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 05:23:46.233982: step: 4/530, loss: 0.014989728108048439
2023-01-24 05:23:47.296734: step: 8/530, loss: 0.0631004273891449
2023-01-24 05:23:48.365705: step: 12/530, loss: 0.057484276592731476
2023-01-24 05:23:49.434166: step: 16/530, loss: 0.014185488224029541
2023-01-24 05:23:50.494982: step: 20/530, loss: 0.023343700915575027
2023-01-24 05:23:51.555875: step: 24/530, loss: 0.023431705310940742
2023-01-24 05:23:52.624144: step: 28/530, loss: 0.06438823789358139
2023-01-24 05:23:53.707307: step: 32/530, loss: 0.017993750050663948
2023-01-24 05:23:54.763447: step: 36/530, loss: 0.014256988652050495
2023-01-24 05:23:55.827156: step: 40/530, loss: 0.04799354448914528
2023-01-24 05:23:56.888768: step: 44/530, loss: 0.016878558322787285
2023-01-24 05:23:57.939650: step: 48/530, loss: 0.06278853863477707
2023-01-24 05:23:59.004537: step: 52/530, loss: 0.058966729789972305
2023-01-24 05:24:00.074406: step: 56/530, loss: 0.01668539270758629
2023-01-24 05:24:01.142804: step: 60/530, loss: 0.01358208991587162
2023-01-24 05:24:02.234157: step: 64/530, loss: 0.06512077152729034
2023-01-24 05:24:03.289061: step: 68/530, loss: 0.01546466164290905
2023-01-24 05:24:04.356464: step: 72/530, loss: 0.04142314940690994
2023-01-24 05:24:05.417744: step: 76/530, loss: 0.07824798673391342
2023-01-24 05:24:06.467254: step: 80/530, loss: 0.015071926638484001
2023-01-24 05:24:07.507617: step: 84/530, loss: 0.010939154773950577
2023-01-24 05:24:08.574202: step: 88/530, loss: 0.11303721368312836
2023-01-24 05:24:09.628802: step: 92/530, loss: 0.021797168999910355
2023-01-24 05:24:10.685038: step: 96/530, loss: 0.032301679253578186
2023-01-24 05:24:11.765882: step: 100/530, loss: 0.010300903581082821
2023-01-24 05:24:12.822789: step: 104/530, loss: 0.028085211291909218
2023-01-24 05:24:13.866123: step: 108/530, loss: 0.04559174180030823
2023-01-24 05:24:14.935584: step: 112/530, loss: 0.01224962342530489
2023-01-24 05:24:15.996363: step: 116/530, loss: 0.024140994995832443
2023-01-24 05:24:17.035728: step: 120/530, loss: 0.005567555315792561
2023-01-24 05:24:18.102762: step: 124/530, loss: 0.029240408912301064
2023-01-24 05:24:19.175647: step: 128/530, loss: 0.05285908281803131
2023-01-24 05:24:20.236541: step: 132/530, loss: 0.010322146117687225
2023-01-24 05:24:21.324975: step: 136/530, loss: 0.029455265030264854
2023-01-24 05:24:22.386956: step: 140/530, loss: 0.007066186983138323
2023-01-24 05:24:23.469565: step: 144/530, loss: 0.011972458101809025
2023-01-24 05:24:24.529401: step: 148/530, loss: 0.1084207221865654
2023-01-24 05:24:25.611052: step: 152/530, loss: 0.01110046822577715
2023-01-24 05:24:26.667450: step: 156/530, loss: 0.02329319156706333
2023-01-24 05:24:27.741002: step: 160/530, loss: 0.05925683677196503
2023-01-24 05:24:28.815778: step: 164/530, loss: 0.04935720935463905
2023-01-24 05:24:29.880484: step: 168/530, loss: 0.05298709124326706
2023-01-24 05:24:30.934797: step: 172/530, loss: 0.012919852510094643
2023-01-24 05:24:31.994745: step: 176/530, loss: 0.02422485686838627
2023-01-24 05:24:33.085171: step: 180/530, loss: 0.017603116109967232
2023-01-24 05:24:34.154978: step: 184/530, loss: 0.06705053895711899
2023-01-24 05:24:35.201554: step: 188/530, loss: 0.0136328199878335
2023-01-24 05:24:36.266358: step: 192/530, loss: 0.015436515212059021
2023-01-24 05:24:37.324672: step: 196/530, loss: 0.009641746990382671
2023-01-24 05:24:38.373599: step: 200/530, loss: 0.01774834841489792
2023-01-24 05:24:39.441764: step: 204/530, loss: 0.028291190043091774
2023-01-24 05:24:40.499702: step: 208/530, loss: 0.05181780084967613
2023-01-24 05:24:41.553237: step: 212/530, loss: 0.013797377236187458
2023-01-24 05:24:42.579969: step: 216/530, loss: 0.020691271871328354
2023-01-24 05:24:43.643733: step: 220/530, loss: 0.043441515415906906
2023-01-24 05:24:44.707010: step: 224/530, loss: 0.01866997219622135
2023-01-24 05:24:45.753107: step: 228/530, loss: 0.018745601177215576
2023-01-24 05:24:46.820110: step: 232/530, loss: 0.07132137566804886
2023-01-24 05:24:47.883498: step: 236/530, loss: 0.054921817034482956
2023-01-24 05:24:48.946881: step: 240/530, loss: 0.009442034177482128
2023-01-24 05:24:49.999312: step: 244/530, loss: 0.007842033170163631
2023-01-24 05:24:51.050552: step: 248/530, loss: 0.0603717677295208
2023-01-24 05:24:52.124965: step: 252/530, loss: 0.01621413044631481
2023-01-24 05:24:53.179285: step: 256/530, loss: 0.05394862964749336
2023-01-24 05:24:54.231957: step: 260/530, loss: 0.0104429442435503
2023-01-24 05:24:55.286374: step: 264/530, loss: 0.0564584918320179
2023-01-24 05:24:56.358679: step: 268/530, loss: 0.019484298303723335
2023-01-24 05:24:57.405467: step: 272/530, loss: 0.019629139453172684
2023-01-24 05:24:58.448346: step: 276/530, loss: 0.021460773423314095
2023-01-24 05:24:59.495828: step: 280/530, loss: 0.05503295361995697
2023-01-24 05:25:00.558762: step: 284/530, loss: 0.009837611578404903
2023-01-24 05:25:01.623004: step: 288/530, loss: 0.011039389297366142
2023-01-24 05:25:02.687305: step: 292/530, loss: 0.057780586183071136
2023-01-24 05:25:03.748657: step: 296/530, loss: 0.014904126524925232
2023-01-24 05:25:04.804176: step: 300/530, loss: 0.016140734776854515
2023-01-24 05:25:05.889429: step: 304/530, loss: 0.009469042532145977
2023-01-24 05:25:06.928888: step: 308/530, loss: 0.009803948923945427
2023-01-24 05:25:07.989570: step: 312/530, loss: 0.01831057481467724
2023-01-24 05:25:09.047619: step: 316/530, loss: 0.021061651408672333
2023-01-24 05:25:10.103235: step: 320/530, loss: 0.009302419610321522
2023-01-24 05:25:11.155250: step: 324/530, loss: 0.014836013317108154
2023-01-24 05:25:12.221055: step: 328/530, loss: 0.01203369814902544
2023-01-24 05:25:13.276253: step: 332/530, loss: 0.01554011832922697
2023-01-24 05:25:14.329459: step: 336/530, loss: 0.01864892616868019
2023-01-24 05:25:15.390459: step: 340/530, loss: 0.020686931908130646
2023-01-24 05:25:16.438368: step: 344/530, loss: 0.054095566272735596
2023-01-24 05:25:17.503618: step: 348/530, loss: 0.01348794437944889
2023-01-24 05:25:18.562704: step: 352/530, loss: 0.03215435519814491
2023-01-24 05:25:19.626388: step: 356/530, loss: 0.0546780526638031
2023-01-24 05:25:20.686339: step: 360/530, loss: 0.015380472876131535
2023-01-24 05:25:21.746116: step: 364/530, loss: 0.042847588658332825
2023-01-24 05:25:22.802660: step: 368/530, loss: 0.04920646920800209
2023-01-24 05:25:23.851529: step: 372/530, loss: 0.0374562032520771
2023-01-24 05:25:24.932650: step: 376/530, loss: 0.008779056370258331
2023-01-24 05:25:25.987303: step: 380/530, loss: 0.020624835044145584
2023-01-24 05:25:27.052462: step: 384/530, loss: 0.02881811000406742
2023-01-24 05:25:28.119977: step: 388/530, loss: 0.010995946824550629
2023-01-24 05:25:29.176035: step: 392/530, loss: 0.01900155283510685
2023-01-24 05:25:30.243007: step: 396/530, loss: 0.010911948047578335
2023-01-24 05:25:31.299772: step: 400/530, loss: 0.012622319161891937
2023-01-24 05:25:32.391276: step: 404/530, loss: 0.0487946979701519
2023-01-24 05:25:33.452942: step: 408/530, loss: 0.017283709719777107
2023-01-24 05:25:34.521413: step: 412/530, loss: 0.023072047159075737
2023-01-24 05:25:35.574783: step: 416/530, loss: 0.011532754637300968
2023-01-24 05:25:36.637685: step: 420/530, loss: 0.034171223640441895
2023-01-24 05:25:37.711515: step: 424/530, loss: 0.011274424381554127
2023-01-24 05:25:38.776341: step: 428/530, loss: 0.012324047274887562
2023-01-24 05:25:39.839973: step: 432/530, loss: 0.024326754733920097
2023-01-24 05:25:40.898531: step: 436/530, loss: 0.007780241314321756
2023-01-24 05:25:41.968868: step: 440/530, loss: 0.01872764155268669
2023-01-24 05:25:43.031624: step: 444/530, loss: 0.011733146384358406
2023-01-24 05:25:44.105858: step: 448/530, loss: 0.047770146280527115
2023-01-24 05:25:45.160588: step: 452/530, loss: 0.016551673412322998
2023-01-24 05:25:46.227656: step: 456/530, loss: 0.02890522964298725
2023-01-24 05:25:47.291991: step: 460/530, loss: 0.013094899244606495
2023-01-24 05:25:48.340755: step: 464/530, loss: 0.04893617704510689
2023-01-24 05:25:49.391496: step: 468/530, loss: 0.01000905130058527
2023-01-24 05:25:50.462352: step: 472/530, loss: 0.03276755288243294
2023-01-24 05:25:51.516762: step: 476/530, loss: 0.011166263371706009
2023-01-24 05:25:52.579837: step: 480/530, loss: 0.00775465602055192
2023-01-24 05:25:53.631780: step: 484/530, loss: 0.01759321428835392
2023-01-24 05:25:54.686822: step: 488/530, loss: 0.015101979486644268
2023-01-24 05:25:55.769534: step: 492/530, loss: 0.06601301580667496
2023-01-24 05:25:56.835038: step: 496/530, loss: 0.019960390403866768
2023-01-24 05:25:57.904721: step: 500/530, loss: 0.01699841395020485
2023-01-24 05:25:58.967179: step: 504/530, loss: 0.03768926113843918
2023-01-24 05:26:00.029734: step: 508/530, loss: 0.00735285971313715
2023-01-24 05:26:01.096726: step: 512/530, loss: 0.05614430457353592
2023-01-24 05:26:02.156420: step: 516/530, loss: 0.012637794949114323
2023-01-24 05:26:03.236034: step: 520/530, loss: 0.057916633784770966
2023-01-24 05:26:04.294462: step: 524/530, loss: 0.010749287903308868
2023-01-24 05:26:05.342333: step: 528/530, loss: 0.008063401095569134
2023-01-24 05:26:06.400191: step: 532/530, loss: 0.02903282269835472
2023-01-24 05:26:07.459097: step: 536/530, loss: 0.023172693327069283
2023-01-24 05:26:08.540055: step: 540/530, loss: 0.015488462522625923
2023-01-24 05:26:09.597900: step: 544/530, loss: 0.026907317340373993
2023-01-24 05:26:10.656151: step: 548/530, loss: 0.045936115086078644
2023-01-24 05:26:11.735161: step: 552/530, loss: 0.011412173509597778
2023-01-24 05:26:12.803197: step: 556/530, loss: 0.04243732988834381
2023-01-24 05:26:13.861379: step: 560/530, loss: 0.04376460239291191
2023-01-24 05:26:14.926630: step: 564/530, loss: 0.026789255440235138
2023-01-24 05:26:15.999196: step: 568/530, loss: 0.012236343696713448
2023-01-24 05:26:17.077626: step: 572/530, loss: 0.012834625318646431
2023-01-24 05:26:18.132893: step: 576/530, loss: 0.016574393957853317
2023-01-24 05:26:19.190801: step: 580/530, loss: 0.009535718709230423
2023-01-24 05:26:20.263433: step: 584/530, loss: 0.012673421762883663
2023-01-24 05:26:21.337505: step: 588/530, loss: 0.018470723181962967
2023-01-24 05:26:22.387446: step: 592/530, loss: 0.0056436434388160706
2023-01-24 05:26:23.462848: step: 596/530, loss: 0.016215182840824127
2023-01-24 05:26:24.527647: step: 600/530, loss: 0.0062405942007899284
2023-01-24 05:26:25.597692: step: 604/530, loss: 0.00820606853812933
2023-01-24 05:26:26.673743: step: 608/530, loss: 0.03268307074904442
2023-01-24 05:26:27.747144: step: 612/530, loss: 0.009284308180212975
2023-01-24 05:26:28.813686: step: 616/530, loss: 0.0331835076212883
2023-01-24 05:26:29.883228: step: 620/530, loss: 0.007031688001006842
2023-01-24 05:26:30.969281: step: 624/530, loss: 0.06537856161594391
2023-01-24 05:26:32.038219: step: 628/530, loss: 0.02514232136309147
2023-01-24 05:26:33.095757: step: 632/530, loss: 0.00874092523008585
2023-01-24 05:26:34.153897: step: 636/530, loss: 0.06390761584043503
2023-01-24 05:26:35.203007: step: 640/530, loss: 0.034691959619522095
2023-01-24 05:26:36.255291: step: 644/530, loss: 0.05095821991562843
2023-01-24 05:26:37.318182: step: 648/530, loss: 0.012088949792087078
2023-01-24 05:26:38.416216: step: 652/530, loss: 0.014043556526303291
2023-01-24 05:26:39.473893: step: 656/530, loss: 0.012328085489571095
2023-01-24 05:26:40.523765: step: 660/530, loss: 0.03906030207872391
2023-01-24 05:26:41.573492: step: 664/530, loss: 0.015492179431021214
2023-01-24 05:26:42.639684: step: 668/530, loss: 0.01013824064284563
2023-01-24 05:26:43.694340: step: 672/530, loss: 0.008601384237408638
2023-01-24 05:26:44.743338: step: 676/530, loss: 0.014922229573130608
2023-01-24 05:26:45.796206: step: 680/530, loss: 0.009068300947546959
2023-01-24 05:26:46.857702: step: 684/530, loss: 0.0280601903796196
2023-01-24 05:26:47.934950: step: 688/530, loss: 0.05199253559112549
2023-01-24 05:26:48.991051: step: 692/530, loss: 0.009235409088432789
2023-01-24 05:26:50.053266: step: 696/530, loss: 0.02695978619158268
2023-01-24 05:26:51.115774: step: 700/530, loss: 0.006813299376517534
2023-01-24 05:26:52.185111: step: 704/530, loss: 0.010859019123017788
2023-01-24 05:26:53.246331: step: 708/530, loss: 0.051554251462221146
2023-01-24 05:26:54.315906: step: 712/530, loss: 0.01295298058539629
2023-01-24 05:26:55.398435: step: 716/530, loss: 0.019465964287519455
2023-01-24 05:26:56.461764: step: 720/530, loss: 0.01544218510389328
2023-01-24 05:26:57.526674: step: 724/530, loss: 0.03997999429702759
2023-01-24 05:26:58.593595: step: 728/530, loss: 0.05005812272429466
2023-01-24 05:26:59.641934: step: 732/530, loss: 0.014670837670564651
2023-01-24 05:27:00.697832: step: 736/530, loss: 0.00936712697148323
2023-01-24 05:27:01.784541: step: 740/530, loss: 0.1010412722826004
2023-01-24 05:27:02.858665: step: 744/530, loss: 0.035943444818258286
2023-01-24 05:27:03.933102: step: 748/530, loss: 0.024367138743400574
2023-01-24 05:27:04.991012: step: 752/530, loss: 0.00898853037506342
2023-01-24 05:27:06.056082: step: 756/530, loss: 0.0656907930970192
2023-01-24 05:27:07.115597: step: 760/530, loss: 0.003028588369488716
2023-01-24 05:27:08.168433: step: 764/530, loss: 0.020819412544369698
2023-01-24 05:27:09.237331: step: 768/530, loss: 0.0076109240762889385
2023-01-24 05:27:10.297119: step: 772/530, loss: 0.005995367653667927
2023-01-24 05:27:11.367948: step: 776/530, loss: 0.011457452550530434
2023-01-24 05:27:12.426961: step: 780/530, loss: 0.01923304609954357
2023-01-24 05:27:13.464490: step: 784/530, loss: 0.004144433420151472
2023-01-24 05:27:14.517898: step: 788/530, loss: 0.0
2023-01-24 05:27:15.584371: step: 792/530, loss: 0.01116340234875679
2023-01-24 05:27:16.647345: step: 796/530, loss: 0.0073156291618943214
2023-01-24 05:27:17.725827: step: 800/530, loss: 0.03794460371136665
2023-01-24 05:27:18.807371: step: 804/530, loss: 0.02856852486729622
2023-01-24 05:27:19.880746: step: 808/530, loss: 0.007266498636454344
2023-01-24 05:27:20.947807: step: 812/530, loss: 0.010797679424285889
2023-01-24 05:27:21.995545: step: 816/530, loss: 0.053594592958688736
2023-01-24 05:27:23.064471: step: 820/530, loss: 0.004362649284303188
2023-01-24 05:27:24.108155: step: 824/530, loss: 0.013535166159272194
2023-01-24 05:27:25.164161: step: 828/530, loss: 0.013190332800149918
2023-01-24 05:27:26.220567: step: 832/530, loss: 0.010341054759919643
2023-01-24 05:27:27.276949: step: 836/530, loss: 0.010193286463618279
2023-01-24 05:27:28.326019: step: 840/530, loss: 0.021329592913389206
2023-01-24 05:27:29.396844: step: 844/530, loss: 0.007516507524996996
2023-01-24 05:27:30.449623: step: 848/530, loss: 0.011846790090203285
2023-01-24 05:27:31.512604: step: 852/530, loss: 0.011247259564697742
2023-01-24 05:27:32.581438: step: 856/530, loss: 0.05322021245956421
2023-01-24 05:27:33.651340: step: 860/530, loss: 0.010131759569048882
2023-01-24 05:27:34.711631: step: 864/530, loss: 0.04282288998365402
2023-01-24 05:27:35.780153: step: 868/530, loss: 0.008373168297111988
2023-01-24 05:27:36.862070: step: 872/530, loss: 0.05640947073698044
2023-01-24 05:27:37.926998: step: 876/530, loss: 0.006427661050111055
2023-01-24 05:27:38.988232: step: 880/530, loss: 0.018995806574821472
2023-01-24 05:27:40.033189: step: 884/530, loss: 0.03825213760137558
2023-01-24 05:27:41.091085: step: 888/530, loss: 0.00936310738325119
2023-01-24 05:27:42.139587: step: 892/530, loss: 0.010521425865590572
2023-01-24 05:27:43.199626: step: 896/530, loss: 0.01497871708124876
2023-01-24 05:27:44.242033: step: 900/530, loss: 0.006770298816263676
2023-01-24 05:27:45.283876: step: 904/530, loss: 0.013842870481312275
2023-01-24 05:27:46.338144: step: 908/530, loss: 0.016851462423801422
2023-01-24 05:27:47.396303: step: 912/530, loss: 0.04374687001109123
2023-01-24 05:27:48.447564: step: 916/530, loss: 0.06402844935655594
2023-01-24 05:27:49.529291: step: 920/530, loss: 0.007186340168118477
2023-01-24 05:27:50.591001: step: 924/530, loss: 0.006947611458599567
2023-01-24 05:27:51.651127: step: 928/530, loss: 0.010150546208024025
2023-01-24 05:27:52.728727: step: 932/530, loss: 0.03677567094564438
2023-01-24 05:27:53.795177: step: 936/530, loss: 0.046463266015052795
2023-01-24 05:27:54.854618: step: 940/530, loss: 0.03405112773180008
2023-01-24 05:27:55.918492: step: 944/530, loss: 0.035727210342884064
2023-01-24 05:27:56.986560: step: 948/530, loss: 0.01393832266330719
2023-01-24 05:27:58.046325: step: 952/530, loss: 0.00514913210645318
2023-01-24 05:27:59.109668: step: 956/530, loss: 0.0049138423055410385
2023-01-24 05:28:00.179409: step: 960/530, loss: 0.014473812654614449
2023-01-24 05:28:01.224181: step: 964/530, loss: 0.01810336485505104
2023-01-24 05:28:02.325060: step: 968/530, loss: 0.06051211804151535
2023-01-24 05:28:03.383719: step: 972/530, loss: 0.025683708488941193
2023-01-24 05:28:04.442950: step: 976/530, loss: 0.04642287641763687
2023-01-24 05:28:05.511458: step: 980/530, loss: 0.007159307133406401
2023-01-24 05:28:06.600618: step: 984/530, loss: 0.01314071100205183
2023-01-24 05:28:07.664397: step: 988/530, loss: 0.008624155074357986
2023-01-24 05:28:08.724185: step: 992/530, loss: 0.011762621812522411
2023-01-24 05:28:09.782081: step: 996/530, loss: 0.002586920280009508
2023-01-24 05:28:10.846539: step: 1000/530, loss: 0.004858341533690691
2023-01-24 05:28:11.906443: step: 1004/530, loss: 0.011473674327135086
2023-01-24 05:28:12.967436: step: 1008/530, loss: 0.012196864932775497
2023-01-24 05:28:14.035628: step: 1012/530, loss: 0.03536411374807358
2023-01-24 05:28:15.096969: step: 1016/530, loss: 0.04359541833400726
2023-01-24 05:28:16.164766: step: 1020/530, loss: 0.010759529657661915
2023-01-24 05:28:17.221808: step: 1024/530, loss: 0.0
2023-01-24 05:28:18.279381: step: 1028/530, loss: 0.007376645691692829
2023-01-24 05:28:19.329248: step: 1032/530, loss: 0.016261782497167587
2023-01-24 05:28:20.394961: step: 1036/530, loss: 0.007587794214487076
2023-01-24 05:28:21.454554: step: 1040/530, loss: 0.012331432662904263
2023-01-24 05:28:22.524839: step: 1044/530, loss: 0.0559673085808754
2023-01-24 05:28:23.618827: step: 1048/530, loss: 0.010683332569897175
2023-01-24 05:28:24.668541: step: 1052/530, loss: 0.01462164893746376
2023-01-24 05:28:25.739832: step: 1056/530, loss: 0.010988554917275906
2023-01-24 05:28:26.826801: step: 1060/530, loss: 0.007587789092212915
2023-01-24 05:28:27.880587: step: 1064/530, loss: 0.04696919396519661
2023-01-24 05:28:28.935709: step: 1068/530, loss: 0.01268306840211153
2023-01-24 05:28:30.002635: step: 1072/530, loss: 0.01825232431292534
2023-01-24 05:28:31.073158: step: 1076/530, loss: 0.0070555065758526325
2023-01-24 05:28:32.149708: step: 1080/530, loss: 0.006043289788067341
2023-01-24 05:28:33.218388: step: 1084/530, loss: 0.012065306305885315
2023-01-24 05:28:34.284114: step: 1088/530, loss: 0.007906339131295681
2023-01-24 05:28:35.343136: step: 1092/530, loss: 0.010578767396509647
2023-01-24 05:28:36.389070: step: 1096/530, loss: 0.014258671551942825
2023-01-24 05:28:37.457068: step: 1100/530, loss: 0.005523975472897291
2023-01-24 05:28:38.523615: step: 1104/530, loss: 0.006160045508295298
2023-01-24 05:28:39.592280: step: 1108/530, loss: 0.019277600571513176
2023-01-24 05:28:40.669165: step: 1112/530, loss: 0.022061079740524292
2023-01-24 05:28:41.723713: step: 1116/530, loss: 0.004279881715774536
2023-01-24 05:28:42.792265: step: 1120/530, loss: 0.027891699224710464
2023-01-24 05:28:43.859884: step: 1124/530, loss: 0.05023053660988808
2023-01-24 05:28:44.934303: step: 1128/530, loss: 0.0016466941451653838
2023-01-24 05:28:46.011053: step: 1132/530, loss: 0.0240631066262722
2023-01-24 05:28:47.070794: step: 1136/530, loss: 0.005580810364335775
2023-01-24 05:28:48.126676: step: 1140/530, loss: 0.0032665585167706013
2023-01-24 05:28:49.196579: step: 1144/530, loss: 0.004518146626651287
2023-01-24 05:28:50.268761: step: 1148/530, loss: 0.008799486793577671
2023-01-24 05:28:51.331980: step: 1152/530, loss: 0.006526159588247538
2023-01-24 05:28:52.387881: step: 1156/530, loss: 0.0445825457572937
2023-01-24 05:28:53.457893: step: 1160/530, loss: 0.04344402253627777
2023-01-24 05:28:54.527309: step: 1164/530, loss: 0.01872437447309494
2023-01-24 05:28:55.607675: step: 1168/530, loss: 0.0625322237610817
2023-01-24 05:28:56.666790: step: 1172/530, loss: 0.007066223304718733
2023-01-24 05:28:57.723492: step: 1176/530, loss: 0.03241466358304024
2023-01-24 05:28:58.805509: step: 1180/530, loss: 0.0055928598158061504
2023-01-24 05:28:59.858960: step: 1184/530, loss: 0.05248646065592766
2023-01-24 05:29:00.923588: step: 1188/530, loss: 0.02023748867213726
2023-01-24 05:29:01.990667: step: 1192/530, loss: 0.0369214229285717
2023-01-24 05:29:03.054478: step: 1196/530, loss: 0.022305499762296677
2023-01-24 05:29:04.128135: step: 1200/530, loss: 0.015122110955417156
2023-01-24 05:29:05.182101: step: 1204/530, loss: 0.01642940565943718
2023-01-24 05:29:06.234766: step: 1208/530, loss: 0.006676771212369204
2023-01-24 05:29:07.307459: step: 1212/530, loss: 0.004971812013536692
2023-01-24 05:29:08.352991: step: 1216/530, loss: 0.01663142256438732
2023-01-24 05:29:09.432401: step: 1220/530, loss: 0.015099186450242996
2023-01-24 05:29:10.495106: step: 1224/530, loss: 0.00491509260609746
2023-01-24 05:29:11.559724: step: 1228/530, loss: 0.050172943621873856
2023-01-24 05:29:12.605648: step: 1232/530, loss: 0.07353024184703827
2023-01-24 05:29:13.682220: step: 1236/530, loss: 0.05253772437572479
2023-01-24 05:29:14.753867: step: 1240/530, loss: 0.07221702486276627
2023-01-24 05:29:15.806078: step: 1244/530, loss: 0.08229915052652359
2023-01-24 05:29:16.860228: step: 1248/530, loss: 0.008013667538762093
2023-01-24 05:29:17.926674: step: 1252/530, loss: 0.008296540938317776
2023-01-24 05:29:18.994018: step: 1256/530, loss: 0.013247084803879261
2023-01-24 05:29:20.055107: step: 1260/530, loss: 0.039408937096595764
2023-01-24 05:29:21.124368: step: 1264/530, loss: 0.022857001051306725
2023-01-24 05:29:22.188486: step: 1268/530, loss: 0.09486035257577896
2023-01-24 05:29:23.230624: step: 1272/530, loss: 0.006343443412333727
2023-01-24 05:29:24.280996: step: 1276/530, loss: 0.006245467346161604
2023-01-24 05:29:25.349034: step: 1280/530, loss: 0.011517812497913837
2023-01-24 05:29:26.432347: step: 1284/530, loss: 0.027390016242861748
2023-01-24 05:29:27.499337: step: 1288/530, loss: 0.05465123429894447
2023-01-24 05:29:28.585707: step: 1292/530, loss: 0.029385672882199287
2023-01-24 05:29:29.667952: step: 1296/530, loss: 0.011082857847213745
2023-01-24 05:29:30.730936: step: 1300/530, loss: 0.010165059007704258
2023-01-24 05:29:31.788046: step: 1304/530, loss: 0.009124458767473698
2023-01-24 05:29:32.879143: step: 1308/530, loss: 0.0709029883146286
2023-01-24 05:29:33.940490: step: 1312/530, loss: 0.017112143337726593
2023-01-24 05:29:35.009619: step: 1316/530, loss: 0.018398692831397057
2023-01-24 05:29:36.079426: step: 1320/530, loss: 0.009186377748847008
2023-01-24 05:29:37.166350: step: 1324/530, loss: 0.0165835153311491
2023-01-24 05:29:38.238416: step: 1328/530, loss: 0.05665843188762665
2023-01-24 05:29:39.286215: step: 1332/530, loss: 0.010099775157868862
2023-01-24 05:29:40.355036: step: 1336/530, loss: 0.009929196909070015
2023-01-24 05:29:41.419358: step: 1340/530, loss: 0.011640582233667374
2023-01-24 05:29:42.480636: step: 1344/530, loss: 0.009187677875161171
2023-01-24 05:29:43.548600: step: 1348/530, loss: 0.05760704725980759
2023-01-24 05:29:44.609400: step: 1352/530, loss: 0.0032530431635677814
2023-01-24 05:29:45.677004: step: 1356/530, loss: 0.010160473175346851
2023-01-24 05:29:46.749111: step: 1360/530, loss: 0.010763449594378471
2023-01-24 05:29:47.810517: step: 1364/530, loss: 0.024489203467965126
2023-01-24 05:29:48.873293: step: 1368/530, loss: 0.044015008956193924
2023-01-24 05:29:49.929137: step: 1372/530, loss: 0.011772742494940758
2023-01-24 05:29:50.991174: step: 1376/530, loss: 0.010082654654979706
2023-01-24 05:29:52.052249: step: 1380/530, loss: 0.011007610708475113
2023-01-24 05:29:53.107421: step: 1384/530, loss: 0.04948361590504646
2023-01-24 05:29:54.166445: step: 1388/530, loss: 0.03764904662966728
2023-01-24 05:29:55.225921: step: 1392/530, loss: 0.015111290849745274
2023-01-24 05:29:56.282006: step: 1396/530, loss: 0.04680466651916504
2023-01-24 05:29:57.345202: step: 1400/530, loss: 0.06037868559360504
2023-01-24 05:29:58.422961: step: 1404/530, loss: 0.0025439017917960882
2023-01-24 05:29:59.492046: step: 1408/530, loss: 0.013582988642156124
2023-01-24 05:30:00.549365: step: 1412/530, loss: 0.011048753745853901
2023-01-24 05:30:01.617877: step: 1416/530, loss: 0.032101117074489594
2023-01-24 05:30:02.660685: step: 1420/530, loss: 0.01761852391064167
2023-01-24 05:30:03.718856: step: 1424/530, loss: 0.05801999941468239
2023-01-24 05:30:04.775875: step: 1428/530, loss: 0.0034850211814045906
2023-01-24 05:30:05.838822: step: 1432/530, loss: 0.006018470507115126
2023-01-24 05:30:06.885212: step: 1436/530, loss: 0.016149142757058144
2023-01-24 05:30:07.953316: step: 1440/530, loss: 0.022863702848553658
2023-01-24 05:30:09.014338: step: 1444/530, loss: 0.012102514505386353
2023-01-24 05:30:10.083136: step: 1448/530, loss: 0.09349612146615982
2023-01-24 05:30:11.153365: step: 1452/530, loss: 0.009717483073472977
2023-01-24 05:30:12.208096: step: 1456/530, loss: 0.007673966232687235
2023-01-24 05:30:13.249885: step: 1460/530, loss: 0.010607304982841015
2023-01-24 05:30:14.312791: step: 1464/530, loss: 0.028118545189499855
2023-01-24 05:30:15.379344: step: 1468/530, loss: 0.05583770573139191
2023-01-24 05:30:16.439872: step: 1472/530, loss: 0.03914321959018707
2023-01-24 05:30:17.510873: step: 1476/530, loss: 0.04705042764544487
2023-01-24 05:30:18.594304: step: 1480/530, loss: 0.011493569239974022
2023-01-24 05:30:19.646950: step: 1484/530, loss: 0.01587658002972603
2023-01-24 05:30:20.716003: step: 1488/530, loss: 0.033804040402173996
2023-01-24 05:30:21.784330: step: 1492/530, loss: 0.038401950150728226
2023-01-24 05:30:22.851623: step: 1496/530, loss: 0.015206553973257542
2023-01-24 05:30:23.920969: step: 1500/530, loss: 0.015448298305273056
2023-01-24 05:30:24.993825: step: 1504/530, loss: 0.0
2023-01-24 05:30:26.041666: step: 1508/530, loss: 0.014555639587342739
2023-01-24 05:30:27.090802: step: 1512/530, loss: 0.01882525533437729
2023-01-24 05:30:28.139018: step: 1516/530, loss: 0.007516829762607813
2023-01-24 05:30:29.199813: step: 1520/530, loss: 0.011755396611988544
2023-01-24 05:30:30.277257: step: 1524/530, loss: 0.04681158438324928
2023-01-24 05:30:31.343947: step: 1528/530, loss: 0.029220009222626686
2023-01-24 05:30:32.410726: step: 1532/530, loss: 0.012017552740871906
2023-01-24 05:30:33.481136: step: 1536/530, loss: 0.049115028232336044
2023-01-24 05:30:34.551915: step: 1540/530, loss: 0.04238603264093399
2023-01-24 05:30:35.613119: step: 1544/530, loss: 0.022604364901781082
2023-01-24 05:30:36.673859: step: 1548/530, loss: 0.06295600533485413
2023-01-24 05:30:37.719245: step: 1552/530, loss: 0.029475726187229156
2023-01-24 05:30:38.781904: step: 1556/530, loss: 0.006206018850207329
2023-01-24 05:30:39.842219: step: 1560/530, loss: 0.0006113530835136771
2023-01-24 05:30:40.903140: step: 1564/530, loss: 0.026363978162407875
2023-01-24 05:30:41.971587: step: 1568/530, loss: 0.005621196702122688
2023-01-24 05:30:43.048016: step: 1572/530, loss: 0.010632461868226528
2023-01-24 05:30:44.118518: step: 1576/530, loss: 0.008851172402501106
2023-01-24 05:30:45.179302: step: 1580/530, loss: 0.007686966098845005
2023-01-24 05:30:46.261959: step: 1584/530, loss: 0.010417128913104534
2023-01-24 05:30:47.329150: step: 1588/530, loss: 0.009220454841852188
2023-01-24 05:30:48.383368: step: 1592/530, loss: 0.04846467077732086
2023-01-24 05:30:49.450498: step: 1596/530, loss: 0.008378441445529461
2023-01-24 05:30:50.512262: step: 1600/530, loss: 0.010829788632690907
2023-01-24 05:30:51.583197: step: 1604/530, loss: 0.05643141269683838
2023-01-24 05:30:52.645139: step: 1608/530, loss: 0.005940014496445656
2023-01-24 05:30:53.725096: step: 1612/530, loss: 0.009098365902900696
2023-01-24 05:30:54.767206: step: 1616/530, loss: 0.005947449244558811
2023-01-24 05:30:55.810907: step: 1620/530, loss: 0.007603847421705723
2023-01-24 05:30:56.868329: step: 1624/530, loss: 0.015103227458894253
2023-01-24 05:30:57.941589: step: 1628/530, loss: 0.03847254812717438
2023-01-24 05:30:59.003628: step: 1632/530, loss: 0.014274196699261665
2023-01-24 05:31:00.055681: step: 1636/530, loss: 0.0012899849098175764
2023-01-24 05:31:01.113508: step: 1640/530, loss: 0.013747187331318855
2023-01-24 05:31:02.169939: step: 1644/530, loss: 0.008819185197353363
2023-01-24 05:31:03.225303: step: 1648/530, loss: 0.013215270824730396
2023-01-24 05:31:04.283896: step: 1652/530, loss: 0.004616389982402325
2023-01-24 05:31:05.341495: step: 1656/530, loss: 0.007974857464432716
2023-01-24 05:31:06.391787: step: 1660/530, loss: 0.0667194351553917
2023-01-24 05:31:07.447588: step: 1664/530, loss: 0.015447521582245827
2023-01-24 05:31:08.508372: step: 1668/530, loss: 0.01486852765083313
2023-01-24 05:31:09.567071: step: 1672/530, loss: 0.015161690302193165
2023-01-24 05:31:10.606680: step: 1676/530, loss: 0.04072938114404678
2023-01-24 05:31:11.671982: step: 1680/530, loss: 0.031799569725990295
2023-01-24 05:31:12.724394: step: 1684/530, loss: 0.017142189666628838
2023-01-24 05:31:13.802374: step: 1688/530, loss: 0.009336385875940323
2023-01-24 05:31:14.863443: step: 1692/530, loss: 0.00813746452331543
2023-01-24 05:31:15.917715: step: 1696/530, loss: 0.02112860605120659
2023-01-24 05:31:16.978151: step: 1700/530, loss: 0.007506415713578463
2023-01-24 05:31:18.035100: step: 1704/530, loss: 0.013389104045927525
2023-01-24 05:31:19.078044: step: 1708/530, loss: 0.011649283580482006
2023-01-24 05:31:20.160543: step: 1712/530, loss: 0.015604037791490555
2023-01-24 05:31:21.200005: step: 1716/530, loss: 0.015770137310028076
2023-01-24 05:31:22.260768: step: 1720/530, loss: 0.003947843797504902
2023-01-24 05:31:23.304517: step: 1724/530, loss: 0.0032538867089897394
2023-01-24 05:31:24.364065: step: 1728/530, loss: 0.006099522579461336
2023-01-24 05:31:25.428777: step: 1732/530, loss: 0.041710905730724335
2023-01-24 05:31:26.480239: step: 1736/530, loss: 0.008037427440285683
2023-01-24 05:31:27.534472: step: 1740/530, loss: 0.00854603759944439
2023-01-24 05:31:28.599634: step: 1744/530, loss: 0.010882861912250519
2023-01-24 05:31:29.653599: step: 1748/530, loss: 0.012188882566988468
2023-01-24 05:31:30.740733: step: 1752/530, loss: 0.0063628642819821835
2023-01-24 05:31:31.800511: step: 1756/530, loss: 0.009983053430914879
2023-01-24 05:31:32.885413: step: 1760/530, loss: 0.007224540691822767
2023-01-24 05:31:33.937121: step: 1764/530, loss: 0.013252705335617065
2023-01-24 05:31:35.004019: step: 1768/530, loss: 0.006915170233696699
2023-01-24 05:31:36.048394: step: 1772/530, loss: 0.004516227636486292
2023-01-24 05:31:37.116836: step: 1776/530, loss: 0.00857698917388916
2023-01-24 05:31:38.175024: step: 1780/530, loss: 0.007978210225701332
2023-01-24 05:31:39.228891: step: 1784/530, loss: 0.028052492067217827
2023-01-24 05:31:40.282894: step: 1788/530, loss: 0.015040180645883083
2023-01-24 05:31:41.335958: step: 1792/530, loss: 0.004561109934002161
2023-01-24 05:31:42.400365: step: 1796/530, loss: 0.0024614883586764336
2023-01-24 05:31:43.445326: step: 1800/530, loss: 0.012629399076104164
2023-01-24 05:31:44.509113: step: 1804/530, loss: 0.026167742908000946
2023-01-24 05:31:45.569838: step: 1808/530, loss: 0.013068159110844135
2023-01-24 05:31:46.630621: step: 1812/530, loss: 0.02562149241566658
2023-01-24 05:31:47.699691: step: 1816/530, loss: 0.03479331359267235
2023-01-24 05:31:48.741491: step: 1820/530, loss: 0.009271216578781605
2023-01-24 05:31:49.800015: step: 1824/530, loss: 0.02221786603331566
2023-01-24 05:31:50.885856: step: 1828/530, loss: 0.04992489144206047
2023-01-24 05:31:51.946040: step: 1832/530, loss: 0.0033437497913837433
2023-01-24 05:31:52.997990: step: 1836/530, loss: 0.006941276602447033
2023-01-24 05:31:54.053402: step: 1840/530, loss: 0.008557932451367378
2023-01-24 05:31:55.112490: step: 1844/530, loss: 0.00855118315666914
2023-01-24 05:31:56.180001: step: 1848/530, loss: 0.011229374445974827
2023-01-24 05:31:57.245351: step: 1852/530, loss: 0.010633961297571659
2023-01-24 05:31:58.291363: step: 1856/530, loss: 0.004392093513160944
2023-01-24 05:31:59.361653: step: 1860/530, loss: 0.029662800952792168
2023-01-24 05:32:00.427193: step: 1864/530, loss: 0.04898121580481529
2023-01-24 05:32:01.483342: step: 1868/530, loss: 0.029796553775668144
2023-01-24 05:32:02.555116: step: 1872/530, loss: 0.005181239452213049
2023-01-24 05:32:03.597611: step: 1876/530, loss: 0.012479596771299839
2023-01-24 05:32:04.650895: step: 1880/530, loss: 0.02138441987335682
2023-01-24 05:32:05.714017: step: 1884/530, loss: 0.006832160521298647
2023-01-24 05:32:06.774384: step: 1888/530, loss: 0.027198806405067444
2023-01-24 05:32:07.834653: step: 1892/530, loss: 0.026703640818595886
2023-01-24 05:32:08.884950: step: 1896/530, loss: 0.013256896287202835
2023-01-24 05:32:09.950576: step: 1900/530, loss: 0.015921026468276978
2023-01-24 05:32:11.022505: step: 1904/530, loss: 0.045949023216962814
2023-01-24 05:32:12.095393: step: 1908/530, loss: 0.020568108186125755
2023-01-24 05:32:13.144540: step: 1912/530, loss: 0.0072805872187018394
2023-01-24 05:32:14.192669: step: 1916/530, loss: 0.0062551070004701614
2023-01-24 05:32:15.258984: step: 1920/530, loss: 0.005042138509452343
2023-01-24 05:32:16.315374: step: 1924/530, loss: 0.07306154817342758
2023-01-24 05:32:17.361340: step: 1928/530, loss: 0.013020550832152367
2023-01-24 05:32:18.404400: step: 1932/530, loss: 0.04458221420645714
2023-01-24 05:32:19.456607: step: 1936/530, loss: 0.025175368413329124
2023-01-24 05:32:20.528877: step: 1940/530, loss: 0.03908427804708481
2023-01-24 05:32:21.581757: step: 1944/530, loss: 0.00235062837600708
2023-01-24 05:32:22.642370: step: 1948/530, loss: 0.010473492555320263
2023-01-24 05:32:23.711182: step: 1952/530, loss: 0.015861013904213905
2023-01-24 05:32:24.761706: step: 1956/530, loss: 0.011858519166707993
2023-01-24 05:32:25.844605: step: 1960/530, loss: 0.004690627567470074
2023-01-24 05:32:26.925021: step: 1964/530, loss: 0.06279172003269196
2023-01-24 05:32:27.993661: step: 1968/530, loss: 0.008779163472354412
2023-01-24 05:32:29.042783: step: 1972/530, loss: 0.013341370970010757
2023-01-24 05:32:30.099329: step: 1976/530, loss: 0.013894190080463886
2023-01-24 05:32:31.161383: step: 1980/530, loss: 0.011428681202232838
2023-01-24 05:32:32.229008: step: 1984/530, loss: 0.005652864463627338
2023-01-24 05:32:33.282446: step: 1988/530, loss: 0.003783381776884198
2023-01-24 05:32:34.340204: step: 1992/530, loss: 0.008703182451426983
2023-01-24 05:32:35.389202: step: 1996/530, loss: 0.03581368550658226
2023-01-24 05:32:36.444507: step: 2000/530, loss: 0.039116986095905304
2023-01-24 05:32:37.499087: step: 2004/530, loss: 0.025204267352819443
2023-01-24 05:32:38.574314: step: 2008/530, loss: 0.008481459692120552
2023-01-24 05:32:39.627102: step: 2012/530, loss: 0.010920289903879166
2023-01-24 05:32:40.688077: step: 2016/530, loss: 0.03312116861343384
2023-01-24 05:32:41.736446: step: 2020/530, loss: 0.06590596586465836
2023-01-24 05:32:42.793100: step: 2024/530, loss: 0.006403861101716757
2023-01-24 05:32:43.851721: step: 2028/530, loss: 0.11277373880147934
2023-01-24 05:32:44.915184: step: 2032/530, loss: 0.012116530910134315
2023-01-24 05:32:45.953103: step: 2036/530, loss: 0.009762010537087917
2023-01-24 05:32:47.007137: step: 2040/530, loss: 0.004549986682832241
2023-01-24 05:32:48.065060: step: 2044/530, loss: 0.00924845039844513
2023-01-24 05:32:49.122471: step: 2048/530, loss: 0.006644858978688717
2023-01-24 05:32:50.194529: step: 2052/530, loss: 0.01775205321609974
2023-01-24 05:32:51.247411: step: 2056/530, loss: 0.014122726395726204
2023-01-24 05:32:52.303774: step: 2060/530, loss: 0.03510434925556183
2023-01-24 05:32:53.373883: step: 2064/530, loss: 0.004604725632816553
2023-01-24 05:32:54.413793: step: 2068/530, loss: 0.007574012037366629
2023-01-24 05:32:55.479742: step: 2072/530, loss: 0.04657677933573723
2023-01-24 05:32:56.543347: step: 2076/530, loss: 0.01097668893635273
2023-01-24 05:32:57.617546: step: 2080/530, loss: 0.032615937292575836
2023-01-24 05:32:58.666004: step: 2084/530, loss: 0.013918210752308369
2023-01-24 05:32:59.729345: step: 2088/530, loss: 0.008181863464415073
2023-01-24 05:33:00.809952: step: 2092/530, loss: 0.008173602633178234
2023-01-24 05:33:01.881790: step: 2096/530, loss: 0.006773681379854679
2023-01-24 05:33:02.968087: step: 2100/530, loss: 0.011949355714023113
2023-01-24 05:33:04.013921: step: 2104/530, loss: 0.014399792067706585
2023-01-24 05:33:05.072443: step: 2108/530, loss: 0.004463918041437864
2023-01-24 05:33:06.117674: step: 2112/530, loss: 0.009530861862003803
2023-01-24 05:33:07.187006: step: 2116/530, loss: 0.010738905519247055
2023-01-24 05:33:08.236331: step: 2120/530, loss: 0.010884009301662445
==================================================
Loss: 0.023
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3689094896331738, 'r': 0.33250855327468226, 'f1': 0.34976448617915684}, 'combined': 0.2577212003425366, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3759754119528371, 'r': 0.29589753200444063, 'f1': 0.33116438901659784}, 'combined': 0.21963234090219957, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35844010917540337, 'r': 0.3271531167236604, 'f1': 0.3420827232408115}, 'combined': 0.25206095396691375, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3766509627820885, 'r': 0.3081689695489815, 'f1': 0.33898586650387963}, 'combined': 0.22481964203366106, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 0}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3689094896331738, 'r': 0.33250855327468226, 'f1': 0.34976448617915684}, 'combined': 0.2577212003425366, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3759754119528371, 'r': 0.29589753200444063, 'f1': 0.33116438901659784}, 'combined': 0.21963234090219957, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35844010917540337, 'r': 0.3271531167236604, 'f1': 0.3420827232408115}, 'combined': 0.25206095396691375, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3766509627820885, 'r': 0.3081689695489815, 'f1': 0.33898586650387963}, 'combined': 0.22481964203366106, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:36:13.278138: step: 4/530, loss: 0.012812042608857155
2023-01-24 05:36:14.329349: step: 8/530, loss: 0.004968743771314621
2023-01-24 05:36:15.382296: step: 12/530, loss: 0.010268469341099262
2023-01-24 05:36:16.462951: step: 16/530, loss: 0.012009065598249435
2023-01-24 05:36:17.521959: step: 20/530, loss: 0.006858623120933771
2023-01-24 05:36:18.596966: step: 24/530, loss: 0.017393426969647408
2023-01-24 05:36:19.644591: step: 28/530, loss: 0.04978247731924057
2023-01-24 05:36:20.707515: step: 32/530, loss: 0.006134674418717623
2023-01-24 05:36:21.758990: step: 36/530, loss: 0.012436299584805965
2023-01-24 05:36:22.809039: step: 40/530, loss: 0.015423350967466831
2023-01-24 05:36:23.859620: step: 44/530, loss: 0.015263188630342484
2023-01-24 05:36:24.906375: step: 48/530, loss: 0.042472150176763535
2023-01-24 05:36:25.946194: step: 52/530, loss: 0.00825263001024723
2023-01-24 05:36:27.005317: step: 56/530, loss: 0.006008844822645187
2023-01-24 05:36:28.061388: step: 60/530, loss: 0.03330196812748909
2023-01-24 05:36:29.129922: step: 64/530, loss: 0.024792250245809555
2023-01-24 05:36:30.189198: step: 68/530, loss: 0.023035090416669846
2023-01-24 05:36:31.267322: step: 72/530, loss: 0.0663604587316513
2023-01-24 05:36:32.348562: step: 76/530, loss: 0.004709298722445965
2023-01-24 05:36:33.397846: step: 80/530, loss: 0.07829374074935913
2023-01-24 05:36:34.458653: step: 84/530, loss: 0.0570572130382061
2023-01-24 05:36:35.515400: step: 88/530, loss: 0.015392381697893143
2023-01-24 05:36:36.595721: step: 92/530, loss: 0.0054253642447292805
2023-01-24 05:36:37.659353: step: 96/530, loss: 0.04380722716450691
2023-01-24 05:36:38.720699: step: 100/530, loss: 0.004719903226941824
2023-01-24 05:36:39.768581: step: 104/530, loss: 0.015461036935448647
2023-01-24 05:36:40.806158: step: 108/530, loss: 0.001330893486738205
2023-01-24 05:36:41.854802: step: 112/530, loss: 0.017028087750077248
2023-01-24 05:36:42.916585: step: 116/530, loss: 0.02221495658159256
2023-01-24 05:36:43.975346: step: 120/530, loss: 0.0018862797878682613
2023-01-24 05:36:45.026215: step: 124/530, loss: 0.049547310918569565
2023-01-24 05:36:46.076412: step: 128/530, loss: 0.011584346182644367
2023-01-24 05:36:47.129752: step: 132/530, loss: 0.006693420931696892
2023-01-24 05:36:48.178771: step: 136/530, loss: 0.014537774957716465
2023-01-24 05:36:49.228954: step: 140/530, loss: 0.003021225333213806
2023-01-24 05:36:50.271883: step: 144/530, loss: 0.01263433787971735
2023-01-24 05:36:51.319723: step: 148/530, loss: 0.005211420822888613
2023-01-24 05:36:52.375077: step: 152/530, loss: 0.011436636559665203
2023-01-24 05:36:53.418688: step: 156/530, loss: 0.01299082487821579
2023-01-24 05:36:54.479271: step: 160/530, loss: 0.009490937925875187
2023-01-24 05:36:55.540500: step: 164/530, loss: 0.009561149403452873
2023-01-24 05:36:56.603838: step: 168/530, loss: 0.024382170289754868
2023-01-24 05:36:57.651124: step: 172/530, loss: 0.013156569562852383
2023-01-24 05:36:58.708438: step: 176/530, loss: 0.05021173134446144
2023-01-24 05:36:59.764467: step: 180/530, loss: 0.02146018296480179
2023-01-24 05:37:00.844988: step: 184/530, loss: 0.014445621520280838
2023-01-24 05:37:01.884888: step: 188/530, loss: 0.008759626187384129
2023-01-24 05:37:02.936365: step: 192/530, loss: 0.01410683523863554
2023-01-24 05:37:03.996542: step: 196/530, loss: 0.010141275823116302
2023-01-24 05:37:05.044963: step: 200/530, loss: 0.047538917511701584
2023-01-24 05:37:06.122991: step: 204/530, loss: 0.018930921331048012
2023-01-24 05:37:07.170377: step: 208/530, loss: 0.01452831644564867
2023-01-24 05:37:08.220224: step: 212/530, loss: 0.001628898666240275
2023-01-24 05:37:09.280733: step: 216/530, loss: 0.01716967485845089
2023-01-24 05:37:10.349785: step: 220/530, loss: 0.008422736078500748
2023-01-24 05:37:11.403319: step: 224/530, loss: 0.03254485875368118
2023-01-24 05:37:12.457234: step: 228/530, loss: 0.005184277892112732
2023-01-24 05:37:13.527367: step: 232/530, loss: 0.012165513820946217
2023-01-24 05:37:14.583310: step: 236/530, loss: 0.0011299249017611146
2023-01-24 05:37:15.628594: step: 240/530, loss: 0.010626495815813541
2023-01-24 05:37:16.690641: step: 244/530, loss: 0.0330374501645565
2023-01-24 05:37:17.772590: step: 248/530, loss: 0.013683048076927662
2023-01-24 05:37:18.832203: step: 252/530, loss: 0.018541518598794937
2023-01-24 05:37:19.887352: step: 256/530, loss: 0.006146200932562351
2023-01-24 05:37:20.974473: step: 260/530, loss: 0.03574364259839058
2023-01-24 05:37:22.032814: step: 264/530, loss: 0.013680302537977695
2023-01-24 05:37:23.092213: step: 268/530, loss: 0.01754814386367798
2023-01-24 05:37:24.168165: step: 272/530, loss: 0.011144958436489105
2023-01-24 05:37:25.227777: step: 276/530, loss: 0.007970360107719898
2023-01-24 05:37:26.292880: step: 280/530, loss: 0.005459174048155546
2023-01-24 05:37:27.374776: step: 284/530, loss: 0.008446728810667992
2023-01-24 05:37:28.426083: step: 288/530, loss: 0.0038400490302592516
2023-01-24 05:37:29.500390: step: 292/530, loss: 0.052778203040361404
2023-01-24 05:37:30.549650: step: 296/530, loss: 0.012762574478983879
2023-01-24 05:37:31.600171: step: 300/530, loss: 0.015266292728483677
2023-01-24 05:37:32.652773: step: 304/530, loss: 0.027815166860818863
2023-01-24 05:37:33.712340: step: 308/530, loss: 0.011306829750537872
2023-01-24 05:37:34.772988: step: 312/530, loss: 0.010101128369569778
2023-01-24 05:37:35.824456: step: 316/530, loss: 0.012637332081794739
2023-01-24 05:37:36.887448: step: 320/530, loss: 0.012996125034987926
2023-01-24 05:37:37.937587: step: 324/530, loss: 0.012186801992356777
2023-01-24 05:37:39.010552: step: 328/530, loss: 0.02957739681005478
2023-01-24 05:37:40.070309: step: 332/530, loss: 0.014164001680910587
2023-01-24 05:37:41.125267: step: 336/530, loss: 0.006234884262084961
2023-01-24 05:37:42.178807: step: 340/530, loss: 0.009840351529419422
2023-01-24 05:37:43.229406: step: 344/530, loss: 0.006597005296498537
2023-01-24 05:37:44.290209: step: 348/530, loss: 0.012403731234371662
2023-01-24 05:37:45.365272: step: 352/530, loss: 0.007966849952936172
2023-01-24 05:37:46.418036: step: 356/530, loss: 0.022204235196113586
2023-01-24 05:37:47.455893: step: 360/530, loss: 0.004735025577247143
2023-01-24 05:37:48.521382: step: 364/530, loss: 0.009826652705669403
2023-01-24 05:37:49.576499: step: 368/530, loss: 0.006812600884586573
2023-01-24 05:37:50.622836: step: 372/530, loss: 0.007569643668830395
2023-01-24 05:37:51.669477: step: 376/530, loss: 0.022164801135659218
2023-01-24 05:37:52.716699: step: 380/530, loss: 0.006721922196447849
2023-01-24 05:37:53.787857: step: 384/530, loss: 0.01070920005440712
2023-01-24 05:37:54.837111: step: 388/530, loss: 0.028800206258893013
2023-01-24 05:37:55.892750: step: 392/530, loss: 0.018672818318009377
2023-01-24 05:37:56.961438: step: 396/530, loss: 0.033573850989341736
2023-01-24 05:37:58.029322: step: 400/530, loss: 0.035121940076351166
2023-01-24 05:37:59.096522: step: 404/530, loss: 0.02438824251294136
2023-01-24 05:38:00.148381: step: 408/530, loss: 0.007556359749287367
2023-01-24 05:38:01.192576: step: 412/530, loss: 0.05502595752477646
2023-01-24 05:38:02.253773: step: 416/530, loss: 0.017103854566812515
2023-01-24 05:38:03.299713: step: 420/530, loss: 0.006410283036530018
2023-01-24 05:38:04.361783: step: 424/530, loss: 0.010382283478975296
2023-01-24 05:38:05.408335: step: 428/530, loss: 0.0422479584813118
2023-01-24 05:38:06.470404: step: 432/530, loss: 0.0054764412343502045
2023-01-24 05:38:07.523302: step: 436/530, loss: 0.004924156703054905
2023-01-24 05:38:08.583749: step: 440/530, loss: 0.006357597652822733
2023-01-24 05:38:09.631457: step: 444/530, loss: 0.01100998930633068
2023-01-24 05:38:10.698948: step: 448/530, loss: 0.00651451013982296
2023-01-24 05:38:11.776736: step: 452/530, loss: 0.006748924497514963
2023-01-24 05:38:12.859923: step: 456/530, loss: 0.028487294912338257
2023-01-24 05:38:13.920122: step: 460/530, loss: 0.02687118947505951
2023-01-24 05:38:15.006448: step: 464/530, loss: 0.010269289836287498
2023-01-24 05:38:16.067386: step: 468/530, loss: 0.015467138029634953
2023-01-24 05:38:17.129065: step: 472/530, loss: 0.006644831970334053
2023-01-24 05:38:18.190820: step: 476/530, loss: 0.015359615907073021
2023-01-24 05:38:19.257903: step: 480/530, loss: 0.01289144903421402
2023-01-24 05:38:20.336216: step: 484/530, loss: 0.03765174746513367
2023-01-24 05:38:21.379445: step: 488/530, loss: 0.005087241996079683
2023-01-24 05:38:22.448697: step: 492/530, loss: 0.04189470037817955
2023-01-24 05:38:23.510911: step: 496/530, loss: 0.002288535237312317
2023-01-24 05:38:24.580225: step: 500/530, loss: 0.006644130684435368
2023-01-24 05:38:25.632422: step: 504/530, loss: 0.013283337466418743
2023-01-24 05:38:26.704545: step: 508/530, loss: 0.010525096207857132
2023-01-24 05:38:27.781217: step: 512/530, loss: 0.009191962890326977
2023-01-24 05:38:28.850457: step: 516/530, loss: 0.02919941395521164
2023-01-24 05:38:29.932229: step: 520/530, loss: 0.013844375498592854
2023-01-24 05:38:30.980710: step: 524/530, loss: 0.011457065120339394
2023-01-24 05:38:32.039966: step: 528/530, loss: 0.009924969635903835
2023-01-24 05:38:33.118058: step: 532/530, loss: 0.004485252778977156
2023-01-24 05:38:34.185134: step: 536/530, loss: 0.01095918845385313
2023-01-24 05:38:35.256694: step: 540/530, loss: 0.00705690449103713
2023-01-24 05:38:36.323540: step: 544/530, loss: 0.005855096038430929
2023-01-24 05:38:37.399256: step: 548/530, loss: 0.00876110140234232
2023-01-24 05:38:38.461573: step: 552/530, loss: 0.0048134238459169865
2023-01-24 05:38:39.521061: step: 556/530, loss: 0.021427888423204422
2023-01-24 05:38:40.576938: step: 560/530, loss: 0.034591518342494965
2023-01-24 05:38:41.653037: step: 564/530, loss: 0.016187012195587158
2023-01-24 05:38:42.719627: step: 568/530, loss: 0.0035373871214687824
2023-01-24 05:38:43.798066: step: 572/530, loss: 0.0032281121239066124
2023-01-24 05:38:44.858073: step: 576/530, loss: 0.009938967414200306
2023-01-24 05:38:45.927254: step: 580/530, loss: 0.00673109432682395
2023-01-24 05:38:46.992736: step: 584/530, loss: 0.005051737651228905
2023-01-24 05:38:48.055587: step: 588/530, loss: 0.003959218971431255
2023-01-24 05:38:49.136727: step: 592/530, loss: 0.0253533236682415
2023-01-24 05:38:50.211468: step: 596/530, loss: 0.018933676183223724
2023-01-24 05:38:51.279973: step: 600/530, loss: 0.018184704706072807
2023-01-24 05:38:52.338775: step: 604/530, loss: 0.040191859006881714
2023-01-24 05:38:53.399205: step: 608/530, loss: 0.005946453660726547
2023-01-24 05:38:54.460195: step: 612/530, loss: 0.016042513772845268
2023-01-24 05:38:55.534487: step: 616/530, loss: 0.009394089691340923
2023-01-24 05:38:56.585804: step: 620/530, loss: 0.00918502826243639
2023-01-24 05:38:57.629916: step: 624/530, loss: 0.008218417875468731
2023-01-24 05:38:58.727891: step: 628/530, loss: 0.0075278691947460175
2023-01-24 05:38:59.771463: step: 632/530, loss: 0.04501500353217125
2023-01-24 05:39:00.838152: step: 636/530, loss: 0.04866698384284973
2023-01-24 05:39:01.900738: step: 640/530, loss: 0.004906733054667711
2023-01-24 05:39:02.973445: step: 644/530, loss: 0.007191901095211506
2023-01-24 05:39:04.040111: step: 648/530, loss: 0.004166802857071161
2023-01-24 05:39:05.109199: step: 652/530, loss: 0.008952178992331028
2023-01-24 05:39:06.166104: step: 656/530, loss: 0.0032867658883333206
2023-01-24 05:39:07.220004: step: 660/530, loss: 0.008846216835081577
2023-01-24 05:39:08.293348: step: 664/530, loss: 0.034426044672727585
2023-01-24 05:39:09.346929: step: 668/530, loss: 0.016851428896188736
2023-01-24 05:39:10.415670: step: 672/530, loss: 0.001728835399262607
2023-01-24 05:39:11.485561: step: 676/530, loss: 0.003514292184263468
2023-01-24 05:39:12.555949: step: 680/530, loss: 0.0014241851167753339
2023-01-24 05:39:13.613614: step: 684/530, loss: 0.011632991954684258
2023-01-24 05:39:14.684860: step: 688/530, loss: 0.0031677905935794115
2023-01-24 05:39:15.751656: step: 692/530, loss: 0.006295075174421072
2023-01-24 05:39:16.813328: step: 696/530, loss: 0.012672558426856995
2023-01-24 05:39:17.873781: step: 700/530, loss: 0.016729509457945824
2023-01-24 05:39:18.943648: step: 704/530, loss: 0.005609654821455479
2023-01-24 05:39:20.015181: step: 708/530, loss: 0.025184353813529015
2023-01-24 05:39:21.066659: step: 712/530, loss: 0.011834022589027882
2023-01-24 05:39:22.126361: step: 716/530, loss: 0.012000779621303082
2023-01-24 05:39:23.180164: step: 720/530, loss: 0.024266935884952545
2023-01-24 05:39:24.244908: step: 724/530, loss: 0.008076450787484646
2023-01-24 05:39:25.291948: step: 728/530, loss: 0.05895301699638367
2023-01-24 05:39:26.357317: step: 732/530, loss: 0.004399893339723349
2023-01-24 05:39:27.422458: step: 736/530, loss: 0.011770348995923996
2023-01-24 05:39:28.476450: step: 740/530, loss: 0.013988112099468708
2023-01-24 05:39:29.524923: step: 744/530, loss: 0.0073435502126812935
2023-01-24 05:39:30.593290: step: 748/530, loss: 0.015257966704666615
2023-01-24 05:39:31.651964: step: 752/530, loss: 0.0061120279133319855
2023-01-24 05:39:32.734057: step: 756/530, loss: 0.038767073303461075
2023-01-24 05:39:33.808818: step: 760/530, loss: 0.009704644791781902
2023-01-24 05:39:34.860642: step: 764/530, loss: 0.026901721954345703
2023-01-24 05:39:35.932909: step: 768/530, loss: 0.004168699029833078
2023-01-24 05:39:36.989053: step: 772/530, loss: 0.041097331792116165
2023-01-24 05:39:38.041179: step: 776/530, loss: 0.03344521299004555
2023-01-24 05:39:39.088193: step: 780/530, loss: 0.03974912688136101
2023-01-24 05:39:40.149213: step: 784/530, loss: 0.005475970916450024
2023-01-24 05:39:41.207800: step: 788/530, loss: 0.011025716550648212
2023-01-24 05:39:42.254863: step: 792/530, loss: 0.0031101240310817957
2023-01-24 05:39:43.303135: step: 796/530, loss: 0.0029792720451951027
2023-01-24 05:39:44.375116: step: 800/530, loss: 0.0446191169321537
2023-01-24 05:39:45.431624: step: 804/530, loss: 0.00830955058336258
2023-01-24 05:39:46.492634: step: 808/530, loss: 0.01628958247601986
2023-01-24 05:39:47.553295: step: 812/530, loss: 0.004423732869327068
2023-01-24 05:39:48.618456: step: 816/530, loss: 0.011006618849933147
2023-01-24 05:39:49.677618: step: 820/530, loss: 0.008579405955970287
2023-01-24 05:39:50.743446: step: 824/530, loss: 0.018149664625525475
2023-01-24 05:39:51.801015: step: 828/530, loss: 0.00688356626778841
2023-01-24 05:39:52.875598: step: 832/530, loss: 0.01976776123046875
2023-01-24 05:39:53.934319: step: 836/530, loss: 0.023456206545233727
2023-01-24 05:39:55.007514: step: 840/530, loss: 0.029343977570533752
2023-01-24 05:39:56.069441: step: 844/530, loss: 0.018927250057458878
2023-01-24 05:39:57.148522: step: 848/530, loss: 0.07061655819416046
2023-01-24 05:39:58.217492: step: 852/530, loss: 0.015483235940337181
2023-01-24 05:39:59.278651: step: 856/530, loss: 0.01061968319118023
2023-01-24 05:40:00.347875: step: 860/530, loss: 0.031189650297164917
2023-01-24 05:40:01.414666: step: 864/530, loss: 0.006935350596904755
2023-01-24 05:40:02.469957: step: 868/530, loss: 0.009298883378505707
2023-01-24 05:40:03.522275: step: 872/530, loss: 0.007129035424441099
2023-01-24 05:40:04.596067: step: 876/530, loss: 0.006253466941416264
2023-01-24 05:40:05.654434: step: 880/530, loss: 0.006499452516436577
2023-01-24 05:40:06.710807: step: 884/530, loss: 0.033299557864665985
2023-01-24 05:40:07.773372: step: 888/530, loss: 0.008984018117189407
2023-01-24 05:40:08.835829: step: 892/530, loss: 0.005039960145950317
2023-01-24 05:40:09.890841: step: 896/530, loss: 0.012044877745211124
2023-01-24 05:40:10.965984: step: 900/530, loss: 0.005887978710234165
2023-01-24 05:40:12.018542: step: 904/530, loss: 0.012302116490900517
2023-01-24 05:40:13.075108: step: 908/530, loss: 0.015675431117415428
2023-01-24 05:40:14.133352: step: 912/530, loss: 0.04208158329129219
2023-01-24 05:40:15.187983: step: 916/530, loss: 0.03659065440297127
2023-01-24 05:40:16.246429: step: 920/530, loss: 0.03763337805867195
2023-01-24 05:40:17.306974: step: 924/530, loss: 0.042064789682626724
2023-01-24 05:40:18.374459: step: 928/530, loss: 0.01969834417104721
2023-01-24 05:40:19.425545: step: 932/530, loss: 0.005926787853240967
2023-01-24 05:40:20.478929: step: 936/530, loss: 0.05853027477860451
2023-01-24 05:40:21.543521: step: 940/530, loss: 0.02152705378830433
2023-01-24 05:40:22.606915: step: 944/530, loss: 0.0007766132475808263
2023-01-24 05:40:23.668912: step: 948/530, loss: 0.010369432158768177
2023-01-24 05:40:24.727454: step: 952/530, loss: 0.005706869065761566
2023-01-24 05:40:25.788143: step: 956/530, loss: 0.02654355764389038
2023-01-24 05:40:26.872293: step: 960/530, loss: 0.02683834172785282
2023-01-24 05:40:27.956688: step: 964/530, loss: 0.011238583363592625
2023-01-24 05:40:29.017376: step: 968/530, loss: 0.012049898505210876
2023-01-24 05:40:30.097518: step: 972/530, loss: 0.06265122443437576
2023-01-24 05:40:31.161800: step: 976/530, loss: 0.013216791674494743
2023-01-24 05:40:32.233005: step: 980/530, loss: 0.014446182176470757
2023-01-24 05:40:33.304936: step: 984/530, loss: 0.008719599805772305
2023-01-24 05:40:34.361996: step: 988/530, loss: 0.012663358822464943
2023-01-24 05:40:35.395968: step: 992/530, loss: 0.004608609713613987
2023-01-24 05:40:36.459576: step: 996/530, loss: 0.023968590423464775
2023-01-24 05:40:37.513371: step: 1000/530, loss: 0.005979705136269331
2023-01-24 05:40:38.593565: step: 1004/530, loss: 0.03635064512491226
2023-01-24 05:40:39.654771: step: 1008/530, loss: 0.05162810534238815
2023-01-24 05:40:40.730507: step: 1012/530, loss: 0.003428681753575802
2023-01-24 05:40:41.795016: step: 1016/530, loss: 0.004650312941521406
2023-01-24 05:40:42.848902: step: 1020/530, loss: 0.0049728392623364925
2023-01-24 05:40:43.911138: step: 1024/530, loss: 0.026036269962787628
2023-01-24 05:40:44.971788: step: 1028/530, loss: 0.010332313366234303
2023-01-24 05:40:46.029696: step: 1032/530, loss: 0.010391296818852425
2023-01-24 05:40:47.088482: step: 1036/530, loss: 0.039661698043346405
2023-01-24 05:40:48.156430: step: 1040/530, loss: 0.009535130113363266
2023-01-24 05:40:49.207555: step: 1044/530, loss: 0.007928818464279175
2023-01-24 05:40:50.269253: step: 1048/530, loss: 0.0036535130348056555
2023-01-24 05:40:51.333385: step: 1052/530, loss: 0.004927432630211115
2023-01-24 05:40:52.387384: step: 1056/530, loss: 0.015324579551815987
2023-01-24 05:40:53.441817: step: 1060/530, loss: 0.050229042768478394
2023-01-24 05:40:54.514925: step: 1064/530, loss: 0.03010651469230652
2023-01-24 05:40:55.579293: step: 1068/530, loss: 0.01899755746126175
2023-01-24 05:40:56.640020: step: 1072/530, loss: 0.01033230870962143
2023-01-24 05:40:57.700384: step: 1076/530, loss: 0.0022809014189988375
2023-01-24 05:40:58.758160: step: 1080/530, loss: 0.005062357522547245
2023-01-24 05:40:59.842933: step: 1084/530, loss: 0.0034568000119179487
2023-01-24 05:41:00.901897: step: 1088/530, loss: 0.00892782025039196
2023-01-24 05:41:01.964993: step: 1092/530, loss: 0.010207334533333778
2023-01-24 05:41:03.053404: step: 1096/530, loss: 0.002616593847051263
2023-01-24 05:41:04.137829: step: 1100/530, loss: 0.005376041866838932
2023-01-24 05:41:05.211000: step: 1104/530, loss: 0.036779046058654785
2023-01-24 05:41:06.272607: step: 1108/530, loss: 0.05293755978345871
2023-01-24 05:41:07.335045: step: 1112/530, loss: 0.0558176189661026
2023-01-24 05:41:08.387896: step: 1116/530, loss: 0.02545098215341568
2023-01-24 05:41:09.455123: step: 1120/530, loss: 0.013991013169288635
2023-01-24 05:41:10.512061: step: 1124/530, loss: 0.006213500164449215
2023-01-24 05:41:11.586071: step: 1128/530, loss: 0.005669683218002319
2023-01-24 05:41:12.676441: step: 1132/530, loss: 0.024124665185809135
2023-01-24 05:41:13.736315: step: 1136/530, loss: 0.04454462230205536
2023-01-24 05:41:14.787411: step: 1140/530, loss: 0.04345531761646271
2023-01-24 05:41:15.841805: step: 1144/530, loss: 0.0588107593357563
2023-01-24 05:41:16.896810: step: 1148/530, loss: 0.0048675453290343285
2023-01-24 05:41:17.962905: step: 1152/530, loss: 0.0032255600672215223
2023-01-24 05:41:19.023622: step: 1156/530, loss: 0.010823904536664486
2023-01-24 05:41:20.084255: step: 1160/530, loss: 0.002180259209126234
2023-01-24 05:41:21.138411: step: 1164/530, loss: 0.002328141126781702
2023-01-24 05:41:22.213577: step: 1168/530, loss: 0.010505598038434982
2023-01-24 05:41:23.276402: step: 1172/530, loss: 0.03759091719985008
2023-01-24 05:41:24.356495: step: 1176/530, loss: 0.0307106152176857
2023-01-24 05:41:25.401704: step: 1180/530, loss: 0.01974612846970558
2023-01-24 05:41:26.499544: step: 1184/530, loss: 0.1052195206284523
2023-01-24 05:41:27.568387: step: 1188/530, loss: 0.08044582605361938
2023-01-24 05:41:28.647908: step: 1192/530, loss: 0.0010620774701237679
2023-01-24 05:41:29.709011: step: 1196/530, loss: 0.00456416979432106
2023-01-24 05:41:30.779277: step: 1200/530, loss: 0.006161686033010483
2023-01-24 05:41:31.842448: step: 1204/530, loss: 0.009766052477061749
2023-01-24 05:41:32.896819: step: 1208/530, loss: 0.03169477730989456
2023-01-24 05:41:33.962777: step: 1212/530, loss: 0.033149056136608124
2023-01-24 05:41:35.020348: step: 1216/530, loss: 0.02226412482559681
2023-01-24 05:41:36.076500: step: 1220/530, loss: 0.0304978396743536
2023-01-24 05:41:37.145348: step: 1224/530, loss: 0.03233238682150841
2023-01-24 05:41:38.205271: step: 1228/530, loss: 0.010222124867141247
2023-01-24 05:41:39.255947: step: 1232/530, loss: 0.00840659812092781
2023-01-24 05:41:40.304065: step: 1236/530, loss: 0.0036301854997873306
2023-01-24 05:41:41.368664: step: 1240/530, loss: 0.0092863654717803
2023-01-24 05:41:42.431577: step: 1244/530, loss: 0.016449958086013794
2023-01-24 05:41:43.476880: step: 1248/530, loss: 0.023955509066581726
2023-01-24 05:41:44.520488: step: 1252/530, loss: 0.013684744946658611
2023-01-24 05:41:45.573052: step: 1256/530, loss: 0.005129117984324694
2023-01-24 05:41:46.666050: step: 1260/530, loss: 0.007209953386336565
2023-01-24 05:41:47.728287: step: 1264/530, loss: 0.014008361846208572
2023-01-24 05:41:48.790862: step: 1268/530, loss: 0.007906931452453136
2023-01-24 05:41:49.841121: step: 1272/530, loss: 0.00965550635010004
2023-01-24 05:41:50.897556: step: 1276/530, loss: 0.037895385175943375
2023-01-24 05:41:51.955814: step: 1280/530, loss: 0.002878161845728755
2023-01-24 05:41:53.045172: step: 1284/530, loss: 0.0038605646695941687
2023-01-24 05:41:54.107736: step: 1288/530, loss: 0.003913390450179577
2023-01-24 05:41:55.186259: step: 1292/530, loss: 0.010950553230941296
2023-01-24 05:41:56.236967: step: 1296/530, loss: 0.005906758364289999
2023-01-24 05:41:57.296128: step: 1300/530, loss: 0.01570514589548111
2023-01-24 05:41:58.359592: step: 1304/530, loss: 0.006531259510666132
2023-01-24 05:41:59.413026: step: 1308/530, loss: 0.041600823402404785
2023-01-24 05:42:00.472138: step: 1312/530, loss: 0.011881793849170208
2023-01-24 05:42:01.520551: step: 1316/530, loss: 0.004571493715047836
2023-01-24 05:42:02.571903: step: 1320/530, loss: 0.08933065831661224
2023-01-24 05:42:03.628606: step: 1324/530, loss: 0.0023517468944191933
2023-01-24 05:42:04.695822: step: 1328/530, loss: 0.020870709791779518
2023-01-24 05:42:05.736817: step: 1332/530, loss: 0.023828677833080292
2023-01-24 05:42:06.786298: step: 1336/530, loss: 0.013462623581290245
2023-01-24 05:42:07.843633: step: 1340/530, loss: 0.010673563927412033
2023-01-24 05:42:08.911640: step: 1344/530, loss: 0.012909299694001675
2023-01-24 05:42:09.970926: step: 1348/530, loss: 0.019762424752116203
2023-01-24 05:42:11.029799: step: 1352/530, loss: 0.005482145585119724
2023-01-24 05:42:12.087117: step: 1356/530, loss: 0.0038648806512355804
2023-01-24 05:42:13.140245: step: 1360/530, loss: 0.004831406287848949
2023-01-24 05:42:14.205922: step: 1364/530, loss: 0.008477620780467987
2023-01-24 05:42:15.268318: step: 1368/530, loss: 0.03622875735163689
2023-01-24 05:42:16.355663: step: 1372/530, loss: 0.05545927584171295
2023-01-24 05:42:17.421679: step: 1376/530, loss: 0.03655295446515083
2023-01-24 05:42:18.491686: step: 1380/530, loss: 0.00972758885473013
2023-01-24 05:42:19.551134: step: 1384/530, loss: 0.03709084913134575
2023-01-24 05:42:20.636946: step: 1388/530, loss: 0.019992642104625702
2023-01-24 05:42:21.684532: step: 1392/530, loss: 0.009150903671979904
2023-01-24 05:42:22.760564: step: 1396/530, loss: 0.002793791936710477
2023-01-24 05:42:23.819483: step: 1400/530, loss: 0.0053272368386387825
2023-01-24 05:42:24.893012: step: 1404/530, loss: 0.005243889056146145
2023-01-24 05:42:25.948568: step: 1408/530, loss: 0.007246647495776415
2023-01-24 05:42:27.015658: step: 1412/530, loss: 0.050715476274490356
2023-01-24 05:42:28.074810: step: 1416/530, loss: 0.051959238946437836
2023-01-24 05:42:29.139840: step: 1420/530, loss: 0.02455473132431507
2023-01-24 05:42:30.205735: step: 1424/530, loss: 0.010326489806175232
2023-01-24 05:42:31.254475: step: 1428/530, loss: 0.009924548678100109
2023-01-24 05:42:32.318598: step: 1432/530, loss: 0.046050846576690674
2023-01-24 05:42:33.379244: step: 1436/530, loss: 0.026995949447155
2023-01-24 05:42:34.431335: step: 1440/530, loss: 0.006940201856195927
2023-01-24 05:42:35.499291: step: 1444/530, loss: 0.01798749342560768
2023-01-24 05:42:36.555717: step: 1448/530, loss: 0.011770684272050858
2023-01-24 05:42:37.629929: step: 1452/530, loss: 0.01490066573023796
2023-01-24 05:42:38.701805: step: 1456/530, loss: 0.02012314833700657
2023-01-24 05:42:39.763837: step: 1460/530, loss: 0.003994438797235489
2023-01-24 05:42:40.827335: step: 1464/530, loss: 0.008913468569517136
2023-01-24 05:42:41.888660: step: 1468/530, loss: 0.007337390910834074
2023-01-24 05:42:42.946155: step: 1472/530, loss: 0.007791111711412668
2023-01-24 05:42:43.994376: step: 1476/530, loss: 0.003587437095120549
2023-01-24 05:42:45.057324: step: 1480/530, loss: 0.026287341490387917
2023-01-24 05:42:46.131274: step: 1484/530, loss: 0.006763038691133261
2023-01-24 05:42:47.195359: step: 1488/530, loss: 0.0037788902409374714
2023-01-24 05:42:48.258748: step: 1492/530, loss: 0.01408185064792633
2023-01-24 05:42:49.313495: step: 1496/530, loss: 0.00588175980374217
2023-01-24 05:42:50.374537: step: 1500/530, loss: 0.009197527542710304
2023-01-24 05:42:51.418307: step: 1504/530, loss: 0.005064733326435089
2023-01-24 05:42:52.472122: step: 1508/530, loss: 0.009162355214357376
2023-01-24 05:42:53.533086: step: 1512/530, loss: 0.010994878597557545
2023-01-24 05:42:54.587871: step: 1516/530, loss: 0.007520737126469612
2023-01-24 05:42:55.643153: step: 1520/530, loss: 0.011643494479358196
2023-01-24 05:42:56.700494: step: 1524/530, loss: 0.006474689580500126
2023-01-24 05:42:57.757512: step: 1528/530, loss: 0.006219760049134493
2023-01-24 05:42:58.805563: step: 1532/530, loss: 0.057099130004644394
2023-01-24 05:42:59.852711: step: 1536/530, loss: 0.009170408360660076
2023-01-24 05:43:00.910051: step: 1540/530, loss: 0.022626172751188278
2023-01-24 05:43:01.960574: step: 1544/530, loss: 0.04263249412178993
2023-01-24 05:43:03.066930: step: 1548/530, loss: 0.005704390350729227
2023-01-24 05:43:04.119193: step: 1552/530, loss: 0.008012990467250347
2023-01-24 05:43:05.190294: step: 1556/530, loss: 0.02050148695707321
2023-01-24 05:43:06.257779: step: 1560/530, loss: 0.03643443435430527
2023-01-24 05:43:07.333904: step: 1564/530, loss: 0.005676362197846174
2023-01-24 05:43:08.394648: step: 1568/530, loss: 0.002216193126514554
2023-01-24 05:43:09.452372: step: 1572/530, loss: 0.03826082870364189
2023-01-24 05:43:10.519058: step: 1576/530, loss: 0.03358278423547745
2023-01-24 05:43:11.585701: step: 1580/530, loss: 0.020951375365257263
2023-01-24 05:43:12.644122: step: 1584/530, loss: 0.010042297653853893
2023-01-24 05:43:13.726572: step: 1588/530, loss: 0.048121415078639984
2023-01-24 05:43:14.792839: step: 1592/530, loss: 0.0379815548658371
2023-01-24 05:43:15.845222: step: 1596/530, loss: 0.008974720723927021
2023-01-24 05:43:16.901380: step: 1600/530, loss: 0.006458432879298925
2023-01-24 05:43:17.958289: step: 1604/530, loss: 0.04805876314640045
2023-01-24 05:43:19.012643: step: 1608/530, loss: 0.005108897108584642
2023-01-24 05:43:20.078252: step: 1612/530, loss: 0.006622752640396357
2023-01-24 05:43:21.129418: step: 1616/530, loss: 0.00990348681807518
2023-01-24 05:43:22.203673: step: 1620/530, loss: 0.014538360759615898
2023-01-24 05:43:23.275367: step: 1624/530, loss: 0.008196043781936169
2023-01-24 05:43:24.343682: step: 1628/530, loss: 0.04106898978352547
2023-01-24 05:43:25.388017: step: 1632/530, loss: 0.0017260070890188217
2023-01-24 05:43:26.464436: step: 1636/530, loss: 0.0043150316923856735
2023-01-24 05:43:27.519674: step: 1640/530, loss: 0.009698811918497086
2023-01-24 05:43:28.583176: step: 1644/530, loss: 0.007644013501703739
2023-01-24 05:43:29.638173: step: 1648/530, loss: 0.0069054607301950455
2023-01-24 05:43:30.698307: step: 1652/530, loss: 0.005940628703683615
2023-01-24 05:43:31.754865: step: 1656/530, loss: 0.018340660259127617
2023-01-24 05:43:32.821436: step: 1660/530, loss: 0.007820161059498787
2023-01-24 05:43:33.882928: step: 1664/530, loss: 0.0076900371350348
2023-01-24 05:43:34.941909: step: 1668/530, loss: 0.005237432196736336
2023-01-24 05:43:36.006167: step: 1672/530, loss: 0.001233618357218802
2023-01-24 05:43:37.069675: step: 1676/530, loss: 0.013445669785141945
2023-01-24 05:43:38.132147: step: 1680/530, loss: 0.009576022624969482
2023-01-24 05:43:39.182239: step: 1684/530, loss: 0.006483124103397131
2023-01-24 05:43:40.241297: step: 1688/530, loss: 0.013715866953134537
2023-01-24 05:43:41.297596: step: 1692/530, loss: 0.0030313965398818254
2023-01-24 05:43:42.371105: step: 1696/530, loss: 0.045827221125364304
2023-01-24 05:43:43.421469: step: 1700/530, loss: 0.016571419313549995
2023-01-24 05:43:44.475974: step: 1704/530, loss: 0.11035176366567612
2023-01-24 05:43:45.544254: step: 1708/530, loss: 0.026345668360590935
2023-01-24 05:43:46.610856: step: 1712/530, loss: 0.036703646183013916
2023-01-24 05:43:47.659196: step: 1716/530, loss: 0.052943695336580276
2023-01-24 05:43:48.714862: step: 1720/530, loss: 0.02062053792178631
2023-01-24 05:43:49.765184: step: 1724/530, loss: 0.0069045559503138065
2023-01-24 05:43:50.839533: step: 1728/530, loss: 0.008250270038843155
2023-01-24 05:43:51.889182: step: 1732/530, loss: 0.007133954670280218
2023-01-24 05:43:52.961441: step: 1736/530, loss: 0.008840522728860378
2023-01-24 05:43:54.016558: step: 1740/530, loss: 0.007804329041391611
2023-01-24 05:43:55.081606: step: 1744/530, loss: 0.013568085618317127
2023-01-24 05:43:56.138223: step: 1748/530, loss: 0.006300191394984722
2023-01-24 05:43:57.195385: step: 1752/530, loss: 0.008131958544254303
2023-01-24 05:43:58.253977: step: 1756/530, loss: 0.00818594265729189
2023-01-24 05:43:59.296687: step: 1760/530, loss: 0.008316697552800179
2023-01-24 05:44:00.350688: step: 1764/530, loss: 0.008807742968201637
2023-01-24 05:44:01.396836: step: 1768/530, loss: 0.0018822801066562533
2023-01-24 05:44:02.441136: step: 1772/530, loss: 0.013648509979248047
2023-01-24 05:44:03.508835: step: 1776/530, loss: 0.017972175031900406
2023-01-24 05:44:04.569806: step: 1780/530, loss: 0.05904356762766838
2023-01-24 05:44:05.632036: step: 1784/530, loss: 0.019957704469561577
2023-01-24 05:44:06.697797: step: 1788/530, loss: 0.015411603264510632
2023-01-24 05:44:07.759226: step: 1792/530, loss: 0.0024024546146392822
2023-01-24 05:44:08.832572: step: 1796/530, loss: 0.0007687581819482148
2023-01-24 05:44:09.887758: step: 1800/530, loss: 0.006707440130412579
2023-01-24 05:44:10.948351: step: 1804/530, loss: 0.00202168058604002
2023-01-24 05:44:12.003314: step: 1808/530, loss: 0.0043829320929944515
2023-01-24 05:44:13.071137: step: 1812/530, loss: 0.005272049456834793
2023-01-24 05:44:14.133231: step: 1816/530, loss: 0.008434496819972992
2023-01-24 05:44:15.195280: step: 1820/530, loss: 0.006302823778241873
2023-01-24 05:44:16.250278: step: 1824/530, loss: 0.009139463305473328
2023-01-24 05:44:17.312711: step: 1828/530, loss: 0.02131139300763607
2023-01-24 05:44:18.355372: step: 1832/530, loss: 0.007144282106310129
2023-01-24 05:44:19.420127: step: 1836/530, loss: 0.102424256503582
2023-01-24 05:44:20.499385: step: 1840/530, loss: 0.044889748096466064
2023-01-24 05:44:21.554434: step: 1844/530, loss: 0.04495002701878548
2023-01-24 05:44:22.624001: step: 1848/530, loss: 0.03323684260249138
2023-01-24 05:44:23.668435: step: 1852/530, loss: 0.005998342763632536
2023-01-24 05:44:24.735632: step: 1856/530, loss: 0.01888926513493061
2023-01-24 05:44:25.798500: step: 1860/530, loss: 0.005591218359768391
2023-01-24 05:44:26.866582: step: 1864/530, loss: 0.02288639359176159
2023-01-24 05:44:27.938277: step: 1868/530, loss: 0.010034807026386261
2023-01-24 05:44:28.998036: step: 1872/530, loss: 0.013417620211839676
2023-01-24 05:44:30.051209: step: 1876/530, loss: 0.003257042495533824
2023-01-24 05:44:31.101492: step: 1880/530, loss: 0.013652905821800232
2023-01-24 05:44:32.153741: step: 1884/530, loss: 0.007731796707957983
2023-01-24 05:44:33.236350: step: 1888/530, loss: 0.03888445720076561
2023-01-24 05:44:34.325963: step: 1892/530, loss: 0.04473840445280075
2023-01-24 05:44:35.384695: step: 1896/530, loss: 0.004404390696436167
2023-01-24 05:44:36.452556: step: 1900/530, loss: 0.013368918560445309
2023-01-24 05:44:37.509864: step: 1904/530, loss: 0.03038119710981846
2023-01-24 05:44:38.561502: step: 1908/530, loss: 0.01971774734556675
2023-01-24 05:44:39.632011: step: 1912/530, loss: 0.003974567167460918
2023-01-24 05:44:40.693244: step: 1916/530, loss: 0.0059807682409882545
2023-01-24 05:44:41.753279: step: 1920/530, loss: 0.006222272291779518
2023-01-24 05:44:42.813907: step: 1924/530, loss: 0.008543187752366066
2023-01-24 05:44:43.881142: step: 1928/530, loss: 0.04808853939175606
2023-01-24 05:44:44.922118: step: 1932/530, loss: 0.0070057157427072525
2023-01-24 05:44:45.997203: step: 1936/530, loss: 0.006611945573240519
2023-01-24 05:44:47.048427: step: 1940/530, loss: 0.0022709087934345007
2023-01-24 05:44:48.102312: step: 1944/530, loss: 0.013978000730276108
2023-01-24 05:44:49.170605: step: 1948/530, loss: 0.007095608394593
2023-01-24 05:44:50.233354: step: 1952/530, loss: 0.0037037008441984653
2023-01-24 05:44:51.309642: step: 1956/530, loss: 0.018672939389944077
2023-01-24 05:44:52.389991: step: 1960/530, loss: 0.03146198019385338
2023-01-24 05:44:53.446381: step: 1964/530, loss: 0.007368862628936768
2023-01-24 05:44:54.509471: step: 1968/530, loss: 0.006628585048019886
2023-01-24 05:44:55.556071: step: 1972/530, loss: 0.009114941582083702
2023-01-24 05:44:56.623723: step: 1976/530, loss: 0.006100182421505451
2023-01-24 05:44:57.677667: step: 1980/530, loss: 0.024046972393989563
2023-01-24 05:44:58.751279: step: 1984/530, loss: 0.03565197065472603
2023-01-24 05:44:59.802601: step: 1988/530, loss: 0.006098717916756868
2023-01-24 05:45:00.851395: step: 1992/530, loss: 0.0014652959071099758
2023-01-24 05:45:01.941042: step: 1996/530, loss: 0.02639559842646122
2023-01-24 05:45:03.012977: step: 2000/530, loss: 0.002592522883787751
2023-01-24 05:45:04.074836: step: 2004/530, loss: 0.005869527813047171
2023-01-24 05:45:05.147131: step: 2008/530, loss: 0.0055039809085428715
2023-01-24 05:45:06.211251: step: 2012/530, loss: 0.0528530478477478
2023-01-24 05:45:07.275752: step: 2016/530, loss: 0.020423760637640953
2023-01-24 05:45:08.336074: step: 2020/530, loss: 0.01448429748415947
2023-01-24 05:45:09.396435: step: 2024/530, loss: 0.049726247787475586
2023-01-24 05:45:10.451014: step: 2028/530, loss: 0.011955785565078259
2023-01-24 05:45:11.498638: step: 2032/530, loss: 0.012852472253143787
2023-01-24 05:45:12.545019: step: 2036/530, loss: 0.01504012756049633
2023-01-24 05:45:13.593500: step: 2040/530, loss: 0.012194959446787834
2023-01-24 05:45:14.675353: step: 2044/530, loss: 0.017821162939071655
2023-01-24 05:45:15.732958: step: 2048/530, loss: 0.0016942271031439304
2023-01-24 05:45:16.796585: step: 2052/530, loss: 0.00821102224290371
2023-01-24 05:45:17.854433: step: 2056/530, loss: 0.007043834775686264
2023-01-24 05:45:18.918220: step: 2060/530, loss: 0.0022062095813453197
2023-01-24 05:45:19.998297: step: 2064/530, loss: 0.013299858197569847
2023-01-24 05:45:21.057955: step: 2068/530, loss: 0.00624550087377429
2023-01-24 05:45:22.122702: step: 2072/530, loss: 0.005537162069231272
2023-01-24 05:45:23.174405: step: 2076/530, loss: 0.04955968260765076
2023-01-24 05:45:24.237716: step: 2080/530, loss: 0.00856846198439598
2023-01-24 05:45:25.284602: step: 2084/530, loss: 0.012305052950978279
2023-01-24 05:45:26.352658: step: 2088/530, loss: 0.021465018391609192
2023-01-24 05:45:27.407187: step: 2092/530, loss: 0.01626303605735302
2023-01-24 05:45:28.474893: step: 2096/530, loss: 0.025284258648753166
2023-01-24 05:45:29.547961: step: 2100/530, loss: 0.0010533814784139395
2023-01-24 05:45:30.592467: step: 2104/530, loss: 0.010778271593153477
2023-01-24 05:45:31.644582: step: 2108/530, loss: 0.035653628408908844
2023-01-24 05:45:32.717130: step: 2112/530, loss: 0.019491948187351227
2023-01-24 05:45:33.786783: step: 2116/530, loss: 0.007639611605554819
2023-01-24 05:45:34.833940: step: 2120/530, loss: 0.025413960218429565
==================================================
Loss: 0.017
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3704884370015949, 'r': 0.33393170317980564, 'f1': 0.3512614921671808}, 'combined': 0.25882425738634374, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3901261575877163, 'r': 0.2994463568648126, 'f1': 0.33882399358697635}, 'combined': 0.22471228590224335, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375848416289593, 'r': 0.2825994318181818, 'f1': 0.30765463917525776}, 'combined': 0.20510309278350516, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.38498121733122165, 'r': 0.29157156321272765, 'f1': 0.33182799205866637}, 'combined': 0.21656142639618223, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3564530180914158, 'r': 0.33075052342827765, 'f1': 0.34312111387146127}, 'combined': 0.2528260839052872, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3877289322756793, 'r': 0.3081689695489815, 'f1': 0.3434010225075481}, 'combined': 0.22774782839878835, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6428571428571429, 'r': 0.391304347826087, 'f1': 0.4864864864864865}, 'combined': 0.32432432432432434, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3704884370015949, 'r': 0.33393170317980564, 'f1': 0.3512614921671808}, 'combined': 0.25882425738634374, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3901261575877163, 'r': 0.2994463568648126, 'f1': 0.33882399358697635}, 'combined': 0.22471228590224335, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3564530180914158, 'r': 0.33075052342827765, 'f1': 0.34312111387146127}, 'combined': 0.2528260839052872, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3877289322756793, 'r': 0.3081689695489815, 'f1': 0.3434010225075481}, 'combined': 0.22774782839878835, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 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 05:48:22.384886: step: 4/530, loss: 0.03830849751830101
2023-01-24 05:48:23.442575: step: 8/530, loss: 0.004272417165338993
2023-01-24 05:48:24.484140: step: 12/530, loss: 0.00348020251840353
2023-01-24 05:48:25.529512: step: 16/530, loss: 0.003912493120878935
2023-01-24 05:48:26.585383: step: 20/530, loss: 0.015317593701183796
2023-01-24 05:48:27.653326: step: 24/530, loss: 0.006323241163045168
2023-01-24 05:48:28.705081: step: 28/530, loss: 0.012455908581614494
2023-01-24 05:48:29.753607: step: 32/530, loss: 0.004830619785934687
2023-01-24 05:48:30.831146: step: 36/530, loss: 0.04608432576060295
2023-01-24 05:48:31.881788: step: 40/530, loss: 0.006739404052495956
2023-01-24 05:48:32.942513: step: 44/530, loss: 0.00015774389612488449
2023-01-24 05:48:33.984247: step: 48/530, loss: 0.006800433155149221
2023-01-24 05:48:35.039078: step: 52/530, loss: 0.005926321726292372
2023-01-24 05:48:36.082008: step: 56/530, loss: 0.00492703914642334
2023-01-24 05:48:37.134099: step: 60/530, loss: 0.016003718599677086
2023-01-24 05:48:38.190544: step: 64/530, loss: 0.011791661381721497
2023-01-24 05:48:39.237828: step: 68/530, loss: 0.007783927954733372
2023-01-24 05:48:40.317336: step: 72/530, loss: 0.010496499016880989
2023-01-24 05:48:41.358024: step: 76/530, loss: 0.024391213431954384
2023-01-24 05:48:42.430605: step: 80/530, loss: 0.008913041092455387
2023-01-24 05:48:43.485125: step: 84/530, loss: 0.019941633567214012
2023-01-24 05:48:44.538778: step: 88/530, loss: 0.006277988199144602
2023-01-24 05:48:45.591656: step: 92/530, loss: 0.0052498579025268555
2023-01-24 05:48:46.648645: step: 96/530, loss: 0.008977203629910946
2023-01-24 05:48:47.692874: step: 100/530, loss: 0.0009111884282901883
2023-01-24 05:48:48.761506: step: 104/530, loss: 0.00698726624250412
2023-01-24 05:48:49.803941: step: 108/530, loss: 0.002838561777025461
2023-01-24 05:48:50.860392: step: 112/530, loss: 0.027512403205037117
2023-01-24 05:48:51.928517: step: 116/530, loss: 0.004172388464212418
2023-01-24 05:48:52.989842: step: 120/530, loss: 0.005863985512405634
2023-01-24 05:48:54.046008: step: 124/530, loss: 0.01308408658951521
2023-01-24 05:48:55.102174: step: 128/530, loss: 0.00741575937718153
2023-01-24 05:48:56.164455: step: 132/530, loss: 0.003897832939401269
2023-01-24 05:48:57.218839: step: 136/530, loss: 0.016058480367064476
2023-01-24 05:48:58.266517: step: 140/530, loss: 0.0027992348186671734
2023-01-24 05:48:59.332307: step: 144/530, loss: 0.00595830986276269
2023-01-24 05:49:00.384805: step: 148/530, loss: 0.0018581663025543094
2023-01-24 05:49:01.446839: step: 152/530, loss: 0.009636035189032555
2023-01-24 05:49:02.532455: step: 156/530, loss: 0.01135893166065216
2023-01-24 05:49:03.584286: step: 160/530, loss: 0.022958068177103996
2023-01-24 05:49:04.647233: step: 164/530, loss: 0.015002578496932983
2023-01-24 05:49:05.710009: step: 168/530, loss: 0.0028302313294261694
2023-01-24 05:49:06.775249: step: 172/530, loss: 0.0030597480945289135
2023-01-24 05:49:07.840008: step: 176/530, loss: 0.008101699873805046
2023-01-24 05:49:08.893104: step: 180/530, loss: 0.008104205131530762
2023-01-24 05:49:09.956673: step: 184/530, loss: 0.0036568562500178814
2023-01-24 05:49:11.038169: step: 188/530, loss: 0.002451567677780986
2023-01-24 05:49:12.089311: step: 192/530, loss: 0.007346960250288248
2023-01-24 05:49:13.129321: step: 196/530, loss: 0.005959811620414257
2023-01-24 05:49:14.178458: step: 200/530, loss: 0.0035565511789172888
2023-01-24 05:49:15.225489: step: 204/530, loss: 0.0018945239717140794
2023-01-24 05:49:16.290268: step: 208/530, loss: 0.040351562201976776
2023-01-24 05:49:17.357416: step: 212/530, loss: 0.006793188862502575
2023-01-24 05:49:18.415292: step: 216/530, loss: 0.0429779551923275
2023-01-24 05:49:19.488270: step: 220/530, loss: 0.021766873076558113
2023-01-24 05:49:20.541317: step: 224/530, loss: 0.0067368075251579285
2023-01-24 05:49:21.593556: step: 228/530, loss: 0.011793391779065132
2023-01-24 05:49:22.643328: step: 232/530, loss: 0.016362538561224937
2023-01-24 05:49:23.698813: step: 236/530, loss: 0.01306929625570774
2023-01-24 05:49:24.760830: step: 240/530, loss: 0.04366306960582733
2023-01-24 05:49:25.823767: step: 244/530, loss: 0.011362576857209206
2023-01-24 05:49:26.876782: step: 248/530, loss: 0.006602996960282326
2023-01-24 05:49:27.938246: step: 252/530, loss: 0.0026361204218119383
2023-01-24 05:49:28.987172: step: 256/530, loss: 0.0072457618080079556
2023-01-24 05:49:30.037796: step: 260/530, loss: 0.0031088402029126883
2023-01-24 05:49:31.102935: step: 264/530, loss: 0.006078782491385937
2023-01-24 05:49:32.157916: step: 268/530, loss: 0.005344335455447435
2023-01-24 05:49:33.228350: step: 272/530, loss: 0.015432574786245823
2023-01-24 05:49:34.288779: step: 276/530, loss: 0.06276095658540726
2023-01-24 05:49:35.348044: step: 280/530, loss: 0.008786395192146301
2023-01-24 05:49:36.407504: step: 284/530, loss: 0.037227388471364975
2023-01-24 05:49:37.463270: step: 288/530, loss: 0.009415870532393456
2023-01-24 05:49:38.531632: step: 292/530, loss: 0.009040523320436478
2023-01-24 05:49:39.580789: step: 296/530, loss: 0.014838225208222866
2023-01-24 05:49:40.659918: step: 300/530, loss: 0.005100354086607695
2023-01-24 05:49:41.731727: step: 304/530, loss: 0.011318660341203213
2023-01-24 05:49:42.812541: step: 308/530, loss: 0.022383419796824455
2023-01-24 05:49:43.885031: step: 312/530, loss: 0.026665139943361282
2023-01-24 05:49:44.951063: step: 316/530, loss: 0.011003552004694939
2023-01-24 05:49:46.028047: step: 320/530, loss: 0.007331583183258772
2023-01-24 05:49:47.101191: step: 324/530, loss: 0.013284152373671532
2023-01-24 05:49:48.159023: step: 328/530, loss: 0.00047639376134611666
2023-01-24 05:49:49.212285: step: 332/530, loss: 0.01065723318606615
2023-01-24 05:49:50.287640: step: 336/530, loss: 0.009985333308577538
2023-01-24 05:49:51.356107: step: 340/530, loss: 0.01382972951978445
2023-01-24 05:49:52.413314: step: 344/530, loss: 0.00889263954013586
2023-01-24 05:49:53.495773: step: 348/530, loss: 0.0050600310787558556
2023-01-24 05:49:54.582703: step: 352/530, loss: 0.014898564666509628
2023-01-24 05:49:55.639884: step: 356/530, loss: 0.0014267188962548971
2023-01-24 05:49:56.713356: step: 360/530, loss: 0.035885490477085114
2023-01-24 05:49:57.782433: step: 364/530, loss: 0.015636736527085304
2023-01-24 05:49:58.843594: step: 368/530, loss: 0.00255257124081254
2023-01-24 05:49:59.907306: step: 372/530, loss: 0.03656373172998428
2023-01-24 05:50:00.962396: step: 376/530, loss: 0.01856282912194729
2023-01-24 05:50:02.047823: step: 380/530, loss: 0.008967249654233456
2023-01-24 05:50:03.117686: step: 384/530, loss: 0.0033324859105050564
2023-01-24 05:50:04.169486: step: 388/530, loss: 0.009601646102964878
2023-01-24 05:50:05.227033: step: 392/530, loss: 0.01912969909608364
2023-01-24 05:50:06.283811: step: 396/530, loss: 0.04187491908669472
2023-01-24 05:50:07.341423: step: 400/530, loss: 0.024936838075518608
2023-01-24 05:50:08.404236: step: 404/530, loss: 0.021949777379631996
2023-01-24 05:50:09.468932: step: 408/530, loss: 0.0026543322019279003
2023-01-24 05:50:10.523604: step: 412/530, loss: 0.019496483728289604
2023-01-24 05:50:11.587187: step: 416/530, loss: 0.016112327575683594
2023-01-24 05:50:12.646020: step: 420/530, loss: 0.0018655316671356559
2023-01-24 05:50:13.713456: step: 424/530, loss: 0.00506379920989275
2023-01-24 05:50:14.795644: step: 428/530, loss: 0.007076523266732693
2023-01-24 05:50:15.882273: step: 432/530, loss: 0.004724256694316864
2023-01-24 05:50:16.943521: step: 436/530, loss: 0.0009300881647504866
2023-01-24 05:50:17.996423: step: 440/530, loss: 0.01967928558588028
2023-01-24 05:50:19.075960: step: 444/530, loss: 0.03559243679046631
2023-01-24 05:50:20.145479: step: 448/530, loss: 0.009139588102698326
2023-01-24 05:50:21.199586: step: 452/530, loss: 0.0041012391448020935
2023-01-24 05:50:22.266010: step: 456/530, loss: 0.005966047290712595
2023-01-24 05:50:23.318596: step: 460/530, loss: 0.007415559142827988
2023-01-24 05:50:24.371494: step: 464/530, loss: 0.021157141774892807
2023-01-24 05:50:25.443177: step: 468/530, loss: 0.08053687959909439
2023-01-24 05:50:26.515000: step: 472/530, loss: 0.01863412745296955
2023-01-24 05:50:27.559603: step: 476/530, loss: 0.002944591222330928
2023-01-24 05:50:28.617572: step: 480/530, loss: 0.0009802079293876886
2023-01-24 05:50:29.667813: step: 484/530, loss: 0.02424168772995472
2023-01-24 05:50:30.711444: step: 488/530, loss: 0.007077371701598167
2023-01-24 05:50:31.767826: step: 492/530, loss: 0.00805947557091713
2023-01-24 05:50:32.860075: step: 496/530, loss: 0.0027319644577801228
2023-01-24 05:50:33.927639: step: 500/530, loss: 0.034257207065820694
2023-01-24 05:50:35.001174: step: 504/530, loss: 0.033649932593107224
2023-01-24 05:50:36.051249: step: 508/530, loss: 0.006967397406697273
2023-01-24 05:50:37.104920: step: 512/530, loss: 0.010623359121382236
2023-01-24 05:50:38.169471: step: 516/530, loss: 0.009382132440805435
2023-01-24 05:50:39.239957: step: 520/530, loss: 0.04060875624418259
2023-01-24 05:50:40.316363: step: 524/530, loss: 0.010053067468106747
2023-01-24 05:50:41.377418: step: 528/530, loss: 0.010939398780465126
2023-01-24 05:50:42.435421: step: 532/530, loss: 0.012207222171127796
2023-01-24 05:50:43.492342: step: 536/530, loss: 0.009608657099306583
2023-01-24 05:50:44.559248: step: 540/530, loss: 0.0790538638830185
2023-01-24 05:50:45.616855: step: 544/530, loss: 0.002581463661044836
2023-01-24 05:50:46.673642: step: 548/530, loss: 0.014704625122249126
2023-01-24 05:50:47.739191: step: 552/530, loss: 0.005571231245994568
2023-01-24 05:50:48.805892: step: 556/530, loss: 0.0032217407133430243
2023-01-24 05:50:49.863054: step: 560/530, loss: 0.018742961809039116
2023-01-24 05:50:50.935869: step: 564/530, loss: 0.02074114792048931
2023-01-24 05:50:52.009657: step: 568/530, loss: 0.004272344522178173
2023-01-24 05:50:53.068890: step: 572/530, loss: 0.007194372359663248
2023-01-24 05:50:54.131405: step: 576/530, loss: 0.005343187600374222
2023-01-24 05:50:55.181143: step: 580/530, loss: 0.04343001917004585
2023-01-24 05:50:56.238756: step: 584/530, loss: 0.025682929903268814
2023-01-24 05:50:57.309624: step: 588/530, loss: 0.022661201655864716
2023-01-24 05:50:58.368646: step: 592/530, loss: 0.006161550059914589
2023-01-24 05:50:59.437303: step: 596/530, loss: 0.004233218729496002
2023-01-24 05:51:00.499395: step: 600/530, loss: 0.02702989988029003
2023-01-24 05:51:01.563624: step: 604/530, loss: 0.011828666552901268
2023-01-24 05:51:02.645194: step: 608/530, loss: 0.0019650631584227085
2023-01-24 05:51:03.701549: step: 612/530, loss: 0.018269114196300507
2023-01-24 05:51:04.749109: step: 616/530, loss: 0.07163850963115692
2023-01-24 05:51:05.804114: step: 620/530, loss: 0.0191291943192482
2023-01-24 05:51:06.877136: step: 624/530, loss: 0.0045981816947460175
2023-01-24 05:51:07.928754: step: 628/530, loss: 0.01305360533297062
2023-01-24 05:51:08.987138: step: 632/530, loss: 0.006944219581782818
2023-01-24 05:51:10.049587: step: 636/530, loss: 0.043573424220085144
2023-01-24 05:51:11.114546: step: 640/530, loss: 0.004806590732187033
2023-01-24 05:51:12.161224: step: 644/530, loss: 0.004089280962944031
2023-01-24 05:51:13.208215: step: 648/530, loss: 0.0021924462635070086
2023-01-24 05:51:14.272560: step: 652/530, loss: 0.027001388370990753
2023-01-24 05:51:15.338869: step: 656/530, loss: 0.009096109308302402
2023-01-24 05:51:16.382695: step: 660/530, loss: 0.005412059370428324
2023-01-24 05:51:17.444965: step: 664/530, loss: 0.0038483578246086836
2023-01-24 05:51:18.499157: step: 668/530, loss: 0.012189789675176144
2023-01-24 05:51:19.585171: step: 672/530, loss: 0.00406645005568862
2023-01-24 05:51:20.643107: step: 676/530, loss: 0.002935217460617423
2023-01-24 05:51:21.721756: step: 680/530, loss: 0.005596601869910955
2023-01-24 05:51:22.773874: step: 684/530, loss: 0.008266955614089966
2023-01-24 05:51:23.825537: step: 688/530, loss: 0.00819226261228323
2023-01-24 05:51:24.887237: step: 692/530, loss: 0.00271823862567544
2023-01-24 05:51:25.936245: step: 696/530, loss: 0.02649662271142006
2023-01-24 05:51:27.011650: step: 700/530, loss: 0.0025134568568319082
2023-01-24 05:51:28.084286: step: 704/530, loss: 0.026998931542038918
2023-01-24 05:51:29.167956: step: 708/530, loss: 0.07398656010627747
2023-01-24 05:51:30.215346: step: 712/530, loss: 0.004583791829645634
2023-01-24 05:51:31.291972: step: 716/530, loss: 0.011217488907277584
2023-01-24 05:51:32.373047: step: 720/530, loss: 0.005903860088437796
2023-01-24 05:51:33.448701: step: 724/530, loss: 0.01827486790716648
2023-01-24 05:51:34.498079: step: 728/530, loss: 0.0011834341567009687
2023-01-24 05:51:35.541678: step: 732/530, loss: 0.009780907072126865
2023-01-24 05:51:36.604381: step: 736/530, loss: 0.014985663816332817
2023-01-24 05:51:37.672513: step: 740/530, loss: 0.005799142178148031
2023-01-24 05:51:38.741743: step: 744/530, loss: 0.03446214646100998
2023-01-24 05:51:39.790873: step: 748/530, loss: 0.007220752537250519
2023-01-24 05:51:40.872559: step: 752/530, loss: 0.006901652552187443
2023-01-24 05:51:41.934142: step: 756/530, loss: 0.007248778827488422
2023-01-24 05:51:43.008137: step: 760/530, loss: 0.020982099696993828
2023-01-24 05:51:44.088439: step: 764/530, loss: 0.0064823743887245655
2023-01-24 05:51:45.140719: step: 768/530, loss: 0.028136756271123886
2023-01-24 05:51:46.200442: step: 772/530, loss: 0.01176868099719286
2023-01-24 05:51:47.256500: step: 776/530, loss: 0.025836462154984474
2023-01-24 05:51:48.334647: step: 780/530, loss: 0.011618404649198055
2023-01-24 05:51:49.402339: step: 784/530, loss: 0.0043899924494326115
2023-01-24 05:51:50.472132: step: 788/530, loss: 0.03393419086933136
2023-01-24 05:51:51.531596: step: 792/530, loss: 0.047133918851614
2023-01-24 05:51:52.588428: step: 796/530, loss: 0.004061580635607243
2023-01-24 05:51:53.642280: step: 800/530, loss: 0.015773583203554153
2023-01-24 05:51:54.684958: step: 804/530, loss: 0.0127754220739007
2023-01-24 05:51:55.741877: step: 808/530, loss: 0.003339008428156376
2023-01-24 05:51:56.820488: step: 812/530, loss: 0.00044267220073379576
2023-01-24 05:51:57.891209: step: 816/530, loss: 0.009378723800182343
2023-01-24 05:51:58.951623: step: 820/530, loss: 0.002209109254181385
2023-01-24 05:52:00.008161: step: 824/530, loss: 0.009332009591162205
2023-01-24 05:52:01.072235: step: 828/530, loss: 0.007360921707004309
2023-01-24 05:52:02.153780: step: 832/530, loss: 0.00873157475143671
2023-01-24 05:52:03.209463: step: 836/530, loss: 0.0046147494576871395
2023-01-24 05:52:04.275866: step: 840/530, loss: 0.03381947800517082
2023-01-24 05:52:05.339638: step: 844/530, loss: 0.00823169108480215
2023-01-24 05:52:06.421850: step: 848/530, loss: 0.012753130868077278
2023-01-24 05:52:07.477697: step: 852/530, loss: 0.0015375040238723159
2023-01-24 05:52:08.569444: step: 856/530, loss: 0.0038569860626012087
2023-01-24 05:52:09.656937: step: 860/530, loss: 0.028392739593982697
2023-01-24 05:52:10.722737: step: 864/530, loss: 0.007941746152937412
2023-01-24 05:52:11.774467: step: 868/530, loss: 0.03349953144788742
2023-01-24 05:52:12.829178: step: 872/530, loss: 0.004938963800668716
2023-01-24 05:52:13.895118: step: 876/530, loss: 0.005563479848206043
2023-01-24 05:52:14.954682: step: 880/530, loss: 0.0005900624673813581
2023-01-24 05:52:16.013736: step: 884/530, loss: 0.0037981749046593904
2023-01-24 05:52:17.069302: step: 888/530, loss: 0.05201589688658714
2023-01-24 05:52:18.120898: step: 892/530, loss: 0.08416608721017838
2023-01-24 05:52:19.183999: step: 896/530, loss: 0.0034238682128489017
2023-01-24 05:52:20.238354: step: 900/530, loss: 0.016306059435009956
2023-01-24 05:52:21.287367: step: 904/530, loss: 0.0248987078666687
2023-01-24 05:52:22.348406: step: 908/530, loss: 0.00760595453903079
2023-01-24 05:52:23.423376: step: 912/530, loss: 0.008105680346488953
2023-01-24 05:52:24.479807: step: 916/530, loss: 0.026912283152341843
2023-01-24 05:52:25.545489: step: 920/530, loss: 0.015558757819235325
2023-01-24 05:52:26.598767: step: 924/530, loss: 0.007810003124177456
2023-01-24 05:52:27.654147: step: 928/530, loss: 0.008646205067634583
2023-01-24 05:52:28.723609: step: 932/530, loss: 0.009670023806393147
2023-01-24 05:52:29.813102: step: 936/530, loss: 0.00692980969324708
2023-01-24 05:52:30.853991: step: 940/530, loss: 0.007936788722872734
2023-01-24 05:52:31.911325: step: 944/530, loss: 0.005081878509372473
2023-01-24 05:52:32.974434: step: 948/530, loss: 0.02534194476902485
2023-01-24 05:52:34.034555: step: 952/530, loss: 0.0066781374625861645
2023-01-24 05:52:35.085947: step: 956/530, loss: 0.017519844695925713
2023-01-24 05:52:36.146748: step: 960/530, loss: 0.0042097545228898525
2023-01-24 05:52:37.207382: step: 964/530, loss: 0.010341073386371136
2023-01-24 05:52:38.256363: step: 968/530, loss: 0.016094431281089783
2023-01-24 05:52:39.341613: step: 972/530, loss: 0.005197430960834026
2023-01-24 05:52:40.382994: step: 976/530, loss: 0.0024263649247586727
2023-01-24 05:52:41.435608: step: 980/530, loss: 0.013275329023599625
2023-01-24 05:52:42.520955: step: 984/530, loss: 0.0313597097992897
2023-01-24 05:52:43.575611: step: 988/530, loss: 0.008750798180699348
2023-01-24 05:52:44.652739: step: 992/530, loss: 0.013497157022356987
2023-01-24 05:52:45.707761: step: 996/530, loss: 0.011439335532486439
2023-01-24 05:52:46.765248: step: 1000/530, loss: 0.0008156416588462889
2023-01-24 05:52:47.812463: step: 1004/530, loss: 0.0024146183859556913
2023-01-24 05:52:48.880100: step: 1008/530, loss: 0.024139579385519028
2023-01-24 05:52:49.951378: step: 1012/530, loss: 0.011094674468040466
2023-01-24 05:52:51.007612: step: 1016/530, loss: 0.000186296776519157
2023-01-24 05:52:52.072545: step: 1020/530, loss: 0.012830633670091629
2023-01-24 05:52:53.137702: step: 1024/530, loss: 0.012097098864614964
2023-01-24 05:52:54.209380: step: 1028/530, loss: 0.07429162412881851
2023-01-24 05:52:55.275233: step: 1032/530, loss: 0.003023487748578191
2023-01-24 05:52:56.336319: step: 1036/530, loss: 0.007510166149586439
2023-01-24 05:52:57.389972: step: 1040/530, loss: 0.030068377032876015
2023-01-24 05:52:58.449713: step: 1044/530, loss: 0.0052937413565814495
2023-01-24 05:52:59.507208: step: 1048/530, loss: 0.023958610370755196
2023-01-24 05:53:00.555164: step: 1052/530, loss: 0.008688181638717651
2023-01-24 05:53:01.597435: step: 1056/530, loss: 0.0022241228725761175
2023-01-24 05:53:02.654909: step: 1060/530, loss: 0.023824557662010193
2023-01-24 05:53:03.739522: step: 1064/530, loss: 0.007908256724476814
2023-01-24 05:53:04.778504: step: 1068/530, loss: 0.008151470683515072
2023-01-24 05:53:05.838039: step: 1072/530, loss: 0.004998909309506416
2023-01-24 05:53:06.911257: step: 1076/530, loss: 0.002809560624882579
2023-01-24 05:53:07.956505: step: 1080/530, loss: 0.006118217017501593
2023-01-24 05:53:09.009725: step: 1084/530, loss: 0.0016347829950973392
