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
2023-01-22 14:03:00.735256: step: 4/530, loss: 0.060033295303583145
2023-01-22 14:03:01.759526: step: 8/530, loss: 0.04589977115392685
2023-01-22 14:03:02.796184: step: 12/530, loss: 0.06528154015541077
2023-01-22 14:03:03.847437: step: 16/530, loss: 0.016343357041478157
2023-01-22 14:03:04.884838: step: 20/530, loss: 0.013062904588878155
2023-01-22 14:03:05.914943: step: 24/530, loss: 0.03764989227056503
2023-01-22 14:03:06.956147: step: 28/530, loss: 0.02163952775299549
2023-01-22 14:03:08.012486: step: 32/530, loss: 0.02140868827700615
2023-01-22 14:03:09.053071: step: 36/530, loss: 0.07444584369659424
2023-01-22 14:03:10.077602: step: 40/530, loss: 0.020764824002981186
2023-01-22 14:03:11.116429: step: 44/530, loss: 0.01761607453227043
2023-01-22 14:03:12.150603: step: 48/530, loss: 0.015811558812856674
2023-01-22 14:03:13.199830: step: 52/530, loss: 0.058635350316762924
2023-01-22 14:03:14.240853: step: 56/530, loss: 0.054577723145484924
2023-01-22 14:03:15.297108: step: 60/530, loss: 0.014780597761273384
2023-01-22 14:03:16.329843: step: 64/530, loss: 0.05506347492337227
2023-01-22 14:03:17.361463: step: 68/530, loss: 0.014647278934717178
2023-01-22 14:03:18.382480: step: 72/530, loss: 0.0471046157181263
2023-01-22 14:03:19.416482: step: 76/530, loss: 0.08761477470397949
2023-01-22 14:03:20.466098: step: 80/530, loss: 0.012713438831269741
2023-01-22 14:03:21.507193: step: 84/530, loss: 0.01254933699965477
2023-01-22 14:03:22.557645: step: 88/530, loss: 0.07934611290693283
2023-01-22 14:03:23.589157: step: 92/530, loss: 0.01443867851048708
2023-01-22 14:03:24.628967: step: 96/530, loss: 0.013973497785627842
2023-01-22 14:03:25.671273: step: 100/530, loss: 0.026187509298324585
2023-01-22 14:03:26.710822: step: 104/530, loss: 0.04219330847263336
2023-01-22 14:03:27.749905: step: 108/530, loss: 0.05404404550790787
2023-01-22 14:03:28.779623: step: 112/530, loss: 0.05650760233402252
2023-01-22 14:03:29.823572: step: 116/530, loss: 0.05717125162482262
2023-01-22 14:03:30.862845: step: 120/530, loss: 0.00882972776889801
2023-01-22 14:03:31.909365: step: 124/530, loss: 0.04490215703845024
2023-01-22 14:03:32.945948: step: 128/530, loss: 0.04658155515789986
2023-01-22 14:03:33.998322: step: 132/530, loss: 0.012538946233689785
2023-01-22 14:03:35.034741: step: 136/530, loss: 0.011128903366625309
2023-01-22 14:03:36.078774: step: 140/530, loss: 0.014826716855168343
2023-01-22 14:03:37.132027: step: 144/530, loss: 0.009929697029292583
2023-01-22 14:03:38.183200: step: 148/530, loss: 0.0678681805729866
2023-01-22 14:03:39.233233: step: 152/530, loss: 0.057826437056064606
2023-01-22 14:03:40.264458: step: 156/530, loss: 0.02970445156097412
2023-01-22 14:03:41.314662: step: 160/530, loss: 0.042627204209566116
2023-01-22 14:03:42.351213: step: 164/530, loss: 0.022546298801898956
2023-01-22 14:03:43.397951: step: 168/530, loss: 0.026655809953808784
2023-01-22 14:03:44.434105: step: 172/530, loss: 0.02497207559645176
2023-01-22 14:03:45.473328: step: 176/530, loss: 0.027215199545025826
2023-01-22 14:03:46.524614: step: 180/530, loss: 0.05222507193684578
2023-01-22 14:03:47.547644: step: 184/530, loss: 0.014712275005877018
2023-01-22 14:03:48.591262: step: 188/530, loss: 0.013996199704706669
2023-01-22 14:03:49.660112: step: 192/530, loss: 0.009635187685489655
2023-01-22 14:03:50.707796: step: 196/530, loss: 0.007943525910377502
2023-01-22 14:03:51.741700: step: 200/530, loss: 0.012248823419213295
2023-01-22 14:03:52.777341: step: 204/530, loss: 0.01388395857065916
2023-01-22 14:03:53.820245: step: 208/530, loss: 0.013846492394804955
2023-01-22 14:03:54.864818: step: 212/530, loss: 0.013890700414776802
2023-01-22 14:03:55.894767: step: 216/530, loss: 0.07550472766160965
2023-01-22 14:03:56.937361: step: 220/530, loss: 0.08688770234584808
2023-01-22 14:03:57.984803: step: 224/530, loss: 0.023570828139781952
2023-01-22 14:03:59.032631: step: 228/530, loss: 0.04166729003190994
2023-01-22 14:04:00.078175: step: 232/530, loss: 0.007473578676581383
2023-01-22 14:04:01.124157: step: 236/530, loss: 0.022276155650615692
2023-01-22 14:04:02.153932: step: 240/530, loss: 0.011229636147618294
2023-01-22 14:04:03.194074: step: 244/530, loss: 0.010996056720614433
2023-01-22 14:04:04.250043: step: 248/530, loss: 0.020953651517629623
2023-01-22 14:04:05.307998: step: 252/530, loss: 0.014445587992668152
2023-01-22 14:04:06.351666: step: 256/530, loss: 0.041544608771800995
2023-01-22 14:04:07.391362: step: 260/530, loss: 0.0196048766374588
2023-01-22 14:04:08.431349: step: 264/530, loss: 0.01599714159965515
2023-01-22 14:04:09.471494: step: 268/530, loss: 0.07050645351409912
2023-01-22 14:04:10.512637: step: 272/530, loss: 0.0421467162668705
2023-01-22 14:04:11.559317: step: 276/530, loss: 0.010393726639449596
2023-01-22 14:04:12.596363: step: 280/530, loss: 0.06304173171520233
2023-01-22 14:04:13.646079: step: 284/530, loss: 0.01447010226547718
2023-01-22 14:04:14.700723: step: 288/530, loss: 0.025486130267381668
2023-01-22 14:04:15.759359: step: 292/530, loss: 0.05997813493013382
2023-01-22 14:04:16.793005: step: 296/530, loss: 0.022653279826045036
2023-01-22 14:04:17.826459: step: 300/530, loss: 0.04908964782953262
2023-01-22 14:04:18.878058: step: 304/530, loss: 0.01200844720005989
2023-01-22 14:04:19.935063: step: 308/530, loss: 0.0060731531120836735
2023-01-22 14:04:20.972436: step: 312/530, loss: 0.044333744794130325
2023-01-22 14:04:22.009298: step: 316/530, loss: 0.038436442613601685
2023-01-22 14:04:23.039987: step: 320/530, loss: 0.0136526795104146
2023-01-22 14:04:24.088379: step: 324/530, loss: 0.020266354084014893
2023-01-22 14:04:25.139197: step: 328/530, loss: 0.012559860944747925
2023-01-22 14:04:26.192129: step: 332/530, loss: 0.01112893782556057
2023-01-22 14:04:27.236936: step: 336/530, loss: 0.013241477310657501
2023-01-22 14:04:28.285506: step: 340/530, loss: 0.010125523433089256
2023-01-22 14:04:29.324138: step: 344/530, loss: 0.01344500482082367
2023-01-22 14:04:30.359740: step: 348/530, loss: 0.014855092391371727
2023-01-22 14:04:31.398584: step: 352/530, loss: 0.042773760855197906
2023-01-22 14:04:32.446971: step: 356/530, loss: 0.05051124840974808
2023-01-22 14:04:33.504170: step: 360/530, loss: 0.040631815791130066
2023-01-22 14:04:34.549353: step: 364/530, loss: 0.06396598368883133
2023-01-22 14:04:35.642442: step: 368/530, loss: 0.051768772304058075
2023-01-22 14:04:36.679073: step: 372/530, loss: 0.031925443559885025
2023-01-22 14:04:37.732408: step: 376/530, loss: 0.014670888893306255
2023-01-22 14:04:38.771075: step: 380/530, loss: 0.04033554345369339
2023-01-22 14:04:39.812508: step: 384/530, loss: 0.02209855057299137
2023-01-22 14:04:40.834409: step: 388/530, loss: 0.01255041267722845
2023-01-22 14:04:41.871546: step: 392/530, loss: 0.012206725776195526
2023-01-22 14:04:42.902300: step: 396/530, loss: 0.0161734726279974
2023-01-22 14:04:43.940663: step: 400/530, loss: 0.026487227529287338
2023-01-22 14:04:44.979882: step: 404/530, loss: 0.014444894157350063
2023-01-22 14:04:46.016797: step: 408/530, loss: 0.010333058424293995
2023-01-22 14:04:47.065660: step: 412/530, loss: 0.006082017906010151
2023-01-22 14:04:48.099998: step: 416/530, loss: 0.01638266071677208
2023-01-22 14:04:49.151016: step: 420/530, loss: 0.04391314834356308
2023-01-22 14:04:50.196606: step: 424/530, loss: 0.016791932284832
2023-01-22 14:04:51.232390: step: 428/530, loss: 0.013436893001198769
2023-01-22 14:04:52.309402: step: 432/530, loss: 0.02358480915427208
2023-01-22 14:04:53.343269: step: 436/530, loss: 0.009498543106019497
2023-01-22 14:04:54.396143: step: 440/530, loss: 0.009855261072516441
2023-01-22 14:04:55.432377: step: 444/530, loss: 0.017667284235358238
2023-01-22 14:04:56.476600: step: 448/530, loss: 0.04631337895989418
2023-01-22 14:04:57.524352: step: 452/530, loss: 0.014315621927380562
2023-01-22 14:04:58.563868: step: 456/530, loss: 0.01812603510916233
2023-01-22 14:04:59.617571: step: 460/530, loss: 0.04465753212571144
2023-01-22 14:05:00.671444: step: 464/530, loss: 0.03727440908551216
2023-01-22 14:05:01.718274: step: 468/530, loss: 0.012952454388141632
2023-01-22 14:05:02.771490: step: 472/530, loss: 0.046937499195337296
2023-01-22 14:05:03.822925: step: 476/530, loss: 0.05256005376577377
2023-01-22 14:05:04.866511: step: 480/530, loss: 0.01981108821928501
2023-01-22 14:05:05.901051: step: 484/530, loss: 0.011906221508979797
2023-01-22 14:05:06.936309: step: 488/530, loss: 0.020235009491443634
2023-01-22 14:05:07.961827: step: 492/530, loss: 0.0391661562025547
2023-01-22 14:05:09.017935: step: 496/530, loss: 0.01849944330751896
2023-01-22 14:05:10.065135: step: 500/530, loss: 0.036094486713409424
2023-01-22 14:05:11.095801: step: 504/530, loss: 0.04758574813604355
2023-01-22 14:05:12.152393: step: 508/530, loss: 0.008935992605984211
2023-01-22 14:05:13.185904: step: 512/530, loss: 0.010376857593655586
2023-01-22 14:05:14.236794: step: 516/530, loss: 0.0186650101095438
2023-01-22 14:05:15.278853: step: 520/530, loss: 0.04050913825631142
2023-01-22 14:05:16.317402: step: 524/530, loss: 0.013347795233130455
2023-01-22 14:05:17.359686: step: 528/530, loss: 0.0032928106375038624
2023-01-22 14:05:18.402945: step: 532/530, loss: 0.03926122188568115
2023-01-22 14:05:19.438937: step: 536/530, loss: 0.016761235892772675
2023-01-22 14:05:20.492576: step: 540/530, loss: 0.01184121798723936
2023-01-22 14:05:21.546486: step: 544/530, loss: 0.007499242201447487
2023-01-22 14:05:22.593907: step: 548/530, loss: 0.03016289323568344
2023-01-22 14:05:23.634297: step: 552/530, loss: 0.0
2023-01-22 14:05:24.686854: step: 556/530, loss: 0.06591839343309402
2023-01-22 14:05:25.718588: step: 560/530, loss: 0.016564559191465378
2023-01-22 14:05:26.767388: step: 564/530, loss: 0.040470533072948456
2023-01-22 14:05:27.809864: step: 568/530, loss: 0.013416310772299767
2023-01-22 14:05:28.858800: step: 572/530, loss: 0.013418116606771946
2023-01-22 14:05:29.902487: step: 576/530, loss: 0.026211488991975784
2023-01-22 14:05:30.944505: step: 580/530, loss: 0.010530592873692513
2023-01-22 14:05:31.974918: step: 584/530, loss: 0.006916653364896774
2023-01-22 14:05:33.021642: step: 588/530, loss: 0.023131463676691055
2023-01-22 14:05:34.055007: step: 592/530, loss: 0.008311344310641289
2023-01-22 14:05:35.104803: step: 596/530, loss: 0.010789063759148121
2023-01-22 14:05:36.130617: step: 600/530, loss: 0.013362892903387547
2023-01-22 14:05:37.171191: step: 604/530, loss: 0.0071099018678069115
2023-01-22 14:05:38.209141: step: 608/530, loss: 0.043009303510189056
2023-01-22 14:05:39.263171: step: 612/530, loss: 0.014970828779041767
2023-01-22 14:05:40.304518: step: 616/530, loss: 0.025337407365441322
2023-01-22 14:05:41.338382: step: 620/530, loss: 0.03408828750252724
2023-01-22 14:05:42.382394: step: 624/530, loss: 0.052135542035102844
2023-01-22 14:05:43.429255: step: 628/530, loss: 0.013007240369915962
2023-01-22 14:05:44.461579: step: 632/530, loss: 0.004831044934689999
2023-01-22 14:05:45.509938: step: 636/530, loss: 0.021757418289780617
2023-01-22 14:05:46.554649: step: 640/530, loss: 0.019257046282291412
2023-01-22 14:05:47.591619: step: 644/530, loss: 0.05620265007019043
2023-01-22 14:05:48.638738: step: 648/530, loss: 0.018570058047771454
2023-01-22 14:05:49.703414: step: 652/530, loss: 0.014045841060578823
2023-01-22 14:05:50.758760: step: 656/530, loss: 0.015940770506858826
2023-01-22 14:05:51.816081: step: 660/530, loss: 0.04787875711917877
2023-01-22 14:05:52.852394: step: 664/530, loss: 0.014105679467320442
2023-01-22 14:05:53.888332: step: 668/530, loss: 0.005747381132096052
2023-01-22 14:05:54.931928: step: 672/530, loss: 0.030748708173632622
2023-01-22 14:05:55.992464: step: 676/530, loss: 0.013762318529188633
2023-01-22 14:05:57.039250: step: 680/530, loss: 0.005123665556311607
2023-01-22 14:05:58.109750: step: 684/530, loss: 0.008086733520030975
2023-01-22 14:05:59.154490: step: 688/530, loss: 0.07292577624320984
2023-01-22 14:06:00.205022: step: 692/530, loss: 0.014001429080963135
2023-01-22 14:06:01.249013: step: 696/530, loss: 0.02192588895559311
2023-01-22 14:06:02.296190: step: 700/530, loss: 0.007155390921980143
2023-01-22 14:06:03.337355: step: 704/530, loss: 0.013085514307022095
2023-01-22 14:06:04.389307: step: 708/530, loss: 0.06873773038387299
2023-01-22 14:06:05.422337: step: 712/530, loss: 0.008516249246895313
2023-01-22 14:06:06.471802: step: 716/530, loss: 0.010924703441560268
2023-01-22 14:06:07.515408: step: 720/530, loss: 0.012691010721027851
2023-01-22 14:06:08.566342: step: 724/530, loss: 0.01605951227247715
2023-01-22 14:06:09.587936: step: 728/530, loss: 0.03922870010137558
2023-01-22 14:06:10.611372: step: 732/530, loss: 0.012207195162773132
2023-01-22 14:06:11.664603: step: 736/530, loss: 0.00918819010257721
2023-01-22 14:06:12.714001: step: 740/530, loss: 0.02580217644572258
2023-01-22 14:06:13.775263: step: 744/530, loss: 0.04725988581776619
2023-01-22 14:06:14.819634: step: 748/530, loss: 0.012820283882319927
2023-01-22 14:06:15.874365: step: 752/530, loss: 0.015654999762773514
2023-01-22 14:06:16.898192: step: 756/530, loss: 0.040799036622047424
2023-01-22 14:06:17.952128: step: 760/530, loss: 0.01090190839022398
2023-01-22 14:06:18.982248: step: 764/530, loss: 0.0206447821110487
2023-01-22 14:06:20.000514: step: 768/530, loss: 0.014084467664361
2023-01-22 14:06:21.032825: step: 772/530, loss: 0.01422564685344696
2023-01-22 14:06:22.057632: step: 776/530, loss: 0.021638158708810806
2023-01-22 14:06:23.119700: step: 780/530, loss: 0.013486064970493317
2023-01-22 14:06:24.174983: step: 784/530, loss: 0.012211788445711136
2023-01-22 14:06:25.208450: step: 788/530, loss: 0.008560619316995144
2023-01-22 14:06:26.259746: step: 792/530, loss: 0.010791781358420849
2023-01-22 14:06:27.307590: step: 796/530, loss: 0.003482502419501543
2023-01-22 14:06:28.361409: step: 800/530, loss: 0.028693271800875664
2023-01-22 14:06:29.401361: step: 804/530, loss: 0.016671275720000267
2023-01-22 14:06:30.437609: step: 808/530, loss: 0.012025181204080582
2023-01-22 14:06:31.478218: step: 812/530, loss: 0.00638112286105752
2023-01-22 14:06:32.510408: step: 816/530, loss: 0.025325119495391846
2023-01-22 14:06:33.550397: step: 820/530, loss: 0.011688685044646263
2023-01-22 14:06:34.611321: step: 824/530, loss: 0.017244286835193634
2023-01-22 14:06:35.646303: step: 828/530, loss: 0.02886471524834633
2023-01-22 14:06:36.689310: step: 832/530, loss: 0.008827954530715942
2023-01-22 14:06:37.733075: step: 836/530, loss: 0.009243848733603954
2023-01-22 14:06:38.786393: step: 840/530, loss: 0.0671924352645874
2023-01-22 14:06:39.827642: step: 844/530, loss: 0.008323246613144875
2023-01-22 14:06:40.864862: step: 848/530, loss: 0.02299247868359089
2023-01-22 14:06:41.905448: step: 852/530, loss: 0.007278129458427429
2023-01-22 14:06:42.960981: step: 856/530, loss: 0.013758787885308266
2023-01-22 14:06:43.996363: step: 860/530, loss: 0.0163110364228487
2023-01-22 14:06:45.051226: step: 864/530, loss: 0.020543154329061508
2023-01-22 14:06:46.087072: step: 868/530, loss: 0.0087375333532691
2023-01-22 14:06:47.128540: step: 872/530, loss: 0.01985197700560093
2023-01-22 14:06:48.155563: step: 876/530, loss: 0.009418798610568047
2023-01-22 14:06:49.187279: step: 880/530, loss: 0.021291011944413185
2023-01-22 14:06:50.220238: step: 884/530, loss: 0.004904871340841055
2023-01-22 14:06:51.269797: step: 888/530, loss: 0.006361250765621662
2023-01-22 14:06:52.325716: step: 892/530, loss: 0.01926605775952339
2023-01-22 14:06:53.364535: step: 896/530, loss: 0.008989362977445126
2023-01-22 14:06:54.400084: step: 900/530, loss: 0.008587433025240898
2023-01-22 14:06:55.439447: step: 904/530, loss: 0.013574305921792984
2023-01-22 14:06:56.480571: step: 908/530, loss: 0.014101570472121239
2023-01-22 14:06:57.529610: step: 912/530, loss: 0.02384394034743309
2023-01-22 14:06:58.563862: step: 916/530, loss: 0.013385653495788574
2023-01-22 14:06:59.619960: step: 920/530, loss: 0.009057825431227684
2023-01-22 14:07:00.679559: step: 924/530, loss: 0.006020522676408291
2023-01-22 14:07:01.717200: step: 928/530, loss: 0.02508201263844967
2023-01-22 14:07:02.754009: step: 932/530, loss: 0.01509543415158987
2023-01-22 14:07:03.802453: step: 936/530, loss: 0.045393481850624084
2023-01-22 14:07:04.850649: step: 940/530, loss: 0.010363052599132061
2023-01-22 14:07:05.877488: step: 944/530, loss: 0.00701740849763155
2023-01-22 14:07:06.920467: step: 948/530, loss: 0.005701584275811911
2023-01-22 14:07:07.962437: step: 952/530, loss: 0.010725860483944416
2023-01-22 14:07:08.990686: step: 956/530, loss: 0.030126554891467094
2023-01-22 14:07:10.034290: step: 960/530, loss: 0.06617061048746109
2023-01-22 14:07:11.070090: step: 964/530, loss: 0.01154240407049656
2023-01-22 14:07:12.116752: step: 968/530, loss: 0.034873731434345245
2023-01-22 14:07:13.154186: step: 972/530, loss: 0.07368557900190353
2023-01-22 14:07:14.192132: step: 976/530, loss: 0.05102427303791046
2023-01-22 14:07:15.224546: step: 980/530, loss: 0.011907286942005157
2023-01-22 14:07:16.269224: step: 984/530, loss: 0.020721912384033203
2023-01-22 14:07:17.301824: step: 988/530, loss: 0.01759176142513752
2023-01-22 14:07:18.337524: step: 992/530, loss: 0.0093492167070508
2023-01-22 14:07:19.385991: step: 996/530, loss: 0.008550026454031467
2023-01-22 14:07:20.443523: step: 1000/530, loss: 0.009914956986904144
2023-01-22 14:07:21.491111: step: 1004/530, loss: 0.008670113980770111
2023-01-22 14:07:22.550903: step: 1008/530, loss: 0.012163816951215267
2023-01-22 14:07:23.583127: step: 1012/530, loss: 0.03422226756811142
2023-01-22 14:07:24.632521: step: 1016/530, loss: 0.037570856511592865
2023-01-22 14:07:25.686105: step: 1020/530, loss: 0.013528211042284966
2023-01-22 14:07:26.720628: step: 1024/530, loss: 0.022508734837174416
2023-01-22 14:07:27.777054: step: 1028/530, loss: 0.009371710941195488
2023-01-22 14:07:28.829155: step: 1032/530, loss: 0.007615245878696442
2023-01-22 14:07:29.870565: step: 1036/530, loss: 0.011166317388415337
2023-01-22 14:07:30.901437: step: 1040/530, loss: 0.006640819367021322
2023-01-22 14:07:31.947995: step: 1044/530, loss: 0.02560454048216343
2023-01-22 14:07:33.022293: step: 1048/530, loss: 0.010287744924426079
2023-01-22 14:07:34.051452: step: 1052/530, loss: 0.005687665194272995
2023-01-22 14:07:35.095737: step: 1056/530, loss: 0.013990354724228382
2023-01-22 14:07:36.142054: step: 1060/530, loss: 0.014633985236287117
2023-01-22 14:07:37.186879: step: 1064/530, loss: 0.013105589896440506
2023-01-22 14:07:38.242498: step: 1068/530, loss: 0.005768314935266972
2023-01-22 14:07:39.290200: step: 1072/530, loss: 0.00640522688627243
2023-01-22 14:07:40.336640: step: 1076/530, loss: 0.005625725723803043
2023-01-22 14:07:41.374278: step: 1080/530, loss: 0.018396489322185516
2023-01-22 14:07:42.419279: step: 1084/530, loss: 0.015970518812537193
2023-01-22 14:07:43.458231: step: 1088/530, loss: 0.011452708393335342
2023-01-22 14:07:44.486138: step: 1092/530, loss: 0.006960126105695963
2023-01-22 14:07:45.521408: step: 1096/530, loss: 0.012958606705069542
2023-01-22 14:07:46.577555: step: 1100/530, loss: 0.03585435077548027
2023-01-22 14:07:47.637751: step: 1104/530, loss: 0.006065783556550741
2023-01-22 14:07:48.669775: step: 1108/530, loss: 0.01325303129851818
2023-01-22 14:07:49.716508: step: 1112/530, loss: 0.014481334015727043
2023-01-22 14:07:50.750482: step: 1116/530, loss: 0.028966834768652916
2023-01-22 14:07:51.789815: step: 1120/530, loss: 0.015271610580384731
2023-01-22 14:07:52.832056: step: 1124/530, loss: 0.020904196426272392
2023-01-22 14:07:53.873821: step: 1128/530, loss: 0.01870165951550007
2023-01-22 14:07:54.911404: step: 1132/530, loss: 0.009080823510885239
2023-01-22 14:07:55.958680: step: 1136/530, loss: 0.009103497490286827
2023-01-22 14:07:56.994035: step: 1140/530, loss: 0.0073168398812413216
2023-01-22 14:07:58.034485: step: 1144/530, loss: 0.01086410041898489
2023-01-22 14:07:59.070469: step: 1148/530, loss: 0.014534154906868935
2023-01-22 14:08:00.109971: step: 1152/530, loss: 0.009434904903173447
2023-01-22 14:08:01.154177: step: 1156/530, loss: 0.039193108677864075
2023-01-22 14:08:02.190589: step: 1160/530, loss: 0.01121500600129366
2023-01-22 14:08:03.240980: step: 1164/530, loss: 0.03556763008236885
2023-01-22 14:08:04.307031: step: 1168/530, loss: 0.048144567757844925
2023-01-22 14:08:05.339715: step: 1172/530, loss: 0.009631075896322727
2023-01-22 14:08:06.368129: step: 1176/530, loss: 0.04500937834382057
2023-01-22 14:08:07.424445: step: 1180/530, loss: 0.008284853771328926
2023-01-22 14:08:08.464042: step: 1184/530, loss: 0.038502469658851624
2023-01-22 14:08:09.502004: step: 1188/530, loss: 0.035055097192525864
2023-01-22 14:08:10.531000: step: 1192/530, loss: 0.0
2023-01-22 14:08:11.569608: step: 1196/530, loss: 0.04667744040489197
2023-01-22 14:08:12.604418: step: 1200/530, loss: 0.02551337517797947
2023-01-22 14:08:13.653170: step: 1204/530, loss: 0.022924574092030525
2023-01-22 14:08:14.670370: step: 1208/530, loss: 0.011838776990771294
2023-01-22 14:08:15.706963: step: 1212/530, loss: 0.017896490171551704
2023-01-22 14:08:16.742327: step: 1216/530, loss: 0.012125873006880283
2023-01-22 14:08:17.784184: step: 1220/530, loss: 0.008926368318498135
2023-01-22 14:08:18.820218: step: 1224/530, loss: 0.006506599485874176
2023-01-22 14:08:19.857686: step: 1228/530, loss: 0.03445328772068024
2023-01-22 14:08:20.894590: step: 1232/530, loss: 0.025107944384217262
2023-01-22 14:08:21.935595: step: 1236/530, loss: 0.07491537928581238
2023-01-22 14:08:22.975104: step: 1240/530, loss: 0.05032229796051979
2023-01-22 14:08:24.028294: step: 1244/530, loss: 0.031171901151537895
2023-01-22 14:08:25.090398: step: 1248/530, loss: 0.008107133209705353
2023-01-22 14:08:26.118234: step: 1252/530, loss: 0.012835049070417881
2023-01-22 14:08:27.158411: step: 1256/530, loss: 0.0331944115459919
2023-01-22 14:08:28.235069: step: 1260/530, loss: 0.012265531346201897
2023-01-22 14:08:29.272321: step: 1264/530, loss: 0.03081982210278511
2023-01-22 14:08:30.299823: step: 1268/530, loss: 0.017442643642425537
2023-01-22 14:08:31.344428: step: 1272/530, loss: 0.008818896487355232
2023-01-22 14:08:32.388195: step: 1276/530, loss: 0.009429981000721455
2023-01-22 14:08:33.419967: step: 1280/530, loss: 0.0068158721551299095
2023-01-22 14:08:34.464568: step: 1284/530, loss: 0.06472896039485931
2023-01-22 14:08:35.511550: step: 1288/530, loss: 0.013817965984344482
2023-01-22 14:08:36.548827: step: 1292/530, loss: 0.04319170489907265
2023-01-22 14:08:37.587851: step: 1296/530, loss: 0.00434703566133976
2023-01-22 14:08:38.639399: step: 1300/530, loss: 0.014109157957136631
2023-01-22 14:08:39.677940: step: 1304/530, loss: 0.0176323764026165
2023-01-22 14:08:40.714748: step: 1308/530, loss: 0.0253970455378294
2023-01-22 14:08:41.755151: step: 1312/530, loss: 0.016420656815171242
2023-01-22 14:08:42.803272: step: 1316/530, loss: 0.016026459634304047
2023-01-22 14:08:43.848520: step: 1320/530, loss: 0.00875675119459629
2023-01-22 14:08:44.896593: step: 1324/530, loss: 0.019109154120087624
2023-01-22 14:08:45.934981: step: 1328/530, loss: 0.02545016258955002
2023-01-22 14:08:46.992434: step: 1332/530, loss: 0.015020868740975857
2023-01-22 14:08:48.030753: step: 1336/530, loss: 0.013192745856940746
2023-01-22 14:08:49.074305: step: 1340/530, loss: 0.008076358586549759
2023-01-22 14:08:50.121068: step: 1344/530, loss: 0.01662585884332657
2023-01-22 14:08:51.154122: step: 1348/530, loss: 0.014491165056824684
2023-01-22 14:08:52.181526: step: 1352/530, loss: 0.007139723282307386
2023-01-22 14:08:53.212594: step: 1356/530, loss: 0.013656837865710258
2023-01-22 14:08:54.251398: step: 1360/530, loss: 0.01911047101020813
2023-01-22 14:08:55.290973: step: 1364/530, loss: 0.0608656108379364
2023-01-22 14:08:56.329000: step: 1368/530, loss: 0.01656697690486908
2023-01-22 14:08:57.370732: step: 1372/530, loss: 0.01165794301778078
2023-01-22 14:08:58.438958: step: 1376/530, loss: 0.007821107283234596
2023-01-22 14:08:59.482806: step: 1380/530, loss: 0.008379621431231499
2023-01-22 14:09:00.549735: step: 1384/530, loss: 0.04263940826058388
2023-01-22 14:09:01.588199: step: 1388/530, loss: 0.03730163723230362
2023-01-22 14:09:02.632049: step: 1392/530, loss: 0.04185022413730621
2023-01-22 14:09:03.685175: step: 1396/530, loss: 0.013346433639526367
2023-01-22 14:09:04.738088: step: 1400/530, loss: 0.010640447027981281
2023-01-22 14:09:05.777824: step: 1404/530, loss: 0.026997994631528854
2023-01-22 14:09:06.845007: step: 1408/530, loss: 0.03975527361035347
2023-01-22 14:09:07.899427: step: 1412/530, loss: 0.007448334246873856
2023-01-22 14:09:08.945681: step: 1416/530, loss: 0.059563349932432175
2023-01-22 14:09:09.982587: step: 1420/530, loss: 0.04467020556330681
2023-01-22 14:09:11.040685: step: 1424/530, loss: 0.015791745856404305
2023-01-22 14:09:12.069935: step: 1428/530, loss: 0.007467383984476328
2023-01-22 14:09:13.118139: step: 1432/530, loss: 0.04677760228514671
2023-01-22 14:09:14.169666: step: 1436/530, loss: 0.014661049470305443
2023-01-22 14:09:15.197069: step: 1440/530, loss: 0.04245565086603165
2023-01-22 14:09:16.247207: step: 1444/530, loss: 0.016248386353254318
2023-01-22 14:09:17.299683: step: 1448/530, loss: 0.0616140142083168
2023-01-22 14:09:18.334768: step: 1452/530, loss: 0.01275690644979477
2023-01-22 14:09:19.377558: step: 1456/530, loss: 0.018116962164640427
2023-01-22 14:09:20.415995: step: 1460/530, loss: 0.03878491371870041
2023-01-22 14:09:21.445161: step: 1464/530, loss: 0.016520487144589424
2023-01-22 14:09:22.485116: step: 1468/530, loss: 0.024132516235113144
2023-01-22 14:09:23.532545: step: 1472/530, loss: 0.04045415297150612
2023-01-22 14:09:24.576045: step: 1476/530, loss: 0.02203725278377533
2023-01-22 14:09:25.623438: step: 1480/530, loss: 0.008971241302788258
2023-01-22 14:09:26.671302: step: 1484/530, loss: 0.03543095663189888
2023-01-22 14:09:27.710699: step: 1488/530, loss: 0.01844763569533825
2023-01-22 14:09:28.742359: step: 1492/530, loss: 0.008905330672860146
2023-01-22 14:09:29.792283: step: 1496/530, loss: 0.01676773652434349
2023-01-22 14:09:30.833630: step: 1500/530, loss: 0.01816197670996189
2023-01-22 14:09:31.873721: step: 1504/530, loss: 0.013253842480480671
2023-01-22 14:09:32.922791: step: 1508/530, loss: 0.01869339309632778
2023-01-22 14:09:33.970849: step: 1512/530, loss: 0.00848846510052681
2023-01-22 14:09:35.002675: step: 1516/530, loss: 0.0009101839968934655
2023-01-22 14:09:36.050217: step: 1520/530, loss: 0.006233740597963333
2023-01-22 14:09:37.100993: step: 1524/530, loss: 0.03229101374745369
2023-01-22 14:09:38.140126: step: 1528/530, loss: 0.013248422183096409
2023-01-22 14:09:39.187037: step: 1532/530, loss: 0.009252777323126793
2023-01-22 14:09:40.231436: step: 1536/530, loss: 0.0035703161265701056
2023-01-22 14:09:41.264172: step: 1540/530, loss: 0.009456614963710308
2023-01-22 14:09:42.304724: step: 1544/530, loss: 0.009363709017634392
2023-01-22 14:09:43.343192: step: 1548/530, loss: 0.0897272378206253
2023-01-22 14:09:44.373040: step: 1552/530, loss: 0.05218866840004921
2023-01-22 14:09:45.426817: step: 1556/530, loss: 0.010671944357454777
2023-01-22 14:09:46.457730: step: 1560/530, loss: 0.008355812169611454
2023-01-22 14:09:47.494054: step: 1564/530, loss: 0.004710738081485033
2023-01-22 14:09:48.543781: step: 1568/530, loss: 0.09251004457473755
2023-01-22 14:09:49.593680: step: 1572/530, loss: 0.007496704813092947
2023-01-22 14:09:50.638014: step: 1576/530, loss: 0.01327112689614296
2023-01-22 14:09:51.663693: step: 1580/530, loss: 0.009883316233754158
2023-01-22 14:09:52.734857: step: 1584/530, loss: 0.02566574700176716
2023-01-22 14:09:53.778606: step: 1588/530, loss: 0.0
2023-01-22 14:09:54.816961: step: 1592/530, loss: 0.006210661493241787
2023-01-22 14:09:55.869930: step: 1596/530, loss: 0.014399432577192783
2023-01-22 14:09:56.918872: step: 1600/530, loss: 0.012009043246507645
2023-01-22 14:09:57.973171: step: 1604/530, loss: 0.025204863399267197
2023-01-22 14:09:59.008700: step: 1608/530, loss: 0.010684474371373653
2023-01-22 14:10:00.071238: step: 1612/530, loss: 0.008406277745962143
2023-01-22 14:10:01.117652: step: 1616/530, loss: 0.00841812789440155
2023-01-22 14:10:02.160214: step: 1620/530, loss: 0.007304898463189602
2023-01-22 14:10:03.194273: step: 1624/530, loss: 0.004615768790245056
2023-01-22 14:10:04.230336: step: 1628/530, loss: 0.03297346085309982
2023-01-22 14:10:05.270317: step: 1632/530, loss: 0.013780905865132809
2023-01-22 14:10:06.326123: step: 1636/530, loss: 0.03210994601249695
2023-01-22 14:10:07.357854: step: 1640/530, loss: 0.007842929102480412
2023-01-22 14:10:08.423724: step: 1644/530, loss: 0.008495690301060677
2023-01-22 14:10:09.461170: step: 1648/530, loss: 0.010128493420779705
2023-01-22 14:10:10.505778: step: 1652/530, loss: 0.006616923026740551
2023-01-22 14:10:11.554019: step: 1656/530, loss: 0.010074500925838947
2023-01-22 14:10:12.599689: step: 1660/530, loss: 0.03827520087361336
2023-01-22 14:10:13.630531: step: 1664/530, loss: 0.014995967969298363
2023-01-22 14:10:14.668153: step: 1668/530, loss: 0.014161030761897564
2023-01-22 14:10:15.708956: step: 1672/530, loss: 0.0067509314976632595
2023-01-22 14:10:16.744673: step: 1676/530, loss: 0.02198561280965805
2023-01-22 14:10:17.787064: step: 1680/530, loss: 0.019412247464060783
2023-01-22 14:10:18.823413: step: 1684/530, loss: 0.013593340292572975
2023-01-22 14:10:19.875973: step: 1688/530, loss: 0.06433723866939545
2023-01-22 14:10:20.917445: step: 1692/530, loss: 0.02928980253636837
2023-01-22 14:10:21.950107: step: 1696/530, loss: 0.013907265849411488
2023-01-22 14:10:22.995803: step: 1700/530, loss: 0.06132680922746658
2023-01-22 14:10:24.041266: step: 1704/530, loss: 0.0038807429373264313
2023-01-22 14:10:25.082250: step: 1708/530, loss: 0.011430630460381508
2023-01-22 14:10:26.112523: step: 1712/530, loss: 0.027682211250066757
2023-01-22 14:10:27.150492: step: 1716/530, loss: 0.029594920575618744
2023-01-22 14:10:28.205250: step: 1720/530, loss: 0.01209992915391922
2023-01-22 14:10:29.247733: step: 1724/530, loss: 0.03204839676618576
2023-01-22 14:10:30.292385: step: 1728/530, loss: 0.009996633976697922
2023-01-22 14:10:31.318574: step: 1732/530, loss: 0.01476296130567789
2023-01-22 14:10:32.376549: step: 1736/530, loss: 0.0039046211168169975
2023-01-22 14:10:33.403685: step: 1740/530, loss: 0.004724082536995411
2023-01-22 14:10:34.444163: step: 1744/530, loss: 0.01035708375275135
2023-01-22 14:10:35.497617: step: 1748/530, loss: 0.01116228848695755
2023-01-22 14:10:36.539572: step: 1752/530, loss: 0.006762249395251274
2023-01-22 14:10:37.591250: step: 1756/530, loss: 0.01807950995862484
2023-01-22 14:10:38.627590: step: 1760/530, loss: 0.00912668276578188
2023-01-22 14:10:39.673116: step: 1764/530, loss: 0.005292718298733234
2023-01-22 14:10:40.710638: step: 1768/530, loss: 0.004882217850536108
2023-01-22 14:10:41.762500: step: 1772/530, loss: 0.007848333567380905
2023-01-22 14:10:42.786094: step: 1776/530, loss: 0.004974755458533764
2023-01-22 14:10:43.842255: step: 1780/530, loss: 0.00784052163362503
2023-01-22 14:10:44.878496: step: 1784/530, loss: 0.006111221853643656
2023-01-22 14:10:45.925309: step: 1788/530, loss: 0.008439870551228523
2023-01-22 14:10:46.969004: step: 1792/530, loss: 0.007257196586579084
2023-01-22 14:10:48.002668: step: 1796/530, loss: 0.03097677417099476
2023-01-22 14:10:49.047526: step: 1800/530, loss: 0.02392994426190853
2023-01-22 14:10:50.099769: step: 1804/530, loss: 0.01921793259680271
2023-01-22 14:10:51.141131: step: 1808/530, loss: 0.0157614853233099
2023-01-22 14:10:52.170587: step: 1812/530, loss: 0.013865902088582516
2023-01-22 14:10:53.218494: step: 1816/530, loss: 0.00809855293482542
2023-01-22 14:10:54.281265: step: 1820/530, loss: 0.009653554297983646
2023-01-22 14:10:55.319710: step: 1824/530, loss: 0.009131310507655144
2023-01-22 14:10:56.363681: step: 1828/530, loss: 0.03661736845970154
2023-01-22 14:10:57.421310: step: 1832/530, loss: 0.01243253331631422
2023-01-22 14:10:58.463728: step: 1836/530, loss: 0.004411943722516298
2023-01-22 14:10:59.509366: step: 1840/530, loss: 0.034142088145017624
2023-01-22 14:11:00.558854: step: 1844/530, loss: 0.0510825589299202
2023-01-22 14:11:01.602682: step: 1848/530, loss: 0.0037943634670227766
2023-01-22 14:11:02.639604: step: 1852/530, loss: 0.007966898381710052
2023-01-22 14:11:03.701514: step: 1856/530, loss: 0.006379609927535057
2023-01-22 14:11:04.749912: step: 1860/530, loss: 0.028586218133568764
2023-01-22 14:11:05.794747: step: 1864/530, loss: 0.024182695895433426
2023-01-22 14:11:06.826264: step: 1868/530, loss: 0.012714968994259834
2023-01-22 14:11:07.871801: step: 1872/530, loss: 0.007266114931553602
2023-01-22 14:11:08.903717: step: 1876/530, loss: 0.016135327517986298
2023-01-22 14:11:09.943271: step: 1880/530, loss: 0.01627356745302677
2023-01-22 14:11:10.970300: step: 1884/530, loss: 0.010763503611087799
2023-01-22 14:11:12.014935: step: 1888/530, loss: 0.044665493071079254
2023-01-22 14:11:13.057878: step: 1892/530, loss: 0.02698495425283909
2023-01-22 14:11:14.091042: step: 1896/530, loss: 0.01269553229212761
2023-01-22 14:11:15.123995: step: 1900/530, loss: 0.006397400051355362
2023-01-22 14:11:16.199189: step: 1904/530, loss: 0.00925454031676054
2023-01-22 14:11:17.239518: step: 1908/530, loss: 0.029682034626603127
2023-01-22 14:11:18.265348: step: 1912/530, loss: 0.017402449622750282
2023-01-22 14:11:19.300923: step: 1916/530, loss: 0.006162512116134167
2023-01-22 14:11:20.347448: step: 1920/530, loss: 0.0045259553007781506
2023-01-22 14:11:21.397098: step: 1924/530, loss: 0.00969818327575922
2023-01-22 14:11:22.444094: step: 1928/530, loss: 0.008025826886296272
2023-01-22 14:11:23.489118: step: 1932/530, loss: 0.01395223569124937
2023-01-22 14:11:24.540736: step: 1936/530, loss: 0.012100683525204659
2023-01-22 14:11:25.571959: step: 1940/530, loss: 0.02019091136753559
2023-01-22 14:11:26.618854: step: 1944/530, loss: 0.018800778314471245
2023-01-22 14:11:27.658075: step: 1948/530, loss: 0.021765897050499916
2023-01-22 14:11:28.697310: step: 1952/530, loss: 0.01721109077334404
2023-01-22 14:11:29.750185: step: 1956/530, loss: 0.03487658500671387
2023-01-22 14:11:30.792635: step: 1960/530, loss: 0.006069914437830448
2023-01-22 14:11:31.842638: step: 1964/530, loss: 0.06411559134721756
2023-01-22 14:11:32.873896: step: 1968/530, loss: 0.01284013967961073
2023-01-22 14:11:33.919659: step: 1972/530, loss: 0.008704513311386108
2023-01-22 14:11:34.954287: step: 1976/530, loss: 0.0011018546065315604
2023-01-22 14:11:35.993996: step: 1980/530, loss: 0.014638877473771572
2023-01-22 14:11:37.032571: step: 1984/530, loss: 0.010074022226035595
2023-01-22 14:11:38.079006: step: 1988/530, loss: 0.031635627150535583
2023-01-22 14:11:39.125915: step: 1992/530, loss: 0.03363392874598503
2023-01-22 14:11:40.175467: step: 1996/530, loss: 0.026511678472161293
2023-01-22 14:11:41.206121: step: 2000/530, loss: 0.02227601781487465
2023-01-22 14:11:42.253258: step: 2004/530, loss: 0.022974004969000816
2023-01-22 14:11:43.306237: step: 2008/530, loss: 0.012734156101942062
2023-01-22 14:11:44.348410: step: 2012/530, loss: 0.016996197402477264
2023-01-22 14:11:45.393919: step: 2016/530, loss: 0.0056351288221776485
2023-01-22 14:11:46.443864: step: 2020/530, loss: 0.008489016443490982
2023-01-22 14:11:47.481698: step: 2024/530, loss: 0.022434482350945473
2023-01-22 14:11:48.521860: step: 2028/530, loss: 0.017772993072867393
2023-01-22 14:11:49.552640: step: 2032/530, loss: 0.012262226082384586
2023-01-22 14:11:50.585015: step: 2036/530, loss: 0.007736681494861841
2023-01-22 14:11:51.625059: step: 2040/530, loss: 0.009416958317160606
2023-01-22 14:11:52.645310: step: 2044/530, loss: 0.006539102178066969
2023-01-22 14:11:53.695170: step: 2048/530, loss: 0.007677316665649414
2023-01-22 14:11:54.727333: step: 2052/530, loss: 0.013833217322826385
2023-01-22 14:11:55.777779: step: 2056/530, loss: 0.012024348601698875
2023-01-22 14:11:56.822927: step: 2060/530, loss: 0.029821518808603287
2023-01-22 14:11:57.884019: step: 2064/530, loss: 0.003974899183958769
2023-01-22 14:11:58.939944: step: 2068/530, loss: 0.023904291912913322
2023-01-22 14:11:59.988889: step: 2072/530, loss: 0.01618839055299759
2023-01-22 14:12:01.047609: step: 2076/530, loss: 0.017006777226924896
2023-01-22 14:12:02.107324: step: 2080/530, loss: 0.03427751362323761
2023-01-22 14:12:03.151894: step: 2084/530, loss: 0.01980504021048546
2023-01-22 14:12:04.181054: step: 2088/530, loss: 0.01490362174808979
2023-01-22 14:12:05.207865: step: 2092/530, loss: 0.01789029687643051
2023-01-22 14:12:06.255736: step: 2096/530, loss: 0.004750585649162531
2023-01-22 14:12:07.293703: step: 2100/530, loss: 0.014235352165997028
2023-01-22 14:12:08.340314: step: 2104/530, loss: 0.006032113451510668
2023-01-22 14:12:09.398711: step: 2108/530, loss: 0.005484898108989
2023-01-22 14:12:10.442650: step: 2112/530, loss: 0.009656216017901897
2023-01-22 14:12:11.492022: step: 2116/530, loss: 0.005013451911509037
2023-01-22 14:12:12.520169: step: 2120/530, loss: 0.007228979840874672
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34057439271255063, 'r': 0.3192481024667932, 'f1': 0.3295666013712047}, 'combined': 0.24283854837878238, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35079685942601757, 'r': 0.3935612795026998, 'f1': 0.3709506314794346}, 'combined': 0.287531111481667, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31253280858904237, 'r': 0.3178701810317395, 'f1': 0.31517890010108507}, 'combined': 0.23223708428501003, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35237998947542964, 'r': 0.3980468814938447, 'f1': 0.3738239163274088}, 'combined': 0.28975825093320684, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32466779659823713, 'r': 0.32898027207487407, 'f1': 0.3268098084513829}, 'combined': 0.24080722727996634, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3507187469215601, 'r': 0.37553983470920727, 'f1': 0.362705139958826}, 'combined': 0.28113986925038187, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3541666666666667, 'r': 0.3695652173913043, 'f1': 0.3617021276595745}, 'combined': 0.18085106382978725, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4861111111111111, 'r': 0.3017241379310345, 'f1': 0.3723404255319149}, 'combined': 0.2482269503546099, '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': 0.34057439271255063, 'r': 0.3192481024667932, 'f1': 0.3295666013712047}, 'combined': 0.24283854837878238, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35079685942601757, 'r': 0.3935612795026998, 'f1': 0.3709506314794346}, 'combined': 0.287531111481667, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31253280858904237, 'r': 0.3178701810317395, 'f1': 0.31517890010108507}, 'combined': 0.23223708428501003, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35237998947542964, 'r': 0.3980468814938447, 'f1': 0.3738239163274088}, 'combined': 0.28975825093320684, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3541666666666667, 'r': 0.3695652173913043, 'f1': 0.3617021276595745}, 'combined': 0.18085106382978725, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32466779659823713, 'r': 0.32898027207487407, 'f1': 0.3268098084513829}, 'combined': 0.24080722727996634, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3507187469215601, 'r': 0.37553983470920727, 'f1': 0.362705139958826}, 'combined': 0.28113986925038187, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4861111111111111, 'r': 0.3017241379310345, 'f1': 0.3723404255319149}, 'combined': 0.2482269503546099, '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
2023-01-22 14:14:59.522007: step: 4/530, loss: 0.0098522137850523
2023-01-22 14:15:00.564324: step: 8/530, loss: 0.005377455148845911
2023-01-22 14:15:01.594627: step: 12/530, loss: 0.006909853778779507
2023-01-22 14:15:02.616989: step: 16/530, loss: 0.006114135030657053
2023-01-22 14:15:03.645755: step: 20/530, loss: 0.012564241886138916
2023-01-22 14:15:04.707466: step: 24/530, loss: 0.0422721803188324
2023-01-22 14:15:05.738938: step: 28/530, loss: 0.020891595631837845
2023-01-22 14:15:06.768708: step: 32/530, loss: 0.0032217446714639664
2023-01-22 14:15:07.805712: step: 36/530, loss: 0.005921873264014721
2023-01-22 14:15:08.821582: step: 40/530, loss: 0.010434969328343868
2023-01-22 14:15:09.861858: step: 44/530, loss: 0.00887048989534378
2023-01-22 14:15:10.910294: step: 48/530, loss: 0.029717912897467613
2023-01-22 14:15:11.951313: step: 52/530, loss: 0.0068167694844305515
2023-01-22 14:15:12.982121: step: 56/530, loss: 0.009218721650540829
2023-01-22 14:15:14.004201: step: 60/530, loss: 0.007991575635969639
2023-01-22 14:15:15.054429: step: 64/530, loss: 0.01888984441757202
2023-01-22 14:15:16.099281: step: 68/530, loss: 0.017180604860186577
2023-01-22 14:15:17.131064: step: 72/530, loss: 0.055858999490737915
2023-01-22 14:15:18.184188: step: 76/530, loss: 0.010794703848659992
2023-01-22 14:15:19.227185: step: 80/530, loss: 0.017841270193457603
2023-01-22 14:15:20.265478: step: 84/530, loss: 0.009985985234379768
2023-01-22 14:15:21.305309: step: 88/530, loss: 0.03523147478699684
2023-01-22 14:15:22.368061: step: 92/530, loss: 0.010065844282507896
2023-01-22 14:15:23.420045: step: 96/530, loss: 0.008606970310211182
2023-01-22 14:15:24.449454: step: 100/530, loss: 0.011893689632415771
2023-01-22 14:15:25.491997: step: 104/530, loss: 0.008819621987640858
2023-01-22 14:15:26.524807: step: 108/530, loss: 0.014171184040606022
2023-01-22 14:15:27.554001: step: 112/530, loss: 0.014161612838506699
2023-01-22 14:15:28.609794: step: 116/530, loss: 0.01990302838385105
2023-01-22 14:15:29.649804: step: 120/530, loss: 0.011115428991615772
2023-01-22 14:15:30.667491: step: 124/530, loss: 0.0008971584029495716
2023-01-22 14:15:31.714232: step: 128/530, loss: 0.013212819583714008
2023-01-22 14:15:32.752810: step: 132/530, loss: 0.013090829364955425
2023-01-22 14:15:33.803154: step: 136/530, loss: 0.00854986160993576
2023-01-22 14:15:34.845903: step: 140/530, loss: 0.00937812589108944
2023-01-22 14:15:35.895062: step: 144/530, loss: 0.005623607896268368
2023-01-22 14:15:36.928627: step: 148/530, loss: 0.03182008117437363
2023-01-22 14:15:37.982200: step: 152/530, loss: 0.011129575781524181
2023-01-22 14:15:39.014689: step: 156/530, loss: 0.006379378028213978
2023-01-22 14:15:40.059885: step: 160/530, loss: 0.009916199371218681
2023-01-22 14:15:41.123732: step: 164/530, loss: 0.011921132914721966
2023-01-22 14:15:42.175710: step: 168/530, loss: 0.019632887095212936
2023-01-22 14:15:43.205912: step: 172/530, loss: 0.00840664654970169
2023-01-22 14:15:44.261618: step: 176/530, loss: 0.010645314119756222
2023-01-22 14:15:45.288142: step: 180/530, loss: 0.01473387610167265
2023-01-22 14:15:46.323682: step: 184/530, loss: 0.001186772482469678
2023-01-22 14:15:47.369454: step: 188/530, loss: 0.011140630580484867
2023-01-22 14:15:48.419290: step: 192/530, loss: 0.049186792224645615
2023-01-22 14:15:49.473430: step: 196/530, loss: 0.008088590577244759
2023-01-22 14:15:50.503018: step: 200/530, loss: 0.0036882306449115276
2023-01-22 14:15:51.548191: step: 204/530, loss: 0.012489606626331806
2023-01-22 14:15:52.590830: step: 208/530, loss: 0.005425607319921255
2023-01-22 14:15:53.630596: step: 212/530, loss: 0.01253504678606987
2023-01-22 14:15:54.687910: step: 216/530, loss: 0.02669784426689148
2023-01-22 14:15:55.736433: step: 220/530, loss: 0.004981519188731909
2023-01-22 14:15:56.780171: step: 224/530, loss: 0.009377394802868366
2023-01-22 14:15:57.842539: step: 228/530, loss: 0.0056566959246993065
2023-01-22 14:15:58.875377: step: 232/530, loss: 0.009297311305999756
2023-01-22 14:15:59.916695: step: 236/530, loss: 0.01048303209245205
2023-01-22 14:16:00.954329: step: 240/530, loss: 0.011084770783782005
2023-01-22 14:16:01.993337: step: 244/530, loss: 0.006352561060339212
2023-01-22 14:16:03.034648: step: 248/530, loss: 0.004507776349782944
2023-01-22 14:16:04.091482: step: 252/530, loss: 0.016194891184568405
2023-01-22 14:16:05.122171: step: 256/530, loss: 0.01039045862853527
2023-01-22 14:16:06.171558: step: 260/530, loss: 0.02721661515533924
2023-01-22 14:16:07.193279: step: 264/530, loss: 0.024171089753508568
2023-01-22 14:16:08.245834: step: 268/530, loss: 0.005026126746088266
2023-01-22 14:16:09.293251: step: 272/530, loss: 0.0088877622038126
2023-01-22 14:16:10.351314: step: 276/530, loss: 0.003714266698807478
2023-01-22 14:16:11.384003: step: 280/530, loss: 0.009569758549332619
2023-01-22 14:16:12.423731: step: 284/530, loss: 0.0025022635236382484
2023-01-22 14:16:13.460954: step: 288/530, loss: 0.012150965631008148
2023-01-22 14:16:14.506314: step: 292/530, loss: 0.07076514512300491
2023-01-22 14:16:15.554833: step: 296/530, loss: 0.011095026507973671
2023-01-22 14:16:16.599025: step: 300/530, loss: 0.024889731779694557
2023-01-22 14:16:17.633018: step: 304/530, loss: 0.03508802503347397
2023-01-22 14:16:18.701809: step: 308/530, loss: 0.009202630259096622
2023-01-22 14:16:19.750449: step: 312/530, loss: 0.024294743314385414
2023-01-22 14:16:20.797608: step: 316/530, loss: 0.007532244548201561
2023-01-22 14:16:21.838441: step: 320/530, loss: 0.007840575650334358
2023-01-22 14:16:22.901808: step: 324/530, loss: 0.011313081718981266
2023-01-22 14:16:23.949001: step: 328/530, loss: 0.017736399546265602
2023-01-22 14:16:24.988948: step: 332/530, loss: 0.013835232704877853
2023-01-22 14:16:26.019909: step: 336/530, loss: 0.007591048255562782
2023-01-22 14:16:27.059650: step: 340/530, loss: 0.012173166498541832
2023-01-22 14:16:28.119574: step: 344/530, loss: 0.008337490260601044
2023-01-22 14:16:29.179728: step: 348/530, loss: 0.018094103783369064
2023-01-22 14:16:30.223643: step: 352/530, loss: 0.011654539033770561
2023-01-22 14:16:31.264751: step: 356/530, loss: 0.0037538036704063416
2023-01-22 14:16:32.310196: step: 360/530, loss: 0.011034824885427952
2023-01-22 14:16:33.345252: step: 364/530, loss: 0.008073040284216404
2023-01-22 14:16:34.388281: step: 368/530, loss: 0.008059673942625523
2023-01-22 14:16:35.450708: step: 372/530, loss: 0.007434504572302103
2023-01-22 14:16:36.496432: step: 376/530, loss: 0.021508976817131042
2023-01-22 14:16:37.537086: step: 380/530, loss: 0.00594729371368885
2023-01-22 14:16:38.575177: step: 384/530, loss: 0.004328927490860224
2023-01-22 14:16:39.611428: step: 388/530, loss: 0.019735587760806084
2023-01-22 14:16:40.656236: step: 392/530, loss: 0.03632958233356476
2023-01-22 14:16:41.710756: step: 396/530, loss: 0.009657775983214378
2023-01-22 14:16:42.758558: step: 400/530, loss: 0.02911049872636795
2023-01-22 14:16:43.800291: step: 404/530, loss: 0.04207779839634895
2023-01-22 14:16:44.822751: step: 408/530, loss: 0.018335117027163506
2023-01-22 14:16:45.869741: step: 412/530, loss: 0.01259111613035202
2023-01-22 14:16:46.937473: step: 416/530, loss: 0.04776895046234131
2023-01-22 14:16:47.989472: step: 420/530, loss: 0.008508259430527687
