: 1296/526, loss: 0.003963765688240528
2023-01-24 06:41:30.081248: step: 1300/526, loss: 0.02162555791437626
2023-01-24 06:41:31.140376: step: 1304/526, loss: 0.0017899292288348079
2023-01-24 06:41:32.208791: step: 1308/526, loss: 0.008302192203700542
2023-01-24 06:41:33.276607: step: 1312/526, loss: 0.0018911845982074738
2023-01-24 06:41:34.339430: step: 1316/526, loss: 0.0028253381606191397
2023-01-24 06:41:35.429305: step: 1320/526, loss: 0.010233358480036259
2023-01-24 06:41:36.497834: step: 1324/526, loss: 0.010742838494479656
2023-01-24 06:41:37.568578: step: 1328/526, loss: 0.0020561402197927237
2023-01-24 06:41:38.630843: step: 1332/526, loss: 0.0062849028035998344
2023-01-24 06:41:39.692634: step: 1336/526, loss: 0.004208073485642672
2023-01-24 06:41:40.751937: step: 1340/526, loss: 0.004627154674381018
2023-01-24 06:41:41.812731: step: 1344/526, loss: 0.009445788338780403
2023-01-24 06:41:42.902139: step: 1348/526, loss: 0.008006146177649498
2023-01-24 06:41:43.970282: step: 1352/526, loss: 0.005335070192813873
2023-01-24 06:41:45.041897: step: 1356/526, loss: 0.00019222882110625505
2023-01-24 06:41:46.115043: step: 1360/526, loss: 0.0024903197772800922
2023-01-24 06:41:47.184031: step: 1364/526, loss: 0.011357102543115616
2023-01-24 06:41:48.245362: step: 1368/526, loss: 0.005335256457328796
2023-01-24 06:41:49.315574: step: 1372/526, loss: 0.005676691420376301
2023-01-24 06:41:50.370377: step: 1376/526, loss: 0.0011054989881813526
2023-01-24 06:41:51.440600: step: 1380/526, loss: 0.004948033485561609
2023-01-24 06:41:52.509112: step: 1384/526, loss: 0.004876416176557541
2023-01-24 06:41:53.582783: step: 1388/526, loss: 0.006801893003284931
2023-01-24 06:41:54.654518: step: 1392/526, loss: 0.0010870686965063214
2023-01-24 06:41:55.710110: step: 1396/526, loss: 0.0039533707313239574
2023-01-24 06:41:56.770010: step: 1400/526, loss: 0.00811266154050827
2023-01-24 06:41:57.834987: step: 1404/526, loss: 0.0011624109465628862
2023-01-24 06:41:58.898641: step: 1408/526, loss: 0.0040072244592010975
2023-01-24 06:41:59.969998: step: 1412/526, loss: 0.004937449935823679
2023-01-24 06:42:01.039039: step: 1416/526, loss: 0.003369309240952134
2023-01-24 06:42:02.079081: step: 1420/526, loss: 0.004999875091016293
2023-01-24 06:42:03.154051: step: 1424/526, loss: 0.02944946102797985
2023-01-24 06:42:04.217739: step: 1428/526, loss: 0.01299162395298481
2023-01-24 06:42:05.290234: step: 1432/526, loss: 0.004025980830192566
2023-01-24 06:42:06.369223: step: 1436/526, loss: 0.012488791719079018
2023-01-24 06:42:07.424968: step: 1440/526, loss: 0.00259688263759017
2023-01-24 06:42:08.495808: step: 1444/526, loss: 0.005833064671605825
2023-01-24 06:42:09.553631: step: 1448/526, loss: 0.01693911850452423
2023-01-24 06:42:10.626700: step: 1452/526, loss: 0.0222051739692688
2023-01-24 06:42:11.698923: step: 1456/526, loss: 0.009521521627902985
2023-01-24 06:42:12.772263: step: 1460/526, loss: 0.006272811908274889
2023-01-24 06:42:13.856799: step: 1464/526, loss: 0.07236727327108383
2023-01-24 06:42:14.924106: step: 1468/526, loss: 0.0027400723192840815
2023-01-24 06:42:15.990488: step: 1472/526, loss: 0.007792161777615547
2023-01-24 06:42:17.053221: step: 1476/526, loss: 0.007038488052785397
2023-01-24 06:42:18.110894: step: 1480/526, loss: 0.004880255553871393
2023-01-24 06:42:19.184411: step: 1484/526, loss: 0.021832432597875595
2023-01-24 06:42:20.255413: step: 1488/526, loss: 0.02342221885919571
2023-01-24 06:42:21.317940: step: 1492/526, loss: 0.008433393202722073
2023-01-24 06:42:22.379660: step: 1496/526, loss: 0.013123411685228348
2023-01-24 06:42:23.471228: step: 1500/526, loss: 0.029821787029504776
2023-01-24 06:42:24.542188: step: 1504/526, loss: 0.00908041000366211
2023-01-24 06:42:25.636881: step: 1508/526, loss: 0.007355151232331991
2023-01-24 06:42:26.698412: step: 1512/526, loss: 0.010647871531546116
2023-01-24 06:42:27.748714: step: 1516/526, loss: 0.0041663506999611855
2023-01-24 06:42:28.818082: step: 1520/526, loss: 0.0074890777468681335
2023-01-24 06:42:29.880290: step: 1524/526, loss: 0.013116743415594101
2023-01-24 06:42:30.949436: step: 1528/526, loss: 0.010179124772548676
2023-01-24 06:42:32.015731: step: 1532/526, loss: 0.002877237508073449
2023-01-24 06:42:33.098269: step: 1536/526, loss: 0.00595517922192812
2023-01-24 06:42:34.190055: step: 1540/526, loss: 0.002787857549265027
2023-01-24 06:42:35.282045: step: 1544/526, loss: 0.01670055463910103
2023-01-24 06:42:36.339422: step: 1548/526, loss: 0.015345240011811256
2023-01-24 06:42:37.414035: step: 1552/526, loss: 0.006643395870923996
2023-01-24 06:42:38.478406: step: 1556/526, loss: 0.006088084075599909
2023-01-24 06:42:39.557468: step: 1560/526, loss: 0.01892280764877796
2023-01-24 06:42:40.613333: step: 1564/526, loss: 0.0015434101223945618
2023-01-24 06:42:41.685979: step: 1568/526, loss: 0.04486711323261261
2023-01-24 06:42:42.753237: step: 1572/526, loss: 0.007180152926594019
2023-01-24 06:42:43.824351: step: 1576/526, loss: 0.0025067832320928574
2023-01-24 06:42:44.874678: step: 1580/526, loss: 0.0025074954610317945
2023-01-24 06:42:45.945936: step: 1584/526, loss: 0.007054222282022238
2023-01-24 06:42:47.019373: step: 1588/526, loss: 0.008581985719501972
2023-01-24 06:42:48.088394: step: 1592/526, loss: 0.00856317114084959
2023-01-24 06:42:49.153753: step: 1596/526, loss: 0.012064811773598194
2023-01-24 06:42:50.240436: step: 1600/526, loss: 0.00014818670751992613
2023-01-24 06:42:51.315623: step: 1604/526, loss: 0.012100787833333015
2023-01-24 06:42:52.397562: step: 1608/526, loss: 0.003516745986416936
2023-01-24 06:42:53.456985: step: 1612/526, loss: 0.03523869812488556
2023-01-24 06:42:54.538962: step: 1616/526, loss: 0.004461720120161772
2023-01-24 06:42:55.605895: step: 1620/526, loss: 0.032758813351392746
2023-01-24 06:42:56.683090: step: 1624/526, loss: 0.0041448506526649
2023-01-24 06:42:57.760722: step: 1628/526, loss: 0.045187175273895264
2023-01-24 06:42:58.817743: step: 1632/526, loss: 0.009123891592025757
2023-01-24 06:42:59.904628: step: 1636/526, loss: 0.005572086665779352
2023-01-24 06:43:00.964354: step: 1640/526, loss: 0.01416696235537529
2023-01-24 06:43:02.024791: step: 1644/526, loss: 0.004191957879811525
2023-01-24 06:43:03.098194: step: 1648/526, loss: 0.02418801188468933
2023-01-24 06:43:04.162664: step: 1652/526, loss: 0.005827329587191343
2023-01-24 06:43:05.235661: step: 1656/526, loss: 0.005489479750394821
2023-01-24 06:43:06.311805: step: 1660/526, loss: 0.014370226301252842
2023-01-24 06:43:07.386361: step: 1664/526, loss: 0.006896455306559801
2023-01-24 06:43:08.466875: step: 1668/526, loss: 0.009979184716939926
2023-01-24 06:43:09.535462: step: 1672/526, loss: 0.002629706170409918
2023-01-24 06:43:10.619874: step: 1676/526, loss: 0.0019369483925402164
2023-01-24 06:43:11.700169: step: 1680/526, loss: 0.004555763676762581
2023-01-24 06:43:12.775942: step: 1684/526, loss: 0.00010799784649861977
2023-01-24 06:43:13.846923: step: 1688/526, loss: 0.001377445412799716
2023-01-24 06:43:14.921373: step: 1692/526, loss: 0.007142608053982258
2023-01-24 06:43:15.983663: step: 1696/526, loss: 0.006169511936604977
2023-01-24 06:43:17.053457: step: 1700/526, loss: 0.005927258636802435
2023-01-24 06:43:18.115005: step: 1704/526, loss: 0.022003227844834328
2023-01-24 06:43:19.166961: step: 1708/526, loss: 0.018207816407084465
2023-01-24 06:43:20.230090: step: 1712/526, loss: 0.0013692082138732076
2023-01-24 06:43:21.316118: step: 1716/526, loss: 0.007651047315448523
2023-01-24 06:43:22.396608: step: 1720/526, loss: 0.0025622923858463764
2023-01-24 06:43:23.448922: step: 1724/526, loss: 0.0033063122536987066
2023-01-24 06:43:24.514064: step: 1728/526, loss: 0.0012544144410640001
2023-01-24 06:43:25.591769: step: 1732/526, loss: 0.005951226688921452
2023-01-24 06:43:26.662084: step: 1736/526, loss: 0.0012751303147524595
2023-01-24 06:43:27.732967: step: 1740/526, loss: 0.011261491104960442
2023-01-24 06:43:28.792025: step: 1744/526, loss: 0.01785769872367382
2023-01-24 06:43:29.863393: step: 1748/526, loss: 0.010424482636153698
2023-01-24 06:43:30.914459: step: 1752/526, loss: 0.004392494447529316
2023-01-24 06:43:31.997453: step: 1756/526, loss: 0.005734024103730917
2023-01-24 06:43:33.083201: step: 1760/526, loss: 0.008379615843296051
2023-01-24 06:43:34.147396: step: 1764/526, loss: 0.006811490282416344
2023-01-24 06:43:35.212385: step: 1768/526, loss: 0.004867592826485634
2023-01-24 06:43:36.288478: step: 1772/526, loss: 0.010081914253532887
2023-01-24 06:43:37.346865: step: 1776/526, loss: 0.009950308129191399
2023-01-24 06:43:38.415145: step: 1780/526, loss: 0.005420364905148745
2023-01-24 06:43:39.487991: step: 1784/526, loss: 0.009828265756368637
2023-01-24 06:43:40.564075: step: 1788/526, loss: 0.004393778275698423
2023-01-24 06:43:41.635247: step: 1792/526, loss: 0.021046601235866547
2023-01-24 06:43:42.705046: step: 1796/526, loss: 0.0021652954164892435
2023-01-24 06:43:43.788507: step: 1800/526, loss: 0.02698512002825737
2023-01-24 06:43:44.865507: step: 1804/526, loss: 0.00442785257473588
2023-01-24 06:43:45.936706: step: 1808/526, loss: 0.0035056646447628736
2023-01-24 06:43:46.995866: step: 1812/526, loss: 0.008704300038516521
2023-01-24 06:43:48.071439: step: 1816/526, loss: 0.00465176347643137
2023-01-24 06:43:49.148449: step: 1820/526, loss: 0.005390379577875137
2023-01-24 06:43:50.221389: step: 1824/526, loss: 0.005838509649038315
2023-01-24 06:43:51.300472: step: 1828/526, loss: 0.0067871734499931335
2023-01-24 06:43:52.364574: step: 1832/526, loss: 0.02269057184457779
2023-01-24 06:43:53.467138: step: 1836/526, loss: 0.020564686506986618
2023-01-24 06:43:54.532619: step: 1840/526, loss: 0.00322343735024333
2023-01-24 06:43:55.601671: step: 1844/526, loss: 0.004267917014658451
2023-01-24 06:43:56.668299: step: 1848/526, loss: 0.003914065193384886
2023-01-24 06:43:57.735501: step: 1852/526, loss: 0.014520698226988316
2023-01-24 06:43:58.815686: step: 1856/526, loss: 0.0070778545923531055
2023-01-24 06:43:59.867606: step: 1860/526, loss: 0.004852039739489555
2023-01-24 06:44:00.936283: step: 1864/526, loss: 0.013096362352371216
2023-01-24 06:44:01.996962: step: 1868/526, loss: 0.003364998148754239
2023-01-24 06:44:03.058697: step: 1872/526, loss: 0.017421839758753777
2023-01-24 06:44:04.136802: step: 1876/526, loss: 0.04439467191696167
2023-01-24 06:44:05.192273: step: 1880/526, loss: 0.006587847135961056
2023-01-24 06:44:06.257359: step: 1884/526, loss: 0.0025913419667631388
2023-01-24 06:44:07.327670: step: 1888/526, loss: 0.016689134761691093
2023-01-24 06:44:08.387857: step: 1892/526, loss: 0.012358699925243855
2023-01-24 06:44:09.451540: step: 1896/526, loss: 0.03405987471342087
2023-01-24 06:44:10.549965: step: 1900/526, loss: 0.016695545986294746
2023-01-24 06:44:11.626922: step: 1904/526, loss: 0.007997590117156506
2023-01-24 06:44:12.700711: step: 1908/526, loss: 0.0005133855156600475
2023-01-24 06:44:13.771286: step: 1912/526, loss: 0.0783570259809494
2023-01-24 06:44:14.850350: step: 1916/526, loss: 0.008114861324429512
2023-01-24 06:44:15.920649: step: 1920/526, loss: 0.008517680689692497
2023-01-24 06:44:16.974548: step: 1924/526, loss: 0.001336141605861485
2023-01-24 06:44:18.046870: step: 1928/526, loss: 0.007499922998249531
2023-01-24 06:44:19.104211: step: 1932/526, loss: 0.0058199567720294
2023-01-24 06:44:20.182349: step: 1936/526, loss: 0.0038512928877025843
2023-01-24 06:44:21.261426: step: 1940/526, loss: 0.01217322051525116
2023-01-24 06:44:22.319395: step: 1944/526, loss: 0.011248461902141571
2023-01-24 06:44:23.387008: step: 1948/526, loss: 0.005188351962715387
2023-01-24 06:44:24.462267: step: 1952/526, loss: 0.0009030320798046887
2023-01-24 06:44:25.527172: step: 1956/526, loss: 0.004988142289221287
2023-01-24 06:44:26.578354: step: 1960/526, loss: 0.005158405285328627
2023-01-24 06:44:27.662599: step: 1964/526, loss: 0.0034259711392223835
2023-01-24 06:44:28.720271: step: 1968/526, loss: 0.007517583202570677
2023-01-24 06:44:29.797741: step: 1972/526, loss: 0.02355273626744747
2023-01-24 06:44:30.869974: step: 1976/526, loss: 0.02196827344596386
2023-01-24 06:44:31.957424: step: 1980/526, loss: 0.008239859715104103
2023-01-24 06:44:33.036477: step: 1984/526, loss: 0.02101517654955387
2023-01-24 06:44:34.106820: step: 1988/526, loss: 0.007755276747047901
2023-01-24 06:44:35.171648: step: 1992/526, loss: 0.0046648369170725346
2023-01-24 06:44:36.252062: step: 1996/526, loss: 0.012993941083550453
2023-01-24 06:44:37.342875: step: 2000/526, loss: 0.006515428423881531
2023-01-24 06:44:38.420972: step: 2004/526, loss: 0.006839878391474485
2023-01-24 06:44:39.490886: step: 2008/526, loss: 0.014127875678241253
2023-01-24 06:44:40.583155: step: 2012/526, loss: 0.009130644612014294
2023-01-24 06:44:41.656399: step: 2016/526, loss: 0.003195829689502716
2023-01-24 06:44:42.731210: step: 2020/526, loss: 0.0185227207839489
2023-01-24 06:44:43.833163: step: 2024/526, loss: 0.006691941060125828
2023-01-24 06:44:44.924721: step: 2028/526, loss: 0.01640489511191845
2023-01-24 06:44:46.001967: step: 2032/526, loss: 0.008451828733086586
2023-01-24 06:44:47.085994: step: 2036/526, loss: 0.016497690230607986
2023-01-24 06:44:48.167888: step: 2040/526, loss: 0.003117659827694297
2023-01-24 06:44:49.220219: step: 2044/526, loss: 0.007110433652997017
2023-01-24 06:44:50.283796: step: 2048/526, loss: 0.01805409975349903
2023-01-24 06:44:51.341200: step: 2052/526, loss: 0.023531576618552208
2023-01-24 06:44:52.411125: step: 2056/526, loss: 0.03242948651313782
2023-01-24 06:44:53.468230: step: 2060/526, loss: 0.002636838238686323
2023-01-24 06:44:54.527559: step: 2064/526, loss: 0.0014066470321267843
2023-01-24 06:44:55.583573: step: 2068/526, loss: 0.008077271282672882
2023-01-24 06:44:56.651143: step: 2072/526, loss: 0.00169633817858994
2023-01-24 06:44:57.716724: step: 2076/526, loss: 0.023290548473596573
2023-01-24 06:44:58.791014: step: 2080/526, loss: 0.009173968806862831
2023-01-24 06:44:59.847983: step: 2084/526, loss: 0.003000599332153797
2023-01-24 06:45:00.909040: step: 2088/526, loss: 0.007806662004441023
2023-01-24 06:45:01.992419: step: 2092/526, loss: 0.0024546682834625244
2023-01-24 06:45:03.069176: step: 2096/526, loss: 0.05753093957901001
2023-01-24 06:45:04.133069: step: 2100/526, loss: 0.018630729988217354
2023-01-24 06:45:05.189099: step: 2104/526, loss: 0.008223350159823895
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37290913200723325, 'r': 0.2795049471401464, 'f1': 0.319520839789278}, 'combined': 0.23543640826578377, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3604567051035661, 'r': 0.22062720559403998, 'f1': 0.27371797470407006}, 'combined': 0.1493007134749473, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33793953011668243, 'r': 0.29048692057468145, 'f1': 0.3124216472303207}, 'combined': 0.23020542427497312, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.365070345298815, 'r': 0.26019194783877114, 'f1': 0.30383525532882144}, 'combined': 0.16572832108844804, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 3}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336995843596059, 'r': 0.29380760368663594, 'f1': 0.31248558454663394}, 'combined': 0.23025253598173026, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597710279387254, 'r': 0.2590483064846998, 'f1': 0.30121255211465625}, 'combined': 0.1642977556989034, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 06:47:54.555606: step: 4/526, loss: 0.04561716690659523
2023-01-24 06:47:55.614246: step: 8/526, loss: 0.009583407081663609
2023-01-24 06:47:56.671184: step: 12/526, loss: 0.008871912024915218
2023-01-24 06:47:57.734775: step: 16/526, loss: 0.03346626088023186
2023-01-24 06:47:58.785890: step: 20/526, loss: 0.016370423138141632
2023-01-24 06:47:59.842630: step: 24/526, loss: 0.009490296244621277
2023-01-24 06:48:00.911964: step: 28/526, loss: 0.016934407874941826
2023-01-24 06:48:01.985492: step: 32/526, loss: 0.015565715730190277
2023-01-24 06:48:03.032041: step: 36/526, loss: 0.0012508517829701304
2023-01-24 06:48:04.118816: step: 40/526, loss: 0.008080514147877693
2023-01-24 06:48:05.187749: step: 44/526, loss: 0.004121420439332724
2023-01-24 06:48:06.251123: step: 48/526, loss: 0.0066663045436143875
2023-01-24 06:48:07.304065: step: 52/526, loss: 0.03254383057355881
2023-01-24 06:48:08.373896: step: 56/526, loss: 0.020131584256887436
2023-01-24 06:48:09.438102: step: 60/526, loss: 0.0019100387580692768
2023-01-24 06:48:10.495675: step: 64/526, loss: 0.004221797920763493
2023-01-24 06:48:11.554926: step: 68/526, loss: 0.0019880777690559626
2023-01-24 06:48:12.638468: step: 72/526, loss: 0.008283071219921112
2023-01-24 06:48:13.720507: step: 76/526, loss: 0.002142650308087468
2023-01-24 06:48:14.788308: step: 80/526, loss: 0.01260561402887106
2023-01-24 06:48:15.869455: step: 84/526, loss: 0.005416129715740681
2023-01-24 06:48:16.942767: step: 88/526, loss: 0.010029232129454613
2023-01-24 06:48:18.013595: step: 92/526, loss: 0.0063294656574726105
2023-01-24 06:48:19.086518: step: 96/526, loss: 0.006487805861979723
2023-01-24 06:48:20.160123: step: 100/526, loss: 0.027292942628264427
2023-01-24 06:48:21.215685: step: 104/526, loss: 0.00549099687486887
2023-01-24 06:48:22.283419: step: 108/526, loss: 0.04029904678463936
2023-01-24 06:48:23.348124: step: 112/526, loss: 0.0190633125603199
2023-01-24 06:48:24.408332: step: 116/526, loss: 0.0027551420498639345
2023-01-24 06:48:25.480761: step: 120/526, loss: 0.008756263181567192
2023-01-24 06:48:26.558259: step: 124/526, loss: 0.02007344178855419
2023-01-24 06:48:27.616938: step: 128/526, loss: 0.005198202561587095
2023-01-24 06:48:28.700022: step: 132/526, loss: 0.018453950062394142
2023-01-24 06:48:29.779745: step: 136/526, loss: 0.009264092892408371
2023-01-24 06:48:30.865768: step: 140/526, loss: 0.012572417967021465
2023-01-24 06:48:31.930687: step: 144/526, loss: 0.0030364994890987873
2023-01-24 06:48:33.007400: step: 148/526, loss: 0.006098009645938873
2023-01-24 06:48:34.085285: step: 152/526, loss: 0.007495851255953312
2023-01-24 06:48:35.146337: step: 156/526, loss: 0.005035730544477701
2023-01-24 06:48:36.208318: step: 160/526, loss: 0.001721342676319182
2023-01-24 06:48:37.285670: step: 164/526, loss: 0.006296331528574228
2023-01-24 06:48:38.347955: step: 168/526, loss: 0.00730692595243454
2023-01-24 06:48:39.431953: step: 172/526, loss: 0.0013020512415096164
2023-01-24 06:48:40.517788: step: 176/526, loss: 0.001522004371508956
2023-01-24 06:48:41.601698: step: 180/526, loss: 0.04031140357255936
2023-01-24 06:48:42.669536: step: 184/526, loss: 0.006029242649674416
2023-01-24 06:48:43.744541: step: 188/526, loss: 0.0065521495416760445
2023-01-24 06:48:44.805480: step: 192/526, loss: 0.029529938474297523
2023-01-24 06:48:45.889298: step: 196/526, loss: 0.006208635400980711
2023-01-24 06:48:46.962082: step: 200/526, loss: 0.020144633948802948
2023-01-24 06:48:48.033664: step: 204/526, loss: 0.007020852528512478
2023-01-24 06:48:49.118543: step: 208/526, loss: 0.04450790584087372
2023-01-24 06:48:50.187830: step: 212/526, loss: 0.015817951411008835
2023-01-24 06:48:51.265029: step: 216/526, loss: 0.008612891659140587
2023-01-24 06:48:52.325462: step: 220/526, loss: 0.005087288562208414
2023-01-24 06:48:53.379634: step: 224/526, loss: 0.002728690393269062
2023-01-24 06:48:54.454035: step: 228/526, loss: 0.015435674227774143
2023-01-24 06:48:55.531802: step: 232/526, loss: 0.006181768141686916
2023-01-24 06:48:56.631686: step: 236/526, loss: 0.011566904373466969
2023-01-24 06:48:57.704112: step: 240/526, loss: 0.005427936092019081
2023-01-24 06:48:58.767058: step: 244/526, loss: 0.0050893500447273254
2023-01-24 06:48:59.834969: step: 248/526, loss: 0.009158079512417316
2023-01-24 06:49:00.920176: step: 252/526, loss: 0.0015035689575597644
2023-01-24 06:49:01.989411: step: 256/526, loss: 0.04388522356748581
2023-01-24 06:49:03.084817: step: 260/526, loss: 0.007679319009184837
2023-01-24 06:49:04.164695: step: 264/526, loss: 0.00824405811727047
2023-01-24 06:49:05.233373: step: 268/526, loss: 0.012040205299854279
2023-01-24 06:49:06.313995: step: 272/526, loss: 0.002386068692430854
2023-01-24 06:49:07.408630: step: 276/526, loss: 0.004297530744224787
2023-01-24 06:49:08.489917: step: 280/526, loss: 0.011628060601651669
2023-01-24 06:49:09.584272: step: 284/526, loss: 0.005363657139241695
2023-01-24 06:49:10.668514: step: 288/526, loss: 0.00326823559589684
2023-01-24 06:49:11.752255: step: 292/526, loss: 0.0031411077361553907
2023-01-24 06:49:12.857336: step: 296/526, loss: 0.003462613094598055
2023-01-24 06:49:13.943007: step: 300/526, loss: 0.01911255531013012
2023-01-24 06:49:15.027080: step: 304/526, loss: 0.006545764394104481
2023-01-24 06:49:16.090223: step: 308/526, loss: 0.0066093867644667625
2023-01-24 06:49:17.162205: step: 312/526, loss: 0.021443061530590057
2023-01-24 06:49:18.238665: step: 316/526, loss: 0.004921016748994589
2023-01-24 06:49:19.306458: step: 320/526, loss: 0.0036913591902703047
2023-01-24 06:49:20.377910: step: 324/526, loss: 0.005502030253410339
2023-01-24 06:49:21.471035: step: 328/526, loss: 0.014686096459627151
2023-01-24 06:49:22.537806: step: 332/526, loss: 0.0074418387375772
2023-01-24 06:49:23.618634: step: 336/526, loss: 0.011564705520868301
2023-01-24 06:49:24.689241: step: 340/526, loss: 0.02050345204770565
2023-01-24 06:49:25.751342: step: 344/526, loss: 0.00533823249861598
2023-01-24 06:49:26.817335: step: 348/526, loss: 0.014311171136796474
2023-01-24 06:49:27.915135: step: 352/526, loss: 0.003921550698578358
2023-01-24 06:49:28.969597: step: 356/526, loss: 0.0388287752866745
2023-01-24 06:49:30.049752: step: 360/526, loss: 0.004193302243947983
2023-01-24 06:49:31.124716: step: 364/526, loss: 0.009171021170914173
2023-01-24 06:49:32.193754: step: 368/526, loss: 0.006631837692111731
2023-01-24 06:49:33.258770: step: 372/526, loss: 0.03862081840634346
2023-01-24 06:49:34.315958: step: 376/526, loss: 0.005430086050182581
2023-01-24 06:49:35.385366: step: 380/526, loss: 0.005405530333518982
2023-01-24 06:49:36.456550: step: 384/526, loss: 0.04989420250058174
2023-01-24 06:49:37.512115: step: 388/526, loss: 0.003538896329700947
2023-01-24 06:49:38.581301: step: 392/526, loss: 0.012618141248822212
2023-01-24 06:49:39.642954: step: 396/526, loss: 0.00478720897808671
2023-01-24 06:49:40.696061: step: 400/526, loss: 0.012967278249561787
2023-01-24 06:49:41.767133: step: 404/526, loss: 0.0074020931497216225
2023-01-24 06:49:42.853644: step: 408/526, loss: 0.013714803382754326
2023-01-24 06:49:43.920940: step: 412/526, loss: 0.024566100910305977
2023-01-24 06:49:44.985269: step: 416/526, loss: 0.014504571445286274
2023-01-24 06:49:46.071303: step: 420/526, loss: 0.03642435744404793
2023-01-24 06:49:47.131512: step: 424/526, loss: 0.004088229034096003
2023-01-24 06:49:48.194869: step: 428/526, loss: 0.0028984721284359694
2023-01-24 06:49:49.254717: step: 432/526, loss: 0.021795539185404778
2023-01-24 06:49:50.321159: step: 436/526, loss: 0.011544923298060894
2023-01-24 06:49:51.387231: step: 440/526, loss: 0.008165497332811356
2023-01-24 06:49:52.461323: step: 444/526, loss: 0.009896943345665932
2023-01-24 06:49:53.535604: step: 448/526, loss: 0.0070206522941589355
2023-01-24 06:49:54.616886: step: 452/526, loss: 0.003799766767770052
2023-01-24 06:49:55.700488: step: 456/526, loss: 0.01626633293926716
2023-01-24 06:49:56.775093: step: 460/526, loss: 0.00402452889829874
2023-01-24 06:49:57.859525: step: 464/526, loss: 0.008234470151364803
2023-01-24 06:49:58.918184: step: 468/526, loss: 0.01112395990639925
2023-01-24 06:49:59.987181: step: 472/526, loss: 0.024101847782731056
2023-01-24 06:50:01.055336: step: 476/526, loss: 0.03141447901725769
2023-01-24 06:50:02.117176: step: 480/526, loss: 0.003685676958411932
2023-01-24 06:50:03.195418: step: 484/526, loss: 0.002476579276844859
2023-01-24 06:50:04.257113: step: 488/526, loss: 0.006108688656240702
2023-01-24 06:50:05.325304: step: 492/526, loss: 0.044986505061388016
2023-01-24 06:50:06.386346: step: 496/526, loss: 0.026766033843159676
2023-01-24 06:50:07.444131: step: 500/526, loss: 0.013256989419460297
2023-01-24 06:50:08.506597: step: 504/526, loss: 0.024712851271033287
2023-01-24 06:50:09.574078: step: 508/526, loss: 0.008650749921798706
2023-01-24 06:50:10.636417: step: 512/526, loss: 0.0394333079457283
2023-01-24 06:50:11.700052: step: 516/526, loss: 0.01165279932320118
2023-01-24 06:50:12.796547: step: 520/526, loss: 0.045307960361242294
2023-01-24 06:50:13.886354: step: 524/526, loss: 0.05910734459757805
2023-01-24 06:50:14.951902: step: 528/526, loss: 0.008395752869546413
2023-01-24 06:50:16.013245: step: 532/526, loss: 0.007766869384795427
2023-01-24 06:50:17.080884: step: 536/526, loss: 0.011209053918719292
2023-01-24 06:50:18.144995: step: 540/526, loss: 0.00456573348492384
2023-01-24 06:50:19.199249: step: 544/526, loss: 0.0036347168497741222
2023-01-24 06:50:20.282408: step: 548/526, loss: 0.007989378646016121
2023-01-24 06:50:21.353325: step: 552/526, loss: 0.030643368139863014
2023-01-24 06:50:22.419678: step: 556/526, loss: 0.0010265993187204003
2023-01-24 06:50:23.488122: step: 560/526, loss: 0.008294590748846531
2023-01-24 06:50:24.551048: step: 564/526, loss: 0.03510265052318573
2023-01-24 06:50:25.627863: step: 568/526, loss: 0.010723576880991459
2023-01-24 06:50:26.687069: step: 572/526, loss: 0.00177483179140836
2023-01-24 06:50:27.765959: step: 576/526, loss: 0.005997425876557827
2023-01-24 06:50:28.830731: step: 580/526, loss: 0.021022701635956764
2023-01-24 06:50:29.896955: step: 584/526, loss: 0.013442527502775192
2023-01-24 06:50:30.968557: step: 588/526, loss: 0.005017580930143595
2023-01-24 06:50:32.034524: step: 592/526, loss: 0.010660244151949883
2023-01-24 06:50:33.114041: step: 596/526, loss: 0.0018021485302597284
2023-01-24 06:50:34.190998: step: 600/526, loss: 0.018023859709501266
2023-01-24 06:50:35.240516: step: 604/526, loss: 0.015794062986969948
2023-01-24 06:50:36.319293: step: 608/526, loss: 0.028301579877734184
2023-01-24 06:50:37.390970: step: 612/526, loss: 0.0025440328754484653
2023-01-24 06:50:38.467924: step: 616/526, loss: 0.013181930407881737
2023-01-24 06:50:39.543933: step: 620/526, loss: 0.011142008006572723
2023-01-24 06:50:40.597444: step: 624/526, loss: 0.00868635531514883
2023-01-24 06:50:41.681499: step: 628/526, loss: 0.010363152250647545
2023-01-24 06:50:42.776952: step: 632/526, loss: 0.01566331833600998
2023-01-24 06:50:43.859765: step: 636/526, loss: 0.002800422254949808
2023-01-24 06:50:44.925623: step: 640/526, loss: 0.009345663711428642
2023-01-24 06:50:45.995120: step: 644/526, loss: 0.007596664130687714
2023-01-24 06:50:47.052509: step: 648/526, loss: 0.010002491995692253
2023-01-24 06:50:48.120243: step: 652/526, loss: 0.011854047887027264
2023-01-24 06:50:49.188712: step: 656/526, loss: 0.0031592161394655704
2023-01-24 06:50:50.246083: step: 660/526, loss: 0.005276334006339312
2023-01-24 06:50:51.319253: step: 664/526, loss: 0.04187704622745514
2023-01-24 06:50:52.368914: step: 668/526, loss: 0.008595994673669338
2023-01-24 06:50:53.461197: step: 672/526, loss: 0.011099678464233875
2023-01-24 06:50:54.527108: step: 676/526, loss: 0.029476739466190338
2023-01-24 06:50:55.601864: step: 680/526, loss: 0.005831962917000055
2023-01-24 06:50:56.659012: step: 684/526, loss: 0.013440776616334915
2023-01-24 06:50:57.720760: step: 688/526, loss: 0.00838993676006794
2023-01-24 06:50:58.778048: step: 692/526, loss: 0.0006554737337864935
2023-01-24 06:50:59.836192: step: 696/526, loss: 0.012389463372528553
2023-01-24 06:51:00.904314: step: 700/526, loss: 0.007408950477838516
2023-01-24 06:51:01.975239: step: 704/526, loss: 0.006197801791131496
2023-01-24 06:51:03.042117: step: 708/526, loss: 0.006031715776771307
2023-01-24 06:51:04.089389: step: 712/526, loss: 0.002810501726344228
2023-01-24 06:51:05.151023: step: 716/526, loss: 0.025104759261012077
2023-01-24 06:51:06.217041: step: 720/526, loss: 0.009968100115656853
2023-01-24 06:51:07.265715: step: 724/526, loss: 0.019871799275279045
2023-01-24 06:51:08.326646: step: 728/526, loss: 0.01130816712975502
2023-01-24 06:51:09.396095: step: 732/526, loss: 0.011507372371852398
2023-01-24 06:51:10.452541: step: 736/526, loss: 0.013298151083290577
2023-01-24 06:51:11.508921: step: 740/526, loss: 0.06474484503269196
2023-01-24 06:51:12.567688: step: 744/526, loss: 0.012374096550047398
2023-01-24 06:51:13.650907: step: 748/526, loss: 0.028651466593146324
2023-01-24 06:51:14.727335: step: 752/526, loss: 0.018522465601563454
2023-01-24 06:51:15.786891: step: 756/526, loss: 0.0014116679085418582
2023-01-24 06:51:16.848678: step: 760/526, loss: 0.012200803495943546
2023-01-24 06:51:17.922195: step: 764/526, loss: 0.0045927297323942184
2023-01-24 06:51:18.986816: step: 768/526, loss: 0.005744764115661383
2023-01-24 06:51:20.053190: step: 772/526, loss: 0.007151265162974596
2023-01-24 06:51:21.110228: step: 776/526, loss: 0.002220354275777936
2023-01-24 06:51:22.175670: step: 780/526, loss: 0.008260620757937431
2023-01-24 06:51:23.238457: step: 784/526, loss: 0.008544021286070347
2023-01-24 06:51:24.326241: step: 788/526, loss: 0.007146183401346207
2023-01-24 06:51:25.407369: step: 792/526, loss: 0.004178935196250677
2023-01-24 06:51:26.486179: step: 796/526, loss: 0.030275003984570503
2023-01-24 06:51:27.576159: step: 800/526, loss: 0.005692994687706232
2023-01-24 06:51:28.644772: step: 804/526, loss: 0.028237413614988327
2023-01-24 06:51:29.722422: step: 808/526, loss: 0.015095150098204613
2023-01-24 06:51:30.786685: step: 812/526, loss: 0.011295042000710964
2023-01-24 06:51:31.854272: step: 816/526, loss: 0.0037475123535841703
2023-01-24 06:51:32.905406: step: 820/526, loss: 0.0073763844557106495
2023-01-24 06:51:33.972718: step: 824/526, loss: 0.002914538374170661
2023-01-24 06:51:35.032169: step: 828/526, loss: 0.0021776368375867605
2023-01-24 06:51:36.093826: step: 832/526, loss: 0.014286899007856846
2023-01-24 06:51:37.159905: step: 836/526, loss: 0.00038108142325654626
2023-01-24 06:51:38.244980: step: 840/526, loss: 0.007071319036185741
2023-01-24 06:51:39.308469: step: 844/526, loss: 0.0065015205182135105
2023-01-24 06:51:40.376444: step: 848/526, loss: 0.00446522980928421
2023-01-24 06:51:41.445427: step: 852/526, loss: 0.01957670785486698
2023-01-24 06:51:42.527770: step: 856/526, loss: 0.02963337115943432
2023-01-24 06:51:43.594854: step: 860/526, loss: 0.009095244109630585
2023-01-24 06:51:44.660416: step: 864/526, loss: 0.023104403167963028
2023-01-24 06:51:45.749922: step: 868/526, loss: 0.005967161152511835
2023-01-24 06:51:46.825133: step: 872/526, loss: 0.0035698008723556995
2023-01-24 06:51:47.897138: step: 876/526, loss: 0.021016787737607956
2023-01-24 06:51:48.981503: step: 880/526, loss: 0.0043370104394853115
2023-01-24 06:51:50.039683: step: 884/526, loss: 0.012632861733436584
2023-01-24 06:51:51.115707: step: 888/526, loss: 0.014910683035850525
2023-01-24 06:51:52.198221: step: 892/526, loss: 0.010937982238829136
2023-01-24 06:51:53.267581: step: 896/526, loss: 0.002072559203952551
2023-01-24 06:51:54.329473: step: 900/526, loss: 0.019145850092172623
2023-01-24 06:51:55.407718: step: 904/526, loss: 0.004065972287207842
2023-01-24 06:51:56.459290: step: 908/526, loss: 0.0021442428696900606
2023-01-24 06:51:57.516181: step: 912/526, loss: 0.004783442709594965
2023-01-24 06:51:58.589998: step: 916/526, loss: 0.029454268515110016
2023-01-24 06:51:59.663254: step: 920/526, loss: 0.009567839093506336
2023-01-24 06:52:00.751078: step: 924/526, loss: 0.030318789184093475
2023-01-24 06:52:01.819560: step: 928/526, loss: 0.008138017728924751
2023-01-24 06:52:02.892232: step: 932/526, loss: 0.009428447112441063
2023-01-24 06:52:03.962868: step: 936/526, loss: 0.016100618988275528
2023-01-24 06:52:05.018192: step: 940/526, loss: 0.0042785778641700745
2023-01-24 06:52:06.070298: step: 944/526, loss: 0.00715788546949625
2023-01-24 06:52:07.133548: step: 948/526, loss: 0.006330091506242752
2023-01-24 06:52:08.199907: step: 952/526, loss: 0.02403317019343376
2023-01-24 06:52:09.265278: step: 956/526, loss: 0.0019050012342631817
2023-01-24 06:52:10.344332: step: 960/526, loss: 0.009052552282810211
2023-01-24 06:52:11.433177: step: 964/526, loss: 0.022979607805609703
2023-01-24 06:52:12.534206: step: 968/526, loss: 0.026355665177106857
2023-01-24 06:52:13.622907: step: 972/526, loss: 0.005978655070066452
2023-01-24 06:52:14.686501: step: 976/526, loss: 0.024148106575012207
2023-01-24 06:52:15.746020: step: 980/526, loss: 0.012789415195584297
2023-01-24 06:52:16.817033: step: 984/526, loss: 0.008457096293568611
2023-01-24 06:52:17.874566: step: 988/526, loss: 0.0015296322526410222
2023-01-24 06:52:18.938403: step: 992/526, loss: 0.006805008742958307
2023-01-24 06:52:20.002941: step: 996/526, loss: 0.0014696972211822867
2023-01-24 06:52:21.072952: step: 1000/526, loss: 0.004566519986838102
2023-01-24 06:52:22.157246: step: 1004/526, loss: 0.00858213659375906
2023-01-24 06:52:23.219797: step: 1008/526, loss: 0.019987408071756363
2023-01-24 06:52:24.282267: step: 1012/526, loss: 0.008939806371927261
2023-01-24 06:52:25.345700: step: 1016/526, loss: 0.009215113706886768
2023-01-24 06:52:26.424801: step: 1020/526, loss: 0.0041547357104718685
2023-01-24 06:52:27.494132: step: 1024/526, loss: 0.00252532004378736
2023-01-24 06:52:28.556188: step: 1028/526, loss: 0.008638842962682247
2023-01-24 06:52:29.618344: step: 1032/526, loss: 0.0027806328143924475
2023-01-24 06:52:30.679354: step: 1036/526, loss: 0.0036902576684951782
2023-01-24 06:52:31.737898: step: 1040/526, loss: 0.00746373925358057
2023-01-24 06:52:32.798590: step: 1044/526, loss: 0.0027634340804070234
2023-01-24 06:52:33.877448: step: 1048/526, loss: 0.05988109111785889
2023-01-24 06:52:34.937488: step: 1052/526, loss: 0.009773884899914265
2023-01-24 06:52:36.007077: step: 1056/526, loss: 0.009274709969758987
2023-01-24 06:52:37.100173: step: 1060/526, loss: 0.008162522688508034
2023-01-24 06:52:38.172191: step: 1064/526, loss: 0.0061418358236551285
2023-01-24 06:52:39.232062: step: 1068/526, loss: 0.0016014976426959038
2023-01-24 06:52:40.276814: step: 1072/526, loss: 0.0014428264694288373
2023-01-24 06:52:41.369656: step: 1076/526, loss: 0.006895169150084257
2023-01-24 06:52:42.434451: step: 1080/526, loss: 0.004000116139650345
2023-01-24 06:52:43.493711: step: 1084/526, loss: 0.008304869756102562
2023-01-24 06:52:44.548978: step: 1088/526, loss: 0.006547779776155949
2023-01-24 06:52:45.614063: step: 1092/526, loss: 0.017215324565768242
2023-01-24 06:52:46.693836: step: 1096/526, loss: 0.010768868029117584
2023-01-24 06:52:47.755335: step: 1100/526, loss: 0.003673287807032466
2023-01-24 06:52:48.828847: step: 1104/526, loss: 0.006040376611053944
2023-01-24 06:52:49.907690: step: 1108/526, loss: 0.008560117334127426
2023-01-24 06:52:50.978748: step: 1112/526, loss: 0.007589159067720175
2023-01-24 06:52:52.052017: step: 1116/526, loss: 0.024056492373347282
2023-01-24 06:52:53.112215: step: 1120/526, loss: 0.0018451682990416884
2023-01-24 06:52:54.170071: step: 1124/526, loss: 0.03260701522231102
2023-01-24 06:52:55.223601: step: 1128/526, loss: 0.00204491033218801
2023-01-24 06:52:56.300949: step: 1132/526, loss: 0.0033616709988564253
2023-01-24 06:52:57.365590: step: 1136/526, loss: 0.007189306430518627
2023-01-24 06:52:58.449798: step: 1140/526, loss: 0.00677073560655117
2023-01-24 06:52:59.519227: step: 1144/526, loss: 0.03640957176685333
2023-01-24 06:53:00.591892: step: 1148/526, loss: 0.011349931359291077
2023-01-24 06:53:01.652480: step: 1152/526, loss: 0.009325725957751274
2023-01-24 06:53:02.720696: step: 1156/526, loss: 0.014557684771716595
2023-01-24 06:53:03.781721: step: 1160/526, loss: 0.009800802916288376
2023-01-24 06:53:04.849937: step: 1164/526, loss: 0.004345850553363562
2023-01-24 06:53:05.924857: step: 1168/526, loss: 0.026662593707442284
2023-01-24 06:53:06.991783: step: 1172/526, loss: 0.03165102377533913
2023-01-24 06:53:08.052866: step: 1176/526, loss: 0.004347292240709066
2023-01-24 06:53:09.144106: step: 1180/526, loss: 0.03501264750957489
2023-01-24 06:53:10.209454: step: 1184/526, loss: 0.011472995392978191
2023-01-24 06:53:11.269535: step: 1188/526, loss: 0.006443241611123085
2023-01-24 06:53:12.315927: step: 1192/526, loss: 0.014392136596143246
2023-01-24 06:53:13.405907: step: 1196/526, loss: 0.006001131609082222
2023-01-24 06:53:14.474039: step: 1200/526, loss: 0.008973582647740841
2023-01-24 06:53:15.561710: step: 1204/526, loss: 0.018911825492978096
2023-01-24 06:53:16.631599: step: 1208/526, loss: 0.008818590082228184
2023-01-24 06:53:17.692110: step: 1212/526, loss: 0.005954004358500242
2023-01-24 06:53:18.750779: step: 1216/526, loss: 0.003068016143515706
2023-01-24 06:53:19.810232: step: 1220/526, loss: 0.0067404573783278465
2023-01-24 06:53:20.879676: step: 1224/526, loss: 0.009271468035876751
2023-01-24 06:53:21.953223: step: 1228/526, loss: 0.00014476769138127565
2023-01-24 06:53:23.023034: step: 1232/526, loss: 0.000542073103133589
2023-01-24 06:53:24.097827: step: 1236/526, loss: 0.002124140737578273
2023-01-24 06:53:25.151694: step: 1240/526, loss: 0.005091676954180002
2023-01-24 06:53:26.214762: step: 1244/526, loss: 0.006924670655280352
2023-01-24 06:53:27.278033: step: 1248/526, loss: 0.01914382353425026
2023-01-24 06:53:28.329804: step: 1252/526, loss: 0.010995729826390743
2023-01-24 06:53:29.408823: step: 1256/526, loss: 0.004292840138077736
2023-01-24 06:53:30.491130: step: 1260/526, loss: 0.003048386424779892
2023-01-24 06:53:31.550853: step: 1264/526, loss: 0.0044347262009978294
2023-01-24 06:53:32.618394: step: 1268/526, loss: 0.012820238247513771
2023-01-24 06:53:33.677921: step: 1272/526, loss: 0.00520427105948329
2023-01-24 06:53:34.733505: step: 1276/526, loss: 0.000263952708337456
2023-01-24 06:53:35.805344: step: 1280/526, loss: 0.0015274424804374576
2023-01-24 06:53:36.900300: step: 1284/526, loss: 0.0005827751010656357
2023-01-24 06:53:37.978903: step: 1288/526, loss: 0.011152703315019608
2023-01-24 06:53:39.069096: step: 1292/526, loss: 0.02018805406987667
2023-01-24 06:53:40.141766: step: 1296/526, loss: 0.0033085145987570286
2023-01-24 06:53:41.215742: step: 1300/526, loss: 0.004105363041162491
2023-01-24 06:53:42.278730: step: 1304/526, loss: 0.003182013053447008
2023-01-24 06:53:43.335537: step: 1308/526, loss: 0.0524308942258358
2023-01-24 06:53:44.437979: step: 1312/526, loss: 0.024237370118498802
2023-01-24 06:53:45.500150: step: 1316/526, loss: 0.00324096716940403
2023-01-24 06:53:46.562294: step: 1320/526, loss: 7.782007742207497e-05
2023-01-24 06:53:47.629614: step: 1324/526, loss: 0.006855267100036144
2023-01-24 06:53:48.698819: step: 1328/526, loss: 0.0
2023-01-24 06:53:49.753607: step: 1332/526, loss: 0.011863539926707745
2023-01-24 06:53:50.838482: step: 1336/526, loss: 0.007088163401931524
2023-01-24 06:53:51.905019: step: 1340/526, loss: 0.011153963394463062
2023-01-24 06:53:52.955088: step: 1344/526, loss: 0.008860246278345585
2023-01-24 06:53:54.022184: step: 1348/526, loss: 0.0036861076951026917
2023-01-24 06:53:55.100471: step: 1352/526, loss: 0.010988442227244377
2023-01-24 06:53:56.160212: step: 1356/526, loss: 0.012536215595901012
2023-01-24 06:53:57.224975: step: 1360/526, loss: 0.0062779588624835014
2023-01-24 06:53:58.278001: step: 1364/526, loss: 0.003220032202079892
2023-01-24 06:53:59.338916: step: 1368/526, loss: 0.018705377355217934
2023-01-24 06:54:00.405654: step: 1372/526, loss: 0.0033201919868588448
2023-01-24 06:54:01.487139: step: 1376/526, loss: 0.002651113783940673
2023-01-24 06:54:02.544411: step: 1380/526, loss: 0.003597776172682643
2023-01-24 06:54:03.591103: step: 1384/526, loss: 0.0337894968688488
2023-01-24 06:54:04.660023: step: 1388/526, loss: 0.009352417662739754
2023-01-24 06:54:05.724303: step: 1392/526, loss: 0.014289254322648048
2023-01-24 06:54:06.791360: step: 1396/526, loss: 0.006687379442155361
2023-01-24 06:54:07.845448: step: 1400/526, loss: 0.03225626051425934
2023-01-24 06:54:08.921008: step: 1404/526, loss: 0.009241082705557346
2023-01-24 06:54:10.008368: step: 1408/526, loss: 0.013390500098466873
2023-01-24 06:54:11.085486: step: 1412/526, loss: 0.048898614943027496
2023-01-24 06:54:12.140906: step: 1416/526, loss: 0.03494878113269806
2023-01-24 06:54:13.193687: step: 1420/526, loss: 0.011786588467657566
2023-01-24 06:54:14.284451: step: 1424/526, loss: 0.003117185551673174
2023-01-24 06:54:15.351900: step: 1428/526, loss: 0.025984065607190132
2023-01-24 06:54:16.421477: step: 1432/526, loss: 0.0054995352402329445
2023-01-24 06:54:17.489654: step: 1436/526, loss: 0.004419961012899876
2023-01-24 06:54:18.571341: step: 1440/526, loss: 0.009918817318975925
2023-01-24 06:54:19.623983: step: 1444/526, loss: 0.040321722626686096
2023-01-24 06:54:20.687162: step: 1448/526, loss: 0.009533429518342018
2023-01-24 06:54:21.755240: step: 1452/526, loss: 0.001707096816971898
2023-01-24 06:54:22.819134: step: 1456/526, loss: 0.009042011573910713
2023-01-24 06:54:23.885371: step: 1460/526, loss: 0.011686024256050587
2023-01-24 06:54:24.952629: step: 1464/526, loss: 0.009117784909904003
2023-01-24 06:54:26.024361: step: 1468/526, loss: 0.0022855165880173445
2023-01-24 06:54:27.118344: step: 1472/526, loss: 0.006800004281103611
2023-01-24 06:54:28.181030: step: 1476/526, loss: 0.0025610551238059998
2023-01-24 06:54:29.240289: step: 1480/526, loss: 0.00568034965544939
2023-01-24 06:54:30.294730: step: 1484/526, loss: 0.0033750650472939014
2023-01-24 06:54:31.344589: step: 1488/526, loss: 0.006656867917627096
2023-01-24 06:54:32.416863: step: 1492/526, loss: 0.010373681783676147
2023-01-24 06:54:33.478104: step: 1496/526, loss: 0.013088964857161045
2023-01-24 06:54:34.540772: step: 1500/526, loss: 0.005912484135478735
2023-01-24 06:54:35.622073: step: 1504/526, loss: 0.006564716808497906
2023-01-24 06:54:36.697319: step: 1508/526, loss: 0.03038611263036728
2023-01-24 06:54:37.756687: step: 1512/526, loss: 0.004240270704030991
2023-01-24 06:54:38.815245: step: 1516/526, loss: 0.020026564598083496
2023-01-24 06:54:39.906200: step: 1520/526, loss: 0.005455078557133675
2023-01-24 06:54:40.979737: step: 1524/526, loss: 0.009953298605978489
2023-01-24 06:54:42.050864: step: 1528/526, loss: 0.009301455691456795
2023-01-24 06:54:43.148147: step: 1532/526, loss: 0.0074359881691634655
2023-01-24 06:54:44.222717: step: 1536/526, loss: 0.045385610312223434
2023-01-24 06:54:45.271649: step: 1540/526, loss: 0.012754186987876892
2023-01-24 06:54:46.346697: step: 1544/526, loss: 0.0032758621964603662
2023-01-24 06:54:47.417977: step: 1548/526, loss: 0.010862481780350208
2023-01-24 06:54:48.486889: step: 1552/526, loss: 0.03498229756951332
2023-01-24 06:54:49.546363: step: 1556/526, loss: 0.00948853138834238
2023-01-24 06:54:50.599081: step: 1560/526, loss: 0.005905711092054844
2023-01-24 06:54:51.656835: step: 1564/526, loss: 0.036922141909599304
2023-01-24 06:54:52.730359: step: 1568/526, loss: 0.010879021137952805
2023-01-24 06:54:53.783992: step: 1572/526, loss: 0.01162551250308752
2023-01-24 06:54:54.846674: step: 1576/526, loss: 0.003965223673731089
2023-01-24 06:54:55.920745: step: 1580/526, loss: 0.004534436855465174
2023-01-24 06:54:56.978188: step: 1584/526, loss: 0.014405800960958004
2023-01-24 06:54:58.036533: step: 1588/526, loss: 0.006816651206463575
2023-01-24 06:54:59.096286: step: 1592/526, loss: 0.0028753068763762712
2023-01-24 06:55:00.162559: step: 1596/526, loss: 0.007793857250362635
2023-01-24 06:55:01.230503: step: 1600/526, loss: 0.014219994656741619
2023-01-24 06:55:02.281997: step: 1604/526, loss: 0.021587563678622246
2023-01-24 06:55:03.355694: step: 1608/526, loss: 0.014752312563359737
2023-01-24 06:55:04.429345: step: 1612/526, loss: 0.0066559696570038795
2023-01-24 06:55:05.496545: step: 1616/526, loss: 0.009911958128213882
2023-01-24 06:55:06.578677: step: 1620/526, loss: 0.005569026339799166
2023-01-24 06:55:07.639503: step: 1624/526, loss: 0.008063066750764847
2023-01-24 06:55:08.692857: step: 1628/526, loss: 0.009966726414859295
2023-01-24 06:55:09.770848: step: 1632/526, loss: 0.005356654059141874
2023-01-24 06:55:10.830152: step: 1636/526, loss: 0.003811662783846259
2023-01-24 06:55:11.909489: step: 1640/526, loss: 0.0017620675498619676
2023-01-24 06:55:12.986737: step: 1644/526, loss: 0.0027516367845237255
2023-01-24 06:55:14.048877: step: 1648/526, loss: 0.0026889985892921686
2023-01-24 06:55:15.120458: step: 1652/526, loss: 0.012888060882687569
2023-01-24 06:55:16.177701: step: 1656/526, loss: 0.009739807806909084
2023-01-24 06:55:17.249591: step: 1660/526, loss: 0.18117985129356384
2023-01-24 06:55:18.310982: step: 1664/526, loss: 0.0027895020321011543
2023-01-24 06:55:19.367245: step: 1668/526, loss: 0.020923787727952003
2023-01-24 06:55:20.436229: step: 1672/526, loss: 0.040421612560749054
2023-01-24 06:55:21.500042: step: 1676/526, loss: 0.052533335983753204
2023-01-24 06:55:22.564478: step: 1680/526, loss: 0.005521412938833237
2023-01-24 06:55:23.639258: step: 1684/526, loss: 0.0008487410959787667
2023-01-24 06:55:24.714404: step: 1688/526, loss: 0.006765359081327915
2023-01-24 06:55:25.784777: step: 1692/526, loss: 0.0014767349930480123
2023-01-24 06:55:26.871118: step: 1696/526, loss: 0.04667261987924576
2023-01-24 06:55:27.954788: step: 1700/526, loss: 0.08534608781337738
2023-01-24 06:55:29.039844: step: 1704/526, loss: 0.004594265483319759
2023-01-24 06:55:30.101459: step: 1708/526, loss: 0.005243775900453329
2023-01-24 06:55:31.171515: step: 1712/526, loss: 0.00753947626799345
2023-01-24 06:55:32.228730: step: 1716/526, loss: 0.005114629864692688
2023-01-24 06:55:33.287767: step: 1720/526, loss: 0.006579662673175335
2023-01-24 06:55:34.367713: step: 1724/526, loss: 0.019045347347855568
2023-01-24 06:55:35.442834: step: 1728/526, loss: 0.003987054340541363
2023-01-24 06:55:36.517140: step: 1732/526, loss: 0.004686868283897638
2023-01-24 06:55:37.595973: step: 1736/526, loss: 0.029049349948763847
2023-01-24 06:55:38.663473: step: 1740/526, loss: 0.007744913455098867
2023-01-24 06:55:39.719116: step: 1744/526, loss: 0.006797657813876867
2023-01-24 06:55:40.781067: step: 1748/526, loss: 0.006971979979425669
2023-01-24 06:55:41.856846: step: 1752/526, loss: 0.016374295577406883
2023-01-24 06:55:42.908690: step: 1756/526, loss: 0.011435119435191154
2023-01-24 06:55:44.002894: step: 1760/526, loss: 0.007884442806243896
2023-01-24 06:55:45.069344: step: 1764/526, loss: 0.030283812433481216
2023-01-24 06:55:46.152022: step: 1768/526, loss: 0.010101406835019588
2023-01-24 06:55:47.213626: step: 1772/526, loss: 0.01943332329392433
2023-01-24 06:55:48.276692: step: 1776/526, loss: 0.020612303167581558
2023-01-24 06:55:49.344508: step: 1780/526, loss: 0.0027994103729724884
2023-01-24 06:55:50.419645: step: 1784/526, loss: 0.028179163113236427
2023-01-24 06:55:51.483731: step: 1788/526, loss: 0.0013047674437984824
2023-01-24 06:55:52.550819: step: 1792/526, loss: 0.004112100228667259
2023-01-24 06:55:53.618706: step: 1796/526, loss: 0.007697451859712601
2023-01-24 06:55:54.686054: step: 1800/526, loss: 0.026814941316843033
2023-01-24 06:55:55.745984: step: 1804/526, loss: 0.0
2023-01-24 06:55:56.825465: step: 1808/526, loss: 0.04936361312866211
2023-01-24 06:55:57.888923: step: 1812/526, loss: 0.004547793883830309
2023-01-24 06:55:58.962464: step: 1816/526, loss: 0.005128554534167051
2023-01-24 06:56:00.036139: step: 1820/526, loss: 0.005846178624778986
2023-01-24 06:56:01.108625: step: 1824/526, loss: 0.05496903881430626
2023-01-24 06:56:02.169348: step: 1828/526, loss: 0.0005155499093234539
2023-01-24 06:56:03.240313: step: 1832/526, loss: 0.007163556758314371
2023-01-24 06:56:04.320466: step: 1836/526, loss: 0.014238342642784119
2023-01-24 06:56:05.378740: step: 1840/526, loss: 0.0009088402730412781
2023-01-24 06:56:06.440583: step: 1844/526, loss: 0.010880879126489162
2023-01-24 06:56:07.513001: step: 1848/526, loss: 0.011659126728773117
2023-01-24 06:56:08.589177: step: 1852/526, loss: 0.003695074236020446
2023-01-24 06:56:09.653575: step: 1856/526, loss: 0.0075827776454389095
2023-01-24 06:56:10.739815: step: 1860/526, loss: 0.01746492087841034
2023-01-24 06:56:11.806783: step: 1864/526, loss: 0.0021194086875766516
2023-01-24 06:56:12.902535: step: 1868/526, loss: 0.016487963497638702
2023-01-24 06:56:13.957110: step: 1872/526, loss: 0.010434810072183609
2023-01-24 06:56:15.018407: step: 1876/526, loss: 0.003129052696749568
2023-01-24 06:56:16.091451: step: 1880/526, loss: 0.02115667052567005
2023-01-24 06:56:17.170650: step: 1884/526, loss: 0.006560357753187418
2023-01-24 06:56:18.230631: step: 1888/526, loss: 0.013516881503164768
2023-01-24 06:56:19.301614: step: 1892/526, loss: 0.0017213800456374884
2023-01-24 06:56:20.361895: step: 1896/526, loss: 0.005959602072834969
2023-01-24 06:56:21.443874: step: 1900/526, loss: 0.0611736923456192
2023-01-24 06:56:22.527510: step: 1904/526, loss: 0.029303476214408875
2023-01-24 06:56:23.602764: step: 1908/526, loss: 0.006181257776916027
2023-01-24 06:56:24.705472: step: 1912/526, loss: 0.0008349527488462627
2023-01-24 06:56:25.770609: step: 1916/526, loss: 0.006332958582788706
2023-01-24 06:56:26.816346: step: 1920/526, loss: 0.0026066889986395836
2023-01-24 06:56:27.906067: step: 1924/526, loss: 0.09447556734085083
2023-01-24 06:56:28.979631: step: 1928/526, loss: 0.00949473213404417
2023-01-24 06:56:30.051969: step: 1932/526, loss: 0.038961321115493774
2023-01-24 06:56:31.112407: step: 1936/526, loss: 0.02917501889169216
2023-01-24 06:56:32.183270: step: 1940/526, loss: 0.0060004303231835365
2023-01-24 06:56:33.255854: step: 1944/526, loss: 0.03455030173063278
2023-01-24 06:56:34.317389: step: 1948/526, loss: 0.024984188377857208
2023-01-24 06:56:35.385544: step: 1952/526, loss: 0.0010579327354207635
2023-01-24 06:56:36.451990: step: 1956/526, loss: 0.012575664557516575
2023-01-24 06:56:37.516955: step: 1960/526, loss: 0.039289750158786774
2023-01-24 06:56:38.575051: step: 1964/526, loss: 0.008157818578183651
2023-01-24 06:56:39.637382: step: 1968/526, loss: 0.0105209955945611
2023-01-24 06:56:40.713369: step: 1972/526, loss: 0.011319060809910297
2023-01-24 06:56:41.793798: step: 1976/526, loss: 0.003198441583663225
2023-01-24 06:56:42.909845: step: 1980/526, loss: 0.008319240994751453
2023-01-24 06:56:43.967388: step: 1984/526, loss: 0.007458826061338186
2023-01-24 06:56:45.020332: step: 1988/526, loss: 0.0017861765809357166
2023-01-24 06:56:46.097397: step: 1992/526, loss: 0.04923545941710472
2023-01-24 06:56:47.157607: step: 1996/526, loss: 0.0041978806257247925
2023-01-24 06:56:48.224866: step: 2000/526, loss: 0.002960208337754011
2023-01-24 06:56:49.325419: step: 2004/526, loss: 0.00424683652818203
2023-01-24 06:56:50.385398: step: 2008/526, loss: 0.0012761231046169996
2023-01-24 06:56:51.454058: step: 2012/526, loss: 0.031041881069540977
2023-01-24 06:56:52.531518: step: 2016/526, loss: 0.04580167308449745
2023-01-24 06:56:53.582040: step: 2020/526, loss: 0.002427198924124241
2023-01-24 06:56:54.644410: step: 2024/526, loss: 0.009471496567130089
2023-01-24 06:56:55.718682: step: 2028/526, loss: 0.02107635699212551
2023-01-24 06:56:56.779048: step: 2032/526, loss: 0.00196745409630239
2023-01-24 06:56:57.833587: step: 2036/526, loss: 0.004283446352928877
2023-01-24 06:56:58.909920: step: 2040/526, loss: 0.004115102346986532
2023-01-24 06:56:59.969791: step: 2044/526, loss: 0.008813424035906792
2023-01-24 06:57:01.057950: step: 2048/526, loss: 0.010435586795210838
2023-01-24 06:57:02.125432: step: 2052/526, loss: 0.008322176523506641
2023-01-24 06:57:03.187679: step: 2056/526, loss: 0.0054909116588532925
2023-01-24 06:57:04.256274: step: 2060/526, loss: 0.0046149869449436665
2023-01-24 06:57:05.323846: step: 2064/526, loss: 0.06510575860738754
2023-01-24 06:57:06.393736: step: 2068/526, loss: 0.009735976345837116
2023-01-24 06:57:07.462050: step: 2072/526, loss: 0.037499263882637024
2023-01-24 06:57:08.520913: step: 2076/526, loss: 0.037874024361371994
2023-01-24 06:57:09.615585: step: 2080/526, loss: 0.003954877145588398
2023-01-24 06:57:10.680645: step: 2084/526, loss: 0.011672727763652802
2023-01-24 06:57:11.745784: step: 2088/526, loss: 0.00925710890442133
2023-01-24 06:57:12.837000: step: 2092/526, loss: 0.03238888457417488
2023-01-24 06:57:13.898715: step: 2096/526, loss: 0.00904457550495863
2023-01-24 06:57:14.956561: step: 2100/526, loss: 0.006982952356338501
2023-01-24 06:57:16.025238: step: 2104/526, loss: 0.019799476489424706
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.342404455941255, 'r': 0.278081797235023, 'f1': 0.3069091249065071}, 'combined': 0.2261435657205842, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.352367677286742, 'r': 0.22405812965625407, 'f1': 0.2739323665707894}, 'combined': 0.14941765449315783, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32649812030075187, 'r': 0.2942819869883437, 'f1': 0.30955410607356715}, 'combined': 0.2280924992121021, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35624505505353804, 'r': 0.2604206761095854, 'f1': 0.3008877367735485}, 'combined': 0.1641205836946628, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3463146768515026, 'r': 0.31674321488126045, 'f1': 0.33086952277983006}, 'combined': 0.24379859573250634, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35883275567592754, 'r': 0.27872736465586684, 'f1': 0.31374769265588304}, 'combined': 0.1711351050850271, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 4}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336995843596059, 'r': 0.29380760368663594, 'f1': 0.31248558454663394}, 'combined': 0.23025253598173026, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597710279387254, 'r': 0.2590483064846998, 'f1': 0.30121255211465625}, 'combined': 0.1642977556989034, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 07:00:03.584277: step: 4/526, loss: 0.004179727286100388
2023-01-24 07:00:04.656561: step: 8/526, loss: 0.009753537364304066
2023-01-24 07:00:05.720097: step: 12/526, loss: 0.012803785502910614
2023-01-24 07:00:06.796337: step: 16/526, loss: 0.022175660356879234
2023-01-24 07:00:07.860116: step: 20/526, loss: 0.010767531581223011
2023-01-24 07:00:08.929613: step: 24/526, loss: 0.008397763594985008
2023-01-24 07:00:10.003217: step: 28/526, loss: 0.013322950340807438
2023-01-24 07:00:11.100394: step: 32/526, loss: 0.017810318619012833
2023-01-24 07:00:12.153425: step: 36/526, loss: 0.0019666124135255814
2023-01-24 07:00:13.218064: step: 40/526, loss: 0.0003568820538930595
2023-01-24 07:00:14.268352: step: 44/526, loss: 0.008955714292824268
2023-01-24 07:00:15.342984: step: 48/526, loss: 0.027219904586672783
2023-01-24 07:00:16.406651: step: 52/526, loss: 0.005599867086857557
2023-01-24 07:00:17.464384: step: 56/526, loss: 0.012424616143107414
2023-01-24 07:00:18.534010: step: 60/526, loss: 0.01338270679116249
2023-01-24 07:00:19.595751: step: 64/526, loss: 0.011990762315690517
2023-01-24 07:00:20.667229: step: 68/526, loss: 0.026391271501779556
2023-01-24 07:00:21.726377: step: 72/526, loss: 0.009049460291862488
2023-01-24 07:00:22.773678: step: 76/526, loss: 0.0063121626153588295
2023-01-24 07:00:23.836845: step: 80/526, loss: 0.01013687252998352
2023-01-24 07:00:24.917592: step: 84/526, loss: 0.007272184826433659
2023-01-24 07:00:26.003886: step: 88/526, loss: 0.005076649133116007
2023-01-24 07:00:27.087533: step: 92/526, loss: 0.006101812701672316
2023-01-24 07:00:28.145259: step: 96/526, loss: 0.0061790477484464645
2023-01-24 07:00:29.226505: step: 100/526, loss: 0.010714037343859673
2023-01-24 07:00:30.314099: step: 104/526, loss: 0.0031410446390509605
2023-01-24 07:00:31.387293: step: 108/526, loss: 0.010581405833363533
2023-01-24 07:00:32.452770: step: 112/526, loss: 0.005645041819661856
2023-01-24 07:00:33.525100: step: 116/526, loss: 0.011688296683132648
2023-01-24 07:00:34.620675: step: 120/526, loss: 0.008537991903722286
2023-01-24 07:00:35.678819: step: 124/526, loss: 0.003914898727089167
2023-01-24 07:00:36.749331: step: 128/526, loss: 0.019281161949038506
2023-01-24 07:00:37.818154: step: 132/526, loss: 0.009023968130350113
2023-01-24 07:00:38.904809: step: 136/526, loss: 0.019723786041140556
2023-01-24 07:00:39.972229: step: 140/526, loss: 0.0014853033935651183
2023-01-24 07:00:41.034964: step: 144/526, loss: 0.0001279439020436257
2023-01-24 07:00:42.121234: step: 148/526, loss: 0.0023864794056862593
2023-01-24 07:00:43.199566: step: 152/526, loss: 0.008895018137991428
2023-01-24 07:00:44.260640: step: 156/526, loss: 0.005564650055021048
2023-01-24 07:00:45.337813: step: 160/526, loss: 0.012530139647424221
2023-01-24 07:00:46.423127: step: 164/526, loss: 0.003924074117094278
2023-01-24 07:00:47.499726: step: 168/526, loss: 0.012075257487595081
2023-01-24 07:00:48.572124: step: 172/526, loss: 0.006730757653713226
2023-01-24 07:00:49.654953: step: 176/526, loss: 0.005005224607884884
2023-01-24 07:00:50.733667: step: 180/526, loss: 0.007279685698449612
2023-01-24 07:00:51.805087: step: 184/526, loss: 0.029033029451966286
2023-01-24 07:00:52.871775: step: 188/526, loss: 0.0035127755254507065
2023-01-24 07:00:53.946364: step: 192/526, loss: 0.018917713314294815
2023-01-24 07:00:55.021149: step: 196/526, loss: 0.0007094627362675965
2023-01-24 07:00:56.093846: step: 200/526, loss: 0.015020279213786125
2023-01-24 07:00:57.174105: step: 204/526, loss: 0.010218324139714241
2023-01-24 07:00:58.271000: step: 208/526, loss: 0.015337863937020302
2023-01-24 07:00:59.340542: step: 212/526, loss: 0.004920123610645533
2023-01-24 07:01:00.403600: step: 216/526, loss: 0.003300401382148266
2023-01-24 07:01:01.476204: step: 220/526, loss: 0.019213594496250153
2023-01-24 07:01:02.581387: step: 224/526, loss: 0.0035804021172225475
2023-01-24 07:01:03.657332: step: 228/526, loss: 0.00969106424599886
2023-01-24 07:01:04.726943: step: 232/526, loss: 0.013144612312316895
2023-01-24 07:01:05.799437: step: 236/526, loss: 0.0018158546881750226
2023-01-24 07:01:06.874405: step: 240/526, loss: 0.007170368451625109
2023-01-24 07:01:07.939198: step: 244/526, loss: 0.004397746175527573
2023-01-24 07:01:09.010642: step: 248/526, loss: 0.0020392145961523056
2023-01-24 07:01:10.101619: step: 252/526, loss: 0.017630061134696007
2023-01-24 07:01:11.162145: step: 256/526, loss: 0.005034159403294325
2023-01-24 07:01:12.232902: step: 260/526, loss: 0.012424739077687263
2023-01-24 07:01:13.327908: step: 264/526, loss: 0.00014680727326776832
2023-01-24 07:01:14.422637: step: 268/526, loss: 0.009586957283318043
2023-01-24 07:01:15.508826: step: 272/526, loss: 0.005599708762019873
2023-01-24 07:01:16.587247: step: 276/526, loss: 0.0
2023-01-24 07:01:17.673556: step: 280/526, loss: 0.0060498532839119434
2023-01-24 07:01:18.760605: step: 284/526, loss: 0.008151538670063019
2023-01-24 07:01:19.852789: step: 288/526, loss: 0.0022136939223855734
2023-01-24 07:01:20.934389: step: 292/526, loss: 0.006422633770853281
2023-01-24 07:01:21.998094: step: 296/526, loss: 0.01070362702012062
2023-01-24 07:01:23.078158: step: 300/526, loss: 0.016296258196234703
2023-01-24 07:01:24.152246: step: 304/526, loss: 0.015589741058647633
2023-01-24 07:01:25.227101: step: 308/526, loss: 0.011069845408201218
2023-01-24 07:01:26.306073: step: 312/526, loss: 0.008630359545350075
2023-01-24 07:01:27.378793: step: 316/526, loss: 0.02647574618458748
2023-01-24 07:01:28.443256: step: 320/526, loss: 0.014696372672915459
2023-01-24 07:01:29.533609: step: 324/526, loss: 0.005338984541594982
2023-01-24 07:01:30.606207: step: 328/526, loss: 0.032988324761390686
2023-01-24 07:01:31.719289: step: 332/526, loss: 0.0032164589501917362
2023-01-24 07:01:32.791944: step: 336/526, loss: 0.006383334752172232
2023-01-24 07:01:33.872344: step: 340/526, loss: 0.027826670557260513
2023-01-24 07:01:34.985028: step: 344/526, loss: 0.0038276338018476963
2023-01-24 07:01:36.072834: step: 348/526, loss: 0.005485524423420429
2023-01-24 07:01:37.134960: step: 352/526, loss: 0.021132487803697586
2023-01-24 07:01:38.201362: step: 356/526, loss: 0.021186646074056625
2023-01-24 07:01:39.267075: step: 360/526, loss: 0.00475958501920104
2023-01-24 07:01:40.350112: step: 364/526, loss: 0.006460696458816528
2023-01-24 07:01:41.426551: step: 368/526, loss: 0.008834296837449074
2023-01-24 07:01:42.505003: step: 372/526, loss: 0.021211925894021988
2023-01-24 07:01:43.583528: step: 376/526, loss: 0.07888615876436234
2023-01-24 07:01:44.663359: step: 380/526, loss: 0.004614879377186298
2023-01-24 07:01:45.758618: step: 384/526, loss: 0.005075387191027403
2023-01-24 07:01:46.826573: step: 388/526, loss: 0.022108184173703194
2023-01-24 07:01:47.905106: step: 392/526, loss: 0.0026717737782746553
2023-01-24 07:01:48.981992: step: 396/526, loss: 0.009287252090871334
2023-01-24 07:01:50.055665: step: 400/526, loss: 0.016370058059692383
2023-01-24 07:01:51.121515: step: 404/526, loss: 0.007083205506205559
2023-01-24 07:01:52.186959: step: 408/526, loss: 0.00928169209510088
2023-01-24 07:01:53.266908: step: 412/526, loss: 0.00436942745000124
2023-01-24 07:01:54.335598: step: 416/526, loss: 0.01769758202135563
2023-01-24 07:01:55.400851: step: 420/526, loss: 0.001189651433378458
2023-01-24 07:01:56.472220: step: 424/526, loss: 0.01525026559829712
2023-01-24 07:01:57.541957: step: 428/526, loss: 0.00677567208185792
2023-01-24 07:01:58.594202: step: 432/526, loss: 0.020197875797748566
2023-01-24 07:01:59.682695: step: 436/526, loss: 0.0060077751986682415
2023-01-24 07:02:00.760487: step: 440/526, loss: 0.007549986243247986
2023-01-24 07:02:01.829517: step: 444/526, loss: 0.002993487287312746
2023-01-24 07:02:02.901437: step: 448/526, loss: 0.05734114721417427
2023-01-24 07:02:03.962775: step: 452/526, loss: 0.003148432355374098
2023-01-24 07:02:05.054796: step: 456/526, loss: 0.006887455936521292
2023-01-24 07:02:06.119002: step: 460/526, loss: 0.004125951323658228
2023-01-24 07:02:07.206079: step: 464/526, loss: 0.010618254542350769
2023-01-24 07:02:08.262560: step: 468/526, loss: 0.011702966876327991
2023-01-24 07:02:09.315349: step: 472/526, loss: 0.006534098647534847
2023-01-24 07:02:10.410736: step: 476/526, loss: 0.0038337104488164186
2023-01-24 07:02:11.466601: step: 480/526, loss: 0.0068637914955616
2023-01-24 07:02:12.537115: step: 484/526, loss: 0.0014776729512959719
2023-01-24 07:02:13.583093: step: 488/526, loss: 0.024531979113817215
2023-01-24 07:02:14.643269: step: 492/526, loss: 0.0010675002122297883
2023-01-24 07:02:15.711791: step: 496/526, loss: 0.004829818848520517
2023-01-24 07:02:16.791412: step: 500/526, loss: 0.017555639147758484
2023-01-24 07:02:17.867364: step: 504/526, loss: 0.0015893825329840183
2023-01-24 07:02:18.943080: step: 508/526, loss: 0.0165556650608778
2023-01-24 07:02:20.010007: step: 512/526, loss: 0.014914087019860744
2023-01-24 07:02:21.086595: step: 516/526, loss: 0.0004235340456943959
2023-01-24 07:02:22.145454: step: 520/526, loss: 0.004362288862466812
2023-01-24 07:02:23.192405: step: 524/526, loss: 0.003972609061747789
2023-01-24 07:02:24.265502: step: 528/526, loss: 0.008093221113085747
2023-01-24 07:02:25.315852: step: 532/526, loss: 0.005594367161393166
2023-01-24 07:02:26.409141: step: 536/526, loss: 0.013115398585796356
2023-01-24 07:02:27.491439: step: 540/526, loss: 0.002219150774180889
2023-01-24 07:02:28.569702: step: 544/526, loss: 0.0037508830428123474
2023-01-24 07:02:29.635603: step: 548/526, loss: 0.01808079145848751
2023-01-24 07:02:30.691133: step: 552/526, loss: 0.02747494913637638
2023-01-24 07:02:31.746445: step: 556/526, loss: 0.0013319260906428099
2023-01-24 07:02:32.808766: step: 560/526, loss: 0.003826683387160301
2023-01-24 07:02:33.868261: step: 564/526, loss: 0.0022062547504901886
2023-01-24 07:02:34.935041: step: 568/526, loss: 0.028814613819122314
2023-01-24 07:02:35.999156: step: 572/526, loss: 5.136105028213933e-05
2023-01-24 07:02:37.073743: step: 576/526, loss: 0.0
2023-01-24 07:02:38.133808: step: 580/526, loss: 0.0004023563815280795
2023-01-24 07:02:39.186598: step: 584/526, loss: 0.00519277760758996
2023-01-24 07:02:40.255357: step: 588/526, loss: 0.02121228538453579
2023-01-24 07:02:41.323324: step: 592/526, loss: 0.00031139684142544866
2023-01-24 07:02:42.400824: step: 596/526, loss: 0.007170545868575573
2023-01-24 07:02:43.475224: step: 600/526, loss: 0.05462522432208061
2023-01-24 07:02:44.545204: step: 604/526, loss: 0.006987426895648241
2023-01-24 07:02:45.607043: step: 608/526, loss: 0.015615695156157017
2023-01-24 07:02:46.675115: step: 612/526, loss: 0.008923091925680637
2023-01-24 07:02:47.739596: step: 616/526, loss: 0.014183570630848408
2023-01-24 07:02:48.811548: step: 620/526, loss: 0.00889973621815443
2023-01-24 07:02:49.912298: step: 624/526, loss: 0.02296479046344757
2023-01-24 07:02:51.015153: step: 628/526, loss: 0.04363659769296646
2023-01-24 07:02:52.075282: step: 632/526, loss: 0.002031927229836583
2023-01-24 07:02:53.150513: step: 636/526, loss: 0.007867912761867046
2023-01-24 07:02:54.222083: step: 640/526, loss: 0.01001647487282753
2023-01-24 07:02:55.305862: step: 644/526, loss: 0.03372461348772049
2023-01-24 07:02:56.373547: step: 648/526, loss: 0.030671315267682076
2023-01-24 07:02:57.446029: step: 652/526, loss: 0.004191583022475243
2023-01-24 07:02:58.517652: step: 656/526, loss: 0.0054128230549395084
2023-01-24 07:02:59.569196: step: 660/526, loss: 0.009346045553684235
2023-01-24 07:03:00.645625: step: 664/526, loss: 0.017420567572116852
2023-01-24 07:03:01.719795: step: 668/526, loss: 0.008749575354158878
2023-01-24 07:03:02.781880: step: 672/526, loss: 0.006593168713152409
2023-01-24 07:03:03.844008: step: 676/526, loss: 0.0041855741292238235
2023-01-24 07:03:04.900698: step: 680/526, loss: 0.0022743400186300278
2023-01-24 07:03:05.980168: step: 684/526, loss: 0.008821789175271988
2023-01-24 07:03:07.058528: step: 688/526, loss: 0.00741354376077652
2023-01-24 07:03:08.122475: step: 692/526, loss: 0.000775563414208591
2023-01-24 07:03:09.200267: step: 696/526, loss: 0.002990931738168001
2023-01-24 07:03:10.261627: step: 700/526, loss: 0.006738306023180485
2023-01-24 07:03:11.320197: step: 704/526, loss: 0.0076050241477787495
2023-01-24 07:03:12.378862: step: 708/526, loss: 0.000842511944938451
2023-01-24 07:03:13.443818: step: 712/526, loss: 0.007258014753460884
2023-01-24 07:03:14.504857: step: 716/526, loss: 0.004061924759298563
2023-01-24 07:03:15.579006: step: 720/526, loss: 0.01440152432769537
2023-01-24 07:03:16.644951: step: 724/526, loss: 0.004295687656849623
2023-01-24 07:03:17.707361: step: 728/526, loss: 0.029901940375566483
2023-01-24 07:03:18.769563: step: 732/526, loss: 0.011741629801690578
2023-01-24 07:03:19.839600: step: 736/526, loss: 0.015979982912540436
2023-01-24 07:03:20.886162: step: 740/526, loss: 0.003879495430737734
2023-01-24 07:03:21.955483: step: 744/526, loss: 0.0013728139456361532
2023-01-24 07:03:23.016408: step: 748/526, loss: 0.0025152782909572124
2023-01-24 07:03:24.100322: step: 752/526, loss: 0.00845578033477068
2023-01-24 07:03:25.178187: step: 756/526, loss: 0.015433473512530327
2023-01-24 07:03:26.247049: step: 760/526, loss: 0.012670719064772129
2023-01-24 07:03:27.311790: step: 764/526, loss: 0.013586791232228279
2023-01-24 07:03:28.371545: step: 768/526, loss: 0.004927001893520355
2023-01-24 07:03:29.462140: step: 772/526, loss: 0.005283229984343052
2023-01-24 07:03:30.551964: step: 776/526, loss: 0.002940341830253601
2023-01-24 07:03:31.612016: step: 780/526, loss: 0.017641184851527214
2023-01-24 07:03:32.689911: step: 784/526, loss: 0.015966741368174553
2023-01-24 07:03:33.736288: step: 788/526, loss: 1.613814129086677e-05
2023-01-24 07:03:34.806921: step: 792/526, loss: 0.014263163320720196
2023-01-24 07:03:35.884987: step: 796/526, loss: 0.0054789320565760136
2023-01-24 07:03:36.936738: step: 800/526, loss: 0.01663241907954216
2023-01-24 07:03:37.987948: step: 804/526, loss: 0.0024871286004781723
2023-01-24 07:03:39.063830: step: 808/526, loss: 0.0029280565213412046
2023-01-24 07:03:40.125063: step: 812/526, loss: 0.004747483879327774
2023-01-24 07:03:41.214460: step: 816/526, loss: 0.017158519476652145
2023-01-24 07:03:42.287419: step: 820/526, loss: 0.004833065904676914
2023-01-24 07:03:43.351221: step: 824/526, loss: 0.0025594686158001423
2023-01-24 07:03:44.456331: step: 828/526, loss: 0.004094590898603201
2023-01-24 07:03:45.524876: step: 832/526, loss: 0.00923250149935484
2023-01-24 07:03:46.621779: step: 836/526, loss: 0.006786765996366739
2023-01-24 07:03:47.710400: step: 840/526, loss: 0.020672639831900597
2023-01-24 07:03:48.777773: step: 844/526, loss: 0.037219345569610596
2023-01-24 07:03:49.869085: step: 848/526, loss: 0.0044114491902291775
2023-01-24 07:03:50.942828: step: 852/526, loss: 0.0033491034992039204
2023-01-24 07:03:52.026475: step: 856/526, loss: 0.005475528072565794
2023-01-24 07:03:53.077526: step: 860/526, loss: 0.09362396597862244
2023-01-24 07:03:54.130867: step: 864/526, loss: 0.004950490314513445
2023-01-24 07:03:55.192868: step: 868/526, loss: 0.039368707686662674
2023-01-24 07:03:56.264614: step: 872/526, loss: 0.008840540423989296
2023-01-24 07:03:57.312942: step: 876/526, loss: 0.0014541647396981716
2023-01-24 07:03:58.393986: step: 880/526, loss: 0.005111478269100189
2023-01-24 07:03:59.465764: step: 884/526, loss: 0.015759732574224472
2023-01-24 07:04:00.536188: step: 888/526, loss: 0.004627150017768145
2023-01-24 07:04:01.601150: step: 892/526, loss: 0.004093928728252649
2023-01-24 07:04:02.658196: step: 896/526, loss: 0.0012903203023597598
2023-01-24 07:04:03.751703: step: 900/526, loss: 0.005743737798184156
2023-01-24 07:04:04.826471: step: 904/526, loss: 0.002530170138925314
2023-01-24 07:04:05.884535: step: 908/526, loss: 0.0028703827410936356
2023-01-24 07:04:06.975949: step: 912/526, loss: 0.03889927640557289
2023-01-24 07:04:08.057136: step: 916/526, loss: 0.009523030370473862
2023-01-24 07:04:09.119123: step: 920/526, loss: 0.0016209364403039217
2023-01-24 07:04:10.181492: step: 924/526, loss: 0.02691265381872654
2023-01-24 07:04:11.255619: step: 928/526, loss: 0.004761083982884884
2023-01-24 07:04:12.325169: step: 932/526, loss: 0.0039682695642113686
2023-01-24 07:04:13.393599: step: 936/526, loss: 0.0037177246995270252
2023-01-24 07:04:14.468786: step: 940/526, loss: 0.020434020087122917
2023-01-24 07:04:15.540480: step: 944/526, loss: 0.025928188115358353
2023-01-24 07:04:16.602710: step: 948/526, loss: 0.006867233198136091
2023-01-24 07:04:17.667093: step: 952/526, loss: 0.005631602369248867
2023-01-24 07:04:18.761976: step: 956/526, loss: 0.022991664707660675
2023-01-24 07:04:19.826089: step: 960/526, loss: 0.011087313294410706
2023-01-24 07:04:20.899621: step: 964/526, loss: 0.06224283203482628
2023-01-24 07:04:21.982470: step: 968/526, loss: 0.012012952007353306
2023-01-24 07:04:23.047723: step: 972/526, loss: 0.03288606181740761
2023-01-24 07:04:24.107239: step: 976/526, loss: 0.011233695782721043
2023-01-24 07:04:25.173906: step: 980/526, loss: 0.014032876119017601
2023-01-24 07:04:26.246344: step: 984/526, loss: 0.0059246402233839035
2023-01-24 07:04:27.312064: step: 988/526, loss: 0.0023051395546644926
2023-01-24 07:04:28.392894: step: 992/526, loss: 0.011434398591518402
2023-01-24 07:04:29.465792: step: 996/526, loss: 0.00955211091786623
2023-01-24 07:04:30.539160: step: 1000/526, loss: 0.008953534997999668
2023-01-24 07:04:31.600577: step: 1004/526, loss: 0.0033022526185959578
2023-01-24 07:04:32.678170: step: 1008/526, loss: 0.0066132317297160625
2023-01-24 07:04:33.751093: step: 1012/526, loss: 0.00418096873909235
2023-01-24 07:04:34.844769: step: 1016/526, loss: 0.0013415899593383074
2023-01-24 07:04:35.913843: step: 1020/526, loss: 0.0038441969081759453
2023-01-24 07:04:36.981700: step: 1024/526, loss: 0.010874784551560879
2023-01-24 07:04:38.068377: step: 1028/526, loss: 0.00413973443210125
2023-01-24 07:04:39.130122: step: 1032/526, loss: 0.03429199382662773
2023-01-24 07:04:40.185045: step: 1036/526, loss: 0.007938297465443611
2023-01-24 07:04:41.258867: step: 1040/526, loss: 0.0060849254950881
2023-01-24 07:04:42.332091: step: 1044/526, loss: 0.009710460901260376
2023-01-24 07:04:43.401468: step: 1048/526, loss: 0.01117774099111557
2023-01-24 07:04:44.483754: step: 1052/526, loss: 0.0043641552329063416
2023-01-24 07:04:45.571273: step: 1056/526, loss: 0.028264088556170464
2023-01-24 07:04:46.636039: step: 1060/526, loss: 0.009676550514996052
2023-01-24 07:04:47.699231: step: 1064/526, loss: 0.005418520886451006
2023-01-24 07:04:48.761871: step: 1068/526, loss: 0.012382950633764267
2023-01-24 07:04:49.833971: step: 1072/526, loss: 0.01254848763346672
2023-01-24 07:04:50.901704: step: 1076/526, loss: 5.0700480642262846e-05
2023-01-24 07:04:51.973931: step: 1080/526, loss: 0.0033137549180537462
2023-01-24 07:04:53.057504: step: 1084/526, loss: 0.008108108304440975
2023-01-24 07:04:54.123583: step: 1088/526, loss: 0.014603527262806892
2023-01-24 07:04:55.208389: step: 1092/526, loss: 0.010312979109585285
2023-01-24 07:04:56.282489: step: 1096/526, loss: 0.005603244062513113
2023-01-24 07:04:57.351676: step: 1100/526, loss: 0.025438936427235603
2023-01-24 07:04:58.406391: step: 1104/526, loss: 0.0005932244821451604
2023-01-24 07:04:59.463925: step: 1108/526, loss: 0.026346363127231598
2023-01-24 07:05:00.524669: step: 1112/526, loss: 0.0018432587385177612
2023-01-24 07:05:01.590877: step: 1116/526, loss: 0.007865209132432938
2023-01-24 07:05:02.653384: step: 1120/526, loss: 0.014973930083215237
2023-01-24 07:05:03.735554: step: 1124/526, loss: 0.005887983366847038
2023-01-24 07:05:04.818516: step: 1128/526, loss: 0.0100959911942482
2023-01-24 07:05:05.888259: step: 1132/526, loss: 0.0026406978722661734
2023-01-24 07:05:06.989431: step: 1136/526, loss: 0.0018007908947765827
2023-01-24 07:05:08.070319: step: 1140/526, loss: 0.014743267558515072
2023-01-24 07:05:09.145994: step: 1144/526, loss: 0.004292478319257498
2023-01-24 07:05:10.230070: step: 1148/526, loss: 0.00288110482506454
2023-01-24 07:05:11.293249: step: 1152/526, loss: 0.015256117098033428
2023-01-24 07:05:12.373530: step: 1156/526, loss: 0.01817067340016365
2023-01-24 07:05:13.449822: step: 1160/526, loss: 4.900084968539886e-05
2023-01-24 07:05:14.527095: step: 1164/526, loss: 0.011496701277792454
2023-01-24 07:05:15.599091: step: 1168/526, loss: 0.0056101372465491295
2023-01-24 07:05:16.668942: step: 1172/526, loss: 0.016931403428316116
2023-01-24 07:05:17.762371: step: 1176/526, loss: 0.04071391746401787
2023-01-24 07:05:18.828951: step: 1180/526, loss: 0.0033191132824867964
2023-01-24 07:05:19.897430: step: 1184/526, loss: 0.021475009620189667
2023-01-24 07:05:20.978677: step: 1188/526, loss: 0.0073226201348006725
2023-01-24 07:05:22.040382: step: 1192/526, loss: 0.0016866996884346008
2023-01-24 07:05:23.108296: step: 1196/526, loss: 0.006712088827043772
2023-01-24 07:05:24.175161: step: 1200/526, loss: 0.020988360047340393
2023-01-24 07:05:25.252105: step: 1204/526, loss: 0.00301780691370368
2023-01-24 07:05:26.315628: step: 1208/526, loss: 0.0002655574062373489
2023-01-24 07:05:27.380190: step: 1212/526, loss: 0.004946304950863123
2023-01-24 07:05:28.446706: step: 1216/526, loss: 0.01819589175283909
2023-01-24 07:05:29.538909: step: 1220/526, loss: 0.06364208459854126
2023-01-24 07:05:30.617564: step: 1224/526, loss: 0.01923818141222
2023-01-24 07:05:31.703988: step: 1228/526, loss: 0.0029363848734647036
2023-01-24 07:05:32.777585: step: 1232/526, loss: 0.003072553314268589
2023-01-24 07:05:33.846733: step: 1236/526, loss: 0.00881422683596611
2023-01-24 07:05:34.914639: step: 1240/526, loss: 0.015196265652775764
2023-01-24 07:05:35.982386: step: 1244/526, loss: 0.00371684436686337
2023-01-24 07:05:37.043199: step: 1248/526, loss: 0.004852376878261566
2023-01-24 07:05:38.104344: step: 1252/526, loss: 0.016384728252887726
2023-01-24 07:05:39.180024: step: 1256/526, loss: 0.0049131265841424465
2023-01-24 07:05:40.260975: step: 1260/526, loss: 0.026592087000608444
2023-01-24 07:05:41.339618: step: 1264/526, loss: 0.0047128344886004925
2023-01-24 07:05:42.414223: step: 1268/526, loss: 0.04022995010018349
2023-01-24 07:05:43.492269: step: 1272/526, loss: 0.042646054178476334
2023-01-24 07:05:44.574634: step: 1276/526, loss: 0.005116072949022055
2023-01-24 07:05:45.645292: step: 1280/526, loss: 0.005358300171792507
2023-01-24 07:05:46.730137: step: 1284/526, loss: 0.0066224741749465466
2023-01-24 07:05:47.808588: step: 1288/526, loss: 0.02043723315000534
2023-01-24 07:05:48.887918: step: 1292/526, loss: 0.033883560448884964
2023-01-24 07:05:49.953499: step: 1296/526, loss: 0.04861082509160042
2023-01-24 07:05:51.037978: step: 1300/526, loss: 0.005043553188443184
2023-01-24 07:05:52.110552: step: 1304/526, loss: 0.014144033193588257
2023-01-24 07:05:53.189224: step: 1308/526, loss: 0.03527822718024254
2023-01-24 07:05:54.245668: step: 1312/526, loss: 0.015718458220362663
2023-01-24 07:05:55.325301: step: 1316/526, loss: 0.0011573919327929616
2023-01-24 07:05:56.401879: step: 1320/526, loss: 0.010420053265988827
2023-01-24 07:05:57.468724: step: 1324/526, loss: 0.008654913865029812
2023-01-24 07:05:58.535829: step: 1328/526, loss: 0.01659526489675045
2023-01-24 07:05:59.631566: step: 1332/526, loss: 0.007835150696337223
2023-01-24 07:06:00.710978: step: 1336/526, loss: 0.0
2023-01-24 07:06:01.778831: step: 1340/526, loss: 0.004185378551483154
2023-01-24 07:06:02.859044: step: 1344/526, loss: 0.0023382902145385742
2023-01-24 07:06:03.931064: step: 1348/526, loss: 0.0475771389901638
2023-01-24 07:06:04.997744: step: 1352/526, loss: 0.0010176255600526929
2023-01-24 07:06:06.060333: step: 1356/526, loss: 0.004088009241968393
2023-01-24 07:06:07.138733: step: 1360/526, loss: 0.0069541484117507935
2023-01-24 07:06:08.208161: step: 1364/526, loss: 0.0013889835681766272
2023-01-24 07:06:09.279697: step: 1368/526, loss: 0.030257955193519592
2023-01-24 07:06:10.362876: step: 1372/526, loss: 0.005183276254683733
2023-01-24 07:06:11.428805: step: 1376/526, loss: 0.04388915374875069
2023-01-24 07:06:12.502686: step: 1380/526, loss: 0.007960905320942402
2023-01-24 07:06:13.604702: step: 1384/526, loss: 0.015411360189318657
2023-01-24 07:06:14.701605: step: 1388/526, loss: 0.011983797885477543
2023-01-24 07:06:15.783947: step: 1392/526, loss: 0.0038152674678713083
2023-01-24 07:06:16.865715: step: 1396/526, loss: 0.0023523501586169004
2023-01-24 07:06:17.962912: step: 1400/526, loss: 0.009872794151306152
2023-01-24 07:06:19.047368: step: 1404/526, loss: 0.045891087502241135
2023-01-24 07:06:20.121824: step: 1408/526, loss: 0.0015547976363450289
2023-01-24 07:06:21.203189: step: 1412/526, loss: 0.004930392373353243
2023-01-24 07:06:22.276244: step: 1416/526, loss: 0.0009030046639963984
2023-01-24 07:06:23.342809: step: 1420/526, loss: 0.004493011627346277
2023-01-24 07:06:24.412908: step: 1424/526, loss: 0.04012685269117355
2023-01-24 07:06:25.498760: step: 1428/526, loss: 0.002666450571268797
2023-01-24 07:06:26.554555: step: 1432/526, loss: 0.004061040468513966
2023-01-24 07:06:27.625084: step: 1436/526, loss: 0.00790204294025898
2023-01-24 07:06:28.702231: step: 1440/526, loss: 0.007304815575480461