2023-01-24 05:53:10.065975: step: 1088/530, loss: 0.007763545960187912
2023-01-24 05:53:11.132726: step: 1092/530, loss: 0.008073820732533932
2023-01-24 05:53:12.173318: step: 1096/530, loss: 0.008089671842753887
2023-01-24 05:53:13.251340: step: 1100/530, loss: 0.002720301505178213
2023-01-24 05:53:14.303365: step: 1104/530, loss: 0.0006606941460631788
2023-01-24 05:53:15.372036: step: 1108/530, loss: 0.008163864724338055
2023-01-24 05:53:16.426493: step: 1112/530, loss: 0.003537238808348775
2023-01-24 05:53:17.485285: step: 1116/530, loss: 0.036442194133996964
2023-01-24 05:53:18.544039: step: 1120/530, loss: 0.0036111362278461456
2023-01-24 05:53:19.604345: step: 1124/530, loss: 0.00657380186021328
2023-01-24 05:53:20.664661: step: 1128/530, loss: 0.012925221584737301
2023-01-24 05:53:21.738236: step: 1132/530, loss: 0.002254266757518053
2023-01-24 05:53:22.794341: step: 1136/530, loss: 0.0030186926014721394
2023-01-24 05:53:23.863507: step: 1140/530, loss: 0.0038074322510510683
2023-01-24 05:53:24.927913: step: 1144/530, loss: 0.02031356655061245
2023-01-24 05:53:25.995382: step: 1148/530, loss: 0.009060061536729336
2023-01-24 05:53:27.072359: step: 1152/530, loss: 0.015726851299405098
2023-01-24 05:53:28.128905: step: 1156/530, loss: 0.015478361397981644
2023-01-24 05:53:29.187362: step: 1160/530, loss: 0.01580202579498291
2023-01-24 05:53:30.243743: step: 1164/530, loss: 0.0048694615252316
2023-01-24 05:53:31.311401: step: 1168/530, loss: 0.0008425582200288773
2023-01-24 05:53:32.398636: step: 1172/530, loss: 0.004964488558471203
2023-01-24 05:53:33.472654: step: 1176/530, loss: 0.003799163270741701
2023-01-24 05:53:34.534062: step: 1180/530, loss: 0.0036438065581023693
2023-01-24 05:53:35.601852: step: 1184/530, loss: 0.009946513921022415
2023-01-24 05:53:36.664883: step: 1188/530, loss: 0.006146504543721676
2023-01-24 05:53:37.743189: step: 1192/530, loss: 0.008281688205897808
2023-01-24 05:53:38.807924: step: 1196/530, loss: 0.008926140144467354
2023-01-24 05:53:39.880110: step: 1200/530, loss: 0.0032253882382065058
2023-01-24 05:53:40.949940: step: 1204/530, loss: 0.005319916643202305
2023-01-24 05:53:42.016520: step: 1208/530, loss: 0.01882709190249443
2023-01-24 05:53:43.059991: step: 1212/530, loss: 0.015157544054090977
2023-01-24 05:53:44.130388: step: 1216/530, loss: 0.028837790712714195
2023-01-24 05:53:45.219685: step: 1220/530, loss: 0.009084654040634632
2023-01-24 05:53:46.290491: step: 1224/530, loss: 0.002967196051031351
2023-01-24 05:53:47.372174: step: 1228/530, loss: 0.005479846149682999
2023-01-24 05:53:48.439086: step: 1232/530, loss: 0.011456901207566261
2023-01-24 05:53:49.499238: step: 1236/530, loss: 0.026058072224259377
2023-01-24 05:53:50.556359: step: 1240/530, loss: 0.009730237536132336
2023-01-24 05:53:51.620479: step: 1244/530, loss: 0.004938570782542229
2023-01-24 05:53:52.671544: step: 1248/530, loss: 0.015716299414634705
2023-01-24 05:53:53.745450: step: 1252/530, loss: 0.005117656663060188
2023-01-24 05:53:54.806945: step: 1256/530, loss: 0.005445735529065132
2023-01-24 05:53:55.876210: step: 1260/530, loss: 0.006621215026825666
2023-01-24 05:53:56.953107: step: 1264/530, loss: 0.003206484019756317
2023-01-24 05:53:58.023770: step: 1268/530, loss: 0.009009724482893944
2023-01-24 05:53:59.096156: step: 1272/530, loss: 0.005450892727822065
2023-01-24 05:54:00.172284: step: 1276/530, loss: 0.004926885012537241
2023-01-24 05:54:01.243383: step: 1280/530, loss: 0.0067573431879282
2023-01-24 05:54:02.316079: step: 1284/530, loss: 0.007508815266191959
2023-01-24 05:54:03.380531: step: 1288/530, loss: 0.006166575010865927
2023-01-24 05:54:04.443036: step: 1292/530, loss: 0.019608868286013603
2023-01-24 05:54:05.523251: step: 1296/530, loss: 0.007370079401880503
2023-01-24 05:54:06.582394: step: 1300/530, loss: 0.008584137074649334
2023-01-24 05:54:07.633524: step: 1304/530, loss: 0.008251721039414406
2023-01-24 05:54:08.698094: step: 1308/530, loss: 0.014559527859091759
2023-01-24 05:54:09.774637: step: 1312/530, loss: 0.00041204720037057996
2023-01-24 05:54:10.850361: step: 1316/530, loss: 0.013654079288244247
2023-01-24 05:54:11.923874: step: 1320/530, loss: 0.011036711744964123
2023-01-24 05:54:13.004229: step: 1324/530, loss: 0.006787970196455717
2023-01-24 05:54:14.071426: step: 1328/530, loss: 0.0062184385024011135
2023-01-24 05:54:15.143206: step: 1332/530, loss: 0.011185524985194206
2023-01-24 05:54:16.197230: step: 1336/530, loss: 0.0020422926172614098
2023-01-24 05:54:17.277059: step: 1340/530, loss: 0.026611292734742165
2023-01-24 05:54:18.350712: step: 1344/530, loss: 0.011061306111514568
2023-01-24 05:54:19.430636: step: 1348/530, loss: 0.002936841920018196
2023-01-24 05:54:20.495728: step: 1352/530, loss: 0.006053184159100056
2023-01-24 05:54:21.570165: step: 1356/530, loss: 0.0078385379165411
2023-01-24 05:54:22.634348: step: 1360/530, loss: 0.027981672435998917
2023-01-24 05:54:23.710657: step: 1364/530, loss: 0.005899256560951471
2023-01-24 05:54:24.761781: step: 1368/530, loss: 0.009277153760194778
2023-01-24 05:54:25.850244: step: 1372/530, loss: 0.013136857189238071
2023-01-24 05:54:26.921642: step: 1376/530, loss: 0.006779379677027464
2023-01-24 05:54:27.982684: step: 1380/530, loss: 0.021974775940179825
2023-01-24 05:54:29.046057: step: 1384/530, loss: 0.017812388017773628
2023-01-24 05:54:30.107658: step: 1388/530, loss: 0.02791920118033886
2023-01-24 05:54:31.165282: step: 1392/530, loss: 0.07180716842412949
2023-01-24 05:54:32.230931: step: 1396/530, loss: 0.029926147311925888
2023-01-24 05:54:33.310830: step: 1400/530, loss: 0.03330957889556885
2023-01-24 05:54:34.364926: step: 1404/530, loss: 0.02639223262667656
2023-01-24 05:54:35.428859: step: 1408/530, loss: 0.006298288702964783
2023-01-24 05:54:36.513730: step: 1412/530, loss: 0.005772239528596401
2023-01-24 05:54:37.587729: step: 1416/530, loss: 0.006503175012767315
2023-01-24 05:54:38.656401: step: 1420/530, loss: 0.007208044640719891
2023-01-24 05:54:39.708461: step: 1424/530, loss: 0.00667016115039587
2023-01-24 05:54:40.767918: step: 1428/530, loss: 0.013332558795809746
2023-01-24 05:54:41.830968: step: 1432/530, loss: 0.007782561704516411
2023-01-24 05:54:42.923476: step: 1436/530, loss: 0.061735544353723526
2023-01-24 05:54:43.996462: step: 1440/530, loss: 0.007760784588754177
2023-01-24 05:54:45.042860: step: 1444/530, loss: 0.00817782711237669
2023-01-24 05:54:46.101041: step: 1448/530, loss: 0.02130030281841755
2023-01-24 05:54:47.158594: step: 1452/530, loss: 0.00745581416413188
2023-01-24 05:54:48.235276: step: 1456/530, loss: 0.006255841813981533
2023-01-24 05:54:49.296320: step: 1460/530, loss: 0.007619886193424463
2023-01-24 05:54:50.355005: step: 1464/530, loss: 0.0015675349859520793
2023-01-24 05:54:51.425782: step: 1468/530, loss: 0.01031919289380312
2023-01-24 05:54:52.483039: step: 1472/530, loss: 0.014294839464128017
2023-01-24 05:54:53.539320: step: 1476/530, loss: 0.03906090930104256
2023-01-24 05:54:54.609259: step: 1480/530, loss: 0.006507217884063721
2023-01-24 05:54:55.666111: step: 1484/530, loss: 0.006505871657282114
2023-01-24 05:54:56.724066: step: 1488/530, loss: 0.006274168845266104
2023-01-24 05:54:57.799954: step: 1492/530, loss: 0.010776106268167496
2023-01-24 05:54:58.860497: step: 1496/530, loss: 0.043974798172712326
2023-01-24 05:54:59.923649: step: 1500/530, loss: 0.018454229459166527
2023-01-24 05:55:00.983374: step: 1504/530, loss: 0.0304866936057806
2023-01-24 05:55:02.074127: step: 1508/530, loss: 0.00503520667552948
2023-01-24 05:55:03.152980: step: 1512/530, loss: 0.05261845141649246
2023-01-24 05:55:04.213120: step: 1516/530, loss: 0.003172110766172409
2023-01-24 05:55:05.287346: step: 1520/530, loss: 0.01669536717236042
2023-01-24 05:55:06.353938: step: 1524/530, loss: 0.022329892963171005
2023-01-24 05:55:07.423722: step: 1528/530, loss: 0.00934907142072916
2023-01-24 05:55:08.491961: step: 1532/530, loss: 0.04218725115060806
2023-01-24 05:55:09.540615: step: 1536/530, loss: 0.001676251762546599
2023-01-24 05:55:10.576954: step: 1540/530, loss: 0.0014983321307227015
2023-01-24 05:55:11.623415: step: 1544/530, loss: 0.002265576971694827
2023-01-24 05:55:12.678870: step: 1548/530, loss: 0.008929194882512093
2023-01-24 05:55:13.745523: step: 1552/530, loss: 0.026078056544065475
2023-01-24 05:55:14.824867: step: 1556/530, loss: 0.05054396018385887
2023-01-24 05:55:15.890858: step: 1560/530, loss: 0.0002468690217938274
2023-01-24 05:55:16.957168: step: 1564/530, loss: 0.014086265116930008
2023-01-24 05:55:18.002983: step: 1568/530, loss: 0.007441191468387842
2023-01-24 05:55:19.068565: step: 1572/530, loss: 0.010648136958479881
2023-01-24 05:55:20.135625: step: 1576/530, loss: 0.005768632981926203
2023-01-24 05:55:21.205751: step: 1580/530, loss: 0.0056974077597260475
2023-01-24 05:55:22.260121: step: 1584/530, loss: 0.00878769438713789
2023-01-24 05:55:23.307938: step: 1588/530, loss: 0.004455979913473129
2023-01-24 05:55:24.370472: step: 1592/530, loss: 0.006661464460194111
2023-01-24 05:55:25.438591: step: 1596/530, loss: 0.01725512370467186
2023-01-24 05:55:26.496602: step: 1600/530, loss: 0.0038942231331020594
2023-01-24 05:55:27.562855: step: 1604/530, loss: 0.019099723547697067
2023-01-24 05:55:28.637971: step: 1608/530, loss: 0.004966052249073982
2023-01-24 05:55:29.710477: step: 1612/530, loss: 0.008269388228654861
2023-01-24 05:55:30.764230: step: 1616/530, loss: 0.006289573386311531
2023-01-24 05:55:31.822699: step: 1620/530, loss: 0.0017546447925269604
2023-01-24 05:55:32.891671: step: 1624/530, loss: 0.03393048793077469
2023-01-24 05:55:33.951748: step: 1628/530, loss: 0.0001804940402507782
2023-01-24 05:55:35.024704: step: 1632/530, loss: 0.003419894725084305
2023-01-24 05:55:36.088240: step: 1636/530, loss: 0.006542523857206106
2023-01-24 05:55:37.133472: step: 1640/530, loss: 0.007139252498745918
2023-01-24 05:55:38.186850: step: 1644/530, loss: 0.043527040630578995
2023-01-24 05:55:39.247303: step: 1648/530, loss: 0.008953775279223919
2023-01-24 05:55:40.300210: step: 1652/530, loss: 0.011791087687015533
2023-01-24 05:55:41.362338: step: 1656/530, loss: 0.021676769480109215
2023-01-24 05:55:42.414769: step: 1660/530, loss: 0.023910125717520714
2023-01-24 05:55:43.469913: step: 1664/530, loss: 0.006911794655025005
2023-01-24 05:55:44.527149: step: 1668/530, loss: 0.0026613674126565456
2023-01-24 05:55:45.583375: step: 1672/530, loss: 0.006056721322238445
2023-01-24 05:55:46.665170: step: 1676/530, loss: 0.07970339059829712
2023-01-24 05:55:47.740792: step: 1680/530, loss: 0.004163119941949844
2023-01-24 05:55:48.789379: step: 1684/530, loss: 0.003548156004399061
2023-01-24 05:55:49.852355: step: 1688/530, loss: 0.01911993883550167
2023-01-24 05:55:50.912654: step: 1692/530, loss: 0.003821560414507985
2023-01-24 05:55:51.969533: step: 1696/530, loss: 0.12350290268659592
2023-01-24 05:55:53.043451: step: 1700/530, loss: 0.008791505359113216
2023-01-24 05:55:54.103120: step: 1704/530, loss: 0.0035048595163971186
2023-01-24 05:55:55.164861: step: 1708/530, loss: 0.022502902895212173
2023-01-24 05:55:56.217519: step: 1712/530, loss: 0.0037889645900577307
2023-01-24 05:55:57.280153: step: 1716/530, loss: 0.006935343146324158
2023-01-24 05:55:58.339504: step: 1720/530, loss: 0.0023403456434607506
2023-01-24 05:55:59.380218: step: 1724/530, loss: 0.035330191254615784
2023-01-24 05:56:00.443621: step: 1728/530, loss: 0.006118969991803169
2023-01-24 05:56:01.502611: step: 1732/530, loss: 0.0026141973212361336
2023-01-24 05:56:02.562063: step: 1736/530, loss: 0.00577622652053833
2023-01-24 05:56:03.640149: step: 1740/530, loss: 0.014890418387949467
2023-01-24 05:56:04.718822: step: 1744/530, loss: 0.0020099061075598
2023-01-24 05:56:05.792904: step: 1748/530, loss: 0.007750468794256449
2023-01-24 05:56:06.855029: step: 1752/530, loss: 0.003517107106745243
2023-01-24 05:56:07.924562: step: 1756/530, loss: 0.0046921223402023315
2023-01-24 05:56:08.978333: step: 1760/530, loss: 0.009625013917684555
2023-01-24 05:56:10.020759: step: 1764/530, loss: 0.00412908848375082
2023-01-24 05:56:11.082372: step: 1768/530, loss: 0.006479433737695217
2023-01-24 05:56:12.150510: step: 1772/530, loss: 0.0018711936427280307
2023-01-24 05:56:13.198013: step: 1776/530, loss: 0.007243666332215071
2023-01-24 05:56:14.274705: step: 1780/530, loss: 0.0015129816019907594
2023-01-24 05:56:15.328347: step: 1784/530, loss: 0.0033547296188771725
2023-01-24 05:56:16.393158: step: 1788/530, loss: 0.007298785727471113
2023-01-24 05:56:17.455823: step: 1792/530, loss: 0.004780021030455828
2023-01-24 05:56:18.526324: step: 1796/530, loss: 0.007903102785348892
2023-01-24 05:56:19.591797: step: 1800/530, loss: 0.0066921161487698555
2023-01-24 05:56:20.664958: step: 1804/530, loss: 0.007224877830594778
2023-01-24 05:56:21.737797: step: 1808/530, loss: 0.049612417817115784
2023-01-24 05:56:22.797640: step: 1812/530, loss: 0.006026745308190584
2023-01-24 05:56:23.842881: step: 1816/530, loss: 0.007636575493961573
2023-01-24 05:56:24.899223: step: 1820/530, loss: 0.047898758202791214
2023-01-24 05:56:25.954697: step: 1824/530, loss: 0.009506751783192158
2023-01-24 05:56:27.009955: step: 1828/530, loss: 0.002883909735828638
2023-01-24 05:56:28.077303: step: 1832/530, loss: 0.003468463895842433
2023-01-24 05:56:29.138330: step: 1836/530, loss: 0.00988856516778469
2023-01-24 05:56:30.208122: step: 1840/530, loss: 0.006861596833914518
2023-01-24 05:56:31.267062: step: 1844/530, loss: 0.003527782391756773
2023-01-24 05:56:32.323479: step: 1848/530, loss: 0.0543820858001709
2023-01-24 05:56:33.396923: step: 1852/530, loss: 0.11515577137470245
2023-01-24 05:56:34.461203: step: 1856/530, loss: 0.020946340635418892
2023-01-24 05:56:35.528935: step: 1860/530, loss: 0.0030384231358766556
2023-01-24 05:56:36.596785: step: 1864/530, loss: 0.013064228929579258
2023-01-24 05:56:37.660871: step: 1868/530, loss: 0.006417909637093544
2023-01-24 05:56:38.725288: step: 1872/530, loss: 0.007266604341566563
2023-01-24 05:56:39.794945: step: 1876/530, loss: 0.021571720018982887
2023-01-24 05:56:40.839486: step: 1880/530, loss: 0.03572744503617287
2023-01-24 05:56:41.891571: step: 1884/530, loss: 0.006688064429908991
2023-01-24 05:56:42.963962: step: 1888/530, loss: 0.005250208079814911
2023-01-24 05:56:44.026355: step: 1892/530, loss: 0.011587629094719887
2023-01-24 05:56:45.083035: step: 1896/530, loss: 0.017239123582839966
2023-01-24 05:56:46.131352: step: 1900/530, loss: 0.006558561697602272
2023-01-24 05:56:47.187821: step: 1904/530, loss: 0.005606526974588633
2023-01-24 05:56:48.244538: step: 1908/530, loss: 0.0046849376522004604
2023-01-24 05:56:49.311252: step: 1912/530, loss: 0.012632392346858978
2023-01-24 05:56:50.367074: step: 1916/530, loss: 0.026876933872699738
2023-01-24 05:56:51.416764: step: 1920/530, loss: 0.0023346610832959414
2023-01-24 05:56:52.484403: step: 1924/530, loss: 0.010086340829730034
2023-01-24 05:56:53.545022: step: 1928/530, loss: 0.0017842890229076147
2023-01-24 05:56:54.591185: step: 1932/530, loss: 0.0038866931572556496
2023-01-24 05:56:55.644180: step: 1936/530, loss: 0.01015001256018877
2023-01-24 05:56:56.694832: step: 1940/530, loss: 0.0034856589045375586
2023-01-24 05:56:57.761676: step: 1944/530, loss: 0.006604752037674189
2023-01-24 05:56:58.832526: step: 1948/530, loss: 0.002270351629704237
2023-01-24 05:56:59.885387: step: 1952/530, loss: 0.012573856860399246
2023-01-24 05:57:00.940410: step: 1956/530, loss: 0.0074013033881783485
2023-01-24 05:57:01.987858: step: 1960/530, loss: 0.013016174547374249
2023-01-24 05:57:03.072911: step: 1964/530, loss: 0.013574600219726562
2023-01-24 05:57:04.145620: step: 1968/530, loss: 0.005106010939925909
2023-01-24 05:57:05.214862: step: 1972/530, loss: 0.008784103207290173
2023-01-24 05:57:06.264819: step: 1976/530, loss: 0.011794948019087315
2023-01-24 05:57:07.319441: step: 1980/530, loss: 0.00013226176088210195
2023-01-24 05:57:08.394434: step: 1984/530, loss: 0.05984872207045555
2023-01-24 05:57:09.467530: step: 1988/530, loss: 0.008299821056425571
2023-01-24 05:57:10.527552: step: 1992/530, loss: 0.018250426277518272
2023-01-24 05:57:11.588840: step: 1996/530, loss: 0.003169644856825471
2023-01-24 05:57:12.662644: step: 2000/530, loss: 0.0028978537302464247
2023-01-24 05:57:13.706765: step: 2004/530, loss: 0.015240422450006008
2023-01-24 05:57:14.768521: step: 2008/530, loss: 0.01981269009411335
2023-01-24 05:57:15.830065: step: 2012/530, loss: 0.005478852428495884
2023-01-24 05:57:16.883664: step: 2016/530, loss: 0.005599991884082556
2023-01-24 05:57:17.956049: step: 2020/530, loss: 0.04507221654057503
2023-01-24 05:57:18.996003: step: 2024/530, loss: 0.006508946884423494
2023-01-24 05:57:20.061504: step: 2028/530, loss: 0.006777461618185043
2023-01-24 05:57:21.122651: step: 2032/530, loss: 0.07480142265558243
2023-01-24 05:57:22.183983: step: 2036/530, loss: 0.01196820754557848
2023-01-24 05:57:23.250837: step: 2040/530, loss: 0.015166237950325012
2023-01-24 05:57:24.306581: step: 2044/530, loss: 0.014804341830313206
2023-01-24 05:57:25.367576: step: 2048/530, loss: 0.019065821543335915
2023-01-24 05:57:26.436420: step: 2052/530, loss: 0.0065493276342749596
2023-01-24 05:57:27.493263: step: 2056/530, loss: 0.004938547033816576
2023-01-24 05:57:28.542489: step: 2060/530, loss: 0.009212430566549301
2023-01-24 05:57:29.609056: step: 2064/530, loss: 0.009946984238922596
2023-01-24 05:57:30.657644: step: 2068/530, loss: 0.01027000229805708
2023-01-24 05:57:31.711033: step: 2072/530, loss: 0.02830147184431553
2023-01-24 05:57:32.806280: step: 2076/530, loss: 0.007420471403747797
2023-01-24 05:57:33.870198: step: 2080/530, loss: 0.003855427959933877
2023-01-24 05:57:34.946428: step: 2084/530, loss: 0.007408120669424534
2023-01-24 05:57:36.007237: step: 2088/530, loss: 0.02598283626139164
2023-01-24 05:57:37.048005: step: 2092/530, loss: 0.035861238837242126
2023-01-24 05:57:38.106622: step: 2096/530, loss: 0.0021612956188619137
2023-01-24 05:57:39.182309: step: 2100/530, loss: 0.005045238416641951
2023-01-24 05:57:40.239854: step: 2104/530, loss: 0.045358043164014816
2023-01-24 05:57:41.299846: step: 2108/530, loss: 0.018878471106290817
2023-01-24 05:57:42.347971: step: 2112/530, loss: 0.02493632212281227
2023-01-24 05:57:43.396342: step: 2116/530, loss: 0.005564841907471418
2023-01-24 05:57:44.470706: step: 2120/530, loss: 0.0032987850718200207
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38578356618129345, 'r': 0.33820115289517566, 'f1': 0.3604287311946564}, 'combined': 0.2655790650907994, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3983333134010764, 'r': 0.2976291337360424, 'f1': 0.34069539094660944}, 'combined': 0.22595341990241452, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34691108545034643, 'r': 0.2844933712121212, 'f1': 0.31261706555671176}, 'combined': 0.20841137703780782, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4004564334668473, 'r': 0.29618533790151763, 'f1': 0.3405174048872744}, 'combined': 0.2222324116106422, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3722338068065038, 'r': 0.3369175063504788, 'f1': 0.35369626662689696}, 'combined': 0.26061830172508194, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39731385965414195, 'r': 0.30925122063123256, 'f1': 0.3477947028520678}, 'combined': 0.23066177183971334, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 2}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38578356618129345, 'r': 0.33820115289517566, 'f1': 0.3604287311946564}, 'combined': 0.2655790650907994, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3983333134010764, 'r': 0.2976291337360424, 'f1': 0.34069539094660944}, 'combined': 0.22595341990241452, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3722338068065038, 'r': 0.3369175063504788, 'f1': 0.35369626662689696}, 'combined': 0.26061830172508194, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39731385965414195, 'r': 0.30925122063123256, 'f1': 0.3477947028520678}, 'combined': 0.23066177183971334, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 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 06:00:27.136513: step: 4/530, loss: 0.011037388816475868
2023-01-24 06:00:28.192080: step: 8/530, loss: 0.0033637695014476776
2023-01-24 06:00:29.232507: step: 12/530, loss: 0.008236338384449482
2023-01-24 06:00:30.280453: step: 16/530, loss: 0.015659745782613754
2023-01-24 06:00:31.327782: step: 20/530, loss: 0.004246231634169817
2023-01-24 06:00:32.392461: step: 24/530, loss: 0.04262460768222809
2023-01-24 06:00:33.464871: step: 28/530, loss: 0.015363809652626514
2023-01-24 06:00:34.501913: step: 32/530, loss: 0.005669242236763239
2023-01-24 06:00:35.552117: step: 36/530, loss: 0.008920131251215935
2023-01-24 06:00:36.600255: step: 40/530, loss: 0.00026123650604858994
2023-01-24 06:00:37.651052: step: 44/530, loss: 0.0073133972473442554
2023-01-24 06:00:38.703832: step: 48/530, loss: 0.013548020273447037
2023-01-24 06:00:39.776971: step: 52/530, loss: 0.003861045464873314
2023-01-24 06:00:40.819614: step: 56/530, loss: 0.0004149958258494735
2023-01-24 06:00:41.867248: step: 60/530, loss: 0.0045206788927316666
2023-01-24 06:00:42.917001: step: 64/530, loss: 0.004160593263804913
2023-01-24 06:00:43.956432: step: 68/530, loss: 0.00907068606466055
2023-01-24 06:00:45.018920: step: 72/530, loss: 0.004222220741212368
2023-01-24 06:00:46.088238: step: 76/530, loss: 0.020256709307432175
2023-01-24 06:00:47.142190: step: 80/530, loss: 0.0011152509832754731
2023-01-24 06:00:48.189124: step: 84/530, loss: 0.006435273215174675
2023-01-24 06:00:49.249952: step: 88/530, loss: 0.00909146573394537
2023-01-24 06:00:50.308453: step: 92/530, loss: 0.001261822646483779
2023-01-24 06:00:51.365144: step: 96/530, loss: 0.004590814001858234
2023-01-24 06:00:52.424658: step: 100/530, loss: 0.040884312242269516
2023-01-24 06:00:53.481512: step: 104/530, loss: 0.007825865410268307
2023-01-24 06:00:54.556570: step: 108/530, loss: 0.022045956924557686
2023-01-24 06:00:55.591398: step: 112/530, loss: 0.014647656120359898
2023-01-24 06:00:56.650296: step: 116/530, loss: 0.010261126793920994
2023-01-24 06:00:57.698783: step: 120/530, loss: 0.003943182528018951
2023-01-24 06:00:58.758633: step: 124/530, loss: 0.006213707383722067
2023-01-24 06:00:59.829866: step: 128/530, loss: 0.0036695185117423534
2023-01-24 06:01:00.894282: step: 132/530, loss: 0.0017012088792398572
2023-01-24 06:01:01.948798: step: 136/530, loss: 0.004110084380954504
2023-01-24 06:01:03.005354: step: 140/530, loss: 0.00849941372871399
2023-01-24 06:01:04.057957: step: 144/530, loss: 0.0022331341169774532
2023-01-24 06:01:05.123281: step: 148/530, loss: 0.029051270335912704
2023-01-24 06:01:06.196353: step: 152/530, loss: 0.003926887642592192
2023-01-24 06:01:07.245063: step: 156/530, loss: 0.0014680703170597553
2023-01-24 06:01:08.313622: step: 160/530, loss: 0.022338997572660446
2023-01-24 06:01:09.368097: step: 164/530, loss: 0.009017284028232098
2023-01-24 06:01:10.419457: step: 168/530, loss: 0.020901868119835854
2023-01-24 06:01:11.462367: step: 172/530, loss: 0.007785148452967405
2023-01-24 06:01:12.528356: step: 176/530, loss: 0.003316078335046768
2023-01-24 06:01:13.574822: step: 180/530, loss: 0.02714390866458416
2023-01-24 06:01:14.632566: step: 184/530, loss: 0.003139380132779479
2023-01-24 06:01:15.689636: step: 188/530, loss: 0.015847723931074142
2023-01-24 06:01:16.730989: step: 192/530, loss: 0.004920356906950474
2023-01-24 06:01:17.806971: step: 196/530, loss: 0.002030257834121585
2023-01-24 06:01:18.853210: step: 200/530, loss: 0.005298843141645193
2023-01-24 06:01:19.914867: step: 204/530, loss: 0.001879102666862309
2023-01-24 06:01:20.973414: step: 208/530, loss: 0.008480825461447239
2023-01-24 06:01:22.025835: step: 212/530, loss: 0.01110406406223774
2023-01-24 06:01:23.092239: step: 216/530, loss: 0.014026210643351078
2023-01-24 06:01:24.139419: step: 220/530, loss: 0.020209141075611115
2023-01-24 06:01:25.188888: step: 224/530, loss: 0.003900995245203376
2023-01-24 06:01:26.234126: step: 228/530, loss: 0.008825898170471191
2023-01-24 06:01:27.318846: step: 232/530, loss: 0.019566548988223076
2023-01-24 06:01:28.388747: step: 236/530, loss: 0.011993246152997017
2023-01-24 06:01:29.454527: step: 240/530, loss: 0.0035306632053107023
2023-01-24 06:01:30.507274: step: 244/530, loss: 0.0027248694095760584
2023-01-24 06:01:31.564869: step: 248/530, loss: 0.0
2023-01-24 06:01:32.645315: step: 252/530, loss: 0.03269648551940918
2023-01-24 06:01:33.697799: step: 256/530, loss: 0.0423007607460022
2023-01-24 06:01:34.757631: step: 260/530, loss: 0.002230660989880562
2023-01-24 06:01:35.816173: step: 264/530, loss: 0.003565023886039853
2023-01-24 06:01:36.880418: step: 268/530, loss: 0.003463475266471505
2023-01-24 06:01:37.953845: step: 272/530, loss: 0.03006424941122532
2023-01-24 06:01:39.004672: step: 276/530, loss: 0.0862032026052475
2023-01-24 06:01:40.058484: step: 280/530, loss: 0.008791036903858185
2023-01-24 06:01:41.131742: step: 284/530, loss: 0.015088467858731747
2023-01-24 06:01:42.184177: step: 288/530, loss: 0.010249665006995201
2023-01-24 06:01:43.253725: step: 292/530, loss: 0.003982336260378361
2023-01-24 06:01:44.316970: step: 296/530, loss: 0.0072026741690933704
2023-01-24 06:01:45.387812: step: 300/530, loss: 0.0024888236075639725
2023-01-24 06:01:46.440484: step: 304/530, loss: 0.002039859304204583
2023-01-24 06:01:47.499269: step: 308/530, loss: 0.008997428230941296
2023-01-24 06:01:48.560998: step: 312/530, loss: 0.03330908715724945
2023-01-24 06:01:49.619405: step: 316/530, loss: 0.0025614972691982985
2023-01-24 06:01:50.683253: step: 320/530, loss: 0.011851364746689796
2023-01-24 06:01:51.727123: step: 324/530, loss: 0.00228997808881104
2023-01-24 06:01:52.775151: step: 328/530, loss: 0.005612990818917751
2023-01-24 06:01:53.840314: step: 332/530, loss: 4.688867193181068e-05
2023-01-24 06:01:54.902740: step: 336/530, loss: 0.004641333594918251
2023-01-24 06:01:55.975486: step: 340/530, loss: 0.018352488055825233
2023-01-24 06:01:57.037752: step: 344/530, loss: 0.0033210974652320147
2023-01-24 06:01:58.085984: step: 348/530, loss: 0.0003681909875012934
2023-01-24 06:01:59.152211: step: 352/530, loss: 0.013355430215597153
2023-01-24 06:02:00.209451: step: 356/530, loss: 0.0031212226022034883
2023-01-24 06:02:01.275981: step: 360/530, loss: 0.004224149975925684
2023-01-24 06:02:02.323637: step: 364/530, loss: 0.0008212754619307816
2023-01-24 06:02:03.388335: step: 368/530, loss: 0.0314108207821846
2023-01-24 06:02:04.454812: step: 372/530, loss: 0.013997214846313
2023-01-24 06:02:05.512499: step: 376/530, loss: 0.0045465137809515
2023-01-24 06:02:06.578037: step: 380/530, loss: 0.006799365859478712
2023-01-24 06:02:07.665492: step: 384/530, loss: 0.02998686023056507
2023-01-24 06:02:08.730845: step: 388/530, loss: 0.027556203305721283
2023-01-24 06:02:09.795346: step: 392/530, loss: 0.007255799137055874
2023-01-24 06:02:10.848074: step: 396/530, loss: 0.006641027517616749
2023-01-24 06:02:11.921810: step: 400/530, loss: 0.004792897496372461
2023-01-24 06:02:12.995769: step: 404/530, loss: 0.000260567496297881
2023-01-24 06:02:14.054625: step: 408/530, loss: 0.0021445187740027905
2023-01-24 06:02:15.104446: step: 412/530, loss: 0.0063408794812858105
2023-01-24 06:02:16.172177: step: 416/530, loss: 0.010694291442632675
2023-01-24 06:02:17.228166: step: 420/530, loss: 0.010802110657095909
2023-01-24 06:02:18.279247: step: 424/530, loss: 0.013180532492697239
2023-01-24 06:02:19.332427: step: 428/530, loss: 0.025315187871456146
2023-01-24 06:02:20.401689: step: 432/530, loss: 0.011261899024248123
2023-01-24 06:02:21.457739: step: 436/530, loss: 0.0028815572150051594
2023-01-24 06:02:22.525381: step: 440/530, loss: 0.009346085600554943
2023-01-24 06:02:23.582745: step: 444/530, loss: 0.003573495429009199
2023-01-24 06:02:24.645095: step: 448/530, loss: 0.017670979723334312
2023-01-24 06:02:25.694514: step: 452/530, loss: 0.0010958461789414287
2023-01-24 06:02:26.755100: step: 456/530, loss: 0.00663788104429841
2023-01-24 06:02:27.806355: step: 460/530, loss: 0.0039746398106217384
2023-01-24 06:02:28.872449: step: 464/530, loss: 0.01288523618131876
2023-01-24 06:02:29.928967: step: 468/530, loss: 0.009165334515273571
2023-01-24 06:02:30.991037: step: 472/530, loss: 0.005334069021046162
2023-01-24 06:02:32.084305: step: 476/530, loss: 0.0032492908649146557
2023-01-24 06:02:33.153757: step: 480/530, loss: 0.050877418369054794
2023-01-24 06:02:34.214107: step: 484/530, loss: 0.009450084529817104
2023-01-24 06:02:35.269138: step: 488/530, loss: 0.012341488152742386
2023-01-24 06:02:36.314497: step: 492/530, loss: 0.004724924918264151
2023-01-24 06:02:37.384744: step: 496/530, loss: 0.010934805497527122
2023-01-24 06:02:38.449431: step: 500/530, loss: 0.0072773960418999195
2023-01-24 06:02:39.505533: step: 504/530, loss: 0.010864170268177986
2023-01-24 06:02:40.568020: step: 508/530, loss: 0.0032583444844931364
2023-01-24 06:02:41.629489: step: 512/530, loss: 0.0021338053047657013
2023-01-24 06:02:42.697208: step: 516/530, loss: 0.005343111697584391
2023-01-24 06:02:43.753112: step: 520/530, loss: 0.03936883062124252
2023-01-24 06:02:44.814941: step: 524/530, loss: 0.010429543443024158
2023-01-24 06:02:45.893170: step: 528/530, loss: 0.0032462028320878744
2023-01-24 06:02:46.956065: step: 532/530, loss: 0.01072680577635765
2023-01-24 06:02:48.019935: step: 536/530, loss: 0.0034480090253055096
2023-01-24 06:02:49.066830: step: 540/530, loss: 0.003447337308898568
2023-01-24 06:02:50.136628: step: 544/530, loss: 0.0023496400099247694
2023-01-24 06:02:51.193801: step: 548/530, loss: 0.0031386411283165216
2023-01-24 06:02:52.262362: step: 552/530, loss: 0.03646097704768181
2023-01-24 06:02:53.336800: step: 556/530, loss: 0.007688587531447411
2023-01-24 06:02:54.398843: step: 560/530, loss: 0.02421599067747593
2023-01-24 06:02:55.454425: step: 564/530, loss: 0.015163530595600605
2023-01-24 06:02:56.514733: step: 568/530, loss: 0.0033448932226747274
2023-01-24 06:02:57.597751: step: 572/530, loss: 0.007094004191458225
2023-01-24 06:02:58.665769: step: 576/530, loss: 0.007009049411863089
2023-01-24 06:02:59.735426: step: 580/530, loss: 0.012880155816674232
2023-01-24 06:03:00.794859: step: 584/530, loss: 0.0003849291242659092
2023-01-24 06:03:01.866945: step: 588/530, loss: 0.0022306242026388645
2023-01-24 06:03:02.920146: step: 592/530, loss: 0.01841331645846367
2023-01-24 06:03:03.985657: step: 596/530, loss: 0.009699378162622452
2023-01-24 06:03:05.046205: step: 600/530, loss: 0.03915206342935562
2023-01-24 06:03:06.097841: step: 604/530, loss: 0.007383402436971664
2023-01-24 06:03:07.158810: step: 608/530, loss: 0.04035816714167595
2023-01-24 06:03:08.216996: step: 612/530, loss: 0.004178424831479788
2023-01-24 06:03:09.277691: step: 616/530, loss: 0.00608796114102006
2023-01-24 06:03:10.340085: step: 620/530, loss: 4.822748087462969e-05
2023-01-24 06:03:11.399956: step: 624/530, loss: 0.025153009220957756
2023-01-24 06:03:12.452860: step: 628/530, loss: 0.003475462319329381
2023-01-24 06:03:13.510278: step: 632/530, loss: 0.01671851985156536
2023-01-24 06:03:14.560222: step: 636/530, loss: 0.013008121401071548
2023-01-24 06:03:15.616103: step: 640/530, loss: 0.006886472925543785
2023-01-24 06:03:16.685202: step: 644/530, loss: 0.010398788377642632
2023-01-24 06:03:17.735835: step: 648/530, loss: 0.010683867149055004
2023-01-24 06:03:18.805936: step: 652/530, loss: 0.03578527271747589
2023-01-24 06:03:19.878569: step: 656/530, loss: 0.005705519579350948
2023-01-24 06:03:20.946088: step: 660/530, loss: 0.011778861284255981
2023-01-24 06:03:21.987828: step: 664/530, loss: 0.015576585195958614
2023-01-24 06:03:23.033164: step: 668/530, loss: 0.005611783359199762
2023-01-24 06:03:24.102816: step: 672/530, loss: 0.0058884210884571075
2023-01-24 06:03:25.166916: step: 676/530, loss: 0.005941211711615324
2023-01-24 06:03:26.228516: step: 680/530, loss: 0.0032191656064242125
2023-01-24 06:03:27.305093: step: 684/530, loss: 0.007754352409392595
2023-01-24 06:03:28.371135: step: 688/530, loss: 0.036522481590509415
2023-01-24 06:03:29.437977: step: 692/530, loss: 0.013598271645605564
2023-01-24 06:03:30.505844: step: 696/530, loss: 0.01127624697983265
2023-01-24 06:03:31.566780: step: 700/530, loss: 0.02059212327003479
2023-01-24 06:03:32.645447: step: 704/530, loss: 0.0027184211649000645
2023-01-24 06:03:33.689277: step: 708/530, loss: 0.002099111909046769
2023-01-24 06:03:34.738203: step: 712/530, loss: 0.003149627475067973
2023-01-24 06:03:35.811979: step: 716/530, loss: 0.005665400065481663
2023-01-24 06:03:36.878980: step: 720/530, loss: 0.0025026474613696337
2023-01-24 06:03:37.939839: step: 724/530, loss: 0.006083074491471052
2023-01-24 06:03:39.011352: step: 728/530, loss: 0.016948169097304344
2023-01-24 06:03:40.084723: step: 732/530, loss: 0.003166420152410865
2023-01-24 06:03:41.145407: step: 736/530, loss: 0.02376437559723854
2023-01-24 06:03:42.197138: step: 740/530, loss: 0.0045867301523685455
2023-01-24 06:03:43.251924: step: 744/530, loss: 0.007157029118388891
2023-01-24 06:03:44.325617: step: 748/530, loss: 0.007166692521423101
2023-01-24 06:03:45.384987: step: 752/530, loss: 0.009258009493350983
2023-01-24 06:03:46.437490: step: 756/530, loss: 0.003960905130952597
2023-01-24 06:03:47.496481: step: 760/530, loss: 0.006320791784673929
2023-01-24 06:03:48.550350: step: 764/530, loss: 0.004994504153728485
2023-01-24 06:03:49.600984: step: 768/530, loss: 0.00482734153047204
2023-01-24 06:03:50.668479: step: 772/530, loss: 0.01570260524749756
2023-01-24 06:03:51.718968: step: 776/530, loss: 9.763549314811826e-05
2023-01-24 06:03:52.785086: step: 780/530, loss: 0.0007025782251730561
2023-01-24 06:03:53.847678: step: 784/530, loss: 0.042397499084472656
2023-01-24 06:03:54.909045: step: 788/530, loss: 0.0076088677160441875
2023-01-24 06:03:55.986762: step: 792/530, loss: 0.010872351005673409
2023-01-24 06:03:57.046830: step: 796/530, loss: 0.0024664278607815504
2023-01-24 06:03:58.093136: step: 800/530, loss: 0.0028902709018439054
2023-01-24 06:03:59.139957: step: 804/530, loss: 0.0033354151528328657
2023-01-24 06:04:00.194964: step: 808/530, loss: 0.007622275035828352
2023-01-24 06:04:01.265149: step: 812/530, loss: 0.006796710193157196
2023-01-24 06:04:02.318613: step: 816/530, loss: 0.009624737314879894
2023-01-24 06:04:03.365951: step: 820/530, loss: 0.013294020667672157
2023-01-24 06:04:04.427114: step: 824/530, loss: 0.03378332406282425
2023-01-24 06:04:05.491218: step: 828/530, loss: 0.0011465639108791947
2023-01-24 06:04:06.556803: step: 832/530, loss: 0.012301189824938774
2023-01-24 06:04:07.602768: step: 836/530, loss: 0.009738078340888023
2023-01-24 06:04:08.646732: step: 840/530, loss: 0.0
2023-01-24 06:04:09.715448: step: 844/530, loss: 0.09453134983778
2023-01-24 06:04:10.772630: step: 848/530, loss: 0.002112054266035557
2023-01-24 06:04:11.830428: step: 852/530, loss: 0.012722463347017765
2023-01-24 06:04:12.891760: step: 856/530, loss: 0.0016223612474277616
2023-01-24 06:04:13.946753: step: 860/530, loss: 0.0022139057982712984
2023-01-24 06:04:14.993762: step: 864/530, loss: 0.00583189632743597
2023-01-24 06:04:16.048384: step: 868/530, loss: 0.008090543560683727
2023-01-24 06:04:17.102163: step: 872/530, loss: 0.003102633636444807
2023-01-24 06:04:18.165835: step: 876/530, loss: 0.02183203212916851
2023-01-24 06:04:19.226142: step: 880/530, loss: 0.0050342814065515995
2023-01-24 06:04:20.305033: step: 884/530, loss: 0.014628928154706955
2023-01-24 06:04:21.369709: step: 888/530, loss: 0.000386589381378144
2023-01-24 06:04:22.431877: step: 892/530, loss: 0.00914692785590887
2023-01-24 06:04:23.501826: step: 896/530, loss: 0.013114671222865582
2023-01-24 06:04:24.552525: step: 900/530, loss: 0.005152002442628145
2023-01-24 06:04:25.631340: step: 904/530, loss: 0.003002758137881756
2023-01-24 06:04:26.736287: step: 908/530, loss: 0.006310395430773497
2023-01-24 06:04:27.788458: step: 912/530, loss: 0.005064757075160742
2023-01-24 06:04:28.891145: step: 916/530, loss: 0.010090429335832596
2023-01-24 06:04:29.951480: step: 920/530, loss: 0.012094387784600258
2023-01-24 06:04:31.032333: step: 924/530, loss: 0.005336686968803406
2023-01-24 06:04:32.110620: step: 928/530, loss: 0.016629178076982498
2023-01-24 06:04:33.163258: step: 932/530, loss: 0.06720240414142609
2023-01-24 06:04:34.208851: step: 936/530, loss: 0.005368458107113838
2023-01-24 06:04:35.259846: step: 940/530, loss: 0.012415033765137196
2023-01-24 06:04:36.308377: step: 944/530, loss: 0.005118426866829395
2023-01-24 06:04:37.363885: step: 948/530, loss: 0.0072637032717466354
2023-01-24 06:04:38.424006: step: 952/530, loss: 0.005285314284265041
2023-01-24 06:04:39.488178: step: 956/530, loss: 0.005225133150815964
2023-01-24 06:04:40.560440: step: 960/530, loss: 0.024208493530750275
2023-01-24 06:04:41.617436: step: 964/530, loss: 0.016217226162552834
2023-01-24 06:04:42.708084: step: 968/530, loss: 0.006129337474703789
2023-01-24 06:04:43.774006: step: 972/530, loss: 0.002516029169782996
2023-01-24 06:04:44.846268: step: 976/530, loss: 0.014980847015976906
2023-01-24 06:04:45.920559: step: 980/530, loss: 0.008146249689161777
2023-01-24 06:04:46.992126: step: 984/530, loss: 0.005085770506411791
2023-01-24 06:04:48.072654: step: 988/530, loss: 0.011522888205945492
2023-01-24 06:04:49.138460: step: 992/530, loss: 0.009969355538487434
2023-01-24 06:04:50.196922: step: 996/530, loss: 0.007449327036738396
2023-01-24 06:04:51.249600: step: 1000/530, loss: 0.0039265332743525505
2023-01-24 06:04:52.316717: step: 1004/530, loss: 0.03362823277711868
2023-01-24 06:04:53.371164: step: 1008/530, loss: 0.05037984997034073
2023-01-24 06:04:54.432357: step: 1012/530, loss: 0.0037533349823206663
2023-01-24 06:04:55.490143: step: 1016/530, loss: 0.01805172860622406
2023-01-24 06:04:56.544400: step: 1020/530, loss: 0.04467471316456795
2023-01-24 06:04:57.589184: step: 1024/530, loss: 0.001675801700912416
2023-01-24 06:04:58.651800: step: 1028/530, loss: 0.00896263774484396
2023-01-24 06:04:59.711443: step: 1032/530, loss: 0.01173726748675108
2023-01-24 06:05:00.769995: step: 1036/530, loss: 0.005703124217689037
2023-01-24 06:05:01.835212: step: 1040/530, loss: 0.00407000444829464
2023-01-24 06:05:02.892418: step: 1044/530, loss: 0.020006271079182625
2023-01-24 06:05:03.949534: step: 1048/530, loss: 0.008091367781162262
2023-01-24 06:05:05.001407: step: 1052/530, loss: 0.004765871446579695
2023-01-24 06:05:06.046254: step: 1056/530, loss: 0.006092479918152094
2023-01-24 06:05:07.105795: step: 1060/530, loss: 0.012051582336425781
2023-01-24 06:05:08.159841: step: 1064/530, loss: 0.013594712130725384
2023-01-24 06:05:09.236524: step: 1068/530, loss: 0.013948970474302769
2023-01-24 06:05:10.280921: step: 1072/530, loss: 0.014910435304045677
2023-01-24 06:05:11.350522: step: 1076/530, loss: 0.0058980342000722885
2023-01-24 06:05:12.417901: step: 1080/530, loss: 0.001361884642392397
2023-01-24 06:05:13.480104: step: 1084/530, loss: 0.011824761517345905
2023-01-24 06:05:14.519750: step: 1088/530, loss: 0.0015725716948509216
2023-01-24 06:05:15.580359: step: 1092/530, loss: 0.013768719509243965
2023-01-24 06:05:16.629928: step: 1096/530, loss: 0.014387240633368492
2023-01-24 06:05:17.680817: step: 1100/530, loss: 0.01927429437637329
2023-01-24 06:05:18.726053: step: 1104/530, loss: 0.005005765240639448
2023-01-24 06:05:19.769190: step: 1108/530, loss: 0.003512695897370577
2023-01-24 06:05:20.817708: step: 1112/530, loss: 0.0004614564822986722
2023-01-24 06:05:21.902444: step: 1116/530, loss: 0.011719648726284504
2023-01-24 06:05:22.956609: step: 1120/530, loss: 0.012000378221273422
2023-01-24 06:05:24.012379: step: 1124/530, loss: 0.022113250568509102
2023-01-24 06:05:25.066833: step: 1128/530, loss: 0.005927121266722679
2023-01-24 06:05:26.129349: step: 1132/530, loss: 0.013145627453923225
2023-01-24 06:05:27.191313: step: 1136/530, loss: 0.009920405223965645
2023-01-24 06:05:28.250619: step: 1140/530, loss: 0.0025121313519775867
2023-01-24 06:05:29.315271: step: 1144/530, loss: 0.022408949211239815
2023-01-24 06:05:30.380277: step: 1148/530, loss: 0.009907946921885014
2023-01-24 06:05:31.431199: step: 1152/530, loss: 0.027946049347519875
2023-01-24 06:05:32.493684: step: 1156/530, loss: 0.023580309003591537
2023-01-24 06:05:33.565883: step: 1160/530, loss: 0.007074342574924231
2023-01-24 06:05:34.647335: step: 1164/530, loss: 0.04781348630785942
2023-01-24 06:05:35.705903: step: 1168/530, loss: 0.01629355549812317
2023-01-24 06:05:36.769622: step: 1172/530, loss: 0.024237146601080894
2023-01-24 06:05:37.827391: step: 1176/530, loss: 0.005001645069569349
2023-01-24 06:05:38.869060: step: 1180/530, loss: 0.013264560140669346
2023-01-24 06:05:39.936037: step: 1184/530, loss: 0.00472449092194438
2023-01-24 06:05:41.009797: step: 1188/530, loss: 0.0008861303795129061
2023-01-24 06:05:42.061179: step: 1192/530, loss: 0.0016576367197558284
2023-01-24 06:05:43.119292: step: 1196/530, loss: 0.0021313801407814026
2023-01-24 06:05:44.198906: step: 1200/530, loss: 0.003909954335540533
2023-01-24 06:05:45.260768: step: 1204/530, loss: 0.017153365537524223
2023-01-24 06:05:46.311305: step: 1208/530, loss: 0.00652704294770956
2023-01-24 06:05:47.357047: step: 1212/530, loss: 0.009187408722937107
2023-01-24 06:05:48.424829: step: 1216/530, loss: 0.006367970257997513
2023-01-24 06:05:49.482472: step: 1220/530, loss: 0.00884553138166666
2023-01-24 06:05:50.545376: step: 1224/530, loss: 0.0034300806000828743
2023-01-24 06:05:51.596985: step: 1228/530, loss: 0.004335857927799225
2023-01-24 06:05:52.669729: step: 1232/530, loss: 0.004962536506354809
2023-01-24 06:05:53.738732: step: 1236/530, loss: 0.004654952324926853
2023-01-24 06:05:54.791148: step: 1240/530, loss: 0.00821628700941801
2023-01-24 06:05:55.841438: step: 1244/530, loss: 0.010016443207859993
2023-01-24 06:05:56.901669: step: 1248/530, loss: 0.013293548487126827
2023-01-24 06:05:57.954896: step: 1252/530, loss: 0.0034096897579729557
2023-01-24 06:05:59.043692: step: 1256/530, loss: 0.11217693239450455
2023-01-24 06:06:00.096900: step: 1260/530, loss: 0.0040709488093853
2023-01-24 06:06:01.171195: step: 1264/530, loss: 0.0040858471766114235
2023-01-24 06:06:02.234142: step: 1268/530, loss: 0.0019328842172399163
2023-01-24 06:06:03.284954: step: 1272/530, loss: 0.0063474178314208984
2023-01-24 06:06:04.351002: step: 1276/530, loss: 0.00012823025463148952
2023-01-24 06:06:05.418607: step: 1280/530, loss: 0.009802342392504215
2023-01-24 06:06:06.472962: step: 1284/530, loss: 0.0645652487874031
2023-01-24 06:06:07.529186: step: 1288/530, loss: 0.010666261427104473
2023-01-24 06:06:08.587067: step: 1292/530, loss: 0.005917792208492756
2023-01-24 06:06:09.647284: step: 1296/530, loss: 0.00842365249991417
2023-01-24 06:06:10.699950: step: 1300/530, loss: 0.0009731862228363752
2023-01-24 06:06:11.745308: step: 1304/530, loss: 0.0032120600808411837
2023-01-24 06:06:12.832325: step: 1308/530, loss: 0.03412623330950737
2023-01-24 06:06:13.900233: step: 1312/530, loss: 0.017298497259616852
2023-01-24 06:06:14.977128: step: 1316/530, loss: 0.012309487909078598
2023-01-24 06:06:16.028931: step: 1320/530, loss: 0.002919018268585205
2023-01-24 06:06:17.083066: step: 1324/530, loss: 0.005242897197604179
2023-01-24 06:06:18.148411: step: 1328/530, loss: 0.027444595471024513
2023-01-24 06:06:19.205806: step: 1332/530, loss: 0.0411381721496582
2023-01-24 06:06:20.278508: step: 1336/530, loss: 0.024505717679858208
2023-01-24 06:06:21.327461: step: 1340/530, loss: 0.005025478545576334
2023-01-24 06:06:22.407932: step: 1344/530, loss: 0.038513533771038055
2023-01-24 06:06:23.468279: step: 1348/530, loss: 0.0034771100617945194
2023-01-24 06:06:24.535492: step: 1352/530, loss: 0.018608078360557556
2023-01-24 06:06:25.591340: step: 1356/530, loss: 0.01439326349645853
2023-01-24 06:06:26.642635: step: 1360/530, loss: 0.01232139952480793
2023-01-24 06:06:27.701172: step: 1364/530, loss: 0.009235356003046036
2023-01-24 06:06:28.749163: step: 1368/530, loss: 0.023434307426214218
2023-01-24 06:06:29.821376: step: 1372/530, loss: 0.0028404712211340666
2023-01-24 06:06:30.873083: step: 1376/530, loss: 0.01623358577489853
2023-01-24 06:06:31.921362: step: 1380/530, loss: 0.012981625273823738
2023-01-24 06:06:32.971553: step: 1384/530, loss: 0.006055581849068403
2023-01-24 06:06:34.030313: step: 1388/530, loss: 0.00852600485086441
2023-01-24 06:06:35.100086: step: 1392/530, loss: 0.015775974839925766
2023-01-24 06:06:36.165238: step: 1396/530, loss: 0.002838095184415579
2023-01-24 06:06:37.242423: step: 1400/530, loss: 0.012099510990083218
2023-01-24 06:06:38.315952: step: 1404/530, loss: 0.006254035513848066
2023-01-24 06:06:39.375692: step: 1408/530, loss: 0.003088791389018297
2023-01-24 06:06:40.429187: step: 1412/530, loss: 0.0022640274837613106
2023-01-24 06:06:41.505422: step: 1416/530, loss: 0.004288996569812298
2023-01-24 06:06:42.574820: step: 1420/530, loss: 0.005868943408131599
2023-01-24 06:06:43.627293: step: 1424/530, loss: 0.010310453362762928
2023-01-24 06:06:44.678323: step: 1428/530, loss: 0.04777528718113899
2023-01-24 06:06:45.732687: step: 1432/530, loss: 0.0029129551257938147
2023-01-24 06:06:46.799952: step: 1436/530, loss: 0.004396195523440838
2023-01-24 06:06:47.843278: step: 1440/530, loss: 0.0026751141995191574
2023-01-24 06:06:48.910787: step: 1444/530, loss: 0.002124643651768565
2023-01-24 06:06:49.981743: step: 1448/530, loss: 0.008699733763933182
2023-01-24 06:06:51.038050: step: 1452/530, loss: 0.004703194834291935
2023-01-24 06:06:52.107626: step: 1456/530, loss: 0.0023235317785292864
2023-01-24 06:06:53.169116: step: 1460/530, loss: 0.003502794075757265
2023-01-24 06:06:54.226938: step: 1464/530, loss: 0.002956230426207185
2023-01-24 06:06:55.295300: step: 1468/530, loss: 0.005893892142921686
2023-01-24 06:06:56.372488: step: 1472/530, loss: 0.05266788229346275
2023-01-24 06:06:57.432537: step: 1476/530, loss: 0.018919985741376877
2023-01-24 06:06:58.499958: step: 1480/530, loss: 0.012196439318358898
2023-01-24 06:06:59.567188: step: 1484/530, loss: 0.004680344834923744
2023-01-24 06:07:00.631375: step: 1488/530, loss: 0.007560653146356344
2023-01-24 06:07:01.686447: step: 1492/530, loss: 0.007548678666353226
2023-01-24 06:07:02.741954: step: 1496/530, loss: 0.004957258701324463
2023-01-24 06:07:03.804141: step: 1500/530, loss: 0.00321231409907341
2023-01-24 06:07:04.857530: step: 1504/530, loss: 0.007621142081916332
2023-01-24 06:07:05.942113: step: 1508/530, loss: 0.0048268819227814674
2023-01-24 06:07:06.989207: step: 1512/530, loss: 0.013526175171136856
2023-01-24 06:07:08.054866: step: 1516/530, loss: 0.012672184966504574
2023-01-24 06:07:09.127002: step: 1520/530, loss: 0.00571331474930048
2023-01-24 06:07:10.183181: step: 1524/530, loss: 0.003061615163460374
2023-01-24 06:07:11.236345: step: 1528/530, loss: 0.02636868692934513
2023-01-24 06:07:12.293039: step: 1532/530, loss: 0.01025893073529005
2023-01-24 06:07:13.348251: step: 1536/530, loss: 0.004355986602604389
2023-01-24 06:07:14.413088: step: 1540/530, loss: 0.007915707305073738
2023-01-24 06:07:15.464192: step: 1544/530, loss: 0.006532545667141676
2023-01-24 06:07:16.535575: step: 1548/530, loss: 0.01847263239324093
2023-01-24 06:07:17.590246: step: 1552/530, loss: 0.003102448768913746
2023-01-24 06:07:18.653705: step: 1556/530, loss: 0.06924397498369217
2023-01-24 06:07:19.722726: step: 1560/530, loss: 0.00920573715120554
2023-01-24 06:07:20.781534: step: 1564/530, loss: 0.0028577041812241077
2023-01-24 06:07:21.846434: step: 1568/530, loss: 0.026675723493099213
2023-01-24 06:07:22.899603: step: 1572/530, loss: 0.013881134800612926
2023-01-24 06:07:23.959321: step: 1576/530, loss: 0.004702684469521046
2023-01-24 06:07:25.002817: step: 1580/530, loss: 0.013468734920024872
2023-01-24 06:07:26.073062: step: 1584/530, loss: 0.04919878765940666
2023-01-24 06:07:27.147795: step: 1588/530, loss: 0.052308760583400726
2023-01-24 06:07:28.214364: step: 1592/530, loss: 0.004034318961203098
2023-01-24 06:07:29.270771: step: 1596/530, loss: 0.011949100531637669
2023-01-24 06:07:30.336299: step: 1600/530, loss: 0.015437108464539051
2023-01-24 06:07:31.407460: step: 1604/530, loss: 0.0021641866769641638
2023-01-24 06:07:32.468888: step: 1608/530, loss: 0.012281359173357487
2023-01-24 06:07:33.533654: step: 1612/530, loss: 0.00956805795431137
2023-01-24 06:07:34.605548: step: 1616/530, loss: 0.00560244033113122
2023-01-24 06:07:35.653889: step: 1620/530, loss: 0.005779684521257877
2023-01-24 06:07:36.710837: step: 1624/530, loss: 0.01142224669456482
2023-01-24 06:07:37.778575: step: 1628/530, loss: 0.02249796688556671
2023-01-24 06:07:38.832577: step: 1632/530, loss: 0.017319761216640472
2023-01-24 06:07:39.885242: step: 1636/530, loss: 0.005452349316328764
2023-01-24 06:07:40.947815: step: 1640/530, loss: 0.02802310697734356
2023-01-24 06:07:41.992706: step: 1644/530, loss: 0.010926993563771248
2023-01-24 06:07:43.066909: step: 1648/530, loss: 0.009614617563784122
2023-01-24 06:07:44.126078: step: 1652/530, loss: 0.0312640517950058
2023-01-24 06:07:45.181153: step: 1656/530, loss: 0.011161825619637966
2023-01-24 06:07:46.251351: step: 1660/530, loss: 0.010059613734483719
2023-01-24 06:07:47.315602: step: 1664/530, loss: 0.00916595570743084
2023-01-24 06:07:48.379907: step: 1668/530, loss: 0.0011666493955999613
2023-01-24 06:07:49.415458: step: 1672/530, loss: 0.018669545650482178
2023-01-24 06:07:50.478303: step: 1676/530, loss: 0.024517547339200974
2023-01-24 06:07:51.554663: step: 1680/530, loss: 0.009119664318859577
2023-01-24 06:07:52.600892: step: 1684/530, loss: 0.002078716177493334
2023-01-24 06:07:53.662811: step: 1688/530, loss: 0.004737490322440863
2023-01-24 06:07:54.714066: step: 1692/530, loss: 0.0035940019879490137
2023-01-24 06:07:55.771208: step: 1696/530, loss: 0.006481850519776344
2023-01-24 06:07:56.835897: step: 1700/530, loss: 0.0066940574906766415
2023-01-24 06:07:57.889158: step: 1704/530, loss: 0.0036061364226043224
2023-01-24 06:07:58.942854: step: 1708/530, loss: 0.005528014153242111
2023-01-24 06:08:00.000229: step: 1712/530, loss: 0.000989230116829276
2023-01-24 06:08:01.067361: step: 1716/530, loss: 0.0024887125473469496
2023-01-24 06:08:02.148612: step: 1720/530, loss: 0.00038045382825657725
2023-01-24 06:08:03.208330: step: 1724/530, loss: 0.005280985962599516
2023-01-24 06:08:04.271800: step: 1728/530, loss: 0.04039860516786575
2023-01-24 06:08:05.341004: step: 1732/530, loss: 0.003629072802141309
2023-01-24 06:08:06.394484: step: 1736/530, loss: 0.045726411044597626
2023-01-24 06:08:07.463144: step: 1740/530, loss: 0.012084231711924076
2023-01-24 06:08:08.520908: step: 1744/530, loss: 0.0011039696400985122
2023-01-24 06:08:09.580650: step: 1748/530, loss: 0.003871541703119874
2023-01-24 06:08:10.638788: step: 1752/530, loss: 0.007040179800242186
2023-01-24 06:08:11.709498: step: 1756/530, loss: 0.003478290745988488
2023-01-24 06:08:12.783919: step: 1760/530, loss: 0.0040003955364227295
2023-01-24 06:08:13.845667: step: 1764/530, loss: 0.004138328600674868
2023-01-24 06:08:14.905284: step: 1768/530, loss: 0.021170681342482567
2023-01-24 06:08:15.975424: step: 1772/530, loss: 0.016243066638708115
2023-01-24 06:08:17.048939: step: 1776/530, loss: 0.004305277951061726
2023-01-24 06:08:18.112416: step: 1780/530, loss: 0.014048103243112564
2023-01-24 06:08:19.169883: step: 1784/530, loss: 0.0247513260692358
2023-01-24 06:08:20.230836: step: 1788/530, loss: 0.003777140751481056
2023-01-24 06:08:21.299738: step: 1792/530, loss: 0.04273241013288498
2023-01-24 06:08:22.365035: step: 1796/530, loss: 0.00622946210205555
2023-01-24 06:08:23.429608: step: 1800/530, loss: 0.01790163852274418
2023-01-24 06:08:24.515237: step: 1804/530, loss: 0.014463473111391068
2023-01-24 06:08:25.576778: step: 1808/530, loss: 0.0037626056000590324
2023-01-24 06:08:26.636600: step: 1812/530, loss: 0.00474170595407486
2023-01-24 06:08:27.693059: step: 1816/530, loss: 0.0031185441184788942
2023-01-24 06:08:28.762524: step: 1820/530, loss: 0.04505028575658798
2023-01-24 06:08:29.817526: step: 1824/530, loss: 0.01430468074977398
2023-01-24 06:08:30.883039: step: 1828/530, loss: 0.005075530149042606
2023-01-24 06:08:31.962339: step: 1832/530, loss: 0.009478818625211716
2023-01-24 06:08:33.041998: step: 1836/530, loss: 0.009214231744408607
2023-01-24 06:08:34.105764: step: 1840/530, loss: 0.00033458220423199236
2023-01-24 06:08:35.169497: step: 1844/530, loss: 0.06962233036756516
2023-01-24 06:08:36.236409: step: 1848/530, loss: 0.010475759394466877
2023-01-24 06:08:37.292766: step: 1852/530, loss: 0.05261128395795822
2023-01-24 06:08:38.343548: step: 1856/530, loss: 0.006615791469812393
2023-01-24 06:08:39.424700: step: 1860/530, loss: 0.03412812575697899
2023-01-24 06:08:40.480698: step: 1864/530, loss: 0.007931055501103401
2023-01-24 06:08:41.545513: step: 1868/530, loss: 0.006649984046816826
2023-01-24 06:08:42.615903: step: 1872/530, loss: 0.06735583394765854
2023-01-24 06:08:43.667585: step: 1876/530, loss: 0.014200116507709026
2023-01-24 06:08:44.721894: step: 1880/530, loss: 0.018247291445732117
2023-01-24 06:08:45.776599: step: 1884/530, loss: 0.010077846236526966
2023-01-24 06:08:46.843013: step: 1888/530, loss: 0.052197154611349106
2023-01-24 06:08:47.890371: step: 1892/530, loss: 0.005303631071001291
2023-01-24 06:08:48.932963: step: 1896/530, loss: 0.002336485544219613
2023-01-24 06:08:49.976714: step: 1900/530, loss: 0.028202222660183907
2023-01-24 06:08:51.041139: step: 1904/530, loss: 0.02427256479859352
2023-01-24 06:08:52.103517: step: 1908/530, loss: 0.008046003989875317
2023-01-24 06:08:53.162016: step: 1912/530, loss: 0.012446272186934948
2023-01-24 06:08:54.236366: step: 1916/530, loss: 0.0050819870084524155
2023-01-24 06:08:55.310394: step: 1920/530, loss: 0.00651470897719264
2023-01-24 06:08:56.381567: step: 1924/530, loss: 0.0051939948461949825
2023-01-24 06:08:57.446215: step: 1928/530, loss: 0.008553149178624153
2023-01-24 06:08:58.509285: step: 1932/530, loss: 0.011007853783667088
2023-01-24 06:08:59.543063: step: 1936/530, loss: 0.011660592630505562
2023-01-24 06:09:00.601238: step: 1940/530, loss: 0.004830527119338512
2023-01-24 06:09:01.671365: step: 1944/530, loss: 0.007369286846369505
2023-01-24 06:09:02.726402: step: 1948/530, loss: 0.0076780496165156364
2023-01-24 06:09:03.785800: step: 1952/530, loss: 0.0041919369250535965
2023-01-24 06:09:04.856124: step: 1956/530, loss: 0.07779137045145035
2023-01-24 06:09:05.942221: step: 1960/530, loss: 0.02050156518816948
2023-01-24 06:09:07.005082: step: 1964/530, loss: 0.007081665098667145
2023-01-24 06:09:08.054111: step: 1968/530, loss: 0.0021032914519309998
2023-01-24 06:09:09.111239: step: 1972/530, loss: 0.009371479973196983
2023-01-24 06:09:10.157016: step: 1976/530, loss: 0.0004164410347584635
2023-01-24 06:09:11.217032: step: 1980/530, loss: 0.00537485396489501
2023-01-24 06:09:12.283113: step: 1984/530, loss: 0.01088883075863123
2023-01-24 06:09:13.335790: step: 1988/530, loss: 0.006430459674447775
2023-01-24 06:09:14.398150: step: 1992/530, loss: 0.007853731513023376
2023-01-24 06:09:15.470385: step: 1996/530, loss: 0.011508864350616932
2023-01-24 06:09:16.522358: step: 2000/530, loss: 0.05309774726629257
2023-01-24 06:09:17.572220: step: 2004/530, loss: 0.030090630054473877
2023-01-24 06:09:18.661961: step: 2008/530, loss: 0.008893055841326714
2023-01-24 06:09:19.722110: step: 2012/530, loss: 0.06681640446186066
2023-01-24 06:09:20.776019: step: 2016/530, loss: 0.0010769636137410998
2023-01-24 06:09:21.833173: step: 2020/530, loss: 0.0020682504400610924
2023-01-24 06:09:22.886625: step: 2024/530, loss: 0.002563395304605365
2023-01-24 06:09:23.969248: step: 2028/530, loss: 0.006997863296419382
2023-01-24 06:09:25.029783: step: 2032/530, loss: 0.05591948702931404
2023-01-24 06:09:26.103092: step: 2036/530, loss: 0.03244248032569885
2023-01-24 06:09:27.147083: step: 2040/530, loss: 0.001269844244234264
2023-01-24 06:09:28.198474: step: 2044/530, loss: 0.0016195080243051052
2023-01-24 06:09:29.232791: step: 2048/530, loss: 0.0018853244837373495
2023-01-24 06:09:30.286385: step: 2052/530, loss: 0.028843555599451065
2023-01-24 06:09:31.351133: step: 2056/530, loss: 0.06822147965431213
2023-01-24 06:09:32.407861: step: 2060/530, loss: 0.0009727854048833251
2023-01-24 06:09:33.456395: step: 2064/530, loss: 0.011867367662489414
2023-01-24 06:09:34.529836: step: 2068/530, loss: 0.005429359618574381
2023-01-24 06:09:35.613387: step: 2072/530, loss: 0.002079221187159419
2023-01-24 06:09:36.666066: step: 2076/530, loss: 0.05388302728533745
2023-01-24 06:09:37.713470: step: 2080/530, loss: 0.000665469968225807
2023-01-24 06:09:38.766464: step: 2084/530, loss: 0.00513417599722743
2023-01-24 06:09:39.819990: step: 2088/530, loss: 0.008952285163104534
2023-01-24 06:09:40.880422: step: 2092/530, loss: 0.07183483988046646
2023-01-24 06:09:41.939629: step: 2096/530, loss: 0.0047781262546777725
2023-01-24 06:09:42.983457: step: 2100/530, loss: 0.00354943354614079
2023-01-24 06:09:44.037761: step: 2104/530, loss: 0.011749199591577053
2023-01-24 06:09:45.108919: step: 2108/530, loss: 0.014387881383299828
2023-01-24 06:09:46.163870: step: 2112/530, loss: 0.004152303095906973
2023-01-24 06:09:47.220660: step: 2116/530, loss: 0.009463369846343994
2023-01-24 06:09:48.280302: step: 2120/530, loss: 0.0057126665487885475
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34534543325526934, 'r': 0.2792850378787879, 'f1': 0.3088219895287958}, 'combined': 0.20588132635253054, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40169840874310664, 'r': 0.2946714970710678, 'f1': 0.3399603299542459}, 'combined': 0.22186884691750783, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3751196677730654, 'r': 0.33027614012656986, 'f1': 0.35127250423148804}, 'combined': 0.2588323715389912, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.397134256792261, 'r': 0.30773606911608103, 'f1': 0.3467660095893401}, 'combined': 0.22997952967583177, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 3}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3722338068065038, 'r': 0.3369175063504788, 'f1': 0.35369626662689696}, 'combined': 0.26061830172508194, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39731385965414195, 'r': 0.30925122063123256, 'f1': 0.3477947028520678}, 'combined': 0.23066177183971334, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:12:18.972837: step: 4/530, loss: 0.006242005620151758
2023-01-24 06:12:20.026587: step: 8/530, loss: 0.008245788514614105
2023-01-24 06:12:21.080041: step: 12/530, loss: 0.020505303516983986
2023-01-24 06:12:22.124448: step: 16/530, loss: 0.012723291292786598
2023-01-24 06:12:23.175672: step: 20/530, loss: 0.006476703565567732
2023-01-24 06:12:24.238424: step: 24/530, loss: 0.005096540320664644
2023-01-24 06:12:25.294966: step: 28/530, loss: 0.005278478842228651
2023-01-24 06:12:26.347344: step: 32/530, loss: 0.008071999065577984
2023-01-24 06:12:27.393056: step: 36/530, loss: 0.011847801506519318
2023-01-24 06:12:28.457376: step: 40/530, loss: 0.037519242614507675
2023-01-24 06:12:29.508567: step: 44/530, loss: 0.003702266840264201
2023-01-24 06:12:30.573657: step: 48/530, loss: 0.0025951655115932226
2023-01-24 06:12:31.616026: step: 52/530, loss: 0.028691096231341362
2023-01-24 06:12:32.655462: step: 56/530, loss: 0.004881665110588074
2023-01-24 06:12:33.694110: step: 60/530, loss: 0.023504680022597313
2023-01-24 06:12:34.741972: step: 64/530, loss: 0.033218350261449814
2023-01-24 06:12:35.796989: step: 68/530, loss: 0.02339085564017296
2023-01-24 06:12:36.831924: step: 72/530, loss: 0.005363741889595985
2023-01-24 06:12:37.883126: step: 76/530, loss: 0.01806650124490261
2023-01-24 06:12:38.943846: step: 80/530, loss: 0.007291574031114578
2023-01-24 06:12:39.991049: step: 84/530, loss: 0.000939376070164144
2023-01-24 06:12:41.042627: step: 88/530, loss: 0.00256658298894763
2023-01-24 06:12:42.096115: step: 92/530, loss: 0.0036157474387437105
2023-01-24 06:12:43.149897: step: 96/530, loss: 0.0009154801955446601
2023-01-24 06:12:44.224114: step: 100/530, loss: 0.012248910032212734
2023-01-24 06:12:45.275827: step: 104/530, loss: 0.006855723913758993
2023-01-24 06:12:46.316265: step: 108/530, loss: 0.017865311354398727
2023-01-24 06:12:47.377955: step: 112/530, loss: 0.01491771824657917
2023-01-24 06:12:48.427207: step: 116/530, loss: 0.004171750042587519
2023-01-24 06:12:49.486416: step: 120/530, loss: 0.020960237830877304
2023-01-24 06:12:50.552129: step: 124/530, loss: 0.008451152592897415
2023-01-24 06:12:51.618331: step: 128/530, loss: 0.12183654308319092
2023-01-24 06:12:52.692943: step: 132/530, loss: 0.0005778635386377573
2023-01-24 06:12:53.746114: step: 136/530, loss: 0.017487315461039543
2023-01-24 06:12:54.804670: step: 140/530, loss: 0.019294297322630882
2023-01-24 06:12:55.864199: step: 144/530, loss: 0.0061052716337144375
2023-01-24 06:12:56.926987: step: 148/530, loss: 0.007047742605209351
2023-01-24 06:12:57.996484: step: 152/530, loss: 0.010840174742043018
2023-01-24 06:12:59.042580: step: 156/530, loss: 0.006134039256721735
2023-01-24 06:13:00.097684: step: 160/530, loss: 0.03142046555876732
2023-01-24 06:13:01.156582: step: 164/530, loss: 0.026667138561606407
2023-01-24 06:13:02.215742: step: 168/530, loss: 0.012985733337700367
2023-01-24 06:13:03.281524: step: 172/530, loss: 0.0085452850908041
2023-01-24 06:13:04.336458: step: 176/530, loss: 0.001029927283525467
2023-01-24 06:13:05.389823: step: 180/530, loss: 0.002813845407217741
2023-01-24 06:13:06.451372: step: 184/530, loss: 0.0048736161552369595
2023-01-24 06:13:07.506634: step: 188/530, loss: 0.006364193744957447
2023-01-24 06:13:08.568101: step: 192/530, loss: 0.004597123712301254
2023-01-24 06:13:09.623770: step: 196/530, loss: 0.00558228325098753
2023-01-24 06:13:10.674152: step: 200/530, loss: 0.028867751359939575
2023-01-24 06:13:11.736284: step: 204/530, loss: 0.011359620839357376
2023-01-24 06:13:12.802924: step: 208/530, loss: 0.01429405901581049
2023-01-24 06:13:13.853047: step: 212/530, loss: 0.001351762330159545
2023-01-24 06:13:14.927653: step: 216/530, loss: 0.006379213649779558
2023-01-24 06:13:15.984994: step: 220/530, loss: 0.004810844082385302
2023-01-24 06:13:17.045417: step: 224/530, loss: 0.0009049431537277997
2023-01-24 06:13:18.117146: step: 228/530, loss: 0.009955755434930325
2023-01-24 06:13:19.171879: step: 232/530, loss: 0.00444530975073576
2023-01-24 06:13:20.239656: step: 236/530, loss: 0.008952903561294079
2023-01-24 06:13:21.300201: step: 240/530, loss: 0.029141144827008247
2023-01-24 06:13:22.362833: step: 244/530, loss: 0.010878726840019226
2023-01-24 06:13:23.450750: step: 248/530, loss: 0.0283419918268919
2023-01-24 06:13:24.519974: step: 252/530, loss: 0.010638169944286346
2023-01-24 06:13:25.586121: step: 256/530, loss: 0.0236524548381567
2023-01-24 06:13:26.636482: step: 260/530, loss: 0.012847517617046833
2023-01-24 06:13:27.703978: step: 264/530, loss: 0.007505145389586687
2023-01-24 06:13:28.782062: step: 268/530, loss: 0.006469777785241604
2023-01-24 06:13:29.841071: step: 272/530, loss: 0.0013294623931869864
2023-01-24 06:13:30.905640: step: 276/530, loss: 0.02256803959608078
2023-01-24 06:13:31.978744: step: 280/530, loss: 0.05706414952874184
2023-01-24 06:13:33.072786: step: 284/530, loss: 0.05866808071732521
2023-01-24 06:13:34.152225: step: 288/530, loss: 0.006458036135882139
2023-01-24 06:13:35.204330: step: 292/530, loss: 0.009204602800309658
2023-01-24 06:13:36.265847: step: 296/530, loss: 0.0023934594355523586
2023-01-24 06:13:37.317865: step: 300/530, loss: 0.0013017728924751282
2023-01-24 06:13:38.385477: step: 304/530, loss: 0.034436073154211044
2023-01-24 06:13:39.463322: step: 308/530, loss: 0.008031786419451237
2023-01-24 06:13:40.531528: step: 312/530, loss: 0.009900466538965702
2023-01-24 06:13:41.590477: step: 316/530, loss: 0.02373206615447998
2023-01-24 06:13:42.673569: step: 320/530, loss: 0.005910777486860752
2023-01-24 06:13:43.729609: step: 324/530, loss: 0.0029667767230421305
2023-01-24 06:13:44.778811: step: 328/530, loss: 0.015294224955141544
2023-01-24 06:13:45.838441: step: 332/530, loss: 0.005187895614653826
2023-01-24 06:13:46.920735: step: 336/530, loss: 0.0024590082466602325
2023-01-24 06:13:47.976948: step: 340/530, loss: 0.003060111775994301
2023-01-24 06:13:49.038829: step: 344/530, loss: 0.014445329084992409
2023-01-24 06:13:50.102489: step: 348/530, loss: 0.011925291270017624
2023-01-24 06:13:51.154832: step: 352/530, loss: 0.004153455141931772
2023-01-24 06:13:52.204667: step: 356/530, loss: 0.014013927429914474
2023-01-24 06:13:53.263552: step: 360/530, loss: 0.003234388306736946
2023-01-24 06:13:54.327906: step: 364/530, loss: 0.01944483071565628
2023-01-24 06:13:55.403720: step: 368/530, loss: 0.005889624822884798
2023-01-24 06:13:56.456371: step: 372/530, loss: 0.0011207029456272721
2023-01-24 06:13:57.523919: step: 376/530, loss: 0.00833882112056017
2023-01-24 06:13:58.593031: step: 380/530, loss: 0.014100892469286919
2023-01-24 06:13:59.648194: step: 384/530, loss: 0.0016534379683434963
2023-01-24 06:14:00.706500: step: 388/530, loss: 0.027605213224887848
2023-01-24 06:14:01.759237: step: 392/530, loss: 0.008122763596475124
2023-01-24 06:14:02.817088: step: 396/530, loss: 0.009683061391115189
2023-01-24 06:14:03.877890: step: 400/530, loss: 0.007796324789524078
2023-01-24 06:14:04.954405: step: 404/530, loss: 0.007705798372626305
2023-01-24 06:14:06.020169: step: 408/530, loss: 0.025324424728751183
2023-01-24 06:14:07.081563: step: 412/530, loss: 0.008328518830239773
2023-01-24 06:14:08.135477: step: 416/530, loss: 0.00972798652946949
2023-01-24 06:14:09.199505: step: 420/530, loss: 0.027181345969438553
2023-01-24 06:14:10.271838: step: 424/530, loss: 0.005988021846860647
2023-01-24 06:14:11.333990: step: 428/530, loss: 0.004521721042692661
2023-01-24 06:14:12.400327: step: 432/530, loss: 0.019364219158887863
2023-01-24 06:14:13.461368: step: 436/530, loss: 0.016134416684508324
2023-01-24 06:14:14.529920: step: 440/530, loss: 0.012655304744839668
2023-01-24 06:14:15.596315: step: 444/530, loss: 0.006167694926261902
2023-01-24 06:14:16.654305: step: 448/530, loss: 0.002977717434987426
2023-01-24 06:14:17.714977: step: 452/530, loss: 0.0
2023-01-24 06:14:18.781249: step: 456/530, loss: 0.004797186236828566
2023-01-24 06:14:19.862801: step: 460/530, loss: 0.0030766879208385944
2023-01-24 06:14:20.915701: step: 464/530, loss: 0.009997088462114334
2023-01-24 06:14:21.972223: step: 468/530, loss: 0.005181621294468641
2023-01-24 06:14:23.042775: step: 472/530, loss: 0.01957887038588524
2023-01-24 06:14:24.109545: step: 476/530, loss: 0.0034870256204158068
2023-01-24 06:14:25.180842: step: 480/530, loss: 0.007872162386775017
2023-01-24 06:14:26.258080: step: 484/530, loss: 0.013051114045083523
2023-01-24 06:14:27.314500: step: 488/530, loss: 0.0017560621490702033
2023-01-24 06:14:28.388204: step: 492/530, loss: 0.006403603125363588
2023-01-24 06:14:29.449023: step: 496/530, loss: 0.013495389372110367
2023-01-24 06:14:30.523259: step: 500/530, loss: 0.006978723220527172
2023-01-24 06:14:31.563172: step: 504/530, loss: 0.0043045454658567905
2023-01-24 06:14:32.650579: step: 508/530, loss: 0.004011874552816153
2023-01-24 06:14:33.716643: step: 512/530, loss: 0.006005128845572472
2023-01-24 06:14:34.766164: step: 516/530, loss: 0.012899733148515224
2023-01-24 06:14:35.849471: step: 520/530, loss: 0.014143591746687889
2023-01-24 06:14:36.914476: step: 524/530, loss: 0.0012672512093558908
2023-01-24 06:14:37.971556: step: 528/530, loss: 0.013819774612784386
2023-01-24 06:14:39.020897: step: 532/530, loss: 0.0007218388491310179
2023-01-24 06:14:40.089681: step: 536/530, loss: 0.0054780421778559685
2023-01-24 06:14:41.136591: step: 540/530, loss: 0.00671600503847003
2023-01-24 06:14:42.211728: step: 544/530, loss: 0.03400363028049469
2023-01-24 06:14:43.276675: step: 548/530, loss: 0.0061050113290548325
2023-01-24 06:14:44.340476: step: 552/530, loss: 0.005579057149589062
2023-01-24 06:14:45.405476: step: 556/530, loss: 0.007945558056235313
2023-01-24 06:14:46.465634: step: 560/530, loss: 0.004668138921260834
2023-01-24 06:14:47.516896: step: 564/530, loss: 0.0
2023-01-24 06:14:48.577722: step: 568/530, loss: 0.004641253035515547
2023-01-24 06:14:49.626798: step: 572/530, loss: 0.026194512844085693
2023-01-24 06:14:50.693096: step: 576/530, loss: 0.001386706717312336
2023-01-24 06:14:51.767312: step: 580/530, loss: 0.001689742668531835
2023-01-24 06:14:52.838651: step: 584/530, loss: 0.009312448091804981
2023-01-24 06:14:53.901010: step: 588/530, loss: 0.019898012280464172
2023-01-24 06:14:54.975623: step: 592/530, loss: 0.005733053665608168
2023-01-24 06:14:56.034180: step: 596/530, loss: 0.022558318451046944
2023-01-24 06:14:57.106559: step: 600/530, loss: 0.00781612005084753
2023-01-24 06:14:58.175717: step: 604/530, loss: 0.004504181910306215
2023-01-24 06:14:59.218557: step: 608/530, loss: 0.0025639899540692568
2023-01-24 06:15:00.273467: step: 612/530, loss: 0.006530654616653919
2023-01-24 06:15:01.349370: step: 616/530, loss: 0.005104152951389551
2023-01-24 06:15:02.436361: step: 620/530, loss: 0.023183520883321762
2023-01-24 06:15:03.482046: step: 624/530, loss: 0.005528166890144348
2023-01-24 06:15:04.567573: step: 628/530, loss: 0.010733848437666893
2023-01-24 06:15:05.627190: step: 632/530, loss: 0.008726513013243675
2023-01-24 06:15:06.674661: step: 636/530, loss: 0.016137996688485146
2023-01-24 06:15:07.742133: step: 640/530, loss: 0.018039697781205177
2023-01-24 06:15:08.800274: step: 644/530, loss: 0.015495195053517818
2023-01-24 06:15:09.855900: step: 648/530, loss: 0.005310748238116503
2023-01-24 06:15:10.923613: step: 652/530, loss: 0.0043844678439199924
2023-01-24 06:15:11.965201: step: 656/530, loss: 0.002531700534746051
2023-01-24 06:15:13.033807: step: 660/530, loss: 0.013699260540306568
2023-01-24 06:15:14.105812: step: 664/530, loss: 0.009461941197514534
2023-01-24 06:15:15.175875: step: 668/530, loss: 0.009556401520967484
2023-01-24 06:15:16.228104: step: 672/530, loss: 0.003004271537065506
2023-01-24 06:15:17.301421: step: 676/530, loss: 0.0029664342291653156
2023-01-24 06:15:18.360057: step: 680/530, loss: 0.011705353856086731
2023-01-24 06:15:19.413912: step: 684/530, loss: 0.007695301435887814
2023-01-24 06:15:20.487611: step: 688/530, loss: 0.02052067220211029
2023-01-24 06:15:21.558642: step: 692/530, loss: 0.005934314336627722
2023-01-24 06:15:22.612120: step: 696/530, loss: 0.01766117289662361
2023-01-24 06:15:23.668433: step: 700/530, loss: 0.02639213763177395
2023-01-24 06:15:24.707330: step: 704/530, loss: 0.0032621584832668304
2023-01-24 06:15:25.766745: step: 708/530, loss: 0.004292854107916355
2023-01-24 06:15:26.835685: step: 712/530, loss: 0.00577222416177392
2023-01-24 06:15:27.897170: step: 716/530, loss: 0.004950164817273617
2023-01-24 06:15:28.962552: step: 720/530, loss: 0.0
2023-01-24 06:15:30.036729: step: 724/530, loss: 0.032266657799482346
2023-01-24 06:15:31.111224: step: 728/530, loss: 0.014548217877745628
2023-01-24 06:15:32.191223: step: 732/530, loss: 0.0009167836396954954
2023-01-24 06:15:33.256178: step: 736/530, loss: 0.017958497628569603
2023-01-24 06:15:34.315736: step: 740/530, loss: 0.04028197005391121
2023-01-24 06:15:35.388411: step: 744/530, loss: 0.003354680724442005
2023-01-24 06:15:36.470433: step: 748/530, loss: 0.0012453513918444514
2023-01-24 06:15:37.525906: step: 752/530, loss: 0.016027182340621948
2023-01-24 06:15:38.605482: step: 756/530, loss: 0.008633469231426716
2023-01-24 06:15:39.672192: step: 760/530, loss: 0.0021633554715663195
2023-01-24 06:15:40.712958: step: 764/530, loss: 0.0004952848539687693
2023-01-24 06:15:41.772673: step: 768/530, loss: 0.007033390458673239
2023-01-24 06:15:42.808651: step: 772/530, loss: 0.0005101479473523796
2023-01-24 06:15:43.881160: step: 776/530, loss: 0.03941182792186737
2023-01-24 06:15:44.951659: step: 780/530, loss: 0.003551010973751545
2023-01-24 06:15:46.023463: step: 784/530, loss: 0.05433085933327675
2023-01-24 06:15:47.069229: step: 788/530, loss: 0.011746729724109173
2023-01-24 06:15:48.146189: step: 792/530, loss: 0.006218962837010622
2023-01-24 06:15:49.197974: step: 796/530, loss: 0.010618261992931366
2023-01-24 06:15:50.257418: step: 800/530, loss: 0.010474246926605701
2023-01-24 06:15:51.316081: step: 804/530, loss: 0.007073442917317152
2023-01-24 06:15:52.392087: step: 808/530, loss: 0.006373879034072161
2023-01-24 06:15:53.439372: step: 812/530, loss: 0.013071115128695965
2023-01-24 06:15:54.498374: step: 816/530, loss: 0.015331631526350975
2023-01-24 06:15:55.537600: step: 820/530, loss: 0.013652443885803223
2023-01-24 06:15:56.606331: step: 824/530, loss: 0.014215467497706413
2023-01-24 06:15:57.679718: step: 828/530, loss: 0.0013818696606904268
2023-01-24 06:15:58.740406: step: 832/530, loss: 0.04369104653596878
2023-01-24 06:15:59.801283: step: 836/530, loss: 0.008813643828034401
2023-01-24 06:16:00.878695: step: 840/530, loss: 0.004462223034352064
2023-01-24 06:16:01.940934: step: 844/530, loss: 0.005348137114197016
2023-01-24 06:16:03.003025: step: 848/530, loss: 0.0015604892978444695
2023-01-24 06:16:04.063860: step: 852/530, loss: 0.0038257630076259375
2023-01-24 06:16:05.119973: step: 856/530, loss: 0.004403373692184687
2023-01-24 06:16:06.191499: step: 860/530, loss: 0.02417404018342495
2023-01-24 06:16:07.273574: step: 864/530, loss: 0.007416969630867243
2023-01-24 06:16:08.345459: step: 868/530, loss: 0.011917450465261936
2023-01-24 06:16:09.422873: step: 872/530, loss: 0.010866710916161537
2023-01-24 06:16:10.479952: step: 876/530, loss: 0.02389059029519558
2023-01-24 06:16:11.545963: step: 880/530, loss: 0.004505249205976725
2023-01-24 06:16:12.609328: step: 884/530, loss: 0.0030617699958384037
2023-01-24 06:16:13.668380: step: 888/530, loss: 0.026835212484002113
2023-01-24 06:16:14.718895: step: 892/530, loss: 0.008420026861131191
2023-01-24 06:16:15.772600: step: 896/530, loss: 0.0017731849802657962
2023-01-24 06:16:16.821792: step: 900/530, loss: 0.015313559211790562
2023-01-24 06:16:17.888295: step: 904/530, loss: 0.00431819399818778
2023-01-24 06:16:18.936865: step: 908/530, loss: 0.014738948084414005
2023-01-24 06:16:20.001944: step: 912/530, loss: 0.004687153734266758
2023-01-24 06:16:21.068462: step: 916/530, loss: 0.007876251824200153
2023-01-24 06:16:22.126492: step: 920/530, loss: 0.014783699065446854
2023-01-24 06:16:23.175449: step: 924/530, loss: 0.014318344183266163
2023-01-24 06:16:24.254922: step: 928/530, loss: 0.005068703088909388
2023-01-24 06:16:25.309376: step: 932/530, loss: 0.0008260238100774586
2023-01-24 06:16:26.361618: step: 936/530, loss: 0.005578598007559776
2023-01-24 06:16:27.420329: step: 940/530, loss: 0.005648624151945114
2023-01-24 06:16:28.484623: step: 944/530, loss: 0.01434145588427782
2023-01-24 06:16:29.533690: step: 948/530, loss: 0.05064533278346062
2023-01-24 06:16:30.597774: step: 952/530, loss: 0.045840006321668625
2023-01-24 06:16:31.667086: step: 956/530, loss: 0.008977357298135757
2023-01-24 06:16:32.726714: step: 960/530, loss: 0.006057981867343187
2023-01-24 06:16:33.786573: step: 964/530, loss: 0.020661020651459694
2023-01-24 06:16:34.852158: step: 968/530, loss: 0.01445910893380642
2023-01-24 06:16:35.923571: step: 972/530, loss: 0.0033617669250816107
2023-01-24 06:16:36.992256: step: 976/530, loss: 0.016689447686076164
2023-01-24 06:16:38.052915: step: 980/530, loss: 0.0020662483293563128
2023-01-24 06:16:39.138806: step: 984/530, loss: 0.015391046181321144
2023-01-24 06:16:40.187044: step: 988/530, loss: 0.008390625938773155
2023-01-24 06:16:41.229843: step: 992/530, loss: 0.012587555684149265
2023-01-24 06:16:42.289149: step: 996/530, loss: 0.003015401540324092
2023-01-24 06:16:43.342896: step: 1000/530, loss: 0.010146197862923145
2023-01-24 06:16:44.416548: step: 1004/530, loss: 0.025247910991311073
2023-01-24 06:16:45.484336: step: 1008/530, loss: 0.012767870910465717
2023-01-24 06:16:46.542062: step: 1012/530, loss: 0.0054501621052622795
2023-01-24 06:16:47.598423: step: 1016/530, loss: 0.0035274086985737085
2023-01-24 06:16:48.659680: step: 1020/530, loss: 0.007923038676381111
2023-01-24 06:16:49.727343: step: 1024/530, loss: 0.010635482147336006
2023-01-24 06:16:50.788679: step: 1028/530, loss: 0.008455418981611729
2023-01-24 06:16:51.838482: step: 1032/530, loss: 0.014862230978906155
2023-01-24 06:16:52.903330: step: 1036/530, loss: 0.0020091694314032793
2023-01-24 06:16:53.971667: step: 1040/530, loss: 0.009307769127190113
2023-01-24 06:16:55.030306: step: 1044/530, loss: 0.017452873289585114
2023-01-24 06:16:56.082377: step: 1048/530, loss: 0.012057536281645298
2023-01-24 06:16:57.141755: step: 1052/530, loss: 0.004280124790966511
2023-01-24 06:16:58.212671: step: 1056/530, loss: 0.008585563860833645
2023-01-24 06:16:59.274462: step: 1060/530, loss: 0.004593647085130215
2023-01-24 06:17:00.324191: step: 1064/530, loss: 0.009818469174206257
2023-01-24 06:17:01.407119: step: 1068/530, loss: 0.006922057364135981
2023-01-24 06:17:02.476759: step: 1072/530, loss: 0.0005158171406947076
2023-01-24 06:17:03.531082: step: 1076/530, loss: 0.008251353166997433
2023-01-24 06:17:04.599431: step: 1080/530, loss: 0.030195636674761772
2023-01-24 06:17:05.652851: step: 1084/530, loss: 0.010877580381929874
2023-01-24 06:17:06.709866: step: 1088/530, loss: 0.008826928213238716
2023-01-24 06:17:07.761711: step: 1092/530, loss: 0.005178998690098524
2023-01-24 06:17:08.822973: step: 1096/530, loss: 0.018378067761659622
2023-01-24 06:17:09.869538: step: 1100/530, loss: 0.007682143244892359
2023-01-24 06:17:10.957222: step: 1104/530, loss: 0.010484902188181877
2023-01-24 06:17:12.023283: step: 1108/530, loss: 0.005770792253315449
2023-01-24 06:17:13.093657: step: 1112/530, loss: 0.02715153805911541
2023-01-24 06:17:14.159230: step: 1116/530, loss: 0.00442056218162179
2023-01-24 06:17:15.232184: step: 1120/530, loss: 0.011488735675811768
2023-01-24 06:17:16.304655: step: 1124/530, loss: 0.007717338856309652
2023-01-24 06:17:17.366346: step: 1128/530, loss: 0.004458797629922628
2023-01-24 06:17:18.432807: step: 1132/530, loss: 0.007859314791858196
2023-01-24 06:17:19.504371: step: 1136/530, loss: 0.009439071640372276
2023-01-24 06:17:20.568137: step: 1140/530, loss: 0.0018428913317620754
2023-01-24 06:17:21.629532: step: 1144/530, loss: 0.016932310536503792
2023-01-24 06:17:22.688649: step: 1148/530, loss: 0.023681361228227615
2023-01-24 06:17:23.741312: step: 1152/530, loss: 0.005086707416921854
2023-01-24 06:17:24.794935: step: 1156/530, loss: 0.03885640203952789
2023-01-24 06:17:25.855664: step: 1160/530, loss: 0.008410545065999031
2023-01-24 06:17:26.906099: step: 1164/530, loss: 0.005495981313288212
2023-01-24 06:17:27.975351: step: 1168/530, loss: 0.0044034128077328205
2023-01-24 06:17:29.035733: step: 1172/530, loss: 0.008320998400449753
2023-01-24 06:17:30.095856: step: 1176/530, loss: 0.002126403385773301
2023-01-24 06:17:31.156399: step: 1180/530, loss: 0.008534141816198826
2023-01-24 06:17:32.219398: step: 1184/530, loss: 0.02552216500043869
2023-01-24 06:17:33.266712: step: 1188/530, loss: 0.008856154046952724
2023-01-24 06:17:34.329557: step: 1192/530, loss: 0.014329968020319939
2023-01-24 06:17:35.393141: step: 1196/530, loss: 0.0038457768969237804
2023-01-24 06:17:36.477406: step: 1200/530, loss: 0.004001577850431204
2023-01-24 06:17:37.535045: step: 1204/530, loss: 0.06063881516456604
2023-01-24 06:17:38.612939: step: 1208/530, loss: 0.001852215500548482
2023-01-24 06:17:39.657799: step: 1212/530, loss: 0.000265490758465603
2023-01-24 06:17:40.723764: step: 1216/530, loss: 0.005868783686310053
2023-01-24 06:17:41.797972: step: 1220/530, loss: 0.004784947726875544
2023-01-24 06:17:42.851788: step: 1224/530, loss: 0.0056470236741006374
2023-01-24 06:17:43.922330: step: 1228/530, loss: 0.003379441797733307
2023-01-24 06:17:44.985953: step: 1232/530, loss: 0.017595067620277405
2023-01-24 06:17:46.044626: step: 1236/530, loss: 0.0006823059520684183
2023-01-24 06:17:47.116048: step: 1240/530, loss: 0.02957821637392044
2023-01-24 06:17:48.184154: step: 1244/530, loss: 0.015399551950395107
2023-01-24 06:17:49.252565: step: 1248/530, loss: 0.03496057540178299
2023-01-24 06:17:50.311093: step: 1252/530, loss: 0.013075352646410465
2023-01-24 06:17:51.367015: step: 1256/530, loss: 0.006731557659804821
2023-01-24 06:17:52.438820: step: 1260/530, loss: 0.007542350795120001
2023-01-24 06:17:53.476796: step: 1264/530, loss: 0.0067122201435267925
2023-01-24 06:17:54.528255: step: 1268/530, loss: 0.006860585417598486
2023-01-24 06:17:55.586376: step: 1272/530, loss: 0.0018497022101655602
2023-01-24 06:17:56.644111: step: 1276/530, loss: 0.0029727229848504066
2023-01-24 06:17:57.710086: step: 1280/530, loss: 5.198213693802245e-05
2023-01-24 06:17:58.770527: step: 1284/530, loss: 0.002206278033554554
2023-01-24 06:17:59.829648: step: 1288/530, loss: 0.003800337901338935
2023-01-24 06:18:00.881934: step: 1292/530, loss: 0.0039053261280059814
2023-01-24 06:18:01.941412: step: 1296/530, loss: 0.007492515724152327
2023-01-24 06:18:03.004386: step: 1300/530, loss: 0.003310520900413394
2023-01-24 06:18:04.081986: step: 1304/530, loss: 0.04276058077812195
2023-01-24 06:18:05.139841: step: 1308/530, loss: 0.0019689034670591354
2023-01-24 06:18:06.205519: step: 1312/530, loss: 0.03961724415421486
2023-01-24 06:18:07.254688: step: 1316/530, loss: 0.026304567232728004
2023-01-24 06:18:08.327791: step: 1320/530, loss: 0.008821340277791023
2023-01-24 06:18:09.382121: step: 1324/530, loss: 0.004957039840519428
2023-01-24 06:18:10.441329: step: 1328/530, loss: 0.00439384113997221
2023-01-24 06:18:11.500422: step: 1332/530, loss: 0.006095076445490122
2023-01-24 06:18:12.560004: step: 1336/530, loss: 0.016416115686297417
2023-01-24 06:18:13.623666: step: 1340/530, loss: 0.012799358926713467
2023-01-24 06:18:14.678585: step: 1344/530, loss: 0.008660982362926006
2023-01-24 06:18:15.730373: step: 1348/530, loss: 0.01265436876565218
2023-01-24 06:18:16.793780: step: 1352/530, loss: 0.0047734021209180355
2023-01-24 06:18:17.848256: step: 1356/530, loss: 0.0072492496110498905
2023-01-24 06:18:18.905001: step: 1360/530, loss: 0.0038048243150115013
2023-01-24 06:18:19.955620: step: 1364/530, loss: 0.006910310126841068
2023-01-24 06:18:21.014901: step: 1368/530, loss: 0.0016836374998092651
2023-01-24 06:18:22.089734: step: 1372/530, loss: 0.0009233251912519336
2023-01-24 06:18:23.148623: step: 1376/530, loss: 0.004404107108712196
2023-01-24 06:18:24.206800: step: 1380/530, loss: 0.007357460912317038
2023-01-24 06:18:25.268453: step: 1384/530, loss: 0.005947975441813469
2023-01-24 06:18:26.319341: step: 1388/530, loss: 0.012318219058215618
2023-01-24 06:18:27.375035: step: 1392/530, loss: 0.012129281647503376
2023-01-24 06:18:28.430767: step: 1396/530, loss: 0.007892495952546597
2023-01-24 06:18:29.483654: step: 1400/530, loss: 0.010094028897583485
2023-01-24 06:18:30.539647: step: 1404/530, loss: 0.0077353776432573795
2023-01-24 06:18:31.593671: step: 1408/530, loss: 0.008069127798080444
2023-01-24 06:18:32.660679: step: 1412/530, loss: 0.005870666354894638
2023-01-24 06:18:33.720757: step: 1416/530, loss: 0.0031757953111082315
2023-01-24 06:18:34.803057: step: 1420/530, loss: 0.004836983047425747
2023-01-24 06:18:35.863729: step: 1424/530, loss: 0.023214153945446014
2023-01-24 06:18:36.921322: step: 1428/530, loss: 0.007668032310903072
2023-01-24 06:18:37.985342: step: 1432/530, loss: 0.0025659494567662477
2023-01-24 06:18:39.050167: step: 1436/530, loss: 0.0055738226510584354
2023-01-24 06:18:40.122365: step: 1440/530, loss: 0.012087934650480747
2023-01-24 06:18:41.183049: step: 1444/530, loss: 0.023460447788238525
2023-01-24 06:18:42.260962: step: 1448/530, loss: 0.02299894392490387
2023-01-24 06:18:43.337443: step: 1452/530, loss: 0.006333088967949152
2023-01-24 06:18:44.394185: step: 1456/530, loss: 0.017905397340655327
2023-01-24 06:18:45.439696: step: 1460/530, loss: 0.00876712892204523
2023-01-24 06:18:46.496766: step: 1464/530, loss: 0.0016122671077027917
2023-01-24 06:18:47.560705: step: 1468/530, loss: 0.007536186836659908
2023-01-24 06:18:48.627232: step: 1472/530, loss: 0.009219365194439888
2023-01-24 06:18:49.690239: step: 1476/530, loss: 0.0021594411227852106
2023-01-24 06:18:50.732698: step: 1480/530, loss: 0.0007112565799616277
2023-01-24 06:18:51.784198: step: 1484/530, loss: 0.05744333192706108
2023-01-24 06:18:52.853253: step: 1488/530, loss: 0.007184475660324097
2023-01-24 06:18:53.897879: step: 1492/530, loss: 0.005146166775375605
2023-01-24 06:18:54.967481: step: 1496/530, loss: 0.016744514927268028
2023-01-24 06:18:56.032790: step: 1500/530, loss: 0.0015380110125988722
2023-01-24 06:18:57.085793: step: 1504/530, loss: 0.01818438246846199
2023-01-24 06:18:58.140888: step: 1508/530, loss: 0.011860612779855728
2023-01-24 06:18:59.184828: step: 1512/530, loss: 0.022063730284571648
2023-01-24 06:19:00.241595: step: 1516/530, loss: 0.014161950908601284
2023-01-24 06:19:01.308037: step: 1520/530, loss: 0.006098361685872078
2023-01-24 06:19:02.387425: step: 1524/530, loss: 0.00678757019340992
2023-01-24 06:19:03.449064: step: 1528/530, loss: 0.004313177894800901
2023-01-24 06:19:04.534100: step: 1532/530, loss: 0.00238241720944643
2023-01-24 06:19:05.612801: step: 1536/530, loss: 0.04220748692750931
2023-01-24 06:19:06.668199: step: 1540/530, loss: 0.012493353337049484
2023-01-24 06:19:07.732770: step: 1544/530, loss: 0.014141512103378773
2023-01-24 06:19:08.787168: step: 1548/530, loss: 0.004078235477209091
2023-01-24 06:19:09.842826: step: 1552/530, loss: 0.010623589158058167
2023-01-24 06:19:10.905691: step: 1556/530, loss: 0.0028034208808094263
2023-01-24 06:19:11.978536: step: 1560/530, loss: 0.009858282282948494
2023-01-24 06:19:13.035680: step: 1564/530, loss: 0.06619033217430115
2023-01-24 06:19:14.091421: step: 1568/530, loss: 0.009783020243048668
2023-01-24 06:19:15.165175: step: 1572/530, loss: 0.008144106715917587
2023-01-24 06:19:16.232501: step: 1576/530, loss: 0.0033767693676054478
2023-01-24 06:19:17.294558: step: 1580/530, loss: 0.004536899738013744
2023-01-24 06:19:18.345529: step: 1584/530, loss: 0.008173903450369835
2023-01-24 06:19:19.416346: step: 1588/530, loss: 0.024307049810886383
2023-01-24 06:19:20.490056: step: 1592/530, loss: 0.007734532933682203
2023-01-24 06:19:21.546133: step: 1596/530, loss: 0.00324499374255538
2023-01-24 06:19:22.607680: step: 1600/530, loss: 0.004094294272363186
2023-01-24 06:19:23.678699: step: 1604/530, loss: 0.004557468928396702
2023-01-24 06:19:24.742073: step: 1608/530, loss: 0.006858260370790958
2023-01-24 06:19:25.800968: step: 1612/530, loss: 0.0020906715653836727
2023-01-24 06:19:26.871372: step: 1616/530, loss: 0.002209588885307312
2023-01-24 06:19:27.937807: step: 1620/530, loss: 0.0023509562015533447
2023-01-24 06:19:29.004860: step: 1624/530, loss: 0.02091505005955696
2023-01-24 06:19:30.074600: step: 1628/530, loss: 0.0033287617843598127
2023-01-24 06:19:31.140407: step: 1632/530, loss: 0.027823925018310547
2023-01-24 06:19:32.197717: step: 1636/530, loss: 0.02562517672777176
2023-01-24 06:19:33.249102: step: 1640/530, loss: 0.01110796257853508
2023-01-24 06:19:34.320306: step: 1644/530, loss: 0.0017457891954109073
2023-01-24 06:19:35.378869: step: 1648/530, loss: 0.01001239288598299
2023-01-24 06:19:36.445175: step: 1652/530, loss: 0.003693507518619299
2023-01-24 06:19:37.513281: step: 1656/530, loss: 0.008189893327653408
2023-01-24 06:19:38.585668: step: 1660/530, loss: 0.035926755517721176
2023-01-24 06:19:39.652148: step: 1664/530, loss: 0.006128427106887102
2023-01-24 06:19:40.707168: step: 1668/530, loss: 0.0005784844397567213
2023-01-24 06:19:41.772364: step: 1672/530, loss: 0.0011727223172783852
2023-01-24 06:19:42.839529: step: 1676/530, loss: 0.010610333643853664
2023-01-24 06:19:43.897978: step: 1680/530, loss: 0.007845600135624409
2023-01-24 06:19:44.970179: step: 1684/530, loss: 0.005412606988102198
2023-01-24 06:19:46.044931: step: 1688/530, loss: 0.006073933560401201
2023-01-24 06:19:47.123268: step: 1692/530, loss: 0.00578222144395113
2023-01-24 06:19:48.177507: step: 1696/530, loss: 0.004798486828804016
2023-01-24 06:19:49.249240: step: 1700/530, loss: 0.011088644154369831
2023-01-24 06:19:50.316993: step: 1704/530, loss: 0.00423861388117075
2023-01-24 06:19:51.370588: step: 1708/530, loss: 0.00791157130151987
2023-01-24 06:19:52.423641: step: 1712/530, loss: 0.008814826607704163
2023-01-24 06:19:53.481390: step: 1716/530, loss: 0.008338840678334236
2023-01-24 06:19:54.540227: step: 1720/530, loss: 0.010151728056371212
2023-01-24 06:19:55.621018: step: 1724/530, loss: 0.014455659314990044
2023-01-24 06:19:56.675732: step: 1728/530, loss: 0.019922861829400063
2023-01-24 06:19:57.719179: step: 1732/530, loss: 6.145249790279195e-05
2023-01-24 06:19:58.773260: step: 1736/530, loss: 0.013147489167749882
2023-01-24 06:19:59.819559: step: 1740/530, loss: 0.0057413214817643166
2023-01-24 06:20:00.883275: step: 1744/530, loss: 0.008017082698643208
2023-01-24 06:20:01.936602: step: 1748/530, loss: 0.0007139178924262524
2023-01-24 06:20:02.997547: step: 1752/530, loss: 0.002503437688574195
2023-01-24 06:20:04.046642: step: 1756/530, loss: 0.0018652512226253748
2023-01-24 06:20:05.125676: step: 1760/530, loss: 0.017183799296617508
2023-01-24 06:20:06.191095: step: 1764/530, loss: 0.004516208544373512
2023-01-24 06:20:07.248019: step: 1768/530, loss: 0.005358563270419836
2023-01-24 06:20:08.312839: step: 1772/530, loss: 0.013709604740142822
2023-01-24 06:20:09.383381: step: 1776/530, loss: 0.0068265474401414394
2023-01-24 06:20:10.450203: step: 1780/530, loss: 0.004847349599003792
2023-01-24 06:20:11.528607: step: 1784/530, loss: 0.003198120975866914
2023-01-24 06:20:12.598002: step: 1788/530, loss: 0.008180898614227772
2023-01-24 06:20:13.664605: step: 1792/530, loss: 0.009698394685983658
2023-01-24 06:20:14.745323: step: 1796/530, loss: 0.0013855216093361378
2023-01-24 06:20:15.795024: step: 1800/530, loss: 0.007150870282202959
2023-01-24 06:20:16.837069: step: 1804/530, loss: 0.024808460846543312
2023-01-24 06:20:17.907354: step: 1808/530, loss: 0.015996579080820084
2023-01-24 06:20:18.976256: step: 1812/530, loss: 0.0029417264740914106
2023-01-24 06:20:20.038801: step: 1816/530, loss: 0.02527133747935295
2023-01-24 06:20:21.098490: step: 1820/530, loss: 0.013187081553041935
2023-01-24 06:20:22.161482: step: 1824/530, loss: 0.003960073925554752
2023-01-24 06:20:23.232742: step: 1828/530, loss: 0.007379563990980387
2023-01-24 06:20:24.293321: step: 1832/530, loss: 0.003773181466385722
2023-01-24 06:20:25.340023: step: 1836/530, loss: 0.005938406102359295
2023-01-24 06:20:26.386066: step: 1840/530, loss: 0.00595604395493865
2023-01-24 06:20:27.432293: step: 1844/530, loss: 0.0023852570448070765
2023-01-24 06:20:28.509549: step: 1848/530, loss: 0.018418559804558754
2023-01-24 06:20:29.587965: step: 1852/530, loss: 0.04562212526798248
2023-01-24 06:20:30.656461: step: 1856/530, loss: 0.0052809021435678005
2023-01-24 06:20:31.711828: step: 1860/530, loss: 0.0029443902894854546
2023-01-24 06:20:32.809814: step: 1864/530, loss: 0.002488562371581793
2023-01-24 06:20:33.871683: step: 1868/530, loss: 0.012983922846615314
2023-01-24 06:20:34.949580: step: 1872/530, loss: 0.004306327551603317
2023-01-24 06:20:36.016102: step: 1876/530, loss: 0.030934635549783707
2023-01-24 06:20:37.088484: step: 1880/530, loss: 0.006068444810807705
2023-01-24 06:20:38.133825: step: 1884/530, loss: 0.005163372959941626
2023-01-24 06:20:39.194406: step: 1888/530, loss: 0.00963459350168705
2023-01-24 06:20:40.246011: step: 1892/530, loss: 0.10993104428052902
2023-01-24 06:20:41.306964: step: 1896/530, loss: 0.06135942041873932
2023-01-24 06:20:42.365211: step: 1900/530, loss: 0.00996585376560688
2023-01-24 06:20:43.412419: step: 1904/530, loss: 0.029266109690070152
2023-01-24 06:20:44.477692: step: 1908/530, loss: 0.021553490310907364
2023-01-24 06:20:45.533326: step: 1912/530, loss: 0.0070451395586133
2023-01-24 06:20:46.588507: step: 1916/530, loss: 0.00193988683167845
2023-01-24 06:20:47.654989: step: 1920/530, loss: 0.002844336209818721
2023-01-24 06:20:48.728423: step: 1924/530, loss: 0.007136641535907984
2023-01-24 06:20:49.812841: step: 1928/530, loss: 0.012044382281601429
2023-01-24 06:20:50.886025: step: 1932/530, loss: 0.005350827239453793
2023-01-24 06:20:51.964287: step: 1936/530, loss: 0.018192842602729797
2023-01-24 06:20:53.028055: step: 1940/530, loss: 0.041843391954898834
2023-01-24 06:20:54.117722: step: 1944/530, loss: 0.008060367777943611
2023-01-24 06:20:55.179257: step: 1948/530, loss: 0.005534703377634287
2023-01-24 06:20:56.230170: step: 1952/530, loss: 0.03554369509220123
2023-01-24 06:20:57.277803: step: 1956/530, loss: 0.024810925126075745
2023-01-24 06:20:58.341710: step: 1960/530, loss: 0.006485390942543745
2023-01-24 06:20:59.387834: step: 1964/530, loss: 0.003931231796741486
2023-01-24 06:21:00.451321: step: 1968/530, loss: 0.011343972757458687
2023-01-24 06:21:01.514835: step: 1972/530, loss: 0.02099820412695408
2023-01-24 06:21:02.608508: step: 1976/530, loss: 0.01283063180744648
2023-01-24 06:21:03.672406: step: 1980/530, loss: 0.026479102671146393
2023-01-24 06:21:04.731573: step: 1984/530, loss: 0.010106467641890049
2023-01-24 06:21:05.789312: step: 1988/530, loss: 0.009236016310751438
2023-01-24 06:21:06.845927: step: 1992/530, loss: 0.0019562605302780867
2023-01-24 06:21:07.908989: step: 1996/530, loss: 0.01028294675052166
2023-01-24 06:21:08.983027: step: 2000/530, loss: 0.004261597525328398
2023-01-24 06:21:10.052622: step: 2004/530, loss: 0.008500543422996998
2023-01-24 06:21:11.112257: step: 2008/530, loss: 0.009794317185878754
2023-01-24 06:21:12.165201: step: 2012/530, loss: 4.980359153705649e-05
2023-01-24 06:21:13.220254: step: 2016/530, loss: 0.00123411207459867
2023-01-24 06:21:14.281520: step: 2020/530, loss: 0.006054098252207041
2023-01-24 06:21:15.344076: step: 2024/530, loss: 0.008578311651945114
2023-01-24 06:21:16.404895: step: 2028/530, loss: 0.004066891502588987
2023-01-24 06:21:17.445931: step: 2032/530, loss: 0.002634467324241996
2023-01-24 06:21:18.497408: step: 2036/530, loss: 0.0039508286863565445
2023-01-24 06:21:19.544441: step: 2040/530, loss: 0.006239681039005518
2023-01-24 06:21:20.602989: step: 2044/530, loss: 0.009295599535107613
2023-01-24 06:21:21.672032: step: 2048/530, loss: 0.0029509584419429302
2023-01-24 06:21:22.737362: step: 2052/530, loss: 0.05808558315038681
2023-01-24 06:21:23.793143: step: 2056/530, loss: 0.01467252615839243
2023-01-24 06:21:24.844933: step: 2060/530, loss: 0.0001521360536571592
2023-01-24 06:21:25.897638: step: 2064/530, loss: 0.004247903823852539
2023-01-24 06:21:26.963077: step: 2068/530, loss: 0.0015431370120495558
2023-01-24 06:21:28.016553: step: 2072/530, loss: 0.024780839681625366
2023-01-24 06:21:29.070733: step: 2076/530, loss: 0.0015181649941951036
2023-01-24 06:21:30.143652: step: 2080/530, loss: 0.042880065739154816
2023-01-24 06:21:31.204528: step: 2084/530, loss: 0.02523890882730484
2023-01-24 06:21:32.312116: step: 2088/530, loss: 0.0056461491622030735
2023-01-24 06:21:33.369132: step: 2092/530, loss: 0.027111073955893517
2023-01-24 06:21:34.437329: step: 2096/530, loss: 0.01819942519068718
2023-01-24 06:21:35.502021: step: 2100/530, loss: 0.010223278775811195
2023-01-24 06:21:36.554531: step: 2104/530, loss: 0.008036882616579533
2023-01-24 06:21:37.627322: step: 2108/530, loss: 0.003609987674281001
2023-01-24 06:21:38.706936: step: 2112/530, loss: 0.0016776188276708126
2023-01-24 06:21:39.767743: step: 2116/530, loss: 0.013583243824541569
2023-01-24 06:21:40.835548: step: 2120/530, loss: 0.009458120912313461
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3855303857350801, 'r': 0.33505297280202406, 'f1': 0.35852368866328255}, 'combined': 0.26417534954136607, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3990240389582409, 'r': 0.2967633328702415, 'f1': 0.34037899648970105}, 'combined': 0.22574358316415402, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3509751773049645, 'r': 0.2811789772727273, 'f1': 0.3122239747634069}, 'combined': 0.20814931650893792, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40051916346008776, 'r': 0.2938064451679536, 'f1': 0.3389623259622299}, 'combined': 0.22121751799640266, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 06:24:10.808966: step: 4/530, loss: 0.003517056116834283
2023-01-24 06:24:11.862620: step: 8/530, loss: 0.009012565016746521
2023-01-24 06:24:12.943758: step: 12/530, loss: 0.00028308710898272693
