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 05:06:41.042128: step: 4/529, loss: 0.07990811765193939
2023-01-24 05:06:42.076179: step: 8/529, loss: 0.014827210456132889
2023-01-24 05:06:43.110518: step: 12/529, loss: 0.020841358229517937
2023-01-24 05:06:44.154364: step: 16/529, loss: 0.027017703279852867
2023-01-24 05:06:45.200021: step: 20/529, loss: 0.05911005660891533
2023-01-24 05:06:46.240644: step: 24/529, loss: 0.016413463279604912
2023-01-24 05:06:47.294288: step: 28/529, loss: 0.06190330535173416
2023-01-24 05:06:48.339386: step: 32/529, loss: 0.10229873657226562
2023-01-24 05:06:49.364036: step: 36/529, loss: 0.02176942303776741
2023-01-24 05:06:50.407129: step: 40/529, loss: 0.01597859524190426
2023-01-24 05:06:51.443101: step: 44/529, loss: 0.019977517426013947
2023-01-24 05:06:52.485325: step: 48/529, loss: 0.012980473227798939
2023-01-24 05:06:53.527169: step: 52/529, loss: 0.03213465213775635
2023-01-24 05:06:54.567824: step: 56/529, loss: 0.0116121219471097
2023-01-24 05:06:55.617018: step: 60/529, loss: 0.03135773912072182
2023-01-24 05:06:56.674441: step: 64/529, loss: 0.09360960125923157
2023-01-24 05:06:57.727706: step: 68/529, loss: 0.0260729119181633
2023-01-24 05:06:58.795599: step: 72/529, loss: 0.04594697430729866
2023-01-24 05:06:59.837760: step: 76/529, loss: 0.02163085900247097
2023-01-24 05:07:00.886732: step: 80/529, loss: 0.028550773859024048
2023-01-24 05:07:01.926421: step: 84/529, loss: 0.07296416163444519
2023-01-24 05:07:02.966786: step: 88/529, loss: 0.05942222476005554
2023-01-24 05:07:04.010460: step: 92/529, loss: 0.015289267525076866
2023-01-24 05:07:05.061171: step: 96/529, loss: 0.019732104614377022
2023-01-24 05:07:06.128511: step: 100/529, loss: 0.045478615909814835
2023-01-24 05:07:07.184321: step: 104/529, loss: 0.0859794020652771
2023-01-24 05:07:08.215955: step: 108/529, loss: 0.02028040401637554
2023-01-24 05:07:09.261320: step: 112/529, loss: 0.09041469544172287
2023-01-24 05:07:10.295305: step: 116/529, loss: 0.1333049088716507
2023-01-24 05:07:11.347145: step: 120/529, loss: 0.010391704738140106
2023-01-24 05:07:12.382772: step: 124/529, loss: 0.008062057197093964
2023-01-24 05:07:13.446479: step: 128/529, loss: 0.06313350796699524
2023-01-24 05:07:14.493422: step: 132/529, loss: 0.062153410166502
2023-01-24 05:07:15.542827: step: 136/529, loss: 0.04618854820728302
2023-01-24 05:07:16.603602: step: 140/529, loss: 0.02758634462952614
2023-01-24 05:07:17.654899: step: 144/529, loss: 0.032050687819719315
2023-01-24 05:07:18.700444: step: 148/529, loss: 0.01767510175704956
2023-01-24 05:07:19.773782: step: 152/529, loss: 0.020812753587961197
2023-01-24 05:07:20.816972: step: 156/529, loss: 0.11757136881351471
2023-01-24 05:07:21.857021: step: 160/529, loss: 0.057380955666303635
2023-01-24 05:07:22.913562: step: 164/529, loss: 0.09593145549297333
2023-01-24 05:07:24.006952: step: 168/529, loss: 0.055508315563201904
2023-01-24 05:07:25.068218: step: 172/529, loss: 0.023263294249773026
2023-01-24 05:07:26.121735: step: 176/529, loss: 0.017478350549936295
2023-01-24 05:07:27.169832: step: 180/529, loss: 0.023210899904370308
2023-01-24 05:07:28.219567: step: 184/529, loss: 0.013754370622336864
2023-01-24 05:07:29.273977: step: 188/529, loss: 0.015873238444328308
2023-01-24 05:07:30.318412: step: 192/529, loss: 0.01860697753727436
2023-01-24 05:07:31.380823: step: 196/529, loss: 0.04310062900185585
2023-01-24 05:07:32.415921: step: 200/529, loss: 0.014168181456625462
2023-01-24 05:07:33.461720: step: 204/529, loss: 0.00864088162779808
2023-01-24 05:07:34.510672: step: 208/529, loss: 0.044519148766994476
2023-01-24 05:07:35.559021: step: 212/529, loss: 0.017318738624453545
2023-01-24 05:07:36.603275: step: 216/529, loss: 0.03859895467758179
2023-01-24 05:07:37.658927: step: 220/529, loss: 0.018590757623314857
2023-01-24 05:07:38.717365: step: 224/529, loss: 0.016344435513019562
2023-01-24 05:07:39.757278: step: 228/529, loss: 0.02652830071747303
2023-01-24 05:07:40.800092: step: 232/529, loss: 0.06508877873420715
2023-01-24 05:07:41.851604: step: 236/529, loss: 0.024108638986945152
2023-01-24 05:07:42.897825: step: 240/529, loss: 0.02974044904112816
2023-01-24 05:07:43.942409: step: 244/529, loss: 0.009025337174534798
2023-01-24 05:07:44.984344: step: 248/529, loss: 0.03340541943907738
2023-01-24 05:07:46.029592: step: 252/529, loss: 0.04070824384689331
2023-01-24 05:07:47.102841: step: 256/529, loss: 0.010483766905963421
2023-01-24 05:07:48.146875: step: 260/529, loss: 0.03871284797787666
2023-01-24 05:07:49.195128: step: 264/529, loss: 0.036469489336013794
2023-01-24 05:07:50.261571: step: 268/529, loss: 0.07533961534500122
2023-01-24 05:07:51.298122: step: 272/529, loss: 0.017238104715943336
2023-01-24 05:07:52.340734: step: 276/529, loss: 0.048346228897571564
2023-01-24 05:07:53.399763: step: 280/529, loss: 0.009969507344067097
2023-01-24 05:07:54.460015: step: 284/529, loss: 0.0049746073782444
2023-01-24 05:07:55.515161: step: 288/529, loss: 0.011463984847068787
2023-01-24 05:07:56.556137: step: 292/529, loss: 0.012212565168738365
2023-01-24 05:07:57.616237: step: 296/529, loss: 0.07199540734291077
2023-01-24 05:07:58.670465: step: 300/529, loss: 0.0088880630210042
2023-01-24 05:07:59.718051: step: 304/529, loss: 0.012977623380720615
2023-01-24 05:08:00.760534: step: 308/529, loss: 0.0069293733686208725
2023-01-24 05:08:01.821230: step: 312/529, loss: 0.014588208869099617
2023-01-24 05:08:02.872752: step: 316/529, loss: 0.048842888325452805
2023-01-24 05:08:03.920439: step: 320/529, loss: 0.06106474623084068
2023-01-24 05:08:04.968481: step: 324/529, loss: 0.022975649684667587
2023-01-24 05:08:06.025756: step: 328/529, loss: 0.07811424881219864
2023-01-24 05:08:07.081247: step: 332/529, loss: 0.037955913692712784
2023-01-24 05:08:08.140147: step: 336/529, loss: 0.015377218835055828
2023-01-24 05:08:09.186008: step: 340/529, loss: 0.05786743387579918
2023-01-24 05:08:10.231499: step: 344/529, loss: 0.01873079501092434
2023-01-24 05:08:11.287301: step: 348/529, loss: 0.022346196696162224
2023-01-24 05:08:12.339495: step: 352/529, loss: 0.014364014379680157
2023-01-24 05:08:13.385957: step: 356/529, loss: 0.012166554108262062
2023-01-24 05:08:14.444946: step: 360/529, loss: 0.020425790920853615
2023-01-24 05:08:15.500852: step: 364/529, loss: 0.01742572896182537
2023-01-24 05:08:16.541913: step: 368/529, loss: 0.057203106582164764
2023-01-24 05:08:17.617341: step: 372/529, loss: 0.005404599942266941
2023-01-24 05:08:18.678243: step: 376/529, loss: 0.024079270660877228
2023-01-24 05:08:19.738223: step: 380/529, loss: 0.017385238781571388
2023-01-24 05:08:20.797765: step: 384/529, loss: 0.04751858115196228
2023-01-24 05:08:21.833578: step: 388/529, loss: 0.009507374837994576
2023-01-24 05:08:22.890604: step: 392/529, loss: 0.022454271093010902
2023-01-24 05:08:23.951509: step: 396/529, loss: 0.056297417730093
2023-01-24 05:08:25.007693: step: 400/529, loss: 0.012025311589241028
2023-01-24 05:08:26.058222: step: 404/529, loss: 0.016522690653800964
2023-01-24 05:08:27.132699: step: 408/529, loss: 0.020530816167593002
2023-01-24 05:08:28.180001: step: 412/529, loss: 0.016060838475823402
2023-01-24 05:08:29.235227: step: 416/529, loss: 0.02488415688276291
2023-01-24 05:08:30.289760: step: 420/529, loss: 0.020370163023471832
2023-01-24 05:08:31.343995: step: 424/529, loss: 0.019878340885043144
2023-01-24 05:08:32.395569: step: 428/529, loss: 0.004518384579569101
2023-01-24 05:08:33.458726: step: 432/529, loss: 0.03485770523548126
2023-01-24 05:08:34.507624: step: 436/529, loss: 0.01472142618149519
2023-01-24 05:08:35.569321: step: 440/529, loss: 0.035705842077732086
2023-01-24 05:08:36.624636: step: 444/529, loss: 0.011892641894519329
2023-01-24 05:08:37.685708: step: 448/529, loss: 0.05103680491447449
2023-01-24 05:08:38.738660: step: 452/529, loss: 0.012885753996670246
2023-01-24 05:08:39.790060: step: 456/529, loss: 0.008832535706460476
2023-01-24 05:08:40.845612: step: 460/529, loss: 0.010149504989385605
2023-01-24 05:08:41.896492: step: 464/529, loss: 0.014036014676094055
2023-01-24 05:08:42.939019: step: 468/529, loss: 0.043695222586393356
2023-01-24 05:08:44.012661: step: 472/529, loss: 0.013185055926442146
2023-01-24 05:08:45.061123: step: 476/529, loss: 0.04924473166465759
2023-01-24 05:08:46.109459: step: 480/529, loss: 0.012842758558690548
2023-01-24 05:08:47.154598: step: 484/529, loss: 0.01636068895459175
2023-01-24 05:08:48.214590: step: 488/529, loss: 0.011149060912430286
2023-01-24 05:08:49.288087: step: 492/529, loss: 0.040947914123535156
2023-01-24 05:08:50.342239: step: 496/529, loss: 0.015999894589185715
2023-01-24 05:08:51.392526: step: 500/529, loss: 0.008272661827504635
2023-01-24 05:08:52.442354: step: 504/529, loss: 0.016934100538492203
2023-01-24 05:08:53.499667: step: 508/529, loss: 0.010307268239557743
2023-01-24 05:08:54.560111: step: 512/529, loss: 0.0783538892865181
2023-01-24 05:08:55.602202: step: 516/529, loss: 0.008236422203481197
2023-01-24 05:08:56.660372: step: 520/529, loss: 0.012457845732569695
2023-01-24 05:08:57.731965: step: 524/529, loss: 0.009356766939163208
2023-01-24 05:08:58.775909: step: 528/529, loss: 0.002937601413577795
2023-01-24 05:08:59.852809: step: 532/529, loss: 0.008586671203374863
2023-01-24 05:09:00.899008: step: 536/529, loss: 0.04243906959891319
2023-01-24 05:09:01.950491: step: 540/529, loss: 0.008048910647630692
2023-01-24 05:09:03.006876: step: 544/529, loss: 0.062262147665023804
2023-01-24 05:09:04.067220: step: 548/529, loss: 0.028016511350870132
2023-01-24 05:09:05.114898: step: 552/529, loss: 0.012315897271037102
2023-01-24 05:09:06.170757: step: 556/529, loss: 0.01563815400004387
2023-01-24 05:09:07.229956: step: 560/529, loss: 0.030016034841537476
2023-01-24 05:09:08.275928: step: 564/529, loss: 0.04939638078212738
2023-01-24 05:09:09.320914: step: 568/529, loss: 0.005209965165704489
2023-01-24 05:09:10.376431: step: 572/529, loss: 0.00775504857301712
2023-01-24 05:09:11.423927: step: 576/529, loss: 0.010861270129680634
2023-01-24 05:09:12.480365: step: 580/529, loss: 0.020030926913022995
2023-01-24 05:09:13.542162: step: 584/529, loss: 0.020260784775018692
2023-01-24 05:09:14.588805: step: 588/529, loss: 0.008802361786365509
2023-01-24 05:09:15.631990: step: 592/529, loss: 0.008022286929190159
2023-01-24 05:09:16.689268: step: 596/529, loss: 0.004244903568178415
2023-01-24 05:09:17.739659: step: 600/529, loss: 0.007763395085930824
2023-01-24 05:09:18.782239: step: 604/529, loss: 0.08844374120235443
2023-01-24 05:09:19.830253: step: 608/529, loss: 0.01280874665826559
2023-01-24 05:09:20.872796: step: 612/529, loss: 0.03086327202618122
2023-01-24 05:09:21.913910: step: 616/529, loss: 0.012198288924992085
2023-01-24 05:09:22.967244: step: 620/529, loss: 0.01792272739112377
2023-01-24 05:09:24.025891: step: 624/529, loss: 0.006117998156696558
2023-01-24 05:09:25.080259: step: 628/529, loss: 0.01971031166613102
2023-01-24 05:09:26.135582: step: 632/529, loss: 0.031505003571510315
2023-01-24 05:09:27.187143: step: 636/529, loss: 0.02580244466662407
2023-01-24 05:09:28.240775: step: 640/529, loss: 0.022704098373651505
2023-01-24 05:09:29.314180: step: 644/529, loss: 0.039758216589689255
2023-01-24 05:09:30.356530: step: 648/529, loss: 0.015006549656391144
2023-01-24 05:09:31.393086: step: 652/529, loss: 0.007417464628815651
2023-01-24 05:09:32.432616: step: 656/529, loss: 0.025882484391331673
2023-01-24 05:09:33.464676: step: 660/529, loss: 0.012646481394767761
2023-01-24 05:09:34.515516: step: 664/529, loss: 0.02698586694896221
2023-01-24 05:09:35.563350: step: 668/529, loss: 0.008092718198895454
2023-01-24 05:09:36.618320: step: 672/529, loss: 0.006220159586519003
2023-01-24 05:09:37.663070: step: 676/529, loss: 0.04047471284866333
2023-01-24 05:09:38.699980: step: 680/529, loss: 0.03407733514904976
2023-01-24 05:09:39.745280: step: 684/529, loss: 0.010705075226724148
2023-01-24 05:09:40.780771: step: 688/529, loss: 0.013215168379247189
2023-01-24 05:09:41.815133: step: 692/529, loss: 0.011659905314445496
2023-01-24 05:09:42.878151: step: 696/529, loss: 0.010189338587224483
2023-01-24 05:09:43.933994: step: 700/529, loss: 0.008281991817057133
2023-01-24 05:09:45.003203: step: 704/529, loss: 0.04534679278731346
2023-01-24 05:09:46.048971: step: 708/529, loss: 0.002377257449552417
2023-01-24 05:09:47.091063: step: 712/529, loss: 0.012265834026038647
2023-01-24 05:09:48.126945: step: 716/529, loss: 0.014682501554489136
2023-01-24 05:09:49.177228: step: 720/529, loss: 0.00967047642916441
2023-01-24 05:09:50.215716: step: 724/529, loss: 0.04534053057432175
2023-01-24 05:09:51.269454: step: 728/529, loss: 0.009595212526619434
2023-01-24 05:09:52.320471: step: 732/529, loss: 0.016976941376924515
2023-01-24 05:09:53.376170: step: 736/529, loss: 0.03377556800842285
2023-01-24 05:09:54.429992: step: 740/529, loss: 0.021184319630265236
2023-01-24 05:09:55.475016: step: 744/529, loss: 0.012997478246688843
2023-01-24 05:09:56.523658: step: 748/529, loss: 0.024401886388659477
2023-01-24 05:09:57.560369: step: 752/529, loss: 0.05132303759455681
2023-01-24 05:09:58.607716: step: 756/529, loss: 0.011608830653131008
2023-01-24 05:09:59.648451: step: 760/529, loss: 0.012680543586611748
2023-01-24 05:10:00.704208: step: 764/529, loss: 0.03228800371289253
2023-01-24 05:10:01.729583: step: 768/529, loss: 0.026904243975877762
2023-01-24 05:10:02.781058: step: 772/529, loss: 0.027837267145514488
2023-01-24 05:10:03.825764: step: 776/529, loss: 0.04205892235040665
2023-01-24 05:10:04.888550: step: 780/529, loss: 0.008602812886238098
2023-01-24 05:10:05.924864: step: 784/529, loss: 0.06736654043197632
2023-01-24 05:10:06.966769: step: 788/529, loss: 0.03358781337738037
2023-01-24 05:10:08.012763: step: 792/529, loss: 0.025038380175828934
2023-01-24 05:10:09.073932: step: 796/529, loss: 0.049624573439359665
2023-01-24 05:10:10.140590: step: 800/529, loss: 0.06829757243394852
2023-01-24 05:10:11.173927: step: 804/529, loss: 0.04474746435880661
2023-01-24 05:10:12.209892: step: 808/529, loss: 0.052247192710638046
2023-01-24 05:10:13.245286: step: 812/529, loss: 0.03364172205328941
2023-01-24 05:10:14.297763: step: 816/529, loss: 0.010718918405473232
2023-01-24 05:10:15.336545: step: 820/529, loss: 0.005122782196849585
2023-01-24 05:10:16.389613: step: 824/529, loss: 0.03489316627383232
2023-01-24 05:10:17.432567: step: 828/529, loss: 0.009914408437907696
2023-01-24 05:10:18.488723: step: 832/529, loss: 0.027348777279257774
2023-01-24 05:10:19.535139: step: 836/529, loss: 0.009882641024887562
2023-01-24 05:10:20.584083: step: 840/529, loss: 0.013581992127001286
2023-01-24 05:10:21.668722: step: 844/529, loss: 0.03712452948093414
2023-01-24 05:10:22.717719: step: 848/529, loss: 0.014871868304908276
2023-01-24 05:10:23.781811: step: 852/529, loss: 0.018262458965182304
2023-01-24 05:10:24.833063: step: 856/529, loss: 0.034095119684934616
2023-01-24 05:10:25.879310: step: 860/529, loss: 0.010032016783952713
2023-01-24 05:10:26.940477: step: 864/529, loss: 0.034494798630476
2023-01-24 05:10:27.984338: step: 868/529, loss: 0.04357277601957321
2023-01-24 05:10:29.033681: step: 872/529, loss: 0.027265435084700584
2023-01-24 05:10:30.095218: step: 876/529, loss: 0.013961665332317352
2023-01-24 05:10:31.158802: step: 880/529, loss: 0.007439268287271261
2023-01-24 05:10:32.206723: step: 884/529, loss: 0.017650846391916275
2023-01-24 05:10:33.238932: step: 888/529, loss: 0.043088555335998535
2023-01-24 05:10:34.299392: step: 892/529, loss: 0.023871731013059616
2023-01-24 05:10:35.367316: step: 896/529, loss: 0.0229964442551136
2023-01-24 05:10:36.415551: step: 900/529, loss: 0.0036926409229636192
2023-01-24 05:10:37.473092: step: 904/529, loss: 0.013771359808743
2023-01-24 05:10:38.540283: step: 908/529, loss: 0.010296299122273922
2023-01-24 05:10:39.589593: step: 912/529, loss: 0.017732994630932808
2023-01-24 05:10:40.642734: step: 916/529, loss: 0.025946009904146194
2023-01-24 05:10:41.674828: step: 920/529, loss: 0.049282774329185486
2023-01-24 05:10:42.714774: step: 924/529, loss: 0.015098088420927525
2023-01-24 05:10:43.761320: step: 928/529, loss: 0.005763272289186716
2023-01-24 05:10:44.801579: step: 932/529, loss: 0.00590843241661787
2023-01-24 05:10:45.847645: step: 936/529, loss: 0.0069006336852908134
2023-01-24 05:10:46.906300: step: 940/529, loss: 0.011012403294444084
2023-01-24 05:10:47.950393: step: 944/529, loss: 0.034919530153274536
2023-01-24 05:10:48.991655: step: 948/529, loss: 0.006291705183684826
2023-01-24 05:10:50.043839: step: 952/529, loss: 0.00841736514121294
2023-01-24 05:10:51.079930: step: 956/529, loss: 0.011827602051198483
2023-01-24 05:10:52.122484: step: 960/529, loss: 0.019710896536707878
2023-01-24 05:10:53.163717: step: 964/529, loss: 0.0038844586815685034
2023-01-24 05:10:54.199179: step: 968/529, loss: 0.0070901853032410145
2023-01-24 05:10:55.233490: step: 972/529, loss: 0.014970028772950172
2023-01-24 05:10:56.271732: step: 976/529, loss: 0.014748920686542988
2023-01-24 05:10:57.324605: step: 980/529, loss: 0.04005814716219902
2023-01-24 05:10:58.365561: step: 984/529, loss: 0.019384905695915222
2023-01-24 05:10:59.421773: step: 988/529, loss: 0.013861997984349728
2023-01-24 05:11:00.483118: step: 992/529, loss: 0.01489313691854477
2023-01-24 05:11:01.523516: step: 996/529, loss: 0.012733696959912777
2023-01-24 05:11:02.550464: step: 1000/529, loss: 0.015110542997717857
2023-01-24 05:11:03.576813: step: 1004/529, loss: 0.016543498262763023
2023-01-24 05:11:04.606969: step: 1008/529, loss: 0.053024791181087494
2023-01-24 05:11:05.657070: step: 1012/529, loss: 0.009391451254487038
2023-01-24 05:11:06.715248: step: 1016/529, loss: 0.014434714801609516
2023-01-24 05:11:07.758517: step: 1020/529, loss: 0.031691450625658035
2023-01-24 05:11:08.810876: step: 1024/529, loss: 0.009974936954677105
2023-01-24 05:11:09.890898: step: 1028/529, loss: 0.06868696957826614
2023-01-24 05:11:10.954711: step: 1032/529, loss: 0.05398740991950035
2023-01-24 05:11:12.002871: step: 1036/529, loss: 0.0282050222158432
2023-01-24 05:11:13.048897: step: 1040/529, loss: 0.0057012466713786125
2023-01-24 05:11:14.100979: step: 1044/529, loss: 0.04486163705587387
2023-01-24 05:11:15.149132: step: 1048/529, loss: 0.0355050191283226
2023-01-24 05:11:16.195645: step: 1052/529, loss: 0.01387431938201189
2023-01-24 05:11:17.239467: step: 1056/529, loss: 0.008000961504876614
2023-01-24 05:11:18.275616: step: 1060/529, loss: 0.0053679319098591805
2023-01-24 05:11:19.336339: step: 1064/529, loss: 0.01253668311983347
2023-01-24 05:11:20.382626: step: 1068/529, loss: 0.009002232924103737
2023-01-24 05:11:21.422037: step: 1072/529, loss: 0.00570894218981266
2023-01-24 05:11:22.470386: step: 1076/529, loss: 0.054735440760850906
2023-01-24 05:11:23.509559: step: 1080/529, loss: 0.006681904662400484
2023-01-24 05:11:24.564075: step: 1084/529, loss: 0.017748413607478142
2023-01-24 05:11:25.617775: step: 1088/529, loss: 0.007863124832510948
2023-01-24 05:11:26.657701: step: 1092/529, loss: 0.006316049490123987
2023-01-24 05:11:27.716220: step: 1096/529, loss: 0.011292953044176102
2023-01-24 05:11:28.785700: step: 1100/529, loss: 0.012597151100635529
2023-01-24 05:11:29.837326: step: 1104/529, loss: 0.04695584252476692
2023-01-24 05:11:30.882691: step: 1108/529, loss: 0.007417854852974415
2023-01-24 05:11:31.927493: step: 1112/529, loss: 0.032040588557720184
2023-01-24 05:11:32.975364: step: 1116/529, loss: 0.019973304122686386
2023-01-24 05:11:34.009779: step: 1120/529, loss: 0.012334685772657394
2023-01-24 05:11:35.065204: step: 1124/529, loss: 0.00912613794207573
2023-01-24 05:11:36.105714: step: 1128/529, loss: 0.011598779819905758
2023-01-24 05:11:37.141705: step: 1132/529, loss: 0.058191776275634766
2023-01-24 05:11:38.195717: step: 1136/529, loss: 0.04152904823422432
2023-01-24 05:11:39.228197: step: 1140/529, loss: 0.013890745118260384
2023-01-24 05:11:40.258353: step: 1144/529, loss: 0.014456016942858696
2023-01-24 05:11:41.327124: step: 1148/529, loss: 0.01755940169095993
2023-01-24 05:11:42.368351: step: 1152/529, loss: 0.039868682622909546
2023-01-24 05:11:43.399870: step: 1156/529, loss: 0.008498022332787514
2023-01-24 05:11:44.437842: step: 1160/529, loss: 0.006830099504441023
2023-01-24 05:11:45.508437: step: 1164/529, loss: 0.012597493827342987
2023-01-24 05:11:46.560794: step: 1168/529, loss: 0.006805849727243185
2023-01-24 05:11:47.614842: step: 1172/529, loss: 0.037344783544540405
2023-01-24 05:11:48.659257: step: 1176/529, loss: 0.033238671720027924
2023-01-24 05:11:49.709807: step: 1180/529, loss: 0.00649050110951066
2023-01-24 05:11:50.758043: step: 1184/529, loss: 0.017561092972755432
2023-01-24 05:11:51.813166: step: 1188/529, loss: 0.013161523267626762
2023-01-24 05:11:52.871080: step: 1192/529, loss: 0.028273042291402817
2023-01-24 05:11:53.919830: step: 1196/529, loss: 0.05599603429436684
2023-01-24 05:11:54.957975: step: 1200/529, loss: 0.04154041409492493
2023-01-24 05:11:56.008052: step: 1204/529, loss: 0.00657001743093133
2023-01-24 05:11:57.069080: step: 1208/529, loss: 0.011616759933531284
2023-01-24 05:11:58.129043: step: 1212/529, loss: 0.010004591196775436
2023-01-24 05:11:59.174610: step: 1216/529, loss: 0.006797294598072767
2023-01-24 05:12:00.232155: step: 1220/529, loss: 0.015774471685290337
2023-01-24 05:12:01.274491: step: 1224/529, loss: 0.06791481375694275
2023-01-24 05:12:02.322725: step: 1228/529, loss: 0.06490154564380646
2023-01-24 05:12:03.362502: step: 1232/529, loss: 0.007676573935896158
2023-01-24 05:12:04.420904: step: 1236/529, loss: 0.015669338405132294
2023-01-24 05:12:05.467809: step: 1240/529, loss: 0.010901951231062412
2023-01-24 05:12:06.506400: step: 1244/529, loss: 0.031759507954120636
2023-01-24 05:12:07.548947: step: 1248/529, loss: 0.05133504047989845
2023-01-24 05:12:08.597394: step: 1252/529, loss: 0.01476442813873291
2023-01-24 05:12:09.652914: step: 1256/529, loss: 0.011178816668689251
2023-01-24 05:12:10.713934: step: 1260/529, loss: 0.00566266430541873
2023-01-24 05:12:11.781446: step: 1264/529, loss: 0.0105745829641819
2023-01-24 05:12:12.839189: step: 1268/529, loss: 0.010931075550615788
2023-01-24 05:12:13.886401: step: 1272/529, loss: 0.019857797771692276
2023-01-24 05:12:14.940929: step: 1276/529, loss: 0.026732290163636208
2023-01-24 05:12:15.982126: step: 1280/529, loss: 0.03947070240974426
2023-01-24 05:12:17.030762: step: 1284/529, loss: 0.016308046877384186
2023-01-24 05:12:18.092240: step: 1288/529, loss: 0.009445912204682827
2023-01-24 05:12:19.135583: step: 1292/529, loss: 0.008985220454633236
2023-01-24 05:12:20.183044: step: 1296/529, loss: 0.009500646032392979
2023-01-24 05:12:21.231750: step: 1300/529, loss: 0.020225435495376587
2023-01-24 05:12:22.307506: step: 1304/529, loss: 0.005524156149476767
2023-01-24 05:12:23.361592: step: 1308/529, loss: 0.008743815124034882
2023-01-24 05:12:24.403440: step: 1312/529, loss: 0.029500380158424377
2023-01-24 05:12:25.460305: step: 1316/529, loss: 0.007472315803170204
2023-01-24 05:12:26.510055: step: 1320/529, loss: 0.007899194024503231
2023-01-24 05:12:27.557126: step: 1324/529, loss: 0.006183188408613205
2023-01-24 05:12:28.607585: step: 1328/529, loss: 0.010686767287552357
2023-01-24 05:12:29.640364: step: 1332/529, loss: 0.007414683699607849
2023-01-24 05:12:30.698680: step: 1336/529, loss: 0.01777159422636032
2023-01-24 05:12:31.755705: step: 1340/529, loss: 0.0460592545568943
2023-01-24 05:12:32.813014: step: 1344/529, loss: 0.015033723786473274
2023-01-24 05:12:33.851389: step: 1348/529, loss: 0.0044701192528009415
2023-01-24 05:12:34.894593: step: 1352/529, loss: 0.007065320387482643
2023-01-24 05:12:35.924299: step: 1356/529, loss: 0.013166139833629131
2023-01-24 05:12:36.970486: step: 1360/529, loss: 0.018071308732032776
2023-01-24 05:12:38.011527: step: 1364/529, loss: 0.05738624185323715
2023-01-24 05:12:39.051828: step: 1368/529, loss: 0.016066044569015503
2023-01-24 05:12:40.127116: step: 1372/529, loss: 0.020052537322044373
2023-01-24 05:12:41.192523: step: 1376/529, loss: 0.02242439240217209
2023-01-24 05:12:42.237132: step: 1380/529, loss: 0.0059359255246818066
2023-01-24 05:12:43.290892: step: 1384/529, loss: 0.009813246317207813
2023-01-24 05:12:44.328426: step: 1388/529, loss: 0.02666051872074604
2023-01-24 05:12:45.377415: step: 1392/529, loss: 0.015051918104290962
2023-01-24 05:12:46.431596: step: 1396/529, loss: 0.02678958885371685
2023-01-24 05:12:47.488052: step: 1400/529, loss: 0.01420626137405634
2023-01-24 05:12:48.553328: step: 1404/529, loss: 0.006496739108115435
2023-01-24 05:12:49.597326: step: 1408/529, loss: 0.00599666265770793
2023-01-24 05:12:50.638327: step: 1412/529, loss: 0.0068876054137945175
2023-01-24 05:12:51.693478: step: 1416/529, loss: 0.009554808959364891
2023-01-24 05:12:52.740997: step: 1420/529, loss: 0.022742340341210365
2023-01-24 05:12:53.791277: step: 1424/529, loss: 0.008414790034294128
2023-01-24 05:12:54.836155: step: 1428/529, loss: 0.012524743564426899
2023-01-24 05:12:55.891704: step: 1432/529, loss: 0.017238492146134377
2023-01-24 05:12:56.930890: step: 1436/529, loss: 0.006536091212183237
2023-01-24 05:12:57.981654: step: 1440/529, loss: 0.014208833687007427
2023-01-24 05:12:59.039438: step: 1444/529, loss: 0.009598673321306705
2023-01-24 05:13:00.097761: step: 1448/529, loss: 0.03988807275891304
2023-01-24 05:13:01.165689: step: 1452/529, loss: 0.011487000621855259
2023-01-24 05:13:02.221598: step: 1456/529, loss: 0.036507438868284225
2023-01-24 05:13:03.285955: step: 1460/529, loss: 0.021896976977586746
2023-01-24 05:13:04.336637: step: 1464/529, loss: 0.016844185069203377
2023-01-24 05:13:05.381257: step: 1468/529, loss: 0.011329648084938526
2023-01-24 05:13:06.420633: step: 1472/529, loss: 0.013393408618867397
2023-01-24 05:13:07.466951: step: 1476/529, loss: 0.007768715266138315
2023-01-24 05:13:08.511621: step: 1480/529, loss: 0.006772950757294893
2023-01-24 05:13:09.573541: step: 1484/529, loss: 0.013589548878371716
2023-01-24 05:13:10.621364: step: 1488/529, loss: 0.02934175357222557
2023-01-24 05:13:11.679665: step: 1492/529, loss: 0.033652111887931824
2023-01-24 05:13:12.722158: step: 1496/529, loss: 0.017602689564228058
2023-01-24 05:13:13.771708: step: 1500/529, loss: 0.059618715196847916
2023-01-24 05:13:14.825499: step: 1504/529, loss: 0.007108935620635748
2023-01-24 05:13:15.874876: step: 1508/529, loss: 0.011854098178446293
2023-01-24 05:13:16.923670: step: 1512/529, loss: 0.01667722873389721
2023-01-24 05:13:17.973385: step: 1516/529, loss: 0.008631790056824684
2023-01-24 05:13:19.010853: step: 1520/529, loss: 0.01149787474423647
2023-01-24 05:13:20.067009: step: 1524/529, loss: 0.04335061460733414
2023-01-24 05:13:21.113577: step: 1528/529, loss: 0.01972944103181362
2023-01-24 05:13:22.156794: step: 1532/529, loss: 0.03526837006211281
2023-01-24 05:13:23.202133: step: 1536/529, loss: 0.026519054546952248
2023-01-24 05:13:24.253468: step: 1540/529, loss: 0.028840841725468636
2023-01-24 05:13:25.316647: step: 1544/529, loss: 0.014388822950422764
2023-01-24 05:13:26.364059: step: 1548/529, loss: 0.011385641992092133
2023-01-24 05:13:27.432782: step: 1552/529, loss: 0.014687527902424335
2023-01-24 05:13:28.489971: step: 1556/529, loss: 0.011664765886962414
2023-01-24 05:13:29.536500: step: 1560/529, loss: 0.017614420503377914
2023-01-24 05:13:30.600311: step: 1564/529, loss: 0.07989468425512314
2023-01-24 05:13:31.659625: step: 1568/529, loss: 0.05172615125775337
2023-01-24 05:13:32.712583: step: 1572/529, loss: 0.013751637190580368
2023-01-24 05:13:33.785685: step: 1576/529, loss: 0.00734727643430233
2023-01-24 05:13:34.839850: step: 1580/529, loss: 0.026030514389276505
2023-01-24 05:13:35.901671: step: 1584/529, loss: 0.05756397545337677
2023-01-24 05:13:36.949647: step: 1588/529, loss: 0.015477882698178291
2023-01-24 05:13:37.997621: step: 1592/529, loss: 0.007318898104131222
2023-01-24 05:13:39.048435: step: 1596/529, loss: 0.011881709098815918
2023-01-24 05:13:40.097345: step: 1600/529, loss: 0.01190242636948824
2023-01-24 05:13:41.156149: step: 1604/529, loss: 0.005208552815020084
2023-01-24 05:13:42.213807: step: 1608/529, loss: 0.006001685280352831
2023-01-24 05:13:43.270992: step: 1612/529, loss: 0.014555458910763264
2023-01-24 05:13:44.314097: step: 1616/529, loss: 0.04213704168796539
2023-01-24 05:13:45.379013: step: 1620/529, loss: 0.004783819429576397
2023-01-24 05:13:46.431171: step: 1624/529, loss: 0.008820750750601292
2023-01-24 05:13:47.480922: step: 1628/529, loss: 0.00777822220697999
2023-01-24 05:13:48.528813: step: 1632/529, loss: 0.02491750754415989
2023-01-24 05:13:49.569166: step: 1636/529, loss: 0.0062635233625769615
2023-01-24 05:13:50.617657: step: 1640/529, loss: 0.00697286007925868
2023-01-24 05:13:51.666760: step: 1644/529, loss: 0.002969509456306696
2023-01-24 05:13:52.714711: step: 1648/529, loss: 0.012704771012067795
2023-01-24 05:13:53.748414: step: 1652/529, loss: 0.006044019944965839
2023-01-24 05:13:54.804826: step: 1656/529, loss: 0.059056662023067474
2023-01-24 05:13:55.844945: step: 1660/529, loss: 0.06059417128562927
2023-01-24 05:13:56.894172: step: 1664/529, loss: 0.027641812339425087
2023-01-24 05:13:57.959053: step: 1668/529, loss: 0.01789151318371296
2023-01-24 05:13:58.997647: step: 1672/529, loss: 0.005856847390532494
2023-01-24 05:14:00.044513: step: 1676/529, loss: 0.0241501796990633
2023-01-24 05:14:01.100087: step: 1680/529, loss: 0.05967726558446884
2023-01-24 05:14:02.155899: step: 1684/529, loss: 0.030968137085437775
2023-01-24 05:14:03.217183: step: 1688/529, loss: 0.042150989174842834
2023-01-24 05:14:04.302960: step: 1692/529, loss: 0.006490673869848251
2023-01-24 05:14:05.349149: step: 1696/529, loss: 0.010684220120310783
2023-01-24 05:14:06.405012: step: 1700/529, loss: 0.008071883581578732
2023-01-24 05:14:07.485977: step: 1704/529, loss: 0.061374738812446594
2023-01-24 05:14:08.530839: step: 1708/529, loss: 0.009467871859669685
2023-01-24 05:14:09.576049: step: 1712/529, loss: 0.00471325870603323
2023-01-24 05:14:10.622678: step: 1716/529, loss: 0.010763736441731453
2023-01-24 05:14:11.690001: step: 1720/529, loss: 0.02753886952996254
2023-01-24 05:14:12.747920: step: 1724/529, loss: 0.0
2023-01-24 05:14:13.806720: step: 1728/529, loss: 0.07493897527456284
2023-01-24 05:14:14.865852: step: 1732/529, loss: 0.06929270178079605
2023-01-24 05:14:15.923433: step: 1736/529, loss: 0.015859266743063927
2023-01-24 05:14:16.987914: step: 1740/529, loss: 0.00466306135058403
2023-01-24 05:14:18.059274: step: 1744/529, loss: 0.01314464956521988
2023-01-24 05:14:19.118807: step: 1748/529, loss: 0.013157541863620281
2023-01-24 05:14:20.215109: step: 1752/529, loss: 0.011773504316806793
2023-01-24 05:14:21.268995: step: 1756/529, loss: 0.0172476414591074
2023-01-24 05:14:22.324489: step: 1760/529, loss: 0.003939643502235413
2023-01-24 05:14:23.377805: step: 1764/529, loss: 0.02368035353720188
2023-01-24 05:14:24.433647: step: 1768/529, loss: 0.04851626232266426
2023-01-24 05:14:25.519450: step: 1772/529, loss: 0.011612799018621445
2023-01-24 05:14:26.582877: step: 1776/529, loss: 0.037775591015815735
2023-01-24 05:14:27.621485: step: 1780/529, loss: 0.017987987026572227
2023-01-24 05:14:28.673634: step: 1784/529, loss: 0.01180795207619667
2023-01-24 05:14:29.741954: step: 1788/529, loss: 0.008999248966574669
2023-01-24 05:14:30.814361: step: 1792/529, loss: 0.0
2023-01-24 05:14:31.881096: step: 1796/529, loss: 0.04875265434384346
2023-01-24 05:14:32.935755: step: 1800/529, loss: 0.06563683599233627
2023-01-24 05:14:33.988303: step: 1804/529, loss: 0.01794552430510521
2023-01-24 05:14:35.037177: step: 1808/529, loss: 0.004249773919582367
2023-01-24 05:14:36.081914: step: 1812/529, loss: 0.07462327927350998
2023-01-24 05:14:37.131600: step: 1816/529, loss: 0.034947510808706284
2023-01-24 05:14:38.160240: step: 1820/529, loss: 0.012136394158005714
2023-01-24 05:14:39.210997: step: 1824/529, loss: 0.0226756501942873
2023-01-24 05:14:40.258039: step: 1828/529, loss: 0.03708178922533989
2023-01-24 05:14:41.328022: step: 1832/529, loss: 0.04001658037304878
2023-01-24 05:14:42.396586: step: 1836/529, loss: 0.002695823786780238
2023-01-24 05:14:43.457391: step: 1840/529, loss: 0.03813839703798294
2023-01-24 05:14:44.504096: step: 1844/529, loss: 0.009640282951295376
2023-01-24 05:14:45.559085: step: 1848/529, loss: 0.017239144071936607
2023-01-24 05:14:46.605379: step: 1852/529, loss: 0.028444131836295128
2023-01-24 05:14:47.642363: step: 1856/529, loss: 0.09313053637742996
2023-01-24 05:14:48.698175: step: 1860/529, loss: 0.011019841767847538
2023-01-24 05:14:49.756115: step: 1864/529, loss: 0.013844712637364864
2023-01-24 05:14:50.816314: step: 1868/529, loss: 0.002909870119765401
2023-01-24 05:14:51.871519: step: 1872/529, loss: 0.012615899555385113
2023-01-24 05:14:52.922233: step: 1876/529, loss: 0.00492201978340745
2023-01-24 05:14:53.991070: step: 1880/529, loss: 0.0061734337359666824
2023-01-24 05:14:55.060397: step: 1884/529, loss: 0.01600251905620098
2023-01-24 05:14:56.107360: step: 1888/529, loss: 0.01045612245798111
2023-01-24 05:14:57.167999: step: 1892/529, loss: 0.014157215133309364
2023-01-24 05:14:58.216896: step: 1896/529, loss: 0.01483991090208292
2023-01-24 05:14:59.271254: step: 1900/529, loss: 0.09080835431814194
2023-01-24 05:15:00.340990: step: 1904/529, loss: 0.014748928137123585
2023-01-24 05:15:01.392636: step: 1908/529, loss: 0.0028220252133905888
2023-01-24 05:15:02.446601: step: 1912/529, loss: 0.03067260980606079
2023-01-24 05:15:03.499703: step: 1916/529, loss: 0.009249846450984478
2023-01-24 05:15:05.144571: step: 1920/529, loss: 0.013515912927687168
2023-01-24 05:15:06.186038: step: 1924/529, loss: 0.003011218970641494
2023-01-24 05:15:07.254819: step: 1928/529, loss: 0.010608375072479248
2023-01-24 05:15:08.314564: step: 1932/529, loss: 0.011607460677623749
2023-01-24 05:15:09.371189: step: 1936/529, loss: 0.008696336299180984
2023-01-24 05:15:10.443042: step: 1940/529, loss: 0.011690421029925346
2023-01-24 05:15:11.506120: step: 1944/529, loss: 0.01527523435652256
2023-01-24 05:15:12.567340: step: 1948/529, loss: 0.04605474695563316
2023-01-24 05:15:13.615282: step: 1952/529, loss: 0.029919173568487167
2023-01-24 05:15:14.677974: step: 1956/529, loss: 0.022050464525818825
2023-01-24 05:15:15.731743: step: 1960/529, loss: 0.03613423556089401
2023-01-24 05:15:16.791313: step: 1964/529, loss: 0.01881842315196991
2023-01-24 05:15:17.856457: step: 1968/529, loss: 0.009463679045438766
2023-01-24 05:15:18.929197: step: 1972/529, loss: 0.05390448868274689
2023-01-24 05:15:19.968380: step: 1976/529, loss: 0.00708890613168478
2023-01-24 05:15:21.041404: step: 1980/529, loss: 0.026748839765787125
2023-01-24 05:15:22.092388: step: 1984/529, loss: 0.00588876660913229
2023-01-24 05:15:23.152280: step: 1988/529, loss: 0.05423406884074211
2023-01-24 05:15:24.209124: step: 1992/529, loss: 0.07117541134357452
2023-01-24 05:15:25.268449: step: 1996/529, loss: 0.061825137585401535
2023-01-24 05:15:26.323832: step: 2000/529, loss: 0.028582893311977386
2023-01-24 05:15:27.397886: step: 2004/529, loss: 0.01340029202401638
2023-01-24 05:15:28.469471: step: 2008/529, loss: 0.008067806251347065
2023-01-24 05:15:29.529862: step: 2012/529, loss: 0.012643524445593357
2023-01-24 05:15:30.605031: step: 2016/529, loss: 0.008147449232637882
2023-01-24 05:15:31.673824: step: 2020/529, loss: 0.006248083431273699
2023-01-24 05:15:32.720211: step: 2024/529, loss: 0.013585902750492096
2023-01-24 05:15:33.773107: step: 2028/529, loss: 0.0667610764503479
2023-01-24 05:15:34.831329: step: 2032/529, loss: 0.017219895496964455
2023-01-24 05:15:35.891579: step: 2036/529, loss: 0.006015201099216938
2023-01-24 05:15:36.936186: step: 2040/529, loss: 0.01091675739735365
2023-01-24 05:15:38.000063: step: 2044/529, loss: 0.0078117321245372295
2023-01-24 05:15:39.060083: step: 2048/529, loss: 0.009715505875647068
2023-01-24 05:15:40.113684: step: 2052/529, loss: 0.016771098598837852
2023-01-24 05:15:41.162592: step: 2056/529, loss: 0.019362032413482666
2023-01-24 05:15:42.203175: step: 2060/529, loss: 0.006257068831473589
2023-01-24 05:15:43.239141: step: 2064/529, loss: 0.014119431376457214
2023-01-24 05:15:44.288827: step: 2068/529, loss: 0.04814297705888748
2023-01-24 05:15:45.341336: step: 2072/529, loss: 0.004365266766399145
2023-01-24 05:15:46.395970: step: 2076/529, loss: 0.05356168746948242
2023-01-24 05:15:47.449662: step: 2080/529, loss: 0.03512370586395264
2023-01-24 05:15:48.517893: step: 2084/529, loss: 0.012180483900010586
2023-01-24 05:15:49.555099: step: 2088/529, loss: 0.007121897768229246
2023-01-24 05:15:50.609693: step: 2092/529, loss: 0.009761323221027851
2023-01-24 05:15:51.658034: step: 2096/529, loss: 0.006173328496515751
2023-01-24 05:15:52.713987: step: 2100/529, loss: 0.017521370202302933
2023-01-24 05:15:53.799917: step: 2104/529, loss: 0.04245489835739136
2023-01-24 05:15:54.862695: step: 2108/529, loss: 0.031457506120204926
2023-01-24 05:15:55.903368: step: 2112/529, loss: 0.021836599335074425
2023-01-24 05:15:56.954524: step: 2116/529, loss: 0.008259828202426434
==================================================
Loss: 0.024
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3243174232309746, 'r': 0.32924064787205204, 'f1': 0.32676049233252624}, 'combined': 0.24077088908712457, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3624079875271184, 'r': 0.3016904189361876, 'f1': 0.32927354295321043}, 'combined': 0.23164972871080133, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34900898520084567, 'r': 0.3132471537001898, 'f1': 0.33016249999999997}, 'combined': 0.24327763157894733, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38180794480633967, 'r': 0.3181732873386164, 'f1': 0.34709813164212694}, 'combined': 0.24643967346591011, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.371333312999324, 'r': 0.34033015214169543, 'f1': 0.35515641619539307}, 'combined': 0.26169420140713173, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3866438321270764, 'r': 0.31167882712077866, 'f1': 0.3451375793552143}, 'combined': 0.24504768134220212, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, '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': 0.3243174232309746, 'r': 0.32924064787205204, 'f1': 0.32676049233252624}, 'combined': 0.24077088908712457, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3624079875271184, 'r': 0.3016904189361876, 'f1': 0.32927354295321043}, 'combined': 0.23164972871080133, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34900898520084567, 'r': 0.3132471537001898, 'f1': 0.33016249999999997}, 'combined': 0.24327763157894733, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38180794480633967, 'r': 0.3181732873386164, 'f1': 0.34709813164212694}, 'combined': 0.24643967346591011, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.371333312999324, 'r': 0.34033015214169543, 'f1': 0.35515641619539307}, 'combined': 0.26169420140713173, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3866438321270764, 'r': 0.31167882712077866, 'f1': 0.3451375793552143}, 'combined': 0.24504768134220212, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:18:59.676330: step: 4/529, loss: 0.009702632203698158
2023-01-24 05:19:00.731560: step: 8/529, loss: 0.004212322179228067
2023-01-24 05:19:01.770620: step: 12/529, loss: 0.03304532915353775
2023-01-24 05:19:02.810138: step: 16/529, loss: 0.015185734257102013
2023-01-24 05:19:03.836100: step: 20/529, loss: 0.028924936428666115
2023-01-24 05:19:04.870841: step: 24/529, loss: 0.006101727485656738
2023-01-24 05:19:05.894821: step: 28/529, loss: 0.008059863932430744
2023-01-24 05:19:06.932429: step: 32/529, loss: 0.015525087714195251
2023-01-24 05:19:07.968676: step: 36/529, loss: 0.015883387997746468
2023-01-24 05:19:08.991657: step: 40/529, loss: 0.007611711975187063
2023-01-24 05:19:10.024499: step: 44/529, loss: 0.024166617542505264
2023-01-24 05:19:11.070030: step: 48/529, loss: 0.012313933111727238
2023-01-24 05:19:12.111184: step: 52/529, loss: 0.010366847738623619
2023-01-24 05:19:13.136018: step: 56/529, loss: 0.012623738497495651
2023-01-24 05:19:14.168457: step: 60/529, loss: 0.00899945292621851
2023-01-24 05:19:15.212161: step: 64/529, loss: 0.03763147071003914
2023-01-24 05:19:16.253642: step: 68/529, loss: 0.012430544942617416
2023-01-24 05:19:17.300181: step: 72/529, loss: 0.00794380996376276
2023-01-24 05:19:18.354786: step: 76/529, loss: 0.011743719689548016
2023-01-24 05:19:19.397045: step: 80/529, loss: 0.008317777886986732
2023-01-24 05:19:20.436637: step: 84/529, loss: 0.020757101476192474
2023-01-24 05:19:21.469224: step: 88/529, loss: 0.010150941088795662
2023-01-24 05:19:22.512021: step: 92/529, loss: 0.006616658065468073
2023-01-24 05:19:23.533930: step: 96/529, loss: 0.006203392520546913
2023-01-24 05:19:24.566713: step: 100/529, loss: 0.016931546851992607
2023-01-24 05:19:25.599023: step: 104/529, loss: 0.012396498583257198
2023-01-24 05:19:26.638707: step: 108/529, loss: 0.006779055576771498
2023-01-24 05:19:27.679618: step: 112/529, loss: 0.009066647849977016
2023-01-24 05:19:28.744532: step: 116/529, loss: 0.011995772831141949
2023-01-24 05:19:29.812823: step: 120/529, loss: 0.01516010519117117
2023-01-24 05:19:30.848196: step: 124/529, loss: 0.014176087453961372
2023-01-24 05:19:31.883528: step: 128/529, loss: 0.0
2023-01-24 05:19:32.926296: step: 132/529, loss: 0.048646312206983566
2023-01-24 05:19:33.976013: step: 136/529, loss: 0.009801060892641544
2023-01-24 05:19:35.017868: step: 140/529, loss: 0.02850925363600254
2023-01-24 05:19:36.072578: step: 144/529, loss: 0.014321591705083847
2023-01-24 05:19:37.107851: step: 148/529, loss: 0.0026925771962851286
2023-01-24 05:19:38.149366: step: 152/529, loss: 0.017567764967679977
2023-01-24 05:19:39.191508: step: 156/529, loss: 0.004184122197329998
2023-01-24 05:19:40.228391: step: 160/529, loss: 0.008230687119066715
2023-01-24 05:19:41.282608: step: 164/529, loss: 0.02939199097454548
2023-01-24 05:19:42.327469: step: 168/529, loss: 0.004161420743912458
2023-01-24 05:19:43.370499: step: 172/529, loss: 0.011520899832248688
2023-01-24 05:19:44.412262: step: 176/529, loss: 0.0038108446169644594
2023-01-24 05:19:45.462755: step: 180/529, loss: 0.026291929185390472
2023-01-24 05:19:46.527389: step: 184/529, loss: 0.007606282364577055
2023-01-24 05:19:47.578918: step: 188/529, loss: 0.022314025089144707
2023-01-24 05:19:48.641697: step: 192/529, loss: 0.03174912929534912
2023-01-24 05:19:49.698462: step: 196/529, loss: 0.004038125276565552
2023-01-24 05:19:50.732620: step: 200/529, loss: 0.005661796312779188
2023-01-24 05:19:51.799051: step: 204/529, loss: 0.0023464723490178585
2023-01-24 05:19:52.848544: step: 208/529, loss: 0.00834522396326065
2023-01-24 05:19:53.897345: step: 212/529, loss: 0.01633678749203682
2023-01-24 05:19:54.939565: step: 216/529, loss: 0.004283620044589043
2023-01-24 05:19:55.987745: step: 220/529, loss: 0.028229283168911934
2023-01-24 05:19:57.026436: step: 224/529, loss: 0.00961701013147831
2023-01-24 05:19:58.083730: step: 228/529, loss: 0.011595970019698143
2023-01-24 05:19:59.130678: step: 232/529, loss: 0.06310028582811356
2023-01-24 05:20:00.178171: step: 236/529, loss: 0.006959089078009129
2023-01-24 05:20:01.247936: step: 240/529, loss: 0.027418065816164017
2023-01-24 05:20:02.292806: step: 244/529, loss: 0.01206853985786438
2023-01-24 05:20:03.340266: step: 248/529, loss: 0.03438446670770645
2023-01-24 05:20:04.382528: step: 252/529, loss: 0.009065095335245132
2023-01-24 05:20:05.425107: step: 256/529, loss: 0.04657723009586334
2023-01-24 05:20:06.470805: step: 260/529, loss: 0.007123757153749466
2023-01-24 05:20:07.538577: step: 264/529, loss: 0.0057588298805058
2023-01-24 05:20:08.591888: step: 268/529, loss: 0.029189610853791237
2023-01-24 05:20:09.641000: step: 272/529, loss: 0.013753708451986313
2023-01-24 05:20:10.691067: step: 276/529, loss: 0.005057580303400755
2023-01-24 05:20:11.750468: step: 280/529, loss: 0.05241711810231209
2023-01-24 05:20:12.797088: step: 284/529, loss: 0.036593712866306305
2023-01-24 05:20:13.871858: step: 288/529, loss: 0.028647996485233307
2023-01-24 05:20:14.922340: step: 292/529, loss: 0.04901021718978882
2023-01-24 05:20:15.988991: step: 296/529, loss: 0.05082092061638832
2023-01-24 05:20:17.041691: step: 300/529, loss: 0.008069179952144623
2023-01-24 05:20:18.090487: step: 304/529, loss: 0.012969561852514744
2023-01-24 05:20:19.148689: step: 308/529, loss: 0.00813002698123455
2023-01-24 05:20:20.199667: step: 312/529, loss: 0.014343906193971634
2023-01-24 05:20:21.247811: step: 316/529, loss: 0.016288744285702705
2023-01-24 05:20:22.295536: step: 320/529, loss: 0.008508963510394096
2023-01-24 05:20:23.350191: step: 324/529, loss: 0.011361664161086082
2023-01-24 05:20:24.404899: step: 328/529, loss: 0.015250255353748798
2023-01-24 05:20:25.466666: step: 332/529, loss: 0.0062587447464466095
2023-01-24 05:20:26.531823: step: 336/529, loss: 0.0019832190591841936
2023-01-24 05:20:27.594735: step: 340/529, loss: 0.006038452964276075
2023-01-24 05:20:28.644107: step: 344/529, loss: 0.043527502566576004
2023-01-24 05:20:29.700053: step: 348/529, loss: 0.010479786433279514
2023-01-24 05:20:30.748658: step: 352/529, loss: 0.00537203811109066
2023-01-24 05:20:31.803261: step: 356/529, loss: 0.010623506270349026
2023-01-24 05:20:32.868764: step: 360/529, loss: 0.06597544997930527
2023-01-24 05:20:33.909535: step: 364/529, loss: 0.007426958065479994
2023-01-24 05:20:34.987083: step: 368/529, loss: 0.031153954565525055
2023-01-24 05:20:36.039776: step: 372/529, loss: 0.006872945930808783
2023-01-24 05:20:37.096624: step: 376/529, loss: 0.0061378865502774715
2023-01-24 05:20:38.148990: step: 380/529, loss: 0.00790957361459732
2023-01-24 05:20:39.208952: step: 384/529, loss: 0.005878101103007793
2023-01-24 05:20:40.258605: step: 388/529, loss: 0.009965133853256702
2023-01-24 05:20:41.307777: step: 392/529, loss: 0.003342794021591544
2023-01-24 05:20:42.357032: step: 396/529, loss: 0.021368833258748055
2023-01-24 05:20:43.411198: step: 400/529, loss: 0.01007467694580555
2023-01-24 05:20:44.449773: step: 404/529, loss: 0.007592642214149237
2023-01-24 05:20:45.488451: step: 408/529, loss: 0.009408257901668549
2023-01-24 05:20:46.552524: step: 412/529, loss: 0.008199675939977169
2023-01-24 05:20:47.588620: step: 416/529, loss: 0.01346003171056509
2023-01-24 05:20:48.642422: step: 420/529, loss: 0.009628926403820515
2023-01-24 05:20:49.705070: step: 424/529, loss: 0.024976592510938644
2023-01-24 05:20:50.754929: step: 428/529, loss: 0.010551844723522663
2023-01-24 05:20:51.815721: step: 432/529, loss: 0.009431814774870872
2023-01-24 05:20:52.864255: step: 436/529, loss: 0.014981884509325027
2023-01-24 05:20:53.915882: step: 440/529, loss: 0.013812443241477013
2023-01-24 05:20:54.962072: step: 444/529, loss: 0.025818997994065285
2023-01-24 05:20:56.027730: step: 448/529, loss: 0.009159760549664497
2023-01-24 05:20:57.090611: step: 452/529, loss: 0.003597363131120801
2023-01-24 05:20:58.139014: step: 456/529, loss: 0.018870214000344276
2023-01-24 05:20:59.189338: step: 460/529, loss: 0.023106761276721954
2023-01-24 05:21:00.242897: step: 464/529, loss: 0.005742175038903952
2023-01-24 05:21:01.306420: step: 468/529, loss: 0.01089457981288433
2023-01-24 05:21:02.357995: step: 472/529, loss: 0.02378915436565876
2023-01-24 05:21:03.439447: step: 476/529, loss: 0.015174404717981815
2023-01-24 05:21:04.491534: step: 480/529, loss: 0.005291799549013376
2023-01-24 05:21:05.533995: step: 484/529, loss: 0.011648435145616531
2023-01-24 05:21:06.584499: step: 488/529, loss: 0.010164718143641949
2023-01-24 05:21:07.631797: step: 492/529, loss: 0.006625893525779247
2023-01-24 05:21:08.677813: step: 496/529, loss: 0.01943482831120491
2023-01-24 05:21:09.727868: step: 500/529, loss: 0.011251815594732761
2023-01-24 05:21:10.770277: step: 504/529, loss: 0.006503934506326914
2023-01-24 05:21:11.835079: step: 508/529, loss: 0.03821869194507599
2023-01-24 05:21:12.891886: step: 512/529, loss: 0.011579535901546478
2023-01-24 05:21:13.937579: step: 516/529, loss: 0.006645224057137966
2023-01-24 05:21:14.997589: step: 520/529, loss: 0.0018232990987598896
2023-01-24 05:21:16.064039: step: 524/529, loss: 0.0014213580871000886
2023-01-24 05:21:17.116133: step: 528/529, loss: 0.014252830296754837
2023-01-24 05:21:18.169932: step: 532/529, loss: 0.005493494216352701
2023-01-24 05:21:19.235196: step: 536/529, loss: 0.012886922806501389
2023-01-24 05:21:20.288153: step: 540/529, loss: 0.014141098596155643
2023-01-24 05:21:21.345275: step: 544/529, loss: 0.028720082715153694
2023-01-24 05:21:22.399044: step: 548/529, loss: 0.023180142045021057
2023-01-24 05:21:23.435829: step: 552/529, loss: 0.009422210045158863
2023-01-24 05:21:24.477623: step: 556/529, loss: 0.01278822310268879
2023-01-24 05:21:25.542424: step: 560/529, loss: 0.006602788809686899
2023-01-24 05:21:26.597167: step: 564/529, loss: 0.005738876294344664
2023-01-24 05:21:27.657267: step: 568/529, loss: 0.0072227781638503075
2023-01-24 05:21:28.701704: step: 572/529, loss: 0.004410790745168924
2023-01-24 05:21:29.755088: step: 576/529, loss: 0.005892443936318159
2023-01-24 05:21:30.805525: step: 580/529, loss: 0.010658673010766506
2023-01-24 05:21:31.857513: step: 584/529, loss: 0.020166177302598953
2023-01-24 05:21:32.905982: step: 588/529, loss: 0.012440183199942112
2023-01-24 05:21:33.958175: step: 592/529, loss: 0.008904715068638325
2023-01-24 05:21:35.001923: step: 596/529, loss: 0.02467149682343006
2023-01-24 05:21:36.056966: step: 600/529, loss: 0.02473810315132141
2023-01-24 05:21:37.111455: step: 604/529, loss: 0.010048349387943745
2023-01-24 05:21:38.148935: step: 608/529, loss: 0.012251696549355984
2023-01-24 05:21:39.211535: step: 612/529, loss: 0.0010070670396089554
2023-01-24 05:21:40.266570: step: 616/529, loss: 0.01081684697419405
2023-01-24 05:21:41.314284: step: 620/529, loss: 0.006674682721495628
2023-01-24 05:21:42.370056: step: 624/529, loss: 0.004897418897598982
2023-01-24 05:21:43.423116: step: 628/529, loss: 0.009355539456009865
2023-01-24 05:21:44.465651: step: 632/529, loss: 0.033505599945783615
2023-01-24 05:21:45.508805: step: 636/529, loss: 0.008581315167248249
2023-01-24 05:21:46.554258: step: 640/529, loss: 0.00946006178855896
2023-01-24 05:21:47.608477: step: 644/529, loss: 0.005713715683668852
2023-01-24 05:21:48.651084: step: 648/529, loss: 0.005415044724941254
2023-01-24 05:21:49.711121: step: 652/529, loss: 0.013631592504680157
2023-01-24 05:21:50.761602: step: 656/529, loss: 0.01755356974899769
2023-01-24 05:21:51.810588: step: 660/529, loss: 0.006203013006597757
2023-01-24 05:21:52.874977: step: 664/529, loss: 0.0276893749833107
2023-01-24 05:21:53.941532: step: 668/529, loss: 0.026160378009080887
2023-01-24 05:21:54.986763: step: 672/529, loss: 0.013735873624682426
2023-01-24 05:21:56.062562: step: 676/529, loss: 0.014522930607199669
2023-01-24 05:21:57.115126: step: 680/529, loss: 0.007470645941793919
2023-01-24 05:21:58.188068: step: 684/529, loss: 0.012211167253553867
2023-01-24 05:21:59.256542: step: 688/529, loss: 0.018837451934814453
2023-01-24 05:22:00.305720: step: 692/529, loss: 0.023331498727202415
2023-01-24 05:22:01.369403: step: 696/529, loss: 0.006521758157759905
2023-01-24 05:22:02.435466: step: 700/529, loss: 0.011741899885237217
2023-01-24 05:22:03.481141: step: 704/529, loss: 0.01141168363392353
2023-01-24 05:22:04.536706: step: 708/529, loss: 0.006443439517170191
2023-01-24 05:22:05.610719: step: 712/529, loss: 0.026486095041036606
2023-01-24 05:22:06.660237: step: 716/529, loss: 0.008651353418827057
2023-01-24 05:22:07.711617: step: 720/529, loss: 0.042408592998981476
2023-01-24 05:22:08.772320: step: 724/529, loss: 0.01639365591108799
2023-01-24 05:22:09.815700: step: 728/529, loss: 0.009071496315300465
2023-01-24 05:22:10.859112: step: 732/529, loss: 0.0024754484184086323
2023-01-24 05:22:11.911451: step: 736/529, loss: 0.01669994927942753
2023-01-24 05:22:12.977632: step: 740/529, loss: 0.01184410322457552
2023-01-24 05:22:14.030273: step: 744/529, loss: 0.009721135720610619
2023-01-24 05:22:15.078498: step: 748/529, loss: 0.022059466689825058
2023-01-24 05:22:16.119497: step: 752/529, loss: 0.011720165610313416
2023-01-24 05:22:17.175667: step: 756/529, loss: 0.008919107727706432
2023-01-24 05:22:18.224277: step: 760/529, loss: 0.001974788261577487
2023-01-24 05:22:19.295378: step: 764/529, loss: 0.03654288873076439
2023-01-24 05:22:20.346282: step: 768/529, loss: 0.005718754138797522
2023-01-24 05:22:21.395351: step: 772/529, loss: 0.015371087938547134
2023-01-24 05:22:22.465894: step: 776/529, loss: 0.013817953877151012
2023-01-24 05:22:23.517274: step: 780/529, loss: 0.028627563267946243
2023-01-24 05:22:24.578171: step: 784/529, loss: 0.037508122622966766
2023-01-24 05:22:25.615791: step: 788/529, loss: 0.010139815509319305
2023-01-24 05:22:26.675031: step: 792/529, loss: 0.005906376522034407
2023-01-24 05:22:27.741245: step: 796/529, loss: 0.022158462554216385
2023-01-24 05:22:28.786821: step: 800/529, loss: 0.0038460742216557264
2023-01-24 05:22:29.832200: step: 804/529, loss: 0.0008138243574649096
2023-01-24 05:22:30.874101: step: 808/529, loss: 0.004285029601305723
2023-01-24 05:22:31.920890: step: 812/529, loss: 0.006061118096113205
2023-01-24 05:22:32.970598: step: 816/529, loss: 0.014257565140724182
2023-01-24 05:22:34.017498: step: 820/529, loss: 0.045225296169519424
2023-01-24 05:22:35.083431: step: 824/529, loss: 0.005086400546133518
2023-01-24 05:22:36.140892: step: 828/529, loss: 0.008096187375485897
2023-01-24 05:22:37.189430: step: 832/529, loss: 0.0034793426748365164
2023-01-24 05:22:38.253065: step: 836/529, loss: 0.012109835632145405
2023-01-24 05:22:39.310289: step: 840/529, loss: 0.0046193962916731834
2023-01-24 05:22:40.351063: step: 844/529, loss: 0.018356528133153915
2023-01-24 05:22:41.395916: step: 848/529, loss: 0.006966340821236372
2023-01-24 05:22:42.458664: step: 852/529, loss: 0.03517195209860802
2023-01-24 05:22:43.513736: step: 856/529, loss: 0.06802359223365784
2023-01-24 05:22:44.570322: step: 860/529, loss: 0.009121929295361042
2023-01-24 05:22:45.621069: step: 864/529, loss: 0.017725694924592972
2023-01-24 05:22:46.671627: step: 868/529, loss: 0.035595402121543884
2023-01-24 05:22:47.723359: step: 872/529, loss: 0.0030177319422364235
2023-01-24 05:22:48.760608: step: 876/529, loss: 0.01256206538528204
2023-01-24 05:22:49.810703: step: 880/529, loss: 0.006419451907277107
2023-01-24 05:22:50.869279: step: 884/529, loss: 0.007674932945519686
2023-01-24 05:22:51.912100: step: 888/529, loss: 0.006237064488232136
2023-01-24 05:22:52.976043: step: 892/529, loss: 0.010784771293401718
2023-01-24 05:22:54.036462: step: 896/529, loss: 0.028481515124440193
2023-01-24 05:22:55.113201: step: 900/529, loss: 0.00234957505017519
2023-01-24 05:22:56.178802: step: 904/529, loss: 0.013047631829977036
2023-01-24 05:22:57.239179: step: 908/529, loss: 0.007418323308229446
2023-01-24 05:22:58.299047: step: 912/529, loss: 0.021263813599944115
2023-01-24 05:22:59.343434: step: 916/529, loss: 0.030619753524661064
2023-01-24 05:23:00.406865: step: 920/529, loss: 0.012389450334012508
2023-01-24 05:23:01.467140: step: 924/529, loss: 0.005037079099565744
2023-01-24 05:23:02.535130: step: 928/529, loss: 0.00879708118736744
2023-01-24 05:23:03.587050: step: 932/529, loss: 0.0076294527389109135
2023-01-24 05:23:04.637513: step: 936/529, loss: 0.021199515089392662
2023-01-24 05:23:05.679021: step: 940/529, loss: 0.009083127602934837
2023-01-24 05:23:06.727918: step: 944/529, loss: 0.006466279271990061
2023-01-24 05:23:07.797831: step: 948/529, loss: 0.016769271343946457
2023-01-24 05:23:08.854322: step: 952/529, loss: 0.009145503863692284
2023-01-24 05:23:09.902006: step: 956/529, loss: 0.015483645722270012
2023-01-24 05:23:10.939614: step: 960/529, loss: 0.006539743859320879
2023-01-24 05:23:12.002166: step: 964/529, loss: 0.020707696676254272
2023-01-24 05:23:13.045069: step: 968/529, loss: 0.009864192456007004
2023-01-24 05:23:14.081441: step: 972/529, loss: 0.003156255232170224
2023-01-24 05:23:15.146223: step: 976/529, loss: 0.010344979353249073
2023-01-24 05:23:16.207795: step: 980/529, loss: 0.007188082206994295
2023-01-24 05:23:17.278255: step: 984/529, loss: 0.008987879380583763
2023-01-24 05:23:18.328458: step: 988/529, loss: 0.0008328420226462185
2023-01-24 05:23:19.395143: step: 992/529, loss: 0.07001011073589325
2023-01-24 05:23:20.453342: step: 996/529, loss: 0.012010048143565655
2023-01-24 05:23:21.509782: step: 1000/529, loss: 0.002473432570695877
2023-01-24 05:23:22.559548: step: 1004/529, loss: 0.017036965116858482
2023-01-24 05:23:23.632586: step: 1008/529, loss: 0.006179991643875837
2023-01-24 05:23:24.680848: step: 1012/529, loss: 0.028912536799907684
2023-01-24 05:23:25.724991: step: 1016/529, loss: 0.008060370571911335
2023-01-24 05:23:26.766149: step: 1020/529, loss: 0.01860123872756958
2023-01-24 05:23:27.834759: step: 1024/529, loss: 0.010317834094166756
2023-01-24 05:23:28.887419: step: 1028/529, loss: 0.014082814566791058
2023-01-24 05:23:29.935031: step: 1032/529, loss: 0.018244944512844086
2023-01-24 05:23:30.984936: step: 1036/529, loss: 0.025161465629935265
2023-01-24 05:23:32.041046: step: 1040/529, loss: 0.008377800695598125
2023-01-24 05:23:33.089409: step: 1044/529, loss: 0.0006229839636944234
2023-01-24 05:23:34.140472: step: 1048/529, loss: 0.010107414796948433
2023-01-24 05:23:35.192253: step: 1052/529, loss: 0.012382734566926956
2023-01-24 05:23:36.253442: step: 1056/529, loss: 0.055391110479831696
2023-01-24 05:23:37.299711: step: 1060/529, loss: 0.005276706535369158
2023-01-24 05:23:38.355261: step: 1064/529, loss: 0.007801515515893698
2023-01-24 05:23:39.399283: step: 1068/529, loss: 0.002068720292299986
2023-01-24 05:23:40.458826: step: 1072/529, loss: 0.01365474984049797
2023-01-24 05:23:41.509682: step: 1076/529, loss: 0.034711677581071854
2023-01-24 05:23:42.580235: step: 1080/529, loss: 0.02822842448949814
2023-01-24 05:23:43.634267: step: 1084/529, loss: 0.0082323607057333
2023-01-24 05:23:44.679871: step: 1088/529, loss: 0.010493023321032524
2023-01-24 05:23:45.725913: step: 1092/529, loss: 0.005425763316452503
2023-01-24 05:23:46.777848: step: 1096/529, loss: 0.0065599605441093445
2023-01-24 05:23:47.828782: step: 1100/529, loss: 0.033498674631118774
2023-01-24 05:23:48.870487: step: 1104/529, loss: 0.00341247022151947
2023-01-24 05:23:49.944414: step: 1108/529, loss: 0.008480322547256947
2023-01-24 05:23:51.011520: step: 1112/529, loss: 0.011904171667993069
2023-01-24 05:23:52.079305: step: 1116/529, loss: 0.007447232026606798
2023-01-24 05:23:53.140268: step: 1120/529, loss: 0.048919033259153366
2023-01-24 05:23:54.184721: step: 1124/529, loss: 0.0039873565547168255
2023-01-24 05:23:55.229474: step: 1128/529, loss: 0.005117345135658979
2023-01-24 05:23:56.269378: step: 1132/529, loss: 0.008980763144791126
2023-01-24 05:23:57.321009: step: 1136/529, loss: 0.009688722901046276
2023-01-24 05:23:58.374638: step: 1140/529, loss: 0.019318226724863052
2023-01-24 05:23:59.430452: step: 1144/529, loss: 0.01431686244904995
2023-01-24 05:24:00.518343: step: 1148/529, loss: 0.004099272191524506
2023-01-24 05:24:01.563860: step: 1152/529, loss: 0.04144096374511719
2023-01-24 05:24:02.624585: step: 1156/529, loss: 0.010227304883301258
2023-01-24 05:24:03.688385: step: 1160/529, loss: 0.06978435814380646
2023-01-24 05:24:04.733982: step: 1164/529, loss: 0.0045188236981630325
2023-01-24 05:24:05.784631: step: 1168/529, loss: 0.03477945178747177
2023-01-24 05:24:06.830123: step: 1172/529, loss: 0.005270407535135746
2023-01-24 05:24:07.898131: step: 1176/529, loss: 0.03386178985238075
2023-01-24 05:24:08.939998: step: 1180/529, loss: 0.006988477427512407
2023-01-24 05:24:09.979957: step: 1184/529, loss: 0.02751697599887848
2023-01-24 05:24:11.039802: step: 1188/529, loss: 0.00937473401427269
2023-01-24 05:24:12.102692: step: 1192/529, loss: 0.007683223113417625
2023-01-24 05:24:13.145370: step: 1196/529, loss: 0.00957627221941948
2023-01-24 05:24:14.195182: step: 1200/529, loss: 0.009469663724303246
2023-01-24 05:24:15.238795: step: 1204/529, loss: 0.004552146885544062
2023-01-24 05:24:16.280836: step: 1208/529, loss: 0.019856223836541176
2023-01-24 05:24:17.339031: step: 1212/529, loss: 0.016805380582809448
2023-01-24 05:24:18.387911: step: 1216/529, loss: 0.009647201746702194
2023-01-24 05:24:19.451538: step: 1220/529, loss: 0.00820984411984682
2023-01-24 05:24:20.506200: step: 1224/529, loss: 0.015046448446810246
2023-01-24 05:24:21.557701: step: 1228/529, loss: 0.012992354109883308
2023-01-24 05:24:22.606476: step: 1232/529, loss: 0.005617902148514986
2023-01-24 05:24:23.643282: step: 1236/529, loss: 0.010727177374064922
2023-01-24 05:24:24.703244: step: 1240/529, loss: 0.004621490836143494
2023-01-24 05:24:25.743718: step: 1244/529, loss: 0.011618840508162975
2023-01-24 05:24:26.812997: step: 1248/529, loss: 0.003948628436774015
2023-01-24 05:24:27.865129: step: 1252/529, loss: 0.012753070332109928
2023-01-24 05:24:28.917038: step: 1256/529, loss: 0.006294343154877424
2023-01-24 05:24:29.956070: step: 1260/529, loss: 0.004398762248456478
2023-01-24 05:24:30.997721: step: 1264/529, loss: 0.0062956372275948524
2023-01-24 05:24:32.058780: step: 1268/529, loss: 0.015930350869894028
2023-01-24 05:24:33.110293: step: 1272/529, loss: 0.006502767093479633
2023-01-24 05:24:34.161895: step: 1276/529, loss: 0.008406359702348709
2023-01-24 05:24:35.206286: step: 1280/529, loss: 0.008282057009637356
2023-01-24 05:24:36.252261: step: 1284/529, loss: 0.023298965767025948
2023-01-24 05:24:37.303451: step: 1288/529, loss: 0.005118640139698982
2023-01-24 05:24:38.351539: step: 1292/529, loss: 0.02254495956003666
2023-01-24 05:24:39.403457: step: 1296/529, loss: 0.004884684924036264
2023-01-24 05:24:40.464431: step: 1300/529, loss: 0.014652098529040813
2023-01-24 05:24:41.510842: step: 1304/529, loss: 0.0018594631692394614
2023-01-24 05:24:42.570771: step: 1308/529, loss: 0.006399250589311123
2023-01-24 05:24:43.617162: step: 1312/529, loss: 0.04432792216539383
2023-01-24 05:24:44.662037: step: 1316/529, loss: 0.014780706726014614
2023-01-24 05:24:45.705133: step: 1320/529, loss: 0.018753711134195328
2023-01-24 05:24:46.749004: step: 1324/529, loss: 0.012934209778904915
2023-01-24 05:24:47.797981: step: 1328/529, loss: 0.0080748051404953
2023-01-24 05:24:48.855040: step: 1332/529, loss: 0.013834808953106403
2023-01-24 05:24:49.900704: step: 1336/529, loss: 0.009937616065144539
2023-01-24 05:24:50.965956: step: 1340/529, loss: 0.005996472202241421
2023-01-24 05:24:52.006221: step: 1344/529, loss: 0.003624585224315524
2023-01-24 05:24:53.054353: step: 1348/529, loss: 0.0077989050187170506
2023-01-24 05:24:54.106655: step: 1352/529, loss: 0.017789974808692932
2023-01-24 05:24:55.159831: step: 1356/529, loss: 0.08401846140623093
2023-01-24 05:24:56.230970: step: 1360/529, loss: 0.004022348206490278
2023-01-24 05:24:57.276885: step: 1364/529, loss: 0.009396846406161785
2023-01-24 05:24:58.347516: step: 1368/529, loss: 0.03380804508924484
2023-01-24 05:24:59.396145: step: 1372/529, loss: 0.0024178980384021997
2023-01-24 05:25:00.446479: step: 1376/529, loss: 0.001569257816299796
2023-01-24 05:25:01.501213: step: 1380/529, loss: 0.004394140560179949
2023-01-24 05:25:02.564793: step: 1384/529, loss: 0.0056083169765770435
2023-01-24 05:25:03.619906: step: 1388/529, loss: 0.005862198770046234
2023-01-24 05:25:04.678453: step: 1392/529, loss: 0.0633922815322876
2023-01-24 05:25:05.724297: step: 1396/529, loss: 0.0053275092504918575
2023-01-24 05:25:06.786051: step: 1400/529, loss: 0.007326117716729641
2023-01-24 05:25:07.827301: step: 1404/529, loss: 0.004777191206812859
2023-01-24 05:25:08.882944: step: 1408/529, loss: 0.045870207250118256
2023-01-24 05:25:09.936327: step: 1412/529, loss: 0.01463842112571001
2023-01-24 05:25:10.971445: step: 1416/529, loss: 0.04828391969203949
2023-01-24 05:25:12.050415: step: 1420/529, loss: 0.008017132990062237
2023-01-24 05:25:13.106979: step: 1424/529, loss: 0.008438260294497013
2023-01-24 05:25:14.158981: step: 1428/529, loss: 0.012026888318359852
2023-01-24 05:25:15.204770: step: 1432/529, loss: 0.017127279192209244
2023-01-24 05:25:16.245474: step: 1436/529, loss: 0.004902486223727465
2023-01-24 05:25:17.295530: step: 1440/529, loss: 0.010724497959017754
2023-01-24 05:25:18.346223: step: 1444/529, loss: 0.010780728422105312
2023-01-24 05:25:19.391833: step: 1448/529, loss: 0.0036838180385529995
2023-01-24 05:25:20.449848: step: 1452/529, loss: 0.012205828912556171
2023-01-24 05:25:21.504203: step: 1456/529, loss: 0.02813957817852497
2023-01-24 05:25:22.575814: step: 1460/529, loss: 0.009332367219030857
2023-01-24 05:25:23.629194: step: 1464/529, loss: 0.006843236740678549
2023-01-24 05:25:24.697866: step: 1468/529, loss: 0.02566590905189514
2023-01-24 05:25:25.776060: step: 1472/529, loss: 0.00420921528711915
2023-01-24 05:25:26.820831: step: 1476/529, loss: 0.016612662002444267
2023-01-24 05:25:27.858256: step: 1480/529, loss: 0.008609619922935963
2023-01-24 05:25:28.911578: step: 1484/529, loss: 0.009465090930461884
2023-01-24 05:25:29.957892: step: 1488/529, loss: 0.03811675310134888
2023-01-24 05:25:31.023374: step: 1492/529, loss: 0.02892463468015194
2023-01-24 05:25:32.074391: step: 1496/529, loss: 0.0032942022662609816
2023-01-24 05:25:33.131589: step: 1500/529, loss: 0.007878275588154793
2023-01-24 05:25:34.183539: step: 1504/529, loss: 0.01102651096880436
2023-01-24 05:25:35.251574: step: 1508/529, loss: 0.027395185083150864
2023-01-24 05:25:36.300631: step: 1512/529, loss: 0.004893516656011343
2023-01-24 05:25:37.345315: step: 1516/529, loss: 0.0019189275335520506
2023-01-24 05:25:38.400817: step: 1520/529, loss: 0.06153124198317528
2023-01-24 05:25:39.456462: step: 1524/529, loss: 0.007808441761881113
2023-01-24 05:25:40.502055: step: 1528/529, loss: 0.020678263157606125
2023-01-24 05:25:41.550294: step: 1532/529, loss: 0.0011994382366538048
2023-01-24 05:25:42.605957: step: 1536/529, loss: 0.014690292999148369
2023-01-24 05:25:43.652165: step: 1540/529, loss: 0.020666059106588364
2023-01-24 05:25:44.708180: step: 1544/529, loss: 0.01238057017326355
2023-01-24 05:25:45.769270: step: 1548/529, loss: 0.02977786399424076
2023-01-24 05:25:46.810682: step: 1552/529, loss: 0.019417615607380867
2023-01-24 05:25:47.857326: step: 1556/529, loss: 0.007700175046920776
2023-01-24 05:25:48.909669: step: 1560/529, loss: 0.02705598808825016
2023-01-24 05:25:49.963871: step: 1564/529, loss: 0.03783218935132027
2023-01-24 05:25:51.024716: step: 1568/529, loss: 0.012546454556286335
2023-01-24 05:25:52.075546: step: 1572/529, loss: 0.014727315865457058
2023-01-24 05:25:53.125758: step: 1576/529, loss: 0.007398312911391258
2023-01-24 05:25:54.160034: step: 1580/529, loss: 0.004260462708771229
2023-01-24 05:25:55.204123: step: 1584/529, loss: 0.006616853177547455
2023-01-24 05:25:56.247788: step: 1588/529, loss: 0.022465188056230545
2023-01-24 05:25:57.309347: step: 1592/529, loss: 0.002625127322971821
2023-01-24 05:25:58.383760: step: 1596/529, loss: 0.008390899747610092
2023-01-24 05:25:59.434473: step: 1600/529, loss: 0.0766826644539833
2023-01-24 05:26:00.485288: step: 1604/529, loss: 0.04171181842684746
2023-01-24 05:26:01.530914: step: 1608/529, loss: 0.007223764434456825
2023-01-24 05:26:02.577168: step: 1612/529, loss: 0.004279943183064461
2023-01-24 05:26:03.618664: step: 1616/529, loss: 0.03503376618027687
2023-01-24 05:26:04.677413: step: 1620/529, loss: 0.008486324921250343
2023-01-24 05:26:05.742403: step: 1624/529, loss: 0.007074407767504454
2023-01-24 05:26:06.790151: step: 1628/529, loss: 0.012124099768698215
2023-01-24 05:26:07.828152: step: 1632/529, loss: 0.005812091287225485
2023-01-24 05:26:08.897303: step: 1636/529, loss: 0.005729333031922579
2023-01-24 05:26:09.951652: step: 1640/529, loss: 0.009815212339162827
2023-01-24 05:26:10.992444: step: 1644/529, loss: 0.010043101385235786
2023-01-24 05:26:12.041922: step: 1648/529, loss: 0.013427400961518288
2023-01-24 05:26:13.094845: step: 1652/529, loss: 0.008553661406040192
2023-01-24 05:26:14.148799: step: 1656/529, loss: 0.007796815596520901
2023-01-24 05:26:15.183217: step: 1660/529, loss: 0.0036519530694931746
2023-01-24 05:26:16.239142: step: 1664/529, loss: 0.0008156916592270136
2023-01-24 05:26:17.294142: step: 1668/529, loss: 0.008023594506084919
2023-01-24 05:26:18.328517: step: 1672/529, loss: 0.007903888821601868
2023-01-24 05:26:19.380020: step: 1676/529, loss: 0.03816872090101242
2023-01-24 05:26:20.453487: step: 1680/529, loss: 0.006926502101123333
2023-01-24 05:26:21.506118: step: 1684/529, loss: 0.011442071758210659
2023-01-24 05:26:22.543635: step: 1688/529, loss: 0.006777629721909761
2023-01-24 05:26:23.583426: step: 1692/529, loss: 0.010109285824000835
2023-01-24 05:26:24.618749: step: 1696/529, loss: 0.005739683285355568
2023-01-24 05:26:25.678877: step: 1700/529, loss: 0.0106072798371315
2023-01-24 05:26:26.732774: step: 1704/529, loss: 0.005274866707623005
2023-01-24 05:26:27.792771: step: 1708/529, loss: 0.007199095096439123
2023-01-24 05:26:28.845684: step: 1712/529, loss: 0.03927978500723839
2023-01-24 05:26:29.882238: step: 1716/529, loss: 0.00974242389202118
2023-01-24 05:26:30.930973: step: 1720/529, loss: 0.01649884320795536
2023-01-24 05:26:31.973500: step: 1724/529, loss: 0.024332767352461815
2023-01-24 05:26:33.021580: step: 1728/529, loss: 0.009163670241832733
2023-01-24 05:26:34.067041: step: 1732/529, loss: 0.01078770775347948
2023-01-24 05:26:35.140578: step: 1736/529, loss: 0.00305701675824821
2023-01-24 05:26:36.186185: step: 1740/529, loss: 0.007236138917505741
2023-01-24 05:26:37.246352: step: 1744/529, loss: 0.01068450789898634
2023-01-24 05:26:38.272004: step: 1748/529, loss: 0.002962834667414427
2023-01-24 05:26:39.313672: step: 1752/529, loss: 0.004199921619147062
2023-01-24 05:26:40.358408: step: 1756/529, loss: 0.010702506639063358
2023-01-24 05:26:41.400507: step: 1760/529, loss: 0.001984353642910719
2023-01-24 05:26:42.440997: step: 1764/529, loss: 0.03887616842985153
2023-01-24 05:26:43.501158: step: 1768/529, loss: 0.031201494857668877
2023-01-24 05:26:44.546795: step: 1772/529, loss: 0.010206346400082111
2023-01-24 05:26:45.608148: step: 1776/529, loss: 0.048408858478069305
2023-01-24 05:26:46.667171: step: 1780/529, loss: 0.00793641060590744
2023-01-24 05:26:47.720730: step: 1784/529, loss: 0.004356002435088158
2023-01-24 05:26:48.774419: step: 1788/529, loss: 0.00403329124674201
2023-01-24 05:26:49.829969: step: 1792/529, loss: 0.00289630563929677
2023-01-24 05:26:50.868577: step: 1796/529, loss: 0.033533867448568344
2023-01-24 05:26:51.920498: step: 1800/529, loss: 0.009799486957490444
2023-01-24 05:26:52.980211: step: 1804/529, loss: 0.0028348518535494804
2023-01-24 05:26:54.032363: step: 1808/529, loss: 0.024223024025559425
2023-01-24 05:26:55.069970: step: 1812/529, loss: 0.005609686020761728
2023-01-24 05:26:56.106116: step: 1816/529, loss: 0.004338175058364868
2023-01-24 05:26:57.144653: step: 1820/529, loss: 0.03996272757649422
2023-01-24 05:26:58.191196: step: 1824/529, loss: 0.0038215667009353638
2023-01-24 05:26:59.234044: step: 1828/529, loss: 0.0062724510207772255
2023-01-24 05:27:00.284885: step: 1832/529, loss: 0.019856298342347145
2023-01-24 05:27:01.358095: step: 1836/529, loss: 0.04596890136599541
2023-01-24 05:27:02.433948: step: 1840/529, loss: 0.003978193271905184
2023-01-24 05:27:03.473094: step: 1844/529, loss: 0.014827871695160866
2023-01-24 05:27:04.524676: step: 1848/529, loss: 0.012244523502886295
2023-01-24 05:27:05.593946: step: 1852/529, loss: 0.002460882533341646
2023-01-24 05:27:06.632777: step: 1856/529, loss: 0.007105730473995209
2023-01-24 05:27:07.671822: step: 1860/529, loss: 0.009142741560935974
2023-01-24 05:27:08.715724: step: 1864/529, loss: 0.027887966483831406
2023-01-24 05:27:09.760470: step: 1868/529, loss: 0.005558456294238567
2023-01-24 05:27:10.808223: step: 1872/529, loss: 0.0025893880520015955
2023-01-24 05:27:11.876609: step: 1876/529, loss: 0.005603237543255091
2023-01-24 05:27:12.938714: step: 1880/529, loss: 0.0294538214802742
2023-01-24 05:27:13.987522: step: 1884/529, loss: 0.0014858595095574856
2023-01-24 05:27:15.029794: step: 1888/529, loss: 0.07919655740261078
2023-01-24 05:27:16.111337: step: 1892/529, loss: 0.009422773495316505
2023-01-24 05:27:17.172325: step: 1896/529, loss: 0.007626679260283709
2023-01-24 05:27:18.200719: step: 1900/529, loss: 0.02495105005800724
2023-01-24 05:27:19.251860: step: 1904/529, loss: 0.03703620657324791
2023-01-24 05:27:20.295194: step: 1908/529, loss: 0.003523309715092182
2023-01-24 05:27:21.337794: step: 1912/529, loss: 0.009008413180708885
2023-01-24 05:27:22.391084: step: 1916/529, loss: 0.007903202436864376
2023-01-24 05:27:23.437387: step: 1920/529, loss: 0.04858347028493881
2023-01-24 05:27:24.504023: step: 1924/529, loss: 0.010702469386160374
2023-01-24 05:27:25.558175: step: 1928/529, loss: 0.02246721088886261
2023-01-24 05:27:26.612583: step: 1932/529, loss: 0.043326664716005325
2023-01-24 05:27:27.655196: step: 1936/529, loss: 0.006225182209163904
2023-01-24 05:27:28.710935: step: 1940/529, loss: 0.007526633329689503
2023-01-24 05:27:29.758165: step: 1944/529, loss: 0.026046033948659897
2023-01-24 05:27:30.791879: step: 1948/529, loss: 0.0008503666613250971
2023-01-24 05:27:31.838398: step: 1952/529, loss: 0.007444911636412144
2023-01-24 05:27:32.881083: step: 1956/529, loss: 0.018954968079924583
2023-01-24 05:27:33.956765: step: 1960/529, loss: 0.008903324604034424
2023-01-24 05:27:35.014249: step: 1964/529, loss: 0.023453492671251297
2023-01-24 05:27:36.054668: step: 1968/529, loss: 0.006797189824283123
2023-01-24 05:27:37.113290: step: 1972/529, loss: 0.012226155959069729
2023-01-24 05:27:38.158126: step: 1976/529, loss: 0.013284561224281788
2023-01-24 05:27:39.209425: step: 1980/529, loss: 0.0025997436605393887
2023-01-24 05:27:40.246696: step: 1984/529, loss: 0.020554156973958015
2023-01-24 05:27:41.285779: step: 1988/529, loss: 0.017263587564229965
2023-01-24 05:27:42.328868: step: 1992/529, loss: 0.021719371899962425
2023-01-24 05:27:43.375276: step: 1996/529, loss: 0.01578526571393013
2023-01-24 05:27:44.408779: step: 2000/529, loss: 0.003141375258564949
2023-01-24 05:27:45.442328: step: 2004/529, loss: 0.006471711676567793
2023-01-24 05:27:46.479407: step: 2008/529, loss: 0.007639199960976839
2023-01-24 05:27:47.523162: step: 2012/529, loss: 0.005469005089253187
2023-01-24 05:27:48.573979: step: 2016/529, loss: 0.02692493051290512
2023-01-24 05:27:49.638816: step: 2020/529, loss: 0.0201416052877903
2023-01-24 05:27:50.683274: step: 2024/529, loss: 0.004232287406921387
2023-01-24 05:27:51.730734: step: 2028/529, loss: 0.01146592479199171
2023-01-24 05:27:52.777836: step: 2032/529, loss: 0.012300624512135983
2023-01-24 05:27:53.850423: step: 2036/529, loss: 0.04645624756813049
2023-01-24 05:27:54.892082: step: 2040/529, loss: 0.040244873613119125
2023-01-24 05:27:55.929808: step: 2044/529, loss: 0.01166488416492939
2023-01-24 05:27:56.978634: step: 2048/529, loss: 0.009399492293596268
2023-01-24 05:27:58.009723: step: 2052/529, loss: 0.03597395494580269
2023-01-24 05:27:59.043285: step: 2056/529, loss: 0.007753419689834118
2023-01-24 05:28:00.089905: step: 2060/529, loss: 0.007896293886005878
2023-01-24 05:28:01.122062: step: 2064/529, loss: 0.00878907646983862
2023-01-24 05:28:02.174683: step: 2068/529, loss: 0.007226321380585432
2023-01-24 05:28:03.226176: step: 2072/529, loss: 0.01596832647919655
2023-01-24 05:28:04.278199: step: 2076/529, loss: 0.025622377172112465
2023-01-24 05:28:05.324818: step: 2080/529, loss: 0.034276705235242844
2023-01-24 05:28:06.401395: step: 2084/529, loss: 0.0031056769657880068
2023-01-24 05:28:07.460722: step: 2088/529, loss: 0.0360809750854969
2023-01-24 05:28:08.521012: step: 2092/529, loss: 0.008559904992580414
2023-01-24 05:28:09.575569: step: 2096/529, loss: 0.020412065088748932
2023-01-24 05:28:10.614063: step: 2100/529, loss: 0.004759244155138731
2023-01-24 05:28:11.670339: step: 2104/529, loss: 0.007820584811270237
2023-01-24 05:28:12.721675: step: 2108/529, loss: 0.028815461322665215
2023-01-24 05:28:13.794879: step: 2112/529, loss: 0.026477031409740448
2023-01-24 05:28:14.850230: step: 2116/529, loss: 0.02446635812520981
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32651086087420045, 'r': 0.33208694768229874, 'f1': 0.3292752990189491}, 'combined': 0.24262390454027827, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37074014872703925, 'r': 0.30474452015782805, 'f1': 0.3345184100583055}, 'combined': 0.23533958496564208, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3565558510638298, 'r': 0.31799098671726755, 'f1': 0.3361710130391174}, 'combined': 0.24770495697619174, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39054296601292, 'r': 0.3179551372513563, 'f1': 0.35053062750365976}, 'combined': 0.24887674552759842, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3741749795389031, 'r': 0.3408045354434032, 'f1': 0.35671100333400896}, 'combined': 0.2628396866671645, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39815022828367314, 'r': 0.31539061751379177, 'f1': 0.35197101077318865}, 'combined': 0.24989941764896392, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, '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': 0.32651086087420045, 'r': 0.33208694768229874, 'f1': 0.3292752990189491}, 'combined': 0.24262390454027827, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37074014872703925, 'r': 0.30474452015782805, 'f1': 0.3345184100583055}, 'combined': 0.23533958496564208, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3565558510638298, 'r': 0.31799098671726755, 'f1': 0.3361710130391174}, 'combined': 0.24770495697619174, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39054296601292, 'r': 0.3179551372513563, 'f1': 0.35053062750365976}, 'combined': 0.24887674552759842, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3741749795389031, 'r': 0.3408045354434032, 'f1': 0.35671100333400896}, 'combined': 0.2628396866671645, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39815022828367314, 'r': 0.31539061751379177, 'f1': 0.35197101077318865}, 'combined': 0.24989941764896392, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:31:13.461033: step: 4/529, loss: 0.016769899055361748
2023-01-24 05:31:14.488515: step: 8/529, loss: 0.004776649177074432
2023-01-24 05:31:15.558754: step: 12/529, loss: 0.005138264037668705
2023-01-24 05:31:16.588037: step: 16/529, loss: 0.003971568308770657
2023-01-24 05:31:17.638941: step: 20/529, loss: 0.03057672828435898
2023-01-24 05:31:18.673248: step: 24/529, loss: 0.017046503722667694
2023-01-24 05:31:19.700795: step: 28/529, loss: 0.014190775342285633
2023-01-24 05:31:20.747616: step: 32/529, loss: 0.006420804653316736
2023-01-24 05:31:21.790265: step: 36/529, loss: 0.012994932942092419
2023-01-24 05:31:22.843001: step: 40/529, loss: 0.015033001080155373
2023-01-24 05:31:23.884577: step: 44/529, loss: 0.006633009761571884
2023-01-24 05:31:24.921191: step: 48/529, loss: 0.0019002615008503199
2023-01-24 05:31:25.970355: step: 52/529, loss: 0.006438171956688166
2023-01-24 05:31:27.027364: step: 56/529, loss: 0.02033413201570511
2023-01-24 05:31:28.066303: step: 60/529, loss: 0.009090491570532322
2023-01-24 05:31:29.126556: step: 64/529, loss: 0.03538947552442551
2023-01-24 05:31:30.203815: step: 68/529, loss: 0.041352227330207825
2023-01-24 05:31:31.237397: step: 72/529, loss: 0.003349186619743705
2023-01-24 05:31:32.281827: step: 76/529, loss: 0.0077846418134868145
2023-01-24 05:31:33.325989: step: 80/529, loss: 0.0008108459878712893
2023-01-24 05:31:34.379165: step: 84/529, loss: 0.005242703948169947
2023-01-24 05:31:35.431001: step: 88/529, loss: 0.027445776388049126
2023-01-24 05:31:36.479916: step: 92/529, loss: 0.012781407684087753
2023-01-24 05:31:37.515054: step: 96/529, loss: 0.005942841526120901
2023-01-24 05:31:38.576999: step: 100/529, loss: 0.0059811207465827465
2023-01-24 05:31:39.604014: step: 104/529, loss: 0.009064748883247375
2023-01-24 05:31:40.641837: step: 108/529, loss: 0.0010065316455438733
2023-01-24 05:31:41.688067: step: 112/529, loss: 0.04195992276072502
2023-01-24 05:31:42.748334: step: 116/529, loss: 0.004021812696009874
2023-01-24 05:31:43.779339: step: 120/529, loss: 0.019543664529919624
2023-01-24 05:31:44.835071: step: 124/529, loss: 0.0022094366140663624
2023-01-24 05:31:45.882776: step: 128/529, loss: 0.001434655045159161
2023-01-24 05:31:46.910056: step: 132/529, loss: 0.009645376354455948
2023-01-24 05:31:47.957541: step: 136/529, loss: 0.022103631868958473
2023-01-24 05:31:49.002875: step: 140/529, loss: 0.014725483022630215
2023-01-24 05:31:50.044282: step: 144/529, loss: 0.005404842551797628
2023-01-24 05:31:51.079618: step: 148/529, loss: 0.0
2023-01-24 05:31:52.123164: step: 152/529, loss: 0.0026340028271079063
2023-01-24 05:31:53.174359: step: 156/529, loss: 0.004697186406701803
2023-01-24 05:31:54.229371: step: 160/529, loss: 0.01897864043712616
2023-01-24 05:31:55.257173: step: 164/529, loss: 0.0031704457942396402
2023-01-24 05:31:56.300906: step: 168/529, loss: 0.014682571403682232
2023-01-24 05:31:57.342942: step: 172/529, loss: 0.008217915892601013
2023-01-24 05:31:58.382599: step: 176/529, loss: 0.0386650450527668
2023-01-24 05:31:59.434826: step: 180/529, loss: 0.011005488224327564
2023-01-24 05:32:00.488462: step: 184/529, loss: 0.006656793411821127
2023-01-24 05:32:01.527174: step: 188/529, loss: 0.007286156993359327
2023-01-24 05:32:02.581662: step: 192/529, loss: 0.00744550209492445
2023-01-24 05:32:03.645731: step: 196/529, loss: 0.01166602037847042
2023-01-24 05:32:04.680694: step: 200/529, loss: 0.000550617347471416
2023-01-24 05:32:05.728668: step: 204/529, loss: 0.011234098114073277
2023-01-24 05:32:06.789353: step: 208/529, loss: 0.006204743403941393
2023-01-24 05:32:07.831350: step: 212/529, loss: 0.007148205768316984
2023-01-24 05:32:08.892153: step: 216/529, loss: 0.012816202826797962
2023-01-24 05:32:09.946838: step: 220/529, loss: 0.002769813407212496
2023-01-24 05:32:10.982894: step: 224/529, loss: 0.013259481638669968
2023-01-24 05:32:12.044451: step: 228/529, loss: 0.008491086773574352
2023-01-24 05:32:13.089338: step: 232/529, loss: 0.009515050798654556
2023-01-24 05:32:14.117096: step: 236/529, loss: 0.005249901209026575
2023-01-24 05:32:15.153247: step: 240/529, loss: 0.008257444947957993
2023-01-24 05:32:16.187012: step: 244/529, loss: 0.030426081269979477
2023-01-24 05:32:17.229940: step: 248/529, loss: 0.020016733556985855
2023-01-24 05:32:18.278903: step: 252/529, loss: 0.0119384890422225
2023-01-24 05:32:19.314285: step: 256/529, loss: 0.016481148079037666
2023-01-24 05:32:20.370356: step: 260/529, loss: 0.001971587771549821
2023-01-24 05:32:21.423156: step: 264/529, loss: 0.006094732321798801
2023-01-24 05:32:22.461159: step: 268/529, loss: 0.00820962619036436
2023-01-24 05:32:23.535167: step: 272/529, loss: 0.005577035713940859
2023-01-24 05:32:24.577516: step: 276/529, loss: 0.005854811519384384
2023-01-24 05:32:25.614264: step: 280/529, loss: 0.006015812512487173
2023-01-24 05:32:26.653402: step: 284/529, loss: 0.0055336481891572475
2023-01-24 05:32:27.697073: step: 288/529, loss: 0.010216631926596165
2023-01-24 05:32:28.738763: step: 292/529, loss: 0.0022466795053333044
2023-01-24 05:32:29.772463: step: 296/529, loss: 0.03526534512639046
2023-01-24 05:32:30.833769: step: 300/529, loss: 0.011181001551449299
2023-01-24 05:32:31.869699: step: 304/529, loss: 0.010571149177849293
2023-01-24 05:32:32.923226: step: 308/529, loss: 0.00047349909436888993
2023-01-24 05:32:33.964667: step: 312/529, loss: 0.04009775444865227
2023-01-24 05:32:35.006321: step: 316/529, loss: 0.035851314663887024
2023-01-24 05:32:36.050890: step: 320/529, loss: 0.003651312319561839
2023-01-24 05:32:37.104775: step: 324/529, loss: 0.004341717343777418
2023-01-24 05:32:38.135351: step: 328/529, loss: 0.02432491071522236
2023-01-24 05:32:39.174842: step: 332/529, loss: 0.016215045005083084
2023-01-24 05:32:40.205575: step: 336/529, loss: 0.01603284664452076
2023-01-24 05:32:41.266551: step: 340/529, loss: 0.006143355276435614
2023-01-24 05:32:42.311482: step: 344/529, loss: 0.004680093843489885
2023-01-24 05:32:43.351138: step: 348/529, loss: 0.04227147996425629
2023-01-24 05:32:44.394589: step: 352/529, loss: 0.010936867445707321
2023-01-24 05:32:45.443077: step: 356/529, loss: 0.030647749081254005
2023-01-24 05:32:46.494402: step: 360/529, loss: 0.058322589844465256
2023-01-24 05:32:47.526621: step: 364/529, loss: 0.00575517863035202
2023-01-24 05:32:48.573252: step: 368/529, loss: 0.005529760383069515
2023-01-24 05:32:49.627467: step: 372/529, loss: 0.021522492170333862
2023-01-24 05:32:50.692021: step: 376/529, loss: 0.028332088142633438
2023-01-24 05:32:51.735624: step: 380/529, loss: 0.017103740945458412
2023-01-24 05:32:52.787128: step: 384/529, loss: 0.004928337410092354
2023-01-24 05:32:53.826238: step: 388/529, loss: 0.0012269220314919949
2023-01-24 05:32:54.883143: step: 392/529, loss: 0.00917463842779398
2023-01-24 05:32:55.925445: step: 396/529, loss: 0.030700793489813805
2023-01-24 05:32:56.974874: step: 400/529, loss: 0.003996746614575386
2023-01-24 05:32:58.009893: step: 404/529, loss: 0.005860441364347935
2023-01-24 05:32:59.058921: step: 408/529, loss: 0.0008575360989198089
2023-01-24 05:33:00.113229: step: 412/529, loss: 0.032596684992313385
2023-01-24 05:33:01.161226: step: 416/529, loss: 0.003979000262916088
2023-01-24 05:33:02.205647: step: 420/529, loss: 0.01501777395606041
2023-01-24 05:33:03.241909: step: 424/529, loss: 0.012400008738040924
2023-01-24 05:33:04.291407: step: 428/529, loss: 0.012709521688520908
2023-01-24 05:33:05.328933: step: 432/529, loss: 0.004359858110547066
2023-01-24 05:33:06.392382: step: 436/529, loss: 0.020600806921720505
2023-01-24 05:33:07.430124: step: 440/529, loss: 0.0013151929015293717
2023-01-24 05:33:08.473661: step: 444/529, loss: 0.03075871430337429
2023-01-24 05:33:09.531470: step: 448/529, loss: 0.011884140782058239
2023-01-24 05:33:10.582390: step: 452/529, loss: 0.014811577275395393
2023-01-24 05:33:11.623842: step: 456/529, loss: 0.0040180878713727
2023-01-24 05:33:12.663452: step: 460/529, loss: 0.003297898219898343
2023-01-24 05:33:13.717680: step: 464/529, loss: 0.0032817753963172436
2023-01-24 05:33:14.760042: step: 468/529, loss: 0.0627603828907013
2023-01-24 05:33:15.813438: step: 472/529, loss: 0.013188144192099571
2023-01-24 05:33:16.850570: step: 476/529, loss: 0.014035405591130257
2023-01-24 05:33:17.898024: step: 480/529, loss: 0.009819992817938328
2023-01-24 05:33:18.948834: step: 484/529, loss: 0.010854062624275684
2023-01-24 05:33:20.009616: step: 488/529, loss: 0.03837253153324127
2023-01-24 05:33:21.049438: step: 492/529, loss: 0.010389309376478195
2023-01-24 05:33:22.086643: step: 496/529, loss: 0.01501044537872076
2023-01-24 05:33:23.119141: step: 500/529, loss: 0.004261473193764687
2023-01-24 05:33:24.153931: step: 504/529, loss: 0.011986332014203072
2023-01-24 05:33:25.203408: step: 508/529, loss: 0.029767416417598724
2023-01-24 05:33:26.242109: step: 512/529, loss: 0.006752622313797474
2023-01-24 05:33:27.290888: step: 516/529, loss: 0.03037738986313343
2023-01-24 05:33:28.342533: step: 520/529, loss: 0.008480550721287727
2023-01-24 05:33:29.384667: step: 524/529, loss: 0.0014338225591927767
2023-01-24 05:33:30.421648: step: 528/529, loss: 0.009833659045398235
2023-01-24 05:33:31.469870: step: 532/529, loss: 0.017395272850990295
2023-01-24 05:33:32.514598: step: 536/529, loss: 0.0011940039694309235
2023-01-24 05:33:33.554718: step: 540/529, loss: 0.024256566539406776
2023-01-24 05:33:34.607375: step: 544/529, loss: 0.005568946711719036
2023-01-24 05:33:35.638793: step: 548/529, loss: 0.056146688759326935
2023-01-24 05:33:36.683743: step: 552/529, loss: 0.027910880744457245
2023-01-24 05:33:37.730883: step: 556/529, loss: 0.0055074989795684814
2023-01-24 05:33:38.781239: step: 560/529, loss: 0.050471581518650055
2023-01-24 05:33:39.811096: step: 564/529, loss: 0.022269802168011665
2023-01-24 05:33:40.859622: step: 568/529, loss: 0.010979728773236275
2023-01-24 05:33:41.904410: step: 572/529, loss: 0.012627990916371346
2023-01-24 05:33:42.949953: step: 576/529, loss: 0.005599132739007473
2023-01-24 05:33:44.007008: step: 580/529, loss: 0.037314314395189285
2023-01-24 05:33:45.069456: step: 584/529, loss: 0.00323654362000525
2023-01-24 05:33:46.120296: step: 588/529, loss: 0.028864700347185135
2023-01-24 05:33:47.158869: step: 592/529, loss: 0.0031013910192996264
2023-01-24 05:33:48.202083: step: 596/529, loss: 0.0014465071726590395
2023-01-24 05:33:49.249883: step: 600/529, loss: 0.005186670459806919
2023-01-24 05:33:50.290142: step: 604/529, loss: 0.008730238303542137
2023-01-24 05:33:51.343377: step: 608/529, loss: 0.013101747259497643
2023-01-24 05:33:52.400323: step: 612/529, loss: 0.007453371305018663
2023-01-24 05:33:53.436674: step: 616/529, loss: 0.02398344874382019
2023-01-24 05:33:54.492928: step: 620/529, loss: 0.04100363329052925
2023-01-24 05:33:55.527127: step: 624/529, loss: 0.003994930535554886
2023-01-24 05:33:56.587767: step: 628/529, loss: 0.009700490161776543
2023-01-24 05:33:57.639800: step: 632/529, loss: 0.004932609852403402
2023-01-24 05:33:58.661629: step: 636/529, loss: 0.006336611695587635
2023-01-24 05:33:59.710729: step: 640/529, loss: 0.004764177370816469
2023-01-24 05:34:00.750601: step: 644/529, loss: 0.04181733354926109
2023-01-24 05:34:01.821057: step: 648/529, loss: 0.004476585425436497
2023-01-24 05:34:02.864937: step: 652/529, loss: 0.007823966443538666
2023-01-24 05:34:03.915259: step: 656/529, loss: 0.022270355373620987
2023-01-24 05:34:04.945482: step: 660/529, loss: 0.004363867919892073
2023-01-24 05:34:05.985826: step: 664/529, loss: 0.003580256598070264
2023-01-24 05:34:07.039772: step: 668/529, loss: 0.004970157518982887
2023-01-24 05:34:08.097823: step: 672/529, loss: 0.01594248041510582
2023-01-24 05:34:09.153562: step: 676/529, loss: 0.03383409604430199
2023-01-24 05:34:10.210741: step: 680/529, loss: 0.011703518219292164
2023-01-24 05:34:11.260651: step: 684/529, loss: 0.01246214471757412
2023-01-24 05:34:12.306402: step: 688/529, loss: 0.035678885877132416
2023-01-24 05:34:13.352392: step: 692/529, loss: 0.008345757611095905
2023-01-24 05:34:14.390084: step: 696/529, loss: 0.010660410858690739
2023-01-24 05:34:15.441347: step: 700/529, loss: 0.02864742837846279
2023-01-24 05:34:16.486800: step: 704/529, loss: 0.0632297545671463
2023-01-24 05:34:17.536025: step: 708/529, loss: 0.0077431160025298595
2023-01-24 05:34:18.574362: step: 712/529, loss: 0.008357308804988861
2023-01-24 05:34:19.628342: step: 716/529, loss: 0.007670058868825436
2023-01-24 05:34:20.676049: step: 720/529, loss: 0.00536184199154377
2023-01-24 05:34:21.718244: step: 724/529, loss: 0.004081163089722395
2023-01-24 05:34:22.765426: step: 728/529, loss: 0.032472047954797745
2023-01-24 05:34:23.811083: step: 732/529, loss: 0.00711841881275177
2023-01-24 05:34:24.854603: step: 736/529, loss: 0.012580592185258865
2023-01-24 05:34:25.905937: step: 740/529, loss: 0.0074384198524057865
2023-01-24 05:34:26.961159: step: 744/529, loss: 0.0
2023-01-24 05:34:28.007245: step: 748/529, loss: 0.01796574890613556
2023-01-24 05:34:29.074050: step: 752/529, loss: 0.006997659802436829
2023-01-24 05:34:30.124404: step: 756/529, loss: 0.008173210546374321
2023-01-24 05:34:31.173222: step: 760/529, loss: 0.00728617375716567
2023-01-24 05:34:32.233653: step: 764/529, loss: 0.05500132590532303
2023-01-24 05:34:33.267620: step: 768/529, loss: 0.007074093446135521
2023-01-24 05:34:34.307099: step: 772/529, loss: 0.004343635402619839
2023-01-24 05:34:35.363369: step: 776/529, loss: 0.009615425951778889
2023-01-24 05:34:36.410418: step: 780/529, loss: 0.004212587606161833
2023-01-24 05:34:37.453559: step: 784/529, loss: 0.010027064010500908
2023-01-24 05:34:38.520297: step: 788/529, loss: 0.027680957689881325
2023-01-24 05:34:39.574426: step: 792/529, loss: 0.016969498246908188
2023-01-24 05:34:40.622816: step: 796/529, loss: 0.0042504798620939255
2023-01-24 05:34:41.666355: step: 800/529, loss: 0.00416368106380105
2023-01-24 05:34:42.720762: step: 804/529, loss: 0.010829695500433445
2023-01-24 05:34:43.774110: step: 808/529, loss: 0.008041387423872948
2023-01-24 05:34:44.812454: step: 812/529, loss: 0.015539851039648056
2023-01-24 05:34:45.847880: step: 816/529, loss: 0.005472727119922638
2023-01-24 05:34:46.897682: step: 820/529, loss: 0.0138620063662529
2023-01-24 05:34:47.934515: step: 824/529, loss: 0.013219275511801243
2023-01-24 05:34:48.980721: step: 828/529, loss: 0.005984208546578884
2023-01-24 05:34:50.023985: step: 832/529, loss: 0.019417408853769302
2023-01-24 05:34:51.084706: step: 836/529, loss: 0.00668446347117424
2023-01-24 05:34:52.134859: step: 840/529, loss: 0.0042038229294121265
2023-01-24 05:34:53.165225: step: 844/529, loss: 0.010490312241017818
2023-01-24 05:34:54.201788: step: 848/529, loss: 0.0029428787529468536
2023-01-24 05:34:55.250740: step: 852/529, loss: 0.008916784077882767
2023-01-24 05:34:56.298453: step: 856/529, loss: 0.015029284171760082
2023-01-24 05:34:57.342503: step: 860/529, loss: 0.010284416377544403
2023-01-24 05:34:58.392112: step: 864/529, loss: 0.010174809023737907
2023-01-24 05:34:59.452673: step: 868/529, loss: 0.0019343511667102575
2023-01-24 05:35:00.480243: step: 872/529, loss: 0.013984021730720997
2023-01-24 05:35:01.514802: step: 876/529, loss: 0.015247956849634647
2023-01-24 05:35:02.575526: step: 880/529, loss: 0.009768275544047356
2023-01-24 05:35:03.619294: step: 884/529, loss: 0.010797047056257725
2023-01-24 05:35:04.676228: step: 888/529, loss: 0.008494413457810879
2023-01-24 05:35:05.734047: step: 892/529, loss: 0.02661999873816967
2023-01-24 05:35:06.791093: step: 896/529, loss: 0.019694015383720398
2023-01-24 05:35:07.844202: step: 900/529, loss: 0.005477281752973795
2023-01-24 05:35:08.885106: step: 904/529, loss: 0.006969843525439501
2023-01-24 05:35:09.934890: step: 908/529, loss: 0.0034596214536577463
2023-01-24 05:35:10.979674: step: 912/529, loss: 0.11315653473138809
2023-01-24 05:35:12.020564: step: 916/529, loss: 0.001395003986544907
2023-01-24 05:35:13.069484: step: 920/529, loss: 0.013216778635978699
2023-01-24 05:35:14.111107: step: 924/529, loss: 0.0031609954312443733
2023-01-24 05:35:15.169039: step: 928/529, loss: 0.011521650478243828
2023-01-24 05:35:16.232395: step: 932/529, loss: 0.007828129455447197
2023-01-24 05:35:17.278667: step: 936/529, loss: 0.011576209217309952
2023-01-24 05:35:18.334881: step: 940/529, loss: 0.00382436765357852
2023-01-24 05:35:19.375551: step: 944/529, loss: 0.008218149654567242
2023-01-24 05:35:20.416447: step: 948/529, loss: 0.022023677825927734
2023-01-24 05:35:21.473101: step: 952/529, loss: 0.039256900548934937
2023-01-24 05:35:22.512998: step: 956/529, loss: 0.007159958593547344
2023-01-24 05:35:23.543099: step: 960/529, loss: 0.021554918959736824
2023-01-24 05:35:24.584004: step: 964/529, loss: 0.032055631279945374
2023-01-24 05:35:25.624228: step: 968/529, loss: 0.00902123935520649
2023-01-24 05:35:26.669998: step: 972/529, loss: 0.005437079817056656
2023-01-24 05:35:27.730985: step: 976/529, loss: 0.05399130657315254
2023-01-24 05:35:28.771122: step: 980/529, loss: 0.004657253157347441
2023-01-24 05:35:29.831011: step: 984/529, loss: 0.009438995271921158
2023-01-24 05:35:30.878118: step: 988/529, loss: 0.011192361824214458
2023-01-24 05:35:31.920110: step: 992/529, loss: 0.0027497827541083097
2023-01-24 05:35:32.952358: step: 996/529, loss: 0.0037775139790028334
2023-01-24 05:35:33.998112: step: 1000/529, loss: 0.0052798413671553135
2023-01-24 05:35:35.034809: step: 1004/529, loss: 0.0042763869278132915
2023-01-24 05:35:36.074343: step: 1008/529, loss: 0.06839495152235031
2023-01-24 05:35:37.114398: step: 1012/529, loss: 0.011692789383232594
2023-01-24 05:35:38.148823: step: 1016/529, loss: 0.009035824798047543
2023-01-24 05:35:39.192509: step: 1020/529, loss: 0.012222695164382458
2023-01-24 05:35:40.237631: step: 1024/529, loss: 0.007833332754671574
2023-01-24 05:35:41.284469: step: 1028/529, loss: 0.014396791346371174
2023-01-24 05:35:42.320908: step: 1032/529, loss: 0.002740769414231181
2023-01-24 05:35:43.366370: step: 1036/529, loss: 0.025663260370492935
2023-01-24 05:35:44.411664: step: 1040/529, loss: 0.009062030352652073
2023-01-24 05:35:45.478428: step: 1044/529, loss: 0.00875516515225172
2023-01-24 05:35:46.543431: step: 1048/529, loss: 0.0007383400807157159
2023-01-24 05:35:47.583481: step: 1052/529, loss: 0.01957930438220501
2023-01-24 05:35:48.646322: step: 1056/529, loss: 0.009622927755117416
2023-01-24 05:35:49.704588: step: 1060/529, loss: 0.07894708216190338
2023-01-24 05:35:50.765868: step: 1064/529, loss: 0.0038776430301368237