2023-01-24 07:06:29.782682: step: 1444/526, loss: 0.027478881180286407
2023-01-24 07:06:30.849226: step: 1448/526, loss: 0.003109800862148404
2023-01-24 07:06:31.932421: step: 1452/526, loss: 0.005814953241497278
2023-01-24 07:06:33.015013: step: 1456/526, loss: 0.03077506460249424
2023-01-24 07:06:34.084334: step: 1460/526, loss: 0.031066054478287697
2023-01-24 07:06:35.157102: step: 1464/526, loss: 0.004671929404139519
2023-01-24 07:06:36.246131: step: 1468/526, loss: 0.009432507678866386
2023-01-24 07:06:37.319560: step: 1472/526, loss: 0.004772165324538946
2023-01-24 07:06:38.395327: step: 1476/526, loss: 0.008943991735577583
2023-01-24 07:06:39.467613: step: 1480/526, loss: 0.022126391530036926
2023-01-24 07:06:40.540074: step: 1484/526, loss: 0.00010280396963935345
2023-01-24 07:06:41.608389: step: 1488/526, loss: 0.0018554840935394168
2023-01-24 07:06:42.687770: step: 1492/526, loss: 0.0035776132717728615
2023-01-24 07:06:43.752517: step: 1496/526, loss: 0.0030853047501295805
2023-01-24 07:06:44.828539: step: 1500/526, loss: 0.0024554000701755285
2023-01-24 07:06:45.911948: step: 1504/526, loss: 0.015467529185116291
2023-01-24 07:06:46.975403: step: 1508/526, loss: 0.01205506268888712
2023-01-24 07:06:48.043912: step: 1512/526, loss: 0.011453481391072273
2023-01-24 07:06:49.128079: step: 1516/526, loss: 0.02545788325369358
2023-01-24 07:06:50.201341: step: 1520/526, loss: 0.002958260476589203
2023-01-24 07:06:51.264542: step: 1524/526, loss: 0.01944192685186863
2023-01-24 07:06:52.329876: step: 1528/526, loss: 0.022666987031698227
2023-01-24 07:06:53.384837: step: 1532/526, loss: 0.028071008622646332
2023-01-24 07:06:54.445281: step: 1536/526, loss: 0.011643345467746258
2023-01-24 07:06:55.520236: step: 1540/526, loss: 0.005877944175153971
2023-01-24 07:06:56.584759: step: 1544/526, loss: 0.0032326069194823503
2023-01-24 07:06:57.656626: step: 1548/526, loss: 0.004629484377801418
2023-01-24 07:06:58.704262: step: 1552/526, loss: 0.0
2023-01-24 07:06:59.764369: step: 1556/526, loss: 0.007165815215557814
2023-01-24 07:07:00.833700: step: 1560/526, loss: 0.0036267568357288837
2023-01-24 07:07:01.904250: step: 1564/526, loss: 0.0032491059973835945
2023-01-24 07:07:02.984341: step: 1568/526, loss: 0.0034492635168135166
2023-01-24 07:07:04.053959: step: 1572/526, loss: 0.0032850925344973803
2023-01-24 07:07:05.120459: step: 1576/526, loss: 0.004286310635507107
2023-01-24 07:07:06.213245: step: 1580/526, loss: 0.004146732855588198
2023-01-24 07:07:07.291900: step: 1584/526, loss: 0.004961901810020208
2023-01-24 07:07:08.363610: step: 1588/526, loss: 0.000617970887105912
2023-01-24 07:07:09.434988: step: 1592/526, loss: 0.023812079802155495
2023-01-24 07:07:10.503789: step: 1596/526, loss: 0.009973493404686451
2023-01-24 07:07:11.559630: step: 1600/526, loss: 0.005224699154496193
2023-01-24 07:07:12.620046: step: 1604/526, loss: 0.013935333117842674
2023-01-24 07:07:13.693441: step: 1608/526, loss: 0.007755911909043789
2023-01-24 07:07:14.766514: step: 1612/526, loss: 0.009887021966278553
2023-01-24 07:07:15.823925: step: 1616/526, loss: 0.002896562684327364
2023-01-24 07:07:16.902687: step: 1620/526, loss: 0.00788772851228714
2023-01-24 07:07:18.001246: step: 1624/526, loss: 0.0056227995082736015
2023-01-24 07:07:19.078304: step: 1628/526, loss: 0.0067305234260857105
2023-01-24 07:07:20.148083: step: 1632/526, loss: 0.03223757445812225
2023-01-24 07:07:21.209735: step: 1636/526, loss: 0.01878163404762745
2023-01-24 07:07:22.298405: step: 1640/526, loss: 0.003956172615289688
2023-01-24 07:07:23.371205: step: 1644/526, loss: 0.006648341193795204
2023-01-24 07:07:24.441595: step: 1648/526, loss: 0.010734629817306995
2023-01-24 07:07:25.510212: step: 1652/526, loss: 0.006555869244039059
2023-01-24 07:07:26.583214: step: 1656/526, loss: 0.016228245571255684
2023-01-24 07:07:27.656077: step: 1660/526, loss: 0.015174386091530323
2023-01-24 07:07:28.709504: step: 1664/526, loss: 0.005016935057938099
2023-01-24 07:07:29.783907: step: 1668/526, loss: 0.008743592537939548
2023-01-24 07:07:30.857310: step: 1672/526, loss: 0.005999026820063591
2023-01-24 07:07:31.935056: step: 1676/526, loss: 0.0069392831064760685
2023-01-24 07:07:33.001034: step: 1680/526, loss: 0.00973892118781805
2023-01-24 07:07:34.052099: step: 1684/526, loss: 0.035884082317352295
2023-01-24 07:07:35.109485: step: 1688/526, loss: 0.0021622362546622753
2023-01-24 07:07:36.167028: step: 1692/526, loss: 0.005209111142903566
2023-01-24 07:07:37.238166: step: 1696/526, loss: 0.005372251849621534
2023-01-24 07:07:38.316465: step: 1700/526, loss: 0.0032869232818484306
2023-01-24 07:07:39.393873: step: 1704/526, loss: 0.020500414073467255
2023-01-24 07:07:40.438995: step: 1708/526, loss: 0.03416214883327484
2023-01-24 07:07:41.501148: step: 1712/526, loss: 0.0037869231309741735
2023-01-24 07:07:42.563673: step: 1716/526, loss: 0.009350288659334183
2023-01-24 07:07:43.641242: step: 1720/526, loss: 0.0017497781664133072
2023-01-24 07:07:44.716275: step: 1724/526, loss: 0.00040508943493478
2023-01-24 07:07:45.781589: step: 1728/526, loss: 0.016947848722338676
2023-01-24 07:07:46.855723: step: 1732/526, loss: 0.00021597662998829037
2023-01-24 07:07:47.914859: step: 1736/526, loss: 0.003410627832636237
2023-01-24 07:07:48.965232: step: 1740/526, loss: 0.0011602664599195123
2023-01-24 07:07:50.010926: step: 1744/526, loss: 0.005013324320316315
2023-01-24 07:07:51.087756: step: 1748/526, loss: 0.004208932165056467
2023-01-24 07:07:52.145916: step: 1752/526, loss: 0.01655876263976097
2023-01-24 07:07:53.204104: step: 1756/526, loss: 0.007851890288293362
2023-01-24 07:07:54.273479: step: 1760/526, loss: 0.18781514465808868
2023-01-24 07:07:55.340476: step: 1764/526, loss: 0.029294034466147423
2023-01-24 07:07:56.431629: step: 1768/526, loss: 0.015067586675286293
2023-01-24 07:07:57.498412: step: 1772/526, loss: 0.0035023908130824566
2023-01-24 07:07:58.565660: step: 1776/526, loss: 0.009105285629630089
2023-01-24 07:07:59.623842: step: 1780/526, loss: 0.0038787275552749634
2023-01-24 07:08:00.701709: step: 1784/526, loss: 0.006649780087172985
2023-01-24 07:08:01.776884: step: 1788/526, loss: 0.009858941659331322
2023-01-24 07:08:02.850896: step: 1792/526, loss: 0.001505280495621264
2023-01-24 07:08:03.932199: step: 1796/526, loss: 0.007555418182164431
2023-01-24 07:08:05.003720: step: 1800/526, loss: 0.0028510408010333776
2023-01-24 07:08:06.062880: step: 1804/526, loss: 0.0017563748406246305
2023-01-24 07:08:07.127234: step: 1808/526, loss: 0.001117513282224536
2023-01-24 07:08:08.206830: step: 1812/526, loss: 0.006782998330891132
2023-01-24 07:08:09.263415: step: 1816/526, loss: 0.0010308542987331748
2023-01-24 07:08:10.330503: step: 1820/526, loss: 0.009075156413018703
2023-01-24 07:08:11.398061: step: 1824/526, loss: 0.01912175677716732
2023-01-24 07:08:12.446260: step: 1828/526, loss: 0.013318387791514397
2023-01-24 07:08:13.513201: step: 1832/526, loss: 0.005430066492408514
2023-01-24 07:08:14.573800: step: 1836/526, loss: 0.0027415018994361162
2023-01-24 07:08:15.651285: step: 1840/526, loss: 0.03963654115796089
2023-01-24 07:08:16.715033: step: 1844/526, loss: 0.025179734453558922
2023-01-24 07:08:17.786026: step: 1848/526, loss: 0.0015749731101095676
2023-01-24 07:08:18.841185: step: 1852/526, loss: 0.012397871352732182
2023-01-24 07:08:19.905840: step: 1856/526, loss: 0.04175456240773201
2023-01-24 07:08:20.976947: step: 1860/526, loss: 0.006538006942719221
2023-01-24 07:08:22.052996: step: 1864/526, loss: 0.0031106697861105204
2023-01-24 07:08:23.107700: step: 1868/526, loss: 0.004724698141217232
2023-01-24 07:08:24.176554: step: 1872/526, loss: 0.012229977175593376
2023-01-24 07:08:25.246883: step: 1876/526, loss: 0.008140761405229568
2023-01-24 07:08:26.315554: step: 1880/526, loss: 0.0005193506949581206
2023-01-24 07:08:27.389166: step: 1884/526, loss: 0.015678822994232178
2023-01-24 07:08:28.458089: step: 1888/526, loss: 0.013109872117638588
2023-01-24 07:08:29.514441: step: 1892/526, loss: 0.007637638133019209
2023-01-24 07:08:30.579894: step: 1896/526, loss: 0.008921423926949501
2023-01-24 07:08:31.639544: step: 1900/526, loss: 0.00119243492372334
2023-01-24 07:08:32.707762: step: 1904/526, loss: 0.011440916918218136
2023-01-24 07:08:33.766486: step: 1908/526, loss: 0.011566330678761005
2023-01-24 07:08:34.825606: step: 1912/526, loss: 0.022982196882367134
2023-01-24 07:08:35.873641: step: 1916/526, loss: 0.020851679146289825
2023-01-24 07:08:36.963475: step: 1920/526, loss: 0.011146592907607555
2023-01-24 07:08:38.025489: step: 1924/526, loss: 0.0020736802835017443
2023-01-24 07:08:39.084245: step: 1928/526, loss: 0.0029388205148279667
2023-01-24 07:08:40.138978: step: 1932/526, loss: 0.007810981944203377
2023-01-24 07:08:41.203775: step: 1936/526, loss: 0.010792273096740246
2023-01-24 07:08:42.257165: step: 1940/526, loss: 0.009290199726819992
2023-01-24 07:08:43.326268: step: 1944/526, loss: 0.014095891267061234
2023-01-24 07:08:44.393748: step: 1948/526, loss: 0.018211590126156807
2023-01-24 07:08:45.477446: step: 1952/526, loss: 0.08417269587516785
2023-01-24 07:08:46.534398: step: 1956/526, loss: 0.003627112368121743
2023-01-24 07:08:47.609353: step: 1960/526, loss: 0.00410380307585001
2023-01-24 07:08:48.660683: step: 1964/526, loss: 0.003400822402909398
2023-01-24 07:08:49.730169: step: 1968/526, loss: 0.007164774928241968
2023-01-24 07:08:50.780043: step: 1972/526, loss: 0.006590539589524269
2023-01-24 07:08:51.832376: step: 1976/526, loss: 0.004770446568727493
2023-01-24 07:08:52.893336: step: 1980/526, loss: 0.0013130620354786515
2023-01-24 07:08:53.966223: step: 1984/526, loss: 0.006059564184397459
2023-01-24 07:08:55.019351: step: 1988/526, loss: 0.016506999731063843
2023-01-24 07:08:56.082865: step: 1992/526, loss: 0.003427164163440466
2023-01-24 07:08:57.150367: step: 1996/526, loss: 0.04940352216362953
2023-01-24 07:08:58.206814: step: 2000/526, loss: 0.002892750781029463
2023-01-24 07:08:59.278660: step: 2004/526, loss: 0.0016225673025473952
2023-01-24 07:09:00.347006: step: 2008/526, loss: 0.007531145587563515
2023-01-24 07:09:01.418496: step: 2012/526, loss: 0.008236940950155258
2023-01-24 07:09:02.490856: step: 2016/526, loss: 0.002024533925577998
2023-01-24 07:09:03.563071: step: 2020/526, loss: 0.007904056459665298
2023-01-24 07:09:04.633290: step: 2024/526, loss: 0.01853630505502224
2023-01-24 07:09:05.686060: step: 2028/526, loss: 0.0016017219750210643
2023-01-24 07:09:06.753192: step: 2032/526, loss: 0.006075717508792877
2023-01-24 07:09:07.834023: step: 2036/526, loss: 0.014267859980463982
2023-01-24 07:09:08.901284: step: 2040/526, loss: 0.000822831760160625
2023-01-24 07:09:09.971051: step: 2044/526, loss: 0.03987755998969078
2023-01-24 07:09:11.038393: step: 2048/526, loss: 0.003301649121567607
2023-01-24 07:09:12.118152: step: 2052/526, loss: 0.005291596986353397
2023-01-24 07:09:13.169499: step: 2056/526, loss: 0.010310320183634758
2023-01-24 07:09:14.237950: step: 2060/526, loss: 0.0006486689671874046
2023-01-24 07:09:15.309373: step: 2064/526, loss: 0.012938452884554863
2023-01-24 07:09:16.396767: step: 2068/526, loss: 0.027604874223470688
2023-01-24 07:09:17.456625: step: 2072/526, loss: 0.00320068234577775
2023-01-24 07:09:18.524141: step: 2076/526, loss: 0.006932328920811415
2023-01-24 07:09:19.594946: step: 2080/526, loss: 0.004462625365704298
2023-01-24 07:09:20.666814: step: 2084/526, loss: 0.005529774818569422
2023-01-24 07:09:21.734865: step: 2088/526, loss: 0.023342285305261612
2023-01-24 07:09:22.802349: step: 2092/526, loss: 0.03901619091629982
2023-01-24 07:09:23.855904: step: 2096/526, loss: 0.026070749387145042
2023-01-24 07:09:24.915227: step: 2100/526, loss: 0.00875986646860838
2023-01-24 07:09:25.986227: step: 2104/526, loss: 0.008785846643149853
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3653141952983725, 'r': 0.273812347519653, 'f1': 0.3130132475983886}, 'combined': 0.23064134033565475, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35557347388294525, 'r': 0.22154211867729706, 'f1': 0.2729938395876953}, 'combined': 0.14890573068419743, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3346282718385367, 'r': 0.2876406207644348, 'f1': 0.3093604227405247}, 'combined': 0.22794978517722872, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597478576672253, 'r': 0.26133558919284255, 'f1': 0.3027448849896946}, 'combined': 0.1651335736307425, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36290037471489084, 'r': 0.3202062129837272, 'f1': 0.3402191012952102}, 'combined': 0.25068775884910227, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36028761680970217, 'r': 0.27392407096876714, 'f1': 0.3112255816724142}, 'combined': 0.1697594081849532, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336995843596059, 'r': 0.29380760368663594, 'f1': 0.31248558454663394}, 'combined': 0.23025253598173026, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3597710279387254, 'r': 0.2590483064846998, 'f1': 0.30121255211465625}, 'combined': 0.1642977556989034, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 07:12:06.676616: step: 4/526, loss: 0.03056020848453045
2023-01-24 07:12:07.722045: step: 8/526, loss: 0.005550703965127468
2023-01-24 07:12:08.788534: step: 12/526, loss: 0.007741289678961039
2023-01-24 07:12:09.857913: step: 16/526, loss: 0.07527825981378555
2023-01-24 07:12:10.926404: step: 20/526, loss: 0.004757534712553024
2023-01-24 07:12:11.992836: step: 24/526, loss: 0.0036126484628766775
2023-01-24 07:12:13.068893: step: 28/526, loss: 0.005891560576856136
2023-01-24 07:12:14.140498: step: 32/526, loss: 0.01705353893339634
2023-01-24 07:12:15.209499: step: 36/526, loss: 0.009754710830748081
2023-01-24 07:12:16.268006: step: 40/526, loss: 0.02737494930624962
2023-01-24 07:12:17.331165: step: 44/526, loss: 0.0036318402271717787
2023-01-24 07:12:18.390985: step: 48/526, loss: 0.0021759348455816507
2023-01-24 07:12:19.444528: step: 52/526, loss: 0.01103932224214077
2023-01-24 07:12:20.514640: step: 56/526, loss: 0.007948559708893299
2023-01-24 07:12:21.587126: step: 60/526, loss: 0.009094356559216976
2023-01-24 07:12:22.676409: step: 64/526, loss: 0.008030201308429241
2023-01-24 07:12:23.746220: step: 68/526, loss: 0.007121507078409195
2023-01-24 07:12:24.806247: step: 72/526, loss: 0.0044227358885109425
2023-01-24 07:12:25.888171: step: 76/526, loss: 0.007090034894645214
2023-01-24 07:12:26.948165: step: 80/526, loss: 0.0025880110915750265
2023-01-24 07:12:28.028625: step: 84/526, loss: 0.013140284456312656
2023-01-24 07:12:29.096616: step: 88/526, loss: 0.010930776596069336
2023-01-24 07:12:30.166044: step: 92/526, loss: 0.00831281952559948
2023-01-24 07:12:31.228159: step: 96/526, loss: 0.003119352040812373
2023-01-24 07:12:32.298828: step: 100/526, loss: 0.015038120560348034
2023-01-24 07:12:33.367596: step: 104/526, loss: 0.004123392049223185
2023-01-24 07:12:34.451543: step: 108/526, loss: 0.005310199223458767
2023-01-24 07:12:35.531065: step: 112/526, loss: 0.0037086547818034887
2023-01-24 07:12:36.593394: step: 116/526, loss: 0.01209168415516615
2023-01-24 07:12:37.657695: step: 120/526, loss: 0.00614965008571744
2023-01-24 07:12:38.725732: step: 124/526, loss: 0.022402137517929077
2023-01-24 07:12:39.788749: step: 128/526, loss: 0.015202345326542854
2023-01-24 07:12:40.846147: step: 132/526, loss: 0.004186494275927544
2023-01-24 07:12:41.924205: step: 136/526, loss: 0.014832055196166039
2023-01-24 07:12:42.995383: step: 140/526, loss: 0.007426561322063208
2023-01-24 07:12:44.081703: step: 144/526, loss: 0.00980204064399004
2023-01-24 07:12:45.154725: step: 148/526, loss: 0.006996991112828255
2023-01-24 07:12:46.206860: step: 152/526, loss: 0.004004724323749542
2023-01-24 07:12:47.275892: step: 156/526, loss: 0.007940438576042652
2023-01-24 07:12:48.342517: step: 160/526, loss: 0.008022377267479897
2023-01-24 07:12:49.411640: step: 164/526, loss: 0.002451209584251046
2023-01-24 07:12:50.466716: step: 168/526, loss: 0.008931722491979599
2023-01-24 07:12:51.549487: step: 172/526, loss: 0.002556374529376626
2023-01-24 07:12:52.638145: step: 176/526, loss: 0.015206307172775269
2023-01-24 07:12:53.710273: step: 180/526, loss: 0.013622324913740158
2023-01-24 07:12:54.778699: step: 184/526, loss: 0.005480619613081217
2023-01-24 07:12:55.844414: step: 188/526, loss: 0.0
2023-01-24 07:12:56.922019: step: 192/526, loss: 0.0005863471305929124
2023-01-24 07:12:58.007950: step: 196/526, loss: 0.027543986216187477
2023-01-24 07:12:59.096674: step: 200/526, loss: 0.00865589827299118
2023-01-24 07:13:00.182966: step: 204/526, loss: 0.0020030769519507885
2023-01-24 07:13:01.248648: step: 208/526, loss: 0.009460987523198128
2023-01-24 07:13:02.303635: step: 212/526, loss: 0.003951487131416798
2023-01-24 07:13:03.386756: step: 216/526, loss: 0.004548159893602133
2023-01-24 07:13:04.476230: step: 220/526, loss: 0.006977055687457323
2023-01-24 07:13:05.546439: step: 224/526, loss: 0.006539938040077686
2023-01-24 07:13:06.611995: step: 228/526, loss: 0.01938641257584095
2023-01-24 07:13:07.695098: step: 232/526, loss: 0.024029238149523735
2023-01-24 07:13:08.765678: step: 236/526, loss: 0.0006959624006412923
2023-01-24 07:13:09.824209: step: 240/526, loss: 0.004568490665405989
2023-01-24 07:13:10.899120: step: 244/526, loss: 0.0032213397789746523
2023-01-24 07:13:11.958364: step: 248/526, loss: 0.0056900824420154095
2023-01-24 07:13:13.028858: step: 252/526, loss: 0.01235982496291399
2023-01-24 07:13:14.129820: step: 256/526, loss: 0.003292555920779705
2023-01-24 07:13:15.201250: step: 260/526, loss: 0.0020116984378546476
2023-01-24 07:13:16.275927: step: 264/526, loss: 0.004956017713993788
2023-01-24 07:13:17.336180: step: 268/526, loss: 0.004580358974635601
2023-01-24 07:13:18.421367: step: 272/526, loss: 0.009182633832097054
2023-01-24 07:13:19.489123: step: 276/526, loss: 0.0059911152347922325
2023-01-24 07:13:20.577320: step: 280/526, loss: 0.014766387641429901
2023-01-24 07:13:21.652911: step: 284/526, loss: 0.0010674602817744017
2023-01-24 07:13:22.736633: step: 288/526, loss: 0.010107072070240974
2023-01-24 07:13:23.809592: step: 292/526, loss: 0.008091469295322895
2023-01-24 07:13:24.883510: step: 296/526, loss: 0.00393038522452116
2023-01-24 07:13:25.964207: step: 300/526, loss: 0.0021983629558235407
2023-01-24 07:13:27.033482: step: 304/526, loss: 0.009886692278087139
2023-01-24 07:13:28.110689: step: 308/526, loss: 0.034597739577293396
2023-01-24 07:13:29.182382: step: 312/526, loss: 0.020144330337643623
2023-01-24 07:13:30.247097: step: 316/526, loss: 0.008640216663479805
2023-01-24 07:13:31.314463: step: 320/526, loss: 0.0056711360812187195
2023-01-24 07:13:32.400246: step: 324/526, loss: 0.004932489711791277
2023-01-24 07:13:33.474050: step: 328/526, loss: 0.0008659413433633745
2023-01-24 07:13:34.548412: step: 332/526, loss: 0.00555976340547204
2023-01-24 07:13:35.630716: step: 336/526, loss: 0.006461212877184153
2023-01-24 07:13:36.735596: step: 340/526, loss: 0.007345697842538357
2023-01-24 07:13:37.814863: step: 344/526, loss: 0.0035378271713852882
2023-01-24 07:13:38.915234: step: 348/526, loss: 0.0037171063013374805
2023-01-24 07:13:39.982190: step: 352/526, loss: 0.007670004386454821
2023-01-24 07:13:41.053066: step: 356/526, loss: 0.008089261129498482
2023-01-24 07:13:42.142526: step: 360/526, loss: 0.008118961937725544
2023-01-24 07:13:43.235290: step: 364/526, loss: 0.014272321946918964
2023-01-24 07:13:44.318349: step: 368/526, loss: 0.002501644194126129
2023-01-24 07:13:45.375933: step: 372/526, loss: 0.0013490453129634261
2023-01-24 07:13:46.440935: step: 376/526, loss: 0.02342231012880802
2023-01-24 07:13:47.522911: step: 380/526, loss: 0.005635560490190983
2023-01-24 07:13:48.609413: step: 384/526, loss: 0.0032323936466127634
2023-01-24 07:13:49.673937: step: 388/526, loss: 0.007500453852117062
2023-01-24 07:13:50.735491: step: 392/526, loss: 0.006203955505043268
2023-01-24 07:13:51.796047: step: 396/526, loss: 0.0024333924520760775
2023-01-24 07:13:52.874403: step: 400/526, loss: 0.012974249199032784
2023-01-24 07:13:53.956197: step: 404/526, loss: 0.005696407984942198
2023-01-24 07:13:55.044166: step: 408/526, loss: 0.0061072902753949165
2023-01-24 07:13:56.105193: step: 412/526, loss: 0.008957736194133759
2023-01-24 07:13:57.172441: step: 416/526, loss: 0.001270537730306387
2023-01-24 07:13:58.238725: step: 420/526, loss: 0.028876159340143204
2023-01-24 07:13:59.303253: step: 424/526, loss: 0.007041980978101492
2023-01-24 07:14:00.369933: step: 428/526, loss: 0.011806683614850044
2023-01-24 07:14:01.453856: step: 432/526, loss: 0.014579186215996742
2023-01-24 07:14:02.540208: step: 436/526, loss: 0.02383432164788246
2023-01-24 07:14:03.610550: step: 440/526, loss: 0.003819467034190893
2023-01-24 07:14:04.685217: step: 444/526, loss: 0.001048753154464066
2023-01-24 07:14:05.780238: step: 448/526, loss: 0.004892498254776001
2023-01-24 07:14:06.855648: step: 452/526, loss: 0.025785304605960846
2023-01-24 07:14:07.924936: step: 456/526, loss: 0.0007533314055763185
2023-01-24 07:14:08.987111: step: 460/526, loss: 0.0004199769755359739
2023-01-24 07:14:10.065612: step: 464/526, loss: 0.009533392265439034
2023-01-24 07:14:11.129812: step: 468/526, loss: 4.4106909626862034e-05
2023-01-24 07:14:12.219170: step: 472/526, loss: 0.009595033712685108
2023-01-24 07:14:13.314574: step: 476/526, loss: 2.0704645066871308e-05
2023-01-24 07:14:14.409862: step: 480/526, loss: 0.03623385727405548
2023-01-24 07:14:15.493183: step: 484/526, loss: 0.011518680490553379
2023-01-24 07:14:16.578396: step: 488/526, loss: 0.047334909439086914
2023-01-24 07:14:17.643967: step: 492/526, loss: 0.004484002012759447
2023-01-24 07:14:18.706116: step: 496/526, loss: 0.004415825009346008
2023-01-24 07:14:19.776753: step: 500/526, loss: 0.0012383628636598587
2023-01-24 07:14:20.852794: step: 504/526, loss: 0.007894769310951233
2023-01-24 07:14:21.922448: step: 508/526, loss: 0.007927427999675274
2023-01-24 07:14:22.990489: step: 512/526, loss: 0.034742943942546844
2023-01-24 07:14:24.065851: step: 516/526, loss: 0.0035664604511111975
2023-01-24 07:14:25.138982: step: 520/526, loss: 0.0035678299609571695
2023-01-24 07:14:26.197112: step: 524/526, loss: 0.0065514277666807175
2023-01-24 07:14:27.276834: step: 528/526, loss: 0.001496276119723916
2023-01-24 07:14:28.350723: step: 532/526, loss: 0.00012217026960570365
2023-01-24 07:14:29.406669: step: 536/526, loss: 0.03548990190029144
2023-01-24 07:14:30.482249: step: 540/526, loss: 0.01503920741379261
2023-01-24 07:14:31.558537: step: 544/526, loss: 0.018218837678432465
2023-01-24 07:14:32.627116: step: 548/526, loss: 0.011441313661634922
2023-01-24 07:14:33.703165: step: 552/526, loss: 0.014774641953408718
2023-01-24 07:14:34.778529: step: 556/526, loss: 0.007690586615353823
2023-01-24 07:14:35.865912: step: 560/526, loss: 0.03551023080945015
2023-01-24 07:14:36.939621: step: 564/526, loss: 0.015166421420872211
2023-01-24 07:14:38.014655: step: 568/526, loss: 0.02888898365199566
2023-01-24 07:14:39.096109: step: 572/526, loss: 0.003510272828862071
2023-01-24 07:14:40.166793: step: 576/526, loss: 0.0005080753471702337
2023-01-24 07:14:41.226312: step: 580/526, loss: 0.007521493826061487
2023-01-24 07:14:42.300344: step: 584/526, loss: 0.04921819269657135
2023-01-24 07:14:43.402358: step: 588/526, loss: 0.012841240502893925
2023-01-24 07:14:44.462741: step: 592/526, loss: 0.008358056657016277
2023-01-24 07:14:45.552917: step: 596/526, loss: 0.012431146577000618
2023-01-24 07:14:46.617638: step: 600/526, loss: 0.006740952841937542
2023-01-24 07:14:47.687095: step: 604/526, loss: 0.0030201685149222612
2023-01-24 07:14:48.759284: step: 608/526, loss: 0.008728429675102234
2023-01-24 07:14:49.845750: step: 612/526, loss: 0.01645864173769951
2023-01-24 07:14:50.914083: step: 616/526, loss: 0.0011229512747377157
2023-01-24 07:14:51.982904: step: 620/526, loss: 0.002545175841078162
2023-01-24 07:14:53.039678: step: 624/526, loss: 0.012281525880098343
2023-01-24 07:14:54.123278: step: 628/526, loss: 0.020619850605726242
2023-01-24 07:14:55.200502: step: 632/526, loss: 0.016358500346541405
2023-01-24 07:14:56.268313: step: 636/526, loss: 0.0026365816593170166
2023-01-24 07:14:57.326523: step: 640/526, loss: 0.005131471436470747
2023-01-24 07:14:58.394909: step: 644/526, loss: 0.015510068275034428
2023-01-24 07:14:59.470634: step: 648/526, loss: 0.017619166523218155
2023-01-24 07:15:00.537020: step: 652/526, loss: 0.0033808285370469093
2023-01-24 07:15:01.612245: step: 656/526, loss: 0.0013684448786079884
2023-01-24 07:15:02.660010: step: 660/526, loss: 0.006766584236174822
2023-01-24 07:15:03.728947: step: 664/526, loss: 0.005997321102768183
2023-01-24 07:15:04.804013: step: 668/526, loss: 0.017537444829940796
2023-01-24 07:15:05.852570: step: 672/526, loss: 0.004844771698117256
2023-01-24 07:15:06.905466: step: 676/526, loss: 0.0007653268403373659
2023-01-24 07:15:07.985749: step: 680/526, loss: 0.0016080039786174893
2023-01-24 07:15:09.044109: step: 684/526, loss: 0.0026193975936621428
2023-01-24 07:15:10.114177: step: 688/526, loss: 0.003294553142040968
2023-01-24 07:15:11.185696: step: 692/526, loss: 0.014027602039277554
2023-01-24 07:15:12.274506: step: 696/526, loss: 0.014805924147367477
2023-01-24 07:15:13.351253: step: 700/526, loss: 0.008626986294984818
2023-01-24 07:15:14.434182: step: 704/526, loss: 0.05580979585647583
2023-01-24 07:15:15.494604: step: 708/526, loss: 0.0016504075611010194
2023-01-24 07:15:16.550187: step: 712/526, loss: 0.026155177503824234
2023-01-24 07:15:17.615990: step: 716/526, loss: 0.0008136740070767701
2023-01-24 07:15:18.701993: step: 720/526, loss: 0.005017417948693037
2023-01-24 07:15:19.750974: step: 724/526, loss: 0.01748201623558998
2023-01-24 07:15:20.816075: step: 728/526, loss: 0.016648339107632637
2023-01-24 07:15:21.874262: step: 732/526, loss: 0.00246058264747262
2023-01-24 07:15:22.939606: step: 736/526, loss: 0.004434761591255665
2023-01-24 07:15:24.009811: step: 740/526, loss: 0.00963085237890482
2023-01-24 07:15:25.069348: step: 744/526, loss: 0.005070148501545191
2023-01-24 07:15:26.147746: step: 748/526, loss: 0.0008291593985632062
2023-01-24 07:15:27.206957: step: 752/526, loss: 0.0025919857434928417
2023-01-24 07:15:28.264871: step: 756/526, loss: 0.000503011979162693
2023-01-24 07:15:29.347091: step: 760/526, loss: 0.0016447021625936031
2023-01-24 07:15:30.419872: step: 764/526, loss: 0.002962449798360467
2023-01-24 07:15:31.472466: step: 768/526, loss: 1.1187505151610821e-05
2023-01-24 07:15:32.533108: step: 772/526, loss: 0.0026745335198938847
2023-01-24 07:15:33.617453: step: 776/526, loss: 0.008055642247200012
2023-01-24 07:15:34.676227: step: 780/526, loss: 0.0012769351014867425
2023-01-24 07:15:35.729983: step: 784/526, loss: 0.001039610942825675
2023-01-24 07:15:36.804855: step: 788/526, loss: 0.013878018595278263
2023-01-24 07:15:37.877874: step: 792/526, loss: 0.030783390626311302
2023-01-24 07:15:38.948190: step: 796/526, loss: 9.280815902457107e-06
2023-01-24 07:15:40.011178: step: 800/526, loss: 0.008469845168292522
2023-01-24 07:15:41.073149: step: 804/526, loss: 0.00041606550803408027
2023-01-24 07:15:42.143672: step: 808/526, loss: 0.0457325279712677
2023-01-24 07:15:43.223092: step: 812/526, loss: 0.004375222604721785
2023-01-24 07:15:44.286081: step: 816/526, loss: 0.0010926228715106845
2023-01-24 07:15:45.339007: step: 820/526, loss: 0.0020371773280203342
2023-01-24 07:15:46.419337: step: 824/526, loss: 0.00791111309081316
2023-01-24 07:15:47.476170: step: 828/526, loss: 0.017372306436300278
2023-01-24 07:15:48.530974: step: 832/526, loss: 0.001993887359276414
2023-01-24 07:15:49.587391: step: 836/526, loss: 0.002606706228107214
2023-01-24 07:15:50.672491: step: 840/526, loss: 0.03999406844377518
2023-01-24 07:15:51.735544: step: 844/526, loss: 0.00800907053053379
2023-01-24 07:15:52.805342: step: 848/526, loss: 0.010427029803395271
2023-01-24 07:15:53.911683: step: 852/526, loss: 0.0029530322644859552
2023-01-24 07:15:55.002377: step: 856/526, loss: 0.03662458434700966
2023-01-24 07:15:56.068499: step: 860/526, loss: 0.009072757326066494
2023-01-24 07:15:57.150439: step: 864/526, loss: 0.00900545809417963
2023-01-24 07:15:58.208386: step: 868/526, loss: 0.003854315495118499
2023-01-24 07:15:59.277552: step: 872/526, loss: 0.0015699114883318543
2023-01-24 07:16:00.363619: step: 876/526, loss: 0.03132845088839531
2023-01-24 07:16:01.431118: step: 880/526, loss: 0.026862921193242073
2023-01-24 07:16:02.500656: step: 884/526, loss: 0.008050457574427128
2023-01-24 07:16:03.556999: step: 888/526, loss: 0.013367857784032822
2023-01-24 07:16:04.629471: step: 892/526, loss: 0.0027895092498511076
2023-01-24 07:16:05.684660: step: 896/526, loss: 0.006650068331509829
2023-01-24 07:16:06.745982: step: 900/526, loss: 0.002781215589493513
2023-01-24 07:16:07.802680: step: 904/526, loss: 0.004364557098597288
2023-01-24 07:16:08.869066: step: 908/526, loss: 0.007103148382157087
2023-01-24 07:16:09.957214: step: 912/526, loss: 0.035328458994627
2023-01-24 07:16:11.036130: step: 916/526, loss: 0.006334730423986912
2023-01-24 07:16:12.096624: step: 920/526, loss: 0.005595427006483078
2023-01-24 07:16:13.171131: step: 924/526, loss: 0.0027736076153814793
2023-01-24 07:16:14.241483: step: 928/526, loss: 0.006798542104661465
2023-01-24 07:16:15.312390: step: 932/526, loss: 0.0187666155397892
2023-01-24 07:16:16.389795: step: 936/526, loss: 0.0067521752789616585
2023-01-24 07:16:17.464345: step: 940/526, loss: 0.0026990140322595835
2023-01-24 07:16:18.529072: step: 944/526, loss: 0.019883237779140472
2023-01-24 07:16:19.586480: step: 948/526, loss: 0.000835177197586745
2023-01-24 07:16:20.645659: step: 952/526, loss: 0.007185594644397497
2023-01-24 07:16:21.701763: step: 956/526, loss: 0.013472693040966988
2023-01-24 07:16:22.766427: step: 960/526, loss: 0.003318228991702199
2023-01-24 07:16:23.856528: step: 964/526, loss: 0.02671235240995884
2023-01-24 07:16:24.914368: step: 968/526, loss: 0.00032923376420512795
2023-01-24 07:16:25.963916: step: 972/526, loss: 0.0039630127139389515
2023-01-24 07:16:27.033650: step: 976/526, loss: 0.0021149753592908382
2023-01-24 07:16:28.093589: step: 980/526, loss: 0.0038768374361097813
2023-01-24 07:16:29.174103: step: 984/526, loss: 0.009342167526483536
2023-01-24 07:16:30.273436: step: 988/526, loss: 0.02566170133650303
2023-01-24 07:16:31.347018: step: 992/526, loss: 0.0455283522605896
2023-01-24 07:16:32.423125: step: 996/526, loss: 0.003501344006508589
2023-01-24 07:16:33.497606: step: 1000/526, loss: 0.021333366632461548
2023-01-24 07:16:34.552153: step: 1004/526, loss: 0.006034106016159058
2023-01-24 07:16:35.638323: step: 1008/526, loss: 0.0113820256665349
2023-01-24 07:16:36.716192: step: 1012/526, loss: 0.0076561542227864265
2023-01-24 07:16:37.776687: step: 1016/526, loss: 0.0024924827739596367
2023-01-24 07:16:38.842187: step: 1020/526, loss: 0.037824634462594986
2023-01-24 07:16:39.889089: step: 1024/526, loss: 0.00809899065643549
2023-01-24 07:16:40.947586: step: 1028/526, loss: 0.007951125502586365
2023-01-24 07:16:42.019011: step: 1032/526, loss: 0.004146024119108915
2023-01-24 07:16:43.081598: step: 1036/526, loss: 0.040169648826122284
2023-01-24 07:16:44.151411: step: 1040/526, loss: 0.014608575031161308
2023-01-24 07:16:45.220562: step: 1044/526, loss: 0.005859078839421272
2023-01-24 07:16:46.269445: step: 1048/526, loss: 0.0035897556226700544
2023-01-24 07:16:47.333914: step: 1052/526, loss: 0.006033977959305048
2023-01-24 07:16:48.388387: step: 1056/526, loss: 0.0017644037725403905
2023-01-24 07:16:49.441339: step: 1060/526, loss: 0.046444620937108994
2023-01-24 07:16:50.504481: step: 1064/526, loss: 0.003138477448374033
2023-01-24 07:16:51.562786: step: 1068/526, loss: 0.0003456490230746567
2023-01-24 07:16:52.638600: step: 1072/526, loss: 0.0021224389784038067
2023-01-24 07:16:53.705906: step: 1076/526, loss: 0.004722969140857458
2023-01-24 07:16:54.769640: step: 1080/526, loss: 0.022206544876098633
2023-01-24 07:16:55.847053: step: 1084/526, loss: 0.01786890998482704
2023-01-24 07:16:56.903058: step: 1088/526, loss: 0.005798814352601767
2023-01-24 07:16:57.983847: step: 1092/526, loss: 0.010083862580358982
2023-01-24 07:16:59.055000: step: 1096/526, loss: 0.06651788204908371
2023-01-24 07:17:00.137450: step: 1100/526, loss: 0.00998808816075325
2023-01-24 07:17:01.202862: step: 1104/526, loss: 0.002352374140173197
2023-01-24 07:17:02.269289: step: 1108/526, loss: 0.007733537815511227
2023-01-24 07:17:03.344709: step: 1112/526, loss: 0.01831551268696785
2023-01-24 07:17:04.412958: step: 1116/526, loss: 0.005822804290801287
2023-01-24 07:17:05.498277: step: 1120/526, loss: 0.0307039525359869
2023-01-24 07:17:06.559925: step: 1124/526, loss: 0.00418469263240695
2023-01-24 07:17:07.630569: step: 1128/526, loss: 0.003654086496680975
2023-01-24 07:17:08.693172: step: 1132/526, loss: 0.04210471361875534
2023-01-24 07:17:09.761231: step: 1136/526, loss: 0.007529860362410545
2023-01-24 07:17:10.809114: step: 1140/526, loss: 0.004805960692465305
2023-01-24 07:17:11.870058: step: 1144/526, loss: 0.003602338721975684
2023-01-24 07:17:12.925163: step: 1148/526, loss: 0.010789827443659306
2023-01-24 07:17:13.991380: step: 1152/526, loss: 0.002499269088730216
2023-01-24 07:17:15.048848: step: 1156/526, loss: 0.005996648222208023
2023-01-24 07:17:16.093600: step: 1160/526, loss: 0.009914937429130077
2023-01-24 07:17:17.173530: step: 1164/526, loss: 0.004271358251571655
2023-01-24 07:17:18.237725: step: 1168/526, loss: 0.055827584117650986
2023-01-24 07:17:19.299095: step: 1172/526, loss: 0.021684378385543823
2023-01-24 07:17:20.362664: step: 1176/526, loss: 0.016439255326986313
2023-01-24 07:17:21.426710: step: 1180/526, loss: 0.0057567209005355835
2023-01-24 07:17:22.521913: step: 1184/526, loss: 0.0607495978474617
2023-01-24 07:17:23.577559: step: 1188/526, loss: 0.024399401620030403
2023-01-24 07:17:24.640575: step: 1192/526, loss: 0.0054026078432798386
2023-01-24 07:17:25.711066: step: 1196/526, loss: 0.012957009486854076
2023-01-24 07:17:26.775049: step: 1200/526, loss: 0.02486690692603588
2023-01-24 07:17:27.848268: step: 1204/526, loss: 0.0027699570637196302
2023-01-24 07:17:28.929467: step: 1208/526, loss: 0.01208297349512577
2023-01-24 07:17:29.998714: step: 1212/526, loss: 0.0010945043759420514
2023-01-24 07:17:31.050008: step: 1216/526, loss: 0.006781335920095444
2023-01-24 07:17:32.100609: step: 1220/526, loss: 0.001397983287461102
2023-01-24 07:17:33.167013: step: 1224/526, loss: 0.0023020459339022636
2023-01-24 07:17:34.256554: step: 1228/526, loss: 0.006321605294942856
2023-01-24 07:17:35.315750: step: 1232/526, loss: 0.0024445573799312115
2023-01-24 07:17:36.393142: step: 1236/526, loss: 0.0010653740027919412
2023-01-24 07:17:37.459704: step: 1240/526, loss: 0.0010765297338366508
2023-01-24 07:17:38.554107: step: 1244/526, loss: 0.00206439895555377
2023-01-24 07:17:39.619758: step: 1248/526, loss: 0.0053231497295200825
2023-01-24 07:17:40.698427: step: 1252/526, loss: 0.015214274637401104
2023-01-24 07:17:41.746906: step: 1256/526, loss: 0.0002356090844841674
2023-01-24 07:17:42.840354: step: 1260/526, loss: 0.00901406817138195
2023-01-24 07:17:43.892670: step: 1264/526, loss: 0.004142566584050655
2023-01-24 07:17:44.945991: step: 1268/526, loss: 0.004701070953160524
2023-01-24 07:17:46.019265: step: 1272/526, loss: 0.0008033206686377525
2023-01-24 07:17:47.110571: step: 1276/526, loss: 0.013277271762490273
2023-01-24 07:17:48.170316: step: 1280/526, loss: 0.002346867462620139
2023-01-24 07:17:49.239635: step: 1284/526, loss: 0.013487554155290127
2023-01-24 07:17:50.311240: step: 1288/526, loss: 0.020648233592510223
2023-01-24 07:17:51.376637: step: 1292/526, loss: 0.0020224498584866524
2023-01-24 07:17:52.451859: step: 1296/526, loss: 0.002598815131932497
2023-01-24 07:17:53.526342: step: 1300/526, loss: 0.006972632370889187
2023-01-24 07:17:54.600336: step: 1304/526, loss: 0.03460879623889923
2023-01-24 07:17:55.676930: step: 1308/526, loss: 0.010561812669038773
2023-01-24 07:17:56.757541: step: 1312/526, loss: 0.017433661967515945
2023-01-24 07:17:57.798830: step: 1316/526, loss: 0.0009524445631541312
2023-01-24 07:17:58.869103: step: 1320/526, loss: 0.017058931291103363
2023-01-24 07:17:59.937655: step: 1324/526, loss: 0.00552911963313818
2023-01-24 07:18:01.016247: step: 1328/526, loss: 0.07649354636669159
2023-01-24 07:18:02.081466: step: 1332/526, loss: 0.004486635327339172
2023-01-24 07:18:03.135006: step: 1336/526, loss: 0.03997723385691643
2023-01-24 07:18:04.186270: step: 1340/526, loss: 0.007076819892972708
2023-01-24 07:18:05.255060: step: 1344/526, loss: 0.0127756642177701
2023-01-24 07:18:06.327281: step: 1348/526, loss: 0.007796027697622776
2023-01-24 07:18:07.384581: step: 1352/526, loss: 0.012270638719201088
2023-01-24 07:18:08.469518: step: 1356/526, loss: 0.003149248892441392
2023-01-24 07:18:09.533154: step: 1360/526, loss: 0.004529505502432585
2023-01-24 07:18:10.607887: step: 1364/526, loss: 0.002220523776486516
2023-01-24 07:18:11.681981: step: 1368/526, loss: 0.0028114519082009792
2023-01-24 07:18:12.750661: step: 1372/526, loss: 0.0045374296605587006
2023-01-24 07:18:13.820978: step: 1376/526, loss: 0.007525020278990269
2023-01-24 07:18:14.881835: step: 1380/526, loss: 0.004115311894565821
2023-01-24 07:18:15.951211: step: 1384/526, loss: 0.011983995325863361
2023-01-24 07:18:17.019605: step: 1388/526, loss: 0.014218327589333057
2023-01-24 07:18:18.109793: step: 1392/526, loss: 0.0334528349339962
2023-01-24 07:18:19.172017: step: 1396/526, loss: 0.038804586976766586
2023-01-24 07:18:20.228643: step: 1400/526, loss: 0.004139270633459091
2023-01-24 07:18:21.288849: step: 1404/526, loss: 0.02219662442803383
2023-01-24 07:18:22.367747: step: 1408/526, loss: 0.026016244664788246
2023-01-24 07:18:23.417034: step: 1412/526, loss: 0.01674872264266014
2023-01-24 07:18:24.471905: step: 1416/526, loss: 0.01808893494307995
2023-01-24 07:18:25.543620: step: 1420/526, loss: 0.002857440384104848
2023-01-24 07:18:26.622269: step: 1424/526, loss: 0.0011322400532662868
2023-01-24 07:18:27.676249: step: 1428/526, loss: 0.004235779866576195
2023-01-24 07:18:28.733568: step: 1432/526, loss: 0.0038578875828534365
2023-01-24 07:18:29.793283: step: 1436/526, loss: 0.006223521661013365
2023-01-24 07:18:30.871762: step: 1440/526, loss: 0.003061942756175995
2023-01-24 07:18:31.925722: step: 1444/526, loss: 0.015388989821076393
2023-01-24 07:18:32.998003: step: 1448/526, loss: 0.018897997215390205
2023-01-24 07:18:34.077839: step: 1452/526, loss: 0.01957865059375763
2023-01-24 07:18:35.157974: step: 1456/526, loss: 0.021583186462521553
2023-01-24 07:18:36.222870: step: 1460/526, loss: 0.005597573705017567
2023-01-24 07:18:37.282888: step: 1464/526, loss: 0.00262489914894104
2023-01-24 07:18:38.363904: step: 1468/526, loss: 0.019800467416644096
2023-01-24 07:18:39.448322: step: 1472/526, loss: 0.0027936387341469526
2023-01-24 07:18:40.514776: step: 1476/526, loss: 0.007734362501651049
2023-01-24 07:18:41.583014: step: 1480/526, loss: 0.002555450890213251
2023-01-24 07:18:42.650306: step: 1484/526, loss: 0.03706897050142288
2023-01-24 07:18:43.721923: step: 1488/526, loss: 0.006347267888486385
2023-01-24 07:18:44.776091: step: 1492/526, loss: 0.019081544131040573
2023-01-24 07:18:45.853918: step: 1496/526, loss: 0.00281783239915967
2023-01-24 07:18:46.966007: step: 1500/526, loss: 0.006851533427834511
2023-01-24 07:18:48.036500: step: 1504/526, loss: 0.005703883245587349
2023-01-24 07:18:49.117417: step: 1508/526, loss: 0.0031425543129444122
2023-01-24 07:18:50.175684: step: 1512/526, loss: 0.009820224717259407
2023-01-24 07:18:51.239881: step: 1516/526, loss: 0.0020063077099621296
2023-01-24 07:18:52.304267: step: 1520/526, loss: 0.07253638654947281
2023-01-24 07:18:53.367453: step: 1524/526, loss: 0.11937223374843597
2023-01-24 07:18:54.432329: step: 1528/526, loss: 0.00813398975878954
2023-01-24 07:18:55.514894: step: 1532/526, loss: 0.0008280671900138259
2023-01-24 07:18:56.576478: step: 1536/526, loss: 0.00029721410828642547
2023-01-24 07:18:57.645423: step: 1540/526, loss: 0.014271453022956848
2023-01-24 07:18:58.710782: step: 1544/526, loss: 0.004293354693800211
2023-01-24 07:18:59.794978: step: 1548/526, loss: 0.011623783968389034
2023-01-24 07:19:00.878563: step: 1552/526, loss: 0.011222359724342823
2023-01-24 07:19:01.963325: step: 1556/526, loss: 0.035718921571969986
2023-01-24 07:19:03.033897: step: 1560/526, loss: 0.017994921654462814
2023-01-24 07:19:04.097206: step: 1564/526, loss: 0.0064345127902925014
2023-01-24 07:19:05.186490: step: 1568/526, loss: 0.013070063665509224
2023-01-24 07:19:06.243635: step: 1572/526, loss: 0.009704822674393654
2023-01-24 07:19:07.310907: step: 1576/526, loss: 0.014365030452609062
2023-01-24 07:19:08.378109: step: 1580/526, loss: 0.02319900505244732
2023-01-24 07:19:09.444584: step: 1584/526, loss: 0.00878023449331522
2023-01-24 07:19:10.518837: step: 1588/526, loss: 0.01395992562174797
2023-01-24 07:19:11.587038: step: 1592/526, loss: 0.0020557951647788286
2023-01-24 07:19:12.677314: step: 1596/526, loss: 0.009000587277114391
2023-01-24 07:19:13.749439: step: 1600/526, loss: 0.004282928537577391
2023-01-24 07:19:14.819218: step: 1604/526, loss: 0.0016594675835222006
2023-01-24 07:19:15.894752: step: 1608/526, loss: 0.005927237682044506
2023-01-24 07:19:16.979683: step: 1612/526, loss: 0.003080021822825074
2023-01-24 07:19:18.054083: step: 1616/526, loss: 0.0035863418597728014
2023-01-24 07:19:19.122765: step: 1620/526, loss: 0.0049010468646883965
2023-01-24 07:19:20.179929: step: 1624/526, loss: 0.0029122792184352875
2023-01-24 07:19:21.246626: step: 1628/526, loss: 0.007731992285698652
2023-01-24 07:19:22.317964: step: 1632/526, loss: 0.0012869666097685695
2023-01-24 07:19:23.397112: step: 1636/526, loss: 0.002036880701780319
2023-01-24 07:19:24.481039: step: 1640/526, loss: 0.024723196402192116
2023-01-24 07:19:25.548539: step: 1644/526, loss: 0.0007505103712901473
2023-01-24 07:19:26.621055: step: 1648/526, loss: 0.006666247732937336
2023-01-24 07:19:27.680647: step: 1652/526, loss: 0.002535420935600996
2023-01-24 07:19:28.743918: step: 1656/526, loss: 0.017096517607569695
2023-01-24 07:19:29.811836: step: 1660/526, loss: 0.014411868527531624
2023-01-24 07:19:30.876347: step: 1664/526, loss: 0.004635794088244438
2023-01-24 07:19:31.970861: step: 1668/526, loss: 0.006019299384206533
2023-01-24 07:19:33.048808: step: 1672/526, loss: 0.005905449390411377
2023-01-24 07:19:34.120947: step: 1676/526, loss: 0.027766354382038116
2023-01-24 07:19:35.205814: step: 1680/526, loss: 0.0011953338980674744
2023-01-24 07:19:36.282572: step: 1684/526, loss: 0.004011579789221287
2023-01-24 07:19:37.354209: step: 1688/526, loss: 0.0030191901605576277
2023-01-24 07:19:38.419357: step: 1692/526, loss: 0.05773008614778519
2023-01-24 07:19:39.501794: step: 1696/526, loss: 0.014474649913609028
2023-01-24 07:19:40.574921: step: 1700/526, loss: 0.002133729634806514
2023-01-24 07:19:41.652350: step: 1704/526, loss: 0.02012203447520733
2023-01-24 07:19:42.736055: step: 1708/526, loss: 0.0069390772841870785
2023-01-24 07:19:43.814312: step: 1712/526, loss: 0.06547851860523224
2023-01-24 07:19:44.878705: step: 1716/526, loss: 0.01818758435547352
2023-01-24 07:19:45.963593: step: 1720/526, loss: 0.016970161348581314
2023-01-24 07:19:47.030827: step: 1724/526, loss: 0.003974339924752712
2023-01-24 07:19:48.106486: step: 1728/526, loss: 0.0018917451379820704
2023-01-24 07:19:49.190176: step: 1732/526, loss: 0.01116181816905737
2023-01-24 07:19:50.274158: step: 1736/526, loss: 0.016343293711543083
2023-01-24 07:19:51.355475: step: 1740/526, loss: 0.0036974104586988688
2023-01-24 07:19:52.442120: step: 1744/526, loss: 0.007054630666971207
2023-01-24 07:19:53.537933: step: 1748/526, loss: 0.09989713877439499
2023-01-24 07:19:54.602962: step: 1752/526, loss: 0.007389947306364775
2023-01-24 07:19:55.646110: step: 1756/526, loss: 0.003911925479769707
2023-01-24 07:19:56.705736: step: 1760/526, loss: 0.0023412429727613926
2023-01-24 07:19:57.782249: step: 1764/526, loss: 0.005940565839409828
2023-01-24 07:19:58.863025: step: 1768/526, loss: 0.0019187636207789183
2023-01-24 07:19:59.944966: step: 1772/526, loss: 0.0025826399214565754
2023-01-24 07:20:01.015365: step: 1776/526, loss: 0.004844007547944784
2023-01-24 07:20:02.077704: step: 1780/526, loss: 0.002479694550856948
2023-01-24 07:20:03.142711: step: 1784/526, loss: 0.02238212339580059
2023-01-24 07:20:04.212108: step: 1788/526, loss: 0.00439298665151
2023-01-24 07:20:05.299568: step: 1792/526, loss: 0.01564399152994156
2023-01-24 07:20:06.380733: step: 1796/526, loss: 0.012087401002645493
2023-01-24 07:20:07.469829: step: 1800/526, loss: 0.006518587935715914
2023-01-24 07:20:08.536763: step: 1804/526, loss: 0.01234168466180563
2023-01-24 07:20:09.600012: step: 1808/526, loss: 0.04436902329325676
2023-01-24 07:20:10.647228: step: 1812/526, loss: 0.010153175331652164
2023-01-24 07:20:11.709053: step: 1816/526, loss: 0.007166760042309761
2023-01-24 07:20:12.771068: step: 1820/526, loss: 0.028396114706993103
2023-01-24 07:20:13.822882: step: 1824/526, loss: 0.0012265837285667658
2023-01-24 07:20:14.895989: step: 1828/526, loss: 0.0029733222909271717
2023-01-24 07:20:15.976522: step: 1832/526, loss: 0.010580579750239849
2023-01-24 07:20:17.032906: step: 1836/526, loss: 0.006216373760253191
2023-01-24 07:20:18.100998: step: 1840/526, loss: 0.0009228076669387519
2023-01-24 07:20:19.146972: step: 1844/526, loss: 0.006918182130903006
2023-01-24 07:20:20.213860: step: 1848/526, loss: 0.003109990619122982
2023-01-24 07:20:21.291859: step: 1852/526, loss: 0.010111591778695583
2023-01-24 07:20:22.384283: step: 1856/526, loss: 0.0370626263320446
2023-01-24 07:20:23.445942: step: 1860/526, loss: 0.0003386267344467342
2023-01-24 07:20:24.506173: step: 1864/526, loss: 0.00941428728401661
2023-01-24 07:20:25.580110: step: 1868/526, loss: 0.0021819707471877337
2023-01-24 07:20:26.658674: step: 1872/526, loss: 0.03399588167667389
2023-01-24 07:20:27.720623: step: 1876/526, loss: 0.006060609593987465
2023-01-24 07:20:28.782689: step: 1880/526, loss: 0.0033985571935772896
2023-01-24 07:20:29.839286: step: 1884/526, loss: 0.009023567661643028
2023-01-24 07:20:30.917091: step: 1888/526, loss: 0.001036790432408452
2023-01-24 07:20:31.977178: step: 1892/526, loss: 0.006437205243855715
2023-01-24 07:20:33.050523: step: 1896/526, loss: 0.0008709206013008952
2023-01-24 07:20:34.110179: step: 1900/526, loss: 0.0014735977165400982
2023-01-24 07:20:35.167381: step: 1904/526, loss: 0.003793305018916726
2023-01-24 07:20:36.228551: step: 1908/526, loss: 0.0007709282217547297
2023-01-24 07:20:37.299154: step: 1912/526, loss: 0.027955088764429092
2023-01-24 07:20:38.378141: step: 1916/526, loss: 0.003278878750279546
2023-01-24 07:20:39.458692: step: 1920/526, loss: 0.004938701633363962
2023-01-24 07:20:40.522878: step: 1924/526, loss: 0.03605610132217407
2023-01-24 07:20:41.615877: step: 1928/526, loss: 0.0028789339121431112
2023-01-24 07:20:42.684194: step: 1932/526, loss: 0.007453788537532091
2023-01-24 07:20:43.772595: step: 1936/526, loss: 0.013742885552346706
2023-01-24 07:20:44.835687: step: 1940/526, loss: 0.0036725637037307024
2023-01-24 07:20:45.910058: step: 1944/526, loss: 0.008672547526657581
2023-01-24 07:20:46.980858: step: 1948/526, loss: 0.05057437717914581
2023-01-24 07:20:48.042966: step: 1952/526, loss: 0.04378332570195198
2023-01-24 07:20:49.109946: step: 1956/526, loss: 0.003826582571491599
2023-01-24 07:20:50.185493: step: 1960/526, loss: 0.01907321624457836
2023-01-24 07:20:51.263797: step: 1964/526, loss: 0.016609249636530876
2023-01-24 07:20:52.329611: step: 1968/526, loss: 0.007328836712986231
2023-01-24 07:20:53.396623: step: 1972/526, loss: 0.007735108491033316
2023-01-24 07:20:54.452302: step: 1976/526, loss: 0.01149886753410101
2023-01-24 07:20:55.516635: step: 1980/526, loss: 0.001523140468634665
2023-01-24 07:20:56.592089: step: 1984/526, loss: 0.006447824649512768
2023-01-24 07:20:57.647195: step: 1988/526, loss: 0.010037658736109734
2023-01-24 07:20:58.701493: step: 1992/526, loss: 0.0008003299008123577
2023-01-24 07:20:59.792254: step: 1996/526, loss: 0.06361684203147888
2023-01-24 07:21:00.863717: step: 2000/526, loss: 0.010843368247151375
2023-01-24 07:21:01.920158: step: 2004/526, loss: 0.004187176004052162
2023-01-24 07:21:02.983023: step: 2008/526, loss: 0.01911861076951027
2023-01-24 07:21:04.055965: step: 2012/526, loss: 0.003816250478848815
2023-01-24 07:21:05.131825: step: 2016/526, loss: 0.005473429337143898
2023-01-24 07:21:06.211173: step: 2020/526, loss: 0.0051955487579107285
2023-01-24 07:21:07.273306: step: 2024/526, loss: 0.0020086413715034723
2023-01-24 07:21:08.343251: step: 2028/526, loss: 0.03298501297831535
2023-01-24 07:21:09.400892: step: 2032/526, loss: 0.05014680325984955
2023-01-24 07:21:10.479846: step: 2036/526, loss: 0.03912079334259033
2023-01-24 07:21:11.552216: step: 2040/526, loss: 0.013243984431028366
2023-01-24 07:21:12.622018: step: 2044/526, loss: 0.006227582227438688
2023-01-24 07:21:13.672869: step: 2048/526, loss: 0.007000616751611233
2023-01-24 07:21:14.734040: step: 2052/526, loss: 0.05694907158613205
2023-01-24 07:21:15.814287: step: 2056/526, loss: 0.011590370908379555
2023-01-24 07:21:16.890592: step: 2060/526, loss: 0.018102457746863365
2023-01-24 07:21:17.949528: step: 2064/526, loss: 0.0022255312651395798
2023-01-24 07:21:19.005882: step: 2068/526, loss: 0.0034415286500006914
2023-01-24 07:21:20.075111: step: 2072/526, loss: 0.00653142761439085
2023-01-24 07:21:21.141126: step: 2076/526, loss: 0.00302940234541893
2023-01-24 07:21:22.198677: step: 2080/526, loss: 0.006129369605332613
2023-01-24 07:21:23.269752: step: 2084/526, loss: 0.007726317271590233
2023-01-24 07:21:24.336051: step: 2088/526, loss: 0.009634272195398808
2023-01-24 07:21:25.405322: step: 2092/526, loss: 0.013455990701913834
2023-01-24 07:21:26.464666: step: 2096/526, loss: 0.010858725756406784
2023-01-24 07:21:27.524477: step: 2100/526, loss: 0.01281960029155016
2023-01-24 07:21:28.592899: step: 2104/526, loss: 0.003467496484518051
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.364575721592985, 'r': 0.27049166440769856, 'f1': 0.31056450357920945}, 'combined': 0.22883700263731221, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3585586174440493, 'r': 0.22405812965625407, 'f1': 0.27578326093951094}, 'combined': 0.15042723323973323, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377168646452016, 'r': 0.29285883708322036, 'f1': 0.31369229094076656}, 'combined': 0.23114168806161745, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36076020150542065, 'r': 0.2604206761095854, 'f1': 0.30248650264375865}, 'combined': 0.16499263780568652, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.359921202261224, 'r': 0.31484568167442933, 'f1': 0.3358778830818305}, 'combined': 0.24748896648134877, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36702778933437497, 'r': 0.278041179843424, 'f1': 0.31639667836425034}, 'combined': 0.17258000638050017, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 6}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377168646452016, 'r': 0.29285883708322036, 'f1': 0.31369229094076656}, 'combined': 0.23114168806161745, 'stategy': 1, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36076020150542065, 'r': 0.2604206761095854, 'f1': 0.30248650264375865}, 'combined': 0.16499263780568652, 'stategy': 1, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 07:24:18.048131: step: 4/526, loss: 0.005681129172444344
2023-01-24 07:24:19.107889: step: 8/526, loss: 0.0010143601102754474
2023-01-24 07:24:20.147862: step: 12/526, loss: 0.005159999709576368
2023-01-24 07:24:21.221791: step: 16/526, loss: 0.011183780618011951
2023-01-24 07:24:22.281949: step: 20/526, loss: 0.0037257422227412462
2023-01-24 07:24:23.341050: step: 24/526, loss: 0.001278422074392438
2023-01-24 07:24:24.406495: step: 28/526, loss: 0.0008670516544952989
2023-01-24 07:24:25.475178: step: 32/526, loss: 0.005145782604813576
2023-01-24 07:24:26.546633: step: 36/526, loss: 0.002572249621152878
2023-01-24 07:24:27.608703: step: 40/526, loss: 0.00873457733541727
2023-01-24 07:24:28.679015: step: 44/526, loss: 0.003323943819850683
2023-01-24 07:24:29.731245: step: 48/526, loss: 0.015720967203378677
2023-01-24 07:24:30.785852: step: 52/526, loss: 0.003789663314819336
2023-01-24 07:24:31.863572: step: 56/526, loss: 0.004524076823145151
2023-01-24 07:24:32.921144: step: 60/526, loss: 0.0029734980780631304
2023-01-24 07:24:33.980268: step: 64/526, loss: 0.008790159597992897
2023-01-24 07:24:35.049972: step: 68/526, loss: 0.008159545250236988
2023-01-24 07:24:36.114312: step: 72/526, loss: 0.00930866226553917
2023-01-24 07:24:37.184922: step: 76/526, loss: 0.003312517888844013
2023-01-24 07:24:38.247818: step: 80/526, loss: 0.0054994067177176476
2023-01-24 07:24:39.312070: step: 84/526, loss: 0.0047514731995761395
2023-01-24 07:24:40.400349: step: 88/526, loss: 0.0011768946424126625
2023-01-24 07:24:41.475581: step: 92/526, loss: 0.005265416111797094
2023-01-24 07:24:42.576041: step: 96/526, loss: 0.009324588812887669
2023-01-24 07:24:43.638011: step: 100/526, loss: 0.003282174002379179
2023-01-24 07:24:44.716475: step: 104/526, loss: 0.0016753204399719834
2023-01-24 07:24:45.790056: step: 108/526, loss: 0.0028524647932499647
2023-01-24 07:24:46.859028: step: 112/526, loss: 0.0067680226638913155
2023-01-24 07:24:47.933026: step: 116/526, loss: 0.001611438812687993
2023-01-24 07:24:48.993000: step: 120/526, loss: 0.00673902640119195
2023-01-24 07:24:50.066923: step: 124/526, loss: 0.008489931933581829
2023-01-24 07:24:51.123182: step: 128/526, loss: 0.007176227401942015
2023-01-24 07:24:52.182212: step: 132/526, loss: 0.016124073415994644
2023-01-24 07:24:53.240761: step: 136/526, loss: 0.00031997408950701356
2023-01-24 07:24:54.314038: step: 140/526, loss: 0.0012919764267280698
2023-01-24 07:24:55.390566: step: 144/526, loss: 0.004090574570000172
2023-01-24 07:24:56.464021: step: 148/526, loss: 0.012636663392186165
2023-01-24 07:24:57.522853: step: 152/526, loss: 0.0058204373344779015
2023-01-24 07:24:58.600961: step: 156/526, loss: 0.004791403189301491
2023-01-24 07:24:59.667646: step: 160/526, loss: 0.0048788427375257015
2023-01-24 07:25:00.743425: step: 164/526, loss: 0.008330618031322956
2023-01-24 07:25:01.815469: step: 168/526, loss: 0.016464125365018845
2023-01-24 07:25:02.900769: step: 172/526, loss: 0.04827934503555298
2023-01-24 07:25:03.985662: step: 176/526, loss: 0.003101169364526868
2023-01-24 07:25:05.064264: step: 180/526, loss: 0.0015956700081005692
2023-01-24 07:25:06.141310: step: 184/526, loss: 0.004257692955434322
2023-01-24 07:25:07.197467: step: 188/526, loss: 0.0006411054637283087
2023-01-24 07:25:08.260551: step: 192/526, loss: 0.0002515445521567017
2023-01-24 07:25:09.334096: step: 196/526, loss: 0.005419893655925989
2023-01-24 07:25:10.434535: step: 200/526, loss: 0.0034781487192958593
2023-01-24 07:25:11.522598: step: 204/526, loss: 0.0037832753732800484
2023-01-24 07:25:12.582873: step: 208/526, loss: 0.0065412214025855064
2023-01-24 07:25:13.660940: step: 212/526, loss: 0.022938640788197517
2023-01-24 07:25:14.727412: step: 216/526, loss: 0.00046589982230216265
2023-01-24 07:25:15.796521: step: 220/526, loss: 0.003605988807976246
2023-01-24 07:25:16.862810: step: 224/526, loss: 0.010898103006184101
2023-01-24 07:25:17.948761: step: 228/526, loss: 0.0004372690455056727
2023-01-24 07:25:19.028144: step: 232/526, loss: 0.00962343905121088
2023-01-24 07:25:20.088377: step: 236/526, loss: 0.0
2023-01-24 07:25:21.153440: step: 240/526, loss: 0.020165417343378067
2023-01-24 07:25:22.226870: step: 244/526, loss: 0.004791875369846821
2023-01-24 07:25:23.303267: step: 248/526, loss: 0.0031337961554527283
2023-01-24 07:25:24.372258: step: 252/526, loss: 0.0110794547945261
2023-01-24 07:25:25.426472: step: 256/526, loss: 0.008565178140997887
2023-01-24 07:25:26.491711: step: 260/526, loss: 0.0027253078296780586
2023-01-24 07:25:27.563199: step: 264/526, loss: 0.0019073592266067863
2023-01-24 07:25:28.646016: step: 268/526, loss: 0.0028594681061804295
2023-01-24 07:25:29.713003: step: 272/526, loss: 0.008038518019020557
2023-01-24 07:25:30.780944: step: 276/526, loss: 0.008343706838786602
2023-01-24 07:25:31.840883: step: 280/526, loss: 0.014430110342800617
2023-01-24 07:25:32.918668: step: 284/526, loss: 0.010138564743101597
2023-01-24 07:25:33.985731: step: 288/526, loss: 0.012738027609884739
2023-01-24 07:25:35.047518: step: 292/526, loss: 0.002907796995714307
2023-01-24 07:25:36.134356: step: 296/526, loss: 0.006457481998950243
2023-01-24 07:25:37.199229: step: 300/526, loss: 0.004271854646503925
2023-01-24 07:25:38.274145: step: 304/526, loss: 0.00224136165343225
2023-01-24 07:25:39.345630: step: 308/526, loss: 0.0009568085661157966
2023-01-24 07:25:40.409704: step: 312/526, loss: 0.007775954902172089
2023-01-24 07:25:41.491547: step: 316/526, loss: 0.002744965488091111
2023-01-24 07:25:42.559348: step: 320/526, loss: 0.0028619111981242895
2023-01-24 07:25:43.665502: step: 324/526, loss: 0.0018685284303501248
2023-01-24 07:25:44.735211: step: 328/526, loss: 0.0035534941125661135
2023-01-24 07:25:45.797910: step: 332/526, loss: 0.01011749915778637
2023-01-24 07:25:46.859339: step: 336/526, loss: 0.00327878980897367
2023-01-24 07:25:47.921615: step: 340/526, loss: 0.006491495296359062
2023-01-24 07:25:49.003221: step: 344/526, loss: 0.004422201309353113
2023-01-24 07:25:50.061537: step: 348/526, loss: 0.0009063204634003341
2023-01-24 07:25:51.115485: step: 352/526, loss: 0.0024999917950481176
2023-01-24 07:25:52.180065: step: 356/526, loss: 4.173920751782134e-05
2023-01-24 07:25:53.265456: step: 360/526, loss: 0.009568093344569206
2023-01-24 07:25:54.327135: step: 364/526, loss: 0.001386543270200491
2023-01-24 07:25:55.400012: step: 368/526, loss: 0.018805434927344322
2023-01-24 07:25:56.481800: step: 372/526, loss: 0.004321052227169275
2023-01-24 07:25:57.551200: step: 376/526, loss: 0.0011334537994116545
2023-01-24 07:25:58.627691: step: 380/526, loss: 0.008020251989364624
2023-01-24 07:25:59.690964: step: 384/526, loss: 0.003865952370688319
2023-01-24 07:26:00.763689: step: 388/526, loss: 0.002532330574467778
2023-01-24 07:26:01.829645: step: 392/526, loss: 0.013063295744359493
2023-01-24 07:26:02.905547: step: 396/526, loss: 0.0056519233621656895
2023-01-24 07:26:03.961393: step: 400/526, loss: 0.004078799858689308
2023-01-24 07:26:05.048748: step: 404/526, loss: 0.009090702049434185
2023-01-24 07:26:06.132743: step: 408/526, loss: 0.01338796503841877
2023-01-24 07:26:07.202866: step: 412/526, loss: 0.023754622787237167
2023-01-24 07:26:08.259002: step: 416/526, loss: 0.0008065896690823138
2023-01-24 07:26:09.328556: step: 420/526, loss: 0.005122347269207239
2023-01-24 07:26:10.391240: step: 424/526, loss: 0.005691178143024445
2023-01-24 07:26:11.464687: step: 428/526, loss: 0.0075169154442846775
2023-01-24 07:26:12.528061: step: 432/526, loss: 0.005046722944825888
2023-01-24 07:26:13.590383: step: 436/526, loss: 0.003507403889670968
2023-01-24 07:26:14.671055: step: 440/526, loss: 0.0069351098500192165
2023-01-24 07:26:15.762505: step: 444/526, loss: 0.07562882453203201
2023-01-24 07:26:16.837094: step: 448/526, loss: 0.009906035847961903
2023-01-24 07:26:17.904905: step: 452/526, loss: 0.0033758808858692646
2023-01-24 07:26:18.994082: step: 456/526, loss: 0.020844178274273872
2023-01-24 07:26:20.072925: step: 460/526, loss: 0.0024903956800699234
2023-01-24 07:26:21.134753: step: 464/526, loss: 0.0015259014908224344
2023-01-24 07:26:22.194260: step: 468/526, loss: 0.0006897325511090457
2023-01-24 07:26:23.276583: step: 472/526, loss: 0.0056253401562571526
2023-01-24 07:26:24.353279: step: 476/526, loss: 0.0004885842208750546
2023-01-24 07:26:25.415596: step: 480/526, loss: 0.010557063855230808
2023-01-24 07:26:26.495330: step: 484/526, loss: 0.03432700037956238
2023-01-24 07:26:27.569226: step: 488/526, loss: 0.009193593636155128
2023-01-24 07:26:28.657516: step: 492/526, loss: 0.0029847752302885056
2023-01-24 07:26:29.715863: step: 496/526, loss: 0.006365698296576738
2023-01-24 07:26:30.790271: step: 500/526, loss: 0.009834758006036282
2023-01-24 07:26:31.880548: step: 504/526, loss: 0.038854554295539856
2023-01-24 07:26:32.964885: step: 508/526, loss: 0.001355179469101131
2023-01-24 07:26:34.052223: step: 512/526, loss: 0.004993292968720198
2023-01-24 07:26:35.118014: step: 516/526, loss: 0.008177582174539566
2023-01-24 07:26:36.172189: step: 520/526, loss: 0.0015152118867263198
2023-01-24 07:26:37.249553: step: 524/526, loss: 0.014209181070327759
2023-01-24 07:26:38.331574: step: 528/526, loss: 0.021385325118899345
2023-01-24 07:26:39.413772: step: 532/526, loss: 0.0015365779399871826
2023-01-24 07:26:40.510086: step: 536/526, loss: 0.006883626338094473
2023-01-24 07:26:41.579233: step: 540/526, loss: 0.0012072596000507474
2023-01-24 07:26:42.664641: step: 544/526, loss: 0.0013109153369441628
2023-01-24 07:26:43.757618: step: 548/526, loss: 0.0209902822971344
2023-01-24 07:26:44.848739: step: 552/526, loss: 0.005961552262306213
2023-01-24 07:26:45.915078: step: 556/526, loss: 0.0029851722065359354
2023-01-24 07:26:46.976248: step: 560/526, loss: 0.004833499900996685
2023-01-24 07:26:48.069742: step: 564/526, loss: 0.0039832089096307755
2023-01-24 07:26:49.124975: step: 568/526, loss: 0.0007380950846709311
2023-01-24 07:26:50.185913: step: 572/526, loss: 0.0030625511426478624
2023-01-24 07:26:51.271350: step: 576/526, loss: 0.004741715732961893
2023-01-24 07:26:52.351873: step: 580/526, loss: 0.0008771279826760292
2023-01-24 07:26:53.443398: step: 584/526, loss: 0.004129146225750446
2023-01-24 07:26:54.507894: step: 588/526, loss: 0.001908286940306425
2023-01-24 07:26:55.578569: step: 592/526, loss: 0.0031311430502682924
2023-01-24 07:26:56.651108: step: 596/526, loss: 0.0024689885322004557
2023-01-24 07:26:57.726901: step: 600/526, loss: 0.012600594200193882
2023-01-24 07:26:58.796227: step: 604/526, loss: 0.005509055685251951
2023-01-24 07:26:59.857473: step: 608/526, loss: 0.0007588063599541783
2023-01-24 07:27:00.926891: step: 612/526, loss: 0.0021500359289348125
2023-01-24 07:27:02.012421: step: 616/526, loss: 0.004716811235994101
2023-01-24 07:27:03.094679: step: 620/526, loss: 0.024872159585356712
2023-01-24 07:27:04.170743: step: 624/526, loss: 0.004087517037987709
2023-01-24 07:27:05.241803: step: 628/526, loss: 0.024557167664170265
2023-01-24 07:27:06.312122: step: 632/526, loss: 0.0034598500933498144
2023-01-24 07:27:07.383331: step: 636/526, loss: 0.005095295608043671
2023-01-24 07:27:08.470477: step: 640/526, loss: 0.005925626493990421
2023-01-24 07:27:09.539343: step: 644/526, loss: 0.004243495874106884
2023-01-24 07:27:10.606189: step: 648/526, loss: 0.023387502878904343
2023-01-24 07:27:11.679613: step: 652/526, loss: 0.0025512438733130693
2023-01-24 07:27:12.749327: step: 656/526, loss: 0.0022255745716392994
2023-01-24 07:27:13.821694: step: 660/526, loss: 0.01528609823435545
2023-01-24 07:27:14.913781: step: 664/526, loss: 0.012744559906423092
2023-01-24 07:27:15.986771: step: 668/526, loss: 0.020494695752859116
2023-01-24 07:27:17.048272: step: 672/526, loss: 0.00991932675242424
2023-01-24 07:27:18.122776: step: 676/526, loss: 0.01480784360319376
2023-01-24 07:27:19.196582: step: 680/526, loss: 0.008984953165054321
2023-01-24 07:27:20.270231: step: 684/526, loss: 0.007365328259766102
2023-01-24 07:27:21.351852: step: 688/526, loss: 0.0004520653164945543
2023-01-24 07:27:22.405652: step: 692/526, loss: 0.0025731660425662994
2023-01-24 07:27:23.469473: step: 696/526, loss: 0.003520233789458871
2023-01-24 07:27:24.532335: step: 700/526, loss: 0.017229948192834854
2023-01-24 07:27:25.610942: step: 704/526, loss: 0.01180350687354803
2023-01-24 07:27:26.680229: step: 708/526, loss: 0.024067580699920654
2023-01-24 07:27:27.757146: step: 712/526, loss: 0.005620887968689203
2023-01-24 07:27:28.819915: step: 716/526, loss: 0.008405043743550777
2023-01-24 07:27:29.882896: step: 720/526, loss: 0.006112702656537294
2023-01-24 07:27:30.953821: step: 724/526, loss: 0.027457116171717644
2023-01-24 07:27:32.068013: step: 728/526, loss: 0.010533414781093597
2023-01-24 07:27:33.144081: step: 732/526, loss: 0.003400026587769389
2023-01-24 07:27:34.213964: step: 736/526, loss: 0.012767207808792591
2023-01-24 07:27:35.290985: step: 740/526, loss: 0.06059146672487259
2023-01-24 07:27:36.364343: step: 744/526, loss: 0.013861028477549553
2023-01-24 07:27:37.434500: step: 748/526, loss: 0.004016069695353508
2023-01-24 07:27:38.504822: step: 752/526, loss: 0.010700277052819729
2023-01-24 07:27:39.572811: step: 756/526, loss: 0.011772260069847107
2023-01-24 07:27:40.641109: step: 760/526, loss: 0.007367943413555622
2023-01-24 07:27:41.707975: step: 764/526, loss: 0.0037237280048429966
2023-01-24 07:27:42.781564: step: 768/526, loss: 0.01740916818380356
2023-01-24 07:27:43.856878: step: 772/526, loss: 0.0037708294112235308
2023-01-24 07:27:44.942637: step: 776/526, loss: 0.0017007385613396764
2023-01-24 07:27:46.013932: step: 780/526, loss: 0.005401583854109049
2023-01-24 07:27:47.092933: step: 784/526, loss: 0.006413219962269068
2023-01-24 07:27:48.171619: step: 788/526, loss: 0.005851361434906721
2023-01-24 07:27:49.255491: step: 792/526, loss: 0.021040815860033035
2023-01-24 07:27:50.328127: step: 796/526, loss: 0.020898278802633286
2023-01-24 07:27:51.406843: step: 800/526, loss: 0.002156848320737481
2023-01-24 07:27:52.488757: step: 804/526, loss: 0.009684685617685318
2023-01-24 07:27:53.565750: step: 808/526, loss: 0.0011495487997308373
2023-01-24 07:27:54.659222: step: 812/526, loss: 0.0066055599600076675
2023-01-24 07:27:55.727708: step: 816/526, loss: 0.004500295501202345
2023-01-24 07:27:56.822391: step: 820/526, loss: 0.0009703778778202832
2023-01-24 07:27:57.893766: step: 824/526, loss: 0.0006261609960347414
2023-01-24 07:27:58.964398: step: 828/526, loss: 0.0043951706029474735
2023-01-24 07:28:00.035534: step: 832/526, loss: 0.009856266900897026
2023-01-24 07:28:01.104659: step: 836/526, loss: 0.007887708023190498
2023-01-24 07:28:02.174316: step: 840/526, loss: 0.0017930191243067384
2023-01-24 07:28:03.245823: step: 844/526, loss: 0.005878266412764788
2023-01-24 07:28:04.310844: step: 848/526, loss: 0.009804030880331993
2023-01-24 07:28:05.378457: step: 852/526, loss: 0.0026165081653743982
2023-01-24 07:28:06.447770: step: 856/526, loss: 0.0004242129507474601
2023-01-24 07:28:07.510158: step: 860/526, loss: 0.004261369351297617
2023-01-24 07:28:08.579498: step: 864/526, loss: 0.025270730257034302
2023-01-24 07:28:09.631934: step: 868/526, loss: 2.5716413802001625e-05
2023-01-24 07:28:10.701257: step: 872/526, loss: 0.0009899325668811798
2023-01-24 07:28:11.755245: step: 876/526, loss: 0.013461158610880375
2023-01-24 07:28:12.841471: step: 880/526, loss: 0.021764567121863365
2023-01-24 07:28:13.898383: step: 884/526, loss: 0.0035536361392587423
2023-01-24 07:28:14.981156: step: 888/526, loss: 0.009750930592417717
2023-01-24 07:28:16.067616: step: 892/526, loss: 0.00548756355419755
2023-01-24 07:28:17.128791: step: 896/526, loss: 0.10667015612125397
2023-01-24 07:28:18.206861: step: 900/526, loss: 0.0003715291095431894
2023-01-24 07:28:19.264824: step: 904/526, loss: 0.014691632241010666
2023-01-24 07:28:20.333686: step: 908/526, loss: 0.002819499233737588
2023-01-24 07:28:21.401060: step: 912/526, loss: 0.01883510872721672
2023-01-24 07:28:22.469826: step: 916/526, loss: 0.00994692463427782
2023-01-24 07:28:23.565791: step: 920/526, loss: 0.005518668331205845
2023-01-24 07:28:24.653453: step: 924/526, loss: 0.029395248740911484
2023-01-24 07:28:25.736104: step: 928/526, loss: 0.00489407405257225
2023-01-24 07:28:26.808199: step: 932/526, loss: 0.0037236004136502743
2023-01-24 07:28:27.894257: step: 936/526, loss: 0.054493267089128494
2023-01-24 07:28:28.949171: step: 940/526, loss: 0.005480606108903885
2023-01-24 07:28:30.005100: step: 944/526, loss: 0.008045137859880924
2023-01-24 07:28:31.072112: step: 948/526, loss: 0.00538345193490386
2023-01-24 07:28:32.133269: step: 952/526, loss: 0.001313667744398117
2023-01-24 07:28:33.197736: step: 956/526, loss: 0.016213377937674522
2023-01-24 07:28:34.270803: step: 960/526, loss: 0.012696747668087482
2023-01-24 07:28:35.350098: step: 964/526, loss: 1.2140513717895374e-05
2023-01-24 07:28:36.434432: step: 968/526, loss: 0.0113800885155797
2023-01-24 07:28:37.522664: step: 972/526, loss: 0.009258749894797802
2023-01-24 07:28:38.574711: step: 976/526, loss: 0.01386339496821165
2023-01-24 07:28:39.640484: step: 980/526, loss: 0.0015523829497396946
2023-01-24 07:28:40.738094: step: 984/526, loss: 0.000966435472946614
2023-01-24 07:28:41.813432: step: 988/526, loss: 0.0010665992740541697
2023-01-24 07:28:42.902164: step: 992/526, loss: 0.00042779018986038864
2023-01-24 07:28:43.975053: step: 996/526, loss: 0.007841132581233978
2023-01-24 07:28:45.038789: step: 1000/526, loss: 0.0045336452312767506
2023-01-24 07:28:46.123302: step: 1004/526, loss: 0.0038128553424030542
2023-01-24 07:28:47.210070: step: 1008/526, loss: 0.0010101242223754525
2023-01-24 07:28:48.285167: step: 1012/526, loss: 0.006563783623278141
2023-01-24 07:28:49.357507: step: 1016/526, loss: 0.001392957055941224
2023-01-24 07:28:50.428092: step: 1020/526, loss: 1.8566330254543573e-05
2023-01-24 07:28:51.500110: step: 1024/526, loss: 0.03251112997531891
2023-01-24 07:28:52.557986: step: 1028/526, loss: 0.0006096226279623806
2023-01-24 07:28:53.645930: step: 1032/526, loss: 0.0047867437824606895
2023-01-24 07:28:54.732935: step: 1036/526, loss: 0.0029120836406946182
2023-01-24 07:28:55.791398: step: 1040/526, loss: 0.005305441562086344
2023-01-24 07:28:56.866588: step: 1044/526, loss: 0.010105530731379986
2023-01-24 07:28:57.939111: step: 1048/526, loss: 0.0018843625439330935
2023-01-24 07:28:59.013842: step: 1052/526, loss: 0.0015610286500304937
2023-01-24 07:29:00.073306: step: 1056/526, loss: 0.0012386649614199996
2023-01-24 07:29:01.141821: step: 1060/526, loss: 4.018219988211058e-05
2023-01-24 07:29:02.227406: step: 1064/526, loss: 0.005092525854706764
2023-01-24 07:29:03.300013: step: 1068/526, loss: 0.026332106441259384
2023-01-24 07:29:04.396983: step: 1072/526, loss: 0.012815611436963081
2023-01-24 07:29:05.461890: step: 1076/526, loss: 0.007480602245777845
2023-01-24 07:29:06.542796: step: 1080/526, loss: 0.012437943369150162
2023-01-24 07:29:07.605685: step: 1084/526, loss: 0.000634836673270911
2023-01-24 07:29:08.684898: step: 1088/526, loss: 0.008440871722996235
2023-01-24 07:29:09.742992: step: 1092/526, loss: 0.013713391497731209
2023-01-24 07:29:10.823907: step: 1096/526, loss: 0.003165673464536667
2023-01-24 07:29:11.886640: step: 1100/526, loss: 0.0009543290361762047
2023-01-24 07:29:12.972939: step: 1104/526, loss: 0.004830463789403439
2023-01-24 07:29:14.050904: step: 1108/526, loss: 0.004033912904560566
2023-01-24 07:29:15.122942: step: 1112/526, loss: 0.03303450345993042
2023-01-24 07:29:16.211711: step: 1116/526, loss: 0.026137851178646088
2023-01-24 07:29:17.277545: step: 1120/526, loss: 0.013627216219902039
2023-01-24 07:29:18.393764: step: 1124/526, loss: 0.004265769384801388
2023-01-24 07:29:19.478068: step: 1128/526, loss: 0.010463309474289417
2023-01-24 07:29:20.552803: step: 1132/526, loss: 0.0004418915486894548
2023-01-24 07:29:21.634844: step: 1136/526, loss: 0.03460986912250519
2023-01-24 07:29:22.699622: step: 1140/526, loss: 0.004669278860092163
2023-01-24 07:29:23.785535: step: 1144/526, loss: 0.0035937430802732706
2023-01-24 07:29:24.880531: step: 1148/526, loss: 0.006591061595827341
2023-01-24 07:29:25.943274: step: 1152/526, loss: 0.0002037236699834466
2023-01-24 07:29:27.009452: step: 1156/526, loss: 0.003959314897656441
2023-01-24 07:29:28.064454: step: 1160/526, loss: 0.005870916415005922
2023-01-24 07:29:29.143449: step: 1164/526, loss: 0.01081240177154541
2023-01-24 07:29:30.196688: step: 1168/526, loss: 0.001602742588147521
2023-01-24 07:29:31.284832: step: 1172/526, loss: 0.015274214558303356
2023-01-24 07:29:32.352313: step: 1176/526, loss: 0.0009931731037795544
2023-01-24 07:29:33.419617: step: 1180/526, loss: 0.006461134180426598
2023-01-24 07:29:34.482908: step: 1184/526, loss: 0.00555135915055871
2023-01-24 07:29:35.560037: step: 1188/526, loss: 0.0007979444926604629
2023-01-24 07:29:36.620292: step: 1192/526, loss: 0.003826882690191269
2023-01-24 07:29:37.691573: step: 1196/526, loss: 0.0037616360932588577
2023-01-24 07:29:38.776798: step: 1200/526, loss: 0.004110532347112894
2023-01-24 07:29:39.860988: step: 1204/526, loss: 0.006867086514830589
2023-01-24 07:29:40.929081: step: 1208/526, loss: 0.005057360976934433
2023-01-24 07:29:42.015567: step: 1212/526, loss: 0.010423664003610611
2023-01-24 07:29:43.086407: step: 1216/526, loss: 0.0005080632981844246
2023-01-24 07:29:44.150926: step: 1220/526, loss: 0.0029604537412524223
2023-01-24 07:29:45.223704: step: 1224/526, loss: 0.0038718911819159985
2023-01-24 07:29:46.299705: step: 1228/526, loss: 0.057234667241573334
2023-01-24 07:29:47.367113: step: 1232/526, loss: 0.037851374596357346
2023-01-24 07:29:48.436357: step: 1236/526, loss: 0.0024671857245266438
2023-01-24 07:29:49.517073: step: 1240/526, loss: 0.0037177084013819695
2023-01-24 07:29:50.618135: step: 1244/526, loss: 0.002856529550626874
2023-01-24 07:29:51.695086: step: 1248/526, loss: 0.0014308544341474771
2023-01-24 07:29:52.767207: step: 1252/526, loss: 0.0039054774679243565
2023-01-24 07:29:53.832745: step: 1256/526, loss: 0.0091661112383008
2023-01-24 07:29:54.896188: step: 1260/526, loss: 0.002865250688046217
2023-01-24 07:29:55.957911: step: 1264/526, loss: 0.014015741646289825
2023-01-24 07:29:57.033320: step: 1268/526, loss: 0.01665918529033661
2023-01-24 07:29:58.094120: step: 1272/526, loss: 0.003201608546078205
2023-01-24 07:29:59.172488: step: 1276/526, loss: 0.0025636558420956135
2023-01-24 07:30:00.261769: step: 1280/526, loss: 0.004745763260871172
2023-01-24 07:30:01.329996: step: 1284/526, loss: 0.00475140567868948
2023-01-24 07:30:02.393223: step: 1288/526, loss: 0.002388492226600647
2023-01-24 07:30:03.467095: step: 1292/526, loss: 0.0016680208500474691
2023-01-24 07:30:04.526714: step: 1296/526, loss: 0.005548520013689995
2023-01-24 07:30:05.599992: step: 1300/526, loss: 0.00956171564757824
2023-01-24 07:30:06.670884: step: 1304/526, loss: 0.008312403224408627
2023-01-24 07:30:07.735316: step: 1308/526, loss: 0.0041682836599648
2023-01-24 07:30:08.804843: step: 1312/526, loss: 0.0015386065933853388
2023-01-24 07:30:09.888468: step: 1316/526, loss: 0.004809641279280186
2023-01-24 07:30:10.971081: step: 1320/526, loss: 0.0071939947083592415
2023-01-24 07:30:12.032797: step: 1324/526, loss: 0.0008508415194228292
2023-01-24 07:30:13.105638: step: 1328/526, loss: 0.03499884903430939
2023-01-24 07:30:14.169503: step: 1332/526, loss: 0.012733954936265945
2023-01-24 07:30:15.257213: step: 1336/526, loss: 0.0029565789736807346
2023-01-24 07:30:16.335046: step: 1340/526, loss: 0.0044716433621943
2023-01-24 07:30:17.419655: step: 1344/526, loss: 7.427403033943847e-05
2023-01-24 07:30:18.497159: step: 1348/526, loss: 0.007862232625484467
2023-01-24 07:30:19.605270: step: 1352/526, loss: 0.0009374048677273095
2023-01-24 07:30:20.679007: step: 1356/526, loss: 0.009015649557113647
2023-01-24 07:30:21.724447: step: 1360/526, loss: 0.021186884492635727
2023-01-24 07:30:22.807993: step: 1364/526, loss: 0.029067885130643845
2023-01-24 07:30:23.881313: step: 1368/526, loss: 0.0068560135550796986
2023-01-24 07:30:24.977149: step: 1372/526, loss: 0.013239089399576187
2023-01-24 07:30:26.060948: step: 1376/526, loss: 0.005027777049690485
2023-01-24 07:30:27.136947: step: 1380/526, loss: 0.09782104194164276
2023-01-24 07:30:28.223671: step: 1384/526, loss: 0.020495202392339706
2023-01-24 07:30:29.309840: step: 1388/526, loss: 0.0003649875579867512
2023-01-24 07:30:30.387633: step: 1392/526, loss: 0.0015582585474476218
2023-01-24 07:30:31.452328: step: 1396/526, loss: 0.006838055327534676
2023-01-24 07:30:32.535422: step: 1400/526, loss: 0.003772750962525606
2023-01-24 07:30:33.600961: step: 1404/526, loss: 0.0011949347099289298
2023-01-24 07:30:34.691682: step: 1408/526, loss: 0.0057137152180075645
2023-01-24 07:30:35.769678: step: 1412/526, loss: 0.006231048610061407
2023-01-24 07:30:36.833245: step: 1416/526, loss: 0.008469206281006336
2023-01-24 07:30:37.894082: step: 1420/526, loss: 0.020381668582558632
2023-01-24 07:30:38.967003: step: 1424/526, loss: 0.003002460580319166
2023-01-24 07:30:40.019932: step: 1428/526, loss: 0.004201877862215042
2023-01-24 07:30:41.089285: step: 1432/526, loss: 0.011313398368656635
2023-01-24 07:30:42.169958: step: 1436/526, loss: 0.053479019552469254
2023-01-24 07:30:43.234642: step: 1440/526, loss: 0.0016285593155771494
2023-01-24 07:30:44.303405: step: 1444/526, loss: 0.01658998243510723
2023-01-24 07:30:45.371374: step: 1448/526, loss: 0.0026117165107280016
2023-01-24 07:30:46.460844: step: 1452/526, loss: 0.002124648541212082
2023-01-24 07:30:47.539700: step: 1456/526, loss: 0.017595259472727776
2023-01-24 07:30:48.624996: step: 1460/526, loss: 0.0003547028172761202
2023-01-24 07:30:49.708352: step: 1464/526, loss: 0.0035118036903440952
2023-01-24 07:30:50.773425: step: 1468/526, loss: 0.008548315614461899
2023-01-24 07:30:51.842897: step: 1472/526, loss: 0.005818708799779415
2023-01-24 07:30:52.923292: step: 1476/526, loss: 0.009090069681406021
2023-01-24 07:30:54.006117: step: 1480/526, loss: 0.005407553631812334
2023-01-24 07:30:55.097933: step: 1484/526, loss: 0.005108366720378399
2023-01-24 07:30:56.175420: step: 1488/526, loss: 0.025298217311501503
2023-01-24 07:30:57.239883: step: 1492/526, loss: 0.004251240286976099
2023-01-24 07:30:58.316158: step: 1496/526, loss: 0.03473653271794319
2023-01-24 07:30:59.383599: step: 1500/526, loss: 0.013348586857318878
2023-01-24 07:31:00.464113: step: 1504/526, loss: 0.006600175052881241
2023-01-24 07:31:01.523290: step: 1508/526, loss: 0.008938651531934738
2023-01-24 07:31:02.600011: step: 1512/526, loss: 0.002422742312774062
2023-01-24 07:31:03.659629: step: 1516/526, loss: 0.003078901208937168
2023-01-24 07:31:04.738597: step: 1520/526, loss: 0.016226626932621002
2023-01-24 07:31:05.815121: step: 1524/526, loss: 0.0006655099568888545
2023-01-24 07:31:06.879981: step: 1528/526, loss: 0.0012265611439943314
2023-01-24 07:31:07.954054: step: 1532/526, loss: 0.005088868085294962
2023-01-24 07:31:09.011977: step: 1536/526, loss: 0.0010596613865345716
2023-01-24 07:31:10.086238: step: 1540/526, loss: 0.009277921169996262
2023-01-24 07:31:11.154928: step: 1544/526, loss: 0.014644542708992958
2023-01-24 07:31:12.223195: step: 1548/526, loss: 0.005800127983093262
2023-01-24 07:31:13.323634: step: 1552/526, loss: 0.011130206286907196
2023-01-24 07:31:14.384168: step: 1556/526, loss: 0.002271250355988741