2023-01-24 06:24:13.983414: step: 16/530, loss: 0.010990330949425697
2023-01-24 06:24:15.040856: step: 20/530, loss: 0.005436756648123264
2023-01-24 06:24:16.092976: step: 24/530, loss: 0.021109772846102715
2023-01-24 06:24:17.135879: step: 28/530, loss: 0.003288938896730542
2023-01-24 06:24:18.186321: step: 32/530, loss: 0.002336812438443303
2023-01-24 06:24:19.243851: step: 36/530, loss: 0.009832453913986683
2023-01-24 06:24:20.288032: step: 40/530, loss: 0.018044572323560715
2023-01-24 06:24:21.351842: step: 44/530, loss: 0.007544408086687326
2023-01-24 06:24:22.382158: step: 48/530, loss: 0.032098546624183655
2023-01-24 06:24:23.434121: step: 52/530, loss: 0.0007190116448327899
2023-01-24 06:24:24.493560: step: 56/530, loss: 0.003889210056513548
2023-01-24 06:24:25.560695: step: 60/530, loss: 0.01738993264734745
2023-01-24 06:24:26.620934: step: 64/530, loss: 0.0037156001199036837
2023-01-24 06:24:27.680612: step: 68/530, loss: 0.005493334028869867
2023-01-24 06:24:28.739690: step: 72/530, loss: 0.004966928623616695
2023-01-24 06:24:29.791323: step: 76/530, loss: 0.007253916468471289
2023-01-24 06:24:30.855628: step: 80/530, loss: 0.003153383731842041
2023-01-24 06:24:31.912838: step: 84/530, loss: 0.026970524340867996
2023-01-24 06:24:32.980100: step: 88/530, loss: 0.011001601815223694
2023-01-24 06:24:34.051421: step: 92/530, loss: 0.004383791703730822
2023-01-24 06:24:35.120237: step: 96/530, loss: 0.0033736806362867355
2023-01-24 06:24:36.190603: step: 100/530, loss: 0.021164245903491974
2023-01-24 06:24:37.252747: step: 104/530, loss: 0.002601813990622759
2023-01-24 06:24:38.316533: step: 108/530, loss: 0.0058281091041862965
2023-01-24 06:24:39.363684: step: 112/530, loss: 0.00868514459580183
2023-01-24 06:24:40.418352: step: 116/530, loss: 0.008433165960013866
2023-01-24 06:24:41.465537: step: 120/530, loss: 0.015177004970610142
2023-01-24 06:24:42.528424: step: 124/530, loss: 0.009002325125038624
2023-01-24 06:24:43.592648: step: 128/530, loss: 0.004818087909370661
2023-01-24 06:24:44.656453: step: 132/530, loss: 0.004497187212109566
2023-01-24 06:24:45.724150: step: 136/530, loss: 0.007404958829283714
2023-01-24 06:24:46.796845: step: 140/530, loss: 0.014937268570065498
2023-01-24 06:24:47.849828: step: 144/530, loss: 0.005882255733013153
2023-01-24 06:24:48.909267: step: 148/530, loss: 0.0081249438226223
2023-01-24 06:24:49.963419: step: 152/530, loss: 0.007643163204193115
2023-01-24 06:24:51.012826: step: 156/530, loss: 0.00040769053157418966
2023-01-24 06:24:52.066902: step: 160/530, loss: 0.00029486906714737415
2023-01-24 06:24:53.126617: step: 164/530, loss: 0.00803198292851448
2023-01-24 06:24:54.193386: step: 168/530, loss: 0.013935316354036331
2023-01-24 06:24:55.261700: step: 172/530, loss: 0.008148878812789917
2023-01-24 06:24:56.332984: step: 176/530, loss: 0.0004398757591843605
2023-01-24 06:24:57.406402: step: 180/530, loss: 0.004782336764037609
2023-01-24 06:24:58.474891: step: 184/530, loss: 0.11121557652950287
2023-01-24 06:24:59.553885: step: 188/530, loss: 0.009383085183799267
2023-01-24 06:25:00.619451: step: 192/530, loss: 0.0029649357311427593
2023-01-24 06:25:01.680009: step: 196/530, loss: 0.008337763138115406
2023-01-24 06:25:02.732341: step: 200/530, loss: 0.019029203802347183
2023-01-24 06:25:03.805230: step: 204/530, loss: 0.006065669469535351
2023-01-24 06:25:04.872485: step: 208/530, loss: 0.013527128845453262
2023-01-24 06:25:05.938617: step: 212/530, loss: 0.009829903021454811
2023-01-24 06:25:07.010165: step: 216/530, loss: 0.010944330133497715
2023-01-24 06:25:08.074235: step: 220/530, loss: 0.0014201614540070295
2023-01-24 06:25:09.157148: step: 224/530, loss: 0.010446802712976933
2023-01-24 06:25:10.233680: step: 228/530, loss: 0.004078686702996492
2023-01-24 06:25:11.285860: step: 232/530, loss: 0.009651732631027699
2023-01-24 06:25:12.321192: step: 236/530, loss: 0.0052575827576220036
2023-01-24 06:25:13.375406: step: 240/530, loss: 0.02713359333574772
2023-01-24 06:25:14.440486: step: 244/530, loss: 0.004265827126801014
2023-01-24 06:25:15.508300: step: 248/530, loss: 0.007725822273641825
2023-01-24 06:25:16.584221: step: 252/530, loss: 0.010921169072389603
2023-01-24 06:25:17.641070: step: 256/530, loss: 0.011113790795207024
2023-01-24 06:25:18.694265: step: 260/530, loss: 0.040320515632629395
2023-01-24 06:25:19.758379: step: 264/530, loss: 0.055253371596336365
2023-01-24 06:25:20.831780: step: 268/530, loss: 0.010644634254276752
2023-01-24 06:25:21.918386: step: 272/530, loss: 0.007393367122858763
2023-01-24 06:25:22.990305: step: 276/530, loss: 0.0014513102360069752
2023-01-24 06:25:24.049638: step: 280/530, loss: 0.019039904698729515
2023-01-24 06:25:25.103965: step: 284/530, loss: 0.054256342351436615
2023-01-24 06:25:26.154955: step: 288/530, loss: 0.01008105743676424
2023-01-24 06:25:27.220660: step: 292/530, loss: 0.0030834078788757324
2023-01-24 06:25:28.294019: step: 296/530, loss: 0.005493767559528351
2023-01-24 06:25:29.375694: step: 300/530, loss: 0.018559183925390244
2023-01-24 06:25:30.433473: step: 304/530, loss: 0.005808869376778603
2023-01-24 06:25:31.497080: step: 308/530, loss: 0.003038781927898526
2023-01-24 06:25:32.555327: step: 312/530, loss: 0.012369743548333645
2023-01-24 06:25:33.612689: step: 316/530, loss: 0.020224418491125107
2023-01-24 06:25:34.684649: step: 320/530, loss: 0.008415408432483673
2023-01-24 06:25:35.757124: step: 324/530, loss: 0.008500777184963226
2023-01-24 06:25:36.830853: step: 328/530, loss: 0.004227547440677881
2023-01-24 06:25:37.900206: step: 332/530, loss: 0.004737782292068005
2023-01-24 06:25:38.977417: step: 336/530, loss: 0.05515721067786217
2023-01-24 06:25:40.041211: step: 340/530, loss: 0.016539499163627625
2023-01-24 06:25:41.114431: step: 344/530, loss: 0.018101219087839127
2023-01-24 06:25:42.187528: step: 348/530, loss: 0.051545072346925735
2023-01-24 06:25:43.247931: step: 352/530, loss: 0.00850539281964302
2023-01-24 06:25:44.331891: step: 356/530, loss: 0.002685853745788336
2023-01-24 06:25:45.401054: step: 360/530, loss: 0.029639797285199165
2023-01-24 06:25:46.455373: step: 364/530, loss: 0.03649447113275528
2023-01-24 06:25:47.523239: step: 368/530, loss: 0.019114157184958458
2023-01-24 06:25:48.597867: step: 372/530, loss: 0.005436555948108435
2023-01-24 06:25:49.670970: step: 376/530, loss: 0.0022181563545018435
2023-01-24 06:25:50.729393: step: 380/530, loss: 0.015655457973480225
2023-01-24 06:25:51.792729: step: 384/530, loss: 0.0010982543462887406
2023-01-24 06:25:52.865667: step: 388/530, loss: 0.002683042548596859
2023-01-24 06:25:53.931850: step: 392/530, loss: 0.03194204717874527
2023-01-24 06:25:55.000359: step: 396/530, loss: 0.01111543644219637
2023-01-24 06:25:56.062098: step: 400/530, loss: 0.024194257333874702
2023-01-24 06:25:57.133456: step: 404/530, loss: 0.0008462219266220927
2023-01-24 06:25:58.199905: step: 408/530, loss: 0.014340794645249844
2023-01-24 06:25:59.247946: step: 412/530, loss: 0.006390500348061323
2023-01-24 06:26:00.311368: step: 416/530, loss: 0.0028179651126265526
2023-01-24 06:26:01.357919: step: 420/530, loss: 0.008723265491425991
2023-01-24 06:26:02.426063: step: 424/530, loss: 0.028755221515893936
2023-01-24 06:26:03.490423: step: 428/530, loss: 0.007391304709017277
2023-01-24 06:26:04.543749: step: 432/530, loss: 0.004387681372463703
2023-01-24 06:26:05.609145: step: 436/530, loss: 0.005039957817643881
2023-01-24 06:26:06.671146: step: 440/530, loss: 0.002497607609257102
2023-01-24 06:26:07.730934: step: 444/530, loss: 0.005696254316717386
2023-01-24 06:26:08.796988: step: 448/530, loss: 0.03760283812880516
2023-01-24 06:26:09.865294: step: 452/530, loss: 0.02391895279288292
2023-01-24 06:26:10.921009: step: 456/530, loss: 0.037628401070833206
2023-01-24 06:26:11.981272: step: 460/530, loss: 0.0896049216389656
2023-01-24 06:26:13.060764: step: 464/530, loss: 0.005308789666742086
2023-01-24 06:26:14.122501: step: 468/530, loss: 0.006673626601696014
2023-01-24 06:26:15.173287: step: 472/530, loss: 0.002351192058995366
2023-01-24 06:26:16.243423: step: 476/530, loss: 0.02134312130510807
2023-01-24 06:26:17.302519: step: 480/530, loss: 0.0056860544718801975
2023-01-24 06:26:18.366485: step: 484/530, loss: 0.008009308949112892
2023-01-24 06:26:19.435597: step: 488/530, loss: 0.009529204107820988
2023-01-24 06:26:20.500631: step: 492/530, loss: 0.012569320388138294
2023-01-24 06:26:21.565463: step: 496/530, loss: 0.011845407076179981
2023-01-24 06:26:22.642406: step: 500/530, loss: 0.002635406795889139
2023-01-24 06:26:23.695415: step: 504/530, loss: 0.005635532084852457
2023-01-24 06:26:24.758098: step: 508/530, loss: 0.0004423644859343767
2023-01-24 06:26:25.821131: step: 512/530, loss: 0.014786526560783386
2023-01-24 06:26:26.890373: step: 516/530, loss: 0.0066650379449129105
2023-01-24 06:26:27.948669: step: 520/530, loss: 0.0490175299346447
2023-01-24 06:26:29.013642: step: 524/530, loss: 0.0055488767102360725
2023-01-24 06:26:30.081603: step: 528/530, loss: 0.011376290582120419
2023-01-24 06:26:31.139639: step: 532/530, loss: 0.010135767981410027
2023-01-24 06:26:32.194893: step: 536/530, loss: 0.032854098826646805
2023-01-24 06:26:33.243075: step: 540/530, loss: 0.005537951830774546
2023-01-24 06:26:34.317970: step: 544/530, loss: 0.0034554556477814913
2023-01-24 06:26:35.392653: step: 548/530, loss: 0.015101026743650436
2023-01-24 06:26:36.453740: step: 552/530, loss: 0.0055346256121993065
2023-01-24 06:26:37.518715: step: 556/530, loss: 0.003905024379491806
2023-01-24 06:26:38.574163: step: 560/530, loss: 0.010141531005501747
2023-01-24 06:26:39.628140: step: 564/530, loss: 0.007455743383616209
2023-01-24 06:26:40.688954: step: 568/530, loss: 0.0037887238431721926
2023-01-24 06:26:41.761917: step: 572/530, loss: 0.002884421031922102
2023-01-24 06:26:42.829170: step: 576/530, loss: 0.004631417337805033
2023-01-24 06:26:43.882784: step: 580/530, loss: 0.0054386756382882595
2023-01-24 06:26:44.971419: step: 584/530, loss: 0.018852079287171364
2023-01-24 06:26:46.017742: step: 588/530, loss: 0.004346480593085289
2023-01-24 06:26:47.074106: step: 592/530, loss: 0.0036986065097153187
2023-01-24 06:26:48.122464: step: 596/530, loss: 0.008397475816309452
2023-01-24 06:26:49.179119: step: 600/530, loss: 0.0032148140016943216
2023-01-24 06:26:50.234900: step: 604/530, loss: 0.0035250037908554077
2023-01-24 06:26:51.293887: step: 608/530, loss: 0.009142866358160973
2023-01-24 06:26:52.345840: step: 612/530, loss: 0.005431356839835644
2023-01-24 06:26:53.402197: step: 616/530, loss: 0.018363559618592262
2023-01-24 06:26:54.473608: step: 620/530, loss: 0.0006756098591722548
2023-01-24 06:26:55.535687: step: 624/530, loss: 0.003582867095246911
2023-01-24 06:26:56.589017: step: 628/530, loss: 0.001773180440068245
2023-01-24 06:26:57.641654: step: 632/530, loss: 0.007147999480366707
2023-01-24 06:26:58.705762: step: 636/530, loss: 0.0022949762642383575
2023-01-24 06:26:59.757214: step: 640/530, loss: 0.03320471942424774
2023-01-24 06:27:00.811297: step: 644/530, loss: 0.00910720881074667
2023-01-24 06:27:01.879665: step: 648/530, loss: 0.007070349995046854
2023-01-24 06:27:02.934129: step: 652/530, loss: 0.005009678658097982
2023-01-24 06:27:03.986003: step: 656/530, loss: 0.0004368265508674085
2023-01-24 06:27:05.050387: step: 660/530, loss: 0.0630410760641098
2023-01-24 06:27:06.104077: step: 664/530, loss: 0.006882937625050545
2023-01-24 06:27:07.165464: step: 668/530, loss: 0.004937580320984125
2023-01-24 06:27:08.206058: step: 672/530, loss: 0.0011543085565790534
2023-01-24 06:27:09.253643: step: 676/530, loss: 0.006621150765568018
2023-01-24 06:27:10.310759: step: 680/530, loss: 0.007325129117816687
2023-01-24 06:27:11.365397: step: 684/530, loss: 0.0074560800567269325
2023-01-24 06:27:12.439100: step: 688/530, loss: 0.050486091524362564
2023-01-24 06:27:13.505837: step: 692/530, loss: 0.004529129713773727
2023-01-24 06:27:14.567340: step: 696/530, loss: 0.007007180713117123
2023-01-24 06:27:15.614099: step: 700/530, loss: 0.009266283363103867
2023-01-24 06:27:16.681551: step: 704/530, loss: 0.02546180598437786
2023-01-24 06:27:17.741001: step: 708/530, loss: 0.010309465229511261
2023-01-24 06:27:18.823565: step: 712/530, loss: 0.0032385371159762144
2023-01-24 06:27:19.883002: step: 716/530, loss: 0.019539283588528633
2023-01-24 06:27:20.957204: step: 720/530, loss: 0.02405500039458275
2023-01-24 06:27:22.004684: step: 724/530, loss: 3.7575437090708874e-06
2023-01-24 06:27:23.054276: step: 728/530, loss: 0.0005081840790808201
2023-01-24 06:27:24.108135: step: 732/530, loss: 0.007044833153486252
2023-01-24 06:27:25.170953: step: 736/530, loss: 0.0045994967222213745
2023-01-24 06:27:26.267734: step: 740/530, loss: 0.011359893716871738
2023-01-24 06:27:27.325393: step: 744/530, loss: 0.0037036314606666565
2023-01-24 06:27:28.373302: step: 748/530, loss: 0.002331929048523307
2023-01-24 06:27:29.425487: step: 752/530, loss: 0.0009123159688897431
2023-01-24 06:27:30.477118: step: 756/530, loss: 0.002318986691534519
2023-01-24 06:27:31.531515: step: 760/530, loss: 0.036909136921167374
2023-01-24 06:27:32.606626: step: 764/530, loss: 0.011546503752470016
2023-01-24 06:27:33.653405: step: 768/530, loss: 0.00661019841209054
2023-01-24 06:27:34.708382: step: 772/530, loss: 0.005355306901037693
2023-01-24 06:27:35.785087: step: 776/530, loss: 0.004799014423042536
2023-01-24 06:27:36.854505: step: 780/530, loss: 0.0015085495542734861
2023-01-24 06:27:37.904429: step: 784/530, loss: 0.009989234618842602
2023-01-24 06:27:38.959613: step: 788/530, loss: 0.0036725574173033237
2023-01-24 06:27:40.027528: step: 792/530, loss: 0.005716994404792786
2023-01-24 06:27:41.093306: step: 796/530, loss: 0.001757194520905614
2023-01-24 06:27:42.143280: step: 800/530, loss: 0.015330669470131397
2023-01-24 06:27:43.203614: step: 804/530, loss: 0.002205889904871583
2023-01-24 06:27:44.264705: step: 808/530, loss: 0.0068893954157829285
2023-01-24 06:27:45.319451: step: 812/530, loss: 0.0077874320559203625
2023-01-24 06:27:46.399429: step: 816/530, loss: 0.016964871436357498
2023-01-24 06:27:47.450626: step: 820/530, loss: 0.004929469898343086
2023-01-24 06:27:48.522682: step: 824/530, loss: 0.004375232849270105
2023-01-24 06:27:49.575149: step: 828/530, loss: 0.011272136121988297
2023-01-24 06:27:50.635298: step: 832/530, loss: 0.01298808678984642
2023-01-24 06:27:51.697100: step: 836/530, loss: 0.032257985323667526
2023-01-24 06:27:52.742879: step: 840/530, loss: 0.013422680087387562
2023-01-24 06:27:53.803663: step: 844/530, loss: 0.005984754767268896
2023-01-24 06:27:54.856005: step: 848/530, loss: 0.004423861857503653
2023-01-24 06:27:55.919464: step: 852/530, loss: 0.003647006116807461
2023-01-24 06:27:56.978978: step: 856/530, loss: 0.0011500094551593065
2023-01-24 06:27:58.059017: step: 860/530, loss: 0.003454555757343769
2023-01-24 06:27:59.104352: step: 864/530, loss: 0.004963899031281471
2023-01-24 06:28:00.174516: step: 868/530, loss: 0.013316702097654343
2023-01-24 06:28:01.223559: step: 872/530, loss: 0.019177105277776718
2023-01-24 06:28:02.320244: step: 876/530, loss: 0.0023701488971710205
2023-01-24 06:28:03.377405: step: 880/530, loss: 0.0029713427647948265
2023-01-24 06:28:04.436132: step: 884/530, loss: 0.008309753611683846
2023-01-24 06:28:05.502536: step: 888/530, loss: 0.016241425648331642
2023-01-24 06:28:06.561237: step: 892/530, loss: 0.007308730389922857
2023-01-24 06:28:07.623466: step: 896/530, loss: 0.04044658690690994
2023-01-24 06:28:08.696028: step: 900/530, loss: 0.011886515654623508
2023-01-24 06:28:09.749628: step: 904/530, loss: 0.006381236016750336
2023-01-24 06:28:10.820635: step: 908/530, loss: 0.004408490844070911
2023-01-24 06:28:11.870979: step: 912/530, loss: 0.004806546028703451
2023-01-24 06:28:12.926998: step: 916/530, loss: 0.005159028805792332
2023-01-24 06:28:14.000057: step: 920/530, loss: 0.005976864602416754
2023-01-24 06:28:15.083098: step: 924/530, loss: 0.005223964340984821
2023-01-24 06:28:16.134853: step: 928/530, loss: 0.005659719929099083
2023-01-24 06:28:17.202890: step: 932/530, loss: 0.013088217005133629
2023-01-24 06:28:18.269332: step: 936/530, loss: 0.0021140507888048887
2023-01-24 06:28:19.324562: step: 940/530, loss: 0.00842966977506876
2023-01-24 06:28:20.380713: step: 944/530, loss: 0.00021945053595118225
2023-01-24 06:28:21.437523: step: 948/530, loss: 0.007516163866966963
2023-01-24 06:28:22.499572: step: 952/530, loss: 0.022173110395669937
2023-01-24 06:28:23.595717: step: 956/530, loss: 0.0868389680981636
2023-01-24 06:28:24.652656: step: 960/530, loss: 0.0025863992050290108
2023-01-24 06:28:25.723138: step: 964/530, loss: 0.005571173969656229
2023-01-24 06:28:26.779984: step: 968/530, loss: 0.006155728362500668
2023-01-24 06:28:27.822127: step: 972/530, loss: 0.004272026475518942
2023-01-24 06:28:28.889033: step: 976/530, loss: 0.002964085666462779
2023-01-24 06:28:29.969635: step: 980/530, loss: 0.0028430030215531588
2023-01-24 06:28:31.025699: step: 984/530, loss: 0.008368617855012417
2023-01-24 06:28:32.103921: step: 988/530, loss: 0.03369031101465225
2023-01-24 06:28:33.157778: step: 992/530, loss: 0.01347421109676361
2023-01-24 06:28:34.219436: step: 996/530, loss: 0.004713854752480984
2023-01-24 06:28:35.288076: step: 1000/530, loss: 0.018790025264024734
2023-01-24 06:28:36.353546: step: 1004/530, loss: 0.021689891815185547
2023-01-24 06:28:37.420488: step: 1008/530, loss: 0.0023492074105888605
2023-01-24 06:28:38.473916: step: 1012/530, loss: 0.01468432042747736
2023-01-24 06:28:39.526363: step: 1016/530, loss: 0.00424958998337388
2023-01-24 06:28:40.582575: step: 1020/530, loss: 0.01432398147881031
2023-01-24 06:28:41.632567: step: 1024/530, loss: 0.0032544690184295177
2023-01-24 06:28:42.706306: step: 1028/530, loss: 0.011772519908845425
2023-01-24 06:28:43.763063: step: 1032/530, loss: 0.005709446035325527
2023-01-24 06:28:44.813508: step: 1036/530, loss: 0.009214820340275764
2023-01-24 06:28:45.866619: step: 1040/530, loss: 0.005603351630270481
2023-01-24 06:28:46.935510: step: 1044/530, loss: 0.029960831627249718
2023-01-24 06:28:48.018645: step: 1048/530, loss: 0.007764473557472229
2023-01-24 06:28:49.075914: step: 1052/530, loss: 0.007633398286998272
2023-01-24 06:28:50.134482: step: 1056/530, loss: 0.002183147706091404
2023-01-24 06:28:51.188397: step: 1060/530, loss: 0.006642820313572884
2023-01-24 06:28:52.258520: step: 1064/530, loss: 0.0033487691543996334
2023-01-24 06:28:53.328687: step: 1068/530, loss: 0.0028577228076756
2023-01-24 06:28:54.398615: step: 1072/530, loss: 0.0036148016806691885
2023-01-24 06:28:55.458697: step: 1076/530, loss: 0.006393277086317539
2023-01-24 06:28:56.520293: step: 1080/530, loss: 0.004756600596010685
2023-01-24 06:28:57.587821: step: 1084/530, loss: 0.0045590270310640335
2023-01-24 06:28:58.638862: step: 1088/530, loss: 0.03936564549803734
2023-01-24 06:28:59.687170: step: 1092/530, loss: 0.00040857470594346523
2023-01-24 06:29:00.726901: step: 1096/530, loss: 0.017735375091433525
2023-01-24 06:29:01.794069: step: 1100/530, loss: 0.009191764518618584
2023-01-24 06:29:02.890307: step: 1104/530, loss: 0.01862039789557457
2023-01-24 06:29:03.950565: step: 1108/530, loss: 0.008660403080284595
2023-01-24 06:29:05.004725: step: 1112/530, loss: 0.0008322783978655934
2023-01-24 06:29:06.061825: step: 1116/530, loss: 0.009353626519441605
2023-01-24 06:29:07.147255: step: 1120/530, loss: 0.005847702268511057
2023-01-24 06:29:08.208527: step: 1124/530, loss: 0.03231755271553993
2023-01-24 06:29:09.283420: step: 1128/530, loss: 0.03832541033625603
2023-01-24 06:29:10.332157: step: 1132/530, loss: 0.0021001286804676056
2023-01-24 06:29:11.376901: step: 1136/530, loss: 0.033331554383039474
2023-01-24 06:29:12.460163: step: 1140/530, loss: 0.022505968809127808
2023-01-24 06:29:13.529491: step: 1144/530, loss: 0.009933141991496086
2023-01-24 06:29:14.576949: step: 1148/530, loss: 0.00809610728174448
2023-01-24 06:29:15.629708: step: 1152/530, loss: 0.059753648936748505
2023-01-24 06:29:16.684259: step: 1156/530, loss: 0.030689775943756104
2023-01-24 06:29:17.745802: step: 1160/530, loss: 0.012817854061722755
2023-01-24 06:29:18.805751: step: 1164/530, loss: 0.016397599130868912
2023-01-24 06:29:19.875935: step: 1168/530, loss: 0.02847987972199917
2023-01-24 06:29:20.926512: step: 1172/530, loss: 0.012905584648251534
2023-01-24 06:29:21.987909: step: 1176/530, loss: 0.004862555302679539
2023-01-24 06:29:23.047793: step: 1180/530, loss: 0.008750325068831444
2023-01-24 06:29:24.090534: step: 1184/530, loss: 0.043315429240465164
2023-01-24 06:29:25.140443: step: 1188/530, loss: 0.01485416479408741
2023-01-24 06:29:26.194700: step: 1192/530, loss: 0.0025665347930043936
2023-01-24 06:29:27.256286: step: 1196/530, loss: 0.002824236173182726
2023-01-24 06:29:28.305623: step: 1200/530, loss: 0.030294490978121758
2023-01-24 06:29:29.382811: step: 1204/530, loss: 0.004747746046632528
2023-01-24 06:29:30.444835: step: 1208/530, loss: 0.011875168420374393
2023-01-24 06:29:31.510587: step: 1212/530, loss: 0.004423817154020071
2023-01-24 06:29:32.563806: step: 1216/530, loss: 0.008163546212017536
2023-01-24 06:29:33.623851: step: 1220/530, loss: 0.009794938378036022
2023-01-24 06:29:34.672160: step: 1224/530, loss: 0.015955302864313126
2023-01-24 06:29:35.742411: step: 1228/530, loss: 0.008795671164989471
2023-01-24 06:29:36.791787: step: 1232/530, loss: 0.07126534730195999
2023-01-24 06:29:37.859350: step: 1236/530, loss: 0.04979224130511284
2023-01-24 06:29:38.926103: step: 1240/530, loss: 0.003912405576556921
2023-01-24 06:29:39.976271: step: 1244/530, loss: 0.0049399458803236485
2023-01-24 06:29:41.036418: step: 1248/530, loss: 0.006058188620954752
2023-01-24 06:29:42.100501: step: 1252/530, loss: 0.0007667996105737984
2023-01-24 06:29:43.159499: step: 1256/530, loss: 0.0057192277163267136
2023-01-24 06:29:44.215847: step: 1260/530, loss: 0.00622472632676363
2023-01-24 06:29:45.270943: step: 1264/530, loss: 0.002794084371998906
2023-01-24 06:29:46.326720: step: 1268/530, loss: 0.005455076228827238
2023-01-24 06:29:47.376694: step: 1272/530, loss: 0.006627157796174288
2023-01-24 06:29:48.431605: step: 1276/530, loss: 0.03485396131873131
2023-01-24 06:29:49.486547: step: 1280/530, loss: 0.03075513243675232
2023-01-24 06:29:50.541316: step: 1284/530, loss: 0.0027068809140473604
2023-01-24 06:29:51.591369: step: 1288/530, loss: 0.007979771122336388
2023-01-24 06:29:52.653066: step: 1292/530, loss: 0.004088948480784893
2023-01-24 06:29:53.711767: step: 1296/530, loss: 0.008268347010016441
2023-01-24 06:29:54.772563: step: 1300/530, loss: 0.008342672139406204
2023-01-24 06:29:55.838833: step: 1304/530, loss: 0.004666406661272049
2023-01-24 06:29:56.891683: step: 1308/530, loss: 0.009865745902061462
2023-01-24 06:29:57.949315: step: 1312/530, loss: 0.0034520637709647417
2023-01-24 06:29:59.038825: step: 1316/530, loss: 0.024848198518157005
2023-01-24 06:30:00.099835: step: 1320/530, loss: 0.0052132029086351395
2023-01-24 06:30:01.151959: step: 1324/530, loss: 0.06313329935073853
2023-01-24 06:30:02.208436: step: 1328/530, loss: 0.0016254446236416698
2023-01-24 06:30:03.265032: step: 1332/530, loss: 0.0056574163027107716
2023-01-24 06:30:04.329025: step: 1336/530, loss: 0.005067254416644573
2023-01-24 06:30:05.385032: step: 1340/530, loss: 0.00024287166888825595
2023-01-24 06:30:06.434400: step: 1344/530, loss: 0.03414236754179001
2023-01-24 06:30:07.503310: step: 1348/530, loss: 0.008662113919854164
2023-01-24 06:30:08.572319: step: 1352/530, loss: 0.0074186003766953945
2023-01-24 06:30:09.627634: step: 1356/530, loss: 0.0050832428969442844
2023-01-24 06:30:10.704028: step: 1360/530, loss: 0.01904802955687046
2023-01-24 06:30:11.758196: step: 1364/530, loss: 0.0051752435974776745
2023-01-24 06:30:12.816051: step: 1368/530, loss: 0.010146742686629295
2023-01-24 06:30:13.877280: step: 1372/530, loss: 0.06443759799003601
2023-01-24 06:30:14.933913: step: 1376/530, loss: 0.007404040079563856
2023-01-24 06:30:16.015256: step: 1380/530, loss: 0.03164595365524292
2023-01-24 06:30:17.069574: step: 1384/530, loss: 0.0308536309748888
2023-01-24 06:30:18.122550: step: 1388/530, loss: 0.0007203335408121347
2023-01-24 06:30:19.180321: step: 1392/530, loss: 0.0030600244645029306
2023-01-24 06:30:20.226523: step: 1396/530, loss: 0.00735328858718276
2023-01-24 06:30:21.292144: step: 1400/530, loss: 0.03782516345381737
2023-01-24 06:30:22.351501: step: 1404/530, loss: 0.005687171593308449
2023-01-24 06:30:23.414246: step: 1408/530, loss: 0.007961194030940533
2023-01-24 06:30:24.472447: step: 1412/530, loss: 0.008044837974011898
2023-01-24 06:30:25.525592: step: 1416/530, loss: 0.010571010410785675
2023-01-24 06:30:26.587539: step: 1420/530, loss: 0.011312278918921947
2023-01-24 06:30:27.667020: step: 1424/530, loss: 0.01273477915674448
2023-01-24 06:30:28.720674: step: 1428/530, loss: 0.008418474346399307
2023-01-24 06:30:29.779628: step: 1432/530, loss: 0.00903947651386261
2023-01-24 06:30:30.838311: step: 1436/530, loss: 0.006529093720018864
2023-01-24 06:30:31.910573: step: 1440/530, loss: 0.03223242610692978
2023-01-24 06:30:32.957053: step: 1444/530, loss: 0.01048089936375618
2023-01-24 06:30:34.029451: step: 1448/530, loss: 0.013730064034461975
2023-01-24 06:30:35.094571: step: 1452/530, loss: 0.03295912966132164
2023-01-24 06:30:36.155837: step: 1456/530, loss: 0.006297646556049585
2023-01-24 06:30:37.218092: step: 1460/530, loss: 0.014950539916753769
2023-01-24 06:30:38.277812: step: 1464/530, loss: 0.002351527102291584
2023-01-24 06:30:39.324882: step: 1468/530, loss: 0.009170595556497574
2023-01-24 06:30:40.389868: step: 1472/530, loss: 0.004258336499333382
2023-01-24 06:30:41.464500: step: 1476/530, loss: 0.015216046944260597
2023-01-24 06:30:42.500095: step: 1480/530, loss: 0.0055315312929451466
2023-01-24 06:30:43.556230: step: 1484/530, loss: 0.0017328830435872078
2023-01-24 06:30:44.610072: step: 1488/530, loss: 0.004406601656228304
2023-01-24 06:30:45.667931: step: 1492/530, loss: 0.004037209786474705
2023-01-24 06:30:46.728393: step: 1496/530, loss: 0.006016279570758343
2023-01-24 06:30:47.775705: step: 1500/530, loss: 0.002808723133057356
2023-01-24 06:30:48.849167: step: 1504/530, loss: 0.02563599869608879
2023-01-24 06:30:49.901383: step: 1508/530, loss: 0.011710327118635178
2023-01-24 06:30:50.959049: step: 1512/530, loss: 0.005440083798021078
2023-01-24 06:30:52.025917: step: 1516/530, loss: 0.08998735249042511
2023-01-24 06:30:53.069212: step: 1520/530, loss: 0.006538390181958675
2023-01-24 06:30:54.116461: step: 1524/530, loss: 0.002666729735210538
2023-01-24 06:30:55.170400: step: 1528/530, loss: 0.003731057047843933
2023-01-24 06:30:56.229790: step: 1532/530, loss: 0.0054165152832865715
2023-01-24 06:30:57.284885: step: 1536/530, loss: 0.010040711611509323
2023-01-24 06:30:58.362956: step: 1540/530, loss: 0.02920636162161827
2023-01-24 06:30:59.417523: step: 1544/530, loss: 0.013925306499004364
2023-01-24 06:31:00.475422: step: 1548/530, loss: 0.013019642792642117
2023-01-24 06:31:01.526592: step: 1552/530, loss: 0.015582763589918613
2023-01-24 06:31:02.581582: step: 1556/530, loss: 0.011520355008542538
2023-01-24 06:31:03.640346: step: 1560/530, loss: 0.0043084206990897655
2023-01-24 06:31:04.700924: step: 1564/530, loss: 0.00961390696465969
2023-01-24 06:31:05.752677: step: 1568/530, loss: 0.0016335458494722843
2023-01-24 06:31:06.807828: step: 1572/530, loss: 0.003929502330720425
2023-01-24 06:31:07.877454: step: 1576/530, loss: 0.001233261777088046
2023-01-24 06:31:08.928698: step: 1580/530, loss: 0.012667790055274963
2023-01-24 06:31:09.989443: step: 1584/530, loss: 0.0026889867149293423
2023-01-24 06:31:11.032647: step: 1588/530, loss: 0.009532587602734566
2023-01-24 06:31:12.078644: step: 1592/530, loss: 0.0021155548747628927
2023-01-24 06:31:13.135957: step: 1596/530, loss: 0.007182436529546976
2023-01-24 06:31:14.193071: step: 1600/530, loss: 0.03723154589533806
2023-01-24 06:31:15.250814: step: 1604/530, loss: 0.0076673575676977634
2023-01-24 06:31:16.317561: step: 1608/530, loss: 0.015933748334646225
2023-01-24 06:31:17.386711: step: 1612/530, loss: 0.019861871376633644
2023-01-24 06:31:18.465655: step: 1616/530, loss: 0.006957708392292261
2023-01-24 06:31:19.518647: step: 1620/530, loss: 0.0017674921546131372
2023-01-24 06:31:20.578561: step: 1624/530, loss: 0.003526045475155115
2023-01-24 06:31:21.658756: step: 1628/530, loss: 0.012933246791362762
2023-01-24 06:31:22.716472: step: 1632/530, loss: 0.012411696836352348
2023-01-24 06:31:23.782271: step: 1636/530, loss: 0.014215086586773396
2023-01-24 06:31:24.856649: step: 1640/530, loss: 0.0036534839309751987
2023-01-24 06:31:25.911514: step: 1644/530, loss: 0.00822637602686882
2023-01-24 06:31:26.970076: step: 1648/530, loss: 0.0028788570780307055
2023-01-24 06:31:28.021687: step: 1652/530, loss: 0.008850933983922005
2023-01-24 06:31:29.086697: step: 1656/530, loss: 0.012631809338927269
2023-01-24 06:31:30.141917: step: 1660/530, loss: 0.008418691344559193
2023-01-24 06:31:31.192677: step: 1664/530, loss: 0.014639188535511494
2023-01-24 06:31:32.258352: step: 1668/530, loss: 0.0032683995086699724
2023-01-24 06:31:33.317140: step: 1672/530, loss: 0.004973691888153553
2023-01-24 06:31:34.379530: step: 1676/530, loss: 0.00462028244510293
2023-01-24 06:31:35.436335: step: 1680/530, loss: 0.07903909683227539
2023-01-24 06:31:36.487750: step: 1684/530, loss: 0.015505899675190449
2023-01-24 06:31:37.561560: step: 1688/530, loss: 0.019500674679875374
2023-01-24 06:31:38.611650: step: 1692/530, loss: 0.016083436086773872
2023-01-24 06:31:39.680866: step: 1696/530, loss: 0.007053493056446314
2023-01-24 06:31:40.736411: step: 1700/530, loss: 0.004030758515000343
2023-01-24 06:31:41.784830: step: 1704/530, loss: 0.006347734481096268
2023-01-24 06:31:42.858319: step: 1708/530, loss: 0.03831996023654938
2023-01-24 06:31:43.915475: step: 1712/530, loss: 0.012755157425999641
2023-01-24 06:31:44.964360: step: 1716/530, loss: 0.006069265305995941
2023-01-24 06:31:46.023626: step: 1720/530, loss: 0.008358371444046497
2023-01-24 06:31:47.084426: step: 1724/530, loss: 0.010149398818612099
2023-01-24 06:31:48.154949: step: 1728/530, loss: 0.0172977764159441
2023-01-24 06:31:49.202682: step: 1732/530, loss: 0.03618042171001434
2023-01-24 06:31:50.266234: step: 1736/530, loss: 0.007877811789512634
2023-01-24 06:31:51.321926: step: 1740/530, loss: 0.005684498697519302
2023-01-24 06:31:52.388698: step: 1744/530, loss: 0.0075081633403897285
2023-01-24 06:31:53.443012: step: 1748/530, loss: 0.0067033008672297
2023-01-24 06:31:54.491892: step: 1752/530, loss: 0.005355026572942734
2023-01-24 06:31:55.539675: step: 1756/530, loss: 0.0036875305231660604
2023-01-24 06:31:56.637826: step: 1760/530, loss: 0.007830041460692883
2023-01-24 06:31:57.703827: step: 1764/530, loss: 0.009110311977565289
2023-01-24 06:31:58.746967: step: 1768/530, loss: 0.007872947491705418
2023-01-24 06:31:59.848691: step: 1772/530, loss: 0.015335457399487495
2023-01-24 06:32:00.919028: step: 1776/530, loss: 0.05458350107073784
2023-01-24 06:32:01.971442: step: 1780/530, loss: 0.004223008640110493
2023-01-24 06:32:03.064445: step: 1784/530, loss: 0.005835706368088722
2023-01-24 06:32:04.121774: step: 1788/530, loss: 0.003655042964965105
2023-01-24 06:32:05.191125: step: 1792/530, loss: 0.016403520479798317
2023-01-24 06:32:06.254832: step: 1796/530, loss: 0.007521182764321566
2023-01-24 06:32:07.308449: step: 1800/530, loss: 0.016147593036293983
2023-01-24 06:32:08.370668: step: 1804/530, loss: 0.001990591175854206
2023-01-24 06:32:09.425126: step: 1808/530, loss: 0.004318589810281992
2023-01-24 06:32:10.475546: step: 1812/530, loss: 0.011621844954788685
2023-01-24 06:32:11.532790: step: 1816/530, loss: 0.0073912786319851875
2023-01-24 06:32:12.590786: step: 1820/530, loss: 0.004409641958773136
2023-01-24 06:32:13.662568: step: 1824/530, loss: 0.009205885231494904
2023-01-24 06:32:14.712732: step: 1828/530, loss: 0.006221571005880833
2023-01-24 06:32:15.764438: step: 1832/530, loss: 0.007805989123880863
2023-01-24 06:32:16.819542: step: 1836/530, loss: 0.006754001136869192
2023-01-24 06:32:17.869963: step: 1840/530, loss: 0.015085451304912567
2023-01-24 06:32:18.940633: step: 1844/530, loss: 0.019204866141080856
2023-01-24 06:32:20.004061: step: 1848/530, loss: 0.008780100382864475
2023-01-24 06:32:21.053052: step: 1852/530, loss: 0.005356362089514732
2023-01-24 06:32:22.127848: step: 1856/530, loss: 0.05792039632797241
2023-01-24 06:32:23.180553: step: 1860/530, loss: 0.0031712681520730257
2023-01-24 06:32:24.252153: step: 1864/530, loss: 0.009036014787852764
2023-01-24 06:32:25.291666: step: 1868/530, loss: 0.005058670416474342
2023-01-24 06:32:26.360916: step: 1872/530, loss: 0.00928338523954153
2023-01-24 06:32:27.417897: step: 1876/530, loss: 0.0011984192533418536
2023-01-24 06:32:28.474537: step: 1880/530, loss: 0.006535263732075691
2023-01-24 06:32:29.533647: step: 1884/530, loss: 0.010922207497060299
2023-01-24 06:32:30.581211: step: 1888/530, loss: 0.005120576359331608
2023-01-24 06:32:31.624676: step: 1892/530, loss: 0.004358522593975067
2023-01-24 06:32:32.659141: step: 1896/530, loss: 0.004579307045787573
2023-01-24 06:32:33.731419: step: 1900/530, loss: 0.007241895888000727
2023-01-24 06:32:34.780940: step: 1904/530, loss: 0.02510642074048519
2023-01-24 06:32:35.844868: step: 1908/530, loss: 0.008431936614215374
2023-01-24 06:32:36.917459: step: 1912/530, loss: 0.04638499766588211
2023-01-24 06:32:37.978943: step: 1916/530, loss: 0.02039339207112789
2023-01-24 06:32:39.010074: step: 1920/530, loss: 0.0005136327818036079
2023-01-24 06:32:40.049053: step: 1924/530, loss: 0.005467600654810667
2023-01-24 06:32:41.100092: step: 1928/530, loss: 0.008041586726903915
2023-01-24 06:32:42.143693: step: 1932/530, loss: 0.02065209671854973
2023-01-24 06:32:43.199007: step: 1936/530, loss: 0.00567570561543107
2023-01-24 06:32:44.253678: step: 1940/530, loss: 0.017883440479636192
2023-01-24 06:32:45.303235: step: 1944/530, loss: 0.003423431422561407
2023-01-24 06:32:46.350974: step: 1948/530, loss: 0.001592633780092001
2023-01-24 06:32:47.408215: step: 1952/530, loss: 0.0023013055324554443
2023-01-24 06:32:48.477692: step: 1956/530, loss: 0.0026466110721230507
2023-01-24 06:32:49.524052: step: 1960/530, loss: 0.0021058772690594196
2023-01-24 06:32:50.584712: step: 1964/530, loss: 0.006164945662021637
2023-01-24 06:32:51.663273: step: 1968/530, loss: 0.03140567988157272
2023-01-24 06:32:52.716404: step: 1972/530, loss: 0.009208698756992817
2023-01-24 06:32:53.767692: step: 1976/530, loss: 0.006094716489315033
2023-01-24 06:32:54.821769: step: 1980/530, loss: 0.008501475676894188
2023-01-24 06:32:55.898782: step: 1984/530, loss: 0.007851428352296352
2023-01-24 06:32:56.967964: step: 1988/530, loss: 0.00667061610147357
2023-01-24 06:32:58.017032: step: 1992/530, loss: 0.002443542703986168
2023-01-24 06:32:59.075610: step: 1996/530, loss: 0.0016685378504917026
2023-01-24 06:33:00.144277: step: 2000/530, loss: 0.0025370209477841854
2023-01-24 06:33:01.192583: step: 2004/530, loss: 0.0051748743280768394
2023-01-24 06:33:02.260320: step: 2008/530, loss: 0.0007593446644023061
2023-01-24 06:33:03.318796: step: 2012/530, loss: 0.01518605463206768
2023-01-24 06:33:04.389759: step: 2016/530, loss: 0.009732052683830261
2023-01-24 06:33:05.443488: step: 2020/530, loss: 0.011828409507870674
2023-01-24 06:33:06.498717: step: 2024/530, loss: 0.0031107300892472267
2023-01-24 06:33:07.554967: step: 2028/530, loss: 0.00406709173694253
2023-01-24 06:33:08.604851: step: 2032/530, loss: 0.005738048814237118
2023-01-24 06:33:09.686663: step: 2036/530, loss: 0.008668201975524426
2023-01-24 06:33:10.746444: step: 2040/530, loss: 0.011014391668140888
2023-01-24 06:33:11.787422: step: 2044/530, loss: 0.008107154630124569
2023-01-24 06:33:12.858865: step: 2048/530, loss: 0.004370998591184616
2023-01-24 06:33:13.928262: step: 2052/530, loss: 0.010136863216757774
2023-01-24 06:33:14.983149: step: 2056/530, loss: 0.005771184340119362
2023-01-24 06:33:16.035547: step: 2060/530, loss: 0.02169601246714592
2023-01-24 06:33:17.113384: step: 2064/530, loss: 0.007024338468909264
2023-01-24 06:33:18.174745: step: 2068/530, loss: 0.001197601668536663
2023-01-24 06:33:19.227293: step: 2072/530, loss: 0.00965450331568718
2023-01-24 06:33:20.295766: step: 2076/530, loss: 0.0038245441392064095
2023-01-24 06:33:21.354461: step: 2080/530, loss: 0.025288328528404236
2023-01-24 06:33:22.408243: step: 2084/530, loss: 0.009369452483952045
2023-01-24 06:33:23.458662: step: 2088/530, loss: 0.0016892123967409134
2023-01-24 06:33:24.518406: step: 2092/530, loss: 0.0044386195950210094
2023-01-24 06:33:25.601615: step: 2096/530, loss: 0.03561408072710037
2023-01-24 06:33:26.661673: step: 2100/530, loss: 0.00871810782700777
2023-01-24 06:33:27.719069: step: 2104/530, loss: 0.008738541975617409
2023-01-24 06:33:28.780859: step: 2108/530, loss: 0.000607248512096703
2023-01-24 06:33:29.832405: step: 2112/530, loss: 0.004152113106101751
2023-01-24 06:33:30.882037: step: 2116/530, loss: 0.002932887291535735
2023-01-24 06:33:31.920697: step: 2120/530, loss: 0.005966485477983952
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3768430270446399, 'r': 0.33250855327468226, 'f1': 0.3532903378543499}, 'combined': 0.26031919631373146, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39575074823171535, 'r': 0.2979285771596955, 'f1': 0.33994225577944476}, 'combined': 0.2254539312941395, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34579411764705886, 'r': 0.27833806818181817, 'f1': 0.30842077649527805}, 'combined': 0.20561385099685203, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3979979515388225, 'r': 0.29453227956165895, 'f1': 0.3385361061893968}, 'combined': 0.22093935351307997, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36851062546871527, 'r': 0.33075052342827765, 'f1': 0.34861105169340467}, 'combined': 0.25687130124777185, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3940522836242501, 'r': 0.30773606911608103, 'f1': 0.3455859599699306}, 'combined': 0.2291969060940472, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 06:35:57.242544: step: 4/530, loss: 0.002935008844360709
2023-01-24 06:35:58.289571: step: 8/530, loss: 0.00553450733423233
2023-01-24 06:35:59.332544: step: 12/530, loss: 0.0036238685715943575
2023-01-24 06:36:00.372609: step: 16/530, loss: 0.009448220022022724
2023-01-24 06:36:01.428461: step: 20/530, loss: 0.003173980861902237
2023-01-24 06:36:02.478849: step: 24/530, loss: 0.010232631117105484
2023-01-24 06:36:03.530282: step: 28/530, loss: 0.010038836859166622
2023-01-24 06:36:04.577015: step: 32/530, loss: 0.000773742503952235
2023-01-24 06:36:05.638075: step: 36/530, loss: 0.008045186288654804
2023-01-24 06:36:06.681319: step: 40/530, loss: 0.0057647330686450005
2023-01-24 06:36:07.763468: step: 44/530, loss: 0.04628004878759384
2023-01-24 06:36:08.824463: step: 48/530, loss: 0.019980663433670998
2023-01-24 06:36:09.892927: step: 52/530, loss: 0.030836906284093857
2023-01-24 06:36:10.940365: step: 56/530, loss: 0.014333067461848259
2023-01-24 06:36:11.985201: step: 60/530, loss: 0.022833118215203285
2023-01-24 06:36:13.033137: step: 64/530, loss: 0.04708084836602211
2023-01-24 06:36:14.088767: step: 68/530, loss: 0.014588503167033195
2023-01-24 06:36:15.149530: step: 72/530, loss: 0.015138708986341953
2023-01-24 06:36:16.192175: step: 76/530, loss: 0.006230298895388842
2023-01-24 06:36:17.259084: step: 80/530, loss: 0.012939664535224438
2023-01-24 06:36:18.319902: step: 84/530, loss: 0.008656331337988377
2023-01-24 06:36:19.386396: step: 88/530, loss: 0.001773890689946711
2023-01-24 06:36:20.442183: step: 92/530, loss: 0.0038941162638366222
2023-01-24 06:36:21.487954: step: 96/530, loss: 0.001993746729567647
2023-01-24 06:36:22.531774: step: 100/530, loss: 0.004627324640750885
2023-01-24 06:36:23.570837: step: 104/530, loss: 0.006845708470791578
2023-01-24 06:36:24.613200: step: 108/530, loss: 0.002246327232569456
2023-01-24 06:36:25.669108: step: 112/530, loss: 0.0014962865971028805
2023-01-24 06:36:26.735979: step: 116/530, loss: 0.026668353006243706
2023-01-24 06:36:27.803768: step: 120/530, loss: 0.00611648615449667
2023-01-24 06:36:28.849156: step: 124/530, loss: 0.001448789844289422
2023-01-24 06:36:29.904088: step: 128/530, loss: 0.001396888867020607
2023-01-24 06:36:30.958237: step: 132/530, loss: 0.0010024980874732137
2023-01-24 06:36:32.015563: step: 136/530, loss: 0.012518187053501606
2023-01-24 06:36:33.077044: step: 140/530, loss: 0.004129523411393166
2023-01-24 06:36:34.117220: step: 144/530, loss: 0.0331420823931694
2023-01-24 06:36:35.156604: step: 148/530, loss: 0.06676769256591797
2023-01-24 06:36:36.207748: step: 152/530, loss: 0.0006281499518081546
2023-01-24 06:36:37.262376: step: 156/530, loss: 0.014255334623157978
2023-01-24 06:36:38.325187: step: 160/530, loss: 0.011756670661270618
2023-01-24 06:36:39.394649: step: 164/530, loss: 0.007124690804630518
2023-01-24 06:36:40.460266: step: 168/530, loss: 0.007193358615040779
2023-01-24 06:36:41.527259: step: 172/530, loss: 0.0037883929908275604
2023-01-24 06:36:42.599012: step: 176/530, loss: 0.005635456647723913
2023-01-24 06:36:43.662251: step: 180/530, loss: 0.004862099885940552
2023-01-24 06:36:44.711658: step: 184/530, loss: 0.0012532506370916963
2023-01-24 06:36:45.755185: step: 188/530, loss: 0.003170378040522337
2023-01-24 06:36:46.814597: step: 192/530, loss: 0.0036637848243117332
2023-01-24 06:36:47.868520: step: 196/530, loss: 0.004866126459091902
2023-01-24 06:36:48.913411: step: 200/530, loss: 0.0031893854029476643
2023-01-24 06:36:49.962217: step: 204/530, loss: 0.002500726841390133
2023-01-24 06:36:51.027527: step: 208/530, loss: 0.012587991543114185
2023-01-24 06:36:52.094677: step: 212/530, loss: 0.019643208011984825
2023-01-24 06:36:53.166396: step: 216/530, loss: 0.011613375507295132
2023-01-24 06:36:54.222641: step: 220/530, loss: 0.007276271935552359
2023-01-24 06:36:55.286428: step: 224/530, loss: 0.012464502826333046
2023-01-24 06:36:56.344082: step: 228/530, loss: 0.10264579206705093
2023-01-24 06:36:57.410269: step: 232/530, loss: 0.03704299405217171
2023-01-24 06:36:58.473854: step: 236/530, loss: 0.004660559818148613
2023-01-24 06:36:59.532245: step: 240/530, loss: 0.0017231680685654283
2023-01-24 06:37:00.593995: step: 244/530, loss: 0.0038283290341496468
2023-01-24 06:37:01.661809: step: 248/530, loss: 0.00805477425456047
2023-01-24 06:37:02.709734: step: 252/530, loss: 0.019948381930589676
2023-01-24 06:37:03.774913: step: 256/530, loss: 0.02022450603544712
2023-01-24 06:37:04.863565: step: 260/530, loss: 0.014648928306996822
2023-01-24 06:37:05.941511: step: 264/530, loss: 0.001241735415533185
2023-01-24 06:37:06.995040: step: 268/530, loss: 0.0006190391723066568
2023-01-24 06:37:08.063989: step: 272/530, loss: 0.0002878374943975359
2023-01-24 06:37:09.134365: step: 276/530, loss: 0.011928042396903038
2023-01-24 06:37:10.218946: step: 280/530, loss: 0.002198312198743224
2023-01-24 06:37:11.269792: step: 284/530, loss: 0.03147488832473755
2023-01-24 06:37:12.318554: step: 288/530, loss: 0.0010817664442583919
2023-01-24 06:37:13.408050: step: 292/530, loss: 0.0057760486379265785
2023-01-24 06:37:14.462576: step: 296/530, loss: 0.005818071309477091
2023-01-24 06:37:15.546154: step: 300/530, loss: 0.010569863021373749
2023-01-24 06:37:16.587157: step: 304/530, loss: 0.0035836913157254457
2023-01-24 06:37:17.641585: step: 308/530, loss: 0.0013431876432150602
2023-01-24 06:37:18.699694: step: 312/530, loss: 0.00991650391370058
2023-01-24 06:37:19.766358: step: 316/530, loss: 0.04024288058280945
2023-01-24 06:37:20.817435: step: 320/530, loss: 0.007050373591482639
2023-01-24 06:37:21.871146: step: 324/530, loss: 0.0062559545040130615
2023-01-24 06:37:22.934772: step: 328/530, loss: 0.002456584945321083
2023-01-24 06:37:24.000909: step: 332/530, loss: 0.020340995863080025
2023-01-24 06:37:25.051494: step: 336/530, loss: 0.009060685522854328
2023-01-24 06:37:26.103408: step: 340/530, loss: 0.009002921171486378
2023-01-24 06:37:27.172983: step: 344/530, loss: 0.002297008875757456
2023-01-24 06:37:28.236988: step: 348/530, loss: 0.007203955668956041
2023-01-24 06:37:29.288672: step: 352/530, loss: 0.0009175653103739023
2023-01-24 06:37:30.351864: step: 356/530, loss: 0.011200152337551117
2023-01-24 06:37:31.410674: step: 360/530, loss: 0.002791506005451083
2023-01-24 06:37:32.486176: step: 364/530, loss: 0.015113864094018936
2023-01-24 06:37:33.543220: step: 368/530, loss: 0.0012664305977523327
2023-01-24 06:37:34.635758: step: 372/530, loss: 0.00632602721452713
2023-01-24 06:37:35.698303: step: 376/530, loss: 0.002704090904444456
2023-01-24 06:37:36.768771: step: 380/530, loss: 0.002333748620003462
2023-01-24 06:37:37.828845: step: 384/530, loss: 0.003553990740329027
2023-01-24 06:37:38.887261: step: 388/530, loss: 0.021430572494864464
2023-01-24 06:37:39.952794: step: 392/530, loss: 0.003722083754837513
2023-01-24 06:37:41.009411: step: 396/530, loss: 0.002973325317725539
2023-01-24 06:37:42.088361: step: 400/530, loss: 0.0028017768636345863
2023-01-24 06:37:43.158303: step: 404/530, loss: 0.00537716643884778
2023-01-24 06:37:44.202541: step: 408/530, loss: 0.014416931197047234
2023-01-24 06:37:45.259787: step: 412/530, loss: 0.0015526312636211514
2023-01-24 06:37:46.318095: step: 416/530, loss: 0.005448088515549898
2023-01-24 06:37:47.369970: step: 420/530, loss: 0.002743306802585721
2023-01-24 06:37:48.423612: step: 424/530, loss: 0.0010752518428489566
2023-01-24 06:37:49.490025: step: 428/530, loss: 0.014399430714547634
2023-01-24 06:37:50.529388: step: 432/530, loss: 0.002354689408093691
2023-01-24 06:37:51.587223: step: 436/530, loss: 0.021478183567523956
2023-01-24 06:37:52.656430: step: 440/530, loss: 0.026265544816851616
2023-01-24 06:37:53.722433: step: 444/530, loss: 0.0015635223826393485
2023-01-24 06:37:54.793696: step: 448/530, loss: 0.00818532146513462
2023-01-24 06:37:55.836907: step: 452/530, loss: 0.0004785509081557393
2023-01-24 06:37:56.908314: step: 456/530, loss: 0.009481661021709442
2023-01-24 06:37:57.970632: step: 460/530, loss: 0.005708055570721626
2023-01-24 06:37:59.038768: step: 464/530, loss: 0.010962888598442078
2023-01-24 06:38:00.092864: step: 468/530, loss: 0.017835110425949097
2023-01-24 06:38:01.165833: step: 472/530, loss: 0.006975238677114248
2023-01-24 06:38:02.236722: step: 476/530, loss: 0.014720846898853779
2023-01-24 06:38:03.311516: step: 480/530, loss: 0.017656855285167694
2023-01-24 06:38:04.376828: step: 484/530, loss: 0.0036886150483042
2023-01-24 06:38:05.435674: step: 488/530, loss: 0.004657586105167866
2023-01-24 06:38:06.499469: step: 492/530, loss: 0.029611514881253242
2023-01-24 06:38:07.570536: step: 496/530, loss: 0.002924734726548195
2023-01-24 06:38:08.641223: step: 500/530, loss: 0.0038471685256808996
2023-01-24 06:38:09.709323: step: 504/530, loss: 0.002278828527778387
2023-01-24 06:38:10.780479: step: 508/530, loss: 0.014040910638868809
2023-01-24 06:38:11.839474: step: 512/530, loss: 0.001243583974428475
2023-01-24 06:38:12.893475: step: 516/530, loss: 0.008267502300441265
2023-01-24 06:38:13.957575: step: 520/530, loss: 0.005858213175088167
2023-01-24 06:38:15.013035: step: 524/530, loss: 0.02089940570294857
2023-01-24 06:38:16.066631: step: 528/530, loss: 0.0022993097081780434
2023-01-24 06:38:17.132542: step: 532/530, loss: 0.004143647849559784
2023-01-24 06:38:18.197772: step: 536/530, loss: 0.019484344869852066
2023-01-24 06:38:19.268443: step: 540/530, loss: 0.005829899106174707
2023-01-24 06:38:20.317544: step: 544/530, loss: 0.023752352222800255
2023-01-24 06:38:21.376250: step: 548/530, loss: 0.004406374413520098
2023-01-24 06:38:22.435841: step: 552/530, loss: 0.021138319745659828
2023-01-24 06:38:23.480695: step: 556/530, loss: 0.0108731584623456
2023-01-24 06:38:24.549277: step: 560/530, loss: 0.008291509933769703
2023-01-24 06:38:25.604655: step: 564/530, loss: 0.007430888246744871
2023-01-24 06:38:26.646100: step: 568/530, loss: 0.002242419868707657
2023-01-24 06:38:27.710936: step: 572/530, loss: 0.007153162267059088
2023-01-24 06:38:28.778020: step: 576/530, loss: 0.00153370073530823
2023-01-24 06:38:29.831274: step: 580/530, loss: 0.021514829248189926
2023-01-24 06:38:30.886879: step: 584/530, loss: 0.012931182980537415
2023-01-24 06:38:31.955828: step: 588/530, loss: 0.01066757831722498
2023-01-24 06:38:33.049650: step: 592/530, loss: 0.004547076765447855
2023-01-24 06:38:34.101099: step: 596/530, loss: 0.0018678150372579694
2023-01-24 06:38:35.170869: step: 600/530, loss: 0.061334703117609024
2023-01-24 06:38:36.236615: step: 604/530, loss: 0.00036601736792363226
2023-01-24 06:38:37.275842: step: 608/530, loss: 3.519013989716768e-05
2023-01-24 06:38:38.352587: step: 612/530, loss: 0.005283213220536709
2023-01-24 06:38:39.420581: step: 616/530, loss: 0.002885697176679969
2023-01-24 06:38:40.470556: step: 620/530, loss: 0.003819693811237812
2023-01-24 06:38:41.535775: step: 624/530, loss: 0.0026370843406766653
2023-01-24 06:38:42.599929: step: 628/530, loss: 0.015561898238956928
2023-01-24 06:38:43.687530: step: 632/530, loss: 0.007443511392921209
2023-01-24 06:38:44.740353: step: 636/530, loss: 0.033750295639038086
2023-01-24 06:38:45.803258: step: 640/530, loss: 0.015521280467510223
2023-01-24 06:38:46.871569: step: 644/530, loss: 0.023418111726641655
2023-01-24 06:38:47.938832: step: 648/530, loss: 0.003972249571233988
2023-01-24 06:38:48.993484: step: 652/530, loss: 1.3918206605012529e-05
2023-01-24 06:38:50.058393: step: 656/530, loss: 0.0073442705906927586
2023-01-24 06:38:51.120848: step: 660/530, loss: 0.0070203267969191074
2023-01-24 06:38:52.183508: step: 664/530, loss: 0.007446333300322294
2023-01-24 06:38:53.244786: step: 668/530, loss: 0.0017605950124561787
2023-01-24 06:38:54.307059: step: 672/530, loss: 0.005377999506890774
2023-01-24 06:38:55.368193: step: 676/530, loss: 0.0012440556893125176
2023-01-24 06:38:56.426013: step: 680/530, loss: 0.009946336038410664
2023-01-24 06:38:57.492770: step: 684/530, loss: 0.005002099554985762
2023-01-24 06:38:58.550815: step: 688/530, loss: 0.014016013592481613
2023-01-24 06:38:59.616909: step: 692/530, loss: 0.0008377187186852098
2023-01-24 06:39:00.666234: step: 696/530, loss: 0.0028977743349969387
2023-01-24 06:39:01.731185: step: 700/530, loss: 0.007128594908863306
2023-01-24 06:39:02.810240: step: 704/530, loss: 0.005335237365216017
2023-01-24 06:39:03.872080: step: 708/530, loss: 0.007555581629276276
2023-01-24 06:39:04.912977: step: 712/530, loss: 0.001965835690498352
2023-01-24 06:39:05.966415: step: 716/530, loss: 0.0018483292078599334
2023-01-24 06:39:07.022562: step: 720/530, loss: 0.014079613611102104
2023-01-24 06:39:08.070489: step: 724/530, loss: 0.009324528276920319
2023-01-24 06:39:09.116492: step: 728/530, loss: 0.007066858932375908
2023-01-24 06:39:10.172701: step: 732/530, loss: 0.019413722679018974
2023-01-24 06:39:11.227982: step: 736/530, loss: 0.0062380400486290455
2023-01-24 06:39:12.276414: step: 740/530, loss: 0.0024765871930867434
2023-01-24 06:39:13.325294: step: 744/530, loss: 0.0005940993432886899
2023-01-24 06:39:14.388920: step: 748/530, loss: 0.04270133003592491
2023-01-24 06:39:15.441032: step: 752/530, loss: 0.009178146719932556
2023-01-24 06:39:16.511346: step: 756/530, loss: 0.007826559245586395
2023-01-24 06:39:17.568130: step: 760/530, loss: 0.003232432994991541
2023-01-24 06:39:18.630208: step: 764/530, loss: 0.006229587830603123
2023-01-24 06:39:19.685570: step: 768/530, loss: 0.012369930744171143
2023-01-24 06:39:20.747547: step: 772/530, loss: 0.015480311587452888
2023-01-24 06:39:21.804251: step: 776/530, loss: 0.005448880605399609
2023-01-24 06:39:22.851877: step: 780/530, loss: 0.005266676191240549
2023-01-24 06:39:23.905883: step: 784/530, loss: 0.010284190066158772
2023-01-24 06:39:24.962157: step: 788/530, loss: 0.011885513551533222
2023-01-24 06:39:26.008503: step: 792/530, loss: 0.0125502310693264
2023-01-24 06:39:27.066123: step: 796/530, loss: 0.01250625029206276
2023-01-24 06:39:28.121783: step: 800/530, loss: 0.058051660656929016
2023-01-24 06:39:29.180969: step: 804/530, loss: 0.005431478843092918
2023-01-24 06:39:30.247482: step: 808/530, loss: 0.004475806839764118
2023-01-24 06:39:31.296436: step: 812/530, loss: 0.01590234600007534
2023-01-24 06:39:32.341808: step: 816/530, loss: 0.0037732599303126335
2023-01-24 06:39:33.395663: step: 820/530, loss: 0.0012804219732061028
2023-01-24 06:39:34.453335: step: 824/530, loss: 0.02562713250517845
2023-01-24 06:39:35.510402: step: 828/530, loss: 0.003869742387905717
2023-01-24 06:39:36.570993: step: 832/530, loss: 0.01133052259683609
2023-01-24 06:39:37.626941: step: 836/530, loss: 0.003731081960722804
2023-01-24 06:39:38.668633: step: 840/530, loss: 0.02150881662964821
2023-01-24 06:39:39.724666: step: 844/530, loss: 0.0125171709805727
2023-01-24 06:39:40.777104: step: 848/530, loss: 0.0021820201072841883
2023-01-24 06:39:41.840807: step: 852/530, loss: 0.007116499822586775
2023-01-24 06:39:42.896411: step: 856/530, loss: 8.16404281067662e-05
2023-01-24 06:39:43.953339: step: 860/530, loss: 0.027179615572094917
2023-01-24 06:39:45.032723: step: 864/530, loss: 0.0028818680439144373
2023-01-24 06:39:46.106292: step: 868/530, loss: 0.005046400241553783
2023-01-24 06:39:47.173463: step: 872/530, loss: 0.029310790821909904
2023-01-24 06:39:48.225472: step: 876/530, loss: 0.002894083270803094
2023-01-24 06:39:49.296949: step: 880/530, loss: 0.01013959851115942
2023-01-24 06:39:50.364088: step: 884/530, loss: 0.0022927518002688885
2023-01-24 06:39:51.432813: step: 888/530, loss: 0.011974267661571503
2023-01-24 06:39:52.479183: step: 892/530, loss: 0.0037686966825276613
2023-01-24 06:39:53.518635: step: 896/530, loss: 0.0012438582489266992
2023-01-24 06:39:54.590642: step: 900/530, loss: 0.018747396767139435
2023-01-24 06:39:55.645523: step: 904/530, loss: 0.03753173351287842
2023-01-24 06:39:56.708047: step: 908/530, loss: 0.0037961772177368402
2023-01-24 06:39:57.765635: step: 912/530, loss: 0.0002140506258001551
2023-01-24 06:39:58.823674: step: 916/530, loss: 9.290588786825538e-05
2023-01-24 06:39:59.922610: step: 920/530, loss: 0.013624818064272404
2023-01-24 06:40:00.980132: step: 924/530, loss: 0.005930694751441479
2023-01-24 06:40:02.073500: step: 928/530, loss: 0.0030376899521797895
2023-01-24 06:40:03.134706: step: 932/530, loss: 0.011940033175051212
2023-01-24 06:40:04.208299: step: 936/530, loss: 0.004891168791800737
2023-01-24 06:40:05.269483: step: 940/530, loss: 0.018233217298984528
2023-01-24 06:40:06.316902: step: 944/530, loss: 0.0002812612510751933
2023-01-24 06:40:07.374764: step: 948/530, loss: 0.0096819419413805
2023-01-24 06:40:08.456477: step: 952/530, loss: 0.010757689364254475
2023-01-24 06:40:09.526489: step: 956/530, loss: 0.003954260144382715
2023-01-24 06:40:10.587627: step: 960/530, loss: 0.006567119620740414
2023-01-24 06:40:11.650460: step: 964/530, loss: 0.0039191520772874355
2023-01-24 06:40:12.711682: step: 968/530, loss: 0.02667185105383396
2023-01-24 06:40:13.773518: step: 972/530, loss: 0.0038634252268821
2023-01-24 06:40:14.837052: step: 976/530, loss: 0.020103279501199722
2023-01-24 06:40:15.884394: step: 980/530, loss: 9.14368501980789e-05
2023-01-24 06:40:16.941961: step: 984/530, loss: 0.012991974130272865
2023-01-24 06:40:18.016731: step: 988/530, loss: 0.005785475950688124
2023-01-24 06:40:19.091722: step: 992/530, loss: 0.01604420319199562
2023-01-24 06:40:20.147248: step: 996/530, loss: 0.02683783508837223
2023-01-24 06:40:21.216194: step: 1000/530, loss: 0.0038679251447319984
2023-01-24 06:40:22.284297: step: 1004/530, loss: 0.004743065685033798
2023-01-24 06:40:23.364154: step: 1008/530, loss: 0.015931354835629463
2023-01-24 06:40:24.429491: step: 1012/530, loss: 0.018804019317030907
2023-01-24 06:40:25.483421: step: 1016/530, loss: 0.007097493391484022
2023-01-24 06:40:26.555467: step: 1020/530, loss: 0.014133797027170658
2023-01-24 06:40:27.604218: step: 1024/530, loss: 0.008046402595937252
2023-01-24 06:40:28.652034: step: 1028/530, loss: 0.0003183053049724549
2023-01-24 06:40:29.707764: step: 1032/530, loss: 0.0
2023-01-24 06:40:30.783307: step: 1036/530, loss: 0.004290013574063778
2023-01-24 06:40:31.842810: step: 1040/530, loss: 0.009799295105040073
2023-01-24 06:40:32.922361: step: 1044/530, loss: 0.004885335452854633
2023-01-24 06:40:33.984148: step: 1048/530, loss: 0.0013348229695111513
2023-01-24 06:40:35.037172: step: 1052/530, loss: 0.00038746907375752926
2023-01-24 06:40:36.091109: step: 1056/530, loss: 0.011195574887096882
2023-01-24 06:40:37.157358: step: 1060/530, loss: 0.00456309923902154
2023-01-24 06:40:38.205968: step: 1064/530, loss: 0.01606837846338749
2023-01-24 06:40:39.274436: step: 1068/530, loss: 0.007236562669277191
2023-01-24 06:40:40.355944: step: 1072/530, loss: 0.0012436611577868462
2023-01-24 06:40:41.406484: step: 1076/530, loss: 0.01422815676778555
2023-01-24 06:40:42.458204: step: 1080/530, loss: 0.0030606589280068874
2023-01-24 06:40:43.496949: step: 1084/530, loss: 0.0028565924149006605
2023-01-24 06:40:44.581316: step: 1088/530, loss: 0.005879318807274103
2023-01-24 06:40:45.629426: step: 1092/530, loss: 0.001622932031750679
2023-01-24 06:40:46.702527: step: 1096/530, loss: 0.012155161239206791
2023-01-24 06:40:47.748966: step: 1100/530, loss: 0.018030766397714615
2023-01-24 06:40:48.806757: step: 1104/530, loss: 0.013453183695673943
2023-01-24 06:40:49.882285: step: 1108/530, loss: 0.004948226734995842
2023-01-24 06:40:50.945336: step: 1112/530, loss: 0.002874464727938175
2023-01-24 06:40:52.010512: step: 1116/530, loss: 0.050375789403915405
2023-01-24 06:40:53.069348: step: 1120/530, loss: 0.019457241520285606
2023-01-24 06:40:54.125341: step: 1124/530, loss: 0.04155614972114563
2023-01-24 06:40:55.206485: step: 1128/530, loss: 0.04811040684580803
2023-01-24 06:40:56.280425: step: 1132/530, loss: 0.005900775548070669
2023-01-24 06:40:57.341682: step: 1136/530, loss: 0.0046536545269191265
2023-01-24 06:40:58.413412: step: 1140/530, loss: 0.011202199384570122
2023-01-24 06:40:59.466942: step: 1144/530, loss: 0.0012106720823794603
2023-01-24 06:41:00.521182: step: 1148/530, loss: 0.008635424077510834
2023-01-24 06:41:01.569789: step: 1152/530, loss: 0.027918661013245583
2023-01-24 06:41:02.639239: step: 1156/530, loss: 0.04734714329242706
2023-01-24 06:41:03.714486: step: 1160/530, loss: 0.000833917991258204
2023-01-24 06:41:04.798526: step: 1164/530, loss: 0.011002247221767902
2023-01-24 06:41:05.847373: step: 1168/530, loss: 0.05000299960374832
2023-01-24 06:41:06.906969: step: 1172/530, loss: 0.005127518437802792
2023-01-24 06:41:07.963163: step: 1176/530, loss: 0.0029571533668786287
2023-01-24 06:41:09.030101: step: 1180/530, loss: 0.03149858117103577
2023-01-24 06:41:10.080200: step: 1184/530, loss: 0.002711329609155655
2023-01-24 06:41:11.129273: step: 1188/530, loss: 0.013199533335864544
2023-01-24 06:41:12.202494: step: 1192/530, loss: 0.015927262604236603
2023-01-24 06:41:13.248575: step: 1196/530, loss: 0.007734857499599457
2023-01-24 06:41:14.304346: step: 1200/530, loss: 0.018418120220303535
2023-01-24 06:41:15.354552: step: 1204/530, loss: 0.0024743482936173677
2023-01-24 06:41:16.411382: step: 1208/530, loss: 0.0034468930680304766
2023-01-24 06:41:17.470939: step: 1212/530, loss: 0.020393524318933487
2023-01-24 06:41:18.551797: step: 1216/530, loss: 0.01308753527700901
2023-01-24 06:41:19.620584: step: 1220/530, loss: 0.007994313724339008
2023-01-24 06:41:20.674735: step: 1224/530, loss: 0.0035022906959056854
2023-01-24 06:41:21.726384: step: 1228/530, loss: 0.010835937224328518
2023-01-24 06:41:22.771371: step: 1232/530, loss: 0.000707242579665035
2023-01-24 06:41:23.827665: step: 1236/530, loss: 0.005404041148722172
2023-01-24 06:41:24.894262: step: 1240/530, loss: 0.0065835705026984215
2023-01-24 06:41:25.951529: step: 1244/530, loss: 0.003519100369885564
2023-01-24 06:41:27.002309: step: 1248/530, loss: 0.005717897322028875
2023-01-24 06:41:28.050480: step: 1252/530, loss: 0.0008940945845097303
2023-01-24 06:41:29.108529: step: 1256/530, loss: 0.0010296402033418417
2023-01-24 06:41:30.170687: step: 1260/530, loss: 0.002223445102572441
2023-01-24 06:41:31.230901: step: 1264/530, loss: 0.02873888984322548
2023-01-24 06:41:32.314279: step: 1268/530, loss: 0.004704189021140337
2023-01-24 06:41:33.365467: step: 1272/530, loss: 0.04207101836800575
2023-01-24 06:41:34.438478: step: 1276/530, loss: 0.003507298184558749
2023-01-24 06:41:35.502625: step: 1280/530, loss: 0.004845779854804277
2023-01-24 06:41:36.587897: step: 1284/530, loss: 0.009277509525418282
2023-01-24 06:41:37.667053: step: 1288/530, loss: 0.001853696652688086
2023-01-24 06:41:38.729602: step: 1292/530, loss: 0.004756136331707239
2023-01-24 06:41:39.775823: step: 1296/530, loss: 0.011717579327523708
2023-01-24 06:41:40.825318: step: 1300/530, loss: 0.017659898847341537
2023-01-24 06:41:41.884038: step: 1304/530, loss: 0.03367912024259567
2023-01-24 06:41:42.948004: step: 1308/530, loss: 0.005786130670458078
2023-01-24 06:41:44.006777: step: 1312/530, loss: 0.0024127408396452665
2023-01-24 06:41:45.066990: step: 1316/530, loss: 0.008533951826393604
2023-01-24 06:41:46.137635: step: 1320/530, loss: 0.011065351776778698
2023-01-24 06:41:47.214904: step: 1324/530, loss: 0.001868952065706253
2023-01-24 06:41:48.280049: step: 1328/530, loss: 0.01387058012187481
2023-01-24 06:41:49.332284: step: 1332/530, loss: 0.001901100855320692
2023-01-24 06:41:50.374632: step: 1336/530, loss: 0.0005004171398468316
2023-01-24 06:41:51.431530: step: 1340/530, loss: 0.006409507244825363
2023-01-24 06:41:52.481358: step: 1344/530, loss: 0.0021359717939049006
2023-01-24 06:41:53.530758: step: 1348/530, loss: 0.002240303438156843
2023-01-24 06:41:54.594493: step: 1352/530, loss: 0.0023708504159003496
2023-01-24 06:41:55.658524: step: 1356/530, loss: 0.0002888084854930639
2023-01-24 06:41:56.724463: step: 1360/530, loss: 0.014817366376519203
2023-01-24 06:41:57.792939: step: 1364/530, loss: 0.029927879571914673
2023-01-24 06:41:58.859307: step: 1368/530, loss: 0.00268600438721478
2023-01-24 06:41:59.926238: step: 1372/530, loss: 0.01663109101355076
2023-01-24 06:42:00.990335: step: 1376/530, loss: 0.0
2023-01-24 06:42:02.072060: step: 1380/530, loss: 0.009185770526528358
2023-01-24 06:42:03.106086: step: 1384/530, loss: 0.010320502333343029
2023-01-24 06:42:04.189851: step: 1388/530, loss: 0.011841828003525734
2023-01-24 06:42:05.255709: step: 1392/530, loss: 0.001995900645852089
2023-01-24 06:42:06.319426: step: 1396/530, loss: 0.012550605461001396
2023-01-24 06:42:07.371405: step: 1400/530, loss: 0.03100932389497757
2023-01-24 06:42:08.435749: step: 1404/530, loss: 0.008636459708213806
2023-01-24 06:42:09.488938: step: 1408/530, loss: 0.01020064577460289
2023-01-24 06:42:10.569300: step: 1412/530, loss: 0.028234366327524185
2023-01-24 06:42:11.635281: step: 1416/530, loss: 0.010167238302528858
2023-01-24 06:42:12.710017: step: 1420/530, loss: 0.010518955998122692
2023-01-24 06:42:13.767350: step: 1424/530, loss: 0.005865598563104868
2023-01-24 06:42:14.823678: step: 1428/530, loss: 0.014418727718293667
2023-01-24 06:42:15.894932: step: 1432/530, loss: 0.004344608169049025
2023-01-24 06:42:16.955488: step: 1436/530, loss: 0.004507642239332199
2023-01-24 06:42:18.033182: step: 1440/530, loss: 0.004870147444307804
2023-01-24 06:42:19.098036: step: 1444/530, loss: 0.009045331738889217
2023-01-24 06:42:20.171772: step: 1448/530, loss: 0.030946195125579834
2023-01-24 06:42:21.240142: step: 1452/530, loss: 0.004933202639222145
2023-01-24 06:42:22.293734: step: 1456/530, loss: 0.01915445178747177
2023-01-24 06:42:23.355902: step: 1460/530, loss: 0.002927019027993083
2023-01-24 06:42:24.416299: step: 1464/530, loss: 0.004657906945794821
2023-01-24 06:42:25.477417: step: 1468/530, loss: 0.007095067761838436
2023-01-24 06:42:26.536114: step: 1472/530, loss: 0.003370932536199689
2023-01-24 06:42:27.594278: step: 1476/530, loss: 0.006741188932210207
2023-01-24 06:42:28.664481: step: 1480/530, loss: 0.013289038091897964
2023-01-24 06:42:29.727209: step: 1484/530, loss: 0.0026068103034049273
2023-01-24 06:42:30.790404: step: 1488/530, loss: 0.010774119757115841
2023-01-24 06:42:31.843585: step: 1492/530, loss: 0.02800523117184639
2023-01-24 06:42:32.912393: step: 1496/530, loss: 0.0021110419183969498
2023-01-24 06:42:33.977714: step: 1500/530, loss: 0.005094290245324373
2023-01-24 06:42:35.029367: step: 1504/530, loss: 0.0016411175020039082
2023-01-24 06:42:36.086146: step: 1508/530, loss: 0.006435022689402103
2023-01-24 06:42:37.143550: step: 1512/530, loss: 0.0038271802477538586
2023-01-24 06:42:38.198501: step: 1516/530, loss: 0.04329176992177963
2023-01-24 06:42:39.278820: step: 1520/530, loss: 0.008502860553562641
2023-01-24 06:42:40.334602: step: 1524/530, loss: 0.0012858954723924398
2023-01-24 06:42:41.384586: step: 1528/530, loss: 0.0023873939644545317
2023-01-24 06:42:42.436817: step: 1532/530, loss: 0.0034275217913091183
2023-01-24 06:42:43.501753: step: 1536/530, loss: 0.0029062544927001
2023-01-24 06:42:44.567799: step: 1540/530, loss: 0.006031538359820843
2023-01-24 06:42:45.632872: step: 1544/530, loss: 0.009023847058415413
2023-01-24 06:42:46.687012: step: 1548/530, loss: 0.005828891880810261
2023-01-24 06:42:47.748545: step: 1552/530, loss: 0.0025264055002480745
2023-01-24 06:42:48.807226: step: 1556/530, loss: 0.005130165256559849
2023-01-24 06:42:49.869977: step: 1560/530, loss: 0.006263383198529482
2023-01-24 06:42:50.940621: step: 1564/530, loss: 0.0036543160676956177
2023-01-24 06:42:52.022351: step: 1568/530, loss: 0.005106837954372168
2023-01-24 06:42:53.078470: step: 1572/530, loss: 0.009351509623229504
2023-01-24 06:42:54.125398: step: 1576/530, loss: 0.0005123890587128699
2023-01-24 06:42:55.191260: step: 1580/530, loss: 0.004762763623148203
2023-01-24 06:42:56.253666: step: 1584/530, loss: 0.011701364070177078
2023-01-24 06:42:57.310570: step: 1588/530, loss: 0.00974379200488329
2023-01-24 06:42:58.385370: step: 1592/530, loss: 0.01635259948670864
2023-01-24 06:42:59.446707: step: 1596/530, loss: 0.013899075798690319
2023-01-24 06:43:00.497924: step: 1600/530, loss: 0.004284922033548355
2023-01-24 06:43:01.548815: step: 1604/530, loss: 0.00440248055383563
2023-01-24 06:43:02.620168: step: 1608/530, loss: 0.005738194100558758
2023-01-24 06:43:03.671390: step: 1612/530, loss: 0.0051477085798978806
2023-01-24 06:43:04.744683: step: 1616/530, loss: 0.009126820601522923
2023-01-24 06:43:05.805401: step: 1620/530, loss: 0.005962767638266087
2023-01-24 06:43:06.887444: step: 1624/530, loss: 0.004526323173195124
2023-01-24 06:43:07.941209: step: 1628/530, loss: 0.0004168787563685328
2023-01-24 06:43:09.013976: step: 1632/530, loss: 0.003620957024395466
2023-01-24 06:43:10.081550: step: 1636/530, loss: 0.01084889005869627
2023-01-24 06:43:11.156825: step: 1640/530, loss: 0.002801034366711974
2023-01-24 06:43:12.203207: step: 1644/530, loss: 0.0
2023-01-24 06:43:13.253634: step: 1648/530, loss: 0.003452253295108676
2023-01-24 06:43:14.320437: step: 1652/530, loss: 0.007097299676388502
2023-01-24 06:43:15.390597: step: 1656/530, loss: 0.002154362155124545
2023-01-24 06:43:16.450817: step: 1660/530, loss: 0.018424391746520996
2023-01-24 06:43:17.533953: step: 1664/530, loss: 0.002080699661746621
2023-01-24 06:43:18.593979: step: 1668/530, loss: 0.005140418652445078
2023-01-24 06:43:19.667773: step: 1672/530, loss: 0.0026606512255966663
2023-01-24 06:43:20.728024: step: 1676/530, loss: 0.002993499394506216
2023-01-24 06:43:21.780204: step: 1680/530, loss: 0.007442861795425415
2023-01-24 06:43:22.841917: step: 1684/530, loss: 0.001975010382011533
2023-01-24 06:43:23.898029: step: 1688/530, loss: 0.0045084343291819096
2023-01-24 06:43:24.973419: step: 1692/530, loss: 0.0069546024315059185
2023-01-24 06:43:26.027283: step: 1696/530, loss: 0.0026663776952773333
2023-01-24 06:43:27.083069: step: 1700/530, loss: 0.018228016793727875
2023-01-24 06:43:28.137839: step: 1704/530, loss: 0.006329392082989216
2023-01-24 06:43:29.214489: step: 1708/530, loss: 0.015090257860720158
2023-01-24 06:43:30.247798: step: 1712/530, loss: 0.002329648472368717
2023-01-24 06:43:31.307114: step: 1716/530, loss: 0.0018962910398840904
2023-01-24 06:43:32.384848: step: 1720/530, loss: 0.0035224477760493755
2023-01-24 06:43:33.446212: step: 1724/530, loss: 0.02298874221742153
2023-01-24 06:43:34.502170: step: 1728/530, loss: 0.003752456046640873
2023-01-24 06:43:35.562859: step: 1732/530, loss: 8.231526589952409e-05
2023-01-24 06:43:36.623554: step: 1736/530, loss: 0.008032851852476597
2023-01-24 06:43:37.681538: step: 1740/530, loss: 0.003820925485342741
2023-01-24 06:43:38.744514: step: 1744/530, loss: 0.01569504290819168
2023-01-24 06:43:39.799007: step: 1748/530, loss: 0.01494849193841219
2023-01-24 06:43:40.868373: step: 1752/530, loss: 0.009397715330123901
2023-01-24 06:43:41.932849: step: 1756/530, loss: 0.007003241218626499
2023-01-24 06:43:42.977624: step: 1760/530, loss: 0.0
2023-01-24 06:43:44.024315: step: 1764/530, loss: 0.0054090735502541065
2023-01-24 06:43:45.077594: step: 1768/530, loss: 0.007713343482464552
2023-01-24 06:43:46.136502: step: 1772/530, loss: 0.02815413661301136
2023-01-24 06:43:47.187560: step: 1776/530, loss: 0.005441877990961075
2023-01-24 06:43:48.250848: step: 1780/530, loss: 0.0009378030081279576
2023-01-24 06:43:49.311501: step: 1784/530, loss: 0.0057209632359445095
2023-01-24 06:43:50.389174: step: 1788/530, loss: 0.008506428450345993
2023-01-24 06:43:51.441192: step: 1792/530, loss: 0.000548729149159044
2023-01-24 06:43:52.494134: step: 1796/530, loss: 0.0037240025121718645
2023-01-24 06:43:53.555781: step: 1800/530, loss: 0.02908029407262802
2023-01-24 06:43:54.608622: step: 1804/530, loss: 0.007563740015029907
2023-01-24 06:43:55.657756: step: 1808/530, loss: 0.0029163400176912546
2023-01-24 06:43:56.717726: step: 1812/530, loss: 0.000839012092910707
2023-01-24 06:43:57.776597: step: 1816/530, loss: 0.003897731890901923
2023-01-24 06:43:58.837842: step: 1820/530, loss: 0.011289495974779129
2023-01-24 06:43:59.892455: step: 1824/530, loss: 0.007079458795487881
2023-01-24 06:44:00.945945: step: 1828/530, loss: 0.0010993704199790955
2023-01-24 06:44:02.015191: step: 1832/530, loss: 0.005862667690962553
2023-01-24 06:44:03.083312: step: 1836/530, loss: 0.0045527806505560875
2023-01-24 06:44:04.138634: step: 1840/530, loss: 0.0007549830479547381
2023-01-24 06:44:05.210269: step: 1844/530, loss: 0.009025884792208672
2023-01-24 06:44:06.262848: step: 1848/530, loss: 0.013387002982199192
2023-01-24 06:44:07.326404: step: 1852/530, loss: 0.0036910264752805233
2023-01-24 06:44:08.385438: step: 1856/530, loss: 0.006511569023132324
2023-01-24 06:44:09.466961: step: 1860/530, loss: 0.005079867783933878
2023-01-24 06:44:10.532198: step: 1864/530, loss: 0.005769079085439444
2023-01-24 06:44:11.624745: step: 1868/530, loss: 0.007010573986917734
2023-01-24 06:44:12.701025: step: 1872/530, loss: 0.004105666186660528
2023-01-24 06:44:13.764669: step: 1876/530, loss: 0.006187903229147196
2023-01-24 06:44:14.822834: step: 1880/530, loss: 0.03970840945839882
2023-01-24 06:44:15.872474: step: 1884/530, loss: 0.012673421762883663
2023-01-24 06:44:16.924540: step: 1888/530, loss: 0.007877575233578682
2023-01-24 06:44:18.004449: step: 1892/530, loss: 0.00033618404995650053
2023-01-24 06:44:19.055285: step: 1896/530, loss: 0.0006555045256391168
2023-01-24 06:44:20.113108: step: 1900/530, loss: 0.019070345908403397
2023-01-24 06:44:21.174028: step: 1904/530, loss: 0.016332026571035385
2023-01-24 06:44:22.241048: step: 1908/530, loss: 0.002249857410788536
2023-01-24 06:44:23.292645: step: 1912/530, loss: 0.01717446930706501
2023-01-24 06:44:24.347062: step: 1916/530, loss: 0.02588737942278385
2023-01-24 06:44:25.406993: step: 1920/530, loss: 0.004456314258277416
2023-01-24 06:44:26.478593: step: 1924/530, loss: 0.019870944321155548
2023-01-24 06:44:27.533687: step: 1928/530, loss: 0.009163443930447102
2023-01-24 06:44:28.590041: step: 1932/530, loss: 0.007564948871731758
2023-01-24 06:44:29.662380: step: 1936/530, loss: 0.027656367048621178
2023-01-24 06:44:30.706259: step: 1940/530, loss: 0.013094200752675533
2023-01-24 06:44:31.775146: step: 1944/530, loss: 0.004170201253145933
2023-01-24 06:44:32.836586: step: 1948/530, loss: 0.012527740560472012
2023-01-24 06:44:33.906569: step: 1952/530, loss: 0.014081531204283237
2023-01-24 06:44:34.981518: step: 1956/530, loss: 0.04590287059545517
2023-01-24 06:44:36.043663: step: 1960/530, loss: 0.018450524657964706
2023-01-24 06:44:37.104379: step: 1964/530, loss: 0.0062479362823069096
2023-01-24 06:44:38.158324: step: 1968/530, loss: 0.003046920755878091
2023-01-24 06:44:39.214108: step: 1972/530, loss: 0.005486463662236929
2023-01-24 06:44:40.274031: step: 1976/530, loss: 0.0023590759374201298
2023-01-24 06:44:41.350543: step: 1980/530, loss: 0.008467772044241428
2023-01-24 06:44:42.403598: step: 1984/530, loss: 0.002321891952306032
2023-01-24 06:44:43.465227: step: 1988/530, loss: 0.002070195507258177
2023-01-24 06:44:44.517809: step: 1992/530, loss: 0.0007618216332048178
2023-01-24 06:44:45.583559: step: 1996/530, loss: 0.002311565214768052
2023-01-24 06:44:46.658507: step: 2000/530, loss: 0.020710498094558716
2023-01-24 06:44:47.734400: step: 2004/530, loss: 0.0038332317490130663
2023-01-24 06:44:48.801527: step: 2008/530, loss: 0.0010175377829000354
2023-01-24 06:44:49.862575: step: 2012/530, loss: 0.012994120828807354
2023-01-24 06:44:50.924628: step: 2016/530, loss: 0.0054857260547578335
2023-01-24 06:44:51.968253: step: 2020/530, loss: 0.007855881005525589
2023-01-24 06:44:53.023020: step: 2024/530, loss: 0.006128398701548576
2023-01-24 06:44:54.079446: step: 2028/530, loss: 0.005347241647541523
2023-01-24 06:44:55.145336: step: 2032/530, loss: 0.006799470167607069
2023-01-24 06:44:56.202630: step: 2036/530, loss: 0.003383493283763528
2023-01-24 06:44:57.250657: step: 2040/530, loss: 0.002997984178364277
2023-01-24 06:44:58.309951: step: 2044/530, loss: 0.004079834092408419
2023-01-24 06:44:59.379866: step: 2048/530, loss: 0.00022045538935344666
2023-01-24 06:45:00.442752: step: 2052/530, loss: 0.005013130605220795
2023-01-24 06:45:01.501058: step: 2056/530, loss: 0.010318366810679436
2023-01-24 06:45:02.569083: step: 2060/530, loss: 0.01189111452549696
2023-01-24 06:45:03.625312: step: 2064/530, loss: 0.012210406363010406
2023-01-24 06:45:04.679616: step: 2068/530, loss: 0.002377450466156006
2023-01-24 06:45:05.728389: step: 2072/530, loss: 2.3413569579133764e-05
2023-01-24 06:45:06.801304: step: 2076/530, loss: 0.0010762023739516735
2023-01-24 06:45:07.861427: step: 2080/530, loss: 0.0015593904536217451
2023-01-24 06:45:08.947107: step: 2084/530, loss: 0.007034834939986467
2023-01-24 06:45:10.007548: step: 2088/530, loss: 0.0084341149777174
2023-01-24 06:45:11.065861: step: 2092/530, loss: 0.0060415565967559814
2023-01-24 06:45:12.124043: step: 2096/530, loss: 0.01563962548971176
2023-01-24 06:45:13.184904: step: 2100/530, loss: 0.0489777997136116
2023-01-24 06:45:14.263086: step: 2104/530, loss: 0.0018306478159502149
2023-01-24 06:45:15.322180: step: 2108/530, loss: 0.0017658383585512638
2023-01-24 06:45:16.382630: step: 2112/530, loss: 0.00671767583116889
2023-01-24 06:45:17.435658: step: 2116/530, loss: 0.012136721052229404
2023-01-24 06:45:18.490789: step: 2120/530, loss: 0.013112825341522694
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37873277494775337, 'r': 0.33345731987809785, 'f1': 0.35465591841727057}, 'combined': 0.2613254135706204, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39385690387241534, 'r': 0.2963304324373411, 'f1': 0.3382032109339219}, 'combined': 0.22430057512716062, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34691108545034643, 'r': 0.2844933712121212, 'f1': 0.31261706555671176}, 'combined': 0.20841137703780782, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40074883112766596, 'r': 0.2964016008772962, 'f1': 0.34076603740840816}, 'combined': 0.2223946770454874, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3677023852684371, 'r': 0.32932737352315433, 'f1': 0.34745851020360824}, 'combined': 0.2560220601500271, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39638445163795527, 'r': 0.3099005712805832, 'f1': 0.3478475800088179}, 'combined': 0.23069684062760976, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 06:47:47.785364: step: 4/530, loss: 0.012904105708003044
2023-01-24 06:47:48.831381: step: 8/530, loss: 0.005067820660769939
2023-01-24 06:47:49.873368: step: 12/530, loss: 0.015916386619210243
2023-01-24 06:47:50.919277: step: 16/530, loss: 0.0021385247819125652
2023-01-24 06:47:51.952195: step: 20/530, loss: 0.0002824341063387692
2023-01-24 06:47:53.020056: step: 24/530, loss: 0.004916571546345949
2023-01-24 06:47:54.080705: step: 28/530, loss: 0.003122350899502635
2023-01-24 06:47:55.129943: step: 32/530, loss: 0.0025584313552826643
2023-01-24 06:47:56.190754: step: 36/530, loss: 0.0014077366795390844
2023-01-24 06:47:57.234079: step: 40/530, loss: 0.0010288550984114408
2023-01-24 06:47:58.289038: step: 44/530, loss: 0.0017241687746718526
2023-01-24 06:47:59.325359: step: 48/530, loss: 0.0023961246479302645
2023-01-24 06:48:00.394165: step: 52/530, loss: 0.0018241873476654291
2023-01-24 06:48:01.458700: step: 56/530, loss: 0.017092470079660416
2023-01-24 06:48:02.543182: step: 60/530, loss: 0.0035566191654652357
2023-01-24 06:48:03.596844: step: 64/530, loss: 0.00324407871812582
2023-01-24 06:48:04.651223: step: 68/530, loss: 0.038889750838279724
2023-01-24 06:48:05.727957: step: 72/530, loss: 0.008168782107532024
2023-01-24 06:48:06.798254: step: 76/530, loss: 0.006335677113384008
2023-01-24 06:48:07.869627: step: 80/530, loss: 0.0049591949209570885
2023-01-24 06:48:08.919440: step: 84/530, loss: 0.011235124431550503
2023-01-24 06:48:10.002222: step: 88/530, loss: 0.01831236481666565
2023-01-24 06:48:11.062373: step: 92/530, loss: 0.002687113592401147
2023-01-24 06:48:12.125698: step: 96/530, loss: 0.0
2023-01-24 06:48:13.192830: step: 100/530, loss: 0.030802110210061073
2023-01-24 06:48:14.265835: step: 104/530, loss: 0.005285268183797598
2023-01-24 06:48:15.330256: step: 108/530, loss: 0.014542270451784134
2023-01-24 06:48:16.408608: step: 112/530, loss: 0.014644518494606018
2023-01-24 06:48:17.450446: step: 116/530, loss: 0.00613078847527504
2023-01-24 06:48:18.506730: step: 120/530, loss: 0.00600211089476943
2023-01-24 06:48:19.563394: step: 124/530, loss: 0.014048912562429905
2023-01-24 06:48:20.616127: step: 128/530, loss: 0.0056924158707261086
2023-01-24 06:48:21.670648: step: 132/530, loss: 0.001396678388118744
2023-01-24 06:48:22.731418: step: 136/530, loss: 0.008538402616977692
2023-01-24 06:48:23.795451: step: 140/530, loss: 0.003192254574969411
2023-01-24 06:48:24.847169: step: 144/530, loss: 0.0006173851434141397
2023-01-24 06:48:25.932608: step: 148/530, loss: 0.0032596508972346783
2023-01-24 06:48:26.978587: step: 152/530, loss: 0.0031438961159437895
2023-01-24 06:48:28.050231: step: 156/530, loss: 0.0072922599501907825
2023-01-24 06:48:29.123864: step: 160/530, loss: 0.008476948365569115
2023-01-24 06:48:30.185609: step: 164/530, loss: 0.0038286589551717043
2023-01-24 06:48:31.277245: step: 168/530, loss: 0.0012812173226848245
2023-01-24 06:48:32.331030: step: 172/530, loss: 0.004581693094223738
2023-01-24 06:48:33.399957: step: 176/530, loss: 0.0022015050053596497
2023-01-24 06:48:34.457892: step: 180/530, loss: 0.001324501819908619
2023-01-24 06:48:35.503061: step: 184/530, loss: 0.001952095190063119
2023-01-24 06:48:36.562704: step: 188/530, loss: 0.007655243389308453
2023-01-24 06:48:37.616456: step: 192/530, loss: 0.0010749392677098513
2023-01-24 06:48:38.677124: step: 196/530, loss: 0.01239064708352089
2023-01-24 06:48:39.747388: step: 200/530, loss: 0.003231559181585908
2023-01-24 06:48:40.817274: step: 204/530, loss: 0.006389062386006117
2023-01-24 06:48:41.880927: step: 208/530, loss: 0.004245605319738388
2023-01-24 06:48:42.949663: step: 212/530, loss: 0.004515692126005888
2023-01-24 06:48:44.007384: step: 216/530, loss: 0.004583229776471853
2023-01-24 06:48:45.074348: step: 220/530, loss: 0.007102194242179394
2023-01-24 06:48:46.137900: step: 224/530, loss: 0.006297165062278509
2023-01-24 06:48:47.203462: step: 228/530, loss: 0.009628817439079285
2023-01-24 06:48:48.273179: step: 232/530, loss: 0.006603987887501717
2023-01-24 06:48:49.344203: step: 236/530, loss: 0.010194784961640835
2023-01-24 06:48:50.397859: step: 240/530, loss: 0.008824080228805542
2023-01-24 06:48:51.447725: step: 244/530, loss: 0.01042764913290739
2023-01-24 06:48:52.501687: step: 248/530, loss: 0.004633546806871891
2023-01-24 06:48:53.571025: step: 252/530, loss: 0.010123567655682564
2023-01-24 06:48:54.639862: step: 256/530, loss: 0.020633762702345848
2023-01-24 06:48:55.700866: step: 260/530, loss: 0.0023980350233614445
2023-01-24 06:48:56.753455: step: 264/530, loss: 0.0012815964873880148
2023-01-24 06:48:57.814618: step: 268/530, loss: 0.010310189798474312
2023-01-24 06:48:58.878235: step: 272/530, loss: 0.002342581283301115
2023-01-24 06:48:59.952559: step: 276/530, loss: 0.0034466953948140144
2023-01-24 06:49:01.023345: step: 280/530, loss: 0.002751181134954095
2023-01-24 06:49:02.104114: step: 284/530, loss: 0.004417013842612505
2023-01-24 06:49:03.149879: step: 288/530, loss: 0.005342142190784216
2023-01-24 06:49:04.210707: step: 292/530, loss: 0.005873918998986483
2023-01-24 06:49:05.267761: step: 296/530, loss: 0.011275001801550388
2023-01-24 06:49:06.332198: step: 300/530, loss: 0.011495187878608704
2023-01-24 06:49:07.394292: step: 304/530, loss: 0.009805244393646717
2023-01-24 06:49:08.472898: step: 308/530, loss: 0.003248715540394187
2023-01-24 06:49:09.527028: step: 312/530, loss: 0.0065356031991541386
2023-01-24 06:49:10.602785: step: 316/530, loss: 0.003382806433364749
2023-01-24 06:49:11.657494: step: 320/530, loss: 0.00671713100746274
2023-01-24 06:49:12.732320: step: 324/530, loss: 0.0053423685021698475
2023-01-24 06:49:13.806298: step: 328/530, loss: 0.001692821504548192
2023-01-24 06:49:14.865667: step: 332/530, loss: 0.012422880157828331
2023-01-24 06:49:15.922188: step: 336/530, loss: 0.001950218342244625
2023-01-24 06:49:16.985853: step: 340/530, loss: 0.0024267653934657574
2023-01-24 06:49:18.055286: step: 344/530, loss: 0.005435770843178034
2023-01-24 06:49:19.123318: step: 348/530, loss: 0.022459276020526886
2023-01-24 06:49:20.189852: step: 352/530, loss: 0.0018614979926496744
2023-01-24 06:49:21.259204: step: 356/530, loss: 0.0009028096683323383
2023-01-24 06:49:22.311734: step: 360/530, loss: 0.002556337509304285
2023-01-24 06:49:23.367228: step: 364/530, loss: 0.0510033443570137
2023-01-24 06:49:24.428449: step: 368/530, loss: 0.0023674292024224997
2023-01-24 06:49:25.488658: step: 372/530, loss: 0.05592985451221466
2023-01-24 06:49:26.553533: step: 376/530, loss: 0.0016794638941064477
2023-01-24 06:49:27.617682: step: 380/530, loss: 0.024966318160295486
2023-01-24 06:49:28.703978: step: 384/530, loss: 0.0001337281719315797
2023-01-24 06:49:29.766150: step: 388/530, loss: 0.0019478683825582266
2023-01-24 06:49:30.842672: step: 392/530, loss: 0.004590095020830631
2023-01-24 06:49:31.908911: step: 396/530, loss: 0.01947448030114174
2023-01-24 06:49:32.954761: step: 400/530, loss: 0.015301542356610298
2023-01-24 06:49:34.031209: step: 404/530, loss: 0.035488683730363846
2023-01-24 06:49:35.086717: step: 408/530, loss: 0.0064904834143817425
2023-01-24 06:49:36.144934: step: 412/530, loss: 0.011119185015559196
2023-01-24 06:49:37.216174: step: 416/530, loss: 0.003027132246643305
2023-01-24 06:49:38.284850: step: 420/530, loss: 0.003070536069571972
2023-01-24 06:49:39.346853: step: 424/530, loss: 0.0030290079303085804
2023-01-24 06:49:40.401616: step: 428/530, loss: 0.0005432139150798321
2023-01-24 06:49:41.461309: step: 432/530, loss: 0.021225526928901672
2023-01-24 06:49:42.534300: step: 436/530, loss: 0.00808823574334383
2023-01-24 06:49:43.590812: step: 440/530, loss: 0.008005386218428612
2023-01-24 06:49:44.656600: step: 444/530, loss: 0.009824836626648903
2023-01-24 06:49:45.712013: step: 448/530, loss: 0.0042246426455676556
2023-01-24 06:49:46.796613: step: 452/530, loss: 0.031005358323454857
2023-01-24 06:49:47.849410: step: 456/530, loss: 0.03189140185713768
2023-01-24 06:49:48.902279: step: 460/530, loss: 0.001855664188042283
2023-01-24 06:49:49.966201: step: 464/530, loss: 0.005303407087922096
2023-01-24 06:49:51.026374: step: 468/530, loss: 0.05523635819554329
2023-01-24 06:49:52.108522: step: 472/530, loss: 0.012483274564146996
2023-01-24 06:49:53.172342: step: 476/530, loss: 0.008177315816283226
2023-01-24 06:49:54.241275: step: 480/530, loss: 0.015551341697573662
2023-01-24 06:49:55.316032: step: 484/530, loss: 0.00317129073664546
2023-01-24 06:49:56.400176: step: 488/530, loss: 0.001939623849466443
2023-01-24 06:49:57.444974: step: 492/530, loss: 0.0018678940832614899
2023-01-24 06:49:58.495717: step: 496/530, loss: 0.009696511551737785
2023-01-24 06:49:59.541373: step: 500/530, loss: 0.003025406738743186
2023-01-24 06:50:00.590840: step: 504/530, loss: 0.00014251504035200924
2023-01-24 06:50:01.664891: step: 508/530, loss: 0.0023462758399546146
2023-01-24 06:50:02.722991: step: 512/530, loss: 0.027908792719244957
2023-01-24 06:50:03.796367: step: 516/530, loss: 0.007968349382281303
2023-01-24 06:50:04.862659: step: 520/530, loss: 0.0037046605721116066
2023-01-24 06:50:05.924834: step: 524/530, loss: 0.0023662070743739605
2023-01-24 06:50:06.978440: step: 528/530, loss: 0.0029715863056480885
2023-01-24 06:50:08.037960: step: 532/530, loss: 0.04702230542898178
2023-01-24 06:50:09.096716: step: 536/530, loss: 0.00636184262111783
2023-01-24 06:50:10.153889: step: 540/530, loss: 3.735798236448318e-05
2023-01-24 06:50:11.231139: step: 544/530, loss: 0.006046726834028959
2023-01-24 06:50:12.309070: step: 548/530, loss: 0.006030308548361063
2023-01-24 06:50:13.371529: step: 552/530, loss: 0.007691062521189451
2023-01-24 06:50:14.455514: step: 556/530, loss: 0.02658338099718094
2023-01-24 06:50:15.523198: step: 560/530, loss: 0.036318786442279816
2023-01-24 06:50:16.587087: step: 564/530, loss: 0.004370391834527254
2023-01-24 06:50:17.641161: step: 568/530, loss: 0.0057694693095982075
2023-01-24 06:50:18.704272: step: 572/530, loss: 0.003114042803645134
2023-01-24 06:50:19.784341: step: 576/530, loss: 0.0017646457999944687
2023-01-24 06:50:20.850381: step: 580/530, loss: 0.003796191653236747
2023-01-24 06:50:21.919825: step: 584/530, loss: 0.006735880393534899
2023-01-24 06:50:22.981531: step: 588/530, loss: 0.010164310224354267
2023-01-24 06:50:24.044629: step: 592/530, loss: 0.00375041039660573
2023-01-24 06:50:25.096406: step: 596/530, loss: 0.0026225331239402294
2023-01-24 06:50:26.159473: step: 600/530, loss: 0.050829388201236725
2023-01-24 06:50:27.225039: step: 604/530, loss: 0.024402683600783348
2023-01-24 06:50:28.285250: step: 608/530, loss: 0.0009690559236332774
2023-01-24 06:50:29.343503: step: 612/530, loss: 0.006643539760261774
2023-01-24 06:50:30.390099: step: 616/530, loss: 0.012132334522902966
2023-01-24 06:50:31.463351: step: 620/530, loss: 0.0003877042618114501
2023-01-24 06:50:32.535127: step: 624/530, loss: 0.0047241211868822575
2023-01-24 06:50:33.581162: step: 628/530, loss: 4.4548753066919744e-05
2023-01-24 06:50:34.639816: step: 632/530, loss: 0.0058892713859677315
2023-01-24 06:50:35.707762: step: 636/530, loss: 0.0022245515137910843
2023-01-24 06:50:36.759808: step: 640/530, loss: 0.004287480376660824
2023-01-24 06:50:37.816851: step: 644/530, loss: 0.003160599386319518
2023-01-24 06:50:38.871613: step: 648/530, loss: 0.0025158494245260954
2023-01-24 06:50:39.934271: step: 652/530, loss: 0.009907666593790054
2023-01-24 06:50:40.988317: step: 656/530, loss: 0.0027273886371403933
2023-01-24 06:50:42.046659: step: 660/530, loss: 0.001808274770155549
2023-01-24 06:50:43.098297: step: 664/530, loss: 0.005245785228908062
2023-01-24 06:50:44.166034: step: 668/530, loss: 0.004788743332028389
2023-01-24 06:50:45.238881: step: 672/530, loss: 0.018536105751991272
2023-01-24 06:50:46.296682: step: 676/530, loss: 0.007577091455459595
2023-01-24 06:50:47.346413: step: 680/530, loss: 0.0031659400556236506
2023-01-24 06:50:48.397535: step: 684/530, loss: 0.005192521959543228
2023-01-24 06:50:49.445798: step: 688/530, loss: 0.005204837769269943
2023-01-24 06:50:50.521319: step: 692/530, loss: 0.008573825471103191
2023-01-24 06:50:51.563932: step: 696/530, loss: 0.005474900361150503
2023-01-24 06:50:52.605666: step: 700/530, loss: 0.0
2023-01-24 06:50:53.668395: step: 704/530, loss: 0.015217592008411884
2023-01-24 06:50:54.716110: step: 708/530, loss: 0.009809939190745354
2023-01-24 06:50:55.759972: step: 712/530, loss: 0.00041440516361035407
2023-01-24 06:50:56.818015: step: 716/530, loss: 0.02617962658405304
2023-01-24 06:50:57.862274: step: 720/530, loss: 0.0044184052385389805
2023-01-24 06:50:58.905964: step: 724/530, loss: 0.011346045881509781
2023-01-24 06:50:59.970617: step: 728/530, loss: 0.001319524715654552
2023-01-24 06:51:01.024918: step: 732/530, loss: 0.0015738967340439558
2023-01-24 06:51:02.104331: step: 736/530, loss: 0.008715679869055748
2023-01-24 06:51:03.143087: step: 740/530, loss: 0.007780200801789761
2023-01-24 06:51:04.197993: step: 744/530, loss: 0.005790016148239374
2023-01-24 06:51:05.256635: step: 748/530, loss: 0.01184441801160574
2023-01-24 06:51:06.325529: step: 752/530, loss: 0.003115267725661397
2023-01-24 06:51:07.381550: step: 756/530, loss: 0.005785453598946333
2023-01-24 06:51:08.446400: step: 760/530, loss: 0.002017201855778694
2023-01-24 06:51:09.504835: step: 764/530, loss: 0.012541850097477436
2023-01-24 06:51:10.559828: step: 768/530, loss: 0.0011365872342139482
2023-01-24 06:51:11.626159: step: 772/530, loss: 0.0036238234024494886
2023-01-24 06:51:12.702264: step: 776/530, loss: 0.001991682220250368
2023-01-24 06:51:13.761231: step: 780/530, loss: 0.0025727893225848675
2023-01-24 06:51:14.830336: step: 784/530, loss: 0.01745470240712166
2023-01-24 06:51:15.893166: step: 788/530, loss: 0.009576544165611267
2023-01-24 06:51:16.954907: step: 792/530, loss: 0.04621589183807373
2023-01-24 06:51:18.005329: step: 796/530, loss: 0.0475594699382782
2023-01-24 06:51:19.064712: step: 800/530, loss: 0.03216009587049484
2023-01-24 06:51:20.118655: step: 804/530, loss: 0.004361926577985287
2023-01-24 06:51:21.171467: step: 808/530, loss: 0.0081463772803545
2023-01-24 06:51:22.236480: step: 812/530, loss: 0.004009263124316931
2023-01-24 06:51:23.306505: step: 816/530, loss: 0.010621353052556515
2023-01-24 06:51:24.378147: step: 820/530, loss: 0.006909035611897707
2023-01-24 06:51:25.441995: step: 824/530, loss: 0.02500341273844242
2023-01-24 06:51:26.507982: step: 828/530, loss: 0.0038473554886877537
2023-01-24 06:51:27.578168: step: 832/530, loss: 0.04069630801677704
2023-01-24 06:51:28.632544: step: 836/530, loss: 0.00748397596180439
2023-01-24 06:51:29.689976: step: 840/530, loss: 0.005101094022393227
2023-01-24 06:51:30.737180: step: 844/530, loss: 0.001419269130565226
2023-01-24 06:51:31.775596: step: 848/530, loss: 0.003133500926196575
2023-01-24 06:51:32.835710: step: 852/530, loss: 0.002805163152515888
2023-01-24 06:51:33.899815: step: 856/530, loss: 0.05616255849599838
2023-01-24 06:51:34.967756: step: 860/530, loss: 0.0016153290634974837
2023-01-24 06:51:36.037173: step: 864/530, loss: 0.010885132476687431
2023-01-24 06:51:37.095542: step: 868/530, loss: 0.0019322059815749526
2023-01-24 06:51:38.160171: step: 872/530, loss: 0.018347369506955147
2023-01-24 06:51:39.218496: step: 876/530, loss: 0.001710647949948907
2023-01-24 06:51:40.268189: step: 880/530, loss: 0.01850125752389431
2023-01-24 06:51:41.341256: step: 884/530, loss: 0.006420777644962072
2023-01-24 06:51:42.412310: step: 888/530, loss: 0.0037274400237947702
2023-01-24 06:51:43.474443: step: 892/530, loss: 0.005759004037827253
2023-01-24 06:51:44.539309: step: 896/530, loss: 0.00858496967703104
2023-01-24 06:51:45.593303: step: 900/530, loss: 0.002263988833874464
2023-01-24 06:51:46.660098: step: 904/530, loss: 0.004606558941304684
2023-01-24 06:51:47.708394: step: 908/530, loss: 0.011999404057860374
2023-01-24 06:51:48.754501: step: 912/530, loss: 0.00040746081504039466
2023-01-24 06:51:49.826763: step: 916/530, loss: 0.012960116378962994
2023-01-24 06:51:50.905255: step: 920/530, loss: 0.010739731602370739
2023-01-24 06:51:51.968983: step: 924/530, loss: 0.0057163783349096775
2023-01-24 06:51:53.032577: step: 928/530, loss: 0.013862252235412598
2023-01-24 06:51:54.103976: step: 932/530, loss: 0.00449756346642971
2023-01-24 06:51:55.166129: step: 936/530, loss: 0.009259038604795933
2023-01-24 06:51:56.219694: step: 940/530, loss: 0.0039864107966423035
2023-01-24 06:51:57.261947: step: 944/530, loss: 0.007436931598931551
2023-01-24 06:51:58.329711: step: 948/530, loss: 0.007982431910932064
2023-01-24 06:51:59.386264: step: 952/530, loss: 0.007112680934369564
2023-01-24 06:52:00.440868: step: 956/530, loss: 0.0008695446304045618
2023-01-24 06:52:01.484351: step: 960/530, loss: 0.009062324650585651
2023-01-24 06:52:02.561280: step: 964/530, loss: 0.006572019774466753
2023-01-24 06:52:03.625192: step: 968/530, loss: 0.0035677673295140266
2023-01-24 06:52:04.691385: step: 972/530, loss: 0.00997459888458252
2023-01-24 06:52:05.746980: step: 976/530, loss: 0.0007607873412780464
2023-01-24 06:52:06.808257: step: 980/530, loss: 2.6377915673947427e-06
2023-01-24 06:52:07.875578: step: 984/530, loss: 0.017499951645731926
2023-01-24 06:52:08.947296: step: 988/530, loss: 0.00032129904138855636
2023-01-24 06:52:09.995042: step: 992/530, loss: 0.0006807407480664551
2023-01-24 06:52:11.053538: step: 996/530, loss: 0.0020977805834263563
2023-01-24 06:52:12.117798: step: 1000/530, loss: 0.0011637582210823894
2023-01-24 06:52:13.160286: step: 1004/530, loss: 0.016961470246315002
2023-01-24 06:52:14.217286: step: 1008/530, loss: 0.0008916959050111473
2023-01-24 06:52:15.264088: step: 1012/530, loss: 0.003647858975455165
2023-01-24 06:52:16.317483: step: 1016/530, loss: 0.006677701137959957
2023-01-24 06:52:17.370571: step: 1020/530, loss: 0.008406870067119598
2023-01-24 06:52:18.435274: step: 1024/530, loss: 0.006686127278953791
2023-01-24 06:52:19.516707: step: 1028/530, loss: 0.013231586664915085
2023-01-24 06:52:20.601770: step: 1032/530, loss: 0.0056766970083117485
2023-01-24 06:52:21.662189: step: 1036/530, loss: 0.0028293116483837366
2023-01-24 06:52:22.731265: step: 1040/530, loss: 0.0027113750111311674
2023-01-24 06:52:23.777534: step: 1044/530, loss: 0.002102357568219304
2023-01-24 06:52:24.840618: step: 1048/530, loss: 0.01977359689772129
2023-01-24 06:52:25.896626: step: 1052/530, loss: 0.005200549028813839
2023-01-24 06:52:26.946148: step: 1056/530, loss: 0.006588608957827091
2023-01-24 06:52:27.986259: step: 1060/530, loss: 0.00048009876627475023
2023-01-24 06:52:29.046384: step: 1064/530, loss: 0.002921079285442829
2023-01-24 06:52:30.112250: step: 1068/530, loss: 0.011613957583904266
2023-01-24 06:52:31.187171: step: 1072/530, loss: 0.03153498098254204
2023-01-24 06:52:32.252484: step: 1076/530, loss: 0.0016926953103393316
2023-01-24 06:52:33.311289: step: 1080/530, loss: 0.0016742394072934985
2023-01-24 06:52:34.371698: step: 1084/530, loss: 0.0006963239284232259
2023-01-24 06:52:35.441135: step: 1088/530, loss: 0.004912762902677059
2023-01-24 06:52:36.503132: step: 1092/530, loss: 0.005121821537613869
2023-01-24 06:52:37.558075: step: 1096/530, loss: 0.006460888776928186
2023-01-24 06:52:38.618171: step: 1100/530, loss: 0.009416701272130013
2023-01-24 06:52:39.672598: step: 1104/530, loss: 0.004715762101113796
2023-01-24 06:52:40.734081: step: 1108/530, loss: 0.005383270792663097
2023-01-24 06:52:41.792937: step: 1112/530, loss: 0.00024060183204710484
2023-01-24 06:52:42.851593: step: 1116/530, loss: 0.015338758006691933
2023-01-24 06:52:43.903376: step: 1120/530, loss: 0.006366773042827845
2023-01-24 06:52:44.969368: step: 1124/530, loss: 0.008398651145398617
2023-01-24 06:52:46.026329: step: 1128/530, loss: 0.024653512984514236
2023-01-24 06:52:47.058113: step: 1132/530, loss: 0.022243818268179893
2023-01-24 06:52:48.110239: step: 1136/530, loss: 0.02027847059071064
2023-01-24 06:52:49.164494: step: 1140/530, loss: 0.015282757580280304
2023-01-24 06:52:50.207707: step: 1144/530, loss: 0.002276965416967869
2023-01-24 06:52:51.278807: step: 1148/530, loss: 0.006992966402322054
2023-01-24 06:52:52.329599: step: 1152/530, loss: 0.018796036019921303