2023-01-22 14:16:49.039322: step: 424/530, loss: 0.005509136710315943
2023-01-22 14:16:50.079564: step: 428/530, loss: 0.022022981196641922
2023-01-22 14:16:51.121633: step: 432/530, loss: 0.005825175903737545
2023-01-22 14:16:52.177405: step: 436/530, loss: 0.006391631439328194
2023-01-22 14:16:53.220925: step: 440/530, loss: 0.029798265546560287
2023-01-22 14:16:54.261733: step: 444/530, loss: 0.01169007271528244
2023-01-22 14:16:55.298181: step: 448/530, loss: 0.00993143580853939
2023-01-22 14:16:56.345604: step: 452/530, loss: 0.023017197847366333
2023-01-22 14:16:57.399522: step: 456/530, loss: 0.045980166643857956
2023-01-22 14:16:58.469085: step: 460/530, loss: 0.0062423935160040855
2023-01-22 14:16:59.508776: step: 464/530, loss: 0.02088567614555359
2023-01-22 14:17:00.567433: step: 468/530, loss: 0.0356353335082531
2023-01-22 14:17:01.616171: step: 472/530, loss: 0.006775871384888887
2023-01-22 14:17:02.662782: step: 476/530, loss: 0.02590928040444851
2023-01-22 14:17:03.715727: step: 480/530, loss: 0.02843741700053215
2023-01-22 14:17:04.756310: step: 484/530, loss: 0.011266574263572693
2023-01-22 14:17:05.808937: step: 488/530, loss: 0.01505152229219675
2023-01-22 14:17:06.856650: step: 492/530, loss: 0.018635883927345276
2023-01-22 14:17:07.897208: step: 496/530, loss: 0.024898337200284004
2023-01-22 14:17:08.941729: step: 500/530, loss: 0.0
2023-01-22 14:17:09.976192: step: 504/530, loss: 0.0073678456246852875
2023-01-22 14:17:11.026003: step: 508/530, loss: 0.00479509960860014
2023-01-22 14:17:12.056590: step: 512/530, loss: 0.022892314940690994
2023-01-22 14:17:13.106325: step: 516/530, loss: 0.018966952338814735
2023-01-22 14:17:14.149137: step: 520/530, loss: 0.00934302806854248
2023-01-22 14:17:15.210693: step: 524/530, loss: 0.006274034269154072
2023-01-22 14:17:16.250826: step: 528/530, loss: 0.010546999052166939
2023-01-22 14:17:17.295680: step: 532/530, loss: 0.052468761801719666
2023-01-22 14:17:18.331882: step: 536/530, loss: 0.06969141960144043
2023-01-22 14:17:19.377040: step: 540/530, loss: 0.010747411288321018
2023-01-22 14:17:20.440783: step: 544/530, loss: 0.009659159928560257
2023-01-22 14:17:21.492092: step: 548/530, loss: 0.016071975231170654
2023-01-22 14:17:22.528089: step: 552/530, loss: 0.007158543914556503
2023-01-22 14:17:23.579286: step: 556/530, loss: 0.009879428893327713
2023-01-22 14:17:24.637898: step: 560/530, loss: 0.0037339518312364817
2023-01-22 14:17:25.690153: step: 564/530, loss: 0.007042306941002607
2023-01-22 14:17:26.738024: step: 568/530, loss: 0.05043751746416092
2023-01-22 14:17:27.790809: step: 572/530, loss: 0.004624256398528814
2023-01-22 14:17:28.821996: step: 576/530, loss: 0.0010471967980265617
2023-01-22 14:17:29.850430: step: 580/530, loss: 0.00454417709261179
2023-01-22 14:17:30.893376: step: 584/530, loss: 0.014900184236466885
2023-01-22 14:17:31.915224: step: 588/530, loss: 0.005375597160309553
2023-01-22 14:17:32.950840: step: 592/530, loss: 0.005241508595645428
2023-01-22 14:17:34.000431: step: 596/530, loss: 0.060182321816682816
2023-01-22 14:17:35.046475: step: 600/530, loss: 0.03885366767644882
2023-01-22 14:17:36.091127: step: 604/530, loss: 0.0677824541926384
2023-01-22 14:17:37.139283: step: 608/530, loss: 0.009053359739482403
2023-01-22 14:17:38.187837: step: 612/530, loss: 0.019364645704627037
2023-01-22 14:17:39.236747: step: 616/530, loss: 0.04223789647221565
2023-01-22 14:17:40.293927: step: 620/530, loss: 0.010694325901567936
2023-01-22 14:17:41.342037: step: 624/530, loss: 0.0040028151124715805
2023-01-22 14:17:42.393085: step: 628/530, loss: 0.023425258696079254
2023-01-22 14:17:43.428778: step: 632/530, loss: 0.0030718552879989147
2023-01-22 14:17:44.472905: step: 636/530, loss: 0.0242239348590374
2023-01-22 14:17:45.508990: step: 640/530, loss: 0.006455741822719574
2023-01-22 14:17:46.545444: step: 644/530, loss: 0.0049271429888904095
2023-01-22 14:17:47.569341: step: 648/530, loss: 0.007410630118101835
2023-01-22 14:17:48.621139: step: 652/530, loss: 0.020723998546600342
2023-01-22 14:17:49.662462: step: 656/530, loss: 0.0067084855400025845
2023-01-22 14:17:50.709599: step: 660/530, loss: 0.005124341230839491
2023-01-22 14:17:51.763916: step: 664/530, loss: 0.02306445688009262
2023-01-22 14:17:52.807649: step: 668/530, loss: 0.018467148765921593
2023-01-22 14:17:53.887805: step: 672/530, loss: 0.008959340862929821
2023-01-22 14:17:54.928942: step: 676/530, loss: 0.0060637579299509525
2023-01-22 14:17:55.964873: step: 680/530, loss: 0.004548309836536646
2023-01-22 14:17:57.028127: step: 684/530, loss: 0.004471042193472385
2023-01-22 14:17:58.082732: step: 688/530, loss: 0.006043381057679653
2023-01-22 14:17:59.118128: step: 692/530, loss: 0.008091883733868599
2023-01-22 14:18:00.159514: step: 696/530, loss: 0.008449411951005459
2023-01-22 14:18:01.205143: step: 700/530, loss: 0.014556603506207466
2023-01-22 14:18:02.234153: step: 704/530, loss: 0.005651827435940504
2023-01-22 14:18:03.310238: step: 708/530, loss: 0.03851265832781792
2023-01-22 14:18:04.351038: step: 712/530, loss: 0.007113317959010601
2023-01-22 14:18:05.404955: step: 716/530, loss: 0.0061908201314508915
2023-01-22 14:18:06.436557: step: 720/530, loss: 0.003702000714838505
2023-01-22 14:18:07.484431: step: 724/530, loss: 0.007190654054284096
2023-01-22 14:18:08.528003: step: 728/530, loss: 0.009460589848458767
2023-01-22 14:18:09.573164: step: 732/530, loss: 0.009790292009711266
2023-01-22 14:18:10.630507: step: 736/530, loss: 0.05745977908372879
2023-01-22 14:18:11.692519: step: 740/530, loss: 0.025261517614126205
2023-01-22 14:18:12.736689: step: 744/530, loss: 0.03459774702787399
2023-01-22 14:18:13.778456: step: 748/530, loss: 0.005876890383660793
2023-01-22 14:18:14.837036: step: 752/530, loss: 0.016318483278155327
2023-01-22 14:18:15.897594: step: 756/530, loss: 0.0425649918615818
2023-01-22 14:18:16.937462: step: 760/530, loss: 0.01010993029922247
2023-01-22 14:18:17.988403: step: 764/530, loss: 0.011428799480199814
2023-01-22 14:18:19.036472: step: 768/530, loss: 0.01426747441291809
2023-01-22 14:18:20.070456: step: 772/530, loss: 0.009529833681881428
2023-01-22 14:18:21.110508: step: 776/530, loss: 0.047059934586286545
2023-01-22 14:18:22.169609: step: 780/530, loss: 0.02529189921915531
2023-01-22 14:18:23.213550: step: 784/530, loss: 0.007859750650823116
2023-01-22 14:18:24.257805: step: 788/530, loss: 0.01606394723057747
2023-01-22 14:18:25.294450: step: 792/530, loss: 0.009316043928265572
2023-01-22 14:18:26.358674: step: 796/530, loss: 0.005559139885008335
2023-01-22 14:18:27.405931: step: 800/530, loss: 0.03796050325036049
2023-01-22 14:18:28.440241: step: 804/530, loss: 0.031788360327482224
2023-01-22 14:18:29.476183: step: 808/530, loss: 0.008990352973341942
2023-01-22 14:18:30.522816: step: 812/530, loss: 0.00991953257471323
2023-01-22 14:18:31.566662: step: 816/530, loss: 0.0075381132774055
2023-01-22 14:18:32.604032: step: 820/530, loss: 0.0027112795505672693
2023-01-22 14:18:33.650770: step: 824/530, loss: 0.009086180478334427
2023-01-22 14:18:34.708805: step: 828/530, loss: 0.005719413049519062
2023-01-22 14:18:35.757702: step: 832/530, loss: 0.006139660254120827
2023-01-22 14:18:36.805629: step: 836/530, loss: 0.01109407190233469
2023-01-22 14:18:37.841216: step: 840/530, loss: 0.015826737508177757
2023-01-22 14:18:38.899808: step: 844/530, loss: 0.010260578244924545
2023-01-22 14:18:39.941304: step: 848/530, loss: 0.07133742421865463
2023-01-22 14:18:40.997279: step: 852/530, loss: 0.005036797374486923
2023-01-22 14:18:42.034460: step: 856/530, loss: 0.0015289344592019916
2023-01-22 14:18:43.062455: step: 860/530, loss: 0.004141239915043116
2023-01-22 14:18:44.106908: step: 864/530, loss: 0.0076431892812252045
2023-01-22 14:18:45.140076: step: 868/530, loss: 0.039615388959646225
2023-01-22 14:18:46.183309: step: 872/530, loss: 0.00718665961176157
2023-01-22 14:18:47.231573: step: 876/530, loss: 0.012222104705870152
2023-01-22 14:18:48.282585: step: 880/530, loss: 0.004468315746635199
2023-01-22 14:18:49.332179: step: 884/530, loss: 0.012883608229458332
2023-01-22 14:18:50.388920: step: 888/530, loss: 0.0043690563179552555
2023-01-22 14:18:51.428658: step: 892/530, loss: 0.004753664135932922
2023-01-22 14:18:52.469516: step: 896/530, loss: 0.011920920573174953
2023-01-22 14:18:53.509072: step: 900/530, loss: 0.02754632756114006
2023-01-22 14:18:54.546134: step: 904/530, loss: 0.0001700153516139835
2023-01-22 14:18:55.582284: step: 908/530, loss: 0.020358387380838394
2023-01-22 14:18:56.627101: step: 912/530, loss: 0.007957402616739273
2023-01-22 14:18:57.669819: step: 916/530, loss: 0.012252870947122574
2023-01-22 14:18:58.718741: step: 920/530, loss: 0.0145163768902421
2023-01-22 14:18:59.786031: step: 924/530, loss: 0.02983572706580162
2023-01-22 14:19:00.833138: step: 928/530, loss: 0.0035612699575722218
2023-01-22 14:19:01.880949: step: 932/530, loss: 0.0055160121992230415
2023-01-22 14:19:02.946363: step: 936/530, loss: 0.055421456694602966
2023-01-22 14:19:03.989767: step: 940/530, loss: 0.007808417547494173
2023-01-22 14:19:05.022031: step: 944/530, loss: 0.012586615048348904
2023-01-22 14:19:06.059106: step: 948/530, loss: 0.004396616481244564
2023-01-22 14:19:07.108741: step: 952/530, loss: 0.00525481766089797
2023-01-22 14:19:08.146883: step: 956/530, loss: 0.02059188112616539
2023-01-22 14:19:09.182086: step: 960/530, loss: 0.003952351398766041
2023-01-22 14:19:10.243076: step: 964/530, loss: 0.01580275222659111
2023-01-22 14:19:11.296945: step: 968/530, loss: 0.007135107647627592
2023-01-22 14:19:12.332031: step: 972/530, loss: 0.006866042967885733
2023-01-22 14:19:13.367967: step: 976/530, loss: 0.005642477422952652
2023-01-22 14:19:14.415613: step: 980/530, loss: 0.0032362625934183598
2023-01-22 14:19:15.449411: step: 984/530, loss: 0.01378723606467247
2023-01-22 14:19:16.480170: step: 988/530, loss: 0.047178059816360474
2023-01-22 14:19:17.523214: step: 992/530, loss: 0.004135483410209417
2023-01-22 14:19:18.571853: step: 996/530, loss: 0.05625234916806221
2023-01-22 14:19:19.631334: step: 1000/530, loss: 0.008552772924304008
2023-01-22 14:19:20.685303: step: 1004/530, loss: 0.005845270119607449
2023-01-22 14:19:21.725453: step: 1008/530, loss: 0.0006229244754649699
2023-01-22 14:19:22.755262: step: 1012/530, loss: 0.052640024572610855
2023-01-22 14:19:23.795321: step: 1016/530, loss: 0.003908698447048664
2023-01-22 14:19:24.823960: step: 1020/530, loss: 0.006324539426714182
2023-01-22 14:19:25.879029: step: 1024/530, loss: 0.027349544689059258
2023-01-22 14:19:26.947555: step: 1028/530, loss: 0.008202177472412586
2023-01-22 14:19:27.991659: step: 1032/530, loss: 0.0035938865039497614
2023-01-22 14:19:29.051741: step: 1036/530, loss: 0.040193237364292145
2023-01-22 14:19:30.097189: step: 1040/530, loss: 0.011916923336684704
2023-01-22 14:19:31.137387: step: 1044/530, loss: 0.03896845132112503
2023-01-22 14:19:32.167173: step: 1048/530, loss: 0.002595658414065838
2023-01-22 14:19:33.230831: step: 1052/530, loss: 0.012275359593331814
2023-01-22 14:19:34.273385: step: 1056/530, loss: 0.007934757508337498
2023-01-22 14:19:35.306171: step: 1060/530, loss: 0.03688136115670204
2023-01-22 14:19:36.349468: step: 1064/530, loss: 0.04775184020400047
2023-01-22 14:19:37.396629: step: 1068/530, loss: 0.007793552242219448
2023-01-22 14:19:38.434281: step: 1072/530, loss: 0.020563939586281776
2023-01-22 14:19:39.473669: step: 1076/530, loss: 0.0057910131290555
2023-01-22 14:19:40.526702: step: 1080/530, loss: 0.007447263225913048
2023-01-22 14:19:41.543442: step: 1084/530, loss: 0.008960508741438389
2023-01-22 14:19:42.583001: step: 1088/530, loss: 0.0017355165909975767
2023-01-22 14:19:43.614078: step: 1092/530, loss: 0.009154271334409714
2023-01-22 14:19:44.658000: step: 1096/530, loss: 0.003979458473622799
2023-01-22 14:19:45.707435: step: 1100/530, loss: 0.0004259079578332603
2023-01-22 14:19:46.755226: step: 1104/530, loss: 0.06848970055580139
2023-01-22 14:19:47.796693: step: 1108/530, loss: 0.008959291502833366
2023-01-22 14:19:48.870577: step: 1112/530, loss: 0.055906157940626144
2023-01-22 14:19:49.919107: step: 1116/530, loss: 0.005702725611627102
2023-01-22 14:19:50.963986: step: 1120/530, loss: 0.008533775806427002
2023-01-22 14:19:51.991254: step: 1124/530, loss: 0.008413284085690975
2023-01-22 14:19:53.030912: step: 1128/530, loss: 0.0384943000972271
2023-01-22 14:19:54.092887: step: 1132/530, loss: 0.01024586521089077
2023-01-22 14:19:55.149550: step: 1136/530, loss: 0.04789073020219803
2023-01-22 14:19:56.210593: step: 1140/530, loss: 0.03734603896737099
2023-01-22 14:19:57.257317: step: 1144/530, loss: 0.0354679711163044
2023-01-22 14:19:58.299959: step: 1148/530, loss: 0.0037439875304698944
2023-01-22 14:19:59.339219: step: 1152/530, loss: 0.012498389929533005
2023-01-22 14:20:00.378164: step: 1156/530, loss: 0.0037895317655056715
2023-01-22 14:20:01.413773: step: 1160/530, loss: 0.039169687777757645
2023-01-22 14:20:02.456607: step: 1164/530, loss: 0.004299154505133629
2023-01-22 14:20:03.511526: step: 1168/530, loss: 0.009770425036549568
2023-01-22 14:20:04.550256: step: 1172/530, loss: 0.03396693617105484
2023-01-22 14:20:05.591299: step: 1176/530, loss: 0.0054685091599822044
2023-01-22 14:20:06.639839: step: 1180/530, loss: 0.008923575282096863
2023-01-22 14:20:07.666078: step: 1184/530, loss: 0.01791532151401043
2023-01-22 14:20:08.727389: step: 1188/530, loss: 0.024384457617998123
2023-01-22 14:20:09.770391: step: 1192/530, loss: 0.01159385871142149
2023-01-22 14:20:10.800214: step: 1196/530, loss: 0.009178542532026768
2023-01-22 14:20:11.842207: step: 1200/530, loss: 0.024461396038532257
2023-01-22 14:20:12.887296: step: 1204/530, loss: 0.009322012774646282
2023-01-22 14:20:13.937289: step: 1208/530, loss: 0.03786756470799446
2023-01-22 14:20:15.003447: step: 1212/530, loss: 0.030062632635235786
2023-01-22 14:20:16.050111: step: 1216/530, loss: 0.007791387382894754
2023-01-22 14:20:17.097607: step: 1220/530, loss: 0.033344484865665436
2023-01-22 14:20:18.149530: step: 1224/530, loss: 0.004832225851714611
2023-01-22 14:20:19.194335: step: 1228/530, loss: 0.009263737127184868
2023-01-22 14:20:20.244459: step: 1232/530, loss: 0.007348473183810711
2023-01-22 14:20:21.289944: step: 1236/530, loss: 0.0008141044527292252
2023-01-22 14:20:22.331116: step: 1240/530, loss: 0.002374466508626938
2023-01-22 14:20:23.369486: step: 1244/530, loss: 0.016089728102087975
2023-01-22 14:20:24.400905: step: 1248/530, loss: 0.019337480887770653
2023-01-22 14:20:25.449720: step: 1252/530, loss: 0.021364131942391396
2023-01-22 14:20:26.491535: step: 1256/530, loss: 0.006602568086236715
2023-01-22 14:20:27.554049: step: 1260/530, loss: 0.0068792556412518024
2023-01-22 14:20:28.605783: step: 1264/530, loss: 0.004075265489518642
2023-01-22 14:20:29.649367: step: 1268/530, loss: 0.041897740215063095
2023-01-22 14:20:30.688317: step: 1272/530, loss: 0.0036564639303833246
2023-01-22 14:20:31.738436: step: 1276/530, loss: 0.0477060005068779
2023-01-22 14:20:32.798926: step: 1280/530, loss: 0.011061074212193489
2023-01-22 14:20:33.850832: step: 1284/530, loss: 0.0031509497202932835
2023-01-22 14:20:34.907766: step: 1288/530, loss: 0.024852100759744644
2023-01-22 14:20:35.952138: step: 1292/530, loss: 0.005682656541466713
2023-01-22 14:20:36.993264: step: 1296/530, loss: 0.0020805818494409323
2023-01-22 14:20:38.035502: step: 1300/530, loss: 0.005957027431577444
2023-01-22 14:20:39.069650: step: 1304/530, loss: 0.003713820595294237
2023-01-22 14:20:40.115632: step: 1308/530, loss: 0.0174169410020113
2023-01-22 14:20:41.156258: step: 1312/530, loss: 0.005139423068612814
2023-01-22 14:20:42.217239: step: 1316/530, loss: 0.008227752521634102
2023-01-22 14:20:43.255485: step: 1320/530, loss: 0.05675537511706352
2023-01-22 14:20:44.294862: step: 1324/530, loss: 0.006580718792974949
2023-01-22 14:20:45.335602: step: 1328/530, loss: 0.0034125992096960545
2023-01-22 14:20:46.408460: step: 1332/530, loss: 0.003971177618950605
2023-01-22 14:20:47.454434: step: 1336/530, loss: 0.006256772205233574
2023-01-22 14:20:48.486873: step: 1340/530, loss: 0.01535890344530344
2023-01-22 14:20:49.535966: step: 1344/530, loss: 0.009639522060751915
2023-01-22 14:20:50.590517: step: 1348/530, loss: 0.005839204881340265
2023-01-22 14:20:51.611036: step: 1352/530, loss: 0.0015847495524212718
2023-01-22 14:20:52.642096: step: 1356/530, loss: 0.004766490776091814
2023-01-22 14:20:53.682887: step: 1360/530, loss: 0.005338684655725956
2023-01-22 14:20:54.726949: step: 1364/530, loss: 0.009421211667358875
2023-01-22 14:20:55.777358: step: 1368/530, loss: 0.03505420684814453
2023-01-22 14:20:56.814725: step: 1372/530, loss: 0.02362665720283985
2023-01-22 14:20:57.859606: step: 1376/530, loss: 0.007698682602494955
2023-01-22 14:20:58.912279: step: 1380/530, loss: 0.03625423461198807
2023-01-22 14:20:59.946129: step: 1384/530, loss: 0.014150853268802166
2023-01-22 14:21:00.985664: step: 1388/530, loss: 0.05872374773025513
2023-01-22 14:21:02.034415: step: 1392/530, loss: 0.01388158556073904
2023-01-22 14:21:03.075667: step: 1396/530, loss: 0.01011976320296526
2023-01-22 14:21:04.119600: step: 1400/530, loss: 0.007690747268497944
2023-01-22 14:21:05.159702: step: 1404/530, loss: 0.014599599875509739
2023-01-22 14:21:06.216934: step: 1408/530, loss: 0.0070943161845207214
2023-01-22 14:21:07.250108: step: 1412/530, loss: 0.027554038912057877
2023-01-22 14:21:08.288761: step: 1416/530, loss: 0.009707432240247726
2023-01-22 14:21:09.343994: step: 1420/530, loss: 0.010745974257588387
2023-01-22 14:21:10.388703: step: 1424/530, loss: 0.010067526251077652
2023-01-22 14:21:11.428949: step: 1428/530, loss: 0.015290834940969944
2023-01-22 14:21:12.468417: step: 1432/530, loss: 0.02790786139667034
2023-01-22 14:21:13.512829: step: 1436/530, loss: 0.008694365620613098
2023-01-22 14:21:14.550908: step: 1440/530, loss: 0.005010063759982586
2023-01-22 14:21:15.613593: step: 1444/530, loss: 0.017848588526248932
2023-01-22 14:21:16.657339: step: 1448/530, loss: 0.008178862743079662
2023-01-22 14:21:17.705741: step: 1452/530, loss: 0.006831485778093338
2023-01-22 14:21:18.739931: step: 1456/530, loss: 0.008371623232960701
2023-01-22 14:21:19.786379: step: 1460/530, loss: 0.004503347910940647
2023-01-22 14:21:20.810484: step: 1464/530, loss: 0.005053850822150707
2023-01-22 14:21:21.855107: step: 1468/530, loss: 0.01969132013618946
2023-01-22 14:21:22.902905: step: 1472/530, loss: 0.005457093007862568
2023-01-22 14:21:23.945010: step: 1476/530, loss: 0.0063288272358477116
2023-01-22 14:21:24.981588: step: 1480/530, loss: 0.029903246089816093
2023-01-22 14:21:26.004856: step: 1484/530, loss: 0.004398359451442957
2023-01-22 14:21:27.051276: step: 1488/530, loss: 0.0025383245665580034
2023-01-22 14:21:28.102426: step: 1492/530, loss: 0.012691888958215714
2023-01-22 14:21:29.140684: step: 1496/530, loss: 0.008883957751095295
2023-01-22 14:21:30.213548: step: 1500/530, loss: 0.006874787621200085
2023-01-22 14:21:31.223632: step: 1504/530, loss: 0.007974770851433277
2023-01-22 14:21:32.268711: step: 1508/530, loss: 0.03388189896941185
2023-01-22 14:21:33.311682: step: 1512/530, loss: 0.011024592444300652
2023-01-22 14:21:34.337803: step: 1516/530, loss: 0.006327065173536539
2023-01-22 14:21:35.364071: step: 1520/530, loss: 0.009689447470009327
2023-01-22 14:21:36.403901: step: 1524/530, loss: 0.026437874883413315
2023-01-22 14:21:37.451545: step: 1528/530, loss: 0.02019422873854637
2023-01-22 14:21:38.488820: step: 1532/530, loss: 0.007898754440248013
2023-01-22 14:21:39.539608: step: 1536/530, loss: 0.004939930513501167
2023-01-22 14:21:40.564212: step: 1540/530, loss: 0.0023355563171207905
2023-01-22 14:21:41.614623: step: 1544/530, loss: 0.054159652441740036
2023-01-22 14:21:42.695918: step: 1548/530, loss: 0.006251053884625435
2023-01-22 14:21:43.741872: step: 1552/530, loss: 0.0070323399268090725
2023-01-22 14:21:44.780987: step: 1556/530, loss: 0.010830866172909737
2023-01-22 14:21:45.823989: step: 1560/530, loss: 0.006331013515591621
2023-01-22 14:21:46.855582: step: 1564/530, loss: 0.0013545668916776776
2023-01-22 14:21:47.898202: step: 1568/530, loss: 0.006860048044472933
2023-01-22 14:21:48.938684: step: 1572/530, loss: 0.0074236588552594185
2023-01-22 14:21:49.970954: step: 1576/530, loss: 0.010446438565850258
2023-01-22 14:21:51.010988: step: 1580/530, loss: 0.055162906646728516
2023-01-22 14:21:52.053956: step: 1584/530, loss: 0.009249155409634113
2023-01-22 14:21:53.075566: step: 1588/530, loss: 0.006983056664466858
2023-01-22 14:21:54.104663: step: 1592/530, loss: 0.021442275494337082
2023-01-22 14:21:55.155019: step: 1596/530, loss: 0.0056538968347013
2023-01-22 14:21:56.190844: step: 1600/530, loss: 0.0027356247883290052
2023-01-22 14:21:57.249314: step: 1604/530, loss: 0.03917904943227768
2023-01-22 14:21:58.283597: step: 1608/530, loss: 0.008144271560013294
2023-01-22 14:21:59.346430: step: 1612/530, loss: 0.0070854779332876205
2023-01-22 14:22:00.398215: step: 1616/530, loss: 0.004183290060609579
2023-01-22 14:22:01.438146: step: 1620/530, loss: 0.016147736459970474
2023-01-22 14:22:02.471508: step: 1624/530, loss: 0.010289404541254044
2023-01-22 14:22:03.509606: step: 1628/530, loss: 0.024762019515037537
2023-01-22 14:22:04.539794: step: 1632/530, loss: 0.0047640688717365265
2023-01-22 14:22:05.581017: step: 1636/530, loss: 0.023279661312699318
2023-01-22 14:22:06.628923: step: 1640/530, loss: 0.005377603694796562
2023-01-22 14:22:07.679599: step: 1644/530, loss: 0.006198327522724867
2023-01-22 14:22:08.732875: step: 1648/530, loss: 0.008368727751076221
2023-01-22 14:22:09.763275: step: 1652/530, loss: 0.0076696304604411125
2023-01-22 14:22:10.792465: step: 1656/530, loss: 0.008824929594993591
2023-01-22 14:22:11.838163: step: 1660/530, loss: 0.007002229802310467
2023-01-22 14:22:12.874756: step: 1664/530, loss: 0.0011630707886070013
2023-01-22 14:22:13.920953: step: 1668/530, loss: 0.01879848539829254
2023-01-22 14:22:14.969864: step: 1672/530, loss: 0.03044995665550232
2023-01-22 14:22:16.008282: step: 1676/530, loss: 0.01741773635149002
2023-01-22 14:22:17.057402: step: 1680/530, loss: 0.02012798935174942
2023-01-22 14:22:18.105511: step: 1684/530, loss: 0.01884358376264572
2023-01-22 14:22:19.159105: step: 1688/530, loss: 0.030331740155816078
2023-01-22 14:22:20.194132: step: 1692/530, loss: 0.017635803669691086
2023-01-22 14:22:21.230997: step: 1696/530, loss: 0.01589863933622837
2023-01-22 14:22:22.266029: step: 1700/530, loss: 0.02311134524643421
2023-01-22 14:22:23.312875: step: 1704/530, loss: 0.01039676833897829
2023-01-22 14:22:24.356967: step: 1708/530, loss: 0.01273310650140047
2023-01-22 14:22:25.391307: step: 1712/530, loss: 0.03517500311136246
2023-01-22 14:22:26.437787: step: 1716/530, loss: 0.014377455227077007
2023-01-22 14:22:27.488092: step: 1720/530, loss: 0.016340885311365128
2023-01-22 14:22:28.527362: step: 1724/530, loss: 0.043678149580955505
2023-01-22 14:22:29.586011: step: 1728/530, loss: 0.007197216618806124
2023-01-22 14:22:30.625943: step: 1732/530, loss: 0.015771903097629547
2023-01-22 14:22:31.653972: step: 1736/530, loss: 0.006788188125938177
2023-01-22 14:22:32.703863: step: 1740/530, loss: 0.00735519640147686
2023-01-22 14:22:33.754580: step: 1744/530, loss: 0.006124390289187431
2023-01-22 14:22:34.778699: step: 1748/530, loss: 0.011308558285236359
2023-01-22 14:22:35.811194: step: 1752/530, loss: 0.008210016414523125
2023-01-22 14:22:36.850180: step: 1756/530, loss: 0.00381703139282763
2023-01-22 14:22:37.909958: step: 1760/530, loss: 0.013667646795511246
2023-01-22 14:22:38.942533: step: 1764/530, loss: 0.05354391783475876
2023-01-22 14:22:39.969500: step: 1768/530, loss: 0.01885106787085533
2023-01-22 14:22:41.011119: step: 1772/530, loss: 0.024088315665721893
2023-01-22 14:22:42.051231: step: 1776/530, loss: 0.007580232340842485
2023-01-22 14:22:43.087497: step: 1780/530, loss: 0.004514814354479313
2023-01-22 14:22:44.123173: step: 1784/530, loss: 0.028666427358984947
2023-01-22 14:22:45.158867: step: 1788/530, loss: 0.008676419965922832
2023-01-22 14:22:46.199076: step: 1792/530, loss: 0.00014260236639529467
2023-01-22 14:22:47.234399: step: 1796/530, loss: 0.03250482305884361
2023-01-22 14:22:48.288430: step: 1800/530, loss: 0.009149912744760513
2023-01-22 14:22:49.312781: step: 1804/530, loss: 0.02026919089257717
2023-01-22 14:22:50.353977: step: 1808/530, loss: 0.007581941317766905
2023-01-22 14:22:51.418006: step: 1812/530, loss: 0.0193567406386137
2023-01-22 14:22:52.456827: step: 1816/530, loss: 0.006984817795455456
2023-01-22 14:22:53.509933: step: 1820/530, loss: 0.013768985867500305
2023-01-22 14:22:54.543418: step: 1824/530, loss: 0.009857522323727608
2023-01-22 14:22:55.603163: step: 1828/530, loss: 0.005508939735591412
2023-01-22 14:22:56.632305: step: 1832/530, loss: 0.012291674502193928
2023-01-22 14:22:57.673488: step: 1836/530, loss: 0.012963545508682728
2023-01-22 14:22:58.701110: step: 1840/530, loss: 0.010597094893455505
2023-01-22 14:22:59.726470: step: 1844/530, loss: 0.00932835228741169
2023-01-22 14:23:00.785418: step: 1848/530, loss: 0.02392713539302349
2023-01-22 14:23:01.811965: step: 1852/530, loss: 0.031300920993089676
2023-01-22 14:23:02.861622: step: 1856/530, loss: 0.008835088461637497
2023-01-22 14:23:03.913965: step: 1860/530, loss: 0.011457874439656734
2023-01-22 14:23:04.945894: step: 1864/530, loss: 0.007875129580497742
2023-01-22 14:23:05.985730: step: 1868/530, loss: 0.0017395004397258162
2023-01-22 14:23:07.021761: step: 1872/530, loss: 0.005940976087003946
2023-01-22 14:23:08.079374: step: 1876/530, loss: 0.03783702105283737
2023-01-22 14:23:09.116151: step: 1880/530, loss: 0.0
2023-01-22 14:23:10.150543: step: 1884/530, loss: 0.007909106090664864
2023-01-22 14:23:11.177217: step: 1888/530, loss: 0.003788345493376255
2023-01-22 14:23:12.230561: step: 1892/530, loss: 0.00865496788173914
2023-01-22 14:23:13.287212: step: 1896/530, loss: 0.014837266877293587
2023-01-22 14:23:14.331147: step: 1900/530, loss: 0.0070227100513875484
2023-01-22 14:23:15.357167: step: 1904/530, loss: 0.004161282442510128
2023-01-22 14:23:16.392038: step: 1908/530, loss: 0.007852397859096527
2023-01-22 14:23:17.429273: step: 1912/530, loss: 0.009977038949728012
2023-01-22 14:23:18.488747: step: 1916/530, loss: 0.013254792429506779
2023-01-22 14:23:19.526530: step: 1920/530, loss: 0.0016520151402801275
2023-01-22 14:23:20.570652: step: 1924/530, loss: 0.005759743973612785
2023-01-22 14:23:21.629087: step: 1928/530, loss: 0.006398218683898449
2023-01-22 14:23:22.666273: step: 1932/530, loss: 0.05232980102300644
2023-01-22 14:23:23.697698: step: 1936/530, loss: 0.005682214628905058
2023-01-22 14:23:24.738463: step: 1940/530, loss: 0.008255409076809883
2023-01-22 14:23:25.766840: step: 1944/530, loss: 0.0038357547018676996
2023-01-22 14:23:26.814061: step: 1948/530, loss: 0.04414479807019234
2023-01-22 14:23:27.845970: step: 1952/530, loss: 0.009515609592199326
2023-01-22 14:23:28.916132: step: 1956/530, loss: 0.004789245780557394
2023-01-22 14:23:29.961348: step: 1960/530, loss: 0.008225589990615845
2023-01-22 14:23:31.005670: step: 1964/530, loss: 0.010477395728230476
2023-01-22 14:23:32.041525: step: 1968/530, loss: 0.005072738975286484
2023-01-22 14:23:33.073911: step: 1972/530, loss: 0.008390477858483791
2023-01-22 14:23:34.116689: step: 1976/530, loss: 0.007936930283904076
2023-01-22 14:23:35.139037: step: 1980/530, loss: 0.012791875749826431
2023-01-22 14:23:36.185139: step: 1984/530, loss: 0.02164677530527115
2023-01-22 14:23:37.224243: step: 1988/530, loss: 0.008725931867957115
2023-01-22 14:23:38.269054: step: 1992/530, loss: 0.01789635419845581
2023-01-22 14:23:39.327973: step: 1996/530, loss: 0.008945249952375889
2023-01-22 14:23:40.361989: step: 2000/530, loss: 0.00822716485708952
2023-01-22 14:23:41.378829: step: 2004/530, loss: 0.03890697658061981
2023-01-22 14:23:42.415940: step: 2008/530, loss: 0.002574681304395199
2023-01-22 14:23:43.459539: step: 2012/530, loss: 0.01289471983909607
2023-01-22 14:23:44.490019: step: 2016/530, loss: 0.017286738380789757
2023-01-22 14:23:45.510566: step: 2020/530, loss: 0.030664438381791115
2023-01-22 14:23:46.536112: step: 2024/530, loss: 0.0028441408649086952
2023-01-22 14:23:47.575743: step: 2028/530, loss: 0.005331079475581646
2023-01-22 14:23:48.606824: step: 2032/530, loss: 0.012977580539882183
2023-01-22 14:23:49.638072: step: 2036/530, loss: 0.0060233548283576965
2023-01-22 14:23:50.681174: step: 2040/530, loss: 0.020656533539295197
2023-01-22 14:23:51.713808: step: 2044/530, loss: 0.0485132671892643
2023-01-22 14:23:52.761952: step: 2048/530, loss: 0.0027876878157258034
2023-01-22 14:23:53.792071: step: 2052/530, loss: 0.0054365163668990135
2023-01-22 14:23:54.829353: step: 2056/530, loss: 0.008313395082950592
2023-01-22 14:23:55.870626: step: 2060/530, loss: 0.00732328649610281
2023-01-22 14:23:56.921407: step: 2064/530, loss: 0.01545261312276125
2023-01-22 14:23:57.965868: step: 2068/530, loss: 0.002826857380568981
2023-01-22 14:23:59.021671: step: 2072/530, loss: 0.008433181792497635
2023-01-22 14:24:00.067341: step: 2076/530, loss: 0.042273689061403275
2023-01-22 14:24:01.124564: step: 2080/530, loss: 0.012588677927851677
2023-01-22 14:24:02.158513: step: 2084/530, loss: 0.021031657233834267
2023-01-22 14:24:03.186219: step: 2088/530, loss: 0.06965355575084686
2023-01-22 14:24:04.233323: step: 2092/530, loss: 0.004588070325553417
2023-01-22 14:24:05.274876: step: 2096/530, loss: 0.005655618384480476
2023-01-22 14:24:06.335192: step: 2100/530, loss: 0.031774524599313736
2023-01-22 14:24:07.378488: step: 2104/530, loss: 0.0034075728617608547
2023-01-22 14:24:08.419986: step: 2108/530, loss: 0.07965991646051407
2023-01-22 14:24:09.476663: step: 2112/530, loss: 0.0087084099650383
2023-01-22 14:24:10.503280: step: 2116/530, loss: 0.006635582074522972
2023-01-22 14:24:11.552239: step: 2120/530, loss: 0.013546297326683998
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33643172888015715, 'r': 0.32494070208728654, 'f1': 0.33058638996138995}, 'combined': 0.24358997155049783, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36038241037194807, 'r': 0.4087425499990661, 'f1': 0.38304211403874583}, 'combined': 0.2969034568147217, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3097263651772472, 'r': 0.3273578470658951, 'f1': 0.31829812805115626}, 'combined': 0.23453546277453619, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3572886937500997, 'r': 0.41015953905686997, 'f1': 0.38190293409830944}, 'combined': 0.29602045609534033, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3259536558092311, 'r': 0.33894232141073743, 'f1': 0.3323211225738765}, 'combined': 0.24486819558075112, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3550019882443649, 'r': 0.38404167294450137, 'f1': 0.3689512937427087}, 'combined': 0.28598138558047276, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33643172888015715, 'r': 0.32494070208728654, 'f1': 0.33058638996138995}, 'combined': 0.24358997155049783, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36038241037194807, 'r': 0.4087425499990661, 'f1': 0.38304211403874583}, 'combined': 0.2969034568147217, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3097263651772472, 'r': 0.3273578470658951, 'f1': 0.31829812805115626}, 'combined': 0.23453546277453619, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3572886937500997, 'r': 0.41015953905686997, 'f1': 0.38190293409830944}, 'combined': 0.29602045609534033, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3259536558092311, 'r': 0.33894232141073743, 'f1': 0.3323211225738765}, 'combined': 0.24486819558075112, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3550019882443649, 'r': 0.38404167294450137, 'f1': 0.3689512937427087}, 'combined': 0.28598138558047276, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, '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
2023-01-22 14:27:00.548563: step: 4/530, loss: 0.0037888602819293737
2023-01-22 14:27:01.577879: step: 8/530, loss: 0.002274070167914033
2023-01-22 14:27:02.602077: step: 12/530, loss: 0.004175004083663225
2023-01-22 14:27:03.635367: step: 16/530, loss: 0.012923570349812508
2023-01-22 14:27:04.651621: step: 20/530, loss: 0.04172271490097046
2023-01-22 14:27:05.698431: step: 24/530, loss: 0.0073312511667609215
2023-01-22 14:27:06.734565: step: 28/530, loss: 0.01263269130140543
2023-01-22 14:27:07.784215: step: 32/530, loss: 0.013178808614611626
2023-01-22 14:27:08.838662: step: 36/530, loss: 0.013025108724832535
2023-01-22 14:27:09.883317: step: 40/530, loss: 0.003801916493102908
2023-01-22 14:27:10.916875: step: 44/530, loss: 0.00686174351722002
2023-01-22 14:27:11.962928: step: 48/530, loss: 0.008977685123682022
2023-01-22 14:27:12.994406: step: 52/530, loss: 0.005197240971028805
2023-01-22 14:27:14.025125: step: 56/530, loss: 0.005364964250475168
2023-01-22 14:27:15.070946: step: 60/530, loss: 0.01704399101436138
2023-01-22 14:27:16.128269: step: 64/530, loss: 0.009992212988436222
2023-01-22 14:27:17.170143: step: 68/530, loss: 0.007765933871269226
2023-01-22 14:27:18.215696: step: 72/530, loss: 0.003925076685845852
2023-01-22 14:27:19.262200: step: 76/530, loss: 0.000541885441634804
2023-01-22 14:27:20.304216: step: 80/530, loss: 0.004293924663215876
2023-01-22 14:27:21.358573: step: 84/530, loss: 0.009389163926243782
2023-01-22 14:27:22.420140: step: 88/530, loss: 0.01748034916818142
2023-01-22 14:27:23.461963: step: 92/530, loss: 0.014097588136792183
2023-01-22 14:27:24.495107: step: 96/530, loss: 0.01041346974670887
2023-01-22 14:27:25.525784: step: 100/530, loss: 0.007205648813396692
2023-01-22 14:27:26.565847: step: 104/530, loss: 0.007947059348225594
2023-01-22 14:27:27.608041: step: 108/530, loss: 0.009083470329642296
2023-01-22 14:27:28.659347: step: 112/530, loss: 0.0061341156251728535
2023-01-22 14:27:29.698710: step: 116/530, loss: 0.015172949060797691
2023-01-22 14:27:30.746796: step: 120/530, loss: 0.009730362333357334
2023-01-22 14:27:31.797095: step: 124/530, loss: 0.005241116043180227
2023-01-22 14:27:32.839891: step: 128/530, loss: 0.005360835697501898
2023-01-22 14:27:33.883839: step: 132/530, loss: 0.008633263409137726
2023-01-22 14:27:34.936658: step: 136/530, loss: 0.015402628108859062
2023-01-22 14:27:35.989234: step: 140/530, loss: 0.03220726549625397
2023-01-22 14:27:37.062074: step: 144/530, loss: 0.0036236399319022894
2023-01-22 14:27:38.124920: step: 148/530, loss: 0.004044572357088327
2023-01-22 14:27:39.175613: step: 152/530, loss: 0.007374633569270372
2023-01-22 14:27:40.228312: step: 156/530, loss: 0.009039615280926228
2023-01-22 14:27:41.283902: step: 160/530, loss: 0.011822286993265152
2023-01-22 14:27:42.324308: step: 164/530, loss: 0.013853204436600208
2023-01-22 14:27:43.359161: step: 168/530, loss: 0.00663926312699914
2023-01-22 14:27:44.407738: step: 172/530, loss: 0.002951239701360464
2023-01-22 14:27:45.472128: step: 176/530, loss: 0.014926016330718994
2023-01-22 14:27:46.500989: step: 180/530, loss: 0.004300619941204786
2023-01-22 14:27:47.556638: step: 184/530, loss: 0.0028859772719442844
2023-01-22 14:27:48.616812: step: 188/530, loss: 0.009648839943110943
2023-01-22 14:27:49.660576: step: 192/530, loss: 0.005239957477897406
2023-01-22 14:27:50.704678: step: 196/530, loss: 0.01581951417028904
2023-01-22 14:27:51.758063: step: 200/530, loss: 0.005738834384828806
2023-01-22 14:27:52.812634: step: 204/530, loss: 0.006783826742321253
2023-01-22 14:27:53.840211: step: 208/530, loss: 0.015379020012915134
2023-01-22 14:27:54.870684: step: 212/530, loss: 0.00494582811370492
2023-01-22 14:27:55.911786: step: 216/530, loss: 0.004406896885484457
2023-01-22 14:27:56.967185: step: 220/530, loss: 0.039395347237586975
2023-01-22 14:27:58.015877: step: 224/530, loss: 0.015137819573283195
2023-01-22 14:27:59.073876: step: 228/530, loss: 0.008169913664460182
2023-01-22 14:28:00.136175: step: 232/530, loss: 0.08331502974033356
2023-01-22 14:28:01.186467: step: 236/530, loss: 0.012254470027983189
2023-01-22 14:28:02.214621: step: 240/530, loss: 0.003868556348606944
2023-01-22 14:28:03.260145: step: 244/530, loss: 0.0060865022242069244
2023-01-22 14:28:04.312462: step: 248/530, loss: 0.003737794002518058
2023-01-22 14:28:05.354814: step: 252/530, loss: 0.010138806886970997
2023-01-22 14:28:06.407393: step: 256/530, loss: 0.010617443360388279
2023-01-22 14:28:07.430112: step: 260/530, loss: 0.003966417163610458
2023-01-22 14:28:08.474397: step: 264/530, loss: 0.007853623479604721
2023-01-22 14:28:09.516737: step: 268/530, loss: 0.0021429879125207663
2023-01-22 14:28:10.560012: step: 272/530, loss: 0.03301749378442764
2023-01-22 14:28:11.594743: step: 276/530, loss: 0.009293826296925545
2023-01-22 14:28:12.646701: step: 280/530, loss: 0.0011327870888635516
2023-01-22 14:28:13.705560: step: 284/530, loss: 0.003882062854245305
2023-01-22 14:28:14.768770: step: 288/530, loss: 0.0051101697608828545
2023-01-22 14:28:15.812867: step: 292/530, loss: 0.002720510819926858
2023-01-22 14:28:16.857352: step: 296/530, loss: 0.015062347054481506
2023-01-22 14:28:17.895666: step: 300/530, loss: 0.011983749456703663
2023-01-22 14:28:18.952447: step: 304/530, loss: 0.004484365228563547
2023-01-22 14:28:20.014502: step: 308/530, loss: 0.017877696081995964
2023-01-22 14:28:21.061068: step: 312/530, loss: 0.021055176854133606
2023-01-22 14:28:22.103334: step: 316/530, loss: 0.005788861308246851
2023-01-22 14:28:23.148134: step: 320/530, loss: 0.00951676070690155
2023-01-22 14:28:24.188480: step: 324/530, loss: 0.008682755753397942
2023-01-22 14:28:25.228080: step: 328/530, loss: 0.005156229715794325
2023-01-22 14:28:26.270240: step: 332/530, loss: 0.010274766944348812
2023-01-22 14:28:27.323195: step: 336/530, loss: 0.007740643806755543
2023-01-22 14:28:28.367097: step: 340/530, loss: 0.007301523350179195
2023-01-22 14:28:29.411103: step: 344/530, loss: 0.0040678647346794605
2023-01-22 14:28:30.464265: step: 348/530, loss: 0.0038683817256242037
2023-01-22 14:28:31.521993: step: 352/530, loss: 0.014949017204344273
2023-01-22 14:28:32.555380: step: 356/530, loss: 0.014149488881230354
2023-01-22 14:28:33.616536: step: 360/530, loss: 0.0299299955368042
2023-01-22 14:28:34.648608: step: 364/530, loss: 0.015602793544530869
2023-01-22 14:28:35.702017: step: 368/530, loss: 0.013038051314651966
2023-01-22 14:28:36.739009: step: 372/530, loss: 0.00841568410396576
2023-01-22 14:28:37.791565: step: 376/530, loss: 0.04445348307490349
2023-01-22 14:28:38.835684: step: 380/530, loss: 0.012290619313716888
2023-01-22 14:28:39.885602: step: 384/530, loss: 0.020278410986065865
2023-01-22 14:28:40.924550: step: 388/530, loss: 0.053476482629776
2023-01-22 14:28:41.973414: step: 392/530, loss: 0.017562100663781166
2023-01-22 14:28:43.024793: step: 396/530, loss: 0.022115476429462433
2023-01-22 14:28:44.076886: step: 400/530, loss: 0.015994062647223473
2023-01-22 14:28:45.126697: step: 404/530, loss: 0.08731957525014877
2023-01-22 14:28:46.180609: step: 408/530, loss: 0.013568167574703693
2023-01-22 14:28:47.213547: step: 412/530, loss: 0.018604643642902374
2023-01-22 14:28:48.268869: step: 416/530, loss: 0.006680516991764307
2023-01-22 14:28:49.321574: step: 420/530, loss: 0.027568768709897995
2023-01-22 14:28:50.377120: step: 424/530, loss: 0.02251289039850235
2023-01-22 14:28:51.423377: step: 428/530, loss: 0.005960583686828613
2023-01-22 14:28:52.488796: step: 432/530, loss: 0.017948690801858902
2023-01-22 14:28:53.528032: step: 436/530, loss: 0.01131599210202694
2023-01-22 14:28:54.576328: step: 440/530, loss: 0.032078713178634644
2023-01-22 14:28:55.633377: step: 444/530, loss: 0.032719556242227554
2023-01-22 14:28:56.679414: step: 448/530, loss: 0.00150158756878227
2023-01-22 14:28:57.725019: step: 452/530, loss: 0.014419044367969036
2023-01-22 14:28:58.787970: step: 456/530, loss: 0.01792624033987522
2023-01-22 14:28:59.834595: step: 460/530, loss: 0.0016940251225605607
2023-01-22 14:29:00.880620: step: 464/530, loss: 0.0064159780740737915
2023-01-22 14:29:01.922519: step: 468/530, loss: 0.010302126407623291
2023-01-22 14:29:02.991949: step: 472/530, loss: 0.01843603141605854
2023-01-22 14:29:04.041145: step: 476/530, loss: 0.002535809064283967
2023-01-22 14:29:05.080555: step: 480/530, loss: 0.008340365253388882
2023-01-22 14:29:06.125154: step: 484/530, loss: 0.036069102585315704
2023-01-22 14:29:07.174977: step: 488/530, loss: 0.003325577126815915
2023-01-22 14:29:08.230616: step: 492/530, loss: 0.0027209504041820765
2023-01-22 14:29:09.283036: step: 496/530, loss: 0.05793335661292076
2023-01-22 14:29:10.330743: step: 500/530, loss: 0.021056879311800003
2023-01-22 14:29:11.389463: step: 504/530, loss: 0.010850130580365658
2023-01-22 14:29:12.449736: step: 508/530, loss: 0.03423653542995453
2023-01-22 14:29:13.499165: step: 512/530, loss: 0.008309063501656055
2023-01-22 14:29:14.536870: step: 516/530, loss: 0.015190846286714077
2023-01-22 14:29:15.594270: step: 520/530, loss: 0.03745207563042641
2023-01-22 14:29:16.641915: step: 524/530, loss: 0.015186917036771774
2023-01-22 14:29:17.689528: step: 528/530, loss: 0.004568911623209715
2023-01-22 14:29:18.732894: step: 532/530, loss: 0.011096176691353321
2023-01-22 14:29:19.775897: step: 536/530, loss: 0.004400535020977259
2023-01-22 14:29:20.817823: step: 540/530, loss: 0.0
2023-01-22 14:29:21.850527: step: 544/530, loss: 0.01683727838099003
2023-01-22 14:29:22.908830: step: 548/530, loss: 0.007855606265366077
2023-01-22 14:29:23.959835: step: 552/530, loss: 0.044630225747823715
2023-01-22 14:29:25.016158: step: 556/530, loss: 0.02824886329472065
2023-01-22 14:29:26.067634: step: 560/530, loss: 0.0037639860529452562
2023-01-22 14:29:27.130055: step: 564/530, loss: 0.00352419912815094
2023-01-22 14:29:28.172289: step: 568/530, loss: 0.0031005952041596174
2023-01-22 14:29:29.213041: step: 572/530, loss: 0.005644264630973339
2023-01-22 14:29:30.265375: step: 576/530, loss: 0.030470222234725952
2023-01-22 14:29:31.320828: step: 580/530, loss: 0.007264934480190277
2023-01-22 14:29:32.366325: step: 584/530, loss: 0.0066889189183712006
2023-01-22 14:29:33.435215: step: 588/530, loss: 0.024554580450057983
2023-01-22 14:29:34.470283: step: 592/530, loss: 0.01446685940027237
2023-01-22 14:29:35.520853: step: 596/530, loss: 0.01411527581512928
2023-01-22 14:29:36.564431: step: 600/530, loss: 0.040842704474925995
2023-01-22 14:29:37.609397: step: 604/530, loss: 0.006944156717509031
2023-01-22 14:29:38.659365: step: 608/530, loss: 0.007428456097841263
2023-01-22 14:29:39.701878: step: 612/530, loss: 0.007626347243785858
2023-01-22 14:29:40.762596: step: 616/530, loss: 0.00712672108784318
2023-01-22 14:29:41.798627: step: 620/530, loss: 0.014052527025341988
2023-01-22 14:29:42.836498: step: 624/530, loss: 0.03125925734639168
2023-01-22 14:29:43.871895: step: 628/530, loss: 0.01052032969892025
2023-01-22 14:29:44.918169: step: 632/530, loss: 0.0023417561315000057
2023-01-22 14:29:45.969629: step: 636/530, loss: 0.038041893392801285
2023-01-22 14:29:47.019437: step: 640/530, loss: 0.05661146342754364
2023-01-22 14:29:48.068213: step: 644/530, loss: 0.005648643709719181
2023-01-22 14:29:49.131365: step: 648/530, loss: 0.010237081907689571
2023-01-22 14:29:50.191354: step: 652/530, loss: 0.06403376162052155
2023-01-22 14:29:51.253141: step: 656/530, loss: 0.004555267747491598
2023-01-22 14:29:52.293477: step: 660/530, loss: 0.006625948939472437
2023-01-22 14:29:53.344936: step: 664/530, loss: 0.015173325315117836
2023-01-22 14:29:54.381250: step: 668/530, loss: 0.000659630517475307
2023-01-22 14:29:55.435043: step: 672/530, loss: 0.019146470353007317
2023-01-22 14:29:56.486995: step: 676/530, loss: 0.0082447724416852
2023-01-22 14:29:57.536561: step: 680/530, loss: 0.010350859723985195
2023-01-22 14:29:58.586516: step: 684/530, loss: 0.004582496359944344
2023-01-22 14:29:59.624776: step: 688/530, loss: 0.0015153058338910341
2023-01-22 14:30:00.675038: step: 692/530, loss: 0.0077805654145777225
2023-01-22 14:30:01.719471: step: 696/530, loss: 0.00929328054189682
2023-01-22 14:30:02.794186: step: 700/530, loss: 0.004751413129270077
2023-01-22 14:30:03.845208: step: 704/530, loss: 0.016598748043179512
2023-01-22 14:30:04.900065: step: 708/530, loss: 0.009224177338182926
2023-01-22 14:30:05.941466: step: 712/530, loss: 0.0027216775342822075
2023-01-22 14:30:06.983391: step: 716/530, loss: 0.007163349539041519
2023-01-22 14:30:08.029054: step: 720/530, loss: 0.007957649417221546
2023-01-22 14:30:09.078041: step: 724/530, loss: 0.011768410913646221
2023-01-22 14:30:10.126822: step: 728/530, loss: 0.003944066818803549
2023-01-22 14:30:11.179268: step: 732/530, loss: 0.056393641978502274
2023-01-22 14:30:12.215688: step: 736/530, loss: 0.011592704802751541
2023-01-22 14:30:13.258546: step: 740/530, loss: 0.005546966101974249
2023-01-22 14:30:14.291239: step: 744/530, loss: 0.0048983097076416016
2023-01-22 14:30:15.340593: step: 748/530, loss: 0.005409256089478731
2023-01-22 14:30:16.385100: step: 752/530, loss: 0.009478812105953693
2023-01-22 14:30:17.431881: step: 756/530, loss: 0.013316327705979347
2023-01-22 14:30:18.467011: step: 760/530, loss: 0.00597356166690588
2023-01-22 14:30:19.535585: step: 764/530, loss: 0.004640889819711447
2023-01-22 14:30:20.595972: step: 768/530, loss: 0.004776876885443926
2023-01-22 14:30:21.635160: step: 772/530, loss: 0.0035329554229974747
2023-01-22 14:30:22.679570: step: 776/530, loss: 0.015949275344610214
2023-01-22 14:30:23.732848: step: 780/530, loss: 0.005042117089033127
2023-01-22 14:30:24.771522: step: 784/530, loss: 0.005862420424818993
2023-01-22 14:30:25.802622: step: 788/530, loss: 0.00669389171525836
2023-01-22 14:30:26.853137: step: 792/530, loss: 0.011051834560930729
2023-01-22 14:30:27.903285: step: 796/530, loss: 0.003256085328757763
2023-01-22 14:30:28.953043: step: 800/530, loss: 0.006045700516551733
2023-01-22 14:30:29.998555: step: 804/530, loss: 0.007932779379189014
2023-01-22 14:30:31.043149: step: 808/530, loss: 0.008154944516718388
2023-01-22 14:30:32.102876: step: 812/530, loss: 0.009056208655238152
2023-01-22 14:30:33.148175: step: 816/530, loss: 0.013150123879313469
2023-01-22 14:30:34.192457: step: 820/530, loss: 0.008306847885251045
2023-01-22 14:30:35.251092: step: 824/530, loss: 0.021365325897932053
2023-01-22 14:30:36.332498: step: 828/530, loss: 0.0075383419170975685
2023-01-22 14:30:37.383494: step: 832/530, loss: 0.0068174246698617935
2023-01-22 14:30:38.424296: step: 836/530, loss: 0.00420548627153039
2023-01-22 14:30:39.458583: step: 840/530, loss: 0.015030053444206715
2023-01-22 14:30:40.498856: step: 844/530, loss: 0.005739784333854914
2023-01-22 14:30:41.554407: step: 848/530, loss: 0.012050241231918335
2023-01-22 14:30:42.597285: step: 852/530, loss: 0.0020066951401531696
2023-01-22 14:30:43.655698: step: 856/530, loss: 0.009453263133764267
2023-01-22 14:30:44.705544: step: 860/530, loss: 0.008722888305783272
2023-01-22 14:30:45.753397: step: 864/530, loss: 0.006742542143911123