2023-01-24 05:35:51.831946: step: 1068/529, loss: 0.005884992890059948
2023-01-24 05:35:52.869505: step: 1072/529, loss: 0.009725396521389484
2023-01-24 05:35:53.922215: step: 1076/529, loss: 0.01828581653535366
2023-01-24 05:35:54.959897: step: 1080/529, loss: 0.0029913042671978474
2023-01-24 05:35:56.005577: step: 1084/529, loss: 0.006572544574737549
2023-01-24 05:35:57.050554: step: 1088/529, loss: 0.00037372627411969006
2023-01-24 05:35:58.100603: step: 1092/529, loss: 0.012744470499455929
2023-01-24 05:35:59.143979: step: 1096/529, loss: 0.006190674379467964
2023-01-24 05:36:00.199679: step: 1100/529, loss: 0.005227075889706612
2023-01-24 05:36:01.252197: step: 1104/529, loss: 0.018090782687067986
2023-01-24 05:36:02.292993: step: 1108/529, loss: 0.016637571156024933
2023-01-24 05:36:03.334065: step: 1112/529, loss: 0.008095446974039078
2023-01-24 05:36:04.373631: step: 1116/529, loss: 0.014164726249873638
2023-01-24 05:36:05.432086: step: 1120/529, loss: 0.003821906168013811
2023-01-24 05:36:06.481781: step: 1124/529, loss: 0.004693558905273676
2023-01-24 05:36:07.528233: step: 1128/529, loss: 0.005518096964806318
2023-01-24 05:36:08.567226: step: 1132/529, loss: 0.008891682140529156
2023-01-24 05:36:09.603095: step: 1136/529, loss: 0.010577702894806862
2023-01-24 05:36:10.660814: step: 1140/529, loss: 0.018562953919172287
2023-01-24 05:36:11.705331: step: 1144/529, loss: 0.020861614495515823
2023-01-24 05:36:12.753483: step: 1148/529, loss: 0.0013329458888620138
2023-01-24 05:36:13.800334: step: 1152/529, loss: 0.010229039005935192
2023-01-24 05:36:14.844456: step: 1156/529, loss: 0.014662380330264568
2023-01-24 05:36:15.904281: step: 1160/529, loss: 0.007699093781411648
2023-01-24 05:36:16.946799: step: 1164/529, loss: 0.0010371600510552526
2023-01-24 05:36:18.004591: step: 1168/529, loss: 0.004747601691633463
2023-01-24 05:36:19.056139: step: 1172/529, loss: 0.009238509461283684
2023-01-24 05:36:20.095515: step: 1176/529, loss: 0.035539064556360245
2023-01-24 05:36:21.144304: step: 1180/529, loss: 0.010874062776565552
2023-01-24 05:36:22.190320: step: 1184/529, loss: 0.012060358189046383
2023-01-24 05:36:23.239644: step: 1188/529, loss: 0.0037941443733870983
2023-01-24 05:36:24.287666: step: 1192/529, loss: 0.004162719007581472
2023-01-24 05:36:25.338615: step: 1196/529, loss: 0.011726537719368935
2023-01-24 05:36:26.378462: step: 1200/529, loss: 0.0064646461978554726
2023-01-24 05:36:27.439131: step: 1204/529, loss: 0.00655716098845005
2023-01-24 05:36:28.484638: step: 1208/529, loss: 0.0048755561001598835
2023-01-24 05:36:29.518329: step: 1212/529, loss: 0.006016227882355452
2023-01-24 05:36:30.562295: step: 1216/529, loss: 0.00848670955747366
2023-01-24 05:36:31.603491: step: 1220/529, loss: 0.01083903294056654
2023-01-24 05:36:32.649113: step: 1224/529, loss: 0.015806326642632484
2023-01-24 05:36:33.710740: step: 1228/529, loss: 0.007597902789711952
2023-01-24 05:36:34.751238: step: 1232/529, loss: 0.0015265881083905697
2023-01-24 05:36:35.799111: step: 1236/529, loss: 0.008632718585431576
2023-01-24 05:36:36.845791: step: 1240/529, loss: 0.03639453276991844
2023-01-24 05:36:37.914940: step: 1244/529, loss: 0.014228655956685543
2023-01-24 05:36:38.957986: step: 1248/529, loss: 0.02356448397040367
2023-01-24 05:36:40.010616: step: 1252/529, loss: 0.0028892129193991423
2023-01-24 05:36:41.055107: step: 1256/529, loss: 0.020002085715532303
2023-01-24 05:36:42.092269: step: 1260/529, loss: 0.006404080428183079
2023-01-24 05:36:43.139519: step: 1264/529, loss: 0.03517806529998779
2023-01-24 05:36:44.184811: step: 1268/529, loss: 0.015657609328627586
2023-01-24 05:36:45.237672: step: 1272/529, loss: 0.012968228198587894
2023-01-24 05:36:46.283318: step: 1276/529, loss: 0.007121562957763672
2023-01-24 05:36:47.336523: step: 1280/529, loss: 0.031889598816633224
2023-01-24 05:36:48.383287: step: 1284/529, loss: 0.005741504952311516
2023-01-24 05:36:49.472545: step: 1288/529, loss: 0.024667486548423767
2023-01-24 05:36:50.535271: step: 1292/529, loss: 0.050742294639348984
2023-01-24 05:36:51.591233: step: 1296/529, loss: 0.008235281333327293
2023-01-24 05:36:52.628771: step: 1300/529, loss: 0.00891843717545271
2023-01-24 05:36:53.678346: step: 1304/529, loss: 0.00452026491984725
2023-01-24 05:36:54.736478: step: 1308/529, loss: 0.004861308261752129
2023-01-24 05:36:55.792151: step: 1312/529, loss: 0.01076226681470871
2023-01-24 05:36:56.871248: step: 1316/529, loss: 0.022111037746071815
2023-01-24 05:36:57.921622: step: 1320/529, loss: 0.019388973712921143
2023-01-24 05:36:58.968732: step: 1324/529, loss: 0.005586306098848581
2023-01-24 05:37:00.022109: step: 1328/529, loss: 0.006610429380089045
2023-01-24 05:37:01.072124: step: 1332/529, loss: 0.007396426983177662
2023-01-24 05:37:02.118519: step: 1336/529, loss: 0.003939315211027861
2023-01-24 05:37:03.184517: step: 1340/529, loss: 0.005185093265026808
2023-01-24 05:37:04.241761: step: 1344/529, loss: 0.010334577411413193
2023-01-24 05:37:05.293539: step: 1348/529, loss: 0.00763534102588892
2023-01-24 05:37:06.360832: step: 1352/529, loss: 0.001809293869882822
2023-01-24 05:37:07.403538: step: 1356/529, loss: 0.009515292942523956
2023-01-24 05:37:08.451695: step: 1360/529, loss: 0.0022127137053757906
2023-01-24 05:37:09.497037: step: 1364/529, loss: 0.005330778658390045
2023-01-24 05:37:10.535256: step: 1368/529, loss: 0.013178571127355099
2023-01-24 05:37:11.591806: step: 1372/529, loss: 0.008235168643295765
2023-01-24 05:37:12.664266: step: 1376/529, loss: 0.0032991915941238403
2023-01-24 05:37:13.713119: step: 1380/529, loss: 0.039646901190280914
2023-01-24 05:37:14.784961: step: 1384/529, loss: 0.09910629689693451
2023-01-24 05:37:15.842028: step: 1388/529, loss: 0.006392909213900566
2023-01-24 05:37:16.889671: step: 1392/529, loss: 0.006639172323048115
2023-01-24 05:37:17.942835: step: 1396/529, loss: 0.004099604208022356
2023-01-24 05:37:18.992195: step: 1400/529, loss: 0.04006190970540047
2023-01-24 05:37:20.046592: step: 1404/529, loss: 0.026349922642111778
2023-01-24 05:37:21.087192: step: 1408/529, loss: 0.004725749138742685
2023-01-24 05:37:22.124660: step: 1412/529, loss: 0.02060350403189659
2023-01-24 05:37:23.183485: step: 1416/529, loss: 0.005630532745271921
2023-01-24 05:37:24.246443: step: 1420/529, loss: 0.005727951880544424
2023-01-24 05:37:25.276888: step: 1424/529, loss: 0.006338499952107668
2023-01-24 05:37:26.340566: step: 1428/529, loss: 0.007026389241218567
2023-01-24 05:37:27.398523: step: 1432/529, loss: 0.006613961886614561
2023-01-24 05:37:28.435594: step: 1436/529, loss: 0.007747239898890257
2023-01-24 05:37:29.483060: step: 1440/529, loss: 0.003882375545799732
2023-01-24 05:37:30.535183: step: 1444/529, loss: 0.006315236911177635
2023-01-24 05:37:31.592768: step: 1448/529, loss: 0.01657625287771225
2023-01-24 05:37:32.655249: step: 1452/529, loss: 0.10470747202634811
2023-01-24 05:37:33.699862: step: 1456/529, loss: 0.024988019838929176
2023-01-24 05:37:34.743817: step: 1460/529, loss: 0.00462451484054327
2023-01-24 05:37:35.784849: step: 1464/529, loss: 0.0057892827317118645
2023-01-24 05:37:36.852545: step: 1468/529, loss: 0.0042790574952960014
2023-01-24 05:37:37.910963: step: 1472/529, loss: 0.0398414246737957
2023-01-24 05:37:38.972775: step: 1476/529, loss: 0.004792596213519573
2023-01-24 05:37:40.018185: step: 1480/529, loss: 0.008492857217788696
2023-01-24 05:37:41.068501: step: 1484/529, loss: 0.009868143126368523
2023-01-24 05:37:42.131535: step: 1488/529, loss: 0.003622837597504258
2023-01-24 05:37:43.161071: step: 1492/529, loss: 0.0035666325129568577
2023-01-24 05:37:44.229360: step: 1496/529, loss: 0.003052003914490342
2023-01-24 05:37:45.290744: step: 1500/529, loss: 0.0025895137805491686
2023-01-24 05:37:46.327828: step: 1504/529, loss: 0.004610867239534855
2023-01-24 05:37:47.367335: step: 1508/529, loss: 0.0033706333488225937
2023-01-24 05:37:48.417153: step: 1512/529, loss: 0.0006292694015428424
2023-01-24 05:37:49.468059: step: 1516/529, loss: 0.0029224965255707502
2023-01-24 05:37:50.505591: step: 1520/529, loss: 0.005507317371666431
2023-01-24 05:37:51.555247: step: 1524/529, loss: 0.013604824431240559
2023-01-24 05:37:52.605950: step: 1528/529, loss: 0.009229722432792187
2023-01-24 05:37:53.661229: step: 1532/529, loss: 0.002615570090711117
2023-01-24 05:37:54.703418: step: 1536/529, loss: 0.03387366980314255
2023-01-24 05:37:55.760522: step: 1540/529, loss: 0.03629336133599281
2023-01-24 05:37:56.821384: step: 1544/529, loss: 0.010828995145857334
2023-01-24 05:37:57.874157: step: 1548/529, loss: 0.04535053297877312
2023-01-24 05:37:58.929609: step: 1552/529, loss: 0.004056266508996487
2023-01-24 05:37:59.978899: step: 1556/529, loss: 0.01961745321750641
2023-01-24 05:38:01.040445: step: 1560/529, loss: 0.0023532933555543423
2023-01-24 05:38:02.117196: step: 1564/529, loss: 0.005861486308276653
2023-01-24 05:38:03.174213: step: 1568/529, loss: 0.005907162092626095
2023-01-24 05:38:04.226284: step: 1572/529, loss: 0.038817085325717926
2023-01-24 05:38:05.289660: step: 1576/529, loss: 0.004155512899160385
2023-01-24 05:38:06.336175: step: 1580/529, loss: 0.019145265221595764
2023-01-24 05:38:07.397707: step: 1584/529, loss: 0.01050573494285345
2023-01-24 05:38:08.442228: step: 1588/529, loss: 0.030349288135766983
2023-01-24 05:38:09.495333: step: 1592/529, loss: 0.010635003447532654
2023-01-24 05:38:10.539355: step: 1596/529, loss: 0.0036935261450707912
2023-01-24 05:38:11.561337: step: 1600/529, loss: 0.003251268295571208
2023-01-24 05:38:12.594334: step: 1604/529, loss: 0.005543887615203857
2023-01-24 05:38:13.655271: step: 1608/529, loss: 0.006734075490385294
2023-01-24 05:38:14.711490: step: 1612/529, loss: 0.0661957636475563
2023-01-24 05:38:15.753941: step: 1616/529, loss: 0.028330544009804726
2023-01-24 05:38:16.795721: step: 1620/529, loss: 0.009527577087283134
2023-01-24 05:38:17.826870: step: 1624/529, loss: 0.005371913313865662
2023-01-24 05:38:18.879327: step: 1628/529, loss: 0.015321719460189342
2023-01-24 05:38:19.954290: step: 1632/529, loss: 0.02746753580868244
2023-01-24 05:38:20.992573: step: 1636/529, loss: 0.006988075096160173
2023-01-24 05:38:22.053051: step: 1640/529, loss: 0.07256995886564255
2023-01-24 05:38:23.091008: step: 1644/529, loss: 0.007382863201200962
2023-01-24 05:38:24.134468: step: 1648/529, loss: 0.008030509576201439
2023-01-24 05:38:25.179498: step: 1652/529, loss: 0.013200175948441029
2023-01-24 05:38:26.235014: step: 1656/529, loss: 0.0049641928635537624
2023-01-24 05:38:27.288889: step: 1660/529, loss: 0.014688693918287754
2023-01-24 05:38:28.322237: step: 1664/529, loss: 0.005491009913384914
2023-01-24 05:38:29.362275: step: 1668/529, loss: 0.008575434796512127
2023-01-24 05:38:30.410006: step: 1672/529, loss: 0.0077672600746154785
2023-01-24 05:38:31.463195: step: 1676/529, loss: 0.007272324524819851
2023-01-24 05:38:32.517742: step: 1680/529, loss: 0.003114038612693548
2023-01-24 05:38:33.568524: step: 1684/529, loss: 0.036389756947755814
2023-01-24 05:38:34.633312: step: 1688/529, loss: 0.00475142989307642
2023-01-24 05:38:35.674833: step: 1692/529, loss: 0.0025000954046845436
2023-01-24 05:38:36.715004: step: 1696/529, loss: 0.004743554629385471
2023-01-24 05:38:37.771695: step: 1700/529, loss: 0.0030509463977068663
2023-01-24 05:38:38.818075: step: 1704/529, loss: 0.033920906484127045
2023-01-24 05:38:39.885001: step: 1708/529, loss: 0.012621713802218437
2023-01-24 05:38:40.959161: step: 1712/529, loss: 0.007365634199231863
2023-01-24 05:38:42.001646: step: 1716/529, loss: 0.008016137406229973
2023-01-24 05:38:43.055257: step: 1720/529, loss: 0.0019524346571415663
2023-01-24 05:38:44.094100: step: 1724/529, loss: 0.040085408836603165
2023-01-24 05:38:45.154419: step: 1728/529, loss: 0.007748884614557028
2023-01-24 05:38:46.191068: step: 1732/529, loss: 0.012218799442052841
2023-01-24 05:38:47.217501: step: 1736/529, loss: 0.00045600938028655946
2023-01-24 05:38:48.278868: step: 1740/529, loss: 0.008562753908336163
2023-01-24 05:38:49.326590: step: 1744/529, loss: 0.014135128818452358
2023-01-24 05:38:50.374506: step: 1748/529, loss: 0.037984106689691544
2023-01-24 05:38:51.435608: step: 1752/529, loss: 0.003595915623009205
2023-01-24 05:38:52.470493: step: 1756/529, loss: 0.00888009276241064
2023-01-24 05:38:53.515346: step: 1760/529, loss: 0.0021698069758713245
2023-01-24 05:38:54.546576: step: 1764/529, loss: 0.01275579258799553
2023-01-24 05:38:55.583401: step: 1768/529, loss: 0.020149672403931618
2023-01-24 05:38:56.646532: step: 1772/529, loss: 0.014540082775056362
2023-01-24 05:38:57.705744: step: 1776/529, loss: 0.07143697887659073
2023-01-24 05:38:58.753437: step: 1780/529, loss: 0.001856763381510973
2023-01-24 05:38:59.783905: step: 1784/529, loss: 0.001417514868080616
2023-01-24 05:39:00.822962: step: 1788/529, loss: 0.0062180873937904835
2023-01-24 05:39:01.886876: step: 1792/529, loss: 0.004356327001005411
2023-01-24 05:39:02.948064: step: 1796/529, loss: 0.010803253389894962
2023-01-24 05:39:04.006414: step: 1800/529, loss: 0.01248183473944664
2023-01-24 05:39:05.048498: step: 1804/529, loss: 0.04637638479471207
2023-01-24 05:39:06.096225: step: 1808/529, loss: 0.011410241015255451
2023-01-24 05:39:07.127944: step: 1812/529, loss: 0.0009561876649968326
2023-01-24 05:39:08.181101: step: 1816/529, loss: 0.08122409880161285
2023-01-24 05:39:09.211395: step: 1820/529, loss: 0.021820086985826492
2023-01-24 05:39:10.259581: step: 1824/529, loss: 0.0022133137099444866
2023-01-24 05:39:11.299806: step: 1828/529, loss: 0.032528430223464966
2023-01-24 05:39:12.352164: step: 1832/529, loss: 0.005764440633356571
2023-01-24 05:39:13.396712: step: 1836/529, loss: 0.004100393038243055
2023-01-24 05:39:14.451426: step: 1840/529, loss: 0.007540260907262564
2023-01-24 05:39:15.506914: step: 1844/529, loss: 0.006106378044933081
2023-01-24 05:39:16.569180: step: 1848/529, loss: 0.009126215241849422
2023-01-24 05:39:17.612512: step: 1852/529, loss: 0.04526838660240173
2023-01-24 05:39:18.661147: step: 1856/529, loss: 0.008118906058371067
2023-01-24 05:39:19.709865: step: 1860/529, loss: 0.017415540292859077
2023-01-24 05:39:20.773135: step: 1864/529, loss: 0.018857847899198532
2023-01-24 05:39:21.818653: step: 1868/529, loss: 0.004406822379678488
2023-01-24 05:39:22.872118: step: 1872/529, loss: 0.053060151636600494
2023-01-24 05:39:23.930815: step: 1876/529, loss: 0.0066854082979261875
2023-01-24 05:39:24.978182: step: 1880/529, loss: 0.006910445634275675
2023-01-24 05:39:26.046691: step: 1884/529, loss: 0.011445866897702217
2023-01-24 05:39:27.107797: step: 1888/529, loss: 0.012498559430241585
2023-01-24 05:39:28.142622: step: 1892/529, loss: 0.010547908022999763
2023-01-24 05:39:29.183796: step: 1896/529, loss: 0.019504351541399956
2023-01-24 05:39:30.242461: step: 1900/529, loss: 0.012519661337137222
2023-01-24 05:39:31.287987: step: 1904/529, loss: 0.008370031602680683
2023-01-24 05:39:32.340189: step: 1908/529, loss: 0.0030402480624616146
2023-01-24 05:39:33.405473: step: 1912/529, loss: 0.012232047505676746
2023-01-24 05:39:34.474706: step: 1916/529, loss: 0.001376642961986363
2023-01-24 05:39:35.526401: step: 1920/529, loss: 0.01706608571112156
2023-01-24 05:39:36.571960: step: 1924/529, loss: 0.009613309055566788
2023-01-24 05:39:37.619200: step: 1928/529, loss: 0.0331423357129097
2023-01-24 05:39:38.663472: step: 1932/529, loss: 0.007739585358649492
2023-01-24 05:39:39.707877: step: 1936/529, loss: 0.007921899668872356
2023-01-24 05:39:40.733949: step: 1940/529, loss: 0.007345499936491251
2023-01-24 05:39:41.785829: step: 1944/529, loss: 0.005489768460392952
2023-01-24 05:39:42.823313: step: 1948/529, loss: 0.014905540272593498
2023-01-24 05:39:43.864839: step: 1952/529, loss: 0.01877637952566147
2023-01-24 05:39:44.891614: step: 1956/529, loss: 0.006906555034220219
2023-01-24 05:39:45.942126: step: 1960/529, loss: 0.01362372562289238
2023-01-24 05:39:46.977875: step: 1964/529, loss: 0.020083505660295486
2023-01-24 05:39:48.034769: step: 1968/529, loss: 0.0038358040619641542
2023-01-24 05:39:49.069613: step: 1972/529, loss: 0.0048320540226995945
2023-01-24 05:39:50.133341: step: 1976/529, loss: 0.0037067104130983353
2023-01-24 05:39:51.198278: step: 1980/529, loss: 0.04109601303935051
2023-01-24 05:39:52.249254: step: 1984/529, loss: 0.0031430714298039675
2023-01-24 05:39:53.305387: step: 1988/529, loss: 0.001824588980525732
2023-01-24 05:39:54.367149: step: 1992/529, loss: 0.025527898222208023
2023-01-24 05:39:55.421467: step: 1996/529, loss: 0.025560569018125534
2023-01-24 05:39:56.462468: step: 2000/529, loss: 0.014694432727992535
2023-01-24 05:39:57.512952: step: 2004/529, loss: 0.014217589050531387
2023-01-24 05:39:58.556856: step: 2008/529, loss: 0.006769063416868448
2023-01-24 05:39:59.613821: step: 2012/529, loss: 0.004187212325632572
2023-01-24 05:40:00.655430: step: 2016/529, loss: 0.007873183116316795
2023-01-24 05:40:01.702849: step: 2020/529, loss: 0.007136023137718439
2023-01-24 05:40:02.758422: step: 2024/529, loss: 0.01103308517485857
2023-01-24 05:40:03.804550: step: 2028/529, loss: 0.02309064380824566
2023-01-24 05:40:04.856890: step: 2032/529, loss: 0.003891361178830266
2023-01-24 05:40:05.906451: step: 2036/529, loss: 0.006231565494090319
2023-01-24 05:40:06.944189: step: 2040/529, loss: 0.013575805351138115
2023-01-24 05:40:07.991629: step: 2044/529, loss: 0.01943735033273697
2023-01-24 05:40:09.045558: step: 2048/529, loss: 0.004879387095570564
2023-01-24 05:40:10.100406: step: 2052/529, loss: 0.028755979612469673
2023-01-24 05:40:11.140639: step: 2056/529, loss: 0.0026007622946053743
2023-01-24 05:40:12.176097: step: 2060/529, loss: 0.019823603332042694
2023-01-24 05:40:13.238368: step: 2064/529, loss: 0.009842712432146072
2023-01-24 05:40:14.294472: step: 2068/529, loss: 0.020212415605783463
2023-01-24 05:40:15.350035: step: 2072/529, loss: 0.01061770785599947
2023-01-24 05:40:16.404106: step: 2076/529, loss: 0.027065467089414597
2023-01-24 05:40:17.454216: step: 2080/529, loss: 0.021899422630667686
2023-01-24 05:40:18.510179: step: 2084/529, loss: 0.015626907348632812
2023-01-24 05:40:19.558860: step: 2088/529, loss: 0.00826290063560009
2023-01-24 05:40:20.599739: step: 2092/529, loss: 0.006980634294450283
2023-01-24 05:40:21.651662: step: 2096/529, loss: 0.005161152221262455
2023-01-24 05:40:22.692774: step: 2100/529, loss: 1.7548653659105184e-06
2023-01-24 05:40:23.742577: step: 2104/529, loss: 0.01337167713791132
2023-01-24 05:40:24.797376: step: 2108/529, loss: 0.009191742166876793
2023-01-24 05:40:25.836905: step: 2112/529, loss: 0.01953154243528843
2023-01-24 05:40:26.879927: step: 2116/529, loss: 0.014801283366978168
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3221068787958806, 'r': 0.33066379777717536, 'f1': 0.32632925361155696}, 'combined': 0.2404531342400946, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3673985304588615, 'r': 0.30103596867440746, 'f1': 0.33092299290251415}, 'combined': 0.23281014576056272, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3798837970511898, 'r': 0.3474459016673121, 'f1': 0.36294150679618137}, 'combined': 0.267430583955081, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3966877164107804, 'r': 0.3114604865094249, 'f1': 0.3489454569993068}, 'combined': 0.24775127446950782, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 2}
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': 0.32651086087420045, 'r': 0.33208694768229874, 'f1': 0.3292752990189491}, 'combined': 0.24262390454027827, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37074014872703925, 'r': 0.30474452015782805, 'f1': 0.3345184100583055}, 'combined': 0.23533958496564208, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3798837970511898, 'r': 0.3474459016673121, 'f1': 0.36294150679618137}, 'combined': 0.267430583955081, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3966877164107804, 'r': 0.3114604865094249, 'f1': 0.3489454569993068}, 'combined': 0.24775127446950782, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:43:12.328387: step: 4/529, loss: 0.0208442322909832
2023-01-24 05:43:13.369074: step: 8/529, loss: 0.012691561132669449
2023-01-24 05:43:14.414175: step: 12/529, loss: 0.01606355980038643
2023-01-24 05:43:15.445977: step: 16/529, loss: 0.011063763871788979
2023-01-24 05:43:16.495886: step: 20/529, loss: 0.010010536760091782
2023-01-24 05:43:17.521965: step: 24/529, loss: 0.006352666299790144
2023-01-24 05:43:18.549896: step: 28/529, loss: 0.009280327707529068
2023-01-24 05:43:19.571811: step: 32/529, loss: 0.0015990022802725434
2023-01-24 05:43:20.616802: step: 36/529, loss: 0.0035235313698649406
2023-01-24 05:43:21.659819: step: 40/529, loss: 0.020566530525684357
2023-01-24 05:43:22.720878: step: 44/529, loss: 0.014135626144707203
2023-01-24 05:43:23.760949: step: 48/529, loss: 0.01160863321274519
2023-01-24 05:43:24.813311: step: 52/529, loss: 0.005531683564186096
2023-01-24 05:43:25.838975: step: 56/529, loss: 4.929221177008003e-06
2023-01-24 05:43:26.892275: step: 60/529, loss: 0.01231343112885952
2023-01-24 05:43:27.933176: step: 64/529, loss: 0.006655183155089617
2023-01-24 05:43:28.969134: step: 68/529, loss: 0.012532497756183147
2023-01-24 05:43:30.026911: step: 72/529, loss: 0.006677405908703804
2023-01-24 05:43:31.070073: step: 76/529, loss: 0.012505155988037586
2023-01-24 05:43:32.109803: step: 80/529, loss: 0.011351573280990124
2023-01-24 05:43:33.156906: step: 84/529, loss: 0.007938939146697521
2023-01-24 05:43:34.231529: step: 88/529, loss: 0.01606198027729988
2023-01-24 05:43:35.276024: step: 92/529, loss: 0.03394055366516113
2023-01-24 05:43:36.315722: step: 96/529, loss: 0.020595764741301537
2023-01-24 05:43:37.361358: step: 100/529, loss: 0.0067069679498672485
2023-01-24 05:43:38.403996: step: 104/529, loss: 0.005074886605143547
2023-01-24 05:43:39.445898: step: 108/529, loss: 0.006034509278833866
2023-01-24 05:43:40.491107: step: 112/529, loss: 0.004844900220632553
2023-01-24 05:43:41.532503: step: 116/529, loss: 0.023634810000658035
2023-01-24 05:43:42.573139: step: 120/529, loss: 0.006076115649193525
2023-01-24 05:43:43.618116: step: 124/529, loss: 0.02622343599796295
2023-01-24 05:43:44.663826: step: 128/529, loss: 0.005706985015422106
2023-01-24 05:43:45.701086: step: 132/529, loss: 0.024679511785507202
2023-01-24 05:43:46.757458: step: 136/529, loss: 0.010190864093601704
2023-01-24 05:43:47.798006: step: 140/529, loss: 0.004191117361187935
2023-01-24 05:43:48.825930: step: 144/529, loss: 0.013690647669136524
2023-01-24 05:43:49.885359: step: 148/529, loss: 0.008994690142571926
2023-01-24 05:43:50.922995: step: 152/529, loss: 0.01983303762972355
2023-01-24 05:43:51.959013: step: 156/529, loss: 0.0020555160008370876
2023-01-24 05:43:52.995273: step: 160/529, loss: 0.00725891487672925
2023-01-24 05:43:54.040504: step: 164/529, loss: 0.013728871010243893
2023-01-24 05:43:55.090629: step: 168/529, loss: 0.009484872221946716
2023-01-24 05:43:56.136359: step: 172/529, loss: 0.009091203100979328
2023-01-24 05:43:57.171392: step: 176/529, loss: 0.010535717010498047
2023-01-24 05:43:58.203149: step: 180/529, loss: 0.03529338538646698
2023-01-24 05:43:59.242526: step: 184/529, loss: 0.003982928115874529
2023-01-24 05:44:00.290210: step: 188/529, loss: 0.01871403492987156
2023-01-24 05:44:01.335027: step: 192/529, loss: 0.03191760554909706
2023-01-24 05:44:02.411625: step: 196/529, loss: 0.0031718104146420956
2023-01-24 05:44:03.448708: step: 200/529, loss: 0.003036828013136983
2023-01-24 05:44:04.488616: step: 204/529, loss: 0.02409512922167778
2023-01-24 05:44:05.546771: step: 208/529, loss: 0.0219293013215065
2023-01-24 05:44:06.586485: step: 212/529, loss: 0.0011673939879983664
2023-01-24 05:44:07.630995: step: 216/529, loss: 0.001010302104987204
2023-01-24 05:44:08.681635: step: 220/529, loss: 0.002797893015667796
2023-01-24 05:44:09.728798: step: 224/529, loss: 0.0021156298462301493
2023-01-24 05:44:10.762976: step: 228/529, loss: 0.008352869190275669
2023-01-24 05:44:11.812641: step: 232/529, loss: 0.005403296090662479
2023-01-24 05:44:12.847839: step: 236/529, loss: 0.005087476689368486
2023-01-24 05:44:13.898009: step: 240/529, loss: 0.009882204234600067
2023-01-24 05:44:14.950954: step: 244/529, loss: 0.004028747323900461
2023-01-24 05:44:15.984125: step: 248/529, loss: 0.0029030530713498592
2023-01-24 05:44:17.030934: step: 252/529, loss: 0.03338465094566345
2023-01-24 05:44:18.063595: step: 256/529, loss: 0.0006526591023430228
2023-01-24 05:44:19.129862: step: 260/529, loss: 0.008654743432998657
2023-01-24 05:44:20.190611: step: 264/529, loss: 0.009621884673833847
2023-01-24 05:44:21.238913: step: 268/529, loss: 0.005640773568302393
2023-01-24 05:44:22.287297: step: 272/529, loss: 0.002039456507191062
2023-01-24 05:44:23.339245: step: 276/529, loss: 0.028312239795923233
2023-01-24 05:44:24.381502: step: 280/529, loss: 0.0019282049033790827
2023-01-24 05:44:25.414396: step: 284/529, loss: 0.00046667290735058486
2023-01-24 05:44:26.453517: step: 288/529, loss: 0.015825647860765457
2023-01-24 05:44:27.504456: step: 292/529, loss: 0.03494861721992493
2023-01-24 05:44:28.536015: step: 296/529, loss: 0.005160809960216284
2023-01-24 05:44:29.592993: step: 300/529, loss: 0.023768030107021332
2023-01-24 05:44:30.649358: step: 304/529, loss: 0.01773795112967491
2023-01-24 05:44:31.715771: step: 308/529, loss: 0.010129460133612156
2023-01-24 05:44:32.754013: step: 312/529, loss: 0.012912639416754246
2023-01-24 05:44:33.797814: step: 316/529, loss: 0.0030903536826372147
2023-01-24 05:44:34.856006: step: 320/529, loss: 0.003855168353766203
2023-01-24 05:44:35.898425: step: 324/529, loss: 0.000534023973159492
2023-01-24 05:44:36.951095: step: 328/529, loss: 0.0013166150311008096
2023-01-24 05:44:37.994465: step: 332/529, loss: 0.008628039620816708
2023-01-24 05:44:39.038159: step: 336/529, loss: 0.005714814644306898
2023-01-24 05:44:40.090226: step: 340/529, loss: 0.0032538832165300846
2023-01-24 05:44:41.132852: step: 344/529, loss: 0.03416123986244202
2023-01-24 05:44:42.169131: step: 348/529, loss: 0.005888884421437979
2023-01-24 05:44:43.250867: step: 352/529, loss: 0.01538755465298891
2023-01-24 05:44:44.295812: step: 356/529, loss: 0.007395452819764614
2023-01-24 05:44:45.341449: step: 360/529, loss: 0.011833365075290203
2023-01-24 05:44:46.381913: step: 364/529, loss: 0.013952210545539856
2023-01-24 05:44:47.426098: step: 368/529, loss: 0.007630400359630585
2023-01-24 05:44:48.467138: step: 372/529, loss: 0.005060497671365738
2023-01-24 05:44:49.514999: step: 376/529, loss: 0.0363008975982666
2023-01-24 05:44:50.584723: step: 380/529, loss: 0.009673144668340683
2023-01-24 05:44:51.626298: step: 384/529, loss: 0.01499855238944292
2023-01-24 05:44:52.689428: step: 388/529, loss: 0.035699956119060516
2023-01-24 05:44:53.772705: step: 392/529, loss: 0.004454293288290501
2023-01-24 05:44:54.824651: step: 396/529, loss: 0.03605381026864052
2023-01-24 05:44:55.866783: step: 400/529, loss: 0.003094918094575405
2023-01-24 05:44:56.907130: step: 404/529, loss: 0.0022648752201348543
2023-01-24 05:44:57.939013: step: 408/529, loss: 0.000579286424908787
2023-01-24 05:44:58.983723: step: 412/529, loss: 0.004001363646239042
2023-01-24 05:45:00.015678: step: 416/529, loss: 6.269874575082213e-05
2023-01-24 05:45:01.071833: step: 420/529, loss: 0.010995334014296532
2023-01-24 05:45:02.123754: step: 424/529, loss: 0.014665324240922928
2023-01-24 05:45:03.167426: step: 428/529, loss: 0.008718844503164291
2023-01-24 05:45:04.223163: step: 432/529, loss: 0.00610192259773612
2023-01-24 05:45:05.271359: step: 436/529, loss: 0.007937761023640633
2023-01-24 05:45:06.349451: step: 440/529, loss: 0.006486135069280863
2023-01-24 05:45:07.378624: step: 444/529, loss: 0.00448181014508009
2023-01-24 05:45:08.424433: step: 448/529, loss: 0.0032839749474078417
2023-01-24 05:45:09.480933: step: 452/529, loss: 0.022131407633423805
2023-01-24 05:45:10.533654: step: 456/529, loss: 0.002007158938795328
2023-01-24 05:45:11.567553: step: 460/529, loss: 0.008322598412632942
2023-01-24 05:45:12.610078: step: 464/529, loss: 0.030704252421855927
2023-01-24 05:45:13.649682: step: 468/529, loss: 0.003225067863240838
2023-01-24 05:45:14.684407: step: 472/529, loss: 0.005971058737486601
2023-01-24 05:45:15.714145: step: 476/529, loss: 0.003775882301852107
2023-01-24 05:45:16.752152: step: 480/529, loss: 0.008580246940255165
2023-01-24 05:45:17.791412: step: 484/529, loss: 0.0051669105887413025
2023-01-24 05:45:18.833112: step: 488/529, loss: 0.002639737445861101
2023-01-24 05:45:19.871594: step: 492/529, loss: 0.004285009112209082
2023-01-24 05:45:20.920761: step: 496/529, loss: 0.007803808897733688
2023-01-24 05:45:21.963983: step: 500/529, loss: 0.0030957337003201246
2023-01-24 05:45:23.031319: step: 504/529, loss: 0.0022118673659861088
2023-01-24 05:45:24.068525: step: 508/529, loss: 0.013683885335922241
2023-01-24 05:45:25.120656: step: 512/529, loss: 0.005295691546052694
2023-01-24 05:45:26.205885: step: 516/529, loss: 0.00547033129259944
2023-01-24 05:45:27.250945: step: 520/529, loss: 0.011031736619770527
2023-01-24 05:45:28.302527: step: 524/529, loss: 0.007539558690041304
2023-01-24 05:45:29.347361: step: 528/529, loss: 0.0042389435693621635
2023-01-24 05:45:30.390799: step: 532/529, loss: 0.007577598560601473
2023-01-24 05:45:31.419756: step: 536/529, loss: 0.012358488515019417
2023-01-24 05:45:32.455316: step: 540/529, loss: 0.00582906836643815
2023-01-24 05:45:33.507984: step: 544/529, loss: 0.0047879330813884735
2023-01-24 05:45:34.554599: step: 548/529, loss: 0.006215913221240044
2023-01-24 05:45:35.600176: step: 552/529, loss: 0.009544332511723042
2023-01-24 05:45:36.640007: step: 556/529, loss: 0.005756858270615339
2023-01-24 05:45:37.673925: step: 560/529, loss: 0.032766226679086685
2023-01-24 05:45:38.713642: step: 564/529, loss: 0.004622172098606825
2023-01-24 05:45:39.788399: step: 568/529, loss: 0.004793106112629175
2023-01-24 05:45:40.840119: step: 572/529, loss: 0.00674926582723856
2023-01-24 05:45:41.890886: step: 576/529, loss: 0.022429246455430984
2023-01-24 05:45:42.937317: step: 580/529, loss: 0.00271551962941885
2023-01-24 05:45:43.993369: step: 584/529, loss: 0.04102171212434769
2023-01-24 05:45:45.020327: step: 588/529, loss: 0.0070463139563798904
2023-01-24 05:45:46.070444: step: 592/529, loss: 0.017212038859725
2023-01-24 05:45:47.119318: step: 596/529, loss: 0.004826388321816921
2023-01-24 05:45:48.175628: step: 600/529, loss: 0.0104568712413311
2023-01-24 05:45:49.239709: step: 604/529, loss: 0.009162485599517822
2023-01-24 05:45:50.277424: step: 608/529, loss: 0.0017922725528478622
2023-01-24 05:45:51.325021: step: 612/529, loss: 0.003059778129681945
2023-01-24 05:45:52.376928: step: 616/529, loss: 0.008877222426235676
2023-01-24 05:45:53.422010: step: 620/529, loss: 0.000661179656162858
2023-01-24 05:45:54.466277: step: 624/529, loss: 0.021183345466852188
2023-01-24 05:45:55.496559: step: 628/529, loss: 0.007263918872922659
2023-01-24 05:45:56.540129: step: 632/529, loss: 0.05522396042943001
2023-01-24 05:45:57.591510: step: 636/529, loss: 0.001382191781885922
2023-01-24 05:45:58.632893: step: 640/529, loss: 0.00908604171127081
2023-01-24 05:45:59.661719: step: 644/529, loss: 0.0021070127841085196
2023-01-24 05:46:00.695024: step: 648/529, loss: 0.005988290533423424
2023-01-24 05:46:01.747487: step: 652/529, loss: 0.006849177181720734
2023-01-24 05:46:02.800987: step: 656/529, loss: 0.007633228320628405
2023-01-24 05:46:03.837361: step: 660/529, loss: 0.015383109450340271
2023-01-24 05:46:04.886844: step: 664/529, loss: 0.006174037698656321
2023-01-24 05:46:05.951322: step: 668/529, loss: 6.417378699552501e-06
2023-01-24 05:46:06.997332: step: 672/529, loss: 0.006210414692759514
2023-01-24 05:46:08.047792: step: 676/529, loss: 0.015877971425652504
2023-01-24 05:46:09.104456: step: 680/529, loss: 0.0027899490669369698
2023-01-24 05:46:10.159435: step: 684/529, loss: 0.02167505770921707
2023-01-24 05:46:11.215175: step: 688/529, loss: 0.007627988699823618
2023-01-24 05:46:12.258897: step: 692/529, loss: 0.0033301939256489277
2023-01-24 05:46:13.307846: step: 696/529, loss: 0.007913576439023018
2023-01-24 05:46:14.344608: step: 700/529, loss: 0.009650005027651787
2023-01-24 05:46:15.393577: step: 704/529, loss: 0.009845939464867115
2023-01-24 05:46:16.450850: step: 708/529, loss: 0.006602531764656305
2023-01-24 05:46:17.492266: step: 712/529, loss: 0.015772363170981407
2023-01-24 05:46:18.537934: step: 716/529, loss: 0.008152037858963013
2023-01-24 05:46:19.581162: step: 720/529, loss: 0.004063493572175503
2023-01-24 05:46:20.630159: step: 724/529, loss: 0.004320870153605938
2023-01-24 05:46:21.663352: step: 728/529, loss: 0.008242408744990826
2023-01-24 05:46:22.695261: step: 732/529, loss: 0.0031298690009862185
2023-01-24 05:46:23.734043: step: 736/529, loss: 0.004474529065191746
2023-01-24 05:46:24.790715: step: 740/529, loss: 0.012551347725093365
2023-01-24 05:46:25.852753: step: 744/529, loss: 0.01277049258351326
2023-01-24 05:46:26.886815: step: 748/529, loss: 0.00032135413493961096
2023-01-24 05:46:27.943879: step: 752/529, loss: 0.0009411997743882239
2023-01-24 05:46:28.971319: step: 756/529, loss: 0.05965364724397659
2023-01-24 05:46:30.011952: step: 760/529, loss: 0.00435011088848114
2023-01-24 05:46:31.053739: step: 764/529, loss: 0.008131771348416805
2023-01-24 05:46:32.105864: step: 768/529, loss: 0.007096108514815569
2023-01-24 05:46:33.148181: step: 772/529, loss: 0.008854346349835396
2023-01-24 05:46:34.182581: step: 776/529, loss: 0.0010187854059040546
2023-01-24 05:46:35.243155: step: 780/529, loss: 0.00849572941660881
2023-01-24 05:46:36.292762: step: 784/529, loss: 0.013858995400369167
2023-01-24 05:46:37.348846: step: 788/529, loss: 0.009879359975457191
2023-01-24 05:46:38.390399: step: 792/529, loss: 0.006350253242999315
2023-01-24 05:46:39.434162: step: 796/529, loss: 0.023349575698375702
2023-01-24 05:46:40.495958: step: 800/529, loss: 0.006229089573025703
2023-01-24 05:46:41.541487: step: 804/529, loss: 0.021389836445450783
2023-01-24 05:46:42.579928: step: 808/529, loss: 0.003919560927897692
2023-01-24 05:46:43.621074: step: 812/529, loss: 0.006096747703850269
2023-01-24 05:46:44.664600: step: 816/529, loss: 0.03172317519783974
2023-01-24 05:46:45.727491: step: 820/529, loss: 0.0035406118258833885
2023-01-24 05:46:46.753109: step: 824/529, loss: 0.009710850194096565
2023-01-24 05:46:47.789053: step: 828/529, loss: 0.006400146521627903
2023-01-24 05:46:48.830379: step: 832/529, loss: 0.005716054700314999
2023-01-24 05:46:49.869538: step: 836/529, loss: 0.0031776505056768656
2023-01-24 05:46:50.904732: step: 840/529, loss: 0.004783932119607925
2023-01-24 05:46:51.951930: step: 844/529, loss: 0.010583682917058468
2023-01-24 05:46:52.991961: step: 848/529, loss: 0.005367538891732693
2023-01-24 05:46:54.033925: step: 852/529, loss: 0.008427374996244907
2023-01-24 05:46:55.075539: step: 856/529, loss: 0.0007629571482539177
2023-01-24 05:46:56.107561: step: 860/529, loss: 0.010558458045125008
2023-01-24 05:46:57.160200: step: 864/529, loss: 0.003048550570383668
2023-01-24 05:46:58.221595: step: 868/529, loss: 0.002945945132523775
2023-01-24 05:46:59.283504: step: 872/529, loss: 0.007721399422734976
2023-01-24 05:47:00.325988: step: 876/529, loss: 0.01770276203751564
2023-01-24 05:47:01.370908: step: 880/529, loss: 0.00855009350925684
2023-01-24 05:47:02.426018: step: 884/529, loss: 0.0036043853033334017
2023-01-24 05:47:03.483603: step: 888/529, loss: 0.009992311708629131
2023-01-24 05:47:04.520547: step: 892/529, loss: 0.023117542266845703
2023-01-24 05:47:05.570299: step: 896/529, loss: 0.012532321736216545
2023-01-24 05:47:06.602558: step: 900/529, loss: 0.0018556644208729267
2023-01-24 05:47:07.653636: step: 904/529, loss: 0.004856654442846775
2023-01-24 05:47:08.708471: step: 908/529, loss: 0.019890183582901955
2023-01-24 05:47:09.739062: step: 912/529, loss: 0.007285080850124359
2023-01-24 05:47:10.774104: step: 916/529, loss: 0.0059034014120697975
2023-01-24 05:47:11.817389: step: 920/529, loss: 0.00897412933409214
2023-01-24 05:47:12.857267: step: 924/529, loss: 0.010564886964857578
2023-01-24 05:47:13.906441: step: 928/529, loss: 0.002053814474493265
2023-01-24 05:47:14.951717: step: 932/529, loss: 0.0012606256641447544
2023-01-24 05:47:16.013040: step: 936/529, loss: 0.005641499534249306
2023-01-24 05:47:17.061596: step: 940/529, loss: 0.005151058547198772
2023-01-24 05:47:18.118737: step: 944/529, loss: 0.004544899333268404
2023-01-24 05:47:19.169245: step: 948/529, loss: 0.004842931870371103
2023-01-24 05:47:20.206678: step: 952/529, loss: 0.01224144920706749
2023-01-24 05:47:21.250659: step: 956/529, loss: 0.011474881321191788
2023-01-24 05:47:22.300764: step: 960/529, loss: 0.0151266073808074
2023-01-24 05:47:23.354598: step: 964/529, loss: 0.047485072165727615
2023-01-24 05:47:24.398586: step: 968/529, loss: 0.016444802284240723
2023-01-24 05:47:25.431501: step: 972/529, loss: 0.014128783717751503
2023-01-24 05:47:26.485352: step: 976/529, loss: 0.04584663361310959
2023-01-24 05:47:27.530056: step: 980/529, loss: 0.0043280962854623795
2023-01-24 05:47:28.561001: step: 984/529, loss: 0.005949350539594889
2023-01-24 05:47:29.635547: step: 988/529, loss: 0.008175183087587357
2023-01-24 05:47:30.697130: step: 992/529, loss: 0.01832376793026924
2023-01-24 05:47:31.748458: step: 996/529, loss: 0.03893590718507767
2023-01-24 05:47:32.814403: step: 1000/529, loss: 0.006128888577222824
2023-01-24 05:47:33.868674: step: 1004/529, loss: 0.009077107533812523
2023-01-24 05:47:34.915864: step: 1008/529, loss: 0.015400653705000877
2023-01-24 05:47:35.969142: step: 1012/529, loss: 0.004606524482369423
2023-01-24 05:47:37.019370: step: 1016/529, loss: 0.00999111495912075
2023-01-24 05:47:38.073051: step: 1020/529, loss: 0.006618921644985676
2023-01-24 05:47:39.119674: step: 1024/529, loss: 0.03537015616893768
2023-01-24 05:47:40.158812: step: 1028/529, loss: 0.012193504720926285
2023-01-24 05:47:41.192574: step: 1032/529, loss: 0.010620943270623684
2023-01-24 05:47:42.240491: step: 1036/529, loss: 0.0030468408949673176
2023-01-24 05:47:43.291745: step: 1040/529, loss: 0.0024327056016772985
2023-01-24 05:47:44.335684: step: 1044/529, loss: 0.008371617645025253
2023-01-24 05:47:45.370776: step: 1048/529, loss: 0.0028606997802853584
2023-01-24 05:47:46.436110: step: 1052/529, loss: 0.008406925946474075
2023-01-24 05:47:47.492684: step: 1056/529, loss: 0.0023276079446077347
2023-01-24 05:47:48.561069: step: 1060/529, loss: 0.024634700268507004
2023-01-24 05:47:49.598358: step: 1064/529, loss: 0.007429181132465601
2023-01-24 05:47:50.655730: step: 1068/529, loss: 0.03736819699406624
2023-01-24 05:47:51.708789: step: 1072/529, loss: 0.011959219351410866
2023-01-24 05:47:52.764235: step: 1076/529, loss: 0.015632368624210358
2023-01-24 05:47:53.811370: step: 1080/529, loss: 0.0036548601929098368
2023-01-24 05:47:54.873989: step: 1084/529, loss: 0.009078995324671268
2023-01-24 05:47:55.922359: step: 1088/529, loss: 0.006588313262909651
2023-01-24 05:47:56.963800: step: 1092/529, loss: 0.006441383622586727
2023-01-24 05:47:58.009026: step: 1096/529, loss: 0.014562997967004776
2023-01-24 05:47:59.053729: step: 1100/529, loss: 0.005533707328140736
2023-01-24 05:48:00.110913: step: 1104/529, loss: 0.01959068700671196
2023-01-24 05:48:01.140882: step: 1108/529, loss: 0.0026985234580934048
2023-01-24 05:48:02.184786: step: 1112/529, loss: 0.005703798495233059
2023-01-24 05:48:03.219303: step: 1116/529, loss: 0.06922367215156555
2023-01-24 05:48:04.263918: step: 1120/529, loss: 0.015925617888569832
2023-01-24 05:48:05.332315: step: 1124/529, loss: 0.015083757229149342
2023-01-24 05:48:06.387479: step: 1128/529, loss: 0.018662579357624054
2023-01-24 05:48:07.444726: step: 1132/529, loss: 0.01122731901705265
2023-01-24 05:48:08.494539: step: 1136/529, loss: 0.004638632293790579
2023-01-24 05:48:09.547652: step: 1140/529, loss: 0.02509639598429203
2023-01-24 05:48:10.611312: step: 1144/529, loss: 0.09302464872598648
2023-01-24 05:48:11.655243: step: 1148/529, loss: 0.0030289706774055958
2023-01-24 05:48:12.697031: step: 1152/529, loss: 0.00594885041937232
2023-01-24 05:48:13.737067: step: 1156/529, loss: 0.006528529338538647
2023-01-24 05:48:14.774063: step: 1160/529, loss: 0.04342134669423103
2023-01-24 05:48:15.804386: step: 1164/529, loss: 0.02307465299963951
2023-01-24 05:48:16.846472: step: 1168/529, loss: 0.0072258529253304005
2023-01-24 05:48:17.928489: step: 1172/529, loss: 0.0020435911137610674
2023-01-24 05:48:18.977530: step: 1176/529, loss: 0.004534694366157055
2023-01-24 05:48:20.039844: step: 1180/529, loss: 0.016949469223618507
2023-01-24 05:48:21.089445: step: 1184/529, loss: 0.005833040457218885
2023-01-24 05:48:22.149628: step: 1188/529, loss: 0.009445838630199432
2023-01-24 05:48:23.185207: step: 1192/529, loss: 0.00451301783323288
2023-01-24 05:48:24.256071: step: 1196/529, loss: 0.00893206987529993
2023-01-24 05:48:25.329245: step: 1200/529, loss: 0.009515452198684216
2023-01-24 05:48:26.377875: step: 1204/529, loss: 0.0037146389950066805
2023-01-24 05:48:27.439593: step: 1208/529, loss: 0.0010736786061897874
2023-01-24 05:48:28.501813: step: 1212/529, loss: 0.004894861951470375
2023-01-24 05:48:29.553574: step: 1216/529, loss: 0.006374821998178959
2023-01-24 05:48:30.595724: step: 1220/529, loss: 0.005195472855120897
2023-01-24 05:48:31.646197: step: 1224/529, loss: 0.007244238164275885
2023-01-24 05:48:32.704507: step: 1228/529, loss: 0.004765903111547232
2023-01-24 05:48:33.761291: step: 1232/529, loss: 0.038049325346946716
2023-01-24 05:48:34.821710: step: 1236/529, loss: 0.027681902050971985
2023-01-24 05:48:35.882922: step: 1240/529, loss: 0.024872610345482826
2023-01-24 05:48:36.938682: step: 1244/529, loss: 0.007776146288961172
2023-01-24 05:48:37.997601: step: 1248/529, loss: 0.019104285165667534
2023-01-24 05:48:39.066107: step: 1252/529, loss: 0.0027267064433544874
2023-01-24 05:48:40.126703: step: 1256/529, loss: 0.0015529862139374018
2023-01-24 05:48:41.169206: step: 1260/529, loss: 0.004872492514550686
2023-01-24 05:48:42.219130: step: 1264/529, loss: 0.01610831916332245
2023-01-24 05:48:43.288113: step: 1268/529, loss: 0.0039037438109517097
2023-01-24 05:48:44.338112: step: 1272/529, loss: 0.00940401665866375
2023-01-24 05:48:45.415301: step: 1276/529, loss: 0.0041777146980166435
2023-01-24 05:48:46.470754: step: 1280/529, loss: 0.06750694662332535
2023-01-24 05:48:47.541661: step: 1284/529, loss: 0.04656890407204628
2023-01-24 05:48:48.604165: step: 1288/529, loss: 0.006866731680929661
2023-01-24 05:48:49.649551: step: 1292/529, loss: 0.005039165262132883
2023-01-24 05:48:50.727996: step: 1296/529, loss: 0.0035023544915020466
2023-01-24 05:48:51.804975: step: 1300/529, loss: 0.0032049373257905245
2023-01-24 05:48:52.847039: step: 1304/529, loss: 0.007449497934430838
2023-01-24 05:48:53.888081: step: 1308/529, loss: 0.003058676142245531
2023-01-24 05:48:54.944606: step: 1312/529, loss: 0.00487959198653698
2023-01-24 05:48:56.001182: step: 1316/529, loss: 0.002432426670566201
2023-01-24 05:48:57.063854: step: 1320/529, loss: 0.003428333904594183
2023-01-24 05:48:58.122218: step: 1324/529, loss: 0.00448904512450099
2023-01-24 05:48:59.176649: step: 1328/529, loss: 0.047091979533433914
2023-01-24 05:49:00.236910: step: 1332/529, loss: 0.031008722260594368
2023-01-24 05:49:01.298899: step: 1336/529, loss: 0.003948854748159647
2023-01-24 05:49:02.374144: step: 1340/529, loss: 0.01910504326224327
2023-01-24 05:49:03.439631: step: 1344/529, loss: 0.04447054862976074
2023-01-24 05:49:04.490288: step: 1348/529, loss: 0.009323792532086372
2023-01-24 05:49:05.534118: step: 1352/529, loss: 0.008373000659048557
2023-01-24 05:49:06.587181: step: 1356/529, loss: 0.007204152178019285
2023-01-24 05:49:07.673905: step: 1360/529, loss: 0.011526384390890598
2023-01-24 05:49:08.723109: step: 1364/529, loss: 0.04535789415240288
2023-01-24 05:49:09.772770: step: 1368/529, loss: 0.004789196420460939
2023-01-24 05:49:10.818523: step: 1372/529, loss: 0.004318946041166782
2023-01-24 05:49:11.882769: step: 1376/529, loss: 0.001332128420472145
2023-01-24 05:49:12.932943: step: 1380/529, loss: 0.0017280379543080926
2023-01-24 05:49:13.994178: step: 1384/529, loss: 0.01079876720905304
2023-01-24 05:49:15.044774: step: 1388/529, loss: 0.04532318562269211
2023-01-24 05:49:16.091031: step: 1392/529, loss: 0.010674613527953625
2023-01-24 05:49:17.145211: step: 1396/529, loss: 0.0007004258222877979
2023-01-24 05:49:18.194242: step: 1400/529, loss: 0.01211795024573803
2023-01-24 05:49:19.254514: step: 1404/529, loss: 0.0042478106915950775
2023-01-24 05:49:20.329113: step: 1408/529, loss: 0.015085237100720406
2023-01-24 05:49:21.396602: step: 1412/529, loss: 0.0063300905749201775
2023-01-24 05:49:22.456814: step: 1416/529, loss: 0.022326374426484108
2023-01-24 05:49:23.512342: step: 1420/529, loss: 0.011718065477907658
2023-01-24 05:49:24.559407: step: 1424/529, loss: 0.007911349646747112
2023-01-24 05:49:25.613694: step: 1428/529, loss: 0.022973133251070976
2023-01-24 05:49:26.672124: step: 1432/529, loss: 0.009008155204355717
2023-01-24 05:49:27.713332: step: 1436/529, loss: 0.00622814055532217
2023-01-24 05:49:28.753455: step: 1440/529, loss: 0.005001131910830736
2023-01-24 05:49:29.796644: step: 1444/529, loss: 0.02673487178981304
2023-01-24 05:49:30.843741: step: 1448/529, loss: 0.020341381430625916
2023-01-24 05:49:31.891247: step: 1452/529, loss: 0.0009337136289104819
2023-01-24 05:49:32.946679: step: 1456/529, loss: 0.029698602855205536
2023-01-24 05:49:34.003067: step: 1460/529, loss: 0.024077508598566055
2023-01-24 05:49:35.051589: step: 1464/529, loss: 0.023606255650520325
2023-01-24 05:49:36.127500: step: 1468/529, loss: 0.00319235073402524
2023-01-24 05:49:37.176025: step: 1472/529, loss: 0.010188245214521885
2023-01-24 05:49:38.235978: step: 1476/529, loss: 0.00591333257034421
2023-01-24 05:49:39.281471: step: 1480/529, loss: 0.00010252791253151372
2023-01-24 05:49:40.336992: step: 1484/529, loss: 0.05019362270832062
2023-01-24 05:49:41.397558: step: 1488/529, loss: 0.0006311187171377242
2023-01-24 05:49:42.451034: step: 1492/529, loss: 0.02612415701150894
2023-01-24 05:49:43.517322: step: 1496/529, loss: 0.007584640756249428
2023-01-24 05:49:44.571436: step: 1500/529, loss: 0.027187936007976532
2023-01-24 05:49:45.632631: step: 1504/529, loss: 0.004561016336083412
2023-01-24 05:49:46.686065: step: 1508/529, loss: 0.025386089459061623
2023-01-24 05:49:47.728422: step: 1512/529, loss: 0.004865674301981926
2023-01-24 05:49:48.774249: step: 1516/529, loss: 0.022975487634539604
2023-01-24 05:49:49.831121: step: 1520/529, loss: 0.01226430106908083
2023-01-24 05:49:50.891053: step: 1524/529, loss: 0.0039506349712610245
2023-01-24 05:49:51.932207: step: 1528/529, loss: 0.0018974298145622015
2023-01-24 05:49:52.983912: step: 1532/529, loss: 0.015290437266230583
2023-01-24 05:49:54.031642: step: 1536/529, loss: 0.005913300905376673
2023-01-24 05:49:55.089516: step: 1540/529, loss: 0.007190620061010122
2023-01-24 05:49:56.131974: step: 1544/529, loss: 0.010892827063798904
2023-01-24 05:49:57.180789: step: 1548/529, loss: 0.0034412264358252287
2023-01-24 05:49:58.247634: step: 1552/529, loss: 0.027340717613697052
2023-01-24 05:49:59.294321: step: 1556/529, loss: 0.00887272972613573
2023-01-24 05:50:00.338948: step: 1560/529, loss: 0.026076752692461014
2023-01-24 05:50:01.393328: step: 1564/529, loss: 0.01325869932770729
2023-01-24 05:50:02.433254: step: 1568/529, loss: 0.019369937479496002
2023-01-24 05:50:03.486041: step: 1572/529, loss: 0.001958054257556796
2023-01-24 05:50:04.573504: step: 1576/529, loss: 0.0316927470266819
2023-01-24 05:50:05.623651: step: 1580/529, loss: 0.0063720098696649075
2023-01-24 05:50:06.668839: step: 1584/529, loss: 0.01358823012560606
2023-01-24 05:50:07.721063: step: 1588/529, loss: 0.0068548438139259815
2023-01-24 05:50:08.761937: step: 1592/529, loss: 0.006176367402076721
2023-01-24 05:50:09.811196: step: 1596/529, loss: 0.005565831437706947
2023-01-24 05:50:10.866006: step: 1600/529, loss: 0.014127799309790134
2023-01-24 05:50:11.913254: step: 1604/529, loss: 0.002745439065620303
2023-01-24 05:50:12.950415: step: 1608/529, loss: 0.0030092273373156786
2023-01-24 05:50:14.000193: step: 1612/529, loss: 0.03675774484872818
2023-01-24 05:50:15.034565: step: 1616/529, loss: 0.0002944464795291424
2023-01-24 05:50:16.079302: step: 1620/529, loss: 0.005533001385629177
2023-01-24 05:50:17.143259: step: 1624/529, loss: 0.0026450827717781067
2023-01-24 05:50:18.206110: step: 1628/529, loss: 0.0037081041373312473
2023-01-24 05:50:19.277902: step: 1632/529, loss: 0.011961379088461399
2023-01-24 05:50:20.331280: step: 1636/529, loss: 0.03103446587920189
2023-01-24 05:50:21.378348: step: 1640/529, loss: 0.0016517981421202421
2023-01-24 05:50:22.431098: step: 1644/529, loss: 0.02793392539024353
2023-01-24 05:50:23.494988: step: 1648/529, loss: 0.005642566364258528
2023-01-24 05:50:24.562902: step: 1652/529, loss: 0.006860267836600542
2023-01-24 05:50:25.610842: step: 1656/529, loss: 0.006212129257619381
2023-01-24 05:50:26.652906: step: 1660/529, loss: 0.002021106192842126
2023-01-24 05:50:27.702515: step: 1664/529, loss: 0.002543028211221099
2023-01-24 05:50:28.749172: step: 1668/529, loss: 0.006388460751622915
2023-01-24 05:50:29.806546: step: 1672/529, loss: 0.07572527229785919
2023-01-24 05:50:30.867723: step: 1676/529, loss: 0.029526885598897934
2023-01-24 05:50:31.926784: step: 1680/529, loss: 0.0019284343579784036
2023-01-24 05:50:32.993102: step: 1684/529, loss: 0.03118252195417881
2023-01-24 05:50:34.034556: step: 1688/529, loss: 0.004910324700176716
2023-01-24 05:50:35.085319: step: 1692/529, loss: 0.017921822145581245
2023-01-24 05:50:36.136974: step: 1696/529, loss: 0.04709478095173836
2023-01-24 05:50:37.170860: step: 1700/529, loss: 0.0
2023-01-24 05:50:38.223047: step: 1704/529, loss: 0.007378748618066311
2023-01-24 05:50:39.271052: step: 1708/529, loss: 0.07707908749580383
2023-01-24 05:50:40.307520: step: 1712/529, loss: 0.01795400120317936
2023-01-24 05:50:41.367832: step: 1716/529, loss: 0.04505113884806633
2023-01-24 05:50:42.401894: step: 1720/529, loss: 0.0050595165230333805
2023-01-24 05:50:43.457852: step: 1724/529, loss: 0.0020369517151266336
2023-01-24 05:50:44.502924: step: 1728/529, loss: 0.0037170760333538055
2023-01-24 05:50:45.550669: step: 1732/529, loss: 0.0060445088893175125
2023-01-24 05:50:46.587275: step: 1736/529, loss: 0.02983376383781433
2023-01-24 05:50:47.634272: step: 1740/529, loss: 0.03832179307937622
2023-01-24 05:50:48.681019: step: 1744/529, loss: 0.0038015972822904587
2023-01-24 05:50:49.728602: step: 1748/529, loss: 0.0025327997282147408
2023-01-24 05:50:50.782290: step: 1752/529, loss: 0.012353229336440563
2023-01-24 05:50:51.849495: step: 1756/529, loss: 0.0031786933541297913
2023-01-24 05:50:52.917406: step: 1760/529, loss: 0.010260271839797497
2023-01-24 05:50:53.956368: step: 1764/529, loss: 0.022884979844093323
2023-01-24 05:50:54.999831: step: 1768/529, loss: 0.006630528252571821
2023-01-24 05:50:56.036972: step: 1772/529, loss: 0.0006608838448300958
2023-01-24 05:50:57.082891: step: 1776/529, loss: 0.006252211052924395
2023-01-24 05:50:58.117697: step: 1780/529, loss: 0.017570924013853073
2023-01-24 05:50:59.146482: step: 1784/529, loss: 0.001727188704535365
2023-01-24 05:51:00.222221: step: 1788/529, loss: 0.025053316727280617
2023-01-24 05:51:01.273639: step: 1792/529, loss: 0.0077858539298176765
2023-01-24 05:51:02.344877: step: 1796/529, loss: 0.008492161519825459
2023-01-24 05:51:03.392136: step: 1800/529, loss: 0.006147698033601046
2023-01-24 05:51:04.453439: step: 1804/529, loss: 0.0027198914904147387
2023-01-24 05:51:05.515231: step: 1808/529, loss: 0.004067946691066027
2023-01-24 05:51:06.575391: step: 1812/529, loss: 0.011367902159690857
2023-01-24 05:51:07.631558: step: 1816/529, loss: 0.009668429382145405
2023-01-24 05:51:08.678942: step: 1820/529, loss: 0.009239554405212402
2023-01-24 05:51:09.710448: step: 1824/529, loss: 0.028391003608703613
2023-01-24 05:51:10.778240: step: 1828/529, loss: 0.009757833555340767
2023-01-24 05:51:11.833132: step: 1832/529, loss: 0.009194308891892433
2023-01-24 05:51:12.894013: step: 1836/529, loss: 0.03597308695316315
2023-01-24 05:51:13.948012: step: 1840/529, loss: 0.027468081563711166
2023-01-24 05:51:14.996418: step: 1844/529, loss: 0.024140816181898117
2023-01-24 05:51:16.037880: step: 1848/529, loss: 0.0008999168057925999
2023-01-24 05:51:17.097102: step: 1852/529, loss: 0.026558518409729004
2023-01-24 05:51:18.133236: step: 1856/529, loss: 0.023927735164761543
2023-01-24 05:51:19.169675: step: 1860/529, loss: 0.004387508146464825
2023-01-24 05:51:20.223046: step: 1864/529, loss: 0.0365816093981266
2023-01-24 05:51:21.270915: step: 1868/529, loss: 0.007019015494734049
2023-01-24 05:51:22.338882: step: 1872/529, loss: 0.004949501249939203
2023-01-24 05:51:23.378571: step: 1876/529, loss: 0.011920304037630558
2023-01-24 05:51:24.434449: step: 1880/529, loss: 0.002672867150977254
2023-01-24 05:51:25.473311: step: 1884/529, loss: 0.013008982874453068
2023-01-24 05:51:26.524504: step: 1888/529, loss: 0.008184824138879776
2023-01-24 05:51:27.568564: step: 1892/529, loss: 0.0009707360877655447
2023-01-24 05:51:28.613889: step: 1896/529, loss: 0.004644864238798618
2023-01-24 05:51:29.662633: step: 1900/529, loss: 0.0055560884065926075
2023-01-24 05:51:30.695587: step: 1904/529, loss: 0.03194780275225639
2023-01-24 05:51:31.725359: step: 1908/529, loss: 0.01184525154531002
2023-01-24 05:51:32.773006: step: 1912/529, loss: 0.006322196684777737
2023-01-24 05:51:33.828429: step: 1916/529, loss: 0.005896944552659988
2023-01-24 05:51:34.867054: step: 1920/529, loss: 0.004764569457620382
2023-01-24 05:51:35.924592: step: 1924/529, loss: 0.014276344329118729
2023-01-24 05:51:36.975534: step: 1928/529, loss: 0.006889773067086935
2023-01-24 05:51:38.021501: step: 1932/529, loss: 0.03408796712756157
2023-01-24 05:51:39.073024: step: 1936/529, loss: 0.005409834906458855
2023-01-24 05:51:40.119910: step: 1940/529, loss: 0.02871054969727993
2023-01-24 05:51:41.162565: step: 1944/529, loss: 0.0030628531239926815
2023-01-24 05:51:42.198724: step: 1948/529, loss: 0.017044296488165855
2023-01-24 05:51:43.242096: step: 1952/529, loss: 0.004314434714615345
2023-01-24 05:51:44.316659: step: 1956/529, loss: 0.006943211425095797
2023-01-24 05:51:45.345025: step: 1960/529, loss: 0.010337771847844124
2023-01-24 05:51:46.373813: step: 1964/529, loss: 0.022018078714609146
2023-01-24 05:51:47.420352: step: 1968/529, loss: 0.008535580709576607
2023-01-24 05:51:48.465270: step: 1972/529, loss: 0.0002158692805096507
2023-01-24 05:51:49.542394: step: 1976/529, loss: 0.04927452653646469
2023-01-24 05:51:50.577037: step: 1980/529, loss: 0.004697205498814583
2023-01-24 05:51:51.631258: step: 1984/529, loss: 0.04207763075828552
2023-01-24 05:51:52.666042: step: 1988/529, loss: 0.005888705141842365
2023-01-24 05:51:53.711197: step: 1992/529, loss: 0.012034029699862003
2023-01-24 05:51:54.759864: step: 1996/529, loss: 0.016230523586273193
2023-01-24 05:51:55.800796: step: 2000/529, loss: 0.005281147547066212
2023-01-24 05:51:56.834332: step: 2004/529, loss: 0.0016457450110465288
2023-01-24 05:51:57.882785: step: 2008/529, loss: 0.014115831814706326
2023-01-24 05:51:58.934209: step: 2012/529, loss: 0.01586255058646202
2023-01-24 05:51:59.993217: step: 2016/529, loss: 0.006525507662445307
2023-01-24 05:52:01.049642: step: 2020/529, loss: 0.04435554891824722
2023-01-24 05:52:02.086097: step: 2024/529, loss: 0.0064546032808721066
2023-01-24 05:52:03.149318: step: 2028/529, loss: 0.005708738230168819
2023-01-24 05:52:04.203993: step: 2032/529, loss: 0.02517998218536377
2023-01-24 05:52:05.243193: step: 2036/529, loss: 0.01227293349802494
2023-01-24 05:52:06.299116: step: 2040/529, loss: 0.014538360759615898
2023-01-24 05:52:07.348126: step: 2044/529, loss: 0.015914535149931908
2023-01-24 05:52:08.394861: step: 2048/529, loss: 0.0041007110849022865
2023-01-24 05:52:09.442137: step: 2052/529, loss: 0.012785022146999836
2023-01-24 05:52:10.476958: step: 2056/529, loss: 0.003201248124241829
2023-01-24 05:52:11.527680: step: 2060/529, loss: 0.004081238526850939
2023-01-24 05:52:12.569951: step: 2064/529, loss: 0.011463594622910023
2023-01-24 05:52:13.616023: step: 2068/529, loss: 0.0006879451684653759
2023-01-24 05:52:14.665936: step: 2072/529, loss: 0.025968505069613457
2023-01-24 05:52:15.705828: step: 2076/529, loss: 0.013166551478207111
2023-01-24 05:52:16.761280: step: 2080/529, loss: 0.018307577818632126
2023-01-24 05:52:17.790827: step: 2084/529, loss: 0.008127505891025066
2023-01-24 05:52:18.835608: step: 2088/529, loss: 0.05062512308359146
2023-01-24 05:52:19.909689: step: 2092/529, loss: 0.005797439254820347
2023-01-24 05:52:20.966314: step: 2096/529, loss: 0.003359495894983411
2023-01-24 05:52:22.021311: step: 2100/529, loss: 0.0053307414054870605
2023-01-24 05:52:23.052833: step: 2104/529, loss: 0.028980115428566933
2023-01-24 05:52:24.094410: step: 2108/529, loss: 0.005553788039833307
2023-01-24 05:52:25.131310: step: 2112/529, loss: 0.019708609208464622
2023-01-24 05:52:26.175847: step: 2116/529, loss: 0.015630964189767838
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32244826435247, 'r': 0.3273431146652209, 'f1': 0.3248772531611515}, 'combined': 0.23938323917137477, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3701991703200755, 'r': 0.3036537697215279, 'f1': 0.33364067123765195}, 'combined': 0.23472208026769487, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.356104343220339, 'r': 0.31893975332068314, 'f1': 0.336498998998999}, 'combined': 0.24794663084136767, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38923041201069614, 'r': 0.3192640377749166, 'f1': 0.3507925093864376}, 'combined': 0.24906268166437068, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3783839455246276, 'r': 0.34033015214169543, 'f1': 0.35834963072662035}, 'combined': 0.26404709632487816, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39742221157618113, 'r': 0.3134255520116083, 'f1': 0.350461188528605}, 'combined': 0.24882744385530955, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3270833333333333, 'r': 0.37380952380952376, 'f1': 0.34888888888888886}, 'combined': 0.23259259259259257, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32651086087420045, 'r': 0.33208694768229874, 'f1': 0.3292752990189491}, 'combined': 0.24262390454027827, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37074014872703925, 'r': 0.30474452015782805, 'f1': 0.3345184100583055}, 'combined': 0.23533958496564208, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3798837970511898, 'r': 0.3474459016673121, 'f1': 0.36294150679618137}, 'combined': 0.267430583955081, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3966877164107804, 'r': 0.3114604865094249, 'f1': 0.3489454569993068}, 'combined': 0.24775127446950782, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:54:59.393693: step: 4/529, loss: 0.004972977098077536
2023-01-24 05:55:00.450505: step: 8/529, loss: 0.015315771102905273
2023-01-24 05:55:01.477895: step: 12/529, loss: 0.006792586296796799
2023-01-24 05:55:02.512453: step: 16/529, loss: 0.002312940079718828
2023-01-24 05:55:03.570595: step: 20/529, loss: 0.016723699867725372
2023-01-24 05:55:04.601157: step: 24/529, loss: 0.02990327961742878
2023-01-24 05:55:05.649422: step: 28/529, loss: 0.006618340499699116
2023-01-24 05:55:06.691565: step: 32/529, loss: 0.001345322118140757
2023-01-24 05:55:07.726492: step: 36/529, loss: 0.03215472027659416
2023-01-24 05:55:08.774604: step: 40/529, loss: 0.005890315864235163
2023-01-24 05:55:09.812995: step: 44/529, loss: 0.021393928676843643
2023-01-24 05:55:10.848236: step: 48/529, loss: 0.0010949615389108658
2023-01-24 05:55:11.862978: step: 52/529, loss: 0.0029673182871192694
2023-01-24 05:55:12.922780: step: 56/529, loss: 0.002470282604917884
2023-01-24 05:55:13.975603: step: 60/529, loss: 0.006345274392515421
2023-01-24 05:55:15.011022: step: 64/529, loss: 0.008853521198034286
2023-01-24 05:55:16.041631: step: 68/529, loss: 0.009107585996389389
2023-01-24 05:55:17.076820: step: 72/529, loss: 0.0016798933502286673
2023-01-24 05:55:18.098183: step: 76/529, loss: 0.006911927834153175
2023-01-24 05:55:19.147217: step: 80/529, loss: 0.007749161217361689
2023-01-24 05:55:20.191625: step: 84/529, loss: 0.008011680096387863
2023-01-24 05:55:21.228911: step: 88/529, loss: 0.004777104128152132
2023-01-24 05:55:22.267285: step: 92/529, loss: 0.03773088753223419
2023-01-24 05:55:23.301542: step: 96/529, loss: 0.0062218159437179565
2023-01-24 05:55:24.342822: step: 100/529, loss: 0.0026181309949606657
2023-01-24 05:55:25.402904: step: 104/529, loss: 0.0029570963233709335
2023-01-24 05:55:26.437549: step: 108/529, loss: 0.005767789203673601
2023-01-24 05:55:27.468969: step: 112/529, loss: 0.025732675567269325
2023-01-24 05:55:28.516222: step: 116/529, loss: 0.015178782865405083
2023-01-24 05:55:29.577826: step: 120/529, loss: 0.01200809795409441
2023-01-24 05:55:30.622094: step: 124/529, loss: 0.008931677788496017
2023-01-24 05:55:31.661909: step: 128/529, loss: 0.007425300311297178
2023-01-24 05:55:32.694635: step: 132/529, loss: 0.0013094847090542316
2023-01-24 05:55:33.758878: step: 136/529, loss: 0.013010287657380104
2023-01-24 05:55:34.815880: step: 140/529, loss: 0.007465814705938101
2023-01-24 05:55:35.861394: step: 144/529, loss: 0.002438231138512492
2023-01-24 05:55:36.909960: step: 148/529, loss: 0.004434029571712017
2023-01-24 05:55:37.965063: step: 152/529, loss: 0.003251565620303154
2023-01-24 05:55:39.008624: step: 156/529, loss: 0.006463929545134306
2023-01-24 05:55:40.061564: step: 160/529, loss: 0.00255812075920403
2023-01-24 05:55:41.093822: step: 164/529, loss: 0.001769814407452941
2023-01-24 05:55:42.155313: step: 168/529, loss: 0.012185326777398586
2023-01-24 05:55:43.208618: step: 172/529, loss: 0.00596971670165658
2023-01-24 05:55:44.258990: step: 176/529, loss: 0.005892569664865732
2023-01-24 05:55:45.329374: step: 180/529, loss: 0.03773678094148636
2023-01-24 05:55:46.363242: step: 184/529, loss: 0.003641950897872448
2023-01-24 05:55:47.420054: step: 188/529, loss: 0.006376815028488636
2023-01-24 05:55:48.468374: step: 192/529, loss: 0.005442554596811533
2023-01-24 05:55:49.494732: step: 196/529, loss: 0.06592044979333878
2023-01-24 05:55:50.540677: step: 200/529, loss: 0.019574610516428947
2023-01-24 05:55:51.575040: step: 204/529, loss: 0.0016029856633394957
2023-01-24 05:55:52.606076: step: 208/529, loss: 0.005014206748455763
2023-01-24 05:55:53.649076: step: 212/529, loss: 0.012270529754459858
2023-01-24 05:55:54.710799: step: 216/529, loss: 0.010463295504450798
2023-01-24 05:55:55.741183: step: 220/529, loss: 0.011553673073649406
2023-01-24 05:55:56.787442: step: 224/529, loss: 0.009193331934511662
2023-01-24 05:55:57.819507: step: 228/529, loss: 0.003707186784595251
2023-01-24 05:55:58.884792: step: 232/529, loss: 0.00783197209239006
2023-01-24 05:55:59.918019: step: 236/529, loss: 0.02482003904879093
2023-01-24 05:56:00.959399: step: 240/529, loss: 0.0977710410952568
2023-01-24 05:56:02.025911: step: 244/529, loss: 0.09337173402309418
2023-01-24 05:56:03.049195: step: 248/529, loss: 0.005586524028331041
2023-01-24 05:56:04.093510: step: 252/529, loss: 0.009423908777534962
2023-01-24 05:56:05.145860: step: 256/529, loss: 0.04345278441905975
2023-01-24 05:56:06.186634: step: 260/529, loss: 0.0033215321600437164
2023-01-24 05:56:07.223473: step: 264/529, loss: 0.031740445643663406
2023-01-24 05:56:08.254967: step: 268/529, loss: 0.007093391381204128
2023-01-24 05:56:09.294397: step: 272/529, loss: 0.006825506221503019
2023-01-24 05:56:10.334072: step: 276/529, loss: 0.016430441290140152
2023-01-24 05:56:11.393853: step: 280/529, loss: 0.022994298487901688
2023-01-24 05:56:12.444799: step: 284/529, loss: 0.002012432087212801
2023-01-24 05:56:13.495335: step: 288/529, loss: 0.004674348048865795
2023-01-24 05:56:14.547117: step: 292/529, loss: 0.008034372702240944
2023-01-24 05:56:15.602869: step: 296/529, loss: 0.0038768788799643517
2023-01-24 05:56:16.647537: step: 300/529, loss: 0.010274171829223633
2023-01-24 05:56:17.691753: step: 304/529, loss: 0.003792906878516078
2023-01-24 05:56:18.731658: step: 308/529, loss: 0.0043530636467039585
2023-01-24 05:56:19.771575: step: 312/529, loss: 0.005646038800477982
2023-01-24 05:56:20.815990: step: 316/529, loss: 0.013997458852827549
2023-01-24 05:56:21.854141: step: 320/529, loss: 0.027582945302128792
2023-01-24 05:56:22.921532: step: 324/529, loss: 0.03427688404917717
2023-01-24 05:56:23.972964: step: 328/529, loss: 0.0034100592602044344
2023-01-24 05:56:25.031646: step: 332/529, loss: 0.004041348118335009
2023-01-24 05:56:26.074233: step: 336/529, loss: 0.006184133235365152
2023-01-24 05:56:27.152287: step: 340/529, loss: 0.026666175574064255
2023-01-24 05:56:28.216915: step: 344/529, loss: 0.009437326341867447
2023-01-24 05:56:29.269249: step: 348/529, loss: 0.04825510457158089
2023-01-24 05:56:30.320830: step: 352/529, loss: 0.009116174653172493
2023-01-24 05:56:31.369564: step: 356/529, loss: 0.037557389587163925
2023-01-24 05:56:32.399320: step: 360/529, loss: 0.003182884305715561
2023-01-24 05:56:33.461038: step: 364/529, loss: 0.006011029705405235
2023-01-24 05:56:34.520645: step: 368/529, loss: 0.008684770204126835
2023-01-24 05:56:35.557178: step: 372/529, loss: 0.004323802422732115
2023-01-24 05:56:36.595341: step: 376/529, loss: 0.019081899896264076
2023-01-24 05:56:37.640250: step: 380/529, loss: 0.013846813701093197
2023-01-24 05:56:38.688381: step: 384/529, loss: 0.013083360157907009
2023-01-24 05:56:39.735514: step: 388/529, loss: 0.002659061225131154
2023-01-24 05:56:40.770689: step: 392/529, loss: 0.0121193528175354
2023-01-24 05:56:41.812782: step: 396/529, loss: 0.01882922649383545
2023-01-24 05:56:42.849225: step: 400/529, loss: 0.017904605716466904
2023-01-24 05:56:43.923145: step: 404/529, loss: 0.0022688633762300014
2023-01-24 05:56:44.979271: step: 408/529, loss: 0.009439710527658463
2023-01-24 05:56:46.038927: step: 412/529, loss: 0.02439112402498722
2023-01-24 05:56:47.095504: step: 416/529, loss: 0.00419649900868535
2023-01-24 05:56:48.150298: step: 420/529, loss: 0.007332560606300831
2023-01-24 05:56:49.222639: step: 424/529, loss: 0.010715237818658352
2023-01-24 05:56:50.247630: step: 428/529, loss: 0.009345471858978271
2023-01-24 05:56:51.297201: step: 432/529, loss: 0.00828529056161642
2023-01-24 05:56:52.328770: step: 436/529, loss: 0.0039924131706357
2023-01-24 05:56:53.362096: step: 440/529, loss: 0.0009335471550002694
2023-01-24 05:56:54.432017: step: 444/529, loss: 0.024950075894594193
2023-01-24 05:56:55.480523: step: 448/529, loss: 0.003914753906428814
2023-01-24 05:56:56.530059: step: 452/529, loss: 0.011607585474848747
2023-01-24 05:56:57.584084: step: 456/529, loss: 0.010729657486081123
2023-01-24 05:56:58.625644: step: 460/529, loss: 0.016343696042895317
2023-01-24 05:56:59.671469: step: 464/529, loss: 0.00885714404284954
2023-01-24 05:57:00.704639: step: 468/529, loss: 0.03314967453479767
2023-01-24 05:57:01.747291: step: 472/529, loss: 0.008124709129333496
2023-01-24 05:57:02.804844: step: 476/529, loss: 0.0014915474457666278
2023-01-24 05:57:03.862943: step: 480/529, loss: 0.02934328466653824
2023-01-24 05:57:04.906357: step: 484/529, loss: 0.008532838895916939
2023-01-24 05:57:05.944778: step: 488/529, loss: 0.0038052164018154144
2023-01-24 05:57:06.988176: step: 492/529, loss: 0.01491015125066042
2023-01-24 05:57:08.047901: step: 496/529, loss: 0.0035228889901190996
2023-01-24 05:57:09.084974: step: 500/529, loss: 0.0019470122642815113
2023-01-24 05:57:10.131264: step: 504/529, loss: 0.038061466068029404
2023-01-24 05:57:11.166515: step: 508/529, loss: 0.008572950027883053
2023-01-24 05:57:12.221329: step: 512/529, loss: 0.009340458549559116
2023-01-24 05:57:13.275820: step: 516/529, loss: 0.0041932035237550735
2023-01-24 05:57:14.322819: step: 520/529, loss: 0.0030380780808627605
2023-01-24 05:57:15.378511: step: 524/529, loss: 0.008492720313370228
2023-01-24 05:57:16.427493: step: 528/529, loss: 0.003924419637769461
2023-01-24 05:57:17.467975: step: 532/529, loss: 0.0033622782211750746
2023-01-24 05:57:18.527835: step: 536/529, loss: 0.0030823287088423967
2023-01-24 05:57:19.573156: step: 540/529, loss: 0.005688593722879887
2023-01-24 05:57:20.613683: step: 544/529, loss: 0.005316615104675293
2023-01-24 05:57:21.664339: step: 548/529, loss: 0.0007958625792525709
2023-01-24 05:57:22.705884: step: 552/529, loss: 0.0039175511337816715
2023-01-24 05:57:23.747449: step: 556/529, loss: 0.0003252278547734022
2023-01-24 05:57:24.788416: step: 560/529, loss: 0.0011216717539355159
2023-01-24 05:57:25.848913: step: 564/529, loss: 0.008563704788684845
2023-01-24 05:57:26.884602: step: 568/529, loss: 0.004667587578296661
2023-01-24 05:57:27.939192: step: 572/529, loss: 0.0037889331579208374
2023-01-24 05:57:28.981868: step: 576/529, loss: 0.0018241889774799347
2023-01-24 05:57:30.035330: step: 580/529, loss: 0.023664621636271477
2023-01-24 05:57:31.089195: step: 584/529, loss: 0.009895668365061283
2023-01-24 05:57:32.125220: step: 588/529, loss: 0.005173603072762489
2023-01-24 05:57:33.191735: step: 592/529, loss: 0.006426761858165264
2023-01-24 05:57:34.244820: step: 596/529, loss: 0.0012574323918670416
2023-01-24 05:57:35.317029: step: 600/529, loss: 0.011035253293812275
2023-01-24 05:57:36.353206: step: 604/529, loss: 0.049063120037317276
2023-01-24 05:57:37.400992: step: 608/529, loss: 0.01464060042053461
2023-01-24 05:57:38.440151: step: 612/529, loss: 0.0024741431698203087
2023-01-24 05:57:39.485172: step: 616/529, loss: 0.007257701829075813
2023-01-24 05:57:40.531746: step: 620/529, loss: 0.0327448695898056
2023-01-24 05:57:41.566692: step: 624/529, loss: 0.025429610162973404
2023-01-24 05:57:42.592366: step: 628/529, loss: 0.005170813761651516
2023-01-24 05:57:43.646054: step: 632/529, loss: 0.010116888210177422
2023-01-24 05:57:44.685673: step: 636/529, loss: 0.010732799768447876
2023-01-24 05:57:45.731367: step: 640/529, loss: 0.006285341922193766
2023-01-24 05:57:46.783817: step: 644/529, loss: 0.008337733335793018
2023-01-24 05:57:47.843331: step: 648/529, loss: 0.030470702797174454
2023-01-24 05:57:48.906440: step: 652/529, loss: 0.002225441625341773
2023-01-24 05:57:49.949034: step: 656/529, loss: 0.0058744559064507484
2023-01-24 05:57:51.001237: step: 660/529, loss: 0.07836455851793289
2023-01-24 05:57:52.057428: step: 664/529, loss: 0.0032941410318017006
2023-01-24 05:57:53.107808: step: 668/529, loss: 0.006888167932629585
2023-01-24 05:57:54.147290: step: 672/529, loss: 0.0037240704987198114
2023-01-24 05:57:55.182974: step: 676/529, loss: 0.003179890336468816
2023-01-24 05:57:56.225050: step: 680/529, loss: 0.01531173475086689
2023-01-24 05:57:57.269940: step: 684/529, loss: 0.008959028869867325
2023-01-24 05:57:58.321555: step: 688/529, loss: 0.009936016984283924
2023-01-24 05:57:59.369510: step: 692/529, loss: 0.009759964421391487
2023-01-24 05:58:00.415730: step: 696/529, loss: 0.00517621822655201
2023-01-24 05:58:01.466972: step: 700/529, loss: 0.028976377099752426
2023-01-24 05:58:02.503676: step: 704/529, loss: 0.00782828126102686
2023-01-24 05:58:03.572304: step: 708/529, loss: 0.05551927909255028
2023-01-24 05:58:04.631642: step: 712/529, loss: 0.0066059185191988945
2023-01-24 05:58:05.652813: step: 716/529, loss: 0.0003861311124637723
2023-01-24 05:58:06.698750: step: 720/529, loss: 0.000487752549815923
2023-01-24 05:58:07.742894: step: 724/529, loss: 0.008599737659096718
2023-01-24 05:58:08.783729: step: 728/529, loss: 0.019140299409627914
2023-01-24 05:58:09.830649: step: 732/529, loss: 0.02642989344894886
2023-01-24 05:58:10.874185: step: 736/529, loss: 0.010605587624013424
2023-01-24 05:58:11.911101: step: 740/529, loss: 0.0062395790591835976
2023-01-24 05:58:12.961692: step: 744/529, loss: 0.005483039654791355
2023-01-24 05:58:14.016439: step: 748/529, loss: 0.0035146691370755434
2023-01-24 05:58:15.097023: step: 752/529, loss: 0.003327739890664816
2023-01-24 05:58:16.127650: step: 756/529, loss: 0.007802151143550873
2023-01-24 05:58:17.166760: step: 760/529, loss: 0.01196114532649517
2023-01-24 05:58:18.206270: step: 764/529, loss: 0.0493021234869957
2023-01-24 05:58:19.249663: step: 768/529, loss: 0.04037129133939743
2023-01-24 05:58:20.281461: step: 772/529, loss: 0.002169232117012143
2023-01-24 05:58:21.338708: step: 776/529, loss: 0.004256423097103834
2023-01-24 05:58:22.378047: step: 780/529, loss: 0.006131183821707964
2023-01-24 05:58:23.423351: step: 784/529, loss: 0.005016126669943333
2023-01-24 05:58:24.478164: step: 788/529, loss: 0.007721309084445238
2023-01-24 05:58:25.537929: step: 792/529, loss: 0.02674700878560543
2023-01-24 05:58:26.604975: step: 796/529, loss: 0.010915335267782211
2023-01-24 05:58:27.642018: step: 800/529, loss: 0.008327090181410313
2023-01-24 05:58:28.688920: step: 804/529, loss: 0.005092321429401636
2023-01-24 05:58:29.735050: step: 808/529, loss: 0.008589416742324829
2023-01-24 05:58:30.770100: step: 812/529, loss: 0.0205709096044302
2023-01-24 05:58:31.802209: step: 816/529, loss: 0.0023053919430822134
2023-01-24 05:58:32.854740: step: 820/529, loss: 0.0009984575444832444
2023-01-24 05:58:33.897552: step: 824/529, loss: 0.016650976613163948
2023-01-24 05:58:34.932019: step: 828/529, loss: 0.009080648422241211
2023-01-24 05:58:35.980258: step: 832/529, loss: 0.011175430379807949
2023-01-24 05:58:37.026712: step: 836/529, loss: 0.014000511728227139
2023-01-24 05:58:38.067691: step: 840/529, loss: 0.011510957032442093
2023-01-24 05:58:39.117616: step: 844/529, loss: 0.0035364616196602583
2023-01-24 05:58:40.159359: step: 848/529, loss: 0.04261104390025139
2023-01-24 05:58:41.205246: step: 852/529, loss: 0.006573243997991085
2023-01-24 05:58:42.246874: step: 856/529, loss: 0.006428370252251625
2023-01-24 05:58:43.284706: step: 860/529, loss: 0.0022880961187183857
2023-01-24 05:58:44.325167: step: 864/529, loss: 0.01483568549156189
2023-01-24 05:58:45.351136: step: 868/529, loss: 0.04817057400941849
2023-01-24 05:58:46.389890: step: 872/529, loss: 0.007387330289930105
2023-01-24 05:58:47.441921: step: 876/529, loss: 0.009630956687033176
2023-01-24 05:58:48.479944: step: 880/529, loss: 0.007426950614899397
2023-01-24 05:58:49.538719: step: 884/529, loss: 0.010775621049106121
2023-01-24 05:58:50.578403: step: 888/529, loss: 0.004999483469873667
2023-01-24 05:58:51.620342: step: 892/529, loss: 0.061828307807445526
2023-01-24 05:58:52.657103: step: 896/529, loss: 0.00502614863216877
2023-01-24 05:58:53.678207: step: 900/529, loss: 0.0044181994162499905
2023-01-24 05:58:54.722940: step: 904/529, loss: 0.0017552727367728949
2023-01-24 05:58:55.755958: step: 908/529, loss: 0.0025432519614696503
2023-01-24 05:58:56.794491: step: 912/529, loss: 0.002674221294000745
2023-01-24 05:58:57.838778: step: 916/529, loss: 0.022594809532165527
2023-01-24 05:58:58.883028: step: 920/529, loss: 0.0010962142841890454
2023-01-24 05:58:59.920407: step: 924/529, loss: 0.0017544376896694303
2023-01-24 05:59:00.965924: step: 928/529, loss: 0.005362001247704029
2023-01-24 05:59:02.012276: step: 932/529, loss: 0.016685402020812035
2023-01-24 05:59:03.042548: step: 936/529, loss: 0.006691533140838146
2023-01-24 05:59:04.107010: step: 940/529, loss: 0.004304968751966953
2023-01-24 05:59:05.145389: step: 944/529, loss: 0.0039007433224469423
2023-01-24 05:59:06.196637: step: 948/529, loss: 0.06480841338634491
2023-01-24 05:59:07.235276: step: 952/529, loss: 0.02269637957215309
2023-01-24 05:59:08.292590: step: 956/529, loss: 0.009550395421683788
2023-01-24 05:59:09.311517: step: 960/529, loss: 0.005923955235630274
2023-01-24 05:59:10.353769: step: 964/529, loss: 0.006150707136839628
2023-01-24 05:59:11.401511: step: 968/529, loss: 0.003835597075521946
2023-01-24 05:59:12.439361: step: 972/529, loss: 0.012381745502352715
2023-01-24 05:59:13.491531: step: 976/529, loss: 0.004982245620340109
2023-01-24 05:59:14.541975: step: 980/529, loss: 0.0028508882969617844
2023-01-24 05:59:15.594238: step: 984/529, loss: 0.0011175476247444749
2023-01-24 05:59:16.639489: step: 988/529, loss: 0.006891999859362841
2023-01-24 05:59:17.679501: step: 992/529, loss: 0.005373796913772821
2023-01-24 05:59:18.717742: step: 996/529, loss: 0.007324570789933205
2023-01-24 05:59:19.769438: step: 1000/529, loss: 0.013494228944182396
2023-01-24 05:59:20.806887: step: 1004/529, loss: 0.004327763803303242
2023-01-24 05:59:21.848200: step: 1008/529, loss: 0.011314337141811848
2023-01-24 05:59:22.883133: step: 1012/529, loss: 0.009498815052211285
2023-01-24 05:59:23.915570: step: 1016/529, loss: 0.0012131336843594909
2023-01-24 05:59:24.960531: step: 1020/529, loss: 0.0061645167879760265
2023-01-24 05:59:26.002506: step: 1024/529, loss: 0.03723980858922005
2023-01-24 05:59:27.039539: step: 1028/529, loss: 0.012592650018632412
2023-01-24 05:59:28.092950: step: 1032/529, loss: 0.04426978901028633
2023-01-24 05:59:29.140031: step: 1036/529, loss: 0.018988968804478645
2023-01-24 05:59:30.188992: step: 1040/529, loss: 0.004733963869512081
2023-01-24 05:59:31.236680: step: 1044/529, loss: 0.011850671842694283
2023-01-24 05:59:32.279005: step: 1048/529, loss: 0.0020663172472268343
2023-01-24 05:59:33.314944: step: 1052/529, loss: 0.018322918564081192
2023-01-24 05:59:34.368312: step: 1056/529, loss: 0.0638110488653183
2023-01-24 05:59:35.414835: step: 1060/529, loss: 0.005235969088971615
2023-01-24 05:59:36.460113: step: 1064/529, loss: 0.011508745141327381
2023-01-24 05:59:37.518351: step: 1068/529, loss: 0.06403662264347076
2023-01-24 05:59:38.556142: step: 1072/529, loss: 0.00485689053311944
2023-01-24 05:59:39.621300: step: 1076/529, loss: 0.0005276335868984461
2023-01-24 05:59:40.671779: step: 1080/529, loss: 0.009044112637639046
2023-01-24 05:59:41.712472: step: 1084/529, loss: 0.0005016711074858904
2023-01-24 05:59:42.761961: step: 1088/529, loss: 0.018513882532715797
2023-01-24 05:59:43.806176: step: 1092/529, loss: 0.0055494150146842
2023-01-24 05:59:44.870869: step: 1096/529, loss: 0.011405867524445057
2023-01-24 05:59:45.914844: step: 1100/529, loss: 0.02754393219947815
2023-01-24 05:59:46.977487: step: 1104/529, loss: 0.036888349801301956
2023-01-24 05:59:48.026486: step: 1108/529, loss: 0.01456030085682869
2023-01-24 05:59:49.071752: step: 1112/529, loss: 0.004660456441342831
2023-01-24 05:59:50.116659: step: 1116/529, loss: 0.01688554137945175
2023-01-24 05:59:51.160269: step: 1120/529, loss: 0.005367800127714872
2023-01-24 05:59:52.198997: step: 1124/529, loss: 0.0020470386371016502
2023-01-24 05:59:53.249085: step: 1128/529, loss: 0.020189180970191956
2023-01-24 05:59:54.284251: step: 1132/529, loss: 0.006316610146313906
2023-01-24 05:59:55.333106: step: 1136/529, loss: 0.017518723383545876
2023-01-24 05:59:56.383239: step: 1140/529, loss: 0.03667588531970978
2023-01-24 05:59:57.427195: step: 1144/529, loss: 0.007369551341980696
2023-01-24 05:59:58.457999: step: 1148/529, loss: 0.008760740980505943
2023-01-24 05:59:59.526057: step: 1152/529, loss: 0.014112078584730625
2023-01-24 06:00:00.561330: step: 1156/529, loss: 0.0018694648751989007
2023-01-24 06:00:01.616534: step: 1160/529, loss: 0.019291620701551437
2023-01-24 06:00:02.660719: step: 1164/529, loss: 0.01479153148829937
2023-01-24 06:00:03.678182: step: 1168/529, loss: 0.00680797453969717
2023-01-24 06:00:04.730783: step: 1172/529, loss: 0.022763116285204887
2023-01-24 06:00:05.776468: step: 1176/529, loss: 0.005885292775928974
2023-01-24 06:00:06.834933: step: 1180/529, loss: 0.0026538600213825703
2023-01-24 06:00:07.881357: step: 1184/529, loss: 0.0019506238168105483
2023-01-24 06:00:08.911589: step: 1188/529, loss: 0.015076315961778164
2023-01-24 06:00:09.960172: step: 1192/529, loss: 0.030256301164627075
2023-01-24 06:00:11.004936: step: 1196/529, loss: 0.0036665780935436487
2023-01-24 06:00:12.041248: step: 1200/529, loss: 0.010747399181127548
2023-01-24 06:00:13.081964: step: 1204/529, loss: 0.012254535220563412
2023-01-24 06:00:14.127829: step: 1208/529, loss: 0.010111925192177296
2023-01-24 06:00:15.169415: step: 1212/529, loss: 0.00012033485836582258
2023-01-24 06:00:16.231890: step: 1216/529, loss: 0.0429873913526535
2023-01-24 06:00:17.295799: step: 1220/529, loss: 0.0037914959248155355
2023-01-24 06:00:18.348755: step: 1224/529, loss: 0.008630845695734024
2023-01-24 06:00:19.428852: step: 1228/529, loss: 0.04507167637348175
2023-01-24 06:00:20.473095: step: 1232/529, loss: 0.01614045538008213
2023-01-24 06:00:21.512104: step: 1236/529, loss: 0.010540727525949478
2023-01-24 06:00:22.546075: step: 1240/529, loss: 0.005351443309336901
2023-01-24 06:00:23.608673: step: 1244/529, loss: 0.004536953754723072
2023-01-24 06:00:24.644466: step: 1248/529, loss: 0.0011442664545029402
2023-01-24 06:00:25.679796: step: 1252/529, loss: 0.014306227676570415
2023-01-24 06:00:26.717558: step: 1256/529, loss: 0.0005278648459352553
2023-01-24 06:00:27.763057: step: 1260/529, loss: 0.010199516080319881
2023-01-24 06:00:28.829527: step: 1264/529, loss: 0.0035249805077910423
2023-01-24 06:00:29.874417: step: 1268/529, loss: 0.006654068361967802
2023-01-24 06:00:30.919668: step: 1272/529, loss: 0.0036469653714448214
2023-01-24 06:00:31.967391: step: 1276/529, loss: 0.007703786715865135
2023-01-24 06:00:33.008597: step: 1280/529, loss: 0.002827998483553529
2023-01-24 06:00:34.064259: step: 1284/529, loss: 0.0
2023-01-24 06:00:35.103443: step: 1288/529, loss: 0.04221372306346893
2023-01-24 06:00:36.161989: step: 1292/529, loss: 0.004524911288172007
2023-01-24 06:00:37.199417: step: 1296/529, loss: 0.023314034566283226
2023-01-24 06:00:38.270047: step: 1300/529, loss: 0.03874615207314491
2023-01-24 06:00:39.309010: step: 1304/529, loss: 0.04160419479012489
2023-01-24 06:00:40.358820: step: 1308/529, loss: 0.022686084732413292
2023-01-24 06:00:41.401209: step: 1312/529, loss: 0.0058804345317184925
2023-01-24 06:00:42.457832: step: 1316/529, loss: 0.012320570647716522
2023-01-24 06:00:43.499546: step: 1320/529, loss: 0.005599238444119692
2023-01-24 06:00:44.556291: step: 1324/529, loss: 0.00872561801224947
2023-01-24 06:00:45.599699: step: 1328/529, loss: 0.018861278891563416
2023-01-24 06:00:46.671020: step: 1332/529, loss: 0.009698063135147095
2023-01-24 06:00:47.725022: step: 1336/529, loss: 0.024158351123332977
2023-01-24 06:00:48.767291: step: 1340/529, loss: 0.008478447794914246
2023-01-24 06:00:49.824662: step: 1344/529, loss: 0.006360412575304508
2023-01-24 06:00:50.868300: step: 1348/529, loss: 0.042263664305210114
2023-01-24 06:00:51.919738: step: 1352/529, loss: 0.027825692668557167
2023-01-24 06:00:52.965752: step: 1356/529, loss: 0.004278220236301422
2023-01-24 06:00:53.996124: step: 1360/529, loss: 0.0018108503427356482
2023-01-24 06:00:55.051125: step: 1364/529, loss: 0.007207158487290144
2023-01-24 06:00:56.103495: step: 1368/529, loss: 0.012632081285119057
2023-01-24 06:00:57.136866: step: 1372/529, loss: 0.024664968252182007
2023-01-24 06:00:58.179334: step: 1376/529, loss: 0.004429580643773079
2023-01-24 06:00:59.225746: step: 1380/529, loss: 0.0011284881038591266
2023-01-24 06:01:00.277042: step: 1384/529, loss: 0.003701432142406702
2023-01-24 06:01:01.307288: step: 1388/529, loss: 0.004340532701462507
2023-01-24 06:01:02.365329: step: 1392/529, loss: 0.07653127610683441
2023-01-24 06:01:03.417743: step: 1396/529, loss: 0.0027604878414422274
2023-01-24 06:01:04.494046: step: 1400/529, loss: 0.04153519496321678
2023-01-24 06:01:05.530440: step: 1404/529, loss: 0.004973276052623987
2023-01-24 06:01:06.571812: step: 1408/529, loss: 0.01086418330669403
2023-01-24 06:01:07.617608: step: 1412/529, loss: 0.004495950415730476
2023-01-24 06:01:08.656077: step: 1416/529, loss: 0.00830911099910736
2023-01-24 06:01:09.709776: step: 1420/529, loss: 0.008292761631309986
2023-01-24 06:01:10.744461: step: 1424/529, loss: 0.03062346950173378
2023-01-24 06:01:11.795071: step: 1428/529, loss: 0.005511709488928318
2023-01-24 06:01:12.842809: step: 1432/529, loss: 0.002510402351617813
2023-01-24 06:01:13.897561: step: 1436/529, loss: 0.009135331027209759
2023-01-24 06:01:14.955196: step: 1440/529, loss: 0.004969322122633457
2023-01-24 06:01:15.990111: step: 1444/529, loss: 0.0034258062951266766
2023-01-24 06:01:17.054294: step: 1448/529, loss: 0.017483189702033997
2023-01-24 06:01:18.094381: step: 1452/529, loss: 0.013794650323688984
2023-01-24 06:01:19.150230: step: 1456/529, loss: 0.01200064830482006
2023-01-24 06:01:20.221344: step: 1460/529, loss: 0.016609076410531998
2023-01-24 06:01:21.281589: step: 1464/529, loss: 0.010299348272383213
2023-01-24 06:01:22.330636: step: 1468/529, loss: 0.008094343356788158
2023-01-24 06:01:23.377348: step: 1472/529, loss: 0.008975815959274769
2023-01-24 06:01:24.432969: step: 1476/529, loss: 0.011079206131398678
2023-01-24 06:01:25.477661: step: 1480/529, loss: 0.010500152595341206
2023-01-24 06:01:26.526758: step: 1484/529, loss: 0.004410214256495237
2023-01-24 06:01:27.586203: step: 1488/529, loss: 0.006896296050399542
2023-01-24 06:01:28.646349: step: 1492/529, loss: 0.003716336563229561
2023-01-24 06:01:29.692604: step: 1496/529, loss: 0.0036580548621714115
2023-01-24 06:01:30.742177: step: 1500/529, loss: 0.0013570705195888877
2023-01-24 06:01:31.792150: step: 1504/529, loss: 0.01896820217370987
2023-01-24 06:01:32.846415: step: 1508/529, loss: 0.00613460224121809
2023-01-24 06:01:33.911381: step: 1512/529, loss: 0.014554130844771862
2023-01-24 06:01:34.956772: step: 1516/529, loss: 0.021483778953552246
2023-01-24 06:01:36.008539: step: 1520/529, loss: 0.038009241223335266
2023-01-24 06:01:37.056602: step: 1524/529, loss: 0.005554992239922285
2023-01-24 06:01:38.113031: step: 1528/529, loss: 0.006833712104707956
2023-01-24 06:01:39.161703: step: 1532/529, loss: 0.014637970365583897
2023-01-24 06:01:40.213999: step: 1536/529, loss: 0.017603188753128052
2023-01-24 06:01:41.257358: step: 1540/529, loss: 0.006117392331361771
2023-01-24 06:01:42.302950: step: 1544/529, loss: 0.03072996623814106
2023-01-24 06:01:43.346256: step: 1548/529, loss: 0.005408911500126123
2023-01-24 06:01:44.396150: step: 1552/529, loss: 0.0013016500743106008
2023-01-24 06:01:45.432728: step: 1556/529, loss: 0.019840022549033165
2023-01-24 06:01:46.476428: step: 1560/529, loss: 0.004837490618228912
2023-01-24 06:01:47.528570: step: 1564/529, loss: 0.028960296884179115
2023-01-24 06:01:48.577424: step: 1568/529, loss: 0.005580108147114515
2023-01-24 06:01:49.632056: step: 1572/529, loss: 0.0157366544008255
2023-01-24 06:01:50.675681: step: 1576/529, loss: 0.02272208221256733
2023-01-24 06:01:51.743683: step: 1580/529, loss: 0.04798628017306328
2023-01-24 06:01:52.792049: step: 1584/529, loss: 0.007160256151109934
2023-01-24 06:01:53.842079: step: 1588/529, loss: 0.011720363050699234
2023-01-24 06:01:54.883818: step: 1592/529, loss: 0.009463370777666569
2023-01-24 06:01:55.941567: step: 1596/529, loss: 0.0019328281050547957
2023-01-24 06:01:57.012767: step: 1600/529, loss: 0.0050371852703392506
2023-01-24 06:01:58.054834: step: 1604/529, loss: 0.03656010702252388
2023-01-24 06:01:59.106030: step: 1608/529, loss: 0.002126434352248907
2023-01-24 06:02:00.170602: step: 1612/529, loss: 0.0036571999080479145
2023-01-24 06:02:01.229730: step: 1616/529, loss: 0.005796024575829506
2023-01-24 06:02:02.280111: step: 1620/529, loss: 0.0052338275127112865
2023-01-24 06:02:03.336122: step: 1624/529, loss: 0.003084834199398756
2023-01-24 06:02:04.385467: step: 1628/529, loss: 0.024948598816990852
2023-01-24 06:02:05.416624: step: 1632/529, loss: 0.002601920161396265
2023-01-24 06:02:06.461729: step: 1636/529, loss: 0.018423190340399742
2023-01-24 06:02:07.531456: step: 1640/529, loss: 0.0028306390158832073
2023-01-24 06:02:08.580440: step: 1644/529, loss: 0.012982552871108055
2023-01-24 06:02:09.610123: step: 1648/529, loss: 0.002954066963866353
2023-01-24 06:02:10.657378: step: 1652/529, loss: 0.01015490386635065
2023-01-24 06:02:11.695792: step: 1656/529, loss: 0.011678203009068966
2023-01-24 06:02:12.745228: step: 1660/529, loss: 0.0052405777387320995
2023-01-24 06:02:13.793429: step: 1664/529, loss: 0.00795319490134716
2023-01-24 06:02:14.838709: step: 1668/529, loss: 0.03392279893159866
2023-01-24 06:02:15.883513: step: 1672/529, loss: 0.007351542357355356
2023-01-24 06:02:16.933371: step: 1676/529, loss: 0.005623773671686649
2023-01-24 06:02:17.979882: step: 1680/529, loss: 0.008912540972232819
2023-01-24 06:02:19.032648: step: 1684/529, loss: 0.013553430326282978
2023-01-24 06:02:20.073522: step: 1688/529, loss: 0.005385417956858873
2023-01-24 06:02:21.107481: step: 1692/529, loss: 0.009424775838851929
2023-01-24 06:02:22.151836: step: 1696/529, loss: 0.005319713149219751
2023-01-24 06:02:23.200106: step: 1700/529, loss: 0.0015801258850842714
2023-01-24 06:02:24.241281: step: 1704/529, loss: 0.006742890924215317
2023-01-24 06:02:25.285591: step: 1708/529, loss: 0.004740002565085888
2023-01-24 06:02:26.325827: step: 1712/529, loss: 0.013140940107405186
2023-01-24 06:02:27.389496: step: 1716/529, loss: 0.039648085832595825
2023-01-24 06:02:28.457322: step: 1720/529, loss: 0.002026183530688286
2023-01-24 06:02:29.484230: step: 1724/529, loss: 0.004469913896173239
2023-01-24 06:02:30.532019: step: 1728/529, loss: 0.007142144255340099
2023-01-24 06:02:31.583164: step: 1732/529, loss: 0.008009987883269787
2023-01-24 06:02:32.620549: step: 1736/529, loss: 0.0020983973518013954
2023-01-24 06:02:33.665416: step: 1740/529, loss: 0.005713168065994978
2023-01-24 06:02:34.702928: step: 1744/529, loss: 0.0019814029801636934
2023-01-24 06:02:35.735837: step: 1748/529, loss: 0.01931850053369999
2023-01-24 06:02:36.783107: step: 1752/529, loss: 0.02419920451939106
2023-01-24 06:02:37.820715: step: 1756/529, loss: 0.03908029571175575
2023-01-24 06:02:38.867105: step: 1760/529, loss: 0.006510796491056681
2023-01-24 06:02:39.925653: step: 1764/529, loss: 0.015054167248308659
2023-01-24 06:02:40.984175: step: 1768/529, loss: 0.009906504303216934
2023-01-24 06:02:42.034281: step: 1772/529, loss: 0.011733652092516422
2023-01-24 06:02:43.079253: step: 1776/529, loss: 0.011637475341558456
2023-01-24 06:02:44.129401: step: 1780/529, loss: 0.009348433464765549
2023-01-24 06:02:45.192864: step: 1784/529, loss: 0.010028909891843796
2023-01-24 06:02:46.254450: step: 1788/529, loss: 0.0031729049514979124
2023-01-24 06:02:47.310251: step: 1792/529, loss: 0.00335936201736331
2023-01-24 06:02:48.361698: step: 1796/529, loss: 0.009620536118745804
2023-01-24 06:02:49.408597: step: 1800/529, loss: 0.014442645944654942
2023-01-24 06:02:50.467140: step: 1804/529, loss: 0.006247695069760084
2023-01-24 06:02:51.519572: step: 1808/529, loss: 0.0036743278615176678
2023-01-24 06:02:52.543213: step: 1812/529, loss: 0.009299288503825665
2023-01-24 06:02:53.597642: step: 1816/529, loss: 0.010432195849716663
2023-01-24 06:02:54.646680: step: 1820/529, loss: 0.03408021852374077
2023-01-24 06:02:55.700633: step: 1824/529, loss: 0.020112326368689537
2023-01-24 06:02:56.758709: step: 1828/529, loss: 0.03447868674993515
2023-01-24 06:02:57.797443: step: 1832/529, loss: 0.0028231474570930004
2023-01-24 06:02:58.839551: step: 1836/529, loss: 0.006711357273161411
2023-01-24 06:02:59.882824: step: 1840/529, loss: 0.002459987299516797
2023-01-24 06:03:00.943031: step: 1844/529, loss: 0.008084967732429504
2023-01-24 06:03:01.977039: step: 1848/529, loss: 0.004666895139962435
2023-01-24 06:03:03.054088: step: 1852/529, loss: 0.007382987532764673
2023-01-24 06:03:04.112238: step: 1856/529, loss: 0.025518856942653656
2023-01-24 06:03:05.170060: step: 1860/529, loss: 0.005023759324103594
2023-01-24 06:03:06.221740: step: 1864/529, loss: 0.017002597451210022
2023-01-24 06:03:07.273732: step: 1868/529, loss: 0.004340636543929577
2023-01-24 06:03:08.320436: step: 1872/529, loss: 0.02818182483315468
2023-01-24 06:03:09.359492: step: 1876/529, loss: 0.0005230815731920302
2023-01-24 06:03:10.406109: step: 1880/529, loss: 0.06654531508684158
2023-01-24 06:03:11.450518: step: 1884/529, loss: 0.0022801330778747797
2023-01-24 06:03:12.512770: step: 1888/529, loss: 0.007670076563954353
2023-01-24 06:03:13.563879: step: 1892/529, loss: 0.009617668576538563
2023-01-24 06:03:14.612453: step: 1896/529, loss: 0.06711260974407196
2023-01-24 06:03:15.665426: step: 1900/529, loss: 0.0067568388767540455
2023-01-24 06:03:16.731967: step: 1904/529, loss: 0.008602142333984375
2023-01-24 06:03:17.781800: step: 1908/529, loss: 0.003868421074002981
2023-01-24 06:03:18.834945: step: 1912/529, loss: 0.006566599477082491
2023-01-24 06:03:19.875276: step: 1916/529, loss: 0.0032664001919329166
2023-01-24 06:03:20.922322: step: 1920/529, loss: 0.006884898990392685
2023-01-24 06:03:21.962738: step: 1924/529, loss: 0.029060304164886475
2023-01-24 06:03:23.008601: step: 1928/529, loss: 0.006362695246934891
2023-01-24 06:03:24.070632: step: 1932/529, loss: 0.026920685544610023
2023-01-24 06:03:25.116725: step: 1936/529, loss: 0.028686033561825752
2023-01-24 06:03:26.170847: step: 1940/529, loss: 0.010637717321515083
2023-01-24 06:03:27.231122: step: 1944/529, loss: 0.014736822806298733
2023-01-24 06:03:28.269157: step: 1948/529, loss: 0.014455122873187065
2023-01-24 06:03:29.320410: step: 1952/529, loss: 0.0034001150634139776
2023-01-24 06:03:30.368637: step: 1956/529, loss: 0.0005323382210917771
2023-01-24 06:03:31.430451: step: 1960/529, loss: 0.009136514738202095
2023-01-24 06:03:32.482608: step: 1964/529, loss: 0.006039501167833805
2023-01-24 06:03:33.529249: step: 1968/529, loss: 0.0016622879775241017
2023-01-24 06:03:34.579171: step: 1972/529, loss: 0.002139670541509986
2023-01-24 06:03:35.626819: step: 1976/529, loss: 0.005963315721601248
2023-01-24 06:03:36.673085: step: 1980/529, loss: 0.001540248398669064
2023-01-24 06:03:37.715531: step: 1984/529, loss: 0.004051562398672104
2023-01-24 06:03:38.779338: step: 1988/529, loss: 0.047785885632038116
2023-01-24 06:03:39.810839: step: 1992/529, loss: 0.01642420142889023
2023-01-24 06:03:40.849814: step: 1996/529, loss: 0.013428923673927784
2023-01-24 06:03:41.893145: step: 2000/529, loss: 0.006780707743018866
2023-01-24 06:03:42.947722: step: 2004/529, loss: 0.00836184062063694
2023-01-24 06:03:43.997854: step: 2008/529, loss: 0.03754450008273125
2023-01-24 06:03:45.035122: step: 2012/529, loss: 0.0017651290399953723
2023-01-24 06:03:46.081877: step: 2016/529, loss: 0.01928066276013851
2023-01-24 06:03:47.127797: step: 2020/529, loss: 0.011845334433019161
2023-01-24 06:03:48.181962: step: 2024/529, loss: 0.0038715298287570477
2023-01-24 06:03:49.249658: step: 2028/529, loss: 0.007522902451455593
2023-01-24 06:03:50.301820: step: 2032/529, loss: 0.021873516961932182
2023-01-24 06:03:51.349715: step: 2036/529, loss: 0.00497586652636528
2023-01-24 06:03:52.392436: step: 2040/529, loss: 0.03909914568066597
2023-01-24 06:03:53.457974: step: 2044/529, loss: 0.004596895072609186
2023-01-24 06:03:54.487599: step: 2048/529, loss: 0.003683784743770957
2023-01-24 06:03:55.536578: step: 2052/529, loss: 0.004018933046609163
2023-01-24 06:03:56.588931: step: 2056/529, loss: 0.0062164198607206345
2023-01-24 06:03:57.628111: step: 2060/529, loss: 0.01098989974707365
2023-01-24 06:03:58.685061: step: 2064/529, loss: 0.018533045426011086
2023-01-24 06:03:59.757223: step: 2068/529, loss: 0.012348774820566177
2023-01-24 06:04:00.811527: step: 2072/529, loss: 0.030592339113354683
2023-01-24 06:04:01.858928: step: 2076/529, loss: 0.01008901558816433
2023-01-24 06:04:02.917760: step: 2080/529, loss: 0.0062245470471680164
2023-01-24 06:04:03.971814: step: 2084/529, loss: 0.008082900196313858
2023-01-24 06:04:05.021431: step: 2088/529, loss: 0.011140274815261364
2023-01-24 06:04:06.065240: step: 2092/529, loss: 0.0274446289986372
2023-01-24 06:04:07.110521: step: 2096/529, loss: 0.00805787555873394
2023-01-24 06:04:08.167031: step: 2100/529, loss: 0.03877079114317894
2023-01-24 06:04:09.206865: step: 2104/529, loss: 0.005485412199050188
2023-01-24 06:04:10.261197: step: 2108/529, loss: 0.006384048145264387
2023-01-24 06:04:11.315560: step: 2112/529, loss: 0.00483703101053834
2023-01-24 06:04:12.372901: step: 2116/529, loss: 0.0844535157084465