2023-01-24 06:52:53.376245: step: 1156/530, loss: 0.02710900828242302
2023-01-24 06:52:54.452379: step: 1160/530, loss: 0.0007463073707185686
2023-01-24 06:52:55.513741: step: 1164/530, loss: 0.008168252184987068
2023-01-24 06:52:56.570854: step: 1168/530, loss: 9.817934187594801e-05
2023-01-24 06:52:57.634069: step: 1172/530, loss: 0.0032565046567469835
2023-01-24 06:52:58.688359: step: 1176/530, loss: 0.002056768862530589
2023-01-24 06:52:59.761990: step: 1180/530, loss: 0.007122029550373554
2023-01-24 06:53:00.809581: step: 1184/530, loss: 0.02258075401186943
2023-01-24 06:53:01.863940: step: 1188/530, loss: 0.005497555714100599
2023-01-24 06:53:02.932412: step: 1192/530, loss: 0.004634596407413483
2023-01-24 06:53:03.984844: step: 1196/530, loss: 0.013754631392657757
2023-01-24 06:53:05.044981: step: 1200/530, loss: 0.0027307530399411917
2023-01-24 06:53:06.108139: step: 1204/530, loss: 0.010373775847256184
2023-01-24 06:53:07.164722: step: 1208/530, loss: 0.005817357916384935
2023-01-24 06:53:08.233573: step: 1212/530, loss: 0.006713941227644682
2023-01-24 06:53:09.292321: step: 1216/530, loss: 0.0033358752261847258
2023-01-24 06:53:10.346827: step: 1220/530, loss: 0.03016490489244461
2023-01-24 06:53:11.401731: step: 1224/530, loss: 0.0023159629199653864
2023-01-24 06:53:12.480134: step: 1228/530, loss: 0.0030180870089679956
2023-01-24 06:53:13.519381: step: 1232/530, loss: 0.0021962819155305624
2023-01-24 06:53:14.572691: step: 1236/530, loss: 0.0034712275955826044
2023-01-24 06:53:15.617531: step: 1240/530, loss: 0.00037702632835134864
2023-01-24 06:53:16.685826: step: 1244/530, loss: 0.0068137929774820805
2023-01-24 06:53:17.744543: step: 1248/530, loss: 0.0032415043096989393
2023-01-24 06:53:18.828062: step: 1252/530, loss: 0.0017898931400850415
2023-01-24 06:53:19.879215: step: 1256/530, loss: 0.008937662467360497
2023-01-24 06:53:20.946125: step: 1260/530, loss: 0.0034522786736488342
2023-01-24 06:53:22.005730: step: 1264/530, loss: 0.005720811430364847
2023-01-24 06:53:23.072172: step: 1268/530, loss: 0.0021059010177850723
2023-01-24 06:53:24.132639: step: 1272/530, loss: 0.007279111072421074
2023-01-24 06:53:25.188633: step: 1276/530, loss: 0.0011908162850886583
2023-01-24 06:53:26.232363: step: 1280/530, loss: 0.008065180853009224
2023-01-24 06:53:27.294952: step: 1284/530, loss: 0.0037832267116755247
2023-01-24 06:53:28.353360: step: 1288/530, loss: 0.0033239414915442467
2023-01-24 06:53:29.417657: step: 1292/530, loss: 0.0021119078155606985
2023-01-24 06:53:30.460178: step: 1296/530, loss: 0.0018069943180307746
2023-01-24 06:53:31.512699: step: 1300/530, loss: 0.006026848219335079
2023-01-24 06:53:32.568789: step: 1304/530, loss: 0.028940873220562935
2023-01-24 06:53:33.625014: step: 1308/530, loss: 0.008290654048323631
2023-01-24 06:53:34.663480: step: 1312/530, loss: 0.002408804837614298
2023-01-24 06:53:35.733371: step: 1316/530, loss: 0.0018591956468299031
2023-01-24 06:53:36.806124: step: 1320/530, loss: 0.010862033814191818
2023-01-24 06:53:37.892767: step: 1324/530, loss: 0.004676288925111294
2023-01-24 06:53:38.928788: step: 1328/530, loss: 0.0024421392008662224
2023-01-24 06:53:39.984712: step: 1332/530, loss: 0.03992559388279915
2023-01-24 06:53:41.055420: step: 1336/530, loss: 0.01180842611938715
2023-01-24 06:53:42.100117: step: 1340/530, loss: 0.0010115193435922265
2023-01-24 06:53:43.169680: step: 1344/530, loss: 0.004760029260069132
2023-01-24 06:53:44.254586: step: 1348/530, loss: 0.016330109909176826
2023-01-24 06:53:45.311713: step: 1352/530, loss: 0.003918833564966917
2023-01-24 06:53:46.379124: step: 1356/530, loss: 0.0017765170196071267
2023-01-24 06:53:47.436569: step: 1360/530, loss: 0.002537443535402417
2023-01-24 06:53:48.494708: step: 1364/530, loss: 7.210003968793899e-05
2023-01-24 06:53:49.550639: step: 1368/530, loss: 0.004111791029572487
2023-01-24 06:53:50.615680: step: 1372/530, loss: 0.0003961895708926022
2023-01-24 06:53:51.663733: step: 1376/530, loss: 0.0004833767598029226
2023-01-24 06:53:52.729105: step: 1380/530, loss: 0.017606612294912338
2023-01-24 06:53:53.796879: step: 1384/530, loss: 0.008703544735908508
2023-01-24 06:53:54.859402: step: 1388/530, loss: 0.06903694570064545
2023-01-24 06:53:55.920173: step: 1392/530, loss: 0.0013172316830605268
2023-01-24 06:53:56.977967: step: 1396/530, loss: 0.01568344421684742
2023-01-24 06:53:58.034689: step: 1400/530, loss: 0.0026344992220401764
2023-01-24 06:53:59.108202: step: 1404/530, loss: 0.0025941431522369385
2023-01-24 06:54:00.171262: step: 1408/530, loss: 0.0031603167299181223
2023-01-24 06:54:01.220757: step: 1412/530, loss: 0.002356140874326229
2023-01-24 06:54:02.308292: step: 1416/530, loss: 0.0015014453092589974
2023-01-24 06:54:03.375574: step: 1420/530, loss: 0.005683632101863623
2023-01-24 06:54:04.435374: step: 1424/530, loss: 0.010207446292042732
2023-01-24 06:54:05.504567: step: 1428/530, loss: 0.02254438027739525
2023-01-24 06:54:06.560371: step: 1432/530, loss: 0.002547829644754529
2023-01-24 06:54:07.621720: step: 1436/530, loss: 0.007191289681941271
2023-01-24 06:54:08.681407: step: 1440/530, loss: 0.005497679114341736
2023-01-24 06:54:09.745970: step: 1444/530, loss: 0.007208880037069321
2023-01-24 06:54:10.808088: step: 1448/530, loss: 0.002145032398402691
2023-01-24 06:54:11.886430: step: 1452/530, loss: 0.018444523215293884
2023-01-24 06:54:12.939263: step: 1456/530, loss: 0.008600176312029362
2023-01-24 06:54:14.010643: step: 1460/530, loss: 0.0028127594850957394
2023-01-24 06:54:15.073654: step: 1464/530, loss: 0.0006874918472021818
2023-01-24 06:54:16.151382: step: 1468/530, loss: 0.0009059992735274136
2023-01-24 06:54:17.221101: step: 1472/530, loss: 0.0056143710389733315
2023-01-24 06:54:18.308384: step: 1476/530, loss: 0.006656808778643608
2023-01-24 06:54:19.358402: step: 1480/530, loss: 0.010336926206946373
2023-01-24 06:54:20.412370: step: 1484/530, loss: 0.028912924230098724
2023-01-24 06:54:21.477674: step: 1488/530, loss: 0.0036904446315020323
2023-01-24 06:54:22.528057: step: 1492/530, loss: 0.0042575360275805
2023-01-24 06:54:23.599198: step: 1496/530, loss: 0.01029388327151537
2023-01-24 06:54:24.671654: step: 1500/530, loss: 0.026503583416342735
2023-01-24 06:54:25.740009: step: 1504/530, loss: 0.00550204748287797
2023-01-24 06:54:26.795078: step: 1508/530, loss: 0.001588418148458004
2023-01-24 06:54:27.860169: step: 1512/530, loss: 0.008536091074347496
2023-01-24 06:54:28.899995: step: 1516/530, loss: 0.006836900487542152
2023-01-24 06:54:29.957671: step: 1520/530, loss: 0.005467474926263094
2023-01-24 06:54:31.032165: step: 1524/530, loss: 0.01290533784776926
2023-01-24 06:54:32.104219: step: 1528/530, loss: 0.0031274205539375544
2023-01-24 06:54:33.163674: step: 1532/530, loss: 0.006203757598996162
2023-01-24 06:54:34.213202: step: 1536/530, loss: 0.00351705146022141
2023-01-24 06:54:35.266750: step: 1540/530, loss: 0.005592579487711191
2023-01-24 06:54:36.322517: step: 1544/530, loss: 0.01513136737048626
2023-01-24 06:54:37.381396: step: 1548/530, loss: 0.01994616910815239
2023-01-24 06:54:38.435905: step: 1552/530, loss: 0.02527095191180706
2023-01-24 06:54:39.502727: step: 1556/530, loss: 0.07543681561946869
2023-01-24 06:54:40.565419: step: 1560/530, loss: 0.005595947150141001
2023-01-24 06:54:41.637153: step: 1564/530, loss: 0.0009166815434582531
2023-01-24 06:54:42.695873: step: 1568/530, loss: 0.013642624020576477
2023-01-24 06:54:43.753018: step: 1572/530, loss: 0.022438788786530495
2023-01-24 06:54:44.811255: step: 1576/530, loss: 0.0005717214662581682
2023-01-24 06:54:45.876074: step: 1580/530, loss: 0.005219507496803999
2023-01-24 06:54:46.944501: step: 1584/530, loss: 0.005995392799377441
2023-01-24 06:54:47.987546: step: 1588/530, loss: 0.01081122923642397
2023-01-24 06:54:49.060011: step: 1592/530, loss: 0.004115510266274214
2023-01-24 06:54:50.115848: step: 1596/530, loss: 0.0038880843203514814
2023-01-24 06:54:51.170100: step: 1600/530, loss: 0.005178489722311497
2023-01-24 06:54:52.243917: step: 1604/530, loss: 0.006016201805323362
2023-01-24 06:54:53.294706: step: 1608/530, loss: 0.009906507097184658
2023-01-24 06:54:54.346640: step: 1612/530, loss: 0.0063696312718093395
2023-01-24 06:54:55.399357: step: 1616/530, loss: 3.598132389015518e-05
2023-01-24 06:54:56.448214: step: 1620/530, loss: 0.0108889639377594
2023-01-24 06:54:57.505719: step: 1624/530, loss: 0.0015007598558440804
2023-01-24 06:54:58.566998: step: 1628/530, loss: 0.0036919787526130676
2023-01-24 06:54:59.617461: step: 1632/530, loss: 0.006333977449685335
2023-01-24 06:55:00.664049: step: 1636/530, loss: 0.004862017463892698
2023-01-24 06:55:01.724982: step: 1640/530, loss: 0.006857108324766159
2023-01-24 06:55:02.805914: step: 1644/530, loss: 0.0006810321356169879
2023-01-24 06:55:03.860107: step: 1648/530, loss: 0.0006151502020657063
2023-01-24 06:55:04.906269: step: 1652/530, loss: 0.0008619756554253399
2023-01-24 06:55:05.986354: step: 1656/530, loss: 0.0022198238875716925
2023-01-24 06:55:07.064709: step: 1660/530, loss: 0.0010134903714060783
2023-01-24 06:55:08.140497: step: 1664/530, loss: 0.006010419689118862
2023-01-24 06:55:09.193646: step: 1668/530, loss: 0.05877001956105232
2023-01-24 06:55:10.254441: step: 1672/530, loss: 0.010641299188137054
2023-01-24 06:55:11.319136: step: 1676/530, loss: 0.002878132276237011
2023-01-24 06:55:12.381202: step: 1680/530, loss: 0.02457360364496708
2023-01-24 06:55:13.431301: step: 1684/530, loss: 0.009073033928871155
2023-01-24 06:55:14.482776: step: 1688/530, loss: 0.0010165708372369409
2023-01-24 06:55:15.547651: step: 1692/530, loss: 0.005371278617531061
2023-01-24 06:55:16.603975: step: 1696/530, loss: 0.004141046199947596
2023-01-24 06:55:17.660629: step: 1700/530, loss: 0.0
2023-01-24 06:55:18.730031: step: 1704/530, loss: 0.009293717332184315
2023-01-24 06:55:19.787683: step: 1708/530, loss: 0.005547970533370972
2023-01-24 06:55:20.849264: step: 1712/530, loss: 0.008700049482285976
2023-01-24 06:55:21.891200: step: 1716/530, loss: 0.008054769597947598
2023-01-24 06:55:22.973906: step: 1720/530, loss: 0.001258236006833613
2023-01-24 06:55:24.007621: step: 1724/530, loss: 0.008488127961754799
2023-01-24 06:55:25.084542: step: 1728/530, loss: 0.029200317338109016
2023-01-24 06:55:26.137689: step: 1732/530, loss: 0.016749313101172447
2023-01-24 06:55:27.197482: step: 1736/530, loss: 0.007692796643823385
2023-01-24 06:55:28.242199: step: 1740/530, loss: 0.013126224279403687
2023-01-24 06:55:29.290925: step: 1744/530, loss: 0.001301880576647818
2023-01-24 06:55:30.344725: step: 1748/530, loss: 0.005355332046747208
2023-01-24 06:55:31.386603: step: 1752/530, loss: 0.02250639535486698
2023-01-24 06:55:32.447854: step: 1756/530, loss: 0.008386602625250816
2023-01-24 06:55:33.499675: step: 1760/530, loss: 0.005702165886759758
2023-01-24 06:55:34.550661: step: 1764/530, loss: 0.008322526700794697
2023-01-24 06:55:35.596320: step: 1768/530, loss: 0.0058671566657722
2023-01-24 06:55:36.652197: step: 1772/530, loss: 0.00073309923755005
2023-01-24 06:55:37.708636: step: 1776/530, loss: 0.010479552671313286
2023-01-24 06:55:38.754046: step: 1780/530, loss: 0.005352622829377651
2023-01-24 06:55:39.818669: step: 1784/530, loss: 0.032972633838653564
2023-01-24 06:55:40.883314: step: 1788/530, loss: 0.0074201771058142185
2023-01-24 06:55:41.951163: step: 1792/530, loss: 0.016771988943219185
2023-01-24 06:55:43.031564: step: 1796/530, loss: 0.031335145235061646
2023-01-24 06:55:44.087356: step: 1800/530, loss: 0.0029944139532744884
2023-01-24 06:55:45.144763: step: 1804/530, loss: 0.004832638893276453
2023-01-24 06:55:46.203898: step: 1808/530, loss: 0.01707667112350464
2023-01-24 06:55:47.277136: step: 1812/530, loss: 0.002868467476218939
2023-01-24 06:55:48.323179: step: 1816/530, loss: 0.009555457159876823
2023-01-24 06:55:49.384710: step: 1820/530, loss: 0.0014934046193957329
2023-01-24 06:55:50.442275: step: 1824/530, loss: 0.016105249524116516
2023-01-24 06:55:51.499107: step: 1828/530, loss: 0.0009161548223346472
2023-01-24 06:55:52.542356: step: 1832/530, loss: 0.006872161291539669
2023-01-24 06:55:53.589845: step: 1836/530, loss: 0.018346259370446205
2023-01-24 06:55:54.656240: step: 1840/530, loss: 0.0011875653872266412
2023-01-24 06:55:55.727529: step: 1844/530, loss: 0.007434564642608166
2023-01-24 06:55:56.806141: step: 1848/530, loss: 0.015627963468432426
2023-01-24 06:55:57.889544: step: 1852/530, loss: 0.0075806668028235435
2023-01-24 06:55:58.939476: step: 1856/530, loss: 0.005289080552756786
2023-01-24 06:55:59.984140: step: 1860/530, loss: 0.006550746038556099
2023-01-24 06:56:01.050777: step: 1864/530, loss: 0.01285226084291935
2023-01-24 06:56:02.148899: step: 1868/530, loss: 0.028356308117508888
2023-01-24 06:56:03.207884: step: 1872/530, loss: 0.006177104078233242
2023-01-24 06:56:04.254483: step: 1876/530, loss: 0.005874236114323139
2023-01-24 06:56:05.301605: step: 1880/530, loss: 0.002133819507434964
2023-01-24 06:56:06.368793: step: 1884/530, loss: 0.0016121327644214034
2023-01-24 06:56:07.435822: step: 1888/530, loss: 0.0014566682511940598
2023-01-24 06:56:08.494309: step: 1892/530, loss: 0.003723465371876955
2023-01-24 06:56:09.538664: step: 1896/530, loss: 0.002977007068693638
2023-01-24 06:56:10.609376: step: 1900/530, loss: 0.0012824763543903828
2023-01-24 06:56:11.652019: step: 1904/530, loss: 0.0015486414777114987
2023-01-24 06:56:12.717549: step: 1908/530, loss: 0.008708218112587929
2023-01-24 06:56:13.780609: step: 1912/530, loss: 0.015091648325324059
2023-01-24 06:56:14.825768: step: 1916/530, loss: 0.011505119502544403
2023-01-24 06:56:15.866039: step: 1920/530, loss: 0.0031264491844922304
2023-01-24 06:56:16.923256: step: 1924/530, loss: 0.012557929381728172
2023-01-24 06:56:17.998908: step: 1928/530, loss: 0.007312506437301636
2023-01-24 06:56:19.053912: step: 1932/530, loss: 0.004234807565808296
2023-01-24 06:56:20.113996: step: 1936/530, loss: 0.007357989903539419
2023-01-24 06:56:21.179976: step: 1940/530, loss: 0.01080083567649126
2023-01-24 06:56:22.220253: step: 1944/530, loss: 0.0027293264865875244
2023-01-24 06:56:23.297455: step: 1948/530, loss: 0.009540950879454613
2023-01-24 06:56:24.369081: step: 1952/530, loss: 0.005311830434948206
2023-01-24 06:56:25.439058: step: 1956/530, loss: 0.0022345108445733786
2023-01-24 06:56:26.498237: step: 1960/530, loss: 0.008572908118367195
2023-01-24 06:56:27.559935: step: 1964/530, loss: 0.003876825561746955
2023-01-24 06:56:28.647006: step: 1968/530, loss: 0.0035365927033126354
2023-01-24 06:56:29.692544: step: 1972/530, loss: 0.0030830225441604853
2023-01-24 06:56:30.734471: step: 1976/530, loss: 0.0024644872173666954
2023-01-24 06:56:31.806005: step: 1980/530, loss: 0.006964856758713722
2023-01-24 06:56:32.873530: step: 1984/530, loss: 0.017210956662893295
2023-01-24 06:56:33.937536: step: 1988/530, loss: 0.0011903017293661833
2023-01-24 06:56:34.999042: step: 1992/530, loss: 0.002029990078881383
2023-01-24 06:56:36.057064: step: 1996/530, loss: 0.00775444321334362
2023-01-24 06:56:37.110943: step: 2000/530, loss: 0.012881227768957615
2023-01-24 06:56:38.173768: step: 2004/530, loss: 0.005271740257740021
2023-01-24 06:56:39.229473: step: 2008/530, loss: 0.015584379434585571
2023-01-24 06:56:40.278561: step: 2012/530, loss: 0.002974665490910411
2023-01-24 06:56:41.329587: step: 2016/530, loss: 0.003269895678386092
2023-01-24 06:56:42.386303: step: 2020/530, loss: 0.010840609669685364
2023-01-24 06:56:43.451868: step: 2024/530, loss: 0.016084840521216393
2023-01-24 06:56:44.529953: step: 2028/530, loss: 0.004212565254420042
2023-01-24 06:56:45.586217: step: 2032/530, loss: 0.00749535858631134
2023-01-24 06:56:46.653327: step: 2036/530, loss: 0.029413238167762756
2023-01-24 06:56:47.720373: step: 2040/530, loss: 0.006110089831054211
2023-01-24 06:56:48.772282: step: 2044/530, loss: 0.007431995123624802
2023-01-24 06:56:49.843590: step: 2048/530, loss: 0.005208600778132677
2023-01-24 06:56:50.894336: step: 2052/530, loss: 0.044159021228551865
2023-01-24 06:56:51.961454: step: 2056/530, loss: 0.043648310005664825
2023-01-24 06:56:53.023890: step: 2060/530, loss: 0.013246748596429825
2023-01-24 06:56:54.085099: step: 2064/530, loss: 0.01302739605307579
2023-01-24 06:56:55.151775: step: 2068/530, loss: 0.010749460197985172
2023-01-24 06:56:56.209097: step: 2072/530, loss: 5.5180520575959235e-05
2023-01-24 06:56:57.280574: step: 2076/530, loss: 0.0023341933265328407
2023-01-24 06:56:58.384690: step: 2080/530, loss: 0.0076659321784973145
2023-01-24 06:56:59.444256: step: 2084/530, loss: 0.03867116943001747
2023-01-24 06:57:00.507551: step: 2088/530, loss: 0.021886657923460007
2023-01-24 06:57:01.561289: step: 2092/530, loss: 0.0023359856568276882
2023-01-24 06:57:02.644651: step: 2096/530, loss: 0.006516108289361
2023-01-24 06:57:03.730405: step: 2100/530, loss: 0.018510611727833748
2023-01-24 06:57:04.783403: step: 2104/530, loss: 0.0019100788049399853
2023-01-24 06:57:05.856316: step: 2108/530, loss: 0.019090835005044937
2023-01-24 06:57:06.917499: step: 2112/530, loss: 0.02267684042453766
2023-01-24 06:57:07.975249: step: 2116/530, loss: 0.003943257033824921
2023-01-24 06:57:09.038966: step: 2120/530, loss: 0.008389642462134361
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38298686105111596, 'r': 0.3364761227071474, 'f1': 0.35822811447811453}, 'combined': 0.26395755803650545, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39857660858060795, 'r': 0.300226536333445, 'f1': 0.34248064144704093}, 'combined': 0.2271374202343069, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34921144859813086, 'r': 0.2830729166666667, 'f1': 0.3126830543933054}, 'combined': 0.20845536959553693, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40221081943175957, 'r': 0.2979984840677248, 'f1': 0.34234967706735137}, 'combined': 0.2234282102965872, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3695120604096801, 'r': 0.3309481831373226, 'f1': 0.34916855358031834}, 'combined': 0.2572820921118135, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39820971156216584, 'r': 0.3109828223628343, 'f1': 0.34923204650371764}, 'combined': 0.23161503602319095, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 06:59:37.764925: step: 4/530, loss: 0.001578222494572401
2023-01-24 06:59:38.799787: step: 8/530, loss: 0.000899963139090687
2023-01-24 06:59:39.842767: step: 12/530, loss: 0.008029366843402386
2023-01-24 06:59:40.903105: step: 16/530, loss: 0.022720078006386757
2023-01-24 06:59:41.959995: step: 20/530, loss: 0.01804449036717415
2023-01-24 06:59:43.018020: step: 24/530, loss: 0.003947988618165255
2023-01-24 06:59:44.076757: step: 28/530, loss: 0.00310538406483829
2023-01-24 06:59:45.145470: step: 32/530, loss: 0.004651452414691448
2023-01-24 06:59:46.192140: step: 36/530, loss: 0.0140745360404253
2023-01-24 06:59:47.253138: step: 40/530, loss: 0.0012586034135892987
2023-01-24 06:59:48.308622: step: 44/530, loss: 0.00970130879431963
2023-01-24 06:59:49.360363: step: 48/530, loss: 0.024466238915920258
2023-01-24 06:59:50.423963: step: 52/530, loss: 0.018754877150058746
2023-01-24 06:59:51.479167: step: 56/530, loss: 0.003244738793000579
2023-01-24 06:59:52.522853: step: 60/530, loss: 0.002220563357695937
2023-01-24 06:59:53.565539: step: 64/530, loss: 0.015442682430148125
2023-01-24 06:59:54.623424: step: 68/530, loss: 0.003957618493586779
2023-01-24 06:59:55.671523: step: 72/530, loss: 0.007866286672651768
2023-01-24 06:59:57.015524: step: 76/530, loss: 0.0008116963435895741
2023-01-24 06:59:58.078106: step: 80/530, loss: 0.0035716306883841753
2023-01-24 06:59:59.136041: step: 84/530, loss: 0.0002185688354074955
2023-01-24 07:00:00.191533: step: 88/530, loss: 0.0044698044657707214
2023-01-24 07:00:01.243536: step: 92/530, loss: 0.011758637614548206
2023-01-24 07:00:02.319895: step: 96/530, loss: 0.005662843585014343
2023-01-24 07:00:03.381057: step: 100/530, loss: 0.004792902618646622
2023-01-24 07:00:04.423163: step: 104/530, loss: 1.8417009414406493e-05
2023-01-24 07:00:05.466217: step: 108/530, loss: 0.0015699961222708225
2023-01-24 07:00:06.512713: step: 112/530, loss: 0.002671522554010153
2023-01-24 07:00:07.564814: step: 116/530, loss: 0.002577098784968257
2023-01-24 07:00:08.623034: step: 120/530, loss: 0.003473773133009672
2023-01-24 07:00:09.677097: step: 124/530, loss: 0.011938536539673805
2023-01-24 07:00:10.735156: step: 128/530, loss: 0.006991213653236628
2023-01-24 07:00:11.783000: step: 132/530, loss: 0.000358393182978034
2023-01-24 07:00:12.829750: step: 136/530, loss: 0.010971558280289173
2023-01-24 07:00:13.877693: step: 140/530, loss: 0.004337462596595287
2023-01-24 07:00:14.927902: step: 144/530, loss: 0.0005295031587593257
2023-01-24 07:00:15.971611: step: 148/530, loss: 0.0009479966829530895
2023-01-24 07:00:17.018155: step: 152/530, loss: 0.0017000744119286537
2023-01-24 07:00:18.057571: step: 156/530, loss: 0.0006047465722076595
2023-01-24 07:00:19.123031: step: 160/530, loss: 0.003590860404074192
2023-01-24 07:00:20.185409: step: 164/530, loss: 0.00035557817318476737
2023-01-24 07:00:21.242279: step: 168/530, loss: 3.231114897062071e-05
2023-01-24 07:00:22.282275: step: 172/530, loss: 0.0009216041653417051
2023-01-24 07:00:23.330865: step: 176/530, loss: 0.002186810364946723
2023-01-24 07:00:24.384072: step: 180/530, loss: 0.024899797514081
2023-01-24 07:00:25.443852: step: 184/530, loss: 0.009470392018556595
2023-01-24 07:00:26.494637: step: 188/530, loss: 0.005112182814627886
2023-01-24 07:00:27.559166: step: 192/530, loss: 0.003691369667649269
2023-01-24 07:00:28.618320: step: 196/530, loss: 0.013270733878016472
2023-01-24 07:00:29.665153: step: 200/530, loss: 0.006272920873016119
2023-01-24 07:00:30.730601: step: 204/530, loss: 0.02067854441702366
2023-01-24 07:00:31.799257: step: 208/530, loss: 0.008375195786356926
2023-01-24 07:00:32.871628: step: 212/530, loss: 0.0010385076748207211
2023-01-24 07:00:33.926648: step: 216/530, loss: 0.0023643074091523886
2023-01-24 07:00:34.980224: step: 220/530, loss: 0.013027149252593517
2023-01-24 07:00:36.036080: step: 224/530, loss: 0.0066559505648911
2023-01-24 07:00:37.102505: step: 228/530, loss: 0.023444408550858498
2023-01-24 07:00:38.188579: step: 232/530, loss: 0.004703290294855833
2023-01-24 07:00:39.245676: step: 236/530, loss: 0.01591780036687851
2023-01-24 07:00:40.318669: step: 240/530, loss: 0.02737894095480442
2023-01-24 07:00:41.355966: step: 244/530, loss: 0.0018430290510877967
2023-01-24 07:00:42.416569: step: 248/530, loss: 0.007181955501437187
2023-01-24 07:00:43.479035: step: 252/530, loss: 0.01720271073281765
2023-01-24 07:00:44.531107: step: 256/530, loss: 0.0031290033366531134
2023-01-24 07:00:45.584773: step: 260/530, loss: 9.991229308070615e-05
2023-01-24 07:00:46.635034: step: 264/530, loss: 0.004231417551636696
2023-01-24 07:00:47.689154: step: 268/530, loss: 0.0006702316459268332
2023-01-24 07:00:48.754121: step: 272/530, loss: 0.00019239106040913612
2023-01-24 07:00:49.811595: step: 276/530, loss: 0.005118575878441334
2023-01-24 07:00:50.867704: step: 280/530, loss: 0.004971566144376993
2023-01-24 07:00:51.929606: step: 284/530, loss: 0.0003004439640790224
2023-01-24 07:00:52.981046: step: 288/530, loss: 0.0041951751336455345
2023-01-24 07:00:54.052495: step: 292/530, loss: 0.01582016982138157
2023-01-24 07:00:55.121658: step: 296/530, loss: 0.006762396078556776
2023-01-24 07:00:56.185848: step: 300/530, loss: 4.750323932967149e-05
2023-01-24 07:00:57.246082: step: 304/530, loss: 0.008418899029493332
2023-01-24 07:00:58.310472: step: 308/530, loss: 0.006618069484829903
2023-01-24 07:00:59.392867: step: 312/530, loss: 0.004107459913939238
2023-01-24 07:01:00.452375: step: 316/530, loss: 0.009810952469706535
2023-01-24 07:01:01.512158: step: 320/530, loss: 0.009370585903525352
2023-01-24 07:01:02.585994: step: 324/530, loss: 0.0019693318754434586
2023-01-24 07:01:03.646230: step: 328/530, loss: 0.0050402795895934105
2023-01-24 07:01:04.701581: step: 332/530, loss: 0.0027141098398715258
2023-01-24 07:01:05.762295: step: 336/530, loss: 0.024775249883532524
2023-01-24 07:01:06.821498: step: 340/530, loss: 0.002051254967227578
2023-01-24 07:01:07.885202: step: 344/530, loss: 0.0008156161056831479
2023-01-24 07:01:08.941100: step: 348/530, loss: 0.010663973167538643
2023-01-24 07:01:10.006855: step: 352/530, loss: 0.0047533828765153885
2023-01-24 07:01:11.078505: step: 356/530, loss: 0.006912748795002699
2023-01-24 07:01:12.137987: step: 360/530, loss: 0.001605372759513557
2023-01-24 07:01:13.196186: step: 364/530, loss: 0.007916337810456753
2023-01-24 07:01:14.241172: step: 368/530, loss: 0.0011368439299985766
2023-01-24 07:01:15.303905: step: 372/530, loss: 0.015500892885029316
2023-01-24 07:01:16.363489: step: 376/530, loss: 0.009428277611732483
2023-01-24 07:01:17.426184: step: 380/530, loss: 0.010872173123061657
2023-01-24 07:01:18.499239: step: 384/530, loss: 0.002144044265151024
2023-01-24 07:01:19.567690: step: 388/530, loss: 0.005862843245267868
2023-01-24 07:01:20.628713: step: 392/530, loss: 0.002543897368013859
2023-01-24 07:01:21.689666: step: 396/530, loss: 0.002472938969731331
2023-01-24 07:01:22.743363: step: 400/530, loss: 0.0008193214307539165
2023-01-24 07:01:23.807411: step: 404/530, loss: 0.005421883426606655
2023-01-24 07:01:24.861562: step: 408/530, loss: 0.006072331219911575
2023-01-24 07:01:25.916560: step: 412/530, loss: 0.002236895263195038
2023-01-24 07:01:26.997224: step: 416/530, loss: 0.0036221640184521675
2023-01-24 07:01:28.053865: step: 420/530, loss: 0.0042864917777478695
2023-01-24 07:01:29.111010: step: 424/530, loss: 0.0004260396817699075
2023-01-24 07:01:30.182071: step: 428/530, loss: 0.0012707824353128672
2023-01-24 07:01:31.228923: step: 432/530, loss: 0.0012458136770874262
2023-01-24 07:01:32.308637: step: 436/530, loss: 0.009500917978584766
2023-01-24 07:01:33.358292: step: 440/530, loss: 0.0011804746463894844
2023-01-24 07:01:34.416233: step: 444/530, loss: 0.006803330034017563
2023-01-24 07:01:35.476717: step: 448/530, loss: 0.0038335993885993958
2023-01-24 07:01:36.543214: step: 452/530, loss: 0.041306860744953156
2023-01-24 07:01:37.605075: step: 456/530, loss: 0.00015529927622992545
2023-01-24 07:01:38.665114: step: 460/530, loss: 0.009807570837438107
2023-01-24 07:01:39.713577: step: 464/530, loss: 0.0015617129392921925
2023-01-24 07:01:40.771373: step: 468/530, loss: 0.000826411007437855
2023-01-24 07:01:41.829908: step: 472/530, loss: 0.00410790229216218
2023-01-24 07:01:42.893663: step: 476/530, loss: 0.0035296306014060974
2023-01-24 07:01:43.969685: step: 480/530, loss: 0.004457561299204826
2023-01-24 07:01:45.045955: step: 484/530, loss: 0.018837295472621918
2023-01-24 07:01:46.108282: step: 488/530, loss: 0.0052842795848846436
2023-01-24 07:01:47.174276: step: 492/530, loss: 0.0011642472818493843
2023-01-24 07:01:48.240724: step: 496/530, loss: 0.0015510981902480125
2023-01-24 07:01:49.306949: step: 500/530, loss: 0.003408548654988408
2023-01-24 07:01:50.389411: step: 504/530, loss: 0.0033200138714164495
2023-01-24 07:01:51.466931: step: 508/530, loss: 0.007814311422407627
2023-01-24 07:01:52.533647: step: 512/530, loss: 0.001283789984881878
2023-01-24 07:01:53.584432: step: 516/530, loss: 0.0032652714289724827
2023-01-24 07:01:54.650739: step: 520/530, loss: 0.012143399566411972
2023-01-24 07:01:55.682040: step: 524/530, loss: 0.00014721114712301642
2023-01-24 07:01:56.738745: step: 528/530, loss: 0.016877857968211174
2023-01-24 07:01:57.812196: step: 532/530, loss: 0.0013240206753835082
2023-01-24 07:01:58.875567: step: 536/530, loss: 0.004016508813947439
2023-01-24 07:01:59.951398: step: 540/530, loss: 0.02041524276137352
2023-01-24 07:02:01.000812: step: 544/530, loss: 0.0017077726079151034
2023-01-24 07:02:02.090899: step: 548/530, loss: 0.0037660400848835707
2023-01-24 07:02:03.153243: step: 552/530, loss: 0.0057712760753929615
2023-01-24 07:02:04.228877: step: 556/530, loss: 0.002878459170460701
2023-01-24 07:02:05.305345: step: 560/530, loss: 0.0017273627454414964
2023-01-24 07:02:06.363013: step: 564/530, loss: 0.004351409617811441
2023-01-24 07:02:07.425509: step: 568/530, loss: 0.0036845330614596605
2023-01-24 07:02:08.478716: step: 572/530, loss: 0.00444047711789608
2023-01-24 07:02:09.534991: step: 576/530, loss: 0.0006759187672287226
2023-01-24 07:02:10.586289: step: 580/530, loss: 0.0048767393454909325
2023-01-24 07:02:11.648270: step: 584/530, loss: 0.0027554964181035757
2023-01-24 07:02:12.699255: step: 588/530, loss: 0.0029018798377364874
2023-01-24 07:02:13.763233: step: 592/530, loss: 0.004838711582124233
2023-01-24 07:02:14.842197: step: 596/530, loss: 0.001147024449892342
2023-01-24 07:02:15.912136: step: 600/530, loss: 0.0013574139447882771
2023-01-24 07:02:16.973061: step: 604/530, loss: 0.01001831702888012
2023-01-24 07:02:18.025619: step: 608/530, loss: 0.004788985010236502
2023-01-24 07:02:19.080247: step: 612/530, loss: 0.0014081747503951192
2023-01-24 07:02:20.126349: step: 616/530, loss: 0.0016465570079162717
2023-01-24 07:02:21.180599: step: 620/530, loss: 0.005801419261842966
2023-01-24 07:02:22.235136: step: 624/530, loss: 0.03987366333603859
2023-01-24 07:02:23.283590: step: 628/530, loss: 0.003176118014380336
2023-01-24 07:02:24.345764: step: 632/530, loss: 0.0008934763609431684
2023-01-24 07:02:25.417168: step: 636/530, loss: 0.005749239586293697
2023-01-24 07:02:26.470389: step: 640/530, loss: 0.004555360414087772
2023-01-24 07:02:27.525545: step: 644/530, loss: 0.0
2023-01-24 07:02:28.573589: step: 648/530, loss: 0.00025537374312989414
2023-01-24 07:02:29.637355: step: 652/530, loss: 0.009222530759871006
2023-01-24 07:02:30.694170: step: 656/530, loss: 0.005340136121958494
2023-01-24 07:02:31.754919: step: 660/530, loss: 0.005938283633440733
2023-01-24 07:02:32.804094: step: 664/530, loss: 0.006589628756046295
2023-01-24 07:02:33.863998: step: 668/530, loss: 0.0024793867487460375
2023-01-24 07:02:34.918751: step: 672/530, loss: 0.00016749647329561412
2023-01-24 07:02:35.992763: step: 676/530, loss: 0.002509690821170807
2023-01-24 07:02:37.060537: step: 680/530, loss: 0.00983802042901516
2023-01-24 07:02:38.133878: step: 684/530, loss: 0.005732954014092684
2023-01-24 07:02:39.205351: step: 688/530, loss: 0.009008189663290977
2023-01-24 07:02:40.278823: step: 692/530, loss: 0.006726323626935482
2023-01-24 07:02:41.318905: step: 696/530, loss: 0.0019366192864254117
2023-01-24 07:02:42.378108: step: 700/530, loss: 0.010213913396000862
2023-01-24 07:02:43.442890: step: 704/530, loss: 0.0014466455904766917
2023-01-24 07:02:44.507486: step: 708/530, loss: 0.003334656823426485
2023-01-24 07:02:45.579573: step: 712/530, loss: 0.0048185852356255054
2023-01-24 07:02:46.632405: step: 716/530, loss: 0.0024992600083351135
2023-01-24 07:02:47.689932: step: 720/530, loss: 0.001594380009919405
2023-01-24 07:02:48.747493: step: 724/530, loss: 0.01058395579457283
2023-01-24 07:02:49.805688: step: 728/530, loss: 0.004823962226510048
2023-01-24 07:02:50.884006: step: 732/530, loss: 0.005900415126234293
2023-01-24 07:02:51.942762: step: 736/530, loss: 0.004103643354028463
2023-01-24 07:02:53.004052: step: 740/530, loss: 0.020892757922410965
2023-01-24 07:02:54.060553: step: 744/530, loss: 0.0016669811448082328
2023-01-24 07:02:55.130045: step: 748/530, loss: 0.0039565060287714005
2023-01-24 07:02:56.193684: step: 752/530, loss: 0.011750808916985989
2023-01-24 07:02:57.252104: step: 756/530, loss: 0.0044591231271624565
2023-01-24 07:02:58.311872: step: 760/530, loss: 0.005317573435604572
2023-01-24 07:02:59.363110: step: 764/530, loss: 0.002158926334232092
2023-01-24 07:03:00.419035: step: 768/530, loss: 0.013807006180286407
2023-01-24 07:03:01.492214: step: 772/530, loss: 0.0006345547735691071
2023-01-24 07:03:02.565504: step: 776/530, loss: 0.02323751337826252
2023-01-24 07:03:03.613169: step: 780/530, loss: 0.008334612473845482
2023-01-24 07:03:04.674501: step: 784/530, loss: 0.010491586290299892
2023-01-24 07:03:05.761929: step: 788/530, loss: 0.01413573045283556
2023-01-24 07:03:06.809402: step: 792/530, loss: 0.008251430466771126
2023-01-24 07:03:07.861558: step: 796/530, loss: 0.011630561202764511
2023-01-24 07:03:08.918908: step: 800/530, loss: 0.0021440545096993446
2023-01-24 07:03:09.974201: step: 804/530, loss: 0.005057157948613167
2023-01-24 07:03:11.031879: step: 808/530, loss: 0.0052289413288235664
2023-01-24 07:03:12.083912: step: 812/530, loss: 0.0038129761815071106
2023-01-24 07:03:13.132367: step: 816/530, loss: 0.0001373779959976673
2023-01-24 07:03:14.177236: step: 820/530, loss: 0.0025319266133010387
2023-01-24 07:03:15.256533: step: 824/530, loss: 0.004143928177654743
2023-01-24 07:03:16.317986: step: 828/530, loss: 0.006298021413385868
2023-01-24 07:03:17.391434: step: 832/530, loss: 0.0037713563069701195
2023-01-24 07:03:18.454897: step: 836/530, loss: 0.003089392092078924
2023-01-24 07:03:19.519600: step: 840/530, loss: 0.0039008057210594416
2023-01-24 07:03:20.578703: step: 844/530, loss: 0.003434424754232168
2023-01-24 07:03:21.644491: step: 848/530, loss: 0.006872132886201143
2023-01-24 07:03:22.704408: step: 852/530, loss: 0.0035184407606720924
2023-01-24 07:03:23.760300: step: 856/530, loss: 0.006169327534735203
2023-01-24 07:03:24.818282: step: 860/530, loss: 0.0015827324241399765
2023-01-24 07:03:25.874627: step: 864/530, loss: 0.008262558840215206
2023-01-24 07:03:26.923983: step: 868/530, loss: 0.006411949638277292
2023-01-24 07:03:27.998776: step: 872/530, loss: 0.000947563792578876
2023-01-24 07:03:29.065680: step: 876/530, loss: 0.011106381192803383
2023-01-24 07:03:30.128061: step: 880/530, loss: 0.0016223759157583117
2023-01-24 07:03:31.184815: step: 884/530, loss: 0.01957591436803341
2023-01-24 07:03:32.234784: step: 888/530, loss: 0.006975620985031128
2023-01-24 07:03:33.293012: step: 892/530, loss: 0.0011496235383674502
2023-01-24 07:03:34.334381: step: 896/530, loss: 0.0003228428540751338
2023-01-24 07:03:35.389867: step: 900/530, loss: 0.010430501773953438
2023-01-24 07:03:36.435510: step: 904/530, loss: 0.005505760665982962
2023-01-24 07:03:37.488058: step: 908/530, loss: 0.004160992801189423
2023-01-24 07:03:38.550886: step: 912/530, loss: 0.00787445716559887
2023-01-24 07:03:39.630314: step: 916/530, loss: 0.016685495153069496
2023-01-24 07:03:40.676772: step: 920/530, loss: 0.005118233617395163
2023-01-24 07:03:41.746803: step: 924/530, loss: 0.00031529227271676064
2023-01-24 07:03:42.807148: step: 928/530, loss: 0.0005196065758354962
2023-01-24 07:03:43.846396: step: 932/530, loss: 0.0033208897802978754
2023-01-24 07:03:44.911701: step: 936/530, loss: 0.013224363327026367
2023-01-24 07:03:45.965557: step: 940/530, loss: 0.008918027393519878
2023-01-24 07:03:47.034221: step: 944/530, loss: 0.005305406637489796
2023-01-24 07:03:48.095626: step: 948/530, loss: 0.001953817205503583
2023-01-24 07:03:49.146383: step: 952/530, loss: 0.0027615586295723915
2023-01-24 07:03:50.214348: step: 956/530, loss: 0.007874968461692333
2023-01-24 07:03:51.287926: step: 960/530, loss: 0.005785588640719652
2023-01-24 07:03:52.342123: step: 964/530, loss: 0.0031078369356691837
2023-01-24 07:03:53.417193: step: 968/530, loss: 0.0004704507300630212
2023-01-24 07:03:54.472082: step: 972/530, loss: 0.004142599646002054
2023-01-24 07:03:55.541341: step: 976/530, loss: 0.01403866708278656
2023-01-24 07:03:56.592312: step: 980/530, loss: 0.016708463430404663
2023-01-24 07:03:57.665330: step: 984/530, loss: 0.006009605713188648
2023-01-24 07:03:58.713216: step: 988/530, loss: 0.0030958850402384996
2023-01-24 07:03:59.774961: step: 992/530, loss: 0.005048592574894428
2023-01-24 07:04:00.828224: step: 996/530, loss: 9.777664672583342e-05
2023-01-24 07:04:01.880731: step: 1000/530, loss: 0.004117369651794434
2023-01-24 07:04:02.935021: step: 1004/530, loss: 0.002292782999575138
2023-01-24 07:04:04.001620: step: 1008/530, loss: 0.0036601070314645767
2023-01-24 07:04:05.060158: step: 1012/530, loss: 0.013988976366817951
2023-01-24 07:04:06.120423: step: 1016/530, loss: 0.003988346550613642
2023-01-24 07:04:07.172929: step: 1020/530, loss: 0.005626540165394545
2023-01-24 07:04:08.244586: step: 1024/530, loss: 0.011585342697799206
2023-01-24 07:04:09.293638: step: 1028/530, loss: 0.009907795116305351
2023-01-24 07:04:10.346368: step: 1032/530, loss: 0.0012083154870197177
2023-01-24 07:04:11.431303: step: 1036/530, loss: 0.0024685675743967295
2023-01-24 07:04:12.494289: step: 1040/530, loss: 0.005400072317570448
2023-01-24 07:04:13.542545: step: 1044/530, loss: 0.0015769656747579575
2023-01-24 07:04:14.589615: step: 1048/530, loss: 0.0038196684326976538
2023-01-24 07:04:15.648099: step: 1052/530, loss: 0.013219322077929974
2023-01-24 07:04:16.709168: step: 1056/530, loss: 0.012918712571263313
2023-01-24 07:04:17.777144: step: 1060/530, loss: 0.010488973930478096
2023-01-24 07:04:18.848604: step: 1064/530, loss: 0.005757351405918598
2023-01-24 07:04:19.903682: step: 1068/530, loss: 0.00045643607154488564
2023-01-24 07:04:20.956774: step: 1072/530, loss: 0.016330217942595482
2023-01-24 07:04:22.012175: step: 1076/530, loss: 0.011616937816143036
2023-01-24 07:04:23.079011: step: 1080/530, loss: 0.00924005638808012
2023-01-24 07:04:24.157167: step: 1084/530, loss: 0.002475353190675378
2023-01-24 07:04:25.220154: step: 1088/530, loss: 0.002158066490665078
2023-01-24 07:04:26.275982: step: 1092/530, loss: 0.0036438305396586657
2023-01-24 07:04:27.351529: step: 1096/530, loss: 0.02925151027739048
2023-01-24 07:04:28.413388: step: 1100/530, loss: 0.002680625766515732
2023-01-24 07:04:29.484971: step: 1104/530, loss: 0.004278386477380991
2023-01-24 07:04:30.536268: step: 1108/530, loss: 0.0017597271362319589
2023-01-24 07:04:31.590271: step: 1112/530, loss: 0.017071500420570374
2023-01-24 07:04:32.647445: step: 1116/530, loss: 0.0023383672814816236
2023-01-24 07:04:33.686932: step: 1120/530, loss: 0.0005948357284069061
2023-01-24 07:04:34.764640: step: 1124/530, loss: 0.023053156211972237
2023-01-24 07:04:35.824456: step: 1128/530, loss: 0.002723283600062132
2023-01-24 07:04:36.887304: step: 1132/530, loss: 0.0012084601912647486
2023-01-24 07:04:37.956448: step: 1136/530, loss: 0.0049757156521081924
2023-01-24 07:04:39.037767: step: 1140/530, loss: 0.027197297662496567
2023-01-24 07:04:40.076049: step: 1144/530, loss: 0.0009958151495084167
2023-01-24 07:04:41.160938: step: 1148/530, loss: 0.009862146340310574
2023-01-24 07:04:42.225192: step: 1152/530, loss: 0.00027023901930078864
2023-01-24 07:04:43.304021: step: 1156/530, loss: 0.0012597389286383986
2023-01-24 07:04:44.352478: step: 1160/530, loss: 0.01348771434277296
2023-01-24 07:04:45.407681: step: 1164/530, loss: 0.004374179523438215
2023-01-24 07:04:46.473956: step: 1168/530, loss: 0.00842099916189909
2023-01-24 07:04:47.532916: step: 1172/530, loss: 0.015802482143044472
2023-01-24 07:04:48.592107: step: 1176/530, loss: 0.0063231815584003925
2023-01-24 07:04:49.647094: step: 1180/530, loss: 0.0027391796465963125
2023-01-24 07:04:50.696372: step: 1184/530, loss: 0.00445235101506114
2023-01-24 07:04:51.754828: step: 1188/530, loss: 0.003377283923327923
2023-01-24 07:04:52.815825: step: 1192/530, loss: 0.016094859689474106
2023-01-24 07:04:53.880698: step: 1196/530, loss: 0.003858909010887146
2023-01-24 07:04:54.947964: step: 1200/530, loss: 0.004194995388388634
2023-01-24 07:04:56.014907: step: 1204/530, loss: 0.009948239661753178
2023-01-24 07:04:57.079703: step: 1208/530, loss: 0.007313582114875317
2023-01-24 07:04:58.128955: step: 1212/530, loss: 0.0032310641836375
2023-01-24 07:04:59.194115: step: 1216/530, loss: 0.02269793674349785
2023-01-24 07:05:00.246817: step: 1220/530, loss: 0.0008559832349419594
2023-01-24 07:05:01.305954: step: 1224/530, loss: 0.004275730811059475
2023-01-24 07:05:02.390426: step: 1228/530, loss: 0.0054108458571136
2023-01-24 07:05:03.442515: step: 1232/530, loss: 0.0036550445947796106
2023-01-24 07:05:04.496659: step: 1236/530, loss: 0.010995370335876942
2023-01-24 07:05:05.563200: step: 1240/530, loss: 0.009659373201429844
2023-01-24 07:05:06.624865: step: 1244/530, loss: 0.017616888508200645
2023-01-24 07:05:07.677526: step: 1248/530, loss: 0.007949767634272575
2023-01-24 07:05:08.745630: step: 1252/530, loss: 0.003466795664280653
2023-01-24 07:05:09.800256: step: 1256/530, loss: 0.008696061559021473
2023-01-24 07:05:10.866206: step: 1260/530, loss: 0.00022204924607649446
2023-01-24 07:05:11.918247: step: 1264/530, loss: 0.005940826144069433
2023-01-24 07:05:12.984863: step: 1268/530, loss: 0.015793664380908012
2023-01-24 07:05:14.047529: step: 1272/530, loss: 0.0030650380067527294
2023-01-24 07:05:15.113223: step: 1276/530, loss: 0.0020106001757085323
2023-01-24 07:05:16.172406: step: 1280/530, loss: 0.007168071810156107
2023-01-24 07:05:17.239650: step: 1284/530, loss: 0.005691030062735081
2023-01-24 07:05:18.306332: step: 1288/530, loss: 0.006314897909760475
2023-01-24 07:05:19.370545: step: 1292/530, loss: 0.0027939819265156984
2023-01-24 07:05:20.419360: step: 1296/530, loss: 0.0034941197372972965
2023-01-24 07:05:21.481012: step: 1300/530, loss: 0.002159245079383254
2023-01-24 07:05:22.539078: step: 1304/530, loss: 0.003573112888261676
2023-01-24 07:05:23.627674: step: 1308/530, loss: 0.042730607092380524
2023-01-24 07:05:24.691009: step: 1312/530, loss: 0.004080480895936489
2023-01-24 07:05:25.735449: step: 1316/530, loss: 0.010974136181175709
2023-01-24 07:05:26.785195: step: 1320/530, loss: 0.0033737365156412125
2023-01-24 07:05:27.835556: step: 1324/530, loss: 0.00639167008921504
2023-01-24 07:05:28.880240: step: 1328/530, loss: 0.011457026936113834
2023-01-24 07:05:29.961382: step: 1332/530, loss: 0.003620082512497902
2023-01-24 07:05:31.014480: step: 1336/530, loss: 0.009034446440637112
2023-01-24 07:05:32.103610: step: 1340/530, loss: 0.005224709864705801
2023-01-24 07:05:33.148213: step: 1344/530, loss: 0.0026099500246345997
2023-01-24 07:05:34.206534: step: 1348/530, loss: 0.008253741078078747
2023-01-24 07:05:35.269973: step: 1352/530, loss: 0.00010915151506196707
2023-01-24 07:05:36.342274: step: 1356/530, loss: 0.04658046364784241
2023-01-24 07:05:37.408117: step: 1360/530, loss: 0.0009694582549855113
2023-01-24 07:05:38.478007: step: 1364/530, loss: 0.01308530941605568
2023-01-24 07:05:39.545511: step: 1368/530, loss: 0.0041906097903847694
2023-01-24 07:05:40.604348: step: 1372/530, loss: 0.0029759081080555916
2023-01-24 07:05:41.655858: step: 1376/530, loss: 0.0021879486739635468
2023-01-24 07:05:42.715680: step: 1380/530, loss: 0.006069571245461702
2023-01-24 07:05:43.762664: step: 1384/530, loss: 0.02840854786336422
2023-01-24 07:05:44.811615: step: 1388/530, loss: 0.001358837354928255
2023-01-24 07:05:45.863023: step: 1392/530, loss: 0.002851101104170084
2023-01-24 07:05:46.933258: step: 1396/530, loss: 0.010881209746003151
2023-01-24 07:05:47.992798: step: 1400/530, loss: 0.00044142352999188006
2023-01-24 07:05:49.058429: step: 1404/530, loss: 0.0081596365198493
2023-01-24 07:05:50.142647: step: 1408/530, loss: 0.01634400151669979
2023-01-24 07:05:51.222308: step: 1412/530, loss: 0.018973123282194138
2023-01-24 07:05:52.311738: step: 1416/530, loss: 0.0029034828767180443
2023-01-24 07:05:53.372323: step: 1420/530, loss: 0.006434266921132803
2023-01-24 07:05:54.436850: step: 1424/530, loss: 0.004963258747011423
2023-01-24 07:05:55.498132: step: 1428/530, loss: 0.0014174885582178831
2023-01-24 07:05:56.562195: step: 1432/530, loss: 0.003842024365440011
2023-01-24 07:05:57.617107: step: 1436/530, loss: 0.007931889966130257
2023-01-24 07:05:58.679084: step: 1440/530, loss: 0.012513709254562855
2023-01-24 07:05:59.727428: step: 1444/530, loss: 0.006279796827584505
2023-01-24 07:06:00.792853: step: 1448/530, loss: 0.017553262412548065
2023-01-24 07:06:01.857394: step: 1452/530, loss: 0.009306592866778374
2023-01-24 07:06:02.934394: step: 1456/530, loss: 0.00352174392901361
2023-01-24 07:06:03.995088: step: 1460/530, loss: 0.0006553736748173833
2023-01-24 07:06:05.065373: step: 1464/530, loss: 0.005264295730739832
2023-01-24 07:06:06.123053: step: 1468/530, loss: 0.0030810050666332245
2023-01-24 07:06:07.186697: step: 1472/530, loss: 0.0030453705694526434
2023-01-24 07:06:08.236279: step: 1476/530, loss: 0.0072273691184818745
2023-01-24 07:06:09.291107: step: 1480/530, loss: 0.007053266745060682
2023-01-24 07:06:10.365645: step: 1484/530, loss: 0.005382508505135775
2023-01-24 07:06:11.424979: step: 1488/530, loss: 0.0011377789778634906
2023-01-24 07:06:12.489425: step: 1492/530, loss: 0.01101296953856945
2023-01-24 07:06:13.564972: step: 1496/530, loss: 0.008875487372279167
2023-01-24 07:06:14.622328: step: 1500/530, loss: 0.0034963919315487146
2023-01-24 07:06:15.682261: step: 1504/530, loss: 0.002814267994835973
2023-01-24 07:06:16.743093: step: 1508/530, loss: 0.002155342372134328
2023-01-24 07:06:17.808452: step: 1512/530, loss: 0.004510057158768177
2023-01-24 07:06:18.876365: step: 1516/530, loss: 0.005277504678815603
2023-01-24 07:06:19.932139: step: 1520/530, loss: 0.009193949401378632
2023-01-24 07:06:20.984494: step: 1524/530, loss: 0.005815129727125168
2023-01-24 07:06:22.050344: step: 1528/530, loss: 0.0026261107996106148
2023-01-24 07:06:23.113374: step: 1532/530, loss: 0.00044258078560233116
2023-01-24 07:06:24.170062: step: 1536/530, loss: 0.008945046924054623
2023-01-24 07:06:25.216490: step: 1540/530, loss: 0.012445696629583836
2023-01-24 07:06:26.287723: step: 1544/530, loss: 0.03725799545645714
2023-01-24 07:06:27.345191: step: 1548/530, loss: 0.0006237589986994863
2023-01-24 07:06:28.397961: step: 1552/530, loss: 0.034031230956315994
2023-01-24 07:06:29.462577: step: 1556/530, loss: 0.004464354831725359
2023-01-24 07:06:30.532018: step: 1560/530, loss: 0.0005066364537924528
2023-01-24 07:06:31.585575: step: 1564/530, loss: 0.009633711539208889
2023-01-24 07:06:32.649038: step: 1568/530, loss: 0.003609366249293089
2023-01-24 07:06:33.709913: step: 1572/530, loss: 0.011584056541323662
2023-01-24 07:06:34.781273: step: 1576/530, loss: 0.007297593168914318
2023-01-24 07:06:35.830646: step: 1580/530, loss: 0.022794876247644424
2023-01-24 07:06:36.884690: step: 1584/530, loss: 0.013751774094998837
2023-01-24 07:06:37.951152: step: 1588/530, loss: 0.006564836483448744
2023-01-24 07:06:39.008750: step: 1592/530, loss: 0.00834104884415865
2023-01-24 07:06:40.083004: step: 1596/530, loss: 0.01275724545121193
2023-01-24 07:06:41.149172: step: 1600/530, loss: 0.006590662058442831
2023-01-24 07:06:42.203989: step: 1604/530, loss: 0.0052870032377541065
2023-01-24 07:06:43.287606: step: 1608/530, loss: 0.044110264629125595
2023-01-24 07:06:44.347520: step: 1612/530, loss: 0.0027077083941549063
2023-01-24 07:06:45.392080: step: 1616/530, loss: 0.0067832572385668755
2023-01-24 07:06:46.450348: step: 1620/530, loss: 0.021005775779485703
2023-01-24 07:06:47.517712: step: 1624/530, loss: 0.0028020518366247416
2023-01-24 07:06:48.578980: step: 1628/530, loss: 0.020514514297246933
2023-01-24 07:06:49.652638: step: 1632/530, loss: 0.013297458179295063
2023-01-24 07:06:50.709382: step: 1636/530, loss: 0.0037885697092860937
2023-01-24 07:06:51.753066: step: 1640/530, loss: 0.0019260881235823035
2023-01-24 07:06:52.800940: step: 1644/530, loss: 0.02238306775689125
2023-01-24 07:06:53.857268: step: 1648/530, loss: 0.006170709151774645
2023-01-24 07:06:54.920543: step: 1652/530, loss: 0.010011142119765282
2023-01-24 07:06:55.980635: step: 1656/530, loss: 0.0015578616876155138
2023-01-24 07:06:57.051030: step: 1660/530, loss: 0.005705316551029682
2023-01-24 07:06:58.106958: step: 1664/530, loss: 0.004996040370315313
2023-01-24 07:06:59.149514: step: 1668/530, loss: 0.004244686104357243
2023-01-24 07:07:00.189763: step: 1672/530, loss: 0.0077867936342954636
2023-01-24 07:07:01.272666: step: 1676/530, loss: 0.006771698594093323
2023-01-24 07:07:02.324387: step: 1680/530, loss: 0.0009493294637650251
2023-01-24 07:07:03.385512: step: 1684/530, loss: 0.003962224815040827
2023-01-24 07:07:04.482135: step: 1688/530, loss: 0.0056709847413003445
2023-01-24 07:07:05.541763: step: 1692/530, loss: 0.013474286533892155
2023-01-24 07:07:06.595231: step: 1696/530, loss: 0.004022576846182346
2023-01-24 07:07:07.645410: step: 1700/530, loss: 0.0048307375982403755
2023-01-24 07:07:08.705246: step: 1704/530, loss: 0.006834511179476976
2023-01-24 07:07:09.765274: step: 1708/530, loss: 0.005257416982203722
2023-01-24 07:07:10.832145: step: 1712/530, loss: 0.014350980520248413
2023-01-24 07:07:11.894935: step: 1716/530, loss: 0.018000328913331032
2023-01-24 07:07:12.945690: step: 1720/530, loss: 0.0003532406408339739
2023-01-24 07:07:14.012017: step: 1724/530, loss: 0.009978021495044231
2023-01-24 07:07:15.063581: step: 1728/530, loss: 0.0007069700513966382
2023-01-24 07:07:16.111998: step: 1732/530, loss: 0.0015021860599517822
2023-01-24 07:07:17.171338: step: 1736/530, loss: 0.017386864870786667
2023-01-24 07:07:18.240358: step: 1740/530, loss: 0.017184417694807053
2023-01-24 07:07:19.299847: step: 1744/530, loss: 0.0067120324820280075
2023-01-24 07:07:20.377323: step: 1748/530, loss: 0.04484333097934723
2023-01-24 07:07:21.424236: step: 1752/530, loss: 0.0033254765439778566
2023-01-24 07:07:22.485048: step: 1756/530, loss: 0.00354401976801455
2023-01-24 07:07:23.548331: step: 1760/530, loss: 0.006634449120610952
2023-01-24 07:07:24.604634: step: 1764/530, loss: 0.0009382428252138197
2023-01-24 07:07:25.665130: step: 1768/530, loss: 0.0018498455174267292
2023-01-24 07:07:26.733929: step: 1772/530, loss: 0.0027881842106580734
2023-01-24 07:07:27.790361: step: 1776/530, loss: 0.0008231662795878947
2023-01-24 07:07:28.847499: step: 1780/530, loss: 0.004137236624956131
2023-01-24 07:07:29.931719: step: 1784/530, loss: 0.00973699614405632
2023-01-24 07:07:30.988076: step: 1788/530, loss: 0.0026099937967956066
2023-01-24 07:07:32.096173: step: 1792/530, loss: 0.002436611568555236
2023-01-24 07:07:33.137601: step: 1796/530, loss: 0.0022602351382374763
2023-01-24 07:07:34.202701: step: 1800/530, loss: 0.0018043058225885034
2023-01-24 07:07:35.291259: step: 1804/530, loss: 0.008009007200598717
2023-01-24 07:07:36.344110: step: 1808/530, loss: 0.005099027883261442
2023-01-24 07:07:37.401944: step: 1812/530, loss: 0.004789561033248901
2023-01-24 07:07:38.467976: step: 1816/530, loss: 0.0005448472802527249
2023-01-24 07:07:39.521034: step: 1820/530, loss: 0.008643064647912979
2023-01-24 07:07:40.585568: step: 1824/530, loss: 0.0017157766269519925
2023-01-24 07:07:41.649459: step: 1828/530, loss: 0.005277327261865139
2023-01-24 07:07:42.720365: step: 1832/530, loss: 0.010374607518315315
2023-01-24 07:07:43.768990: step: 1836/530, loss: 0.0017752469284459949
2023-01-24 07:07:44.835555: step: 1840/530, loss: 0.010292110964655876
2023-01-24 07:07:45.887360: step: 1844/530, loss: 0.03987564519047737
2023-01-24 07:07:46.951876: step: 1848/530, loss: 0.007781487423926592
2023-01-24 07:07:48.012655: step: 1852/530, loss: 0.017869969829916954
2023-01-24 07:07:49.072854: step: 1856/530, loss: 0.003552844049409032
2023-01-24 07:07:50.135279: step: 1860/530, loss: 0.0013825483620166779
2023-01-24 07:07:51.206693: step: 1864/530, loss: 0.02778548188507557
2023-01-24 07:07:52.257541: step: 1868/530, loss: 0.0021867360919713974
2023-01-24 07:07:53.316615: step: 1872/530, loss: 0.009883199818432331
2023-01-24 07:07:54.399790: step: 1876/530, loss: 0.00491854315623641
2023-01-24 07:07:55.469470: step: 1880/530, loss: 0.004421879071742296
2023-01-24 07:07:56.524927: step: 1884/530, loss: 0.005779049824923277
2023-01-24 07:07:57.593558: step: 1888/530, loss: 0.005704408977180719
2023-01-24 07:07:58.659294: step: 1892/530, loss: 0.018534252420067787
2023-01-24 07:07:59.712939: step: 1896/530, loss: 0.006822432857006788
2023-01-24 07:08:00.763954: step: 1900/530, loss: 0.007705484051257372
2023-01-24 07:08:01.840862: step: 1904/530, loss: 0.0028729026671499014
2023-01-24 07:08:02.915394: step: 1908/530, loss: 0.0026009564753621817
2023-01-24 07:08:03.964508: step: 1912/530, loss: 0.007517572026699781
2023-01-24 07:08:05.028654: step: 1916/530, loss: 0.026851356029510498
2023-01-24 07:08:06.097099: step: 1920/530, loss: 0.003632955253124237
2023-01-24 07:08:07.164151: step: 1924/530, loss: 0.01801270991563797
2023-01-24 07:08:08.202797: step: 1928/530, loss: 0.015021150931715965
2023-01-24 07:08:09.261423: step: 1932/530, loss: 0.001532773021608591
2023-01-24 07:08:10.308813: step: 1936/530, loss: 0.002741945208981633
2023-01-24 07:08:11.362540: step: 1940/530, loss: 0.005579810123890638
2023-01-24 07:08:12.425371: step: 1944/530, loss: 0.0036730861756950617
2023-01-24 07:08:13.489938: step: 1948/530, loss: 0.019181568175554276
2023-01-24 07:08:14.546177: step: 1952/530, loss: 0.05246738716959953
2023-01-24 07:08:15.598189: step: 1956/530, loss: 0.012826553545892239
2023-01-24 07:08:16.655392: step: 1960/530, loss: 0.00749613530933857
2023-01-24 07:08:17.702523: step: 1964/530, loss: 0.0021970057860016823
2023-01-24 07:08:18.760321: step: 1968/530, loss: 0.0033430519979447126
2023-01-24 07:08:19.821834: step: 1972/530, loss: 0.014233284629881382
2023-01-24 07:08:20.885756: step: 1976/530, loss: 0.006610978860408068
2023-01-24 07:08:21.947568: step: 1980/530, loss: 0.004730131011456251
2023-01-24 07:08:23.011790: step: 1984/530, loss: 0.0243196040391922
2023-01-24 07:08:24.074750: step: 1988/530, loss: 0.0034956117160618305
2023-01-24 07:08:25.134746: step: 1992/530, loss: 0.01712939701974392
2023-01-24 07:08:26.205105: step: 1996/530, loss: 0.0041745854541659355
2023-01-24 07:08:27.278613: step: 2000/530, loss: 0.04020633175969124
2023-01-24 07:08:28.333715: step: 2004/530, loss: 0.01455580722540617
2023-01-24 07:08:29.397271: step: 2008/530, loss: 0.00015746141434647143
2023-01-24 07:08:30.459964: step: 2012/530, loss: 0.009296857751905918
2023-01-24 07:08:31.514700: step: 2016/530, loss: 0.04265981912612915
2023-01-24 07:08:32.569981: step: 2020/530, loss: 0.005813135765492916
2023-01-24 07:08:33.650418: step: 2024/530, loss: 0.004123806953430176
2023-01-24 07:08:34.723436: step: 2028/530, loss: 0.0077259354293346405
2023-01-24 07:08:35.776832: step: 2032/530, loss: 0.007799016311764717
2023-01-24 07:08:36.837589: step: 2036/530, loss: 0.000558257510419935
2023-01-24 07:08:37.897960: step: 2040/530, loss: 0.0023471165914088488
2023-01-24 07:08:38.963128: step: 2044/530, loss: 0.02511187456548214
2023-01-24 07:08:40.000627: step: 2048/530, loss: 0.010988562367856503
2023-01-24 07:08:41.067682: step: 2052/530, loss: 0.002913655247539282
2023-01-24 07:08:42.127808: step: 2056/530, loss: 0.006095722317695618
2023-01-24 07:08:43.182041: step: 2060/530, loss: 0.007117302622646093
2023-01-24 07:08:44.255691: step: 2064/530, loss: 0.01098459493368864
2023-01-24 07:08:45.327901: step: 2068/530, loss: 0.024153364822268486
2023-01-24 07:08:46.398536: step: 2072/530, loss: 0.0010887591633945704
2023-01-24 07:08:47.465850: step: 2076/530, loss: 0.019949011504650116
2023-01-24 07:08:48.519752: step: 2080/530, loss: 0.09003783762454987
2023-01-24 07:08:49.594019: step: 2084/530, loss: 0.004630534444004297
2023-01-24 07:08:50.649704: step: 2088/530, loss: 0.0029297247529029846
2023-01-24 07:08:51.721787: step: 2092/530, loss: 0.006283792667090893
2023-01-24 07:08:52.769575: step: 2096/530, loss: 0.005687047727406025
2023-01-24 07:08:53.832525: step: 2100/530, loss: 0.005041434895247221
2023-01-24 07:08:54.898024: step: 2104/530, loss: 0.009113487787544727
2023-01-24 07:08:55.954759: step: 2108/530, loss: 0.0020749259274452925
2023-01-24 07:08:57.013386: step: 2112/530, loss: 0.0012578677851706743
2023-01-24 07:08:58.082670: step: 2116/530, loss: 0.0004785159835591912
2023-01-24 07:08:59.141685: step: 2120/530, loss: 0.005833215545862913
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3835638105567607, 'r': 0.33552735610373186, 'f1': 0.3579411268556006}, 'combined': 0.2637460934725478, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3946894091031585, 'r': 0.2957603204380997, 'f1': 0.33813748087766876}, 'combined': 0.22425698213648496, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3427204176334107, 'r': 0.27975852272727275, 'f1': 0.3080552659019813}, 'combined': 0.2053701772679875, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3996347294978236, 'r': 0.2936657284351425, 'f1': 0.3385516989152392}, 'combined': 0.2209495298183666, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3693154553727897, 'r': 0.332173673333401, 'f1': 0.34976129040300163}, 'combined': 0.25771884556010644, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39670938937744016, 'r': 0.3094676708476828, 'f1': 0.34769957181816497}, 'combined': 0.23059867975505238, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.13793103448275862, 'f1': 0.2162162162162162}, 'combined': 0.14414414414414412, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:11:26.364298: step: 4/530, loss: 0.015453999862074852
2023-01-24 07:11:27.395447: step: 8/530, loss: 0.007492606993764639
2023-01-24 07:11:28.440621: step: 12/530, loss: 0.00014246927457861602
2023-01-24 07:11:29.484993: step: 16/530, loss: 0.011854852549731731
2023-01-24 07:11:30.540165: step: 20/530, loss: 0.0029151272028684616
2023-01-24 07:11:31.590471: step: 24/530, loss: 0.018363848328590393
2023-01-24 07:11:32.634329: step: 28/530, loss: 0.0013391694519668818
2023-01-24 07:11:33.687388: step: 32/530, loss: 0.006418815813958645
2023-01-24 07:11:34.745099: step: 36/530, loss: 0.0024502796586602926
2023-01-24 07:11:35.797088: step: 40/530, loss: 0.002085303422063589
2023-01-24 07:11:36.850694: step: 44/530, loss: 0.004141415003687143
2023-01-24 07:11:37.908571: step: 48/530, loss: 0.0027567066717892885
2023-01-24 07:11:38.960153: step: 52/530, loss: 0.007397840265184641
2023-01-24 07:11:40.014817: step: 56/530, loss: 0.004578541498631239
2023-01-24 07:11:41.063959: step: 60/530, loss: 0.0007039898191578686
2023-01-24 07:11:42.110527: step: 64/530, loss: 0.001355127664282918
2023-01-24 07:11:43.155570: step: 68/530, loss: 0.00461657764390111
2023-01-24 07:11:44.199329: step: 72/530, loss: 0.004640455823391676
2023-01-24 07:11:45.243284: step: 76/530, loss: 0.012126055546104908
2023-01-24 07:11:46.323614: step: 80/530, loss: 0.0030512565281242132
2023-01-24 07:11:47.375688: step: 84/530, loss: 0.008379384875297546
2023-01-24 07:11:48.434068: step: 88/530, loss: 0.006320971064269543
2023-01-24 07:11:49.494831: step: 92/530, loss: 0.008114654570817947
2023-01-24 07:11:50.545581: step: 96/530, loss: 0.0004159668169450015
2023-01-24 07:11:51.601019: step: 100/530, loss: 0.0027421661652624607
2023-01-24 07:11:52.660751: step: 104/530, loss: 0.002439852338284254
2023-01-24 07:11:53.721367: step: 108/530, loss: 0.009213601239025593
2023-01-24 07:11:54.798005: step: 112/530, loss: 0.013362675905227661
2023-01-24 07:11:55.847997: step: 116/530, loss: 0.0008297545136883855
2023-01-24 07:11:56.904138: step: 120/530, loss: 0.006370811257511377
2023-01-24 07:11:57.970080: step: 124/530, loss: 0.005854370538145304
2023-01-24 07:11:59.031309: step: 128/530, loss: 0.003679548157379031
2023-01-24 07:12:00.109657: step: 132/530, loss: 0.0009568792302161455
2023-01-24 07:12:01.176159: step: 136/530, loss: 0.004784580320119858
2023-01-24 07:12:02.242605: step: 140/530, loss: 0.0058162580244243145
2023-01-24 07:12:03.310698: step: 144/530, loss: 0.0008889066521078348
2023-01-24 07:12:04.365826: step: 148/530, loss: 0.007078120484948158
2023-01-24 07:12:05.413836: step: 152/530, loss: 0.00599098764359951
2023-01-24 07:12:06.481277: step: 156/530, loss: 0.06296837329864502
2023-01-24 07:12:07.532803: step: 160/530, loss: 0.003585967468097806
2023-01-24 07:12:08.595303: step: 164/530, loss: 0.00626272801309824
2023-01-24 07:12:09.660222: step: 168/530, loss: 0.0049561080522835255
2023-01-24 07:12:10.710389: step: 172/530, loss: 0.0030540090519934893
2023-01-24 07:12:11.781675: step: 176/530, loss: 0.0015736365457996726
2023-01-24 07:12:12.827129: step: 180/530, loss: 0.0030348163563758135
2023-01-24 07:12:13.891651: step: 184/530, loss: 0.0036298318300396204
2023-01-24 07:12:14.974842: step: 188/530, loss: 0.026296341791749
2023-01-24 07:12:16.037981: step: 192/530, loss: 0.003975518047809601
2023-01-24 07:12:17.098796: step: 196/530, loss: 0.0022665925789624453
2023-01-24 07:12:18.165701: step: 200/530, loss: 0.012239893898367882
2023-01-24 07:12:19.240920: step: 204/530, loss: 0.008207200095057487
2023-01-24 07:12:20.295838: step: 208/530, loss: 0.004619590938091278
2023-01-24 07:12:21.358621: step: 212/530, loss: 0.005163558758795261
2023-01-24 07:12:22.413406: step: 216/530, loss: 0.009994187392294407
2023-01-24 07:12:23.457614: step: 220/530, loss: 0.045528192073106766
2023-01-24 07:12:24.503848: step: 224/530, loss: 0.0012525701895356178
2023-01-24 07:12:25.557805: step: 228/530, loss: 0.0006718150107190013
2023-01-24 07:12:26.616770: step: 232/530, loss: 0.000846226466819644
2023-01-24 07:12:27.668618: step: 236/530, loss: 0.0026339988689869642
2023-01-24 07:12:28.736876: step: 240/530, loss: 0.0029404209926724434
2023-01-24 07:12:29.810866: step: 244/530, loss: 0.0028495085425674915
2023-01-24 07:12:30.885717: step: 248/530, loss: 0.004417273681610823
2023-01-24 07:12:31.943858: step: 252/530, loss: 0.006803040858358145
2023-01-24 07:12:33.002012: step: 256/530, loss: 0.005339222028851509
2023-01-24 07:12:34.067677: step: 260/530, loss: 0.011898625642061234
2023-01-24 07:12:35.138126: step: 264/530, loss: 0.008732391521334648
2023-01-24 07:12:36.204101: step: 268/530, loss: 0.006564145442098379
2023-01-24 07:12:37.277960: step: 272/530, loss: 0.004995036404579878
2023-01-24 07:12:38.338286: step: 276/530, loss: 0.012199289165437222
2023-01-24 07:12:39.398051: step: 280/530, loss: 0.0018923735478892922
2023-01-24 07:12:40.445280: step: 284/530, loss: 0.0011896748328581452
2023-01-24 07:12:41.507420: step: 288/530, loss: 0.00014055822975933552
2023-01-24 07:12:42.559135: step: 292/530, loss: 0.0016469121910631657
2023-01-24 07:12:43.621404: step: 296/530, loss: 0.0032895649783313274
2023-01-24 07:12:44.688998: step: 300/530, loss: 0.04233624413609505
2023-01-24 07:12:45.741001: step: 304/530, loss: 0.0010820298921316862
2023-01-24 07:12:46.799613: step: 308/530, loss: 0.004549311473965645
2023-01-24 07:12:47.870763: step: 312/530, loss: 0.0067084794864058495
2023-01-24 07:12:48.942077: step: 316/530, loss: 0.0011970365885645151
2023-01-24 07:12:50.008873: step: 320/530, loss: 0.00020241158199496567
2023-01-24 07:12:51.069652: step: 324/530, loss: 0.004127122927457094
2023-01-24 07:12:52.127856: step: 328/530, loss: 0.0014319818001240492
2023-01-24 07:12:53.182569: step: 332/530, loss: 0.0004152162582613528
2023-01-24 07:12:54.246995: step: 336/530, loss: 0.0036277943290770054
2023-01-24 07:12:55.329348: step: 340/530, loss: 0.03309885412454605
2023-01-24 07:12:56.401277: step: 344/530, loss: 0.0026101842522621155
2023-01-24 07:12:57.467407: step: 348/530, loss: 0.007072480395436287
2023-01-24 07:12:58.538271: step: 352/530, loss: 0.02057088539004326
2023-01-24 07:12:59.586245: step: 356/530, loss: 0.000909652968402952
2023-01-24 07:13:00.645484: step: 360/530, loss: 0.0030061097349971533
2023-01-24 07:13:01.704527: step: 364/530, loss: 0.0027174167335033417
2023-01-24 07:13:02.815752: step: 368/530, loss: 0.011390430852770805
2023-01-24 07:13:03.895526: step: 372/530, loss: 0.004826629534363747
2023-01-24 07:13:04.969732: step: 376/530, loss: 0.019450442865490913
2023-01-24 07:13:06.033939: step: 380/530, loss: 0.003957065753638744
2023-01-24 07:13:07.095773: step: 384/530, loss: 0.0004515479377005249
2023-01-24 07:13:08.162357: step: 388/530, loss: 0.007636076305061579
2023-01-24 07:13:09.210203: step: 392/530, loss: 0.0028993040323257446
2023-01-24 07:13:10.268251: step: 396/530, loss: 0.0002904027933254838
2023-01-24 07:13:11.324418: step: 400/530, loss: 0.0
2023-01-24 07:13:12.377407: step: 404/530, loss: 2.7460991987027228e-05
2023-01-24 07:13:13.426893: step: 408/530, loss: 0.03271704912185669
2023-01-24 07:13:14.476748: step: 412/530, loss: 0.003774759592488408
2023-01-24 07:13:15.524818: step: 416/530, loss: 0.0030925965402275324
2023-01-24 07:13:16.570353: step: 420/530, loss: 0.004614985082298517
2023-01-24 07:13:17.638219: step: 424/530, loss: 0.005455093923956156
2023-01-24 07:13:18.683694: step: 428/530, loss: 0.006341665051877499
2023-01-24 07:13:19.742714: step: 432/530, loss: 0.017181839793920517
2023-01-24 07:13:20.786729: step: 436/530, loss: 0.002694448223337531
2023-01-24 07:13:21.860938: step: 440/530, loss: 0.05161819979548454
2023-01-24 07:13:22.936020: step: 444/530, loss: 0.0013058632612228394
2023-01-24 07:13:24.005903: step: 448/530, loss: 0.0029132997151464224
2023-01-24 07:13:25.075752: step: 452/530, loss: 0.004522283561527729
2023-01-24 07:13:26.147583: step: 456/530, loss: 0.0010106154950335622
2023-01-24 07:13:27.222789: step: 460/530, loss: 0.005339529365301132
2023-01-24 07:13:28.289657: step: 464/530, loss: 0.0026368643157184124
2023-01-24 07:13:29.338449: step: 468/530, loss: 0.009323693811893463
2023-01-24 07:13:30.399541: step: 472/530, loss: 0.013810019940137863
2023-01-24 07:13:31.457398: step: 476/530, loss: 0.011116879060864449
2023-01-24 07:13:32.553792: step: 480/530, loss: 0.002194151049479842
2023-01-24 07:13:33.609546: step: 484/530, loss: 0.006756369024515152
2023-01-24 07:13:34.677374: step: 488/530, loss: 0.0003016063419636339
2023-01-24 07:13:35.763080: step: 492/530, loss: 0.006293751765042543
2023-01-24 07:13:36.819527: step: 496/530, loss: 0.0029896721243858337
2023-01-24 07:13:37.890703: step: 500/530, loss: 0.006648496259003878
2023-01-24 07:13:38.965046: step: 504/530, loss: 0.00203089346177876
2023-01-24 07:13:40.042347: step: 508/530, loss: 0.005479095969349146
2023-01-24 07:13:41.097328: step: 512/530, loss: 0.0015512114623561502
2023-01-24 07:13:42.157486: step: 516/530, loss: 0.006149264983832836
2023-01-24 07:13:43.225601: step: 520/530, loss: 0.013237375766038895
2023-01-24 07:13:44.289627: step: 524/530, loss: 0.007827612571418285
2023-01-24 07:13:45.349096: step: 528/530, loss: 0.016051651909947395
2023-01-24 07:13:46.408360: step: 532/530, loss: 0.003809115616604686
2023-01-24 07:13:47.463453: step: 536/530, loss: 0.0007821884355507791
2023-01-24 07:13:48.518730: step: 540/530, loss: 0.003712996141985059
2023-01-24 07:13:49.581204: step: 544/530, loss: 0.005278317723423243
2023-01-24 07:13:50.637957: step: 548/530, loss: 3.0008284738869406e-05
2023-01-24 07:13:51.703658: step: 552/530, loss: 0.004711154382675886
2023-01-24 07:13:52.783621: step: 556/530, loss: 0.004152313806116581
2023-01-24 07:13:53.854779: step: 560/530, loss: 0.0036589601077139378
2023-01-24 07:13:54.930055: step: 564/530, loss: 0.0008431334281340241
2023-01-24 07:13:55.989826: step: 568/530, loss: 0.005460687913000584
2023-01-24 07:13:57.071452: step: 572/530, loss: 0.08068236708641052
2023-01-24 07:13:58.117778: step: 576/530, loss: 0.0027963733300566673
2023-01-24 07:13:59.175565: step: 580/530, loss: 0.006012422032654285
2023-01-24 07:14:00.248227: step: 584/530, loss: 0.01018478348851204
2023-01-24 07:14:01.339268: step: 588/530, loss: 0.004423086065798998
2023-01-24 07:14:02.411975: step: 592/530, loss: 0.0031773997470736504
2023-01-24 07:14:03.491886: step: 596/530, loss: 0.030890708789229393
2023-01-24 07:14:04.550437: step: 600/530, loss: 0.028727402910590172
2023-01-24 07:14:05.626116: step: 604/530, loss: 0.002231570426374674
2023-01-24 07:14:06.684045: step: 608/530, loss: 0.003950521815568209
2023-01-24 07:14:07.758784: step: 612/530, loss: 0.012898269109427929
2023-01-24 07:14:08.837641: step: 616/530, loss: 0.004336596932262182
2023-01-24 07:14:09.908964: step: 620/530, loss: 0.002114019123837352
2023-01-24 07:14:10.991535: step: 624/530, loss: 0.02313615195453167
2023-01-24 07:14:12.050076: step: 628/530, loss: 0.008622352033853531
2023-01-24 07:14:13.122942: step: 632/530, loss: 0.007752744480967522
2023-01-24 07:14:14.198258: step: 636/530, loss: 0.0032598418183624744
2023-01-24 07:14:15.248799: step: 640/530, loss: 0.0012892093509435654
2023-01-24 07:14:16.310170: step: 644/530, loss: 0.0027099954895675182
2023-01-24 07:14:17.379873: step: 648/530, loss: 0.0035064304247498512
2023-01-24 07:14:18.427513: step: 652/530, loss: 0.0016977464547380805
2023-01-24 07:14:19.490122: step: 656/530, loss: 0.0031078618485480547
2023-01-24 07:14:20.542926: step: 660/530, loss: 0.011553210206329823
2023-01-24 07:14:21.625233: step: 664/530, loss: 0.10066927224397659
2023-01-24 07:14:22.697119: step: 668/530, loss: 0.0072242445312440395
2023-01-24 07:14:23.760447: step: 672/530, loss: 0.0024160207249224186
2023-01-24 07:14:24.835332: step: 676/530, loss: 0.010552321560680866
2023-01-24 07:14:25.888991: step: 680/530, loss: 0.0035529660526663065
2023-01-24 07:14:26.949215: step: 684/530, loss: 0.0023826996330171824
2023-01-24 07:14:28.001751: step: 688/530, loss: 0.0022004724014550447
2023-01-24 07:14:29.071523: step: 692/530, loss: 0.0024364585988223553
2023-01-24 07:14:30.129191: step: 696/530, loss: 0.012206265702843666
2023-01-24 07:14:31.218087: step: 700/530, loss: 0.00589038897305727
2023-01-24 07:14:32.302427: step: 704/530, loss: 0.004035803955048323
2023-01-24 07:14:33.354967: step: 708/530, loss: 0.002244410803541541
2023-01-24 07:14:34.449915: step: 712/530, loss: 0.004526213277131319
2023-01-24 07:14:35.513885: step: 716/530, loss: 0.004469079896807671
2023-01-24 07:14:36.566903: step: 720/530, loss: 0.00046579272020608187
2023-01-24 07:14:37.650291: step: 724/530, loss: 0.003095470368862152
2023-01-24 07:14:38.713790: step: 728/530, loss: 0.002439818112179637
2023-01-24 07:14:39.770804: step: 732/530, loss: 0.005467942915856838
2023-01-24 07:14:40.821347: step: 736/530, loss: 0.001995539991185069
2023-01-24 07:14:41.887554: step: 740/530, loss: 0.0030730287544429302
2023-01-24 07:14:42.945990: step: 744/530, loss: 0.0012522361939772964
2023-01-24 07:14:44.006311: step: 748/530, loss: 0.002423665951937437
2023-01-24 07:14:45.076106: step: 752/530, loss: 0.006869632750749588
2023-01-24 07:14:46.130787: step: 756/530, loss: 0.0001799451420083642
2023-01-24 07:14:47.193988: step: 760/530, loss: 0.0029497332870960236
2023-01-24 07:14:48.266337: step: 764/530, loss: 0.002520194509997964
2023-01-24 07:14:49.328167: step: 768/530, loss: 0.003950153011828661
2023-01-24 07:14:50.398273: step: 772/530, loss: 0.0004641618288587779
2023-01-24 07:14:51.462281: step: 776/530, loss: 0.00600142776966095
2023-01-24 07:14:52.539970: step: 780/530, loss: 0.007325040176510811
2023-01-24 07:14:53.595800: step: 784/530, loss: 0.0017829153221100569
2023-01-24 07:14:54.642540: step: 788/530, loss: 3.85610073863063e-05
2023-01-24 07:14:55.702918: step: 792/530, loss: 0.03337559476494789
2023-01-24 07:14:56.784518: step: 796/530, loss: 0.003583089681342244
2023-01-24 07:14:57.837028: step: 800/530, loss: 0.004981456324458122
2023-01-24 07:14:58.897873: step: 804/530, loss: 0.0207794439047575
2023-01-24 07:14:59.965559: step: 808/530, loss: 0.0010892957216128707
2023-01-24 07:15:01.023304: step: 812/530, loss: 0.0027127661742269993
2023-01-24 07:15:02.105017: step: 816/530, loss: 0.001927546109072864
2023-01-24 07:15:03.136381: step: 820/530, loss: 1.3253365978016518e-05
2023-01-24 07:15:04.203169: step: 824/530, loss: 0.00104722217656672
2023-01-24 07:15:05.288357: step: 828/530, loss: 0.008881953544914722
2023-01-24 07:15:06.365867: step: 832/530, loss: 0.000970495748333633
2023-01-24 07:15:07.415274: step: 836/530, loss: 0.0029569535981863737
2023-01-24 07:15:08.501566: step: 840/530, loss: 0.003989328630268574
2023-01-24 07:15:09.584703: step: 844/530, loss: 0.001307170488871634
2023-01-24 07:15:10.657075: step: 848/530, loss: 0.002456264803186059
2023-01-24 07:15:11.709173: step: 852/530, loss: 0.004593417048454285
2023-01-24 07:15:12.764752: step: 856/530, loss: 0.002916011493653059
2023-01-24 07:15:13.825234: step: 860/530, loss: 0.003267683321610093
2023-01-24 07:15:14.884937: step: 864/530, loss: 0.00366516993381083
2023-01-24 07:15:15.940163: step: 868/530, loss: 0.0005363342352211475
2023-01-24 07:15:16.998017: step: 872/530, loss: 0.0031091896817088127
2023-01-24 07:15:18.068640: step: 876/530, loss: 0.004570943769067526
2023-01-24 07:15:19.123438: step: 880/530, loss: 0.0002666552609298378
2023-01-24 07:15:20.181880: step: 884/530, loss: 0.0
2023-01-24 07:15:21.244990: step: 888/530, loss: 0.005018032155930996
2023-01-24 07:15:22.298008: step: 892/530, loss: 0.0034780981950461864
2023-01-24 07:15:23.357551: step: 896/530, loss: 0.031597428023815155
2023-01-24 07:15:24.415038: step: 900/530, loss: 0.011771705001592636
2023-01-24 07:15:25.477372: step: 904/530, loss: 0.02103698067367077
2023-01-24 07:15:26.547683: step: 908/530, loss: 0.008566686883568764
2023-01-24 07:15:27.616480: step: 912/530, loss: 0.0006476959679275751
2023-01-24 07:15:28.682918: step: 916/530, loss: 0.017150847241282463
2023-01-24 07:15:29.752237: step: 920/530, loss: 0.0008063833811320364
2023-01-24 07:15:30.808880: step: 924/530, loss: 0.0003461026353761554
2023-01-24 07:15:31.882576: step: 928/530, loss: 0.007730963174253702
2023-01-24 07:15:32.954979: step: 932/530, loss: 0.005475018639117479
2023-01-24 07:15:33.990239: step: 936/530, loss: 0.00197156285867095
2023-01-24 07:15:35.047652: step: 940/530, loss: 0.006250013597309589
2023-01-24 07:15:36.111582: step: 944/530, loss: 0.007999706082046032
2023-01-24 07:15:37.168341: step: 948/530, loss: 0.016621405258774757
2023-01-24 07:15:38.232414: step: 952/530, loss: 0.010028475895524025
2023-01-24 07:15:39.296161: step: 956/530, loss: 0.03006618842482567
2023-01-24 07:15:40.372408: step: 960/530, loss: 0.0018241485813632607
2023-01-24 07:15:41.435048: step: 964/530, loss: 0.0054228161461651325
2023-01-24 07:15:42.493499: step: 968/530, loss: 0.0029113006312400103
2023-01-24 07:15:43.545739: step: 972/530, loss: 0.006533229257911444
2023-01-24 07:15:44.600248: step: 976/530, loss: 0.0004995585768483579
2023-01-24 07:15:45.660772: step: 980/530, loss: 0.010044052265584469
2023-01-24 07:15:46.741913: step: 984/530, loss: 0.004120043013244867
2023-01-24 07:15:47.812197: step: 988/530, loss: 0.011376149952411652
2023-01-24 07:15:48.874681: step: 992/530, loss: 0.012200153432786465
2023-01-24 07:15:49.931656: step: 996/530, loss: 0.0024647866375744343
2023-01-24 07:15:50.995687: step: 1000/530, loss: 0.00512643251568079
2023-01-24 07:15:52.048476: step: 1004/530, loss: 0.0031221136450767517
2023-01-24 07:15:53.098182: step: 1008/530, loss: 0.0029007140547037125
2023-01-24 07:15:54.149180: step: 1012/530, loss: 0.023068975657224655
2023-01-24 07:15:55.211076: step: 1016/530, loss: 0.047838084399700165
2023-01-24 07:15:56.285423: step: 1020/530, loss: 0.01036304421722889
2023-01-24 07:15:57.337633: step: 1024/530, loss: 0.0007745142211206257
2023-01-24 07:15:58.387987: step: 1028/530, loss: 0.004627063404768705
2023-01-24 07:15:59.448423: step: 1032/530, loss: 0.03404998779296875
2023-01-24 07:16:00.509796: step: 1036/530, loss: 0.005893825087696314
2023-01-24 07:16:01.582565: step: 1040/530, loss: 0.003592468798160553
2023-01-24 07:16:02.644717: step: 1044/530, loss: 0.031811878085136414
2023-01-24 07:16:03.697568: step: 1048/530, loss: 0.000999869778752327
2023-01-24 07:16:04.764394: step: 1052/530, loss: 0.0028399198781698942
2023-01-24 07:16:05.819754: step: 1056/530, loss: 0.0024975307751446962
2023-01-24 07:16:06.891967: step: 1060/530, loss: 0.006558599416166544
2023-01-24 07:16:07.956602: step: 1064/530, loss: 0.0022379420697689056
2023-01-24 07:16:09.015023: step: 1068/530, loss: 0.00027735999901778996
2023-01-24 07:16:10.072858: step: 1072/530, loss: 0.0037738613318651915
2023-01-24 07:16:11.124527: step: 1076/530, loss: 0.0014299798058345914
2023-01-24 07:16:12.183817: step: 1080/530, loss: 0.00029566450393758714
2023-01-24 07:16:13.248814: step: 1084/530, loss: 0.0005588725907728076
2023-01-24 07:16:14.303553: step: 1088/530, loss: 0.006791661959141493
2023-01-24 07:16:15.363690: step: 1092/530, loss: 0.0004303640453144908
2023-01-24 07:16:16.399214: step: 1096/530, loss: 0.0012932104291394353
2023-01-24 07:16:17.465996: step: 1100/530, loss: 0.010163214057683945
2023-01-24 07:16:18.516157: step: 1104/530, loss: 0.00528957461938262
2023-01-24 07:16:19.597274: step: 1108/530, loss: 0.0036679564509540796
2023-01-24 07:16:20.657164: step: 1112/530, loss: 0.003352685598656535
2023-01-24 07:16:21.707460: step: 1116/530, loss: 0.010087912902235985
2023-01-24 07:16:22.781870: step: 1120/530, loss: 0.00860240962356329
2023-01-24 07:16:23.855942: step: 1124/530, loss: 0.015045109204947948
2023-01-24 07:16:24.915477: step: 1128/530, loss: 0.03174243122339249
2023-01-24 07:16:25.971542: step: 1132/530, loss: 0.003598960116505623
2023-01-24 07:16:27.027127: step: 1136/530, loss: 0.001524300780147314
2023-01-24 07:16:28.081808: step: 1140/530, loss: 0.03787195682525635
2023-01-24 07:16:29.168529: step: 1144/530, loss: 0.006270979065448046
2023-01-24 07:16:30.216249: step: 1148/530, loss: 0.037914324551820755
2023-01-24 07:16:31.278857: step: 1152/530, loss: 0.005124355666339397
2023-01-24 07:16:32.335454: step: 1156/530, loss: 0.002639026613906026
2023-01-24 07:16:33.386477: step: 1160/530, loss: 0.001762067317031324
2023-01-24 07:16:34.459872: step: 1164/530, loss: 0.004346344619989395
2023-01-24 07:16:35.534259: step: 1168/530, loss: 0.004185069818049669
2023-01-24 07:16:36.586929: step: 1172/530, loss: 0.005861604120582342
2023-01-24 07:16:37.652023: step: 1176/530, loss: 0.00017850550648290664
2023-01-24 07:16:38.712594: step: 1180/530, loss: 0.0061139194294810295
2023-01-24 07:16:39.777752: step: 1184/530, loss: 0.0057471212930977345
2023-01-24 07:16:40.830943: step: 1188/530, loss: 0.000685409118887037
2023-01-24 07:16:41.892079: step: 1192/530, loss: 0.0029984633438289165
2023-01-24 07:16:42.954818: step: 1196/530, loss: 0.04240376129746437
2023-01-24 07:16:44.020894: step: 1200/530, loss: 0.003919998649507761
2023-01-24 07:16:45.075613: step: 1204/530, loss: 0.005296318791806698
2023-01-24 07:16:46.130072: step: 1208/530, loss: 0.0004119572404306382
2023-01-24 07:16:47.187353: step: 1212/530, loss: 0.0044286539778113365
2023-01-24 07:16:48.248268: step: 1216/530, loss: 0.02172204479575157
2023-01-24 07:16:49.321647: step: 1220/530, loss: 0.007352832239121199
2023-01-24 07:16:50.377004: step: 1224/530, loss: 0.01899542845785618
2023-01-24 07:16:51.437545: step: 1228/530, loss: 0.0027936678379774094
2023-01-24 07:16:52.490468: step: 1232/530, loss: 0.003451894037425518
2023-01-24 07:16:53.559036: step: 1236/530, loss: 0.0018620435148477554
2023-01-24 07:16:54.629368: step: 1240/530, loss: 0.002224933123216033
2023-01-24 07:16:55.713346: step: 1244/530, loss: 0.007762577384710312
2023-01-24 07:16:56.780992: step: 1248/530, loss: 0.017033562064170837
2023-01-24 07:16:57.828890: step: 1252/530, loss: 0.004851041827350855
2023-01-24 07:16:58.895063: step: 1256/530, loss: 0.0036906248424202204
2023-01-24 07:16:59.972808: step: 1260/530, loss: 0.004080755636096001
2023-01-24 07:17:01.039930: step: 1264/530, loss: 0.022719234228134155
2023-01-24 07:17:02.107800: step: 1268/530, loss: 0.005870419088751078
2023-01-24 07:17:03.155341: step: 1272/530, loss: 0.0017245433991774917
2023-01-24 07:17:04.204221: step: 1276/530, loss: 0.0006084832129999995
2023-01-24 07:17:05.261923: step: 1280/530, loss: 0.006511473562568426
2023-01-24 07:17:06.320948: step: 1284/530, loss: 0.004114076495170593
2023-01-24 07:17:07.369999: step: 1288/530, loss: 0.026190178468823433
2023-01-24 07:17:08.437266: step: 1292/530, loss: 0.014754963107407093
2023-01-24 07:17:09.490694: step: 1296/530, loss: 0.022561874240636826
2023-01-24 07:17:10.624036: step: 1300/530, loss: 0.005654872395098209
2023-01-24 07:17:11.682644: step: 1304/530, loss: 0.005959267262369394
2023-01-24 07:17:12.745268: step: 1308/530, loss: 0.004220210015773773
2023-01-24 07:17:13.819905: step: 1312/530, loss: 0.0037146471440792084
2023-01-24 07:17:14.874223: step: 1316/530, loss: 0.005266808904707432
2023-01-24 07:17:15.936642: step: 1320/530, loss: 0.01826951652765274
2023-01-24 07:17:17.017038: step: 1324/530, loss: 0.0056020235642790794
2023-01-24 07:17:18.071443: step: 1328/530, loss: 0.0016568299615755677
2023-01-24 07:17:19.158812: step: 1332/530, loss: 0.01378651149570942
2023-01-24 07:17:20.212001: step: 1336/530, loss: 0.0017705034697428346
2023-01-24 07:17:21.280689: step: 1340/530, loss: 0.009712358005344868
2023-01-24 07:17:22.326850: step: 1344/530, loss: 0.003285177517682314
2023-01-24 07:17:23.412018: step: 1348/530, loss: 0.004849891643971205
2023-01-24 07:17:24.486387: step: 1352/530, loss: 0.0017801231006160378
2023-01-24 07:17:25.541583: step: 1356/530, loss: 0.0005661412724293768
2023-01-24 07:17:26.593631: step: 1360/530, loss: 0.001966212410479784
2023-01-24 07:17:27.642155: step: 1364/530, loss: 0.001030753250233829
2023-01-24 07:17:28.699984: step: 1368/530, loss: 0.006670091766864061
2023-01-24 07:17:29.749321: step: 1372/530, loss: 0.004116909112781286
2023-01-24 07:17:30.806838: step: 1376/530, loss: 0.004152644891291857
2023-01-24 07:17:31.870443: step: 1380/530, loss: 0.023611480370163918
2023-01-24 07:17:32.943659: step: 1384/530, loss: 0.0012033339589834213
2023-01-24 07:17:34.004101: step: 1388/530, loss: 0.01597212813794613
2023-01-24 07:17:35.090234: step: 1392/530, loss: 0.004310728516429663
2023-01-24 07:17:36.155052: step: 1396/530, loss: 0.0
2023-01-24 07:17:37.214364: step: 1400/530, loss: 0.007765563670545816
2023-01-24 07:17:38.269168: step: 1404/530, loss: 0.002658066339790821
2023-01-24 07:17:39.329296: step: 1408/530, loss: 0.00451562087982893
2023-01-24 07:17:40.387542: step: 1412/530, loss: 0.0007149119628593326
2023-01-24 07:17:41.442210: step: 1416/530, loss: 0.0023501284886151552
2023-01-24 07:17:42.512841: step: 1420/530, loss: 0.0010535606415942311
2023-01-24 07:17:43.561306: step: 1424/530, loss: 0.0032468412537127733
2023-01-24 07:17:44.626722: step: 1428/530, loss: 0.0017454884946346283
2023-01-24 07:17:45.687511: step: 1432/530, loss: 0.0031624729745090008
2023-01-24 07:17:46.737707: step: 1436/530, loss: 0.0014564775628969073
2023-01-24 07:17:47.806317: step: 1440/530, loss: 0.001146955182775855
2023-01-24 07:17:48.870198: step: 1444/530, loss: 0.0021946232300251722
2023-01-24 07:17:49.929422: step: 1448/530, loss: 0.0005177851999178529
2023-01-24 07:17:50.987453: step: 1452/530, loss: 0.003388088196516037
2023-01-24 07:17:52.062415: step: 1456/530, loss: 0.0035457343328744173
2023-01-24 07:17:53.118392: step: 1460/530, loss: 0.0037906935904175043
2023-01-24 07:17:54.183304: step: 1464/530, loss: 0.017454415559768677
2023-01-24 07:17:55.242277: step: 1468/530, loss: 2.6523704946157522e-05
2023-01-24 07:17:56.302615: step: 1472/530, loss: 0.0074873254634439945
2023-01-24 07:17:57.359231: step: 1476/530, loss: 0.00312393088825047
2023-01-24 07:17:58.402176: step: 1480/530, loss: 0.0010542598320171237
2023-01-24 07:17:59.480435: step: 1484/530, loss: 0.007353622000664473
2023-01-24 07:18:00.538501: step: 1488/530, loss: 0.0031232002656906843
2023-01-24 07:18:01.599262: step: 1492/530, loss: 0.0025893906131386757
2023-01-24 07:18:02.674546: step: 1496/530, loss: 0.0038539941888302565
2023-01-24 07:18:03.728910: step: 1500/530, loss: 0.0005502093117684126
2023-01-24 07:18:04.791228: step: 1504/530, loss: 0.004979806952178478
2023-01-24 07:18:05.839336: step: 1508/530, loss: 0.0071946061216294765
2023-01-24 07:18:06.912661: step: 1512/530, loss: 0.004448692314326763
2023-01-24 07:18:07.976565: step: 1516/530, loss: 0.008576873689889908
2023-01-24 07:18:09.026595: step: 1520/530, loss: 0.010550213046371937
2023-01-24 07:18:10.092112: step: 1524/530, loss: 0.002015024423599243
2023-01-24 07:18:11.154737: step: 1528/530, loss: 0.0003246348933316767
2023-01-24 07:18:12.218201: step: 1532/530, loss: 0.001094534993171692
2023-01-24 07:18:13.263585: step: 1536/530, loss: 7.546626147814095e-05
2023-01-24 07:18:14.316661: step: 1540/530, loss: 0.01880665309727192
2023-01-24 07:18:15.403341: step: 1544/530, loss: 0.0005597545532509685
2023-01-24 07:18:16.451451: step: 1548/530, loss: 0.0004759436706081033
2023-01-24 07:18:17.517753: step: 1552/530, loss: 0.0021646360401064157
2023-01-24 07:18:18.566299: step: 1556/530, loss: 0.003993749152868986
2023-01-24 07:18:19.630015: step: 1560/530, loss: 0.016274502500891685
2023-01-24 07:18:20.704237: step: 1564/530, loss: 0.00545907998457551
2023-01-24 07:18:21.775796: step: 1568/530, loss: 0.002751567866653204
2023-01-24 07:18:22.841107: step: 1572/530, loss: 0.0025406652130186558
2023-01-24 07:18:23.891661: step: 1576/530, loss: 0.007754336576908827
2023-01-24 07:18:24.947059: step: 1580/530, loss: 0.0018910899525508285
2023-01-24 07:18:26.019426: step: 1584/530, loss: 0.0033316491171717644
2023-01-24 07:18:27.080381: step: 1588/530, loss: 0.004890511743724346
2023-01-24 07:18:28.139866: step: 1592/530, loss: 0.0029237642884254456
2023-01-24 07:18:29.213732: step: 1596/530, loss: 0.0047064004465937614
2023-01-24 07:18:30.267469: step: 1600/530, loss: 0.012439337559044361
2023-01-24 07:18:31.328018: step: 1604/530, loss: 0.004547871649265289
2023-01-24 07:18:32.387831: step: 1608/530, loss: 0.007630421780049801
2023-01-24 07:18:33.452254: step: 1612/530, loss: 0.003931929357349873
2023-01-24 07:18:34.512328: step: 1616/530, loss: 0.0010509529383853078
2023-01-24 07:18:35.574939: step: 1620/530, loss: 1.1811276635853574e-05
2023-01-24 07:18:36.641377: step: 1624/530, loss: 0.006874265149235725
2023-01-24 07:18:37.698097: step: 1628/530, loss: 0.0033264446537941694
2023-01-24 07:18:38.778336: step: 1632/530, loss: 0.011376772075891495
2023-01-24 07:18:39.842093: step: 1636/530, loss: 0.0079652676358819
2023-01-24 07:18:40.905555: step: 1640/530, loss: 0.011988547630608082
2023-01-24 07:18:41.957626: step: 1644/530, loss: 0.001716411323286593
2023-01-24 07:18:43.028281: step: 1648/530, loss: 0.006442325189709663
2023-01-24 07:18:44.079487: step: 1652/530, loss: 0.004815125837922096
2023-01-24 07:18:45.136401: step: 1656/530, loss: 0.0030966070480644703
2023-01-24 07:18:46.177049: step: 1660/530, loss: 0.0030099775176495314
2023-01-24 07:18:47.252857: step: 1664/530, loss: 0.016650628298521042
2023-01-24 07:18:48.312834: step: 1668/530, loss: 0.005719719920307398
2023-01-24 07:18:49.383524: step: 1672/530, loss: 0.006935207638889551
2023-01-24 07:18:50.466273: step: 1676/530, loss: 0.00628667650744319
2023-01-24 07:18:51.523507: step: 1680/530, loss: 0.002305967966094613
2023-01-24 07:18:52.591979: step: 1684/530, loss: 0.020011622458696365
2023-01-24 07:18:53.632701: step: 1688/530, loss: 6.817995017627254e-05
2023-01-24 07:18:54.690872: step: 1692/530, loss: 0.0026268830988556147
2023-01-24 07:18:55.753534: step: 1696/530, loss: 0.01031313743442297
2023-01-24 07:18:56.811501: step: 1700/530, loss: 0.008934480138123035
2023-01-24 07:18:57.899698: step: 1704/530, loss: 0.009671562351286411
2023-01-24 07:18:58.952443: step: 1708/530, loss: 0.007136296946555376
2023-01-24 07:19:00.020643: step: 1712/530, loss: 0.0012411527568474412
2023-01-24 07:19:01.080344: step: 1716/530, loss: 0.002238886198028922
2023-01-24 07:19:02.148375: step: 1720/530, loss: 0.004407891537994146
2023-01-24 07:19:03.201756: step: 1724/530, loss: 0.0024260831996798515
2023-01-24 07:19:04.280336: step: 1728/530, loss: 0.0027922929730266333
2023-01-24 07:19:05.334916: step: 1732/530, loss: 0.0013444084906950593
2023-01-24 07:19:06.403420: step: 1736/530, loss: 0.003485999070107937
2023-01-24 07:19:07.469640: step: 1740/530, loss: 0.0022258758544921875
2023-01-24 07:19:08.534342: step: 1744/530, loss: 0.005299723707139492
2023-01-24 07:19:09.603745: step: 1748/530, loss: 0.0040181661024689674
2023-01-24 07:19:10.663885: step: 1752/530, loss: 0.00608889851719141
2023-01-24 07:19:11.732380: step: 1756/530, loss: 0.008787447586655617
2023-01-24 07:19:12.792220: step: 1760/530, loss: 0.00335937412455678
2023-01-24 07:19:13.842874: step: 1764/530, loss: 0.0006332100601866841
2023-01-24 07:19:14.898654: step: 1768/530, loss: 0.0026157693937420845
2023-01-24 07:19:15.968678: step: 1772/530, loss: 0.012421693652868271
2023-01-24 07:19:17.036765: step: 1776/530, loss: 0.014119272120296955
2023-01-24 07:19:18.094218: step: 1780/530, loss: 0.004634774290025234
2023-01-24 07:19:19.159864: step: 1784/530, loss: 0.004941467195749283
2023-01-24 07:19:20.215154: step: 1788/530, loss: 0.009459305554628372
2023-01-24 07:19:21.267505: step: 1792/530, loss: 0.0013591843890026212
2023-01-24 07:19:22.313790: step: 1796/530, loss: 0.0013900460908189416
2023-01-24 07:19:23.375636: step: 1800/530, loss: 0.0014651138335466385
2023-01-24 07:19:24.450270: step: 1804/530, loss: 0.004790878389030695
2023-01-24 07:19:25.505396: step: 1808/530, loss: 0.0011318136239424348
2023-01-24 07:19:26.567812: step: 1812/530, loss: 0.0114417290315032
2023-01-24 07:19:27.633430: step: 1816/530, loss: 0.0011340589262545109
2023-01-24 07:19:28.696872: step: 1820/530, loss: 0.002051965333521366
2023-01-24 07:19:29.739287: step: 1824/530, loss: 0.009309789165854454
2023-01-24 07:19:30.799032: step: 1828/530, loss: 0.008583464659750462
2023-01-24 07:19:31.847779: step: 1832/530, loss: 0.007632608059793711
2023-01-24 07:19:32.916155: step: 1836/530, loss: 0.0067378380335867405
2023-01-24 07:19:33.969099: step: 1840/530, loss: 0.005021728575229645
2023-01-24 07:19:35.023040: step: 1844/530, loss: 0.00027121329912915826
2023-01-24 07:19:36.090266: step: 1848/530, loss: 4.9419384595239535e-05
2023-01-24 07:19:37.144825: step: 1852/530, loss: 0.003072956344112754
2023-01-24 07:19:38.205026: step: 1856/530, loss: 0.013318224810063839
2023-01-24 07:19:39.262425: step: 1860/530, loss: 0.00018171007104683667
2023-01-24 07:19:40.319488: step: 1864/530, loss: 0.005385766737163067
2023-01-24 07:19:41.378437: step: 1868/530, loss: 0.011189702898263931
2023-01-24 07:19:42.433368: step: 1872/530, loss: 0.00024802316329441965
2023-01-24 07:19:43.488402: step: 1876/530, loss: 0.004605870693922043
2023-01-24 07:19:44.529398: step: 1880/530, loss: 0.0006274774787016213
2023-01-24 07:19:45.589769: step: 1884/530, loss: 0.0008639899315312505
2023-01-24 07:19:46.656049: step: 1888/530, loss: 0.015022809617221355
2023-01-24 07:19:47.733398: step: 1892/530, loss: 0.01180972345173359
2023-01-24 07:19:48.788040: step: 1896/530, loss: 0.0068591078743338585
2023-01-24 07:19:49.841910: step: 1900/530, loss: 0.0009627597755752504
2023-01-24 07:19:50.906242: step: 1904/530, loss: 0.00474949786439538
2023-01-24 07:19:51.977696: step: 1908/530, loss: 0.009530254639685154
2023-01-24 07:19:53.033082: step: 1912/530, loss: 0.008258212357759476
2023-01-24 07:19:54.091419: step: 1916/530, loss: 0.001977296080440283
2023-01-24 07:19:55.156817: step: 1920/530, loss: 0.0033020772971212864
2023-01-24 07:19:56.226075: step: 1924/530, loss: 0.007882621139287949
2023-01-24 07:19:57.298406: step: 1928/530, loss: 0.0013385629281401634
2023-01-24 07:19:58.352070: step: 1932/530, loss: 0.0016821427270770073
2023-01-24 07:19:59.405776: step: 1936/530, loss: 0.005206750705838203
2023-01-24 07:20:00.461114: step: 1940/530, loss: 0.0021994311828166246
2023-01-24 07:20:01.527738: step: 1944/530, loss: 0.0020676536951214075
2023-01-24 07:20:02.593557: step: 1948/530, loss: 1.5307270587072708e-05
2023-01-24 07:20:03.668891: step: 1952/530, loss: 0.012561663053929806
2023-01-24 07:20:04.722884: step: 1956/530, loss: 0.00014406019181478769
2023-01-24 07:20:05.769032: step: 1960/530, loss: 0.0021386772859841585
2023-01-24 07:20:06.833270: step: 1964/530, loss: 0.0024375899229198694
2023-01-24 07:20:07.899650: step: 1968/530, loss: 0.005967001896351576
2023-01-24 07:20:08.963283: step: 1972/530, loss: 0.002499812515452504
2023-01-24 07:20:10.021600: step: 1976/530, loss: 0.011896908283233643
2023-01-24 07:20:11.082527: step: 1980/530, loss: 0.026470324024558067
2023-01-24 07:20:12.146149: step: 1984/530, loss: 0.002903343178331852
2023-01-24 07:20:13.205546: step: 1988/530, loss: 0.005702989175915718
2023-01-24 07:20:14.279379: step: 1992/530, loss: 0.004622644279152155
2023-01-24 07:20:15.329639: step: 1996/530, loss: 0.005409538745880127
2023-01-24 07:20:16.391093: step: 2000/530, loss: 0.028159616515040398
2023-01-24 07:20:17.452503: step: 2004/530, loss: 0.007374122738838196
2023-01-24 07:20:18.514432: step: 2008/530, loss: 0.02760150283575058
2023-01-24 07:20:19.571879: step: 2012/530, loss: 0.0006752068875357509
2023-01-24 07:20:20.622570: step: 2016/530, loss: 0.0023797007743269205
2023-01-24 07:20:21.678003: step: 2020/530, loss: 0.00374113698489964
2023-01-24 07:20:22.746408: step: 2024/530, loss: 0.020107867196202278
2023-01-24 07:20:23.811412: step: 2028/530, loss: 0.025108661502599716
2023-01-24 07:20:24.887193: step: 2032/530, loss: 0.0013643424026668072
2023-01-24 07:20:25.962320: step: 2036/530, loss: 0.02076365426182747
2023-01-24 07:20:27.012887: step: 2040/530, loss: 1.422083005309105e-05
2023-01-24 07:20:28.067367: step: 2044/530, loss: 0.0027981242164969444
2023-01-24 07:20:29.123479: step: 2048/530, loss: 0.00246158754453063
2023-01-24 07:20:30.179508: step: 2052/530, loss: 0.005010621156543493
2023-01-24 07:20:31.249724: step: 2056/530, loss: 0.003826865227892995
2023-01-24 07:20:32.314840: step: 2060/530, loss: 0.027288202196359634
2023-01-24 07:20:33.372956: step: 2064/530, loss: 0.005993329919874668
2023-01-24 07:20:34.441944: step: 2068/530, loss: 0.005882537458091974
2023-01-24 07:20:35.497563: step: 2072/530, loss: 0.005566827952861786
2023-01-24 07:20:36.568250: step: 2076/530, loss: 0.02576258033514023
2023-01-24 07:20:37.626660: step: 2080/530, loss: 0.0036768531426787376
2023-01-24 07:20:38.688158: step: 2084/530, loss: 0.019224215298891068
2023-01-24 07:20:39.752210: step: 2088/530, loss: 0.005851175170391798
2023-01-24 07:20:40.822977: step: 2092/530, loss: 0.007477684877812862
2023-01-24 07:20:41.882367: step: 2096/530, loss: 0.0010198538657277822
2023-01-24 07:20:42.932222: step: 2100/530, loss: 0.02209564484655857
2023-01-24 07:20:43.979041: step: 2104/530, loss: 0.007262577768415213
2023-01-24 07:20:45.051907: step: 2108/530, loss: 0.020717797800898552
2023-01-24 07:20:46.130193: step: 2112/530, loss: 0.016722410917282104
2023-01-24 07:20:47.202663: step: 2116/530, loss: 0.015207355841994286
2023-01-24 07:20:48.250546: step: 2120/530, loss: 0.0026982848066836596
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38445120949188194, 'r': 0.33630361968834455, 'f1': 0.3587692461047724}, 'combined': 0.2643562866035165, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39732454172211545, 'r': 0.3006594367663454, 'f1': 0.34229832377045727}, 'combined': 0.2270165048840338, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34593091334894616, 'r': 0.27975852272727275, 'f1': 0.3093455497382199}, 'combined': 0.2062303664921466, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.39929098908622607, 'r': 0.29705038980463183, 'f1': 0.34066493116483576}, 'combined': 0.2223286919181033, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3687351613759624, 'r': 0.32885299022144654, 'f1': 0.34765401373460847}, 'combined': 0.2561661153833957, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3946066073493055, 'r': 0.3081689695489815, 'f1': 0.3460721048411021}, 'combined': 0.229519323417933, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 07:23:15.248821: step: 4/530, loss: 0.005412028171122074
2023-01-24 07:23:16.295991: step: 8/530, loss: 0.00799354538321495
2023-01-24 07:23:17.347590: step: 12/530, loss: 0.0029653378296643496
2023-01-24 07:23:18.397423: step: 16/530, loss: 0.0020137429237365723
2023-01-24 07:23:19.456042: step: 20/530, loss: 0.005955493077635765
2023-01-24 07:23:20.523659: step: 24/530, loss: 0.0054463790729641914
2023-01-24 07:23:21.575763: step: 28/530, loss: 0.012393060140311718
2023-01-24 07:23:22.618056: step: 32/530, loss: 0.011158104054629803
2023-01-24 07:23:23.665389: step: 36/530, loss: 0.00027762309764511883
2023-01-24 07:23:24.731630: step: 40/530, loss: 0.007811457850039005
2023-01-24 07:23:25.797598: step: 44/530, loss: 0.003230190835893154
2023-01-24 07:23:26.852638: step: 48/530, loss: 0.001531480811536312
2023-01-24 07:23:27.931995: step: 52/530, loss: 0.007215119898319244
2023-01-24 07:23:28.997123: step: 56/530, loss: 0.003241087542846799
2023-01-24 07:23:30.039842: step: 60/530, loss: 0.008438044227659702
2023-01-24 07:23:31.083078: step: 64/530, loss: 0.000715838628821075
2023-01-24 07:23:32.148645: step: 68/530, loss: 0.009207389317452908
2023-01-24 07:23:33.204854: step: 72/530, loss: 0.002230619313195348
2023-01-24 07:23:34.256626: step: 76/530, loss: 0.004442438017576933
2023-01-24 07:23:35.313541: step: 80/530, loss: 0.004486694000661373
2023-01-24 07:23:36.380865: step: 84/530, loss: 0.0038605076260864735