2023-01-22 14:30:46.805792: step: 868/530, loss: 0.004183107055723667
2023-01-22 14:30:47.854266: step: 872/530, loss: 0.004332275129854679
2023-01-22 14:30:48.911387: step: 876/530, loss: 0.011938884854316711
2023-01-22 14:30:49.970414: step: 880/530, loss: 0.008039558306336403
2023-01-22 14:30:51.004025: step: 884/530, loss: 0.012793056666851044
2023-01-22 14:30:52.047847: step: 888/530, loss: 0.00379876303486526
2023-01-22 14:30:53.103660: step: 892/530, loss: 0.03832479566335678
2023-01-22 14:30:54.162765: step: 896/530, loss: 0.010300673544406891
2023-01-22 14:30:55.203803: step: 900/530, loss: 0.03753114119172096
2023-01-22 14:30:56.266578: step: 904/530, loss: 0.01747182384133339
2023-01-22 14:30:57.306014: step: 908/530, loss: 0.0008860359666869044
2023-01-22 14:30:58.380190: step: 912/530, loss: 0.006400313228368759
2023-01-22 14:30:59.425789: step: 916/530, loss: 0.01691780611872673
2023-01-22 14:31:00.493215: step: 920/530, loss: 0.08044847846031189
2023-01-22 14:31:01.534505: step: 924/530, loss: 0.007671186234802008
2023-01-22 14:31:02.609935: step: 928/530, loss: 0.004856127314269543
2023-01-22 14:31:03.653585: step: 932/530, loss: 0.0024805711582303047
2023-01-22 14:31:04.724317: step: 936/530, loss: 0.007052455563098192
2023-01-22 14:31:05.771601: step: 940/530, loss: 0.018911350518465042
2023-01-22 14:31:06.815117: step: 944/530, loss: 0.009532704949378967
2023-01-22 14:31:07.860941: step: 948/530, loss: 0.012691096402704716
2023-01-22 14:31:08.902686: step: 952/530, loss: 0.008381885476410389
2023-01-22 14:31:09.945737: step: 956/530, loss: 0.0026562383864074945
2023-01-22 14:31:10.983205: step: 960/530, loss: 0.003332835389301181
2023-01-22 14:31:12.033211: step: 964/530, loss: 0.00530997384339571
2023-01-22 14:31:13.081738: step: 968/530, loss: 0.0006700890953652561
2023-01-22 14:31:14.146165: step: 972/530, loss: 0.0058180964551866055
2023-01-22 14:31:15.200922: step: 976/530, loss: 0.005701414309442043
2023-01-22 14:31:16.238729: step: 980/530, loss: 0.001955924555659294
2023-01-22 14:31:17.278772: step: 984/530, loss: 0.024068683385849
2023-01-22 14:31:18.325946: step: 988/530, loss: 0.0031588070560246706
2023-01-22 14:31:19.373138: step: 992/530, loss: 0.00401584105566144
2023-01-22 14:31:20.439723: step: 996/530, loss: 0.005481899715960026
2023-01-22 14:31:21.490902: step: 1000/530, loss: 0.010975665412843227
2023-01-22 14:31:22.535202: step: 1004/530, loss: 0.0035874273162335157
2023-01-22 14:31:23.587738: step: 1008/530, loss: 0.005873409099876881
2023-01-22 14:31:24.623923: step: 1012/530, loss: 0.0036414589267224073
2023-01-22 14:31:25.677938: step: 1016/530, loss: 0.0025522729847580194
2023-01-22 14:31:26.756325: step: 1020/530, loss: 0.013500872068107128
2023-01-22 14:31:27.811766: step: 1024/530, loss: 0.01034728717058897
2023-01-22 14:31:28.854078: step: 1028/530, loss: 0.010017571970820427
2023-01-22 14:31:29.902467: step: 1032/530, loss: 0.006204309407621622
2023-01-22 14:31:30.950065: step: 1036/530, loss: 0.006021259818226099
2023-01-22 14:31:31.993355: step: 1040/530, loss: 0.002929095411673188
2023-01-22 14:31:33.038601: step: 1044/530, loss: 0.010702336207032204
2023-01-22 14:31:34.106916: step: 1048/530, loss: 0.017417805269360542
2023-01-22 14:31:35.153915: step: 1052/530, loss: 0.024475088343024254
2023-01-22 14:31:36.194198: step: 1056/530, loss: 0.003840898396447301
2023-01-22 14:31:37.237795: step: 1060/530, loss: 0.004448775202035904
2023-01-22 14:31:38.289828: step: 1064/530, loss: 0.011634442955255508
2023-01-22 14:31:39.322017: step: 1068/530, loss: 0.008896343410015106
2023-01-22 14:31:40.395182: step: 1072/530, loss: 0.0029097062069922686
2023-01-22 14:31:41.448853: step: 1076/530, loss: 0.005392597522586584
2023-01-22 14:31:42.525043: step: 1080/530, loss: 0.03362016752362251
2023-01-22 14:31:43.586154: step: 1084/530, loss: 0.008171535097062588
2023-01-22 14:31:44.670172: step: 1088/530, loss: 0.0062361485324800014
2023-01-22 14:31:45.738810: step: 1092/530, loss: 0.014005381613969803
2023-01-22 14:31:46.791633: step: 1096/530, loss: 0.004480735398828983
2023-01-22 14:31:47.844794: step: 1100/530, loss: 0.00035368840326555073
2023-01-22 14:31:48.904425: step: 1104/530, loss: 0.024342549964785576
2023-01-22 14:31:49.964933: step: 1108/530, loss: 0.004262437578290701
2023-01-22 14:31:51.024454: step: 1112/530, loss: 0.012259361334145069
2023-01-22 14:31:52.081716: step: 1116/530, loss: 0.014585102908313274
2023-01-22 14:31:53.137191: step: 1120/530, loss: 0.00612040376290679
2023-01-22 14:31:54.181787: step: 1124/530, loss: 0.002209411235526204
2023-01-22 14:31:55.235341: step: 1128/530, loss: 0.05484972894191742
2023-01-22 14:31:56.294084: step: 1132/530, loss: 0.0029807996470481157
2023-01-22 14:31:57.353046: step: 1136/530, loss: 0.0065013933926820755
2023-01-22 14:31:58.425668: step: 1140/530, loss: 0.03368424251675606
2023-01-22 14:31:59.464593: step: 1144/530, loss: 0.0046228389255702496
2023-01-22 14:32:00.494774: step: 1148/530, loss: 0.0
2023-01-22 14:32:01.561456: step: 1152/530, loss: 0.00875432975590229
2023-01-22 14:32:02.603047: step: 1156/530, loss: 0.016462694853544235
2023-01-22 14:32:03.656496: step: 1160/530, loss: 0.02316376380622387
2023-01-22 14:32:04.699485: step: 1164/530, loss: 0.004688203800469637
2023-01-22 14:32:05.765132: step: 1168/530, loss: 0.0018599749309942126
2023-01-22 14:32:06.832449: step: 1172/530, loss: 0.014798082411289215
2023-01-22 14:32:07.887016: step: 1176/530, loss: 0.013131591491401196
2023-01-22 14:32:08.939301: step: 1180/530, loss: 0.0017979169497266412
2023-01-22 14:32:09.989047: step: 1184/530, loss: 0.005597659386694431
2023-01-22 14:32:11.037738: step: 1188/530, loss: 0.058025751262903214
2023-01-22 14:32:12.096843: step: 1192/530, loss: 0.009247376583516598
2023-01-22 14:32:13.123271: step: 1196/530, loss: 0.014901560731232166
2023-01-22 14:32:14.157883: step: 1200/530, loss: 0.0023767035454511642
2023-01-22 14:32:15.208942: step: 1204/530, loss: 0.0117331612855196
2023-01-22 14:32:16.243857: step: 1208/530, loss: 0.007630191743373871
2023-01-22 14:32:17.295867: step: 1212/530, loss: 0.011550309136509895
2023-01-22 14:32:18.336881: step: 1216/530, loss: 0.025422869250178337
2023-01-22 14:32:19.390393: step: 1220/530, loss: 0.008089822717010975
2023-01-22 14:32:20.434935: step: 1224/530, loss: 0.005569732282310724
2023-01-22 14:32:21.486432: step: 1228/530, loss: 0.009212653152644634
2023-01-22 14:32:22.521758: step: 1232/530, loss: 0.004605633672326803
2023-01-22 14:32:23.562924: step: 1236/530, loss: 0.003863939084112644
2023-01-22 14:32:24.596181: step: 1240/530, loss: 0.01663948781788349
2023-01-22 14:32:25.624930: step: 1244/530, loss: 0.0005199595470912755
2023-01-22 14:32:26.659699: step: 1248/530, loss: 0.006381301674991846
2023-01-22 14:32:27.693894: step: 1252/530, loss: 0.013552563264966011
2023-01-22 14:32:28.737966: step: 1256/530, loss: 0.027677103877067566
2023-01-22 14:32:29.781593: step: 1260/530, loss: 0.005271045491099358
2023-01-22 14:32:30.824859: step: 1264/530, loss: 0.0034594007302075624
2023-01-22 14:32:31.881535: step: 1268/530, loss: 0.017985286191105843
2023-01-22 14:32:32.934108: step: 1272/530, loss: 0.008233219385147095
2023-01-22 14:32:33.974084: step: 1276/530, loss: 0.003561665304005146
2023-01-22 14:32:35.006291: step: 1280/530, loss: 0.0040474990382790565
2023-01-22 14:32:36.048209: step: 1284/530, loss: 0.008383186534047127
2023-01-22 14:32:37.089123: step: 1288/530, loss: 0.04187886416912079
2023-01-22 14:32:38.124049: step: 1292/530, loss: 0.009270424954593182
2023-01-22 14:32:39.155780: step: 1296/530, loss: 0.009301802143454552
2023-01-22 14:32:40.197882: step: 1300/530, loss: 0.007039169780910015
2023-01-22 14:32:41.248208: step: 1304/530, loss: 0.006889335345476866
2023-01-22 14:32:42.295433: step: 1308/530, loss: 0.008197125978767872
2023-01-22 14:32:43.333615: step: 1312/530, loss: 0.001126836403273046
2023-01-22 14:32:44.365341: step: 1316/530, loss: 0.006413801107555628
2023-01-22 14:32:45.411517: step: 1320/530, loss: 0.047761209309101105
2023-01-22 14:32:46.445469: step: 1324/530, loss: 0.0010622147237882018
2023-01-22 14:32:47.496437: step: 1328/530, loss: 0.006086141336709261
2023-01-22 14:32:48.551180: step: 1332/530, loss: 0.06170609965920448
2023-01-22 14:32:49.595514: step: 1336/530, loss: 0.003733492223545909
2023-01-22 14:32:50.662831: step: 1340/530, loss: 0.006471488159149885
2023-01-22 14:32:51.701615: step: 1344/530, loss: 0.010077622719109058
2023-01-22 14:32:52.743178: step: 1348/530, loss: 0.015354132279753685
2023-01-22 14:32:53.784743: step: 1352/530, loss: 0.009535085409879684
2023-01-22 14:32:54.834474: step: 1356/530, loss: 0.004882055334746838
2023-01-22 14:32:55.870693: step: 1360/530, loss: 0.029433147981762886
2023-01-22 14:32:56.920677: step: 1364/530, loss: 0.008147753775119781
2023-01-22 14:32:57.965547: step: 1368/530, loss: 0.006073904689401388
2023-01-22 14:32:59.029387: step: 1372/530, loss: 0.01107755582779646
2023-01-22 14:33:00.079385: step: 1376/530, loss: 0.002783454954624176
2023-01-22 14:33:01.115821: step: 1380/530, loss: 0.0037271399050951004
2023-01-22 14:33:02.160139: step: 1384/530, loss: 0.002598479390144348
2023-01-22 14:33:03.235982: step: 1388/530, loss: 0.02149217016994953
2023-01-22 14:33:04.270927: step: 1392/530, loss: 0.004607797600328922
2023-01-22 14:33:05.302205: step: 1396/530, loss: 0.0
2023-01-22 14:33:06.335447: step: 1400/530, loss: 0.025173932313919067
2023-01-22 14:33:07.366417: step: 1404/530, loss: 0.006708444561809301
2023-01-22 14:33:08.393817: step: 1408/530, loss: 0.031152212992310524
2023-01-22 14:33:09.422658: step: 1412/530, loss: 0.008127504028379917
2023-01-22 14:33:10.469118: step: 1416/530, loss: 0.007615264039486647
2023-01-22 14:33:11.508762: step: 1420/530, loss: 0.004270453471690416
2023-01-22 14:33:12.577855: step: 1424/530, loss: 0.005471104755997658
2023-01-22 14:33:13.615648: step: 1428/530, loss: 0.01035796944051981
2023-01-22 14:33:14.667282: step: 1432/530, loss: 0.008425642736256123
2023-01-22 14:33:15.724744: step: 1436/530, loss: 0.01042137574404478
2023-01-22 14:33:16.769712: step: 1440/530, loss: 0.00039081694558262825
2023-01-22 14:33:17.813113: step: 1444/530, loss: 0.007506794296205044
2023-01-22 14:33:18.847840: step: 1448/530, loss: 0.0031182970851659775
2023-01-22 14:33:19.888823: step: 1452/530, loss: 0.0005422660033218563
2023-01-22 14:33:20.922013: step: 1456/530, loss: 0.004031767603009939
2023-01-22 14:33:21.957911: step: 1460/530, loss: 0.005994164850562811
2023-01-22 14:33:22.986483: step: 1464/530, loss: 0.0005023129051551223
2023-01-22 14:33:24.049558: step: 1468/530, loss: 0.012664709240198135
2023-01-22 14:33:25.088582: step: 1472/530, loss: 0.049943484365940094
2023-01-22 14:33:26.123566: step: 1476/530, loss: 0.0015420836862176657
2023-01-22 14:33:27.167469: step: 1480/530, loss: 0.0033133160322904587
2023-01-22 14:33:28.204174: step: 1484/530, loss: 0.00653122179210186
2023-01-22 14:33:29.240530: step: 1488/530, loss: 0.007186573464423418
2023-01-22 14:33:30.285476: step: 1492/530, loss: 0.011969853192567825
2023-01-22 14:33:31.326952: step: 1496/530, loss: 0.014530536718666553
2023-01-22 14:33:32.369880: step: 1500/530, loss: 0.006307149305939674
2023-01-22 14:33:33.419715: step: 1504/530, loss: 0.003479381324723363
2023-01-22 14:33:34.457120: step: 1508/530, loss: 0.011177916079759598
2023-01-22 14:33:35.501983: step: 1512/530, loss: 0.005139518994837999
2023-01-22 14:33:36.547254: step: 1516/530, loss: 0.0006295983912423253
2023-01-22 14:33:37.592949: step: 1520/530, loss: 0.006515598390251398
2023-01-22 14:33:38.632358: step: 1524/530, loss: 0.002554867882281542
2023-01-22 14:33:39.674068: step: 1528/530, loss: 0.008377340622246265
2023-01-22 14:33:40.722444: step: 1532/530, loss: 0.05783534795045853
2023-01-22 14:33:41.754343: step: 1536/530, loss: 0.005389595869928598
2023-01-22 14:33:42.779956: step: 1540/530, loss: 0.007903750985860825
2023-01-22 14:33:43.828072: step: 1544/530, loss: 0.0038705479819327593
2023-01-22 14:33:44.875277: step: 1548/530, loss: 0.028735095635056496
2023-01-22 14:33:45.933774: step: 1552/530, loss: 0.005190129857510328
2023-01-22 14:33:46.982804: step: 1556/530, loss: 0.021424822509288788
2023-01-22 14:33:48.030257: step: 1560/530, loss: 0.008036785759031773
2023-01-22 14:33:49.089508: step: 1564/530, loss: 0.04125150665640831
2023-01-22 14:33:50.125339: step: 1568/530, loss: 0.00927783828228712
2023-01-22 14:33:51.155150: step: 1572/530, loss: 0.011850586161017418
2023-01-22 14:33:52.198693: step: 1576/530, loss: 0.005020054988563061
2023-01-22 14:33:53.251358: step: 1580/530, loss: 0.003278045216575265
2023-01-22 14:33:54.294183: step: 1584/530, loss: 0.031927503645420074
2023-01-22 14:33:55.326784: step: 1588/530, loss: 0.026801520958542824
2023-01-22 14:33:56.372153: step: 1592/530, loss: 0.003425628412514925
2023-01-22 14:33:57.410429: step: 1596/530, loss: 0.049877263605594635
2023-01-22 14:33:58.467132: step: 1600/530, loss: 0.006141694262623787
2023-01-22 14:33:59.545202: step: 1604/530, loss: 0.006621780805289745
2023-01-22 14:34:00.588782: step: 1608/530, loss: 0.007877185009419918
2023-01-22 14:34:01.625036: step: 1612/530, loss: 0.0021937566343694925
2023-01-22 14:34:02.667987: step: 1616/530, loss: 0.006378753576427698
2023-01-22 14:34:03.723388: step: 1620/530, loss: 0.011783838272094727
2023-01-22 14:34:04.761105: step: 1624/530, loss: 0.015877580270171165
2023-01-22 14:34:05.796367: step: 1628/530, loss: 0.00994875468313694
2023-01-22 14:34:06.836893: step: 1632/530, loss: 0.00414926465600729
2023-01-22 14:34:07.892390: step: 1636/530, loss: 0.003867295803502202
2023-01-22 14:34:08.949043: step: 1640/530, loss: 0.027900317683815956
2023-01-22 14:34:09.995723: step: 1644/530, loss: 0.053811896592378616
2023-01-22 14:34:11.053249: step: 1648/530, loss: 0.060002632439136505
2023-01-22 14:34:12.106473: step: 1652/530, loss: 0.029271814972162247
2023-01-22 14:34:13.135647: step: 1656/530, loss: 0.011379271745681763
2023-01-22 14:34:14.175170: step: 1660/530, loss: 0.012634336948394775
2023-01-22 14:34:15.202776: step: 1664/530, loss: 0.0009583713253960013
2023-01-22 14:34:16.240321: step: 1668/530, loss: 0.015642007812857628
2023-01-22 14:34:17.267667: step: 1672/530, loss: 0.0030116497073322535
2023-01-22 14:34:18.318311: step: 1676/530, loss: 0.004310282878577709
2023-01-22 14:34:19.361116: step: 1680/530, loss: 0.0039841230027377605
2023-01-22 14:34:20.395334: step: 1684/530, loss: 0.0407322533428669
2023-01-22 14:34:21.422676: step: 1688/530, loss: 0.038015179336071014
2023-01-22 14:34:22.488113: step: 1692/530, loss: 0.0069891661405563354
2023-01-22 14:34:23.529370: step: 1696/530, loss: 0.11138701438903809
2023-01-22 14:34:24.574092: step: 1700/530, loss: 0.019396452233195305
2023-01-22 14:34:25.634288: step: 1704/530, loss: 0.01320500485599041
2023-01-22 14:34:26.685469: step: 1708/530, loss: 0.03175336495041847
2023-01-22 14:34:27.724834: step: 1712/530, loss: 0.006625065114349127
2023-01-22 14:34:28.751615: step: 1716/530, loss: 0.004687377251684666
2023-01-22 14:34:29.791249: step: 1720/530, loss: 0.04952029883861542
2023-01-22 14:34:30.840930: step: 1724/530, loss: 0.07533345371484756
2023-01-22 14:34:31.893168: step: 1728/530, loss: 0.01125490665435791
2023-01-22 14:34:32.942607: step: 1732/530, loss: 0.00745021877810359
2023-01-22 14:34:33.978394: step: 1736/530, loss: 0.037051569670438766
2023-01-22 14:34:35.018399: step: 1740/530, loss: 0.01379351131618023
2023-01-22 14:34:36.064232: step: 1744/530, loss: 0.008265962824225426
2023-01-22 14:34:37.097504: step: 1748/530, loss: 0.00685100955888629
2023-01-22 14:34:38.133918: step: 1752/530, loss: 0.026263441890478134
2023-01-22 14:34:39.176757: step: 1756/530, loss: 0.032217733561992645
2023-01-22 14:34:40.255956: step: 1760/530, loss: 0.008177057839930058
2023-01-22 14:34:41.284162: step: 1764/530, loss: 0.005513209383934736
2023-01-22 14:34:42.311245: step: 1768/530, loss: 0.0
2023-01-22 14:34:43.365434: step: 1772/530, loss: 0.06811343878507614
2023-01-22 14:34:44.413024: step: 1776/530, loss: 0.013587906956672668
2023-01-22 14:34:45.467330: step: 1780/530, loss: 0.05199526995420456
2023-01-22 14:34:46.519887: step: 1784/530, loss: 0.0057129389606416225
2023-01-22 14:34:47.579606: step: 1788/530, loss: 0.007696868851780891
2023-01-22 14:34:48.625770: step: 1792/530, loss: 0.014432776719331741
2023-01-22 14:34:49.688123: step: 1796/530, loss: 0.016515566036105156
2023-01-22 14:34:50.731662: step: 1800/530, loss: 0.005326796788722277
2023-01-22 14:34:51.781390: step: 1804/530, loss: 0.010185799561440945
2023-01-22 14:34:52.826730: step: 1808/530, loss: 0.01364689040929079
2023-01-22 14:34:53.864710: step: 1812/530, loss: 0.07476868480443954
2023-01-22 14:34:54.907083: step: 1816/530, loss: 0.0037018347065895796
2023-01-22 14:34:55.954049: step: 1820/530, loss: 0.005702932830899954
2023-01-22 14:34:57.020772: step: 1824/530, loss: 0.07156221568584442
2023-01-22 14:34:58.065855: step: 1828/530, loss: 0.0053881024941802025
2023-01-22 14:34:59.106308: step: 1832/530, loss: 0.006276683881878853
2023-01-22 14:35:00.141611: step: 1836/530, loss: 0.010244112461805344
2023-01-22 14:35:01.194145: step: 1840/530, loss: 0.008763822726905346
2023-01-22 14:35:02.244297: step: 1844/530, loss: 0.002047961577773094
2023-01-22 14:35:03.291495: step: 1848/530, loss: 0.032293811440467834
2023-01-22 14:35:04.339725: step: 1852/530, loss: 0.04200919345021248
2023-01-22 14:35:05.378329: step: 1856/530, loss: 0.006460108328610659
2023-01-22 14:35:06.417902: step: 1860/530, loss: 0.005821909289807081
2023-01-22 14:35:07.464677: step: 1864/530, loss: 0.03500371426343918
2023-01-22 14:35:08.503165: step: 1868/530, loss: 0.004076194949448109
2023-01-22 14:35:09.540002: step: 1872/530, loss: 0.026200944557785988
2023-01-22 14:35:10.590850: step: 1876/530, loss: 0.006102739367634058
2023-01-22 14:35:11.638309: step: 1880/530, loss: 0.0129562858492136
2023-01-22 14:35:12.677335: step: 1884/530, loss: 0.0
2023-01-22 14:35:13.711016: step: 1888/530, loss: 0.005350232124328613
2023-01-22 14:35:14.748977: step: 1892/530, loss: 0.04558427631855011
2023-01-22 14:35:15.786649: step: 1896/530, loss: 0.007803677581250668
2023-01-22 14:35:16.808455: step: 1900/530, loss: 0.011326824314892292
2023-01-22 14:35:17.863804: step: 1904/530, loss: 0.009796587750315666
2023-01-22 14:35:18.902376: step: 1908/530, loss: 0.024081693962216377
2023-01-22 14:35:19.963011: step: 1912/530, loss: 0.019140874966979027
2023-01-22 14:35:20.999106: step: 1916/530, loss: 0.020053837448358536
2023-01-22 14:35:22.036250: step: 1920/530, loss: 0.005911235697567463
2023-01-22 14:35:23.065235: step: 1924/530, loss: 0.04242753982543945
2023-01-22 14:35:24.100407: step: 1928/530, loss: 0.0036718174815177917
2023-01-22 14:35:25.149362: step: 1932/530, loss: 0.010214921087026596
2023-01-22 14:35:26.192858: step: 1936/530, loss: 0.004558503162115812
2023-01-22 14:35:27.238163: step: 1940/530, loss: 0.006958734709769487
2023-01-22 14:35:28.285681: step: 1944/530, loss: 0.006459183059632778
2023-01-22 14:35:29.340783: step: 1948/530, loss: 0.0028059878386557102
2023-01-22 14:35:30.383733: step: 1952/530, loss: 0.0032257791608572006
2023-01-22 14:35:31.423406: step: 1956/530, loss: 0.008603297173976898
2023-01-22 14:35:32.459113: step: 1960/530, loss: 0.023853909224271774
2023-01-22 14:35:33.527146: step: 1964/530, loss: 0.0091539416462183
2023-01-22 14:35:34.574540: step: 1968/530, loss: 0.009850227274000645
2023-01-22 14:35:35.610570: step: 1972/530, loss: 0.013459211215376854
2023-01-22 14:35:36.642837: step: 1976/530, loss: 0.005713855382055044
2023-01-22 14:35:37.684123: step: 1980/530, loss: 0.0053106388077139854
2023-01-22 14:35:38.713981: step: 1984/530, loss: 0.058550428599119186
2023-01-22 14:35:39.749130: step: 1988/530, loss: 0.0019260910339653492
2023-01-22 14:35:40.797089: step: 1992/530, loss: 0.005154873710125685
2023-01-22 14:35:41.853111: step: 1996/530, loss: 0.0057460288517177105
2023-01-22 14:35:42.886155: step: 2000/530, loss: 0.004854988772422075
2023-01-22 14:35:43.921183: step: 2004/530, loss: 0.035891011357307434
2023-01-22 14:35:44.968343: step: 2008/530, loss: 0.03619098290801048
2023-01-22 14:35:46.017997: step: 2012/530, loss: 0.026967423036694527
2023-01-22 14:35:47.046701: step: 2016/530, loss: 0.0007727580377832055
2023-01-22 14:35:48.093012: step: 2020/530, loss: 0.00412522628903389
2023-01-22 14:35:49.134353: step: 2024/530, loss: 0.004455647896975279
2023-01-22 14:35:50.171757: step: 2028/530, loss: 0.0035373647697269917
2023-01-22 14:35:51.232154: step: 2032/530, loss: 0.01102820411324501
2023-01-22 14:35:52.287181: step: 2036/530, loss: 0.019225461408495903
2023-01-22 14:35:53.340770: step: 2040/530, loss: 0.00877375528216362
2023-01-22 14:35:54.402514: step: 2044/530, loss: 0.009944208897650242
2023-01-22 14:35:55.447124: step: 2048/530, loss: 0.002099336124956608
2023-01-22 14:35:56.520921: step: 2052/530, loss: 0.0059543452225625515
2023-01-22 14:35:57.591107: step: 2056/530, loss: 0.00714087812229991
2023-01-22 14:35:58.642031: step: 2060/530, loss: 0.009105266071856022
2023-01-22 14:35:59.679629: step: 2064/530, loss: 0.004115113522857428
2023-01-22 14:36:00.743014: step: 2068/530, loss: 0.0011670852545648813
2023-01-22 14:36:01.809529: step: 2072/530, loss: 0.018462466076016426
2023-01-22 14:36:02.856642: step: 2076/530, loss: 0.0032242254819720984
2023-01-22 14:36:03.934827: step: 2080/530, loss: 0.0011447686702013016
2023-01-22 14:36:04.977292: step: 2084/530, loss: 0.00122128298971802
2023-01-22 14:36:06.043064: step: 2088/530, loss: 0.03524351119995117
2023-01-22 14:36:07.093373: step: 2092/530, loss: 0.00704927509650588
2023-01-22 14:36:08.161082: step: 2096/530, loss: 0.006289287470281124
2023-01-22 14:36:09.203206: step: 2100/530, loss: 0.004395214840769768
2023-01-22 14:36:10.253582: step: 2104/530, loss: 0.023771753534674644
2023-01-22 14:36:11.307301: step: 2108/530, loss: 0.001265095779672265
2023-01-22 14:36:12.333993: step: 2112/530, loss: 0.0093479473143816
2023-01-22 14:36:13.379581: step: 2116/530, loss: 0.004298749379813671
2023-01-22 14:36:14.403262: step: 2120/530, loss: 0.028923824429512024
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3369657057654076, 'r': 0.3216200189753321, 'f1': 0.32911407766990297}, 'combined': 0.24250510986203375, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3576305599991806, 'r': 0.4075936529402426, 'f1': 0.380981008933835}, 'combined': 0.29530585381474295, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32686606456835515, 'r': 0.33989108801415296, 'f1': 0.33325135513201604}, 'combined': 0.24555363009727496, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3546952438349727, 'r': 0.38794792294450137, 'f1': 0.37057712042459834}, 'combined': 0.2872415957358131, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 2}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33643172888015715, 'r': 0.32494070208728654, 'f1': 0.33058638996138995}, 'combined': 0.24358997155049783, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36038241037194807, 'r': 0.4087425499990661, 'f1': 0.38304211403874583}, 'combined': 0.2969034568147217, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32686606456835515, 'r': 0.33989108801415296, 'f1': 0.33325135513201604}, 'combined': 0.24555363009727496, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3546952438349727, 'r': 0.38794792294450137, 'f1': 0.37057712042459834}, 'combined': 0.2872415957358131, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, '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
2023-01-22 14:38:52.611123: step: 4/530, loss: 0.005431821569800377
2023-01-22 14:38:53.659663: step: 8/530, loss: 0.009996199049055576
2023-01-22 14:38:54.686120: step: 12/530, loss: 0.002863501198589802
2023-01-22 14:38:55.719757: step: 16/530, loss: 0.01014662254601717
2023-01-22 14:38:56.764865: step: 20/530, loss: 0.01043922919780016
2023-01-22 14:38:57.819960: step: 24/530, loss: 0.026406753808259964
2023-01-22 14:38:58.862556: step: 28/530, loss: 0.009597786702215672
2023-01-22 14:38:59.915457: step: 32/530, loss: 0.002693016780540347
2023-01-22 14:39:00.961655: step: 36/530, loss: 0.00951580610126257
2023-01-22 14:39:02.005605: step: 40/530, loss: 0.004581989720463753
2023-01-22 14:39:03.050343: step: 44/530, loss: 0.023599563166499138
2023-01-22 14:39:04.080773: step: 48/530, loss: 0.0036640758626163006
2023-01-22 14:39:05.109256: step: 52/530, loss: 0.004040162544697523
2023-01-22 14:39:06.141231: step: 56/530, loss: 0.005668823607265949
2023-01-22 14:39:07.174854: step: 60/530, loss: 0.003638617228716612
2023-01-22 14:39:08.209150: step: 64/530, loss: 0.006536995060741901
2023-01-22 14:39:09.251576: step: 68/530, loss: 0.007913414388895035
2023-01-22 14:39:10.297797: step: 72/530, loss: 0.03715172037482262
2023-01-22 14:39:11.349706: step: 76/530, loss: 0.007902665063738823
2023-01-22 14:39:12.406371: step: 80/530, loss: 0.015202267095446587
2023-01-22 14:39:13.450248: step: 84/530, loss: 0.005592564586549997
2023-01-22 14:39:14.491260: step: 88/530, loss: 0.017473073676228523
2023-01-22 14:39:15.538316: step: 92/530, loss: 0.010819935239851475
2023-01-22 14:39:16.572220: step: 96/530, loss: 0.00913731288164854
2023-01-22 14:39:17.603110: step: 100/530, loss: 0.005119699519127607
2023-01-22 14:39:18.648999: step: 104/530, loss: 0.005616622511297464
2023-01-22 14:39:19.702896: step: 108/530, loss: 0.019643492996692657
2023-01-22 14:39:20.739437: step: 112/530, loss: 0.010574262589216232
2023-01-22 14:39:21.789341: step: 116/530, loss: 0.005679734982550144
2023-01-22 14:39:22.843862: step: 120/530, loss: 0.004575694911181927
2023-01-22 14:39:23.884924: step: 124/530, loss: 0.0025474310386925936
2023-01-22 14:39:24.942200: step: 128/530, loss: 0.0032287563662976027
2023-01-22 14:39:26.004647: step: 132/530, loss: 0.00046567703248001635
2023-01-22 14:39:27.054371: step: 136/530, loss: 0.01558406837284565
2023-01-22 14:39:28.095936: step: 140/530, loss: 0.0031504291109740734
2023-01-22 14:39:29.136993: step: 144/530, loss: 0.004133196547627449
2023-01-22 14:39:30.184327: step: 148/530, loss: 0.007097297813743353
2023-01-22 14:39:31.217912: step: 152/530, loss: 0.020086877048015594
2023-01-22 14:39:32.258302: step: 156/530, loss: 0.016046728938817978
2023-01-22 14:39:33.283186: step: 160/530, loss: 0.008558408357203007
2023-01-22 14:39:34.348910: step: 164/530, loss: 0.0038368371315300465
2023-01-22 14:39:35.399330: step: 168/530, loss: 0.008134753443300724
2023-01-22 14:39:36.441180: step: 172/530, loss: 0.0055014705285429955
2023-01-22 14:39:37.495892: step: 176/530, loss: 0.0055412412621080875
2023-01-22 14:39:38.526889: step: 180/530, loss: 0.04135976359248161
2023-01-22 14:39:39.563286: step: 184/530, loss: 0.011304151266813278
2023-01-22 14:39:40.612639: step: 188/530, loss: 0.007178763393312693
2023-01-22 14:39:41.675698: step: 192/530, loss: 0.007974209263920784
2023-01-22 14:39:42.758271: step: 196/530, loss: 0.006611658725887537
2023-01-22 14:39:43.809635: step: 200/530, loss: 0.007347870152443647
2023-01-22 14:39:44.870785: step: 204/530, loss: 0.0027312615420669317
2023-01-22 14:39:45.916066: step: 208/530, loss: 0.005284967366605997
2023-01-22 14:39:46.952421: step: 212/530, loss: 0.009669600985944271
2023-01-22 14:39:48.003937: step: 216/530, loss: 0.01777213253080845
2023-01-22 14:39:49.046514: step: 220/530, loss: 0.008092140778899193
2023-01-22 14:39:50.087443: step: 224/530, loss: 0.013502043671905994
2023-01-22 14:39:51.155626: step: 228/530, loss: 0.00566902058199048
2023-01-22 14:39:52.232915: step: 232/530, loss: 0.0021324350964277983
2023-01-22 14:39:53.279970: step: 236/530, loss: 0.0709192305803299
2023-01-22 14:39:54.320230: step: 240/530, loss: 0.006102538201957941
2023-01-22 14:39:55.370086: step: 244/530, loss: 0.024573395028710365
2023-01-22 14:39:56.412029: step: 248/530, loss: 0.009836941957473755
2023-01-22 14:39:57.462014: step: 252/530, loss: 0.0063698445446789265
2023-01-22 14:39:58.526734: step: 256/530, loss: 0.07554195821285248
2023-01-22 14:39:59.568389: step: 260/530, loss: 0.004398987628519535
2023-01-22 14:40:00.604549: step: 264/530, loss: 0.01768602430820465
2023-01-22 14:40:01.663138: step: 268/530, loss: 0.0414053350687027
2023-01-22 14:40:02.697838: step: 272/530, loss: 0.018624572083353996
2023-01-22 14:40:03.758363: step: 276/530, loss: 0.02465970069169998
2023-01-22 14:40:04.794400: step: 280/530, loss: 0.016789887100458145
2023-01-22 14:40:05.858039: step: 284/530, loss: 0.02029453217983246
2023-01-22 14:40:06.907997: step: 288/530, loss: 0.005288269836455584
2023-01-22 14:40:07.954502: step: 292/530, loss: 0.003636611858382821
2023-01-22 14:40:08.999202: step: 296/530, loss: 0.026374856010079384
2023-01-22 14:40:10.052127: step: 300/530, loss: 0.002348975045606494
2023-01-22 14:40:11.103252: step: 304/530, loss: 0.009162580594420433
2023-01-22 14:40:12.144055: step: 308/530, loss: 0.004208069294691086
2023-01-22 14:40:13.195565: step: 312/530, loss: 0.020622577518224716
2023-01-22 14:40:14.226761: step: 316/530, loss: 0.0021263256203383207
2023-01-22 14:40:15.285871: step: 320/530, loss: 0.007317597512155771
2023-01-22 14:40:16.318276: step: 324/530, loss: 0.0004972377209924161
2023-01-22 14:40:17.379565: step: 328/530, loss: 0.0056449174880981445
2023-01-22 14:40:18.426869: step: 332/530, loss: 0.0039084292948246
2023-01-22 14:40:19.467038: step: 336/530, loss: 0.00307081057690084
2023-01-22 14:40:20.513192: step: 340/530, loss: 0.02081211656332016
2023-01-22 14:40:21.583158: step: 344/530, loss: 0.017144719138741493
2023-01-22 14:40:22.636679: step: 348/530, loss: 0.002932160161435604
2023-01-22 14:40:23.678440: step: 352/530, loss: 0.012656448408961296
2023-01-22 14:40:24.743878: step: 356/530, loss: 0.000280795618891716
2023-01-22 14:40:25.787694: step: 360/530, loss: 0.0072136023081839085
2023-01-22 14:40:26.831262: step: 364/530, loss: 0.007043606601655483
2023-01-22 14:40:27.870693: step: 368/530, loss: 0.013517667539417744
2023-01-22 14:40:28.910542: step: 372/530, loss: 0.004874826408922672
2023-01-22 14:40:29.947021: step: 376/530, loss: 0.003717508865520358
2023-01-22 14:40:31.002235: step: 380/530, loss: 0.010346094146370888
2023-01-22 14:40:32.057496: step: 384/530, loss: 0.0156561266630888
2023-01-22 14:40:33.104805: step: 388/530, loss: 0.012330153957009315
2023-01-22 14:40:34.145452: step: 392/530, loss: 0.006983927451074123
2023-01-22 14:40:35.199937: step: 396/530, loss: 0.00360304513014853
2023-01-22 14:40:36.250147: step: 400/530, loss: 0.0014622666640207171
2023-01-22 14:40:37.298924: step: 404/530, loss: 0.0037822534795850515
2023-01-22 14:40:38.345963: step: 408/530, loss: 0.009406151250004768
2023-01-22 14:40:39.407237: step: 412/530, loss: 0.02384459413588047
2023-01-22 14:40:40.444682: step: 416/530, loss: 0.003428320400416851
2023-01-22 14:40:41.490446: step: 420/530, loss: 0.001968947472050786
2023-01-22 14:40:42.553127: step: 424/530, loss: 0.002706412458792329
2023-01-22 14:40:43.614518: step: 428/530, loss: 0.00510001927614212
2023-01-22 14:40:44.664895: step: 432/530, loss: 0.05905650928616524
2023-01-22 14:40:45.716766: step: 436/530, loss: 0.034021515399217606
2023-01-22 14:40:46.759692: step: 440/530, loss: 0.004314336460083723
2023-01-22 14:40:47.802272: step: 444/530, loss: 0.00461387075483799
2023-01-22 14:40:48.854480: step: 448/530, loss: 0.003960966132581234
2023-01-22 14:40:49.906806: step: 452/530, loss: 0.008891516365110874
2023-01-22 14:40:50.956234: step: 456/530, loss: 0.004702720325440168
2023-01-22 14:40:52.021444: step: 460/530, loss: 0.00783851370215416
2023-01-22 14:40:53.063595: step: 464/530, loss: 0.003973011393100023
2023-01-22 14:40:54.099094: step: 468/530, loss: 0.0057945833541452885
2023-01-22 14:40:55.139749: step: 472/530, loss: 0.006109802983701229
2023-01-22 14:40:56.178545: step: 476/530, loss: 0.004593989811837673
2023-01-22 14:40:57.225171: step: 480/530, loss: 0.004475194960832596
2023-01-22 14:40:58.295597: step: 484/530, loss: 0.0083687175065279
2023-01-22 14:40:59.345052: step: 488/530, loss: 0.004098036326467991
2023-01-22 14:41:00.397275: step: 492/530, loss: 0.007627636194229126
2023-01-22 14:41:01.451044: step: 496/530, loss: 0.039637550711631775
2023-01-22 14:41:02.481749: step: 500/530, loss: 0.004907737020403147
2023-01-22 14:41:03.524953: step: 504/530, loss: 0.0031770847272127867
2023-01-22 14:41:04.558534: step: 508/530, loss: 0.005108467768877745
2023-01-22 14:41:05.600332: step: 512/530, loss: 0.004742048680782318
2023-01-22 14:41:06.644217: step: 516/530, loss: 0.006341639906167984
2023-01-22 14:41:07.679750: step: 520/530, loss: 0.0015437587862834334
2023-01-22 14:41:08.731993: step: 524/530, loss: 0.011380205862224102
2023-01-22 14:41:09.780401: step: 528/530, loss: 0.004746524151414633
2023-01-22 14:41:10.844484: step: 532/530, loss: 0.015550093725323677
2023-01-22 14:41:11.882502: step: 536/530, loss: 0.0020516414660960436
2023-01-22 14:41:12.927099: step: 540/530, loss: 0.005931579973548651
2023-01-22 14:41:13.986590: step: 544/530, loss: 0.00400571059435606
2023-01-22 14:41:15.051682: step: 548/530, loss: 0.0054653421975672245
2023-01-22 14:41:16.098491: step: 552/530, loss: 0.003762952983379364
2023-01-22 14:41:17.146411: step: 556/530, loss: 0.015496413223445415
2023-01-22 14:41:18.210205: step: 560/530, loss: 0.03712219372391701
2023-01-22 14:41:19.244517: step: 564/530, loss: 0.03386061638593674
2023-01-22 14:41:20.296500: step: 568/530, loss: 0.0016969263087958097
2023-01-22 14:41:21.348974: step: 572/530, loss: 0.010116786696016788
2023-01-22 14:41:22.379097: step: 576/530, loss: 0.011949919164180756
2023-01-22 14:41:23.446412: step: 580/530, loss: 0.022678064182400703
2023-01-22 14:41:24.492830: step: 584/530, loss: 0.026317300274968147
2023-01-22 14:41:25.527956: step: 588/530, loss: 0.0053278496488928795
2023-01-22 14:41:26.555339: step: 592/530, loss: 0.017307987436652184
2023-01-22 14:41:27.614533: step: 596/530, loss: 0.017238279804587364
2023-01-22 14:41:28.679737: step: 600/530, loss: 0.026832664385437965
2023-01-22 14:41:29.727084: step: 604/530, loss: 0.015705600380897522
2023-01-22 14:41:30.760044: step: 608/530, loss: 0.005115372594445944
2023-01-22 14:41:31.798472: step: 612/530, loss: 0.005850158631801605
2023-01-22 14:41:32.853446: step: 616/530, loss: 0.0015624072402715683
2023-01-22 14:41:33.893137: step: 620/530, loss: 0.0031924168579280376
2023-01-22 14:41:34.947501: step: 624/530, loss: 0.010317697189748287
2023-01-22 14:41:35.992743: step: 628/530, loss: 0.0330805741250515
2023-01-22 14:41:37.033875: step: 632/530, loss: 0.02072126604616642
2023-01-22 14:41:38.083462: step: 636/530, loss: 0.0029019995126873255
2023-01-22 14:41:39.140016: step: 640/530, loss: 0.0052552009001374245
2023-01-22 14:41:40.189842: step: 644/530, loss: 0.009886824525892735
2023-01-22 14:41:41.237252: step: 648/530, loss: 0.01690363511443138
2023-01-22 14:41:42.282719: step: 652/530, loss: 0.01833905093371868
2023-01-22 14:41:43.338069: step: 656/530, loss: 0.008822561241686344
2023-01-22 14:41:44.382767: step: 660/530, loss: 0.006634217221289873
2023-01-22 14:41:45.443602: step: 664/530, loss: 0.010887330397963524
2023-01-22 14:41:46.494939: step: 668/530, loss: 0.004357458092272282
2023-01-22 14:41:47.534287: step: 672/530, loss: 0.004532279912382364
2023-01-22 14:41:48.577534: step: 676/530, loss: 0.0032102311961352825
2023-01-22 14:41:49.625374: step: 680/530, loss: 0.00895298644900322
2023-01-22 14:41:50.675627: step: 684/530, loss: 0.05064159631729126
2023-01-22 14:41:51.713361: step: 688/530, loss: 0.006235008593648672
2023-01-22 14:41:52.784386: step: 692/530, loss: 0.020631618797779083
2023-01-22 14:41:53.831271: step: 696/530, loss: 0.0035677680280059576
2023-01-22 14:41:54.868474: step: 700/530, loss: 0.0010200878605246544
2023-01-22 14:41:55.912048: step: 704/530, loss: 0.009017433039844036
2023-01-22 14:41:56.959610: step: 708/530, loss: 0.005654364824295044
2023-01-22 14:41:58.011023: step: 712/530, loss: 0.0012615763116627932
2023-01-22 14:41:59.087811: step: 716/530, loss: 0.008098145946860313
2023-01-22 14:42:00.132616: step: 720/530, loss: 0.009016198106110096
2023-01-22 14:42:01.209018: step: 724/530, loss: 0.009763686917722225
2023-01-22 14:42:02.255436: step: 728/530, loss: 0.005619431380182505
2023-01-22 14:42:03.295489: step: 732/530, loss: 0.00087446573888883
2023-01-22 14:42:04.334145: step: 736/530, loss: 0.01173071376979351
2023-01-22 14:42:05.388538: step: 740/530, loss: 0.0013534734025597572
2023-01-22 14:42:06.420036: step: 744/530, loss: 0.006439316552132368
2023-01-22 14:42:07.498527: step: 748/530, loss: 0.0033913280349224806
2023-01-22 14:42:08.528362: step: 752/530, loss: 0.007247533183544874
2023-01-22 14:42:09.584956: step: 756/530, loss: 0.0018336847424507141
2023-01-22 14:42:10.623522: step: 760/530, loss: 0.006364730652421713
2023-01-22 14:42:11.669338: step: 764/530, loss: 0.002719556214287877
2023-01-22 14:42:12.733644: step: 768/530, loss: 0.026545636355876923
2023-01-22 14:42:13.783561: step: 772/530, loss: 0.011393429711461067
2023-01-22 14:42:14.830493: step: 776/530, loss: 0.007845165207982063
2023-01-22 14:42:15.872895: step: 780/530, loss: 0.032166190445423126
2023-01-22 14:42:16.909743: step: 784/530, loss: 0.01356776524335146
2023-01-22 14:42:17.954622: step: 788/530, loss: 0.007504757028073072
2023-01-22 14:42:19.001311: step: 792/530, loss: 0.0068154968321323395
2023-01-22 14:42:20.038665: step: 796/530, loss: 0.00044549262383952737
2023-01-22 14:42:21.074264: step: 800/530, loss: 0.0025988593697547913
2023-01-22 14:42:22.108562: step: 804/530, loss: 0.0017277478473260999
2023-01-22 14:42:23.152748: step: 808/530, loss: 0.028265642002224922
2023-01-22 14:42:24.199103: step: 812/530, loss: 0.00908300094306469
2023-01-22 14:42:25.249577: step: 816/530, loss: 0.003962434828281403
2023-01-22 14:42:26.303005: step: 820/530, loss: 0.029387155547738075
2023-01-22 14:42:27.340562: step: 824/530, loss: 0.01663140393793583
2023-01-22 14:42:28.396930: step: 828/530, loss: 0.027380110695958138
2023-01-22 14:42:29.461452: step: 832/530, loss: 0.02776745893061161
2023-01-22 14:42:30.488641: step: 836/530, loss: 0.012709911912679672
2023-01-22 14:42:31.527313: step: 840/530, loss: 0.010074610821902752
2023-01-22 14:42:32.583262: step: 844/530, loss: 0.009502899833023548
2023-01-22 14:42:33.639292: step: 848/530, loss: 0.011394928209483624
2023-01-22 14:42:34.687523: step: 852/530, loss: 0.0006734206690452993
2023-01-22 14:42:35.729703: step: 856/530, loss: 0.011475330218672752
2023-01-22 14:42:36.790230: step: 860/530, loss: 0.021002793684601784
2023-01-22 14:42:37.825957: step: 864/530, loss: 0.012125730514526367
2023-01-22 14:42:38.861669: step: 868/530, loss: 0.0024132307153195143
2023-01-22 14:42:39.925403: step: 872/530, loss: 0.004029131960123777
2023-01-22 14:42:40.970533: step: 876/530, loss: 0.015598522499203682
2023-01-22 14:42:42.015407: step: 880/530, loss: 0.032264843583106995
2023-01-22 14:42:43.064576: step: 884/530, loss: 0.009966591373085976
2023-01-22 14:42:44.118791: step: 888/530, loss: 0.014536065980792046
2023-01-22 14:42:45.168748: step: 892/530, loss: 0.007731547579169273
2023-01-22 14:42:46.226965: step: 896/530, loss: 0.005296436604112387
2023-01-22 14:42:47.334027: step: 900/530, loss: 0.008345085196197033
2023-01-22 14:42:48.374332: step: 904/530, loss: 0.004201252479106188
2023-01-22 14:42:49.432448: step: 908/530, loss: 0.004555849824100733
2023-01-22 14:42:50.470467: step: 912/530, loss: 0.006779415998607874
2023-01-22 14:42:51.525732: step: 916/530, loss: 0.0053204880096018314
2023-01-22 14:42:52.562797: step: 920/530, loss: 0.018930848687887192
2023-01-22 14:42:53.612946: step: 924/530, loss: 0.013539772480726242
2023-01-22 14:42:54.657264: step: 928/530, loss: 0.023202110081911087
2023-01-22 14:42:55.705176: step: 932/530, loss: 0.022371899336576462
2023-01-22 14:42:56.758868: step: 936/530, loss: 0.004724096041172743
2023-01-22 14:42:57.802376: step: 940/530, loss: 0.005772337317466736
2023-01-22 14:42:58.828195: step: 944/530, loss: 0.005176054313778877
2023-01-22 14:42:59.875013: step: 948/530, loss: 0.003047067206352949
2023-01-22 14:43:00.945563: step: 952/530, loss: 0.02281697653234005
2023-01-22 14:43:01.991762: step: 956/530, loss: 0.005941150244325399
2023-01-22 14:43:03.045518: step: 960/530, loss: 0.019261520355939865
2023-01-22 14:43:04.100656: step: 964/530, loss: 0.006394181400537491
2023-01-22 14:43:05.150714: step: 968/530, loss: 0.010386641137301922
2023-01-22 14:43:06.188844: step: 972/530, loss: 0.002203629817813635
2023-01-22 14:43:07.236227: step: 976/530, loss: 0.023285146802663803
2023-01-22 14:43:08.286681: step: 980/530, loss: 0.03983256220817566
2023-01-22 14:43:09.326592: step: 984/530, loss: 0.017802519723773003
2023-01-22 14:43:10.356711: step: 988/530, loss: 0.010056165978312492
2023-01-22 14:43:11.416348: step: 992/530, loss: 0.003944454248994589
2023-01-22 14:43:12.460540: step: 996/530, loss: 0.010143429972231388
2023-01-22 14:43:13.507723: step: 1000/530, loss: 0.007448958232998848
2023-01-22 14:43:14.550584: step: 1004/530, loss: 0.026389002799987793
2023-01-22 14:43:15.608225: step: 1008/530, loss: 0.02232789620757103
2023-01-22 14:43:16.650157: step: 1012/530, loss: 0.004627691116183996
2023-01-22 14:43:17.686021: step: 1016/530, loss: 0.01990676485002041
2023-01-22 14:43:18.730640: step: 1020/530, loss: 0.007293072063475847
2023-01-22 14:43:19.785456: step: 1024/530, loss: 0.0034510032273828983
2023-01-22 14:43:20.835317: step: 1028/530, loss: 0.03335084393620491
2023-01-22 14:43:21.869701: step: 1032/530, loss: 0.021045751869678497
2023-01-22 14:43:22.912370: step: 1036/530, loss: 0.022299353033304214
2023-01-22 14:43:23.973830: step: 1040/530, loss: 0.004965097177773714
2023-01-22 14:43:25.027379: step: 1044/530, loss: 0.0012303362600505352
2023-01-22 14:43:26.081155: step: 1048/530, loss: 0.012189645320177078
2023-01-22 14:43:27.128244: step: 1052/530, loss: 0.009075603447854519
2023-01-22 14:43:28.159088: step: 1056/530, loss: 0.007207685615867376
2023-01-22 14:43:29.219768: step: 1060/530, loss: 0.003411687444895506
2023-01-22 14:43:30.266657: step: 1064/530, loss: 0.0025498555041849613
2023-01-22 14:43:31.321068: step: 1068/530, loss: 0.005067363381385803
2023-01-22 14:43:32.369785: step: 1072/530, loss: 0.004650200717151165
2023-01-22 14:43:33.411299: step: 1076/530, loss: 0.009816146455705166
2023-01-22 14:43:34.451505: step: 1080/530, loss: 0.007132126018404961
2023-01-22 14:43:35.509689: step: 1084/530, loss: 0.013316216878592968
2023-01-22 14:43:36.568103: step: 1088/530, loss: 0.009215674363076687
2023-01-22 14:43:37.618302: step: 1092/530, loss: 0.010878689587116241
2023-01-22 14:43:38.674813: step: 1096/530, loss: 0.008455169387161732
2023-01-22 14:43:39.735775: step: 1100/530, loss: 0.0463222935795784
2023-01-22 14:43:40.767692: step: 1104/530, loss: 0.0018649438861757517
2023-01-22 14:43:41.795675: step: 1108/530, loss: 0.014679823070764542
2023-01-22 14:43:42.838324: step: 1112/530, loss: 0.013960030861198902
2023-01-22 14:43:43.894960: step: 1116/530, loss: 0.009450647979974747
2023-01-22 14:43:44.930057: step: 1120/530, loss: 0.005764094181358814
2023-01-22 14:43:45.994946: step: 1124/530, loss: 0.002159183146432042
2023-01-22 14:43:47.055459: step: 1128/530, loss: 0.006127052009105682
2023-01-22 14:43:48.095122: step: 1132/530, loss: 0.004724337253719568
2023-01-22 14:43:49.147759: step: 1136/530, loss: 0.010194825008511543
2023-01-22 14:43:50.198924: step: 1140/530, loss: 0.012295125052332878
2023-01-22 14:43:51.234271: step: 1144/530, loss: 0.03260317072272301
2023-01-22 14:43:52.293351: step: 1148/530, loss: 0.028742346912622452
2023-01-22 14:43:53.338401: step: 1152/530, loss: 0.006975257769227028
2023-01-22 14:43:54.384727: step: 1156/530, loss: 0.038547661155462265
2023-01-22 14:43:55.431429: step: 1160/530, loss: 0.0048523638397455215
2023-01-22 14:43:56.464319: step: 1164/530, loss: 0.003225501161068678
2023-01-22 14:43:57.500237: step: 1168/530, loss: 0.005581739824265242
2023-01-22 14:43:58.531225: step: 1172/530, loss: 0.016334837302565575
2023-01-22 14:43:59.584208: step: 1176/530, loss: 0.0056094275787472725
2023-01-22 14:44:00.639083: step: 1180/530, loss: 0.0046770451590418816
2023-01-22 14:44:01.694962: step: 1184/530, loss: 0.00882962066680193
2023-01-22 14:44:02.736441: step: 1188/530, loss: 0.007463640533387661
2023-01-22 14:44:03.775331: step: 1192/530, loss: 0.03753942996263504
2023-01-22 14:44:04.809996: step: 1196/530, loss: 0.0013762930175289512
2023-01-22 14:44:05.872030: step: 1200/530, loss: 0.0070342812687158585
2023-01-22 14:44:06.896149: step: 1204/530, loss: 0.002245308831334114
2023-01-22 14:44:07.955895: step: 1208/530, loss: 0.004292265046387911
2023-01-22 14:44:08.996683: step: 1212/530, loss: 0.003306174650788307
2023-01-22 14:44:10.057768: step: 1216/530, loss: 0.003461097367107868
2023-01-22 14:44:11.108894: step: 1220/530, loss: 0.008810692466795444
2023-01-22 14:44:12.172775: step: 1224/530, loss: 0.004546773619949818
2023-01-22 14:44:13.207951: step: 1228/530, loss: 0.014986623078584671
2023-01-22 14:44:14.253865: step: 1232/530, loss: 0.003765576519072056
2023-01-22 14:44:15.296067: step: 1236/530, loss: 0.009695884771645069
2023-01-22 14:44:16.339904: step: 1240/530, loss: 0.001070527476258576
2023-01-22 14:44:17.387711: step: 1244/530, loss: 0.0036728207487612963
2023-01-22 14:44:18.418989: step: 1248/530, loss: 0.006865540519356728
2023-01-22 14:44:19.461837: step: 1252/530, loss: 0.001643989933654666
2023-01-22 14:44:20.487363: step: 1256/530, loss: 0.007976176217198372
2023-01-22 14:44:21.525537: step: 1260/530, loss: 0.03025640919804573
2023-01-22 14:44:22.576225: step: 1264/530, loss: 0.002342989668250084
2023-01-22 14:44:23.622852: step: 1268/530, loss: 0.0005315643502399325
2023-01-22 14:44:24.664558: step: 1272/530, loss: 0.010589626617729664
2023-01-22 14:44:25.709472: step: 1276/530, loss: 0.016972288489341736
2023-01-22 14:44:26.752523: step: 1280/530, loss: 0.003189470386132598
2023-01-22 14:44:27.799009: step: 1284/530, loss: 0.0029718868900090456
2023-01-22 14:44:28.839047: step: 1288/530, loss: 0.011221029795706272
2023-01-22 14:44:29.882617: step: 1292/530, loss: 0.00947148259729147
2023-01-22 14:44:30.929589: step: 1296/530, loss: 0.005764075554907322
2023-01-22 14:44:31.972957: step: 1300/530, loss: 0.01618027128279209
2023-01-22 14:44:33.005184: step: 1304/530, loss: 0.01004018634557724
2023-01-22 14:44:34.056984: step: 1308/530, loss: 0.059785742312669754
2023-01-22 14:44:35.113719: step: 1312/530, loss: 0.01082677859812975
2023-01-22 14:44:36.138144: step: 1316/530, loss: 0.004467769525945187
2023-01-22 14:44:37.186629: step: 1320/530, loss: 0.0015378388343378901
2023-01-22 14:44:38.240878: step: 1324/530, loss: 0.028778837993741035
2023-01-22 14:44:39.274405: step: 1328/530, loss: 0.007330745458602905
2023-01-22 14:44:40.316183: step: 1332/530, loss: 0.012670734897255898