2023-01-24 07:31:15.451167: step: 1560/526, loss: 0.004625855945050716
2023-01-24 07:31:16.516184: step: 1564/526, loss: 0.00019734085071831942
2023-01-24 07:31:17.596526: step: 1568/526, loss: 0.002903470303863287
2023-01-24 07:31:18.688589: step: 1572/526, loss: 0.0055061206221580505
2023-01-24 07:31:19.751758: step: 1576/526, loss: 0.014441757462918758
2023-01-24 07:31:20.819241: step: 1580/526, loss: 0.0029819512274116278
2023-01-24 07:31:21.873820: step: 1584/526, loss: 0.015545613132417202
2023-01-24 07:31:22.962240: step: 1588/526, loss: 0.0005880399839952588
2023-01-24 07:31:24.040434: step: 1592/526, loss: 0.005186446476727724
2023-01-24 07:31:25.116117: step: 1596/526, loss: 0.043246544897556305
2023-01-24 07:31:26.190330: step: 1600/526, loss: 0.007097621913999319
2023-01-24 07:31:27.281821: step: 1604/526, loss: 0.006098034791648388
2023-01-24 07:31:28.365219: step: 1608/526, loss: 0.007078444119542837
2023-01-24 07:31:29.444445: step: 1612/526, loss: 0.017605388537049294
2023-01-24 07:31:30.516061: step: 1616/526, loss: 0.004377124365419149
2023-01-24 07:31:31.587018: step: 1620/526, loss: 0.0048618135042488575
2023-01-24 07:31:32.651389: step: 1624/526, loss: 0.0027774160262197256
2023-01-24 07:31:33.733831: step: 1628/526, loss: 0.004077346064150333
2023-01-24 07:31:34.808702: step: 1632/526, loss: 0.038192201405763626
2023-01-24 07:31:35.856351: step: 1636/526, loss: 0.017146332189440727
2023-01-24 07:31:36.934931: step: 1640/526, loss: 0.014185166917741299
2023-01-24 07:31:37.985876: step: 1644/526, loss: 0.002837585285305977
2023-01-24 07:31:39.057368: step: 1648/526, loss: 0.005212290212512016
2023-01-24 07:31:40.124511: step: 1652/526, loss: 0.0020114383660256863
2023-01-24 07:31:41.199736: step: 1656/526, loss: 0.008721740916371346
2023-01-24 07:31:42.265155: step: 1660/526, loss: 0.004408359527587891
2023-01-24 07:31:43.348484: step: 1664/526, loss: 0.004980864934623241
2023-01-24 07:31:44.436041: step: 1668/526, loss: 0.004344732966274023
2023-01-24 07:31:45.511609: step: 1672/526, loss: 0.000978962634690106
2023-01-24 07:31:46.607366: step: 1676/526, loss: 0.0012102506589144468
2023-01-24 07:31:47.684521: step: 1680/526, loss: 0.00945677887648344
2023-01-24 07:31:48.756018: step: 1684/526, loss: 0.004169594030827284
2023-01-24 07:31:49.812721: step: 1688/526, loss: 1.1368526429578196e-05
2023-01-24 07:31:50.877975: step: 1692/526, loss: 0.0006582618225365877
2023-01-24 07:31:51.954450: step: 1696/526, loss: 0.007216115947812796
2023-01-24 07:31:53.033915: step: 1700/526, loss: 0.008537952788174152
2023-01-24 07:31:54.088219: step: 1704/526, loss: 0.008632871322333813
2023-01-24 07:31:55.168786: step: 1708/526, loss: 0.0029105464927852154
2023-01-24 07:31:56.241099: step: 1712/526, loss: 0.001449619885534048
2023-01-24 07:31:57.301467: step: 1716/526, loss: 0.00844323169440031
2023-01-24 07:31:58.364751: step: 1720/526, loss: 0.014320994727313519
2023-01-24 07:31:59.427542: step: 1724/526, loss: 0.0012402012944221497
2023-01-24 07:32:00.503741: step: 1728/526, loss: 0.0024995682761073112
2023-01-24 07:32:01.595603: step: 1732/526, loss: 0.002082785591483116
2023-01-24 07:32:02.649219: step: 1736/526, loss: 0.00018656860629562289
2023-01-24 07:32:03.746811: step: 1740/526, loss: 0.0029906679410487413
2023-01-24 07:32:04.832575: step: 1744/526, loss: 0.007322310004383326
2023-01-24 07:32:05.914100: step: 1748/526, loss: 0.011403138749301434
2023-01-24 07:32:07.001973: step: 1752/526, loss: 0.01549022737890482
2023-01-24 07:32:08.064220: step: 1756/526, loss: 0.05550411343574524
2023-01-24 07:32:09.136069: step: 1760/526, loss: 0.006561277899891138
2023-01-24 07:32:10.207223: step: 1764/526, loss: 0.01718747429549694
2023-01-24 07:32:11.277677: step: 1768/526, loss: 0.0062029482796788216
2023-01-24 07:32:12.343742: step: 1772/526, loss: 0.015745092183351517
2023-01-24 07:32:13.411244: step: 1776/526, loss: 0.023954901844263077
2023-01-24 07:32:14.476043: step: 1780/526, loss: 0.006017810199409723
2023-01-24 07:32:15.542007: step: 1784/526, loss: 0.012075243517756462
2023-01-24 07:32:16.601565: step: 1788/526, loss: 0.005847611464560032
2023-01-24 07:32:17.678905: step: 1792/526, loss: 0.002950123278424144
2023-01-24 07:32:18.735531: step: 1796/526, loss: 0.009506269358098507
2023-01-24 07:32:19.804357: step: 1800/526, loss: 0.0029114210046827793
2023-01-24 07:32:20.880340: step: 1804/526, loss: 0.0005668816738761961
2023-01-24 07:32:21.943780: step: 1808/526, loss: 0.010006722062826157
2023-01-24 07:32:23.006819: step: 1812/526, loss: 0.0024292946327477694
2023-01-24 07:32:24.081834: step: 1816/526, loss: 0.005452687386423349
2023-01-24 07:32:25.143022: step: 1820/526, loss: 0.0046021295711398125
2023-01-24 07:32:26.199184: step: 1824/526, loss: 0.007638941053301096
2023-01-24 07:32:27.258178: step: 1828/526, loss: 0.0063230618834495544
2023-01-24 07:32:28.340247: step: 1832/526, loss: 0.005664732772856951
2023-01-24 07:32:29.414838: step: 1836/526, loss: 0.004440494813024998
2023-01-24 07:32:30.468575: step: 1840/526, loss: 0.015246671624481678
2023-01-24 07:32:31.518241: step: 1844/526, loss: 0.004059979692101479
2023-01-24 07:32:32.589255: step: 1848/526, loss: 5.105124364490621e-05
2023-01-24 07:32:33.656923: step: 1852/526, loss: 0.007765565533190966
2023-01-24 07:32:34.718538: step: 1856/526, loss: 0.00982578843832016
2023-01-24 07:32:35.801801: step: 1860/526, loss: 0.005411851219832897
2023-01-24 07:32:36.874506: step: 1864/526, loss: 0.02710109017789364
2023-01-24 07:32:37.946225: step: 1868/526, loss: 0.005173692479729652
2023-01-24 07:32:39.005168: step: 1872/526, loss: 0.008736705407500267
2023-01-24 07:32:40.075268: step: 1876/526, loss: 0.00696840463206172
2023-01-24 07:32:41.140511: step: 1880/526, loss: 0.01092579960823059
2023-01-24 07:32:42.234437: step: 1884/526, loss: 0.0038575599901378155
2023-01-24 07:32:43.308408: step: 1888/526, loss: 0.00013975257752463222
2023-01-24 07:32:44.377212: step: 1892/526, loss: 0.006790732499212027
2023-01-24 07:32:45.450524: step: 1896/526, loss: 0.006647312548011541
2023-01-24 07:32:46.511332: step: 1900/526, loss: 0.007207388058304787
2023-01-24 07:32:47.579050: step: 1904/526, loss: 0.030093692243099213
2023-01-24 07:32:48.645556: step: 1908/526, loss: 0.054702356457710266
2023-01-24 07:32:49.723415: step: 1912/526, loss: 0.0034478632733225822
2023-01-24 07:32:50.803836: step: 1916/526, loss: 0.007571808993816376
2023-01-24 07:32:51.881493: step: 1920/526, loss: 0.013936576433479786
2023-01-24 07:32:52.946827: step: 1924/526, loss: 0.005216843914240599
2023-01-24 07:32:53.997551: step: 1928/526, loss: 0.0012667336268350482
2023-01-24 07:32:55.063090: step: 1932/526, loss: 0.01398126594722271
2023-01-24 07:32:56.130893: step: 1936/526, loss: 0.0038864300586283207
2023-01-24 07:32:57.196760: step: 1940/526, loss: 0.004495956469327211
2023-01-24 07:32:58.280840: step: 1944/526, loss: 0.012851502746343613
2023-01-24 07:32:59.352670: step: 1948/526, loss: 0.0078731132671237
2023-01-24 07:33:00.438002: step: 1952/526, loss: 0.003647000063210726
2023-01-24 07:33:01.512938: step: 1956/526, loss: 0.00452793063595891
2023-01-24 07:33:02.590042: step: 1960/526, loss: 0.005784343462437391
2023-01-24 07:33:03.660987: step: 1964/526, loss: 0.006865252275019884
2023-01-24 07:33:04.740766: step: 1968/526, loss: 0.00446565356105566
2023-01-24 07:33:05.795817: step: 1972/526, loss: 0.0005312049761414528
2023-01-24 07:33:06.859045: step: 1976/526, loss: 0.01868703030049801
2023-01-24 07:33:07.920465: step: 1980/526, loss: 0.008483445271849632
2023-01-24 07:33:08.999747: step: 1984/526, loss: 0.05349397659301758
2023-01-24 07:33:10.063022: step: 1988/526, loss: 0.004792788997292519
2023-01-24 07:33:11.142081: step: 1992/526, loss: 0.0016174135962501168
2023-01-24 07:33:12.207395: step: 1996/526, loss: 0.004809586331248283
2023-01-24 07:33:13.266018: step: 2000/526, loss: 0.00432139215990901
2023-01-24 07:33:14.340697: step: 2004/526, loss: 0.006920506712049246
2023-01-24 07:33:15.409084: step: 2008/526, loss: 0.007075745612382889
2023-01-24 07:33:16.476037: step: 2012/526, loss: 0.0050687906332314014
2023-01-24 07:33:17.559069: step: 2016/526, loss: 0.017767786979675293
2023-01-24 07:33:18.642958: step: 2020/526, loss: 0.004493189509958029
2023-01-24 07:33:19.713253: step: 2024/526, loss: 0.004642934072762728
2023-01-24 07:33:20.787128: step: 2028/526, loss: 0.004403568338602781
2023-01-24 07:33:21.845718: step: 2032/526, loss: 0.006857232190668583
2023-01-24 07:33:22.914092: step: 2036/526, loss: 0.012456074357032776
2023-01-24 07:33:23.990239: step: 2040/526, loss: 0.012994619086384773
2023-01-24 07:33:25.077158: step: 2044/526, loss: 0.005447262432426214
2023-01-24 07:33:26.143573: step: 2048/526, loss: 0.01025354117155075
2023-01-24 07:33:27.213723: step: 2052/526, loss: 0.053243450820446014
2023-01-24 07:33:28.278188: step: 2056/526, loss: 0.019626379013061523
2023-01-24 07:33:29.338692: step: 2060/526, loss: 0.07240425050258636
2023-01-24 07:33:30.402810: step: 2064/526, loss: 0.006490351632237434
2023-01-24 07:33:31.483219: step: 2068/526, loss: 0.030568212270736694
2023-01-24 07:33:32.565153: step: 2072/526, loss: 0.01846432127058506
2023-01-24 07:33:33.651171: step: 2076/526, loss: 0.002376555697992444
2023-01-24 07:33:34.721618: step: 2080/526, loss: 0.0010407415684312582
2023-01-24 07:33:35.799528: step: 2084/526, loss: 0.005833109840750694
2023-01-24 07:33:36.873807: step: 2088/526, loss: 0.006362421438097954
2023-01-24 07:33:37.955013: step: 2092/526, loss: 0.005434426013380289
2023-01-24 07:33:39.024559: step: 2096/526, loss: 0.003740588901564479
2023-01-24 07:33:40.117248: step: 2100/526, loss: 0.0039010117761790752
2023-01-24 07:33:41.192213: step: 2104/526, loss: 0.03432996943593025
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3632367792875505, 'r': 0.26811974789915966, 'f1': 0.30851333437305056}, 'combined': 0.22732561480119515, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36157158659924143, 'r': 0.22428685792706834, 'f1': 0.2768441961764943}, 'combined': 0.1510059251871787, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3382964915040906, 'r': 0.29143568717809704, 'f1': 0.3131225425950196}, 'combined': 0.23072187349106704, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3599106857350851, 'r': 0.2588195782138855, 'f1': 0.3011067578369099}, 'combined': 0.16424004972922357, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36033626748889336, 'r': 0.3124737651658904, 'f1': 0.3347025899236265}, 'combined': 0.24662296099635636, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36505321592365475, 'r': 0.27621135367690985, 'f1': 0.3144781349675651}, 'combined': 0.1715335281641264, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377168646452016, 'r': 0.29285883708322036, 'f1': 0.31369229094076656}, 'combined': 0.23114168806161745, 'stategy': 1, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36076020150542065, 'r': 0.2604206761095854, 'f1': 0.30248650264375865}, 'combined': 0.16499263780568652, 'stategy': 1, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 07:36:23.393603: step: 4/526, loss: 0.010899268090724945
2023-01-24 07:36:24.449755: step: 8/526, loss: 0.0030616391450166702
2023-01-24 07:36:25.524861: step: 12/526, loss: 0.01314435712993145
2023-01-24 07:36:26.572071: step: 16/526, loss: 0.0002661587204784155
2023-01-24 07:36:27.633878: step: 20/526, loss: 0.008434689603745937
2023-01-24 07:36:28.684210: step: 24/526, loss: 0.005727472715079784
2023-01-24 07:36:29.737575: step: 28/526, loss: 0.005028573330491781
2023-01-24 07:36:30.809941: step: 32/526, loss: 0.019856305792927742
2023-01-24 07:36:31.887992: step: 36/526, loss: 0.002529808785766363
2023-01-24 07:36:32.954203: step: 40/526, loss: 0.002600078471004963
2023-01-24 07:36:34.023675: step: 44/526, loss: 0.022507553920149803
2023-01-24 07:36:35.075827: step: 48/526, loss: 0.006190139334648848
2023-01-24 07:36:36.138187: step: 52/526, loss: 0.019749416038393974
2023-01-24 07:36:37.189103: step: 56/526, loss: 0.0069786179810762405
2023-01-24 07:36:38.248754: step: 60/526, loss: 0.003600344993174076
2023-01-24 07:36:39.321323: step: 64/526, loss: 0.007230598945170641
2023-01-24 07:36:40.384603: step: 68/526, loss: 0.005291781388223171
2023-01-24 07:36:41.449440: step: 72/526, loss: 0.0035029686987400055
2023-01-24 07:36:42.501553: step: 76/526, loss: 0.0026197240222245455
2023-01-24 07:36:43.566429: step: 80/526, loss: 0.007565547712147236
2023-01-24 07:36:44.620904: step: 84/526, loss: 0.0021991266403347254
2023-01-24 07:36:45.675605: step: 88/526, loss: 0.000680313678458333
2023-01-24 07:36:46.745132: step: 92/526, loss: 0.01031088549643755
2023-01-24 07:36:47.790504: step: 96/526, loss: 0.0050867400132119656
2023-01-24 07:36:48.832039: step: 100/526, loss: 0.0
2023-01-24 07:36:49.898184: step: 104/526, loss: 0.003087876131758094
2023-01-24 07:36:50.952851: step: 108/526, loss: 0.003220552345737815
2023-01-24 07:36:52.016952: step: 112/526, loss: 0.028040826320648193
2023-01-24 07:36:53.077536: step: 116/526, loss: 0.004460204858332872
2023-01-24 07:36:54.152068: step: 120/526, loss: 0.004889460280537605
2023-01-24 07:36:55.234769: step: 124/526, loss: 0.004017074126750231
2023-01-24 07:36:56.289772: step: 128/526, loss: 0.008606400340795517
2023-01-24 07:36:57.336691: step: 132/526, loss: 0.0019883138593286276
2023-01-24 07:36:58.407362: step: 136/526, loss: 0.0025338460691273212
2023-01-24 07:36:59.477003: step: 140/526, loss: 0.019969364628195763
2023-01-24 07:37:00.543851: step: 144/526, loss: 0.007962181232869625
2023-01-24 07:37:01.620014: step: 148/526, loss: 0.0053929053246974945
2023-01-24 07:37:02.680889: step: 152/526, loss: 0.004747800063341856
2023-01-24 07:37:03.747881: step: 156/526, loss: 0.006381009239703417
2023-01-24 07:37:04.804216: step: 160/526, loss: 0.0004650416085496545
2023-01-24 07:37:05.857527: step: 164/526, loss: 0.0014457793440669775
2023-01-24 07:37:06.912272: step: 168/526, loss: 0.01151053886860609
2023-01-24 07:37:07.966941: step: 172/526, loss: 0.004655364900827408
2023-01-24 07:37:09.048636: step: 176/526, loss: 0.004202236421406269
2023-01-24 07:37:10.113826: step: 180/526, loss: 0.0007839004974812269
2023-01-24 07:37:11.172666: step: 184/526, loss: 0.0025609065778553486
2023-01-24 07:37:12.233257: step: 188/526, loss: 0.0008630530210211873
2023-01-24 07:37:13.316630: step: 192/526, loss: 0.008424773812294006
2023-01-24 07:37:14.373599: step: 196/526, loss: 0.0018581899348646402
2023-01-24 07:37:15.442185: step: 200/526, loss: 0.008963003754615784
2023-01-24 07:37:16.510277: step: 204/526, loss: 0.0008392927120439708
2023-01-24 07:37:17.579180: step: 208/526, loss: 0.0008842563256621361
2023-01-24 07:37:18.672007: step: 212/526, loss: 0.005269532557576895
2023-01-24 07:37:19.740319: step: 216/526, loss: 0.04264936223626137
2023-01-24 07:37:20.809261: step: 220/526, loss: 0.03305068239569664
2023-01-24 07:37:21.861988: step: 224/526, loss: 0.0007441497873514891
2023-01-24 07:37:22.921775: step: 228/526, loss: 0.02527272142469883
2023-01-24 07:37:23.993603: step: 232/526, loss: 0.00832196231931448
2023-01-24 07:37:25.082587: step: 236/526, loss: 0.004788657650351524
2023-01-24 07:37:26.182589: step: 240/526, loss: 0.005434014834463596
2023-01-24 07:37:27.246892: step: 244/526, loss: 0.001945069176144898
2023-01-24 07:37:28.316014: step: 248/526, loss: 0.0
2023-01-24 07:37:29.390112: step: 252/526, loss: 0.0004295838880352676
2023-01-24 07:37:30.453801: step: 256/526, loss: 0.0034755917731672525
2023-01-24 07:37:31.526662: step: 260/526, loss: 0.00377582386136055
2023-01-24 07:37:32.599111: step: 264/526, loss: 0.048546332865953445
2023-01-24 07:37:33.664766: step: 268/526, loss: 0.0016245838487520814
2023-01-24 07:37:34.729068: step: 272/526, loss: 0.002566190203651786
2023-01-24 07:37:35.785300: step: 276/526, loss: 0.002763283671811223
2023-01-24 07:37:36.844763: step: 280/526, loss: 6.963249325053766e-05
2023-01-24 07:37:37.917193: step: 284/526, loss: 0.009911938570439816
2023-01-24 07:37:38.994225: step: 288/526, loss: 0.026897506788372993
2023-01-24 07:37:40.067268: step: 292/526, loss: 0.007379285991191864
2023-01-24 07:37:41.143555: step: 296/526, loss: 0.01772451400756836
2023-01-24 07:37:42.218556: step: 300/526, loss: 0.01802189089357853
2023-01-24 07:37:43.318834: step: 304/526, loss: 0.0012491790112107992
2023-01-24 07:37:44.395732: step: 308/526, loss: 0.0023968906607478857
2023-01-24 07:37:45.461999: step: 312/526, loss: 0.013670278713107109
2023-01-24 07:37:46.519827: step: 316/526, loss: 0.003918391186743975
2023-01-24 07:37:47.585940: step: 320/526, loss: 0.001893170876428485
2023-01-24 07:37:48.658820: step: 324/526, loss: 0.007293326780200005
2023-01-24 07:37:49.712123: step: 328/526, loss: 0.021721050143241882
2023-01-24 07:37:50.766709: step: 332/526, loss: 0.0015705113764852285
2023-01-24 07:37:51.834551: step: 336/526, loss: 0.007181911263614893
2023-01-24 07:37:52.900746: step: 340/526, loss: 0.0011621711309999228
2023-01-24 07:37:53.988396: step: 344/526, loss: 0.009121734648942947
2023-01-24 07:37:55.057069: step: 348/526, loss: 0.019756240770220757
2023-01-24 07:37:56.131216: step: 352/526, loss: 0.03507305681705475
2023-01-24 07:37:57.197417: step: 356/526, loss: 0.0035847711842507124
2023-01-24 07:37:58.261060: step: 360/526, loss: 0.0020180491264909506
2023-01-24 07:37:59.326794: step: 364/526, loss: 0.004328557290136814
2023-01-24 07:38:00.384020: step: 368/526, loss: 0.0011874393094331026
2023-01-24 07:38:01.454534: step: 372/526, loss: 0.0040312777273356915
2023-01-24 07:38:02.546748: step: 376/526, loss: 0.0044716899283230305
2023-01-24 07:38:03.620592: step: 380/526, loss: 0.010534740053117275
2023-01-24 07:38:04.686154: step: 384/526, loss: 0.0006007138290442526
2023-01-24 07:38:05.760978: step: 388/526, loss: 0.0030399055685847998
2023-01-24 07:38:06.826124: step: 392/526, loss: 0.0009213355951942503
2023-01-24 07:38:07.886985: step: 396/526, loss: 0.004745754878968
2023-01-24 07:38:08.931779: step: 400/526, loss: 0.002493172651156783
2023-01-24 07:38:09.996793: step: 404/526, loss: 0.0021334898192435503
2023-01-24 07:38:11.066287: step: 408/526, loss: 0.007485872600227594
2023-01-24 07:38:12.125917: step: 412/526, loss: 0.004724218510091305
2023-01-24 07:38:13.194317: step: 416/526, loss: 0.013886557891964912
2023-01-24 07:38:14.264753: step: 420/526, loss: 0.0035828452091664076
2023-01-24 07:38:15.333304: step: 424/526, loss: 0.00639519514515996
2023-01-24 07:38:16.396875: step: 428/526, loss: 0.0055870735086500645
2023-01-24 07:38:17.453020: step: 432/526, loss: 0.001009528641588986
2023-01-24 07:38:18.506432: step: 436/526, loss: 0.012413972988724709
2023-01-24 07:38:19.588036: step: 440/526, loss: 0.0059785377234220505
2023-01-24 07:38:20.646389: step: 444/526, loss: 0.015663810074329376
2023-01-24 07:38:21.702663: step: 448/526, loss: 0.014677578583359718
2023-01-24 07:38:22.758278: step: 452/526, loss: 0.003707374446094036
2023-01-24 07:38:23.823306: step: 456/526, loss: 0.0025234143249690533
2023-01-24 07:38:24.891455: step: 460/526, loss: 0.00508946692571044
2023-01-24 07:38:25.966385: step: 464/526, loss: 0.011581063270568848
2023-01-24 07:38:27.036944: step: 468/526, loss: 0.004123955499380827
2023-01-24 07:38:28.127239: step: 472/526, loss: 0.002478219335898757
2023-01-24 07:38:29.196977: step: 476/526, loss: 0.009361781179904938
2023-01-24 07:38:30.288965: step: 480/526, loss: 0.0031668555457144976
2023-01-24 07:38:31.351093: step: 484/526, loss: 0.01846126839518547
2023-01-24 07:38:32.420145: step: 488/526, loss: 0.00579203013330698
2023-01-24 07:38:33.480471: step: 492/526, loss: 0.004004118964076042
2023-01-24 07:38:34.568511: step: 496/526, loss: 0.010433213785290718
2023-01-24 07:38:35.653277: step: 500/526, loss: 0.0012413881486281753
2023-01-24 07:38:36.723247: step: 504/526, loss: 0.052186258137226105
2023-01-24 07:38:37.806792: step: 508/526, loss: 0.004598609171807766
2023-01-24 07:38:38.873269: step: 512/526, loss: 0.00733589380979538
2023-01-24 07:38:39.963783: step: 516/526, loss: 0.011689831502735615
2023-01-24 07:38:41.027485: step: 520/526, loss: 0.00664775725454092
2023-01-24 07:38:42.120288: step: 524/526, loss: 0.012676513753831387
2023-01-24 07:38:43.196879: step: 528/526, loss: 0.013543674722313881
2023-01-24 07:38:44.263848: step: 532/526, loss: 0.00021971965907141566
2023-01-24 07:38:45.346669: step: 536/526, loss: 0.0045703742653131485
2023-01-24 07:38:46.403373: step: 540/526, loss: 0.0020279698073863983
2023-01-24 07:38:47.490936: step: 544/526, loss: 0.019192779436707497
2023-01-24 07:38:48.558271: step: 548/526, loss: 0.006866115611046553
2023-01-24 07:38:49.624148: step: 552/526, loss: 0.008568652905523777
2023-01-24 07:38:50.691539: step: 556/526, loss: 0.002849880140274763
2023-01-24 07:38:51.765965: step: 560/526, loss: 0.007152759935706854
2023-01-24 07:38:52.857542: step: 564/526, loss: 0.002433264395222068
2023-01-24 07:38:53.928097: step: 568/526, loss: 0.005239705555140972
2023-01-24 07:38:54.997974: step: 572/526, loss: 0.008249285630881786
2023-01-24 07:38:56.085138: step: 576/526, loss: 0.0074399858713150024
2023-01-24 07:38:57.145482: step: 580/526, loss: 0.007843276485800743
2023-01-24 07:38:58.209941: step: 584/526, loss: 0.009459164924919605
2023-01-24 07:38:59.269635: step: 588/526, loss: 0.012332292273640633
2023-01-24 07:39:00.331252: step: 592/526, loss: 0.0019126208499073982
2023-01-24 07:39:01.414134: step: 596/526, loss: 0.004313490819185972
2023-01-24 07:39:02.472821: step: 600/526, loss: 0.0034413503017276525
2023-01-24 07:39:03.555189: step: 604/526, loss: 0.0028735999949276447
2023-01-24 07:39:04.642873: step: 608/526, loss: 0.008208543993532658
2023-01-24 07:39:05.715083: step: 612/526, loss: 0.00790444202721119
2023-01-24 07:39:06.782589: step: 616/526, loss: 0.0035831709392368793
2023-01-24 07:39:07.849815: step: 620/526, loss: 0.004880182910710573
2023-01-24 07:39:08.913872: step: 624/526, loss: 0.0027925942558795214
2023-01-24 07:39:09.994629: step: 628/526, loss: 0.005777599755674601
2023-01-24 07:39:11.072111: step: 632/526, loss: 0.007344453129917383
2023-01-24 07:39:12.141060: step: 636/526, loss: 0.009829001501202583
2023-01-24 07:39:13.225303: step: 640/526, loss: 0.0023153286892920732
2023-01-24 07:39:14.325383: step: 644/526, loss: 0.037738338112831116
2023-01-24 07:39:15.407629: step: 648/526, loss: 0.012994375079870224
2023-01-24 07:39:16.486438: step: 652/526, loss: 0.0015481819864362478
2023-01-24 07:39:17.550670: step: 656/526, loss: 0.0017289051320403814
2023-01-24 07:39:18.623961: step: 660/526, loss: 0.002095303498208523
2023-01-24 07:39:19.715372: step: 664/526, loss: 0.008841686882078648
2023-01-24 07:39:20.775851: step: 668/526, loss: 0.0016738995909690857
2023-01-24 07:39:21.840015: step: 672/526, loss: 0.008282607421278954
2023-01-24 07:39:22.920053: step: 676/526, loss: 0.0016179295489564538
2023-01-24 07:39:23.990380: step: 680/526, loss: 0.005020576529204845
2023-01-24 07:39:25.064137: step: 684/526, loss: 0.015881359577178955
2023-01-24 07:39:26.145046: step: 688/526, loss: 0.001501933904364705
2023-01-24 07:39:27.202557: step: 692/526, loss: 0.009338192641735077
2023-01-24 07:39:28.274990: step: 696/526, loss: 0.05601728707551956
2023-01-24 07:39:29.341453: step: 700/526, loss: 0.007577328477054834
2023-01-24 07:39:30.418113: step: 704/526, loss: 0.0
2023-01-24 07:39:31.512811: step: 708/526, loss: 0.028329677879810333
2023-01-24 07:39:32.581746: step: 712/526, loss: 0.016650890931487083
2023-01-24 07:39:33.654403: step: 716/526, loss: 0.0027997170109301805
2023-01-24 07:39:34.718985: step: 720/526, loss: 0.003414830658584833
2023-01-24 07:39:35.801146: step: 724/526, loss: 0.004446730948984623
2023-01-24 07:39:36.884128: step: 728/526, loss: 0.006720058619976044
2023-01-24 07:39:37.972069: step: 732/526, loss: 0.006368011236190796
2023-01-24 07:39:39.032053: step: 736/526, loss: 0.0004205916484352201
2023-01-24 07:39:40.098149: step: 740/526, loss: 0.00021764103439636528
2023-01-24 07:39:41.198817: step: 744/526, loss: 0.005215159151703119
2023-01-24 07:39:42.271123: step: 748/526, loss: 0.011008137837052345
2023-01-24 07:39:43.354507: step: 752/526, loss: 0.0044187502935528755
2023-01-24 07:39:44.419439: step: 756/526, loss: 0.0068278443068265915
2023-01-24 07:39:45.503143: step: 760/526, loss: 0.008587944321334362
2023-01-24 07:39:46.560244: step: 764/526, loss: 0.000590951123740524
2023-01-24 07:39:47.630351: step: 768/526, loss: 0.0019527932163327932
2023-01-24 07:39:48.691288: step: 772/526, loss: 0.0036437748931348324
2023-01-24 07:39:49.765962: step: 776/526, loss: 0.008449382148683071
2023-01-24 07:39:50.843319: step: 780/526, loss: 0.006135961506515741
2023-01-24 07:39:51.916091: step: 784/526, loss: 0.004804146941751242
2023-01-24 07:39:52.981222: step: 788/526, loss: 0.0021569302771240473
2023-01-24 07:39:54.056779: step: 792/526, loss: 0.007811501156538725
2023-01-24 07:39:55.127178: step: 796/526, loss: 0.01714414358139038
2023-01-24 07:39:56.199835: step: 800/526, loss: 0.024840185418725014
2023-01-24 07:39:57.267937: step: 804/526, loss: 0.00048400156083516777
2023-01-24 07:39:58.354113: step: 808/526, loss: 0.007126195821911097
2023-01-24 07:39:59.427047: step: 812/526, loss: 8.099444676190615e-05
2023-01-24 07:40:00.500331: step: 816/526, loss: 0.0003011475782841444
2023-01-24 07:40:01.598218: step: 820/526, loss: 0.003924433141946793
2023-01-24 07:40:02.680036: step: 824/526, loss: 0.0013155933702364564
2023-01-24 07:40:03.750894: step: 828/526, loss: 0.0024910878855735064
2023-01-24 07:40:04.838775: step: 832/526, loss: 0.000884887995198369
2023-01-24 07:40:05.904574: step: 836/526, loss: 0.004059998784214258
2023-01-24 07:40:07.014419: step: 840/526, loss: 0.017620541155338287
2023-01-24 07:40:08.096034: step: 844/526, loss: 0.00626614922657609
2023-01-24 07:40:09.158858: step: 848/526, loss: 0.002911080839112401
2023-01-24 07:40:10.233381: step: 852/526, loss: 0.0018006776226684451
2023-01-24 07:40:11.316753: step: 856/526, loss: 0.001855318434536457
2023-01-24 07:40:12.381131: step: 860/526, loss: 0.007864564657211304
2023-01-24 07:40:13.471195: step: 864/526, loss: 0.0021635969169437885
2023-01-24 07:40:14.551546: step: 868/526, loss: 0.0037115311715751886
2023-01-24 07:40:15.624472: step: 872/526, loss: 9.951701940735802e-05
2023-01-24 07:40:16.703548: step: 876/526, loss: 0.0038975137285888195
2023-01-24 07:40:17.763063: step: 880/526, loss: 0.00393241411074996
2023-01-24 07:40:18.829218: step: 884/526, loss: 0.0
2023-01-24 07:40:19.896533: step: 888/526, loss: 0.0008587830816395581
2023-01-24 07:40:20.966616: step: 892/526, loss: 0.03417181223630905
2023-01-24 07:40:22.048796: step: 896/526, loss: 0.0010484495433047414
2023-01-24 07:40:23.121326: step: 900/526, loss: 0.0039267041720449924
2023-01-24 07:40:24.181248: step: 904/526, loss: 0.0013858022866770625
2023-01-24 07:40:25.244734: step: 908/526, loss: 0.004585203714668751
2023-01-24 07:40:26.300532: step: 912/526, loss: 0.00661693187430501
2023-01-24 07:40:27.368451: step: 916/526, loss: 0.006822461262345314
2023-01-24 07:40:28.452512: step: 920/526, loss: 0.004754720255732536
2023-01-24 07:40:29.536219: step: 924/526, loss: 0.006811104714870453
2023-01-24 07:40:30.596622: step: 928/526, loss: 0.006537212990224361
2023-01-24 07:40:31.669772: step: 932/526, loss: 0.003616190515458584
2023-01-24 07:40:32.728069: step: 936/526, loss: 0.0010003787465393543
2023-01-24 07:40:33.790362: step: 940/526, loss: 0.0031409617513418198
2023-01-24 07:40:34.872602: step: 944/526, loss: 0.001413355697877705
2023-01-24 07:40:35.938862: step: 948/526, loss: 0.0005370237049646676
2023-01-24 07:40:37.011689: step: 952/526, loss: 0.002327698515728116
2023-01-24 07:40:38.069043: step: 956/526, loss: 0.004209585953503847
2023-01-24 07:40:39.147791: step: 960/526, loss: 0.001094841631129384
2023-01-24 07:40:40.234815: step: 964/526, loss: 0.005400075577199459
2023-01-24 07:40:41.311647: step: 968/526, loss: 0.012738915160298347
2023-01-24 07:40:42.407761: step: 972/526, loss: 0.003163806861266494
2023-01-24 07:40:43.495054: step: 976/526, loss: 0.010877230204641819
2023-01-24 07:40:44.572873: step: 980/526, loss: 0.0035219392739236355
2023-01-24 07:40:45.657578: step: 984/526, loss: 0.01758062280714512
2023-01-24 07:40:46.754984: step: 988/526, loss: 0.004554011858999729
2023-01-24 07:40:47.824204: step: 992/526, loss: 0.0012336608488112688
2023-01-24 07:40:48.891016: step: 996/526, loss: 0.0016016424633562565
2023-01-24 07:40:49.943310: step: 1000/526, loss: 0.005224517080932856
2023-01-24 07:40:51.032823: step: 1004/526, loss: 0.0032092106994241476
2023-01-24 07:40:52.115375: step: 1008/526, loss: 0.0040969569236040115
2023-01-24 07:40:53.196123: step: 1012/526, loss: 0.03528813272714615
2023-01-24 07:40:54.268552: step: 1016/526, loss: 0.00044168398017063737
2023-01-24 07:40:55.346869: step: 1020/526, loss: 0.006870711222290993
2023-01-24 07:40:56.431405: step: 1024/526, loss: 0.00038013941957615316
2023-01-24 07:40:57.488273: step: 1028/526, loss: 0.00493632210418582
2023-01-24 07:40:58.567962: step: 1032/526, loss: 0.0026533312629908323
2023-01-24 07:40:59.630975: step: 1036/526, loss: 0.007120381575077772
2023-01-24 07:41:00.695338: step: 1040/526, loss: 0.008523966185748577
2023-01-24 07:41:01.781693: step: 1044/526, loss: 0.004000928718596697
2023-01-24 07:41:02.875847: step: 1048/526, loss: 0.0037398335989564657
2023-01-24 07:41:03.936032: step: 1052/526, loss: 0.003333235392346978
2023-01-24 07:41:05.014039: step: 1056/526, loss: 0.0012805245351046324
2023-01-24 07:41:06.085605: step: 1060/526, loss: 0.001410696073435247
2023-01-24 07:41:07.169883: step: 1064/526, loss: 0.007828780449926853
2023-01-24 07:41:08.230498: step: 1068/526, loss: 0.0003510605019982904
2023-01-24 07:41:09.295476: step: 1072/526, loss: 0.01994696818292141
2023-01-24 07:41:10.387775: step: 1076/526, loss: 0.0049826474860310555
2023-01-24 07:41:11.455903: step: 1080/526, loss: 0.003470906987786293
2023-01-24 07:41:12.532529: step: 1084/526, loss: 0.002952217124402523
2023-01-24 07:41:13.598772: step: 1088/526, loss: 0.004679102450609207
2023-01-24 07:41:14.666572: step: 1092/526, loss: 0.0037274339701980352
2023-01-24 07:41:15.758057: step: 1096/526, loss: 0.006447460502386093
2023-01-24 07:41:16.820062: step: 1100/526, loss: 0.007627236191183329
2023-01-24 07:41:17.879176: step: 1104/526, loss: 0.00705467164516449
2023-01-24 07:41:18.954137: step: 1108/526, loss: 0.004185685887932777
2023-01-24 07:41:20.029002: step: 1112/526, loss: 0.008962001651525497
2023-01-24 07:41:21.117108: step: 1116/526, loss: 0.011833866126835346
2023-01-24 07:41:22.194540: step: 1120/526, loss: 0.0022730305790901184
2023-01-24 07:41:23.258755: step: 1124/526, loss: 0.0030844039283692837
2023-01-24 07:41:24.326902: step: 1128/526, loss: 0.0021184836514294147
2023-01-24 07:41:25.382084: step: 1132/526, loss: 5.327435064828023e-05
2023-01-24 07:41:26.462032: step: 1136/526, loss: 0.013489339500665665
2023-01-24 07:41:27.532625: step: 1140/526, loss: 0.0339508093893528
2023-01-24 07:41:28.582453: step: 1144/526, loss: 0.0004990124143660069
2023-01-24 07:41:29.654801: step: 1148/526, loss: 0.006240393966436386
2023-01-24 07:41:30.730013: step: 1152/526, loss: 0.008802542462944984
2023-01-24 07:41:31.801159: step: 1156/526, loss: 0.00857494119554758
2023-01-24 07:41:32.869558: step: 1160/526, loss: 0.0029678912833333015
2023-01-24 07:41:33.944786: step: 1164/526, loss: 0.0014113453216850758
2023-01-24 07:41:34.997544: step: 1168/526, loss: 0.0037383323069661856
2023-01-24 07:41:36.073555: step: 1172/526, loss: 0.0032509141601622105
2023-01-24 07:41:37.154393: step: 1176/526, loss: 0.002277893014252186
2023-01-24 07:41:38.228537: step: 1180/526, loss: 0.0013324364554136992
2023-01-24 07:41:39.292414: step: 1184/526, loss: 0.0028657233342528343
2023-01-24 07:41:40.354776: step: 1188/526, loss: 0.004632764030247927
2023-01-24 07:41:41.441495: step: 1192/526, loss: 0.007884617894887924
2023-01-24 07:41:42.513694: step: 1196/526, loss: 0.0036501542199403048
2023-01-24 07:41:43.581954: step: 1200/526, loss: 0.004037424921989441
2023-01-24 07:41:44.637240: step: 1204/526, loss: 0.009743054397404194
2023-01-24 07:41:45.715383: step: 1208/526, loss: 0.0020211022347211838
2023-01-24 07:41:46.781124: step: 1212/526, loss: 0.002254490740597248
2023-01-24 07:41:47.848534: step: 1216/526, loss: 0.00022705357696395367
2023-01-24 07:41:48.916253: step: 1220/526, loss: 0.0018595204455778003
2023-01-24 07:41:49.986695: step: 1224/526, loss: 0.0066552553325891495
2023-01-24 07:41:51.062431: step: 1228/526, loss: 0.0007397474837489426
2023-01-24 07:41:52.126844: step: 1232/526, loss: 0.00040422313031740487
2023-01-24 07:41:53.197633: step: 1236/526, loss: 0.0009621197823435068
2023-01-24 07:41:54.259605: step: 1240/526, loss: 0.010266823694109917
2023-01-24 07:41:55.328160: step: 1244/526, loss: 0.0008489550091326237
2023-01-24 07:41:56.388291: step: 1248/526, loss: 0.0022352978121489286
2023-01-24 07:41:57.433302: step: 1252/526, loss: 0.0009734187624417245
2023-01-24 07:41:58.497354: step: 1256/526, loss: 0.05258942395448685
2023-01-24 07:41:59.586224: step: 1260/526, loss: 0.0009521223837509751
2023-01-24 07:42:00.658004: step: 1264/526, loss: 0.0014694444835186005
2023-01-24 07:42:01.729038: step: 1268/526, loss: 0.0028021077159792185
2023-01-24 07:42:02.798739: step: 1272/526, loss: 0.011146968230605125
2023-01-24 07:42:03.856619: step: 1276/526, loss: 0.004251406062394381
2023-01-24 07:42:04.939566: step: 1280/526, loss: 0.00867058802396059
2023-01-24 07:42:06.012938: step: 1284/526, loss: 0.004412802401930094
2023-01-24 07:42:07.084589: step: 1288/526, loss: 0.001694925012998283
2023-01-24 07:42:08.150843: step: 1292/526, loss: 0.002022380940616131
2023-01-24 07:42:09.225115: step: 1296/526, loss: 0.008119679987430573
2023-01-24 07:42:10.300155: step: 1300/526, loss: 0.010428724810481071
2023-01-24 07:42:11.352182: step: 1304/526, loss: 0.00814066082239151
2023-01-24 07:42:12.422064: step: 1308/526, loss: 0.02768310345709324
2023-01-24 07:42:13.487112: step: 1312/526, loss: 0.0021256140898913145
2023-01-24 07:42:14.559733: step: 1316/526, loss: 0.008671700023114681
2023-01-24 07:42:15.613007: step: 1320/526, loss: 0.00039050879422575235
2023-01-24 07:42:16.657015: step: 1324/526, loss: 0.00012860716378781945
2023-01-24 07:42:17.722366: step: 1328/526, loss: 0.0033445963636040688
2023-01-24 07:42:18.797332: step: 1332/526, loss: 0.0023296927101910114
2023-01-24 07:42:19.871536: step: 1336/526, loss: 0.004069339018315077
2023-01-24 07:42:20.942993: step: 1340/526, loss: 0.0023620116990059614
2023-01-24 07:42:22.014955: step: 1344/526, loss: 0.007237502373754978
2023-01-24 07:42:23.079146: step: 1348/526, loss: 0.0007343686302192509
2023-01-24 07:42:24.159338: step: 1352/526, loss: 0.0001781665050657466
2023-01-24 07:42:25.228640: step: 1356/526, loss: 0.0065128314308822155
2023-01-24 07:42:26.296075: step: 1360/526, loss: 0.006090397015213966
2023-01-24 07:42:27.357964: step: 1364/526, loss: 0.009424989111721516
2023-01-24 07:42:28.429714: step: 1368/526, loss: 0.0043399520218372345
2023-01-24 07:42:29.492011: step: 1372/526, loss: 0.012488430365920067
2023-01-24 07:42:30.571404: step: 1376/526, loss: 0.005547517444938421
2023-01-24 07:42:31.647744: step: 1380/526, loss: 0.004449707921594381
2023-01-24 07:42:32.720163: step: 1384/526, loss: 0.018844323232769966
2023-01-24 07:42:33.792378: step: 1388/526, loss: 0.0033769886940717697
2023-01-24 07:42:34.857713: step: 1392/526, loss: 0.008900512009859085
2023-01-24 07:42:35.933812: step: 1396/526, loss: 0.007564301136881113
2023-01-24 07:42:37.011837: step: 1400/526, loss: 0.0005988328484818339
2023-01-24 07:42:38.067874: step: 1404/526, loss: 0.0028724120929837227
2023-01-24 07:42:39.140638: step: 1408/526, loss: 0.007799883838742971
2023-01-24 07:42:40.213183: step: 1412/526, loss: 0.001433442928828299
2023-01-24 07:42:41.299663: step: 1416/526, loss: 0.0012137835146859288
2023-01-24 07:42:42.363725: step: 1420/526, loss: 0.00638975203037262
2023-01-24 07:42:43.420717: step: 1424/526, loss: 0.0019523389637470245
2023-01-24 07:42:44.494108: step: 1428/526, loss: 0.015957552939653397
2023-01-24 07:42:45.545939: step: 1432/526, loss: 0.010864854790270329
2023-01-24 07:42:46.612199: step: 1436/526, loss: 0.000659624463878572
2023-01-24 07:42:47.675795: step: 1440/526, loss: 0.0093257250264287
2023-01-24 07:42:48.765634: step: 1444/526, loss: 0.03805235028266907
2023-01-24 07:42:49.814928: step: 1448/526, loss: 0.0027287560515105724
2023-01-24 07:42:50.874571: step: 1452/526, loss: 0.004940278362482786
2023-01-24 07:42:51.953259: step: 1456/526, loss: 0.008313498459756374
2023-01-24 07:42:53.026384: step: 1460/526, loss: 0.023574357852339745
2023-01-24 07:42:54.088106: step: 1464/526, loss: 0.006596646271646023
2023-01-24 07:42:55.159504: step: 1468/526, loss: 0.008456969633698463
2023-01-24 07:42:56.233302: step: 1472/526, loss: 0.004637174773961306
2023-01-24 07:42:57.282356: step: 1476/526, loss: 0.009196712635457516
2023-01-24 07:42:58.350355: step: 1480/526, loss: 0.013665327802300453
2023-01-24 07:42:59.416008: step: 1484/526, loss: 0.0036045322194695473
2023-01-24 07:43:00.500301: step: 1488/526, loss: 0.030869755893945694
2023-01-24 07:43:01.558952: step: 1492/526, loss: 0.004974499810487032
2023-01-24 07:43:02.621644: step: 1496/526, loss: 0.00295928749255836
2023-01-24 07:43:03.678819: step: 1500/526, loss: 0.004706934560090303
2023-01-24 07:43:04.771531: step: 1504/526, loss: 0.030107242986559868
2023-01-24 07:43:05.838054: step: 1508/526, loss: 0.004500477574765682
2023-01-24 07:43:06.910687: step: 1512/526, loss: 0.015397071838378906
2023-01-24 07:43:07.977783: step: 1516/526, loss: 0.002677349839359522
2023-01-24 07:43:09.026808: step: 1520/526, loss: 0.001125907525420189
2023-01-24 07:43:10.086124: step: 1524/526, loss: 0.00018671000725589693
2023-01-24 07:43:11.141009: step: 1528/526, loss: 0.008221160620450974
2023-01-24 07:43:12.197327: step: 1532/526, loss: 0.0026178406551480293
2023-01-24 07:43:13.254396: step: 1536/526, loss: 0.03792737051844597
2023-01-24 07:43:14.321100: step: 1540/526, loss: 0.00810444075614214
2023-01-24 07:43:15.379178: step: 1544/526, loss: 0.03169369697570801
2023-01-24 07:43:16.446100: step: 1548/526, loss: 0.014530322514474392
2023-01-24 07:43:17.513612: step: 1552/526, loss: 0.003152405144646764
2023-01-24 07:43:18.577801: step: 1556/526, loss: 0.0044007617980241776
2023-01-24 07:43:19.651357: step: 1560/526, loss: 0.006703834515064955
2023-01-24 07:43:20.722566: step: 1564/526, loss: 0.004929485265165567
2023-01-24 07:43:21.804172: step: 1568/526, loss: 0.013477531261742115
2023-01-24 07:43:22.882172: step: 1572/526, loss: 0.0037053553387522697
2023-01-24 07:43:23.953682: step: 1576/526, loss: 0.0017258892767131329
2023-01-24 07:43:25.004991: step: 1580/526, loss: 0.03574566915631294
2023-01-24 07:43:26.076253: step: 1584/526, loss: 0.002785998862236738
2023-01-24 07:43:27.151517: step: 1588/526, loss: 0.004753216169774532
2023-01-24 07:43:28.234724: step: 1592/526, loss: 0.00606357678771019
2023-01-24 07:43:29.335759: step: 1596/526, loss: 0.0009245178662240505
2023-01-24 07:43:30.395497: step: 1600/526, loss: 0.0007811725372448564
2023-01-24 07:43:31.454696: step: 1604/526, loss: 0.005165122915059328
2023-01-24 07:43:32.517429: step: 1608/526, loss: 0.012915108352899551
2023-01-24 07:43:33.602000: step: 1612/526, loss: 0.0039015228394418955
2023-01-24 07:43:34.678105: step: 1616/526, loss: 0.016677485778927803
2023-01-24 07:43:35.730354: step: 1620/526, loss: 0.003994401078671217
2023-01-24 07:43:36.816108: step: 1624/526, loss: 0.002671940019354224
2023-01-24 07:43:37.868412: step: 1628/526, loss: 0.00498681515455246
2023-01-24 07:43:38.928113: step: 1632/526, loss: 0.04805762320756912
2023-01-24 07:43:39.978232: step: 1636/526, loss: 0.05779241770505905
2023-01-24 07:43:41.031290: step: 1640/526, loss: 0.0033233652357012033
2023-01-24 07:43:42.113189: step: 1644/526, loss: 0.012875787913799286
2023-01-24 07:43:43.179084: step: 1648/526, loss: 0.004377391654998064
2023-01-24 07:43:44.245047: step: 1652/526, loss: 0.0019602095708251
2023-01-24 07:43:45.290691: step: 1656/526, loss: 0.013964900746941566
2023-01-24 07:43:46.349034: step: 1660/526, loss: 0.003034943016245961
2023-01-24 07:43:47.414525: step: 1664/526, loss: 0.002081464510411024
2023-01-24 07:43:48.473714: step: 1668/526, loss: 0.004796476569026709
2023-01-24 07:43:49.533931: step: 1672/526, loss: 0.011374261230230331
2023-01-24 07:43:50.589790: step: 1676/526, loss: 0.006944901309907436
2023-01-24 07:43:51.646566: step: 1680/526, loss: 0.00426824577152729
2023-01-24 07:43:52.717226: step: 1684/526, loss: 0.04126424714922905
2023-01-24 07:43:53.797219: step: 1688/526, loss: 0.005446398630738258
2023-01-24 07:43:54.861305: step: 1692/526, loss: 4.939519726576691e-07
2023-01-24 07:43:55.916143: step: 1696/526, loss: 0.008905082941055298
2023-01-24 07:43:56.987548: step: 1700/526, loss: 0.007130885496735573
2023-01-24 07:43:58.053733: step: 1704/526, loss: 0.002106334315612912
2023-01-24 07:43:59.141736: step: 1708/526, loss: 0.004011321812868118
2023-01-24 07:44:00.212137: step: 1712/526, loss: 0.010999292135238647
2023-01-24 07:44:01.279892: step: 1716/526, loss: 0.00357854668982327
2023-01-24 07:44:02.351891: step: 1720/526, loss: 0.008787340484559536
2023-01-24 07:44:03.412403: step: 1724/526, loss: 0.01996440440416336
2023-01-24 07:44:04.482402: step: 1728/526, loss: 0.006099092308431864
2023-01-24 07:44:05.567723: step: 1732/526, loss: 0.01982984133064747
2023-01-24 07:44:06.643553: step: 1736/526, loss: 0.0032578238751739264
2023-01-24 07:44:07.708894: step: 1740/526, loss: 0.011187322437763214
2023-01-24 07:44:08.797677: step: 1744/526, loss: 0.030422843992710114
2023-01-24 07:44:09.860548: step: 1748/526, loss: 0.00736046489328146
2023-01-24 07:44:10.932597: step: 1752/526, loss: 0.0023059165105223656
2023-01-24 07:44:11.995990: step: 1756/526, loss: 0.01954231783747673
2023-01-24 07:44:13.074764: step: 1760/526, loss: 0.004743980243802071
2023-01-24 07:44:14.138213: step: 1764/526, loss: 0.0045912181958556175
2023-01-24 07:44:15.218196: step: 1768/526, loss: 0.009715816006064415
2023-01-24 07:44:16.270984: step: 1772/526, loss: 0.007264117244631052
2023-01-24 07:44:17.348358: step: 1776/526, loss: 0.011482124216854572
2023-01-24 07:44:18.420168: step: 1780/526, loss: 0.011981969699263573
2023-01-24 07:44:19.491690: step: 1784/526, loss: 0.004446870181709528
2023-01-24 07:44:20.558316: step: 1788/526, loss: 0.0013532961020246148
2023-01-24 07:44:21.631329: step: 1792/526, loss: 0.008777124807238579
2023-01-24 07:44:22.693633: step: 1796/526, loss: 0.002468526130542159
2023-01-24 07:44:23.762927: step: 1800/526, loss: 0.00039130181539803743
2023-01-24 07:44:24.834353: step: 1804/526, loss: 0.004155596252530813
2023-01-24 07:44:25.894625: step: 1808/526, loss: 0.0017546814633533359
2023-01-24 07:44:26.954868: step: 1812/526, loss: 0.00041980567038990557
2023-01-24 07:44:28.019518: step: 1816/526, loss: 0.0015959583688527346
2023-01-24 07:44:29.086730: step: 1820/526, loss: 0.005487230606377125
2023-01-24 07:44:30.155002: step: 1824/526, loss: 0.014632657170295715
2023-01-24 07:44:31.205713: step: 1828/526, loss: 0.00432452792301774
2023-01-24 07:44:32.284623: step: 1832/526, loss: 0.00875879917293787
2023-01-24 07:44:33.348975: step: 1836/526, loss: 0.003968818578869104
2023-01-24 07:44:34.416426: step: 1840/526, loss: 0.0019335468532517552
2023-01-24 07:44:35.468117: step: 1844/526, loss: 0.004339843522757292
2023-01-24 07:44:36.535949: step: 1848/526, loss: 0.005686920136213303
2023-01-24 07:44:37.611132: step: 1852/526, loss: 0.0038829019758850336
2023-01-24 07:44:38.693594: step: 1856/526, loss: 0.001413828693330288
2023-01-24 07:44:39.749803: step: 1860/526, loss: 0.009554093703627586
2023-01-24 07:44:40.810879: step: 1864/526, loss: 0.008032902143895626
2023-01-24 07:44:41.879766: step: 1868/526, loss: 0.0013813204132020473
2023-01-24 07:44:42.943763: step: 1872/526, loss: 0.00010282945731887594
2023-01-24 07:44:44.007366: step: 1876/526, loss: 0.0037616966292262077
2023-01-24 07:44:45.079216: step: 1880/526, loss: 0.007655742112547159
2023-01-24 07:44:46.151531: step: 1884/526, loss: 0.02388540841639042
2023-01-24 07:44:47.225639: step: 1888/526, loss: 0.022810786962509155
2023-01-24 07:44:48.297523: step: 1892/526, loss: 0.02503994293510914
2023-01-24 07:44:49.367323: step: 1896/526, loss: 0.00503999600186944
2023-01-24 07:44:50.452052: step: 1900/526, loss: 0.02420971542596817
2023-01-24 07:44:51.510110: step: 1904/526, loss: 0.0004633065254893154
2023-01-24 07:44:52.573950: step: 1908/526, loss: 0.0007413079147227108
2023-01-24 07:44:53.644630: step: 1912/526, loss: 0.00847114808857441
2023-01-24 07:44:54.711208: step: 1916/526, loss: 0.039886489510536194
2023-01-24 07:44:55.772473: step: 1920/526, loss: 0.018483810126781464
2023-01-24 07:44:56.831658: step: 1924/526, loss: 0.0064291395246982574
2023-01-24 07:44:57.904556: step: 1928/526, loss: 0.004161641001701355
2023-01-24 07:44:58.987929: step: 1932/526, loss: 0.004157512914389372
2023-01-24 07:45:00.058495: step: 1936/526, loss: 0.008234788663685322
2023-01-24 07:45:01.126019: step: 1940/526, loss: 0.002967260777950287
2023-01-24 07:45:02.183601: step: 1944/526, loss: 0.010103443637490273
2023-01-24 07:45:03.249373: step: 1948/526, loss: 0.001317432732321322
2023-01-24 07:45:04.331255: step: 1952/526, loss: 0.006541980430483818
2023-01-24 07:45:05.397128: step: 1956/526, loss: 0.004061629064381123
2023-01-24 07:45:06.477447: step: 1960/526, loss: 0.0044001564383506775
2023-01-24 07:45:07.565971: step: 1964/526, loss: 0.003215089440345764
2023-01-24 07:45:08.621885: step: 1968/526, loss: 0.0030986550264060497
2023-01-24 07:45:09.696735: step: 1972/526, loss: 0.004986410494893789
2023-01-24 07:45:10.759111: step: 1976/526, loss: 0.008318000473082066
2023-01-24 07:45:11.820023: step: 1980/526, loss: 0.00040151720168069005
2023-01-24 07:45:12.904071: step: 1984/526, loss: 0.005011571105569601
2023-01-24 07:45:14.000661: step: 1988/526, loss: 0.003120447276160121
2023-01-24 07:45:15.056329: step: 1992/526, loss: 0.011333759874105453
2023-01-24 07:45:16.119121: step: 1996/526, loss: 0.0038796989247202873
2023-01-24 07:45:17.177469: step: 2000/526, loss: 0.00019722431898117065
2023-01-24 07:45:18.240186: step: 2004/526, loss: 0.008071818388998508
2023-01-24 07:45:19.306015: step: 2008/526, loss: 0.010678013786673546
2023-01-24 07:45:20.361645: step: 2012/526, loss: 0.01557554304599762
2023-01-24 07:45:21.425980: step: 2016/526, loss: 0.019661106169223785
2023-01-24 07:45:22.487398: step: 2020/526, loss: 0.002549381460994482
2023-01-24 07:45:23.536077: step: 2024/526, loss: 0.0063002691604197025
2023-01-24 07:45:24.599682: step: 2028/526, loss: 0.0005513711948879063
2023-01-24 07:45:25.669556: step: 2032/526, loss: 0.000553164747543633
2023-01-24 07:45:26.744155: step: 2036/526, loss: 0.006509793922305107
2023-01-24 07:45:27.818318: step: 2040/526, loss: 0.0066698892042040825
2023-01-24 07:45:28.888267: step: 2044/526, loss: 0.01583942212164402
2023-01-24 07:45:29.954025: step: 2048/526, loss: 0.01418278831988573
2023-01-24 07:45:31.019455: step: 2052/526, loss: 0.005408493336290121
2023-01-24 07:45:32.095571: step: 2056/526, loss: 0.0005478183156810701
2023-01-24 07:45:33.155963: step: 2060/526, loss: 0.0040389057248830795
2023-01-24 07:45:34.233961: step: 2064/526, loss: 0.01307224202901125
2023-01-24 07:45:35.289295: step: 2068/526, loss: 0.009238021448254585
2023-01-24 07:45:36.368799: step: 2072/526, loss: 0.011187410913407803
2023-01-24 07:45:37.437523: step: 2076/526, loss: 0.003588580060750246
2023-01-24 07:45:38.523984: step: 2080/526, loss: 0.0046479483135044575
2023-01-24 07:45:39.584638: step: 2084/526, loss: 0.004652297589927912
2023-01-24 07:45:40.652852: step: 2088/526, loss: 0.00234913919121027
2023-01-24 07:45:41.745733: step: 2092/526, loss: 0.006776631344109774
2023-01-24 07:45:42.841257: step: 2096/526, loss: 0.033366456627845764
2023-01-24 07:45:43.897081: step: 2100/526, loss: 0.0011444361880421638
2023-01-24 07:45:44.949063: step: 2104/526, loss: 0.0001746313355397433
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3700735028860029, 'r': 0.278081797235023, 'f1': 0.3175495279368519}, 'combined': 0.23398386269031193, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.362233732513777, 'r': 0.22337194484381126, 'f1': 0.2763390330665373}, 'combined': 0.1507303816726567, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33884715229704215, 'r': 0.29191007047980483, 'f1': 0.3136322265909422}, 'combined': 0.2310974301196416, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35791364572833856, 'r': 0.25803838319664296, 'f1': 0.299878737728794}, 'combined': 0.16357022057934215, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3635840744400527, 'r': 0.31735991317348056, 'f1': 0.3389030886371312}, 'combined': 0.24971806531157034, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3639673917557914, 'r': 0.2740577890347816, 'f1': 0.3126776236064889}, 'combined': 0.17055143105808482, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377168646452016, 'r': 0.29285883708322036, 'f1': 0.31369229094076656}, 'combined': 0.23114168806161745, 'stategy': 1, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36076020150542065, 'r': 0.2604206761095854, 'f1': 0.30248650264375865}, 'combined': 0.16499263780568652, 'stategy': 1, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 07:48:24.509612: step: 4/526, loss: 0.013079594820737839
2023-01-24 07:48:25.570595: step: 8/526, loss: 0.00904446467757225
2023-01-24 07:48:26.627511: step: 12/526, loss: 0.024451300501823425
2023-01-24 07:48:27.690602: step: 16/526, loss: 0.021447081118822098
2023-01-24 07:48:28.747133: step: 20/526, loss: 0.0033413756173104048
2023-01-24 07:48:29.813164: step: 24/526, loss: 0.0016094744205474854
2023-01-24 07:48:30.873426: step: 28/526, loss: 0.009556883946061134
2023-01-24 07:48:31.925446: step: 32/526, loss: 0.003605821868404746
2023-01-24 07:48:33.006026: step: 36/526, loss: 0.0031286971643567085
2023-01-24 07:48:34.076979: step: 40/526, loss: 0.003452236531302333
2023-01-24 07:48:35.137325: step: 44/526, loss: 0.00021833633945789188
2023-01-24 07:48:36.198752: step: 48/526, loss: 0.000872007803991437
2023-01-24 07:48:37.243795: step: 52/526, loss: 0.008121087215840816
2023-01-24 07:48:38.320028: step: 56/526, loss: 0.0017759572947397828
2023-01-24 07:48:39.385396: step: 60/526, loss: 0.001073908293619752
2023-01-24 07:48:40.439971: step: 64/526, loss: 0.011140496470034122
2023-01-24 07:48:41.505045: step: 68/526, loss: 0.0017967929597944021
2023-01-24 07:48:42.571082: step: 72/526, loss: 0.005892232526093721
2023-01-24 07:48:43.651071: step: 76/526, loss: 0.004117245320230722
2023-01-24 07:48:44.708353: step: 80/526, loss: 0.006771462503820658
2023-01-24 07:48:45.767802: step: 84/526, loss: 0.0037146317772567272
2023-01-24 07:48:46.829467: step: 88/526, loss: 0.0035161625128239393
2023-01-24 07:48:47.891999: step: 92/526, loss: 0.004980398807674646
2023-01-24 07:48:48.952410: step: 96/526, loss: 0.0006558881141245365
2023-01-24 07:48:50.006853: step: 100/526, loss: 0.0010797990253195167
2023-01-24 07:48:51.080827: step: 104/526, loss: 0.008615699596703053
2023-01-24 07:48:52.159743: step: 108/526, loss: 0.004968350287526846
2023-01-24 07:48:53.223596: step: 112/526, loss: 0.029111092910170555
2023-01-24 07:48:54.286839: step: 116/526, loss: 0.018352240324020386
2023-01-24 07:48:55.351534: step: 120/526, loss: 0.009935823269188404
2023-01-24 07:48:56.422808: step: 124/526, loss: 0.0024441261775791645
2023-01-24 07:48:57.485035: step: 128/526, loss: 0.00545929791405797
2023-01-24 07:48:58.560457: step: 132/526, loss: 0.00011647606879705563
2023-01-24 07:48:59.629307: step: 136/526, loss: 0.007359283044934273
2023-01-24 07:49:00.675573: step: 140/526, loss: 0.008807172998785973
2023-01-24 07:49:01.766626: step: 144/526, loss: 0.002639482729136944
2023-01-24 07:49:02.836502: step: 148/526, loss: 0.0006521404720842838
2023-01-24 07:49:03.924053: step: 152/526, loss: 0.00625608628615737
2023-01-24 07:49:04.997512: step: 156/526, loss: 0.013787361793220043
2023-01-24 07:49:06.083400: step: 160/526, loss: 0.002106620231643319
2023-01-24 07:49:07.134645: step: 164/526, loss: 0.0066810185089707375
2023-01-24 07:49:08.205476: step: 168/526, loss: 0.002057743724435568
2023-01-24 07:49:09.274517: step: 172/526, loss: 0.00016635513748042285
2023-01-24 07:49:10.344020: step: 176/526, loss: 0.007131034974008799
2023-01-24 07:49:11.420208: step: 180/526, loss: 0.0017956976080313325
2023-01-24 07:49:12.503791: step: 184/526, loss: 0.013966855593025684
2023-01-24 07:49:13.573082: step: 188/526, loss: 0.0027393600903451443
2023-01-24 07:49:14.640523: step: 192/526, loss: 0.0012498266296461225
2023-01-24 07:49:15.704370: step: 196/526, loss: 0.00817183218896389
2023-01-24 07:49:16.775773: step: 200/526, loss: 0.0004959365469403565
2023-01-24 07:49:17.837286: step: 204/526, loss: 0.02556758187711239
2023-01-24 07:49:18.901256: step: 208/526, loss: 0.008016317151486874
2023-01-24 07:49:19.965972: step: 212/526, loss: 0.015316873788833618
2023-01-24 07:49:21.020200: step: 216/526, loss: 0.0010514894966036081
2023-01-24 07:49:22.094299: step: 220/526, loss: 0.007979926653206348
2023-01-24 07:49:23.178758: step: 224/526, loss: 0.004599989857524633
2023-01-24 07:49:24.244118: step: 228/526, loss: 0.0018322113901376724
2023-01-24 07:49:25.331531: step: 232/526, loss: 0.029261555522680283
2023-01-24 07:49:26.404878: step: 236/526, loss: 0.010123688727617264
2023-01-24 07:49:27.470712: step: 240/526, loss: 0.005275878123939037
2023-01-24 07:49:28.547214: step: 244/526, loss: 0.03178130462765694
2023-01-24 07:49:29.614732: step: 248/526, loss: 0.000533056678250432
2023-01-24 07:49:30.689719: step: 252/526, loss: 0.005214234348386526
2023-01-24 07:49:31.770615: step: 256/526, loss: 0.0017743855714797974
2023-01-24 07:49:32.843362: step: 260/526, loss: 0.0033710047136992216
2023-01-24 07:49:33.918419: step: 264/526, loss: 0.009170453064143658
2023-01-24 07:49:35.023829: step: 268/526, loss: 0.007401072420179844
2023-01-24 07:49:36.091598: step: 272/526, loss: 3.725290076417309e-10
2023-01-24 07:49:37.155118: step: 276/526, loss: 0.007131366524845362
2023-01-24 07:49:38.220153: step: 280/526, loss: 0.005157087463885546
2023-01-24 07:49:39.288826: step: 284/526, loss: 0.014146647416055202
2023-01-24 07:49:40.353496: step: 288/526, loss: 0.005302580539137125
2023-01-24 07:49:41.419593: step: 292/526, loss: 0.003181050531566143
2023-01-24 07:49:42.496092: step: 296/526, loss: 0.010133090429008007
2023-01-24 07:49:43.592730: step: 300/526, loss: 0.003045728662982583
2023-01-24 07:49:44.692100: step: 304/526, loss: 0.04759509861469269
2023-01-24 07:49:45.756266: step: 308/526, loss: 0.0030888644978404045
2023-01-24 07:49:46.835916: step: 312/526, loss: 0.0013615991920232773
2023-01-24 07:49:47.905628: step: 316/526, loss: 0.003262763377279043
2023-01-24 07:49:48.974743: step: 320/526, loss: 1.9154898836859502e-05
2023-01-24 07:49:50.027584: step: 324/526, loss: 0.0016366096679121256
2023-01-24 07:49:51.092275: step: 328/526, loss: 0.0009521624888293445
2023-01-24 07:49:52.157122: step: 332/526, loss: 0.002164134057238698
2023-01-24 07:49:53.245210: step: 336/526, loss: 0.004773444961756468
2023-01-24 07:49:54.312438: step: 340/526, loss: 0.00251379469409585
2023-01-24 07:49:55.385152: step: 344/526, loss: 0.0005149704520590603
2023-01-24 07:49:56.466636: step: 348/526, loss: 0.021555345505475998
2023-01-24 07:49:57.551433: step: 352/526, loss: 0.0031156721524894238
2023-01-24 07:49:58.637115: step: 356/526, loss: 0.002873737830668688
2023-01-24 07:49:59.706400: step: 360/526, loss: 8.233762491727248e-05
2023-01-24 07:50:00.803595: step: 364/526, loss: 0.005617564544081688
2023-01-24 07:50:01.868076: step: 368/526, loss: 0.001380230882205069
2023-01-24 07:50:02.941635: step: 372/526, loss: 0.000144410616485402
2023-01-24 07:50:04.017783: step: 376/526, loss: 0.0014523608842864633
2023-01-24 07:50:05.085846: step: 380/526, loss: 0.0016333027742803097
2023-01-24 07:50:06.158603: step: 384/526, loss: 0.015328395180404186
2023-01-24 07:50:07.224463: step: 388/526, loss: 0.004146549850702286
2023-01-24 07:50:08.280707: step: 392/526, loss: 5.721750540033099e-07
2023-01-24 07:50:09.374801: step: 396/526, loss: 0.005526612978428602
2023-01-24 07:50:10.455021: step: 400/526, loss: 0.016683924943208694
2023-01-24 07:50:11.506262: step: 404/526, loss: 0.003495132550597191
2023-01-24 07:50:12.573737: step: 408/526, loss: 0.003528200089931488
2023-01-24 07:50:13.657031: step: 412/526, loss: 0.0008445320418104529
2023-01-24 07:50:14.723071: step: 416/526, loss: 0.004156423266977072
2023-01-24 07:50:15.789079: step: 420/526, loss: 0.006627610418945551
2023-01-24 07:50:16.869863: step: 424/526, loss: 0.00634584529325366
2023-01-24 07:50:17.924792: step: 428/526, loss: 0.011854343116283417
2023-01-24 07:50:18.990919: step: 432/526, loss: 0.0012294589541852474
2023-01-24 07:50:20.047483: step: 436/526, loss: 0.0006020539440214634
2023-01-24 07:50:21.115575: step: 440/526, loss: 0.007180261891335249
2023-01-24 07:50:22.177295: step: 444/526, loss: 0.002214729320257902
2023-01-24 07:50:23.237732: step: 448/526, loss: 0.004700632765889168
2023-01-24 07:50:24.325714: step: 452/526, loss: 0.022810641676187515
2023-01-24 07:50:25.382474: step: 456/526, loss: 8.707172673894092e-05
2023-01-24 07:50:26.450133: step: 460/526, loss: 0.0009464430040679872
2023-01-24 07:50:27.523026: step: 464/526, loss: 0.0012505368795245886
2023-01-24 07:50:28.579361: step: 468/526, loss: 0.020038196817040443
2023-01-24 07:50:29.662002: step: 472/526, loss: 0.0027339826337993145
2023-01-24 07:50:30.744010: step: 476/526, loss: 0.0011264992645010352
2023-01-24 07:50:31.822168: step: 480/526, loss: 0.005158867686986923
2023-01-24 07:50:32.903287: step: 484/526, loss: 0.0008930271724238992
2023-01-24 07:50:33.961873: step: 488/526, loss: 0.00048052764032036066
2023-01-24 07:50:35.029080: step: 492/526, loss: 0.0013856820296496153
2023-01-24 07:50:36.110144: step: 496/526, loss: 0.003456941805779934
2023-01-24 07:50:37.190881: step: 500/526, loss: 0.005218749865889549
2023-01-24 07:50:38.258516: step: 504/526, loss: 0.011373475193977356
2023-01-24 07:50:39.339803: step: 508/526, loss: 0.0020359831396490335
2023-01-24 07:50:40.406823: step: 512/526, loss: 0.0016010890249162912
2023-01-24 07:50:41.456120: step: 516/526, loss: 0.004258866887539625
2023-01-24 07:50:42.509021: step: 520/526, loss: 4.085959153599106e-05
2023-01-24 07:50:43.579149: step: 524/526, loss: 0.008100834675133228
2023-01-24 07:50:44.646324: step: 528/526, loss: 0.002264282898977399
2023-01-24 07:50:45.726284: step: 532/526, loss: 0.004935526754707098
2023-01-24 07:50:46.798107: step: 536/526, loss: 0.0016905742231756449
2023-01-24 07:50:47.874100: step: 540/526, loss: 0.0064620026387274265
2023-01-24 07:50:48.947916: step: 544/526, loss: 0.009874554350972176
2023-01-24 07:50:50.011205: step: 548/526, loss: 0.004197982605546713
2023-01-24 07:50:51.087478: step: 552/526, loss: 0.019544487819075584
2023-01-24 07:50:52.150048: step: 556/526, loss: 0.003573755966499448
2023-01-24 07:50:53.219777: step: 560/526, loss: 0.001996786566451192
2023-01-24 07:50:54.284676: step: 564/526, loss: 0.0069455611519515514
2023-01-24 07:50:55.357107: step: 568/526, loss: 0.0006901415181346238
2023-01-24 07:50:56.444880: step: 572/526, loss: 0.002882111119106412
2023-01-24 07:50:57.517732: step: 576/526, loss: 0.0006492440588772297
2023-01-24 07:50:58.592240: step: 580/526, loss: 0.012737701646983624
2023-01-24 07:50:59.644215: step: 584/526, loss: 0.0023327190428972244
2023-01-24 07:51:00.725306: step: 588/526, loss: 0.008727316744625568
2023-01-24 07:51:01.803674: step: 592/526, loss: 0.007423246745020151
2023-01-24 07:51:02.888127: step: 596/526, loss: 0.0008849871228449047
2023-01-24 07:51:03.969402: step: 600/526, loss: 0.003652324201539159
2023-01-24 07:51:05.031026: step: 604/526, loss: 0.015387420542538166
2023-01-24 07:51:06.096547: step: 608/526, loss: 5.522069113794714e-05
2023-01-24 07:51:07.169643: step: 612/526, loss: 0.008015790954232216
2023-01-24 07:51:08.234563: step: 616/526, loss: 0.004074361640959978
2023-01-24 07:51:09.305305: step: 620/526, loss: 0.0012326088035479188
2023-01-24 07:51:10.361372: step: 624/526, loss: 0.0021513698156923056
2023-01-24 07:51:11.427416: step: 628/526, loss: 0.0036216145381331444
2023-01-24 07:51:12.524011: step: 632/526, loss: 0.0009492533281445503
2023-01-24 07:51:13.602085: step: 636/526, loss: 0.011502153240144253
2023-01-24 07:51:14.658044: step: 640/526, loss: 0.002579902298748493
2023-01-24 07:51:15.726456: step: 644/526, loss: 0.00262247771024704
2023-01-24 07:51:16.794982: step: 648/526, loss: 0.007683777250349522
2023-01-24 07:51:17.860411: step: 652/526, loss: 0.0014152165967971087
2023-01-24 07:51:18.940715: step: 656/526, loss: 0.001773946569301188
2023-01-24 07:51:20.019508: step: 660/526, loss: 0.010569152422249317
2023-01-24 07:51:21.081550: step: 664/526, loss: 0.0003729837480932474
2023-01-24 07:51:22.148204: step: 668/526, loss: 0.002267500152811408
2023-01-24 07:51:23.208787: step: 672/526, loss: 0.0009689492871984839
2023-01-24 07:51:24.301630: step: 676/526, loss: 4.996197822038084e-05
2023-01-24 07:51:25.352688: step: 680/526, loss: 0.005962591152638197
2023-01-24 07:51:26.437656: step: 684/526, loss: 0.0032020793296396732
2023-01-24 07:51:27.501974: step: 688/526, loss: 0.002128659514710307
2023-01-24 07:51:28.581836: step: 692/526, loss: 2.5682535124360584e-05
2023-01-24 07:51:29.661393: step: 696/526, loss: 0.0033702075015753508
2023-01-24 07:51:30.754686: step: 700/526, loss: 0.004174541216343641
2023-01-24 07:51:31.813745: step: 704/526, loss: 0.00545587157830596
2023-01-24 07:51:32.880085: step: 708/526, loss: 0.00704062869772315
2023-01-24 07:51:33.938348: step: 712/526, loss: 0.0009306574356742203
2023-01-24 07:51:35.007486: step: 716/526, loss: 0.004401668906211853
2023-01-24 07:51:36.069149: step: 720/526, loss: 0.0038557122461497784
2023-01-24 07:51:37.126498: step: 724/526, loss: 0.0022898337338119745
2023-01-24 07:51:38.206268: step: 728/526, loss: 0.00023781249183230102
2023-01-24 07:51:39.275158: step: 732/526, loss: 0.0037209673319011927
2023-01-24 07:51:40.357376: step: 736/526, loss: 0.015409648418426514
2023-01-24 07:51:41.436883: step: 740/526, loss: 0.0037468383088707924
2023-01-24 07:51:42.500046: step: 744/526, loss: 0.003940398804843426
2023-01-24 07:51:43.571922: step: 748/526, loss: 0.0016385382041335106
2023-01-24 07:51:44.658601: step: 752/526, loss: 0.0033500271383672953
2023-01-24 07:51:45.739015: step: 756/526, loss: 0.0003862368466798216
2023-01-24 07:51:46.816981: step: 760/526, loss: 0.0006065507768653333
2023-01-24 07:51:47.897443: step: 764/526, loss: 0.00435351999476552
2023-01-24 07:51:48.969635: step: 768/526, loss: 0.001354056061245501
2023-01-24 07:51:50.044486: step: 772/526, loss: 0.00980560015887022
2023-01-24 07:51:51.131188: step: 776/526, loss: 0.0006540766917169094
2023-01-24 07:51:52.200335: step: 780/526, loss: 0.005372548010200262
2023-01-24 07:51:53.268209: step: 784/526, loss: 0.005511634983122349
2023-01-24 07:51:54.349340: step: 788/526, loss: 0.0032642828300595284
2023-01-24 07:51:55.402124: step: 792/526, loss: 0.02014615200459957
2023-01-24 07:51:56.479208: step: 796/526, loss: 0.008796419017016888
2023-01-24 07:51:57.572149: step: 800/526, loss: 0.0008439103839918971
2023-01-24 07:51:58.642509: step: 804/526, loss: 0.009275809861719608
2023-01-24 07:51:59.725128: step: 808/526, loss: 0.013660918921232224
2023-01-24 07:52:00.791066: step: 812/526, loss: 0.003361928276717663
2023-01-24 07:52:01.865700: step: 816/526, loss: 0.005954174790531397
2023-01-24 07:52:02.935233: step: 820/526, loss: 0.0007312035304494202
2023-01-24 07:52:04.007698: step: 824/526, loss: 0.004792365711182356
2023-01-24 07:52:05.068971: step: 828/526, loss: 0.0075009847059845924
2023-01-24 07:52:06.122026: step: 832/526, loss: 0.0026808949187397957
2023-01-24 07:52:07.192910: step: 836/526, loss: 0.02192048355937004
2023-01-24 07:52:08.260162: step: 840/526, loss: 0.018550509586930275
2023-01-24 07:52:09.332814: step: 844/526, loss: 0.002833773149177432
2023-01-24 07:52:10.397119: step: 848/526, loss: 0.0017575517995283008
2023-01-24 07:52:11.468838: step: 852/526, loss: 0.007136870641261339
2023-01-24 07:52:12.542734: step: 856/526, loss: 0.005001316778361797
2023-01-24 07:52:13.612458: step: 860/526, loss: 0.00017664016922935843
2023-01-24 07:52:14.673960: step: 864/526, loss: 0.0011570138158276677
2023-01-24 07:52:15.736264: step: 868/526, loss: 0.009741325862705708
2023-01-24 07:52:16.807731: step: 872/526, loss: 0.00023128798056859523
2023-01-24 07:52:17.878584: step: 876/526, loss: 0.0032117220107465982
2023-01-24 07:52:18.942956: step: 880/526, loss: 0.00822259671986103
2023-01-24 07:52:20.010415: step: 884/526, loss: 0.04778725653886795
2023-01-24 07:52:21.062398: step: 888/526, loss: 0.02158493548631668
2023-01-24 07:52:22.125362: step: 892/526, loss: 0.001879831776022911
2023-01-24 07:52:23.203918: step: 896/526, loss: 0.0036572597455233335
2023-01-24 07:52:24.290568: step: 900/526, loss: 0.013711349107325077
2023-01-24 07:52:25.342977: step: 904/526, loss: 0.0041593159548938274
2023-01-24 07:52:26.395685: step: 908/526, loss: 0.00014704930072184652
2023-01-24 07:52:27.475510: step: 912/526, loss: 0.010209574364125729
2023-01-24 07:52:28.542851: step: 916/526, loss: 0.0013150412123650312
2023-01-24 07:52:29.611568: step: 920/526, loss: 0.003515928518027067
2023-01-24 07:52:30.697062: step: 924/526, loss: 0.0009061343735083938
2023-01-24 07:52:31.792849: step: 928/526, loss: 0.025345806032419205
2023-01-24 07:52:32.838115: step: 932/526, loss: 0.00040686913416720927
2023-01-24 07:52:33.903442: step: 936/526, loss: 0.00034084025537595153
2023-01-24 07:52:34.964405: step: 940/526, loss: 0.003772574011236429
2023-01-24 07:52:36.045541: step: 944/526, loss: 0.006722453981637955
2023-01-24 07:52:37.120212: step: 948/526, loss: 0.007665977813303471
2023-01-24 07:52:38.174278: step: 952/526, loss: 0.005467934533953667
2023-01-24 07:52:39.252487: step: 956/526, loss: 0.0015559265157207847
2023-01-24 07:52:40.337607: step: 960/526, loss: 0.0033845871221274137
2023-01-24 07:52:41.418803: step: 964/526, loss: 0.0061858962289988995
2023-01-24 07:52:42.491797: step: 968/526, loss: 0.005246929358690977
2023-01-24 07:52:43.577236: step: 972/526, loss: 0.004883466754108667
2023-01-24 07:52:44.629165: step: 976/526, loss: 0.003289029933512211
2023-01-24 07:52:45.689616: step: 980/526, loss: 0.004805135540664196
2023-01-24 07:52:46.758935: step: 984/526, loss: 0.002463815500959754
2023-01-24 07:52:47.836368: step: 988/526, loss: 0.023306015878915787
2023-01-24 07:52:48.908670: step: 992/526, loss: 0.006063970737159252
2023-01-24 07:52:49.973802: step: 996/526, loss: 0.00376648991368711
2023-01-24 07:52:51.044178: step: 1000/526, loss: 0.020093783736228943
2023-01-24 07:52:52.121137: step: 1004/526, loss: 0.005251782014966011
2023-01-24 07:52:53.183789: step: 1008/526, loss: 0.0038181315176188946
2023-01-24 07:52:54.252221: step: 1012/526, loss: 0.0173733439296484
2023-01-24 07:52:55.342354: step: 1016/526, loss: 0.003919048700481653
2023-01-24 07:52:56.409057: step: 1020/526, loss: 1.0426172138977563e-06
2023-01-24 07:52:57.474794: step: 1024/526, loss: 0.006582462694495916
2023-01-24 07:52:58.534150: step: 1028/526, loss: 0.009237326681613922
2023-01-24 07:52:59.587591: step: 1032/526, loss: 0.001396065461449325
2023-01-24 07:53:00.681231: step: 1036/526, loss: 0.009620334953069687
2023-01-24 07:53:01.741574: step: 1040/526, loss: 0.003203710075467825
2023-01-24 07:53:02.802432: step: 1044/526, loss: 0.009948832914233208
2023-01-24 07:53:03.888920: step: 1048/526, loss: 0.001592310843989253
2023-01-24 07:53:04.979481: step: 1052/526, loss: 0.001643832423724234
2023-01-24 07:53:06.057767: step: 1056/526, loss: 0.005469069816172123
2023-01-24 07:53:07.126149: step: 1060/526, loss: 0.006859211251139641
2023-01-24 07:53:08.198826: step: 1064/526, loss: 0.0056801168248057365
2023-01-24 07:53:09.265539: step: 1068/526, loss: 0.0005950412596575916
2023-01-24 07:53:10.341359: step: 1072/526, loss: 0.007422159891575575
2023-01-24 07:53:11.404559: step: 1076/526, loss: 0.002564589260146022
2023-01-24 07:53:12.471389: step: 1080/526, loss: 0.0018462928710505366
2023-01-24 07:53:13.573394: step: 1084/526, loss: 0.00596190569922328
2023-01-24 07:53:14.642194: step: 1088/526, loss: 0.010247442871332169
2023-01-24 07:53:15.708167: step: 1092/526, loss: 0.0011546171735972166
2023-01-24 07:53:16.771866: step: 1096/526, loss: 0.012049159035086632
2023-01-24 07:53:17.844404: step: 1100/526, loss: 0.0021646914537996054
2023-01-24 07:53:18.918619: step: 1104/526, loss: 0.011634151451289654
2023-01-24 07:53:19.990914: step: 1108/526, loss: 0.0017849744763225317
2023-01-24 07:53:21.053173: step: 1112/526, loss: 0.004648881033062935
2023-01-24 07:53:22.114344: step: 1116/526, loss: 0.0010674720397219062
2023-01-24 07:53:23.191949: step: 1120/526, loss: 0.0037717395462095737
2023-01-24 07:53:24.263374: step: 1124/526, loss: 0.001733866287395358
2023-01-24 07:53:25.342654: step: 1128/526, loss: 0.011036127805709839
2023-01-24 07:53:26.413410: step: 1132/526, loss: 0.0
2023-01-24 07:53:27.477337: step: 1136/526, loss: 0.012006633915007114
2023-01-24 07:53:28.544293: step: 1140/526, loss: 0.00693461624905467
2023-01-24 07:53:29.648243: step: 1144/526, loss: 0.008088336326181889
2023-01-24 07:53:30.714301: step: 1148/526, loss: 0.007631760556250811
2023-01-24 07:53:31.786539: step: 1152/526, loss: 0.008798143826425076
2023-01-24 07:53:32.881319: step: 1156/526, loss: 0.005036241374909878
2023-01-24 07:53:33.947897: step: 1160/526, loss: 0.000274105928838253
2023-01-24 07:53:35.013955: step: 1164/526, loss: 0.008674328215420246
2023-01-24 07:53:36.084737: step: 1168/526, loss: 0.0009908691281452775
2023-01-24 07:53:37.154076: step: 1172/526, loss: 0.0033133842516690493
2023-01-24 07:53:38.219054: step: 1176/526, loss: 0.023453017696738243
2023-01-24 07:53:39.292363: step: 1180/526, loss: 0.0027759382501244545
2023-01-24 07:53:40.352776: step: 1184/526, loss: 9.883051097858697e-05
2023-01-24 07:53:41.420706: step: 1188/526, loss: 0.005009297281503677
2023-01-24 07:53:42.494533: step: 1192/526, loss: 0.001685858704149723
2023-01-24 07:53:43.560815: step: 1196/526, loss: 0.008580422960221767
2023-01-24 07:53:44.636434: step: 1200/526, loss: 0.011451034806668758
2023-01-24 07:53:45.695674: step: 1204/526, loss: 0.000860861677210778
2023-01-24 07:53:46.777693: step: 1208/526, loss: 0.000365014944691211
2023-01-24 07:53:47.845411: step: 1212/526, loss: 0.014941053465008736
2023-01-24 07:53:48.927082: step: 1216/526, loss: 0.009724997915327549
2023-01-24 07:53:50.007790: step: 1220/526, loss: 0.0015168003737926483
2023-01-24 07:53:51.088567: step: 1224/526, loss: 0.0019922954961657524
2023-01-24 07:53:52.174437: step: 1228/526, loss: 0.021697305142879486
2023-01-24 07:53:53.270611: step: 1232/526, loss: 0.0006142150377854705
2023-01-24 07:53:54.346584: step: 1236/526, loss: 0.0014331192942336202
2023-01-24 07:53:55.403414: step: 1240/526, loss: 0.004747698549181223
2023-01-24 07:53:56.474941: step: 1244/526, loss: 0.005667760502547026
2023-01-24 07:53:57.544134: step: 1248/526, loss: 0.002338648308068514
2023-01-24 07:53:58.622674: step: 1252/526, loss: 0.005550717934966087
2023-01-24 07:53:59.702024: step: 1256/526, loss: 0.03065328486263752
2023-01-24 07:54:00.763297: step: 1260/526, loss: 0.0
2023-01-24 07:54:01.832429: step: 1264/526, loss: 0.0031456623692065477
2023-01-24 07:54:02.917958: step: 1268/526, loss: 0.008177438750863075
2023-01-24 07:54:03.988002: step: 1272/526, loss: 0.007453497499227524
2023-01-24 07:54:05.042142: step: 1276/526, loss: 0.00031914940336719155
2023-01-24 07:54:06.119543: step: 1280/526, loss: 0.007359337527304888
2023-01-24 07:54:07.201890: step: 1284/526, loss: 0.012301357463002205
2023-01-24 07:54:08.310059: step: 1288/526, loss: 0.0032113343477249146
2023-01-24 07:54:09.390316: step: 1292/526, loss: 0.0004054347809869796
2023-01-24 07:54:10.444485: step: 1296/526, loss: 4.1995637729996815e-05
2023-01-24 07:54:11.515176: step: 1300/526, loss: 0.005636436864733696
2023-01-24 07:54:12.577106: step: 1304/526, loss: 0.0032630146015435457
2023-01-24 07:54:13.646332: step: 1308/526, loss: 0.00539812259376049
2023-01-24 07:54:14.706465: step: 1312/526, loss: 0.0077217682264745235
2023-01-24 07:54:15.781159: step: 1316/526, loss: 0.0014386394759640098
2023-01-24 07:54:16.853408: step: 1320/526, loss: 0.007581560406833887
2023-01-24 07:54:17.951776: step: 1324/526, loss: 0.006626219023019075
2023-01-24 07:54:19.030478: step: 1328/526, loss: 0.003095823572948575
2023-01-24 07:54:20.114184: step: 1332/526, loss: 0.0029299117159098387
2023-01-24 07:54:21.198296: step: 1336/526, loss: 0.029629366472363472
2023-01-24 07:54:22.262098: step: 1340/526, loss: 0.008206835947930813
2023-01-24 07:54:23.330656: step: 1344/526, loss: 0.00363155291415751
2023-01-24 07:54:24.384003: step: 1348/526, loss: 0.009168574586510658
2023-01-24 07:54:25.467111: step: 1352/526, loss: 0.0009880515281111002
2023-01-24 07:54:26.568171: step: 1356/526, loss: 0.0007103616371750832
2023-01-24 07:54:27.642200: step: 1360/526, loss: 0.0025437932927161455
2023-01-24 07:54:28.726471: step: 1364/526, loss: 0.0289238803088665
2023-01-24 07:54:29.810423: step: 1368/526, loss: 0.00441761314868927
2023-01-24 07:54:30.876847: step: 1372/526, loss: 0.0003461152664385736
2023-01-24 07:54:31.954404: step: 1376/526, loss: 0.002913940232247114
2023-01-24 07:54:33.018141: step: 1380/526, loss: 0.0017914064228534698
2023-01-24 07:54:34.083294: step: 1384/526, loss: 0.00041023417725227773
2023-01-24 07:54:35.134701: step: 1388/526, loss: 0.015686744824051857
2023-01-24 07:54:36.207416: step: 1392/526, loss: 0.017496313899755478
2023-01-24 07:54:37.298869: step: 1396/526, loss: 0.002222283510491252
2023-01-24 07:54:38.375622: step: 1400/526, loss: 0.0009443407179787755
2023-01-24 07:54:39.451980: step: 1404/526, loss: 0.005772572476416826
2023-01-24 07:54:40.516486: step: 1408/526, loss: 0.002379060024395585
2023-01-24 07:54:41.603923: step: 1412/526, loss: 0.010205735452473164
2023-01-24 07:54:42.687571: step: 1416/526, loss: 0.01043506246060133
2023-01-24 07:54:43.757059: step: 1420/526, loss: 0.0020910585299134254
2023-01-24 07:54:44.841479: step: 1424/526, loss: 0.00906625296920538
2023-01-24 07:54:45.921210: step: 1428/526, loss: 0.0006995234871283174
2023-01-24 07:54:46.998175: step: 1432/526, loss: 0.00631823530420661
2023-01-24 07:54:48.060811: step: 1436/526, loss: 0.003414412261918187
2023-01-24 07:54:49.136167: step: 1440/526, loss: 0.003993874415755272
2023-01-24 07:54:50.206743: step: 1444/526, loss: 0.007262456230819225
2023-01-24 07:54:51.274492: step: 1448/526, loss: 0.004374999552965164
2023-01-24 07:54:52.370224: step: 1452/526, loss: 0.0030179843306541443
2023-01-24 07:54:53.448834: step: 1456/526, loss: 0.005736122373491526
2023-01-24 07:54:54.530963: step: 1460/526, loss: 0.0027171254623681307
2023-01-24 07:54:55.590561: step: 1464/526, loss: 0.00468910438939929
2023-01-24 07:54:56.642065: step: 1468/526, loss: 0.0038674722891300917
2023-01-24 07:54:57.708402: step: 1472/526, loss: 0.0009095493005588651
2023-01-24 07:54:58.765844: step: 1476/526, loss: 0.001541096600703895
2023-01-24 07:54:59.833229: step: 1480/526, loss: 0.004774812143296003
2023-01-24 07:55:00.892931: step: 1484/526, loss: 0.0020774423610419035
2023-01-24 07:55:01.967267: step: 1488/526, loss: 0.008269724436104298
2023-01-24 07:55:03.039435: step: 1492/526, loss: 0.003047727979719639
2023-01-24 07:55:04.103248: step: 1496/526, loss: 0.006301156245172024
2023-01-24 07:55:05.179402: step: 1500/526, loss: 0.017137933522462845
2023-01-24 07:55:06.262048: step: 1504/526, loss: 0.05789651721715927
2023-01-24 07:55:07.323505: step: 1508/526, loss: 0.019466396421194077
2023-01-24 07:55:08.389802: step: 1512/526, loss: 0.0030354063492268324
2023-01-24 07:55:09.461609: step: 1516/526, loss: 0.007000172510743141
2023-01-24 07:55:10.535337: step: 1520/526, loss: 0.010465754196047783
2023-01-24 07:55:11.606316: step: 1524/526, loss: 0.0016235969960689545
2023-01-24 07:55:12.678245: step: 1528/526, loss: 0.0052039301954209805
2023-01-24 07:55:13.741976: step: 1532/526, loss: 0.006547519937157631
2023-01-24 07:55:14.835829: step: 1536/526, loss: 0.0036778971552848816
2023-01-24 07:55:15.912188: step: 1540/526, loss: 0.002224015537649393
2023-01-24 07:55:16.974402: step: 1544/526, loss: 0.011120656505227089
2023-01-24 07:55:18.071578: step: 1548/526, loss: 0.004064811393618584
2023-01-24 07:55:19.134555: step: 1552/526, loss: 0.0008163480670191348
2023-01-24 07:55:20.203295: step: 1556/526, loss: 0.0027425058651715517
2023-01-24 07:55:21.283047: step: 1560/526, loss: 0.0034983966033905745
2023-01-24 07:55:22.346729: step: 1564/526, loss: 0.006434377748519182
2023-01-24 07:55:23.426900: step: 1568/526, loss: 0.001518317381851375
2023-01-24 07:55:24.499307: step: 1572/526, loss: 0.00011459342204034328
2023-01-24 07:55:25.582057: step: 1576/526, loss: 0.0024109946098178625
2023-01-24 07:55:26.649331: step: 1580/526, loss: 0.0051181805320084095
2023-01-24 07:55:27.734768: step: 1584/526, loss: 0.0038799168542027473
2023-01-24 07:55:28.809620: step: 1588/526, loss: 0.0027905148454010487
2023-01-24 07:55:29.877983: step: 1592/526, loss: 9.780994150787592e-05
2023-01-24 07:55:30.961192: step: 1596/526, loss: 0.005336377769708633
2023-01-24 07:55:32.065789: step: 1600/526, loss: 0.0069270809181034565
2023-01-24 07:55:33.146536: step: 1604/526, loss: 0.010091659612953663
2023-01-24 07:55:34.219662: step: 1608/526, loss: 0.0038561539258807898
2023-01-24 07:55:35.279126: step: 1612/526, loss: 0.0020094066858291626
2023-01-24 07:55:36.360837: step: 1616/526, loss: 0.02275482937693596
2023-01-24 07:55:37.446004: step: 1620/526, loss: 0.0001950414734892547
2023-01-24 07:55:38.510802: step: 1624/526, loss: 0.005835406016558409
2023-01-24 07:55:39.580966: step: 1628/526, loss: 0.008719498291611671
2023-01-24 07:55:40.636270: step: 1632/526, loss: 0.006848846096545458
2023-01-24 07:55:41.698821: step: 1636/526, loss: 0.005393713712692261
2023-01-24 07:55:42.791943: step: 1640/526, loss: 0.004651104565709829
2023-01-24 07:55:43.872959: step: 1644/526, loss: 0.0002404949045740068
2023-01-24 07:55:44.947393: step: 1648/526, loss: 0.0042755152098834515
2023-01-24 07:55:46.010526: step: 1652/526, loss: 0.006463938392698765
2023-01-24 07:55:47.078291: step: 1656/526, loss: 0.008712255395948887
2023-01-24 07:55:48.153473: step: 1660/526, loss: 0.006245963275432587
2023-01-24 07:55:49.240817: step: 1664/526, loss: 0.005003716796636581
2023-01-24 07:55:50.333455: step: 1668/526, loss: 0.005037671886384487
2023-01-24 07:55:51.396356: step: 1672/526, loss: 0.00518902437761426