2023-01-24 07:23:37.449319: step: 88/530, loss: 0.006671932991594076
2023-01-24 07:23:38.530437: step: 92/530, loss: 0.004980923607945442
2023-01-24 07:23:39.585316: step: 96/530, loss: 0.006761566270142794
2023-01-24 07:23:40.664631: step: 100/530, loss: 0.008938229642808437
2023-01-24 07:23:41.733673: step: 104/530, loss: 0.0012818132527172565
2023-01-24 07:23:42.805916: step: 108/530, loss: 0.0050885300152003765
2023-01-24 07:23:43.869067: step: 112/530, loss: 0.0027815958019346
2023-01-24 07:23:44.936898: step: 116/530, loss: 0.00494090560823679
2023-01-24 07:23:46.019021: step: 120/530, loss: 0.00021240457135718316
2023-01-24 07:23:47.066636: step: 124/530, loss: 0.0010529932333156466
2023-01-24 07:23:48.114338: step: 128/530, loss: 0.004356097895652056
2023-01-24 07:23:49.176060: step: 132/530, loss: 0.0007834674906916916
2023-01-24 07:23:50.238953: step: 136/530, loss: 0.00023933756165206432
2023-01-24 07:23:51.310617: step: 140/530, loss: 0.002770785940811038
2023-01-24 07:23:52.379141: step: 144/530, loss: 0.0031675801146775484
2023-01-24 07:23:53.442118: step: 148/530, loss: 0.0037156403996050358
2023-01-24 07:23:54.509030: step: 152/530, loss: 0.009367075748741627
2023-01-24 07:23:55.549872: step: 156/530, loss: 0.0020011523738503456
2023-01-24 07:23:56.615982: step: 160/530, loss: 0.008942898362874985
2023-01-24 07:23:57.679010: step: 164/530, loss: 0.0025392426177859306
2023-01-24 07:23:58.739945: step: 168/530, loss: 0.0016115570906549692
2023-01-24 07:23:59.802803: step: 172/530, loss: 0.001309082144871354
2023-01-24 07:24:00.864345: step: 176/530, loss: 0.006817675661295652
2023-01-24 07:24:01.920124: step: 180/530, loss: 0.010326175019145012
2023-01-24 07:24:02.970605: step: 184/530, loss: 0.008611856028437614
2023-01-24 07:24:04.022239: step: 188/530, loss: 0.001145673100836575
2023-01-24 07:24:05.080172: step: 192/530, loss: 0.000756487890612334
2023-01-24 07:24:06.148245: step: 196/530, loss: 0.001342158648185432
2023-01-24 07:24:07.192458: step: 200/530, loss: 0.00012038677232339978
2023-01-24 07:24:08.253584: step: 204/530, loss: 2.525281706766691e-05
2023-01-24 07:24:09.322953: step: 208/530, loss: 0.011847678571939468
2023-01-24 07:24:10.389001: step: 212/530, loss: 0.0037661634851247072
2023-01-24 07:24:11.456825: step: 216/530, loss: 0.012080597691237926
2023-01-24 07:24:12.520179: step: 220/530, loss: 0.008036069571971893
2023-01-24 07:24:13.584789: step: 224/530, loss: 0.0011363114463165402
2023-01-24 07:24:14.654980: step: 228/530, loss: 0.004003074485808611
2023-01-24 07:24:15.709964: step: 232/530, loss: 0.011443397961556911
2023-01-24 07:24:16.782266: step: 236/530, loss: 0.004135990981012583
2023-01-24 07:24:17.856752: step: 240/530, loss: 0.00223351432941854
2023-01-24 07:24:18.909706: step: 244/530, loss: 0.019779633730649948
2023-01-24 07:24:19.962928: step: 248/530, loss: 0.0012376937083899975
2023-01-24 07:24:21.031738: step: 252/530, loss: 0.0026815005112439394
2023-01-24 07:24:22.085301: step: 256/530, loss: 0.0013566955458372831
2023-01-24 07:24:23.147365: step: 260/530, loss: 0.003945737611502409
2023-01-24 07:24:24.203011: step: 264/530, loss: 0.0039780898950994015
2023-01-24 07:24:25.275414: step: 268/530, loss: 0.0025932311546057463
2023-01-24 07:24:26.348376: step: 272/530, loss: 0.005599125754088163
2023-01-24 07:24:27.399411: step: 276/530, loss: 0.005882116965949535
2023-01-24 07:24:28.473790: step: 280/530, loss: 0.004954581148922443
2023-01-24 07:24:29.534211: step: 284/530, loss: 0.0007497848710045218
2023-01-24 07:24:30.570009: step: 288/530, loss: 0.028717370703816414
2023-01-24 07:24:31.626193: step: 292/530, loss: 0.012738501653075218
2023-01-24 07:24:32.690325: step: 296/530, loss: 0.0017897089710459113
2023-01-24 07:24:33.754112: step: 300/530, loss: 0.0008936472004279494
2023-01-24 07:24:34.820824: step: 304/530, loss: 0.002889385214075446
2023-01-24 07:24:35.885276: step: 308/530, loss: 0.01940256729722023
2023-01-24 07:24:36.950646: step: 312/530, loss: 0.0032737015280872583
2023-01-24 07:24:38.011573: step: 316/530, loss: 0.0023911716416478157
2023-01-24 07:24:39.083761: step: 320/530, loss: 0.009060151875019073
2023-01-24 07:24:40.190492: step: 324/530, loss: 0.008702633902430534
2023-01-24 07:24:41.243382: step: 328/530, loss: 0.0012962038163095713
2023-01-24 07:24:42.295797: step: 332/530, loss: 0.003141292603686452
2023-01-24 07:24:43.345692: step: 336/530, loss: 0.02390456199645996
2023-01-24 07:24:44.399156: step: 340/530, loss: 0.002323173452168703
2023-01-24 07:24:45.442999: step: 344/530, loss: 0.0007194870850071311
2023-01-24 07:24:46.506187: step: 348/530, loss: 0.010091970674693584
2023-01-24 07:24:47.560393: step: 352/530, loss: 0.008088504895567894
2023-01-24 07:24:48.608587: step: 356/530, loss: 0.007213442120701075
2023-01-24 07:24:49.696116: step: 360/530, loss: 0.005028596147894859
2023-01-24 07:24:50.752654: step: 364/530, loss: 0.028195269405841827
2023-01-24 07:24:51.811789: step: 368/530, loss: 0.0008819270879030228
2023-01-24 07:24:52.862554: step: 372/530, loss: 0.002613019198179245
2023-01-24 07:24:53.909491: step: 376/530, loss: 0.0042737871408462524
2023-01-24 07:24:54.978499: step: 380/530, loss: 0.0020033158361911774
2023-01-24 07:24:56.049713: step: 384/530, loss: 0.008950011804699898
2023-01-24 07:24:57.131943: step: 388/530, loss: 0.03141036257147789
2023-01-24 07:24:58.204468: step: 392/530, loss: 0.002115897135809064
2023-01-24 07:24:59.269324: step: 396/530, loss: 0.007330651860684156
2023-01-24 07:25:00.345340: step: 400/530, loss: 0.00850588083267212
2023-01-24 07:25:01.402986: step: 404/530, loss: 0.007080476265400648
2023-01-24 07:25:02.465431: step: 408/530, loss: 0.027313269674777985
2023-01-24 07:25:03.514072: step: 412/530, loss: 0.004629465285688639
2023-01-24 07:25:04.578785: step: 416/530, loss: 0.0057193925604224205
2023-01-24 07:25:05.640026: step: 420/530, loss: 0.002772792475298047
2023-01-24 07:25:06.699116: step: 424/530, loss: 0.005171502940356731
2023-01-24 07:25:07.769199: step: 428/530, loss: 0.004835939966142178
2023-01-24 07:25:08.837520: step: 432/530, loss: 0.0023077453952282667
2023-01-24 07:25:09.892960: step: 436/530, loss: 0.00010802211181726307
2023-01-24 07:25:10.961508: step: 440/530, loss: 0.010833747684955597
2023-01-24 07:25:12.012865: step: 444/530, loss: 0.00038866957766003907
2023-01-24 07:25:13.052486: step: 448/530, loss: 0.0002362951636314392
2023-01-24 07:25:14.113955: step: 452/530, loss: 0.005280998535454273
2023-01-24 07:25:15.174854: step: 456/530, loss: 0.012531696818768978
2023-01-24 07:25:16.221750: step: 460/530, loss: 0.001054047723300755
2023-01-24 07:25:17.259670: step: 464/530, loss: 0.00017180261784233153
2023-01-24 07:25:18.342943: step: 468/530, loss: 0.026325508952140808
2023-01-24 07:25:19.412080: step: 472/530, loss: 0.015517164953052998
2023-01-24 07:25:20.468057: step: 476/530, loss: 0.004619554150849581
2023-01-24 07:25:21.529162: step: 480/530, loss: 0.0022884318605065346
2023-01-24 07:25:22.602574: step: 484/530, loss: 0.009126914665102959
2023-01-24 07:25:23.661751: step: 488/530, loss: 0.007223417051136494
2023-01-24 07:25:24.714675: step: 492/530, loss: 0.0011125747114419937
2023-01-24 07:25:25.777293: step: 496/530, loss: 0.002948937937617302
2023-01-24 07:25:26.828004: step: 500/530, loss: 0.0010918269399553537
2023-01-24 07:25:27.891060: step: 504/530, loss: 0.0006206376128830016
2023-01-24 07:25:28.966608: step: 508/530, loss: 0.004366508685052395
2023-01-24 07:25:30.024425: step: 512/530, loss: 0.0027248221449553967
2023-01-24 07:25:31.080114: step: 516/530, loss: 0.003083973890170455
2023-01-24 07:25:32.153850: step: 520/530, loss: 0.006019479129463434
2023-01-24 07:25:33.224235: step: 524/530, loss: 0.004589051939547062
2023-01-24 07:25:34.279908: step: 528/530, loss: 0.03312420845031738
2023-01-24 07:25:35.332186: step: 532/530, loss: 0.0002147872728528455
2023-01-24 07:25:36.401115: step: 536/530, loss: 0.004653861280530691
2023-01-24 07:25:37.455450: step: 540/530, loss: 0.005667768884450197
2023-01-24 07:25:38.522877: step: 544/530, loss: 0.008122372440993786
2023-01-24 07:25:39.579513: step: 548/530, loss: 0.0036178031004965305
2023-01-24 07:25:40.649259: step: 552/530, loss: 0.0012721389066427946
2023-01-24 07:25:41.714892: step: 556/530, loss: 0.006121991667896509
2023-01-24 07:25:42.770698: step: 560/530, loss: 0.0004973919130861759
2023-01-24 07:25:43.837386: step: 564/530, loss: 0.0072229038923978806
2023-01-24 07:25:44.910096: step: 568/530, loss: 0.003401955356821418
2023-01-24 07:25:45.975065: step: 572/530, loss: 0.0019759531132876873
2023-01-24 07:25:47.039070: step: 576/530, loss: 0.007179000414907932
2023-01-24 07:25:48.083277: step: 580/530, loss: 0.01063327956944704
2023-01-24 07:25:49.150579: step: 584/530, loss: 0.005065048113465309
2023-01-24 07:25:50.206958: step: 588/530, loss: 0.008108510635793209
2023-01-24 07:25:51.265894: step: 592/530, loss: 0.00701938197016716
2023-01-24 07:25:52.340722: step: 596/530, loss: 0.0002842854300979525
2023-01-24 07:25:53.396729: step: 600/530, loss: 0.0016940321074798703
2023-01-24 07:25:54.444474: step: 604/530, loss: 0.025617994368076324
2023-01-24 07:25:55.497465: step: 608/530, loss: 4.666324457502924e-05
2023-01-24 07:25:56.580476: step: 612/530, loss: 0.005088458303362131
2023-01-24 07:25:57.627870: step: 616/530, loss: 0.008997460827231407
2023-01-24 07:25:58.690238: step: 620/530, loss: 0.002423650585114956
2023-01-24 07:25:59.741603: step: 624/530, loss: 0.056079424917697906
2023-01-24 07:26:00.805405: step: 628/530, loss: 0.012369221076369286
2023-01-24 07:26:01.857552: step: 632/530, loss: 0.0015017739497125149
2023-01-24 07:26:02.919683: step: 636/530, loss: 0.007779762148857117
2023-01-24 07:26:03.974376: step: 640/530, loss: 0.00034266404691152275
2023-01-24 07:26:05.041600: step: 644/530, loss: 0.008342042565345764
2023-01-24 07:26:06.101780: step: 648/530, loss: 0.00013007245433982462
2023-01-24 07:26:07.183610: step: 652/530, loss: 0.0007750781951472163
2023-01-24 07:26:08.230012: step: 656/530, loss: 0.0018715604674071074
2023-01-24 07:26:09.291298: step: 660/530, loss: 0.0016354137333109975
2023-01-24 07:26:10.374250: step: 664/530, loss: 0.0012279903749004006
2023-01-24 07:26:11.449134: step: 668/530, loss: 0.009681175462901592
2023-01-24 07:26:12.514879: step: 672/530, loss: 0.003347435500472784
2023-01-24 07:26:13.586366: step: 676/530, loss: 0.011745578609406948
2023-01-24 07:26:14.650239: step: 680/530, loss: 0.00831012986600399
2023-01-24 07:26:15.703796: step: 684/530, loss: 0.001262263860553503
2023-01-24 07:26:16.776751: step: 688/530, loss: 0.0048485505394637585
2023-01-24 07:26:17.829021: step: 692/530, loss: 0.014339500106871128
2023-01-24 07:26:18.881710: step: 696/530, loss: 0.007572287227958441
2023-01-24 07:26:19.950779: step: 700/530, loss: 0.010303635150194168
2023-01-24 07:26:21.008524: step: 704/530, loss: 0.00027843870338983834
2023-01-24 07:26:22.057711: step: 708/530, loss: 0.01371452771127224
2023-01-24 07:26:23.114043: step: 712/530, loss: 0.00042528987978585064
2023-01-24 07:26:24.162626: step: 716/530, loss: 0.0005616341950371861
2023-01-24 07:26:25.225262: step: 720/530, loss: 0.0028855102136731148
2023-01-24 07:26:26.292885: step: 724/530, loss: 0.001164730405434966
2023-01-24 07:26:27.335370: step: 728/530, loss: 0.0011211609235033393
2023-01-24 07:26:28.403856: step: 732/530, loss: 0.015907419845461845
2023-01-24 07:26:29.467930: step: 736/530, loss: 0.08569792658090591
2023-01-24 07:26:30.531644: step: 740/530, loss: 0.023858193308115005
2023-01-24 07:26:31.580077: step: 744/530, loss: 0.0037874882109463215
2023-01-24 07:26:32.650870: step: 748/530, loss: 0.0006449953652918339
2023-01-24 07:26:33.703633: step: 752/530, loss: 9.023010534292553e-06
2023-01-24 07:26:34.735410: step: 756/530, loss: 0.0008476577349938452
2023-01-24 07:26:35.786624: step: 760/530, loss: 0.00924161821603775
2023-01-24 07:26:36.833325: step: 764/530, loss: 0.0001442963257431984
2023-01-24 07:26:37.877130: step: 768/530, loss: 0.015980752184987068
2023-01-24 07:26:38.936138: step: 772/530, loss: 5.119547495269217e-06
2023-01-24 07:26:40.006769: step: 776/530, loss: 0.00010676019883248955
2023-01-24 07:26:41.063624: step: 780/530, loss: 0.0024200999177992344
2023-01-24 07:26:42.123434: step: 784/530, loss: 0.003979182336479425
2023-01-24 07:26:43.178935: step: 788/530, loss: 0.0018113116966560483
2023-01-24 07:26:44.249638: step: 792/530, loss: 0.008732148446142673
2023-01-24 07:26:45.316563: step: 796/530, loss: 0.003172091208398342
2023-01-24 07:26:46.374781: step: 800/530, loss: 0.004854040220379829
2023-01-24 07:26:47.457984: step: 804/530, loss: 0.004063732456415892
2023-01-24 07:26:48.527687: step: 808/530, loss: 0.0013634428614750504
2023-01-24 07:26:49.584264: step: 812/530, loss: 0.005167086608707905
2023-01-24 07:26:50.636423: step: 816/530, loss: 0.012295229360461235
2023-01-24 07:26:51.689782: step: 820/530, loss: 0.006900577340275049
2023-01-24 07:26:52.745691: step: 824/530, loss: 5.419595981948078e-05
2023-01-24 07:26:53.818582: step: 828/530, loss: 0.006632449571043253
2023-01-24 07:26:54.877375: step: 832/530, loss: 0.0017331892158836126
2023-01-24 07:26:55.931035: step: 836/530, loss: 0.0006142915808595717
2023-01-24 07:26:56.979112: step: 840/530, loss: 0.0037633369211107492
2023-01-24 07:26:58.028532: step: 844/530, loss: 0.0010070562129840255
2023-01-24 07:26:59.078411: step: 848/530, loss: 0.002478070789948106
2023-01-24 07:27:00.141710: step: 852/530, loss: 0.003714849939569831
2023-01-24 07:27:01.193241: step: 856/530, loss: 0.0009307508589699864
2023-01-24 07:27:02.248495: step: 860/530, loss: 0.0010487677063792944
2023-01-24 07:27:03.309409: step: 864/530, loss: 0.0012491183588281274
2023-01-24 07:27:04.385529: step: 868/530, loss: 0.007583253085613251
2023-01-24 07:27:05.469007: step: 872/530, loss: 0.005695600062608719
2023-01-24 07:27:06.531554: step: 876/530, loss: 0.003532192436978221
2023-01-24 07:27:07.588231: step: 880/530, loss: 0.028896501287817955
2023-01-24 07:27:08.643463: step: 884/530, loss: 0.0018249228596687317
2023-01-24 07:27:09.707214: step: 888/530, loss: 0.006584419868886471
2023-01-24 07:27:10.750386: step: 892/530, loss: 0.004012554418295622
2023-01-24 07:27:11.836478: step: 896/530, loss: 0.021657193079590797
2023-01-24 07:27:12.905107: step: 900/530, loss: 0.003510869573801756
2023-01-24 07:27:13.952873: step: 904/530, loss: 9.504158515483141e-05
2023-01-24 07:27:15.024494: step: 908/530, loss: 0.015397016890347004
2023-01-24 07:27:16.101740: step: 912/530, loss: 0.050935372710227966
2023-01-24 07:27:17.177298: step: 916/530, loss: 0.005209668073803186
2023-01-24 07:27:18.227732: step: 920/530, loss: 0.0015431750798597932
2023-01-24 07:27:19.294233: step: 924/530, loss: 0.004369240254163742
2023-01-24 07:27:20.351904: step: 928/530, loss: 0.03550203517079353
2023-01-24 07:27:21.417938: step: 932/530, loss: 0.006693502422422171
2023-01-24 07:27:22.488704: step: 936/530, loss: 0.00041917807538993657
2023-01-24 07:27:23.539903: step: 940/530, loss: 0.0028434705454856157
2023-01-24 07:27:24.616018: step: 944/530, loss: 0.002211144659668207
2023-01-24 07:27:25.665506: step: 948/530, loss: 0.006492828484624624
2023-01-24 07:27:26.736864: step: 952/530, loss: 0.02865644358098507
2023-01-24 07:27:27.798096: step: 956/530, loss: 0.007353669963777065
2023-01-24 07:27:28.837050: step: 960/530, loss: 0.004926623776555061
2023-01-24 07:27:29.888823: step: 964/530, loss: 0.0020286948420107365
2023-01-24 07:27:30.964108: step: 968/530, loss: 0.002209634752944112
2023-01-24 07:27:32.028982: step: 972/530, loss: 0.0023933867923915386
2023-01-24 07:27:33.080871: step: 976/530, loss: 0.0006421073921956122
2023-01-24 07:27:34.141905: step: 980/530, loss: 0.0014324311632663012
2023-01-24 07:27:35.190540: step: 984/530, loss: 0.0019344848114997149
2023-01-24 07:27:36.269056: step: 988/530, loss: 0.05040892958641052
2023-01-24 07:27:37.331579: step: 992/530, loss: 0.0019419536693021655
2023-01-24 07:27:38.382177: step: 996/530, loss: 0.001619693823158741
2023-01-24 07:27:39.453945: step: 1000/530, loss: 0.014715269207954407
2023-01-24 07:27:40.521052: step: 1004/530, loss: 0.030769888311624527
2023-01-24 07:27:41.604148: step: 1008/530, loss: 0.0016084014205262065
2023-01-24 07:27:42.667718: step: 1012/530, loss: 0.007312459871172905
2023-01-24 07:27:43.720161: step: 1016/530, loss: 0.005628805607557297
2023-01-24 07:27:44.773187: step: 1020/530, loss: 0.0025717057287693024
2023-01-24 07:27:45.832916: step: 1024/530, loss: 0.00790424831211567
2023-01-24 07:27:46.884778: step: 1028/530, loss: 0.003198872087523341
2023-01-24 07:27:47.931341: step: 1032/530, loss: 0.011551324278116226
2023-01-24 07:27:48.994863: step: 1036/530, loss: 0.0030645655933767557
2023-01-24 07:27:50.074546: step: 1040/530, loss: 0.005343732889741659
2023-01-24 07:27:51.134614: step: 1044/530, loss: 0.00837535411119461
2023-01-24 07:27:52.199446: step: 1048/530, loss: 0.00354607030749321
2023-01-24 07:27:53.257260: step: 1052/530, loss: 0.0015075349947437644
2023-01-24 07:27:54.306428: step: 1056/530, loss: 0.003086197655647993
2023-01-24 07:27:55.354949: step: 1060/530, loss: 0.0021570981480181217
2023-01-24 07:27:56.417012: step: 1064/530, loss: 0.00012293148029129952
2023-01-24 07:27:57.482474: step: 1068/530, loss: 0.0034800937864929438
2023-01-24 07:27:58.532574: step: 1072/530, loss: 0.030885253101587296
2023-01-24 07:27:59.594242: step: 1076/530, loss: 0.006151766516268253
2023-01-24 07:28:00.674805: step: 1080/530, loss: 0.0034379761200398207
2023-01-24 07:28:01.730268: step: 1084/530, loss: 0.001509494730271399
2023-01-24 07:28:02.803519: step: 1088/530, loss: 0.0024860992562025785
2023-01-24 07:28:03.852947: step: 1092/530, loss: 5.1756880566244945e-05
2023-01-24 07:28:04.922791: step: 1096/530, loss: 0.025292042642831802
2023-01-24 07:28:05.997312: step: 1100/530, loss: 0.0009208132396452129
2023-01-24 07:28:07.059944: step: 1104/530, loss: 0.0038977907970547676
2023-01-24 07:28:08.112348: step: 1108/530, loss: 0.005086773540824652
2023-01-24 07:28:09.170912: step: 1112/530, loss: 0.0033402193803340197
2023-01-24 07:28:10.228966: step: 1116/530, loss: 0.0027043165173381567
2023-01-24 07:28:11.304942: step: 1120/530, loss: 0.012632989324629307
2023-01-24 07:28:12.366816: step: 1124/530, loss: 0.006464587990194559
2023-01-24 07:28:13.419067: step: 1128/530, loss: 0.009527401067316532
2023-01-24 07:28:14.474148: step: 1132/530, loss: 0.0022216616198420525
2023-01-24 07:28:15.545617: step: 1136/530, loss: 0.002615844365209341
2023-01-24 07:28:16.601447: step: 1140/530, loss: 0.006682222709059715
2023-01-24 07:28:17.692507: step: 1144/530, loss: 0.0048462203703820705
2023-01-24 07:28:18.741681: step: 1148/530, loss: 0.0007670805207453668
2023-01-24 07:28:19.818898: step: 1152/530, loss: 0.009593291208148003
2023-01-24 07:28:20.872337: step: 1156/530, loss: 0.0004975621704943478
2023-01-24 07:28:21.935463: step: 1160/530, loss: 0.009345789439976215
2023-01-24 07:28:22.990650: step: 1164/530, loss: 0.0008754830923862755
2023-01-24 07:28:24.056600: step: 1168/530, loss: 0.011169680394232273
2023-01-24 07:28:25.112340: step: 1172/530, loss: 0.0026201759465038776
2023-01-24 07:28:26.170901: step: 1176/530, loss: 0.011243724264204502
2023-01-24 07:28:27.220858: step: 1180/530, loss: 0.0019960992503911257
2023-01-24 07:28:28.286570: step: 1184/530, loss: 1.4583305528503843e-05
2023-01-24 07:28:29.347152: step: 1188/530, loss: 0.007272704038769007
2023-01-24 07:28:30.402952: step: 1192/530, loss: 0.002686869353055954
2023-01-24 07:28:31.461781: step: 1196/530, loss: 0.005081926006823778
2023-01-24 07:28:32.541984: step: 1200/530, loss: 0.001307943370193243
2023-01-24 07:28:33.591708: step: 1204/530, loss: 0.0031069398391991854
2023-01-24 07:28:34.639228: step: 1208/530, loss: 0.0005948446341790259
2023-01-24 07:28:35.693979: step: 1212/530, loss: 1.0914909580606036e-06
2023-01-24 07:28:36.753046: step: 1216/530, loss: 0.0038150139153003693
2023-01-24 07:28:37.811184: step: 1220/530, loss: 0.0026223729364573956
2023-01-24 07:28:38.856454: step: 1224/530, loss: 0.004283602349460125
2023-01-24 07:28:39.930177: step: 1228/530, loss: 0.0072454530745744705
2023-01-24 07:28:40.979919: step: 1232/530, loss: 0.009494572877883911
2023-01-24 07:28:42.020781: step: 1236/530, loss: 0.0005140142166055739
2023-01-24 07:28:43.069036: step: 1240/530, loss: 0.0007592645124532282
2023-01-24 07:28:44.125168: step: 1244/530, loss: 0.0071346634067595005
2023-01-24 07:28:45.198932: step: 1248/530, loss: 0.0038870633579790592
2023-01-24 07:28:46.278991: step: 1252/530, loss: 0.0030153635889291763
2023-01-24 07:28:47.326689: step: 1256/530, loss: 0.001416281796991825
2023-01-24 07:28:48.389743: step: 1260/530, loss: 0.0018125182250514627
2023-01-24 07:28:49.464912: step: 1264/530, loss: 0.010289902798831463
2023-01-24 07:28:50.546801: step: 1268/530, loss: 0.0031385901384055614
2023-01-24 07:28:51.604017: step: 1272/530, loss: 0.003156331367790699
2023-01-24 07:28:52.666071: step: 1276/530, loss: 0.005723380483686924
2023-01-24 07:28:53.714196: step: 1280/530, loss: 0.01197907142341137
2023-01-24 07:28:54.760469: step: 1284/530, loss: 0.007802318315953016
2023-01-24 07:28:55.815340: step: 1288/530, loss: 0.01617361046373844
2023-01-24 07:28:56.861951: step: 1292/530, loss: 0.009799396619200706
2023-01-24 07:28:57.913049: step: 1296/530, loss: 0.02666343003511429
2023-01-24 07:28:58.975323: step: 1300/530, loss: 0.0029205642640590668
2023-01-24 07:29:00.045060: step: 1304/530, loss: 0.008449913933873177
2023-01-24 07:29:01.101840: step: 1308/530, loss: 0.012554100714623928
2023-01-24 07:29:02.164471: step: 1312/530, loss: 0.002242621034383774
2023-01-24 07:29:03.229460: step: 1316/530, loss: 0.005994822364300489
2023-01-24 07:29:04.296559: step: 1320/530, loss: 0.003377022221684456
2023-01-24 07:29:05.368922: step: 1324/530, loss: 0.005406593903899193
2023-01-24 07:29:06.432553: step: 1328/530, loss: 0.01103257667273283
2023-01-24 07:29:07.512112: step: 1332/530, loss: 0.002860089996829629
2023-01-24 07:29:08.593053: step: 1336/530, loss: 0.0015651839785277843
2023-01-24 07:29:09.650109: step: 1340/530, loss: 0.005619209725409746
2023-01-24 07:29:10.736785: step: 1344/530, loss: 0.007609691470861435
2023-01-24 07:29:11.787084: step: 1348/530, loss: 0.0023679123260080814
2023-01-24 07:29:12.854915: step: 1352/530, loss: 0.0014374775346368551
2023-01-24 07:29:13.905155: step: 1356/530, loss: 0.004368546884506941
2023-01-24 07:29:14.973149: step: 1360/530, loss: 0.00044674932723864913
2023-01-24 07:29:16.038833: step: 1364/530, loss: 0.007170870900154114
2023-01-24 07:29:17.083602: step: 1368/530, loss: 0.0070548150688409805
2023-01-24 07:29:18.135056: step: 1372/530, loss: 0.0036726747639477253
2023-01-24 07:29:19.176581: step: 1376/530, loss: 0.0034284647554159164
2023-01-24 07:29:20.235504: step: 1380/530, loss: 0.0032980607356876135
2023-01-24 07:29:21.301640: step: 1384/530, loss: 0.008908475749194622
2023-01-24 07:29:22.358980: step: 1388/530, loss: 4.6096618461888283e-05
2023-01-24 07:29:23.404363: step: 1392/530, loss: 0.00038111634785309434
2023-01-24 07:29:24.463816: step: 1396/530, loss: 0.002776114968582988
2023-01-24 07:29:25.562297: step: 1400/530, loss: 0.013103046454489231
2023-01-24 07:29:26.611438: step: 1404/530, loss: 0.012746206484735012
2023-01-24 07:29:27.666782: step: 1408/530, loss: 0.0025733094662427902
2023-01-24 07:29:28.731188: step: 1412/530, loss: 0.007026394363492727
2023-01-24 07:29:29.783901: step: 1416/530, loss: 0.004523235838860273
2023-01-24 07:29:30.847497: step: 1420/530, loss: 0.0043120249174535275
2023-01-24 07:29:31.894826: step: 1424/530, loss: 0.001962050097063184
2023-01-24 07:29:32.938376: step: 1428/530, loss: 0.0013175873318687081
2023-01-24 07:29:33.994427: step: 1432/530, loss: 0.008567588403820992
2023-01-24 07:29:35.056611: step: 1436/530, loss: 0.015097937546670437
2023-01-24 07:29:36.114904: step: 1440/530, loss: 0.005013413727283478
2023-01-24 07:29:37.178025: step: 1444/530, loss: 0.0019324166933074594
2023-01-24 07:29:38.235684: step: 1448/530, loss: 0.0024225011002272367
2023-01-24 07:29:39.285655: step: 1452/530, loss: 0.0022114012390375137
2023-01-24 07:29:40.333423: step: 1456/530, loss: 0.004004094284027815
2023-01-24 07:29:41.417473: step: 1460/530, loss: 0.010377401486039162
2023-01-24 07:29:42.482401: step: 1464/530, loss: 0.005856323521584272
2023-01-24 07:29:43.535148: step: 1468/530, loss: 0.0006262914394028485
2023-01-24 07:29:44.584001: step: 1472/530, loss: 0.004930655471980572
2023-01-24 07:29:45.640189: step: 1476/530, loss: 0.00011783480294980109
2023-01-24 07:29:46.706266: step: 1480/530, loss: 0.0012534589041024446
2023-01-24 07:29:47.760723: step: 1484/530, loss: 0.006297635845839977
2023-01-24 07:29:48.816719: step: 1488/530, loss: 0.001348702935501933
2023-01-24 07:29:49.876327: step: 1492/530, loss: 0.002381858415901661
2023-01-24 07:29:50.923858: step: 1496/530, loss: 0.0017556046368554235
2023-01-24 07:29:51.994299: step: 1500/530, loss: 0.0036560851149260998
2023-01-24 07:29:53.033035: step: 1504/530, loss: 0.00041475845500826836
2023-01-24 07:29:54.078706: step: 1508/530, loss: 0.02395522966980934
2023-01-24 07:29:55.142554: step: 1512/530, loss: 0.0092427097260952
2023-01-24 07:29:56.191114: step: 1516/530, loss: 0.0
2023-01-24 07:29:57.251905: step: 1520/530, loss: 0.0024025836028158665
2023-01-24 07:29:58.293459: step: 1524/530, loss: 0.0044045038521289825
2023-01-24 07:29:59.356963: step: 1528/530, loss: 0.0007563966792076826
2023-01-24 07:30:00.418535: step: 1532/530, loss: 0.0017078659730032086
2023-01-24 07:30:01.489822: step: 1536/530, loss: 0.0018770396709442139
2023-01-24 07:30:02.554439: step: 1540/530, loss: 0.0038097607903182507
2023-01-24 07:30:03.608068: step: 1544/530, loss: 0.0037790362257510424
2023-01-24 07:30:04.663779: step: 1548/530, loss: 0.01185193657875061
2023-01-24 07:30:05.707870: step: 1552/530, loss: 0.0014775642193853855
2023-01-24 07:30:06.783741: step: 1556/530, loss: 0.004230780992656946
2023-01-24 07:30:07.842016: step: 1560/530, loss: 0.005669799167662859
2023-01-24 07:30:08.910782: step: 1564/530, loss: 0.008223684504628181
2023-01-24 07:30:09.962076: step: 1568/530, loss: 0.0006993726710788906
2023-01-24 07:30:11.021582: step: 1572/530, loss: 0.012956804595887661
2023-01-24 07:30:12.056727: step: 1576/530, loss: 0.019530994817614555
2023-01-24 07:30:13.114970: step: 1580/530, loss: 0.015981880947947502
2023-01-24 07:30:14.168929: step: 1584/530, loss: 0.028154440224170685
2023-01-24 07:30:15.211814: step: 1588/530, loss: 0.0001211744238389656
2023-01-24 07:30:16.270723: step: 1592/530, loss: 0.002829579869285226
2023-01-24 07:30:17.333409: step: 1596/530, loss: 0.008065136149525642
2023-01-24 07:30:18.403750: step: 1600/530, loss: 0.004729262553155422
2023-01-24 07:30:19.450734: step: 1604/530, loss: 0.0032550536561757326
2023-01-24 07:30:20.506961: step: 1608/530, loss: 0.00024565367493778467
2023-01-24 07:30:21.557938: step: 1612/530, loss: 0.0001351367827737704
2023-01-24 07:30:22.620980: step: 1616/530, loss: 0.03533303365111351
2023-01-24 07:30:23.709191: step: 1620/530, loss: 0.002575187012553215
2023-01-24 07:30:24.757795: step: 1624/530, loss: 0.005571381654590368
2023-01-24 07:30:25.803332: step: 1628/530, loss: 0.019285814836621284
2023-01-24 07:30:26.857395: step: 1632/530, loss: 0.005768598057329655
2023-01-24 07:30:27.911374: step: 1636/530, loss: 0.009555893950164318
2023-01-24 07:30:28.988975: step: 1640/530, loss: 0.032931383699178696
2023-01-24 07:30:30.058113: step: 1644/530, loss: 0.007134437561035156
2023-01-24 07:30:31.121914: step: 1648/530, loss: 0.003770155366510153
2023-01-24 07:30:32.166006: step: 1652/530, loss: 0.0008252543630078435
2023-01-24 07:30:33.218407: step: 1656/530, loss: 0.008655122481286526
2023-01-24 07:30:34.264005: step: 1660/530, loss: 1.3274970115162432e-05
2023-01-24 07:30:35.329590: step: 1664/530, loss: 0.013387207873165607
2023-01-24 07:30:36.387064: step: 1668/530, loss: 0.00020029177539981902
2023-01-24 07:30:37.453537: step: 1672/530, loss: 0.0022071530111134052
2023-01-24 07:30:38.529519: step: 1676/530, loss: 0.008076482452452183
2023-01-24 07:30:39.595508: step: 1680/530, loss: 0.0030460453126579523
2023-01-24 07:30:40.648658: step: 1684/530, loss: 0.0002496523957233876
2023-01-24 07:30:41.707609: step: 1688/530, loss: 4.8003726988099515e-05
2023-01-24 07:30:42.781680: step: 1692/530, loss: 0.008199339732527733
2023-01-24 07:30:43.830280: step: 1696/530, loss: 0.0032098277006298304
2023-01-24 07:30:44.899113: step: 1700/530, loss: 0.023149412125349045
2023-01-24 07:30:45.950030: step: 1704/530, loss: 0.009380985051393509
2023-01-24 07:30:47.000256: step: 1708/530, loss: 0.0038052101153880358
2023-01-24 07:30:48.055536: step: 1712/530, loss: 0.0014844831312075257
2023-01-24 07:30:49.110961: step: 1716/530, loss: 0.00926840677857399
2023-01-24 07:30:50.170505: step: 1720/530, loss: 0.03820732235908508
2023-01-24 07:30:51.230007: step: 1724/530, loss: 0.00701737217605114
2023-01-24 07:30:52.291461: step: 1728/530, loss: 0.013338825665414333
2023-01-24 07:30:53.349907: step: 1732/530, loss: 0.01182057335972786
2023-01-24 07:30:54.416886: step: 1736/530, loss: 0.003039284609258175
2023-01-24 07:30:55.474290: step: 1740/530, loss: 0.0039274804294109344
2023-01-24 07:30:56.516320: step: 1744/530, loss: 0.007153353653848171
2023-01-24 07:30:57.552891: step: 1748/530, loss: 0.006228177342563868
2023-01-24 07:30:58.616361: step: 1752/530, loss: 0.0013471595011651516
2023-01-24 07:30:59.672434: step: 1756/530, loss: 0.0014786750543862581
2023-01-24 07:31:00.729471: step: 1760/530, loss: 0.007056983653455973
2023-01-24 07:31:01.788760: step: 1764/530, loss: 0.016859661787748337
2023-01-24 07:31:02.855608: step: 1768/530, loss: 0.029031939804553986
2023-01-24 07:31:03.915585: step: 1772/530, loss: 0.0014349292032420635
2023-01-24 07:31:04.996474: step: 1776/530, loss: 0.0005414266488514841
2023-01-24 07:31:06.054173: step: 1780/530, loss: 0.0001226823078468442
2023-01-24 07:31:07.123382: step: 1784/530, loss: 0.008234023116528988
2023-01-24 07:31:08.199230: step: 1788/530, loss: 0.013443831354379654
2023-01-24 07:31:09.253043: step: 1792/530, loss: 0.008219048380851746
2023-01-24 07:31:10.324303: step: 1796/530, loss: 0.002434235531836748
2023-01-24 07:31:11.376131: step: 1800/530, loss: 0.0038213038351386786
2023-01-24 07:31:12.422069: step: 1804/530, loss: 0.0005589558277279139
2023-01-24 07:31:13.477407: step: 1808/530, loss: 0.025622064247727394
2023-01-24 07:31:14.540215: step: 1812/530, loss: 0.0028967352118343115
2023-01-24 07:31:15.622463: step: 1816/530, loss: 0.004630516283214092
2023-01-24 07:31:16.701368: step: 1820/530, loss: 0.0023333700373768806
2023-01-24 07:31:17.746609: step: 1824/530, loss: 0.0002672844857443124
2023-01-24 07:31:18.809010: step: 1828/530, loss: 0.011140204966068268
2023-01-24 07:31:19.868227: step: 1832/530, loss: 0.010136320255696774
2023-01-24 07:31:20.935186: step: 1836/530, loss: 0.004595352802425623
2023-01-24 07:31:21.996227: step: 1840/530, loss: 0.0032366826198995113
2023-01-24 07:31:23.049309: step: 1844/530, loss: 0.0003080504829995334
2023-01-24 07:31:24.114562: step: 1848/530, loss: 0.0024106702767312527
2023-01-24 07:31:25.164300: step: 1852/530, loss: 0.0012788112508133054
2023-01-24 07:31:26.239438: step: 1856/530, loss: 0.0005130224162712693
2023-01-24 07:31:27.306106: step: 1860/530, loss: 0.005843916442245245
2023-01-24 07:31:28.348764: step: 1864/530, loss: 0.0002107807667925954
2023-01-24 07:31:29.409251: step: 1868/530, loss: 0.003569738008081913
2023-01-24 07:31:30.459220: step: 1872/530, loss: 0.007909591309726238
2023-01-24 07:31:31.513776: step: 1876/530, loss: 2.0655966181948315e-06
2023-01-24 07:31:32.586241: step: 1880/530, loss: 0.005712231155484915
2023-01-24 07:31:33.636597: step: 1884/530, loss: 0.00027401791885495186
2023-01-24 07:31:34.696491: step: 1888/530, loss: 0.008661773055791855
2023-01-24 07:31:35.759175: step: 1892/530, loss: 0.0005759687046520412
2023-01-24 07:31:36.817313: step: 1896/530, loss: 0.0021990234963595867
2023-01-24 07:31:37.882664: step: 1900/530, loss: 0.003655859036371112
2023-01-24 07:31:38.948406: step: 1904/530, loss: 0.006165719125419855
2023-01-24 07:31:40.003573: step: 1908/530, loss: 0.005128706339746714
2023-01-24 07:31:41.049141: step: 1912/530, loss: 0.00694511691108346
2023-01-24 07:31:42.112689: step: 1916/530, loss: 0.005738366395235062
2023-01-24 07:31:43.178203: step: 1920/530, loss: 0.002607991686090827
2023-01-24 07:31:44.254122: step: 1924/530, loss: 0.0027916536200791597
2023-01-24 07:31:45.318596: step: 1928/530, loss: 0.0044531007297337055
2023-01-24 07:31:46.381716: step: 1932/530, loss: 0.0023015339393168688
2023-01-24 07:31:47.448447: step: 1936/530, loss: 0.009302242659032345
2023-01-24 07:31:48.511750: step: 1940/530, loss: 0.0015341931721195579
2023-01-24 07:31:49.577269: step: 1944/530, loss: 0.01171820517629385
2023-01-24 07:31:50.630899: step: 1948/530, loss: 0.008585739880800247
2023-01-24 07:31:51.692343: step: 1952/530, loss: 0.0031274575740098953
2023-01-24 07:31:52.746073: step: 1956/530, loss: 0.0018474524840712547
2023-01-24 07:31:53.798917: step: 1960/530, loss: 0.003800723236054182
2023-01-24 07:31:54.843822: step: 1964/530, loss: 0.0033009557519108057
2023-01-24 07:31:55.906602: step: 1968/530, loss: 0.0005532049108296633
2023-01-24 07:31:56.964408: step: 1972/530, loss: 2.481062983861193e-05
2023-01-24 07:31:58.023691: step: 1976/530, loss: 0.0029250739607959986
2023-01-24 07:31:59.082165: step: 1980/530, loss: 0.014450984075665474
2023-01-24 07:32:00.133145: step: 1984/530, loss: 0.002528311451897025
2023-01-24 07:32:01.182278: step: 1988/530, loss: 0.0035096043720841408
2023-01-24 07:32:02.251997: step: 1992/530, loss: 0.0005530567723326385
2023-01-24 07:32:03.300684: step: 1996/530, loss: 0.002930987160652876
2023-01-24 07:32:04.344938: step: 2000/530, loss: 0.0007623318233527243
2023-01-24 07:32:05.410137: step: 2004/530, loss: 0.013793833553791046
2023-01-24 07:32:06.462109: step: 2008/530, loss: 0.006455506198108196
2023-01-24 07:32:07.524464: step: 2012/530, loss: 0.00045024670544080436
2023-01-24 07:32:08.582965: step: 2016/530, loss: 0.0024875919334590435
2023-01-24 07:32:09.641597: step: 2020/530, loss: 0.003820327576249838
2023-01-24 07:32:10.711061: step: 2024/530, loss: 0.0027273381128907204
2023-01-24 07:32:11.771299: step: 2028/530, loss: 0.012514801695942879
2023-01-24 07:32:12.819548: step: 2032/530, loss: 0.0038836959283798933
2023-01-24 07:32:13.875638: step: 2036/530, loss: 0.0006056068232282996
2023-01-24 07:32:14.942576: step: 2040/530, loss: 0.006492273882031441
2023-01-24 07:32:16.001637: step: 2044/530, loss: 0.006946875248104334
2023-01-24 07:32:17.051884: step: 2048/530, loss: 0.006958520971238613
2023-01-24 07:32:18.097341: step: 2052/530, loss: 0.0009556170552968979
2023-01-24 07:32:19.159010: step: 2056/530, loss: 0.004036551341414452
2023-01-24 07:32:20.216118: step: 2060/530, loss: 0.01723671704530716
2023-01-24 07:32:21.263634: step: 2064/530, loss: 0.0015155597357079387
2023-01-24 07:32:22.340679: step: 2068/530, loss: 0.009895886294543743
2023-01-24 07:32:23.393936: step: 2072/530, loss: 0.004562380723655224
2023-01-24 07:32:24.436611: step: 2076/530, loss: 0.008926686830818653
2023-01-24 07:32:25.489997: step: 2080/530, loss: 0.003324170596897602
2023-01-24 07:32:26.542860: step: 2084/530, loss: 0.0008891146862879395
2023-01-24 07:32:27.612075: step: 2088/530, loss: 0.001414359314367175
2023-01-24 07:32:28.666813: step: 2092/530, loss: 0.00538351247087121
2023-01-24 07:32:29.744882: step: 2096/530, loss: 0.0008270586840808392
2023-01-24 07:32:30.810496: step: 2100/530, loss: 0.0028769485652446747
2023-01-24 07:32:31.900684: step: 2104/530, loss: 0.002638063160702586
2023-01-24 07:32:32.959026: step: 2108/530, loss: 0.0010600145906209946
2023-01-24 07:32:34.025012: step: 2112/530, loss: 0.007189236581325531
2023-01-24 07:32:35.094242: step: 2116/530, loss: 0.013191532343626022
2023-01-24 07:32:36.154891: step: 2120/530, loss: 0.008546882309019566
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38445120949188194, 'r': 0.33630361968834455, 'f1': 0.3587692461047724}, 'combined': 0.2643562866035165, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993190387327881, 'r': 0.29871138481829346, 'f1': 0.3417648830759078}, 'combined': 0.22666272038194918, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3485035211267606, 'r': 0.2811789772727273, 'f1': 0.3112421383647799}, 'combined': 0.20749475890985325, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4020963121945602, 'r': 0.29705038980463183, 'f1': 0.3416818414071188}, 'combined': 0.22299235965517225, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37592189688801353, 'r': 0.33312243993681656, 'f1': 0.35323043429919987}, 'combined': 0.260275056852042, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3994234712531619, 'r': 0.3088183201983321, 'f1': 0.3483253513955797}, 'combined': 0.23101370455250878, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 07:34:58.918232: step: 4/530, loss: 0.015927644446492195
2023-01-24 07:34:59.954973: step: 8/530, loss: 0.0008314985316246748
2023-01-24 07:35:00.998259: step: 12/530, loss: 0.0005987015319988132
2023-01-24 07:35:02.087083: step: 16/530, loss: 0.010028494521975517
2023-01-24 07:35:03.127735: step: 20/530, loss: 0.006948505993932486
2023-01-24 07:35:04.177659: step: 24/530, loss: 0.00400298647582531
2023-01-24 07:35:05.228735: step: 28/530, loss: 0.006426467094570398
2023-01-24 07:35:06.288870: step: 32/530, loss: 0.005779062397778034
2023-01-24 07:35:07.336913: step: 36/530, loss: 0.007021808531135321
2023-01-24 07:35:08.414128: step: 40/530, loss: 0.0023366441018879414
2023-01-24 07:35:09.484551: step: 44/530, loss: 0.12267465144395828
2023-01-24 07:35:10.565571: step: 48/530, loss: 0.0029192203655838966
2023-01-24 07:35:11.621580: step: 52/530, loss: 0.004540501162409782
2023-01-24 07:35:12.683143: step: 56/530, loss: 0.004050453193485737
2023-01-24 07:35:13.734613: step: 60/530, loss: 0.008094841614365578
2023-01-24 07:35:14.791875: step: 64/530, loss: 0.005523865111172199
2023-01-24 07:35:15.846437: step: 68/530, loss: 0.002569005358964205
2023-01-24 07:35:16.905916: step: 72/530, loss: 0.0015843015862628818
2023-01-24 07:35:17.965040: step: 76/530, loss: 0.0051142075099051
2023-01-24 07:35:19.018224: step: 80/530, loss: 0.004364377819001675
2023-01-24 07:35:20.066472: step: 84/530, loss: 0.006407077889889479
2023-01-24 07:35:21.094494: step: 88/530, loss: 0.004744573030620813
2023-01-24 07:35:22.149438: step: 92/530, loss: 0.006140295881778002
2023-01-24 07:35:23.220790: step: 96/530, loss: 0.005057979840785265
2023-01-24 07:35:24.272563: step: 100/530, loss: 0.0040791695937514305
2023-01-24 07:35:25.341919: step: 104/530, loss: 0.004173126071691513
2023-01-24 07:35:26.403862: step: 108/530, loss: 0.0037336116656661034
2023-01-24 07:35:27.467356: step: 112/530, loss: 0.006566036958247423
2023-01-24 07:35:28.516070: step: 116/530, loss: 0.0008445894345641136
2023-01-24 07:35:29.572360: step: 120/530, loss: 0.006509669125080109
2023-01-24 07:35:30.626546: step: 124/530, loss: 0.00409277668222785
2023-01-24 07:35:31.688531: step: 128/530, loss: 0.010612607933580875
2023-01-24 07:35:32.749615: step: 132/530, loss: 0.005248177796602249
2023-01-24 07:35:33.806727: step: 136/530, loss: 0.006438387557864189
2023-01-24 07:35:34.874334: step: 140/530, loss: 0.004107519518584013
2023-01-24 07:35:35.934390: step: 144/530, loss: 0.0032958744559437037
2023-01-24 07:35:36.982465: step: 148/530, loss: 0.0006733645568601787
2023-01-24 07:35:38.031347: step: 152/530, loss: 0.00517798587679863
2023-01-24 07:35:39.094099: step: 156/530, loss: 0.0001367157674394548
2023-01-24 07:35:40.134364: step: 160/530, loss: 0.00021519158326555043
2023-01-24 07:35:41.192580: step: 164/530, loss: 0.00035449492861516774
2023-01-24 07:35:42.261382: step: 168/530, loss: 0.016030261293053627
2023-01-24 07:35:43.323608: step: 172/530, loss: 0.0023506467696279287
2023-01-24 07:35:44.388577: step: 176/530, loss: 0.004691210109740496
2023-01-24 07:35:45.433621: step: 180/530, loss: 0.02522299252450466
2023-01-24 07:35:46.480492: step: 184/530, loss: 0.0034060394391417503
2023-01-24 07:35:47.548191: step: 188/530, loss: 0.002211774466559291
2023-01-24 07:35:48.613079: step: 192/530, loss: 0.0043431916274130344
2023-01-24 07:35:49.676519: step: 196/530, loss: 0.01457833219319582
2023-01-24 07:35:50.728607: step: 200/530, loss: 0.002763106720522046
2023-01-24 07:35:51.801022: step: 204/530, loss: 0.004409968387335539
2023-01-24 07:35:52.862705: step: 208/530, loss: 0.0028461955953389406
2023-01-24 07:35:53.938046: step: 212/530, loss: 0.0014478196389973164
2023-01-24 07:35:54.981538: step: 216/530, loss: 0.00030926355975680053
2023-01-24 07:35:56.016561: step: 220/530, loss: 0.002106926403939724
2023-01-24 07:35:57.074197: step: 224/530, loss: 0.0014854887267574668
2023-01-24 07:35:58.140297: step: 228/530, loss: 0.0343819335103035
2023-01-24 07:35:59.192583: step: 232/530, loss: 0.0038134222850203514
2023-01-24 07:36:00.272403: step: 236/530, loss: 0.004319116938859224
2023-01-24 07:36:01.340588: step: 240/530, loss: 0.0007618785602971911
2023-01-24 07:36:02.400104: step: 244/530, loss: 0.005231081508100033
2023-01-24 07:36:03.440021: step: 248/530, loss: 0.00034870783565565944
2023-01-24 07:36:04.490310: step: 252/530, loss: 0.006212800275534391
2023-01-24 07:36:05.532140: step: 256/530, loss: 0.0002306024543941021
2023-01-24 07:36:06.589989: step: 260/530, loss: 0.0005440199165605009
2023-01-24 07:36:07.648178: step: 264/530, loss: 0.00894810352474451
2023-01-24 07:36:08.706644: step: 268/530, loss: 0.033572353422641754
2023-01-24 07:36:09.763637: step: 272/530, loss: 0.01326671801507473
2023-01-24 07:36:10.818095: step: 276/530, loss: 0.0032431071158498526
2023-01-24 07:36:11.873206: step: 280/530, loss: 0.00031948211835697293
2023-01-24 07:36:12.927450: step: 284/530, loss: 0.0036425578873604536
2023-01-24 07:36:13.996698: step: 288/530, loss: 0.007322228513658047
2023-01-24 07:36:15.046409: step: 292/530, loss: 0.005125284194946289
2023-01-24 07:36:16.108900: step: 296/530, loss: 0.009313278831541538
2023-01-24 07:36:17.168714: step: 300/530, loss: 0.004412886220961809
2023-01-24 07:36:18.224329: step: 304/530, loss: 0.0070163654163479805
2023-01-24 07:36:19.273707: step: 308/530, loss: 8.047714800341055e-05
2023-01-24 07:36:20.315023: step: 312/530, loss: 0.0023837205953896046
2023-01-24 07:36:21.385192: step: 316/530, loss: 0.0054130093194544315
2023-01-24 07:36:22.433380: step: 320/530, loss: 0.0029596390668302774
2023-01-24 07:36:23.496632: step: 324/530, loss: 0.0002044261054834351
2023-01-24 07:36:24.553160: step: 328/530, loss: 0.24544937908649445
2023-01-24 07:36:25.610049: step: 332/530, loss: 0.001435103709809482
2023-01-24 07:36:26.671448: step: 336/530, loss: 0.001408419688232243
2023-01-24 07:36:27.725099: step: 340/530, loss: 0.0001884626253740862
2023-01-24 07:36:28.793642: step: 344/530, loss: 0.008062949404120445
2023-01-24 07:36:29.855037: step: 348/530, loss: 0.004432308487594128
2023-01-24 07:36:30.900295: step: 352/530, loss: 0.00018615700537338853
2023-01-24 07:36:31.954362: step: 356/530, loss: 0.03113900125026703
2023-01-24 07:36:33.025622: step: 360/530, loss: 0.0012075015110895038
2023-01-24 07:36:34.077752: step: 364/530, loss: 0.007036595139652491
2023-01-24 07:36:35.126894: step: 368/530, loss: 0.0027034436352550983
2023-01-24 07:36:36.181940: step: 372/530, loss: 0.0030246013775467873
2023-01-24 07:36:37.241200: step: 376/530, loss: 0.018699076026678085
2023-01-24 07:36:38.290019: step: 380/530, loss: 0.0009343913989141583
2023-01-24 07:36:39.359385: step: 384/530, loss: 0.003655866254121065
2023-01-24 07:36:40.426965: step: 388/530, loss: 0.004558792803436518
2023-01-24 07:36:41.472301: step: 392/530, loss: 7.05994461895898e-05
2023-01-24 07:36:42.524765: step: 396/530, loss: 0.004327529575675726
2023-01-24 07:36:43.575849: step: 400/530, loss: 0.005280277691781521
2023-01-24 07:36:44.633935: step: 404/530, loss: 0.00345603353343904
2023-01-24 07:36:45.702883: step: 408/530, loss: 0.027603723108768463
2023-01-24 07:36:46.754304: step: 412/530, loss: 0.009201932698488235
2023-01-24 07:36:47.829048: step: 416/530, loss: 0.024548783898353577
2023-01-24 07:36:48.904108: step: 420/530, loss: 0.004014628008008003
2023-01-24 07:36:49.972855: step: 424/530, loss: 0.005797058343887329
2023-01-24 07:36:51.025569: step: 428/530, loss: 0.0009839124977588654
2023-01-24 07:36:52.064350: step: 432/530, loss: 0.0021490410435944796
2023-01-24 07:36:53.143342: step: 436/530, loss: 0.006196657661348581
2023-01-24 07:36:54.187061: step: 440/530, loss: 0.007675060071051121
2023-01-24 07:36:55.245309: step: 444/530, loss: 0.014316799119114876
2023-01-24 07:36:56.300330: step: 448/530, loss: 0.009575974196195602
2023-01-24 07:36:57.362054: step: 452/530, loss: 0.013419738039374352
2023-01-24 07:36:58.423802: step: 456/530, loss: 0.003999773878604174
2023-01-24 07:36:59.489268: step: 460/530, loss: 0.004203292075544596
2023-01-24 07:37:00.530171: step: 464/530, loss: 0.0028406099881976843
2023-01-24 07:37:01.589952: step: 468/530, loss: 0.0010555546032264829
2023-01-24 07:37:02.636084: step: 472/530, loss: 0.0012232547160238028
2023-01-24 07:37:03.687801: step: 476/530, loss: 0.01999991200864315
2023-01-24 07:37:04.756422: step: 480/530, loss: 0.007830601185560226
2023-01-24 07:37:05.816806: step: 484/530, loss: 0.0031262922566384077
2023-01-24 07:37:06.875932: step: 488/530, loss: 0.006909772753715515
2023-01-24 07:37:07.955563: step: 492/530, loss: 0.008000316098332405
2023-01-24 07:37:09.013305: step: 496/530, loss: 0.005164084490388632
2023-01-24 07:37:10.085426: step: 500/530, loss: 0.00842166319489479
2023-01-24 07:37:11.144181: step: 504/530, loss: 0.00445551285520196
2023-01-24 07:37:12.223375: step: 508/530, loss: 0.03764331340789795
2023-01-24 07:37:13.283930: step: 512/530, loss: 0.0024514200631529093
2023-01-24 07:37:14.330460: step: 516/530, loss: 0.0033493717201054096
2023-01-24 07:37:15.377934: step: 520/530, loss: 0.0019446861697360873
2023-01-24 07:37:16.430987: step: 524/530, loss: 0.0011561862193048
2023-01-24 07:37:17.475074: step: 528/530, loss: 1.3254373698146082e-05
2023-01-24 07:37:18.531666: step: 532/530, loss: 0.0013337228447198868
2023-01-24 07:37:19.606948: step: 536/530, loss: 0.004951189737766981
2023-01-24 07:37:20.661738: step: 540/530, loss: 0.008516372181475163
2023-01-24 07:37:21.699929: step: 544/530, loss: 0.006416157819330692
2023-01-24 07:37:22.776901: step: 548/530, loss: 0.001722979242913425
2023-01-24 07:37:23.826214: step: 552/530, loss: 0.003638720139861107
2023-01-24 07:37:24.884150: step: 556/530, loss: 0.018069975078105927
2023-01-24 07:37:25.952043: step: 560/530, loss: 0.0002427633007755503
2023-01-24 07:37:26.999595: step: 564/530, loss: 0.009420906193554401
2023-01-24 07:37:28.050301: step: 568/530, loss: 0.0045921290293335915
2023-01-24 07:37:29.118494: step: 572/530, loss: 0.0005713204154744744
2023-01-24 07:37:30.167461: step: 576/530, loss: 0.006289421580731869
2023-01-24 07:37:31.230083: step: 580/530, loss: 0.004684799816459417
2023-01-24 07:37:32.309753: step: 584/530, loss: 0.0006750068860128522
2023-01-24 07:37:33.361247: step: 588/530, loss: 4.2831211430893745e-06
2023-01-24 07:37:34.429748: step: 592/530, loss: 0.019326431676745415
2023-01-24 07:37:35.484578: step: 596/530, loss: 0.004922597203403711
2023-01-24 07:37:36.539896: step: 600/530, loss: 0.0009555994183756411
2023-01-24 07:37:37.609032: step: 604/530, loss: 0.0
2023-01-24 07:37:38.671084: step: 608/530, loss: 0.0018904495518654585
2023-01-24 07:37:39.736612: step: 612/530, loss: 0.0006573530263267457
2023-01-24 07:37:40.807146: step: 616/530, loss: 0.007349018007516861
2023-01-24 07:37:41.874932: step: 620/530, loss: 0.00732880225405097
2023-01-24 07:37:42.929755: step: 624/530, loss: 0.007181914057582617
2023-01-24 07:37:43.981864: step: 628/530, loss: 0.005422661546617746
2023-01-24 07:37:45.051287: step: 632/530, loss: 0.00471876934170723
2023-01-24 07:37:46.110949: step: 636/530, loss: 0.0037823922466486692
2023-01-24 07:37:47.194893: step: 640/530, loss: 0.023475103080272675
2023-01-24 07:37:48.266674: step: 644/530, loss: 0.001388481934554875
2023-01-24 07:37:49.327526: step: 648/530, loss: 0.0012594583677127957
2023-01-24 07:37:50.384917: step: 652/530, loss: 0.004343141335994005
2023-01-24 07:37:51.448180: step: 656/530, loss: 0.006917532999068499
2023-01-24 07:37:52.508976: step: 660/530, loss: 0.0031417841091752052
2023-01-24 07:37:53.563710: step: 664/530, loss: 0.005103804636746645
2023-01-24 07:37:54.626218: step: 668/530, loss: 0.0013484611408784986
2023-01-24 07:37:55.687926: step: 672/530, loss: 0.00772235868498683
2023-01-24 07:37:56.726289: step: 676/530, loss: 0.0031657651998102665
2023-01-24 07:37:57.792422: step: 680/530, loss: 0.03739647567272186
2023-01-24 07:37:58.867279: step: 684/530, loss: 0.0238046832382679
2023-01-24 07:37:59.928547: step: 688/530, loss: 0.004072646144777536
2023-01-24 07:38:00.983835: step: 692/530, loss: 0.0007109611760824919
2023-01-24 07:38:02.046955: step: 696/530, loss: 0.006285248789936304
2023-01-24 07:38:03.116507: step: 700/530, loss: 0.010502849705517292
2023-01-24 07:38:04.185749: step: 704/530, loss: 0.004541243426501751
2023-01-24 07:38:05.238033: step: 708/530, loss: 0.019364066421985626
2023-01-24 07:38:06.294098: step: 712/530, loss: 0.003215125761926174
2023-01-24 07:38:07.381705: step: 716/530, loss: 0.004471972119063139
2023-01-24 07:38:08.436508: step: 720/530, loss: 0.00035115217906422913
2023-01-24 07:38:09.487320: step: 724/530, loss: 0.0019015392754226923
2023-01-24 07:38:10.546388: step: 728/530, loss: 0.010658822022378445
2023-01-24 07:38:11.610558: step: 732/530, loss: 0.0025435646530240774
2023-01-24 07:38:12.672788: step: 736/530, loss: 0.0009237733902409673
2023-01-24 07:38:13.739578: step: 740/530, loss: 0.002559992950409651
2023-01-24 07:38:14.798664: step: 744/530, loss: 0.027732260525226593
2023-01-24 07:38:15.872333: step: 748/530, loss: 0.011358147487044334
2023-01-24 07:38:16.955816: step: 752/530, loss: 0.0031314108055084944
2023-01-24 07:38:18.011826: step: 756/530, loss: 0.0029461474623531103
2023-01-24 07:38:19.073974: step: 760/530, loss: 0.0009313707705587149
2023-01-24 07:38:20.130121: step: 764/530, loss: 0.012383795343339443
2023-01-24 07:38:21.188510: step: 768/530, loss: 0.00035698837018571794
2023-01-24 07:38:22.251234: step: 772/530, loss: 0.0014801776269450784
2023-01-24 07:38:23.321801: step: 776/530, loss: 0.04260542243719101
2023-01-24 07:38:24.411258: step: 780/530, loss: 0.008443552069365978
2023-01-24 07:38:25.466762: step: 784/530, loss: 0.009735611267387867
2023-01-24 07:38:26.546632: step: 788/530, loss: 0.0008686337387189269
2023-01-24 07:38:27.598020: step: 792/530, loss: 0.002671161200851202
2023-01-24 07:38:28.679129: step: 796/530, loss: 0.002173204207792878
2023-01-24 07:38:29.750064: step: 800/530, loss: 0.01370356697589159
2023-01-24 07:38:30.812288: step: 804/530, loss: 0.0017238699365407228
2023-01-24 07:38:31.874559: step: 808/530, loss: 0.02576804719865322
2023-01-24 07:38:32.932169: step: 812/530, loss: 0.006545905955135822
2023-01-24 07:38:33.981884: step: 816/530, loss: 0.003871291410177946
2023-01-24 07:38:35.042605: step: 820/530, loss: 0.018059369176626205
2023-01-24 07:38:36.103087: step: 824/530, loss: 0.0037166739348322153
2023-01-24 07:38:37.171418: step: 828/530, loss: 0.0030634873546659946
2023-01-24 07:38:38.249480: step: 832/530, loss: 0.0036304688546806574
2023-01-24 07:38:39.306624: step: 836/530, loss: 0.0020787473767995834
2023-01-24 07:38:40.373483: step: 840/530, loss: 0.0031391947995871305
2023-01-24 07:38:41.429399: step: 844/530, loss: 0.007681672461330891
2023-01-24 07:38:42.499962: step: 848/530, loss: 0.002553332829847932
2023-01-24 07:38:43.547624: step: 852/530, loss: 0.004553305450826883
2023-01-24 07:38:44.638936: step: 856/530, loss: 0.0016303982120007277
2023-01-24 07:38:45.691999: step: 860/530, loss: 5.975810836389428e-06
2023-01-24 07:38:46.744058: step: 864/530, loss: 0.0005275781149975955
2023-01-24 07:38:47.793968: step: 868/530, loss: 0.04236587509512901
2023-01-24 07:38:48.848740: step: 872/530, loss: 0.00021000744891352952
2023-01-24 07:38:49.910568: step: 876/530, loss: 0.004119101911783218
2023-01-24 07:38:50.960297: step: 880/530, loss: 0.0002598412102088332
2023-01-24 07:38:52.019648: step: 884/530, loss: 0.00025763074518181384
2023-01-24 07:38:53.074581: step: 888/530, loss: 0.002313523320481181
2023-01-24 07:38:54.114714: step: 892/530, loss: 0.00018398166866973042
2023-01-24 07:38:55.175931: step: 896/530, loss: 0.005753064062446356
2023-01-24 07:38:56.235900: step: 900/530, loss: 0.0010670917108654976
2023-01-24 07:38:57.286846: step: 904/530, loss: 0.0011302694911137223
2023-01-24 07:38:58.370265: step: 908/530, loss: 0.013157066889107227
2023-01-24 07:38:59.429189: step: 912/530, loss: 0.0026933434419333935
2023-01-24 07:39:00.492520: step: 916/530, loss: 0.0068700178526341915
2023-01-24 07:39:01.558580: step: 920/530, loss: 0.00660925917327404
2023-01-24 07:39:02.645501: step: 924/530, loss: 0.02645551785826683
2023-01-24 07:39:03.726558: step: 928/530, loss: 0.028280384838581085
2023-01-24 07:39:04.780196: step: 932/530, loss: 0.00302509730681777
2023-01-24 07:39:05.831305: step: 936/530, loss: 0.026667091995477676
2023-01-24 07:39:06.882657: step: 940/530, loss: 0.003322065807878971
2023-01-24 07:39:07.942743: step: 944/530, loss: 0.0018791877664625645
2023-01-24 07:39:09.013018: step: 948/530, loss: 0.00295850308611989
2023-01-24 07:39:10.091873: step: 952/530, loss: 0.011943128891289234
2023-01-24 07:39:11.158947: step: 956/530, loss: 0.009050185792148113
2023-01-24 07:39:12.233483: step: 960/530, loss: 0.012569201178848743
2023-01-24 07:39:13.297955: step: 964/530, loss: 0.004016493912786245
2023-01-24 07:39:14.367641: step: 968/530, loss: 0.002299533924087882
2023-01-24 07:39:15.425627: step: 972/530, loss: 0.0026719390880316496
2023-01-24 07:39:16.476934: step: 976/530, loss: 0.011718140915036201
2023-01-24 07:39:17.534164: step: 980/530, loss: 0.0014752658316865563
2023-01-24 07:39:18.600197: step: 984/530, loss: 0.004211958963423967
2023-01-24 07:39:19.653043: step: 988/530, loss: 0.0
2023-01-24 07:39:20.700764: step: 992/530, loss: 0.0001493980671511963
2023-01-24 07:39:21.765895: step: 996/530, loss: 0.0008119151461869478
2023-01-24 07:39:22.833300: step: 1000/530, loss: 0.003098259447142482
2023-01-24 07:39:23.888454: step: 1004/530, loss: 0.002368541434407234
2023-01-24 07:39:24.950656: step: 1008/530, loss: 0.007792165037244558
2023-01-24 07:39:26.008152: step: 1012/530, loss: 0.0014715869911015034
2023-01-24 07:39:27.080305: step: 1016/530, loss: 0.0015814263606444001
2023-01-24 07:39:28.137826: step: 1020/530, loss: 0.0010000880574807525
2023-01-24 07:39:29.193775: step: 1024/530, loss: 0.0005833122995682061
2023-01-24 07:39:30.267657: step: 1028/530, loss: 0.0034772504586726427
2023-01-24 07:39:31.333684: step: 1032/530, loss: 0.01191109512001276
2023-01-24 07:39:32.398611: step: 1036/530, loss: 0.002839866327121854
2023-01-24 07:39:33.469066: step: 1040/530, loss: 0.0007197019876912236
2023-01-24 07:39:34.547684: step: 1044/530, loss: 0.001009781495667994
2023-01-24 07:39:35.619540: step: 1048/530, loss: 0.002634261269122362
2023-01-24 07:39:36.702482: step: 1052/530, loss: 0.0025090479757636786
2023-01-24 07:39:37.751423: step: 1056/530, loss: 0.0006466375198215246
2023-01-24 07:39:38.808962: step: 1060/530, loss: 0.009640929289162159
2023-01-24 07:39:39.868584: step: 1064/530, loss: 0.0007870576228015125
2023-01-24 07:39:40.949470: step: 1068/530, loss: 0.0062566520646214485
2023-01-24 07:39:42.014083: step: 1072/530, loss: 0.0021695138420909643
2023-01-24 07:39:43.059289: step: 1076/530, loss: 0.004995639435946941
2023-01-24 07:39:44.130435: step: 1080/530, loss: 0.024274542927742004
2023-01-24 07:39:45.193176: step: 1084/530, loss: 0.006547966506332159
2023-01-24 07:39:46.274841: step: 1088/530, loss: 0.005423553287982941
2023-01-24 07:39:47.338428: step: 1092/530, loss: 0.0009255635086447
2023-01-24 07:39:48.412467: step: 1096/530, loss: 0.001235869713127613
2023-01-24 07:39:49.454580: step: 1100/530, loss: 0.0034246433060616255
2023-01-24 07:39:50.509051: step: 1104/530, loss: 0.010006594471633434
2023-01-24 07:39:51.552218: step: 1108/530, loss: 0.001413852209225297
2023-01-24 07:39:52.602475: step: 1112/530, loss: 0.005569763481616974
2023-01-24 07:39:53.645646: step: 1116/530, loss: 0.0006357765523716807
2023-01-24 07:39:54.698464: step: 1120/530, loss: 0.00542420381680131
2023-01-24 07:39:55.756101: step: 1124/530, loss: 0.0020649973303079605
2023-01-24 07:39:56.834960: step: 1128/530, loss: 0.0008013544720597565
2023-01-24 07:39:57.885404: step: 1132/530, loss: 3.835871393675916e-05
2023-01-24 07:39:58.938942: step: 1136/530, loss: 0.0020174754317849874
2023-01-24 07:39:59.987414: step: 1140/530, loss: 0.0005846507847309113
2023-01-24 07:40:01.065185: step: 1144/530, loss: 0.006800536997616291
2023-01-24 07:40:02.146213: step: 1148/530, loss: 0.0003378924448043108
2023-01-24 07:40:03.199944: step: 1152/530, loss: 0.001740907202474773
2023-01-24 07:40:04.259121: step: 1156/530, loss: 0.005147941410541534
2023-01-24 07:40:05.328598: step: 1160/530, loss: 0.006817403249442577
2023-01-24 07:40:06.393713: step: 1164/530, loss: 0.02316501922905445
2023-01-24 07:40:07.464699: step: 1168/530, loss: 0.002055207034572959
2023-01-24 07:40:08.533008: step: 1172/530, loss: 0.0021133250556886196
2023-01-24 07:40:09.585253: step: 1176/530, loss: 0.009937414899468422
2023-01-24 07:40:10.640930: step: 1180/530, loss: 7.805306267982814e-06
2023-01-24 07:40:11.709099: step: 1184/530, loss: 0.063641257584095
2023-01-24 07:40:12.776253: step: 1188/530, loss: 0.00038742704782634974
2023-01-24 07:40:13.826925: step: 1192/530, loss: 0.0032423243392258883
2023-01-24 07:40:14.888726: step: 1196/530, loss: 0.004681752994656563
2023-01-24 07:40:15.938305: step: 1200/530, loss: 0.0027724565006792545
2023-01-24 07:40:17.006690: step: 1204/530, loss: 0.014422204345464706
2023-01-24 07:40:18.064870: step: 1208/530, loss: 0.0007912633591331542
2023-01-24 07:40:19.135353: step: 1212/530, loss: 0.008981010876595974
2023-01-24 07:40:20.206470: step: 1216/530, loss: 0.00025331697543151677
2023-01-24 07:40:21.260734: step: 1220/530, loss: 0.009442894719541073
2023-01-24 07:40:22.315437: step: 1224/530, loss: 0.0033431989140808582
2023-01-24 07:40:23.376110: step: 1228/530, loss: 0.0010546607663854957
2023-01-24 07:40:24.441460: step: 1232/530, loss: 0.010316262021660805
2023-01-24 07:40:25.512631: step: 1236/530, loss: 0.01360830757766962
2023-01-24 07:40:26.593021: step: 1240/530, loss: 0.0015769846504554152
2023-01-24 07:40:27.667178: step: 1244/530, loss: 0.002931649563834071
2023-01-24 07:40:28.731894: step: 1248/530, loss: 0.011826610192656517
2023-01-24 07:40:29.789028: step: 1252/530, loss: 0.031738314777612686
2023-01-24 07:40:30.836329: step: 1256/530, loss: 0.007316206116229296
2023-01-24 07:40:31.907828: step: 1260/530, loss: 0.00010550727893132716
2023-01-24 07:40:32.980595: step: 1264/530, loss: 0.007459431886672974
2023-01-24 07:40:34.033363: step: 1268/530, loss: 0.00347651494666934
2023-01-24 07:40:35.090686: step: 1272/530, loss: 0.0053300149738788605
2023-01-24 07:40:36.147798: step: 1276/530, loss: 0.00813503097742796
2023-01-24 07:40:37.203357: step: 1280/530, loss: 0.0032836797181516886
2023-01-24 07:40:38.246832: step: 1284/530, loss: 5.7676017604535446e-05
2023-01-24 07:40:39.291888: step: 1288/530, loss: 0.007579579018056393
2023-01-24 07:40:40.360403: step: 1292/530, loss: 0.00030347672873176634
2023-01-24 07:40:41.409832: step: 1296/530, loss: 0.009218649938702583
2023-01-24 07:40:42.466093: step: 1300/530, loss: 0.003888055682182312
2023-01-24 07:40:43.534180: step: 1304/530, loss: 0.004083716776221991
2023-01-24 07:40:44.585899: step: 1308/530, loss: 0.006607308052480221
2023-01-24 07:40:45.655273: step: 1312/530, loss: 0.015921570360660553
2023-01-24 07:40:46.717344: step: 1316/530, loss: 0.0011330116540193558
2023-01-24 07:40:47.775836: step: 1320/530, loss: 0.005118370521813631
2023-01-24 07:40:48.839706: step: 1324/530, loss: 0.009682781994342804
2023-01-24 07:40:49.896631: step: 1328/530, loss: 0.0
2023-01-24 07:40:50.963921: step: 1332/530, loss: 0.010913779027760029
2023-01-24 07:40:52.031257: step: 1336/530, loss: 0.0012872458901256323
2023-01-24 07:40:53.098460: step: 1340/530, loss: 0.0005801309598609805
2023-01-24 07:40:54.148978: step: 1344/530, loss: 0.004209278617054224
2023-01-24 07:40:55.204458: step: 1348/530, loss: 0.00030627899104729295
2023-01-24 07:40:56.250105: step: 1352/530, loss: 0.00452372245490551
2023-01-24 07:40:57.306947: step: 1356/530, loss: 0.007813968695700169
2023-01-24 07:40:58.362449: step: 1360/530, loss: 0.006410367786884308
2023-01-24 07:40:59.410933: step: 1364/530, loss: 0.00013037113239988685
2023-01-24 07:41:00.486530: step: 1368/530, loss: 0.006338878534734249
2023-01-24 07:41:01.549378: step: 1372/530, loss: 0.007964469492435455
2023-01-24 07:41:02.604357: step: 1376/530, loss: 0.007284740451723337
2023-01-24 07:41:03.671530: step: 1380/530, loss: 0.0032373496796935797
2023-01-24 07:41:04.735164: step: 1384/530, loss: 0.003451686352491379
2023-01-24 07:41:05.800558: step: 1388/530, loss: 0.001442793756723404
2023-01-24 07:41:06.860258: step: 1392/530, loss: 0.0004326379857957363
2023-01-24 07:41:07.922942: step: 1396/530, loss: 0.007162436842918396
2023-01-24 07:41:09.016252: step: 1400/530, loss: 0.007310534827411175
2023-01-24 07:41:10.100905: step: 1404/530, loss: 0.00580007117241621
2023-01-24 07:41:11.166641: step: 1408/530, loss: 0.001106907962821424
2023-01-24 07:41:12.230245: step: 1412/530, loss: 0.0003788106550928205
2023-01-24 07:41:13.292208: step: 1416/530, loss: 0.001676419167779386
2023-01-24 07:41:14.365100: step: 1420/530, loss: 0.00019797220011241734
2023-01-24 07:41:15.417597: step: 1424/530, loss: 0.001173590775579214
2023-01-24 07:41:16.463484: step: 1428/530, loss: 0.0011421255767345428
2023-01-24 07:41:17.510339: step: 1432/530, loss: 0.0020894964691251516
2023-01-24 07:41:18.566924: step: 1436/530, loss: 0.0011938372626900673
2023-01-24 07:41:19.631976: step: 1440/530, loss: 0.005563205573707819
2023-01-24 07:41:20.692302: step: 1444/530, loss: 0.003811065573245287
2023-01-24 07:41:21.734139: step: 1448/530, loss: 0.00515342503786087
2023-01-24 07:41:22.791493: step: 1452/530, loss: 0.003028250765055418
2023-01-24 07:41:23.847315: step: 1456/530, loss: 0.010524586774408817
2023-01-24 07:41:24.901377: step: 1460/530, loss: 0.0016798849683254957
2023-01-24 07:41:25.964120: step: 1464/530, loss: 0.01206453051418066
2023-01-24 07:41:27.025559: step: 1468/530, loss: 0.0017865870613604784
2023-01-24 07:41:28.076687: step: 1472/530, loss: 0.0026840041391551495
2023-01-24 07:41:29.125335: step: 1476/530, loss: 7.70620463299565e-05
2023-01-24 07:41:30.188841: step: 1480/530, loss: 0.00045172072714194655
2023-01-24 07:41:31.258695: step: 1484/530, loss: 0.00787447951734066
2023-01-24 07:41:32.317849: step: 1488/530, loss: 0.00321327056735754
2023-01-24 07:41:33.381644: step: 1492/530, loss: 0.006025717593729496
2023-01-24 07:41:34.437158: step: 1496/530, loss: 0.00025547249242663383
2023-01-24 07:41:35.504931: step: 1500/530, loss: 0.0001262098376173526
2023-01-24 07:41:36.574610: step: 1504/530, loss: 0.003317362628877163
2023-01-24 07:41:37.656603: step: 1508/530, loss: 0.0278952457010746
2023-01-24 07:41:38.732305: step: 1512/530, loss: 0.0003014483954757452
2023-01-24 07:41:39.785358: step: 1516/530, loss: 0.013164707459509373
2023-01-24 07:41:40.851945: step: 1520/530, loss: 0.00140077352989465
2023-01-24 07:41:41.903135: step: 1524/530, loss: 0.0013717414112761617
2023-01-24 07:41:42.957721: step: 1528/530, loss: 0.002023855457082391
2023-01-24 07:41:44.014400: step: 1532/530, loss: 0.004170695319771767
2023-01-24 07:41:45.074912: step: 1536/530, loss: 0.00061720673693344
2023-01-24 07:41:46.127439: step: 1540/530, loss: 0.000912063813302666
2023-01-24 07:41:47.181912: step: 1544/530, loss: 0.0032152016647160053
2023-01-24 07:41:48.241320: step: 1548/530, loss: 0.002805764554068446
2023-01-24 07:41:49.294381: step: 1552/530, loss: 0.0008888099691830575
2023-01-24 07:41:50.339347: step: 1556/530, loss: 0.004206516779959202
2023-01-24 07:41:51.414411: step: 1560/530, loss: 0.00432842830196023
2023-01-24 07:41:52.479334: step: 1564/530, loss: 0.001752279931679368
2023-01-24 07:41:53.532807: step: 1568/530, loss: 0.0009820128325372934
2023-01-24 07:41:54.593607: step: 1572/530, loss: 0.00031587018747814
2023-01-24 07:41:55.650143: step: 1576/530, loss: 0.0003350767365191132
2023-01-24 07:41:56.703305: step: 1580/530, loss: 0.01824451982975006
2023-01-24 07:41:57.751996: step: 1584/530, loss: 0.000544765149243176
2023-01-24 07:41:58.806285: step: 1588/530, loss: 0.016581397503614426
2023-01-24 07:41:59.867851: step: 1592/530, loss: 0.0027360336389392614
2023-01-24 07:42:00.920167: step: 1596/530, loss: 3.345218715367082e-07
2023-01-24 07:42:01.969600: step: 1600/530, loss: 0.0003424906462896615
2023-01-24 07:42:03.060299: step: 1604/530, loss: 0.0003842185251414776
2023-01-24 07:42:04.114886: step: 1608/530, loss: 0.003292701207101345
2023-01-24 07:42:05.192653: step: 1612/530, loss: 0.0030974324326962233
2023-01-24 07:42:06.266011: step: 1616/530, loss: 0.08294067531824112
2023-01-24 07:42:07.343635: step: 1620/530, loss: 0.0010433156276121736
2023-01-24 07:42:08.409633: step: 1624/530, loss: 7.316777919186279e-05
2023-01-24 07:42:09.469606: step: 1628/530, loss: 0.00175048119854182
2023-01-24 07:42:10.548707: step: 1632/530, loss: 0.02194075472652912
2023-01-24 07:42:11.622503: step: 1636/530, loss: 0.0022982191294431686
2023-01-24 07:42:12.690186: step: 1640/530, loss: 0.0034323742147535086
2023-01-24 07:42:13.763679: step: 1644/530, loss: 0.006930475123226643
2023-01-24 07:42:14.815805: step: 1648/530, loss: 0.00407805060967803
2023-01-24 07:42:15.891326: step: 1652/530, loss: 0.0014996958198025823
2023-01-24 07:42:16.930050: step: 1656/530, loss: 0.005112234503030777
2023-01-24 07:42:17.996851: step: 1660/530, loss: 0.008222192525863647
2023-01-24 07:42:19.045209: step: 1664/530, loss: 0.00886036641895771
2023-01-24 07:42:20.104869: step: 1668/530, loss: 0.0004207780584692955
2023-01-24 07:42:21.174802: step: 1672/530, loss: 0.0012578913010656834
2023-01-24 07:42:22.226465: step: 1676/530, loss: 0.0003702753456309438
2023-01-24 07:42:23.278891: step: 1680/530, loss: 0.00027476067771203816
2023-01-24 07:42:24.334699: step: 1684/530, loss: 0.00023447100829798728
2023-01-24 07:42:25.415832: step: 1688/530, loss: 0.009226815775036812
2023-01-24 07:42:26.477468: step: 1692/530, loss: 0.007423891220241785
2023-01-24 07:42:27.539580: step: 1696/530, loss: 0.004156404174864292
2023-01-24 07:42:28.597959: step: 1700/530, loss: 0.002900763414800167
2023-01-24 07:42:29.655607: step: 1704/530, loss: 0.002932594157755375
2023-01-24 07:42:30.715847: step: 1708/530, loss: 0.009009765461087227
2023-01-24 07:42:31.775385: step: 1712/530, loss: 0.00167070550378412
2023-01-24 07:42:32.829366: step: 1716/530, loss: 0.0011218409053981304
2023-01-24 07:42:33.884872: step: 1720/530, loss: 0.0010735613759607077
2023-01-24 07:42:34.935796: step: 1724/530, loss: 0.0027676960453391075
2023-01-24 07:42:35.994066: step: 1728/530, loss: 0.004438402596861124
2023-01-24 07:42:37.029455: step: 1732/530, loss: 6.169595872052014e-05
2023-01-24 07:42:38.095818: step: 1736/530, loss: 0.011559482663869858
2023-01-24 07:42:39.168308: step: 1740/530, loss: 0.004667510744184256
2023-01-24 07:42:40.236600: step: 1744/530, loss: 0.0001360240567009896
2023-01-24 07:42:41.306630: step: 1748/530, loss: 0.03332662582397461
2023-01-24 07:42:42.379546: step: 1752/530, loss: 0.005930274724960327
2023-01-24 07:42:43.461442: step: 1756/530, loss: 0.0652540922164917
2023-01-24 07:42:44.507242: step: 1760/530, loss: 0.004535254556685686
2023-01-24 07:42:45.567103: step: 1764/530, loss: 0.002991259563714266
2023-01-24 07:42:46.612309: step: 1768/530, loss: 0.0008298219763673842
2023-01-24 07:42:47.691142: step: 1772/530, loss: 0.008967505767941475
2023-01-24 07:42:48.796680: step: 1776/530, loss: 0.003104770788922906
2023-01-24 07:42:49.851505: step: 1780/530, loss: 0.0010101236402988434
2023-01-24 07:42:50.911637: step: 1784/530, loss: 0.0008991596987470984
2023-01-24 07:42:51.976197: step: 1788/530, loss: 0.001970746321603656
2023-01-24 07:42:53.034172: step: 1792/530, loss: 0.0022328312043100595
2023-01-24 07:42:54.099256: step: 1796/530, loss: 0.00284550990909338
2023-01-24 07:42:55.164400: step: 1800/530, loss: 0.0032706218771636486
2023-01-24 07:42:56.230847: step: 1804/530, loss: 0.0001248436456080526
2023-01-24 07:42:57.295905: step: 1808/530, loss: 0.0003272875037509948
2023-01-24 07:42:58.356889: step: 1812/530, loss: 0.009997248649597168
2023-01-24 07:42:59.417588: step: 1816/530, loss: 0.0008368525886908174
2023-01-24 07:43:00.464989: step: 1820/530, loss: 0.0015876280376687646
2023-01-24 07:43:01.530549: step: 1824/530, loss: 0.002629116177558899
2023-01-24 07:43:02.593812: step: 1828/530, loss: 0.004525650758296251
2023-01-24 07:43:03.671464: step: 1832/530, loss: 0.02819177694618702
2023-01-24 07:43:04.724933: step: 1836/530, loss: 0.005889588035643101
2023-01-24 07:43:05.783965: step: 1840/530, loss: 0.0006788388127461076
2023-01-24 07:43:06.842213: step: 1844/530, loss: 0.0006677304627373815
2023-01-24 07:43:07.897870: step: 1848/530, loss: 0.008282354101538658
2023-01-24 07:43:08.956338: step: 1852/530, loss: 0.0008350508287549019
2023-01-24 07:43:10.024800: step: 1856/530, loss: 0.014092615805566311
2023-01-24 07:43:11.078206: step: 1860/530, loss: 0.00304342620074749
2023-01-24 07:43:12.135053: step: 1864/530, loss: 0.0005976548418402672
2023-01-24 07:43:13.206660: step: 1868/530, loss: 0.005507944617420435
2023-01-24 07:43:14.282960: step: 1872/530, loss: 0.006886770948767662
2023-01-24 07:43:15.343053: step: 1876/530, loss: 0.004653391428291798
2023-01-24 07:43:16.415834: step: 1880/530, loss: 0.009824220091104507
2023-01-24 07:43:17.477449: step: 1884/530, loss: 0.01097895111888647
2023-01-24 07:43:18.530788: step: 1888/530, loss: 0.008392523042857647
2023-01-24 07:43:19.596054: step: 1892/530, loss: 0.011279174126684666
2023-01-24 07:43:20.653929: step: 1896/530, loss: 0.002961927792057395
2023-01-24 07:43:21.726291: step: 1900/530, loss: 0.006292080506682396
2023-01-24 07:43:22.786075: step: 1904/530, loss: 0.0016209312016144395
2023-01-24 07:43:23.835137: step: 1908/530, loss: 0.001214727875776589
2023-01-24 07:43:24.910589: step: 1912/530, loss: 0.0003028415667358786
2023-01-24 07:43:25.969427: step: 1916/530, loss: 0.004107190761715174
2023-01-24 07:43:27.008088: step: 1920/530, loss: 0.00702214241027832
2023-01-24 07:43:28.056994: step: 1924/530, loss: 0.007610386703163385
2023-01-24 07:43:29.101622: step: 1928/530, loss: 0.0034361856523901224
2023-01-24 07:43:30.173471: step: 1932/530, loss: 0.002816550899296999
2023-01-24 07:43:31.232560: step: 1936/530, loss: 0.003611439373344183
2023-01-24 07:43:32.315903: step: 1940/530, loss: 0.007487880997359753
2023-01-24 07:43:33.378630: step: 1944/530, loss: 0.003865041770040989
2023-01-24 07:43:34.439970: step: 1948/530, loss: 0.001151856267824769
2023-01-24 07:43:35.486624: step: 1952/530, loss: 0.0038708734791725874
2023-01-24 07:43:36.537216: step: 1956/530, loss: 1.4826046935922932e-05
2023-01-24 07:43:37.586849: step: 1960/530, loss: 0.011877520941197872
2023-01-24 07:43:38.647365: step: 1964/530, loss: 0.016567381098866463
2023-01-24 07:43:39.687325: step: 1968/530, loss: 0.006150108762085438
2023-01-24 07:43:40.743491: step: 1972/530, loss: 0.003371666418388486
2023-01-24 07:43:41.804440: step: 1976/530, loss: 0.009631413966417313
2023-01-24 07:43:42.859086: step: 1980/530, loss: 0.001984379952773452
2023-01-24 07:43:43.927610: step: 1984/530, loss: 0.021570490673184395
2023-01-24 07:43:44.991760: step: 1988/530, loss: 0.004815895576030016
2023-01-24 07:43:46.052106: step: 1992/530, loss: 0.001309867831878364
2023-01-24 07:43:47.102580: step: 1996/530, loss: 0.005153494421392679
2023-01-24 07:43:48.166968: step: 2000/530, loss: 0.0022641292307525873
2023-01-24 07:43:49.229803: step: 2004/530, loss: 0.003979336004704237
2023-01-24 07:43:50.298922: step: 2008/530, loss: 0.007276598829776049
2023-01-24 07:43:51.363577: step: 2012/530, loss: 0.0030632787384092808
2023-01-24 07:43:52.419250: step: 2016/530, loss: 0.0013041881611570716
2023-01-24 07:43:53.490756: step: 2020/530, loss: 0.0005160032887943089
2023-01-24 07:43:54.567289: step: 2024/530, loss: 0.0013672898057848215
2023-01-24 07:43:55.624813: step: 2028/530, loss: 0.0049277967773377895
2023-01-24 07:43:56.681221: step: 2032/530, loss: 0.0016568928258493543
2023-01-24 07:43:57.740846: step: 2036/530, loss: 0.0031998734921216965
2023-01-24 07:43:58.817956: step: 2040/530, loss: 0.00034540813066996634
2023-01-24 07:43:59.882989: step: 2044/530, loss: 0.0014932570047676563
2023-01-24 07:44:00.929141: step: 2048/530, loss: 0.005445054266601801
2023-01-24 07:44:01.989084: step: 2052/530, loss: 0.002347063273191452
2023-01-24 07:44:03.049769: step: 2056/530, loss: 0.006142171565443277
2023-01-24 07:44:04.115411: step: 2060/530, loss: 0.0036080344580113888
2023-01-24 07:44:05.182058: step: 2064/530, loss: 0.008136573247611523
2023-01-24 07:44:06.252076: step: 2068/530, loss: 0.004509699065238237
2023-01-24 07:44:07.306675: step: 2072/530, loss: 6.327142909867689e-05
2023-01-24 07:44:08.371377: step: 2076/530, loss: 0.009542361833155155
2023-01-24 07:44:09.417353: step: 2080/530, loss: 0.0006430309149436653
2023-01-24 07:44:10.468850: step: 2084/530, loss: 0.0005659364978782833
2023-01-24 07:44:11.528058: step: 2088/530, loss: 0.00048064705333672464
2023-01-24 07:44:12.597303: step: 2092/530, loss: 0.008232426829636097
2023-01-24 07:44:13.681097: step: 2096/530, loss: 0.005026193335652351
2023-01-24 07:44:14.738017: step: 2100/530, loss: 0.00412242254242301
2023-01-24 07:44:15.794299: step: 2104/530, loss: 0.003266087267547846
2023-01-24 07:44:16.847645: step: 2108/530, loss: 0.00027584817144088447
2023-01-24 07:44:17.925853: step: 2112/530, loss: 0.0018737884238362312
2023-01-24 07:44:18.988025: step: 2116/530, loss: 0.00425515603274107
2023-01-24 07:44:20.056446: step: 2120/530, loss: 0.006231745705008507
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3838541666666667, 'r': 0.33505297280202406, 'f1': 0.3577971968929416}, 'combined': 0.2636400398158517, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39406656982116506, 'r': 0.29597714611025927, 'f1': 0.3380501728233075}, 'combined': 0.22419907834913655, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3467807424593968, 'r': 0.2830729166666667, 'f1': 0.3117049009384776}, 'combined': 0.20780326729231838, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40004713186669133, 'r': 0.29604874403306275, 'f1': 0.34027913407784305}, 'combined': 0.22207690855606596, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3705900685936055, 'r': 0.3333200996458615, 'f1': 0.35096841661012784}, 'combined': 0.25860830697588366, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3929835109211929, 'r': 0.3062209176009295, 'f1': 0.34421913365359963}, 'combined': 0.2282904098842526, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 07:46:48.997869: step: 4/530, loss: 0.0021094956900924444
2023-01-24 07:46:50.052366: step: 8/530, loss: 0.01311890222132206
2023-01-24 07:46:51.094237: step: 12/530, loss: 5.68782415939495e-05
2023-01-24 07:46:52.145306: step: 16/530, loss: 0.0013302834704518318
2023-01-24 07:46:53.213870: step: 20/530, loss: 0.007437954656779766
2023-01-24 07:46:54.268828: step: 24/530, loss: 0.022962521761655807
2023-01-24 07:46:55.321689: step: 28/530, loss: 0.0009972292464226484
2023-01-24 07:46:56.370480: step: 32/530, loss: 0.00037892538239248097
2023-01-24 07:46:57.439535: step: 36/530, loss: 0.0007030340493656695
2023-01-24 07:46:58.501902: step: 40/530, loss: 0.007828260771930218
2023-01-24 07:46:59.559517: step: 44/530, loss: 0.004577526822686195
2023-01-24 07:47:00.617348: step: 48/530, loss: 0.00975757371634245
2023-01-24 07:47:01.670752: step: 52/530, loss: 0.0036127290222793818
2023-01-24 07:47:02.740347: step: 56/530, loss: 0.002661227248609066
2023-01-24 07:47:03.811164: step: 60/530, loss: 1.735929686219606e-06
2023-01-24 07:47:04.865015: step: 64/530, loss: 0.005232215393334627
2023-01-24 07:47:05.924599: step: 68/530, loss: 0.002060589613392949
2023-01-24 07:47:06.977098: step: 72/530, loss: 0.00871964544057846
2023-01-24 07:47:08.030530: step: 76/530, loss: 0.008005631156265736
2023-01-24 07:47:09.075693: step: 80/530, loss: 0.0041761561296880245
2023-01-24 07:47:10.129082: step: 84/530, loss: 0.00016803358448669314
2023-01-24 07:47:11.174242: step: 88/530, loss: 0.0021858823020011187
2023-01-24 07:47:12.217716: step: 92/530, loss: 0.008031019009649754
2023-01-24 07:47:13.274400: step: 96/530, loss: 0.019964169710874557
2023-01-24 07:47:14.345293: step: 100/530, loss: 0.0006089920061640441
2023-01-24 07:47:15.398008: step: 104/530, loss: 0.00021269729768391699
2023-01-24 07:47:16.451512: step: 108/530, loss: 0.015228603966534138
2023-01-24 07:47:17.509810: step: 112/530, loss: 0.010490295477211475
2023-01-24 07:47:18.576347: step: 116/530, loss: 0.00946330837905407
2023-01-24 07:47:19.634092: step: 120/530, loss: 0.0055718692019581795
2023-01-24 07:47:20.692771: step: 124/530, loss: 0.0025457674637436867
2023-01-24 07:47:21.753404: step: 128/530, loss: 0.0012628454715013504
2023-01-24 07:47:22.815311: step: 132/530, loss: 0.0018173173302784562
2023-01-24 07:47:23.875350: step: 136/530, loss: 0.003521144622936845
2023-01-24 07:47:24.922108: step: 140/530, loss: 4.411282134242356e-05
2023-01-24 07:47:25.975020: step: 144/530, loss: 0.0013732301304116845
2023-01-24 07:47:27.022792: step: 148/530, loss: 0.00035474516334943473
2023-01-24 07:47:28.091103: step: 152/530, loss: 0.00474494369700551
2023-01-24 07:47:29.144958: step: 156/530, loss: 0.009792686440050602
2023-01-24 07:47:30.207894: step: 160/530, loss: 0.002052793512120843
2023-01-24 07:47:31.254146: step: 164/530, loss: 0.004068868234753609
2023-01-24 07:47:32.330669: step: 168/530, loss: 8.105426968540996e-05
2023-01-24 07:47:33.379710: step: 172/530, loss: 0.0036880180705338717
2023-01-24 07:47:34.438962: step: 176/530, loss: 0.0011073502246290445
2023-01-24 07:47:35.509596: step: 180/530, loss: 0.003766452195122838
2023-01-24 07:47:36.560664: step: 184/530, loss: 0.0005020612734369934
2023-01-24 07:47:37.630137: step: 188/530, loss: 0.012637553736567497
2023-01-24 07:47:38.682980: step: 192/530, loss: 0.0007634004577994347
2023-01-24 07:47:39.756005: step: 196/530, loss: 0.0008837177301757038
2023-01-24 07:47:40.814403: step: 200/530, loss: 0.002109450288116932
2023-01-24 07:47:41.881154: step: 204/530, loss: 0.006022005807608366
2023-01-24 07:47:42.935796: step: 208/530, loss: 0.004695853218436241
2023-01-24 07:47:43.996377: step: 212/530, loss: 0.002789364429190755
2023-01-24 07:47:45.054134: step: 216/530, loss: 0.00016741837316658348
2023-01-24 07:47:46.133498: step: 220/530, loss: 0.001817410346120596
2023-01-24 07:47:47.191362: step: 224/530, loss: 0.0037393856327980757
2023-01-24 07:47:48.258191: step: 228/530, loss: 0.007606687489897013
2023-01-24 07:47:49.341919: step: 232/530, loss: 0.000278868421446532
2023-01-24 07:47:50.393134: step: 236/530, loss: 0.00959752406924963
2023-01-24 07:47:51.451513: step: 240/530, loss: 0.0002712109999265522
2023-01-24 07:47:52.530304: step: 244/530, loss: 0.002412226051092148
2023-01-24 07:47:53.604505: step: 248/530, loss: 0.00445058848708868
2023-01-24 07:47:54.665349: step: 252/530, loss: 0.001412743586115539
2023-01-24 07:47:55.722509: step: 256/530, loss: 0.0006932559190317988
2023-01-24 07:47:56.778342: step: 260/530, loss: 0.0005659185699187219
2023-01-24 07:47:57.828201: step: 264/530, loss: 0.001991112483665347
2023-01-24 07:47:58.893266: step: 268/530, loss: 0.008442804217338562
2023-01-24 07:47:59.963334: step: 272/530, loss: 0.0014403002569451928
2023-01-24 07:48:01.008815: step: 276/530, loss: 0.0
2023-01-24 07:48:02.092105: step: 280/530, loss: 0.007657312788069248
2023-01-24 07:48:03.154153: step: 284/530, loss: 3.607563121477142e-05
2023-01-24 07:48:04.215559: step: 288/530, loss: 0.002834174083545804
2023-01-24 07:48:05.269503: step: 292/530, loss: 0.0027063863817602396
2023-01-24 07:48:06.335291: step: 296/530, loss: 0.0022629655431956053
2023-01-24 07:48:07.390637: step: 300/530, loss: 0.0012459707213565707
2023-01-24 07:48:08.442910: step: 304/530, loss: 0.00220873998478055
2023-01-24 07:48:09.503073: step: 308/530, loss: 0.004601443186402321
2023-01-24 07:48:10.569901: step: 312/530, loss: 0.00023372155555989593
2023-01-24 07:48:11.638559: step: 316/530, loss: 0.001204905565828085
2023-01-24 07:48:12.692839: step: 320/530, loss: 0.0012778834206983447
2023-01-24 07:48:13.746073: step: 324/530, loss: 2.5372843083459884e-05
2023-01-24 07:48:14.798504: step: 328/530, loss: 0.0021881035063415766
2023-01-24 07:48:15.861145: step: 332/530, loss: 0.0008263842319138348
2023-01-24 07:48:16.930976: step: 336/530, loss: 0.004658328369259834
2023-01-24 07:48:17.997832: step: 340/530, loss: 0.005119822919368744
2023-01-24 07:48:19.070510: step: 344/530, loss: 0.004938906989991665
2023-01-24 07:48:20.133490: step: 348/530, loss: 0.007177949883043766
2023-01-24 07:48:21.183838: step: 352/530, loss: 0.0011792953591793776
2023-01-24 07:48:22.253905: step: 356/530, loss: 0.006008140277117491
2023-01-24 07:48:23.313818: step: 360/530, loss: 0.003989999648183584
2023-01-24 07:48:24.388737: step: 364/530, loss: 0.010769250802695751
2023-01-24 07:48:25.445158: step: 368/530, loss: 0.008618909865617752
2023-01-24 07:48:26.509762: step: 372/530, loss: 0.0006336081423796713
2023-01-24 07:48:27.575858: step: 376/530, loss: 0.0014145129825919867
2023-01-24 07:48:28.619231: step: 380/530, loss: 0.0007761603919789195
2023-01-24 07:48:29.692448: step: 384/530, loss: 0.0005060825496912003
2023-01-24 07:48:30.750498: step: 388/530, loss: 0.0012338366359472275
2023-01-24 07:48:31.818004: step: 392/530, loss: 0.02588936872780323
2023-01-24 07:48:32.891214: step: 396/530, loss: 1.960390727617778e-05
2023-01-24 07:48:33.949101: step: 400/530, loss: 0.0029859195929020643
2023-01-24 07:48:35.008331: step: 404/530, loss: 0.0025051666889339685
2023-01-24 07:48:36.057973: step: 408/530, loss: 0.0028211469762027264
2023-01-24 07:48:37.098689: step: 412/530, loss: 0.004626823123544455
2023-01-24 07:48:38.162844: step: 416/530, loss: 0.007663717959076166
2023-01-24 07:48:39.207372: step: 420/530, loss: 0.005124426446855068
2023-01-24 07:48:40.279419: step: 424/530, loss: 0.0013528214767575264
2023-01-24 07:48:41.337446: step: 428/530, loss: 0.0014767188113182783
2023-01-24 07:48:42.388700: step: 432/530, loss: 0.001254978938959539
2023-01-24 07:48:43.433265: step: 436/530, loss: 0.01409226469695568
2023-01-24 07:48:44.476998: step: 440/530, loss: 0.00011738141620298848
2023-01-24 07:48:45.523786: step: 444/530, loss: 0.00019990344299003482
2023-01-24 07:48:46.571424: step: 448/530, loss: 0.011193651705980301
2023-01-24 07:48:47.632015: step: 452/530, loss: 0.006073852069675922
2023-01-24 07:48:48.684712: step: 456/530, loss: 0.0028117834590375423
2023-01-24 07:48:49.753016: step: 460/530, loss: 0.003322468139231205
2023-01-24 07:48:50.810186: step: 464/530, loss: 0.0007779276929795742
2023-01-24 07:48:51.891075: step: 468/530, loss: 0.004181955941021442
2023-01-24 07:48:52.935809: step: 472/530, loss: 6.901913729961962e-05
2023-01-24 07:48:54.001965: step: 476/530, loss: 0.012137278914451599
2023-01-24 07:48:55.080883: step: 480/530, loss: 5.6343269534409046e-05
2023-01-24 07:48:56.134212: step: 484/530, loss: 0.010861517861485481
2023-01-24 07:48:57.198663: step: 488/530, loss: 0.024029167369008064
2023-01-24 07:48:58.256784: step: 492/530, loss: 0.00993871409446001
2023-01-24 07:48:59.317899: step: 496/530, loss: 0.003906929399818182
2023-01-24 07:49:00.395926: step: 500/530, loss: 0.001860091113485396
2023-01-24 07:49:01.447512: step: 504/530, loss: 0.003279547905549407
2023-01-24 07:49:02.502560: step: 508/530, loss: 0.004254957661032677
2023-01-24 07:49:03.585740: step: 512/530, loss: 0.0016864299541339278
2023-01-24 07:49:04.656650: step: 516/530, loss: 0.0035776819568127394
2023-01-24 07:49:05.727798: step: 520/530, loss: 0.01032742578536272
2023-01-24 07:49:06.789192: step: 524/530, loss: 0.0018546065548434854
2023-01-24 07:49:07.834841: step: 528/530, loss: 0.0006155781447887421
2023-01-24 07:49:08.879886: step: 532/530, loss: 0.0005933456122875214
2023-01-24 07:49:09.951680: step: 536/530, loss: 0.009491799399256706
2023-01-24 07:49:11.027607: step: 540/530, loss: 0.015153428539633751
2023-01-24 07:49:12.082318: step: 544/530, loss: 0.0011128297774121165
2023-01-24 07:49:13.142093: step: 548/530, loss: 0.005828630179166794
2023-01-24 07:49:14.211310: step: 552/530, loss: 0.0003642754163593054
2023-01-24 07:49:15.269149: step: 556/530, loss: 0.01035226508975029
2023-01-24 07:49:16.337541: step: 560/530, loss: 0.025892533361911774
2023-01-24 07:49:17.401399: step: 564/530, loss: 0.010160128585994244
2023-01-24 07:49:18.456246: step: 568/530, loss: 0.006989937741309404
2023-01-24 07:49:19.516839: step: 572/530, loss: 0.008228665217757225
2023-01-24 07:49:20.583564: step: 576/530, loss: 0.0011891174362972379
2023-01-24 07:49:21.651996: step: 580/530, loss: 0.0011885742424055934
2023-01-24 07:49:22.713627: step: 584/530, loss: 0.01902218721807003
2023-01-24 07:49:23.767938: step: 588/530, loss: 0.002112123416736722
2023-01-24 07:49:24.826572: step: 592/530, loss: 0.0014739600010216236
2023-01-24 07:49:25.892107: step: 596/530, loss: 0.003994252532720566
2023-01-24 07:49:26.946162: step: 600/530, loss: 6.639136245212285e-07
2023-01-24 07:49:27.994042: step: 604/530, loss: 0.010039624758064747
2023-01-24 07:49:29.052587: step: 608/530, loss: 0.000832458958029747
2023-01-24 07:49:30.093424: step: 612/530, loss: 0.004489888437092304
2023-01-24 07:49:31.157063: step: 616/530, loss: 0.007010675501078367
2023-01-24 07:49:32.224477: step: 620/530, loss: 8.574331332056317e-06
2023-01-24 07:49:33.300177: step: 624/530, loss: 0.002068987349048257
2023-01-24 07:49:34.363054: step: 628/530, loss: 0.0007186959264799953
2023-01-24 07:49:35.423831: step: 632/530, loss: 0.009036572650074959
2023-01-24 07:49:36.493701: step: 636/530, loss: 0.000980931450612843
2023-01-24 07:49:37.549585: step: 640/530, loss: 0.0005726184463128448
2023-01-24 07:49:38.608538: step: 644/530, loss: 0.008107513189315796
2023-01-24 07:49:39.668416: step: 648/530, loss: 0.0014254581183195114
2023-01-24 07:49:40.730270: step: 652/530, loss: 0.010879823938012123
2023-01-24 07:49:41.781640: step: 656/530, loss: 0.002156768925487995
2023-01-24 07:49:42.857269: step: 660/530, loss: 0.018113087862730026
2023-01-24 07:49:43.919088: step: 664/530, loss: 0.0005491006304509938
2023-01-24 07:49:44.987121: step: 668/530, loss: 0.003203930100426078
2023-01-24 07:49:46.064284: step: 672/530, loss: 0.008084729313850403
2023-01-24 07:49:47.120577: step: 676/530, loss: 0.00035008369013667107
2023-01-24 07:49:48.179681: step: 680/530, loss: 0.011634944938123226
2023-01-24 07:49:49.230036: step: 684/530, loss: 0.003046165220439434
2023-01-24 07:49:50.281448: step: 688/530, loss: 0.003385255578905344
2023-01-24 07:49:51.340942: step: 692/530, loss: 0.001965835690498352
2023-01-24 07:49:52.390235: step: 696/530, loss: 0.001608905615285039
2023-01-24 07:49:53.438038: step: 700/530, loss: 0.0017961891135200858
2023-01-24 07:49:54.539681: step: 704/530, loss: 0.01001130510121584
2023-01-24 07:49:55.600226: step: 708/530, loss: 0.013646242208778858
2023-01-24 07:49:56.662560: step: 712/530, loss: 0.011228703893721104
2023-01-24 07:49:57.716048: step: 716/530, loss: 0.008186562918126583
2023-01-24 07:49:58.774958: step: 720/530, loss: 0.002894805744290352
2023-01-24 07:49:59.852883: step: 724/530, loss: 0.0039372979663312435
2023-01-24 07:50:00.918261: step: 728/530, loss: 0.002604193054139614
2023-01-24 07:50:01.980733: step: 732/530, loss: 0.0016125808469951153
2023-01-24 07:50:03.054850: step: 736/530, loss: 0.0024360036477446556
2023-01-24 07:50:04.121198: step: 740/530, loss: 0.010964752174913883
2023-01-24 07:50:05.191772: step: 744/530, loss: 0.018129222095012665
2023-01-24 07:50:06.254016: step: 748/530, loss: 0.00019537939806468785
2023-01-24 07:50:07.303120: step: 752/530, loss: 0.004652428440749645
2023-01-24 07:50:08.361421: step: 756/530, loss: 0.011240316554903984
2023-01-24 07:50:09.421881: step: 760/530, loss: 0.003953434992581606
2023-01-24 07:50:10.482119: step: 764/530, loss: 0.01022385898977518
2023-01-24 07:50:11.531357: step: 768/530, loss: 0.004109564237296581
2023-01-24 07:50:12.599405: step: 772/530, loss: 0.0027495494578033686
2023-01-24 07:50:13.656043: step: 776/530, loss: 0.0020026029087603092
2023-01-24 07:50:14.727068: step: 780/530, loss: 0.0038549068849533796
2023-01-24 07:50:15.792215: step: 784/530, loss: 0.0016286814352497458
2023-01-24 07:50:16.848186: step: 788/530, loss: 0.0003526336804497987
2023-01-24 07:50:17.899477: step: 792/530, loss: 0.0037495382130146027
2023-01-24 07:50:18.960204: step: 796/530, loss: 0.0010510339634492993
2023-01-24 07:50:20.022171: step: 800/530, loss: 0.01007411815226078
2023-01-24 07:50:21.081425: step: 804/530, loss: 0.0002998080162797123
2023-01-24 07:50:22.128751: step: 808/530, loss: 5.281314952298999e-05
2023-01-24 07:50:23.189767: step: 812/530, loss: 0.006465135142207146
2023-01-24 07:50:24.240198: step: 816/530, loss: 0.004686877131462097
2023-01-24 07:50:25.325098: step: 820/530, loss: 0.004502084571868181
2023-01-24 07:50:26.391055: step: 824/530, loss: 0.017148464918136597
2023-01-24 07:50:27.451302: step: 828/530, loss: 0.004372735042124987
2023-01-24 07:50:28.518548: step: 832/530, loss: 0.01028257142752409
2023-01-24 07:50:29.585920: step: 836/530, loss: 0.002823252696543932
2023-01-24 07:50:30.642755: step: 840/530, loss: 0.002731231739744544
2023-01-24 07:50:31.698317: step: 844/530, loss: 0.006105278618633747
2023-01-24 07:50:32.751918: step: 848/530, loss: 0.016903437674045563
2023-01-24 07:50:33.813853: step: 852/530, loss: 0.0007305179606191814
2023-01-24 07:50:34.884347: step: 856/530, loss: 0.005039713345468044
2023-01-24 07:50:35.931857: step: 860/530, loss: 0.004273528233170509
2023-01-24 07:50:37.017625: step: 864/530, loss: 0.0023842991795390844
2023-01-24 07:50:38.068356: step: 868/530, loss: 0.0032738943118602037
2023-01-24 07:50:39.116549: step: 872/530, loss: 0.00440587243065238
2023-01-24 07:50:40.174632: step: 876/530, loss: 0.0022535305470228195
2023-01-24 07:50:41.235916: step: 880/530, loss: 0.0012918816646561027
2023-01-24 07:50:42.293326: step: 884/530, loss: 0.004441816359758377
2023-01-24 07:50:43.347365: step: 888/530, loss: 0.0014922457048669457
2023-01-24 07:50:44.429084: step: 892/530, loss: 0.00581457419320941
2023-01-24 07:50:45.494572: step: 896/530, loss: 0.006170479580760002
2023-01-24 07:50:46.555472: step: 900/530, loss: 0.015530979260802269
2023-01-24 07:50:47.617323: step: 904/530, loss: 0.005349037237465382
2023-01-24 07:50:48.681731: step: 908/530, loss: 0.006273407489061356
2023-01-24 07:50:49.766098: step: 912/530, loss: 0.008132955059409142
2023-01-24 07:50:50.825786: step: 916/530, loss: 0.0030964715406298637
2023-01-24 07:50:51.898954: step: 920/530, loss: 0.01400149054825306
2023-01-24 07:50:52.948331: step: 924/530, loss: 0.0028561505023390055
2023-01-24 07:50:54.041677: step: 928/530, loss: 0.029421506449580193
2023-01-24 07:50:55.083801: step: 932/530, loss: 0.001328668207861483
2023-01-24 07:50:56.146277: step: 936/530, loss: 6.479109288193285e-05
2023-01-24 07:50:57.205484: step: 940/530, loss: 0.0013753786915913224
2023-01-24 07:50:58.269073: step: 944/530, loss: 0.004724790342152119
2023-01-24 07:50:59.349320: step: 948/530, loss: 0.004426884464919567
2023-01-24 07:51:00.410109: step: 952/530, loss: 0.00037916458677500486
2023-01-24 07:51:01.491168: step: 956/530, loss: 0.006889330223202705
2023-01-24 07:51:02.568070: step: 960/530, loss: 0.006863574963063002
2023-01-24 07:51:03.629406: step: 964/530, loss: 0.0020583600271493196
2023-01-24 07:51:04.698566: step: 968/530, loss: 0.024703780189156532
2023-01-24 07:51:05.760726: step: 972/530, loss: 6.011876030243002e-05
2023-01-24 07:51:06.819630: step: 976/530, loss: 0.006502603646367788
2023-01-24 07:51:07.878156: step: 980/530, loss: 0.010413480922579765
2023-01-24 07:51:08.951597: step: 984/530, loss: 0.05847205966711044
2023-01-24 07:51:10.026069: step: 988/530, loss: 0.0022907813545316458
2023-01-24 07:51:11.079436: step: 992/530, loss: 0.0017779474146664143
2023-01-24 07:51:12.132992: step: 996/530, loss: 0.009272441267967224
2023-01-24 07:51:13.181421: step: 1000/530, loss: 0.0010802585165947676
2023-01-24 07:51:14.234256: step: 1004/530, loss: 0.008206567727029324
2023-01-24 07:51:15.288704: step: 1008/530, loss: 0.007077578920871019
2023-01-24 07:51:16.357239: step: 1012/530, loss: 0.005512617994099855
2023-01-24 07:51:17.414308: step: 1016/530, loss: 0.0031960357446223497
2023-01-24 07:51:18.468183: step: 1020/530, loss: 0.000671093468554318
2023-01-24 07:51:19.531587: step: 1024/530, loss: 0.0014497991651296616
2023-01-24 07:51:20.586189: step: 1028/530, loss: 0.005251995753496885
2023-01-24 07:51:21.647162: step: 1032/530, loss: 0.0006869861972518265
2023-01-24 07:51:22.698178: step: 1036/530, loss: 0.0003046881465706974
2023-01-24 07:51:23.782042: step: 1040/530, loss: 0.00020803413644898683
2023-01-24 07:51:24.856873: step: 1044/530, loss: 0.006651169154793024
2023-01-24 07:51:25.899065: step: 1048/530, loss: 0.0034765827003866434
2023-01-24 07:51:26.953993: step: 1052/530, loss: 0.004014601930975914
2023-01-24 07:51:28.015401: step: 1056/530, loss: 0.0021639573387801647
2023-01-24 07:51:29.070625: step: 1060/530, loss: 0.001757454709149897
2023-01-24 07:51:30.132443: step: 1064/530, loss: 0.00246369163505733
2023-01-24 07:51:31.217222: step: 1068/530, loss: 0.002517396816983819
2023-01-24 07:51:32.318459: step: 1072/530, loss: 0.0030611990951001644
2023-01-24 07:51:33.374105: step: 1076/530, loss: 0.002291389275342226
2023-01-24 07:51:34.432309: step: 1080/530, loss: 0.012959088198840618
2023-01-24 07:51:35.507840: step: 1084/530, loss: 0.020819442346692085
2023-01-24 07:51:36.575114: step: 1088/530, loss: 0.006599036045372486
2023-01-24 07:51:37.638687: step: 1092/530, loss: 0.0009701611124910414
2023-01-24 07:51:38.690880: step: 1096/530, loss: 0.0013894721632823348
2023-01-24 07:51:39.757814: step: 1100/530, loss: 0.006052486132830381
2023-01-24 07:51:40.810411: step: 1104/530, loss: 0.0004752454406116158
2023-01-24 07:51:41.870736: step: 1108/530, loss: 0.0039168051443994045
2023-01-24 07:51:42.932360: step: 1112/530, loss: 0.01796250231564045
2023-01-24 07:51:43.996515: step: 1116/530, loss: 0.008454777300357819
2023-01-24 07:51:45.043418: step: 1120/530, loss: 0.0003409204655326903
2023-01-24 07:51:46.120774: step: 1124/530, loss: 0.00257872580550611
2023-01-24 07:51:47.200437: step: 1128/530, loss: 0.0021439490374177694
2023-01-24 07:51:48.260172: step: 1132/530, loss: 0.00038046290865167975
2023-01-24 07:51:49.327251: step: 1136/530, loss: 0.019083842635154724
2023-01-24 07:51:50.376731: step: 1140/530, loss: 0.010760469362139702
2023-01-24 07:51:51.434155: step: 1144/530, loss: 0.012481419369578362
2023-01-24 07:51:52.502718: step: 1148/530, loss: 0.007176099810749292
2023-01-24 07:51:53.545834: step: 1152/530, loss: 0.007717461790889502
2023-01-24 07:51:54.613797: step: 1156/530, loss: 8.064800931606442e-05
2023-01-24 07:51:55.646832: step: 1160/530, loss: 8.959236583905295e-05
2023-01-24 07:51:56.707450: step: 1164/530, loss: 0.00043193131568841636
2023-01-24 07:51:57.767207: step: 1168/530, loss: 0.0027817648369818926
2023-01-24 07:51:58.823988: step: 1172/530, loss: 0.0002408848813502118
2023-01-24 07:51:59.869844: step: 1176/530, loss: 0.007526103872805834
2023-01-24 07:52:00.937370: step: 1180/530, loss: 0.007288565393537283
2023-01-24 07:52:02.002565: step: 1184/530, loss: 0.00638193404302001
2023-01-24 07:52:03.060751: step: 1188/530, loss: 0.005992783233523369
2023-01-24 07:52:04.113932: step: 1192/530, loss: 0.0013478028122335672
2023-01-24 07:52:05.178125: step: 1196/530, loss: 0.006875394843518734
2023-01-24 07:52:06.239932: step: 1200/530, loss: 0.0032173816580325365