2023-01-22 14:44:41.355961: step: 1336/530, loss: 0.0005725579103454947
2023-01-22 14:44:42.408674: step: 1340/530, loss: 0.026643341407179832
2023-01-22 14:44:43.448491: step: 1344/530, loss: 0.03726726397871971
2023-01-22 14:44:44.485663: step: 1348/530, loss: 0.0052210381254553795
2023-01-22 14:44:45.547969: step: 1352/530, loss: 0.0029350989498198032
2023-01-22 14:44:46.591093: step: 1356/530, loss: 0.0041256071999669075
2023-01-22 14:44:47.636850: step: 1360/530, loss: 0.006800183095037937
2023-01-22 14:44:48.670927: step: 1364/530, loss: 0.005037812516093254
2023-01-22 14:44:49.708851: step: 1368/530, loss: 0.005107303615659475
2023-01-22 14:44:50.739225: step: 1372/530, loss: 0.010213006287813187
2023-01-22 14:44:51.787855: step: 1376/530, loss: 0.004052733536809683
2023-01-22 14:44:52.823833: step: 1380/530, loss: 0.008409635163843632
2023-01-22 14:44:53.858640: step: 1384/530, loss: 0.0036329312715679407
2023-01-22 14:44:54.915345: step: 1388/530, loss: 0.016174299642443657
2023-01-22 14:44:55.962335: step: 1392/530, loss: 0.001608862541615963
2023-01-22 14:44:57.000460: step: 1396/530, loss: 0.005092690233141184
2023-01-22 14:44:58.041659: step: 1400/530, loss: 0.005035769194364548
2023-01-22 14:44:59.079332: step: 1404/530, loss: 0.03963950276374817
2023-01-22 14:45:00.126523: step: 1408/530, loss: 0.0007013366557657719
2023-01-22 14:45:01.170244: step: 1412/530, loss: 0.002183702774345875
2023-01-22 14:45:02.200262: step: 1416/530, loss: 0.0044519598595798016
2023-01-22 14:45:03.255471: step: 1420/530, loss: 0.010128378868103027
2023-01-22 14:45:04.296602: step: 1424/530, loss: 0.004775649402290583
2023-01-22 14:45:05.337989: step: 1428/530, loss: 0.034105680882930756
2023-01-22 14:45:06.370613: step: 1432/530, loss: 0.006160160526633263
2023-01-22 14:45:07.421468: step: 1436/530, loss: 0.005872759502381086
2023-01-22 14:45:08.458241: step: 1440/530, loss: 0.007892990484833717
2023-01-22 14:45:09.503384: step: 1444/530, loss: 0.005610210355371237
2023-01-22 14:45:10.532726: step: 1448/530, loss: 0.0038250540383160114
2023-01-22 14:45:11.585677: step: 1452/530, loss: 0.0013907239772379398
2023-01-22 14:45:12.636791: step: 1456/530, loss: 0.01629927195608616
2023-01-22 14:45:13.672120: step: 1460/530, loss: 0.014263872057199478
2023-01-22 14:45:14.718360: step: 1464/530, loss: 0.007095483597368002
2023-01-22 14:45:15.756311: step: 1468/530, loss: 0.008866426534950733
2023-01-22 14:45:16.809888: step: 1472/530, loss: 0.02516775205731392
2023-01-22 14:45:17.853943: step: 1476/530, loss: 0.003279719967395067
2023-01-22 14:45:18.908541: step: 1480/530, loss: 0.007173987105488777
2023-01-22 14:45:19.946909: step: 1484/530, loss: 0.028564566746354103
2023-01-22 14:45:20.980535: step: 1488/530, loss: 0.00827405322343111
2023-01-22 14:45:22.032110: step: 1492/530, loss: 0.0018098428845405579
2023-01-22 14:45:23.072443: step: 1496/530, loss: 0.0017288204981014132
2023-01-22 14:45:24.117231: step: 1500/530, loss: 0.01009152177721262
2023-01-22 14:45:25.160278: step: 1504/530, loss: 0.011685575358569622
2023-01-22 14:45:26.217924: step: 1508/530, loss: 0.024191131815314293
2023-01-22 14:45:27.261624: step: 1512/530, loss: 0.009218844585120678
2023-01-22 14:45:28.297304: step: 1516/530, loss: 0.008201340213418007
2023-01-22 14:45:29.336063: step: 1520/530, loss: 0.007130790967494249
2023-01-22 14:45:30.384650: step: 1524/530, loss: 0.007450486999005079
2023-01-22 14:45:31.440505: step: 1528/530, loss: 0.009018649347126484
2023-01-22 14:45:32.488748: step: 1532/530, loss: 0.02397296577692032
2023-01-22 14:45:33.535548: step: 1536/530, loss: 0.04176093265414238
2023-01-22 14:45:34.596057: step: 1540/530, loss: 0.0031963936053216457
2023-01-22 14:45:35.643713: step: 1544/530, loss: 0.007208811119198799
2023-01-22 14:45:36.672996: step: 1548/530, loss: 0.006259385030716658
2023-01-22 14:45:37.716323: step: 1552/530, loss: 0.004566723946481943
2023-01-22 14:45:38.758829: step: 1556/530, loss: 0.02112419717013836
2023-01-22 14:45:39.806055: step: 1560/530, loss: 0.0035256589762866497
2023-01-22 14:45:40.856225: step: 1564/530, loss: 0.0024700728245079517
2023-01-22 14:45:41.910177: step: 1568/530, loss: 0.0009783357381820679
2023-01-22 14:45:42.965021: step: 1572/530, loss: 0.011006603948771954
2023-01-22 14:45:44.010371: step: 1576/530, loss: 0.004175816662609577
2023-01-22 14:45:45.042652: step: 1580/530, loss: 0.0032647140324115753
2023-01-22 14:45:46.080781: step: 1584/530, loss: 0.003850224893540144
2023-01-22 14:45:47.146427: step: 1588/530, loss: 0.07564166188240051
2023-01-22 14:45:48.191319: step: 1592/530, loss: 0.00911492109298706
2023-01-22 14:45:49.234678: step: 1596/530, loss: 0.01377045176923275
2023-01-22 14:45:50.278709: step: 1600/530, loss: 0.006769889499992132
2023-01-22 14:45:51.341955: step: 1604/530, loss: 0.016160011291503906
2023-01-22 14:45:52.407359: step: 1608/530, loss: 0.02482665702700615
2023-01-22 14:45:53.477046: step: 1612/530, loss: 0.018679991364479065
2023-01-22 14:45:54.516034: step: 1616/530, loss: 0.006689343601465225
2023-01-22 14:45:55.565264: step: 1620/530, loss: 0.012558117508888245
2023-01-22 14:45:56.611025: step: 1624/530, loss: 0.0026630351785570383
2023-01-22 14:45:57.657503: step: 1628/530, loss: 0.0007008531829342246
2023-01-22 14:45:58.698929: step: 1632/530, loss: 0.007186629809439182
2023-01-22 14:45:59.745181: step: 1636/530, loss: 0.001530971727333963
2023-01-22 14:46:00.794262: step: 1640/530, loss: 0.0047542336396873
2023-01-22 14:46:01.838856: step: 1644/530, loss: 0.006223517470061779
2023-01-22 14:46:02.896178: step: 1648/530, loss: 0.0139730554074049
2023-01-22 14:46:03.962690: step: 1652/530, loss: 0.0036268585827201605
2023-01-22 14:46:05.011302: step: 1656/530, loss: 0.006946123205125332
2023-01-22 14:46:06.056431: step: 1660/530, loss: 0.006818384863436222
2023-01-22 14:46:07.096080: step: 1664/530, loss: 0.0011433502659201622
2023-01-22 14:46:08.157733: step: 1668/530, loss: 0.004938792437314987
2023-01-22 14:46:09.192340: step: 1672/530, loss: 0.011463537812232971
2023-01-22 14:46:10.235460: step: 1676/530, loss: 0.032061465084552765
2023-01-22 14:46:11.265526: step: 1680/530, loss: 0.002863953821361065
2023-01-22 14:46:12.316134: step: 1684/530, loss: 0.04139088839292526
2023-01-22 14:46:13.357492: step: 1688/530, loss: 0.008814378641545773
2023-01-22 14:46:14.410652: step: 1692/530, loss: 0.0033131532836705446
2023-01-22 14:46:15.460068: step: 1696/530, loss: 0.00244878395460546
2023-01-22 14:46:16.493822: step: 1700/530, loss: 0.006749260239303112
2023-01-22 14:46:17.542140: step: 1704/530, loss: 0.005634751170873642
2023-01-22 14:46:18.589523: step: 1708/530, loss: 0.005944405682384968
2023-01-22 14:46:19.618753: step: 1712/530, loss: 0.0054340241476893425
2023-01-22 14:46:20.661319: step: 1716/530, loss: 0.011103671975433826
2023-01-22 14:46:21.704106: step: 1720/530, loss: 0.005122414790093899
2023-01-22 14:46:22.730256: step: 1724/530, loss: 0.01340001355856657
2023-01-22 14:46:23.784588: step: 1728/530, loss: 0.0029655080288648605
2023-01-22 14:46:24.825304: step: 1732/530, loss: 0.002911247778683901
2023-01-22 14:46:25.850928: step: 1736/530, loss: 0.01641754060983658
2023-01-22 14:46:26.915710: step: 1740/530, loss: 0.00841789972037077
2023-01-22 14:46:27.954853: step: 1744/530, loss: 0.0006806628662161529
2023-01-22 14:46:29.001929: step: 1748/530, loss: 0.0027705375105142593
2023-01-22 14:46:30.043601: step: 1752/530, loss: 0.006467380095273256
2023-01-22 14:46:31.089500: step: 1756/530, loss: 0.005140830297023058
2023-01-22 14:46:32.129303: step: 1760/530, loss: 0.004015334416180849
2023-01-22 14:46:33.159835: step: 1764/530, loss: 0.0005897469818592072
2023-01-22 14:46:34.201686: step: 1768/530, loss: 0.022029118612408638
2023-01-22 14:46:35.238158: step: 1772/530, loss: 0.006759891286492348
2023-01-22 14:46:36.290558: step: 1776/530, loss: 0.005062441807240248
2023-01-22 14:46:37.333434: step: 1780/530, loss: 0.03204406052827835
2023-01-22 14:46:38.399246: step: 1784/530, loss: 0.02780924178659916
2023-01-22 14:46:39.445572: step: 1788/530, loss: 0.009049559943377972
2023-01-22 14:46:40.481773: step: 1792/530, loss: 0.025827880948781967
2023-01-22 14:46:41.544467: step: 1796/530, loss: 0.009122991934418678
2023-01-22 14:46:42.573226: step: 1800/530, loss: 0.002891652984544635
2023-01-22 14:46:43.602558: step: 1804/530, loss: 0.019659172743558884
2023-01-22 14:46:44.670410: step: 1808/530, loss: 0.0005233991541899741
2023-01-22 14:46:45.705861: step: 1812/530, loss: 0.024127474054694176
2023-01-22 14:46:46.771042: step: 1816/530, loss: 0.04506048560142517
2023-01-22 14:46:47.813643: step: 1820/530, loss: 0.007663419004529715
2023-01-22 14:46:48.871945: step: 1824/530, loss: 0.0012375907972455025
2023-01-22 14:46:49.927532: step: 1828/530, loss: 0.002767898142337799
2023-01-22 14:46:50.987280: step: 1832/530, loss: 0.007024152670055628
2023-01-22 14:46:52.033167: step: 1836/530, loss: 0.007125238422304392
2023-01-22 14:46:53.075836: step: 1840/530, loss: 0.000880287610925734
2023-01-22 14:46:54.126975: step: 1844/530, loss: 0.02423970401287079
2023-01-22 14:46:55.169267: step: 1848/530, loss: 0.0023451962042599916
2023-01-22 14:46:56.222837: step: 1852/530, loss: 0.015652643516659737
2023-01-22 14:46:57.264455: step: 1856/530, loss: 0.009162044152617455
2023-01-22 14:46:58.318841: step: 1860/530, loss: 0.005536372773349285
2023-01-22 14:46:59.373847: step: 1864/530, loss: 0.006407800130546093
2023-01-22 14:47:00.445155: step: 1868/530, loss: 0.003582555102184415
2023-01-22 14:47:01.497489: step: 1872/530, loss: 0.0066716293804347515
2023-01-22 14:47:02.542179: step: 1876/530, loss: 0.022897623479366302
2023-01-22 14:47:03.589568: step: 1880/530, loss: 0.028789767995476723
2023-01-22 14:47:04.635223: step: 1884/530, loss: 0.003493228694424033
2023-01-22 14:47:05.688235: step: 1888/530, loss: 0.028540266677737236
2023-01-22 14:47:06.745869: step: 1892/530, loss: 0.008012617006897926
2023-01-22 14:47:07.795632: step: 1896/530, loss: 0.004202555399388075
2023-01-22 14:47:08.861471: step: 1900/530, loss: 0.009900493547320366
2023-01-22 14:47:09.892889: step: 1904/530, loss: 0.0005783902597613633
2023-01-22 14:47:10.939860: step: 1908/530, loss: 0.006170824635773897
2023-01-22 14:47:11.985070: step: 1912/530, loss: 0.0012728653382509947
2023-01-22 14:47:13.023184: step: 1916/530, loss: 0.0021315414924174547
2023-01-22 14:47:14.079963: step: 1920/530, loss: 0.002017686842009425
2023-01-22 14:47:15.141145: step: 1924/530, loss: 0.008344687521457672
2023-01-22 14:47:16.189777: step: 1928/530, loss: 0.015048304572701454
2023-01-22 14:47:17.240818: step: 1932/530, loss: 0.025304270908236504
2023-01-22 14:47:18.281378: step: 1936/530, loss: 0.005524095147848129
2023-01-22 14:47:19.326849: step: 1940/530, loss: 0.01964718848466873
2023-01-22 14:47:20.360400: step: 1944/530, loss: 0.006864464376121759
2023-01-22 14:47:21.403449: step: 1948/530, loss: 0.02290772646665573
2023-01-22 14:47:22.441338: step: 1952/530, loss: 0.0013200819958001375
2023-01-22 14:47:23.477230: step: 1956/530, loss: 0.01248240564018488
2023-01-22 14:47:24.550914: step: 1960/530, loss: 0.013508937321603298
2023-01-22 14:47:25.588278: step: 1964/530, loss: 0.015507044270634651
2023-01-22 14:47:26.647539: step: 1968/530, loss: 0.005352470558136702
2023-01-22 14:47:27.696197: step: 1972/530, loss: 0.021453987807035446
2023-01-22 14:47:28.740745: step: 1976/530, loss: 0.0345342680811882
2023-01-22 14:47:29.785687: step: 1980/530, loss: 0.05825893208384514
2023-01-22 14:47:30.833121: step: 1984/530, loss: 0.01437149103730917
2023-01-22 14:47:31.889811: step: 1988/530, loss: 0.006067384500056505
2023-01-22 14:47:32.948739: step: 1992/530, loss: 0.01749325357377529
2023-01-22 14:47:33.985112: step: 1996/530, loss: 0.019947359338402748
2023-01-22 14:47:35.035084: step: 2000/530, loss: 0.04971623420715332
2023-01-22 14:47:36.078985: step: 2004/530, loss: 0.004467702936381102
2023-01-22 14:47:37.123949: step: 2008/530, loss: 0.006505491677671671
2023-01-22 14:47:38.174556: step: 2012/530, loss: 0.023121826350688934
2023-01-22 14:47:39.225336: step: 2016/530, loss: 0.003948783036321402
2023-01-22 14:47:40.248462: step: 2020/530, loss: 0.001281349454075098
2023-01-22 14:47:41.292858: step: 2024/530, loss: 0.003601230215281248
2023-01-22 14:47:42.341143: step: 2028/530, loss: 0.0015417259419336915
2023-01-22 14:47:43.399470: step: 2032/530, loss: 0.03109133429825306
2023-01-22 14:47:44.441994: step: 2036/530, loss: 0.0067815459333360195
2023-01-22 14:47:45.491932: step: 2040/530, loss: 0.003272899193689227
2023-01-22 14:47:46.545334: step: 2044/530, loss: 0.0023744083009660244
2023-01-22 14:47:47.599451: step: 2048/530, loss: 0.010213518515229225
2023-01-22 14:47:48.643040: step: 2052/530, loss: 0.039266642183065414
2023-01-22 14:47:49.695717: step: 2056/530, loss: 0.047216176986694336
2023-01-22 14:47:50.737026: step: 2060/530, loss: 0.003252866445109248
2023-01-22 14:47:51.790895: step: 2064/530, loss: 0.007022211793810129
2023-01-22 14:47:52.834014: step: 2068/530, loss: 0.020488189533352852
2023-01-22 14:47:53.885487: step: 2072/530, loss: 0.006667060777544975
2023-01-22 14:47:54.930120: step: 2076/530, loss: 0.026132578030228615
2023-01-22 14:47:55.970385: step: 2080/530, loss: 0.011762279085814953
2023-01-22 14:47:57.011735: step: 2084/530, loss: 0.010906804352998734
2023-01-22 14:47:58.058203: step: 2088/530, loss: 0.03486092761158943
2023-01-22 14:47:59.118557: step: 2092/530, loss: 0.006506910547614098
2023-01-22 14:48:00.166719: step: 2096/530, loss: 0.002649609697982669
2023-01-22 14:48:01.211031: step: 2100/530, loss: 0.009220363572239876
2023-01-22 14:48:02.264100: step: 2104/530, loss: 0.009778588078916073
2023-01-22 14:48:03.301636: step: 2108/530, loss: 0.021150244399905205
2023-01-22 14:48:04.337540: step: 2112/530, loss: 0.004198956768959761
2023-01-22 14:48:05.381915: step: 2116/530, loss: 0.026482384651899338
2023-01-22 14:48:06.412941: step: 2120/530, loss: 0.0015386679442599416
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33887072434607646, 'r': 0.3195801707779886, 'f1': 0.32894287109375}, 'combined': 0.24237895764802628, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3628786019663803, 'r': 0.4069043147049485, 'f1': 0.3836324908136776}, 'combined': 0.2973610694345252, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3132297126463322, 'r': 0.3197677142385706, 'f1': 0.31646494911497974}, 'combined': 0.2331846993478798, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36007601827284685, 'r': 0.40740218611569345, 'f1': 0.3822799297057995}, 'combined': 0.2963126727863135, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3309190361631691, 'r': 0.33657040490219853, 'f1': 0.3337207965822364}, 'combined': 0.24589953432375314, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3625966782819428, 'r': 0.38725858470920727, 'f1': 0.3745220801454378}, 'combined': 0.29029941140459775, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 3}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33643172888015715, 'r': 0.32494070208728654, 'f1': 0.33058638996138995}, 'combined': 0.24358997155049783, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36038241037194807, 'r': 0.4087425499990661, 'f1': 0.38304211403874583}, 'combined': 0.2969034568147217, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3309190361631691, 'r': 0.33657040490219853, 'f1': 0.3337207965822364}, 'combined': 0.24589953432375314, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3625966782819428, 'r': 0.38725858470920727, 'f1': 0.3745220801454378}, 'combined': 0.29029941140459775, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 14:50:40.285539: step: 4/530, loss: 0.00698957359418273
2023-01-22 14:50:41.326449: step: 8/530, loss: 0.005577901378273964
2023-01-22 14:50:42.385599: step: 12/530, loss: 0.009759383276104927
2023-01-22 14:50:43.436797: step: 16/530, loss: 0.00972414668649435
2023-01-22 14:50:44.485736: step: 20/530, loss: 0.003607033519074321
2023-01-22 14:50:45.562890: step: 24/530, loss: 0.0061666653491556644
2023-01-22 14:50:46.596297: step: 28/530, loss: 0.0029013005550950766
2023-01-22 14:50:47.642898: step: 32/530, loss: 0.003962663933634758
2023-01-22 14:50:48.673719: step: 36/530, loss: 0.0003702733083628118
2023-01-22 14:50:49.732314: step: 40/530, loss: 0.008750868029892445
2023-01-22 14:50:50.793713: step: 44/530, loss: 0.014158329926431179
2023-01-22 14:50:51.843567: step: 48/530, loss: 0.0054846820421516895
2023-01-22 14:50:52.904878: step: 52/530, loss: 0.03825291246175766
2023-01-22 14:50:53.939708: step: 56/530, loss: 0.009429728612303734
2023-01-22 14:50:54.993259: step: 60/530, loss: 0.08134341239929199
2023-01-22 14:50:56.037694: step: 64/530, loss: 0.04206562042236328
2023-01-22 14:50:57.097940: step: 68/530, loss: 0.03217296302318573
2023-01-22 14:50:58.145241: step: 72/530, loss: 0.025985410436987877
2023-01-22 14:50:59.211626: step: 76/530, loss: 0.0024232903961092234
2023-01-22 14:51:00.247178: step: 80/530, loss: 0.0027772444300353527
2023-01-22 14:51:01.277105: step: 84/530, loss: 0.007249601185321808
2023-01-22 14:51:02.311194: step: 88/530, loss: 0.008542601019144058
2023-01-22 14:51:03.382526: step: 92/530, loss: 0.014220623299479485
2023-01-22 14:51:04.435522: step: 96/530, loss: 0.0028424325864762068
2023-01-22 14:51:05.484078: step: 100/530, loss: 0.003984866198152304
2023-01-22 14:51:06.538219: step: 104/530, loss: 0.0011020959354937077
2023-01-22 14:51:07.592976: step: 108/530, loss: 0.01406872272491455
2023-01-22 14:51:08.654577: step: 112/530, loss: 0.018042679876089096
2023-01-22 14:51:09.718233: step: 116/530, loss: 0.01465566549450159
2023-01-22 14:51:10.766116: step: 120/530, loss: 0.022666359320282936
2023-01-22 14:51:11.810849: step: 124/530, loss: 0.006903568748384714
2023-01-22 14:51:12.863938: step: 128/530, loss: 0.016194384545087814
2023-01-22 14:51:13.910037: step: 132/530, loss: 0.00874684751033783
2023-01-22 14:51:14.951131: step: 136/530, loss: 0.013416357338428497
2023-01-22 14:51:15.997543: step: 140/530, loss: 0.028904622420668602
2023-01-22 14:51:17.063135: step: 144/530, loss: 0.010000213049352169
2023-01-22 14:51:18.131719: step: 148/530, loss: 0.03181010112166405
2023-01-22 14:51:19.185867: step: 152/530, loss: 0.009423215873539448
2023-01-22 14:51:20.241256: step: 156/530, loss: 0.019819416105747223
2023-01-22 14:51:21.291073: step: 160/530, loss: 0.020426101982593536
2023-01-22 14:51:22.340297: step: 164/530, loss: 0.005861368030309677
2023-01-22 14:51:23.404847: step: 168/530, loss: 0.0040320781990885735
2023-01-22 14:51:24.505069: step: 172/530, loss: 0.0059257387183606625
2023-01-22 14:51:25.555413: step: 176/530, loss: 0.00250278995372355
2023-01-22 14:51:26.598133: step: 180/530, loss: 8.345173409907147e-05
2023-01-22 14:51:27.645693: step: 184/530, loss: 0.007993591018021107
2023-01-22 14:51:28.706044: step: 188/530, loss: 0.007652263157069683
2023-01-22 14:51:29.758745: step: 192/530, loss: 0.004316218197345734
2023-01-22 14:51:30.816937: step: 196/530, loss: 0.06565670669078827
2023-01-22 14:51:31.861991: step: 200/530, loss: 0.0024813583586364985
2023-01-22 14:51:32.921385: step: 204/530, loss: 0.005987337324768305
2023-01-22 14:51:33.976517: step: 208/530, loss: 0.04859894514083862
2023-01-22 14:51:35.046236: step: 212/530, loss: 0.006227625068277121
2023-01-22 14:51:36.103805: step: 216/530, loss: 0.0035669042263180017
2023-01-22 14:51:37.151669: step: 220/530, loss: 0.03454126417636871
2023-01-22 14:51:38.214883: step: 224/530, loss: 0.0043172771111130714
2023-01-22 14:51:39.262454: step: 228/530, loss: 0.015398088842630386
2023-01-22 14:51:40.332213: step: 232/530, loss: 0.009715782478451729
2023-01-22 14:51:41.401638: step: 236/530, loss: 0.006490217987447977
2023-01-22 14:51:42.467859: step: 240/530, loss: 0.036483947187662125
2023-01-22 14:51:43.517197: step: 244/530, loss: 0.0027672559954226017
2023-01-22 14:51:44.572896: step: 248/530, loss: 0.015252219513058662
2023-01-22 14:51:45.620111: step: 252/530, loss: 0.0074973339214921
2023-01-22 14:51:46.664081: step: 256/530, loss: 0.04847541078925133
2023-01-22 14:51:47.711040: step: 260/530, loss: 0.0017978476826101542
2023-01-22 14:51:48.746010: step: 264/530, loss: 0.004983450286090374
2023-01-22 14:51:49.792292: step: 268/530, loss: 0.017880983650684357
2023-01-22 14:51:50.834351: step: 272/530, loss: 0.008143497630953789
2023-01-22 14:51:51.873935: step: 276/530, loss: 0.0400056317448616
2023-01-22 14:51:52.912354: step: 280/530, loss: 0.03198184072971344
2023-01-22 14:51:53.956046: step: 284/530, loss: 0.008575517684221268
2023-01-22 14:51:55.002811: step: 288/530, loss: 0.004899682942777872
2023-01-22 14:51:56.053238: step: 292/530, loss: 0.016800422221422195
2023-01-22 14:51:57.106105: step: 296/530, loss: 0.023409012705087662
2023-01-22 14:51:58.166097: step: 300/530, loss: 0.00782209075987339
2023-01-22 14:51:59.218628: step: 304/530, loss: 0.04012562334537506
2023-01-22 14:52:00.273808: step: 308/530, loss: 0.006925216410309076
2023-01-22 14:52:01.324122: step: 312/530, loss: 0.01726115122437477
2023-01-22 14:52:02.366683: step: 316/530, loss: 0.006735904607921839
2023-01-22 14:52:03.415424: step: 320/530, loss: 0.004824697971343994
2023-01-22 14:52:04.474227: step: 324/530, loss: 0.005202784202992916
2023-01-22 14:52:05.518998: step: 328/530, loss: 0.02611328847706318
2023-01-22 14:52:06.582703: step: 332/530, loss: 0.004486046265810728
2023-01-22 14:52:07.641185: step: 336/530, loss: 0.0007102540112100542
2023-01-22 14:52:08.678835: step: 340/530, loss: 0.009318984113633633
2023-01-22 14:52:09.731522: step: 344/530, loss: 0.0221951212733984
2023-01-22 14:52:10.774163: step: 348/530, loss: 0.011044745333492756
2023-01-22 14:52:11.831142: step: 352/530, loss: 0.00498811574652791
2023-01-22 14:52:12.880696: step: 356/530, loss: 0.005252169445157051
2023-01-22 14:52:13.924239: step: 360/530, loss: 0.0043073296546936035
2023-01-22 14:52:14.977951: step: 364/530, loss: 0.02234904281795025
2023-01-22 14:52:16.048582: step: 368/530, loss: 0.021820997819304466
2023-01-22 14:52:17.108845: step: 372/530, loss: 0.010399678722023964
2023-01-22 14:52:18.146903: step: 376/530, loss: 0.0050969491712749004
2023-01-22 14:52:19.187994: step: 380/530, loss: 0.008448018692433834
2023-01-22 14:52:20.243073: step: 384/530, loss: 0.005333400797098875
2023-01-22 14:52:21.293460: step: 388/530, loss: 0.008766456507146358
2023-01-22 14:52:22.351065: step: 392/530, loss: 0.010591150261461735
2023-01-22 14:52:23.406819: step: 396/530, loss: 0.009006449021399021
2023-01-22 14:52:24.470943: step: 400/530, loss: 0.0032896576449275017
2023-01-22 14:52:25.527764: step: 404/530, loss: 0.021293066442012787
2023-01-22 14:52:26.572668: step: 408/530, loss: 0.05242776498198509
2023-01-22 14:52:27.617698: step: 412/530, loss: 3.434674727031961e-05
2023-01-22 14:52:28.666982: step: 416/530, loss: 0.01999284327030182
2023-01-22 14:52:29.727143: step: 420/530, loss: 0.0074043977074325085
2023-01-22 14:52:30.800608: step: 424/530, loss: 0.13366059958934784
2023-01-22 14:52:31.853997: step: 428/530, loss: 0.023255396634340286
2023-01-22 14:52:32.932506: step: 432/530, loss: 0.0004912642179988325
2023-01-22 14:52:33.979765: step: 436/530, loss: 0.011607680469751358
2023-01-22 14:52:35.050669: step: 440/530, loss: 0.0020752574782818556
2023-01-22 14:52:36.109169: step: 444/530, loss: 0.07099786400794983
2023-01-22 14:52:37.169915: step: 448/530, loss: 0.005907267332077026
2023-01-22 14:52:38.213281: step: 452/530, loss: 0.06996611505746841
2023-01-22 14:52:39.279464: step: 456/530, loss: 0.005881482269614935
2023-01-22 14:52:40.339463: step: 460/530, loss: 0.005062122363597155
2023-01-22 14:52:41.374581: step: 464/530, loss: 0.003372237551957369
2023-01-22 14:52:42.423373: step: 468/530, loss: 0.005257321987301111
2023-01-22 14:52:43.458898: step: 472/530, loss: 0.03172683343291283
2023-01-22 14:52:44.499638: step: 476/530, loss: 0.01225967239588499
2023-01-22 14:52:45.553620: step: 480/530, loss: 0.0013167110737413168
2023-01-22 14:52:46.618486: step: 484/530, loss: 0.003937763627618551
2023-01-22 14:52:47.695803: step: 488/530, loss: 0.007725742179900408
2023-01-22 14:52:48.723442: step: 492/530, loss: 0.006535510998219252
2023-01-22 14:52:49.775019: step: 496/530, loss: 0.017793122678995132
2023-01-22 14:52:50.833951: step: 500/530, loss: 0.022887732833623886
2023-01-22 14:52:51.876231: step: 504/530, loss: 0.005900170188397169
2023-01-22 14:52:52.929837: step: 508/530, loss: 0.008673862554132938
2023-01-22 14:52:53.972067: step: 512/530, loss: 0.037150681018829346
2023-01-22 14:52:55.016769: step: 516/530, loss: 0.013750494457781315
2023-01-22 14:52:56.072840: step: 520/530, loss: 0.010467853397130966
2023-01-22 14:52:57.113173: step: 524/530, loss: 0.0056411041878163815
2023-01-22 14:52:58.163066: step: 528/530, loss: 0.005132163409143686
2023-01-22 14:52:59.217223: step: 532/530, loss: 0.00888803694397211
2023-01-22 14:53:00.274083: step: 536/530, loss: 0.007849623449146748
2023-01-22 14:53:01.344927: step: 540/530, loss: 0.004741653800010681
2023-01-22 14:53:02.385440: step: 544/530, loss: 0.008709482848644257
2023-01-22 14:53:03.440063: step: 548/530, loss: 0.011547000147402287
2023-01-22 14:53:04.492580: step: 552/530, loss: 0.006960046011954546
2023-01-22 14:53:05.533487: step: 556/530, loss: 0.00825323723256588
2023-01-22 14:53:06.586655: step: 560/530, loss: 0.00787415076047182
2023-01-22 14:53:07.637654: step: 564/530, loss: 0.008960647508502007
2023-01-22 14:53:08.673110: step: 568/530, loss: 0.007930672727525234
2023-01-22 14:53:09.728829: step: 572/530, loss: 0.014611798338592052
2023-01-22 14:53:10.770736: step: 576/530, loss: 0.013681265525519848
2023-01-22 14:53:11.817185: step: 580/530, loss: 0.016878889873623848
2023-01-22 14:53:12.877014: step: 584/530, loss: 0.010972322896122932
2023-01-22 14:53:13.934036: step: 588/530, loss: 0.0035258731804788113
2023-01-22 14:53:14.978890: step: 592/530, loss: 0.0016698520630598068
2023-01-22 14:53:16.046131: step: 596/530, loss: 0.0011435960186645389
2023-01-22 14:53:17.101310: step: 600/530, loss: 0.010016154497861862
2023-01-22 14:53:18.155907: step: 604/530, loss: 0.0032938197255134583
2023-01-22 14:53:19.200715: step: 608/530, loss: 0.0033495163079351187
2023-01-22 14:53:20.251234: step: 612/530, loss: 0.014365960843861103
2023-01-22 14:53:21.318550: step: 616/530, loss: 0.0025987266562879086
2023-01-22 14:53:22.383081: step: 620/530, loss: 0.012022805400192738
2023-01-22 14:53:23.443368: step: 624/530, loss: 0.009118536487221718
2023-01-22 14:53:24.501229: step: 628/530, loss: 0.007564467843621969
2023-01-22 14:53:25.550423: step: 632/530, loss: 0.002989412983879447
2023-01-22 14:53:26.612547: step: 636/530, loss: 0.007266636472195387
2023-01-22 14:53:27.653253: step: 640/530, loss: 0.014965740032494068
2023-01-22 14:53:28.681252: step: 644/530, loss: 0.013009588234126568
2023-01-22 14:53:29.723817: step: 648/530, loss: 0.005896244663745165
2023-01-22 14:53:30.744701: step: 652/530, loss: 0.004902588203549385
2023-01-22 14:53:31.797143: step: 656/530, loss: 0.02602233737707138
2023-01-22 14:53:32.844911: step: 660/530, loss: 0.025441834703087807
2023-01-22 14:53:33.896065: step: 664/530, loss: 0.0050089797005057335
2023-01-22 14:53:34.934306: step: 668/530, loss: 0.00533172395080328
2023-01-22 14:53:35.976698: step: 672/530, loss: 0.017497049644589424
2023-01-22 14:53:37.032812: step: 676/530, loss: 0.006845802068710327
2023-01-22 14:53:38.085380: step: 680/530, loss: 0.04576035961508751
2023-01-22 14:53:39.130696: step: 684/530, loss: 0.017015686258673668
2023-01-22 14:53:40.188341: step: 688/530, loss: 0.013764607720077038
2023-01-22 14:53:41.249507: step: 692/530, loss: 0.0059730298817157745
2023-01-22 14:53:42.304924: step: 696/530, loss: 0.016906701028347015
2023-01-22 14:53:43.341615: step: 700/530, loss: 0.011254091747105122
2023-01-22 14:53:44.385567: step: 704/530, loss: 0.04165195673704147
2023-01-22 14:53:45.445236: step: 708/530, loss: 0.008709629997611046
2023-01-22 14:53:46.520920: step: 712/530, loss: 0.003495514625683427
2023-01-22 14:53:47.562449: step: 716/530, loss: 0.013519697822630405
2023-01-22 14:53:48.604312: step: 720/530, loss: 0.00479164207354188
2023-01-22 14:53:49.652411: step: 724/530, loss: 0.023748546838760376
2023-01-22 14:53:50.700075: step: 728/530, loss: 0.003291499335318804
2023-01-22 14:53:51.755492: step: 732/530, loss: 0.0074381339363753796
2023-01-22 14:53:52.794019: step: 736/530, loss: 0.006539748050272465
2023-01-22 14:53:53.852709: step: 740/530, loss: 0.017345279455184937
2023-01-22 14:53:54.892191: step: 744/530, loss: 0.0003344478609506041
2023-01-22 14:53:55.956417: step: 748/530, loss: 0.007867151871323586
2023-01-22 14:53:57.000156: step: 752/530, loss: 0.005007112864404917
2023-01-22 14:53:58.026411: step: 756/530, loss: 0.0016287514008581638
2023-01-22 14:53:59.079895: step: 760/530, loss: 0.09510177373886108
2023-01-22 14:54:00.104949: step: 764/530, loss: 0.005689023062586784
2023-01-22 14:54:01.147271: step: 768/530, loss: 0.012977197766304016
2023-01-22 14:54:02.196651: step: 772/530, loss: 0.03646525740623474
2023-01-22 14:54:03.260865: step: 776/530, loss: 0.003714514896273613
2023-01-22 14:54:04.311508: step: 780/530, loss: 0.0008592036901973188
2023-01-22 14:54:05.377461: step: 784/530, loss: 0.005687682423740625
2023-01-22 14:54:06.424168: step: 788/530, loss: 0.004032238852232695
2023-01-22 14:54:07.482029: step: 792/530, loss: 0.00727576669305563
2023-01-22 14:54:08.522480: step: 796/530, loss: 0.007024645805358887
2023-01-22 14:54:09.560617: step: 800/530, loss: 0.00732702761888504
2023-01-22 14:54:10.612645: step: 804/530, loss: 0.022994497790932655
2023-01-22 14:54:11.658949: step: 808/530, loss: 0.0047180429100990295
2023-01-22 14:54:12.718258: step: 812/530, loss: 0.01518941204994917
2023-01-22 14:54:13.759209: step: 816/530, loss: 0.033338144421577454
2023-01-22 14:54:14.795433: step: 820/530, loss: 0.0
2023-01-22 14:54:15.847414: step: 824/530, loss: 0.010284901596605778
2023-01-22 14:54:16.893309: step: 828/530, loss: 0.010736415162682533
2023-01-22 14:54:17.922813: step: 832/530, loss: 0.009313641116023064
2023-01-22 14:54:18.978737: step: 836/530, loss: 0.0029275002889335155
2023-01-22 14:54:20.039488: step: 840/530, loss: 0.003788512898609042
2023-01-22 14:54:21.077389: step: 844/530, loss: 0.017399154603481293
2023-01-22 14:54:22.137382: step: 848/530, loss: 0.02060185931622982
2023-01-22 14:54:23.227078: step: 852/530, loss: 0.010406752116978168
2023-01-22 14:54:24.268736: step: 856/530, loss: 0.04205852746963501
2023-01-22 14:54:25.305642: step: 860/530, loss: 0.0013028442626819015
2023-01-22 14:54:26.367449: step: 864/530, loss: 0.002421698998659849
2023-01-22 14:54:27.426713: step: 868/530, loss: 0.009311051107943058
2023-01-22 14:54:28.495480: step: 872/530, loss: 0.008731632493436337
2023-01-22 14:54:29.540209: step: 876/530, loss: 0.01109696738421917
2023-01-22 14:54:30.591358: step: 880/530, loss: 0.00536033371463418
2023-01-22 14:54:31.631036: step: 884/530, loss: 0.007589268498122692
2023-01-22 14:54:32.672779: step: 888/530, loss: 0.010429609566926956
2023-01-22 14:54:33.711802: step: 892/530, loss: 0.009333876892924309
2023-01-22 14:54:34.767901: step: 896/530, loss: 0.011744623072445393
2023-01-22 14:54:35.795927: step: 900/530, loss: 0.050074562430381775
2023-01-22 14:54:36.838093: step: 904/530, loss: 0.012248623184859753
2023-01-22 14:54:37.884843: step: 908/530, loss: 0.03647422045469284
2023-01-22 14:54:38.911144: step: 912/530, loss: 0.008958926424384117
2023-01-22 14:54:39.962409: step: 916/530, loss: 0.00616225553676486
2023-01-22 14:54:41.010881: step: 920/530, loss: 0.008525794371962547
2023-01-22 14:54:42.086261: step: 924/530, loss: 0.05312938243150711
2023-01-22 14:54:43.132349: step: 928/530, loss: 0.007054210640490055
2023-01-22 14:54:44.169728: step: 932/530, loss: 0.00624262448400259
2023-01-22 14:54:45.210930: step: 936/530, loss: 0.010174065828323364
2023-01-22 14:54:46.255987: step: 940/530, loss: 0.006507161073386669
2023-01-22 14:54:47.296925: step: 944/530, loss: 0.0018366253934800625
2023-01-22 14:54:48.339591: step: 948/530, loss: 0.005892733111977577
2023-01-22 14:54:49.394731: step: 952/530, loss: 0.017710620537400246
2023-01-22 14:54:50.439086: step: 956/530, loss: 0.0052134995348751545
2023-01-22 14:54:51.473706: step: 960/530, loss: 0.010730620473623276
2023-01-22 14:54:52.526145: step: 964/530, loss: 0.007666897028684616
2023-01-22 14:54:53.576745: step: 968/530, loss: 0.006504003424197435
2023-01-22 14:54:54.640671: step: 972/530, loss: 0.020299887284636497
2023-01-22 14:54:55.671689: step: 976/530, loss: 0.034470751881599426
2023-01-22 14:54:56.736286: step: 980/530, loss: 0.03596094623208046
2023-01-22 14:54:57.798546: step: 984/530, loss: 0.03155870363116264
2023-01-22 14:54:58.846137: step: 988/530, loss: 0.004506540019065142
2023-01-22 14:54:59.884616: step: 992/530, loss: 0.0012982550542801619
2023-01-22 14:55:00.926845: step: 996/530, loss: 0.004639551974833012
2023-01-22 14:55:01.974254: step: 1000/530, loss: 0.007976015098392963
2023-01-22 14:55:03.012349: step: 1004/530, loss: 0.0011813045712187886
2023-01-22 14:55:04.057786: step: 1008/530, loss: 0.035291992127895355
2023-01-22 14:55:05.107416: step: 1012/530, loss: 0.007459714077413082
2023-01-22 14:55:06.166900: step: 1016/530, loss: 0.002157620619982481
2023-01-22 14:55:07.214056: step: 1020/530, loss: 0.02274075336754322
2023-01-22 14:55:08.264226: step: 1024/530, loss: 0.006961097940802574
2023-01-22 14:55:09.328613: step: 1028/530, loss: 0.010232280939817429
2023-01-22 14:55:10.364424: step: 1032/530, loss: 0.04055550694465637
2023-01-22 14:55:11.397677: step: 1036/530, loss: 0.01339031383395195
2023-01-22 14:55:12.445856: step: 1040/530, loss: 0.004634765442460775
2023-01-22 14:55:13.491843: step: 1044/530, loss: 0.006842790171504021
2023-01-22 14:55:14.523232: step: 1048/530, loss: 0.016985837370157242
2023-01-22 14:55:15.555376: step: 1052/530, loss: 0.005740019958466291
2023-01-22 14:55:16.604450: step: 1056/530, loss: 0.005261383019387722
2023-01-22 14:55:17.641513: step: 1060/530, loss: 0.005717601627111435
2023-01-22 14:55:18.679141: step: 1064/530, loss: 0.005638803355395794
2023-01-22 14:55:19.734666: step: 1068/530, loss: 0.01046875212341547
2023-01-22 14:55:20.786675: step: 1072/530, loss: 0.017455007880926132
2023-01-22 14:55:21.826933: step: 1076/530, loss: 0.06218757480382919
2023-01-22 14:55:22.868491: step: 1080/530, loss: 0.005418209824711084
2023-01-22 14:55:23.917361: step: 1084/530, loss: 0.0048764487728476524
2023-01-22 14:55:24.969825: step: 1088/530, loss: 0.003680927213281393
2023-01-22 14:55:26.017993: step: 1092/530, loss: 0.01458392571657896
2023-01-22 14:55:27.058659: step: 1096/530, loss: 0.01482077594846487
2023-01-22 14:55:28.127507: step: 1100/530, loss: 0.009594163857400417
2023-01-22 14:55:29.190351: step: 1104/530, loss: 0.009059345349669456
2023-01-22 14:55:30.233453: step: 1108/530, loss: 0.005022795870900154
2023-01-22 14:55:31.267488: step: 1112/530, loss: 0.03085966967046261
2023-01-22 14:55:32.307700: step: 1116/530, loss: 0.02273603156208992
2023-01-22 14:55:33.384275: step: 1120/530, loss: 0.002015126636251807
2023-01-22 14:55:34.424820: step: 1124/530, loss: 0.004609286785125732
2023-01-22 14:55:35.472247: step: 1128/530, loss: 0.019310960546135902
2023-01-22 14:55:36.517880: step: 1132/530, loss: 0.003627246478572488
2023-01-22 14:55:37.541627: step: 1136/530, loss: 0.04110556095838547
2023-01-22 14:55:38.575915: step: 1140/530, loss: 0.04287181794643402
2023-01-22 14:55:39.613846: step: 1144/530, loss: 0.020180117338895798
2023-01-22 14:55:40.648788: step: 1148/530, loss: 0.007182359229773283
2023-01-22 14:55:41.713805: step: 1152/530, loss: 0.009614327922463417
2023-01-22 14:55:42.763140: step: 1156/530, loss: 0.013087702915072441
2023-01-22 14:55:43.813679: step: 1160/530, loss: 0.005982095841318369
2023-01-22 14:55:44.847818: step: 1164/530, loss: 0.017094234004616737
2023-01-22 14:55:45.907107: step: 1168/530, loss: 0.03535285219550133
2023-01-22 14:55:46.953559: step: 1172/530, loss: 0.005485684610903263
2023-01-22 14:55:47.984058: step: 1176/530, loss: 0.008174329996109009
2023-01-22 14:55:49.022259: step: 1180/530, loss: 0.054272785782814026
2023-01-22 14:55:50.085336: step: 1184/530, loss: 0.0036752077285200357
2023-01-22 14:55:51.131671: step: 1188/530, loss: 0.005187473725527525
2023-01-22 14:55:52.183321: step: 1192/530, loss: 0.009865966625511646
2023-01-22 14:55:53.222603: step: 1196/530, loss: 0.013367796316742897
2023-01-22 14:55:54.253825: step: 1200/530, loss: 0.0031492505222558975
2023-01-22 14:55:55.308228: step: 1204/530, loss: 0.0247766375541687
2023-01-22 14:55:56.358568: step: 1208/530, loss: 0.009023106656968594
2023-01-22 14:55:57.408980: step: 1212/530, loss: 0.017439616844058037
2023-01-22 14:55:58.461815: step: 1216/530, loss: 0.016809113323688507
2023-01-22 14:55:59.510133: step: 1220/530, loss: 0.010281943716108799
2023-01-22 14:56:00.555411: step: 1224/530, loss: 0.010823133401572704
2023-01-22 14:56:01.600241: step: 1228/530, loss: 0.0019613010808825493
2023-01-22 14:56:02.647240: step: 1232/530, loss: 0.01822686567902565
2023-01-22 14:56:03.733538: step: 1236/530, loss: 0.0029462017118930817
2023-01-22 14:56:04.781572: step: 1240/530, loss: 0.020956365391612053
2023-01-22 14:56:05.835145: step: 1244/530, loss: 0.0054284934885799885
2023-01-22 14:56:06.879181: step: 1248/530, loss: 0.012328865006566048
2023-01-22 14:56:07.921974: step: 1252/530, loss: 0.006256837397813797
2023-01-22 14:56:08.971880: step: 1256/530, loss: 0.017065048217773438
2023-01-22 14:56:10.012890: step: 1260/530, loss: 0.028776071965694427
2023-01-22 14:56:11.059038: step: 1264/530, loss: 0.01057056151330471
2023-01-22 14:56:12.110494: step: 1268/530, loss: 0.006096193566918373
2023-01-22 14:56:13.157310: step: 1272/530, loss: 0.008900323882699013
2023-01-22 14:56:14.203778: step: 1276/530, loss: 0.024897761642932892
2023-01-22 14:56:15.248385: step: 1280/530, loss: 0.004362307954579592
2023-01-22 14:56:16.296169: step: 1284/530, loss: 0.017800914123654366
2023-01-22 14:56:17.352358: step: 1288/530, loss: 0.004053147044032812
2023-01-22 14:56:18.442217: step: 1292/530, loss: 0.010714251548051834
2023-01-22 14:56:19.468584: step: 1296/530, loss: 0.003834869246929884
2023-01-22 14:56:20.499394: step: 1300/530, loss: 0.0013706920435652137
2023-01-22 14:56:21.530693: step: 1304/530, loss: 0.0031859204173088074
2023-01-22 14:56:22.570427: step: 1308/530, loss: 0.0012207464314997196
2023-01-22 14:56:23.619241: step: 1312/530, loss: 0.009991885162889957
2023-01-22 14:56:24.658892: step: 1316/530, loss: 0.015509245917201042
2023-01-22 14:56:25.712778: step: 1320/530, loss: 0.019073287025094032
2023-01-22 14:56:26.741129: step: 1324/530, loss: 0.0037361180875450373
2023-01-22 14:56:27.788832: step: 1328/530, loss: 0.006787933874875307
2023-01-22 14:56:28.848723: step: 1332/530, loss: 0.00792840775102377
2023-01-22 14:56:29.897516: step: 1336/530, loss: 0.006871415302157402
2023-01-22 14:56:30.972587: step: 1340/530, loss: 0.0063455612398684025
2023-01-22 14:56:32.037848: step: 1344/530, loss: 0.00801592506468296
2023-01-22 14:56:33.082090: step: 1348/530, loss: 0.005658675916492939
2023-01-22 14:56:34.122765: step: 1352/530, loss: 0.0009868519846349955
2023-01-22 14:56:35.159678: step: 1356/530, loss: 0.0038439419586211443
2023-01-22 14:56:36.201991: step: 1360/530, loss: 0.013685734011232853
2023-01-22 14:56:37.239672: step: 1364/530, loss: 0.008099840953946114
2023-01-22 14:56:38.290650: step: 1368/530, loss: 0.02620629221200943
2023-01-22 14:56:39.343076: step: 1372/530, loss: 0.007384863682091236
2023-01-22 14:56:40.373572: step: 1376/530, loss: 0.007157912943512201
2023-01-22 14:56:41.431699: step: 1380/530, loss: 0.009436335414648056
2023-01-22 14:56:42.474291: step: 1384/530, loss: 0.0024360492825508118
2023-01-22 14:56:43.509917: step: 1388/530, loss: 0.0035571043845266104
2023-01-22 14:56:44.558240: step: 1392/530, loss: 0.003238662611693144
2023-01-22 14:56:45.603141: step: 1396/530, loss: 0.010676134377717972
2023-01-22 14:56:46.642965: step: 1400/530, loss: 0.023820823058485985
2023-01-22 14:56:47.709513: step: 1404/530, loss: 0.007093852385878563
2023-01-22 14:56:48.755237: step: 1408/530, loss: 0.01626482978463173
2023-01-22 14:56:49.802496: step: 1412/530, loss: 0.007416965905576944
2023-01-22 14:56:50.842186: step: 1416/530, loss: 0.008428905159235
2023-01-22 14:56:51.874605: step: 1420/530, loss: 0.006196982692927122
2023-01-22 14:56:52.917323: step: 1424/530, loss: 0.007847960107028484
2023-01-22 14:56:53.982911: step: 1428/530, loss: 0.011245768517255783
2023-01-22 14:56:55.032760: step: 1432/530, loss: 0.009996861219406128
2023-01-22 14:56:56.068923: step: 1436/530, loss: 0.006398098077625036
2023-01-22 14:56:57.100035: step: 1440/530, loss: 0.007841511629521847
2023-01-22 14:56:58.150203: step: 1444/530, loss: 0.01365701574832201
2023-01-22 14:56:59.215500: step: 1448/530, loss: 0.0033150888048112392
2023-01-22 14:57:00.261613: step: 1452/530, loss: 0.006269114091992378
2023-01-22 14:57:01.328136: step: 1456/530, loss: 0.007052919827401638
2023-01-22 14:57:02.380299: step: 1460/530, loss: 0.009731998667120934
2023-01-22 14:57:03.439606: step: 1464/530, loss: 0.003838661126792431
2023-01-22 14:57:04.473364: step: 1468/530, loss: 0.01154538057744503
2023-01-22 14:57:05.509051: step: 1472/530, loss: 0.0013273765798658133
2023-01-22 14:57:06.552799: step: 1476/530, loss: 0.0021753162145614624
2023-01-22 14:57:07.605387: step: 1480/530, loss: 0.0069759986363351345
2023-01-22 14:57:08.668099: step: 1484/530, loss: 0.008999811485409737
2023-01-22 14:57:09.712227: step: 1488/530, loss: 0.0032044530380517244
2023-01-22 14:57:10.760635: step: 1492/530, loss: 0.014354582875967026
2023-01-22 14:57:11.807623: step: 1496/530, loss: 0.006890683434903622
2023-01-22 14:57:12.862513: step: 1500/530, loss: 0.02164403349161148
2023-01-22 14:57:13.907807: step: 1504/530, loss: 0.03095339424908161
2023-01-22 14:57:14.967505: step: 1508/530, loss: 0.0008790783467702568
2023-01-22 14:57:16.005504: step: 1512/530, loss: 0.04674437269568443
2023-01-22 14:57:17.063165: step: 1516/530, loss: 0.101894311606884
2023-01-22 14:57:18.115238: step: 1520/530, loss: 0.0021620166953653097
2023-01-22 14:57:19.172829: step: 1524/530, loss: 0.0021734475158154964
2023-01-22 14:57:20.231236: step: 1528/530, loss: 0.0014497135998681188
2023-01-22 14:57:21.291815: step: 1532/530, loss: 0.010232940316200256
2023-01-22 14:57:22.334890: step: 1536/530, loss: 0.0036849970929324627
2023-01-22 14:57:23.363345: step: 1540/530, loss: 0.0018424472073093057
2023-01-22 14:57:24.416638: step: 1544/530, loss: 0.05146528780460358
2023-01-22 14:57:25.457030: step: 1548/530, loss: 0.0035465096589177847
2023-01-22 14:57:26.505954: step: 1552/530, loss: 0.061646562069654465
2023-01-22 14:57:27.545479: step: 1556/530, loss: 0.0005200144951231778
2023-01-22 14:57:28.609019: step: 1560/530, loss: 0.01526939868927002
2023-01-22 14:57:29.658777: step: 1564/530, loss: 0.027888912707567215
2023-01-22 14:57:30.683008: step: 1568/530, loss: 0.05533529072999954
2023-01-22 14:57:31.730816: step: 1572/530, loss: 0.01628085970878601
2023-01-22 14:57:32.777024: step: 1576/530, loss: 0.00815799180418253
2023-01-22 14:57:33.830394: step: 1580/530, loss: 0.014769169501960278
2023-01-22 14:57:34.890999: step: 1584/530, loss: 0.005658401176333427
2023-01-22 14:57:35.939188: step: 1588/530, loss: 0.015470368787646294
2023-01-22 14:57:36.979801: step: 1592/530, loss: 0.008477414958178997
2023-01-22 14:57:38.034575: step: 1596/530, loss: 0.010669825598597527
2023-01-22 14:57:39.082635: step: 1600/530, loss: 0.009646205231547356
2023-01-22 14:57:40.144432: step: 1604/530, loss: 0.010238900780677795
2023-01-22 14:57:41.188205: step: 1608/530, loss: 0.008970411494374275
2023-01-22 14:57:42.229480: step: 1612/530, loss: 0.02410770393908024
2023-01-22 14:57:43.263332: step: 1616/530, loss: 0.002660715952515602
2023-01-22 14:57:44.319044: step: 1620/530, loss: 0.035264208912849426
2023-01-22 14:57:45.373445: step: 1624/530, loss: 0.040786709636449814
2023-01-22 14:57:46.436613: step: 1628/530, loss: 0.013235140591859818
2023-01-22 14:57:47.492937: step: 1632/530, loss: 0.003664294956251979
2023-01-22 14:57:48.532404: step: 1636/530, loss: 0.010146270506083965
2023-01-22 14:57:49.583517: step: 1640/530, loss: 0.01120872050523758
2023-01-22 14:57:50.630362: step: 1644/530, loss: 0.0021815954241901636
2023-01-22 14:57:51.684502: step: 1648/530, loss: 0.0029521456453949213
2023-01-22 14:57:52.728514: step: 1652/530, loss: 0.0017736885929480195
2023-01-22 14:57:53.764660: step: 1656/530, loss: 0.01834573969244957
2023-01-22 14:57:54.822222: step: 1660/530, loss: 0.011319626122713089
2023-01-22 14:57:55.870557: step: 1664/530, loss: 0.016198961064219475
2023-01-22 14:57:56.921099: step: 1668/530, loss: 0.056787099689245224
2023-01-22 14:57:57.966846: step: 1672/530, loss: 0.045961495488882065
2023-01-22 14:57:59.008298: step: 1676/530, loss: 0.0072120968252420425
2023-01-22 14:58:00.077404: step: 1680/530, loss: 0.023251408711075783
2023-01-22 14:58:01.134851: step: 1684/530, loss: 0.03631749376654625
2023-01-22 14:58:02.171257: step: 1688/530, loss: 0.007739008869975805
2023-01-22 14:58:03.234197: step: 1692/530, loss: 0.011212572455406189
2023-01-22 14:58:04.269152: step: 1696/530, loss: 0.0021334963385015726
2023-01-22 14:58:05.330278: step: 1700/530, loss: 0.00017072352056857198
2023-01-22 14:58:06.394686: step: 1704/530, loss: 0.0054739732295274734
2023-01-22 14:58:07.431803: step: 1708/530, loss: 0.010552710853517056
2023-01-22 14:58:08.486572: step: 1712/530, loss: 0.008474929258227348
2023-01-22 14:58:09.542857: step: 1716/530, loss: 0.13012246787548065
2023-01-22 14:58:10.589208: step: 1720/530, loss: 0.02956259623169899
2023-01-22 14:58:11.628130: step: 1724/530, loss: 0.0059948209673166275
2023-01-22 14:58:12.676336: step: 1728/530, loss: 0.017709113657474518
2023-01-22 14:58:13.725193: step: 1732/530, loss: 0.0005050949403084815
2023-01-22 14:58:14.774486: step: 1736/530, loss: 0.004136632662266493
2023-01-22 14:58:15.840298: step: 1740/530, loss: 0.008426767773926258
2023-01-22 14:58:16.897528: step: 1744/530, loss: 0.016573533415794373
2023-01-22 14:58:17.947153: step: 1748/530, loss: 0.00579869793727994
2023-01-22 14:58:18.997090: step: 1752/530, loss: 0.005031159613281488
2023-01-22 14:58:20.064051: step: 1756/530, loss: 0.003828752087429166
2023-01-22 14:58:21.115494: step: 1760/530, loss: 0.010850084945559502
2023-01-22 14:58:22.164426: step: 1764/530, loss: 0.010462482459843159
2023-01-22 14:58:23.215651: step: 1768/530, loss: 0.005388755816966295
2023-01-22 14:58:24.241721: step: 1772/530, loss: 0.005045648198574781
2023-01-22 14:58:25.289260: step: 1776/530, loss: 0.03065331280231476
2023-01-22 14:58:26.346282: step: 1780/530, loss: 0.015230027958750725
2023-01-22 14:58:27.392320: step: 1784/530, loss: 0.009330620057880878