2023-01-24 07:55:52.470706: step: 1676/526, loss: 0.006831640377640724
2023-01-24 07:55:53.538319: step: 1680/526, loss: 0.011011738330125809
2023-01-24 07:55:54.615139: step: 1684/526, loss: 0.0005441741086542606
2023-01-24 07:55:55.676601: step: 1688/526, loss: 0.001533876871690154
2023-01-24 07:55:56.748684: step: 1692/526, loss: 0.009481044486165047
2023-01-24 07:55:57.819225: step: 1696/526, loss: 0.00797145627439022
2023-01-24 07:55:58.908544: step: 1700/526, loss: 0.004354438278824091
2023-01-24 07:55:59.978031: step: 1704/526, loss: 0.004230857361108065
2023-01-24 07:56:01.063803: step: 1708/526, loss: 0.0026106340810656548
2023-01-24 07:56:02.144969: step: 1712/526, loss: 0.03682756796479225
2023-01-24 07:56:03.210994: step: 1716/526, loss: 0.00035873689921572804
2023-01-24 07:56:04.284524: step: 1720/526, loss: 0.008056238293647766
2023-01-24 07:56:05.360402: step: 1724/526, loss: 0.0027793829794973135
2023-01-24 07:56:06.453281: step: 1728/526, loss: 0.02800150029361248
2023-01-24 07:56:07.533191: step: 1732/526, loss: 0.004113492090255022
2023-01-24 07:56:08.593507: step: 1736/526, loss: 0.0018264194950461388
2023-01-24 07:56:09.657671: step: 1740/526, loss: 0.001853841356933117
2023-01-24 07:56:10.724977: step: 1744/526, loss: 0.0014736369485035539
2023-01-24 07:56:11.796748: step: 1748/526, loss: 0.002336955862119794
2023-01-24 07:56:12.882848: step: 1752/526, loss: 0.029125962406396866
2023-01-24 07:56:13.949787: step: 1756/526, loss: 0.00979869719594717
2023-01-24 07:56:15.019354: step: 1760/526, loss: 0.0052991947159171104
2023-01-24 07:56:16.081284: step: 1764/526, loss: 1.6575935660512187e-05
2023-01-24 07:56:17.145760: step: 1768/526, loss: 0.0003262819955125451
2023-01-24 07:56:18.213397: step: 1772/526, loss: 0.002665152307599783
2023-01-24 07:56:19.284339: step: 1776/526, loss: 0.007335955277085304
2023-01-24 07:56:20.358354: step: 1780/526, loss: 0.009206417948007584
2023-01-24 07:56:21.423582: step: 1784/526, loss: 0.004034833982586861
2023-01-24 07:56:22.510098: step: 1788/526, loss: 0.041636377573013306
2023-01-24 07:56:23.586490: step: 1792/526, loss: 0.0008861317182891071
2023-01-24 07:56:24.646432: step: 1796/526, loss: 0.005037650465965271
2023-01-24 07:56:25.710743: step: 1800/526, loss: 0.0004444077785592526
2023-01-24 07:56:26.769540: step: 1804/526, loss: 0.00010646445298334584
2023-01-24 07:56:27.831205: step: 1808/526, loss: 0.0034417728893458843
2023-01-24 07:56:28.905145: step: 1812/526, loss: 0.003349489765241742
2023-01-24 07:56:29.963499: step: 1816/526, loss: 0.004526312462985516
2023-01-24 07:56:31.043290: step: 1820/526, loss: 0.00029587274184450507
2023-01-24 07:56:32.111407: step: 1824/526, loss: 0.0013475136365741491
2023-01-24 07:56:33.186702: step: 1828/526, loss: 0.0009167612879537046
2023-01-24 07:56:34.247200: step: 1832/526, loss: 0.004182068165391684
2023-01-24 07:56:35.318166: step: 1836/526, loss: 0.005378655157983303
2023-01-24 07:56:36.374347: step: 1840/526, loss: 0.000523278780747205
2023-01-24 07:56:37.444510: step: 1844/526, loss: 0.020257247611880302
2023-01-24 07:56:38.517167: step: 1848/526, loss: 0.0006278672954067588
2023-01-24 07:56:39.592881: step: 1852/526, loss: 0.0011107685277238488
2023-01-24 07:56:40.679767: step: 1856/526, loss: 0.016520028933882713
2023-01-24 07:56:41.740869: step: 1860/526, loss: 0.0008798314956948161
2023-01-24 07:56:42.831302: step: 1864/526, loss: 0.0024338355287909508
2023-01-24 07:56:43.897357: step: 1868/526, loss: 0.002423889935016632
2023-01-24 07:56:44.963267: step: 1872/526, loss: 0.0014391009462997317
2023-01-24 07:56:46.038483: step: 1876/526, loss: 0.0032042853999882936
2023-01-24 07:56:47.101489: step: 1880/526, loss: 0.0013594884658232331
2023-01-24 07:56:48.178623: step: 1884/526, loss: 0.002975313924252987
2023-01-24 07:56:49.263648: step: 1888/526, loss: 0.006427662447094917
2023-01-24 07:56:50.335581: step: 1892/526, loss: 0.006068871356546879
2023-01-24 07:56:51.414916: step: 1896/526, loss: 0.0007641970296390355
2023-01-24 07:56:52.465929: step: 1900/526, loss: 0.0006615650490857661
2023-01-24 07:56:53.525450: step: 1904/526, loss: 0.0011104480363428593
2023-01-24 07:56:54.600842: step: 1908/526, loss: 0.0028059682808816433
2023-01-24 07:56:55.685522: step: 1912/526, loss: 0.0027646261733025312
2023-01-24 07:56:56.747867: step: 1916/526, loss: 0.0099010169506073
2023-01-24 07:56:57.812816: step: 1920/526, loss: 0.00015959309530444443
2023-01-24 07:56:58.882118: step: 1924/526, loss: 0.0035765361972153187
2023-01-24 07:56:59.954072: step: 1928/526, loss: 0.008528263308107853
2023-01-24 07:57:01.040179: step: 1932/526, loss: 0.0027974469121545553
2023-01-24 07:57:02.130571: step: 1936/526, loss: 0.0065225595608353615
2023-01-24 07:57:03.214528: step: 1940/526, loss: 0.006657288875430822
2023-01-24 07:57:04.279508: step: 1944/526, loss: 0.011110926046967506
2023-01-24 07:57:05.352623: step: 1948/526, loss: 0.0020117724779993296
2023-01-24 07:57:06.433062: step: 1952/526, loss: 0.0007542409002780914
2023-01-24 07:57:07.509570: step: 1956/526, loss: 0.0035255032125860453
2023-01-24 07:57:08.569437: step: 1960/526, loss: 0.012512335553765297
2023-01-24 07:57:09.661507: step: 1964/526, loss: 0.0010673401411622763
2023-01-24 07:57:10.745388: step: 1968/526, loss: 0.00037337830872274935
2023-01-24 07:57:11.832025: step: 1972/526, loss: 0.01309991255402565
2023-01-24 07:57:12.907075: step: 1976/526, loss: 0.0011735076550394297
2023-01-24 07:57:13.973941: step: 1980/526, loss: 0.016302626579999924
2023-01-24 07:57:15.036283: step: 1984/526, loss: 0.0008477665251120925
2023-01-24 07:57:16.108695: step: 1988/526, loss: 0.003587673883885145
2023-01-24 07:57:17.177176: step: 1992/526, loss: 0.011979344300925732
2023-01-24 07:57:18.255532: step: 1996/526, loss: 0.0028485064394772053
2023-01-24 07:57:19.320431: step: 2000/526, loss: 0.018039528280496597
2023-01-24 07:57:20.397251: step: 2004/526, loss: 0.0019866209477186203
2023-01-24 07:57:21.461906: step: 2008/526, loss: 0.008165537379682064
2023-01-24 07:57:22.522694: step: 2012/526, loss: 0.007037199102342129
2023-01-24 07:57:23.593939: step: 2016/526, loss: 0.0003728357551153749
2023-01-24 07:57:24.677461: step: 2020/526, loss: 0.0006959430756978691
2023-01-24 07:57:25.761514: step: 2024/526, loss: 0.05053370073437691
2023-01-24 07:57:26.845980: step: 2028/526, loss: 0.006268172059208155
2023-01-24 07:57:27.932684: step: 2032/526, loss: 0.00017043150728568435
2023-01-24 07:57:29.012031: step: 2036/526, loss: 0.008184626698493958
2023-01-24 07:57:30.072410: step: 2040/526, loss: 0.01348032895475626
2023-01-24 07:57:31.137189: step: 2044/526, loss: 0.003239545039832592
2023-01-24 07:57:32.215575: step: 2048/526, loss: 0.0024152989499270916
2023-01-24 07:57:33.298304: step: 2052/526, loss: 0.005631963722407818
2023-01-24 07:57:34.364845: step: 2056/526, loss: 0.0002426598803140223
2023-01-24 07:57:35.429859: step: 2060/526, loss: 0.00610897783190012
2023-01-24 07:57:36.500165: step: 2064/526, loss: 0.0058256033807992935
2023-01-24 07:57:37.571005: step: 2068/526, loss: 0.015423965640366077
2023-01-24 07:57:38.647572: step: 2072/526, loss: 0.002549290657043457
2023-01-24 07:57:39.717835: step: 2076/526, loss: 0.001205370295792818
2023-01-24 07:57:40.790609: step: 2080/526, loss: 0.033404458314180374
2023-01-24 07:57:41.879004: step: 2084/526, loss: 0.0018363238777965307
2023-01-24 07:57:42.970291: step: 2088/526, loss: 0.018268831074237823
2023-01-24 07:57:44.038293: step: 2092/526, loss: 0.002536095678806305
2023-01-24 07:57:45.127190: step: 2096/526, loss: 0.014475345611572266
2023-01-24 07:57:46.213384: step: 2100/526, loss: 0.0019569203723222017
2023-01-24 07:57:47.289189: step: 2104/526, loss: 0.01226720493286848
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3610946610787172, 'r': 0.26859413120086745, 'f1': 0.30805028757966735}, 'combined': 0.2269844224271233, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3617363895336569, 'r': 0.22405812965625407, 'f1': 0.2767181194511703}, 'combined': 0.1509371560642747, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33994847388294525, 'r': 0.29285883708322036, 'f1': 0.31465159458278724}, 'combined': 0.2318485433767906, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3579084904788047, 'r': 0.258362121672257, 'f1': 0.30009542931750993}, 'combined': 0.16368841599136905, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3597132625380442, 'r': 0.31261608015640274, 'f1': 0.33451507460390706}, 'combined': 0.24648479181340519, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36400846566287737, 'r': 0.2757538971352813, 'f1': 0.3137938673283316}, 'combined': 0.17116029126999904, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.42045454545454547, 'r': 0.40217391304347827, 'f1': 0.41111111111111115}, 'combined': 0.20555555555555557, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377168646452016, 'r': 0.29285883708322036, 'f1': 0.31369229094076656}, 'combined': 0.23114168806161745, 'stategy': 1, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36076020150542065, 'r': 0.2604206761095854, 'f1': 0.30248650264375865}, 'combined': 0.16499263780568652, 'stategy': 1, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 08:00:27.740184: step: 4/526, loss: 0.03914384916424751
2023-01-24 08:00:28.803221: step: 8/526, loss: 0.012458334676921368
2023-01-24 08:00:29.852541: step: 12/526, loss: 0.0011874176561832428
2023-01-24 08:00:30.913438: step: 16/526, loss: 0.006760450545698404
2023-01-24 08:00:31.976447: step: 20/526, loss: 0.003804833395406604
2023-01-24 08:00:33.035787: step: 24/526, loss: 0.003031475469470024
2023-01-24 08:00:34.080373: step: 28/526, loss: 0.0024960062000900507
2023-01-24 08:00:35.132484: step: 32/526, loss: 0.011792642995715141
2023-01-24 08:00:36.199285: step: 36/526, loss: 0.003637844929471612
2023-01-24 08:00:37.279664: step: 40/526, loss: 0.001144232926890254
2023-01-24 08:00:38.355000: step: 44/526, loss: 0.009493201971054077
2023-01-24 08:00:39.411462: step: 48/526, loss: 0.0037126510869711637
2023-01-24 08:00:40.485711: step: 52/526, loss: 0.08734021335840225
2023-01-24 08:00:41.552281: step: 56/526, loss: 0.020190024748444557
2023-01-24 08:00:42.623052: step: 60/526, loss: 0.0010884770890697837
2023-01-24 08:00:43.668458: step: 64/526, loss: 0.00432793190702796
2023-01-24 08:00:44.745559: step: 68/526, loss: 0.014436259865760803
2023-01-24 08:00:45.820504: step: 72/526, loss: 0.0028390262741595507
2023-01-24 08:00:46.879156: step: 76/526, loss: 0.004512321203947067
2023-01-24 08:00:47.945228: step: 80/526, loss: 0.0027164120692759752
2023-01-24 08:00:49.003182: step: 84/526, loss: 0.0013908883556723595
2023-01-24 08:00:50.053919: step: 88/526, loss: 0.004421636927872896
2023-01-24 08:00:51.111297: step: 92/526, loss: 0.009385128505527973
2023-01-24 08:00:52.154602: step: 96/526, loss: 0.0009007321204990149
2023-01-24 08:00:53.214313: step: 100/526, loss: 0.015045412816107273
2023-01-24 08:00:54.278476: step: 104/526, loss: 0.005501618143171072
2023-01-24 08:00:55.360114: step: 108/526, loss: 0.005629522260278463
2023-01-24 08:00:56.401815: step: 112/526, loss: 0.001161363790743053
2023-01-24 08:00:57.447404: step: 116/526, loss: 0.0034099631011486053
2023-01-24 08:00:58.514583: step: 120/526, loss: 0.0011534694349393249
2023-01-24 08:00:59.589155: step: 124/526, loss: 0.014831599779427052
2023-01-24 08:01:00.679860: step: 128/526, loss: 0.0006340779364109039
2023-01-24 08:01:01.748512: step: 132/526, loss: 0.0061704134568572044
2023-01-24 08:01:02.811961: step: 136/526, loss: 0.006142008118331432
2023-01-24 08:01:03.892157: step: 140/526, loss: 0.03993793576955795
2023-01-24 08:01:04.956633: step: 144/526, loss: 0.0008726411615498364
2023-01-24 08:01:06.008919: step: 148/526, loss: 0.00754851708188653
2023-01-24 08:01:07.088477: step: 152/526, loss: 0.011415963061153889
2023-01-24 08:01:08.153496: step: 156/526, loss: 0.0063007972203195095
2023-01-24 08:01:09.217317: step: 160/526, loss: 0.014107774011790752
2023-01-24 08:01:10.301067: step: 164/526, loss: 0.010831790044903755
2023-01-24 08:01:11.354116: step: 168/526, loss: 0.0032410998828709126
2023-01-24 08:01:12.421957: step: 172/526, loss: 0.0034866398200392723
2023-01-24 08:01:13.481233: step: 176/526, loss: 0.019249439239501953
2023-01-24 08:01:14.544285: step: 180/526, loss: 0.002934157382696867
2023-01-24 08:01:15.601969: step: 184/526, loss: 3.073999687330797e-05
2023-01-24 08:01:16.673710: step: 188/526, loss: 0.0021913948003202677
2023-01-24 08:01:17.745378: step: 192/526, loss: 1.5047981833049562e-05
2023-01-24 08:01:18.830820: step: 196/526, loss: 0.00964015256613493
2023-01-24 08:01:19.893230: step: 200/526, loss: 0.0052771237678825855
2023-01-24 08:01:20.974282: step: 204/526, loss: 0.0024171725381165743
2023-01-24 08:01:22.049972: step: 208/526, loss: 0.029271699488162994
2023-01-24 08:01:23.120570: step: 212/526, loss: 0.014002806507050991
2023-01-24 08:01:24.180237: step: 216/526, loss: 0.004147626459598541
2023-01-24 08:01:25.242623: step: 220/526, loss: 0.002527667907997966
2023-01-24 08:01:26.297152: step: 224/526, loss: 0.010924090631306171
2023-01-24 08:01:27.351113: step: 228/526, loss: 0.0022656205110251904
2023-01-24 08:01:28.411096: step: 232/526, loss: 0.002628905698657036
2023-01-24 08:01:29.481960: step: 236/526, loss: 0.0029345862567424774
2023-01-24 08:01:30.561334: step: 240/526, loss: 0.004847095813602209
2023-01-24 08:01:31.614597: step: 244/526, loss: 0.0006241805385798216
2023-01-24 08:01:32.695238: step: 248/526, loss: 0.04192202538251877
2023-01-24 08:01:33.764586: step: 252/526, loss: 0.0073339734226465225
2023-01-24 08:01:34.830029: step: 256/526, loss: 0.004048834089189768
2023-01-24 08:01:35.884195: step: 260/526, loss: 0.0018592940177768469
2023-01-24 08:01:36.957965: step: 264/526, loss: 0.003509767819195986
2023-01-24 08:01:38.018085: step: 268/526, loss: 0.007049216888844967
2023-01-24 08:01:39.071114: step: 272/526, loss: 0.000458940165117383
2023-01-24 08:01:40.131948: step: 276/526, loss: 0.0013739545829594135
2023-01-24 08:01:41.205060: step: 280/526, loss: 0.009642442688345909
2023-01-24 08:01:42.275713: step: 284/526, loss: 8.788464037934318e-05
2023-01-24 08:01:43.338346: step: 288/526, loss: 0.00039300654316321015
2023-01-24 08:01:44.387416: step: 292/526, loss: 0.001044073374941945
2023-01-24 08:01:45.448803: step: 296/526, loss: 0.00024214394215960056
2023-01-24 08:01:46.495530: step: 300/526, loss: 0.0010353511897847056
2023-01-24 08:01:47.557626: step: 304/526, loss: 0.0053918128833174706
2023-01-24 08:01:48.620311: step: 308/526, loss: 0.004577489569783211
2023-01-24 08:01:49.680291: step: 312/526, loss: 0.002369215711951256
2023-01-24 08:01:50.754111: step: 316/526, loss: 0.007408234756439924
2023-01-24 08:01:51.819521: step: 320/526, loss: 0.005347894504666328
2023-01-24 08:01:52.887375: step: 324/526, loss: 0.0003589502302929759
2023-01-24 08:01:53.948534: step: 328/526, loss: 0.009502967819571495
2023-01-24 08:01:55.004375: step: 332/526, loss: 0.004050052259117365
2023-01-24 08:01:56.054429: step: 336/526, loss: 0.0026822916697710752
2023-01-24 08:01:57.105008: step: 340/526, loss: 0.006174871698021889
2023-01-24 08:01:58.171849: step: 344/526, loss: 0.003229816211387515
2023-01-24 08:01:59.227429: step: 348/526, loss: 0.00220097741112113
2023-01-24 08:02:00.300050: step: 352/526, loss: 0.005181090906262398
2023-01-24 08:02:01.349705: step: 356/526, loss: 0.02471998706459999
2023-01-24 08:02:02.424584: step: 360/526, loss: 0.002874291967600584
2023-01-24 08:02:03.479339: step: 364/526, loss: 0.0009685191907919943
2023-01-24 08:02:04.539070: step: 368/526, loss: 0.0014047357253730297
2023-01-24 08:02:05.620085: step: 372/526, loss: 0.0039881691336631775
2023-01-24 08:02:06.687066: step: 376/526, loss: 0.0036766391713172197
2023-01-24 08:02:07.751391: step: 380/526, loss: 0.004806995391845703
2023-01-24 08:02:08.823264: step: 384/526, loss: 0.018413497135043144
2023-01-24 08:02:09.885838: step: 388/526, loss: 0.0006281603127717972
2023-01-24 08:02:10.935854: step: 392/526, loss: 0.0018995624268427491
2023-01-24 08:02:11.999545: step: 396/526, loss: 0.02252894453704357
2023-01-24 08:02:13.077280: step: 400/526, loss: 0.0031219327356666327
2023-01-24 08:02:14.143905: step: 404/526, loss: 0.004498603288084269
2023-01-24 08:02:15.209803: step: 408/526, loss: 0.004424775019288063
2023-01-24 08:02:16.270957: step: 412/526, loss: 0.014513521455228329
2023-01-24 08:02:17.353903: step: 416/526, loss: 0.02892647683620453
2023-01-24 08:02:18.423170: step: 420/526, loss: 0.0039602783508598804
2023-01-24 08:02:19.484166: step: 424/526, loss: 0.018903126940131187
2023-01-24 08:02:20.568669: step: 428/526, loss: 0.006359412334859371
2023-01-24 08:02:21.635362: step: 432/526, loss: 0.0012890842044726014
2023-01-24 08:02:22.700314: step: 436/526, loss: 0.007926391437649727
2023-01-24 08:02:23.760241: step: 440/526, loss: 0.009608851745724678
2023-01-24 08:02:24.818400: step: 444/526, loss: 0.007655289489775896
2023-01-24 08:02:25.889394: step: 448/526, loss: 0.005288000218570232
2023-01-24 08:02:26.961354: step: 452/526, loss: 0.0030700673814862967
2023-01-24 08:02:28.037369: step: 456/526, loss: 0.01592688076198101
2023-01-24 08:02:29.093080: step: 460/526, loss: 0.004105378873646259
2023-01-24 08:02:30.154461: step: 464/526, loss: 0.0009433595114387572
2023-01-24 08:02:31.212378: step: 468/526, loss: 0.0019469358958303928
2023-01-24 08:02:32.263825: step: 472/526, loss: 0.005649545695632696
2023-01-24 08:02:33.340918: step: 476/526, loss: 0.009048526175320148
2023-01-24 08:02:34.397722: step: 480/526, loss: 0.002955965232104063
2023-01-24 08:02:35.459682: step: 484/526, loss: 0.0016291955253109336
2023-01-24 08:02:36.530555: step: 488/526, loss: 0.004816431552171707
2023-01-24 08:02:37.596822: step: 492/526, loss: 0.005789854098111391
2023-01-24 08:02:38.658765: step: 496/526, loss: 0.014252807945013046
2023-01-24 08:02:39.725663: step: 500/526, loss: 1.580585740157403e-05
2023-01-24 08:02:40.783689: step: 504/526, loss: 0.003073624335229397
2023-01-24 08:02:41.852077: step: 508/526, loss: 0.018114915117621422
2023-01-24 08:02:42.936984: step: 512/526, loss: 0.00632064463570714
2023-01-24 08:02:44.017177: step: 516/526, loss: 0.009451929479837418
2023-01-24 08:02:45.071833: step: 520/526, loss: 0.003335179528221488
2023-01-24 08:02:46.128662: step: 524/526, loss: 0.013502035290002823
2023-01-24 08:02:47.184799: step: 528/526, loss: 0.010950354859232903
2023-01-24 08:02:48.262785: step: 532/526, loss: 0.0017414387548342347
2023-01-24 08:02:49.324633: step: 536/526, loss: 0.007401375100016594
2023-01-24 08:02:50.388270: step: 540/526, loss: 0.0005550369969569147
2023-01-24 08:02:51.442843: step: 544/526, loss: 0.003469782182946801
2023-01-24 08:02:52.508082: step: 548/526, loss: 0.002681322628632188
2023-01-24 08:02:53.575213: step: 552/526, loss: 0.0065278890542685986
2023-01-24 08:02:54.645647: step: 556/526, loss: 0.002598665887489915
2023-01-24 08:02:55.701182: step: 560/526, loss: 0.011027329601347446
2023-01-24 08:02:56.780652: step: 564/526, loss: 0.004067003261297941
2023-01-24 08:02:57.841106: step: 568/526, loss: 0.0017140146810561419
2023-01-24 08:02:58.917407: step: 572/526, loss: 0.014103577472269535
2023-01-24 08:02:59.989133: step: 576/526, loss: 0.005832192953675985
2023-01-24 08:03:01.050369: step: 580/526, loss: 0.0025809190701693296
2023-01-24 08:03:02.113530: step: 584/526, loss: 0.008384406566619873
2023-01-24 08:03:03.181169: step: 588/526, loss: 0.000408686202717945
2023-01-24 08:03:04.236647: step: 592/526, loss: 0.004185400903224945
2023-01-24 08:03:05.312673: step: 596/526, loss: 0.0025841384194791317
2023-01-24 08:03:06.391766: step: 600/526, loss: 0.02498718723654747
2023-01-24 08:03:07.459915: step: 604/526, loss: 0.0011584153398871422
2023-01-24 08:03:08.516697: step: 608/526, loss: 0.0002652000111993402
2023-01-24 08:03:09.584448: step: 612/526, loss: 0.004533391445875168
2023-01-24 08:03:10.650691: step: 616/526, loss: 0.0021636730525642633
2023-01-24 08:03:11.720464: step: 620/526, loss: 0.00018159067258238792
2023-01-24 08:03:12.795268: step: 624/526, loss: 0.0067629567347466946
2023-01-24 08:03:13.869319: step: 628/526, loss: 4.668658220907673e-05
2023-01-24 08:03:14.940268: step: 632/526, loss: 0.012922360561788082
2023-01-24 08:03:16.015250: step: 636/526, loss: 0.00164447957649827
2023-01-24 08:03:17.074792: step: 640/526, loss: 0.009876989759504795
2023-01-24 08:03:18.140475: step: 644/526, loss: 0.006384863518178463
2023-01-24 08:03:19.207756: step: 648/526, loss: 0.001361687434837222
2023-01-24 08:03:20.281830: step: 652/526, loss: 0.0016008722595870495
2023-01-24 08:03:21.352328: step: 656/526, loss: 0.0030787885189056396
2023-01-24 08:03:22.407333: step: 660/526, loss: 0.000887411879375577
2023-01-24 08:03:23.490473: step: 664/526, loss: 0.0016765184700489044
2023-01-24 08:03:24.557725: step: 668/526, loss: 0.00010889178520301357
2023-01-24 08:03:25.617300: step: 672/526, loss: 0.009153757244348526
2023-01-24 08:03:26.680641: step: 676/526, loss: 0.005686105694621801
2023-01-24 08:03:27.744909: step: 680/526, loss: 0.0020400178618729115
2023-01-24 08:03:28.810273: step: 684/526, loss: 0.008220906369388103
2023-01-24 08:03:29.870918: step: 688/526, loss: 0.011818169616162777
2023-01-24 08:03:30.949848: step: 692/526, loss: 0.010587401688098907
2023-01-24 08:03:32.026430: step: 696/526, loss: 0.0010475068120285869
2023-01-24 08:03:33.101244: step: 700/526, loss: 0.0034396848641335964
2023-01-24 08:03:34.191609: step: 704/526, loss: 0.030698630958795547
2023-01-24 08:03:35.246954: step: 708/526, loss: 0.0010491388384252787
2023-01-24 08:03:36.321242: step: 712/526, loss: 0.0016570492880418897
2023-01-24 08:03:37.391424: step: 716/526, loss: 0.0022557477932423353
2023-01-24 08:03:38.447073: step: 720/526, loss: 0.0025538038462400436
2023-01-24 08:03:39.517208: step: 724/526, loss: 0.012905474752187729
2023-01-24 08:03:40.573798: step: 728/526, loss: 0.0001540376542834565
2023-01-24 08:03:41.651813: step: 732/526, loss: 0.009049699641764164
2023-01-24 08:03:42.730768: step: 736/526, loss: 0.0014287405647337437
2023-01-24 08:03:43.816970: step: 740/526, loss: 0.00016093575686682016
2023-01-24 08:03:44.870261: step: 744/526, loss: 0.0012757738586515188
2023-01-24 08:03:45.945280: step: 748/526, loss: 0.0018830905901268125
2023-01-24 08:03:47.011480: step: 752/526, loss: 0.004661615937948227
2023-01-24 08:03:48.080562: step: 756/526, loss: 0.005450590513646603
2023-01-24 08:03:49.153556: step: 760/526, loss: 0.0035836242605000734
2023-01-24 08:03:50.227454: step: 764/526, loss: 0.0036698803305625916
2023-01-24 08:03:51.267483: step: 768/526, loss: 0.00018407157040201128
2023-01-24 08:03:52.314287: step: 772/526, loss: 0.006386274006217718
2023-01-24 08:03:53.376862: step: 776/526, loss: 0.005379513371735811
2023-01-24 08:03:54.452364: step: 780/526, loss: 0.005845651030540466
2023-01-24 08:03:55.514373: step: 784/526, loss: 7.169665332185104e-05
2023-01-24 08:03:56.566420: step: 788/526, loss: 0.008214220404624939
2023-01-24 08:03:57.633300: step: 792/526, loss: 0.002594218822196126
2023-01-24 08:03:58.700265: step: 796/526, loss: 0.007495261263102293
2023-01-24 08:03:59.778806: step: 800/526, loss: 0.001038069138303399
2023-01-24 08:04:00.839077: step: 804/526, loss: 0.0034643833059817553
2023-01-24 08:04:01.896166: step: 808/526, loss: 0.003417538944631815
2023-01-24 08:04:02.964614: step: 812/526, loss: 0.003827321110293269
2023-01-24 08:04:04.033283: step: 816/526, loss: 0.003469871822744608
2023-01-24 08:04:05.090367: step: 820/526, loss: 0.0008538606343790889
2023-01-24 08:04:06.157930: step: 824/526, loss: 0.007968323305249214
2023-01-24 08:04:07.224420: step: 828/526, loss: 0.013973237946629524
2023-01-24 08:04:08.267164: step: 832/526, loss: 0.003516615368425846
2023-01-24 08:04:09.335165: step: 836/526, loss: 9.520177627564408e-06
2023-01-24 08:04:10.400483: step: 840/526, loss: 0.016389090567827225
2023-01-24 08:04:11.485535: step: 844/526, loss: 0.0018904394237324595
2023-01-24 08:04:12.560263: step: 848/526, loss: 0.004854640457779169
2023-01-24 08:04:13.646345: step: 852/526, loss: 0.00011276135046500713
2023-01-24 08:04:14.702664: step: 856/526, loss: 0.000125417675008066
2023-01-24 08:04:15.779794: step: 860/526, loss: 0.0028902566991746426
2023-01-24 08:04:16.825177: step: 864/526, loss: 0.0005327682010829449
2023-01-24 08:04:17.903504: step: 868/526, loss: 0.008473590947687626
2023-01-24 08:04:18.969276: step: 872/526, loss: 0.0011575708631426096
2023-01-24 08:04:20.037071: step: 876/526, loss: 0.007531928364187479
2023-01-24 08:04:21.115485: step: 880/526, loss: 0.002268790500238538
2023-01-24 08:04:22.181708: step: 884/526, loss: 0.01531816367059946
2023-01-24 08:04:23.248618: step: 888/526, loss: 0.008446996100246906
2023-01-24 08:04:24.321042: step: 892/526, loss: 0.016245784237980843
2023-01-24 08:04:25.402842: step: 896/526, loss: 0.0008730721310712397
2023-01-24 08:04:26.482085: step: 900/526, loss: 0.002750067040324211
2023-01-24 08:04:27.552943: step: 904/526, loss: 0.005723040085285902
2023-01-24 08:04:28.629649: step: 908/526, loss: 0.003289812942966819
2023-01-24 08:04:29.680822: step: 912/526, loss: 0.0006030689692124724
2023-01-24 08:04:30.743906: step: 916/526, loss: 0.005199831910431385
2023-01-24 08:04:31.807760: step: 920/526, loss: 0.013157131150364876
2023-01-24 08:04:32.882354: step: 924/526, loss: 0.0037393078673630953
2023-01-24 08:04:33.939290: step: 928/526, loss: 0.0006819416303187609
2023-01-24 08:04:35.025641: step: 932/526, loss: 0.0004163504345342517
2023-01-24 08:04:36.081343: step: 936/526, loss: 0.003460089908912778
2023-01-24 08:04:37.156032: step: 940/526, loss: 0.003104201750829816
2023-01-24 08:04:38.230282: step: 944/526, loss: 0.008607184514403343
2023-01-24 08:04:39.300311: step: 948/526, loss: 0.008992396295070648
2023-01-24 08:04:40.350471: step: 952/526, loss: 0.0016876272857189178
2023-01-24 08:04:41.427605: step: 956/526, loss: 0.008374501019716263
2023-01-24 08:04:42.490900: step: 960/526, loss: 0.0006010061479173601
2023-01-24 08:04:43.553827: step: 964/526, loss: 0.00041502172825857997
2023-01-24 08:04:44.612600: step: 968/526, loss: 0.002488055732101202
2023-01-24 08:04:45.674640: step: 972/526, loss: 0.0030510660726577044
2023-01-24 08:04:46.736732: step: 976/526, loss: 0.006629373412579298
2023-01-24 08:04:47.816124: step: 980/526, loss: 0.000984479789622128
2023-01-24 08:04:48.891605: step: 984/526, loss: 0.009197777137160301
2023-01-24 08:04:49.954507: step: 988/526, loss: 0.002648509806022048
2023-01-24 08:04:51.022078: step: 992/526, loss: 0.008000624366104603
2023-01-24 08:04:52.081835: step: 996/526, loss: 0.006690055597573519
2023-01-24 08:04:53.145320: step: 1000/526, loss: 0.00349241541698575
2023-01-24 08:04:54.225288: step: 1004/526, loss: 0.007179903332144022
2023-01-24 08:04:55.304645: step: 1008/526, loss: 0.0016613035695627332
2023-01-24 08:04:56.373846: step: 1012/526, loss: 0.0054354192689061165
2023-01-24 08:04:57.439154: step: 1016/526, loss: 0.002949904650449753
2023-01-24 08:04:58.523523: step: 1020/526, loss: 0.0014861278468742967
2023-01-24 08:04:59.588158: step: 1024/526, loss: 0.005480223800987005
2023-01-24 08:05:00.657003: step: 1028/526, loss: 0.00015086343046277761
2023-01-24 08:05:01.719028: step: 1032/526, loss: 0.00649261474609375
2023-01-24 08:05:02.799654: step: 1036/526, loss: 0.007078051567077637
2023-01-24 08:05:03.885649: step: 1040/526, loss: 0.001564691192470491
2023-01-24 08:05:04.973120: step: 1044/526, loss: 0.005240923259407282
2023-01-24 08:05:06.033235: step: 1048/526, loss: 0.0001548617146909237
2023-01-24 08:05:07.098820: step: 1052/526, loss: 0.0038983726408332586
2023-01-24 08:05:08.158878: step: 1056/526, loss: 0.001131076947785914
2023-01-24 08:05:09.239173: step: 1060/526, loss: 0.010171943344175816
2023-01-24 08:05:10.331855: step: 1064/526, loss: 0.004994820803403854
2023-01-24 08:05:11.394227: step: 1068/526, loss: 0.0004371219838503748
2023-01-24 08:05:12.458145: step: 1072/526, loss: 0.0031380902510136366
2023-01-24 08:05:13.571546: step: 1076/526, loss: 0.004172165412455797
2023-01-24 08:05:14.653738: step: 1080/526, loss: 0.0037502821069210768
2023-01-24 08:05:15.719734: step: 1084/526, loss: 7.080791692715138e-05
2023-01-24 08:05:16.808416: step: 1088/526, loss: 0.00041992071783170104
2023-01-24 08:05:17.889752: step: 1092/526, loss: 0.009625636041164398
2023-01-24 08:05:18.972476: step: 1096/526, loss: 0.006246599834412336
2023-01-24 08:05:20.039831: step: 1100/526, loss: 0.0034431691747158766
2023-01-24 08:05:21.112585: step: 1104/526, loss: 0.0004512475279625505
2023-01-24 08:05:22.185049: step: 1108/526, loss: 0.008080788888037205
2023-01-24 08:05:23.278130: step: 1112/526, loss: 0.008534091524779797
2023-01-24 08:05:24.349742: step: 1116/526, loss: 0.003935400862246752
2023-01-24 08:05:25.418027: step: 1120/526, loss: 0.007640754338353872
2023-01-24 08:05:26.485136: step: 1124/526, loss: 0.0037388226483017206
2023-01-24 08:05:27.547005: step: 1128/526, loss: 0.006042583379894495
2023-01-24 08:05:28.611372: step: 1132/526, loss: 0.0033820010721683502
2023-01-24 08:05:29.652363: step: 1136/526, loss: 0.004182777367532253
2023-01-24 08:05:30.726734: step: 1140/526, loss: 0.009561761282384396
2023-01-24 08:05:31.805931: step: 1144/526, loss: 0.00428747246041894
2023-01-24 08:05:32.860848: step: 1148/526, loss: 0.001208893721923232
2023-01-24 08:05:33.930647: step: 1152/526, loss: 0.015343909151852131
2023-01-24 08:05:35.017533: step: 1156/526, loss: 0.00758409732952714
2023-01-24 08:05:36.102618: step: 1160/526, loss: 0.0031642108224332333
2023-01-24 08:05:37.160417: step: 1164/526, loss: 0.008916519582271576
2023-01-24 08:05:38.239042: step: 1168/526, loss: 0.0031977524049580097
2023-01-24 08:05:39.300129: step: 1172/526, loss: 0.006974969524890184
2023-01-24 08:05:40.390835: step: 1176/526, loss: 0.0029876295011490583
2023-01-24 08:05:41.454636: step: 1180/526, loss: 0.004767078440636396
2023-01-24 08:05:42.527039: step: 1184/526, loss: 0.002089911140501499
2023-01-24 08:05:43.594120: step: 1188/526, loss: 0.00031690316973254085
2023-01-24 08:05:44.676650: step: 1192/526, loss: 0.0023573071230202913
2023-01-24 08:05:45.735975: step: 1196/526, loss: 0.004057617392390966
2023-01-24 08:05:46.812033: step: 1200/526, loss: 0.016314206644892693
2023-01-24 08:05:47.895857: step: 1204/526, loss: 0.002020896878093481
2023-01-24 08:05:48.958563: step: 1208/526, loss: 0.005386164877563715
2023-01-24 08:05:50.015414: step: 1212/526, loss: 0.00048268295358866453
2023-01-24 08:05:51.087709: step: 1216/526, loss: 0.0036476771347224712
2023-01-24 08:05:52.157357: step: 1220/526, loss: 0.0019774893298745155
2023-01-24 08:05:53.229001: step: 1224/526, loss: 0.0013882461935281754
2023-01-24 08:05:54.301957: step: 1228/526, loss: 0.002059339312836528
2023-01-24 08:05:55.346322: step: 1232/526, loss: 0.0005826130509376526
2023-01-24 08:05:56.399437: step: 1236/526, loss: 0.00014105670561548322
2023-01-24 08:05:57.474569: step: 1240/526, loss: 0.0026437670458108187
2023-01-24 08:05:58.539736: step: 1244/526, loss: 0.021763278171420097
2023-01-24 08:05:59.610233: step: 1248/526, loss: 0.0022564467508345842
2023-01-24 08:06:00.685237: step: 1252/526, loss: 0.004126391373574734
2023-01-24 08:06:01.739864: step: 1256/526, loss: 0.010915586724877357
2023-01-24 08:06:02.805609: step: 1260/526, loss: 0.0025179910007864237
2023-01-24 08:06:03.892255: step: 1264/526, loss: 0.0007698491681367159
2023-01-24 08:06:04.959669: step: 1268/526, loss: 0.0037589343264698982
2023-01-24 08:06:06.029691: step: 1272/526, loss: 0.0009809480980038643
2023-01-24 08:06:07.090841: step: 1276/526, loss: 0.002951584756374359
2023-01-24 08:06:08.153415: step: 1280/526, loss: 0.00807819701731205
2023-01-24 08:06:09.225612: step: 1284/526, loss: 0.0036871337797492743
2023-01-24 08:06:10.280462: step: 1288/526, loss: 0.0027246992103755474
2023-01-24 08:06:11.352724: step: 1292/526, loss: 0.0006611350690945983
2023-01-24 08:06:12.425703: step: 1296/526, loss: 0.0006722900434397161
2023-01-24 08:06:13.506409: step: 1300/526, loss: 0.005657564383000135
2023-01-24 08:06:14.577509: step: 1304/526, loss: 0.0008522614371031523
2023-01-24 08:06:15.657642: step: 1308/526, loss: 0.002993806032463908
2023-01-24 08:06:16.737642: step: 1312/526, loss: 0.001959262415766716
2023-01-24 08:06:17.849033: step: 1316/526, loss: 0.0008473132620565593
2023-01-24 08:06:18.908194: step: 1320/526, loss: 0.021236548200249672
2023-01-24 08:06:19.984635: step: 1324/526, loss: 0.008937397040426731
2023-01-24 08:06:21.043822: step: 1328/526, loss: 0.023066446185112
2023-01-24 08:06:22.120808: step: 1332/526, loss: 0.002669062465429306
2023-01-24 08:06:23.185445: step: 1336/526, loss: 0.009775707498192787
2023-01-24 08:06:24.268665: step: 1340/526, loss: 0.00567167392000556
2023-01-24 08:06:25.344746: step: 1344/526, loss: 0.0010038410546258092
2023-01-24 08:06:26.405738: step: 1348/526, loss: 0.003936221357434988
2023-01-24 08:06:27.492603: step: 1352/526, loss: 0.014694486744701862
2023-01-24 08:06:28.581501: step: 1356/526, loss: 0.002703920006752014
2023-01-24 08:06:29.638231: step: 1360/526, loss: 0.0029441246297210455
2023-01-24 08:06:30.722053: step: 1364/526, loss: 0.006541743408888578
2023-01-24 08:06:31.805333: step: 1368/526, loss: 0.0013960616197437048
2023-01-24 08:06:32.870846: step: 1372/526, loss: 0.0019162222743034363
2023-01-24 08:06:33.937738: step: 1376/526, loss: 0.0029492340981960297
2023-01-24 08:06:35.009351: step: 1380/526, loss: 0.00548131437972188
2023-01-24 08:06:36.077754: step: 1384/526, loss: 0.0013217887608334422
2023-01-24 08:06:37.149439: step: 1388/526, loss: 0.010780309326946735
2023-01-24 08:06:38.229160: step: 1392/526, loss: 0.002327525522559881
2023-01-24 08:06:39.298543: step: 1396/526, loss: 0.005291208159178495
2023-01-24 08:06:40.365763: step: 1400/526, loss: 0.045353829860687256
2023-01-24 08:06:41.437270: step: 1404/526, loss: 0.012458308599889278
2023-01-24 08:06:42.526214: step: 1408/526, loss: 0.0007240973063744605
2023-01-24 08:06:43.600904: step: 1412/526, loss: 0.006956041324883699
2023-01-24 08:06:44.696627: step: 1416/526, loss: 0.0014333715662360191
2023-01-24 08:06:45.755244: step: 1420/526, loss: 1.070375446943217e-06
2023-01-24 08:06:46.819273: step: 1424/526, loss: 0.0012360136024653912
2023-01-24 08:06:47.876554: step: 1428/526, loss: 0.0007054863963276148
2023-01-24 08:06:48.950946: step: 1432/526, loss: 0.0022484958171844482
2023-01-24 08:06:50.023097: step: 1436/526, loss: 0.004151784814894199
2023-01-24 08:06:51.086173: step: 1440/526, loss: 0.00780200120061636
2023-01-24 08:06:52.162154: step: 1444/526, loss: 5.254819188849069e-05
2023-01-24 08:06:53.241143: step: 1448/526, loss: 0.0012296994682401419
2023-01-24 08:06:54.323184: step: 1452/526, loss: 0.009779248386621475
2023-01-24 08:06:55.389776: step: 1456/526, loss: 0.025997979566454887
2023-01-24 08:06:56.446265: step: 1460/526, loss: 0.0006762303528375924
2023-01-24 08:06:57.519856: step: 1464/526, loss: 0.0008575352840125561
2023-01-24 08:06:58.619035: step: 1468/526, loss: 0.001646463293582201
2023-01-24 08:06:59.687747: step: 1472/526, loss: 0.007763678673654795
2023-01-24 08:07:00.774067: step: 1476/526, loss: 0.0030321392696350813
2023-01-24 08:07:01.841969: step: 1480/526, loss: 0.007338542956858873
2023-01-24 08:07:02.929296: step: 1484/526, loss: 0.004938645288348198
2023-01-24 08:07:03.990919: step: 1488/526, loss: 0.011469047516584396
2023-01-24 08:07:05.047304: step: 1492/526, loss: 0.006655020639300346
2023-01-24 08:07:06.103572: step: 1496/526, loss: 0.02961951494216919
2023-01-24 08:07:07.168845: step: 1500/526, loss: 0.0001534883485874161
2023-01-24 08:07:08.227557: step: 1504/526, loss: 0.003928833641111851
2023-01-24 08:07:09.282092: step: 1508/526, loss: 0.018733810633420944
2023-01-24 08:07:10.328710: step: 1512/526, loss: 0.0005932717467658222
2023-01-24 08:07:11.376151: step: 1516/526, loss: 0.0012880591675639153
2023-01-24 08:07:12.452017: step: 1520/526, loss: 0.0016507901018485427
2023-01-24 08:07:13.513758: step: 1524/526, loss: 0.007693939842283726
2023-01-24 08:07:14.564877: step: 1528/526, loss: 0.001705571310594678
2023-01-24 08:07:15.620794: step: 1532/526, loss: 0.005585390608757734
2023-01-24 08:07:16.696423: step: 1536/526, loss: 0.001855135546065867
2023-01-24 08:07:17.774576: step: 1540/526, loss: 0.002898991806432605
2023-01-24 08:07:18.830215: step: 1544/526, loss: 0.006664915941655636
2023-01-24 08:07:19.885515: step: 1548/526, loss: 0.001996766310185194
2023-01-24 08:07:20.973684: step: 1552/526, loss: 0.0051386235281825066
2023-01-24 08:07:22.016508: step: 1556/526, loss: 0.0005143631133250892
2023-01-24 08:07:23.097376: step: 1560/526, loss: 0.012425909750163555
2023-01-24 08:07:24.166130: step: 1564/526, loss: 0.009358774870634079
2023-01-24 08:07:25.239360: step: 1568/526, loss: 0.007750874850898981
2023-01-24 08:07:26.309068: step: 1572/526, loss: 3.952288534492254e-05
2023-01-24 08:07:27.367405: step: 1576/526, loss: 2.425097136438126e-07
2023-01-24 08:07:28.441172: step: 1580/526, loss: 0.004351557698100805
2023-01-24 08:07:29.509976: step: 1584/526, loss: 0.004653299227356911
2023-01-24 08:07:30.575384: step: 1588/526, loss: 0.005408448167145252
2023-01-24 08:07:31.660770: step: 1592/526, loss: 0.003711160272359848
2023-01-24 08:07:32.757942: step: 1596/526, loss: 0.007804130669683218
2023-01-24 08:07:33.824345: step: 1600/526, loss: 0.00831583607941866
2023-01-24 08:07:34.905818: step: 1604/526, loss: 0.004499559290707111
2023-01-24 08:07:35.988359: step: 1608/526, loss: 0.00016871334810275584
2023-01-24 08:07:37.041061: step: 1612/526, loss: 0.0040127187967300415
2023-01-24 08:07:38.116443: step: 1616/526, loss: 0.009973247535526752
2023-01-24 08:07:39.184285: step: 1620/526, loss: 0.018963787704706192
2023-01-24 08:07:40.261601: step: 1624/526, loss: 0.0055965096689760685
2023-01-24 08:07:41.310970: step: 1628/526, loss: 0.015125522390007973
2023-01-24 08:07:42.397412: step: 1632/526, loss: 0.006289013661444187
2023-01-24 08:07:43.444488: step: 1636/526, loss: 0.016031652688980103
2023-01-24 08:07:44.532613: step: 1640/526, loss: 0.0021265451796352863
2023-01-24 08:07:45.584485: step: 1644/526, loss: 0.00998340267688036
2023-01-24 08:07:46.676913: step: 1648/526, loss: 0.008487081155180931
2023-01-24 08:07:47.749451: step: 1652/526, loss: 0.00037652032915502787
2023-01-24 08:07:48.828895: step: 1656/526, loss: 0.01791190728545189
2023-01-24 08:07:49.885877: step: 1660/526, loss: 0.0
2023-01-24 08:07:50.961409: step: 1664/526, loss: 0.010901509784162045
2023-01-24 08:07:52.038213: step: 1668/526, loss: 0.007096904795616865
2023-01-24 08:07:53.096196: step: 1672/526, loss: 0.003612255910411477
2023-01-24 08:07:54.158397: step: 1676/526, loss: 0.0021530084777623415
2023-01-24 08:07:55.230958: step: 1680/526, loss: 0.0030258512124419212
2023-01-24 08:07:56.297272: step: 1684/526, loss: 0.0048541477881371975
2023-01-24 08:07:57.381962: step: 1688/526, loss: 0.0006590585107915103
2023-01-24 08:07:58.448505: step: 1692/526, loss: 0.009203913621604443
2023-01-24 08:07:59.534559: step: 1696/526, loss: 0.0005242836778052151
2023-01-24 08:08:00.622454: step: 1700/526, loss: 0.00464558694511652
2023-01-24 08:08:01.688895: step: 1704/526, loss: 0.00245933816768229
2023-01-24 08:08:02.760377: step: 1708/526, loss: 0.0018439812120050192
2023-01-24 08:08:03.837035: step: 1712/526, loss: 0.010666943155229092
2023-01-24 08:08:04.905099: step: 1716/526, loss: 0.00019439266179688275
2023-01-24 08:08:05.974602: step: 1720/526, loss: 0.003129103686660528
2023-01-24 08:08:07.060874: step: 1724/526, loss: 0.0022669986356049776
2023-01-24 08:08:08.119483: step: 1728/526, loss: 0.006754318252205849
2023-01-24 08:08:09.196631: step: 1732/526, loss: 0.003376535139977932
2023-01-24 08:08:10.263533: step: 1736/526, loss: 0.007157266139984131
2023-01-24 08:08:11.350470: step: 1740/526, loss: 0.0134523194283247
2023-01-24 08:08:12.403266: step: 1744/526, loss: 0.0051355487667024136
2023-01-24 08:08:13.482451: step: 1748/526, loss: 0.006010604090988636
2023-01-24 08:08:14.546639: step: 1752/526, loss: 0.0007501115323975682
2023-01-24 08:08:15.611984: step: 1756/526, loss: 0.0002574706741143018
2023-01-24 08:08:16.663325: step: 1760/526, loss: 0.006906383205205202
2023-01-24 08:08:17.734995: step: 1764/526, loss: 0.003060990246012807
2023-01-24 08:08:18.829221: step: 1768/526, loss: 0.00755661353468895
2023-01-24 08:08:19.895469: step: 1772/526, loss: 0.0031891348771750927
2023-01-24 08:08:20.949992: step: 1776/526, loss: 0.008128157816827297
2023-01-24 08:08:21.998993: step: 1780/526, loss: 0.0039753383025527
2023-01-24 08:08:23.069637: step: 1784/526, loss: 0.004681938327848911
2023-01-24 08:08:24.121125: step: 1788/526, loss: 0.00044340832391753793
2023-01-24 08:08:25.193214: step: 1792/526, loss: 0.007938959635794163
2023-01-24 08:08:26.288706: step: 1796/526, loss: 0.010996698401868343
2023-01-24 08:08:27.360661: step: 1800/526, loss: 0.00542069086804986
2023-01-24 08:08:28.432500: step: 1804/526, loss: 0.010516573674976826
2023-01-24 08:08:29.478296: step: 1808/526, loss: 0.001993355806916952
2023-01-24 08:08:30.531766: step: 1812/526, loss: 0.001645339885726571
2023-01-24 08:08:31.601884: step: 1816/526, loss: 0.001747045200318098
2023-01-24 08:08:32.661690: step: 1820/526, loss: 0.0017123748548328876
2023-01-24 08:08:33.718605: step: 1824/526, loss: 0.00014265051868278533
2023-01-24 08:08:34.790054: step: 1828/526, loss: 0.04269849509000778
2023-01-24 08:08:35.852375: step: 1832/526, loss: 0.00025080618797801435
2023-01-24 08:08:36.907311: step: 1836/526, loss: 0.002907001879066229
2023-01-24 08:08:37.981744: step: 1840/526, loss: 0.0049316114746034145
2023-01-24 08:08:39.051146: step: 1844/526, loss: 0.018841296434402466
2023-01-24 08:08:40.144563: step: 1848/526, loss: 0.00803183764219284
2023-01-24 08:08:41.209318: step: 1852/526, loss: 0.004255578387528658
2023-01-24 08:08:42.280410: step: 1856/526, loss: 0.003771889489144087
2023-01-24 08:08:43.347393: step: 1860/526, loss: 0.006448616273701191
2023-01-24 08:08:44.421381: step: 1864/526, loss: 0.011281045153737068
2023-01-24 08:08:45.492842: step: 1868/526, loss: 0.0024426572490483522
2023-01-24 08:08:46.555884: step: 1872/526, loss: 0.000969375076238066
2023-01-24 08:08:47.602809: step: 1876/526, loss: 0.004139092285186052
2023-01-24 08:08:48.671498: step: 1880/526, loss: 0.0036636251024901867
2023-01-24 08:08:49.734972: step: 1884/526, loss: 0.005768220871686935
2023-01-24 08:08:50.795652: step: 1888/526, loss: 0.014645333401858807
2023-01-24 08:08:51.859666: step: 1892/526, loss: 0.0038437529001384974
2023-01-24 08:08:52.924172: step: 1896/526, loss: 0.006669899448752403
2023-01-24 08:08:54.005383: step: 1900/526, loss: 0.0027901632711291313
2023-01-24 08:08:55.071764: step: 1904/526, loss: 0.0050841630436480045
2023-01-24 08:08:56.127991: step: 1908/526, loss: 0.0026445232797414064
2023-01-24 08:08:57.189098: step: 1912/526, loss: 0.008343411609530449
2023-01-24 08:08:58.265442: step: 1916/526, loss: 0.0038834193255752325
2023-01-24 08:08:59.332044: step: 1920/526, loss: 0.008884825743734837
2023-01-24 08:09:00.395589: step: 1924/526, loss: 3.729144009412266e-05
2023-01-24 08:09:01.468187: step: 1928/526, loss: 0.009907491505146027
2023-01-24 08:09:02.523583: step: 1932/526, loss: 0.009486119262874126
2023-01-24 08:09:03.592241: step: 1936/526, loss: 0.025884343311190605
2023-01-24 08:09:04.661917: step: 1940/526, loss: 0.004642680287361145
2023-01-24 08:09:05.739466: step: 1944/526, loss: 0.003738254541531205
2023-01-24 08:09:06.801765: step: 1948/526, loss: 0.003660036949440837
2023-01-24 08:09:07.862856: step: 1952/526, loss: 0.0011103119468316436
2023-01-24 08:09:08.948426: step: 1956/526, loss: 0.005755078047513962
2023-01-24 08:09:10.031101: step: 1960/526, loss: 0.0012564045609906316
2023-01-24 08:09:11.099690: step: 1964/526, loss: 0.003929882310330868
2023-01-24 08:09:12.165079: step: 1968/526, loss: 0.002068354981020093
2023-01-24 08:09:13.229757: step: 1972/526, loss: 0.013658208772540092
2023-01-24 08:09:14.319754: step: 1976/526, loss: 0.0031996287871152163
2023-01-24 08:09:15.376156: step: 1980/526, loss: 0.0004426951054483652
2023-01-24 08:09:16.441476: step: 1984/526, loss: 0.007202464155852795
2023-01-24 08:09:17.519266: step: 1988/526, loss: 0.0019553338643163443
2023-01-24 08:09:18.576712: step: 1992/526, loss: 0.0005978432018309832
2023-01-24 08:09:19.637230: step: 1996/526, loss: 0.01198502816259861
2023-01-24 08:09:20.712179: step: 2000/526, loss: 0.006707605440169573
2023-01-24 08:09:21.773816: step: 2004/526, loss: 0.0064396606758236885
2023-01-24 08:09:22.842642: step: 2008/526, loss: 0.015926480293273926
2023-01-24 08:09:23.911168: step: 2012/526, loss: 0.00544326938688755
2023-01-24 08:09:24.980193: step: 2016/526, loss: 0.0013194968923926353
2023-01-24 08:09:26.042364: step: 2020/526, loss: 0.007548683788627386
2023-01-24 08:09:27.110057: step: 2024/526, loss: 0.005086565390229225
2023-01-24 08:09:28.165079: step: 2028/526, loss: 0.009567863307893276
2023-01-24 08:09:29.239013: step: 2032/526, loss: 0.004748514387756586
2023-01-24 08:09:30.316597: step: 2036/526, loss: 0.013343237340450287
2023-01-24 08:09:31.384322: step: 2040/526, loss: 0.005300730932503939
2023-01-24 08:09:32.451227: step: 2044/526, loss: 0.005254854913800955
2023-01-24 08:09:33.514436: step: 2048/526, loss: 0.00332982768304646
2023-01-24 08:09:34.586715: step: 2052/526, loss: 0.005135139916092157
2023-01-24 08:09:35.634490: step: 2056/526, loss: 0.0008605180773884058
2023-01-24 08:09:36.721424: step: 2060/526, loss: 0.0008949894108809531
2023-01-24 08:09:37.796457: step: 2064/526, loss: 0.003249643836170435
2023-01-24 08:09:38.881102: step: 2068/526, loss: 0.002316853031516075
2023-01-24 08:09:39.944354: step: 2072/526, loss: 0.0030070352368056774
2023-01-24 08:09:41.015963: step: 2076/526, loss: 0.01448208000510931
2023-01-24 08:09:42.093371: step: 2080/526, loss: 0.003342254087328911
2023-01-24 08:09:43.155746: step: 2084/526, loss: 0.002919140039011836
2023-01-24 08:09:44.207021: step: 2088/526, loss: 0.0007625837461091578
2023-01-24 08:09:45.277739: step: 2092/526, loss: 0.012680702842772007
2023-01-24 08:09:46.349792: step: 2096/526, loss: 0.0038279560394585133
2023-01-24 08:09:47.414950: step: 2100/526, loss: 0.007321455050259829
2023-01-24 08:09:48.493561: step: 2104/526, loss: 9.103171032620594e-05
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3627203744093057, 'r': 0.27049166440769856, 'f1': 0.3098893633540373}, 'combined': 0.22833953089244852, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3595663265306122, 'r': 0.22337194484381126, 'f1': 0.2755592953885843}, 'combined': 0.15030507021195508, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35907320487483535, 'r': 0.313422531769306, 'f1': 0.33469842804949196}, 'combined': 0.24661989435225723, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36662067881327265, 'r': 0.2784036261802528, 'f1': 0.31647962913678246}, 'combined': 0.17262525225642678, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 08:12:39.571880: step: 4/526, loss: 0.0015527985524386168
2023-01-24 08:12:40.631460: step: 8/526, loss: 0.014374683611094952
2023-01-24 08:12:41.685171: step: 12/526, loss: 0.031547218561172485
2023-01-24 08:12:42.743731: step: 16/526, loss: 0.0018152552656829357
2023-01-24 08:12:43.809565: step: 20/526, loss: 0.005823378451168537
2023-01-24 08:12:44.899911: step: 24/526, loss: 0.0015533366240561008
2023-01-24 08:12:45.940273: step: 28/526, loss: 0.0017239629523828626
2023-01-24 08:12:47.005825: step: 32/526, loss: 0.0015903108287602663
2023-01-24 08:12:48.077097: step: 36/526, loss: 0.02297254465520382
2023-01-24 08:12:49.124288: step: 40/526, loss: 0.006770250853151083
2023-01-24 08:12:50.189600: step: 44/526, loss: 1.668453660386149e-05
2023-01-24 08:12:51.240611: step: 48/526, loss: 0.006846142932772636
2023-01-24 08:12:52.297628: step: 52/526, loss: 0.008534999564290047
2023-01-24 08:12:53.365240: step: 56/526, loss: 0.0011843078536912799
2023-01-24 08:12:54.429079: step: 60/526, loss: 0.0013481620699167252
2023-01-24 08:12:55.493014: step: 64/526, loss: 1.7529895558254793e-05
2023-01-24 08:12:56.556431: step: 68/526, loss: 0.0027651020791381598
2023-01-24 08:12:57.612037: step: 72/526, loss: 0.0037084210198372602
2023-01-24 08:12:58.657910: step: 76/526, loss: 0.004029603209346533
2023-01-24 08:12:59.713903: step: 80/526, loss: 0.0006209263810887933
2023-01-24 08:13:00.764273: step: 84/526, loss: 0.0076514557003974915
2023-01-24 08:13:01.837983: step: 88/526, loss: 0.0038024436216801405
2023-01-24 08:13:02.905964: step: 92/526, loss: 0.00641417084261775
2023-01-24 08:13:03.981143: step: 96/526, loss: 0.00012367230374366045
2023-01-24 08:13:05.045298: step: 100/526, loss: 0.02735537476837635
2023-01-24 08:13:06.116546: step: 104/526, loss: 0.004092162940651178
2023-01-24 08:13:07.186748: step: 108/526, loss: 0.011058001779019833
2023-01-24 08:13:08.271291: step: 112/526, loss: 0.02300676517188549
2023-01-24 08:13:09.334230: step: 116/526, loss: 0.022482266649603844
2023-01-24 08:13:10.406206: step: 120/526, loss: 0.005871300119906664
2023-01-24 08:13:11.468796: step: 124/526, loss: 0.004005140159279108
2023-01-24 08:13:12.528262: step: 128/526, loss: 0.0016097135376185179
2023-01-24 08:13:13.592865: step: 132/526, loss: 0.01079469919204712
2023-01-24 08:13:14.650857: step: 136/526, loss: 0.0074540250934660435
2023-01-24 08:13:15.711972: step: 140/526, loss: 0.009236044250428677
2023-01-24 08:13:16.779497: step: 144/526, loss: 0.0033466038294136524
2023-01-24 08:13:17.842034: step: 148/526, loss: 0.01184664387255907
2023-01-24 08:13:18.900552: step: 152/526, loss: 0.007839243859052658
2023-01-24 08:13:19.967119: step: 156/526, loss: 0.0007059240597300231
2023-01-24 08:13:21.038533: step: 160/526, loss: 0.00021463612210936844
2023-01-24 08:13:22.123517: step: 164/526, loss: 0.0018794374773278832
2023-01-24 08:13:23.184012: step: 168/526, loss: 1.3485400529589242e-07
2023-01-24 08:13:24.245800: step: 172/526, loss: 0.008626885712146759
2023-01-24 08:13:25.311044: step: 176/526, loss: 0.0022632277105003595
2023-01-24 08:13:26.377293: step: 180/526, loss: 0.0004742064338643104
2023-01-24 08:13:27.435747: step: 184/526, loss: 0.005966256372630596
2023-01-24 08:13:28.491842: step: 188/526, loss: 0.006731688976287842
2023-01-24 08:13:29.567272: step: 192/526, loss: 0.003024298930540681
2023-01-24 08:13:30.624452: step: 196/526, loss: 0.0009065989870578051
2023-01-24 08:13:31.702492: step: 200/526, loss: 0.005843481048941612
2023-01-24 08:13:32.771846: step: 204/526, loss: 0.007101226598024368
2023-01-24 08:13:33.870285: step: 208/526, loss: 0.0020167578477412462
2023-01-24 08:13:34.920522: step: 212/526, loss: 0.004854851868003607
2023-01-24 08:13:35.980662: step: 216/526, loss: 0.012142536230385303
2023-01-24 08:13:37.043576: step: 220/526, loss: 0.0005539586418308318
2023-01-24 08:13:38.133213: step: 224/526, loss: 0.04283495992422104
2023-01-24 08:13:39.182941: step: 228/526, loss: 0.008202563039958477
2023-01-24 08:13:40.263231: step: 232/526, loss: 7.255576929310337e-05
2023-01-24 08:13:41.315566: step: 236/526, loss: 0.005904634948819876
2023-01-24 08:13:42.384217: step: 240/526, loss: 0.006485240068286657
2023-01-24 08:13:43.447362: step: 244/526, loss: 0.0017279810272157192
2023-01-24 08:13:44.509565: step: 248/526, loss: 0.0019765414763242006
2023-01-24 08:13:45.590077: step: 252/526, loss: 0.011654307134449482
2023-01-24 08:13:46.650054: step: 256/526, loss: 0.0013926109531894326
2023-01-24 08:13:47.719983: step: 260/526, loss: 0.0012710947776213288
2023-01-24 08:13:48.795326: step: 264/526, loss: 0.004178334027528763
2023-01-24 08:13:49.861446: step: 268/526, loss: 0.005153834819793701
2023-01-24 08:13:50.932757: step: 272/526, loss: 0.009852041490375996
2023-01-24 08:13:52.006194: step: 276/526, loss: 0.014089401811361313
2023-01-24 08:13:53.064292: step: 280/526, loss: 0.0109657421708107
2023-01-24 08:13:54.135230: step: 284/526, loss: 0.009788258001208305
2023-01-24 08:13:55.203925: step: 288/526, loss: 0.0015343743143603206
2023-01-24 08:13:56.271629: step: 292/526, loss: 0.004654880613088608
2023-01-24 08:13:57.350980: step: 296/526, loss: 0.003607081947848201
2023-01-24 08:13:58.409618: step: 300/526, loss: 0.0023208078928291798
2023-01-24 08:13:59.480682: step: 304/526, loss: 9.466566552873701e-05
2023-01-24 08:14:00.551479: step: 308/526, loss: 0.0012133034178987145
2023-01-24 08:14:01.611154: step: 312/526, loss: 1.093564696930116e-05
2023-01-24 08:14:02.688783: step: 316/526, loss: 0.0027408935129642487
2023-01-24 08:14:03.744680: step: 320/526, loss: 0.0001672089856583625
2023-01-24 08:14:04.807316: step: 324/526, loss: 0.001920043141581118
2023-01-24 08:14:05.877673: step: 328/526, loss: 0.008366193622350693
2023-01-24 08:14:06.942590: step: 332/526, loss: 0.0013664762955158949
2023-01-24 08:14:08.022862: step: 336/526, loss: 0.0013654837384819984
2023-01-24 08:14:09.102533: step: 340/526, loss: 0.00759208295494318
2023-01-24 08:14:10.166198: step: 344/526, loss: 0.00845970306545496
2023-01-24 08:14:11.228482: step: 348/526, loss: 0.00380527856759727
2023-01-24 08:14:12.305907: step: 352/526, loss: 0.004360434133559465
2023-01-24 08:14:13.395605: step: 356/526, loss: 0.003152074757963419
2023-01-24 08:14:14.448331: step: 360/526, loss: 0.003814096562564373
2023-01-24 08:14:15.521730: step: 364/526, loss: 0.006370061542838812
2023-01-24 08:14:16.569416: step: 368/526, loss: 0.0013150274753570557
2023-01-24 08:14:17.639214: step: 372/526, loss: 0.004130323883146048
2023-01-24 08:14:18.688045: step: 376/526, loss: 0.003450981108471751
2023-01-24 08:14:19.760255: step: 380/526, loss: 0.009133800864219666
2023-01-24 08:14:20.836208: step: 384/526, loss: 0.0006803752621635795
2023-01-24 08:14:21.913892: step: 388/526, loss: 0.004730725660920143
2023-01-24 08:14:22.974451: step: 392/526, loss: 0.0004839395696762949
2023-01-24 08:14:24.028449: step: 396/526, loss: 0.001510030822828412
2023-01-24 08:14:25.081742: step: 400/526, loss: 0.000566075905226171
2023-01-24 08:14:26.156206: step: 404/526, loss: 0.013921750709414482
2023-01-24 08:14:27.213831: step: 408/526, loss: 0.0026388985570520163
2023-01-24 08:14:28.277809: step: 412/526, loss: 0.0052538057789206505
2023-01-24 08:14:29.324749: step: 416/526, loss: 0.004278465639799833
2023-01-24 08:14:30.401643: step: 420/526, loss: 0.0018223561346530914
2023-01-24 08:14:31.471940: step: 424/526, loss: 0.0027730856090784073
2023-01-24 08:14:32.548082: step: 428/526, loss: 0.0028003661427646875
2023-01-24 08:14:33.610841: step: 432/526, loss: 0.0019438628805801272
2023-01-24 08:14:34.682830: step: 436/526, loss: 0.03799775615334511
2023-01-24 08:14:35.739367: step: 440/526, loss: 0.0010687094181776047
2023-01-24 08:14:36.805070: step: 444/526, loss: 0.003563548671081662
2023-01-24 08:14:37.891078: step: 448/526, loss: 3.423057569307275e-05
2023-01-24 08:14:38.964101: step: 452/526, loss: 0.00042447546729817986
2023-01-24 08:14:40.036930: step: 456/526, loss: 0.003115955973044038
2023-01-24 08:14:41.118330: step: 460/526, loss: 0.0036883896682411432
2023-01-24 08:14:42.175673: step: 464/526, loss: 0.0007377912406809628
2023-01-24 08:14:43.233799: step: 468/526, loss: 0.0027743177488446236
2023-01-24 08:14:44.303379: step: 472/526, loss: 0.0005061248666606843
2023-01-24 08:14:45.381591: step: 476/526, loss: 0.011965678073465824
2023-01-24 08:14:46.450410: step: 480/526, loss: 0.0027339213993400335
2023-01-24 08:14:47.527883: step: 484/526, loss: 0.006434708833694458
2023-01-24 08:14:48.597223: step: 488/526, loss: 0.006143766921013594
2023-01-24 08:14:49.674623: step: 492/526, loss: 0.00266039720736444
2023-01-24 08:14:50.756384: step: 496/526, loss: 0.004466984886676073
2023-01-24 08:14:51.830345: step: 500/526, loss: 0.007771104574203491
2023-01-24 08:14:52.900733: step: 504/526, loss: 0.0009978280868381262
2023-01-24 08:14:53.969223: step: 508/526, loss: 0.003268573898822069
2023-01-24 08:14:55.038856: step: 512/526, loss: 0.026066893711686134
2023-01-24 08:14:56.134518: step: 516/526, loss: 0.001402052235789597
2023-01-24 08:14:57.210122: step: 520/526, loss: 0.0007467272225767374
2023-01-24 08:14:58.293386: step: 524/526, loss: 3.6508750781649724e-05
2023-01-24 08:14:59.359656: step: 528/526, loss: 0.00518309511244297
2023-01-24 08:15:00.426219: step: 532/526, loss: 0.005357992369681597
2023-01-24 08:15:01.492058: step: 536/526, loss: 0.005535739473998547
2023-01-24 08:15:02.546274: step: 540/526, loss: 0.0008894001948647201
2023-01-24 08:15:03.621670: step: 544/526, loss: 0.011152184568345547
2023-01-24 08:15:04.694409: step: 548/526, loss: 0.0015413216315209866
2023-01-24 08:15:05.756236: step: 552/526, loss: 0.003057967172935605
2023-01-24 08:15:06.833551: step: 556/526, loss: 0.004721699748188257
2023-01-24 08:15:07.906491: step: 560/526, loss: 0.007417446468025446
2023-01-24 08:15:08.988372: step: 564/526, loss: 0.002286262344568968
2023-01-24 08:15:10.056921: step: 568/526, loss: 0.004955897573381662
2023-01-24 08:15:11.124511: step: 572/526, loss: 0.0023692059330642223
2023-01-24 08:15:12.194248: step: 576/526, loss: 0.0017217101994901896
2023-01-24 08:15:13.285526: step: 580/526, loss: 0.0013488983968272805
2023-01-24 08:15:14.344026: step: 584/526, loss: 0.01599848084151745
2023-01-24 08:15:15.422199: step: 588/526, loss: 0.0005247867084108293
2023-01-24 08:15:16.494045: step: 592/526, loss: 0.001362834358587861
2023-01-24 08:15:17.563744: step: 596/526, loss: 0.0014658961445093155
2023-01-24 08:15:18.641100: step: 600/526, loss: 0.006384869571775198
2023-01-24 08:15:19.704539: step: 604/526, loss: 0.0025591112207621336
2023-01-24 08:15:20.787654: step: 608/526, loss: 0.004175042267888784
2023-01-24 08:15:21.848555: step: 612/526, loss: 0.0018523165490478277
2023-01-24 08:15:22.920923: step: 616/526, loss: 0.009955846704542637
2023-01-24 08:15:23.987117: step: 620/526, loss: 0.0005123216542415321
2023-01-24 08:15:25.052483: step: 624/526, loss: 0.004340380430221558
2023-01-24 08:15:26.127885: step: 628/526, loss: 0.003832641988992691
2023-01-24 08:15:27.194450: step: 632/526, loss: 0.005103746894747019
2023-01-24 08:15:28.277834: step: 636/526, loss: 0.0017348246183246374
2023-01-24 08:15:29.340167: step: 640/526, loss: 0.007120194844901562
2023-01-24 08:15:30.412320: step: 644/526, loss: 0.00256592920050025
2023-01-24 08:15:31.494226: step: 648/526, loss: 0.0014505682047456503
2023-01-24 08:15:32.578104: step: 652/526, loss: 0.006125299725681543
2023-01-24 08:15:33.638345: step: 656/526, loss: 0.0025907312519848347
2023-01-24 08:15:34.703050: step: 660/526, loss: 0.00689921248704195
2023-01-24 08:15:35.763217: step: 664/526, loss: 0.0011587593471631408
2023-01-24 08:15:36.834544: step: 668/526, loss: 0.0008978423429653049
2023-01-24 08:15:37.919449: step: 672/526, loss: 0.025185955688357353
2023-01-24 08:15:38.996837: step: 676/526, loss: 0.006375297904014587
2023-01-24 08:15:40.063959: step: 680/526, loss: 0.0036048106849193573
2023-01-24 08:15:41.136921: step: 684/526, loss: 0.004133682232350111
2023-01-24 08:15:42.201381: step: 688/526, loss: 0.003429161850363016
2023-01-24 08:15:43.278959: step: 692/526, loss: 0.0010575143387541175
2023-01-24 08:15:44.328563: step: 696/526, loss: 0.0071308184415102005
2023-01-24 08:15:45.415981: step: 700/526, loss: 0.0032010809518396854
2023-01-24 08:15:46.482998: step: 704/526, loss: 0.0027031844947487116
2023-01-24 08:15:47.555196: step: 708/526, loss: 0.0027517429552972317
2023-01-24 08:15:48.644052: step: 712/526, loss: 0.0039056241512298584
2023-01-24 08:15:49.738224: step: 716/526, loss: 0.00367858842946589
2023-01-24 08:15:50.805892: step: 720/526, loss: 0.005079750902950764
2023-01-24 08:15:51.881298: step: 724/526, loss: 0.014265777543187141
2023-01-24 08:15:52.934798: step: 728/526, loss: 0.004944941960275173
2023-01-24 08:15:54.010894: step: 732/526, loss: 0.007102068513631821
2023-01-24 08:15:55.094420: step: 736/526, loss: 0.004638230428099632
2023-01-24 08:15:56.171842: step: 740/526, loss: 0.00040970550617203116
2023-01-24 08:15:57.250700: step: 744/526, loss: 0.00910506397485733
2023-01-24 08:15:58.312191: step: 748/526, loss: 0.005753392819315195
2023-01-24 08:15:59.402826: step: 752/526, loss: 0.0017255906714126468
2023-01-24 08:16:00.471948: step: 756/526, loss: 0.0064187017269432545
2023-01-24 08:16:01.539025: step: 760/526, loss: 5.205323759582825e-06
2023-01-24 08:16:02.603291: step: 764/526, loss: 0.010814828798174858
2023-01-24 08:16:03.674674: step: 768/526, loss: 0.0007021827041171491
2023-01-24 08:16:04.741083: step: 772/526, loss: 0.017233768478035927
2023-01-24 08:16:05.816721: step: 776/526, loss: 0.0018336690263822675
2023-01-24 08:16:06.883494: step: 780/526, loss: 0.017620448023080826
2023-01-24 08:16:07.953852: step: 784/526, loss: 0.0032585207372903824
2023-01-24 08:16:09.019602: step: 788/526, loss: 0.003399219363927841
2023-01-24 08:16:10.097954: step: 792/526, loss: 0.002600764622911811
2023-01-24 08:16:11.169714: step: 796/526, loss: 0.0220213383436203
2023-01-24 08:16:12.240742: step: 800/526, loss: 0.005034157540649176
2023-01-24 08:16:13.317986: step: 804/526, loss: 0.0007320235599763691
2023-01-24 08:16:14.388702: step: 808/526, loss: 0.005935746245086193
2023-01-24 08:16:15.465362: step: 812/526, loss: 0.007137676235288382
2023-01-24 08:16:16.553858: step: 816/526, loss: 0.0001293757522944361
2023-01-24 08:16:17.607397: step: 820/526, loss: 0.0055822706781327724
2023-01-24 08:16:18.676154: step: 824/526, loss: 0.006855186074972153
2023-01-24 08:16:19.752131: step: 828/526, loss: 0.00790692213922739
2023-01-24 08:16:20.828943: step: 832/526, loss: 0.005788835696876049
2023-01-24 08:16:21.896228: step: 836/526, loss: 0.0043522366322577
2023-01-24 08:16:22.952470: step: 840/526, loss: 0.005438192281872034
2023-01-24 08:16:24.021347: step: 844/526, loss: 0.008489994332194328
2023-01-24 08:16:25.103142: step: 848/526, loss: 0.009495867416262627
2023-01-24 08:16:26.171308: step: 852/526, loss: 0.0021484524477273226
2023-01-24 08:16:27.245104: step: 856/526, loss: 0.00551944226026535
2023-01-24 08:16:28.305863: step: 860/526, loss: 0.007676903158426285
2023-01-24 08:16:29.376267: step: 864/526, loss: 0.0011822825763374567
2023-01-24 08:16:30.433128: step: 868/526, loss: 9.398196561960503e-05
2023-01-24 08:16:31.508124: step: 872/526, loss: 0.0012379330582916737
2023-01-24 08:16:32.594078: step: 876/526, loss: 0.0032965163700282574
2023-01-24 08:16:33.670073: step: 880/526, loss: 0.0019311937503516674
2023-01-24 08:16:34.739862: step: 884/526, loss: 0.004509120713919401
2023-01-24 08:16:35.803889: step: 888/526, loss: 7.450580152834618e-10
2023-01-24 08:16:36.886342: step: 892/526, loss: 0.0016446230001747608
2023-01-24 08:16:37.964884: step: 896/526, loss: 0.0030757449567317963
2023-01-24 08:16:39.044082: step: 900/526, loss: 0.0008036759681999683
2023-01-24 08:16:40.132265: step: 904/526, loss: 0.005558198317885399
2023-01-24 08:16:41.214343: step: 908/526, loss: 0.004003367852419615
2023-01-24 08:16:42.293791: step: 912/526, loss: 0.0060005527921020985
2023-01-24 08:16:43.373656: step: 916/526, loss: 0.004042772110551596
2023-01-24 08:16:44.442020: step: 920/526, loss: 0.005234920885413885
2023-01-24 08:16:45.501034: step: 924/526, loss: 0.0028326527681201696
2023-01-24 08:16:46.571792: step: 928/526, loss: 0.0022338866256177425
2023-01-24 08:16:47.647778: step: 932/526, loss: 0.0014650358352810144
2023-01-24 08:16:48.714547: step: 936/526, loss: 0.0013492372818291187
2023-01-24 08:16:49.803946: step: 940/526, loss: 0.0060861967504024506
2023-01-24 08:16:50.869329: step: 944/526, loss: 0.0016624766867607832
2023-01-24 08:16:51.955255: step: 948/526, loss: 0.000540849519893527
2023-01-24 08:16:53.030144: step: 952/526, loss: 0.011057938449084759
2023-01-24 08:16:54.111480: step: 956/526, loss: 0.006618036888539791
2023-01-24 08:16:55.175744: step: 960/526, loss: 0.049181126058101654
2023-01-24 08:16:56.244211: step: 964/526, loss: 0.00348468660376966
2023-01-24 08:16:57.303571: step: 968/526, loss: 0.00021710555301979184
2023-01-24 08:16:58.370442: step: 972/526, loss: 0.004641115665435791
2023-01-24 08:16:59.429769: step: 976/526, loss: 0.0018969716038554907
2023-01-24 08:17:00.519737: step: 980/526, loss: 0.011055637151002884
2023-01-24 08:17:01.602849: step: 984/526, loss: 0.01181644294410944
2023-01-24 08:17:02.679590: step: 988/526, loss: 0.00918593630194664
2023-01-24 08:17:03.743856: step: 992/526, loss: 0.020358357578516006
2023-01-24 08:17:04.832365: step: 996/526, loss: 0.00013514564489014447
2023-01-24 08:17:05.902092: step: 1000/526, loss: 0.0010516230249777436
2023-01-24 08:17:06.982320: step: 1004/526, loss: 0.0015638668555766344
2023-01-24 08:17:08.057033: step: 1008/526, loss: 0.0017984991427510977
2023-01-24 08:17:09.133526: step: 1012/526, loss: 0.026647118851542473
2023-01-24 08:17:10.226464: step: 1016/526, loss: 0.004543284419924021
2023-01-24 08:17:11.296959: step: 1020/526, loss: 3.2825851121742744e-06
2023-01-24 08:17:12.359862: step: 1024/526, loss: 0.0040977406315505505
2023-01-24 08:17:13.453365: step: 1028/526, loss: 0.005318142008036375
2023-01-24 08:17:14.528448: step: 1032/526, loss: 4.423849532031454e-05
2023-01-24 08:17:15.598624: step: 1036/526, loss: 0.00011153249943163246
2023-01-24 08:17:16.674973: step: 1040/526, loss: 0.006767992861568928
2023-01-24 08:17:17.748127: step: 1044/526, loss: 0.004334311932325363
2023-01-24 08:17:18.822155: step: 1048/526, loss: 0.0030721663497388363
2023-01-24 08:17:19.884656: step: 1052/526, loss: 0.0003806806926149875
2023-01-24 08:17:20.954676: step: 1056/526, loss: 0.008242100477218628
2023-01-24 08:17:22.020567: step: 1060/526, loss: 0.0037150925491005182
2023-01-24 08:17:23.081625: step: 1064/526, loss: 0.0025621983222663403
2023-01-24 08:17:24.151671: step: 1068/526, loss: 0.00516100600361824
2023-01-24 08:17:25.226277: step: 1072/526, loss: 0.0015349017921835184
2023-01-24 08:17:26.301115: step: 1076/526, loss: 0.0004905465175397694
2023-01-24 08:17:27.380412: step: 1080/526, loss: 0.005299912765622139
2023-01-24 08:17:28.435496: step: 1084/526, loss: 0.0012664188398048282
2023-01-24 08:17:29.509112: step: 1088/526, loss: 0.00358656351454556
2023-01-24 08:17:30.564373: step: 1092/526, loss: 0.023373868316411972
2023-01-24 08:17:31.637117: step: 1096/526, loss: 0.009309697896242142
2023-01-24 08:17:32.688224: step: 1100/526, loss: 0.004484089557081461
2023-01-24 08:17:33.777080: step: 1104/526, loss: 0.02947205677628517
2023-01-24 08:17:34.847713: step: 1108/526, loss: 0.002234118990600109
2023-01-24 08:17:35.910842: step: 1112/526, loss: 0.0008561440627090633
2023-01-24 08:17:36.990260: step: 1116/526, loss: 0.004330252762883902
2023-01-24 08:17:38.052472: step: 1120/526, loss: 0.0005354993045330048
2023-01-24 08:17:39.121404: step: 1124/526, loss: 0.0032475648913532495
2023-01-24 08:17:40.183649: step: 1128/526, loss: 0.008089636452496052
2023-01-24 08:17:41.240755: step: 1132/526, loss: 0.0055059525184333324
2023-01-24 08:17:42.327226: step: 1136/526, loss: 0.01154759619385004
2023-01-24 08:17:43.398686: step: 1140/526, loss: 6.383806612575427e-05
2023-01-24 08:17:44.443926: step: 1144/526, loss: 0.010982904583215714
2023-01-24 08:17:45.506098: step: 1148/526, loss: 0.00451228441670537
2023-01-24 08:17:46.579210: step: 1152/526, loss: 7.669332262594253e-06
2023-01-24 08:17:47.676011: step: 1156/526, loss: 0.0006826398312114179
2023-01-24 08:17:48.739872: step: 1160/526, loss: 0.004565628245472908
2023-01-24 08:17:49.815633: step: 1164/526, loss: 0.007722855545580387
2023-01-24 08:17:50.890385: step: 1168/526, loss: 0.0016432913253083825
2023-01-24 08:17:51.951037: step: 1172/526, loss: 2.1040261344751343e-05
2023-01-24 08:17:53.029665: step: 1176/526, loss: 0.004352714866399765
2023-01-24 08:17:54.098285: step: 1180/526, loss: 0.004593819845467806
2023-01-24 08:17:55.155212: step: 1184/526, loss: 1.4244415979192127e-05
2023-01-24 08:17:56.219579: step: 1188/526, loss: 0.002957102144137025
2023-01-24 08:17:57.281750: step: 1192/526, loss: 0.012502138502895832
2023-01-24 08:17:58.367890: step: 1196/526, loss: 0.012206131592392921
2023-01-24 08:17:59.429976: step: 1200/526, loss: 0.005621777847409248
2023-01-24 08:18:00.502160: step: 1204/526, loss: 0.0005674066487699747
2023-01-24 08:18:01.570155: step: 1208/526, loss: 0.0027566973585635424
2023-01-24 08:18:02.631115: step: 1212/526, loss: 0.009235570207238197
2023-01-24 08:18:03.708449: step: 1216/526, loss: 0.00575832137838006
2023-01-24 08:18:04.779955: step: 1220/526, loss: 0.011415249668061733
2023-01-24 08:18:05.872080: step: 1224/526, loss: 0.004225266631692648
2023-01-24 08:18:06.931609: step: 1228/526, loss: 0.007484679110348225
2023-01-24 08:18:08.013153: step: 1232/526, loss: 0.0015892009250819683
2023-01-24 08:18:09.075707: step: 1236/526, loss: 0.005136185325682163
2023-01-24 08:18:10.130121: step: 1240/526, loss: 0.003244815394282341
2023-01-24 08:18:11.186325: step: 1244/526, loss: 0.0006238819914869964
2023-01-24 08:18:12.287148: step: 1248/526, loss: 0.043548181653022766
2023-01-24 08:18:13.343374: step: 1252/526, loss: 0.0016069854609668255
2023-01-24 08:18:14.406232: step: 1256/526, loss: 0.0024691345170140266
2023-01-24 08:18:15.463827: step: 1260/526, loss: 0.00343396607786417
2023-01-24 08:18:16.518905: step: 1264/526, loss: 0.00020056105859111995
2023-01-24 08:18:17.594770: step: 1268/526, loss: 5.516166129382327e-05
2023-01-24 08:18:18.661923: step: 1272/526, loss: 0.00014844803081359714
2023-01-24 08:18:19.724245: step: 1276/526, loss: 0.012826718389987946
2023-01-24 08:18:20.787591: step: 1280/526, loss: 0.001885322853922844
2023-01-24 08:18:21.851594: step: 1284/526, loss: 0.01198611967265606
2023-01-24 08:18:22.936404: step: 1288/526, loss: 0.0013885529479011893
2023-01-24 08:18:24.008607: step: 1292/526, loss: 0.012700226157903671
2023-01-24 08:18:25.071644: step: 1296/526, loss: 6.615779966523405e-06
2023-01-24 08:18:26.126969: step: 1300/526, loss: 0.0020006364211440086
2023-01-24 08:18:27.182253: step: 1304/526, loss: 0.010526680387556553
2023-01-24 08:18:28.244516: step: 1308/526, loss: 0.01219138316810131
2023-01-24 08:18:29.314243: step: 1312/526, loss: 0.0016996189951896667
2023-01-24 08:18:30.386112: step: 1316/526, loss: 0.0021444889716804028
2023-01-24 08:18:31.467497: step: 1320/526, loss: 0.0048052906058728695
2023-01-24 08:18:32.539081: step: 1324/526, loss: 0.00048242032062262297
2023-01-24 08:18:33.609868: step: 1328/526, loss: 0.004876694642007351
2023-01-24 08:18:34.670691: step: 1332/526, loss: 0.0002365312830079347
2023-01-24 08:18:35.752906: step: 1336/526, loss: 0.0013371994718909264
2023-01-24 08:18:36.804578: step: 1340/526, loss: 0.0025196231435984373
2023-01-24 08:18:37.887913: step: 1344/526, loss: 0.029093828052282333
2023-01-24 08:18:38.972154: step: 1348/526, loss: 0.00916947703808546
2023-01-24 08:18:40.038399: step: 1352/526, loss: 0.001004858990199864
2023-01-24 08:18:41.116330: step: 1356/526, loss: 0.010506617836654186
2023-01-24 08:18:42.185961: step: 1360/526, loss: 0.001510967849753797
2023-01-24 08:18:43.260502: step: 1364/526, loss: 0.0021811414044350386
2023-01-24 08:18:44.321249: step: 1368/526, loss: 0.007610586006194353
2023-01-24 08:18:45.392825: step: 1372/526, loss: 0.0058801425620913506
2023-01-24 08:18:46.457317: step: 1376/526, loss: 0.008549570105969906
2023-01-24 08:18:47.517201: step: 1380/526, loss: 0.003672333201393485
2023-01-24 08:18:48.580319: step: 1384/526, loss: 0.009058075025677681
2023-01-24 08:18:49.674937: step: 1388/526, loss: 0.006501309107989073
2023-01-24 08:18:50.745019: step: 1392/526, loss: 0.007007825654000044
2023-01-24 08:18:51.816094: step: 1396/526, loss: 0.007669099606573582
2023-01-24 08:18:52.872554: step: 1400/526, loss: 8.381891802855534e-08
2023-01-24 08:18:53.962786: step: 1404/526, loss: 0.005447391886264086
2023-01-24 08:18:55.038884: step: 1408/526, loss: 0.00405966117978096
2023-01-24 08:18:56.102092: step: 1412/526, loss: 0.0013689192710444331
2023-01-24 08:18:57.157209: step: 1416/526, loss: 0.0015988851664587855
2023-01-24 08:18:58.217744: step: 1420/526, loss: 0.015160990878939629
2023-01-24 08:18:59.296790: step: 1424/526, loss: 0.000712490756995976
2023-01-24 08:19:00.390451: step: 1428/526, loss: 0.0020193003583699465
2023-01-24 08:19:01.460433: step: 1432/526, loss: 0.005865667946636677
2023-01-24 08:19:02.526527: step: 1436/526, loss: 0.0017918252851814032
2023-01-24 08:19:03.615681: step: 1440/526, loss: 0.0035313840489834547
2023-01-24 08:19:04.687778: step: 1444/526, loss: 0.0026456057094037533
2023-01-24 08:19:05.747845: step: 1448/526, loss: 0.003913404885679483
2023-01-24 08:19:06.819637: step: 1452/526, loss: 0.00258021242916584
2023-01-24 08:19:07.891685: step: 1456/526, loss: 0.0009279975784011185
2023-01-24 08:19:08.950593: step: 1460/526, loss: 2.5730187189765275e-05
2023-01-24 08:19:10.021228: step: 1464/526, loss: 0.00010479407501406968
2023-01-24 08:19:11.079568: step: 1468/526, loss: 0.0012222465593367815
2023-01-24 08:19:12.138788: step: 1472/526, loss: 0.010760725475847721
2023-01-24 08:19:13.195551: step: 1476/526, loss: 0.0032381017226725817
2023-01-24 08:19:14.260346: step: 1480/526, loss: 0.003977091982960701
2023-01-24 08:19:15.327462: step: 1484/526, loss: 0.006333249621093273
2023-01-24 08:19:16.401508: step: 1488/526, loss: 0.0033643092028796673
2023-01-24 08:19:17.460341: step: 1492/526, loss: 0.0012857952388003469
2023-01-24 08:19:18.530550: step: 1496/526, loss: 0.0041739000007510185
2023-01-24 08:19:19.582702: step: 1500/526, loss: 0.002837817184627056
2023-01-24 08:19:20.656572: step: 1504/526, loss: 0.101455919444561
2023-01-24 08:19:21.739578: step: 1508/526, loss: 0.006391642615199089
2023-01-24 08:19:22.820433: step: 1512/526, loss: 0.011850404553115368
2023-01-24 08:19:23.876022: step: 1516/526, loss: 0.00957333855330944
2023-01-24 08:19:24.924318: step: 1520/526, loss: 0.0016149585135281086
2023-01-24 08:19:25.982555: step: 1524/526, loss: 0.010195809416472912
2023-01-24 08:19:27.073361: step: 1528/526, loss: 0.001148558920249343
2023-01-24 08:19:28.145170: step: 1532/526, loss: 0.007005386985838413
2023-01-24 08:19:29.222761: step: 1536/526, loss: 0.006135713774710894
2023-01-24 08:19:30.282809: step: 1540/526, loss: 0.004064920358359814
2023-01-24 08:19:31.333315: step: 1544/526, loss: 0.0025080936029553413
2023-01-24 08:19:32.402892: step: 1548/526, loss: 0.008785512298345566
2023-01-24 08:19:33.475305: step: 1552/526, loss: 0.002307741204276681
2023-01-24 08:19:34.555222: step: 1556/526, loss: 0.004109462723135948
2023-01-24 08:19:35.623329: step: 1560/526, loss: 0.006284110248088837
2023-01-24 08:19:36.715941: step: 1564/526, loss: 0.021242180839180946
2023-01-24 08:19:37.797121: step: 1568/526, loss: 0.00031133886659517884
2023-01-24 08:19:38.871460: step: 1572/526, loss: 0.007188607472926378
2023-01-24 08:19:39.939984: step: 1576/526, loss: 0.0045284247025847435
2023-01-24 08:19:40.994273: step: 1580/526, loss: 0.025905510410666466
2023-01-24 08:19:42.072533: step: 1584/526, loss: 0.006384619511663914
2023-01-24 08:19:43.147075: step: 1588/526, loss: 0.002577879000455141
2023-01-24 08:19:44.209789: step: 1592/526, loss: 0.005117006134241819
2023-01-24 08:19:45.280526: step: 1596/526, loss: 0.0030828595627099276
2023-01-24 08:19:46.347527: step: 1600/526, loss: 0.0005668936646543443
2023-01-24 08:19:47.415989: step: 1604/526, loss: 0.008498278446495533
2023-01-24 08:19:48.478661: step: 1608/526, loss: 0.0005774215096607804
2023-01-24 08:19:49.561202: step: 1612/526, loss: 0.004483935888856649
2023-01-24 08:19:50.636815: step: 1616/526, loss: 0.013668697327375412
2023-01-24 08:19:51.695704: step: 1620/526, loss: 0.0028071808628737926
2023-01-24 08:19:52.759140: step: 1624/526, loss: 0.00044962106039747596
2023-01-24 08:19:53.821750: step: 1628/526, loss: 0.0017513372004032135
2023-01-24 08:19:54.895328: step: 1632/526, loss: 0.00021313379693310708
2023-01-24 08:19:55.969130: step: 1636/526, loss: 0.004358714912086725
2023-01-24 08:19:57.034399: step: 1640/526, loss: 0.003260429948568344
2023-01-24 08:19:58.119008: step: 1644/526, loss: 0.010220948606729507
2023-01-24 08:19:59.189819: step: 1648/526, loss: 0.003521028673276305
2023-01-24 08:20:00.256199: step: 1652/526, loss: 0.004618900362402201
2023-01-24 08:20:01.326817: step: 1656/526, loss: 0.006055415607988834
2023-01-24 08:20:02.397467: step: 1660/526, loss: 0.0022699935361742973
2023-01-24 08:20:03.484724: step: 1664/526, loss: 0.0019782076124101877
2023-01-24 08:20:04.552642: step: 1668/526, loss: 0.0008403612300753593
2023-01-24 08:20:05.613681: step: 1672/526, loss: 0.010374226607382298
2023-01-24 08:20:06.682403: step: 1676/526, loss: 0.013295567594468594
2023-01-24 08:20:07.736861: step: 1680/526, loss: 0.0026011704467236996
2023-01-24 08:20:08.822897: step: 1684/526, loss: 0.022898836061358452
2023-01-24 08:20:09.881605: step: 1688/526, loss: 0.0145388413220644
2023-01-24 08:20:10.969879: step: 1692/526, loss: 0.0014042035909369588
2023-01-24 08:20:12.028328: step: 1696/526, loss: 0.0037161032669246197
2023-01-24 08:20:13.098938: step: 1700/526, loss: 0.011581058613955975
2023-01-24 08:20:14.207284: step: 1704/526, loss: 0.008050082251429558
2023-01-24 08:20:15.275260: step: 1708/526, loss: 0.001337134512141347
2023-01-24 08:20:16.347573: step: 1712/526, loss: 0.0012007122859358788
2023-01-24 08:20:17.439381: step: 1716/526, loss: 0.0028656721115112305
2023-01-24 08:20:18.513360: step: 1720/526, loss: 0.0032513882033526897
2023-01-24 08:20:19.585611: step: 1724/526, loss: 0.004646581131964922
2023-01-24 08:20:20.661880: step: 1728/526, loss: 0.001016543130390346
2023-01-24 08:20:21.726047: step: 1732/526, loss: 0.0004443769867066294
2023-01-24 08:20:22.785860: step: 1736/526, loss: 0.003729267744347453
2023-01-24 08:20:23.854130: step: 1740/526, loss: 0.0011827360140159726
2023-01-24 08:20:24.933265: step: 1744/526, loss: 0.00376526964828372
2023-01-24 08:20:26.010101: step: 1748/526, loss: 0.01286687608808279
2023-01-24 08:20:27.066130: step: 1752/526, loss: 0.0014182575978338718
2023-01-24 08:20:28.134273: step: 1756/526, loss: 0.00057150365319103
2023-01-24 08:20:29.195813: step: 1760/526, loss: 0.011356213130056858
2023-01-24 08:20:30.252203: step: 1764/526, loss: 0.0033282830845564604
2023-01-24 08:20:31.332649: step: 1768/526, loss: 0.0003513133560772985
2023-01-24 08:20:32.409261: step: 1772/526, loss: 3.9954767999006435e-05
2023-01-24 08:20:33.472008: step: 1776/526, loss: 0.0029689716175198555
2023-01-24 08:20:34.536663: step: 1780/526, loss: 0.001050980412401259
2023-01-24 08:20:35.607366: step: 1784/526, loss: 0.0033109993673861027
2023-01-24 08:20:36.680359: step: 1788/526, loss: 0.0029314623679965734
2023-01-24 08:20:37.739427: step: 1792/526, loss: 0.01881171576678753
2023-01-24 08:20:38.802631: step: 1796/526, loss: 0.0016048286342993379
2023-01-24 08:20:39.879420: step: 1800/526, loss: 0.00024121090245898813
2023-01-24 08:20:40.952249: step: 1804/526, loss: 0.010174653492867947