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.328792115902965, 'r': 0.33066379777717536, 'f1': 0.329725300716313}, 'combined': 0.2429554847383359, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3699439703830902, 'r': 0.304090069896048, 'f1': 0.33380001925370784}, 'combined': 0.23483418439959347, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35473726114649684, 'r': 0.317042220113852, 'f1': 0.33483216432865737}, 'combined': 0.24671843687374753, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3947173683369682, 'r': 0.32100923847299684, 'f1': 0.3540679377190129}, 'combined': 0.2513882357804991, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3749557687972073, 'r': 0.3379582356331565, 'f1': 0.3554969863845778}, 'combined': 0.2619451478623204, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.40113081532443756, 'r': 0.31670066118191403, 'f1': 0.35395047052541884}, 'combined': 0.2513048340730474, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 4}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.328792115902965, 'r': 0.33066379777717536, 'f1': 0.329725300716313}, 'combined': 0.2429554847383359, 'stategy': 1, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3699439703830902, 'r': 0.304090069896048, 'f1': 0.33380001925370784}, 'combined': 0.23483418439959347, 'stategy': 1, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3798837970511898, 'r': 0.3474459016673121, 'f1': 0.36294150679618137}, 'combined': 0.267430583955081, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3966877164107804, 'r': 0.3114604865094249, 'f1': 0.3489454569993068}, 'combined': 0.24775127446950782, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 5
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:06:46.364746: step: 4/529, loss: 0.005364897195249796
2023-01-24 06:06:47.401954: step: 8/529, loss: 0.004931538365781307
2023-01-24 06:06:48.429266: step: 12/529, loss: 0.042458392679691315
2023-01-24 06:06:49.458517: step: 16/529, loss: 0.008594376966357231
2023-01-24 06:06:50.493728: step: 20/529, loss: 0.06183550879359245
2023-01-24 06:06:51.547663: step: 24/529, loss: 0.018887361511588097
2023-01-24 06:06:52.583762: step: 28/529, loss: 0.017884232103824615
2023-01-24 06:06:53.613039: step: 32/529, loss: 0.005103182978928089
2023-01-24 06:06:54.670426: step: 36/529, loss: 0.009733383543789387
2023-01-24 06:06:55.705489: step: 40/529, loss: 0.019029386341571808
2023-01-24 06:06:56.750645: step: 44/529, loss: 0.004970462527126074
2023-01-24 06:06:57.785571: step: 48/529, loss: 0.004223539959639311
2023-01-24 06:06:58.819790: step: 52/529, loss: 0.004985135514289141
2023-01-24 06:06:59.877574: step: 56/529, loss: 0.005571466404944658
2023-01-24 06:07:00.908208: step: 60/529, loss: 0.019706817343831062
2023-01-24 06:07:01.969746: step: 64/529, loss: 0.011472995392978191
2023-01-24 06:07:03.000840: step: 68/529, loss: 0.018539801239967346
2023-01-24 06:07:04.055023: step: 72/529, loss: 0.007469809614121914
2023-01-24 06:07:05.093727: step: 76/529, loss: 0.006544867530465126
2023-01-24 06:07:06.128690: step: 80/529, loss: 0.006753964815288782
2023-01-24 06:07:07.178505: step: 84/529, loss: 0.007025041151791811
2023-01-24 06:07:08.238712: step: 88/529, loss: 0.02341260015964508
2023-01-24 06:07:09.286194: step: 92/529, loss: 0.012081352062523365
2023-01-24 06:07:10.317899: step: 96/529, loss: 0.006929039489477873
2023-01-24 06:07:11.350895: step: 100/529, loss: 0.002449444029480219
2023-01-24 06:07:12.413894: step: 104/529, loss: 0.0008001966052688658
2023-01-24 06:07:13.462384: step: 108/529, loss: 0.004132513888180256
2023-01-24 06:07:14.512741: step: 112/529, loss: 0.02204287238419056
2023-01-24 06:07:15.570098: step: 116/529, loss: 0.007078323047608137
2023-01-24 06:07:16.623017: step: 120/529, loss: 0.04411591589450836
2023-01-24 06:07:17.681350: step: 124/529, loss: 0.00865920353680849
2023-01-24 06:07:18.728535: step: 128/529, loss: 0.007296320516616106
2023-01-24 06:07:19.786083: step: 132/529, loss: 0.025038892403244972
2023-01-24 06:07:20.821784: step: 136/529, loss: 0.01331130601465702
2023-01-24 06:07:21.863166: step: 140/529, loss: 0.004764609970152378
2023-01-24 06:07:22.913086: step: 144/529, loss: 0.1314569115638733
2023-01-24 06:07:23.956927: step: 148/529, loss: 0.012255770154297352
2023-01-24 06:07:25.008620: step: 152/529, loss: 0.025610357522964478
2023-01-24 06:07:26.047836: step: 156/529, loss: 0.001146187772974372
2023-01-24 06:07:27.090385: step: 160/529, loss: 0.026933500543236732
2023-01-24 06:07:28.124147: step: 164/529, loss: 0.006794935557991266
2023-01-24 06:07:29.162011: step: 168/529, loss: 0.011631562374532223
2023-01-24 06:07:30.198140: step: 172/529, loss: 0.009567644447088242
2023-01-24 06:07:31.231809: step: 176/529, loss: 0.008561263792216778
2023-01-24 06:07:32.275435: step: 180/529, loss: 0.007446425501257181
2023-01-24 06:07:33.312105: step: 184/529, loss: 0.0043754479847848415
2023-01-24 06:07:34.364965: step: 188/529, loss: 0.014223598875105381
2023-01-24 06:07:35.389825: step: 192/529, loss: 0.003788086585700512
2023-01-24 06:07:36.431981: step: 196/529, loss: 0.009034320712089539
2023-01-24 06:07:37.481489: step: 200/529, loss: 0.008966310881078243
2023-01-24 06:07:38.534804: step: 204/529, loss: 0.007116635330021381
2023-01-24 06:07:39.595314: step: 208/529, loss: 0.025811906903982162
2023-01-24 06:07:40.644914: step: 212/529, loss: 0.001223785220645368
2023-01-24 06:07:41.693690: step: 216/529, loss: 0.01091198530048132
2023-01-24 06:07:42.734997: step: 220/529, loss: 0.016014914959669113
2023-01-24 06:07:43.779213: step: 224/529, loss: 0.0011714407010003924
2023-01-24 06:07:44.840343: step: 228/529, loss: 0.013587542809545994
2023-01-24 06:07:45.898704: step: 232/529, loss: 0.023932525888085365
2023-01-24 06:07:46.978329: step: 236/529, loss: 0.08474171161651611
2023-01-24 06:07:48.016851: step: 240/529, loss: 0.0032490412704646587
2023-01-24 06:07:49.074977: step: 244/529, loss: 0.01775207184255123
2023-01-24 06:07:50.109627: step: 248/529, loss: 0.032986804842948914
2023-01-24 06:07:51.150045: step: 252/529, loss: 0.0101573895663023
2023-01-24 06:07:52.204588: step: 256/529, loss: 0.007543529849499464
2023-01-24 06:07:53.250905: step: 260/529, loss: 0.0067266845144331455
2023-01-24 06:07:54.305269: step: 264/529, loss: 0.01214275136590004
2023-01-24 06:07:55.339536: step: 268/529, loss: 0.004478552378714085
2023-01-24 06:07:56.379891: step: 272/529, loss: 0.003686230629682541
2023-01-24 06:07:57.415969: step: 276/529, loss: 0.0021067685447633266
2023-01-24 06:07:58.465118: step: 280/529, loss: 0.05271173268556595
2023-01-24 06:07:59.517137: step: 284/529, loss: 0.004390914458781481
2023-01-24 06:08:00.570566: step: 288/529, loss: 0.0009522793116047978
2023-01-24 06:08:01.613527: step: 292/529, loss: 0.0046539995819330215
2023-01-24 06:08:02.657132: step: 296/529, loss: 0.04465093836188316
2023-01-24 06:08:03.700464: step: 300/529, loss: 0.000985415535978973
2023-01-24 06:08:04.748724: step: 304/529, loss: 0.003451620927080512
2023-01-24 06:08:05.801986: step: 308/529, loss: 0.03451988101005554
2023-01-24 06:08:06.838607: step: 312/529, loss: 0.02739393152296543
2023-01-24 06:08:07.887166: step: 316/529, loss: 0.009458549320697784
2023-01-24 06:08:08.928833: step: 320/529, loss: 0.02049271948635578
2023-01-24 06:08:09.968122: step: 324/529, loss: 0.004238644149154425
2023-01-24 06:08:11.017142: step: 328/529, loss: 0.014069757424294949
2023-01-24 06:08:12.072147: step: 332/529, loss: 0.010747433640062809
2023-01-24 06:08:13.126459: step: 336/529, loss: 0.010514998808503151
2023-01-24 06:08:14.165472: step: 340/529, loss: 0.0031810454092919827
2023-01-24 06:08:15.220086: step: 344/529, loss: 0.015154997818171978
2023-01-24 06:08:16.258306: step: 348/529, loss: 0.0017330572009086609
2023-01-24 06:08:17.316597: step: 352/529, loss: 0.02123137190937996
2023-01-24 06:08:18.384516: step: 356/529, loss: 0.010340305045247078
2023-01-24 06:08:19.457150: step: 360/529, loss: 0.04764502868056297
2023-01-24 06:08:20.499321: step: 364/529, loss: 0.009089462459087372
2023-01-24 06:08:21.562028: step: 368/529, loss: 0.004281953442841768
2023-01-24 06:08:22.608583: step: 372/529, loss: 0.009463080205023289
2023-01-24 06:08:23.670929: step: 376/529, loss: 0.0063528623431921005
2023-01-24 06:08:24.729107: step: 380/529, loss: 0.07916349172592163
2023-01-24 06:08:25.774145: step: 384/529, loss: 0.0025667110458016396
2023-01-24 06:08:26.824705: step: 388/529, loss: 0.007856834679841995
2023-01-24 06:08:27.866249: step: 392/529, loss: 0.03807508572936058
2023-01-24 06:08:28.929094: step: 396/529, loss: 0.007178302854299545
2023-01-24 06:08:29.974072: step: 400/529, loss: 0.006062962580472231
2023-01-24 06:08:31.036815: step: 404/529, loss: 0.002284921007230878
2023-01-24 06:08:32.099896: step: 408/529, loss: 0.004220856819301844
2023-01-24 06:08:33.154952: step: 412/529, loss: 0.013605697080492973
2023-01-24 06:08:34.218883: step: 416/529, loss: 0.003448856296017766
2023-01-24 06:08:35.267731: step: 420/529, loss: 0.008349359966814518
2023-01-24 06:08:36.331505: step: 424/529, loss: 0.011480436660349369
2023-01-24 06:08:37.372033: step: 428/529, loss: 0.012101083062589169
2023-01-24 06:08:38.417893: step: 432/529, loss: 0.006895421538501978
2023-01-24 06:08:39.456975: step: 436/529, loss: 0.007857260294258595
2023-01-24 06:08:40.516616: step: 440/529, loss: 0.009770847856998444
2023-01-24 06:08:41.568760: step: 444/529, loss: 0.01389055885374546
2023-01-24 06:08:42.625093: step: 448/529, loss: 0.004073754884302616
2023-01-24 06:08:43.662283: step: 452/529, loss: 0.008267389610409737
2023-01-24 06:08:44.696612: step: 456/529, loss: 0.006309390999376774
2023-01-24 06:08:45.754289: step: 460/529, loss: 0.0031993803568184376
2023-01-24 06:08:46.796650: step: 464/529, loss: 0.006238818634301424
2023-01-24 06:08:47.856701: step: 468/529, loss: 0.002088994951918721
2023-01-24 06:08:48.911193: step: 472/529, loss: 0.00038658682024106383
2023-01-24 06:08:49.968982: step: 476/529, loss: 0.006095749791711569
2023-01-24 06:08:51.028006: step: 480/529, loss: 0.01574626937508583
2023-01-24 06:08:52.087360: step: 484/529, loss: 0.02289753407239914
2023-01-24 06:08:53.137726: step: 488/529, loss: 0.04616186022758484
2023-01-24 06:08:54.185265: step: 492/529, loss: 0.018004965037107468
2023-01-24 06:08:55.222570: step: 496/529, loss: 0.06021159142255783
2023-01-24 06:08:56.285298: step: 500/529, loss: 0.022619400173425674
2023-01-24 06:08:57.319356: step: 504/529, loss: 0.00624881824478507
2023-01-24 06:08:58.364230: step: 508/529, loss: 0.001245412277057767
2023-01-24 06:08:59.390782: step: 512/529, loss: 0.011291474103927612
2023-01-24 06:09:00.424995: step: 516/529, loss: 0.015675190836191177
2023-01-24 06:09:01.463960: step: 520/529, loss: 0.016101239249110222
2023-01-24 06:09:02.498189: step: 524/529, loss: 0.004864449147135019
2023-01-24 06:09:03.543240: step: 528/529, loss: 0.043788231909275055
2023-01-24 06:09:04.576076: step: 532/529, loss: 0.0017816489562392235
2023-01-24 06:09:05.621302: step: 536/529, loss: 0.05425938591361046
2023-01-24 06:09:06.670327: step: 540/529, loss: 0.013950561173260212
2023-01-24 06:09:07.717042: step: 544/529, loss: 0.014342723414301872
2023-01-24 06:09:08.750190: step: 548/529, loss: 0.0007592327892780304
2023-01-24 06:09:09.794263: step: 552/529, loss: 0.013166018761694431
2023-01-24 06:09:10.816368: step: 556/529, loss: 0.002326821442693472
2023-01-24 06:09:11.858278: step: 560/529, loss: 0.004837039392441511
2023-01-24 06:09:12.917327: step: 564/529, loss: 0.01746991276741028
2023-01-24 06:09:13.962348: step: 568/529, loss: 0.02432219497859478
2023-01-24 06:09:14.999211: step: 572/529, loss: 0.04641801491379738
2023-01-24 06:09:16.038439: step: 576/529, loss: 0.01043460052460432
2023-01-24 06:09:17.077696: step: 580/529, loss: 0.0017497893422842026
2023-01-24 06:09:18.107417: step: 584/529, loss: 0.019565477967262268
2023-01-24 06:09:19.156313: step: 588/529, loss: 0.004007019102573395
2023-01-24 06:09:20.199754: step: 592/529, loss: 0.005320222117006779
2023-01-24 06:09:21.249622: step: 596/529, loss: 0.005766451358795166
2023-01-24 06:09:22.288813: step: 600/529, loss: 0.0033813375048339367
2023-01-24 06:09:23.323310: step: 604/529, loss: 0.01414481271058321
2023-01-24 06:09:24.358207: step: 608/529, loss: 0.020853595808148384
2023-01-24 06:09:25.404539: step: 612/529, loss: 0.03695572912693024
2023-01-24 06:09:26.452770: step: 616/529, loss: 0.0061587863601744175
2023-01-24 06:09:27.495468: step: 620/529, loss: 0.020196961238980293
2023-01-24 06:09:28.529163: step: 624/529, loss: 0.0011422814568504691
2023-01-24 06:09:29.575614: step: 628/529, loss: 0.006703149992972612
2023-01-24 06:09:30.628281: step: 632/529, loss: 0.005099339410662651
2023-01-24 06:09:31.678504: step: 636/529, loss: 0.002160494914278388
2023-01-24 06:09:32.728415: step: 640/529, loss: 0.0052924067713320255
2023-01-24 06:09:33.778183: step: 644/529, loss: 0.0031330962665379047
2023-01-24 06:09:34.844692: step: 648/529, loss: 0.024307547137141228
2023-01-24 06:09:35.900861: step: 652/529, loss: 0.0043894401751458645
2023-01-24 06:09:36.940438: step: 656/529, loss: 0.008192530833184719
2023-01-24 06:09:37.976256: step: 660/529, loss: 0.004176565445959568
2023-01-24 06:09:39.002471: step: 664/529, loss: 0.00844507198780775
2023-01-24 06:09:40.056364: step: 668/529, loss: 0.009645390324294567
2023-01-24 06:09:41.107860: step: 672/529, loss: 0.02573040872812271
2023-01-24 06:09:42.157075: step: 676/529, loss: 0.03124813735485077
2023-01-24 06:09:43.218565: step: 680/529, loss: 0.003575752954930067
2023-01-24 06:09:44.264260: step: 684/529, loss: 0.005831555463373661
2023-01-24 06:09:45.293751: step: 688/529, loss: 0.0034943372011184692
2023-01-24 06:09:46.331085: step: 692/529, loss: 0.006965093780308962
2023-01-24 06:09:47.377416: step: 696/529, loss: 0.015788927674293518
2023-01-24 06:09:48.413334: step: 700/529, loss: 4.810214522876777e-05
2023-01-24 06:09:49.460210: step: 704/529, loss: 0.007447210140526295
2023-01-24 06:09:50.521832: step: 708/529, loss: 0.0047540850937366486
2023-01-24 06:09:51.559331: step: 712/529, loss: 0.021725395694375038
2023-01-24 06:09:52.622331: step: 716/529, loss: 0.0037376945838332176
2023-01-24 06:09:53.661080: step: 720/529, loss: 0.0064669400453567505
2023-01-24 06:09:54.705901: step: 724/529, loss: 0.02181701548397541
2023-01-24 06:09:55.754952: step: 728/529, loss: 0.00855700671672821
2023-01-24 06:09:56.805735: step: 732/529, loss: 0.0017172066727653146
2023-01-24 06:09:57.859279: step: 736/529, loss: 0.01525746937841177
2023-01-24 06:09:58.914563: step: 740/529, loss: 0.004627066198736429
2023-01-24 06:09:59.951272: step: 744/529, loss: 0.01301474031060934
2023-01-24 06:10:01.013518: step: 748/529, loss: 0.062107790261507034
2023-01-24 06:10:02.054470: step: 752/529, loss: 0.003088456578552723
2023-01-24 06:10:03.101107: step: 756/529, loss: 0.0012178504839539528
2023-01-24 06:10:04.160343: step: 760/529, loss: 0.011936604976654053
2023-01-24 06:10:05.206653: step: 764/529, loss: 0.0017584498273208737
2023-01-24 06:10:06.246898: step: 768/529, loss: 0.012138997204601765
2023-01-24 06:10:07.288966: step: 772/529, loss: 0.0034058126620948315
2023-01-24 06:10:08.334625: step: 776/529, loss: 0.004693990107625723
2023-01-24 06:10:09.368731: step: 780/529, loss: 0.04076867923140526
2023-01-24 06:10:10.437604: step: 784/529, loss: 0.012388116680085659
2023-01-24 06:10:11.484129: step: 788/529, loss: 0.05503527820110321
2023-01-24 06:10:12.520666: step: 792/529, loss: 0.004318998195230961
2023-01-24 06:10:13.574725: step: 796/529, loss: 0.016699189320206642
2023-01-24 06:10:14.595825: step: 800/529, loss: 0.0
2023-01-24 06:10:15.634461: step: 804/529, loss: 0.0037614901084452868
2023-01-24 06:10:16.699613: step: 808/529, loss: 0.05063679441809654
2023-01-24 06:10:17.767674: step: 812/529, loss: 0.010210197418928146
2023-01-24 06:10:18.803182: step: 816/529, loss: 0.003371186088770628
2023-01-24 06:10:19.845938: step: 820/529, loss: 0.004693231545388699
2023-01-24 06:10:20.890772: step: 824/529, loss: 0.015938010066747665
2023-01-24 06:10:21.946220: step: 828/529, loss: 0.005017869174480438
2023-01-24 06:10:22.994615: step: 832/529, loss: 0.02590348944067955
2023-01-24 06:10:24.038114: step: 836/529, loss: 0.005456249229609966
2023-01-24 06:10:25.089516: step: 840/529, loss: 0.021907538175582886
2023-01-24 06:10:26.142663: step: 844/529, loss: 0.019583018496632576
2023-01-24 06:10:27.185115: step: 848/529, loss: 0.016717204824090004
2023-01-24 06:10:28.227839: step: 852/529, loss: 0.0024689314886927605
2023-01-24 06:10:29.263720: step: 856/529, loss: 0.011851905845105648
2023-01-24 06:10:30.287548: step: 860/529, loss: 0.008563940413296223
2023-01-24 06:10:31.320530: step: 864/529, loss: 0.007139807567000389
2023-01-24 06:10:32.366258: step: 868/529, loss: 0.0045534586533904076
2023-01-24 06:10:33.414570: step: 872/529, loss: 0.012220026925206184
2023-01-24 06:10:34.461800: step: 876/529, loss: 0.009112739004194736
2023-01-24 06:10:35.510832: step: 880/529, loss: 0.006252597086131573
2023-01-24 06:10:36.569579: step: 884/529, loss: 0.0022403374314308167
2023-01-24 06:10:37.606535: step: 888/529, loss: 0.01112377643585205
2023-01-24 06:10:38.639548: step: 892/529, loss: 0.002552672289311886
2023-01-24 06:10:39.681830: step: 896/529, loss: 0.014382297173142433
2023-01-24 06:10:40.738154: step: 900/529, loss: 0.003760137129575014
2023-01-24 06:10:41.792730: step: 904/529, loss: 0.0017142000142484903
2023-01-24 06:10:42.836040: step: 908/529, loss: 0.02293550781905651
2023-01-24 06:10:43.887268: step: 912/529, loss: 0.004898466635495424
2023-01-24 06:10:44.925733: step: 916/529, loss: 0.0018605765653774142
2023-01-24 06:10:45.970585: step: 920/529, loss: 0.002343763131648302
2023-01-24 06:10:47.014328: step: 924/529, loss: 0.005788714624941349
2023-01-24 06:10:48.061952: step: 928/529, loss: 0.002147121587768197
2023-01-24 06:10:49.094369: step: 932/529, loss: 0.009194801561534405
2023-01-24 06:10:50.135867: step: 936/529, loss: 0.03976268693804741
2023-01-24 06:10:51.177969: step: 940/529, loss: 0.009609239175915718
2023-01-24 06:10:52.231421: step: 944/529, loss: 0.02151433378458023
2023-01-24 06:10:53.286349: step: 948/529, loss: 0.005309975706040859
2023-01-24 06:10:54.317107: step: 952/529, loss: 0.004263193812221289
2023-01-24 06:10:55.376386: step: 956/529, loss: 0.011733454652130604
2023-01-24 06:10:56.433149: step: 960/529, loss: 0.004412689711898565
2023-01-24 06:10:57.481538: step: 964/529, loss: 0.00568025466054678
2023-01-24 06:10:58.525760: step: 968/529, loss: 0.0010944223031401634
2023-01-24 06:10:59.569695: step: 972/529, loss: 0.03886739909648895
2023-01-24 06:11:00.614564: step: 976/529, loss: 0.005676777567714453
2023-01-24 06:11:01.675948: step: 980/529, loss: 0.01659751869738102
2023-01-24 06:11:02.718584: step: 984/529, loss: 0.004885291680693626
2023-01-24 06:11:03.766853: step: 988/529, loss: 0.07421057671308517
2023-01-24 06:11:04.808066: step: 992/529, loss: 0.00395796587690711
2023-01-24 06:11:05.849647: step: 996/529, loss: 0.0024158861488103867
2023-01-24 06:11:06.893995: step: 1000/529, loss: 0.007917395792901516
2023-01-24 06:11:07.936965: step: 1004/529, loss: 0.005638586822897196
2023-01-24 06:11:09.006632: step: 1008/529, loss: 0.06871917843818665
2023-01-24 06:11:10.055077: step: 1012/529, loss: 0.002509874990209937
2023-01-24 06:11:11.096698: step: 1016/529, loss: 0.003588253166526556
2023-01-24 06:11:12.132551: step: 1020/529, loss: 0.003243096172809601
2023-01-24 06:11:13.168701: step: 1024/529, loss: 0.009450647979974747
2023-01-24 06:11:14.208850: step: 1028/529, loss: 0.003258467884734273
2023-01-24 06:11:15.243888: step: 1032/529, loss: 6.282091635512188e-05
2023-01-24 06:11:16.294240: step: 1036/529, loss: 0.004367231857031584
2023-01-24 06:11:17.369808: step: 1040/529, loss: 0.0035699144937098026
2023-01-24 06:11:18.411007: step: 1044/529, loss: 0.008112414740025997
2023-01-24 06:11:19.464360: step: 1048/529, loss: 0.019451016560196877
2023-01-24 06:11:20.509686: step: 1052/529, loss: 0.01603654958307743
2023-01-24 06:11:21.555549: step: 1056/529, loss: 0.009122052229940891
2023-01-24 06:11:22.611409: step: 1060/529, loss: 0.018931401893496513
2023-01-24 06:11:23.664698: step: 1064/529, loss: 0.014438833110034466
2023-01-24 06:11:24.712916: step: 1068/529, loss: 0.0016548129497095942
2023-01-24 06:11:25.764706: step: 1072/529, loss: 0.0038174220826476812
2023-01-24 06:11:26.811582: step: 1076/529, loss: 0.012156601995229721
2023-01-24 06:11:27.856659: step: 1080/529, loss: 0.011824763379991055
2023-01-24 06:11:28.914084: step: 1084/529, loss: 0.00810436625033617
2023-01-24 06:11:29.959089: step: 1088/529, loss: 0.00559873366728425
2023-01-24 06:11:31.002516: step: 1092/529, loss: 0.006152109242975712
2023-01-24 06:11:32.046494: step: 1096/529, loss: 0.004729011561721563
2023-01-24 06:11:33.107341: step: 1100/529, loss: 0.01180565357208252
2023-01-24 06:11:34.151589: step: 1104/529, loss: 0.007704509422183037
2023-01-24 06:11:35.204729: step: 1108/529, loss: 0.009104235097765923
2023-01-24 06:11:36.245764: step: 1112/529, loss: 0.009237431921064854
2023-01-24 06:11:37.290986: step: 1116/529, loss: 0.000431711261626333
2023-01-24 06:11:38.348993: step: 1120/529, loss: 0.029774652794003487
2023-01-24 06:11:39.392729: step: 1124/529, loss: 0.01060602255165577
2023-01-24 06:11:40.427445: step: 1128/529, loss: 0.004135953728109598
2023-01-24 06:11:41.475734: step: 1132/529, loss: 0.022009432315826416
2023-01-24 06:11:42.531023: step: 1136/529, loss: 0.007538885809481144
2023-01-24 06:11:43.579183: step: 1140/529, loss: 0.012654234655201435
2023-01-24 06:11:44.628140: step: 1144/529, loss: 0.003313296940177679
2023-01-24 06:11:45.677649: step: 1148/529, loss: 0.010472552850842476
2023-01-24 06:11:46.734817: step: 1152/529, loss: 0.002015798119828105
2023-01-24 06:11:47.782467: step: 1156/529, loss: 0.004793969914317131
2023-01-24 06:11:48.829649: step: 1160/529, loss: 0.008662129752337933
2023-01-24 06:11:49.868063: step: 1164/529, loss: 0.007208022754639387
2023-01-24 06:11:50.914814: step: 1168/529, loss: 0.002850503195077181
2023-01-24 06:11:51.959082: step: 1172/529, loss: 0.009645634330809116
2023-01-24 06:11:53.024404: step: 1176/529, loss: 0.009073411114513874
2023-01-24 06:11:54.070780: step: 1180/529, loss: 0.004340526182204485
2023-01-24 06:11:55.113263: step: 1184/529, loss: 0.0012939763255417347
2023-01-24 06:11:56.160218: step: 1188/529, loss: 0.0013405996141955256
2023-01-24 06:11:57.214079: step: 1192/529, loss: 0.0062379734590649605
2023-01-24 06:11:58.250780: step: 1196/529, loss: 0.019409896805882454
2023-01-24 06:11:59.292848: step: 1200/529, loss: 0.006402980536222458
2023-01-24 06:12:00.343909: step: 1204/529, loss: 0.0
2023-01-24 06:12:01.397062: step: 1208/529, loss: 0.010526749305427074
2023-01-24 06:12:02.443468: step: 1212/529, loss: 0.015439791604876518
2023-01-24 06:12:03.485846: step: 1216/529, loss: 0.03193796053528786
2023-01-24 06:12:04.526100: step: 1220/529, loss: 0.00831770058721304
2023-01-24 06:12:05.571475: step: 1224/529, loss: 0.0038911544252187014
2023-01-24 06:12:06.627044: step: 1228/529, loss: 0.00986575335264206
2023-01-24 06:12:07.677550: step: 1232/529, loss: 0.0018234552117064595
2023-01-24 06:12:08.730870: step: 1236/529, loss: 0.029101356863975525
2023-01-24 06:12:09.781242: step: 1240/529, loss: 0.004143872763961554
2023-01-24 06:12:10.823516: step: 1244/529, loss: 0.004696296527981758
2023-01-24 06:12:11.873245: step: 1248/529, loss: 0.002087387954816222
2023-01-24 06:12:12.923242: step: 1252/529, loss: 0.004218920134007931
2023-01-24 06:12:13.969803: step: 1256/529, loss: 0.01317879930138588
2023-01-24 06:12:15.016790: step: 1260/529, loss: 0.004585915245115757
2023-01-24 06:12:16.068977: step: 1264/529, loss: 0.028849679976701736
2023-01-24 06:12:17.132642: step: 1268/529, loss: 0.004952044226229191
2023-01-24 06:12:18.189921: step: 1272/529, loss: 0.006961579900234938
2023-01-24 06:12:19.249652: step: 1276/529, loss: 0.004382673650979996
2023-01-24 06:12:20.296208: step: 1280/529, loss: 0.009211041033267975
2023-01-24 06:12:21.335422: step: 1284/529, loss: 0.002410503337159753
2023-01-24 06:12:22.396389: step: 1288/529, loss: 0.01267029158771038
2023-01-24 06:12:23.436318: step: 1292/529, loss: 0.003697623498737812
2023-01-24 06:12:24.495433: step: 1296/529, loss: 0.0025258862879127264
2023-01-24 06:12:25.540495: step: 1300/529, loss: 0.0022309906780719757
2023-01-24 06:12:26.606683: step: 1304/529, loss: 0.007378202863037586
2023-01-24 06:12:27.651314: step: 1308/529, loss: 0.0098244184628129
2023-01-24 06:12:28.707674: step: 1312/529, loss: 0.003958418034017086
2023-01-24 06:12:29.759452: step: 1316/529, loss: 0.0542299821972847
2023-01-24 06:12:30.806462: step: 1320/529, loss: 0.008136685006320477
2023-01-24 06:12:31.860283: step: 1324/529, loss: 0.007354076951742172
2023-01-24 06:12:32.908740: step: 1328/529, loss: 0.0011552138021215796
2023-01-24 06:12:33.971435: step: 1332/529, loss: 0.013669280335307121
2023-01-24 06:12:35.025882: step: 1336/529, loss: 0.01054068561643362
2023-01-24 06:12:36.076540: step: 1340/529, loss: 0.010914186015725136
2023-01-24 06:12:37.118799: step: 1344/529, loss: 0.0061391075141727924
2023-01-24 06:12:38.172204: step: 1348/529, loss: 0.015552214346826077
2023-01-24 06:12:39.239004: step: 1352/529, loss: 0.005872183945029974
2023-01-24 06:12:40.302777: step: 1356/529, loss: 0.009975351393222809
2023-01-24 06:12:41.361210: step: 1360/529, loss: 0.02735932543873787
2023-01-24 06:12:42.409706: step: 1364/529, loss: 0.007191893644630909
2023-01-24 06:12:43.466770: step: 1368/529, loss: 0.011145122349262238
2023-01-24 06:12:44.515638: step: 1372/529, loss: 0.0003216253244318068
2023-01-24 06:12:45.581622: step: 1376/529, loss: 0.010975110344588757
2023-01-24 06:12:46.629905: step: 1380/529, loss: 0.0009541421895846725
2023-01-24 06:12:47.683977: step: 1384/529, loss: 0.00790709350258112
2023-01-24 06:12:48.733717: step: 1388/529, loss: 0.0011792776640504599
2023-01-24 06:12:49.788316: step: 1392/529, loss: 0.0034517974127084017
2023-01-24 06:12:50.847234: step: 1396/529, loss: 0.009446525014936924
2023-01-24 06:12:51.903183: step: 1400/529, loss: 0.011488438583910465
2023-01-24 06:12:52.960150: step: 1404/529, loss: 0.0019498568726703525
2023-01-24 06:12:54.015976: step: 1408/529, loss: 0.00443405332043767
2023-01-24 06:12:55.056988: step: 1412/529, loss: 3.3390904718544334e-05
2023-01-24 06:12:56.118484: step: 1416/529, loss: 0.0006125321961008012
2023-01-24 06:12:57.180505: step: 1420/529, loss: 0.007208527065813541
2023-01-24 06:12:58.235764: step: 1424/529, loss: 0.022011684253811836
2023-01-24 06:12:59.296176: step: 1428/529, loss: 0.0076451716013252735
2023-01-24 06:13:00.351149: step: 1432/529, loss: 0.021180637180805206
2023-01-24 06:13:01.408772: step: 1436/529, loss: 0.005078395828604698
2023-01-24 06:13:02.478381: step: 1440/529, loss: 0.0032672728411853313
2023-01-24 06:13:03.536069: step: 1444/529, loss: 0.0034984382800757885
2023-01-24 06:13:04.594563: step: 1448/529, loss: 0.0012936186976730824
2023-01-24 06:13:05.670738: step: 1452/529, loss: 0.004346802830696106
2023-01-24 06:13:06.723743: step: 1456/529, loss: 0.012945122085511684
2023-01-24 06:13:07.777307: step: 1460/529, loss: 0.02515929564833641
2023-01-24 06:13:08.813720: step: 1464/529, loss: 0.008811013773083687
2023-01-24 06:13:09.869615: step: 1468/529, loss: 0.016155611723661423
2023-01-24 06:13:10.903163: step: 1472/529, loss: 0.00851103849709034
2023-01-24 06:13:11.958786: step: 1476/529, loss: 0.023528946563601494
2023-01-24 06:13:13.005170: step: 1480/529, loss: 0.006576701533049345
2023-01-24 06:13:14.064207: step: 1484/529, loss: 0.004462636541575193
2023-01-24 06:13:15.114249: step: 1488/529, loss: 0.0058347429148852825
2023-01-24 06:13:16.161857: step: 1492/529, loss: 0.00028820225270465016
2023-01-24 06:13:17.213177: step: 1496/529, loss: 0.013267778791487217
2023-01-24 06:13:18.259996: step: 1500/529, loss: 0.0006704726256430149
2023-01-24 06:13:19.320963: step: 1504/529, loss: 0.008622322231531143
2023-01-24 06:13:20.383251: step: 1508/529, loss: 0.005056119058281183
2023-01-24 06:13:21.430818: step: 1512/529, loss: 0.005860959179699421
2023-01-24 06:13:22.489255: step: 1516/529, loss: 0.005031220149248838
2023-01-24 06:13:23.563612: step: 1520/529, loss: 0.003332293126732111
2023-01-24 06:13:24.624087: step: 1524/529, loss: 0.005705941002815962
2023-01-24 06:13:25.672209: step: 1528/529, loss: 0.0161629356443882
2023-01-24 06:13:26.723334: step: 1532/529, loss: 0.009504578076303005
2023-01-24 06:13:27.760602: step: 1536/529, loss: 0.018351538106799126
2023-01-24 06:13:28.797415: step: 1540/529, loss: 0.01501642819494009
2023-01-24 06:13:29.856060: step: 1544/529, loss: 0.009062089025974274
2023-01-24 06:13:30.893879: step: 1548/529, loss: 0.005738650448620319
2023-01-24 06:13:31.946883: step: 1552/529, loss: 0.007332745473831892
2023-01-24 06:13:33.020185: step: 1556/529, loss: 0.010884511284530163
2023-01-24 06:13:34.099230: step: 1560/529, loss: 0.0022634186316281557
2023-01-24 06:13:35.153035: step: 1564/529, loss: 0.0089864581823349
2023-01-24 06:13:36.214707: step: 1568/529, loss: 0.054286062717437744
2023-01-24 06:13:37.270486: step: 1572/529, loss: 0.004494091030210257
2023-01-24 06:13:38.343117: step: 1576/529, loss: 0.0038285499904304743
2023-01-24 06:13:39.379135: step: 1580/529, loss: 0.0014065966242924333
2023-01-24 06:13:40.427127: step: 1584/529, loss: 0.011168353259563446
2023-01-24 06:13:41.472656: step: 1588/529, loss: 0.002279081381857395
2023-01-24 06:13:42.556451: step: 1592/529, loss: 0.0026932191103696823
2023-01-24 06:13:43.592942: step: 1596/529, loss: 0.00128878653049469
2023-01-24 06:13:44.658714: step: 1600/529, loss: 0.006494956091046333
2023-01-24 06:13:45.692084: step: 1604/529, loss: 0.01833772473037243
2023-01-24 06:13:46.736538: step: 1608/529, loss: 0.01639338582754135
2023-01-24 06:13:47.805414: step: 1612/529, loss: 0.08848409354686737
2023-01-24 06:13:48.853535: step: 1616/529, loss: 0.005832102615386248
2023-01-24 06:13:49.902448: step: 1620/529, loss: 0.002370870439335704
2023-01-24 06:13:50.953241: step: 1624/529, loss: 0.02834174782037735
2023-01-24 06:13:52.008271: step: 1628/529, loss: 0.000945900974329561
2023-01-24 06:13:53.069108: step: 1632/529, loss: 0.0153167974203825
2023-01-24 06:13:54.122088: step: 1636/529, loss: 0.003908591810613871
2023-01-24 06:13:55.162486: step: 1640/529, loss: 0.017594778910279274
2023-01-24 06:13:56.217413: step: 1644/529, loss: 0.002155149821192026
2023-01-24 06:13:57.255551: step: 1648/529, loss: 0.04294760897755623
2023-01-24 06:13:58.300128: step: 1652/529, loss: 0.0
2023-01-24 06:13:59.352448: step: 1656/529, loss: 0.0072180768474936485
2023-01-24 06:14:00.397959: step: 1660/529, loss: 0.007787659298628569
2023-01-24 06:14:01.450010: step: 1664/529, loss: 0.006282668095082045
2023-01-24 06:14:02.505507: step: 1668/529, loss: 0.007096918765455484
2023-01-24 06:14:03.546951: step: 1672/529, loss: 0.014727005735039711
2023-01-24 06:14:04.613281: step: 1676/529, loss: 0.0067855981178581715
2023-01-24 06:14:05.656074: step: 1680/529, loss: 0.001603766344487667
2023-01-24 06:14:06.695379: step: 1684/529, loss: 0.004314210265874863
2023-01-24 06:14:07.759642: step: 1688/529, loss: 0.008225671015679836
2023-01-24 06:14:08.804455: step: 1692/529, loss: 0.004177814815193415
2023-01-24 06:14:09.851200: step: 1696/529, loss: 0.0005804678658023477
2023-01-24 06:14:10.917551: step: 1700/529, loss: 0.020535405725240707
2023-01-24 06:14:11.967029: step: 1704/529, loss: 0.009242628701031208
2023-01-24 06:14:13.016729: step: 1708/529, loss: 0.004243496339768171
2023-01-24 06:14:14.062485: step: 1712/529, loss: 0.012518382631242275
2023-01-24 06:14:15.110770: step: 1716/529, loss: 0.004606115166097879
2023-01-24 06:14:16.165015: step: 1720/529, loss: 0.007482695858925581
2023-01-24 06:14:17.223831: step: 1724/529, loss: 0.06701914966106415
2023-01-24 06:14:18.270791: step: 1728/529, loss: 0.05648639798164368
2023-01-24 06:14:19.328977: step: 1732/529, loss: 0.017292285338044167
2023-01-24 06:14:20.377742: step: 1736/529, loss: 0.02491857297718525
2023-01-24 06:14:21.432215: step: 1740/529, loss: 0.014872078783810139
2023-01-24 06:14:22.474955: step: 1744/529, loss: 0.029166337102651596
2023-01-24 06:14:23.545117: step: 1748/529, loss: 0.012679904699325562
2023-01-24 06:14:24.604367: step: 1752/529, loss: 0.009680034592747688
2023-01-24 06:14:25.630665: step: 1756/529, loss: 0.013375414535403252
2023-01-24 06:14:26.684403: step: 1760/529, loss: 0.004014882724732161
2023-01-24 06:14:27.725854: step: 1764/529, loss: 0.004619982559233904
2023-01-24 06:14:28.761882: step: 1768/529, loss: 0.00829849299043417
2023-01-24 06:14:29.821446: step: 1772/529, loss: 0.005871128290891647
2023-01-24 06:14:30.877625: step: 1776/529, loss: 0.002497660694643855
2023-01-24 06:14:31.931824: step: 1780/529, loss: 0.016429323703050613
2023-01-24 06:14:32.981456: step: 1784/529, loss: 0.016005050390958786
2023-01-24 06:14:34.027251: step: 1788/529, loss: 0.011435303837060928
2023-01-24 06:14:35.063744: step: 1792/529, loss: 0.003906558267772198
2023-01-24 06:14:36.128079: step: 1796/529, loss: 0.019485201686620712
2023-01-24 06:14:37.177020: step: 1800/529, loss: 0.004587591625750065
2023-01-24 06:14:38.212768: step: 1804/529, loss: 0.0027694660238921642
2023-01-24 06:14:39.255104: step: 1808/529, loss: 0.007504927460104227
2023-01-24 06:14:40.295854: step: 1812/529, loss: 0.004087294451892376
2023-01-24 06:14:41.335813: step: 1816/529, loss: 0.007184195797890425
2023-01-24 06:14:42.403087: step: 1820/529, loss: 0.007019483018666506
2023-01-24 06:14:43.450570: step: 1824/529, loss: 0.0346452035009861
2023-01-24 06:14:44.489501: step: 1828/529, loss: 0.0024064257740974426
2023-01-24 06:14:45.511633: step: 1832/529, loss: 0.0026801915373653173
2023-01-24 06:14:46.547639: step: 1836/529, loss: 4.24527024733834e-05
2023-01-24 06:14:47.606762: step: 1840/529, loss: 0.038760650902986526
2023-01-24 06:14:48.652798: step: 1844/529, loss: 0.012975029647350311
2023-01-24 06:14:49.707956: step: 1848/529, loss: 0.010356522165238857
2023-01-24 06:14:50.758341: step: 1852/529, loss: 0.008925179950892925
2023-01-24 06:14:51.822878: step: 1856/529, loss: 0.010802081786096096
2023-01-24 06:14:52.892085: step: 1860/529, loss: 0.00594439497217536
2023-01-24 06:14:53.939352: step: 1864/529, loss: 0.016758378595113754
2023-01-24 06:14:54.981519: step: 1868/529, loss: 0.0022920190822333097
2023-01-24 06:14:56.036961: step: 1872/529, loss: 0.01095986645668745
2023-01-24 06:14:57.084709: step: 1876/529, loss: 0.018821481615304947
2023-01-24 06:14:58.115156: step: 1880/529, loss: 0.054840877652168274
2023-01-24 06:14:59.154695: step: 1884/529, loss: 0.007524373009800911
2023-01-24 06:15:00.185331: step: 1888/529, loss: 0.032600287348032
2023-01-24 06:15:01.223615: step: 1892/529, loss: 0.009916742332279682
2023-01-24 06:15:02.263825: step: 1896/529, loss: 0.013087676838040352
2023-01-24 06:15:03.308811: step: 1900/529, loss: 0.006917009595781565
2023-01-24 06:15:04.380066: step: 1904/529, loss: 0.0009078065631911159
2023-01-24 06:15:05.421530: step: 1908/529, loss: 0.010523991659283638
2023-01-24 06:15:06.472666: step: 1912/529, loss: 0.001266071223653853
2023-01-24 06:15:07.516900: step: 1916/529, loss: 0.003956879023462534
2023-01-24 06:15:08.561010: step: 1920/529, loss: 0.044897980988025665
2023-01-24 06:15:09.603531: step: 1924/529, loss: 0.00875797402113676
2023-01-24 06:15:10.663213: step: 1928/529, loss: 0.0034518318716436625
2023-01-24 06:15:11.704259: step: 1932/529, loss: 0.00888245552778244
2023-01-24 06:15:12.761291: step: 1936/529, loss: 0.012659145519137383
2023-01-24 06:15:13.823703: step: 1940/529, loss: 0.023738525807857513
2023-01-24 06:15:14.859855: step: 1944/529, loss: 0.0008952609496191144
2023-01-24 06:15:15.913870: step: 1948/529, loss: 0.02853865921497345
2023-01-24 06:15:16.966768: step: 1952/529, loss: 0.0011694193817675114
2023-01-24 06:15:18.006495: step: 1956/529, loss: 0.008649631403386593
2023-01-24 06:15:19.050843: step: 1960/529, loss: 0.0089822793379426
2023-01-24 06:15:20.087518: step: 1964/529, loss: 0.005365021526813507
2023-01-24 06:15:21.141266: step: 1968/529, loss: 0.07763940840959549
2023-01-24 06:15:22.185467: step: 1972/529, loss: 0.01008632406592369
2023-01-24 06:15:23.246843: step: 1976/529, loss: 0.0007939829956740141
2023-01-24 06:15:24.306696: step: 1980/529, loss: 0.014864037744700909
2023-01-24 06:15:25.353212: step: 1984/529, loss: 0.013313878327608109
2023-01-24 06:15:26.394338: step: 1988/529, loss: 0.010894953273236752
2023-01-24 06:15:27.449808: step: 1992/529, loss: 0.004349092021584511
2023-01-24 06:15:28.495548: step: 1996/529, loss: 0.009638441726565361
2023-01-24 06:15:29.544735: step: 2000/529, loss: 0.0061707524582743645
2023-01-24 06:15:30.588456: step: 2004/529, loss: 0.002053322969004512
2023-01-24 06:15:31.613596: step: 2008/529, loss: 0.0005394183099269867
2023-01-24 06:15:32.658127: step: 2012/529, loss: 0.009594489820301533
2023-01-24 06:15:33.707606: step: 2016/529, loss: 0.0015609830152243376
2023-01-24 06:15:34.764288: step: 2020/529, loss: 0.009851885959506035
2023-01-24 06:15:35.813137: step: 2024/529, loss: 0.023001283407211304
2023-01-24 06:15:36.866240: step: 2028/529, loss: 0.0032469695433974266
2023-01-24 06:15:37.947020: step: 2032/529, loss: 0.02607772871851921
2023-01-24 06:15:38.976460: step: 2036/529, loss: 0.011506660841405392
2023-01-24 06:15:40.012128: step: 2040/529, loss: 0.00343112600967288
2023-01-24 06:15:41.061056: step: 2044/529, loss: 0.0008999130222946405
2023-01-24 06:15:42.111017: step: 2048/529, loss: 0.007807687856256962
2023-01-24 06:15:43.156969: step: 2052/529, loss: 0.02372725121676922
2023-01-24 06:15:44.199798: step: 2056/529, loss: 0.03458522632718086
2023-01-24 06:15:45.242323: step: 2060/529, loss: 0.003015015507116914
2023-01-24 06:15:46.304072: step: 2064/529, loss: 0.008491916581988335
2023-01-24 06:15:47.357884: step: 2068/529, loss: 0.00469997338950634
2023-01-24 06:15:48.423012: step: 2072/529, loss: 0.0129986722022295
2023-01-24 06:15:49.462482: step: 2076/529, loss: 0.035609424114227295
2023-01-24 06:15:50.511249: step: 2080/529, loss: 0.05366597697138786
2023-01-24 06:15:51.548445: step: 2084/529, loss: 0.004191091284155846
2023-01-24 06:15:52.596211: step: 2088/529, loss: 0.007715316955000162
2023-01-24 06:15:53.634882: step: 2092/529, loss: 0.004350960720330477
2023-01-24 06:15:54.694426: step: 2096/529, loss: 0.043105389922857285
2023-01-24 06:15:55.744642: step: 2100/529, loss: 0.007859050296247005
2023-01-24 06:15:56.794274: step: 2104/529, loss: 0.003910794388502836
2023-01-24 06:15:57.845476: step: 2108/529, loss: 0.01939493604004383
2023-01-24 06:15:58.907173: step: 2112/529, loss: 0.006374196149408817
2023-01-24 06:15:59.960032: step: 2116/529, loss: 0.005078229587525129
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32864373150390097, 'r': 0.33113818107888315, 'f1': 0.3298862408857683}, 'combined': 0.24307407223161873, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3706665443853898, 'r': 0.2995089180635872, 'f1': 0.3313100580124237}, 'combined': 0.2330824528730619, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3569340128755365, 'r': 0.31561907020872865, 'f1': 0.33500755287009065}, 'combined': 0.24684767053585627, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39334043936359697, 'r': 0.3181732873386164, 'f1': 0.3517863842644037}, 'combined': 0.2497683328277266, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37654120545174097, 'r': 0.3379582356331565, 'f1': 0.356207980357347}, 'combined': 0.2624690381580452, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.401932948432426, 'r': 0.3127705301775472, 'f1': 0.35179003639812534}, 'combined': 0.24977092584266897, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 5}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32864373150390097, 'r': 0.33113818107888315, 'f1': 0.3298862408857683}, 'combined': 0.24307407223161873, 'stategy': 1, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3706665443853898, 'r': 0.2995089180635872, 'f1': 0.3313100580124237}, 'combined': 0.2330824528730619, 'stategy': 1, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3798837970511898, 'r': 0.3474459016673121, 'f1': 0.36294150679618137}, 'combined': 0.267430583955081, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3966877164107804, 'r': 0.3114604865094249, 'f1': 0.3489454569993068}, 'combined': 0.24775127446950782, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 6
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:18:28.767159: step: 4/529, loss: 0.004742167890071869
2023-01-24 06:18:29.811147: step: 8/529, loss: 0.0036565768532454967
2023-01-24 06:18:30.843977: step: 12/529, loss: 0.0018223716178908944
2023-01-24 06:18:31.894920: step: 16/529, loss: 0.005090882536023855
2023-01-24 06:18:32.936019: step: 20/529, loss: 0.0199209526181221
2023-01-24 06:18:33.957331: step: 24/529, loss: 0.0003567904932424426
2023-01-24 06:18:35.007309: step: 28/529, loss: 0.02007969468832016
2023-01-24 06:18:36.049687: step: 32/529, loss: 0.00613051000982523
2023-01-24 06:18:37.088748: step: 36/529, loss: 0.003461189568042755
2023-01-24 06:18:38.141929: step: 40/529, loss: 0.0017779492773115635
2023-01-24 06:18:39.186146: step: 44/529, loss: 0.008025181479752064
2023-01-24 06:18:40.225857: step: 48/529, loss: 0.01793014630675316
2023-01-24 06:18:41.269807: step: 52/529, loss: 0.009517989121377468
2023-01-24 06:18:42.305729: step: 56/529, loss: 0.0061738030053675175
2023-01-24 06:18:43.355941: step: 60/529, loss: 0.0035525846760720015
2023-01-24 06:18:44.380176: step: 64/529, loss: 0.004170773550868034
2023-01-24 06:18:45.436674: step: 68/529, loss: 0.010141300968825817
2023-01-24 06:18:46.478397: step: 72/529, loss: 0.001489673973992467
2023-01-24 06:18:47.521732: step: 76/529, loss: 0.00888165831565857
2023-01-24 06:18:48.560613: step: 80/529, loss: 0.003602228593081236
2023-01-24 06:18:49.613507: step: 84/529, loss: 0.00792065542191267
2023-01-24 06:18:50.658262: step: 88/529, loss: 0.02555099129676819
2023-01-24 06:18:51.700874: step: 92/529, loss: 0.007738249376416206
2023-01-24 06:18:52.747075: step: 96/529, loss: 0.011598734185099602
2023-01-24 06:18:53.799228: step: 100/529, loss: 0.0032476165797561407
2023-01-24 06:18:54.843308: step: 104/529, loss: 0.0058266338892281055
2023-01-24 06:18:55.884753: step: 108/529, loss: 0.006213184911757708
2023-01-24 06:18:56.909743: step: 112/529, loss: 0.008658098056912422
2023-01-24 06:18:57.962205: step: 116/529, loss: 0.03862125054001808
2023-01-24 06:18:59.008433: step: 120/529, loss: 0.028483223170042038
2023-01-24 06:19:00.057373: step: 124/529, loss: 0.012792219407856464
2023-01-24 06:19:01.096643: step: 128/529, loss: 0.0007580016390420496
2023-01-24 06:19:02.132127: step: 132/529, loss: 0.07374080270528793
2023-01-24 06:19:03.169867: step: 136/529, loss: 0.010961364023387432
2023-01-24 06:19:04.214192: step: 140/529, loss: 0.011940453201532364
2023-01-24 06:19:05.283697: step: 144/529, loss: 0.013146958313882351
2023-01-24 06:19:06.337498: step: 148/529, loss: 0.010877873748540878
2023-01-24 06:19:07.386370: step: 152/529, loss: 0.0020709247328341007
2023-01-24 06:19:08.433802: step: 156/529, loss: 0.0031474612187594175
2023-01-24 06:19:09.472717: step: 160/529, loss: 0.02551279217004776
2023-01-24 06:19:10.508577: step: 164/529, loss: 0.012841667979955673
2023-01-24 06:19:11.549625: step: 168/529, loss: 0.0032924795523285866
2023-01-24 06:19:12.589611: step: 172/529, loss: 0.0016286119353026152
2023-01-24 06:19:13.630232: step: 176/529, loss: 0.011194484308362007
2023-01-24 06:19:14.682220: step: 180/529, loss: 0.007908947765827179
2023-01-24 06:19:15.706457: step: 184/529, loss: 0.0104463379830122
2023-01-24 06:19:16.760064: step: 188/529, loss: 0.0012408499605953693
2023-01-24 06:19:17.787655: step: 192/529, loss: 0.005134171340614557
2023-01-24 06:19:18.821343: step: 196/529, loss: 0.031151393428444862
2023-01-24 06:19:19.866995: step: 200/529, loss: 0.006274307146668434
2023-01-24 06:19:20.921027: step: 204/529, loss: 0.008539692498743534
2023-01-24 06:19:21.981999: step: 208/529, loss: 0.004239651840180159
2023-01-24 06:19:23.037873: step: 212/529, loss: 0.029458889737725258
2023-01-24 06:19:24.084045: step: 216/529, loss: 0.0017249897355213761
2023-01-24 06:19:25.140598: step: 220/529, loss: 0.007696910761296749
2023-01-24 06:19:26.192143: step: 224/529, loss: 0.004568984732031822
2023-01-24 06:19:27.236386: step: 228/529, loss: 0.028919141739606857
2023-01-24 06:19:28.288006: step: 232/529, loss: 0.008101379498839378
2023-01-24 06:19:29.318789: step: 236/529, loss: 0.0009102600743062794
2023-01-24 06:19:30.369896: step: 240/529, loss: 0.002067000837996602
2023-01-24 06:19:31.421127: step: 244/529, loss: 0.009263182058930397
2023-01-24 06:19:32.462465: step: 248/529, loss: 0.0115694310516119
2023-01-24 06:19:33.514677: step: 252/529, loss: 0.18416275084018707
2023-01-24 06:19:34.563229: step: 256/529, loss: 0.0518353171646595
2023-01-24 06:19:35.610720: step: 260/529, loss: 0.0029434156604111195
2023-01-24 06:19:36.659826: step: 264/529, loss: 0.013119274750351906
2023-01-24 06:19:37.724468: step: 268/529, loss: 0.005223182495683432
2023-01-24 06:19:38.766052: step: 272/529, loss: 0.005790745373815298
2023-01-24 06:19:39.806803: step: 276/529, loss: 0.0026379176415503025
2023-01-24 06:19:40.845765: step: 280/529, loss: 0.0037465891800820827
2023-01-24 06:19:41.911505: step: 284/529, loss: 0.013140812516212463
2023-01-24 06:19:42.942610: step: 288/529, loss: 0.011482231318950653
2023-01-24 06:19:43.986064: step: 292/529, loss: 0.016089053824543953
2023-01-24 06:19:45.037376: step: 296/529, loss: 0.00786222517490387
2023-01-24 06:19:46.073081: step: 300/529, loss: 0.012310792692005634
2023-01-24 06:19:47.115851: step: 304/529, loss: 0.016517577692866325
2023-01-24 06:19:48.173613: step: 308/529, loss: 0.02212962880730629
2023-01-24 06:19:49.221551: step: 312/529, loss: 0.0016913588624447584
2023-01-24 06:19:50.262928: step: 316/529, loss: 0.0044386680237948895
2023-01-24 06:19:51.304500: step: 320/529, loss: 0.041396837681531906
2023-01-24 06:19:52.349373: step: 324/529, loss: 0.0
2023-01-24 06:19:53.394561: step: 328/529, loss: 0.005812098737806082
2023-01-24 06:19:54.443403: step: 332/529, loss: 0.008507197722792625
2023-01-24 06:19:55.489920: step: 336/529, loss: 0.022704802453517914
2023-01-24 06:19:56.534165: step: 340/529, loss: 0.00018631767306942493
2023-01-24 06:19:57.577042: step: 344/529, loss: 0.014528080821037292
2023-01-24 06:19:58.623797: step: 348/529, loss: 0.02608819305896759
2023-01-24 06:19:59.669748: step: 352/529, loss: 0.006677224300801754
2023-01-24 06:20:00.703055: step: 356/529, loss: 0.006541381124407053
2023-01-24 06:20:01.761365: step: 360/529, loss: 0.000843782676383853
2023-01-24 06:20:02.809139: step: 364/529, loss: 0.0013773947721347213
2023-01-24 06:20:03.872846: step: 368/529, loss: 0.004629874601960182
2023-01-24 06:20:04.914266: step: 372/529, loss: 0.023446664214134216
2023-01-24 06:20:05.960724: step: 376/529, loss: 0.017254117876291275
2023-01-24 06:20:07.002679: step: 380/529, loss: 0.011426403187215328
2023-01-24 06:20:08.032911: step: 384/529, loss: 0.002016189508140087
2023-01-24 06:20:09.079428: step: 388/529, loss: 0.011657757684588432
2023-01-24 06:20:10.119538: step: 392/529, loss: 0.005400735419243574
2023-01-24 06:20:11.178763: step: 396/529, loss: 0.010577062144875526
2023-01-24 06:20:12.219572: step: 400/529, loss: 0.005472579505294561
2023-01-24 06:20:13.265179: step: 404/529, loss: 0.007579367142170668
2023-01-24 06:20:14.312135: step: 408/529, loss: 0.0029342707712203264
2023-01-24 06:20:15.351899: step: 412/529, loss: 0.0026867901906371117
2023-01-24 06:20:16.402889: step: 416/529, loss: 0.009467937052249908
2023-01-24 06:20:17.442097: step: 420/529, loss: 0.007822707295417786
2023-01-24 06:20:18.499149: step: 424/529, loss: 0.00530764227733016
2023-01-24 06:20:19.540743: step: 428/529, loss: 0.012376729398965836
2023-01-24 06:20:20.588614: step: 432/529, loss: 0.012746045365929604
2023-01-24 06:20:21.625827: step: 436/529, loss: 0.012784531340003014
2023-01-24 06:20:22.663074: step: 440/529, loss: 0.011401951313018799
2023-01-24 06:20:23.704318: step: 444/529, loss: 0.014958926476538181
2023-01-24 06:20:24.749076: step: 448/529, loss: 0.007821457460522652
2023-01-24 06:20:25.790898: step: 452/529, loss: 4.247689503245056e-05
2023-01-24 06:20:26.841081: step: 456/529, loss: 0.011198826134204865
2023-01-24 06:20:27.884717: step: 460/529, loss: 0.005356063600629568
2023-01-24 06:20:28.930000: step: 464/529, loss: 0.015696559101343155
2023-01-24 06:20:29.980237: step: 468/529, loss: 0.019132040441036224
2023-01-24 06:20:31.026164: step: 472/529, loss: 0.003525756299495697
2023-01-24 06:20:32.053776: step: 476/529, loss: 0.02598177269101143
2023-01-24 06:20:33.100272: step: 480/529, loss: 0.005338669288903475
2023-01-24 06:20:34.169388: step: 484/529, loss: 0.00499527296051383
2023-01-24 06:20:35.217836: step: 488/529, loss: 0.05169805511832237
2023-01-24 06:20:36.244472: step: 492/529, loss: 0.012880816124379635
2023-01-24 06:20:37.273560: step: 496/529, loss: 0.0283990316092968
2023-01-24 06:20:38.318208: step: 500/529, loss: 0.0036583489272743464
2023-01-24 06:20:39.364335: step: 504/529, loss: 0.0064158630557358265
2023-01-24 06:20:40.399912: step: 508/529, loss: 0.0031435575801879168
2023-01-24 06:20:41.438996: step: 512/529, loss: 0.004737897776067257
2023-01-24 06:20:42.487991: step: 516/529, loss: 0.0034656536299735308
2023-01-24 06:20:43.527925: step: 520/529, loss: 0.00832302961498499
2023-01-24 06:20:44.585230: step: 524/529, loss: 0.0
2023-01-24 06:20:45.635642: step: 528/529, loss: 0.0032608206383883953
2023-01-24 06:20:46.683671: step: 532/529, loss: 0.003181769512593746
2023-01-24 06:20:47.712383: step: 536/529, loss: 0.0018491375958546996
2023-01-24 06:20:48.742497: step: 540/529, loss: 0.003867859486490488
2023-01-24 06:20:49.775652: step: 544/529, loss: 9.876215335680172e-05
2023-01-24 06:20:50.824071: step: 548/529, loss: 0.006455567199736834
2023-01-24 06:20:51.877716: step: 552/529, loss: 0.012330739758908749
2023-01-24 06:20:52.931489: step: 556/529, loss: 0.0028007859364151955
2023-01-24 06:20:53.967850: step: 560/529, loss: 0.024414516985416412
2023-01-24 06:20:55.020903: step: 564/529, loss: 0.0048380568623542786
2023-01-24 06:20:56.061299: step: 568/529, loss: 0.0009671932784840465
2023-01-24 06:20:57.118025: step: 572/529, loss: 0.007043642457574606
2023-01-24 06:20:58.182669: step: 576/529, loss: 0.012031720019876957
2023-01-24 06:20:59.220033: step: 580/529, loss: 0.007606689352542162
2023-01-24 06:21:00.260828: step: 584/529, loss: 0.005316408816725016
2023-01-24 06:21:01.289373: step: 588/529, loss: 0.018632540479302406
2023-01-24 06:21:02.335112: step: 592/529, loss: 0.0007140995585359633
2023-01-24 06:21:03.374370: step: 596/529, loss: 0.01693444326519966
2023-01-24 06:21:04.454023: step: 600/529, loss: 0.002484208205714822
2023-01-24 06:21:05.500687: step: 604/529, loss: 0.012808961793780327
2023-01-24 06:21:06.548529: step: 608/529, loss: 0.023313501849770546
2023-01-24 06:21:07.598942: step: 612/529, loss: 0.0005394491017796099
2023-01-24 06:21:08.634520: step: 616/529, loss: 0.0213242806494236
2023-01-24 06:21:09.684146: step: 620/529, loss: 0.0038967744912952185
2023-01-24 06:21:10.745646: step: 624/529, loss: 0.0005699424655176699
2023-01-24 06:21:11.791191: step: 628/529, loss: 0.0024028411135077477
2023-01-24 06:21:12.827355: step: 632/529, loss: 0.005883142817765474
2023-01-24 06:21:13.864800: step: 636/529, loss: 0.0005097048124298453
2023-01-24 06:21:14.910981: step: 640/529, loss: 0.005305488593876362
2023-01-24 06:21:15.958119: step: 644/529, loss: 0.007276056334376335
2023-01-24 06:21:16.993760: step: 648/529, loss: 0.020804421976208687
2023-01-24 06:21:18.042131: step: 652/529, loss: 0.005687142256647348
2023-01-24 06:21:19.105645: step: 656/529, loss: 7.923376688268036e-05
2023-01-24 06:21:20.163536: step: 660/529, loss: 0.013029214926064014
2023-01-24 06:21:21.203309: step: 664/529, loss: 0.003912067040801048
2023-01-24 06:21:22.253133: step: 668/529, loss: 0.034013353288173676
2023-01-24 06:21:23.284343: step: 672/529, loss: 0.008656191639602184
2023-01-24 06:21:24.338902: step: 676/529, loss: 0.005629325285553932
2023-01-24 06:21:25.396295: step: 680/529, loss: 0.0034782651346176863
2023-01-24 06:21:26.450210: step: 684/529, loss: 0.00882573239505291
2023-01-24 06:21:27.488203: step: 688/529, loss: 0.0016626326832920313
2023-01-24 06:21:28.526155: step: 692/529, loss: 2.3558945031254552e-05
2023-01-24 06:21:29.581105: step: 696/529, loss: 0.019673597067594528
2023-01-24 06:21:30.632723: step: 700/529, loss: 0.009327026084065437
2023-01-24 06:21:31.683425: step: 704/529, loss: 0.0001285663020098582
2023-01-24 06:21:32.725930: step: 708/529, loss: 0.00439535453915596
2023-01-24 06:21:33.789725: step: 712/529, loss: 0.003424061695113778
2023-01-24 06:21:34.832794: step: 716/529, loss: 0.009291629306972027
2023-01-24 06:21:35.900898: step: 720/529, loss: 0.007102983072400093
2023-01-24 06:21:36.955018: step: 724/529, loss: 0.00016753238742239773
2023-01-24 06:21:38.028466: step: 728/529, loss: 0.00897889118641615
2023-01-24 06:21:39.083568: step: 732/529, loss: 0.019379105418920517
2023-01-24 06:21:40.145846: step: 736/529, loss: 0.0031782547011971474
2023-01-24 06:21:41.186124: step: 740/529, loss: 0.0006825546734035015
2023-01-24 06:21:42.246913: step: 744/529, loss: 0.04118768125772476
2023-01-24 06:21:43.300055: step: 748/529, loss: 0.009162982925772667
2023-01-24 06:21:44.356840: step: 752/529, loss: 0.02648012712597847
2023-01-24 06:21:45.390862: step: 756/529, loss: 0.00011568747140699998
2023-01-24 06:21:46.423164: step: 760/529, loss: 0.009785100817680359
2023-01-24 06:21:47.486593: step: 764/529, loss: 0.02606017328798771
2023-01-24 06:21:48.524831: step: 768/529, loss: 0.0034594100434333086
2023-01-24 06:21:49.572099: step: 772/529, loss: 0.005184119567275047
2023-01-24 06:21:50.626604: step: 776/529, loss: 0.024212410673499107
2023-01-24 06:21:51.660141: step: 780/529, loss: 0.02686261385679245
2023-01-24 06:21:52.710829: step: 784/529, loss: 0.015509597025811672
2023-01-24 06:21:53.756733: step: 788/529, loss: 0.014809778891503811
2023-01-24 06:21:54.815525: step: 792/529, loss: 0.0032797246240079403
2023-01-24 06:21:55.865837: step: 796/529, loss: 0.0006011223886162043
2023-01-24 06:21:56.905188: step: 800/529, loss: 0.005283440928906202
2023-01-24 06:21:57.948535: step: 804/529, loss: 0.011103903874754906
2023-01-24 06:21:58.987070: step: 808/529, loss: 0.004357552621513605
2023-01-24 06:22:00.038051: step: 812/529, loss: 0.00954181607812643
2023-01-24 06:22:01.071076: step: 816/529, loss: 0.008148825727403164
2023-01-24 06:22:02.116857: step: 820/529, loss: 0.006697388365864754
2023-01-24 06:22:03.174698: step: 824/529, loss: 0.0010361068416386843
2023-01-24 06:22:04.236908: step: 828/529, loss: 0.003057020017877221
2023-01-24 06:22:05.296960: step: 832/529, loss: 0.09200213104486465
2023-01-24 06:22:06.329294: step: 836/529, loss: 0.002408974803984165
2023-01-24 06:22:07.367137: step: 840/529, loss: 0.005381615832448006
2023-01-24 06:22:08.415921: step: 844/529, loss: 0.002756470814347267
2023-01-24 06:22:09.446731: step: 848/529, loss: 0.005640943069010973
2023-01-24 06:22:10.471157: step: 852/529, loss: 0.002816244261339307
2023-01-24 06:22:11.499855: step: 856/529, loss: 0.017023885622620583
2023-01-24 06:22:12.552644: step: 860/529, loss: 0.0034948564134538174
2023-01-24 06:22:13.601901: step: 864/529, loss: 0.012284182012081146
2023-01-24 06:22:14.659527: step: 868/529, loss: 0.007817283272743225
2023-01-24 06:22:15.716345: step: 872/529, loss: 0.005652410443872213
2023-01-24 06:22:16.780659: step: 876/529, loss: 0.0035922580864280462
2023-01-24 06:22:17.826428: step: 880/529, loss: 0.009137238375842571
2023-01-24 06:22:18.875153: step: 884/529, loss: 0.0075898319482803345
2023-01-24 06:22:19.949121: step: 888/529, loss: 0.005378589499741793
2023-01-24 06:22:20.994393: step: 892/529, loss: 0.0027653842698782682
2023-01-24 06:22:22.050297: step: 896/529, loss: 0.009672717191278934
2023-01-24 06:22:23.094978: step: 900/529, loss: 0.013271757401525974
2023-01-24 06:22:24.131194: step: 904/529, loss: 0.01503598690032959
2023-01-24 06:22:25.195485: step: 908/529, loss: 0.006287833210080862
2023-01-24 06:22:26.245692: step: 912/529, loss: 0.0029748398810625076
2023-01-24 06:22:27.302490: step: 916/529, loss: 0.008829597383737564
2023-01-24 06:22:28.335195: step: 920/529, loss: 0.007881560362875462
2023-01-24 06:22:29.378332: step: 924/529, loss: 0.00848472025245428
2023-01-24 06:22:30.407346: step: 928/529, loss: 0.043218858540058136
2023-01-24 06:22:31.450084: step: 932/529, loss: 0.0205976665019989
2023-01-24 06:22:32.481557: step: 936/529, loss: 0.001519115292467177
2023-01-24 06:22:33.522023: step: 940/529, loss: 0.0715329498052597
2023-01-24 06:22:34.559780: step: 944/529, loss: 0.01387772336602211
2023-01-24 06:22:35.628489: step: 948/529, loss: 0.005131635349243879
2023-01-24 06:22:36.672713: step: 952/529, loss: 0.006119557190686464
2023-01-24 06:22:37.734312: step: 956/529, loss: 0.013821277767419815
2023-01-24 06:22:38.793224: step: 960/529, loss: 0.011609617620706558
2023-01-24 06:22:39.841599: step: 964/529, loss: 0.0023277131840586662
2023-01-24 06:22:40.883857: step: 968/529, loss: 0.04275273531675339
2023-01-24 06:22:41.921014: step: 972/529, loss: 0.007000874727964401
2023-01-24 06:22:42.985147: step: 976/529, loss: 0.05131024122238159
2023-01-24 06:22:44.030166: step: 980/529, loss: 0.027935031801462173
2023-01-24 06:22:45.071129: step: 984/529, loss: 0.006313640158623457
2023-01-24 06:22:46.123485: step: 988/529, loss: 0.013393081724643707
2023-01-24 06:22:47.156137: step: 992/529, loss: 0.0013849545503035188
2023-01-24 06:22:48.207216: step: 996/529, loss: 0.0034446455538272858
2023-01-24 06:22:49.252204: step: 1000/529, loss: 0.0019654599018394947
2023-01-24 06:22:50.283016: step: 1004/529, loss: 0.008411969058215618
2023-01-24 06:22:51.343738: step: 1008/529, loss: 0.012529555708169937
2023-01-24 06:22:52.395587: step: 1012/529, loss: 0.01764804497361183
2023-01-24 06:22:53.441186: step: 1016/529, loss: 0.004600695800036192
2023-01-24 06:22:54.477168: step: 1020/529, loss: 0.007580797653645277
2023-01-24 06:22:55.525526: step: 1024/529, loss: 0.005055199842900038
2023-01-24 06:22:56.566278: step: 1028/529, loss: 0.009149763733148575
2023-01-24 06:22:57.621208: step: 1032/529, loss: 0.04893635958433151
2023-01-24 06:22:58.661081: step: 1036/529, loss: 0.008037861436605453
2023-01-24 06:22:59.692806: step: 1040/529, loss: 0.0021698998752981424
2023-01-24 06:23:00.744373: step: 1044/529, loss: 0.009808819741010666
2023-01-24 06:23:01.801715: step: 1048/529, loss: 0.022708097472786903
2023-01-24 06:23:02.839653: step: 1052/529, loss: 0.007051931694149971
2023-01-24 06:23:03.882496: step: 1056/529, loss: 0.01182352565228939
2023-01-24 06:23:04.937594: step: 1060/529, loss: 0.005562472157180309
2023-01-24 06:23:05.983137: step: 1064/529, loss: 0.005953978281468153
2023-01-24 06:23:07.028811: step: 1068/529, loss: 0.008256226778030396
2023-01-24 06:23:08.067013: step: 1072/529, loss: 0.008127371780574322
2023-01-24 06:23:09.093914: step: 1076/529, loss: 0.008761660195887089
2023-01-24 06:23:10.155508: step: 1080/529, loss: 0.005018271040171385
2023-01-24 06:23:11.205810: step: 1084/529, loss: 0.018078407272696495
2023-01-24 06:23:12.252295: step: 1088/529, loss: 0.006192586850374937
2023-01-24 06:23:13.295776: step: 1092/529, loss: 0.009030920453369617
2023-01-24 06:23:14.344621: step: 1096/529, loss: 0.0027431806083768606
2023-01-24 06:23:15.401448: step: 1100/529, loss: 0.0041840458288788795
2023-01-24 06:23:16.468909: step: 1104/529, loss: 0.004774863366037607
2023-01-24 06:23:17.506505: step: 1108/529, loss: 0.0007985194679349661
2023-01-24 06:23:18.550672: step: 1112/529, loss: 0.02322738990187645
2023-01-24 06:23:19.588896: step: 1116/529, loss: 0.000559560488909483
2023-01-24 06:23:20.641081: step: 1120/529, loss: 0.0015954470727592707
2023-01-24 06:23:21.686597: step: 1124/529, loss: 0.0021640071645379066
2023-01-24 06:23:22.748026: step: 1128/529, loss: 0.03130905702710152
2023-01-24 06:23:23.806109: step: 1132/529, loss: 0.0035858768969774246
2023-01-24 06:23:24.849016: step: 1136/529, loss: 0.00625680573284626
2023-01-24 06:23:25.906276: step: 1140/529, loss: 0.005452013574540615
2023-01-24 06:23:26.957517: step: 1144/529, loss: 0.007115437649190426
2023-01-24 06:23:28.013635: step: 1148/529, loss: 0.004546810407191515
2023-01-24 06:23:29.072308: step: 1152/529, loss: 0.0034040322061628103
2023-01-24 06:23:30.112912: step: 1156/529, loss: 0.006536812521517277
2023-01-24 06:23:31.151720: step: 1160/529, loss: 0.006710847374051809
2023-01-24 06:23:32.200704: step: 1164/529, loss: 0.00020382300135679543
2023-01-24 06:23:33.237193: step: 1168/529, loss: 0.01146881002932787
2023-01-24 06:23:34.273444: step: 1172/529, loss: 0.0019391977693885565
2023-01-24 06:23:35.346817: step: 1176/529, loss: 0.04001364856958389
2023-01-24 06:23:36.400450: step: 1180/529, loss: 0.003103894181549549
2023-01-24 06:23:37.422119: step: 1184/529, loss: 0.000752914696931839
2023-01-24 06:23:38.469248: step: 1188/529, loss: 0.029446875676512718
2023-01-24 06:23:39.549388: step: 1192/529, loss: 0.010021678172051907
2023-01-24 06:23:40.604644: step: 1196/529, loss: 0.007594669237732887
2023-01-24 06:23:41.656827: step: 1200/529, loss: 0.012734473682940006
2023-01-24 06:23:42.697014: step: 1204/529, loss: 0.005931871943175793
2023-01-24 06:23:43.747814: step: 1208/529, loss: 0.013309831731021404
2023-01-24 06:23:44.806561: step: 1212/529, loss: 0.006066114641726017
2023-01-24 06:23:45.845009: step: 1216/529, loss: 0.003518663579598069
2023-01-24 06:23:46.895870: step: 1220/529, loss: 0.011779836378991604
2023-01-24 06:23:47.955448: step: 1224/529, loss: 0.005570013076066971
2023-01-24 06:23:49.003974: step: 1228/529, loss: 0.0026514141354709864
2023-01-24 06:23:50.086278: step: 1232/529, loss: 0.0028603507671505213
2023-01-24 06:23:51.127111: step: 1236/529, loss: 0.002618933329358697
2023-01-24 06:23:52.161869: step: 1240/529, loss: 0.015570678748190403
2023-01-24 06:23:53.199482: step: 1244/529, loss: 0.012244373559951782
2023-01-24 06:23:54.244004: step: 1248/529, loss: 0.0038620950654149055
2023-01-24 06:23:55.304373: step: 1252/529, loss: 0.005834421142935753
2023-01-24 06:23:56.355151: step: 1256/529, loss: 0.007925285957753658
2023-01-24 06:23:57.416287: step: 1260/529, loss: 0.0010500873904675245
2023-01-24 06:23:58.470478: step: 1264/529, loss: 0.0038320235908031464
2023-01-24 06:23:59.513507: step: 1268/529, loss: 0.0023174425587058067
2023-01-24 06:24:00.579968: step: 1272/529, loss: 0.0249689519405365
2023-01-24 06:24:01.627112: step: 1276/529, loss: 0.01003737561404705
2023-01-24 06:24:02.696128: step: 1280/529, loss: 0.008079884573817253
2023-01-24 06:24:03.737775: step: 1284/529, loss: 0.0019671660847961903
2023-01-24 06:24:04.779872: step: 1288/529, loss: 0.005430907476693392
2023-01-24 06:24:05.824024: step: 1292/529, loss: 0.004998387303203344
2023-01-24 06:24:06.876020: step: 1296/529, loss: 0.010008488781750202
2023-01-24 06:24:07.936427: step: 1300/529, loss: 0.007138208486139774
2023-01-24 06:24:09.006614: step: 1304/529, loss: 0.004537483677268028
2023-01-24 06:24:10.073508: step: 1308/529, loss: 0.0026460825465619564
2023-01-24 06:24:11.120254: step: 1312/529, loss: 0.008456207811832428
2023-01-24 06:24:12.158069: step: 1316/529, loss: 0.003798689227551222
2023-01-24 06:24:13.209919: step: 1320/529, loss: 0.0051660300232470036
2023-01-24 06:24:14.250844: step: 1324/529, loss: 0.0005838748766109347
2023-01-24 06:24:15.315136: step: 1328/529, loss: 0.03099573403596878
2023-01-24 06:24:16.367738: step: 1332/529, loss: 0.00020527427841443568
2023-01-24 06:24:17.408954: step: 1336/529, loss: 6.52045855531469e-05
2023-01-24 06:24:18.460390: step: 1340/529, loss: 0.010828651487827301
2023-01-24 06:24:19.542417: step: 1344/529, loss: 0.008284438401460648
2023-01-24 06:24:20.597216: step: 1348/529, loss: 0.004853402730077505
2023-01-24 06:24:21.647078: step: 1352/529, loss: 0.01000240258872509
2023-01-24 06:24:22.700703: step: 1356/529, loss: 0.00013289348862599581
2023-01-24 06:24:23.747758: step: 1360/529, loss: 0.006068001501262188
2023-01-24 06:24:24.802529: step: 1364/529, loss: 0.023817013949155807
2023-01-24 06:24:25.849061: step: 1368/529, loss: 0.020465966314077377
2023-01-24 06:24:26.892646: step: 1372/529, loss: 0.008516632951796055
2023-01-24 06:24:27.948177: step: 1376/529, loss: 0.005069859325885773
2023-01-24 06:24:29.005368: step: 1380/529, loss: 0.035662490874528885
2023-01-24 06:24:30.071172: step: 1384/529, loss: 0.0018937982385978103
2023-01-24 06:24:31.120745: step: 1388/529, loss: 0.0024043733719736338
2023-01-24 06:24:32.187613: step: 1392/529, loss: 0.004089605063199997
2023-01-24 06:24:33.236426: step: 1396/529, loss: 0.02496258169412613
2023-01-24 06:24:34.281829: step: 1400/529, loss: 0.004224271513521671
2023-01-24 06:24:35.331855: step: 1404/529, loss: 0.002199976472184062
2023-01-24 06:24:36.384328: step: 1408/529, loss: 0.00746961822733283
2023-01-24 06:24:37.443337: step: 1412/529, loss: 0.00982865784317255
2023-01-24 06:24:38.485673: step: 1416/529, loss: 0.0016633948544040322
2023-01-24 06:24:39.543853: step: 1420/529, loss: 0.004381684586405754
2023-01-24 06:24:40.621402: step: 1424/529, loss: 0.03226260840892792
2023-01-24 06:24:41.702752: step: 1428/529, loss: 0.008671775460243225
2023-01-24 06:24:42.759980: step: 1432/529, loss: 0.003400318557396531
2023-01-24 06:24:43.795858: step: 1436/529, loss: 0.007719533052295446
2023-01-24 06:24:44.847418: step: 1440/529, loss: 0.01135760173201561
2023-01-24 06:24:45.892633: step: 1444/529, loss: 0.009906083345413208
2023-01-24 06:24:46.959053: step: 1448/529, loss: 0.006750479340553284
2023-01-24 06:24:48.021755: step: 1452/529, loss: 0.008141616359353065
2023-01-24 06:24:49.074202: step: 1456/529, loss: 0.0022892772685736418
2023-01-24 06:24:50.137973: step: 1460/529, loss: 0.007740786299109459
2023-01-24 06:24:51.179902: step: 1464/529, loss: 0.0022128659766167402
2023-01-24 06:24:52.233221: step: 1468/529, loss: 0.003114899154752493
2023-01-24 06:24:53.296663: step: 1472/529, loss: 0.0039520529098808765
2023-01-24 06:24:54.388071: step: 1476/529, loss: 0.004174373112618923
2023-01-24 06:24:55.427641: step: 1480/529, loss: 0.005985192954540253
2023-01-24 06:24:56.475058: step: 1484/529, loss: 0.010510027408599854
2023-01-24 06:24:57.523209: step: 1488/529, loss: 0.002910297829657793
2023-01-24 06:24:58.592797: step: 1492/529, loss: 0.004397583659738302
2023-01-24 06:24:59.654391: step: 1496/529, loss: 0.009632998146116734
2023-01-24 06:25:00.711417: step: 1500/529, loss: 0.02090447209775448
2023-01-24 06:25:01.755200: step: 1504/529, loss: 0.0013201754773035645
2023-01-24 06:25:02.818606: step: 1508/529, loss: 0.015047918073832989
2023-01-24 06:25:03.872711: step: 1512/529, loss: 0.017057547345757484
2023-01-24 06:25:04.935812: step: 1516/529, loss: 0.0014086196897551417
2023-01-24 06:25:05.983544: step: 1520/529, loss: 0.005536028183996677
2023-01-24 06:25:07.031829: step: 1524/529, loss: 0.007469982840120792
2023-01-24 06:25:08.084626: step: 1528/529, loss: 0.00017267375369556248
2023-01-24 06:25:09.132664: step: 1532/529, loss: 0.067486472427845
2023-01-24 06:25:10.196343: step: 1536/529, loss: 0.003867912571877241
2023-01-24 06:25:11.246503: step: 1540/529, loss: 0.0032956181094050407
2023-01-24 06:25:12.301686: step: 1544/529, loss: 0.015459376387298107
2023-01-24 06:25:13.341831: step: 1548/529, loss: 0.004179155919700861
2023-01-24 06:25:14.406604: step: 1552/529, loss: 0.005018417723476887
2023-01-24 06:25:15.461647: step: 1556/529, loss: 0.0007420636829920113
2023-01-24 06:25:16.523531: step: 1560/529, loss: 0.008511663414537907
2023-01-24 06:25:17.619019: step: 1564/529, loss: 0.008958940394222736
2023-01-24 06:25:18.670518: step: 1568/529, loss: 0.006533031817525625
2023-01-24 06:25:19.727873: step: 1572/529, loss: 0.0024251060094684362
2023-01-24 06:25:20.788545: step: 1576/529, loss: 0.015983154997229576
2023-01-24 06:25:21.841655: step: 1580/529, loss: 0.004558037035167217
2023-01-24 06:25:22.910288: step: 1584/529, loss: 0.0016301891300827265
2023-01-24 06:25:23.977333: step: 1588/529, loss: 0.003920048475265503
2023-01-24 06:25:25.018579: step: 1592/529, loss: 0.00460980786010623
2023-01-24 06:25:26.065222: step: 1596/529, loss: 0.0022013839334249496
2023-01-24 06:25:27.108142: step: 1600/529, loss: 0.0028462756890803576
2023-01-24 06:25:28.159517: step: 1604/529, loss: 0.011513668112456799
2023-01-24 06:25:29.231184: step: 1608/529, loss: 0.00922415778040886
2023-01-24 06:25:30.291093: step: 1612/529, loss: 0.027424195781350136
2023-01-24 06:25:31.334830: step: 1616/529, loss: 0.0104572344571352
2023-01-24 06:25:32.397508: step: 1620/529, loss: 0.007106281351298094
2023-01-24 06:25:33.451457: step: 1624/529, loss: 0.01389244757592678
2023-01-24 06:25:34.510558: step: 1628/529, loss: 0.01727847009897232
2023-01-24 06:25:35.581719: step: 1632/529, loss: 0.016096945852041245
2023-01-24 06:25:36.646750: step: 1636/529, loss: 0.0060960156843066216
2023-01-24 06:25:37.724221: step: 1640/529, loss: 0.030349215492606163
2023-01-24 06:25:38.779286: step: 1644/529, loss: 0.026542028412222862
2023-01-24 06:25:39.833422: step: 1648/529, loss: 0.006606078706681728
2023-01-24 06:25:40.877626: step: 1652/529, loss: 0.006048164330422878
2023-01-24 06:25:41.919180: step: 1656/529, loss: 0.040182679891586304
2023-01-24 06:25:42.965401: step: 1660/529, loss: 0.012790779583156109
2023-01-24 06:25:44.027126: step: 1664/529, loss: 0.0005048942985013127
2023-01-24 06:25:45.080774: step: 1668/529, loss: 0.007903759367763996
2023-01-24 06:25:46.124032: step: 1672/529, loss: 0.002809855854138732
2023-01-24 06:25:47.167574: step: 1676/529, loss: 0.013880029320716858
2023-01-24 06:25:48.218929: step: 1680/529, loss: 0.030947690829634666
2023-01-24 06:25:49.295136: step: 1684/529, loss: 0.006410995963960886
2023-01-24 06:25:50.331335: step: 1688/529, loss: 0.003931113518774509
2023-01-24 06:25:51.373044: step: 1692/529, loss: 0.0059612346813082695
2023-01-24 06:25:52.421445: step: 1696/529, loss: 0.014973499812185764
2023-01-24 06:25:53.477147: step: 1700/529, loss: 0.006248392630368471
2023-01-24 06:25:54.517381: step: 1704/529, loss: 0.0033808392472565174
2023-01-24 06:25:55.570146: step: 1708/529, loss: 0.003967809025198221
2023-01-24 06:25:56.616673: step: 1712/529, loss: 0.005686058662831783
2023-01-24 06:25:57.651947: step: 1716/529, loss: 0.008055990561842918
2023-01-24 06:25:58.688512: step: 1720/529, loss: 0.017830757424235344
2023-01-24 06:25:59.752245: step: 1724/529, loss: 0.026042364537715912
2023-01-24 06:26:00.802799: step: 1728/529, loss: 0.009538806043565273
2023-01-24 06:26:01.853520: step: 1732/529, loss: 0.02040978893637657
2023-01-24 06:26:02.899047: step: 1736/529, loss: 0.005226320121437311
2023-01-24 06:26:03.938564: step: 1740/529, loss: 0.01148279570043087
2023-01-24 06:26:04.995363: step: 1744/529, loss: 0.002418922958895564
2023-01-24 06:26:06.032748: step: 1748/529, loss: 0.0027232333086431026
2023-01-24 06:26:07.091795: step: 1752/529, loss: 0.0008075407240539789
2023-01-24 06:26:08.156615: step: 1756/529, loss: 0.015472984872758389
2023-01-24 06:26:09.217909: step: 1760/529, loss: 0.0021383606363087893
2023-01-24 06:26:10.280285: step: 1764/529, loss: 0.0044258409179747105
2023-01-24 06:26:11.334608: step: 1768/529, loss: 0.028770407661795616
2023-01-24 06:26:12.382095: step: 1772/529, loss: 0.003733373247087002
2023-01-24 06:26:13.439526: step: 1776/529, loss: 0.01202247105538845
2023-01-24 06:26:14.492529: step: 1780/529, loss: 0.0035271558444947004
2023-01-24 06:26:15.556514: step: 1784/529, loss: 0.018062949180603027
2023-01-24 06:26:16.607584: step: 1788/529, loss: 4.362559047876857e-05
2023-01-24 06:26:17.661624: step: 1792/529, loss: 0.017346929758787155
2023-01-24 06:26:18.723637: step: 1796/529, loss: 0.01283997017890215
2023-01-24 06:26:19.785084: step: 1800/529, loss: 0.041725918650627136
2023-01-24 06:26:20.834999: step: 1804/529, loss: 0.0027287781704217196
2023-01-24 06:26:21.891586: step: 1808/529, loss: 0.01752067171037197
2023-01-24 06:26:22.934026: step: 1812/529, loss: 0.004307575523853302
2023-01-24 06:26:23.966517: step: 1816/529, loss: 0.00557295884937048
2023-01-24 06:26:24.994766: step: 1820/529, loss: 0.00024069013306871057
2023-01-24 06:26:26.042205: step: 1824/529, loss: 0.008719326928257942
2023-01-24 06:26:27.088469: step: 1828/529, loss: 0.005578347481787205
2023-01-24 06:26:28.145808: step: 1832/529, loss: 0.015396920032799244
2023-01-24 06:26:29.203322: step: 1836/529, loss: 0.008813274092972279
2023-01-24 06:26:30.247687: step: 1840/529, loss: 0.01484970934689045
2023-01-24 06:26:31.297068: step: 1844/529, loss: 0.0043105692602694035
2023-01-24 06:26:32.331213: step: 1848/529, loss: 0.027481095865368843
2023-01-24 06:26:33.386796: step: 1852/529, loss: 0.008960974402725697
2023-01-24 06:26:34.449726: step: 1856/529, loss: 0.007280465215444565
2023-01-24 06:26:35.494954: step: 1860/529, loss: 0.003491520183160901
2023-01-24 06:26:36.581150: step: 1864/529, loss: 0.06849480420351028
2023-01-24 06:26:37.633458: step: 1868/529, loss: 3.203741272272964e-08
2023-01-24 06:26:38.674012: step: 1872/529, loss: 0.028073083609342575
2023-01-24 06:26:39.726223: step: 1876/529, loss: 0.0019630317110568285
2023-01-24 06:26:40.781505: step: 1880/529, loss: 0.010865608230233192
2023-01-24 06:26:41.833788: step: 1884/529, loss: 0.008823062293231487
2023-01-24 06:26:42.883864: step: 1888/529, loss: 0.01453643012791872
2023-01-24 06:26:43.955765: step: 1892/529, loss: 0.008397593162953854
2023-01-24 06:26:45.010731: step: 1896/529, loss: 0.009981879964470863
2023-01-24 06:26:46.068292: step: 1900/529, loss: 0.015491724014282227
2023-01-24 06:26:47.107525: step: 1904/529, loss: 0.01963350549340248
2023-01-24 06:26:48.153655: step: 1908/529, loss: 0.006219983100891113
2023-01-24 06:26:49.235323: step: 1912/529, loss: 0.0020787317771464586
2023-01-24 06:26:50.279972: step: 1916/529, loss: 0.01209577638655901
2023-01-24 06:26:51.337930: step: 1920/529, loss: 0.01098283939063549
2023-01-24 06:26:52.411992: step: 1924/529, loss: 0.020216599106788635
2023-01-24 06:26:53.450608: step: 1928/529, loss: 0.001231981790624559
2023-01-24 06:26:54.493456: step: 1932/529, loss: 0.013211369514465332
2023-01-24 06:26:55.531680: step: 1936/529, loss: 0.004367074929177761
2023-01-24 06:26:56.566487: step: 1940/529, loss: 0.006536758970469236
2023-01-24 06:26:57.614596: step: 1944/529, loss: 0.015867548063397408
2023-01-24 06:26:58.682430: step: 1948/529, loss: 0.01573462225496769
2023-01-24 06:26:59.710333: step: 1952/529, loss: 0.02607549913227558
2023-01-24 06:27:00.748270: step: 1956/529, loss: 0.006091012619435787
2023-01-24 06:27:01.788291: step: 1960/529, loss: 0.0029211300425231457
2023-01-24 06:27:02.827918: step: 1964/529, loss: 0.0058385953307151794
2023-01-24 06:27:03.867415: step: 1968/529, loss: 0.0616777129471302
2023-01-24 06:27:04.913049: step: 1972/529, loss: 0.0019854146521538496
2023-01-24 06:27:05.958501: step: 1976/529, loss: 0.025478098541498184
2023-01-24 06:27:06.999711: step: 1980/529, loss: 0.02005152218043804
2023-01-24 06:27:08.053349: step: 1984/529, loss: 0.012796014547348022
2023-01-24 06:27:09.107918: step: 1988/529, loss: 0.03704017400741577
2023-01-24 06:27:10.165458: step: 1992/529, loss: 0.012510542757809162
2023-01-24 06:27:11.216824: step: 1996/529, loss: 0.008263529278337955
2023-01-24 06:27:12.265137: step: 2000/529, loss: 0.007862303406000137
2023-01-24 06:27:13.316247: step: 2004/529, loss: 0.0045217182487249374
2023-01-24 06:27:14.391136: step: 2008/529, loss: 0.005549720488488674
2023-01-24 06:27:15.432129: step: 2012/529, loss: 0.006743513513356447
2023-01-24 06:27:16.477127: step: 2016/529, loss: 0.006827748380601406
2023-01-24 06:27:17.531970: step: 2020/529, loss: 0.014867347665131092
2023-01-24 06:27:18.602629: step: 2024/529, loss: 0.037739746272563934
2023-01-24 06:27:19.640945: step: 2028/529, loss: 0.010698607191443443
2023-01-24 06:27:20.679559: step: 2032/529, loss: 0.013002397492527962
2023-01-24 06:27:21.733157: step: 2036/529, loss: 0.004617432598024607
2023-01-24 06:27:22.772727: step: 2040/529, loss: 0.012744104489684105
2023-01-24 06:27:23.825864: step: 2044/529, loss: 0.006440219469368458
2023-01-24 06:27:24.863766: step: 2048/529, loss: 0.02469000592827797
2023-01-24 06:27:25.908200: step: 2052/529, loss: 0.0010574222542345524
2023-01-24 06:27:26.951658: step: 2056/529, loss: 0.0030768837314099073
2023-01-24 06:27:28.006067: step: 2060/529, loss: 0.003656399203464389
2023-01-24 06:27:29.066016: step: 2064/529, loss: 0.001612451276741922
2023-01-24 06:27:30.109627: step: 2068/529, loss: 0.004286501090973616
2023-01-24 06:27:31.163399: step: 2072/529, loss: 0.008329802192747593
2023-01-24 06:27:32.210900: step: 2076/529, loss: 0.004642146173864603
2023-01-24 06:27:33.267521: step: 2080/529, loss: 0.0008475060458295047
2023-01-24 06:27:34.313226: step: 2084/529, loss: 0.012219317257404327
2023-01-24 06:27:35.340790: step: 2088/529, loss: 0.0028849546797573566
2023-01-24 06:27:36.372686: step: 2092/529, loss: 0.0019038283498957753
2023-01-24 06:27:37.429722: step: 2096/529, loss: 0.0038213240914046764
2023-01-24 06:27:38.483002: step: 2100/529, loss: 0.007835282944142818
2023-01-24 06:27:39.541409: step: 2104/529, loss: 0.001253671245649457
2023-01-24 06:27:40.595126: step: 2108/529, loss: 0.0258998554199934
2023-01-24 06:27:41.636187: step: 2112/529, loss: 0.004032108001410961
2023-01-24 06:27:42.676517: step: 2116/529, loss: 0.008642514236271381
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32697727878464816, 'r': 0.33256133098400653, 'f1': 0.32974566590512033}, 'combined': 0.24297049066693077, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37270870321636757, 'r': 0.30343561963426785, 'f1': 0.3345235402605781}, 'combined': 0.23534319415317057, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3592823093220339, 'r': 0.32178605313092984, 'f1': 0.33950200200200203}, 'combined': 0.250159369896212, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3937584000965213, 'r': 0.3205729382984768, 'f1': 0.3534166303896627}, 'combined': 0.2509258075766605, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32864373150390097, 'r': 0.33113818107888315, 'f1': 0.3298862408857683}, 'combined': 0.24307407223161873, 'stategy': 1, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3706665443853898, 'r': 0.2995089180635872, 'f1': 0.3313100580124237}, 'combined': 0.2330824528730619, 'stategy': 1, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:30:14.352997: step: 4/529, loss: 0.0023045274429023266
2023-01-24 06:30:15.384122: step: 8/529, loss: 0.011228933930397034
2023-01-24 06:30:16.418183: step: 12/529, loss: 0.004253579769283533
2023-01-24 06:30:17.459256: step: 16/529, loss: 0.021976569667458534
2023-01-24 06:30:18.496207: step: 20/529, loss: 0.006206500809639692
2023-01-24 06:30:19.532070: step: 24/529, loss: 0.006819066591560841
2023-01-24 06:30:20.589017: step: 28/529, loss: 0.0112458486109972
2023-01-24 06:30:21.624710: step: 32/529, loss: 0.011133863590657711
2023-01-24 06:30:22.667100: step: 36/529, loss: 0.03443567082285881
2023-01-24 06:30:23.699367: step: 40/529, loss: 0.02194317616522312
2023-01-24 06:30:24.736878: step: 44/529, loss: 0.0016771041555330157
2023-01-24 06:30:25.770568: step: 48/529, loss: 0.007127740420401096
2023-01-24 06:30:26.803633: step: 52/529, loss: 0.0048787579871714115
2023-01-24 06:30:27.853676: step: 56/529, loss: 0.00648889783769846
2023-01-24 06:30:28.903256: step: 60/529, loss: 0.06373632699251175
2023-01-24 06:30:29.943791: step: 64/529, loss: 0.009561716578900814
2023-01-24 06:30:30.976169: step: 68/529, loss: 0.0013499922351911664
2023-01-24 06:30:32.011694: step: 72/529, loss: 0.0023670061491429806
2023-01-24 06:30:33.050550: step: 76/529, loss: 0.003257190575823188
2023-01-24 06:30:34.091794: step: 80/529, loss: 0.007145741954445839
2023-01-24 06:30:35.155043: step: 84/529, loss: 0.010281720198690891
2023-01-24 06:30:36.196676: step: 88/529, loss: 0.007999295368790627
2023-01-24 06:30:37.239739: step: 92/529, loss: 0.000205404227017425
2023-01-24 06:30:38.280582: step: 96/529, loss: 0.00958223920315504
2023-01-24 06:30:39.323516: step: 100/529, loss: 0.008379525505006313
2023-01-24 06:30:40.386496: step: 104/529, loss: 0.031177092343568802
2023-01-24 06:30:41.426136: step: 108/529, loss: 0.001502710161730647
2023-01-24 06:30:42.468854: step: 112/529, loss: 0.004969471134245396
2023-01-24 06:30:43.526058: step: 116/529, loss: 0.008130726404488087
2023-01-24 06:30:44.572446: step: 120/529, loss: 0.007696308195590973
2023-01-24 06:30:45.602961: step: 124/529, loss: 0.004909994546324015
2023-01-24 06:30:46.641024: step: 128/529, loss: 0.006238368805497885
2023-01-24 06:30:47.683913: step: 132/529, loss: 0.004564911127090454
2023-01-24 06:30:48.713809: step: 136/529, loss: 0.001993659185245633
2023-01-24 06:30:49.765691: step: 140/529, loss: 0.006207111291587353
2023-01-24 06:30:50.798479: step: 144/529, loss: 0.0020644920878112316
2023-01-24 06:30:51.848890: step: 148/529, loss: 0.006921760272234678
2023-01-24 06:30:52.879784: step: 152/529, loss: 7.124265539459884e-05
2023-01-24 06:30:53.942812: step: 156/529, loss: 0.06694398820400238
2023-01-24 06:30:54.995094: step: 160/529, loss: 0.0016502841608598828
2023-01-24 06:30:56.039626: step: 164/529, loss: 0.004898045677691698
2023-01-24 06:30:57.068023: step: 168/529, loss: 0.004016496241092682
2023-01-24 06:30:58.102998: step: 172/529, loss: 0.000222889706492424
2023-01-24 06:30:59.149095: step: 176/529, loss: 0.005828389432281256
2023-01-24 06:31:00.210788: step: 180/529, loss: 0.005710930563509464
2023-01-24 06:31:01.267235: step: 184/529, loss: 0.0019523096270859241
2023-01-24 06:31:02.302662: step: 188/529, loss: 0.0022768601775169373
2023-01-24 06:31:03.333465: step: 192/529, loss: 0.03230486065149307
2023-01-24 06:31:04.360783: step: 196/529, loss: 0.01586371660232544
2023-01-24 06:31:05.400636: step: 200/529, loss: 0.014680094085633755
2023-01-24 06:31:06.453029: step: 204/529, loss: 0.005278198514133692
2023-01-24 06:31:07.489300: step: 208/529, loss: 0.010319733060896397
2023-01-24 06:31:08.525410: step: 212/529, loss: 0.003149011405184865
2023-01-24 06:31:09.563766: step: 216/529, loss: 0.005597005132585764
2023-01-24 06:31:10.607194: step: 220/529, loss: 0.0010876570595428348
2023-01-24 06:31:11.641476: step: 224/529, loss: 0.00404005404561758
2023-01-24 06:31:12.665517: step: 228/529, loss: 0.004743700847029686
2023-01-24 06:31:13.691948: step: 232/529, loss: 0.017000112682580948
2023-01-24 06:31:14.736150: step: 236/529, loss: 0.00542871467769146
2023-01-24 06:31:15.780932: step: 240/529, loss: 0.003282651538029313
2023-01-24 06:31:16.828937: step: 244/529, loss: 0.0023716045543551445
2023-01-24 06:31:17.888385: step: 248/529, loss: 0.0062157646752893925
2023-01-24 06:31:18.932656: step: 252/529, loss: 0.0042026755400002
2023-01-24 06:31:19.980690: step: 256/529, loss: 0.009019405581057072
2023-01-24 06:31:21.038768: step: 260/529, loss: 0.00553872948512435
2023-01-24 06:31:22.093640: step: 264/529, loss: 0.03417680412530899
2023-01-24 06:31:23.144351: step: 268/529, loss: 0.010676387697458267
2023-01-24 06:31:24.183684: step: 272/529, loss: 0.003809739602729678
2023-01-24 06:31:25.216239: step: 276/529, loss: 0.01024115364998579
2023-01-24 06:31:26.262439: step: 280/529, loss: 0.003652864834293723
2023-01-24 06:31:27.301219: step: 284/529, loss: 0.008994110859930515
2023-01-24 06:31:28.347254: step: 288/529, loss: 0.0377771221101284
2023-01-24 06:31:29.386786: step: 292/529, loss: 0.014945383183658123
2023-01-24 06:31:30.435617: step: 296/529, loss: 0.009220863692462444
2023-01-24 06:31:31.472872: step: 300/529, loss: 0.0026840995997190475
2023-01-24 06:31:32.515608: step: 304/529, loss: 0.0006836710963398218
2023-01-24 06:31:33.555197: step: 308/529, loss: 0.004090073984116316
2023-01-24 06:31:34.599605: step: 312/529, loss: 0.001996321137994528
2023-01-24 06:31:35.637851: step: 316/529, loss: 0.01451816689223051
2023-01-24 06:31:36.680628: step: 320/529, loss: 0.0025968351401388645
2023-01-24 06:31:37.724650: step: 324/529, loss: 0.003326504025608301
2023-01-24 06:31:38.776441: step: 328/529, loss: 0.0036721371579915285
2023-01-24 06:31:39.807988: step: 332/529, loss: 0.0005125876050442457
2023-01-24 06:31:40.873000: step: 336/529, loss: 0.009359709918498993
2023-01-24 06:31:41.915069: step: 340/529, loss: 0.006428618915379047
2023-01-24 06:31:42.968242: step: 344/529, loss: 0.01610073819756508
2023-01-24 06:31:44.019300: step: 348/529, loss: 0.001758598256856203
2023-01-24 06:31:45.056588: step: 352/529, loss: 0.014601621776819229
2023-01-24 06:31:46.103788: step: 356/529, loss: 0.020786141976714134
2023-01-24 06:31:47.165362: step: 360/529, loss: 0.004753530956804752
2023-01-24 06:31:48.207024: step: 364/529, loss: 0.0029584027361124754
2023-01-24 06:31:49.258532: step: 368/529, loss: 0.0018564896890893579
2023-01-24 06:31:50.291882: step: 372/529, loss: 0.002674866234883666
2023-01-24 06:31:51.321869: step: 376/529, loss: 0.0014381998917087913
2023-01-24 06:31:52.356083: step: 380/529, loss: 0.0005801094812341034
2023-01-24 06:31:53.393493: step: 384/529, loss: 0.007998351939022541
2023-01-24 06:31:54.456124: step: 388/529, loss: 0.0054602669551968575
2023-01-24 06:31:55.487018: step: 392/529, loss: 0.012484036386013031
2023-01-24 06:31:56.527248: step: 396/529, loss: 0.003845102619379759
2023-01-24 06:31:57.557640: step: 400/529, loss: 0.000901897728908807
2023-01-24 06:31:58.587814: step: 404/529, loss: 0.010156513191759586
2023-01-24 06:31:59.620380: step: 408/529, loss: 0.053882233798503876
2023-01-24 06:32:00.673473: step: 412/529, loss: 0.0032782733906060457
2023-01-24 06:32:01.727445: step: 416/529, loss: 0.013057449832558632
2023-01-24 06:32:02.778273: step: 420/529, loss: 0.018242230638861656
2023-01-24 06:32:03.826559: step: 424/529, loss: 0.0039817881770431995
2023-01-24 06:32:04.866885: step: 428/529, loss: 0.010982389561831951
2023-01-24 06:32:05.914729: step: 432/529, loss: 0.022366533055901527
2023-01-24 06:32:06.949949: step: 436/529, loss: 0.006050330586731434
2023-01-24 06:32:07.997379: step: 440/529, loss: 0.0035406271927058697
2023-01-24 06:32:09.037664: step: 444/529, loss: 0.001523448503576219
2023-01-24 06:32:10.088391: step: 448/529, loss: 0.012140117585659027
2023-01-24 06:32:11.143767: step: 452/529, loss: 0.006151004694402218
2023-01-24 06:32:12.201714: step: 456/529, loss: 0.009581267833709717
2023-01-24 06:32:13.254264: step: 460/529, loss: 0.014867383986711502
2023-01-24 06:32:14.285158: step: 464/529, loss: 0.0007373564876616001
2023-01-24 06:32:15.330075: step: 468/529, loss: 0.007127965800464153
2023-01-24 06:32:16.387117: step: 472/529, loss: 0.032232873141765594
2023-01-24 06:32:17.431111: step: 476/529, loss: 0.0012849037302657962
2023-01-24 06:32:18.465830: step: 480/529, loss: 0.0035016729962080717
2023-01-24 06:32:19.507683: step: 484/529, loss: 0.004301457665860653
2023-01-24 06:32:20.549180: step: 488/529, loss: 0.012563398107886314
2023-01-24 06:32:21.594720: step: 492/529, loss: 0.030823377892374992
2023-01-24 06:32:22.638085: step: 496/529, loss: 0.04405725374817848
2023-01-24 06:32:23.680545: step: 500/529, loss: 0.036730095744132996
2023-01-24 06:32:24.732156: step: 504/529, loss: 0.01858927123248577
2023-01-24 06:32:25.775851: step: 508/529, loss: 0.015251416712999344
2023-01-24 06:32:26.828964: step: 512/529, loss: 0.002448983723297715
2023-01-24 06:32:27.874083: step: 516/529, loss: 0.01166907325387001
2023-01-24 06:32:28.915172: step: 520/529, loss: 0.003254219191148877
2023-01-24 06:32:29.970916: step: 524/529, loss: 0.0464460551738739
2023-01-24 06:32:31.008440: step: 528/529, loss: 0.0031164067331701517
2023-01-24 06:32:32.048735: step: 532/529, loss: 0.009115656837821007
2023-01-24 06:32:33.101041: step: 536/529, loss: 0.009100779891014099
2023-01-24 06:32:34.130603: step: 540/529, loss: 0.0
2023-01-24 06:32:35.165231: step: 544/529, loss: 0.010497533716261387
2023-01-24 06:32:36.228768: step: 548/529, loss: 0.02581813745200634
2023-01-24 06:32:37.261263: step: 552/529, loss: 0.011672892607748508
2023-01-24 06:32:38.303713: step: 556/529, loss: 0.001962442649528384
2023-01-24 06:32:39.335897: step: 560/529, loss: 0.008429953828454018
2023-01-24 06:32:40.372171: step: 564/529, loss: 0.0024303190875798464
2023-01-24 06:32:41.408844: step: 568/529, loss: 0.00038723612669855356
2023-01-24 06:32:42.442794: step: 572/529, loss: 0.013444959186017513
2023-01-24 06:32:43.498396: step: 576/529, loss: 0.01430303230881691
2023-01-24 06:32:44.535305: step: 580/529, loss: 0.009034675545990467
2023-01-24 06:32:45.600393: step: 584/529, loss: 0.006245921831578016
2023-01-24 06:32:46.637329: step: 588/529, loss: 0.00422328058630228
2023-01-24 06:32:47.673955: step: 592/529, loss: 0.0333227813243866
2023-01-24 06:32:48.713138: step: 596/529, loss: 0.003813460934907198
2023-01-24 06:32:49.781725: step: 600/529, loss: 0.00518802460283041
2023-01-24 06:32:50.822109: step: 604/529, loss: 0.004532285500317812
2023-01-24 06:32:51.866439: step: 608/529, loss: 0.004152851644903421
2023-01-24 06:32:52.903161: step: 612/529, loss: 0.002888813614845276
2023-01-24 06:32:53.946119: step: 616/529, loss: 0.0029874832835048437
2023-01-24 06:32:54.991206: step: 620/529, loss: 0.012224213220179081
2023-01-24 06:32:56.035288: step: 624/529, loss: 0.005523674190044403
2023-01-24 06:32:57.083839: step: 628/529, loss: 0.011892084032297134
2023-01-24 06:32:58.121709: step: 632/529, loss: 0.004358323756605387
2023-01-24 06:32:59.173101: step: 636/529, loss: 0.0020290189422667027
2023-01-24 06:33:00.215657: step: 640/529, loss: 0.005568331573158503
2023-01-24 06:33:01.261508: step: 644/529, loss: 0.00047043198719620705
2023-01-24 06:33:02.299750: step: 648/529, loss: 0.015411232598125935
2023-01-24 06:33:03.351409: step: 652/529, loss: 0.0385340191423893
2023-01-24 06:33:04.381247: step: 656/529, loss: 0.006036559119820595
2023-01-24 06:33:05.420609: step: 660/529, loss: 0.0030251743737608194
2023-01-24 06:33:06.498078: step: 664/529, loss: 0.0003360217378940433
2023-01-24 06:33:07.542064: step: 668/529, loss: 0.0020887404680252075
2023-01-24 06:33:08.595967: step: 672/529, loss: 0.005592403933405876
2023-01-24 06:33:09.636820: step: 676/529, loss: 3.7154324672883376e-05
2023-01-24 06:33:10.687415: step: 680/529, loss: 0.0002183835895266384
2023-01-24 06:33:11.735357: step: 684/529, loss: 0.03913566470146179
2023-01-24 06:33:12.783803: step: 688/529, loss: 0.0005605136975646019
2023-01-24 06:33:13.835547: step: 692/529, loss: 0.023040948435664177
2023-01-24 06:33:14.875182: step: 696/529, loss: 0.003610490122810006
2023-01-24 06:33:15.920391: step: 700/529, loss: 0.0033817924559116364
2023-01-24 06:33:16.956707: step: 704/529, loss: 0.0011157958069816232
2023-01-24 06:33:17.998002: step: 708/529, loss: 0.004889626521617174
2023-01-24 06:33:19.034125: step: 712/529, loss: 0.008227786980569363
2023-01-24 06:33:20.088536: step: 716/529, loss: 0.009387004189193249
2023-01-24 06:33:21.120810: step: 720/529, loss: 0.00011768360127462074
2023-01-24 06:33:22.154687: step: 724/529, loss: 0.0030078573618084192
2023-01-24 06:33:23.189278: step: 728/529, loss: 7.887894025770947e-05
2023-01-24 06:33:24.241172: step: 732/529, loss: 0.0013173844199627638
2023-01-24 06:33:25.288195: step: 736/529, loss: 0.004169007297605276
2023-01-24 06:33:26.348102: step: 740/529, loss: 0.006584996823221445
2023-01-24 06:33:27.401652: step: 744/529, loss: 0.003529854817315936
2023-01-24 06:33:28.459588: step: 748/529, loss: 0.004300139844417572
2023-01-24 06:33:29.523874: step: 752/529, loss: 0.0019124459940940142
2023-01-24 06:33:30.580311: step: 756/529, loss: 0.00455786008387804
2023-01-24 06:33:31.631833: step: 760/529, loss: 0.016308844089508057
2023-01-24 06:33:32.686519: step: 764/529, loss: 0.026593182235956192
2023-01-24 06:33:33.717499: step: 768/529, loss: 0.030140027403831482
2023-01-24 06:33:34.757802: step: 772/529, loss: 0.004473466891795397
2023-01-24 06:33:35.801438: step: 776/529, loss: 0.01213291846215725
2023-01-24 06:33:36.828165: step: 780/529, loss: 0.013113019056618214
2023-01-24 06:33:37.896825: step: 784/529, loss: 0.0051805018447339535
2023-01-24 06:33:38.930185: step: 788/529, loss: 0.0035665922332555056
2023-01-24 06:33:39.976885: step: 792/529, loss: 0.005198049359023571
2023-01-24 06:33:41.034326: step: 796/529, loss: 0.00770610012114048
2023-01-24 06:33:42.077488: step: 800/529, loss: 0.008671020157635212
2023-01-24 06:33:43.131466: step: 804/529, loss: 0.015641216188669205
2023-01-24 06:33:44.167617: step: 808/529, loss: 0.003296887269243598
2023-01-24 06:33:45.219460: step: 812/529, loss: 0.003373671555891633
2023-01-24 06:33:46.274698: step: 816/529, loss: 0.019740156829357147
2023-01-24 06:33:47.317813: step: 820/529, loss: 0.011013539507985115
2023-01-24 06:33:48.368285: step: 824/529, loss: 0.008105099201202393
2023-01-24 06:33:49.461724: step: 828/529, loss: 0.007988348603248596
2023-01-24 06:33:50.505780: step: 832/529, loss: 0.002680855104699731
2023-01-24 06:33:51.550789: step: 836/529, loss: 0.0035361938644200563
2023-01-24 06:33:52.601576: step: 840/529, loss: 0.002939994214102626
2023-01-24 06:33:53.656854: step: 844/529, loss: 0.002155761234462261
2023-01-24 06:33:54.719575: step: 848/529, loss: 0.0012092282995581627
2023-01-24 06:33:55.764505: step: 852/529, loss: 0.007570883724838495
2023-01-24 06:33:56.812699: step: 856/529, loss: 0.002645100699737668
2023-01-24 06:33:57.870952: step: 860/529, loss: 0.017419008538126945
2023-01-24 06:33:58.908642: step: 864/529, loss: 0.0007256052922457457
2023-01-24 06:33:59.950454: step: 868/529, loss: 0.003953471779823303
2023-01-24 06:34:00.974963: step: 872/529, loss: 0.00542035885155201
2023-01-24 06:34:02.020092: step: 876/529, loss: 0.0033736240584403276
2023-01-24 06:34:03.067570: step: 880/529, loss: 0.006717555690556765
2023-01-24 06:34:04.100187: step: 884/529, loss: 0.002057659672573209
2023-01-24 06:34:05.155112: step: 888/529, loss: 0.038611918687820435
2023-01-24 06:34:06.204954: step: 892/529, loss: 0.012965199537575245
2023-01-24 06:34:07.231525: step: 896/529, loss: 0.01855887845158577
2023-01-24 06:34:08.283000: step: 900/529, loss: 0.014985074289143085
2023-01-24 06:34:09.333339: step: 904/529, loss: 0.030968019738793373
2023-01-24 06:34:10.391266: step: 908/529, loss: 0.033924926072359085
2023-01-24 06:34:11.443735: step: 912/529, loss: 0.003549429355189204
2023-01-24 06:34:12.520232: step: 916/529, loss: 0.0009133667917922139
2023-01-24 06:34:13.566597: step: 920/529, loss: 0.006067577749490738
2023-01-24 06:34:14.617901: step: 924/529, loss: 0.0076386407017707825
2023-01-24 06:34:15.662688: step: 928/529, loss: 0.005393982399255037
2023-01-24 06:34:16.695293: step: 932/529, loss: 0.0028873516712337732
2023-01-24 06:34:17.743354: step: 936/529, loss: 7.591808389406651e-05
2023-01-24 06:34:18.790275: step: 940/529, loss: 0.0061194030568003654
2023-01-24 06:34:19.835471: step: 944/529, loss: 0.0017075904179364443
2023-01-24 06:34:20.884282: step: 948/529, loss: 0.013637788593769073
2023-01-24 06:34:21.904969: step: 952/529, loss: 0.0040211803279817104
2023-01-24 06:34:22.941741: step: 956/529, loss: 0.008782819844782352
2023-01-24 06:34:23.987782: step: 960/529, loss: 0.009358215145766735
2023-01-24 06:34:25.028244: step: 964/529, loss: 0.004064645618200302
2023-01-24 06:34:26.062077: step: 968/529, loss: 0.0026523994747549295
2023-01-24 06:34:27.104182: step: 972/529, loss: 0.00479916762560606
2023-01-24 06:34:28.154274: step: 976/529, loss: 0.012865317054092884
2023-01-24 06:34:29.182797: step: 980/529, loss: 0.00043983873911201954
2023-01-24 06:34:30.203724: step: 984/529, loss: 0.0053704543970525265
2023-01-24 06:34:31.256122: step: 988/529, loss: 0.006389323156327009
2023-01-24 06:34:32.314511: step: 992/529, loss: 0.00329760042950511
2023-01-24 06:34:33.352912: step: 996/529, loss: 0.015907973051071167
2023-01-24 06:34:34.380935: step: 1000/529, loss: 0.0013318161945790052
2023-01-24 06:34:35.432351: step: 1004/529, loss: 0.01142899040132761
2023-01-24 06:34:36.484013: step: 1008/529, loss: 0.017719736322760582
2023-01-24 06:34:37.522256: step: 1012/529, loss: 0.001215964788571
2023-01-24 06:34:38.566746: step: 1016/529, loss: 0.0021219556219875813
2023-01-24 06:34:39.613000: step: 1020/529, loss: 0.006792683620005846
2023-01-24 06:34:40.667800: step: 1024/529, loss: 0.01315910741686821
2023-01-24 06:34:41.703645: step: 1028/529, loss: 0.003544391365721822
2023-01-24 06:34:42.747589: step: 1032/529, loss: 0.01260813232511282
2023-01-24 06:34:43.793550: step: 1036/529, loss: 0.01115341205149889
2023-01-24 06:34:44.845292: step: 1040/529, loss: 0.0018189814873039722
2023-01-24 06:34:45.886553: step: 1044/529, loss: 0.0248299241065979
2023-01-24 06:34:46.921115: step: 1048/529, loss: 0.0036285428795963526
2023-01-24 06:34:47.969018: step: 1052/529, loss: 0.005281612277030945
2023-01-24 06:34:49.012994: step: 1056/529, loss: 0.007375138811767101
2023-01-24 06:34:50.043004: step: 1060/529, loss: 0.0008645905181765556