2023-01-22 14:58:28.450092: step: 1788/530, loss: 0.01424208004027605
2023-01-22 14:58:29.491687: step: 1792/530, loss: 0.0177735835313797
2023-01-22 14:58:30.527559: step: 1796/530, loss: 0.0021712735760957003
2023-01-22 14:58:31.577916: step: 1800/530, loss: 0.02098984457552433
2023-01-22 14:58:32.630198: step: 1804/530, loss: 0.007077093701809645
2023-01-22 14:58:33.702726: step: 1808/530, loss: 0.014779459685087204
2023-01-22 14:58:34.747686: step: 1812/530, loss: 0.009713179431855679
2023-01-22 14:58:35.783400: step: 1816/530, loss: 0.007239634171128273
2023-01-22 14:58:36.821983: step: 1820/530, loss: 0.016949862241744995
2023-01-22 14:58:37.869557: step: 1824/530, loss: 0.006182401441037655
2023-01-22 14:58:38.922001: step: 1828/530, loss: 0.00745818205177784
2023-01-22 14:58:39.952120: step: 1832/530, loss: 0.005689422599971294
2023-01-22 14:58:41.008718: step: 1836/530, loss: 0.013964063487946987
2023-01-22 14:58:42.053183: step: 1840/530, loss: 0.013131942600011826
2023-01-22 14:58:43.109493: step: 1844/530, loss: 0.08743832260370255
2023-01-22 14:58:44.143929: step: 1848/530, loss: 0.04414644464850426
2023-01-22 14:58:45.210183: step: 1852/530, loss: 0.026749644428491592
2023-01-22 14:58:46.245742: step: 1856/530, loss: 0.009580439887940884
2023-01-22 14:58:47.289528: step: 1860/530, loss: 0.005677979905158281
2023-01-22 14:58:48.333656: step: 1864/530, loss: 0.03229353204369545
2023-01-22 14:58:49.375764: step: 1868/530, loss: 0.04599224776029587
2023-01-22 14:58:50.407931: step: 1872/530, loss: 0.011477844789624214
2023-01-22 14:58:51.464736: step: 1876/530, loss: 0.009884202852845192
2023-01-22 14:58:52.515070: step: 1880/530, loss: 0.05241717770695686
2023-01-22 14:58:53.588122: step: 1884/530, loss: 0.010632255114614964
2023-01-22 14:58:54.629470: step: 1888/530, loss: 0.024795083329081535
2023-01-22 14:58:55.658317: step: 1892/530, loss: 0.026442566886544228
2023-01-22 14:58:56.707521: step: 1896/530, loss: 0.01335377898067236
2023-01-22 14:58:57.743271: step: 1900/530, loss: 0.008220052346587181
2023-01-22 14:58:58.795621: step: 1904/530, loss: 0.0382801778614521
2023-01-22 14:58:59.853777: step: 1908/530, loss: 0.021652933210134506
2023-01-22 14:59:00.937651: step: 1912/530, loss: 0.007596184033900499
2023-01-22 14:59:02.001983: step: 1916/530, loss: 0.022892331704497337
2023-01-22 14:59:03.028620: step: 1920/530, loss: 0.02290131151676178
2023-01-22 14:59:04.068111: step: 1924/530, loss: 0.009573090821504593
2023-01-22 14:59:05.110669: step: 1928/530, loss: 0.01821368932723999
2023-01-22 14:59:06.162887: step: 1932/530, loss: 0.006589924450963736
2023-01-22 14:59:07.215666: step: 1936/530, loss: 0.009054798632860184
2023-01-22 14:59:08.277481: step: 1940/530, loss: 0.008845238015055656
2023-01-22 14:59:09.320851: step: 1944/530, loss: 0.012344438582658768
2023-01-22 14:59:10.365806: step: 1948/530, loss: 0.0037157577462494373
2023-01-22 14:59:11.425049: step: 1952/530, loss: 0.04312935099005699
2023-01-22 14:59:12.458720: step: 1956/530, loss: 0.011651946231722832
2023-01-22 14:59:13.495117: step: 1960/530, loss: 0.008804849348962307
2023-01-22 14:59:14.556487: step: 1964/530, loss: 0.006081140600144863
2023-01-22 14:59:15.598729: step: 1968/530, loss: 0.01485342625528574
2023-01-22 14:59:16.655539: step: 1972/530, loss: 0.05511125922203064
2023-01-22 14:59:17.696092: step: 1976/530, loss: 0.0005198437720537186
2023-01-22 14:59:18.743541: step: 1980/530, loss: 0.012522531673312187
2023-01-22 14:59:19.795063: step: 1984/530, loss: 0.005106591619551182
2023-01-22 14:59:20.845123: step: 1988/530, loss: 0.011177177540957928
2023-01-22 14:59:21.908785: step: 1992/530, loss: 0.10730155557394028
2023-01-22 14:59:22.964292: step: 1996/530, loss: 0.0010632263729348779
2023-01-22 14:59:24.032139: step: 2000/530, loss: 0.01684959977865219
2023-01-22 14:59:25.100630: step: 2004/530, loss: 0.009729632176458836
2023-01-22 14:59:26.151149: step: 2008/530, loss: 0.0021659997291862965
2023-01-22 14:59:27.189905: step: 2012/530, loss: 0.0
2023-01-22 14:59:28.245998: step: 2016/530, loss: 0.006851190701127052
2023-01-22 14:59:29.291638: step: 2020/530, loss: 0.008856294676661491
2023-01-22 14:59:30.338339: step: 2024/530, loss: 0.035453442484140396
2023-01-22 14:59:31.398380: step: 2028/530, loss: 0.004786839243024588
2023-01-22 14:59:32.439108: step: 2032/530, loss: 0.004009741358458996
2023-01-22 14:59:33.483829: step: 2036/530, loss: 0.0008362511289305985
2023-01-22 14:59:34.519448: step: 2040/530, loss: 0.006732499692589045
2023-01-22 14:59:35.583197: step: 2044/530, loss: 0.0007510983268730342
2023-01-22 14:59:36.628477: step: 2048/530, loss: 0.0034757957328110933
2023-01-22 14:59:37.670699: step: 2052/530, loss: 0.03197331726551056
2023-01-22 14:59:38.721692: step: 2056/530, loss: 0.020527182146906853
2023-01-22 14:59:39.764332: step: 2060/530, loss: 0.014108306728303432
2023-01-22 14:59:40.807968: step: 2064/530, loss: 0.00789572298526764
2023-01-22 14:59:41.839333: step: 2068/530, loss: 0.005245354492217302
2023-01-22 14:59:42.866897: step: 2072/530, loss: 0.02112613432109356
2023-01-22 14:59:43.925590: step: 2076/530, loss: 0.018814364448189735
2023-01-22 14:59:44.980727: step: 2080/530, loss: 0.02076384611427784
2023-01-22 14:59:46.054836: step: 2084/530, loss: 0.0627404972910881
2023-01-22 14:59:47.100194: step: 2088/530, loss: 0.005093692801892757
2023-01-22 14:59:48.161634: step: 2092/530, loss: 0.0432882159948349
2023-01-22 14:59:49.208792: step: 2096/530, loss: 0.035880811512470245
2023-01-22 14:59:50.259100: step: 2100/530, loss: 0.00565405422821641
2023-01-22 14:59:51.295531: step: 2104/530, loss: 0.051265835762023926
2023-01-22 14:59:52.331128: step: 2108/530, loss: 0.0059537808410823345
2023-01-22 14:59:53.369829: step: 2112/530, loss: 0.006259667221456766
2023-01-22 14:59:54.409059: step: 2116/530, loss: 0.0066326819360256195
2023-01-22 14:59:55.452248: step: 2120/530, loss: 0.026345986872911453
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3390625, 'r': 0.32683823529411765, 'f1': 0.3328381642512077}, 'combined': 0.24524917365878462, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36247919934929645, 'r': 0.4101212264696543, 'f1': 0.38483130176712715}, 'combined': 0.29829029132188806, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3048877435318826, 'r': 0.32166524744540176, 'f1': 0.31305186593486006}, 'combined': 0.23066979595200213, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35455193814355507, 'r': 0.4083213037627523, 'f1': 0.3795417159281286}, 'combined': 0.2941902295710853, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3235916727961207, 'r': 0.33894232141073743, 'f1': 0.331089162897977}, 'combined': 0.243960435819562, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35840045893255523, 'r': 0.3877181435327367, 'f1': 0.3724833025727307}, 'combined': 0.28871911491283436, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 4}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3390625, 'r': 0.32683823529411765, 'f1': 0.3328381642512077}, 'combined': 0.24524917365878462, 'stategy': 1, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36247919934929645, 'r': 0.4101212264696543, 'f1': 0.38483130176712715}, 'combined': 0.29829029132188806, 'stategy': 1, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3309190361631691, 'r': 0.33657040490219853, 'f1': 0.3337207965822364}, 'combined': 0.24589953432375314, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3625966782819428, 'r': 0.38725858470920727, 'f1': 0.3745220801454378}, 'combined': 0.29029941140459775, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 5
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 15:02:34.423477: step: 4/530, loss: 0.005588268395513296
2023-01-22 15:02:35.452896: step: 8/530, loss: 0.06199086457490921
2023-01-22 15:02:36.493901: step: 12/530, loss: 0.008542483672499657
2023-01-22 15:02:37.543074: step: 16/530, loss: 0.012168132700026035
2023-01-22 15:02:38.590157: step: 20/530, loss: 0.00337317306548357
2023-01-22 15:02:39.648654: step: 24/530, loss: 0.0333375446498394
2023-01-22 15:02:40.680440: step: 28/530, loss: 0.007256587501615286
2023-01-22 15:02:41.720827: step: 32/530, loss: 0.00467006815597415
2023-01-22 15:02:42.754547: step: 36/530, loss: 0.020394522696733475
2023-01-22 15:02:43.793320: step: 40/530, loss: 0.00021476308756973594
2023-01-22 15:02:44.843889: step: 44/530, loss: 0.003353406907990575
2023-01-22 15:02:45.887682: step: 48/530, loss: 0.005317258648574352
2023-01-22 15:02:46.921445: step: 52/530, loss: 0.00396682508289814
2023-01-22 15:02:47.968742: step: 56/530, loss: 0.0380081981420517
2023-01-22 15:02:49.013868: step: 60/530, loss: 0.011497588828206062
2023-01-22 15:02:50.066177: step: 64/530, loss: 0.07676336914300919
2023-01-22 15:02:51.115020: step: 68/530, loss: 0.002930128015577793
2023-01-22 15:02:52.154726: step: 72/530, loss: 0.0007320598815567791
2023-01-22 15:02:53.186936: step: 76/530, loss: 0.002627731766551733
2023-01-22 15:02:54.236897: step: 80/530, loss: 0.009351525455713272
2023-01-22 15:02:55.283728: step: 84/530, loss: 0.05400629714131355
2023-01-22 15:02:56.346169: step: 88/530, loss: 0.006733783986419439
2023-01-22 15:02:57.396170: step: 92/530, loss: 0.00025184068363159895
2023-01-22 15:02:58.446906: step: 96/530, loss: 0.003704732283949852
2023-01-22 15:02:59.493960: step: 100/530, loss: 0.012821323238313198
2023-01-22 15:03:00.543420: step: 104/530, loss: 0.021979887038469315
2023-01-22 15:03:01.592788: step: 108/530, loss: 0.1744893342256546
2023-01-22 15:03:02.627532: step: 112/530, loss: 0.010326141491532326
2023-01-22 15:03:03.668958: step: 116/530, loss: 0.001342359697446227
2023-01-22 15:03:04.711485: step: 120/530, loss: 0.00981202907860279
2023-01-22 15:03:05.745067: step: 124/530, loss: 0.009443918243050575
2023-01-22 15:03:06.796167: step: 128/530, loss: 0.004539586137980223
2023-01-22 15:03:07.838931: step: 132/530, loss: 0.003658464876934886
2023-01-22 15:03:08.873155: step: 136/530, loss: 0.012751545757055283
2023-01-22 15:03:09.934638: step: 140/530, loss: 0.01059018261730671
2023-01-22 15:03:10.994868: step: 144/530, loss: 0.008634681813418865
2023-01-22 15:03:12.021570: step: 148/530, loss: 0.004486961755901575
2023-01-22 15:03:13.068015: step: 152/530, loss: 0.0006435240502469242
2023-01-22 15:03:14.104784: step: 156/530, loss: 0.005888973828405142
2023-01-22 15:03:15.133342: step: 160/530, loss: 0.009699084796011448
2023-01-22 15:03:16.205020: step: 164/530, loss: 0.007755785249173641
2023-01-22 15:03:17.248513: step: 168/530, loss: 0.0071268281899392605
2023-01-22 15:03:18.295000: step: 172/530, loss: 0.024319598451256752
2023-01-22 15:03:19.341826: step: 176/530, loss: 0.01250580232590437
2023-01-22 15:03:20.396445: step: 180/530, loss: 0.010109507478773594
2023-01-22 15:03:21.445166: step: 184/530, loss: 0.009292527101933956
2023-01-22 15:03:22.479943: step: 188/530, loss: 0.007427418604493141
2023-01-22 15:03:23.512012: step: 192/530, loss: 0.0013856547884643078
2023-01-22 15:03:24.567216: step: 196/530, loss: 0.018948283046483994
2023-01-22 15:03:25.604749: step: 200/530, loss: 0.01557439286261797
2023-01-22 15:03:26.636240: step: 204/530, loss: 0.007975871674716473
2023-01-22 15:03:27.683612: step: 208/530, loss: 0.004301536828279495
2023-01-22 15:03:28.724753: step: 212/530, loss: 0.009251746349036694
2023-01-22 15:03:29.759180: step: 216/530, loss: 0.0
2023-01-22 15:03:30.826561: step: 220/530, loss: 0.0011706381337717175
2023-01-22 15:03:31.866796: step: 224/530, loss: 0.009251845069229603
2023-01-22 15:03:32.938570: step: 228/530, loss: 0.038894303143024445
2023-01-22 15:03:33.969394: step: 232/530, loss: 0.00913916900753975
2023-01-22 15:03:35.005676: step: 236/530, loss: 0.001993473619222641
2023-01-22 15:03:36.053739: step: 240/530, loss: 0.025272438302636147
2023-01-22 15:03:37.092398: step: 244/530, loss: 0.012085416354238987
2023-01-22 15:03:38.134597: step: 248/530, loss: 0.07184196263551712
2023-01-22 15:03:39.181282: step: 252/530, loss: 0.00636153481900692
2023-01-22 15:03:40.228681: step: 256/530, loss: 0.013592966832220554
2023-01-22 15:03:41.291161: step: 260/530, loss: 0.0817423090338707
2023-01-22 15:03:42.372999: step: 264/530, loss: 0.0049986811354756355
2023-01-22 15:03:43.439687: step: 268/530, loss: 0.0133290383964777
2023-01-22 15:03:44.479366: step: 272/530, loss: 0.010724496096372604
2023-01-22 15:03:45.535560: step: 276/530, loss: 0.006141698453575373
2023-01-22 15:03:46.591728: step: 280/530, loss: 0.02279144525527954
2023-01-22 15:03:47.651811: step: 284/530, loss: 0.02106567658483982
2023-01-22 15:03:48.715034: step: 288/530, loss: 0.0033782399259507656
2023-01-22 15:03:49.773142: step: 292/530, loss: 0.002073576208204031
2023-01-22 15:03:50.829976: step: 296/530, loss: 0.017554903402924538
2023-01-22 15:03:51.889788: step: 300/530, loss: 0.002421154174953699
2023-01-22 15:03:52.931321: step: 304/530, loss: 0.008731690235435963
2023-01-22 15:03:53.994932: step: 308/530, loss: 0.005585075821727514
2023-01-22 15:03:55.061934: step: 312/530, loss: 0.007909399457275867
2023-01-22 15:03:56.109440: step: 316/530, loss: 0.01444508507847786
2023-01-22 15:03:57.149963: step: 320/530, loss: 0.0014222756726667285
2023-01-22 15:03:58.185706: step: 324/530, loss: 0.0058175381273031235
2023-01-22 15:03:59.261618: step: 328/530, loss: 0.008278501220047474
2023-01-22 15:04:00.297549: step: 332/530, loss: 0.006105876062065363
2023-01-22 15:04:01.342319: step: 336/530, loss: 0.014510361477732658
2023-01-22 15:04:02.431205: step: 340/530, loss: 0.009033264592289925
2023-01-22 15:04:03.494960: step: 344/530, loss: 0.016659408807754517
2023-01-22 15:04:04.549155: step: 348/530, loss: 0.014676532708108425
2023-01-22 15:04:05.593875: step: 352/530, loss: 0.01533645112067461
2023-01-22 15:04:06.643252: step: 356/530, loss: 0.005074299406260252
2023-01-22 15:04:07.699391: step: 360/530, loss: 0.008287280797958374
2023-01-22 15:04:08.756999: step: 364/530, loss: 0.007156094536185265
2023-01-22 15:04:09.800444: step: 368/530, loss: 0.0060427263379096985
2023-01-22 15:04:10.854620: step: 372/530, loss: 0.00333373062312603
2023-01-22 15:04:11.896292: step: 376/530, loss: 0.03617725521326065
2023-01-22 15:04:12.959332: step: 380/530, loss: 0.06736189126968384
2023-01-22 15:04:14.013074: step: 384/530, loss: 0.01101057231426239
2023-01-22 15:04:15.070631: step: 388/530, loss: 0.005865860264748335
2023-01-22 15:04:16.140192: step: 392/530, loss: 0.019206885248422623
2023-01-22 15:04:17.191919: step: 396/530, loss: 0.027501532807946205
2023-01-22 15:04:18.233652: step: 400/530, loss: 0.004797319415956736
2023-01-22 15:04:19.281982: step: 404/530, loss: 0.027632728219032288
2023-01-22 15:04:20.333912: step: 408/530, loss: 0.005168435163795948
2023-01-22 15:04:21.366920: step: 412/530, loss: 0.0024470994248986244
2023-01-22 15:04:22.432673: step: 416/530, loss: 0.008314166218042374
2023-01-22 15:04:23.482940: step: 420/530, loss: 0.011156322434544563
2023-01-22 15:04:24.527952: step: 424/530, loss: 0.00198349473066628
2023-01-22 15:04:25.589787: step: 428/530, loss: 0.013873168267309666
2023-01-22 15:04:26.642573: step: 432/530, loss: 0.002291059121489525
2023-01-22 15:04:27.700622: step: 436/530, loss: 0.0072277989238500595
2023-01-22 15:04:28.756194: step: 440/530, loss: 0.004856232553720474
2023-01-22 15:04:29.808879: step: 444/530, loss: 0.005774457938969135
2023-01-22 15:04:30.869418: step: 448/530, loss: 0.006547051481902599
2023-01-22 15:04:31.922228: step: 452/530, loss: 0.01283668540418148
2023-01-22 15:04:32.993654: step: 456/530, loss: 0.02289484441280365
2023-01-22 15:04:34.048924: step: 460/530, loss: 0.014524105936288834
2023-01-22 15:04:35.092816: step: 464/530, loss: 0.01727128215134144
2023-01-22 15:04:36.157347: step: 468/530, loss: 0.007598747964948416
2023-01-22 15:04:37.207607: step: 472/530, loss: 0.043174732476472855
2023-01-22 15:04:38.259639: step: 476/530, loss: 0.018201831728219986
2023-01-22 15:04:39.321535: step: 480/530, loss: 0.007098087575286627
2023-01-22 15:04:40.364657: step: 484/530, loss: 0.004643871448934078
2023-01-22 15:04:41.421740: step: 488/530, loss: 0.022589458152651787
2023-01-22 15:04:42.461893: step: 492/530, loss: 0.01867409609258175
2023-01-22 15:04:43.508680: step: 496/530, loss: 0.003510940819978714
2023-01-22 15:04:44.554899: step: 500/530, loss: 0.0043696747161448
2023-01-22 15:04:45.605464: step: 504/530, loss: 0.007139483001083136
2023-01-22 15:04:46.683765: step: 508/530, loss: 0.006248056888580322
2023-01-22 15:04:47.733508: step: 512/530, loss: 0.006899184547364712
2023-01-22 15:04:48.782654: step: 516/530, loss: 0.008954247459769249
2023-01-22 15:04:49.835532: step: 520/530, loss: 0.03826233372092247
2023-01-22 15:04:50.877918: step: 524/530, loss: 0.004296408034861088
2023-01-22 15:04:51.915625: step: 528/530, loss: 0.026388704776763916
2023-01-22 15:04:52.959884: step: 532/530, loss: 0.007237255573272705
2023-01-22 15:04:54.016507: step: 536/530, loss: 0.012714683078229427
2023-01-22 15:04:55.074679: step: 540/530, loss: 0.009270096197724342
2023-01-22 15:04:56.138896: step: 544/530, loss: 0.010957039892673492
2023-01-22 15:04:57.201414: step: 548/530, loss: 0.046413011848926544
2023-01-22 15:04:58.244311: step: 552/530, loss: 0.0012702905805781484
2023-01-22 15:04:59.307638: step: 556/530, loss: 0.01454729214310646
2023-01-22 15:05:00.356415: step: 560/530, loss: 0.0012946755159646273
2023-01-22 15:05:01.404451: step: 564/530, loss: 0.004580217879265547
2023-01-22 15:05:02.445866: step: 568/530, loss: 0.007749276235699654
2023-01-22 15:05:03.487468: step: 572/530, loss: 0.0048573557287454605
2023-01-22 15:05:04.534336: step: 576/530, loss: 0.00838461983948946
2023-01-22 15:05:05.562115: step: 580/530, loss: 4.731139415525831e-05
2023-01-22 15:05:06.605010: step: 584/530, loss: 0.008801799267530441
2023-01-22 15:05:07.651990: step: 588/530, loss: 0.005033318884670734
2023-01-22 15:05:08.693247: step: 592/530, loss: 0.006699038669466972
2023-01-22 15:05:09.738614: step: 596/530, loss: 0.010545856319367886
2023-01-22 15:05:10.789045: step: 600/530, loss: 0.009249220602214336
2023-01-22 15:05:11.829223: step: 604/530, loss: 0.005822946783155203
2023-01-22 15:05:12.862896: step: 608/530, loss: 0.004310784861445427
2023-01-22 15:05:13.912411: step: 612/530, loss: 1.7877981008496135e-05
2023-01-22 15:05:14.954470: step: 616/530, loss: 0.0038097696378827095
2023-01-22 15:05:16.013071: step: 620/530, loss: 0.005796156357973814
2023-01-22 15:05:17.079351: step: 624/530, loss: 0.006661856546998024
2023-01-22 15:05:18.153346: step: 628/530, loss: 0.0018134411657229066
2023-01-22 15:05:19.210142: step: 632/530, loss: 0.004046429414302111
2023-01-22 15:05:20.246984: step: 636/530, loss: 0.021363284438848495
2023-01-22 15:05:21.307756: step: 640/530, loss: 0.011556833051145077
2023-01-22 15:05:22.369007: step: 644/530, loss: 0.012669372372329235
2023-01-22 15:05:23.431797: step: 648/530, loss: 0.01908951997756958
2023-01-22 15:05:24.467089: step: 652/530, loss: 0.003526262938976288
2023-01-22 15:05:25.516479: step: 656/530, loss: 0.009629894979298115
2023-01-22 15:05:26.553208: step: 660/530, loss: 0.0016331829829141498
2023-01-22 15:05:27.604644: step: 664/530, loss: 0.01964084431529045
2023-01-22 15:05:28.645988: step: 668/530, loss: 0.004161123652011156
2023-01-22 15:05:29.685158: step: 672/530, loss: 0.011294153518974781
2023-01-22 15:05:30.725368: step: 676/530, loss: 0.0018205394735559821
2023-01-22 15:05:31.764387: step: 680/530, loss: 0.007117633707821369
2023-01-22 15:05:32.828080: step: 684/530, loss: 0.010359746403992176
2023-01-22 15:05:33.870105: step: 688/530, loss: 0.006559242028743029
2023-01-22 15:05:34.908315: step: 692/530, loss: 0.00043034047121182084
2023-01-22 15:05:35.966331: step: 696/530, loss: 0.0070377835072577
2023-01-22 15:05:37.013761: step: 700/530, loss: 0.003006778424605727
2023-01-22 15:05:38.072700: step: 704/530, loss: 0.021097030490636826
2023-01-22 15:05:39.120297: step: 708/530, loss: 0.005191988777369261
2023-01-22 15:05:40.162387: step: 712/530, loss: 0.005960002541542053
2023-01-22 15:05:41.203369: step: 716/530, loss: 0.006902558263391256
2023-01-22 15:05:42.260979: step: 720/530, loss: 0.010176354087889194
2023-01-22 15:05:43.295295: step: 724/530, loss: 0.002411438850685954
2023-01-22 15:05:44.360701: step: 728/530, loss: 0.004508199170231819
2023-01-22 15:05:45.399549: step: 732/530, loss: 0.006601941771805286
2023-01-22 15:05:46.458024: step: 736/530, loss: 0.006622927263379097
2023-01-22 15:05:47.522620: step: 740/530, loss: 0.01019946951419115
2023-01-22 15:05:48.551896: step: 744/530, loss: 0.001228116569109261
2023-01-22 15:05:49.610799: step: 748/530, loss: 0.00554271275177598
2023-01-22 15:05:50.650607: step: 752/530, loss: 0.006356098689138889
2023-01-22 15:05:51.694877: step: 756/530, loss: 0.009608251973986626
2023-01-22 15:05:52.734958: step: 760/530, loss: 0.009014172479510307
2023-01-22 15:05:53.766015: step: 764/530, loss: 0.005637074820697308
2023-01-22 15:05:54.802391: step: 768/530, loss: 0.014369937591254711
2023-01-22 15:05:55.844707: step: 772/530, loss: 0.008542876690626144
2023-01-22 15:05:56.902496: step: 776/530, loss: 0.009192418307065964
2023-01-22 15:05:57.940660: step: 780/530, loss: 0.0009707133867777884
2023-01-22 15:05:58.983894: step: 784/530, loss: 0.005935297347605228
2023-01-22 15:06:00.053509: step: 788/530, loss: 0.013970510102808475
2023-01-22 15:06:01.110120: step: 792/530, loss: 0.024999402463436127
2023-01-22 15:06:02.156547: step: 796/530, loss: 0.004415830131620169
2023-01-22 15:06:03.209076: step: 800/530, loss: 0.01320775505155325
2023-01-22 15:06:04.260226: step: 804/530, loss: 0.00629342021420598
2023-01-22 15:06:05.319939: step: 808/530, loss: 0.00999950710684061
2023-01-22 15:06:06.378395: step: 812/530, loss: 0.010659722611308098
2023-01-22 15:06:07.422889: step: 816/530, loss: 0.008501281030476093
2023-01-22 15:06:08.467882: step: 820/530, loss: 0.0007197453523986042
2023-01-22 15:06:09.530046: step: 824/530, loss: 0.01655275747179985
2023-01-22 15:06:10.559188: step: 828/530, loss: 5.6251541536767036e-05
2023-01-22 15:06:11.620407: step: 832/530, loss: 0.0009268919238820672
2023-01-22 15:06:12.682317: step: 836/530, loss: 0.004103783052414656
2023-01-22 15:06:13.727680: step: 840/530, loss: 0.004988683853298426
2023-01-22 15:06:14.763038: step: 844/530, loss: 0.012605680152773857
2023-01-22 15:06:15.807362: step: 848/530, loss: 0.006974476855248213
2023-01-22 15:06:16.858011: step: 852/530, loss: 0.005091514904052019
2023-01-22 15:06:17.918599: step: 856/530, loss: 0.0014694997807964683
2023-01-22 15:06:18.976583: step: 860/530, loss: 0.0010220871772617102
2023-01-22 15:06:20.046515: step: 864/530, loss: 0.001836717943660915
2023-01-22 15:06:21.112323: step: 868/530, loss: 0.005687267053872347
2023-01-22 15:06:22.164246: step: 872/530, loss: 0.004915875382721424
2023-01-22 15:06:23.214722: step: 876/530, loss: 0.019141381606459618
2023-01-22 15:06:24.253173: step: 880/530, loss: 1.2647478797589429e-05
2023-01-22 15:06:25.292141: step: 884/530, loss: 0.022044172510504723
2023-01-22 15:06:26.338379: step: 888/530, loss: 0.010193722322583199
2023-01-22 15:06:27.395748: step: 892/530, loss: 0.00859873741865158
2023-01-22 15:06:28.427724: step: 896/530, loss: 0.02680361270904541
2023-01-22 15:06:29.460851: step: 900/530, loss: 0.0014909657184034586
2023-01-22 15:06:30.503125: step: 904/530, loss: 0.017367621883749962
2023-01-22 15:06:31.551822: step: 908/530, loss: 0.005413647275418043
2023-01-22 15:06:32.612068: step: 912/530, loss: 0.01309147384017706
2023-01-22 15:06:33.693885: step: 916/530, loss: 0.010298328474164009
2023-01-22 15:06:34.736972: step: 920/530, loss: 0.0014911723555997014
2023-01-22 15:06:35.771625: step: 924/530, loss: 0.00562900910153985
2023-01-22 15:06:36.826658: step: 928/530, loss: 0.00012551721010822803
2023-01-22 15:06:37.863948: step: 932/530, loss: 0.016936399042606354
2023-01-22 15:06:38.919772: step: 936/530, loss: 0.017997879534959793
2023-01-22 15:06:39.969976: step: 940/530, loss: 0.011630039662122726
2023-01-22 15:06:41.011193: step: 944/530, loss: 0.004711678251624107
2023-01-22 15:06:42.075734: step: 948/530, loss: 0.008336941711604595
2023-01-22 15:06:43.128129: step: 952/530, loss: 0.02768378145992756
2023-01-22 15:06:44.168719: step: 956/530, loss: 0.016323048621416092
2023-01-22 15:06:45.220884: step: 960/530, loss: 0.014767490327358246
2023-01-22 15:06:46.261888: step: 964/530, loss: 0.017576850950717926
2023-01-22 15:06:47.326396: step: 968/530, loss: 0.0017638560384511948
2023-01-22 15:06:48.392282: step: 972/530, loss: 0.03149247169494629
2023-01-22 15:06:49.441168: step: 976/530, loss: 0.08389350771903992
2023-01-22 15:06:50.522416: step: 980/530, loss: 0.012167435139417648
2023-01-22 15:06:51.558034: step: 984/530, loss: 0.01404179260134697
2023-01-22 15:06:52.602440: step: 988/530, loss: 0.003598138689994812
2023-01-22 15:06:53.644578: step: 992/530, loss: 0.007787288166582584
2023-01-22 15:06:54.691235: step: 996/530, loss: 0.04942134767770767
2023-01-22 15:06:55.754864: step: 1000/530, loss: 0.037217091768980026
2023-01-22 15:06:56.813522: step: 1004/530, loss: 0.00025469358661212027
2023-01-22 15:06:57.869181: step: 1008/530, loss: 0.011966563761234283
2023-01-22 15:06:58.926711: step: 1012/530, loss: 0.0011575728422030807
2023-01-22 15:06:59.969873: step: 1016/530, loss: 0.04056147113442421
2023-01-22 15:07:01.029093: step: 1020/530, loss: 0.0110407043248415
2023-01-22 15:07:02.064547: step: 1024/530, loss: 0.01687813177704811
2023-01-22 15:07:03.155398: step: 1028/530, loss: 0.028553498908877373
2023-01-22 15:07:04.216228: step: 1032/530, loss: 0.008772153407335281
2023-01-22 15:07:05.278768: step: 1036/530, loss: 0.02754429168999195
2023-01-22 15:07:06.323883: step: 1040/530, loss: 0.012440082617104053
2023-01-22 15:07:07.376797: step: 1044/530, loss: 0.013174206018447876
2023-01-22 15:07:08.422167: step: 1048/530, loss: 0.01911246031522751
2023-01-22 15:07:09.475903: step: 1052/530, loss: 0.0011527083115652204
2023-01-22 15:07:10.525494: step: 1056/530, loss: 0.016724998131394386
2023-01-22 15:07:11.577565: step: 1060/530, loss: 0.005059492774307728
2023-01-22 15:07:12.619055: step: 1064/530, loss: 0.005888041108846664
2023-01-22 15:07:13.659869: step: 1068/530, loss: 0.011758263222873211
2023-01-22 15:07:14.710678: step: 1072/530, loss: 6.988779932726175e-05
2023-01-22 15:07:15.745389: step: 1076/530, loss: 0.012905214913189411
2023-01-22 15:07:16.796469: step: 1080/530, loss: 0.004845108836889267
2023-01-22 15:07:17.846561: step: 1084/530, loss: 0.002205712255090475
2023-01-22 15:07:18.879431: step: 1088/530, loss: 0.0022706834133714437
2023-01-22 15:07:19.921527: step: 1092/530, loss: 0.015068558044731617
2023-01-22 15:07:20.957405: step: 1096/530, loss: 0.054232239723205566
2023-01-22 15:07:22.015480: step: 1100/530, loss: 0.004397891461849213
2023-01-22 15:07:23.074024: step: 1104/530, loss: 0.008655865676701069
2023-01-22 15:07:24.109949: step: 1108/530, loss: 0.004208332393318415
2023-01-22 15:07:25.155248: step: 1112/530, loss: 0.04608648642897606
2023-01-22 15:07:26.183328: step: 1116/530, loss: 0.006368137430399656
2023-01-22 15:07:27.237073: step: 1120/530, loss: 0.0024866051971912384
2023-01-22 15:07:28.291612: step: 1124/530, loss: 0.010059923864901066
2023-01-22 15:07:29.331682: step: 1128/530, loss: 0.017094725742936134
2023-01-22 15:07:30.371529: step: 1132/530, loss: 0.009986259043216705
2023-01-22 15:07:31.402101: step: 1136/530, loss: 0.01738540641963482
2023-01-22 15:07:32.442696: step: 1140/530, loss: 0.014111127704381943
2023-01-22 15:07:33.493619: step: 1144/530, loss: 0.007241981569677591
2023-01-22 15:07:34.524656: step: 1148/530, loss: 0.04822762683033943
2023-01-22 15:07:35.568977: step: 1152/530, loss: 0.006277620326727629
2023-01-22 15:07:36.621214: step: 1156/530, loss: 0.0023210307117551565
2023-01-22 15:07:37.694812: step: 1160/530, loss: 0.04634594917297363
2023-01-22 15:07:38.729450: step: 1164/530, loss: 0.005923795979470015
2023-01-22 15:07:39.771892: step: 1168/530, loss: 0.011370973661541939
2023-01-22 15:07:40.823983: step: 1172/530, loss: 0.02970983274281025
2023-01-22 15:07:41.862440: step: 1176/530, loss: 0.0075255706906318665
2023-01-22 15:07:42.908455: step: 1180/530, loss: 0.0018460537539795041
2023-01-22 15:07:43.938502: step: 1184/530, loss: 0.003375509986653924
2023-01-22 15:07:45.012701: step: 1188/530, loss: 0.002060431521385908
2023-01-22 15:07:46.041018: step: 1192/530, loss: 0.004417150281369686
2023-01-22 15:07:47.085022: step: 1196/530, loss: 0.010483695194125175
2023-01-22 15:07:48.123523: step: 1200/530, loss: 0.014702011831104755
2023-01-22 15:07:49.181693: step: 1204/530, loss: 0.003159887855872512
2023-01-22 15:07:50.240384: step: 1208/530, loss: 0.008196812123060226
2023-01-22 15:07:51.272814: step: 1212/530, loss: 0.006565215531736612
2023-01-22 15:07:52.316886: step: 1216/530, loss: 0.01153595745563507
2023-01-22 15:07:53.370897: step: 1220/530, loss: 0.0017138427356258035
2023-01-22 15:07:54.402261: step: 1224/530, loss: 0.008832437917590141
2023-01-22 15:07:55.443756: step: 1228/530, loss: 0.0037844006437808275
2023-01-22 15:07:56.485355: step: 1232/530, loss: 0.016488144174218178
2023-01-22 15:07:57.562115: step: 1236/530, loss: 0.028776640072464943
2023-01-22 15:07:58.616491: step: 1240/530, loss: 0.004934842698276043
2023-01-22 15:07:59.636256: step: 1244/530, loss: 0.0015925107290968299
2023-01-22 15:08:00.685223: step: 1248/530, loss: 0.0024560329038649797
2023-01-22 15:08:01.738167: step: 1252/530, loss: 0.006669624708592892
2023-01-22 15:08:02.786755: step: 1256/530, loss: 0.002642344683408737
2023-01-22 15:08:03.870077: step: 1260/530, loss: 0.012166638858616352
2023-01-22 15:08:04.910860: step: 1264/530, loss: 0.002556038787588477
2023-01-22 15:08:05.967685: step: 1268/530, loss: 0.0019084386294707656
2023-01-22 15:08:07.005009: step: 1272/530, loss: 0.02241872251033783
2023-01-22 15:08:08.059064: step: 1276/530, loss: 0.005768246483057737
2023-01-22 15:08:09.107810: step: 1280/530, loss: 0.00721336342394352
2023-01-22 15:08:10.148346: step: 1284/530, loss: 0.0032619929406791925
2023-01-22 15:08:11.188682: step: 1288/530, loss: 0.002321878680959344
2023-01-22 15:08:12.228347: step: 1292/530, loss: 0.0
2023-01-22 15:08:13.295364: step: 1296/530, loss: 0.003975667990744114
2023-01-22 15:08:14.353239: step: 1300/530, loss: 0.0027384948916733265
2023-01-22 15:08:15.408368: step: 1304/530, loss: 0.009381299838423729
2023-01-22 15:08:16.459659: step: 1308/530, loss: 0.00651626056060195
2023-01-22 15:08:17.498873: step: 1312/530, loss: 0.01557151135057211
2023-01-22 15:08:18.548230: step: 1316/530, loss: 0.03151615336537361
2023-01-22 15:08:19.586662: step: 1320/530, loss: 0.004775182344019413
2023-01-22 15:08:20.634704: step: 1324/530, loss: 0.0051331715658307076
2023-01-22 15:08:21.693039: step: 1328/530, loss: 0.015781784430146217
2023-01-22 15:08:22.724491: step: 1332/530, loss: 0.006004722323268652
2023-01-22 15:08:23.772916: step: 1336/530, loss: 0.012165858410298824
2023-01-22 15:08:24.812567: step: 1340/530, loss: 0.0021781730465590954
2023-01-22 15:08:25.875943: step: 1344/530, loss: 0.017394790425896645
2023-01-22 15:08:26.918300: step: 1348/530, loss: 0.004634325858205557
2023-01-22 15:08:27.976780: step: 1352/530, loss: 0.004140722565352917
2023-01-22 15:08:29.040163: step: 1356/530, loss: 0.007242133375257254
2023-01-22 15:08:30.079315: step: 1360/530, loss: 0.0038441636133939028
2023-01-22 15:08:31.121647: step: 1364/530, loss: 0.00365601503290236
2023-01-22 15:08:32.148380: step: 1368/530, loss: 0.008653477765619755
2023-01-22 15:08:33.231728: step: 1372/530, loss: 0.06473550200462341
2023-01-22 15:08:34.284686: step: 1376/530, loss: 0.012365452945232391
2023-01-22 15:08:35.340639: step: 1380/530, loss: 0.01687469333410263
2023-01-22 15:08:36.385178: step: 1384/530, loss: 0.013735839165747166
2023-01-22 15:08:37.420049: step: 1388/530, loss: 0.002074249554425478
2023-01-22 15:08:38.467337: step: 1392/530, loss: 0.0066183325834572315
2023-01-22 15:08:39.515759: step: 1396/530, loss: 0.003992049489170313
2023-01-22 15:08:40.572850: step: 1400/530, loss: 0.01779647171497345
2023-01-22 15:08:41.628350: step: 1404/530, loss: 0.005528097972273827
2023-01-22 15:08:42.710629: step: 1408/530, loss: 0.007138720713555813
2023-01-22 15:08:43.762745: step: 1412/530, loss: 0.011370713822543621
2023-01-22 15:08:44.814640: step: 1416/530, loss: 0.013343335129320621
2023-01-22 15:08:45.866107: step: 1420/530, loss: 0.003445129841566086
2023-01-22 15:08:46.909030: step: 1424/530, loss: 0.03647959977388382
2023-01-22 15:08:47.969034: step: 1428/530, loss: 0.0046344357542693615
2023-01-22 15:08:49.010860: step: 1432/530, loss: 0.012319570407271385
2023-01-22 15:08:50.053260: step: 1436/530, loss: 0.006243827287107706
2023-01-22 15:08:51.101849: step: 1440/530, loss: 0.014569567516446114
2023-01-22 15:08:52.154019: step: 1444/530, loss: 0.038104668259620667
2023-01-22 15:08:53.184766: step: 1448/530, loss: 0.0027446846943348646
2023-01-22 15:08:54.230294: step: 1452/530, loss: 0.037536486983299255
2023-01-22 15:08:55.276866: step: 1456/530, loss: 0.0038887758273631334
2023-01-22 15:08:56.312244: step: 1460/530, loss: 0.005944808013737202
2023-01-22 15:08:57.357219: step: 1464/530, loss: 0.006518770940601826
2023-01-22 15:08:58.402426: step: 1468/530, loss: 0.006378414575010538
2023-01-22 15:08:59.449105: step: 1472/530, loss: 0.00516114104539156
2023-01-22 15:09:00.487404: step: 1476/530, loss: 0.00238236621953547
2023-01-22 15:09:01.531408: step: 1480/530, loss: 0.007914666086435318
2023-01-22 15:09:02.598079: step: 1484/530, loss: 0.021690787747502327
2023-01-22 15:09:03.647178: step: 1488/530, loss: 0.03436211124062538
2023-01-22 15:09:04.693655: step: 1492/530, loss: 0.00542786531150341
2023-01-22 15:09:05.751848: step: 1496/530, loss: 0.0016266766469925642
2023-01-22 15:09:06.797050: step: 1500/530, loss: 0.004417261108756065
2023-01-22 15:09:07.857148: step: 1504/530, loss: 0.010348916985094547
2023-01-22 15:09:08.899801: step: 1508/530, loss: 0.0024823001585900784
2023-01-22 15:09:09.930511: step: 1512/530, loss: 0.0027275504544377327
2023-01-22 15:09:10.973628: step: 1516/530, loss: 0.024256065487861633
2023-01-22 15:09:12.020158: step: 1520/530, loss: 0.006303762551397085
2023-01-22 15:09:13.070594: step: 1524/530, loss: 0.0005122361471876502
2023-01-22 15:09:14.112905: step: 1528/530, loss: 0.005714477971196175
2023-01-22 15:09:15.147274: step: 1532/530, loss: 0.0032499264925718307
2023-01-22 15:09:16.198743: step: 1536/530, loss: 0.0031902496702969074
2023-01-22 15:09:17.240737: step: 1540/530, loss: 0.006088098045438528
2023-01-22 15:09:18.285309: step: 1544/530, loss: 0.041882455348968506
2023-01-22 15:09:19.335639: step: 1548/530, loss: 0.012648779898881912
2023-01-22 15:09:20.366901: step: 1552/530, loss: 0.0029303147457540035
2023-01-22 15:09:21.403299: step: 1556/530, loss: 0.0025913789868354797
2023-01-22 15:09:22.448162: step: 1560/530, loss: 0.010696973651647568
2023-01-22 15:09:23.493627: step: 1564/530, loss: 0.013189993798732758
2023-01-22 15:09:24.548950: step: 1568/530, loss: 0.003158735577017069
2023-01-22 15:09:25.592916: step: 1572/530, loss: 0.010850224643945694
2023-01-22 15:09:26.637680: step: 1576/530, loss: 0.0022604234982281923
2023-01-22 15:09:27.680944: step: 1580/530, loss: 0.01447734422981739
2023-01-22 15:09:28.719681: step: 1584/530, loss: 0.002383883111178875
2023-01-22 15:09:29.779249: step: 1588/530, loss: 0.005349942948669195
2023-01-22 15:09:30.845060: step: 1592/530, loss: 0.010400950908660889
2023-01-22 15:09:31.918361: step: 1596/530, loss: 0.009962107054889202
2023-01-22 15:09:32.949160: step: 1600/530, loss: 0.0005176945705898106
2023-01-22 15:09:33.997075: step: 1604/530, loss: 0.003487328765913844
2023-01-22 15:09:35.042483: step: 1608/530, loss: 0.01664735935628414
2023-01-22 15:09:36.077364: step: 1612/530, loss: 0.00046591219143010676
2023-01-22 15:09:37.152727: step: 1616/530, loss: 0.022153649479150772
2023-01-22 15:09:38.196528: step: 1620/530, loss: 0.001370233716443181
2023-01-22 15:09:39.246668: step: 1624/530, loss: 0.013568615540862083
2023-01-22 15:09:40.311457: step: 1628/530, loss: 0.010257410816848278
2023-01-22 15:09:41.356474: step: 1632/530, loss: 0.0013606279389932752
2023-01-22 15:09:42.408102: step: 1636/530, loss: 0.010526888072490692
2023-01-22 15:09:43.468706: step: 1640/530, loss: 0.0003021125157829374
2023-01-22 15:09:44.523187: step: 1644/530, loss: 0.03822477161884308
2023-01-22 15:09:45.564580: step: 1648/530, loss: 0.0069490112364292145
2023-01-22 15:09:46.599302: step: 1652/530, loss: 0.008463256992399693
2023-01-22 15:09:47.663542: step: 1656/530, loss: 0.002760227071121335
2023-01-22 15:09:48.693801: step: 1660/530, loss: 0.003952574450522661
2023-01-22 15:09:49.747586: step: 1664/530, loss: 0.019917337223887444
2023-01-22 15:09:50.789270: step: 1668/530, loss: 0.0009388299658894539
2023-01-22 15:09:51.847614: step: 1672/530, loss: 0.0026818157639354467
2023-01-22 15:09:52.899587: step: 1676/530, loss: 0.0008446202846243978
2023-01-22 15:09:53.946113: step: 1680/530, loss: 0.003061462426558137
2023-01-22 15:09:55.007818: step: 1684/530, loss: 0.01259323488920927
2023-01-22 15:09:56.063736: step: 1688/530, loss: 0.003192199394106865
2023-01-22 15:09:57.100348: step: 1692/530, loss: 0.0030326182022690773
2023-01-22 15:09:58.138806: step: 1696/530, loss: 0.0023902729153633118
2023-01-22 15:09:59.193735: step: 1700/530, loss: 0.010590974241495132
2023-01-22 15:10:00.255226: step: 1704/530, loss: 0.005997471511363983
2023-01-22 15:10:01.309978: step: 1708/530, loss: 0.0042737917974591255
2023-01-22 15:10:02.352448: step: 1712/530, loss: 0.0019460093462839723
2023-01-22 15:10:03.409403: step: 1716/530, loss: 0.009023701772093773
2023-01-22 15:10:04.442338: step: 1720/530, loss: 0.03829607367515564
2023-01-22 15:10:05.501025: step: 1724/530, loss: 0.001464914996176958
2023-01-22 15:10:06.547193: step: 1728/530, loss: 0.011218001134693623
2023-01-22 15:10:07.603752: step: 1732/530, loss: 0.006468515843153
2023-01-22 15:10:08.641185: step: 1736/530, loss: 0.05774828791618347
2023-01-22 15:10:09.687761: step: 1740/530, loss: 0.004463072866201401
2023-01-22 15:10:10.730164: step: 1744/530, loss: 0.004707530606538057
2023-01-22 15:10:11.777037: step: 1748/530, loss: 0.00423012301325798
2023-01-22 15:10:12.821977: step: 1752/530, loss: 0.0026463803369551897
2023-01-22 15:10:13.866659: step: 1756/530, loss: 0.0012509971857070923
2023-01-22 15:10:14.904692: step: 1760/530, loss: 0.03683941438794136
2023-01-22 15:10:15.958954: step: 1764/530, loss: 0.004583033733069897
2023-01-22 15:10:17.018696: step: 1768/530, loss: 0.001848480082117021
2023-01-22 15:10:18.066728: step: 1772/530, loss: 0.005092152394354343
2023-01-22 15:10:19.138533: step: 1776/530, loss: 0.010181999765336514
2023-01-22 15:10:20.178922: step: 1780/530, loss: 0.004218610934913158
2023-01-22 15:10:21.219397: step: 1784/530, loss: 0.0066188001073896885
2023-01-22 15:10:22.299607: step: 1788/530, loss: 0.006293498445302248
2023-01-22 15:10:23.362039: step: 1792/530, loss: 0.029996046796441078
2023-01-22 15:10:24.423954: step: 1796/530, loss: 0.006235219072550535
2023-01-22 15:10:25.454657: step: 1800/530, loss: 0.0007102636736817658
2023-01-22 15:10:26.518812: step: 1804/530, loss: 0.01009336393326521
2023-01-22 15:10:27.566632: step: 1808/530, loss: 0.019660072401165962
2023-01-22 15:10:28.605852: step: 1812/530, loss: 0.0034724606666713953
2023-01-22 15:10:29.671955: step: 1816/530, loss: 4.8215253627859056e-05
2023-01-22 15:10:30.707064: step: 1820/530, loss: 0.0020423235837370157
2023-01-22 15:10:31.775649: step: 1824/530, loss: 0.0020411359146237373
2023-01-22 15:10:32.838089: step: 1828/530, loss: 0.0008384475950151682
2023-01-22 15:10:33.889978: step: 1832/530, loss: 0.007453765720129013
2023-01-22 15:10:34.931492: step: 1836/530, loss: 0.005854646675288677
2023-01-22 15:10:35.989676: step: 1840/530, loss: 0.01420413888990879
2023-01-22 15:10:37.034513: step: 1844/530, loss: 0.005356969777494669
2023-01-22 15:10:38.077403: step: 1848/530, loss: 0.004413146525621414
2023-01-22 15:10:39.136073: step: 1852/530, loss: 0.0024649128317832947
2023-01-22 15:10:40.199471: step: 1856/530, loss: 0.01569589413702488
2023-01-22 15:10:41.245663: step: 1860/530, loss: 0.005170603282749653
2023-01-22 15:10:42.320674: step: 1864/530, loss: 0.015741726383566856
2023-01-22 15:10:43.381971: step: 1868/530, loss: 0.003222364466637373
2023-01-22 15:10:44.445380: step: 1872/530, loss: 0.004273899830877781
2023-01-22 15:10:45.500158: step: 1876/530, loss: 0.005244630854576826
2023-01-22 15:10:46.558733: step: 1880/530, loss: 0.005790162831544876
2023-01-22 15:10:47.611024: step: 1884/530, loss: 0.004424300044775009
2023-01-22 15:10:48.660064: step: 1888/530, loss: 0.0076529355719685555
2023-01-22 15:10:49.707115: step: 1892/530, loss: 0.004454405978322029
2023-01-22 15:10:50.765478: step: 1896/530, loss: 0.0012347509618848562
2023-01-22 15:10:51.847363: step: 1900/530, loss: 0.004442939534783363
2023-01-22 15:10:52.883855: step: 1904/530, loss: 0.007836198434233665
2023-01-22 15:10:53.919910: step: 1908/530, loss: 0.006599419750273228
2023-01-22 15:10:54.993283: step: 1912/530, loss: 0.005424900911748409
2023-01-22 15:10:56.058329: step: 1916/530, loss: 0.023368019610643387
2023-01-22 15:10:57.095497: step: 1920/530, loss: 0.0005079061957076192
2023-01-22 15:10:58.145014: step: 1924/530, loss: 0.002876706188544631
2023-01-22 15:10:59.189376: step: 1928/530, loss: 0.002839681226760149
2023-01-22 15:11:00.229612: step: 1932/530, loss: 0.002800461370497942
2023-01-22 15:11:01.282087: step: 1936/530, loss: 0.0345260426402092
2023-01-22 15:11:02.317626: step: 1940/530, loss: 0.0011219825828447938
2023-01-22 15:11:03.375446: step: 1944/530, loss: 0.03704563155770302
2023-01-22 15:11:04.428048: step: 1948/530, loss: 0.0020183371379971504
2023-01-22 15:11:05.494886: step: 1952/530, loss: 0.007695924025028944
2023-01-22 15:11:06.553003: step: 1956/530, loss: 0.00744060892611742
2023-01-22 15:11:07.601908: step: 1960/530, loss: 0.006299425847828388
2023-01-22 15:11:08.648454: step: 1964/530, loss: 0.009902258403599262
2023-01-22 15:11:09.714827: step: 1968/530, loss: 0.030299803242087364
2023-01-22 15:11:10.760500: step: 1972/530, loss: 0.021792281419038773
2023-01-22 15:11:11.807125: step: 1976/530, loss: 0.009079894982278347
2023-01-22 15:11:12.850092: step: 1980/530, loss: 0.016156412661075592
2023-01-22 15:11:13.904846: step: 1984/530, loss: 0.0008829004946164787
2023-01-22 15:11:14.944069: step: 1988/530, loss: 0.009219007566571236
2023-01-22 15:11:15.990349: step: 1992/530, loss: 0.004383533261716366
2023-01-22 15:11:17.040924: step: 1996/530, loss: 0.004133886191993952
2023-01-22 15:11:18.088607: step: 2000/530, loss: 0.012615744024515152
2023-01-22 15:11:19.132887: step: 2004/530, loss: 0.0044347625225782394
2023-01-22 15:11:20.180795: step: 2008/530, loss: 0.00016376172425225377
2023-01-22 15:11:21.233633: step: 2012/530, loss: 0.0031638555228710175
2023-01-22 15:11:22.282428: step: 2016/530, loss: 0.0008808086859062314
2023-01-22 15:11:23.327199: step: 2020/530, loss: 0.0026555319782346487
2023-01-22 15:11:24.363000: step: 2024/530, loss: 0.01694948598742485
2023-01-22 15:11:25.409314: step: 2028/530, loss: 0.0021222829818725586
2023-01-22 15:11:26.460960: step: 2032/530, loss: 0.042453326284885406
2023-01-22 15:11:27.506362: step: 2036/530, loss: 2.66447068497655e-06
2023-01-22 15:11:28.544425: step: 2040/530, loss: 0.008571631275117397
2023-01-22 15:11:29.568144: step: 2044/530, loss: 0.004397754091769457
2023-01-22 15:11:30.615506: step: 2048/530, loss: 0.001480049453675747
2023-01-22 15:11:31.655645: step: 2052/530, loss: 0.004592315759509802
2023-01-22 15:11:32.698698: step: 2056/530, loss: 0.013568039983510971
2023-01-22 15:11:33.748447: step: 2060/530, loss: 0.005409645847976208
2023-01-22 15:11:34.795564: step: 2064/530, loss: 0.01585240475833416
2023-01-22 15:11:35.848725: step: 2068/530, loss: 0.005477391183376312
2023-01-22 15:11:36.889148: step: 2072/530, loss: 0.008745000697672367
2023-01-22 15:11:37.923466: step: 2076/530, loss: 0.0028602932579815388
2023-01-22 15:11:38.972103: step: 2080/530, loss: 0.027682442218065262
2023-01-22 15:11:40.024879: step: 2084/530, loss: 0.0026634125970304012
2023-01-22 15:11:41.077578: step: 2088/530, loss: 0.0068257697857916355
2023-01-22 15:11:42.121206: step: 2092/530, loss: 0.12185706198215485
2023-01-22 15:11:43.175022: step: 2096/530, loss: 0.0046238708309829235
2023-01-22 15:11:44.230481: step: 2100/530, loss: 0.011242169886827469
2023-01-22 15:11:45.264164: step: 2104/530, loss: 0.038506343960762024
2023-01-22 15:11:46.338812: step: 2108/530, loss: 0.002894774777814746
2023-01-22 15:11:47.393585: step: 2112/530, loss: 0.0052803680300712585
2023-01-22 15:11:48.436653: step: 2116/530, loss: 0.005777029786258936
2023-01-22 15:11:49.463881: step: 2120/530, loss: 0.001339518348686397
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3423145325203252, 'r': 0.3195801707779886, 'f1': 0.33055691854759567}, 'combined': 0.24356825577191257, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3635677028750895, 'r': 0.40667453529318376, 'f1': 0.3839148758342594}, 'combined': 0.29757995160358863, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31547567872641563, 'r': 0.3178701810317395, 'f1': 0.31666840340969127}, 'combined': 0.23333461303871986, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3619799659506764, 'r': 0.4055639508215758, 'f1': 0.38253452838654056}, 'combined': 0.29651001721827547, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329372244049974, 'r': 0.33609602160049074, 'f1': 0.3345091659744261}, 'combined': 0.2464804380864192, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3633772445092006, 'r': 0.3854203494150896, 'f1': 0.37407434448137156}, 'combined': 0.2899523627080488, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 5}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3390625, 'r': 0.32683823529411765, 'f1': 0.3328381642512077}, 'combined': 0.24524917365878462, 'stategy': 1, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36247919934929645, 'r': 0.4101212264696543, 'f1': 0.38483130176712715}, 'combined': 0.29829029132188806, 'stategy': 1, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329372244049974, 'r': 0.33609602160049074, 'f1': 0.3345091659744261}, 'combined': 0.2464804380864192, 'stategy': 1, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3633772445092006, 'r': 0.3854203494150896, 'f1': 0.37407434448137156}, 'combined': 0.2899523627080488, 'stategy': 1, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 5}
******************************
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
2023-01-22 15:14:22.778715: step: 4/530, loss: 0.002410094253718853
2023-01-22 15:14:23.823870: step: 8/530, loss: 0.007437431253492832
2023-01-22 15:14:24.882926: step: 12/530, loss: 0.00877330731600523