2023-01-24 07:52:07.309604: step: 1204/530, loss: 0.0013164657866582274
2023-01-24 07:52:08.366495: step: 1208/530, loss: 0.0013198578963056207
2023-01-24 07:52:09.425936: step: 1212/530, loss: 0.00010920914064627141
2023-01-24 07:52:10.499398: step: 1216/530, loss: 0.0014433127362281084
2023-01-24 07:52:11.556526: step: 1220/530, loss: 0.0038386075757443905
2023-01-24 07:52:12.613470: step: 1224/530, loss: 0.010455395095050335
2023-01-24 07:52:13.659849: step: 1228/530, loss: 7.119439260350191e-09
2023-01-24 07:52:14.725326: step: 1232/530, loss: 0.010438834317028522
2023-01-24 07:52:15.790576: step: 1236/530, loss: 0.005345779471099377
2023-01-24 07:52:16.852918: step: 1240/530, loss: 0.00016140179650392383
2023-01-24 07:52:17.905946: step: 1244/530, loss: 0.0022262553684413433
2023-01-24 07:52:18.949256: step: 1248/530, loss: 0.0019818528089672327
2023-01-24 07:52:20.014010: step: 1252/530, loss: 0.00013990153092890978
2023-01-24 07:52:21.083695: step: 1256/530, loss: 0.008081446401774883
2023-01-24 07:52:22.156404: step: 1260/530, loss: 2.049219619948417e-05
2023-01-24 07:52:23.216871: step: 1264/530, loss: 0.008635352365672588
2023-01-24 07:52:24.264607: step: 1268/530, loss: 0.0005168033530935645
2023-01-24 07:52:25.336521: step: 1272/530, loss: 0.004564700648188591
2023-01-24 07:52:26.402180: step: 1276/530, loss: 0.0020665416959673166
2023-01-24 07:52:27.463469: step: 1280/530, loss: 0.001532746129669249
2023-01-24 07:52:28.514995: step: 1284/530, loss: 0.0020006042905151844
2023-01-24 07:52:29.567898: step: 1288/530, loss: 0.00018192874267697334
2023-01-24 07:52:30.622055: step: 1292/530, loss: 0.00016661809058859944
2023-01-24 07:52:31.696360: step: 1296/530, loss: 0.005625535733997822
2023-01-24 07:52:32.743123: step: 1300/530, loss: 0.0014008082216605544
2023-01-24 07:52:33.809214: step: 1304/530, loss: 0.00012441261787898839
2023-01-24 07:52:34.857307: step: 1308/530, loss: 0.002166094956919551
2023-01-24 07:52:35.902221: step: 1312/530, loss: 0.00018916135013569146
2023-01-24 07:52:36.965753: step: 1316/530, loss: 0.005777540151029825
2023-01-24 07:52:38.029269: step: 1320/530, loss: 0.005481211002916098
2023-01-24 07:52:39.084030: step: 1324/530, loss: 0.01034446619451046
2023-01-24 07:52:40.149906: step: 1328/530, loss: 0.00807970855385065
2023-01-24 07:52:41.210028: step: 1332/530, loss: 0.009156055748462677
2023-01-24 07:52:42.282459: step: 1336/530, loss: 0.0037293985951691866
2023-01-24 07:52:43.362544: step: 1340/530, loss: 0.0008094247314147651
2023-01-24 07:52:44.428987: step: 1344/530, loss: 0.0014338564360514283
2023-01-24 07:52:45.486560: step: 1348/530, loss: 0.0030299918726086617
2023-01-24 07:52:46.541975: step: 1352/530, loss: 0.001763385720551014
2023-01-24 07:52:47.605759: step: 1356/530, loss: 0.01738511584699154
2023-01-24 07:52:48.675307: step: 1360/530, loss: 0.0004947047564201057
2023-01-24 07:52:49.734621: step: 1364/530, loss: 0.00026786079979501665
2023-01-24 07:52:50.803555: step: 1368/530, loss: 0.0019334799144417048
2023-01-24 07:52:51.852489: step: 1372/530, loss: 3.631848449003883e-05
2023-01-24 07:52:52.909626: step: 1376/530, loss: 0.00024570233654230833
2023-01-24 07:52:53.967925: step: 1380/530, loss: 0.0009549768292345107
2023-01-24 07:52:55.016795: step: 1384/530, loss: 0.0011146035976707935
2023-01-24 07:52:56.072415: step: 1388/530, loss: 0.007656758185476065
2023-01-24 07:52:57.132099: step: 1392/530, loss: 0.0015436556423082948
2023-01-24 07:52:58.189819: step: 1396/530, loss: 0.0015269832219928503
2023-01-24 07:52:59.256756: step: 1400/530, loss: 0.005968090612441301
2023-01-24 07:53:00.315893: step: 1404/530, loss: 0.0006276214262470603
2023-01-24 07:53:01.367852: step: 1408/530, loss: 0.0004965476109646261
2023-01-24 07:53:02.428669: step: 1412/530, loss: 0.002950194524601102
2023-01-24 07:53:03.483933: step: 1416/530, loss: 0.0026596609968692064
2023-01-24 07:53:04.551696: step: 1420/530, loss: 0.0009486007620580494
2023-01-24 07:53:05.622248: step: 1424/530, loss: 0.007135091815143824
2023-01-24 07:53:06.673702: step: 1428/530, loss: 0.013007229194045067
2023-01-24 07:53:07.738886: step: 1432/530, loss: 0.008039118722081184
2023-01-24 07:53:08.782861: step: 1436/530, loss: 0.00043564659426920116
2023-01-24 07:53:09.836814: step: 1440/530, loss: 0.00016066610987763852
2023-01-24 07:53:10.906316: step: 1444/530, loss: 0.004876438062638044
2023-01-24 07:53:11.977927: step: 1448/530, loss: 0.013507763855159283
2023-01-24 07:53:13.043912: step: 1452/530, loss: 0.0037977967876940966
2023-01-24 07:53:14.101911: step: 1456/530, loss: 0.004352536518126726
2023-01-24 07:53:15.147106: step: 1460/530, loss: 0.00146788964048028
2023-01-24 07:53:16.210262: step: 1464/530, loss: 0.002133857225999236
2023-01-24 07:53:17.286070: step: 1468/530, loss: 0.0037330419290810823
2023-01-24 07:53:18.334729: step: 1472/530, loss: 0.0004797769943252206
2023-01-24 07:53:19.390172: step: 1476/530, loss: 0.008645614609122276
2023-01-24 07:53:20.438459: step: 1480/530, loss: 0.0021444440353661776
2023-01-24 07:53:21.503709: step: 1484/530, loss: 4.29782630817499e-05
2023-01-24 07:53:22.570048: step: 1488/530, loss: 0.0023098120000213385
2023-01-24 07:53:23.637830: step: 1492/530, loss: 0.004420808982104063
2023-01-24 07:53:24.692502: step: 1496/530, loss: 0.0077218953520059586
2023-01-24 07:53:25.751669: step: 1500/530, loss: 0.0022348875645548105
2023-01-24 07:53:26.808386: step: 1504/530, loss: 1.2686515219684225e-05
2023-01-24 07:53:27.880291: step: 1508/530, loss: 0.019776422530412674
2023-01-24 07:53:28.954735: step: 1512/530, loss: 0.02693009003996849
2023-01-24 07:53:30.031642: step: 1516/530, loss: 0.001665038405917585
2023-01-24 07:53:31.102568: step: 1520/530, loss: 0.006000143941491842
2023-01-24 07:53:32.158386: step: 1524/530, loss: 0.006056696642190218
2023-01-24 07:53:33.212604: step: 1528/530, loss: 0.0008812794694676995
2023-01-24 07:53:34.270166: step: 1532/530, loss: 0.002790366066619754
2023-01-24 07:53:35.327358: step: 1536/530, loss: 0.002530885860323906
2023-01-24 07:53:36.378001: step: 1540/530, loss: 0.00013026398664806038
2023-01-24 07:53:37.431254: step: 1544/530, loss: 0.0027537934947758913
2023-01-24 07:53:38.492454: step: 1548/530, loss: 0.006445032078772783
2023-01-24 07:53:39.548181: step: 1552/530, loss: 0.002408068859949708
2023-01-24 07:53:40.601714: step: 1556/530, loss: 0.002585968002676964
2023-01-24 07:53:41.659260: step: 1560/530, loss: 0.0020395778119564056
2023-01-24 07:53:42.724162: step: 1564/530, loss: 0.0022965550888329744
2023-01-24 07:53:43.773732: step: 1568/530, loss: 0.00021644317894242704
2023-01-24 07:53:44.829567: step: 1572/530, loss: 0.002595591591671109
2023-01-24 07:53:45.883023: step: 1576/530, loss: 0.019007235765457153
2023-01-24 07:53:46.945194: step: 1580/530, loss: 0.0025495353620499372
2023-01-24 07:53:48.009296: step: 1584/530, loss: 0.006664119195193052
2023-01-24 07:53:49.070068: step: 1588/530, loss: 0.0022273568902164698
2023-01-24 07:53:50.117945: step: 1592/530, loss: 0.010411778464913368
2023-01-24 07:53:51.173152: step: 1596/530, loss: 0.001893027569167316
2023-01-24 07:53:52.224746: step: 1600/530, loss: 2.3663549654884264e-05
2023-01-24 07:53:53.284512: step: 1604/530, loss: 0.005143004935234785
2023-01-24 07:53:54.342552: step: 1608/530, loss: 0.0007624438148923218
2023-01-24 07:53:55.417256: step: 1612/530, loss: 0.0005540741258300841
2023-01-24 07:53:56.475870: step: 1616/530, loss: 0.0016197680961340666
2023-01-24 07:53:57.524979: step: 1620/530, loss: 0.0016089766286313534
2023-01-24 07:53:58.585647: step: 1624/530, loss: 0.001013288157992065
2023-01-24 07:53:59.640625: step: 1628/530, loss: 0.0021637678146362305
2023-01-24 07:54:00.702469: step: 1632/530, loss: 0.003966888412833214
2023-01-24 07:54:01.769253: step: 1636/530, loss: 0.005445551592856646
2023-01-24 07:54:02.840403: step: 1640/530, loss: 0.0011840645456686616
2023-01-24 07:54:03.900602: step: 1644/530, loss: 0.00056924216914922
2023-01-24 07:54:04.957900: step: 1648/530, loss: 0.0016776478150859475
2023-01-24 07:54:06.028390: step: 1652/530, loss: 0.004186647478491068
2023-01-24 07:54:07.081497: step: 1656/530, loss: 0.0036190024111419916
2023-01-24 07:54:08.143358: step: 1660/530, loss: 0.001610213192179799
2023-01-24 07:54:09.214796: step: 1664/530, loss: 0.000516460626386106
2023-01-24 07:54:10.258067: step: 1668/530, loss: 0.0005445809219963849
2023-01-24 07:54:11.309348: step: 1672/530, loss: 0.004317122045904398
2023-01-24 07:54:12.366058: step: 1676/530, loss: 0.0005467144073918462
2023-01-24 07:54:13.417024: step: 1680/530, loss: 0.007170079741626978
2023-01-24 07:54:14.460236: step: 1684/530, loss: 0.0007546812994405627
2023-01-24 07:54:15.516294: step: 1688/530, loss: 0.0083444369956851
2023-01-24 07:54:16.565633: step: 1692/530, loss: 0.0031342809088528156
2023-01-24 07:54:17.604765: step: 1696/530, loss: 0.007302084006369114
2023-01-24 07:54:18.679392: step: 1700/530, loss: 0.0024414104409515858
2023-01-24 07:54:19.733405: step: 1704/530, loss: 0.011127714067697525
2023-01-24 07:54:20.807327: step: 1708/530, loss: 0.0053037721663713455
2023-01-24 07:54:21.854804: step: 1712/530, loss: 0.0007818203885108232
2023-01-24 07:54:22.898816: step: 1716/530, loss: 0.0033460850827395916
2023-01-24 07:54:23.971787: step: 1720/530, loss: 0.0031537010800093412
2023-01-24 07:54:25.017369: step: 1724/530, loss: 0.00017203677271027118
2023-01-24 07:54:26.072892: step: 1728/530, loss: 0.0004809864913113415
2023-01-24 07:54:27.120869: step: 1732/530, loss: 0.00078528409358114
2023-01-24 07:54:28.163167: step: 1736/530, loss: 0.0038315928541123867
2023-01-24 07:54:29.209676: step: 1740/530, loss: 0.010124877095222473
2023-01-24 07:54:30.268730: step: 1744/530, loss: 0.0016368799842894077
2023-01-24 07:54:31.330615: step: 1748/530, loss: 0.002827103016898036
2023-01-24 07:54:32.394465: step: 1752/530, loss: 0.003476216457784176
2023-01-24 07:54:33.454305: step: 1756/530, loss: 0.004301495850086212
2023-01-24 07:54:34.513917: step: 1760/530, loss: 0.0
2023-01-24 07:54:35.579609: step: 1764/530, loss: 0.006158389151096344
2023-01-24 07:54:36.653842: step: 1768/530, loss: 0.0020148418843746185
2023-01-24 07:54:37.717226: step: 1772/530, loss: 0.0007876895251683891
2023-01-24 07:54:38.777932: step: 1776/530, loss: 0.0011058927047997713
2023-01-24 07:54:39.842796: step: 1780/530, loss: 0.0018458337290212512
2023-01-24 07:54:40.892420: step: 1784/530, loss: 0.0030139549635350704
2023-01-24 07:54:41.939560: step: 1788/530, loss: 0.0011102540884166956
2023-01-24 07:54:43.002211: step: 1792/530, loss: 0.005093112587928772
2023-01-24 07:54:44.076527: step: 1796/530, loss: 0.0006039586733095348
2023-01-24 07:54:45.118360: step: 1800/530, loss: 0.0003881119773723185
2023-01-24 07:54:46.173059: step: 1804/530, loss: 0.000486546108732
2023-01-24 07:54:47.234369: step: 1808/530, loss: 0.01677919365465641
2023-01-24 07:54:48.299486: step: 1812/530, loss: 0.024995028972625732
2023-01-24 07:54:49.349623: step: 1816/530, loss: 0.006688401103019714
2023-01-24 07:54:50.401982: step: 1820/530, loss: 0.005299373529851437
2023-01-24 07:54:51.465998: step: 1824/530, loss: 0.001538599724881351
2023-01-24 07:54:52.522589: step: 1828/530, loss: 0.0022909792605787516
2023-01-24 07:54:53.583321: step: 1832/530, loss: 0.019943134859204292
2023-01-24 07:54:54.634691: step: 1836/530, loss: 0.00012144041829742491
2023-01-24 07:54:55.679097: step: 1840/530, loss: 0.0
2023-01-24 07:54:56.733971: step: 1844/530, loss: 0.0005485381698235869
2023-01-24 07:54:57.800255: step: 1848/530, loss: 0.009844658896327019
2023-01-24 07:54:58.852778: step: 1852/530, loss: 2.9308232114999555e-05
2023-01-24 07:54:59.914081: step: 1856/530, loss: 0.008227067068219185
2023-01-24 07:55:00.960660: step: 1860/530, loss: 0.003899388713762164
2023-01-24 07:55:02.017555: step: 1864/530, loss: 0.00796444807201624
2023-01-24 07:55:03.071541: step: 1868/530, loss: 0.004359161015599966
2023-01-24 07:55:04.126198: step: 1872/530, loss: 0.0009831773350015283
2023-01-24 07:55:05.199509: step: 1876/530, loss: 0.008360393345355988
2023-01-24 07:55:06.268997: step: 1880/530, loss: 0.005839694757014513
2023-01-24 07:55:07.331125: step: 1884/530, loss: 0.030147099867463112
2023-01-24 07:55:08.378628: step: 1888/530, loss: 0.0003252174938097596
2023-01-24 07:55:09.431580: step: 1892/530, loss: 0.0034150569699704647
2023-01-24 07:55:10.493605: step: 1896/530, loss: 0.08521401137113571
2023-01-24 07:55:11.542503: step: 1900/530, loss: 0.00020494101045187563
2023-01-24 07:55:12.625971: step: 1904/530, loss: 7.621472377650207e-07
2023-01-24 07:55:13.684601: step: 1908/530, loss: 0.007479064166545868
2023-01-24 07:55:14.746403: step: 1912/530, loss: 0.002421255921944976
2023-01-24 07:55:15.822255: step: 1916/530, loss: 0.0023866642732173204
2023-01-24 07:55:16.874320: step: 1920/530, loss: 0.0
2023-01-24 07:55:17.941569: step: 1924/530, loss: 2.1468096747412346e-05
2023-01-24 07:55:18.998976: step: 1928/530, loss: 0.003941888455301523
2023-01-24 07:55:20.047660: step: 1932/530, loss: 5.8215318858856335e-05
2023-01-24 07:55:21.115054: step: 1936/530, loss: 0.06962382048368454
2023-01-24 07:55:22.159773: step: 1940/530, loss: 0.005815138574689627
2023-01-24 07:55:23.225359: step: 1944/530, loss: 0.002845507813617587
2023-01-24 07:55:24.303134: step: 1948/530, loss: 0.0038012012373656034
2023-01-24 07:55:25.363293: step: 1952/530, loss: 0.00035948309232480824
2023-01-24 07:55:26.425580: step: 1956/530, loss: 0.004982306156307459
2023-01-24 07:55:27.488223: step: 1960/530, loss: 0.0037483167834579945
2023-01-24 07:55:28.542200: step: 1964/530, loss: 0.005964509677141905
2023-01-24 07:55:29.585561: step: 1968/530, loss: 0.004076770972460508
2023-01-24 07:55:30.657874: step: 1972/530, loss: 0.0019410912645980716
2023-01-24 07:55:31.715977: step: 1976/530, loss: 0.0037738399114459753
2023-01-24 07:55:32.790448: step: 1980/530, loss: 0.0007405421347357333
2023-01-24 07:55:33.862412: step: 1984/530, loss: 0.005200081970542669
2023-01-24 07:55:34.930029: step: 1988/530, loss: 0.021056078374385834
2023-01-24 07:55:35.993604: step: 1992/530, loss: 0.004166916012763977
2023-01-24 07:55:37.054294: step: 1996/530, loss: 0.00013920108904130757
2023-01-24 07:55:38.122987: step: 2000/530, loss: 2.0488516838668147e-06
2023-01-24 07:55:39.186936: step: 2004/530, loss: 0.00863782037049532
2023-01-24 07:55:40.240622: step: 2008/530, loss: 0.012423371896147728
2023-01-24 07:55:41.329053: step: 2012/530, loss: 0.0002685433137230575
2023-01-24 07:55:42.393276: step: 2016/530, loss: 0.0023049134761095047
2023-01-24 07:55:43.475827: step: 2020/530, loss: 0.0006565408548340201
2023-01-24 07:55:44.533722: step: 2024/530, loss: 0.000225957075599581
2023-01-24 07:55:45.600488: step: 2028/530, loss: 0.0017843234818428755
2023-01-24 07:55:46.651783: step: 2032/530, loss: 0.0014595558168366551
2023-01-24 07:55:47.716433: step: 2036/530, loss: 0.004431008826941252
2023-01-24 07:55:48.774653: step: 2040/530, loss: 0.0001075672116712667
2023-01-24 07:55:49.825384: step: 2044/530, loss: 0.0038190234918147326
2023-01-24 07:55:50.884925: step: 2048/530, loss: 0.0003169569536112249
2023-01-24 07:55:51.930240: step: 2052/530, loss: 0.000324446358717978
2023-01-24 07:55:53.007294: step: 2056/530, loss: 0.003834645263850689
2023-01-24 07:55:54.079389: step: 2060/530, loss: 0.0008672822150401771
2023-01-24 07:55:55.142155: step: 2064/530, loss: 0.0012764601269736886
2023-01-24 07:55:56.197636: step: 2068/530, loss: 0.001300034229643643
2023-01-24 07:55:57.254880: step: 2072/530, loss: 0.007917891256511211
2023-01-24 07:55:58.323254: step: 2076/530, loss: 0.00218352023512125
2023-01-24 07:55:59.378650: step: 2080/530, loss: 0.0020616771653294563
2023-01-24 07:56:00.422582: step: 2084/530, loss: 0.00010413958807475865
2023-01-24 07:56:01.490618: step: 2088/530, loss: 0.002087678061798215
2023-01-24 07:56:02.574329: step: 2092/530, loss: 0.009423180483281612
2023-01-24 07:56:03.626553: step: 2096/530, loss: 0.0011999638518318534
2023-01-24 07:56:04.690706: step: 2100/530, loss: 0.010037058964371681
2023-01-24 07:56:05.755257: step: 2104/530, loss: 0.004111235495656729
2023-01-24 07:56:06.820902: step: 2108/530, loss: 0.00021061539882794023
2023-01-24 07:56:07.881854: step: 2112/530, loss: 0.00044255657121539116
2023-01-24 07:56:08.953308: step: 2116/530, loss: 0.0031181317754089832
2023-01-24 07:56:10.000873: step: 2120/530, loss: 0.00498694134876132
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38435696248196255, 'r': 0.3369505060088552, 'f1': 0.3590958881024604}, 'combined': 0.2645969701807603, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3978722794735288, 'r': 0.2976291337360424, 'f1': 0.34052664632504104}, 'combined': 0.22584150637101164, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3479166666666667, 'r': 0.2807054924242424, 'f1': 0.31071802935010484}, 'combined': 0.20714535290006988, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40304020025135495, 'r': 0.29705038980463183, 'f1': 0.3420221619662892}, 'combined': 0.22321446359905187, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37272935423928305, 'r': 0.33312243993681656, 'f1': 0.3518146810555157}, 'combined': 0.25923187025143263, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39697004445209105, 'r': 0.30795251933253126, 'f1': 0.3468407214325437}, 'combined': 0.23002907949930357, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 07:58:36.119231: step: 4/530, loss: 0.0008320769411511719
2023-01-24 07:58:37.166566: step: 8/530, loss: 0.014367454685270786
2023-01-24 07:58:38.229079: step: 12/530, loss: 0.040785402059555054
2023-01-24 07:58:39.281670: step: 16/530, loss: 0.0021763211116194725
2023-01-24 07:58:40.335604: step: 20/530, loss: 0.00861972477287054
2023-01-24 07:58:41.395426: step: 24/530, loss: 0.0018987206276506186
2023-01-24 07:58:42.443180: step: 28/530, loss: 0.0013313519302755594
2023-01-24 07:58:43.491138: step: 32/530, loss: 0.0117793595418334
2023-01-24 07:58:44.542174: step: 36/530, loss: 0.0009330848697572947
2023-01-24 07:58:45.616346: step: 40/530, loss: 0.002755777444690466
2023-01-24 07:58:46.664511: step: 44/530, loss: 0.007323131896555424
2023-01-24 07:58:47.707292: step: 48/530, loss: 0.010742099024355412
2023-01-24 07:58:48.743836: step: 52/530, loss: 0.002013320568948984
2023-01-24 07:58:49.803124: step: 56/530, loss: 0.000884855689946562
2023-01-24 07:58:50.860372: step: 60/530, loss: 0.001123062102124095
2023-01-24 07:58:51.925693: step: 64/530, loss: 0.0009394078515470028
2023-01-24 07:58:52.977730: step: 68/530, loss: 0.00286126509308815
2023-01-24 07:58:54.046080: step: 72/530, loss: 0.008185154758393764
2023-01-24 07:58:55.102981: step: 76/530, loss: 0.00321989506483078
2023-01-24 07:58:56.171946: step: 80/530, loss: 0.0021773437038064003
2023-01-24 07:58:57.225915: step: 84/530, loss: 0.0010736762778833508
2023-01-24 07:58:58.277256: step: 88/530, loss: 0.000245375296799466
2023-01-24 07:58:59.329938: step: 92/530, loss: 0.0036642253398895264
2023-01-24 07:59:00.373946: step: 96/530, loss: 0.0018407822353765368
2023-01-24 07:59:01.421565: step: 100/530, loss: 0.0011522320564836264
2023-01-24 07:59:02.489884: step: 104/530, loss: 0.004422913305461407
2023-01-24 07:59:03.551175: step: 108/530, loss: 0.00038650084752589464
2023-01-24 07:59:04.618106: step: 112/530, loss: 0.000989661319181323
2023-01-24 07:59:05.679419: step: 116/530, loss: 0.006751012522727251
2023-01-24 07:59:06.755573: step: 120/530, loss: 0.004980576224625111
2023-01-24 07:59:07.799679: step: 124/530, loss: 1.8379096218268387e-05
2023-01-24 07:59:08.860300: step: 128/530, loss: 0.0003218639176338911
2023-01-24 07:59:09.928231: step: 132/530, loss: 0.0112758232280612
2023-01-24 07:59:10.992864: step: 136/530, loss: 0.009117452427744865
2023-01-24 07:59:12.046883: step: 140/530, loss: 0.0037655173800885677
2023-01-24 07:59:13.111534: step: 144/530, loss: 0.0030212050769478083
2023-01-24 07:59:14.167786: step: 148/530, loss: 0.0029100566171109676
2023-01-24 07:59:15.223911: step: 152/530, loss: 0.0013753143139183521
2023-01-24 07:59:16.278276: step: 156/530, loss: 0.00029679088038392365
2023-01-24 07:59:17.340464: step: 160/530, loss: 0.00014125104644335806
2023-01-24 07:59:18.385584: step: 164/530, loss: 0.0026432317681610584
2023-01-24 07:59:19.450366: step: 168/530, loss: 0.0011071398621425033
2023-01-24 07:59:20.504107: step: 172/530, loss: 0.001150714815594256
2023-01-24 07:59:21.573761: step: 176/530, loss: 0.0009518184815533459
2023-01-24 07:59:22.627794: step: 180/530, loss: 0.0030756117776036263
2023-01-24 07:59:23.681699: step: 184/530, loss: 0.004332979209721088
2023-01-24 07:59:24.726179: step: 188/530, loss: 0.0005897373775951564
2023-01-24 07:59:25.789703: step: 192/530, loss: 0.0009652886656112969
2023-01-24 07:59:26.842877: step: 196/530, loss: 0.003094347193837166
2023-01-24 07:59:27.892921: step: 200/530, loss: 0.0005280639161355793
2023-01-24 07:59:28.941600: step: 204/530, loss: 1.8843253201339394e-05
2023-01-24 07:59:29.991763: step: 208/530, loss: 0.0004711709334515035
2023-01-24 07:59:31.044010: step: 212/530, loss: 0.007090361788868904
2023-01-24 07:59:32.103776: step: 216/530, loss: 0.0006955088465474546
2023-01-24 07:59:33.155823: step: 220/530, loss: 0.0003505217900965363
2023-01-24 07:59:34.197398: step: 224/530, loss: 0.0009581840713508427
2023-01-24 07:59:35.264205: step: 228/530, loss: 0.00020301745098549873
2023-01-24 07:59:36.330026: step: 232/530, loss: 0.00123145233374089
2023-01-24 07:59:37.392158: step: 236/530, loss: 0.009180593304336071
2023-01-24 07:59:38.470651: step: 240/530, loss: 0.0010323997121304274
2023-01-24 07:59:39.537127: step: 244/530, loss: 0.0034350408241152763
2023-01-24 07:59:40.595871: step: 248/530, loss: 0.0056566656567156315
2023-01-24 07:59:41.657468: step: 252/530, loss: 0.003973392769694328
2023-01-24 07:59:42.713076: step: 256/530, loss: 0.004792486317455769
2023-01-24 07:59:43.767562: step: 260/530, loss: 0.000585669360589236
2023-01-24 07:59:44.815916: step: 264/530, loss: 0.0003002863086294383
2023-01-24 07:59:45.871905: step: 268/530, loss: 0.0005055919755250216
2023-01-24 07:59:46.926731: step: 272/530, loss: 0.021637700498104095
2023-01-24 07:59:47.988293: step: 276/530, loss: 0.0014909520978108048
2023-01-24 07:59:49.037114: step: 280/530, loss: 0.009958428330719471
2023-01-24 07:59:50.118798: step: 284/530, loss: 0.01677277311682701
2023-01-24 07:59:51.171608: step: 288/530, loss: 0.0002959614503197372
2023-01-24 07:59:52.258794: step: 292/530, loss: 0.021321265026926994
2023-01-24 07:59:53.322517: step: 296/530, loss: 0.0026408189442008734
2023-01-24 07:59:54.390591: step: 300/530, loss: 0.0009057041606865823
2023-01-24 07:59:55.449423: step: 304/530, loss: 0.0042593698017299175
2023-01-24 07:59:56.498889: step: 308/530, loss: 0.003941622097045183
2023-01-24 07:59:57.546722: step: 312/530, loss: 6.589168151549529e-06
2023-01-24 07:59:58.594973: step: 316/530, loss: 0.0005271020345389843
2023-01-24 07:59:59.679935: step: 320/530, loss: 0.003769570728763938
2023-01-24 08:00:00.740916: step: 324/530, loss: 0.002862769179046154
2023-01-24 08:00:01.804213: step: 328/530, loss: 0.003058553207665682
2023-01-24 08:00:02.902457: step: 332/530, loss: 0.004292203579097986
2023-01-24 08:00:03.958362: step: 336/530, loss: 0.011226531118154526
2023-01-24 08:00:05.012560: step: 340/530, loss: 0.00023230203078128397
2023-01-24 08:00:06.053948: step: 344/530, loss: 0.004742414690554142
2023-01-24 08:00:07.125545: step: 348/530, loss: 0.0006980329053476453
2023-01-24 08:00:08.178925: step: 352/530, loss: 0.001675250823609531
2023-01-24 08:00:09.220287: step: 356/530, loss: 0.0026135961525142193
2023-01-24 08:00:10.287594: step: 360/530, loss: 0.0057469625025987625
2023-01-24 08:00:11.339227: step: 364/530, loss: 0.003330593928694725
2023-01-24 08:00:12.409085: step: 368/530, loss: 0.003779633669182658
2023-01-24 08:00:13.479045: step: 372/530, loss: 0.017489172518253326
2023-01-24 08:00:14.516743: step: 376/530, loss: 0.006842587608844042
2023-01-24 08:00:15.587691: step: 380/530, loss: 0.012858384288847446
2023-01-24 08:00:16.639854: step: 384/530, loss: 0.0009603927610442042
2023-01-24 08:00:17.707893: step: 388/530, loss: 0.0038138707168400288
2023-01-24 08:00:18.775249: step: 392/530, loss: 0.0048032780177891254
2023-01-24 08:00:19.846294: step: 396/530, loss: 0.002552689053118229
2023-01-24 08:00:20.901054: step: 400/530, loss: 0.0014193045208230615
2023-01-24 08:00:21.952412: step: 404/530, loss: 0.0027619136963039637
2023-01-24 08:00:23.029565: step: 408/530, loss: 0.0024915006943047047
2023-01-24 08:00:24.088659: step: 412/530, loss: 0.00102722248993814
2023-01-24 08:00:25.166881: step: 416/530, loss: 0.0009601069032214582
2023-01-24 08:00:26.221283: step: 420/530, loss: 0.0022687669843435287
2023-01-24 08:00:27.284521: step: 424/530, loss: 0.0018105338094756007
2023-01-24 08:00:28.337281: step: 428/530, loss: 0.0033635010477155447
2023-01-24 08:00:29.402743: step: 432/530, loss: 0.0012814328074455261
2023-01-24 08:00:30.489921: step: 436/530, loss: 0.0005406891577877104
2023-01-24 08:00:31.547495: step: 440/530, loss: 0.005423763766884804
2023-01-24 08:00:32.642174: step: 444/530, loss: 0.0020923998672515154
2023-01-24 08:00:33.704591: step: 448/530, loss: 0.0006722522084601223
2023-01-24 08:00:34.768355: step: 452/530, loss: 0.02272350713610649
2023-01-24 08:00:35.838569: step: 456/530, loss: 0.0005271777044981718
2023-01-24 08:00:36.897146: step: 460/530, loss: 0.00429708743467927
2023-01-24 08:00:37.955774: step: 464/530, loss: 0.0014052659971639514
2023-01-24 08:00:39.032027: step: 468/530, loss: 0.0017484532436355948
2023-01-24 08:00:40.089981: step: 472/530, loss: 0.003103214083239436
2023-01-24 08:00:41.135327: step: 476/530, loss: 0.003538790624588728
2023-01-24 08:00:42.201220: step: 480/530, loss: 0.007891153916716576
2023-01-24 08:00:43.259176: step: 484/530, loss: 0.016561798751354218
2023-01-24 08:00:44.317789: step: 488/530, loss: 0.021601224318146706
2023-01-24 08:00:45.392465: step: 492/530, loss: 0.004168195649981499
2023-01-24 08:00:46.463522: step: 496/530, loss: 0.005666607990860939
2023-01-24 08:00:47.514650: step: 500/530, loss: 0.0035148924216628075
2023-01-24 08:00:48.554872: step: 504/530, loss: 0.00020331161795184016
2023-01-24 08:00:49.613792: step: 508/530, loss: 0.006514247972518206
2023-01-24 08:00:50.650529: step: 512/530, loss: 0.0015850355848670006
2023-01-24 08:00:51.715432: step: 516/530, loss: 0.0003407117328606546
2023-01-24 08:00:52.793760: step: 520/530, loss: 0.014483748003840446
2023-01-24 08:00:53.851465: step: 524/530, loss: 0.014640352688729763
2023-01-24 08:00:54.910280: step: 528/530, loss: 0.0002690246910788119
2023-01-24 08:00:55.964571: step: 532/530, loss: 0.006800653412938118
2023-01-24 08:00:57.042460: step: 536/530, loss: 0.0012988498201593757
2023-01-24 08:00:58.089151: step: 540/530, loss: 0.008248641155660152
2023-01-24 08:00:59.147588: step: 544/530, loss: 0.011483488604426384
2023-01-24 08:01:00.200652: step: 548/530, loss: 0.00792290735989809
2023-01-24 08:01:01.259804: step: 552/530, loss: 0.0002428980078548193
2023-01-24 08:01:02.319873: step: 556/530, loss: 0.0025394458789378405
2023-01-24 08:01:03.392530: step: 560/530, loss: 0.008252744562923908
2023-01-24 08:01:04.449261: step: 564/530, loss: 8.642394095659256e-05
2023-01-24 08:01:05.504685: step: 568/530, loss: 0.0009812781354412436
2023-01-24 08:01:06.562994: step: 572/530, loss: 0.0021326018031686544
2023-01-24 08:01:07.645834: step: 576/530, loss: 0.00280452286824584
2023-01-24 08:01:08.696388: step: 580/530, loss: 0.002680838108062744
2023-01-24 08:01:09.754547: step: 584/530, loss: 0.0009603391517885029
2023-01-24 08:01:10.819137: step: 588/530, loss: 0.0017605674220249057
2023-01-24 08:01:11.876195: step: 592/530, loss: 7.512886077165604e-05
2023-01-24 08:01:12.939924: step: 596/530, loss: 0.002198146190494299
2023-01-24 08:01:14.003837: step: 600/530, loss: 0.0003285809070803225
2023-01-24 08:01:15.060105: step: 604/530, loss: 0.002589072333648801
2023-01-24 08:01:16.110799: step: 608/530, loss: 0.019502662122249603
2023-01-24 08:01:17.179070: step: 612/530, loss: 0.0017936592921614647
2023-01-24 08:01:18.229037: step: 616/530, loss: 0.0005071019404567778
2023-01-24 08:01:19.282198: step: 620/530, loss: 0.0009245231631211936
2023-01-24 08:01:20.336656: step: 624/530, loss: 0.005336207803338766
2023-01-24 08:01:21.415616: step: 628/530, loss: 0.0006078645237721503
2023-01-24 08:01:22.496616: step: 632/530, loss: 0.006319988053292036
2023-01-24 08:01:23.542914: step: 636/530, loss: 0.0029545859433710575
2023-01-24 08:01:24.613607: step: 640/530, loss: 0.0002314333396498114
2023-01-24 08:01:25.675782: step: 644/530, loss: 0.004481207113713026
2023-01-24 08:01:26.729868: step: 648/530, loss: 0.00017579400446265936
2023-01-24 08:01:27.792925: step: 652/530, loss: 0.0053586214780807495
2023-01-24 08:01:28.862611: step: 656/530, loss: 0.0017509327735751867
2023-01-24 08:01:29.918271: step: 660/530, loss: 0.0017079696990549564
2023-01-24 08:01:30.977632: step: 664/530, loss: 0.0013236228842288256
2023-01-24 08:01:32.037581: step: 668/530, loss: 0.002056313445791602
2023-01-24 08:01:33.087400: step: 672/530, loss: 0.0038687021005898714
2023-01-24 08:01:34.157383: step: 676/530, loss: 0.005694231018424034
2023-01-24 08:01:35.222773: step: 680/530, loss: 0.005716739688068628
2023-01-24 08:01:36.305520: step: 684/530, loss: 0.002786272671073675
2023-01-24 08:01:37.356269: step: 688/530, loss: 0.0024394888896495104
2023-01-24 08:01:38.404836: step: 692/530, loss: 0.004570594523102045
2023-01-24 08:01:39.487461: step: 696/530, loss: 0.007836435921490192
2023-01-24 08:01:40.545061: step: 700/530, loss: 0.00041332971886731684
2023-01-24 08:01:41.607842: step: 704/530, loss: 0.0037523575592786074
2023-01-24 08:01:42.669765: step: 708/530, loss: 0.008568313904106617
2023-01-24 08:01:43.723147: step: 712/530, loss: 0.002507713856175542
2023-01-24 08:01:44.785262: step: 716/530, loss: 6.599714834010229e-05
2023-01-24 08:01:45.836302: step: 720/530, loss: 0.0016238060779869556
2023-01-24 08:01:46.898513: step: 724/530, loss: 0.0023533115163445473
2023-01-24 08:01:47.969034: step: 728/530, loss: 0.0006747259176336229
2023-01-24 08:01:49.033369: step: 732/530, loss: 0.0007141977548599243
2023-01-24 08:01:50.080988: step: 736/530, loss: 0.003219838486984372
2023-01-24 08:01:51.136616: step: 740/530, loss: 0.0015786078292876482
2023-01-24 08:01:52.201965: step: 744/530, loss: 0.0037862283643335104
2023-01-24 08:01:53.264476: step: 748/530, loss: 0.0016279892297461629
2023-01-24 08:01:54.312749: step: 752/530, loss: 0.0014700100291520357
2023-01-24 08:01:55.370138: step: 756/530, loss: 0.006723557133227587
2023-01-24 08:01:56.429816: step: 760/530, loss: 0.007349103689193726
2023-01-24 08:01:57.485951: step: 764/530, loss: 0.0006401078426279128
2023-01-24 08:01:58.538622: step: 768/530, loss: 0.008178593590855598
2023-01-24 08:01:59.611267: step: 772/530, loss: 0.0009549085516482592
2023-01-24 08:02:00.652519: step: 776/530, loss: 5.3505613323068246e-05
2023-01-24 08:02:01.710130: step: 780/530, loss: 8.332834113389254e-06
2023-01-24 08:02:02.782209: step: 784/530, loss: 0.0004199588729534298
2023-01-24 08:02:03.845265: step: 788/530, loss: 0.005242860410362482
2023-01-24 08:02:04.895023: step: 792/530, loss: 1.751254967530258e-05
2023-01-24 08:02:05.951630: step: 796/530, loss: 0.0038681384176015854
2023-01-24 08:02:07.013841: step: 800/530, loss: 0.0035651838406920433
2023-01-24 08:02:08.077714: step: 804/530, loss: 0.005050069186836481
2023-01-24 08:02:09.134100: step: 808/530, loss: 0.004731187131255865
2023-01-24 08:02:10.201563: step: 812/530, loss: 0.003956017084419727
2023-01-24 08:02:11.253065: step: 816/530, loss: 0.013566078618168831
2023-01-24 08:02:12.303951: step: 820/530, loss: 0.003332513850182295
2023-01-24 08:02:13.375640: step: 824/530, loss: 0.0077276979573071
2023-01-24 08:02:14.431634: step: 828/530, loss: 0.0010049307020381093
2023-01-24 08:02:15.489329: step: 832/530, loss: 0.00036363702383823693
2023-01-24 08:02:16.559663: step: 836/530, loss: 0.0028144861571490765
2023-01-24 08:02:17.620085: step: 840/530, loss: 0.004796306602656841
2023-01-24 08:02:18.682768: step: 844/530, loss: 0.009523033164441586
2023-01-24 08:02:19.746584: step: 848/530, loss: 2.0529869289021008e-05
2023-01-24 08:02:20.800475: step: 852/530, loss: 0.0025669445749372244
2023-01-24 08:02:21.850746: step: 856/530, loss: 5.4223983170231804e-05
2023-01-24 08:02:22.892879: step: 860/530, loss: 0.008463486097753048
2023-01-24 08:02:23.952356: step: 864/530, loss: 0.0005861074314452708
2023-01-24 08:02:25.007283: step: 868/530, loss: 0.022007029503583908
2023-01-24 08:02:26.063995: step: 872/530, loss: 0.03023066371679306
2023-01-24 08:02:27.112410: step: 876/530, loss: 0.0008784490055404603
2023-01-24 08:02:28.176293: step: 880/530, loss: 0.01051307562738657
2023-01-24 08:02:29.236234: step: 884/530, loss: 0.005714877508580685
2023-01-24 08:02:30.305720: step: 888/530, loss: 0.006544552743434906
2023-01-24 08:02:31.356392: step: 892/530, loss: 0.0050248634070158005
2023-01-24 08:02:32.413966: step: 896/530, loss: 0.010159206576645374
2023-01-24 08:02:33.476974: step: 900/530, loss: 0.0010611327597871423
2023-01-24 08:02:34.551386: step: 904/530, loss: 0.005536375101655722
2023-01-24 08:02:35.604043: step: 908/530, loss: 0.0040043070912361145
2023-01-24 08:02:36.663953: step: 912/530, loss: 0.002809088909998536
2023-01-24 08:02:37.729926: step: 916/530, loss: 0.003653450170531869
2023-01-24 08:02:38.787539: step: 920/530, loss: 0.015358002856373787
2023-01-24 08:02:39.853473: step: 924/530, loss: 0.008732953108847141
2023-01-24 08:02:40.907747: step: 928/530, loss: 0.0020503837149590254
2023-01-24 08:02:41.976211: step: 932/530, loss: 0.0007922257063910365
2023-01-24 08:02:43.033825: step: 936/530, loss: 3.98771844629664e-05
2023-01-24 08:02:44.099879: step: 940/530, loss: 0.009864992462098598
2023-01-24 08:02:45.158621: step: 944/530, loss: 0.008958365768194199
2023-01-24 08:02:46.228120: step: 948/530, loss: 0.0018235777970403433
2023-01-24 08:02:47.292050: step: 952/530, loss: 7.47388185118325e-05
2023-01-24 08:02:48.361173: step: 956/530, loss: 0.0055508483201265335
2023-01-24 08:02:49.426504: step: 960/530, loss: 0.000520433415658772
2023-01-24 08:02:50.502844: step: 964/530, loss: 0.002398409880697727
2023-01-24 08:02:51.559917: step: 968/530, loss: 0.003401942318305373
2023-01-24 08:02:52.618309: step: 972/530, loss: 0.004163446836173534
2023-01-24 08:02:53.663032: step: 976/530, loss: 0.00033889958285726607
2023-01-24 08:02:54.729350: step: 980/530, loss: 0.013147062622010708
2023-01-24 08:02:55.812989: step: 984/530, loss: 0.0016859377501532435
2023-01-24 08:02:56.867678: step: 988/530, loss: 0.004161641001701355
2023-01-24 08:02:57.927565: step: 992/530, loss: 0.0024572047404944897
2023-01-24 08:02:58.970006: step: 996/530, loss: 0.0002782403025776148
2023-01-24 08:03:00.026565: step: 1000/530, loss: 0.005075226072221994
2023-01-24 08:03:01.101740: step: 1004/530, loss: 0.004046840593218803
2023-01-24 08:03:02.153672: step: 1008/530, loss: 0.01393798552453518
2023-01-24 08:03:03.220254: step: 1012/530, loss: 0.0027777086943387985
2023-01-24 08:03:04.287626: step: 1016/530, loss: 0.0016684230649843812
2023-01-24 08:03:05.342704: step: 1020/530, loss: 0.008456406183540821
2023-01-24 08:03:06.411844: step: 1024/530, loss: 0.014498726464807987
2023-01-24 08:03:07.466999: step: 1028/530, loss: 4.467165854293853e-05
2023-01-24 08:03:08.523485: step: 1032/530, loss: 0.004397765267640352
2023-01-24 08:03:09.574765: step: 1036/530, loss: 0.011192373000085354
2023-01-24 08:03:10.638817: step: 1040/530, loss: 0.0002414122864138335
2023-01-24 08:03:11.707717: step: 1044/530, loss: 0.009831283241510391
2023-01-24 08:03:12.763701: step: 1048/530, loss: 0.0004700064309872687
2023-01-24 08:03:13.833650: step: 1052/530, loss: 0.001353634288534522
2023-01-24 08:03:14.893334: step: 1056/530, loss: 0.002589730080217123
2023-01-24 08:03:15.945338: step: 1060/530, loss: 0.001597752794623375
2023-01-24 08:03:16.996512: step: 1064/530, loss: 0.0028609249275177717
2023-01-24 08:03:18.055973: step: 1068/530, loss: 0.0007374901324510574
2023-01-24 08:03:19.126489: step: 1072/530, loss: 0.007631149608641863
2023-01-24 08:03:20.198390: step: 1076/530, loss: 0.005985576659440994
2023-01-24 08:03:21.259678: step: 1080/530, loss: 0.00020712753757834435
2023-01-24 08:03:22.318939: step: 1084/530, loss: 0.0009111129911616445
2023-01-24 08:03:23.394679: step: 1088/530, loss: 0.019185533747076988
2023-01-24 08:03:24.457173: step: 1092/530, loss: 0.0016105037648230791
2023-01-24 08:03:25.529791: step: 1096/530, loss: 0.00957140140235424
2023-01-24 08:03:26.592457: step: 1100/530, loss: 0.0010641703847795725
2023-01-24 08:03:27.655176: step: 1104/530, loss: 0.008787252940237522
2023-01-24 08:03:28.728293: step: 1108/530, loss: 0.0019633693154901266
2023-01-24 08:03:29.773549: step: 1112/530, loss: 0.0007620689575560391
2023-01-24 08:03:30.833020: step: 1116/530, loss: 0.005614517722278833
2023-01-24 08:03:31.883440: step: 1120/530, loss: 0.0010899496264755726
2023-01-24 08:03:32.923471: step: 1124/530, loss: 0.0006819992559030652
2023-01-24 08:03:33.984493: step: 1128/530, loss: 0.0002976080577354878
2023-01-24 08:03:35.081002: step: 1132/530, loss: 0.0024264827370643616
2023-01-24 08:03:36.141725: step: 1136/530, loss: 0.0004275397805031389
2023-01-24 08:03:37.201556: step: 1140/530, loss: 0.0010892460122704506
2023-01-24 08:03:38.263460: step: 1144/530, loss: 0.00582385016605258
2023-01-24 08:03:39.348361: step: 1148/530, loss: 1.1483742127893493e-05
2023-01-24 08:03:40.404482: step: 1152/530, loss: 0.019962813705205917
2023-01-24 08:03:41.457734: step: 1156/530, loss: 3.742724220501259e-05
2023-01-24 08:03:42.515236: step: 1160/530, loss: 2.1465788449859247e-05
2023-01-24 08:03:43.577679: step: 1164/530, loss: 0.0036628860980272293
2023-01-24 08:03:44.642383: step: 1168/530, loss: 0.0022252164781093597
2023-01-24 08:03:45.697974: step: 1172/530, loss: 0.00573334563523531
2023-01-24 08:03:46.758496: step: 1176/530, loss: 0.013025280088186264
2023-01-24 08:03:47.821168: step: 1180/530, loss: 0.006561050191521645
2023-01-24 08:03:48.867256: step: 1184/530, loss: 0.0005698238383047283
2023-01-24 08:03:49.938792: step: 1188/530, loss: 0.004795927554368973
2023-01-24 08:03:50.997510: step: 1192/530, loss: 0.003382658353075385
2023-01-24 08:03:52.050945: step: 1196/530, loss: 0.0014618497807532549
2023-01-24 08:03:53.101537: step: 1200/530, loss: 0.00024218717589974403
2023-01-24 08:03:54.153726: step: 1204/530, loss: 0.01129582617431879
2023-01-24 08:03:55.214895: step: 1208/530, loss: 0.006110831629484892
2023-01-24 08:03:56.279833: step: 1212/530, loss: 0.0067613385617733
2023-01-24 08:03:57.329223: step: 1216/530, loss: 6.554491392307682e-06
2023-01-24 08:03:58.387871: step: 1220/530, loss: 0.0007601960678584874
2023-01-24 08:03:59.452138: step: 1224/530, loss: 0.0058824834413826466
2023-01-24 08:04:00.510817: step: 1228/530, loss: 0.011657321825623512
2023-01-24 08:04:01.589204: step: 1232/530, loss: 0.012146913446485996
2023-01-24 08:04:02.665141: step: 1236/530, loss: 0.002405834849923849
2023-01-24 08:04:03.730637: step: 1240/530, loss: 0.004847335163503885
2023-01-24 08:04:04.799302: step: 1244/530, loss: 0.008989602327346802
2023-01-24 08:04:05.870786: step: 1248/530, loss: 0.012629348784685135
2023-01-24 08:04:06.922323: step: 1252/530, loss: 0.0033187069930136204
2023-01-24 08:04:07.970976: step: 1256/530, loss: 0.0035006855614483356
2023-01-24 08:04:09.038293: step: 1260/530, loss: 0.003410729579627514
2023-01-24 08:04:10.090100: step: 1264/530, loss: 0.00025031305267475545
2023-01-24 08:04:11.157929: step: 1268/530, loss: 0.0013060449855402112
2023-01-24 08:04:12.229654: step: 1272/530, loss: 0.005291915498673916
2023-01-24 08:04:13.292205: step: 1276/530, loss: 0.006256693508476019
2023-01-24 08:04:14.342374: step: 1280/530, loss: 0.008116258308291435
2023-01-24 08:04:15.404209: step: 1284/530, loss: 0.0034394909162074327
2023-01-24 08:04:16.454591: step: 1288/530, loss: 0.0008718370227143168
2023-01-24 08:04:17.514662: step: 1292/530, loss: 0.0017200798029080033
2023-01-24 08:04:18.577937: step: 1296/530, loss: 0.0033651867415755987
2023-01-24 08:04:19.639216: step: 1300/530, loss: 0.00204497785307467
2023-01-24 08:04:20.712138: step: 1304/530, loss: 0.008543741889297962
2023-01-24 08:04:21.757119: step: 1308/530, loss: 0.018549108877778053
2023-01-24 08:04:22.807958: step: 1312/530, loss: 0.007454019971191883
2023-01-24 08:04:23.867034: step: 1316/530, loss: 0.007118787616491318
2023-01-24 08:04:24.925413: step: 1320/530, loss: 0.004104725085198879
2023-01-24 08:04:25.971343: step: 1324/530, loss: 0.004213666543364525
2023-01-24 08:04:27.030243: step: 1328/530, loss: 0.007506143767386675
2023-01-24 08:04:28.090747: step: 1332/530, loss: 0.005709733348339796
2023-01-24 08:04:29.144824: step: 1336/530, loss: 0.0014935473445802927
2023-01-24 08:04:30.216241: step: 1340/530, loss: 0.0021362542174756527
2023-01-24 08:04:31.266960: step: 1344/530, loss: 0.03108602575957775
2023-01-24 08:04:32.332287: step: 1348/530, loss: 0.004666692577302456
2023-01-24 08:04:33.390712: step: 1352/530, loss: 0.00016875712026376277
2023-01-24 08:04:34.479934: step: 1356/530, loss: 0.000258055777521804
2023-01-24 08:04:35.535891: step: 1360/530, loss: 0.004876892548054457
2023-01-24 08:04:36.589380: step: 1364/530, loss: 0.009992648847401142
2023-01-24 08:04:37.629218: step: 1368/530, loss: 0.013313684612512589
2023-01-24 08:04:38.701065: step: 1372/530, loss: 0.007920022122561932
2023-01-24 08:04:39.777677: step: 1376/530, loss: 0.007979034446179867
2023-01-24 08:04:40.841203: step: 1380/530, loss: 0.003216430777683854
2023-01-24 08:04:41.889105: step: 1384/530, loss: 7.377401288977126e-06
2023-01-24 08:04:42.945612: step: 1388/530, loss: 0.002688719192519784
2023-01-24 08:04:44.005494: step: 1392/530, loss: 0.0019228315213695168
2023-01-24 08:04:45.058251: step: 1396/530, loss: 0.0019534912426024675
2023-01-24 08:04:46.103766: step: 1400/530, loss: 0.0034197440836578608
2023-01-24 08:04:47.149033: step: 1404/530, loss: 0.0047003235667943954
2023-01-24 08:04:48.190020: step: 1408/530, loss: 0.005180078558623791
2023-01-24 08:04:49.261932: step: 1412/530, loss: 0.0019711009226739407
2023-01-24 08:04:50.315983: step: 1416/530, loss: 0.0009574324358254671
2023-01-24 08:04:51.364449: step: 1420/530, loss: 0.004306775517761707
2023-01-24 08:04:52.427289: step: 1424/530, loss: 0.007848543114960194
2023-01-24 08:04:53.486720: step: 1428/530, loss: 0.0049766600131988525
2023-01-24 08:04:54.560527: step: 1432/530, loss: 0.00013813500117976218
2023-01-24 08:04:55.616595: step: 1436/530, loss: 0.009219067171216011
2023-01-24 08:04:56.664747: step: 1440/530, loss: 0.007901976816356182
2023-01-24 08:04:57.739007: step: 1444/530, loss: 0.0039823222905397415
2023-01-24 08:04:58.783543: step: 1448/530, loss: 3.9467883539145987e-07
2023-01-24 08:04:59.847584: step: 1452/530, loss: 0.0038937460631132126
2023-01-24 08:05:00.917956: step: 1456/530, loss: 0.0035226172767579556
2023-01-24 08:05:01.974484: step: 1460/530, loss: 0.0019560500513762236
2023-01-24 08:05:03.047341: step: 1464/530, loss: 0.0016298429109156132
2023-01-24 08:05:04.108921: step: 1468/530, loss: 0.00813937745988369
2023-01-24 08:05:05.164783: step: 1472/530, loss: 0.003750380128622055
2023-01-24 08:05:06.222369: step: 1476/530, loss: 0.0020555732771754265
2023-01-24 08:05:07.272721: step: 1480/530, loss: 0.003399333916604519
2023-01-24 08:05:08.319799: step: 1484/530, loss: 0.0015278421342372894
2023-01-24 08:05:09.374766: step: 1488/530, loss: 4.8100246203830466e-06
2023-01-24 08:05:10.431384: step: 1492/530, loss: 0.003036718349903822
2023-01-24 08:05:11.502295: step: 1496/530, loss: 0.00015581339539494365
2023-01-24 08:05:12.567435: step: 1500/530, loss: 0.015179021283984184
2023-01-24 08:05:13.612799: step: 1504/530, loss: 0.005659155081957579
2023-01-24 08:05:14.655672: step: 1508/530, loss: 0.002290590899065137
2023-01-24 08:05:15.710885: step: 1512/530, loss: 1.9928136680391617e-05
2023-01-24 08:05:16.774988: step: 1516/530, loss: 0.006302024703472853
2023-01-24 08:05:17.840734: step: 1520/530, loss: 0.002138543175533414
2023-01-24 08:05:18.904255: step: 1524/530, loss: 0.0023551583290100098
2023-01-24 08:05:19.969619: step: 1528/530, loss: 0.0051754252053797245
2023-01-24 08:05:21.025844: step: 1532/530, loss: 0.019789498299360275
2023-01-24 08:05:22.102622: step: 1536/530, loss: 0.0015414366498589516
2023-01-24 08:05:23.156802: step: 1540/530, loss: 0.0195549838244915
2023-01-24 08:05:24.215449: step: 1544/530, loss: 0.0013208319433033466
2023-01-24 08:05:25.272715: step: 1548/530, loss: 4.4737938878824934e-05
2023-01-24 08:05:26.339011: step: 1552/530, loss: 0.0003518607118166983
2023-01-24 08:05:27.402063: step: 1556/530, loss: 7.921305041236337e-06
2023-01-24 08:05:28.464333: step: 1560/530, loss: 0.0020726770162582397
2023-01-24 08:05:29.514478: step: 1564/530, loss: 2.9866330805816688e-05
2023-01-24 08:05:30.586939: step: 1568/530, loss: 0.008643691428005695
2023-01-24 08:05:31.658260: step: 1572/530, loss: 0.005970974452793598
2023-01-24 08:05:32.719296: step: 1576/530, loss: 0.00368315982632339
2023-01-24 08:05:33.775084: step: 1580/530, loss: 2.786415279842913e-05
2023-01-24 08:05:34.833522: step: 1584/530, loss: 0.0016321302391588688
2023-01-24 08:05:35.903837: step: 1588/530, loss: 0.006393588148057461
2023-01-24 08:05:36.962664: step: 1592/530, loss: 0.0043124244548380375
2023-01-24 08:05:38.012893: step: 1596/530, loss: 0.005268516950309277
2023-01-24 08:05:39.072094: step: 1600/530, loss: 0.0024041703436523676
2023-01-24 08:05:40.116133: step: 1604/530, loss: 0.0007791827665641904
2023-01-24 08:05:41.164905: step: 1608/530, loss: 0.0031291747000068426
2023-01-24 08:05:42.240449: step: 1612/530, loss: 0.0008868605364114046
2023-01-24 08:05:43.312054: step: 1616/530, loss: 0.0037790548522025347
2023-01-24 08:05:44.382298: step: 1620/530, loss: 0.0010254508815705776
2023-01-24 08:05:45.436261: step: 1624/530, loss: 8.481103577651083e-05
2023-01-24 08:05:46.487435: step: 1628/530, loss: 0.0008550605271011591
2023-01-24 08:05:47.557597: step: 1632/530, loss: 0.0038089745212346315
2023-01-24 08:05:48.619749: step: 1636/530, loss: 0.0059053897857666016
2023-01-24 08:05:49.670479: step: 1640/530, loss: 0.0004412377020344138
2023-01-24 08:05:50.736667: step: 1644/530, loss: 0.008484939113259315
2023-01-24 08:05:51.799315: step: 1648/530, loss: 0.0021386367734521627
2023-01-24 08:05:52.867497: step: 1652/530, loss: 0.0016081653302535415
2023-01-24 08:05:53.936020: step: 1656/530, loss: 0.006513381842523813
2023-01-24 08:05:55.000593: step: 1660/530, loss: 0.001056722947396338
2023-01-24 08:05:56.058773: step: 1664/530, loss: 0.028058689087629318
2023-01-24 08:05:57.115976: step: 1668/530, loss: 0.0004959757789038122
2023-01-24 08:05:58.177785: step: 1672/530, loss: 0.003795412601903081
2023-01-24 08:05:59.257747: step: 1676/530, loss: 0.009061677381396294
2023-01-24 08:06:00.348269: step: 1680/530, loss: 0.0026089122984558344
2023-01-24 08:06:01.403951: step: 1684/530, loss: 0.0057379938662052155
2023-01-24 08:06:02.459536: step: 1688/530, loss: 0.008395579643547535
2023-01-24 08:06:03.508317: step: 1692/530, loss: 0.0003318342787679285
2023-01-24 08:06:04.550203: step: 1696/530, loss: 0.0010075566824525595
2023-01-24 08:06:05.605854: step: 1700/530, loss: 0.008269023150205612
2023-01-24 08:06:06.666762: step: 1704/530, loss: 0.004361629486083984
2023-01-24 08:06:07.738659: step: 1708/530, loss: 0.007040684577077627
2023-01-24 08:06:08.775113: step: 1712/530, loss: 0.00014054319763090461
2023-01-24 08:06:09.824448: step: 1716/530, loss: 0.00010745009785750881
2023-01-24 08:06:10.874505: step: 1720/530, loss: 0.0018832228379324079
2023-01-24 08:06:11.947929: step: 1724/530, loss: 0.0012280558003112674
2023-01-24 08:06:13.018047: step: 1728/530, loss: 0.001697151456028223
2023-01-24 08:06:14.070263: step: 1732/530, loss: 0.0002664512721821666
2023-01-24 08:06:15.135105: step: 1736/530, loss: 0.003983442671597004
2023-01-24 08:06:16.194493: step: 1740/530, loss: 0.0023063533008098602
2023-01-24 08:06:17.246419: step: 1744/530, loss: 0.003796427743509412
2023-01-24 08:06:18.309796: step: 1748/530, loss: 0.00020887312712147832
2023-01-24 08:06:19.367931: step: 1752/530, loss: 0.0011428105644881725
2023-01-24 08:06:20.435835: step: 1756/530, loss: 0.00014010202721692622
2023-01-24 08:06:21.488807: step: 1760/530, loss: 0.0007599526434205472
2023-01-24 08:06:22.554594: step: 1764/530, loss: 0.0029602961149066687
2023-01-24 08:06:23.591597: step: 1768/530, loss: 0.00019839184824377298
2023-01-24 08:06:24.665587: step: 1772/530, loss: 0.006114319432526827
2023-01-24 08:06:25.730101: step: 1776/530, loss: 0.003739685984328389
2023-01-24 08:06:26.774362: step: 1780/530, loss: 0.0027159047313034534
2023-01-24 08:06:27.819399: step: 1784/530, loss: 9.57014417508617e-05
2023-01-24 08:06:28.872242: step: 1788/530, loss: 0.010722307488322258
2023-01-24 08:06:29.943840: step: 1792/530, loss: 0.005990995094180107
2023-01-24 08:06:31.024240: step: 1796/530, loss: 0.0002609161310829222
2023-01-24 08:06:32.099666: step: 1800/530, loss: 0.006569515448063612
2023-01-24 08:06:33.151687: step: 1804/530, loss: 0.0033165786880999804
2023-01-24 08:06:34.208433: step: 1808/530, loss: 0.0032061832025647163
2023-01-24 08:06:35.265264: step: 1812/530, loss: 0.014142590574920177
2023-01-24 08:06:36.322664: step: 1816/530, loss: 0.0018370056059211493
2023-01-24 08:06:37.359649: step: 1820/530, loss: 0.0022949185222387314
2023-01-24 08:06:38.412825: step: 1824/530, loss: 0.003224811516702175
2023-01-24 08:06:39.455900: step: 1828/530, loss: 0.006816777400672436
2023-01-24 08:06:40.494313: step: 1832/530, loss: 0.004744057077914476
2023-01-24 08:06:41.543990: step: 1836/530, loss: 0.0011790888383984566
2023-01-24 08:06:42.628302: step: 1840/530, loss: 7.049964915495366e-05
2023-01-24 08:06:43.698675: step: 1844/530, loss: 0.011590033769607544
2023-01-24 08:06:44.747769: step: 1848/530, loss: 0.002682075835764408
2023-01-24 08:06:45.816094: step: 1852/530, loss: 0.004180378746241331
2023-01-24 08:06:46.875022: step: 1856/530, loss: 0.0019671451300382614
2023-01-24 08:06:47.932453: step: 1860/530, loss: 0.0045006959699094296
2023-01-24 08:06:48.996491: step: 1864/530, loss: 3.1965690141078085e-05
2023-01-24 08:06:50.067382: step: 1868/530, loss: 0.003039903938770294
2023-01-24 08:06:51.133350: step: 1872/530, loss: 0.012033623643219471
2023-01-24 08:06:52.172236: step: 1876/530, loss: 0.0006262253155000508
2023-01-24 08:06:53.255695: step: 1880/530, loss: 0.002116111572831869
2023-01-24 08:06:54.302643: step: 1884/530, loss: 0.006007688120007515
2023-01-24 08:06:55.363747: step: 1888/530, loss: 0.0028912299312651157
2023-01-24 08:06:56.429848: step: 1892/530, loss: 0.0011746311793103814
2023-01-24 08:06:57.481382: step: 1896/530, loss: 0.0
2023-01-24 08:06:58.536246: step: 1900/530, loss: 0.0005869127344340086
2023-01-24 08:06:59.594744: step: 1904/530, loss: 0.0012781622353941202
2023-01-24 08:07:00.653078: step: 1908/530, loss: 0.0012501388555392623
2023-01-24 08:07:01.711527: step: 1912/530, loss: 0.0043746731244027615
2023-01-24 08:07:02.802460: step: 1916/530, loss: 0.00043803712469525635
2023-01-24 08:07:03.852365: step: 1920/530, loss: 0.0075974599458277225
2023-01-24 08:07:04.920258: step: 1924/530, loss: 0.010968511924147606
2023-01-24 08:07:05.984776: step: 1928/530, loss: 0.004631384275853634
2023-01-24 08:07:07.038947: step: 1932/530, loss: 0.009578884579241276
2023-01-24 08:07:08.082918: step: 1936/530, loss: 0.005059940740466118
2023-01-24 08:07:09.150993: step: 1940/530, loss: 0.00046195185859687626
2023-01-24 08:07:10.203743: step: 1944/530, loss: 0.002232220722362399
2023-01-24 08:07:11.291251: step: 1948/530, loss: 0.008636283688247204
2023-01-24 08:07:12.354291: step: 1952/530, loss: 0.0013060978380963206
2023-01-24 08:07:13.411792: step: 1956/530, loss: 0.0018417044775560498
2023-01-24 08:07:14.485312: step: 1960/530, loss: 0.0022587471175938845
2023-01-24 08:07:15.564617: step: 1964/530, loss: 0.0011911691399291158
2023-01-24 08:07:16.636632: step: 1968/530, loss: 0.0004273304366506636
2023-01-24 08:07:17.696640: step: 1972/530, loss: 0.001487808651290834
2023-01-24 08:07:18.760180: step: 1976/530, loss: 0.0051035829819738865
2023-01-24 08:07:19.813548: step: 1980/530, loss: 0.00016551661246921867
2023-01-24 08:07:20.868352: step: 1984/530, loss: 0.002814291976392269
2023-01-24 08:07:21.926747: step: 1988/530, loss: 0.0002734197478275746
2023-01-24 08:07:22.991535: step: 1992/530, loss: 0.0007374505512416363
2023-01-24 08:07:24.063389: step: 1996/530, loss: 0.012616774998605251
2023-01-24 08:07:25.114300: step: 2000/530, loss: 0.0017067051958292723
2023-01-24 08:07:26.164401: step: 2004/530, loss: 0.00023139607219491154
2023-01-24 08:07:27.222834: step: 2008/530, loss: 0.012642091140151024
2023-01-24 08:07:28.285336: step: 2012/530, loss: 0.0031683321576565504
2023-01-24 08:07:29.356839: step: 2016/530, loss: 0.0006153160938993096
2023-01-24 08:07:30.428815: step: 2020/530, loss: 0.014677880331873894
2023-01-24 08:07:31.485707: step: 2024/530, loss: 0.00584376510232687
2023-01-24 08:07:32.558684: step: 2028/530, loss: 0.0015228864504024386
2023-01-24 08:07:33.617498: step: 2032/530, loss: 0.0009278134675696492
2023-01-24 08:07:34.670196: step: 2036/530, loss: 0.0002502513234503567
2023-01-24 08:07:35.746450: step: 2040/530, loss: 0.0019562600646167994
2023-01-24 08:07:36.815239: step: 2044/530, loss: 0.0008782261284068227
2023-01-24 08:07:37.888394: step: 2048/530, loss: 1.352880644844845e-05
2023-01-24 08:07:38.942916: step: 2052/530, loss: 9.31391041376628e-05
2023-01-24 08:07:39.999126: step: 2056/530, loss: 0.00023792771389707923
2023-01-24 08:07:41.058882: step: 2060/530, loss: 1.8051039660349488e-05
2023-01-24 08:07:42.114918: step: 2064/530, loss: 0.009793025441467762
2023-01-24 08:07:43.165240: step: 2068/530, loss: 0.005851043853908777
2023-01-24 08:07:44.235703: step: 2072/530, loss: 0.0022626316640526056
2023-01-24 08:07:45.285198: step: 2076/530, loss: 0.002183223608881235
2023-01-24 08:07:46.357294: step: 2080/530, loss: 0.006486327853053808
2023-01-24 08:07:47.418157: step: 2084/530, loss: 0.0006909652147442102
2023-01-24 08:07:48.489484: step: 2088/530, loss: 2.8288905014051124e-06
2023-01-24 08:07:49.539471: step: 2092/530, loss: 0.0009959451854228973
2023-01-24 08:07:50.617431: step: 2096/530, loss: 0.006946542765945196
2023-01-24 08:07:51.679461: step: 2100/530, loss: 0.0064200120978057384
2023-01-24 08:07:52.745230: step: 2104/530, loss: 1.0432649105496239e-05
2023-01-24 08:07:53.793846: step: 2108/530, loss: 0.0073416028171777725
2023-01-24 08:07:54.825397: step: 2112/530, loss: 0.0038483100943267345
2023-01-24 08:07:55.879551: step: 2116/530, loss: 0.006809014827013016
2023-01-24 08:07:56.931768: step: 2120/530, loss: 0.001411612844094634
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.386620406888845, 'r': 0.33820115289517566, 'f1': 0.3607935376027481}, 'combined': 0.26584786981255126, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39764896132079464, 'r': 0.29849493460184323, 'f1': 0.34101053359557765}, 'combined': 0.22616242642608256, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34697058823529414, 'r': 0.2792850378787879, 'f1': 0.3094700944386149}, 'combined': 0.2063133962924099, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3988761716793377, 'r': 0.2946714970710678, 'f1': 0.33894552299915864}, 'combined': 0.22120655185208246, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3716163670497213, 'r': 0.3314225664390304, 'f1': 0.3503704965162869}, 'combined': 0.2581677342751587, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39842620670642226, 'r': 0.3101170214970334, 'f1': 0.34876841268653713}, 'combined': 0.23130754831024222, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:10:22.469607: step: 4/530, loss: 0.002581825014203787
2023-01-24 08:10:23.526333: step: 8/530, loss: 0.006619778927415609
2023-01-24 08:10:24.566112: step: 12/530, loss: 0.0005360495997592807
2023-01-24 08:10:25.629508: step: 16/530, loss: 0.0016956243198364973
2023-01-24 08:10:26.700941: step: 20/530, loss: 0.006960383616387844
2023-01-24 08:10:27.749460: step: 24/530, loss: 0.0015290328301489353
2023-01-24 08:10:28.835902: step: 28/530, loss: 0.003123462898656726
2023-01-24 08:10:29.887961: step: 32/530, loss: 0.0022524131927639246
2023-01-24 08:10:30.948059: step: 36/530, loss: 0.00020455248886719346
2023-01-24 08:10:32.007433: step: 40/530, loss: 0.0036411837209016085
2023-01-24 08:10:33.059571: step: 44/530, loss: 3.546790321706794e-05
2023-01-24 08:10:34.124725: step: 48/530, loss: 0.001803272869437933
2023-01-24 08:10:35.177353: step: 52/530, loss: 0.0009551815455779433
2023-01-24 08:10:36.240767: step: 56/530, loss: 0.00025073063443414867
2023-01-24 08:10:37.288941: step: 60/530, loss: 0.004440452437847853
2023-01-24 08:10:38.355932: step: 64/530, loss: 0.013381106778979301
2023-01-24 08:10:39.427991: step: 68/530, loss: 0.0010746110929176211
2023-01-24 08:10:40.491149: step: 72/530, loss: 0.003233750117942691
2023-01-24 08:10:41.553375: step: 76/530, loss: 0.001029081642627716
2023-01-24 08:10:42.598572: step: 80/530, loss: 0.0025157034397125244
2023-01-24 08:10:43.665629: step: 84/530, loss: 0.005530400667339563
2023-01-24 08:10:44.723109: step: 88/530, loss: 0.01063416339457035
2023-01-24 08:10:45.784977: step: 92/530, loss: 0.00411126296967268
2023-01-24 08:10:46.855433: step: 96/530, loss: 0.0006830185302533209
2023-01-24 08:10:47.919765: step: 100/530, loss: 0.0022188322618603706
2023-01-24 08:10:48.987907: step: 104/530, loss: 1.4419346371141728e-05
2023-01-24 08:10:50.043504: step: 108/530, loss: 0.0030531820375472307
2023-01-24 08:10:51.102253: step: 112/530, loss: 4.8055200750241056e-05
2023-01-24 08:10:52.156233: step: 116/530, loss: 0.0029897962231189013
2023-01-24 08:10:53.215576: step: 120/530, loss: 7.18240044079721e-05
2023-01-24 08:10:54.268774: step: 124/530, loss: 0.00024895212845876813
2023-01-24 08:10:55.333172: step: 128/530, loss: 0.001364733325317502
2023-01-24 08:10:56.387675: step: 132/530, loss: 0.03680232912302017
2023-01-24 08:10:57.448696: step: 136/530, loss: 7.626634032931179e-05
2023-01-24 08:10:58.509313: step: 140/530, loss: 0.0018529273802414536
2023-01-24 08:10:59.560503: step: 144/530, loss: 0.004630149807780981
2023-01-24 08:11:00.617036: step: 148/530, loss: 0.0023875257465988398
2023-01-24 08:11:01.695504: step: 152/530, loss: 0.0001668501936364919
2023-01-24 08:11:02.739108: step: 156/530, loss: 0.002660535741597414
2023-01-24 08:11:03.797342: step: 160/530, loss: 0.006991139613091946
2023-01-24 08:11:04.869605: step: 164/530, loss: 0.008228965103626251
2023-01-24 08:11:05.924714: step: 168/530, loss: 9.058923023985699e-05
2023-01-24 08:11:06.993823: step: 172/530, loss: 0.0020049859303981066
2023-01-24 08:11:08.059354: step: 176/530, loss: 0.004972059745341539
2023-01-24 08:11:09.102509: step: 180/530, loss: 0.016794217750430107
2023-01-24 08:11:10.151886: step: 184/530, loss: 0.004986226558685303
2023-01-24 08:11:11.206757: step: 188/530, loss: 0.0055866544134914875
2023-01-24 08:11:12.259641: step: 192/530, loss: 0.0005941632553003728
2023-01-24 08:11:13.313978: step: 196/530, loss: 0.012751948088407516
2023-01-24 08:11:14.382378: step: 200/530, loss: 0.0026953136548399925
2023-01-24 08:11:15.438465: step: 204/530, loss: 0.0025713969953358173
2023-01-24 08:11:16.495356: step: 208/530, loss: 0.001725605921819806
2023-01-24 08:11:17.549649: step: 212/530, loss: 0.0018055252730846405
2023-01-24 08:11:18.615547: step: 216/530, loss: 0.00407212320715189
2023-01-24 08:11:19.682891: step: 220/530, loss: 0.0002567624324001372
2023-01-24 08:11:20.741139: step: 224/530, loss: 0.00971232634037733
2023-01-24 08:11:21.792511: step: 228/530, loss: 0.0003279975207988173
2023-01-24 08:11:22.846404: step: 232/530, loss: 0.0010163073893636465
2023-01-24 08:11:23.910121: step: 236/530, loss: 0.00034463824704289436
2023-01-24 08:11:24.965773: step: 240/530, loss: 0.006095506716519594
2023-01-24 08:11:26.061526: step: 244/530, loss: 0.0018111647805199027
2023-01-24 08:11:27.120736: step: 248/530, loss: 0.0017166829202324152
2023-01-24 08:11:28.186772: step: 252/530, loss: 0.0029127250891178846
2023-01-24 08:11:29.223950: step: 256/530, loss: 6.0145110182929784e-05
2023-01-24 08:11:30.277912: step: 260/530, loss: 0.0018024436431005597
2023-01-24 08:11:31.347094: step: 264/530, loss: 2.5659552193246782e-05
2023-01-24 08:11:32.399836: step: 268/530, loss: 0.002872179029509425
2023-01-24 08:11:33.444720: step: 272/530, loss: 0.0025366514455527067
2023-01-24 08:11:34.514211: step: 276/530, loss: 0.00363520928658545
2023-01-24 08:11:35.561093: step: 280/530, loss: 0.0010392050025984645
2023-01-24 08:11:36.618606: step: 284/530, loss: 0.003522642655298114
2023-01-24 08:11:37.674099: step: 288/530, loss: 0.00032669026404619217
2023-01-24 08:11:38.729257: step: 292/530, loss: 0.0007757392595522106
2023-01-24 08:11:39.781657: step: 296/530, loss: 9.982248593587428e-05
2023-01-24 08:11:40.842493: step: 300/530, loss: 0.0011167319025844336
2023-01-24 08:11:41.906203: step: 304/530, loss: 0.003380789887160063
2023-01-24 08:11:42.970883: step: 308/530, loss: 0.002762816147878766
2023-01-24 08:11:44.018970: step: 312/530, loss: 5.8911522501148283e-05
2023-01-24 08:11:45.071061: step: 316/530, loss: 0.005111285950988531
2023-01-24 08:11:46.123461: step: 320/530, loss: 1.0968845344905276e-05
2023-01-24 08:11:47.174365: step: 324/530, loss: 0.0012409324990585446
2023-01-24 08:11:48.235929: step: 328/530, loss: 0.00444065872579813
2023-01-24 08:11:49.301932: step: 332/530, loss: 0.0071311285719275475
2023-01-24 08:11:50.362465: step: 336/530, loss: 0.002979936311021447
2023-01-24 08:11:51.421081: step: 340/530, loss: 4.4204705773154274e-05
2023-01-24 08:11:52.498333: step: 344/530, loss: 0.005602729506790638
2023-01-24 08:11:53.560197: step: 348/530, loss: 0.010418785735964775
2023-01-24 08:11:54.619855: step: 352/530, loss: 0.007625289261341095
2023-01-24 08:11:55.682383: step: 356/530, loss: 0.005736652296036482
2023-01-24 08:11:56.736732: step: 360/530, loss: 9.349539027425635e-07
2023-01-24 08:11:57.779679: step: 364/530, loss: 0.0021775986533612013
2023-01-24 08:11:58.838692: step: 368/530, loss: 0.003915868699550629
2023-01-24 08:11:59.898208: step: 372/530, loss: 0.04896125942468643
2023-01-24 08:12:00.968984: step: 376/530, loss: 0.0001042205112753436
2023-01-24 08:12:02.037001: step: 380/530, loss: 0.0017008360009640455
2023-01-24 08:12:03.100217: step: 384/530, loss: 0.0029940218664705753
2023-01-24 08:12:04.182590: step: 388/530, loss: 0.0010300650028511882
2023-01-24 08:12:05.250968: step: 392/530, loss: 0.00015870867355260998
2023-01-24 08:12:06.306758: step: 396/530, loss: 0.006296739913523197
2023-01-24 08:12:07.375454: step: 400/530, loss: 0.003334162523970008
2023-01-24 08:12:08.437449: step: 404/530, loss: 3.72045069525484e-05
2023-01-24 08:12:09.502445: step: 408/530, loss: 0.008457803167402744
2023-01-24 08:12:10.563964: step: 412/530, loss: 0.007899478077888489
2023-01-24 08:12:11.615251: step: 416/530, loss: 0.0014235851122066379
2023-01-24 08:12:12.681678: step: 420/530, loss: 0.003728689858689904
2023-01-24 08:12:13.742007: step: 424/530, loss: 0.0022654810454696417
2023-01-24 08:12:14.817939: step: 428/530, loss: 0.02324497140944004
2023-01-24 08:12:15.882307: step: 432/530, loss: 0.0020368474069982767
2023-01-24 08:12:16.968345: step: 436/530, loss: 0.00020153888908680528
2023-01-24 08:12:18.039377: step: 440/530, loss: 4.303013702156022e-05
2023-01-24 08:12:19.105945: step: 444/530, loss: 0.0014824257232248783
2023-01-24 08:12:20.165761: step: 448/530, loss: 0.015982531011104584
2023-01-24 08:12:21.216825: step: 452/530, loss: 0.00019782452727667987
2023-01-24 08:12:22.268646: step: 456/530, loss: 0.0004076980403624475
2023-01-24 08:12:23.300103: step: 460/530, loss: 0.00018251534493174404
2023-01-24 08:12:24.366960: step: 464/530, loss: 0.01019479800015688
2023-01-24 08:12:25.429450: step: 468/530, loss: 0.0024552149698138237
2023-01-24 08:12:26.492823: step: 472/530, loss: 9.550879622111097e-05
2023-01-24 08:12:27.544599: step: 476/530, loss: 0.018162155523896217
2023-01-24 08:12:28.623488: step: 480/530, loss: 0.0061699082143604755
2023-01-24 08:12:29.679576: step: 484/530, loss: 0.00011448593431850895
2023-01-24 08:12:30.755592: step: 488/530, loss: 0.006930534727871418
2023-01-24 08:12:31.832729: step: 492/530, loss: 0.0024129217490553856
2023-01-24 08:12:32.904452: step: 496/530, loss: 0.0021330404561012983
2023-01-24 08:12:33.962664: step: 500/530, loss: 0.0
2023-01-24 08:12:35.009158: step: 504/530, loss: 2.8366664537315955e-06
2023-01-24 08:12:36.055386: step: 508/530, loss: 0.0035516696516424417
2023-01-24 08:12:37.093952: step: 512/530, loss: 0.0017698646988719702
2023-01-24 08:12:38.172819: step: 516/530, loss: 0.00905707385390997
2023-01-24 08:12:39.231012: step: 520/530, loss: 0.0007563039544038475
2023-01-24 08:12:40.292804: step: 524/530, loss: 0.003938170149922371
2023-01-24 08:12:41.338313: step: 528/530, loss: 0.0
2023-01-24 08:12:42.396798: step: 532/530, loss: 0.005788673646748066
2023-01-24 08:12:43.484312: step: 536/530, loss: 0.0055591338314116
2023-01-24 08:12:44.548087: step: 540/530, loss: 0.025313809514045715
2023-01-24 08:12:45.605545: step: 544/530, loss: 0.0012019500136375427
2023-01-24 08:12:46.648659: step: 548/530, loss: 0.0026905620470643044
2023-01-24 08:12:47.723984: step: 552/530, loss: 0.0035372653510421515
2023-01-24 08:12:48.782642: step: 556/530, loss: 0.0058954074047505856
2023-01-24 08:12:49.842887: step: 560/530, loss: 0.001668637036345899
2023-01-24 08:12:50.896863: step: 564/530, loss: 0.0048230416141450405
2023-01-24 08:12:51.958379: step: 568/530, loss: 0.0004215730878058821
2023-01-24 08:12:53.016357: step: 572/530, loss: 0.006306564435362816
2023-01-24 08:12:54.081293: step: 576/530, loss: 0.007425761315971613
2023-01-24 08:12:55.128112: step: 580/530, loss: 0.0012103727785870433
2023-01-24 08:12:56.175473: step: 584/530, loss: 0.013819319196045399
2023-01-24 08:12:57.259589: step: 588/530, loss: 0.0032062337268143892
2023-01-24 08:12:58.328176: step: 592/530, loss: 0.002507188357412815
2023-01-24 08:12:59.395969: step: 596/530, loss: 0.00642424076795578
2023-01-24 08:13:00.463201: step: 600/530, loss: 0.0026239582803100348
2023-01-24 08:13:01.538081: step: 604/530, loss: 0.002418368589133024
2023-01-24 08:13:02.609216: step: 608/530, loss: 0.0023264652118086815
2023-01-24 08:13:03.693350: step: 612/530, loss: 0.009183662943542004
2023-01-24 08:13:04.767032: step: 616/530, loss: 0.008495069108903408
2023-01-24 08:13:05.821922: step: 620/530, loss: 0.007957619614899158
2023-01-24 08:13:06.872498: step: 624/530, loss: 0.0016105532413348556
2023-01-24 08:13:07.926998: step: 628/530, loss: 0.005336131900548935
2023-01-24 08:13:08.999586: step: 632/530, loss: 0.0008452058536931872
2023-01-24 08:13:10.053358: step: 636/530, loss: 0.0021655745804309845
2023-01-24 08:13:11.125373: step: 640/530, loss: 2.5903731511789374e-05
2023-01-24 08:13:12.189033: step: 644/530, loss: 0.004575239960104227
2023-01-24 08:13:13.254707: step: 648/530, loss: 0.011776391416788101
2023-01-24 08:13:14.318479: step: 652/530, loss: 0.002930695889517665
2023-01-24 08:13:15.365869: step: 656/530, loss: 0.00041023746598511934
2023-01-24 08:13:16.414840: step: 660/530, loss: 0.0011043745325878263
2023-01-24 08:13:17.473328: step: 664/530, loss: 0.0008587486809119582
2023-01-24 08:13:18.538026: step: 668/530, loss: 0.0069945501163601875
2023-01-24 08:13:19.594266: step: 672/530, loss: 0.0027160656172782183
2023-01-24 08:13:20.660264: step: 676/530, loss: 0.0002792657760437578
2023-01-24 08:13:21.736144: step: 680/530, loss: 0.004578132648020983
2023-01-24 08:13:22.790643: step: 684/530, loss: 4.543236627796432e-06
2023-01-24 08:13:23.843154: step: 688/530, loss: 0.0037390990182757378
2023-01-24 08:13:24.899006: step: 692/530, loss: 6.106190994614735e-05
2023-01-24 08:13:25.955432: step: 696/530, loss: 0.0026797375176101923
2023-01-24 08:13:27.026422: step: 700/530, loss: 0.0033157041762024164
2023-01-24 08:13:28.073875: step: 704/530, loss: 0.004262496251612902
2023-01-24 08:13:29.144275: step: 708/530, loss: 0.05321928858757019
2023-01-24 08:13:30.194824: step: 712/530, loss: 0.004236577078700066
2023-01-24 08:13:31.255851: step: 716/530, loss: 0.0007178787491284311
2023-01-24 08:13:32.312562: step: 720/530, loss: 0.004924480337649584
2023-01-24 08:13:33.351189: step: 724/530, loss: 0.004528968129307032
2023-01-24 08:13:34.396676: step: 728/530, loss: 0.0017166959587484598
2023-01-24 08:13:35.449362: step: 732/530, loss: 0.002583642490208149
2023-01-24 08:13:36.514414: step: 736/530, loss: 0.0006176792667247355
2023-01-24 08:13:37.584056: step: 740/530, loss: 0.002775475149974227
2023-01-24 08:13:38.652742: step: 744/530, loss: 0.006214153952896595
2023-01-24 08:13:39.702279: step: 748/530, loss: 0.00022231538605410606
2023-01-24 08:13:40.747713: step: 752/530, loss: 0.00011115198867628351
2023-01-24 08:13:41.792235: step: 756/530, loss: 0.0014645750634372234
2023-01-24 08:13:42.864072: step: 760/530, loss: 0.0009270327282138169
2023-01-24 08:13:43.946451: step: 764/530, loss: 0.0028734307270497084
2023-01-24 08:13:44.997360: step: 768/530, loss: 0.01239060889929533
2023-01-24 08:13:46.047046: step: 772/530, loss: 0.0021370186004787683
2023-01-24 08:13:47.098638: step: 776/530, loss: 0.0018930728547275066
2023-01-24 08:13:48.158478: step: 780/530, loss: 0.009109108708798885
2023-01-24 08:13:49.218826: step: 784/530, loss: 0.0015687990235164762
2023-01-24 08:13:50.275108: step: 788/530, loss: 0.0
2023-01-24 08:13:51.334684: step: 792/530, loss: 0.011761723086237907
2023-01-24 08:13:52.388811: step: 796/530, loss: 0.0003380372072570026
2023-01-24 08:13:53.445918: step: 800/530, loss: 0.008242730051279068
2023-01-24 08:13:54.501420: step: 804/530, loss: 0.0008853185572661459
2023-01-24 08:13:55.555415: step: 808/530, loss: 0.0004365322820376605
2023-01-24 08:13:56.607237: step: 812/530, loss: 0.0004911092692054808
2023-01-24 08:13:57.641418: step: 816/530, loss: 0.0009347404120489955
2023-01-24 08:13:58.730361: step: 820/530, loss: 0.0013178896624594927
2023-01-24 08:13:59.794759: step: 824/530, loss: 0.0029908129945397377
2023-01-24 08:14:00.865324: step: 828/530, loss: 0.002864066045731306
2023-01-24 08:14:01.943087: step: 832/530, loss: 0.009295692667365074
2023-01-24 08:14:02.993905: step: 836/530, loss: 0.0021121858153492212
2023-01-24 08:14:04.039369: step: 840/530, loss: 0.0006936705904081464
2023-01-24 08:14:05.086526: step: 844/530, loss: 0.01071300357580185
2023-01-24 08:14:06.148969: step: 848/530, loss: 0.002960806479677558
2023-01-24 08:14:07.199246: step: 852/530, loss: 0.005278423428535461
2023-01-24 08:14:08.247527: step: 856/530, loss: 0.00425961846485734
2023-01-24 08:14:09.301490: step: 860/530, loss: 0.0057912892661988735
2023-01-24 08:14:10.350452: step: 864/530, loss: 0.0004971798625774682
2023-01-24 08:14:11.418165: step: 868/530, loss: 0.0035598990507423878
2023-01-24 08:14:12.464187: step: 872/530, loss: 0.0023684045299887657
2023-01-24 08:14:13.519095: step: 876/530, loss: 0.0002959244011435658
2023-01-24 08:14:14.577364: step: 880/530, loss: 0.0027957954443991184
2023-01-24 08:14:15.629405: step: 884/530, loss: 0.012473799288272858
2023-01-24 08:14:16.699812: step: 888/530, loss: 0.00181030691601336
2023-01-24 08:14:17.766374: step: 892/530, loss: 0.00269837467931211
2023-01-24 08:14:18.830448: step: 896/530, loss: 0.008018838241696358
2023-01-24 08:14:19.870452: step: 900/530, loss: 1.3784369002678432e-05
2023-01-24 08:14:20.923682: step: 904/530, loss: 0.009204037487506866
2023-01-24 08:14:21.968549: step: 908/530, loss: 7.278906559804454e-05
2023-01-24 08:14:23.009234: step: 912/530, loss: 0.0007557955104857683
2023-01-24 08:14:24.099162: step: 916/530, loss: 0.004523287061601877
2023-01-24 08:14:25.146689: step: 920/530, loss: 0.004014754667878151
2023-01-24 08:14:26.221049: step: 924/530, loss: 0.003916308283805847
2023-01-24 08:14:27.279900: step: 928/530, loss: 0.000837705738376826
2023-01-24 08:14:28.336673: step: 932/530, loss: 0.0013259451370686293
2023-01-24 08:14:29.391658: step: 936/530, loss: 0.00012868944031652063
2023-01-24 08:14:30.449734: step: 940/530, loss: 0.0040209353901445866
2023-01-24 08:14:31.525768: step: 944/530, loss: 0.0002446983999107033
2023-01-24 08:14:32.594938: step: 948/530, loss: 0.001639649854041636
2023-01-24 08:14:33.664577: step: 952/530, loss: 0.011721325106918812
2023-01-24 08:14:34.707261: step: 956/530, loss: 0.0011594862444326282
2023-01-24 08:14:35.771801: step: 960/530, loss: 0.0006356053636409342
2023-01-24 08:14:36.824538: step: 964/530, loss: 0.009116455912590027
2023-01-24 08:14:37.895533: step: 968/530, loss: 0.004880056716501713
2023-01-24 08:14:38.947149: step: 972/530, loss: 0.004856486339122057
2023-01-24 08:14:39.995015: step: 976/530, loss: 0.010619249194860458
2023-01-24 08:14:41.050173: step: 980/530, loss: 0.005518024787306786
2023-01-24 08:14:42.101592: step: 984/530, loss: 0.02494860626757145
2023-01-24 08:14:43.181814: step: 988/530, loss: 0.0003843820304609835
2023-01-24 08:14:44.236155: step: 992/530, loss: 5.3429052059073e-05
2023-01-24 08:14:45.289685: step: 996/530, loss: 0.010356186889111996
2023-01-24 08:14:46.347367: step: 1000/530, loss: 0.0023228719364851713
2023-01-24 08:14:47.401611: step: 1004/530, loss: 0.013973345048725605
2023-01-24 08:14:48.476454: step: 1008/530, loss: 0.0019040392944589257
2023-01-24 08:14:49.532579: step: 1012/530, loss: 0.0027658697217702866
2023-01-24 08:14:50.582734: step: 1016/530, loss: 0.0001303055469179526
2023-01-24 08:14:51.646426: step: 1020/530, loss: 0.00109787005931139
2023-01-24 08:14:52.712707: step: 1024/530, loss: 0.02494070678949356
2023-01-24 08:14:53.768847: step: 1028/530, loss: 0.002307172631844878
2023-01-24 08:14:54.834595: step: 1032/530, loss: 0.001349496771581471
2023-01-24 08:14:55.886987: step: 1036/530, loss: 0.0002724653750192374
2023-01-24 08:14:56.943825: step: 1040/530, loss: 0.011107711121439934
2023-01-24 08:14:58.000335: step: 1044/530, loss: 0.005380466114729643
2023-01-24 08:14:59.064299: step: 1048/530, loss: 0.006467881612479687
2023-01-24 08:15:00.137491: step: 1052/530, loss: 0.0008323421352542937
2023-01-24 08:15:01.215467: step: 1056/530, loss: 0.0030333863105624914
2023-01-24 08:15:02.302416: step: 1060/530, loss: 1.357122619083384e-05
2023-01-24 08:15:03.368591: step: 1064/530, loss: 0.005428476259112358
2023-01-24 08:15:04.429224: step: 1068/530, loss: 6.146852683741599e-06
2023-01-24 08:15:05.492233: step: 1072/530, loss: 8.115013770293444e-05
2023-01-24 08:15:06.551033: step: 1076/530, loss: 0.001163430861197412
2023-01-24 08:15:07.629575: step: 1080/530, loss: 3.33540556312073e-05
2023-01-24 08:15:08.696447: step: 1084/530, loss: 0.004403300583362579
2023-01-24 08:15:09.744796: step: 1088/530, loss: 0.002152044326066971
2023-01-24 08:15:10.796842: step: 1092/530, loss: 0.0005421810783445835
2023-01-24 08:15:11.862232: step: 1096/530, loss: 0.011456393636763096
2023-01-24 08:15:12.898052: step: 1100/530, loss: 0.0032643110025674105
2023-01-24 08:15:13.960908: step: 1104/530, loss: 0.0008727310341782868
2023-01-24 08:15:15.013174: step: 1108/530, loss: 0.0029799621552228928
2023-01-24 08:15:16.073551: step: 1112/530, loss: 0.001928052632138133
2023-01-24 08:15:17.137000: step: 1116/530, loss: 0.0030343958642333746
2023-01-24 08:15:18.187426: step: 1120/530, loss: 0.012347896583378315
2023-01-24 08:15:19.242743: step: 1124/530, loss: 0.003494786797091365
2023-01-24 08:15:20.298858: step: 1128/530, loss: 0.005212375894188881
2023-01-24 08:15:21.362796: step: 1132/530, loss: 0.030489826574921608
2023-01-24 08:15:22.435490: step: 1136/530, loss: 0.0030600493773818016
2023-01-24 08:15:23.503894: step: 1140/530, loss: 0.002947741886600852
2023-01-24 08:15:24.566514: step: 1144/530, loss: 0.00041754983249120414
2023-01-24 08:15:25.620123: step: 1148/530, loss: 0.006820475682616234
2023-01-24 08:15:26.673486: step: 1152/530, loss: 0.030965633690357208
2023-01-24 08:15:27.742185: step: 1156/530, loss: 0.0009975474094972014
2023-01-24 08:15:28.803977: step: 1160/530, loss: 0.00589167233556509
2023-01-24 08:15:29.860248: step: 1164/530, loss: 0.003530725836753845
2023-01-24 08:15:30.922986: step: 1168/530, loss: 0.0005125369061715901
2023-01-24 08:15:32.002807: step: 1172/530, loss: 0.005166999530047178
2023-01-24 08:15:33.054014: step: 1176/530, loss: 0.005154833663254976
2023-01-24 08:15:34.119326: step: 1180/530, loss: 0.0028606008272618055
2023-01-24 08:15:35.191583: step: 1184/530, loss: 0.00778200151398778
2023-01-24 08:15:36.239930: step: 1188/530, loss: 0.012655799277126789
2023-01-24 08:15:37.320540: step: 1192/530, loss: 0.00463914405554533
2023-01-24 08:15:38.391093: step: 1196/530, loss: 0.016776612028479576
2023-01-24 08:15:39.457293: step: 1200/530, loss: 0.0010947714326903224
2023-01-24 08:15:40.517406: step: 1204/530, loss: 0.004286728799343109
2023-01-24 08:15:41.579827: step: 1208/530, loss: 0.014476386830210686
2023-01-24 08:15:42.647364: step: 1212/530, loss: 0.00017879836377687752
2023-01-24 08:15:43.717013: step: 1216/530, loss: 0.0029981951229274273
2023-01-24 08:15:44.785671: step: 1220/530, loss: 0.0067831166088581085
2023-01-24 08:15:45.836212: step: 1224/530, loss: 0.0004000284825451672
2023-01-24 08:15:46.896363: step: 1228/530, loss: 0.004634473472833633
2023-01-24 08:15:47.965196: step: 1232/530, loss: 0.00031167708220891654
2023-01-24 08:15:49.026467: step: 1236/530, loss: 0.00014672642282675952
2023-01-24 08:15:50.093321: step: 1240/530, loss: 0.0001291943044634536
2023-01-24 08:15:51.155634: step: 1244/530, loss: 0.00040160107892006636
2023-01-24 08:15:52.234368: step: 1248/530, loss: 0.0027477906551212072
2023-01-24 08:15:53.294178: step: 1252/530, loss: 0.0026647248305380344
2023-01-24 08:15:54.349284: step: 1256/530, loss: 0.0050496975891292095
2023-01-24 08:15:55.417316: step: 1260/530, loss: 0.007349679246544838
2023-01-24 08:15:56.488754: step: 1264/530, loss: 0.002333305310457945
2023-01-24 08:15:57.551978: step: 1268/530, loss: 0.005892075132578611
2023-01-24 08:15:58.602263: step: 1272/530, loss: 3.1096162274479866e-05
2023-01-24 08:15:59.673492: step: 1276/530, loss: 0.00208910065703094
2023-01-24 08:16:00.728655: step: 1280/530, loss: 0.0013125840341672301
2023-01-24 08:16:01.778742: step: 1284/530, loss: 0.01049579307436943
2023-01-24 08:16:02.859895: step: 1288/530, loss: 0.00017735878645908087
2023-01-24 08:16:03.922372: step: 1292/530, loss: 0.0026174653321504593
2023-01-24 08:16:04.989390: step: 1296/530, loss: 0.004889457952231169
2023-01-24 08:16:06.060244: step: 1300/530, loss: 0.004436878953129053
2023-01-24 08:16:07.120159: step: 1304/530, loss: 0.04407677426934242
2023-01-24 08:16:08.182791: step: 1308/530, loss: 0.009135912172496319
2023-01-24 08:16:09.238901: step: 1312/530, loss: 0.00012033154780510813
2023-01-24 08:16:10.307105: step: 1316/530, loss: 0.0005741912173107266
2023-01-24 08:16:11.371645: step: 1320/530, loss: 0.000827984360512346
2023-01-24 08:16:12.423540: step: 1324/530, loss: 0.00039905644371174276
2023-01-24 08:16:13.484907: step: 1328/530, loss: 0.012761428020894527
2023-01-24 08:16:14.568957: step: 1332/530, loss: 0.003925918135792017
2023-01-24 08:16:15.632109: step: 1336/530, loss: 0.00011272216215729713
2023-01-24 08:16:16.686708: step: 1340/530, loss: 0.005644111894071102
2023-01-24 08:16:17.744034: step: 1344/530, loss: 0.002674018731340766
2023-01-24 08:16:18.810634: step: 1348/530, loss: 0.008589793927967548
2023-01-24 08:16:19.874798: step: 1352/530, loss: 0.001278763753362
2023-01-24 08:16:20.940778: step: 1356/530, loss: 0.0033858329989016056
2023-01-24 08:16:21.999277: step: 1360/530, loss: 0.0007215364603325725
2023-01-24 08:16:23.050884: step: 1364/530, loss: 0.0008494686335325241
2023-01-24 08:16:24.107081: step: 1368/530, loss: 0.0020682066679000854
2023-01-24 08:16:25.184390: step: 1372/530, loss: 0.0009404866141267121
2023-01-24 08:16:26.249779: step: 1376/530, loss: 0.014776553958654404
2023-01-24 08:16:27.307287: step: 1380/530, loss: 0.0024232049472630024
2023-01-24 08:16:28.356114: step: 1384/530, loss: 0.00016248329484369606
2023-01-24 08:16:29.419332: step: 1388/530, loss: 3.867230589094106e-06
2023-01-24 08:16:30.464082: step: 1392/530, loss: 0.012080510146915913
2023-01-24 08:16:31.520485: step: 1396/530, loss: 0.007514503318816423
2023-01-24 08:16:32.572792: step: 1400/530, loss: 0.0004357305879238993
2023-01-24 08:16:33.616796: step: 1404/530, loss: 0.0015582782216370106
2023-01-24 08:16:34.669420: step: 1408/530, loss: 0.0005134954117238522
2023-01-24 08:16:35.752220: step: 1412/530, loss: 0.005048430059105158
2023-01-24 08:16:36.838824: step: 1416/530, loss: 0.005916623864322901
2023-01-24 08:16:37.890621: step: 1420/530, loss: 0.0006959058227948844
2023-01-24 08:16:38.955410: step: 1424/530, loss: 0.00013622238475363702
2023-01-24 08:16:40.051947: step: 1428/530, loss: 0.00473270658403635
2023-01-24 08:16:41.107152: step: 1432/530, loss: 0.00217193691059947
2023-01-24 08:16:42.166048: step: 1436/530, loss: 0.0030863445717841387
2023-01-24 08:16:43.228078: step: 1440/530, loss: 0.0029959524981677532
2023-01-24 08:16:44.288662: step: 1444/530, loss: 0.004369216971099377
2023-01-24 08:16:45.323300: step: 1448/530, loss: 0.0002775027242023498
2023-01-24 08:16:46.372441: step: 1452/530, loss: 0.012105317786335945
2023-01-24 08:16:47.429767: step: 1456/530, loss: 0.0007738307467661798
2023-01-24 08:16:48.508235: step: 1460/530, loss: 0.0016105304239317775
2023-01-24 08:16:49.578752: step: 1464/530, loss: 0.0007385810022242367
2023-01-24 08:16:50.633164: step: 1468/530, loss: 0.010588613338768482
2023-01-24 08:16:51.686084: step: 1472/530, loss: 0.002354239346459508
2023-01-24 08:16:52.742794: step: 1476/530, loss: 0.004085084423422813
2023-01-24 08:16:53.800927: step: 1480/530, loss: 0.0014612242812290788
2023-01-24 08:16:54.856573: step: 1484/530, loss: 0.001157862483523786
2023-01-24 08:16:55.916467: step: 1488/530, loss: 0.00991156417876482
2023-01-24 08:16:56.963650: step: 1492/530, loss: 0.0013073643203824759
2023-01-24 08:16:58.014211: step: 1496/530, loss: 0.0008875157218426466
2023-01-24 08:16:59.078758: step: 1500/530, loss: 0.005048149731010199
2023-01-24 08:17:00.128914: step: 1504/530, loss: 0.0013094150926917791
2023-01-24 08:17:01.181819: step: 1508/530, loss: 0.009651774540543556
2023-01-24 08:17:02.242555: step: 1512/530, loss: 2.1703603124478832e-05
2023-01-24 08:17:03.283786: step: 1516/530, loss: 0.005784967914223671
2023-01-24 08:17:04.336853: step: 1520/530, loss: 0.003384597133845091
2023-01-24 08:17:05.400506: step: 1524/530, loss: 0.001116138300858438
2023-01-24 08:17:06.466948: step: 1528/530, loss: 0.0064106713980436325
2023-01-24 08:17:07.519894: step: 1532/530, loss: 0.00103941117413342
2023-01-24 08:17:08.594358: step: 1536/530, loss: 0.002000241307541728
2023-01-24 08:17:09.667864: step: 1540/530, loss: 0.003647992154583335
2023-01-24 08:17:10.724550: step: 1544/530, loss: 0.00013092538574710488
2023-01-24 08:17:11.773112: step: 1548/530, loss: 0.0021415052469819784
2023-01-24 08:17:12.853264: step: 1552/530, loss: 0.002189740538597107
2023-01-24 08:17:13.904438: step: 1556/530, loss: 0.004675908945500851
2023-01-24 08:17:14.961552: step: 1560/530, loss: 0.0064605651423335075
2023-01-24 08:17:16.030620: step: 1564/530, loss: 0.003457580925896764
2023-01-24 08:17:17.082497: step: 1568/530, loss: 0.002549791010096669
2023-01-24 08:17:18.148138: step: 1572/530, loss: 0.003073513275012374
2023-01-24 08:17:19.203291: step: 1576/530, loss: 0.0017663181060925126
2023-01-24 08:17:20.256041: step: 1580/530, loss: 0.004768700338900089
2023-01-24 08:17:21.308223: step: 1584/530, loss: 0.001490938593633473
2023-01-24 08:17:22.380487: step: 1588/530, loss: 0.0035764218773692846
2023-01-24 08:17:23.426867: step: 1592/530, loss: 0.002601673360913992
2023-01-24 08:17:24.492176: step: 1596/530, loss: 0.004360167309641838
2023-01-24 08:17:25.550951: step: 1600/530, loss: 0.0017813154263421893
2023-01-24 08:17:26.616156: step: 1604/530, loss: 0.0005115437088534236
2023-01-24 08:17:27.664926: step: 1608/530, loss: 0.0015580097679048777
2023-01-24 08:17:28.715600: step: 1612/530, loss: 0.0009313811897300184
2023-01-24 08:17:29.776885: step: 1616/530, loss: 0.003170141950249672
2023-01-24 08:17:30.840459: step: 1620/530, loss: 0.0066484976559877396
2023-01-24 08:17:31.893824: step: 1624/530, loss: 0.03129187598824501
2023-01-24 08:17:32.941898: step: 1628/530, loss: 0.0017491650069132447
2023-01-24 08:17:34.003976: step: 1632/530, loss: 0.005608345847576857
2023-01-24 08:17:35.063772: step: 1636/530, loss: 3.549307393768686e-06
2023-01-24 08:17:36.111434: step: 1640/530, loss: 0.002708329353481531
2023-01-24 08:17:37.189311: step: 1644/530, loss: 0.0030882530845701694
2023-01-24 08:17:38.237764: step: 1648/530, loss: 0.001372261205688119
2023-01-24 08:17:39.298595: step: 1652/530, loss: 0.004122499376535416
2023-01-24 08:17:40.362237: step: 1656/530, loss: 0.0012495401315391064
2023-01-24 08:17:41.458255: step: 1660/530, loss: 0.00310580269433558
2023-01-24 08:17:42.506983: step: 1664/530, loss: 0.003324440447613597
2023-01-24 08:17:43.573316: step: 1668/530, loss: 0.008820747956633568
2023-01-24 08:17:44.618639: step: 1672/530, loss: 0.0003008394851349294
2023-01-24 08:17:45.669793: step: 1676/530, loss: 0.00015873562369961292
2023-01-24 08:17:46.730610: step: 1680/530, loss: 0.0014639886794611812
2023-01-24 08:17:47.788741: step: 1684/530, loss: 0.0038634841330349445
2023-01-24 08:17:48.842177: step: 1688/530, loss: 0.0022937003523111343
2023-01-24 08:17:49.911108: step: 1692/530, loss: 0.0018387915333732963
2023-01-24 08:17:50.959363: step: 1696/530, loss: 0.000539447006303817
2023-01-24 08:17:52.022285: step: 1700/530, loss: 1.8636201275512576e-05
2023-01-24 08:17:53.081300: step: 1704/530, loss: 0.002009348012506962
2023-01-24 08:17:54.156087: step: 1708/530, loss: 0.003003309480845928
2023-01-24 08:17:55.218216: step: 1712/530, loss: 0.00573319336399436
2023-01-24 08:17:56.269852: step: 1716/530, loss: 2.1565016140812077e-05
2023-01-24 08:17:57.328892: step: 1720/530, loss: 0.0024107687640935183
2023-01-24 08:17:58.381635: step: 1724/530, loss: 0.0027836698573082685
2023-01-24 08:17:59.440202: step: 1728/530, loss: 0.013397029601037502
2023-01-24 08:18:00.496429: step: 1732/530, loss: 0.0029961131513118744
2023-01-24 08:18:01.555116: step: 1736/530, loss: 0.001511456212028861
2023-01-24 08:18:02.638095: step: 1740/530, loss: 0.002070426242426038
2023-01-24 08:18:03.693360: step: 1744/530, loss: 0.004805145785212517
2023-01-24 08:18:04.743062: step: 1748/530, loss: 0.00802450068295002
2023-01-24 08:18:05.814369: step: 1752/530, loss: 0.007181966211646795
2023-01-24 08:18:06.868134: step: 1756/530, loss: 0.0002228617377113551
2023-01-24 08:18:07.911762: step: 1760/530, loss: 0.0006234684260562062
2023-01-24 08:18:08.960279: step: 1764/530, loss: 0.011605664156377316
2023-01-24 08:18:10.014791: step: 1768/530, loss: 0.0024073508102446795
2023-01-24 08:18:11.073088: step: 1772/530, loss: 0.00016558643255848438
2023-01-24 08:18:12.129906: step: 1776/530, loss: 0.0038935376796871424
2023-01-24 08:18:13.182767: step: 1780/530, loss: 0.0018876600079238415
2023-01-24 08:18:14.256471: step: 1784/530, loss: 0.00028517073951661587
2023-01-24 08:18:15.309708: step: 1788/530, loss: 0.0016901235794648528
2023-01-24 08:18:16.364320: step: 1792/530, loss: 0.001723955268971622
2023-01-24 08:18:17.445691: step: 1796/530, loss: 0.007639243733137846
2023-01-24 08:18:18.508065: step: 1800/530, loss: 2.240624553451198e-06
2023-01-24 08:18:19.560240: step: 1804/530, loss: 0.0035283362958580256
2023-01-24 08:18:20.632466: step: 1808/530, loss: 0.00013449843390844762
2023-01-24 08:18:21.701485: step: 1812/530, loss: 0.00010105366527568549
2023-01-24 08:18:22.759149: step: 1816/530, loss: 0.020721998065710068
2023-01-24 08:18:23.821123: step: 1820/530, loss: 0.0004792529216501862
2023-01-24 08:18:24.879970: step: 1824/530, loss: 0.00237208791077137
2023-01-24 08:18:25.916139: step: 1828/530, loss: 0.000804501585662365
2023-01-24 08:18:26.972365: step: 1832/530, loss: 0.0017982082208618522
2023-01-24 08:18:28.032852: step: 1836/530, loss: 0.00035185753949917853
2023-01-24 08:18:29.093676: step: 1840/530, loss: 0.00035365656367503107
2023-01-24 08:18:30.160657: step: 1844/530, loss: 0.0028863309416919947
2023-01-24 08:18:31.212616: step: 1848/530, loss: 0.003302385099232197
2023-01-24 08:18:32.289085: step: 1852/530, loss: 0.004862851928919554
2023-01-24 08:18:33.345904: step: 1856/530, loss: 0.0013533816672861576
2023-01-24 08:18:34.412966: step: 1860/530, loss: 0.0017837887862697244
2023-01-24 08:18:35.469952: step: 1864/530, loss: 0.0010549998842179775
2023-01-24 08:18:36.530716: step: 1868/530, loss: 0.0033746499102562666
2023-01-24 08:18:37.603373: step: 1872/530, loss: 0.003407091833651066
2023-01-24 08:18:38.673486: step: 1876/530, loss: 0.0002877535589504987
2023-01-24 08:18:39.725468: step: 1880/530, loss: 0.008806528523564339
2023-01-24 08:18:40.775837: step: 1884/530, loss: 0.008145834319293499
2023-01-24 08:18:41.851532: step: 1888/530, loss: 0.02251402474939823
2023-01-24 08:18:42.910419: step: 1892/530, loss: 0.0033284134697169065
2023-01-24 08:18:43.962800: step: 1896/530, loss: 0.0007608557934872806
2023-01-24 08:18:45.018381: step: 1900/530, loss: 0.0035523436963558197
2023-01-24 08:18:46.088805: step: 1904/530, loss: 0.0019328538328409195
2023-01-24 08:18:47.148257: step: 1908/530, loss: 0.004374410957098007
2023-01-24 08:18:48.200303: step: 1912/530, loss: 0.0021371780894696712
2023-01-24 08:18:49.278030: step: 1916/530, loss: 0.0006871892837807536
2023-01-24 08:18:50.327343: step: 1920/530, loss: 0.016005143523216248
2023-01-24 08:18:51.392184: step: 1924/530, loss: 0.004985588602721691
2023-01-24 08:18:52.458207: step: 1928/530, loss: 0.002317729638889432
2023-01-24 08:18:53.518405: step: 1932/530, loss: 0.0018285639816895127
2023-01-24 08:18:54.570187: step: 1936/530, loss: 0.00011135570821352303
2023-01-24 08:18:55.615300: step: 1940/530, loss: 0.0018454341916367412
2023-01-24 08:18:56.672785: step: 1944/530, loss: 0.004229668527841568
2023-01-24 08:18:57.709555: step: 1948/530, loss: 7.189160533016548e-05
2023-01-24 08:18:58.760989: step: 1952/530, loss: 0.0024383391719311476
2023-01-24 08:18:59.819605: step: 1956/530, loss: 0.011738252826035023
2023-01-24 08:19:00.892555: step: 1960/530, loss: 0.005646354053169489
2023-01-24 08:19:01.950704: step: 1964/530, loss: 0.005883152596652508
2023-01-24 08:19:03.047258: step: 1968/530, loss: 0.014391114003956318
2023-01-24 08:19:04.103452: step: 1972/530, loss: 0.001084222225472331
2023-01-24 08:19:05.164425: step: 1976/530, loss: 0.0014072353951632977
2023-01-24 08:19:06.244261: step: 1980/530, loss: 0.006906730588525534
2023-01-24 08:19:07.296386: step: 1984/530, loss: 0.0017693625995889306
2023-01-24 08:19:08.361839: step: 1988/530, loss: 0.0013903853250667453
2023-01-24 08:19:09.443382: step: 1992/530, loss: 0.0021799863316118717
2023-01-24 08:19:10.480156: step: 1996/530, loss: 0.00016508408589288592
2023-01-24 08:19:11.538940: step: 2000/530, loss: 0.0038060236256569624
2023-01-24 08:19:12.600766: step: 2004/530, loss: 0.0005931927007623017
2023-01-24 08:19:13.641528: step: 2008/530, loss: 0.002115587005391717
2023-01-24 08:19:14.701634: step: 2012/530, loss: 0.015803448855876923
2023-01-24 08:19:15.769513: step: 2016/530, loss: 0.002373557770624757
2023-01-24 08:19:16.825204: step: 2020/530, loss: 4.712997542810626e-05
2023-01-24 08:19:17.877867: step: 2024/530, loss: 0.012704210355877876
2023-01-24 08:19:18.924102: step: 2028/530, loss: 0.005773926619440317
2023-01-24 08:19:19.968737: step: 2032/530, loss: 0.0030485300812870264
2023-01-24 08:19:21.019002: step: 2036/530, loss: 0.00439033005386591
2023-01-24 08:19:22.059751: step: 2040/530, loss: 0.0001475557655794546
2023-01-24 08:19:23.137622: step: 2044/530, loss: 0.0007186115835793316
2023-01-24 08:19:24.208820: step: 2048/530, loss: 0.005137973930686712
2023-01-24 08:19:25.261318: step: 2052/530, loss: 0.001257850555703044
2023-01-24 08:19:26.334783: step: 2056/530, loss: 0.0031440432649105787
2023-01-24 08:19:27.378412: step: 2060/530, loss: 0.02054126001894474
2023-01-24 08:19:28.434627: step: 2064/530, loss: 0.006343626417219639
2023-01-24 08:19:29.500511: step: 2068/530, loss: 0.00048386285197921097
2023-01-24 08:19:30.567389: step: 2072/530, loss: 0.004758656956255436
2023-01-24 08:19:31.622295: step: 2076/530, loss: 0.0004961027880199254
2023-01-24 08:19:32.695841: step: 2080/530, loss: 0.001984576229006052
2023-01-24 08:19:33.765372: step: 2084/530, loss: 0.005387153942137957
2023-01-24 08:19:34.815110: step: 2088/530, loss: 0.007111052051186562
2023-01-24 08:19:35.883653: step: 2092/530, loss: 0.014361165463924408
2023-01-24 08:19:36.937380: step: 2096/530, loss: 0.005159243941307068
2023-01-24 08:19:37.992468: step: 2100/530, loss: 0.01888951100409031
2023-01-24 08:19:39.054795: step: 2104/530, loss: 0.0012335758656263351
2023-01-24 08:19:40.107802: step: 2108/530, loss: 0.016428260132670403
2023-01-24 08:19:41.181347: step: 2112/530, loss: 0.010537414811551571
2023-01-24 08:19:42.225277: step: 2116/530, loss: 0.0018130127573385835
2023-01-24 08:19:43.302006: step: 2120/530, loss: 0.006279817782342434
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3849935088411227, 'r': 0.3367780029900523, 'f1': 0.35927531897926634}, 'combined': 0.2647291824057752, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.40018709428834365, 'r': 0.2993607354676441, 'f1': 0.34250782512642786}, 'combined': 0.2271554487885117, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35085093896713615, 'r': 0.2830729166666667, 'f1': 0.31333857442348007}, 'combined': 0.2088923829489867, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4005760876782073, 'r': 0.29488776004684636, 'f1': 0.3397012960778818}, 'combined': 0.22169979322977545, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37405831747182694, 'r': 0.3350199731436477, 'f1': 0.3534645162096142}, 'combined': 0.2604475382597157, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.4000392408806625, 'r': 0.31033347171348363, 'f1': 0.34952234015511807}, 'combined': 0.23180756238266895, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 08:22:06.208416: step: 4/530, loss: 0.0009386829333379865
2023-01-24 08:22:07.242335: step: 8/530, loss: 0.00021448858024086803
2023-01-24 08:22:08.292075: step: 12/530, loss: 0.002030710456892848
2023-01-24 08:22:09.352323: step: 16/530, loss: 0.007472326513379812
2023-01-24 08:22:10.406407: step: 20/530, loss: 0.0024618019815534353
2023-01-24 08:22:11.462781: step: 24/530, loss: 0.007355418987572193
2023-01-24 08:22:12.511632: step: 28/530, loss: 0.0018335689092054963
2023-01-24 08:22:13.564786: step: 32/530, loss: 0.005031111184507608
2023-01-24 08:22:14.618037: step: 36/530, loss: 0.0028262948617339134
2023-01-24 08:22:15.661508: step: 40/530, loss: 0.02769174799323082
2023-01-24 08:22:16.714839: step: 44/530, loss: 3.081093018408865e-05
2023-01-24 08:22:17.765323: step: 48/530, loss: 0.004454792011529207
2023-01-24 08:22:18.818552: step: 52/530, loss: 0.005327933933585882
2023-01-24 08:22:19.865410: step: 56/530, loss: 0.04255596920847893
2023-01-24 08:22:20.907042: step: 60/530, loss: 0.0041749305091798306
2023-01-24 08:22:21.966712: step: 64/530, loss: 0.0022202820982784033
2023-01-24 08:22:23.017864: step: 68/530, loss: 0.0018177309539169073
2023-01-24 08:22:24.069962: step: 72/530, loss: 0.00785097386687994
2023-01-24 08:22:25.138879: step: 76/530, loss: 0.0007124464609660208
2023-01-24 08:22:26.186694: step: 80/530, loss: 0.004217336419969797
2023-01-24 08:22:27.235977: step: 84/530, loss: 0.015137048438191414
2023-01-24 08:22:28.275482: step: 88/530, loss: 1.621049341338221e-05
2023-01-24 08:22:29.341914: step: 92/530, loss: 0.005527848843485117
2023-01-24 08:22:30.392858: step: 96/530, loss: 1.3223519090388436e-05
2023-01-24 08:22:31.456292: step: 100/530, loss: 0.007298769894987345
2023-01-24 08:22:32.555754: step: 104/530, loss: 0.0031019283924251795
2023-01-24 08:22:33.622367: step: 108/530, loss: 0.00399396475404501
2023-01-24 08:22:34.674472: step: 112/530, loss: 0.00026533877826295793
2023-01-24 08:22:35.715373: step: 116/530, loss: 0.008851900696754456
2023-01-24 08:22:36.764454: step: 120/530, loss: 0.011578517965972424