2023-01-24 06:34:51.074219: step: 1064/529, loss: 7.84682561061345e-05
2023-01-24 06:34:52.112302: step: 1068/529, loss: 0.005328230559825897
2023-01-24 06:34:53.162783: step: 1072/529, loss: 0.00221210322342813
2023-01-24 06:34:54.189088: step: 1076/529, loss: 0.008061792701482773
2023-01-24 06:34:55.243964: step: 1080/529, loss: 0.010331466794013977
2023-01-24 06:34:56.290787: step: 1084/529, loss: 0.004379634745419025
2023-01-24 06:34:57.327414: step: 1088/529, loss: 0.0032090258318930864
2023-01-24 06:34:58.391529: step: 1092/529, loss: 0.002273597987368703
2023-01-24 06:34:59.434069: step: 1096/529, loss: 0.011950631625950336
2023-01-24 06:35:00.479739: step: 1100/529, loss: 0.0032040292862802744
2023-01-24 06:35:01.519966: step: 1104/529, loss: 0.02441319450736046
2023-01-24 06:35:02.571890: step: 1108/529, loss: 0.0013557999627664685
2023-01-24 06:35:03.615355: step: 1112/529, loss: 0.015338200144469738
2023-01-24 06:35:04.670684: step: 1116/529, loss: 0.012637415900826454
2023-01-24 06:35:05.713864: step: 1120/529, loss: 0.010589070618152618
2023-01-24 06:35:06.777420: step: 1124/529, loss: 0.00889888871461153
2023-01-24 06:35:07.860784: step: 1128/529, loss: 0.04252238571643829
2023-01-24 06:35:08.927121: step: 1132/529, loss: 0.014491250738501549
2023-01-24 06:35:09.965301: step: 1136/529, loss: 0.02215750329196453
2023-01-24 06:35:11.019167: step: 1140/529, loss: 0.003690396435558796
2023-01-24 06:35:12.062841: step: 1144/529, loss: 0.008793325163424015
2023-01-24 06:35:13.121570: step: 1148/529, loss: 0.0024294236209243536
2023-01-24 06:35:14.166377: step: 1152/529, loss: 0.006633859593421221
2023-01-24 06:35:15.206019: step: 1156/529, loss: 0.002428903244435787
2023-01-24 06:35:16.239495: step: 1160/529, loss: 0.00016320333816111088
2023-01-24 06:35:17.287172: step: 1164/529, loss: 0.01386997476220131
2023-01-24 06:35:18.315208: step: 1168/529, loss: 0.00738599942997098
2023-01-24 06:35:19.352371: step: 1172/529, loss: 0.006210622377693653
2023-01-24 06:35:20.397529: step: 1176/529, loss: 0.005919476505368948
2023-01-24 06:35:21.432674: step: 1180/529, loss: 0.003125750692561269
2023-01-24 06:35:22.492182: step: 1184/529, loss: 0.008433100767433643
2023-01-24 06:35:23.541934: step: 1188/529, loss: 0.0072503420524299145
2023-01-24 06:35:24.606995: step: 1192/529, loss: 0.007994864135980606
2023-01-24 06:35:25.655983: step: 1196/529, loss: 0.027764689177274704
2023-01-24 06:35:26.701931: step: 1200/529, loss: 0.0020462661050260067
2023-01-24 06:35:27.749605: step: 1204/529, loss: 3.4006596251856536e-05
2023-01-24 06:35:28.793427: step: 1208/529, loss: 0.01064429059624672
2023-01-24 06:35:29.860148: step: 1212/529, loss: 0.003012238536030054
2023-01-24 06:35:30.904789: step: 1216/529, loss: 0.03419587388634682
2023-01-24 06:35:31.952646: step: 1220/529, loss: 0.0023410115391016006
2023-01-24 06:35:32.986493: step: 1224/529, loss: 0.015048685483634472
2023-01-24 06:35:34.071894: step: 1228/529, loss: 0.016846148297190666
2023-01-24 06:35:35.121638: step: 1232/529, loss: 0.00884309969842434
2023-01-24 06:35:36.163626: step: 1236/529, loss: 0.0032399767078459263
2023-01-24 06:35:37.202312: step: 1240/529, loss: 0.0198514387011528
2023-01-24 06:35:38.239570: step: 1244/529, loss: 0.001148194307461381
2023-01-24 06:35:39.294364: step: 1248/529, loss: 0.015299823135137558
2023-01-24 06:35:40.341635: step: 1252/529, loss: 0.004690001253038645
2023-01-24 06:35:41.408865: step: 1256/529, loss: 0.006144427694380283
2023-01-24 06:35:42.451957: step: 1260/529, loss: 0.008631566539406776
2023-01-24 06:35:43.498123: step: 1264/529, loss: 0.020800327882170677
2023-01-24 06:35:44.542286: step: 1268/529, loss: 0.003588703228160739
2023-01-24 06:35:45.592058: step: 1272/529, loss: 0.0070841144770383835
2023-01-24 06:35:46.627344: step: 1276/529, loss: 0.0013627351727336645
2023-01-24 06:35:47.680069: step: 1280/529, loss: 0.010242646560072899
2023-01-24 06:35:48.743965: step: 1284/529, loss: 0.012464502826333046
2023-01-24 06:35:49.788759: step: 1288/529, loss: 0.026520315557718277
2023-01-24 06:35:50.835598: step: 1292/529, loss: 0.002117802621796727
2023-01-24 06:35:51.872930: step: 1296/529, loss: 0.014670378528535366
2023-01-24 06:35:52.912663: step: 1300/529, loss: 0.008451445028185844
2023-01-24 06:35:53.964167: step: 1304/529, loss: 0.05057818815112114
2023-01-24 06:35:55.005466: step: 1308/529, loss: 0.0013881870545446873
2023-01-24 06:35:56.052680: step: 1312/529, loss: 0.0060692536644637585
2023-01-24 06:35:57.085327: step: 1316/529, loss: 0.010907678864896297
2023-01-24 06:35:58.131922: step: 1320/529, loss: 0.003996334038674831
2023-01-24 06:35:59.185387: step: 1324/529, loss: 0.03376008942723274
2023-01-24 06:36:00.247399: step: 1328/529, loss: 0.005806329194456339
2023-01-24 06:36:01.283211: step: 1332/529, loss: 0.0014413440367206931
2023-01-24 06:36:02.319371: step: 1336/529, loss: 0.0020342892967164516
2023-01-24 06:36:03.346208: step: 1340/529, loss: 0.0023035078775137663
2023-01-24 06:36:04.385762: step: 1344/529, loss: 0.023279035463929176
2023-01-24 06:36:05.433693: step: 1348/529, loss: 0.006513782311230898
2023-01-24 06:36:06.499885: step: 1352/529, loss: 0.011667712591588497
2023-01-24 06:36:07.554191: step: 1356/529, loss: 0.008554453030228615
2023-01-24 06:36:08.609708: step: 1360/529, loss: 0.002800234593451023
2023-01-24 06:36:09.650226: step: 1364/529, loss: 0.010815789923071861
2023-01-24 06:36:10.707022: step: 1368/529, loss: 0.008118579164147377
2023-01-24 06:36:11.755280: step: 1372/529, loss: 0.001998700201511383
2023-01-24 06:36:12.810332: step: 1376/529, loss: 0.0020198209676891565
2023-01-24 06:36:13.849829: step: 1380/529, loss: 0.013016052544116974
2023-01-24 06:36:14.903440: step: 1384/529, loss: 0.03426613658666611
2023-01-24 06:36:15.964992: step: 1388/529, loss: 0.0
2023-01-24 06:36:17.003112: step: 1392/529, loss: 0.0031165643595159054
2023-01-24 06:36:18.051390: step: 1396/529, loss: 0.009783484973013401
2023-01-24 06:36:19.098914: step: 1400/529, loss: 0.011780040338635445
2023-01-24 06:36:20.175764: step: 1404/529, loss: 0.02556476928293705
2023-01-24 06:36:21.214721: step: 1408/529, loss: 0.0045912424102425575
2023-01-24 06:36:22.258374: step: 1412/529, loss: 0.0018574637360870838
2023-01-24 06:36:23.304855: step: 1416/529, loss: 0.006926057860255241
2023-01-24 06:36:24.333478: step: 1420/529, loss: 0.0006686334381811321
2023-01-24 06:36:25.384532: step: 1424/529, loss: 0.003066191216930747
2023-01-24 06:36:26.421313: step: 1428/529, loss: 0.000542367110028863
2023-01-24 06:36:27.476819: step: 1432/529, loss: 0.017975715920329094
2023-01-24 06:36:28.528509: step: 1436/529, loss: 0.0035078623332083225
2023-01-24 06:36:29.577631: step: 1440/529, loss: 0.008245199918746948
2023-01-24 06:36:30.649485: step: 1444/529, loss: 0.010481682606041431
2023-01-24 06:36:31.703800: step: 1448/529, loss: 0.006614771671593189
2023-01-24 06:36:32.744222: step: 1452/529, loss: 0.002646519336849451
2023-01-24 06:36:33.798220: step: 1456/529, loss: 0.010859166271984577
2023-01-24 06:36:34.854781: step: 1460/529, loss: 0.005819415673613548
2023-01-24 06:36:35.889656: step: 1464/529, loss: 0.007664044853299856
2023-01-24 06:36:36.928310: step: 1468/529, loss: 0.003635488450527191
2023-01-24 06:36:37.967224: step: 1472/529, loss: 0.013249932788312435
2023-01-24 06:36:39.025482: step: 1476/529, loss: 0.024490676820278168
2023-01-24 06:36:40.083765: step: 1480/529, loss: 0.0032691149972379208
2023-01-24 06:36:41.128804: step: 1484/529, loss: 0.00745146069675684
2023-01-24 06:36:42.190288: step: 1488/529, loss: 0.009740645065903664
2023-01-24 06:36:43.231286: step: 1492/529, loss: 0.006744786631315947
2023-01-24 06:36:44.278435: step: 1496/529, loss: 0.004934070631861687
2023-01-24 06:36:45.334673: step: 1500/529, loss: 0.0036018043756484985
2023-01-24 06:36:46.388776: step: 1504/529, loss: 0.008820726536214352
2023-01-24 06:36:47.419545: step: 1508/529, loss: 0.0027645002119243145
2023-01-24 06:36:48.469918: step: 1512/529, loss: 0.006532615050673485
2023-01-24 06:36:49.532115: step: 1516/529, loss: 0.018036650493741035
2023-01-24 06:36:50.597343: step: 1520/529, loss: 0.008637567982077599
2023-01-24 06:36:51.647254: step: 1524/529, loss: 0.00607710424810648
2023-01-24 06:36:52.697831: step: 1528/529, loss: 0.0010983337415382266
2023-01-24 06:36:53.742605: step: 1532/529, loss: 3.8286190829239786e-05
2023-01-24 06:36:54.818097: step: 1536/529, loss: 0.0023076815996319056
2023-01-24 06:36:55.864148: step: 1540/529, loss: 0.002279708394780755
2023-01-24 06:36:56.930415: step: 1544/529, loss: 0.0029560986440628767
2023-01-24 06:36:57.981730: step: 1548/529, loss: 0.0011503908317536116
2023-01-24 06:36:59.029892: step: 1552/529, loss: 0.004796003922820091
2023-01-24 06:37:00.081415: step: 1556/529, loss: 0.003004387952387333
2023-01-24 06:37:01.136783: step: 1560/529, loss: 0.011867834255099297
2023-01-24 06:37:02.158768: step: 1564/529, loss: 0.0016365665942430496
2023-01-24 06:37:03.204396: step: 1568/529, loss: 0.010986359789967537
2023-01-24 06:37:04.248501: step: 1572/529, loss: 0.0015012421645224094
2023-01-24 06:37:05.293222: step: 1576/529, loss: 0.012717810459434986
2023-01-24 06:37:06.369886: step: 1580/529, loss: 0.07196919620037079
2023-01-24 06:37:07.419913: step: 1584/529, loss: 0.0015860494459047914
2023-01-24 06:37:08.460296: step: 1588/529, loss: 0.00582316005602479
2023-01-24 06:37:09.507387: step: 1592/529, loss: 0.022280210629105568
2023-01-24 06:37:10.542388: step: 1596/529, loss: 0.005692686419934034
2023-01-24 06:37:11.610819: step: 1600/529, loss: 0.019194211810827255
2023-01-24 06:37:12.662805: step: 1604/529, loss: 0.007020164746791124
2023-01-24 06:37:13.725497: step: 1608/529, loss: 0.008333721198141575
2023-01-24 06:37:14.798889: step: 1612/529, loss: 0.008188854902982712
2023-01-24 06:37:15.849991: step: 1616/529, loss: 0.006952732801437378
2023-01-24 06:37:16.899125: step: 1620/529, loss: 0.004966230597347021
2023-01-24 06:37:17.935687: step: 1624/529, loss: 0.04598314315080643
2023-01-24 06:37:18.985846: step: 1628/529, loss: 0.001166617264971137
2023-01-24 06:37:20.023242: step: 1632/529, loss: 0.003217097371816635
2023-01-24 06:37:21.069641: step: 1636/529, loss: 0.007968607358634472
2023-01-24 06:37:22.123949: step: 1640/529, loss: 0.004410277586430311
2023-01-24 06:37:23.167788: step: 1644/529, loss: 0.006269694305956364
2023-01-24 06:37:24.202575: step: 1648/529, loss: 0.0014677905710414052
2023-01-24 06:37:25.251948: step: 1652/529, loss: 0.07598873972892761
2023-01-24 06:37:26.299002: step: 1656/529, loss: 0.005206728354096413
2023-01-24 06:37:27.366119: step: 1660/529, loss: 0.005225660279393196
2023-01-24 06:37:28.405470: step: 1664/529, loss: 0.004242300521582365
2023-01-24 06:37:29.443153: step: 1668/529, loss: 0.05876302719116211
2023-01-24 06:37:30.476465: step: 1672/529, loss: 0.03848068788647652
2023-01-24 06:37:31.523954: step: 1676/529, loss: 0.002204981166869402
2023-01-24 06:37:32.565939: step: 1680/529, loss: 0.007873247377574444
2023-01-24 06:37:33.630518: step: 1684/529, loss: 0.01370218675583601
2023-01-24 06:37:34.683756: step: 1688/529, loss: 0.01081059966236353
2023-01-24 06:37:35.726020: step: 1692/529, loss: 0.0035049791913479567
2023-01-24 06:37:36.774261: step: 1696/529, loss: 0.015782542526721954
2023-01-24 06:37:37.830760: step: 1700/529, loss: 0.02889157459139824
2023-01-24 06:37:38.863295: step: 1704/529, loss: 0.00474894093349576
2023-01-24 06:37:39.926201: step: 1708/529, loss: 0.04621373489499092
2023-01-24 06:37:40.975417: step: 1712/529, loss: 0.04079722613096237
2023-01-24 06:37:42.024111: step: 1716/529, loss: 0.0030744050163775682
2023-01-24 06:37:43.086324: step: 1720/529, loss: 0.007096126675605774
2023-01-24 06:37:44.133932: step: 1724/529, loss: 0.008257281966507435
2023-01-24 06:37:45.183504: step: 1728/529, loss: 0.001956286607310176
2023-01-24 06:37:46.253507: step: 1732/529, loss: 0.012075965292751789
2023-01-24 06:37:47.295315: step: 1736/529, loss: 0.0040674954652786255
2023-01-24 06:37:48.344234: step: 1740/529, loss: 0.0010538293281570077
2023-01-24 06:37:49.447864: step: 1744/529, loss: 0.006394412834197283
2023-01-24 06:37:50.500320: step: 1748/529, loss: 0.005157122388482094
2023-01-24 06:37:51.562576: step: 1752/529, loss: 0.0071691726334393024
2023-01-24 06:37:52.613366: step: 1756/529, loss: 0.00511873047798872
2023-01-24 06:37:53.672077: step: 1760/529, loss: 0.004206851590424776
2023-01-24 06:37:54.726472: step: 1764/529, loss: 0.0030038170516490936
2023-01-24 06:37:55.766471: step: 1768/529, loss: 0.006952269468456507
2023-01-24 06:37:56.803429: step: 1772/529, loss: 0.03365598991513252
2023-01-24 06:37:57.853398: step: 1776/529, loss: 0.007901431992650032
2023-01-24 06:37:58.885995: step: 1780/529, loss: 0.03756910189986229
2023-01-24 06:37:59.948552: step: 1784/529, loss: 0.0027143415063619614
2023-01-24 06:38:01.004336: step: 1788/529, loss: 0.007896346040070057
2023-01-24 06:38:02.059870: step: 1792/529, loss: 0.003454769728705287
2023-01-24 06:38:03.122072: step: 1796/529, loss: 0.008012359961867332
2023-01-24 06:38:04.179201: step: 1800/529, loss: 0.007863893173635006
2023-01-24 06:38:05.233333: step: 1804/529, loss: 0.002791995881125331
2023-01-24 06:38:06.287301: step: 1808/529, loss: 0.0037006670609116554
2023-01-24 06:38:07.325730: step: 1812/529, loss: 0.0075706117786467075
2023-01-24 06:38:08.378363: step: 1816/529, loss: 0.002864219481125474
2023-01-24 06:38:09.429283: step: 1820/529, loss: 0.0026690769009292126
2023-01-24 06:38:10.467647: step: 1824/529, loss: 0.004721864592283964
2023-01-24 06:38:11.521962: step: 1828/529, loss: 0.004358608741313219
2023-01-24 06:38:12.569087: step: 1832/529, loss: 0.006964650470763445
2023-01-24 06:38:13.605640: step: 1836/529, loss: 0.003265456762164831
2023-01-24 06:38:14.674160: step: 1840/529, loss: 0.02012091502547264
2023-01-24 06:38:15.728744: step: 1844/529, loss: 0.039580173790454865
2023-01-24 06:38:16.772750: step: 1848/529, loss: 0.005878944415599108
2023-01-24 06:38:17.837142: step: 1852/529, loss: 0.042363233864307404
2023-01-24 06:38:18.879960: step: 1856/529, loss: 0.0034193145111203194
2023-01-24 06:38:19.943356: step: 1860/529, loss: 0.010416567325592041
2023-01-24 06:38:20.983549: step: 1864/529, loss: 0.00946347787976265
2023-01-24 06:38:22.028771: step: 1868/529, loss: 0.015299217775464058
2023-01-24 06:38:23.082538: step: 1872/529, loss: 0.007803606800734997
2023-01-24 06:38:24.124420: step: 1876/529, loss: 0.034077953547239304
2023-01-24 06:38:25.187425: step: 1880/529, loss: 0.018398471176624298
2023-01-24 06:38:26.236407: step: 1884/529, loss: 0.025905737653374672
2023-01-24 06:38:27.318838: step: 1888/529, loss: 0.002401346806436777
2023-01-24 06:38:28.356841: step: 1892/529, loss: 0.014000258408486843
2023-01-24 06:38:29.405302: step: 1896/529, loss: 0.011593669652938843
2023-01-24 06:38:30.478016: step: 1900/529, loss: 0.018433650955557823
2023-01-24 06:38:31.527521: step: 1904/529, loss: 0.00021729448053520173
2023-01-24 06:38:32.562366: step: 1908/529, loss: 0.0025396591518074274
2023-01-24 06:38:33.631037: step: 1912/529, loss: 0.01734977960586548
2023-01-24 06:38:34.703144: step: 1916/529, loss: 0.021788204088807106
2023-01-24 06:38:35.759350: step: 1920/529, loss: 0.010209101252257824
2023-01-24 06:38:36.784217: step: 1924/529, loss: 0.0027999449521303177
2023-01-24 06:38:37.849786: step: 1928/529, loss: 0.006282568909227848
2023-01-24 06:38:38.872532: step: 1932/529, loss: 0.0023444530088454485
2023-01-24 06:38:39.925012: step: 1936/529, loss: 0.0015021865256130695
2023-01-24 06:38:40.973376: step: 1940/529, loss: 0.0232656579464674
2023-01-24 06:38:42.010772: step: 1944/529, loss: 0.0429142564535141
2023-01-24 06:38:43.056400: step: 1948/529, loss: 0.00369791011326015
2023-01-24 06:38:44.125232: step: 1952/529, loss: 0.004101696889847517
2023-01-24 06:38:45.178106: step: 1956/529, loss: 0.006419582292437553
2023-01-24 06:38:46.223506: step: 1960/529, loss: 0.009770194999873638
2023-01-24 06:38:47.272880: step: 1964/529, loss: 0.01119499932974577
2023-01-24 06:38:48.324920: step: 1968/529, loss: 0.0066248755902051926
2023-01-24 06:38:49.375981: step: 1972/529, loss: 0.014222013764083385
2023-01-24 06:38:50.437311: step: 1976/529, loss: 0.0012636489700526
2023-01-24 06:38:51.464637: step: 1980/529, loss: 0.0044588493183255196
2023-01-24 06:38:52.497792: step: 1984/529, loss: 0.006572291254997253
2023-01-24 06:38:53.547858: step: 1988/529, loss: 0.011034170165657997
2023-01-24 06:38:54.580335: step: 1992/529, loss: 0.013087132014334202
2023-01-24 06:38:55.624072: step: 1996/529, loss: 0.002118147676810622
2023-01-24 06:38:56.665769: step: 2000/529, loss: 0.0017166564939543605
2023-01-24 06:38:57.705293: step: 2004/529, loss: 0.0007918201736174524
2023-01-24 06:38:58.758374: step: 2008/529, loss: 0.0058188652619719505
2023-01-24 06:38:59.802109: step: 2012/529, loss: 0.004463243763893843
2023-01-24 06:39:00.849828: step: 2016/529, loss: 0.01546636875718832
2023-01-24 06:39:01.873150: step: 2020/529, loss: 0.006115283817052841
2023-01-24 06:39:02.919670: step: 2024/529, loss: 0.0038313865661621094
2023-01-24 06:39:03.956079: step: 2028/529, loss: 0.010081807151436806
2023-01-24 06:39:05.011586: step: 2032/529, loss: 0.011871806345880032
2023-01-24 06:39:06.059407: step: 2036/529, loss: 0.004678971599787474
2023-01-24 06:39:07.111818: step: 2040/529, loss: 0.005616115406155586
2023-01-24 06:39:08.152152: step: 2044/529, loss: 0.02291368879377842
2023-01-24 06:39:09.189263: step: 2048/529, loss: 0.0019425592618063092
2023-01-24 06:39:10.247022: step: 2052/529, loss: 0.0016388616058975458
2023-01-24 06:39:11.289913: step: 2056/529, loss: 0.01724652759730816
2023-01-24 06:39:12.330307: step: 2060/529, loss: 0.004556211177259684
2023-01-24 06:39:13.389755: step: 2064/529, loss: 0.0035861663054674864
2023-01-24 06:39:14.427068: step: 2068/529, loss: 0.0020745142828673124
2023-01-24 06:39:15.473105: step: 2072/529, loss: 0.004656584933400154
2023-01-24 06:39:16.516941: step: 2076/529, loss: 0.008734665811061859
2023-01-24 06:39:17.562864: step: 2080/529, loss: 0.003935365937650204
2023-01-24 06:39:18.594971: step: 2084/529, loss: 0.008014556020498276
2023-01-24 06:39:19.636984: step: 2088/529, loss: 0.0054819961078464985
2023-01-24 06:39:20.672751: step: 2092/529, loss: 0.003953464329242706
2023-01-24 06:39:21.719609: step: 2096/529, loss: 0.003167897928506136
2023-01-24 06:39:22.769149: step: 2100/529, loss: 0.0013746214099228382
2023-01-24 06:39:23.815482: step: 2104/529, loss: 0.0053943064995110035
2023-01-24 06:39:24.856416: step: 2108/529, loss: 0.00604413915425539
2023-01-24 06:39:25.883041: step: 2112/529, loss: 0.00036190840182825923
2023-01-24 06:39:26.943935: step: 2116/529, loss: 0.01194050908088684
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.329309368336887, 'r': 0.3349332474925454, 'f1': 0.33209750033597635}, 'combined': 0.2447034213001931, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.36921291095689684, 'r': 0.29994521823810727, 'f1': 0.3309939529136937}, 'combined': 0.23286006737646794, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35648684210526316, 'r': 0.32131166982922205, 'f1': 0.3379865269461078}, 'combined': 0.24904270406555312, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39084488430725495, 'r': 0.31751883707683626, 'f1': 0.3503866993645203}, 'combined': 0.24877455654880942, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37887864054115794, 'r': 0.34365083525364987, 'f1': 0.3604059506043254}, 'combined': 0.2655622793926608, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39985806339254615, 'r': 0.3142989144570232, 'f1': 0.35195330763158095}, 'combined': 0.24988684841842246, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3270833333333333, 'r': 0.37380952380952376, 'f1': 0.34888888888888886}, 'combined': 0.23259259259259257, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.38, 'r': 0.41304347826086957, 'f1': 0.39583333333333337}, 'combined': 0.19791666666666669, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32864373150390097, 'r': 0.33113818107888315, 'f1': 0.3298862408857683}, 'combined': 0.24307407223161873, 'stategy': 1, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3706665443853898, 'r': 0.2995089180635872, 'f1': 0.3313100580124237}, 'combined': 0.2330824528730619, 'stategy': 1, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:41:57.124729: step: 4/529, loss: 0.00418679416179657
2023-01-24 06:41:58.147981: step: 8/529, loss: 0.00024320787633769214
2023-01-24 06:41:59.168566: step: 12/529, loss: 0.0021170873660594225
2023-01-24 06:42:00.224295: step: 16/529, loss: 0.0034182819072157145
2023-01-24 06:42:01.280206: step: 20/529, loss: 0.015641946345567703
2023-01-24 06:42:02.297292: step: 24/529, loss: 0.0004319738072808832
2023-01-24 06:42:03.360675: step: 28/529, loss: 0.0016258681425824761
2023-01-24 06:42:04.416833: step: 32/529, loss: 0.005644837860018015
2023-01-24 06:42:05.463676: step: 36/529, loss: 0.0015868940390646458
2023-01-24 06:42:06.506112: step: 40/529, loss: 0.0026029327418655157
2023-01-24 06:42:07.551259: step: 44/529, loss: 0.0011572610819712281
2023-01-24 06:42:08.586026: step: 48/529, loss: 0.09177444875240326
2023-01-24 06:42:09.651188: step: 52/529, loss: 0.006089744623750448
2023-01-24 06:42:10.698461: step: 56/529, loss: 0.006039205472916365
2023-01-24 06:42:11.727596: step: 60/529, loss: 0.003792577888816595
2023-01-24 06:42:12.759635: step: 64/529, loss: 0.008594024926424026
2023-01-24 06:42:13.787657: step: 68/529, loss: 0.020279861986637115
2023-01-24 06:42:14.824287: step: 72/529, loss: 0.00022051918494980782
2023-01-24 06:42:15.868913: step: 76/529, loss: 0.005525319371372461
2023-01-24 06:42:16.915464: step: 80/529, loss: 0.004667379893362522
2023-01-24 06:42:17.977378: step: 84/529, loss: 0.009687199257314205
2023-01-24 06:42:19.051375: step: 88/529, loss: 0.004570450633764267
2023-01-24 06:42:20.103665: step: 92/529, loss: 0.005088334903120995
2023-01-24 06:42:21.174119: step: 96/529, loss: 0.006963053252547979
2023-01-24 06:42:22.223121: step: 100/529, loss: 0.01978379860520363
2023-01-24 06:42:23.262926: step: 104/529, loss: 0.004413002170622349
2023-01-24 06:42:24.319249: step: 108/529, loss: 0.002835626946762204
2023-01-24 06:42:25.378899: step: 112/529, loss: 0.0014767611864954233
2023-01-24 06:42:26.409741: step: 116/529, loss: 0.004016049671918154
2023-01-24 06:42:27.445842: step: 120/529, loss: 0.034448012709617615
2023-01-24 06:42:28.479231: step: 124/529, loss: 0.0014202462043613195
2023-01-24 06:42:29.537083: step: 128/529, loss: 0.0018970968667417765
2023-01-24 06:42:30.584183: step: 132/529, loss: 0.0013371362583711743
2023-01-24 06:42:31.634890: step: 136/529, loss: 0.005217510275542736
2023-01-24 06:42:32.675279: step: 140/529, loss: 0.0025468477979302406
2023-01-24 06:42:33.702256: step: 144/529, loss: 0.0036807500291615725
2023-01-24 06:42:34.748210: step: 148/529, loss: 0.00315466639585793
2023-01-24 06:42:35.817151: step: 152/529, loss: 0.019548948854207993
2023-01-24 06:42:36.883005: step: 156/529, loss: 0.019182687625288963
2023-01-24 06:42:37.914794: step: 160/529, loss: 0.00523687107488513
2023-01-24 06:42:38.957714: step: 164/529, loss: 0.026018721982836723
2023-01-24 06:42:40.004166: step: 168/529, loss: 0.002533954568207264
2023-01-24 06:42:41.028664: step: 172/529, loss: 0.0016875425353646278
2023-01-24 06:42:42.071256: step: 176/529, loss: 0.009932790882885456
2023-01-24 06:42:43.112015: step: 180/529, loss: 0.01693861186504364
2023-01-24 06:42:44.155691: step: 184/529, loss: 0.00642986036837101
2023-01-24 06:42:45.193003: step: 188/529, loss: 0.007867802865803242
2023-01-24 06:42:46.239702: step: 192/529, loss: 0.017002422362565994
2023-01-24 06:42:47.276567: step: 196/529, loss: 0.0017728491220623255
2023-01-24 06:42:48.322843: step: 200/529, loss: 0.003194941207766533
2023-01-24 06:42:49.368700: step: 204/529, loss: 0.003827095264568925
2023-01-24 06:42:50.399212: step: 208/529, loss: 0.00481391279026866
2023-01-24 06:42:51.432410: step: 212/529, loss: 0.004151469562202692
2023-01-24 06:42:52.465309: step: 216/529, loss: 0.0036621044855564833
2023-01-24 06:42:53.505131: step: 220/529, loss: 0.012713721953332424
2023-01-24 06:42:54.570670: step: 224/529, loss: 0.011146667413413525
2023-01-24 06:42:55.627992: step: 228/529, loss: 0.012993094511330128
2023-01-24 06:42:56.677972: step: 232/529, loss: 0.02289563976228237
2023-01-24 06:42:57.727245: step: 236/529, loss: 0.00946480967104435
2023-01-24 06:42:58.774029: step: 240/529, loss: 0.0014833833556622267
2023-01-24 06:42:59.827315: step: 244/529, loss: 0.004948390647768974
2023-01-24 06:43:00.879673: step: 248/529, loss: 0.004082354251295328
2023-01-24 06:43:01.940488: step: 252/529, loss: 0.0009998567402362823
2023-01-24 06:43:02.987638: step: 256/529, loss: 0.005059545394033194
2023-01-24 06:43:04.035269: step: 260/529, loss: 0.0012378237443044782
2023-01-24 06:43:05.080463: step: 264/529, loss: 0.04017799347639084
2023-01-24 06:43:06.121217: step: 268/529, loss: 0.004544986877590418
2023-01-24 06:43:07.170103: step: 272/529, loss: 0.0021344891283661127
2023-01-24 06:43:08.224545: step: 276/529, loss: 0.01584240049123764
2023-01-24 06:43:09.266073: step: 280/529, loss: 0.012545171193778515
2023-01-24 06:43:10.327150: step: 284/529, loss: 0.012593216262757778
2023-01-24 06:43:11.372309: step: 288/529, loss: 0.003506703535094857
2023-01-24 06:43:12.400938: step: 292/529, loss: 0.015691058710217476
2023-01-24 06:43:13.445584: step: 296/529, loss: 0.007280253805220127
2023-01-24 06:43:14.507365: step: 300/529, loss: 0.0170859694480896
2023-01-24 06:43:15.557618: step: 304/529, loss: 0.005679363384842873
2023-01-24 06:43:16.587602: step: 308/529, loss: 0.0002973276423290372
2023-01-24 06:43:17.615868: step: 312/529, loss: 0.004358048550784588
2023-01-24 06:43:18.665310: step: 316/529, loss: 0.008698815479874611
2023-01-24 06:43:19.718978: step: 320/529, loss: 0.005490819923579693
2023-01-24 06:43:20.774466: step: 324/529, loss: 0.01282102894037962
2023-01-24 06:43:21.820554: step: 328/529, loss: 0.010726699605584145
2023-01-24 06:43:22.869968: step: 332/529, loss: 0.004520405549556017
2023-01-24 06:43:23.895730: step: 336/529, loss: 0.005283476784825325
2023-01-24 06:43:24.938929: step: 340/529, loss: 0.0027138590812683105
2023-01-24 06:43:25.986684: step: 344/529, loss: 0.003003682941198349
2023-01-24 06:43:27.042947: step: 348/529, loss: 0.011491017416119576
2023-01-24 06:43:28.096531: step: 352/529, loss: 0.007983622141182423
2023-01-24 06:43:29.145998: step: 356/529, loss: 0.011500740423798561
2023-01-24 06:43:30.206835: step: 360/529, loss: 0.031198058277368546
2023-01-24 06:43:31.272796: step: 364/529, loss: 0.0029806382954120636
2023-01-24 06:43:32.339636: step: 368/529, loss: 0.019409112632274628
2023-01-24 06:43:33.384290: step: 372/529, loss: 0.005313187837600708
2023-01-24 06:43:34.435303: step: 376/529, loss: 0.030536234378814697
2023-01-24 06:43:35.470709: step: 380/529, loss: 0.002520354464650154
2023-01-24 06:43:36.532298: step: 384/529, loss: 0.0021227183751761913
2023-01-24 06:43:37.578859: step: 388/529, loss: 0.010852312669157982
2023-01-24 06:43:38.634897: step: 392/529, loss: 0.02787388116121292
2023-01-24 06:43:39.679885: step: 396/529, loss: 0.005178820341825485
2023-01-24 06:43:40.705019: step: 400/529, loss: 0.006441417150199413
2023-01-24 06:43:41.739109: step: 404/529, loss: 0.003956621512770653
2023-01-24 06:43:42.790783: step: 408/529, loss: 0.0022857231087982655
2023-01-24 06:43:43.834597: step: 412/529, loss: 0.002254004590213299
2023-01-24 06:43:44.883949: step: 416/529, loss: 0.005189592484384775
2023-01-24 06:43:45.923439: step: 420/529, loss: 0.003928902093321085
2023-01-24 06:43:46.982566: step: 424/529, loss: 0.003885621204972267
2023-01-24 06:43:48.017989: step: 428/529, loss: 0.04855571687221527
2023-01-24 06:43:49.053773: step: 432/529, loss: 0.01071907952427864
2023-01-24 06:43:50.097471: step: 436/529, loss: 0.0030133952386677265
2023-01-24 06:43:51.140050: step: 440/529, loss: 0.00532871950417757
2023-01-24 06:43:52.191448: step: 444/529, loss: 0.00952321756631136
2023-01-24 06:43:53.236867: step: 448/529, loss: 0.00878421775996685
2023-01-24 06:43:54.287465: step: 452/529, loss: 0.006957669742405415
2023-01-24 06:43:55.331281: step: 456/529, loss: 0.0015822151908650994
2023-01-24 06:43:56.364128: step: 460/529, loss: 0.010986107401549816
2023-01-24 06:43:57.420750: step: 464/529, loss: 0.0009427077602595091
2023-01-24 06:43:58.449518: step: 468/529, loss: 0.0008773641893640161
2023-01-24 06:43:59.491559: step: 472/529, loss: 0.019628306850790977
2023-01-24 06:44:00.536228: step: 476/529, loss: 0.012755539268255234
2023-01-24 06:44:01.578404: step: 480/529, loss: 0.006823853589594364
2023-01-24 06:44:02.624302: step: 484/529, loss: 0.006882214453071356
2023-01-24 06:44:03.660179: step: 488/529, loss: 0.012533913366496563
2023-01-24 06:44:04.703403: step: 492/529, loss: 0.004268737509846687
2023-01-24 06:44:05.745721: step: 496/529, loss: 0.02475816383957863
2023-01-24 06:44:06.809855: step: 500/529, loss: 0.0008665351197123528
2023-01-24 06:44:07.838916: step: 504/529, loss: 0.0058772689662873745
2023-01-24 06:44:08.883620: step: 508/529, loss: 0.006087447050958872
2023-01-24 06:44:09.935676: step: 512/529, loss: 0.0039688218384981155
2023-01-24 06:44:10.986928: step: 516/529, loss: 0.002285595517605543
2023-01-24 06:44:12.026807: step: 520/529, loss: 0.003919811919331551
2023-01-24 06:44:13.067307: step: 524/529, loss: 0.0034155845642089844
2023-01-24 06:44:14.110535: step: 528/529, loss: 0.016393642872571945
2023-01-24 06:44:15.152270: step: 532/529, loss: 0.005018963012844324
2023-01-24 06:44:16.220709: step: 536/529, loss: 0.009512615390121937
2023-01-24 06:44:17.264112: step: 540/529, loss: 0.013742680661380291
2023-01-24 06:44:18.310850: step: 544/529, loss: 0.006120592355728149
2023-01-24 06:44:19.360875: step: 548/529, loss: 0.0055603631772100925
2023-01-24 06:44:20.395882: step: 552/529, loss: 0.0033476371318101883
2023-01-24 06:44:21.455610: step: 556/529, loss: 0.012790605425834656
2023-01-24 06:44:22.509375: step: 560/529, loss: 0.0031049575190991163
2023-01-24 06:44:23.544521: step: 564/529, loss: 8.340136264450848e-05
2023-01-24 06:44:24.590084: step: 568/529, loss: 0.044959839433431625
2023-01-24 06:44:25.617369: step: 572/529, loss: 0.002194754546508193
2023-01-24 06:44:26.671467: step: 576/529, loss: 0.0023691949900239706
2023-01-24 06:44:27.711146: step: 580/529, loss: 0.0014328605029731989
2023-01-24 06:44:28.768759: step: 584/529, loss: 0.009362118318676949
2023-01-24 06:44:29.805646: step: 588/529, loss: 0.005044514779001474
2023-01-24 06:44:30.851642: step: 592/529, loss: 0.0028894487768411636
2023-01-24 06:44:31.882504: step: 596/529, loss: 0.0012223867233842611
2023-01-24 06:44:32.945115: step: 600/529, loss: 0.0030365968123078346
2023-01-24 06:44:33.993494: step: 604/529, loss: 0.006186846178025007
2023-01-24 06:44:35.032706: step: 608/529, loss: 0.011325540021061897
2023-01-24 06:44:36.082141: step: 612/529, loss: 0.000886776892002672
2023-01-24 06:44:37.113520: step: 616/529, loss: 0.0035998898092657328
2023-01-24 06:44:38.173692: step: 620/529, loss: 0.0025763448793441057
2023-01-24 06:44:39.214617: step: 624/529, loss: 0.004772564861923456
2023-01-24 06:44:40.270387: step: 628/529, loss: 0.0006545006181113422
2023-01-24 06:44:41.332630: step: 632/529, loss: 0.0658249482512474
2023-01-24 06:44:42.379673: step: 636/529, loss: 0.0037241396494209766
2023-01-24 06:44:43.420516: step: 640/529, loss: 0.007055758032947779
2023-01-24 06:44:44.491253: step: 644/529, loss: 0.014152373187243938
2023-01-24 06:44:45.550620: step: 648/529, loss: 0.031136812642216682
2023-01-24 06:44:46.596914: step: 652/529, loss: 0.01173525582998991
2023-01-24 06:44:47.652153: step: 656/529, loss: 0.003205682383850217
2023-01-24 06:44:48.697939: step: 660/529, loss: 0.013180609792470932
2023-01-24 06:44:49.785289: step: 664/529, loss: 0.0017198617570102215
2023-01-24 06:44:50.859497: step: 668/529, loss: 0.010948908515274525
2023-01-24 06:44:51.912185: step: 672/529, loss: 0.004982938524335623
2023-01-24 06:44:52.974939: step: 676/529, loss: 0.011175957508385181
2023-01-24 06:44:54.022538: step: 680/529, loss: 0.004167577251791954
2023-01-24 06:44:55.074899: step: 684/529, loss: 0.004932687617838383
2023-01-24 06:44:56.117844: step: 688/529, loss: 0.0017282726475968957
2023-01-24 06:44:57.165308: step: 692/529, loss: 0.003486054250970483
2023-01-24 06:44:58.205615: step: 696/529, loss: 0.021378057077527046
2023-01-24 06:44:59.244263: step: 700/529, loss: 0.0025207463186234236
2023-01-24 06:45:00.279562: step: 704/529, loss: 0.0016067586839199066
2023-01-24 06:45:01.326573: step: 708/529, loss: 0.0031255383510142565
2023-01-24 06:45:02.363442: step: 712/529, loss: 0.01948780193924904
2023-01-24 06:45:03.421569: step: 716/529, loss: 0.0009144945070147514
2023-01-24 06:45:04.463445: step: 720/529, loss: 0.00979230459779501
2023-01-24 06:45:05.523584: step: 724/529, loss: 0.00207799905911088
2023-01-24 06:45:06.559561: step: 728/529, loss: 0.001519421930424869
2023-01-24 06:45:07.595575: step: 732/529, loss: 0.0032010162249207497
2023-01-24 06:45:08.654094: step: 736/529, loss: 0.02200601063668728
2023-01-24 06:45:09.707365: step: 740/529, loss: 0.005108694080263376
2023-01-24 06:45:10.764071: step: 744/529, loss: 0.006854139268398285
2023-01-24 06:45:11.803731: step: 748/529, loss: 0.0009267330169677734
2023-01-24 06:45:12.840646: step: 752/529, loss: 0.012000516057014465
2023-01-24 06:45:13.875136: step: 756/529, loss: 0.0005193682154640555
2023-01-24 06:45:14.930110: step: 760/529, loss: 0.028842847794294357
2023-01-24 06:45:15.978602: step: 764/529, loss: 0.00018473275122232735
2023-01-24 06:45:17.043523: step: 768/529, loss: 0.0016618078807368875
2023-01-24 06:45:18.089431: step: 772/529, loss: 0.0046205357648432255
2023-01-24 06:45:19.136690: step: 776/529, loss: 0.002604840788990259
2023-01-24 06:45:20.174707: step: 780/529, loss: 0.0010007359087467194
2023-01-24 06:45:21.235296: step: 784/529, loss: 0.005958912428468466
2023-01-24 06:45:22.292275: step: 788/529, loss: 0.002130286069586873
2023-01-24 06:45:23.336889: step: 792/529, loss: 0.0007109068683348596
2023-01-24 06:45:24.388028: step: 796/529, loss: 0.001822280348278582
2023-01-24 06:45:25.447504: step: 800/529, loss: 0.005782265681773424
2023-01-24 06:45:26.508338: step: 804/529, loss: 0.010541227646172047
2023-01-24 06:45:27.543933: step: 808/529, loss: 0.0004067984991706908
2023-01-24 06:45:28.585563: step: 812/529, loss: 0.0033398461528122425
2023-01-24 06:45:29.617196: step: 816/529, loss: 0.0020836712792515755
2023-01-24 06:45:30.660084: step: 820/529, loss: 0.00021697222837246954
2023-01-24 06:45:31.714437: step: 824/529, loss: 0.004366052802652121
2023-01-24 06:45:32.744680: step: 828/529, loss: 0.0027180283796042204
2023-01-24 06:45:33.793435: step: 832/529, loss: 0.005855072755366564
2023-01-24 06:45:34.832402: step: 836/529, loss: 0.0015405826270580292
2023-01-24 06:45:35.874210: step: 840/529, loss: 0.0014148568734526634
2023-01-24 06:45:36.916987: step: 844/529, loss: 0.0060127414762973785
2023-01-24 06:45:37.952483: step: 848/529, loss: 0.0026360999327152967
2023-01-24 06:45:38.990045: step: 852/529, loss: 0.006164724472910166
2023-01-24 06:45:40.036294: step: 856/529, loss: 0.0005568200722336769
2023-01-24 06:45:41.081850: step: 860/529, loss: 0.0031530912965536118
2023-01-24 06:45:42.114651: step: 864/529, loss: 0.00020890013547614217
2023-01-24 06:45:43.178902: step: 868/529, loss: 0.010337824001908302
2023-01-24 06:45:44.226567: step: 872/529, loss: 0.003372880630195141
2023-01-24 06:45:45.277292: step: 876/529, loss: 0.003235666314139962
2023-01-24 06:45:46.338158: step: 880/529, loss: 0.01767680235207081
2023-01-24 06:45:47.385971: step: 884/529, loss: 0.004162862431257963
2023-01-24 06:45:48.424156: step: 888/529, loss: 0.01351142767816782
2023-01-24 06:45:49.482501: step: 892/529, loss: 0.0017237719148397446
2023-01-24 06:45:50.522882: step: 896/529, loss: 0.004608328454196453
2023-01-24 06:45:51.565471: step: 900/529, loss: 0.006700914818793535
2023-01-24 06:45:52.610260: step: 904/529, loss: 0.0010789984371513128
2023-01-24 06:45:53.660267: step: 908/529, loss: 0.0014517439994961023
2023-01-24 06:45:54.697180: step: 912/529, loss: 0.00187535653822124
2023-01-24 06:45:55.747551: step: 916/529, loss: 0.11291077733039856
2023-01-24 06:45:56.784558: step: 920/529, loss: 0.003345996607095003
2023-01-24 06:45:57.831773: step: 924/529, loss: 0.037647683173418045
2023-01-24 06:45:58.859108: step: 928/529, loss: 0.0003483584150671959
2023-01-24 06:45:59.901221: step: 932/529, loss: 0.0035272075328975916
2023-01-24 06:46:00.934630: step: 936/529, loss: 0.0019465115619823337
2023-01-24 06:46:01.965204: step: 940/529, loss: 0.0008050024043768644
2023-01-24 06:46:03.013691: step: 944/529, loss: 0.010214627720415592
2023-01-24 06:46:04.051585: step: 948/529, loss: 0.011353747919201851
2023-01-24 06:46:05.108503: step: 952/529, loss: 0.004682374652475119
2023-01-24 06:46:06.138983: step: 956/529, loss: 0.029736792668700218
2023-01-24 06:46:07.188846: step: 960/529, loss: 0.06589806079864502
2023-01-24 06:46:08.239032: step: 964/529, loss: 0.018441027030348778
2023-01-24 06:46:09.292962: step: 968/529, loss: 0.010233191773295403
2023-01-24 06:46:10.347179: step: 972/529, loss: 0.010023259557783604
2023-01-24 06:46:11.406732: step: 976/529, loss: 0.003923496697098017
2023-01-24 06:46:12.446123: step: 980/529, loss: 0.0017873788019642234
2023-01-24 06:46:13.470692: step: 984/529, loss: 0.002645807806402445
2023-01-24 06:46:14.522617: step: 988/529, loss: 0.0050481995567679405
2023-01-24 06:46:15.577875: step: 992/529, loss: 0.0012396216625347733
2023-01-24 06:46:16.622718: step: 996/529, loss: 0.006174897309392691
2023-01-24 06:46:17.688343: step: 1000/529, loss: 0.005880600307136774
2023-01-24 06:46:18.756058: step: 1004/529, loss: 0.010341616347432137
2023-01-24 06:46:19.837731: step: 1008/529, loss: 0.005105757620185614
2023-01-24 06:46:20.879563: step: 1012/529, loss: 0.010343586094677448
2023-01-24 06:46:21.919119: step: 1016/529, loss: 0.0034047835506498814
2023-01-24 06:46:22.960929: step: 1020/529, loss: 0.00567442923784256
2023-01-24 06:46:24.027045: step: 1024/529, loss: 0.010222043842077255
2023-01-24 06:46:25.075163: step: 1028/529, loss: 0.0197332501411438
2023-01-24 06:46:26.120665: step: 1032/529, loss: 0.003273306880146265
2023-01-24 06:46:27.157543: step: 1036/529, loss: 0.00402007857337594
2023-01-24 06:46:28.198387: step: 1040/529, loss: 0.003292643465101719
2023-01-24 06:46:29.227466: step: 1044/529, loss: 0.006321679335087538
2023-01-24 06:46:30.277497: step: 1048/529, loss: 0.0028350367210805416
2023-01-24 06:46:31.324430: step: 1052/529, loss: 0.0015393736539408565
2023-01-24 06:46:32.354182: step: 1056/529, loss: 0.00930643081665039
2023-01-24 06:46:33.385044: step: 1060/529, loss: 0.009996904991567135
2023-01-24 06:46:34.427233: step: 1064/529, loss: 1.867491846496705e-05
2023-01-24 06:46:35.484049: step: 1068/529, loss: 0.013489971868693829
2023-01-24 06:46:36.553782: step: 1072/529, loss: 0.010666463524103165
2023-01-24 06:46:37.603202: step: 1076/529, loss: 0.0023364105727523565
2023-01-24 06:46:38.645355: step: 1080/529, loss: 0.004974940791726112
2023-01-24 06:46:39.714930: step: 1084/529, loss: 0.010700489394366741
2023-01-24 06:46:40.747127: step: 1088/529, loss: 0.006985725834965706
2023-01-24 06:46:41.787839: step: 1092/529, loss: 0.004594434984028339
2023-01-24 06:46:42.844748: step: 1096/529, loss: 0.004355976358056068
2023-01-24 06:46:43.900852: step: 1100/529, loss: 0.0022873496636748314
2023-01-24 06:46:44.959984: step: 1104/529, loss: 0.09679481387138367
2023-01-24 06:46:46.000723: step: 1108/529, loss: 0.0036758319474756718
2023-01-24 06:46:47.067951: step: 1112/529, loss: 0.001414563157595694
2023-01-24 06:46:48.120426: step: 1116/529, loss: 0.005843575578182936
2023-01-24 06:46:49.160493: step: 1120/529, loss: 0.003531578229740262
2023-01-24 06:46:50.219514: step: 1124/529, loss: 0.0021109702065587044
2023-01-24 06:46:51.252888: step: 1128/529, loss: 0.0007224337314255536
2023-01-24 06:46:52.295094: step: 1132/529, loss: 0.021974900737404823
2023-01-24 06:46:53.340073: step: 1136/529, loss: 0.0061231935396790504
2023-01-24 06:46:54.371032: step: 1140/529, loss: 0.0019948554690927267
2023-01-24 06:46:55.433473: step: 1144/529, loss: 0.0036585237830877304
2023-01-24 06:46:56.493216: step: 1148/529, loss: 0.016825184226036072
2023-01-24 06:46:57.555803: step: 1152/529, loss: 0.021752147004008293
2023-01-24 06:46:58.605295: step: 1156/529, loss: 0.006467336788773537
2023-01-24 06:46:59.640622: step: 1160/529, loss: 0.001560449949465692
2023-01-24 06:47:00.688792: step: 1164/529, loss: 0.005150810815393925
2023-01-24 06:47:01.725941: step: 1168/529, loss: 0.002788701094686985
2023-01-24 06:47:02.774125: step: 1172/529, loss: 0.00016972224693745375
2023-01-24 06:47:03.821132: step: 1176/529, loss: 0.0017187473131343722
2023-01-24 06:47:04.869440: step: 1180/529, loss: 0.002455262467265129
2023-01-24 06:47:05.924013: step: 1184/529, loss: 0.0024022443685680628
2023-01-24 06:47:06.984313: step: 1188/529, loss: 0.005293928552418947
2023-01-24 06:47:08.006124: step: 1192/529, loss: 0.010014212690293789
2023-01-24 06:47:09.062112: step: 1196/529, loss: 0.0057226428762078285
2023-01-24 06:47:10.110743: step: 1200/529, loss: 0.015261152759194374
2023-01-24 06:47:11.150136: step: 1204/529, loss: 0.0036069059278815985
2023-01-24 06:47:12.204993: step: 1208/529, loss: 0.022153861820697784
2023-01-24 06:47:13.256232: step: 1212/529, loss: 0.020718999207019806
2023-01-24 06:47:14.306564: step: 1216/529, loss: 0.02209906093776226
2023-01-24 06:47:15.341584: step: 1220/529, loss: 0.0646977424621582
2023-01-24 06:47:16.392515: step: 1224/529, loss: 0.004512893036007881
2023-01-24 06:47:17.428282: step: 1228/529, loss: 0.001222978695295751
2023-01-24 06:47:18.477297: step: 1232/529, loss: 0.010980901308357716
2023-01-24 06:47:19.550735: step: 1236/529, loss: 0.005596710368990898
2023-01-24 06:47:20.599559: step: 1240/529, loss: 0.0060578021220862865
2023-01-24 06:47:21.645880: step: 1244/529, loss: 0.006224739830940962
2023-01-24 06:47:22.687075: step: 1248/529, loss: 0.009836849756538868
2023-01-24 06:47:23.751810: step: 1252/529, loss: 0.007444403599947691
2023-01-24 06:47:24.797702: step: 1256/529, loss: 0.007615205831825733
2023-01-24 06:47:25.857961: step: 1260/529, loss: 0.009487012401223183
2023-01-24 06:47:26.912989: step: 1264/529, loss: 0.0037185424007475376
2023-01-24 06:47:27.968889: step: 1268/529, loss: 0.00032172995270229876
2023-01-24 06:47:29.038912: step: 1272/529, loss: 0.0013614734634757042
2023-01-24 06:47:30.078474: step: 1276/529, loss: 0.0034371695946902037
2023-01-24 06:47:31.124186: step: 1280/529, loss: 0.007634851615875959
2023-01-24 06:47:32.179376: step: 1284/529, loss: 0.039624497294425964
2023-01-24 06:47:33.223741: step: 1288/529, loss: 0.005870536435395479
2023-01-24 06:47:34.277994: step: 1292/529, loss: 0.0066833700984716415
2023-01-24 06:47:35.328432: step: 1296/529, loss: 0.009734535589814186
2023-01-24 06:47:36.379328: step: 1300/529, loss: 0.004231844563037157
2023-01-24 06:47:37.443203: step: 1304/529, loss: 0.01276403944939375
2023-01-24 06:47:38.512760: step: 1308/529, loss: 0.00589427724480629
2023-01-24 06:47:39.562519: step: 1312/529, loss: 0.01865006797015667
2023-01-24 06:47:40.600429: step: 1316/529, loss: 0.010553350672125816
2023-01-24 06:47:41.650963: step: 1320/529, loss: 0.0034456339199095964
2023-01-24 06:47:42.706079: step: 1324/529, loss: 0.004795698449015617
2023-01-24 06:47:43.736981: step: 1328/529, loss: 0.0005342481308616698
2023-01-24 06:47:44.779251: step: 1332/529, loss: 0.0017165472963824868
2023-01-24 06:47:45.810978: step: 1336/529, loss: 0.007456735707819462
2023-01-24 06:47:46.887025: step: 1340/529, loss: 0.023134509101510048
2023-01-24 06:47:47.957791: step: 1344/529, loss: 0.005263397470116615
2023-01-24 06:47:49.005598: step: 1348/529, loss: 0.0059796771965920925
2023-01-24 06:47:50.062247: step: 1352/529, loss: 0.005494790151715279
2023-01-24 06:47:51.123244: step: 1356/529, loss: 0.01765313744544983
2023-01-24 06:47:52.175971: step: 1360/529, loss: 0.010995949618518353
2023-01-24 06:47:53.235496: step: 1364/529, loss: 0.0022110093850642443
2023-01-24 06:47:54.302226: step: 1368/529, loss: 0.02863430045545101
2023-01-24 06:47:55.379639: step: 1372/529, loss: 0.005511537194252014
2023-01-24 06:47:56.438545: step: 1376/529, loss: 0.004279316868633032
2023-01-24 06:47:57.484726: step: 1380/529, loss: 0.009396612644195557
2023-01-24 06:47:58.536167: step: 1384/529, loss: 0.004264641087502241
2023-01-24 06:47:59.587276: step: 1388/529, loss: 0.003186908783391118
2023-01-24 06:48:00.635405: step: 1392/529, loss: 0.00893084704875946
2023-01-24 06:48:01.697198: step: 1396/529, loss: 0.005201453343033791
2023-01-24 06:48:02.738494: step: 1400/529, loss: 0.004537770990282297
2023-01-24 06:48:03.777871: step: 1404/529, loss: 0.0027724585961550474
2023-01-24 06:48:04.826712: step: 1408/529, loss: 0.013007668778300285
2023-01-24 06:48:05.916218: step: 1412/529, loss: 0.0039587197825312614
2023-01-24 06:48:06.995064: step: 1416/529, loss: 0.0021988931111991405
2023-01-24 06:48:08.054788: step: 1420/529, loss: 0.007401087321341038
2023-01-24 06:48:09.114485: step: 1424/529, loss: 0.002529607620090246
2023-01-24 06:48:10.164694: step: 1428/529, loss: 0.004105293191969395
2023-01-24 06:48:11.231927: step: 1432/529, loss: 0.00038521201349794865
2023-01-24 06:48:12.283104: step: 1436/529, loss: 0.0028108262922614813
2023-01-24 06:48:13.326377: step: 1440/529, loss: 0.02009866014122963
2023-01-24 06:48:14.380424: step: 1444/529, loss: 0.005186332389712334
2023-01-24 06:48:15.437930: step: 1448/529, loss: 0.00943546462804079
2023-01-24 06:48:16.487839: step: 1452/529, loss: 0.0028669829480350018
2023-01-24 06:48:17.534094: step: 1456/529, loss: 0.0006739003001712263
2023-01-24 06:48:18.586114: step: 1460/529, loss: 0.002959716599434614
2023-01-24 06:48:19.639996: step: 1464/529, loss: 0.025490200147032738
2023-01-24 06:48:20.685986: step: 1468/529, loss: 0.0006220805807970464
2023-01-24 06:48:21.730196: step: 1472/529, loss: 0.0045493426732718945
2023-01-24 06:48:22.799162: step: 1476/529, loss: 0.007422023452818394
2023-01-24 06:48:23.854010: step: 1480/529, loss: 0.0003434363752603531
2023-01-24 06:48:24.903886: step: 1484/529, loss: 0.002908052410930395
2023-01-24 06:48:25.952198: step: 1488/529, loss: 0.008059931918978691
2023-01-24 06:48:27.012086: step: 1492/529, loss: 0.009029661305248737
2023-01-24 06:48:28.048504: step: 1496/529, loss: 0.011172882281243801
2023-01-24 06:48:29.113829: step: 1500/529, loss: 0.007685962598770857
2023-01-24 06:48:30.172866: step: 1504/529, loss: 0.00531420623883605
2023-01-24 06:48:31.222905: step: 1508/529, loss: 0.00048667757073417306
2023-01-24 06:48:32.299448: step: 1512/529, loss: 0.012706358917057514
2023-01-24 06:48:33.347580: step: 1516/529, loss: 0.002237442648038268
2023-01-24 06:48:34.417166: step: 1520/529, loss: 0.0040430352091789246
2023-01-24 06:48:35.474692: step: 1524/529, loss: 0.03662671893835068
2023-01-24 06:48:36.545010: step: 1528/529, loss: 0.0010449369437992573
2023-01-24 06:48:37.591560: step: 1532/529, loss: 0.00566144660115242
2023-01-24 06:48:38.643788: step: 1536/529, loss: 0.0002811216691043228
2023-01-24 06:48:39.693039: step: 1540/529, loss: 0.0010364975314587355
2023-01-24 06:48:40.750221: step: 1544/529, loss: 0.0019227811135351658
2023-01-24 06:48:41.808133: step: 1548/529, loss: 0.01226894836872816
2023-01-24 06:48:42.853101: step: 1552/529, loss: 0.0028614425100386143
2023-01-24 06:48:43.904442: step: 1556/529, loss: 0.0017028783913701773
2023-01-24 06:48:44.964618: step: 1560/529, loss: 0.005646460223942995
2023-01-24 06:48:45.999953: step: 1564/529, loss: 0.011266736313700676
2023-01-24 06:48:47.048800: step: 1568/529, loss: 0.0068841492757201195
2023-01-24 06:48:48.111155: step: 1572/529, loss: 0.022557435557246208
2023-01-24 06:48:49.151088: step: 1576/529, loss: 0.007782240863889456
2023-01-24 06:48:50.210158: step: 1580/529, loss: 0.0022903589997440577
2023-01-24 06:48:51.293741: step: 1584/529, loss: 0.016455868259072304
2023-01-24 06:48:52.348670: step: 1588/529, loss: 0.0071045998483896255
2023-01-24 06:48:53.406697: step: 1592/529, loss: 0.018862931057810783
2023-01-24 06:48:54.458769: step: 1596/529, loss: 0.009078999049961567
2023-01-24 06:48:55.504533: step: 1600/529, loss: 0.004598978441208601
2023-01-24 06:48:56.551835: step: 1604/529, loss: 0.0017273937119171023
2023-01-24 06:48:57.601860: step: 1608/529, loss: 0.0034220723900943995
2023-01-24 06:48:58.636586: step: 1612/529, loss: 0.002577882958576083
2023-01-24 06:48:59.675888: step: 1616/529, loss: 0.0023255664855241776
2023-01-24 06:49:00.742693: step: 1620/529, loss: 0.005078338086605072
2023-01-24 06:49:01.794247: step: 1624/529, loss: 0.0017022796673700213
2023-01-24 06:49:02.847995: step: 1628/529, loss: 0.004401816986501217
2023-01-24 06:49:03.885134: step: 1632/529, loss: 0.006114621181041002
2023-01-24 06:49:04.917906: step: 1636/529, loss: 0.003404750255867839
2023-01-24 06:49:05.971524: step: 1640/529, loss: 0.0029521449469029903
2023-01-24 06:49:07.031048: step: 1644/529, loss: 0.01737884245812893
2023-01-24 06:49:08.079638: step: 1648/529, loss: 0.003609592327848077
2023-01-24 06:49:09.116357: step: 1652/529, loss: 0.0006018771673552692
2023-01-24 06:49:10.171248: step: 1656/529, loss: 0.00840011890977621
2023-01-24 06:49:11.213364: step: 1660/529, loss: 0.027620581910014153
2023-01-24 06:49:12.257003: step: 1664/529, loss: 0.0013584413100033998
2023-01-24 06:49:13.312783: step: 1668/529, loss: 0.020687013864517212
2023-01-24 06:49:14.398891: step: 1672/529, loss: 0.0036367462016642094
2023-01-24 06:49:15.455040: step: 1676/529, loss: 0.002350281924009323
2023-01-24 06:49:16.506332: step: 1680/529, loss: 0.0041205789893865585
2023-01-24 06:49:17.542556: step: 1684/529, loss: 0.00909779965877533
2023-01-24 06:49:18.606835: step: 1688/529, loss: 0.0005393131286837161
2023-01-24 06:49:19.650698: step: 1692/529, loss: 0.001936891465447843
2023-01-24 06:49:20.708259: step: 1696/529, loss: 0.025961333885788918
2023-01-24 06:49:21.756012: step: 1700/529, loss: 0.022636907175183296
2023-01-24 06:49:22.802372: step: 1704/529, loss: 0.004636785946786404
2023-01-24 06:49:23.847626: step: 1708/529, loss: 0.004595298320055008
2023-01-24 06:49:24.889149: step: 1712/529, loss: 0.00046826706966385245
2023-01-24 06:49:25.926830: step: 1716/529, loss: 0.006994291208684444
2023-01-24 06:49:26.974923: step: 1720/529, loss: 0.005971079226583242
2023-01-24 06:49:28.010307: step: 1724/529, loss: 0.009745530784130096
2023-01-24 06:49:29.068172: step: 1728/529, loss: 0.00013580379891209304
2023-01-24 06:49:30.113942: step: 1732/529, loss: 0.004373595584183931
2023-01-24 06:49:31.169397: step: 1736/529, loss: 0.02308701165020466
2023-01-24 06:49:32.211621: step: 1740/529, loss: 0.001067155273631215
2023-01-24 06:49:33.261952: step: 1744/529, loss: 0.0004653588111978024
2023-01-24 06:49:34.328000: step: 1748/529, loss: 0.005620166193693876
2023-01-24 06:49:35.377138: step: 1752/529, loss: 0.005924263037741184
2023-01-24 06:49:36.420082: step: 1756/529, loss: 0.00017855333862826228
2023-01-24 06:49:37.478510: step: 1760/529, loss: 0.002827636431902647
2023-01-24 06:49:38.523802: step: 1764/529, loss: 0.0012677439954131842
2023-01-24 06:49:39.578998: step: 1768/529, loss: 0.006064257584512234
2023-01-24 06:49:40.627529: step: 1772/529, loss: 0.010223768651485443
2023-01-24 06:49:41.691729: step: 1776/529, loss: 0.0016981661319732666
2023-01-24 06:49:42.748423: step: 1780/529, loss: 0.0022718484979122877
2023-01-24 06:49:43.805721: step: 1784/529, loss: 0.007074328605085611
2023-01-24 06:49:44.857329: step: 1788/529, loss: 0.004383916035294533
2023-01-24 06:49:45.908286: step: 1792/529, loss: 0.01516591664403677
2023-01-24 06:49:46.943996: step: 1796/529, loss: 0.01723382994532585
2023-01-24 06:49:48.000671: step: 1800/529, loss: 0.002176165347918868
2023-01-24 06:49:49.056922: step: 1804/529, loss: 0.0010999891674146056
2023-01-24 06:49:50.101715: step: 1808/529, loss: 0.00583680858835578
2023-01-24 06:49:51.152895: step: 1812/529, loss: 0.0063547235913574696
2023-01-24 06:49:52.192923: step: 1816/529, loss: 0.01315275114029646
2023-01-24 06:49:53.227585: step: 1820/529, loss: 0.005829112138599157
2023-01-24 06:49:54.271063: step: 1824/529, loss: 0.0037796262186020613
2023-01-24 06:49:55.311947: step: 1828/529, loss: 0.0016116027254611254
2023-01-24 06:49:56.355426: step: 1832/529, loss: 0.004495531786233187
2023-01-24 06:49:57.400924: step: 1836/529, loss: 0.0033119108993560076
2023-01-24 06:49:58.458040: step: 1840/529, loss: 0.015245331451296806
2023-01-24 06:49:59.506210: step: 1844/529, loss: 0.011795220896601677
2023-01-24 06:50:00.557511: step: 1848/529, loss: 0.00022787578927818686
2023-01-24 06:50:01.614725: step: 1852/529, loss: 0.0005150833167135715
2023-01-24 06:50:02.661228: step: 1856/529, loss: 0.006519637070596218
2023-01-24 06:50:03.698533: step: 1860/529, loss: 6.537542276419117e-07
2023-01-24 06:50:04.742183: step: 1864/529, loss: 0.0013407135847955942
2023-01-24 06:50:05.799966: step: 1868/529, loss: 0.005626714788377285
2023-01-24 06:50:06.872269: step: 1872/529, loss: 0.008508286438882351
2023-01-24 06:50:07.935786: step: 1876/529, loss: 0.0024089752696454525
2023-01-24 06:50:08.991980: step: 1880/529, loss: 0.008103289641439915
2023-01-24 06:50:10.032124: step: 1884/529, loss: 0.036085814237594604
2023-01-24 06:50:11.079361: step: 1888/529, loss: 0.020635241642594337
2023-01-24 06:50:12.131195: step: 1892/529, loss: 0.003302657278254628
2023-01-24 06:50:13.176689: step: 1896/529, loss: 0.004418402444571257
2023-01-24 06:50:14.225623: step: 1900/529, loss: 0.011185157112777233
2023-01-24 06:50:15.278235: step: 1904/529, loss: 0.014876248314976692
2023-01-24 06:50:16.335161: step: 1908/529, loss: 0.00410253182053566
2023-01-24 06:50:17.371058: step: 1912/529, loss: 0.0025743674486875534
2023-01-24 06:50:18.412191: step: 1916/529, loss: 5.1235416322015226e-05
2023-01-24 06:50:19.465847: step: 1920/529, loss: 0.01078212633728981
2023-01-24 06:50:20.510407: step: 1924/529, loss: 0.0040357462130486965
2023-01-24 06:50:21.557943: step: 1928/529, loss: 0.011944519355893135
2023-01-24 06:50:22.617979: step: 1932/529, loss: 0.014269320294260979
2023-01-24 06:50:23.662350: step: 1936/529, loss: 0.0864657610654831
2023-01-24 06:50:24.716267: step: 1940/529, loss: 0.006890103220939636
2023-01-24 06:50:25.726968: step: 1944/529, loss: 0.020429786294698715
2023-01-24 06:50:26.783632: step: 1948/529, loss: 0.015258668921887875
2023-01-24 06:50:27.821388: step: 1952/529, loss: 0.005719974637031555
2023-01-24 06:50:28.876191: step: 1956/529, loss: 0.016125567257404327
2023-01-24 06:50:29.921425: step: 1960/529, loss: 0.0015064983163028955
2023-01-24 06:50:30.963093: step: 1964/529, loss: 0.02629963494837284
2023-01-24 06:50:32.015386: step: 1968/529, loss: 0.0013904025545343757
2023-01-24 06:50:33.072306: step: 1972/529, loss: 0.001332998275756836
2023-01-24 06:50:34.129769: step: 1976/529, loss: 0.01769978180527687
2023-01-24 06:50:35.173092: step: 1980/529, loss: 0.028006859123706818
2023-01-24 06:50:36.227643: step: 1984/529, loss: 0.002977078314870596
2023-01-24 06:50:37.279597: step: 1988/529, loss: 0.3105734884738922
2023-01-24 06:50:38.317514: step: 1992/529, loss: 0.014351844787597656
2023-01-24 06:50:39.366912: step: 1996/529, loss: 0.008118154481053352
2023-01-24 06:50:40.410495: step: 2000/529, loss: 0.009803789667785168
2023-01-24 06:50:41.454821: step: 2004/529, loss: 0.011053507216274738
2023-01-24 06:50:42.486363: step: 2008/529, loss: 0.0022000197786837816
2023-01-24 06:50:43.542887: step: 2012/529, loss: 0.04004212096333504
2023-01-24 06:50:44.606990: step: 2016/529, loss: 0.003663303330540657
2023-01-24 06:50:45.649822: step: 2020/529, loss: 0.003477126592770219
2023-01-24 06:50:46.696127: step: 2024/529, loss: 0.0024025526363402605
2023-01-24 06:50:47.731442: step: 2028/529, loss: 0.0015577829908579588
2023-01-24 06:50:48.782153: step: 2032/529, loss: 0.002356215612962842
2023-01-24 06:50:49.822942: step: 2036/529, loss: 0.004957434721291065
2023-01-24 06:50:50.875970: step: 2040/529, loss: 0.01695277914404869
2023-01-24 06:50:51.926230: step: 2044/529, loss: 0.0
2023-01-24 06:50:52.984917: step: 2048/529, loss: 0.0058385892771184444
2023-01-24 06:50:54.023061: step: 2052/529, loss: 0.025018231943249702
2023-01-24 06:50:55.060217: step: 2056/529, loss: 0.001199639169499278
2023-01-24 06:50:56.117906: step: 2060/529, loss: 0.004526037257164717
2023-01-24 06:50:57.169876: step: 2064/529, loss: 0.016652587801218033
2023-01-24 06:50:58.244537: step: 2068/529, loss: 0.006676653865724802
2023-01-24 06:50:59.286786: step: 2072/529, loss: 0.004255416803061962
2023-01-24 06:51:00.333909: step: 2076/529, loss: 0.005319209769368172
2023-01-24 06:51:01.379870: step: 2080/529, loss: 0.008580082096159458
2023-01-24 06:51:02.439825: step: 2084/529, loss: 0.034373655915260315
2023-01-24 06:51:03.508240: step: 2088/529, loss: 0.0027881034184247255
2023-01-24 06:51:04.548989: step: 2092/529, loss: 0.04488471895456314
2023-01-24 06:51:05.596177: step: 2096/529, loss: 0.002458750270307064
2023-01-24 06:51:06.629674: step: 2100/529, loss: 0.011102106422185898
2023-01-24 06:51:07.659082: step: 2104/529, loss: 0.002054554643109441
2023-01-24 06:51:08.714748: step: 2108/529, loss: 0.01581074297428131
2023-01-24 06:51:09.757336: step: 2112/529, loss: 0.007924499921500683
2023-01-24 06:51:10.799583: step: 2116/529, loss: 0.02802487276494503
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35648684210526316, 'r': 0.32131166982922205, 'f1': 0.3379865269461078}, 'combined': 0.24904270406555312, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.391998487462585, 'r': 0.3194821878621766, 'f1': 0.3520447954712061}, 'combined': 0.2499518047845563, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38067357625503845, 'r': 0.3474459016673121, 'f1': 0.36330156781482836}, 'combined': 0.26769589207408406, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3969170444542636, 'r': 0.3123338489548398, 'f1': 0.34958187395238666}, 'combined': 0.24820313050619452, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 8}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:53:50.195404: step: 4/529, loss: 0.006300678476691246
2023-01-24 06:53:51.216281: step: 8/529, loss: 0.0010124027030542493
2023-01-24 06:53:52.251002: step: 12/529, loss: 0.005624172277748585
2023-01-24 06:53:53.288647: step: 16/529, loss: 0.0018110325327143073
2023-01-24 06:53:54.311718: step: 20/529, loss: 0.01202508807182312
2023-01-24 06:53:55.341111: step: 24/529, loss: 0.01973545178771019
2023-01-24 06:53:56.383153: step: 28/529, loss: 0.002924524713307619
2023-01-24 06:53:57.414142: step: 32/529, loss: 0.004013107158243656
2023-01-24 06:53:58.449910: step: 36/529, loss: 0.0044119092635810375
2023-01-24 06:53:59.476519: step: 40/529, loss: 0.00377178774215281
2023-01-24 06:54:00.501305: step: 44/529, loss: 0.005118925590068102
2023-01-24 06:54:01.540337: step: 48/529, loss: 1.1169495337526314e-05
2023-01-24 06:54:02.567031: step: 52/529, loss: 0.0015382913406938314
2023-01-24 06:54:03.617643: step: 56/529, loss: 0.003531418740749359
2023-01-24 06:54:04.665849: step: 60/529, loss: 0.003769496688619256
2023-01-24 06:54:05.699763: step: 64/529, loss: 0.004782876465469599
2023-01-24 06:54:06.728401: step: 68/529, loss: 0.0048364801332354546
2023-01-24 06:54:07.770214: step: 72/529, loss: 0.013067131862044334
2023-01-24 06:54:08.817639: step: 76/529, loss: 0.03310670703649521
2023-01-24 06:54:09.850019: step: 80/529, loss: 0.02008361928164959
2023-01-24 06:54:10.886823: step: 84/529, loss: 0.00011589369387365878
2023-01-24 06:54:11.916937: step: 88/529, loss: 0.002125108614563942
2023-01-24 06:54:12.953977: step: 92/529, loss: 0.010413751937448978
2023-01-24 06:54:14.011185: step: 96/529, loss: 0.003419365268200636
2023-01-24 06:54:15.059810: step: 100/529, loss: 0.006584096699953079
2023-01-24 06:54:16.103645: step: 104/529, loss: 0.008205682039260864
2023-01-24 06:54:17.139030: step: 108/529, loss: 0.0008537423564121127
2023-01-24 06:54:18.174698: step: 112/529, loss: 0.0020073417108505964
2023-01-24 06:54:19.249596: step: 116/529, loss: 0.004572881385684013
2023-01-24 06:54:20.292324: step: 120/529, loss: 0.003769422648474574
2023-01-24 06:54:21.351084: step: 124/529, loss: 0.0068070776760578156
2023-01-24 06:54:22.422186: step: 128/529, loss: 0.004832706414163113
2023-01-24 06:54:23.468078: step: 132/529, loss: 5.883812627871521e-05
2023-01-24 06:54:24.504831: step: 136/529, loss: 0.005368275102227926
2023-01-24 06:54:25.548538: step: 140/529, loss: 0.025845011696219444
2023-01-24 06:54:26.574620: step: 144/529, loss: 0.0010977952042594552
2023-01-24 06:54:27.624218: step: 148/529, loss: 0.009125487878918648
2023-01-24 06:54:28.670223: step: 152/529, loss: 0.017263898625969887
2023-01-24 06:54:29.712772: step: 156/529, loss: 0.04713668301701546
2023-01-24 06:54:30.758157: step: 160/529, loss: 0.0034220970701426268
2023-01-24 06:54:31.812237: step: 164/529, loss: 0.0039162649773061275
2023-01-24 06:54:32.856566: step: 168/529, loss: 0.00571163697168231
2023-01-24 06:54:33.909828: step: 172/529, loss: 0.002208835445344448
2023-01-24 06:54:34.948975: step: 176/529, loss: 0.01873951405286789
2023-01-24 06:54:35.998108: step: 180/529, loss: 1.901809810078703e-05
2023-01-24 06:54:37.038208: step: 184/529, loss: 0.0003114901774097234
2023-01-24 06:54:38.080856: step: 188/529, loss: 0.0011132288491353393
2023-01-24 06:54:39.130593: step: 192/529, loss: 0.015212882310152054
2023-01-24 06:54:40.191407: step: 196/529, loss: 0.006722830235958099
2023-01-24 06:54:41.219210: step: 200/529, loss: 0.006900318432599306
2023-01-24 06:54:42.255954: step: 204/529, loss: 0.0025597952771931887
2023-01-24 06:54:43.306471: step: 208/529, loss: 0.016573838889598846
2023-01-24 06:54:44.358333: step: 212/529, loss: 0.007509148679673672
2023-01-24 06:54:45.425104: step: 216/529, loss: 0.0031382490415126085
2023-01-24 06:54:46.455155: step: 220/529, loss: 0.0022234388161450624
2023-01-24 06:54:47.497817: step: 224/529, loss: 0.19986917078495026
2023-01-24 06:54:48.557426: step: 228/529, loss: 0.005614585243165493
2023-01-24 06:54:49.616299: step: 232/529, loss: 0.0059786103665828705
2023-01-24 06:54:50.653115: step: 236/529, loss: 0.015377702191472054
2023-01-24 06:54:51.692491: step: 240/529, loss: 0.0018340423703193665
2023-01-24 06:54:52.735945: step: 244/529, loss: 0.004900996573269367
2023-01-24 06:54:53.777700: step: 248/529, loss: 0.004624504595994949
2023-01-24 06:54:54.814696: step: 252/529, loss: 0.005510708317160606
2023-01-24 06:54:55.851977: step: 256/529, loss: 0.015011359006166458
2023-01-24 06:54:56.875147: step: 260/529, loss: 0.004912584088742733
2023-01-24 06:54:57.930868: step: 264/529, loss: 0.004095816984772682
2023-01-24 06:54:58.973322: step: 268/529, loss: 0.006231776904314756
2023-01-24 06:55:00.020123: step: 272/529, loss: 0.006075344048440456
2023-01-24 06:55:01.055132: step: 276/529, loss: 0.009774001315236092
2023-01-24 06:55:02.098007: step: 280/529, loss: 0.008760093711316586
2023-01-24 06:55:03.158192: step: 284/529, loss: 0.016454629600048065
2023-01-24 06:55:04.194074: step: 288/529, loss: 0.003196598496288061
2023-01-24 06:55:05.253983: step: 292/529, loss: 0.01105580572038889
2023-01-24 06:55:06.298117: step: 296/529, loss: 0.012824133038520813
2023-01-24 06:55:07.360615: step: 300/529, loss: 0.00654851458966732
2023-01-24 06:55:08.398017: step: 304/529, loss: 0.0002847735886462033
2023-01-24 06:55:09.430111: step: 308/529, loss: 0.006640063598752022
2023-01-24 06:55:10.468664: step: 312/529, loss: 0.0031307535246014595
2023-01-24 06:55:11.510799: step: 316/529, loss: 0.0006091123213991523
2023-01-24 06:55:12.546270: step: 320/529, loss: 0.006259743589907885
2023-01-24 06:55:13.594114: step: 324/529, loss: 0.0014743837527930737
2023-01-24 06:55:14.641465: step: 328/529, loss: 0.002671916503459215
2023-01-24 06:55:15.683755: step: 332/529, loss: 0.00605043675750494
2023-01-24 06:55:16.734876: step: 336/529, loss: 0.008138896897435188
2023-01-24 06:55:17.777875: step: 340/529, loss: 0.007081998512148857
2023-01-24 06:55:18.837649: step: 344/529, loss: 0.0178579930216074
2023-01-24 06:55:19.884119: step: 348/529, loss: 0.04688217490911484
2023-01-24 06:55:20.936895: step: 352/529, loss: 0.0034469827078282833
2023-01-24 06:55:21.971118: step: 356/529, loss: 0.002957022748887539
2023-01-24 06:55:23.024200: step: 360/529, loss: 0.0022730641067028046
2023-01-24 06:55:24.064949: step: 364/529, loss: 0.024246053770184517
2023-01-24 06:55:25.112755: step: 368/529, loss: 0.0020896270871162415
2023-01-24 06:55:26.163214: step: 372/529, loss: 0.005090031307190657
2023-01-24 06:55:27.235666: step: 376/529, loss: 0.016175616532564163
2023-01-24 06:55:28.293601: step: 380/529, loss: 0.011649226769804955
2023-01-24 06:55:29.368664: step: 384/529, loss: 0.001625675125978887
2023-01-24 06:55:30.414439: step: 388/529, loss: 0.0021939226426184177
2023-01-24 06:55:31.474971: step: 392/529, loss: 0.011116301640868187
2023-01-24 06:55:32.523146: step: 396/529, loss: 0.009499894455075264
2023-01-24 06:55:33.561088: step: 400/529, loss: 0.005800594110041857
2023-01-24 06:55:34.611889: step: 404/529, loss: 3.698108412208967e-05
2023-01-24 06:55:35.665105: step: 408/529, loss: 0.021780554205179214
2023-01-24 06:55:36.697183: step: 412/529, loss: 0.006811901926994324
2023-01-24 06:55:37.759081: step: 416/529, loss: 0.0037943851202726364
2023-01-24 06:55:38.816282: step: 420/529, loss: 0.005671271588653326
2023-01-24 06:55:39.855967: step: 424/529, loss: 0.005850177723914385
2023-01-24 06:55:40.919167: step: 428/529, loss: 0.0018757515354081988
2023-01-24 06:55:41.964255: step: 432/529, loss: 0.004273649770766497
2023-01-24 06:55:43.010359: step: 436/529, loss: 0.058385588228702545
2023-01-24 06:55:44.048798: step: 440/529, loss: 0.0034359463024884462
2023-01-24 06:55:45.085058: step: 444/529, loss: 0.00020473668701015413
2023-01-24 06:55:46.129784: step: 448/529, loss: 0.0007670792983844876
2023-01-24 06:55:47.202543: step: 452/529, loss: 0.0024094106629490852
2023-01-24 06:55:48.248641: step: 456/529, loss: 0.004597185179591179
2023-01-24 06:55:49.294826: step: 460/529, loss: 0.0015014943201094866
2023-01-24 06:55:50.329816: step: 464/529, loss: 0.00015867469483055174
2023-01-24 06:55:51.383661: step: 468/529, loss: 0.0029733991250395775
2023-01-24 06:55:52.414362: step: 472/529, loss: 0.006710219196975231
2023-01-24 06:55:53.450722: step: 476/529, loss: 0.0032519851811230183
2023-01-24 06:55:54.485176: step: 480/529, loss: 0.0009933942928910255
2023-01-24 06:55:55.539762: step: 484/529, loss: 0.01579311676323414
2023-01-24 06:55:56.575293: step: 488/529, loss: 0.0030558560974895954
2023-01-24 06:55:57.613027: step: 492/529, loss: 0.004293438978493214
2023-01-24 06:55:58.669609: step: 496/529, loss: 0.006788470782339573
2023-01-24 06:55:59.720077: step: 500/529, loss: 0.00423421198502183
2023-01-24 06:56:00.785577: step: 504/529, loss: 0.0215873084962368
2023-01-24 06:56:01.824694: step: 508/529, loss: 0.002454339526593685
2023-01-24 06:56:02.865141: step: 512/529, loss: 0.0126581359654665
2023-01-24 06:56:03.901438: step: 516/529, loss: 0.002481881296262145
2023-01-24 06:56:04.940366: step: 520/529, loss: 0.00029030904988758266
2023-01-24 06:56:05.976763: step: 524/529, loss: 0.0014340935740619898
2023-01-24 06:56:06.999420: step: 528/529, loss: 0.001938837580382824
2023-01-24 06:56:08.054916: step: 532/529, loss: 0.02064271830022335
2023-01-24 06:56:09.091469: step: 536/529, loss: 0.017089057713747025
2023-01-24 06:56:10.129558: step: 540/529, loss: 0.008119807578623295
2023-01-24 06:56:11.170314: step: 544/529, loss: 0.00399622181430459
2023-01-24 06:56:12.210958: step: 548/529, loss: 0.007835932075977325
2023-01-24 06:56:13.249978: step: 552/529, loss: 0.00044475361937657
2023-01-24 06:56:14.304022: step: 556/529, loss: 0.007072226610034704
2023-01-24 06:56:15.344649: step: 560/529, loss: 0.0001500154030509293
2023-01-24 06:56:16.395005: step: 564/529, loss: 0.006587793584913015
2023-01-24 06:56:17.436926: step: 568/529, loss: 0.00090974842896685
2023-01-24 06:56:18.495708: step: 572/529, loss: 0.0008496007067151368
2023-01-24 06:56:19.547688: step: 576/529, loss: 0.01644875481724739
2023-01-24 06:56:20.576667: step: 580/529, loss: 0.0014555059606209397
2023-01-24 06:56:21.635752: step: 584/529, loss: 0.01223946362733841
2023-01-24 06:56:22.678391: step: 588/529, loss: 0.013972879387438297
2023-01-24 06:56:23.738494: step: 592/529, loss: 0.0011880487436428666
2023-01-24 06:56:24.782562: step: 596/529, loss: 0.010912670753896236
2023-01-24 06:56:25.828980: step: 600/529, loss: 0.005654783919453621
2023-01-24 06:56:26.881370: step: 604/529, loss: 0.01036121416836977
2023-01-24 06:56:27.910079: step: 608/529, loss: 0.001505812630057335
2023-01-24 06:56:28.934890: step: 612/529, loss: 0.000928484951145947
2023-01-24 06:56:29.978285: step: 616/529, loss: 0.003394001629203558
2023-01-24 06:56:31.011637: step: 620/529, loss: 0.0040245638228952885
2023-01-24 06:56:32.059236: step: 624/529, loss: 0.0036833074409514666
2023-01-24 06:56:33.100757: step: 628/529, loss: 0.018184546381235123
2023-01-24 06:56:34.153297: step: 632/529, loss: 0.010472928173840046
2023-01-24 06:56:35.198213: step: 636/529, loss: 0.004791125655174255
2023-01-24 06:56:36.249511: step: 640/529, loss: 0.0016424853820353746
2023-01-24 06:56:37.296535: step: 644/529, loss: 0.00336257042363286
2023-01-24 06:56:38.344160: step: 648/529, loss: 0.008741194382309914
2023-01-24 06:56:39.386217: step: 652/529, loss: 0.00500513194128871
2023-01-24 06:56:40.426740: step: 656/529, loss: 0.0025286588352173567
2023-01-24 06:56:41.472102: step: 660/529, loss: 0.006148525048047304
2023-01-24 06:56:42.512203: step: 664/529, loss: 0.006512647494673729
2023-01-24 06:56:43.560839: step: 668/529, loss: 0.005718899425119162
2023-01-24 06:56:44.601510: step: 672/529, loss: 0.0015654120361432433
2023-01-24 06:56:45.637436: step: 676/529, loss: 0.002474777866154909
2023-01-24 06:56:46.689166: step: 680/529, loss: 0.00628057774156332
2023-01-24 06:56:47.725882: step: 684/529, loss: 0.0046486700884997845
2023-01-24 06:56:48.773795: step: 688/529, loss: 0.0025023389607667923
2023-01-24 06:56:49.860831: step: 692/529, loss: 0.0046284496784210205
2023-01-24 06:56:50.901750: step: 696/529, loss: 0.004663518629968166
2023-01-24 06:56:51.963476: step: 700/529, loss: 0.002358801197260618
2023-01-24 06:56:53.009073: step: 704/529, loss: 0.0038717612624168396
2023-01-24 06:56:54.066632: step: 708/529, loss: 0.01180274412035942
2023-01-24 06:56:55.116149: step: 712/529, loss: 0.0002772000734694302
2023-01-24 06:56:56.167871: step: 716/529, loss: 0.0019642598927021027
2023-01-24 06:56:57.231503: step: 720/529, loss: 0.00062557467026636
2023-01-24 06:56:58.269030: step: 724/529, loss: 0.003036304609850049
2023-01-24 06:56:59.315995: step: 728/529, loss: 0.0039842030964791775
2023-01-24 06:57:00.365204: step: 732/529, loss: 0.0019089869456365705
2023-01-24 06:57:01.413495: step: 736/529, loss: 0.0006355307996273041
2023-01-24 06:57:02.486395: step: 740/529, loss: 0.003295942209661007
2023-01-24 06:57:03.545758: step: 744/529, loss: 0.0062166741117835045
2023-01-24 06:57:04.584494: step: 748/529, loss: 0.0016474102158099413
2023-01-24 06:57:05.634877: step: 752/529, loss: 0.0015284394612535834
2023-01-24 06:57:06.693738: step: 756/529, loss: 0.005231295246630907
2023-01-24 06:57:07.731240: step: 760/529, loss: 0.010162388905882835
2023-01-24 06:57:08.791879: step: 764/529, loss: 0.0011594555107876658
2023-01-24 06:57:09.823136: step: 768/529, loss: 0.0014539504190906882
2023-01-24 06:57:10.883935: step: 772/529, loss: 0.005979025736451149
2023-01-24 06:57:11.947293: step: 776/529, loss: 0.004823142662644386
2023-01-24 06:57:12.997020: step: 780/529, loss: 0.017872508615255356
2023-01-24 06:57:14.043923: step: 784/529, loss: 0.0021699729841202497
2023-01-24 06:57:15.076114: step: 788/529, loss: 0.010397344827651978
2023-01-24 06:57:16.109620: step: 792/529, loss: 0.004523996729403734
2023-01-24 06:57:17.147643: step: 796/529, loss: 0.006840874440968037
2023-01-24 06:57:18.178167: step: 800/529, loss: 0.00152712466660887
2023-01-24 06:57:19.235744: step: 804/529, loss: 0.001005453639663756
2023-01-24 06:57:20.285847: step: 808/529, loss: 0.005728109274059534
2023-01-24 06:57:21.315592: step: 812/529, loss: 0.005101579707115889
2023-01-24 06:57:22.356030: step: 816/529, loss: 0.010346205905079842
2023-01-24 06:57:23.402075: step: 820/529, loss: 0.004148328211158514
2023-01-24 06:57:24.446748: step: 824/529, loss: 0.0022742159198969603
2023-01-24 06:57:25.478819: step: 828/529, loss: 0.005398695822805166
2023-01-24 06:57:26.525096: step: 832/529, loss: 0.00025242235278710723
2023-01-24 06:57:27.570825: step: 836/529, loss: 0.011434529908001423
2023-01-24 06:57:28.616549: step: 840/529, loss: 0.010000054724514484
2023-01-24 06:57:29.642036: step: 844/529, loss: 0.008968652226030827
2023-01-24 06:57:30.678734: step: 848/529, loss: 0.003606243757531047
2023-01-24 06:57:31.730488: step: 852/529, loss: 0.004035185556858778
2023-01-24 06:57:32.777814: step: 856/529, loss: 0.017740394920110703
2023-01-24 06:57:33.843656: step: 860/529, loss: 0.002499544760212302
2023-01-24 06:57:34.889992: step: 864/529, loss: 0.003376048058271408
2023-01-24 06:57:35.913104: step: 868/529, loss: 0.006387442350387573
2023-01-24 06:57:36.960809: step: 872/529, loss: 0.00011014998017344624
2023-01-24 06:57:38.013652: step: 876/529, loss: 0.004113172180950642
2023-01-24 06:57:39.081027: step: 880/529, loss: 0.006529481150209904
2023-01-24 06:57:40.121475: step: 884/529, loss: 0.007111255079507828
2023-01-24 06:57:41.158772: step: 888/529, loss: 0.010991730727255344
2023-01-24 06:57:42.212694: step: 892/529, loss: 0.015675922855734825
2023-01-24 06:57:43.261960: step: 896/529, loss: 0.004603234585374594
2023-01-24 06:57:44.332367: step: 900/529, loss: 0.0019323823507875204
2023-01-24 06:57:45.383060: step: 904/529, loss: 0.011816330254077911
2023-01-24 06:57:46.419084: step: 908/529, loss: 0.00700808921828866
2023-01-24 06:57:47.452324: step: 912/529, loss: 0.0396735705435276
2023-01-24 06:57:48.492558: step: 916/529, loss: 0.009099606424570084
2023-01-24 06:57:49.548036: step: 920/529, loss: 0.011520998552441597
2023-01-24 06:57:50.587875: step: 924/529, loss: 0.0048079960979521275
2023-01-24 06:57:51.624410: step: 928/529, loss: 0.0005959143745712936
2023-01-24 06:57:52.665048: step: 932/529, loss: 0.011329959146678448
2023-01-24 06:57:53.708573: step: 936/529, loss: 0.0014785476960241795
2023-01-24 06:57:54.766038: step: 940/529, loss: 0.0021816124208271503
2023-01-24 06:57:55.806669: step: 944/529, loss: 0.008383725769817829
2023-01-24 06:57:56.851024: step: 948/529, loss: 0.012099064886569977
2023-01-24 06:57:57.889262: step: 952/529, loss: 0.010949932038784027
2023-01-24 06:57:58.940822: step: 956/529, loss: 0.0030963753815740347
2023-01-24 06:57:59.981812: step: 960/529, loss: 0.00010512776498217136
2023-01-24 06:58:01.026159: step: 964/529, loss: 0.0034836141858249903
2023-01-24 06:58:02.060610: step: 968/529, loss: 0.009435310959815979
2023-01-24 06:58:03.122915: step: 972/529, loss: 0.009063382633030415
2023-01-24 06:58:04.160663: step: 976/529, loss: 0.001009809784591198
2023-01-24 06:58:05.199993: step: 980/529, loss: 0.007951056584715843
2023-01-24 06:58:06.251551: step: 984/529, loss: 0.009092065505683422
2023-01-24 06:58:07.310045: step: 988/529, loss: 0.003922322764992714
2023-01-24 06:58:08.353072: step: 992/529, loss: 0.0006192208966240287
2023-01-24 06:58:09.380507: step: 996/529, loss: 0.004097390454262495
2023-01-24 06:58:10.422456: step: 1000/529, loss: 0.012018872424960136
2023-01-24 06:58:11.478032: step: 1004/529, loss: 0.03923084959387779
2023-01-24 06:58:12.533663: step: 1008/529, loss: 0.008151457644999027
2023-01-24 06:58:13.577342: step: 1012/529, loss: 0.000528968230355531
2023-01-24 06:58:14.623405: step: 1016/529, loss: 0.007962619885802269
2023-01-24 06:58:15.653552: step: 1020/529, loss: 2.5195267880917527e-05
2023-01-24 06:58:16.691358: step: 1024/529, loss: 0.0011565190507099032
2023-01-24 06:58:17.746511: step: 1028/529, loss: 0.004009074065834284
2023-01-24 06:58:18.794671: step: 1032/529, loss: 0.0020806114189326763
2023-01-24 06:58:19.847529: step: 1036/529, loss: 0.004213140346109867
2023-01-24 06:58:20.892815: step: 1040/529, loss: 0.005793469026684761
2023-01-24 06:58:21.931071: step: 1044/529, loss: 8.711584086995572e-05
2023-01-24 06:58:22.964615: step: 1048/529, loss: 0.0008608251810073853
2023-01-24 06:58:24.012801: step: 1052/529, loss: 0.00797390379011631
2023-01-24 06:58:25.058993: step: 1056/529, loss: 0.006473200861364603
2023-01-24 06:58:26.104114: step: 1060/529, loss: 0.009393997490406036
2023-01-24 06:58:27.138143: step: 1064/529, loss: 0.000984341953881085
2023-01-24 06:58:28.193469: step: 1068/529, loss: 0.008125782944262028
2023-01-24 06:58:29.245453: step: 1072/529, loss: 0.022238871082663536
2023-01-24 06:58:30.297309: step: 1076/529, loss: 0.0008515786030329764
2023-01-24 06:58:31.353919: step: 1080/529, loss: 0.07729467004537582
2023-01-24 06:58:32.403422: step: 1084/529, loss: 0.009878535754978657
2023-01-24 06:58:33.446109: step: 1088/529, loss: 0.0023015232291072607
2023-01-24 06:58:34.494642: step: 1092/529, loss: 0.00883267167955637
2023-01-24 06:58:35.546595: step: 1096/529, loss: 0.00739073334261775
2023-01-24 06:58:36.588134: step: 1100/529, loss: 0.016659047454595566
2023-01-24 06:58:37.630583: step: 1104/529, loss: 0.0016267206519842148
2023-01-24 06:58:38.678261: step: 1108/529, loss: 0.0017009723233059049
2023-01-24 06:58:39.728640: step: 1112/529, loss: 0.00375702534802258
2023-01-24 06:58:40.767580: step: 1116/529, loss: 0.016666973009705544
2023-01-24 06:58:41.813480: step: 1120/529, loss: 0.0037795458920300007
2023-01-24 06:58:42.867541: step: 1124/529, loss: 0.004482579883188009
2023-01-24 06:58:43.902560: step: 1128/529, loss: 0.008286291733384132
2023-01-24 06:58:44.946608: step: 1132/529, loss: 0.0054707773961126804
2023-01-24 06:58:46.000554: step: 1136/529, loss: 0.0034230626188218594
2023-01-24 06:58:47.039684: step: 1140/529, loss: 0.01532284077256918
2023-01-24 06:58:48.097354: step: 1144/529, loss: 0.0024429569020867348
2023-01-24 06:58:49.142392: step: 1148/529, loss: 0.0010498602641746402
2023-01-24 06:58:50.200163: step: 1152/529, loss: 0.02562536858022213
2023-01-24 06:58:51.236678: step: 1156/529, loss: 0.005093762651085854
2023-01-24 06:58:52.277061: step: 1160/529, loss: 0.000866380927618593
2023-01-24 06:58:53.318735: step: 1164/529, loss: 0.0005144627066329122
2023-01-24 06:58:54.383080: step: 1168/529, loss: 0.0027241436764597893
2023-01-24 06:58:55.431808: step: 1172/529, loss: 0.0005300686461851001
2023-01-24 06:58:56.463447: step: 1176/529, loss: 0.0008234158158302307
2023-01-24 06:58:57.496621: step: 1180/529, loss: 0.00796295702457428
2023-01-24 06:58:58.552402: step: 1184/529, loss: 0.0014958082465454936
2023-01-24 06:58:59.602988: step: 1188/529, loss: 0.0001174230346805416
2023-01-24 06:59:00.648944: step: 1192/529, loss: 0.009548977948725224
2023-01-24 06:59:01.697736: step: 1196/529, loss: 0.004236704204231501
2023-01-24 06:59:02.752004: step: 1200/529, loss: 0.008820915594696999
2023-01-24 06:59:03.792128: step: 1204/529, loss: 0.001488731475546956
2023-01-24 06:59:04.837844: step: 1208/529, loss: 0.008006872609257698
2023-01-24 06:59:05.876349: step: 1212/529, loss: 0.0036577205173671246
2023-01-24 06:59:06.910363: step: 1216/529, loss: 0.006865944713354111
2023-01-24 06:59:07.957512: step: 1220/529, loss: 0.09012701362371445
2023-01-24 06:59:08.995372: step: 1224/529, loss: 0.006028877571225166
2023-01-24 06:59:10.032035: step: 1228/529, loss: 0.003818704979494214
2023-01-24 06:59:11.075464: step: 1232/529, loss: 0.0022012065164744854
2023-01-24 06:59:12.114067: step: 1236/529, loss: 0.05324241518974304
2023-01-24 06:59:13.159083: step: 1240/529, loss: 0.004673610907047987
2023-01-24 06:59:14.199696: step: 1244/529, loss: 0.003439712105318904
2023-01-24 06:59:15.237998: step: 1248/529, loss: 0.0005930070765316486
2023-01-24 06:59:16.295926: step: 1252/529, loss: 0.01084781251847744
2023-01-24 06:59:17.354002: step: 1256/529, loss: 0.03378957509994507
2023-01-24 06:59:18.405782: step: 1260/529, loss: 0.0139120789244771
2023-01-24 06:59:19.462187: step: 1264/529, loss: 0.0071626571007072926
2023-01-24 06:59:20.506475: step: 1268/529, loss: 0.0032292359974235296
2023-01-24 06:59:21.560094: step: 1272/529, loss: 0.009731153026223183
2023-01-24 06:59:22.603632: step: 1276/529, loss: 0.011153255589306355
2023-01-24 06:59:23.651527: step: 1280/529, loss: 0.011540660634636879
2023-01-24 06:59:24.697539: step: 1284/529, loss: 0.0007765796617604792
2023-01-24 06:59:25.743487: step: 1288/529, loss: 0.015370507724583149
2023-01-24 06:59:26.814161: step: 1292/529, loss: 0.0027697307523339987
2023-01-24 06:59:27.853177: step: 1296/529, loss: 0.0029579424299299717
2023-01-24 06:59:28.877847: step: 1300/529, loss: 0.0027856891974806786
2023-01-24 06:59:29.930414: step: 1304/529, loss: 0.0014508719323202968
2023-01-24 06:59:30.971352: step: 1308/529, loss: 0.0056475563906133175
2023-01-24 06:59:32.029287: step: 1312/529, loss: 0.009944622404873371
2023-01-24 06:59:33.065218: step: 1316/529, loss: 0.008630159310996532
2023-01-24 06:59:34.116250: step: 1320/529, loss: 0.011891843751072884
2023-01-24 06:59:35.169754: step: 1324/529, loss: 0.0006453021196648479
2023-01-24 06:59:36.227219: step: 1328/529, loss: 0.002190463710576296
2023-01-24 06:59:37.275891: step: 1332/529, loss: 0.010509279556572437
2023-01-24 06:59:38.330845: step: 1336/529, loss: 0.00253860279917717
2023-01-24 06:59:39.386015: step: 1340/529, loss: 0.0028235469944775105
2023-01-24 06:59:40.437808: step: 1344/529, loss: 0.005779411178082228
2023-01-24 06:59:41.473861: step: 1348/529, loss: 0.008151914924383163
2023-01-24 06:59:42.523646: step: 1352/529, loss: 0.0002389306464465335
2023-01-24 06:59:43.578048: step: 1356/529, loss: 0.019289448857307434
2023-01-24 06:59:44.619982: step: 1360/529, loss: 0.006370015442371368
2023-01-24 06:59:45.667905: step: 1364/529, loss: 0.0014786451356485486
2023-01-24 06:59:46.704012: step: 1368/529, loss: 0.002718487521633506
2023-01-24 06:59:47.743122: step: 1372/529, loss: 0.0013724368764087558
2023-01-24 06:59:48.795078: step: 1376/529, loss: 0.01049088966101408
2023-01-24 06:59:49.850017: step: 1380/529, loss: 0.00016955556930042803
2023-01-24 06:59:50.901693: step: 1384/529, loss: 0.008403759449720383
2023-01-24 06:59:51.945056: step: 1388/529, loss: 0.007500526495277882
2023-01-24 06:59:52.986897: step: 1392/529, loss: 0.00339939771220088
2023-01-24 06:59:54.019539: step: 1396/529, loss: 0.0010053713340312243
2023-01-24 06:59:55.046594: step: 1400/529, loss: 0.004347257316112518
2023-01-24 06:59:56.108183: step: 1404/529, loss: 0.02101157233119011
2023-01-24 06:59:57.146796: step: 1408/529, loss: 0.00039704336086288095
2023-01-24 06:59:58.202217: step: 1412/529, loss: 0.013309722766280174
2023-01-24 06:59:59.242602: step: 1416/529, loss: 0.003684376133605838
2023-01-24 07:00:00.300318: step: 1420/529, loss: 0.011502178385853767
2023-01-24 07:00:01.348447: step: 1424/529, loss: 0.0029402689542621374
2023-01-24 07:00:02.407914: step: 1428/529, loss: 0.011624012142419815
2023-01-24 07:00:03.491044: step: 1432/529, loss: 0.0010776517447084188
2023-01-24 07:00:04.537474: step: 1436/529, loss: 0.015498697757720947
2023-01-24 07:00:05.596928: step: 1440/529, loss: 0.005593031644821167
2023-01-24 07:00:06.644599: step: 1444/529, loss: 0.00390962278470397
2023-01-24 07:00:07.690878: step: 1448/529, loss: 0.005855011288076639
2023-01-24 07:00:08.735440: step: 1452/529, loss: 0.003248876892030239
2023-01-24 07:00:09.772028: step: 1456/529, loss: 0.0023326303344219923
2023-01-24 07:00:10.808481: step: 1460/529, loss: 1.2782409612555057e-05
2023-01-24 07:00:11.849263: step: 1464/529, loss: 0.0012349772732704878
2023-01-24 07:00:12.888745: step: 1468/529, loss: 0.0027779163792729378
2023-01-24 07:00:13.941702: step: 1472/529, loss: 0.0056990971788764
2023-01-24 07:00:14.999264: step: 1476/529, loss: 0.0035232354421168566
2023-01-24 07:00:16.046607: step: 1480/529, loss: 0.0039021545089781284
2023-01-24 07:00:17.077818: step: 1484/529, loss: 0.027668049558997154
2023-01-24 07:00:18.111986: step: 1488/529, loss: 0.0005954480729997158
2023-01-24 07:00:19.179449: step: 1492/529, loss: 0.0011912855552509427
2023-01-24 07:00:20.228272: step: 1496/529, loss: 0.00047708695637993515
2023-01-24 07:00:21.264685: step: 1500/529, loss: 0.004602633882313967
2023-01-24 07:00:22.307314: step: 1504/529, loss: 0.0015028327470645308
2023-01-24 07:00:23.352685: step: 1508/529, loss: 0.010026974603533745
2023-01-24 07:00:24.425017: step: 1512/529, loss: 0.003305347403511405
2023-01-24 07:00:25.485119: step: 1516/529, loss: 0.004152633249759674
2023-01-24 07:00:26.535443: step: 1520/529, loss: 0.0019243067363277078
2023-01-24 07:00:27.601154: step: 1524/529, loss: 0.0026344864163547754
2023-01-24 07:00:28.632842: step: 1528/529, loss: 0.0036074661184102297
2023-01-24 07:00:29.672250: step: 1532/529, loss: 0.0037625590339303017
2023-01-24 07:00:30.718752: step: 1536/529, loss: 0.0075498102232813835
2023-01-24 07:00:31.754709: step: 1540/529, loss: 0.008727450855076313
2023-01-24 07:00:32.824283: step: 1544/529, loss: 0.011576127260923386
2023-01-24 07:00:33.863688: step: 1548/529, loss: 0.003296859096735716
2023-01-24 07:00:34.915033: step: 1552/529, loss: 0.037110909819602966
2023-01-24 07:00:35.956904: step: 1556/529, loss: 0.005566664971411228
2023-01-24 07:00:37.013130: step: 1560/529, loss: 0.005826834589242935
2023-01-24 07:00:38.073005: step: 1564/529, loss: 0.024887530133128166
2023-01-24 07:00:39.121698: step: 1568/529, loss: 0.006921121384948492
2023-01-24 07:00:40.162548: step: 1572/529, loss: 0.00469944067299366
2023-01-24 07:00:41.188670: step: 1576/529, loss: 0.005027053412050009
2023-01-24 07:00:42.240808: step: 1580/529, loss: 0.0029274122789502144
2023-01-24 07:00:43.296004: step: 1584/529, loss: 0.0025618746876716614
2023-01-24 07:00:44.329269: step: 1588/529, loss: 0.02697928622364998
2023-01-24 07:00:45.371971: step: 1592/529, loss: 0.005197387654334307
2023-01-24 07:00:46.401303: step: 1596/529, loss: 1.45377816807013e-05
2023-01-24 07:00:47.457262: step: 1600/529, loss: 0.009968889877200127
2023-01-24 07:00:48.505968: step: 1604/529, loss: 0.002264374867081642
2023-01-24 07:00:49.568380: step: 1608/529, loss: 0.013011283241212368
2023-01-24 07:00:50.618815: step: 1612/529, loss: 0.0013504907255992293
2023-01-24 07:00:51.660379: step: 1616/529, loss: 0.008070433512330055
2023-01-24 07:00:52.733240: step: 1620/529, loss: 0.007053612265735865
2023-01-24 07:00:53.772642: step: 1624/529, loss: 0.007642920594662428
2023-01-24 07:00:54.812041: step: 1628/529, loss: 0.003725780174136162
2023-01-24 07:00:55.850225: step: 1632/529, loss: 0.007207238115370274
2023-01-24 07:00:56.903244: step: 1636/529, loss: 0.004764213226735592
2023-01-24 07:00:57.946094: step: 1640/529, loss: 0.004099587444216013
2023-01-24 07:00:58.976542: step: 1644/529, loss: 0.02866634726524353
2023-01-24 07:01:00.031391: step: 1648/529, loss: 0.00864456593990326
2023-01-24 07:01:01.075207: step: 1652/529, loss: 0.0008208337821997702
2023-01-24 07:01:02.123955: step: 1656/529, loss: 0.0026163270231336355
2023-01-24 07:01:03.165978: step: 1660/529, loss: 0.0034363132435828447
2023-01-24 07:01:04.215131: step: 1664/529, loss: 0.0016965939430519938
2023-01-24 07:01:05.268107: step: 1668/529, loss: 0.0014859935035929084
2023-01-24 07:01:06.316555: step: 1672/529, loss: 0.00024222467618528754
2023-01-24 07:01:07.361976: step: 1676/529, loss: 0.008612056262791157
2023-01-24 07:01:08.410767: step: 1680/529, loss: 0.0019694555085152388
2023-01-24 07:01:09.460170: step: 1684/529, loss: 0.009304205887019634
2023-01-24 07:01:10.514820: step: 1688/529, loss: 0.002786159748211503
2023-01-24 07:01:11.559790: step: 1692/529, loss: 0.002137355040758848
2023-01-24 07:01:12.614932: step: 1696/529, loss: 0.005678205285221338
2023-01-24 07:01:13.663871: step: 1700/529, loss: 0.0030227606184780598
2023-01-24 07:01:14.723335: step: 1704/529, loss: 0.0007980649243108928
2023-01-24 07:01:15.767024: step: 1708/529, loss: 0.007143289782106876
2023-01-24 07:01:16.810939: step: 1712/529, loss: 0.005251258611679077
2023-01-24 07:01:17.861762: step: 1716/529, loss: 0.009905372746288776
2023-01-24 07:01:18.916294: step: 1720/529, loss: 0.0006169564439915121
2023-01-24 07:01:19.958218: step: 1724/529, loss: 0.0006739806267432868
2023-01-24 07:01:20.995358: step: 1728/529, loss: 0.0003520239260978997
2023-01-24 07:01:22.030530: step: 1732/529, loss: 0.0025270460173487663
2023-01-24 07:01:23.071782: step: 1736/529, loss: 0.007693251129239798
2023-01-24 07:01:24.128409: step: 1740/529, loss: 0.003914014436304569
2023-01-24 07:01:25.180768: step: 1744/529, loss: 0.010403660126030445
2023-01-24 07:01:26.224458: step: 1748/529, loss: 1.3354620023164898e-06
2023-01-24 07:01:27.267053: step: 1752/529, loss: 0.0007473742589354515
2023-01-24 07:01:28.316073: step: 1756/529, loss: 0.004681863822042942
2023-01-24 07:01:29.358538: step: 1760/529, loss: 0.005493064410984516
2023-01-24 07:01:30.412978: step: 1764/529, loss: 0.00654172757640481
2023-01-24 07:01:31.460779: step: 1768/529, loss: 0.010084450244903564
2023-01-24 07:01:32.512427: step: 1772/529, loss: 0.004706752020865679
2023-01-24 07:01:33.543832: step: 1776/529, loss: 0.0009514093981124461
2023-01-24 07:01:34.577823: step: 1780/529, loss: 0.0014096301747485995
2023-01-24 07:01:35.615530: step: 1784/529, loss: 0.00012572364357765764
2023-01-24 07:01:36.669903: step: 1788/529, loss: 0.0232260599732399
2023-01-24 07:01:37.723336: step: 1792/529, loss: 0.0031046848744153976
2023-01-24 07:01:38.769993: step: 1796/529, loss: 0.006571891251951456
2023-01-24 07:01:39.810185: step: 1800/529, loss: 0.00016387851792387664
2023-01-24 07:01:40.867337: step: 1804/529, loss: 0.004842417314648628
2023-01-24 07:01:41.911974: step: 1808/529, loss: 0.005944418720901012
2023-01-24 07:01:42.980737: step: 1812/529, loss: 0.017155833542346954
2023-01-24 07:01:44.018835: step: 1816/529, loss: 0.011897356249392033
2023-01-24 07:01:45.057998: step: 1820/529, loss: 0.005222734529525042
2023-01-24 07:01:46.087668: step: 1824/529, loss: 0.005071532912552357
2023-01-24 07:01:47.120133: step: 1828/529, loss: 0.008446223102509975
2023-01-24 07:01:48.169894: step: 1832/529, loss: 0.004176684655249119
2023-01-24 07:01:49.251054: step: 1836/529, loss: 0.006557229906320572
2023-01-24 07:01:50.290168: step: 1840/529, loss: 0.0024884988088160753
2023-01-24 07:01:51.355627: step: 1844/529, loss: 0.00580362556502223
2023-01-24 07:01:52.410009: step: 1848/529, loss: 0.0016856566071510315
2023-01-24 07:01:53.473533: step: 1852/529, loss: 0.01191211398690939
2023-01-24 07:01:54.525983: step: 1856/529, loss: 0.0036614499986171722
2023-01-24 07:01:55.568238: step: 1860/529, loss: 0.03037346713244915
2023-01-24 07:01:56.615280: step: 1864/529, loss: 0.0011730212718248367
2023-01-24 07:01:57.662128: step: 1868/529, loss: 0.006767342798411846
2023-01-24 07:01:58.717833: step: 1872/529, loss: 0.006049699150025845
2023-01-24 07:01:59.764136: step: 1876/529, loss: 0.0009717896464280784
2023-01-24 07:02:00.829662: step: 1880/529, loss: 0.0024402965791523457
2023-01-24 07:02:01.889974: step: 1884/529, loss: 0.007370056584477425
2023-01-24 07:02:02.943522: step: 1888/529, loss: 0.007271936628967524
2023-01-24 07:02:03.990988: step: 1892/529, loss: 0.0024247579276561737
2023-01-24 07:02:05.035349: step: 1896/529, loss: 0.0014247093349695206
2023-01-24 07:02:06.086954: step: 1900/529, loss: 0.00316026178188622
2023-01-24 07:02:07.120935: step: 1904/529, loss: 0.0006484553450718522
2023-01-24 07:02:08.162056: step: 1908/529, loss: 0.003457282204180956
2023-01-24 07:02:09.199592: step: 1912/529, loss: 0.017518872395157814
2023-01-24 07:02:10.242413: step: 1916/529, loss: 0.01227415632456541
2023-01-24 07:02:11.303436: step: 1920/529, loss: 0.001206504413858056
2023-01-24 07:02:12.366085: step: 1924/529, loss: 0.003585570491850376
2023-01-24 07:02:13.417153: step: 1928/529, loss: 0.0017001867527142167
2023-01-24 07:02:14.474084: step: 1932/529, loss: 0.01086181029677391
2023-01-24 07:02:15.517394: step: 1936/529, loss: 0.01084099430590868
2023-01-24 07:02:16.581182: step: 1940/529, loss: 0.002988401334732771
2023-01-24 07:02:17.614464: step: 1944/529, loss: 0.0008111881325021386
2023-01-24 07:02:18.659757: step: 1948/529, loss: 0.0033058254048228264
2023-01-24 07:02:19.706060: step: 1952/529, loss: 0.006359463557600975
2023-01-24 07:02:20.758114: step: 1956/529, loss: 0.006494003813713789
2023-01-24 07:02:21.804293: step: 1960/529, loss: 0.0013034224975854158
2023-01-24 07:02:22.856776: step: 1964/529, loss: 0.0004844609065912664
2023-01-24 07:02:23.897968: step: 1968/529, loss: 0.0025299948174506426
2023-01-24 07:02:24.927453: step: 1972/529, loss: 0.004244665149599314
2023-01-24 07:02:25.984183: step: 1976/529, loss: 0.0024343086406588554
2023-01-24 07:02:27.036210: step: 1980/529, loss: 0.006696697324514389
2023-01-24 07:02:28.082796: step: 1984/529, loss: 0.001419520704075694
2023-01-24 07:02:29.134787: step: 1988/529, loss: 0.018003270030021667
2023-01-24 07:02:30.187962: step: 1992/529, loss: 0.017761848866939545
2023-01-24 07:02:31.220087: step: 1996/529, loss: 0.005436298903077841
2023-01-24 07:02:32.267123: step: 2000/529, loss: 0.001219843397848308
2023-01-24 07:02:33.291889: step: 2004/529, loss: 0.0013173733605071902
2023-01-24 07:02:34.318812: step: 2008/529, loss: 0.0013252663193270564
2023-01-24 07:02:35.379289: step: 2012/529, loss: 0.004386176820844412
2023-01-24 07:02:36.434837: step: 2016/529, loss: 0.003439849941059947
2023-01-24 07:02:37.485839: step: 2020/529, loss: 0.009806548245251179
2023-01-24 07:02:38.538876: step: 2024/529, loss: 0.022853875532746315
2023-01-24 07:02:39.583912: step: 2028/529, loss: 9.54199640545994e-05
2023-01-24 07:02:40.633945: step: 2032/529, loss: 0.007101565599441528
2023-01-24 07:02:41.695696: step: 2036/529, loss: 0.014761477708816528
2023-01-24 07:02:42.730369: step: 2040/529, loss: 0.002811864949762821
2023-01-24 07:02:43.784502: step: 2044/529, loss: 0.0033866928424686193
2023-01-24 07:02:44.830453: step: 2048/529, loss: 0.017494065687060356
2023-01-24 07:02:45.879518: step: 2052/529, loss: 0.001159417093731463
2023-01-24 07:02:46.935005: step: 2056/529, loss: 0.04199489578604698
2023-01-24 07:02:47.972678: step: 2060/529, loss: 0.00893386173993349
2023-01-24 07:02:49.044150: step: 2064/529, loss: 0.007701272610574961
2023-01-24 07:02:50.087229: step: 2068/529, loss: 0.00024471365031786263
2023-01-24 07:02:51.157879: step: 2072/529, loss: 0.01347952801734209
2023-01-24 07:02:52.182430: step: 2076/529, loss: 0.001283814199268818
2023-01-24 07:02:53.234478: step: 2080/529, loss: 0.006390150170773268
2023-01-24 07:02:54.274269: step: 2084/529, loss: 0.014116287231445312
2023-01-24 07:02:55.321199: step: 2088/529, loss: 0.0037055735010653734
2023-01-24 07:02:56.376631: step: 2092/529, loss: 0.008043169975280762
2023-01-24 07:02:57.414473: step: 2096/529, loss: 0.0025078430771827698
2023-01-24 07:02:58.463806: step: 2100/529, loss: 0.009062597528100014
2023-01-24 07:02:59.506319: step: 2104/529, loss: 0.004181451629847288
2023-01-24 07:03:00.551191: step: 2108/529, loss: 0.0007406818913295865
2023-01-24 07:03:01.603963: step: 2112/529, loss: 0.0006511376122944057
2023-01-24 07:03:02.677472: step: 2116/529, loss: 0.02515660598874092
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3300745719636169, 'r': 0.33445886419083765, 'f1': 0.33225225528477176}, 'combined': 0.24481745126246338, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3693893604486897, 'r': 0.30234486919796766, 'f1': 0.33252132447300475}, 'combined': 0.23393460013176215, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3582229872881356, 'r': 0.32083728652751425, 'f1': 0.338501001001001}, 'combined': 0.24942179021126387, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3905097190267961, 'r': 0.31860958751313645, 'f1': 0.35091454809231554}, 'combined': 0.24914932914554402, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37758734774457575, 'r': 0.34033015214169543, 'f1': 0.3579919963646177}, 'combined': 0.26378357626866566, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3967541652475516, 'r': 0.3125521895661935, 'f1': 0.34965535618299126}, 'combined': 0.24825530288992378, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:05:30.881398: step: 4/529, loss: 0.01954532414674759