2023-01-24 08:20:42.030935: step: 1808/526, loss: 0.011384622193872929
2023-01-24 08:20:43.090801: step: 1812/526, loss: 0.00020782684441655874
2023-01-24 08:20:44.155648: step: 1816/526, loss: 0.0058898888528347015
2023-01-24 08:20:45.224793: step: 1820/526, loss: 0.0040581803768873215
2023-01-24 08:20:46.287265: step: 1824/526, loss: 0.0041685886681079865
2023-01-24 08:20:47.344642: step: 1828/526, loss: 0.0007716206018812954
2023-01-24 08:20:48.423329: step: 1832/526, loss: 0.00015300473023671657
2023-01-24 08:20:49.501009: step: 1836/526, loss: 0.006592265330255032
2023-01-24 08:20:50.586509: step: 1840/526, loss: 0.011776725761592388
2023-01-24 08:20:51.673883: step: 1844/526, loss: 0.018989983946084976
2023-01-24 08:20:52.742753: step: 1848/526, loss: 0.0064499578438699245
2023-01-24 08:20:53.811031: step: 1852/526, loss: 0.0008649341762065887
2023-01-24 08:20:54.873645: step: 1856/526, loss: 0.0003299264644738287
2023-01-24 08:20:55.941916: step: 1860/526, loss: 7.778425242577214e-06
2023-01-24 08:20:57.002010: step: 1864/526, loss: 1.5760853784740902e-05
2023-01-24 08:20:58.080267: step: 1868/526, loss: 0.01908731460571289
2023-01-24 08:20:59.154396: step: 1872/526, loss: 0.0025268851313740015
2023-01-24 08:21:00.237118: step: 1876/526, loss: 0.0
2023-01-24 08:21:01.306359: step: 1880/526, loss: 0.007457737345248461
2023-01-24 08:21:02.372290: step: 1884/526, loss: 0.009490340948104858
2023-01-24 08:21:03.461599: step: 1888/526, loss: 0.004845378454774618
2023-01-24 08:21:04.531471: step: 1892/526, loss: 0.0028228999581187963
2023-01-24 08:21:05.593155: step: 1896/526, loss: 0.0077581084333360195
2023-01-24 08:21:06.658982: step: 1900/526, loss: 0.003925779834389687
2023-01-24 08:21:07.735305: step: 1904/526, loss: 0.002297257073223591
2023-01-24 08:21:08.804429: step: 1908/526, loss: 0.012945166788995266
2023-01-24 08:21:09.909068: step: 1912/526, loss: 0.03262411803007126
2023-01-24 08:21:10.988918: step: 1916/526, loss: 0.00223451666533947
2023-01-24 08:21:12.057609: step: 1920/526, loss: 0.003882618388161063
2023-01-24 08:21:13.151469: step: 1924/526, loss: 0.0033083721064031124
2023-01-24 08:21:14.238880: step: 1928/526, loss: 0.0044806464575231075
2023-01-24 08:21:15.338451: step: 1932/526, loss: 0.015671787783503532
2023-01-24 08:21:16.418658: step: 1936/526, loss: 0.00082369614392519
2023-01-24 08:21:17.485974: step: 1940/526, loss: 0.005413532257080078
2023-01-24 08:21:18.548973: step: 1944/526, loss: 2.8437520086299628e-05
2023-01-24 08:21:19.617585: step: 1948/526, loss: 0.02288207970559597
2023-01-24 08:21:20.687632: step: 1952/526, loss: 0.0006015666294842958
2023-01-24 08:21:21.743508: step: 1956/526, loss: 0.002368087647482753
2023-01-24 08:21:22.829649: step: 1960/526, loss: 0.0009501436143182218
2023-01-24 08:21:23.905029: step: 1964/526, loss: 0.005070342216640711
2023-01-24 08:21:24.970914: step: 1968/526, loss: 0.0077898805029690266
2023-01-24 08:21:26.074350: step: 1972/526, loss: 0.0027656888123601675
2023-01-24 08:21:27.146228: step: 1976/526, loss: 0.0021161020267754793
2023-01-24 08:21:28.214817: step: 1980/526, loss: 0.0005242753541097045
2023-01-24 08:21:29.308980: step: 1984/526, loss: 6.239534968699445e-07
2023-01-24 08:21:30.378377: step: 1988/526, loss: 0.007229828275740147
2023-01-24 08:21:31.454333: step: 1992/526, loss: 0.034025538712739944
2023-01-24 08:21:32.553556: step: 1996/526, loss: 0.019669758155941963
2023-01-24 08:21:33.626306: step: 2000/526, loss: 0.002099134959280491
2023-01-24 08:21:34.697129: step: 2004/526, loss: 0.00038834975566715
2023-01-24 08:21:35.776642: step: 2008/526, loss: 0.002441603457555175
2023-01-24 08:21:36.843349: step: 2012/526, loss: 0.0048280274495482445
2023-01-24 08:21:37.920486: step: 2016/526, loss: 0.013527227565646172
2023-01-24 08:21:38.983502: step: 2020/526, loss: 0.003949955105781555
2023-01-24 08:21:40.059668: step: 2024/526, loss: 4.812977203982882e-05
2023-01-24 08:21:41.117478: step: 2028/526, loss: 0.002293851226568222
2023-01-24 08:21:42.196602: step: 2032/526, loss: 0.003258189419284463
2023-01-24 08:21:43.294713: step: 2036/526, loss: 0.0047264802269637585
2023-01-24 08:21:44.388653: step: 2040/526, loss: 0.00121023238170892
2023-01-24 08:21:45.457297: step: 2044/526, loss: 0.004911414347589016
2023-01-24 08:21:46.517839: step: 2048/526, loss: 0.0007358885486610234
2023-01-24 08:21:47.582754: step: 2052/526, loss: 0.009156769141554832
2023-01-24 08:21:48.671519: step: 2056/526, loss: 0.003198770107701421
2023-01-24 08:21:49.745657: step: 2060/526, loss: 0.02316271699965
2023-01-24 08:21:50.807994: step: 2064/526, loss: 0.0004598215455189347
2023-01-24 08:21:51.866407: step: 2068/526, loss: 0.0014651265228167176
2023-01-24 08:21:52.943519: step: 2072/526, loss: 0.01609884202480316
2023-01-24 08:21:54.028706: step: 2076/526, loss: 0.007467396557331085
2023-01-24 08:21:55.109732: step: 2080/526, loss: 0.008745291270315647
2023-01-24 08:21:56.173552: step: 2084/526, loss: 0.0014709733659401536
2023-01-24 08:21:57.252661: step: 2088/526, loss: 0.0023643779568374157
2023-01-24 08:21:58.314271: step: 2092/526, loss: 0.01048876903951168
2023-01-24 08:21:59.370389: step: 2096/526, loss: 0.0013966734986752272
2023-01-24 08:22:00.439411: step: 2100/526, loss: 0.010592360980808735
2023-01-24 08:22:01.505498: step: 2104/526, loss: 0.014253076165914536
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37004849528643946, 'r': 0.2766586473298997, 'f1': 0.31661043896385915}, 'combined': 0.23329190239442252, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35449932516611293, 'r': 0.223143216572997, 'f1': 0.2738860591962782}, 'combined': 0.14939239592524264, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33826391059706157, 'r': 0.29333322038492815, 'f1': 0.31420042102206736}, 'combined': 0.23151609970047066, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3558362251418577, 'r': 0.2588195782138855, 'f1': 0.2996713972328145}, 'combined': 0.16345712576335336, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3640122819100092, 'r': 0.31911513138979936, 'f1': 0.3400883200049024}, 'combined': 0.2505913936878228, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.363052706070494, 'r': 0.2773549950309812, 'f1': 0.314469926938654}, 'combined': 0.17152905105744762, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 08:24:47.071916: step: 4/526, loss: 0.00031437506549991667
2023-01-24 08:24:48.139597: step: 8/526, loss: 0.000721877790056169
2023-01-24 08:24:49.219410: step: 12/526, loss: 0.0002992902009282261
2023-01-24 08:24:50.279696: step: 16/526, loss: 0.001107602845877409
2023-01-24 08:24:51.340033: step: 20/526, loss: 0.005010148044675589
2023-01-24 08:24:52.387008: step: 24/526, loss: 0.0013369632652029395
2023-01-24 08:24:53.457891: step: 28/526, loss: 0.005854390095919371
2023-01-24 08:24:54.516772: step: 32/526, loss: 0.0010378245497122407
2023-01-24 08:24:55.574737: step: 36/526, loss: 0.005830280017107725
2023-01-24 08:24:56.626980: step: 40/526, loss: 0.004884921479970217
2023-01-24 08:24:57.678644: step: 44/526, loss: 0.0001447704853489995
2023-01-24 08:24:58.744822: step: 48/526, loss: 0.0011601501610130072
2023-01-24 08:24:59.807803: step: 52/526, loss: 0.00152221426833421
2023-01-24 08:25:00.868752: step: 56/526, loss: 0.0020156328100711107
2023-01-24 08:25:01.921523: step: 60/526, loss: 1.1011295100615826e-05
2023-01-24 08:25:02.980911: step: 64/526, loss: 0.001265243161469698
2023-01-24 08:25:04.036929: step: 68/526, loss: 0.0
2023-01-24 08:25:05.105011: step: 72/526, loss: 0.0005425070412456989
2023-01-24 08:25:06.171074: step: 76/526, loss: 0.0013437970774248242
2023-01-24 08:25:07.239193: step: 80/526, loss: 0.004624505992978811
2023-01-24 08:25:08.300351: step: 84/526, loss: 0.00032763893250375986
2023-01-24 08:25:09.365090: step: 88/526, loss: 0.0016169139416888356
2023-01-24 08:25:10.433200: step: 92/526, loss: 0.0037228604778647423
2023-01-24 08:25:11.499990: step: 96/526, loss: 0.01544990111142397
2023-01-24 08:25:12.549182: step: 100/526, loss: 0.0019161321688443422
2023-01-24 08:25:13.634323: step: 104/526, loss: 0.007739551831036806
2023-01-24 08:25:14.695020: step: 108/526, loss: 0.0033388000447303057
2023-01-24 08:25:15.753582: step: 112/526, loss: 0.005482289008796215
2023-01-24 08:25:16.808707: step: 116/526, loss: 0.016631007194519043
2023-01-24 08:25:17.887856: step: 120/526, loss: 0.0017945574363693595
2023-01-24 08:25:18.948902: step: 124/526, loss: 0.008565624244511127
2023-01-24 08:25:20.010970: step: 128/526, loss: 0.001546542509458959
2023-01-24 08:25:21.083092: step: 132/526, loss: 0.0070532034151256084
2023-01-24 08:25:22.140620: step: 136/526, loss: 0.004942536354064941
2023-01-24 08:25:23.201076: step: 140/526, loss: 0.00022651706240139902
2023-01-24 08:25:24.281661: step: 144/526, loss: 0.0015404631849378347
2023-01-24 08:25:25.328965: step: 148/526, loss: 0.004854219034314156
2023-01-24 08:25:26.403859: step: 152/526, loss: 0.004633516073226929
2023-01-24 08:25:27.471991: step: 156/526, loss: 0.0013367460342124104
2023-01-24 08:25:28.511958: step: 160/526, loss: 0.0004760772571898997
2023-01-24 08:25:29.567209: step: 164/526, loss: 0.00910631287842989
2023-01-24 08:25:30.634385: step: 168/526, loss: 0.034501541405916214
2023-01-24 08:25:31.691907: step: 172/526, loss: 0.0021336048375815153
2023-01-24 08:25:32.755273: step: 176/526, loss: 0.000841932778712362
2023-01-24 08:25:33.815301: step: 180/526, loss: 0.0013022262137383223
2023-01-24 08:25:34.889948: step: 184/526, loss: 0.006308686453849077
2023-01-24 08:25:35.947446: step: 188/526, loss: 0.0015304558910429478
2023-01-24 08:25:37.020324: step: 192/526, loss: 0.0014959670370444655
2023-01-24 08:25:38.071361: step: 196/526, loss: 0.004925600253045559
2023-01-24 08:25:39.144990: step: 200/526, loss: 0.0009841794380918145
2023-01-24 08:25:40.209162: step: 204/526, loss: 0.0014439214719459414
2023-01-24 08:25:41.267458: step: 208/526, loss: 0.002681492827832699
2023-01-24 08:25:42.324809: step: 212/526, loss: 0.0010890221456065774
2023-01-24 08:25:43.398286: step: 216/526, loss: 0.003575438866391778
2023-01-24 08:25:44.472415: step: 220/526, loss: 0.0075643728487193584
2023-01-24 08:25:45.549843: step: 224/526, loss: 0.00011623015598161146
2023-01-24 08:25:46.620685: step: 228/526, loss: 0.007574285846203566
2023-01-24 08:25:47.673481: step: 232/526, loss: 0.002350882161408663
2023-01-24 08:25:48.734790: step: 236/526, loss: 0.006298688240349293
2023-01-24 08:25:49.800361: step: 240/526, loss: 0.001984883565455675
2023-01-24 08:25:50.846189: step: 244/526, loss: 0.0012347263982519507
2023-01-24 08:25:51.913409: step: 248/526, loss: 0.0029861200600862503
2023-01-24 08:25:52.991763: step: 252/526, loss: 0.013707672245800495
2023-01-24 08:25:54.057119: step: 256/526, loss: 0.0027485175523906946
2023-01-24 08:25:55.119998: step: 260/526, loss: 0.007076349575072527
2023-01-24 08:25:56.189139: step: 264/526, loss: 0.0007557463250122964
2023-01-24 08:25:57.258643: step: 268/526, loss: 0.0018420928390696645
2023-01-24 08:25:58.309710: step: 272/526, loss: 0.004124253056943417
2023-01-24 08:25:59.384788: step: 276/526, loss: 0.00149305141530931
2023-01-24 08:26:00.436815: step: 280/526, loss: 0.10160735249519348
2023-01-24 08:26:01.488011: step: 284/526, loss: 0.03166588023304939
2023-01-24 08:26:02.554423: step: 288/526, loss: 0.014715251512825489
2023-01-24 08:26:03.616771: step: 292/526, loss: 0.006889783311635256
2023-01-24 08:26:04.701100: step: 296/526, loss: 0.001305997371673584
2023-01-24 08:26:05.767479: step: 300/526, loss: 0.0012758137891069055
2023-01-24 08:26:06.855310: step: 304/526, loss: 0.0001605924335308373
2023-01-24 08:26:07.930810: step: 308/526, loss: 0.003369224490597844
2023-01-24 08:26:08.992177: step: 312/526, loss: 0.00020925667195115238
2023-01-24 08:26:10.048403: step: 316/526, loss: 0.009680021554231644
2023-01-24 08:26:11.105846: step: 320/526, loss: 0.008730200119316578
2023-01-24 08:26:12.160526: step: 324/526, loss: 0.010040685534477234
2023-01-24 08:26:13.232961: step: 328/526, loss: 0.0019895322620868683
2023-01-24 08:26:14.288822: step: 332/526, loss: 0.0005051528569310904
2023-01-24 08:26:15.351329: step: 336/526, loss: 0.003201629500836134
2023-01-24 08:26:16.412094: step: 340/526, loss: 0.005166755057871342
2023-01-24 08:26:17.467682: step: 344/526, loss: 0.0031377023551613092
2023-01-24 08:26:18.537933: step: 348/526, loss: 7.840106263756752e-05
2023-01-24 08:26:19.609177: step: 352/526, loss: 0.001754283206537366
2023-01-24 08:26:20.674587: step: 356/526, loss: 0.0007279195706360042
2023-01-24 08:26:21.731769: step: 360/526, loss: 0.013939459808170795
2023-01-24 08:26:22.795954: step: 364/526, loss: 0.009014920331537724
2023-01-24 08:26:23.847090: step: 368/526, loss: 0.004237246233969927
2023-01-24 08:26:24.911876: step: 372/526, loss: 0.0013433074345812201
2023-01-24 08:26:25.972818: step: 376/526, loss: 0.0005890174070373178
2023-01-24 08:26:27.039388: step: 380/526, loss: 0.003365324577316642
2023-01-24 08:26:28.095947: step: 384/526, loss: 0.0010860550682991743
2023-01-24 08:26:29.169418: step: 388/526, loss: 0.009376972913742065
2023-01-24 08:26:30.237278: step: 392/526, loss: 0.004481134936213493
2023-01-24 08:26:31.323927: step: 396/526, loss: 0.002291429089382291
2023-01-24 08:26:32.385390: step: 400/526, loss: 0.0002782550291158259
2023-01-24 08:26:33.475590: step: 404/526, loss: 0.0035371528938412666
2023-01-24 08:26:34.533385: step: 408/526, loss: 0.0007806267822161317
2023-01-24 08:26:35.587492: step: 412/526, loss: 0.0005052492488175631
2023-01-24 08:26:36.660444: step: 416/526, loss: 0.0021530049853026867
2023-01-24 08:26:37.724289: step: 420/526, loss: 0.023135367780923843
2023-01-24 08:26:38.792662: step: 424/526, loss: 0.002787533914670348
2023-01-24 08:26:39.851430: step: 428/526, loss: 0.010927122086286545
2023-01-24 08:26:40.918009: step: 432/526, loss: 0.002425807761028409
2023-01-24 08:26:41.979007: step: 436/526, loss: 0.004753129091113806
2023-01-24 08:26:43.065792: step: 440/526, loss: 5.0614195060916245e-05
2023-01-24 08:26:44.130108: step: 444/526, loss: 0.005468595307320356
2023-01-24 08:26:45.193984: step: 448/526, loss: 0.02075253054499626
2023-01-24 08:26:46.263045: step: 452/526, loss: 0.0013232381315901875
2023-01-24 08:26:47.332166: step: 456/526, loss: 0.004991380963474512
2023-01-24 08:26:48.409409: step: 460/526, loss: 0.01074813213199377
2023-01-24 08:26:49.494159: step: 464/526, loss: 0.0038094213232398033
2023-01-24 08:26:50.579511: step: 468/526, loss: 0.00588549580425024
2023-01-24 08:26:51.650068: step: 472/526, loss: 0.009350107982754707
2023-01-24 08:26:52.709789: step: 476/526, loss: 0.001876753056421876
2023-01-24 08:26:53.769064: step: 480/526, loss: 0.005339787341654301
2023-01-24 08:26:54.854941: step: 484/526, loss: 0.00220359954982996
2023-01-24 08:26:55.916686: step: 488/526, loss: 0.0006181065109558403
2023-01-24 08:26:56.977160: step: 492/526, loss: 0.002066671848297119
2023-01-24 08:26:58.025232: step: 496/526, loss: 0.011612337082624435
2023-01-24 08:26:59.086052: step: 500/526, loss: 8.063924906309694e-05
2023-01-24 08:27:00.152553: step: 504/526, loss: 0.007404741831123829
2023-01-24 08:27:01.209647: step: 508/526, loss: 0.009839549660682678
2023-01-24 08:27:02.252561: step: 512/526, loss: 0.004122963175177574
2023-01-24 08:27:03.334389: step: 516/526, loss: 0.0015515643171966076
2023-01-24 08:27:04.392507: step: 520/526, loss: 0.004361818544566631
2023-01-24 08:27:05.464522: step: 524/526, loss: 8.91040253918618e-05
2023-01-24 08:27:06.538505: step: 528/526, loss: 0.0017529523465782404
2023-01-24 08:27:07.605648: step: 532/526, loss: 0.006028460338711739
2023-01-24 08:27:08.664374: step: 536/526, loss: 0.001939959591254592
2023-01-24 08:27:09.730220: step: 540/526, loss: 0.004281359259039164
2023-01-24 08:27:10.789677: step: 544/526, loss: 0.017347289249300957
2023-01-24 08:27:11.843783: step: 548/526, loss: 0.0016728440532460809
2023-01-24 08:27:12.904844: step: 552/526, loss: 0.0009446667972952127
2023-01-24 08:27:13.960026: step: 556/526, loss: 0.025606101378798485
2023-01-24 08:27:15.025054: step: 560/526, loss: 0.00013952061999589205
2023-01-24 08:27:16.087664: step: 564/526, loss: 0.0009214154561050236
2023-01-24 08:27:17.148329: step: 568/526, loss: 0.0031211338937282562
2023-01-24 08:27:18.207661: step: 572/526, loss: 0.0005275773000903428
2023-01-24 08:27:19.262815: step: 576/526, loss: 0.004554534796625376
2023-01-24 08:27:20.332194: step: 580/526, loss: 0.004487162921577692
2023-01-24 08:27:21.402883: step: 584/526, loss: 0.013655285350978374
2023-01-24 08:27:22.480492: step: 588/526, loss: 0.005994296167045832
2023-01-24 08:27:23.558685: step: 592/526, loss: 0.0005603848258033395
2023-01-24 08:27:24.641291: step: 596/526, loss: 0.0005197998252697289
2023-01-24 08:27:25.735901: step: 600/526, loss: 0.002649688394740224
2023-01-24 08:27:26.805425: step: 604/526, loss: 0.0013523525558412075
2023-01-24 08:27:27.861156: step: 608/526, loss: 0.004355909768491983
2023-01-24 08:27:28.930881: step: 612/526, loss: 0.0036479176487773657
2023-01-24 08:27:29.988411: step: 616/526, loss: 0.00855250284075737
2023-01-24 08:27:31.058851: step: 620/526, loss: 0.010242723859846592
2023-01-24 08:27:32.112363: step: 624/526, loss: 0.006170874927192926
2023-01-24 08:27:33.165378: step: 628/526, loss: 0.001439704792574048
2023-01-24 08:27:34.234621: step: 632/526, loss: 0.002179022179916501
2023-01-24 08:27:35.318515: step: 636/526, loss: 0.004114803392440081
2023-01-24 08:27:36.390493: step: 640/526, loss: 0.009873596020042896
2023-01-24 08:27:37.455904: step: 644/526, loss: 0.0020701757166534662
2023-01-24 08:27:38.522269: step: 648/526, loss: 0.007152346428483725
2023-01-24 08:27:39.601880: step: 652/526, loss: 0.002764208009466529
2023-01-24 08:27:40.678266: step: 656/526, loss: 0.0021466331090778112
2023-01-24 08:27:41.748018: step: 660/526, loss: 0.0025273330975323915
2023-01-24 08:27:42.842677: step: 664/526, loss: 0.0004839191387873143
2023-01-24 08:27:43.882166: step: 668/526, loss: 0.0001491934817750007
2023-01-24 08:27:44.944345: step: 672/526, loss: 5.0661230488913134e-05
2023-01-24 08:27:46.016619: step: 676/526, loss: 2.291400232934393e-05
2023-01-24 08:27:47.082671: step: 680/526, loss: 0.018560536205768585
2023-01-24 08:27:48.136503: step: 684/526, loss: 0.004976227879524231
2023-01-24 08:27:49.189471: step: 688/526, loss: 0.0005298475152812898
2023-01-24 08:27:50.260625: step: 692/526, loss: 0.005328733008354902
2023-01-24 08:27:51.310683: step: 696/526, loss: 0.0026134364306926727
2023-01-24 08:27:52.361061: step: 700/526, loss: 0.008869764395058155
2023-01-24 08:27:53.434991: step: 704/526, loss: 0.005638923030346632
2023-01-24 08:27:54.500203: step: 708/526, loss: 0.003231939859688282
2023-01-24 08:27:55.569875: step: 712/526, loss: 0.0004281184228602797
2023-01-24 08:27:56.646872: step: 716/526, loss: 0.0039603570476174355
2023-01-24 08:27:57.712997: step: 720/526, loss: 0.005882779601961374
2023-01-24 08:27:58.774627: step: 724/526, loss: 0.00305167306214571
2023-01-24 08:27:59.834114: step: 728/526, loss: 0.0016637013759464025
2023-01-24 08:28:00.902340: step: 732/526, loss: 0.003287063678726554
2023-01-24 08:28:01.965792: step: 736/526, loss: 0.005487238988280296
2023-01-24 08:28:03.028318: step: 740/526, loss: 0.033265359699726105
2023-01-24 08:28:04.105109: step: 744/526, loss: 0.00586258340626955
2023-01-24 08:28:05.174540: step: 748/526, loss: 0.0032196512911468744
2023-01-24 08:28:06.225815: step: 752/526, loss: 0.010227379389107227
2023-01-24 08:28:07.297074: step: 756/526, loss: 0.0020482593681663275
2023-01-24 08:28:08.356644: step: 760/526, loss: 0.003393246093764901
2023-01-24 08:28:09.414038: step: 764/526, loss: 0.0035101633984595537
2023-01-24 08:28:10.480386: step: 768/526, loss: 0.006472909357398748
2023-01-24 08:28:11.544578: step: 772/526, loss: 0.0054479134269058704
2023-01-24 08:28:12.609788: step: 776/526, loss: 2.027765958700911e-06
2023-01-24 08:28:13.661926: step: 780/526, loss: 0.00970985647290945
2023-01-24 08:28:14.731224: step: 784/526, loss: 0.0011454956838861108
2023-01-24 08:28:15.781929: step: 788/526, loss: 0.0006247623823583126
2023-01-24 08:28:16.849101: step: 792/526, loss: 0.0010254670633003116
2023-01-24 08:28:17.923755: step: 796/526, loss: 0.02520628832280636
2023-01-24 08:28:18.990911: step: 800/526, loss: 0.0014865443808957934
2023-01-24 08:28:20.072414: step: 804/526, loss: 0.0014674272388219833
2023-01-24 08:28:21.131957: step: 808/526, loss: 0.007118089124560356
2023-01-24 08:28:22.191075: step: 812/526, loss: 0.00023000827059149742
2023-01-24 08:28:23.253525: step: 816/526, loss: 0.007735084742307663
2023-01-24 08:28:24.318738: step: 820/526, loss: 0.0023086194414645433
2023-01-24 08:28:25.369914: step: 824/526, loss: 0.004207658115774393
2023-01-24 08:28:26.437382: step: 828/526, loss: 0.002537284279242158
2023-01-24 08:28:27.520596: step: 832/526, loss: 0.002568707102909684
2023-01-24 08:28:28.585020: step: 836/526, loss: 0.005868341773748398
2023-01-24 08:28:29.654179: step: 840/526, loss: 0.0009080182062461972
2023-01-24 08:28:30.715968: step: 844/526, loss: 0.008289956487715244
2023-01-24 08:28:31.787761: step: 848/526, loss: 0.0021764319390058517
2023-01-24 08:28:32.871635: step: 852/526, loss: 0.007497809827327728
2023-01-24 08:28:33.930147: step: 856/526, loss: 0.0034732576459646225
2023-01-24 08:28:34.997763: step: 860/526, loss: 0.00010057733015855774
2023-01-24 08:28:36.065692: step: 864/526, loss: 0.0005223654443398118
2023-01-24 08:28:37.147414: step: 868/526, loss: 0.0010158532531931996
2023-01-24 08:28:38.223416: step: 872/526, loss: 0.0003555673756636679
2023-01-24 08:28:39.275860: step: 876/526, loss: 0.01709245890378952
2023-01-24 08:28:40.353653: step: 880/526, loss: 0.0021394919604063034
2023-01-24 08:28:41.420146: step: 884/526, loss: 0.007290750741958618
2023-01-24 08:28:42.484564: step: 888/526, loss: 0.001117272418923676
2023-01-24 08:28:43.560948: step: 892/526, loss: 0.005706317722797394
2023-01-24 08:28:44.620469: step: 896/526, loss: 0.0005349827115423977
2023-01-24 08:28:45.703430: step: 900/526, loss: 0.0011702262563630939
2023-01-24 08:28:46.787394: step: 904/526, loss: 0.008477872237563133
2023-01-24 08:28:47.856507: step: 908/526, loss: 0.0004924589302390814
2023-01-24 08:28:48.930751: step: 912/526, loss: 0.003951834514737129
2023-01-24 08:28:49.985367: step: 916/526, loss: 0.009175797924399376
2023-01-24 08:28:51.058283: step: 920/526, loss: 0.0007077965419739485
2023-01-24 08:28:52.104845: step: 924/526, loss: 0.0014777312753722072
2023-01-24 08:28:53.163869: step: 928/526, loss: 0.040600694715976715
2023-01-24 08:28:54.227800: step: 932/526, loss: 0.003321695839986205
2023-01-24 08:28:55.288376: step: 936/526, loss: 0.0034956419840455055
2023-01-24 08:28:56.370303: step: 940/526, loss: 0.001856361050158739
2023-01-24 08:28:57.435690: step: 944/526, loss: 0.003936657682061195
2023-01-24 08:28:58.498227: step: 948/526, loss: 0.00014782967627979815
2023-01-24 08:28:59.561656: step: 952/526, loss: 0.0032827730756253004
2023-01-24 08:29:00.617166: step: 956/526, loss: 0.02049161121249199
2023-01-24 08:29:01.685978: step: 960/526, loss: 0.006885509938001633
2023-01-24 08:29:02.757709: step: 964/526, loss: 0.0013700233539566398
2023-01-24 08:29:03.827164: step: 968/526, loss: 0.0029252131935209036
2023-01-24 08:29:04.887294: step: 972/526, loss: 0.00019866864022333175
2023-01-24 08:29:05.951172: step: 976/526, loss: 0.002738167531788349
2023-01-24 08:29:07.016212: step: 980/526, loss: 0.00046391243813559413
2023-01-24 08:29:08.093738: step: 984/526, loss: 0.004509535152465105
2023-01-24 08:29:09.166711: step: 988/526, loss: 0.008534682914614677
2023-01-24 08:29:10.233382: step: 992/526, loss: 0.0025360353756695986
2023-01-24 08:29:11.312896: step: 996/526, loss: 0.011647382751107216
2023-01-24 08:29:12.364767: step: 1000/526, loss: 0.003562483936548233
2023-01-24 08:29:13.423530: step: 1004/526, loss: 2.0158728148089722e-05
2023-01-24 08:29:14.473777: step: 1008/526, loss: 0.0031182165257632732
2023-01-24 08:29:15.528667: step: 1012/526, loss: 0.0
2023-01-24 08:29:16.596081: step: 1016/526, loss: 0.0003311119507998228
2023-01-24 08:29:17.667534: step: 1020/526, loss: 0.0023517049849033356
2023-01-24 08:29:18.728235: step: 1024/526, loss: 0.0025499663315713406
2023-01-24 08:29:19.793715: step: 1028/526, loss: 0.0022722072899341583
2023-01-24 08:29:20.877270: step: 1032/526, loss: 0.0007208083407022059
2023-01-24 08:29:21.943089: step: 1036/526, loss: 0.005427314434200525
2023-01-24 08:29:23.012210: step: 1040/526, loss: 0.0038968222215771675
2023-01-24 08:29:24.081049: step: 1044/526, loss: 0.005707144737243652
2023-01-24 08:29:25.143517: step: 1048/526, loss: 0.0029660374857485294
2023-01-24 08:29:26.219540: step: 1052/526, loss: 0.004226453136652708
2023-01-24 08:29:27.286195: step: 1056/526, loss: 0.019874300807714462
2023-01-24 08:29:28.358326: step: 1060/526, loss: 0.006841110065579414
2023-01-24 08:29:29.437721: step: 1064/526, loss: 0.007175834383815527
2023-01-24 08:29:30.495667: step: 1068/526, loss: 0.0005810825387015939
2023-01-24 08:29:31.556712: step: 1072/526, loss: 0.01439677644520998
2023-01-24 08:29:32.620341: step: 1076/526, loss: 0.006567763164639473
2023-01-24 08:29:33.676057: step: 1080/526, loss: 0.0012794440845027566
2023-01-24 08:29:34.743465: step: 1084/526, loss: 0.0029513114131987095
2023-01-24 08:29:35.821069: step: 1088/526, loss: 0.00069697096478194
2023-01-24 08:29:36.898496: step: 1092/526, loss: 0.006819003727287054
2023-01-24 08:29:37.953245: step: 1096/526, loss: 0.005154205486178398
2023-01-24 08:29:39.033981: step: 1100/526, loss: 0.013068868778645992
2023-01-24 08:29:40.119678: step: 1104/526, loss: 0.0005962604773230851
2023-01-24 08:29:41.189706: step: 1108/526, loss: 0.002312930766493082
2023-01-24 08:29:42.266809: step: 1112/526, loss: 0.0012140960898250341
2023-01-24 08:29:43.330134: step: 1116/526, loss: 0.002851397730410099
2023-01-24 08:29:44.421539: step: 1120/526, loss: 0.0029857249464839697
2023-01-24 08:29:45.502682: step: 1124/526, loss: 0.005991691257804632
2023-01-24 08:29:46.576583: step: 1128/526, loss: 0.003597614821046591
2023-01-24 08:29:47.640741: step: 1132/526, loss: 0.005559731740504503
2023-01-24 08:29:48.733246: step: 1136/526, loss: 0.005038572940975428
2023-01-24 08:29:49.833100: step: 1140/526, loss: 0.011019838973879814
2023-01-24 08:29:50.900601: step: 1144/526, loss: 0.012714000418782234
2023-01-24 08:29:51.967101: step: 1148/526, loss: 6.798392860218883e-05
2023-01-24 08:29:53.030311: step: 1152/526, loss: 0.0046712374314665794
2023-01-24 08:29:54.115652: step: 1156/526, loss: 0.004524369724094868
2023-01-24 08:29:55.180114: step: 1160/526, loss: 0.006142141297459602
2023-01-24 08:29:56.246085: step: 1164/526, loss: 0.0015335364732891321
2023-01-24 08:29:57.296295: step: 1168/526, loss: 0.002124929800629616
2023-01-24 08:29:58.353746: step: 1172/526, loss: 0.003984525799751282
2023-01-24 08:29:59.416205: step: 1176/526, loss: 0.0003349226899445057
2023-01-24 08:30:00.483705: step: 1180/526, loss: 0.0021272897720336914
2023-01-24 08:30:01.551333: step: 1184/526, loss: 0.0013589432928711176
2023-01-24 08:30:02.624853: step: 1188/526, loss: 0.0028363335877656937
2023-01-24 08:30:03.700522: step: 1192/526, loss: 0.0016845815116539598
2023-01-24 08:30:04.770807: step: 1196/526, loss: 0.003293329617008567
2023-01-24 08:30:05.834080: step: 1200/526, loss: 0.0057005551643669605
2023-01-24 08:30:06.886248: step: 1204/526, loss: 0.005940551403909922
2023-01-24 08:30:07.956643: step: 1208/526, loss: 0.0027162879705429077
2023-01-24 08:30:09.037091: step: 1212/526, loss: 0.0034054783172905445
2023-01-24 08:30:10.097339: step: 1216/526, loss: 0.00657767616212368
2023-01-24 08:30:11.166821: step: 1220/526, loss: 0.009493658319115639
2023-01-24 08:30:12.238152: step: 1224/526, loss: 2.3338565370067954e-05
2023-01-24 08:30:13.322862: step: 1228/526, loss: 0.0018641414353623986
2023-01-24 08:30:14.394386: step: 1232/526, loss: 0.0017801745561882854
2023-01-24 08:30:15.466478: step: 1236/526, loss: 0.004656145349144936
2023-01-24 08:30:16.540587: step: 1240/526, loss: 0.004090503789484501
2023-01-24 08:30:17.602446: step: 1244/526, loss: 0.009272011928260326
2023-01-24 08:30:18.685190: step: 1248/526, loss: 0.00012689131835941225
2023-01-24 08:30:19.750968: step: 1252/526, loss: 0.0055953143164515495
2023-01-24 08:30:20.817005: step: 1256/526, loss: 0.004648896865546703
2023-01-24 08:30:21.873248: step: 1260/526, loss: 0.002918428275734186
2023-01-24 08:30:22.925021: step: 1264/526, loss: 0.00188479945063591
2023-01-24 08:30:24.009645: step: 1268/526, loss: 0.0023304992355406284
2023-01-24 08:30:25.085217: step: 1272/526, loss: 0.003591935383155942
2023-01-24 08:30:26.160562: step: 1276/526, loss: 0.0075240060687065125
2023-01-24 08:30:27.223318: step: 1280/526, loss: 0.004160855431109667
2023-01-24 08:30:28.302528: step: 1284/526, loss: 0.0010498282499611378
2023-01-24 08:30:29.368830: step: 1288/526, loss: 0.013328592292964458
2023-01-24 08:30:30.440686: step: 1292/526, loss: 0.00090277154231444
2023-01-24 08:30:31.527336: step: 1296/526, loss: 0.004142351448535919
2023-01-24 08:30:32.604960: step: 1300/526, loss: 0.0008531195344403386
2023-01-24 08:30:33.666254: step: 1304/526, loss: 0.00687104556709528
2023-01-24 08:30:34.736477: step: 1308/526, loss: 0.0004095988115295768
2023-01-24 08:30:35.807216: step: 1312/526, loss: 0.010410458780825138
2023-01-24 08:30:36.902114: step: 1316/526, loss: 0.01988687925040722
2023-01-24 08:30:37.966258: step: 1320/526, loss: 0.0024965452030301094
2023-01-24 08:30:39.037883: step: 1324/526, loss: 0.003737257793545723
2023-01-24 08:30:40.108013: step: 1328/526, loss: 0.0007387580117210746
2023-01-24 08:30:41.178291: step: 1332/526, loss: 0.0034012352116405964
2023-01-24 08:30:42.255885: step: 1336/526, loss: 0.005119304172694683
2023-01-24 08:30:43.316112: step: 1340/526, loss: 0.000796099950093776
2023-01-24 08:30:44.396460: step: 1344/526, loss: 0.004002515226602554
2023-01-24 08:30:45.457124: step: 1348/526, loss: 0.002700971905142069
2023-01-24 08:30:46.533605: step: 1352/526, loss: 7.12940382072702e-05
2023-01-24 08:30:47.593609: step: 1356/526, loss: 0.001824081758968532
2023-01-24 08:30:48.661781: step: 1360/526, loss: 0.0008810501312837005
2023-01-24 08:30:49.733339: step: 1364/526, loss: 0.003603171557188034
2023-01-24 08:30:50.804055: step: 1368/526, loss: 0.006394225172698498
2023-01-24 08:30:51.886944: step: 1372/526, loss: 0.007410027086734772
2023-01-24 08:30:52.962291: step: 1376/526, loss: 0.005779553670436144
2023-01-24 08:30:54.036617: step: 1380/526, loss: 0.007174394093453884
2023-01-24 08:30:55.108990: step: 1384/526, loss: 0.03878473863005638
2023-01-24 08:30:56.191406: step: 1388/526, loss: 0.07310990989208221
2023-01-24 08:30:57.265807: step: 1392/526, loss: 0.02617347612977028
2023-01-24 08:30:58.340934: step: 1396/526, loss: 0.05329953506588936
2023-01-24 08:30:59.411265: step: 1400/526, loss: 0.0
2023-01-24 08:31:00.473911: step: 1404/526, loss: 0.017215203493833542
2023-01-24 08:31:01.537335: step: 1408/526, loss: 0.0026311581023037434
2023-01-24 08:31:02.592304: step: 1412/526, loss: 0.0010681774001568556
2023-01-24 08:31:03.657746: step: 1416/526, loss: 0.0020601856522262096
2023-01-24 08:31:04.721383: step: 1420/526, loss: 0.002179694129154086
2023-01-24 08:31:05.788534: step: 1424/526, loss: 0.0013555905316025019
2023-01-24 08:31:06.846545: step: 1428/526, loss: 0.006631419062614441
2023-01-24 08:31:07.911399: step: 1432/526, loss: 0.012579905800521374
2023-01-24 08:31:08.977636: step: 1436/526, loss: 0.004499421454966068
2023-01-24 08:31:10.058842: step: 1440/526, loss: 0.04087740555405617
2023-01-24 08:31:11.128619: step: 1444/526, loss: 0.00010615806968417019
2023-01-24 08:31:12.193796: step: 1448/526, loss: 0.006730419117957354
2023-01-24 08:31:13.258828: step: 1452/526, loss: 0.00636819563806057
2023-01-24 08:31:14.338440: step: 1456/526, loss: 0.01905321143567562
2023-01-24 08:31:15.422534: step: 1460/526, loss: 0.0031310312915593386
2023-01-24 08:31:16.480029: step: 1464/526, loss: 0.0027232805732637644
2023-01-24 08:31:17.562619: step: 1468/526, loss: 0.010189528577029705
2023-01-24 08:31:18.633080: step: 1472/526, loss: 0.004538217093795538
2023-01-24 08:31:19.684694: step: 1476/526, loss: 0.0019517021719366312
2023-01-24 08:31:20.741015: step: 1480/526, loss: 0.0003497126745060086
2023-01-24 08:31:21.811755: step: 1484/526, loss: 6.269663572311401e-05
2023-01-24 08:31:22.874466: step: 1488/526, loss: 5.916481313761324e-05
2023-01-24 08:31:23.943141: step: 1492/526, loss: 0.004511381033807993
2023-01-24 08:31:25.015382: step: 1496/526, loss: 2.935009979410097e-05
2023-01-24 08:31:26.065595: step: 1500/526, loss: 0.00831483956426382
2023-01-24 08:31:27.148318: step: 1504/526, loss: 0.006276101339608431
2023-01-24 08:31:28.230749: step: 1508/526, loss: 0.001494137686677277
2023-01-24 08:31:29.307926: step: 1512/526, loss: 0.009022546000778675
2023-01-24 08:31:30.374619: step: 1516/526, loss: 0.02004232071340084
2023-01-24 08:31:31.434167: step: 1520/526, loss: 0.060813140124082565
2023-01-24 08:31:32.495185: step: 1524/526, loss: 0.00411297706887126
2023-01-24 08:31:33.564647: step: 1528/526, loss: 0.016256025061011314
2023-01-24 08:31:34.646989: step: 1532/526, loss: 0.02163807675242424
2023-01-24 08:31:35.711144: step: 1536/526, loss: 0.000977646792307496
2023-01-24 08:31:36.778874: step: 1540/526, loss: 0.00652306480333209
2023-01-24 08:31:37.849436: step: 1544/526, loss: 0.02499307133257389
2023-01-24 08:31:38.902006: step: 1548/526, loss: 0.0010517260525375605
2023-01-24 08:31:39.983024: step: 1552/526, loss: 0.00844988226890564
2023-01-24 08:31:41.075175: step: 1556/526, loss: 0.006858066190034151
2023-01-24 08:31:42.134250: step: 1560/526, loss: 0.0036917785182595253
2023-01-24 08:31:43.183929: step: 1564/526, loss: 0.0032497786451131105
2023-01-24 08:31:44.259665: step: 1568/526, loss: 0.0035531248431652784
2023-01-24 08:31:45.316139: step: 1572/526, loss: 0.0020319416653364897
2023-01-24 08:31:46.387046: step: 1576/526, loss: 0.00012026914191665128
2023-01-24 08:31:47.467342: step: 1580/526, loss: 0.0006924492190591991
2023-01-24 08:31:48.530822: step: 1584/526, loss: 0.012939331121742725
2023-01-24 08:31:49.604180: step: 1588/526, loss: 0.0003669472935143858
2023-01-24 08:31:50.658363: step: 1592/526, loss: 0.004529666155576706
2023-01-24 08:31:51.732109: step: 1596/526, loss: 0.008283115923404694
2023-01-24 08:31:52.792324: step: 1600/526, loss: 0.004352471325546503
2023-01-24 08:31:53.859901: step: 1604/526, loss: 0.018357954919338226
2023-01-24 08:31:54.937044: step: 1608/526, loss: 0.007702977396547794
2023-01-24 08:31:56.025161: step: 1612/526, loss: 0.005042489618062973
2023-01-24 08:31:57.098651: step: 1616/526, loss: 0.00972728244960308
2023-01-24 08:31:58.161764: step: 1620/526, loss: 0.009273105300962925
2023-01-24 08:31:59.246789: step: 1624/526, loss: 7.472003198927268e-05
2023-01-24 08:32:00.342046: step: 1628/526, loss: 0.011308124288916588
2023-01-24 08:32:01.407391: step: 1632/526, loss: 0.002210986101999879
2023-01-24 08:32:02.486537: step: 1636/526, loss: 0.0015535252168774605
2023-01-24 08:32:03.542766: step: 1640/526, loss: 0.0019940512720495462
2023-01-24 08:32:04.610188: step: 1644/526, loss: 4.983371400157921e-05
2023-01-24 08:32:05.681900: step: 1648/526, loss: 0.0005068308091722429
2023-01-24 08:32:06.752342: step: 1652/526, loss: 0.008029392920434475
2023-01-24 08:32:07.827742: step: 1656/526, loss: 0.03286871686577797
2023-01-24 08:32:08.910131: step: 1660/526, loss: 0.0011309122201055288
2023-01-24 08:32:09.970667: step: 1664/526, loss: 0.0019505774835124612
2023-01-24 08:32:11.046772: step: 1668/526, loss: 0.0023209021892398596
2023-01-24 08:32:12.116629: step: 1672/526, loss: 0.0003546491207089275
2023-01-24 08:32:13.196403: step: 1676/526, loss: 0.004372374154627323
2023-01-24 08:32:14.271775: step: 1680/526, loss: 0.0036947571206837893
2023-01-24 08:32:15.334412: step: 1684/526, loss: 0.026176095008850098
2023-01-24 08:32:16.393204: step: 1688/526, loss: 7.028792197161238e-07
2023-01-24 08:32:17.446767: step: 1692/526, loss: 0.006586136296391487
2023-01-24 08:32:18.506506: step: 1696/526, loss: 0.01703745685517788
2023-01-24 08:32:19.598694: step: 1700/526, loss: 0.009997772052884102
2023-01-24 08:32:20.676430: step: 1704/526, loss: 0.0013539936626330018
2023-01-24 08:32:21.761098: step: 1708/526, loss: 0.00545844342559576
2023-01-24 08:32:22.823646: step: 1712/526, loss: 0.003199740080162883
2023-01-24 08:32:23.895970: step: 1716/526, loss: 0.004632893949747086
2023-01-24 08:32:24.951676: step: 1720/526, loss: 0.0006263629184104502
2023-01-24 08:32:26.038842: step: 1724/526, loss: 0.01591830886900425
2023-01-24 08:32:27.103828: step: 1728/526, loss: 0.007647314108908176
2023-01-24 08:32:28.174429: step: 1732/526, loss: 0.003030173946171999
2023-01-24 08:32:29.229385: step: 1736/526, loss: 0.007665179669857025
2023-01-24 08:32:30.296436: step: 1740/526, loss: 0.007942522875964642
2023-01-24 08:32:31.359741: step: 1744/526, loss: 0.0168094951659441
2023-01-24 08:32:32.421939: step: 1748/526, loss: 0.0019358332501724362
2023-01-24 08:32:33.490663: step: 1752/526, loss: 5.112489088787697e-05
2023-01-24 08:32:34.577095: step: 1756/526, loss: 0.001044497941620648
2023-01-24 08:32:35.646093: step: 1760/526, loss: 0.011358664371073246
2023-01-24 08:32:36.738689: step: 1764/526, loss: 0.0041775889694690704
2023-01-24 08:32:37.822534: step: 1768/526, loss: 0.0010591248283162713
2023-01-24 08:32:38.883643: step: 1772/526, loss: 0.00029247647034935653
2023-01-24 08:32:39.954814: step: 1776/526, loss: 0.006607255432754755
2023-01-24 08:32:41.020629: step: 1780/526, loss: 0.001824350212700665
2023-01-24 08:32:42.088171: step: 1784/526, loss: 0.0005624218611046672
2023-01-24 08:32:43.159565: step: 1788/526, loss: 0.01835312321782112
2023-01-24 08:32:44.220382: step: 1792/526, loss: 0.0026089251041412354
2023-01-24 08:32:45.290557: step: 1796/526, loss: 0.005027491599321365
2023-01-24 08:32:46.359046: step: 1800/526, loss: 0.0036666837986558676
2023-01-24 08:32:47.425326: step: 1804/526, loss: 0.004081855993717909
2023-01-24 08:32:48.500913: step: 1808/526, loss: 0.004595533944666386
2023-01-24 08:32:49.546159: step: 1812/526, loss: 0.008726425468921661
2023-01-24 08:32:50.603916: step: 1816/526, loss: 0.00014430210285354406
2023-01-24 08:32:51.668684: step: 1820/526, loss: 0.02427584119141102
2023-01-24 08:32:52.748935: step: 1824/526, loss: 0.024298807606101036
2023-01-24 08:32:53.813204: step: 1828/526, loss: 0.017614293843507767
2023-01-24 08:32:54.884009: step: 1832/526, loss: 0.004321054555475712
2023-01-24 08:32:55.949762: step: 1836/526, loss: 0.001116780680604279
2023-01-24 08:32:57.002473: step: 1840/526, loss: 0.004009234253317118
2023-01-24 08:32:58.069731: step: 1844/526, loss: 0.004184509627521038
2023-01-24 08:32:59.135849: step: 1848/526, loss: 0.0007857540622353554
2023-01-24 08:33:00.195883: step: 1852/526, loss: 0.002389674074947834
2023-01-24 08:33:01.266506: step: 1856/526, loss: 0.005993325263261795
2023-01-24 08:33:02.331295: step: 1860/526, loss: 0.011724431067705154
2023-01-24 08:33:03.391595: step: 1864/526, loss: 0.0001669973280513659
2023-01-24 08:33:04.479179: step: 1868/526, loss: 0.004174278117716312
2023-01-24 08:33:05.551712: step: 1872/526, loss: 0.0048838225193321705
2023-01-24 08:33:06.630183: step: 1876/526, loss: 0.00153544161003083
2023-01-24 08:33:07.688544: step: 1880/526, loss: 0.0016118037747219205
2023-01-24 08:33:08.769193: step: 1884/526, loss: 0.0014590248465538025
2023-01-24 08:33:09.843648: step: 1888/526, loss: 0.034674499183893204
2023-01-24 08:33:10.902271: step: 1892/526, loss: 0.00033258445910178125
2023-01-24 08:33:11.971362: step: 1896/526, loss: 0.006668785586953163
2023-01-24 08:33:13.069650: step: 1900/526, loss: 0.006076838355511427
2023-01-24 08:33:14.150205: step: 1904/526, loss: 0.010348460637032986
2023-01-24 08:33:15.252280: step: 1908/526, loss: 0.0012399296974763274
2023-01-24 08:33:16.326824: step: 1912/526, loss: 0.0014980159467086196
2023-01-24 08:33:17.413405: step: 1916/526, loss: 0.005179837811738253
2023-01-24 08:33:18.473069: step: 1920/526, loss: 0.0004589584714267403
2023-01-24 08:33:19.571147: step: 1924/526, loss: 0.002740239491686225
2023-01-24 08:33:20.655093: step: 1928/526, loss: 0.0029836641624569893
2023-01-24 08:33:21.731500: step: 1932/526, loss: 0.0030564088374376297
2023-01-24 08:33:22.802201: step: 1936/526, loss: 0.0006544237257912755
2023-01-24 08:33:23.876586: step: 1940/526, loss: 0.0024999219458550215
2023-01-24 08:33:24.946941: step: 1944/526, loss: 0.007214280776679516
2023-01-24 08:33:26.029825: step: 1948/526, loss: 0.0008418355137109756
2023-01-24 08:33:27.093350: step: 1952/526, loss: 8.560383139410987e-05
2023-01-24 08:33:28.160543: step: 1956/526, loss: 0.004812711384147406
2023-01-24 08:33:29.248263: step: 1960/526, loss: 0.014564109966158867
2023-01-24 08:33:30.347437: step: 1964/526, loss: 0.02157345600426197
2023-01-24 08:33:31.447510: step: 1968/526, loss: 0.005345316603779793
2023-01-24 08:33:32.532715: step: 1972/526, loss: 0.008475751616060734
2023-01-24 08:33:33.609530: step: 1976/526, loss: 0.004904601722955704
2023-01-24 08:33:34.682521: step: 1980/526, loss: 0.03099743276834488
2023-01-24 08:33:35.773635: step: 1984/526, loss: 0.0004093674651812762
2023-01-24 08:33:36.845173: step: 1988/526, loss: 0.016514822840690613
2023-01-24 08:33:37.904805: step: 1992/526, loss: 0.0014487385051324964
2023-01-24 08:33:38.996195: step: 1996/526, loss: 0.0004042002547066659
2023-01-24 08:33:40.067524: step: 2000/526, loss: 0.0007758474675938487
2023-01-24 08:33:41.148948: step: 2004/526, loss: 0.0043033999390900135
2023-01-24 08:33:42.222723: step: 2008/526, loss: 0.0067427936010062695
2023-01-24 08:33:43.313629: step: 2012/526, loss: 0.0038654550444334745
2023-01-24 08:33:44.384004: step: 2016/526, loss: 0.0068710013292729855
2023-01-24 08:33:45.446874: step: 2020/526, loss: 0.008543653413653374
2023-01-24 08:33:46.512675: step: 2024/526, loss: 0.0040159812197089195
2023-01-24 08:33:47.577861: step: 2028/526, loss: 0.007723723538219929
2023-01-24 08:33:48.636839: step: 2032/526, loss: 0.003561505815014243
2023-01-24 08:33:49.705156: step: 2036/526, loss: 8.433743641944602e-05
2023-01-24 08:33:50.750711: step: 2040/526, loss: 0.0007240792619995773
2023-01-24 08:33:51.844126: step: 2044/526, loss: 0.004231943283230066
2023-01-24 08:33:52.935822: step: 2048/526, loss: 0.0024330653250217438
2023-01-24 08:33:54.000998: step: 2052/526, loss: 0.00860643945634365
2023-01-24 08:33:55.089018: step: 2056/526, loss: 0.0004952047020196915
2023-01-24 08:33:56.175870: step: 2060/526, loss: 0.00782067608088255
2023-01-24 08:33:57.253599: step: 2064/526, loss: 0.0006878709536977112
2023-01-24 08:33:58.325339: step: 2068/526, loss: 4.943471139995381e-05
2023-01-24 08:33:59.421217: step: 2072/526, loss: 0.0070662242360413074
2023-01-24 08:34:00.499717: step: 2076/526, loss: 0.0008313669823110104
2023-01-24 08:34:01.570796: step: 2080/526, loss: 0.005298133939504623
2023-01-24 08:34:02.661074: step: 2084/526, loss: 0.001045431476086378
2023-01-24 08:34:03.747494: step: 2088/526, loss: 0.0005098225083202124
2023-01-24 08:34:04.828218: step: 2092/526, loss: 0.012814799323678017
2023-01-24 08:34:05.916309: step: 2096/526, loss: 0.0020076052751392126
2023-01-24 08:34:07.002467: step: 2100/526, loss: 0.004314163234084845
2023-01-24 08:34:08.082211: step: 2104/526, loss: 0.006428925786167383
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3576313158851327, 'r': 0.26669659799403633, 'f1': 0.3055415372670807}, 'combined': 0.22513586956521736, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3591309001670844, 'r': 0.2247443144686969, 'f1': 0.2764721842591848}, 'combined': 0.15080300959591897, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3349816348859018, 'r': 0.29048692057468145, 'f1': 0.3111516405342625}, 'combined': 0.22926962986735128, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3594329962062681, 'r': 0.2611068609220283, 'f1': 0.3024799141364885}, 'combined': 0.16498904407444825, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3575298564245071, 'r': 0.31071854694957163, 'f1': 0.3324846177511152}, 'combined': 0.24498866571134803, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3641136478096441, 'r': 0.27849863638505257, 'f1': 0.3156029129796397}, 'combined': 0.17214704344343984, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.44047619047619047, 'r': 0.40217391304347827, 'f1': 0.4204545454545454}, 'combined': 0.2102272727272727, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 08:36:51.273210: step: 4/526, loss: 0.0038160455878823996
2023-01-24 08:36:52.336779: step: 8/526, loss: 0.002674256917089224
2023-01-24 08:36:53.406275: step: 12/526, loss: 0.004621006548404694
2023-01-24 08:36:54.467894: step: 16/526, loss: 0.003732952056452632
2023-01-24 08:36:55.524196: step: 20/526, loss: 0.006812302861362696
2023-01-24 08:36:56.581520: step: 24/526, loss: 0.00046529434621334076
2023-01-24 08:36:57.670138: step: 28/526, loss: 0.0023023944813758135
2023-01-24 08:36:58.725618: step: 32/526, loss: 0.0070501365698874
2023-01-24 08:36:59.775124: step: 36/526, loss: 0.0027976122219115496
2023-01-24 08:37:00.850182: step: 40/526, loss: 0.0023237173445522785
2023-01-24 08:37:01.909648: step: 44/526, loss: 0.0016857532318681479
2023-01-24 08:37:02.963682: step: 48/526, loss: 0.003736741142347455
2023-01-24 08:37:04.036084: step: 52/526, loss: 0.0010771984234452248
2023-01-24 08:37:05.088964: step: 56/526, loss: 0.0005143777816556394
2023-01-24 08:37:06.144869: step: 60/526, loss: 0.004283219110220671
2023-01-24 08:37:07.226663: step: 64/526, loss: 0.00323097943328321
2023-01-24 08:37:08.287518: step: 68/526, loss: 0.0270400233566761
2023-01-24 08:37:09.346473: step: 72/526, loss: 0.0008317366009578109
2023-01-24 08:37:10.413817: step: 76/526, loss: 0.0031352487858384848
2023-01-24 08:37:11.485690: step: 80/526, loss: 0.0028990048449486494
2023-01-24 08:37:12.561885: step: 84/526, loss: 0.00010778255091281608
2023-01-24 08:37:13.634276: step: 88/526, loss: 0.007569632027298212
2023-01-24 08:37:14.679307: step: 92/526, loss: 0.003725457936525345
2023-01-24 08:37:15.749064: step: 96/526, loss: 0.005097818095237017
2023-01-24 08:37:16.797586: step: 100/526, loss: 0.005310761742293835
2023-01-24 08:37:17.850493: step: 104/526, loss: 0.0038388094399124384
2023-01-24 08:37:18.900948: step: 108/526, loss: 0.02295560948550701
2023-01-24 08:37:19.984622: step: 112/526, loss: 0.0023131135385483503
2023-01-24 08:37:21.043451: step: 116/526, loss: 0.005850787740200758
2023-01-24 08:37:22.091131: step: 120/526, loss: 0.0006953251431696117
2023-01-24 08:37:23.164308: step: 124/526, loss: 0.005086628720164299
2023-01-24 08:37:24.227790: step: 128/526, loss: 0.0022583589889109135
2023-01-24 08:37:25.291762: step: 132/526, loss: 0.004099803976714611
2023-01-24 08:37:26.357511: step: 136/526, loss: 0.001496132928878069
2023-01-24 08:37:27.415898: step: 140/526, loss: 3.492146424832754e-05
2023-01-24 08:37:28.476227: step: 144/526, loss: 0.0012209846172481775
2023-01-24 08:37:29.536955: step: 148/526, loss: 0.004968051798641682
2023-01-24 08:37:30.621749: step: 152/526, loss: 0.003387398086488247
2023-01-24 08:37:31.685818: step: 156/526, loss: 0.00079245341476053
2023-01-24 08:37:32.761167: step: 160/526, loss: 0.004783318378031254
2023-01-24 08:37:33.821585: step: 164/526, loss: 0.00048400519881397486
2023-01-24 08:37:34.887137: step: 168/526, loss: 0.0016160618979483843
2023-01-24 08:37:35.956822: step: 172/526, loss: 0.00713609391823411
2023-01-24 08:37:37.016313: step: 176/526, loss: 0.004505706951022148
2023-01-24 08:37:38.089424: step: 180/526, loss: 0.013733535073697567
2023-01-24 08:37:39.157956: step: 184/526, loss: 0.00499225128442049
2023-01-24 08:37:40.218156: step: 188/526, loss: 0.00606751162558794
2023-01-24 08:37:41.287461: step: 192/526, loss: 0.002098146826028824
2023-01-24 08:37:42.334610: step: 196/526, loss: 0.002904574852436781
2023-01-24 08:37:43.398632: step: 200/526, loss: 0.0004220707342028618
2023-01-24 08:37:44.462853: step: 204/526, loss: 0.002314547775313258
2023-01-24 08:37:45.531582: step: 208/526, loss: 0.009258140809834003
2023-01-24 08:37:46.601200: step: 212/526, loss: 0.0006761526456102729
2023-01-24 08:37:47.672743: step: 216/526, loss: 0.004619353450834751
2023-01-24 08:37:48.731596: step: 220/526, loss: 0.0006481197196990252
2023-01-24 08:37:49.805292: step: 224/526, loss: 0.008110636845231056
2023-01-24 08:37:50.865841: step: 228/526, loss: 0.004194497596472502
2023-01-24 08:37:51.924450: step: 232/526, loss: 0.006563953123986721
2023-01-24 08:37:52.989111: step: 236/526, loss: 0.004174908623099327
2023-01-24 08:37:54.062187: step: 240/526, loss: 0.003269864246249199
2023-01-24 08:37:55.123234: step: 244/526, loss: 0.0012675767065957189
2023-01-24 08:37:56.191569: step: 248/526, loss: 0.0012934055412188172
2023-01-24 08:37:57.264362: step: 252/526, loss: 0.02725783921778202
2023-01-24 08:37:58.326092: step: 256/526, loss: 0.001841770252212882
2023-01-24 08:37:59.385836: step: 260/526, loss: 0.005191021133214235
2023-01-24 08:38:00.454879: step: 264/526, loss: 0.00185909285210073
2023-01-24 08:38:01.528737: step: 268/526, loss: 0.0045059965923428535
2023-01-24 08:38:02.600209: step: 272/526, loss: 0.0065894341096282005
2023-01-24 08:38:03.664221: step: 276/526, loss: 0.004639733117073774
2023-01-24 08:38:04.721365: step: 280/526, loss: 0.0016907708486542106
2023-01-24 08:38:05.782140: step: 284/526, loss: 0.0005969437770545483
2023-01-24 08:38:06.839136: step: 288/526, loss: 0.004094295669347048
2023-01-24 08:38:07.905870: step: 292/526, loss: 0.0058018798008561134
2023-01-24 08:38:08.973225: step: 296/526, loss: 0.00014649178774561733
2023-01-24 08:38:10.034472: step: 300/526, loss: 0.0004003380599897355
2023-01-24 08:38:11.100515: step: 304/526, loss: 0.006760130170732737
2023-01-24 08:38:12.163043: step: 308/526, loss: 0.00048514080117456615
2023-01-24 08:38:13.247816: step: 312/526, loss: 0.00806464534252882
2023-01-24 08:38:14.307217: step: 316/526, loss: 0.0018172974232584238
2023-01-24 08:38:15.375589: step: 320/526, loss: 0.006813384592533112
2023-01-24 08:38:16.432505: step: 324/526, loss: 1.2232379049237352e-05
2023-01-24 08:38:17.506465: step: 328/526, loss: 0.00028781688888557255
2023-01-24 08:38:18.570306: step: 332/526, loss: 0.0031622473616153
2023-01-24 08:38:19.623621: step: 336/526, loss: 0.0003086850920226425
2023-01-24 08:38:20.723165: step: 340/526, loss: 0.0005392441526055336
2023-01-24 08:38:21.809941: step: 344/526, loss: 0.005243216175585985
2023-01-24 08:38:22.875799: step: 348/526, loss: 0.0031118332408368587
2023-01-24 08:38:23.948816: step: 352/526, loss: 0.0036169998347759247
2023-01-24 08:38:25.010244: step: 356/526, loss: 0.00370042328722775
2023-01-24 08:38:26.081621: step: 360/526, loss: 0.010754608549177647
2023-01-24 08:38:27.158671: step: 364/526, loss: 0.003144514514133334
2023-01-24 08:38:28.224486: step: 368/526, loss: 0.002588221337646246
2023-01-24 08:38:29.280929: step: 372/526, loss: 0.006095807068049908
2023-01-24 08:38:30.356039: step: 376/526, loss: 0.0034547345712780952
2023-01-24 08:38:31.428653: step: 380/526, loss: 0.0033636896405369043
2023-01-24 08:38:32.516181: step: 384/526, loss: 0.0008751609711907804
2023-01-24 08:38:33.564265: step: 388/526, loss: 0.0005274321883916855
2023-01-24 08:38:34.625232: step: 392/526, loss: 0.045020926743745804
2023-01-24 08:38:35.701358: step: 396/526, loss: 0.004994106013327837
2023-01-24 08:38:36.760009: step: 400/526, loss: 0.0030030838679522276
2023-01-24 08:38:37.829117: step: 404/526, loss: 0.002722801873460412
2023-01-24 08:38:38.880172: step: 408/526, loss: 0.00035113509511575103
2023-01-24 08:38:39.963970: step: 412/526, loss: 0.002638966543599963
2023-01-24 08:38:41.038484: step: 416/526, loss: 0.0010901845525950193
2023-01-24 08:38:42.112414: step: 420/526, loss: 0.006364356726408005
2023-01-24 08:38:43.189677: step: 424/526, loss: 0.006897682324051857
2023-01-24 08:38:44.259704: step: 428/526, loss: 0.007479271851480007
2023-01-24 08:38:45.327681: step: 432/526, loss: 0.01680966094136238
2023-01-24 08:38:46.411970: step: 436/526, loss: 0.007896722294390202
2023-01-24 08:38:47.465234: step: 440/526, loss: 0.0063851564191281796
2023-01-24 08:38:48.542237: step: 444/526, loss: 0.008131866343319416
2023-01-24 08:38:49.609994: step: 448/526, loss: 0.0006371065974235535
2023-01-24 08:38:50.683027: step: 452/526, loss: 0.005970512051135302
2023-01-24 08:38:51.743223: step: 456/526, loss: 0.00030315155163407326
2023-01-24 08:38:52.810577: step: 460/526, loss: 0.005403812509030104
2023-01-24 08:38:53.895739: step: 464/526, loss: 0.0019965041428804398
2023-01-24 08:38:54.951184: step: 468/526, loss: 0.002764735836535692
2023-01-24 08:38:56.014766: step: 472/526, loss: 0.0028944150544703007
2023-01-24 08:38:57.084667: step: 476/526, loss: 0.006938498001545668
2023-01-24 08:38:58.143564: step: 480/526, loss: 0.004693842492997646
2023-01-24 08:38:59.204649: step: 484/526, loss: 0.0007596335490234196
2023-01-24 08:39:00.275762: step: 488/526, loss: 0.0001611992047401145
2023-01-24 08:39:01.328803: step: 492/526, loss: 0.0010644515277817845
2023-01-24 08:39:02.404677: step: 496/526, loss: 0.003196912119165063
2023-01-24 08:39:03.465659: step: 500/526, loss: 0.003928244113922119
2023-01-24 08:39:04.544410: step: 504/526, loss: 0.0023313816636800766
2023-01-24 08:39:05.602630: step: 508/526, loss: 0.0010442739585414529
2023-01-24 08:39:06.690756: step: 512/526, loss: 0.005013664253056049
2023-01-24 08:39:07.752223: step: 516/526, loss: 0.005086920224130154
2023-01-24 08:39:08.808171: step: 520/526, loss: 0.00214071455411613
2023-01-24 08:39:09.870180: step: 524/526, loss: 0.0009304194245487452
2023-01-24 08:39:10.935931: step: 528/526, loss: 0.003397251944988966
2023-01-24 08:39:12.002314: step: 532/526, loss: 0.001379756722599268
2023-01-24 08:39:13.071605: step: 536/526, loss: 0.0003635635948739946
2023-01-24 08:39:14.138924: step: 540/526, loss: 2.497303648851812e-05
2023-01-24 08:39:15.201066: step: 544/526, loss: 0.007742059882730246
2023-01-24 08:39:16.265508: step: 548/526, loss: 0.00014858537178952247
2023-01-24 08:39:17.334485: step: 552/526, loss: 0.002425577025860548
2023-01-24 08:39:18.401047: step: 556/526, loss: 0.00551773514598608
2023-01-24 08:39:19.465247: step: 560/526, loss: 0.0014679240994155407
2023-01-24 08:39:20.535858: step: 564/526, loss: 0.010785788297653198
2023-01-24 08:39:21.605580: step: 568/526, loss: 0.0007370549137704074
2023-01-24 08:39:22.679106: step: 572/526, loss: 0.00351623073220253
2023-01-24 08:39:23.757459: step: 576/526, loss: 0.0031941228080540895
2023-01-24 08:39:24.829136: step: 580/526, loss: 0.0018449927447363734
2023-01-24 08:39:25.888640: step: 584/526, loss: 0.0013085560640320182
2023-01-24 08:39:26.972516: step: 588/526, loss: 0.012037588283419609
2023-01-24 08:39:28.045291: step: 592/526, loss: 0.00040585047099739313
2023-01-24 08:39:29.107088: step: 596/526, loss: 0.00393644068390131
2023-01-24 08:39:30.174886: step: 600/526, loss: 0.0020843103993684053
2023-01-24 08:39:31.223860: step: 604/526, loss: 0.0017401882214471698
2023-01-24 08:39:32.276693: step: 608/526, loss: 0.00011535193334566429
2023-01-24 08:39:33.340238: step: 612/526, loss: 0.0033245920203626156
2023-01-24 08:39:34.411091: step: 616/526, loss: 0.00035558539093472064
2023-01-24 08:39:35.495158: step: 620/526, loss: 0.023518720641732216
2023-01-24 08:39:36.565381: step: 624/526, loss: 0.007926519960165024
2023-01-24 08:39:37.643963: step: 628/526, loss: 0.002083064988255501
2023-01-24 08:39:38.710538: step: 632/526, loss: 0.0016286555910483003
2023-01-24 08:39:39.793721: step: 636/526, loss: 0.0015901544829830527
2023-01-24 08:39:40.869567: step: 640/526, loss: 0.0018651778809726238
2023-01-24 08:39:41.922534: step: 644/526, loss: 0.004405217245221138
2023-01-24 08:39:42.973147: step: 648/526, loss: 0.005960434675216675
2023-01-24 08:39:44.027961: step: 652/526, loss: 4.190753770672018e-06
2023-01-24 08:39:45.090703: step: 656/526, loss: 0.0030449663754552603
2023-01-24 08:39:46.155336: step: 660/526, loss: 0.0040357387624681
2023-01-24 08:39:47.208715: step: 664/526, loss: 0.0010376276914030313
2023-01-24 08:39:48.299434: step: 668/526, loss: 0.00599429989233613
2023-01-24 08:39:49.361409: step: 672/526, loss: 9.253184543922544e-05
2023-01-24 08:39:50.420615: step: 676/526, loss: 0.00021377208759076893
2023-01-24 08:39:51.479465: step: 680/526, loss: 0.0012489090440794826
2023-01-24 08:39:52.554802: step: 684/526, loss: 0.0052191708236932755
2023-01-24 08:39:53.644912: step: 688/526, loss: 0.0028376926202327013
2023-01-24 08:39:54.706971: step: 692/526, loss: 0.009810381568968296
2023-01-24 08:39:55.770714: step: 696/526, loss: 0.006933249533176422
2023-01-24 08:39:56.831928: step: 700/526, loss: 0.0074748084880411625
2023-01-24 08:39:57.919292: step: 704/526, loss: 0.008868585340678692
2023-01-24 08:39:59.014634: step: 708/526, loss: 0.060324057936668396
2023-01-24 08:40:00.073156: step: 712/526, loss: 0.0018125202041119337
2023-01-24 08:40:01.151898: step: 716/526, loss: 9.370889893034473e-05
2023-01-24 08:40:02.217624: step: 720/526, loss: 0.0038213878870010376
2023-01-24 08:40:03.283152: step: 724/526, loss: 0.01805827207863331
2023-01-24 08:40:04.360990: step: 728/526, loss: 0.0323360413312912
2023-01-24 08:40:05.420986: step: 732/526, loss: 0.010594063438475132
2023-01-24 08:40:06.498980: step: 736/526, loss: 0.002987007610499859
2023-01-24 08:40:07.566344: step: 740/526, loss: 0.0011591152288019657
2023-01-24 08:40:08.635069: step: 744/526, loss: 0.006188101135194302
2023-01-24 08:40:09.726352: step: 748/526, loss: 0.0031672571785748005
2023-01-24 08:40:10.788514: step: 752/526, loss: 0.0032132300548255444
2023-01-24 08:40:11.842035: step: 756/526, loss: 3.894660494552227e-06
2023-01-24 08:40:12.913045: step: 760/526, loss: 0.007211936637759209
2023-01-24 08:40:14.011555: step: 764/526, loss: 0.012980573810636997
2023-01-24 08:40:15.078862: step: 768/526, loss: 0.0025059001054614782
2023-01-24 08:40:16.144846: step: 772/526, loss: 0.002924935193732381
2023-01-24 08:40:17.216423: step: 776/526, loss: 0.008592157624661922
2023-01-24 08:40:18.281015: step: 780/526, loss: 0.00019979050557594746
2023-01-24 08:40:19.370975: step: 784/526, loss: 0.0001128509029513225
2023-01-24 08:40:20.423901: step: 788/526, loss: 0.0
2023-01-24 08:40:21.500308: step: 792/526, loss: 0.0019905706867575645
2023-01-24 08:40:22.570004: step: 796/526, loss: 0.003986770287156105
2023-01-24 08:40:23.649088: step: 800/526, loss: 0.0027946890331804752
2023-01-24 08:40:24.708618: step: 804/526, loss: 0.019000818952918053
2023-01-24 08:40:25.777352: step: 808/526, loss: 0.008973361924290657
2023-01-24 08:40:26.852325: step: 812/526, loss: 0.0011635440168902278
2023-01-24 08:40:27.924812: step: 816/526, loss: 6.616743485210463e-05
2023-01-24 08:40:28.987672: step: 820/526, loss: 0.0033114461693912745
2023-01-24 08:40:30.069567: step: 824/526, loss: 0.001900022616609931
2023-01-24 08:40:31.136323: step: 828/526, loss: 0.002874800469726324
2023-01-24 08:40:32.200501: step: 832/526, loss: 0.0013039191253483295
2023-01-24 08:40:33.264408: step: 836/526, loss: 0.0022603338584303856
2023-01-24 08:40:34.320548: step: 840/526, loss: 0.008574477396905422
2023-01-24 08:40:35.393389: step: 844/526, loss: 2.190962368331384e-05
2023-01-24 08:40:36.459549: step: 848/526, loss: 0.004295805934816599
2023-01-24 08:40:37.537334: step: 852/526, loss: 0.003289527492597699
2023-01-24 08:40:38.601718: step: 856/526, loss: 0.005523450206965208
2023-01-24 08:40:39.685069: step: 860/526, loss: 0.0016545332036912441
2023-01-24 08:40:40.759900: step: 864/526, loss: 0.0038719524163752794
2023-01-24 08:40:41.837647: step: 868/526, loss: 0.008013435639441013
2023-01-24 08:40:42.915435: step: 872/526, loss: 0.000556713028345257
2023-01-24 08:40:43.974687: step: 876/526, loss: 0.003172683995217085
2023-01-24 08:40:45.029695: step: 880/526, loss: 0.00021134625421836972
2023-01-24 08:40:46.094243: step: 884/526, loss: 0.0016915379092097282
2023-01-24 08:40:47.148288: step: 888/526, loss: 0.0017804628005251288
2023-01-24 08:40:48.220725: step: 892/526, loss: 0.0026804746594280005
2023-01-24 08:40:49.276684: step: 896/526, loss: 0.014465970918536186
2023-01-24 08:40:50.367303: step: 900/526, loss: 0.007293372415006161
2023-01-24 08:40:51.462388: step: 904/526, loss: 0.006600086577236652
2023-01-24 08:40:52.511470: step: 908/526, loss: 0.0007659685797989368
2023-01-24 08:40:53.573407: step: 912/526, loss: 0.00018975512648466974
2023-01-24 08:40:54.657976: step: 916/526, loss: 0.005219451151788235
2023-01-24 08:40:55.732482: step: 920/526, loss: 0.001895737717859447
2023-01-24 08:40:56.804960: step: 924/526, loss: 0.000740026356652379
2023-01-24 08:40:57.871473: step: 928/526, loss: 0.006662923377007246
2023-01-24 08:40:58.955377: step: 932/526, loss: 0.0013474173611029983
2023-01-24 08:41:00.020256: step: 936/526, loss: 0.002233668463304639
2023-01-24 08:41:01.074237: step: 940/526, loss: 0.0038880868814885616
2023-01-24 08:41:02.140172: step: 944/526, loss: 0.011396192014217377
2023-01-24 08:41:03.210462: step: 948/526, loss: 0.0037230944726616144
2023-01-24 08:41:04.286890: step: 952/526, loss: 0.0034529289696365595
2023-01-24 08:41:05.350983: step: 956/526, loss: 0.004115849733352661
2023-01-24 08:41:06.419435: step: 960/526, loss: 0.0022732792422175407
2023-01-24 08:41:07.518094: step: 964/526, loss: 0.007227274589240551
2023-01-24 08:41:08.594457: step: 968/526, loss: 0.0020248712971806526
2023-01-24 08:41:09.656772: step: 972/526, loss: 0.005124710500240326
2023-01-24 08:41:10.729452: step: 976/526, loss: 0.00014067483425606042
2023-01-24 08:41:11.808523: step: 980/526, loss: 0.021593360230326653
2023-01-24 08:41:12.899814: step: 984/526, loss: 0.005690298974514008
2023-01-24 08:41:13.982968: step: 988/526, loss: 0.009877980686724186
2023-01-24 08:41:15.044860: step: 992/526, loss: 0.004007709678262472
2023-01-24 08:41:16.115667: step: 996/526, loss: 0.000538425229024142
2023-01-24 08:41:17.167765: step: 1000/526, loss: 0.002025959547609091
2023-01-24 08:41:18.236311: step: 1004/526, loss: 0.005184090230613947
2023-01-24 08:41:19.295702: step: 1008/526, loss: 0.005766283720731735
2023-01-24 08:41:20.360126: step: 1012/526, loss: 0.0011326140956953168
2023-01-24 08:41:21.444007: step: 1016/526, loss: 0.0030917273834347725
2023-01-24 08:41:22.492898: step: 1020/526, loss: 0.006913172546774149
2023-01-24 08:41:23.578804: step: 1024/526, loss: 0.002029015449807048
2023-01-24 08:41:24.636289: step: 1028/526, loss: 0.004745482467114925
2023-01-24 08:41:25.699289: step: 1032/526, loss: 0.0005182833410799503
2023-01-24 08:41:26.745818: step: 1036/526, loss: 0.0001842290657805279
2023-01-24 08:41:27.814622: step: 1040/526, loss: 0.0011114665539935231
2023-01-24 08:41:28.882670: step: 1044/526, loss: 0.0016391983954235911
2023-01-24 08:41:29.939336: step: 1048/526, loss: 0.0013662866549566388
2023-01-24 08:41:31.006374: step: 1052/526, loss: 0.0003473217075224966
2023-01-24 08:41:32.074087: step: 1056/526, loss: 0.0001806815853342414
2023-01-24 08:41:33.153633: step: 1060/526, loss: 4.835849176743068e-05
2023-01-24 08:41:34.225208: step: 1064/526, loss: 0.013094817288219929
2023-01-24 08:41:35.284618: step: 1068/526, loss: 0.00040008482756093144
2023-01-24 08:41:36.353879: step: 1072/526, loss: 0.019123949110507965
2023-01-24 08:41:37.415758: step: 1076/526, loss: 0.006047382019460201
2023-01-24 08:41:38.490978: step: 1080/526, loss: 0.0006867832271382213
2023-01-24 08:41:39.563744: step: 1084/526, loss: 0.0026648559141904116
2023-01-24 08:41:40.627496: step: 1088/526, loss: 0.0013683350989595056
2023-01-24 08:41:41.692095: step: 1092/526, loss: 2.264326212753076e-06
2023-01-24 08:41:42.782018: step: 1096/526, loss: 0.03855287283658981
2023-01-24 08:41:43.837170: step: 1100/526, loss: 0.0012021881993860006
2023-01-24 08:41:44.909786: step: 1104/526, loss: 0.003373167011886835
2023-01-24 08:41:45.973116: step: 1108/526, loss: 0.00037629471626132727
2023-01-24 08:41:47.031856: step: 1112/526, loss: 0.0031781475991010666
2023-01-24 08:41:48.094676: step: 1116/526, loss: 0.003785996697843075
2023-01-24 08:41:49.161698: step: 1120/526, loss: 0.008271785452961922
2023-01-24 08:41:50.259433: step: 1124/526, loss: 0.004597133491188288
2023-01-24 08:41:51.322722: step: 1128/526, loss: 0.00392197398468852
2023-01-24 08:41:52.371522: step: 1132/526, loss: 0.0005994778475724161
2023-01-24 08:41:53.443307: step: 1136/526, loss: 0.003938647452741861
2023-01-24 08:41:54.548647: step: 1140/526, loss: 0.0038212265353649855
2023-01-24 08:41:55.617652: step: 1144/526, loss: 0.00294835539534688
2023-01-24 08:41:56.707429: step: 1148/526, loss: 0.007164319511502981
2023-01-24 08:41:57.783410: step: 1152/526, loss: 2.6576759410090744e-05
2023-01-24 08:41:58.846174: step: 1156/526, loss: 0.0032929328735917807
2023-01-24 08:41:59.908243: step: 1160/526, loss: 0.00012819006224162877
2023-01-24 08:42:00.972118: step: 1164/526, loss: 0.003070864826440811
2023-01-24 08:42:02.041164: step: 1168/526, loss: 0.0036052772775292397
2023-01-24 08:42:03.098129: step: 1172/526, loss: 0.0032888096757233143
2023-01-24 08:42:04.160937: step: 1176/526, loss: 0.004941609688103199
2023-01-24 08:42:05.224022: step: 1180/526, loss: 0.00017654371913522482
2023-01-24 08:42:06.286522: step: 1184/526, loss: 0.00016994915495160967
2023-01-24 08:42:07.359594: step: 1188/526, loss: 0.0024686739780008793
2023-01-24 08:42:08.421637: step: 1192/526, loss: 0.002231811173260212
2023-01-24 08:42:09.482383: step: 1196/526, loss: 0.0019481753697618842
2023-01-24 08:42:10.545328: step: 1200/526, loss: 0.005375716369599104
2023-01-24 08:42:11.613472: step: 1204/526, loss: 0.011711164377629757
2023-01-24 08:42:12.692119: step: 1208/526, loss: 0.0010047671385109425
2023-01-24 08:42:13.775251: step: 1212/526, loss: 0.00487243477255106
2023-01-24 08:42:14.839000: step: 1216/526, loss: 0.007283544633537531
2023-01-24 08:42:15.914370: step: 1220/526, loss: 0.002689747139811516
2023-01-24 08:42:16.979886: step: 1224/526, loss: 0.012705979868769646
2023-01-24 08:42:18.050580: step: 1228/526, loss: 0.0022503305226564407
2023-01-24 08:42:19.113115: step: 1232/526, loss: 0.0039559220895171165
2023-01-24 08:42:20.189023: step: 1236/526, loss: 0.002737303264439106
2023-01-24 08:42:21.265648: step: 1240/526, loss: 0.006115739233791828
2023-01-24 08:42:22.349021: step: 1244/526, loss: 0.0063429721631109715
2023-01-24 08:42:23.420957: step: 1248/526, loss: 0.004716824274510145
2023-01-24 08:42:24.494802: step: 1252/526, loss: 0.0030517836567014456
2023-01-24 08:42:25.558431: step: 1256/526, loss: 0.01928587630391121
2023-01-24 08:42:26.626499: step: 1260/526, loss: 0.0038072813767939806
2023-01-24 08:42:27.693585: step: 1264/526, loss: 0.009622993879020214
2023-01-24 08:42:28.754139: step: 1268/526, loss: 0.002055876422673464
2023-01-24 08:42:29.828741: step: 1272/526, loss: 0.0011493697529658675
2023-01-24 08:42:30.895547: step: 1276/526, loss: 0.002703531412407756
2023-01-24 08:42:31.984572: step: 1280/526, loss: 0.015853796154260635
2023-01-24 08:42:33.067951: step: 1284/526, loss: 0.0015725308330729604
2023-01-24 08:42:34.137002: step: 1288/526, loss: 4.404744231578661e-06
2023-01-24 08:42:35.206159: step: 1292/526, loss: 0.002780213486403227
2023-01-24 08:42:36.281646: step: 1296/526, loss: 0.001070625614374876
2023-01-24 08:42:37.356136: step: 1300/526, loss: 0.0006446315092034638
2023-01-24 08:42:38.415294: step: 1304/526, loss: 3.962144910474308e-05
2023-01-24 08:42:39.482392: step: 1308/526, loss: 0.0008306821109727025
2023-01-24 08:42:40.551538: step: 1312/526, loss: 0.004246818833053112
2023-01-24 08:42:41.611142: step: 1316/526, loss: 0.0076587446965277195
2023-01-24 08:42:42.680577: step: 1320/526, loss: 0.006820672657340765
2023-01-24 08:42:43.754179: step: 1324/526, loss: 0.0016523490194231272
2023-01-24 08:42:44.799365: step: 1328/526, loss: 0.0062357583083212376
2023-01-24 08:42:45.894803: step: 1332/526, loss: 0.0062552401795983315
2023-01-24 08:42:46.955740: step: 1336/526, loss: 0.00016951176803559065
2023-01-24 08:42:48.016955: step: 1340/526, loss: 0.0019224941497668624
2023-01-24 08:42:49.071799: step: 1344/526, loss: 0.014512458816170692
2023-01-24 08:42:50.132209: step: 1348/526, loss: 0.0014699813909828663
2023-01-24 08:42:51.191737: step: 1352/526, loss: 2.0005210899398662e-05
2023-01-24 08:42:52.245946: step: 1356/526, loss: 0.00202702428214252
2023-01-24 08:42:53.303136: step: 1360/526, loss: 0.011726485565304756
2023-01-24 08:42:54.373068: step: 1364/526, loss: 0.00832261424511671
2023-01-24 08:42:55.435786: step: 1368/526, loss: 9.265230801247526e-06
2023-01-24 08:42:56.510399: step: 1372/526, loss: 0.003955105319619179
2023-01-24 08:42:57.578951: step: 1376/526, loss: 0.0012653687736019492
2023-01-24 08:42:58.644112: step: 1380/526, loss: 0.0023829981219023466
2023-01-24 08:42:59.719372: step: 1384/526, loss: 0.0024809204041957855
2023-01-24 08:43:00.780912: step: 1388/526, loss: 0.0013029719702899456
2023-01-24 08:43:01.857259: step: 1392/526, loss: 0.009118972346186638
2023-01-24 08:43:02.906536: step: 1396/526, loss: 0.010650471784174442
2023-01-24 08:43:03.961272: step: 1400/526, loss: 0.000396323564928025
2023-01-24 08:43:05.014398: step: 1404/526, loss: 0.00012168128159828484
2023-01-24 08:43:06.072103: step: 1408/526, loss: 0.016102680936455727
2023-01-24 08:43:07.125886: step: 1412/526, loss: 0.013401266187429428
2023-01-24 08:43:08.196078: step: 1416/526, loss: 0.003793393261730671
2023-01-24 08:43:09.265783: step: 1420/526, loss: 0.000843375688418746
2023-01-24 08:43:10.350568: step: 1424/526, loss: 0.008080673404037952
2023-01-24 08:43:11.420269: step: 1428/526, loss: 0.005300865508615971
2023-01-24 08:43:12.484933: step: 1432/526, loss: 0.004407604690641165
2023-01-24 08:43:13.575179: step: 1436/526, loss: 8.405968401348218e-05
2023-01-24 08:43:14.623627: step: 1440/526, loss: 0.00010387034126324579
2023-01-24 08:43:15.685191: step: 1444/526, loss: 0.008012795820832253
2023-01-24 08:43:16.756226: step: 1448/526, loss: 0.00514595489948988
2023-01-24 08:43:17.832782: step: 1452/526, loss: 0.000801900343503803
2023-01-24 08:43:18.899398: step: 1456/526, loss: 0.00414240313693881
2023-01-24 08:43:19.971952: step: 1460/526, loss: 0.02435186132788658
2023-01-24 08:43:21.033860: step: 1464/526, loss: 0.0
2023-01-24 08:43:22.096243: step: 1468/526, loss: 0.004740624222904444
2023-01-24 08:43:23.152867: step: 1472/526, loss: 0.019496286287903786
2023-01-24 08:43:24.210820: step: 1476/526, loss: 0.0034376918338239193
2023-01-24 08:43:25.271041: step: 1480/526, loss: 1.0285552889399696e-05
2023-01-24 08:43:26.343433: step: 1484/526, loss: 0.0026216916739940643
2023-01-24 08:43:27.397978: step: 1488/526, loss: 0.0010655343066900969
2023-01-24 08:43:28.469699: step: 1492/526, loss: 0.00011161769361933693
2023-01-24 08:43:29.536323: step: 1496/526, loss: 0.00897468626499176
2023-01-24 08:43:30.605473: step: 1500/526, loss: 0.003293408080935478
2023-01-24 08:43:31.672528: step: 1504/526, loss: 0.007067199796438217
2023-01-24 08:43:32.748789: step: 1508/526, loss: 0.004014688543975353
2023-01-24 08:43:33.813808: step: 1512/526, loss: 0.00434343796223402
2023-01-24 08:43:34.891612: step: 1516/526, loss: 0.011981457471847534
2023-01-24 08:43:35.961086: step: 1520/526, loss: 0.00016639447130728513
2023-01-24 08:43:37.023661: step: 1524/526, loss: 0.013790886849164963
2023-01-24 08:43:38.081472: step: 1528/526, loss: 0.00020824189414270222
2023-01-24 08:43:39.145451: step: 1532/526, loss: 0.0012086728820577264
2023-01-24 08:43:40.216738: step: 1536/526, loss: 0.04319644719362259
2023-01-24 08:43:41.287567: step: 1540/526, loss: 0.011203614994883537
2023-01-24 08:43:42.365210: step: 1544/526, loss: 0.005573430098593235
2023-01-24 08:43:43.429905: step: 1548/526, loss: 0.045756854116916656
2023-01-24 08:43:44.502376: step: 1552/526, loss: 0.011881670914590359
2023-01-24 08:43:45.568487: step: 1556/526, loss: 0.011266571469604969
2023-01-24 08:43:46.634777: step: 1560/526, loss: 0.0001165743960882537
2023-01-24 08:43:47.688163: step: 1564/526, loss: 0.006261349655687809
2023-01-24 08:43:48.748917: step: 1568/526, loss: 0.0
2023-01-24 08:43:49.831551: step: 1572/526, loss: 0.004248825833201408
2023-01-24 08:43:50.894055: step: 1576/526, loss: 0.0038028049748390913
2023-01-24 08:43:51.963177: step: 1580/526, loss: 0.0007728872587904334
2023-01-24 08:43:53.035614: step: 1584/526, loss: 0.015161864459514618
2023-01-24 08:43:54.107592: step: 1588/526, loss: 0.004029589239507914
2023-01-24 08:43:55.169840: step: 1592/526, loss: 0.0016217725351452827
2023-01-24 08:43:56.240171: step: 1596/526, loss: 0.02138603664934635
2023-01-24 08:43:57.300427: step: 1600/526, loss: 8.453485497739166e-05
2023-01-24 08:43:58.347719: step: 1604/526, loss: 0.03369440510869026
2023-01-24 08:43:59.445123: step: 1608/526, loss: 0.014535359106957912
2023-01-24 08:44:00.527897: step: 1612/526, loss: 0.0036891575437039137
2023-01-24 08:44:01.597265: step: 1616/526, loss: 0.010762116871774197
2023-01-24 08:44:02.673063: step: 1620/526, loss: 2.4214376281861405e-08
2023-01-24 08:44:03.747434: step: 1624/526, loss: 0.004704159218817949
2023-01-24 08:44:04.813620: step: 1628/526, loss: 0.008366054855287075
2023-01-24 08:44:05.871787: step: 1632/526, loss: 0.007280722260475159
2023-01-24 08:44:06.930186: step: 1636/526, loss: 0.0005960150738246739
2023-01-24 08:44:07.991496: step: 1640/526, loss: 0.009195374324917793
2023-01-24 08:44:09.053340: step: 1644/526, loss: 0.0010494155576452613
2023-01-24 08:44:10.113232: step: 1648/526, loss: 0.0012640261556953192
2023-01-24 08:44:11.182385: step: 1652/526, loss: 0.0015899322461336851
2023-01-24 08:44:12.245055: step: 1656/526, loss: 0.0003950555110350251
2023-01-24 08:44:13.327865: step: 1660/526, loss: 0.011772912926971912
2023-01-24 08:44:14.408055: step: 1664/526, loss: 0.0038584391586482525
2023-01-24 08:44:15.482210: step: 1668/526, loss: 0.004730330314487219
2023-01-24 08:44:16.539393: step: 1672/526, loss: 0.001573633635416627
2023-01-24 08:44:17.609276: step: 1676/526, loss: 0.003443900728598237
2023-01-24 08:44:18.673685: step: 1680/526, loss: 0.0012091778917238116
2023-01-24 08:44:19.731570: step: 1684/526, loss: 0.00231906003318727
2023-01-24 08:44:20.821899: step: 1688/526, loss: 0.005402205046266317
2023-01-24 08:44:21.884233: step: 1692/526, loss: 0.02763788402080536
2023-01-24 08:44:22.969211: step: 1696/526, loss: 0.012245790101587772
2023-01-24 08:44:24.041628: step: 1700/526, loss: 0.002371357986703515
2023-01-24 08:44:25.103625: step: 1704/526, loss: 0.0001006985257845372
2023-01-24 08:44:26.167441: step: 1708/526, loss: 0.00019306459580548108
2023-01-24 08:44:27.241298: step: 1712/526, loss: 0.0002702659403439611
2023-01-24 08:44:28.309197: step: 1716/526, loss: 0.00045841519022360444
2023-01-24 08:44:29.385528: step: 1720/526, loss: 0.009159048087894917
2023-01-24 08:44:30.460127: step: 1724/526, loss: 0.0026574034709483385
2023-01-24 08:44:31.520954: step: 1728/526, loss: 0.0026909809093922377
2023-01-24 08:44:32.585951: step: 1732/526, loss: 0.0038029202260077
2023-01-24 08:44:33.660207: step: 1736/526, loss: 0.0006001431029289961
2023-01-24 08:44:34.737159: step: 1740/526, loss: 0.02261241339147091
2023-01-24 08:44:35.798440: step: 1744/526, loss: 0.004342994187027216
2023-01-24 08:44:36.864701: step: 1748/526, loss: 0.0018650016281753778
2023-01-24 08:44:37.920289: step: 1752/526, loss: 0.0003598167095333338
2023-01-24 08:44:38.974387: step: 1756/526, loss: 0.0018435847014188766
2023-01-24 08:44:40.048362: step: 1760/526, loss: 0.000660406774841249
2023-01-24 08:44:41.125974: step: 1764/526, loss: 0.007831739261746407
2023-01-24 08:44:42.200654: step: 1768/526, loss: 0.009272853843867779
2023-01-24 08:44:43.286103: step: 1772/526, loss: 0.0011731403646990657
2023-01-24 08:44:44.339271: step: 1776/526, loss: 0.0036302516236901283
2023-01-24 08:44:45.416346: step: 1780/526, loss: 0.0040840343572199345
2023-01-24 08:44:46.493136: step: 1784/526, loss: 0.00019168520520906895
2023-01-24 08:44:47.555355: step: 1788/526, loss: 0.003376036649569869
2023-01-24 08:44:48.617264: step: 1792/526, loss: 0.0020819026976823807
2023-01-24 08:44:49.669163: step: 1796/526, loss: 0.011754350736737251
2023-01-24 08:44:50.734315: step: 1800/526, loss: 0.005021013785153627
2023-01-24 08:44:51.796319: step: 1804/526, loss: 0.0022896593436598778
2023-01-24 08:44:52.877931: step: 1808/526, loss: 0.00749589316546917
2023-01-24 08:44:53.943881: step: 1812/526, loss: 0.00020558516553137451
2023-01-24 08:44:55.014725: step: 1816/526, loss: 2.550763383624144e-05
2023-01-24 08:44:56.097551: step: 1820/526, loss: 0.002272322541102767
2023-01-24 08:44:57.165330: step: 1824/526, loss: 0.004736368544399738
2023-01-24 08:44:58.225928: step: 1828/526, loss: 0.0037193482276052237
2023-01-24 08:44:59.286428: step: 1832/526, loss: 0.000213428313145414
2023-01-24 08:45:00.370732: step: 1836/526, loss: 0.004171588458120823
2023-01-24 08:45:01.443221: step: 1840/526, loss: 0.002222105860710144
2023-01-24 08:45:02.508179: step: 1844/526, loss: 0.007533005438745022
2023-01-24 08:45:03.581748: step: 1848/526, loss: 0.0026535443030297756
2023-01-24 08:45:04.659041: step: 1852/526, loss: 0.001969150034710765
2023-01-24 08:45:05.716668: step: 1856/526, loss: 6.986632070038468e-05
2023-01-24 08:45:06.764400: step: 1860/526, loss: 0.000547143688891083
2023-01-24 08:45:07.835565: step: 1864/526, loss: 0.01142438966780901
2023-01-24 08:45:08.910180: step: 1868/526, loss: 0.00744243897497654
2023-01-24 08:45:09.975798: step: 1872/526, loss: 0.008655395358800888
2023-01-24 08:45:11.061838: step: 1876/526, loss: 0.004293091129511595
2023-01-24 08:45:12.126310: step: 1880/526, loss: 0.0027628173120319843
2023-01-24 08:45:13.192844: step: 1884/526, loss: 3.396796455490403e-05
2023-01-24 08:45:14.261435: step: 1888/526, loss: 0.0010185787687078118
2023-01-24 08:45:15.347711: step: 1892/526, loss: 0.0015422259457409382
2023-01-24 08:45:16.423188: step: 1896/526, loss: 0.007528111804276705
2023-01-24 08:45:17.496484: step: 1900/526, loss: 0.0017608848866075277
2023-01-24 08:45:18.567432: step: 1904/526, loss: 0.00040609354618936777
2023-01-24 08:45:19.656982: step: 1908/526, loss: 0.0008595864637754858
2023-01-24 08:45:20.737153: step: 1912/526, loss: 0.0008734037401154637
2023-01-24 08:45:21.806360: step: 1916/526, loss: 0.004083402454853058
2023-01-24 08:45:22.858965: step: 1920/526, loss: 0.014334799721837044
2023-01-24 08:45:23.933940: step: 1924/526, loss: 0.0008618760039098561
2023-01-24 08:45:24.997563: step: 1928/526, loss: 0.004487842321395874
2023-01-24 08:45:26.050637: step: 1932/526, loss: 0.0019823003094643354
2023-01-24 08:45:27.116955: step: 1936/526, loss: 0.011330187320709229
2023-01-24 08:45:28.179530: step: 1940/526, loss: 0.004352687858045101