2023-01-22 15:14:25.935971: step: 16/530, loss: 0.01219247281551361
2023-01-22 15:14:26.978023: step: 20/530, loss: 0.010418952442705631
2023-01-22 15:14:28.043748: step: 24/530, loss: 0.00411903066560626
2023-01-22 15:14:29.085005: step: 28/530, loss: 0.003494005184620619
2023-01-22 15:14:30.127777: step: 32/530, loss: 0.01221332885324955
2023-01-22 15:14:31.179668: step: 36/530, loss: 0.0071880570612847805
2023-01-22 15:14:32.225410: step: 40/530, loss: 0.015654858201742172
2023-01-22 15:14:33.290968: step: 44/530, loss: 0.01211537141352892
2023-01-22 15:14:34.332308: step: 48/530, loss: 0.003388779703527689
2023-01-22 15:14:35.385608: step: 52/530, loss: 0.006029969546943903
2023-01-22 15:14:36.423135: step: 56/530, loss: 0.00984850525856018
2023-01-22 15:14:37.452092: step: 60/530, loss: 0.0013922890648245811
2023-01-22 15:14:38.494269: step: 64/530, loss: 0.005875272210687399
2023-01-22 15:14:39.537585: step: 68/530, loss: 0.006032685283571482
2023-01-22 15:14:40.578997: step: 72/530, loss: 0.0074692657217383385
2023-01-22 15:14:41.615168: step: 76/530, loss: 0.001431178068742156
2023-01-22 15:14:42.665596: step: 80/530, loss: 0.0010363295441493392
2023-01-22 15:14:43.715446: step: 84/530, loss: 0.0036098435521125793
2023-01-22 15:14:44.751916: step: 88/530, loss: 0.004584179725497961
2023-01-22 15:14:45.803248: step: 92/530, loss: 0.0020966327283531427
2023-01-22 15:14:46.872301: step: 96/530, loss: 0.019692474976181984
2023-01-22 15:14:47.926562: step: 100/530, loss: 0.003456499893218279
2023-01-22 15:14:48.986196: step: 104/530, loss: 0.028512200340628624
2023-01-22 15:14:50.024858: step: 108/530, loss: 0.005234116688370705
2023-01-22 15:14:51.058621: step: 112/530, loss: 0.021136388182640076
2023-01-22 15:14:52.133464: step: 116/530, loss: 0.003945980221033096
2023-01-22 15:14:53.175126: step: 120/530, loss: 0.02525639906525612
2023-01-22 15:14:54.220799: step: 124/530, loss: 0.007580672390758991
2023-01-22 15:14:55.288835: step: 128/530, loss: 0.0042554219253361225
2023-01-22 15:14:56.337136: step: 132/530, loss: 0.0026932593900710344
2023-01-22 15:14:57.389700: step: 136/530, loss: 0.015149188227951527
2023-01-22 15:14:58.436109: step: 140/530, loss: 0.009992536157369614
2023-01-22 15:14:59.483538: step: 144/530, loss: 0.05954030901193619
2023-01-22 15:15:00.534348: step: 148/530, loss: 0.004324452951550484
2023-01-22 15:15:01.566939: step: 152/530, loss: 0.0016933104488998652
2023-01-22 15:15:02.615278: step: 156/530, loss: 0.017377691343426704
2023-01-22 15:15:03.670302: step: 160/530, loss: 0.013133893720805645
2023-01-22 15:15:04.715977: step: 164/530, loss: 0.010859663598239422
2023-01-22 15:15:05.758048: step: 168/530, loss: 0.006150545086711645
2023-01-22 15:15:06.805857: step: 172/530, loss: 0.002983695827424526
2023-01-22 15:15:07.847584: step: 176/530, loss: 0.003486424218863249
2023-01-22 15:15:08.897762: step: 180/530, loss: 0.007634737063199282
2023-01-22 15:15:09.935803: step: 184/530, loss: 0.0019673083443194628
2023-01-22 15:15:10.982080: step: 188/530, loss: 0.037448983639478683
2023-01-22 15:15:12.027683: step: 192/530, loss: 0.005233213305473328
2023-01-22 15:15:13.098000: step: 196/530, loss: 0.008048838004469872
2023-01-22 15:15:14.142520: step: 200/530, loss: 0.009631250984966755
2023-01-22 15:15:15.216214: step: 204/530, loss: 0.0036192014813423157
2023-01-22 15:15:16.245116: step: 208/530, loss: 0.00941761676222086
2023-01-22 15:15:17.305082: step: 212/530, loss: 0.007438240107148886
2023-01-22 15:15:18.360494: step: 216/530, loss: 0.009174337610602379
2023-01-22 15:15:19.411526: step: 220/530, loss: 0.012814212590456009
2023-01-22 15:15:20.458634: step: 224/530, loss: 0.003169468604028225
2023-01-22 15:15:21.520197: step: 228/530, loss: 0.01477832067757845
2023-01-22 15:15:22.571188: step: 232/530, loss: 0.004762791097164154
2023-01-22 15:15:23.612374: step: 236/530, loss: 0.0009118078742176294
2023-01-22 15:15:24.663662: step: 240/530, loss: 0.0076090204529464245
2023-01-22 15:15:25.689835: step: 244/530, loss: 0.01418292336165905
2023-01-22 15:15:26.736323: step: 248/530, loss: 0.002979577984660864
2023-01-22 15:15:27.772091: step: 252/530, loss: 0.016973827034235
2023-01-22 15:15:28.811452: step: 256/530, loss: 0.03841639310121536
2023-01-22 15:15:29.858288: step: 260/530, loss: 0.005691807251423597
2023-01-22 15:15:30.904516: step: 264/530, loss: 0.012516610324382782
2023-01-22 15:15:31.946856: step: 268/530, loss: 0.004631086718291044
2023-01-22 15:15:32.993502: step: 272/530, loss: 0.00608882075175643
2023-01-22 15:15:34.045066: step: 276/530, loss: 0.007790985982865095
2023-01-22 15:15:35.076650: step: 280/530, loss: 0.0038460693322122097
2023-01-22 15:15:36.134646: step: 284/530, loss: 0.010678712278604507
2023-01-22 15:15:37.183339: step: 288/530, loss: 0.006827929522842169
2023-01-22 15:15:38.225373: step: 292/530, loss: 0.009913576766848564
2023-01-22 15:15:39.285251: step: 296/530, loss: 0.007829931564629078
2023-01-22 15:15:40.340629: step: 300/530, loss: 0.007564726285636425
2023-01-22 15:15:41.398172: step: 304/530, loss: 0.0016680812695994973
2023-01-22 15:15:42.449540: step: 308/530, loss: 0.0019515500171110034
2023-01-22 15:15:43.504136: step: 312/530, loss: 0.006295766215771437
2023-01-22 15:15:44.548885: step: 316/530, loss: 0.014552712440490723
2023-01-22 15:15:45.610496: step: 320/530, loss: 0.015734106302261353
2023-01-22 15:15:46.658055: step: 324/530, loss: 0.029018845409154892
2023-01-22 15:15:47.708064: step: 328/530, loss: 0.002421098994091153
2023-01-22 15:15:48.743471: step: 332/530, loss: 0.007607277948409319
2023-01-22 15:15:49.821803: step: 336/530, loss: 0.008062227629125118
2023-01-22 15:15:50.872131: step: 340/530, loss: 0.002171614672988653
2023-01-22 15:15:51.927069: step: 344/530, loss: 0.005242005456238985
2023-01-22 15:15:53.000931: step: 348/530, loss: 0.03092706948518753
2023-01-22 15:15:54.038890: step: 352/530, loss: 0.0011545714223757386
2023-01-22 15:15:55.084565: step: 356/530, loss: 0.014324848540127277
2023-01-22 15:15:56.139411: step: 360/530, loss: 0.0010595325147733092
2023-01-22 15:15:57.212154: step: 364/530, loss: 0.00783079955726862
2023-01-22 15:15:58.270053: step: 368/530, loss: 0.02011287398636341
2023-01-22 15:15:59.316640: step: 372/530, loss: 0.008472003042697906
2023-01-22 15:16:00.374826: step: 376/530, loss: 0.004476419184356928
2023-01-22 15:16:01.430625: step: 380/530, loss: 0.002901660744100809
2023-01-22 15:16:02.479568: step: 384/530, loss: 0.004274390172213316
2023-01-22 15:16:03.529967: step: 388/530, loss: 0.007560750935226679
2023-01-22 15:16:04.589436: step: 392/530, loss: 0.008412742987275124
2023-01-22 15:16:05.628002: step: 396/530, loss: 0.002534314524382353
2023-01-22 15:16:06.676923: step: 400/530, loss: 0.0003153608995489776
2023-01-22 15:16:07.745078: step: 404/530, loss: 0.011063888669013977
2023-01-22 15:16:08.794012: step: 408/530, loss: 0.01040762010961771
2023-01-22 15:16:09.839338: step: 412/530, loss: 0.0013059860793873668
2023-01-22 15:16:10.877372: step: 416/530, loss: 0.002887838752940297
2023-01-22 15:16:11.936903: step: 420/530, loss: 0.003689179429784417
2023-01-22 15:16:12.994874: step: 424/530, loss: 0.006608184892684221
2023-01-22 15:16:14.053988: step: 428/530, loss: 0.0027508896309882402
2023-01-22 15:16:15.108989: step: 432/530, loss: 0.03888503462076187
2023-01-22 15:16:16.154411: step: 436/530, loss: 0.011268495582044125
2023-01-22 15:16:17.201692: step: 440/530, loss: 0.007574399467557669
2023-01-22 15:16:18.247875: step: 444/530, loss: 0.004419418517500162
2023-01-22 15:16:19.306184: step: 448/530, loss: 0.00045379874063655734
2023-01-22 15:16:20.347221: step: 452/530, loss: 0.0008488036692142487
2023-01-22 15:16:21.398275: step: 456/530, loss: 0.020364968106150627
2023-01-22 15:16:22.456988: step: 460/530, loss: 0.003826733212918043
2023-01-22 15:16:23.504680: step: 464/530, loss: 0.010594396851956844
2023-01-22 15:16:24.551528: step: 468/530, loss: 0.004512263927608728
2023-01-22 15:16:25.587961: step: 472/530, loss: 0.009800147265195847
2023-01-22 15:16:26.654834: step: 476/530, loss: 0.047890421003103256
2023-01-22 15:16:27.727040: step: 480/530, loss: 0.009888233616948128
2023-01-22 15:16:28.788703: step: 484/530, loss: 0.006917847320437431
2023-01-22 15:16:29.846568: step: 488/530, loss: 0.0050926003605127335
2023-01-22 15:16:30.889777: step: 492/530, loss: 0.0029797812458127737
2023-01-22 15:16:31.913945: step: 496/530, loss: 0.013459056615829468
2023-01-22 15:16:32.978615: step: 500/530, loss: 0.025662623345851898
2023-01-22 15:16:34.025398: step: 504/530, loss: 0.0174722783267498
2023-01-22 15:16:35.090148: step: 508/530, loss: 0.010713571682572365
2023-01-22 15:16:36.141170: step: 512/530, loss: 0.0031614790204912424
2023-01-22 15:16:37.197863: step: 516/530, loss: 0.005334513261914253
2023-01-22 15:16:38.247825: step: 520/530, loss: 0.003554454306140542
2023-01-22 15:16:39.305386: step: 524/530, loss: 0.015352113172411919
2023-01-22 15:16:40.351917: step: 528/530, loss: 0.01889767497777939
2023-01-22 15:16:41.398277: step: 532/530, loss: 0.023547524586319923
2023-01-22 15:16:42.438389: step: 536/530, loss: 0.022570954635739326
2023-01-22 15:16:43.493433: step: 540/530, loss: 0.002468713792040944
2023-01-22 15:16:44.547799: step: 544/530, loss: 0.0029661296866834164
2023-01-22 15:16:45.578822: step: 548/530, loss: 0.0069870189763605595
2023-01-22 15:16:46.629838: step: 552/530, loss: 0.012515907175838947
2023-01-22 15:16:47.680846: step: 556/530, loss: 0.006003242917358875
2023-01-22 15:16:48.714713: step: 560/530, loss: 0.006347401533275843
2023-01-22 15:16:49.765427: step: 564/530, loss: 0.004825224634259939
2023-01-22 15:16:50.816313: step: 568/530, loss: 0.010376404970884323
2023-01-22 15:16:51.874321: step: 572/530, loss: 0.00442598108202219
2023-01-22 15:16:52.910041: step: 576/530, loss: 0.0035153068602085114
2023-01-22 15:16:53.976582: step: 580/530, loss: 0.001959670102223754
2023-01-22 15:16:55.028980: step: 584/530, loss: 0.0016146284760907292
2023-01-22 15:16:56.077533: step: 588/530, loss: 0.03220200538635254
2023-01-22 15:16:57.129287: step: 592/530, loss: 0.006691142916679382
2023-01-22 15:16:58.186497: step: 596/530, loss: 0.007411698345094919
2023-01-22 15:16:59.238575: step: 600/530, loss: 0.022594882175326347
2023-01-22 15:17:00.283057: step: 604/530, loss: 0.019872277975082397
2023-01-22 15:17:01.335018: step: 608/530, loss: 0.004766772501170635
2023-01-22 15:17:02.398770: step: 612/530, loss: 0.001640079659409821
2023-01-22 15:17:03.467226: step: 616/530, loss: 0.026924069970846176
2023-01-22 15:17:04.522013: step: 620/530, loss: 0.004269296769052744
2023-01-22 15:17:05.550019: step: 624/530, loss: 0.032938603311777115
2023-01-22 15:17:06.623183: step: 628/530, loss: 0.07112736999988556
2023-01-22 15:17:07.675851: step: 632/530, loss: 0.002609388902783394
2023-01-22 15:17:08.735135: step: 636/530, loss: 0.005671422462910414
2023-01-22 15:17:09.766257: step: 640/530, loss: 0.010422873310744762
2023-01-22 15:17:10.802428: step: 644/530, loss: 0.004011990502476692
2023-01-22 15:17:11.839121: step: 648/530, loss: 0.004823459777981043
2023-01-22 15:17:12.878604: step: 652/530, loss: 0.0007633664645254612
2023-01-22 15:17:13.932204: step: 656/530, loss: 0.005875679198652506
2023-01-22 15:17:14.986122: step: 660/530, loss: 0.00778320524841547
2023-01-22 15:17:16.029830: step: 664/530, loss: 0.007265261374413967
2023-01-22 15:17:17.065385: step: 668/530, loss: 0.016020778566598892
2023-01-22 15:17:18.102155: step: 672/530, loss: 0.00456432206556201
2023-01-22 15:17:19.136233: step: 676/530, loss: 0.004717620089650154
2023-01-22 15:17:20.201956: step: 680/530, loss: 0.004241175018250942
2023-01-22 15:17:21.239268: step: 684/530, loss: 0.0016837397124618292
2023-01-22 15:17:22.278924: step: 688/530, loss: 0.0077882069163024426
2023-01-22 15:17:23.324952: step: 692/530, loss: 0.004180263262242079
2023-01-22 15:17:24.378796: step: 696/530, loss: 0.0011722301132977009
2023-01-22 15:17:25.428194: step: 700/530, loss: 0.003927664831280708
2023-01-22 15:17:26.475869: step: 704/530, loss: 0.003746821777895093
2023-01-22 15:17:27.531641: step: 708/530, loss: 0.010402302257716656
2023-01-22 15:17:28.580513: step: 712/530, loss: 0.003486238420009613
2023-01-22 15:17:29.624127: step: 716/530, loss: 0.007428276818245649
2023-01-22 15:17:30.690505: step: 720/530, loss: 0.0062630134634673595
2023-01-22 15:17:31.722405: step: 724/530, loss: 0.006969220004975796
2023-01-22 15:17:32.770448: step: 728/530, loss: 0.0075798118487000465
2023-01-22 15:17:33.837906: step: 732/530, loss: 0.004669481422752142
2023-01-22 15:17:34.900402: step: 736/530, loss: 0.003979456145316362
2023-01-22 15:17:35.941019: step: 740/530, loss: 0.0
2023-01-22 15:17:37.011263: step: 744/530, loss: 0.008986570872366428
2023-01-22 15:17:38.059654: step: 748/530, loss: 0.00022098649060353637
2023-01-22 15:17:39.106755: step: 752/530, loss: 0.014801819808781147
2023-01-22 15:17:40.151955: step: 756/530, loss: 0.00024320901138707995
2023-01-22 15:17:41.187655: step: 760/530, loss: 0.010732698254287243
2023-01-22 15:17:42.232266: step: 764/530, loss: 0.0075147259049117565
2023-01-22 15:17:43.272868: step: 768/530, loss: 0.005018957890570164
2023-01-22 15:17:44.310362: step: 772/530, loss: 0.013307273387908936
2023-01-22 15:17:45.363836: step: 776/530, loss: 0.008007578551769257
2023-01-22 15:17:46.428787: step: 780/530, loss: 0.009756868705153465
2023-01-22 15:17:47.502183: step: 784/530, loss: 0.008467484265565872
2023-01-22 15:17:48.538738: step: 788/530, loss: 0.004501370247453451
2023-01-22 15:17:49.587641: step: 792/530, loss: 0.003742700908333063
2023-01-22 15:17:50.626527: step: 796/530, loss: 0.012340862303972244
2023-01-22 15:17:51.674454: step: 800/530, loss: 0.016069967299699783
2023-01-22 15:17:52.719117: step: 804/530, loss: 0.02661287970840931
2023-01-22 15:17:53.772193: step: 808/530, loss: 0.004242150112986565
2023-01-22 15:17:54.837874: step: 812/530, loss: 0.00043672951869666576
2023-01-22 15:17:55.884274: step: 816/530, loss: 0.004944864194840193
2023-01-22 15:17:56.940167: step: 820/530, loss: 0.002860134234651923
2023-01-22 15:17:57.994999: step: 824/530, loss: 0.010515425354242325
2023-01-22 15:17:59.048647: step: 828/530, loss: 0.006130465306341648
2023-01-22 15:18:00.086157: step: 832/530, loss: 0.006505517289042473
2023-01-22 15:18:01.152719: step: 836/530, loss: 0.005574814509600401
2023-01-22 15:18:02.205391: step: 840/530, loss: 0.0022138457279652357
2023-01-22 15:18:03.252533: step: 844/530, loss: 0.001904115080833435
2023-01-22 15:18:04.304402: step: 848/530, loss: 0.009070370346307755
2023-01-22 15:18:05.341347: step: 852/530, loss: 0.0078091854229569435
2023-01-22 15:18:06.372764: step: 856/530, loss: 0.006255922839045525
2023-01-22 15:18:07.442182: step: 860/530, loss: 0.004079470876604319
2023-01-22 15:18:08.488096: step: 864/530, loss: 0.024813443422317505
2023-01-22 15:18:09.526858: step: 868/530, loss: 0.009829799644649029
2023-01-22 15:18:10.556531: step: 872/530, loss: 0.0006468616193160415
2023-01-22 15:18:11.608206: step: 876/530, loss: 0.010373394005000591
2023-01-22 15:18:12.656387: step: 880/530, loss: 0.0077370535582304
2023-01-22 15:18:13.721349: step: 884/530, loss: 0.009096537716686726
2023-01-22 15:18:14.784052: step: 888/530, loss: 0.006196631584316492
2023-01-22 15:18:15.822923: step: 892/530, loss: 0.013388208113610744
2023-01-22 15:18:16.869847: step: 896/530, loss: 0.00273515866138041
2023-01-22 15:18:17.922739: step: 900/530, loss: 0.037651825696229935
2023-01-22 15:18:18.983375: step: 904/530, loss: 0.001838191761635244
2023-01-22 15:18:20.038360: step: 908/530, loss: 0.01699456200003624
2023-01-22 15:18:21.092970: step: 912/530, loss: 0.019773347303271294
2023-01-22 15:18:22.138919: step: 916/530, loss: 0.005390337202697992
2023-01-22 15:18:23.198744: step: 920/530, loss: 0.003894219407811761
2023-01-22 15:18:24.250394: step: 924/530, loss: 0.002449760679155588
2023-01-22 15:18:25.304559: step: 928/530, loss: 0.006844779476523399
2023-01-22 15:18:26.351705: step: 932/530, loss: 0.0027226568199694157
2023-01-22 15:18:27.412264: step: 936/530, loss: 0.0017901048995554447
2023-01-22 15:18:28.473137: step: 940/530, loss: 0.0005953708314336836
2023-01-22 15:18:29.545697: step: 944/530, loss: 0.006889801938086748
2023-01-22 15:18:30.604115: step: 948/530, loss: 0.009537424892187119
2023-01-22 15:18:31.661919: step: 952/530, loss: 0.0047201733104884624
2023-01-22 15:18:32.718286: step: 956/530, loss: 0.002545745112001896
2023-01-22 15:18:33.773537: step: 960/530, loss: 0.0071816653944551945
2023-01-22 15:18:34.830035: step: 964/530, loss: 0.0063903070986270905
2023-01-22 15:18:35.871460: step: 968/530, loss: 0.007996964268386364
2023-01-22 15:18:36.926335: step: 972/530, loss: 0.020088938996195793
2023-01-22 15:18:37.976825: step: 976/530, loss: 0.026697447523474693
2023-01-22 15:18:39.029436: step: 980/530, loss: 0.0035822000354528427
2023-01-22 15:18:40.087347: step: 984/530, loss: 0.05621730536222458
2023-01-22 15:18:41.138601: step: 988/530, loss: 0.0037705895956605673
2023-01-22 15:18:42.189946: step: 992/530, loss: 0.007121534086763859
2023-01-22 15:18:43.237810: step: 996/530, loss: 0.010187803767621517
2023-01-22 15:18:44.279534: step: 1000/530, loss: 0.004600352607667446
2023-01-22 15:18:45.324762: step: 1004/530, loss: 0.00710757402703166
2023-01-22 15:18:46.373041: step: 1008/530, loss: 0.013693444430828094
2023-01-22 15:18:47.423138: step: 1012/530, loss: 0.006806944962590933
2023-01-22 15:18:48.465807: step: 1016/530, loss: 0.005661698989570141
2023-01-22 15:18:49.507809: step: 1020/530, loss: 0.021601727232336998
2023-01-22 15:18:50.546672: step: 1024/530, loss: 0.0143333300948143
2023-01-22 15:18:51.598332: step: 1028/530, loss: 0.0030909921042621136
2023-01-22 15:18:52.643591: step: 1032/530, loss: 0.025878949090838432
2023-01-22 15:18:53.723385: step: 1036/530, loss: 0.022994389757514
2023-01-22 15:18:54.766775: step: 1040/530, loss: 0.007277947384864092
2023-01-22 15:18:55.797712: step: 1044/530, loss: 0.0001771945389918983
2023-01-22 15:18:56.846571: step: 1048/530, loss: 0.025386063382029533
2023-01-22 15:18:57.883442: step: 1052/530, loss: 0.013307204470038414
2023-01-22 15:18:58.947623: step: 1056/530, loss: 0.0018151187105104327
2023-01-22 15:18:59.988089: step: 1060/530, loss: 0.004172686021775007
2023-01-22 15:19:01.027147: step: 1064/530, loss: 0.008838359266519547
2023-01-22 15:19:02.070042: step: 1068/530, loss: 0.01083298772573471
2023-01-22 15:19:03.133806: step: 1072/530, loss: 0.023340122774243355
2023-01-22 15:19:04.164743: step: 1076/530, loss: 0.01825847290456295
2023-01-22 15:19:05.221609: step: 1080/530, loss: 0.005503007210791111
2023-01-22 15:19:06.274747: step: 1084/530, loss: 0.009955443441867828
2023-01-22 15:19:07.313123: step: 1088/530, loss: 0.004059256985783577
2023-01-22 15:19:08.349391: step: 1092/530, loss: 0.012757353484630585
2023-01-22 15:19:09.409342: step: 1096/530, loss: 0.019996175542473793
2023-01-22 15:19:10.447330: step: 1100/530, loss: 0.012939047068357468
2023-01-22 15:19:11.494438: step: 1104/530, loss: 0.0037144487723708153
2023-01-22 15:19:12.539813: step: 1108/530, loss: 0.008983484469354153
2023-01-22 15:19:13.602849: step: 1112/530, loss: 0.0027749284636229277
2023-01-22 15:19:14.644427: step: 1116/530, loss: 0.0632312148809433
2023-01-22 15:19:15.678780: step: 1120/530, loss: 0.010624143294990063
2023-01-22 15:19:16.714842: step: 1124/530, loss: 0.002980514196678996
2023-01-22 15:19:17.765011: step: 1128/530, loss: 0.029609989374876022
2023-01-22 15:19:18.809131: step: 1132/530, loss: 0.013118281029164791
2023-01-22 15:19:19.858899: step: 1136/530, loss: 0.0006186221726238728
2023-01-22 15:19:20.910338: step: 1140/530, loss: 0.00036158814327791333
2023-01-22 15:19:21.943740: step: 1144/530, loss: 0.00920632854104042
2023-01-22 15:19:22.981155: step: 1148/530, loss: 0.020401351153850555
2023-01-22 15:19:24.016957: step: 1152/530, loss: 0.0003302432014606893
2023-01-22 15:19:25.076488: step: 1156/530, loss: 0.021824853494763374
2023-01-22 15:19:26.125111: step: 1160/530, loss: 0.012219293043017387
2023-01-22 15:19:27.163043: step: 1164/530, loss: 0.013180164620280266
2023-01-22 15:19:28.203537: step: 1168/530, loss: 0.0035963330883532763
2023-01-22 15:19:29.243749: step: 1172/530, loss: 0.002271289238706231
2023-01-22 15:19:30.274401: step: 1176/530, loss: 0.02488148957490921
2023-01-22 15:19:31.315002: step: 1180/530, loss: 0.002901423256844282
2023-01-22 15:19:32.387279: step: 1184/530, loss: 0.0026070319581776857
2023-01-22 15:19:33.439890: step: 1188/530, loss: 0.0025322569999843836
2023-01-22 15:19:34.478261: step: 1192/530, loss: 0.0012351305922493339
2023-01-22 15:19:35.519065: step: 1196/530, loss: 0.011039367876946926
2023-01-22 15:19:36.563035: step: 1200/530, loss: 0.009021017700433731
2023-01-22 15:19:37.591989: step: 1204/530, loss: 0.002864608308300376
2023-01-22 15:19:38.644636: step: 1208/530, loss: 0.014229614287614822
2023-01-22 15:19:39.691684: step: 1212/530, loss: 0.02456767112016678
2023-01-22 15:19:40.736878: step: 1216/530, loss: 0.01543382741510868
2023-01-22 15:19:41.778792: step: 1220/530, loss: 0.004292861558496952
2023-01-22 15:19:42.816931: step: 1224/530, loss: 0.007197290658950806
2023-01-22 15:19:43.859361: step: 1228/530, loss: 0.01018136739730835
2023-01-22 15:19:44.903050: step: 1232/530, loss: 0.002991825109347701
2023-01-22 15:19:45.939940: step: 1236/530, loss: 0.022423578426241875
2023-01-22 15:19:46.993470: step: 1240/530, loss: 0.002303708577528596
2023-01-22 15:19:48.038868: step: 1244/530, loss: 0.021710142493247986
2023-01-22 15:19:49.106331: step: 1248/530, loss: 0.009048247709870338
2023-01-22 15:19:50.150833: step: 1252/530, loss: 0.035389285534620285
2023-01-22 15:19:51.203386: step: 1256/530, loss: 0.010742432437837124
2023-01-22 15:19:52.244079: step: 1260/530, loss: 0.010142643935978413
2023-01-22 15:19:53.282519: step: 1264/530, loss: 0.022211836650967598
2023-01-22 15:19:54.331806: step: 1268/530, loss: 0.007839965634047985
2023-01-22 15:19:55.373798: step: 1272/530, loss: 0.02114162966609001
2023-01-22 15:19:56.407286: step: 1276/530, loss: 0.013651162385940552
2023-01-22 15:19:57.448017: step: 1280/530, loss: 0.005986716598272324
2023-01-22 15:19:58.492853: step: 1284/530, loss: 0.017527097836136818
2023-01-22 15:19:59.533120: step: 1288/530, loss: 0.004508642479777336
2023-01-22 15:20:00.577668: step: 1292/530, loss: 0.04023851826786995
2023-01-22 15:20:01.614236: step: 1296/530, loss: 0.006751182954758406
2023-01-22 15:20:02.671829: step: 1300/530, loss: 0.016403554007411003
2023-01-22 15:20:03.734265: step: 1304/530, loss: 0.0015220451168715954
2023-01-22 15:20:04.780258: step: 1308/530, loss: 0.004788473714143038
2023-01-22 15:20:05.834463: step: 1312/530, loss: 0.010849830694496632
2023-01-22 15:20:06.880082: step: 1316/530, loss: 0.004726604092866182
2023-01-22 15:20:07.922328: step: 1320/530, loss: 0.026048095896840096
2023-01-22 15:20:08.977209: step: 1324/530, loss: 0.02229171432554722
2023-01-22 15:20:10.029359: step: 1328/530, loss: 0.0006768946768715978
2023-01-22 15:20:11.064802: step: 1332/530, loss: 0.0069791232235729694
2023-01-22 15:20:12.111160: step: 1336/530, loss: 0.0015911575173959136
2023-01-22 15:20:13.160283: step: 1340/530, loss: 0.0032544168643653393
2023-01-22 15:20:14.198392: step: 1344/530, loss: 0.005280646961182356
2023-01-22 15:20:15.242665: step: 1348/530, loss: 0.00202184752561152
2023-01-22 15:20:16.287628: step: 1352/530, loss: 0.0004644987639039755
2023-01-22 15:20:17.337671: step: 1356/530, loss: 0.010267892852425575
2023-01-22 15:20:18.389660: step: 1360/530, loss: 0.003436907660216093
2023-01-22 15:20:19.441523: step: 1364/530, loss: 0.00423907907679677
2023-01-22 15:20:20.489462: step: 1368/530, loss: 0.019025731831789017
2023-01-22 15:20:21.531926: step: 1372/530, loss: 0.00795195996761322
2023-01-22 15:20:22.567157: step: 1376/530, loss: 3.6636803997680545e-05
2023-01-22 15:20:23.629499: step: 1380/530, loss: 0.004467297345399857
2023-01-22 15:20:24.667416: step: 1384/530, loss: 0.00039880044641904533
2023-01-22 15:20:25.736666: step: 1388/530, loss: 0.0064514027908444405
2023-01-22 15:20:26.775363: step: 1392/530, loss: 0.0030811401084065437
2023-01-22 15:20:27.830752: step: 1396/530, loss: 0.004701836965978146
2023-01-22 15:20:28.871709: step: 1400/530, loss: 0.0043533421121537685
2023-01-22 15:20:29.913195: step: 1404/530, loss: 0.01922466792166233
2023-01-22 15:20:30.953359: step: 1408/530, loss: 0.006513860542327166
2023-01-22 15:20:32.003572: step: 1412/530, loss: 0.057321395725011826
2023-01-22 15:20:33.062487: step: 1416/530, loss: 0.0027382546104490757
2023-01-22 15:20:34.129968: step: 1420/530, loss: 0.018424641340970993
2023-01-22 15:20:35.162635: step: 1424/530, loss: 0.004779089242219925
2023-01-22 15:20:36.204604: step: 1428/530, loss: 0.002440408570691943
2023-01-22 15:20:37.239402: step: 1432/530, loss: 0.01081522461026907
2023-01-22 15:20:38.279516: step: 1436/530, loss: 0.0016349562210962176
2023-01-22 15:20:39.316048: step: 1440/530, loss: 0.018720485270023346
2023-01-22 15:20:40.370364: step: 1444/530, loss: 0.009044265374541283
2023-01-22 15:20:41.421079: step: 1448/530, loss: 0.011946936137974262
2023-01-22 15:20:42.469775: step: 1452/530, loss: 0.0019487175159156322
2023-01-22 15:20:43.518578: step: 1456/530, loss: 0.05007105693221092
2023-01-22 15:20:44.558722: step: 1460/530, loss: 0.02294820360839367
2023-01-22 15:20:45.613204: step: 1464/530, loss: 0.016945742070674896
2023-01-22 15:20:46.648921: step: 1468/530, loss: 0.004874739795923233
2023-01-22 15:20:47.710982: step: 1472/530, loss: 0.00848757941275835
2023-01-22 15:20:48.761371: step: 1476/530, loss: 0.005451865494251251
2023-01-22 15:20:49.792631: step: 1480/530, loss: 0.002858688123524189
2023-01-22 15:20:50.850751: step: 1484/530, loss: 0.009365770034492016
2023-01-22 15:20:51.896917: step: 1488/530, loss: 0.01442341972142458
2023-01-22 15:20:52.930927: step: 1492/530, loss: 0.00444852514192462
2023-01-22 15:20:53.963676: step: 1496/530, loss: 0.0044186906889081
2023-01-22 15:20:54.999279: step: 1500/530, loss: 0.002757208188995719
2023-01-22 15:20:56.071146: step: 1504/530, loss: 0.009161938913166523
2023-01-22 15:20:57.103787: step: 1508/530, loss: 0.006433708593249321
2023-01-22 15:20:58.154153: step: 1512/530, loss: 0.011822265572845936
2023-01-22 15:20:59.203142: step: 1516/530, loss: 0.01151095051318407
2023-01-22 15:21:00.254150: step: 1520/530, loss: 0.004070369992405176
2023-01-22 15:21:01.311736: step: 1524/530, loss: 0.002289979485794902
2023-01-22 15:21:02.356186: step: 1528/530, loss: 0.0016516131581738591
2023-01-22 15:21:03.400953: step: 1532/530, loss: 0.0033080594148486853
2023-01-22 15:21:04.459427: step: 1536/530, loss: 0.015890631824731827
2023-01-22 15:21:05.518903: step: 1540/530, loss: 0.0019086874090135098
2023-01-22 15:21:06.582195: step: 1544/530, loss: 0.02645191363990307
2023-01-22 15:21:07.628929: step: 1548/530, loss: 0.005352192558348179
2023-01-22 15:21:08.665718: step: 1552/530, loss: 0.0018773925257846713
2023-01-22 15:21:09.705169: step: 1556/530, loss: 0.004711862187832594
2023-01-22 15:21:10.747777: step: 1560/530, loss: 0.007976806722581387
2023-01-22 15:21:11.792419: step: 1564/530, loss: 0.009661748073995113
2023-01-22 15:21:12.860976: step: 1568/530, loss: 0.006966938264667988
2023-01-22 15:21:13.896148: step: 1572/530, loss: 0.005844578146934509
2023-01-22 15:21:14.947873: step: 1576/530, loss: 0.02175166830420494
2023-01-22 15:21:16.001897: step: 1580/530, loss: 0.010553802363574505
2023-01-22 15:21:17.056471: step: 1584/530, loss: 0.018760759383440018
2023-01-22 15:21:18.101961: step: 1588/530, loss: 0.008100664243102074
2023-01-22 15:21:19.144430: step: 1592/530, loss: 0.002234217943623662
2023-01-22 15:21:20.188601: step: 1596/530, loss: 0.006893356796354055
2023-01-22 15:21:21.229208: step: 1600/530, loss: 0.006318795960396528
2023-01-22 15:21:22.270584: step: 1604/530, loss: 0.00822544563561678
2023-01-22 15:21:23.306095: step: 1608/530, loss: 0.008038416504859924
2023-01-22 15:21:24.368320: step: 1612/530, loss: 0.01708037406206131
2023-01-22 15:21:25.411860: step: 1616/530, loss: 0.006844771560281515
2023-01-22 15:21:26.440713: step: 1620/530, loss: 0.05640245974063873
2023-01-22 15:21:27.490188: step: 1624/530, loss: 0.011180452071130276
2023-01-22 15:21:28.532142: step: 1628/530, loss: 0.041737161576747894
2023-01-22 15:21:29.579393: step: 1632/530, loss: 0.004179058596491814
2023-01-22 15:21:30.619993: step: 1636/530, loss: 0.004697559867054224
2023-01-22 15:21:31.691467: step: 1640/530, loss: 0.04130321368575096
2023-01-22 15:21:32.754134: step: 1644/530, loss: 0.01205145101994276
2023-01-22 15:21:33.792441: step: 1648/530, loss: 0.01519062276929617
2023-01-22 15:21:34.856066: step: 1652/530, loss: 0.006274986546486616
2023-01-22 15:21:35.899964: step: 1656/530, loss: 0.02690383791923523
2023-01-22 15:21:36.935214: step: 1660/530, loss: 0.0022225563880056143
2023-01-22 15:21:37.987716: step: 1664/530, loss: 0.012799485586583614
2023-01-22 15:21:39.021727: step: 1668/530, loss: 0.013212735764682293
2023-01-22 15:21:40.056233: step: 1672/530, loss: 0.04080083221197128
2023-01-22 15:21:41.102306: step: 1676/530, loss: 0.005913273897022009
2023-01-22 15:21:42.157002: step: 1680/530, loss: 0.015069507993757725
2023-01-22 15:21:43.195957: step: 1684/530, loss: 0.004546095617115498
2023-01-22 15:21:44.230966: step: 1688/530, loss: 0.007551766466349363
2023-01-22 15:21:45.268995: step: 1692/530, loss: 0.010521274991333485
2023-01-22 15:21:46.312682: step: 1696/530, loss: 0.006171573884785175
2023-01-22 15:21:47.363434: step: 1700/530, loss: 0.03709413856267929
2023-01-22 15:21:48.401135: step: 1704/530, loss: 0.0009492139797657728
2023-01-22 15:21:49.454335: step: 1708/530, loss: 0.005416674539446831
2023-01-22 15:21:50.486153: step: 1712/530, loss: 0.0021202301140874624
2023-01-22 15:21:51.531611: step: 1716/530, loss: 0.0019722450524568558
2023-01-22 15:21:52.574562: step: 1720/530, loss: 0.014917327091097832
2023-01-22 15:21:53.621922: step: 1724/530, loss: 0.008332163095474243
2023-01-22 15:21:54.700934: step: 1728/530, loss: 0.009225474670529366
2023-01-22 15:21:55.750661: step: 1732/530, loss: 0.001848805695772171
2023-01-22 15:21:56.790279: step: 1736/530, loss: 0.013050920329988003
2023-01-22 15:21:57.838004: step: 1740/530, loss: 0.0025201637763530016
2023-01-22 15:21:58.892108: step: 1744/530, loss: 0.004326107446104288
2023-01-22 15:21:59.945841: step: 1748/530, loss: 0.005695197265595198
2023-01-22 15:22:01.005035: step: 1752/530, loss: 0.012486633844673634
2023-01-22 15:22:02.062259: step: 1756/530, loss: 0.006287648808211088
2023-01-22 15:22:03.109221: step: 1760/530, loss: 0.019704468548297882
2023-01-22 15:22:04.149465: step: 1764/530, loss: 0.005859240423887968
2023-01-22 15:22:05.199718: step: 1768/530, loss: 0.0019336638506501913
2023-01-22 15:22:06.257666: step: 1772/530, loss: 0.005709787365049124
2023-01-22 15:22:07.320621: step: 1776/530, loss: 0.003635913133621216
2023-01-22 15:22:08.378461: step: 1780/530, loss: 0.005575036630034447
2023-01-22 15:22:09.433162: step: 1784/530, loss: 0.0020982197020202875
2023-01-22 15:22:10.459673: step: 1788/530, loss: 0.02108420990407467
2023-01-22 15:22:11.510009: step: 1792/530, loss: 0.005897968076169491
2023-01-22 15:22:12.543649: step: 1796/530, loss: 0.006525702774524689
2023-01-22 15:22:13.595831: step: 1800/530, loss: 0.00445253262296319
2023-01-22 15:22:14.660418: step: 1804/530, loss: 0.013924259692430496
2023-01-22 15:22:15.709632: step: 1808/530, loss: 0.04297326132655144
2023-01-22 15:22:16.751597: step: 1812/530, loss: 0.004864335525780916
2023-01-22 15:22:17.794848: step: 1816/530, loss: 0.012600874528288841
2023-01-22 15:22:18.848125: step: 1820/530, loss: 0.011261162348091602
2023-01-22 15:22:19.918234: step: 1824/530, loss: 0.01003257930278778
2023-01-22 15:22:20.983349: step: 1828/530, loss: 0.007177611812949181
2023-01-22 15:22:22.039852: step: 1832/530, loss: 0.005457644816488028
2023-01-22 15:22:23.084631: step: 1836/530, loss: 0.010346289724111557
2023-01-22 15:22:24.150070: step: 1840/530, loss: 0.02937886118888855
2023-01-22 15:22:25.194854: step: 1844/530, loss: 0.009209373965859413
2023-01-22 15:22:26.253824: step: 1848/530, loss: 0.009007374756038189
2023-01-22 15:22:27.283784: step: 1852/530, loss: 0.010204768739640713
2023-01-22 15:22:28.326689: step: 1856/530, loss: 0.005483309272676706
2023-01-22 15:22:29.356285: step: 1860/530, loss: 0.0017381259240210056
2023-01-22 15:22:30.416120: step: 1864/530, loss: 0.0029665653128176928
2023-01-22 15:22:31.461227: step: 1868/530, loss: 0.0047257947735488415
2023-01-22 15:22:32.504702: step: 1872/530, loss: 0.003776599420234561
2023-01-22 15:22:33.565424: step: 1876/530, loss: 0.008062978275120258
2023-01-22 15:22:34.615662: step: 1880/530, loss: 0.008315728977322578
2023-01-22 15:22:35.653190: step: 1884/530, loss: 0.0033979981672018766
2023-01-22 15:22:36.702278: step: 1888/530, loss: 0.010533134452998638
2023-01-22 15:22:37.754224: step: 1892/530, loss: 0.019899064674973488
2023-01-22 15:22:38.803500: step: 1896/530, loss: 0.0027368925511837006
2023-01-22 15:22:39.850791: step: 1900/530, loss: 0.04092983528971672
2023-01-22 15:22:40.911304: step: 1904/530, loss: 0.00851442664861679
2023-01-22 15:22:41.954220: step: 1908/530, loss: 0.02917405776679516
2023-01-22 15:22:42.987520: step: 1912/530, loss: 0.01269491482526064
2023-01-22 15:22:44.043978: step: 1916/530, loss: 0.007485529407858849
2023-01-22 15:22:45.123619: step: 1920/530, loss: 0.004053287208080292
2023-01-22 15:22:46.181322: step: 1924/530, loss: 0.0034167389385402203
2023-01-22 15:22:47.232065: step: 1928/530, loss: 0.00985283125191927
2023-01-22 15:22:48.284976: step: 1932/530, loss: 0.004041532054543495
2023-01-22 15:22:49.321391: step: 1936/530, loss: 0.007994909770786762
2023-01-22 15:22:50.367073: step: 1940/530, loss: 0.06089195981621742
2023-01-22 15:22:51.407460: step: 1944/530, loss: 0.004458821844309568
2023-01-22 15:22:52.430634: step: 1948/530, loss: 0.004738977644592524
2023-01-22 15:22:53.476973: step: 1952/530, loss: 0.01475786603987217
2023-01-22 15:22:54.537623: step: 1956/530, loss: 0.024411706253886223
2023-01-22 15:22:55.586838: step: 1960/530, loss: 0.011239174753427505
2023-01-22 15:22:56.650930: step: 1964/530, loss: 0.031950339674949646
2023-01-22 15:22:57.706923: step: 1968/530, loss: 0.031904272735118866
2023-01-22 15:22:58.742088: step: 1972/530, loss: 0.003503339132294059
2023-01-22 15:22:59.799646: step: 1976/530, loss: 0.0022566267289221287
2023-01-22 15:23:00.853850: step: 1980/530, loss: 0.022635025903582573
2023-01-22 15:23:01.904403: step: 1984/530, loss: 0.014758494682610035
2023-01-22 15:23:02.990942: step: 1988/530, loss: 0.002663377206772566
2023-01-22 15:23:04.057495: step: 1992/530, loss: 0.004463164601475
2023-01-22 15:23:05.108544: step: 1996/530, loss: 0.005761934909969568
2023-01-22 15:23:06.150780: step: 2000/530, loss: 0.006272409576922655
2023-01-22 15:23:07.197908: step: 2004/530, loss: 0.0031166779808700085
2023-01-22 15:23:08.250432: step: 2008/530, loss: 0.012926271185278893
2023-01-22 15:23:09.288395: step: 2012/530, loss: 0.01276963111013174
2023-01-22 15:23:10.326209: step: 2016/530, loss: 0.002114873146638274
2023-01-22 15:23:11.358324: step: 2020/530, loss: 0.011003976687788963
2023-01-22 15:23:12.412059: step: 2024/530, loss: 0.0037110212724655867
2023-01-22 15:23:13.457051: step: 2028/530, loss: 0.04115549474954605
2023-01-22 15:23:14.492837: step: 2032/530, loss: 0.0006640140782110393
2023-01-22 15:23:15.533667: step: 2036/530, loss: 0.0007594458875246346
2023-01-22 15:23:16.573353: step: 2040/530, loss: 0.003376855980604887
2023-01-22 15:23:17.612404: step: 2044/530, loss: 0.012279235757887363
2023-01-22 15:23:18.705921: step: 2048/530, loss: 0.00034014126867987216
2023-01-22 15:23:19.759908: step: 2052/530, loss: 0.000714337860699743
2023-01-22 15:23:20.798363: step: 2056/530, loss: 0.0021405701991170645
2023-01-22 15:23:21.841591: step: 2060/530, loss: 0.005742653273046017
2023-01-22 15:23:22.891307: step: 2064/530, loss: 0.0018683884991332889
2023-01-22 15:23:23.960057: step: 2068/530, loss: 0.0021885179448872805
2023-01-22 15:23:24.986276: step: 2072/530, loss: 0.001408782321959734
2023-01-22 15:23:26.040664: step: 2076/530, loss: 0.001911174738779664
2023-01-22 15:23:27.085464: step: 2080/530, loss: 0.00855308212339878
2023-01-22 15:23:28.125559: step: 2084/530, loss: 0.010563374496996403
2023-01-22 15:23:29.174160: step: 2088/530, loss: 0.004736981354653835
2023-01-22 15:23:30.218365: step: 2092/530, loss: 0.0024413892533630133
2023-01-22 15:23:31.274780: step: 2096/530, loss: 0.0101556908339262
2023-01-22 15:23:32.308357: step: 2100/530, loss: 0.00508415512740612
2023-01-22 15:23:33.392881: step: 2104/530, loss: 0.004340960178524256
2023-01-22 15:23:34.423360: step: 2108/530, loss: 0.010126103647053242
2023-01-22 15:23:35.465647: step: 2112/530, loss: 0.024528298527002335
2023-01-22 15:23:36.497383: step: 2116/530, loss: 0.00544694671407342
2023-01-22 15:23:37.545657: step: 2120/530, loss: 0.007919400930404663
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31128418403580166, 'r': 0.325460313859064, 'f1': 0.3182144441627583}, 'combined': 0.2344738009620324, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35769209218508413, 'r': 0.4083213037627523, 'f1': 0.38133354377156614}, 'combined': 0.29557911048322355, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
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': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 15:26:20.559844: step: 4/530, loss: 0.011587036773562431
2023-01-22 15:26:21.624543: step: 8/530, loss: 0.008058561012148857
2023-01-22 15:26:22.674710: step: 12/530, loss: 0.009622877463698387
2023-01-22 15:26:23.705216: step: 16/530, loss: 0.00474189966917038
2023-01-22 15:26:24.730336: step: 20/530, loss: 0.017884546890854836
2023-01-22 15:26:25.771180: step: 24/530, loss: 0.012270621955394745
2023-01-22 15:26:26.817695: step: 28/530, loss: 0.024582723155617714
2023-01-22 15:26:27.853275: step: 32/530, loss: 0.0006849112687632442
2023-01-22 15:26:28.897514: step: 36/530, loss: 0.012950761243700981
2023-01-22 15:26:29.952279: step: 40/530, loss: 0.00873364694416523
2023-01-22 15:26:30.980138: step: 44/530, loss: 0.0024029721971601248
2023-01-22 15:26:32.021576: step: 48/530, loss: 5.633518594549969e-05
2023-01-22 15:26:33.070934: step: 52/530, loss: 0.002093082293868065
2023-01-22 15:26:34.110095: step: 56/530, loss: 0.003843276994302869
2023-01-22 15:26:35.146749: step: 60/530, loss: 0.003618384012952447
2023-01-22 15:26:36.188057: step: 64/530, loss: 0.03478454798460007
2023-01-22 15:26:37.233491: step: 68/530, loss: 0.008315201848745346
2023-01-22 15:26:38.290957: step: 72/530, loss: 0.002127622254192829
2023-01-22 15:26:39.358897: step: 76/530, loss: 0.006504325661808252
2023-01-22 15:26:40.396330: step: 80/530, loss: 0.0010370308300480247
2023-01-22 15:26:41.429016: step: 84/530, loss: 0.005459685809910297
2023-01-22 15:26:42.474982: step: 88/530, loss: 0.010153745301067829
2023-01-22 15:26:43.512102: step: 92/530, loss: 0.008685597218573093
2023-01-22 15:26:44.564129: step: 96/530, loss: 0.0016931957798078656
2023-01-22 15:26:45.602653: step: 100/530, loss: 0.0009202314540743828
2023-01-22 15:26:46.637610: step: 104/530, loss: 0.009704441763460636
2023-01-22 15:26:47.682948: step: 108/530, loss: 0.02716992050409317
2023-01-22 15:26:48.733457: step: 112/530, loss: 0.0056611159816384315
2023-01-22 15:26:49.768652: step: 116/530, loss: 0.0019131782464683056
2023-01-22 15:26:50.812849: step: 120/530, loss: 0.008631687611341476
2023-01-22 15:26:51.858950: step: 124/530, loss: 0.00399860879406333
2023-01-22 15:26:52.904756: step: 128/530, loss: 0.005334592889994383
2023-01-22 15:26:53.943483: step: 132/530, loss: 0.014294576831161976
2023-01-22 15:26:54.996930: step: 136/530, loss: 0.017037982121109962
2023-01-22 15:26:56.047169: step: 140/530, loss: 0.00272139860317111
2023-01-22 15:26:57.087056: step: 144/530, loss: 0.03012244403362274
2023-01-22 15:26:58.147803: step: 148/530, loss: 0.001278023119084537
2023-01-22 15:26:59.196041: step: 152/530, loss: 0.0034183640964329243
2023-01-22 15:27:00.244714: step: 156/530, loss: 0.0046643540263175964
2023-01-22 15:27:01.295164: step: 160/530, loss: 0.007372661028057337
2023-01-22 15:27:02.338731: step: 164/530, loss: 0.0008810541476123035
2023-01-22 15:27:03.401610: step: 168/530, loss: 0.009536619298160076
2023-01-22 15:27:04.460291: step: 172/530, loss: 0.002241946989670396
2023-01-22 15:27:05.500909: step: 176/530, loss: 0.003911525011062622
2023-01-22 15:27:06.543382: step: 180/530, loss: 0.0025393657851964235
2023-01-22 15:27:07.592814: step: 184/530, loss: 0.004790137056261301
2023-01-22 15:27:08.628077: step: 188/530, loss: 0.00042702045175246894
2023-01-22 15:27:09.677616: step: 192/530, loss: 0.004295692313462496
2023-01-22 15:27:10.721938: step: 196/530, loss: 0.0034668322186917067
2023-01-22 15:27:11.761956: step: 200/530, loss: 0.01009513158351183
2023-01-22 15:27:12.791828: step: 204/530, loss: 0.006042029242962599
2023-01-22 15:27:13.844433: step: 208/530, loss: 0.015337937511503696
2023-01-22 15:27:14.887144: step: 212/530, loss: 0.0026511764153838158
2023-01-22 15:27:15.944827: step: 216/530, loss: 0.003912328276783228
2023-01-22 15:27:16.988128: step: 220/530, loss: 0.0022922749631106853
2023-01-22 15:27:18.038325: step: 224/530, loss: 0.012015871703624725
2023-01-22 15:27:19.092701: step: 228/530, loss: 0.00681014871224761
2023-01-22 15:27:20.146276: step: 232/530, loss: 0.0022635767236351967
2023-01-22 15:27:21.190469: step: 236/530, loss: 0.014557711780071259
2023-01-22 15:27:22.239750: step: 240/530, loss: 0.005466057453304529
2023-01-22 15:27:23.289515: step: 244/530, loss: 0.0012775585055351257
2023-01-22 15:27:24.332477: step: 248/530, loss: 0.01565469801425934
2023-01-22 15:27:25.392106: step: 252/530, loss: 0.004362897947430611
2023-01-22 15:27:26.474797: step: 256/530, loss: 0.02090446650981903
2023-01-22 15:27:27.514404: step: 260/530, loss: 0.011011134833097458
2023-01-22 15:27:28.562418: step: 264/530, loss: 0.0014319868059828877
2023-01-22 15:27:29.619626: step: 268/530, loss: 0.006045954301953316
2023-01-22 15:27:30.658023: step: 272/530, loss: 0.0225754976272583
2023-01-22 15:27:31.707542: step: 276/530, loss: 0.0027312817983329296
2023-01-22 15:27:32.755528: step: 280/530, loss: 0.0006080306484363973
2023-01-22 15:27:33.789023: step: 284/530, loss: 0.0031787727493792772
2023-01-22 15:27:34.838524: step: 288/530, loss: 6.515099084936082e-05
2023-01-22 15:27:35.881384: step: 292/530, loss: 0.00177150743547827
2023-01-22 15:27:36.955989: step: 296/530, loss: 0.0148751987144351
2023-01-22 15:27:38.008385: step: 300/530, loss: 0.026419559493660927
2023-01-22 15:27:39.059435: step: 304/530, loss: 0.0022575596813112497
2023-01-22 15:27:40.116279: step: 308/530, loss: 0.005201238207519054
2023-01-22 15:27:41.169476: step: 312/530, loss: 0.0711824893951416
2023-01-22 15:27:42.214371: step: 316/530, loss: 0.005875852424651384
2023-01-22 15:27:43.253058: step: 320/530, loss: 0.0016077982727438211
2023-01-22 15:27:44.294268: step: 324/530, loss: 0.002177596092224121
2023-01-22 15:27:45.349527: step: 328/530, loss: 0.0152108334004879
2023-01-22 15:27:46.383972: step: 332/530, loss: 0.001335029024630785
2023-01-22 15:27:47.423718: step: 336/530, loss: 0.00045931493514217436
2023-01-22 15:27:48.469429: step: 340/530, loss: 0.002613889053463936
2023-01-22 15:27:49.513539: step: 344/530, loss: 0.0006383536383509636
2023-01-22 15:27:50.557219: step: 348/530, loss: 0.0064877974800765514
2023-01-22 15:27:51.606497: step: 352/530, loss: 0.0014528051251545548
2023-01-22 15:27:52.664285: step: 356/530, loss: 0.007218583486974239
2023-01-22 15:27:53.705433: step: 360/530, loss: 0.002755946945399046
2023-01-22 15:27:54.757665: step: 364/530, loss: 0.003286286722868681
2023-01-22 15:27:55.785574: step: 368/530, loss: 0.00666410569101572
2023-01-22 15:27:56.816313: step: 372/530, loss: 0.0016173524782061577
2023-01-22 15:27:57.931632: step: 376/530, loss: 0.008841770701110363
2023-01-22 15:27:58.990554: step: 380/530, loss: 0.0210097823292017
2023-01-22 15:28:00.050156: step: 384/530, loss: 0.0037013778928667307
2023-01-22 15:28:01.102211: step: 388/530, loss: 0.058689914643764496
2023-01-22 15:28:02.150710: step: 392/530, loss: 0.01135192159563303
2023-01-22 15:28:03.227175: step: 396/530, loss: 0.0011508228490129113
2023-01-22 15:28:04.257977: step: 400/530, loss: 0.013402036391198635
2023-01-22 15:28:05.308664: step: 404/530, loss: 0.00433835806325078
2023-01-22 15:28:06.360300: step: 408/530, loss: 0.005923935677856207
2023-01-22 15:28:07.408277: step: 412/530, loss: 0.0013145239790901542
2023-01-22 15:28:08.454805: step: 416/530, loss: 0.014649472199380398
2023-01-22 15:28:09.509779: step: 420/530, loss: 0.002501662587746978
2023-01-22 15:28:10.544023: step: 424/530, loss: 0.00226204888895154
2023-01-22 15:28:11.581264: step: 428/530, loss: 0.005570810753852129
2023-01-22 15:28:12.626813: step: 432/530, loss: 0.0018400277476757765
2023-01-22 15:28:13.681591: step: 436/530, loss: 0.0057077002711594105
2023-01-22 15:28:14.726440: step: 440/530, loss: 0.0029061168897897005
2023-01-22 15:28:15.804751: step: 444/530, loss: 0.004631864372640848
2023-01-22 15:28:16.855422: step: 448/530, loss: 0.013594035059213638
2023-01-22 15:28:17.897809: step: 452/530, loss: 0.006473762448877096
2023-01-22 15:28:18.950061: step: 456/530, loss: 0.024219676852226257
2023-01-22 15:28:19.998478: step: 460/530, loss: 0.01045110821723938
2023-01-22 15:28:21.054771: step: 464/530, loss: 0.0012683115201070905
2023-01-22 15:28:22.102034: step: 468/530, loss: 0.027867794036865234
2023-01-22 15:28:23.153299: step: 472/530, loss: 0.01294589415192604
2023-01-22 15:28:24.203817: step: 476/530, loss: 0.009049591608345509
2023-01-22 15:28:25.246603: step: 480/530, loss: 0.0025234143249690533
2023-01-22 15:28:26.303528: step: 484/530, loss: 0.0033417821396142244
2023-01-22 15:28:27.366294: step: 488/530, loss: 0.014079265296459198
2023-01-22 15:28:28.400250: step: 492/530, loss: 0.0033510210923850536
2023-01-22 15:28:29.456408: step: 496/530, loss: 0.0005681717302650213
2023-01-22 15:28:30.486028: step: 500/530, loss: 0.011738928966224194
2023-01-22 15:28:31.540081: step: 504/530, loss: 0.0186759103089571
2023-01-22 15:28:32.591794: step: 508/530, loss: 0.003980475943535566
2023-01-22 15:28:33.638104: step: 512/530, loss: 0.008400819264352322
2023-01-22 15:28:34.686812: step: 516/530, loss: 0.007605388760566711
2023-01-22 15:28:35.749823: step: 520/530, loss: 0.009616143070161343
2023-01-22 15:28:36.791558: step: 524/530, loss: 0.003983595408499241
2023-01-22 15:28:37.842361: step: 528/530, loss: 0.006217450834810734
2023-01-22 15:28:38.885381: step: 532/530, loss: 0.00698980875313282
2023-01-22 15:28:39.926009: step: 536/530, loss: 0.010664377361536026