2023-01-24 07:05:31.912359: step: 8/529, loss: 0.004827527794986963
2023-01-24 07:05:32.963130: step: 12/529, loss: 0.0023530549369752407
2023-01-24 07:05:33.999845: step: 16/529, loss: 0.007843287661671638
2023-01-24 07:05:35.030569: step: 20/529, loss: 0.00231068953871727
2023-01-24 07:05:36.075815: step: 24/529, loss: 0.00043287378503009677
2023-01-24 07:05:37.122125: step: 28/529, loss: 0.0011379376519471407
2023-01-24 07:05:38.158572: step: 32/529, loss: 0.002764686942100525
2023-01-24 07:05:39.199526: step: 36/529, loss: 0.001859096810221672
2023-01-24 07:05:40.239133: step: 40/529, loss: 0.003255079500377178
2023-01-24 07:05:41.265571: step: 44/529, loss: 0.005087681580334902
2023-01-24 07:05:42.301594: step: 48/529, loss: 0.0029920516535639763
2023-01-24 07:05:43.330311: step: 52/529, loss: 0.0067216381430625916
2023-01-24 07:05:44.367159: step: 56/529, loss: 0.004546578042209148
2023-01-24 07:05:45.420634: step: 60/529, loss: 0.0018207207322120667
2023-01-24 07:05:46.456005: step: 64/529, loss: 6.823855073889717e-05
2023-01-24 07:05:47.490693: step: 68/529, loss: 0.0031718455720692873
2023-01-24 07:05:48.517668: step: 72/529, loss: 0.006877357605844736
2023-01-24 07:05:49.572426: step: 76/529, loss: 0.013448301702737808
2023-01-24 07:05:50.593775: step: 80/529, loss: 0.007238812744617462
2023-01-24 07:05:51.652481: step: 84/529, loss: 0.014285692013800144
2023-01-24 07:05:52.725104: step: 88/529, loss: 0.0036882429849356413
2023-01-24 07:05:53.757667: step: 92/529, loss: 0.0005338211194612086
2023-01-24 07:05:54.813714: step: 96/529, loss: 0.0038916023913770914
2023-01-24 07:05:55.849259: step: 100/529, loss: 0.00026086208526976407
2023-01-24 07:05:56.884024: step: 104/529, loss: 0.002933319192379713
2023-01-24 07:05:57.907824: step: 108/529, loss: 0.003995558712631464
2023-01-24 07:05:58.935730: step: 112/529, loss: 0.005591453984379768
2023-01-24 07:05:59.968087: step: 116/529, loss: 0.011964301578700542
2023-01-24 07:06:00.996751: step: 120/529, loss: 0.0051795560866594315
2023-01-24 07:06:02.042957: step: 124/529, loss: 0.007419218774884939
2023-01-24 07:06:03.082704: step: 128/529, loss: 0.023781759664416313
2023-01-24 07:06:04.119892: step: 132/529, loss: 0.003751203417778015
2023-01-24 07:06:05.158369: step: 136/529, loss: 0.004550854209810495
2023-01-24 07:06:06.201073: step: 140/529, loss: 0.02266247384250164
2023-01-24 07:06:07.240647: step: 144/529, loss: 0.010759777389466763
2023-01-24 07:06:08.318108: step: 148/529, loss: 0.002957502380013466
2023-01-24 07:06:09.366187: step: 152/529, loss: 0.0010958747006952763
2023-01-24 07:06:10.395341: step: 156/529, loss: 0.003890435677021742
2023-01-24 07:06:11.433347: step: 160/529, loss: 0.003994130529463291
2023-01-24 07:06:12.463524: step: 164/529, loss: 0.0005350682185962796
2023-01-24 07:06:13.516957: step: 168/529, loss: 0.01354897953569889
2023-01-24 07:06:14.570053: step: 172/529, loss: 0.000780853966716677
2023-01-24 07:06:15.612438: step: 176/529, loss: 0.00374949281103909
2023-01-24 07:06:16.663910: step: 180/529, loss: 0.00015729459119029343
2023-01-24 07:06:17.719483: step: 184/529, loss: 0.0020107519812881947
2023-01-24 07:06:18.778934: step: 188/529, loss: 0.00917111523449421
2023-01-24 07:06:19.821233: step: 192/529, loss: 0.00017682556062936783
2023-01-24 07:06:20.866241: step: 196/529, loss: 0.002421912271529436
2023-01-24 07:06:21.912699: step: 200/529, loss: 0.01361052505671978
2023-01-24 07:06:22.946222: step: 204/529, loss: 0.0035274813417345285
2023-01-24 07:06:23.979108: step: 208/529, loss: 0.011465724557638168
2023-01-24 07:06:25.021416: step: 212/529, loss: 0.005470445845276117
2023-01-24 07:06:26.062287: step: 216/529, loss: 0.0017092960188165307
2023-01-24 07:06:27.106407: step: 220/529, loss: 0.0019453064305707812
2023-01-24 07:06:28.155444: step: 224/529, loss: 0.0016606864519417286
2023-01-24 07:06:29.205169: step: 228/529, loss: 0.0024217041209340096
2023-01-24 07:06:30.239806: step: 232/529, loss: 0.0025438994634896517
2023-01-24 07:06:31.273624: step: 236/529, loss: 0.010617089457809925
2023-01-24 07:06:32.299260: step: 240/529, loss: 0.0002892845368478447
2023-01-24 07:06:33.353268: step: 244/529, loss: 0.0010042962385341525
2023-01-24 07:06:34.400758: step: 248/529, loss: 0.0031687342561781406
2023-01-24 07:06:35.445659: step: 252/529, loss: 0.0027466958854347467
2023-01-24 07:06:36.489537: step: 256/529, loss: 0.004958385601639748
2023-01-24 07:06:37.546398: step: 260/529, loss: 0.005573937203735113
2023-01-24 07:06:38.609020: step: 264/529, loss: 0.012827573344111443
2023-01-24 07:06:39.648597: step: 268/529, loss: 0.0027617281302809715
2023-01-24 07:06:40.676996: step: 272/529, loss: 0.0012532523833215237
2023-01-24 07:06:41.727907: step: 276/529, loss: 0.003218661993741989
2023-01-24 07:06:42.758135: step: 280/529, loss: 0.01514330692589283
2023-01-24 07:06:43.807445: step: 284/529, loss: 0.005460134241729975
2023-01-24 07:06:44.870025: step: 288/529, loss: 0.008205071091651917
2023-01-24 07:06:45.899563: step: 292/529, loss: 0.024040840566158295
2023-01-24 07:06:46.944520: step: 296/529, loss: 0.00874184537678957
2023-01-24 07:06:47.983880: step: 300/529, loss: 0.0034786139149218798
2023-01-24 07:06:49.033243: step: 304/529, loss: 0.0006200448842719197
2023-01-24 07:06:50.076203: step: 308/529, loss: 0.0003087203367613256
2023-01-24 07:06:51.133556: step: 312/529, loss: 0.02923998236656189
2023-01-24 07:06:52.178504: step: 316/529, loss: 0.0016877205343917012
2023-01-24 07:06:53.232539: step: 320/529, loss: 0.004156186711043119
2023-01-24 07:06:54.269483: step: 324/529, loss: 0.0034036983270198107
2023-01-24 07:06:55.297732: step: 328/529, loss: 0.007906085811555386
2023-01-24 07:06:56.346813: step: 332/529, loss: 0.003128611948341131
2023-01-24 07:06:57.381417: step: 336/529, loss: 0.0002056318917311728
2023-01-24 07:06:58.409311: step: 340/529, loss: 0.0006218391354195774
2023-01-24 07:06:59.466502: step: 344/529, loss: 0.00024410530750174075
2023-01-24 07:07:00.501508: step: 348/529, loss: 0.009633667767047882
2023-01-24 07:07:01.548691: step: 352/529, loss: 0.005283441860228777
2023-01-24 07:07:02.591475: step: 356/529, loss: 0.01262367982417345
2023-01-24 07:07:03.642944: step: 360/529, loss: 0.0043320441618561745
2023-01-24 07:07:04.706746: step: 364/529, loss: 0.006589141208678484
2023-01-24 07:07:05.747016: step: 368/529, loss: 0.0113912895321846
2023-01-24 07:07:06.795580: step: 372/529, loss: 0.008942551910877228
2023-01-24 07:07:07.851958: step: 376/529, loss: 0.014269191771745682
2023-01-24 07:07:08.893065: step: 380/529, loss: 0.0004190189065411687
2023-01-24 07:07:09.947854: step: 384/529, loss: 0.005326719954609871
2023-01-24 07:07:11.002110: step: 388/529, loss: 0.004991291556507349
2023-01-24 07:07:12.054604: step: 392/529, loss: 0.001971410820260644
2023-01-24 07:07:13.099879: step: 396/529, loss: 0.002824721857905388
2023-01-24 07:07:14.150188: step: 400/529, loss: 0.0025639294181019068
2023-01-24 07:07:15.180971: step: 404/529, loss: 3.207637200830504e-05
2023-01-24 07:07:16.223835: step: 408/529, loss: 0.00017237129213754088
2023-01-24 07:07:17.257219: step: 412/529, loss: 0.0005034393398091197
2023-01-24 07:07:18.313123: step: 416/529, loss: 0.0036588930524885654
2023-01-24 07:07:19.350057: step: 420/529, loss: 0.013937288895249367
2023-01-24 07:07:20.405277: step: 424/529, loss: 0.005364018492400646
2023-01-24 07:07:21.444485: step: 428/529, loss: 0.009514844976365566
2023-01-24 07:07:22.506871: step: 432/529, loss: 0.004260318353772163
2023-01-24 07:07:23.542493: step: 436/529, loss: 0.013584223575890064
2023-01-24 07:07:24.586537: step: 440/529, loss: 0.0012761547695845366
2023-01-24 07:07:25.644454: step: 444/529, loss: 0.004958345089107752
2023-01-24 07:07:26.688712: step: 448/529, loss: 0.0019658866804093122
2023-01-24 07:07:27.728951: step: 452/529, loss: 0.0008602796588093042
2023-01-24 07:07:28.799403: step: 456/529, loss: 0.005384955555200577
2023-01-24 07:07:29.865084: step: 460/529, loss: 0.0273515023291111
2023-01-24 07:07:30.929263: step: 464/529, loss: 0.0008273616549558938
2023-01-24 07:07:31.968213: step: 468/529, loss: 0.0031173808965831995
2023-01-24 07:07:33.008574: step: 472/529, loss: 0.0018533933907747269
2023-01-24 07:07:34.061175: step: 476/529, loss: 0.009084579534828663
2023-01-24 07:07:35.115467: step: 480/529, loss: 0.012417135760188103
2023-01-24 07:07:36.172137: step: 484/529, loss: 0.0009216720936819911
2023-01-24 07:07:37.211395: step: 488/529, loss: 0.0036223020870238543
2023-01-24 07:07:38.248095: step: 492/529, loss: 0.005514702759683132
2023-01-24 07:07:39.285264: step: 496/529, loss: 0.0013914547162130475
2023-01-24 07:07:40.335176: step: 500/529, loss: 0.0010951007716357708
2023-01-24 07:07:41.394216: step: 504/529, loss: 0.006260767113417387
2023-01-24 07:07:42.442809: step: 508/529, loss: 0.0001973892649402842
2023-01-24 07:07:43.487880: step: 512/529, loss: 0.005953501909971237
2023-01-24 07:07:44.542551: step: 516/529, loss: 0.009086262434720993
2023-01-24 07:07:45.593710: step: 520/529, loss: 0.0066679841838777065
2023-01-24 07:07:46.626489: step: 524/529, loss: 0.0023904310073703527
2023-01-24 07:07:47.678003: step: 528/529, loss: 0.0009538081358186901
2023-01-24 07:07:48.731649: step: 532/529, loss: 0.00764401163905859
2023-01-24 07:07:49.784146: step: 536/529, loss: 0.013999774120748043
2023-01-24 07:07:50.827880: step: 540/529, loss: 0.0009262578678317368
2023-01-24 07:07:51.870264: step: 544/529, loss: 0.001954246312379837
2023-01-24 07:07:52.915030: step: 548/529, loss: 0.0017167457845062017
2023-01-24 07:07:53.964049: step: 552/529, loss: 0.0032756426371634007
2023-01-24 07:07:55.017453: step: 556/529, loss: 0.008779548108577728
2023-01-24 07:07:56.059175: step: 560/529, loss: 0.006169681437313557
2023-01-24 07:07:57.105370: step: 564/529, loss: 0.005783047992736101
2023-01-24 07:07:58.160272: step: 568/529, loss: 0.0008857750217430294
2023-01-24 07:07:59.205318: step: 572/529, loss: 0.001680071814917028
2023-01-24 07:08:00.253849: step: 576/529, loss: 0.016182927414774895
2023-01-24 07:08:01.293367: step: 580/529, loss: 0.00239744083955884
2023-01-24 07:08:02.350704: step: 584/529, loss: 0.004633632488548756
2023-01-24 07:08:03.406977: step: 588/529, loss: 0.0033443255815654993
2023-01-24 07:08:04.433836: step: 592/529, loss: 0.0024107503704726696
2023-01-24 07:08:05.474765: step: 596/529, loss: 0.003631486790254712
2023-01-24 07:08:06.517872: step: 600/529, loss: 0.005317643750458956
2023-01-24 07:08:07.556899: step: 604/529, loss: 0.0025396232958883047
2023-01-24 07:08:08.605262: step: 608/529, loss: 0.003428045194596052
2023-01-24 07:08:09.641164: step: 612/529, loss: 0.0021843810100108385
2023-01-24 07:08:10.682719: step: 616/529, loss: 0.0038149873726069927
2023-01-24 07:08:11.721318: step: 620/529, loss: 0.0032608467154204845
2023-01-24 07:08:12.765669: step: 624/529, loss: 0.014715909957885742
2023-01-24 07:08:13.811175: step: 628/529, loss: 0.008677640929818153
2023-01-24 07:08:14.855910: step: 632/529, loss: 0.0063589587807655334
2023-01-24 07:08:15.904384: step: 636/529, loss: 0.00017495227803010494
2023-01-24 07:08:16.955911: step: 640/529, loss: 0.005503390915691853
2023-01-24 07:08:18.010705: step: 644/529, loss: 0.0024252599105238914
2023-01-24 07:08:19.058148: step: 648/529, loss: 0.007494138553738594
2023-01-24 07:08:20.111478: step: 652/529, loss: 0.010659885592758656
2023-01-24 07:08:21.164027: step: 656/529, loss: 0.00572338979691267
2023-01-24 07:08:22.204466: step: 660/529, loss: 0.01918092370033264
2023-01-24 07:08:23.253919: step: 664/529, loss: 0.003935312386602163
2023-01-24 07:08:24.305525: step: 668/529, loss: 0.004943212028592825
2023-01-24 07:08:25.345969: step: 672/529, loss: 0.0056266882456839085
2023-01-24 07:08:26.381447: step: 676/529, loss: 0.005428919568657875
2023-01-24 07:08:27.418581: step: 680/529, loss: 0.001886368845589459
2023-01-24 07:08:28.468535: step: 684/529, loss: 0.0029110547620803118
2023-01-24 07:08:29.500907: step: 688/529, loss: 0.00042290231795050204
2023-01-24 07:08:30.532306: step: 692/529, loss: 0.000785257900133729
2023-01-24 07:08:31.603552: step: 696/529, loss: 0.020851055160164833
2023-01-24 07:08:32.649492: step: 700/529, loss: 0.02555830404162407
2023-01-24 07:08:33.679765: step: 704/529, loss: 0.0007838797755539417
2023-01-24 07:08:34.731764: step: 708/529, loss: 3.426442344789393e-05
2023-01-24 07:08:35.763346: step: 712/529, loss: 0.0012816892703995109
2023-01-24 07:08:36.807409: step: 716/529, loss: 0.01079493761062622
2023-01-24 07:08:37.868167: step: 720/529, loss: 0.004079950973391533
2023-01-24 07:08:38.919956: step: 724/529, loss: 0.0009261576342396438
2023-01-24 07:08:39.964813: step: 728/529, loss: 0.0036834871862083673
2023-01-24 07:08:41.007502: step: 732/529, loss: 0.004398300778120756
2023-01-24 07:08:42.053155: step: 736/529, loss: 0.006478363182395697
2023-01-24 07:08:43.094989: step: 740/529, loss: 0.01300923153758049
2023-01-24 07:08:44.147583: step: 744/529, loss: 0.0057972632348537445
2023-01-24 07:08:45.214227: step: 748/529, loss: 0.0016906349919736385
2023-01-24 07:08:46.278413: step: 752/529, loss: 0.027488330379128456
2023-01-24 07:08:47.325258: step: 756/529, loss: 0.0013829410308972
2023-01-24 07:08:48.353297: step: 760/529, loss: 1.2820759366150014e-05
2023-01-24 07:08:49.407446: step: 764/529, loss: 0.0007968873251229525
2023-01-24 07:08:50.452803: step: 768/529, loss: 0.010744359344244003
2023-01-24 07:08:51.495319: step: 772/529, loss: 0.0016503616934642196
2023-01-24 07:08:52.547432: step: 776/529, loss: 0.004419537261128426
2023-01-24 07:08:53.591663: step: 780/529, loss: 0.00807860679924488
2023-01-24 07:08:54.642427: step: 784/529, loss: 0.012245913036167622
2023-01-24 07:08:55.691743: step: 788/529, loss: 0.00864124670624733
2023-01-24 07:08:56.739827: step: 792/529, loss: 5.279907782096416e-05
2023-01-24 07:08:57.779130: step: 796/529, loss: 0.0022962461225688457
2023-01-24 07:08:58.827039: step: 800/529, loss: 0.008585786446928978
2023-01-24 07:08:59.876142: step: 804/529, loss: 0.0009987863013520837
2023-01-24 07:09:00.920897: step: 808/529, loss: 0.0019152145832777023
2023-01-24 07:09:01.955615: step: 812/529, loss: 0.002717895433306694
2023-01-24 07:09:03.024793: step: 816/529, loss: 0.0072733149863779545
2023-01-24 07:09:04.071523: step: 820/529, loss: 0.0013716627145186067
2023-01-24 07:09:05.116510: step: 824/529, loss: 0.003835399867966771
2023-01-24 07:09:06.168225: step: 828/529, loss: 0.0007232326315715909
2023-01-24 07:09:07.217907: step: 832/529, loss: 0.002630772301927209
2023-01-24 07:09:08.272952: step: 836/529, loss: 0.004273257218301296
2023-01-24 07:09:09.319533: step: 840/529, loss: 0.0020624990575015545
2023-01-24 07:09:10.364049: step: 844/529, loss: 0.000740404415410012
2023-01-24 07:09:11.426014: step: 848/529, loss: 0.0037550434935837984
2023-01-24 07:09:12.481474: step: 852/529, loss: 0.004778649192303419
2023-01-24 07:09:13.521388: step: 856/529, loss: 0.0029009883292019367
2023-01-24 07:09:14.551671: step: 860/529, loss: 0.0007351295789703727
2023-01-24 07:09:15.610530: step: 864/529, loss: 5.348044214770198e-05
2023-01-24 07:09:16.663856: step: 868/529, loss: 0.0013033861760050058
2023-01-24 07:09:17.701149: step: 872/529, loss: 0.0012773633934557438
2023-01-24 07:09:18.759695: step: 876/529, loss: 0.0026880817022174597
2023-01-24 07:09:19.803816: step: 880/529, loss: 0.0012941344175487757
2023-01-24 07:09:20.838731: step: 884/529, loss: 0.003138786880299449
2023-01-24 07:09:21.863257: step: 888/529, loss: 0.0030836386140435934
2023-01-24 07:09:22.902829: step: 892/529, loss: 0.0
2023-01-24 07:09:23.954654: step: 896/529, loss: 0.006097411271184683
2023-01-24 07:09:24.996630: step: 900/529, loss: 0.030221397057175636
2023-01-24 07:09:26.033589: step: 904/529, loss: 0.005850756540894508
2023-01-24 07:09:27.061054: step: 908/529, loss: 0.00020152056822553277
2023-01-24 07:09:28.098102: step: 912/529, loss: 0.0044646733440458775
2023-01-24 07:09:29.151230: step: 916/529, loss: 0.006392831448465586
2023-01-24 07:09:30.195212: step: 920/529, loss: 0.0030963122844696045
2023-01-24 07:09:31.246975: step: 924/529, loss: 0.00047330569941550493
2023-01-24 07:09:32.310042: step: 928/529, loss: 0.006304592825472355
2023-01-24 07:09:33.333534: step: 932/529, loss: 0.002993023255839944
2023-01-24 07:09:34.362698: step: 936/529, loss: 0.00042874671635217965
2023-01-24 07:09:35.412804: step: 940/529, loss: 0.0001371793623548001
2023-01-24 07:09:36.453670: step: 944/529, loss: 3.6573783290805295e-05
2023-01-24 07:09:37.491432: step: 948/529, loss: 0.00013529634452424943
2023-01-24 07:09:38.533694: step: 952/529, loss: 0.019869500771164894
2023-01-24 07:09:39.572241: step: 956/529, loss: 0.038167525082826614
2023-01-24 07:09:40.632549: step: 960/529, loss: 0.0019290340133011341
2023-01-24 07:09:41.681829: step: 964/529, loss: 0.012385385110974312
2023-01-24 07:09:42.728548: step: 968/529, loss: 0.0015146546065807343
2023-01-24 07:09:43.780875: step: 972/529, loss: 0.0008462521946057677
2023-01-24 07:09:44.824259: step: 976/529, loss: 0.0033068947959691286
2023-01-24 07:09:45.863439: step: 980/529, loss: 0.0017208864446729422
2023-01-24 07:09:46.900921: step: 984/529, loss: 0.0017936790827661753
2023-01-24 07:09:47.965313: step: 988/529, loss: 0.0028875700663775206
2023-01-24 07:09:49.020490: step: 992/529, loss: 0.004011997953057289
2023-01-24 07:09:50.080294: step: 996/529, loss: 0.010539746843278408
2023-01-24 07:09:51.125027: step: 1000/529, loss: 0.015139748342335224
2023-01-24 07:09:52.163179: step: 1004/529, loss: 0.008691334165632725
2023-01-24 07:09:53.214974: step: 1008/529, loss: 0.00022248673485592008
2023-01-24 07:09:54.260128: step: 1012/529, loss: 0.011865814216434956
2023-01-24 07:09:55.293259: step: 1016/529, loss: 0.003201371291652322
2023-01-24 07:09:56.337285: step: 1020/529, loss: 0.003212942508980632
2023-01-24 07:09:57.388671: step: 1024/529, loss: 0.0038315316196531057
2023-01-24 07:09:58.418841: step: 1028/529, loss: 0.004290254786610603
2023-01-24 07:09:59.460286: step: 1032/529, loss: 0.0040176319889724255
2023-01-24 07:10:00.501248: step: 1036/529, loss: 0.005949924234300852
2023-01-24 07:10:01.533677: step: 1040/529, loss: 0.0007018258911557496
2023-01-24 07:10:02.575371: step: 1044/529, loss: 0.0027438232209533453
2023-01-24 07:10:03.626390: step: 1048/529, loss: 0.0018250832799822092
2023-01-24 07:10:04.668985: step: 1052/529, loss: 0.005582096055150032
2023-01-24 07:10:05.701933: step: 1056/529, loss: 0.004173826426267624
2023-01-24 07:10:06.740202: step: 1060/529, loss: 0.001151932985521853
2023-01-24 07:10:07.775008: step: 1064/529, loss: 0.0037320926785469055
2023-01-24 07:10:08.825131: step: 1068/529, loss: 0.00966629572212696
2023-01-24 07:10:09.898353: step: 1072/529, loss: 0.002055887598544359
2023-01-24 07:10:10.946219: step: 1076/529, loss: 0.01772480458021164
2023-01-24 07:10:11.999624: step: 1080/529, loss: 0.0003332009073346853
2023-01-24 07:10:13.045252: step: 1084/529, loss: 0.03068283572793007
2023-01-24 07:10:14.086146: step: 1088/529, loss: 0.003818134544417262
2023-01-24 07:10:15.122993: step: 1092/529, loss: 0.0016117250779643655
2023-01-24 07:10:16.153252: step: 1096/529, loss: 0.0033208210952579975
2023-01-24 07:10:17.191870: step: 1100/529, loss: 0.003668887075036764
2023-01-24 07:10:18.228012: step: 1104/529, loss: 0.003003299469128251
2023-01-24 07:10:19.296319: step: 1108/529, loss: 0.006399332545697689
2023-01-24 07:10:20.349779: step: 1112/529, loss: 0.0035741664469242096
2023-01-24 07:10:21.391232: step: 1116/529, loss: 0.0029484916012734175
2023-01-24 07:10:22.427298: step: 1120/529, loss: 0.005300041288137436
2023-01-24 07:10:23.472714: step: 1124/529, loss: 0.0008431575843133032
2023-01-24 07:10:24.512248: step: 1128/529, loss: 0.017666339874267578
2023-01-24 07:10:25.561265: step: 1132/529, loss: 0.0021952930837869644
2023-01-24 07:10:26.611498: step: 1136/529, loss: 0.0014462918043136597
2023-01-24 07:10:27.663642: step: 1140/529, loss: 0.00015663470549043268
2023-01-24 07:10:28.693783: step: 1144/529, loss: 0.025589918717741966
2023-01-24 07:10:29.745778: step: 1148/529, loss: 0.004201234318315983
2023-01-24 07:10:30.805128: step: 1152/529, loss: 0.013504664413630962
2023-01-24 07:10:31.851550: step: 1156/529, loss: 0.0031026527285575867
2023-01-24 07:10:32.891574: step: 1160/529, loss: 0.0063041215762495995
2023-01-24 07:10:33.925973: step: 1164/529, loss: 1.8157057638745755e-05
2023-01-24 07:10:34.995896: step: 1168/529, loss: 0.013643822632730007
2023-01-24 07:10:36.035779: step: 1172/529, loss: 0.0004492891894187778
2023-01-24 07:10:37.078897: step: 1176/529, loss: 0.002873055636882782
2023-01-24 07:10:38.115687: step: 1180/529, loss: 0.0022310272324830294
2023-01-24 07:10:39.169473: step: 1184/529, loss: 0.003860749304294586
2023-01-24 07:10:40.224310: step: 1188/529, loss: 0.0006902585737407207
2023-01-24 07:10:41.267944: step: 1192/529, loss: 0.03136343136429787
2023-01-24 07:10:42.327255: step: 1196/529, loss: 0.0003888942883349955
2023-01-24 07:10:43.362705: step: 1200/529, loss: 0.0014790548011660576
2023-01-24 07:10:44.403050: step: 1204/529, loss: 0.03887784853577614
2023-01-24 07:10:45.453995: step: 1208/529, loss: 0.007573306560516357
2023-01-24 07:10:46.504970: step: 1212/529, loss: 0.001519863959401846
2023-01-24 07:10:47.546073: step: 1216/529, loss: 0.00047163767158053815
2023-01-24 07:10:48.598972: step: 1220/529, loss: 0.01812143065035343
2023-01-24 07:10:49.653072: step: 1224/529, loss: 0.005998395383358002
2023-01-24 07:10:50.707590: step: 1228/529, loss: 0.003092394443228841
2023-01-24 07:10:51.785619: step: 1232/529, loss: 0.000265609472990036
2023-01-24 07:10:52.824044: step: 1236/529, loss: 0.0027293041348457336
2023-01-24 07:10:53.872084: step: 1240/529, loss: 0.01495912205427885
2023-01-24 07:10:54.928864: step: 1244/529, loss: 0.0053753117099404335
2023-01-24 07:10:55.982950: step: 1248/529, loss: 0.00598317664116621
2023-01-24 07:10:57.034832: step: 1252/529, loss: 0.0014641213929280639
2023-01-24 07:10:58.072028: step: 1256/529, loss: 0.008569150231778622
2023-01-24 07:10:59.119263: step: 1260/529, loss: 0.00345128052867949
2023-01-24 07:11:00.159932: step: 1264/529, loss: 0.000868515926413238
2023-01-24 07:11:01.211407: step: 1268/529, loss: 0.0023537895176559687
2023-01-24 07:11:02.267162: step: 1272/529, loss: 0.0015392887871712446
2023-01-24 07:11:03.313686: step: 1276/529, loss: 0.007391153369098902
2023-01-24 07:11:04.351005: step: 1280/529, loss: 0.0016162912361323833
2023-01-24 07:11:05.404804: step: 1284/529, loss: 0.0026112550403922796
2023-01-24 07:11:06.451688: step: 1288/529, loss: 0.0003828108892776072
2023-01-24 07:11:07.501718: step: 1292/529, loss: 0.003627361264079809
2023-01-24 07:11:08.561183: step: 1296/529, loss: 0.007039359770715237
2023-01-24 07:11:09.625904: step: 1300/529, loss: 0.00841111596673727
2023-01-24 07:11:10.675371: step: 1304/529, loss: 0.004582188557833433
2023-01-24 07:11:11.730188: step: 1308/529, loss: 0.0029177479445934296
2023-01-24 07:11:12.770533: step: 1312/529, loss: 0.0015576387522742152
2023-01-24 07:11:13.833857: step: 1316/529, loss: 0.035095054656267166
2023-01-24 07:11:14.885516: step: 1320/529, loss: 0.002325756009668112
2023-01-24 07:11:15.941669: step: 1324/529, loss: 0.001977218547835946
2023-01-24 07:11:17.010742: step: 1328/529, loss: 0.0022204043343663216
2023-01-24 07:11:18.059249: step: 1332/529, loss: 0.005964240524917841
2023-01-24 07:11:19.130387: step: 1336/529, loss: 0.004625619389116764
2023-01-24 07:11:20.191788: step: 1340/529, loss: 0.02371775358915329
2023-01-24 07:11:21.255202: step: 1344/529, loss: 0.011852601543068886
2023-01-24 07:11:22.310264: step: 1348/529, loss: 0.00196265522390604
2023-01-24 07:11:23.363354: step: 1352/529, loss: 0.007200157269835472
2023-01-24 07:11:24.411368: step: 1356/529, loss: 0.0016054463339969516
2023-01-24 07:11:25.444755: step: 1360/529, loss: 0.0001437036698916927
2023-01-24 07:11:26.496314: step: 1364/529, loss: 0.0014729555696249008
2023-01-24 07:11:27.562064: step: 1368/529, loss: 0.0012370975455269217
2023-01-24 07:11:28.597829: step: 1372/529, loss: 0.0005450923927128315
2023-01-24 07:11:29.654014: step: 1376/529, loss: 0.0024576110299676657
2023-01-24 07:11:30.699607: step: 1380/529, loss: 0.004145471844822168
2023-01-24 07:11:31.769228: step: 1384/529, loss: 0.0034017690923064947
2023-01-24 07:11:32.814870: step: 1388/529, loss: 0.0026113372296094894
2023-01-24 07:11:33.864432: step: 1392/529, loss: 0.018207484856247902
2023-01-24 07:11:34.916111: step: 1396/529, loss: 0.002914435463026166
2023-01-24 07:11:35.962132: step: 1400/529, loss: 0.026484588161110878
2023-01-24 07:11:37.003326: step: 1404/529, loss: 0.0011438442161306739
2023-01-24 07:11:38.037972: step: 1408/529, loss: 0.0011647769715636969
2023-01-24 07:11:39.087212: step: 1412/529, loss: 0.014256704598665237
2023-01-24 07:11:40.124535: step: 1416/529, loss: 0.008479629643261433
2023-01-24 07:11:41.187237: step: 1420/529, loss: 0.026539508253335953
2023-01-24 07:11:42.253172: step: 1424/529, loss: 0.003622222924605012
2023-01-24 07:11:43.310622: step: 1428/529, loss: 0.006273642648011446
2023-01-24 07:11:44.382940: step: 1432/529, loss: 0.008784571662545204
2023-01-24 07:11:45.426950: step: 1436/529, loss: 0.0009311490575782955
2023-01-24 07:11:46.473610: step: 1440/529, loss: 0.0015597260789945722
2023-01-24 07:11:47.536162: step: 1444/529, loss: 0.005850150249898434
2023-01-24 07:11:48.583671: step: 1448/529, loss: 0.0019786760676652193
2023-01-24 07:11:49.621162: step: 1452/529, loss: 0.0026978172827512026
2023-01-24 07:11:50.712622: step: 1456/529, loss: 0.006016007624566555
2023-01-24 07:11:51.755675: step: 1460/529, loss: 0.0029158438555896282
2023-01-24 07:11:52.817111: step: 1464/529, loss: 0.003299807431176305
2023-01-24 07:11:53.865265: step: 1468/529, loss: 0.00104052503593266
2023-01-24 07:11:54.921126: step: 1472/529, loss: 0.020689290016889572
2023-01-24 07:11:55.978549: step: 1476/529, loss: 0.0032323915511369705
2023-01-24 07:11:57.031286: step: 1480/529, loss: 0.011013713665306568
2023-01-24 07:11:58.075822: step: 1484/529, loss: 0.004391280468553305
2023-01-24 07:11:59.129729: step: 1488/529, loss: 0.0005535929813049734
2023-01-24 07:12:00.175405: step: 1492/529, loss: 0.005308902822434902
2023-01-24 07:12:01.254058: step: 1496/529, loss: 0.004690089263021946
2023-01-24 07:12:02.307985: step: 1500/529, loss: 0.009551119059324265
2023-01-24 07:12:03.354672: step: 1504/529, loss: 0.017965057864785194
2023-01-24 07:12:04.403325: step: 1508/529, loss: 0.009646509774029255
2023-01-24 07:12:05.451111: step: 1512/529, loss: 0.0019925751257687807
2023-01-24 07:12:06.509013: step: 1516/529, loss: 0.0031494018621742725
2023-01-24 07:12:07.572722: step: 1520/529, loss: 0.0037305722944438457
2023-01-24 07:12:08.635444: step: 1524/529, loss: 0.0010255238739773631
2023-01-24 07:12:09.690232: step: 1528/529, loss: 0.01110782753676176
2023-01-24 07:12:10.736506: step: 1532/529, loss: 0.007464790251106024
2023-01-24 07:12:11.820687: step: 1536/529, loss: 0.0172900203615427
2023-01-24 07:12:12.872541: step: 1540/529, loss: 0.0004540151567198336
2023-01-24 07:12:13.910701: step: 1544/529, loss: 0.0010561620583757758
2023-01-24 07:12:14.971243: step: 1548/529, loss: 0.0011781761422753334
2023-01-24 07:12:16.023107: step: 1552/529, loss: 0.010241216979920864
2023-01-24 07:12:17.087755: step: 1556/529, loss: 0.031845126301050186
2023-01-24 07:12:18.143877: step: 1560/529, loss: 0.04116947203874588
2023-01-24 07:12:19.189407: step: 1564/529, loss: 0.00023168123152572662
2023-01-24 07:12:20.268200: step: 1568/529, loss: 0.0013503329828381538
2023-01-24 07:12:21.311203: step: 1572/529, loss: 0.0028104600496590137
2023-01-24 07:12:22.358055: step: 1576/529, loss: 0.0056841871701180935
2023-01-24 07:12:23.413768: step: 1580/529, loss: 0.004517252091318369
2023-01-24 07:12:24.460355: step: 1584/529, loss: 0.004436878953129053
2023-01-24 07:12:25.525881: step: 1588/529, loss: 0.021682292222976685
2023-01-24 07:12:26.569631: step: 1592/529, loss: 0.012700929306447506
2023-01-24 07:12:27.634756: step: 1596/529, loss: 0.0085939671844244
2023-01-24 07:12:28.694876: step: 1600/529, loss: 0.0023251515813171864
2023-01-24 07:12:29.749883: step: 1604/529, loss: 0.00247582676820457
2023-01-24 07:12:30.796264: step: 1608/529, loss: 0.003466186812147498
2023-01-24 07:12:31.842242: step: 1612/529, loss: 0.020121384412050247
2023-01-24 07:12:32.891243: step: 1616/529, loss: 0.045501064509153366
2023-01-24 07:12:33.926782: step: 1620/529, loss: 0.0024784705601632595
2023-01-24 07:12:34.978403: step: 1624/529, loss: 0.005667181685566902
2023-01-24 07:12:36.029984: step: 1628/529, loss: 0.016882605850696564
2023-01-24 07:12:37.087186: step: 1632/529, loss: 0.004980574361979961
2023-01-24 07:12:38.147227: step: 1636/529, loss: 0.0016548606799915433
2023-01-24 07:12:39.204764: step: 1640/529, loss: 0.004596744664013386
2023-01-24 07:12:40.233971: step: 1644/529, loss: 0.0037330964114516973
2023-01-24 07:12:41.284435: step: 1648/529, loss: 0.0028481564950197935
2023-01-24 07:12:42.342235: step: 1652/529, loss: 0.0036452983040362597
2023-01-24 07:12:43.394871: step: 1656/529, loss: 0.0010336849372833967
2023-01-24 07:12:44.439322: step: 1660/529, loss: 0.0020581153221428394
2023-01-24 07:12:45.483454: step: 1664/529, loss: 0.0674237385392189
2023-01-24 07:12:46.539367: step: 1668/529, loss: 0.0003872031229548156
2023-01-24 07:12:47.589053: step: 1672/529, loss: 0.0003695247578434646
2023-01-24 07:12:48.659558: step: 1676/529, loss: 0.005342777818441391
2023-01-24 07:12:49.732494: step: 1680/529, loss: 0.006996373645961285
2023-01-24 07:12:50.786584: step: 1684/529, loss: 0.0035497688222676516
2023-01-24 07:12:51.863792: step: 1688/529, loss: 0.008472017012536526
2023-01-24 07:12:52.946086: step: 1692/529, loss: 0.10133443772792816
2023-01-24 07:12:53.998556: step: 1696/529, loss: 0.007926572114229202
2023-01-24 07:12:55.050042: step: 1700/529, loss: 0.004285447299480438
2023-01-24 07:12:56.089236: step: 1704/529, loss: 0.001144508132711053
2023-01-24 07:12:57.144876: step: 1708/529, loss: 0.0031161054503172636
2023-01-24 07:12:58.173244: step: 1712/529, loss: 0.002313500503078103
2023-01-24 07:12:59.235769: step: 1716/529, loss: 0.004640093073248863
2023-01-24 07:13:00.290174: step: 1720/529, loss: 0.00805331114679575
2023-01-24 07:13:01.357908: step: 1724/529, loss: 0.010073693469166756
2023-01-24 07:13:02.409700: step: 1728/529, loss: 0.0038662077859044075
2023-01-24 07:13:03.460952: step: 1732/529, loss: 0.0020495520438998938
2023-01-24 07:13:04.519075: step: 1736/529, loss: 0.003315746784210205
2023-01-24 07:13:05.563280: step: 1740/529, loss: 0.0011245302157476544
2023-01-24 07:13:06.618513: step: 1744/529, loss: 0.001619907096028328
2023-01-24 07:13:07.703213: step: 1748/529, loss: 0.0073272655718028545
2023-01-24 07:13:08.761725: step: 1752/529, loss: 0.0023567990865558386
2023-01-24 07:13:09.821761: step: 1756/529, loss: 0.0016487013781443238
2023-01-24 07:13:10.874928: step: 1760/529, loss: 0.010578070767223835
2023-01-24 07:13:11.944145: step: 1764/529, loss: 0.00725053995847702
2023-01-24 07:13:12.994734: step: 1768/529, loss: 0.013981441967189312
2023-01-24 07:13:14.038341: step: 1772/529, loss: 0.004138213116675615
2023-01-24 07:13:15.099808: step: 1776/529, loss: 0.002512231469154358
2023-01-24 07:13:16.153859: step: 1780/529, loss: 0.0007638219394721091
2023-01-24 07:13:17.224378: step: 1784/529, loss: 0.0032695638947188854
2023-01-24 07:13:18.285862: step: 1788/529, loss: 0.011093172244727612
2023-01-24 07:13:19.335863: step: 1792/529, loss: 0.023647598922252655
2023-01-24 07:13:20.399139: step: 1796/529, loss: 0.003556785173714161
2023-01-24 07:13:21.469558: step: 1800/529, loss: 0.00263601029291749
2023-01-24 07:13:22.518093: step: 1804/529, loss: 0.0054610725492239
2023-01-24 07:13:23.550291: step: 1808/529, loss: 0.002868467476218939
2023-01-24 07:13:24.599530: step: 1812/529, loss: 0.0035832358989864588
2023-01-24 07:13:25.659780: step: 1816/529, loss: 0.00465819425880909
2023-01-24 07:13:26.713437: step: 1820/529, loss: 0.00011471866309875622
2023-01-24 07:13:27.783217: step: 1824/529, loss: 0.0043467143550515175
2023-01-24 07:13:28.820750: step: 1828/529, loss: 0.007312522269785404
2023-01-24 07:13:29.875720: step: 1832/529, loss: 0.010814406909048557
2023-01-24 07:13:30.937070: step: 1836/529, loss: 0.0018458807608112693
2023-01-24 07:13:31.986022: step: 1840/529, loss: 0.006079292390495539
2023-01-24 07:13:33.042311: step: 1844/529, loss: 0.0033890395425260067
2023-01-24 07:13:34.091117: step: 1848/529, loss: 0.002275952138006687
2023-01-24 07:13:35.156903: step: 1852/529, loss: 0.0033465127926319838
2023-01-24 07:13:36.223489: step: 1856/529, loss: 0.007121488451957703
2023-01-24 07:13:37.293106: step: 1860/529, loss: 0.0057334741577506065
2023-01-24 07:13:38.364757: step: 1864/529, loss: 0.001228256500326097
2023-01-24 07:13:39.424896: step: 1868/529, loss: 0.0007331818924285471
2023-01-24 07:13:40.477844: step: 1872/529, loss: 0.006026719696819782
2023-01-24 07:13:41.534268: step: 1876/529, loss: 0.0013718903064727783
2023-01-24 07:13:42.586459: step: 1880/529, loss: 0.0017088564345613122
2023-01-24 07:13:43.640644: step: 1884/529, loss: 0.0013164597330614924
2023-01-24 07:13:44.688146: step: 1888/529, loss: 0.0020321484189480543
2023-01-24 07:13:45.755683: step: 1892/529, loss: 0.0026107255835086107
2023-01-24 07:13:46.792987: step: 1896/529, loss: 0.003549418644979596
2023-01-24 07:13:47.837500: step: 1900/529, loss: 0.0066976300440728664
2023-01-24 07:13:48.892778: step: 1904/529, loss: 0.006736681796610355
2023-01-24 07:13:49.950834: step: 1908/529, loss: 0.003880217904224992
2023-01-24 07:13:51.015992: step: 1912/529, loss: 0.0009326647268608212
2023-01-24 07:13:52.055606: step: 1916/529, loss: 0.0010575373889878392
2023-01-24 07:13:53.100507: step: 1920/529, loss: 0.0017090090550482273
2023-01-24 07:13:54.149327: step: 1924/529, loss: 0.004903963766992092
2023-01-24 07:13:55.193483: step: 1928/529, loss: 0.00022782431915402412
2023-01-24 07:13:56.233804: step: 1932/529, loss: 0.0030873375944793224
2023-01-24 07:13:57.292623: step: 1936/529, loss: 0.0012864961754530668
2023-01-24 07:13:58.374259: step: 1940/529, loss: 0.042002640664577484
2023-01-24 07:13:59.425687: step: 1944/529, loss: 0.004080172162503004
2023-01-24 07:14:00.485062: step: 1948/529, loss: 0.0033888269681483507
2023-01-24 07:14:01.553517: step: 1952/529, loss: 0.0010484391823410988
2023-01-24 07:14:02.615907: step: 1956/529, loss: 0.023458587005734444
2023-01-24 07:14:03.678054: step: 1960/529, loss: 0.0014475197531282902
2023-01-24 07:14:04.730062: step: 1964/529, loss: 0.026408446952700615
2023-01-24 07:14:05.787329: step: 1968/529, loss: 0.0014669850934296846
2023-01-24 07:14:06.832800: step: 1972/529, loss: 0.004631843883544207
2023-01-24 07:14:07.902355: step: 1976/529, loss: 0.0020155864767730236
2023-01-24 07:14:08.943181: step: 1980/529, loss: 0.0070532942190766335
2023-01-24 07:14:10.014943: step: 1984/529, loss: 0.016619721427559853
2023-01-24 07:14:11.062457: step: 1988/529, loss: 0.025262262672185898
2023-01-24 07:14:12.095094: step: 1992/529, loss: 0.02170470356941223
2023-01-24 07:14:13.149351: step: 1996/529, loss: 0.0022279764525592327
2023-01-24 07:14:14.232041: step: 2000/529, loss: 0.007930046878755093
2023-01-24 07:14:15.302398: step: 2004/529, loss: 0.0034217883367091417
2023-01-24 07:14:16.366793: step: 2008/529, loss: 0.001281469827517867
2023-01-24 07:14:17.432693: step: 2012/529, loss: 0.003413531230762601
2023-01-24 07:14:18.485037: step: 2016/529, loss: 0.002780960639938712
2023-01-24 07:14:19.537835: step: 2020/529, loss: 0.015387630090117455
2023-01-24 07:14:20.566710: step: 2024/529, loss: 0.015134617686271667
2023-01-24 07:14:21.618491: step: 2028/529, loss: 0.004267601296305656
2023-01-24 07:14:22.672920: step: 2032/529, loss: 0.001568476902320981
2023-01-24 07:14:23.733687: step: 2036/529, loss: 0.003909156192094088
2023-01-24 07:14:24.797638: step: 2040/529, loss: 0.010754327289760113
2023-01-24 07:14:25.849587: step: 2044/529, loss: 0.004229620564728975
2023-01-24 07:14:26.897400: step: 2048/529, loss: 0.00015167212404776365
2023-01-24 07:14:27.952797: step: 2052/529, loss: 0.001203554798848927
2023-01-24 07:14:29.001059: step: 2056/529, loss: 0.0020384385716170073
2023-01-24 07:14:30.043342: step: 2060/529, loss: 0.027280915528535843
2023-01-24 07:14:31.098315: step: 2064/529, loss: 0.01512991264462471
2023-01-24 07:14:32.140791: step: 2068/529, loss: 0.0004443250654730946
2023-01-24 07:14:33.192988: step: 2072/529, loss: 0.005818449892103672
2023-01-24 07:14:34.239101: step: 2076/529, loss: 0.002622608793899417
2023-01-24 07:14:35.275867: step: 2080/529, loss: 0.018039708957076073
2023-01-24 07:14:36.346843: step: 2084/529, loss: 0.026779957115650177
2023-01-24 07:14:37.410517: step: 2088/529, loss: 0.001887702033855021
2023-01-24 07:14:38.459892: step: 2092/529, loss: 0.001718476414680481
2023-01-24 07:14:39.517032: step: 2096/529, loss: 0.06352747976779938
2023-01-24 07:14:40.576377: step: 2100/529, loss: 0.00918897520750761
2023-01-24 07:14:41.617955: step: 2104/529, loss: 0.014546978287398815
2023-01-24 07:14:42.687132: step: 2108/529, loss: 0.016607722267508507
2023-01-24 07:14:43.733801: step: 2112/529, loss: 0.0009315998759120703
2023-01-24 07:14:44.787719: step: 2116/529, loss: 0.004374222829937935
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3256763560687433, 'r': 0.32876626457034425, 'f1': 0.3272140159179819}, 'combined': 0.2411050643606182, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37338378215905016, 'r': 0.3049626702450881, 'f1': 0.3357225937568405}, 'combined': 0.23618674937667172, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3576196808510639, 'r': 0.31893975332068314, 'f1': 0.3371740220661986}, 'combined': 0.24844401625930423, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39044364993616015, 'r': 0.31991848803669665, 'f1': 0.3516801796547284}, 'combined': 0.24969292755485717, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37495558177309407, 'r': 0.3365350857280332, 'f1': 0.354707980357347}, 'combined': 0.2613637750001504, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.4001907608563583, 'r': 0.31560895812514544, 'f1': 0.35290259477860497}, 'combined': 0.2505608422928095, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:17:15.085532: step: 4/529, loss: 0.0037140233907848597
2023-01-24 07:17:16.106911: step: 8/529, loss: 0.007363326847553253
2023-01-24 07:17:17.151344: step: 12/529, loss: 0.004608663730323315
2023-01-24 07:17:18.176085: step: 16/529, loss: 0.0027266694232821465
2023-01-24 07:17:19.240277: step: 20/529, loss: 0.0044874330051243305
2023-01-24 07:17:20.277681: step: 24/529, loss: 0.0015738230431452394
2023-01-24 07:17:21.306208: step: 28/529, loss: 0.004707221407443285
2023-01-24 07:17:22.353714: step: 32/529, loss: 0.03244788572192192
2023-01-24 07:17:23.392505: step: 36/529, loss: 0.00859522819519043
2023-01-24 07:17:24.434983: step: 40/529, loss: 0.0037811105139553547
2023-01-24 07:17:25.467681: step: 44/529, loss: 0.0032610762864351273
2023-01-24 07:17:26.492981: step: 48/529, loss: 0.012759698554873466
2023-01-24 07:17:27.547062: step: 52/529, loss: 0.00409624632447958
2023-01-24 07:17:28.589380: step: 56/529, loss: 0.002068314701318741
2023-01-24 07:17:29.646464: step: 60/529, loss: 0.01663852483034134
2023-01-24 07:17:30.689377: step: 64/529, loss: 0.005965459160506725
2023-01-24 07:17:31.719506: step: 68/529, loss: 0.008445071056485176
2023-01-24 07:17:32.759518: step: 72/529, loss: 0.0005764389061369002
2023-01-24 07:17:33.795777: step: 76/529, loss: 0.010759158059954643
2023-01-24 07:17:34.834308: step: 80/529, loss: 0.00017509213648736477
2023-01-24 07:17:35.877365: step: 84/529, loss: 0.0007360644522123039
2023-01-24 07:17:36.916997: step: 88/529, loss: 0.004500131588429213
2023-01-24 07:17:37.967300: step: 92/529, loss: 0.008626696653664112
2023-01-24 07:17:39.012514: step: 96/529, loss: 0.0027312820311635733
2023-01-24 07:17:40.056156: step: 100/529, loss: 0.012191029265522957
2023-01-24 07:17:41.083509: step: 104/529, loss: 0.007185385096818209
2023-01-24 07:17:42.143086: step: 108/529, loss: 0.004905566107481718
2023-01-24 07:17:43.185041: step: 112/529, loss: 0.004030782263725996
2023-01-24 07:17:44.218758: step: 116/529, loss: 0.016415033489465714
2023-01-24 07:17:45.263012: step: 120/529, loss: 0.0008366347174160182
2023-01-24 07:17:46.326515: step: 124/529, loss: 0.0015930411173030734
2023-01-24 07:17:47.354418: step: 128/529, loss: 0.002372258808463812
2023-01-24 07:17:48.402434: step: 132/529, loss: 0.009112424217164516
2023-01-24 07:17:49.455338: step: 136/529, loss: 0.0010882836068049073
2023-01-24 07:17:50.496058: step: 140/529, loss: 0.0032116733491420746
2023-01-24 07:17:51.543379: step: 144/529, loss: 0.004124924074858427
2023-01-24 07:17:52.597127: step: 148/529, loss: 0.0026849282439798117
2023-01-24 07:17:53.655662: step: 152/529, loss: 0.012590489350259304
2023-01-24 07:17:54.696428: step: 156/529, loss: 0.003016457427293062
2023-01-24 07:17:55.752838: step: 160/529, loss: 0.005077538546174765
2023-01-24 07:17:56.784055: step: 164/529, loss: 0.0031695785000920296
2023-01-24 07:17:57.830193: step: 168/529, loss: 0.0020259791053831577
2023-01-24 07:17:58.876517: step: 172/529, loss: 0.004039300139993429
2023-01-24 07:17:59.936188: step: 176/529, loss: 3.323805867694318e-05
2023-01-24 07:18:00.974796: step: 180/529, loss: 0.003353292355313897
2023-01-24 07:18:02.028128: step: 184/529, loss: 0.005855282302945852
2023-01-24 07:18:03.071500: step: 188/529, loss: 0.006960767786949873
2023-01-24 07:18:04.104561: step: 192/529, loss: 7.998461660463363e-05
2023-01-24 07:18:05.146982: step: 196/529, loss: 0.002480238676071167
2023-01-24 07:18:06.213157: step: 200/529, loss: 0.0027573422994464636
2023-01-24 07:18:07.248982: step: 204/529, loss: 9.641732322052121e-05
2023-01-24 07:18:08.302847: step: 208/529, loss: 0.00012682353553827852
2023-01-24 07:18:09.347262: step: 212/529, loss: 0.004122037906199694
2023-01-24 07:18:10.397653: step: 216/529, loss: 0.006666763219982386
2023-01-24 07:18:11.469104: step: 220/529, loss: 0.004897987935692072
2023-01-24 07:18:12.515535: step: 224/529, loss: 0.004491490311920643
2023-01-24 07:18:13.556402: step: 228/529, loss: 0.003970337100327015
2023-01-24 07:18:14.594627: step: 232/529, loss: 0.0026997982058674097
2023-01-24 07:18:15.640546: step: 236/529, loss: 0.0018035128014162183
2023-01-24 07:18:16.702201: step: 240/529, loss: 0.044095251709222794
2023-01-24 07:18:17.751083: step: 244/529, loss: 0.0046372017823159695
2023-01-24 07:18:18.791315: step: 248/529, loss: 0.0023649989161640406
2023-01-24 07:18:19.843575: step: 252/529, loss: 0.0108381612226367
2023-01-24 07:18:20.884130: step: 256/529, loss: 0.014285038225352764
2023-01-24 07:18:21.924641: step: 260/529, loss: 0.007839308120310307
2023-01-24 07:18:22.982664: step: 264/529, loss: 0.003131538862362504
2023-01-24 07:18:24.033757: step: 268/529, loss: 0.0014012412866577506
2023-01-24 07:18:25.082708: step: 272/529, loss: 1.2645472452277318e-05
2023-01-24 07:18:26.123171: step: 276/529, loss: 0.000384706596378237
2023-01-24 07:18:27.167808: step: 280/529, loss: 0.0059829652309417725
2023-01-24 07:18:28.232141: step: 284/529, loss: 0.00219951244071126
2023-01-24 07:18:29.274918: step: 288/529, loss: 0.003878541523590684
2023-01-24 07:18:30.321365: step: 292/529, loss: 0.0031933258287608624
2023-01-24 07:18:31.365250: step: 296/529, loss: 0.0010053592268377542
2023-01-24 07:18:32.411837: step: 300/529, loss: 0.011579213663935661
2023-01-24 07:18:33.441943: step: 304/529, loss: 0.013161268085241318
2023-01-24 07:18:34.489819: step: 308/529, loss: 0.0021102421451359987
2023-01-24 07:18:35.543421: step: 312/529, loss: 0.0006987681845203042
2023-01-24 07:18:36.582624: step: 316/529, loss: 0.022646820172667503
2023-01-24 07:18:37.626981: step: 320/529, loss: 0.01387560274451971
2023-01-24 07:18:38.680061: step: 324/529, loss: 0.004615884739905596
2023-01-24 07:18:39.729214: step: 328/529, loss: 0.0035643107257783413
2023-01-24 07:18:40.795979: step: 332/529, loss: 0.00041610028711147606
2023-01-24 07:18:41.857654: step: 336/529, loss: 0.025767065584659576
2023-01-24 07:18:42.922513: step: 340/529, loss: 0.013144945725798607
2023-01-24 07:18:43.961638: step: 344/529, loss: 0.00955265574157238
2023-01-24 07:18:45.002823: step: 348/529, loss: 0.0015506912022829056
2023-01-24 07:18:46.055528: step: 352/529, loss: 0.0009194116573780775
2023-01-24 07:18:47.091025: step: 356/529, loss: 0.026821289211511612
2023-01-24 07:18:48.164494: step: 360/529, loss: 0.027703434228897095
2023-01-24 07:18:49.234726: step: 364/529, loss: 0.00823939312249422
2023-01-24 07:18:50.266322: step: 368/529, loss: 6.478669092757627e-05
2023-01-24 07:18:51.323164: step: 372/529, loss: 0.012762855738401413
2023-01-24 07:18:52.379762: step: 376/529, loss: 0.01189438160508871
2023-01-24 07:18:53.422893: step: 380/529, loss: 0.002343898406252265
2023-01-24 07:18:54.470071: step: 384/529, loss: 0.004080342594534159
2023-01-24 07:18:55.517496: step: 388/529, loss: 0.0017143720760941505
2023-01-24 07:18:56.562230: step: 392/529, loss: 0.0038161305710673332
2023-01-24 07:18:57.621341: step: 396/529, loss: 0.00879244226962328
2023-01-24 07:18:58.656891: step: 400/529, loss: 0.01280451100319624
2023-01-24 07:18:59.712468: step: 404/529, loss: 0.01117230299860239
2023-01-24 07:19:00.756129: step: 408/529, loss: 9.91434990282869e-06
2023-01-24 07:19:01.790438: step: 412/529, loss: 0.0004885715316049755
2023-01-24 07:19:02.843230: step: 416/529, loss: 0.0038478204514831305
2023-01-24 07:19:03.901505: step: 420/529, loss: 0.0007420756155624986
2023-01-24 07:19:04.946549: step: 424/529, loss: 0.0049125379882752895
2023-01-24 07:19:05.999011: step: 428/529, loss: 0.006404376123100519
2023-01-24 07:19:07.052605: step: 432/529, loss: 0.0026791549753397703
2023-01-24 07:19:08.109923: step: 436/529, loss: 0.0013678320683538914
2023-01-24 07:19:09.174188: step: 440/529, loss: 3.432455559959635e-05
2023-01-24 07:19:10.218359: step: 444/529, loss: 0.00014037317305337638
2023-01-24 07:19:11.267981: step: 448/529, loss: 0.006670426111668348
2023-01-24 07:19:12.319768: step: 452/529, loss: 0.006580918561667204
2023-01-24 07:19:13.374656: step: 456/529, loss: 0.0009833669755607843
2023-01-24 07:19:14.423786: step: 460/529, loss: 0.004689553752541542
2023-01-24 07:19:15.471320: step: 464/529, loss: 0.0023072869516909122
2023-01-24 07:19:16.519403: step: 468/529, loss: 0.00025368755450472236
2023-01-24 07:19:17.567469: step: 472/529, loss: 0.009030071087181568
2023-01-24 07:19:18.620607: step: 476/529, loss: 0.00792622659355402
2023-01-24 07:19:19.690762: step: 480/529, loss: 0.018542658537626266
2023-01-24 07:19:20.729560: step: 484/529, loss: 0.00496524665504694
2023-01-24 07:19:21.792796: step: 488/529, loss: 0.001907652709633112
2023-01-24 07:19:22.846672: step: 492/529, loss: 0.010789998807013035
2023-01-24 07:19:23.897496: step: 496/529, loss: 0.0005600329604931176
2023-01-24 07:19:24.945646: step: 500/529, loss: 0.024913666769862175
2023-01-24 07:19:25.990773: step: 504/529, loss: 0.0014568931655958295
2023-01-24 07:19:27.036741: step: 508/529, loss: 0.004080232698470354
2023-01-24 07:19:28.086845: step: 512/529, loss: 0.0031587211415171623
2023-01-24 07:19:29.132651: step: 516/529, loss: 0.001987533876672387
2023-01-24 07:19:30.181908: step: 520/529, loss: 0.004712260328233242
2023-01-24 07:19:31.230507: step: 524/529, loss: 0.0010895893210545182
2023-01-24 07:19:32.273248: step: 528/529, loss: 0.004248771816492081
2023-01-24 07:19:33.317546: step: 532/529, loss: 0.0009934406261891127
2023-01-24 07:19:34.368927: step: 536/529, loss: 0.014179419726133347
2023-01-24 07:19:35.423922: step: 540/529, loss: 0.0005689356476068497
2023-01-24 07:19:36.465685: step: 544/529, loss: 0.011986362747848034
2023-01-24 07:19:37.512646: step: 548/529, loss: 0.010499045252799988
2023-01-24 07:19:38.574548: step: 552/529, loss: 0.006522223353385925
2023-01-24 07:19:39.627869: step: 556/529, loss: 0.012940270826220512
2023-01-24 07:19:40.666481: step: 560/529, loss: 0.005161145236343145
2023-01-24 07:19:41.701997: step: 564/529, loss: 0.009197832085192204
2023-01-24 07:19:42.745789: step: 568/529, loss: 0.0036527689080685377
2023-01-24 07:19:43.803297: step: 572/529, loss: 0.0020357053726911545
2023-01-24 07:19:44.848667: step: 576/529, loss: 0.025222772732377052
2023-01-24 07:19:45.908590: step: 580/529, loss: 0.008358001708984375
2023-01-24 07:19:46.967303: step: 584/529, loss: 0.0016905934317037463
2023-01-24 07:19:48.018059: step: 588/529, loss: 0.005074611399322748
2023-01-24 07:19:49.059949: step: 592/529, loss: 0.009218421764671803
2023-01-24 07:19:50.101346: step: 596/529, loss: 0.0033109921496361494
2023-01-24 07:19:51.145252: step: 600/529, loss: 0.017501311376690865
2023-01-24 07:19:52.194183: step: 604/529, loss: 0.005896209739148617
2023-01-24 07:19:53.245675: step: 608/529, loss: 0.0027542482130229473
2023-01-24 07:19:54.280719: step: 612/529, loss: 0.00024768355069682
2023-01-24 07:19:55.325030: step: 616/529, loss: 0.01774778589606285
2023-01-24 07:19:56.380736: step: 620/529, loss: 0.0021654502488672733
2023-01-24 07:19:57.413408: step: 624/529, loss: 0.0026314547285437584
2023-01-24 07:19:58.448354: step: 628/529, loss: 0.009898966178297997
2023-01-24 07:19:59.486908: step: 632/529, loss: 0.011996070854365826
2023-01-24 07:20:00.530433: step: 636/529, loss: 0.0032017745543271303
2023-01-24 07:20:01.594919: step: 640/529, loss: 0.0027105931658297777
2023-01-24 07:20:02.653415: step: 644/529, loss: 0.001175255049020052
2023-01-24 07:20:03.696933: step: 648/529, loss: 0.0024072739761322737
2023-01-24 07:20:04.745206: step: 652/529, loss: 3.804731750278734e-05
2023-01-24 07:20:05.790253: step: 656/529, loss: 0.006953171920031309
2023-01-24 07:20:06.850786: step: 660/529, loss: 0.004596054553985596
2023-01-24 07:20:07.900247: step: 664/529, loss: 0.00041125252027995884
2023-01-24 07:20:08.949036: step: 668/529, loss: 0.0030098790302872658
2023-01-24 07:20:09.994777: step: 672/529, loss: 7.274878953467123e-06
2023-01-24 07:20:11.060476: step: 676/529, loss: 0.003445247421041131
2023-01-24 07:20:12.112424: step: 680/529, loss: 0.0002504125877749175
2023-01-24 07:20:13.148499: step: 684/529, loss: 0.010124568827450275
2023-01-24 07:20:14.200367: step: 688/529, loss: 0.0045191217213869095
2023-01-24 07:20:15.244085: step: 692/529, loss: 1.2206885912746657e-05
2023-01-24 07:20:16.281352: step: 696/529, loss: 0.0002887707087211311
2023-01-24 07:20:17.334938: step: 700/529, loss: 0.015842795372009277
2023-01-24 07:20:18.399868: step: 704/529, loss: 0.0023848742712289095
2023-01-24 07:20:19.462276: step: 708/529, loss: 0.006225676275789738
2023-01-24 07:20:20.507398: step: 712/529, loss: 0.01146108377724886
2023-01-24 07:20:21.562119: step: 716/529, loss: 0.01568037085235119
2023-01-24 07:20:22.601545: step: 720/529, loss: 0.003764503635466099
2023-01-24 07:20:23.655087: step: 724/529, loss: 0.004998202435672283
2023-01-24 07:20:24.694094: step: 728/529, loss: 0.0030842002015560865
2023-01-24 07:20:25.737800: step: 732/529, loss: 0.009460856206715107
2023-01-24 07:20:26.800088: step: 736/529, loss: 0.004166828002780676
2023-01-24 07:20:27.862541: step: 740/529, loss: 0.008676378056406975
2023-01-24 07:20:28.904703: step: 744/529, loss: 0.007000930607318878
2023-01-24 07:20:29.950735: step: 748/529, loss: 0.0025891580153256655
2023-01-24 07:20:30.997129: step: 752/529, loss: 0.0013015758013352752
2023-01-24 07:20:32.062227: step: 756/529, loss: 0.004177324939519167
2023-01-24 07:20:33.093786: step: 760/529, loss: 1.4848366845399141e-05
2023-01-24 07:20:34.132945: step: 764/529, loss: 4.147878280491568e-05
2023-01-24 07:20:35.176553: step: 768/529, loss: 0.00991077534854412
2023-01-24 07:20:36.227212: step: 772/529, loss: 0.0014547478640452027
2023-01-24 07:20:37.282012: step: 776/529, loss: 0.001693952246569097
2023-01-24 07:20:38.325013: step: 780/529, loss: 0.00014577664842363447
2023-01-24 07:20:39.361892: step: 784/529, loss: 0.00577347120270133
2023-01-24 07:20:40.420390: step: 788/529, loss: 0.013503513298928738
2023-01-24 07:20:41.482937: step: 792/529, loss: 0.004513662774115801
2023-01-24 07:20:42.523236: step: 796/529, loss: 4.7638040996389464e-05
2023-01-24 07:20:43.557354: step: 800/529, loss: 0.0004572199541144073
2023-01-24 07:20:44.612464: step: 804/529, loss: 0.007813621312379837
2023-01-24 07:20:45.657920: step: 808/529, loss: 0.05005307123064995
2023-01-24 07:20:46.706060: step: 812/529, loss: 0.002417173469439149
2023-01-24 07:20:47.748333: step: 816/529, loss: 0.0017533792415633798
2023-01-24 07:20:48.795798: step: 820/529, loss: 0.014769935049116611
2023-01-24 07:20:49.838969: step: 824/529, loss: 0.004178961273282766
2023-01-24 07:20:50.887224: step: 828/529, loss: 0.00013096911425236613
2023-01-24 07:20:51.935080: step: 832/529, loss: 0.0037084289360791445
2023-01-24 07:20:52.974834: step: 836/529, loss: 0.004279987886548042
2023-01-24 07:20:54.024298: step: 840/529, loss: 0.0011910549364984035
2023-01-24 07:20:55.062913: step: 844/529, loss: 0.0047609745524823666
2023-01-24 07:20:56.129865: step: 848/529, loss: 0.002467039041221142
2023-01-24 07:20:57.177457: step: 852/529, loss: 0.003256711643189192
2023-01-24 07:20:58.218419: step: 856/529, loss: 0.007680240087211132
2023-01-24 07:20:59.255637: step: 860/529, loss: 0.002249338896945119
2023-01-24 07:21:00.302259: step: 864/529, loss: 0.005415516905486584
2023-01-24 07:21:01.361793: step: 868/529, loss: 0.0019472382264211774
2023-01-24 07:21:02.399591: step: 872/529, loss: 0.002556249499320984
2023-01-24 07:21:03.468340: step: 876/529, loss: 0.006466090679168701
2023-01-24 07:21:04.508559: step: 880/529, loss: 0.002294387901201844
2023-01-24 07:21:05.569355: step: 884/529, loss: 0.01852002553641796
2023-01-24 07:21:06.602966: step: 888/529, loss: 0.0030034990049898624
2023-01-24 07:21:07.646726: step: 892/529, loss: 0.0011849309084936976
2023-01-24 07:21:08.701782: step: 896/529, loss: 0.0020137985702604055
2023-01-24 07:21:09.752987: step: 900/529, loss: 0.009167115204036236
2023-01-24 07:21:10.803405: step: 904/529, loss: 0.002979674143716693
2023-01-24 07:21:11.849739: step: 908/529, loss: 0.0035214924719184637
2023-01-24 07:21:12.902568: step: 912/529, loss: 0.0065216198563575745
2023-01-24 07:21:13.967668: step: 916/529, loss: 0.005801389925181866
2023-01-24 07:21:15.021362: step: 920/529, loss: 0.004252105951309204
2023-01-24 07:21:16.052032: step: 924/529, loss: 0.0007447049720212817
2023-01-24 07:21:17.089547: step: 928/529, loss: 0.0006038918509148061
2023-01-24 07:21:18.128018: step: 932/529, loss: 0.0005102146533317864
2023-01-24 07:21:19.181422: step: 936/529, loss: 0.015616899356245995
2023-01-24 07:21:20.224657: step: 940/529, loss: 0.0020776998717337847
2023-01-24 07:21:21.272861: step: 944/529, loss: 0.00170222541783005
2023-01-24 07:21:22.313587: step: 948/529, loss: 0.0004186028672847897
2023-01-24 07:21:23.354654: step: 952/529, loss: 0.0005757810431532562
2023-01-24 07:21:24.410627: step: 956/529, loss: 0.005286172963678837
2023-01-24 07:21:25.450901: step: 960/529, loss: 0.006571881007403135
2023-01-24 07:21:26.500606: step: 964/529, loss: 0.010248671285808086
2023-01-24 07:21:27.543581: step: 968/529, loss: 0.0007061854121275246
2023-01-24 07:21:28.579816: step: 972/529, loss: 0.0005732354475185275
2023-01-24 07:21:29.613256: step: 976/529, loss: 0.00342729315161705
2023-01-24 07:21:30.645399: step: 980/529, loss: 0.0004146279243286699
2023-01-24 07:21:31.699161: step: 984/529, loss: 0.0023045900743454695
2023-01-24 07:21:32.740632: step: 988/529, loss: 0.006229712627828121
2023-01-24 07:21:33.782364: step: 992/529, loss: 0.0031180190853774548
2023-01-24 07:21:34.837650: step: 996/529, loss: 0.0009226909605786204
2023-01-24 07:21:35.886312: step: 1000/529, loss: 0.003265135455876589
2023-01-24 07:21:36.929670: step: 1004/529, loss: 0.00539995776489377
2023-01-24 07:21:37.983064: step: 1008/529, loss: 0.0003146221279166639
2023-01-24 07:21:39.037447: step: 1012/529, loss: 0.0054960367269814014
2023-01-24 07:21:40.089957: step: 1016/529, loss: 0.008426538668572903
2023-01-24 07:21:41.119674: step: 1020/529, loss: 0.00016055663581937551
2023-01-24 07:21:42.173446: step: 1024/529, loss: 0.00010434867726871744
2023-01-24 07:21:43.218496: step: 1028/529, loss: 0.004037004429847002
2023-01-24 07:21:44.256523: step: 1032/529, loss: 0.010236815549433231
2023-01-24 07:21:45.297013: step: 1036/529, loss: 0.0004770483647007495
2023-01-24 07:21:46.340579: step: 1040/529, loss: 0.00807817094027996
2023-01-24 07:21:47.375433: step: 1044/529, loss: 0.0033139334991574287
2023-01-24 07:21:48.423742: step: 1048/529, loss: 0.003517554607242346
2023-01-24 07:21:49.461079: step: 1052/529, loss: 0.0037483545020222664
2023-01-24 07:21:50.527948: step: 1056/529, loss: 0.006665835622698069
2023-01-24 07:21:51.589922: step: 1060/529, loss: 0.01069339457899332
2023-01-24 07:21:52.639912: step: 1064/529, loss: 0.011766803450882435
2023-01-24 07:21:53.687595: step: 1068/529, loss: 0.01205790601670742
2023-01-24 07:21:54.743645: step: 1072/529, loss: 0.0007381334435194731
2023-01-24 07:21:55.785388: step: 1076/529, loss: 0.009628570638597012
2023-01-24 07:21:56.846951: step: 1080/529, loss: 0.0015007449546828866
2023-01-24 07:21:57.889449: step: 1084/529, loss: 0.005146688316017389
2023-01-24 07:21:58.946825: step: 1088/529, loss: 0.09127529710531235
2023-01-24 07:21:59.980530: step: 1092/529, loss: 0.00021335705241654068
2023-01-24 07:22:01.025918: step: 1096/529, loss: 0.003383737290278077
2023-01-24 07:22:02.065217: step: 1100/529, loss: 0.0036397406365722418
2023-01-24 07:22:03.120483: step: 1104/529, loss: 0.039512280374765396
2023-01-24 07:22:04.181357: step: 1108/529, loss: 0.013543150387704372
2023-01-24 07:22:05.223448: step: 1112/529, loss: 0.014971619471907616
2023-01-24 07:22:06.291712: step: 1116/529, loss: 0.0005985999014228582
2023-01-24 07:22:07.329575: step: 1120/529, loss: 0.0002031822077697143
2023-01-24 07:22:08.379486: step: 1124/529, loss: 0.004033518023788929
2023-01-24 07:22:09.436613: step: 1128/529, loss: 0.012922819703817368
2023-01-24 07:22:10.489281: step: 1132/529, loss: 0.005352956708520651
2023-01-24 07:22:11.530164: step: 1136/529, loss: 0.002476489171385765
2023-01-24 07:22:12.599616: step: 1140/529, loss: 0.0013561686500906944
2023-01-24 07:22:13.645878: step: 1144/529, loss: 0.05515532195568085
2023-01-24 07:22:14.729712: step: 1148/529, loss: 0.028133900836110115
2023-01-24 07:22:15.774556: step: 1152/529, loss: 0.002206395147368312
2023-01-24 07:22:16.816060: step: 1156/529, loss: 0.01955327019095421
2023-01-24 07:22:17.857036: step: 1160/529, loss: 0.004749919753521681
2023-01-24 07:22:18.895612: step: 1164/529, loss: 1.1817434142358252e-06
2023-01-24 07:22:19.948170: step: 1168/529, loss: 0.004447528161108494
2023-01-24 07:22:20.991984: step: 1172/529, loss: 0.001559864031150937
2023-01-24 07:22:22.034959: step: 1176/529, loss: 0.0051524150185287
2023-01-24 07:22:23.090463: step: 1180/529, loss: 7.988676225068048e-05
2023-01-24 07:22:24.143200: step: 1184/529, loss: 0.016568822786211967
2023-01-24 07:22:25.216489: step: 1188/529, loss: 0.006948177237063646
2023-01-24 07:22:26.268932: step: 1192/529, loss: 0.00016617057553958148
2023-01-24 07:22:27.322857: step: 1196/529, loss: 0.02696973644196987
2023-01-24 07:22:28.382942: step: 1200/529, loss: 0.002667576540261507
2023-01-24 07:22:29.422228: step: 1204/529, loss: 0.008679074235260487
2023-01-24 07:22:30.475675: step: 1208/529, loss: 0.0016724177403375506
2023-01-24 07:22:31.533556: step: 1212/529, loss: 0.002812038641422987
2023-01-24 07:22:32.578666: step: 1216/529, loss: 0.00047247158363461494
2023-01-24 07:22:33.636220: step: 1220/529, loss: 0.0018974867416545749
2023-01-24 07:22:34.689112: step: 1224/529, loss: 3.432413359405473e-05
2023-01-24 07:22:35.727657: step: 1228/529, loss: 0.003925752826035023
2023-01-24 07:22:36.783944: step: 1232/529, loss: 0.01531320158392191
2023-01-24 07:22:37.843532: step: 1236/529, loss: 0.000788183300755918
2023-01-24 07:22:38.890481: step: 1240/529, loss: 0.0027437377721071243
2023-01-24 07:22:39.947724: step: 1244/529, loss: 0.004910984542220831
2023-01-24 07:22:40.988830: step: 1248/529, loss: 0.008901037275791168
2023-01-24 07:22:42.037355: step: 1252/529, loss: 0.01265747845172882
2023-01-24 07:22:43.091916: step: 1256/529, loss: 0.002478359267115593
2023-01-24 07:22:44.141142: step: 1260/529, loss: 0.010530180297791958
2023-01-24 07:22:45.199721: step: 1264/529, loss: 0.002999641001224518
2023-01-24 07:22:46.266369: step: 1268/529, loss: 0.01876983419060707
2023-01-24 07:22:47.309302: step: 1272/529, loss: 0.041945409029722214
2023-01-24 07:22:48.381391: step: 1276/529, loss: 0.006962242536246777
2023-01-24 07:22:49.449080: step: 1280/529, loss: 0.0027996469289064407
2023-01-24 07:22:50.494265: step: 1284/529, loss: 0.02595708705484867
2023-01-24 07:22:51.546491: step: 1288/529, loss: 0.0034862279426306486
2023-01-24 07:22:52.584577: step: 1292/529, loss: 0.0
2023-01-24 07:22:53.618500: step: 1296/529, loss: 0.003192838979884982
2023-01-24 07:22:54.665108: step: 1300/529, loss: 0.004453867673873901
2023-01-24 07:22:55.707986: step: 1304/529, loss: 0.002583130495622754
2023-01-24 07:22:56.753566: step: 1308/529, loss: 0.002401629462838173
2023-01-24 07:22:57.824766: step: 1312/529, loss: 0.011069645173847675
2023-01-24 07:22:58.882838: step: 1316/529, loss: 0.009756780229508877
2023-01-24 07:22:59.939575: step: 1320/529, loss: 0.005467626266181469
2023-01-24 07:23:00.990635: step: 1324/529, loss: 0.005336384754627943
2023-01-24 07:23:02.038493: step: 1328/529, loss: 0.0009322090772911906
2023-01-24 07:23:03.083876: step: 1332/529, loss: 0.0006837813998572528
2023-01-24 07:23:04.139550: step: 1336/529, loss: 0.00910196453332901
2023-01-24 07:23:05.179787: step: 1340/529, loss: 0.0006432613590732217
2023-01-24 07:23:06.234389: step: 1344/529, loss: 0.007985581643879414
2023-01-24 07:23:07.288648: step: 1348/529, loss: 0.0021324334666132927
2023-01-24 07:23:08.333351: step: 1352/529, loss: 0.0001354393461951986
2023-01-24 07:23:09.375188: step: 1356/529, loss: 0.006900588050484657
2023-01-24 07:23:10.425703: step: 1360/529, loss: 0.0008141408325172961
2023-01-24 07:23:11.473414: step: 1364/529, loss: 0.00016899597540032119
2023-01-24 07:23:12.536246: step: 1368/529, loss: 0.0012238860363140702
2023-01-24 07:23:13.591508: step: 1372/529, loss: 0.005127795040607452
2023-01-24 07:23:14.643844: step: 1376/529, loss: 8.328542025992647e-05
2023-01-24 07:23:15.694256: step: 1380/529, loss: 0.0007493635639548302
2023-01-24 07:23:16.753852: step: 1384/529, loss: 0.0011074476642534137
2023-01-24 07:23:17.815909: step: 1388/529, loss: 0.0018748913425952196
2023-01-24 07:23:18.875288: step: 1392/529, loss: 0.003236520104110241
2023-01-24 07:23:19.956147: step: 1396/529, loss: 0.002921327482908964
2023-01-24 07:23:21.008934: step: 1400/529, loss: 0.03134811669588089
2023-01-24 07:23:22.070748: step: 1404/529, loss: 0.0015671526780351996
2023-01-24 07:23:23.120120: step: 1408/529, loss: 0.0011532946955412626
2023-01-24 07:23:24.187517: step: 1412/529, loss: 0.004763533361256123
2023-01-24 07:23:25.244575: step: 1416/529, loss: 2.480861803633161e-05
2023-01-24 07:23:26.293175: step: 1420/529, loss: 0.0009689464932307601
2023-01-24 07:23:27.352046: step: 1424/529, loss: 0.0019960098434239626
2023-01-24 07:23:28.412965: step: 1428/529, loss: 0.00026565336156636477
2023-01-24 07:23:29.467279: step: 1432/529, loss: 0.003497309982776642
2023-01-24 07:23:30.539597: step: 1436/529, loss: 0.0014974374789744616
2023-01-24 07:23:31.577626: step: 1440/529, loss: 0.0028620664961636066
2023-01-24 07:23:32.639644: step: 1444/529, loss: 0.0024662851355969906
2023-01-24 07:23:33.703416: step: 1448/529, loss: 0.020522547885775566
2023-01-24 07:23:34.760246: step: 1452/529, loss: 0.0006964959902688861
2023-01-24 07:23:35.816179: step: 1456/529, loss: 0.009692458435893059
2023-01-24 07:23:36.874610: step: 1460/529, loss: 0.006227830890566111
2023-01-24 07:23:37.941847: step: 1464/529, loss: 0.006993358489125967
2023-01-24 07:23:39.014249: step: 1468/529, loss: 0.0041832816787064075
2023-01-24 07:23:40.067912: step: 1472/529, loss: 0.0029888206627219915
2023-01-24 07:23:41.133750: step: 1476/529, loss: 0.005621057469397783
2023-01-24 07:23:42.177484: step: 1480/529, loss: 0.0009370629559271038
2023-01-24 07:23:43.229647: step: 1484/529, loss: 0.00045446419971995056
2023-01-24 07:23:44.287548: step: 1488/529, loss: 0.0029750578105449677
2023-01-24 07:23:45.364935: step: 1492/529, loss: 0.003995663020759821
2023-01-24 07:23:46.412016: step: 1496/529, loss: 0.0024975668638944626
2023-01-24 07:23:47.483148: step: 1500/529, loss: 0.011821907013654709
2023-01-24 07:23:48.547107: step: 1504/529, loss: 0.005453081801533699
2023-01-24 07:23:49.591273: step: 1508/529, loss: 0.002573229605332017
2023-01-24 07:23:50.644657: step: 1512/529, loss: 0.00237230840139091
2023-01-24 07:23:51.710821: step: 1516/529, loss: 0.0050940620712935925
2023-01-24 07:23:52.763207: step: 1520/529, loss: 0.004747120197862387
2023-01-24 07:23:53.848445: step: 1524/529, loss: 0.005388921592384577
2023-01-24 07:23:54.915887: step: 1528/529, loss: 0.004092082846909761
2023-01-24 07:23:55.956311: step: 1532/529, loss: 0.00019601719395723194
2023-01-24 07:23:56.998178: step: 1536/529, loss: 0.00010974735778290778
2023-01-24 07:23:58.061798: step: 1540/529, loss: 0.002975917886942625
2023-01-24 07:23:59.123566: step: 1544/529, loss: 0.0005187825881876051
2023-01-24 07:24:00.177969: step: 1548/529, loss: 0.002703945618122816
2023-01-24 07:24:01.241577: step: 1552/529, loss: 0.01375254150480032
2023-01-24 07:24:02.294799: step: 1556/529, loss: 0.0013686912134289742
2023-01-24 07:24:03.372395: step: 1560/529, loss: 0.002727731829509139
2023-01-24 07:24:04.462811: step: 1564/529, loss: 0.006979046855121851
2023-01-24 07:24:05.530540: step: 1568/529, loss: 0.005205978639423847
2023-01-24 07:24:06.592512: step: 1572/529, loss: 0.006595241837203503
2023-01-24 07:24:07.637182: step: 1576/529, loss: 0.009415585547685623
2023-01-24 07:24:08.692893: step: 1580/529, loss: 0.00011147946497658268
2023-01-24 07:24:09.760715: step: 1584/529, loss: 0.0024288652930408716
2023-01-24 07:24:10.809775: step: 1588/529, loss: 2.269660217280034e-05
2023-01-24 07:24:11.875172: step: 1592/529, loss: 0.004198869224637747
2023-01-24 07:24:12.926562: step: 1596/529, loss: 0.0013804089976474643
2023-01-24 07:24:13.985649: step: 1600/529, loss: 0.0008442662074230611
2023-01-24 07:24:15.038488: step: 1604/529, loss: 0.001134915160946548
2023-01-24 07:24:16.088317: step: 1608/529, loss: 0.009165355935692787
2023-01-24 07:24:17.145604: step: 1612/529, loss: 0.005637517664581537
2023-01-24 07:24:18.206075: step: 1616/529, loss: 0.007507156580686569
2023-01-24 07:24:19.294952: step: 1620/529, loss: 0.0029284728225320578
2023-01-24 07:24:20.360567: step: 1624/529, loss: 0.012668718583881855
2023-01-24 07:24:21.425867: step: 1628/529, loss: 0.0013841319596394897
2023-01-24 07:24:22.482751: step: 1632/529, loss: 0.0024372327607125044
2023-01-24 07:24:23.549933: step: 1636/529, loss: 0.0012555678840726614
2023-01-24 07:24:24.596881: step: 1640/529, loss: 0.002120430115610361
2023-01-24 07:24:25.643428: step: 1644/529, loss: 0.0008931196061894298
2023-01-24 07:24:26.702988: step: 1648/529, loss: 0.010051054880023003
2023-01-24 07:24:27.752151: step: 1652/529, loss: 0.002121733734384179
2023-01-24 07:24:28.809226: step: 1656/529, loss: 0.001377974753268063
2023-01-24 07:24:29.882738: step: 1660/529, loss: 0.0012314737541601062
2023-01-24 07:24:30.937189: step: 1664/529, loss: 0.0050186412408947945
2023-01-24 07:24:31.998234: step: 1668/529, loss: 0.0019156120251864195
2023-01-24 07:24:33.071328: step: 1672/529, loss: 0.0025133220478892326
2023-01-24 07:24:34.117943: step: 1676/529, loss: 1.6332645827787928e-05
2023-01-24 07:24:35.194660: step: 1680/529, loss: 0.012591800652444363
2023-01-24 07:24:36.254818: step: 1684/529, loss: 0.0008415223564952612
2023-01-24 07:24:37.314187: step: 1688/529, loss: 0.001133262412622571
2023-01-24 07:24:38.369535: step: 1692/529, loss: 0.016971612349152565
2023-01-24 07:24:39.426630: step: 1696/529, loss: 0.002832441357895732
2023-01-24 07:24:40.490834: step: 1700/529, loss: 0.006976114585995674
2023-01-24 07:24:41.567133: step: 1704/529, loss: 0.007624673191457987
2023-01-24 07:24:42.626284: step: 1708/529, loss: 0.00490959919989109
2023-01-24 07:24:43.700497: step: 1712/529, loss: 0.0020893074106425047
2023-01-24 07:24:44.764125: step: 1716/529, loss: 0.004579850006848574
2023-01-24 07:24:45.826498: step: 1720/529, loss: 0.0037009124644100666
2023-01-24 07:24:46.883321: step: 1724/529, loss: 0.005810212809592485
2023-01-24 07:24:47.936281: step: 1728/529, loss: 0.0008320951019413769
2023-01-24 07:24:48.996211: step: 1732/529, loss: 0.004227285273373127
2023-01-24 07:24:50.057293: step: 1736/529, loss: 0.004570974502712488
2023-01-24 07:24:51.111158: step: 1740/529, loss: 0.006186396349221468
2023-01-24 07:24:52.159734: step: 1744/529, loss: 0.0009346940205432475
2023-01-24 07:24:53.206348: step: 1748/529, loss: 0.00037364018498919904
2023-01-24 07:24:54.260483: step: 1752/529, loss: 0.007283602841198444
2023-01-24 07:24:55.323930: step: 1756/529, loss: 0.046040501445531845
2023-01-24 07:24:56.386373: step: 1760/529, loss: 0.005600692238658667
2023-01-24 07:24:57.437108: step: 1764/529, loss: 0.0
2023-01-24 07:24:58.484291: step: 1768/529, loss: 0.008639183826744556
2023-01-24 07:24:59.547333: step: 1772/529, loss: 0.02638068050146103
2023-01-24 07:25:00.598882: step: 1776/529, loss: 0.024783330038189888
2023-01-24 07:25:01.642208: step: 1780/529, loss: 0.0004539838992059231
2023-01-24 07:25:02.703232: step: 1784/529, loss: 0.025161137804389
2023-01-24 07:25:03.752909: step: 1788/529, loss: 0.0012859432026743889
2023-01-24 07:25:04.808248: step: 1792/529, loss: 0.014201657846570015
2023-01-24 07:25:05.850053: step: 1796/529, loss: 0.0021940567530691624
2023-01-24 07:25:06.891503: step: 1800/529, loss: 0.0005616530543193221
2023-01-24 07:25:07.932057: step: 1804/529, loss: 0.004170292988419533
2023-01-24 07:25:08.988175: step: 1808/529, loss: 0.008446595631539822
2023-01-24 07:25:10.034901: step: 1812/529, loss: 0.000450603140052408
2023-01-24 07:25:11.076800: step: 1816/529, loss: 0.0029140945989638567
2023-01-24 07:25:12.103786: step: 1820/529, loss: 0.0017332229763269424
2023-01-24 07:25:13.151687: step: 1824/529, loss: 0.004897206090390682
2023-01-24 07:25:14.196690: step: 1828/529, loss: 0.006870834622532129
2023-01-24 07:25:15.244302: step: 1832/529, loss: 0.014151008799672127
2023-01-24 07:25:16.311733: step: 1836/529, loss: 0.036038123071193695
2023-01-24 07:25:17.368841: step: 1840/529, loss: 0.011616545729339123
2023-01-24 07:25:18.421638: step: 1844/529, loss: 0.018927808851003647
2023-01-24 07:25:19.460424: step: 1848/529, loss: 0.0
2023-01-24 07:25:20.502619: step: 1852/529, loss: 0.004454266745597124
2023-01-24 07:25:21.555055: step: 1856/529, loss: 0.0035331835970282555
2023-01-24 07:25:22.595598: step: 1860/529, loss: 1.868805702542886e-05
2023-01-24 07:25:23.649717: step: 1864/529, loss: 0.0021432985085994005
2023-01-24 07:25:24.710201: step: 1868/529, loss: 0.003018022049218416
2023-01-24 07:25:25.776897: step: 1872/529, loss: 0.009025768376886845
2023-01-24 07:25:26.818697: step: 1876/529, loss: 0.0006289375596679747
2023-01-24 07:25:27.872043: step: 1880/529, loss: 0.0043432037346065044
2023-01-24 07:25:28.934358: step: 1884/529, loss: 0.0023552393540740013
2023-01-24 07:25:29.973995: step: 1888/529, loss: 0.0007116672350093722
2023-01-24 07:25:31.036333: step: 1892/529, loss: 0.023320242762565613
2023-01-24 07:25:32.088362: step: 1896/529, loss: 0.009287681430578232
2023-01-24 07:25:33.126403: step: 1900/529, loss: 0.0048317378386855125
2023-01-24 07:25:34.173127: step: 1904/529, loss: 0.0021411834750324488
2023-01-24 07:25:35.218039: step: 1908/529, loss: 0.0043587158434093
2023-01-24 07:25:36.246461: step: 1912/529, loss: 0.0
2023-01-24 07:25:37.296813: step: 1916/529, loss: 0.0004871864803135395
2023-01-24 07:25:38.364085: step: 1920/529, loss: 0.0004517881607171148
2023-01-24 07:25:39.421353: step: 1924/529, loss: 0.0035631738137453794
2023-01-24 07:25:40.480509: step: 1928/529, loss: 0.0037075397558510303
2023-01-24 07:25:41.526711: step: 1932/529, loss: 0.005595594644546509
2023-01-24 07:25:42.565341: step: 1936/529, loss: 0.002533398102968931
2023-01-24 07:25:43.617250: step: 1940/529, loss: 0.002870419528335333
2023-01-24 07:25:44.663045: step: 1944/529, loss: 0.003952626138925552
2023-01-24 07:25:45.696516: step: 1948/529, loss: 0.0018022614531219006
2023-01-24 07:25:46.729252: step: 1952/529, loss: 0.005801658611744642
2023-01-24 07:25:47.777106: step: 1956/529, loss: 0.0008817269117571414
2023-01-24 07:25:48.831809: step: 1960/529, loss: 0.0038247734773904085
2023-01-24 07:25:49.880807: step: 1964/529, loss: 0.004059887956827879
2023-01-24 07:25:50.922226: step: 1968/529, loss: 0.02748439647257328
2023-01-24 07:25:51.980718: step: 1972/529, loss: 0.011934623122215271
2023-01-24 07:25:53.030445: step: 1976/529, loss: 0.0038518719375133514
2023-01-24 07:25:54.101812: step: 1980/529, loss: 0.0031616054475307465
2023-01-24 07:25:55.151818: step: 1984/529, loss: 0.005377650260925293
2023-01-24 07:25:56.196243: step: 1988/529, loss: 0.0032389755360782146
2023-01-24 07:25:57.258893: step: 1992/529, loss: 0.0034783773589879274
2023-01-24 07:25:58.307653: step: 1996/529, loss: 0.001888565137051046
2023-01-24 07:25:59.356647: step: 2000/529, loss: 0.014660288579761982
2023-01-24 07:26:00.417966: step: 2004/529, loss: 0.002842474263161421
2023-01-24 07:26:01.473397: step: 2008/529, loss: 0.01490737684071064
2023-01-24 07:26:02.533096: step: 2012/529, loss: 0.0063547599129378796
2023-01-24 07:26:03.595957: step: 2016/529, loss: 0.016145624220371246
2023-01-24 07:26:04.660386: step: 2020/529, loss: 0.0008024487760849297
2023-01-24 07:26:05.712878: step: 2024/529, loss: 0.002280746353790164
2023-01-24 07:26:06.746678: step: 2028/529, loss: 0.0002587547351140529
2023-01-24 07:26:07.795219: step: 2032/529, loss: 0.008462951518595219
2023-01-24 07:26:08.839048: step: 2036/529, loss: 0.005481327418237925
2023-01-24 07:26:09.886109: step: 2040/529, loss: 0.003511536167934537
2023-01-24 07:26:10.937426: step: 2044/529, loss: 0.005110475234687328
2023-01-24 07:26:11.998080: step: 2048/529, loss: 0.0042467848397791386
2023-01-24 07:26:13.038960: step: 2052/529, loss: 0.000514945772010833
2023-01-24 07:26:14.095711: step: 2056/529, loss: 0.024979516863822937
2023-01-24 07:26:15.160853: step: 2060/529, loss: 0.007289297878742218
2023-01-24 07:26:16.215108: step: 2064/529, loss: 0.004846369381994009
2023-01-24 07:26:17.242382: step: 2068/529, loss: 0.001162551692686975
2023-01-24 07:26:18.294317: step: 2072/529, loss: 0.002346632769331336
2023-01-24 07:26:19.337547: step: 2076/529, loss: 0.00891745276749134
2023-01-24 07:26:20.382547: step: 2080/529, loss: 0.0025244178250432014
2023-01-24 07:26:21.432739: step: 2084/529, loss: 0.006365702021867037
2023-01-24 07:26:22.502453: step: 2088/529, loss: 0.005297030787914991
2023-01-24 07:26:23.540558: step: 2092/529, loss: 0.0007587825530208647
2023-01-24 07:26:24.593784: step: 2096/529, loss: 0.008229751139879227
2023-01-24 07:26:25.666683: step: 2100/529, loss: 0.0023025795817375183
2023-01-24 07:26:26.707336: step: 2104/529, loss: 0.0029667671769857407
2023-01-24 07:26:27.753423: step: 2108/529, loss: 0.0015449775382876396
2023-01-24 07:26:28.827838: step: 2112/529, loss: 0.005429327487945557
2023-01-24 07:26:29.878402: step: 2116/529, loss: 0.003750232746824622
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32483238183749336, 'r': 0.33161256438059095, 'f1': 0.32818745808182426}, 'combined': 0.24182233753397575, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3721727975357674, 'r': 0.3029993194597478, 'f1': 0.33404253977957765}, 'combined': 0.23500480185497927, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3591184210526316, 'r': 0.32368358633776095, 'f1': 0.34048153692614774}, 'combined': 0.2508811324718983, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39318351581823996, 'r': 0.3207910883857368, 'f1': 0.3533172391062512}, 'combined': 0.25085523976543833, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37810060834103454, 'r': 0.34222768534852654, 'f1': 0.35927089677026586}, 'combined': 0.2647259239359854, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.397194513932621, 'r': 0.3125521895661935, 'f1': 0.349826253229024}, 'combined': 0.24837663979260702, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3270833333333333, 'r': 0.37380952380952376, 'f1': 0.34888888888888886}, 'combined': 0.23259259259259257, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 12
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:29:00.554138: step: 4/529, loss: 0.0034538169857114553
2023-01-24 07:29:01.609641: step: 8/529, loss: 0.0016711006173864007
2023-01-24 07:29:02.651209: step: 12/529, loss: 0.01156221330165863
2023-01-24 07:29:03.708877: step: 16/529, loss: 0.00015871012874413282
2023-01-24 07:29:04.756855: step: 20/529, loss: 0.003133102087303996
2023-01-24 07:29:05.787307: step: 24/529, loss: 0.0010158048244193196
2023-01-24 07:29:06.822898: step: 28/529, loss: 0.003993500489741564
2023-01-24 07:29:07.864390: step: 32/529, loss: 0.005018666852265596
2023-01-24 07:29:08.931740: step: 36/529, loss: 0.0014677639119327068
2023-01-24 07:29:09.969534: step: 40/529, loss: 0.0026256253477185965
2023-01-24 07:29:11.013040: step: 44/529, loss: 0.0006456120172515512
2023-01-24 07:29:12.063161: step: 48/529, loss: 0.0033675660379230976
2023-01-24 07:29:13.100019: step: 52/529, loss: 0.009733915328979492
2023-01-24 07:29:14.138309: step: 56/529, loss: 0.0034726152662187815
2023-01-24 07:29:15.178702: step: 60/529, loss: 0.0018313925247639418
2023-01-24 07:29:16.214817: step: 64/529, loss: 0.00013744371244683862
2023-01-24 07:29:17.239018: step: 68/529, loss: 0.003951665014028549
2023-01-24 07:29:18.273882: step: 72/529, loss: 0.003070714185014367
2023-01-24 07:29:19.317639: step: 76/529, loss: 0.004276313818991184
2023-01-24 07:29:20.366825: step: 80/529, loss: 0.004900243598967791
2023-01-24 07:29:21.415764: step: 84/529, loss: 0.009483034722507
2023-01-24 07:29:22.445562: step: 88/529, loss: 0.0
2023-01-24 07:29:23.502432: step: 92/529, loss: 0.0053872899152338505
2023-01-24 07:29:24.568132: step: 96/529, loss: 0.00832262635231018
2023-01-24 07:29:25.610180: step: 100/529, loss: 0.0006826301105320454
2023-01-24 07:29:26.666131: step: 104/529, loss: 0.0007925773970782757
2023-01-24 07:29:27.704186: step: 108/529, loss: 0.01183923427015543
2023-01-24 07:29:28.744818: step: 112/529, loss: 0.0062284646555781364
2023-01-24 07:29:29.796064: step: 116/529, loss: 0.010330263525247574
2023-01-24 07:29:30.834386: step: 120/529, loss: 0.0029908437281847
2023-01-24 07:29:31.875647: step: 124/529, loss: 0.0037122832145541906
2023-01-24 07:29:32.906810: step: 128/529, loss: 0.0021550990641117096
2023-01-24 07:29:33.957915: step: 132/529, loss: 0.0009647613042034209
2023-01-24 07:29:35.005159: step: 136/529, loss: 0.0009003085433505476
2023-01-24 07:29:36.046058: step: 140/529, loss: 0.011518586426973343
2023-01-24 07:29:37.106378: step: 144/529, loss: 0.008874570950865746
2023-01-24 07:29:38.157467: step: 148/529, loss: 0.00550888990983367
2023-01-24 07:29:39.199570: step: 152/529, loss: 0.0016588961007073522
2023-01-24 07:29:40.252198: step: 156/529, loss: 0.0010452051647007465
2023-01-24 07:29:41.294522: step: 160/529, loss: 0.010655257850885391
2023-01-24 07:29:42.343738: step: 164/529, loss: 0.01128036342561245
2023-01-24 07:29:43.409046: step: 168/529, loss: 0.0031479373574256897
2023-01-24 07:29:44.460695: step: 172/529, loss: 0.0006826169556006789
2023-01-24 07:29:45.489147: step: 176/529, loss: 0.002177071524783969
2023-01-24 07:29:46.528662: step: 180/529, loss: 0.00041223509470000863
2023-01-24 07:29:47.579161: step: 184/529, loss: 0.0014141061110422015
2023-01-24 07:29:48.617578: step: 188/529, loss: 0.002947329543530941
2023-01-24 07:29:49.702334: step: 192/529, loss: 0.027088206261396408
2023-01-24 07:29:50.753234: step: 196/529, loss: 0.004891794640570879
2023-01-24 07:29:51.801529: step: 200/529, loss: 0.0029908197466284037
2023-01-24 07:29:52.848849: step: 204/529, loss: 0.0033854979556053877
2023-01-24 07:29:53.896969: step: 208/529, loss: 0.0030778059735894203
2023-01-24 07:29:54.945133: step: 212/529, loss: 9.326578947366215e-06
2023-01-24 07:29:55.999621: step: 216/529, loss: 0.009751619771122932
2023-01-24 07:29:57.050306: step: 220/529, loss: 0.00016446239897049963
2023-01-24 07:29:58.098972: step: 224/529, loss: 0.0047297230921685696
2023-01-24 07:29:59.134361: step: 228/529, loss: 0.003842433448880911
2023-01-24 07:30:00.206432: step: 232/529, loss: 0.020309636369347572
2023-01-24 07:30:01.258148: step: 236/529, loss: 0.0009144988725893199
2023-01-24 07:30:02.297431: step: 240/529, loss: 0.006281842943280935
2023-01-24 07:30:03.334325: step: 244/529, loss: 0.0013440930051729083
2023-01-24 07:30:04.369104: step: 248/529, loss: 0.0018926558550447226
2023-01-24 07:30:05.416150: step: 252/529, loss: 0.0012141893384978175
2023-01-24 07:30:06.469708: step: 256/529, loss: 0.0010878157336264849
2023-01-24 07:30:07.507760: step: 260/529, loss: 0.001576004084199667
2023-01-24 07:30:08.549618: step: 264/529, loss: 0.024168329313397408
2023-01-24 07:30:09.590339: step: 268/529, loss: 0.0028887009248137474
2023-01-24 07:30:10.649752: step: 272/529, loss: 0.0031978636980056763
2023-01-24 07:30:11.694748: step: 276/529, loss: 0.0031443950720131397
2023-01-24 07:30:12.740015: step: 280/529, loss: 0.00029196255491115153
2023-01-24 07:30:13.784986: step: 284/529, loss: 0.0007459737826138735
2023-01-24 07:30:14.824292: step: 288/529, loss: 0.011547936126589775
2023-01-24 07:30:15.878520: step: 292/529, loss: 0.01153575349599123
2023-01-24 07:30:16.924243: step: 296/529, loss: 0.00045906411833129823
2023-01-24 07:30:17.984956: step: 300/529, loss: 0.000437918643001467
2023-01-24 07:30:19.046334: step: 304/529, loss: 0.011378184892237186
2023-01-24 07:30:20.094945: step: 308/529, loss: 0.0032906539272516966
2023-01-24 07:30:21.140922: step: 312/529, loss: 0.0014775949530303478
2023-01-24 07:30:22.177064: step: 316/529, loss: 0.00013546424452215433
2023-01-24 07:30:23.208139: step: 320/529, loss: 0.0022926980163902044
2023-01-24 07:30:24.252569: step: 324/529, loss: 0.003716593375429511
2023-01-24 07:30:25.305589: step: 328/529, loss: 0.004395076539367437
2023-01-24 07:30:26.347315: step: 332/529, loss: 3.9748797462380026e-06
2023-01-24 07:30:27.391938: step: 336/529, loss: 0.0008925807778723538
2023-01-24 07:30:28.434367: step: 340/529, loss: 3.408240445423871e-05
2023-01-24 07:30:29.472540: step: 344/529, loss: 0.0003700566594488919
2023-01-24 07:30:30.530765: step: 348/529, loss: 0.0013339375145733356
2023-01-24 07:30:31.574545: step: 352/529, loss: 0.0017752345884218812
2023-01-24 07:30:32.618327: step: 356/529, loss: 0.00028631434543058276
2023-01-24 07:30:33.696217: step: 360/529, loss: 0.006901028100401163
2023-01-24 07:30:34.750687: step: 364/529, loss: 0.00553686311468482
2023-01-24 07:30:35.775926: step: 368/529, loss: 0.00450486596673727
2023-01-24 07:30:36.813904: step: 372/529, loss: 0.0002825112023856491
2023-01-24 07:30:37.856959: step: 376/529, loss: 0.004270290490239859
2023-01-24 07:30:38.891300: step: 380/529, loss: 0.0010503791272640228
2023-01-24 07:30:39.946963: step: 384/529, loss: 0.0004965506959706545
2023-01-24 07:30:40.986905: step: 388/529, loss: 0.015216793864965439
2023-01-24 07:30:42.055807: step: 392/529, loss: 0.004793694242835045
2023-01-24 07:30:43.086272: step: 396/529, loss: 0.00018608092796057463
2023-01-24 07:30:44.127118: step: 400/529, loss: 0.0012672869488596916
2023-01-24 07:30:45.179156: step: 404/529, loss: 0.007794622331857681
2023-01-24 07:30:46.210594: step: 408/529, loss: 0.001383294933475554
2023-01-24 07:30:47.259497: step: 412/529, loss: 0.0012107929214835167
2023-01-24 07:30:48.308688: step: 416/529, loss: 0.005087608005851507
2023-01-24 07:30:49.356165: step: 420/529, loss: 0.0041254255920648575
2023-01-24 07:30:50.397545: step: 424/529, loss: 2.905014980569831e-06
2023-01-24 07:30:51.466330: step: 428/529, loss: 0.00452798418700695
2023-01-24 07:30:52.509010: step: 432/529, loss: 0.00936139840632677
2023-01-24 07:30:53.561362: step: 436/529, loss: 0.0002534158411435783
2023-01-24 07:30:54.615618: step: 440/529, loss: 0.003384101903066039
2023-01-24 07:30:55.682752: step: 444/529, loss: 0.019990907981991768
2023-01-24 07:30:56.735439: step: 448/529, loss: 0.0031755047384649515
2023-01-24 07:30:57.772117: step: 452/529, loss: 0.0009907354833558202
2023-01-24 07:30:58.811659: step: 456/529, loss: 0.0047884550876915455
2023-01-24 07:30:59.866892: step: 460/529, loss: 0.0032467516139149666
2023-01-24 07:31:00.932160: step: 464/529, loss: 0.003332197666168213
2023-01-24 07:31:01.971433: step: 468/529, loss: 0.00868942029774189
2023-01-24 07:31:03.016702: step: 472/529, loss: 0.005520698148757219
2023-01-24 07:31:04.084612: step: 476/529, loss: 0.004008840769529343
2023-01-24 07:31:05.139986: step: 480/529, loss: 0.005649685859680176
2023-01-24 07:31:06.189056: step: 484/529, loss: 0.0016456665471196175
2023-01-24 07:31:07.234692: step: 488/529, loss: 7.642077980563045e-05
2023-01-24 07:31:08.278579: step: 492/529, loss: 0.019764306023716927
2023-01-24 07:31:09.318638: step: 496/529, loss: 0.0016616829670965672
2023-01-24 07:31:10.358665: step: 500/529, loss: 0.003973504062741995
2023-01-24 07:31:11.391429: step: 504/529, loss: 0.001964021008461714
2023-01-24 07:31:12.442953: step: 508/529, loss: 0.02109139785170555
2023-01-24 07:31:13.492080: step: 512/529, loss: 0.0010557562345638871
2023-01-24 07:31:14.533390: step: 516/529, loss: 0.005340509582310915
2023-01-24 07:31:15.587235: step: 520/529, loss: 0.008324533700942993
2023-01-24 07:31:16.625060: step: 524/529, loss: 6.679386569885537e-05
2023-01-24 07:31:17.663686: step: 528/529, loss: 0.00031830911757424474
2023-01-24 07:31:18.704200: step: 532/529, loss: 0.0005614500259980559
2023-01-24 07:31:19.751621: step: 536/529, loss: 0.0015028188936412334
2023-01-24 07:31:20.787787: step: 540/529, loss: 0.0034789899364113808
2023-01-24 07:31:21.841933: step: 544/529, loss: 0.003667730139568448
2023-01-24 07:31:22.899610: step: 548/529, loss: 0.0026404177770018578
2023-01-24 07:31:23.956465: step: 552/529, loss: 0.003268154803663492
2023-01-24 07:31:24.998375: step: 556/529, loss: 0.0051860809326171875
2023-01-24 07:31:26.039298: step: 560/529, loss: 0.002388609340414405
2023-01-24 07:31:27.072887: step: 564/529, loss: 0.003886688034981489
2023-01-24 07:31:28.142186: step: 568/529, loss: 0.003776333061978221
2023-01-24 07:31:29.196972: step: 572/529, loss: 0.0010710746282711625
2023-01-24 07:31:30.242440: step: 576/529, loss: 0.07810000330209732
2023-01-24 07:31:31.282086: step: 580/529, loss: 0.009665369987487793
2023-01-24 07:31:32.333396: step: 584/529, loss: 0.011006626300513744
2023-01-24 07:31:33.379806: step: 588/529, loss: 0.005104816053062677
2023-01-24 07:31:34.423495: step: 592/529, loss: 0.0031157396733760834
2023-01-24 07:31:35.466950: step: 596/529, loss: 0.013658968731760979
2023-01-24 07:31:36.525001: step: 600/529, loss: 0.008167355321347713
2023-01-24 07:31:37.562290: step: 604/529, loss: 0.007260228507220745
2023-01-24 07:31:38.606037: step: 608/529, loss: 0.0036794058978557587
2023-01-24 07:31:39.639711: step: 612/529, loss: 0.0023569369222968817
2023-01-24 07:31:40.688760: step: 616/529, loss: 0.0006588835385628045
2023-01-24 07:31:41.725486: step: 620/529, loss: 0.003614986315369606
2023-01-24 07:31:42.783928: step: 624/529, loss: 0.004600749351084232
2023-01-24 07:31:43.831270: step: 628/529, loss: 0.01361650601029396
2023-01-24 07:31:44.872660: step: 632/529, loss: 0.005067877471446991
2023-01-24 07:31:45.896702: step: 636/529, loss: 0.002755256835371256
2023-01-24 07:31:46.963532: step: 640/529, loss: 0.007259910460561514
2023-01-24 07:31:48.006633: step: 644/529, loss: 0.0013632168993353844
2023-01-24 07:31:49.027216: step: 648/529, loss: 0.0010076288599520922
2023-01-24 07:31:50.077162: step: 652/529, loss: 0.008541107177734375
2023-01-24 07:31:51.105193: step: 656/529, loss: 0.00029975667712278664
2023-01-24 07:31:52.158855: step: 660/529, loss: 0.0031777096446603537
2023-01-24 07:31:53.232808: step: 664/529, loss: 0.014218487776815891
2023-01-24 07:31:54.287004: step: 668/529, loss: 0.0036193605046719313
2023-01-24 07:31:55.338018: step: 672/529, loss: 0.0037756417877972126
2023-01-24 07:31:56.378953: step: 676/529, loss: 0.018947923555970192
2023-01-24 07:31:57.434077: step: 680/529, loss: 0.0020872927270829678
2023-01-24 07:31:58.473914: step: 684/529, loss: 0.008403408341109753
2023-01-24 07:31:59.518800: step: 688/529, loss: 0.001032195519655943
2023-01-24 07:32:00.562421: step: 692/529, loss: 0.0011361497454345226
2023-01-24 07:32:01.604268: step: 696/529, loss: 0.003513647010549903
2023-01-24 07:32:02.657486: step: 700/529, loss: 0.0001323939359281212
2023-01-24 07:32:03.720824: step: 704/529, loss: 0.00027199662872590125
2023-01-24 07:32:04.763214: step: 708/529, loss: 0.021403253078460693
2023-01-24 07:32:05.812053: step: 712/529, loss: 0.028027458116412163
2023-01-24 07:32:06.874348: step: 716/529, loss: 0.0006352125201374292
2023-01-24 07:32:07.922579: step: 720/529, loss: 3.136417217319831e-05
2023-01-24 07:32:08.967149: step: 724/529, loss: 0.0061670932918787
2023-01-24 07:32:10.018548: step: 728/529, loss: 0.005565732251852751
2023-01-24 07:32:11.074833: step: 732/529, loss: 0.0010282763978466392
2023-01-24 07:32:12.110486: step: 736/529, loss: 0.0016645464347675443
2023-01-24 07:32:13.171796: step: 740/529, loss: 0.0024394686333835125
2023-01-24 07:32:14.218692: step: 744/529, loss: 0.001042565330862999
2023-01-24 07:32:15.265717: step: 748/529, loss: 0.005726627539843321
2023-01-24 07:32:16.314599: step: 752/529, loss: 0.0016147037968039513
2023-01-24 07:32:17.352461: step: 756/529, loss: 0.0038548894226551056
2023-01-24 07:32:18.394819: step: 760/529, loss: 0.002423239406198263
2023-01-24 07:32:19.459565: step: 764/529, loss: 0.00017455000488553196
2023-01-24 07:32:20.511970: step: 768/529, loss: 0.017610331997275352
2023-01-24 07:32:21.552874: step: 772/529, loss: 0.0
2023-01-24 07:32:22.588266: step: 776/529, loss: 4.326991620473564e-05
2023-01-24 07:32:23.635382: step: 780/529, loss: 0.0027888838667422533
2023-01-24 07:32:24.687120: step: 784/529, loss: 0.022689491510391235
2023-01-24 07:32:25.729523: step: 788/529, loss: 0.0008440619567409158
2023-01-24 07:32:26.808045: step: 792/529, loss: 0.0021070868242532015
2023-01-24 07:32:27.853095: step: 796/529, loss: 0.0049596624448895454
2023-01-24 07:32:28.901130: step: 800/529, loss: 0.0001836716110119596
2023-01-24 07:32:29.956483: step: 804/529, loss: 0.006417789030820131
2023-01-24 07:32:31.011051: step: 808/529, loss: 0.0004340535379014909
2023-01-24 07:32:32.080126: step: 812/529, loss: 0.009803470224142075
2023-01-24 07:32:33.140035: step: 816/529, loss: 0.005087788216769695
2023-01-24 07:32:34.193157: step: 820/529, loss: 0.0021837654057890177
2023-01-24 07:32:35.254160: step: 824/529, loss: 0.015038087964057922
2023-01-24 07:32:36.300803: step: 828/529, loss: 0.008199043571949005
2023-01-24 07:32:37.331689: step: 832/529, loss: 0.00026388303376734257
2023-01-24 07:32:38.372276: step: 836/529, loss: 0.00013836135622113943
2023-01-24 07:32:39.424045: step: 840/529, loss: 0.00014398775238078088
2023-01-24 07:32:40.490384: step: 844/529, loss: 0.007086677476763725
2023-01-24 07:32:41.528345: step: 848/529, loss: 0.000679773569572717
2023-01-24 07:32:42.563769: step: 852/529, loss: 0.0003471091913525015
2023-01-24 07:32:43.613395: step: 856/529, loss: 0.00017987570026889443
2023-01-24 07:32:44.658022: step: 860/529, loss: 0.0060335020534694195
2023-01-24 07:32:45.717945: step: 864/529, loss: 0.0013328570639714599
2023-01-24 07:32:46.768153: step: 868/529, loss: 0.008790730498731136
2023-01-24 07:32:47.813512: step: 872/529, loss: 0.049121756106615067
2023-01-24 07:32:48.866584: step: 876/529, loss: 0.000212679457035847
2023-01-24 07:32:49.919407: step: 880/529, loss: 0.0013097607297822833
2023-01-24 07:32:50.967120: step: 884/529, loss: 0.0009541487670503557
2023-01-24 07:32:52.013206: step: 888/529, loss: 0.005695894360542297
2023-01-24 07:32:53.055341: step: 892/529, loss: 0.036895278841257095
2023-01-24 07:32:54.097606: step: 896/529, loss: 0.004692884627729654
2023-01-24 07:32:55.141976: step: 900/529, loss: 0.0002595408004708588
2023-01-24 07:32:56.172685: step: 904/529, loss: 0.0007599055534228683
2023-01-24 07:32:57.203851: step: 908/529, loss: 0.0011384158860892057
2023-01-24 07:32:58.253961: step: 912/529, loss: 0.0008297098102048039
2023-01-24 07:32:59.300391: step: 916/529, loss: 0.00234603532589972
2023-01-24 07:33:00.344250: step: 920/529, loss: 0.0019602435640990734
2023-01-24 07:33:01.405148: step: 924/529, loss: 0.00711282342672348
2023-01-24 07:33:02.448989: step: 928/529, loss: 0.005014392081648111
2023-01-24 07:33:03.488733: step: 932/529, loss: 0.001218703924678266
2023-01-24 07:33:04.549760: step: 936/529, loss: 0.005473948549479246
2023-01-24 07:33:05.594956: step: 940/529, loss: 0.001442932989448309
2023-01-24 07:33:06.631213: step: 944/529, loss: 0.002020786516368389
2023-01-24 07:33:07.668126: step: 948/529, loss: 0.004130592104047537
2023-01-24 07:33:08.701808: step: 952/529, loss: 0.0004926081164740026
2023-01-24 07:33:09.750325: step: 956/529, loss: 0.006414211355149746
2023-01-24 07:33:10.794214: step: 960/529, loss: 0.0008974411757662892
2023-01-24 07:33:11.834244: step: 964/529, loss: 0.0013735558604821563
2023-01-24 07:33:12.891789: step: 968/529, loss: 0.0026449968572705984
2023-01-24 07:33:13.926321: step: 972/529, loss: 0.016979465261101723
2023-01-24 07:33:14.964975: step: 976/529, loss: 0.006331773474812508
2023-01-24 07:33:16.023493: step: 980/529, loss: 0.0014255353016778827
2023-01-24 07:33:17.063225: step: 984/529, loss: 0.001388548407703638
2023-01-24 07:33:18.120119: step: 988/529, loss: 0.005819765385240316
2023-01-24 07:33:19.149758: step: 992/529, loss: 0.002782560186460614
2023-01-24 07:33:20.216710: step: 996/529, loss: 0.0005248901434242725
2023-01-24 07:33:21.270762: step: 1000/529, loss: 0.005262112710624933
2023-01-24 07:33:22.311975: step: 1004/529, loss: 0.0017985641025006771
2023-01-24 07:33:23.355470: step: 1008/529, loss: 0.0009738872176967561
2023-01-24 07:33:24.396651: step: 1012/529, loss: 0.004128714092075825
2023-01-24 07:33:25.447558: step: 1016/529, loss: 0.009687910787761211
2023-01-24 07:33:26.501550: step: 1020/529, loss: 0.0061416723765432835
2023-01-24 07:33:27.559996: step: 1024/529, loss: 0.0007446203380823135
2023-01-24 07:33:28.605250: step: 1028/529, loss: 0.00688126077875495
2023-01-24 07:33:29.668164: step: 1032/529, loss: 0.002748201135545969
2023-01-24 07:33:30.723158: step: 1036/529, loss: 0.009075099602341652
2023-01-24 07:33:31.780049: step: 1040/529, loss: 0.009910820052027702
2023-01-24 07:33:32.824681: step: 1044/529, loss: 0.016206787899136543
2023-01-24 07:33:33.853937: step: 1048/529, loss: 0.00026731740217655897
2023-01-24 07:33:34.895428: step: 1052/529, loss: 0.023184679448604584
2023-01-24 07:33:35.946985: step: 1056/529, loss: 0.0005515580996870995
2023-01-24 07:33:36.989745: step: 1060/529, loss: 0.006231253035366535
2023-01-24 07:33:38.035685: step: 1064/529, loss: 0.004519576672464609
2023-01-24 07:33:39.076134: step: 1068/529, loss: 0.006572348531335592
2023-01-24 07:33:40.141878: step: 1072/529, loss: 0.0019725102465599775
2023-01-24 07:33:41.198704: step: 1076/529, loss: 0.01795819029211998
2023-01-24 07:33:42.246902: step: 1080/529, loss: 0.0052817221730947495
2023-01-24 07:33:43.290078: step: 1084/529, loss: 0.004028265364468098
2023-01-24 07:33:44.326862: step: 1088/529, loss: 0.0028873439878225327
2023-01-24 07:33:45.364388: step: 1092/529, loss: 0.00017623452004045248
2023-01-24 07:33:46.442056: step: 1096/529, loss: 0.00811166875064373
2023-01-24 07:33:47.500502: step: 1100/529, loss: 0.0035460330545902252
2023-01-24 07:33:48.547723: step: 1104/529, loss: 0.0014432879397645593
2023-01-24 07:33:49.590028: step: 1108/529, loss: 9.490230877418071e-05
2023-01-24 07:33:50.645416: step: 1112/529, loss: 6.598322215722874e-06
2023-01-24 07:33:51.701887: step: 1116/529, loss: 0.003287338884547353
2023-01-24 07:33:52.746929: step: 1120/529, loss: 0.0043175108730793
2023-01-24 07:33:53.781161: step: 1124/529, loss: 0.0068112327717244625
2023-01-24 07:33:54.836513: step: 1128/529, loss: 0.002569206990301609
2023-01-24 07:33:55.887319: step: 1132/529, loss: 0.003962248098105192