2023-01-24 08:45:29.247458: step: 1944/526, loss: 0.00017388183914590627
2023-01-24 08:45:30.321995: step: 1948/526, loss: 0.007207114715129137
2023-01-24 08:45:31.380981: step: 1952/526, loss: 0.005646920762956142
2023-01-24 08:45:32.465045: step: 1956/526, loss: 0.0038300473242998123
2023-01-24 08:45:33.543258: step: 1960/526, loss: 0.010747403837740421
2023-01-24 08:45:34.609402: step: 1964/526, loss: 0.0013486654497683048
2023-01-24 08:45:35.698838: step: 1968/526, loss: 0.010565017350018024
2023-01-24 08:45:36.769814: step: 1972/526, loss: 0.005794962402433157
2023-01-24 08:45:37.847176: step: 1976/526, loss: 0.009057620540261269
2023-01-24 08:45:38.912246: step: 1980/526, loss: 0.029522715136408806
2023-01-24 08:45:39.995549: step: 1984/526, loss: 0.006884191185235977
2023-01-24 08:45:41.076716: step: 1988/526, loss: 0.004918457008898258
2023-01-24 08:45:42.151698: step: 1992/526, loss: 0.02453145571053028
2023-01-24 08:45:43.249316: step: 1996/526, loss: 0.004031417425721884
2023-01-24 08:45:44.322596: step: 2000/526, loss: 0.0009891398949548602
2023-01-24 08:45:45.394010: step: 2004/526, loss: 0.00017858234059531242
2023-01-24 08:45:46.479167: step: 2008/526, loss: 0.0069486224092543125
2023-01-24 08:45:47.539589: step: 2012/526, loss: 0.0012803251156583428
2023-01-24 08:45:48.628201: step: 2016/526, loss: 0.005079634487628937
2023-01-24 08:45:49.696293: step: 2020/526, loss: 0.0021159108728170395
2023-01-24 08:45:50.770120: step: 2024/526, loss: 0.005618637893348932
2023-01-24 08:45:51.858189: step: 2028/526, loss: 0.00835944339632988
2023-01-24 08:45:52.931843: step: 2032/526, loss: 0.0010824339697137475
2023-01-24 08:45:53.990822: step: 2036/526, loss: 0.0034036103170365095
2023-01-24 08:45:55.057639: step: 2040/526, loss: 1.948093449755106e-05
2023-01-24 08:45:56.163944: step: 2044/526, loss: 0.001862821402028203
2023-01-24 08:45:57.243106: step: 2048/526, loss: 0.000306715868646279
2023-01-24 08:45:58.331640: step: 2052/526, loss: 0.004162499215453863
2023-01-24 08:45:59.397843: step: 2056/526, loss: 0.005048396531492472
2023-01-24 08:46:00.481112: step: 2060/526, loss: 0.001531820627860725
2023-01-24 08:46:01.552358: step: 2064/526, loss: 0.007688785437494516
2023-01-24 08:46:02.621515: step: 2068/526, loss: 0.0029728268273174763
2023-01-24 08:46:03.705409: step: 2072/526, loss: 0.03896621987223625
2023-01-24 08:46:04.789287: step: 2076/526, loss: 0.0004868621763307601
2023-01-24 08:46:05.870245: step: 2080/526, loss: 0.0005071642808616161
2023-01-24 08:46:06.952716: step: 2084/526, loss: 0.004734321031719446
2023-01-24 08:46:08.006749: step: 2088/526, loss: 0.000133141249534674
2023-01-24 08:46:09.082982: step: 2092/526, loss: 0.0053694709204137325
2023-01-24 08:46:10.172186: step: 2096/526, loss: 0.005157975479960442
2023-01-24 08:46:11.254715: step: 2100/526, loss: 0.0001623660937184468
2023-01-24 08:46:12.313829: step: 2104/526, loss: 0.0005135132814757526
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3636456814868805, 'r': 0.27049166440769856, 'f1': 0.3102265661433235}, 'combined': 0.2285879961056068, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3617363895336569, 'r': 0.22405812965625407, 'f1': 0.2767181194511703}, 'combined': 0.1509371560642747, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33924028128950695, 'r': 0.29096130387638924, 'f1': 0.3132514956953159}, 'combined': 0.2308168915649696, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36086488420836754, 'r': 0.25950576302632833, 'f1': 0.3019050548033814}, 'combined': 0.16467548443820804, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3636185432000531, 'r': 0.3153200649761371, 'f1': 0.33775137041143144}, 'combined': 0.2488694308294758, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3651925055313105, 'r': 0.2759826254060956, 'f1': 0.3143814586439421}, 'combined': 0.17148079562396842, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 08:48:55.293115: step: 4/526, loss: 0.002307166112586856
2023-01-24 08:48:56.366774: step: 8/526, loss: 0.00016390436212532222
2023-01-24 08:48:57.418772: step: 12/526, loss: 0.003355986438691616
2023-01-24 08:48:58.455761: step: 16/526, loss: 0.0032070777378976345
2023-01-24 08:48:59.505554: step: 20/526, loss: 0.000874431396368891
2023-01-24 08:49:00.572708: step: 24/526, loss: 0.0017243623733520508
2023-01-24 08:49:01.617798: step: 28/526, loss: 0.0002141358272638172
2023-01-24 08:49:02.691367: step: 32/526, loss: 0.004313035402446985
2023-01-24 08:49:03.737510: step: 36/526, loss: 0.009496822021901608
2023-01-24 08:49:04.788679: step: 40/526, loss: 0.015115546062588692
2023-01-24 08:49:05.852557: step: 44/526, loss: 0.0006571476114913821
2023-01-24 08:49:06.925633: step: 48/526, loss: 0.0005053265485912561
2023-01-24 08:49:07.988052: step: 52/526, loss: 0.007660075090825558
2023-01-24 08:49:09.054852: step: 56/526, loss: 0.002688624430447817
2023-01-24 08:49:10.118451: step: 60/526, loss: 0.009465493261814117
2023-01-24 08:49:11.193143: step: 64/526, loss: 0.003573128255084157
2023-01-24 08:49:12.254170: step: 68/526, loss: 0.0008480855613015592
2023-01-24 08:49:13.308458: step: 72/526, loss: 0.010601562447845936
2023-01-24 08:49:14.384443: step: 76/526, loss: 0.004917262587696314
2023-01-24 08:49:15.442324: step: 80/526, loss: 0.012845807708799839
2023-01-24 08:49:16.499375: step: 84/526, loss: 0.001812226721085608
2023-01-24 08:49:17.567675: step: 88/526, loss: 0.002933220937848091
2023-01-24 08:49:18.628180: step: 92/526, loss: 0.002123152371495962
2023-01-24 08:49:19.681932: step: 96/526, loss: 2.8769592972821556e-05
2023-01-24 08:49:20.755919: step: 100/526, loss: 0.007094432599842548
2023-01-24 08:49:21.819241: step: 104/526, loss: 0.0007247141329571605
2023-01-24 08:49:22.872852: step: 108/526, loss: 4.0705032006371766e-05
2023-01-24 08:49:23.926070: step: 112/526, loss: 0.004695121664553881
2023-01-24 08:49:24.991064: step: 116/526, loss: 7.974659820320085e-05
2023-01-24 08:49:26.042140: step: 120/526, loss: 0.0008255448192358017
2023-01-24 08:49:27.108572: step: 124/526, loss: 0.0070709241554141045
2023-01-24 08:49:28.176600: step: 128/526, loss: 0.0016856011934578419
2023-01-24 08:49:29.242487: step: 132/526, loss: 1.3539904102799483e-05
2023-01-24 08:49:30.314682: step: 136/526, loss: 0.007703426294028759
2023-01-24 08:49:31.381420: step: 140/526, loss: 0.0006940584280528128
2023-01-24 08:49:32.449994: step: 144/526, loss: 0.007444867864251137
2023-01-24 08:49:33.540716: step: 148/526, loss: 0.006417728029191494
2023-01-24 08:49:34.600212: step: 152/526, loss: 0.00017218659922946244
2023-01-24 08:49:35.678088: step: 156/526, loss: 0.0003996709128841758
2023-01-24 08:49:36.733247: step: 160/526, loss: 0.00028717415989376605
2023-01-24 08:49:37.791807: step: 164/526, loss: 0.0036907135508954525
2023-01-24 08:49:38.858188: step: 168/526, loss: 0.0024098502472043037
2023-01-24 08:49:39.930182: step: 172/526, loss: 0.005466167815029621
2023-01-24 08:49:40.995347: step: 176/526, loss: 0.0004699561686720699
2023-01-24 08:49:42.047901: step: 180/526, loss: 0.000760965165682137
2023-01-24 08:49:43.149270: step: 184/526, loss: 0.00011297981109237298
2023-01-24 08:49:44.220258: step: 188/526, loss: 0.008172375150024891
2023-01-24 08:49:45.288664: step: 192/526, loss: 0.0004477706679608673
2023-01-24 08:49:46.356392: step: 196/526, loss: 0.0038734604604542255
2023-01-24 08:49:47.447526: step: 200/526, loss: 0.014641694724559784
2023-01-24 08:49:48.504730: step: 204/526, loss: 0.0037262861151248217
2023-01-24 08:49:49.579624: step: 208/526, loss: 0.00356103852391243
2023-01-24 08:49:50.633994: step: 212/526, loss: 0.001980154076591134
2023-01-24 08:49:51.711444: step: 216/526, loss: 0.0034438883885741234
2023-01-24 08:49:52.782856: step: 220/526, loss: 0.004583067260682583
2023-01-24 08:49:53.867615: step: 224/526, loss: 0.002736735623329878
2023-01-24 08:49:54.935771: step: 228/526, loss: 0.013606034219264984
2023-01-24 08:49:56.006053: step: 232/526, loss: 0.004091767128556967
2023-01-24 08:49:57.071793: step: 236/526, loss: 0.0037918041925877333
2023-01-24 08:49:58.133899: step: 240/526, loss: 5.625628909911029e-05
2023-01-24 08:49:59.202076: step: 244/526, loss: 0.0
2023-01-24 08:50:00.274256: step: 248/526, loss: 0.00024778343504294753
2023-01-24 08:50:01.343628: step: 252/526, loss: 3.603561708587222e-05
2023-01-24 08:50:02.383840: step: 256/526, loss: 5.9348498325562105e-05
2023-01-24 08:50:03.470141: step: 260/526, loss: 0.0035893144086003304
2023-01-24 08:50:04.536423: step: 264/526, loss: 0.006451513152569532
2023-01-24 08:50:05.616910: step: 268/526, loss: 0.021374007686972618
2023-01-24 08:50:06.710295: step: 272/526, loss: 0.0026988228783011436
2023-01-24 08:50:07.778941: step: 276/526, loss: 0.0035164428409188986
2023-01-24 08:50:08.844630: step: 280/526, loss: 0.0035909716971218586
2023-01-24 08:50:09.906266: step: 284/526, loss: 0.005486360285431147
2023-01-24 08:50:10.973414: step: 288/526, loss: 0.0019414079142734408
2023-01-24 08:50:12.066161: step: 292/526, loss: 0.007578476332128048
2023-01-24 08:50:13.144799: step: 296/526, loss: 6.2344761317945085e-06
2023-01-24 08:50:14.235700: step: 300/526, loss: 0.0033236127346754074
2023-01-24 08:50:15.289570: step: 304/526, loss: 0.010147430002689362
2023-01-24 08:50:16.356331: step: 308/526, loss: 0.002167791360989213
2023-01-24 08:50:17.429995: step: 312/526, loss: 0.00039145632763393223
2023-01-24 08:50:18.484845: step: 316/526, loss: 0.02178303897380829
2023-01-24 08:50:19.550599: step: 320/526, loss: 0.004287473391741514
2023-01-24 08:50:20.617851: step: 324/526, loss: 0.006246659904718399
2023-01-24 08:50:21.691372: step: 328/526, loss: 0.002571484539657831
2023-01-24 08:50:22.756733: step: 332/526, loss: 0.0004141709068790078
2023-01-24 08:50:23.829206: step: 336/526, loss: 7.810800161678344e-05
2023-01-24 08:50:24.909062: step: 340/526, loss: 0.005919633898884058
2023-01-24 08:50:25.994600: step: 344/526, loss: 0.0003430758079048246
2023-01-24 08:50:27.056083: step: 348/526, loss: 0.0013421847252175212
2023-01-24 08:50:28.106995: step: 352/526, loss: 0.0011762031354010105
2023-01-24 08:50:29.187110: step: 356/526, loss: 0.00042755200411193073
2023-01-24 08:50:30.237213: step: 360/526, loss: 1.2852225950155116e-07
2023-01-24 08:50:31.314861: step: 364/526, loss: 0.0021133606787770987
2023-01-24 08:50:32.371558: step: 368/526, loss: 0.0013215214712545276
2023-01-24 08:50:33.443007: step: 372/526, loss: 0.002105488209053874
2023-01-24 08:50:34.522687: step: 376/526, loss: 0.005996872205287218
2023-01-24 08:50:35.598278: step: 380/526, loss: 0.0012232906883582473
2023-01-24 08:50:36.662025: step: 384/526, loss: 0.00020889371808152646
2023-01-24 08:50:37.750942: step: 388/526, loss: 0.0007443691720254719
2023-01-24 08:50:38.840712: step: 392/526, loss: 0.017321476712822914
2023-01-24 08:50:39.926657: step: 396/526, loss: 0.0005412495229393244
2023-01-24 08:50:41.000617: step: 400/526, loss: 0.00012738963414449245
2023-01-24 08:50:42.062120: step: 404/526, loss: 0.006571083329617977
2023-01-24 08:50:43.145769: step: 408/526, loss: 0.0068222819827497005
2023-01-24 08:50:44.220297: step: 412/526, loss: 0.0012285879347473383
2023-01-24 08:50:45.303461: step: 416/526, loss: 1.7125488511737785e-06
2023-01-24 08:50:46.396581: step: 420/526, loss: 0.0077162547968328
2023-01-24 08:50:47.481721: step: 424/526, loss: 0.021344834938645363
2023-01-24 08:50:48.561282: step: 428/526, loss: 0.0022521985229104757
2023-01-24 08:50:49.639225: step: 432/526, loss: 0.0032798433676362038
2023-01-24 08:50:50.709192: step: 436/526, loss: 0.006046767346560955
2023-01-24 08:50:51.787770: step: 440/526, loss: 0.017067667096853256
2023-01-24 08:50:52.843399: step: 444/526, loss: 0.0008532463689334691
2023-01-24 08:50:53.912951: step: 448/526, loss: 0.0032414861489087343
2023-01-24 08:50:55.007489: step: 452/526, loss: 0.004999093245714903
2023-01-24 08:50:56.078767: step: 456/526, loss: 0.0040327440947294235
2023-01-24 08:50:57.157929: step: 460/526, loss: 0.0020243411418050528
2023-01-24 08:50:58.230282: step: 464/526, loss: 0.0022450743708759546
2023-01-24 08:50:59.295474: step: 468/526, loss: 3.589477637433447e-05
2023-01-24 08:51:00.360645: step: 472/526, loss: 0.0010907717514783144
2023-01-24 08:51:01.426946: step: 476/526, loss: 0.0004973181057721376
2023-01-24 08:51:02.504400: step: 480/526, loss: 0.010154790244996548
2023-01-24 08:51:03.579366: step: 484/526, loss: 0.0004196219961158931
2023-01-24 08:51:04.648877: step: 488/526, loss: 0.005656337831169367
2023-01-24 08:51:05.730442: step: 492/526, loss: 0.004369535017758608
2023-01-24 08:51:06.808051: step: 496/526, loss: 0.0001062605733750388
2023-01-24 08:51:07.879963: step: 500/526, loss: 0.004484541714191437
2023-01-24 08:51:08.941410: step: 504/526, loss: 0.00677845673635602
2023-01-24 08:51:10.019094: step: 508/526, loss: 0.0002809167781379074
2023-01-24 08:51:11.101360: step: 512/526, loss: 0.0029430161230266094
2023-01-24 08:51:12.165607: step: 516/526, loss: 0.0005283295176923275
2023-01-24 08:51:13.242377: step: 520/526, loss: 0.006898556370288134
2023-01-24 08:51:14.312938: step: 524/526, loss: 0.008260136470198631
2023-01-24 08:51:15.390019: step: 528/526, loss: 0.008318664506077766
2023-01-24 08:51:16.436635: step: 532/526, loss: 5.350386709324084e-05
2023-01-24 08:51:17.494721: step: 536/526, loss: 0.0066989148035645485
2023-01-24 08:51:18.554690: step: 540/526, loss: 0.0002137723204214126
2023-01-24 08:51:19.629753: step: 544/526, loss: 0.011100714094936848
2023-01-24 08:51:20.720654: step: 548/526, loss: 0.0029905603732913733
2023-01-24 08:51:21.783905: step: 552/526, loss: 4.41963056800887e-05
2023-01-24 08:51:22.855799: step: 556/526, loss: 0.019678698852658272
2023-01-24 08:51:23.919838: step: 560/526, loss: 0.0003933538682758808
2023-01-24 08:51:24.999002: step: 564/526, loss: 0.004244382027536631
2023-01-24 08:51:26.074631: step: 568/526, loss: 0.0026927590370178223
2023-01-24 08:51:27.148804: step: 572/526, loss: 0.0013517928309738636
2023-01-24 08:51:28.241623: step: 576/526, loss: 0.0028755960520356894
2023-01-24 08:51:29.308614: step: 580/526, loss: 0.0009696271736174822
2023-01-24 08:51:30.375986: step: 584/526, loss: 0.002408436266705394
2023-01-24 08:51:31.444976: step: 588/526, loss: 0.005607598926872015
2023-01-24 08:51:32.508624: step: 592/526, loss: 0.0017189460340887308
2023-01-24 08:51:33.576645: step: 596/526, loss: 0.00016286822210531682
2023-01-24 08:51:34.640939: step: 600/526, loss: 0.00045663630589842796
2023-01-24 08:51:35.709580: step: 604/526, loss: 0.007644603028893471
2023-01-24 08:51:36.783994: step: 608/526, loss: 0.003453565528616309
2023-01-24 08:51:37.890023: step: 612/526, loss: 0.0024117999710142612
2023-01-24 08:51:38.953299: step: 616/526, loss: 0.0017960545374080539
2023-01-24 08:51:40.009203: step: 620/526, loss: 0.0016979104839265347
2023-01-24 08:51:41.082317: step: 624/526, loss: 0.0016665789298713207
2023-01-24 08:51:42.143215: step: 628/526, loss: 0.009512514807283878
2023-01-24 08:51:43.229957: step: 632/526, loss: 0.0005530774360522628
2023-01-24 08:51:44.299894: step: 636/526, loss: 0.0023438313510268927
2023-01-24 08:51:45.357985: step: 640/526, loss: 0.0009590488043613732
2023-01-24 08:51:46.414380: step: 644/526, loss: 0.004253941588103771
2023-01-24 08:51:47.504822: step: 648/526, loss: 0.0003688369761221111
2023-01-24 08:51:48.563696: step: 652/526, loss: 0.0001511715236119926
2023-01-24 08:51:49.625875: step: 656/526, loss: 7.127510457394237e-07
2023-01-24 08:51:50.705062: step: 660/526, loss: 0.0003850888169836253
2023-01-24 08:51:51.767232: step: 664/526, loss: 0.0011288495734333992
2023-01-24 08:51:52.860194: step: 668/526, loss: 0.004587870091199875
2023-01-24 08:51:53.939131: step: 672/526, loss: 0.019386034458875656
2023-01-24 08:51:54.997846: step: 676/526, loss: 0.021321089938282967
2023-01-24 08:51:56.060352: step: 680/526, loss: 0.0010789288207888603
2023-01-24 08:51:57.140142: step: 684/526, loss: 0.0037535966839641333
2023-01-24 08:51:58.222978: step: 688/526, loss: 0.0023384590167552233
2023-01-24 08:51:59.275394: step: 692/526, loss: 0.0070309690199792385
2023-01-24 08:52:00.338339: step: 696/526, loss: 0.00038893689634278417
2023-01-24 08:52:01.416279: step: 700/526, loss: 4.2838233639486134e-05
2023-01-24 08:52:02.482363: step: 704/526, loss: 0.009444604627788067
2023-01-24 08:52:03.542166: step: 708/526, loss: 0.010152694769203663
2023-01-24 08:52:04.623385: step: 712/526, loss: 0.0028974285814911127
2023-01-24 08:52:05.710854: step: 716/526, loss: 0.0032435518223792315
2023-01-24 08:52:06.779862: step: 720/526, loss: 0.0010638185776770115
2023-01-24 08:52:07.848599: step: 724/526, loss: 0.0033046293538063765
2023-01-24 08:52:08.918733: step: 728/526, loss: 0.013791908510029316
2023-01-24 08:52:09.982430: step: 732/526, loss: 2.527087417547591e-06
2023-01-24 08:52:11.043489: step: 736/526, loss: 0.00329029094427824
2023-01-24 08:52:12.114848: step: 740/526, loss: 0.0009505374473519623
2023-01-24 08:52:13.182212: step: 744/526, loss: 5.103231046632573e-07
2023-01-24 08:52:14.247935: step: 748/526, loss: 0.0021410330664366484
2023-01-24 08:52:15.322535: step: 752/526, loss: 0.0019387867068871856
2023-01-24 08:52:16.401207: step: 756/526, loss: 0.005651320796459913
2023-01-24 08:52:17.481611: step: 760/526, loss: 0.008545869030058384
2023-01-24 08:52:18.561071: step: 764/526, loss: 0.0011596831027418375
2023-01-24 08:52:19.621555: step: 768/526, loss: 0.0032350532710552216
2023-01-24 08:52:20.686647: step: 772/526, loss: 0.012262407690286636
2023-01-24 08:52:21.756551: step: 776/526, loss: 0.0034392091911286116
2023-01-24 08:52:22.827962: step: 780/526, loss: 0.02677333354949951
2023-01-24 08:52:23.898545: step: 784/526, loss: 8.11841255199397e-06
2023-01-24 08:52:24.950648: step: 788/526, loss: 1.0902474059548695e-05
2023-01-24 08:52:26.026506: step: 792/526, loss: 0.005818450823426247
2023-01-24 08:52:27.090911: step: 796/526, loss: 0.002057104604318738
2023-01-24 08:52:28.177880: step: 800/526, loss: 0.004009247291833162
2023-01-24 08:52:29.251933: step: 804/526, loss: 0.006768904626369476
2023-01-24 08:52:30.313984: step: 808/526, loss: 0.01550119835883379
2023-01-24 08:52:31.386772: step: 812/526, loss: 0.002734885783866048
2023-01-24 08:52:32.470263: step: 816/526, loss: 0.0004063333908561617
2023-01-24 08:52:33.540152: step: 820/526, loss: 0.005199453327804804
2023-01-24 08:52:34.609158: step: 824/526, loss: 0.00032127118902280927
2023-01-24 08:52:35.693282: step: 828/526, loss: 0.0037883908953517675
2023-01-24 08:52:36.773923: step: 832/526, loss: 0.0018259456846863031
2023-01-24 08:52:37.850305: step: 836/526, loss: 0.012628414668142796
2023-01-24 08:52:38.925184: step: 840/526, loss: 0.0022392510436475277
2023-01-24 08:52:39.985642: step: 844/526, loss: 0.0010122767416760325
2023-01-24 08:52:41.070343: step: 848/526, loss: 0.003944905940443277
2023-01-24 08:52:42.153783: step: 852/526, loss: 0.00800758134573698
2023-01-24 08:52:43.225488: step: 856/526, loss: 0.009272287599742413
2023-01-24 08:52:44.313370: step: 860/526, loss: 0.007457132916897535
2023-01-24 08:52:45.397601: step: 864/526, loss: 0.008085169829428196
2023-01-24 08:52:46.462402: step: 868/526, loss: 0.018574386835098267
2023-01-24 08:52:47.525841: step: 872/526, loss: 0.0013659705873578787
2023-01-24 08:52:48.598180: step: 876/526, loss: 0.0022928675170987844
2023-01-24 08:52:49.664918: step: 880/526, loss: 2.8176586056360975e-05
2023-01-24 08:52:50.754890: step: 884/526, loss: 0.0028159264475107193
2023-01-24 08:52:51.826230: step: 888/526, loss: 0.002168482169508934
2023-01-24 08:52:52.912736: step: 892/526, loss: 0.002853300189599395
2023-01-24 08:52:53.988894: step: 896/526, loss: 0.00027688051341101527
2023-01-24 08:52:55.055748: step: 900/526, loss: 0.0013850006507709622
2023-01-24 08:52:56.128700: step: 904/526, loss: 0.001309840939939022
2023-01-24 08:52:57.184070: step: 908/526, loss: 7.723381713731214e-05
2023-01-24 08:52:58.273289: step: 912/526, loss: 0.0020622939337044954
2023-01-24 08:52:59.345169: step: 916/526, loss: 0.0009144251816906035
2023-01-24 08:53:00.403902: step: 920/526, loss: 0.0067610410042107105
2023-01-24 08:53:01.461369: step: 924/526, loss: 0.005464465357363224
2023-01-24 08:53:02.521557: step: 928/526, loss: 0.00013922154903411865
2023-01-24 08:53:03.571832: step: 932/526, loss: 0.0022986449766904116
2023-01-24 08:53:04.656984: step: 936/526, loss: 0.004184935707598925
2023-01-24 08:53:05.730045: step: 940/526, loss: 0.0007891824934631586
2023-01-24 08:53:06.816091: step: 944/526, loss: 0.004375447519123554
2023-01-24 08:53:07.890534: step: 948/526, loss: 0.0005012222100049257
2023-01-24 08:53:08.946858: step: 952/526, loss: 0.014180784113705158
2023-01-24 08:53:10.030360: step: 956/526, loss: 0.005079489666968584
2023-01-24 08:53:11.110951: step: 960/526, loss: 0.0028964467346668243
2023-01-24 08:53:12.179029: step: 964/526, loss: 0.0024710383731871843
2023-01-24 08:53:13.263683: step: 968/526, loss: 0.026737647131085396
2023-01-24 08:53:14.340454: step: 972/526, loss: 0.017084207385778427
2023-01-24 08:53:15.405439: step: 976/526, loss: 0.011491220444440842
2023-01-24 08:53:16.475811: step: 980/526, loss: 0.0007972380262799561
2023-01-24 08:53:17.553448: step: 984/526, loss: 0.0014202527236193419
2023-01-24 08:53:18.663982: step: 988/526, loss: 0.0015676483744755387
2023-01-24 08:53:19.738498: step: 992/526, loss: 0.0031679163221269846
2023-01-24 08:53:20.802014: step: 996/526, loss: 0.0033847338054329157
2023-01-24 08:53:21.862858: step: 1000/526, loss: 0.002245976123958826
2023-01-24 08:53:22.922057: step: 1004/526, loss: 0.0019594307523220778
2023-01-24 08:53:23.991577: step: 1008/526, loss: 0.0007398559246212244
2023-01-24 08:53:25.069569: step: 1012/526, loss: 0.0002759054768830538
2023-01-24 08:53:26.132040: step: 1016/526, loss: 0.0007809091475792229
2023-01-24 08:53:27.207275: step: 1020/526, loss: 7.455585728166625e-05
2023-01-24 08:53:28.275816: step: 1024/526, loss: 0.006111177150160074
2023-01-24 08:53:29.347877: step: 1028/526, loss: 0.0006516418652608991
2023-01-24 08:53:30.416782: step: 1032/526, loss: 0.0012602662900462747
2023-01-24 08:53:31.477481: step: 1036/526, loss: 0.00102605065330863
2023-01-24 08:53:32.563451: step: 1040/526, loss: 0.0005091484053991735
2023-01-24 08:53:33.638556: step: 1044/526, loss: 0.029566867277026176
2023-01-24 08:53:34.702345: step: 1048/526, loss: 0.00036553433164954185
2023-01-24 08:53:35.772330: step: 1052/526, loss: 0.0033097942359745502
2023-01-24 08:53:36.844944: step: 1056/526, loss: 0.001217966666445136
2023-01-24 08:53:37.919530: step: 1060/526, loss: 0.0014171070652082562
2023-01-24 08:53:38.976467: step: 1064/526, loss: 0.023390233516693115
2023-01-24 08:53:40.044863: step: 1068/526, loss: 0.0004296435508877039
2023-01-24 08:53:41.117815: step: 1072/526, loss: 0.0016299390699714422
2023-01-24 08:53:42.189697: step: 1076/526, loss: 0.0017074395436793566
2023-01-24 08:53:43.260529: step: 1080/526, loss: 0.00136851635761559
2023-01-24 08:53:44.346028: step: 1084/526, loss: 0.0011942698620259762
2023-01-24 08:53:45.435376: step: 1088/526, loss: 0.006335163488984108
2023-01-24 08:53:46.492001: step: 1092/526, loss: 1.2097493709006812e-05
2023-01-24 08:53:47.559648: step: 1096/526, loss: 0.006443346384912729
2023-01-24 08:53:48.625708: step: 1100/526, loss: 0.002692027948796749
2023-01-24 08:53:49.701489: step: 1104/526, loss: 0.0007058934425003827
2023-01-24 08:53:50.787086: step: 1108/526, loss: 0.010884067043662071
2023-01-24 08:53:51.873466: step: 1112/526, loss: 0.011060385033488274
2023-01-24 08:53:52.949076: step: 1116/526, loss: 0.0005565279861912131
2023-01-24 08:53:54.016553: step: 1120/526, loss: 0.0027569830417633057
2023-01-24 08:53:55.086323: step: 1124/526, loss: 0.007407648488879204
2023-01-24 08:53:56.162023: step: 1128/526, loss: 0.0076655857264995575
2023-01-24 08:53:57.225175: step: 1132/526, loss: 0.0008564227027818561
2023-01-24 08:53:58.287823: step: 1136/526, loss: 0.002139363205060363
2023-01-24 08:53:59.350314: step: 1140/526, loss: 0.00011179518332937732
2023-01-24 08:54:00.414839: step: 1144/526, loss: 0.00026275331038050354
2023-01-24 08:54:01.504344: step: 1148/526, loss: 0.017415888607501984
2023-01-24 08:54:02.583836: step: 1152/526, loss: 0.0012456434778869152
2023-01-24 08:54:03.647459: step: 1156/526, loss: 0.00034680109820328653
2023-01-24 08:54:04.694505: step: 1160/526, loss: 0.0007098432979546487
2023-01-24 08:54:05.786575: step: 1164/526, loss: 3.0032533686608076e-05
2023-01-24 08:54:06.865794: step: 1168/526, loss: 0.0028228273149579763
2023-01-24 08:54:07.949865: step: 1172/526, loss: 0.003709799377247691
2023-01-24 08:54:09.024596: step: 1176/526, loss: 0.02493387646973133
2023-01-24 08:54:10.092726: step: 1180/526, loss: 0.01921447180211544
2023-01-24 08:54:11.159435: step: 1184/526, loss: 1.3776319974567741e-05
2023-01-24 08:54:12.221668: step: 1188/526, loss: 0.0022829556837677956
2023-01-24 08:54:13.314314: step: 1192/526, loss: 0.00014040459063835442
2023-01-24 08:54:14.392353: step: 1196/526, loss: 0.002130881417542696
2023-01-24 08:54:15.445243: step: 1200/526, loss: 0.00022746642935089767
2023-01-24 08:54:16.520338: step: 1204/526, loss: 0.0020031214226037264
2023-01-24 08:54:17.579418: step: 1208/526, loss: 0.000355652766302228
2023-01-24 08:54:18.646573: step: 1212/526, loss: 0.0020097908563911915
2023-01-24 08:54:19.720485: step: 1216/526, loss: 0.0001625945296837017
2023-01-24 08:54:20.809656: step: 1220/526, loss: 0.006345596630126238
2023-01-24 08:54:21.872238: step: 1224/526, loss: 0.00043828244088217616
2023-01-24 08:54:22.927045: step: 1228/526, loss: 0.0003940975875593722
2023-01-24 08:54:23.996042: step: 1232/526, loss: 0.0013128803111612797
2023-01-24 08:54:25.058963: step: 1236/526, loss: 0.004025301430374384
2023-01-24 08:54:26.135960: step: 1240/526, loss: 0.009535791352391243
2023-01-24 08:54:27.214549: step: 1244/526, loss: 0.0067873080261051655
2023-01-24 08:54:28.288826: step: 1248/526, loss: 0.0031826540362089872
2023-01-24 08:54:29.347906: step: 1252/526, loss: 0.0003247931017540395
2023-01-24 08:54:30.440611: step: 1256/526, loss: 0.0019273733487352729
2023-01-24 08:54:31.504230: step: 1260/526, loss: 0.0014707774389535189
2023-01-24 08:54:32.555314: step: 1264/526, loss: 0.004232752602547407
2023-01-24 08:54:33.620027: step: 1268/526, loss: 0.000627980858553201
2023-01-24 08:54:34.682657: step: 1272/526, loss: 0.011762239970266819
2023-01-24 08:54:35.754586: step: 1276/526, loss: 0.00855042040348053
2023-01-24 08:54:36.822403: step: 1280/526, loss: 0.0014893842162564397
2023-01-24 08:54:37.893110: step: 1284/526, loss: 0.00023896177299320698
2023-01-24 08:54:38.981647: step: 1288/526, loss: 0.0037234509363770485
2023-01-24 08:54:40.057579: step: 1292/526, loss: 0.0015185344964265823
2023-01-24 08:54:41.121707: step: 1296/526, loss: 0.009883145801723003
2023-01-24 08:54:42.203693: step: 1300/526, loss: 0.006715449504554272
2023-01-24 08:54:43.312124: step: 1304/526, loss: 0.010385330766439438
2023-01-24 08:54:44.372755: step: 1308/526, loss: 0.016307534649968147
2023-01-24 08:54:45.457610: step: 1312/526, loss: 0.00171584018971771
2023-01-24 08:54:46.514964: step: 1316/526, loss: 0.004585589747875929
2023-01-24 08:54:47.563555: step: 1320/526, loss: 0.0017021321691572666
2023-01-24 08:54:48.645189: step: 1324/526, loss: 0.0023780791088938713
2023-01-24 08:54:49.702457: step: 1328/526, loss: 0.0005325642414391041
2023-01-24 08:54:50.786952: step: 1332/526, loss: 0.004799291025847197
2023-01-24 08:54:51.845435: step: 1336/526, loss: 8.75878322403878e-05
2023-01-24 08:54:52.929037: step: 1340/526, loss: 0.013781948946416378
2023-01-24 08:54:54.001148: step: 1344/526, loss: 0.0018188146641477942
2023-01-24 08:54:55.073801: step: 1348/526, loss: 0.0011055388022214174
2023-01-24 08:54:56.138358: step: 1352/526, loss: 0.0021018851548433304
2023-01-24 08:54:57.193162: step: 1356/526, loss: 0.0001546824350953102
2023-01-24 08:54:58.249438: step: 1360/526, loss: 0.0022100184578448534
2023-01-24 08:54:59.307173: step: 1364/526, loss: 0.002128913765773177
2023-01-24 08:55:00.372149: step: 1368/526, loss: 0.0008413918549194932
2023-01-24 08:55:01.439770: step: 1372/526, loss: 0.00020194821991026402
2023-01-24 08:55:02.503724: step: 1376/526, loss: 0.01098920963704586
2023-01-24 08:55:03.576797: step: 1380/526, loss: 0.002626180648803711
2023-01-24 08:55:04.649692: step: 1384/526, loss: 8.364782843273133e-06
2023-01-24 08:55:05.741844: step: 1388/526, loss: 0.00019631536270026118
2023-01-24 08:55:06.827432: step: 1392/526, loss: 0.024831082671880722
2023-01-24 08:55:07.916347: step: 1396/526, loss: 0.0033678554464131594
2023-01-24 08:55:08.986171: step: 1400/526, loss: 0.005119773093611002
2023-01-24 08:55:10.043145: step: 1404/526, loss: 0.0038946541026234627
2023-01-24 08:55:11.103175: step: 1408/526, loss: 5.344546298147179e-05
2023-01-24 08:55:12.178403: step: 1412/526, loss: 0.002227138727903366
2023-01-24 08:55:13.264731: step: 1416/526, loss: 0.0013618605444207788
2023-01-24 08:55:14.352868: step: 1420/526, loss: 0.0016318444395437837
2023-01-24 08:55:15.414288: step: 1424/526, loss: 0.003463602624833584
2023-01-24 08:55:16.477697: step: 1428/526, loss: 0.0008891662582755089
2023-01-24 08:55:17.564156: step: 1432/526, loss: 0.001142619177699089
2023-01-24 08:55:18.635396: step: 1436/526, loss: 7.592178735649213e-05
2023-01-24 08:55:19.725411: step: 1440/526, loss: 0.00045594715629704297
2023-01-24 08:55:20.788939: step: 1444/526, loss: 0.004796857479959726
2023-01-24 08:55:21.851297: step: 1448/526, loss: 0.00995884370058775
2023-01-24 08:55:22.913481: step: 1452/526, loss: 0.0018776168581098318
2023-01-24 08:55:24.001263: step: 1456/526, loss: 0.002360767684876919
2023-01-24 08:55:25.067680: step: 1460/526, loss: 0.004143232014030218
2023-01-24 08:55:26.122034: step: 1464/526, loss: 0.00925966165959835
2023-01-24 08:55:27.188453: step: 1468/526, loss: 0.0022747707553207874
2023-01-24 08:55:28.248224: step: 1472/526, loss: 0.0030110818333923817
2023-01-24 08:55:29.307836: step: 1476/526, loss: 0.000270563003141433
2023-01-24 08:55:30.368160: step: 1480/526, loss: 0.00017031615425366908
2023-01-24 08:55:31.430945: step: 1484/526, loss: 0.0049527850933372974
2023-01-24 08:55:32.503379: step: 1488/526, loss: 0.0016987328417599201
2023-01-24 08:55:33.577210: step: 1492/526, loss: 0.005898380186408758
2023-01-24 08:55:34.638612: step: 1496/526, loss: 0.004284883849322796
2023-01-24 08:55:35.724471: step: 1500/526, loss: 0.025537550449371338
2023-01-24 08:55:36.793490: step: 1504/526, loss: 0.004737743642181158
2023-01-24 08:55:37.858106: step: 1508/526, loss: 0.00871719978749752
2023-01-24 08:55:38.921670: step: 1512/526, loss: 0.00036977906711399555
2023-01-24 08:55:39.995880: step: 1516/526, loss: 0.0009836264653131366
2023-01-24 08:55:41.062290: step: 1520/526, loss: 0.00043516108416952193
2023-01-24 08:55:42.124487: step: 1524/526, loss: 0.05500594899058342
2023-01-24 08:55:43.209794: step: 1528/526, loss: 0.00010957517224596813
2023-01-24 08:55:44.291431: step: 1532/526, loss: 0.003940837923437357
2023-01-24 08:55:45.356966: step: 1536/526, loss: 0.00016839402087498456
2023-01-24 08:55:46.425723: step: 1540/526, loss: 0.00221430417150259
2023-01-24 08:55:47.488946: step: 1544/526, loss: 0.002151322551071644
2023-01-24 08:55:48.543786: step: 1548/526, loss: 0.002618568716570735
2023-01-24 08:55:49.607939: step: 1552/526, loss: 0.0002220207534264773
2023-01-24 08:55:50.668341: step: 1556/526, loss: 0.0
2023-01-24 08:55:51.733794: step: 1560/526, loss: 0.0033717863261699677
2023-01-24 08:55:52.802072: step: 1564/526, loss: 1.969084951269906e-05
2023-01-24 08:55:53.875584: step: 1568/526, loss: 0.001348881283774972
2023-01-24 08:55:54.943989: step: 1572/526, loss: 0.003764993976801634
2023-01-24 08:55:56.020416: step: 1576/526, loss: 0.0006136494339443743
2023-01-24 08:55:57.103159: step: 1580/526, loss: 0.0022987457923591137
2023-01-24 08:55:58.170190: step: 1584/526, loss: 0.014885510317981243
2023-01-24 08:55:59.248572: step: 1588/526, loss: 0.006264332681894302
2023-01-24 08:56:00.349295: step: 1592/526, loss: 1.3827666407451034e-05
2023-01-24 08:56:01.406703: step: 1596/526, loss: 0.013956621289253235
2023-01-24 08:56:02.476219: step: 1600/526, loss: 0.0021332809701561928
2023-01-24 08:56:03.534700: step: 1604/526, loss: 0.00043565905070863664
2023-01-24 08:56:04.608366: step: 1608/526, loss: 0.00025349942734465003
2023-01-24 08:56:05.691013: step: 1612/526, loss: 0.0009876987896859646
2023-01-24 08:56:06.769992: step: 1616/526, loss: 0.0023905502166599035
2023-01-24 08:56:07.855101: step: 1620/526, loss: 0.0028823192697018385
2023-01-24 08:56:08.916653: step: 1624/526, loss: 0.008391663432121277
2023-01-24 08:56:09.984978: step: 1628/526, loss: 0.01414255890995264
2023-01-24 08:56:11.058425: step: 1632/526, loss: 0.0006167968967929482
2023-01-24 08:56:12.132435: step: 1636/526, loss: 0.0017983202124014497
2023-01-24 08:56:13.208085: step: 1640/526, loss: 0.00035625157761387527
2023-01-24 08:56:14.267963: step: 1644/526, loss: 0.001247352221980691
2023-01-24 08:56:15.339535: step: 1648/526, loss: 0.00615895027294755
2023-01-24 08:56:16.409710: step: 1652/526, loss: 0.00038407949614338577
2023-01-24 08:56:17.479069: step: 1656/526, loss: 0.0007547169225290418
2023-01-24 08:56:18.560533: step: 1660/526, loss: 0.0030446143355220556
2023-01-24 08:56:19.633049: step: 1664/526, loss: 0.00211614603176713
2023-01-24 08:56:20.697992: step: 1668/526, loss: 1.129423708334798e-05
2023-01-24 08:56:21.762354: step: 1672/526, loss: 6.556462750495484e-08
2023-01-24 08:56:22.830714: step: 1676/526, loss: 0.0011379700154066086
2023-01-24 08:56:23.896194: step: 1680/526, loss: 0.0006366141024045646
2023-01-24 08:56:24.952575: step: 1684/526, loss: 0.0068187415599823
2023-01-24 08:56:26.017221: step: 1688/526, loss: 0.005435027182102203
2023-01-24 08:56:27.094842: step: 1692/526, loss: 0.006031684577465057
2023-01-24 08:56:28.174422: step: 1696/526, loss: 0.004352853633463383
2023-01-24 08:56:29.246605: step: 1700/526, loss: 0.0036465846933424473
2023-01-24 08:56:30.326281: step: 1704/526, loss: 0.0008612232632003725
2023-01-24 08:56:31.380784: step: 1708/526, loss: 0.002266576746478677
2023-01-24 08:56:32.451850: step: 1712/526, loss: 1.0622950867400505e-05
2023-01-24 08:56:33.513781: step: 1716/526, loss: 0.002228684024885297
2023-01-24 08:56:34.572869: step: 1720/526, loss: 0.00016539690841455013
2023-01-24 08:56:35.639152: step: 1724/526, loss: 0.004582252353429794
2023-01-24 08:56:36.722774: step: 1728/526, loss: 0.0024971964303404093
2023-01-24 08:56:37.788385: step: 1732/526, loss: 0.000973179005086422
2023-01-24 08:56:38.860597: step: 1736/526, loss: 0.0020890154410153627
2023-01-24 08:56:39.945583: step: 1740/526, loss: 0.0013916163006797433
2023-01-24 08:56:41.019715: step: 1744/526, loss: 0.001978084212169051
2023-01-24 08:56:42.112369: step: 1748/526, loss: 0.0027675561141222715
2023-01-24 08:56:43.180745: step: 1752/526, loss: 0.0013488027034327388
2023-01-24 08:56:44.262998: step: 1756/526, loss: 0.005854002665728331
2023-01-24 08:56:45.353418: step: 1760/526, loss: 0.007177778985351324
2023-01-24 08:56:46.447830: step: 1764/526, loss: 0.0071561397053301334
2023-01-24 08:56:47.535869: step: 1768/526, loss: 0.011648480780422688
2023-01-24 08:56:48.628486: step: 1772/526, loss: 0.005798365455120802
2023-01-24 08:56:49.699626: step: 1776/526, loss: 0.0035777639131993055
2023-01-24 08:56:50.786856: step: 1780/526, loss: 0.002151547698304057
2023-01-24 08:56:51.874925: step: 1784/526, loss: 0.0028241644613444805
2023-01-24 08:56:52.940295: step: 1788/526, loss: 0.002040019491687417
2023-01-24 08:56:54.014291: step: 1792/526, loss: 0.002346805762499571
2023-01-24 08:56:55.082753: step: 1796/526, loss: 0.0003907376085408032
2023-01-24 08:56:56.156092: step: 1800/526, loss: 0.007825076580047607
2023-01-24 08:56:57.237773: step: 1804/526, loss: 0.000653119059279561
2023-01-24 08:56:58.313735: step: 1808/526, loss: 0.005234704352915287
2023-01-24 08:56:59.370390: step: 1812/526, loss: 0.0002433751942589879
2023-01-24 08:57:00.427024: step: 1816/526, loss: 3.3592212275834754e-05
2023-01-24 08:57:01.494326: step: 1820/526, loss: 0.0006443400634452701
2023-01-24 08:57:02.574688: step: 1824/526, loss: 0.005711184814572334
2023-01-24 08:57:03.636468: step: 1828/526, loss: 0.005810832604765892
2023-01-24 08:57:04.707795: step: 1832/526, loss: 0.012061625719070435
2023-01-24 08:57:05.786800: step: 1836/526, loss: 0.027010422199964523
2023-01-24 08:57:06.855147: step: 1840/526, loss: 0.002008101437240839
2023-01-24 08:57:07.934582: step: 1844/526, loss: 0.0037057814188301563
2023-01-24 08:57:08.998353: step: 1848/526, loss: 0.002416230970993638
2023-01-24 08:57:10.067198: step: 1852/526, loss: 6.940684397704899e-05
2023-01-24 08:57:11.123875: step: 1856/526, loss: 0.003448176896199584
2023-01-24 08:57:12.204860: step: 1860/526, loss: 0.020395131781697273
2023-01-24 08:57:13.291314: step: 1864/526, loss: 0.0014182326849550009
2023-01-24 08:57:14.364412: step: 1868/526, loss: 0.002631265437230468
2023-01-24 08:57:15.464285: step: 1872/526, loss: 0.004197416361421347
2023-01-24 08:57:16.542280: step: 1876/526, loss: 0.0028786426410079002
2023-01-24 08:57:17.635613: step: 1880/526, loss: 0.005287399515509605
2023-01-24 08:57:18.702637: step: 1884/526, loss: 0.00788356363773346
2023-01-24 08:57:19.811669: step: 1888/526, loss: 0.007930414751172066
2023-01-24 08:57:20.890594: step: 1892/526, loss: 0.0024912424851208925
2023-01-24 08:57:21.975699: step: 1896/526, loss: 0.0017342055216431618
2023-01-24 08:57:23.053533: step: 1900/526, loss: 0.004057242069393396
2023-01-24 08:57:24.130697: step: 1904/526, loss: 0.0010492629371583462
2023-01-24 08:57:25.190078: step: 1908/526, loss: 0.0007356642163358629
2023-01-24 08:57:26.271679: step: 1912/526, loss: 0.0019300456624478102
2023-01-24 08:57:27.332460: step: 1916/526, loss: 0.00762151600793004
2023-01-24 08:57:28.395153: step: 1920/526, loss: 0.012163740582764149
2023-01-24 08:57:29.460666: step: 1924/526, loss: 0.0008196496637538075
2023-01-24 08:57:30.537301: step: 1928/526, loss: 0.009409359656274319
2023-01-24 08:57:31.613273: step: 1932/526, loss: 0.0034837662242352962
2023-01-24 08:57:32.676760: step: 1936/526, loss: 0.0024080027360469103
2023-01-24 08:57:33.726837: step: 1940/526, loss: 0.005544229876250029
2023-01-24 08:57:34.810037: step: 1944/526, loss: 2.0633342501241714e-06
2023-01-24 08:57:35.871504: step: 1948/526, loss: 0.0016030978877097368
2023-01-24 08:57:36.940798: step: 1952/526, loss: 0.001350992708466947
2023-01-24 08:57:38.010246: step: 1956/526, loss: 0.004187397193163633
2023-01-24 08:57:39.087473: step: 1960/526, loss: 0.0009545682114548981
2023-01-24 08:57:40.138896: step: 1964/526, loss: 0.0011566587490960956
2023-01-24 08:57:41.199459: step: 1968/526, loss: 0.0005285569932311773
2023-01-24 08:57:42.283250: step: 1972/526, loss: 0.008675693534314632
2023-01-24 08:57:43.362375: step: 1976/526, loss: 0.006488036829978228
2023-01-24 08:57:44.452076: step: 1980/526, loss: 0.001760836923494935
2023-01-24 08:57:45.525949: step: 1984/526, loss: 0.0003029238432645798
2023-01-24 08:57:46.592262: step: 1988/526, loss: 0.002028706483542919
2023-01-24 08:57:47.665290: step: 1992/526, loss: 0.00293004815466702
2023-01-24 08:57:48.726809: step: 1996/526, loss: 0.003305745078250766
2023-01-24 08:57:49.801747: step: 2000/526, loss: 0.002126662991940975
2023-01-24 08:57:50.858476: step: 2004/526, loss: 0.0017672862159088254
2023-01-24 08:57:51.947234: step: 2008/526, loss: 0.004866019822657108
2023-01-24 08:57:53.023413: step: 2012/526, loss: 0.009832726791501045
2023-01-24 08:57:54.077835: step: 2016/526, loss: 0.0006234565516933799
2023-01-24 08:57:55.167904: step: 2020/526, loss: 0.023399246856570244
2023-01-24 08:57:56.247943: step: 2024/526, loss: 0.0049022892490029335
2023-01-24 08:57:57.325629: step: 2028/526, loss: 0.003801533719524741
2023-01-24 08:57:58.397179: step: 2032/526, loss: 0.0014570566127076745
2023-01-24 08:57:59.450877: step: 2036/526, loss: 0.0033299934584647417
2023-01-24 08:58:00.517287: step: 2040/526, loss: 0.0007682955474592745
2023-01-24 08:58:01.568284: step: 2044/526, loss: 0.007122586015611887
2023-01-24 08:58:02.631999: step: 2048/526, loss: 0.001749532762914896
2023-01-24 08:58:03.710624: step: 2052/526, loss: 4.950724814989371e-06
2023-01-24 08:58:04.771707: step: 2056/526, loss: 0.00013669295003637671
2023-01-24 08:58:05.859689: step: 2060/526, loss: 0.0047966125421226025
2023-01-24 08:58:06.924361: step: 2064/526, loss: 0.006963830441236496
2023-01-24 08:58:07.991037: step: 2068/526, loss: 0.00017712145927362144
2023-01-24 08:58:09.048057: step: 2072/526, loss: 0.003607033286243677
2023-01-24 08:58:10.107492: step: 2076/526, loss: 0.0011266947258263826
2023-01-24 08:58:11.174256: step: 2080/526, loss: 0.0041417754255235195
2023-01-24 08:58:12.242043: step: 2084/526, loss: 1.3134545042703394e-05
2023-01-24 08:58:13.323228: step: 2088/526, loss: 6.524119271489326e-06
2023-01-24 08:58:14.404162: step: 2092/526, loss: 0.0020126684103161097
2023-01-24 08:58:15.468644: step: 2096/526, loss: 0.003926699049770832
2023-01-24 08:58:16.538439: step: 2100/526, loss: 0.02189287543296814
2023-01-24 08:58:17.598267: step: 2104/526, loss: 0.005942977499216795
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3646287713558706, 'r': 0.2719148143128219, 'f1': 0.3115197981366459}, 'combined': 0.2295409038901601, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3612028550358196, 'r': 0.22405812965625407, 'f1': 0.2765618698072114}, 'combined': 0.15085192898575167, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33774583071113906, 'r': 0.29096130387638924, 'f1': 0.3126128585990971}, 'combined': 0.23034631686249257, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3642456260935068, 'r': 0.26293668708854245, 'f1': 0.30540892559806254}, 'combined': 0.16658668668985227, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.359921202261224, 'r': 0.31484568167442933, 'f1': 0.3358778830818305}, 'combined': 0.24748896648134877, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36495194621835503, 'r': 0.2768025282845529, 'f1': 0.31482327098336765}, 'combined': 0.17172178417274597, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 09:01:00.225998: step: 4/526, loss: 0.0030837920494377613
2023-01-24 09:01:01.272084: step: 8/526, loss: 5.392525054048747e-06
2023-01-24 09:01:02.338022: step: 12/526, loss: 3.723362533492036e-05
2023-01-24 09:01:03.369959: step: 16/526, loss: 3.468860813882202e-05
2023-01-24 09:01:04.416853: step: 20/526, loss: 1.832795959444411e-07
2023-01-24 09:01:05.478604: step: 24/526, loss: 0.001636696164496243
2023-01-24 09:01:06.548238: step: 28/526, loss: 0.01823437213897705
2023-01-24 09:01:07.605290: step: 32/526, loss: 0.002591481665149331
2023-01-24 09:01:08.662260: step: 36/526, loss: 3.17294652631972e-05
2023-01-24 09:01:09.741151: step: 40/526, loss: 0.005457828287035227
2023-01-24 09:01:10.810587: step: 44/526, loss: 0.008973308838903904
2023-01-24 09:01:11.872106: step: 48/526, loss: 0.002074422314763069
2023-01-24 09:01:12.930074: step: 52/526, loss: 0.002159965457394719
2023-01-24 09:01:14.006370: step: 56/526, loss: 0.004904224071651697
2023-01-24 09:01:15.056417: step: 60/526, loss: 0.0021082209423184395
2023-01-24 09:01:16.143642: step: 64/526, loss: 0.004400089383125305
2023-01-24 09:01:17.202149: step: 68/526, loss: 0.007214154116809368
2023-01-24 09:01:18.269857: step: 72/526, loss: 0.0073178550228476524
2023-01-24 09:01:19.328185: step: 76/526, loss: 0.002440760377794504
2023-01-24 09:01:20.395184: step: 80/526, loss: 0.004771697334945202
2023-01-24 09:01:21.462627: step: 84/526, loss: 2.9408399768726667e-06
2023-01-24 09:01:22.529261: step: 88/526, loss: 0.055071085691452026
2023-01-24 09:01:23.585385: step: 92/526, loss: 0.0007967138080857694
2023-01-24 09:01:24.653765: step: 96/526, loss: 0.0013606281718239188
2023-01-24 09:01:25.751654: step: 100/526, loss: 0.004530522506684065
2023-01-24 09:01:26.813214: step: 104/526, loss: 0.00034838594729080796
2023-01-24 09:01:27.875237: step: 108/526, loss: 0.00045359120122157037
2023-01-24 09:01:28.942343: step: 112/526, loss: 0.0021417131647467613
2023-01-24 09:01:30.005894: step: 116/526, loss: 0.004992205183953047
2023-01-24 09:01:31.071883: step: 120/526, loss: 0.00042990536894649267
2023-01-24 09:01:32.133643: step: 124/526, loss: 0.002021200256422162
2023-01-24 09:01:33.201665: step: 128/526, loss: 6.429754284908995e-05
2023-01-24 09:01:34.263855: step: 132/526, loss: 0.0036365953274071217
2023-01-24 09:01:35.337252: step: 136/526, loss: 0.008111150935292244
2023-01-24 09:01:36.411871: step: 140/526, loss: 0.0005944063304923475
2023-01-24 09:01:37.469757: step: 144/526, loss: 0.001067745964974165
2023-01-24 09:01:38.535720: step: 148/526, loss: 0.000510052777826786
2023-01-24 09:01:39.599523: step: 152/526, loss: 0.005446300841867924
2023-01-24 09:01:40.664300: step: 156/526, loss: 5.827929999213666e-05
2023-01-24 09:01:41.735395: step: 160/526, loss: 0.0017400509677827358
2023-01-24 09:01:42.845640: step: 164/526, loss: 0.003879789263010025
2023-01-24 09:01:43.889681: step: 168/526, loss: 0.002057411940768361
2023-01-24 09:01:44.954441: step: 172/526, loss: 0.006376966834068298
2023-01-24 09:01:46.022439: step: 176/526, loss: 0.006155486684292555
2023-01-24 09:01:47.113021: step: 180/526, loss: 0.0008909195312298834
2023-01-24 09:01:48.179351: step: 184/526, loss: 0.0017011663876473904
2023-01-24 09:01:49.235709: step: 188/526, loss: 6.545661108248169e-06
2023-01-24 09:01:50.306544: step: 192/526, loss: 0.0014572531217709184
2023-01-24 09:01:51.365820: step: 196/526, loss: 0.0029842257499694824
2023-01-24 09:01:52.439470: step: 200/526, loss: 0.00021754551562480628
2023-01-24 09:01:53.501217: step: 204/526, loss: 0.0018615300068631768
2023-01-24 09:01:54.574563: step: 208/526, loss: 0.0027310634031891823
2023-01-24 09:01:55.660147: step: 212/526, loss: 0.0007247552275657654
2023-01-24 09:01:56.721476: step: 216/526, loss: 0.005324308294802904
2023-01-24 09:01:57.792214: step: 220/526, loss: 0.001008346094749868
2023-01-24 09:01:58.877203: step: 224/526, loss: 0.02025071531534195
2023-01-24 09:01:59.941573: step: 228/526, loss: 0.002746953396126628
2023-01-24 09:02:00.993631: step: 232/526, loss: 5.369909922592342e-05
2023-01-24 09:02:02.095050: step: 236/526, loss: 0.0011727057863026857
2023-01-24 09:02:03.166847: step: 240/526, loss: 0.0015861911233514547
2023-01-24 09:02:04.228356: step: 244/526, loss: 0.0011751428246498108
2023-01-24 09:02:05.311178: step: 248/526, loss: 0.005034309811890125
2023-01-24 09:02:06.372924: step: 252/526, loss: 1.7892503819894046e-05
2023-01-24 09:02:07.441730: step: 256/526, loss: 0.005751111079007387
2023-01-24 09:02:08.498611: step: 260/526, loss: 0.005098654888570309
2023-01-24 09:02:09.572405: step: 264/526, loss: 0.0010037494357675314
2023-01-24 09:02:10.637416: step: 268/526, loss: 0.002472367836162448
2023-01-24 09:02:11.720352: step: 272/526, loss: 0.003121607471257448
2023-01-24 09:02:12.804392: step: 276/526, loss: 0.00014994754747021943
2023-01-24 09:02:13.904372: step: 280/526, loss: 0.003918241709470749
2023-01-24 09:02:14.969597: step: 284/526, loss: 9.827670874074101e-05
2023-01-24 09:02:16.028578: step: 288/526, loss: 0.0021978854201734066
2023-01-24 09:02:17.093249: step: 292/526, loss: 1.741137748467736e-05
2023-01-24 09:02:18.152568: step: 296/526, loss: 0.0014372613513842225
2023-01-24 09:02:19.233969: step: 300/526, loss: 0.0003253793402109295
2023-01-24 09:02:20.322154: step: 304/526, loss: 0.020002910867333412
2023-01-24 09:02:21.391165: step: 308/526, loss: 0.002194400876760483
2023-01-24 09:02:22.462071: step: 312/526, loss: 0.003964131698012352
2023-01-24 09:02:23.525617: step: 316/526, loss: 0.001673134509474039
2023-01-24 09:02:24.589735: step: 320/526, loss: 0.00022924515360500664
2023-01-24 09:02:25.668934: step: 324/526, loss: 0.0007709195488132536
2023-01-24 09:02:26.745331: step: 328/526, loss: 0.001254845643416047
2023-01-24 09:02:27.810453: step: 332/526, loss: 0.002715372946113348
2023-01-24 09:02:28.875842: step: 336/526, loss: 0.0002852242032531649
2023-01-24 09:02:29.945777: step: 340/526, loss: 0.004312833771109581
2023-01-24 09:02:31.019844: step: 344/526, loss: 0.007030846551060677
2023-01-24 09:02:32.096707: step: 348/526, loss: 0.0018822341226041317
2023-01-24 09:02:33.163324: step: 352/526, loss: 0.004254063591361046
2023-01-24 09:02:34.224305: step: 356/526, loss: 0.002120479941368103
2023-01-24 09:02:35.301147: step: 360/526, loss: 0.007172430399805307
2023-01-24 09:02:36.377967: step: 364/526, loss: 0.006202549207955599
2023-01-24 09:02:37.440513: step: 368/526, loss: 0.00013633868366014212
2023-01-24 09:02:38.508483: step: 372/526, loss: 0.0009908577194437385
2023-01-24 09:02:39.571361: step: 376/526, loss: 0.0046517071314156055
2023-01-24 09:02:40.641528: step: 380/526, loss: 0.0016412843251600862
2023-01-24 09:02:41.723140: step: 384/526, loss: 0.008400763384997845
2023-01-24 09:02:42.799914: step: 388/526, loss: 0.0003771914925891906
2023-01-24 09:02:43.885845: step: 392/526, loss: 0.007985120639204979
2023-01-24 09:02:44.946358: step: 396/526, loss: 0.00022815779084339738
2023-01-24 09:02:46.026787: step: 400/526, loss: 0.0019783317111432552
2023-01-24 09:02:47.108427: step: 404/526, loss: 0.002509333658963442
2023-01-24 09:02:48.178314: step: 408/526, loss: 0.002491546329110861
2023-01-24 09:02:49.237116: step: 412/526, loss: 0.0038743168115615845
2023-01-24 09:02:50.308329: step: 416/526, loss: 0.003474264871329069
2023-01-24 09:02:51.361792: step: 420/526, loss: 1.7693611880531535e-05
2023-01-24 09:02:52.424726: step: 424/526, loss: 9.059806325240061e-05
2023-01-24 09:02:53.477201: step: 428/526, loss: 0.0005716729792766273
2023-01-24 09:02:54.547153: step: 432/526, loss: 0.007911231368780136
2023-01-24 09:02:55.620138: step: 436/526, loss: 0.0011817221529781818
2023-01-24 09:02:56.690168: step: 440/526, loss: 7.003147038631141e-05
2023-01-24 09:02:57.749389: step: 444/526, loss: 0.024542130529880524
2023-01-24 09:02:58.833156: step: 448/526, loss: 0.0009809286566451192
2023-01-24 09:02:59.903830: step: 452/526, loss: 2.513647632440552e-05
2023-01-24 09:03:00.946462: step: 456/526, loss: 0.003996597602963448
2023-01-24 09:03:02.013258: step: 460/526, loss: 0.0010373241966590285
2023-01-24 09:03:03.107884: step: 464/526, loss: 0.00015869905473664403
2023-01-24 09:03:04.180083: step: 468/526, loss: 0.001618224661797285
2023-01-24 09:03:05.265005: step: 472/526, loss: 0.0003693256003316492
2023-01-24 09:03:06.349912: step: 476/526, loss: 0.004332988988608122
2023-01-24 09:03:07.425129: step: 480/526, loss: 0.00193475850392133
2023-01-24 09:03:08.507421: step: 484/526, loss: 0.009533879347145557
2023-01-24 09:03:09.573723: step: 488/526, loss: 0.005407858639955521
2023-01-24 09:03:10.638157: step: 492/526, loss: 0.0011100302217528224
2023-01-24 09:03:11.701218: step: 496/526, loss: 0.007173910737037659
2023-01-24 09:03:12.766148: step: 500/526, loss: 9.391533967573196e-05
2023-01-24 09:03:13.835056: step: 504/526, loss: 5.143625458003953e-05
2023-01-24 09:03:14.910335: step: 508/526, loss: 0.00042028838652186096
2023-01-24 09:03:15.976879: step: 512/526, loss: 0.0005628418875858188
2023-01-24 09:03:17.064687: step: 516/526, loss: 0.004128247033804655
2023-01-24 09:03:18.141315: step: 520/526, loss: 0.013559453189373016
2023-01-24 09:03:19.208219: step: 524/526, loss: 3.6681096389656886e-05
2023-01-24 09:03:20.261505: step: 528/526, loss: 0.003175022779032588
2023-01-24 09:03:21.327257: step: 532/526, loss: 0.0035885819233953953
2023-01-24 09:03:22.393753: step: 536/526, loss: 0.0002623856416903436
2023-01-24 09:03:23.454153: step: 540/526, loss: 3.9572631067130715e-05
2023-01-24 09:03:24.534507: step: 544/526, loss: 0.004054659511893988
2023-01-24 09:03:25.599219: step: 548/526, loss: 0.00040347164031118155
2023-01-24 09:03:26.669041: step: 552/526, loss: 5.39237807970494e-05
2023-01-24 09:03:27.730213: step: 556/526, loss: 3.1650237360736355e-05
2023-01-24 09:03:28.803980: step: 560/526, loss: 0.005598296876996756
2023-01-24 09:03:29.872242: step: 564/526, loss: 0.0028897884767502546
2023-01-24 09:03:30.937154: step: 568/526, loss: 0.0011353478766977787
2023-01-24 09:03:32.000986: step: 572/526, loss: 0.0019426702056080103
2023-01-24 09:03:33.070666: step: 576/526, loss: 0.0028505504596978426
2023-01-24 09:03:34.139360: step: 580/526, loss: 0.026631765067577362
2023-01-24 09:03:35.213121: step: 584/526, loss: 0.00011829569848487154
2023-01-24 09:03:36.281356: step: 588/526, loss: 0.001947137643583119
2023-01-24 09:03:37.337571: step: 592/526, loss: 0.002710395958274603
2023-01-24 09:03:38.401808: step: 596/526, loss: 0.0033332386519759893
2023-01-24 09:03:39.464953: step: 600/526, loss: 0.010657456703484058
2023-01-24 09:03:40.535639: step: 604/526, loss: 0.0006016839761286974
2023-01-24 09:03:41.643224: step: 608/526, loss: 0.008573072031140327
2023-01-24 09:03:42.736082: step: 612/526, loss: 0.0037041762843728065
2023-01-24 09:03:43.823142: step: 616/526, loss: 0.001809286535717547
2023-01-24 09:03:44.902536: step: 620/526, loss: 0.003464053850620985
2023-01-24 09:03:45.986526: step: 624/526, loss: 0.03140509873628616
2023-01-24 09:03:47.079632: step: 628/526, loss: 3.086018477915786e-05
2023-01-24 09:03:48.148282: step: 632/526, loss: 0.0005039675161242485
2023-01-24 09:03:49.228958: step: 636/526, loss: 0.006325926166027784
2023-01-24 09:03:50.307074: step: 640/526, loss: 0.021041058003902435
2023-01-24 09:03:51.376597: step: 644/526, loss: 0.00012388094910420477
2023-01-24 09:03:52.438867: step: 648/526, loss: 0.0009035734110511839
2023-01-24 09:03:53.489578: step: 652/526, loss: 0.0025565605610609055
2023-01-24 09:03:54.566287: step: 656/526, loss: 0.00212524994276464
2023-01-24 09:03:55.646461: step: 660/526, loss: 3.650477447081357e-05
2023-01-24 09:03:56.704465: step: 664/526, loss: 0.0030039974953979254
2023-01-24 09:03:57.773661: step: 668/526, loss: 0.0033427078742533922
2023-01-24 09:03:58.841687: step: 672/526, loss: 0.00217223446816206
2023-01-24 09:03:59.924104: step: 676/526, loss: 0.003401148598641157
2023-01-24 09:04:01.024448: step: 680/526, loss: 0.0015600905753672123
2023-01-24 09:04:02.089086: step: 684/526, loss: 0.0010989258298650384
2023-01-24 09:04:03.174987: step: 688/526, loss: 0.007191374897956848
2023-01-24 09:04:04.254441: step: 692/526, loss: 0.0015263402601704001
2023-01-24 09:04:05.342554: step: 696/526, loss: 2.1196392481215298e-05
2023-01-24 09:04:06.414969: step: 700/526, loss: 8.010312740225345e-05
2023-01-24 09:04:07.504451: step: 704/526, loss: 0.010291696526110172
2023-01-24 09:04:08.571095: step: 708/526, loss: 0.00112661044113338
2023-01-24 09:04:09.621335: step: 712/526, loss: 0.0002964239101856947
2023-01-24 09:04:10.691247: step: 716/526, loss: 0.011497760191559792
2023-01-24 09:04:11.762923: step: 720/526, loss: 0.006778793875128031
2023-01-24 09:04:12.857542: step: 724/526, loss: 0.005778077989816666
2023-01-24 09:04:13.915764: step: 728/526, loss: 0.004655781202018261
2023-01-24 09:04:14.989176: step: 732/526, loss: 0.015510223805904388
2023-01-24 09:04:16.067976: step: 736/526, loss: 0.0029409381095319986
2023-01-24 09:04:17.147181: step: 740/526, loss: 0.0007851281552575529
2023-01-24 09:04:18.233578: step: 744/526, loss: 0.0039327433332800865
2023-01-24 09:04:19.307490: step: 748/526, loss: 0.008739260025322437
2023-01-24 09:04:20.359098: step: 752/526, loss: 0.00786527618765831
2023-01-24 09:04:21.435995: step: 756/526, loss: 0.00018130269018001854
2023-01-24 09:04:22.491209: step: 760/526, loss: 0.0013243837747722864
2023-01-24 09:04:23.568464: step: 764/526, loss: 0.001044142059981823
2023-01-24 09:04:24.621004: step: 768/526, loss: 0.005148190073668957
2023-01-24 09:04:25.693509: step: 772/526, loss: 0.002936548786237836
2023-01-24 09:04:26.766649: step: 776/526, loss: 0.0024159452877938747
2023-01-24 09:04:27.838587: step: 780/526, loss: 0.0020789632108062506
2023-01-24 09:04:28.915449: step: 784/526, loss: 0.00671969261020422
2023-01-24 09:04:29.981941: step: 788/526, loss: 0.0045554968528449535
2023-01-24 09:04:31.053668: step: 792/526, loss: 0.0027457494288682938
2023-01-24 09:04:32.132113: step: 796/526, loss: 0.0029943548142910004
2023-01-24 09:04:33.198723: step: 800/526, loss: 2.6185055048699724e-06
2023-01-24 09:04:34.265434: step: 804/526, loss: 0.0009109939564950764
2023-01-24 09:04:35.344829: step: 808/526, loss: 0.0033608537632972
2023-01-24 09:04:36.421152: step: 812/526, loss: 0.0009890490910038352
2023-01-24 09:04:37.493059: step: 816/526, loss: 0.008628185838460922
2023-01-24 09:04:38.554362: step: 820/526, loss: 0.0002820239751599729
2023-01-24 09:04:39.610983: step: 824/526, loss: 0.001793151954188943
2023-01-24 09:04:40.688750: step: 828/526, loss: 0.00478060357272625
2023-01-24 09:04:41.755098: step: 832/526, loss: 0.008563145995140076
2023-01-24 09:04:42.852097: step: 836/526, loss: 7.561895927210571e-07
2023-01-24 09:04:43.911856: step: 840/526, loss: 0.0048646871000528336
2023-01-24 09:04:44.988467: step: 844/526, loss: 0.005125503521412611
2023-01-24 09:04:46.047087: step: 848/526, loss: 0.005483269691467285
2023-01-24 09:04:47.128745: step: 852/526, loss: 0.004141530022025108
2023-01-24 09:04:48.187741: step: 856/526, loss: 0.005066207610070705
2023-01-24 09:04:49.248793: step: 860/526, loss: 0.004884377587586641
2023-01-24 09:04:50.338224: step: 864/526, loss: 0.005633790977299213
2023-01-24 09:04:51.422944: step: 868/526, loss: 0.003129212185740471
2023-01-24 09:04:52.495465: step: 872/526, loss: 0.010895761661231518
2023-01-24 09:04:53.553434: step: 876/526, loss: 6.200697680469602e-05
2023-01-24 09:04:54.621107: step: 880/526, loss: 0.002143584191799164
2023-01-24 09:04:55.693764: step: 884/526, loss: 0.0023682815954089165
2023-01-24 09:04:56.753748: step: 888/526, loss: 0.006069981958717108
2023-01-24 09:04:57.823751: step: 892/526, loss: 0.0014427766436710954
2023-01-24 09:04:58.894114: step: 896/526, loss: 0.01585986278951168
2023-01-24 09:04:59.967259: step: 900/526, loss: 2.9660292057087645e-05
2023-01-24 09:05:01.040561: step: 904/526, loss: 4.7156729124253616e-05
2023-01-24 09:05:02.112579: step: 908/526, loss: 1.3617322110803798e-05
2023-01-24 09:05:03.171776: step: 912/526, loss: 8.883810551196802e-06
2023-01-24 09:05:04.240958: step: 916/526, loss: 0.0001118779182434082
2023-01-24 09:05:05.313694: step: 920/526, loss: 0.005256551317870617
2023-01-24 09:05:06.396998: step: 924/526, loss: 0.009016133844852448
2023-01-24 09:05:07.486900: step: 928/526, loss: 0.00021188198297750205
2023-01-24 09:05:08.561291: step: 932/526, loss: 0.003637598594650626
2023-01-24 09:05:09.643831: step: 936/526, loss: 0.016615239903330803
2023-01-24 09:05:10.719066: step: 940/526, loss: 0.00040934860589914024
2023-01-24 09:05:11.786006: step: 944/526, loss: 0.0044012474827468395
2023-01-24 09:05:12.865522: step: 948/526, loss: 0.006855659186840057
2023-01-24 09:05:13.928545: step: 952/526, loss: 0.0003996416344307363
2023-01-24 09:05:14.994302: step: 956/526, loss: 7.552288298029453e-05
2023-01-24 09:05:16.071512: step: 960/526, loss: 0.0003318695235066116
2023-01-24 09:05:17.166869: step: 964/526, loss: 0.0017283064080402255
2023-01-24 09:05:18.264994: step: 968/526, loss: 0.0026691537350416183
2023-01-24 09:05:19.342518: step: 972/526, loss: 0.019624311476945877
2023-01-24 09:05:20.438921: step: 976/526, loss: 0.00014126319729257375
2023-01-24 09:05:21.527852: step: 980/526, loss: 0.0018047704361379147
2023-01-24 09:05:22.602771: step: 984/526, loss: 0.005832708440721035
2023-01-24 09:05:23.675244: step: 988/526, loss: 0.0017403271049261093
2023-01-24 09:05:24.753704: step: 992/526, loss: 0.0018242273945361376
2023-01-24 09:05:25.820057: step: 996/526, loss: 0.0009334094938822091
2023-01-24 09:05:26.880436: step: 1000/526, loss: 1.8027827763944515e-06
2023-01-24 09:05:27.945296: step: 1004/526, loss: 0.00012063900067005306
2023-01-24 09:05:29.017972: step: 1008/526, loss: 0.0023849811404943466
2023-01-24 09:05:30.100773: step: 1012/526, loss: 0.0011543261352926493
2023-01-24 09:05:31.165186: step: 1016/526, loss: 0.006599085405468941
2023-01-24 09:05:32.243540: step: 1020/526, loss: 0.0015714691253378987
2023-01-24 09:05:33.313583: step: 1024/526, loss: 0.0004263747250661254
2023-01-24 09:05:34.380369: step: 1028/526, loss: 0.0019194228807464242
2023-01-24 09:05:35.444890: step: 1032/526, loss: 0.008408263325691223
2023-01-24 09:05:36.532984: step: 1036/526, loss: 0.008526553399860859
2023-01-24 09:05:37.591632: step: 1040/526, loss: 0.005731299519538879
2023-01-24 09:05:38.657302: step: 1044/526, loss: 0.0020719878375530243
2023-01-24 09:05:39.721468: step: 1048/526, loss: 0.000633670948445797
2023-01-24 09:05:40.803444: step: 1052/526, loss: 0.0077095492742955685
2023-01-24 09:05:41.856333: step: 1056/526, loss: 0.0008598942076787353
2023-01-24 09:05:42.912313: step: 1060/526, loss: 0.004499847535043955
2023-01-24 09:05:43.978247: step: 1064/526, loss: 0.0008381953230127692
2023-01-24 09:05:45.051129: step: 1068/526, loss: 1.901035284390673e-05
2023-01-24 09:05:46.124788: step: 1072/526, loss: 0.005073018372058868
2023-01-24 09:05:47.195904: step: 1076/526, loss: 0.0025398065336048603
2023-01-24 09:05:48.275704: step: 1080/526, loss: 0.00629441486671567
2023-01-24 09:05:49.339568: step: 1084/526, loss: 0.00017982145072892308
2023-01-24 09:05:50.442946: step: 1088/526, loss: 0.0069209313951432705
2023-01-24 09:05:51.527570: step: 1092/526, loss: 0.0008697143639437854
2023-01-24 09:05:52.600973: step: 1096/526, loss: 0.0031767701730132103
2023-01-24 09:05:53.678745: step: 1100/526, loss: 0.0003001618024427444
2023-01-24 09:05:54.741116: step: 1104/526, loss: 0.0014380216598510742
2023-01-24 09:05:55.821582: step: 1108/526, loss: 0.0025857852306216955
2023-01-24 09:05:56.899283: step: 1112/526, loss: 0.000907846842892468
2023-01-24 09:05:57.970951: step: 1116/526, loss: 0.0008653496624901891
2023-01-24 09:05:59.035678: step: 1120/526, loss: 0.004827171564102173
2023-01-24 09:06:00.108825: step: 1124/526, loss: 0.026355817914009094
2023-01-24 09:06:01.176088: step: 1128/526, loss: 0.0024555332493036985
2023-01-24 09:06:02.233496: step: 1132/526, loss: 0.0009359808755107224
2023-01-24 09:06:03.293928: step: 1136/526, loss: 0.0004610107862390578
2023-01-24 09:06:04.388205: step: 1140/526, loss: 9.134774882113561e-05
2023-01-24 09:06:05.473559: step: 1144/526, loss: 0.00035617267712950706
2023-01-24 09:06:06.540737: step: 1148/526, loss: 4.709354470833205e-05
2023-01-24 09:06:07.634007: step: 1152/526, loss: 0.002250316087156534
2023-01-24 09:06:08.706246: step: 1156/526, loss: 3.417308835196309e-05
2023-01-24 09:06:09.775274: step: 1160/526, loss: 0.002382897771894932
2023-01-24 09:06:10.848915: step: 1164/526, loss: 0.04007905349135399
2023-01-24 09:06:11.916740: step: 1168/526, loss: 0.00044090134906582534
2023-01-24 09:06:13.005890: step: 1172/526, loss: 0.0035805406514555216
2023-01-24 09:06:14.074166: step: 1176/526, loss: 0.0007598121301271021
2023-01-24 09:06:15.147075: step: 1180/526, loss: 0.0035539648961275816
2023-01-24 09:06:16.242371: step: 1184/526, loss: 0.006274072453379631
2023-01-24 09:06:17.323159: step: 1188/526, loss: 0.0008535367669537663
2023-01-24 09:06:18.401888: step: 1192/526, loss: 9.034009053721093e-06
2023-01-24 09:06:19.482189: step: 1196/526, loss: 0.0010479734046384692
2023-01-24 09:06:20.548984: step: 1200/526, loss: 8.021449320949614e-05
2023-01-24 09:06:21.638607: step: 1204/526, loss: 0.012833714485168457
2023-01-24 09:06:22.720491: step: 1208/526, loss: 0.0031448130030184984
2023-01-24 09:06:23.798613: step: 1212/526, loss: 0.0006451279041357338
2023-01-24 09:06:24.845579: step: 1216/526, loss: 4.499461283558048e-06
2023-01-24 09:06:25.909625: step: 1220/526, loss: 0.0018942963797599077
2023-01-24 09:06:26.980379: step: 1224/526, loss: 0.0002706024970393628
2023-01-24 09:06:28.035575: step: 1228/526, loss: 0.007170474156737328
2023-01-24 09:06:29.143255: step: 1232/526, loss: 0.002073476789519191
2023-01-24 09:06:30.215356: step: 1236/526, loss: 0.0014980868436396122
2023-01-24 09:06:31.283141: step: 1240/526, loss: 0.0036375101190060377
2023-01-24 09:06:32.344477: step: 1244/526, loss: 0.006721377372741699
2023-01-24 09:06:33.435191: step: 1248/526, loss: 0.002317317295819521
2023-01-24 09:06:34.499430: step: 1252/526, loss: 0.0017704438650980592
2023-01-24 09:06:35.566258: step: 1256/526, loss: 0.009525641798973083
2023-01-24 09:06:36.671397: step: 1260/526, loss: 0.000281882646959275
2023-01-24 09:06:37.740869: step: 1264/526, loss: 0.0019992971792817116
2023-01-24 09:06:38.791691: step: 1268/526, loss: 0.0002666060463525355
2023-01-24 09:06:39.866539: step: 1272/526, loss: 0.0005354165914468467
2023-01-24 09:06:40.943518: step: 1276/526, loss: 1.6846135622472502e-05
2023-01-24 09:06:42.032500: step: 1280/526, loss: 0.0006203344091773033
2023-01-24 09:06:43.083839: step: 1284/526, loss: 0.0017842404777184129
2023-01-24 09:06:44.162804: step: 1288/526, loss: 0.0007508570561185479
2023-01-24 09:06:45.224656: step: 1292/526, loss: 0.004485786892473698
2023-01-24 09:06:46.295224: step: 1296/526, loss: 0.00012149167741881683
2023-01-24 09:06:47.358453: step: 1300/526, loss: 6.777839007554576e-05
2023-01-24 09:06:48.423514: step: 1304/526, loss: 0.010077118873596191
2023-01-24 09:06:49.507416: step: 1308/526, loss: 0.0033351690508425236
2023-01-24 09:06:50.577711: step: 1312/526, loss: 0.0044865114614367485
2023-01-24 09:06:51.649283: step: 1316/526, loss: 0.00027660667547024786
2023-01-24 09:06:52.719923: step: 1320/526, loss: 0.0003761245170608163
2023-01-24 09:06:53.801229: step: 1324/526, loss: 0.0065785860642790794
2023-01-24 09:06:54.848456: step: 1328/526, loss: 1.4990439467510441e-06
2023-01-24 09:06:55.910259: step: 1332/526, loss: 0.0018392038764432073
2023-01-24 09:06:56.984451: step: 1336/526, loss: 9.461479749006685e-06
2023-01-24 09:06:58.064393: step: 1340/526, loss: 0.0026516823563724756
2023-01-24 09:06:59.143149: step: 1344/526, loss: 0.0034164125099778175
2023-01-24 09:07:00.200024: step: 1348/526, loss: 0.006494275294244289
2023-01-24 09:07:01.270524: step: 1352/526, loss: 6.096492143115029e-05
2023-01-24 09:07:02.342528: step: 1356/526, loss: 0.001117043779231608
2023-01-24 09:07:03.428268: step: 1360/526, loss: 0.004773973952978849
2023-01-24 09:07:04.485385: step: 1364/526, loss: 0.00043638001079671085
2023-01-24 09:07:05.553914: step: 1368/526, loss: 0.0005487690214067698
2023-01-24 09:07:06.635662: step: 1372/526, loss: 7.673940126551315e-05
2023-01-24 09:07:07.702076: step: 1376/526, loss: 0.010712930001318455
2023-01-24 09:07:08.785004: step: 1380/526, loss: 0.004162668716162443
2023-01-24 09:07:09.857700: step: 1384/526, loss: 0.0001251902140211314
2023-01-24 09:07:10.925460: step: 1388/526, loss: 0.003523906460031867
2023-01-24 09:07:11.993799: step: 1392/526, loss: 7.750542863504961e-05
2023-01-24 09:07:13.064040: step: 1396/526, loss: 0.013332800939679146
2023-01-24 09:07:14.149412: step: 1400/526, loss: 0.000300068553769961
2023-01-24 09:07:15.218930: step: 1404/526, loss: 0.000286574853817001
2023-01-24 09:07:16.279180: step: 1408/526, loss: 0.0067119356244802475
2023-01-24 09:07:17.351414: step: 1412/526, loss: 0.008381916210055351
2023-01-24 09:07:18.429949: step: 1416/526, loss: 0.021354010328650475
2023-01-24 09:07:19.484242: step: 1420/526, loss: 0.0021013005170971155
2023-01-24 09:07:20.578166: step: 1424/526, loss: 0.007751236204057932
2023-01-24 09:07:21.648162: step: 1428/526, loss: 0.0023494577035307884
2023-01-24 09:07:22.711679: step: 1432/526, loss: 1.2432211406121496e-05
2023-01-24 09:07:23.793123: step: 1436/526, loss: 0.0022359767463058233
2023-01-24 09:07:24.870713: step: 1440/526, loss: 0.01749587617814541
2023-01-24 09:07:25.957215: step: 1444/526, loss: 0.003885730169713497
2023-01-24 09:07:27.022066: step: 1448/526, loss: 0.003991383593529463
2023-01-24 09:07:28.093694: step: 1452/526, loss: 0.002184422453865409
2023-01-24 09:07:29.176944: step: 1456/526, loss: 0.001274257549084723
2023-01-24 09:07:30.253986: step: 1460/526, loss: 3.861587174469605e-05
2023-01-24 09:07:31.322531: step: 1464/526, loss: 0.001832600450143218
2023-01-24 09:07:32.395686: step: 1468/526, loss: 1.347813395113917e-05
2023-01-24 09:07:33.460841: step: 1472/526, loss: 0.001567143015563488
2023-01-24 09:07:34.536196: step: 1476/526, loss: 0.002534782513976097
2023-01-24 09:07:35.604672: step: 1480/526, loss: 0.0012802876299247146
2023-01-24 09:07:36.691598: step: 1484/526, loss: 0.0027030291967093945
2023-01-24 09:07:37.768364: step: 1488/526, loss: 0.00013787155330646783
2023-01-24 09:07:38.845335: step: 1492/526, loss: 0.0011151605285704136
2023-01-24 09:07:39.913497: step: 1496/526, loss: 0.0018621307099238038
2023-01-24 09:07:40.972461: step: 1500/526, loss: 1.7261953644265304e-06
2023-01-24 09:07:42.036157: step: 1504/526, loss: 5.487791349878535e-05
2023-01-24 09:07:43.090820: step: 1508/526, loss: 0.0016611238243058324
2023-01-24 09:07:44.153420: step: 1512/526, loss: 0.004168468527495861
2023-01-24 09:07:45.226677: step: 1516/526, loss: 6.243514235393377e-06
2023-01-24 09:07:46.302074: step: 1520/526, loss: 0.005801422521471977
2023-01-24 09:07:47.365828: step: 1524/526, loss: 2.4645178200444207e-05
2023-01-24 09:07:48.446581: step: 1528/526, loss: 0.022216124460101128
2023-01-24 09:07:49.525752: step: 1532/526, loss: 0.0007919517811387777
2023-01-24 09:07:50.584370: step: 1536/526, loss: 0.00010203020792687312
2023-01-24 09:07:51.654992: step: 1540/526, loss: 0.0037814879324287176
2023-01-24 09:07:52.732344: step: 1544/526, loss: 0.0026631627697497606
2023-01-24 09:07:53.793526: step: 1548/526, loss: 0.007588594686239958
2023-01-24 09:07:54.852193: step: 1552/526, loss: 0.0005021351389586926
2023-01-24 09:07:55.932266: step: 1556/526, loss: 0.004490867257118225
2023-01-24 09:07:57.010789: step: 1560/526, loss: 0.006299326196312904
2023-01-24 09:07:58.073739: step: 1564/526, loss: 8.10993806226179e-05
2023-01-24 09:07:59.133753: step: 1568/526, loss: 3.5936860513174906e-05
2023-01-24 09:08:00.204307: step: 1572/526, loss: 0.005455671343952417
2023-01-24 09:08:01.269731: step: 1576/526, loss: 0.0022343171294778585
2023-01-24 09:08:02.328685: step: 1580/526, loss: 0.00565881934016943
2023-01-24 09:08:03.410521: step: 1584/526, loss: 0.002394011477008462
2023-01-24 09:08:04.491871: step: 1588/526, loss: 0.0005993566010147333
2023-01-24 09:08:05.565288: step: 1592/526, loss: 0.0018220811616629362
2023-01-24 09:08:06.652052: step: 1596/526, loss: 0.0029813917353749275
2023-01-24 09:08:07.728328: step: 1600/526, loss: 0.011426822282373905
2023-01-24 09:08:08.782034: step: 1604/526, loss: 0.001398384920321405
2023-01-24 09:08:09.862865: step: 1608/526, loss: 0.013480094261467457
2023-01-24 09:08:10.929305: step: 1612/526, loss: 0.004890612792223692
2023-01-24 09:08:11.995118: step: 1616/526, loss: 0.0
2023-01-24 09:08:13.078310: step: 1620/526, loss: 0.004262028727680445
2023-01-24 09:08:14.160073: step: 1624/526, loss: 0.001888250932097435
2023-01-24 09:08:15.224550: step: 1628/526, loss: 0.0030150809325277805
2023-01-24 09:08:16.317868: step: 1632/526, loss: 0.004785026889294386
2023-01-24 09:08:17.392615: step: 1636/526, loss: 0.006957195699214935
2023-01-24 09:08:18.479186: step: 1640/526, loss: 0.0035553639754652977
2023-01-24 09:08:19.561314: step: 1644/526, loss: 0.01161589939147234
2023-01-24 09:08:20.654425: step: 1648/526, loss: 0.008723870851099491
2023-01-24 09:08:21.719129: step: 1652/526, loss: 8.930452167987823e-05
2023-01-24 09:08:22.799169: step: 1656/526, loss: 0.013251790776848793
2023-01-24 09:08:23.869364: step: 1660/526, loss: 0.00013941475481260568
2023-01-24 09:08:24.954423: step: 1664/526, loss: 0.007746046409010887
2023-01-24 09:08:26.026558: step: 1668/526, loss: 0.004453939851373434
2023-01-24 09:08:27.102221: step: 1672/526, loss: 0.005910741165280342
2023-01-24 09:08:28.178482: step: 1676/526, loss: 0.007134700194001198
2023-01-24 09:08:29.239861: step: 1680/526, loss: 0.001658489927649498
2023-01-24 09:08:30.319977: step: 1684/526, loss: 0.00494175311177969
2023-01-24 09:08:31.383403: step: 1688/526, loss: 0.009418007917702198
2023-01-24 09:08:32.463664: step: 1692/526, loss: 0.009221172891557217
2023-01-24 09:08:33.539450: step: 1696/526, loss: 0.0004322432796470821
2023-01-24 09:08:34.610388: step: 1700/526, loss: 0.004004043061286211
2023-01-24 09:08:35.674257: step: 1704/526, loss: 0.002552700461819768
2023-01-24 09:08:36.746799: step: 1708/526, loss: 0.004919564817100763
2023-01-24 09:08:37.824564: step: 1712/526, loss: 0.006907130591571331
2023-01-24 09:08:38.890264: step: 1716/526, loss: 0.0006193004664964974
2023-01-24 09:08:39.970946: step: 1720/526, loss: 0.0037172953598201275
2023-01-24 09:08:41.042047: step: 1724/526, loss: 0.0005401995731517673
2023-01-24 09:08:42.098965: step: 1728/526, loss: 0.0053809951059520245
2023-01-24 09:08:43.166368: step: 1732/526, loss: 0.0023989479523152113
2023-01-24 09:08:44.239925: step: 1736/526, loss: 0.0012443233281373978
2023-01-24 09:08:45.309429: step: 1740/526, loss: 0.000889366667252034
2023-01-24 09:08:46.385754: step: 1744/526, loss: 0.0032394747249782085
2023-01-24 09:08:47.462238: step: 1748/526, loss: 0.003769340692088008
2023-01-24 09:08:48.545808: step: 1752/526, loss: 0.0005162744782865047
2023-01-24 09:08:49.629505: step: 1756/526, loss: 0.0006097472505643964
2023-01-24 09:08:50.712877: step: 1760/526, loss: 0.0001414238940924406
2023-01-24 09:08:51.781708: step: 1764/526, loss: 0.003278970718383789
2023-01-24 09:08:52.856449: step: 1768/526, loss: 0.000331067421939224
2023-01-24 09:08:53.940714: step: 1772/526, loss: 0.006036052014678717
2023-01-24 09:08:55.016240: step: 1776/526, loss: 0.0033444338478147984
2023-01-24 09:08:56.088625: step: 1780/526, loss: 0.0003828260232694447
2023-01-24 09:08:57.157200: step: 1784/526, loss: 0.004634466953575611
2023-01-24 09:08:58.226617: step: 1788/526, loss: 0.006191542837768793
2023-01-24 09:08:59.310450: step: 1792/526, loss: 0.010699182748794556
2023-01-24 09:09:00.394714: step: 1796/526, loss: 0.0032722302712500095
2023-01-24 09:09:01.477140: step: 1800/526, loss: 0.0
2023-01-24 09:09:02.549397: step: 1804/526, loss: 0.006117125041782856
2023-01-24 09:09:03.609084: step: 1808/526, loss: 0.007697529159486294
2023-01-24 09:09:04.682413: step: 1812/526, loss: 0.00014335779997054487
2023-01-24 09:09:05.756922: step: 1816/526, loss: 0.00042543807649053633
2023-01-24 09:09:06.834107: step: 1820/526, loss: 7.046247674225015e-07
2023-01-24 09:09:07.902941: step: 1824/526, loss: 0.001535007613711059
2023-01-24 09:09:08.990721: step: 1828/526, loss: 0.011807135306298733
2023-01-24 09:09:10.068840: step: 1832/526, loss: 0.0045645572245121
2023-01-24 09:09:11.142792: step: 1836/526, loss: 2.718126961553935e-05
2023-01-24 09:09:12.210916: step: 1840/526, loss: 0.00169331522192806
2023-01-24 09:09:13.305062: step: 1844/526, loss: 0.005931252613663673
2023-01-24 09:09:14.381438: step: 1848/526, loss: 0.002233896404504776
2023-01-24 09:09:15.463687: step: 1852/526, loss: 0.005738517735153437
2023-01-24 09:09:16.534376: step: 1856/526, loss: 0.006837034597992897
2023-01-24 09:09:17.621053: step: 1860/526, loss: 0.007836534641683102
2023-01-24 09:09:18.690040: step: 1864/526, loss: 0.006747606676071882
2023-01-24 09:09:19.745544: step: 1868/526, loss: 0.0005719589535146952
2023-01-24 09:09:20.831530: step: 1872/526, loss: 0.0006534755229949951
2023-01-24 09:09:21.883101: step: 1876/526, loss: 0.00026500006788410246
2023-01-24 09:09:22.950436: step: 1880/526, loss: 0.004114976618438959
2023-01-24 09:09:24.026934: step: 1884/526, loss: 0.0024707880802452564
2023-01-24 09:09:25.089145: step: 1888/526, loss: 0.0055861808359622955
2023-01-24 09:09:26.160721: step: 1892/526, loss: 0.004871733486652374
2023-01-24 09:09:27.210987: step: 1896/526, loss: 3.1851061521592783e-07
2023-01-24 09:09:28.277988: step: 1900/526, loss: 0.0063774725422263145
2023-01-24 09:09:29.347906: step: 1904/526, loss: 0.000972148438449949
2023-01-24 09:09:30.411853: step: 1908/526, loss: 0.0008065954898484051
2023-01-24 09:09:31.496156: step: 1912/526, loss: 0.0013497774489223957
2023-01-24 09:09:32.580371: step: 1916/526, loss: 0.0036005214788019657
2023-01-24 09:09:33.656247: step: 1920/526, loss: 8.062608685577288e-05
2023-01-24 09:09:34.727979: step: 1924/526, loss: 0.006431287154555321
2023-01-24 09:09:35.794090: step: 1928/526, loss: 0.006485434714704752
2023-01-24 09:09:36.853352: step: 1932/526, loss: 0.0005947311292402446
2023-01-24 09:09:37.922153: step: 1936/526, loss: 0.003580398391932249
2023-01-24 09:09:38.989266: step: 1940/526, loss: 0.0007175241480581462
2023-01-24 09:09:40.064538: step: 1944/526, loss: 0.002594831632450223
2023-01-24 09:09:41.137229: step: 1948/526, loss: 0.004493865184485912
2023-01-24 09:09:42.204022: step: 1952/526, loss: 6.127478991402313e-05
2023-01-24 09:09:43.303236: step: 1956/526, loss: 0.002369788009673357
2023-01-24 09:09:44.369280: step: 1960/526, loss: 0.002066218527033925
2023-01-24 09:09:45.443009: step: 1964/526, loss: 0.001789343194104731
2023-01-24 09:09:46.511047: step: 1968/526, loss: 0.0037907143123447895
2023-01-24 09:09:47.576614: step: 1972/526, loss: 8.078163955360651e-05
2023-01-24 09:09:48.637605: step: 1976/526, loss: 0.018211212009191513
2023-01-24 09:09:49.712812: step: 1980/526, loss: 0.007960271090269089
2023-01-24 09:09:50.776787: step: 1984/526, loss: 0.000857973878737539
2023-01-24 09:09:51.849608: step: 1988/526, loss: 0.00034316728124395013
2023-01-24 09:09:52.924319: step: 1992/526, loss: 0.001411373377777636
2023-01-24 09:09:53.993820: step: 1996/526, loss: 0.003415762446820736
2023-01-24 09:09:55.074070: step: 2000/526, loss: 0.011371809989213943
2023-01-24 09:09:56.142462: step: 2004/526, loss: 0.005508440546691418
2023-01-24 09:09:57.223676: step: 2008/526, loss: 0.00264719408005476
2023-01-24 09:09:58.272476: step: 2012/526, loss: 1.6927418982959352e-05
2023-01-24 09:09:59.355017: step: 2016/526, loss: 0.000632552313618362
2023-01-24 09:10:00.418827: step: 2020/526, loss: 0.0013850086834281683
2023-01-24 09:10:01.497043: step: 2024/526, loss: 0.0017230726080015302
2023-01-24 09:10:02.583852: step: 2028/526, loss: 0.0006493153050541878
2023-01-24 09:10:03.645862: step: 2032/526, loss: 0.0014450449962168932
2023-01-24 09:10:04.731565: step: 2036/526, loss: 0.004113477189093828
2023-01-24 09:10:05.798525: step: 2040/526, loss: 0.0014669264201074839
2023-01-24 09:10:06.909377: step: 2044/526, loss: 0.010625802911818027
2023-01-24 09:10:07.990999: step: 2048/526, loss: 0.001426542759872973
2023-01-24 09:10:09.062191: step: 2052/526, loss: 0.0011626218911260366
2023-01-24 09:10:10.122444: step: 2056/526, loss: 0.0018838917603716254
2023-01-24 09:10:11.211858: step: 2060/526, loss: 0.0001352133695036173
2023-01-24 09:10:12.278901: step: 2064/526, loss: 0.014209941029548645
2023-01-24 09:10:13.350789: step: 2068/526, loss: 0.005324861500412226
2023-01-24 09:10:14.419933: step: 2072/526, loss: 0.0004976170603185892