2023-01-24 08:22:37.822403: step: 124/530, loss: 0.001883233548142016
2023-01-24 08:22:38.875478: step: 128/530, loss: 0.006535989232361317
2023-01-24 08:22:39.934996: step: 132/530, loss: 0.00044140484533272684
2023-01-24 08:22:40.978982: step: 136/530, loss: 0.010019097477197647
2023-01-24 08:22:42.009839: step: 140/530, loss: 0.0022441791370511055
2023-01-24 08:22:43.077753: step: 144/530, loss: 0.0056763035245239735
2023-01-24 08:22:44.128419: step: 148/530, loss: 0.0002883502747863531
2023-01-24 08:22:45.194390: step: 152/530, loss: 0.004349716007709503
2023-01-24 08:22:46.232469: step: 156/530, loss: 4.808623270946555e-05
2023-01-24 08:22:47.305801: step: 160/530, loss: 0.0036020230036228895
2023-01-24 08:22:48.354131: step: 164/530, loss: 0.012690776959061623
2023-01-24 08:22:49.411815: step: 168/530, loss: 0.0038006429094821215
2023-01-24 08:22:50.481278: step: 172/530, loss: 0.00041007701656781137
2023-01-24 08:22:51.540865: step: 176/530, loss: 0.0014719851315021515
2023-01-24 08:22:52.590945: step: 180/530, loss: 0.001649768091738224
2023-01-24 08:22:53.644900: step: 184/530, loss: 0.0001243392180185765
2023-01-24 08:22:54.699531: step: 188/530, loss: 0.0003862860321532935
2023-01-24 08:22:55.753454: step: 192/530, loss: 3.218917845515534e-05
2023-01-24 08:22:56.841420: step: 196/530, loss: 0.009885952807962894
2023-01-24 08:22:57.898497: step: 200/530, loss: 0.0009832639480009675
2023-01-24 08:22:58.950225: step: 204/530, loss: 0.014232131652534008
2023-01-24 08:22:59.998886: step: 208/530, loss: 0.00450295303016901
2023-01-24 08:23:01.054977: step: 212/530, loss: 0.003632990876212716
2023-01-24 08:23:02.139020: step: 216/530, loss: 0.002428669948130846
2023-01-24 08:23:03.189008: step: 220/530, loss: 0.0012075200211256742
2023-01-24 08:23:04.234794: step: 224/530, loss: 0.001973214326426387
2023-01-24 08:23:05.293023: step: 228/530, loss: 0.0008062385604716837
2023-01-24 08:23:06.352121: step: 232/530, loss: 0.0019380688900128007
2023-01-24 08:23:07.403873: step: 236/530, loss: 0.003825535997748375
2023-01-24 08:23:08.442021: step: 240/530, loss: 5.544281066249823e-06
2023-01-24 08:23:09.524274: step: 244/530, loss: 0.004524745978415012
2023-01-24 08:23:10.583543: step: 248/530, loss: 0.0005649895174428821
2023-01-24 08:23:11.655734: step: 252/530, loss: 0.0007945309625938535
2023-01-24 08:23:12.723677: step: 256/530, loss: 0.004739412106573582
2023-01-24 08:23:13.768273: step: 260/530, loss: 0.009475553408265114
2023-01-24 08:23:14.829473: step: 264/530, loss: 0.005468673072755337
2023-01-24 08:23:15.899259: step: 268/530, loss: 0.045450951904058456
2023-01-24 08:23:17.000297: step: 272/530, loss: 0.004849474411457777
2023-01-24 08:23:18.080787: step: 276/530, loss: 0.0021401692647486925
2023-01-24 08:23:19.131561: step: 280/530, loss: 0.009155112318694592
2023-01-24 08:23:20.203577: step: 284/530, loss: 0.00668818736448884
2023-01-24 08:23:21.262677: step: 288/530, loss: 0.0021922269370406866
2023-01-24 08:23:22.302375: step: 292/530, loss: 0.002677822019904852
2023-01-24 08:23:23.362588: step: 296/530, loss: 0.002026274800300598
2023-01-24 08:23:24.408494: step: 300/530, loss: 0.0004909008857794106
2023-01-24 08:23:25.462411: step: 304/530, loss: 0.0018706420669332147
2023-01-24 08:23:26.531204: step: 308/530, loss: 0.005222581792622805
2023-01-24 08:23:27.590315: step: 312/530, loss: 0.0012957018334418535
2023-01-24 08:23:28.644727: step: 316/530, loss: 0.0007491899887099862
2023-01-24 08:23:29.712643: step: 320/530, loss: 0.0018411485943943262
2023-01-24 08:23:30.765787: step: 324/530, loss: 0.0009789136238396168
2023-01-24 08:23:31.852695: step: 328/530, loss: 0.006667387206107378
2023-01-24 08:23:32.905860: step: 332/530, loss: 0.0030638682655990124
2023-01-24 08:23:33.962020: step: 336/530, loss: 0.005697141867130995
2023-01-24 08:23:35.011071: step: 340/530, loss: 0.0005658336449414492
2023-01-24 08:23:36.068453: step: 344/530, loss: 0.004876302555203438
2023-01-24 08:23:37.115221: step: 348/530, loss: 0.0062772962264716625
2023-01-24 08:23:38.162389: step: 352/530, loss: 0.001867501880042255
2023-01-24 08:23:39.217259: step: 356/530, loss: 0.0002820830559358001
2023-01-24 08:23:40.275390: step: 360/530, loss: 0.0019512730650603771
2023-01-24 08:23:41.333849: step: 364/530, loss: 0.004519370384514332
2023-01-24 08:23:42.391263: step: 368/530, loss: 0.005315495189279318
2023-01-24 08:23:43.448791: step: 372/530, loss: 0.004027731716632843
2023-01-24 08:23:44.494722: step: 376/530, loss: 0.00014638186257798225
2023-01-24 08:23:45.550490: step: 380/530, loss: 0.00039292260771617293
2023-01-24 08:23:46.608559: step: 384/530, loss: 7.301506599333152e-08
2023-01-24 08:23:47.659242: step: 388/530, loss: 7.057004722810234e-07
2023-01-24 08:23:48.717964: step: 392/530, loss: 0.0014324997318908572
2023-01-24 08:23:49.774902: step: 396/530, loss: 0.011277749203145504
2023-01-24 08:23:50.821921: step: 400/530, loss: 0.002842929447069764
2023-01-24 08:23:51.899945: step: 404/530, loss: 0.005885696969926357
2023-01-24 08:23:52.954697: step: 408/530, loss: 0.0016754758544266224
2023-01-24 08:23:54.016287: step: 412/530, loss: 0.002650156384333968
2023-01-24 08:23:55.070908: step: 416/530, loss: 0.0065586562268435955
2023-01-24 08:23:56.146104: step: 420/530, loss: 0.0033050866331905127
2023-01-24 08:23:57.196796: step: 424/530, loss: 0.0026223042514175177
2023-01-24 08:23:58.243225: step: 428/530, loss: 0.0020132584031671286
2023-01-24 08:23:59.302391: step: 432/530, loss: 0.0009613293223083019
2023-01-24 08:24:00.367039: step: 436/530, loss: 0.0007674201624467969
2023-01-24 08:24:01.433679: step: 440/530, loss: 0.0019727502949535847
2023-01-24 08:24:02.497296: step: 444/530, loss: 0.003658716334030032
2023-01-24 08:24:03.572968: step: 448/530, loss: 0.0037849824875593185
2023-01-24 08:24:04.646997: step: 452/530, loss: 0.011315709911286831
2023-01-24 08:24:05.727597: step: 456/530, loss: 0.015622415579855442
2023-01-24 08:24:06.774309: step: 460/530, loss: 0.011789409443736076
2023-01-24 08:24:07.846790: step: 464/530, loss: 0.003437911393120885
2023-01-24 08:24:08.887992: step: 468/530, loss: 0.005939699709415436
2023-01-24 08:24:09.966101: step: 472/530, loss: 0.0016335212858393788
2023-01-24 08:24:11.043774: step: 476/530, loss: 0.0040862420573830605
2023-01-24 08:24:12.097548: step: 480/530, loss: 0.00496178911998868
2023-01-24 08:24:13.157777: step: 484/530, loss: 0.003899594768881798
2023-01-24 08:24:14.214708: step: 488/530, loss: 0.00574311101809144
2023-01-24 08:24:15.272102: step: 492/530, loss: 0.007534942589700222
2023-01-24 08:24:16.319995: step: 496/530, loss: 0.0028131166473031044
2023-01-24 08:24:17.382563: step: 500/530, loss: 0.001040592440403998
2023-01-24 08:24:18.466295: step: 504/530, loss: 0.0051602027378976345
2023-01-24 08:24:19.519577: step: 508/530, loss: 0.010511002503335476
2023-01-24 08:24:20.598305: step: 512/530, loss: 0.0028887316584587097
2023-01-24 08:24:21.649670: step: 516/530, loss: 0.000825155118945986
2023-01-24 08:24:22.713242: step: 520/530, loss: 0.0029051725286990404
2023-01-24 08:24:23.777556: step: 524/530, loss: 3.2719781302148476e-05
2023-01-24 08:24:24.850577: step: 528/530, loss: 0.025147877633571625
2023-01-24 08:24:25.914379: step: 532/530, loss: 0.003658863017335534
2023-01-24 08:24:26.962460: step: 536/530, loss: 0.007298395037651062
2023-01-24 08:24:28.012152: step: 540/530, loss: 0.004791155457496643
2023-01-24 08:24:29.067787: step: 544/530, loss: 0.0009713844629004598
2023-01-24 08:24:30.125562: step: 548/530, loss: 0.000187056211871095
2023-01-24 08:24:31.191116: step: 552/530, loss: 0.0031633852049708366
2023-01-24 08:24:32.255758: step: 556/530, loss: 0.0023610880598425865
2023-01-24 08:24:33.311459: step: 560/530, loss: 1.6934537825363805e-06
2023-01-24 08:24:34.380321: step: 564/530, loss: 0.006590954959392548
2023-01-24 08:24:35.434878: step: 568/530, loss: 0.00823607761412859
2023-01-24 08:24:36.494081: step: 572/530, loss: 0.000521054258570075
2023-01-24 08:24:37.546485: step: 576/530, loss: 0.0033228641841560602
2023-01-24 08:24:38.591266: step: 580/530, loss: 0.007264060899615288
2023-01-24 08:24:39.663398: step: 584/530, loss: 0.0006039158324711025
2023-01-24 08:24:40.723404: step: 588/530, loss: 0.00033796080970205367
2023-01-24 08:24:41.787219: step: 592/530, loss: 0.006586736999452114
2023-01-24 08:24:42.835052: step: 596/530, loss: 0.01144842617213726
2023-01-24 08:24:43.911187: step: 600/530, loss: 0.0010035395389422774
2023-01-24 08:24:44.960391: step: 604/530, loss: 0.003973324783146381
2023-01-24 08:24:46.023680: step: 608/530, loss: 5.2629133278969675e-05
2023-01-24 08:24:47.082822: step: 612/530, loss: 0.0010918211191892624
2023-01-24 08:24:48.139958: step: 616/530, loss: 0.0023431035224348307
2023-01-24 08:24:49.194706: step: 620/530, loss: 0.00015734006592538208
2023-01-24 08:24:50.245742: step: 624/530, loss: 0.00744766928255558
2023-01-24 08:24:51.300780: step: 628/530, loss: 0.0037689898163080215
2023-01-24 08:24:52.363852: step: 632/530, loss: 0.0036387047730386257
2023-01-24 08:24:53.420424: step: 636/530, loss: 0.0030482758302241564
2023-01-24 08:24:54.467494: step: 640/530, loss: 7.787552749505267e-05
2023-01-24 08:24:55.531012: step: 644/530, loss: 0.002574192127212882
2023-01-24 08:24:56.591088: step: 648/530, loss: 0.0011378563940525055
2023-01-24 08:24:57.654944: step: 652/530, loss: 0.0014655538834631443
2023-01-24 08:24:58.710106: step: 656/530, loss: 4.273462764103897e-05
2023-01-24 08:24:59.762217: step: 660/530, loss: 0.002614873694255948
2023-01-24 08:25:00.813794: step: 664/530, loss: 4.4426753447623923e-05
2023-01-24 08:25:01.880690: step: 668/530, loss: 0.0025797775015234947
2023-01-24 08:25:02.959077: step: 672/530, loss: 0.007049053907394409
2023-01-24 08:25:04.018640: step: 676/530, loss: 0.006039605475962162
2023-01-24 08:25:05.077635: step: 680/530, loss: 0.0002868953160941601
2023-01-24 08:25:06.134239: step: 684/530, loss: 0.003985260613262653
2023-01-24 08:25:07.184596: step: 688/530, loss: 0.004556918051093817
2023-01-24 08:25:08.232273: step: 692/530, loss: 0.004089372232556343
2023-01-24 08:25:09.289529: step: 696/530, loss: 0.0012868152698501945
2023-01-24 08:25:10.355470: step: 700/530, loss: 0.0004368739027995616
2023-01-24 08:25:11.418082: step: 704/530, loss: 0.00017612661758903414
2023-01-24 08:25:12.480303: step: 708/530, loss: 0.0006340441177599132
2023-01-24 08:25:13.539593: step: 712/530, loss: 0.0006080247112549841
2023-01-24 08:25:14.601909: step: 716/530, loss: 0.0025806252378970385
2023-01-24 08:25:15.663347: step: 720/530, loss: 0.0020334688015282154
2023-01-24 08:25:16.724610: step: 724/530, loss: 0.005636615213006735
2023-01-24 08:25:17.779755: step: 728/530, loss: 0.002521292772144079
2023-01-24 08:25:18.840648: step: 732/530, loss: 0.007601853925734758
2023-01-24 08:25:19.887396: step: 736/530, loss: 0.0007143801194615662
2023-01-24 08:25:20.939625: step: 740/530, loss: 0.0004314613761380315
2023-01-24 08:25:22.016028: step: 744/530, loss: 0.0007660879055038095
2023-01-24 08:25:23.059076: step: 748/530, loss: 0.002923080697655678
2023-01-24 08:25:24.129024: step: 752/530, loss: 0.001329029444605112
2023-01-24 08:25:25.180511: step: 756/530, loss: 0.0006486055790446699
2023-01-24 08:25:26.224104: step: 760/530, loss: 0.006709316745400429
2023-01-24 08:25:27.297177: step: 764/530, loss: 0.01356930285692215
2023-01-24 08:25:28.358133: step: 768/530, loss: 0.0009534488781355321
2023-01-24 08:25:29.410450: step: 772/530, loss: 0.003793965559452772
2023-01-24 08:25:30.461960: step: 776/530, loss: 0.0031500798650085926
2023-01-24 08:25:31.524164: step: 780/530, loss: 0.00013121060328558087
2023-01-24 08:25:32.577610: step: 784/530, loss: 0.000225961281103082
2023-01-24 08:25:33.628786: step: 788/530, loss: 0.002349739195778966
2023-01-24 08:25:34.676232: step: 792/530, loss: 0.0002679908648133278
2023-01-24 08:25:35.731303: step: 796/530, loss: 0.009738844819366932
2023-01-24 08:25:36.805084: step: 800/530, loss: 0.0044809612445533276
2023-01-24 08:25:37.856045: step: 804/530, loss: 3.349226972204633e-05
2023-01-24 08:25:38.898166: step: 808/530, loss: 0.0002546035102568567
2023-01-24 08:25:39.954783: step: 812/530, loss: 3.3927477488759905e-05
2023-01-24 08:25:41.011995: step: 816/530, loss: 0.003463677829131484
2023-01-24 08:25:42.085048: step: 820/530, loss: 0.002745649078860879
2023-01-24 08:25:43.154399: step: 824/530, loss: 0.0011064013233408332
2023-01-24 08:25:44.224922: step: 828/530, loss: 0.005074132699519396
2023-01-24 08:25:45.294168: step: 832/530, loss: 1.626579432922881e-05
2023-01-24 08:25:46.368502: step: 836/530, loss: 0.005866446997970343
2023-01-24 08:25:47.418664: step: 840/530, loss: 0.00099858024623245
2023-01-24 08:25:48.495704: step: 844/530, loss: 0.0027507091872394085
2023-01-24 08:25:49.552348: step: 848/530, loss: 0.0003187166294082999
2023-01-24 08:25:50.607230: step: 852/530, loss: 0.0035293144173920155
2023-01-24 08:25:51.662983: step: 856/530, loss: 0.0005090002669021487
2023-01-24 08:25:52.723451: step: 860/530, loss: 0.000783972383942455
2023-01-24 08:25:53.793034: step: 864/530, loss: 0.0016587880672886968
2023-01-24 08:25:54.857063: step: 868/530, loss: 1.529602400296426e-06
2023-01-24 08:25:55.908363: step: 872/530, loss: 5.782703374279663e-05
2023-01-24 08:25:56.952026: step: 876/530, loss: 6.204834789969027e-05
2023-01-24 08:25:58.028750: step: 880/530, loss: 0.0006993655697442591
2023-01-24 08:25:59.106593: step: 884/530, loss: 0.0017498458037152886
2023-01-24 08:26:00.144110: step: 888/530, loss: 0.007793949451297522
2023-01-24 08:26:01.203051: step: 892/530, loss: 0.00730760907754302
2023-01-24 08:26:02.246991: step: 896/530, loss: 0.006792369764298201
2023-01-24 08:26:03.308165: step: 900/530, loss: 0.004635286051779985
2023-01-24 08:26:04.367485: step: 904/530, loss: 0.0025487684179097414
2023-01-24 08:26:05.410383: step: 908/530, loss: 0.0011107393074780703
2023-01-24 08:26:06.454780: step: 912/530, loss: 0.01115464698523283
2023-01-24 08:26:07.499672: step: 916/530, loss: 0.0014674729900434613
2023-01-24 08:26:08.566687: step: 920/530, loss: 0.002353713382035494
2023-01-24 08:26:09.655197: step: 924/530, loss: 0.005914868786931038
2023-01-24 08:26:10.713933: step: 928/530, loss: 0.002360415877774358
2023-01-24 08:26:11.774997: step: 932/530, loss: 0.006875370629131794
2023-01-24 08:26:12.843926: step: 936/530, loss: 0.002805947558954358
2023-01-24 08:26:13.888307: step: 940/530, loss: 0.0009517442667856812
2023-01-24 08:26:14.940970: step: 944/530, loss: 0.012530175037682056
2023-01-24 08:26:16.008547: step: 948/530, loss: 0.001134154968895018
2023-01-24 08:26:17.053588: step: 952/530, loss: 0.07279449701309204
2023-01-24 08:26:18.115136: step: 956/530, loss: 0.00794054102152586
2023-01-24 08:26:19.187442: step: 960/530, loss: 0.0028819472063332796
2023-01-24 08:26:20.263858: step: 964/530, loss: 0.006080431863665581
2023-01-24 08:26:21.332105: step: 968/530, loss: 0.0005027989391237497
2023-01-24 08:26:22.385315: step: 972/530, loss: 0.003265087027102709
2023-01-24 08:26:23.440505: step: 976/530, loss: 0.004198809154331684
2023-01-24 08:26:24.499298: step: 980/530, loss: 0.006787418853491545
2023-01-24 08:26:25.562543: step: 984/530, loss: 0.006619878113269806
2023-01-24 08:26:26.598058: step: 988/530, loss: 0.00013095859321765602
2023-01-24 08:26:27.656562: step: 992/530, loss: 4.987631655239966e-06
2023-01-24 08:26:28.725439: step: 996/530, loss: 0.0016563341487199068
2023-01-24 08:26:29.779837: step: 1000/530, loss: 0.008938069455325603
2023-01-24 08:26:30.839152: step: 1004/530, loss: 0.00020557682728394866
2023-01-24 08:26:31.892983: step: 1008/530, loss: 0.004281255882233381
2023-01-24 08:26:32.954866: step: 1012/530, loss: 0.00846561137586832
2023-01-24 08:26:34.016006: step: 1016/530, loss: 0.008833480067551136
2023-01-24 08:26:35.080716: step: 1020/530, loss: 0.0008627060451544821
2023-01-24 08:26:36.157739: step: 1024/530, loss: 0.0017180436989292502
2023-01-24 08:26:37.205697: step: 1028/530, loss: 7.940216164570302e-05
2023-01-24 08:26:38.251893: step: 1032/530, loss: 0.005288590677082539
2023-01-24 08:26:39.310134: step: 1036/530, loss: 0.002299256157130003
2023-01-24 08:26:40.379332: step: 1040/530, loss: 0.004205361939966679
2023-01-24 08:26:41.427271: step: 1044/530, loss: 0.0010540197836235166
2023-01-24 08:26:42.493494: step: 1048/530, loss: 0.004733267240226269
2023-01-24 08:26:43.560331: step: 1052/530, loss: 0.0010042184730991721
2023-01-24 08:26:44.613562: step: 1056/530, loss: 0.007854187861084938
2023-01-24 08:26:45.682428: step: 1060/530, loss: 0.00882694497704506
2023-01-24 08:26:46.780459: step: 1064/530, loss: 0.005203136708587408
2023-01-24 08:26:47.855322: step: 1068/530, loss: 0.007038532756268978
2023-01-24 08:26:48.918924: step: 1072/530, loss: 0.0008152843220159411
2023-01-24 08:26:49.984712: step: 1076/530, loss: 0.009514098055660725
2023-01-24 08:26:51.049690: step: 1080/530, loss: 0.03624803572893143
2023-01-24 08:26:52.105712: step: 1084/530, loss: 0.00037415686529129744
2023-01-24 08:26:53.161347: step: 1088/530, loss: 0.002060860861092806
2023-01-24 08:26:54.228389: step: 1092/530, loss: 0.005768889561295509
2023-01-24 08:26:55.292942: step: 1096/530, loss: 0.0021620236802846193
2023-01-24 08:26:56.349485: step: 1100/530, loss: 0.0009779763640835881
2023-01-24 08:26:57.413974: step: 1104/530, loss: 0.0027924994938075542
2023-01-24 08:26:58.474913: step: 1108/530, loss: 0.00261816312558949
2023-01-24 08:26:59.527651: step: 1112/530, loss: 0.0007506689871661365
2023-01-24 08:27:00.579929: step: 1116/530, loss: 0.0007846153457649052
2023-01-24 08:27:01.643147: step: 1120/530, loss: 0.0005506880697794259
2023-01-24 08:27:02.700638: step: 1124/530, loss: 0.008922494947910309
2023-01-24 08:27:03.766672: step: 1128/530, loss: 0.0006309906602837145
2023-01-24 08:27:04.846740: step: 1132/530, loss: 0.001818582764826715
2023-01-24 08:27:05.892725: step: 1136/530, loss: 0.00010083736560773104
2023-01-24 08:27:06.954972: step: 1140/530, loss: 0.0019913718570023775
2023-01-24 08:27:08.014007: step: 1144/530, loss: 0.002719827927649021
2023-01-24 08:27:09.068610: step: 1148/530, loss: 0.0029059916269034147
2023-01-24 08:27:10.122768: step: 1152/530, loss: 0.0018283172976225615
2023-01-24 08:27:11.187821: step: 1156/530, loss: 0.0021711259614676237
2023-01-24 08:27:12.230181: step: 1160/530, loss: 0.0002222816547146067
2023-01-24 08:27:13.282012: step: 1164/530, loss: 0.004044365603476763
2023-01-24 08:27:14.345454: step: 1168/530, loss: 0.0010410137474536896
2023-01-24 08:27:15.404470: step: 1172/530, loss: 0.003217563033103943
2023-01-24 08:27:16.467769: step: 1176/530, loss: 0.014680308289825916
2023-01-24 08:27:17.524753: step: 1180/530, loss: 0.001965750940144062
2023-01-24 08:27:18.594288: step: 1184/530, loss: 0.0006287461728788912
2023-01-24 08:27:19.660802: step: 1188/530, loss: 0.0015455151442438364
2023-01-24 08:27:20.740305: step: 1192/530, loss: 0.0037629411090165377
2023-01-24 08:27:21.802864: step: 1196/530, loss: 0.020471738651394844
2023-01-24 08:27:22.867412: step: 1200/530, loss: 0.009383459575474262
2023-01-24 08:27:23.942302: step: 1204/530, loss: 4.2920266423607245e-05
2023-01-24 08:27:24.999204: step: 1208/530, loss: 0.002182356547564268
2023-01-24 08:27:26.051309: step: 1212/530, loss: 1.681403591646813e-05
2023-01-24 08:27:27.113160: step: 1216/530, loss: 6.735124043188989e-05
2023-01-24 08:27:28.176716: step: 1220/530, loss: 0.010192221961915493
2023-01-24 08:27:29.246337: step: 1224/530, loss: 0.0027165452484041452
2023-01-24 08:27:30.304710: step: 1228/530, loss: 0.01934061385691166
2023-01-24 08:27:31.372409: step: 1232/530, loss: 0.00330965593457222
2023-01-24 08:27:32.435954: step: 1236/530, loss: 0.0012744124978780746
2023-01-24 08:27:33.484209: step: 1240/530, loss: 0.0047326479107141495
2023-01-24 08:27:34.543176: step: 1244/530, loss: 0.010859795846045017
2023-01-24 08:27:35.591442: step: 1248/530, loss: 0.0033006141893565655
2023-01-24 08:27:36.646829: step: 1252/530, loss: 0.028408804908394814
2023-01-24 08:27:37.701047: step: 1256/530, loss: 0.0025512906722724438
2023-01-24 08:27:38.758951: step: 1260/530, loss: 9.052365385286976e-06
2023-01-24 08:27:39.812598: step: 1264/530, loss: 0.0008138024131767452
2023-01-24 08:27:40.877222: step: 1268/530, loss: 0.002259439555928111
2023-01-24 08:27:41.932125: step: 1272/530, loss: 0.00476970337331295
2023-01-24 08:27:42.987485: step: 1276/530, loss: 0.004920868668705225
2023-01-24 08:27:44.042924: step: 1280/530, loss: 0.0011291453847661614
2023-01-24 08:27:45.115295: step: 1284/530, loss: 0.0050354450941085815
2023-01-24 08:27:46.168678: step: 1288/530, loss: 0.004044852219521999
2023-01-24 08:27:47.218780: step: 1292/530, loss: 0.014269684441387653
2023-01-24 08:27:48.285349: step: 1296/530, loss: 0.008953960612416267
2023-01-24 08:27:49.336511: step: 1300/530, loss: 0.009656088426709175
2023-01-24 08:27:50.385267: step: 1304/530, loss: 0.0004117403586860746
2023-01-24 08:27:51.455326: step: 1308/530, loss: 0.0026506329886615276
2023-01-24 08:27:52.505554: step: 1312/530, loss: 0.0006844486342743039
2023-01-24 08:27:53.567924: step: 1316/530, loss: 0.0008493617060594261
2023-01-24 08:27:54.622249: step: 1320/530, loss: 0.007252085022628307
2023-01-24 08:27:55.697721: step: 1324/530, loss: 0.0040780045092105865
2023-01-24 08:27:56.759436: step: 1328/530, loss: 0.0041299546137452126
2023-01-24 08:27:57.814998: step: 1332/530, loss: 0.005475865676999092
2023-01-24 08:27:58.880716: step: 1336/530, loss: 0.0008960633422248065
2023-01-24 08:27:59.943058: step: 1340/530, loss: 0.0003693457110784948
2023-01-24 08:28:00.994396: step: 1344/530, loss: 0.006004272494465113
2023-01-24 08:28:02.043234: step: 1348/530, loss: 0.0055852667428553104
2023-01-24 08:28:03.125208: step: 1352/530, loss: 0.0005606253980658948
2023-01-24 08:28:04.176336: step: 1356/530, loss: 0.015660429373383522
2023-01-24 08:28:05.250239: step: 1360/530, loss: 0.006589094176888466
2023-01-24 08:28:06.307817: step: 1364/530, loss: 0.0006552804261445999
2023-01-24 08:28:07.363396: step: 1368/530, loss: 0.0018360433168709278
2023-01-24 08:28:08.428134: step: 1372/530, loss: 0.0008776461472734809
2023-01-24 08:28:09.499667: step: 1376/530, loss: 0.00030968282953836024
2023-01-24 08:28:10.540833: step: 1380/530, loss: 0.002020672196522355
2023-01-24 08:28:11.605217: step: 1384/530, loss: 0.0008043415145948529
2023-01-24 08:28:12.667862: step: 1388/530, loss: 0.000731975887902081
2023-01-24 08:28:13.741008: step: 1392/530, loss: 0.00030642494675703347
2023-01-24 08:28:14.815620: step: 1396/530, loss: 0.005770261865109205
2023-01-24 08:28:15.878822: step: 1400/530, loss: 0.0033982235472649336
2023-01-24 08:28:16.957524: step: 1404/530, loss: 0.005668317433446646
2023-01-24 08:28:18.025518: step: 1408/530, loss: 0.002456605900079012
2023-01-24 08:28:19.088413: step: 1412/530, loss: 0.0006804352160543203
2023-01-24 08:28:20.152013: step: 1416/530, loss: 0.0038925365079194307
2023-01-24 08:28:21.237020: step: 1420/530, loss: 0.009606541134417057
2023-01-24 08:28:22.290519: step: 1424/530, loss: 0.0043859235011041164
2023-01-24 08:28:23.359640: step: 1428/530, loss: 0.0015504687326028943
2023-01-24 08:28:24.404142: step: 1432/530, loss: 0.0007106783450581133
2023-01-24 08:28:25.457689: step: 1436/530, loss: 0.0004182421544101089
2023-01-24 08:28:26.525804: step: 1440/530, loss: 4.3359714254620485e-06
2023-01-24 08:28:27.593840: step: 1444/530, loss: 0.0009537481237202883
2023-01-24 08:28:28.648611: step: 1448/530, loss: 0.002968014217913151
2023-01-24 08:28:29.695160: step: 1452/530, loss: 0.007387248799204826
2023-01-24 08:28:30.743648: step: 1456/530, loss: 0.004928029142320156
2023-01-24 08:28:31.811409: step: 1460/530, loss: 0.003396560437977314
2023-01-24 08:28:32.887882: step: 1464/530, loss: 0.0039823311381042
2023-01-24 08:28:33.947224: step: 1468/530, loss: 0.0003091523831244558
2023-01-24 08:28:35.008734: step: 1472/530, loss: 0.009883124381303787
2023-01-24 08:28:36.080446: step: 1476/530, loss: 0.005797490477561951
2023-01-24 08:28:37.148689: step: 1480/530, loss: 7.638749229954556e-05
2023-01-24 08:28:38.214627: step: 1484/530, loss: 0.002113157883286476
2023-01-24 08:28:39.271847: step: 1488/530, loss: 3.481158637441695e-05
2023-01-24 08:28:40.345941: step: 1492/530, loss: 0.032113559544086456
2023-01-24 08:28:41.406101: step: 1496/530, loss: 0.0008705498185008764
2023-01-24 08:28:42.482041: step: 1500/530, loss: 0.0005705328658223152
2023-01-24 08:28:43.544642: step: 1504/530, loss: 0.0012229810236021876
2023-01-24 08:28:44.593678: step: 1508/530, loss: 0.006625020876526833
2023-01-24 08:28:45.650129: step: 1512/530, loss: 0.00024427458993159235
2023-01-24 08:28:46.720457: step: 1516/530, loss: 0.0003933395491912961
2023-01-24 08:28:47.768076: step: 1520/530, loss: 0.00021803095296490937
2023-01-24 08:28:48.828392: step: 1524/530, loss: 0.0016110274009406567
2023-01-24 08:28:49.882807: step: 1528/530, loss: 0.00801507942378521
2023-01-24 08:28:50.931531: step: 1532/530, loss: 0.0022511526476591825
2023-01-24 08:28:52.013483: step: 1536/530, loss: 0.004053221549838781
2023-01-24 08:28:53.076580: step: 1540/530, loss: 8.856142812874168e-05
2023-01-24 08:28:54.118528: step: 1544/530, loss: 0.001768397749401629
2023-01-24 08:28:55.183118: step: 1548/530, loss: 0.0007420568726956844
2023-01-24 08:28:56.236274: step: 1552/530, loss: 0.0009184726513922215
2023-01-24 08:28:57.302512: step: 1556/530, loss: 0.007182806730270386
2023-01-24 08:28:58.369560: step: 1560/530, loss: 0.0013950478751212358
2023-01-24 08:28:59.432020: step: 1564/530, loss: 0.0002595543919596821
2023-01-24 08:29:00.494228: step: 1568/530, loss: 0.00802836287766695
2023-01-24 08:29:01.567444: step: 1572/530, loss: 0.0010372252436354756
2023-01-24 08:29:02.633609: step: 1576/530, loss: 0.008910938166081905
2023-01-24 08:29:03.680073: step: 1580/530, loss: 0.004611999727785587
2023-01-24 08:29:04.729747: step: 1584/530, loss: 0.0023956496734172106
2023-01-24 08:29:05.785669: step: 1588/530, loss: 0.0006668035639449954
2023-01-24 08:29:06.860163: step: 1592/530, loss: 0.0012624349910765886
2023-01-24 08:29:07.909641: step: 1596/530, loss: 0.004224380478262901
2023-01-24 08:29:08.970709: step: 1600/530, loss: 0.0
2023-01-24 08:29:10.033533: step: 1604/530, loss: 0.004453417845070362
2023-01-24 08:29:11.095591: step: 1608/530, loss: 0.0002074887161143124
2023-01-24 08:29:12.172800: step: 1612/530, loss: 0.0019296916434541345
2023-01-24 08:29:13.240897: step: 1616/530, loss: 0.003930032253265381
2023-01-24 08:29:14.289014: step: 1620/530, loss: 0.005718322936445475
2023-01-24 08:29:15.344228: step: 1624/530, loss: 0.007376953028142452
2023-01-24 08:29:16.406634: step: 1628/530, loss: 4.6544264478143305e-05
2023-01-24 08:29:17.463162: step: 1632/530, loss: 2.080125705106184e-05
2023-01-24 08:29:18.533909: step: 1636/530, loss: 0.00038969746674411
2023-01-24 08:29:19.602823: step: 1640/530, loss: 2.7635526294034207e-06
2023-01-24 08:29:20.650028: step: 1644/530, loss: 0.0018047861522063613
2023-01-24 08:29:21.720360: step: 1648/530, loss: 0.018415110185742378
2023-01-24 08:29:22.779395: step: 1652/530, loss: 0.006245397496968508
2023-01-24 08:29:23.843653: step: 1656/530, loss: 0.008730108849704266
2023-01-24 08:29:24.893124: step: 1660/530, loss: 0.0005476248916238546
2023-01-24 08:29:25.943449: step: 1664/530, loss: 0.005872698500752449
2023-01-24 08:29:27.006843: step: 1668/530, loss: 0.006725342478603125
2023-01-24 08:29:28.065382: step: 1672/530, loss: 0.002643076702952385
2023-01-24 08:29:29.151935: step: 1676/530, loss: 0.0018357306253165007
2023-01-24 08:29:30.210158: step: 1680/530, loss: 0.0025024511851370335
2023-01-24 08:29:31.270046: step: 1684/530, loss: 0.0017786616226658225
2023-01-24 08:29:32.351246: step: 1688/530, loss: 0.0014846071135252714
2023-01-24 08:29:33.391381: step: 1692/530, loss: 0.0043900697492063046
2023-01-24 08:29:34.462584: step: 1696/530, loss: 0.0005729013355448842
2023-01-24 08:29:35.519433: step: 1700/530, loss: 0.000537501648068428
2023-01-24 08:29:36.574523: step: 1704/530, loss: 0.00025959074264392257
2023-01-24 08:29:37.625022: step: 1708/530, loss: 0.0007950629806146026
2023-01-24 08:29:38.679542: step: 1712/530, loss: 0.000675673596560955
2023-01-24 08:29:39.747811: step: 1716/530, loss: 0.003960703033953905
2023-01-24 08:29:40.803399: step: 1720/530, loss: 0.0008025092538446188
2023-01-24 08:29:41.855230: step: 1724/530, loss: 9.509678784525022e-05
2023-01-24 08:29:42.909823: step: 1728/530, loss: 0.0008456521318294108
2023-01-24 08:29:43.984437: step: 1732/530, loss: 0.0012850385392084718
2023-01-24 08:29:45.051476: step: 1736/530, loss: 0.00015842165157664567
2023-01-24 08:29:46.111804: step: 1740/530, loss: 0.0028479828033596277
2023-01-24 08:29:47.174456: step: 1744/530, loss: 0.004899812396615744
2023-01-24 08:29:48.226779: step: 1748/530, loss: 0.0021729222498834133
2023-01-24 08:29:49.285425: step: 1752/530, loss: 0.0006834256928414106
2023-01-24 08:29:50.359787: step: 1756/530, loss: 0.0008538194815628231
2023-01-24 08:29:51.421625: step: 1760/530, loss: 0.003740330459550023
2023-01-24 08:29:52.479262: step: 1764/530, loss: 0.002530330792069435
2023-01-24 08:29:53.543367: step: 1768/530, loss: 0.0019842495676130056
2023-01-24 08:29:54.607702: step: 1772/530, loss: 0.0023462462704628706
2023-01-24 08:29:55.664646: step: 1776/530, loss: 0.0018969499506056309
2023-01-24 08:29:56.717290: step: 1780/530, loss: 0.00016835425049066544
2023-01-24 08:29:57.768051: step: 1784/530, loss: 0.00010306596232112497
2023-01-24 08:29:58.833482: step: 1788/530, loss: 0.0004965196712873876
2023-01-24 08:29:59.891156: step: 1792/530, loss: 0.004526231437921524
2023-01-24 08:30:00.956275: step: 1796/530, loss: 0.007723315618932247
2023-01-24 08:30:02.026881: step: 1800/530, loss: 0.022789280861616135
2023-01-24 08:30:03.080413: step: 1804/530, loss: 0.012160413898527622
2023-01-24 08:30:04.127339: step: 1808/530, loss: 7.116822234820575e-05
2023-01-24 08:30:05.204255: step: 1812/530, loss: 0.003039315342903137
2023-01-24 08:30:06.257767: step: 1816/530, loss: 0.003282669000327587
2023-01-24 08:30:07.336036: step: 1820/530, loss: 0.0035452661104500294
2023-01-24 08:30:08.379842: step: 1824/530, loss: 0.0012875092215836048
2023-01-24 08:30:09.435191: step: 1828/530, loss: 0.0011750131379812956
2023-01-24 08:30:10.490781: step: 1832/530, loss: 0.0004066886322107166
2023-01-24 08:30:11.538797: step: 1836/530, loss: 0.007107979152351618
2023-01-24 08:30:12.598540: step: 1840/530, loss: 0.06521487236022949
2023-01-24 08:30:13.658247: step: 1844/530, loss: 0.0008080429979600012
2023-01-24 08:30:14.717256: step: 1848/530, loss: 0.0002981397556141019
2023-01-24 08:30:15.760633: step: 1852/530, loss: 0.002167333848774433
2023-01-24 08:30:16.822967: step: 1856/530, loss: 0.005629674065858126
2023-01-24 08:30:17.882987: step: 1860/530, loss: 0.003950349520891905
2023-01-24 08:30:18.944168: step: 1864/530, loss: 0.027358174324035645
2023-01-24 08:30:19.994403: step: 1868/530, loss: 0.003266548039391637
2023-01-24 08:30:21.052868: step: 1872/530, loss: 0.009740294888615608
2023-01-24 08:30:22.101294: step: 1876/530, loss: 0.003349998500198126
2023-01-24 08:30:23.137955: step: 1880/530, loss: 0.029655758291482925
2023-01-24 08:30:24.205358: step: 1884/530, loss: 0.08274171501398087
2023-01-24 08:30:25.246902: step: 1888/530, loss: 0.007874841801822186
2023-01-24 08:30:26.316946: step: 1892/530, loss: 0.005087847355753183
2023-01-24 08:30:27.374260: step: 1896/530, loss: 0.013425260782241821
2023-01-24 08:30:28.418503: step: 1900/530, loss: 0.012691500596702099
2023-01-24 08:30:29.469888: step: 1904/530, loss: 0.006187261547893286
2023-01-24 08:30:30.529661: step: 1908/530, loss: 0.0008559083216823637
2023-01-24 08:30:31.586371: step: 1912/530, loss: 0.0035449869465082884
2023-01-24 08:30:32.656522: step: 1916/530, loss: 0.003675689222291112
2023-01-24 08:30:33.728843: step: 1920/530, loss: 0.003050812752917409
2023-01-24 08:30:34.777736: step: 1924/530, loss: 0.002955114236101508
2023-01-24 08:30:35.847941: step: 1928/530, loss: 0.012532936409115791
2023-01-24 08:30:36.892006: step: 1932/530, loss: 4.164597271483217e-07
2023-01-24 08:30:37.953420: step: 1936/530, loss: 0.0037662910763174295
2023-01-24 08:30:39.013422: step: 1940/530, loss: 0.00575527036562562
2023-01-24 08:30:40.071130: step: 1944/530, loss: 0.003928194288164377
2023-01-24 08:30:41.129212: step: 1948/530, loss: 0.0014893363695591688
2023-01-24 08:30:42.188164: step: 1952/530, loss: 0.006476827897131443
2023-01-24 08:30:43.254412: step: 1956/530, loss: 0.002577632898464799
2023-01-24 08:30:44.320503: step: 1960/530, loss: 0.01879754103720188
2023-01-24 08:30:45.375056: step: 1964/530, loss: 0.005210411734879017
2023-01-24 08:30:46.420770: step: 1968/530, loss: 0.004157794173806906
2023-01-24 08:30:47.478469: step: 1972/530, loss: 0.005670475773513317
2023-01-24 08:30:48.551501: step: 1976/530, loss: 0.00019238569075241685
2023-01-24 08:30:49.611395: step: 1980/530, loss: 0.0010525088291615248
2023-01-24 08:30:50.673374: step: 1984/530, loss: 0.007439812179654837
2023-01-24 08:30:51.747889: step: 1988/530, loss: 0.009524581953883171
2023-01-24 08:30:52.822998: step: 1992/530, loss: 0.00033826479921117425
2023-01-24 08:30:53.873422: step: 1996/530, loss: 0.00013386989303398877
2023-01-24 08:30:54.953106: step: 2000/530, loss: 0.001947549288161099
2023-01-24 08:30:56.011398: step: 2004/530, loss: 0.0036375918425619602
2023-01-24 08:30:57.063972: step: 2008/530, loss: 0.00015946265193633735
2023-01-24 08:30:58.124189: step: 2012/530, loss: 0.010268784128129482
2023-01-24 08:30:59.177854: step: 2016/530, loss: 0.0007080572540871799
2023-01-24 08:31:00.225954: step: 2020/530, loss: 0.0031804454047232866
2023-01-24 08:31:01.295546: step: 2024/530, loss: 4.408857421367429e-07
2023-01-24 08:31:02.347994: step: 2028/530, loss: 0.0021610078401863575
2023-01-24 08:31:03.424533: step: 2032/530, loss: 0.003540750127285719
2023-01-24 08:31:04.480510: step: 2036/530, loss: 7.505811663577333e-05
2023-01-24 08:31:05.543818: step: 2040/530, loss: 0.028510065749287605
2023-01-24 08:31:06.616588: step: 2044/530, loss: 0.00204320065677166
2023-01-24 08:31:07.656226: step: 2048/530, loss: 0.00035411937278695405
2023-01-24 08:31:08.728102: step: 2052/530, loss: 0.007907198742032051
2023-01-24 08:31:09.784799: step: 2056/530, loss: 0.01116646733134985
2023-01-24 08:31:10.826361: step: 2060/530, loss: 0.0043425001204013824
2023-01-24 08:31:11.868431: step: 2064/530, loss: 0.003712503472343087
2023-01-24 08:31:12.928482: step: 2068/530, loss: 0.0024377384688705206
2023-01-24 08:31:13.992850: step: 2072/530, loss: 0.004469151142984629
2023-01-24 08:31:15.054929: step: 2076/530, loss: 0.0001533506001578644
2023-01-24 08:31:16.110776: step: 2080/530, loss: 0.007181589026004076
2023-01-24 08:31:17.175074: step: 2084/530, loss: 9.24554933590116e-06
2023-01-24 08:31:18.234650: step: 2088/530, loss: 0.0080645140260458
2023-01-24 08:31:19.294942: step: 2092/530, loss: 0.00018640329653862864
2023-01-24 08:31:20.359027: step: 2096/530, loss: 0.006666557863354683
2023-01-24 08:31:21.416530: step: 2100/530, loss: 0.001275298185646534
2023-01-24 08:31:22.470911: step: 2104/530, loss: 0.0011793274898082018
2023-01-24 08:31:23.535429: step: 2108/530, loss: 0.0007606271537952125
2023-01-24 08:31:24.601908: step: 2112/530, loss: 0.0006227828562259674
2023-01-24 08:31:25.668331: step: 2116/530, loss: 0.00595064926892519
2023-01-24 08:31:26.730025: step: 2120/530, loss: 0.001748465234413743
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3822820120949188, 'r': 0.3344060864815134, 'f1': 0.3567449546067967}, 'combined': 0.26286470339448176, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.4011091689332514, 'r': 0.30109233719924583, 'f1': 0.3439778926460227}, 'combined': 0.22813041584813937, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34852088167053363, 'r': 0.2844933712121212, 'f1': 0.31326903023983316}, 'combined': 0.20884602015988876, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3998716381452098, 'r': 0.29575281194996056, 'f1': 0.34002013984500684}, 'combined': 0.2219078807409518, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3745879784887761, 'r': 0.33549435644535547, 'f1': 0.3539650167101147}, 'combined': 0.2608163281021898, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39564533907572147, 'r': 0.30795251933253126, 'f1': 0.3463341381003638}, 'combined': 0.22969310713392, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 08:33:52.625692: step: 4/530, loss: 0.059192683547735214
2023-01-24 08:33:53.674191: step: 8/530, loss: 0.018978990614414215
2023-01-24 08:33:54.716981: step: 12/530, loss: 9.410739585291594e-05
2023-01-24 08:33:55.763372: step: 16/530, loss: 0.004438491538167
2023-01-24 08:33:56.809825: step: 20/530, loss: 0.006157925818115473
2023-01-24 08:33:57.858704: step: 24/530, loss: 0.018327059224247932
2023-01-24 08:33:58.905602: step: 28/530, loss: 0.00019550872093532234
2023-01-24 08:33:59.954053: step: 32/530, loss: 0.0012724412372335792
2023-01-24 08:34:01.017971: step: 36/530, loss: 0.002525192452594638
2023-01-24 08:34:02.098597: step: 40/530, loss: 0.001945075928233564
2023-01-24 08:34:03.143982: step: 44/530, loss: 0.0008830477017909288
2023-01-24 08:34:04.199248: step: 48/530, loss: 0.00800615455955267
2023-01-24 08:34:05.261427: step: 52/530, loss: 0.00035377449239604175
2023-01-24 08:34:06.330294: step: 56/530, loss: 0.0018717804923653603
2023-01-24 08:34:07.381810: step: 60/530, loss: 0.027395132929086685
2023-01-24 08:34:08.433994: step: 64/530, loss: 0.0031870929524302483
2023-01-24 08:34:09.482884: step: 68/530, loss: 0.00011143877782160416
2023-01-24 08:34:10.541653: step: 72/530, loss: 0.0002747525868471712
2023-01-24 08:34:11.592974: step: 76/530, loss: 0.000694293761625886
2023-01-24 08:34:12.664668: step: 80/530, loss: 0.00042259268229827285
2023-01-24 08:34:13.714115: step: 84/530, loss: 5.9114667237736285e-05
2023-01-24 08:34:14.779385: step: 88/530, loss: 0.004674218129366636
2023-01-24 08:34:15.827987: step: 92/530, loss: 0.052190858870744705
2023-01-24 08:34:16.889255: step: 96/530, loss: 0.00015036837430670857
2023-01-24 08:34:17.948782: step: 100/530, loss: 0.00038838229374960065
2023-01-24 08:34:19.008388: step: 104/530, loss: 0.0001253630471182987
2023-01-24 08:34:20.058818: step: 108/530, loss: 0.003455952275544405
2023-01-24 08:34:21.121631: step: 112/530, loss: 0.0035629766061902046
2023-01-24 08:34:22.184995: step: 116/530, loss: 0.001422525616362691
2023-01-24 08:34:23.254002: step: 120/530, loss: 0.0019508430268615484
2023-01-24 08:34:24.323259: step: 124/530, loss: 2.9280734452186152e-05
2023-01-24 08:34:25.368495: step: 128/530, loss: 0.0036827914882451296
2023-01-24 08:34:26.426342: step: 132/530, loss: 0.0029714140109717846
2023-01-24 08:34:27.504990: step: 136/530, loss: 0.0007055926253087819
2023-01-24 08:34:28.566332: step: 140/530, loss: 0.0022545759566128254
2023-01-24 08:34:29.628869: step: 144/530, loss: 0.0013193677878007293
2023-01-24 08:34:30.683187: step: 148/530, loss: 0.001877557602711022
2023-01-24 08:34:31.735196: step: 152/530, loss: 0.002412040950730443
2023-01-24 08:34:32.822688: step: 156/530, loss: 0.0014203011523932219
2023-01-24 08:34:33.875733: step: 160/530, loss: 0.0003093588165938854
2023-01-24 08:34:34.933051: step: 164/530, loss: 0.0015182859497144818
2023-01-24 08:34:35.994516: step: 168/530, loss: 0.0034255818463861942
2023-01-24 08:34:37.054871: step: 172/530, loss: 0.004508716054260731
2023-01-24 08:34:38.118573: step: 176/530, loss: 0.0077097536996006966
2023-01-24 08:34:39.167541: step: 180/530, loss: 0.0043347966857254505
2023-01-24 08:34:40.215522: step: 184/530, loss: 5.008099105907604e-05
2023-01-24 08:34:41.263229: step: 188/530, loss: 0.00194566382560879
2023-01-24 08:34:42.338395: step: 192/530, loss: 0.00796483177691698
2023-01-24 08:34:43.422524: step: 196/530, loss: 0.0011695085559040308
2023-01-24 08:34:44.484156: step: 200/530, loss: 0.0010574993211776018
2023-01-24 08:34:45.553180: step: 204/530, loss: 0.003104089293628931
2023-01-24 08:34:46.605135: step: 208/530, loss: 7.081463991198689e-05
2023-01-24 08:34:47.665352: step: 212/530, loss: 0.0027858209796249866
2023-01-24 08:34:48.721653: step: 216/530, loss: 6.906247290316969e-05
2023-01-24 08:34:49.785451: step: 220/530, loss: 0.00041725742630660534
2023-01-24 08:34:50.846682: step: 224/530, loss: 0.0024785296991467476
2023-01-24 08:34:51.919400: step: 228/530, loss: 3.743664638022892e-05
2023-01-24 08:34:53.004467: step: 232/530, loss: 0.0028732968494296074
2023-01-24 08:34:54.076466: step: 236/530, loss: 0.0007182710105553269
2023-01-24 08:34:55.141660: step: 240/530, loss: 0.00526081770658493
2023-01-24 08:34:56.202919: step: 244/530, loss: 0.00021167834347579628
2023-01-24 08:34:57.275321: step: 248/530, loss: 5.612459790427238e-05
2023-01-24 08:34:58.333287: step: 252/530, loss: 0.0019344433676451445
2023-01-24 08:34:59.392371: step: 256/530, loss: 0.0001750602386891842
2023-01-24 08:35:00.453195: step: 260/530, loss: 0.004162892699241638
2023-01-24 08:35:01.503617: step: 264/530, loss: 0.004696071147918701
2023-01-24 08:35:02.566940: step: 268/530, loss: 0.009673106484115124
2023-01-24 08:35:03.634429: step: 272/530, loss: 0.0001945290860021487
2023-01-24 08:35:04.694180: step: 276/530, loss: 0.0024551234673708677
2023-01-24 08:35:05.736129: step: 280/530, loss: 1.4490629837382585e-05
2023-01-24 08:35:06.804812: step: 284/530, loss: 0.006912935990840197
2023-01-24 08:35:07.881322: step: 288/530, loss: 0.0045605809427797794
2023-01-24 08:35:08.933606: step: 292/530, loss: 0.00010753023525467142
2023-01-24 08:35:10.013812: step: 296/530, loss: 0.002402425277978182
2023-01-24 08:35:11.073280: step: 300/530, loss: 0.004039755556732416
2023-01-24 08:35:12.143584: step: 304/530, loss: 0.0015180999180302024
2023-01-24 08:35:13.222699: step: 308/530, loss: 0.002066213171929121
2023-01-24 08:35:14.284569: step: 312/530, loss: 0.0009286271524615586
2023-01-24 08:35:15.368096: step: 316/530, loss: 0.0018390915356576443
2023-01-24 08:35:16.421819: step: 320/530, loss: 0.02612193487584591
2023-01-24 08:35:17.468204: step: 324/530, loss: 0.0024463869631290436
2023-01-24 08:35:18.533086: step: 328/530, loss: 0.00011146204633405432
2023-01-24 08:35:19.613534: step: 332/530, loss: 0.015038790181279182
2023-01-24 08:35:20.671667: step: 336/530, loss: 0.0002600799489300698
2023-01-24 08:35:21.735378: step: 340/530, loss: 0.0004936715704388916
2023-01-24 08:35:22.797101: step: 344/530, loss: 0.0001181312181870453
2023-01-24 08:35:23.850727: step: 348/530, loss: 0.0006630150019191206
2023-01-24 08:35:24.927430: step: 352/530, loss: 0.0006449768552556634
2023-01-24 08:35:25.987277: step: 356/530, loss: 0.00047739691217429936
2023-01-24 08:35:27.072474: step: 360/530, loss: 0.0056565250270068645
2023-01-24 08:35:28.131683: step: 364/530, loss: 0.026908257976174355
2023-01-24 08:35:29.198019: step: 368/530, loss: 0.015328820794820786
2023-01-24 08:35:30.242714: step: 372/530, loss: 0.0006343196728266776
2023-01-24 08:35:31.303983: step: 376/530, loss: 0.004836970940232277
2023-01-24 08:35:32.392379: step: 380/530, loss: 0.004707732703536749
2023-01-24 08:35:33.443026: step: 384/530, loss: 0.0003783739230129868
2023-01-24 08:35:34.496528: step: 388/530, loss: 0.001054164837114513
2023-01-24 08:35:35.566927: step: 392/530, loss: 3.850094071822241e-05
2023-01-24 08:35:36.620369: step: 396/530, loss: 0.00015232873556669801
2023-01-24 08:35:37.687189: step: 400/530, loss: 0.002443079836666584
2023-01-24 08:35:38.735297: step: 404/530, loss: 0.0010974782053381205
2023-01-24 08:35:39.786289: step: 408/530, loss: 0.0009960555471479893
2023-01-24 08:35:40.846541: step: 412/530, loss: 0.004391951486468315
2023-01-24 08:35:41.907901: step: 416/530, loss: 6.38125347904861e-05
2023-01-24 08:35:42.973450: step: 420/530, loss: 0.0028816601261496544
2023-01-24 08:35:44.022577: step: 424/530, loss: 2.3729235181235708e-05
2023-01-24 08:35:45.081423: step: 428/530, loss: 1.2100885214749724e-05
2023-01-24 08:35:46.134448: step: 432/530, loss: 0.006377737037837505
2023-01-24 08:35:47.193936: step: 436/530, loss: 0.00010560540977166966
2023-01-24 08:35:48.241261: step: 440/530, loss: 0.003498068079352379
2023-01-24 08:35:49.298121: step: 444/530, loss: 0.0036812257021665573
2023-01-24 08:35:50.346808: step: 448/530, loss: 0.0003007199557032436
2023-01-24 08:35:51.412240: step: 452/530, loss: 5.695580057363259e-06
2023-01-24 08:35:52.475213: step: 456/530, loss: 7.539513899246231e-05
2023-01-24 08:35:53.541801: step: 460/530, loss: 0.0001270364155061543
2023-01-24 08:35:54.598909: step: 464/530, loss: 0.0045892782509326935
2023-01-24 08:35:55.650097: step: 468/530, loss: 0.005200125277042389
2023-01-24 08:35:56.692518: step: 472/530, loss: 0.007242385298013687
2023-01-24 08:35:57.774174: step: 476/530, loss: 0.0016656728694215417
2023-01-24 08:35:58.841308: step: 480/530, loss: 0.003390140598639846
2023-01-24 08:35:59.900983: step: 484/530, loss: 0.00383104314096272
2023-01-24 08:36:00.950341: step: 488/530, loss: 0.0015725400298833847
2023-01-24 08:36:02.007086: step: 492/530, loss: 0.0016765035688877106
2023-01-24 08:36:03.078325: step: 496/530, loss: 3.927049419871764e-06
2023-01-24 08:36:04.143524: step: 500/530, loss: 0.00038760618190281093
2023-01-24 08:36:05.200152: step: 504/530, loss: 0.0019126972183585167
2023-01-24 08:36:06.251725: step: 508/530, loss: 3.307884526293492e-07
2023-01-24 08:36:07.306222: step: 512/530, loss: 0.0002243128401460126
2023-01-24 08:36:08.377000: step: 516/530, loss: 0.0016231201589107513
2023-01-24 08:36:09.442772: step: 520/530, loss: 0.00022361693845596164
2023-01-24 08:36:10.491728: step: 524/530, loss: 1.0578037290542852e-06
2023-01-24 08:36:11.569472: step: 528/530, loss: 0.000610057613812387
2023-01-24 08:36:12.649128: step: 532/530, loss: 0.02693955972790718
2023-01-24 08:36:13.721063: step: 536/530, loss: 0.0011799965286627412
2023-01-24 08:36:14.772118: step: 540/530, loss: 0.00018336896027904004
2023-01-24 08:36:15.843945: step: 544/530, loss: 0.0024420383851975203
2023-01-24 08:36:16.896339: step: 548/530, loss: 0.0002216171706095338
2023-01-24 08:36:17.968580: step: 552/530, loss: 0.00658275093883276
2023-01-24 08:36:19.026525: step: 556/530, loss: 0.003861658973619342
2023-01-24 08:36:20.082438: step: 560/530, loss: 5.7165570979123e-06
2023-01-24 08:36:21.132638: step: 564/530, loss: 0.00014908910088706762
2023-01-24 08:36:22.205220: step: 568/530, loss: 0.0011630464578047395
2023-01-24 08:36:23.248356: step: 572/530, loss: 0.0021871866192668676
2023-01-24 08:36:24.328623: step: 576/530, loss: 0.003597014583647251
2023-01-24 08:36:25.381636: step: 580/530, loss: 0.00036163374898023903
2023-01-24 08:36:26.442854: step: 584/530, loss: 0.0010645553702488542
2023-01-24 08:36:27.506585: step: 588/530, loss: 0.00039010285399854183
2023-01-24 08:36:28.553025: step: 592/530, loss: 0.00018555395945440978
2023-01-24 08:36:29.619466: step: 596/530, loss: 0.0017795072635635734
2023-01-24 08:36:30.677617: step: 600/530, loss: 0.0035783988423645496
2023-01-24 08:36:31.747800: step: 604/530, loss: 0.00029110696050338447
2023-01-24 08:36:32.814140: step: 608/530, loss: 1.0441685844853055e-05
2023-01-24 08:36:33.874643: step: 612/530, loss: 0.0014422353124246001
2023-01-24 08:36:34.934932: step: 616/530, loss: 0.0011893962509930134
2023-01-24 08:36:36.008574: step: 620/530, loss: 0.0061098914593458176
2023-01-24 08:36:37.062690: step: 624/530, loss: 0.0005330511485226452
2023-01-24 08:36:38.109667: step: 628/530, loss: 0.0008534502703696489
2023-01-24 08:36:39.156150: step: 632/530, loss: 0.0019492448773235083
2023-01-24 08:36:40.212415: step: 636/530, loss: 6.99654410709627e-05
2023-01-24 08:36:41.293614: step: 640/530, loss: 0.00010752879461506382
2023-01-24 08:36:42.363634: step: 644/530, loss: 0.004178246483206749
2023-01-24 08:36:43.427394: step: 648/530, loss: 6.285926065174863e-05
2023-01-24 08:36:44.491715: step: 652/530, loss: 0.0019955423194915056
2023-01-24 08:36:45.550945: step: 656/530, loss: 0.0033051460050046444
2023-01-24 08:36:46.594464: step: 660/530, loss: 0.0028750444762408733
2023-01-24 08:36:47.671579: step: 664/530, loss: 0.007834425196051598
2023-01-24 08:36:48.723405: step: 668/530, loss: 0.0015952582471072674
2023-01-24 08:36:49.779051: step: 672/530, loss: 0.013982315547764301
2023-01-24 08:36:50.836397: step: 676/530, loss: 0.0004253937513567507
2023-01-24 08:36:51.901520: step: 680/530, loss: 0.0013414053246378899
2023-01-24 08:36:52.970043: step: 684/530, loss: 0.0031976685859262943
2023-01-24 08:36:54.021679: step: 688/530, loss: 0.0023528647143393755
2023-01-24 08:36:55.068466: step: 692/530, loss: 0.00017307992675341666
2023-01-24 08:36:56.118449: step: 696/530, loss: 0.00038725489866919816
2023-01-24 08:36:57.167188: step: 700/530, loss: 0.000329225993482396
2023-01-24 08:36:58.234527: step: 704/530, loss: 0.0032823269721120596
2023-01-24 08:36:59.295557: step: 708/530, loss: 0.007279534358531237
2023-01-24 08:37:00.345514: step: 712/530, loss: 0.00010168641165364534
2023-01-24 08:37:01.400481: step: 716/530, loss: 0.0034339067060500383
2023-01-24 08:37:02.464860: step: 720/530, loss: 6.240996299311519e-05
2023-01-24 08:37:03.519008: step: 724/530, loss: 0.00193593162111938
2023-01-24 08:37:04.576729: step: 728/530, loss: 0.0016734879463911057
2023-01-24 08:37:05.645323: step: 732/530, loss: 0.0009187238174490631
2023-01-24 08:37:06.698651: step: 736/530, loss: 8.056082879193127e-05
2023-01-24 08:37:07.739862: step: 740/530, loss: 0.00010100848157890141
2023-01-24 08:37:08.815253: step: 744/530, loss: 8.939360122894868e-05
2023-01-24 08:37:09.868132: step: 748/530, loss: 0.0037521186750382185
2023-01-24 08:37:10.918388: step: 752/530, loss: 0.0014936678344383836
2023-01-24 08:37:11.980561: step: 756/530, loss: 0.0012043665628880262
2023-01-24 08:37:13.050762: step: 760/530, loss: 0.00025564085808582604
2023-01-24 08:37:14.101960: step: 764/530, loss: 0.000357006152626127
2023-01-24 08:37:15.161907: step: 768/530, loss: 0.00039656521403230727
2023-01-24 08:37:16.211303: step: 772/530, loss: 0.003564214101061225
2023-01-24 08:37:17.261137: step: 776/530, loss: 0.0007091726874932647
2023-01-24 08:37:18.313645: step: 780/530, loss: 0.003948886413127184
2023-01-24 08:37:19.364937: step: 784/530, loss: 0.00039099648711271584
2023-01-24 08:37:20.415940: step: 788/530, loss: 0.002238166518509388
2023-01-24 08:37:21.467973: step: 792/530, loss: 0.00766237685456872
2023-01-24 08:37:22.535017: step: 796/530, loss: 0.0028105962555855513
2023-01-24 08:37:23.586665: step: 800/530, loss: 0.00036568735959008336
2023-01-24 08:37:24.659579: step: 804/530, loss: 0.0015537930885329843
2023-01-24 08:37:25.707458: step: 808/530, loss: 0.005717322696000338
2023-01-24 08:37:26.754729: step: 812/530, loss: 0.0021680595818907022
2023-01-24 08:37:27.821620: step: 816/530, loss: 0.0010745642939582467
2023-01-24 08:37:28.879385: step: 820/530, loss: 0.00030915025854483247
2023-01-24 08:37:29.940303: step: 824/530, loss: 0.002057289471849799
2023-01-24 08:37:30.995995: step: 828/530, loss: 0.010349827818572521
2023-01-24 08:37:32.071688: step: 832/530, loss: 0.0056083351373672485
2023-01-24 08:37:33.111961: step: 836/530, loss: 0.0010183104313910007
2023-01-24 08:37:34.181264: step: 840/530, loss: 0.00018976262072101235
2023-01-24 08:37:35.236336: step: 844/530, loss: 0.0007217067177407444
2023-01-24 08:37:36.296409: step: 848/530, loss: 0.003354766871780157
2023-01-24 08:37:37.356309: step: 852/530, loss: 0.0035875998437404633
2023-01-24 08:37:38.418311: step: 856/530, loss: 3.900817682733759e-05
2023-01-24 08:37:39.481585: step: 860/530, loss: 1.2187253560114186e-05
2023-01-24 08:37:40.548434: step: 864/530, loss: 0.0016954968450590968
2023-01-24 08:37:41.605763: step: 868/530, loss: 0.00143439881503582
2023-01-24 08:37:42.673087: step: 872/530, loss: 0.0017256420105695724
2023-01-24 08:37:43.741625: step: 876/530, loss: 0.004252709448337555
2023-01-24 08:37:44.813383: step: 880/530, loss: 0.0013457630993798375
2023-01-24 08:37:45.886884: step: 884/530, loss: 0.0016396567225456238
2023-01-24 08:37:46.939425: step: 888/530, loss: 0.00033936084946617484
2023-01-24 08:37:47.982098: step: 892/530, loss: 0.0056954738683998585
2023-01-24 08:37:49.035766: step: 896/530, loss: 0.00223240302875638
2023-01-24 08:37:50.079827: step: 900/530, loss: 0.00028004436171613634
2023-01-24 08:37:51.146259: step: 904/530, loss: 0.002180548617616296
2023-01-24 08:37:52.200409: step: 908/530, loss: 3.755977377295494e-05
2023-01-24 08:37:53.292539: step: 912/530, loss: 0.0005344985402189195
2023-01-24 08:37:54.350916: step: 916/530, loss: 0.0016251313500106335
2023-01-24 08:37:55.399548: step: 920/530, loss: 3.0200213586795144e-05
2023-01-24 08:37:56.468597: step: 924/530, loss: 0.0026034389156848192
2023-01-24 08:37:57.511786: step: 928/530, loss: 3.562566689652158e-06
2023-01-24 08:37:58.554205: step: 932/530, loss: 0.002469759900122881
2023-01-24 08:37:59.593003: step: 936/530, loss: 0.0
2023-01-24 08:38:00.673796: step: 940/530, loss: 0.003475326346233487
2023-01-24 08:38:01.726239: step: 944/530, loss: 0.003895876230672002
2023-01-24 08:38:02.802031: step: 948/530, loss: 0.0014570595230907202
2023-01-24 08:38:03.858409: step: 952/530, loss: 0.0064370231702923775
2023-01-24 08:38:04.907909: step: 956/530, loss: 0.0008968209731392562
2023-01-24 08:38:05.980538: step: 960/530, loss: 0.004135685041546822
2023-01-24 08:38:07.053069: step: 964/530, loss: 0.0024486889597028494
2023-01-24 08:38:08.121478: step: 968/530, loss: 0.0005546585307456553
2023-01-24 08:38:09.201031: step: 972/530, loss: 0.002434910973533988
2023-01-24 08:38:10.250088: step: 976/530, loss: 0.0002758363843895495
2023-01-24 08:38:11.308182: step: 980/530, loss: 0.0034822560846805573
2023-01-24 08:38:12.379202: step: 984/530, loss: 0.005226087756454945
2023-01-24 08:38:13.430424: step: 988/530, loss: 0.01056690327823162
2023-01-24 08:38:14.500711: step: 992/530, loss: 0.006436006166040897
2023-01-24 08:38:15.561446: step: 996/530, loss: 0.002738002687692642
2023-01-24 08:38:16.624186: step: 1000/530, loss: 0.0009512731339782476
2023-01-24 08:38:17.681507: step: 1004/530, loss: 0.002380600431933999
2023-01-24 08:38:18.729946: step: 1008/530, loss: 0.0001242822763742879
2023-01-24 08:38:19.780189: step: 1012/530, loss: 5.010862878407352e-06
2023-01-24 08:38:20.840493: step: 1016/530, loss: 0.003960699774324894
2023-01-24 08:38:21.874843: step: 1020/530, loss: 0.00123043661005795
2023-01-24 08:38:22.953201: step: 1024/530, loss: 0.005833625327795744
2023-01-24 08:38:23.986263: step: 1028/530, loss: 0.0007101250812411308
2023-01-24 08:38:25.065056: step: 1032/530, loss: 0.00026671000523492694
2023-01-24 08:38:26.126233: step: 1036/530, loss: 0.0023285045754164457
2023-01-24 08:38:27.193981: step: 1040/530, loss: 0.003951370716094971
2023-01-24 08:38:28.240747: step: 1044/530, loss: 0.0002584291505627334
2023-01-24 08:38:29.294966: step: 1048/530, loss: 0.0021018036641180515
2023-01-24 08:38:30.366702: step: 1052/530, loss: 0.0052032009698450565
2023-01-24 08:38:31.408542: step: 1056/530, loss: 0.0011574843665584922
2023-01-24 08:38:32.470491: step: 1060/530, loss: 5.633717591990717e-05
2023-01-24 08:38:33.533149: step: 1064/530, loss: 0.005318668205291033
2023-01-24 08:38:34.580824: step: 1068/530, loss: 0.00034650444285944104
2023-01-24 08:38:35.651345: step: 1072/530, loss: 0.0007226613233797252
2023-01-24 08:38:36.702571: step: 1076/530, loss: 4.142200850765221e-05
2023-01-24 08:38:37.765111: step: 1080/530, loss: 1.4579084108845564e-06
2023-01-24 08:38:38.814423: step: 1084/530, loss: 0.01942112296819687
2023-01-24 08:38:39.865300: step: 1088/530, loss: 0.001533513073809445
2023-01-24 08:38:40.917574: step: 1092/530, loss: 0.004345688968896866
2023-01-24 08:38:41.982563: step: 1096/530, loss: 0.005718563683331013
2023-01-24 08:38:43.032908: step: 1100/530, loss: 8.072733908193186e-05
2023-01-24 08:38:44.087187: step: 1104/530, loss: 0.0013543821405619383
2023-01-24 08:38:45.167957: step: 1108/530, loss: 0.005944791249930859
2023-01-24 08:38:46.220160: step: 1112/530, loss: 0.0018408535979688168
2023-01-24 08:38:47.274656: step: 1116/530, loss: 0.003505851374939084
2023-01-24 08:38:48.327283: step: 1120/530, loss: 0.00042468865285627544
2023-01-24 08:38:49.405984: step: 1124/530, loss: 0.004140383563935757
2023-01-24 08:38:50.451855: step: 1128/530, loss: 0.0019997083581984043
2023-01-24 08:38:51.504399: step: 1132/530, loss: 0.0007268836488947272
2023-01-24 08:38:52.573753: step: 1136/530, loss: 0.0012896410189568996
2023-01-24 08:38:53.630595: step: 1140/530, loss: 0.00014028334408067167
2023-01-24 08:38:54.692745: step: 1144/530, loss: 0.0006800381815992296
2023-01-24 08:38:55.753784: step: 1148/530, loss: 9.279007713303145e-07
2023-01-24 08:38:56.808940: step: 1152/530, loss: 0.0012208139523863792
2023-01-24 08:38:57.860987: step: 1156/530, loss: 0.006226833909749985
2023-01-24 08:38:58.933783: step: 1160/530, loss: 0.014818019233644009
2023-01-24 08:38:59.989137: step: 1164/530, loss: 0.004462834447622299
2023-01-24 08:39:01.056648: step: 1168/530, loss: 0.00024710659636184573
2023-01-24 08:39:02.142281: step: 1172/530, loss: 0.0015258699422702193
2023-01-24 08:39:03.214343: step: 1176/530, loss: 0.0003391695208847523
2023-01-24 08:39:04.277734: step: 1180/530, loss: 0.001951267127878964
2023-01-24 08:39:05.335326: step: 1184/530, loss: 0.002194629516452551
2023-01-24 08:39:06.399391: step: 1188/530, loss: 0.0003462890163064003
2023-01-24 08:39:07.465078: step: 1192/530, loss: 0.00012193290604045615
2023-01-24 08:39:08.524373: step: 1196/530, loss: 0.0015159074682742357
2023-01-24 08:39:09.590240: step: 1200/530, loss: 0.009451931342482567
2023-01-24 08:39:10.659051: step: 1204/530, loss: 0.0008692930568940938
2023-01-24 08:39:11.712488: step: 1208/530, loss: 0.006785715464502573
2023-01-24 08:39:12.781274: step: 1212/530, loss: 5.553445953410119e-05
2023-01-24 08:39:13.837853: step: 1216/530, loss: 0.0009975282009691
2023-01-24 08:39:14.889938: step: 1220/530, loss: 0.017443593591451645
2023-01-24 08:39:15.959157: step: 1224/530, loss: 0.0062513891607522964
2023-01-24 08:39:17.027506: step: 1228/530, loss: 0.005552260670810938
2023-01-24 08:39:18.091410: step: 1232/530, loss: 0.005000651814043522
2023-01-24 08:39:19.140820: step: 1236/530, loss: 0.005314888432621956
2023-01-24 08:39:20.203152: step: 1240/530, loss: 0.0009264182881452143
2023-01-24 08:39:21.259961: step: 1244/530, loss: 0.0016931642312556505
2023-01-24 08:39:22.314429: step: 1248/530, loss: 0.003390031633898616
2023-01-24 08:39:23.363844: step: 1252/530, loss: 0.000913382216822356
2023-01-24 08:39:24.402344: step: 1256/530, loss: 5.861747558810748e-05
2023-01-24 08:39:25.471014: step: 1260/530, loss: 0.0018918963614851236
2023-01-24 08:39:26.524318: step: 1264/530, loss: 0.0035234461538493633
2023-01-24 08:39:27.588276: step: 1268/530, loss: 0.0037734070792794228
2023-01-24 08:39:28.633620: step: 1272/530, loss: 0.011028153821825981
2023-01-24 08:39:29.684987: step: 1276/530, loss: 0.011834010481834412
2023-01-24 08:39:30.747246: step: 1280/530, loss: 0.0032597710378468037
2023-01-24 08:39:31.822407: step: 1284/530, loss: 0.009212887845933437
2023-01-24 08:39:32.897307: step: 1288/530, loss: 0.001232433714903891
2023-01-24 08:39:33.961888: step: 1292/530, loss: 0.0013742693699896336
2023-01-24 08:39:35.013252: step: 1296/530, loss: 0.0017181668663397431
2023-01-24 08:39:36.063543: step: 1300/530, loss: 0.00022880798496771604
2023-01-24 08:39:37.109831: step: 1304/530, loss: 0.00033933110535144806
2023-01-24 08:39:38.161319: step: 1308/530, loss: 0.002581647364422679
2023-01-24 08:39:39.210636: step: 1312/530, loss: 0.000677432690281421
2023-01-24 08:39:40.263958: step: 1316/530, loss: 0.001540435361675918
2023-01-24 08:39:41.312943: step: 1320/530, loss: 0.0012464426690712571
2023-01-24 08:39:42.380463: step: 1324/530, loss: 0.0010704627493396401
2023-01-24 08:39:43.440544: step: 1328/530, loss: 0.003316232468932867
2023-01-24 08:39:44.500892: step: 1332/530, loss: 0.010116294026374817
2023-01-24 08:39:45.582124: step: 1336/530, loss: 0.000527312804479152
2023-01-24 08:39:46.634651: step: 1340/530, loss: 0.0008955479715950787
2023-01-24 08:39:47.685004: step: 1344/530, loss: 0.0014403837267309427
2023-01-24 08:39:48.738840: step: 1348/530, loss: 0.00608457624912262
2023-01-24 08:39:49.789539: step: 1352/530, loss: 0.00012017461995128542
2023-01-24 08:39:50.851486: step: 1356/530, loss: 0.005782244261354208
2023-01-24 08:39:51.908272: step: 1360/530, loss: 0.02346494235098362
2023-01-24 08:39:52.965973: step: 1364/530, loss: 0.0001532189198769629
2023-01-24 08:39:54.020187: step: 1368/530, loss: 0.002110595116391778
2023-01-24 08:39:55.097048: step: 1372/530, loss: 0.06614694744348526
2023-01-24 08:39:56.156931: step: 1376/530, loss: 1.986814446297558e-08
2023-01-24 08:39:57.233169: step: 1380/530, loss: 0.0025785844773054123
2023-01-24 08:39:58.305016: step: 1384/530, loss: 0.0021717411000281572
2023-01-24 08:39:59.383248: step: 1388/530, loss: 0.010472293943166733
2023-01-24 08:40:00.451186: step: 1392/530, loss: 0.001528059015981853
2023-01-24 08:40:01.496280: step: 1396/530, loss: 0.0036804266273975372
2023-01-24 08:40:02.551962: step: 1400/530, loss: 0.0016494496958330274
2023-01-24 08:40:03.610351: step: 1404/530, loss: 0.003875534050166607
2023-01-24 08:40:04.667701: step: 1408/530, loss: 7.9530400398653e-05
2023-01-24 08:40:05.709299: step: 1412/530, loss: 0.011152983643114567
2023-01-24 08:40:06.756034: step: 1416/530, loss: 0.0017858123173937201
2023-01-24 08:40:07.802404: step: 1420/530, loss: 0.0016966091934591532
2023-01-24 08:40:08.844143: step: 1424/530, loss: 0.0011043237755075097
2023-01-24 08:40:09.900704: step: 1428/530, loss: 0.0025296914391219616
2023-01-24 08:40:10.961633: step: 1432/530, loss: 0.0001698226697044447
2023-01-24 08:40:12.021619: step: 1436/530, loss: 0.0005540081183426082
2023-01-24 08:40:13.074488: step: 1440/530, loss: 0.0038423589430749416
2023-01-24 08:40:14.141732: step: 1444/530, loss: 0.0008583692833781242
2023-01-24 08:40:15.191436: step: 1448/530, loss: 0.002930636517703533
2023-01-24 08:40:16.235957: step: 1452/530, loss: 0.00040480177267454565
2023-01-24 08:40:17.295421: step: 1456/530, loss: 0.02402661181986332
2023-01-24 08:40:18.340064: step: 1460/530, loss: 1.8284675888935453e-06
2023-01-24 08:40:19.401190: step: 1464/530, loss: 0.00520919868722558
2023-01-24 08:40:20.446148: step: 1468/530, loss: 0.0003348229220137
2023-01-24 08:40:21.485953: step: 1472/530, loss: 0.0
2023-01-24 08:40:22.569307: step: 1476/530, loss: 0.021019157022237778
2023-01-24 08:40:23.631447: step: 1480/530, loss: 0.004463464021682739
2023-01-24 08:40:24.690935: step: 1484/530, loss: 0.0036678018514066935
2023-01-24 08:40:25.777267: step: 1488/530, loss: 0.03458976745605469
2023-01-24 08:40:26.825750: step: 1492/530, loss: 0.01479429379105568
2023-01-24 08:40:27.893498: step: 1496/530, loss: 0.011129218153655529
2023-01-24 08:40:28.945673: step: 1500/530, loss: 0.005471966695040464
2023-01-24 08:40:30.008999: step: 1504/530, loss: 0.012077328749001026
2023-01-24 08:40:31.065244: step: 1508/530, loss: 0.0044840550981462
2023-01-24 08:40:32.110610: step: 1512/530, loss: 0.00026452881866134703
2023-01-24 08:40:33.155883: step: 1516/530, loss: 0.00044833586434833705
2023-01-24 08:40:34.222169: step: 1520/530, loss: 0.000541728048119694
2023-01-24 08:40:35.265455: step: 1524/530, loss: 0.0007533407770097256
2023-01-24 08:40:36.326420: step: 1528/530, loss: 0.0
2023-01-24 08:40:37.384548: step: 1532/530, loss: 0.00019487006647977978
2023-01-24 08:40:38.433284: step: 1536/530, loss: 0.0006437512929551303
2023-01-24 08:40:39.491263: step: 1540/530, loss: 0.0014870183076709509
2023-01-24 08:40:40.546570: step: 1544/530, loss: 0.0015436818357557058
2023-01-24 08:40:41.591935: step: 1548/530, loss: 0.00519077992066741
2023-01-24 08:40:42.650199: step: 1552/530, loss: 0.0007815276039764285
2023-01-24 08:40:43.709542: step: 1556/530, loss: 0.003829352091997862
2023-01-24 08:40:44.763770: step: 1560/530, loss: 0.002531065372750163
2023-01-24 08:40:45.810933: step: 1564/530, loss: 0.0032826003152877092
2023-01-24 08:40:46.847269: step: 1568/530, loss: 0.0012569900136440992
2023-01-24 08:40:47.909654: step: 1572/530, loss: 0.0005269836401566863
2023-01-24 08:40:48.978594: step: 1576/530, loss: 0.0025522541254758835
2023-01-24 08:40:50.029244: step: 1580/530, loss: 0.0027215268928557634
2023-01-24 08:40:51.075455: step: 1584/530, loss: 0.0008277919259853661
2023-01-24 08:40:52.146771: step: 1588/530, loss: 0.00014382500376086682
2023-01-24 08:40:53.192120: step: 1592/530, loss: 0.002043931046500802
2023-01-24 08:40:54.242996: step: 1596/530, loss: 0.0010352483950555325
2023-01-24 08:40:55.306727: step: 1600/530, loss: 0.0022766483016312122
2023-01-24 08:40:56.363775: step: 1604/530, loss: 0.00511900894343853
2023-01-24 08:40:57.423425: step: 1608/530, loss: 0.0033122305758297443
2023-01-24 08:40:58.478739: step: 1612/530, loss: 0.0019924254156649113
2023-01-24 08:40:59.546418: step: 1616/530, loss: 0.0004986777203157544
2023-01-24 08:41:00.603153: step: 1620/530, loss: 8.124688406496716e-07
2023-01-24 08:41:01.663325: step: 1624/530, loss: 4.141549288760871e-05
2023-01-24 08:41:02.719885: step: 1628/530, loss: 0.001991770463064313
2023-01-24 08:41:03.768512: step: 1632/530, loss: 0.0001452805008739233
2023-01-24 08:41:04.837037: step: 1636/530, loss: 0.00014028162695467472
2023-01-24 08:41:05.897028: step: 1640/530, loss: 0.007117794826626778
2023-01-24 08:41:06.965350: step: 1644/530, loss: 0.007529959548264742
2023-01-24 08:41:08.026913: step: 1648/530, loss: 0.0012098860461264849
2023-01-24 08:41:09.075263: step: 1652/530, loss: 0.005414650775492191
2023-01-24 08:41:10.142178: step: 1656/530, loss: 0.005151515360921621
2023-01-24 08:41:11.200047: step: 1660/530, loss: 0.00044063912355341017
2023-01-24 08:41:12.282156: step: 1664/530, loss: 0.0018273539608344436
2023-01-24 08:41:13.350044: step: 1668/530, loss: 0.004269003868103027
2023-01-24 08:41:14.406272: step: 1672/530, loss: 0.0026084587443619967
2023-01-24 08:41:15.473385: step: 1676/530, loss: 0.0046369279734790325
2023-01-24 08:41:16.537107: step: 1680/530, loss: 0.003920101094990969
2023-01-24 08:41:17.599362: step: 1684/530, loss: 0.004268328659236431
2023-01-24 08:41:18.655740: step: 1688/530, loss: 0.0012724155094474554
2023-01-24 08:41:19.744581: step: 1692/530, loss: 0.00011943405115744099
2023-01-24 08:41:20.800228: step: 1696/530, loss: 0.00030443575815297663
2023-01-24 08:41:21.863161: step: 1700/530, loss: 0.007141844369471073
2023-01-24 08:41:22.924471: step: 1704/530, loss: 0.01584586687386036
2023-01-24 08:41:23.985249: step: 1708/530, loss: 0.0005249660462141037
2023-01-24 08:41:25.054375: step: 1712/530, loss: 0.0021053049713373184
2023-01-24 08:41:26.114972: step: 1716/530, loss: 0.003415602957829833
2023-01-24 08:41:27.174468: step: 1720/530, loss: 0.0027876971289515495
2023-01-24 08:41:28.227893: step: 1724/530, loss: 0.0023400920908898115
2023-01-24 08:41:29.270163: step: 1728/530, loss: 5.0695602112682536e-05
2023-01-24 08:41:30.329038: step: 1732/530, loss: 0.0014937978703528643
2023-01-24 08:41:31.380528: step: 1736/530, loss: 0.001036931062117219
2023-01-24 08:41:32.439745: step: 1740/530, loss: 0.001710493816062808
2023-01-24 08:41:33.487255: step: 1744/530, loss: 0.0009898740099743009
2023-01-24 08:41:34.525464: step: 1748/530, loss: 7.949067367007956e-05
2023-01-24 08:41:35.579646: step: 1752/530, loss: 0.0011929996544495225
2023-01-24 08:41:36.643423: step: 1756/530, loss: 0.018602391704916954
2023-01-24 08:41:37.707734: step: 1760/530, loss: 0.0025694086216390133
2023-01-24 08:41:38.785960: step: 1764/530, loss: 0.0025392230600118637
2023-01-24 08:41:39.837996: step: 1768/530, loss: 0.0021785683929920197
2023-01-24 08:41:40.904084: step: 1772/530, loss: 0.0007225180743262172
2023-01-24 08:41:41.957985: step: 1776/530, loss: 0.0017456581117585301
2023-01-24 08:41:43.006157: step: 1780/530, loss: 0.00014750612899661064
2023-01-24 08:41:44.065302: step: 1784/530, loss: 0.023750416934490204
2023-01-24 08:41:45.127364: step: 1788/530, loss: 0.010610049590468407
2023-01-24 08:41:46.224446: step: 1792/530, loss: 0.002239265711978078
2023-01-24 08:41:47.284312: step: 1796/530, loss: 0.0002765243989415467
2023-01-24 08:41:48.344266: step: 1800/530, loss: 0.0009584600920788944
2023-01-24 08:41:49.400195: step: 1804/530, loss: 0.0013351335655897856
2023-01-24 08:41:50.454483: step: 1808/530, loss: 0.0002709985710680485
2023-01-24 08:41:51.524952: step: 1812/530, loss: 0.008790990337729454
2023-01-24 08:41:52.578557: step: 1816/530, loss: 0.0031469326931983232
2023-01-24 08:41:53.615489: step: 1820/530, loss: 0.0008656151476316154
2023-01-24 08:41:54.670363: step: 1824/530, loss: 0.0007396457949653268
2023-01-24 08:41:55.720771: step: 1828/530, loss: 9.953258995665237e-05
2023-01-24 08:41:56.769390: step: 1832/530, loss: 0.017821967601776123
2023-01-24 08:41:57.822144: step: 1836/530, loss: 0.00010098525672219694
2023-01-24 08:41:58.903260: step: 1840/530, loss: 0.0051336647011339664
2023-01-24 08:41:59.966785: step: 1844/530, loss: 0.02245226874947548
2023-01-24 08:42:01.031695: step: 1848/530, loss: 0.006239595822989941
2023-01-24 08:42:02.103460: step: 1852/530, loss: 0.003103002905845642
2023-01-24 08:42:03.142990: step: 1856/530, loss: 0.012939448468387127
2023-01-24 08:42:04.206746: step: 1860/530, loss: 0.003480520797893405
2023-01-24 08:42:05.265632: step: 1864/530, loss: 0.005201444961130619
2023-01-24 08:42:06.324680: step: 1868/530, loss: 1.646712689762353e-06
2023-01-24 08:42:07.391812: step: 1872/530, loss: 0.0019753824453800917
2023-01-24 08:42:08.444706: step: 1876/530, loss: 0.0007966823759488761
2023-01-24 08:42:09.500526: step: 1880/530, loss: 0.004779266193509102
2023-01-24 08:42:10.550532: step: 1884/530, loss: 1.5865351087995805e-05
2023-01-24 08:42:11.613661: step: 1888/530, loss: 0.0030656461603939533
2023-01-24 08:42:12.659610: step: 1892/530, loss: 0.0031413172837346792
2023-01-24 08:42:13.731540: step: 1896/530, loss: 0.0026001152582466602
2023-01-24 08:42:14.782511: step: 1900/530, loss: 0.012475541792809963
2023-01-24 08:42:15.837690: step: 1904/530, loss: 0.002798421774059534
2023-01-24 08:42:16.908108: step: 1908/530, loss: 0.0011059010867029428
2023-01-24 08:42:17.956203: step: 1912/530, loss: 0.0032019491773098707
2023-01-24 08:42:19.020117: step: 1916/530, loss: 0.0014143269509077072
2023-01-24 08:42:20.083997: step: 1920/530, loss: 0.00516804214566946
2023-01-24 08:42:21.121367: step: 1924/530, loss: 0.0004980072844773531
2023-01-24 08:42:22.178175: step: 1928/530, loss: 0.0015539845917373896
2023-01-24 08:42:23.241956: step: 1932/530, loss: 0.007791064213961363
2023-01-24 08:42:24.304519: step: 1936/530, loss: 0.0029779367614537477
2023-01-24 08:42:25.350218: step: 1940/530, loss: 0.0002129616477759555
2023-01-24 08:42:26.401378: step: 1944/530, loss: 0.007697421591728926
2023-01-24 08:42:27.449353: step: 1948/530, loss: 8.336954124388285e-06
2023-01-24 08:42:28.495154: step: 1952/530, loss: 0.0
2023-01-24 08:42:29.573214: step: 1956/530, loss: 0.0016274317167699337
2023-01-24 08:42:30.621073: step: 1960/530, loss: 0.00016795731789898127
2023-01-24 08:42:31.678241: step: 1964/530, loss: 0.001051002531312406
2023-01-24 08:42:32.729670: step: 1968/530, loss: 5.956008317298256e-05
2023-01-24 08:42:33.772527: step: 1972/530, loss: 1.7269834643229842e-05
2023-01-24 08:42:34.818532: step: 1976/530, loss: 0.010293925181031227
2023-01-24 08:42:35.883375: step: 1980/530, loss: 2.021647378569469e-05
2023-01-24 08:42:36.954186: step: 1984/530, loss: 0.0010774305555969477
2023-01-24 08:42:37.997019: step: 1988/530, loss: 0.004185184836387634
2023-01-24 08:42:39.046776: step: 1992/530, loss: 0.0008530158083885908
2023-01-24 08:42:40.085889: step: 1996/530, loss: 0.00020995458180550486
2023-01-24 08:42:41.142237: step: 2000/530, loss: 0.0014600830618292093
2023-01-24 08:42:42.187608: step: 2004/530, loss: 0.010365885682404041
2023-01-24 08:42:43.263183: step: 2008/530, loss: 0.003824816783890128
2023-01-24 08:42:44.314315: step: 2012/530, loss: 0.00023553035862278193
2023-01-24 08:42:45.373491: step: 2016/530, loss: 0.0018162557389587164
2023-01-24 08:42:46.438300: step: 2020/530, loss: 1.6719199265935458e-05
2023-01-24 08:42:47.490314: step: 2024/530, loss: 0.002557012252509594
2023-01-24 08:42:48.550518: step: 2028/530, loss: 0.001878247712738812
2023-01-24 08:42:49.597644: step: 2032/530, loss: 0.0002744736848399043
2023-01-24 08:42:50.666579: step: 2036/530, loss: 0.0069994451478123665
2023-01-24 08:42:51.734297: step: 2040/530, loss: 0.00042627903167158365
2023-01-24 08:42:52.810181: step: 2044/530, loss: 0.0028313985094428062
2023-01-24 08:42:53.901822: step: 2048/530, loss: 0.008968052454292774
2023-01-24 08:42:54.944230: step: 2052/530, loss: 0.001041926210746169
2023-01-24 08:42:56.001139: step: 2056/530, loss: 0.0017015936318784952
2023-01-24 08:42:57.050583: step: 2060/530, loss: 2.1103512608533492e-06
2023-01-24 08:42:58.115440: step: 2064/530, loss: 0.0004375509452074766
2023-01-24 08:42:59.183016: step: 2068/530, loss: 0.0010493847075849771
2023-01-24 08:43:00.242965: step: 2072/530, loss: 0.00040845919284038246
2023-01-24 08:43:01.301013: step: 2076/530, loss: 0.0014651058008894324
2023-01-24 08:43:02.389358: step: 2080/530, loss: 0.0030638158787041903
2023-01-24 08:43:03.447885: step: 2084/530, loss: 0.00020849764405284077
2023-01-24 08:43:04.508012: step: 2088/530, loss: 0.00010747854685178027
2023-01-24 08:43:05.558420: step: 2092/530, loss: 0.0007673745276406407
2023-01-24 08:43:06.616053: step: 2096/530, loss: 9.36534779611975e-05
2023-01-24 08:43:07.687640: step: 2100/530, loss: 0.00384254171513021
2023-01-24 08:43:08.748401: step: 2104/530, loss: 0.013815202750265598
2023-01-24 08:43:09.828932: step: 2108/530, loss: 0.0030671143904328346
2023-01-24 08:43:10.900945: step: 2112/530, loss: 0.00277753546833992
2023-01-24 08:43:11.962382: step: 2116/530, loss: 0.007929054088890553
2023-01-24 08:43:13.010376: step: 2120/530, loss: 1.8626433728741176e-08
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38361906401679124, 'r': 0.33630361968834455, 'f1': 0.3584064865030487}, 'combined': 0.26408899005487796, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.4025019091031585, 'r': 0.30109233719924583, 'f1': 0.3444890039278147}, 'combined': 0.22846939120601178, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34921144859813086, 'r': 0.2830729166666667, 'f1': 0.3126830543933054}, 'combined': 0.20845536959553693, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40010530993483595, 'r': 0.29661786385307476, 'f1': 0.34067585754014346}, 'combined': 0.22233582281567255, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37091497026618137, 'r': 0.3350199731436477, 'f1': 0.35205488703230775}, 'combined': 0.25940886412906883, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3967576861280018, 'r': 0.3088183201983321, 'f1': 0.3473078479348331}, 'combined': 0.23033888360444887, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 08:45:41.725176: step: 4/530, loss: 0.0003250110021326691
2023-01-24 08:45:42.765355: step: 8/530, loss: 0.00010327000927645713
2023-01-24 08:45:43.809234: step: 12/530, loss: 0.0029094081837683916
2023-01-24 08:45:44.895929: step: 16/530, loss: 0.0
2023-01-24 08:45:45.932743: step: 20/530, loss: 0.00045091984793543816
2023-01-24 08:45:46.989085: step: 24/530, loss: 0.00033032710780389607
2023-01-24 08:45:48.029528: step: 28/530, loss: 0.0015701358206570148
2023-01-24 08:45:49.075584: step: 32/530, loss: 0.0036558376159518957
2023-01-24 08:45:50.122612: step: 36/530, loss: 2.623400359880179e-05
2023-01-24 08:45:51.182679: step: 40/530, loss: 0.00898011028766632
2023-01-24 08:45:52.218456: step: 44/530, loss: 0.0030468327458947897
2023-01-24 08:45:53.271265: step: 48/530, loss: 0.0067582339979708195
2023-01-24 08:45:54.311451: step: 52/530, loss: 0.0015654424205422401
2023-01-24 08:45:55.361823: step: 56/530, loss: 6.553632556460798e-05
2023-01-24 08:45:56.422771: step: 60/530, loss: 0.001344228396192193
2023-01-24 08:45:57.485955: step: 64/530, loss: 0.006579705514013767
2023-01-24 08:45:58.541801: step: 68/530, loss: 0.003154532518237829
2023-01-24 08:45:59.589305: step: 72/530, loss: 0.0008696566219441593
2023-01-24 08:46:00.636926: step: 76/530, loss: 0.033768150955438614
2023-01-24 08:46:01.673602: step: 80/530, loss: 7.055199375827215e-07
2023-01-24 08:46:02.707584: step: 84/530, loss: 0.00012695426994469017
2023-01-24 08:46:03.753990: step: 88/530, loss: 0.00019828276708722115
2023-01-24 08:46:04.816411: step: 92/530, loss: 9.579466131981462e-05
2023-01-24 08:46:05.883631: step: 96/530, loss: 0.00297187315300107
2023-01-24 08:46:06.931788: step: 100/530, loss: 0.0022006661165505648
2023-01-24 08:46:07.984036: step: 104/530, loss: 0.007217789068818092
2023-01-24 08:46:09.047893: step: 108/530, loss: 4.5530872739618644e-05
2023-01-24 08:46:10.089290: step: 112/530, loss: 1.4114721125224605e-05
2023-01-24 08:46:11.159013: step: 116/530, loss: 0.020827410742640495
2023-01-24 08:46:12.210961: step: 120/530, loss: 0.00043991932761855423
2023-01-24 08:46:13.284425: step: 124/530, loss: 0.008572726510465145
2023-01-24 08:46:14.329588: step: 128/530, loss: 0.0016485165106132627
2023-01-24 08:46:15.374471: step: 132/530, loss: 0.001300851465202868
2023-01-24 08:46:16.447982: step: 136/530, loss: 0.010175375267863274
2023-01-24 08:46:17.516169: step: 140/530, loss: 0.004779119044542313
2023-01-24 08:46:18.573997: step: 144/530, loss: 0.0004490238206926733
2023-01-24 08:46:19.632126: step: 148/530, loss: 0.0074737402610480785
2023-01-24 08:46:20.671204: step: 152/530, loss: 0.0009050205117091537
2023-01-24 08:46:21.722450: step: 156/530, loss: 0.0025042006745934486
2023-01-24 08:46:22.794671: step: 160/530, loss: 0.00015788176096975803
2023-01-24 08:46:23.855829: step: 164/530, loss: 0.004179377108812332
2023-01-24 08:46:24.931436: step: 168/530, loss: 0.006657128222286701
2023-01-24 08:46:25.999453: step: 172/530, loss: 0.0011968639446422458
2023-01-24 08:46:27.052016: step: 176/530, loss: 0.0019788455683737993
2023-01-24 08:46:28.111468: step: 180/530, loss: 0.004991799592971802
2023-01-24 08:46:29.165880: step: 184/530, loss: 0.003967749420553446
2023-01-24 08:46:30.216699: step: 188/530, loss: 0.000524609989952296
2023-01-24 08:46:31.267301: step: 192/530, loss: 0.0030326517298817635
2023-01-24 08:46:32.329824: step: 196/530, loss: 0.008878742344677448
2023-01-24 08:46:33.394506: step: 200/530, loss: 1.5498861102969386e-05
2023-01-24 08:46:34.446105: step: 204/530, loss: 0.0052151451818645
2023-01-24 08:46:35.496965: step: 208/530, loss: 0.0016239526448771358
2023-01-24 08:46:36.556238: step: 212/530, loss: 0.011361966840922832
2023-01-24 08:46:37.613582: step: 216/530, loss: 0.0081169493496418
2023-01-24 08:46:38.687924: step: 220/530, loss: 8.157993579516187e-05
2023-01-24 08:46:39.741281: step: 224/530, loss: 0.0002733671572059393
2023-01-24 08:46:40.806529: step: 228/530, loss: 0.0023612172808498144
2023-01-24 08:46:41.862817: step: 232/530, loss: 0.00019490058184601367
2023-01-24 08:46:42.934577: step: 236/530, loss: 0.0022635594941675663
2023-01-24 08:46:43.993013: step: 240/530, loss: 0.02954304963350296
2023-01-24 08:46:45.052443: step: 244/530, loss: 0.00023685931228101254
2023-01-24 08:46:46.109803: step: 248/530, loss: 0.0036271577700972557
2023-01-24 08:46:47.164591: step: 252/530, loss: 0.00201923749409616
2023-01-24 08:46:48.217542: step: 256/530, loss: 0.0019371494418010116
2023-01-24 08:46:49.283557: step: 260/530, loss: 0.00025146856205537915
2023-01-24 08:46:50.350148: step: 264/530, loss: 0.00024632373242639005
2023-01-24 08:46:51.397900: step: 268/530, loss: 0.012415675446391106
2023-01-24 08:46:52.446891: step: 272/530, loss: 0.0007977241184562445
2023-01-24 08:46:53.503017: step: 276/530, loss: 0.003661759663373232
2023-01-24 08:46:54.551281: step: 280/530, loss: 0.0016316329129040241
2023-01-24 08:46:55.605716: step: 284/530, loss: 0.005037873983383179
2023-01-24 08:46:56.651445: step: 288/530, loss: 0.00019436987349763513
2023-01-24 08:46:57.702853: step: 292/530, loss: 0.0022037222515791655
2023-01-24 08:46:58.754387: step: 296/530, loss: 1.2144417269155383e-05
2023-01-24 08:46:59.820250: step: 300/530, loss: 0.011175122112035751
2023-01-24 08:47:00.887448: step: 304/530, loss: 0.00039242859929800034
2023-01-24 08:47:01.949398: step: 308/530, loss: 0.004104190971702337
2023-01-24 08:47:03.047065: step: 312/530, loss: 0.0014982802094891667
2023-01-24 08:47:04.102005: step: 316/530, loss: 0.0002822606184054166
2023-01-24 08:47:05.167521: step: 320/530, loss: 0.0031672792974859476
2023-01-24 08:47:06.227153: step: 324/530, loss: 0.0014289245009422302
2023-01-24 08:47:07.280129: step: 328/530, loss: 0.0023983647115528584
2023-01-24 08:47:08.334826: step: 332/530, loss: 0.00016546070401091129
2023-01-24 08:47:09.391735: step: 336/530, loss: 0.0037717868108302355
2023-01-24 08:47:10.447330: step: 340/530, loss: 4.238985184201738e-06
2023-01-24 08:47:11.502364: step: 344/530, loss: 0.0024787706788629293
2023-01-24 08:47:12.561810: step: 348/530, loss: 0.001191026996821165
2023-01-24 08:47:13.635424: step: 352/530, loss: 0.0031788628548383713
2023-01-24 08:47:14.700364: step: 356/530, loss: 0.00018072384409606457
2023-01-24 08:47:15.759191: step: 360/530, loss: 0.031905610114336014
2023-01-24 08:47:16.819132: step: 364/530, loss: 0.0008393478346988559
2023-01-24 08:47:17.877431: step: 368/530, loss: 7.809021917637438e-05
2023-01-24 08:47:18.935243: step: 372/530, loss: 0.0009407387115061283
2023-01-24 08:47:19.989665: step: 376/530, loss: 0.0018041894072666764
2023-01-24 08:47:21.037475: step: 380/530, loss: 0.0010646820301190019
2023-01-24 08:47:22.106048: step: 384/530, loss: 0.0005362660740502179
2023-01-24 08:47:23.155224: step: 388/530, loss: 0.0017718817107379436
2023-01-24 08:47:24.229210: step: 392/530, loss: 0.001660363283008337
2023-01-24 08:47:25.291966: step: 396/530, loss: 4.280201028450392e-05
2023-01-24 08:47:26.337953: step: 400/530, loss: 0.0001180175386252813
2023-01-24 08:47:27.420881: step: 404/530, loss: 0.0034996657632291317
2023-01-24 08:47:28.490321: step: 408/530, loss: 0.0009065588237717748
2023-01-24 08:47:29.544256: step: 412/530, loss: 0.00014249492960516363
2023-01-24 08:47:30.596659: step: 416/530, loss: 0.007452043239027262
2023-01-24 08:47:31.664320: step: 420/530, loss: 3.975400613853708e-05
2023-01-24 08:47:32.717302: step: 424/530, loss: 0.0002114443777827546
2023-01-24 08:47:33.772396: step: 428/530, loss: 0.0010021415073424578
2023-01-24 08:47:34.822546: step: 432/530, loss: 0.0009182122303172946
2023-01-24 08:47:35.869707: step: 436/530, loss: 0.0015905495965853333
2023-01-24 08:47:36.933326: step: 440/530, loss: 0.0002427100553177297
2023-01-24 08:47:37.993768: step: 444/530, loss: 0.0030908097978681326
2023-01-24 08:47:39.039179: step: 448/530, loss: 0.008275626227259636
2023-01-24 08:47:40.108319: step: 452/530, loss: 0.0020911593455821276
2023-01-24 08:47:41.164571: step: 456/530, loss: 0.002013309160247445
2023-01-24 08:47:42.217773: step: 460/530, loss: 0.0005033549969084561
2023-01-24 08:47:43.265663: step: 464/530, loss: 0.001824121573008597
2023-01-24 08:47:44.330164: step: 468/530, loss: 0.003075605956837535
2023-01-24 08:47:45.392659: step: 472/530, loss: 0.002276838291436434
2023-01-24 08:47:46.447438: step: 476/530, loss: 0.006126571912318468
2023-01-24 08:47:47.495340: step: 480/530, loss: 0.003306641010567546
2023-01-24 08:47:48.549326: step: 484/530, loss: 0.0016706627793610096
2023-01-24 08:47:49.601139: step: 488/530, loss: 0.0010184097336605191
2023-01-24 08:47:50.636363: step: 492/530, loss: 0.0007417145534418523
2023-01-24 08:47:51.683216: step: 496/530, loss: 0.0032276702113449574
2023-01-24 08:47:52.734150: step: 500/530, loss: 0.0046856035478413105
2023-01-24 08:47:53.787579: step: 504/530, loss: 0.008639886043965816
2023-01-24 08:47:54.828843: step: 508/530, loss: 0.0005481612170115113
2023-01-24 08:47:55.878341: step: 512/530, loss: 0.008955665864050388
2023-01-24 08:47:56.923881: step: 516/530, loss: 0.0035444090608507395
2023-01-24 08:47:57.971525: step: 520/530, loss: 0.0004243760777171701
2023-01-24 08:47:59.019041: step: 524/530, loss: 0.0027096732519567013
2023-01-24 08:48:00.096679: step: 528/530, loss: 0.0042732576839625835
2023-01-24 08:48:01.153756: step: 532/530, loss: 0.002493184059858322
2023-01-24 08:48:02.213321: step: 536/530, loss: 0.0014989409828558564
2023-01-24 08:48:03.278558: step: 540/530, loss: 0.0009775498183444142
2023-01-24 08:48:04.328293: step: 544/530, loss: 0.003676595399156213
2023-01-24 08:48:05.378179: step: 548/530, loss: 0.0009262002422474325
2023-01-24 08:48:06.433174: step: 552/530, loss: 0.0005359672359190881
2023-01-24 08:48:07.483470: step: 556/530, loss: 3.6649249523179606e-05
2023-01-24 08:48:08.551710: step: 560/530, loss: 0.001422971487045288
2023-01-24 08:48:09.595204: step: 564/530, loss: 0.00014482016558758914
2023-01-24 08:48:10.636156: step: 568/530, loss: 8.522219286533073e-05
2023-01-24 08:48:11.695765: step: 572/530, loss: 0.00022604662808589637
2023-01-24 08:48:12.757825: step: 576/530, loss: 7.563818508060649e-05
2023-01-24 08:48:13.824304: step: 580/530, loss: 0.007900391705334187
2023-01-24 08:48:14.890447: step: 584/530, loss: 0.0036498778499662876
2023-01-24 08:48:15.957722: step: 588/530, loss: 0.0059960526414215565
2023-01-24 08:48:17.012139: step: 592/530, loss: 2.7462847356218845e-06
2023-01-24 08:48:18.065241: step: 596/530, loss: 0.001986027229577303
2023-01-24 08:48:19.112651: step: 600/530, loss: 0.0006223671953193843
2023-01-24 08:48:20.178679: step: 604/530, loss: 0.0006608201656490564
2023-01-24 08:48:21.235205: step: 608/530, loss: 0.002817604225128889
2023-01-24 08:48:22.297606: step: 612/530, loss: 0.0049211266450583935
2023-01-24 08:48:23.350150: step: 616/530, loss: 0.0011279383907094598
2023-01-24 08:48:24.402191: step: 620/530, loss: 0.0017556088278070092
2023-01-24 08:48:25.471064: step: 624/530, loss: 0.0036397427320480347
2023-01-24 08:48:26.533929: step: 628/530, loss: 0.0012460562866181135
2023-01-24 08:48:27.581242: step: 632/530, loss: 0.0012989867245778441
2023-01-24 08:48:28.636922: step: 636/530, loss: 0.010031579062342644
2023-01-24 08:48:29.699971: step: 640/530, loss: 0.00268359063193202
2023-01-24 08:48:30.775393: step: 644/530, loss: 0.0002749410050455481
2023-01-24 08:48:31.830121: step: 648/530, loss: 1.8663156708953466e-07
2023-01-24 08:48:32.885672: step: 652/530, loss: 2.0861405403138633e-07
2023-01-24 08:48:33.944781: step: 656/530, loss: 0.0016519913915544748
2023-01-24 08:48:35.009658: step: 660/530, loss: 0.00027360403328202665
2023-01-24 08:48:36.052654: step: 664/530, loss: 0.0020784749649465084
2023-01-24 08:48:37.099080: step: 668/530, loss: 0.001132887788116932
2023-01-24 08:48:38.152701: step: 672/530, loss: 8.980271377367899e-05
2023-01-24 08:48:39.224069: step: 676/530, loss: 0.003592818509787321
2023-01-24 08:48:40.300675: step: 680/530, loss: 0.0014212786918506026
2023-01-24 08:48:41.361652: step: 684/530, loss: 0.00031213992042467
2023-01-24 08:48:42.423265: step: 688/530, loss: 0.007671969477087259
2023-01-24 08:48:43.482403: step: 692/530, loss: 0.0007366955396719277
2023-01-24 08:48:44.541555: step: 696/530, loss: 0.007115547079592943
2023-01-24 08:48:45.596652: step: 700/530, loss: 0.001698613865301013
2023-01-24 08:48:46.671456: step: 704/530, loss: 0.002809738740324974
2023-01-24 08:48:47.742202: step: 708/530, loss: 2.667678563739173e-05
2023-01-24 08:48:48.795335: step: 712/530, loss: 0.0002682785561773926
2023-01-24 08:48:49.854062: step: 716/530, loss: 0.003121049841865897
2023-01-24 08:48:50.905345: step: 720/530, loss: 0.0020823145750910044
2023-01-24 08:48:51.972939: step: 724/530, loss: 0.001403205911628902
2023-01-24 08:48:53.051279: step: 728/530, loss: 0.0034690317697823048
2023-01-24 08:48:54.100578: step: 732/530, loss: 0.0003169336123391986
2023-01-24 08:48:55.170138: step: 736/530, loss: 0.0003119395696558058
2023-01-24 08:48:56.216130: step: 740/530, loss: 0.0017081854166463017
2023-01-24 08:48:57.280379: step: 744/530, loss: 0.001549523905850947
2023-01-24 08:48:58.342925: step: 748/530, loss: 3.537727388902567e-05
2023-01-24 08:48:59.417523: step: 752/530, loss: 0.004651418887078762
2023-01-24 08:49:00.479001: step: 756/530, loss: 0.005748758092522621
2023-01-24 08:49:01.542360: step: 760/530, loss: 0.003338283160701394
2023-01-24 08:49:02.622524: step: 764/530, loss: 0.002226133830845356
2023-01-24 08:49:03.694463: step: 768/530, loss: 3.279270822531544e-05
2023-01-24 08:49:04.756382: step: 772/530, loss: 0.0009650117135606706
2023-01-24 08:49:05.821784: step: 776/530, loss: 0.05621209368109703
2023-01-24 08:49:06.878363: step: 780/530, loss: 0.007143400609493256
2023-01-24 08:49:07.940333: step: 784/530, loss: 0.0015492329839617014
2023-01-24 08:49:09.013571: step: 788/530, loss: 4.681041173171252e-05
2023-01-24 08:49:10.072787: step: 792/530, loss: 0.0003306333674117923
2023-01-24 08:49:11.130767: step: 796/530, loss: 0.00036596370046027005
2023-01-24 08:49:12.184917: step: 800/530, loss: 0.00041176885133609176
2023-01-24 08:49:13.235686: step: 804/530, loss: 0.0019819489680230618
2023-01-24 08:49:14.292613: step: 808/530, loss: 0.00010756034316727892
2023-01-24 08:49:15.358736: step: 812/530, loss: 0.007222232408821583
2023-01-24 08:49:16.411240: step: 816/530, loss: 0.0004381787439342588
2023-01-24 08:49:17.467710: step: 820/530, loss: 0.0014265939826145768
2023-01-24 08:49:18.533146: step: 824/530, loss: 0.0034175862092524767
2023-01-24 08:49:19.596750: step: 828/530, loss: 0.0007666954770684242
2023-01-24 08:49:20.657796: step: 832/530, loss: 0.0026328640524297953
2023-01-24 08:49:21.737402: step: 836/530, loss: 0.0005103026051074266
2023-01-24 08:49:22.782627: step: 840/530, loss: 0.0021974763367325068
2023-01-24 08:49:23.844765: step: 844/530, loss: 0.0075005535036325455
2023-01-24 08:49:24.909650: step: 848/530, loss: 0.006352907046675682
2023-01-24 08:49:25.953451: step: 852/530, loss: 0.001549455919303
2023-01-24 08:49:27.017926: step: 856/530, loss: 0.0029803344514220953
2023-01-24 08:49:28.066873: step: 860/530, loss: 0.0010252937208861113
2023-01-24 08:49:29.130434: step: 864/530, loss: 6.62251768517308e-05
2023-01-24 08:49:30.179583: step: 868/530, loss: 0.0002176843408960849
2023-01-24 08:49:31.247981: step: 872/530, loss: 0.003625124227255583
2023-01-24 08:49:32.325217: step: 876/530, loss: 0.0008013990591280162
2023-01-24 08:49:33.382665: step: 880/530, loss: 0.00041871133726090193
2023-01-24 08:49:34.441426: step: 884/530, loss: 0.00020458332437556237
2023-01-24 08:49:35.518779: step: 888/530, loss: 5.5012726079439744e-05
2023-01-24 08:49:36.577697: step: 892/530, loss: 0.00031431164825335145
2023-01-24 08:49:37.648929: step: 896/530, loss: 0.0017172252992168069
2023-01-24 08:49:38.713333: step: 900/530, loss: 0.0024885099846869707
2023-01-24 08:49:39.769716: step: 904/530, loss: 0.0006603936199098825
2023-01-24 08:49:40.819523: step: 908/530, loss: 0.0005029587191529572
2023-01-24 08:49:41.886389: step: 912/530, loss: 0.0034463279880583286
2023-01-24 08:49:42.936924: step: 916/530, loss: 0.0029321303591132164
2023-01-24 08:49:43.988674: step: 920/530, loss: 0.007881742902100086
2023-01-24 08:49:45.056794: step: 924/530, loss: 0.0015492836246266961
2023-01-24 08:49:46.124810: step: 928/530, loss: 0.003039595205336809
2023-01-24 08:49:47.196033: step: 932/530, loss: 0.005576764233410358
2023-01-24 08:49:48.250389: step: 936/530, loss: 0.0055366335436701775
2023-01-24 08:49:49.303513: step: 940/530, loss: 0.0007363850600086153
2023-01-24 08:49:50.363478: step: 944/530, loss: 0.007611500099301338
2023-01-24 08:49:51.411992: step: 948/530, loss: 0.001019624643959105
2023-01-24 08:49:52.476236: step: 952/530, loss: 0.001155313802883029
2023-01-24 08:49:53.527495: step: 956/530, loss: 0.002034812467172742
2023-01-24 08:49:54.578016: step: 960/530, loss: 0.0004842204798478633
2023-01-24 08:49:55.649679: step: 964/530, loss: 6.876084626128431e-06
2023-01-24 08:49:56.702010: step: 968/530, loss: 0.0028653740882873535
2023-01-24 08:49:57.757838: step: 972/530, loss: 0.0021431182976812124
2023-01-24 08:49:58.796292: step: 976/530, loss: 0.00021729804575443268
2023-01-24 08:49:59.855059: step: 980/530, loss: 0.0007025641389191151
2023-01-24 08:50:00.923918: step: 984/530, loss: 0.005403316579759121
2023-01-24 08:50:01.981069: step: 988/530, loss: 7.84470648795832e-06
2023-01-24 08:50:03.054880: step: 992/530, loss: 0.003874309593811631
2023-01-24 08:50:04.110226: step: 996/530, loss: 0.0016382955946028233
2023-01-24 08:50:05.176120: step: 1000/530, loss: 0.0020589837804436684
2023-01-24 08:50:06.238075: step: 1004/530, loss: 0.0018492179224267602
2023-01-24 08:50:07.289093: step: 1008/530, loss: 5.34553182660602e-05
2023-01-24 08:50:08.350324: step: 1012/530, loss: 0.0030979823786765337
2023-01-24 08:50:09.394497: step: 1016/530, loss: 0.00023496735957451165
2023-01-24 08:50:10.455950: step: 1020/530, loss: 0.0012345234863460064
2023-01-24 08:50:11.503603: step: 1024/530, loss: 0.002092586364597082
2023-01-24 08:50:12.573351: step: 1028/530, loss: 0.0019468979444354773
2023-01-24 08:50:13.636448: step: 1032/530, loss: 0.001180277089588344
2023-01-24 08:50:14.695051: step: 1036/530, loss: 9.015834802994505e-05
2023-01-24 08:50:15.750683: step: 1040/530, loss: 0.012760174460709095
2023-01-24 08:50:16.825894: step: 1044/530, loss: 0.0012736788485199213
2023-01-24 08:50:17.916767: step: 1048/530, loss: 0.0026498460210859776
2023-01-24 08:50:18.981417: step: 1052/530, loss: 3.430072183618904e-06
2023-01-24 08:50:20.021081: step: 1056/530, loss: 0.002392443595454097
2023-01-24 08:50:21.086949: step: 1060/530, loss: 0.004322984255850315
2023-01-24 08:50:22.145422: step: 1064/530, loss: 0.0024266396649181843
2023-01-24 08:50:23.196590: step: 1068/530, loss: 0.00026486036949791014
2023-01-24 08:50:24.242394: step: 1072/530, loss: 0.0005378081696107984
2023-01-24 08:50:25.293694: step: 1076/530, loss: 6.746695726178586e-05
2023-01-24 08:50:26.351948: step: 1080/530, loss: 0.0024029582273215055
2023-01-24 08:50:27.424153: step: 1084/530, loss: 0.000427486898843199
2023-01-24 08:50:28.479490: step: 1088/530, loss: 2.8370410291245207e-05
2023-01-24 08:50:29.518434: step: 1092/530, loss: 0.00019718451949302107
2023-01-24 08:50:30.584986: step: 1096/530, loss: 0.0018824022263288498
2023-01-24 08:50:31.633755: step: 1100/530, loss: 5.85204288654495e-05
2023-01-24 08:50:32.674770: step: 1104/530, loss: 2.7342852604306245e-07
2023-01-24 08:50:33.735018: step: 1108/530, loss: 0.006888635456562042
2023-01-24 08:50:34.802329: step: 1112/530, loss: 0.000852369936183095
2023-01-24 08:50:35.844032: step: 1116/530, loss: 0.0003036827838514
2023-01-24 08:50:36.908886: step: 1120/530, loss: 0.0032860341016203165
2023-01-24 08:50:37.977324: step: 1124/530, loss: 0.01569513976573944
2023-01-24 08:50:39.022253: step: 1128/530, loss: 0.0033217757008969784
2023-01-24 08:50:40.098804: step: 1132/530, loss: 0.001954219304025173
2023-01-24 08:50:41.160917: step: 1136/530, loss: 0.006013811100274324
2023-01-24 08:50:42.234155: step: 1140/530, loss: 0.013793780468404293
2023-01-24 08:50:43.296218: step: 1144/530, loss: 0.0009063066099770367
2023-01-24 08:50:44.363049: step: 1148/530, loss: 0.003874919842928648
2023-01-24 08:50:45.440025: step: 1152/530, loss: 0.004496643785387278
2023-01-24 08:50:46.488961: step: 1156/530, loss: 0.001483607105910778
2023-01-24 08:50:47.544388: step: 1160/530, loss: 0.020650101825594902
2023-01-24 08:50:48.590250: step: 1164/530, loss: 0.00012711789167951792
2023-01-24 08:50:49.649840: step: 1168/530, loss: 0.0057564121671020985
2023-01-24 08:50:50.719984: step: 1172/530, loss: 9.468714415561408e-05
2023-01-24 08:50:51.781707: step: 1176/530, loss: 0.0037629269063472748
2023-01-24 08:50:52.846429: step: 1180/530, loss: 0.0032165481243282557
2023-01-24 08:50:53.898165: step: 1184/530, loss: 0.0007219966500997543
2023-01-24 08:50:54.945222: step: 1188/530, loss: 0.0012121982872486115
2023-01-24 08:50:56.001450: step: 1192/530, loss: 0.0017229666700586677
2023-01-24 08:50:57.057764: step: 1196/530, loss: 4.226937107887352e-06
2023-01-24 08:50:58.120663: step: 1200/530, loss: 0.0009013205417431891
2023-01-24 08:50:59.174657: step: 1204/530, loss: 0.0018238970078527927
2023-01-24 08:51:00.236374: step: 1208/530, loss: 0.01084953173995018
2023-01-24 08:51:01.290438: step: 1212/530, loss: 9.311814210377634e-05
2023-01-24 08:51:02.336386: step: 1216/530, loss: 0.00024655534070916474