2023-01-24 07:33:56.936680: step: 1136/529, loss: 3.942374314647168e-05
2023-01-24 07:33:57.981067: step: 1140/529, loss: 0.0015602442435920238
2023-01-24 07:33:59.019349: step: 1144/529, loss: 0.003851967863738537
2023-01-24 07:34:00.068432: step: 1148/529, loss: 0.005517622455954552
2023-01-24 07:34:01.113322: step: 1152/529, loss: 0.0045139179565012455
2023-01-24 07:34:02.170871: step: 1156/529, loss: 0.00961222406476736
2023-01-24 07:34:03.220481: step: 1160/529, loss: 0.00814170204102993
2023-01-24 07:34:04.252070: step: 1164/529, loss: 0.000687994179315865
2023-01-24 07:34:05.296955: step: 1168/529, loss: 0.0016381940804421902
2023-01-24 07:34:06.342803: step: 1172/529, loss: 0.0023828938137739897
2023-01-24 07:34:07.384143: step: 1176/529, loss: 0.00030106629128567874
2023-01-24 07:34:08.442449: step: 1180/529, loss: 0.0014321234775707126
2023-01-24 07:34:09.489118: step: 1184/529, loss: 0.006543700583279133
2023-01-24 07:34:10.530013: step: 1188/529, loss: 0.002816717606037855
2023-01-24 07:34:11.585703: step: 1192/529, loss: 0.0027113796677440405
2023-01-24 07:34:12.634853: step: 1196/529, loss: 0.0018475671531632543
2023-01-24 07:34:13.672377: step: 1200/529, loss: 0.00477629667147994
2023-01-24 07:34:14.730596: step: 1204/529, loss: 0.008887148462235928
2023-01-24 07:34:15.775008: step: 1208/529, loss: 0.007356569170951843
2023-01-24 07:34:16.835008: step: 1212/529, loss: 0.0033601808827370405
2023-01-24 07:34:17.896982: step: 1216/529, loss: 0.0026360158808529377
2023-01-24 07:34:18.953814: step: 1220/529, loss: 0.002555998507887125
2023-01-24 07:34:20.022735: step: 1224/529, loss: 0.00549728749319911
2023-01-24 07:34:21.087514: step: 1228/529, loss: 0.013226628303527832
2023-01-24 07:34:22.137470: step: 1232/529, loss: 0.0025701280683279037
2023-01-24 07:34:23.182852: step: 1236/529, loss: 0.006285619456321001
2023-01-24 07:34:24.237354: step: 1240/529, loss: 0.001428676419891417
2023-01-24 07:34:25.279020: step: 1244/529, loss: 0.004736202768981457
2023-01-24 07:34:26.333743: step: 1248/529, loss: 0.019103853031992912
2023-01-24 07:34:27.389977: step: 1252/529, loss: 0.0007028862019069493
2023-01-24 07:34:28.441852: step: 1256/529, loss: 0.001356936409138143
2023-01-24 07:34:29.488940: step: 1260/529, loss: 0.003363113384693861
2023-01-24 07:34:30.535783: step: 1264/529, loss: 0.006181258242577314
2023-01-24 07:34:31.592193: step: 1268/529, loss: 0.004516343120485544
2023-01-24 07:34:32.649323: step: 1272/529, loss: 0.002820379566401243
2023-01-24 07:34:33.689304: step: 1276/529, loss: 0.00543256476521492
2023-01-24 07:34:34.739362: step: 1280/529, loss: 0.0019710632041096687
2023-01-24 07:34:35.783672: step: 1284/529, loss: 0.0027457019314169884
2023-01-24 07:34:36.814154: step: 1288/529, loss: 0.001080790301784873
2023-01-24 07:34:37.847263: step: 1292/529, loss: 0.007547048386186361
2023-01-24 07:34:38.895200: step: 1296/529, loss: 0.02213042415678501
2023-01-24 07:34:39.913166: step: 1300/529, loss: 3.618982373154722e-05
2023-01-24 07:34:40.970217: step: 1304/529, loss: 0.008058971725404263
2023-01-24 07:34:42.029902: step: 1308/529, loss: 0.005725135561078787
2023-01-24 07:34:43.082682: step: 1312/529, loss: 0.003886567195877433
2023-01-24 07:34:44.125798: step: 1316/529, loss: 0.006567446980625391
2023-01-24 07:34:45.181533: step: 1320/529, loss: 0.007206076756119728
2023-01-24 07:34:46.237913: step: 1324/529, loss: 0.009695267304778099
2023-01-24 07:34:47.274329: step: 1328/529, loss: 0.005573967006057501
2023-01-24 07:34:48.319934: step: 1332/529, loss: 0.003601539647206664
2023-01-24 07:34:49.357972: step: 1336/529, loss: 0.005629237741231918
2023-01-24 07:34:50.412812: step: 1340/529, loss: 0.008871670812368393
2023-01-24 07:34:51.446042: step: 1344/529, loss: 0.0026468003634363413
2023-01-24 07:34:52.484271: step: 1348/529, loss: 0.005154135636985302
2023-01-24 07:34:53.545351: step: 1352/529, loss: 0.002335173077881336
2023-01-24 07:34:54.575415: step: 1356/529, loss: 0.008903377689421177
2023-01-24 07:34:55.619069: step: 1360/529, loss: 0.00041577909723855555
2023-01-24 07:34:56.655865: step: 1364/529, loss: 0.0027857183013111353
2023-01-24 07:34:57.695466: step: 1368/529, loss: 0.005076603032648563
2023-01-24 07:34:58.745185: step: 1372/529, loss: 0.0035085254348814487
2023-01-24 07:34:59.783781: step: 1376/529, loss: 0.006606556009501219
2023-01-24 07:35:00.836397: step: 1380/529, loss: 6.7213268266641535e-06
2023-01-24 07:35:01.904086: step: 1384/529, loss: 0.0004115298215765506
2023-01-24 07:35:02.948319: step: 1388/529, loss: 0.007112570106983185
2023-01-24 07:35:03.994129: step: 1392/529, loss: 0.002831387799233198
2023-01-24 07:35:05.030410: step: 1396/529, loss: 0.000764812168199569
2023-01-24 07:35:06.072206: step: 1400/529, loss: 0.0021896029356867075
2023-01-24 07:35:07.116633: step: 1404/529, loss: 0.002743021585047245
2023-01-24 07:35:08.168302: step: 1408/529, loss: 8.683648775331676e-05
2023-01-24 07:35:09.207669: step: 1412/529, loss: 0.00040909796371124685
2023-01-24 07:35:10.261527: step: 1416/529, loss: 0.006013940554112196
2023-01-24 07:35:11.304243: step: 1420/529, loss: 0.0031260058749467134
2023-01-24 07:35:12.342980: step: 1424/529, loss: 0.0031865935306996107
2023-01-24 07:35:13.409036: step: 1428/529, loss: 0.002149343490600586
2023-01-24 07:35:14.460404: step: 1432/529, loss: 0.001372204627841711
2023-01-24 07:35:15.481525: step: 1436/529, loss: 0.02134183794260025
2023-01-24 07:35:16.537413: step: 1440/529, loss: 0.01621353067457676
2023-01-24 07:35:17.569995: step: 1444/529, loss: 0.0009152347920462489
2023-01-24 07:35:18.613106: step: 1448/529, loss: 0.004257665015757084
2023-01-24 07:35:19.703333: step: 1452/529, loss: 0.007955099456012249
2023-01-24 07:35:20.753416: step: 1456/529, loss: 0.001764209708198905
2023-01-24 07:35:21.826853: step: 1460/529, loss: 0.022892527282238007
2023-01-24 07:35:22.880423: step: 1464/529, loss: 0.009340415708720684
2023-01-24 07:35:23.929746: step: 1468/529, loss: 0.0027028219774365425
2023-01-24 07:35:24.983112: step: 1472/529, loss: 0.0027752385940402746
2023-01-24 07:35:26.009057: step: 1476/529, loss: 0.00025280597037635744
2023-01-24 07:35:27.055951: step: 1480/529, loss: 0.0013899061596021056
2023-01-24 07:35:28.111477: step: 1484/529, loss: 0.002894199453294277
2023-01-24 07:35:29.152941: step: 1488/529, loss: 3.107917291345075e-05
2023-01-24 07:35:30.207216: step: 1492/529, loss: 0.004997130483388901
2023-01-24 07:35:31.257923: step: 1496/529, loss: 0.004742403980344534
2023-01-24 07:35:32.313143: step: 1500/529, loss: 0.002078400691971183
2023-01-24 07:35:33.362300: step: 1504/529, loss: 0.015194614417850971
2023-01-24 07:35:34.428293: step: 1508/529, loss: 0.0025632097385823727
2023-01-24 07:35:35.481082: step: 1512/529, loss: 0.0006677258061245084
2023-01-24 07:35:36.535720: step: 1516/529, loss: 0.004418171476572752
2023-01-24 07:35:37.569184: step: 1520/529, loss: 0.004550809971988201
2023-01-24 07:35:38.613572: step: 1524/529, loss: 9.262320236302912e-05
2023-01-24 07:35:39.653818: step: 1528/529, loss: 0.004586302675306797
2023-01-24 07:35:40.699517: step: 1532/529, loss: 0.02046208828687668
2023-01-24 07:35:41.739592: step: 1536/529, loss: 0.0026131935883313417
2023-01-24 07:35:42.784914: step: 1540/529, loss: 0.0024927135091274977
2023-01-24 07:35:43.818858: step: 1544/529, loss: 0.0028580259531736374
2023-01-24 07:35:44.862949: step: 1548/529, loss: 0.009128554724156857
2023-01-24 07:35:45.913162: step: 1552/529, loss: 0.002217313041910529
2023-01-24 07:35:46.961219: step: 1556/529, loss: 0.006017806939780712
2023-01-24 07:35:48.009442: step: 1560/529, loss: 0.006406652275472879
2023-01-24 07:35:49.051784: step: 1564/529, loss: 0.0005443730624392629
2023-01-24 07:35:50.085045: step: 1568/529, loss: 5.7744142395677045e-05
2023-01-24 07:35:51.136516: step: 1572/529, loss: 0.011759455315768719
2023-01-24 07:35:52.173228: step: 1576/529, loss: 0.0014660715823993087
2023-01-24 07:35:53.221741: step: 1580/529, loss: 0.005744372494518757
2023-01-24 07:35:54.266079: step: 1584/529, loss: 0.001768304966390133
2023-01-24 07:35:55.310466: step: 1588/529, loss: 0.0025157839991152287
2023-01-24 07:35:56.356401: step: 1592/529, loss: 0.0037688319571316242
2023-01-24 07:35:57.399001: step: 1596/529, loss: 0.0014135395176708698
2023-01-24 07:35:58.443750: step: 1600/529, loss: 0.0036624078638851643
2023-01-24 07:35:59.485175: step: 1604/529, loss: 0.0006104863132350147
2023-01-24 07:36:00.542409: step: 1608/529, loss: 4.5989978389116004e-05
2023-01-24 07:36:01.594513: step: 1612/529, loss: 0.0017223499016836286
2023-01-24 07:36:02.643028: step: 1616/529, loss: 0.007549617905169725
2023-01-24 07:36:03.680759: step: 1620/529, loss: 0.004971557296812534
2023-01-24 07:36:04.740330: step: 1624/529, loss: 0.012937960214912891
2023-01-24 07:36:05.774233: step: 1628/529, loss: 0.0021600075997412205
2023-01-24 07:36:06.799563: step: 1632/529, loss: 0.007813052274286747
2023-01-24 07:36:07.841030: step: 1636/529, loss: 0.01909341663122177
2023-01-24 07:36:08.878867: step: 1640/529, loss: 0.0017056944780051708
2023-01-24 07:36:09.918294: step: 1644/529, loss: 0.005108917597681284
2023-01-24 07:36:10.964653: step: 1648/529, loss: 0.0015330326277762651
2023-01-24 07:36:12.012695: step: 1652/529, loss: 0.005255911964923143
2023-01-24 07:36:13.056815: step: 1656/529, loss: 0.0001902960066217929
2023-01-24 07:36:14.095578: step: 1660/529, loss: 0.001039320370182395
2023-01-24 07:36:15.166428: step: 1664/529, loss: 0.004947258625179529
2023-01-24 07:36:16.212863: step: 1668/529, loss: 0.009913178160786629
2023-01-24 07:36:17.255706: step: 1672/529, loss: 0.0032350632827728987
2023-01-24 07:36:18.303080: step: 1676/529, loss: 0.0020946054719388485
2023-01-24 07:36:19.365468: step: 1680/529, loss: 0.010111463256180286
2023-01-24 07:36:20.400952: step: 1684/529, loss: 0.006983467377722263
2023-01-24 07:36:21.438968: step: 1688/529, loss: 0.009233947843313217
2023-01-24 07:36:22.479025: step: 1692/529, loss: 0.0008421643287874758
2023-01-24 07:36:23.532412: step: 1696/529, loss: 0.011338598094880581
2023-01-24 07:36:24.575214: step: 1700/529, loss: 0.008865226060152054
2023-01-24 07:36:25.620950: step: 1704/529, loss: 0.05970841646194458
2023-01-24 07:36:26.681172: step: 1708/529, loss: 0.0056977653875947
2023-01-24 07:36:27.752523: step: 1712/529, loss: 0.003153856610879302
2023-01-24 07:36:28.817295: step: 1716/529, loss: 0.0013077165931463242
2023-01-24 07:36:29.886499: step: 1720/529, loss: 0.004332357551902533
2023-01-24 07:36:30.937351: step: 1724/529, loss: 0.0056518083438277245
2023-01-24 07:36:31.988725: step: 1728/529, loss: 0.0014051418984308839
2023-01-24 07:36:33.052905: step: 1732/529, loss: 0.012752902694046497
2023-01-24 07:36:34.092546: step: 1736/529, loss: 0.001972480211406946
2023-01-24 07:36:35.130512: step: 1740/529, loss: 0.0025719499681144953
2023-01-24 07:36:36.178038: step: 1744/529, loss: 0.006823750212788582
2023-01-24 07:36:37.215785: step: 1748/529, loss: 0.005476097110658884
2023-01-24 07:36:38.274801: step: 1752/529, loss: 0.011366089805960655
2023-01-24 07:36:39.313753: step: 1756/529, loss: 0.00028451211983338
2023-01-24 07:36:40.367261: step: 1760/529, loss: 0.0023403684608638287
2023-01-24 07:36:41.409525: step: 1764/529, loss: 0.0043478477746248245
2023-01-24 07:36:42.457926: step: 1768/529, loss: 0.0056175971403717995
2023-01-24 07:36:43.506622: step: 1772/529, loss: 0.010001528076827526
2023-01-24 07:36:44.540325: step: 1776/529, loss: 0.011165730655193329
2023-01-24 07:36:45.581414: step: 1780/529, loss: 0.0014509441098198295
2023-01-24 07:36:46.626138: step: 1784/529, loss: 0.0008313686703331769
2023-01-24 07:36:47.676180: step: 1788/529, loss: 0.003808972192928195
2023-01-24 07:36:48.722470: step: 1792/529, loss: 0.0002662185288500041
2023-01-24 07:36:49.783141: step: 1796/529, loss: 0.008610406890511513
2023-01-24 07:36:50.826837: step: 1800/529, loss: 0.0011986854951828718
2023-01-24 07:36:51.869744: step: 1804/529, loss: 0.004532924387603998
2023-01-24 07:36:52.930794: step: 1808/529, loss: 0.0023454048205167055
2023-01-24 07:36:53.985981: step: 1812/529, loss: 0.00456051854416728
2023-01-24 07:36:55.035262: step: 1816/529, loss: 0.0001380283065373078
2023-01-24 07:36:56.068439: step: 1820/529, loss: 0.0028413415420800447
2023-01-24 07:36:57.116545: step: 1824/529, loss: 0.0010695684468373656
2023-01-24 07:36:58.170161: step: 1828/529, loss: 0.00026654437533579767
2023-01-24 07:36:59.219746: step: 1832/529, loss: 0.0013222841080278158
2023-01-24 07:37:00.256168: step: 1836/529, loss: 0.0005296416929922998
2023-01-24 07:37:01.296555: step: 1840/529, loss: 0.005853899754583836
2023-01-24 07:37:02.341521: step: 1844/529, loss: 0.0041617522947490215
2023-01-24 07:37:03.406193: step: 1848/529, loss: 0.0015156196895986795
2023-01-24 07:37:04.441078: step: 1852/529, loss: 0.0035164745058864355
2023-01-24 07:37:05.478578: step: 1856/529, loss: 0.00017092064081225544
2023-01-24 07:37:06.533429: step: 1860/529, loss: 0.00426424341276288
2023-01-24 07:37:07.588948: step: 1864/529, loss: 0.003121687099337578
2023-01-24 07:37:08.640047: step: 1868/529, loss: 0.00400412455201149
2023-01-24 07:37:09.684145: step: 1872/529, loss: 0.0123432707041502
2023-01-24 07:37:10.745870: step: 1876/529, loss: 0.0005002549150958657
2023-01-24 07:37:11.791248: step: 1880/529, loss: 0.001664901152253151
2023-01-24 07:37:12.852447: step: 1884/529, loss: 0.008837983012199402
2023-01-24 07:37:13.916801: step: 1888/529, loss: 0.00404225243255496
2023-01-24 07:37:14.967492: step: 1892/529, loss: 0.01162963267415762
2023-01-24 07:37:15.998341: step: 1896/529, loss: 0.003960322123020887
2023-01-24 07:37:17.043095: step: 1900/529, loss: 8.359771527466364e-06
2023-01-24 07:37:18.082223: step: 1904/529, loss: 0.0008350919233635068
2023-01-24 07:37:19.133235: step: 1908/529, loss: 0.007631985936313868
2023-01-24 07:37:20.206472: step: 1912/529, loss: 0.0056535713374614716
2023-01-24 07:37:21.270604: step: 1916/529, loss: 0.0006918919389136136
2023-01-24 07:37:22.313244: step: 1920/529, loss: 0.0027876945678144693
2023-01-24 07:37:23.349468: step: 1924/529, loss: 0.0018325918354094028
2023-01-24 07:37:24.407789: step: 1928/529, loss: 0.0023743915371596813
2023-01-24 07:37:25.444046: step: 1932/529, loss: 0.0025626919232308865
2023-01-24 07:37:26.489022: step: 1936/529, loss: 0.012492476031184196
2023-01-24 07:37:27.540055: step: 1940/529, loss: 0.004952891264110804
2023-01-24 07:37:28.588269: step: 1944/529, loss: 0.0029234527610242367
2023-01-24 07:37:29.626971: step: 1948/529, loss: 0.0027377381920814514
2023-01-24 07:37:30.681715: step: 1952/529, loss: 0.0008895958890207112
2023-01-24 07:37:31.716437: step: 1956/529, loss: 0.0013366240309551358
2023-01-24 07:37:32.756455: step: 1960/529, loss: 0.0002729465486481786
2023-01-24 07:37:33.800363: step: 1964/529, loss: 0.0007911220891401172
2023-01-24 07:37:34.852864: step: 1968/529, loss: 0.0022898789029568434
2023-01-24 07:37:35.905870: step: 1972/529, loss: 0.0005048089078627527
2023-01-24 07:37:36.972364: step: 1976/529, loss: 0.0016113612800836563
2023-01-24 07:37:38.017144: step: 1980/529, loss: 0.002150622196495533
2023-01-24 07:37:39.057059: step: 1984/529, loss: 0.00198745122179389
2023-01-24 07:37:40.111941: step: 1988/529, loss: 0.0005819597281515598
2023-01-24 07:37:41.159840: step: 1992/529, loss: 0.015266776084899902
2023-01-24 07:37:42.204000: step: 1996/529, loss: 0.010057618841528893
2023-01-24 07:37:43.262559: step: 2000/529, loss: 0.0023630731739103794
2023-01-24 07:37:44.317268: step: 2004/529, loss: 0.0004862755013164133
2023-01-24 07:37:45.377989: step: 2008/529, loss: 0.005735492333769798
2023-01-24 07:37:46.429997: step: 2012/529, loss: 0.0018624253571033478
2023-01-24 07:37:47.478257: step: 2016/529, loss: 0.005650147795677185
2023-01-24 07:37:48.531815: step: 2020/529, loss: 3.1878375011729077e-05
2023-01-24 07:37:49.560028: step: 2024/529, loss: 0.0011836141347885132
2023-01-24 07:37:50.605607: step: 2028/529, loss: 0.008907408453524113
2023-01-24 07:37:51.670716: step: 2032/529, loss: 0.0010813509579747915
2023-01-24 07:37:52.750140: step: 2036/529, loss: 0.022435814142227173
2023-01-24 07:37:53.806538: step: 2040/529, loss: 0.006156958173960447
2023-01-24 07:37:54.852359: step: 2044/529, loss: 0.004454421810805798
2023-01-24 07:37:55.907777: step: 2048/529, loss: 0.007299572229385376
2023-01-24 07:37:56.954327: step: 2052/529, loss: 0.00802726112306118
2023-01-24 07:37:57.999364: step: 2056/529, loss: 0.0005126087926328182
2023-01-24 07:37:59.039520: step: 2060/529, loss: 0.0022101940121501684
2023-01-24 07:38:00.094309: step: 2064/529, loss: 0.023532552644610405
2023-01-24 07:38:01.152744: step: 2068/529, loss: 0.01658235676586628
2023-01-24 07:38:02.208060: step: 2072/529, loss: 0.010429018177092075
2023-01-24 07:38:03.286046: step: 2076/529, loss: 0.0028988479170948267
2023-01-24 07:38:04.341293: step: 2080/529, loss: 0.005375751294195652
2023-01-24 07:38:05.412714: step: 2084/529, loss: 0.0018056014087051153
2023-01-24 07:38:06.463708: step: 2088/529, loss: 0.0120967086404562
2023-01-24 07:38:07.500147: step: 2092/529, loss: 0.003507033921778202
2023-01-24 07:38:08.544765: step: 2096/529, loss: 0.0016474586445838213
2023-01-24 07:38:09.581480: step: 2100/529, loss: 0.0030624258797615767
2023-01-24 07:38:10.638487: step: 2104/529, loss: 0.009287316352128983
2023-01-24 07:38:11.676668: step: 2108/529, loss: 0.0013327146880328655
2023-01-24 07:38:12.710862: step: 2112/529, loss: 0.00021456743706949055
2023-01-24 07:38:13.768630: step: 2116/529, loss: 0.02893240936100483
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32310953711093376, 'r': 0.32924064787205204, 'f1': 0.32614628088077335}, 'combined': 0.24031831222793826, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.36744312510869714, 'r': 0.2975455672782469, 'f1': 0.32882084869900763}, 'combined': 0.2313312503410104, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3556566455696203, 'r': 0.31988851992409867, 'f1': 0.33682567432567434}, 'combined': 0.24818733897681267, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3916950718910837, 'r': 0.31991848803669665, 'f1': 0.35218692342944696}, 'combined': 0.25005271563490733, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3778326154365554, 'r': 0.34270206865023434, 'f1': 0.35941092572870353}, 'combined': 0.2648291031685184, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39685106576090373, 'r': 0.3112421458980712, 'f1': 0.3488715193864822}, 'combined': 0.24769877876440236, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 13
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:40:43.359816: step: 4/529, loss: 0.0020661125890910625
2023-01-24 07:40:44.395418: step: 8/529, loss: 0.004797362256795168
2023-01-24 07:40:45.442962: step: 12/529, loss: 0.0030104818288236856
2023-01-24 07:40:46.468032: step: 16/529, loss: 0.005209543276578188
2023-01-24 07:40:47.502108: step: 20/529, loss: 0.003855886636301875
2023-01-24 07:40:48.549333: step: 24/529, loss: 0.008314124308526516
2023-01-24 07:40:49.573735: step: 28/529, loss: 0.0010546843986958265
2023-01-24 07:40:50.614941: step: 32/529, loss: 0.002141502918675542
2023-01-24 07:40:51.651171: step: 36/529, loss: 0.0009814116638153791
2023-01-24 07:40:52.701945: step: 40/529, loss: 0.003405241295695305
2023-01-24 07:40:53.745329: step: 44/529, loss: 0.00189563340973109
2023-01-24 07:40:54.794589: step: 48/529, loss: 0.0020448495633900166
2023-01-24 07:40:55.828292: step: 52/529, loss: 0.002719337586313486
2023-01-24 07:40:56.871954: step: 56/529, loss: 0.03908460587263107
2023-01-24 07:40:57.903649: step: 60/529, loss: 0.0020464614499360323
2023-01-24 07:40:58.969258: step: 64/529, loss: 0.0036927012261003256
2023-01-24 07:41:00.005912: step: 68/529, loss: 0.0058067562058568
2023-01-24 07:41:01.039247: step: 72/529, loss: 0.024410398676991463
2023-01-24 07:41:02.075056: step: 76/529, loss: 0.0010673971846699715
2023-01-24 07:41:03.129811: step: 80/529, loss: 0.0007646349840797484
2023-01-24 07:41:04.163315: step: 84/529, loss: 0.00024966764613054693
2023-01-24 07:41:05.213846: step: 88/529, loss: 0.005194772034883499
2023-01-24 07:41:06.258794: step: 92/529, loss: 0.000579176819883287
2023-01-24 07:41:07.316235: step: 96/529, loss: 0.004788865800946951
2023-01-24 07:41:08.357503: step: 100/529, loss: 0.006167104467749596
2023-01-24 07:41:09.398472: step: 104/529, loss: 0.008440110832452774
2023-01-24 07:41:10.450640: step: 108/529, loss: 0.00958058051764965
2023-01-24 07:41:11.517243: step: 112/529, loss: 0.00473578367382288
2023-01-24 07:41:12.553147: step: 116/529, loss: 0.0003848426276817918
2023-01-24 07:41:13.568811: step: 120/529, loss: 0.013177048414945602
2023-01-24 07:41:14.617259: step: 124/529, loss: 0.029592398554086685
2023-01-24 07:41:15.658451: step: 128/529, loss: 0.00013439639587886631
2023-01-24 07:41:16.688143: step: 132/529, loss: 0.0008256007567979395
2023-01-24 07:41:17.754431: step: 136/529, loss: 0.0034323392901569605
2023-01-24 07:41:18.791579: step: 140/529, loss: 0.001702593988738954
2023-01-24 07:41:19.826648: step: 144/529, loss: 2.79263872471347e-06
2023-01-24 07:41:20.871344: step: 148/529, loss: 0.010335664264857769
2023-01-24 07:41:21.921213: step: 152/529, loss: 0.004042556043714285
2023-01-24 07:41:22.950193: step: 156/529, loss: 0.003973588813096285
2023-01-24 07:41:23.989459: step: 160/529, loss: 0.00038929111906327307
2023-01-24 07:41:25.035382: step: 164/529, loss: 0.003283280413597822
2023-01-24 07:41:26.078887: step: 168/529, loss: 0.019665243104100227
2023-01-24 07:41:27.123493: step: 172/529, loss: 0.0005752895958721638
2023-01-24 07:41:28.188794: step: 176/529, loss: 0.003360697301104665
2023-01-24 07:41:29.242687: step: 180/529, loss: 0.0008212961256504059
2023-01-24 07:41:30.287232: step: 184/529, loss: 0.0006881274748593569
2023-01-24 07:41:31.336413: step: 188/529, loss: 0.007221120875328779
2023-01-24 07:41:32.383465: step: 192/529, loss: 0.006299884989857674
2023-01-24 07:41:33.431048: step: 196/529, loss: 0.00047569183516316116
2023-01-24 07:41:34.469926: step: 200/529, loss: 0.009679806418716908
2023-01-24 07:41:35.536523: step: 204/529, loss: 0.001241132733412087
2023-01-24 07:41:36.617416: step: 208/529, loss: 0.0017919227248057723
2023-01-24 07:41:37.665876: step: 212/529, loss: 0.0006977166049182415
2023-01-24 07:41:38.701083: step: 216/529, loss: 0.0027206167578697205
2023-01-24 07:41:39.736313: step: 220/529, loss: 1.4901126554889288e-08
2023-01-24 07:41:40.794061: step: 224/529, loss: 0.004480557981878519
2023-01-24 07:41:41.830437: step: 228/529, loss: 6.839342677267268e-05
2023-01-24 07:41:42.871847: step: 232/529, loss: 0.018638627603650093
2023-01-24 07:41:43.938024: step: 236/529, loss: 0.0004414775758050382
2023-01-24 07:41:44.988226: step: 240/529, loss: 0.005069043952971697
2023-01-24 07:41:46.034837: step: 244/529, loss: 0.0065057347528636456
2023-01-24 07:41:47.080791: step: 248/529, loss: 0.014601541683077812
2023-01-24 07:41:48.120380: step: 252/529, loss: 0.017725970596075058
2023-01-24 07:41:49.159601: step: 256/529, loss: 9.545955435896758e-06
2023-01-24 07:41:50.214702: step: 260/529, loss: 0.005442390218377113
2023-01-24 07:41:51.255104: step: 264/529, loss: 0.006095238495618105
2023-01-24 07:41:52.303262: step: 268/529, loss: 0.0005663083284161985
2023-01-24 07:41:53.353022: step: 272/529, loss: 0.006307459902018309
2023-01-24 07:41:54.395034: step: 276/529, loss: 0.005606014281511307
2023-01-24 07:41:55.441507: step: 280/529, loss: 0.0009300084784626961
2023-01-24 07:41:56.480298: step: 284/529, loss: 0.024398071691393852
2023-01-24 07:41:57.523758: step: 288/529, loss: 0.0015872081276029348
2023-01-24 07:41:58.572064: step: 292/529, loss: 0.0037489307578653097
2023-01-24 07:41:59.636219: step: 296/529, loss: 0.0005181817687116563
2023-01-24 07:42:00.677154: step: 300/529, loss: 0.0006078698788769543
2023-01-24 07:42:01.708246: step: 304/529, loss: 0.00024561380269005895
2023-01-24 07:42:02.753350: step: 308/529, loss: 0.006673007272183895
2023-01-24 07:42:03.811730: step: 312/529, loss: 0.029074745252728462
2023-01-24 07:42:04.855531: step: 316/529, loss: 0.001385142095386982
2023-01-24 07:42:05.913879: step: 320/529, loss: 0.004524963907897472
2023-01-24 07:42:06.958839: step: 324/529, loss: 8.751742279855534e-05
2023-01-24 07:42:08.000288: step: 328/529, loss: 9.058280738827307e-06
2023-01-24 07:42:09.036239: step: 332/529, loss: 0.003962811082601547
2023-01-24 07:42:10.079530: step: 336/529, loss: 0.008100816048681736
2023-01-24 07:42:11.107076: step: 340/529, loss: 1.4225344102669624e-06
2023-01-24 07:42:12.137709: step: 344/529, loss: 0.0009997226297855377
2023-01-24 07:42:13.179890: step: 348/529, loss: 0.0045590875670313835
2023-01-24 07:42:14.221960: step: 352/529, loss: 0.004171362612396479
2023-01-24 07:42:15.267900: step: 356/529, loss: 0.003166272072121501
2023-01-24 07:42:16.309060: step: 360/529, loss: 0.00483390549197793
2023-01-24 07:42:17.365280: step: 364/529, loss: 0.00013336514530237764
2023-01-24 07:42:18.412113: step: 368/529, loss: 0.005746159702539444
2023-01-24 07:42:19.463157: step: 372/529, loss: 0.0021320979576557875
2023-01-24 07:42:20.497692: step: 376/529, loss: 0.0010759546421468258
2023-01-24 07:42:21.539299: step: 380/529, loss: 0.004866831935942173
2023-01-24 07:42:22.595459: step: 384/529, loss: 0.00578966923058033
2023-01-24 07:42:23.637585: step: 388/529, loss: 0.00445671146735549
2023-01-24 07:42:24.689262: step: 392/529, loss: 0.0017480573151260614
2023-01-24 07:42:25.713753: step: 396/529, loss: 4.209559278933739e-08
2023-01-24 07:42:26.757992: step: 400/529, loss: 0.002795041538774967
2023-01-24 07:42:27.797201: step: 404/529, loss: 0.0003665978729259223
2023-01-24 07:42:28.849265: step: 408/529, loss: 3.003964593517594e-06
2023-01-24 07:42:29.909307: step: 412/529, loss: 0.00517407339066267
2023-01-24 07:42:30.945221: step: 416/529, loss: 0.001969423610717058
2023-01-24 07:42:31.992240: step: 420/529, loss: 0.002456636866554618
2023-01-24 07:42:33.037027: step: 424/529, loss: 0.004229211248457432
2023-01-24 07:42:34.089988: step: 428/529, loss: 0.0047072554007172585
2023-01-24 07:42:35.136610: step: 432/529, loss: 0.001991803525015712
2023-01-24 07:42:36.188520: step: 436/529, loss: 0.0005003004334867001
2023-01-24 07:42:37.219717: step: 440/529, loss: 3.7962745409458876e-06
2023-01-24 07:42:38.251857: step: 444/529, loss: 0.00012111301475670189
2023-01-24 07:42:39.296355: step: 448/529, loss: 0.0017179299611598253
2023-01-24 07:42:40.336206: step: 452/529, loss: 0.0014325024094432592
2023-01-24 07:42:41.392226: step: 456/529, loss: 0.00023156014503911138
2023-01-24 07:42:42.424968: step: 460/529, loss: 0.00570771936327219
2023-01-24 07:42:43.465919: step: 464/529, loss: 0.0027715875767171383
2023-01-24 07:42:44.515842: step: 468/529, loss: 0.0049084508791565895
2023-01-24 07:42:45.568214: step: 472/529, loss: 0.0016448169481009245
2023-01-24 07:42:46.617107: step: 476/529, loss: 0.0030526258051395416
2023-01-24 07:42:47.656093: step: 480/529, loss: 0.003808526787906885
2023-01-24 07:42:48.695345: step: 484/529, loss: 0.0011900898534804583
2023-01-24 07:42:49.739299: step: 488/529, loss: 0.015231611207127571
2023-01-24 07:42:50.774069: step: 492/529, loss: 2.99135058412503e-06
2023-01-24 07:42:51.816218: step: 496/529, loss: 0.001119957072660327
2023-01-24 07:42:52.862692: step: 500/529, loss: 0.0035611132625490427
2023-01-24 07:42:53.904493: step: 504/529, loss: 0.002170960884541273
2023-01-24 07:42:54.951899: step: 508/529, loss: 0.0002338943595532328
2023-01-24 07:42:56.014593: step: 512/529, loss: 0.007079706992954016
2023-01-24 07:42:57.060730: step: 516/529, loss: 0.001179091283120215
2023-01-24 07:42:58.120986: step: 520/529, loss: 0.0005809864378534257
2023-01-24 07:42:59.164753: step: 524/529, loss: 0.00419318163767457
2023-01-24 07:43:00.229892: step: 528/529, loss: 0.001712079276330769
2023-01-24 07:43:01.281792: step: 532/529, loss: 8.249054371844977e-05
2023-01-24 07:43:02.337637: step: 536/529, loss: 0.0008708325331099331
2023-01-24 07:43:03.375560: step: 540/529, loss: 0.00023778510512784123
2023-01-24 07:43:04.412827: step: 544/529, loss: 0.00044428210821934044
2023-01-24 07:43:05.454098: step: 548/529, loss: 0.001483298372477293
2023-01-24 07:43:06.498101: step: 552/529, loss: 0.0007793279364705086
2023-01-24 07:43:07.536146: step: 556/529, loss: 8.888561751518864e-06
2023-01-24 07:43:08.598125: step: 560/529, loss: 0.00010682106949388981
2023-01-24 07:43:09.642441: step: 564/529, loss: 0.0035573970526456833
2023-01-24 07:43:10.712656: step: 568/529, loss: 0.0010148158762603998
2023-01-24 07:43:11.771549: step: 572/529, loss: 0.003898882307112217
2023-01-24 07:43:12.811996: step: 576/529, loss: 0.002758265007287264
2023-01-24 07:43:13.865646: step: 580/529, loss: 0.0031173850875347853
2023-01-24 07:43:14.913320: step: 584/529, loss: 0.005281922873109579
2023-01-24 07:43:15.958658: step: 588/529, loss: 0.0021905687171965837
2023-01-24 07:43:17.018804: step: 592/529, loss: 0.0040220702067017555
2023-01-24 07:43:18.056564: step: 596/529, loss: 0.00012050622171955183
2023-01-24 07:43:19.097061: step: 600/529, loss: 0.005438728258013725
2023-01-24 07:43:20.139162: step: 604/529, loss: 0.0038155545480549335
2023-01-24 07:43:21.177270: step: 608/529, loss: 0.0031832456588745117
2023-01-24 07:43:22.249295: step: 612/529, loss: 0.0066933236084878445
2023-01-24 07:43:23.297695: step: 616/529, loss: 0.0057805622927844524
2023-01-24 07:43:24.352569: step: 620/529, loss: 0.0010341937886551023
2023-01-24 07:43:25.390988: step: 624/529, loss: 0.0030660927295684814
2023-01-24 07:43:26.435959: step: 628/529, loss: 0.009330186992883682
2023-01-24 07:43:27.481837: step: 632/529, loss: 0.00010489900887478143
2023-01-24 07:43:28.506996: step: 636/529, loss: 0.034650009125471115
2023-01-24 07:43:29.556800: step: 640/529, loss: 0.004256380721926689
2023-01-24 07:43:30.601628: step: 644/529, loss: 0.006344602443277836
2023-01-24 07:43:31.642645: step: 648/529, loss: 0.0023871518205851316
2023-01-24 07:43:32.686686: step: 652/529, loss: 0.001650508027523756
2023-01-24 07:43:33.736476: step: 656/529, loss: 0.0018196991877630353
2023-01-24 07:43:34.803425: step: 660/529, loss: 0.00402287021279335
2023-01-24 07:43:35.855384: step: 664/529, loss: 0.004933268763124943
2023-01-24 07:43:36.908019: step: 668/529, loss: 8.87352871359326e-05
2023-01-24 07:43:37.960076: step: 672/529, loss: 0.0035212389193475246
2023-01-24 07:43:39.002533: step: 676/529, loss: 0.0037635432090610266
2023-01-24 07:43:40.074104: step: 680/529, loss: 0.005341978743672371
2023-01-24 07:43:41.135906: step: 684/529, loss: 0.005741693079471588
2023-01-24 07:43:42.176881: step: 688/529, loss: 0.009633461944758892
2023-01-24 07:43:43.232788: step: 692/529, loss: 0.0036536778789013624
2023-01-24 07:43:44.290033: step: 696/529, loss: 0.012270782142877579
2023-01-24 07:43:45.329988: step: 700/529, loss: 0.0007505777175538242
2023-01-24 07:43:46.394028: step: 704/529, loss: 0.008541149087250233
2023-01-24 07:43:47.446123: step: 708/529, loss: 0.0002813671890180558
2023-01-24 07:43:48.480262: step: 712/529, loss: 8.576991240261123e-05
2023-01-24 07:43:49.528860: step: 716/529, loss: 0.002426203340291977
2023-01-24 07:43:50.582420: step: 720/529, loss: 0.00396518362686038
2023-01-24 07:43:51.623944: step: 724/529, loss: 0.0037479812745004892
2023-01-24 07:43:52.663850: step: 728/529, loss: 0.0020349733531475067
2023-01-24 07:43:53.712581: step: 732/529, loss: 8.447006985079497e-05
2023-01-24 07:43:54.763064: step: 736/529, loss: 0.0046722679398953915
2023-01-24 07:43:55.810976: step: 740/529, loss: 0.012401421554386616
2023-01-24 07:43:56.862156: step: 744/529, loss: 3.371183538547484e-06
2023-01-24 07:43:57.917124: step: 748/529, loss: 0.0030706883408129215
2023-01-24 07:43:58.956515: step: 752/529, loss: 0.004088858142495155
2023-01-24 07:43:59.998915: step: 756/529, loss: 0.0031179229263216257
2023-01-24 07:44:01.058501: step: 760/529, loss: 0.001078569795936346
2023-01-24 07:44:02.097131: step: 764/529, loss: 0.0008053707424551249
2023-01-24 07:44:03.157492: step: 768/529, loss: 0.006676113232970238
2023-01-24 07:44:04.216121: step: 772/529, loss: 0.00822971947491169
2023-01-24 07:44:05.260938: step: 776/529, loss: 0.013130847364664078
2023-01-24 07:44:06.320563: step: 780/529, loss: 0.004000606946647167
2023-01-24 07:44:07.375101: step: 784/529, loss: 0.0074057066813111305
2023-01-24 07:44:08.410929: step: 788/529, loss: 0.00500484649091959
2023-01-24 07:44:09.471866: step: 792/529, loss: 0.005439819302409887
2023-01-24 07:44:10.518840: step: 796/529, loss: 0.0075200339779257774
2023-01-24 07:44:11.559824: step: 800/529, loss: 0.0011484931455925107
2023-01-24 07:44:12.623489: step: 804/529, loss: 0.001748825772665441
2023-01-24 07:44:13.669559: step: 808/529, loss: 0.01814914681017399
2023-01-24 07:44:14.710324: step: 812/529, loss: 0.0004535217594821006
2023-01-24 07:44:15.761018: step: 816/529, loss: 0.0007095172768458724
2023-01-24 07:44:16.790032: step: 820/529, loss: 0.004177503287792206
2023-01-24 07:44:17.835921: step: 824/529, loss: 0.0007283009472303092
2023-01-24 07:44:18.879640: step: 828/529, loss: 0.005750639364123344
2023-01-24 07:44:19.946032: step: 832/529, loss: 0.0017952565103769302
2023-01-24 07:44:20.989334: step: 836/529, loss: 0.00019902654457837343
2023-01-24 07:44:22.023515: step: 840/529, loss: 0.0028454596176743507
2023-01-24 07:44:23.066644: step: 844/529, loss: 0.007106723263859749
2023-01-24 07:44:24.128877: step: 848/529, loss: 0.003491441486403346
2023-01-24 07:44:25.171553: step: 852/529, loss: 0.005451558157801628
2023-01-24 07:44:26.218386: step: 856/529, loss: 0.006979256868362427
2023-01-24 07:44:27.269097: step: 860/529, loss: 0.010109237395226955
2023-01-24 07:44:28.324486: step: 864/529, loss: 0.0021151432301849127
2023-01-24 07:44:29.353700: step: 868/529, loss: 0.003990199416875839
2023-01-24 07:44:30.410357: step: 872/529, loss: 0.00414115097373724
2023-01-24 07:44:31.469603: step: 876/529, loss: 0.0018837007228285074
2023-01-24 07:44:32.528781: step: 880/529, loss: 0.0015135619323700666
2023-01-24 07:44:33.592023: step: 884/529, loss: 0.0002434489142615348
2023-01-24 07:44:34.626157: step: 888/529, loss: 7.682701834710315e-05
2023-01-24 07:44:35.678622: step: 892/529, loss: 0.009019049815833569
2023-01-24 07:44:36.720955: step: 896/529, loss: 0.0029005573596805334
2023-01-24 07:44:37.769352: step: 900/529, loss: 0.002610166324302554
2023-01-24 07:44:38.826589: step: 904/529, loss: 0.0032255917321890593
2023-01-24 07:44:39.872813: step: 908/529, loss: 0.005235786084085703
2023-01-24 07:44:40.914625: step: 912/529, loss: 0.0025006921496242285
2023-01-24 07:44:41.960791: step: 916/529, loss: 0.0007335762493312359
2023-01-24 07:44:42.987496: step: 920/529, loss: 0.002886684611439705
2023-01-24 07:44:44.028293: step: 924/529, loss: 0.00046012047096155584
2023-01-24 07:44:45.087645: step: 928/529, loss: 0.0027566186618059874
2023-01-24 07:44:46.126394: step: 932/529, loss: 0.0010049877455458045
2023-01-24 07:44:47.171601: step: 936/529, loss: 0.006620476022362709
2023-01-24 07:44:48.207633: step: 940/529, loss: 0.000793657498434186
2023-01-24 07:44:49.256695: step: 944/529, loss: 0.00758998142555356
2023-01-24 07:44:50.290222: step: 948/529, loss: 0.0013402948388829827
2023-01-24 07:44:51.325374: step: 952/529, loss: 0.007372173015028238
2023-01-24 07:44:52.370832: step: 956/529, loss: 0.0013702159048989415
2023-01-24 07:44:53.413871: step: 960/529, loss: 0.000671215180773288
2023-01-24 07:44:54.488287: step: 964/529, loss: 0.00010007419768953696
2023-01-24 07:44:55.570201: step: 968/529, loss: 0.00841107964515686
2023-01-24 07:44:56.607526: step: 972/529, loss: 0.0013482884969562292
2023-01-24 07:44:57.650632: step: 976/529, loss: 0.0025155905168503523
2023-01-24 07:44:58.685642: step: 980/529, loss: 0.00037983356742188334
2023-01-24 07:44:59.725392: step: 984/529, loss: 0.001696680672466755
2023-01-24 07:45:00.770000: step: 988/529, loss: 0.005443311296403408
2023-01-24 07:45:01.812330: step: 992/529, loss: 0.0049167596735060215
2023-01-24 07:45:02.863735: step: 996/529, loss: 0.001431543962098658
2023-01-24 07:45:03.921853: step: 1000/529, loss: 0.00031198316719383
2023-01-24 07:45:04.971537: step: 1004/529, loss: 0.0003814932715613395
2023-01-24 07:45:06.027180: step: 1008/529, loss: 0.0009857534896582365
2023-01-24 07:45:07.070589: step: 1012/529, loss: 0.00374615122564137
2023-01-24 07:45:08.123494: step: 1016/529, loss: 0.0025709676556289196
2023-01-24 07:45:09.181702: step: 1020/529, loss: 0.003676342312246561
2023-01-24 07:45:10.228601: step: 1024/529, loss: 0.005495840683579445
2023-01-24 07:45:11.274473: step: 1028/529, loss: 0.0005040357937105
2023-01-24 07:45:12.336074: step: 1032/529, loss: 0.010000457987189293
2023-01-24 07:45:13.390721: step: 1036/529, loss: 0.004912738688290119
2023-01-24 07:45:14.464599: step: 1040/529, loss: 0.01084085926413536
2023-01-24 07:45:15.509377: step: 1044/529, loss: 0.0009981781477108598
2023-01-24 07:45:16.549772: step: 1048/529, loss: 8.090591290965676e-05
2023-01-24 07:45:17.610557: step: 1052/529, loss: 0.016693925485014915
2023-01-24 07:45:18.662720: step: 1056/529, loss: 0.009830198250710964
2023-01-24 07:45:19.705217: step: 1060/529, loss: 0.0007593714981339872
2023-01-24 07:45:20.761281: step: 1064/529, loss: 0.002879825420677662
2023-01-24 07:45:21.830953: step: 1068/529, loss: 0.006912213750183582
2023-01-24 07:45:22.888202: step: 1072/529, loss: 0.0023335698060691357
2023-01-24 07:45:23.930313: step: 1076/529, loss: 0.0051352763548493385
2023-01-24 07:45:24.995843: step: 1080/529, loss: 0.006917743943631649
2023-01-24 07:45:26.045773: step: 1084/529, loss: 0.005088940262794495
2023-01-24 07:45:27.101485: step: 1088/529, loss: 0.013597643934190273
2023-01-24 07:45:28.179814: step: 1092/529, loss: 0.0037607047706842422
2023-01-24 07:45:29.229605: step: 1096/529, loss: 0.002548146527260542
2023-01-24 07:45:30.285820: step: 1100/529, loss: 0.004771307110786438
2023-01-24 07:45:31.350334: step: 1104/529, loss: 0.0005690946127288043
2023-01-24 07:45:32.389149: step: 1108/529, loss: 0.03359944745898247
2023-01-24 07:45:33.436386: step: 1112/529, loss: 0.0028464437928050756
2023-01-24 07:45:34.483019: step: 1116/529, loss: 0.0009826518362388015
2023-01-24 07:45:35.532453: step: 1120/529, loss: 0.004724137019366026
2023-01-24 07:45:36.589171: step: 1124/529, loss: 0.004929270129650831
2023-01-24 07:45:37.639604: step: 1128/529, loss: 0.013819349929690361
2023-01-24 07:45:38.699518: step: 1132/529, loss: 0.0013363063335418701
2023-01-24 07:45:39.741104: step: 1136/529, loss: 0.0019385061459615827
2023-01-24 07:45:40.797389: step: 1140/529, loss: 0.0021166556980460882
2023-01-24 07:45:41.868379: step: 1144/529, loss: 0.0015858920523896813
2023-01-24 07:45:42.921612: step: 1148/529, loss: 0.0013822591863572598
2023-01-24 07:45:43.973349: step: 1152/529, loss: 0.0007352886605076492
2023-01-24 07:45:45.009999: step: 1156/529, loss: 0.003908718936145306
2023-01-24 07:45:46.059945: step: 1160/529, loss: 0.005205837544053793
2023-01-24 07:45:47.099087: step: 1164/529, loss: 7.31611653463915e-05
2023-01-24 07:45:48.140387: step: 1168/529, loss: 0.0021883153822273016
2023-01-24 07:45:49.179832: step: 1172/529, loss: 0.003466276917606592
2023-01-24 07:45:50.226374: step: 1176/529, loss: 2.9402990548987873e-05
2023-01-24 07:45:51.273327: step: 1180/529, loss: 0.0007753438549116254
2023-01-24 07:45:52.315236: step: 1184/529, loss: 0.0012284221593290567
2023-01-24 07:45:53.353618: step: 1188/529, loss: 0.005005307495594025
2023-01-24 07:45:54.394221: step: 1192/529, loss: 0.00047058000927791
2023-01-24 07:45:55.447245: step: 1196/529, loss: 0.03527161106467247
2023-01-24 07:45:56.474172: step: 1200/529, loss: 0.0010925685055553913
2023-01-24 07:45:57.524461: step: 1204/529, loss: 0.006169338244944811
2023-01-24 07:45:58.580974: step: 1208/529, loss: 0.004179372917860746
2023-01-24 07:45:59.631230: step: 1212/529, loss: 0.002172439359128475
2023-01-24 07:46:00.689997: step: 1216/529, loss: 0.013159377500414848
2023-01-24 07:46:01.724991: step: 1220/529, loss: 0.0007594486232846975
2023-01-24 07:46:02.781955: step: 1224/529, loss: 0.010045397095382214
2023-01-24 07:46:03.832900: step: 1228/529, loss: 0.0003671941813081503
2023-01-24 07:46:04.875301: step: 1232/529, loss: 0.014888791367411613
2023-01-24 07:46:05.915996: step: 1236/529, loss: 0.0013621074613183737
2023-01-24 07:46:06.962543: step: 1240/529, loss: 0.000595246150624007
2023-01-24 07:46:08.013228: step: 1244/529, loss: 0.0011664701160043478
2023-01-24 07:46:09.059973: step: 1248/529, loss: 0.008231216110289097
2023-01-24 07:46:10.095800: step: 1252/529, loss: 1.5318893929361366e-05
2023-01-24 07:46:11.154776: step: 1256/529, loss: 0.005235225893557072
2023-01-24 07:46:12.189505: step: 1260/529, loss: 0.0008889954187907279
2023-01-24 07:46:13.256948: step: 1264/529, loss: 0.00544637069106102
2023-01-24 07:46:14.303028: step: 1268/529, loss: 0.0017070675967261195
2023-01-24 07:46:15.346246: step: 1272/529, loss: 0.0032997624948620796
2023-01-24 07:46:16.388468: step: 1276/529, loss: 0.0027532135136425495
2023-01-24 07:46:17.436510: step: 1280/529, loss: 0.004179778508841991
2023-01-24 07:46:18.480399: step: 1284/529, loss: 0.005422530695796013
2023-01-24 07:46:19.532395: step: 1288/529, loss: 0.00449686124920845
2023-01-24 07:46:20.577962: step: 1292/529, loss: 0.005088336765766144
2023-01-24 07:46:21.640452: step: 1296/529, loss: 0.002625285880640149
2023-01-24 07:46:22.699666: step: 1300/529, loss: 0.003848590888082981
2023-01-24 07:46:23.739278: step: 1304/529, loss: 0.0032895051408559084
2023-01-24 07:46:24.780330: step: 1308/529, loss: 0.022802336141467094
2023-01-24 07:46:25.829447: step: 1312/529, loss: 0.0009778965031728148
2023-01-24 07:46:26.869428: step: 1316/529, loss: 0.002754578134045005
2023-01-24 07:46:27.924078: step: 1320/529, loss: 0.007280981168150902
2023-01-24 07:46:28.968355: step: 1324/529, loss: 7.569111858174438e-06
2023-01-24 07:46:30.012009: step: 1328/529, loss: 0.0017688446678221226
2023-01-24 07:46:31.074160: step: 1332/529, loss: 0.006402065046131611
2023-01-24 07:46:32.133352: step: 1336/529, loss: 0.005658620968461037
2023-01-24 07:46:33.174637: step: 1340/529, loss: 0.000416864815633744
2023-01-24 07:46:34.216224: step: 1344/529, loss: 0.0076031978242099285
2023-01-24 07:46:35.269176: step: 1348/529, loss: 0.010647532530128956
2023-01-24 07:46:36.344865: step: 1352/529, loss: 0.0029094917699694633
2023-01-24 07:46:37.394127: step: 1356/529, loss: 0.00999512616544962
2023-01-24 07:46:38.454181: step: 1360/529, loss: 0.0018489662325009704
2023-01-24 07:46:39.491618: step: 1364/529, loss: 0.0031395924743264914
2023-01-24 07:46:40.546551: step: 1368/529, loss: 0.0034959500189870596
2023-01-24 07:46:41.584907: step: 1372/529, loss: 0.0017480578972026706
2023-01-24 07:46:42.639722: step: 1376/529, loss: 5.7238441513618454e-05
2023-01-24 07:46:43.701922: step: 1380/529, loss: 0.0035993969067931175
2023-01-24 07:46:44.749935: step: 1384/529, loss: 0.00016169989248737693
2023-01-24 07:46:45.799930: step: 1388/529, loss: 0.00029528679442591965
2023-01-24 07:46:46.857107: step: 1392/529, loss: 0.00122136774007231
2023-01-24 07:46:47.914290: step: 1396/529, loss: 0.01023776549845934
2023-01-24 07:46:48.963316: step: 1400/529, loss: 0.0012139384634792805
2023-01-24 07:46:50.033474: step: 1404/529, loss: 0.007344082463532686
2023-01-24 07:46:51.090315: step: 1408/529, loss: 0.0012629888951778412
2023-01-24 07:46:52.145461: step: 1412/529, loss: 0.007245719898492098
2023-01-24 07:46:53.200606: step: 1416/529, loss: 0.00011588398047024384
2023-01-24 07:46:54.256591: step: 1420/529, loss: 0.009380210191011429
2023-01-24 07:46:55.314934: step: 1424/529, loss: 0.0013724250020459294
2023-01-24 07:46:56.376753: step: 1428/529, loss: 0.008972019888460636
2023-01-24 07:46:57.430782: step: 1432/529, loss: 0.001762324245646596
2023-01-24 07:46:58.478492: step: 1436/529, loss: 0.024198533967137337
2023-01-24 07:46:59.538834: step: 1440/529, loss: 0.00026054983027279377
2023-01-24 07:47:00.624794: step: 1444/529, loss: 0.007760311011224985
2023-01-24 07:47:01.660276: step: 1448/529, loss: 0.0011082420824095607
2023-01-24 07:47:02.730080: step: 1452/529, loss: 1.0289173587807454e-05
2023-01-24 07:47:03.777325: step: 1456/529, loss: 0.0013445861404761672
2023-01-24 07:47:04.836152: step: 1460/529, loss: 0.0054323081858456135
2023-01-24 07:47:05.880317: step: 1464/529, loss: 0.004967245738953352
2023-01-24 07:47:06.947222: step: 1468/529, loss: 0.0005596865667030215
2023-01-24 07:47:08.014934: step: 1472/529, loss: 0.0036300430074334145
2023-01-24 07:47:09.070976: step: 1476/529, loss: 0.001081341877579689
2023-01-24 07:47:10.124076: step: 1480/529, loss: 0.0033402361441403627
2023-01-24 07:47:11.185367: step: 1484/529, loss: 8.448483276879415e-05
2023-01-24 07:47:12.233545: step: 1488/529, loss: 0.0019197298679500818
2023-01-24 07:47:13.299838: step: 1492/529, loss: 0.03283115103840828
2023-01-24 07:47:14.373536: step: 1496/529, loss: 0.030642159283161163
2023-01-24 07:47:15.439929: step: 1500/529, loss: 0.0003372599894646555
2023-01-24 07:47:16.488344: step: 1504/529, loss: 0.0056101055815815926
2023-01-24 07:47:17.578178: step: 1508/529, loss: 0.002772001549601555
2023-01-24 07:47:18.640510: step: 1512/529, loss: 0.005742242094129324
2023-01-24 07:47:19.711457: step: 1516/529, loss: 0.001894099055789411
2023-01-24 07:47:20.784952: step: 1520/529, loss: 0.0035289162769913673
2023-01-24 07:47:21.844557: step: 1524/529, loss: 0.0035893614403903484
2023-01-24 07:47:22.895266: step: 1528/529, loss: 0.0023253585677593946
2023-01-24 07:47:23.965551: step: 1532/529, loss: 0.007577994838356972
2023-01-24 07:47:25.041983: step: 1536/529, loss: 0.029570136219263077
2023-01-24 07:47:26.092055: step: 1540/529, loss: 0.000860285887029022
2023-01-24 07:47:27.154242: step: 1544/529, loss: 0.013597846031188965
2023-01-24 07:47:28.200809: step: 1548/529, loss: 0.003933881875127554
2023-01-24 07:47:29.264156: step: 1552/529, loss: 0.015945985913276672
2023-01-24 07:47:30.329488: step: 1556/529, loss: 0.027418581768870354
2023-01-24 07:47:31.405980: step: 1560/529, loss: 0.027375882491469383
2023-01-24 07:47:32.484782: step: 1564/529, loss: 0.0002518148685339838
2023-01-24 07:47:33.539215: step: 1568/529, loss: 0.004726926330476999
2023-01-24 07:47:34.612191: step: 1572/529, loss: 0.01280633918941021
2023-01-24 07:47:35.650393: step: 1576/529, loss: 0.001645186566747725
2023-01-24 07:47:36.717635: step: 1580/529, loss: 0.0077974833548069
2023-01-24 07:47:37.773181: step: 1584/529, loss: 0.009461759589612484
2023-01-24 07:47:38.842890: step: 1588/529, loss: 0.0042156437411904335
2023-01-24 07:47:39.906494: step: 1592/529, loss: 0.0005270384717732668
2023-01-24 07:47:40.967731: step: 1596/529, loss: 0.0077084568329155445
2023-01-24 07:47:42.031002: step: 1600/529, loss: 0.0017473968910053372
2023-01-24 07:47:43.101366: step: 1604/529, loss: 0.002532375743612647
2023-01-24 07:47:44.162821: step: 1608/529, loss: 0.005044633522629738
2023-01-24 07:47:45.214166: step: 1612/529, loss: 0.002297821454703808
2023-01-24 07:47:46.271452: step: 1616/529, loss: 0.003892823588103056
2023-01-24 07:47:47.346422: step: 1620/529, loss: 0.0002748209226410836
2023-01-24 07:47:48.391307: step: 1624/529, loss: 9.179872904496733e-06
2023-01-24 07:47:49.463554: step: 1628/529, loss: 0.001021646079607308
2023-01-24 07:47:50.517767: step: 1632/529, loss: 0.005978672299534082
2023-01-24 07:47:51.585070: step: 1636/529, loss: 0.006814329884946346
2023-01-24 07:47:52.630614: step: 1640/529, loss: 0.03574233502149582
2023-01-24 07:47:53.686583: step: 1644/529, loss: 0.02467593178153038
2023-01-24 07:47:54.729133: step: 1648/529, loss: 0.008382775820791721
2023-01-24 07:47:55.787414: step: 1652/529, loss: 0.013118617236614227
2023-01-24 07:47:56.841488: step: 1656/529, loss: 0.003820637706667185
2023-01-24 07:47:57.894920: step: 1660/529, loss: 0.0017149208579212427
2023-01-24 07:47:58.953149: step: 1664/529, loss: 0.00028046814259141684
2023-01-24 07:48:00.034856: step: 1668/529, loss: 0.0019609276205301285
2023-01-24 07:48:01.082072: step: 1672/529, loss: 0.0032593209762126207
2023-01-24 07:48:02.135478: step: 1676/529, loss: 0.006112730596214533
2023-01-24 07:48:03.180826: step: 1680/529, loss: 0.00010005044896388426
2023-01-24 07:48:04.239086: step: 1684/529, loss: 3.4220702218590304e-05
2023-01-24 07:48:05.297652: step: 1688/529, loss: 0.004033186472952366
2023-01-24 07:48:06.368594: step: 1692/529, loss: 0.008895925246179104
2023-01-24 07:48:07.418683: step: 1696/529, loss: 0.008494758978486061
2023-01-24 07:48:08.466906: step: 1700/529, loss: 0.002115307841449976
2023-01-24 07:48:09.527361: step: 1704/529, loss: 0.007378788664937019
2023-01-24 07:48:10.596659: step: 1708/529, loss: 0.002627026755362749
2023-01-24 07:48:11.630261: step: 1712/529, loss: 0.009284731931984425
2023-01-24 07:48:12.689391: step: 1716/529, loss: 0.006106279790401459
2023-01-24 07:48:13.744785: step: 1720/529, loss: 0.0019213747000321746
2023-01-24 07:48:14.808380: step: 1724/529, loss: 0.0005601948359981179
2023-01-24 07:48:15.882779: step: 1728/529, loss: 0.010213938541710377
2023-01-24 07:48:16.931420: step: 1732/529, loss: 0.0005565674509853125
2023-01-24 07:48:17.991191: step: 1736/529, loss: 0.000787131953984499
2023-01-24 07:48:19.061131: step: 1740/529, loss: 0.00015847556642256677
2023-01-24 07:48:20.109910: step: 1744/529, loss: 0.00042605522321537137
2023-01-24 07:48:21.168405: step: 1748/529, loss: 0.004209085367619991
2023-01-24 07:48:22.223005: step: 1752/529, loss: 0.000641661521513015
2023-01-24 07:48:23.265397: step: 1756/529, loss: 8.162459562299773e-05
2023-01-24 07:48:24.321165: step: 1760/529, loss: 0.024534158408641815
2023-01-24 07:48:25.375288: step: 1764/529, loss: 0.0014209687942638993
2023-01-24 07:48:26.446541: step: 1768/529, loss: 0.0010247068712487817
2023-01-24 07:48:27.479912: step: 1772/529, loss: 3.590714914025739e-05
2023-01-24 07:48:28.530644: step: 1776/529, loss: 0.02816914953291416
2023-01-24 07:48:29.591509: step: 1780/529, loss: 0.00558052584528923
2023-01-24 07:48:30.651151: step: 1784/529, loss: 0.009706541895866394
2023-01-24 07:48:31.703370: step: 1788/529, loss: 0.0005814678152091801
2023-01-24 07:48:32.773931: step: 1792/529, loss: 0.0017659314908087254
2023-01-24 07:48:33.818183: step: 1796/529, loss: 0.0008670383831486106
2023-01-24 07:48:34.877344: step: 1800/529, loss: 0.0028869614470750093
2023-01-24 07:48:35.921873: step: 1804/529, loss: 0.011576946824789047
2023-01-24 07:48:36.963461: step: 1808/529, loss: 0.00038343342021107674
2023-01-24 07:48:38.015897: step: 1812/529, loss: 0.00820641964673996
2023-01-24 07:48:39.055181: step: 1816/529, loss: 0.0005200691521167755
2023-01-24 07:48:40.111679: step: 1820/529, loss: 9.082742326427251e-05
2023-01-24 07:48:41.173837: step: 1824/529, loss: 0.007103316485881805
2023-01-24 07:48:42.237620: step: 1828/529, loss: 0.012334599159657955
2023-01-24 07:48:43.274104: step: 1832/529, loss: 0.0004765341291204095
2023-01-24 07:48:44.331569: step: 1836/529, loss: 0.0059090047143399715
2023-01-24 07:48:45.381262: step: 1840/529, loss: 0.007239827420562506
2023-01-24 07:48:46.420647: step: 1844/529, loss: 0.002510536927729845
2023-01-24 07:48:47.498775: step: 1848/529, loss: 0.017909036949276924
2023-01-24 07:48:48.560541: step: 1852/529, loss: 0.0015903770690783858
2023-01-24 07:48:49.630911: step: 1856/529, loss: 0.0007870272966101766
2023-01-24 07:48:50.668870: step: 1860/529, loss: 0.0011313335271552205
2023-01-24 07:48:51.705209: step: 1864/529, loss: 0.0006634037126787007
2023-01-24 07:48:52.753707: step: 1868/529, loss: 0.0016665610019117594
2023-01-24 07:48:53.794402: step: 1872/529, loss: 0.0005217918078415096
2023-01-24 07:48:54.875728: step: 1876/529, loss: 0.006858109962195158
2023-01-24 07:48:55.909088: step: 1880/529, loss: 0.0031124502420425415
2023-01-24 07:48:56.959555: step: 1884/529, loss: 0.00012151140253990889
2023-01-24 07:48:58.002649: step: 1888/529, loss: 0.0066160480491817
2023-01-24 07:48:59.042322: step: 1892/529, loss: 0.0004973806207999587
2023-01-24 07:49:00.092551: step: 1896/529, loss: 0.00022057184833101928
2023-01-24 07:49:01.139600: step: 1900/529, loss: 0.00285763549618423
2023-01-24 07:49:02.187320: step: 1904/529, loss: 0.002581467851996422
2023-01-24 07:49:03.229690: step: 1908/529, loss: 0.0006056476850062609
2023-01-24 07:49:04.278460: step: 1912/529, loss: 0.008550887927412987
2023-01-24 07:49:05.330583: step: 1916/529, loss: 7.217138045234606e-05
2023-01-24 07:49:06.371939: step: 1920/529, loss: 0.0030196711886674166
2023-01-24 07:49:07.435438: step: 1924/529, loss: 0.004655394237488508
2023-01-24 07:49:08.479014: step: 1928/529, loss: 0.0003646163095254451
2023-01-24 07:49:09.526990: step: 1932/529, loss: 0.00010691424540709704
2023-01-24 07:49:10.563348: step: 1936/529, loss: 9.057366696652025e-05
2023-01-24 07:49:11.612183: step: 1940/529, loss: 0.0007152705220505595
2023-01-24 07:49:12.669244: step: 1944/529, loss: 0.0013242709683254361
2023-01-24 07:49:13.724780: step: 1948/529, loss: 0.029559042304754257
2023-01-24 07:49:14.778846: step: 1952/529, loss: 0.0009429925703443587
2023-01-24 07:49:15.816540: step: 1956/529, loss: 0.0024571174290031195
2023-01-24 07:49:16.863847: step: 1960/529, loss: 0.004922664258629084
2023-01-24 07:49:17.924246: step: 1964/529, loss: 0.007519112899899483
2023-01-24 07:49:18.958936: step: 1968/529, loss: 0.008268882520496845
2023-01-24 07:49:20.037997: step: 1972/529, loss: 0.008260934613645077
2023-01-24 07:49:21.083154: step: 1976/529, loss: 0.0023932557087391615
2023-01-24 07:49:22.131001: step: 1980/529, loss: 0.0017931960755959153
2023-01-24 07:49:23.176248: step: 1984/529, loss: 0.0020225034095346928
2023-01-24 07:49:24.212019: step: 1988/529, loss: 0.0015393097419291735
2023-01-24 07:49:25.259136: step: 1992/529, loss: 0.002816372085362673
2023-01-24 07:49:26.306913: step: 1996/529, loss: 0.003302858443930745
2023-01-24 07:49:27.361568: step: 2000/529, loss: 0.001450967276468873
2023-01-24 07:49:28.425567: step: 2004/529, loss: 0.0015459076967090368
2023-01-24 07:49:29.486201: step: 2008/529, loss: 0.006638125516474247
2023-01-24 07:49:30.541428: step: 2012/529, loss: 0.0036761483643203974
2023-01-24 07:49:31.599656: step: 2016/529, loss: 0.0077044907957315445
2023-01-24 07:49:32.644537: step: 2020/529, loss: 0.0005872112233191729
2023-01-24 07:49:33.682351: step: 2024/529, loss: 0.002109806053340435
2023-01-24 07:49:34.729268: step: 2028/529, loss: 0.005489069037139416
2023-01-24 07:49:35.778718: step: 2032/529, loss: 0.003942413255572319
2023-01-24 07:49:36.823100: step: 2036/529, loss: 0.0008662652689963579
2023-01-24 07:49:37.866744: step: 2040/529, loss: 0.006898907478898764
2023-01-24 07:49:38.933189: step: 2044/529, loss: 9.478346328251064e-06
2023-01-24 07:49:39.979709: step: 2048/529, loss: 0.004567817784845829
2023-01-24 07:49:41.047524: step: 2052/529, loss: 0.004708696622401476
2023-01-24 07:49:42.092256: step: 2056/529, loss: 0.00026184471789747477
2023-01-24 07:49:43.156039: step: 2060/529, loss: 0.01017149817198515
2023-01-24 07:49:44.197663: step: 2064/529, loss: 0.006889031268656254
2023-01-24 07:49:45.245081: step: 2068/529, loss: 3.684464900288731e-05
2023-01-24 07:49:46.299346: step: 2072/529, loss: 0.004533926025032997
2023-01-24 07:49:47.361170: step: 2076/529, loss: 0.0059210010804235935
2023-01-24 07:49:48.389879: step: 2080/529, loss: 0.0006793277570977807
2023-01-24 07:49:49.460190: step: 2084/529, loss: 0.0015826687449589372
2023-01-24 07:49:50.497400: step: 2088/529, loss: 0.005795718170702457
2023-01-24 07:49:51.530891: step: 2092/529, loss: 0.0038641574792563915
2023-01-24 07:49:52.584390: step: 2096/529, loss: 0.004207300953567028
2023-01-24 07:49:53.622551: step: 2100/529, loss: 0.008558275178074837
2023-01-24 07:49:54.681583: step: 2104/529, loss: 0.0020565742161124945
2023-01-24 07:49:55.723990: step: 2108/529, loss: 0.006336023565381765
2023-01-24 07:49:56.776227: step: 2112/529, loss: 0.005426003597676754
2023-01-24 07:49:57.812967: step: 2116/529, loss: 0.006619339343160391
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32562119003445533, 'r': 0.33303571428571427, 'f1': 0.3292867193781828}, 'combined': 0.2426323195418189, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3713611386690343, 'r': 0.3016904189361876, 'f1': 0.33291980751167166}, 'combined': 0.23421493995795997, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3569371035940804, 'r': 0.32036290322580646, 'f1': 0.3376625}, 'combined': 0.248803947368421, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3934857311596323, 'r': 0.3227544391710771, 'f1': 0.3546276004698508}, 'combined': 0.25178559633359404, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3757374795389031, 'r': 0.34222768534852654, 'f1': 0.35820057632308533}, 'combined': 0.2639372667643787, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39985806339254615, 'r': 0.3142989144570232, 'f1': 0.35195330763158095}, 'combined': 0.24988684841842246, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:52:29.487778: step: 4/529, loss: 0.002155041554942727
2023-01-24 07:52:30.519910: step: 8/529, loss: 0.0024896918330341578
2023-01-24 07:52:31.561540: step: 12/529, loss: 0.0019456169102340937
2023-01-24 07:52:32.595711: step: 16/529, loss: 0.0026377339381724596
2023-01-24 07:52:33.650790: step: 20/529, loss: 0.0028321901336312294
2023-01-24 07:52:34.678496: step: 24/529, loss: 0.004259231500327587
2023-01-24 07:52:35.699960: step: 28/529, loss: 0.018199829384684563
2023-01-24 07:52:36.735753: step: 32/529, loss: 0.007439835928380489
2023-01-24 07:52:37.776203: step: 36/529, loss: 0.0032286536879837513
2023-01-24 07:52:38.821179: step: 40/529, loss: 0.005584105849266052
2023-01-24 07:52:39.841216: step: 44/529, loss: 0.000737053225748241
2023-01-24 07:52:40.872560: step: 48/529, loss: 8.867979340720922e-05
2023-01-24 07:52:41.908173: step: 52/529, loss: 0.0032440032809972763
2023-01-24 07:52:42.958546: step: 56/529, loss: 0.000398068135837093
2023-01-24 07:52:44.005446: step: 60/529, loss: 0.0005101492861285806
2023-01-24 07:52:45.041038: step: 64/529, loss: 0.00027752568712458014
2023-01-24 07:52:46.074922: step: 68/529, loss: 0.0002734805748332292
2023-01-24 07:52:47.120963: step: 72/529, loss: 0.0017120081465691328
2023-01-24 07:52:48.164179: step: 76/529, loss: 0.00775559339672327
2023-01-24 07:52:49.225815: step: 80/529, loss: 0.0
2023-01-24 07:52:50.267627: step: 84/529, loss: 0.0017491179751232266
2023-01-24 07:52:51.300431: step: 88/529, loss: 0.0003052113752346486
2023-01-24 07:52:52.333513: step: 92/529, loss: 0.004354408010840416
2023-01-24 07:52:53.392952: step: 96/529, loss: 0.00548102892935276
2023-01-24 07:52:54.453185: step: 100/529, loss: 0.00046892414684407413
2023-01-24 07:52:55.490475: step: 104/529, loss: 0.024891097098588943
2023-01-24 07:52:56.555107: step: 108/529, loss: 0.002255897969007492
2023-01-24 07:52:57.611094: step: 112/529, loss: 0.0025460803881287575
2023-01-24 07:52:58.647538: step: 116/529, loss: 0.000157733287778683
2023-01-24 07:52:59.683740: step: 120/529, loss: 0.0006947237998247147
2023-01-24 07:53:00.720673: step: 124/529, loss: 0.005598415154963732
2023-01-24 07:53:01.777102: step: 128/529, loss: 0.005664017051458359
2023-01-24 07:53:02.841207: step: 132/529, loss: 0.005263058934360743
2023-01-24 07:53:03.880813: step: 136/529, loss: 0.010701052844524384
2023-01-24 07:53:04.928616: step: 140/529, loss: 0.0008631572127342224
2023-01-24 07:53:05.962406: step: 144/529, loss: 0.0003937564615625888
2023-01-24 07:53:06.995590: step: 148/529, loss: 0.0011120919371023774
2023-01-24 07:53:08.038971: step: 152/529, loss: 0.01467109564691782
2023-01-24 07:53:09.074712: step: 156/529, loss: 0.005467843730002642
2023-01-24 07:53:10.116042: step: 160/529, loss: 0.0001164595887530595
2023-01-24 07:53:11.181744: step: 164/529, loss: 0.005824428051710129
2023-01-24 07:53:12.225701: step: 168/529, loss: 0.0009500669548287988
2023-01-24 07:53:13.277075: step: 172/529, loss: 0.00394128542393446
2023-01-24 07:53:14.310188: step: 176/529, loss: 0.0038720332086086273
2023-01-24 07:53:15.342802: step: 180/529, loss: 0.003293375950306654
2023-01-24 07:53:16.373124: step: 184/529, loss: 0.00012934478581883013
2023-01-24 07:53:17.414651: step: 188/529, loss: 0.003876871196553111
2023-01-24 07:53:18.450484: step: 192/529, loss: 0.010672000236809254
2023-01-24 07:53:19.503044: step: 196/529, loss: 0.0033258579205721617
2023-01-24 07:53:20.558974: step: 200/529, loss: 0.0007002443890087306
2023-01-24 07:53:21.621302: step: 204/529, loss: 0.0027310438454151154
2023-01-24 07:53:22.667760: step: 208/529, loss: 0.001031105755828321
2023-01-24 07:53:23.713492: step: 212/529, loss: 0.0027227492537349463
2023-01-24 07:53:24.765454: step: 216/529, loss: 0.0012246674159541726
2023-01-24 07:53:25.809682: step: 220/529, loss: 0.0028238133527338505
2023-01-24 07:53:26.867208: step: 224/529, loss: 0.0016362721798941493
2023-01-24 07:53:27.899847: step: 228/529, loss: 0.0014409139985218644
2023-01-24 07:53:28.937720: step: 232/529, loss: 0.0034382170997560024
2023-01-24 07:53:29.984118: step: 236/529, loss: 0.0010161075042560697
2023-01-24 07:53:31.026218: step: 240/529, loss: 0.005142989568412304
2023-01-24 07:53:32.080209: step: 244/529, loss: 0.0007435519946739078
2023-01-24 07:53:33.129423: step: 248/529, loss: 3.999934415332973e-05
2023-01-24 07:53:34.166491: step: 252/529, loss: 0.0007353387190960348
2023-01-24 07:53:35.228157: step: 256/529, loss: 0.01636943407356739
2023-01-24 07:53:36.281276: step: 260/529, loss: 0.0003766532754525542
2023-01-24 07:53:37.344535: step: 264/529, loss: 0.005757701583206654
2023-01-24 07:53:38.381308: step: 268/529, loss: 0.01307438500225544
2023-01-24 07:53:39.417555: step: 272/529, loss: 0.004971130285412073
2023-01-24 07:53:40.478221: step: 276/529, loss: 0.008131401613354683
2023-01-24 07:53:41.538539: step: 280/529, loss: 0.008967198431491852
2023-01-24 07:53:42.589979: step: 284/529, loss: 0.00253537530079484
2023-01-24 07:53:43.669424: step: 288/529, loss: 0.00853712297976017
2023-01-24 07:53:44.714890: step: 292/529, loss: 0.0031157343182712793
2023-01-24 07:53:45.768047: step: 296/529, loss: 0.000533953367266804
2023-01-24 07:53:46.802295: step: 300/529, loss: 0.0009093710104934871
2023-01-24 07:53:47.845896: step: 304/529, loss: 0.024085940793156624
2023-01-24 07:53:48.880304: step: 308/529, loss: 0.003846596460789442
2023-01-24 07:53:49.948733: step: 312/529, loss: 0.0037498008459806442
2023-01-24 07:53:50.984686: step: 316/529, loss: 0.001778452773578465
2023-01-24 07:53:52.031674: step: 320/529, loss: 0.0061292885802686214
2023-01-24 07:53:53.072262: step: 324/529, loss: 0.0021300611551851034
2023-01-24 07:53:54.126303: step: 328/529, loss: 0.0011772337602451444
2023-01-24 07:53:55.186018: step: 332/529, loss: 8.890203753253445e-05
2023-01-24 07:53:56.233583: step: 336/529, loss: 0.000312322867102921
2023-01-24 07:53:57.271938: step: 340/529, loss: 0.00734830554574728
2023-01-24 07:53:58.302590: step: 344/529, loss: 0.004455361049622297
2023-01-24 07:53:59.349176: step: 348/529, loss: 0.00104904780164361
2023-01-24 07:54:00.391493: step: 352/529, loss: 0.0019082671497017145
2023-01-24 07:54:01.450815: step: 356/529, loss: 0.0028017640579491854
2023-01-24 07:54:02.513967: step: 360/529, loss: 0.00459581334143877
2023-01-24 07:54:03.550668: step: 364/529, loss: 0.002507390920072794
2023-01-24 07:54:04.586283: step: 368/529, loss: 0.005696725565940142
2023-01-24 07:54:05.629699: step: 372/529, loss: 0.0025276239030063152
2023-01-24 07:54:06.672115: step: 376/529, loss: 0.0014634763356298208
2023-01-24 07:54:07.734815: step: 380/529, loss: 0.0009265472763217986
2023-01-24 07:54:08.771421: step: 384/529, loss: 0.001057068700902164
2023-01-24 07:54:09.815921: step: 388/529, loss: 0.00324159674346447
2023-01-24 07:54:10.855145: step: 392/529, loss: 0.0004419496690388769
2023-01-24 07:54:11.902986: step: 396/529, loss: 0.033807914704084396
2023-01-24 07:54:12.951598: step: 400/529, loss: 0.0019463013159111142
2023-01-24 07:54:13.991111: step: 404/529, loss: 0.001065503223799169
2023-01-24 07:54:15.023324: step: 408/529, loss: 0.0009013141389004886
2023-01-24 07:54:16.062726: step: 412/529, loss: 0.0005079795373603702
2023-01-24 07:54:17.111146: step: 416/529, loss: 0.008460178039968014
2023-01-24 07:54:18.163586: step: 420/529, loss: 0.00020978682732675225
2023-01-24 07:54:19.198889: step: 424/529, loss: 0.007690533995628357
2023-01-24 07:54:20.243163: step: 428/529, loss: 0.002265217714011669
2023-01-24 07:54:21.282012: step: 432/529, loss: 0.0010795852867886424
2023-01-24 07:54:22.326527: step: 436/529, loss: 8.389084541704506e-05
2023-01-24 07:54:23.371279: step: 440/529, loss: 0.00022258538228925318
2023-01-24 07:54:24.419726: step: 444/529, loss: 0.0032947936560958624
2023-01-24 07:54:25.470070: step: 448/529, loss: 0.002077118493616581
2023-01-24 07:54:26.518063: step: 452/529, loss: 0.0038745917845517397
2023-01-24 07:54:27.558313: step: 456/529, loss: 0.006758896633982658
2023-01-24 07:54:28.620701: step: 460/529, loss: 0.002824159571900964
2023-01-24 07:54:29.681778: step: 464/529, loss: 0.0017004429828375578
2023-01-24 07:54:30.716706: step: 468/529, loss: 0.004164464771747589
2023-01-24 07:54:31.760753: step: 472/529, loss: 0.0004152019682805985
2023-01-24 07:54:32.805422: step: 476/529, loss: 0.03245808929204941
2023-01-24 07:54:33.846589: step: 480/529, loss: 0.002974143484607339
2023-01-24 07:54:34.889413: step: 484/529, loss: 0.000262746267253533
2023-01-24 07:54:35.925379: step: 488/529, loss: 0.002748754806816578
2023-01-24 07:54:36.989704: step: 492/529, loss: 0.005684906151145697
2023-01-24 07:54:38.043921: step: 496/529, loss: 0.0008600415894761682
2023-01-24 07:54:39.105630: step: 500/529, loss: 0.002134669106453657
2023-01-24 07:54:40.146792: step: 504/529, loss: 0.0003652505110949278
2023-01-24 07:54:41.189443: step: 508/529, loss: 9.394869266543537e-05
2023-01-24 07:54:42.234283: step: 512/529, loss: 0.003705232171341777
2023-01-24 07:54:43.279630: step: 516/529, loss: 4.8185422201640904e-05
2023-01-24 07:54:44.325804: step: 520/529, loss: 0.0011554473312571645
2023-01-24 07:54:45.370849: step: 524/529, loss: 0.004970197100192308
2023-01-24 07:54:46.428482: step: 528/529, loss: 0.003078704932704568
2023-01-24 07:54:47.492610: step: 532/529, loss: 0.005329811945557594
2023-01-24 07:54:48.533500: step: 536/529, loss: 0.005917105358093977
2023-01-24 07:54:49.577013: step: 540/529, loss: 0.003959241788834333
2023-01-24 07:54:50.611047: step: 544/529, loss: 7.423215720336884e-05
2023-01-24 07:54:51.656975: step: 548/529, loss: 0.002601574407890439
2023-01-24 07:54:52.725272: step: 552/529, loss: 0.0009090172243304551
2023-01-24 07:54:53.766006: step: 556/529, loss: 0.011935210786759853
2023-01-24 07:54:54.800969: step: 560/529, loss: 0.0008761092321947217
2023-01-24 07:54:55.838536: step: 564/529, loss: 0.007983102463185787
2023-01-24 07:54:56.874492: step: 568/529, loss: 0.0009231130825355649
2023-01-24 07:54:57.925503: step: 572/529, loss: 0.0145405363291502
2023-01-24 07:54:58.991455: step: 576/529, loss: 0.004041179083287716
2023-01-24 07:55:00.032830: step: 580/529, loss: 0.00153260154183954
2023-01-24 07:55:01.081157: step: 584/529, loss: 0.010185637511312962
2023-01-24 07:55:02.129932: step: 588/529, loss: 0.00577272055670619
2023-01-24 07:55:03.177207: step: 592/529, loss: 0.0002528772165533155
2023-01-24 07:55:04.209446: step: 596/529, loss: 2.7549012884264812e-05
2023-01-24 07:55:05.264005: step: 600/529, loss: 0.0031712548807263374
2023-01-24 07:55:06.323416: step: 604/529, loss: 0.0013344237813726068
2023-01-24 07:55:07.372121: step: 608/529, loss: 0.00024164778005797416
2023-01-24 07:55:08.426633: step: 612/529, loss: 0.020136168226599693
2023-01-24 07:55:09.467123: step: 616/529, loss: 0.006162128411233425
2023-01-24 07:55:10.536209: step: 620/529, loss: 0.00643115071579814
2023-01-24 07:55:11.576643: step: 624/529, loss: 0.0015247485134750605
2023-01-24 07:55:12.632331: step: 628/529, loss: 0.00420212559401989
2023-01-24 07:55:13.675151: step: 632/529, loss: 0.005724126938730478
2023-01-24 07:55:14.731858: step: 636/529, loss: 0.004357540979981422
2023-01-24 07:55:15.760137: step: 640/529, loss: 0.001910732826218009
2023-01-24 07:55:16.816630: step: 644/529, loss: 0.00031357069383375347
2023-01-24 07:55:17.860357: step: 648/529, loss: 0.004843851551413536
2023-01-24 07:55:18.902820: step: 652/529, loss: 0.00043408438796177506
2023-01-24 07:55:19.953023: step: 656/529, loss: 0.006753296125680208
2023-01-24 07:55:21.013739: step: 660/529, loss: 0.0032933454494923353
2023-01-24 07:55:22.068948: step: 664/529, loss: 0.0027763620018959045
2023-01-24 07:55:23.110726: step: 668/529, loss: 0.0038538069929927588
2023-01-24 07:55:24.156116: step: 672/529, loss: 0.0014959522522985935
2023-01-24 07:55:25.199376: step: 676/529, loss: 0.0011482766130939126
2023-01-24 07:55:26.244151: step: 680/529, loss: 0.006304308772087097
2023-01-24 07:55:27.282673: step: 684/529, loss: 0.028128989040851593
2023-01-24 07:55:28.321067: step: 688/529, loss: 7.844861102057621e-06
2023-01-24 07:55:29.362735: step: 692/529, loss: 0.004067400004714727
2023-01-24 07:55:30.406087: step: 696/529, loss: 0.0036468200851231813
2023-01-24 07:55:31.453431: step: 700/529, loss: 0.007611549459397793
2023-01-24 07:55:32.508443: step: 704/529, loss: 0.0027929057832807302
2023-01-24 07:55:33.546560: step: 708/529, loss: 7.540291699115187e-05
2023-01-24 07:55:34.598747: step: 712/529, loss: 0.0030069584026932716
2023-01-24 07:55:35.666886: step: 716/529, loss: 2.465686065988848e-06
2023-01-24 07:55:36.701556: step: 720/529, loss: 0.0004384104977361858
2023-01-24 07:55:37.742712: step: 724/529, loss: 0.005286080297082663
2023-01-24 07:55:38.781441: step: 728/529, loss: 2.288771611347329e-06
2023-01-24 07:55:39.842584: step: 732/529, loss: 0.0015304546104744077
2023-01-24 07:55:40.888798: step: 736/529, loss: 0.002393218455836177
2023-01-24 07:55:41.932457: step: 740/529, loss: 0.002610682975500822
2023-01-24 07:55:42.976769: step: 744/529, loss: 0.0013310756767168641
2023-01-24 07:55:44.012455: step: 748/529, loss: 6.078930709918495e-06
2023-01-24 07:55:45.053521: step: 752/529, loss: 0.009128289297223091
2023-01-24 07:55:46.080937: step: 756/529, loss: 0.00015589853865094483
2023-01-24 07:55:47.124037: step: 760/529, loss: 0.00020308865350671113
2023-01-24 07:55:48.174857: step: 764/529, loss: 0.0062463413923978806
2023-01-24 07:55:49.237305: step: 768/529, loss: 0.005044538527727127
2023-01-24 07:55:50.284543: step: 772/529, loss: 0.0030988561920821667
2023-01-24 07:55:51.333884: step: 776/529, loss: 0.00045495491940528154
2023-01-24 07:55:52.397410: step: 780/529, loss: 0.006148281041532755
2023-01-24 07:55:53.447758: step: 784/529, loss: 0.0037484855856746435
2023-01-24 07:55:54.495803: step: 788/529, loss: 0.0024214996956288815
2023-01-24 07:55:55.536695: step: 792/529, loss: 0.001267142128199339
2023-01-24 07:55:56.583377: step: 796/529, loss: 0.010626288130879402
2023-01-24 07:55:57.621268: step: 800/529, loss: 0.00012084989430150017
2023-01-24 07:55:58.673890: step: 804/529, loss: 0.004150815773755312
2023-01-24 07:55:59.722611: step: 808/529, loss: 0.0003200530481990427
2023-01-24 07:56:00.771486: step: 812/529, loss: 0.07948880642652512
2023-01-24 07:56:01.804990: step: 816/529, loss: 0.00025089934933930635
2023-01-24 07:56:02.846769: step: 820/529, loss: 0.006020818371325731
2023-01-24 07:56:03.882173: step: 824/529, loss: 0.004475736059248447
2023-01-24 07:56:04.922773: step: 828/529, loss: 0.0023098408710211515
2023-01-24 07:56:05.964644: step: 832/529, loss: 0.004625964909791946
2023-01-24 07:56:07.018913: step: 836/529, loss: 0.0036058761179447174
2023-01-24 07:56:08.047173: step: 840/529, loss: 0.00279402662999928
2023-01-24 07:56:09.080891: step: 844/529, loss: 0.016049500554800034
2023-01-24 07:56:10.117660: step: 848/529, loss: 0.001846490427851677
2023-01-24 07:56:11.185759: step: 852/529, loss: 0.02167278155684471
2023-01-24 07:56:12.224652: step: 856/529, loss: 0.00016633969789836556
2023-01-24 07:56:13.271801: step: 860/529, loss: 0.005792663432657719
2023-01-24 07:56:14.317840: step: 864/529, loss: 0.0022735409438610077
2023-01-24 07:56:15.358997: step: 868/529, loss: 0.02926735393702984
2023-01-24 07:56:16.404551: step: 872/529, loss: 0.001265300321392715
2023-01-24 07:56:17.443874: step: 876/529, loss: 0.0004687622422352433
2023-01-24 07:56:18.478621: step: 880/529, loss: 0.0007134170737117529
2023-01-24 07:56:19.544199: step: 884/529, loss: 0.0013752337545156479
2023-01-24 07:56:20.585280: step: 888/529, loss: 0.0016911706188693643
2023-01-24 07:56:21.624743: step: 892/529, loss: 0.0035386206582188606
2023-01-24 07:56:22.669054: step: 896/529, loss: 0.004194940906018019
2023-01-24 07:56:23.725214: step: 900/529, loss: 0.0007625749567523599
2023-01-24 07:56:24.766018: step: 904/529, loss: 0.001970997080206871
2023-01-24 07:56:25.796525: step: 908/529, loss: 0.00860562827438116
2023-01-24 07:56:26.838890: step: 912/529, loss: 9.350409158059847e-08
2023-01-24 07:56:27.880785: step: 916/529, loss: 4.811794497072697e-05
2023-01-24 07:56:28.928884: step: 920/529, loss: 0.0011264131171628833
2023-01-24 07:56:29.989262: step: 924/529, loss: 0.00645265681669116
2023-01-24 07:56:31.081045: step: 928/529, loss: 0.017367225140333176
2023-01-24 07:56:32.137241: step: 932/529, loss: 2.5015289793373086e-05
2023-01-24 07:56:33.194178: step: 936/529, loss: 0.009600379504263401
2023-01-24 07:56:34.228810: step: 940/529, loss: 0.0007128501893021166
2023-01-24 07:56:35.286598: step: 944/529, loss: 0.0011572977527976036
2023-01-24 07:56:36.323700: step: 948/529, loss: 0.0
2023-01-24 07:56:37.368944: step: 952/529, loss: 0.005213496740907431
2023-01-24 07:56:38.424418: step: 956/529, loss: 0.009229489602148533
2023-01-24 07:56:39.466109: step: 960/529, loss: 0.00018803254351951182
2023-01-24 07:56:40.522190: step: 964/529, loss: 1.0339845175622031e-06
2023-01-24 07:56:41.561310: step: 968/529, loss: 0.0019180604722350836
2023-01-24 07:56:42.595550: step: 972/529, loss: 0.0005541059072129428
2023-01-24 07:56:43.646068: step: 976/529, loss: 0.00013990083243697882
2023-01-24 07:56:44.696839: step: 980/529, loss: 0.003979128319770098
2023-01-24 07:56:45.737637: step: 984/529, loss: 0.00013347630738280714
2023-01-24 07:56:46.784332: step: 988/529, loss: 0.010431413538753986
2023-01-24 07:56:47.824368: step: 992/529, loss: 0.013405528850853443
2023-01-24 07:56:48.858425: step: 996/529, loss: 0.005670431535691023
2023-01-24 07:56:49.923745: step: 1000/529, loss: 4.412421549204737e-05
2023-01-24 07:56:50.987178: step: 1004/529, loss: 0.005037806462496519
2023-01-24 07:56:52.050114: step: 1008/529, loss: 0.013764195144176483
2023-01-24 07:56:53.092722: step: 1012/529, loss: 0.01303254347294569
2023-01-24 07:56:54.135854: step: 1016/529, loss: 0.0015644734958186746
2023-01-24 07:56:55.197418: step: 1020/529, loss: 0.015473760664463043
2023-01-24 07:56:56.268314: step: 1024/529, loss: 0.010308913886547089
2023-01-24 07:56:57.321142: step: 1028/529, loss: 0.00089548050891608
2023-01-24 07:56:58.368076: step: 1032/529, loss: 0.00725750345736742
2023-01-24 07:56:59.430809: step: 1036/529, loss: 9.78075186139904e-05
2023-01-24 07:57:00.463437: step: 1040/529, loss: 8.911739132599905e-05
2023-01-24 07:57:01.502536: step: 1044/529, loss: 0.0020880233496427536
2023-01-24 07:57:02.549355: step: 1048/529, loss: 0.0030502784065902233
2023-01-24 07:57:03.599706: step: 1052/529, loss: 2.607702498380604e-09
2023-01-24 07:57:04.638827: step: 1056/529, loss: 0.007089340128004551
2023-01-24 07:57:05.677068: step: 1060/529, loss: 0.0038894531317055225
2023-01-24 07:57:06.722247: step: 1064/529, loss: 0.0003203263331670314
2023-01-24 07:57:07.777890: step: 1068/529, loss: 0.00047433737199753523
2023-01-24 07:57:08.846112: step: 1072/529, loss: 0.0030498255509883165
2023-01-24 07:57:09.877381: step: 1076/529, loss: 0.00015224394155666232
2023-01-24 07:57:10.911333: step: 1080/529, loss: 0.0026026112027466297
2023-01-24 07:57:11.956437: step: 1084/529, loss: 0.006098547484725714
2023-01-24 07:57:12.999309: step: 1088/529, loss: 0.003093560691922903
2023-01-24 07:57:14.038034: step: 1092/529, loss: 0.006555825471878052
2023-01-24 07:57:15.073048: step: 1096/529, loss: 0.002913222648203373
2023-01-24 07:57:16.110244: step: 1100/529, loss: 0.0013297703117132187
2023-01-24 07:57:17.167916: step: 1104/529, loss: 0.0017203304450958967
2023-01-24 07:57:18.218930: step: 1108/529, loss: 0.007219015620648861
2023-01-24 07:57:19.280245: step: 1112/529, loss: 0.005297096446156502
2023-01-24 07:57:20.314957: step: 1116/529, loss: 0.005970312282443047
2023-01-24 07:57:21.359519: step: 1120/529, loss: 0.0008048623567447066
2023-01-24 07:57:22.410998: step: 1124/529, loss: 0.005152496043592691
2023-01-24 07:57:23.451948: step: 1128/529, loss: 0.006924059242010117
2023-01-24 07:57:24.485609: step: 1132/529, loss: 8.650627933093347e-06
2023-01-24 07:57:25.542939: step: 1136/529, loss: 0.003863108344376087
2023-01-24 07:57:26.584525: step: 1140/529, loss: 0.0020686748903244734
2023-01-24 07:57:27.633160: step: 1144/529, loss: 0.002790396334603429
2023-01-24 07:57:28.696234: step: 1148/529, loss: 0.0071144853718578815
2023-01-24 07:57:29.724896: step: 1152/529, loss: 0.00039947134791873395
2023-01-24 07:57:30.772420: step: 1156/529, loss: 0.003844982013106346
2023-01-24 07:57:31.804309: step: 1160/529, loss: 0.0016410565003752708
2023-01-24 07:57:32.847169: step: 1164/529, loss: 0.009676797315478325
2023-01-24 07:57:33.918219: step: 1168/529, loss: 0.001850215601734817
2023-01-24 07:57:34.967926: step: 1172/529, loss: 0.005094414576888084
2023-01-24 07:57:35.999436: step: 1176/529, loss: 0.00012213742593303323
2023-01-24 07:57:37.067042: step: 1180/529, loss: 0.0033602348994463682
2023-01-24 07:57:38.115470: step: 1184/529, loss: 0.0028793150559067726
2023-01-24 07:57:39.152566: step: 1188/529, loss: 4.4469630665844306e-05
2023-01-24 07:57:40.195983: step: 1192/529, loss: 0.01524511817842722
2023-01-24 07:57:41.226845: step: 1196/529, loss: 0.003424513852223754
2023-01-24 07:57:42.280837: step: 1200/529, loss: 0.018090898171067238
2023-01-24 07:57:43.325456: step: 1204/529, loss: 0.006048219744116068
2023-01-24 07:57:44.379806: step: 1208/529, loss: 0.010499890893697739
2023-01-24 07:57:45.425195: step: 1212/529, loss: 0.0007027279934845865
2023-01-24 07:57:46.475639: step: 1216/529, loss: 0.009670097380876541
2023-01-24 07:57:47.513055: step: 1220/529, loss: 0.0006043684552423656
2023-01-24 07:57:48.557860: step: 1224/529, loss: 0.008252520114183426
2023-01-24 07:57:49.605710: step: 1228/529, loss: 0.0016587678110226989
2023-01-24 07:57:50.664331: step: 1232/529, loss: 0.0037884386256337166
2023-01-24 07:57:51.703645: step: 1236/529, loss: 0.00356994173489511
2023-01-24 07:57:52.747025: step: 1240/529, loss: 0.004430616274476051
2023-01-24 07:57:53.796462: step: 1244/529, loss: 0.003589344909414649
2023-01-24 07:57:54.852765: step: 1248/529, loss: 0.0034834539983421564
2023-01-24 07:57:55.891482: step: 1252/529, loss: 0.0011686928337439895
2023-01-24 07:57:56.924041: step: 1256/529, loss: 0.00046972971176728606
2023-01-24 07:57:57.965467: step: 1260/529, loss: 0.0004676127282436937
2023-01-24 07:57:59.013769: step: 1264/529, loss: 0.002452847780659795
2023-01-24 07:58:00.064658: step: 1268/529, loss: 0.00738517427816987
2023-01-24 07:58:01.111316: step: 1272/529, loss: 0.0006423183949664235
2023-01-24 07:58:02.163160: step: 1276/529, loss: 0.0014510777546092868
2023-01-24 07:58:03.205649: step: 1280/529, loss: 0.002393566071987152
2023-01-24 07:58:04.255598: step: 1284/529, loss: 3.10423674818594e-05
2023-01-24 07:58:05.310651: step: 1288/529, loss: 7.145856943679973e-05
2023-01-24 07:58:06.359377: step: 1292/529, loss: 0.0017516142688691616
2023-01-24 07:58:07.422846: step: 1296/529, loss: 0.0008705674554221332
2023-01-24 07:58:08.465759: step: 1300/529, loss: 8.241000614361838e-05
2023-01-24 07:58:09.516088: step: 1304/529, loss: 0.006379532627761364
2023-01-24 07:58:10.568962: step: 1308/529, loss: 0.001797855831682682
2023-01-24 07:58:11.620158: step: 1312/529, loss: 0.0020840391516685486
2023-01-24 07:58:12.660919: step: 1316/529, loss: 0.005940550472587347
2023-01-24 07:58:13.699895: step: 1320/529, loss: 0.000661805912386626
2023-01-24 07:58:14.746716: step: 1324/529, loss: 0.0022622672840952873
2023-01-24 07:58:15.791704: step: 1328/529, loss: 0.012145286425948143
2023-01-24 07:58:16.836635: step: 1332/529, loss: 0.0002955519303213805
2023-01-24 07:58:17.884006: step: 1336/529, loss: 0.0020370502024888992
2023-01-24 07:58:18.928392: step: 1340/529, loss: 0.0025677757803350687
2023-01-24 07:58:19.985667: step: 1344/529, loss: 0.000634418916888535
2023-01-24 07:58:21.036113: step: 1348/529, loss: 0.004189720377326012
2023-01-24 07:58:22.088459: step: 1352/529, loss: 0.005921152886003256
2023-01-24 07:58:23.125163: step: 1356/529, loss: 0.0022508951369673014
2023-01-24 07:58:24.168367: step: 1360/529, loss: 0.00119803287088871
2023-01-24 07:58:25.212167: step: 1364/529, loss: 0.0036022388376295567
2023-01-24 07:58:26.251675: step: 1368/529, loss: 0.0006720342789776623
2023-01-24 07:58:27.288667: step: 1372/529, loss: 0.0022841556929051876
2023-01-24 07:58:28.334467: step: 1376/529, loss: 0.00012633096775971353
2023-01-24 07:58:29.387482: step: 1380/529, loss: 0.0010301998117938638
2023-01-24 07:58:30.429862: step: 1384/529, loss: 0.0014144123997539282
2023-01-24 07:58:31.472642: step: 1388/529, loss: 0.00037574220914393663
2023-01-24 07:58:32.530042: step: 1392/529, loss: 0.0001125840499298647
2023-01-24 07:58:33.580789: step: 1396/529, loss: 0.0015256714541465044
2023-01-24 07:58:34.657932: step: 1400/529, loss: 0.0010932701407000422
2023-01-24 07:58:35.707694: step: 1404/529, loss: 0.030305279418826103
2023-01-24 07:58:36.746759: step: 1408/529, loss: 0.00935385748744011
2023-01-24 07:58:37.804321: step: 1412/529, loss: 0.006787709891796112
2023-01-24 07:58:38.851834: step: 1416/529, loss: 6.2260933191282675e-06
2023-01-24 07:58:39.879378: step: 1420/529, loss: 0.00024706675321795046
2023-01-24 07:58:40.934894: step: 1424/529, loss: 0.0016209837049245834
2023-01-24 07:58:41.974837: step: 1428/529, loss: 0.00030261397478170693
2023-01-24 07:58:43.019904: step: 1432/529, loss: 0.000810148601885885
2023-01-24 07:58:44.066334: step: 1436/529, loss: 0.002890772419050336
2023-01-24 07:58:45.107803: step: 1440/529, loss: 0.0015610548434779048
2023-01-24 07:58:46.153821: step: 1444/529, loss: 0.003267600666731596
2023-01-24 07:58:47.185783: step: 1448/529, loss: 0.0009290831512771547
2023-01-24 07:58:48.239046: step: 1452/529, loss: 0.004930882249027491
2023-01-24 07:58:49.300127: step: 1456/529, loss: 0.0014959500404074788
2023-01-24 07:58:50.345218: step: 1460/529, loss: 0.001852201297879219
2023-01-24 07:58:51.378860: step: 1464/529, loss: 0.0013484645169228315
2023-01-24 07:58:52.422754: step: 1468/529, loss: 8.979537960840389e-05
2023-01-24 07:58:53.464190: step: 1472/529, loss: 0.0047757914289832115
2023-01-24 07:58:54.511353: step: 1476/529, loss: 0.0012093611294403672
2023-01-24 07:58:55.570254: step: 1480/529, loss: 0.006836912594735622
2023-01-24 07:58:56.615070: step: 1484/529, loss: 0.03023025020956993
2023-01-24 07:58:57.654695: step: 1488/529, loss: 0.0027947898488491774
2023-01-24 07:58:58.703546: step: 1492/529, loss: 0.0011901309480890632
2023-01-24 07:58:59.746230: step: 1496/529, loss: 0.00440404424443841
2023-01-24 07:59:00.815231: step: 1500/529, loss: 0.0022089453414082527
2023-01-24 07:59:01.859158: step: 1504/529, loss: 0.0015562280314043164
2023-01-24 07:59:02.900940: step: 1508/529, loss: 0.004183995071798563
2023-01-24 07:59:03.967388: step: 1512/529, loss: 0.0017055704956874251
2023-01-24 07:59:05.018479: step: 1516/529, loss: 0.0004223677678965032
2023-01-24 07:59:06.082314: step: 1520/529, loss: 0.00618738355115056
2023-01-24 07:59:07.124210: step: 1524/529, loss: 0.0017013464821502566
2023-01-24 07:59:08.174329: step: 1528/529, loss: 0.008293135091662407
2023-01-24 07:59:09.241229: step: 1532/529, loss: 0.0015210562851279974
2023-01-24 07:59:10.279297: step: 1536/529, loss: 0.00017991337517742068
2023-01-24 07:59:11.320002: step: 1540/529, loss: 0.0006232120795175433
2023-01-24 07:59:12.384315: step: 1544/529, loss: 0.0008592517697252333
2023-01-24 07:59:13.438577: step: 1548/529, loss: 0.00017508870223537087
2023-01-24 07:59:14.492738: step: 1552/529, loss: 0.0019115714821964502
2023-01-24 07:59:15.536949: step: 1556/529, loss: 0.007235506549477577
2023-01-24 07:59:16.572593: step: 1560/529, loss: 0.00026587743195705116
2023-01-24 07:59:17.627015: step: 1564/529, loss: 0.02108778990805149
2023-01-24 07:59:18.685278: step: 1568/529, loss: 0.0002542046713642776
2023-01-24 07:59:19.744637: step: 1572/529, loss: 0.043281376361846924
2023-01-24 07:59:20.808499: step: 1576/529, loss: 0.0018378469394519925
2023-01-24 07:59:21.842479: step: 1580/529, loss: 0.0005417782231234014
2023-01-24 07:59:22.890339: step: 1584/529, loss: 0.0037707893643528223
2023-01-24 07:59:23.933381: step: 1588/529, loss: 0.0007958101341500878
2023-01-24 07:59:24.994675: step: 1592/529, loss: 0.0039056213572621346
2023-01-24 07:59:26.055424: step: 1596/529, loss: 0.005149473436176777
2023-01-24 07:59:27.109357: step: 1600/529, loss: 0.01222204603254795
2023-01-24 07:59:28.151651: step: 1604/529, loss: 0.01026830356568098
2023-01-24 07:59:29.199175: step: 1608/529, loss: 0.0020108758471906185
2023-01-24 07:59:30.250568: step: 1612/529, loss: 0.0037760769482702017
2023-01-24 07:59:31.298859: step: 1616/529, loss: 0.0014027329161763191
2023-01-24 07:59:32.353437: step: 1620/529, loss: 0.0037235114723443985
2023-01-24 07:59:33.404896: step: 1624/529, loss: 0.003399776527658105
2023-01-24 07:59:34.450806: step: 1628/529, loss: 0.0009062264580279589
2023-01-24 07:59:35.500947: step: 1632/529, loss: 0.006494338158518076
2023-01-24 07:59:36.554979: step: 1636/529, loss: 0.0031147990375757217
2023-01-24 07:59:37.595891: step: 1640/529, loss: 0.0019699931144714355
2023-01-24 07:59:38.658198: step: 1644/529, loss: 0.00017522247799206525
2023-01-24 07:59:39.725592: step: 1648/529, loss: 0.009914258494973183
2023-01-24 07:59:40.764342: step: 1652/529, loss: 0.0004724213504232466
2023-01-24 07:59:41.826161: step: 1656/529, loss: 0.029571304097771645
2023-01-24 07:59:42.888329: step: 1660/529, loss: 0.003799635451287031
2023-01-24 07:59:43.943880: step: 1664/529, loss: 0.0020503555424511433
2023-01-24 07:59:45.009614: step: 1668/529, loss: 0.0030156716238707304
2023-01-24 07:59:46.073741: step: 1672/529, loss: 0.0007942665251903236
2023-01-24 07:59:47.114666: step: 1676/529, loss: 0.00023483762925025076
2023-01-24 07:59:48.177943: step: 1680/529, loss: 0.00456179678440094
2023-01-24 07:59:49.248230: step: 1684/529, loss: 0.00029944704147055745
2023-01-24 07:59:50.273679: step: 1688/529, loss: 0.004664743784815073
2023-01-24 07:59:51.329477: step: 1692/529, loss: 0.008343634195625782
2023-01-24 07:59:52.373707: step: 1696/529, loss: 0.006985554937273264
2023-01-24 07:59:53.428379: step: 1700/529, loss: 0.0020220025908201933
2023-01-24 07:59:54.483778: step: 1704/529, loss: 0.00547309685498476
2023-01-24 07:59:55.526529: step: 1708/529, loss: 0.001600018353201449
2023-01-24 07:59:56.602470: step: 1712/529, loss: 0.0012805818114429712
2023-01-24 07:59:57.658753: step: 1716/529, loss: 0.003580654039978981
2023-01-24 07:59:58.695729: step: 1720/529, loss: 0.0027319910004734993
2023-01-24 07:59:59.749980: step: 1724/529, loss: 0.006305277347564697
2023-01-24 08:00:00.814303: step: 1728/529, loss: 0.0007833088166080415
2023-01-24 08:00:01.885720: step: 1732/529, loss: 0.0032503888942301273
2023-01-24 08:00:02.927831: step: 1736/529, loss: 0.007268775720149279
2023-01-24 08:00:03.977485: step: 1740/529, loss: 0.003392603248357773
2023-01-24 08:00:05.023130: step: 1744/529, loss: 0.00544536579400301
2023-01-24 08:00:06.089611: step: 1748/529, loss: 0.0060477484948933125
2023-01-24 08:00:07.135792: step: 1752/529, loss: 0.002798511879518628
2023-01-24 08:00:08.178370: step: 1756/529, loss: 0.006484963931143284
2023-01-24 08:00:09.221886: step: 1760/529, loss: 0.004555354826152325
2023-01-24 08:00:10.264150: step: 1764/529, loss: 0.0005081974086351693
2023-01-24 08:00:11.326335: step: 1768/529, loss: 0.00535816652700305
2023-01-24 08:00:12.383824: step: 1772/529, loss: 0.00024211459094658494
2023-01-24 08:00:13.464718: step: 1776/529, loss: 0.004681541118770838
2023-01-24 08:00:14.509673: step: 1780/529, loss: 0.0004348951333668083
2023-01-24 08:00:15.563069: step: 1784/529, loss: 0.012286700308322906
2023-01-24 08:00:16.613204: step: 1788/529, loss: 0.010655753314495087
2023-01-24 08:00:17.653101: step: 1792/529, loss: 0.00028969047707505524
2023-01-24 08:00:18.705439: step: 1796/529, loss: 0.002627830719575286
2023-01-24 08:00:19.786633: step: 1800/529, loss: 0.001515217125415802
2023-01-24 08:00:20.840078: step: 1804/529, loss: 0.010236173868179321
2023-01-24 08:00:21.892080: step: 1808/529, loss: 0.001353904022835195
2023-01-24 08:00:22.956730: step: 1812/529, loss: 0.0016460255719721317
2023-01-24 08:00:24.033892: step: 1816/529, loss: 0.010405554436147213
2023-01-24 08:00:25.083951: step: 1820/529, loss: 0.0007682672585360706
2023-01-24 08:00:26.128629: step: 1824/529, loss: 0.011460606940090656
2023-01-24 08:00:27.177724: step: 1828/529, loss: 0.0007372607942670584
2023-01-24 08:00:28.236826: step: 1832/529, loss: 0.0008323192014358938
2023-01-24 08:00:29.263411: step: 1836/529, loss: 0.018875084817409515
2023-01-24 08:00:30.314701: step: 1840/529, loss: 0.0017271727556362748
2023-01-24 08:00:31.359275: step: 1844/529, loss: 0.017299069091677666
2023-01-24 08:00:32.390997: step: 1848/529, loss: 0.00012825964950025082
2023-01-24 08:00:33.433949: step: 1852/529, loss: 0.0035302641335874796
2023-01-24 08:00:34.493120: step: 1856/529, loss: 0.00363427447155118
2023-01-24 08:00:35.537916: step: 1860/529, loss: 0.004317414481192827
2023-01-24 08:00:36.592458: step: 1864/529, loss: 2.819651854224503e-05
2023-01-24 08:00:37.658521: step: 1868/529, loss: 0.00021076505072414875
2023-01-24 08:00:38.709928: step: 1872/529, loss: 0.0018988648662343621
2023-01-24 08:00:39.763860: step: 1876/529, loss: 0.02652699127793312
2023-01-24 08:00:40.834389: step: 1880/529, loss: 0.004440431483089924
2023-01-24 08:00:41.910670: step: 1884/529, loss: 0.006358923856168985
2023-01-24 08:00:42.961408: step: 1888/529, loss: 0.003089465433731675
2023-01-24 08:00:43.997624: step: 1892/529, loss: 0.0008446264546364546
2023-01-24 08:00:45.044285: step: 1896/529, loss: 0.0005855276831425726
2023-01-24 08:00:46.110740: step: 1900/529, loss: 0.004542219452559948
2023-01-24 08:00:47.164012: step: 1904/529, loss: 0.005437630694359541
2023-01-24 08:00:48.217865: step: 1908/529, loss: 0.0001455077581340447
2023-01-24 08:00:49.280931: step: 1912/529, loss: 0.0003511338436510414
2023-01-24 08:00:50.319147: step: 1916/529, loss: 0.004878541920334101
2023-01-24 08:00:51.381552: step: 1920/529, loss: 0.007897789590060711
2023-01-24 08:00:52.426631: step: 1924/529, loss: 0.00013669008330907673
2023-01-24 08:00:53.486684: step: 1928/529, loss: 3.771206320379861e-05
2023-01-24 08:00:54.534418: step: 1932/529, loss: 0.0010777936549857259
2023-01-24 08:00:55.561717: step: 1936/529, loss: 0.0012563636992126703
2023-01-24 08:00:56.601821: step: 1940/529, loss: 0.0006482333992607892
2023-01-24 08:00:57.647504: step: 1944/529, loss: 0.002654564566910267
2023-01-24 08:00:58.692065: step: 1948/529, loss: 0.0015561624895781279
2023-01-24 08:00:59.752014: step: 1952/529, loss: 0.002170481253415346
2023-01-24 08:01:00.806152: step: 1956/529, loss: 0.00042557946289889514
2023-01-24 08:01:01.857464: step: 1960/529, loss: 0.0014467902947217226
2023-01-24 08:01:02.900543: step: 1964/529, loss: 3.72021459043026e-05
2023-01-24 08:01:03.950323: step: 1968/529, loss: 0.0004619108804035932
2023-01-24 08:01:05.000364: step: 1972/529, loss: 0.0078103202395141125
2023-01-24 08:01:06.045714: step: 1976/529, loss: 2.5208486476913095e-05
2023-01-24 08:01:07.102567: step: 1980/529, loss: 0.0024055971298366785
2023-01-24 08:01:08.151068: step: 1984/529, loss: 0.0017308022361248732
2023-01-24 08:01:09.218951: step: 1988/529, loss: 0.0021961783058941364
2023-01-24 08:01:10.280517: step: 1992/529, loss: 0.004103126935660839
2023-01-24 08:01:11.329662: step: 1996/529, loss: 0.0026436406187713146
2023-01-24 08:01:12.376478: step: 2000/529, loss: 0.0019824618939310312
2023-01-24 08:01:13.434335: step: 2004/529, loss: 0.005595298949629068
2023-01-24 08:01:14.478968: step: 2008/529, loss: 0.001071313163265586
2023-01-24 08:01:15.532660: step: 2012/529, loss: 0.009003261104226112
2023-01-24 08:01:16.576833: step: 2016/529, loss: 0.05005432292819023
2023-01-24 08:01:17.635180: step: 2020/529, loss: 0.0026370352134108543
2023-01-24 08:01:18.668913: step: 2024/529, loss: 0.003142518224194646
2023-01-24 08:01:19.741502: step: 2028/529, loss: 0.005490990821272135
2023-01-24 08:01:20.818087: step: 2032/529, loss: 0.004497552756220102
2023-01-24 08:01:21.870563: step: 2036/529, loss: 0.009655139409005642
2023-01-24 08:01:22.919257: step: 2040/529, loss: 6.18443446001038e-05
2023-01-24 08:01:23.951048: step: 2044/529, loss: 0.0007054428569972515
2023-01-24 08:01:25.018188: step: 2048/529, loss: 0.004290977958589792
2023-01-24 08:01:26.053369: step: 2052/529, loss: 0.01048473734408617
2023-01-24 08:01:27.103282: step: 2056/529, loss: 0.00985910277813673
2023-01-24 08:01:28.164961: step: 2060/529, loss: 0.00368954217992723
2023-01-24 08:01:29.202668: step: 2064/529, loss: 2.9466292517099646e-07
2023-01-24 08:01:30.247656: step: 2068/529, loss: 0.01730327121913433
2023-01-24 08:01:31.292653: step: 2072/529, loss: 0.0021001403219997883
2023-01-24 08:01:32.350229: step: 2076/529, loss: 0.0007918146438896656
2023-01-24 08:01:33.394252: step: 2080/529, loss: 0.004450857173651457
2023-01-24 08:01:34.440277: step: 2084/529, loss: 0.010045414790511131
2023-01-24 08:01:35.486393: step: 2088/529, loss: 0.000921680883038789
2023-01-24 08:01:36.568437: step: 2092/529, loss: 0.0015958340372890234
2023-01-24 08:01:37.624621: step: 2096/529, loss: 0.0005397596978582442
2023-01-24 08:01:38.664560: step: 2100/529, loss: 0.006287833675742149
2023-01-24 08:01:39.703571: step: 2104/529, loss: 0.00022083580552134663
2023-01-24 08:01:40.752260: step: 2108/529, loss: 0.0034712550695985556
2023-01-24 08:01:41.805923: step: 2112/529, loss: 0.00458060996606946
2023-01-24 08:01:42.848471: step: 2116/529, loss: 0.01014195941388607
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3249717345038574, 'r': 0.33113818107888315, 'f1': 0.32802598012889367}, 'combined': 0.24170335377918478, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.37123092285501175, 'r': 0.3019085690234476, 'f1': 0.3330002118391443}, 'combined': 0.23427150581648346, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3595143312101911, 'r': 0.32131166982922205, 'f1': 0.3393411823647295}, 'combined': 0.25004087121611646, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39180278203231655, 'r': 0.3179551372513563, 'f1': 0.35103717465323153}, 'combined': 0.24923639400379438, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3783697272661208, 'r': 0.34175330204681875, 'f1': 0.35913058859157226}, 'combined': 0.2646225389622111, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3983562369892008, 'r': 0.3127705301775472, 'f1': 0.3504131673711267}, 'combined': 0.24879334883349996, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:04:12.404575: step: 4/529, loss: 0.02547350898385048
2023-01-24 08:04:13.436766: step: 8/529, loss: 0.0024359237868338823
2023-01-24 08:04:14.475935: step: 12/529, loss: 0.010536756366491318
2023-01-24 08:04:15.524063: step: 16/529, loss: 0.004394357558339834
2023-01-24 08:04:16.585760: step: 20/529, loss: 0.005176179111003876
2023-01-24 08:04:17.620602: step: 24/529, loss: 0.006142718717455864
2023-01-24 08:04:18.655336: step: 28/529, loss: 0.0014051987091079354
2023-01-24 08:04:19.703624: step: 32/529, loss: 0.002256381558254361
2023-01-24 08:04:20.716834: step: 36/529, loss: 0.00350232794880867
2023-01-24 08:04:21.764250: step: 40/529, loss: 5.2118579333182424e-05
2023-01-24 08:04:22.806580: step: 44/529, loss: 0.005257933400571346
2023-01-24 08:04:23.849774: step: 48/529, loss: 0.0021917736157774925
2023-01-24 08:04:24.880472: step: 52/529, loss: 0.0002937588142231107
2023-01-24 08:04:25.919117: step: 56/529, loss: 0.0036064530722796917
2023-01-24 08:04:26.957377: step: 60/529, loss: 0.008360263891518116
2023-01-24 08:04:27.991112: step: 64/529, loss: 0.0011056349612772465
2023-01-24 08:04:29.040299: step: 68/529, loss: 0.0011078242678195238
2023-01-24 08:04:30.072602: step: 72/529, loss: 0.003867167979478836
2023-01-24 08:04:31.111168: step: 76/529, loss: 0.0028319107368588448