2023-01-24 09:10:15.484606: step: 2076/526, loss: 0.001420331303961575
2023-01-24 09:10:16.556789: step: 2080/526, loss: 0.006688391324132681
2023-01-24 09:10:17.624157: step: 2084/526, loss: 0.0013125926489010453
2023-01-24 09:10:18.714511: step: 2088/526, loss: 0.0029741707257926464
2023-01-24 09:10:19.787034: step: 2092/526, loss: 0.003950865939259529
2023-01-24 09:10:20.853213: step: 2096/526, loss: 0.00022132458980195224
2023-01-24 09:10:21.945340: step: 2100/526, loss: 0.0014117838582023978
2023-01-24 09:10:23.024505: step: 2104/526, loss: 0.002955192234367132
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3627203744093057, 'r': 0.27049166440769856, 'f1': 0.3098893633540373}, 'combined': 0.22833953089244852, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36014049369747897, 'r': 0.22405812965625407, 'f1': 0.2762498992828942}, 'combined': 0.15068176324521498, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33935800250078146, 'r': 0.2942819869883437, 'f1': 0.31521668118466895}, 'combined': 0.2322649229781771, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3582253472595398, 'r': 0.25859084994307124, 'f1': 0.3003611041315376}, 'combined': 0.16383332952629323, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35907320487483535, 'r': 0.313422531769306, 'f1': 0.33469842804949196}, 'combined': 0.24661989435225723, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3645122450783329, 'r': 0.2768025282845529, 'f1': 0.3146595563338703}, 'combined': 0.17163248527302016, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.44047619047619047, 'r': 0.40217391304347827, 'f1': 0.4204545454545454}, 'combined': 0.2102272727272727, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 09:13:05.788577: step: 4/526, loss: 4.068960151926149e-06
2023-01-24 09:13:06.855577: step: 8/526, loss: 0.0010283082956448197
2023-01-24 09:13:07.910053: step: 12/526, loss: 0.0008490660111419857
2023-01-24 09:13:08.955695: step: 16/526, loss: 0.005104940850287676
2023-01-24 09:13:10.006071: step: 20/526, loss: 0.0044412012211978436
2023-01-24 09:13:11.072660: step: 24/526, loss: 0.0003217730263713747
2023-01-24 09:13:12.139564: step: 28/526, loss: 0.0014519531978294253
2023-01-24 09:13:13.229670: step: 32/526, loss: 0.0076652467250823975
2023-01-24 09:13:14.308443: step: 36/526, loss: 9.561112528899685e-05
2023-01-24 09:13:15.375517: step: 40/526, loss: 0.003580830991268158
2023-01-24 09:13:16.446947: step: 44/526, loss: 4.567169526126236e-05
2023-01-24 09:13:17.539626: step: 48/526, loss: 0.004925690125674009
2023-01-24 09:13:18.616432: step: 52/526, loss: 0.006543352734297514
2023-01-24 09:13:19.667896: step: 56/526, loss: 4.94741543661803e-05
2023-01-24 09:13:20.726152: step: 60/526, loss: 0.0013182016555219889
2023-01-24 09:13:21.788653: step: 64/526, loss: 0.0053622061386704445
2023-01-24 09:13:22.848566: step: 68/526, loss: 0.002632154617458582
2023-01-24 09:13:23.912718: step: 72/526, loss: 0.0018756737699732184
2023-01-24 09:13:24.979361: step: 76/526, loss: 4.548280230665114e-06
2023-01-24 09:13:26.034442: step: 80/526, loss: 0.00036563625326380134
2023-01-24 09:13:27.107058: step: 84/526, loss: 0.000709105865098536
2023-01-24 09:13:28.172265: step: 88/526, loss: 0.00803337711840868
2023-01-24 09:13:29.258136: step: 92/526, loss: 0.00015364907449111342
2023-01-24 09:13:30.332180: step: 96/526, loss: 0.011357865296304226
2023-01-24 09:13:31.395047: step: 100/526, loss: 0.0007185018621385098
2023-01-24 09:13:32.464723: step: 104/526, loss: 0.0031617230270057917
2023-01-24 09:13:33.530034: step: 108/526, loss: 0.002540634712204337
2023-01-24 09:13:34.579092: step: 112/526, loss: 0.0017137971008196473
2023-01-24 09:13:35.655857: step: 116/526, loss: 0.009323597885668278
2023-01-24 09:13:36.726592: step: 120/526, loss: 0.005170644260942936
2023-01-24 09:13:37.802469: step: 124/526, loss: 0.0014280106406658888
2023-01-24 09:13:38.869952: step: 128/526, loss: 0.002427392639219761
2023-01-24 09:13:39.938895: step: 132/526, loss: 0.003096052911132574
2023-01-24 09:13:41.019387: step: 136/526, loss: 0.0019009527750313282
2023-01-24 09:13:42.111075: step: 140/526, loss: 0.0002588734496384859
2023-01-24 09:13:43.182948: step: 144/526, loss: 0.002704356098547578
2023-01-24 09:13:44.242075: step: 148/526, loss: 0.0046740686520934105
2023-01-24 09:13:45.306190: step: 152/526, loss: 0.000814518250990659
2023-01-24 09:13:46.386777: step: 156/526, loss: 0.0011716143926605582
2023-01-24 09:13:47.451267: step: 160/526, loss: 0.003976736683398485
2023-01-24 09:13:48.537651: step: 164/526, loss: 1.899892225765143e-07
2023-01-24 09:13:49.591994: step: 168/526, loss: 0.004484981298446655
2023-01-24 09:13:50.657529: step: 172/526, loss: 0.006474488414824009
2023-01-24 09:13:51.737277: step: 176/526, loss: 0.0006338073872029781
2023-01-24 09:13:52.811467: step: 180/526, loss: 0.0008972170180641115
2023-01-24 09:13:53.894552: step: 184/526, loss: 0.0003931898099835962
2023-01-24 09:13:54.943944: step: 188/526, loss: 0.006468059495091438
2023-01-24 09:13:56.018353: step: 192/526, loss: 0.003356741974130273
2023-01-24 09:13:57.086954: step: 196/526, loss: 0.00032153548090718687
2023-01-24 09:13:58.174720: step: 200/526, loss: 0.0027515965048223734
2023-01-24 09:13:59.248291: step: 204/526, loss: 0.0005426167626865208
2023-01-24 09:14:00.319959: step: 208/526, loss: 0.0001539260701974854
2023-01-24 09:14:01.392626: step: 212/526, loss: 0.004132452886551619
2023-01-24 09:14:02.462897: step: 216/526, loss: 0.0036066637840121984
2023-01-24 09:14:03.535165: step: 220/526, loss: 0.010818486101925373
2023-01-24 09:14:04.597145: step: 224/526, loss: 7.07808940205723e-05
2023-01-24 09:14:05.676538: step: 228/526, loss: 0.027018606662750244
2023-01-24 09:14:06.762562: step: 232/526, loss: 0.008826402947306633
2023-01-24 09:14:07.845221: step: 236/526, loss: 0.00012490537483245134
2023-01-24 09:14:08.895462: step: 240/526, loss: 9.547896479489282e-05
2023-01-24 09:14:09.981573: step: 244/526, loss: 0.0031370255164802074
2023-01-24 09:14:11.054550: step: 248/526, loss: 0.00010075035970658064
2023-01-24 09:14:12.128275: step: 252/526, loss: 0.002512074541300535
2023-01-24 09:14:13.209260: step: 256/526, loss: 0.001070154830813408
2023-01-24 09:14:14.267632: step: 260/526, loss: 0.0002965281018987298
2023-01-24 09:14:15.339569: step: 264/526, loss: 0.0008890108438208699
2023-01-24 09:14:16.411636: step: 268/526, loss: 0.0033979739528149366
2023-01-24 09:14:17.498079: step: 272/526, loss: 0.0011074502253904939
2023-01-24 09:14:18.578263: step: 276/526, loss: 0.00023713205882813781
2023-01-24 09:14:19.636467: step: 280/526, loss: 0.010953271761536598
2023-01-24 09:14:20.702667: step: 284/526, loss: 0.00011625825572991744
2023-01-24 09:14:21.801293: step: 288/526, loss: 0.0014055744977667928
2023-01-24 09:14:22.885888: step: 292/526, loss: 0.005265504587441683
2023-01-24 09:14:23.986066: step: 296/526, loss: 0.0021303279791027308
2023-01-24 09:14:25.057011: step: 300/526, loss: 0.0002604361798148602
2023-01-24 09:14:26.135284: step: 304/526, loss: 0.0006046337075531483
2023-01-24 09:14:27.197160: step: 308/526, loss: 0.0003276804636698216
2023-01-24 09:14:28.275633: step: 312/526, loss: 0.0008781430660746992
2023-01-24 09:14:29.347859: step: 316/526, loss: 3.695489795063622e-05
2023-01-24 09:14:30.432957: step: 320/526, loss: 0.0010540714720264077
2023-01-24 09:14:31.491404: step: 324/526, loss: 0.0006770803011022508
2023-01-24 09:14:32.563837: step: 328/526, loss: 0.0005231563118286431
2023-01-24 09:14:33.633636: step: 332/526, loss: 0.006028560921549797
2023-01-24 09:14:34.706876: step: 336/526, loss: 0.0022658423986285925
2023-01-24 09:14:35.784668: step: 340/526, loss: 0.0016470607370138168
2023-01-24 09:14:36.863462: step: 344/526, loss: 0.0007941769436001778
2023-01-24 09:14:37.927441: step: 348/526, loss: 0.0001967969146789983
2023-01-24 09:14:39.013493: step: 352/526, loss: 0.0034742760471999645
2023-01-24 09:14:40.095172: step: 356/526, loss: 0.00588691420853138
2023-01-24 09:14:41.170699: step: 360/526, loss: 0.002327021909877658
2023-01-24 09:14:42.228596: step: 364/526, loss: 0.0023656049743294716
2023-01-24 09:14:43.317607: step: 368/526, loss: 0.0026068270672112703
2023-01-24 09:14:44.376923: step: 372/526, loss: 0.0004402359772939235
2023-01-24 09:14:45.443596: step: 376/526, loss: 0.0018315461929887533
2023-01-24 09:14:46.520769: step: 380/526, loss: 0.0009081062162294984
2023-01-24 09:14:47.591008: step: 384/526, loss: 0.00020659201254602522
2023-01-24 09:14:48.655472: step: 388/526, loss: 0.00024463256704621017
2023-01-24 09:14:49.750402: step: 392/526, loss: 0.04892623797059059
2023-01-24 09:14:50.810428: step: 396/526, loss: 0.0076407152228057384
2023-01-24 09:14:51.905457: step: 400/526, loss: 0.0008287741802632809
2023-01-24 09:14:52.980443: step: 404/526, loss: 0.0003356395463924855
2023-01-24 09:14:54.054650: step: 408/526, loss: 0.01065562292933464
2023-01-24 09:14:55.120698: step: 412/526, loss: 5.333791341399774e-05
2023-01-24 09:14:56.206703: step: 416/526, loss: 6.649323040619493e-05
2023-01-24 09:14:57.278773: step: 420/526, loss: 0.00020237365970388055
2023-01-24 09:14:58.341202: step: 424/526, loss: 2.79204632533947e-05
2023-01-24 09:14:59.424601: step: 428/526, loss: 0.0009523549815639853
2023-01-24 09:15:00.480441: step: 432/526, loss: 0.00656931521371007
2023-01-24 09:15:01.546681: step: 436/526, loss: 1.2138661986682564e-06
2023-01-24 09:15:02.611144: step: 440/526, loss: 2.51901747105876e-05
2023-01-24 09:15:03.696489: step: 444/526, loss: 0.002826628740876913
2023-01-24 09:15:04.759777: step: 448/526, loss: 6.302967813098803e-05
2023-01-24 09:15:05.828498: step: 452/526, loss: 0.006691085174679756
2023-01-24 09:15:06.900705: step: 456/526, loss: 0.0016829074593260884
2023-01-24 09:15:07.981522: step: 460/526, loss: 0.004967859480530024
2023-01-24 09:15:09.063413: step: 464/526, loss: 0.001895446446724236
2023-01-24 09:15:10.125313: step: 468/526, loss: 0.006243078038096428
2023-01-24 09:15:11.230918: step: 472/526, loss: 0.002942392136901617
2023-01-24 09:15:12.288461: step: 476/526, loss: 0.0003913755645044148
2023-01-24 09:15:13.382813: step: 480/526, loss: 0.0001730632793623954
2023-01-24 09:15:14.453441: step: 484/526, loss: 0.0012408597394824028
2023-01-24 09:15:15.537464: step: 488/526, loss: 2.2972491933614947e-05
2023-01-24 09:15:16.615361: step: 492/526, loss: 0.0018391635967418551
2023-01-24 09:15:17.707317: step: 496/526, loss: 0.0035132095217704773
2023-01-24 09:15:18.782305: step: 500/526, loss: 0.0032427296973764896
2023-01-24 09:15:19.839743: step: 504/526, loss: 0.0003710891760420054
2023-01-24 09:15:20.919763: step: 508/526, loss: 0.00019869758398272097
2023-01-24 09:15:21.990181: step: 512/526, loss: 0.012902242131531239
2023-01-24 09:15:23.063961: step: 516/526, loss: 0.006148544140160084
2023-01-24 09:15:24.126268: step: 520/526, loss: 0.0013278629630804062
2023-01-24 09:15:25.185152: step: 524/526, loss: 0.00012468411296140403
2023-01-24 09:15:26.243762: step: 528/526, loss: 0.0007348512881435454
2023-01-24 09:15:27.326385: step: 532/526, loss: 0.0028557819314301014
2023-01-24 09:15:28.386822: step: 536/526, loss: 0.0013069960987195373
2023-01-24 09:15:29.454344: step: 540/526, loss: 5.154605560164782e-07
2023-01-24 09:15:30.518291: step: 544/526, loss: 0.005783005617558956
2023-01-24 09:15:31.576938: step: 548/526, loss: 0.004283764399588108
2023-01-24 09:15:32.661670: step: 552/526, loss: 0.0016775608528405428
2023-01-24 09:15:33.726067: step: 556/526, loss: 0.002984053920954466
2023-01-24 09:15:34.811883: step: 560/526, loss: 0.005226318724453449
2023-01-24 09:15:35.890710: step: 564/526, loss: 0.004898657090961933
2023-01-24 09:15:36.962481: step: 568/526, loss: 0.000245068920776248
2023-01-24 09:15:38.072481: step: 572/526, loss: 0.0023428683634847403
2023-01-24 09:15:39.134176: step: 576/526, loss: 0.0027577108703553677
2023-01-24 09:15:40.202296: step: 580/526, loss: 0.008508670143783092
2023-01-24 09:15:41.261488: step: 584/526, loss: 0.00961547251790762
2023-01-24 09:15:42.318959: step: 588/526, loss: 6.287618361966452e-06
2023-01-24 09:15:43.410460: step: 592/526, loss: 0.00040863556205295026
2023-01-24 09:15:44.476169: step: 596/526, loss: 0.001620003255084157
2023-01-24 09:15:45.535171: step: 600/526, loss: 0.0004178356612101197
2023-01-24 09:15:46.588715: step: 604/526, loss: 0.0023813536390662193
2023-01-24 09:15:47.650584: step: 608/526, loss: 0.003520034020766616
2023-01-24 09:15:48.732796: step: 612/526, loss: 0.004535804968327284
2023-01-24 09:15:49.802117: step: 616/526, loss: 0.005251354072242975
2023-01-24 09:15:50.883311: step: 620/526, loss: 0.006738132797181606
2023-01-24 09:15:51.957520: step: 624/526, loss: 0.009503346867859364
2023-01-24 09:15:53.035437: step: 628/526, loss: 0.0016803494654595852
2023-01-24 09:15:54.093189: step: 632/526, loss: 0.0001733922545099631
2023-01-24 09:15:55.145581: step: 636/526, loss: 0.0021864569280296564
2023-01-24 09:15:56.208705: step: 640/526, loss: 0.0009065971826203167
2023-01-24 09:15:57.282368: step: 644/526, loss: 0.004248241428285837
2023-01-24 09:15:58.363451: step: 648/526, loss: 0.003038237104192376
2023-01-24 09:15:59.416063: step: 652/526, loss: 0.0012156427837908268
2023-01-24 09:16:00.477637: step: 656/526, loss: 0.0007117817876860499
2023-01-24 09:16:01.548852: step: 660/526, loss: 0.0007347794016823173
2023-01-24 09:16:02.605880: step: 664/526, loss: 0.000734483590349555
2023-01-24 09:16:03.679286: step: 668/526, loss: 0.003017725655809045
2023-01-24 09:16:04.745372: step: 672/526, loss: 3.981875124736689e-06
2023-01-24 09:16:05.841922: step: 676/526, loss: 0.0028258981183171272
2023-01-24 09:16:06.926147: step: 680/526, loss: 7.842243940103799e-05
2023-01-24 09:16:07.992029: step: 684/526, loss: 0.003698616288602352
2023-01-24 09:16:09.063324: step: 688/526, loss: 0.012323994189500809
2023-01-24 09:16:10.119948: step: 692/526, loss: 0.00047964302939362824
2023-01-24 09:16:11.186229: step: 696/526, loss: 0.008856515400111675
2023-01-24 09:16:12.235458: step: 700/526, loss: 0.0016728986520320177
2023-01-24 09:16:13.333865: step: 704/526, loss: 0.003224977059289813
2023-01-24 09:16:14.411581: step: 708/526, loss: 0.0005297587485983968
2023-01-24 09:16:15.498352: step: 712/526, loss: 0.0014179447898641229
2023-01-24 09:16:16.566872: step: 716/526, loss: 0.0033910893835127354
2023-01-24 09:16:17.647560: step: 720/526, loss: 0.0012026974000036716
2023-01-24 09:16:18.706879: step: 724/526, loss: 0.0008877201471477747
2023-01-24 09:16:19.782557: step: 728/526, loss: 0.0003373197396285832
2023-01-24 09:16:20.843189: step: 732/526, loss: 0.003152693621814251
2023-01-24 09:16:21.902989: step: 736/526, loss: 0.0013204979477450252
2023-01-24 09:16:22.972108: step: 740/526, loss: 0.0005635274574160576
2023-01-24 09:16:24.043591: step: 744/526, loss: 3.672230013762601e-05
2023-01-24 09:16:25.105429: step: 748/526, loss: 0.00015696999616920948
2023-01-24 09:16:26.157648: step: 752/526, loss: 2.9896282285335474e-05
2023-01-24 09:16:27.214474: step: 756/526, loss: 0.00040561743662692606
2023-01-24 09:16:28.290072: step: 760/526, loss: 0.014711439609527588
2023-01-24 09:16:29.364598: step: 764/526, loss: 0.00485612777993083
2023-01-24 09:16:30.439488: step: 768/526, loss: 0.0010174484923481941
2023-01-24 09:16:31.495194: step: 772/526, loss: 0.0018834865186363459
2023-01-24 09:16:32.568062: step: 776/526, loss: 0.0003905899648088962
2023-01-24 09:16:33.638410: step: 780/526, loss: 0.0012355458457022905
2023-01-24 09:16:34.703229: step: 784/526, loss: 0.0020234622061252594
2023-01-24 09:16:35.772847: step: 788/526, loss: 3.3573032851563767e-05
2023-01-24 09:16:36.855058: step: 792/526, loss: 0.0018341653048992157
2023-01-24 09:16:37.949225: step: 796/526, loss: 0.012312685139477253
2023-01-24 09:16:39.010780: step: 800/526, loss: 0.0008794953464530408
2023-01-24 09:16:40.071939: step: 804/526, loss: 0.0002312470314791426
2023-01-24 09:16:41.139189: step: 808/526, loss: 0.00383273814804852
2023-01-24 09:16:42.191761: step: 812/526, loss: 0.0037538649048656225
2023-01-24 09:16:43.262352: step: 816/526, loss: 0.005142300855368376
2023-01-24 09:16:44.319339: step: 820/526, loss: 0.0004101977974642068
2023-01-24 09:16:45.388459: step: 824/526, loss: 0.0037264302372932434
2023-01-24 09:16:46.451004: step: 828/526, loss: 0.0015933893155306578
2023-01-24 09:16:47.516061: step: 832/526, loss: 3.902550361090107e-06
2023-01-24 09:16:48.577330: step: 836/526, loss: 0.0007026093080639839
2023-01-24 09:16:49.638635: step: 840/526, loss: 6.361864961945685e-06
2023-01-24 09:16:50.723332: step: 844/526, loss: 0.005074107553809881
2023-01-24 09:16:51.801645: step: 848/526, loss: 0.0006282091489993036
2023-01-24 09:16:52.864123: step: 852/526, loss: 0.025801418349146843
2023-01-24 09:16:53.928691: step: 856/526, loss: 0.00027012216742150486
2023-01-24 09:16:55.014504: step: 860/526, loss: 0.0008300377521663904
2023-01-24 09:16:56.078310: step: 864/526, loss: 0.0003779538383241743
2023-01-24 09:16:57.133415: step: 868/526, loss: 0.0005150707438588142
2023-01-24 09:16:58.198149: step: 872/526, loss: 0.0019969423301517963
2023-01-24 09:16:59.289547: step: 876/526, loss: 0.003915760666131973
2023-01-24 09:17:00.357356: step: 880/526, loss: 0.0008733583963476121
2023-01-24 09:17:01.426077: step: 884/526, loss: 0.000988204381428659
2023-01-24 09:17:02.488173: step: 888/526, loss: 0.00015588136739097536
2023-01-24 09:17:03.593764: step: 892/526, loss: 0.004775822162628174
2023-01-24 09:17:04.651787: step: 896/526, loss: 0.00043138235923834145
2023-01-24 09:17:05.735469: step: 900/526, loss: 0.0018807523883879185
2023-01-24 09:17:06.814368: step: 904/526, loss: 0.002841358305886388
2023-01-24 09:17:07.884960: step: 908/526, loss: 0.008554196916520596
2023-01-24 09:17:08.959609: step: 912/526, loss: 0.0013046994572505355
2023-01-24 09:17:10.035413: step: 916/526, loss: 0.002964446786791086
2023-01-24 09:17:11.104478: step: 920/526, loss: 0.007046420592814684
2023-01-24 09:17:12.167261: step: 924/526, loss: 0.00029620452551171184
2023-01-24 09:17:13.235171: step: 928/526, loss: 0.0010005889926105738
2023-01-24 09:17:14.305785: step: 932/526, loss: 0.005172127857804298
2023-01-24 09:17:15.356790: step: 936/526, loss: 1.3173620573070366e-05
2023-01-24 09:17:16.419376: step: 940/526, loss: 0.0014675639104098082
2023-01-24 09:17:17.493776: step: 944/526, loss: 0.0006840009591542184
2023-01-24 09:17:18.566068: step: 948/526, loss: 0.0015970367239788175
2023-01-24 09:17:19.645733: step: 952/526, loss: 0.00048429524758830667
2023-01-24 09:17:20.717197: step: 956/526, loss: 0.00012359561515040696
2023-01-24 09:17:21.771687: step: 960/526, loss: 0.0005046874866820872
2023-01-24 09:17:22.842036: step: 964/526, loss: 0.005257238168269396
2023-01-24 09:17:23.918817: step: 968/526, loss: 0.00025499783805571496
2023-01-24 09:17:24.988280: step: 972/526, loss: 0.0010451560374349356
2023-01-24 09:17:26.073595: step: 976/526, loss: 0.005054119508713484
2023-01-24 09:17:27.165052: step: 980/526, loss: 0.002518031280487776
2023-01-24 09:17:28.229276: step: 984/526, loss: 0.002625023713335395
2023-01-24 09:17:29.306702: step: 988/526, loss: 0.0029690733645111322
2023-01-24 09:17:30.365480: step: 992/526, loss: 0.0016516625182703137
2023-01-24 09:17:31.430872: step: 996/526, loss: 0.004330814816057682
2023-01-24 09:17:32.513327: step: 1000/526, loss: 0.0007549662259407341
2023-01-24 09:17:33.573122: step: 1004/526, loss: 0.001201360602863133
2023-01-24 09:17:34.645165: step: 1008/526, loss: 0.025760134682059288
2023-01-24 09:17:35.738619: step: 1012/526, loss: 0.0006959103047847748
2023-01-24 09:17:36.806111: step: 1016/526, loss: 0.0007833081763237715
2023-01-24 09:17:37.881616: step: 1020/526, loss: 0.00019327751942910254
2023-01-24 09:17:38.954597: step: 1024/526, loss: 0.005619648844003677
2023-01-24 09:17:40.015399: step: 1028/526, loss: 0.0009776627412065864
2023-01-24 09:17:41.074317: step: 1032/526, loss: 6.949681119294837e-05
2023-01-24 09:17:42.138513: step: 1036/526, loss: 0.019426757469773293
2023-01-24 09:17:43.220148: step: 1040/526, loss: 0.007642331998795271
2023-01-24 09:17:44.318562: step: 1044/526, loss: 0.00037573548615910113
2023-01-24 09:17:45.393275: step: 1048/526, loss: 0.0027573942206799984
2023-01-24 09:17:46.467064: step: 1052/526, loss: 0.006561039015650749
2023-01-24 09:17:47.534622: step: 1056/526, loss: 0.000256403029197827
2023-01-24 09:17:48.600901: step: 1060/526, loss: 0.026282310485839844
2023-01-24 09:17:49.661748: step: 1064/526, loss: 0.0025156671181321144
2023-01-24 09:17:50.723942: step: 1068/526, loss: 0.002596191829070449
2023-01-24 09:17:51.787123: step: 1072/526, loss: 0.0012271407758817077
2023-01-24 09:17:52.865653: step: 1076/526, loss: 0.0027946566697210073
2023-01-24 09:17:53.927265: step: 1080/526, loss: 0.008756760507822037
2023-01-24 09:17:55.004950: step: 1084/526, loss: 0.009264402091503143
2023-01-24 09:17:56.071631: step: 1088/526, loss: 0.0018663645023480058
2023-01-24 09:17:57.151740: step: 1092/526, loss: 0.004904875531792641
2023-01-24 09:17:58.215989: step: 1096/526, loss: 0.0001582323748152703
2023-01-24 09:17:59.270135: step: 1100/526, loss: 0.000568255374673754
2023-01-24 09:18:00.330105: step: 1104/526, loss: 0.004775824025273323
2023-01-24 09:18:01.393474: step: 1108/526, loss: 0.0055280146189033985
2023-01-24 09:18:02.457015: step: 1112/526, loss: 0.003691577585414052
2023-01-24 09:18:03.512492: step: 1116/526, loss: 0.00018885928147938102
2023-01-24 09:18:04.581781: step: 1120/526, loss: 0.0007241407874971628
2023-01-24 09:18:05.663562: step: 1124/526, loss: 0.00014857054338790476
2023-01-24 09:18:06.727900: step: 1128/526, loss: 9.757585939951241e-05
2023-01-24 09:18:07.794811: step: 1132/526, loss: 0.0001084349351003766
2023-01-24 09:18:08.860172: step: 1136/526, loss: 0.00022744714806322008
2023-01-24 09:18:09.924425: step: 1140/526, loss: 0.0033771421294659376
2023-01-24 09:18:10.990197: step: 1144/526, loss: 0.008672861382365227
2023-01-24 09:18:12.046919: step: 1148/526, loss: 0.0002721585042309016
2023-01-24 09:18:13.106138: step: 1152/526, loss: 0.0007387588266283274
2023-01-24 09:18:14.166591: step: 1156/526, loss: 0.0036961787845939398
2023-01-24 09:18:15.240869: step: 1160/526, loss: 0.007462798152118921
2023-01-24 09:18:16.296406: step: 1164/526, loss: 4.965122116118437e-06
2023-01-24 09:18:17.375416: step: 1168/526, loss: 0.0025989911518990993
2023-01-24 09:18:18.456947: step: 1172/526, loss: 9.702862371341325e-06
2023-01-24 09:18:19.516953: step: 1176/526, loss: 0.007660785689949989
2023-01-24 09:18:20.581325: step: 1180/526, loss: 0.0233598779886961
2023-01-24 09:18:21.657526: step: 1184/526, loss: 0.00031129305716603994
2023-01-24 09:18:22.735028: step: 1188/526, loss: 0.0014312692219391465
2023-01-24 09:18:23.804469: step: 1192/526, loss: 0.006747620180249214
2023-01-24 09:18:24.885208: step: 1196/526, loss: 0.0053878226317465305
2023-01-24 09:18:25.960979: step: 1200/526, loss: 0.00036053103394806385
2023-01-24 09:18:27.024430: step: 1204/526, loss: 0.004016116727143526
2023-01-24 09:18:28.112368: step: 1208/526, loss: 0.0005234128329902887
2023-01-24 09:18:29.182112: step: 1212/526, loss: 0.0008772523142397404
2023-01-24 09:18:30.252483: step: 1216/526, loss: 0.0006490530795417726
2023-01-24 09:18:31.313551: step: 1220/526, loss: 0.002764162141829729
2023-01-24 09:18:32.371652: step: 1224/526, loss: 0.00039265770465135574
2023-01-24 09:18:33.423279: step: 1228/526, loss: 0.0022180587984621525
2023-01-24 09:18:34.501965: step: 1232/526, loss: 0.002280870685353875
2023-01-24 09:18:35.579395: step: 1236/526, loss: 0.0023603339213877916
2023-01-24 09:18:36.643533: step: 1240/526, loss: 0.0003964714123867452
2023-01-24 09:18:37.719796: step: 1244/526, loss: 0.022700568661093712
2023-01-24 09:18:38.792935: step: 1248/526, loss: 0.0120023088529706
2023-01-24 09:18:39.860998: step: 1252/526, loss: 0.001121222274377942
2023-01-24 09:18:40.947237: step: 1256/526, loss: 0.0008426845888607204
2023-01-24 09:18:41.993362: step: 1260/526, loss: 0.005639289505779743
2023-01-24 09:18:43.074617: step: 1264/526, loss: 0.05096236243844032
2023-01-24 09:18:44.153608: step: 1268/526, loss: 0.00015530727978330106
2023-01-24 09:18:45.222850: step: 1272/526, loss: 0.004302356857806444
2023-01-24 09:18:46.291816: step: 1276/526, loss: 4.115326373721473e-05
2023-01-24 09:18:47.355350: step: 1280/526, loss: 0.002614434575662017
2023-01-24 09:18:48.417967: step: 1284/526, loss: 0.004619142971932888
2023-01-24 09:18:49.475492: step: 1288/526, loss: 0.001732018543407321
2023-01-24 09:18:50.524893: step: 1292/526, loss: 0.01094040460884571
2023-01-24 09:18:51.592141: step: 1296/526, loss: 0.009468117728829384
2023-01-24 09:18:52.651806: step: 1300/526, loss: 0.00018498997087590396
2023-01-24 09:18:53.730084: step: 1304/526, loss: 0.004117588046938181
2023-01-24 09:18:54.785033: step: 1308/526, loss: 0.0008519261027686298
2023-01-24 09:18:55.878403: step: 1312/526, loss: 0.0042347111739218235
2023-01-24 09:18:56.950137: step: 1316/526, loss: 0.002486675977706909
2023-01-24 09:18:58.009447: step: 1320/526, loss: 0.004362615756690502
2023-01-24 09:18:59.076474: step: 1324/526, loss: 0.004353542346507311
2023-01-24 09:19:00.151944: step: 1328/526, loss: 0.0025297722313553095
2023-01-24 09:19:01.199271: step: 1332/526, loss: 0.0013502462534233928
2023-01-24 09:19:02.261721: step: 1336/526, loss: 0.004053368698805571
2023-01-24 09:19:03.339456: step: 1340/526, loss: 0.0014518317766487598
2023-01-24 09:19:04.392141: step: 1344/526, loss: 0.000652880291454494
2023-01-24 09:19:05.463282: step: 1348/526, loss: 7.175199425546452e-05
2023-01-24 09:19:06.528122: step: 1352/526, loss: 0.00521273585036397
2023-01-24 09:19:07.597103: step: 1356/526, loss: 0.0006639304338023067
2023-01-24 09:19:08.679352: step: 1360/526, loss: 0.009443363174796104
2023-01-24 09:19:09.751094: step: 1364/526, loss: 0.021721703931689262
2023-01-24 09:19:10.820519: step: 1368/526, loss: 0.009586770087480545
2023-01-24 09:19:11.905612: step: 1372/526, loss: 0.0026133153587579727
2023-01-24 09:19:12.957289: step: 1376/526, loss: 0.004981752950698137
2023-01-24 09:19:14.010166: step: 1380/526, loss: 0.0008841459057293832
2023-01-24 09:19:15.071757: step: 1384/526, loss: 0.005524763371795416
2023-01-24 09:19:16.138354: step: 1388/526, loss: 0.004551276098936796
2023-01-24 09:19:17.204706: step: 1392/526, loss: 0.0033916854299604893
2023-01-24 09:19:18.274367: step: 1396/526, loss: 0.0003417876723688096
2023-01-24 09:19:19.333935: step: 1400/526, loss: 0.005211398005485535
2023-01-24 09:19:20.382801: step: 1404/526, loss: 0.0066888281144201756
2023-01-24 09:19:21.464433: step: 1408/526, loss: 0.001584374695084989
2023-01-24 09:19:22.547380: step: 1412/526, loss: 0.01504538208246231
2023-01-24 09:19:23.621350: step: 1416/526, loss: 0.006462868768721819
2023-01-24 09:19:24.700900: step: 1420/526, loss: 2.6769657779368572e-05
2023-01-24 09:19:25.768146: step: 1424/526, loss: 0.0009967457735911012
2023-01-24 09:19:26.816039: step: 1428/526, loss: 0.000379564386093989
2023-01-24 09:19:27.867344: step: 1432/526, loss: 1.5280096704373136e-05
2023-01-24 09:19:28.923388: step: 1436/526, loss: 0.0013429338578134775
2023-01-24 09:19:29.991353: step: 1440/526, loss: 0.0020745915826410055
2023-01-24 09:19:31.064973: step: 1444/526, loss: 6.939359445823357e-05
2023-01-24 09:19:32.129748: step: 1448/526, loss: 0.007030988112092018
2023-01-24 09:19:33.201268: step: 1452/526, loss: 0.0007565665291622281
2023-01-24 09:19:34.266282: step: 1456/526, loss: 0.0010497402399778366
2023-01-24 09:19:35.345396: step: 1460/526, loss: 0.0021779565140604973
2023-01-24 09:19:36.396233: step: 1464/526, loss: 1.1618034477578476e-05
2023-01-24 09:19:37.480441: step: 1468/526, loss: 0.0005448565352708101
2023-01-24 09:19:38.563263: step: 1472/526, loss: 0.0010734691750258207
2023-01-24 09:19:39.609060: step: 1476/526, loss: 0.00302223046310246
2023-01-24 09:19:40.664899: step: 1480/526, loss: 0.0034733391366899014
2023-01-24 09:19:41.736642: step: 1484/526, loss: 5.210693871049443e-06
2023-01-24 09:19:42.798138: step: 1488/526, loss: 0.009244834072887897
2023-01-24 09:19:43.884148: step: 1492/526, loss: 0.0016329266363754869
2023-01-24 09:19:44.946762: step: 1496/526, loss: 0.007443442940711975
2023-01-24 09:19:46.010871: step: 1500/526, loss: 0.005738737992942333
2023-01-24 09:19:47.078628: step: 1504/526, loss: 0.009049099870026112
2023-01-24 09:19:48.137242: step: 1508/526, loss: 0.0006189775886014104
2023-01-24 09:19:49.205559: step: 1512/526, loss: 0.0015118439914658666
2023-01-24 09:19:50.265360: step: 1516/526, loss: 1.087980763259111e-06
2023-01-24 09:19:51.316054: step: 1520/526, loss: 0.005591883324086666
2023-01-24 09:19:52.382709: step: 1524/526, loss: 0.0005771254654973745
2023-01-24 09:19:53.463755: step: 1528/526, loss: 0.005772868171334267
2023-01-24 09:19:54.527370: step: 1532/526, loss: 0.0005950903287157416
2023-01-24 09:19:55.577564: step: 1536/526, loss: 0.0033837007358670235
2023-01-24 09:19:56.637471: step: 1540/526, loss: 0.0016145651461556554
2023-01-24 09:19:57.694260: step: 1544/526, loss: 0.002009027637541294
2023-01-24 09:19:58.748978: step: 1548/526, loss: 0.004241458605974913
2023-01-24 09:19:59.820641: step: 1552/526, loss: 0.03162920102477074
2023-01-24 09:20:00.892293: step: 1556/526, loss: 0.04032851383090019
2023-01-24 09:20:01.955284: step: 1560/526, loss: 4.8521524149691686e-05
2023-01-24 09:20:03.028823: step: 1564/526, loss: 0.002941735554486513
2023-01-24 09:20:04.091452: step: 1568/526, loss: 0.0013211008626967669
2023-01-24 09:20:05.158255: step: 1572/526, loss: 0.00104530097451061
2023-01-24 09:20:06.207110: step: 1576/526, loss: 0.00015663108206354082
2023-01-24 09:20:07.280363: step: 1580/526, loss: 0.00042911607306450605
2023-01-24 09:20:08.338978: step: 1584/526, loss: 0.0017179639544337988
2023-01-24 09:20:09.397641: step: 1588/526, loss: 0.0005434823106043041
2023-01-24 09:20:10.475670: step: 1592/526, loss: 0.007555896881967783
2023-01-24 09:20:11.550038: step: 1596/526, loss: 0.0017910299357026815
2023-01-24 09:20:12.610718: step: 1600/526, loss: 0.011661226861178875
2023-01-24 09:20:13.684958: step: 1604/526, loss: 0.008104612119495869
2023-01-24 09:20:14.757365: step: 1608/526, loss: 0.01066520158201456
2023-01-24 09:20:15.828505: step: 1612/526, loss: 0.00431863171979785
2023-01-24 09:20:16.891164: step: 1616/526, loss: 0.0006449631182476878
2023-01-24 09:20:17.949248: step: 1620/526, loss: 0.0013828417286276817
2023-01-24 09:20:19.009846: step: 1624/526, loss: 0.000535124447196722
2023-01-24 09:20:20.091606: step: 1628/526, loss: 0.0016050381818786263
2023-01-24 09:20:21.143421: step: 1632/526, loss: 0.0070837028324604034
2023-01-24 09:20:22.210999: step: 1636/526, loss: 0.005527130328118801
2023-01-24 09:20:23.299746: step: 1640/526, loss: 0.010753164999186993
2023-01-24 09:20:24.357662: step: 1644/526, loss: 0.002849144861102104
2023-01-24 09:20:25.424567: step: 1648/526, loss: 0.00012709471047855914
2023-01-24 09:20:26.482618: step: 1652/526, loss: 0.00023370598501060158
2023-01-24 09:20:27.560960: step: 1656/526, loss: 0.00445404089987278
2023-01-24 09:20:28.617590: step: 1660/526, loss: 0.023180246353149414
2023-01-24 09:20:29.691078: step: 1664/526, loss: 0.0011947044404223561
2023-01-24 09:20:30.766447: step: 1668/526, loss: 0.004260911140590906
2023-01-24 09:20:31.846519: step: 1672/526, loss: 8.963334403233603e-05
2023-01-24 09:20:32.933427: step: 1676/526, loss: 0.0007914318703114986
2023-01-24 09:20:33.992426: step: 1680/526, loss: 0.0015796126099303365
2023-01-24 09:20:35.066076: step: 1684/526, loss: 0.0013691557105630636
2023-01-24 09:20:36.127687: step: 1688/526, loss: 0.0003086199576500803
2023-01-24 09:20:37.204605: step: 1692/526, loss: 0.008661982603371143
2023-01-24 09:20:38.269172: step: 1696/526, loss: 0.00021431955974549055
2023-01-24 09:20:39.328544: step: 1700/526, loss: 0.001694253645837307
2023-01-24 09:20:40.382341: step: 1704/526, loss: 0.0001425338996341452
2023-01-24 09:20:41.431070: step: 1708/526, loss: 0.002138415351510048
2023-01-24 09:20:42.487051: step: 1712/526, loss: 0.00791004579514265
2023-01-24 09:20:43.564875: step: 1716/526, loss: 0.00325650442391634
2023-01-24 09:20:44.630208: step: 1720/526, loss: 0.007972813211381435
2023-01-24 09:20:45.693948: step: 1724/526, loss: 0.001294921850785613
2023-01-24 09:20:46.789676: step: 1728/526, loss: 0.0015757974470034242
2023-01-24 09:20:47.867039: step: 1732/526, loss: 0.007017717696726322
2023-01-24 09:20:48.936933: step: 1736/526, loss: 0.0016986187547445297
2023-01-24 09:20:49.996112: step: 1740/526, loss: 0.0077350446954369545
2023-01-24 09:20:51.063205: step: 1744/526, loss: 0.0003149181429762393
2023-01-24 09:20:52.124262: step: 1748/526, loss: 0.0009582445491105318
2023-01-24 09:20:53.185309: step: 1752/526, loss: 0.001306909485720098
2023-01-24 09:20:54.228806: step: 1756/526, loss: 0.00040419885772280395
2023-01-24 09:20:55.284041: step: 1760/526, loss: 0.0005854007904417813
2023-01-24 09:20:56.351000: step: 1764/526, loss: 0.018983155488967896
2023-01-24 09:20:57.414856: step: 1768/526, loss: 0.0009746649884618819
2023-01-24 09:20:58.474389: step: 1772/526, loss: 0.0016093113226816058
2023-01-24 09:20:59.548978: step: 1776/526, loss: 0.00048363127280026674
2023-01-24 09:21:00.615470: step: 1780/526, loss: 0.004746370483189821
2023-01-24 09:21:01.676690: step: 1784/526, loss: 0.003191588679328561
2023-01-24 09:21:02.729469: step: 1788/526, loss: 0.004765322897583246
2023-01-24 09:21:03.775636: step: 1792/526, loss: 0.002008237410336733
2023-01-24 09:21:04.848930: step: 1796/526, loss: 0.0025999981444329023
2023-01-24 09:21:05.900376: step: 1800/526, loss: 0.0008397491765208542
2023-01-24 09:21:06.988369: step: 1804/526, loss: 0.04514950513839722
2023-01-24 09:21:08.052398: step: 1808/526, loss: 0.005623677745461464
2023-01-24 09:21:09.108152: step: 1812/526, loss: 0.0019293545046821237
2023-01-24 09:21:10.184302: step: 1816/526, loss: 0.005144578870385885
2023-01-24 09:21:11.232955: step: 1820/526, loss: 0.0005856275092810392
2023-01-24 09:21:12.296670: step: 1824/526, loss: 0.0028202657122164965
2023-01-24 09:21:13.345029: step: 1828/526, loss: 0.0016322726150974631
2023-01-24 09:21:14.406230: step: 1832/526, loss: 0.024153169244527817
2023-01-24 09:21:15.454850: step: 1836/526, loss: 0.03205622360110283
2023-01-24 09:21:16.522822: step: 1840/526, loss: 0.013268989510834217
2023-01-24 09:21:17.588358: step: 1844/526, loss: 0.0019674438517540693
2023-01-24 09:21:18.646966: step: 1848/526, loss: 8.317752508446574e-05
2023-01-24 09:21:19.711414: step: 1852/526, loss: 2.348231828364078e-05
2023-01-24 09:21:20.772447: step: 1856/526, loss: 0.006586694624274969
2023-01-24 09:21:21.841398: step: 1860/526, loss: 4.206393350614235e-05
2023-01-24 09:21:22.902276: step: 1864/526, loss: 1.93113082787022e-05
2023-01-24 09:21:23.961588: step: 1868/526, loss: 0.00041411424172110856
2023-01-24 09:21:25.019094: step: 1872/526, loss: 0.0025553200393915176
2023-01-24 09:21:26.076492: step: 1876/526, loss: 0.015814675018191338
2023-01-24 09:21:27.145758: step: 1880/526, loss: 0.0005905671860091388
2023-01-24 09:21:28.210115: step: 1884/526, loss: 0.003998665139079094
2023-01-24 09:21:29.257673: step: 1888/526, loss: 1.3777264939562883e-05
2023-01-24 09:21:30.310307: step: 1892/526, loss: 0.000997500610537827
2023-01-24 09:21:31.367722: step: 1896/526, loss: 0.004966071341186762
2023-01-24 09:21:32.447297: step: 1900/526, loss: 0.006368839647620916
2023-01-24 09:21:33.492629: step: 1904/526, loss: 1.996709897866822e-06
2023-01-24 09:21:34.564063: step: 1908/526, loss: 0.009706745855510235
2023-01-24 09:21:35.616478: step: 1912/526, loss: 0.0
2023-01-24 09:21:36.677848: step: 1916/526, loss: 0.000681404781062156
2023-01-24 09:21:37.726087: step: 1920/526, loss: 0.00039162480970844626
2023-01-24 09:21:38.807819: step: 1924/526, loss: 0.004568703938275576
2023-01-24 09:21:39.896918: step: 1928/526, loss: 0.006932826712727547
2023-01-24 09:21:40.955479: step: 1932/526, loss: 0.010500838980078697
2023-01-24 09:21:42.008340: step: 1936/526, loss: 0.0037788108456879854
2023-01-24 09:21:43.067296: step: 1940/526, loss: 0.0022299950942397118
2023-01-24 09:21:44.133982: step: 1944/526, loss: 0.0011111543281003833
2023-01-24 09:21:45.186370: step: 1948/526, loss: 0.000446643796749413
2023-01-24 09:21:46.259678: step: 1952/526, loss: 0.01724560745060444
2023-01-24 09:21:47.329789: step: 1956/526, loss: 0.002889660419896245
2023-01-24 09:21:48.419846: step: 1960/526, loss: 0.005162473302334547
2023-01-24 09:21:49.475646: step: 1964/526, loss: 0.0034572849981486797
2023-01-24 09:21:50.553748: step: 1968/526, loss: 0.0018098610453307629
2023-01-24 09:21:51.605275: step: 1972/526, loss: 0.0025778994895517826
2023-01-24 09:21:52.666940: step: 1976/526, loss: 0.00012220801727380604
2023-01-24 09:21:53.729773: step: 1980/526, loss: 0.005837772972881794
2023-01-24 09:21:54.785484: step: 1984/526, loss: 0.00015310892194975168
2023-01-24 09:21:55.837352: step: 1988/526, loss: 0.006770716048777103
2023-01-24 09:21:56.895820: step: 1992/526, loss: 0.002294846111908555
2023-01-24 09:21:57.951789: step: 1996/526, loss: 0.006976480595767498
2023-01-24 09:21:59.024944: step: 2000/526, loss: 0.0006915026460774243
2023-01-24 09:22:00.095840: step: 2004/526, loss: 0.0003553621645551175
2023-01-24 09:22:01.167742: step: 2008/526, loss: 0.0068934205919504166
2023-01-24 09:22:02.242085: step: 2012/526, loss: 0.0031260449904948473
2023-01-24 09:22:03.315390: step: 2016/526, loss: 0.0005862055695615709
2023-01-24 09:22:04.363292: step: 2020/526, loss: 0.012843873351812363
2023-01-24 09:22:05.419998: step: 2024/526, loss: 1.1201146662642714e-05
2023-01-24 09:22:06.486993: step: 2028/526, loss: 0.0007346518686972558
2023-01-24 09:22:07.568244: step: 2032/526, loss: 0.0020734791178256273
2023-01-24 09:22:08.638464: step: 2036/526, loss: 0.0020234466064721346
2023-01-24 09:22:09.699816: step: 2040/526, loss: 0.0004323887114878744
2023-01-24 09:22:10.771120: step: 2044/526, loss: 0.0011445109266787767
2023-01-24 09:22:11.837197: step: 2048/526, loss: 5.2066792704863474e-05
2023-01-24 09:22:12.918640: step: 2052/526, loss: 0.0017658856231719255
2023-01-24 09:22:14.006231: step: 2056/526, loss: 0.011797196231782436
2023-01-24 09:22:15.085020: step: 2060/526, loss: 0.0002819258952513337
2023-01-24 09:22:16.160534: step: 2064/526, loss: 0.00212306366302073
2023-01-24 09:22:17.214540: step: 2068/526, loss: 0.00039372092578560114
2023-01-24 09:22:18.277770: step: 2072/526, loss: 0.0016727183246985078
2023-01-24 09:22:19.369585: step: 2076/526, loss: 0.0034725950099527836
2023-01-24 09:22:20.455293: step: 2080/526, loss: 0.0016738607082515955
2023-01-24 09:22:21.494711: step: 2084/526, loss: 1.2970345778740011e-05
2023-01-24 09:22:22.557422: step: 2088/526, loss: 0.007320513017475605
2023-01-24 09:22:23.631984: step: 2092/526, loss: 1.9310269635752775e-05
2023-01-24 09:22:24.703686: step: 2096/526, loss: 0.007351463660597801
2023-01-24 09:22:25.791435: step: 2100/526, loss: 0.0007869754335843027
2023-01-24 09:22:26.858145: step: 2104/526, loss: 0.0004477521579246968
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36186643217893216, 'r': 0.2719148143128219, 'f1': 0.3105072744157251}, 'combined': 0.22879483378000798, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3561518118977796, 'r': 0.2222283034897399, 'f1': 0.2736851106639839}, 'combined': 0.1492827876349003, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3386170461634435, 'r': 0.2942819869883437, 'f1': 0.31489666424945606}, 'combined': 0.23202912102591497, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35777687304680705, 'r': 0.25826711146745723, 'f1': 0.29998507208706776}, 'combined': 0.1636282211384006, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3583664670462727, 'r': 0.31484568167442933, 'f1': 0.3351993419038874}, 'combined': 0.24698898877128544, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36481344989761, 'r': 0.27703125655536714, 'f1': 0.31491956673428634}, 'combined': 0.17177430912779254, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 09:25:09.447144: step: 4/526, loss: 0.0463980957865715
2023-01-24 09:25:10.499857: step: 8/526, loss: 0.00010991937597282231
2023-01-24 09:25:11.545087: step: 12/526, loss: 0.004510130267590284
2023-01-24 09:25:12.603487: step: 16/526, loss: 1.4702322005177848e-05
2023-01-24 09:25:13.679101: step: 20/526, loss: 0.0006512802792713046
2023-01-24 09:25:14.747188: step: 24/526, loss: 0.0010251847561448812
2023-01-24 09:25:15.782734: step: 28/526, loss: 1.1938166608160827e-05
2023-01-24 09:25:16.853196: step: 32/526, loss: 0.00642089918255806
2023-01-24 09:25:17.912388: step: 36/526, loss: 1.5204660485323984e-05
2023-01-24 09:25:18.975686: step: 40/526, loss: 0.0020667295902967453
2023-01-24 09:25:20.036432: step: 44/526, loss: 0.004025040194392204
2023-01-24 09:25:21.098913: step: 48/526, loss: 0.0002887505106627941
2023-01-24 09:25:22.176907: step: 52/526, loss: 0.0001808819069992751
2023-01-24 09:25:23.258150: step: 56/526, loss: 0.0009427643963135779
2023-01-24 09:25:24.342713: step: 60/526, loss: 0.0016344982432201505
2023-01-24 09:25:25.395949: step: 64/526, loss: 4.090594302397221e-06
2023-01-24 09:25:26.458009: step: 68/526, loss: 0.0003312677436042577
2023-01-24 09:25:27.513476: step: 72/526, loss: 0.00603075185790658
2023-01-24 09:25:28.587234: step: 76/526, loss: 0.003071579383686185
2023-01-24 09:25:29.646388: step: 80/526, loss: 0.0028638802468776703
2023-01-24 09:25:30.698534: step: 84/526, loss: 0.001981923822313547
2023-01-24 09:25:31.749783: step: 88/526, loss: 0.0013352293753996491
2023-01-24 09:25:32.841779: step: 92/526, loss: 0.0016963854432106018
2023-01-24 09:25:33.897236: step: 96/526, loss: 0.0008963853470049798
2023-01-24 09:25:34.980216: step: 100/526, loss: 0.0018659612396731973
2023-01-24 09:25:36.043173: step: 104/526, loss: 0.0013818941079080105
2023-01-24 09:25:37.110187: step: 108/526, loss: 0.00042988662607967854
2023-01-24 09:25:38.170661: step: 112/526, loss: 0.0006805207231082022
2023-01-24 09:25:39.213561: step: 116/526, loss: 0.0001503357052570209
2023-01-24 09:25:40.263672: step: 120/526, loss: 0.0036784945987164974
2023-01-24 09:25:41.310651: step: 124/526, loss: 0.0030546069610863924
2023-01-24 09:25:42.372754: step: 128/526, loss: 0.003129085060209036
2023-01-24 09:25:43.423480: step: 132/526, loss: 6.463538738898933e-05
2023-01-24 09:25:44.485831: step: 136/526, loss: 0.00036310305586084723
2023-01-24 09:25:45.526440: step: 140/526, loss: 0.0016909617697820067
2023-01-24 09:25:46.593482: step: 144/526, loss: 0.010252445936203003
2023-01-24 09:25:47.648745: step: 148/526, loss: 0.0054732272401452065
2023-01-24 09:25:48.692935: step: 152/526, loss: 0.0015789339086040854
2023-01-24 09:25:49.772713: step: 156/526, loss: 0.0012789018219336867
2023-01-24 09:25:50.866702: step: 160/526, loss: 7.850086694816127e-05
2023-01-24 09:25:51.917335: step: 164/526, loss: 0.0014245674246922135
2023-01-24 09:25:52.998411: step: 168/526, loss: 0.0036292877048254013
2023-01-24 09:25:54.066085: step: 172/526, loss: 0.0018398505635559559
2023-01-24 09:25:55.125588: step: 176/526, loss: 0.0002395951742073521
2023-01-24 09:25:56.189882: step: 180/526, loss: 0.0033870332408696413
2023-01-24 09:25:57.252272: step: 184/526, loss: 0.010737528093159199
2023-01-24 09:25:58.336465: step: 188/526, loss: 0.0025251656770706177
2023-01-24 09:25:59.415745: step: 192/526, loss: 0.0008991694776341319
2023-01-24 09:26:00.497131: step: 196/526, loss: 0.0049573746509850025
2023-01-24 09:26:01.554798: step: 200/526, loss: 0.01414923369884491
2023-01-24 09:26:02.607116: step: 204/526, loss: 0.002367520472034812
2023-01-24 09:26:03.669046: step: 208/526, loss: 0.004535994958132505
2023-01-24 09:26:04.733052: step: 212/526, loss: 0.00047451950376853347
2023-01-24 09:26:05.776357: step: 216/526, loss: 0.006600670516490936
2023-01-24 09:26:06.828984: step: 220/526, loss: 0.00016484559455420822
2023-01-24 09:26:07.901786: step: 224/526, loss: 0.0022476345766335726
2023-01-24 09:26:08.970078: step: 228/526, loss: 0.0013701578136533499
2023-01-24 09:26:10.024205: step: 232/526, loss: 0.00036878802347928286
2023-01-24 09:26:11.092714: step: 236/526, loss: 0.002993670292198658
2023-01-24 09:26:12.168434: step: 240/526, loss: 0.001210243790410459
2023-01-24 09:26:13.236865: step: 244/526, loss: 0.003514036536216736
2023-01-24 09:26:14.305302: step: 248/526, loss: 0.001499002450145781
2023-01-24 09:26:15.363078: step: 252/526, loss: 0.003715614089742303
2023-01-24 09:26:16.438716: step: 256/526, loss: 0.034819819033145905
2023-01-24 09:26:17.501307: step: 260/526, loss: 0.0037892204709351063
2023-01-24 09:26:18.573973: step: 264/526, loss: 0.0003726025461219251
2023-01-24 09:26:19.637775: step: 268/526, loss: 0.005182519089430571
2023-01-24 09:26:20.715725: step: 272/526, loss: 0.007129094563424587
2023-01-24 09:26:21.772800: step: 276/526, loss: 0.0014610864454880357
2023-01-24 09:26:22.845721: step: 280/526, loss: 0.00016787397908046842
2023-01-24 09:26:23.916841: step: 284/526, loss: 0.0033606623765081167
2023-01-24 09:26:24.981284: step: 288/526, loss: 0.0008211909444071352
2023-01-24 09:26:26.039519: step: 292/526, loss: 0.0011222274042665958
2023-01-24 09:26:27.103574: step: 296/526, loss: 1.1055620916522457e-06
2023-01-24 09:26:28.166150: step: 300/526, loss: 0.00038951190072111785
2023-01-24 09:26:29.251653: step: 304/526, loss: 0.0004283290181774646
2023-01-24 09:26:30.311310: step: 308/526, loss: 0.001642512739636004
2023-01-24 09:26:31.375566: step: 312/526, loss: 0.005180171225219965
2023-01-24 09:26:32.452218: step: 316/526, loss: 0.01095285452902317
2023-01-24 09:26:33.509810: step: 320/526, loss: 0.00023335735022556037
2023-01-24 09:26:34.559992: step: 324/526, loss: 0.00012285835691727698
2023-01-24 09:26:35.623797: step: 328/526, loss: 0.0018274281173944473
2023-01-24 09:26:36.692603: step: 332/526, loss: 0.0010510620195418596
2023-01-24 09:26:37.754080: step: 336/526, loss: 0.0028317952528595924
2023-01-24 09:26:38.804056: step: 340/526, loss: 0.004292685072869062
2023-01-24 09:26:39.861954: step: 344/526, loss: 0.003843134269118309
2023-01-24 09:26:40.918669: step: 348/526, loss: 0.0006477513234131038
2023-01-24 09:26:41.989663: step: 352/526, loss: 0.0001832250418374315
2023-01-24 09:26:43.078531: step: 356/526, loss: 0.00012352815247140825
2023-01-24 09:26:44.149872: step: 360/526, loss: 7.168961246861727e-08
2023-01-24 09:26:45.209738: step: 364/526, loss: 0.0075658452697098255
2023-01-24 09:26:46.282945: step: 368/526, loss: 0.004586181603372097
2023-01-24 09:26:47.351269: step: 372/526, loss: 0.000249495729804039
2023-01-24 09:26:48.410221: step: 376/526, loss: 0.0002550693752709776
2023-01-24 09:26:49.473714: step: 380/526, loss: 0.003682951908558607
2023-01-24 09:26:50.525640: step: 384/526, loss: 0.0015401209238916636
2023-01-24 09:26:51.592818: step: 388/526, loss: 0.011026284657418728
2023-01-24 09:26:52.677246: step: 392/526, loss: 0.001119575696066022
2023-01-24 09:26:53.732331: step: 396/526, loss: 0.00017400254728272557
2023-01-24 09:26:54.792227: step: 400/526, loss: 0.004120440222322941
2023-01-24 09:26:55.851600: step: 404/526, loss: 0.003093558130785823
2023-01-24 09:26:56.910127: step: 408/526, loss: 0.0018006149912253022
2023-01-24 09:26:57.970161: step: 412/526, loss: 0.00022988353157415986
2023-01-24 09:26:59.016035: step: 416/526, loss: 0.00015818413521628827
2023-01-24 09:27:00.104415: step: 420/526, loss: 0.0016527051338925958
2023-01-24 09:27:01.192082: step: 424/526, loss: 0.001137578277848661
2023-01-24 09:27:02.247989: step: 428/526, loss: 7.243343134177849e-05
2023-01-24 09:27:03.303784: step: 432/526, loss: 0.0004274975508451462
2023-01-24 09:27:04.388353: step: 436/526, loss: 0.003246559528633952
2023-01-24 09:27:05.452989: step: 440/526, loss: 0.0019939234480261803
2023-01-24 09:27:06.519151: step: 444/526, loss: 0.0015268611023202538
2023-01-24 09:27:07.581341: step: 448/526, loss: 0.01211488526314497
2023-01-24 09:27:08.647750: step: 452/526, loss: 0.0031942531932145357
2023-01-24 09:27:09.711832: step: 456/526, loss: 0.00773973111063242
2023-01-24 09:27:10.777040: step: 460/526, loss: 6.892277451697737e-05
2023-01-24 09:27:11.839046: step: 464/526, loss: 0.0005133071099407971
2023-01-24 09:27:12.910311: step: 468/526, loss: 0.002507448196411133
2023-01-24 09:27:13.995734: step: 472/526, loss: 0.0012764750281348825
2023-01-24 09:27:15.069940: step: 476/526, loss: 0.0010258274851366878
2023-01-24 09:27:16.128380: step: 480/526, loss: 0.00020125247829128057
2023-01-24 09:27:17.202638: step: 484/526, loss: 0.0011133721563965082
2023-01-24 09:27:18.264369: step: 488/526, loss: 0.0011401246301829815
2023-01-24 09:27:19.315079: step: 492/526, loss: 0.0016982285305857658
2023-01-24 09:27:20.377339: step: 496/526, loss: 0.00862390547990799
2023-01-24 09:27:21.434980: step: 500/526, loss: 0.0004218018730171025
2023-01-24 09:27:22.502419: step: 504/526, loss: 0.007057816721498966
2023-01-24 09:27:23.556677: step: 508/526, loss: 0.007039402611553669
2023-01-24 09:27:24.613769: step: 512/526, loss: 0.005749070085585117
2023-01-24 09:27:25.674163: step: 516/526, loss: 0.0037090883124619722
2023-01-24 09:27:26.744533: step: 520/526, loss: 4.112521310162265e-07
2023-01-24 09:27:27.814234: step: 524/526, loss: 0.0020158865954726934
2023-01-24 09:27:28.870373: step: 528/526, loss: 2.7897622203454375e-05
2023-01-24 09:27:29.939666: step: 532/526, loss: 0.0008194040274247527
2023-01-24 09:27:31.013192: step: 536/526, loss: 0.005127327982336283
2023-01-24 09:27:32.067776: step: 540/526, loss: 4.3473715777508914e-05
2023-01-24 09:27:33.124098: step: 544/526, loss: 0.003732114564627409
2023-01-24 09:27:34.192064: step: 548/526, loss: 0.008060650900006294
2023-01-24 09:27:35.232927: step: 552/526, loss: 0.004624656867235899
2023-01-24 09:27:36.322927: step: 556/526, loss: 0.0032527304720133543
2023-01-24 09:27:37.395079: step: 560/526, loss: 0.00018322185496799648
2023-01-24 09:27:38.458876: step: 564/526, loss: 0.0021202941425144672
2023-01-24 09:27:39.514713: step: 568/526, loss: 0.0020952620543539524
2023-01-24 09:27:40.601301: step: 572/526, loss: 0.0027186234947293997
2023-01-24 09:27:41.663969: step: 576/526, loss: 0.005280424375087023
2023-01-24 09:27:42.728656: step: 580/526, loss: 0.0011867227731272578
2023-01-24 09:27:43.804636: step: 584/526, loss: 5.937131936661899e-05
2023-01-24 09:27:44.875017: step: 588/526, loss: 0.0008186287013813853
2023-01-24 09:27:45.953416: step: 592/526, loss: 0.002644090913236141
2023-01-24 09:27:47.011235: step: 596/526, loss: 2.1075493350508623e-05
2023-01-24 09:27:48.060877: step: 600/526, loss: 5.671819508279441e-06
2023-01-24 09:27:49.121105: step: 604/526, loss: 3.3184303902089596e-05
2023-01-24 09:27:50.192446: step: 608/526, loss: 0.010636086575686932
2023-01-24 09:27:51.262012: step: 612/526, loss: 0.0005038361414335668
2023-01-24 09:27:52.340887: step: 616/526, loss: 0.003825089894235134
2023-01-24 09:27:53.419516: step: 620/526, loss: 0.00010419063619337976
2023-01-24 09:27:54.489645: step: 624/526, loss: 0.005193542223423719
2023-01-24 09:27:55.554958: step: 628/526, loss: 0.005949428305029869
2023-01-24 09:27:56.624075: step: 632/526, loss: 8.242437615990639e-06
2023-01-24 09:27:57.682117: step: 636/526, loss: 0.01410337258130312
2023-01-24 09:27:58.740763: step: 640/526, loss: 0.0002600831212475896
2023-01-24 09:27:59.808930: step: 644/526, loss: 0.0010079031344503164
2023-01-24 09:28:00.869809: step: 648/526, loss: 0.00011994480155408382
2023-01-24 09:28:01.939197: step: 652/526, loss: 0.00839836336672306
2023-01-24 09:28:02.994491: step: 656/526, loss: 8.093093128991313e-06
2023-01-24 09:28:04.066577: step: 660/526, loss: 0.012778832577168941
2023-01-24 09:28:05.131025: step: 664/526, loss: 0.007677122019231319
2023-01-24 09:28:06.180376: step: 668/526, loss: 4.567364157992415e-05
2023-01-24 09:28:07.236129: step: 672/526, loss: 0.00015888040070421994
2023-01-24 09:28:08.297877: step: 676/526, loss: 0.0023467233404517174
2023-01-24 09:28:09.375796: step: 680/526, loss: 0.002413022331893444
2023-01-24 09:28:10.438119: step: 684/526, loss: 0.003936802037060261
2023-01-24 09:28:11.493018: step: 688/526, loss: 0.00031596774351783097
2023-01-24 09:28:12.552003: step: 692/526, loss: 0.0037119807675480843
2023-01-24 09:28:13.623099: step: 696/526, loss: 0.0020477024372667074
2023-01-24 09:28:14.685497: step: 700/526, loss: 0.006950508803129196
2023-01-24 09:28:15.749397: step: 704/526, loss: 0.0001317803980782628
2023-01-24 09:28:16.816145: step: 708/526, loss: 0.006935785990208387
2023-01-24 09:28:17.881363: step: 712/526, loss: 1.296458958677249e-05
2023-01-24 09:28:18.941179: step: 716/526, loss: 0.0006262968527153134
2023-01-24 09:28:20.017507: step: 720/526, loss: 0.0008764247177168727
2023-01-24 09:28:21.090350: step: 724/526, loss: 0.002296761143952608
2023-01-24 09:28:22.174734: step: 728/526, loss: 0.0046785855665802956
2023-01-24 09:28:23.242507: step: 732/526, loss: 0.0030133621767163277
2023-01-24 09:28:24.301611: step: 736/526, loss: 0.0013013080460950732
2023-01-24 09:28:25.391918: step: 740/526, loss: 0.019722046330571175
2023-01-24 09:28:26.466673: step: 744/526, loss: 0.00013010535622015595
2023-01-24 09:28:27.538352: step: 748/526, loss: 0.004622706212103367
2023-01-24 09:28:28.614491: step: 752/526, loss: 0.0040210518054664135
2023-01-24 09:28:29.687662: step: 756/526, loss: 0.0013683774741366506
2023-01-24 09:28:30.752127: step: 760/526, loss: 0.000799557426944375
2023-01-24 09:28:31.806824: step: 764/526, loss: 6.303599366219714e-05
2023-01-24 09:28:32.865317: step: 768/526, loss: 0.0005105281597934663
2023-01-24 09:28:33.937476: step: 772/526, loss: 2.7423491701483727e-05
2023-01-24 09:28:35.006042: step: 776/526, loss: 0.0011220870073884726
2023-01-24 09:28:36.070259: step: 780/526, loss: 0.00508394418284297
2023-01-24 09:28:37.140382: step: 784/526, loss: 0.00108869350515306
2023-01-24 09:28:38.230750: step: 788/526, loss: 0.005428141448646784
2023-01-24 09:28:39.287707: step: 792/526, loss: 0.0010028373217210174
2023-01-24 09:28:40.351995: step: 796/526, loss: 6.29554824627121e-06
2023-01-24 09:28:41.411737: step: 800/526, loss: 0.0014613389503210783
2023-01-24 09:28:42.480037: step: 804/526, loss: 0.0006679213256575167
2023-01-24 09:28:43.565918: step: 808/526, loss: 0.002016930840909481
2023-01-24 09:28:44.629151: step: 812/526, loss: 0.0024851940106600523
2023-01-24 09:28:45.698085: step: 816/526, loss: 0.0006577189778909087
2023-01-24 09:28:46.764595: step: 820/526, loss: 0.0016194492345675826
2023-01-24 09:28:47.823698: step: 824/526, loss: 0.004470439162105322
2023-01-24 09:28:48.896491: step: 828/526, loss: 0.0027023714501410723
2023-01-24 09:28:49.971829: step: 832/526, loss: 4.603931665769778e-05
2023-01-24 09:28:51.042447: step: 836/526, loss: 5.3113872127141804e-05
2023-01-24 09:28:52.140932: step: 840/526, loss: 0.0031346650794148445
2023-01-24 09:28:53.198547: step: 844/526, loss: 3.0452334613073617e-05
2023-01-24 09:28:54.264083: step: 848/526, loss: 0.0023021860979497433
2023-01-24 09:28:55.335584: step: 852/526, loss: 0.00036915394593961537
2023-01-24 09:28:56.396683: step: 856/526, loss: 0.0008140862337313592
2023-01-24 09:28:57.442923: step: 860/526, loss: 0.0006362684653140604
2023-01-24 09:28:58.503594: step: 864/526, loss: 9.940393647411838e-05
2023-01-24 09:28:59.593410: step: 868/526, loss: 0.008510332554578781
2023-01-24 09:29:00.654605: step: 872/526, loss: 0.0002390950539847836
2023-01-24 09:29:01.708932: step: 876/526, loss: 0.0013669779291376472
2023-01-24 09:29:02.770086: step: 880/526, loss: 0.003962170332670212
2023-01-24 09:29:03.837062: step: 884/526, loss: 0.004155547358095646
2023-01-24 09:29:04.893560: step: 888/526, loss: 0.0016149826114997268
2023-01-24 09:29:05.949467: step: 892/526, loss: 0.017426956444978714
2023-01-24 09:29:07.006278: step: 896/526, loss: 7.972426828928292e-05
2023-01-24 09:29:08.076753: step: 900/526, loss: 0.019362036138772964
2023-01-24 09:29:09.156244: step: 904/526, loss: 0.0078095560893416405
2023-01-24 09:29:10.231215: step: 908/526, loss: 0.0005308479885570705
2023-01-24 09:29:11.311056: step: 912/526, loss: 2.2195943529368378e-05
2023-01-24 09:29:12.371830: step: 916/526, loss: 4.1376155422767624e-05
2023-01-24 09:29:13.460118: step: 920/526, loss: 0.0024681328795850277
2023-01-24 09:29:14.519770: step: 924/526, loss: 0.01001826487481594
2023-01-24 09:29:15.603028: step: 928/526, loss: 0.01671735569834709
2023-01-24 09:29:16.671150: step: 932/526, loss: 0.006348755676299334
2023-01-24 09:29:17.738981: step: 936/526, loss: 0.0004991499008610845
2023-01-24 09:29:18.799118: step: 940/526, loss: 6.73061003908515e-06
2023-01-24 09:29:19.861224: step: 944/526, loss: 0.0015974065754562616
2023-01-24 09:29:20.917842: step: 948/526, loss: 0.0007682112045586109
2023-01-24 09:29:21.962144: step: 952/526, loss: 3.084801937802695e-05
2023-01-24 09:29:23.029423: step: 956/526, loss: 0.002170176012441516
2023-01-24 09:29:24.103790: step: 960/526, loss: 3.2930158340604976e-05
2023-01-24 09:29:25.169835: step: 964/526, loss: 0.0003970520047005266
2023-01-24 09:29:26.240955: step: 968/526, loss: 0.0002952840004581958
2023-01-24 09:29:27.314034: step: 972/526, loss: 7.388223821180873e-06
2023-01-24 09:29:28.374047: step: 976/526, loss: 7.909903797553852e-05
2023-01-24 09:29:29.426985: step: 980/526, loss: 5.600322037935257e-05
2023-01-24 09:29:30.495618: step: 984/526, loss: 0.0005911869811825454
2023-01-24 09:29:31.584746: step: 988/526, loss: 0.0035353952553123236
2023-01-24 09:29:32.656518: step: 992/526, loss: 0.00419087428599596
2023-01-24 09:29:33.727784: step: 996/526, loss: 9.73637816059636e-06
2023-01-24 09:29:34.790984: step: 1000/526, loss: 0.0007429146207869053
2023-01-24 09:29:35.861044: step: 1004/526, loss: 0.0023746758233755827
2023-01-24 09:29:36.927773: step: 1008/526, loss: 0.0007079019560478628
2023-01-24 09:29:38.015521: step: 1012/526, loss: 0.015971630811691284
2023-01-24 09:29:39.080844: step: 1016/526, loss: 0.0018676278414204717
2023-01-24 09:29:40.142559: step: 1020/526, loss: 0.0007657906389795244
2023-01-24 09:29:41.204395: step: 1024/526, loss: 0.006397362798452377
2023-01-24 09:29:42.268984: step: 1028/526, loss: 9.910325752571225e-05
2023-01-24 09:29:43.331462: step: 1032/526, loss: 0.005097044166177511
2023-01-24 09:29:44.400712: step: 1036/526, loss: 0.0003145902301184833
2023-01-24 09:29:45.456052: step: 1040/526, loss: 0.0015700054354965687
2023-01-24 09:29:46.518856: step: 1044/526, loss: 0.0014154105447232723
2023-01-24 09:29:47.563072: step: 1048/526, loss: 9.224838140653446e-05
2023-01-24 09:29:48.614189: step: 1052/526, loss: 0.0006847636541351676
2023-01-24 09:29:49.684961: step: 1056/526, loss: 0.0030639139004051685
2023-01-24 09:29:50.764683: step: 1060/526, loss: 0.00014613453822676092
2023-01-24 09:29:51.823668: step: 1064/526, loss: 0.004744696896523237
2023-01-24 09:29:52.898048: step: 1068/526, loss: 3.0585622880607843e-05
2023-01-24 09:29:53.943310: step: 1072/526, loss: 0.00046359343104995787
2023-01-24 09:29:55.022082: step: 1076/526, loss: 0.0016133025055751204
2023-01-24 09:29:56.078666: step: 1080/526, loss: 6.0761421991628595e-06
2023-01-24 09:29:57.170956: step: 1084/526, loss: 0.0034017544239759445
2023-01-24 09:29:58.245453: step: 1088/526, loss: 5.141642031958327e-05
2023-01-24 09:29:59.297127: step: 1092/526, loss: 0.0027938869316130877
2023-01-24 09:30:00.376519: step: 1096/526, loss: 4.976510808774037e-06
2023-01-24 09:30:01.462478: step: 1100/526, loss: 0.02569619193673134
2023-01-24 09:30:02.511301: step: 1104/526, loss: 0.0012464254396036267
2023-01-24 09:30:03.589238: step: 1108/526, loss: 0.0017776619642972946
2023-01-24 09:30:04.652719: step: 1112/526, loss: 0.0008599167922511697
2023-01-24 09:30:05.713442: step: 1116/526, loss: 0.0005587437190115452
2023-01-24 09:30:06.768899: step: 1120/526, loss: 0.002503796713426709
2023-01-24 09:30:07.836475: step: 1124/526, loss: 0.008139527402818203
2023-01-24 09:30:08.889392: step: 1128/526, loss: 8.482647535856813e-05
2023-01-24 09:30:09.965590: step: 1132/526, loss: 0.001659313915297389
2023-01-24 09:30:11.035012: step: 1136/526, loss: 1.154838447092743e-08
2023-01-24 09:30:12.098052: step: 1140/526, loss: 0.0034066070802509785
2023-01-24 09:30:13.158058: step: 1144/526, loss: 0.00011975752568105236
2023-01-24 09:30:14.218094: step: 1148/526, loss: 0.028846673667430878
2023-01-24 09:30:15.284035: step: 1152/526, loss: 0.0016402938636019826
2023-01-24 09:30:16.344868: step: 1156/526, loss: 0.0002949299232568592
2023-01-24 09:30:17.402837: step: 1160/526, loss: 1.1845213521155529e-05
2023-01-24 09:30:18.466654: step: 1164/526, loss: 0.00739887123927474
2023-01-24 09:30:19.537697: step: 1168/526, loss: 0.0024101652670651674
2023-01-24 09:30:20.595835: step: 1172/526, loss: 0.003392466576769948
2023-01-24 09:30:21.694211: step: 1176/526, loss: 0.0017701422329992056
2023-01-24 09:30:22.754521: step: 1180/526, loss: 0.0008206646889448166
2023-01-24 09:30:23.812630: step: 1184/526, loss: 0.00033309072023257613
2023-01-24 09:30:24.886780: step: 1188/526, loss: 0.0029173051007092
2023-01-24 09:30:25.951590: step: 1192/526, loss: 0.00566058186814189
2023-01-24 09:30:27.021779: step: 1196/526, loss: 0.0035131387412548065
2023-01-24 09:30:28.110153: step: 1200/526, loss: 0.00038095717900432646
2023-01-24 09:30:29.178289: step: 1204/526, loss: 0.0006500615272670984
2023-01-24 09:30:30.236464: step: 1208/526, loss: 0.00023163575679063797
2023-01-24 09:30:31.322976: step: 1212/526, loss: 0.005997935775667429
2023-01-24 09:30:32.390599: step: 1216/526, loss: 0.00024209878756664693
2023-01-24 09:30:33.452223: step: 1220/526, loss: 0.004172225948423147
2023-01-24 09:30:34.512654: step: 1224/526, loss: 0.0001175685683847405
2023-01-24 09:30:35.557530: step: 1228/526, loss: 0.0002994227106682956
2023-01-24 09:30:36.619751: step: 1232/526, loss: 0.0001685644529061392
2023-01-24 09:30:37.681536: step: 1236/526, loss: 0.0025238997768610716
2023-01-24 09:30:38.760801: step: 1240/526, loss: 0.006070937030017376
2023-01-24 09:30:39.821010: step: 1244/526, loss: 0.0007993319886736572
2023-01-24 09:30:40.910313: step: 1248/526, loss: 0.0009237503982149065
2023-01-24 09:30:41.966995: step: 1252/526, loss: 0.011913645081222057
2023-01-24 09:30:43.057525: step: 1256/526, loss: 0.0013019415782764554
2023-01-24 09:30:44.127085: step: 1260/526, loss: 1.474797954870155e-06
2023-01-24 09:30:45.199565: step: 1264/526, loss: 0.026881493628025055
2023-01-24 09:30:46.259537: step: 1268/526, loss: 0.00030063901795074344
2023-01-24 09:30:47.314655: step: 1272/526, loss: 0.005757459439337254
2023-01-24 09:30:48.385554: step: 1276/526, loss: 0.0024113182444125414
2023-01-24 09:30:49.444113: step: 1280/526, loss: 0.002858600579202175
2023-01-24 09:30:50.507967: step: 1284/526, loss: 0.0003360543632879853
2023-01-24 09:30:51.566125: step: 1288/526, loss: 0.00010401618055766448
2023-01-24 09:30:52.648507: step: 1292/526, loss: 0.002575970022007823
2023-01-24 09:30:53.711924: step: 1296/526, loss: 0.00018918524438049644
2023-01-24 09:30:54.755172: step: 1300/526, loss: 5.509396578418091e-05
2023-01-24 09:30:55.830531: step: 1304/526, loss: 0.00040850392542779446
2023-01-24 09:30:56.902849: step: 1308/526, loss: 0.0033422140404582024
2023-01-24 09:30:57.973616: step: 1312/526, loss: 0.00016894582950044423
2023-01-24 09:30:59.037373: step: 1316/526, loss: 0.004275804851204157
2023-01-24 09:31:00.105262: step: 1320/526, loss: 0.0005342953372746706
2023-01-24 09:31:01.166545: step: 1324/526, loss: 0.00015412109496537596
2023-01-24 09:31:02.248071: step: 1328/526, loss: 0.003829848486930132
2023-01-24 09:31:03.313858: step: 1332/526, loss: 0.00039161162567324936
2023-01-24 09:31:04.374155: step: 1336/526, loss: 0.00024154286074917763
2023-01-24 09:31:05.439930: step: 1340/526, loss: 0.0016671280609443784
2023-01-24 09:31:06.495202: step: 1344/526, loss: 0.00041484637768007815
2023-01-24 09:31:07.559559: step: 1348/526, loss: 0.001319577102549374
2023-01-24 09:31:08.633655: step: 1352/526, loss: 0.0048068612813949585
2023-01-24 09:31:09.685171: step: 1356/526, loss: 0.005619472824037075
2023-01-24 09:31:10.737095: step: 1360/526, loss: 1.8526162648413447e-06
2023-01-24 09:31:11.801799: step: 1364/526, loss: 0.01796802692115307
2023-01-24 09:31:12.896388: step: 1368/526, loss: 0.0016684645088389516
2023-01-24 09:31:13.955527: step: 1372/526, loss: 0.006749644875526428
2023-01-24 09:31:15.014458: step: 1376/526, loss: 0.00036148566869087517
2023-01-24 09:31:16.083129: step: 1380/526, loss: 0.0059757172130048275
2023-01-24 09:31:17.146429: step: 1384/526, loss: 0.002105912659317255
2023-01-24 09:31:18.215691: step: 1388/526, loss: 0.00016594017506577075
2023-01-24 09:31:19.276589: step: 1392/526, loss: 0.0063743372447788715
2023-01-24 09:31:20.346655: step: 1396/526, loss: 0.006596965715289116
2023-01-24 09:31:21.410390: step: 1400/526, loss: 0.0002547740878071636
2023-01-24 09:31:22.480271: step: 1404/526, loss: 0.009166822768747807
2023-01-24 09:31:23.553490: step: 1408/526, loss: 0.005374606233090162
2023-01-24 09:31:24.608779: step: 1412/526, loss: 0.0013521861983463168
2023-01-24 09:31:25.691111: step: 1416/526, loss: 0.006498397793620825
2023-01-24 09:31:26.755462: step: 1420/526, loss: 0.0008393136085942388
2023-01-24 09:31:27.821091: step: 1424/526, loss: 0.00023064140987116843
2023-01-24 09:31:28.866873: step: 1428/526, loss: 3.39574853569502e-06
2023-01-24 09:31:29.934335: step: 1432/526, loss: 0.00016327248886227608
2023-01-24 09:31:31.001542: step: 1436/526, loss: 0.0004489348502829671
2023-01-24 09:31:32.054427: step: 1440/526, loss: 1.8964508853969164e-05
2023-01-24 09:31:33.146164: step: 1444/526, loss: 0.0023021011147648096
2023-01-24 09:31:34.219892: step: 1448/526, loss: 0.007020849268883467
2023-01-24 09:31:35.273861: step: 1452/526, loss: 6.2382678152062e-05
2023-01-24 09:31:36.353324: step: 1456/526, loss: 0.001106567564420402
2023-01-24 09:31:37.421762: step: 1460/526, loss: 0.002262725029140711
2023-01-24 09:31:38.500762: step: 1464/526, loss: 0.01350381225347519
2023-01-24 09:31:39.542327: step: 1468/526, loss: 0.00018576462753117085
2023-01-24 09:31:40.608873: step: 1472/526, loss: 0.0015261798398569226
2023-01-24 09:31:41.673228: step: 1476/526, loss: 4.380718746688217e-05
2023-01-24 09:31:42.727898: step: 1480/526, loss: 8.293452992802486e-05
2023-01-24 09:31:43.812235: step: 1484/526, loss: 6.634479359490797e-05
2023-01-24 09:31:44.872434: step: 1488/526, loss: 0.0038234770763665438
2023-01-24 09:31:45.942417: step: 1492/526, loss: 0.0013298607664182782
2023-01-24 09:31:46.998618: step: 1496/526, loss: 4.532401726464741e-05
2023-01-24 09:31:48.056342: step: 1500/526, loss: 4.7750781959621236e-05
2023-01-24 09:31:49.110854: step: 1504/526, loss: 0.00211342447437346
2023-01-24 09:31:50.173201: step: 1508/526, loss: 0.008225289173424244
2023-01-24 09:31:51.245217: step: 1512/526, loss: 0.002450736705213785
2023-01-24 09:31:52.304009: step: 1516/526, loss: 0.0007001644698902965
2023-01-24 09:31:53.358844: step: 1520/526, loss: 0.007758734747767448
2023-01-24 09:31:54.425640: step: 1524/526, loss: 0.016332169994711876
2023-01-24 09:31:55.493656: step: 1528/526, loss: 0.000947068736422807
2023-01-24 09:31:56.557430: step: 1532/526, loss: 0.002255253028124571
2023-01-24 09:31:57.625987: step: 1536/526, loss: 0.002192385494709015
2023-01-24 09:31:58.689796: step: 1540/526, loss: 0.010639390908181667
2023-01-24 09:31:59.763663: step: 1544/526, loss: 0.005155371502041817
2023-01-24 09:32:00.823342: step: 1548/526, loss: 0.008084229193627834
2023-01-24 09:32:01.894385: step: 1552/526, loss: 0.0002110498317051679
2023-01-24 09:32:02.963307: step: 1556/526, loss: 0.01814371533691883
2023-01-24 09:32:04.016824: step: 1560/526, loss: 2.07447854450038e-07
2023-01-24 09:32:05.089225: step: 1564/526, loss: 0.0015109218657016754
2023-01-24 09:32:06.157534: step: 1568/526, loss: 0.0008219032315537333
2023-01-24 09:32:07.214010: step: 1572/526, loss: 0.0027636263985186815
2023-01-24 09:32:08.284268: step: 1576/526, loss: 0.003368040546774864
2023-01-24 09:32:09.366952: step: 1580/526, loss: 0.001999292988330126
2023-01-24 09:32:10.428438: step: 1584/526, loss: 0.0016826161881908774
2023-01-24 09:32:11.500460: step: 1588/526, loss: 0.00857156328856945
2023-01-24 09:32:12.579709: step: 1592/526, loss: 2.837777356035076e-05
2023-01-24 09:32:13.642480: step: 1596/526, loss: 0.0005658446461893618
2023-01-24 09:32:14.708007: step: 1600/526, loss: 0.0022893897257745266
2023-01-24 09:32:15.813258: step: 1604/526, loss: 0.003975036554038525
2023-01-24 09:32:16.878067: step: 1608/526, loss: 0.0005028306040912867
2023-01-24 09:32:17.949883: step: 1612/526, loss: 0.0007159552769735456
2023-01-24 09:32:19.000303: step: 1616/526, loss: 0.006780128926038742
2023-01-24 09:32:20.075554: step: 1620/526, loss: 0.003525175154209137
2023-01-24 09:32:21.132601: step: 1624/526, loss: 0.00011376501061022282
2023-01-24 09:32:22.220666: step: 1628/526, loss: 0.003667653538286686
2023-01-24 09:32:23.284691: step: 1632/526, loss: 0.003684388706460595
2023-01-24 09:32:24.339097: step: 1636/526, loss: 0.0022180743981152773
2023-01-24 09:32:25.406861: step: 1640/526, loss: 0.001281987875699997
2023-01-24 09:32:26.456273: step: 1644/526, loss: 0.00011861836537718773
2023-01-24 09:32:27.514149: step: 1648/526, loss: 0.0014403087552636862
2023-01-24 09:32:28.578239: step: 1652/526, loss: 5.618975046672858e-05
2023-01-24 09:32:29.654230: step: 1656/526, loss: 0.004613439552485943
2023-01-24 09:32:30.733942: step: 1660/526, loss: 0.0007005402585491538
2023-01-24 09:32:31.787798: step: 1664/526, loss: 0.0003630566643550992
2023-01-24 09:32:32.855627: step: 1668/526, loss: 0.007170497439801693
2023-01-24 09:32:33.923833: step: 1672/526, loss: 0.004329638555645943
2023-01-24 09:32:34.995292: step: 1676/526, loss: 0.0053426772356033325
2023-01-24 09:32:36.057755: step: 1680/526, loss: 0.00219931872561574
2023-01-24 09:32:37.112898: step: 1684/526, loss: 0.002501806477084756
2023-01-24 09:32:38.199696: step: 1688/526, loss: 0.0022931781131774187
2023-01-24 09:32:39.269509: step: 1692/526, loss: 0.006508628372102976
2023-01-24 09:32:40.329704: step: 1696/526, loss: 0.001422066823579371
2023-01-24 09:32:41.389447: step: 1700/526, loss: 1.9098439224762842e-05
2023-01-24 09:32:42.442815: step: 1704/526, loss: 0.0021764866542071104
2023-01-24 09:32:43.500189: step: 1708/526, loss: 2.0567573301377706e-05
2023-01-24 09:32:44.564231: step: 1712/526, loss: 0.0009687712299637496
2023-01-24 09:32:45.627383: step: 1716/526, loss: 0.03214814513921738
2023-01-24 09:32:46.687325: step: 1720/526, loss: 0.00015621911734342575
2023-01-24 09:32:47.754744: step: 1724/526, loss: 0.0026943183038383722
2023-01-24 09:32:48.827494: step: 1728/526, loss: 0.004763968288898468
2023-01-24 09:32:49.910785: step: 1732/526, loss: 0.005509181879460812
2023-01-24 09:32:50.967281: step: 1736/526, loss: 0.006067181006073952
2023-01-24 09:32:52.029688: step: 1740/526, loss: 7.264299028975074e-08
2023-01-24 09:32:53.095429: step: 1744/526, loss: 0.0003242361999582499
2023-01-24 09:32:54.155762: step: 1748/526, loss: 0.0012354010250419378
2023-01-24 09:32:55.207862: step: 1752/526, loss: 0.007575752679258585
2023-01-24 09:32:56.285427: step: 1756/526, loss: 0.020506858825683594
2023-01-24 09:32:57.334837: step: 1760/526, loss: 0.00012024528405163437
2023-01-24 09:32:58.410460: step: 1764/526, loss: 0.0060985335148870945
2023-01-24 09:32:59.459374: step: 1768/526, loss: 0.00016203972336370498
2023-01-24 09:33:00.517399: step: 1772/526, loss: 0.0017784223891794682
2023-01-24 09:33:01.583039: step: 1776/526, loss: 6.240505172172561e-05
2023-01-24 09:33:02.638913: step: 1780/526, loss: 0.007599841337651014
2023-01-24 09:33:03.692577: step: 1784/526, loss: 0.0002489571343176067
2023-01-24 09:33:04.761594: step: 1788/526, loss: 0.0031920955516397953
2023-01-24 09:33:05.826771: step: 1792/526, loss: 0.000125853403005749
2023-01-24 09:33:06.879287: step: 1796/526, loss: 0.003233651164919138
2023-01-24 09:33:07.939530: step: 1800/526, loss: 0.004029898438602686
2023-01-24 09:33:09.005361: step: 1804/526, loss: 0.003109175246208906
2023-01-24 09:33:10.071188: step: 1808/526, loss: 0.0013230028562247753
2023-01-24 09:33:11.133157: step: 1812/526, loss: 0.011759774759411812
2023-01-24 09:33:12.207894: step: 1816/526, loss: 0.001905420096591115
2023-01-24 09:33:13.266198: step: 1820/526, loss: 0.000376980664441362
2023-01-24 09:33:14.322914: step: 1824/526, loss: 0.003011233638972044
2023-01-24 09:33:15.380580: step: 1828/526, loss: 0.0036070875357836485
2023-01-24 09:33:16.428162: step: 1832/526, loss: 1.220539274982002e-06
2023-01-24 09:33:17.501287: step: 1836/526, loss: 0.005619187839329243
2023-01-24 09:33:18.547783: step: 1840/526, loss: 0.00010750297224149108
2023-01-24 09:33:19.609076: step: 1844/526, loss: 9.586124360794201e-05
2023-01-24 09:33:20.677746: step: 1848/526, loss: 0.0029806678649038076
2023-01-24 09:33:21.722479: step: 1852/526, loss: 0.00026063984842039645
2023-01-24 09:33:22.791338: step: 1856/526, loss: 0.00395971117541194
2023-01-24 09:33:23.857683: step: 1860/526, loss: 0.0036354425828903913
2023-01-24 09:33:24.906893: step: 1864/526, loss: 0.00698345759883523
2023-01-24 09:33:25.976461: step: 1868/526, loss: 0.002495624590665102
2023-01-24 09:33:27.041335: step: 1872/526, loss: 0.0001881919160950929
2023-01-24 09:33:28.090425: step: 1876/526, loss: 0.0022773980163037777
2023-01-24 09:33:29.149938: step: 1880/526, loss: 0.01914193667471409
2023-01-24 09:33:30.219034: step: 1884/526, loss: 0.00043189391726627946
2023-01-24 09:33:31.273789: step: 1888/526, loss: 0.002126776846125722
2023-01-24 09:33:32.341535: step: 1892/526, loss: 0.007313101086765528
2023-01-24 09:33:33.401563: step: 1896/526, loss: 0.0006145249353721738
2023-01-24 09:33:34.460361: step: 1900/526, loss: 4.086378339707153e-06
2023-01-24 09:33:35.534684: step: 1904/526, loss: 0.002802101895213127
2023-01-24 09:33:36.615716: step: 1908/526, loss: 0.0017569992924109101
2023-01-24 09:33:37.669069: step: 1912/526, loss: 3.8908549271354786e-08
2023-01-24 09:33:38.749108: step: 1916/526, loss: 0.0006196315516717732
2023-01-24 09:33:39.808394: step: 1920/526, loss: 0.00011819563223980367
2023-01-24 09:33:40.894618: step: 1924/526, loss: 0.0014133146032691002
2023-01-24 09:33:41.974363: step: 1928/526, loss: 0.002454676665365696
2023-01-24 09:33:43.074701: step: 1932/526, loss: 0.0020834344904869795
2023-01-24 09:33:44.151941: step: 1936/526, loss: 0.004841333720833063
2023-01-24 09:33:45.209539: step: 1940/526, loss: 0.002398829907178879
2023-01-24 09:33:46.261286: step: 1944/526, loss: 0.022020474076271057
2023-01-24 09:33:47.323146: step: 1948/526, loss: 0.0002267273812321946
2023-01-24 09:33:48.378258: step: 1952/526, loss: 0.005362228490412235
2023-01-24 09:33:49.460071: step: 1956/526, loss: 0.004876091610640287
2023-01-24 09:33:50.523584: step: 1960/526, loss: 0.000742474861908704
2023-01-24 09:33:51.595272: step: 1964/526, loss: 0.0007090331055223942
2023-01-24 09:33:52.663435: step: 1968/526, loss: 0.005307865794748068
2023-01-24 09:33:53.745288: step: 1972/526, loss: 0.00046011366066522896
2023-01-24 09:33:54.814295: step: 1976/526, loss: 2.7777618015534244e-05
2023-01-24 09:33:55.901401: step: 1980/526, loss: 0.0022148333955556154
2023-01-24 09:33:56.959114: step: 1984/526, loss: 0.00011739695037249476
2023-01-24 09:33:58.034624: step: 1988/526, loss: 0.0007252011564560235
2023-01-24 09:33:59.120557: step: 1992/526, loss: 0.005862390622496605
2023-01-24 09:34:00.184082: step: 1996/526, loss: 0.0009581076446920633
2023-01-24 09:34:01.273509: step: 2000/526, loss: 0.0003459296131040901
2023-01-24 09:34:02.335303: step: 2004/526, loss: 0.0059761786833405495
2023-01-24 09:34:03.406214: step: 2008/526, loss: 1.6038326066336595e-05
2023-01-24 09:34:04.462392: step: 2012/526, loss: 0.0003017112903762609
2023-01-24 09:34:05.533150: step: 2016/526, loss: 0.004875024780631065
2023-01-24 09:34:06.589317: step: 2020/526, loss: 0.0007622579578310251
2023-01-24 09:34:07.644206: step: 2024/526, loss: 0.0005461559630930424
2023-01-24 09:34:08.718327: step: 2028/526, loss: 0.004356930032372475
2023-01-24 09:34:09.795545: step: 2032/526, loss: 0.01109517365694046
2023-01-24 09:34:10.858851: step: 2036/526, loss: 0.0016498526092618704
2023-01-24 09:34:11.925676: step: 2040/526, loss: 0.002063177293166518
2023-01-24 09:34:12.981611: step: 2044/526, loss: 0.004093632567673922
2023-01-24 09:34:14.031960: step: 2048/526, loss: 0.0005458946106955409
2023-01-24 09:34:15.119875: step: 2052/526, loss: 0.0023855725303292274
2023-01-24 09:34:16.196094: step: 2056/526, loss: 0.002443872159346938
2023-01-24 09:34:17.253460: step: 2060/526, loss: 0.0003304611600469798
2023-01-24 09:34:18.313487: step: 2064/526, loss: 0.00010898959590122104
2023-01-24 09:34:19.382931: step: 2068/526, loss: 1.2314034393057227e-05
2023-01-24 09:34:20.464596: step: 2072/526, loss: 0.00027076713740825653
2023-01-24 09:34:21.542196: step: 2076/526, loss: 0.017586981877684593
2023-01-24 09:34:22.632172: step: 2080/526, loss: 3.6498055123956874e-05
2023-01-24 09:34:23.710960: step: 2084/526, loss: 0.0009478374267928302
2023-01-24 09:34:24.796643: step: 2088/526, loss: 0.003462414722889662
2023-01-24 09:34:25.883492: step: 2092/526, loss: 0.0009158753091469407
2023-01-24 09:34:26.956378: step: 2096/526, loss: 0.0028194477781653404
2023-01-24 09:34:28.029125: step: 2100/526, loss: 0.000534126244019717
2023-01-24 09:34:29.100538: step: 2104/526, loss: 3.6577486753230914e-05
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36478472968134623, 'r': 0.2761842640281919, 'f1': 0.31436092255476705}, 'combined': 0.23163436398772308, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3585586174440493, 'r': 0.22405812965625407, 'f1': 0.27578326093951094}, 'combined': 0.15042723323973323, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33823175465838506, 'r': 0.29523075359175927, 'f1': 0.315271746996671}, 'combined': 0.23230549778702073, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3614034934440746, 'r': 0.26055439417559995, 'f1': 0.30280271433698114}, 'combined': 0.1651651169110806, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3595132779406973, 'r': 0.31721759818296824, 'f1': 0.33704369806940376}, 'combined': 0.2483479880511396, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36213360987381765, 'r': 0.2756588869304815, 'f1': 0.3130339360156013}, 'combined': 0.17074578328123707, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3401022086466165, 'r': 0.2942819869883437, 'f1': 0.31553734922249665}, 'combined': 0.23250120469026067, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3602287518928459, 'r': 0.2590483064846998, 'f1': 0.3013728568257337}, 'combined': 0.16438519463221837, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4868421052631579, 'r': 0.40217391304347827, 'f1': 0.44047619047619047}, 'combined': 0.22023809523809523, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 09:37:11.162174: step: 4/526, loss: 0.0012552232947200537