2023-01-22 15:28:40.970502: step: 540/530, loss: 0.0032485490664839745
2023-01-22 15:28:42.038225: step: 544/530, loss: 0.022555796429514885
2023-01-22 15:28:43.095651: step: 548/530, loss: 0.01435762643814087
2023-01-22 15:28:44.140922: step: 552/530, loss: 0.004576300270855427
2023-01-22 15:28:45.192777: step: 556/530, loss: 0.002943630563095212
2023-01-22 15:28:46.247608: step: 560/530, loss: 0.002787049161270261
2023-01-22 15:28:47.294196: step: 564/530, loss: 0.007462665904313326
2023-01-22 15:28:48.345388: step: 568/530, loss: 0.011899206787347794
2023-01-22 15:28:49.410465: step: 572/530, loss: 0.0024678679183125496
2023-01-22 15:28:50.447972: step: 576/530, loss: 0.003009113483130932
2023-01-22 15:28:51.487932: step: 580/530, loss: 0.011800347827374935
2023-01-22 15:28:52.525982: step: 584/530, loss: 0.014704861678183079
2023-01-22 15:28:53.560991: step: 588/530, loss: 1.7893730728246737e-06
2023-01-22 15:28:54.615334: step: 592/530, loss: 0.019476916640996933
2023-01-22 15:28:55.659698: step: 596/530, loss: 0.00475380988791585
2023-01-22 15:28:56.702686: step: 600/530, loss: 0.010056141763925552
2023-01-22 15:28:57.747215: step: 604/530, loss: 0.016903912648558617
2023-01-22 15:28:58.798521: step: 608/530, loss: 0.018231775611639023
2023-01-22 15:28:59.851904: step: 612/530, loss: 0.012347852811217308
2023-01-22 15:29:00.890893: step: 616/530, loss: 0.005395600106567144
2023-01-22 15:29:01.929412: step: 620/530, loss: 0.004717149306088686
2023-01-22 15:29:02.998915: step: 624/530, loss: 0.12797679007053375
2023-01-22 15:29:04.041840: step: 628/530, loss: 0.00015378544048871845
2023-01-22 15:29:05.088279: step: 632/530, loss: 0.03753596544265747
2023-01-22 15:29:06.116156: step: 636/530, loss: 0.0038369777612388134
2023-01-22 15:29:07.155301: step: 640/530, loss: 0.002048106398433447
2023-01-22 15:29:08.203721: step: 644/530, loss: 0.0035770984832197428
2023-01-22 15:29:09.257869: step: 648/530, loss: 0.004911252297461033
2023-01-22 15:29:10.316601: step: 652/530, loss: 0.014666815288364887
2023-01-22 15:29:11.359289: step: 656/530, loss: 0.026117080822587013
2023-01-22 15:29:12.390420: step: 660/530, loss: 0.00010257835674565285
2023-01-22 15:29:13.431611: step: 664/530, loss: 0.0025673743803054094
2023-01-22 15:29:14.466884: step: 668/530, loss: 0.0013420850737020373
2023-01-22 15:29:15.501440: step: 672/530, loss: 0.014642364345490932
2023-01-22 15:29:16.542864: step: 676/530, loss: 0.00024920047144405544
2023-01-22 15:29:17.589764: step: 680/530, loss: 0.0008633178658783436
2023-01-22 15:29:18.648311: step: 684/530, loss: 0.024829626083374023
2023-01-22 15:29:19.699903: step: 688/530, loss: 0.0017917653312906623
2023-01-22 15:29:20.749802: step: 692/530, loss: 0.014723587781190872
2023-01-22 15:29:21.797400: step: 696/530, loss: 0.007423742208629847
2023-01-22 15:29:22.837828: step: 700/530, loss: 0.006035512313246727
2023-01-22 15:29:23.891287: step: 704/530, loss: 0.013542910106480122
2023-01-22 15:29:24.935150: step: 708/530, loss: 0.005212020128965378
2023-01-22 15:29:25.979432: step: 712/530, loss: 0.006673903204500675
2023-01-22 15:29:27.015588: step: 716/530, loss: 0.005888357292860746
2023-01-22 15:29:28.040450: step: 720/530, loss: 0.001742396503686905
2023-01-22 15:29:29.106530: step: 724/530, loss: 0.009401286020874977
2023-01-22 15:29:30.158930: step: 728/530, loss: 0.01121896505355835
2023-01-22 15:29:31.198191: step: 732/530, loss: 0.0128102358430624
2023-01-22 15:29:32.232534: step: 736/530, loss: 0.005448071751743555
2023-01-22 15:29:33.279525: step: 740/530, loss: 0.00313611445017159
2023-01-22 15:29:34.320878: step: 744/530, loss: 0.006634856108576059
2023-01-22 15:29:35.357835: step: 748/530, loss: 0.010065586306154728
2023-01-22 15:29:36.433534: step: 752/530, loss: 0.004102368839085102
2023-01-22 15:29:37.481770: step: 756/530, loss: 0.01233601663261652
2023-01-22 15:29:38.530768: step: 760/530, loss: 0.011272737756371498
2023-01-22 15:29:39.577586: step: 764/530, loss: 0.05126696825027466
2023-01-22 15:29:40.615021: step: 768/530, loss: 0.0011142394505441189
2023-01-22 15:29:41.659948: step: 772/530, loss: 0.010090713389217854
2023-01-22 15:29:42.718241: step: 776/530, loss: 0.0035307412035763264
2023-01-22 15:29:43.774603: step: 780/530, loss: 0.002695351606234908
2023-01-22 15:29:44.830104: step: 784/530, loss: 0.006723582744598389
2023-01-22 15:29:45.883292: step: 788/530, loss: 0.00822901539504528
2023-01-22 15:29:46.945367: step: 792/530, loss: 0.055528152734041214
2023-01-22 15:29:48.004109: step: 796/530, loss: 0.03605087473988533
2023-01-22 15:29:49.061756: step: 800/530, loss: 0.042120590806007385
2023-01-22 15:29:50.111001: step: 804/530, loss: 0.017894096672534943
2023-01-22 15:29:51.148455: step: 808/530, loss: 0.0023750171530991793
2023-01-22 15:29:52.200567: step: 812/530, loss: 0.004050438292324543
2023-01-22 15:29:53.253196: step: 816/530, loss: 0.006625940091907978
2023-01-22 15:29:54.293459: step: 820/530, loss: 0.006925683468580246
2023-01-22 15:29:55.333807: step: 824/530, loss: 0.001783377374522388
2023-01-22 15:29:56.389285: step: 828/530, loss: 0.0013652881607413292
2023-01-22 15:29:57.428665: step: 832/530, loss: 0.02358374185860157
2023-01-22 15:29:58.477939: step: 836/530, loss: 0.00915016420185566
2023-01-22 15:29:59.524843: step: 840/530, loss: 0.021526407450437546
2023-01-22 15:30:00.565577: step: 844/530, loss: 0.0072245243936777115
2023-01-22 15:30:01.604318: step: 848/530, loss: 0.011357876472175121
2023-01-22 15:30:02.661378: step: 852/530, loss: 0.004106700886040926
2023-01-22 15:30:03.722685: step: 856/530, loss: 0.0035375088918954134
2023-01-22 15:30:04.773561: step: 860/530, loss: 0.00566155556589365
2023-01-22 15:30:05.804701: step: 864/530, loss: 0.003982520196586847
2023-01-22 15:30:06.847571: step: 868/530, loss: 0.013738138601183891
2023-01-22 15:30:07.884065: step: 872/530, loss: 0.0007419064058922231
2023-01-22 15:30:08.935890: step: 876/530, loss: 0.0013948254054412246
2023-01-22 15:30:09.998569: step: 880/530, loss: 0.03332987427711487
2023-01-22 15:30:11.036015: step: 884/530, loss: 0.0021401913836598396
2023-01-22 15:30:12.085217: step: 888/530, loss: 0.005231750663369894
2023-01-22 15:30:13.126331: step: 892/530, loss: 0.003046355675905943
2023-01-22 15:30:14.160229: step: 896/530, loss: 0.024647263810038567
2023-01-22 15:30:15.208438: step: 900/530, loss: 0.002115655457600951
2023-01-22 15:30:16.259020: step: 904/530, loss: 0.008259736001491547
2023-01-22 15:30:17.307334: step: 908/530, loss: 0.011261925101280212
2023-01-22 15:30:18.358856: step: 912/530, loss: 0.0063118175603449345
2023-01-22 15:30:19.409145: step: 916/530, loss: 0.002154545858502388
2023-01-22 15:30:20.458464: step: 920/530, loss: 0.013554207980632782
2023-01-22 15:30:21.509733: step: 924/530, loss: 0.007091938052326441
2023-01-22 15:30:22.561970: step: 928/530, loss: 0.0002836388011928648
2023-01-22 15:30:23.619124: step: 932/530, loss: 0.0044651515781879425
2023-01-22 15:30:24.669526: step: 936/530, loss: 0.00012386986054480076
2023-01-22 15:30:25.702440: step: 940/530, loss: 0.0012076901039108634
2023-01-22 15:30:26.741868: step: 944/530, loss: 0.022072333842515945
2023-01-22 15:30:27.791298: step: 948/530, loss: 0.00045723607763648033
2023-01-22 15:30:28.834630: step: 952/530, loss: 0.0022414680570364
2023-01-22 15:30:29.869040: step: 956/530, loss: 0.0011253998382017016
2023-01-22 15:30:30.930414: step: 960/530, loss: 0.0028189762961119413
2023-01-22 15:30:31.996326: step: 964/530, loss: 0.007082141470164061
2023-01-22 15:30:33.044940: step: 968/530, loss: 0.0015966114588081837
2023-01-22 15:30:34.099539: step: 972/530, loss: 0.0062012518756091595
2023-01-22 15:30:35.139040: step: 976/530, loss: 0.003764570225030184
2023-01-22 15:30:36.190313: step: 980/530, loss: 0.005828135646879673
2023-01-22 15:30:37.257816: step: 984/530, loss: 0.0010315744439139962
2023-01-22 15:30:38.291121: step: 988/530, loss: 0.005860264878720045
2023-01-22 15:30:39.343359: step: 992/530, loss: 0.022004127502441406
2023-01-22 15:30:40.382589: step: 996/530, loss: 0.033604830503463745
2023-01-22 15:30:41.429350: step: 1000/530, loss: 0.002532367594540119
2023-01-22 15:30:42.472343: step: 1004/530, loss: 0.017336059361696243
2023-01-22 15:30:43.503053: step: 1008/530, loss: 0.00043345935409888625
2023-01-22 15:30:44.549103: step: 1012/530, loss: 0.009619265794754028
2023-01-22 15:30:45.608991: step: 1016/530, loss: 0.0039932867512106895
2023-01-22 15:30:46.684508: step: 1020/530, loss: 0.0015555518912151456
2023-01-22 15:30:47.729432: step: 1024/530, loss: 0.010970303788781166
2023-01-22 15:30:48.763677: step: 1028/530, loss: 0.014511861838400364
2023-01-22 15:30:49.807202: step: 1032/530, loss: 0.0016790189547464252
2023-01-22 15:30:50.869329: step: 1036/530, loss: 0.0051798587664961815
2023-01-22 15:30:51.905635: step: 1040/530, loss: 0.006959626916795969
2023-01-22 15:30:52.966016: step: 1044/530, loss: 0.007949652150273323
2023-01-22 15:30:54.007729: step: 1048/530, loss: 0.009618671610951424
2023-01-22 15:30:55.050615: step: 1052/530, loss: 0.0061713093891739845
2023-01-22 15:30:56.102403: step: 1056/530, loss: 0.0021594311110675335
2023-01-22 15:30:57.138248: step: 1060/530, loss: 0.006789663806557655
2023-01-22 15:30:58.185884: step: 1064/530, loss: 0.0050207884050905704
2023-01-22 15:30:59.215288: step: 1068/530, loss: 0.009896758943796158
2023-01-22 15:31:00.258762: step: 1072/530, loss: 0.001345921540632844
2023-01-22 15:31:01.278186: step: 1076/530, loss: 0.004463690798729658
2023-01-22 15:31:02.335724: step: 1080/530, loss: 0.008156121708452702
2023-01-22 15:31:03.411021: step: 1084/530, loss: 0.0011514750076457858
2023-01-22 15:31:04.444277: step: 1088/530, loss: 0.012830271385610104
2023-01-22 15:31:05.490501: step: 1092/530, loss: 0.004054079297930002
2023-01-22 15:31:06.526487: step: 1096/530, loss: 0.00606739055365324
2023-01-22 15:31:07.566706: step: 1100/530, loss: 0.0023006938863545656
2023-01-22 15:31:08.605102: step: 1104/530, loss: 0.003015143098309636
2023-01-22 15:31:09.647298: step: 1108/530, loss: 0.0005504557047970593
2023-01-22 15:31:10.702473: step: 1112/530, loss: 0.009094920940697193
2023-01-22 15:31:11.753751: step: 1116/530, loss: 0.00686934357509017
2023-01-22 15:31:12.804646: step: 1120/530, loss: 0.009619171731173992
2023-01-22 15:31:13.852224: step: 1124/530, loss: 0.00299668125808239
2023-01-22 15:31:14.894300: step: 1128/530, loss: 0.0014781909994781017
2023-01-22 15:31:15.954606: step: 1132/530, loss: 0.0006976496079005301
2023-01-22 15:31:16.997893: step: 1136/530, loss: 0.033183954656124115
2023-01-22 15:31:18.038282: step: 1140/530, loss: 0.0017599496059119701
2023-01-22 15:31:19.105211: step: 1144/530, loss: 0.004342691972851753
2023-01-22 15:31:20.141457: step: 1148/530, loss: 0.0027980192098766565
2023-01-22 15:31:21.172895: step: 1152/530, loss: 0.0007540630758740008
2023-01-22 15:31:22.215940: step: 1156/530, loss: 0.005419062450528145
2023-01-22 15:31:23.262154: step: 1160/530, loss: 0.0004526493139564991
2023-01-22 15:31:24.320860: step: 1164/530, loss: 0.007975961081683636
2023-01-22 15:31:25.360349: step: 1168/530, loss: 0.005577439442276955
2023-01-22 15:31:26.421476: step: 1172/530, loss: 0.008031746372580528
2023-01-22 15:31:27.480077: step: 1176/530, loss: 0.006097746547311544
2023-01-22 15:31:28.519413: step: 1180/530, loss: 0.0027745519764721394
2023-01-22 15:31:29.561723: step: 1184/530, loss: 0.0011434364132583141
2023-01-22 15:31:30.599179: step: 1188/530, loss: 0.008492808789014816
2023-01-22 15:31:31.640903: step: 1192/530, loss: 0.020877238363027573
2023-01-22 15:31:32.699757: step: 1196/530, loss: 0.0038514393381774426
2023-01-22 15:31:33.727407: step: 1200/530, loss: 0.0017219502478837967
2023-01-22 15:31:34.785746: step: 1204/530, loss: 0.02591611258685589
2023-01-22 15:31:35.816205: step: 1208/530, loss: 0.0024388241581618786
2023-01-22 15:31:36.866540: step: 1212/530, loss: 0.008103693835437298
2023-01-22 15:31:37.914123: step: 1216/530, loss: 0.0017703513149172068
2023-01-22 15:31:38.959632: step: 1220/530, loss: 0.008272632025182247
2023-01-22 15:31:40.018957: step: 1224/530, loss: 0.0572965033352375
2023-01-22 15:31:41.056159: step: 1228/530, loss: 0.0006666359840892255
2023-01-22 15:31:42.109079: step: 1232/530, loss: 0.004535286221653223
2023-01-22 15:31:43.172054: step: 1236/530, loss: 0.01695200987160206
2023-01-22 15:31:44.207595: step: 1240/530, loss: 0.00516910944133997
2023-01-22 15:31:45.255165: step: 1244/530, loss: 0.011784598231315613
2023-01-22 15:31:46.292986: step: 1248/530, loss: 0.004188059363514185
2023-01-22 15:31:47.342126: step: 1252/530, loss: 0.0030765607953071594
2023-01-22 15:31:48.380893: step: 1256/530, loss: 0.009448111057281494
2023-01-22 15:31:49.425622: step: 1260/530, loss: 0.009654028341174126
2023-01-22 15:31:50.466628: step: 1264/530, loss: 0.0035153296776115894
2023-01-22 15:31:51.516545: step: 1268/530, loss: 0.020746583119034767
2023-01-22 15:31:52.567668: step: 1272/530, loss: 0.01471230573952198
2023-01-22 15:31:53.619818: step: 1276/530, loss: 0.04179929941892624
2023-01-22 15:31:54.654154: step: 1280/530, loss: 0.01124724093824625
2023-01-22 15:31:55.711225: step: 1284/530, loss: 0.012675424106419086
2023-01-22 15:31:56.763589: step: 1288/530, loss: 0.03778376057744026
2023-01-22 15:31:57.833606: step: 1292/530, loss: 0.009309976361691952
2023-01-22 15:31:58.909083: step: 1296/530, loss: 0.0157157015055418
2023-01-22 15:31:59.943910: step: 1300/530, loss: 0.004673982039093971
2023-01-22 15:32:00.988779: step: 1304/530, loss: 0.015413263812661171
2023-01-22 15:32:02.072751: step: 1308/530, loss: 0.03117533028125763
2023-01-22 15:32:03.142081: step: 1312/530, loss: 0.009356277994811535
2023-01-22 15:32:04.175612: step: 1316/530, loss: 0.0004866087401751429
2023-01-22 15:32:05.214253: step: 1320/530, loss: 0.00893944501876831
2023-01-22 15:32:06.257610: step: 1324/530, loss: 0.00032654768438078463
2023-01-22 15:32:07.305708: step: 1328/530, loss: 0.003849738510325551
2023-01-22 15:32:08.347096: step: 1332/530, loss: 0.0030810150783509016
2023-01-22 15:32:09.393481: step: 1336/530, loss: 0.002669693436473608
2023-01-22 15:32:10.436349: step: 1340/530, loss: 0.007426968310028315
2023-01-22 15:32:11.496669: step: 1344/530, loss: 0.00268171401694417
2023-01-22 15:32:12.549048: step: 1348/530, loss: 0.005337265320122242
2023-01-22 15:32:13.599532: step: 1352/530, loss: 0.006659374572336674
2023-01-22 15:32:14.644942: step: 1356/530, loss: 0.008167142979800701
2023-01-22 15:32:15.677130: step: 1360/530, loss: 0.003705062670633197
2023-01-22 15:32:16.714989: step: 1364/530, loss: 1.6634365238132887e-05
2023-01-22 15:32:17.750416: step: 1368/530, loss: 0.00021377854864113033
2023-01-22 15:32:18.779237: step: 1372/530, loss: 0.0007707129116170108
2023-01-22 15:32:19.819062: step: 1376/530, loss: 0.00490058958530426
2023-01-22 15:32:20.876744: step: 1380/530, loss: 0.004877751227468252
2023-01-22 15:32:21.918925: step: 1384/530, loss: 0.005202609114348888
2023-01-22 15:32:22.955538: step: 1388/530, loss: 0.004492300562560558
2023-01-22 15:32:23.991514: step: 1392/530, loss: 0.01172257773578167
2023-01-22 15:32:25.045180: step: 1396/530, loss: 0.0003633679007180035
2023-01-22 15:32:26.085147: step: 1400/530, loss: 0.004841018933802843
2023-01-22 15:32:27.135306: step: 1404/530, loss: 0.0068899798206985
2023-01-22 15:32:28.195686: step: 1408/530, loss: 0.00931174959987402
2023-01-22 15:32:29.258852: step: 1412/530, loss: 0.0010873842984437943
2023-01-22 15:32:30.298744: step: 1416/530, loss: 0.0012167481472715735
2023-01-22 15:32:31.338720: step: 1420/530, loss: 0.002931437687948346
2023-01-22 15:32:32.369769: step: 1424/530, loss: 0.010780932381749153
2023-01-22 15:32:33.421005: step: 1428/530, loss: 0.01095562893897295
2023-01-22 15:32:34.468426: step: 1432/530, loss: 0.005082893185317516
2023-01-22 15:32:35.532005: step: 1436/530, loss: 0.027777351438999176
2023-01-22 15:32:36.555796: step: 1440/530, loss: 0.008518178015947342
2023-01-22 15:32:37.596102: step: 1444/530, loss: 0.008129827678203583
2023-01-22 15:32:38.643218: step: 1448/530, loss: 0.00014765679952688515
2023-01-22 15:32:39.708643: step: 1452/530, loss: 0.003138082567602396
2023-01-22 15:32:40.756808: step: 1456/530, loss: 0.0010229966137558222
2023-01-22 15:32:41.802486: step: 1460/530, loss: 0.0009907567873597145
2023-01-22 15:32:42.858354: step: 1464/530, loss: 0.039192862808704376
2023-01-22 15:32:43.904362: step: 1468/530, loss: 0.003133070422336459
2023-01-22 15:32:44.962175: step: 1472/530, loss: 0.006975098047405481
2023-01-22 15:32:45.984464: step: 1476/530, loss: 0.005560264922678471
2023-01-22 15:32:47.038397: step: 1480/530, loss: 0.002051321789622307
2023-01-22 15:32:48.062527: step: 1484/530, loss: 0.007071810774505138
2023-01-22 15:32:49.110766: step: 1488/530, loss: 0.003039976581931114
2023-01-22 15:32:50.167291: step: 1492/530, loss: 0.0081557035446167
2023-01-22 15:32:51.205578: step: 1496/530, loss: 0.0017127173487097025
2023-01-22 15:32:52.243845: step: 1500/530, loss: 0.004103124141693115
2023-01-22 15:32:53.310876: step: 1504/530, loss: 0.0076441168785095215
2023-01-22 15:32:54.360582: step: 1508/530, loss: 0.003528046887367964
2023-01-22 15:32:55.392556: step: 1512/530, loss: 0.00017241571913473308
2023-01-22 15:32:56.438788: step: 1516/530, loss: 0.03309021145105362
2023-01-22 15:32:57.488578: step: 1520/530, loss: 0.0021175690926611423
2023-01-22 15:32:58.531325: step: 1524/530, loss: 5.452296682051383e-05
2023-01-22 15:32:59.577806: step: 1528/530, loss: 0.005031760782003403
2023-01-22 15:33:00.613512: step: 1532/530, loss: 0.009345093742012978
2023-01-22 15:33:01.641156: step: 1536/530, loss: 0.00022777014237362891
2023-01-22 15:33:02.682748: step: 1540/530, loss: 0.00560781778767705
2023-01-22 15:33:03.734496: step: 1544/530, loss: 0.003189577255398035
2023-01-22 15:33:04.783628: step: 1548/530, loss: 0.034571677446365356
2023-01-22 15:33:05.846714: step: 1552/530, loss: 0.010642732493579388
2023-01-22 15:33:06.880967: step: 1556/530, loss: 0.010461527854204178
2023-01-22 15:33:07.916277: step: 1560/530, loss: 0.006962204352021217
2023-01-22 15:33:08.946798: step: 1564/530, loss: 0.00022156462364364415
2023-01-22 15:33:10.005931: step: 1568/530, loss: 0.01962459459900856
2023-01-22 15:33:11.046471: step: 1572/530, loss: 0.024988656863570213
2023-01-22 15:33:12.105675: step: 1576/530, loss: 0.0006200416246429086
2023-01-22 15:33:13.138208: step: 1580/530, loss: 0.001931198756210506
2023-01-22 15:33:14.201627: step: 1584/530, loss: 0.0051574138924479485
2023-01-22 15:33:15.255101: step: 1588/530, loss: 0.002465372672304511
2023-01-22 15:33:16.307306: step: 1592/530, loss: 0.005042010452598333
2023-01-22 15:33:17.351370: step: 1596/530, loss: 0.001665488351136446
2023-01-22 15:33:18.391600: step: 1600/530, loss: 0.0028303733561187983
2023-01-22 15:33:19.423585: step: 1604/530, loss: 0.0056994580663740635
2023-01-22 15:33:20.452818: step: 1608/530, loss: 0.022639593109488487
2023-01-22 15:33:21.501535: step: 1612/530, loss: 0.011843492276966572
2023-01-22 15:33:22.546527: step: 1616/530, loss: 0.005340182688087225
2023-01-22 15:33:23.594897: step: 1620/530, loss: 0.013917685486376286
2023-01-22 15:33:24.635226: step: 1624/530, loss: 0.0009470715885981917
2023-01-22 15:33:25.709268: step: 1628/530, loss: 0.004929047543555498
2023-01-22 15:33:26.736411: step: 1632/530, loss: 0.003021953394636512
2023-01-22 15:33:27.797629: step: 1636/530, loss: 0.007950888946652412
2023-01-22 15:33:28.855908: step: 1640/530, loss: 0.012573221698403358
2023-01-22 15:33:29.899468: step: 1644/530, loss: 0.002465897938236594
2023-01-22 15:33:30.947299: step: 1648/530, loss: 0.004494422115385532
2023-01-22 15:33:31.992763: step: 1652/530, loss: 0.009269678965210915
2023-01-22 15:33:33.055744: step: 1656/530, loss: 0.007741387467831373
2023-01-22 15:33:34.118192: step: 1660/530, loss: 0.0027917560655623674
2023-01-22 15:33:35.162570: step: 1664/530, loss: 0.010698728263378143
2023-01-22 15:33:36.218941: step: 1668/530, loss: 0.033907629549503326
2023-01-22 15:33:37.263696: step: 1672/530, loss: 0.00538603775203228
2023-01-22 15:33:38.302470: step: 1676/530, loss: 0.013717618770897388
2023-01-22 15:33:39.357564: step: 1680/530, loss: 0.04286370426416397
2023-01-22 15:33:40.399735: step: 1684/530, loss: 0.001058622496202588
2023-01-22 15:33:41.450595: step: 1688/530, loss: 0.007325112819671631
2023-01-22 15:33:42.489222: step: 1692/530, loss: 0.001125282607972622
2023-01-22 15:33:43.552755: step: 1696/530, loss: 0.02404114417731762
2023-01-22 15:33:44.594626: step: 1700/530, loss: 0.009457694366574287
2023-01-22 15:33:45.643599: step: 1704/530, loss: 0.0050507597625255585
2023-01-22 15:33:46.684720: step: 1708/530, loss: 0.011520587839186192
2023-01-22 15:33:47.715132: step: 1712/530, loss: 0.005167321301996708
2023-01-22 15:33:48.753302: step: 1716/530, loss: 0.000495509710162878
2023-01-22 15:33:49.807200: step: 1720/530, loss: 0.04686035215854645
2023-01-22 15:33:50.837252: step: 1724/530, loss: 0.004802131559699774
2023-01-22 15:33:51.885477: step: 1728/530, loss: 0.027188561856746674
2023-01-22 15:33:52.927557: step: 1732/530, loss: 0.0045398324728012085
2023-01-22 15:33:53.988486: step: 1736/530, loss: 0.00954074040055275
2023-01-22 15:33:55.061104: step: 1740/530, loss: 0.02895531803369522
2023-01-22 15:33:56.101176: step: 1744/530, loss: 0.007887580431997776
2023-01-22 15:33:57.141624: step: 1748/530, loss: 0.006940619088709354
2023-01-22 15:33:58.200805: step: 1752/530, loss: 0.014873044565320015
2023-01-22 15:33:59.259857: step: 1756/530, loss: 0.013985712081193924
2023-01-22 15:34:00.309241: step: 1760/530, loss: 0.0066060591489076614
2023-01-22 15:34:01.364678: step: 1764/530, loss: 0.0035264333710074425
2023-01-22 15:34:02.406408: step: 1768/530, loss: 0.007560395170003176
2023-01-22 15:34:03.467137: step: 1772/530, loss: 0.003613527398556471
2023-01-22 15:34:04.509449: step: 1776/530, loss: 0.008606057614088058
2023-01-22 15:34:05.548861: step: 1780/530, loss: 0.005605859681963921
2023-01-22 15:34:06.590573: step: 1784/530, loss: 0.009676764719188213
2023-01-22 15:34:07.625703: step: 1788/530, loss: 0.0035846084356307983
2023-01-22 15:34:08.672394: step: 1792/530, loss: 0.02194957062602043
2023-01-22 15:34:09.698110: step: 1796/530, loss: 0.0011832561576738954
2023-01-22 15:34:10.742904: step: 1800/530, loss: 0.005594130605459213
2023-01-22 15:34:11.783992: step: 1804/530, loss: 0.0002772388979792595
2023-01-22 15:34:12.831912: step: 1808/530, loss: 0.012176196090877056
2023-01-22 15:34:13.874084: step: 1812/530, loss: 0.012571971863508224
2023-01-22 15:34:14.916951: step: 1816/530, loss: 0.0014177965931594372
2023-01-22 15:34:15.963749: step: 1820/530, loss: 0.009228182956576347
2023-01-22 15:34:17.003162: step: 1824/530, loss: 0.0022225137799978256
2023-01-22 15:34:18.043253: step: 1828/530, loss: 0.004359425976872444
2023-01-22 15:34:19.066434: step: 1832/530, loss: 0.0091276029124856
2023-01-22 15:34:20.112289: step: 1836/530, loss: 0.0047169518657028675
2023-01-22 15:34:21.168207: step: 1840/530, loss: 0.006618256215006113
2023-01-22 15:34:22.230335: step: 1844/530, loss: 0.010478464886546135
2023-01-22 15:34:23.279840: step: 1848/530, loss: 0.011988803744316101
2023-01-22 15:34:24.312746: step: 1852/530, loss: 0.0010404754430055618
2023-01-22 15:34:25.342543: step: 1856/530, loss: 0.00516689196228981
2023-01-22 15:34:26.379505: step: 1860/530, loss: 0.008548935875296593
2023-01-22 15:34:27.418964: step: 1864/530, loss: 0.0006177427130751312
2023-01-22 15:34:28.480079: step: 1868/530, loss: 0.009331200271844864
2023-01-22 15:34:29.509203: step: 1872/530, loss: 0.013278198428452015
2023-01-22 15:34:30.575461: step: 1876/530, loss: 0.0013035439187660813
2023-01-22 15:34:31.622092: step: 1880/530, loss: 0.004163411911576986
2023-01-22 15:34:32.683406: step: 1884/530, loss: 0.0009789917385205626
2023-01-22 15:34:33.739920: step: 1888/530, loss: 0.005735444836318493
2023-01-22 15:34:34.781896: step: 1892/530, loss: 0.016716675832867622
2023-01-22 15:34:35.812676: step: 1896/530, loss: 0.010332795791327953
2023-01-22 15:34:36.854616: step: 1900/530, loss: 0.0139173474162817
2023-01-22 15:34:37.899931: step: 1904/530, loss: 0.0194231066852808
2023-01-22 15:34:38.924051: step: 1908/530, loss: 0.009279022924602032
2023-01-22 15:34:39.968539: step: 1912/530, loss: 0.0007891654968261719
2023-01-22 15:34:41.011514: step: 1916/530, loss: 0.012249928899109364
2023-01-22 15:34:42.037125: step: 1920/530, loss: 0.002090978669002652
2023-01-22 15:34:43.071513: step: 1924/530, loss: 0.014435498043894768
2023-01-22 15:34:44.127242: step: 1928/530, loss: 0.03690756484866142
2023-01-22 15:34:45.173247: step: 1932/530, loss: 0.012080319225788116
2023-01-22 15:34:46.207364: step: 1936/530, loss: 0.001113247824832797
2023-01-22 15:34:47.262354: step: 1940/530, loss: 0.017281649634242058
2023-01-22 15:34:48.310808: step: 1944/530, loss: 0.0026332216802984476
2023-01-22 15:34:49.353761: step: 1948/530, loss: 0.00022906468075234443
2023-01-22 15:34:50.396589: step: 1952/530, loss: 0.02236367017030716
2023-01-22 15:34:51.425611: step: 1956/530, loss: 0.009231156669557095
2023-01-22 15:34:52.483087: step: 1960/530, loss: 0.0034171987790614367
2023-01-22 15:34:53.544778: step: 1964/530, loss: 0.003969093319028616
2023-01-22 15:34:54.585894: step: 1968/530, loss: 0.012047340162098408
2023-01-22 15:34:55.621378: step: 1972/530, loss: 0.0021097136195749044
2023-01-22 15:34:56.661336: step: 1976/530, loss: 0.009480580687522888
2023-01-22 15:34:57.701169: step: 1980/530, loss: 0.0002342582738492638
2023-01-22 15:34:58.731795: step: 1984/530, loss: 0.0166630819439888
2023-01-22 15:34:59.784244: step: 1988/530, loss: 0.002624457934871316
2023-01-22 15:35:00.818745: step: 1992/530, loss: 0.004591317847371101
2023-01-22 15:35:01.847109: step: 1996/530, loss: 0.011766986921429634
2023-01-22 15:35:02.892276: step: 2000/530, loss: 0.009464697912335396
2023-01-22 15:35:03.951659: step: 2004/530, loss: 0.013496533036231995
2023-01-22 15:35:04.987282: step: 2008/530, loss: 0.0018837039824575186
2023-01-22 15:35:06.031217: step: 2012/530, loss: 0.0042829993180930614
2023-01-22 15:35:07.066661: step: 2016/530, loss: 0.009306607767939568
2023-01-22 15:35:08.101376: step: 2020/530, loss: 0.012653127312660217
2023-01-22 15:35:09.127986: step: 2024/530, loss: 0.007929597981274128
2023-01-22 15:35:10.174487: step: 2028/530, loss: 0.00470797810703516
2023-01-22 15:35:11.213966: step: 2032/530, loss: 0.0014896313659846783
2023-01-22 15:35:12.253789: step: 2036/530, loss: 0.007710399106144905
2023-01-22 15:35:13.302622: step: 2040/530, loss: 0.0028835029806941748
2023-01-22 15:35:14.343031: step: 2044/530, loss: 0.0026091367471963167
2023-01-22 15:35:15.402480: step: 2048/530, loss: 0.005126492120325565
2023-01-22 15:35:16.434008: step: 2052/530, loss: 0.055129051208496094
2023-01-22 15:35:17.472530: step: 2056/530, loss: 0.01895103231072426
2023-01-22 15:35:18.504802: step: 2060/530, loss: 0.0013110397849231958
2023-01-22 15:35:19.542515: step: 2064/530, loss: 0.003503028303384781
2023-01-22 15:35:20.582887: step: 2068/530, loss: 0.00581095227971673
2023-01-22 15:35:21.620548: step: 2072/530, loss: 0.00411786325275898
2023-01-22 15:35:22.659838: step: 2076/530, loss: 0.005775300785899162
2023-01-22 15:35:23.688530: step: 2080/530, loss: 0.017651807516813278
2023-01-22 15:35:24.722153: step: 2084/530, loss: 0.005945092067122459
2023-01-22 15:35:25.767489: step: 2088/530, loss: 0.017199594527482986
2023-01-22 15:35:26.809947: step: 2092/530, loss: 0.001704596565105021
2023-01-22 15:35:27.859696: step: 2096/530, loss: 0.010168765671551228
2023-01-22 15:35:28.905178: step: 2100/530, loss: 0.0018051320221275091
2023-01-22 15:35:29.938899: step: 2104/530, loss: 0.014632332138717175
2023-01-22 15:35:30.977453: step: 2108/530, loss: 0.011417794041335583
2023-01-22 15:35:32.011269: step: 2112/530, loss: 0.0013669944601133466
2023-01-22 15:35:33.041707: step: 2116/530, loss: 0.0018338194349780679
2023-01-22 15:35:34.070821: step: 2120/530, loss: 0.002114777220413089
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3376890120967742, 'r': 0.3178249525616698, 'f1': 0.3274560117302053}, 'combined': 0.24128337706436176, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3623054692802156, 'r': 0.4075936529402426, 'f1': 0.3836175557084636}, 'combined': 0.29734949294148855, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3118306842766418, 'r': 0.31597264782490836, 'f1': 0.31388800264604466}, 'combined': 0.23128589668655922, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36085633690365515, 'r': 0.4086167344350212, 'f1': 0.38325431643560615}, 'combined': 0.2970679390553502, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3310702866980535, 'r': 0.33609602160049074, 'f1': 0.3335642248276057}, 'combined': 0.24578416566244632, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3628327664635889, 'r': 0.3881777023562661, 'f1': 0.3750775667527686}, 'combined': 0.29072997997104555, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3125, 'r': 0.35714285714285715, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 15:37:59.709475: step: 4/530, loss: 0.006443020887672901
2023-01-22 15:38:00.748899: step: 8/530, loss: 0.00317304371856153
2023-01-22 15:38:01.796562: step: 12/530, loss: 0.008027322590351105
2023-01-22 15:38:02.846823: step: 16/530, loss: 0.01722724735736847
2023-01-22 15:38:03.886675: step: 20/530, loss: 0.01067101676017046
2023-01-22 15:38:04.923752: step: 24/530, loss: 0.018055465072393417
2023-01-22 15:38:05.962947: step: 28/530, loss: 0.010839723981916904
2023-01-22 15:38:07.009541: step: 32/530, loss: 0.04166977480053902
2023-01-22 15:38:08.062883: step: 36/530, loss: 0.004870374221354723
2023-01-22 15:38:09.116351: step: 40/530, loss: 0.004758880473673344
2023-01-22 15:38:10.169827: step: 44/530, loss: 0.0035378627944737673
2023-01-22 15:38:11.215791: step: 48/530, loss: 0.023192228749394417
2023-01-22 15:38:12.283440: step: 52/530, loss: 0.0012242362136021256
2023-01-22 15:38:13.344344: step: 56/530, loss: 0.011190163902938366
2023-01-22 15:38:14.392186: step: 60/530, loss: 0.011091810651123524
2023-01-22 15:38:15.435619: step: 64/530, loss: 0.006872337311506271
2023-01-22 15:38:16.473327: step: 68/530, loss: 0.0040228236466646194
2023-01-22 15:38:17.536324: step: 72/530, loss: 0.014228034764528275
2023-01-22 15:38:18.574845: step: 76/530, loss: 0.0019172192551195621
2023-01-22 15:38:19.613099: step: 80/530, loss: 0.005322155077010393
2023-01-22 15:38:20.669371: step: 84/530, loss: 0.0030950221698731184
2023-01-22 15:38:21.708227: step: 88/530, loss: 0.010197141207754612
2023-01-22 15:38:22.740313: step: 92/530, loss: 0.0058609540574252605
2023-01-22 15:38:23.773734: step: 96/530, loss: 0.0037929746322333813
2023-01-22 15:38:24.813146: step: 100/530, loss: 0.005724242422729731
2023-01-22 15:38:25.843064: step: 104/530, loss: 0.0029091271571815014
2023-01-22 15:38:26.892657: step: 108/530, loss: 0.005397266708314419
2023-01-22 15:38:27.927636: step: 112/530, loss: 0.012336493469774723
2023-01-22 15:38:28.962966: step: 116/530, loss: 0.0025623124092817307
2023-01-22 15:38:30.012855: step: 120/530, loss: 0.0015331917675212026
2023-01-22 15:38:31.066427: step: 124/530, loss: 0.007481038570404053
2023-01-22 15:38:32.123297: step: 128/530, loss: 0.005113583989441395
2023-01-22 15:38:33.158974: step: 132/530, loss: 0.00024479778949171305
2023-01-22 15:38:34.194797: step: 136/530, loss: 0.0010996824130415916
2023-01-22 15:38:35.240769: step: 140/530, loss: 0.0004907758557237685
2023-01-22 15:38:36.290722: step: 144/530, loss: 0.023959992453455925
2023-01-22 15:38:37.348654: step: 148/530, loss: 0.004271361045539379
2023-01-22 15:38:38.392559: step: 152/530, loss: 0.0033653138671070337
2023-01-22 15:38:39.432486: step: 156/530, loss: 0.009489140473306179
2023-01-22 15:38:40.489447: step: 160/530, loss: 0.0012906421907246113
2023-01-22 15:38:41.527307: step: 164/530, loss: 0.007899273186922073
2023-01-22 15:38:42.557901: step: 168/530, loss: 0.007317421957850456
2023-01-22 15:38:43.613460: step: 172/530, loss: 0.003954316955059767
2023-01-22 15:38:44.665783: step: 176/530, loss: 0.0013688422041013837
2023-01-22 15:38:45.702202: step: 180/530, loss: 0.017612328752875328
2023-01-22 15:38:46.763884: step: 184/530, loss: 0.0013631233014166355
2023-01-22 15:38:47.803406: step: 188/530, loss: 0.015199512243270874
2023-01-22 15:38:48.872996: step: 192/530, loss: 0.0046225921250879765
2023-01-22 15:38:49.927295: step: 196/530, loss: 0.0032397285103797913
2023-01-22 15:38:50.986713: step: 200/530, loss: 0.009918945841491222
2023-01-22 15:38:52.027474: step: 204/530, loss: 0.0008518360555171967
2023-01-22 15:38:53.073538: step: 208/530, loss: 0.0040648216381669044
2023-01-22 15:38:54.114269: step: 212/530, loss: 0.003091565566137433
2023-01-22 15:38:55.152188: step: 216/530, loss: 0.000684376631397754
2023-01-22 15:38:56.188194: step: 220/530, loss: 0.0028783048037439585
2023-01-22 15:38:57.232398: step: 224/530, loss: 3.2991629268508404e-05
2023-01-22 15:38:58.292748: step: 228/530, loss: 0.0013385203201323748
2023-01-22 15:38:59.355039: step: 232/530, loss: 0.014296078123152256
2023-01-22 15:39:00.399143: step: 236/530, loss: 0.01647352986037731
2023-01-22 15:39:01.448106: step: 240/530, loss: 0.005481907166540623
2023-01-22 15:39:02.496418: step: 244/530, loss: 0.015058851800858974
2023-01-22 15:39:03.550392: step: 248/530, loss: 0.0016618070658296347
2023-01-22 15:39:04.611956: step: 252/530, loss: 0.002154336078092456
2023-01-22 15:39:05.649979: step: 256/530, loss: 0.010336115956306458
2023-01-22 15:39:06.701652: step: 260/530, loss: 0.003075753804296255
2023-01-22 15:39:07.745516: step: 264/530, loss: 0.003258376382291317
2023-01-22 15:39:08.786282: step: 268/530, loss: 0.0054964106529951096
2023-01-22 15:39:09.827536: step: 272/530, loss: 0.012814630754292011
2023-01-22 15:39:10.870288: step: 276/530, loss: 0.007176750805228949
2023-01-22 15:39:11.912452: step: 280/530, loss: 0.0068128290586173534
2023-01-22 15:39:12.957999: step: 284/530, loss: 0.005921709351241589
2023-01-22 15:39:13.997026: step: 288/530, loss: 0.0019552442245185375
2023-01-22 15:39:15.050424: step: 292/530, loss: 0.013440625742077827
2023-01-22 15:39:16.090979: step: 296/530, loss: 0.004721327684819698
2023-01-22 15:39:17.146591: step: 300/530, loss: 0.014077827334403992
2023-01-22 15:39:18.208559: step: 304/530, loss: 0.01970062404870987
2023-01-22 15:39:19.255707: step: 308/530, loss: 0.008239652030169964
2023-01-22 15:39:20.293031: step: 312/530, loss: 0.008537107147276402
2023-01-22 15:39:21.339507: step: 316/530, loss: 0.024481305852532387
2023-01-22 15:39:22.372881: step: 320/530, loss: 0.0008368688868358731
2023-01-22 15:39:23.415817: step: 324/530, loss: 0.010338678024709225
2023-01-22 15:39:24.455914: step: 328/530, loss: 0.016843730583786964
2023-01-22 15:39:25.498196: step: 332/530, loss: 0.007332807872444391
2023-01-22 15:39:26.567230: step: 336/530, loss: 0.015916921198368073
2023-01-22 15:39:27.619938: step: 340/530, loss: 0.027416598051786423
2023-01-22 15:39:28.665999: step: 344/530, loss: 0.015442077070474625
2023-01-22 15:39:29.706157: step: 348/530, loss: 0.003721862332895398
2023-01-22 15:39:30.737775: step: 352/530, loss: 0.017598453909158707
2023-01-22 15:39:31.792326: step: 356/530, loss: 0.0043983543291687965
2023-01-22 15:39:32.845532: step: 360/530, loss: 0.004982681013643742
2023-01-22 15:39:33.878744: step: 364/530, loss: 0.007238171994686127
2023-01-22 15:39:34.929632: step: 368/530, loss: 0.004519812762737274
2023-01-22 15:39:35.987651: step: 372/530, loss: 0.00703876418992877
2023-01-22 15:39:37.038064: step: 376/530, loss: 0.001871192711405456
2023-01-22 15:39:38.074366: step: 380/530, loss: 0.000646625820081681
2023-01-22 15:39:39.109482: step: 384/530, loss: 0.006171062588691711
2023-01-22 15:39:40.173022: step: 388/530, loss: 0.01040917169302702
2023-01-22 15:39:41.218038: step: 392/530, loss: 0.008386931382119656
2023-01-22 15:39:42.277635: step: 396/530, loss: 0.004858999978750944
2023-01-22 15:39:43.340921: step: 400/530, loss: 0.0013101871591061354
2023-01-22 15:39:44.395844: step: 404/530, loss: 0.0023410820867866278
2023-01-22 15:39:45.443428: step: 408/530, loss: 0.008878541179001331
2023-01-22 15:39:46.479934: step: 412/530, loss: 0.006445564795285463
2023-01-22 15:39:47.521987: step: 416/530, loss: 0.003902277210727334
2023-01-22 15:39:48.583075: step: 420/530, loss: 0.002342721913009882
2023-01-22 15:39:49.629927: step: 424/530, loss: 0.005214674398303032
2023-01-22 15:39:50.686819: step: 428/530, loss: 0.007068710867315531
2023-01-22 15:39:51.731581: step: 432/530, loss: 0.006550357211381197
2023-01-22 15:39:52.793946: step: 436/530, loss: 0.005082268733531237
2023-01-22 15:39:53.835031: step: 440/530, loss: 0.008528613485395908
2023-01-22 15:39:54.875789: step: 444/530, loss: 0.009027947671711445
2023-01-22 15:39:55.914858: step: 448/530, loss: 0.00039609186933375895
2023-01-22 15:39:56.960616: step: 452/530, loss: 0.018422113731503487
2023-01-22 15:39:58.000083: step: 456/530, loss: 0.0049692667089402676
2023-01-22 15:39:59.051714: step: 460/530, loss: 0.012376712635159492
2023-01-22 15:40:00.102013: step: 464/530, loss: 0.002245863899588585
2023-01-22 15:40:01.145815: step: 468/530, loss: 0.008253208361566067
2023-01-22 15:40:02.199515: step: 472/530, loss: 0.01068258285522461
2023-01-22 15:40:03.243965: step: 476/530, loss: 0.015965888276696205
2023-01-22 15:40:04.272285: step: 480/530, loss: 0.0020470772869884968
2023-01-22 15:40:05.303113: step: 484/530, loss: 0.006847771350294352
2023-01-22 15:40:06.346557: step: 488/530, loss: 0.0016153039177879691
2023-01-22 15:40:07.421102: step: 492/530, loss: 0.021052658557891846
2023-01-22 15:40:08.470264: step: 496/530, loss: 0.0015370118198916316
2023-01-22 15:40:09.516182: step: 500/530, loss: 0.003250798210501671
2023-01-22 15:40:10.554324: step: 504/530, loss: 1.4903104101904319e-06
2023-01-22 15:40:11.594302: step: 508/530, loss: 0.003133803838863969
2023-01-22 15:40:12.627722: step: 512/530, loss: 0.015905944630503654
2023-01-22 15:40:13.669772: step: 516/530, loss: 0.00484615471214056
2023-01-22 15:40:14.709588: step: 520/530, loss: 0.004640527069568634
2023-01-22 15:40:15.736950: step: 524/530, loss: 0.004660589620471001
2023-01-22 15:40:16.801641: step: 528/530, loss: 0.007647755090147257
2023-01-22 15:40:17.838963: step: 532/530, loss: 0.0005355802131816745
2023-01-22 15:40:18.866523: step: 536/530, loss: 0.0021537370048463345
2023-01-22 15:40:19.912078: step: 540/530, loss: 0.00440042233094573
2023-01-22 15:40:20.945684: step: 544/530, loss: 0.0011832388117909431
2023-01-22 15:40:22.019988: step: 548/530, loss: 0.008624980226159096
2023-01-22 15:40:23.065037: step: 552/530, loss: 0.003169151721522212
2023-01-22 15:40:24.113952: step: 556/530, loss: 0.00429248483851552
2023-01-22 15:40:25.173314: step: 560/530, loss: 0.0509367473423481
2023-01-22 15:40:26.238191: step: 564/530, loss: 0.01222795620560646
2023-01-22 15:40:27.286480: step: 568/530, loss: 0.01895686239004135
2023-01-22 15:40:28.337213: step: 572/530, loss: 0.004771255422383547
2023-01-22 15:40:29.370088: step: 576/530, loss: 0.0001255811075679958
2023-01-22 15:40:30.419370: step: 580/530, loss: 0.0038223492447286844
2023-01-22 15:40:31.466135: step: 584/530, loss: 0.002349498216062784
2023-01-22 15:40:32.506046: step: 588/530, loss: 0.0036266311071813107
2023-01-22 15:40:33.543075: step: 592/530, loss: 0.00019072755821980536
2023-01-22 15:40:34.585516: step: 596/530, loss: 0.005181869957596064
2023-01-22 15:40:35.643503: step: 600/530, loss: 0.007897347211837769
2023-01-22 15:40:36.694774: step: 604/530, loss: 0.006267680786550045
2023-01-22 15:40:37.742715: step: 608/530, loss: 0.006488562095910311
2023-01-22 15:40:38.785123: step: 612/530, loss: 0.034043002873659134
2023-01-22 15:40:39.814514: step: 616/530, loss: 0.009407413192093372
2023-01-22 15:40:40.856036: step: 620/530, loss: 0.0329255610704422
2023-01-22 15:40:41.898079: step: 624/530, loss: 0.016118628904223442
2023-01-22 15:40:42.951278: step: 628/530, loss: 0.009390652179718018
2023-01-22 15:40:43.979561: step: 632/530, loss: 0.006520468275994062
2023-01-22 15:40:45.012600: step: 636/530, loss: 0.0053998189978301525
2023-01-22 15:40:46.063253: step: 640/530, loss: 0.0018274616450071335
2023-01-22 15:40:47.105490: step: 644/530, loss: 0.010771005414426327
2023-01-22 15:40:48.148763: step: 648/530, loss: 0.007071325089782476
2023-01-22 15:40:49.192364: step: 652/530, loss: 0.007078418042510748
2023-01-22 15:40:50.229756: step: 656/530, loss: 0.005073783919215202
2023-01-22 15:40:51.273074: step: 660/530, loss: 0.006542540155351162
2023-01-22 15:40:52.314006: step: 664/530, loss: 0.007633148226886988
2023-01-22 15:40:53.359583: step: 668/530, loss: 0.019827213138341904
2023-01-22 15:40:54.395709: step: 672/530, loss: 0.002795290434733033
2023-01-22 15:40:55.431594: step: 676/530, loss: 0.0062452093698084354
2023-01-22 15:40:56.473509: step: 680/530, loss: 0.006274326704442501
2023-01-22 15:40:57.514949: step: 684/530, loss: 0.0023696166463196278
2023-01-22 15:40:58.556023: step: 688/530, loss: 0.009987825527787209
2023-01-22 15:40:59.594541: step: 692/530, loss: 0.0011304875370115042
2023-01-22 15:41:00.652310: step: 696/530, loss: 0.0034530742559581995
2023-01-22 15:41:01.695351: step: 700/530, loss: 0.004940489307045937
2023-01-22 15:41:02.753103: step: 704/530, loss: 0.003079000161960721
2023-01-22 15:41:03.784378: step: 708/530, loss: 0.0002853375917766243
2023-01-22 15:41:04.852548: step: 712/530, loss: 0.008336411789059639
2023-01-22 15:41:05.900998: step: 716/530, loss: 0.00026188010815531015
2023-01-22 15:41:06.933888: step: 720/530, loss: 0.00022757177066523582
2023-01-22 15:41:07.976242: step: 724/530, loss: 0.0132845314219594
2023-01-22 15:41:09.007510: step: 728/530, loss: 0.006128624081611633
2023-01-22 15:41:10.050169: step: 732/530, loss: 0.006772862281650305
2023-01-22 15:41:11.095045: step: 736/530, loss: 0.01080066803842783
2023-01-22 15:41:12.145634: step: 740/530, loss: 0.0018177388701587915
2023-01-22 15:41:13.171235: step: 744/530, loss: 0.004945053718984127
2023-01-22 15:41:14.217909: step: 748/530, loss: 0.006223143078386784
2023-01-22 15:41:15.269932: step: 752/530, loss: 0.001619755057618022
2023-01-22 15:41:16.312621: step: 756/530, loss: 0.0038573327474296093
2023-01-22 15:41:17.369397: step: 760/530, loss: 0.0326252356171608
2023-01-22 15:41:18.414206: step: 764/530, loss: 0.02476155012845993
2023-01-22 15:41:19.464918: step: 768/530, loss: 0.0029471255838871002
2023-01-22 15:41:20.517006: step: 772/530, loss: 0.0028389617800712585
2023-01-22 15:41:21.575276: step: 776/530, loss: 0.004500068258494139
2023-01-22 15:41:22.632558: step: 780/530, loss: 0.03257456421852112
2023-01-22 15:41:23.699771: step: 784/530, loss: 0.004930510651320219
2023-01-22 15:41:24.757091: step: 788/530, loss: 0.004476903006434441
2023-01-22 15:41:25.802635: step: 792/530, loss: 0.0011893552727997303
2023-01-22 15:41:26.841188: step: 796/530, loss: 0.012703250162303448
2023-01-22 15:41:27.925066: step: 800/530, loss: 0.004259241744875908
2023-01-22 15:41:28.965771: step: 804/530, loss: 0.009800449945032597
2023-01-22 15:41:30.006871: step: 808/530, loss: 0.005722482688724995
2023-01-22 15:41:31.040141: step: 812/530, loss: 0.006868877448141575
2023-01-22 15:41:32.095359: step: 816/530, loss: 8.425168925896287e-05
2023-01-22 15:41:33.156994: step: 820/530, loss: 0.00022072407591622323
2023-01-22 15:41:34.223059: step: 824/530, loss: 0.007139390800148249
2023-01-22 15:41:35.275423: step: 828/530, loss: 0.0016285597812384367
2023-01-22 15:41:36.327987: step: 832/530, loss: 0.0010771198431029916
2023-01-22 15:41:37.372600: step: 836/530, loss: 0.01445038802921772
2023-01-22 15:41:38.434300: step: 840/530, loss: 0.004866424482315779
2023-01-22 15:41:39.500564: step: 844/530, loss: 0.0052887857891619205
2023-01-22 15:41:40.549339: step: 848/530, loss: 0.0034097700845450163
2023-01-22 15:41:41.604148: step: 852/530, loss: 0.005129923112690449
2023-01-22 15:41:42.652635: step: 856/530, loss: 0.02154039591550827
2023-01-22 15:41:43.715634: step: 860/530, loss: 0.005358666181564331
2023-01-22 15:41:44.771593: step: 864/530, loss: 0.0014924720162525773
2023-01-22 15:41:45.806763: step: 868/530, loss: 0.005080854054540396
2023-01-22 15:41:46.862273: step: 872/530, loss: 0.019516028463840485
2023-01-22 15:41:47.888964: step: 876/530, loss: 0.0014875243650749326
2023-01-22 15:41:48.921660: step: 880/530, loss: 0.013087298721075058
2023-01-22 15:41:49.978972: step: 884/530, loss: 0.010942541062831879
2023-01-22 15:41:51.013513: step: 888/530, loss: 0.007191112730652094
2023-01-22 15:41:52.061523: step: 892/530, loss: 0.003926681354641914
2023-01-22 15:41:53.102229: step: 896/530, loss: 0.0004315909754950553
2023-01-22 15:41:54.137938: step: 900/530, loss: 0.004317270591855049
2023-01-22 15:41:55.175081: step: 904/530, loss: 0.0015492003876715899
2023-01-22 15:41:56.231865: step: 908/530, loss: 0.0026503349654376507
2023-01-22 15:41:57.289780: step: 912/530, loss: 0.004143655765801668
2023-01-22 15:41:58.328206: step: 916/530, loss: 0.006869420874863863
2023-01-22 15:41:59.366616: step: 920/530, loss: 0.0018275945913046598
2023-01-22 15:42:00.413873: step: 924/530, loss: 0.011466322466731071
2023-01-22 15:42:01.486207: step: 928/530, loss: 0.02957484871149063
2023-01-22 15:42:02.528173: step: 932/530, loss: 0.0016847008373588324
2023-01-22 15:42:03.560545: step: 936/530, loss: 0.002385699423030019
2023-01-22 15:42:04.613678: step: 940/530, loss: 0.007095735985785723
2023-01-22 15:42:05.667110: step: 944/530, loss: 0.0009214837336912751
2023-01-22 15:42:06.719556: step: 948/530, loss: 0.007418160326778889
2023-01-22 15:42:07.752453: step: 952/530, loss: 0.006413837429136038
2023-01-22 15:42:08.814529: step: 956/530, loss: 0.0035916813649237156
2023-01-22 15:42:09.848077: step: 960/530, loss: 0.005150137469172478
2023-01-22 15:42:10.902891: step: 964/530, loss: 0.02176482044160366
2023-01-22 15:42:11.950875: step: 968/530, loss: 0.02143683284521103
2023-01-22 15:42:12.993681: step: 972/530, loss: 0.0117194764316082
2023-01-22 15:42:14.045857: step: 976/530, loss: 0.004103964660316706
2023-01-22 15:42:15.089065: step: 980/530, loss: 0.01312597468495369
2023-01-22 15:42:16.109570: step: 984/530, loss: 0.007851426489651203
2023-01-22 15:42:17.149818: step: 988/530, loss: 0.0032611184287816286
2023-01-22 15:42:18.185644: step: 992/530, loss: 0.044866736978292465
2023-01-22 15:42:19.212360: step: 996/530, loss: 0.0005240231403149664
2023-01-22 15:42:20.253941: step: 1000/530, loss: 0.009989464655518532
2023-01-22 15:42:21.299113: step: 1004/530, loss: 0.003820350393652916
2023-01-22 15:42:22.348329: step: 1008/530, loss: 0.009437700733542442
2023-01-22 15:42:23.392061: step: 1012/530, loss: 0.0017604655586183071
2023-01-22 15:42:24.423187: step: 1016/530, loss: 0.0025235763750970364