2023-01-24 08:04:32.142839: step: 80/529, loss: 0.0055654821917414665
2023-01-24 08:04:33.179579: step: 84/529, loss: 0.0013121470110490918
2023-01-24 08:04:34.211747: step: 88/529, loss: 3.651808583526872e-05
2023-01-24 08:04:35.248238: step: 92/529, loss: 0.0029635934624820948
2023-01-24 08:04:36.275504: step: 96/529, loss: 0.0007521317456848919
2023-01-24 08:04:37.334576: step: 100/529, loss: 4.6694611228303984e-05
2023-01-24 08:04:38.386874: step: 104/529, loss: 0.006930282339453697
2023-01-24 08:04:39.429303: step: 108/529, loss: 0.01244620606303215
2023-01-24 08:04:40.449412: step: 112/529, loss: 0.00013211714394856244
2023-01-24 08:04:41.477892: step: 116/529, loss: 0.0009811338968575
2023-01-24 08:04:42.520708: step: 120/529, loss: 0.006453531328588724
2023-01-24 08:04:43.575683: step: 124/529, loss: 0.00013782500172965229
2023-01-24 08:04:44.619177: step: 128/529, loss: 0.0031705941073596478
2023-01-24 08:04:45.674800: step: 132/529, loss: 0.000844110909383744
2023-01-24 08:04:46.714508: step: 136/529, loss: 0.00041022332152351737
2023-01-24 08:04:47.747307: step: 140/529, loss: 0.003398698288947344
2023-01-24 08:04:48.790736: step: 144/529, loss: 0.0006233734311535954
2023-01-24 08:04:49.840009: step: 148/529, loss: 0.0002525327727198601
2023-01-24 08:04:50.873281: step: 152/529, loss: 0.001142202178016305
2023-01-24 08:04:51.912847: step: 156/529, loss: 0.00030284057720564306
2023-01-24 08:04:52.968281: step: 160/529, loss: 0.0012181728379800916
2023-01-24 08:04:54.000276: step: 164/529, loss: 0.01125998143106699
2023-01-24 08:04:55.050993: step: 168/529, loss: 0.0018623822834342718
2023-01-24 08:04:56.100561: step: 172/529, loss: 0.001834856579080224
2023-01-24 08:04:57.143875: step: 176/529, loss: 0.0
2023-01-24 08:04:58.192411: step: 180/529, loss: 0.017671937122941017
2023-01-24 08:04:59.218477: step: 184/529, loss: 0.0015418316470459104
2023-01-24 08:05:00.263314: step: 188/529, loss: 0.0037392976228147745
2023-01-24 08:05:01.320392: step: 192/529, loss: 0.010129069909453392
2023-01-24 08:05:02.367451: step: 196/529, loss: 9.772488556336612e-05
2023-01-24 08:05:03.407268: step: 200/529, loss: 0.0009238485945388675
2023-01-24 08:05:04.476101: step: 204/529, loss: 0.002464145887643099
2023-01-24 08:05:05.517716: step: 208/529, loss: 0.030568746849894524
2023-01-24 08:05:06.580157: step: 212/529, loss: 0.0010398138547316194
2023-01-24 08:05:07.644845: step: 216/529, loss: 0.002943401224911213
2023-01-24 08:05:08.692558: step: 220/529, loss: 0.0008004967239685357
2023-01-24 08:05:09.734478: step: 224/529, loss: 0.012237193062901497
2023-01-24 08:05:10.771260: step: 228/529, loss: 0.0064261299557983875
2023-01-24 08:05:11.825844: step: 232/529, loss: 0.001803913852199912
2023-01-24 08:05:12.867990: step: 236/529, loss: 0.0001677940017543733
2023-01-24 08:05:13.906205: step: 240/529, loss: 0.005809134803712368
2023-01-24 08:05:14.944144: step: 244/529, loss: 0.0031476204749196768
2023-01-24 08:05:15.994791: step: 248/529, loss: 0.0023658541031181812
2023-01-24 08:05:17.048142: step: 252/529, loss: 0.003516340861096978
2023-01-24 08:05:18.100994: step: 256/529, loss: 6.895070328027941e-06
2023-01-24 08:05:19.140353: step: 260/529, loss: 2.7178200980415568e-05
2023-01-24 08:05:20.201046: step: 264/529, loss: 0.002515393542125821
2023-01-24 08:05:21.278551: step: 268/529, loss: 0.0016364234033972025
2023-01-24 08:05:22.317925: step: 272/529, loss: 0.00437150988727808
2023-01-24 08:05:23.354638: step: 276/529, loss: 0.006446543149650097
2023-01-24 08:05:24.402746: step: 280/529, loss: 0.004683638922870159
2023-01-24 08:05:25.449497: step: 284/529, loss: 0.024891860783100128
2023-01-24 08:05:26.499820: step: 288/529, loss: 0.0013586105778813362
2023-01-24 08:05:27.546223: step: 292/529, loss: 0.00580563023686409
2023-01-24 08:05:28.591148: step: 296/529, loss: 0.0007761814049445093
2023-01-24 08:05:29.629681: step: 300/529, loss: 0.0007714795065112412
2023-01-24 08:05:30.679804: step: 304/529, loss: 0.00043657227070070803
2023-01-24 08:05:31.736573: step: 308/529, loss: 0.010554426349699497
2023-01-24 08:05:32.770179: step: 312/529, loss: 0.003605673788115382
2023-01-24 08:05:33.831618: step: 316/529, loss: 0.0010989387519657612
2023-01-24 08:05:34.865632: step: 320/529, loss: 0.0009404823067598045
2023-01-24 08:05:35.923959: step: 324/529, loss: 0.007967980578541756
2023-01-24 08:05:36.974468: step: 328/529, loss: 0.004060606472194195
2023-01-24 08:05:38.030477: step: 332/529, loss: 0.02769039385020733
2023-01-24 08:05:39.092203: step: 336/529, loss: 0.008088546805083752
2023-01-24 08:05:40.135792: step: 340/529, loss: 0.0007039580959826708
2023-01-24 08:05:41.203181: step: 344/529, loss: 0.0022395076230168343
2023-01-24 08:05:42.238889: step: 348/529, loss: 0.01384727843105793
2023-01-24 08:05:43.288758: step: 352/529, loss: 0.00398551020771265
2023-01-24 08:05:44.349838: step: 356/529, loss: 0.005353952292352915
2023-01-24 08:05:45.381565: step: 360/529, loss: 0.0175437293946743
2023-01-24 08:05:46.428923: step: 364/529, loss: 0.0021287009585648775
2023-01-24 08:05:47.469015: step: 368/529, loss: 0.007279746234416962
2023-01-24 08:05:48.529973: step: 372/529, loss: 0.005400799680501223
2023-01-24 08:05:49.587552: step: 376/529, loss: 0.0007781374733895063
2023-01-24 08:05:50.633324: step: 380/529, loss: 0.0069593945518136024
2023-01-24 08:05:51.683085: step: 384/529, loss: 0.008567679673433304
2023-01-24 08:05:52.744199: step: 388/529, loss: 0.0024873402435332537
2023-01-24 08:05:53.781388: step: 392/529, loss: 7.720361463725567e-05
2023-01-24 08:05:54.827253: step: 396/529, loss: 0.0021369722671806812
2023-01-24 08:05:55.869662: step: 400/529, loss: 0.002031546551734209
2023-01-24 08:05:56.903295: step: 404/529, loss: 0.017181765288114548
2023-01-24 08:05:57.953962: step: 408/529, loss: 0.008010189048945904
2023-01-24 08:05:58.992417: step: 412/529, loss: 0.005657844245433807
2023-01-24 08:06:00.010413: step: 416/529, loss: 0.002242745365947485
2023-01-24 08:06:01.095899: step: 420/529, loss: 0.00472149346023798
2023-01-24 08:06:02.143829: step: 424/529, loss: 0.002846792573109269
2023-01-24 08:06:03.184642: step: 428/529, loss: 0.0038022934459149837
2023-01-24 08:06:04.230329: step: 432/529, loss: 0.007306874729692936
2023-01-24 08:06:05.257629: step: 436/529, loss: 0.0017006334383040667
2023-01-24 08:06:06.301925: step: 440/529, loss: 0.00595502695068717
2023-01-24 08:06:07.330844: step: 444/529, loss: 0.0022472855634987354
2023-01-24 08:06:08.380386: step: 448/529, loss: 0.0021269740536808968
2023-01-24 08:06:09.441934: step: 452/529, loss: 0.006769747007638216
2023-01-24 08:06:10.489399: step: 456/529, loss: 0.002602675464004278
2023-01-24 08:06:11.535020: step: 460/529, loss: 0.007864139974117279
2023-01-24 08:06:12.598006: step: 464/529, loss: 0.0011239133309572935
2023-01-24 08:06:13.632477: step: 468/529, loss: 0.002571893623098731
2023-01-24 08:06:14.675266: step: 472/529, loss: 0.0008138378616422415
2023-01-24 08:06:15.722128: step: 476/529, loss: 0.0007387528312392533
2023-01-24 08:06:16.765571: step: 480/529, loss: 5.3386305808089674e-05
2023-01-24 08:06:17.800354: step: 484/529, loss: 0.0008478633244521916
2023-01-24 08:06:18.847492: step: 488/529, loss: 0.00877456646412611
2023-01-24 08:06:19.919429: step: 492/529, loss: 0.000730357482098043
2023-01-24 08:06:20.962741: step: 496/529, loss: 0.006803086493164301
2023-01-24 08:06:22.000684: step: 500/529, loss: 0.009922508150339127
2023-01-24 08:06:23.046326: step: 504/529, loss: 0.0013279798440635204
2023-01-24 08:06:24.085915: step: 508/529, loss: 0.004157001152634621
2023-01-24 08:06:25.126203: step: 512/529, loss: 0.0011677667498588562
2023-01-24 08:06:26.170602: step: 516/529, loss: 0.006929452531039715
2023-01-24 08:06:27.214383: step: 520/529, loss: 0.00869422871619463
2023-01-24 08:06:28.271993: step: 524/529, loss: 0.007221246603876352
2023-01-24 08:06:29.318035: step: 528/529, loss: 0.0027418616227805614
2023-01-24 08:06:30.366150: step: 532/529, loss: 0.00040890014497563243
2023-01-24 08:06:31.415500: step: 536/529, loss: 0.046654339879751205
2023-01-24 08:06:32.484614: step: 540/529, loss: 0.010836038738489151
2023-01-24 08:06:33.546592: step: 544/529, loss: 0.0014794718008488417
2023-01-24 08:06:34.598635: step: 548/529, loss: 0.00042480259435251355
2023-01-24 08:06:35.636149: step: 552/529, loss: 0.009522294625639915
2023-01-24 08:06:36.695219: step: 556/529, loss: 0.062240198254585266
2023-01-24 08:06:37.730902: step: 560/529, loss: 0.011479411274194717
2023-01-24 08:06:38.789611: step: 564/529, loss: 0.01005205325782299
2023-01-24 08:06:39.824581: step: 568/529, loss: 0.008391836658120155
2023-01-24 08:06:40.861086: step: 572/529, loss: 2.6581063139019534e-05
2023-01-24 08:06:41.906416: step: 576/529, loss: 0.00020754177239723504
2023-01-24 08:06:42.964449: step: 580/529, loss: 0.0021191900596022606
2023-01-24 08:06:44.015969: step: 584/529, loss: 0.0059251622296869755
2023-01-24 08:06:45.073843: step: 588/529, loss: 0.015873238444328308
2023-01-24 08:06:46.118006: step: 592/529, loss: 0.0022850006353110075
2023-01-24 08:06:47.154935: step: 596/529, loss: 0.009629203006625175
2023-01-24 08:06:48.203775: step: 600/529, loss: 0.0008775306050665677
2023-01-24 08:06:49.250249: step: 604/529, loss: 0.0015412142965942621
2023-01-24 08:06:50.292824: step: 608/529, loss: 0.002682688180357218
2023-01-24 08:06:51.329119: step: 612/529, loss: 0.00675795366987586
2023-01-24 08:06:52.376475: step: 616/529, loss: 0.0038627793546766043
2023-01-24 08:06:53.412140: step: 620/529, loss: 0.007737928070127964
2023-01-24 08:06:54.461065: step: 624/529, loss: 0.005158205982297659
2023-01-24 08:06:55.507048: step: 628/529, loss: 0.002522035501897335
2023-01-24 08:06:56.562266: step: 632/529, loss: 0.0022010558750480413
2023-01-24 08:06:57.602359: step: 636/529, loss: 0.007542647421360016
2023-01-24 08:06:58.646837: step: 640/529, loss: 0.006155920680612326
2023-01-24 08:06:59.696827: step: 644/529, loss: 0.0018787117442116141
2023-01-24 08:07:00.744536: step: 648/529, loss: 0.003504598280414939
2023-01-24 08:07:01.790050: step: 652/529, loss: 0.002860158681869507
2023-01-24 08:07:02.844714: step: 656/529, loss: 0.005974387284368277
2023-01-24 08:07:03.889680: step: 660/529, loss: 0.004573486279696226
2023-01-24 08:07:04.944562: step: 664/529, loss: 0.0013934510061517358
2023-01-24 08:07:06.006849: step: 668/529, loss: 0.002816671971231699
2023-01-24 08:07:07.048084: step: 672/529, loss: 0.00842900387942791
2023-01-24 08:07:08.084960: step: 676/529, loss: 3.678074062918313e-05
2023-01-24 08:07:09.134037: step: 680/529, loss: 0.007004658225923777
2023-01-24 08:07:10.174335: step: 684/529, loss: 0.0030656338203698397
2023-01-24 08:07:11.204983: step: 688/529, loss: 0.009362931363284588
2023-01-24 08:07:12.261331: step: 692/529, loss: 0.00020349063561297953
2023-01-24 08:07:13.297417: step: 696/529, loss: 0.0032213758677244186
2023-01-24 08:07:14.340492: step: 700/529, loss: 0.005186780821532011
2023-01-24 08:07:15.388439: step: 704/529, loss: 0.011361275799572468
2023-01-24 08:07:16.432723: step: 708/529, loss: 0.0035757229197770357
2023-01-24 08:07:17.476199: step: 712/529, loss: 0.04425759240984917
2023-01-24 08:07:18.540211: step: 716/529, loss: 0.0067059057764709
2023-01-24 08:07:19.576002: step: 720/529, loss: 0.006438928656280041
2023-01-24 08:07:20.599729: step: 724/529, loss: 0.00032496300991624594
2023-01-24 08:07:21.647258: step: 728/529, loss: 0.0012740223901346326
2023-01-24 08:07:22.683891: step: 732/529, loss: 0.007967410609126091
2023-01-24 08:07:23.737503: step: 736/529, loss: 0.005423595663160086
2023-01-24 08:07:24.789328: step: 740/529, loss: 0.007249068934470415
2023-01-24 08:07:25.817652: step: 744/529, loss: 0.007369640748947859
2023-01-24 08:07:26.871863: step: 748/529, loss: 0.0006447425112128258
2023-01-24 08:07:27.925344: step: 752/529, loss: 0.00011417798668844625
2023-01-24 08:07:28.976015: step: 756/529, loss: 0.00752163166180253
2023-01-24 08:07:30.033766: step: 760/529, loss: 0.0035515357740223408
2023-01-24 08:07:31.076809: step: 764/529, loss: 0.03446972742676735
2023-01-24 08:07:32.139887: step: 768/529, loss: 0.000921080878470093
2023-01-24 08:07:33.183763: step: 772/529, loss: 0.0012987533118575811
2023-01-24 08:07:34.230864: step: 776/529, loss: 0.004751041065901518
2023-01-24 08:07:35.261310: step: 780/529, loss: 0.007162058260291815
2023-01-24 08:07:36.289404: step: 784/529, loss: 0.0030342331156134605
2023-01-24 08:07:37.333035: step: 788/529, loss: 0.001183570479042828
2023-01-24 08:07:38.374377: step: 792/529, loss: 4.184794670436531e-05
2023-01-24 08:07:39.410057: step: 796/529, loss: 0.0
2023-01-24 08:07:40.441053: step: 800/529, loss: 0.007229954935610294
2023-01-24 08:07:41.507169: step: 804/529, loss: 0.0014380726497620344
2023-01-24 08:07:42.554694: step: 808/529, loss: 0.0007997100474312901
2023-01-24 08:07:43.632272: step: 812/529, loss: 0.02172614075243473
2023-01-24 08:07:44.700231: step: 816/529, loss: 0.0026660545263439417
2023-01-24 08:07:45.747534: step: 820/529, loss: 0.0014644160401076078
2023-01-24 08:07:46.787625: step: 824/529, loss: 0.00634665647521615
2023-01-24 08:07:47.815034: step: 828/529, loss: 0.0008031089673750103
2023-01-24 08:07:48.851098: step: 832/529, loss: 0.0011976719833910465
2023-01-24 08:07:49.924179: step: 836/529, loss: 6.576683517778292e-05
2023-01-24 08:07:50.964834: step: 840/529, loss: 0.015353788621723652
2023-01-24 08:07:52.002303: step: 844/529, loss: 0.0001090245132218115
2023-01-24 08:07:53.065905: step: 848/529, loss: 0.001465656328946352
2023-01-24 08:07:54.101592: step: 852/529, loss: 0.00026879823417402804
2023-01-24 08:07:55.141750: step: 856/529, loss: 0.0032660504803061485
2023-01-24 08:07:56.188420: step: 860/529, loss: 2.0073419364052825e-05
2023-01-24 08:07:57.235598: step: 864/529, loss: 0.004537275992333889
2023-01-24 08:07:58.304076: step: 868/529, loss: 0.0021819269750267267
2023-01-24 08:07:59.330220: step: 872/529, loss: 0.0001611022889846936
2023-01-24 08:08:00.360045: step: 876/529, loss: 0.00015540956519544125
2023-01-24 08:08:01.407956: step: 880/529, loss: 0.003966639284044504
2023-01-24 08:08:02.458947: step: 884/529, loss: 0.009977524168789387
2023-01-24 08:08:03.513448: step: 888/529, loss: 0.0008841767557896674
2023-01-24 08:08:04.551684: step: 892/529, loss: 0.004638585262000561
2023-01-24 08:08:05.593971: step: 896/529, loss: 0.002827602904289961
2023-01-24 08:08:06.636358: step: 900/529, loss: 0.007450871169567108
2023-01-24 08:08:07.684497: step: 904/529, loss: 0.007704949472099543
2023-01-24 08:08:08.742862: step: 908/529, loss: 0.0012313313782215118
2023-01-24 08:08:09.791739: step: 912/529, loss: 0.004235626198351383
2023-01-24 08:08:10.840108: step: 916/529, loss: 0.001037833048030734
2023-01-24 08:08:11.889078: step: 920/529, loss: 0.060191232711076736
2023-01-24 08:08:12.933299: step: 924/529, loss: 0.001633047591894865
2023-01-24 08:08:14.007626: step: 928/529, loss: 0.0011934576323255897
2023-01-24 08:08:15.056617: step: 932/529, loss: 0.0010923752561211586
2023-01-24 08:08:16.091922: step: 936/529, loss: 0.007551896385848522
2023-01-24 08:08:17.144573: step: 940/529, loss: 0.001908862846903503
2023-01-24 08:08:18.185551: step: 944/529, loss: 0.008333663456141949
2023-01-24 08:08:19.245294: step: 948/529, loss: 0.013990223407745361
2023-01-24 08:08:20.281023: step: 952/529, loss: 0.003981521353125572
2023-01-24 08:08:21.327472: step: 956/529, loss: 0.01204980444163084
2023-01-24 08:08:22.382807: step: 960/529, loss: 0.0024978260044008493
2023-01-24 08:08:23.428652: step: 964/529, loss: 0.0012541920877993107
2023-01-24 08:08:24.480700: step: 968/529, loss: 0.011120478622615337
2023-01-24 08:08:25.526127: step: 972/529, loss: 0.01642058975994587
2023-01-24 08:08:26.577897: step: 976/529, loss: 0.0008371184812858701
2023-01-24 08:08:27.617670: step: 980/529, loss: 0.0033924595918506384
2023-01-24 08:08:28.673418: step: 984/529, loss: 0.0605584979057312
2023-01-24 08:08:29.723984: step: 988/529, loss: 0.029489995911717415
2023-01-24 08:08:30.768555: step: 992/529, loss: 0.0028151371516287327
2023-01-24 08:08:31.826322: step: 996/529, loss: 0.0014346233801916242
2023-01-24 08:08:32.881414: step: 1000/529, loss: 0.005104742478579283
2023-01-24 08:08:33.938161: step: 1004/529, loss: 0.003330428386107087
2023-01-24 08:08:34.996696: step: 1008/529, loss: 0.00872800499200821
2023-01-24 08:08:36.044185: step: 1012/529, loss: 0.009540783241391182
2023-01-24 08:08:37.082815: step: 1016/529, loss: 0.012608298100531101
2023-01-24 08:08:38.137639: step: 1020/529, loss: 0.0002557553816586733
2023-01-24 08:08:39.171421: step: 1024/529, loss: 0.01341619249433279
2023-01-24 08:08:40.203670: step: 1028/529, loss: 0.0011868203291669488
2023-01-24 08:08:41.227445: step: 1032/529, loss: 0.00023331133706960827
2023-01-24 08:08:42.285437: step: 1036/529, loss: 0.021170977503061295
2023-01-24 08:08:43.330816: step: 1040/529, loss: 0.009980987757444382
2023-01-24 08:08:44.363244: step: 1044/529, loss: 0.00884020421653986
2023-01-24 08:08:45.400218: step: 1048/529, loss: 0.00028001322061754763
2023-01-24 08:08:46.444132: step: 1052/529, loss: 0.0014264644123613834
2023-01-24 08:08:47.490450: step: 1056/529, loss: 0.013133921660482883
2023-01-24 08:08:48.528869: step: 1060/529, loss: 0.00042832340113818645
2023-01-24 08:08:49.575581: step: 1064/529, loss: 0.001327728503383696
2023-01-24 08:08:50.621121: step: 1068/529, loss: 0.01047524530440569
2023-01-24 08:08:51.652880: step: 1072/529, loss: 0.00042269338155165315
2023-01-24 08:08:52.693797: step: 1076/529, loss: 0.0021684295497834682
2023-01-24 08:08:53.729477: step: 1080/529, loss: 0.020686794072389603
2023-01-24 08:08:54.784896: step: 1084/529, loss: 0.021807998418807983
2023-01-24 08:08:55.840374: step: 1088/529, loss: 0.014890799298882484
2023-01-24 08:08:56.880037: step: 1092/529, loss: 0.009047629311680794
2023-01-24 08:08:57.922830: step: 1096/529, loss: 0.009094939567148685
2023-01-24 08:08:58.965117: step: 1100/529, loss: 0.0036889223847538233
2023-01-24 08:09:00.036080: step: 1104/529, loss: 0.002958907512947917
2023-01-24 08:09:01.079050: step: 1108/529, loss: 0.00041549192974343896
2023-01-24 08:09:02.125229: step: 1112/529, loss: 0.000194278807612136
2023-01-24 08:09:03.162851: step: 1116/529, loss: 7.379856106126681e-05
2023-01-24 08:09:04.215249: step: 1120/529, loss: 4.395669748191722e-07
2023-01-24 08:09:05.266237: step: 1124/529, loss: 0.013221163302659988
2023-01-24 08:09:06.321337: step: 1128/529, loss: 0.02606922574341297
2023-01-24 08:09:07.365863: step: 1132/529, loss: 0.0003559020406100899
2023-01-24 08:09:08.403431: step: 1136/529, loss: 0.0002540110726840794
2023-01-24 08:09:09.444017: step: 1140/529, loss: 0.0008303250651806593
2023-01-24 08:09:10.495132: step: 1144/529, loss: 0.04103177785873413
2023-01-24 08:09:11.529709: step: 1148/529, loss: 0.00151734403334558
2023-01-24 08:09:12.595541: step: 1152/529, loss: 0.018841566517949104
2023-01-24 08:09:13.622324: step: 1156/529, loss: 0.0016617031069472432
2023-01-24 08:09:14.678634: step: 1160/529, loss: 0.0002569114731159061
2023-01-24 08:09:15.726984: step: 1164/529, loss: 0.00046839378774166107
2023-01-24 08:09:16.776970: step: 1168/529, loss: 0.0011505342554301023
2023-01-24 08:09:17.816259: step: 1172/529, loss: 0.006648893002420664
2023-01-24 08:09:18.864809: step: 1176/529, loss: 6.648615089943632e-05
2023-01-24 08:09:19.924283: step: 1180/529, loss: 0.008183448575437069
2023-01-24 08:09:20.968012: step: 1184/529, loss: 0.005855028983205557
2023-01-24 08:09:22.018160: step: 1188/529, loss: 0.0055140843614935875
2023-01-24 08:09:23.061686: step: 1192/529, loss: 0.0005517246900126338
2023-01-24 08:09:24.096956: step: 1196/529, loss: 0.0009113152627833188
2023-01-24 08:09:25.133085: step: 1200/529, loss: 2.0724279238493182e-05
2023-01-24 08:09:26.186585: step: 1204/529, loss: 0.04111278057098389
2023-01-24 08:09:27.237914: step: 1208/529, loss: 0.003848353633657098
2023-01-24 08:09:28.278261: step: 1212/529, loss: 0.005723903886973858
2023-01-24 08:09:29.318307: step: 1216/529, loss: 0.0015278341015800834
2023-01-24 08:09:30.369859: step: 1220/529, loss: 0.003078390145674348
2023-01-24 08:09:31.403588: step: 1224/529, loss: 0.00029825459932908416
2023-01-24 08:09:32.461551: step: 1228/529, loss: 0.006305004935711622
2023-01-24 08:09:33.494913: step: 1232/529, loss: 0.003038804279640317
2023-01-24 08:09:34.554984: step: 1236/529, loss: 0.019613297656178474
2023-01-24 08:09:35.591131: step: 1240/529, loss: 0.006205080542713404
2023-01-24 08:09:36.630800: step: 1244/529, loss: 0.002174819353967905
2023-01-24 08:09:37.680847: step: 1248/529, loss: 0.007180603686720133
2023-01-24 08:09:38.742138: step: 1252/529, loss: 0.011505067348480225
2023-01-24 08:09:39.783265: step: 1256/529, loss: 0.018739808350801468
2023-01-24 08:09:40.841827: step: 1260/529, loss: 0.007175636012107134
2023-01-24 08:09:41.876838: step: 1264/529, loss: 0.0007976465858519077
2023-01-24 08:09:42.932699: step: 1268/529, loss: 0.0011825715191662312
2023-01-24 08:09:43.974502: step: 1272/529, loss: 0.02307371236383915
2023-01-24 08:09:45.021120: step: 1276/529, loss: 0.0007031054701656103
2023-01-24 08:09:46.077952: step: 1280/529, loss: 0.004278052132576704
2023-01-24 08:09:47.113242: step: 1284/529, loss: 0.00021557587024290115
2023-01-24 08:09:48.168326: step: 1288/529, loss: 0.0046916864812374115
2023-01-24 08:09:49.249124: step: 1292/529, loss: 0.009935064241290092
2023-01-24 08:09:50.302118: step: 1296/529, loss: 3.562248093658127e-05
2023-01-24 08:09:51.356394: step: 1300/529, loss: 0.0010613743215799332
2023-01-24 08:09:52.409872: step: 1304/529, loss: 0.014720913954079151
2023-01-24 08:09:53.464099: step: 1308/529, loss: 0.0009182118810713291
2023-01-24 08:09:54.506543: step: 1312/529, loss: 0.0007193423807621002
2023-01-24 08:09:55.560994: step: 1316/529, loss: 0.0038255939725786448
2023-01-24 08:09:56.607165: step: 1320/529, loss: 0.0019312261138111353
2023-01-24 08:09:57.652925: step: 1324/529, loss: 0.0019026235677301884
2023-01-24 08:09:58.705858: step: 1328/529, loss: 0.03608163446187973
2023-01-24 08:09:59.742716: step: 1332/529, loss: 0.005005764774978161
2023-01-24 08:10:00.778767: step: 1336/529, loss: 0.003935342654585838
2023-01-24 08:10:01.821730: step: 1340/529, loss: 0.0024578962475061417
2023-01-24 08:10:02.880356: step: 1344/529, loss: 0.0019849329255521297
2023-01-24 08:10:03.927024: step: 1348/529, loss: 5.3696952818427235e-05
2023-01-24 08:10:04.971479: step: 1352/529, loss: 0.003461863612756133
2023-01-24 08:10:06.009841: step: 1356/529, loss: 0.00017433488392271101
2023-01-24 08:10:07.064866: step: 1360/529, loss: 0.005787468980997801
2023-01-24 08:10:08.126560: step: 1364/529, loss: 0.003369669895619154
2023-01-24 08:10:09.165858: step: 1368/529, loss: 0.00422493414953351
2023-01-24 08:10:10.226081: step: 1372/529, loss: 0.006990745663642883
2023-01-24 08:10:11.284420: step: 1376/529, loss: 0.008735550567507744
2023-01-24 08:10:12.348339: step: 1380/529, loss: 0.008439648896455765
2023-01-24 08:10:13.398630: step: 1384/529, loss: 0.005575504619628191
2023-01-24 08:10:14.445541: step: 1388/529, loss: 0.007669614627957344
2023-01-24 08:10:15.494744: step: 1392/529, loss: 0.002193581545725465
2023-01-24 08:10:16.553289: step: 1396/529, loss: 0.00018089528020936996
2023-01-24 08:10:17.605655: step: 1400/529, loss: 0.0005955706001259387
2023-01-24 08:10:18.645705: step: 1404/529, loss: 0.0010929397540166974
2023-01-24 08:10:19.704487: step: 1408/529, loss: 0.01696513593196869
2023-01-24 08:10:20.765803: step: 1412/529, loss: 0.014978902414441109
2023-01-24 08:10:21.825849: step: 1416/529, loss: 0.0025212853215634823
2023-01-24 08:10:22.872700: step: 1420/529, loss: 0.0011030887253582478
2023-01-24 08:10:23.919786: step: 1424/529, loss: 0.005700564943253994
2023-01-24 08:10:24.964610: step: 1428/529, loss: 0.003724184585735202
2023-01-24 08:10:26.020592: step: 1432/529, loss: 0.003426947630941868
2023-01-24 08:10:27.061794: step: 1436/529, loss: 0.008364698849618435
2023-01-24 08:10:28.115579: step: 1440/529, loss: 0.0014146262547001243
2023-01-24 08:10:29.165561: step: 1444/529, loss: 0.0006436764961108565
2023-01-24 08:10:30.220371: step: 1448/529, loss: 0.004170652944594622
2023-01-24 08:10:31.270965: step: 1452/529, loss: 0.0038733934052288532
2023-01-24 08:10:32.334698: step: 1456/529, loss: 0.009054483845829964
2023-01-24 08:10:33.397022: step: 1460/529, loss: 0.0011655604466795921
2023-01-24 08:10:34.442353: step: 1464/529, loss: 0.0017788042314350605
2023-01-24 08:10:35.480177: step: 1468/529, loss: 0.0019456666195765138
2023-01-24 08:10:36.519702: step: 1472/529, loss: 0.0035811972338706255
2023-01-24 08:10:37.562239: step: 1476/529, loss: 0.001796094817109406
2023-01-24 08:10:38.616585: step: 1480/529, loss: 0.0002110555360559374
2023-01-24 08:10:39.671153: step: 1484/529, loss: 3.618112896219827e-05
2023-01-24 08:10:40.726313: step: 1488/529, loss: 2.2881127733853646e-05
2023-01-24 08:10:41.794173: step: 1492/529, loss: 4.8986486945068464e-05
2023-01-24 08:10:42.869212: step: 1496/529, loss: 0.008576088584959507
2023-01-24 08:10:43.949573: step: 1500/529, loss: 0.0032493879552930593
2023-01-24 08:10:44.999941: step: 1504/529, loss: 0.004876949358731508
2023-01-24 08:10:46.048977: step: 1508/529, loss: 0.0013323853490874171
2023-01-24 08:10:47.106732: step: 1512/529, loss: 0.002135796006768942
2023-01-24 08:10:48.142779: step: 1516/529, loss: 1.8612987332744524e-05
2023-01-24 08:10:49.188896: step: 1520/529, loss: 0.009267893619835377
2023-01-24 08:10:50.246224: step: 1524/529, loss: 0.0032342039048671722
2023-01-24 08:10:51.311599: step: 1528/529, loss: 0.005769701674580574
2023-01-24 08:10:52.358444: step: 1532/529, loss: 0.008464229293167591
2023-01-24 08:10:53.421698: step: 1536/529, loss: 0.07072443515062332
2023-01-24 08:10:54.469389: step: 1540/529, loss: 0.005040166899561882
2023-01-24 08:10:55.514485: step: 1544/529, loss: 0.0010388904483988881
2023-01-24 08:10:56.570980: step: 1548/529, loss: 0.0021455856040120125
2023-01-24 08:10:57.637074: step: 1552/529, loss: 2.0178003978799097e-06
2023-01-24 08:10:58.697131: step: 1556/529, loss: 0.00013423204654827714
2023-01-24 08:10:59.754540: step: 1560/529, loss: 0.0010413069976493716
2023-01-24 08:11:00.812552: step: 1564/529, loss: 0.002832639729604125
2023-01-24 08:11:01.848439: step: 1568/529, loss: 0.0003754736972041428
2023-01-24 08:11:02.900590: step: 1572/529, loss: 0.007404036819934845
2023-01-24 08:11:03.934607: step: 1576/529, loss: 0.0008828699355944991
2023-01-24 08:11:04.979177: step: 1580/529, loss: 0.0003870359214488417
2023-01-24 08:11:06.023625: step: 1584/529, loss: 0.0023760509211570024
2023-01-24 08:11:07.070308: step: 1588/529, loss: 9.630201384425163e-05
2023-01-24 08:11:08.122573: step: 1592/529, loss: 0.005458700470626354
2023-01-24 08:11:09.185494: step: 1596/529, loss: 0.010021292604506016
2023-01-24 08:11:10.232998: step: 1600/529, loss: 0.002486381446942687
2023-01-24 08:11:11.276215: step: 1604/529, loss: 0.0083415936678648
2023-01-24 08:11:12.333882: step: 1608/529, loss: 0.008551139384508133
2023-01-24 08:11:13.399801: step: 1612/529, loss: 0.006925257854163647
2023-01-24 08:11:14.462709: step: 1616/529, loss: 0.005146630574017763
2023-01-24 08:11:15.515224: step: 1620/529, loss: 0.003973962739109993
2023-01-24 08:11:16.562580: step: 1624/529, loss: 0.0007142430986277759
2023-01-24 08:11:17.607410: step: 1628/529, loss: 0.0016972122248262167
2023-01-24 08:11:18.658373: step: 1632/529, loss: 0.004277615807950497
2023-01-24 08:11:19.716305: step: 1636/529, loss: 0.00030127615900710225
2023-01-24 08:11:20.759054: step: 1640/529, loss: 0.0039160898886621
2023-01-24 08:11:21.814056: step: 1644/529, loss: 0.0014413015451282263
2023-01-24 08:11:22.865693: step: 1648/529, loss: 0.00010024020593846217
2023-01-24 08:11:23.898622: step: 1652/529, loss: 0.004258297383785248
2023-01-24 08:11:24.950130: step: 1656/529, loss: 0.005418865941464901
2023-01-24 08:11:26.008818: step: 1660/529, loss: 0.007196826860308647
2023-01-24 08:11:27.074467: step: 1664/529, loss: 0.003028488950803876
2023-01-24 08:11:28.128013: step: 1668/529, loss: 0.00010984179971273988
2023-01-24 08:11:29.178145: step: 1672/529, loss: 0.0008404529071412981
2023-01-24 08:11:30.221332: step: 1676/529, loss: 0.00011003081453964114
2023-01-24 08:11:31.272305: step: 1680/529, loss: 0.0001030673083732836
2023-01-24 08:11:32.324133: step: 1684/529, loss: 0.000246745184995234
2023-01-24 08:11:33.394991: step: 1688/529, loss: 0.00010838175512617454
2023-01-24 08:11:34.429044: step: 1692/529, loss: 0.0009822645224630833
2023-01-24 08:11:35.479559: step: 1696/529, loss: 0.002012751530855894
2023-01-24 08:11:36.525994: step: 1700/529, loss: 6.477873102994636e-05
2023-01-24 08:11:37.586770: step: 1704/529, loss: 0.0005273003480397165
2023-01-24 08:11:38.623206: step: 1708/529, loss: 0.0054536545649170876
2023-01-24 08:11:39.666654: step: 1712/529, loss: 0.003672548569738865
2023-01-24 08:11:40.720121: step: 1716/529, loss: 3.28023852489423e-05
2023-01-24 08:11:41.770061: step: 1720/529, loss: 0.0010711478535085917
2023-01-24 08:11:42.818907: step: 1724/529, loss: 0.01713605411350727
2023-01-24 08:11:43.882003: step: 1728/529, loss: 0.0016306425677612424
2023-01-24 08:11:44.936639: step: 1732/529, loss: 0.005326485726982355
2023-01-24 08:11:46.004267: step: 1736/529, loss: 0.01241031289100647
2023-01-24 08:11:47.058977: step: 1740/529, loss: 0.000909050926566124
2023-01-24 08:11:48.121067: step: 1744/529, loss: 0.003233623458072543
2023-01-24 08:11:49.170335: step: 1748/529, loss: 0.006340848281979561
2023-01-24 08:11:50.214308: step: 1752/529, loss: 0.002494446001946926
2023-01-24 08:11:51.273630: step: 1756/529, loss: 6.975528231123462e-05
2023-01-24 08:11:52.318793: step: 1760/529, loss: 0.0044804723002016544
2023-01-24 08:11:53.385907: step: 1764/529, loss: 0.002811324317008257
2023-01-24 08:11:54.443676: step: 1768/529, loss: 0.014119782485067844
2023-01-24 08:11:55.473358: step: 1772/529, loss: 0.0007044809171929955
2023-01-24 08:11:56.529458: step: 1776/529, loss: 0.00011078844545409083
2023-01-24 08:11:57.562706: step: 1780/529, loss: 0.0009673495660535991
2023-01-24 08:11:58.616354: step: 1784/529, loss: 0.001845009857788682
2023-01-24 08:11:59.666073: step: 1788/529, loss: 0.00029794545844197273
2023-01-24 08:12:00.707913: step: 1792/529, loss: 5.079575566924177e-05
2023-01-24 08:12:01.746530: step: 1796/529, loss: 0.014804074540734291
2023-01-24 08:12:02.799751: step: 1800/529, loss: 0.0012412871001288295
2023-01-24 08:12:03.870850: step: 1804/529, loss: 0.018694493919610977
2023-01-24 08:12:04.930910: step: 1808/529, loss: 0.002348124049603939
2023-01-24 08:12:05.980711: step: 1812/529, loss: 0.00012574980792123824
2023-01-24 08:12:07.037379: step: 1816/529, loss: 0.002805741736665368
2023-01-24 08:12:08.109543: step: 1820/529, loss: 0.0022428843658417463
2023-01-24 08:12:09.156263: step: 1824/529, loss: 0.000614923716057092
2023-01-24 08:12:10.213626: step: 1828/529, loss: 0.001742077525705099
2023-01-24 08:12:11.267756: step: 1832/529, loss: 0.008281680755317211
2023-01-24 08:12:12.307770: step: 1836/529, loss: 0.005693594925105572
2023-01-24 08:12:13.349813: step: 1840/529, loss: 0.0005140280118212104
2023-01-24 08:12:14.401403: step: 1844/529, loss: 0.005766930989921093
2023-01-24 08:12:15.448939: step: 1848/529, loss: 0.000772569328546524
2023-01-24 08:12:16.499667: step: 1852/529, loss: 0.0020715140271931887
2023-01-24 08:12:17.551619: step: 1856/529, loss: 0.0030506481416523457
2023-01-24 08:12:18.609846: step: 1860/529, loss: 0.0015574651770293713
2023-01-24 08:12:19.674246: step: 1864/529, loss: 0.004971726797521114
2023-01-24 08:12:20.708573: step: 1868/529, loss: 0.0052582258358597755
2023-01-24 08:12:21.755348: step: 1872/529, loss: 0.013295542448759079
2023-01-24 08:12:22.816315: step: 1876/529, loss: 0.004197181202471256
2023-01-24 08:12:23.889531: step: 1880/529, loss: 0.0027576754800975323
2023-01-24 08:12:24.950984: step: 1884/529, loss: 0.003946739714592695
2023-01-24 08:12:25.999282: step: 1888/529, loss: 0.00249081919901073
2023-01-24 08:12:27.054999: step: 1892/529, loss: 0.0010628255549818277
2023-01-24 08:12:28.107927: step: 1896/529, loss: 0.000503671180922538
2023-01-24 08:12:29.156774: step: 1900/529, loss: 0.0081910640001297
2023-01-24 08:12:30.193942: step: 1904/529, loss: 0.00023846494150348008
2023-01-24 08:12:31.238664: step: 1908/529, loss: 0.0032240136060863733
2023-01-24 08:12:32.294071: step: 1912/529, loss: 0.012257558293640614
2023-01-24 08:12:33.342171: step: 1916/529, loss: 0.000457115878816694
2023-01-24 08:12:34.397217: step: 1920/529, loss: 0.0074079311452806
2023-01-24 08:12:35.438258: step: 1924/529, loss: 0.003005512058734894
2023-01-24 08:12:36.487371: step: 1928/529, loss: 0.004610523581504822
2023-01-24 08:12:37.538263: step: 1932/529, loss: 0.00012290927406866103
2023-01-24 08:12:38.580004: step: 1936/529, loss: 0.003614837070927024
2023-01-24 08:12:39.624221: step: 1940/529, loss: 0.004162222612649202
2023-01-24 08:12:40.663105: step: 1944/529, loss: 0.0025061958003789186
2023-01-24 08:12:41.718024: step: 1948/529, loss: 0.0016118192579597235
2023-01-24 08:12:42.766793: step: 1952/529, loss: 0.0035871940199285746
2023-01-24 08:12:43.808053: step: 1956/529, loss: 0.004990218207240105
2023-01-24 08:12:44.849948: step: 1960/529, loss: 0.007121474482119083
2023-01-24 08:12:45.890386: step: 1964/529, loss: 0.0031373086385428905
2023-01-24 08:12:46.930861: step: 1968/529, loss: 0.0021349869202822447
2023-01-24 08:12:47.991765: step: 1972/529, loss: 0.007196491584181786
2023-01-24 08:12:49.060695: step: 1976/529, loss: 0.008731399662792683
2023-01-24 08:12:50.102094: step: 1980/529, loss: 0.0022996803745627403
2023-01-24 08:12:51.135139: step: 1984/529, loss: 0.009347790852189064
2023-01-24 08:12:52.180473: step: 1988/529, loss: 0.002855120226740837
2023-01-24 08:12:53.218764: step: 1992/529, loss: 0.0009848474292084575
2023-01-24 08:12:54.281022: step: 1996/529, loss: 0.002582747722044587
2023-01-24 08:12:55.311530: step: 2000/529, loss: 3.786386514548212e-05
2023-01-24 08:12:56.366830: step: 2004/529, loss: 0.0004998651565983891
2023-01-24 08:12:57.416670: step: 2008/529, loss: 0.0010684020817279816
2023-01-24 08:12:58.455254: step: 2012/529, loss: 0.00010652600758476183
2023-01-24 08:12:59.500293: step: 2016/529, loss: 0.018018808215856552
2023-01-24 08:13:00.550319: step: 2020/529, loss: 0.0013210283359512687
2023-01-24 08:13:01.598863: step: 2024/529, loss: 0.0001975179329747334
2023-01-24 08:13:02.634855: step: 2028/529, loss: 0.004234502092003822
2023-01-24 08:13:03.687314: step: 2032/529, loss: 0.0004407464584801346
2023-01-24 08:13:04.731416: step: 2036/529, loss: 0.001212246366776526
2023-01-24 08:13:05.766897: step: 2040/529, loss: 0.000988429645076394
2023-01-24 08:13:06.834355: step: 2044/529, loss: 0.015469436533749104
2023-01-24 08:13:07.896864: step: 2048/529, loss: 0.002529177349060774
2023-01-24 08:13:08.945357: step: 2052/529, loss: 0.0005427937721833587
2023-01-24 08:13:09.989763: step: 2056/529, loss: 1.3922626749263145e-05
2023-01-24 08:13:11.028037: step: 2060/529, loss: 0.002548729069530964
2023-01-24 08:13:12.084033: step: 2064/529, loss: 0.001122251502238214
2023-01-24 08:13:13.134071: step: 2068/529, loss: 0.001024989876896143
2023-01-24 08:13:14.190699: step: 2072/529, loss: 0.00022314635862130672
2023-01-24 08:13:15.227746: step: 2076/529, loss: 8.953847282100469e-05
2023-01-24 08:13:16.253608: step: 2080/529, loss: 0.000566621427424252
2023-01-24 08:13:17.299839: step: 2084/529, loss: 0.0018103665206581354
2023-01-24 08:13:18.342707: step: 2088/529, loss: 0.0006287604919634759
2023-01-24 08:13:19.386174: step: 2092/529, loss: 0.0002173274988308549
2023-01-24 08:13:20.437808: step: 2096/529, loss: 0.0313841849565506
2023-01-24 08:13:21.497942: step: 2100/529, loss: 0.0014324260409921408
2023-01-24 08:13:22.542406: step: 2104/529, loss: 0.0011754590086638927
2023-01-24 08:13:23.599179: step: 2108/529, loss: 0.000206009965040721
2023-01-24 08:13:24.655278: step: 2112/529, loss: 0.006074794102460146
2023-01-24 08:13:25.688571: step: 2116/529, loss: 0.004383652005344629
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32455522486772487, 'r': 0.33256133098400653, 'f1': 0.3285095059579596}, 'combined': 0.24205963596902283, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3674755580481448, 'r': 0.29885446780180713, 'f1': 0.3296315881625322}, 'combined': 0.23190161981283672, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35656446540880504, 'r': 0.32273481973434537, 'f1': 0.33880727091633467}, 'combined': 0.2496474627804571, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39222925992527174, 'r': 0.3203547882112167, 'f1': 0.35266723082618096}, 'combined': 0.2503937338865885, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37887864054115794, 'r': 0.34365083525364987, 'f1': 0.3604059506043254}, 'combined': 0.2655622793926608, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39596917450365726, 'r': 0.3112421458980712, 'f1': 0.34853032474649537}, 'combined': 0.2474565305700117, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:15:55.833965: step: 4/529, loss: 0.0008352497825399041
2023-01-24 08:15:56.859166: step: 8/529, loss: 0.004078231751918793
2023-01-24 08:15:57.899793: step: 12/529, loss: 0.0013906897511333227
2023-01-24 08:15:58.941930: step: 16/529, loss: 0.00027968670474365354
2023-01-24 08:15:59.978490: step: 20/529, loss: 6.573928840225562e-05
2023-01-24 08:16:01.034376: step: 24/529, loss: 0.000341216626111418
2023-01-24 08:16:02.072358: step: 28/529, loss: 0.0004673922376241535
2023-01-24 08:16:03.116117: step: 32/529, loss: 0.00481852050870657
2023-01-24 08:16:04.162454: step: 36/529, loss: 0.0002737178292591125
2023-01-24 08:16:05.208653: step: 40/529, loss: 0.0001533913309685886
2023-01-24 08:16:06.233840: step: 44/529, loss: 0.0006647821865044534
2023-01-24 08:16:07.288086: step: 48/529, loss: 9.900423174258322e-05
2023-01-24 08:16:08.340088: step: 52/529, loss: 0.05244966223835945
2023-01-24 08:16:09.377458: step: 56/529, loss: 0.0017704941565170884
2023-01-24 08:16:10.404688: step: 60/529, loss: 0.02957840822637081
2023-01-24 08:16:11.438195: step: 64/529, loss: 0.00543832266703248
2023-01-24 08:16:12.482303: step: 68/529, loss: 0.005368039943277836
2023-01-24 08:16:13.522186: step: 72/529, loss: 0.008126365952193737
2023-01-24 08:16:14.555515: step: 76/529, loss: 0.0016023352509364486
2023-01-24 08:16:15.607776: step: 80/529, loss: 0.00793336983770132
2023-01-24 08:16:16.673969: step: 84/529, loss: 0.0010627913288772106
2023-01-24 08:16:17.736217: step: 88/529, loss: 0.0004878414620179683
2023-01-24 08:16:18.790487: step: 92/529, loss: 0.000876517326105386
2023-01-24 08:16:19.833728: step: 96/529, loss: 1.0525673133088276e-06
2023-01-24 08:16:20.863209: step: 100/529, loss: 0.00041814500582404435
2023-01-24 08:16:21.923337: step: 104/529, loss: 0.0010216075461357832
2023-01-24 08:16:22.966290: step: 108/529, loss: 0.024219796061515808
2023-01-24 08:16:24.021939: step: 112/529, loss: 0.002600511536002159
2023-01-24 08:16:25.074769: step: 116/529, loss: 0.00044134625932201743
2023-01-24 08:16:26.134053: step: 120/529, loss: 0.0047204033471643925
2023-01-24 08:16:27.185248: step: 124/529, loss: 0.014981193467974663
2023-01-24 08:16:28.227053: step: 128/529, loss: 8.036367944441736e-05
2023-01-24 08:16:29.273722: step: 132/529, loss: 0.002071731723845005
2023-01-24 08:16:30.312098: step: 136/529, loss: 0.0003172782016918063
2023-01-24 08:16:31.355422: step: 140/529, loss: 0.003152410266920924
2023-01-24 08:16:32.403000: step: 144/529, loss: 0.048385705798864365
2023-01-24 08:16:33.453848: step: 148/529, loss: 0.005180898122489452
2023-01-24 08:16:34.481802: step: 152/529, loss: 0.00030260326457209885
2023-01-24 08:16:35.524203: step: 156/529, loss: 0.00290667824447155
2023-01-24 08:16:36.568768: step: 160/529, loss: 0.004487393423914909
2023-01-24 08:16:37.606088: step: 164/529, loss: 0.0004990944289602339
2023-01-24 08:16:38.640847: step: 168/529, loss: 0.0006227202829904854
2023-01-24 08:16:39.672462: step: 172/529, loss: 9.849414345808327e-05
2023-01-24 08:16:40.720874: step: 176/529, loss: 0.004696741234511137
2023-01-24 08:16:41.763616: step: 180/529, loss: 0.0026739477179944515
2023-01-24 08:16:42.808728: step: 184/529, loss: 0.009527433663606644
2023-01-24 08:16:43.862641: step: 188/529, loss: 0.002856643171980977
2023-01-24 08:16:44.908288: step: 192/529, loss: 0.00040713392081670463
2023-01-24 08:16:45.956841: step: 196/529, loss: 0.0025559449568390846
2023-01-24 08:16:46.993830: step: 200/529, loss: 0.0034359805285930634
2023-01-24 08:16:48.028947: step: 204/529, loss: 0.0123750614002347
2023-01-24 08:16:49.076747: step: 208/529, loss: 0.01791662536561489
2023-01-24 08:16:50.109063: step: 212/529, loss: 4.506243203650229e-05
2023-01-24 08:16:51.133773: step: 216/529, loss: 0.0007484178058803082
2023-01-24 08:16:52.171368: step: 220/529, loss: 0.0033656363375484943
2023-01-24 08:16:53.218474: step: 224/529, loss: 0.00407741405069828
2023-01-24 08:16:54.266522: step: 228/529, loss: 0.0006752608460374177
2023-01-24 08:16:55.314543: step: 232/529, loss: 0.0016098516061902046
2023-01-24 08:16:56.366432: step: 236/529, loss: 0.016018150374293327
2023-01-24 08:16:57.415202: step: 240/529, loss: 6.399289850378409e-05
2023-01-24 08:16:58.473269: step: 244/529, loss: 0.00240446999669075
2023-01-24 08:16:59.527808: step: 248/529, loss: 0.0006661063525825739
2023-01-24 08:17:00.570618: step: 252/529, loss: 9.479092841502279e-05
2023-01-24 08:17:01.612846: step: 256/529, loss: 0.0013702742289751768
2023-01-24 08:17:02.654920: step: 260/529, loss: 5.1778410124825314e-05
2023-01-24 08:17:03.690872: step: 264/529, loss: 0.0004261040885467082
2023-01-24 08:17:04.719802: step: 268/529, loss: 0.0008805907564237714
2023-01-24 08:17:05.758704: step: 272/529, loss: 0.00448616174980998
2023-01-24 08:17:06.804011: step: 276/529, loss: 0.00040727463783696294
2023-01-24 08:17:07.839217: step: 280/529, loss: 0.005305705592036247
2023-01-24 08:17:08.878139: step: 284/529, loss: 0.016064930707216263
2023-01-24 08:17:09.922829: step: 288/529, loss: 0.008089309558272362
2023-01-24 08:17:10.970433: step: 292/529, loss: 0.0012017115950584412
2023-01-24 08:17:12.014922: step: 296/529, loss: 0.00027334154583513737
2023-01-24 08:17:13.048838: step: 300/529, loss: 0.00013047060929238796
2023-01-24 08:17:14.088441: step: 304/529, loss: 0.00014351372374221683
2023-01-24 08:17:15.144226: step: 308/529, loss: 0.0010556101333349943
2023-01-24 08:17:16.188704: step: 312/529, loss: 0.0018022399162873626
2023-01-24 08:17:17.242474: step: 316/529, loss: 8.848635479807854e-05
2023-01-24 08:17:18.269818: step: 320/529, loss: 0.0022214234340935946
2023-01-24 08:17:19.317389: step: 324/529, loss: 0.0008178128045983613
2023-01-24 08:17:20.362982: step: 328/529, loss: 0.0081281503662467
2023-01-24 08:17:21.423612: step: 332/529, loss: 0.004785628989338875
2023-01-24 08:17:22.457345: step: 336/529, loss: 0.0004804731288459152
2023-01-24 08:17:23.496646: step: 340/529, loss: 2.2609745428781025e-05
2023-01-24 08:17:24.544413: step: 344/529, loss: 0.0034750434570014477
2023-01-24 08:17:25.577968: step: 348/529, loss: 0.0018449969356879592
2023-01-24 08:17:26.623692: step: 352/529, loss: 0.002631227020174265
2023-01-24 08:17:27.652861: step: 356/529, loss: 0.00014063646085560322
2023-01-24 08:17:28.692256: step: 360/529, loss: 0.0004171330656390637
2023-01-24 08:17:29.712722: step: 364/529, loss: 0.002189196180552244
2023-01-24 08:17:30.753957: step: 368/529, loss: 0.004228558856993914
2023-01-24 08:17:31.803718: step: 372/529, loss: 0.019063761457800865
2023-01-24 08:17:32.850973: step: 376/529, loss: 0.0009880102006718516
2023-01-24 08:17:33.918034: step: 380/529, loss: 0.010479042306542397
2023-01-24 08:17:34.958700: step: 384/529, loss: 0.0027219983749091625
2023-01-24 08:17:35.993535: step: 388/529, loss: 0.0005921715637668967
2023-01-24 08:17:37.040209: step: 392/529, loss: 0.004992567002773285
2023-01-24 08:17:38.080431: step: 396/529, loss: 0.008218024857342243
2023-01-24 08:17:39.122708: step: 400/529, loss: 5.4673455451847985e-05
2023-01-24 08:17:40.168797: step: 404/529, loss: 0.0011151168728247285
2023-01-24 08:17:41.218237: step: 408/529, loss: 0.006082640960812569
2023-01-24 08:17:42.284119: step: 412/529, loss: 0.0007668251055292785
2023-01-24 08:17:43.333334: step: 416/529, loss: 0.0020557192619889975
2023-01-24 08:17:44.388087: step: 420/529, loss: 0.004256993066519499
2023-01-24 08:17:45.445853: step: 424/529, loss: 0.005285164806991816
2023-01-24 08:17:46.499835: step: 428/529, loss: 0.0007947867270559072
2023-01-24 08:17:47.551398: step: 432/529, loss: 0.0017105155857279897
2023-01-24 08:17:48.587218: step: 436/529, loss: 0.002169121755287051
2023-01-24 08:17:49.649457: step: 440/529, loss: 0.003915147855877876
2023-01-24 08:17:50.687300: step: 444/529, loss: 5.4450207244371995e-05
2023-01-24 08:17:51.726436: step: 448/529, loss: 0.0067147123627364635
2023-01-24 08:17:52.787737: step: 452/529, loss: 0.0001681046123849228
2023-01-24 08:17:53.832733: step: 456/529, loss: 0.002292748773470521
2023-01-24 08:17:54.876890: step: 460/529, loss: 0.005784038919955492
2023-01-24 08:17:55.918114: step: 464/529, loss: 0.012059425003826618
2023-01-24 08:17:56.958523: step: 468/529, loss: 0.004067446570843458
2023-01-24 08:17:58.008108: step: 472/529, loss: 0.002616090001538396
2023-01-24 08:17:59.062762: step: 476/529, loss: 0.0029812497086822987
2023-01-24 08:18:00.112997: step: 480/529, loss: 0.0012229267740622163
2023-01-24 08:18:01.161057: step: 484/529, loss: 0.000983092817477882
2023-01-24 08:18:02.204894: step: 488/529, loss: 0.0017438458744436502
2023-01-24 08:18:03.237219: step: 492/529, loss: 0.0007921059732325375
2023-01-24 08:18:04.272755: step: 496/529, loss: 0.007515037432312965
2023-01-24 08:18:05.312386: step: 500/529, loss: 0.002744954079389572
2023-01-24 08:18:06.369532: step: 504/529, loss: 0.004854784347116947
2023-01-24 08:18:07.425241: step: 508/529, loss: 0.0002995973627548665
2023-01-24 08:18:08.468098: step: 512/529, loss: 0.0030475344974547625
2023-01-24 08:18:09.502683: step: 516/529, loss: 3.5621828828880098e-06
2023-01-24 08:18:10.543392: step: 520/529, loss: 0.000995233771391213
2023-01-24 08:18:11.585769: step: 524/529, loss: 0.007095505017787218
2023-01-24 08:18:12.638398: step: 528/529, loss: 0.0015335733769461513
2023-01-24 08:18:13.682174: step: 532/529, loss: 0.0002862678375095129
2023-01-24 08:18:14.716056: step: 536/529, loss: 0.0022908649407327175
2023-01-24 08:18:15.758417: step: 540/529, loss: 0.0026858216151595116
2023-01-24 08:18:16.799233: step: 544/529, loss: 0.0034945036750286818
2023-01-24 08:18:17.837434: step: 548/529, loss: 0.00019250012701377273
2023-01-24 08:18:18.903095: step: 552/529, loss: 0.008986166678369045
2023-01-24 08:18:19.950687: step: 556/529, loss: 0.004181261174380779
2023-01-24 08:18:20.990208: step: 560/529, loss: 0.005867184139788151
2023-01-24 08:18:22.031023: step: 564/529, loss: 0.0009576360462233424
2023-01-24 08:18:23.066610: step: 568/529, loss: 0.00015088755753822625
2023-01-24 08:18:24.127885: step: 572/529, loss: 0.008697553537786007
2023-01-24 08:18:25.168707: step: 576/529, loss: 0.0022136373445391655
2023-01-24 08:18:26.223731: step: 580/529, loss: 0.012643320485949516
2023-01-24 08:18:27.261651: step: 584/529, loss: 0.008251936174929142
2023-01-24 08:18:28.307180: step: 588/529, loss: 0.00020720501197502017
2023-01-24 08:18:29.368372: step: 592/529, loss: 0.00682100560516119
2023-01-24 08:18:30.408373: step: 596/529, loss: 9.279289952246472e-05
2023-01-24 08:18:31.463369: step: 600/529, loss: 0.018781989812850952
2023-01-24 08:18:32.515364: step: 604/529, loss: 0.0048301187343895435
2023-01-24 08:18:33.561748: step: 608/529, loss: 0.007250762544572353
2023-01-24 08:18:34.608862: step: 612/529, loss: 0.0010262010619044304
2023-01-24 08:18:35.649445: step: 616/529, loss: 0.0006206289981491864
2023-01-24 08:18:36.691504: step: 620/529, loss: 0.00022213127522263676
2023-01-24 08:18:37.733342: step: 624/529, loss: 0.0050963144749403
2023-01-24 08:18:38.762541: step: 628/529, loss: 0.0033172564581036568
2023-01-24 08:18:39.800966: step: 632/529, loss: 0.0030756439082324505
2023-01-24 08:18:40.833128: step: 636/529, loss: 0.005096208769828081
2023-01-24 08:18:41.878254: step: 640/529, loss: 0.002249770564958453
2023-01-24 08:18:42.937841: step: 644/529, loss: 0.008157442323863506
2023-01-24 08:18:43.991373: step: 648/529, loss: 0.0012797346571460366
2023-01-24 08:18:45.036691: step: 652/529, loss: 0.0005326832761056721
2023-01-24 08:18:46.086020: step: 656/529, loss: 0.00044118391815572977
2023-01-24 08:18:47.117521: step: 660/529, loss: 0.0005492839845828712
2023-01-24 08:18:48.155289: step: 664/529, loss: 0.0018050550715997815
2023-01-24 08:18:49.222837: step: 668/529, loss: 0.004495986737310886
2023-01-24 08:18:50.253226: step: 672/529, loss: 0.004443437326699495
2023-01-24 08:18:51.293550: step: 676/529, loss: 0.00021187537640798837
2023-01-24 08:18:52.332370: step: 680/529, loss: 4.35755355283618e-05
2023-01-24 08:18:53.365790: step: 684/529, loss: 3.831455251201987e-05
2023-01-24 08:18:54.410942: step: 688/529, loss: 4.212204657960683e-05
2023-01-24 08:18:55.444739: step: 692/529, loss: 0.007300470490008593
2023-01-24 08:18:56.510503: step: 696/529, loss: 0.0007477918989025056
2023-01-24 08:18:57.559988: step: 700/529, loss: 0.0037029797676950693
2023-01-24 08:18:58.599307: step: 704/529, loss: 0.005753783974796534
2023-01-24 08:18:59.662771: step: 708/529, loss: 0.0029113520868122578
2023-01-24 08:19:00.700384: step: 712/529, loss: 0.002503064926713705
2023-01-24 08:19:01.761869: step: 716/529, loss: 0.004338518250733614
2023-01-24 08:19:02.816550: step: 720/529, loss: 0.010502398014068604
2023-01-24 08:19:03.840339: step: 724/529, loss: 1.895812965813093e-05
2023-01-24 08:19:04.881922: step: 728/529, loss: 0.009539663791656494
2023-01-24 08:19:05.920872: step: 732/529, loss: 0.000875416211783886
2023-01-24 08:19:06.962419: step: 736/529, loss: 0.00022103587980382144
2023-01-24 08:19:08.012458: step: 740/529, loss: 0.0003958956222049892
2023-01-24 08:19:09.058245: step: 744/529, loss: 0.0006257392815314233
2023-01-24 08:19:10.116077: step: 748/529, loss: 0.007873651571571827
2023-01-24 08:19:11.162827: step: 752/529, loss: 0.0070301988162100315
2023-01-24 08:19:12.221348: step: 756/529, loss: 7.34411587473005e-05
2023-01-24 08:19:13.254203: step: 760/529, loss: 5.6964319810504094e-05
2023-01-24 08:19:14.291801: step: 764/529, loss: 0.0012240585638210177
2023-01-24 08:19:15.325637: step: 768/529, loss: 0.0002077206881949678
2023-01-24 08:19:16.367761: step: 772/529, loss: 0.0017296469304710627
2023-01-24 08:19:17.415484: step: 776/529, loss: 0.002311060903593898
2023-01-24 08:19:18.460714: step: 780/529, loss: 0.0025948307011276484
2023-01-24 08:19:19.539380: step: 784/529, loss: 0.004161428660154343
2023-01-24 08:19:20.579117: step: 788/529, loss: 0.005635375622659922
2023-01-24 08:19:21.611303: step: 792/529, loss: 0.00011246439680689946
2023-01-24 08:19:22.646752: step: 796/529, loss: 0.01886409893631935
2023-01-24 08:19:23.684457: step: 800/529, loss: 0.009209426119923592
2023-01-24 08:19:24.759111: step: 804/529, loss: 0.004663406405597925
2023-01-24 08:19:25.800886: step: 808/529, loss: 0.0011369960848242044
2023-01-24 08:19:26.841725: step: 812/529, loss: 0.0016129232244566083
2023-01-24 08:19:27.904107: step: 816/529, loss: 1.2793821952072904e-05
2023-01-24 08:19:28.958259: step: 820/529, loss: 0.0019323163433000445
2023-01-24 08:19:30.009430: step: 824/529, loss: 0.001820737379603088
2023-01-24 08:19:31.061924: step: 828/529, loss: 0.0008540013805031776
2023-01-24 08:19:32.102391: step: 832/529, loss: 0.0005600686999969184
2023-01-24 08:19:33.166153: step: 836/529, loss: 0.0010771576780825853
2023-01-24 08:19:34.210218: step: 840/529, loss: 0.00017267640214413404
2023-01-24 08:19:35.264184: step: 844/529, loss: 0.0029180734418332577
2023-01-24 08:19:36.306380: step: 848/529, loss: 0.0013812831602990627
2023-01-24 08:19:37.355758: step: 852/529, loss: 4.473709395824699e-06
2023-01-24 08:19:38.396678: step: 856/529, loss: 0.008165249601006508
2023-01-24 08:19:39.440667: step: 860/529, loss: 0.01582416333258152
2023-01-24 08:19:40.487295: step: 864/529, loss: 0.007594390772283077
2023-01-24 08:19:41.520919: step: 868/529, loss: 0.012652688659727573
2023-01-24 08:19:42.552899: step: 872/529, loss: 0.003081762697547674
2023-01-24 08:19:43.598691: step: 876/529, loss: 0.0009592437418177724
2023-01-24 08:19:44.652067: step: 880/529, loss: 0.0037696349900215864
2023-01-24 08:19:45.714362: step: 884/529, loss: 0.001623764750547707
2023-01-24 08:19:46.749530: step: 888/529, loss: 0.0001962757669389248
2023-01-24 08:19:47.779597: step: 892/529, loss: 0.0008244204218499362
2023-01-24 08:19:48.826801: step: 896/529, loss: 0.009198804385960102
2023-01-24 08:19:49.871207: step: 900/529, loss: 0.0005498820100910962
2023-01-24 08:19:50.918323: step: 904/529, loss: 0.006923763547092676
2023-01-24 08:19:51.970473: step: 908/529, loss: 2.6771653210744262e-05
2023-01-24 08:19:53.035522: step: 912/529, loss: 0.004113171715289354
2023-01-24 08:19:54.071784: step: 916/529, loss: 0.0010723625309765339
2023-01-24 08:19:55.134156: step: 920/529, loss: 0.006901412270963192
2023-01-24 08:19:56.198003: step: 924/529, loss: 0.008161801844835281
2023-01-24 08:19:57.243587: step: 928/529, loss: 2.9370366974035278e-05
2023-01-24 08:19:58.286548: step: 932/529, loss: 0.0035291474778205156
2023-01-24 08:19:59.333112: step: 936/529, loss: 0.002092214999720454
2023-01-24 08:20:00.392591: step: 940/529, loss: 0.0022200271487236023
2023-01-24 08:20:01.447184: step: 944/529, loss: 0.0048616607673466206
2023-01-24 08:20:02.502656: step: 948/529, loss: 0.007801448460668325
2023-01-24 08:20:03.536118: step: 952/529, loss: 0.0025164796970784664
2023-01-24 08:20:04.575781: step: 956/529, loss: 0.0007975324988365173
2023-01-24 08:20:05.621753: step: 960/529, loss: 0.0019139735959470272
2023-01-24 08:20:06.679750: step: 964/529, loss: 0.0012918042484670877
2023-01-24 08:20:07.731426: step: 968/529, loss: 0.002581177279353142
2023-01-24 08:20:08.780770: step: 972/529, loss: 4.3875129307480165e-08
2023-01-24 08:20:09.829522: step: 976/529, loss: 0.0031610054429620504
2023-01-24 08:20:10.859243: step: 980/529, loss: 0.0027935670223087072
2023-01-24 08:20:11.906776: step: 984/529, loss: 0.0070877536199986935
2023-01-24 08:20:12.960973: step: 988/529, loss: 0.008069803938269615
2023-01-24 08:20:14.025579: step: 992/529, loss: 0.014591886661946774
2023-01-24 08:20:15.071996: step: 996/529, loss: 0.0009630898712202907
2023-01-24 08:20:16.120561: step: 1000/529, loss: 0.0002405676495982334
2023-01-24 08:20:17.171003: step: 1004/529, loss: 0.009807177819311619
2023-01-24 08:20:18.221746: step: 1008/529, loss: 0.0001440555352019146
2023-01-24 08:20:19.296132: step: 1012/529, loss: 0.0021732975728809834
2023-01-24 08:20:20.360345: step: 1016/529, loss: 0.004840366542339325
2023-01-24 08:20:21.426076: step: 1020/529, loss: 0.0037037923466414213
2023-01-24 08:20:22.470929: step: 1024/529, loss: 0.0032236503902822733
2023-01-24 08:20:23.540309: step: 1028/529, loss: 0.0033569352235645056
2023-01-24 08:20:24.588671: step: 1032/529, loss: 0.0007555480115115643
2023-01-24 08:20:25.646942: step: 1036/529, loss: 0.0208508912473917
2023-01-24 08:20:26.690181: step: 1040/529, loss: 0.003467023139819503
2023-01-24 08:20:27.732205: step: 1044/529, loss: 0.011952086351811886
2023-01-24 08:20:28.789835: step: 1048/529, loss: 4.5896860683569685e-05
2023-01-24 08:20:29.838516: step: 1052/529, loss: 0.00658138794824481
2023-01-24 08:20:30.900468: step: 1056/529, loss: 0.01360861025750637
2023-01-24 08:20:31.956990: step: 1060/529, loss: 0.00710264453664422
2023-01-24 08:20:32.995584: step: 1064/529, loss: 0.0019593273755162954
2023-01-24 08:20:34.040690: step: 1068/529, loss: 0.0005734366714023054
2023-01-24 08:20:35.099138: step: 1072/529, loss: 0.005368330050259829
2023-01-24 08:20:36.153269: step: 1076/529, loss: 0.0037115546874701977
2023-01-24 08:20:37.199144: step: 1080/529, loss: 0.01065273117274046
2023-01-24 08:20:38.236764: step: 1084/529, loss: 0.0006542496848851442
2023-01-24 08:20:39.299558: step: 1088/529, loss: 7.731306686764583e-05
2023-01-24 08:20:40.353053: step: 1092/529, loss: 3.200436549377628e-05
2023-01-24 08:20:41.420727: step: 1096/529, loss: 0.0020976027008146048
2023-01-24 08:20:42.466564: step: 1100/529, loss: 0.0013106416445225477
2023-01-24 08:20:43.528040: step: 1104/529, loss: 0.006252394989132881
2023-01-24 08:20:44.582882: step: 1108/529, loss: 0.0016766333719715476
2023-01-24 08:20:45.627018: step: 1112/529, loss: 0.0037892102263867855
2023-01-24 08:20:46.689994: step: 1116/529, loss: 0.0030038889963179827
2023-01-24 08:20:47.735117: step: 1120/529, loss: 0.001456426689401269
2023-01-24 08:20:48.777836: step: 1124/529, loss: 0.00023112937924452126
2023-01-24 08:20:49.808049: step: 1128/529, loss: 0.004987484775483608
2023-01-24 08:20:50.881550: step: 1132/529, loss: 0.012704534456133842
2023-01-24 08:20:51.925516: step: 1136/529, loss: 0.0033161386381834745
2023-01-24 08:20:52.960961: step: 1140/529, loss: 0.0005040763062424958
2023-01-24 08:20:54.009315: step: 1144/529, loss: 0.0011770855635404587
2023-01-24 08:20:55.050853: step: 1148/529, loss: 0.0043403953313827515
2023-01-24 08:20:56.095899: step: 1152/529, loss: 0.01647000201046467
2023-01-24 08:20:57.151317: step: 1156/529, loss: 1.9293385776109062e-05
2023-01-24 08:20:58.214584: step: 1160/529, loss: 0.0037687825970351696
2023-01-24 08:20:59.255399: step: 1164/529, loss: 0.002070172457024455
2023-01-24 08:21:00.301518: step: 1168/529, loss: 0.000909997324924916
2023-01-24 08:21:01.346007: step: 1172/529, loss: 6.248754743864993e-06
2023-01-24 08:21:02.398848: step: 1176/529, loss: 0.00039893900975584984
2023-01-24 08:21:03.459457: step: 1180/529, loss: 0.006092698313295841
2023-01-24 08:21:04.502165: step: 1184/529, loss: 0.0043531786650419235
2023-01-24 08:21:05.568570: step: 1188/529, loss: 0.00520012341439724
2023-01-24 08:21:06.636529: step: 1192/529, loss: 0.006355540826916695
2023-01-24 08:21:07.684424: step: 1196/529, loss: 0.0020271993707865477
2023-01-24 08:21:08.741023: step: 1200/529, loss: 0.004707496613264084
2023-01-24 08:21:09.786468: step: 1204/529, loss: 1.0801390999404248e-05
2023-01-24 08:21:10.845648: step: 1208/529, loss: 8.091667405096814e-05
2023-01-24 08:21:11.897184: step: 1212/529, loss: 0.0008515420486219227
2023-01-24 08:21:12.946564: step: 1216/529, loss: 0.00017601822037249804
2023-01-24 08:21:14.009094: step: 1220/529, loss: 0.0030931856017559767
2023-01-24 08:21:15.062954: step: 1224/529, loss: 0.0029360740445554256
2023-01-24 08:21:16.116083: step: 1228/529, loss: 7.156916581152473e-06
2023-01-24 08:21:17.165763: step: 1232/529, loss: 0.002061406848952174
2023-01-24 08:21:18.213764: step: 1236/529, loss: 0.004107621032744646
2023-01-24 08:21:19.292991: step: 1240/529, loss: 0.0031285628210753202
2023-01-24 08:21:20.356114: step: 1244/529, loss: 0.000600891828071326
2023-01-24 08:21:21.391635: step: 1248/529, loss: 0.00016651688201818615
2023-01-24 08:21:22.442426: step: 1252/529, loss: 0.013147317804396152
2023-01-24 08:21:23.485174: step: 1256/529, loss: 0.0021729725413024426
2023-01-24 08:21:24.522668: step: 1260/529, loss: 0.0029413981828838587
2023-01-24 08:21:25.566799: step: 1264/529, loss: 0.0028131473809480667
2023-01-24 08:21:26.618611: step: 1268/529, loss: 9.685465192887932e-05
2023-01-24 08:21:27.677479: step: 1272/529, loss: 0.0002806572592817247
2023-01-24 08:21:28.716131: step: 1276/529, loss: 0.006952605210244656
2023-01-24 08:21:29.761292: step: 1280/529, loss: 0.0052100555039942265
2023-01-24 08:21:30.810165: step: 1284/529, loss: 1.157667429652065e-05
2023-01-24 08:21:31.863532: step: 1288/529, loss: 0.00551730627194047
2023-01-24 08:21:32.915343: step: 1292/529, loss: 0.001863752375356853
2023-01-24 08:21:33.959723: step: 1296/529, loss: 0.008507753722369671
2023-01-24 08:21:35.009678: step: 1300/529, loss: 5.0377650040900335e-05
2023-01-24 08:21:36.063609: step: 1304/529, loss: 0.00025106253451667726
2023-01-24 08:21:37.108786: step: 1308/529, loss: 0.0002420292585156858
2023-01-24 08:21:38.145354: step: 1312/529, loss: 1.1386105143174063e-05
2023-01-24 08:21:39.204378: step: 1316/529, loss: 4.4861601054435596e-05
2023-01-24 08:21:40.277168: step: 1320/529, loss: 0.0041152373887598515
2023-01-24 08:21:41.316849: step: 1324/529, loss: 0.000209692312637344
2023-01-24 08:21:42.377745: step: 1328/529, loss: 0.0008439704542979598
2023-01-24 08:21:43.450847: step: 1332/529, loss: 0.0011212762910872698
2023-01-24 08:21:44.476644: step: 1336/529, loss: 0.0019543522503226995
2023-01-24 08:21:45.521452: step: 1340/529, loss: 0.0012216477189213037
2023-01-24 08:21:46.587734: step: 1344/529, loss: 0.007631693501025438
2023-01-24 08:21:47.642843: step: 1348/529, loss: 0.0019851881079375744
2023-01-24 08:21:48.692483: step: 1352/529, loss: 0.003368675010278821
2023-01-24 08:21:49.749780: step: 1356/529, loss: 4.534842446446419e-05
2023-01-24 08:21:50.793905: step: 1360/529, loss: 0.002428041072562337
2023-01-24 08:21:51.839569: step: 1364/529, loss: 3.295796341262758e-05
2023-01-24 08:21:52.907252: step: 1368/529, loss: 0.010210973210632801
2023-01-24 08:21:53.950041: step: 1372/529, loss: 0.007162292953580618
2023-01-24 08:21:55.040305: step: 1376/529, loss: 0.002224746160209179
2023-01-24 08:21:56.114971: step: 1380/529, loss: 0.002603420987725258
2023-01-24 08:21:57.157987: step: 1384/529, loss: 0.0013631234178319573
2023-01-24 08:21:58.214424: step: 1388/529, loss: 0.0019771484658122063
2023-01-24 08:21:59.261337: step: 1392/529, loss: 0.002403853926807642
2023-01-24 08:22:00.313676: step: 1396/529, loss: 0.002271877368912101
2023-01-24 08:22:01.395792: step: 1400/529, loss: 0.012783573009073734
2023-01-24 08:22:02.460670: step: 1404/529, loss: 7.497885962948203e-05
2023-01-24 08:22:03.509134: step: 1408/529, loss: 0.0012927278876304626
2023-01-24 08:22:04.557443: step: 1412/529, loss: 0.006812716368585825
2023-01-24 08:22:05.601413: step: 1416/529, loss: 0.0003691313322633505
2023-01-24 08:22:06.660183: step: 1420/529, loss: 0.0034026389475911856
2023-01-24 08:22:07.714273: step: 1424/529, loss: 0.0026886307168751955
2023-01-24 08:22:08.782161: step: 1428/529, loss: 0.0037182399537414312
2023-01-24 08:22:09.823656: step: 1432/529, loss: 0.0065586017444729805
2023-01-24 08:22:10.861422: step: 1436/529, loss: 0.0014909732853993773
2023-01-24 08:22:11.946881: step: 1440/529, loss: 0.00020075227075722069
2023-01-24 08:22:13.002510: step: 1444/529, loss: 0.0
2023-01-24 08:22:14.058418: step: 1448/529, loss: 0.003260991768911481
2023-01-24 08:22:15.102806: step: 1452/529, loss: 0.00022431010438594967
2023-01-24 08:22:16.163373: step: 1456/529, loss: 0.0075931241735816
2023-01-24 08:22:17.225705: step: 1460/529, loss: 0.0035737031139433384
2023-01-24 08:22:18.270106: step: 1464/529, loss: 0.001429764204658568
2023-01-24 08:22:19.324579: step: 1468/529, loss: 0.00016408709052484483
2023-01-24 08:22:20.376176: step: 1472/529, loss: 0.0003474982804618776
2023-01-24 08:22:21.462523: step: 1476/529, loss: 0.0017152386717498302
2023-01-24 08:22:22.525587: step: 1480/529, loss: 0.002597115933895111
2023-01-24 08:22:23.560458: step: 1484/529, loss: 0.00594564201310277
2023-01-24 08:22:24.617291: step: 1488/529, loss: 8.28837655717507e-05
2023-01-24 08:22:25.651756: step: 1492/529, loss: 0.010234294459223747
2023-01-24 08:22:26.715494: step: 1496/529, loss: 0.01666048727929592
2023-01-24 08:22:27.764112: step: 1500/529, loss: 0.0038576407823711634
2023-01-24 08:22:28.810455: step: 1504/529, loss: 0.0024879348929971457
2023-01-24 08:22:29.875243: step: 1508/529, loss: 0.0016234299400821328
2023-01-24 08:22:30.924175: step: 1512/529, loss: 0.0023737314622849226
2023-01-24 08:22:31.978863: step: 1516/529, loss: 0.004893099889159203
2023-01-24 08:22:33.018669: step: 1520/529, loss: 5.415095074567944e-05
2023-01-24 08:22:34.101107: step: 1524/529, loss: 0.004278518725186586
2023-01-24 08:22:35.158162: step: 1528/529, loss: 0.00717477360740304
2023-01-24 08:22:36.214603: step: 1532/529, loss: 0.006437546107918024
2023-01-24 08:22:37.278640: step: 1536/529, loss: 0.005547700449824333
2023-01-24 08:22:38.344296: step: 1540/529, loss: 0.0010556257329881191
2023-01-24 08:22:39.388362: step: 1544/529, loss: 2.8790680062229512e-06
2023-01-24 08:22:40.443142: step: 1548/529, loss: 0.002369623864069581
2023-01-24 08:22:41.489623: step: 1552/529, loss: 3.2628628105157986e-05
2023-01-24 08:22:42.549304: step: 1556/529, loss: 0.024006646126508713
2023-01-24 08:22:43.593059: step: 1560/529, loss: 0.004097315948456526
2023-01-24 08:22:44.636431: step: 1564/529, loss: 0.0011803561355918646
2023-01-24 08:22:45.705437: step: 1568/529, loss: 0.0070240069180727005
2023-01-24 08:22:46.773473: step: 1572/529, loss: 0.001090403413400054
2023-01-24 08:22:47.816461: step: 1576/529, loss: 0.00019787046767305583
2023-01-24 08:22:48.859970: step: 1580/529, loss: 0.001648088451474905
2023-01-24 08:22:49.932162: step: 1584/529, loss: 0.003295780858024955
2023-01-24 08:22:50.977835: step: 1588/529, loss: 0.004932744894176722
2023-01-24 08:22:52.024536: step: 1592/529, loss: 0.0005097811808809638
2023-01-24 08:22:53.075309: step: 1596/529, loss: 1.440069991076598e-05
2023-01-24 08:22:54.123711: step: 1600/529, loss: 0.0012152633862569928
2023-01-24 08:22:55.173289: step: 1604/529, loss: 6.642210337304277e-06
2023-01-24 08:22:56.222494: step: 1608/529, loss: 0.0035081172827631235
2023-01-24 08:22:57.283151: step: 1612/529, loss: 0.0024415708612650633
2023-01-24 08:22:58.339909: step: 1616/529, loss: 0.0010083145461976528
2023-01-24 08:22:59.390244: step: 1620/529, loss: 6.086014036554843e-05
2023-01-24 08:23:00.450992: step: 1624/529, loss: 0.0040126279927790165
2023-01-24 08:23:01.517097: step: 1628/529, loss: 0.00014069178723730147
2023-01-24 08:23:02.571583: step: 1632/529, loss: 0.0022944877855479717
2023-01-24 08:23:03.648261: step: 1636/529, loss: 0.004165433347225189
2023-01-24 08:23:04.704416: step: 1640/529, loss: 0.014277707785367966
2023-01-24 08:23:05.760882: step: 1644/529, loss: 0.0001579952222527936
2023-01-24 08:23:06.810550: step: 1648/529, loss: 0.0016477806493639946
2023-01-24 08:23:07.879428: step: 1652/529, loss: 0.002662413753569126
2023-01-24 08:23:08.919679: step: 1656/529, loss: 7.163675945776049e-07
2023-01-24 08:23:09.957740: step: 1660/529, loss: 7.214298966573551e-05
2023-01-24 08:23:11.001903: step: 1664/529, loss: 0.0007739229477010667
2023-01-24 08:23:12.048782: step: 1668/529, loss: 0.0004776465939357877
2023-01-24 08:23:13.132180: step: 1672/529, loss: 0.00014145145541988313
2023-01-24 08:23:14.184219: step: 1676/529, loss: 0.00013233826030045748
2023-01-24 08:23:15.250254: step: 1680/529, loss: 0.004139878787100315
2023-01-24 08:23:16.315673: step: 1684/529, loss: 9.499406417035061e-08
2023-01-24 08:23:17.378526: step: 1688/529, loss: 0.0009501029853709042
2023-01-24 08:23:18.438252: step: 1692/529, loss: 0.0049570901319384575
2023-01-24 08:23:19.498680: step: 1696/529, loss: 0.001914069289341569
2023-01-24 08:23:20.572319: step: 1700/529, loss: 0.0016323172021657228
2023-01-24 08:23:21.610348: step: 1704/529, loss: 7.966714474605396e-05
2023-01-24 08:23:22.668775: step: 1708/529, loss: 0.0038385128136724234
2023-01-24 08:23:23.708646: step: 1712/529, loss: 0.007875789888203144
2023-01-24 08:23:24.760344: step: 1716/529, loss: 0.000277939805528149
2023-01-24 08:23:25.818193: step: 1720/529, loss: 1.9125598555547185e-05
2023-01-24 08:23:26.881529: step: 1724/529, loss: 0.000593114469666034
2023-01-24 08:23:27.937811: step: 1728/529, loss: 0.012972467578947544
2023-01-24 08:23:29: step: 1732/529, loss: 0.008414629846811295
2023-01-24 08:23:30.066057: step: 1736/529, loss: 0.0006538414163514972
2023-01-24 08:23:31.122658: step: 1740/529, loss: 0.006761146243661642
2023-01-24 08:23:32.179051: step: 1744/529, loss: 0.00873110443353653
2023-01-24 08:23:33.221964: step: 1748/529, loss: 0.0006710360175929964
2023-01-24 08:23:34.297850: step: 1752/529, loss: 0.010579305700957775
2023-01-24 08:23:35.341166: step: 1756/529, loss: 0.004736666101962328
2023-01-24 08:23:36.413731: step: 1760/529, loss: 0.0031256123911589384
2023-01-24 08:23:37.463273: step: 1764/529, loss: 0.0005983375012874603
2023-01-24 08:23:38.505982: step: 1768/529, loss: 0.006297392770648003
2023-01-24 08:23:39.537702: step: 1772/529, loss: 0.00025753394584171474
2023-01-24 08:23:40.605527: step: 1776/529, loss: 0.007904550060629845
2023-01-24 08:23:41.664511: step: 1780/529, loss: 0.0018922050949186087
2023-01-24 08:23:42.719289: step: 1784/529, loss: 0.004244326148182154
2023-01-24 08:23:43.757766: step: 1788/529, loss: 0.00033448083559051156
2023-01-24 08:23:44.811133: step: 1792/529, loss: 0.002368123969063163
2023-01-24 08:23:45.851602: step: 1796/529, loss: 6.148507236503065e-05
2023-01-24 08:23:46.903297: step: 1800/529, loss: 0.00037344664451666176
2023-01-24 08:23:47.957186: step: 1804/529, loss: 0.0019409320084378123
2023-01-24 08:23:49.002815: step: 1808/529, loss: 0.0010393742704764009
2023-01-24 08:23:50.064637: step: 1812/529, loss: 0.0020587670151144266
2023-01-24 08:23:51.134207: step: 1816/529, loss: 0.0007704040035605431
2023-01-24 08:23:52.204087: step: 1820/529, loss: 0.002932679606601596
2023-01-24 08:23:53.242181: step: 1824/529, loss: 0.0
2023-01-24 08:23:54.292833: step: 1828/529, loss: 0.01196280587464571
2023-01-24 08:23:55.367085: step: 1832/529, loss: 9.895335824694484e-05
2023-01-24 08:23:56.426905: step: 1836/529, loss: 0.005144460126757622
2023-01-24 08:23:57.475226: step: 1840/529, loss: 0.0016843825578689575
2023-01-24 08:23:58.536345: step: 1844/529, loss: 0.0007539439829997718
2023-01-24 08:23:59.589555: step: 1848/529, loss: 0.0038900652434676886
2023-01-24 08:24:00.654137: step: 1852/529, loss: 0.0004884360823780298
2023-01-24 08:24:01.705304: step: 1856/529, loss: 0.001202086452394724
2023-01-24 08:24:02.748794: step: 1860/529, loss: 0.0013118046335875988
2023-01-24 08:24:03.809873: step: 1864/529, loss: 0.001143162720836699
2023-01-24 08:24:04.856159: step: 1868/529, loss: 0.002513331128284335
2023-01-24 08:24:05.929224: step: 1872/529, loss: 0.003349148202687502
2023-01-24 08:24:06.986214: step: 1876/529, loss: 0.003546215360984206
2023-01-24 08:24:08.054300: step: 1880/529, loss: 0.0010163020342588425
2023-01-24 08:24:09.114153: step: 1884/529, loss: 0.0037165971007198095
2023-01-24 08:24:10.144891: step: 1888/529, loss: 0.00022542655642610043
2023-01-24 08:24:11.183297: step: 1892/529, loss: 0.0008177642012014985
2023-01-24 08:24:12.248723: step: 1896/529, loss: 0.00025068718241527677
2023-01-24 08:24:13.323071: step: 1900/529, loss: 0.003530950751155615
2023-01-24 08:24:14.363354: step: 1904/529, loss: 0.0011494796490296721
2023-01-24 08:24:15.405474: step: 1908/529, loss: 0.0011248602531850338
2023-01-24 08:24:16.459198: step: 1912/529, loss: 0.00185218988917768
2023-01-24 08:24:17.499687: step: 1916/529, loss: 0.000301682623103261
2023-01-24 08:24:18.572511: step: 1920/529, loss: 0.0006263204268179834
2023-01-24 08:24:19.605757: step: 1924/529, loss: 0.004094806965440512
2023-01-24 08:24:20.665510: step: 1928/529, loss: 0.002375388750806451
2023-01-24 08:24:21.731732: step: 1932/529, loss: 0.00980651006102562
2023-01-24 08:24:22.783629: step: 1936/529, loss: 0.00040529455873183906
2023-01-24 08:24:23.820434: step: 1940/529, loss: 4.1402134229429066e-05
2023-01-24 08:24:24.864334: step: 1944/529, loss: 0.005306723993271589
2023-01-24 08:24:25.934506: step: 1948/529, loss: 0.00018188105605076998
2023-01-24 08:24:26.981372: step: 1952/529, loss: 0.004576907027512789
2023-01-24 08:24:28.042317: step: 1956/529, loss: 0.002825178438797593
2023-01-24 08:24:29.124198: step: 1960/529, loss: 0.00822812132537365
2023-01-24 08:24:30.183445: step: 1964/529, loss: 0.018383197486400604
2023-01-24 08:24:31.230931: step: 1968/529, loss: 0.003967686556279659
2023-01-24 08:24:32.303239: step: 1972/529, loss: 0.008985044434666634
2023-01-24 08:24:33.345073: step: 1976/529, loss: 0.0038528938312083483
2023-01-24 08:24:34.402724: step: 1980/529, loss: 0.003997777123004198
2023-01-24 08:24:35.446924: step: 1984/529, loss: 0.0034540072083473206
2023-01-24 08:24:36.494666: step: 1988/529, loss: 0.007070994004607201
2023-01-24 08:24:37.534919: step: 1992/529, loss: 0.002674548188224435
2023-01-24 08:24:38.596748: step: 1996/529, loss: 0.0015828735195100307
2023-01-24 08:24:39.673619: step: 2000/529, loss: 0.004673106130212545
2023-01-24 08:24:40.725179: step: 2004/529, loss: 0.00763740623369813
2023-01-24 08:24:41.782006: step: 2008/529, loss: 0.02358953095972538
2023-01-24 08:24:42.855096: step: 2012/529, loss: 0.0008703985367901623
2023-01-24 08:24:43.915769: step: 2016/529, loss: 8.111830538837239e-05
2023-01-24 08:24:44.964559: step: 2020/529, loss: 8.71208067110274e-06
2023-01-24 08:24:46.014455: step: 2024/529, loss: 0.0006541019538417459
2023-01-24 08:24:47.063313: step: 2028/529, loss: 0.0005558844422921538
2023-01-24 08:24:48.100603: step: 2032/529, loss: 0.005073852371424437
2023-01-24 08:24:49.146770: step: 2036/529, loss: 0.0034488425590097904
2023-01-24 08:24:50.205147: step: 2040/529, loss: 1.2294560292502865e-05
2023-01-24 08:24:51.273060: step: 2044/529, loss: 0.005507190711796284
2023-01-24 08:24:52.342198: step: 2048/529, loss: 0.0003300464013591409
2023-01-24 08:24:53.406418: step: 2052/529, loss: 0.0030865869484841824
2023-01-24 08:24:54.467773: step: 2056/529, loss: 0.00204469240270555
2023-01-24 08:24:55.528868: step: 2060/529, loss: 0.015188870020210743
2023-01-24 08:24:56.579035: step: 2064/529, loss: 0.0007283998420462012
2023-01-24 08:24:57.620411: step: 2068/529, loss: 0.01700059324502945
2023-01-24 08:24:58.673544: step: 2072/529, loss: 0.00129891827236861
2023-01-24 08:24:59.721515: step: 2076/529, loss: 0.0028964467346668243
2023-01-24 08:25:00.790784: step: 2080/529, loss: 0.0037925851065665483
2023-01-24 08:25:01.841259: step: 2084/529, loss: 0.0024698269553482533
2023-01-24 08:25:02.894183: step: 2088/529, loss: 0.0012474246323108673
2023-01-24 08:25:03.957839: step: 2092/529, loss: 0.0009113414562307298
2023-01-24 08:25:05.004852: step: 2096/529, loss: 0.00015967717627063394
2023-01-24 08:25:06.033431: step: 2100/529, loss: 3.983715214417316e-05
2023-01-24 08:25:07.080797: step: 2104/529, loss: 0.0044643208384513855
2023-01-24 08:25:08.123631: step: 2108/529, loss: 0.0035878391936421394
2023-01-24 08:25:09.163825: step: 2112/529, loss: 0.0009981963085010648
2023-01-24 08:25:10.208391: step: 2116/529, loss: 0.003890544641762972
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32310953711093376, 'r': 0.32924064787205204, 'f1': 0.32614628088077335}, 'combined': 0.24031831222793826, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.36643933771460574, 'r': 0.2992907679763272, 'f1': 0.3294785975992997}, 'combined': 0.23179398826081388, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.357465644820296, 'r': 0.32083728652751425, 'f1': 0.33816250000000003}, 'combined': 0.24917236842105264, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3872066387232343, 'r': 0.31490103602971586, 'f1': 0.3473306903657886}, 'combined': 0.2466047901597099, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37810060834103454, 'r': 0.34222768534852654, 'f1': 0.35927089677026586}, 'combined': 0.2647259239359854, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.396543930445626, 'r': 0.3134255520116083, 'f1': 0.350119275173943}, 'combined': 0.2485846853734995, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3270833333333333, 'r': 0.37380952380952376, 'f1': 0.34888888888888886}, 'combined': 0.23259259259259257, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 17
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:27:43.032460: step: 4/529, loss: 0.001979679800570011
2023-01-24 08:27:44.086623: step: 8/529, loss: 0.000323904532706365
2023-01-24 08:27:45.123994: step: 12/529, loss: 0.0004696924879681319
2023-01-24 08:27:46.179236: step: 16/529, loss: 0.005513431970030069
2023-01-24 08:27:47.211514: step: 20/529, loss: 0.0005147429765202105
2023-01-24 08:27:48.260892: step: 24/529, loss: 0.0021051180083304644
2023-01-24 08:27:49.307447: step: 28/529, loss: 0.00010728325287345797
2023-01-24 08:27:50.385188: step: 32/529, loss: 0.018907487392425537
2023-01-24 08:27:51.436533: step: 36/529, loss: 0.0020073980558663607
2023-01-24 08:27:52.502335: step: 40/529, loss: 0.0010086934780701995
2023-01-24 08:27:53.546555: step: 44/529, loss: 0.0005943200667388737
2023-01-24 08:27:54.594249: step: 48/529, loss: 0.00017684587510302663
2023-01-24 08:27:55.632466: step: 52/529, loss: 0.0017115434166043997
2023-01-24 08:27:56.689184: step: 56/529, loss: 4.336572965257801e-05
2023-01-24 08:27:57.743835: step: 60/529, loss: 5.474903809954412e-05
2023-01-24 08:27:58.785162: step: 64/529, loss: 0.0033923950977623463
2023-01-24 08:27:59.828818: step: 68/529, loss: 0.0016745933098718524
2023-01-24 08:28:00.873707: step: 72/529, loss: 0.00179290899541229
2023-01-24 08:28:01.920941: step: 76/529, loss: 0.012125317938625813
2023-01-24 08:28:02.953159: step: 80/529, loss: 1.832306406868156e-05
2023-01-24 08:28:04.017213: step: 84/529, loss: 3.1222793040797114e-05
2023-01-24 08:28:05.066683: step: 88/529, loss: 0.0008944679284468293
2023-01-24 08:28:06.101407: step: 92/529, loss: 0.0013630266766995192
2023-01-24 08:28:07.153417: step: 96/529, loss: 0.002934899413958192
2023-01-24 08:28:08.218605: step: 100/529, loss: 0.004789014812558889
2023-01-24 08:28:09.273807: step: 104/529, loss: 0.011363266035914421
2023-01-24 08:28:10.323001: step: 108/529, loss: 0.002246186602860689
2023-01-24 08:28:11.376625: step: 112/529, loss: 0.00043904688209295273
2023-01-24 08:28:12.429529: step: 116/529, loss: 0.012139673344790936
2023-01-24 08:28:13.471906: step: 120/529, loss: 0.0003828826011158526
2023-01-24 08:28:14.512262: step: 124/529, loss: 0.00039395870408043265
2023-01-24 08:28:15.546445: step: 128/529, loss: 2.512885203032056e-06
2023-01-24 08:28:16.576898: step: 132/529, loss: 1.9514911400619894e-05
2023-01-24 08:28:17.640670: step: 136/529, loss: 0.005341281183063984
2023-01-24 08:28:18.679671: step: 140/529, loss: 0.0005437136278487742
2023-01-24 08:28:19.724662: step: 144/529, loss: 0.006263319868594408
2023-01-24 08:28:20.770502: step: 148/529, loss: 0.0003503037733025849
2023-01-24 08:28:21.815019: step: 152/529, loss: 0.00029023794922977686
2023-01-24 08:28:22.850314: step: 156/529, loss: 0.002042224630713463
2023-01-24 08:28:23.905975: step: 160/529, loss: 0.0016620674869045615
2023-01-24 08:28:24.975208: step: 164/529, loss: 1.500479015703604e-06
2023-01-24 08:28:26.027568: step: 168/529, loss: 0.0003196543548256159
2023-01-24 08:28:27.073934: step: 172/529, loss: 0.0022029231768101454
2023-01-24 08:28:28.128276: step: 176/529, loss: 0.0007330220541916788
2023-01-24 08:28:29.170733: step: 180/529, loss: 0.001181742292828858
2023-01-24 08:28:30.205975: step: 184/529, loss: 0.000990207539871335
2023-01-24 08:28:31.235146: step: 188/529, loss: 0.002197195775806904
2023-01-24 08:28:32.269476: step: 192/529, loss: 0.000547136936802417
2023-01-24 08:28:33.327038: step: 196/529, loss: 0.0005627564387395978
2023-01-24 08:28:34.379541: step: 200/529, loss: 0.001279753167182207
2023-01-24 08:28:35.446483: step: 204/529, loss: 0.00030547703499905765
2023-01-24 08:28:36.486234: step: 208/529, loss: 0.0009775698417797685
2023-01-24 08:28:37.528501: step: 212/529, loss: 0.0
2023-01-24 08:28:38.564165: step: 216/529, loss: 0.0007619349635206163
2023-01-24 08:28:39.604321: step: 220/529, loss: 0.0003181833599228412
2023-01-24 08:28:40.665870: step: 224/529, loss: 0.0076162246987223625
2023-01-24 08:28:41.710659: step: 228/529, loss: 0.0043853954412043095
2023-01-24 08:28:42.756273: step: 232/529, loss: 0.008801596239209175
2023-01-24 08:28:43.796383: step: 236/529, loss: 0.0007346550701186061
2023-01-24 08:28:44.842315: step: 240/529, loss: 0.004155769478529692
2023-01-24 08:28:45.899055: step: 244/529, loss: 0.0029669490177184343
2023-01-24 08:28:46.962621: step: 248/529, loss: 0.0009297950891777873
2023-01-24 08:28:48.013277: step: 252/529, loss: 0.004259558394551277
2023-01-24 08:28:49.049813: step: 256/529, loss: 0.008117446675896645
2023-01-24 08:28:50.106267: step: 260/529, loss: 0.002745047677308321
2023-01-24 08:28:51.148564: step: 264/529, loss: 0.001905286917462945
2023-01-24 08:28:52.199021: step: 268/529, loss: 0.0029612730722874403
2023-01-24 08:28:53.259929: step: 272/529, loss: 0.003946423064917326
2023-01-24 08:28:54.305751: step: 276/529, loss: 0.0031625088304281235
2023-01-24 08:28:55.347936: step: 280/529, loss: 0.00047844057553447783
2023-01-24 08:28:56.405159: step: 284/529, loss: 0.006953620817512274
2023-01-24 08:28:57.450669: step: 288/529, loss: 0.0016610261518508196
2023-01-24 08:28:58.506683: step: 292/529, loss: 0.0008976393728516996
2023-01-24 08:28:59.552032: step: 296/529, loss: 0.014088860712945461
2023-01-24 08:29:00.595288: step: 300/529, loss: 0.0002413712936686352
2023-01-24 08:29:01.630906: step: 304/529, loss: 0.0017692968249320984
2023-01-24 08:29:02.671036: step: 308/529, loss: 9.219790808856487e-05
2023-01-24 08:29:03.717859: step: 312/529, loss: 0.006365868728607893
2023-01-24 08:29:04.790101: step: 316/529, loss: 0.001232083304785192
2023-01-24 08:29:05.855513: step: 320/529, loss: 3.171627031406388e-05
2023-01-24 08:29:06.915088: step: 324/529, loss: 0.0017329216934740543
2023-01-24 08:29:07.963375: step: 328/529, loss: 0.00014214050315786153
2023-01-24 08:29:09.001319: step: 332/529, loss: 9.037533891387284e-05
2023-01-24 08:29:10.036514: step: 336/529, loss: 6.725789717165753e-05
2023-01-24 08:29:11.099723: step: 340/529, loss: 4.364574124338105e-05
2023-01-24 08:29:12.161421: step: 344/529, loss: 0.0005389410653151572
2023-01-24 08:29:13.217709: step: 348/529, loss: 0.003135477425530553
2023-01-24 08:29:14.282121: step: 352/529, loss: 0.004622049164026976
2023-01-24 08:29:15.333387: step: 356/529, loss: 0.004625746980309486
2023-01-24 08:29:16.379786: step: 360/529, loss: 0.002108829328790307
2023-01-24 08:29:17.419723: step: 364/529, loss: 0.0033576281275600195
2023-01-24 08:29:18.473328: step: 368/529, loss: 0.0032943664118647575
2023-01-24 08:29:19.536160: step: 372/529, loss: 3.5910335327571374e-07
2023-01-24 08:29:20.590794: step: 376/529, loss: 0.0010327312629669905
2023-01-24 08:29:21.631800: step: 380/529, loss: 0.005264889448881149
2023-01-24 08:29:22.686522: step: 384/529, loss: 0.002409805776551366
2023-01-24 08:29:23.732426: step: 388/529, loss: 6.404477608157322e-05
2023-01-24 08:29:24.791573: step: 392/529, loss: 0.0006295220227912068
2023-01-24 08:29:25.837771: step: 396/529, loss: 0.0007395798456855118
2023-01-24 08:29:26.876174: step: 400/529, loss: 0.0007506815018132329
2023-01-24 08:29:27.927409: step: 404/529, loss: 0.0006419341079890728
2023-01-24 08:29:28.977437: step: 408/529, loss: 0.060576267540454865
2023-01-24 08:29:30.020945: step: 412/529, loss: 5.433255137177184e-05
2023-01-24 08:29:31.094310: step: 416/529, loss: 0.0001986789720831439
2023-01-24 08:29:32.140187: step: 420/529, loss: 0.0019164758268743753
2023-01-24 08:29:33.192367: step: 424/529, loss: 0.006326535250991583
2023-01-24 08:29:34.236151: step: 428/529, loss: 0.00014479334640782326
2023-01-24 08:29:35.269010: step: 432/529, loss: 0.00047467503463849425
2023-01-24 08:29:36.313393: step: 436/529, loss: 0.00854411069303751
2023-01-24 08:29:37.345486: step: 440/529, loss: 0.002031397307291627
2023-01-24 08:29:38.385665: step: 444/529, loss: 0.0003723583649843931
2023-01-24 08:29:39.420115: step: 448/529, loss: 0.0011161983711645007
2023-01-24 08:29:40.460083: step: 452/529, loss: 0.0030313616152852774
2023-01-24 08:29:41.523225: step: 456/529, loss: 0.0002898721140809357
2023-01-24 08:29:42.577272: step: 460/529, loss: 0.0015235858736559749
2023-01-24 08:29:43.625825: step: 464/529, loss: 0.0021801134571433067
2023-01-24 08:29:44.665976: step: 468/529, loss: 0.003303066361695528
2023-01-24 08:29:45.713065: step: 472/529, loss: 0.009290232323110104
2023-01-24 08:29:46.765683: step: 476/529, loss: 0.006175410933792591
2023-01-24 08:29:47.807981: step: 480/529, loss: 0.008844809606671333
2023-01-24 08:29:48.856011: step: 484/529, loss: 0.0017871590098366141
2023-01-24 08:29:49.887731: step: 488/529, loss: 0.0036425276193767786
2023-01-24 08:29:50.925993: step: 492/529, loss: 3.2200995292441803e-07
2023-01-24 08:29:51.966734: step: 496/529, loss: 9.023367653071546e-08
2023-01-24 08:29:53.010198: step: 500/529, loss: 1.5982701370376162e-05
2023-01-24 08:29:54.065936: step: 504/529, loss: 1.555716517032124e-05
2023-01-24 08:29:55.112369: step: 508/529, loss: 0.00333710596896708
2023-01-24 08:29:56.176623: step: 512/529, loss: 0.002485116245225072
2023-01-24 08:29:57.243070: step: 516/529, loss: 0.001291679684072733
2023-01-24 08:29:58.279231: step: 520/529, loss: 0.011360274627804756
2023-01-24 08:29:59.329906: step: 524/529, loss: 0.0003248619905207306
2023-01-24 08:30:00.371542: step: 528/529, loss: 0.003231351263821125
2023-01-24 08:30:01.419236: step: 532/529, loss: 0.0011035160860046744
2023-01-24 08:30:02.467454: step: 536/529, loss: 0.0005290131084620953
2023-01-24 08:30:03.520147: step: 540/529, loss: 0.0033448045141994953
2023-01-24 08:30:04.560732: step: 544/529, loss: 0.00045974631211720407
2023-01-24 08:30:05.597868: step: 548/529, loss: 5.834714465891011e-05
2023-01-24 08:30:06.652275: step: 552/529, loss: 0.0006600487395189703
2023-01-24 08:30:07.700886: step: 556/529, loss: 9.860486898105592e-06
2023-01-24 08:30:08.727682: step: 560/529, loss: 0.00019670808978844434
2023-01-24 08:30:09.787717: step: 564/529, loss: 0.0005100234993733466
2023-01-24 08:30:10.821102: step: 568/529, loss: 0.0011270275572314858
2023-01-24 08:30:11.880072: step: 572/529, loss: 0.004317504353821278
2023-01-24 08:30:12.941734: step: 576/529, loss: 0.0018919811118394136
2023-01-24 08:30:13.996923: step: 580/529, loss: 0.0005818606587126851
2023-01-24 08:30:15.055934: step: 584/529, loss: 0.0005637775175273418
2023-01-24 08:30:16.112453: step: 588/529, loss: 0.00023896007041912526
2023-01-24 08:30:17.168740: step: 592/529, loss: 0.0015199716435745358
2023-01-24 08:30:18.221188: step: 596/529, loss: 0.003908474463969469
2023-01-24 08:30:19.280078: step: 600/529, loss: 0.004019847605377436
2023-01-24 08:30:20.334770: step: 604/529, loss: 7.381595787592232e-05
2023-01-24 08:30:21.375625: step: 608/529, loss: 0.001343755517154932
2023-01-24 08:30:22.435541: step: 612/529, loss: 0.00019564401009120047
2023-01-24 08:30:23.492920: step: 616/529, loss: 0.0016836681170389056
2023-01-24 08:30:24.542127: step: 620/529, loss: 0.0013199449749663472
2023-01-24 08:30:25.590904: step: 624/529, loss: 0.000585422501899302
2023-01-24 08:30:26.628600: step: 628/529, loss: 0.005263371858745813
2023-01-24 08:30:27.672460: step: 632/529, loss: 0.0041062780655920506
2023-01-24 08:30:28.736047: step: 636/529, loss: 0.0025430978275835514
2023-01-24 08:30:29.790461: step: 640/529, loss: 0.0019583110697567463
2023-01-24 08:30:30.843406: step: 644/529, loss: 0.0005868739681318402
2023-01-24 08:30:31.879379: step: 648/529, loss: 2.9392556825769134e-05
2023-01-24 08:30:32.907731: step: 652/529, loss: 0.0005852890317328274
2023-01-24 08:30:33.963446: step: 656/529, loss: 0.0023192160297185183
2023-01-24 08:30:35.007393: step: 660/529, loss: 0.0027780914679169655
2023-01-24 08:30:36.055057: step: 664/529, loss: 0.00658578984439373
2023-01-24 08:30:37.113377: step: 668/529, loss: 0.0011716954177245498
2023-01-24 08:30:38.155207: step: 672/529, loss: 0.004284984897822142
2023-01-24 08:30:39.209495: step: 676/529, loss: 0.0015833433717489243
2023-01-24 08:30:40.254765: step: 680/529, loss: 0.009919038973748684
2023-01-24 08:30:41.315755: step: 684/529, loss: 0.0025329850614070892
2023-01-24 08:30:42.376581: step: 688/529, loss: 0.001043997472152114
2023-01-24 08:30:43.421303: step: 692/529, loss: 0.009608566761016846
2023-01-24 08:30:44.469423: step: 696/529, loss: 6.847268377896398e-05
2023-01-24 08:30:45.522833: step: 700/529, loss: 0.0018306252313777804
2023-01-24 08:30:46.576353: step: 704/529, loss: 0.00016421428881585598
2023-01-24 08:30:47.630910: step: 708/529, loss: 0.0027302103117108345
2023-01-24 08:30:48.704308: step: 712/529, loss: 0.00011108987382613122
2023-01-24 08:30:49.776291: step: 716/529, loss: 0.0017001992091536522
2023-01-24 08:30:50.834103: step: 720/529, loss: 0.02088848687708378
2023-01-24 08:30:51.888299: step: 724/529, loss: 0.000701676239259541
2023-01-24 08:30:52.949810: step: 728/529, loss: 0.0017831319710239768
2023-01-24 08:30:54.012538: step: 732/529, loss: 1.4592502566301846e-06
2023-01-24 08:30:55.056131: step: 736/529, loss: 3.0039145713089965e-06
2023-01-24 08:30:56.092961: step: 740/529, loss: 0.00035662358277477324
2023-01-24 08:30:57.126042: step: 744/529, loss: 0.0028334285598248243
2023-01-24 08:30:58.179054: step: 748/529, loss: 0.005084024276584387
2023-01-24 08:30:59.257405: step: 752/529, loss: 0.0015805682633072138
2023-01-24 08:31:00.299945: step: 756/529, loss: 0.001544327475130558
2023-01-24 08:31:01.341171: step: 760/529, loss: 0.004154146648943424
2023-01-24 08:31:02.403953: step: 764/529, loss: 0.0001707561605144292
2023-01-24 08:31:03.449830: step: 768/529, loss: 0.00039336318150162697
2023-01-24 08:31:04.500751: step: 772/529, loss: 0.001681500463746488
2023-01-24 08:31:05.538486: step: 776/529, loss: 0.0049059526063501835
2023-01-24 08:31:06.581913: step: 780/529, loss: 0.0005734350415877998
2023-01-24 08:31:07.631941: step: 784/529, loss: 0.0001834934373619035
2023-01-24 08:31:08.682790: step: 788/529, loss: 0.0003649888385552913
2023-01-24 08:31:09.756684: step: 792/529, loss: 0.015202866867184639
2023-01-24 08:31:10.811735: step: 796/529, loss: 0.0005916806985624135
2023-01-24 08:31:11.855905: step: 800/529, loss: 3.496696808724664e-05
2023-01-24 08:31:12.897849: step: 804/529, loss: 0.0007714180974289775
2023-01-24 08:31:13.952162: step: 808/529, loss: 0.003937914036214352
2023-01-24 08:31:15.006899: step: 812/529, loss: 0.00012536370195448399
2023-01-24 08:31:16.054349: step: 816/529, loss: 0.00139383424539119
2023-01-24 08:31:17.104395: step: 820/529, loss: 0.0010384443448856473
2023-01-24 08:31:18.161239: step: 824/529, loss: 0.0009705409756861627
2023-01-24 08:31:19.196224: step: 828/529, loss: 0.004878194071352482
2023-01-24 08:31:20.271275: step: 832/529, loss: 0.0004180468968115747
2023-01-24 08:31:21.301341: step: 836/529, loss: 0.013880755752325058
2023-01-24 08:31:22.353162: step: 840/529, loss: 0.0010464306687936187
2023-01-24 08:31:23.401234: step: 844/529, loss: 0.004251787904649973
2023-01-24 08:31:24.453691: step: 848/529, loss: 0.010634826496243477
2023-01-24 08:31:25.522248: step: 852/529, loss: 0.0008128765039145947
2023-01-24 08:31:26.580347: step: 856/529, loss: 0.0028192505706101656
2023-01-24 08:31:27.626319: step: 860/529, loss: 0.0027611961122602224
2023-01-24 08:31:28.671647: step: 864/529, loss: 0.0011970183113589883
2023-01-24 08:31:29.721073: step: 868/529, loss: 0.004674768075346947
2023-01-24 08:31:30.774495: step: 872/529, loss: 7.495319005101919e-05
2023-01-24 08:31:31.823361: step: 876/529, loss: 0.00566103495657444
2023-01-24 08:31:32.867898: step: 880/529, loss: 7.269711932167411e-05
2023-01-24 08:31:33.907824: step: 884/529, loss: 0.00979250855743885
2023-01-24 08:31:34.969586: step: 888/529, loss: 0.0019730094354599714
2023-01-24 08:31:36.020905: step: 892/529, loss: 6.7589120590128e-05
2023-01-24 08:31:37.082854: step: 896/529, loss: 0.001957797212526202
2023-01-24 08:31:38.130016: step: 900/529, loss: 0.006936739664524794
2023-01-24 08:31:39.179236: step: 904/529, loss: 0.011035311967134476
2023-01-24 08:31:40.240022: step: 908/529, loss: 0.0002993621164932847
2023-01-24 08:31:41.291755: step: 912/529, loss: 0.006157435942441225
2023-01-24 08:31:42.342537: step: 916/529, loss: 0.02472860738635063
2023-01-24 08:31:43.392184: step: 920/529, loss: 0.02365192212164402
2023-01-24 08:31:44.446579: step: 924/529, loss: 0.00038917764322832227
2023-01-24 08:31:45.490045: step: 928/529, loss: 0.013665257021784782
2023-01-24 08:31:46.546174: step: 932/529, loss: 0.0019580943044275045
2023-01-24 08:31:47.585029: step: 936/529, loss: 2.3207071535580326e-06
2023-01-24 08:31:48.631820: step: 940/529, loss: 0.004930335562676191
2023-01-24 08:31:49.699677: step: 944/529, loss: 0.011395915411412716
2023-01-24 08:31:50.770668: step: 948/529, loss: 0.0002880800166167319
2023-01-24 08:31:51.829194: step: 952/529, loss: 0.00039002057746984065
2023-01-24 08:31:52.880703: step: 956/529, loss: 0.004201086238026619
2023-01-24 08:31:53.939611: step: 960/529, loss: 0.004787670448422432
2023-01-24 08:31:54.986851: step: 964/529, loss: 0.0022140436340123415
2023-01-24 08:31:56.038024: step: 968/529, loss: 0.004820188973098993
2023-01-24 08:31:57.083013: step: 972/529, loss: 0.0
2023-01-24 08:31:58.134240: step: 976/529, loss: 0.00015084446931723505
2023-01-24 08:31:59.174283: step: 980/529, loss: 0.00048781069926917553
2023-01-24 08:32:00.242276: step: 984/529, loss: 0.0022004051133990288
2023-01-24 08:32:01.291356: step: 988/529, loss: 0.0018612545682117343
2023-01-24 08:32:02.336915: step: 992/529, loss: 0.001421335618942976
2023-01-24 08:32:03.372692: step: 996/529, loss: 0.0016851964173838496
2023-01-24 08:32:04.419027: step: 1000/529, loss: 0.0014501754194498062
2023-01-24 08:32:05.454526: step: 1004/529, loss: 0.00021850656776223332
2023-01-24 08:32:06.506375: step: 1008/529, loss: 0.003421073080971837
2023-01-24 08:32:07.551512: step: 1012/529, loss: 0.0026755977887660265
2023-01-24 08:32:08.587908: step: 1016/529, loss: 0.002640267601236701
2023-01-24 08:32:09.635554: step: 1020/529, loss: 0.0007453488069586456
2023-01-24 08:32:10.692302: step: 1024/529, loss: 8.922214328777045e-05
2023-01-24 08:32:11.739067: step: 1028/529, loss: 0.0003001664881594479
2023-01-24 08:32:12.780581: step: 1032/529, loss: 0.0004137743671890348
2023-01-24 08:32:13.850052: step: 1036/529, loss: 0.015160735696554184
2023-01-24 08:32:14.896349: step: 1040/529, loss: 6.713119546475355e-06
2023-01-24 08:32:15.938905: step: 1044/529, loss: 0.004256968852132559
2023-01-24 08:32:16.994799: step: 1048/529, loss: 0.0009546860819682479
2023-01-24 08:32:18.042656: step: 1052/529, loss: 0.0020999980624765158
2023-01-24 08:32:19.074245: step: 1056/529, loss: 0.0004954183241352439
2023-01-24 08:32:20.120351: step: 1060/529, loss: 0.00025377506972290576
2023-01-24 08:32:21.166086: step: 1064/529, loss: 0.006007860880345106
2023-01-24 08:32:22.210408: step: 1068/529, loss: 0.005761732812970877
2023-01-24 08:32:23.273726: step: 1072/529, loss: 0.0008052823250181973
2023-01-24 08:32:24.331746: step: 1076/529, loss: 0.004675415810197592
2023-01-24 08:32:25.378051: step: 1080/529, loss: 0.001172406948171556
2023-01-24 08:32:26.425133: step: 1084/529, loss: 0.013882599771022797
2023-01-24 08:32:27.483543: step: 1088/529, loss: 0.0031140537466853857
2023-01-24 08:32:28.547967: step: 1092/529, loss: 0.0018750755116343498
2023-01-24 08:32:29.608663: step: 1096/529, loss: 0.00041053167660720646
2023-01-24 08:32:30.679711: step: 1100/529, loss: 0.02071894332766533
2023-01-24 08:32:31.728757: step: 1104/529, loss: 0.005824276711791754
2023-01-24 08:32:32.757618: step: 1108/529, loss: 0.0034398278221488
2023-01-24 08:32:33.805702: step: 1112/529, loss: 0.0007248343317769468
2023-01-24 08:32:34.854752: step: 1116/529, loss: 0.0016272348584607244
2023-01-24 08:32:35.910072: step: 1120/529, loss: 0.024270696565508842
2023-01-24 08:32:36.985256: step: 1124/529, loss: 0.008198066614568233
2023-01-24 08:32:38.020894: step: 1128/529, loss: 0.00017716338334139436
2023-01-24 08:32:39.063671: step: 1132/529, loss: 0.0023339868057519197
2023-01-24 08:32:40.104765: step: 1136/529, loss: 0.004348753951489925
2023-01-24 08:32:41.163672: step: 1140/529, loss: 0.0005047456361353397
2023-01-24 08:32:42.217105: step: 1144/529, loss: 0.001348583959043026
2023-01-24 08:32:43.271915: step: 1148/529, loss: 0.008867360651493073
2023-01-24 08:32:44.321609: step: 1152/529, loss: 1.4973020370234735e-06
2023-01-24 08:32:45.369525: step: 1156/529, loss: 0.00012705654080491513
2023-01-24 08:32:46.414262: step: 1160/529, loss: 0.0011150601785629988
2023-01-24 08:32:47.458584: step: 1164/529, loss: 2.5084837034228258e-05
2023-01-24 08:32:48.518349: step: 1168/529, loss: 0.000639009231235832
2023-01-24 08:32:49.572245: step: 1172/529, loss: 0.00010808456863742322
2023-01-24 08:32:50.631194: step: 1176/529, loss: 4.692208312917501e-05
2023-01-24 08:32:51.661304: step: 1180/529, loss: 0.0
2023-01-24 08:32:52.698380: step: 1184/529, loss: 0.0006674528121948242
2023-01-24 08:32:53.765677: step: 1188/529, loss: 0.003931404557079077