2023-01-24 09:37:12.214433: step: 8/526, loss: 0.0015432165237143636
2023-01-24 09:37:13.299428: step: 12/526, loss: 0.00029508236912079155
2023-01-24 09:37:14.378412: step: 16/526, loss: 0.0018553943373262882
2023-01-24 09:37:15.451969: step: 20/526, loss: 0.002844705479219556
2023-01-24 09:37:16.508354: step: 24/526, loss: 0.005759004037827253
2023-01-24 09:37:17.580663: step: 28/526, loss: 0.007542275823652744
2023-01-24 09:37:18.628673: step: 32/526, loss: 5.0567694415804e-05
2023-01-24 09:37:19.676056: step: 36/526, loss: 0.0005824349937029183
2023-01-24 09:37:20.740054: step: 40/526, loss: 5.674270505551249e-05
2023-01-24 09:37:21.808887: step: 44/526, loss: 0.005207403562963009
2023-01-24 09:37:22.876414: step: 48/526, loss: 0.004842313472181559
2023-01-24 09:37:23.952685: step: 52/526, loss: 0.016914453357458115
2023-01-24 09:37:25.008722: step: 56/526, loss: 0.0007114142063073814
2023-01-24 09:37:26.073178: step: 60/526, loss: 0.0053308820351958275
2023-01-24 09:37:27.134884: step: 64/526, loss: 0.0013062546495348215
2023-01-24 09:37:28.202359: step: 68/526, loss: 0.00212805881164968
2023-01-24 09:37:29.276277: step: 72/526, loss: 0.003834059927612543
2023-01-24 09:37:30.340324: step: 76/526, loss: 1.2718445759674069e-05
2023-01-24 09:37:31.389566: step: 80/526, loss: 4.7502679080935195e-05
2023-01-24 09:37:32.454521: step: 84/526, loss: 0.00018531570094637573
2023-01-24 09:37:33.509541: step: 88/526, loss: 0.0014669826487079263
2023-01-24 09:37:34.559961: step: 92/526, loss: 0.0002054189535556361
2023-01-24 09:37:35.619938: step: 96/526, loss: 0.0005185614572837949
2023-01-24 09:37:36.685134: step: 100/526, loss: 0.0020779587794095278
2023-01-24 09:37:37.749666: step: 104/526, loss: 0.00024974357802420855
2023-01-24 09:37:38.830778: step: 108/526, loss: 0.00022171359159983695
2023-01-24 09:37:39.888542: step: 112/526, loss: 1.4006927528953383e-07
2023-01-24 09:37:40.949996: step: 116/526, loss: 0.0016064938390627503
2023-01-24 09:37:42.026515: step: 120/526, loss: 0.000878556165844202
2023-01-24 09:37:43.094265: step: 124/526, loss: 0.0001981613168027252
2023-01-24 09:37:44.167203: step: 128/526, loss: 0.0005566237377934158
2023-01-24 09:37:45.223413: step: 132/526, loss: 0.0008138316916301847
2023-01-24 09:37:46.282856: step: 136/526, loss: 1.825946856115479e-05
2023-01-24 09:37:47.365955: step: 140/526, loss: 0.001798274926841259
2023-01-24 09:37:48.421134: step: 144/526, loss: 0.00013317097909748554
2023-01-24 09:37:49.488255: step: 148/526, loss: 0.0001498697092756629
2023-01-24 09:37:50.557154: step: 152/526, loss: 0.006235620938241482
2023-01-24 09:37:51.615407: step: 156/526, loss: 4.8580281145405024e-05
2023-01-24 09:37:52.671001: step: 160/526, loss: 3.3379259548382834e-05
2023-01-24 09:37:53.748817: step: 164/526, loss: 0.00551857752725482
2023-01-24 09:37:54.802790: step: 168/526, loss: 0.015086750499904156
2023-01-24 09:37:55.863804: step: 172/526, loss: 0.01825663261115551
2023-01-24 09:37:56.931293: step: 176/526, loss: 0.0008697194280102849
2023-01-24 09:37:57.982824: step: 180/526, loss: 0.00011589085625018924
2023-01-24 09:37:59.047593: step: 184/526, loss: 0.0015482259914278984
2023-01-24 09:38:00.104358: step: 188/526, loss: 0.00011017138604074717
2023-01-24 09:38:01.179807: step: 192/526, loss: 5.817196870339103e-05
2023-01-24 09:38:02.244995: step: 196/526, loss: 0.0013396100839599967
2023-01-24 09:38:03.321014: step: 200/526, loss: 5.4391639423556626e-05
2023-01-24 09:38:04.386511: step: 204/526, loss: 0.009423713199794292
2023-01-24 09:38:05.458804: step: 208/526, loss: 0.002839298453181982
2023-01-24 09:38:06.502910: step: 212/526, loss: 0.02412470243871212
2023-01-24 09:38:07.566506: step: 216/526, loss: 0.003705165581777692
2023-01-24 09:38:08.623085: step: 220/526, loss: 5.2387463256309275e-06
2023-01-24 09:38:09.678704: step: 224/526, loss: 5.684604911948554e-05
2023-01-24 09:38:10.749456: step: 228/526, loss: 0.00020536499505396932
2023-01-24 09:38:11.811374: step: 232/526, loss: 0.0006745310383848846
2023-01-24 09:38:12.903038: step: 236/526, loss: 0.000883669825270772
2023-01-24 09:38:13.965735: step: 240/526, loss: 0.0013289484195411205
2023-01-24 09:38:15.018041: step: 244/526, loss: 7.763106987113133e-05
2023-01-24 09:38:16.075775: step: 248/526, loss: 0.006935635581612587
2023-01-24 09:38:17.150042: step: 252/526, loss: 0.01863492652773857
2023-01-24 09:38:18.221437: step: 256/526, loss: 0.00023739633616060019
2023-01-24 09:38:19.297244: step: 260/526, loss: 0.002382552018389106
2023-01-24 09:38:20.353607: step: 264/526, loss: 0.0004798165464308113
2023-01-24 09:38:21.429941: step: 268/526, loss: 0.008879052475094795
2023-01-24 09:38:22.474619: step: 272/526, loss: 7.940034265629947e-06
2023-01-24 09:38:23.540110: step: 276/526, loss: 0.00391066400334239
2023-01-24 09:38:24.597523: step: 280/526, loss: 1.1152409570058808e-05
2023-01-24 09:38:25.676003: step: 284/526, loss: 0.009206926450133324
2023-01-24 09:38:26.737544: step: 288/526, loss: 0.004390468820929527
2023-01-24 09:38:27.804005: step: 292/526, loss: 0.0010674571385607123
2023-01-24 09:38:28.873915: step: 296/526, loss: 0.009136535227298737
2023-01-24 09:38:29.932814: step: 300/526, loss: 0.00143871596083045
2023-01-24 09:38:30.982039: step: 304/526, loss: 0.006449790671467781
2023-01-24 09:38:32.043882: step: 308/526, loss: 0.002073228359222412
2023-01-24 09:38:33.120738: step: 312/526, loss: 0.0001982772082556039
2023-01-24 09:38:34.175769: step: 316/526, loss: 0.00011031299800379202
2023-01-24 09:38:35.229193: step: 320/526, loss: 0.0018698429921641946
2023-01-24 09:38:36.288381: step: 324/526, loss: 0.011391861364245415
2023-01-24 09:38:37.357945: step: 328/526, loss: 0.003047780366614461
2023-01-24 09:38:38.420312: step: 332/526, loss: 0.0006797324167564511
2023-01-24 09:38:39.487874: step: 336/526, loss: 0.0009688339196145535
2023-01-24 09:38:40.537135: step: 340/526, loss: 0.0008761750650592148
2023-01-24 09:38:41.602626: step: 344/526, loss: 0.00014412908058147877
2023-01-24 09:38:42.659846: step: 348/526, loss: 0.005223248619586229
2023-01-24 09:38:43.729708: step: 352/526, loss: 0.001717216451652348
2023-01-24 09:38:44.790462: step: 356/526, loss: 0.0007923348457552493
2023-01-24 09:38:45.864448: step: 360/526, loss: 0.0024021712597459555
2023-01-24 09:38:46.940426: step: 364/526, loss: 0.0038250302895903587
2023-01-24 09:38:48.009464: step: 368/526, loss: 0.00015468662604689598
2023-01-24 09:38:49.070487: step: 372/526, loss: 0.008588100783526897
2023-01-24 09:38:50.139885: step: 376/526, loss: 7.460331107722595e-05
2023-01-24 09:38:51.207210: step: 380/526, loss: 0.0007693101069889963
2023-01-24 09:38:52.274022: step: 384/526, loss: 8.940690854331024e-09
2023-01-24 09:38:53.335952: step: 388/526, loss: 0.00017963080608751625
2023-01-24 09:38:54.416866: step: 392/526, loss: 0.004797870293259621
2023-01-24 09:38:55.470713: step: 396/526, loss: 0.004584247712045908
2023-01-24 09:38:56.520854: step: 400/526, loss: 0.0027248673141002655
2023-01-24 09:38:57.570632: step: 404/526, loss: 0.0012818766990676522
2023-01-24 09:38:58.634924: step: 408/526, loss: 0.000545281043741852
2023-01-24 09:38:59.692880: step: 412/526, loss: 5.995823084958829e-05
2023-01-24 09:39:00.755910: step: 416/526, loss: 0.005484024528414011
2023-01-24 09:39:01.809008: step: 420/526, loss: 0.01205903384834528
2023-01-24 09:39:02.909381: step: 424/526, loss: 0.004198983311653137
2023-01-24 09:39:03.964248: step: 428/526, loss: 0.004050122573971748
2023-01-24 09:39:05.031712: step: 432/526, loss: 4.898705583400442e-07
2023-01-24 09:39:06.107623: step: 436/526, loss: 0.0020249783992767334
2023-01-24 09:39:07.174198: step: 440/526, loss: 0.0012515069684013724
2023-01-24 09:39:08.272495: step: 444/526, loss: 0.007109955884516239
2023-01-24 09:39:09.331881: step: 448/526, loss: 9.808143659029156e-05
2023-01-24 09:39:10.382724: step: 452/526, loss: 4.350836206867825e-07
2023-01-24 09:39:11.469316: step: 456/526, loss: 0.0023045584093779325
2023-01-24 09:39:12.532342: step: 460/526, loss: 0.006414884701371193
2023-01-24 09:39:13.595059: step: 464/526, loss: 0.0014815098838880658
2023-01-24 09:39:14.683843: step: 468/526, loss: 0.003358148969709873
2023-01-24 09:39:15.741297: step: 472/526, loss: 0.00015327546861954033
2023-01-24 09:39:16.804893: step: 476/526, loss: 2.0948546080035158e-05
2023-01-24 09:39:17.886045: step: 480/526, loss: 0.00772051140666008
2023-01-24 09:39:18.940705: step: 484/526, loss: 0.0003301272518001497
2023-01-24 09:39:20.001234: step: 488/526, loss: 0.0018478522542864084
2023-01-24 09:39:21.064295: step: 492/526, loss: 0.0019110242137685418
2023-01-24 09:39:22.125685: step: 496/526, loss: 0.0033654216676950455
2023-01-24 09:39:23.188462: step: 500/526, loss: 0.0014292567502707243
2023-01-24 09:39:24.255404: step: 504/526, loss: 0.0013498679036274552
2023-01-24 09:39:25.318797: step: 508/526, loss: 0.00046547886449843645
2023-01-24 09:39:26.400467: step: 512/526, loss: 0.00325377332046628
2023-01-24 09:39:27.471748: step: 516/526, loss: 0.0006572949350811541
2023-01-24 09:39:28.547820: step: 520/526, loss: 0.01178732793778181
2023-01-24 09:39:29.619737: step: 524/526, loss: 0.04705970361828804
2023-01-24 09:39:30.693795: step: 528/526, loss: 0.010218554176390171
2023-01-24 09:39:31.744318: step: 532/526, loss: 0.004194215871393681
2023-01-24 09:39:32.802171: step: 536/526, loss: 0.000167710124514997
2023-01-24 09:39:33.868127: step: 540/526, loss: 0.0002781951043289155
2023-01-24 09:39:34.932725: step: 544/526, loss: 0.00947430357336998
2023-01-24 09:39:35.998419: step: 548/526, loss: 0.00024416757514700294
2023-01-24 09:39:37.079877: step: 552/526, loss: 0.007816259749233723
2023-01-24 09:39:38.160211: step: 556/526, loss: 0.00991266593337059
2023-01-24 09:39:39.226392: step: 560/526, loss: 0.00022158684441819787
2023-01-24 09:39:40.299099: step: 564/526, loss: 0.00968110840767622
2023-01-24 09:39:41.346007: step: 568/526, loss: 0.00019517895998433232
2023-01-24 09:39:42.418089: step: 572/526, loss: 0.000621023413259536
2023-01-24 09:39:43.498734: step: 576/526, loss: 0.0002952921495307237
2023-01-24 09:39:44.547333: step: 580/526, loss: 0.012463895604014397
2023-01-24 09:39:45.625469: step: 584/526, loss: 0.045810893177986145
2023-01-24 09:39:46.690738: step: 588/526, loss: 0.00214147986844182
2023-01-24 09:39:47.750741: step: 592/526, loss: 0.005158303305506706
2023-01-24 09:39:48.819117: step: 596/526, loss: 1.2003584970443626e-07
2023-01-24 09:39:49.893799: step: 600/526, loss: 1.314815790465218e-06
2023-01-24 09:39:50.953616: step: 604/526, loss: 7.70184415159747e-05
2023-01-24 09:39:52.020879: step: 608/526, loss: 0.010479443706572056
2023-01-24 09:39:53.090455: step: 612/526, loss: 0.010963741689920425
2023-01-24 09:39:54.159365: step: 616/526, loss: 2.131580731656868e-05
2023-01-24 09:39:55.216361: step: 620/526, loss: 0.0013266350142657757
2023-01-24 09:39:56.285712: step: 624/526, loss: 0.029699038714170456
2023-01-24 09:39:57.345632: step: 628/526, loss: 1.816090843931306e-05
2023-01-24 09:39:58.418463: step: 632/526, loss: 0.0066762701608240604
2023-01-24 09:39:59.473348: step: 636/526, loss: 0.0032258988358080387
2023-01-24 09:40:00.546395: step: 640/526, loss: 0.0013715425739064813
2023-01-24 09:40:01.615105: step: 644/526, loss: 0.0016116806073114276
2023-01-24 09:40:02.677616: step: 648/526, loss: 0.0020830663852393627
2023-01-24 09:40:03.741054: step: 652/526, loss: 0.0019107782281935215
2023-01-24 09:40:04.795378: step: 656/526, loss: 0.00430784048512578
2023-01-24 09:40:05.854127: step: 660/526, loss: 0.0019466597586870193
2023-01-24 09:40:06.927991: step: 664/526, loss: 0.010582627728581429
2023-01-24 09:40:07.981678: step: 668/526, loss: 5.284410872263834e-05
2023-01-24 09:40:09.044687: step: 672/526, loss: 0.002617364749312401
2023-01-24 09:40:10.117984: step: 676/526, loss: 0.000698226154781878
2023-01-24 09:40:11.186421: step: 680/526, loss: 0.0015460714930668473
2023-01-24 09:40:12.249689: step: 684/526, loss: 0.0019059531623497605
2023-01-24 09:40:13.310830: step: 688/526, loss: 0.005433516576886177
2023-01-24 09:40:14.358795: step: 692/526, loss: 0.00041815851000137627
2023-01-24 09:40:15.431291: step: 696/526, loss: 0.006803176831454039
2023-01-24 09:40:16.494175: step: 700/526, loss: 0.005165285896509886
2023-01-24 09:40:17.551008: step: 704/526, loss: 0.0012575032887980342
2023-01-24 09:40:18.617831: step: 708/526, loss: 0.004025866277515888
2023-01-24 09:40:19.693431: step: 712/526, loss: 0.005767675116658211
2023-01-24 09:40:20.744382: step: 716/526, loss: 0.002313079545274377
2023-01-24 09:40:21.809148: step: 720/526, loss: 0.005921508651226759
2023-01-24 09:40:22.910181: step: 724/526, loss: 1.7197493434650823e-05
2023-01-24 09:40:23.968516: step: 728/526, loss: 0.0003048692306037992
2023-01-24 09:40:25.051971: step: 732/526, loss: 2.1102641767356545e-05
2023-01-24 09:40:26.097198: step: 736/526, loss: 0.0010254151420667768
2023-01-24 09:40:27.152588: step: 740/526, loss: 2.731672975642141e-05
2023-01-24 09:40:28.206668: step: 744/526, loss: 0.0015289149014279246
2023-01-24 09:40:29.279827: step: 748/526, loss: 0.004055901430547237
2023-01-24 09:40:30.361980: step: 752/526, loss: 0.0011888708686456084
2023-01-24 09:40:31.435979: step: 756/526, loss: 0.001324503100477159
2023-01-24 09:40:32.497305: step: 760/526, loss: 0.0005707154050469398
2023-01-24 09:40:33.564942: step: 764/526, loss: 0.0003623607917688787
2023-01-24 09:40:34.629344: step: 768/526, loss: 0.017197584733366966
2023-01-24 09:40:35.691936: step: 772/526, loss: 0.007878645323216915
2023-01-24 09:40:36.762437: step: 776/526, loss: 0.0019487126264721155
2023-01-24 09:40:37.833434: step: 780/526, loss: 0.0001883176009869203
2023-01-24 09:40:38.898104: step: 784/526, loss: 0.00622760783880949
2023-01-24 09:40:39.954432: step: 788/526, loss: 0.020675070583820343
2023-01-24 09:40:41.032540: step: 792/526, loss: 0.0001200784754473716
2023-01-24 09:40:42.085479: step: 796/526, loss: 6.32395267530228e-06
2023-01-24 09:40:43.150501: step: 800/526, loss: 8.042090485105291e-05
2023-01-24 09:40:44.234017: step: 804/526, loss: 0.00407861452549696
2023-01-24 09:40:45.304712: step: 808/526, loss: 0.0008503625285811722
2023-01-24 09:40:46.374559: step: 812/526, loss: 0.0016875102883204818
2023-01-24 09:40:47.446452: step: 816/526, loss: 0.00010302245937054977
2023-01-24 09:40:48.538407: step: 820/526, loss: 0.016716904938220978
2023-01-24 09:40:49.610104: step: 824/526, loss: 0.008030310273170471
2023-01-24 09:40:50.692565: step: 828/526, loss: 0.004671158734709024
2023-01-24 09:40:51.782502: step: 832/526, loss: 0.0042756772600114346
2023-01-24 09:40:52.870760: step: 836/526, loss: 0.01802619732916355
2023-01-24 09:40:53.925600: step: 840/526, loss: 0.00265071471221745
2023-01-24 09:40:54.988082: step: 844/526, loss: 8.32009973237291e-05
2023-01-24 09:40:56.066980: step: 848/526, loss: 0.007865662686526775
2023-01-24 09:40:57.143882: step: 852/526, loss: 0.002822272013872862
2023-01-24 09:40:58.205415: step: 856/526, loss: 0.020397650077939034
2023-01-24 09:40:59.260041: step: 860/526, loss: 0.005402701906859875
2023-01-24 09:41:00.305128: step: 864/526, loss: 0.005068182945251465
2023-01-24 09:41:01.369060: step: 868/526, loss: 0.007363060489296913
2023-01-24 09:41:02.448942: step: 872/526, loss: 0.005407257936894894
2023-01-24 09:41:03.517540: step: 876/526, loss: 0.002812668215483427
2023-01-24 09:41:04.600746: step: 880/526, loss: 0.002861372660845518
2023-01-24 09:41:05.650982: step: 884/526, loss: 0.0036447602324187756
2023-01-24 09:41:06.708120: step: 888/526, loss: 0.0014477837830781937
2023-01-24 09:41:07.757808: step: 892/526, loss: 0.0039412034675478935
2023-01-24 09:41:08.824357: step: 896/526, loss: 0.0034513745922595263
2023-01-24 09:41:09.900187: step: 900/526, loss: 0.002188685117289424
2023-01-24 09:41:10.960866: step: 904/526, loss: 0.017191726714372635
2023-01-24 09:41:12.019783: step: 908/526, loss: 0.0036448754835873842
2023-01-24 09:41:13.089118: step: 912/526, loss: 0.00021355488570407033
2023-01-24 09:41:14.157459: step: 916/526, loss: 0.006277720909565687
2023-01-24 09:41:15.220035: step: 920/526, loss: 0.0027636305894702673
2023-01-24 09:41:16.274893: step: 924/526, loss: 0.0003872735833283514
2023-01-24 09:41:17.344949: step: 928/526, loss: 0.00211701774969697
2023-01-24 09:41:18.406661: step: 932/526, loss: 5.502950443769805e-06
2023-01-24 09:41:19.468833: step: 936/526, loss: 0.0
2023-01-24 09:41:20.523237: step: 940/526, loss: 0.023802487179636955
2023-01-24 09:41:21.587455: step: 944/526, loss: 0.0020583763252943754
2023-01-24 09:41:22.661202: step: 948/526, loss: 0.00654433760792017
2023-01-24 09:41:23.728033: step: 952/526, loss: 0.00029706076020374894
2023-01-24 09:41:24.785211: step: 956/526, loss: 1.2530629192042397e-06
2023-01-24 09:41:25.862361: step: 960/526, loss: 0.00025267916498705745
2023-01-24 09:41:26.950761: step: 964/526, loss: 0.011599645018577576
2023-01-24 09:41:28.013307: step: 968/526, loss: 0.00014393254241440445
2023-01-24 09:41:29.081873: step: 972/526, loss: 0.003187676426023245
2023-01-24 09:41:30.149051: step: 976/526, loss: 0.018875805661082268
2023-01-24 09:41:31.210644: step: 980/526, loss: 0.001086581964045763
2023-01-24 09:41:32.296180: step: 984/526, loss: 0.0055618006736040115
2023-01-24 09:41:33.358950: step: 988/526, loss: 0.0018091712845489383
2023-01-24 09:41:34.440130: step: 992/526, loss: 0.0011270674876868725
2023-01-24 09:41:35.537216: step: 996/526, loss: 0.003447149880230427
2023-01-24 09:41:36.613859: step: 1000/526, loss: 0.005919341463595629
2023-01-24 09:41:37.675130: step: 1004/526, loss: 9.845956810750067e-05
2023-01-24 09:41:38.740125: step: 1008/526, loss: 0.005300566554069519
2023-01-24 09:41:39.815189: step: 1012/526, loss: 0.023917904123663902
2023-01-24 09:41:40.893295: step: 1016/526, loss: 0.005917427595704794
2023-01-24 09:41:41.959179: step: 1020/526, loss: 1.5766294382046908e-05
2023-01-24 09:41:43.017178: step: 1024/526, loss: 0.0003110162215307355
2023-01-24 09:41:44.070915: step: 1028/526, loss: 0.014999203383922577
2023-01-24 09:41:45.138968: step: 1032/526, loss: 0.0016218553064391017
2023-01-24 09:41:46.195567: step: 1036/526, loss: 0.00023428162967320532
2023-01-24 09:41:47.263042: step: 1040/526, loss: 0.001272703055292368
2023-01-24 09:41:48.315866: step: 1044/526, loss: 0.00016677107487339526
2023-01-24 09:41:49.376260: step: 1048/526, loss: 0.001082417438738048
2023-01-24 09:41:50.445286: step: 1052/526, loss: 0.00884781964123249
2023-01-24 09:41:51.497084: step: 1056/526, loss: 3.5004750316147693e-06
2023-01-24 09:41:52.584748: step: 1060/526, loss: 0.00772174634039402
2023-01-24 09:41:53.634895: step: 1064/526, loss: 1.67637832504397e-08
2023-01-24 09:41:54.697558: step: 1068/526, loss: 0.003868556348606944
2023-01-24 09:41:55.760079: step: 1072/526, loss: 0.0027479268610477448
2023-01-24 09:41:56.816879: step: 1076/526, loss: 0.001488381065428257
2023-01-24 09:41:57.895924: step: 1080/526, loss: 0.000838089850731194
2023-01-24 09:41:58.957082: step: 1084/526, loss: 0.0033276726026088
2023-01-24 09:42:00.021764: step: 1088/526, loss: 0.010394815355539322
2023-01-24 09:42:01.090248: step: 1092/526, loss: 0.0001972942118300125
2023-01-24 09:42:02.151362: step: 1096/526, loss: 0.003735617734491825
2023-01-24 09:42:03.217820: step: 1100/526, loss: 0.002268086886033416
2023-01-24 09:42:04.280516: step: 1104/526, loss: 0.0003494498669169843
2023-01-24 09:42:05.345459: step: 1108/526, loss: 0.009836919605731964
2023-01-24 09:42:06.412657: step: 1112/526, loss: 0.0021283235400915146
2023-01-24 09:42:07.500557: step: 1116/526, loss: 0.001698526437394321
2023-01-24 09:42:08.559376: step: 1120/526, loss: 0.002202930161729455
2023-01-24 09:42:09.632547: step: 1124/526, loss: 0.0014717536978423595
2023-01-24 09:42:10.713511: step: 1128/526, loss: 0.0005914639332331717
2023-01-24 09:42:11.809056: step: 1132/526, loss: 0.0019307390321046114
2023-01-24 09:42:12.900141: step: 1136/526, loss: 0.0006913546239957213
2023-01-24 09:42:13.968437: step: 1140/526, loss: 2.4064775061560795e-07
2023-01-24 09:42:15.044027: step: 1144/526, loss: 0.0036357359495013952
2023-01-24 09:42:16.107800: step: 1148/526, loss: 0.00438983179628849
2023-01-24 09:42:17.187695: step: 1152/526, loss: 0.006356218364089727
2023-01-24 09:42:18.237919: step: 1156/526, loss: 6.725236016791314e-05
2023-01-24 09:42:19.295490: step: 1160/526, loss: 0.004138583783060312
2023-01-24 09:42:20.364748: step: 1164/526, loss: 0.014911224134266376
2023-01-24 09:42:21.430177: step: 1168/526, loss: 0.0010892170248553157
2023-01-24 09:42:22.496635: step: 1172/526, loss: 0.0026417344342917204
2023-01-24 09:42:23.575162: step: 1176/526, loss: 0.0014654689002782106
2023-01-24 09:42:24.643802: step: 1180/526, loss: 0.0023486234713345766
2023-01-24 09:42:25.718629: step: 1184/526, loss: 0.016048137098550797
2023-01-24 09:42:26.778721: step: 1188/526, loss: 0.0032369846012443304
2023-01-24 09:42:27.849045: step: 1192/526, loss: 0.003851949004456401
2023-01-24 09:42:28.933835: step: 1196/526, loss: 0.0007502248627133667
2023-01-24 09:42:30.003113: step: 1200/526, loss: 0.0017704274505376816
2023-01-24 09:42:31.067307: step: 1204/526, loss: 0.000317789992550388
2023-01-24 09:42:32.128629: step: 1208/526, loss: 0.00018782414554152638
2023-01-24 09:42:33.201468: step: 1212/526, loss: 0.0005745368544012308
2023-01-24 09:42:34.242821: step: 1216/526, loss: 0.0016599230002611876
2023-01-24 09:42:35.300824: step: 1220/526, loss: 0.0050687422044575214
2023-01-24 09:42:36.362699: step: 1224/526, loss: 0.0016273499932140112
2023-01-24 09:42:37.414438: step: 1228/526, loss: 5.8454443205846474e-05
2023-01-24 09:42:38.497425: step: 1232/526, loss: 0.0006205542595125735
2023-01-24 09:42:39.557681: step: 1236/526, loss: 0.0033030908089131117
2023-01-24 09:42:40.613659: step: 1240/526, loss: 0.00029082567198202014
2023-01-24 09:42:41.686952: step: 1244/526, loss: 0.0015689934371039271
2023-01-24 09:42:42.738703: step: 1248/526, loss: 0.0007233127835206687
2023-01-24 09:42:43.819258: step: 1252/526, loss: 0.002532371086999774
2023-01-24 09:42:44.884275: step: 1256/526, loss: 2.2210946553968824e-05
2023-01-24 09:42:45.947960: step: 1260/526, loss: 0.002181590534746647
2023-01-24 09:42:47.016163: step: 1264/526, loss: 0.0019160900264978409
2023-01-24 09:42:48.092407: step: 1268/526, loss: 0.00016038064495660365
2023-01-24 09:42:49.151227: step: 1272/526, loss: 0.00285283918492496
2023-01-24 09:42:50.213512: step: 1276/526, loss: 0.00339349708519876
2023-01-24 09:42:51.266509: step: 1280/526, loss: 0.004356840159744024
2023-01-24 09:42:52.332347: step: 1284/526, loss: 3.193903830833733e-05
2023-01-24 09:42:53.381276: step: 1288/526, loss: 0.0013525394024327397
2023-01-24 09:42:54.429659: step: 1292/526, loss: 0.00020840868819504976
2023-01-24 09:42:55.495100: step: 1296/526, loss: 0.0008722965721972287
2023-01-24 09:42:56.570387: step: 1300/526, loss: 0.006697444710880518
2023-01-24 09:42:57.651789: step: 1304/526, loss: 0.00042540772119536996
2023-01-24 09:42:58.715410: step: 1308/526, loss: 0.0019329932983964682
2023-01-24 09:42:59.789987: step: 1312/526, loss: 0.0026747705414891243
2023-01-24 09:43:00.854512: step: 1316/526, loss: 0.00422718096524477
2023-01-24 09:43:01.899696: step: 1320/526, loss: 0.0002730051055550575
2023-01-24 09:43:02.970977: step: 1324/526, loss: 0.0023508635349571705
2023-01-24 09:43:04.027916: step: 1328/526, loss: 0.0005915589863434434
2023-01-24 09:43:05.087760: step: 1332/526, loss: 0.015235540457069874
2023-01-24 09:43:06.152447: step: 1336/526, loss: 3.590072810766287e-05
2023-01-24 09:43:07.232518: step: 1340/526, loss: 0.0007943271775729954
2023-01-24 09:43:08.296576: step: 1344/526, loss: 0.0016559530049562454
2023-01-24 09:43:09.350547: step: 1348/526, loss: 0.0007076248293742537
2023-01-24 09:43:10.421588: step: 1352/526, loss: 8.903425907647033e-08
2023-01-24 09:43:11.480533: step: 1356/526, loss: 0.001404323149472475
2023-01-24 09:43:12.547855: step: 1360/526, loss: 0.015384942293167114
2023-01-24 09:43:13.630619: step: 1364/526, loss: 0.012438459321856499
2023-01-24 09:43:14.695763: step: 1368/526, loss: 3.979983739554882e-05
2023-01-24 09:43:15.747301: step: 1372/526, loss: 4.5222627704788465e-06
2023-01-24 09:43:16.817453: step: 1376/526, loss: 1.7502095943200402e-05
2023-01-24 09:43:17.888171: step: 1380/526, loss: 0.002580471569672227
2023-01-24 09:43:18.957872: step: 1384/526, loss: 0.0015712663298472762
2023-01-24 09:43:20.032035: step: 1388/526, loss: 0.00015530420932918787
2023-01-24 09:43:21.119135: step: 1392/526, loss: 0.002688699634745717
2023-01-24 09:43:22.189105: step: 1396/526, loss: 0.0003553742717485875
2023-01-24 09:43:23.251931: step: 1400/526, loss: 0.0008208309882320464
2023-01-24 09:43:24.346058: step: 1404/526, loss: 0.0028692386113107204
2023-01-24 09:43:25.408189: step: 1408/526, loss: 0.007166000548750162
2023-01-24 09:43:26.479275: step: 1412/526, loss: 0.0019115055911242962
2023-01-24 09:43:27.533524: step: 1416/526, loss: 0.0001056921246345155
2023-01-24 09:43:28.600719: step: 1420/526, loss: 0.0048519521951675415
2023-01-24 09:43:29.660816: step: 1424/526, loss: 0.0022555729374289513
2023-01-24 09:43:30.745821: step: 1428/526, loss: 0.001717675942927599
2023-01-24 09:43:31.793002: step: 1432/526, loss: 0.0009089690865948796
2023-01-24 09:43:32.866910: step: 1436/526, loss: 0.0009131130645982921
2023-01-24 09:43:33.930770: step: 1440/526, loss: 3.941644899896346e-05
2023-01-24 09:43:34.987685: step: 1444/526, loss: 0.004647328983992338
2023-01-24 09:43:36.060873: step: 1448/526, loss: 0.004759537987411022
2023-01-24 09:43:37.143212: step: 1452/526, loss: 0.009364446625113487
2023-01-24 09:43:38.193741: step: 1456/526, loss: 0.004628939554095268
2023-01-24 09:43:39.265095: step: 1460/526, loss: 0.003136337734758854
2023-01-24 09:43:40.310678: step: 1464/526, loss: 0.0025901608169078827
2023-01-24 09:43:41.373057: step: 1468/526, loss: 0.002862700028344989
2023-01-24 09:43:42.442165: step: 1472/526, loss: 0.0007572476170025766
2023-01-24 09:43:43.533398: step: 1476/526, loss: 0.00041822122875601053
2023-01-24 09:43:44.586274: step: 1480/526, loss: 1.0058267996271297e-08
2023-01-24 09:43:45.641122: step: 1484/526, loss: 0.0030537082348018885
2023-01-24 09:43:46.710220: step: 1488/526, loss: 0.0032735567074269056
2023-01-24 09:43:47.781697: step: 1492/526, loss: 0.005973272956907749
2023-01-24 09:43:48.832559: step: 1496/526, loss: 0.0034401416778564453
2023-01-24 09:43:49.915347: step: 1500/526, loss: 0.0072583528235554695
2023-01-24 09:43:50.980601: step: 1504/526, loss: 0.027225736528635025
2023-01-24 09:43:52.041791: step: 1508/526, loss: 3.34796350216493e-05
2023-01-24 09:43:53.120344: step: 1512/526, loss: 0.0007972502498887479
2023-01-24 09:43:54.184579: step: 1516/526, loss: 0.002958337077870965
2023-01-24 09:43:55.243621: step: 1520/526, loss: 0.0003607078979257494
2023-01-24 09:43:56.302398: step: 1524/526, loss: 0.002616273704916239
2023-01-24 09:43:57.379461: step: 1528/526, loss: 0.03285061568021774
2023-01-24 09:43:58.448176: step: 1532/526, loss: 0.0025253540370613337
2023-01-24 09:43:59.533865: step: 1536/526, loss: 0.0006588302785530686
2023-01-24 09:44:00.598763: step: 1540/526, loss: 0.0011586386244744062
2023-01-24 09:44:01.665969: step: 1544/526, loss: 0.001132720848545432
2023-01-24 09:44:02.738957: step: 1548/526, loss: 0.0004962706007063389
2023-01-24 09:44:03.784298: step: 1552/526, loss: 0.008462740108370781
2023-01-24 09:44:04.841180: step: 1556/526, loss: 0.0015544499037787318
2023-01-24 09:44:05.904516: step: 1560/526, loss: 0.002198633970692754
2023-01-24 09:44:06.981377: step: 1564/526, loss: 0.0031304911244660616
2023-01-24 09:44:08.065980: step: 1568/526, loss: 0.0003748323943000287
2023-01-24 09:44:09.159072: step: 1572/526, loss: 0.002680462319403887
2023-01-24 09:44:10.229246: step: 1576/526, loss: 0.0027973796240985394
2023-01-24 09:44:11.298928: step: 1580/526, loss: 2.9268176149344072e-05
2023-01-24 09:44:12.384048: step: 1584/526, loss: 0.0005433326005004346
2023-01-24 09:44:13.458097: step: 1588/526, loss: 0.004561637528240681
2023-01-24 09:44:14.514933: step: 1592/526, loss: 0.00035780001780949533
2023-01-24 09:44:15.570391: step: 1596/526, loss: 0.00047474136226810515
2023-01-24 09:44:16.625783: step: 1600/526, loss: 2.9299728339537978e-05
2023-01-24 09:44:17.692627: step: 1604/526, loss: 0.002011873759329319
2023-01-24 09:44:18.748926: step: 1608/526, loss: 5.00100250064861e-05
2023-01-24 09:44:19.788356: step: 1612/526, loss: 6.500922609120607e-06
2023-01-24 09:44:20.854183: step: 1616/526, loss: 0.006943310145288706
2023-01-24 09:44:21.927646: step: 1620/526, loss: 0.0010031199781224132
2023-01-24 09:44:22.991748: step: 1624/526, loss: 0.0005478385137394071
2023-01-24 09:44:24.053686: step: 1628/526, loss: 0.0005698002642020583
2023-01-24 09:44:25.136202: step: 1632/526, loss: 0.0018338001100346446
2023-01-24 09:44:26.218893: step: 1636/526, loss: 0.0005114403320476413
2023-01-24 09:44:27.287673: step: 1640/526, loss: 7.066483522066846e-05
2023-01-24 09:44:28.345271: step: 1644/526, loss: 2.204283737228252e-05
2023-01-24 09:44:29.418556: step: 1648/526, loss: 0.00647963210940361
2023-01-24 09:44:30.474575: step: 1652/526, loss: 0.003956041298806667
2023-01-24 09:44:31.549347: step: 1656/526, loss: 0.0016059986082836986
2023-01-24 09:44:32.624578: step: 1660/526, loss: 0.001439710846170783
2023-01-24 09:44:33.687578: step: 1664/526, loss: 0.0032056074123829603
2023-01-24 09:44:34.760479: step: 1668/526, loss: 0.0007851261761970818
2023-01-24 09:44:35.822611: step: 1672/526, loss: 0.003304389538243413
2023-01-24 09:44:36.887979: step: 1676/526, loss: 0.0013723867014050484
2023-01-24 09:44:37.962595: step: 1680/526, loss: 0.002044790191575885
2023-01-24 09:44:39.035345: step: 1684/526, loss: 0.0009177444153465331
2023-01-24 09:44:40.113240: step: 1688/526, loss: 0.0008950474439188838
2023-01-24 09:44:41.180397: step: 1692/526, loss: 0.002920059720054269
2023-01-24 09:44:42.265024: step: 1696/526, loss: 1.0374760677223094e-06
2023-01-24 09:44:43.321523: step: 1700/526, loss: 0.0005049766623415053
2023-01-24 09:44:44.377414: step: 1704/526, loss: 0.002634551841765642
2023-01-24 09:44:45.432642: step: 1708/526, loss: 0.0002857272047549486
2023-01-24 09:44:46.493560: step: 1712/526, loss: 2.25374515139265e-05
2023-01-24 09:44:47.558158: step: 1716/526, loss: 0.0007042968063615263
2023-01-24 09:44:48.632084: step: 1720/526, loss: 4.939256177749485e-05
2023-01-24 09:44:49.691846: step: 1724/526, loss: 0.001288863830268383
2023-01-24 09:44:50.753400: step: 1728/526, loss: 0.002705493476241827
2023-01-24 09:44:51.814947: step: 1732/526, loss: 0.0029062661342322826
2023-01-24 09:44:52.886109: step: 1736/526, loss: 2.4182270863093436e-05
2023-01-24 09:44:53.941749: step: 1740/526, loss: 0.005565832369029522
2023-01-24 09:44:55.025204: step: 1744/526, loss: 4.294197788112797e-05
2023-01-24 09:44:56.093413: step: 1748/526, loss: 0.0010161824757233262
2023-01-24 09:44:57.171583: step: 1752/526, loss: 6.783211574656889e-06
2023-01-24 09:44:58.234653: step: 1756/526, loss: 0.043723803013563156
2023-01-24 09:44:59.310990: step: 1760/526, loss: 0.001600755611434579
2023-01-24 09:45:00.356604: step: 1764/526, loss: 5.468020845000865e-06
2023-01-24 09:45:01.415548: step: 1768/526, loss: 0.0036688607651740313
2023-01-24 09:45:02.478561: step: 1772/526, loss: 0.005449839401990175
2023-01-24 09:45:03.549539: step: 1776/526, loss: 0.004576548933982849
2023-01-24 09:45:04.625661: step: 1780/526, loss: 0.005206066649407148
2023-01-24 09:45:05.679565: step: 1784/526, loss: 3.613529386825576e-08
2023-01-24 09:45:06.744022: step: 1788/526, loss: 0.0015814868966117501
2023-01-24 09:45:07.823326: step: 1792/526, loss: 0.0016092988662421703
2023-01-24 09:45:08.893521: step: 1796/526, loss: 0.00021931059018243104
2023-01-24 09:45:09.963510: step: 1800/526, loss: 0.005094549153000116
2023-01-24 09:45:11.023179: step: 1804/526, loss: 0.0007954631582833827
2023-01-24 09:45:12.078361: step: 1808/526, loss: 0.0015829253243282437
2023-01-24 09:45:13.153562: step: 1812/526, loss: 0.003134468337520957
2023-01-24 09:45:14.225502: step: 1816/526, loss: 0.0036410358734428883
2023-01-24 09:45:15.300311: step: 1820/526, loss: 0.004590882919728756
2023-01-24 09:45:16.362496: step: 1824/526, loss: 0.0006469223299063742
2023-01-24 09:45:17.432525: step: 1828/526, loss: 0.0007000057958066463
2023-01-24 09:45:18.485039: step: 1832/526, loss: 0.0028438419103622437
2023-01-24 09:45:19.538988: step: 1836/526, loss: 0.000142493678140454
2023-01-24 09:45:20.590947: step: 1840/526, loss: 0.00486264331266284
2023-01-24 09:45:21.651919: step: 1844/526, loss: 0.0035808393731713295
2023-01-24 09:45:22.705870: step: 1848/526, loss: 0.0003518101875670254
2023-01-24 09:45:23.769956: step: 1852/526, loss: 0.002024126471951604
2023-01-24 09:45:24.830800: step: 1856/526, loss: 0.012850222177803516
2023-01-24 09:45:25.877578: step: 1860/526, loss: 0.00039805955020710826
2023-01-24 09:45:26.919431: step: 1864/526, loss: 0.0037232115864753723
2023-01-24 09:45:27.977577: step: 1868/526, loss: 0.005582768004387617
2023-01-24 09:45:29.031021: step: 1872/526, loss: 0.0005623808247037232
2023-01-24 09:45:30.111582: step: 1876/526, loss: 0.0016592019237577915
2023-01-24 09:45:31.176144: step: 1880/526, loss: 0.004121776670217514
2023-01-24 09:45:32.247505: step: 1884/526, loss: 0.007590590510517359
2023-01-24 09:45:33.328170: step: 1888/526, loss: 0.0072757345624268055
2023-01-24 09:45:34.390391: step: 1892/526, loss: 0.005597613751888275
2023-01-24 09:45:35.461615: step: 1896/526, loss: 0.0008631025557406247
2023-01-24 09:45:36.535620: step: 1900/526, loss: 0.0017087755259126425
2023-01-24 09:45:37.598632: step: 1904/526, loss: 0.004748784936964512
2023-01-24 09:45:38.670763: step: 1908/526, loss: 0.004131928086280823
2023-01-24 09:45:39.729483: step: 1912/526, loss: 0.0014519084943458438
2023-01-24 09:45:40.787507: step: 1916/526, loss: 0.00809105858206749
2023-01-24 09:45:41.856911: step: 1920/526, loss: 0.0004664697335101664
2023-01-24 09:45:42.918335: step: 1924/526, loss: 0.0006500197923742235
2023-01-24 09:45:43.983505: step: 1928/526, loss: 0.0017618017736822367
2023-01-24 09:45:45.040067: step: 1932/526, loss: 6.68510765535757e-05
2023-01-24 09:45:46.100170: step: 1936/526, loss: 0.002272934652864933
2023-01-24 09:45:47.178173: step: 1940/526, loss: 0.0025545170065015554
2023-01-24 09:45:48.249163: step: 1944/526, loss: 5.807965135318227e-05
2023-01-24 09:45:49.322377: step: 1948/526, loss: 0.0007770382217131555
2023-01-24 09:45:50.379779: step: 1952/526, loss: 2.8514297810033895e-05
2023-01-24 09:45:51.472560: step: 1956/526, loss: 0.0037726627197116613
2023-01-24 09:45:52.525302: step: 1960/526, loss: 3.890847821708121e-08
2023-01-24 09:45:53.604321: step: 1964/526, loss: 0.0003265069972258061
2023-01-24 09:45:54.694047: step: 1968/526, loss: 0.0034496900625526905
2023-01-24 09:45:55.745706: step: 1972/526, loss: 0.005602105986326933
2023-01-24 09:45:56.811331: step: 1976/526, loss: 0.004039344377815723
2023-01-24 09:45:57.880434: step: 1980/526, loss: 0.0053483834490180016
2023-01-24 09:45:58.942140: step: 1984/526, loss: 0.032101910561323166
2023-01-24 09:46:00.015681: step: 1988/526, loss: 0.00018123260815627873
2023-01-24 09:46:01.104289: step: 1992/526, loss: 2.514551340482285e-07
2023-01-24 09:46:02.179430: step: 1996/526, loss: 0.0031049828976392746
2023-01-24 09:46:03.239221: step: 2000/526, loss: 0.00010156889766221866
2023-01-24 09:46:04.302680: step: 2004/526, loss: 0.0019236773950979114
2023-01-24 09:46:05.368588: step: 2008/526, loss: 0.004513517487794161
2023-01-24 09:46:06.460370: step: 2012/526, loss: 0.000804692623205483
2023-01-24 09:46:07.528001: step: 2016/526, loss: 0.013205349445343018
2023-01-24 09:46:08.599493: step: 2020/526, loss: 0.0024769336450845003
2023-01-24 09:46:09.682989: step: 2024/526, loss: 0.013315088115632534
2023-01-24 09:46:10.753159: step: 2028/526, loss: 0.007460259832441807
2023-01-24 09:46:11.823700: step: 2032/526, loss: 0.002822374226525426
2023-01-24 09:46:12.906954: step: 2036/526, loss: 0.0010779191507026553
2023-01-24 09:46:13.977548: step: 2040/526, loss: 0.001435117213986814
2023-01-24 09:46:15.036412: step: 2044/526, loss: 0.0010898748878389597
2023-01-24 09:46:16.088056: step: 2048/526, loss: 0.0006823171279393137
2023-01-24 09:46:17.175902: step: 2052/526, loss: 0.005039572715759277
2023-01-24 09:46:18.264719: step: 2056/526, loss: 0.008580667898058891
2023-01-24 09:46:19.321801: step: 2060/526, loss: 0.0006023873575031757
2023-01-24 09:46:20.385511: step: 2064/526, loss: 5.9271555073792115e-05
2023-01-24 09:46:21.458531: step: 2068/526, loss: 0.0025310919154435396
2023-01-24 09:46:22.533792: step: 2072/526, loss: 0.003380388719961047
2023-01-24 09:46:23.615125: step: 2076/526, loss: 0.0006637676269747317
2023-01-24 09:46:24.708228: step: 2080/526, loss: 0.004664552863687277
2023-01-24 09:46:25.803613: step: 2084/526, loss: 0.00042629099334590137
2023-01-24 09:46:26.862907: step: 2088/526, loss: 5.476576916407794e-06
2023-01-24 09:46:27.933453: step: 2092/526, loss: 0.0011100373230874538
2023-01-24 09:46:28.990448: step: 2096/526, loss: 0.0008667405345477164
2023-01-24 09:46:30.077837: step: 2100/526, loss: 0.001465075183659792
2023-01-24 09:46:31.143430: step: 2104/526, loss: 0.0012715288903564215
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3685116048938467, 'r': 0.27760741393331523, 'f1': 0.3166647340754483}, 'combined': 0.2333319093187514, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3581925852332148, 'r': 0.2238294013854398, 'f1': 0.2755017294079794}, 'combined': 0.15027367058617058, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3413463038053649, 'r': 0.2966539034968826, 'f1': 0.31743473531544597}, 'combined': 0.2338992786534865, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3571390200599459, 'r': 0.2604206761095854, 'f1': 0.30120613649500194}, 'combined': 0.16429425627000105, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3596832775810049, 'r': 0.3153200649761371, 'f1': 0.3360438306216871}, 'combined': 0.24761124361597994, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36381460474744315, 'r': 0.2782699081142383, 'f1': 0.31534371132074906}, 'combined': 0.17200566072040857, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.47619047619047616, 'r': 0.43478260869565216, 'f1': 0.4545454545454545}, 'combined': 0.22727272727272724, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 18}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3413463038053649, 'r': 0.2966539034968826, 'f1': 0.31743473531544597}, 'combined': 0.2338992786534865, 'stategy': 1, 'epoch': 18}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3571390200599459, 'r': 0.2604206761095854, 'f1': 0.30120613649500194}, 'combined': 0.16429425627000105, 'stategy': 1, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.47619047619047616, 'r': 0.43478260869565216, 'f1': 0.4545454545454545}, 'combined': 0.22727272727272724, 'stategy': 1, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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 09:49:19.905226: step: 4/526, loss: 0.000569669995456934
2023-01-24 09:49:20.971049: step: 8/526, loss: 3.2244915928458795e-05
2023-01-24 09:49:22.031861: step: 12/526, loss: 0.0024412390775978565
2023-01-24 09:49:23.070944: step: 16/526, loss: 0.006111631169915199
2023-01-24 09:49:24.125382: step: 20/526, loss: 0.00016594465705566108
2023-01-24 09:49:25.176901: step: 24/526, loss: 0.0001973848120542243
2023-01-24 09:49:26.236260: step: 28/526, loss: 0.00048437825171276927
2023-01-24 09:49:27.286861: step: 32/526, loss: 0.00014461729733739048
2023-01-24 09:49:28.348288: step: 36/526, loss: 5.002100806450471e-05
2023-01-24 09:49:29.416000: step: 40/526, loss: 0.000659647339489311
2023-01-24 09:49:30.452770: step: 44/526, loss: 0.0010140965459868312
2023-01-24 09:49:31.510966: step: 48/526, loss: 0.0045945728197693825
2023-01-24 09:49:32.570454: step: 52/526, loss: 0.01648615673184395
2023-01-24 09:49:33.621576: step: 56/526, loss: 0.014753147959709167
2023-01-24 09:49:34.671844: step: 60/526, loss: 0.0036627831868827343
2023-01-24 09:49:35.722176: step: 64/526, loss: 0.0016998531064018607
2023-01-24 09:49:36.789064: step: 68/526, loss: 0.0015511858509853482
2023-01-24 09:49:37.830617: step: 72/526, loss: 0.0016527875559404492
2023-01-24 09:49:38.884951: step: 76/526, loss: 0.008284826762974262
2023-01-24 09:49:39.947927: step: 80/526, loss: 0.0019192583858966827
2023-01-24 09:49:41.006468: step: 84/526, loss: 0.00046214356552809477
2023-01-24 09:49:42.063011: step: 88/526, loss: 0.0023678361903876066
2023-01-24 09:49:43.132107: step: 92/526, loss: 0.0011270419927313924
2023-01-24 09:49:44.200148: step: 96/526, loss: 0.0011837695492431521
2023-01-24 09:49:45.274446: step: 100/526, loss: 0.005285175982862711
2023-01-24 09:49:46.324339: step: 104/526, loss: 0.00016043600044213235
2023-01-24 09:49:47.388060: step: 108/526, loss: 0.005015851464122534
2023-01-24 09:49:48.450460: step: 112/526, loss: 0.00028798842686228454
2023-01-24 09:49:49.529368: step: 116/526, loss: 0.0035528892185539007
2023-01-24 09:49:50.572761: step: 120/526, loss: 0.003343100193887949
2023-01-24 09:49:51.625166: step: 124/526, loss: 0.0009230113355442882
2023-01-24 09:49:52.670699: step: 128/526, loss: 0.0028537840116769075
2023-01-24 09:49:53.726781: step: 132/526, loss: 0.0014088028110563755
2023-01-24 09:49:54.775689: step: 136/526, loss: 0.00044063152745366096
2023-01-24 09:49:55.838535: step: 140/526, loss: 0.0011419329093769193
2023-01-24 09:49:56.887136: step: 144/526, loss: 0.00012337852967903018
2023-01-24 09:49:57.954950: step: 148/526, loss: 7.015644223429263e-05
2023-01-24 09:49:59.004315: step: 152/526, loss: 0.0028316678944975138
2023-01-24 09:50:00.069131: step: 156/526, loss: 0.0024008823093026876
2023-01-24 09:50:01.129907: step: 160/526, loss: 0.013563969172537327
2023-01-24 09:50:02.201269: step: 164/526, loss: 0.0017817881889641285
2023-01-24 09:50:03.269622: step: 168/526, loss: 0.006673426833003759
2023-01-24 09:50:04.316317: step: 172/526, loss: 4.339169754530303e-05
2023-01-24 09:50:05.380031: step: 176/526, loss: 0.001986489864066243
2023-01-24 09:50:06.443667: step: 180/526, loss: 0.016091465950012207
2023-01-24 09:50:07.499902: step: 184/526, loss: 0.000978349125944078
2023-01-24 09:50:08.567850: step: 188/526, loss: 0.012071536853909492
2023-01-24 09:50:09.648288: step: 192/526, loss: 0.0010617480147629976
2023-01-24 09:50:10.713303: step: 196/526, loss: 2.8688744350802153e-05
2023-01-24 09:50:11.774048: step: 200/526, loss: 0.00386435491964221
2023-01-24 09:50:12.857751: step: 204/526, loss: 0.005183544475585222
2023-01-24 09:50:13.903552: step: 208/526, loss: 0.0015531701501458883
2023-01-24 09:50:14.957692: step: 212/526, loss: 0.04391736909747124
2023-01-24 09:50:16.000551: step: 216/526, loss: 0.001453329692594707
2023-01-24 09:50:17.057486: step: 220/526, loss: 0.0009062530589289963
2023-01-24 09:50:18.114887: step: 224/526, loss: 1.8443685689817357e-07
2023-01-24 09:50:19.167392: step: 228/526, loss: 0.003171028569340706
2023-01-24 09:50:20.225658: step: 232/526, loss: 0.012162331491708755
2023-01-24 09:50:21.291052: step: 236/526, loss: 0.0022634435445070267
2023-01-24 09:50:22.342852: step: 240/526, loss: 0.00045546016190201044
2023-01-24 09:50:23.423353: step: 244/526, loss: 0.0020304692443460226
2023-01-24 09:50:24.502609: step: 248/526, loss: 0.008071152493357658
2023-01-24 09:50:25.563324: step: 252/526, loss: 0.0001804004714358598
2023-01-24 09:50:26.651367: step: 256/526, loss: 0.006697654724121094
2023-01-24 09:50:27.706006: step: 260/526, loss: 0.016047224402427673
2023-01-24 09:50:28.770703: step: 264/526, loss: 0.005625705700367689
2023-01-24 09:50:29.821323: step: 268/526, loss: 0.0002054600336123258
2023-01-24 09:50:30.887652: step: 272/526, loss: 3.677611312014051e-05
2023-01-24 09:50:31.964455: step: 276/526, loss: 0.003997755236923695
2023-01-24 09:50:33.034034: step: 280/526, loss: 0.00029645985341630876
2023-01-24 09:50:34.088577: step: 284/526, loss: 0.0006751755136065185
2023-01-24 09:50:35.154134: step: 288/526, loss: 0.001563030993565917
2023-01-24 09:50:36.200495: step: 292/526, loss: 0.00112351484131068
2023-01-24 09:50:37.280106: step: 296/526, loss: 0.0025632455945014954
2023-01-24 09:50:38.327978: step: 300/526, loss: 0.005517404060810804
2023-01-24 09:50:39.377541: step: 304/526, loss: 8.595208055339754e-05
2023-01-24 09:50:40.450836: step: 308/526, loss: 0.0011672399705275893
2023-01-24 09:50:41.519169: step: 312/526, loss: 0.0028854880947619677
2023-01-24 09:50:42.582798: step: 316/526, loss: 0.0003983911301475018
2023-01-24 09:50:43.657292: step: 320/526, loss: 1.4268714039644692e-05
2023-01-24 09:50:44.708966: step: 324/526, loss: 0.002732402179390192
2023-01-24 09:50:45.769850: step: 328/526, loss: 0.003224008483812213
2023-01-24 09:50:46.838188: step: 332/526, loss: 9.395511006005108e-05
2023-01-24 09:50:47.900369: step: 336/526, loss: 0.0034900426398962736
2023-01-24 09:50:48.961177: step: 340/526, loss: 0.005861368961632252
2023-01-24 09:50:50.049379: step: 344/526, loss: 0.002362034749239683
2023-01-24 09:50:51.113852: step: 348/526, loss: 0.0017583552980795503
2023-01-24 09:50:52.173592: step: 352/526, loss: 0.008526742458343506
2023-01-24 09:50:53.234502: step: 356/526, loss: 0.000456963200122118
2023-01-24 09:50:54.299649: step: 360/526, loss: 0.004144969396293163
2023-01-24 09:50:55.364921: step: 364/526, loss: 0.0024426057934761047
2023-01-24 09:50:56.430866: step: 368/526, loss: 0.0011936324881389737
2023-01-24 09:50:57.498307: step: 372/526, loss: 2.695504690564121e-06
2023-01-24 09:50:58.561339: step: 376/526, loss: 0.0002537055697757751
2023-01-24 09:50:59.633846: step: 380/526, loss: 0.0034151566214859486
2023-01-24 09:51:00.694350: step: 384/526, loss: 0.0006154229631647468
2023-01-24 09:51:01.763053: step: 388/526, loss: 0.00034621491795405746
2023-01-24 09:51:02.842765: step: 392/526, loss: 0.0012314682826399803
2023-01-24 09:51:03.913365: step: 396/526, loss: 0.00019274740770924836
2023-01-24 09:51:04.974090: step: 400/526, loss: 0.002828571479767561
2023-01-24 09:51:06.031605: step: 404/526, loss: 8.624631959719409e-07
2023-01-24 09:51:07.086556: step: 408/526, loss: 0.0013867750531062484
2023-01-24 09:51:08.148591: step: 412/526, loss: 1.3585689885076135e-05
2023-01-24 09:51:09.211768: step: 416/526, loss: 0.0030869045294821262
2023-01-24 09:51:10.281291: step: 420/526, loss: 5.697604592569405e-06
2023-01-24 09:51:11.351402: step: 424/526, loss: 0.0044848923571407795
2023-01-24 09:51:12.411879: step: 428/526, loss: 0.00022074829030316323
2023-01-24 09:51:13.489584: step: 432/526, loss: 0.000835778599139303
2023-01-24 09:51:14.566250: step: 436/526, loss: 2.2209900635061786e-05
2023-01-24 09:51:15.636051: step: 440/526, loss: 0.0015263669192790985
2023-01-24 09:51:16.691214: step: 444/526, loss: 0.0013343016617000103
2023-01-24 09:51:17.750266: step: 448/526, loss: 0.0004796128487214446
2023-01-24 09:51:18.826133: step: 452/526, loss: 0.0045418450608849525
2023-01-24 09:51:19.896948: step: 456/526, loss: 0.0002619755978230387
2023-01-24 09:51:20.966605: step: 460/526, loss: 0.003085214179009199
2023-01-24 09:51:22.019835: step: 464/526, loss: 6.343096174532548e-05
2023-01-24 09:51:23.091461: step: 468/526, loss: 0.0013672653585672379
2023-01-24 09:51:24.151119: step: 472/526, loss: 0.003144089598208666
2023-01-24 09:51:25.224522: step: 476/526, loss: 0.0060950350016355515
2023-01-24 09:51:26.302847: step: 480/526, loss: 0.00015191845886874944
2023-01-24 09:51:27.368558: step: 484/526, loss: 0.009082391858100891
2023-01-24 09:51:28.467669: step: 488/526, loss: 0.005123598035424948
2023-01-24 09:51:29.519809: step: 492/526, loss: 9.851953564066207e-07
2023-01-24 09:51:30.593900: step: 496/526, loss: 0.00010150056186830625
2023-01-24 09:51:31.656074: step: 500/526, loss: 0.0009043654426932335
2023-01-24 09:51:32.722835: step: 504/526, loss: 0.003390824655070901
2023-01-24 09:51:33.791814: step: 508/526, loss: 0.0026581601705402136
2023-01-24 09:51:34.866533: step: 512/526, loss: 0.0013180566020309925
2023-01-24 09:51:35.935697: step: 516/526, loss: 0.0028439939487725496
2023-01-24 09:51:37.006252: step: 520/526, loss: 0.0023930263705551624
2023-01-24 09:51:38.059611: step: 524/526, loss: 0.00011110230116173625
2023-01-24 09:51:39.130464: step: 528/526, loss: 0.0007991700549609959
2023-01-24 09:51:40.205306: step: 532/526, loss: 0.004436293616890907
2023-01-24 09:51:41.266546: step: 536/526, loss: 0.0008413216564804316
2023-01-24 09:51:42.342977: step: 540/526, loss: 0.0013426182558760047
2023-01-24 09:51:43.418438: step: 544/526, loss: 0.011862105689942837
2023-01-24 09:51:44.488452: step: 548/526, loss: 0.000603470194619149
2023-01-24 09:51:45.559413: step: 552/526, loss: 0.0012973761186003685
2023-01-24 09:51:46.621211: step: 556/526, loss: 0.005763054825365543
2023-01-24 09:51:47.693032: step: 560/526, loss: 0.0020640764851123095
2023-01-24 09:51:48.764502: step: 564/526, loss: 0.0017110321205109358
2023-01-24 09:51:49.834469: step: 568/526, loss: 0.0024442095309495926
2023-01-24 09:51:50.929767: step: 572/526, loss: 0.04741708189249039
2023-01-24 09:51:52.024081: step: 576/526, loss: 0.0006900339503772557
2023-01-24 09:51:53.101609: step: 580/526, loss: 0.00041801895713433623
2023-01-24 09:51:54.171568: step: 584/526, loss: 0.00019650156900752336
2023-01-24 09:51:55.252464: step: 588/526, loss: 0.00042187742656096816
2023-01-24 09:51:56.317485: step: 592/526, loss: 0.00012364753638394177
2023-01-24 09:51:57.396934: step: 596/526, loss: 0.00045142672024667263
2023-01-24 09:51:58.471991: step: 600/526, loss: 0.0035812421701848507
2023-01-24 09:51:59.534151: step: 604/526, loss: 0.0034070913679897785
2023-01-24 09:52:00.595192: step: 608/526, loss: 0.002796769142150879
2023-01-24 09:52:01.679202: step: 612/526, loss: 0.010457450523972511
2023-01-24 09:52:02.744137: step: 616/526, loss: 0.0021682356018573046
2023-01-24 09:52:03.813489: step: 620/526, loss: 0.0013233019271865487
2023-01-24 09:52:04.881501: step: 624/526, loss: 0.0010071101132780313
2023-01-24 09:52:05.958238: step: 628/526, loss: 0.001086207339540124
2023-01-24 09:52:07.020740: step: 632/526, loss: 0.0038121482357382774
2023-01-24 09:52:08.091345: step: 636/526, loss: 0.0034389120992273092
2023-01-24 09:52:09.171531: step: 640/526, loss: 0.0036294718738645315
2023-01-24 09:52:10.225404: step: 644/526, loss: 0.0021401431877166033
2023-01-24 09:52:11.284042: step: 648/526, loss: 0.0011671707034111023
2023-01-24 09:52:12.365485: step: 652/526, loss: 0.0002695779548957944
2023-01-24 09:52:13.433615: step: 656/526, loss: 0.0038533394690603018
2023-01-24 09:52:14.510964: step: 660/526, loss: 0.00017523662245366722
2023-01-24 09:52:15.585693: step: 664/526, loss: 4.067300324095413e-05
2023-01-24 09:52:16.654682: step: 668/526, loss: 0.002836147788912058
2023-01-24 09:52:17.732026: step: 672/526, loss: 0.0037578134797513485
2023-01-24 09:52:18.796820: step: 676/526, loss: 0.00014514665235765278
2023-01-24 09:52:19.875192: step: 680/526, loss: 0.0015787945594638586
2023-01-24 09:52:20.953174: step: 684/526, loss: 0.010320290923118591
2023-01-24 09:52:22.029984: step: 688/526, loss: 0.007087341509759426
2023-01-24 09:52:23.106013: step: 692/526, loss: 1.1761619134631474e-05
2023-01-24 09:52:24.160382: step: 696/526, loss: 0.0007945873658172786
2023-01-24 09:52:25.220330: step: 700/526, loss: 0.0002718539035413414
2023-01-24 09:52:26.283216: step: 704/526, loss: 0.0
2023-01-24 09:52:27.355271: step: 708/526, loss: 0.00011284255015198141
2023-01-24 09:52:28.426797: step: 712/526, loss: 3.4059776226058602e-06
2023-01-24 09:52:29.505384: step: 716/526, loss: 0.003200100501999259
2023-01-24 09:52:30.583482: step: 720/526, loss: 0.006048861891031265
2023-01-24 09:52:31.682986: step: 724/526, loss: 0.0012870689388364553
2023-01-24 09:52:32.759983: step: 728/526, loss: 2.732599023147486e-05
2023-01-24 09:52:33.849351: step: 732/526, loss: 0.0008709495887160301
2023-01-24 09:52:34.917711: step: 736/526, loss: 0.003461112268269062
2023-01-24 09:52:35.996050: step: 740/526, loss: 0.00013872893759980798
2023-01-24 09:52:37.066706: step: 744/526, loss: 0.007967110723257065
2023-01-24 09:52:38.145071: step: 748/526, loss: 0.0004007107054349035
2023-01-24 09:52:39.219441: step: 752/526, loss: 3.608710176195018e-05
2023-01-24 09:52:40.280916: step: 756/526, loss: 6.621971988352016e-05
2023-01-24 09:52:41.347923: step: 760/526, loss: 0.007780269719660282
2023-01-24 09:52:42.429640: step: 764/526, loss: 0.001570235239341855
2023-01-24 09:52:43.494246: step: 768/526, loss: 0.0058837831020355225
2023-01-24 09:52:44.559870: step: 772/526, loss: 3.5347639482097293e-07
2023-01-24 09:52:45.649038: step: 776/526, loss: 0.0017492821207270026
2023-01-24 09:52:46.711242: step: 780/526, loss: 0.00011164666648255661
2023-01-24 09:52:47.773144: step: 784/526, loss: 0.01498086005449295
2023-01-24 09:52:48.842412: step: 788/526, loss: 0.00361587293446064
2023-01-24 09:52:49.926852: step: 792/526, loss: 3.799923797487281e-05
2023-01-24 09:52:50.994154: step: 796/526, loss: 0.0005075965891592205
2023-01-24 09:52:52.067567: step: 800/526, loss: 0.01113780029118061
2023-01-24 09:52:53.139194: step: 804/526, loss: 0.0006841511349193752
2023-01-24 09:52:54.208409: step: 808/526, loss: 0.0003625400713644922
2023-01-24 09:52:55.305713: step: 812/526, loss: 0.00024903123266994953
2023-01-24 09:52:56.371030: step: 816/526, loss: 0.0005136379622854292
2023-01-24 09:52:57.456925: step: 820/526, loss: 0.0004205251461826265
2023-01-24 09:52:58.541245: step: 824/526, loss: 0.0035737608559429646
2023-01-24 09:52:59.626236: step: 828/526, loss: 0.00017109981854446232
2023-01-24 09:53:00.697055: step: 832/526, loss: 0.001606510835699737
2023-01-24 09:53:01.776030: step: 836/526, loss: 0.00104121258482337
2023-01-24 09:53:02.842248: step: 840/526, loss: 0.016616296023130417
2023-01-24 09:53:03.935394: step: 844/526, loss: 0.004030216485261917
2023-01-24 09:53:05.005893: step: 848/526, loss: 0.00169152463786304
2023-01-24 09:53:06.068888: step: 852/526, loss: 3.169671253999695e-05
2023-01-24 09:53:07.146418: step: 856/526, loss: 0.027636200189590454
2023-01-24 09:53:08.214921: step: 860/526, loss: 0.0014092089841142297
2023-01-24 09:53:09.290993: step: 864/526, loss: 0.001951780985109508
2023-01-24 09:53:10.369458: step: 868/526, loss: 8.349808922503144e-05
2023-01-24 09:53:11.448198: step: 872/526, loss: 0.0006212798180058599
2023-01-24 09:53:12.512161: step: 876/526, loss: 0.0037468839436769485
2023-01-24 09:53:13.608802: step: 880/526, loss: 0.006238115485757589
2023-01-24 09:53:14.674316: step: 884/526, loss: 0.0010426564840599895
2023-01-24 09:53:15.744158: step: 888/526, loss: 0.006967831403017044
2023-01-24 09:53:16.807977: step: 892/526, loss: 0.0062560816295444965
2023-01-24 09:53:17.874465: step: 896/526, loss: 0.0051534236408770084
2023-01-24 09:53:18.957740: step: 900/526, loss: 0.009966417215764523
2023-01-24 09:53:20.022208: step: 904/526, loss: 0.02571197599172592
2023-01-24 09:53:21.107899: step: 908/526, loss: 0.0004537216736935079
2023-01-24 09:53:22.184162: step: 912/526, loss: 0.001871958957053721
2023-01-24 09:53:23.256140: step: 916/526, loss: 0.003109056269749999
2023-01-24 09:53:24.328708: step: 920/526, loss: 0.0003085378557443619
2023-01-24 09:53:25.402687: step: 924/526, loss: 0.014510254375636578
2023-01-24 09:53:26.467458: step: 928/526, loss: 0.00020686320203822106
2023-01-24 09:53:27.543391: step: 932/526, loss: 1.6763797461294416e-08
2023-01-24 09:53:28.625087: step: 936/526, loss: 0.00014371155702974647
2023-01-24 09:53:29.701462: step: 940/526, loss: 0.0007291205110959709
2023-01-24 09:53:30.765307: step: 944/526, loss: 0.006861106026917696
2023-01-24 09:53:31.836091: step: 948/526, loss: 0.0008004697156138718
2023-01-24 09:53:32.899678: step: 952/526, loss: 0.0031208854634314775
2023-01-24 09:53:33.972092: step: 956/526, loss: 0.0013908748514950275
2023-01-24 09:53:35.047689: step: 960/526, loss: 0.00047287711640819907
2023-01-24 09:53:36.124840: step: 964/526, loss: 0.0074398452416062355
2023-01-24 09:53:37.199973: step: 968/526, loss: 0.0003213495365343988
2023-01-24 09:53:38.261325: step: 972/526, loss: 0.003496794728562236
2023-01-24 09:53:39.333956: step: 976/526, loss: 0.0002683876664377749
2023-01-24 09:53:40.408439: step: 980/526, loss: 0.002398095326498151
2023-01-24 09:53:41.489913: step: 984/526, loss: 0.0013283496955409646
2023-01-24 09:53:42.563230: step: 988/526, loss: 0.004707751329988241
2023-01-24 09:53:43.644650: step: 992/526, loss: 0.0007992981700226665
2023-01-24 09:53:44.729970: step: 996/526, loss: 0.004032555967569351
2023-01-24 09:53:45.808034: step: 1000/526, loss: 0.002073394600301981
2023-01-24 09:53:46.891960: step: 1004/526, loss: 0.004528529476374388
2023-01-24 09:53:47.967942: step: 1008/526, loss: 0.001896018162369728
2023-01-24 09:53:49.034899: step: 1012/526, loss: 0.001797710545361042
2023-01-24 09:53:50.101867: step: 1016/526, loss: 0.012676495127379894
2023-01-24 09:53:51.166753: step: 1020/526, loss: 5.2017931011505425e-05
2023-01-24 09:53:52.254350: step: 1024/526, loss: 6.385130109265447e-05
2023-01-24 09:53:53.322259: step: 1028/526, loss: 0.0012638600310310721
2023-01-24 09:53:54.388565: step: 1032/526, loss: 0.0005611968226730824
2023-01-24 09:53:55.460167: step: 1036/526, loss: 0.005554665811359882
2023-01-24 09:53:56.537449: step: 1040/526, loss: 0.00988900475203991
2023-01-24 09:53:57.610596: step: 1044/526, loss: 0.003970308229327202
2023-01-24 09:53:58.667781: step: 1048/526, loss: 0.0005954879452474415
2023-01-24 09:53:59.735833: step: 1052/526, loss: 0.00013599077647086233
2023-01-24 09:54:00.800853: step: 1056/526, loss: 0.0007825624197721481
2023-01-24 09:54:01.866835: step: 1060/526, loss: 0.0034719433169811964
2023-01-24 09:54:02.940708: step: 1064/526, loss: 0.00015020959835965186
2023-01-24 09:54:04.005500: step: 1068/526, loss: 0.0036959724966436625
2023-01-24 09:54:05.066715: step: 1072/526, loss: 0.00019078415061812848
2023-01-24 09:54:06.139809: step: 1076/526, loss: 0.001046059071086347
2023-01-24 09:54:07.208801: step: 1080/526, loss: 0.00045754920574836433
2023-01-24 09:54:08.269800: step: 1084/526, loss: 0.001041437266394496
2023-01-24 09:54:09.334624: step: 1088/526, loss: 0.0008761699427850544
2023-01-24 09:54:10.407747: step: 1092/526, loss: 0.0007837422890588641
2023-01-24 09:54:11.469810: step: 1096/526, loss: 5.401765156420879e-05
2023-01-24 09:54:12.527398: step: 1100/526, loss: 0.00015237083425745368
2023-01-24 09:54:13.597556: step: 1104/526, loss: 0.004630605690181255
2023-01-24 09:54:14.648869: step: 1108/526, loss: 0.0014717730227857828
2023-01-24 09:54:15.695134: step: 1112/526, loss: 8.019447705009952e-05
2023-01-24 09:54:16.755604: step: 1116/526, loss: 0.00020317891903687268
2023-01-24 09:54:17.836504: step: 1120/526, loss: 0.004466088488698006
2023-01-24 09:54:18.919938: step: 1124/526, loss: 0.004833556246012449
2023-01-24 09:54:19.982789: step: 1128/526, loss: 4.4164062273921445e-05
2023-01-24 09:54:21.051172: step: 1132/526, loss: 0.0004955878830514848
2023-01-24 09:54:22.109765: step: 1136/526, loss: 0.0006191849242895842
2023-01-24 09:54:23.178329: step: 1140/526, loss: 0.004287369549274445
2023-01-24 09:54:24.251634: step: 1144/526, loss: 4.887943941866979e-05
2023-01-24 09:54:25.330154: step: 1148/526, loss: 0.00021259553614072502
2023-01-24 09:54:26.382064: step: 1152/526, loss: 0.00047071417793631554
2023-01-24 09:54:27.451753: step: 1156/526, loss: 0.0013863551430404186
2023-01-24 09:54:28.505226: step: 1160/526, loss: 0.0013225360307842493
2023-01-24 09:54:29.571012: step: 1164/526, loss: 0.0018136282451450825
2023-01-24 09:54:30.631996: step: 1168/526, loss: 0.023360004648566246
2023-01-24 09:54:31.697581: step: 1172/526, loss: 0.0027511168736964464
2023-01-24 09:54:32.750265: step: 1176/526, loss: 0.0030257117468863726
2023-01-24 09:54:33.808480: step: 1180/526, loss: 9.190230048261583e-05
2023-01-24 09:54:34.867931: step: 1184/526, loss: 2.0414516654909676e-07
2023-01-24 09:54:35.938828: step: 1188/526, loss: 0.0011328563559800386
2023-01-24 09:54:37.010844: step: 1192/526, loss: 0.005524192471057177
2023-01-24 09:54:38.068376: step: 1196/526, loss: 0.00010769408982014284
2023-01-24 09:54:39.127642: step: 1200/526, loss: 0.0001532303140265867
2023-01-24 09:54:40.183179: step: 1204/526, loss: 0.0004255402891431004
2023-01-24 09:54:41.248624: step: 1208/526, loss: 7.860360346967354e-05
2023-01-24 09:54:42.292827: step: 1212/526, loss: 3.3908506793522974e-06
2023-01-24 09:54:43.360055: step: 1216/526, loss: 1.0914414815488271e-05
2023-01-24 09:54:44.425548: step: 1220/526, loss: 0.001297007780522108
2023-01-24 09:54:45.505950: step: 1224/526, loss: 0.0076791089959442616
2023-01-24 09:54:46.570982: step: 1228/526, loss: 0.0002545668394304812
2023-01-24 09:54:47.630510: step: 1232/526, loss: 0.010161765851080418
2023-01-24 09:54:48.679207: step: 1236/526, loss: 0.0006302600377239287
2023-01-24 09:54:49.750722: step: 1240/526, loss: 0.0034730457700788975
2023-01-24 09:54:50.814642: step: 1244/526, loss: 0.0014930617762729526
2023-01-24 09:54:51.876550: step: 1248/526, loss: 0.006188447121530771
2023-01-24 09:54:52.936433: step: 1252/526, loss: 0.004832875449210405
2023-01-24 09:54:54.001967: step: 1256/526, loss: 0.0005920781404711306
2023-01-24 09:54:55.087236: step: 1260/526, loss: 0.000316679390380159
2023-01-24 09:54:56.157059: step: 1264/526, loss: 0.00042659611790440977
2023-01-24 09:54:57.230237: step: 1268/526, loss: 0.0013608381850644946
2023-01-24 09:54:58.291911: step: 1272/526, loss: 0.000839449290651828
2023-01-24 09:54:59.349389: step: 1276/526, loss: 0.0024914476089179516
2023-01-24 09:55:00.402742: step: 1280/526, loss: 4.108694156457204e-06
2023-01-24 09:55:01.466719: step: 1284/526, loss: 9.43108261708403e-07
2023-01-24 09:55:02.539265: step: 1288/526, loss: 0.014416714198887348
2023-01-24 09:55:03.595173: step: 1292/526, loss: 0.0003294550988357514
2023-01-24 09:55:04.678158: step: 1296/526, loss: 0.0025182405952364206
2023-01-24 09:55:05.730737: step: 1300/526, loss: 0.0005686861695721745
2023-01-24 09:55:06.794177: step: 1304/526, loss: 3.637062764028087e-05
2023-01-24 09:55:07.861707: step: 1308/526, loss: 0.0015812882920727134
2023-01-24 09:55:08.916440: step: 1312/526, loss: 0.00033929257187992334
2023-01-24 09:55:09.982437: step: 1316/526, loss: 0.004336930811405182
2023-01-24 09:55:11.038713: step: 1320/526, loss: 0.005707069765776396
2023-01-24 09:55:12.103384: step: 1324/526, loss: 0.0019213082268834114
2023-01-24 09:55:13.160617: step: 1328/526, loss: 0.0014584719901904464
2023-01-24 09:55:14.224194: step: 1332/526, loss: 8.348702249350026e-05
2023-01-24 09:55:15.288082: step: 1336/526, loss: 0.0004102880193386227
2023-01-24 09:55:16.353978: step: 1340/526, loss: 0.00021070781804155558
2023-01-24 09:55:17.427989: step: 1344/526, loss: 0.002992538968101144
2023-01-24 09:55:18.485771: step: 1348/526, loss: 0.00023836577020119876
2023-01-24 09:55:19.545883: step: 1352/526, loss: 0.006522088311612606
2023-01-24 09:55:20.606442: step: 1356/526, loss: 0.00012933120888192207
2023-01-24 09:55:21.651331: step: 1360/526, loss: 0.0007604683632962406
2023-01-24 09:55:22.707619: step: 1364/526, loss: 0.0026534099597483873
2023-01-24 09:55:23.766015: step: 1368/526, loss: 0.00029512442415580153
2023-01-24 09:55:24.820771: step: 1372/526, loss: 0.004442297853529453
2023-01-24 09:55:25.884392: step: 1376/526, loss: 0.0023686098866164684
2023-01-24 09:55:26.954157: step: 1380/526, loss: 0.0020333111751824617
2023-01-24 09:55:28.009277: step: 1384/526, loss: 0.0017943915445357561
2023-01-24 09:55:29.067109: step: 1388/526, loss: 0.0005311199347488582
2023-01-24 09:55:30.128293: step: 1392/526, loss: 0.001915119239129126
2023-01-24 09:55:31.200878: step: 1396/526, loss: 0.000977266812697053
2023-01-24 09:55:32.272186: step: 1400/526, loss: 0.011393888853490353
2023-01-24 09:55:33.322348: step: 1404/526, loss: 0.0007187350420281291
2023-01-24 09:55:34.389741: step: 1408/526, loss: 0.007377948146313429
2023-01-24 09:55:35.447576: step: 1412/526, loss: 0.001826529041863978
2023-01-24 09:55:36.501077: step: 1416/526, loss: 9.130862054007594e-06
2023-01-24 09:55:37.556341: step: 1420/526, loss: 7.097920752130449e-05
2023-01-24 09:55:38.620970: step: 1424/526, loss: 0.0007022854988463223
2023-01-24 09:55:39.693052: step: 1428/526, loss: 1.1935015209019184e-05
2023-01-24 09:55:40.751964: step: 1432/526, loss: 0.0018706510309129953
2023-01-24 09:55:41.833587: step: 1436/526, loss: 0.0015774505445733666
2023-01-24 09:55:42.902693: step: 1440/526, loss: 0.005842737387865782
2023-01-24 09:55:43.955498: step: 1444/526, loss: 0.0018355679931119084
2023-01-24 09:55:45.010659: step: 1448/526, loss: 0.0037214672192931175
2023-01-24 09:55:46.063781: step: 1452/526, loss: 0.005495049990713596
2023-01-24 09:55:47.121066: step: 1456/526, loss: 3.282867692178115e-05
2023-01-24 09:55:48.177569: step: 1460/526, loss: 0.00829373113811016
2023-01-24 09:55:49.256035: step: 1464/526, loss: 0.0008721364429220557
2023-01-24 09:55:50.322163: step: 1468/526, loss: 0.002679194789379835
2023-01-24 09:55:51.381713: step: 1472/526, loss: 0.0013993995962664485
2023-01-24 09:55:52.448734: step: 1476/526, loss: 0.0017318251775577664
2023-01-24 09:55:53.508734: step: 1480/526, loss: 0.0020512931514531374
2023-01-24 09:55:54.574726: step: 1484/526, loss: 0.0028425874188542366
2023-01-24 09:55:55.628274: step: 1488/526, loss: 0.001211543451063335
2023-01-24 09:55:56.691696: step: 1492/526, loss: 0.00012597184104379267
2023-01-24 09:55:57.751024: step: 1496/526, loss: 0.00021376338554546237
2023-01-24 09:55:58.799384: step: 1500/526, loss: 5.690865691576619e-06
2023-01-24 09:55:59.881346: step: 1504/526, loss: 0.009615123271942139
2023-01-24 09:56:00.949462: step: 1508/526, loss: 0.001319476985372603
2023-01-24 09:56:02.017786: step: 1512/526, loss: 0.00040984631050378084
2023-01-24 09:56:03.076869: step: 1516/526, loss: 0.001269143307581544
2023-01-24 09:56:04.152919: step: 1520/526, loss: 0.0027608280070126057
2023-01-24 09:56:05.207937: step: 1524/526, loss: 0.00368399266153574
2023-01-24 09:56:06.260760: step: 1528/526, loss: 0.003042002907022834
2023-01-24 09:56:07.341972: step: 1532/526, loss: 0.0037112620193511248
2023-01-24 09:56:08.400066: step: 1536/526, loss: 0.0006520982133224607
2023-01-24 09:56:09.450421: step: 1540/526, loss: 0.0001832563430070877
2023-01-24 09:56:10.511320: step: 1544/526, loss: 0.0007733324309810996
2023-01-24 09:56:11.581559: step: 1548/526, loss: 0.002382730133831501
2023-01-24 09:56:12.655242: step: 1552/526, loss: 0.0029309310484677553
2023-01-24 09:56:13.718293: step: 1556/526, loss: 0.00018036349501926452
2023-01-24 09:56:14.775056: step: 1560/526, loss: 0.007770819123834372
2023-01-24 09:56:15.852748: step: 1564/526, loss: 0.00019999477081000805
2023-01-24 09:56:16.910677: step: 1568/526, loss: 0.005768663249909878
2023-01-24 09:56:17.964254: step: 1572/526, loss: 0.0002435079513816163
2023-01-24 09:56:19.027135: step: 1576/526, loss: 0.0025663760025054216
2023-01-24 09:56:20.084045: step: 1580/526, loss: 0.004356759134680033
2023-01-24 09:56:21.142745: step: 1584/526, loss: 0.0036898008547723293
2023-01-24 09:56:22.208052: step: 1588/526, loss: 0.011443507857620716
2023-01-24 09:56:23.257206: step: 1592/526, loss: 0.000976758892647922
2023-01-24 09:56:24.325862: step: 1596/526, loss: 0.002183235716074705
2023-01-24 09:56:25.370843: step: 1600/526, loss: 0.00021467276383191347
2023-01-24 09:56:26.434478: step: 1604/526, loss: 0.0006088180234655738
2023-01-24 09:56:27.482149: step: 1608/526, loss: 0.0012263018870726228
2023-01-24 09:56:28.533956: step: 1612/526, loss: 0.0009391807834617794
2023-01-24 09:56:29.592227: step: 1616/526, loss: 0.01722201704978943
2023-01-24 09:56:30.651866: step: 1620/526, loss: 0.0006972018163651228
2023-01-24 09:56:31.708790: step: 1624/526, loss: 0.0
2023-01-24 09:56:32.766560: step: 1628/526, loss: 2.719453107147274e-08
2023-01-24 09:56:33.833188: step: 1632/526, loss: 0.003350720275193453
2023-01-24 09:56:34.895999: step: 1636/526, loss: 0.012177029624581337
2023-01-24 09:56:35.964951: step: 1640/526, loss: 0.002311804797500372
2023-01-24 09:56:37.027997: step: 1644/526, loss: 3.591082349885255e-05
2023-01-24 09:56:38.088984: step: 1648/526, loss: 0.011936341412365437
2023-01-24 09:56:39.147229: step: 1652/526, loss: 0.0007209527539089322
2023-01-24 09:56:40.205256: step: 1656/526, loss: 0.002192405052483082
2023-01-24 09:56:41.272927: step: 1660/526, loss: 0.00033770635491237044
2023-01-24 09:56:42.319984: step: 1664/526, loss: 0.0022931727580726147
2023-01-24 09:56:43.399270: step: 1668/526, loss: 0.000733984517864883
2023-01-24 09:56:44.456284: step: 1672/526, loss: 0.0008263453491963446
2023-01-24 09:56:45.527636: step: 1676/526, loss: 0.001402566907927394
2023-01-24 09:56:46.602119: step: 1680/526, loss: 0.007053116336464882
2023-01-24 09:56:47.693968: step: 1684/526, loss: 0.005855896044522524
2023-01-24 09:56:48.769182: step: 1688/526, loss: 0.005505474284291267
2023-01-24 09:56:49.835258: step: 1692/526, loss: 0.0013290958013385534
2023-01-24 09:56:50.916140: step: 1696/526, loss: 0.0039756507612764835
2023-01-24 09:56:51.983031: step: 1700/526, loss: 0.0
2023-01-24 09:56:53.028396: step: 1704/526, loss: 0.002265496412292123
2023-01-24 09:56:54.096291: step: 1708/526, loss: 0.001697678118944168
2023-01-24 09:56:55.182127: step: 1712/526, loss: 0.0003724343259818852
2023-01-24 09:56:56.245687: step: 1716/526, loss: 0.00453084846958518
2023-01-24 09:56:57.297620: step: 1720/526, loss: 3.149261374346679e-06
2023-01-24 09:56:58.346522: step: 1724/526, loss: 0.0005596246337518096
2023-01-24 09:56:59.416448: step: 1728/526, loss: 0.002456620568409562
2023-01-24 09:57:00.489946: step: 1732/526, loss: 0.001171683892607689
2023-01-24 09:57:01.572478: step: 1736/526, loss: 0.006751475390046835
2023-01-24 09:57:02.639050: step: 1740/526, loss: 0.007621586322784424
2023-01-24 09:57:03.699244: step: 1744/526, loss: 0.0016836391296237707
2023-01-24 09:57:04.761442: step: 1748/526, loss: 0.0012501185992732644
2023-01-24 09:57:05.821577: step: 1752/526, loss: 0.00405002711340785
2023-01-24 09:57:06.900867: step: 1756/526, loss: 0.010960236191749573
2023-01-24 09:57:07.985056: step: 1760/526, loss: 0.0007426299271173775
2023-01-24 09:57:09.051940: step: 1764/526, loss: 0.0017698564333841205
2023-01-24 09:57:10.122692: step: 1768/526, loss: 0.0021087094210088253
2023-01-24 09:57:11.175870: step: 1772/526, loss: 0.0014048486482352018
2023-01-24 09:57:12.249546: step: 1776/526, loss: 0.0007239112164825201
2023-01-24 09:57:13.323157: step: 1780/526, loss: 0.004561044741421938
2023-01-24 09:57:14.394526: step: 1784/526, loss: 0.0002426331047900021
2023-01-24 09:57:15.480772: step: 1788/526, loss: 0.00249788467772305
2023-01-24 09:57:16.546019: step: 1792/526, loss: 0.0013936988543719053
2023-01-24 09:57:17.617045: step: 1796/526, loss: 0.004205132834613323
2023-01-24 09:57:18.689445: step: 1800/526, loss: 0.003447645576670766
2023-01-24 09:57:19.750969: step: 1804/526, loss: 0.04244941845536232
2023-01-24 09:57:20.807257: step: 1808/526, loss: 0.0004102271341253072
2023-01-24 09:57:21.870542: step: 1812/526, loss: 0.001691601937636733
2023-01-24 09:57:22.948658: step: 1816/526, loss: 0.0008515746449120343
2023-01-24 09:57:24.010998: step: 1820/526, loss: 0.0035659619607031345
2023-01-24 09:57:25.077488: step: 1824/526, loss: 0.0009378705872222781
2023-01-24 09:57:26.138988: step: 1828/526, loss: 0.002529499586671591
2023-01-24 09:57:27.199207: step: 1832/526, loss: 0.00209238869138062
2023-01-24 09:57:28.256163: step: 1836/526, loss: 0.0014279825845733285
2023-01-24 09:57:29.338017: step: 1840/526, loss: 0.0037378163542598486
2023-01-24 09:57:30.400585: step: 1844/526, loss: 0.004979941062629223
2023-01-24 09:57:31.459007: step: 1848/526, loss: 0.012022201903164387
2023-01-24 09:57:32.534909: step: 1852/526, loss: 0.01618291810154915
2023-01-24 09:57:33.604925: step: 1856/526, loss: 0.0029926386196166277
2023-01-24 09:57:34.662697: step: 1860/526, loss: 0.00028098246548324823
2023-01-24 09:57:35.725771: step: 1864/526, loss: 0.0013977146008983254
2023-01-24 09:57:36.814282: step: 1868/526, loss: 0.0006358748651109636
2023-01-24 09:57:37.882903: step: 1872/526, loss: 0.00019496819004416466
2023-01-24 09:57:38.914534: step: 1876/526, loss: 0.0006264228140935302
2023-01-24 09:57:39.984843: step: 1880/526, loss: 0.0015917223645374179
2023-01-24 09:57:41.044204: step: 1884/526, loss: 0.005444049835205078
2023-01-24 09:57:42.119161: step: 1888/526, loss: 0.000791533850133419
2023-01-24 09:57:43.200453: step: 1892/526, loss: 0.004104716703295708
2023-01-24 09:57:44.257243: step: 1896/526, loss: 0.0005158140556886792
2023-01-24 09:57:45.313603: step: 1900/526, loss: 0.0015277708880603313
2023-01-24 09:57:46.367627: step: 1904/526, loss: 0.005023960955440998
2023-01-24 09:57:47.420354: step: 1908/526, loss: 0.016057617962360382
2023-01-24 09:57:48.484693: step: 1912/526, loss: 0.0055084978230297565
2023-01-24 09:57:49.530102: step: 1916/526, loss: 2.6908952349913307e-05
2023-01-24 09:57:50.605234: step: 1920/526, loss: 0.00023559413966722786
2023-01-24 09:57:51.675692: step: 1924/526, loss: 0.002671909285709262
2023-01-24 09:57:52.749286: step: 1928/526, loss: 0.0022257629316300154
2023-01-24 09:57:53.814442: step: 1932/526, loss: 0.004569669719785452
2023-01-24 09:57:54.879712: step: 1936/526, loss: 0.0007130609592422843
2023-01-24 09:57:55.955502: step: 1940/526, loss: 0.0005388118443079293
2023-01-24 09:57:57.040240: step: 1944/526, loss: 8.003956281754654e-06
2023-01-24 09:57:58.116804: step: 1948/526, loss: 0.000334419310092926
2023-01-24 09:57:59.180389: step: 1952/526, loss: 0.0001431743148714304
2023-01-24 09:58:00.246786: step: 1956/526, loss: 5.982616130495444e-05
2023-01-24 09:58:01.299400: step: 1960/526, loss: 1.8170852854382247e-05
2023-01-24 09:58:02.373591: step: 1964/526, loss: 0.00025206009740941226
2023-01-24 09:58:03.432995: step: 1968/526, loss: 3.678839129861444e-05
2023-01-24 09:58:04.487504: step: 1972/526, loss: 0.0007890138658694923
2023-01-24 09:58:05.550755: step: 1976/526, loss: 0.00011741852358682081
2023-01-24 09:58:06.622361: step: 1980/526, loss: 0.002405744045972824
2023-01-24 09:58:07.700481: step: 1984/526, loss: 0.01120900921523571
2023-01-24 09:58:08.759376: step: 1988/526, loss: 0.006500423885881901
2023-01-24 09:58:09.807125: step: 1992/526, loss: 0.00035128547460772097
2023-01-24 09:58:10.903515: step: 1996/526, loss: 2.3441616576747037e-05
2023-01-24 09:58:11.969429: step: 2000/526, loss: 0.004306937102228403
2023-01-24 09:58:13.051992: step: 2004/526, loss: 0.0032469145953655243
2023-01-24 09:58:14.118995: step: 2008/526, loss: 0.0008283528732135892
2023-01-24 09:58:15.186696: step: 2012/526, loss: 0.001748239970766008
2023-01-24 09:58:16.248597: step: 2016/526, loss: 0.00016227687592618167
2023-01-24 09:58:17.315985: step: 2020/526, loss: 0.000812965095974505
2023-01-24 09:58:18.383845: step: 2024/526, loss: 8.890100434655324e-05
2023-01-24 09:58:19.453210: step: 2028/526, loss: 0.008077074773609638
2023-01-24 09:58:20.524843: step: 2032/526, loss: 0.0025476557202637196
2023-01-24 09:58:21.596158: step: 2036/526, loss: 0.005910987034440041
2023-01-24 09:58:22.667055: step: 2040/526, loss: 0.0006522894254885614
2023-01-24 09:58:23.733165: step: 2044/526, loss: 0.00014745125372428447
2023-01-24 09:58:24.802686: step: 2048/526, loss: 0.006271205842494965
2023-01-24 09:58:25.888803: step: 2052/526, loss: 0.006025245878845453
2023-01-24 09:58:26.950917: step: 2056/526, loss: 4.4928023271495476e-05
2023-01-24 09:58:28.019829: step: 2060/526, loss: 0.00013033021241426468
2023-01-24 09:58:29.080595: step: 2064/526, loss: 0.004828251898288727
2023-01-24 09:58:30.140416: step: 2068/526, loss: 0.0005814018659293652
2023-01-24 09:58:31.222375: step: 2072/526, loss: 0.004634057637304068
2023-01-24 09:58:32.292766: step: 2076/526, loss: 0.007452423218637705
2023-01-24 09:58:33.354657: step: 2080/526, loss: 0.0005268630338832736
2023-01-24 09:58:34.414393: step: 2084/526, loss: 0.007408125326037407
2023-01-24 09:58:35.480458: step: 2088/526, loss: 0.00011818054917966947
2023-01-24 09:58:36.545996: step: 2092/526, loss: 0.004184565506875515
2023-01-24 09:58:37.620667: step: 2096/526, loss: 0.0006894851103425026
2023-01-24 09:58:38.691173: step: 2100/526, loss: 5.0117723731091246e-05
2023-01-24 09:58:39.763355: step: 2104/526, loss: 2.5599050786695443e-05
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37101039783001805, 'r': 0.278081797235023, 'f1': 0.3178939417415556}, 'combined': 0.23423764128325147, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3613267195767196, 'r': 0.223143216572997, 'f1': 0.27589992727860374}, 'combined': 0.15049086942469295, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3364336400499064, 'r': 0.29238445378151257, 'f1': 0.3128662073966642}, 'combined': 0.23053299492385781, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36343883120276255, 'r': 0.26202177400528537, 'f1': 0.30450802656860915}, 'combined': 0.16609528721924133, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36716776294260095, 'r': 0.3225781294922661, 'f1': 0.3434316651362106}, 'combined': 0.2530549111529973, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3665647032271614, 'r': 0.2773549950309812, 'f1': 0.3157802183008984}, 'combined': 0.17224375543685366, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4625, 'r': 0.40217391304347827, 'f1': 0.43023255813953487}, 'combined': 0.21511627906976744, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668282730782731, 'r': 0.2833000135538086, 'f1': 0.31969830223309886}, 'combined': 0.2355671700664939, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36005256762468296, 'r': 0.22268576003136845, 'f1': 0.27517867237341515}, 'combined': 0.15009745765822644, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42528735632183906, 'r': 0.35238095238095235, 'f1': 0.3854166666666667}, 'combined': 0.2569444444444444, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3413463038053649, 'r': 0.2966539034968826, 'f1': 0.31743473531544597}, 'combined': 0.2338992786534865, 'stategy': 1, 'epoch': 18}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3571390200599459, 'r': 0.2604206761095854, 'f1': 0.30120613649500194}, 'combined': 0.16429425627000105, 'stategy': 1, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.47619047619047616, 'r': 0.43478260869565216, 'f1': 0.4545454545454545}, 'combined': 0.22727272727272724, 'stategy': 1, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36796249836022565, 'r': 0.3225781294922661, 'f1': 0.3437789165670865}, 'combined': 0.2533107806283795, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.36542562142544205, 'r': 0.2741527992395814, 'f1': 0.3132765390160612}, 'combined': 0.1708781121905788, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 3}