2023-01-24 08:51:03.386672: step: 1220/530, loss: 0.007411518599838018
2023-01-24 08:51:04.447151: step: 1224/530, loss: 0.004581660032272339
2023-01-24 08:51:05.538453: step: 1228/530, loss: 0.0025393676478415728
2023-01-24 08:51:06.603246: step: 1232/530, loss: 0.00494487676769495
2023-01-24 08:51:07.670305: step: 1236/530, loss: 0.00782996416091919
2023-01-24 08:51:08.725147: step: 1240/530, loss: 0.0075223809108138084
2023-01-24 08:51:09.776473: step: 1244/530, loss: 0.0014412979362532496
2023-01-24 08:51:10.829607: step: 1248/530, loss: 0.0028542662039399147
2023-01-24 08:51:11.903837: step: 1252/530, loss: 0.0012522474862635136
2023-01-24 08:51:12.965888: step: 1256/530, loss: 0.0010438697645440698
2023-01-24 08:51:14.034321: step: 1260/530, loss: 0.0018528149230405688
2023-01-24 08:51:15.101713: step: 1264/530, loss: 0.0036280627828091383
2023-01-24 08:51:16.168956: step: 1268/530, loss: 0.005273927003145218
2023-01-24 08:51:17.236276: step: 1272/530, loss: 0.015992240980267525
2023-01-24 08:51:18.300573: step: 1276/530, loss: 0.005024413578212261
2023-01-24 08:51:19.359814: step: 1280/530, loss: 0.01363756787031889
2023-01-24 08:51:20.427014: step: 1284/530, loss: 0.009442714974284172
2023-01-24 08:51:21.487057: step: 1288/530, loss: 0.0003609588020481169
2023-01-24 08:51:22.536468: step: 1292/530, loss: 0.0020176107063889503
2023-01-24 08:51:23.601218: step: 1296/530, loss: 0.00019862435874529183
2023-01-24 08:51:24.649113: step: 1300/530, loss: 0.00012516188144218177
2023-01-24 08:51:25.711105: step: 1304/530, loss: 0.0028694551438093185
2023-01-24 08:51:26.747382: step: 1308/530, loss: 0.0004534932959359139
2023-01-24 08:51:27.806565: step: 1312/530, loss: 0.0034714879002422094
2023-01-24 08:51:28.911317: step: 1316/530, loss: 0.003963474649935961
2023-01-24 08:51:29.961240: step: 1320/530, loss: 0.005531396716833115
2023-01-24 08:51:31.010635: step: 1324/530, loss: 0.0017692631809040904
2023-01-24 08:51:32.098251: step: 1328/530, loss: 0.004140998236835003
2023-01-24 08:51:33.139880: step: 1332/530, loss: 0.00028991670114919543
2023-01-24 08:51:34.199473: step: 1336/530, loss: 0.0005217614816501737
2023-01-24 08:51:35.278681: step: 1340/530, loss: 0.001401195302605629
2023-01-24 08:51:36.332170: step: 1344/530, loss: 0.0015678979689255357
2023-01-24 08:51:37.409224: step: 1348/530, loss: 0.019129017367959023
2023-01-24 08:51:38.470760: step: 1352/530, loss: 0.005313987378031015
2023-01-24 08:51:39.527970: step: 1356/530, loss: 0.00037107185926288366
2023-01-24 08:51:40.601621: step: 1360/530, loss: 0.013496131636202335
2023-01-24 08:51:41.675197: step: 1364/530, loss: 0.013313413597643375
2023-01-24 08:51:42.713249: step: 1368/530, loss: 0.0002980967110488564
2023-01-24 08:51:43.788475: step: 1372/530, loss: 0.003133540041744709
2023-01-24 08:51:44.830605: step: 1376/530, loss: 0.0021681066136807203
2023-01-24 08:51:45.886342: step: 1380/530, loss: 0.0034840391017496586
2023-01-24 08:51:46.956073: step: 1384/530, loss: 0.001007427810691297
2023-01-24 08:51:48.012488: step: 1388/530, loss: 0.00429577799513936
2023-01-24 08:51:49.072523: step: 1392/530, loss: 0.0018511416856199503
2023-01-24 08:51:50.117896: step: 1396/530, loss: 0.0013401811011135578
2023-01-24 08:51:51.168650: step: 1400/530, loss: 0.0040626623667776585
2023-01-24 08:51:52.237309: step: 1404/530, loss: 0.018888691440224648
2023-01-24 08:51:53.276911: step: 1408/530, loss: 1.6510579371242784e-05
2023-01-24 08:51:54.340846: step: 1412/530, loss: 4.73581712867599e-05
2023-01-24 08:51:55.390701: step: 1416/530, loss: 0.0003874922695104033
2023-01-24 08:51:56.458472: step: 1420/530, loss: 0.0016836185241118073
2023-01-24 08:51:57.506839: step: 1424/530, loss: 0.003717202227562666
2023-01-24 08:51:58.577784: step: 1428/530, loss: 0.0021370332688093185
2023-01-24 08:51:59.627083: step: 1432/530, loss: 0.000662588223349303
2023-01-24 08:52:00.678490: step: 1436/530, loss: 0.00035708450013771653
2023-01-24 08:52:01.740078: step: 1440/530, loss: 0.0006263340474106371
2023-01-24 08:52:02.809984: step: 1444/530, loss: 8.564797462895513e-05
2023-01-24 08:52:03.852486: step: 1448/530, loss: 0.00959504023194313
2023-01-24 08:52:04.909475: step: 1452/530, loss: 8.74536344781518e-05
2023-01-24 08:52:05.963093: step: 1456/530, loss: 0.0033525987528264523
2023-01-24 08:52:07.016254: step: 1460/530, loss: 0.0035980045795440674
2023-01-24 08:52:08.065552: step: 1464/530, loss: 0.0029600048437714577
2023-01-24 08:52:09.148586: step: 1468/530, loss: 0.004253932274878025
2023-01-24 08:52:10.221199: step: 1472/530, loss: 0.05450672283768654
2023-01-24 08:52:11.281058: step: 1476/530, loss: 0.0010646131122484803
2023-01-24 08:52:12.329706: step: 1480/530, loss: 0.0006881079752929509
2023-01-24 08:52:13.371830: step: 1484/530, loss: 0.01149194035679102
2023-01-24 08:52:14.429709: step: 1488/530, loss: 0.00024345077690668404
2023-01-24 08:52:15.484740: step: 1492/530, loss: 0.0002043069980572909
2023-01-24 08:52:16.532369: step: 1496/530, loss: 0.0013637623051181436
2023-01-24 08:52:17.586759: step: 1500/530, loss: 0.014276815578341484
2023-01-24 08:52:18.657496: step: 1504/530, loss: 0.04338778555393219
2023-01-24 08:52:19.710671: step: 1508/530, loss: 3.986604860983789e-05
2023-01-24 08:52:20.778876: step: 1512/530, loss: 7.127715070964769e-05
2023-01-24 08:52:21.853905: step: 1516/530, loss: 0.0028541740030050278
2023-01-24 08:52:22.930059: step: 1520/530, loss: 0.00022994137543719262
2023-01-24 08:52:23.978061: step: 1524/530, loss: 0.00358932395465672
2023-01-24 08:52:25.031863: step: 1528/530, loss: 0.004346812143921852
2023-01-24 08:52:26.103868: step: 1532/530, loss: 0.004899824503809214
2023-01-24 08:52:27.165521: step: 1536/530, loss: 0.006737318355590105
2023-01-24 08:52:28.227235: step: 1540/530, loss: 0.004996676463633776
2023-01-24 08:52:29.292391: step: 1544/530, loss: 0.002813290571793914
2023-01-24 08:52:30.357254: step: 1548/530, loss: 0.006961551960557699
2023-01-24 08:52:31.407537: step: 1552/530, loss: 4.238111068843864e-05
2023-01-24 08:52:32.454298: step: 1556/530, loss: 0.010405754670500755
2023-01-24 08:52:33.518893: step: 1560/530, loss: 0.0030532919336110353
2023-01-24 08:52:34.582360: step: 1564/530, loss: 0.0027179024182260036
2023-01-24 08:52:35.664896: step: 1568/530, loss: 0.001679647364653647
2023-01-24 08:52:36.719531: step: 1572/530, loss: 0.0047917854972183704
2023-01-24 08:52:37.778564: step: 1576/530, loss: 0.00747528625652194
2023-01-24 08:52:38.865296: step: 1580/530, loss: 0.003177801612764597
2023-01-24 08:52:39.914790: step: 1584/530, loss: 2.820929694280494e-05
2023-01-24 08:52:40.975642: step: 1588/530, loss: 0.00019561413500923663
2023-01-24 08:52:42.027590: step: 1592/530, loss: 0.00038614243385381997
2023-01-24 08:52:43.110757: step: 1596/530, loss: 0.0035345363430678844
2023-01-24 08:52:44.162513: step: 1600/530, loss: 0.00246001360937953
2023-01-24 08:52:45.218414: step: 1604/530, loss: 0.0001315363188041374
2023-01-24 08:52:46.277522: step: 1608/530, loss: 0.0019230565521866083
2023-01-24 08:52:47.342149: step: 1612/530, loss: 0.0019322532461956143
2023-01-24 08:52:48.396860: step: 1616/530, loss: 0.0010026090312749147
2023-01-24 08:52:49.465833: step: 1620/530, loss: 0.004481487907469273
2023-01-24 08:52:50.520158: step: 1624/530, loss: 2.8371416192385368e-05
2023-01-24 08:52:51.588466: step: 1628/530, loss: 0.0006140859331935644
2023-01-24 08:52:52.652438: step: 1632/530, loss: 0.0018426628084853292
2023-01-24 08:52:53.724613: step: 1636/530, loss: 0.0007340333540923893
2023-01-24 08:52:54.789276: step: 1640/530, loss: 0.0005867245490662754
2023-01-24 08:52:55.846438: step: 1644/530, loss: 0.004103363025933504
2023-01-24 08:52:56.901299: step: 1648/530, loss: 0.0010689737973734736
2023-01-24 08:52:57.955044: step: 1652/530, loss: 0.0013210683828219771
2023-01-24 08:52:59.009152: step: 1656/530, loss: 0.004026887938380241
2023-01-24 08:53:00.076781: step: 1660/530, loss: 0.005119039677083492
2023-01-24 08:53:01.129557: step: 1664/530, loss: 0.0027865655720233917
2023-01-24 08:53:02.199871: step: 1668/530, loss: 0.004173601046204567
2023-01-24 08:53:03.252666: step: 1672/530, loss: 0.00014177977573126554
2023-01-24 08:53:04.294805: step: 1676/530, loss: 7.248708425322548e-05
2023-01-24 08:53:05.346062: step: 1680/530, loss: 0.0018180040642619133
2023-01-24 08:53:06.408404: step: 1684/530, loss: 0.002683144062757492
2023-01-24 08:53:07.468222: step: 1688/530, loss: 0.002299362327903509
2023-01-24 08:53:08.547853: step: 1692/530, loss: 0.00463888980448246
2023-01-24 08:53:09.607207: step: 1696/530, loss: 0.005600419361144304
2023-01-24 08:53:10.656737: step: 1700/530, loss: 0.00019638679805211723
2023-01-24 08:53:11.715447: step: 1704/530, loss: 0.0021644234657287598
2023-01-24 08:53:12.766905: step: 1708/530, loss: 0.03413008898496628
2023-01-24 08:53:13.821527: step: 1712/530, loss: 0.001362007693387568
2023-01-24 08:53:14.876835: step: 1716/530, loss: 0.0007608101004734635
2023-01-24 08:53:15.952517: step: 1720/530, loss: 0.0023260891903191805
2023-01-24 08:53:17.017196: step: 1724/530, loss: 0.00019812978280242532
2023-01-24 08:53:18.084184: step: 1728/530, loss: 0.00020771523122675717
2023-01-24 08:53:19.128965: step: 1732/530, loss: 0.003942670300602913
2023-01-24 08:53:20.173459: step: 1736/530, loss: 0.0027706718537956476
2023-01-24 08:53:21.253123: step: 1740/530, loss: 0.00036004491266794503
2023-01-24 08:53:22.304007: step: 1744/530, loss: 0.0038998809177428484
2023-01-24 08:53:23.372344: step: 1748/530, loss: 0.0010251781204715371
2023-01-24 08:53:24.422056: step: 1752/530, loss: 0.0075123608112335205
2023-01-24 08:53:25.491777: step: 1756/530, loss: 0.003972136415541172
2023-01-24 08:53:26.562263: step: 1760/530, loss: 0.007886619307100773
2023-01-24 08:53:27.604462: step: 1764/530, loss: 0.006952735595405102
2023-01-24 08:53:28.650243: step: 1768/530, loss: 0.0053995330817997456
2023-01-24 08:53:29.705512: step: 1772/530, loss: 0.010685128159821033
2023-01-24 08:53:30.761174: step: 1776/530, loss: 0.00011691226973198354
2023-01-24 08:53:31.816262: step: 1780/530, loss: 1.5086674238773412e-06
2023-01-24 08:53:32.876640: step: 1784/530, loss: 0.005432500038295984
2023-01-24 08:53:33.935178: step: 1788/530, loss: 3.687410207930952e-05
2023-01-24 08:53:35.010687: step: 1792/530, loss: 0.0005185672198422253
2023-01-24 08:53:36.060698: step: 1796/530, loss: 0.0019357283599674702
2023-01-24 08:53:37.117864: step: 1800/530, loss: 0.01091307494789362
2023-01-24 08:53:38.175564: step: 1804/530, loss: 0.007589819375425577
2023-01-24 08:53:39.229697: step: 1808/530, loss: 0.013362376019358635
2023-01-24 08:53:40.298014: step: 1812/530, loss: 0.0018293482717126608
2023-01-24 08:53:41.354491: step: 1816/530, loss: 0.0003368749166838825
2023-01-24 08:53:42.422624: step: 1820/530, loss: 0.004391562193632126
2023-01-24 08:53:43.481236: step: 1824/530, loss: 0.0012822910211980343
2023-01-24 08:53:44.539966: step: 1828/530, loss: 0.00024131685495376587
2023-01-24 08:53:45.604396: step: 1832/530, loss: 0.010517972521483898
2023-01-24 08:53:46.677724: step: 1836/530, loss: 0.0025146042462438345
2023-01-24 08:53:47.751216: step: 1840/530, loss: 0.001509475172497332
2023-01-24 08:53:48.820046: step: 1844/530, loss: 0.005089438054710627
2023-01-24 08:53:49.878044: step: 1848/530, loss: 8.90941282705171e-06
2023-01-24 08:53:50.932032: step: 1852/530, loss: 0.002184090204536915
2023-01-24 08:53:51.992052: step: 1856/530, loss: 0.0047272187657654285
2023-01-24 08:53:53.039382: step: 1860/530, loss: 9.413125371793285e-05
2023-01-24 08:53:54.095283: step: 1864/530, loss: 0.008647437207400799
2023-01-24 08:53:55.173456: step: 1868/530, loss: 0.0008382656960748136
2023-01-24 08:53:56.219912: step: 1872/530, loss: 6.864711758680642e-05
2023-01-24 08:53:57.263957: step: 1876/530, loss: 0.004007184877991676
2023-01-24 08:53:58.317031: step: 1880/530, loss: 0.0005845247651450336
2023-01-24 08:53:59.368777: step: 1884/530, loss: 0.0008356075850315392
2023-01-24 08:54:00.423304: step: 1888/530, loss: 0.00012236642942298204
2023-01-24 08:54:01.494319: step: 1892/530, loss: 0.0055170198902487755
2023-01-24 08:54:02.557103: step: 1896/530, loss: 0.000331994699081406
2023-01-24 08:54:03.605236: step: 1900/530, loss: 0.000142114789923653
2023-01-24 08:54:04.643309: step: 1904/530, loss: 0.0016532046720385551
2023-01-24 08:54:05.705355: step: 1908/530, loss: 7.965428267198149e-06
2023-01-24 08:54:06.771184: step: 1912/530, loss: 0.004498992580920458
2023-01-24 08:54:07.838946: step: 1916/530, loss: 0.0007155256462283432
2023-01-24 08:54:08.907165: step: 1920/530, loss: 0.00512723159044981
2023-01-24 08:54:09.963628: step: 1924/530, loss: 0.00016985174443107098
2023-01-24 08:54:11.021610: step: 1928/530, loss: 0.005829189904034138
2023-01-24 08:54:12.069895: step: 1932/530, loss: 0.009337147697806358
2023-01-24 08:54:13.132203: step: 1936/530, loss: 0.00381950824521482
2023-01-24 08:54:14.190777: step: 1940/530, loss: 7.528157584602013e-05
2023-01-24 08:54:15.244382: step: 1944/530, loss: 0.0036042584106326103
2023-01-24 08:54:16.315666: step: 1948/530, loss: 7.970676233526319e-05
2023-01-24 08:54:17.374168: step: 1952/530, loss: 0.0019424905767664313
2023-01-24 08:54:18.424238: step: 1956/530, loss: 0.0010044575901702046
2023-01-24 08:54:19.474370: step: 1960/530, loss: 6.521415343740955e-06
2023-01-24 08:54:20.532413: step: 1964/530, loss: 0.0030489973723888397
2023-01-24 08:54:21.582206: step: 1968/530, loss: 0.004461432341486216
2023-01-24 08:54:22.629666: step: 1972/530, loss: 4.626946247299202e-05
2023-01-24 08:54:23.696851: step: 1976/530, loss: 0.0030204516369849443
2023-01-24 08:54:24.746416: step: 1980/530, loss: 0.001155806239694357
2023-01-24 08:54:25.803666: step: 1984/530, loss: 0.00499724643304944
2023-01-24 08:54:26.870380: step: 1988/530, loss: 0.003911454696208239
2023-01-24 08:54:27.928099: step: 1992/530, loss: 0.0007650654297322035
2023-01-24 08:54:28.996884: step: 1996/530, loss: 1.7457738067605533e-05
2023-01-24 08:54:30.053794: step: 2000/530, loss: 0.0015691019361838698
2023-01-24 08:54:31.125345: step: 2004/530, loss: 0.009454813785851002
2023-01-24 08:54:32.182425: step: 2008/530, loss: 0.0009072218672372401
2023-01-24 08:54:33.245993: step: 2012/530, loss: 0.0026456110645085573
2023-01-24 08:54:34.299882: step: 2016/530, loss: 0.0021392330527305603
2023-01-24 08:54:35.358357: step: 2020/530, loss: 0.009899473749101162
2023-01-24 08:54:36.415484: step: 2024/530, loss: 0.00014786029350943863
2023-01-24 08:54:37.490733: step: 2028/530, loss: 0.005883692763745785
2023-01-24 08:54:38.551504: step: 2032/530, loss: 0.00018104046466760337
2023-01-24 08:54:39.603580: step: 2036/530, loss: 0.005610117223113775
2023-01-24 08:54:40.673842: step: 2040/530, loss: 0.049600813537836075
2023-01-24 08:54:41.737395: step: 2044/530, loss: 0.0004004179500043392
2023-01-24 08:54:42.788061: step: 2048/530, loss: 0.00449847336858511
2023-01-24 08:54:43.832903: step: 2052/530, loss: 0.00216514035128057
2023-01-24 08:54:44.896046: step: 2056/530, loss: 0.00015487248310819268
2023-01-24 08:54:45.956350: step: 2060/530, loss: 0.0025290220510214567
2023-01-24 08:54:47.025351: step: 2064/530, loss: 0.0018151961266994476
2023-01-24 08:54:48.085877: step: 2068/530, loss: 0.005314223002642393
2023-01-24 08:54:49.136929: step: 2072/530, loss: 1.5052189155539963e-05
2023-01-24 08:54:50.184373: step: 2076/530, loss: 0.004058415070176125
2023-01-24 08:54:51.245681: step: 2080/530, loss: 0.0026998277753591537
2023-01-24 08:54:52.294014: step: 2084/530, loss: 0.005886686034500599
2023-01-24 08:54:53.351650: step: 2088/530, loss: 3.8928203139221296e-05
2023-01-24 08:54:54.393781: step: 2092/530, loss: 3.731488322955556e-05
2023-01-24 08:54:55.448297: step: 2096/530, loss: 0.008258545771241188
2023-01-24 08:54:56.503830: step: 2100/530, loss: 0.01345754973590374
2023-01-24 08:54:57.561617: step: 2104/530, loss: 0.0013605003478005528
2023-01-24 08:54:58.625602: step: 2108/530, loss: 0.00012094646808691323
2023-01-24 08:54:59.672196: step: 2112/530, loss: 0.008695867843925953
2023-01-24 08:55:00.738778: step: 2116/530, loss: 0.0035952930338680744
2023-01-24 08:55:01.822115: step: 2120/530, loss: 0.003573654219508171
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38151093357152305, 'r': 0.33155978667126673, 'f1': 0.3547858021842793}, 'combined': 0.26142111739894264, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3981616313253807, 'r': 0.29836222850401467, 'f1': 0.3411121958008219}, 'combined': 0.2262298500647938, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35072843822843824, 'r': 0.28496685606060607, 'f1': 0.31444618599791013}, 'combined': 0.2096307906652734, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3988761716793377, 'r': 0.2946714970710678, 'f1': 0.33894552299915864}, 'combined': 0.22120655185208246, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37379092536454844, 'r': 0.3340712065402321, 'f1': 0.3528166850635317}, 'combined': 0.25997018899418123, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39697004445209105, 'r': 0.30795251933253126, 'f1': 0.3468407214325437}, 'combined': 0.23002907949930357, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7708333333333334, 'r': 0.40217391304347827, 'f1': 0.5285714285714287}, 'combined': 0.35238095238095246, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
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 08:57:23.361856: step: 4/530, loss: 0.001752302865497768
2023-01-24 08:57:24.423178: step: 8/530, loss: 0.0016389511292800307
2023-01-24 08:57:25.474688: step: 12/530, loss: 0.006602039095014334
2023-01-24 08:57:26.536847: step: 16/530, loss: 0.0006128773675300181
2023-01-24 08:57:27.579080: step: 20/530, loss: 0.0015524306800216436
2023-01-24 08:57:28.620979: step: 24/530, loss: 0.001283848425373435
2023-01-24 08:57:29.671504: step: 28/530, loss: 0.00037966444506309927
2023-01-24 08:57:30.722102: step: 32/530, loss: 0.040175192058086395
2023-01-24 08:57:31.780131: step: 36/530, loss: 0.0063542937859892845
2023-01-24 08:57:32.839552: step: 40/530, loss: 0.0001701469300314784
2023-01-24 08:57:33.899678: step: 44/530, loss: 3.2335567084373906e-05
2023-01-24 08:57:34.951166: step: 48/530, loss: 0.020908227190375328
2023-01-24 08:57:36.000154: step: 52/530, loss: 2.1651270799338818e-05
2023-01-24 08:57:37.063631: step: 56/530, loss: 0.0004686538886744529
2023-01-24 08:57:38.112612: step: 60/530, loss: 0.018815917894244194
2023-01-24 08:57:39.150777: step: 64/530, loss: 0.0006118938326835632
2023-01-24 08:57:40.194608: step: 68/530, loss: 0.01032250840216875
2023-01-24 08:57:41.230136: step: 72/530, loss: 0.005057737696915865
2023-01-24 08:57:42.271864: step: 76/530, loss: 0.0005119513371028006
2023-01-24 08:57:43.312307: step: 80/530, loss: 0.013875901699066162
2023-01-24 08:57:44.352886: step: 84/530, loss: 0.007181371096521616
2023-01-24 08:57:45.399802: step: 88/530, loss: 0.009162049740552902
2023-01-24 08:57:46.448897: step: 92/530, loss: 0.00541257718577981
2023-01-24 08:57:47.493787: step: 96/530, loss: 0.0005214555421844125
2023-01-24 08:57:48.554545: step: 100/530, loss: 1.9868207079554168e-09
2023-01-24 08:57:49.599956: step: 104/530, loss: 0.005176474805921316
2023-01-24 08:57:50.665441: step: 108/530, loss: 0.0151984179392457
2023-01-24 08:57:51.714729: step: 112/530, loss: 0.003376663662493229
2023-01-24 08:57:52.777590: step: 116/530, loss: 0.0008604144095443189
2023-01-24 08:57:53.822846: step: 120/530, loss: 7.793185795890167e-05
2023-01-24 08:57:54.866763: step: 124/530, loss: 4.572741119091006e-08
2023-01-24 08:57:55.911779: step: 128/530, loss: 0.0053338948637247086
2023-01-24 08:57:56.969422: step: 132/530, loss: 0.004737090785056353
2023-01-24 08:57:58.038644: step: 136/530, loss: 3.977471715188585e-05
2023-01-24 08:57:59.078909: step: 140/530, loss: 8.840263944875915e-06
2023-01-24 08:58:00.131057: step: 144/530, loss: 0.0013821236789226532
2023-01-24 08:58:01.189493: step: 148/530, loss: 0.0006252435850910842
2023-01-24 08:58:02.255032: step: 152/530, loss: 0.0017567923059687018
2023-01-24 08:58:03.311282: step: 156/530, loss: 0.0019348494242876768
2023-01-24 08:58:04.362531: step: 160/530, loss: 0.00154181569814682
2023-01-24 08:58:05.414881: step: 164/530, loss: 0.0
2023-01-24 08:58:06.453262: step: 168/530, loss: 6.259909241634887e-06
2023-01-24 08:58:07.503138: step: 172/530, loss: 7.605681457789615e-05
2023-01-24 08:58:08.570337: step: 176/530, loss: 0.0058680991642177105
2023-01-24 08:58:09.637749: step: 180/530, loss: 0.004403875675052404
2023-01-24 08:58:10.693910: step: 184/530, loss: 0.0035206452012062073
2023-01-24 08:58:11.753380: step: 188/530, loss: 0.0004406616499181837
2023-01-24 08:58:12.797981: step: 192/530, loss: 0.00164504861459136
2023-01-24 08:58:13.849219: step: 196/530, loss: 5.073590045867604e-07
2023-01-24 08:58:14.904770: step: 200/530, loss: 0.00026435221661813557
2023-01-24 08:58:15.962208: step: 204/530, loss: 9.625990787753835e-05
2023-01-24 08:58:17.021170: step: 208/530, loss: 0.0012669884599745274
2023-01-24 08:58:18.072960: step: 212/530, loss: 0.00018781240214593709
2023-01-24 08:58:19.124491: step: 216/530, loss: 0.0002451986656524241
2023-01-24 08:58:20.166952: step: 220/530, loss: 0.00016452287673018873
2023-01-24 08:58:21.221062: step: 224/530, loss: 0.009959731251001358
2023-01-24 08:58:22.288578: step: 228/530, loss: 0.0007803167682141066
2023-01-24 08:58:23.340408: step: 232/530, loss: 0.001685862080194056
2023-01-24 08:58:24.386574: step: 236/530, loss: 0.0
2023-01-24 08:58:25.446071: step: 240/530, loss: 0.0012693736935034394
2023-01-24 08:58:26.496509: step: 244/530, loss: 0.00279949395917356
2023-01-24 08:58:27.557772: step: 248/530, loss: 0.0009765727445483208
2023-01-24 08:58:28.608278: step: 252/530, loss: 0.0016541201621294022
2023-01-24 08:58:29.669006: step: 256/530, loss: 0.009226897731423378
2023-01-24 08:58:30.726430: step: 260/530, loss: 0.004949219524860382
2023-01-24 08:58:31.786506: step: 264/530, loss: 0.0024971093516796827
2023-01-24 08:58:32.838113: step: 268/530, loss: 0.0025289629120379686
2023-01-24 08:58:33.902899: step: 272/530, loss: 0.001997048733755946
2023-01-24 08:58:34.969387: step: 276/530, loss: 0.0027037053368985653
2023-01-24 08:58:36.022508: step: 280/530, loss: 0.0035312389954924583
2023-01-24 08:58:37.085073: step: 284/530, loss: 8.356961916433647e-05
2023-01-24 08:58:38.136757: step: 288/530, loss: 0.0007067765691317618
2023-01-24 08:58:39.189514: step: 292/530, loss: 0.002174037043005228
2023-01-24 08:58:40.244523: step: 296/530, loss: 0.003014680929481983
2023-01-24 08:58:41.302212: step: 300/530, loss: 8.532369247404858e-05
2023-01-24 08:58:42.340115: step: 304/530, loss: 0.0003013579989783466
2023-01-24 08:58:43.392133: step: 308/530, loss: 0.0011720972834154963
2023-01-24 08:58:44.452499: step: 312/530, loss: 0.0030178409069776535
2023-01-24 08:58:45.513287: step: 316/530, loss: 0.0023797014728188515
2023-01-24 08:58:46.575706: step: 320/530, loss: 0.003959394060075283
2023-01-24 08:58:47.634253: step: 324/530, loss: 0.013838368467986584
2023-01-24 08:58:48.722687: step: 328/530, loss: 0.0031495261937379837
2023-01-24 08:58:49.770013: step: 332/530, loss: 0.005242731422185898
2023-01-24 08:58:50.823067: step: 336/530, loss: 0.00033640279434621334
2023-01-24 08:58:51.872511: step: 340/530, loss: 0.0034763794392347336
2023-01-24 08:58:52.924425: step: 344/530, loss: 0.00017940586258191615
2023-01-24 08:58:53.957421: step: 348/530, loss: 0.003981929738074541
2023-01-24 08:58:54.999580: step: 352/530, loss: 0.005513024050742388
2023-01-24 08:58:56.057552: step: 356/530, loss: 0.000940346100833267
2023-01-24 08:58:57.113876: step: 360/530, loss: 0.014222263358533382
2023-01-24 08:58:58.174420: step: 364/530, loss: 0.0033718652557581663
2023-01-24 08:58:59.224820: step: 368/530, loss: 0.00012514233822003007
2023-01-24 08:59:00.289242: step: 372/530, loss: 7.972505409270525e-05
2023-01-24 08:59:01.342348: step: 376/530, loss: 0.0019516331376507878
2023-01-24 08:59:02.398037: step: 380/530, loss: 0.0011451207101345062
2023-01-24 08:59:03.451031: step: 384/530, loss: 0.00444561755284667
2023-01-24 08:59:04.517603: step: 388/530, loss: 0.0024688197299838066
2023-01-24 08:59:05.580601: step: 392/530, loss: 0.004034331068396568
2023-01-24 08:59:06.637972: step: 396/530, loss: 0.0006795467925257981
2023-01-24 08:59:07.697222: step: 400/530, loss: 8.253064879681915e-05
2023-01-24 08:59:08.758585: step: 404/530, loss: 0.00033168913796544075
2023-01-24 08:59:09.809572: step: 408/530, loss: 0.00021120651217643172
2023-01-24 08:59:10.868306: step: 412/530, loss: 0.0004992078174836934
2023-01-24 08:59:11.928133: step: 416/530, loss: 6.285808922257274e-05
2023-01-24 08:59:12.979469: step: 420/530, loss: 0.003226697212085128
2023-01-24 08:59:14.023636: step: 424/530, loss: 0.00013692451466340572
2023-01-24 08:59:15.094492: step: 428/530, loss: 0.006708402186632156
2023-01-24 08:59:16.159137: step: 432/530, loss: 0.004447572864592075
2023-01-24 08:59:17.216011: step: 436/530, loss: 0.007740409579128027
2023-01-24 08:59:18.279607: step: 440/530, loss: 0.002659456105902791
2023-01-24 08:59:19.352625: step: 444/530, loss: 0.00010265692253597081
2023-01-24 08:59:20.419558: step: 448/530, loss: 0.0027501555159687996
2023-01-24 08:59:21.497010: step: 452/530, loss: 1.460834300814895e-05
2023-01-24 08:59:22.564392: step: 456/530, loss: 0.00573878875002265
2023-01-24 08:59:23.626814: step: 460/530, loss: 0.002819736022502184
2023-01-24 08:59:24.680729: step: 464/530, loss: 1.0765440492832568e-05
2023-01-24 08:59:25.742948: step: 468/530, loss: 0.008204531855881214
2023-01-24 08:59:26.784063: step: 472/530, loss: 4.598198938765563e-05
2023-01-24 08:59:27.850996: step: 476/530, loss: 0.0004426180967129767
2023-01-24 08:59:28.913409: step: 480/530, loss: 0.0029682456515729427
2023-01-24 08:59:29.957447: step: 484/530, loss: 3.419702920837153e-07
2023-01-24 08:59:31.010768: step: 488/530, loss: 0.001659355009905994
2023-01-24 08:59:32.095265: step: 492/530, loss: 0.00994129665195942
2023-01-24 08:59:33.144004: step: 496/530, loss: 0.004415545146912336
2023-01-24 08:59:34.195386: step: 500/530, loss: 0.0001393342827213928
2023-01-24 08:59:35.261398: step: 504/530, loss: 0.004157865419983864
2023-01-24 08:59:36.321838: step: 508/530, loss: 0.0005262452177703381
2023-01-24 08:59:37.411634: step: 512/530, loss: 0.020847121253609657
2023-01-24 08:59:38.476509: step: 516/530, loss: 0.005480272229760885
2023-01-24 08:59:39.524815: step: 520/530, loss: 0.00218738941475749
2023-01-24 08:59:40.586758: step: 524/530, loss: 0.003092500614002347
2023-01-24 08:59:41.658421: step: 528/530, loss: 0.028495432808995247
2023-01-24 08:59:42.700321: step: 532/530, loss: 0.006432359106838703
2023-01-24 08:59:43.768536: step: 536/530, loss: 0.012999472208321095
2023-01-24 08:59:44.829844: step: 540/530, loss: 0.0020123906433582306
2023-01-24 08:59:45.892859: step: 544/530, loss: 0.0013998314971104264
2023-01-24 08:59:46.971335: step: 548/530, loss: 0.0016724411398172379
2023-01-24 08:59:48.012670: step: 552/530, loss: 8.652758651805925e-07
2023-01-24 08:59:49.076839: step: 556/530, loss: 0.003603859804570675
2023-01-24 08:59:50.151902: step: 560/530, loss: 0.00787485670298338
2023-01-24 08:59:51.198790: step: 564/530, loss: 0.003121920395642519
2023-01-24 08:59:52.263279: step: 568/530, loss: 0.009287911467254162
2023-01-24 08:59:53.337164: step: 572/530, loss: 3.983230271842331e-06
2023-01-24 08:59:54.395343: step: 576/530, loss: 0.003140023909509182
2023-01-24 08:59:55.464138: step: 580/530, loss: 2.6439010980539024e-05
2023-01-24 08:59:56.535613: step: 584/530, loss: 0.004500710871070623
2023-01-24 08:59:57.591350: step: 588/530, loss: 0.001247038715519011
2023-01-24 08:59:58.641015: step: 592/530, loss: 3.1810628570383415e-05
2023-01-24 08:59:59.691793: step: 596/530, loss: 0.0036331121809780598
2023-01-24 09:00:00.751314: step: 600/530, loss: 5.078564299765276e-06
2023-01-24 09:00:01.819651: step: 604/530, loss: 0.0017249556258320808
2023-01-24 09:00:02.887785: step: 608/530, loss: 6.259195652091876e-05
2023-01-24 09:00:03.951446: step: 612/530, loss: 0.0014514377107843757
2023-01-24 09:00:05.005440: step: 616/530, loss: 0.0002850772289093584
2023-01-24 09:00:06.050050: step: 620/530, loss: 0.0005553573137149215
2023-01-24 09:00:07.108972: step: 624/530, loss: 0.012637272477149963
2023-01-24 09:00:08.156997: step: 628/530, loss: 9.784231224330142e-05
2023-01-24 09:00:09.212168: step: 632/530, loss: 0.0040410771034657955
2023-01-24 09:00:10.250242: step: 636/530, loss: 0.001638334128074348
2023-01-24 09:00:11.288428: step: 640/530, loss: 5.00682472193148e-05
2023-01-24 09:00:12.366838: step: 644/530, loss: 6.940359162399545e-05
2023-01-24 09:00:13.406768: step: 648/530, loss: 0.0006881205481477082
2023-01-24 09:00:14.462093: step: 652/530, loss: 0.0029281096067279577
2023-01-24 09:00:15.505197: step: 656/530, loss: 0.0
2023-01-24 09:00:16.567744: step: 660/530, loss: 0.004639377351850271
2023-01-24 09:00:17.610421: step: 664/530, loss: 0.004380300175398588
2023-01-24 09:00:18.653745: step: 668/530, loss: 0.00012675949255935848
2023-01-24 09:00:19.706056: step: 672/530, loss: 0.0006016083061695099
2023-01-24 09:00:20.778203: step: 676/530, loss: 0.011187789030373096
2023-01-24 09:00:21.835115: step: 680/530, loss: 0.003848572727292776
2023-01-24 09:00:22.893428: step: 684/530, loss: 0.004137535113841295
2023-01-24 09:00:23.956730: step: 688/530, loss: 0.0028142426162958145
2023-01-24 09:00:25.007921: step: 692/530, loss: 0.0007270050118677318
2023-01-24 09:00:26.068599: step: 696/530, loss: 3.770620241994038e-05
2023-01-24 09:00:27.120920: step: 700/530, loss: 0.022405892610549927
2023-01-24 09:00:28.180022: step: 704/530, loss: 0.0024828980676829815
2023-01-24 09:00:29.231658: step: 708/530, loss: 0.0014510038308799267
2023-01-24 09:00:30.294379: step: 712/530, loss: 0.000299901730613783
2023-01-24 09:00:31.338524: step: 716/530, loss: 0.002773511689156294
2023-01-24 09:00:32.407664: step: 720/530, loss: 0.007063380908221006
2023-01-24 09:00:33.459003: step: 724/530, loss: 0.0016142678214237094
2023-01-24 09:00:34.511781: step: 728/530, loss: 0.0038000394124537706
2023-01-24 09:00:35.561173: step: 732/530, loss: 0.00038545799907296896
2023-01-24 09:00:36.614459: step: 736/530, loss: 1.4375986211234704e-05
2023-01-24 09:00:37.677701: step: 740/530, loss: 0.024682098999619484
2023-01-24 09:00:38.734211: step: 744/530, loss: 9.876345757220406e-06
2023-01-24 09:00:39.788006: step: 748/530, loss: 3.379245026735589e-05
2023-01-24 09:00:40.839503: step: 752/530, loss: 0.005003856960684061
2023-01-24 09:00:41.915390: step: 756/530, loss: 0.003168597584590316
2023-01-24 09:00:42.982205: step: 760/530, loss: 0.0068447170779109
2023-01-24 09:00:44.045901: step: 764/530, loss: 0.0038939560763537884
2023-01-24 09:00:45.118028: step: 768/530, loss: 1.3161532478989102e-05
2023-01-24 09:00:46.186343: step: 772/530, loss: 0.0009245398687198758
2023-01-24 09:00:47.245989: step: 776/530, loss: 0.00034620013320818543
2023-01-24 09:00:48.305602: step: 780/530, loss: 0.004762914497405291
2023-01-24 09:00:49.374010: step: 784/530, loss: 0.007647800724953413
2023-01-24 09:00:50.411840: step: 788/530, loss: 0.0005343404482118785
2023-01-24 09:00:51.468506: step: 792/530, loss: 0.004137787036597729
2023-01-24 09:00:52.524731: step: 796/530, loss: 0.00023037564824335277
2023-01-24 09:00:53.571766: step: 800/530, loss: 0.007016750518232584
2023-01-24 09:00:54.621362: step: 804/530, loss: 0.00936032086610794
2023-01-24 09:00:55.699881: step: 808/530, loss: 0.004378096200525761
2023-01-24 09:00:56.767276: step: 812/530, loss: 0.0002547816256992519
2023-01-24 09:00:57.829930: step: 816/530, loss: 0.00659840926527977
2023-01-24 09:00:58.875055: step: 820/530, loss: 2.0800029233214445e-05
2023-01-24 09:00:59.926645: step: 824/530, loss: 0.017561456188559532
2023-01-24 09:01:00.992163: step: 828/530, loss: 0.0009880434954538941
2023-01-24 09:01:02.047397: step: 832/530, loss: 3.384624142199755e-05
2023-01-24 09:01:03.124482: step: 836/530, loss: 0.0017293887212872505
2023-01-24 09:01:04.189290: step: 840/530, loss: 0.012923546135425568
2023-01-24 09:01:05.238723: step: 844/530, loss: 0.004564765375107527
2023-01-24 09:01:06.302844: step: 848/530, loss: 0.001028168830089271
2023-01-24 09:01:07.362304: step: 852/530, loss: 0.0009403776493854821
2023-01-24 09:01:08.411208: step: 856/530, loss: 0.001699383370578289
2023-01-24 09:01:09.479879: step: 860/530, loss: 0.0027443207800388336
2023-01-24 09:01:10.539781: step: 864/530, loss: 0.008542467840015888
2023-01-24 09:01:11.594187: step: 868/530, loss: 0.006661437451839447
2023-01-24 09:01:12.646955: step: 872/530, loss: 0.008112785406410694
2023-01-24 09:01:13.715009: step: 876/530, loss: 0.008347105234861374
2023-01-24 09:01:14.765364: step: 880/530, loss: 0.000577003404032439
2023-01-24 09:01:15.839242: step: 884/530, loss: 6.859995482955128e-05
2023-01-24 09:01:16.900527: step: 888/530, loss: 0.005183335859328508
2023-01-24 09:01:17.949762: step: 892/530, loss: 0.005544007755815983
2023-01-24 09:01:19.012540: step: 896/530, loss: 0.0013655393850058317
2023-01-24 09:01:20.065862: step: 900/530, loss: 0.0010157300857827067
2023-01-24 09:01:21.108463: step: 904/530, loss: 0.000509263074491173
2023-01-24 09:01:22.168026: step: 908/530, loss: 9.949225932359695e-05
2023-01-24 09:01:23.222211: step: 912/530, loss: 0.00041577493539080024
2023-01-24 09:01:24.288701: step: 916/530, loss: 0.003287137486040592
2023-01-24 09:01:25.344797: step: 920/530, loss: 0.0052236150950193405
2023-01-24 09:01:26.410418: step: 924/530, loss: 1.2356086699583102e-05
2023-01-24 09:01:27.454804: step: 928/530, loss: 0.00040745915612205863
2023-01-24 09:01:28.508898: step: 932/530, loss: 0.00033783091930672526
2023-01-24 09:01:29.574195: step: 936/530, loss: 0.006726912688463926
2023-01-24 09:01:30.624015: step: 940/530, loss: 0.003163578687235713
2023-01-24 09:01:31.687805: step: 944/530, loss: 0.0010459624463692307
2023-01-24 09:01:32.784208: step: 948/530, loss: 1.7605721950531006e-05
2023-01-24 09:01:33.839896: step: 952/530, loss: 6.035666956449859e-06
2023-01-24 09:01:34.895506: step: 956/530, loss: 0.00016880819748621434
2023-01-24 09:01:35.947284: step: 960/530, loss: 0.000227796655963175
2023-01-24 09:01:36.998693: step: 964/530, loss: 0.0010014348663389683
2023-01-24 09:01:38.047284: step: 968/530, loss: 0.0013350655790418386
2023-01-24 09:01:39.089267: step: 972/530, loss: 0.0005010308232158422
2023-01-24 09:01:40.134854: step: 976/530, loss: 0.0006129872053861618
2023-01-24 09:01:41.197722: step: 980/530, loss: 0.0011787122348323464
2023-01-24 09:01:42.244046: step: 984/530, loss: 0.002530441852286458
2023-01-24 09:01:43.299919: step: 988/530, loss: 0.013662178069353104
2023-01-24 09:01:44.355311: step: 992/530, loss: 0.019461173564195633
2023-01-24 09:01:45.404195: step: 996/530, loss: 0.0019518026383593678
2023-01-24 09:01:46.458621: step: 1000/530, loss: 0.0004617640806827694
2023-01-24 09:01:47.513722: step: 1004/530, loss: 0.0014622590970247984
2023-01-24 09:01:48.565244: step: 1008/530, loss: 7.19355302862823e-05
2023-01-24 09:01:49.628774: step: 1012/530, loss: 0.002228764584288001
2023-01-24 09:01:50.686910: step: 1016/530, loss: 0.056037988513708115
2023-01-24 09:01:51.741580: step: 1020/530, loss: 0.0010082368971779943
2023-01-24 09:01:52.797052: step: 1024/530, loss: 0.0022039019968360662
2023-01-24 09:01:53.853862: step: 1028/530, loss: 0.0007634743233211339
2023-01-24 09:01:54.917301: step: 1032/530, loss: 0.001595959416590631
2023-01-24 09:01:55.968169: step: 1036/530, loss: 0.0009367107995785773
2023-01-24 09:01:57.029703: step: 1040/530, loss: 0.0002886794973164797
2023-01-24 09:01:58.073936: step: 1044/530, loss: 0.0008652876131236553
2023-01-24 09:01:59.126806: step: 1048/530, loss: 0.020551834255456924
2023-01-24 09:02:00.178059: step: 1052/530, loss: 0.027009015902876854
2023-01-24 09:02:01.240962: step: 1056/530, loss: 0.008178578689694405
2023-01-24 09:02:02.306425: step: 1060/530, loss: 0.006356274709105492
2023-01-24 09:02:03.364687: step: 1064/530, loss: 0.0008796472102403641
2023-01-24 09:02:04.408186: step: 1068/530, loss: 0.004666866268962622
2023-01-24 09:02:05.470837: step: 1072/530, loss: 0.0017187492921948433
2023-01-24 09:02:06.520311: step: 1076/530, loss: 0.0015398325631394982
2023-01-24 09:02:07.570573: step: 1080/530, loss: 0.0002882368862628937
2023-01-24 09:02:08.639608: step: 1084/530, loss: 0.003046171274036169
2023-01-24 09:02:09.706306: step: 1088/530, loss: 0.0006463193567469716
2023-01-24 09:02:10.790456: step: 1092/530, loss: 0.00010992652823915705
2023-01-24 09:02:11.833026: step: 1096/530, loss: 0.001654975931160152
2023-01-24 09:02:12.898967: step: 1100/530, loss: 0.012699581682682037
2023-01-24 09:02:13.957841: step: 1104/530, loss: 0.00716777890920639
2023-01-24 09:02:15.029833: step: 1108/530, loss: 0.00681094778701663
2023-01-24 09:02:16.089998: step: 1112/530, loss: 0.000222817572648637
2023-01-24 09:02:17.186009: step: 1116/530, loss: 0.009048809297382832
2023-01-24 09:02:18.226574: step: 1120/530, loss: 0.0006711932946927845
2023-01-24 09:02:19.277218: step: 1124/530, loss: 0.0015377732925117016
2023-01-24 09:02:20.330173: step: 1128/530, loss: 7.38136877771467e-05
2023-01-24 09:02:21.388697: step: 1132/530, loss: 0.0014566653408110142
2023-01-24 09:02:22.443298: step: 1136/530, loss: 3.048654798476491e-05
2023-01-24 09:02:23.502621: step: 1140/530, loss: 1.8965063645737246e-05
2023-01-24 09:02:24.550421: step: 1144/530, loss: 0.004442988894879818
2023-01-24 09:02:25.595009: step: 1148/530, loss: 0.003879878204315901
2023-01-24 09:02:26.671298: step: 1152/530, loss: 3.460418520262465e-05
2023-01-24 09:02:27.735594: step: 1156/530, loss: 0.0026914526242762804
2023-01-24 09:02:28.785445: step: 1160/530, loss: 0.000454261782579124
2023-01-24 09:02:29.829693: step: 1164/530, loss: 0.0012476884294301271
2023-01-24 09:02:30.886763: step: 1168/530, loss: 0.007799950893968344
2023-01-24 09:02:31.955009: step: 1172/530, loss: 0.0012154633877798915
2023-01-24 09:02:33.055467: step: 1176/530, loss: 0.00908190943300724
2023-01-24 09:02:34.109826: step: 1180/530, loss: 4.060582068632357e-05
2023-01-24 09:02:35.164632: step: 1184/530, loss: 8.804251592664514e-06
2023-01-24 09:02:36.209700: step: 1188/530, loss: 0.00040031614480540156
2023-01-24 09:02:37.251202: step: 1192/530, loss: 0.00599023187533021
2023-01-24 09:02:38.300085: step: 1196/530, loss: 0.002464772667735815
2023-01-24 09:02:39.341400: step: 1200/530, loss: 5.606355898635229e-06
2023-01-24 09:02:40.380546: step: 1204/530, loss: 0.0004145588318351656
2023-01-24 09:02:41.427690: step: 1208/530, loss: 0.00013903662329539657
2023-01-24 09:02:42.485021: step: 1212/530, loss: 0.0014565952587872744
2023-01-24 09:02:43.540724: step: 1216/530, loss: 0.0036121434532105923
2023-01-24 09:02:44.598501: step: 1220/530, loss: 0.0003554648137651384
2023-01-24 09:02:45.667204: step: 1224/530, loss: 0.0021264769602566957
2023-01-24 09:02:46.717964: step: 1228/530, loss: 5.610079097095877e-05
2023-01-24 09:02:47.775301: step: 1232/530, loss: 0.0004236284294165671
2023-01-24 09:02:48.852029: step: 1236/530, loss: 6.0965485317865387e-05
2023-01-24 09:02:49.915974: step: 1240/530, loss: 5.6363460316788405e-05
2023-01-24 09:02:50.959275: step: 1244/530, loss: 0.004429629538208246
2023-01-24 09:02:52.006240: step: 1248/530, loss: 4.690885543823242e-05
2023-01-24 09:02:53.066981: step: 1252/530, loss: 0.00017911115719471127
2023-01-24 09:02:54.131294: step: 1256/530, loss: 0.0023545955773442984
2023-01-24 09:02:55.189371: step: 1260/530, loss: 0.0016902872594073415
2023-01-24 09:02:56.248230: step: 1264/530, loss: 7.412501145154238e-05
2023-01-24 09:02:57.320449: step: 1268/530, loss: 2.3037136998027563e-05
2023-01-24 09:02:58.384232: step: 1272/530, loss: 6.271031452342868e-05
2023-01-24 09:02:59.463819: step: 1276/530, loss: 8.948436516220681e-07
2023-01-24 09:03:00.509144: step: 1280/530, loss: 0.001532075461000204
2023-01-24 09:03:01.573644: step: 1284/530, loss: 0.0004931019502691925
2023-01-24 09:03:02.639324: step: 1288/530, loss: 0.00395149365067482
2023-01-24 09:03:03.706504: step: 1292/530, loss: 5.169353971723467e-05
2023-01-24 09:03:04.782750: step: 1296/530, loss: 0.010782415978610516
2023-01-24 09:03:05.834428: step: 1300/530, loss: 0.0004477275360841304
2023-01-24 09:03:06.882276: step: 1304/530, loss: 0.0008825917611829937
2023-01-24 09:03:07.936293: step: 1308/530, loss: 0.020749520510435104
2023-01-24 09:03:08.999815: step: 1312/530, loss: 5.01430404256098e-05
2023-01-24 09:03:10.066416: step: 1316/530, loss: 0.0025758296251296997
2023-01-24 09:03:11.113448: step: 1320/530, loss: 2.5561619622749276e-05
2023-01-24 09:03:12.197609: step: 1324/530, loss: 0.00024029469932429492
2023-01-24 09:03:13.254922: step: 1328/530, loss: 3.0458546461886726e-05
2023-01-24 09:03:14.298945: step: 1332/530, loss: 0.004547671880573034
2023-01-24 09:03:15.355380: step: 1336/530, loss: 0.00048235684516839683
2023-01-24 09:03:16.407123: step: 1340/530, loss: 0.002156138652935624
2023-01-24 09:03:17.487817: step: 1344/530, loss: 0.005517592653632164
2023-01-24 09:03:18.532578: step: 1348/530, loss: 2.982908881676849e-05
2023-01-24 09:03:19.600146: step: 1352/530, loss: 0.001281043398194015
2023-01-24 09:03:20.665156: step: 1356/530, loss: 0.0006219832575879991
2023-01-24 09:03:21.725234: step: 1360/530, loss: 0.021388936787843704
2023-01-24 09:03:22.779778: step: 1364/530, loss: 0.0014244536869227886
2023-01-24 09:03:23.821609: step: 1368/530, loss: 0.0022719851695001125
2023-01-24 09:03:24.885723: step: 1372/530, loss: 0.0009321668767370284
2023-01-24 09:03:25.939926: step: 1376/530, loss: 4.062427251483314e-05
2023-01-24 09:03:26.989147: step: 1380/530, loss: 0.004758135881274939
2023-01-24 09:03:28.042860: step: 1384/530, loss: 0.0063188043422997
2023-01-24 09:03:29.090260: step: 1388/530, loss: 0.004103731829673052
2023-01-24 09:03:30.139291: step: 1392/530, loss: 0.004832057747989893
2023-01-24 09:03:31.206974: step: 1396/530, loss: 0.0037866709753870964
2023-01-24 09:03:32.287888: step: 1400/530, loss: 0.004212132655084133
2023-01-24 09:03:33.340448: step: 1404/530, loss: 0.00500048091635108
2023-01-24 09:03:34.403461: step: 1408/530, loss: 4.953197276336141e-06
2023-01-24 09:03:35.474621: step: 1412/530, loss: 0.004411301575601101
2023-01-24 09:03:36.540549: step: 1416/530, loss: 0.0017443530960008502
2023-01-24 09:03:37.600638: step: 1420/530, loss: 1.373694703943329e-05
2023-01-24 09:03:38.665856: step: 1424/530, loss: 0.0044926670379936695
2023-01-24 09:03:39.720644: step: 1428/530, loss: 0.003479141043499112
2023-01-24 09:03:40.783009: step: 1432/530, loss: 0.0018363717244938016
2023-01-24 09:03:41.838853: step: 1436/530, loss: 0.009559924714267254
2023-01-24 09:03:42.888984: step: 1440/530, loss: 0.0005628743092529476
2023-01-24 09:03:43.941513: step: 1444/530, loss: 0.005261993035674095
2023-01-24 09:03:44.996249: step: 1448/530, loss: 0.0006315595237538218
2023-01-24 09:03:46.054197: step: 1452/530, loss: 0.004621594678610563
2023-01-24 09:03:47.099742: step: 1456/530, loss: 8.12647704151459e-05
2023-01-24 09:03:48.145936: step: 1460/530, loss: 6.221111448212469e-07
2023-01-24 09:03:49.210595: step: 1464/530, loss: 0.00024380855029448867
2023-01-24 09:03:50.269935: step: 1468/530, loss: 0.006493727210909128
2023-01-24 09:03:51.325077: step: 1472/530, loss: 0.0019776339177042246
2023-01-24 09:03:52.402455: step: 1476/530, loss: 0.0011832970194518566
2023-01-24 09:03:53.469210: step: 1480/530, loss: 0.006625242996960878
2023-01-24 09:03:54.508926: step: 1484/530, loss: 0.0006374718504957855
2023-01-24 09:03:55.561644: step: 1488/530, loss: 0.0009573863353580236
2023-01-24 09:03:56.621247: step: 1492/530, loss: 0.00025285579613409936
2023-01-24 09:03:57.685615: step: 1496/530, loss: 0.002323656575754285
2023-01-24 09:03:58.745581: step: 1500/530, loss: 0.003548703622072935
2023-01-24 09:03:59.803359: step: 1504/530, loss: 0.008402667008340359
2023-01-24 09:04:00.856391: step: 1508/530, loss: 0.00010735232353908941
2023-01-24 09:04:01.923274: step: 1512/530, loss: 0.0029170061461627483
2023-01-24 09:04:02.973386: step: 1516/530, loss: 0.003136037616059184
2023-01-24 09:04:04.027312: step: 1520/530, loss: 0.0005236623110249639
2023-01-24 09:04:05.095201: step: 1524/530, loss: 2.936218152171932e-05
2023-01-24 09:04:06.152238: step: 1528/530, loss: 4.369170346762985e-05
2023-01-24 09:04:07.227263: step: 1532/530, loss: 0.000450140330940485
2023-01-24 09:04:08.291239: step: 1536/530, loss: 0.0032530699390918016
2023-01-24 09:04:09.348218: step: 1540/530, loss: 7.536407792940736e-06
2023-01-24 09:04:10.404591: step: 1544/530, loss: 0.00036497111432254314
2023-01-24 09:04:11.460170: step: 1548/530, loss: 0.003464294131845236
2023-01-24 09:04:12.495403: step: 1552/530, loss: 2.537953207593091e-07
2023-01-24 09:04:13.543274: step: 1556/530, loss: 4.48406717623584e-06
2023-01-24 09:04:14.599438: step: 1560/530, loss: 0.00012007732584606856
2023-01-24 09:04:15.649593: step: 1564/530, loss: 0.0010876161977648735
2023-01-24 09:04:16.720060: step: 1568/530, loss: 0.00012068310752511024
2023-01-24 09:04:17.780768: step: 1572/530, loss: 7.002367055974901e-06
2023-01-24 09:04:18.827168: step: 1576/530, loss: 0.002143105026334524
2023-01-24 09:04:19.894441: step: 1580/530, loss: 0.004553679376840591
2023-01-24 09:04:20.956122: step: 1584/530, loss: 0.0006215042667463422
2023-01-24 09:04:22.009434: step: 1588/530, loss: 4.3228345020907e-05
2023-01-24 09:04:23.061268: step: 1592/530, loss: 0.0002511601778678596
2023-01-24 09:04:24.125395: step: 1596/530, loss: 0.00047809912939555943
2023-01-24 09:04:25.180415: step: 1600/530, loss: 0.001023935736157
2023-01-24 09:04:26.241662: step: 1604/530, loss: 5.057837915956043e-05
2023-01-24 09:04:27.307104: step: 1608/530, loss: 0.000748688296880573
2023-01-24 09:04:28.360396: step: 1612/530, loss: 0.00024229013069998473
2023-01-24 09:04:29.418117: step: 1616/530, loss: 1.9422168406890705e-06
2023-01-24 09:04:30.457977: step: 1620/530, loss: 3.119130997220054e-05
2023-01-24 09:04:31.511348: step: 1624/530, loss: 0.0003685960255097598
2023-01-24 09:04:32.582985: step: 1628/530, loss: 0.00042629207018762827
2023-01-24 09:04:33.660710: step: 1632/530, loss: 0.0030993702821433544
2023-01-24 09:04:34.709768: step: 1636/530, loss: 0.001755658071488142
2023-01-24 09:04:35.760039: step: 1640/530, loss: 0.00043842277955263853
2023-01-24 09:04:36.816689: step: 1644/530, loss: 0.0028608699794858694
2023-01-24 09:04:37.875735: step: 1648/530, loss: 0.009217122569680214
2023-01-24 09:04:38.943362: step: 1652/530, loss: 0.00317751569673419
2023-01-24 09:04:39.998942: step: 1656/530, loss: 0.0011297761229798198
2023-01-24 09:04:41.044889: step: 1660/530, loss: 1.0433981515234336e-05
2023-01-24 09:04:42.109701: step: 1664/530, loss: 0.0004397172888275236
2023-01-24 09:04:43.180248: step: 1668/530, loss: 0.002238500863313675
2023-01-24 09:04:44.246765: step: 1672/530, loss: 0.0022370817605406046
2023-01-24 09:04:45.300973: step: 1676/530, loss: 0.0035973885096609592
2023-01-24 09:04:46.356561: step: 1680/530, loss: 8.798352791927755e-05
2023-01-24 09:04:47.409740: step: 1684/530, loss: 0.00458543049171567
2023-01-24 09:04:48.483770: step: 1688/530, loss: 0.0029092200566083193
2023-01-24 09:04:49.529065: step: 1692/530, loss: 1.9163313481840305e-05
2023-01-24 09:04:50.591072: step: 1696/530, loss: 0.0016301489667966962
2023-01-24 09:04:51.650938: step: 1700/530, loss: 0.002227955497801304
2023-01-24 09:04:52.704347: step: 1704/530, loss: 0.0010239663533866405
2023-01-24 09:04:53.752817: step: 1708/530, loss: 0.0010610586032271385
2023-01-24 09:04:54.805115: step: 1712/530, loss: 0.00018567325605545193
2023-01-24 09:04:55.856454: step: 1716/530, loss: 7.646896119695157e-05
2023-01-24 09:04:56.908397: step: 1720/530, loss: 1.054508720699232e-05
2023-01-24 09:04:57.970244: step: 1724/530, loss: 0.0005834304611198604
2023-01-24 09:04:59.029123: step: 1728/530, loss: 0.00032743901829235256
2023-01-24 09:05:00.088626: step: 1732/530, loss: 0.010699824430048466
2023-01-24 09:05:01.137422: step: 1736/530, loss: 0.0001258936244994402
2023-01-24 09:05:02.199208: step: 1740/530, loss: 0.00025616458151489496
2023-01-24 09:05:03.285469: step: 1744/530, loss: 0.00027458544354885817
2023-01-24 09:05:04.331529: step: 1748/530, loss: 6.776011787223979e-07
2023-01-24 09:05:05.383735: step: 1752/530, loss: 3.7080109905218706e-05
2023-01-24 09:05:06.434129: step: 1756/530, loss: 0.004809232894331217
2023-01-24 09:05:07.473636: step: 1760/530, loss: 0.000706952647306025
2023-01-24 09:05:08.538512: step: 1764/530, loss: 0.0028235595673322678
2023-01-24 09:05:09.586408: step: 1768/530, loss: 0.0016812203684821725
2023-01-24 09:05:10.618279: step: 1772/530, loss: 8.328335388796404e-05
2023-01-24 09:05:11.669265: step: 1776/530, loss: 0.0018091369420289993
2023-01-24 09:05:12.724662: step: 1780/530, loss: 0.013767399825155735
2023-01-24 09:05:13.784936: step: 1784/530, loss: 0.0005033770576119423
2023-01-24 09:05:14.839936: step: 1788/530, loss: 2.011625110753812e-05
2023-01-24 09:05:15.909757: step: 1792/530, loss: 7.018488395260647e-05
2023-01-24 09:05:16.960775: step: 1796/530, loss: 0.004645438864827156
2023-01-24 09:05:18.024604: step: 1800/530, loss: 0.0003077214059885591
2023-01-24 09:05:19.085325: step: 1804/530, loss: 6.319866952253506e-05
2023-01-24 09:05:20.137905: step: 1808/530, loss: 6.23879095655866e-05
2023-01-24 09:05:21.197592: step: 1812/530, loss: 0.006554232910275459
2023-01-24 09:05:22.235721: step: 1816/530, loss: 0.00044025102397426963
2023-01-24 09:05:23.307822: step: 1820/530, loss: 0.00025310626369901
2023-01-24 09:05:24.394981: step: 1824/530, loss: 0.0015613521682098508
2023-01-24 09:05:25.451433: step: 1828/530, loss: 0.0210096538066864
2023-01-24 09:05:26.516010: step: 1832/530, loss: 1.633365172892809e-05
2023-01-24 09:05:27.575359: step: 1836/530, loss: 0.005266386549919844
2023-01-24 09:05:28.636640: step: 1840/530, loss: 0.06566346436738968
2023-01-24 09:05:29.693068: step: 1844/530, loss: 0.0016165070701390505
2023-01-24 09:05:30.735996: step: 1848/530, loss: 0.004166364204138517
2023-01-24 09:05:31.795250: step: 1852/530, loss: 0.00019329850329086185
2023-01-24 09:05:32.867693: step: 1856/530, loss: 0.0032499053049832582
2023-01-24 09:05:33.923481: step: 1860/530, loss: 0.020395835861563683
2023-01-24 09:05:34.959788: step: 1864/530, loss: 0.00029200062272138894
2023-01-24 09:05:36.009410: step: 1868/530, loss: 0.0010121092200279236
2023-01-24 09:05:37.045157: step: 1872/530, loss: 0.009185848757624626
2023-01-24 09:05:38.099076: step: 1876/530, loss: 0.007306584157049656
2023-01-24 09:05:39.143665: step: 1880/530, loss: 0.0009480341104790568
2023-01-24 09:05:40.212356: step: 1884/530, loss: 0.004072495736181736
2023-01-24 09:05:41.263711: step: 1888/530, loss: 0.006742303259670734
2023-01-24 09:05:42.319311: step: 1892/530, loss: 0.00236950209364295
2023-01-24 09:05:43.366924: step: 1896/530, loss: 2.604699567143598e-08
2023-01-24 09:05:44.440010: step: 1900/530, loss: 0.00043559985351748765
2023-01-24 09:05:45.495680: step: 1904/530, loss: 0.00042992053204216063
2023-01-24 09:05:46.540715: step: 1908/530, loss: 0.00659569725394249
2023-01-24 09:05:47.584782: step: 1912/530, loss: 6.511341325676767e-06
2023-01-24 09:05:48.656476: step: 1916/530, loss: 0.013887734152376652
2023-01-24 09:05:49.702108: step: 1920/530, loss: 0.003350155660882592
2023-01-24 09:05:50.768329: step: 1924/530, loss: 0.0015852149808779359
2023-01-24 09:05:51.841981: step: 1928/530, loss: 0.0007855534204281867
2023-01-24 09:05:52.910641: step: 1932/530, loss: 6.717738142469898e-05
2023-01-24 09:05:53.973306: step: 1936/530, loss: 1.2404269000398926e-05
2023-01-24 09:05:55.045525: step: 1940/530, loss: 0.003950254060328007
2023-01-24 09:05:56.101563: step: 1944/530, loss: 0.0008896337240003049
2023-01-24 09:05:57.158588: step: 1948/530, loss: 0.002133734757080674
2023-01-24 09:05:58.206987: step: 1952/530, loss: 0.0023981048725545406
2023-01-24 09:05:59.265525: step: 1956/530, loss: 0.004024495370686054
2023-01-24 09:06:00.306074: step: 1960/530, loss: 0.001832007197663188
2023-01-24 09:06:01.364375: step: 1964/530, loss: 0.00044516808702610433
2023-01-24 09:06:02.398242: step: 1968/530, loss: 0.0005577250849455595
2023-01-24 09:06:03.453331: step: 1972/530, loss: 0.00012662411609198898
2023-01-24 09:06:04.506853: step: 1976/530, loss: 0.0005612174863927066
2023-01-24 09:06:05.557779: step: 1980/530, loss: 4.664589596359292e-06
2023-01-24 09:06:06.618607: step: 1984/530, loss: 0.0003954134590458125
2023-01-24 09:06:07.669082: step: 1988/530, loss: 0.0028227027505636215
2023-01-24 09:06:08.735000: step: 1992/530, loss: 0.0032181960996240377
2023-01-24 09:06:09.794080: step: 1996/530, loss: 0.006779888179153204
2023-01-24 09:06:10.829265: step: 2000/530, loss: 0.005467736627906561
2023-01-24 09:06:11.894694: step: 2004/530, loss: 0.013756637461483479
2023-01-24 09:06:12.945227: step: 2008/530, loss: 0.0007858102326281369
2023-01-24 09:06:13.998654: step: 2012/530, loss: 1.3361885748963687e-06
2023-01-24 09:06:15.060623: step: 2016/530, loss: 0.005576764699071646
2023-01-24 09:06:16.124002: step: 2020/530, loss: 0.000756444875150919
2023-01-24 09:06:17.193192: step: 2024/530, loss: 0.0013267290778458118
2023-01-24 09:06:18.250561: step: 2028/530, loss: 0.0017476563807576895
2023-01-24 09:06:19.312871: step: 2032/530, loss: 0.0017575218807905912
2023-01-24 09:06:20.358494: step: 2036/530, loss: 0.003545111045241356
2023-01-24 09:06:21.411197: step: 2040/530, loss: 9.358391253044829e-05
2023-01-24 09:06:22.458196: step: 2044/530, loss: 0.0011822226224467158
2023-01-24 09:06:23.504330: step: 2048/530, loss: 0.0008207531645894051
2023-01-24 09:06:24.572471: step: 2052/530, loss: 0.003093077102676034
2023-01-24 09:06:25.640433: step: 2056/530, loss: 0.008489741012454033
2023-01-24 09:06:26.701224: step: 2060/530, loss: 0.0007912173750810325
2023-01-24 09:06:27.767166: step: 2064/530, loss: 0.00011926981096621603
2023-01-24 09:06:28.809356: step: 2068/530, loss: 0.00023459186195395887
2023-01-24 09:06:29.861829: step: 2072/530, loss: 0.0018284308025613427
2023-01-24 09:06:30.921434: step: 2076/530, loss: 0.00011667969374684617
2023-01-24 09:06:31.974037: step: 2080/530, loss: 0.00277364207431674
2023-01-24 09:06:33.052250: step: 2084/530, loss: 0.00027282341034151614
2023-01-24 09:06:34.101697: step: 2088/530, loss: 0.0037249084562063217
2023-01-24 09:06:35.160221: step: 2092/530, loss: 0.01464503537863493
2023-01-24 09:06:36.200210: step: 2096/530, loss: 3.0795246857451275e-05
2023-01-24 09:06:37.258178: step: 2100/530, loss: 4.297842679079622e-05
2023-01-24 09:06:38.330633: step: 2104/530, loss: 0.000861082982737571
2023-01-24 09:06:39.414962: step: 2108/530, loss: 0.003851526416838169
2023-01-24 09:06:40.487133: step: 2112/530, loss: 0.0066820536740124226
2023-01-24 09:06:41.545072: step: 2116/530, loss: 0.0022826846688985825
2023-01-24 09:06:42.602804: step: 2120/530, loss: 0.012766195461153984
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.386620406888845, 'r': 0.33820115289517566, 'f1': 0.3607935376027481}, 'combined': 0.26584786981255126, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3986230005389675, 'r': 0.29784558395249255, 'f1': 0.3409431610159851}, 'combined': 0.22611774409350305, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35014568764568765, 'r': 0.2844933712121212, 'f1': 0.3139237199582028}, 'combined': 0.20928247997213517, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4009253520072066, 'r': 0.29618533790151763, 'f1': 0.3406868165314969}, 'combined': 0.22234297499950323, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3706247903735779, 'r': 0.33264805663510877, 'f1': 0.3506110516934046}, 'combined': 0.25834498545829815, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39715017758785953, 'r': 0.3094676708476828, 'f1': 0.347868768690096}, 'combined': 0.23071089322451957, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37645101459851243, 'r': 0.3350199731436477, 'f1': 0.35452916836687215}, 'combined': 0.2612320187966426, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3980753757902061, 'r': 0.3070867184667304, 'f1': 0.34671081117211494}, 'combined': 0.22994292139912284, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:09:05.508021: step: 4/530, loss: 4.358332807896659e-05
2023-01-24 09:09:06.566471: step: 8/530, loss: 0.0001222815626533702
2023-01-24 09:09:07.604575: step: 12/530, loss: 0.00037242783582769334
2023-01-24 09:09:08.651153: step: 16/530, loss: 0.00019953807350248098
2023-01-24 09:09:09.723776: step: 20/530, loss: 0.0015346790896728635
2023-01-24 09:09:10.770031: step: 24/530, loss: 0.0005334898014552891
2023-01-24 09:09:11.819870: step: 28/530, loss: 0.0003760063846129924
2023-01-24 09:09:12.885185: step: 32/530, loss: 0.0001605412835488096
2023-01-24 09:09:13.928869: step: 36/530, loss: 0.0007944625103846192
2023-01-24 09:09:14.991258: step: 40/530, loss: 0.003619913011789322
2023-01-24 09:09:16.036646: step: 44/530, loss: 0.000696202798280865
2023-01-24 09:09:17.084687: step: 48/530, loss: 6.0909369494766e-05
2023-01-24 09:09:18.143430: step: 52/530, loss: 0.0011853754986077547
2023-01-24 09:09:19.202964: step: 56/530, loss: 0.0029107267037034035
2023-01-24 09:09:20.253496: step: 60/530, loss: 0.0012074995320290327
2023-01-24 09:09:21.312960: step: 64/530, loss: 0.0
2023-01-24 09:09:22.350834: step: 68/530, loss: 2.6410196369397454e-05
2023-01-24 09:09:23.419439: step: 72/530, loss: 0.0011837774654850364
2023-01-24 09:09:24.731227: step: 76/530, loss: 7.056760750856483e-06
2023-01-24 09:09:25.776787: step: 80/530, loss: 0.00019833551777992398
2023-01-24 09:09:26.822444: step: 84/530, loss: 0.0021719750948250294
2023-01-24 09:09:27.864919: step: 88/530, loss: 0.022907907143235207
2023-01-24 09:09:28.914247: step: 92/530, loss: 0.0030612957198172808
2023-01-24 09:09:29.967792: step: 96/530, loss: 1.803574377845507e-05
2023-01-24 09:09:31.012613: step: 100/530, loss: 0.00017038150690495968
2023-01-24 09:09:32.090721: step: 104/530, loss: 0.0011330187553539872
2023-01-24 09:09:33.135208: step: 108/530, loss: 0.0041223010048270226
2023-01-24 09:09:34.191571: step: 112/530, loss: 0.003346719779074192
2023-01-24 09:09:35.242085: step: 116/530, loss: 0.00016849975509103388
2023-01-24 09:09:36.306074: step: 120/530, loss: 0.0007259040721692145
2023-01-24 09:09:37.358522: step: 124/530, loss: 0.00664887111634016
2023-01-24 09:09:38.404829: step: 128/530, loss: 0.00209051207639277
2023-01-24 09:09:39.473200: step: 132/530, loss: 0.00332703092135489
2023-01-24 09:09:40.526001: step: 136/530, loss: 0.0027179408352822065
2023-01-24 09:09:41.584181: step: 140/530, loss: 0.0005587544874288142
2023-01-24 09:09:42.655534: step: 144/530, loss: 0.0028140260837972164
2023-01-24 09:09:43.707647: step: 148/530, loss: 0.0019028286915272474
2023-01-24 09:09:44.766205: step: 152/530, loss: 0.0031918652821332216
2023-01-24 09:09:45.810403: step: 156/530, loss: 0.0008683777996338904
2023-01-24 09:09:46.863120: step: 160/530, loss: 5.054091161582619e-05
2023-01-24 09:09:47.916568: step: 164/530, loss: 0.004312948789447546
2023-01-24 09:09:48.979276: step: 168/530, loss: 0.0012752775801345706
2023-01-24 09:09:50.033494: step: 172/530, loss: 0.0002565025060903281
2023-01-24 09:09:51.093887: step: 176/530, loss: 0.0006659210775978863
2023-01-24 09:09:52.148872: step: 180/530, loss: 7.552302849944681e-05
2023-01-24 09:09:53.200834: step: 184/530, loss: 0.00293757114559412
2023-01-24 09:09:54.257852: step: 188/530, loss: 0.0085314204916358
2023-01-24 09:09:55.311707: step: 192/530, loss: 9.237771882908419e-05
2023-01-24 09:09:56.362519: step: 196/530, loss: 0.0006973854033276439
2023-01-24 09:09:57.408063: step: 200/530, loss: 0.005273876246064901
2023-01-24 09:09:58.466193: step: 204/530, loss: 0.0009348890744149685
2023-01-24 09:09:59.517444: step: 208/530, loss: 0.0007975925109349191
2023-01-24 09:10:00.578275: step: 212/530, loss: 0.0047297729179263115
2023-01-24 09:10:01.633038: step: 216/530, loss: 1.019892079057172e-05
2023-01-24 09:10:02.695302: step: 220/530, loss: 0.0040236846543848515
2023-01-24 09:10:03.765577: step: 224/530, loss: 0.0074284435249865055
2023-01-24 09:10:04.842018: step: 228/530, loss: 0.0002129941276507452
2023-01-24 09:10:05.910213: step: 232/530, loss: 0.0024064898025244474
2023-01-24 09:10:06.959681: step: 236/530, loss: 0.0029794531874358654
2023-01-24 09:10:08.006846: step: 240/530, loss: 0.00036643038038164377
2023-01-24 09:10:09.074215: step: 244/530, loss: 0.0010701948776841164
2023-01-24 09:10:10.119600: step: 248/530, loss: 0.0036041669081896544
2023-01-24 09:10:11.165482: step: 252/530, loss: 4.41591655544471e-05
2023-01-24 09:10:12.217825: step: 256/530, loss: 0.0005571102374233305
2023-01-24 09:10:13.263201: step: 260/530, loss: 0.0005424362607300282
2023-01-24 09:10:14.309182: step: 264/530, loss: 0.002520616864785552
2023-01-24 09:10:15.373602: step: 268/530, loss: 0.0010175707284361124
2023-01-24 09:10:16.434693: step: 272/530, loss: 6.816221684857737e-06
2023-01-24 09:10:17.474483: step: 276/530, loss: 0.002496181521564722
2023-01-24 09:10:18.558012: step: 280/530, loss: 0.0010457811877131462
2023-01-24 09:10:19.595671: step: 284/530, loss: 1.5459572466625104e-07
2023-01-24 09:10:20.644168: step: 288/530, loss: 0.0018196814926341176
2023-01-24 09:10:21.709819: step: 292/530, loss: 0.00687964865937829
2023-01-24 09:10:22.773176: step: 296/530, loss: 6.041045708116144e-06
2023-01-24 09:10:23.822797: step: 300/530, loss: 0.0007787408540025353
2023-01-24 09:10:24.889423: step: 304/530, loss: 0.004605806432664394
2023-01-24 09:10:25.944929: step: 308/530, loss: 0.002598462626338005
2023-01-24 09:10:27.006714: step: 312/530, loss: 0.0005670848186127841
2023-01-24 09:10:28.084969: step: 316/530, loss: 0.006672226823866367
2023-01-24 09:10:29.142420: step: 320/530, loss: 0.0065813204273581505
2023-01-24 09:10:30.188845: step: 324/530, loss: 5.380020957090892e-05
2023-01-24 09:10:31.254195: step: 328/530, loss: 0.0037262907717376947
2023-01-24 09:10:32.333652: step: 332/530, loss: 0.0003701312525663525
2023-01-24 09:10:33.400396: step: 336/530, loss: 0.00015366739535238594
2023-01-24 09:10:34.460363: step: 340/530, loss: 0.00253116968087852
2023-01-24 09:10:35.515098: step: 344/530, loss: 0.0003403834125492722
2023-01-24 09:10:36.584509: step: 348/530, loss: 0.0015883836895227432
2023-01-24 09:10:37.648232: step: 352/530, loss: 0.002112868707627058
2023-01-24 09:10:38.703268: step: 356/530, loss: 0.001961903879418969
2023-01-24 09:10:39.745735: step: 360/530, loss: 0.0015745072159916162
2023-01-24 09:10:40.806205: step: 364/530, loss: 1.5377738236566074e-05
2023-01-24 09:10:41.861543: step: 368/530, loss: 0.0009542052284814417
2023-01-24 09:10:42.927123: step: 372/530, loss: 3.190553979948163e-05
2023-01-24 09:10:43.986254: step: 376/530, loss: 0.00013872676936443895
2023-01-24 09:10:45.048333: step: 380/530, loss: 0.0003621930372901261
2023-01-24 09:10:46.121853: step: 384/530, loss: 0.0018190853297710419
2023-01-24 09:10:47.181858: step: 388/530, loss: 0.00251941429451108
2023-01-24 09:10:48.238722: step: 392/530, loss: 7.396494765998796e-05
2023-01-24 09:10:49.280134: step: 396/530, loss: 0.00039291175198741257
2023-01-24 09:10:50.335536: step: 400/530, loss: 0.0031388038769364357
2023-01-24 09:10:51.388168: step: 404/530, loss: 0.0055846828036010265
2023-01-24 09:10:52.460350: step: 408/530, loss: 0.00625471118837595
2023-01-24 09:10:53.515454: step: 412/530, loss: 0.004725403152406216
2023-01-24 09:10:54.561626: step: 416/530, loss: 0.0
2023-01-24 09:10:55.619881: step: 420/530, loss: 1.6092570149339736e-05
2023-01-24 09:10:56.698335: step: 424/530, loss: 0.0005232045077718794
2023-01-24 09:10:57.750750: step: 428/530, loss: 0.0007933232118375599
2023-01-24 09:10:58.815380: step: 432/530, loss: 6.643269443884492e-05
2023-01-24 09:10:59.876508: step: 436/530, loss: 0.013064311817288399
2023-01-24 09:11:00.935228: step: 440/530, loss: 0.0010323922615498304
2023-01-24 09:11:01.983597: step: 444/530, loss: 9.289631270803511e-05
2023-01-24 09:11:03.057602: step: 448/530, loss: 0.001928345998749137
2023-01-24 09:11:04.129565: step: 452/530, loss: 0.0031566466204822063
2023-01-24 09:11:05.183139: step: 456/530, loss: 6.839210982434452e-06
2023-01-24 09:11:06.247978: step: 460/530, loss: 0.0008118044934235513
2023-01-24 09:11:07.307279: step: 464/530, loss: 0.0063606128096580505
2023-01-24 09:11:08.361041: step: 468/530, loss: 0.000748766993638128
2023-01-24 09:11:09.423204: step: 472/530, loss: 0.00223116809502244
2023-01-24 09:11:10.476193: step: 476/530, loss: 0.005639788694679737
2023-01-24 09:11:11.552782: step: 480/530, loss: 0.00019345695909578353
2023-01-24 09:11:12.601467: step: 484/530, loss: 0.0015198041219264269
2023-01-24 09:11:13.673155: step: 488/530, loss: 0.003536706557497382
2023-01-24 09:11:14.732201: step: 492/530, loss: 0.0008151055662892759
2023-01-24 09:11:15.797603: step: 496/530, loss: 3.203093365300447e-05
2023-01-24 09:11:16.863438: step: 500/530, loss: 0.003479176666587591
2023-01-24 09:11:17.930923: step: 504/530, loss: 0.0008451720350421965
2023-01-24 09:11:18.977294: step: 508/530, loss: 3.2402367651229724e-05
2023-01-24 09:11:20.037938: step: 512/530, loss: 0.000926514680031687
2023-01-24 09:11:21.092569: step: 516/530, loss: 0.0022055639419704676
2023-01-24 09:11:22.141667: step: 520/530, loss: 6.625810783589259e-05
2023-01-24 09:11:23.192670: step: 524/530, loss: 0.0022769938223063946
2023-01-24 09:11:24.245552: step: 528/530, loss: 7.696865213802084e-05
2023-01-24 09:11:25.352282: step: 532/530, loss: 0.006276157684624195
2023-01-24 09:11:26.405970: step: 536/530, loss: 0.00013256288366392255
2023-01-24 09:11:27.452870: step: 540/530, loss: 1.2412041542120278e-05
2023-01-24 09:11:28.513620: step: 544/530, loss: 0.00023237848654389381
2023-01-24 09:11:29.563017: step: 548/530, loss: 0.0012774645583704114
2023-01-24 09:11:30.642261: step: 552/530, loss: 0.0011081855045631528
2023-01-24 09:11:31.705878: step: 556/530, loss: 0.00021407069289125502
2023-01-24 09:11:32.788204: step: 560/530, loss: 2.156742311854032e-06
2023-01-24 09:11:33.860404: step: 564/530, loss: 7.0766827775514685e-06
2023-01-24 09:11:34.917544: step: 568/530, loss: 0.0007736588013358414
2023-01-24 09:11:35.987848: step: 572/530, loss: 0.0018381121335551143
2023-01-24 09:11:37.044449: step: 576/530, loss: 0.04918888211250305
2023-01-24 09:11:38.105305: step: 580/530, loss: 0.0008418259094469249
2023-01-24 09:11:39.164490: step: 584/530, loss: 0.0017115594819188118
2023-01-24 09:11:40.210221: step: 588/530, loss: 0.0037227999418973923
2023-01-24 09:11:41.273783: step: 592/530, loss: 0.01742004230618477
2023-01-24 09:11:42.334305: step: 596/530, loss: 0.0006874825339764357
2023-01-24 09:11:43.381507: step: 600/530, loss: 0.0021324604749679565
2023-01-24 09:11:44.426079: step: 604/530, loss: 0.006022090557962656
2023-01-24 09:11:45.489627: step: 608/530, loss: 0.0004250803904142231
2023-01-24 09:11:46.565227: step: 612/530, loss: 0.002226212527602911
2023-01-24 09:11:47.626946: step: 616/530, loss: 0.012614063918590546
2023-01-24 09:11:48.673315: step: 620/530, loss: 0.0003680614463519305
2023-01-24 09:11:49.734519: step: 624/530, loss: 0.0007466141832992435
2023-01-24 09:11:50.799994: step: 628/530, loss: 0.0003385867166798562
2023-01-24 09:11:51.859527: step: 632/530, loss: 0.00013613130431622267
2023-01-24 09:11:52.903997: step: 636/530, loss: 7.823104830606553e-09
2023-01-24 09:11:53.960621: step: 640/530, loss: 1.2813528655897244e-06
2023-01-24 09:11:55.033174: step: 644/530, loss: 0.004567637573927641
2023-01-24 09:11:56.083513: step: 648/530, loss: 0.0025851507671177387
2023-01-24 09:11:57.140355: step: 652/530, loss: 0.007685238961130381
2023-01-24 09:11:58.194738: step: 656/530, loss: 7.399920377793023e-06
2023-01-24 09:11:59.258685: step: 660/530, loss: 0.0012012807419523597
2023-01-24 09:12:00.309529: step: 664/530, loss: 0.0005388844874687493
2023-01-24 09:12:01.358456: step: 668/530, loss: 0.0004091424052603543
2023-01-24 09:12:02.430649: step: 672/530, loss: 0.004368112422525883
2023-01-24 09:12:03.479304: step: 676/530, loss: 0.004165349528193474
2023-01-24 09:12:04.532422: step: 680/530, loss: 0.0014751310227438807
2023-01-24 09:12:05.603449: step: 684/530, loss: 0.004650105256587267
2023-01-24 09:12:06.651774: step: 688/530, loss: 0.0005390184815041721
2023-01-24 09:12:07.711223: step: 692/530, loss: 0.000247360352659598
2023-01-24 09:12:08.751866: step: 696/530, loss: 0.0036877612583339214
2023-01-24 09:12:09.816520: step: 700/530, loss: 0.004171156324446201
2023-01-24 09:12:10.889379: step: 704/530, loss: 0.02749238722026348
2023-01-24 09:12:11.945744: step: 708/530, loss: 0.0005593261448666453
2023-01-24 09:12:13.005919: step: 712/530, loss: 0.002645747270435095
2023-01-24 09:12:14.055295: step: 716/530, loss: 0.0038409684784710407
2023-01-24 09:12:15.111744: step: 720/530, loss: 0.006444224622100592
2023-01-24 09:12:16.153539: step: 724/530, loss: 0.00019817698921542615
2023-01-24 09:12:17.225604: step: 728/530, loss: 0.010310865007340908
2023-01-24 09:12:18.301498: step: 732/530, loss: 1.1548365819180617e-07
2023-01-24 09:12:19.372796: step: 736/530, loss: 0.0008617074345238507
2023-01-24 09:12:20.438420: step: 740/530, loss: 0.004651867784559727
2023-01-24 09:12:21.490019: step: 744/530, loss: 0.002701647114008665
2023-01-24 09:12:22.540951: step: 748/530, loss: 1.1392212400096469e-06
2023-01-24 09:12:23.595062: step: 752/530, loss: 8.342586079379544e-05
2023-01-24 09:12:24.654212: step: 756/530, loss: 0.0
2023-01-24 09:12:25.722663: step: 760/530, loss: 0.0024088951759040356
2023-01-24 09:12:26.793650: step: 764/530, loss: 0.004983244463801384
2023-01-24 09:12:27.840455: step: 768/530, loss: 0.0034380133729428053
2023-01-24 09:12:28.908845: step: 772/530, loss: 0.002349910093471408
2023-01-24 09:12:29.959862: step: 776/530, loss: 0.000318461301503703
2023-01-24 09:12:31.008029: step: 780/530, loss: 0.0014323717914521694
2023-01-24 09:12:32.092719: step: 784/530, loss: 0.0031647919677197933
2023-01-24 09:12:33.130448: step: 788/530, loss: 0.003769282018765807
2023-01-24 09:12:34.190727: step: 792/530, loss: 0.004636148922145367
2023-01-24 09:12:35.240157: step: 796/530, loss: 3.136169834760949e-05
2023-01-24 09:12:36.292911: step: 800/530, loss: 0.001004164689220488
2023-01-24 09:12:37.347271: step: 804/530, loss: 0.0023598624393343925
2023-01-24 09:12:38.396487: step: 808/530, loss: 0.00020291241526138037
2023-01-24 09:12:39.460690: step: 812/530, loss: 0.0016126090195029974
2023-01-24 09:12:40.526383: step: 816/530, loss: 4.961536319569859e-07
2023-01-24 09:12:41.585494: step: 820/530, loss: 0.002547695068642497
2023-01-24 09:12:42.650196: step: 824/530, loss: 0.010903198271989822
2023-01-24 09:12:43.708859: step: 828/530, loss: 0.0006640401552431285
2023-01-24 09:12:44.796281: step: 832/530, loss: 0.00965951383113861
2023-01-24 09:12:45.862314: step: 836/530, loss: 0.008431728929281235
2023-01-24 09:12:46.923248: step: 840/530, loss: 0.00041934216278605163
2023-01-24 09:12:47.966179: step: 844/530, loss: 2.2771193471271545e-05
2023-01-24 09:12:49.031674: step: 848/530, loss: 0.002858812687918544
2023-01-24 09:12:50.083307: step: 852/530, loss: 9.671240695752203e-05
2023-01-24 09:12:51.146546: step: 856/530, loss: 1.9999399228254333e-05
2023-01-24 09:12:52.196831: step: 860/530, loss: 0.0015814757207408547
2023-01-24 09:12:53.249224: step: 864/530, loss: 0.0038441878277808428
2023-01-24 09:12:54.309091: step: 868/530, loss: 0.003081025555729866
2023-01-24 09:12:55.351933: step: 872/530, loss: 0.006502851378172636
2023-01-24 09:12:56.397676: step: 876/530, loss: 0.0036619931925088167
2023-01-24 09:12:57.458037: step: 880/530, loss: 0.004631872288882732
2023-01-24 09:12:58.527538: step: 884/530, loss: 0.0006069493247196078
2023-01-24 09:12:59.593818: step: 888/530, loss: 0.0002082035061903298
2023-01-24 09:13:00.647211: step: 892/530, loss: 0.0013439744943752885
2023-01-24 09:13:01.702217: step: 896/530, loss: 0.00020763858628924936
2023-01-24 09:13:02.799198: step: 900/530, loss: 0.00020743614004459232
2023-01-24 09:13:03.856588: step: 904/530, loss: 0.0014298639725893736
2023-01-24 09:13:04.907654: step: 908/530, loss: 0.00015233505109790713
2023-01-24 09:13:05.961608: step: 912/530, loss: 1.6949562677837093e-06
2023-01-24 09:13:07.020923: step: 916/530, loss: 0.0029666146729141474
2023-01-24 09:13:08.084201: step: 920/530, loss: 0.0038765030913054943
2023-01-24 09:13:09.136242: step: 924/530, loss: 0.0006100321188569069
2023-01-24 09:13:10.198164: step: 928/530, loss: 9.341269105789252e-06
2023-01-24 09:13:11.275598: step: 932/530, loss: 9.834764205152169e-05
2023-01-24 09:13:12.322030: step: 936/530, loss: 0.0001672635698923841
2023-01-24 09:13:13.383144: step: 940/530, loss: 0.00016907465760596097
2023-01-24 09:13:14.426958: step: 944/530, loss: 4.353276835900033e-06
2023-01-24 09:13:15.494556: step: 948/530, loss: 0.001261532655917108
2023-01-24 09:13:16.554370: step: 952/530, loss: 0.00028174096951261163
2023-01-24 09:13:17.608227: step: 956/530, loss: 2.0496001525316387e-05
2023-01-24 09:13:18.685495: step: 960/530, loss: 0.0011348148109391332
2023-01-24 09:13:19.753113: step: 964/530, loss: 0.003016910282894969
2023-01-24 09:13:20.799950: step: 968/530, loss: 6.167294486658648e-06
2023-01-24 09:13:21.861364: step: 972/530, loss: 0.0020489676389843225
2023-01-24 09:13:22.931913: step: 976/530, loss: 0.0005256329895928502
2023-01-24 09:13:23.992328: step: 980/530, loss: 0.002442756202071905
2023-01-24 09:13:25.038644: step: 984/530, loss: 0.0012856120010837913
2023-01-24 09:13:26.116252: step: 988/530, loss: 0.00038124556886032224
2023-01-24 09:13:27.185791: step: 992/530, loss: 0.0017621335573494434
2023-01-24 09:13:28.239010: step: 996/530, loss: 0.001312508713454008
2023-01-24 09:13:29.291018: step: 1000/530, loss: 2.6656339358055448e-08
2023-01-24 09:13:30.334711: step: 1004/530, loss: 0.003280250821262598
2023-01-24 09:13:31.391126: step: 1008/530, loss: 4.267723124939948e-05
2023-01-24 09:13:32.449806: step: 1012/530, loss: 5.9973299357807264e-05
2023-01-24 09:13:33.495216: step: 1016/530, loss: 0.00016806698113214225
2023-01-24 09:13:34.568519: step: 1020/530, loss: 0.0076988753862679005
2023-01-24 09:13:35.629736: step: 1024/530, loss: 0.0017748448299244046
2023-01-24 09:13:36.688549: step: 1028/530, loss: 7.556439959444106e-05
2023-01-24 09:13:37.743370: step: 1032/530, loss: 0.0007024398073554039
2023-01-24 09:13:38.789691: step: 1036/530, loss: 0.0002144437748938799
2023-01-24 09:13:39.849293: step: 1040/530, loss: 0.002975761890411377
2023-01-24 09:13:40.911009: step: 1044/530, loss: 0.00018304727564100176
2023-01-24 09:13:41.976073: step: 1048/530, loss: 0.0013600110542029142
2023-01-24 09:13:43.024092: step: 1052/530, loss: 1.528535221950733e-06
2023-01-24 09:13:44.078872: step: 1056/530, loss: 0.0011544511653482914
2023-01-24 09:13:45.135482: step: 1060/530, loss: 5.596477785729803e-05
2023-01-24 09:13:46.187598: step: 1064/530, loss: 0.00022398446162696928
2023-01-24 09:13:47.253830: step: 1068/530, loss: 0.0025621468666940928
2023-01-24 09:13:48.301895: step: 1072/530, loss: 0.0022698238026350737
2023-01-24 09:13:49.357853: step: 1076/530, loss: 0.002758368384093046
2023-01-24 09:13:50.437398: step: 1080/530, loss: 0.023883560672402382
2023-01-24 09:13:51.497618: step: 1084/530, loss: 0.0003798389807343483
2023-01-24 09:13:52.561348: step: 1088/530, loss: 0.011034381575882435
2023-01-24 09:13:53.621737: step: 1092/530, loss: 8.343707804669975e-07
2023-01-24 09:13:54.665745: step: 1096/530, loss: 3.8988386222627014e-05
2023-01-24 09:13:55.714855: step: 1100/530, loss: 0.009063157252967358
2023-01-24 09:13:56.747797: step: 1104/530, loss: 0.003054446540772915
2023-01-24 09:13:57.801992: step: 1108/530, loss: 0.004694691859185696
2023-01-24 09:13:58.861432: step: 1112/530, loss: 0.002871186938136816
2023-01-24 09:13:59.928413: step: 1116/530, loss: 0.00413478771224618
2023-01-24 09:14:00.979222: step: 1120/530, loss: 0.0037038077134639025
2023-01-24 09:14:02.044443: step: 1124/530, loss: 0.001354366890154779
2023-01-24 09:14:03.119164: step: 1128/530, loss: 0.010890726000070572
2023-01-24 09:14:04.164631: step: 1132/530, loss: 0.002016516635194421
2023-01-24 09:14:05.212683: step: 1136/530, loss: 0.000916333228815347
2023-01-24 09:14:06.277286: step: 1140/530, loss: 0.006287013180553913
2023-01-24 09:14:07.321758: step: 1144/530, loss: 0.0013387412764132023
2023-01-24 09:14:08.390557: step: 1148/530, loss: 0.0
2023-01-24 09:14:09.469000: step: 1152/530, loss: 0.0005171552766114473
2023-01-24 09:14:10.527045: step: 1156/530, loss: 0.0017185205360874534
2023-01-24 09:14:11.583028: step: 1160/530, loss: 0.0003559146716725081
2023-01-24 09:14:12.643704: step: 1164/530, loss: 0.000423509773099795
2023-01-24 09:14:13.695521: step: 1168/530, loss: 0.00029431929579004645
2023-01-24 09:14:14.733396: step: 1172/530, loss: 0.001086080214008689
2023-01-24 09:14:15.788250: step: 1176/530, loss: 0.0009367995662614703
2023-01-24 09:14:16.840055: step: 1180/530, loss: 0.016340885311365128
2023-01-24 09:14:17.890389: step: 1184/530, loss: 0.0018556666327640414
2023-01-24 09:14:18.952827: step: 1188/530, loss: 0.0019157781498506665
2023-01-24 09:14:20.011044: step: 1192/530, loss: 0.000545868300832808
2023-01-24 09:14:21.080324: step: 1196/530, loss: 0.0022360514849424362
2023-01-24 09:14:22.145750: step: 1200/530, loss: 0.0006502094329334795
2023-01-24 09:14:23.197712: step: 1204/530, loss: 2.955450145236682e-05
2023-01-24 09:14:24.252152: step: 1208/530, loss: 0.005296939052641392
2023-01-24 09:14:25.299227: step: 1212/530, loss: 2.97556853183778e-05
2023-01-24 09:14:26.344559: step: 1216/530, loss: 0.004185340367257595
2023-01-24 09:14:27.406003: step: 1220/530, loss: 0.0014158920384943485
2023-01-24 09:14:28.462637: step: 1224/530, loss: 0.0016025553923100233
2023-01-24 09:14:29.513308: step: 1228/530, loss: 0.01026669517159462
2023-01-24 09:14:30.561141: step: 1232/530, loss: 0.0005135299870744348
2023-01-24 09:14:31.630024: step: 1236/530, loss: 4.446384991751984e-05
2023-01-24 09:14:32.678884: step: 1240/530, loss: 0.00016691209748387337
2023-01-24 09:14:33.741057: step: 1244/530, loss: 0.0014156574616208673
2023-01-24 09:14:34.808020: step: 1248/530, loss: 0.00014650814409833401
2023-01-24 09:14:35.869445: step: 1252/530, loss: 0.0006092636613175273
2023-01-24 09:14:36.912691: step: 1256/530, loss: 0.0019875189755111933
2023-01-24 09:14:37.976640: step: 1260/530, loss: 0.0006706563872285187
2023-01-24 09:14:39.042610: step: 1264/530, loss: 0.0016247257590293884
2023-01-24 09:14:40.095202: step: 1268/530, loss: 1.8511378584662452e-05
2023-01-24 09:14:41.152647: step: 1272/530, loss: 0.00027250946732237935
2023-01-24 09:14:42.201985: step: 1276/530, loss: 0.0032922381069511175
2023-01-24 09:14:43.247497: step: 1280/530, loss: 0.0008868347504176199
2023-01-24 09:14:44.311154: step: 1284/530, loss: 0.0013795640552416444
2023-01-24 09:14:45.367834: step: 1288/530, loss: 0.004981372971087694
2023-01-24 09:14:46.423286: step: 1292/530, loss: 0.0003823238948825747
2023-01-24 09:14:47.468375: step: 1296/530, loss: 0.0048320177011191845
2023-01-24 09:14:48.520429: step: 1300/530, loss: 0.01629387028515339
2023-01-24 09:14:49.586150: step: 1304/530, loss: 0.0005811612354591489
2023-01-24 09:14:50.652666: step: 1308/530, loss: 2.5535851818858646e-05
2023-01-24 09:14:51.718985: step: 1312/530, loss: 0.0021639582701027393
2023-01-24 09:14:52.772253: step: 1316/530, loss: 0.0001765547349350527
2023-01-24 09:14:53.835886: step: 1320/530, loss: 0.0021695985924452543
2023-01-24 09:14:54.889507: step: 1324/530, loss: 0.00022371923842001706
2023-01-24 09:14:55.957981: step: 1328/530, loss: 4.400361888201587e-07
2023-01-24 09:14:57.002862: step: 1332/530, loss: 1.7383737827003642e-07
2023-01-24 09:14:58.045858: step: 1336/530, loss: 0.0002773888409137726
2023-01-24 09:14:59.108251: step: 1340/530, loss: 0.007211625576019287
2023-01-24 09:15:00.181245: step: 1344/530, loss: 0.0002806336560752243
2023-01-24 09:15:01.248309: step: 1348/530, loss: 0.0029637389816343784
2023-01-24 09:15:02.313745: step: 1352/530, loss: 0.00015604398504365236
2023-01-24 09:15:03.384316: step: 1356/530, loss: 0.004185238387435675
2023-01-24 09:15:04.429769: step: 1360/530, loss: 0.012260166928172112
2023-01-24 09:15:05.472974: step: 1364/530, loss: 9.475841943640262e-05
2023-01-24 09:15:06.512502: step: 1368/530, loss: 7.681493298150599e-05
2023-01-24 09:15:07.563164: step: 1372/530, loss: 3.408749080335838e-06
2023-01-24 09:15:08.634013: step: 1376/530, loss: 0.0001385969517286867
2023-01-24 09:15:09.694293: step: 1380/530, loss: 0.001058325171470642
2023-01-24 09:15:10.757302: step: 1384/530, loss: 0.0030905918683856726
2023-01-24 09:15:11.803336: step: 1388/530, loss: 8.95018019946292e-05
2023-01-24 09:15:12.865066: step: 1392/530, loss: 0.004047696944326162
2023-01-24 09:15:13.910622: step: 1396/530, loss: 0.00015116769645828754
2023-01-24 09:15:14.980278: step: 1400/530, loss: 0.000206448879907839
2023-01-24 09:15:16.032539: step: 1404/530, loss: 8.953497854236048e-06
2023-01-24 09:15:17.091990: step: 1408/530, loss: 0.0025303333532065153
2023-01-24 09:15:18.148411: step: 1412/530, loss: 0.0001910560531541705
2023-01-24 09:15:19.213514: step: 1416/530, loss: 3.147565439576283e-05
2023-01-24 09:15:20.271721: step: 1420/530, loss: 0.0036020714323967695
2023-01-24 09:15:21.329532: step: 1424/530, loss: 0.00024343312543351203
2023-01-24 09:15:22.373409: step: 1428/530, loss: 0.0016813600668683648
2023-01-24 09:15:23.440207: step: 1432/530, loss: 0.007239566184580326
2023-01-24 09:15:24.487568: step: 1436/530, loss: 1.7316924640908837e-05
2023-01-24 09:15:25.549649: step: 1440/530, loss: 0.0053115058690309525
2023-01-24 09:15:26.627126: step: 1444/530, loss: 0.003082724055275321
2023-01-24 09:15:27.688193: step: 1448/530, loss: 0.0006793970824219286
2023-01-24 09:15:28.735508: step: 1452/530, loss: 0.00024168261734303087
2023-01-24 09:15:29.789967: step: 1456/530, loss: 7.014258881099522e-05
2023-01-24 09:15:30.852570: step: 1460/530, loss: 1.3151779057807289e-05
2023-01-24 09:15:31.924545: step: 1464/530, loss: 0.0012929317308589816
2023-01-24 09:15:32.968653: step: 1468/530, loss: 0.00027637367020361125
2023-01-24 09:15:34.023603: step: 1472/530, loss: 0.001176758436486125
2023-01-24 09:15:35.075376: step: 1476/530, loss: 2.7925574613618664e-05
2023-01-24 09:15:36.134735: step: 1480/530, loss: 0.0008473570342175663
2023-01-24 09:15:37.185107: step: 1484/530, loss: 7.32930566300638e-05
2023-01-24 09:15:38.235143: step: 1488/530, loss: 0.002474632579833269
2023-01-24 09:15:39.295596: step: 1492/530, loss: 0.0016974069876596332
2023-01-24 09:15:40.353178: step: 1496/530, loss: 0.007753693498671055
2023-01-24 09:15:41.408608: step: 1500/530, loss: 0.0005194901605136693
2023-01-24 09:15:42.456802: step: 1504/530, loss: 0.0016985370311886072
2023-01-24 09:15:43.513080: step: 1508/530, loss: 0.0027572494000196457
2023-01-24 09:15:44.555019: step: 1512/530, loss: 0.0043540699407458305
2023-01-24 09:15:45.601741: step: 1516/530, loss: 0.0005303248763084412
2023-01-24 09:15:46.667690: step: 1520/530, loss: 0.006779911927878857
2023-01-24 09:15:47.718280: step: 1524/530, loss: 0.0032566606532782316
2023-01-24 09:15:48.767157: step: 1528/530, loss: 1.0943324923573527e-05
2023-01-24 09:15:49.812033: step: 1532/530, loss: 5.825030257256003e-06
2023-01-24 09:15:50.881538: step: 1536/530, loss: 0.0052016787230968475
2023-01-24 09:15:51.950548: step: 1540/530, loss: 0.0030401197727769613
2023-01-24 09:15:52.997351: step: 1544/530, loss: 0.001184574794024229
2023-01-24 09:15:54.053526: step: 1548/530, loss: 0.0002245716896140948
2023-01-24 09:15:55.099525: step: 1552/530, loss: 0.0058486429043114185
2023-01-24 09:15:56.151336: step: 1556/530, loss: 0.0002876336802728474
2023-01-24 09:15:57.218506: step: 1560/530, loss: 0.0022663280833512545
2023-01-24 09:15:58.279848: step: 1564/530, loss: 0.000839273096062243
2023-01-24 09:15:59.331310: step: 1568/530, loss: 0.0032593607902526855
2023-01-24 09:16:00.391607: step: 1572/530, loss: 0.008406402543187141
2023-01-24 09:16:01.440796: step: 1576/530, loss: 0.00025903346249833703
2023-01-24 09:16:02.503367: step: 1580/530, loss: 3.8040841900510713e-05
2023-01-24 09:16:03.563947: step: 1584/530, loss: 0.0007708763005211949
2023-01-24 09:16:04.633885: step: 1588/530, loss: 0.0016108440468087792
2023-01-24 09:16:05.693397: step: 1592/530, loss: 0.0004349317750893533
2023-01-24 09:16:06.733615: step: 1596/530, loss: 1.9772909581661224e-05
2023-01-24 09:16:07.782545: step: 1600/530, loss: 5.2032377425348386e-05
2023-01-24 09:16:08.852490: step: 1604/530, loss: 0.002038426697254181
2023-01-24 09:16:09.920405: step: 1608/530, loss: 0.0009587907115928829
2023-01-24 09:16:10.983734: step: 1612/530, loss: 0.003981547895818949
2023-01-24 09:16:12.043067: step: 1616/530, loss: 0.0011710278922691941
2023-01-24 09:16:13.100545: step: 1620/530, loss: 0.0007438991451635957
2023-01-24 09:16:14.161172: step: 1624/530, loss: 0.0018043600721284747
2023-01-24 09:16:15.223364: step: 1628/530, loss: 0.0015680512879043818
2023-01-24 09:16:16.269326: step: 1632/530, loss: 0.0010865392396226525
2023-01-24 09:16:17.337627: step: 1636/530, loss: 0.001785994740203023
2023-01-24 09:16:18.391968: step: 1640/530, loss: 4.9126210797112435e-05
2023-01-24 09:16:19.454442: step: 1644/530, loss: 3.431293953326531e-05
2023-01-24 09:16:20.506488: step: 1648/530, loss: 3.208514317520894e-05
2023-01-24 09:16:21.561691: step: 1652/530, loss: 0.004645385779440403
2023-01-24 09:16:22.626146: step: 1656/530, loss: 0.005052377935498953
2023-01-24 09:16:23.675405: step: 1660/530, loss: 0.006233102176338434
2023-01-24 09:16:24.736387: step: 1664/530, loss: 0.0032794878352433443
2023-01-24 09:16:25.807291: step: 1668/530, loss: 0.003302312921732664
2023-01-24 09:16:26.863524: step: 1672/530, loss: 7.185374852269888e-05
2023-01-24 09:16:27.922535: step: 1676/530, loss: 6.818242400186136e-05
2023-01-24 09:16:28.973073: step: 1680/530, loss: 0.0009039552533067763
2023-01-24 09:16:30.032823: step: 1684/530, loss: 0.0016256526578217745
2023-01-24 09:16:31.080761: step: 1688/530, loss: 0.0015177977038547397
2023-01-24 09:16:32.148503: step: 1692/530, loss: 2.727987157413736e-05
2023-01-24 09:16:33.198907: step: 1696/530, loss: 0.00011824251123471186
2023-01-24 09:16:34.285994: step: 1700/530, loss: 0.0009916438721120358
2023-01-24 09:16:35.351971: step: 1704/530, loss: 9.497692190052476e-06
2023-01-24 09:16:36.414511: step: 1708/530, loss: 0.00812023226171732
2023-01-24 09:16:37.477246: step: 1712/530, loss: 8.056111983023584e-05
2023-01-24 09:16:38.539130: step: 1716/530, loss: 0.00035489178844727576
2023-01-24 09:16:39.583186: step: 1720/530, loss: 0.0001230276538990438
2023-01-24 09:16:40.640059: step: 1724/530, loss: 0.0056683882139623165
2023-01-24 09:16:41.679040: step: 1728/530, loss: 0.0003738945524673909
2023-01-24 09:16:42.733025: step: 1732/530, loss: 0.0005729576223529875
2023-01-24 09:16:43.798625: step: 1736/530, loss: 0.0008201290620490909
2023-01-24 09:16:44.852438: step: 1740/530, loss: 0.001202728133648634
2023-01-24 09:16:45.907897: step: 1744/530, loss: 0.0017263969639316201
2023-01-24 09:16:46.979726: step: 1748/530, loss: 0.0021032593213021755
2023-01-24 09:16:48.033683: step: 1752/530, loss: 0.003257678123190999
2023-01-24 09:16:49.086378: step: 1756/530, loss: 8.008502845768817e-06
2023-01-24 09:16:50.138551: step: 1760/530, loss: 2.317342114110943e-05
2023-01-24 09:16:51.195497: step: 1764/530, loss: 0.001302529708482325
2023-01-24 09:16:52.249568: step: 1768/530, loss: 0.01977110467851162
2023-01-24 09:16:53.311172: step: 1772/530, loss: 0.0033850783947855234
2023-01-24 09:16:54.369202: step: 1776/530, loss: 0.00316097354516387
2023-01-24 09:16:55.445501: step: 1780/530, loss: 0.0034116278402507305
2023-01-24 09:16:56.506886: step: 1784/530, loss: 0.0005083832074888051
2023-01-24 09:16:57.556387: step: 1788/530, loss: 0.0027566407807171345
2023-01-24 09:16:58.616851: step: 1792/530, loss: 0.0017061693361029029
2023-01-24 09:16:59.677701: step: 1796/530, loss: 9.384921577293426e-05
2023-01-24 09:17:00.731143: step: 1800/530, loss: 6.57826240058057e-05
2023-01-24 09:17:01.778169: step: 1804/530, loss: 0.007787159178406
2023-01-24 09:17:02.838164: step: 1808/530, loss: 0.00397125631570816
2023-01-24 09:17:03.888512: step: 1812/530, loss: 0.0001655475643929094
2023-01-24 09:17:04.935878: step: 1816/530, loss: 1.7508815730593597e-08
2023-01-24 09:17:05.984793: step: 1820/530, loss: 2.2891772459843196e-05
2023-01-24 09:17:07.044161: step: 1824/530, loss: 0.00040441000601276755
2023-01-24 09:17:08.099594: step: 1828/530, loss: 2.132779627572745e-05
2023-01-24 09:17:09.150136: step: 1832/530, loss: 0.00047313820687122643
2023-01-24 09:17:10.199964: step: 1836/530, loss: 1.781730679795146e-05
2023-01-24 09:17:11.255954: step: 1840/530, loss: 2.5383496904396452e-05
2023-01-24 09:17:12.318369: step: 1844/530, loss: 0.0005910950712859631
2023-01-24 09:17:13.384990: step: 1848/530, loss: 0.0001238746044691652
2023-01-24 09:17:14.424262: step: 1852/530, loss: 0.007283177226781845
2023-01-24 09:17:15.501975: step: 1856/530, loss: 0.006267290096729994
2023-01-24 09:17:16.562049: step: 1860/530, loss: 0.003503653919324279
2023-01-24 09:17:17.627177: step: 1864/530, loss: 0.002001160988584161
2023-01-24 09:17:18.680682: step: 1868/530, loss: 1.126896975733871e-08
2023-01-24 09:17:19.739673: step: 1872/530, loss: 8.465792780043557e-05
2023-01-24 09:17:20.804312: step: 1876/530, loss: 0.003231597598642111
2023-01-24 09:17:21.867324: step: 1880/530, loss: 0.0001995859493035823
2023-01-24 09:17:22.926380: step: 1884/530, loss: 0.010597738437354565
2023-01-24 09:17:23.977318: step: 1888/530, loss: 0.005382729694247246
2023-01-24 09:17:25.015297: step: 1892/530, loss: 0.00167090876493603
2023-01-24 09:17:26.077755: step: 1896/530, loss: 7.297228876268491e-05
2023-01-24 09:17:27.142008: step: 1900/530, loss: 0.008068029768764973
2023-01-24 09:17:28.197809: step: 1904/530, loss: 0.0005959459813311696
2023-01-24 09:17:29.253924: step: 1908/530, loss: 0.000444756296928972
2023-01-24 09:17:30.304184: step: 1912/530, loss: 4.090618313057348e-05
2023-01-24 09:17:31.369953: step: 1916/530, loss: 0.00695403665304184
2023-01-24 09:17:32.437198: step: 1920/530, loss: 0.0002737498434726149
2023-01-24 09:17:33.512284: step: 1924/530, loss: 5.258370492811082e-06
2023-01-24 09:17:34.570685: step: 1928/530, loss: 0.0008209809311665595
2023-01-24 09:17:35.616357: step: 1932/530, loss: 3.482078682282008e-05
2023-01-24 09:17:36.669973: step: 1936/530, loss: 7.039401680231094e-05
2023-01-24 09:17:37.722937: step: 1940/530, loss: 0.0022663441486656666
2023-01-24 09:17:38.788349: step: 1944/530, loss: 7.089827704476193e-05
2023-01-24 09:17:39.834848: step: 1948/530, loss: 0.003127817530184984
2023-01-24 09:17:40.887414: step: 1952/530, loss: 0.0023610026109963655
2023-01-24 09:17:41.929771: step: 1956/530, loss: 7.367778920297496e-08
2023-01-24 09:17:42.989079: step: 1960/530, loss: 0.00044750398956239223
2023-01-24 09:17:44.044652: step: 1964/530, loss: 0.0002953125222120434
2023-01-24 09:17:45.094974: step: 1968/530, loss: 0.0032857945188879967
2023-01-24 09:17:46.162538: step: 1972/530, loss: 0.000277798215392977
2023-01-24 09:17:47.214634: step: 1976/530, loss: 0.003090447746217251
2023-01-24 09:17:48.301280: step: 1980/530, loss: 0.0045261383056640625
2023-01-24 09:17:49.366903: step: 1984/530, loss: 0.0002901342522818595
2023-01-24 09:17:50.411108: step: 1988/530, loss: 0.001559880212880671
2023-01-24 09:17:51.488814: step: 1992/530, loss: 0.0010950490832328796
2023-01-24 09:17:52.530571: step: 1996/530, loss: 0.0001488328562118113
2023-01-24 09:17:53.592452: step: 2000/530, loss: 0.0023567762691527605
2023-01-24 09:17:54.648018: step: 2004/530, loss: 0.0008475448121316731
2023-01-24 09:17:55.695808: step: 2008/530, loss: 2.2833859475213103e-05
2023-01-24 09:17:56.756379: step: 2012/530, loss: 0.0005100523703731596
2023-01-24 09:17:57.805677: step: 2016/530, loss: 0.01809227094054222
2023-01-24 09:17:58.871346: step: 2020/530, loss: 0.006908607669174671
2023-01-24 09:17:59.921971: step: 2024/530, loss: 0.0006793041247874498
2023-01-24 09:18:00.966941: step: 2028/530, loss: 7.700379683228675e-06
2023-01-24 09:18:02.020350: step: 2032/530, loss: 0.0017141217831522226
2023-01-24 09:18:03.065020: step: 2036/530, loss: 0.0023029486183077097
2023-01-24 09:18:04.129973: step: 2040/530, loss: 8.715346484677866e-05
2023-01-24 09:18:05.199482: step: 2044/530, loss: 0.001045835204422474
2023-01-24 09:18:06.245572: step: 2048/530, loss: 9.370435691380408e-06
2023-01-24 09:18:07.284336: step: 2052/530, loss: 0.001589095452800393
2023-01-24 09:18:08.331999: step: 2056/530, loss: 0.00012409732153173536
2023-01-24 09:18:09.378150: step: 2060/530, loss: 0.004516906570643187
2023-01-24 09:18:10.427523: step: 2064/530, loss: 0.005698220804333687
2023-01-24 09:18:11.485581: step: 2068/530, loss: 0.00023478364164475352
2023-01-24 09:18:12.534613: step: 2072/530, loss: 0.0012739752419292927
2023-01-24 09:18:13.593065: step: 2076/530, loss: 0.003576847957447171
2023-01-24 09:18:14.645854: step: 2080/530, loss: 0.002340570092201233
2023-01-24 09:18:15.728695: step: 2084/530, loss: 0.002400406636297703
2023-01-24 09:18:16.794143: step: 2088/530, loss: 2.1095705960760824e-05
2023-01-24 09:18:17.850177: step: 2092/530, loss: 0.0019320037681609392
2023-01-24 09:18:18.910031: step: 2096/530, loss: 0.00022332361550070345
2023-01-24 09:18:19.976692: step: 2100/530, loss: 0.0001658980909269303
2023-01-24 09:18:21.031376: step: 2104/530, loss: 0.0015217919135466218
2023-01-24 09:18:22.091973: step: 2108/530, loss: 0.003103397088125348
2023-01-24 09:18:23.132543: step: 2112/530, loss: 0.0008773942245170474
2023-01-24 09:18:24.188719: step: 2116/530, loss: 7.185334106907248e-05
2023-01-24 09:18:25.253926: step: 2120/530, loss: 0.00010265658784192055
==================================================
Loss: 0.002
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38275700553926356, 'r': 0.33772676959346787, 'f1': 0.35883469269305956}, 'combined': 0.2644045104054123, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39503621220266466, 'r': 0.2989278350347437, 'f1': 0.3403269092805608}, 'combined': 0.22570903827933564, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3447413793103448, 'r': 0.2840198863636364, 'f1': 0.3114485981308412}, 'combined': 0.2076323987538941, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.39534291592817006, 'r': 0.2949655551249172, 'f1': 0.33785632815300687}, 'combined': 0.2204957088998571, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3735471252023061, 'r': 0.3388150395573099, 'f1': 0.35533437979443244}, 'combined': 0.2618253324801081, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39589973491067726, 'r': 0.31054992192993386, 'f1': 0.34806905369148333}, 'combined': 0.23084372472803036, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7115384615384616, 'r': 0.40217391304347827, 'f1': 0.513888888888889}, 'combined': 0.3425925925925926, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 19}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38795842411038495, 'r': 0.33789927261227076, 'f1': 0.36120267072346185}, 'combined': 0.26614933632255083, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3993718196792636, 'r': 0.2963304324373411, 'f1': 0.34022032750012815}, 'combined': 0.2256383519171834, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38541666666666663, 'r': 0.35238095238095235, 'f1': 0.36815920398009944}, 'combined': 0.24543946932006627, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3429360465116279, 'r': 0.2792850378787879, 'f1': 0.30785490605427973}, 'combined': 0.2052366040361865, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3728896603190763, 'r': 0.2911382876494694, 'f1': 0.32698159021653306}, 'combined': 0.21339851150973735, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7142857142857143, 'r': 0.43478260869565216, 'f1': 0.5405405405405405}, 'combined': 0.3603603603603603, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3735471252023061, 'r': 0.3388150395573099, 'f1': 0.35533437979443244}, 'combined': 0.2618253324801081, 'stategy': 1, 'epoch': 19}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.39589973491067726, 'r': 0.31054992192993386, 'f1': 0.34806905369148333}, 'combined': 0.23084372472803036, 'stategy': 1, 'epoch': 19}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'stategy': 1, 'epoch': 19}