2023-01-24 08:32:54.810404: step: 1192/529, loss: 0.00039345386903733015
2023-01-24 08:32:55.866936: step: 1196/529, loss: 0.0007931482396088541
2023-01-24 08:32:56.917801: step: 1200/529, loss: 0.003250508103519678
2023-01-24 08:32:57.969314: step: 1204/529, loss: 0.002107614651322365
2023-01-24 08:32:59.028185: step: 1208/529, loss: 0.003857313422486186
2023-01-24 08:33:00.087762: step: 1212/529, loss: 0.0014843317912891507
2023-01-24 08:33:01.151188: step: 1216/529, loss: 0.007462157867848873
2023-01-24 08:33:02.211314: step: 1220/529, loss: 0.000763463496696204
2023-01-24 08:33:03.270082: step: 1224/529, loss: 0.00010832014959305525
2023-01-24 08:33:04.347033: step: 1228/529, loss: 0.00197398173622787
2023-01-24 08:33:05.383924: step: 1232/529, loss: 0.0023675919510424137
2023-01-24 08:33:06.451217: step: 1236/529, loss: 0.0011089424369856715
2023-01-24 08:33:07.521537: step: 1240/529, loss: 0.006854542996734381
2023-01-24 08:33:08.580958: step: 1244/529, loss: 0.002792416140437126
2023-01-24 08:33:09.614395: step: 1248/529, loss: 0.005460486281663179
2023-01-24 08:33:10.662822: step: 1252/529, loss: 0.002688487758859992
2023-01-24 08:33:11.719533: step: 1256/529, loss: 0.0028811884112656116
2023-01-24 08:33:12.773336: step: 1260/529, loss: 0.008913027122616768
2023-01-24 08:33:13.833876: step: 1264/529, loss: 0.0026025138795375824
2023-01-24 08:33:14.874035: step: 1268/529, loss: 0.004478189628571272
2023-01-24 08:33:15.929358: step: 1272/529, loss: 0.0033880663104355335
2023-01-24 08:33:16.984076: step: 1276/529, loss: 0.006151091307401657
2023-01-24 08:33:18.021683: step: 1280/529, loss: 0.00021981036115903407
2023-01-24 08:33:19.067991: step: 1284/529, loss: 0.005274428986012936
2023-01-24 08:33:20.114967: step: 1288/529, loss: 0.011619441211223602
2023-01-24 08:33:21.168169: step: 1292/529, loss: 0.0019642231054604053
2023-01-24 08:33:22.216711: step: 1296/529, loss: 0.0017691556131467223
2023-01-24 08:33:23.278859: step: 1300/529, loss: 0.0014775648014619946
2023-01-24 08:33:24.341512: step: 1304/529, loss: 0.0072374409064650536
2023-01-24 08:33:25.386780: step: 1308/529, loss: 0.0010560991941019893
2023-01-24 08:33:26.446088: step: 1312/529, loss: 0.007952402345836163
2023-01-24 08:33:27.503937: step: 1316/529, loss: 0.0018213354051113129
2023-01-24 08:33:28.547710: step: 1320/529, loss: 0.0021132086403667927
2023-01-24 08:33:29.586550: step: 1324/529, loss: 1.349380198689687e-07
2023-01-24 08:33:30.629483: step: 1328/529, loss: 0.007909039966762066
2023-01-24 08:33:31.691188: step: 1332/529, loss: 0.0002813753089867532
2023-01-24 08:33:32.733198: step: 1336/529, loss: 0.0006604505470022559
2023-01-24 08:33:33.790187: step: 1340/529, loss: 0.0032843132503330708
2023-01-24 08:33:34.849376: step: 1344/529, loss: 0.0004775068664457649
2023-01-24 08:33:35.901575: step: 1348/529, loss: 0.00631076330319047
2023-01-24 08:33:36.950699: step: 1352/529, loss: 0.004779646173119545
2023-01-24 08:33:37.999300: step: 1356/529, loss: 6.307166040642187e-05
2023-01-24 08:33:39.073602: step: 1360/529, loss: 1.3627866792376153e-05
2023-01-24 08:33:40.137974: step: 1364/529, loss: 0.004057176876813173
2023-01-24 08:33:41.187637: step: 1368/529, loss: 0.0001814868301153183
2023-01-24 08:33:42.247986: step: 1372/529, loss: 0.0015653633745387197
2023-01-24 08:33:43.293168: step: 1376/529, loss: 0.00458559999242425
2023-01-24 08:33:44.350552: step: 1380/529, loss: 0.0016290690982714295
2023-01-24 08:33:45.397830: step: 1384/529, loss: 0.002829401521012187
2023-01-24 08:33:46.449497: step: 1388/529, loss: 0.0003560252080205828
2023-01-24 08:33:47.512850: step: 1392/529, loss: 0.0023760502226650715
2023-01-24 08:33:48.567195: step: 1396/529, loss: 0.0012170489644631743
2023-01-24 08:33:49.638827: step: 1400/529, loss: 0.02561815455555916
2023-01-24 08:33:50.686589: step: 1404/529, loss: 0.00332474778406322
2023-01-24 08:33:51.727278: step: 1408/529, loss: 0.00012231868458911777
2023-01-24 08:33:52.788398: step: 1412/529, loss: 0.002176988171413541
2023-01-24 08:33:53.865301: step: 1416/529, loss: 8.222395263146609e-05
2023-01-24 08:33:54.936918: step: 1420/529, loss: 0.004346745554357767
2023-01-24 08:33:55.990118: step: 1424/529, loss: 0.0004068028647452593
2023-01-24 08:33:57.030302: step: 1428/529, loss: 0.004758084658533335
2023-01-24 08:33:58.078595: step: 1432/529, loss: 7.143113907659426e-05
2023-01-24 08:33:59.126058: step: 1436/529, loss: 9.0739231382031e-05
2023-01-24 08:34:00.171735: step: 1440/529, loss: 0.002087126951664686
2023-01-24 08:34:01.223441: step: 1444/529, loss: 0.0010433309944346547
2023-01-24 08:34:02.291917: step: 1448/529, loss: 0.006269447039812803
2023-01-24 08:34:03.349437: step: 1452/529, loss: 0.002007029252126813
2023-01-24 08:34:04.401115: step: 1456/529, loss: 0.0007953843451105058
2023-01-24 08:34:05.481337: step: 1460/529, loss: 0.0007068383856676519
2023-01-24 08:34:06.542172: step: 1464/529, loss: 0.004258796572685242
2023-01-24 08:34:07.607766: step: 1468/529, loss: 0.0019357955316081643
2023-01-24 08:34:08.663640: step: 1472/529, loss: 0.0009981559123843908
2023-01-24 08:34:09.719544: step: 1476/529, loss: 0.0012059188447892666
2023-01-24 08:34:10.777604: step: 1480/529, loss: 0.0007138180662877858
2023-01-24 08:34:11.826590: step: 1484/529, loss: 0.0009562759078107774
2023-01-24 08:34:12.878468: step: 1488/529, loss: 3.163414658047259e-05
2023-01-24 08:34:13.928723: step: 1492/529, loss: 0.004259578417986631
2023-01-24 08:34:14.979420: step: 1496/529, loss: 0.021436817944049835
2023-01-24 08:34:16.039234: step: 1500/529, loss: 0.0033630160614848137
2023-01-24 08:34:17.090396: step: 1504/529, loss: 0.0007126299315132201
2023-01-24 08:34:18.132483: step: 1508/529, loss: 0.0003147026873193681
2023-01-24 08:34:19.223279: step: 1512/529, loss: 0.004060304258018732
2023-01-24 08:34:20.274548: step: 1516/529, loss: 3.923227723134914e-06
2023-01-24 08:34:21.346141: step: 1520/529, loss: 0.0019892677664756775
2023-01-24 08:34:22.411786: step: 1524/529, loss: 0.006891978904604912
2023-01-24 08:34:23.499279: step: 1528/529, loss: 0.001804531435482204
2023-01-24 08:34:24.574580: step: 1532/529, loss: 0.005080916918814182
2023-01-24 08:34:25.644559: step: 1536/529, loss: 0.0035506347194314003
2023-01-24 08:34:26.716924: step: 1540/529, loss: 3.150193515466526e-05
2023-01-24 08:34:27.773916: step: 1544/529, loss: 0.0007339027943089604
2023-01-24 08:34:28.819649: step: 1548/529, loss: 0.0004887094255536795
2023-01-24 08:34:29.879282: step: 1552/529, loss: 2.196420064137783e-05
2023-01-24 08:34:30.922247: step: 1556/529, loss: 0.0023421177174896
2023-01-24 08:34:31.978838: step: 1560/529, loss: 7.45276702218689e-05
2023-01-24 08:34:33.042737: step: 1564/529, loss: 0.00016004449571482837
2023-01-24 08:34:34.097773: step: 1568/529, loss: 0.012211759574711323
2023-01-24 08:34:35.154899: step: 1572/529, loss: 0.003549716668203473
2023-01-24 08:34:36.199070: step: 1576/529, loss: 0.0037560889031738043
2023-01-24 08:34:37.271310: step: 1580/529, loss: 0.008464363403618336
2023-01-24 08:34:38.354428: step: 1584/529, loss: 0.00816214270889759
2023-01-24 08:34:39.413025: step: 1588/529, loss: 0.0007251078495755792
2023-01-24 08:34:40.463197: step: 1592/529, loss: 0.009346088394522667
2023-01-24 08:34:41.532565: step: 1596/529, loss: 0.008776242844760418
2023-01-24 08:34:42.575386: step: 1600/529, loss: 7.301029199879849e-06
2023-01-24 08:34:43.639161: step: 1604/529, loss: 0.0033990193624049425
2023-01-24 08:34:44.694529: step: 1608/529, loss: 0.00962216779589653
2023-01-24 08:34:45.764811: step: 1612/529, loss: 0.001602620119228959
2023-01-24 08:34:46.826265: step: 1616/529, loss: 0.000756696448661387
2023-01-24 08:34:47.882977: step: 1620/529, loss: 9.583556675352156e-05
2023-01-24 08:34:48.945760: step: 1624/529, loss: 0.004409597720950842
2023-01-24 08:34:50.021843: step: 1628/529, loss: 0.001160959480330348
2023-01-24 08:34:51.078570: step: 1632/529, loss: 0.0019770523067563772
2023-01-24 08:34:52.123327: step: 1636/529, loss: 0.0023759084288030863
2023-01-24 08:34:53.178507: step: 1640/529, loss: 0.0020013824105262756
2023-01-24 08:34:54.253162: step: 1644/529, loss: 0.00030835915822535753
2023-01-24 08:34:55.315121: step: 1648/529, loss: 0.0002436820068396628
2023-01-24 08:34:56.390371: step: 1652/529, loss: 0.005246229935437441
2023-01-24 08:34:57.459610: step: 1656/529, loss: 0.0009176006424240768
2023-01-24 08:34:58.539001: step: 1660/529, loss: 0.0029546599835157394
2023-01-24 08:34:59.594967: step: 1664/529, loss: 0.00011861661187140271
2023-01-24 08:35:00.642168: step: 1668/529, loss: 0.003408083925023675
2023-01-24 08:35:01.706302: step: 1672/529, loss: 0.005017903167754412
2023-01-24 08:35:02.783784: step: 1676/529, loss: 0.00034586136462166905
2023-01-24 08:35:03.846041: step: 1680/529, loss: 0.0014413106255233288
2023-01-24 08:35:04.900126: step: 1684/529, loss: 0.001533097238279879
2023-01-24 08:35:05.963171: step: 1688/529, loss: 0.01825839653611183
2023-01-24 08:35:07.017587: step: 1692/529, loss: 0.001877815229818225
2023-01-24 08:35:08.066493: step: 1696/529, loss: 4.092630661034491e-06
2023-01-24 08:35:09.133305: step: 1700/529, loss: 0.0003072339459322393
2023-01-24 08:35:10.185556: step: 1704/529, loss: 1.233212174156506e-06
2023-01-24 08:35:11.245101: step: 1708/529, loss: 0.0040343767032027245
2023-01-24 08:35:12.313888: step: 1712/529, loss: 0.0017201175214722753
2023-01-24 08:35:13.387368: step: 1716/529, loss: 0.0008348234696313739
2023-01-24 08:35:14.440596: step: 1720/529, loss: 0.0021006113383919
2023-01-24 08:35:15.506074: step: 1724/529, loss: 0.003452489385381341
2023-01-24 08:35:16.560856: step: 1728/529, loss: 0.02030882239341736
2023-01-24 08:35:17.613602: step: 1732/529, loss: 0.001655923086218536
2023-01-24 08:35:18.683237: step: 1736/529, loss: 0.061582282185554504
2023-01-24 08:35:19.773984: step: 1740/529, loss: 0.0009948700899258256
2023-01-24 08:35:20.834637: step: 1744/529, loss: 0.0023519229143857956
2023-01-24 08:35:21.897578: step: 1748/529, loss: 0.002199391834437847
2023-01-24 08:35:22.971026: step: 1752/529, loss: 0.001334262196905911
2023-01-24 08:35:24.026338: step: 1756/529, loss: 0.0009589419350959361
2023-01-24 08:35:25.074087: step: 1760/529, loss: 1.4634616491093766e-05
2023-01-24 08:35:26.134140: step: 1764/529, loss: 0.0019049779511988163
2023-01-24 08:35:27.198321: step: 1768/529, loss: 0.0003587405080907047
2023-01-24 08:35:28.261687: step: 1772/529, loss: 0.005450187250971794
2023-01-24 08:35:29.313218: step: 1776/529, loss: 0.0013658484676852822
2023-01-24 08:35:30.361229: step: 1780/529, loss: 0.00014007485879119486
2023-01-24 08:35:31.420226: step: 1784/529, loss: 0.015004838816821575
2023-01-24 08:35:32.465952: step: 1788/529, loss: 1.0008646995629533e-06
2023-01-24 08:35:33.516133: step: 1792/529, loss: 0.004474562127143145
2023-01-24 08:35:34.571059: step: 1796/529, loss: 0.001065478310920298
2023-01-24 08:35:35.627118: step: 1800/529, loss: 0.0018748308066278696
2023-01-24 08:35:36.687069: step: 1804/529, loss: 0.0001023206059471704
2023-01-24 08:35:37.732198: step: 1808/529, loss: 0.00014324145740829408
2023-01-24 08:35:38.771443: step: 1812/529, loss: 0.0014645956689491868
2023-01-24 08:35:39.833188: step: 1816/529, loss: 2.510145350242965e-05
2023-01-24 08:35:40.927910: step: 1820/529, loss: 0.01156536303460598
2023-01-24 08:35:41.981400: step: 1824/529, loss: 0.003507490735501051
2023-01-24 08:35:43.039395: step: 1828/529, loss: 0.0006680257502011955
2023-01-24 08:35:44.124715: step: 1832/529, loss: 3.684385956148617e-05
2023-01-24 08:35:45.161730: step: 1836/529, loss: 0.00018191280832979828
2023-01-24 08:35:46.213830: step: 1840/529, loss: 0.015484696254134178
2023-01-24 08:35:47.292350: step: 1844/529, loss: 0.0013007192173972726
2023-01-24 08:35:48.346822: step: 1848/529, loss: 7.69111211411655e-05
2023-01-24 08:35:49.396236: step: 1852/529, loss: 0.004221030510962009
2023-01-24 08:35:50.470387: step: 1856/529, loss: 0.008564862422645092
2023-01-24 08:35:51.518342: step: 1860/529, loss: 0.001313916058279574
2023-01-24 08:35:52.565107: step: 1864/529, loss: 0.008299976587295532
2023-01-24 08:35:53.628127: step: 1868/529, loss: 0.0011678538285195827
2023-01-24 08:35:54.658670: step: 1872/529, loss: 0.0030510015785694122
2023-01-24 08:35:55.715414: step: 1876/529, loss: 0.005101947113871574
2023-01-24 08:35:56.774746: step: 1880/529, loss: 0.0008690987597219646
2023-01-24 08:35:57.821899: step: 1884/529, loss: 0.0033924232702702284
2023-01-24 08:35:58.878798: step: 1888/529, loss: 4.251694554113783e-05
2023-01-24 08:35:59.946523: step: 1892/529, loss: 6.332990576396469e-09
2023-01-24 08:36:01.001758: step: 1896/529, loss: 0.004680524114519358
2023-01-24 08:36:02.044618: step: 1900/529, loss: 0.001898404792882502
2023-01-24 08:36:03.082467: step: 1904/529, loss: 0.0009078923030756414
2023-01-24 08:36:04.155123: step: 1908/529, loss: 0.0017915766220539808
2023-01-24 08:36:05.245827: step: 1912/529, loss: 0.0026256723795086145
2023-01-24 08:36:06.322005: step: 1916/529, loss: 0.0008288290118798614
2023-01-24 08:36:07.374305: step: 1920/529, loss: 0.0009454202954657376
2023-01-24 08:36:08.418771: step: 1924/529, loss: 0.0
2023-01-24 08:36:09.464457: step: 1928/529, loss: 0.00721781188622117
2023-01-24 08:36:10.513880: step: 1932/529, loss: 0.005545284133404493
2023-01-24 08:36:11.560438: step: 1936/529, loss: 2.6539389637036948e-06
2023-01-24 08:36:12.603947: step: 1940/529, loss: 0.005530808120965958
2023-01-24 08:36:13.667231: step: 1944/529, loss: 0.00016681908164173365
2023-01-24 08:36:14.739181: step: 1948/529, loss: 0.018619904294610023
2023-01-24 08:36:15.799840: step: 1952/529, loss: 0.0006719669327139854
2023-01-24 08:36:16.848940: step: 1956/529, loss: 0.0033222078345716
2023-01-24 08:36:17.890107: step: 1960/529, loss: 0.0009013910312205553
2023-01-24 08:36:18.941346: step: 1964/529, loss: 0.0031685710418969393
2023-01-24 08:36:20.015812: step: 1968/529, loss: 0.026316506788134575
2023-01-24 08:36:21.089699: step: 1972/529, loss: 0.0029956272337585688
2023-01-24 08:36:22.144168: step: 1976/529, loss: 0.0006829300546087325
2023-01-24 08:36:23.207821: step: 1980/529, loss: 0.0026774373836815357
2023-01-24 08:36:24.250501: step: 1984/529, loss: 0.0015835872618481517
2023-01-24 08:36:25.293877: step: 1988/529, loss: 0.0008484829450026155
2023-01-24 08:36:26.331848: step: 1992/529, loss: 1.2046068604831817e-06
2023-01-24 08:36:27.371950: step: 1996/529, loss: 0.006513392087072134
2023-01-24 08:36:28.420670: step: 2000/529, loss: 0.0006468179635703564
2023-01-24 08:36:29.478889: step: 2004/529, loss: 0.004053688142448664
2023-01-24 08:36:30.527893: step: 2008/529, loss: 0.016508420929312706
2023-01-24 08:36:31.583976: step: 2012/529, loss: 0.00010688937618397176
2023-01-24 08:36:32.642512: step: 2016/529, loss: 0.008635124191641808
2023-01-24 08:36:33.709466: step: 2020/529, loss: 0.00540296221151948
2023-01-24 08:36:34.749456: step: 2024/529, loss: 0.0004748922074213624
2023-01-24 08:36:35.801578: step: 2028/529, loss: 0.00018765135610010475
2023-01-24 08:36:36.860277: step: 2032/529, loss: 0.00013595052587334067
2023-01-24 08:36:37.921854: step: 2036/529, loss: 0.002440395997837186
2023-01-24 08:36:38.992864: step: 2040/529, loss: 0.004034511279314756
2023-01-24 08:36:40.065831: step: 2044/529, loss: 0.002472696593031287
2023-01-24 08:36:41.101355: step: 2048/529, loss: 0.012192792259156704
2023-01-24 08:36:42.163982: step: 2052/529, loss: 1.6977021005004644e-05
2023-01-24 08:36:43.231651: step: 2056/529, loss: 0.0026067972648888826
2023-01-24 08:36:44.297519: step: 2060/529, loss: 0.010212764143943787
2023-01-24 08:36:45.381016: step: 2064/529, loss: 0.002877873368561268
2023-01-24 08:36:46.435445: step: 2068/529, loss: 0.00030163623159751296
2023-01-24 08:36:47.485862: step: 2072/529, loss: 0.000647848763037473
2023-01-24 08:36:48.541740: step: 2076/529, loss: 0.0001491221773903817
2023-01-24 08:36:49.581496: step: 2080/529, loss: 0.0004166766593698412
2023-01-24 08:36:50.631538: step: 2084/529, loss: 0.006063665729016066
2023-01-24 08:36:51.685195: step: 2088/529, loss: 0.00013983083772473037
2023-01-24 08:36:52.750588: step: 2092/529, loss: 0.002264385810121894
2023-01-24 08:36:53.801724: step: 2096/529, loss: 0.0033933003433048725
2023-01-24 08:36:54.857101: step: 2100/529, loss: 0.002809097757562995
2023-01-24 08:36:55.919234: step: 2104/529, loss: 0.00815637968480587
2023-01-24 08:36:56.965509: step: 2108/529, loss: 0.00015013592201285064
2023-01-24 08:36:58.003682: step: 2112/529, loss: 0.01059667207300663
2023-01-24 08:36:59.052833: step: 2116/529, loss: 0.0008185316110029817
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32455522486772487, 'r': 0.33256133098400653, 'f1': 0.3285095059579596}, 'combined': 0.24205963596902283, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.370050394984921, 'r': 0.3025630192852277, 'f1': 0.33292099865662117}, 'combined': 0.23421577794938175, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35446802935010485, 'r': 0.32083728652751425, 'f1': 0.33681523904382477}, 'combined': 0.2481796498217656, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3885799651651271, 'r': 0.31839143742587644, 'f1': 0.35000152258038786}, 'combined': 0.24850108103207535, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3801970443997348, 'r': 0.34412521855535766, 'f1': 0.3612629286427758}, 'combined': 0.2661937368946769, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39592267965996847, 'r': 0.31189716773213233, 'f1': 0.3489225765054143}, 'combined': 0.24773502931884414, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 18
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:39:31.724741: step: 4/529, loss: 8.586660442233551e-06
2023-01-24 08:39:32.769781: step: 8/529, loss: 0.005795099772512913
2023-01-24 08:39:33.817718: step: 12/529, loss: 5.505406079464592e-05
2023-01-24 08:39:34.848065: step: 16/529, loss: 0.0028429310768842697
2023-01-24 08:39:35.909255: step: 20/529, loss: 0.0010310659417882562
2023-01-24 08:39:36.963943: step: 24/529, loss: 0.0023168507032096386
2023-01-24 08:39:38.013917: step: 28/529, loss: 7.804288202351017e-07
2023-01-24 08:39:39.071706: step: 32/529, loss: 0.0003537945740390569
2023-01-24 08:39:40.111838: step: 36/529, loss: 0.0026274633128196
2023-01-24 08:39:41.162365: step: 40/529, loss: 0.004386108368635178
2023-01-24 08:39:42.216460: step: 44/529, loss: 0.0036779025103896856
2023-01-24 08:39:43.260447: step: 48/529, loss: 0.0027557911816984415
2023-01-24 08:39:44.326010: step: 52/529, loss: 0.0008563187438994646
2023-01-24 08:39:45.367448: step: 56/529, loss: 0.00017050962196663022
2023-01-24 08:39:46.413818: step: 60/529, loss: 0.003166683716699481
2023-01-24 08:39:47.473491: step: 64/529, loss: 0.0019586498383432627
2023-01-24 08:39:48.521311: step: 68/529, loss: 5.037395112594822e-06
2023-01-24 08:39:49.566066: step: 72/529, loss: 0.00822482444345951
2023-01-24 08:39:50.611342: step: 76/529, loss: 0.0013353358954191208
2023-01-24 08:39:51.659854: step: 80/529, loss: 0.0016978532075881958
2023-01-24 08:39:52.703811: step: 84/529, loss: 0.005429303739219904
2023-01-24 08:39:53.747699: step: 88/529, loss: 0.001017825212329626
2023-01-24 08:39:54.800056: step: 92/529, loss: 0.02247755602002144
2023-01-24 08:39:55.833668: step: 96/529, loss: 0.0012538210721686482
2023-01-24 08:39:56.873398: step: 100/529, loss: 0.00032289890805259347
2023-01-24 08:39:57.923530: step: 104/529, loss: 0.0033722184598445892
2023-01-24 08:39:58.955405: step: 108/529, loss: 0.0003131965931970626
2023-01-24 08:40:00.010398: step: 112/529, loss: 0.00034734487417154014
2023-01-24 08:40:01.069716: step: 116/529, loss: 0.010033790022134781
2023-01-24 08:40:02.128866: step: 120/529, loss: 8.165013423422351e-05
2023-01-24 08:40:03.176775: step: 124/529, loss: 0.0015796237858012319
2023-01-24 08:40:04.215740: step: 128/529, loss: 0.0025013068225234747
2023-01-24 08:40:05.257157: step: 132/529, loss: 8.389886352233589e-05
2023-01-24 08:40:06.309674: step: 136/529, loss: 1.5850202544243075e-05
2023-01-24 08:40:07.349623: step: 140/529, loss: 0.00073649687692523
2023-01-24 08:40:08.386075: step: 144/529, loss: 0.002633465453982353
2023-01-24 08:40:09.434673: step: 148/529, loss: 0.004230194725096226
2023-01-24 08:40:10.470867: step: 152/529, loss: 0.0001614537468412891
2023-01-24 08:40:11.497071: step: 156/529, loss: 2.349677015445195e-05
2023-01-24 08:40:12.543607: step: 160/529, loss: 0.0002939012192655355
2023-01-24 08:40:13.590052: step: 164/529, loss: 0.001155578880570829
2023-01-24 08:40:14.628163: step: 168/529, loss: 0.0024723673705011606
2023-01-24 08:40:15.678622: step: 172/529, loss: 0.000858198560308665
2023-01-24 08:40:16.724664: step: 176/529, loss: 0.0018640168709680438
2023-01-24 08:40:17.780551: step: 180/529, loss: 0.0011896634241566062
2023-01-24 08:40:18.817164: step: 184/529, loss: 0.0020641929004341364
2023-01-24 08:40:19.867865: step: 188/529, loss: 0.012836151756346226
2023-01-24 08:40:20.931078: step: 192/529, loss: 0.001028097583912313
2023-01-24 08:40:21.973827: step: 196/529, loss: 0.0005629516090266407
2023-01-24 08:40:23.022451: step: 200/529, loss: 0.006482400465756655
2023-01-24 08:40:24.076112: step: 204/529, loss: 0.021435415372252464
2023-01-24 08:40:25.150255: step: 208/529, loss: 0.0016346926568076015
2023-01-24 08:40:26.196409: step: 212/529, loss: 0.0020646380726248026
2023-01-24 08:40:27.236337: step: 216/529, loss: 0.0014477386139333248
2023-01-24 08:40:28.275192: step: 220/529, loss: 0.0002352001320105046
2023-01-24 08:40:29.323045: step: 224/529, loss: 0.0004439159529283643
2023-01-24 08:40:30.393311: step: 228/529, loss: 0.0030090094078332186
2023-01-24 08:40:31.432549: step: 232/529, loss: 0.0023054282646626234
2023-01-24 08:40:32.489783: step: 236/529, loss: 0.0023689251393079758
2023-01-24 08:40:33.530435: step: 240/529, loss: 0.006893096026033163
2023-01-24 08:40:34.582942: step: 244/529, loss: 0.00014931939949747175
2023-01-24 08:40:35.643148: step: 248/529, loss: 3.470656884019263e-05
2023-01-24 08:40:36.710540: step: 252/529, loss: 0.00027937404229305685
2023-01-24 08:40:37.780163: step: 256/529, loss: 0.004906128626316786
2023-01-24 08:40:38.840381: step: 260/529, loss: 0.010787881910800934
2023-01-24 08:40:39.903495: step: 264/529, loss: 0.000797909393440932
2023-01-24 08:40:40.951463: step: 268/529, loss: 0.0012772743357345462
2023-01-24 08:40:41.986142: step: 272/529, loss: 0.005077512934803963
2023-01-24 08:40:43.035965: step: 276/529, loss: 0.0004535203624982387
2023-01-24 08:40:44.092439: step: 280/529, loss: 0.0008805394754745066
2023-01-24 08:40:45.143938: step: 284/529, loss: 0.007728349417448044
2023-01-24 08:40:46.182459: step: 288/529, loss: 1.2472240996430628e-05
2023-01-24 08:40:47.217724: step: 292/529, loss: 6.202335498528555e-05
2023-01-24 08:40:48.259395: step: 296/529, loss: 0.0004313747340347618
2023-01-24 08:40:49.295813: step: 300/529, loss: 0.007569751236587763
2023-01-24 08:40:50.342409: step: 304/529, loss: 0.003194732591509819
2023-01-24 08:40:51.382805: step: 308/529, loss: 0.0009146026568487287
2023-01-24 08:40:52.433085: step: 312/529, loss: 0.004747942090034485
2023-01-24 08:40:53.498827: step: 316/529, loss: 0.0003494467819109559
2023-01-24 08:40:54.535677: step: 320/529, loss: 0.0018791165202856064
2023-01-24 08:40:55.564882: step: 324/529, loss: 0.00035345181822776794
2023-01-24 08:40:56.621960: step: 328/529, loss: 0.001224325387738645
2023-01-24 08:40:57.661696: step: 332/529, loss: 0.0008218127186410129
2023-01-24 08:40:58.695607: step: 336/529, loss: 0.0015079537406563759
2023-01-24 08:40:59.743920: step: 340/529, loss: 0.0002608805079944432
2023-01-24 08:41:00.793117: step: 344/529, loss: 0.0024979806039482355
2023-01-24 08:41:01.843837: step: 348/529, loss: 0.0009410845814272761
2023-01-24 08:41:02.891660: step: 352/529, loss: 2.0451292584766634e-05
2023-01-24 08:41:03.925283: step: 356/529, loss: 0.0018921707523986697
2023-01-24 08:41:04.981216: step: 360/529, loss: 0.0010745306499302387
2023-01-24 08:41:06.014211: step: 364/529, loss: 0.0029170666821300983
2023-01-24 08:41:07.074971: step: 368/529, loss: 0.0016907989047467709
2023-01-24 08:41:08.123436: step: 372/529, loss: 0.006942319683730602
2023-01-24 08:41:09.188159: step: 376/529, loss: 1.5828476534807123e-05
2023-01-24 08:41:10.244470: step: 380/529, loss: 0.006122441031038761
2023-01-24 08:41:11.272688: step: 384/529, loss: 0.001404011039994657
2023-01-24 08:41:12.315561: step: 388/529, loss: 0.00027714911266230047
2023-01-24 08:41:13.385903: step: 392/529, loss: 0.00347343017347157
2023-01-24 08:41:14.438259: step: 396/529, loss: 0.0003073842090088874
2023-01-24 08:41:15.477180: step: 400/529, loss: 6.205717363627627e-05
2023-01-24 08:41:16.530230: step: 404/529, loss: 0.00029305979842320085
2023-01-24 08:41:17.599517: step: 408/529, loss: 0.002027434529736638
2023-01-24 08:41:18.646854: step: 412/529, loss: 6.37602624919964e-06
2023-01-24 08:41:19.707313: step: 416/529, loss: 4.345694833318703e-05
2023-01-24 08:41:20.790830: step: 420/529, loss: 0.0003523665072862059
2023-01-24 08:41:21.843795: step: 424/529, loss: 0.00023176777176558971
2023-01-24 08:41:22.890261: step: 428/529, loss: 0.0010578720830380917
2023-01-24 08:41:23.945093: step: 432/529, loss: 0.0002500005648471415
2023-01-24 08:41:24.997502: step: 436/529, loss: 0.00020129384938627481
2023-01-24 08:41:26.028915: step: 440/529, loss: 3.6399935197550803e-05
2023-01-24 08:41:27.067811: step: 444/529, loss: 0.0002900024119298905
2023-01-24 08:41:28.116668: step: 448/529, loss: 3.000873221026268e-06
2023-01-24 08:41:29.165115: step: 452/529, loss: 0.00388632295653224
2023-01-24 08:41:30.198303: step: 456/529, loss: 0.0022911729756742716
2023-01-24 08:41:31.281672: step: 460/529, loss: 0.05139154568314552
2023-01-24 08:41:32.323073: step: 464/529, loss: 0.011684039607644081
2023-01-24 08:41:33.358860: step: 468/529, loss: 0.00010053443111246452
2023-01-24 08:41:34.407555: step: 472/529, loss: 0.004266801290214062
2023-01-24 08:41:35.469534: step: 476/529, loss: 6.221300282049924e-05
2023-01-24 08:41:36.517489: step: 480/529, loss: 0.003004474565386772
2023-01-24 08:41:37.573727: step: 484/529, loss: 0.0007768917130306363
2023-01-24 08:41:38.630890: step: 488/529, loss: 0.0007365065976046026
2023-01-24 08:41:39.680195: step: 492/529, loss: 0.011613000184297562
2023-01-24 08:41:40.730305: step: 496/529, loss: 0.002508936682716012
2023-01-24 08:41:41.772646: step: 500/529, loss: 0.0029823200311511755
2023-01-24 08:41:42.817895: step: 504/529, loss: 9.209271956933662e-05
2023-01-24 08:41:43.874219: step: 508/529, loss: 0.00030721898656338453
2023-01-24 08:41:44.904796: step: 512/529, loss: 0.019506681710481644
2023-01-24 08:41:45.962713: step: 516/529, loss: 0.0025473216082900763
2023-01-24 08:41:47.012042: step: 520/529, loss: 0.002272443613037467
2023-01-24 08:41:48.070003: step: 524/529, loss: 0.014924327842891216
2023-01-24 08:41:49.109801: step: 528/529, loss: 0.0005151796503923833
2023-01-24 08:41:50.192199: step: 532/529, loss: 0.0011023536790162325
2023-01-24 08:41:51.232024: step: 536/529, loss: 0.005972834769636393
2023-01-24 08:41:52.276791: step: 540/529, loss: 0.0021462044678628445
2023-01-24 08:41:53.338365: step: 544/529, loss: 0.001406265189871192
2023-01-24 08:41:54.372629: step: 548/529, loss: 0.0020305414218455553
2023-01-24 08:41:55.410742: step: 552/529, loss: 0.0002446957223583013
2023-01-24 08:41:56.470108: step: 556/529, loss: 0.009484723210334778
2023-01-24 08:41:57.518421: step: 560/529, loss: 0.001028704922646284
2023-01-24 08:41:58.574869: step: 564/529, loss: 0.0009129958925768733
2023-01-24 08:41:59.617722: step: 568/529, loss: 6.725028015353018e-06
2023-01-24 08:42:00.653332: step: 572/529, loss: 0.00032894001924432814
2023-01-24 08:42:01.715432: step: 576/529, loss: 0.004418517462909222
2023-01-24 08:42:02.763780: step: 580/529, loss: 0.003917934373021126
2023-01-24 08:42:03.819642: step: 584/529, loss: 0.0015810285694897175
2023-01-24 08:42:04.858923: step: 588/529, loss: 0.0013649979373440146
2023-01-24 08:42:05.903952: step: 592/529, loss: 0.01249530166387558
2023-01-24 08:42:06.952102: step: 596/529, loss: 0.0014215236296877265
2023-01-24 08:42:07.990844: step: 600/529, loss: 0.004968359135091305
2023-01-24 08:42:09.034107: step: 604/529, loss: 0.00117832375690341
2023-01-24 08:42:10.070014: step: 608/529, loss: 0.001479918835684657
2023-01-24 08:42:11.101242: step: 612/529, loss: 0.008590305224061012
2023-01-24 08:42:12.148490: step: 616/529, loss: 0.0016176907811313868
2023-01-24 08:42:13.200035: step: 620/529, loss: 0.00010884598304983228
2023-01-24 08:42:14.260806: step: 624/529, loss: 0.0022317273542284966
2023-01-24 08:42:15.300196: step: 628/529, loss: 0.00021314225159585476
2023-01-24 08:42:16.366562: step: 632/529, loss: 0.0006850367062725127
2023-01-24 08:42:17.422213: step: 636/529, loss: 2.6239118597004563e-05
2023-01-24 08:42:18.500035: step: 640/529, loss: 0.001985847717151046
2023-01-24 08:42:19.550473: step: 644/529, loss: 0.0017262045294046402
2023-01-24 08:42:20.608578: step: 648/529, loss: 0.003773147240281105
2023-01-24 08:42:21.665514: step: 652/529, loss: 0.0033027108293026686
2023-01-24 08:42:22.722466: step: 656/529, loss: 0.000779220717959106
2023-01-24 08:42:23.779408: step: 660/529, loss: 0.00028235986246727407
2023-01-24 08:42:24.839967: step: 664/529, loss: 0.00014228932559490204
2023-01-24 08:42:25.884886: step: 668/529, loss: 0.00037381722358986735
2023-01-24 08:42:26.938315: step: 672/529, loss: 0.0005348371341824532
2023-01-24 08:42:27.985353: step: 676/529, loss: 0.004633604548871517
2023-01-24 08:42:29.041562: step: 680/529, loss: 0.00862125400453806
2023-01-24 08:42:30.090781: step: 684/529, loss: 0.0024875199887901545
2023-01-24 08:42:31.142517: step: 688/529, loss: 0.021306846290826797
2023-01-24 08:42:32.192150: step: 692/529, loss: 0.0036454664077609777
2023-01-24 08:42:33.233424: step: 696/529, loss: 0.004500422161072493
2023-01-24 08:42:34.288497: step: 700/529, loss: 0.0004410268156789243
2023-01-24 08:42:35.341623: step: 704/529, loss: 4.7825353249209e-05
2023-01-24 08:42:36.390585: step: 708/529, loss: 0.0037369218189269304
2023-01-24 08:42:37.427831: step: 712/529, loss: 0.0019938212353736162
2023-01-24 08:42:38.508407: step: 716/529, loss: 0.0012977971928194165
2023-01-24 08:42:39.562781: step: 720/529, loss: 0.00042828364530578256
2023-01-24 08:42:40.616769: step: 724/529, loss: 0.0017755843000486493
2023-01-24 08:42:41.654603: step: 728/529, loss: 0.0004886184469796717
2023-01-24 08:42:42.707526: step: 732/529, loss: 7.520935469074175e-05
2023-01-24 08:42:43.763501: step: 736/529, loss: 0.0010965857654809952
2023-01-24 08:42:44.811045: step: 740/529, loss: 1.2635744042199804e-06
2023-01-24 08:42:45.869415: step: 744/529, loss: 0.0007283779559656978
2023-01-24 08:42:46.931486: step: 748/529, loss: 0.001425099209882319
2023-01-24 08:42:47.963699: step: 752/529, loss: 6.97213617968373e-05
2023-01-24 08:42:49.000878: step: 756/529, loss: 0.001094419858418405
2023-01-24 08:42:50.041092: step: 760/529, loss: 0.0001864241057774052
2023-01-24 08:42:51.085521: step: 764/529, loss: 0.0023755196016281843
2023-01-24 08:42:52.145628: step: 768/529, loss: 8.630496267869603e-06
2023-01-24 08:42:53.192281: step: 772/529, loss: 0.00038352972478605807
2023-01-24 08:42:54.232856: step: 776/529, loss: 0.004829848650842905
2023-01-24 08:42:55.289426: step: 780/529, loss: 1.7460631624999223e-06
2023-01-24 08:42:56.342388: step: 784/529, loss: 4.2972205847036093e-05
2023-01-24 08:42:57.398053: step: 788/529, loss: 0.0031249886378645897
2023-01-24 08:42:58.452440: step: 792/529, loss: 0.006286737509071827
2023-01-24 08:42:59.503294: step: 796/529, loss: 0.0014750432455912232
2023-01-24 08:43:00.538438: step: 800/529, loss: 0.0011810950236395001
2023-01-24 08:43:01.609381: step: 804/529, loss: 0.0018894333625212312
2023-01-24 08:43:02.651496: step: 808/529, loss: 0.0008275836007669568
2023-01-24 08:43:03.700465: step: 812/529, loss: 0.0076791951432824135
2023-01-24 08:43:04.747129: step: 816/529, loss: 1.6077235613920493e-06
2023-01-24 08:43:05.811120: step: 820/529, loss: 0.0036914304364472628
2023-01-24 08:43:06.853275: step: 824/529, loss: 0.0021473763044923544
2023-01-24 08:43:07.898612: step: 828/529, loss: 0.010765096172690392
2023-01-24 08:43:08.931019: step: 832/529, loss: 0.004371407441794872
2023-01-24 08:43:10.001421: step: 836/529, loss: 0.0016161790117621422
2023-01-24 08:43:11.049399: step: 840/529, loss: 0.0005308036343194544
2023-01-24 08:43:12.092257: step: 844/529, loss: 0.0069002858363091946
2023-01-24 08:43:13.150937: step: 848/529, loss: 0.00028333981754258275
2023-01-24 08:43:14.180022: step: 852/529, loss: 0.0005437321960926056
2023-01-24 08:43:15.235078: step: 856/529, loss: 0.0007248332840390503
2023-01-24 08:43:16.289189: step: 860/529, loss: 4.7009449190227315e-05
2023-01-24 08:43:17.337774: step: 864/529, loss: 3.047305654035881e-05
2023-01-24 08:43:18.389644: step: 868/529, loss: 0.001942401984706521
2023-01-24 08:43:19.460945: step: 872/529, loss: 0.00011781221110140905
2023-01-24 08:43:20.491688: step: 876/529, loss: 0.008294951170682907
2023-01-24 08:43:21.528522: step: 880/529, loss: 0.0026332433335483074
2023-01-24 08:43:22.578545: step: 884/529, loss: 0.0037599210627377033
2023-01-24 08:43:23.621520: step: 888/529, loss: 0.004231975879520178
2023-01-24 08:43:24.668077: step: 892/529, loss: 7.831253242329694e-06
2023-01-24 08:43:25.703971: step: 896/529, loss: 0.0035610187333077192
2023-01-24 08:43:26.745678: step: 900/529, loss: 3.974658829974942e-05
2023-01-24 08:43:27.800669: step: 904/529, loss: 0.002892760094255209
2023-01-24 08:43:28.858792: step: 908/529, loss: 3.0464763767668046e-05
2023-01-24 08:43:29.901776: step: 912/529, loss: 0.01057673804461956
2023-01-24 08:43:30.970568: step: 916/529, loss: 3.01747817843534e-08
2023-01-24 08:43:32.012145: step: 920/529, loss: 1.3981808706375887e-06
2023-01-24 08:43:33.056404: step: 924/529, loss: 0.000484986521769315
2023-01-24 08:43:34.110227: step: 928/529, loss: 0.0007219705730676651
2023-01-24 08:43:35.158426: step: 932/529, loss: 0.00012011743820039555
2023-01-24 08:43:36.204691: step: 936/529, loss: 6.555985601153225e-05
2023-01-24 08:43:37.247249: step: 940/529, loss: 6.393817670868884e-07
2023-01-24 08:43:38.295672: step: 944/529, loss: 0.0004756335401907563
2023-01-24 08:43:39.352713: step: 948/529, loss: 0.002182045252993703
2023-01-24 08:43:40.409022: step: 952/529, loss: 0.0037338100373744965
2023-01-24 08:43:41.460762: step: 956/529, loss: 0.0005437470390461385
2023-01-24 08:43:42.498399: step: 960/529, loss: 6.26626206212677e-05
2023-01-24 08:43:43.556703: step: 964/529, loss: 0.001162477070465684
2023-01-24 08:43:44.629511: step: 968/529, loss: 0.00018080721201840788
2023-01-24 08:43:45.669080: step: 972/529, loss: 0.0038940110243856907
2023-01-24 08:43:46.709690: step: 976/529, loss: 0.0009183697402477264
2023-01-24 08:43:47.763503: step: 980/529, loss: 0.0024008257314562798
2023-01-24 08:43:48.812831: step: 984/529, loss: 2.4911403670557775e-05
2023-01-24 08:43:49.859557: step: 988/529, loss: 9.713450708659366e-06
2023-01-24 08:43:50.898479: step: 992/529, loss: 0.0035002371296286583
2023-01-24 08:43:51.964156: step: 996/529, loss: 5.7572629884816706e-05
2023-01-24 08:43:53.001725: step: 1000/529, loss: 0.0008224198245443404
2023-01-24 08:43:54.066235: step: 1004/529, loss: 0.0009950370294973254
2023-01-24 08:43:55.100441: step: 1008/529, loss: 0.073013536632061
2023-01-24 08:43:56.162704: step: 1012/529, loss: 0.001277234754525125
2023-01-24 08:43:57.219075: step: 1016/529, loss: 0.0016240478726103902
2023-01-24 08:43:58.276710: step: 1020/529, loss: 0.0007413453422486782
2023-01-24 08:43:59.323925: step: 1024/529, loss: 0.0026388107798993587
2023-01-24 08:44:00.374926: step: 1028/529, loss: 0.014710264280438423
2023-01-24 08:44:01.451093: step: 1032/529, loss: 0.0020226004999130964
2023-01-24 08:44:02.494418: step: 1036/529, loss: 3.451769953244366e-05
2023-01-24 08:44:03.553978: step: 1040/529, loss: 0.0006276927306316793
2023-01-24 08:44:04.603699: step: 1044/529, loss: 0.008803611621260643
2023-01-24 08:44:05.655685: step: 1048/529, loss: 0.0048092738725245
2023-01-24 08:44:06.712616: step: 1052/529, loss: 0.0048506841994822025
2023-01-24 08:44:07.757225: step: 1056/529, loss: 0.00015693934983573854
2023-01-24 08:44:08.797368: step: 1060/529, loss: 0.006304030306637287
2023-01-24 08:44:09.835259: step: 1064/529, loss: 0.0005672169500030577
2023-01-24 08:44:10.884817: step: 1068/529, loss: 0.003880853531882167
2023-01-24 08:44:11.930121: step: 1072/529, loss: 0.001101834699511528
2023-01-24 08:44:12.971264: step: 1076/529, loss: 0.004893228877335787
2023-01-24 08:44:14.019659: step: 1080/529, loss: 0.0019595681224018335
2023-01-24 08:44:15.081250: step: 1084/529, loss: 6.072706310078502e-05
2023-01-24 08:44:16.114188: step: 1088/529, loss: 0.00018633095896802843
2023-01-24 08:44:17.150199: step: 1092/529, loss: 0.0006666929693892598
2023-01-24 08:44:18.209336: step: 1096/529, loss: 0.0025697543751448393
2023-01-24 08:44:19.257046: step: 1100/529, loss: 0.00966360792517662
2023-01-24 08:44:20.299845: step: 1104/529, loss: 0.007758964318782091
2023-01-24 08:44:21.336813: step: 1108/529, loss: 0.0001557979267090559
2023-01-24 08:44:22.374638: step: 1112/529, loss: 0.0025031110271811485
2023-01-24 08:44:23.433816: step: 1116/529, loss: 8.279283065348864e-05
2023-01-24 08:44:24.480786: step: 1120/529, loss: 0.00025012283003889024
2023-01-24 08:44:25.543942: step: 1124/529, loss: 0.012522703967988491
2023-01-24 08:44:26.593015: step: 1128/529, loss: 0.003896977286785841
2023-01-24 08:44:27.625748: step: 1132/529, loss: 0.004279047716408968
2023-01-24 08:44:28.661888: step: 1136/529, loss: 0.012906303629279137
2023-01-24 08:44:29.700532: step: 1140/529, loss: 0.000456074601970613
2023-01-24 08:44:30.744283: step: 1144/529, loss: 0.005379275418817997
2023-01-24 08:44:31.797345: step: 1148/529, loss: 0.0
2023-01-24 08:44:32.845502: step: 1152/529, loss: 7.604463917232351e-06
2023-01-24 08:44:33.902842: step: 1156/529, loss: 0.0008659998420625925
2023-01-24 08:44:34.940601: step: 1160/529, loss: 3.2693136745365337e-05
2023-01-24 08:44:35.997892: step: 1164/529, loss: 1.654587140365038e-05
2023-01-24 08:44:37.039675: step: 1168/529, loss: 0.0027732406742870808
2023-01-24 08:44:38.091886: step: 1172/529, loss: 0.002571322023868561
2023-01-24 08:44:39.163228: step: 1176/529, loss: 0.0010921157663688064
2023-01-24 08:44:40.205621: step: 1180/529, loss: 0.00040716270450502634
2023-01-24 08:44:41.243321: step: 1184/529, loss: 0.00018432759679853916
2023-01-24 08:44:42.294234: step: 1188/529, loss: 0.0016521831275895238
2023-01-24 08:44:43.358409: step: 1192/529, loss: 0.0032053953036665916
2023-01-24 08:44:44.401112: step: 1196/529, loss: 0.00013636599760502577
2023-01-24 08:44:45.455170: step: 1200/529, loss: 0.002532496117055416
2023-01-24 08:44:46.503761: step: 1204/529, loss: 0.0006596947787329555
2023-01-24 08:44:47.548551: step: 1208/529, loss: 0.003431640798225999
2023-01-24 08:44:48.607521: step: 1212/529, loss: 0.006484686397016048
2023-01-24 08:44:49.640375: step: 1216/529, loss: 0.011783484369516373
2023-01-24 08:44:50.707325: step: 1220/529, loss: 0.0014571624342352152
2023-01-24 08:44:51.763892: step: 1224/529, loss: 0.00394710386171937
2023-01-24 08:44:52.816423: step: 1228/529, loss: 0.0011190678924322128
2023-01-24 08:44:53.859489: step: 1232/529, loss: 0.0008478391682729125
2023-01-24 08:44:54.914727: step: 1236/529, loss: 0.008487425744533539
2023-01-24 08:44:55.967941: step: 1240/529, loss: 0.0018266314873471856
2023-01-24 08:44:57.006077: step: 1244/529, loss: 2.629393065944896e-06
2023-01-24 08:44:58.072922: step: 1248/529, loss: 0.010793100111186504
2023-01-24 08:44:59.121815: step: 1252/529, loss: 0.00481420336291194
2023-01-24 08:45:00.187556: step: 1256/529, loss: 0.0035192565992474556
2023-01-24 08:45:01.278937: step: 1260/529, loss: 0.0017764148069545627
2023-01-24 08:45:02.344240: step: 1264/529, loss: 0.012766020372509956
2023-01-24 08:45:03.402736: step: 1268/529, loss: 0.003010217100381851
2023-01-24 08:45:04.452262: step: 1272/529, loss: 6.0132886574137956e-05
2023-01-24 08:45:05.496172: step: 1276/529, loss: 0.0004403900820761919
2023-01-24 08:45:06.557608: step: 1280/529, loss: 0.0009248501737602055
2023-01-24 08:45:07.593840: step: 1284/529, loss: 0.0002384582912782207
2023-01-24 08:45:08.661211: step: 1288/529, loss: 0.002555337967351079
2023-01-24 08:45:09.712077: step: 1292/529, loss: 0.0002507092140149325
2023-01-24 08:45:10.745842: step: 1296/529, loss: 0.0026015995535999537
2023-01-24 08:45:11.806709: step: 1300/529, loss: 0.001694812555797398
2023-01-24 08:45:12.849159: step: 1304/529, loss: 0.0011641810415312648
2023-01-24 08:45:13.902529: step: 1308/529, loss: 0.001724598347209394
2023-01-24 08:45:14.967807: step: 1312/529, loss: 0.006431593094021082
2023-01-24 08:45:16.017566: step: 1316/529, loss: 0.002090152120217681
2023-01-24 08:45:17.047622: step: 1320/529, loss: 5.487705857376568e-05
2023-01-24 08:45:18.100730: step: 1324/529, loss: 2.2745467504137196e-05
2023-01-24 08:45:19.157383: step: 1328/529, loss: 0.003300593700259924
2023-01-24 08:45:20.215967: step: 1332/529, loss: 0.005172648001462221
2023-01-24 08:45:21.263688: step: 1336/529, loss: 0.0007595181232318282
2023-01-24 08:45:22.304943: step: 1340/529, loss: 1.1450428019088577e-06
2023-01-24 08:45:23.367621: step: 1344/529, loss: 0.007162860594689846
2023-01-24 08:45:24.423650: step: 1348/529, loss: 0.00020933207997586578
2023-01-24 08:45:25.472760: step: 1352/529, loss: 0.0005401194794103503
2023-01-24 08:45:26.518463: step: 1356/529, loss: 0.0008008277509361506
2023-01-24 08:45:27.573017: step: 1360/529, loss: 0.001986524323001504
2023-01-24 08:45:28.622938: step: 1364/529, loss: 0.002074284479022026
2023-01-24 08:45:29.672868: step: 1368/529, loss: 0.005155413877218962
2023-01-24 08:45:30.723472: step: 1372/529, loss: 0.0012436567340046167
2023-01-24 08:45:31.765099: step: 1376/529, loss: 0.0004564172704704106
2023-01-24 08:45:32.815054: step: 1380/529, loss: 0.0005330528365448117
2023-01-24 08:45:33.865662: step: 1384/529, loss: 0.0032763807103037834
2023-01-24 08:45:34.928482: step: 1388/529, loss: 0.005949295591562986
2023-01-24 08:45:35.976801: step: 1392/529, loss: 0.0003071699175052345
2023-01-24 08:45:37.042799: step: 1396/529, loss: 0.0008657476282678545
2023-01-24 08:45:38.088717: step: 1400/529, loss: 1.7594938981346786e-05
2023-01-24 08:45:39.145375: step: 1404/529, loss: 0.0017142250435426831
2023-01-24 08:45:40.194675: step: 1408/529, loss: 0.00010513482993701473
2023-01-24 08:45:41.246329: step: 1412/529, loss: 0.0031617714557796717
2023-01-24 08:45:42.311122: step: 1416/529, loss: 0.000547991890925914
2023-01-24 08:45:43.363767: step: 1420/529, loss: 0.004454748705029488
2023-01-24 08:45:44.429526: step: 1424/529, loss: 0.0002123908489011228
2023-01-24 08:45:45.493692: step: 1428/529, loss: 0.004882570821791887
2023-01-24 08:45:46.540395: step: 1432/529, loss: 0.00019020128820557147
2023-01-24 08:45:47.593988: step: 1436/529, loss: 0.00027187715750187635
2023-01-24 08:45:48.629352: step: 1440/529, loss: 0.005305198486894369
2023-01-24 08:45:49.701827: step: 1444/529, loss: 0.0012449203059077263
2023-01-24 08:45:50.755279: step: 1448/529, loss: 1.5262037777574733e-05
2023-01-24 08:45:51.812430: step: 1452/529, loss: 0.0006348938914015889
2023-01-24 08:45:52.840588: step: 1456/529, loss: 0.0016872693086043
2023-01-24 08:45:53.884292: step: 1460/529, loss: 0.015192359685897827
2023-01-24 08:45:54.935068: step: 1464/529, loss: 0.0032447664998471737
2023-01-24 08:45:55.984307: step: 1468/529, loss: 0.00844020489603281
2023-01-24 08:45:57.032226: step: 1472/529, loss: 0.00022272532805800438
2023-01-24 08:45:58.092214: step: 1476/529, loss: 0.00022737997642252594
2023-01-24 08:45:59.154254: step: 1480/529, loss: 0.0
2023-01-24 08:46:00.197928: step: 1484/529, loss: 0.001874983892776072
2023-01-24 08:46:01.232042: step: 1488/529, loss: 0.00038065973785705864
2023-01-24 08:46:02.281106: step: 1492/529, loss: 8.692263122611621e-07
2023-01-24 08:46:03.335774: step: 1496/529, loss: 0.0004208291647955775
2023-01-24 08:46:04.418955: step: 1500/529, loss: 5.434994454844855e-05
2023-01-24 08:46:05.487502: step: 1504/529, loss: 0.00021171863772906363
2023-01-24 08:46:06.550135: step: 1508/529, loss: 0.0011946558952331543
2023-01-24 08:46:07.593599: step: 1512/529, loss: 2.910380317189265e-06
2023-01-24 08:46:08.643731: step: 1516/529, loss: 0.0
2023-01-24 08:46:09.702841: step: 1520/529, loss: 0.007969740778207779
2023-01-24 08:46:10.750844: step: 1524/529, loss: 0.0032453781459480524
2023-01-24 08:46:11.808499: step: 1528/529, loss: 0.0008800202631391585
2023-01-24 08:46:12.883883: step: 1532/529, loss: 0.0012012722436338663
2023-01-24 08:46:13.937325: step: 1536/529, loss: 0.005758719053119421
2023-01-24 08:46:14.994232: step: 1540/529, loss: 0.0003173638542648405
2023-01-24 08:46:16.033837: step: 1544/529, loss: 0.0008564730524085462
2023-01-24 08:46:17.093155: step: 1548/529, loss: 0.005344030912965536
2023-01-24 08:46:18.138053: step: 1552/529, loss: 2.9557879770436557e-06
2023-01-24 08:46:19.190437: step: 1556/529, loss: 0.0023200325667858124
2023-01-24 08:46:20.259035: step: 1560/529, loss: 0.00039861808181740344
2023-01-24 08:46:21.318107: step: 1564/529, loss: 0.00012419767153915018
2023-01-24 08:46:22.366130: step: 1568/529, loss: 0.0004468669358175248
2023-01-24 08:46:23.402436: step: 1572/529, loss: 8.895461360225454e-05
2023-01-24 08:46:24.456361: step: 1576/529, loss: 0.0001357120490865782
2023-01-24 08:46:25.506806: step: 1580/529, loss: 0.003642322728410363
2023-01-24 08:46:26.546729: step: 1584/529, loss: 0.00018658670887816697
2023-01-24 08:46:27.600994: step: 1588/529, loss: 0.000754933396819979
2023-01-24 08:46:28.661125: step: 1592/529, loss: 0.0016611487371847034
2023-01-24 08:46:29.725688: step: 1596/529, loss: 0.00251749693416059
2023-01-24 08:46:30.775775: step: 1600/529, loss: 4.964217805536464e-05
2023-01-24 08:46:31.842017: step: 1604/529, loss: 0.006396192591637373
2023-01-24 08:46:32.904289: step: 1608/529, loss: 0.0006187082035467029
2023-01-24 08:46:33.955395: step: 1612/529, loss: 0.002235645428299904
2023-01-24 08:46:35.022825: step: 1616/529, loss: 0.014985614456236362
2023-01-24 08:46:36.081559: step: 1620/529, loss: 0.0016157664358615875
2023-01-24 08:46:37.129777: step: 1624/529, loss: 0.001053877524100244
2023-01-24 08:46:38.175081: step: 1628/529, loss: 8.34692400530912e-06
2023-01-24 08:46:39.230296: step: 1632/529, loss: 0.0004970920272171497
2023-01-24 08:46:40.277411: step: 1636/529, loss: 0.0015114513225853443
2023-01-24 08:46:41.356046: step: 1640/529, loss: 0.006017165258526802
2023-01-24 08:46:42.410463: step: 1644/529, loss: 5.3845211368752643e-05
2023-01-24 08:46:43.465591: step: 1648/529, loss: 0.004303459543734789
2023-01-24 08:46:44.512447: step: 1652/529, loss: 0.004388025496155024
2023-01-24 08:46:45.583331: step: 1656/529, loss: 3.1548393053526524e-06
2023-01-24 08:46:46.624865: step: 1660/529, loss: 0.0027100027073174715
2023-01-24 08:46:47.674721: step: 1664/529, loss: 0.00015716601046733558
2023-01-24 08:46:48.737363: step: 1668/529, loss: 1.820285979192704e-05
2023-01-24 08:46:49.786923: step: 1672/529, loss: 0.0003008978965226561
2023-01-24 08:46:50.841119: step: 1676/529, loss: 0.0002841920650098473
2023-01-24 08:46:51.897113: step: 1680/529, loss: 0.002616081153973937
2023-01-24 08:46:52.957900: step: 1684/529, loss: 0.003498291363939643
2023-01-24 08:46:54.000938: step: 1688/529, loss: 0.0023818283807486296
2023-01-24 08:46:55.060012: step: 1692/529, loss: 0.006639233790338039
2023-01-24 08:46:56.115563: step: 1696/529, loss: 0.003016442758962512
2023-01-24 08:46:57.165497: step: 1700/529, loss: 0.017751796171069145
2023-01-24 08:46:58.223087: step: 1704/529, loss: 6.527372170239687e-05
2023-01-24 08:46:59.277638: step: 1708/529, loss: 0.0005193384713493288
2023-01-24 08:47:00.337871: step: 1712/529, loss: 0.004485581070184708
2023-01-24 08:47:01.383951: step: 1716/529, loss: 0.0031725435983389616
2023-01-24 08:47:02.439914: step: 1720/529, loss: 5.109316771267913e-05
2023-01-24 08:47:03.487624: step: 1724/529, loss: 0.002191543811932206
2023-01-24 08:47:04.550114: step: 1728/529, loss: 0.001410142402164638
2023-01-24 08:47:05.595197: step: 1732/529, loss: 0.01683090627193451
2023-01-24 08:47:06.654247: step: 1736/529, loss: 0.0008119948906823993
2023-01-24 08:47:07.706138: step: 1740/529, loss: 3.625940371421166e-05
2023-01-24 08:47:08.757326: step: 1744/529, loss: 0.0033166503999382257
2023-01-24 08:47:09.794039: step: 1748/529, loss: 0.0022314991801977158
2023-01-24 08:47:10.829284: step: 1752/529, loss: 0.013277075253427029
2023-01-24 08:47:11.888037: step: 1756/529, loss: 0.0037621031515300274
2023-01-24 08:47:12.942848: step: 1760/529, loss: 0.0037755039520561695
2023-01-24 08:47:14.013991: step: 1764/529, loss: 0.004270235542207956
2023-01-24 08:47:15.072997: step: 1768/529, loss: 0.0008133032824844122
2023-01-24 08:47:16.134275: step: 1772/529, loss: 0.0040944661013782024
2023-01-24 08:47:17.194059: step: 1776/529, loss: 0.0029680330771952868
2023-01-24 08:47:18.245435: step: 1780/529, loss: 0.0017528339521959424
2023-01-24 08:47:19.306951: step: 1784/529, loss: 4.329274452175014e-05
2023-01-24 08:47:20.365482: step: 1788/529, loss: 0.0037056405562907457
2023-01-24 08:47:21.391885: step: 1792/529, loss: 0.005271711852401495
2023-01-24 08:47:22.442550: step: 1796/529, loss: 0.013049079105257988
2023-01-24 08:47:23.484027: step: 1800/529, loss: 0.0018134876154363155
2023-01-24 08:47:24.542281: step: 1804/529, loss: 0.0010871447157114744
2023-01-24 08:47:25.587341: step: 1808/529, loss: 0.0016010960098356009
2023-01-24 08:47:26.635745: step: 1812/529, loss: 0.0004666384484153241
2023-01-24 08:47:27.677738: step: 1816/529, loss: 0.00020002412202302366
2023-01-24 08:47:28.746386: step: 1820/529, loss: 1.077331580745522e-05
2023-01-24 08:47:29.803866: step: 1824/529, loss: 0.00046289816964417696
2023-01-24 08:47:30.860048: step: 1828/529, loss: 6.392893965312396e-07
2023-01-24 08:47:31.902676: step: 1832/529, loss: 0.00522138737142086
2023-01-24 08:47:32.960136: step: 1836/529, loss: 0.012564638629555702
2023-01-24 08:47:34.017906: step: 1840/529, loss: 0.0016117030754685402
2023-01-24 08:47:35.063819: step: 1844/529, loss: 0.001953144557774067
2023-01-24 08:47:36.142982: step: 1848/529, loss: 0.0006540084141306579
2023-01-24 08:47:37.196265: step: 1852/529, loss: 0.0015052793314680457
2023-01-24 08:47:38.257426: step: 1856/529, loss: 0.002739968476817012
2023-01-24 08:47:39.320500: step: 1860/529, loss: 0.0009505036869086325
2023-01-24 08:47:40.378604: step: 1864/529, loss: 0.0024099587462842464
2023-01-24 08:47:41.439756: step: 1868/529, loss: 0.07025769352912903
2023-01-24 08:47:42.483477: step: 1872/529, loss: 0.026688817888498306
2023-01-24 08:47:43.554888: step: 1876/529, loss: 0.00548132648691535
2023-01-24 08:47:44.604067: step: 1880/529, loss: 0.0007190339383669198
2023-01-24 08:47:45.665462: step: 1884/529, loss: 0.0017968656029552221
2023-01-24 08:47:46.724764: step: 1888/529, loss: 0.004982132464647293
2023-01-24 08:47:47.785332: step: 1892/529, loss: 0.00042749184649437666
2023-01-24 08:47:48.828440: step: 1896/529, loss: 0.0024509751237928867
2023-01-24 08:47:49.897425: step: 1900/529, loss: 0.0037298649549484253
2023-01-24 08:47:50.946431: step: 1904/529, loss: 0.0017633719835430384
2023-01-24 08:47:52.005352: step: 1908/529, loss: 0.005243165418505669
2023-01-24 08:47:53.053667: step: 1912/529, loss: 0.005373849533498287
2023-01-24 08:47:54.096857: step: 1916/529, loss: 0.00032256729900836945
2023-01-24 08:47:55.159443: step: 1920/529, loss: 0.0033623534254729748
2023-01-24 08:47:56.216724: step: 1924/529, loss: 0.003070567501708865
2023-01-24 08:47:57.271860: step: 1928/529, loss: 0.002718368312343955
2023-01-24 08:47:58.306104: step: 1932/529, loss: 0.002011633012443781
2023-01-24 08:47:59.354765: step: 1936/529, loss: 0.0019927772227674723
2023-01-24 08:48:00.389613: step: 1940/529, loss: 0.034562043845653534
2023-01-24 08:48:01.447400: step: 1944/529, loss: 0.0008598021231591702
2023-01-24 08:48:02.498977: step: 1948/529, loss: 0.0007520705694332719
2023-01-24 08:48:03.552167: step: 1952/529, loss: 2.8965780074940994e-05
2023-01-24 08:48:04.599449: step: 1956/529, loss: 2.3590742785017937e-05
2023-01-24 08:48:05.649838: step: 1960/529, loss: 0.0007883641519583762
2023-01-24 08:48:06.706707: step: 1964/529, loss: 3.965615906054154e-05
2023-01-24 08:48:07.753405: step: 1968/529, loss: 0.0003276301722507924
2023-01-24 08:48:08.817051: step: 1972/529, loss: 0.027409350499510765
2023-01-24 08:48:09.851542: step: 1976/529, loss: 0.00011540864215930924
2023-01-24 08:48:10.909322: step: 1980/529, loss: 0.004336873535066843
2023-01-24 08:48:11.960876: step: 1984/529, loss: 0.0015077319694682956
2023-01-24 08:48:13.013459: step: 1988/529, loss: 0.00011231971438974142
2023-01-24 08:48:14.062913: step: 1992/529, loss: 0.0077577074989676476
2023-01-24 08:48:15.117547: step: 1996/529, loss: 0.002097738441079855
2023-01-24 08:48:16.175336: step: 2000/529, loss: 0.0027897495310753584
2023-01-24 08:48:17.224269: step: 2004/529, loss: 0.005683586001396179
2023-01-24 08:48:18.277812: step: 2008/529, loss: 0.0024295884650200605
2023-01-24 08:48:19.308864: step: 2012/529, loss: 0.0014635955449193716
2023-01-24 08:48:20.372686: step: 2016/529, loss: 0.0021009203046560287
2023-01-24 08:48:21.438106: step: 2020/529, loss: 0.002894146367907524
2023-01-24 08:48:22.489259: step: 2024/529, loss: 0.0025358994025737047
2023-01-24 08:48:23.534258: step: 2028/529, loss: 0.0012495365226641297
2023-01-24 08:48:24.582917: step: 2032/529, loss: 0.001947436947375536
2023-01-24 08:48:25.643511: step: 2036/529, loss: 0.001579639152623713
2023-01-24 08:48:26.697442: step: 2040/529, loss: 0.003084776224568486
2023-01-24 08:48:27.759594: step: 2044/529, loss: 0.005247666500508785
2023-01-24 08:48:28.804872: step: 2048/529, loss: 3.92394099435478e-08
2023-01-24 08:48:29.848901: step: 2052/529, loss: 8.468618034385145e-05
2023-01-24 08:48:30.914588: step: 2056/529, loss: 0.00024022898287512362
2023-01-24 08:48:31.976494: step: 2060/529, loss: 0.003459519473835826
2023-01-24 08:48:33.038459: step: 2064/529, loss: 0.0008804468088783324
2023-01-24 08:48:34.093028: step: 2068/529, loss: 0.0029390763957053423
2023-01-24 08:48:35.148424: step: 2072/529, loss: 3.3073738450184464e-06
2023-01-24 08:48:36.217239: step: 2076/529, loss: 9.248141577700153e-05
2023-01-24 08:48:37.266828: step: 2080/529, loss: 0.0015206700190901756
2023-01-24 08:48:38.322998: step: 2084/529, loss: 0.0020256293937563896
2023-01-24 08:48:39.372446: step: 2088/529, loss: 0.002304591005668044
2023-01-24 08:48:40.430607: step: 2092/529, loss: 0.005249789450317621
2023-01-24 08:48:41.490900: step: 2096/529, loss: 0.0014370408607646823
2023-01-24 08:48:42.553946: step: 2100/529, loss: 1.5333351257140748e-05
2023-01-24 08:48:43.600906: step: 2104/529, loss: 0.00028622866375371814
2023-01-24 08:48:44.657233: step: 2108/529, loss: 0.00023616160615347326
2023-01-24 08:48:45.712416: step: 2112/529, loss: 0.0035260908771306276
2023-01-24 08:48:46.765350: step: 2116/529, loss: 0.0014810424763709307
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32576174986723316, 'r': 0.33256133098400653, 'f1': 0.3291264252179745}, 'combined': 0.24251420805534965, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.36977242791537, 'r': 0.3016904189361876, 'f1': 0.3322798847677761}, 'combined': 0.2337647430527068, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3601083509513742, 'r': 0.32320920303605316, 'f1': 0.3406625}, 'combined': 0.2510144736842105, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39413981508571133, 'r': 0.32122738856025684, 'f1': 0.35396787239428307}, 'combined': 0.25131718939994097, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3783697272661208, 'r': 0.34175330204681875, 'f1': 0.35913058859157226}, 'combined': 0.2646225389622111, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39946858404148117, 'r': 0.31364389262296205, 'f1': 0.3513916409523401}, 'combined': 0.24948806507616145, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3958333333333333, 'r': 0.41304347826086957, 'f1': 0.4042553191489362}, 'combined': 0.2021276595744681, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:51:18.877100: step: 4/529, loss: 0.01020224578678608
2023-01-24 08:51:19.942263: step: 8/529, loss: 0.001038275775499642
2023-01-24 08:51:20.983432: step: 12/529, loss: 0.004451533313840628
2023-01-24 08:51:22.019290: step: 16/529, loss: 6.889773067086935e-05
2023-01-24 08:51:23.063851: step: 20/529, loss: 0.00025243801064789295
2023-01-24 08:51:24.101917: step: 24/529, loss: 0.0004957487108185887
2023-01-24 08:51:25.162004: step: 28/529, loss: 0.004734248388558626
2023-01-24 08:51:26.205304: step: 32/529, loss: 2.4283556285809027e-06
2023-01-24 08:51:27.249463: step: 36/529, loss: 0.003568907268345356
2023-01-24 08:51:28.298397: step: 40/529, loss: 0.011332735419273376
2023-01-24 08:51:29.348484: step: 44/529, loss: 0.004035491030663252
2023-01-24 08:51:30.395060: step: 48/529, loss: 3.6534580431180075e-05
2023-01-24 08:51:31.440360: step: 52/529, loss: 0.0024630988482385874
2023-01-24 08:51:32.505537: step: 56/529, loss: 0.0050966860726475716
2023-01-24 08:51:33.548783: step: 60/529, loss: 0.0029295955318957567
2023-01-24 08:51:34.598454: step: 64/529, loss: 0.00012394499208312482
2023-01-24 08:51:35.638285: step: 68/529, loss: 0.006961142644286156
2023-01-24 08:51:36.687460: step: 72/529, loss: 0.0004412034759297967
2023-01-24 08:51:37.743151: step: 76/529, loss: 0.0004533159371931106
2023-01-24 08:51:38.783634: step: 80/529, loss: 0.0007916198228485882
2023-01-24 08:51:39.826626: step: 84/529, loss: 0.005906139966100454
2023-01-24 08:51:40.861789: step: 88/529, loss: 3.851462315651588e-05
2023-01-24 08:51:41.904525: step: 92/529, loss: 0.00021679847850464284
2023-01-24 08:51:42.945697: step: 96/529, loss: 0.00014462390390690416
2023-01-24 08:51:43.994096: step: 100/529, loss: 8.64245248521911e-06
2023-01-24 08:51:45.035134: step: 104/529, loss: 0.0012243962846696377
2023-01-24 08:51:46.059769: step: 108/529, loss: 0.0003185325476806611
2023-01-24 08:51:47.104575: step: 112/529, loss: 3.520370626119984e-07
2023-01-24 08:51:48.152390: step: 116/529, loss: 0.0038901912048459053
2023-01-24 08:51:49.221800: step: 120/529, loss: 0.003946762066334486
2023-01-24 08:51:50.239420: step: 124/529, loss: 0.0016868034144863486
2023-01-24 08:51:51.273752: step: 128/529, loss: 0.0010096969781443477
2023-01-24 08:51:52.312586: step: 132/529, loss: 0.0018946416676044464
2023-01-24 08:51:53.361171: step: 136/529, loss: 0.0005420464440248907
2023-01-24 08:51:54.419028: step: 140/529, loss: 0.00042443640995770693
2023-01-24 08:51:55.483000: step: 144/529, loss: 0.0032309689559042454
2023-01-24 08:51:56.543320: step: 148/529, loss: 0.0005011008470319211
2023-01-24 08:51:57.592689: step: 152/529, loss: 0.004462476819753647
2023-01-24 08:51:58.643846: step: 156/529, loss: 0.0002301966305822134
2023-01-24 08:51:59.692378: step: 160/529, loss: 0.0018660646164789796
2023-01-24 08:52:00.750512: step: 164/529, loss: 0.000342863000696525
2023-01-24 08:52:01.804565: step: 168/529, loss: 0.0010734939714893699
2023-01-24 08:52:02.841700: step: 172/529, loss: 4.1415383748244494e-05
2023-01-24 08:52:03.894233: step: 176/529, loss: 0.0016425435896962881
2023-01-24 08:52:04.934735: step: 180/529, loss: 0.00011480485409265384
2023-01-24 08:52:05.972701: step: 184/529, loss: 0.0012230741558596492
2023-01-24 08:52:07.062002: step: 188/529, loss: 0.0028023933991789818
2023-01-24 08:52:08.107017: step: 192/529, loss: 0.0006267766002565622
2023-01-24 08:52:09.160984: step: 196/529, loss: 0.004661646671593189
2023-01-24 08:52:10.218483: step: 200/529, loss: 2.9502174584195018e-05
2023-01-24 08:52:11.280419: step: 204/529, loss: 0.003575083101168275
2023-01-24 08:52:12.322345: step: 208/529, loss: 0.003380367299541831
2023-01-24 08:52:13.373663: step: 212/529, loss: 3.789372931350954e-05
2023-01-24 08:52:14.435113: step: 216/529, loss: 0.004658025223761797
2023-01-24 08:52:15.505146: step: 220/529, loss: 0.0013689477927982807
2023-01-24 08:52:16.538612: step: 224/529, loss: 0.003041380550712347
2023-01-24 08:52:17.580105: step: 228/529, loss: 0.00035840945201925933
2023-01-24 08:52:18.633161: step: 232/529, loss: 0.0015149172395467758
2023-01-24 08:52:19.704006: step: 236/529, loss: 0.002465092809870839
2023-01-24 08:52:20.760466: step: 240/529, loss: 0.004693541210144758
2023-01-24 08:52:21.845942: step: 244/529, loss: 0.001552620786242187
2023-01-24 08:52:22.902460: step: 248/529, loss: 0.0038326524663716555
2023-01-24 08:52:23.952873: step: 252/529, loss: 0.0004647152090910822
2023-01-24 08:52:25.026040: step: 256/529, loss: 0.025042515248060226
2023-01-24 08:52:26.054788: step: 260/529, loss: 0.0010135261109098792
2023-01-24 08:52:27.113427: step: 264/529, loss: 0.014272991567850113
2023-01-24 08:52:28.165044: step: 268/529, loss: 0.0023797154426574707
2023-01-24 08:52:29.218201: step: 272/529, loss: 0.00495926896110177
2023-01-24 08:52:30.287285: step: 276/529, loss: 0.0006001275032758713
2023-01-24 08:52:31.334907: step: 280/529, loss: 0.0002924794389400631
2023-01-24 08:52:32.392421: step: 284/529, loss: 0.0015000400599092245
2023-01-24 08:52:33.440061: step: 288/529, loss: 0.001308021484874189
2023-01-24 08:52:34.487285: step: 292/529, loss: 0.0010522921802476048
2023-01-24 08:52:35.533762: step: 296/529, loss: 0.0004613245837390423
2023-01-24 08:52:36.573490: step: 300/529, loss: 0.0002842767571564764
2023-01-24 08:52:37.615936: step: 304/529, loss: 0.0008032741025090218
2023-01-24 08:52:38.668362: step: 308/529, loss: 0.0012269504368305206
2023-01-24 08:52:39.721971: step: 312/529, loss: 0.001243873848579824
2023-01-24 08:52:40.786390: step: 316/529, loss: 0.0002523374860174954
2023-01-24 08:52:41.838322: step: 320/529, loss: 0.016158223152160645
2023-01-24 08:52:42.892213: step: 324/529, loss: 0.00047297487617470324
2023-01-24 08:52:43.936758: step: 328/529, loss: 0.0009529035305604339
2023-01-24 08:52:44.981868: step: 332/529, loss: 0.0028613354079425335
2023-01-24 08:52:46.033748: step: 336/529, loss: 0.0027586016803979874
2023-01-24 08:52:47.087003: step: 340/529, loss: 0.021542571485042572
2023-01-24 08:52:48.135219: step: 344/529, loss: 0.0006635222816839814
2023-01-24 08:52:49.179712: step: 348/529, loss: 0.002457924885675311
2023-01-24 08:52:50.223629: step: 352/529, loss: 0.004370444919914007
2023-01-24 08:52:51.267420: step: 356/529, loss: 4.536691994871944e-05
2023-01-24 08:52:52.309948: step: 360/529, loss: 0.0006607715040445328
2023-01-24 08:52:53.371068: step: 364/529, loss: 0.018543273210525513
2023-01-24 08:52:54.397461: step: 368/529, loss: 7.442723472195212e-06
2023-01-24 08:52:55.448462: step: 372/529, loss: 0.0004316781123634428
2023-01-24 08:52:56.482965: step: 376/529, loss: 0.0008909843163564801
2023-01-24 08:52:57.528048: step: 380/529, loss: 0.00260305218398571
2023-01-24 08:52:58.575522: step: 384/529, loss: 0.0016021401388570666
2023-01-24 08:52:59.621557: step: 388/529, loss: 0.0008654327248223126
2023-01-24 08:53:00.660348: step: 392/529, loss: 0.0017343726940453053
2023-01-24 08:53:01.711042: step: 396/529, loss: 0.006103570107370615
2023-01-24 08:53:02.768621: step: 400/529, loss: 0.0053910077549517155
2023-01-24 08:53:03.824071: step: 404/529, loss: 0.0010192233603447676
2023-01-24 08:53:04.876179: step: 408/529, loss: 0.00035351718543097377
2023-01-24 08:53:05.921631: step: 412/529, loss: 1.469642847951036e-05
2023-01-24 08:53:06.983969: step: 416/529, loss: 0.01276242733001709
2023-01-24 08:53:08.045123: step: 420/529, loss: 0.0004489815328270197
2023-01-24 08:53:09.113275: step: 424/529, loss: 0.006302860099822283
2023-01-24 08:53:10.159426: step: 428/529, loss: 0.0028011573012918234
2023-01-24 08:53:11.229172: step: 432/529, loss: 0.004192736465483904
2023-01-24 08:53:12.275575: step: 436/529, loss: 6.994755040068412e-06
2023-01-24 08:53:13.319435: step: 440/529, loss: 0.004379527177661657
2023-01-24 08:53:14.362445: step: 444/529, loss: 1.3323429811862297e-05
2023-01-24 08:53:15.414731: step: 448/529, loss: 1.2350157703622244e-05
2023-01-24 08:53:16.470192: step: 452/529, loss: 0.008350362069904804
2023-01-24 08:53:17.523811: step: 456/529, loss: 0.0014827616978436708
2023-01-24 08:53:18.593117: step: 460/529, loss: 0.0069276271387934685
2023-01-24 08:53:19.632342: step: 464/529, loss: 1.3515322279999964e-05
2023-01-24 08:53:20.671319: step: 468/529, loss: 0.0072339847683906555
2023-01-24 08:53:21.707651: step: 472/529, loss: 2.939150908787269e-05
2023-01-24 08:53:22.759731: step: 476/529, loss: 0.001304112491197884
2023-01-24 08:53:23.796918: step: 480/529, loss: 0.0
2023-01-24 08:53:24.844995: step: 484/529, loss: 0.0019746138714253902
2023-01-24 08:53:25.878468: step: 488/529, loss: 0.0010257518151775002
2023-01-24 08:53:26.936240: step: 492/529, loss: 0.0005876186187379062
2023-01-24 08:53:27.985303: step: 496/529, loss: 0.0009390351478941739
2023-01-24 08:53:29.035567: step: 500/529, loss: 0.00014850680599920452
2023-01-24 08:53:30.076206: step: 504/529, loss: 0.0008926878799684346
2023-01-24 08:53:31.105537: step: 508/529, loss: 0.00010936923354165629
2023-01-24 08:53:32.142239: step: 512/529, loss: 0.0020567565225064754
2023-01-24 08:53:33.202614: step: 516/529, loss: 0.0011070627951994538
2023-01-24 08:53:34.258014: step: 520/529, loss: 0.0011743379291146994
2023-01-24 08:53:35.291837: step: 524/529, loss: 0.0
2023-01-24 08:53:36.324993: step: 528/529, loss: 0.0017727799713611603
2023-01-24 08:53:37.362783: step: 532/529, loss: 0.002959632547572255
2023-01-24 08:53:38.413101: step: 536/529, loss: 0.0024419750552624464
2023-01-24 08:53:39.448452: step: 540/529, loss: 0.0018535548588261008
2023-01-24 08:53:40.514362: step: 544/529, loss: 0.002284358022734523
2023-01-24 08:53:41.548153: step: 548/529, loss: 0.0002934330841526389
2023-01-24 08:53:42.609119: step: 552/529, loss: 0.013296701945364475
2023-01-24 08:53:43.665103: step: 556/529, loss: 0.007606794126331806
2023-01-24 08:53:44.711472: step: 560/529, loss: 0.00023121789854485542
2023-01-24 08:53:45.745175: step: 564/529, loss: 0.002005623187869787
2023-01-24 08:53:46.787462: step: 568/529, loss: 0.0008986073080450296
2023-01-24 08:53:47.839079: step: 572/529, loss: 0.0038451733998954296
2023-01-24 08:53:48.884822: step: 576/529, loss: 0.00019060981867369264
2023-01-24 08:53:49.944141: step: 580/529, loss: 0.007954967208206654
2023-01-24 08:53:50.988627: step: 584/529, loss: 0.0008204479236155748
2023-01-24 08:53:52.036428: step: 588/529, loss: 0.00015575738507322967
2023-01-24 08:53:53.074919: step: 592/529, loss: 7.283411105163395e-05
2023-01-24 08:53:54.116482: step: 596/529, loss: 0.005061878822743893
2023-01-24 08:53:55.152892: step: 600/529, loss: 0.0006283560651354492
2023-01-24 08:53:56.196523: step: 604/529, loss: 0.0012664952082559466
2023-01-24 08:53:57.250602: step: 608/529, loss: 0.012886171229183674
2023-01-24 08:53:58.324284: step: 612/529, loss: 0.008504888974130154
2023-01-24 08:53:59.369114: step: 616/529, loss: 0.005694072227925062
2023-01-24 08:54:00.417338: step: 620/529, loss: 0.0014585453318431973
2023-01-24 08:54:01.452164: step: 624/529, loss: 0.004682051949203014
2023-01-24 08:54:02.489002: step: 628/529, loss: 0.0008764326921664178
2023-01-24 08:54:03.528651: step: 632/529, loss: 0.007216657046228647
2023-01-24 08:54:04.563172: step: 636/529, loss: 0.0024405259173363447
2023-01-24 08:54:05.612695: step: 640/529, loss: 0.015043944120407104
2023-01-24 08:54:06.667327: step: 644/529, loss: 0.0016021638875827193
2023-01-24 08:54:07.729527: step: 648/529, loss: 0.0069177523255348206
2023-01-24 08:54:08.792914: step: 652/529, loss: 0.020598584786057472
2023-01-24 08:54:09.850204: step: 656/529, loss: 0.005299469921737909
2023-01-24 08:54:10.914240: step: 660/529, loss: 0.0014310082187876105
2023-01-24 08:54:11.960254: step: 664/529, loss: 0.018393322825431824
2023-01-24 08:54:12.995430: step: 668/529, loss: 0.001749953255057335
2023-01-24 08:54:14.066668: step: 672/529, loss: 0.00043215241748839617
2023-01-24 08:54:15.117949: step: 676/529, loss: 0.00037163993692956865
2023-01-24 08:54:16.152146: step: 680/529, loss: 0.00016871781554073095
2023-01-24 08:54:17.202319: step: 684/529, loss: 0.0006988471141085029
2023-01-24 08:54:18.242032: step: 688/529, loss: 0.0005486601730808616
2023-01-24 08:54:19.301710: step: 692/529, loss: 0.0005506413872353733
2023-01-24 08:54:20.347153: step: 696/529, loss: 0.0015154248103499413
2023-01-24 08:54:21.387557: step: 700/529, loss: 3.223792009521276e-05
2023-01-24 08:54:22.433755: step: 704/529, loss: 5.116996544529684e-05
2023-01-24 08:54:23.474382: step: 708/529, loss: 0.0024150782264769077
2023-01-24 08:54:24.518808: step: 712/529, loss: 0.012429103255271912
2023-01-24 08:54:25.562245: step: 716/529, loss: 6.511987885460258e-05
2023-01-24 08:54:26.602032: step: 720/529, loss: 0.00019002445333171636
2023-01-24 08:54:27.644240: step: 724/529, loss: 0.0019587879069149494
2023-01-24 08:54:28.683217: step: 728/529, loss: 0.00010216245573246852
2023-01-24 08:54:29.750522: step: 732/529, loss: 0.007114600855857134
2023-01-24 08:54:30.803504: step: 736/529, loss: 0.0023248428478837013
2023-01-24 08:54:31.853424: step: 740/529, loss: 0.00011114242079202086
2023-01-24 08:54:32.896695: step: 744/529, loss: 0.0037037425208836794
2023-01-24 08:54:33.944411: step: 748/529, loss: 0.0018974484410136938
2023-01-24 08:54:34.992612: step: 752/529, loss: 0.0017257638974115252
2023-01-24 08:54:36.054580: step: 756/529, loss: 0.004929222632199526
2023-01-24 08:54:37.075832: step: 760/529, loss: 0.0007392786210402846
2023-01-24 08:54:38.115817: step: 764/529, loss: 0.0011080619879066944
2023-01-24 08:54:39.166496: step: 768/529, loss: 0.003100053174421191
2023-01-24 08:54:40.209739: step: 772/529, loss: 0.00916068535298109
2023-01-24 08:54:41.258542: step: 776/529, loss: 0.0002855100610759109
2023-01-24 08:54:42.299006: step: 780/529, loss: 2.480176590324845e-06
2023-01-24 08:54:43.353069: step: 784/529, loss: 0.0020733042620122433
2023-01-24 08:54:44.397994: step: 788/529, loss: 0.020637864246964455
2023-01-24 08:54:45.447608: step: 792/529, loss: 0.0021397285163402557
2023-01-24 08:54:46.479724: step: 796/529, loss: 0.0007428013486787677
2023-01-24 08:54:47.528391: step: 800/529, loss: 0.0027772216126322746
2023-01-24 08:54:48.577882: step: 804/529, loss: 0.009713134728372097
2023-01-24 08:54:49.635867: step: 808/529, loss: 0.00010844670032383874
2023-01-24 08:54:50.694501: step: 812/529, loss: 0.00199515069834888
2023-01-24 08:54:51.726588: step: 816/529, loss: 0.0012411541538313031
2023-01-24 08:54:52.768320: step: 820/529, loss: 0.0025561873335391283
2023-01-24 08:54:53.815571: step: 824/529, loss: 0.0028636467177420855
2023-01-24 08:54:54.870948: step: 828/529, loss: 0.001038305344991386
2023-01-24 08:54:55.911447: step: 832/529, loss: 0.0001132742254412733
2023-01-24 08:54:56.941478: step: 836/529, loss: 0.00041263323510065675
2023-01-24 08:54:58.011895: step: 840/529, loss: 0.0021278837230056524
2023-01-24 08:54:59.054192: step: 844/529, loss: 0.0016210832400247455
2023-01-24 08:55:00.100537: step: 848/529, loss: 0.0021596672013401985
2023-01-24 08:55:01.150010: step: 852/529, loss: 0.007536971475929022
2023-01-24 08:55:02.216744: step: 856/529, loss: 5.318777311913436e-06
2023-01-24 08:55:03.259277: step: 860/529, loss: 0.002978099975734949
2023-01-24 08:55:04.304961: step: 864/529, loss: 0.00030756407068111
2023-01-24 08:55:05.368753: step: 868/529, loss: 0.0021170349791646004
2023-01-24 08:55:06.402250: step: 872/529, loss: 0.00036889847251586616
2023-01-24 08:55:07.451168: step: 876/529, loss: 0.0014328219695016742
2023-01-24 08:55:08.507460: step: 880/529, loss: 0.012280371971428394
2023-01-24 08:55:09.545963: step: 884/529, loss: 0.00022847653599455953
2023-01-24 08:55:10.597213: step: 888/529, loss: 0.0008070432231761515
2023-01-24 08:55:11.636297: step: 892/529, loss: 8.982085273601115e-05
2023-01-24 08:55:12.682917: step: 896/529, loss: 0.0003182872314937413
2023-01-24 08:55:13.731893: step: 900/529, loss: 0.0029419977217912674
2023-01-24 08:55:14.774071: step: 904/529, loss: 0.0009877756237983704
2023-01-24 08:55:15.827071: step: 908/529, loss: 0.002101416001096368
2023-01-24 08:55:16.874008: step: 912/529, loss: 0.0014667791547253728
2023-01-24 08:55:17.912904: step: 916/529, loss: 0.006308733485639095
2023-01-24 08:55:18.945927: step: 920/529, loss: 0.005197822581976652
2023-01-24 08:55:19.999278: step: 924/529, loss: 0.006319757085293531
2023-01-24 08:55:21.048854: step: 928/529, loss: 0.0011957674287259579
2023-01-24 08:55:22.101115: step: 932/529, loss: 0.012306534685194492
2023-01-24 08:55:23.153851: step: 936/529, loss: 0.011566175147891045
2023-01-24 08:55:24.205727: step: 940/529, loss: 0.002246666233986616
2023-01-24 08:55:25.266902: step: 944/529, loss: 0.004516944754868746
2023-01-24 08:55:26.316172: step: 948/529, loss: 0.0011546433670446277
2023-01-24 08:55:27.365808: step: 952/529, loss: 0.0025093036238104105
2023-01-24 08:55:28.404058: step: 956/529, loss: 3.030756488442421e-05
2023-01-24 08:55:29.459288: step: 960/529, loss: 0.00680478336289525
2023-01-24 08:55:30.503596: step: 964/529, loss: 0.0028056518640369177
2023-01-24 08:55:31.558631: step: 968/529, loss: 0.002442787867039442
2023-01-24 08:55:32.609743: step: 972/529, loss: 0.009488247334957123
2023-01-24 08:55:33.669237: step: 976/529, loss: 0.005477927625179291
2023-01-24 08:55:34.719438: step: 980/529, loss: 0.0022455574944615364
2023-01-24 08:55:35.746509: step: 984/529, loss: 1.61015805133502e-06
2023-01-24 08:55:36.808607: step: 988/529, loss: 0.0037905306089669466
2023-01-24 08:55:37.847236: step: 992/529, loss: 0.008491587825119495
2023-01-24 08:55:38.896810: step: 996/529, loss: 0.0014774297596886754
2023-01-24 08:55:39.961741: step: 1000/529, loss: 0.04087931290268898
2023-01-24 08:55:41.007577: step: 1004/529, loss: 0.0004079646023456007
2023-01-24 08:55:42.065366: step: 1008/529, loss: 0.01202444825321436
2023-01-24 08:55:43.117307: step: 1012/529, loss: 0.007861970923841
2023-01-24 08:55:44.155569: step: 1016/529, loss: 0.0023448551073670387
2023-01-24 08:55:45.200294: step: 1020/529, loss: 0.0004027860122732818
2023-01-24 08:55:46.246695: step: 1024/529, loss: 0.0017309002578258514
2023-01-24 08:55:47.296766: step: 1028/529, loss: 0.006349599454551935
2023-01-24 08:55:48.354558: step: 1032/529, loss: 0.004194891545921564
2023-01-24 08:55:49.385875: step: 1036/529, loss: 0.0005259187310002744
2023-01-24 08:55:50.426814: step: 1040/529, loss: 1.7603459127712995e-05
2023-01-24 08:55:51.464275: step: 1044/529, loss: 0.0031094972509890795
2023-01-24 08:55:52.510406: step: 1048/529, loss: 0.0008957649115473032
2023-01-24 08:55:53.571213: step: 1052/529, loss: 0.00022809002257417887
2023-01-24 08:55:54.624964: step: 1056/529, loss: 0.0004975793417543173
2023-01-24 08:55:55.696921: step: 1060/529, loss: 0.0015375262591987848
2023-01-24 08:55:56.735178: step: 1064/529, loss: 6.921199542375689e-07
2023-01-24 08:55:57.801652: step: 1068/529, loss: 0.014460639096796513
2023-01-24 08:55:58.851364: step: 1072/529, loss: 3.608040788094513e-05
2023-01-24 08:55:59.896203: step: 1076/529, loss: 0.004664809443056583
2023-01-24 08:56:00.943799: step: 1080/529, loss: 0.0016583483666181564
2023-01-24 08:56:01.997248: step: 1084/529, loss: 9.832870273385197e-05
2023-01-24 08:56:03.050118: step: 1088/529, loss: 0.009572996757924557
2023-01-24 08:56:04.100298: step: 1092/529, loss: 0.0008603604510426521
2023-01-24 08:56:05.146083: step: 1096/529, loss: 0.0018287329003214836
2023-01-24 08:56:06.192047: step: 1100/529, loss: 6.251832382986322e-05
2023-01-24 08:56:07.253183: step: 1104/529, loss: 0.00021906968322582543
2023-01-24 08:56:08.285639: step: 1108/529, loss: 0.0006251359009183943
2023-01-24 08:56:09.361356: step: 1112/529, loss: 0.004658331163227558
2023-01-24 08:56:10.416660: step: 1116/529, loss: 0.0001569118903717026
2023-01-24 08:56:11.478513: step: 1120/529, loss: 0.0026589396875351667
2023-01-24 08:56:12.546522: step: 1124/529, loss: 0.004061589483171701
2023-01-24 08:56:13.591504: step: 1128/529, loss: 0.00023084548593033105
2023-01-24 08:56:14.638453: step: 1132/529, loss: 0.0002481299452483654
2023-01-24 08:56:15.690536: step: 1136/529, loss: 0.0007127048447728157
2023-01-24 08:56:16.744681: step: 1140/529, loss: 0.0012552737025544047
2023-01-24 08:56:17.781804: step: 1144/529, loss: 0.001212707837112248
2023-01-24 08:56:18.821506: step: 1148/529, loss: 0.015147602185606956
2023-01-24 08:56:19.860227: step: 1152/529, loss: 9.632313776819501e-06
2023-01-24 08:56:20.940614: step: 1156/529, loss: 0.0006420030258595943
2023-01-24 08:56:21.990327: step: 1160/529, loss: 0.003143442329019308
2023-01-24 08:56:23.015644: step: 1164/529, loss: 3.996547377482784e-07
2023-01-24 08:56:24.083632: step: 1168/529, loss: 0.0017192100640386343
2023-01-24 08:56:25.132967: step: 1172/529, loss: 0.006267572287470102
2023-01-24 08:56:26.197419: step: 1176/529, loss: 0.003107649739831686
2023-01-24 08:56:27.236788: step: 1180/529, loss: 0.009173891507089138
2023-01-24 08:56:28.282992: step: 1184/529, loss: 0.00747704366222024
2023-01-24 08:56:29.314874: step: 1188/529, loss: 4.948522837366909e-05
2023-01-24 08:56:30.344148: step: 1192/529, loss: 0.014866524375975132
2023-01-24 08:56:31.399759: step: 1196/529, loss: 0.0005889609456062317
2023-01-24 08:56:32.446790: step: 1200/529, loss: 0.005924674682319164
2023-01-24 08:56:33.486592: step: 1204/529, loss: 0.0015966873615980148
2023-01-24 08:56:34.547484: step: 1208/529, loss: 0.0036177290603518486
2023-01-24 08:56:35.585269: step: 1212/529, loss: 0.0025649038143455982
2023-01-24 08:56:36.646427: step: 1216/529, loss: 0.0003095596330240369
2023-01-24 08:56:37.704806: step: 1220/529, loss: 0.0013760351575911045
2023-01-24 08:56:38.770895: step: 1224/529, loss: 0.0001268725172849372
2023-01-24 08:56:39.857161: step: 1228/529, loss: 0.005040319170802832
2023-01-24 08:56:40.902264: step: 1232/529, loss: 0.0011752358404919505
2023-01-24 08:56:41.949469: step: 1236/529, loss: 0.0002349714341107756
2023-01-24 08:56:43.014668: step: 1240/529, loss: 0.00020718541054520756
2023-01-24 08:56:44.074158: step: 1244/529, loss: 5.89954033785034e-05
2023-01-24 08:56:45.122593: step: 1248/529, loss: 0.012769248336553574
2023-01-24 08:56:46.179954: step: 1252/529, loss: 2.2140580767882057e-05
2023-01-24 08:56:47.231414: step: 1256/529, loss: 0.002064930973574519
2023-01-24 08:56:48.279783: step: 1260/529, loss: 0.0002060915867332369
2023-01-24 08:56:49.340992: step: 1264/529, loss: 0.003926435951143503
2023-01-24 08:56:50.424929: step: 1268/529, loss: 0.0073271035216748714
2023-01-24 08:56:51.517187: step: 1272/529, loss: 0.006204522680491209
2023-01-24 08:56:52.567948: step: 1276/529, loss: 0.00024930195650085807
2023-01-24 08:56:53.614816: step: 1280/529, loss: 0.00010061332432087511
2023-01-24 08:56:54.667472: step: 1284/529, loss: 0.1535150110721588
2023-01-24 08:56:55.718940: step: 1288/529, loss: 7.727369666099548e-05
2023-01-24 08:56:56.779656: step: 1292/529, loss: 0.006720155943185091
2023-01-24 08:56:57.837109: step: 1296/529, loss: 0.0010046196402981877
2023-01-24 08:56:58.897431: step: 1300/529, loss: 0.003363081719726324
2023-01-24 08:56:59.966986: step: 1304/529, loss: 0.0024511751253157854
2023-01-24 08:57:01.002463: step: 1308/529, loss: 0.005486737471073866
2023-01-24 08:57:02.055744: step: 1312/529, loss: 1.6120116015372332e-06
2023-01-24 08:57:03.110705: step: 1316/529, loss: 0.00022121271467767656
2023-01-24 08:57:04.158886: step: 1320/529, loss: 0.004983570426702499
2023-01-24 08:57:05.217199: step: 1324/529, loss: 0.00015361949044745415
2023-01-24 08:57:06.285752: step: 1328/529, loss: 0.01476310845464468
2023-01-24 08:57:07.356032: step: 1332/529, loss: 0.0020758826285600662
2023-01-24 08:57:08.398280: step: 1336/529, loss: 0.009583096951246262
2023-01-24 08:57:09.457384: step: 1340/529, loss: 0.01055409200489521
2023-01-24 08:57:10.525996: step: 1344/529, loss: 0.0013980608200654387
2023-01-24 08:57:11.590864: step: 1348/529, loss: 9.119920287048444e-05
2023-01-24 08:57:12.649555: step: 1352/529, loss: 0.0014233322581276298
2023-01-24 08:57:13.702963: step: 1356/529, loss: 0.0010201798286288977
2023-01-24 08:57:14.752312: step: 1360/529, loss: 0.005234031472355127
2023-01-24 08:57:15.809564: step: 1364/529, loss: 0.0004037442849949002
2023-01-24 08:57:16.855312: step: 1368/529, loss: 0.0031365558970719576
2023-01-24 08:57:17.915780: step: 1372/529, loss: 0.0037918919697403908
2023-01-24 08:57:18.963629: step: 1376/529, loss: 0.005489441566169262
2023-01-24 08:57:20.026094: step: 1380/529, loss: 0.0016331516671925783
2023-01-24 08:57:21.087535: step: 1384/529, loss: 0.0007724243914708495
2023-01-24 08:57:22.123519: step: 1388/529, loss: 0.0005115661770105362
2023-01-24 08:57:23.176239: step: 1392/529, loss: 0.0009362163837067783
2023-01-24 08:57:24.234619: step: 1396/529, loss: 0.006333890836685896
2023-01-24 08:57:25.282823: step: 1400/529, loss: 0.001726830843836069
2023-01-24 08:57:26.332068: step: 1404/529, loss: 0.0012369524920359254
2023-01-24 08:57:27.401362: step: 1408/529, loss: 0.0012533077970147133
2023-01-24 08:57:28.452986: step: 1412/529, loss: 5.9968128880427685e-06
2023-01-24 08:57:29.508722: step: 1416/529, loss: 0.012621133588254452
2023-01-24 08:57:30.565003: step: 1420/529, loss: 2.3485405108658597e-05
2023-01-24 08:57:31.618485: step: 1424/529, loss: 0.0007823948399163783
2023-01-24 08:57:32.662200: step: 1428/529, loss: 0.00030054710805416107
2023-01-24 08:57:33.720013: step: 1432/529, loss: 0.0003316019137855619
2023-01-24 08:57:34.764726: step: 1436/529, loss: 0.00023224482720252126
2023-01-24 08:57:35.819570: step: 1440/529, loss: 0.0015086120693013072
2023-01-24 08:57:36.866971: step: 1444/529, loss: 2.732667098825914e-06
2023-01-24 08:57:37.924958: step: 1448/529, loss: 2.0481225874391384e-05
2023-01-24 08:57:38.982352: step: 1452/529, loss: 0.0005306907696649432
2023-01-24 08:57:40.030296: step: 1456/529, loss: 0.0032069191802293062
2023-01-24 08:57:41.090643: step: 1460/529, loss: 0.0004867032403126359
2023-01-24 08:57:42.145547: step: 1464/529, loss: 0.0007719406276009977
2023-01-24 08:57:43.211761: step: 1468/529, loss: 0.00237912661395967
2023-01-24 08:57:44.256677: step: 1472/529, loss: 0.005480147898197174
2023-01-24 08:57:45.305568: step: 1476/529, loss: 0.0023350315168499947
2023-01-24 08:57:46.356408: step: 1480/529, loss: 0.0004631670599337667
2023-01-24 08:57:47.434291: step: 1484/529, loss: 0.0005192183889448643
2023-01-24 08:57:48.505478: step: 1488/529, loss: 5.6485387176508084e-05
2023-01-24 08:57:49.560359: step: 1492/529, loss: 2.33264818234602e-05
2023-01-24 08:57:50.619755: step: 1496/529, loss: 0.004151428584009409
2023-01-24 08:57:51.685525: step: 1500/529, loss: 0.01216032262891531
2023-01-24 08:57:52.728222: step: 1504/529, loss: 0.003236118471249938
2023-01-24 08:57:53.795058: step: 1508/529, loss: 0.0007681510178372264
2023-01-24 08:57:54.851319: step: 1512/529, loss: 0.005313130095601082
2023-01-24 08:57:55.910320: step: 1516/529, loss: 0.0159964170306921
2023-01-24 08:57:56.976336: step: 1520/529, loss: 0.0031766127794981003
2023-01-24 08:57:58.018804: step: 1524/529, loss: 0.0011474760249257088
2023-01-24 08:57:59.079417: step: 1528/529, loss: 0.0017171096988022327
2023-01-24 08:58:00.129429: step: 1532/529, loss: 0.0030203568749129772
2023-01-24 08:58:01.186201: step: 1536/529, loss: 0.0029920160304754972
2023-01-24 08:58:02.230421: step: 1540/529, loss: 0.0011178237618878484
2023-01-24 08:58:03.289581: step: 1544/529, loss: 0.00041494384640827775
2023-01-24 08:58:04.339098: step: 1548/529, loss: 0.00232159742154181
2023-01-24 08:58:05.397734: step: 1552/529, loss: 0.00640843017026782
2023-01-24 08:58:06.459963: step: 1556/529, loss: 0.25127729773521423
2023-01-24 08:58:07.521097: step: 1560/529, loss: 0.00010403389751445502
2023-01-24 08:58:08.589255: step: 1564/529, loss: 0.005879843141883612
2023-01-24 08:58:09.633093: step: 1568/529, loss: 0.0007149177836254239
2023-01-24 08:58:10.688367: step: 1572/529, loss: 0.004294427111744881
2023-01-24 08:58:11.746548: step: 1576/529, loss: 0.00491734454408288
2023-01-24 08:58:12.811215: step: 1580/529, loss: 0.0003780702536460012
2023-01-24 08:58:13.886477: step: 1584/529, loss: 0.0009615807211957872
2023-01-24 08:58:14.937816: step: 1588/529, loss: 0.003977536223828793
2023-01-24 08:58:15.990598: step: 1592/529, loss: 0.0015690993750467896
2023-01-24 08:58:17.063959: step: 1596/529, loss: 0.00018145998183172196
2023-01-24 08:58:18.121681: step: 1600/529, loss: 0.004153602756559849
2023-01-24 08:58:19.188125: step: 1604/529, loss: 0.002182509284466505
2023-01-24 08:58:20.239952: step: 1608/529, loss: 0.000531440949998796
2023-01-24 08:58:21.284755: step: 1612/529, loss: 0.0010977921774610877
2023-01-24 08:58:22.349821: step: 1616/529, loss: 7.736185580142774e-06
2023-01-24 08:58:23.406572: step: 1620/529, loss: 0.00362329906783998
2023-01-24 08:58:24.465369: step: 1624/529, loss: 0.0030081227887421846
2023-01-24 08:58:25.526430: step: 1628/529, loss: 0.0012319168308749795
2023-01-24 08:58:26.576971: step: 1632/529, loss: 0.00022978046035859734
2023-01-24 08:58:27.629598: step: 1636/529, loss: 0.00293981796130538
2023-01-24 08:58:28.667100: step: 1640/529, loss: 0.00022636291396338493
2023-01-24 08:58:29.729835: step: 1644/529, loss: 0.00259410054422915
2023-01-24 08:58:30.781687: step: 1648/529, loss: 0.015043898485600948
2023-01-24 08:58:31.836493: step: 1652/529, loss: 0.001447760034352541
2023-01-24 08:58:32.901614: step: 1656/529, loss: 0.0020101305563002825
2023-01-24 08:58:33.980426: step: 1660/529, loss: 0.00012862659059464931
2023-01-24 08:58:35.049679: step: 1664/529, loss: 0.005591467954218388
2023-01-24 08:58:36.125789: step: 1668/529, loss: 0.0018924109172075987
2023-01-24 08:58:37.164037: step: 1672/529, loss: 0.00044598328531719744
2023-01-24 08:58:38.231207: step: 1676/529, loss: 0.001887521124444902
2023-01-24 08:58:39.266421: step: 1680/529, loss: 6.434936949517578e-05
2023-01-24 08:58:40.316172: step: 1684/529, loss: 0.000166017358424142
2023-01-24 08:58:41.400307: step: 1688/529, loss: 0.0009693322353996336
2023-01-24 08:58:42.448247: step: 1692/529, loss: 0.0002992482332047075
2023-01-24 08:58:43.493986: step: 1696/529, loss: 0.0031635286286473274
2023-01-24 08:58:44.562871: step: 1700/529, loss: 0.00011007118155248463
2023-01-24 08:58:45.612145: step: 1704/529, loss: 0.0014852352906018496
2023-01-24 08:58:46.658489: step: 1708/529, loss: 0.006421650759875774
2023-01-24 08:58:47.722066: step: 1712/529, loss: 0.004296513274312019
2023-01-24 08:58:48.794663: step: 1716/529, loss: 0.0036323938984423876
2023-01-24 08:58:49.847922: step: 1720/529, loss: 0.004876084625720978
2023-01-24 08:58:50.903510: step: 1724/529, loss: 0.11596772819757462
2023-01-24 08:58:51.960201: step: 1728/529, loss: 0.0007337495917454362
2023-01-24 08:58:53.012436: step: 1732/529, loss: 2.5273668597947108e-06
2023-01-24 08:58:54.086239: step: 1736/529, loss: 0.0026273801922798157
2023-01-24 08:58:55.156631: step: 1740/529, loss: 0.0017783537041395903
2023-01-24 08:58:56.208277: step: 1744/529, loss: 0.00010373223631177098
2023-01-24 08:58:57.271462: step: 1748/529, loss: 0.006678291596472263
2023-01-24 08:58:58.327448: step: 1752/529, loss: 0.0002827780263032764
2023-01-24 08:58:59.377894: step: 1756/529, loss: 0.0020619984716176987
2023-01-24 08:59:00.438553: step: 1760/529, loss: 0.00019636383512988687
2023-01-24 08:59:01.497079: step: 1764/529, loss: 0.008841020055115223
2023-01-24 08:59:02.569022: step: 1768/529, loss: 0.00794808566570282
2023-01-24 08:59:03.641478: step: 1772/529, loss: 0.0038560901302844286
2023-01-24 08:59:04.705199: step: 1776/529, loss: 0.0001471444556955248
2023-01-24 08:59:05.767619: step: 1780/529, loss: 0.0003520071040838957
2023-01-24 08:59:06.833169: step: 1784/529, loss: 0.0003683063550852239
2023-01-24 08:59:07.886951: step: 1788/529, loss: 0.0083543099462986
2023-01-24 08:59:08.936430: step: 1792/529, loss: 0.0006132580456323922
2023-01-24 08:59:09.986573: step: 1796/529, loss: 0.000706404447555542
2023-01-24 08:59:11.041283: step: 1800/529, loss: 0.0030958366114646196
2023-01-24 08:59:12.108466: step: 1804/529, loss: 0.00011058008385589346
2023-01-24 08:59:13.169649: step: 1808/529, loss: 0.0007416533771902323
2023-01-24 08:59:14.249454: step: 1812/529, loss: 0.0008773966110311449
2023-01-24 08:59:15.315116: step: 1816/529, loss: 3.629598722909577e-05
2023-01-24 08:59:16.365492: step: 1820/529, loss: 0.02118159830570221
2023-01-24 08:59:17.416443: step: 1824/529, loss: 0.006366293411701918
2023-01-24 08:59:18.496465: step: 1828/529, loss: 0.0031670264434069395
2023-01-24 08:59:19.557131: step: 1832/529, loss: 0.005692395381629467
2023-01-24 08:59:20.620606: step: 1836/529, loss: 0.0023344557266682386
2023-01-24 08:59:21.691888: step: 1840/529, loss: 0.0003732141340151429
2023-01-24 08:59:22.764472: step: 1844/529, loss: 0.002459442475810647
2023-01-24 08:59:23.814797: step: 1848/529, loss: 2.0189596398267895e-05
2023-01-24 08:59:24.869183: step: 1852/529, loss: 1.2635156053875107e-05
2023-01-24 08:59:25.920003: step: 1856/529, loss: 0.002220204332843423
2023-01-24 08:59:26.979331: step: 1860/529, loss: 0.0021807756274938583
2023-01-24 08:59:28.034382: step: 1864/529, loss: 3.0074792448431253e-05
2023-01-24 08:59:29.083712: step: 1868/529, loss: 0.00047109430306591094
2023-01-24 08:59:30.127061: step: 1872/529, loss: 0.00038470799336209893
2023-01-24 08:59:31.184923: step: 1876/529, loss: 0.005071605555713177
2023-01-24 08:59:32.234255: step: 1880/529, loss: 0.002654257696121931
2023-01-24 08:59:33.286201: step: 1884/529, loss: 0.002751089632511139
2023-01-24 08:59:34.330242: step: 1888/529, loss: 3.567804378690198e-05
2023-01-24 08:59:35.398463: step: 1892/529, loss: 0.0017417185008525848
2023-01-24 08:59:36.445320: step: 1896/529, loss: 0.0025109131820499897
2023-01-24 08:59:37.509449: step: 1900/529, loss: 0.002155064605176449
2023-01-24 08:59:38.571555: step: 1904/529, loss: 8.691265247762203e-05
2023-01-24 08:59:39.624813: step: 1908/529, loss: 0.0017757097957655787
2023-01-24 08:59:40.694426: step: 1912/529, loss: 0.012518827803432941
2023-01-24 08:59:41.753427: step: 1916/529, loss: 2.4005545128602535e-05
2023-01-24 08:59:42.816393: step: 1920/529, loss: 0.0029318202286958694
2023-01-24 08:59:43.872315: step: 1924/529, loss: 0.025592084974050522
2023-01-24 08:59:44.924787: step: 1928/529, loss: 0.0016514227027073503
2023-01-24 08:59:45.990098: step: 1932/529, loss: 0.00030073366360738873
2023-01-24 08:59:47.049972: step: 1936/529, loss: 0.002554918173700571
2023-01-24 08:59:48.124179: step: 1940/529, loss: 0.003918772097676992
2023-01-24 08:59:49.178162: step: 1944/529, loss: 0.0046285828575491905
2023-01-24 08:59:50.218036: step: 1948/529, loss: 1.0803324457242525e-08
2023-01-24 08:59:51.276967: step: 1952/529, loss: 0.00011952361819567159
2023-01-24 08:59:52.345140: step: 1956/529, loss: 0.0016779478173702955
2023-01-24 08:59:53.409085: step: 1960/529, loss: 0.00011592160444706678
2023-01-24 08:59:54.483659: step: 1964/529, loss: 0.007755772210657597
2023-01-24 08:59:55.551875: step: 1968/529, loss: 0.0001563423138577491
2023-01-24 08:59:56.609520: step: 1972/529, loss: 0.0029163986910134554
2023-01-24 08:59:57.672543: step: 1976/529, loss: 0.0015888672787696123
2023-01-24 08:59:58.729986: step: 1980/529, loss: 0.0048807356506586075
2023-01-24 08:59:59.785864: step: 1984/529, loss: 0.12338808923959732
2023-01-24 09:00:00.842852: step: 1988/529, loss: 0.0004344675107859075
2023-01-24 09:00:01.913915: step: 1992/529, loss: 0.0013709142804145813
2023-01-24 09:00:02.971352: step: 1996/529, loss: 3.03494198305998e-05
2023-01-24 09:00:04.028730: step: 2000/529, loss: 0.0017180825816467404
2023-01-24 09:00:05.084760: step: 2004/529, loss: 0.00857827253639698
2023-01-24 09:00:06.155273: step: 2008/529, loss: 0.005571542773395777
2023-01-24 09:00:07.215479: step: 2012/529, loss: 0.0001555430790176615
2023-01-24 09:00:08.271125: step: 2016/529, loss: 3.72719659935683e-05
2023-01-24 09:00:09.331431: step: 2020/529, loss: 0.000969858025200665
2023-01-24 09:00:10.398597: step: 2024/529, loss: 0.0016988699790090322
2023-01-24 09:00:11.457416: step: 2028/529, loss: 8.89981965883635e-05
2023-01-24 09:00:12.521429: step: 2032/529, loss: 0.004049374256283045
2023-01-24 09:00:13.585980: step: 2036/529, loss: 0.0025800098665058613
2023-01-24 09:00:14.639778: step: 2040/529, loss: 0.0009006074978969991
2023-01-24 09:00:15.696496: step: 2044/529, loss: 0.009920774959027767
2023-01-24 09:00:16.771719: step: 2048/529, loss: 0.007663106080144644
2023-01-24 09:00:17.825838: step: 2052/529, loss: 0.008067748509347439
2023-01-24 09:00:18.891643: step: 2056/529, loss: 0.012743399478495121
2023-01-24 09:00:19.954715: step: 2060/529, loss: 0.0007361077005043626
2023-01-24 09:00:20.999911: step: 2064/529, loss: 8.902257832232863e-05
2023-01-24 09:00:22.049659: step: 2068/529, loss: 4.594496203935705e-05
2023-01-24 09:00:23.113446: step: 2072/529, loss: 0.007268163841217756
2023-01-24 09:00:24.173545: step: 2076/529, loss: 0.01350079569965601
2023-01-24 09:00:25.230649: step: 2080/529, loss: 0.00037354984669946134
2023-01-24 09:00:26.282926: step: 2084/529, loss: 0.0017832600278779864
2023-01-24 09:00:27.344457: step: 2088/529, loss: 0.0001588617597008124
2023-01-24 09:00:28.406492: step: 2092/529, loss: 0.0036517693661153316
2023-01-24 09:00:29.462380: step: 2096/529, loss: 0.0006017301348038018
2023-01-24 09:00:30.531427: step: 2100/529, loss: 0.02015826478600502
2023-01-24 09:00:31.582190: step: 2104/529, loss: 0.0005979997222311795
2023-01-24 09:00:32.633929: step: 2108/529, loss: 0.0026851126458495855
2023-01-24 09:00:33.709412: step: 2112/529, loss: 0.0015570722753182054
2023-01-24 09:00:34.755411: step: 2116/529, loss: 0.003935635089874268
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32138088660878716, 'r': 0.33113818107888315, 'f1': 0.3261865821094793}, 'combined': 0.24034800787014265, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.36928655365946017, 'r': 0.3038719198087879, 'f1': 0.33340088090078596}, 'combined': 0.23455338354829164, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35184748427672957, 'r': 0.31846537001897535, 'f1': 0.3343251992031873}, 'combined': 0.24634488362340118, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3894655916030301, 'r': 0.3201366381239567, 'f1': 0.35141435564181456}, 'combined': 0.2495041925056883, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37730960288425414, 'r': 0.34222768534852654, 'f1': 0.35891341329089255}, 'combined': 0.26446251505644713, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.3952337632745502, 'r': 0.3134255520116083, 'f1': 0.34960765421655293}, 'combined': 0.24822143449375256, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3270833333333333, 'r': 0.37380952380952376, 'f1': 0.34888888888888886}, 'combined': 0.23259259259259257, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3942307692307692, 'r': 0.44565217391304346, 'f1': 0.4183673469387755}, 'combined': 0.20918367346938774, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3301107804232804, 'r': 0.3382539306044999, 'f1': 0.33413274869460435}, 'combined': 0.24620307798549793, 'stategy': 1, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9722222222222222, 'r': 0.5511811023622047, 'f1': 0.7035175879396985}, 'slot': {'p': 0.3732446088969678, 'r': 0.3038719198087879, 'f1': 0.33500454074157865}, 'combined': 0.2356815864513619, 'stategy': 1, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33547008547008544, 'r': 0.37380952380952376, 'f1': 0.3536036036036036}, 'combined': 0.23573573573573572, 'stategy': 1, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36017105263157895, 'r': 0.3246323529411765, 'f1': 0.3414795409181637}, 'combined': 0.2516165038344364, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.38863806127278544, 'r': 0.3170825369023162, 'f1': 0.3492326643825607}, 'combined': 0.24795519171161806, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41304347826086957, 'r': 0.41304347826086957, 'f1': 0.41304347826086957}, 'combined': 0.20652173913043478, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3843507101851221, 'r': 0.3493434348741432, 'f1': 0.36601190890392343}, 'combined': 0.26969298550815407, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9726027397260274, 'r': 0.5590551181102362, 'f1': 0.71}, 'slot': {'p': 0.39924443372719237, 'r': 0.3127705301775472, 'f1': 0.3507563732157606}, 'combined': 0.24903702498319, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.71875, 'r': 0.19827586206896552, 'f1': 0.31081081081081086}, 'combined': 0.20720720720720723, 'stategy': 1, 'epoch': 6}