2023-01-22 15:42:25.454792: step: 1020/530, loss: 0.0037349306512624025
2023-01-22 15:42:26.486887: step: 1024/530, loss: 0.0013715805253013968
2023-01-22 15:42:27.543974: step: 1028/530, loss: 0.011247486807405949
2023-01-22 15:42:28.592366: step: 1032/530, loss: 0.003384503535926342
2023-01-22 15:42:29.643665: step: 1036/530, loss: 0.009993638843297958
2023-01-22 15:42:30.673780: step: 1040/530, loss: 0.0016267661703750491
2023-01-22 15:42:31.707928: step: 1044/530, loss: 0.006866056472063065
2023-01-22 15:42:32.747276: step: 1048/530, loss: 0.016553768888115883
2023-01-22 15:42:33.781711: step: 1052/530, loss: 0.008998163044452667
2023-01-22 15:42:34.837197: step: 1056/530, loss: 0.03297252953052521
2023-01-22 15:42:35.870563: step: 1060/530, loss: 0.021336859092116356
2023-01-22 15:42:36.915736: step: 1064/530, loss: 0.0045573231764137745
2023-01-22 15:42:37.945282: step: 1068/530, loss: 0.0048517524264752865
2023-01-22 15:42:38.995738: step: 1072/530, loss: 5.3648618631996214e-05
2023-01-22 15:42:40.038671: step: 1076/530, loss: 0.0048005483113229275
2023-01-22 15:42:41.079388: step: 1080/530, loss: 0.017492195591330528
2023-01-22 15:42:42.139533: step: 1084/530, loss: 0.002924201311543584
2023-01-22 15:42:43.190857: step: 1088/530, loss: 0.0017691574757918715
2023-01-22 15:42:44.233823: step: 1092/530, loss: 0.006907281931489706
2023-01-22 15:42:45.285371: step: 1096/530, loss: 0.003989166114479303
2023-01-22 15:42:46.315456: step: 1100/530, loss: 0.0014421823434531689
2023-01-22 15:42:47.356475: step: 1104/530, loss: 0.0005379109643399715
2023-01-22 15:42:48.394408: step: 1108/530, loss: 0.029883868992328644
2023-01-22 15:42:49.431670: step: 1112/530, loss: 0.006449008826166391
2023-01-22 15:42:50.461203: step: 1116/530, loss: 0.0029880276415497065
2023-01-22 15:42:51.496200: step: 1120/530, loss: 0.010432815179228783
2023-01-22 15:42:52.555620: step: 1124/530, loss: 0.008568570017814636
2023-01-22 15:42:53.608093: step: 1128/530, loss: 0.0017055398784577847
2023-01-22 15:42:54.645702: step: 1132/530, loss: 0.000813948514405638
2023-01-22 15:42:55.704133: step: 1136/530, loss: 0.004094402771443129
2023-01-22 15:42:56.757811: step: 1140/530, loss: 0.001564537757076323
2023-01-22 15:42:57.816938: step: 1144/530, loss: 0.00947826448827982
2023-01-22 15:42:58.845935: step: 1148/530, loss: 0.0015115514397621155
2023-01-22 15:42:59.899692: step: 1152/530, loss: 0.004356694407761097
2023-01-22 15:43:00.943153: step: 1156/530, loss: 0.008171956986188889
2023-01-22 15:43:01.978120: step: 1160/530, loss: 0.014146357774734497
2023-01-22 15:43:03.020224: step: 1164/530, loss: 0.00569186033681035
2023-01-22 15:43:04.072294: step: 1168/530, loss: 0.02225622348487377
2023-01-22 15:43:05.119231: step: 1172/530, loss: 0.05347214266657829
2023-01-22 15:43:06.150209: step: 1176/530, loss: 0.0071417526341974735
2023-01-22 15:43:07.210316: step: 1180/530, loss: 0.003233895869925618
2023-01-22 15:43:08.245154: step: 1184/530, loss: 0.007582392077893019
2023-01-22 15:43:09.300405: step: 1188/530, loss: 0.03176518902182579
2023-01-22 15:43:10.322735: step: 1192/530, loss: 0.02226613275706768
2023-01-22 15:43:11.380607: step: 1196/530, loss: 0.008522610180079937
2023-01-22 15:43:12.423100: step: 1200/530, loss: 0.004799327347427607
2023-01-22 15:43:13.451619: step: 1204/530, loss: 0.016248898580670357
2023-01-22 15:43:14.490161: step: 1208/530, loss: 0.004367674235254526
2023-01-22 15:43:15.541151: step: 1212/530, loss: 0.005273491144180298
2023-01-22 15:43:16.587097: step: 1216/530, loss: 0.0064430818893015385
2023-01-22 15:43:17.611039: step: 1220/530, loss: 0.006095066666603088
2023-01-22 15:43:18.647741: step: 1224/530, loss: 0.0018999907188117504
2023-01-22 15:43:19.679298: step: 1228/530, loss: 0.001671053934842348
2023-01-22 15:43:20.733882: step: 1232/530, loss: 0.002718855394050479
2023-01-22 15:43:21.759442: step: 1236/530, loss: 0.00263481424190104
2023-01-22 15:43:22.796762: step: 1240/530, loss: 0.0017753038555383682
2023-01-22 15:43:23.851836: step: 1244/530, loss: 0.005754063371568918
2023-01-22 15:43:24.891717: step: 1248/530, loss: 0.0019165900303050876
2023-01-22 15:43:25.924369: step: 1252/530, loss: 0.00745938066393137
2023-01-22 15:43:26.957229: step: 1256/530, loss: 0.0020056532230228186
2023-01-22 15:43:28.005867: step: 1260/530, loss: 0.0032334693241864443
2023-01-22 15:43:29.064181: step: 1264/530, loss: 0.0031998935155570507
2023-01-22 15:43:30.112127: step: 1268/530, loss: 0.007909215055406094
2023-01-22 15:43:31.140121: step: 1272/530, loss: 0.012260696850717068
2023-01-22 15:43:32.169067: step: 1276/530, loss: 0.003334488021209836
2023-01-22 15:43:33.242485: step: 1280/530, loss: 0.009210821241140366
2023-01-22 15:43:34.293608: step: 1284/530, loss: 0.012615853920578957
2023-01-22 15:43:35.339252: step: 1288/530, loss: 0.01089463196694851
2023-01-22 15:43:36.373522: step: 1292/530, loss: 0.0032961037941277027
2023-01-22 15:43:37.408010: step: 1296/530, loss: 0.005276534240692854
2023-01-22 15:43:38.446536: step: 1300/530, loss: 0.001777772675268352
2023-01-22 15:43:39.492591: step: 1304/530, loss: 0.0032450249418616295
2023-01-22 15:43:40.522307: step: 1308/530, loss: 0.008616378530859947
2023-01-22 15:43:41.552474: step: 1312/530, loss: 0.0014581545256078243
2023-01-22 15:43:42.590112: step: 1316/530, loss: 0.00254250830039382
2023-01-22 15:43:43.630715: step: 1320/530, loss: 0.014334144070744514
2023-01-22 15:43:44.691176: step: 1324/530, loss: 0.05240749567747116
2023-01-22 15:43:45.724053: step: 1328/530, loss: 0.0019484309013932943
2023-01-22 15:43:46.776890: step: 1332/530, loss: 0.0003880032163579017
2023-01-22 15:43:47.845250: step: 1336/530, loss: 0.0029791533015668392
2023-01-22 15:43:48.885548: step: 1340/530, loss: 0.0009021844016388059
2023-01-22 15:43:49.930971: step: 1344/530, loss: 0.01908363774418831
2023-01-22 15:43:50.984706: step: 1348/530, loss: 0.008514597080647945
2023-01-22 15:43:52.015890: step: 1352/530, loss: 0.018725385889410973
2023-01-22 15:43:53.049947: step: 1356/530, loss: 9.112127372645773e-06
2023-01-22 15:43:54.086587: step: 1360/530, loss: 0.007284039631485939
2023-01-22 15:43:55.122303: step: 1364/530, loss: 0.0056719123385846615
2023-01-22 15:43:56.156517: step: 1368/530, loss: 0.0002533484366722405
2023-01-22 15:43:57.205400: step: 1372/530, loss: 0.0037012940738350153
2023-01-22 15:43:58.300634: step: 1376/530, loss: 0.006074863485991955
2023-01-22 15:43:59.335767: step: 1380/530, loss: 0.008641631342470646
2023-01-22 15:44:00.382400: step: 1384/530, loss: 0.0013487815158441663
2023-01-22 15:44:01.411733: step: 1388/530, loss: 0.0063590798527002335
2023-01-22 15:44:02.453374: step: 1392/530, loss: 0.01117555983364582
2023-01-22 15:44:03.487028: step: 1396/530, loss: 0.0009980843169614673
2023-01-22 15:44:04.529927: step: 1400/530, loss: 0.01162731647491455
2023-01-22 15:44:05.567080: step: 1404/530, loss: 0.005328621249645948
2023-01-22 15:44:06.602188: step: 1408/530, loss: 0.003818571101874113
2023-01-22 15:44:07.641822: step: 1412/530, loss: 0.004043970722705126
2023-01-22 15:44:08.679127: step: 1416/530, loss: 0.004837583750486374
2023-01-22 15:44:09.731592: step: 1420/530, loss: 0.0059318398125469685
2023-01-22 15:44:10.785655: step: 1424/530, loss: 0.0014331568963825703
2023-01-22 15:44:11.849606: step: 1428/530, loss: 0.007052761502563953
2023-01-22 15:44:12.896375: step: 1432/530, loss: 0.0038785580545663834
2023-01-22 15:44:13.943766: step: 1436/530, loss: 0.0014316333690658212
2023-01-22 15:44:14.996348: step: 1440/530, loss: 0.01590970903635025
2023-01-22 15:44:16.041504: step: 1444/530, loss: 0.0
2023-01-22 15:44:17.092655: step: 1448/530, loss: 0.0015100068412721157
2023-01-22 15:44:18.118541: step: 1452/530, loss: 0.02849707566201687
2023-01-22 15:44:19.167290: step: 1456/530, loss: 0.004898302257061005
2023-01-22 15:44:20.214583: step: 1460/530, loss: 0.010679779574275017
2023-01-22 15:44:21.248331: step: 1464/530, loss: 0.007697803433984518
2023-01-22 15:44:22.288648: step: 1468/530, loss: 0.0028260282706469297
2023-01-22 15:44:23.325936: step: 1472/530, loss: 0.006924837362021208
2023-01-22 15:44:24.368181: step: 1476/530, loss: 0.015142632648348808
2023-01-22 15:44:25.411951: step: 1480/530, loss: 0.0008756800089031458
2023-01-22 15:44:26.455638: step: 1484/530, loss: 0.013374381698668003
2023-01-22 15:44:27.497976: step: 1488/530, loss: 0.005547772627323866
2023-01-22 15:44:28.530834: step: 1492/530, loss: 0.00014117249520495534
2023-01-22 15:44:29.583237: step: 1496/530, loss: 0.09097698330879211
2023-01-22 15:44:30.632001: step: 1500/530, loss: 0.004561661276966333
2023-01-22 15:44:31.675911: step: 1504/530, loss: 0.005302931182086468
2023-01-22 15:44:32.709389: step: 1508/530, loss: 0.00365307554602623
2023-01-22 15:44:33.760932: step: 1512/530, loss: 0.004533231258392334
2023-01-22 15:44:34.781586: step: 1516/530, loss: 0.0005154838436283171
2023-01-22 15:44:35.850990: step: 1520/530, loss: 0.0012163642095401883
2023-01-22 15:44:36.894336: step: 1524/530, loss: 0.010871480219066143
2023-01-22 15:44:37.927685: step: 1528/530, loss: 0.004683495499193668
2023-01-22 15:44:38.965880: step: 1532/530, loss: 0.006208150181919336
2023-01-22 15:44:40.012189: step: 1536/530, loss: 0.026776233687996864
2023-01-22 15:44:41.041120: step: 1540/530, loss: 0.008641284890472889
2023-01-22 15:44:42.090207: step: 1544/530, loss: 0.0034048634115606546
2023-01-22 15:44:43.130481: step: 1548/530, loss: 0.0019314669771119952
2023-01-22 15:44:44.166474: step: 1552/530, loss: 0.01194714568555355
2023-01-22 15:44:45.209027: step: 1556/530, loss: 0.004168049432337284
2023-01-22 15:44:46.246611: step: 1560/530, loss: 0.010259849950671196
2023-01-22 15:44:47.305263: step: 1564/530, loss: 0.002234025625512004
2023-01-22 15:44:48.350916: step: 1568/530, loss: 0.004801113158464432
2023-01-22 15:44:49.392867: step: 1572/530, loss: 0.009865065105259418
2023-01-22 15:44:50.431627: step: 1576/530, loss: 0.02490215189754963
2023-01-22 15:44:51.481048: step: 1580/530, loss: 0.004020696971565485
2023-01-22 15:44:52.531315: step: 1584/530, loss: 0.004061207640916109
2023-01-22 15:44:53.586294: step: 1588/530, loss: 0.007300190627574921
2023-01-22 15:44:54.643542: step: 1592/530, loss: 0.007340441923588514
2023-01-22 15:44:55.694574: step: 1596/530, loss: 0.019605109468102455
2023-01-22 15:44:56.740914: step: 1600/530, loss: 0.007271318696439266
2023-01-22 15:44:57.789073: step: 1604/530, loss: 0.0002542764414101839
2023-01-22 15:44:58.816058: step: 1608/530, loss: 8.247878577094525e-05
2023-01-22 15:44:59.855267: step: 1612/530, loss: 0.002961857244372368
2023-01-22 15:45:00.904389: step: 1616/530, loss: 0.002005236456170678
2023-01-22 15:45:01.954382: step: 1620/530, loss: 0.03412347286939621
2023-01-22 15:45:02.994913: step: 1624/530, loss: 0.005694087594747543
2023-01-22 15:45:04.023671: step: 1628/530, loss: 0.002938526216894388
2023-01-22 15:45:05.079325: step: 1632/530, loss: 0.0035656930413097143
2023-01-22 15:45:06.125417: step: 1636/530, loss: 0.007496458012610674
2023-01-22 15:45:07.164978: step: 1640/530, loss: 0.015275801531970501
2023-01-22 15:45:08.201800: step: 1644/530, loss: 0.00030952124507166445
2023-01-22 15:45:09.262878: step: 1648/530, loss: 0.0016049513360485435
2023-01-22 15:45:10.353480: step: 1652/530, loss: 0.06627373397350311
2023-01-22 15:45:11.412304: step: 1656/530, loss: 0.004653996787965298
2023-01-22 15:45:12.475513: step: 1660/530, loss: 0.01616736687719822
2023-01-22 15:45:13.544248: step: 1664/530, loss: 0.004366998095065355
2023-01-22 15:45:14.595185: step: 1668/530, loss: 0.020630398765206337
2023-01-22 15:45:15.648347: step: 1672/530, loss: 0.008225682191550732
2023-01-22 15:45:16.700227: step: 1676/530, loss: 0.005981991998851299
2023-01-22 15:45:17.746116: step: 1680/530, loss: 0.019214877858757973
2023-01-22 15:45:18.791166: step: 1684/530, loss: 0.004969678353518248
2023-01-22 15:45:19.835609: step: 1688/530, loss: 0.01868354342877865
2023-01-22 15:45:20.883546: step: 1692/530, loss: 0.002672115806490183
2023-01-22 15:45:21.940080: step: 1696/530, loss: 0.03800823539495468
2023-01-22 15:45:22.974248: step: 1700/530, loss: 0.010799265466630459
2023-01-22 15:45:24.033941: step: 1704/530, loss: 0.02098977006971836
2023-01-22 15:45:25.087018: step: 1708/530, loss: 0.004991845693439245
2023-01-22 15:45:26.136731: step: 1712/530, loss: 0.0561748743057251
2023-01-22 15:45:27.183165: step: 1716/530, loss: 0.0015178319299593568
2023-01-22 15:45:28.226784: step: 1720/530, loss: 0.002624554792419076
2023-01-22 15:45:29.294937: step: 1724/530, loss: 0.0014093922218307853
2023-01-22 15:45:30.343848: step: 1728/530, loss: 0.004691623616963625
2023-01-22 15:45:31.389889: step: 1732/530, loss: 0.0004925410030409694
2023-01-22 15:45:32.441495: step: 1736/530, loss: 0.05746084824204445
2023-01-22 15:45:33.492162: step: 1740/530, loss: 0.0037279885727912188
2023-01-22 15:45:34.535878: step: 1744/530, loss: 0.003784911008551717
2023-01-22 15:45:35.592168: step: 1748/530, loss: 0.0002881013788282871
2023-01-22 15:45:36.634955: step: 1752/530, loss: 0.012532379478216171
2023-01-22 15:45:37.674720: step: 1756/530, loss: 0.0021440708078444004
2023-01-22 15:45:38.715033: step: 1760/530, loss: 0.0002058007230516523
2023-01-22 15:45:39.756825: step: 1764/530, loss: 0.0006012417725287378
2023-01-22 15:45:40.799830: step: 1768/530, loss: 0.0016347682103514671
2023-01-22 15:45:41.844677: step: 1772/530, loss: 0.003658115165308118
2023-01-22 15:45:42.879410: step: 1776/530, loss: 0.004269181285053492
2023-01-22 15:45:43.939304: step: 1780/530, loss: 0.00791000947356224
2023-01-22 15:45:44.999973: step: 1784/530, loss: 0.026806047186255455
2023-01-22 15:45:46.026080: step: 1788/530, loss: 0.00948000606149435
2023-01-22 15:45:47.081475: step: 1792/530, loss: 0.011920362710952759
2023-01-22 15:45:48.120774: step: 1796/530, loss: 0.03282766789197922
2023-01-22 15:45:49.176282: step: 1800/530, loss: 0.000908299523871392
2023-01-22 15:45:50.243919: step: 1804/530, loss: 0.0018953416729345918
2023-01-22 15:45:51.285298: step: 1808/530, loss: 0.005275444593280554
2023-01-22 15:45:52.335611: step: 1812/530, loss: 0.008262324146926403
2023-01-22 15:45:53.386329: step: 1816/530, loss: 0.0015323427505791187
2023-01-22 15:45:54.458051: step: 1820/530, loss: 0.004005383234471083
2023-01-22 15:45:55.502871: step: 1824/530, loss: 0.0029299065936356783
2023-01-22 15:45:56.550433: step: 1828/530, loss: 0.0006123905768617988
2023-01-22 15:45:57.603916: step: 1832/530, loss: 0.006294749211519957
2023-01-22 15:45:58.643422: step: 1836/530, loss: 0.006262174341827631
2023-01-22 15:45:59.701086: step: 1840/530, loss: 0.005474178120493889
2023-01-22 15:46:00.743317: step: 1844/530, loss: 0.007734323851764202
2023-01-22 15:46:01.784485: step: 1848/530, loss: 0.017927972599864006
2023-01-22 15:46:02.827855: step: 1852/530, loss: 0.01759951189160347
2023-01-22 15:46:03.907822: step: 1856/530, loss: 0.0019120501819998026
2023-01-22 15:46:04.944915: step: 1860/530, loss: 0.01430408377200365
2023-01-22 15:46:05.977301: step: 1864/530, loss: 0.008443888276815414
2023-01-22 15:46:07.033116: step: 1868/530, loss: 0.029394129291176796
2023-01-22 15:46:08.073034: step: 1872/530, loss: 0.005415191873908043
2023-01-22 15:46:09.103059: step: 1876/530, loss: 0.002877107122913003
2023-01-22 15:46:10.142501: step: 1880/530, loss: 0.01959078013896942
2023-01-22 15:46:11.191339: step: 1884/530, loss: 0.0007007047533988953
2023-01-22 15:46:12.227433: step: 1888/530, loss: 0.024128485471010208
2023-01-22 15:46:13.271892: step: 1892/530, loss: 0.006385908927768469
2023-01-22 15:46:14.322136: step: 1896/530, loss: 0.0003817017131950706
2023-01-22 15:46:15.379171: step: 1900/530, loss: 0.045657165348529816
2023-01-22 15:46:16.417281: step: 1904/530, loss: 0.004568448755890131
2023-01-22 15:46:17.442287: step: 1908/530, loss: 0.00264281895942986
2023-01-22 15:46:18.488410: step: 1912/530, loss: 0.0071998341009020805
2023-01-22 15:46:19.532449: step: 1916/530, loss: 0.001907242345623672
2023-01-22 15:46:20.575627: step: 1920/530, loss: 0.01005789265036583
2023-01-22 15:46:21.614331: step: 1924/530, loss: 0.011069388128817081
2023-01-22 15:46:22.654100: step: 1928/530, loss: 0.00021996225405018777
2023-01-22 15:46:23.691965: step: 1932/530, loss: 0.0023647595662623644
2023-01-22 15:46:24.733475: step: 1936/530, loss: 0.034565169364213943
2023-01-22 15:46:25.764948: step: 1940/530, loss: 0.00128383026458323
2023-01-22 15:46:26.807434: step: 1944/530, loss: 0.003384356154128909
2023-01-22 15:46:27.858445: step: 1948/530, loss: 0.0057662129402160645
2023-01-22 15:46:28.910944: step: 1952/530, loss: 0.004734586924314499
2023-01-22 15:46:29.953147: step: 1956/530, loss: 0.0028805905021727085
2023-01-22 15:46:31.004751: step: 1960/530, loss: 0.005686209537088871
2023-01-22 15:46:32.036597: step: 1964/530, loss: 0.07512509077787399
2023-01-22 15:46:33.086890: step: 1968/530, loss: 0.007569109555333853
2023-01-22 15:46:34.119499: step: 1972/530, loss: 0.011002618819475174
2023-01-22 15:46:35.164016: step: 1976/530, loss: 0.0035132223274558783
2023-01-22 15:46:36.194416: step: 1980/530, loss: 0.005859080236405134
2023-01-22 15:46:37.228331: step: 1984/530, loss: 0.013466530479490757
2023-01-22 15:46:38.266764: step: 1988/530, loss: 0.015540882013738155
2023-01-22 15:46:39.327684: step: 1992/530, loss: 0.015781747177243233
2023-01-22 15:46:40.371928: step: 1996/530, loss: 0.014215042814612389
2023-01-22 15:46:41.418261: step: 2000/530, loss: 0.018209019675850868
2023-01-22 15:46:42.456230: step: 2004/530, loss: 0.004298359155654907
2023-01-22 15:46:43.496010: step: 2008/530, loss: 0.003188485512509942
2023-01-22 15:46:44.538952: step: 2012/530, loss: 0.0033658568281680346
2023-01-22 15:46:45.576520: step: 2016/530, loss: 0.005697112064808607
2023-01-22 15:46:46.607227: step: 2020/530, loss: 0.0010083907982334495
2023-01-22 15:46:47.647139: step: 2024/530, loss: 0.0069275605492293835
2023-01-22 15:46:48.686433: step: 2028/530, loss: 0.009948932565748692
2023-01-22 15:46:49.723631: step: 2032/530, loss: 0.007743677590042353
2023-01-22 15:46:50.775726: step: 2036/530, loss: 0.0029076864011585712
2023-01-22 15:46:51.834276: step: 2040/530, loss: 0.0050680204294621944
2023-01-22 15:46:52.875693: step: 2044/530, loss: 0.002660448430106044
2023-01-22 15:46:53.930054: step: 2048/530, loss: 0.019445575773715973
2023-01-22 15:46:54.969523: step: 2052/530, loss: 0.0033525116741657257
2023-01-22 15:46:56.010357: step: 2056/530, loss: 0.009775001555681229
2023-01-22 15:46:57.039987: step: 2060/530, loss: 0.00822951178997755
2023-01-22 15:46:58.070883: step: 2064/530, loss: 0.03787067160010338
2023-01-22 15:46:59.104269: step: 2068/530, loss: 0.008486567065119743
2023-01-22 15:47:00.161923: step: 2072/530, loss: 0.02640714682638645
2023-01-22 15:47:01.204337: step: 2076/530, loss: 0.003663779702037573
2023-01-22 15:47:02.265028: step: 2080/530, loss: 0.023887792602181435
2023-01-22 15:47:03.337696: step: 2084/530, loss: 0.004308950621634722
2023-01-22 15:47:04.378772: step: 2088/530, loss: 0.005090512800961733
2023-01-22 15:47:05.430337: step: 2092/530, loss: 0.004757900722324848
2023-01-22 15:47:06.486746: step: 2096/530, loss: 0.017214633524417877
2023-01-22 15:47:07.528145: step: 2100/530, loss: 0.0040232776664197445
2023-01-22 15:47:08.571259: step: 2104/530, loss: 0.018518147990107536
2023-01-22 15:47:09.628269: step: 2108/530, loss: 0.0037364864256232977
2023-01-22 15:47:10.694184: step: 2112/530, loss: 0.016615334898233414
2023-01-22 15:47:11.748400: step: 2116/530, loss: 0.04572223871946335
2023-01-22 15:47:12.776128: step: 2120/530, loss: 0.0041249594651162624
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34165419161676647, 'r': 0.32479838709677417, 'f1': 0.33301313229571977}, 'combined': 0.24537809748105666, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3600178148079609, 'r': 0.40667453529318376, 'f1': 0.3819265381087475}, 'combined': 0.2960387520268761, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3145038690236117, 'r': 0.32166524744540176, 'f1': 0.3180442502884178}, 'combined': 0.2343483949493605, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36075471179779667, 'r': 0.41015953905686997, 'f1': 0.3838740460162361}, 'combined': 0.2975483036106711, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3310953851819938, 'r': 0.33989108801415296, 'f1': 0.3354355868604094}, 'combined': 0.24716306400240692, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3621142589234083, 'r': 0.3884074817680308, 'f1': 0.3748003016972217}, 'combined': 0.2905150663873202, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 15:49:43.054112: step: 4/530, loss: 0.0006209381972439587
2023-01-22 15:49:44.102579: step: 8/530, loss: 0.005409138277173042
2023-01-22 15:49:45.127525: step: 12/530, loss: 0.0015448397025465965
2023-01-22 15:49:46.161463: step: 16/530, loss: 0.010289283469319344
2023-01-22 15:49:47.193022: step: 20/530, loss: 0.0035234715323895216
2023-01-22 15:49:48.220780: step: 24/530, loss: 0.0014163681771606207
2023-01-22 15:49:49.250648: step: 28/530, loss: 0.0028939873445779085
2023-01-22 15:49:50.294249: step: 32/530, loss: 0.00071155303157866
2023-01-22 15:49:51.347779: step: 36/530, loss: 0.0013890970731154084
2023-01-22 15:49:52.389690: step: 40/530, loss: 0.01129063218832016
2023-01-22 15:49:53.423097: step: 44/530, loss: 0.008677608333528042
2023-01-22 15:49:54.456546: step: 48/530, loss: 0.003512483322992921
2023-01-22 15:49:55.513567: step: 52/530, loss: 0.007468697149306536
2023-01-22 15:49:56.553952: step: 56/530, loss: 0.0032410991843789816
2023-01-22 15:49:57.594678: step: 60/530, loss: 0.005233378149569035
2023-01-22 15:49:58.624162: step: 64/530, loss: 0.0013106934493407607
2023-01-22 15:49:59.661522: step: 68/530, loss: 0.002669335575774312
2023-01-22 15:50:00.701607: step: 72/530, loss: 0.009931476786732674
2023-01-22 15:50:01.749744: step: 76/530, loss: 0.008454172872006893
2023-01-22 15:50:02.801169: step: 80/530, loss: 0.0012372930068522692
2023-01-22 15:50:03.874059: step: 84/530, loss: 0.006941849831491709
2023-01-22 15:50:04.905335: step: 88/530, loss: 0.003480770858004689
2023-01-22 15:50:05.960951: step: 92/530, loss: 0.003321863943710923
2023-01-22 15:50:07.016927: step: 96/530, loss: 0.006346917245537043
2023-01-22 15:50:08.057584: step: 100/530, loss: 0.004151160828769207
2023-01-22 15:50:09.093997: step: 104/530, loss: 0.010191456414759159
2023-01-22 15:50:10.136883: step: 108/530, loss: 0.00170665024779737
2023-01-22 15:50:11.175751: step: 112/530, loss: 0.010996382683515549
2023-01-22 15:50:12.221546: step: 116/530, loss: 0.005379866808652878
2023-01-22 15:50:13.264230: step: 120/530, loss: 0.013132884167134762
2023-01-22 15:50:14.307826: step: 124/530, loss: 0.002991231856867671
2023-01-22 15:50:15.345562: step: 128/530, loss: 0.005615054629743099
2023-01-22 15:50:16.387932: step: 132/530, loss: 0.0002714320144150406
2023-01-22 15:50:17.432909: step: 136/530, loss: 0.0022933476138859987
2023-01-22 15:50:18.491286: step: 140/530, loss: 0.010669552721083164
2023-01-22 15:50:19.544127: step: 144/530, loss: 0.0037675295025110245
2023-01-22 15:50:20.592048: step: 148/530, loss: 0.009470069780945778
2023-01-22 15:50:21.617436: step: 152/530, loss: 0.0024332383181899786
2023-01-22 15:50:22.653993: step: 156/530, loss: 0.0005654859123751521
2023-01-22 15:50:23.701397: step: 160/530, loss: 0.005316976923495531
2023-01-22 15:50:24.756224: step: 164/530, loss: 0.0028190724551677704
2023-01-22 15:50:25.798392: step: 168/530, loss: 0.018861649557948112
2023-01-22 15:50:26.834146: step: 172/530, loss: 0.004665170796215534
2023-01-22 15:50:27.871789: step: 176/530, loss: 0.006975051015615463
2023-01-22 15:50:28.927182: step: 180/530, loss: 0.005266045220196247
2023-01-22 15:50:29.959268: step: 184/530, loss: 0.0073999869637191296
2023-01-22 15:50:30.998194: step: 188/530, loss: 0.005271570757031441
2023-01-22 15:50:32.027446: step: 192/530, loss: 0.0040196911431849
2023-01-22 15:50:33.083991: step: 196/530, loss: 0.0050012799911201
2023-01-22 15:50:34.127929: step: 200/530, loss: 0.009146283380687237
2023-01-22 15:50:35.191238: step: 204/530, loss: 0.0016826997743919492
2023-01-22 15:50:36.244160: step: 208/530, loss: 0.0018508293433114886
2023-01-22 15:50:37.294712: step: 212/530, loss: 0.002263486385345459
2023-01-22 15:50:38.345925: step: 216/530, loss: 0.003722940571606159
2023-01-22 15:50:39.382449: step: 220/530, loss: 0.004396012052893639
2023-01-22 15:50:40.426045: step: 224/530, loss: 0.0007305858307518065
2023-01-22 15:50:41.465059: step: 228/530, loss: 0.0157123152166605
2023-01-22 15:50:42.498689: step: 232/530, loss: 0.002254583640024066
2023-01-22 15:50:43.557504: step: 236/530, loss: 0.02397082932293415
2023-01-22 15:50:44.604807: step: 240/530, loss: 0.0029040116351097822
2023-01-22 15:50:45.651264: step: 244/530, loss: 0.002293383004143834
2023-01-22 15:50:46.690833: step: 248/530, loss: 0.0024760798551142216
2023-01-22 15:50:47.733315: step: 252/530, loss: 0.0003948241355828941
2023-01-22 15:50:48.770565: step: 256/530, loss: 0.005318681709468365
2023-01-22 15:50:49.806361: step: 260/530, loss: 0.003933188039809465
2023-01-22 15:50:50.850004: step: 264/530, loss: 0.0022918349131941795
2023-01-22 15:50:51.911488: step: 268/530, loss: 0.001917347894050181
2023-01-22 15:50:52.977770: step: 272/530, loss: 0.008362486027181149
2023-01-22 15:50:54.027947: step: 276/530, loss: 0.003461591899394989
2023-01-22 15:50:55.096017: step: 280/530, loss: 0.014286975376307964
2023-01-22 15:50:56.150406: step: 284/530, loss: 0.005234415177255869
2023-01-22 15:50:57.192159: step: 288/530, loss: 0.006149015389382839
2023-01-22 15:50:58.239027: step: 292/530, loss: 0.008718025870621204
2023-01-22 15:50:59.302814: step: 296/530, loss: 0.003898176597431302
2023-01-22 15:51:00.338606: step: 300/530, loss: 0.004752518143504858
2023-01-22 15:51:01.382264: step: 304/530, loss: 0.00403517996892333
2023-01-22 15:51:02.432761: step: 308/530, loss: 0.002216941677033901
2023-01-22 15:51:03.494958: step: 312/530, loss: 0.01114710420370102
2023-01-22 15:51:04.555355: step: 316/530, loss: 0.0022061492782086134
2023-01-22 15:51:05.610522: step: 320/530, loss: 0.0073404936119914055
2023-01-22 15:51:06.650686: step: 324/530, loss: 0.0035091866739094257
2023-01-22 15:51:07.701425: step: 328/530, loss: 0.007213753182440996
2023-01-22 15:51:08.753275: step: 332/530, loss: 0.0007382984622381628
2023-01-22 15:51:09.794604: step: 336/530, loss: 0.002657539676874876
2023-01-22 15:51:10.863826: step: 340/530, loss: 0.015084072947502136
2023-01-22 15:51:11.913307: step: 344/530, loss: 0.002511706668883562
2023-01-22 15:51:12.945254: step: 348/530, loss: 0.008695260621607304
2023-01-22 15:51:14.001413: step: 352/530, loss: 0.0001467554538976401
2023-01-22 15:51:15.045284: step: 356/530, loss: 0.002057208912447095
2023-01-22 15:51:16.085260: step: 360/530, loss: 0.00023294858692679554
2023-01-22 15:51:17.128296: step: 364/530, loss: 0.003144181100651622
2023-01-22 15:51:18.191491: step: 368/530, loss: 0.001276860828511417
2023-01-22 15:51:19.249618: step: 372/530, loss: 0.0028216044884175062
2023-01-22 15:51:20.298619: step: 376/530, loss: 0.010744867846369743
2023-01-22 15:51:21.347716: step: 380/530, loss: 0.012082196772098541
2023-01-22 15:51:22.416680: step: 384/530, loss: 0.01160083245486021
2023-01-22 15:51:23.485060: step: 388/530, loss: 0.004039873369038105
2023-01-22 15:51:24.539028: step: 392/530, loss: 0.002372811082750559
2023-01-22 15:51:25.565236: step: 396/530, loss: 0.0052165803499519825
2023-01-22 15:51:26.624502: step: 400/530, loss: 0.010901889763772488
2023-01-22 15:51:27.690425: step: 404/530, loss: 7.632553024450317e-05
2023-01-22 15:51:28.745549: step: 408/530, loss: 0.007905535399913788
2023-01-22 15:51:29.781850: step: 412/530, loss: 0.023107746616005898
2023-01-22 15:51:30.839950: step: 416/530, loss: 0.004115113522857428
2023-01-22 15:51:31.879945: step: 420/530, loss: 0.005026670638471842
2023-01-22 15:51:32.943420: step: 424/530, loss: 0.0001979036896955222
2023-01-22 15:51:33.979795: step: 428/530, loss: 2.4248825866379775e-05
2023-01-22 15:51:35.026161: step: 432/530, loss: 0.003198995254933834
2023-01-22 15:51:36.071835: step: 436/530, loss: 0.006178115028887987
2023-01-22 15:51:37.126741: step: 440/530, loss: 0.013625619001686573
2023-01-22 15:51:38.162917: step: 444/530, loss: 0.012171263806521893
2023-01-22 15:51:39.198395: step: 448/530, loss: 0.0010392614640295506
2023-01-22 15:51:40.234355: step: 452/530, loss: 0.00856825988739729
2023-01-22 15:51:41.275870: step: 456/530, loss: 0.0022253484930843115
2023-01-22 15:51:42.328558: step: 460/530, loss: 5.9952533774776384e-05
2023-01-22 15:51:43.384163: step: 464/530, loss: 0.00378594477660954
2023-01-22 15:51:44.426255: step: 468/530, loss: 0.002749522915109992
2023-01-22 15:51:45.474044: step: 472/530, loss: 4.452800203580409e-05
2023-01-22 15:51:46.531289: step: 476/530, loss: 0.039248015731573105
2023-01-22 15:51:47.583481: step: 480/530, loss: 0.0035848915576934814
2023-01-22 15:51:48.635356: step: 484/530, loss: 0.010259442962706089
2023-01-22 15:51:49.674233: step: 488/530, loss: 0.0048105353489518166
2023-01-22 15:51:50.725398: step: 492/530, loss: 0.00436235498636961
2023-01-22 15:51:51.762787: step: 496/530, loss: 0.006622565444558859
2023-01-22 15:51:52.815958: step: 500/530, loss: 0.007045813370496035
2023-01-22 15:51:53.871541: step: 504/530, loss: 0.013757947832345963
2023-01-22 15:51:54.931105: step: 508/530, loss: 0.0018067141063511372
2023-01-22 15:51:55.965628: step: 512/530, loss: 0.0005818530917167664
2023-01-22 15:51:57.011750: step: 516/530, loss: 4.2711140849860385e-05
2023-01-22 15:51:58.058482: step: 520/530, loss: 0.0030087523628026247
2023-01-22 15:51:59.111564: step: 524/530, loss: 0.011717578396201134
2023-01-22 15:52:00.167620: step: 528/530, loss: 0.004926319234073162
2023-01-22 15:52:01.205229: step: 532/530, loss: 0.005543484352529049
2023-01-22 15:52:02.245581: step: 536/530, loss: 0.0037364745512604713
2023-01-22 15:52:03.290547: step: 540/530, loss: 0.012873668223619461
2023-01-22 15:52:04.328911: step: 544/530, loss: 0.0017886903369799256
2023-01-22 15:52:05.381204: step: 548/530, loss: 0.0009586654487065971
2023-01-22 15:52:06.428121: step: 552/530, loss: 0.00022563175298273563
2023-01-22 15:52:07.461982: step: 556/530, loss: 0.001532841706648469
2023-01-22 15:52:08.501934: step: 560/530, loss: 0.002271534875035286
2023-01-22 15:52:09.556086: step: 564/530, loss: 0.0018010871717706323
2023-01-22 15:52:10.612874: step: 568/530, loss: 0.0018214972224086523
2023-01-22 15:52:11.669131: step: 572/530, loss: 0.010475671850144863
2023-01-22 15:52:12.717642: step: 576/530, loss: 0.0017840828513726592
2023-01-22 15:52:13.763343: step: 580/530, loss: 0.0007851749542169273
2023-01-22 15:52:14.805537: step: 584/530, loss: 0.010895797982811928
2023-01-22 15:52:15.879832: step: 588/530, loss: 0.0010575465857982635
2023-01-22 15:52:16.920282: step: 592/530, loss: 0.0058981976471841335
2023-01-22 15:52:17.964735: step: 596/530, loss: 0.009622196666896343
2023-01-22 15:52:18.993171: step: 600/530, loss: 0.005134582985192537
2023-01-22 15:52:20.062955: step: 604/530, loss: 0.01785311847925186
2023-01-22 15:52:21.102115: step: 608/530, loss: 0.004243937321007252
2023-01-22 15:52:22.149348: step: 612/530, loss: 0.0037687995936721563
2023-01-22 15:52:23.211279: step: 616/530, loss: 0.008864447474479675
2023-01-22 15:52:24.260937: step: 620/530, loss: 0.002821667119860649
2023-01-22 15:52:25.312862: step: 624/530, loss: 0.009178198873996735
2023-01-22 15:52:26.357104: step: 628/530, loss: 0.0051460848189890385
2023-01-22 15:52:27.407741: step: 632/530, loss: 0.002938908291980624
2023-01-22 15:52:28.448285: step: 636/530, loss: 0.0010824577184394002
2023-01-22 15:52:29.505238: step: 640/530, loss: 0.0030520702712237835
2023-01-22 15:52:30.565670: step: 644/530, loss: 0.005224923603236675
2023-01-22 15:52:31.610479: step: 648/530, loss: 0.0032114519271999598
2023-01-22 15:52:32.660953: step: 652/530, loss: 0.0025177313946187496
2023-01-22 15:52:33.712071: step: 656/530, loss: 0.003136696759611368
2023-01-22 15:52:34.740099: step: 660/530, loss: 0.010835128836333752
2023-01-22 15:52:35.772941: step: 664/530, loss: 0.000787380849942565
2023-01-22 15:52:36.808694: step: 668/530, loss: 0.0014537522802129388
2023-01-22 15:52:37.842086: step: 672/530, loss: 1.820558827603236e-05
2023-01-22 15:52:38.893691: step: 676/530, loss: 0.026104798540472984
2023-01-22 15:52:39.925108: step: 680/530, loss: 0.0033932935912162066
2023-01-22 15:52:40.975448: step: 684/530, loss: 0.0176799725741148
2023-01-22 15:52:42.024351: step: 688/530, loss: 0.0019636424258351326
2023-01-22 15:52:43.094537: step: 692/530, loss: 0.0056401388719677925
2023-01-22 15:52:44.148240: step: 696/530, loss: 0.0040038335137069225
2023-01-22 15:52:45.196519: step: 700/530, loss: 0.00013681819837074727
2023-01-22 15:52:46.249687: step: 704/530, loss: 0.005105760879814625
2023-01-22 15:52:47.303442: step: 708/530, loss: 0.0054229130037128925
2023-01-22 15:52:48.346888: step: 712/530, loss: 0.010855082422494888
2023-01-22 15:52:49.389387: step: 716/530, loss: 0.0009179575135931373
2023-01-22 15:52:50.434204: step: 720/530, loss: 0.003498739330098033
2023-01-22 15:52:51.487735: step: 724/530, loss: 0.03850526362657547
2023-01-22 15:52:52.529090: step: 728/530, loss: 0.0026494988705962896
2023-01-22 15:52:53.582396: step: 732/530, loss: 0.004396180156618357
2023-01-22 15:52:54.649583: step: 736/530, loss: 0.004936248064041138
2023-01-22 15:52:55.708196: step: 740/530, loss: 0.041989538818597794
2023-01-22 15:52:56.750896: step: 744/530, loss: 0.00226575112901628
2023-01-22 15:52:57.796547: step: 748/530, loss: 0.003907649777829647
2023-01-22 15:52:58.878322: step: 752/530, loss: 0.006387569475919008
2023-01-22 15:52:59.941799: step: 756/530, loss: 0.001551038702018559
2023-01-22 15:53:00.995264: step: 760/530, loss: 0.0010991533054038882
2023-01-22 15:53:02.030987: step: 764/530, loss: 0.0021354707423597574
2023-01-22 15:53:03.077714: step: 768/530, loss: 0.0043305279687047005
2023-01-22 15:53:04.118418: step: 772/530, loss: 0.0020844945684075356
2023-01-22 15:53:05.182267: step: 776/530, loss: 0.00469202222302556
2023-01-22 15:53:06.234379: step: 780/530, loss: 0.0034021888859570026
2023-01-22 15:53:07.263702: step: 784/530, loss: 0.0017556928796693683
2023-01-22 15:53:08.310589: step: 788/530, loss: 0.0032824957743287086
2023-01-22 15:53:09.372934: step: 792/530, loss: 0.010158962570130825
2023-01-22 15:53:10.413896: step: 796/530, loss: 0.007878285832703114
2023-01-22 15:53:11.466513: step: 800/530, loss: 0.004742312710732222
2023-01-22 15:53:12.516037: step: 804/530, loss: 0.009991863742470741
2023-01-22 15:53:13.551831: step: 808/530, loss: 0.0013612674083560705
2023-01-22 15:53:14.601594: step: 812/530, loss: 0.0015850623603910208
2023-01-22 15:53:15.661744: step: 816/530, loss: 0.002510854508727789
2023-01-22 15:53:16.704166: step: 820/530, loss: 2.8556860343087465e-05
2023-01-22 15:53:17.754518: step: 824/530, loss: 0.015842730179429054
2023-01-22 15:53:18.807471: step: 828/530, loss: 0.00478518707677722
2023-01-22 15:53:19.841460: step: 832/530, loss: 0.0014124192530289292
2023-01-22 15:53:20.919666: step: 836/530, loss: 0.0008071013726294041
2023-01-22 15:53:21.965656: step: 840/530, loss: 0.0035026699770241976
2023-01-22 15:53:23.022286: step: 844/530, loss: 0.006822494324296713
2023-01-22 15:53:24.073014: step: 848/530, loss: 0.002910975832492113
2023-01-22 15:53:25.112953: step: 852/530, loss: 0.007475380785763264
2023-01-22 15:53:26.156693: step: 856/530, loss: 0.009072045795619488
2023-01-22 15:53:27.200856: step: 860/530, loss: 0.002773278160020709
2023-01-22 15:53:28.242339: step: 864/530, loss: 0.01841503381729126
2023-01-22 15:53:29.275926: step: 868/530, loss: 0.0025660002138465643
2023-01-22 15:53:30.315233: step: 872/530, loss: 0.0016632447950541973
2023-01-22 15:53:31.365043: step: 876/530, loss: 0.008733168244361877
2023-01-22 15:53:32.394931: step: 880/530, loss: 0.0022561594378203154
2023-01-22 15:53:33.424364: step: 884/530, loss: 0.007295619696378708
2023-01-22 15:53:34.483243: step: 888/530, loss: 0.0019046009983867407
2023-01-22 15:53:35.540922: step: 892/530, loss: 0.021429788321256638
2023-01-22 15:53:36.571364: step: 896/530, loss: 0.004059345927089453
2023-01-22 15:53:37.610411: step: 900/530, loss: 0.023798787966370583
2023-01-22 15:53:38.651946: step: 904/530, loss: 0.00261833518743515
2023-01-22 15:53:39.680076: step: 908/530, loss: 0.005177017766982317
2023-01-22 15:53:40.726077: step: 912/530, loss: 0.0010973135940730572
2023-01-22 15:53:41.778686: step: 916/530, loss: 0.003613788168877363
2023-01-22 15:53:42.828644: step: 920/530, loss: 0.003889397718012333
2023-01-22 15:53:43.872346: step: 924/530, loss: 0.010057389736175537
2023-01-22 15:53:44.917882: step: 928/530, loss: 0.0015708347782492638
2023-01-22 15:53:45.961590: step: 932/530, loss: 0.007073408458381891
2023-01-22 15:53:47.006700: step: 936/530, loss: 0.0020177685655653477
2023-01-22 15:53:48.052798: step: 940/530, loss: 0.05060373619198799
2023-01-22 15:53:49.104372: step: 944/530, loss: 0.002321278676390648
2023-01-22 15:53:50.140708: step: 948/530, loss: 0.001859754789620638
2023-01-22 15:53:51.168928: step: 952/530, loss: 0.0010469758417457342
2023-01-22 15:53:52.194244: step: 956/530, loss: 0.00036462058778852224
2023-01-22 15:53:53.255267: step: 960/530, loss: 0.004063926171511412
2023-01-22 15:53:54.287481: step: 964/530, loss: 0.0006449102656915784
2023-01-22 15:53:55.345355: step: 968/530, loss: 0.04210960492491722
2023-01-22 15:53:56.400948: step: 972/530, loss: 0.011882578022778034
2023-01-22 15:53:57.456070: step: 976/530, loss: 0.004899441264569759
2023-01-22 15:53:58.502788: step: 980/530, loss: 0.00011892046313732862
2023-01-22 15:53:59.552565: step: 984/530, loss: 0.0013491458958014846
2023-01-22 15:54:00.611980: step: 988/530, loss: 0.00580895971506834
2023-01-22 15:54:01.645373: step: 992/530, loss: 0.0039952704682946205
2023-01-22 15:54:02.706373: step: 996/530, loss: 0.006136264652013779
2023-01-22 15:54:03.729517: step: 1000/530, loss: 0.0034204628318548203
2023-01-22 15:54:04.771613: step: 1004/530, loss: 0.008623231202363968
2023-01-22 15:54:05.809108: step: 1008/530, loss: 0.0007546083070337772
2023-01-22 15:54:06.847222: step: 1012/530, loss: 0.009424910880625248
2023-01-22 15:54:07.881779: step: 1016/530, loss: 0.006336224731057882
2023-01-22 15:54:08.953771: step: 1020/530, loss: 0.01862392947077751
2023-01-22 15:54:09.998969: step: 1024/530, loss: 0.003281189827248454
2023-01-22 15:54:11.024189: step: 1028/530, loss: 0.002109914319589734
2023-01-22 15:54:12.062184: step: 1032/530, loss: 0.0030730459839105606
2023-01-22 15:54:13.124879: step: 1036/530, loss: 0.005453116726130247
2023-01-22 15:54:14.167454: step: 1040/530, loss: 0.0020153226796537638
2023-01-22 15:54:15.189876: step: 1044/530, loss: 0.0016653892816975713
2023-01-22 15:54:16.249684: step: 1048/530, loss: 0.00027228944236412644
2023-01-22 15:54:17.294532: step: 1052/530, loss: 0.0072599113918840885
2023-01-22 15:54:18.331549: step: 1056/530, loss: 0.0001541073725093156
2023-01-22 15:54:19.373776: step: 1060/530, loss: 0.001273548579774797
2023-01-22 15:54:20.421397: step: 1064/530, loss: 0.0017354830633848906
2023-01-22 15:54:21.462539: step: 1068/530, loss: 0.007379298098385334
2023-01-22 15:54:22.513203: step: 1072/530, loss: 0.007031646091490984
2023-01-22 15:54:23.574611: step: 1076/530, loss: 0.006455523893237114
2023-01-22 15:54:24.618222: step: 1080/530, loss: 0.01946997083723545
2023-01-22 15:54:25.696096: step: 1084/530, loss: 0.006793544627726078
2023-01-22 15:54:26.727283: step: 1088/530, loss: 0.0008276875596493483
2023-01-22 15:54:27.766542: step: 1092/530, loss: 0.0005426559946499765
2023-01-22 15:54:28.796483: step: 1096/530, loss: 0.010740218684077263
2023-01-22 15:54:29.848350: step: 1100/530, loss: 0.03218856453895569
2023-01-22 15:54:30.892740: step: 1104/530, loss: 0.006087642628699541
2023-01-22 15:54:31.939654: step: 1108/530, loss: 0.003980571404099464
2023-01-22 15:54:32.992355: step: 1112/530, loss: 0.00027696104370988905
2023-01-22 15:54:34.037340: step: 1116/530, loss: 0.0037075176369398832
2023-01-22 15:54:35.082454: step: 1120/530, loss: 0.012608006596565247
2023-01-22 15:54:36.140118: step: 1124/530, loss: 0.003824002342298627
2023-01-22 15:54:37.183572: step: 1128/530, loss: 0.001979410881176591
2023-01-22 15:54:38.228999: step: 1132/530, loss: 0.008721797727048397
2023-01-22 15:54:39.267635: step: 1136/530, loss: 0.004777163732796907
2023-01-22 15:54:40.314251: step: 1140/530, loss: 0.001700170454569161
2023-01-22 15:54:41.381250: step: 1144/530, loss: 0.0046541024930775166
2023-01-22 15:54:42.427671: step: 1148/530, loss: 0.10870716720819473
2023-01-22 15:54:43.458624: step: 1152/530, loss: 0.00021920898871030658
2023-01-22 15:54:44.492497: step: 1156/530, loss: 0.011056621558964252
2023-01-22 15:54:45.554773: step: 1160/530, loss: 0.011159135028719902
2023-01-22 15:54:46.578648: step: 1164/530, loss: 0.0024081047158688307
2023-01-22 15:54:47.611575: step: 1168/530, loss: 0.0057925088331103325
2023-01-22 15:54:48.665009: step: 1172/530, loss: 0.007608622312545776
2023-01-22 15:54:49.705845: step: 1176/530, loss: 1.2015492529826588e-06
2023-01-22 15:54:50.740825: step: 1180/530, loss: 0.020681289955973625
2023-01-22 15:54:51.796673: step: 1184/530, loss: 0.006975239608436823
2023-01-22 15:54:52.839163: step: 1188/530, loss: 0.0026035597547888756
2023-01-22 15:54:53.885559: step: 1192/530, loss: 0.007371784653514624
2023-01-22 15:54:54.927771: step: 1196/530, loss: 0.03399481251835823
2023-01-22 15:54:55.966244: step: 1200/530, loss: 0.011416000314056873
2023-01-22 15:54:57.001124: step: 1204/530, loss: 0.010691234841942787
2023-01-22 15:54:58.045862: step: 1208/530, loss: 0.0019936019089072943
2023-01-22 15:54:59.088437: step: 1212/530, loss: 0.001048463280312717
2023-01-22 15:55:00.149129: step: 1216/530, loss: 0.007577843498438597
2023-01-22 15:55:01.189807: step: 1220/530, loss: 0.004762694239616394
2023-01-22 15:55:02.230605: step: 1224/530, loss: 0.0044346340000629425
2023-01-22 15:55:03.264907: step: 1228/530, loss: 0.00024039229901973158
2023-01-22 15:55:04.321111: step: 1232/530, loss: 0.005222438368946314
2023-01-22 15:55:05.364588: step: 1236/530, loss: 0.0035616266541182995
2023-01-22 15:55:06.405514: step: 1240/530, loss: 0.004955634009093046
2023-01-22 15:55:07.439457: step: 1244/530, loss: 0.010248035192489624
2023-01-22 15:55:08.482635: step: 1248/530, loss: 0.00953050795942545
2023-01-22 15:55:09.539472: step: 1252/530, loss: 0.010992596857249737
2023-01-22 15:55:10.568662: step: 1256/530, loss: 0.005536581855267286
2023-01-22 15:55:11.624425: step: 1260/530, loss: 0.0011358698830008507
2023-01-22 15:55:12.661713: step: 1264/530, loss: 0.002192847430706024
2023-01-22 15:55:13.706726: step: 1268/530, loss: 0.006236623506993055
2023-01-22 15:55:14.755142: step: 1272/530, loss: 0.002121654571965337
2023-01-22 15:55:15.798660: step: 1276/530, loss: 0.00792581308633089
2023-01-22 15:55:16.846418: step: 1280/530, loss: 0.0014265021309256554
2023-01-22 15:55:17.884223: step: 1284/530, loss: 0.007405952550470829
2023-01-22 15:55:18.952820: step: 1288/530, loss: 0.0682988241314888
2023-01-22 15:55:19.999028: step: 1292/530, loss: 6.156717427074909e-05
2023-01-22 15:55:21.032576: step: 1296/530, loss: 0.002823916729539633
2023-01-22 15:55:22.078032: step: 1300/530, loss: 0.017848273739218712
2023-01-22 15:55:23.130342: step: 1304/530, loss: 0.0051645454950630665
2023-01-22 15:55:24.154968: step: 1308/530, loss: 0.0030845499131828547
2023-01-22 15:55:25.192134: step: 1312/530, loss: 0.004272168967872858
2023-01-22 15:55:26.249969: step: 1316/530, loss: 0.006515360437333584
2023-01-22 15:55:27.305263: step: 1320/530, loss: 0.007780950050801039
2023-01-22 15:55:28.360811: step: 1324/530, loss: 0.02745509147644043
2023-01-22 15:55:29.392216: step: 1328/530, loss: 0.009014702402055264
2023-01-22 15:55:30.434776: step: 1332/530, loss: 0.0016517748590558767
2023-01-22 15:55:31.477302: step: 1336/530, loss: 0.004722333047538996
2023-01-22 15:55:32.533291: step: 1340/530, loss: 0.011146903038024902
2023-01-22 15:55:33.577955: step: 1344/530, loss: 0.007080514915287495
2023-01-22 15:55:34.638491: step: 1348/530, loss: 0.004426012746989727
2023-01-22 15:55:35.699448: step: 1352/530, loss: 0.011999353766441345
2023-01-22 15:55:36.758521: step: 1356/530, loss: 0.006804373115301132
2023-01-22 15:55:37.801775: step: 1360/530, loss: 0.006184310186654329
2023-01-22 15:55:38.866652: step: 1364/530, loss: 0.00030462408903986216
2023-01-22 15:55:39.910306: step: 1368/530, loss: 0.004529778379946947
2023-01-22 15:55:40.968264: step: 1372/530, loss: 0.002193887485191226
2023-01-22 15:55:41.996914: step: 1376/530, loss: 0.004749293439090252
2023-01-22 15:55:43.035912: step: 1380/530, loss: 0.011622396297752857
2023-01-22 15:55:44.070768: step: 1384/530, loss: 0.00034916159347631037
2023-01-22 15:55:45.107964: step: 1388/530, loss: 0.006426604930311441
2023-01-22 15:55:46.150598: step: 1392/530, loss: 0.0006140635814517736
2023-01-22 15:55:47.204583: step: 1396/530, loss: 0.006234284956008196
2023-01-22 15:55:48.243894: step: 1400/530, loss: 0.0029865936376154423
2023-01-22 15:55:49.290387: step: 1404/530, loss: 0.01206700224429369
2023-01-22 15:55:50.325850: step: 1408/530, loss: 0.004013594705611467
2023-01-22 15:55:51.356148: step: 1412/530, loss: 0.0014471722533926368
2023-01-22 15:55:52.400390: step: 1416/530, loss: 0.005429612472653389
2023-01-22 15:55:53.442493: step: 1420/530, loss: 0.007490025833249092
2023-01-22 15:55:54.494005: step: 1424/530, loss: 0.012800934724509716
2023-01-22 15:55:55.533360: step: 1428/530, loss: 0.0016171160386875272
2023-01-22 15:55:56.622256: step: 1432/530, loss: 0.0018943685572594404
2023-01-22 15:55:57.675225: step: 1436/530, loss: 0.008185381069779396
2023-01-22 15:55:58.724816: step: 1440/530, loss: 0.001986532937735319
2023-01-22 15:55:59.774854: step: 1444/530, loss: 0.001074748346582055
2023-01-22 15:56:00.831921: step: 1448/530, loss: 0.011742767877876759
2023-01-22 15:56:01.890124: step: 1452/530, loss: 0.0008364357054233551
2023-01-22 15:56:02.948377: step: 1456/530, loss: 0.015845948830246925
2023-01-22 15:56:03.978195: step: 1460/530, loss: 0.0010480317287147045
2023-01-22 15:56:05.022924: step: 1464/530, loss: 0.043194811791181564
2023-01-22 15:56:06.056021: step: 1468/530, loss: 0.0013388304505497217
2023-01-22 15:56:07.115029: step: 1472/530, loss: 0.0005215198616497219
2023-01-22 15:56:08.160412: step: 1476/530, loss: 0.0014749027322977781
2023-01-22 15:56:09.206387: step: 1480/530, loss: 0.006819496396929026
2023-01-22 15:56:10.261824: step: 1484/530, loss: 0.003423040732741356
2023-01-22 15:56:11.315014: step: 1488/530, loss: 0.016143960878252983
2023-01-22 15:56:12.366033: step: 1492/530, loss: 0.008534249849617481
2023-01-22 15:56:13.433389: step: 1496/530, loss: 0.004776821006089449
2023-01-22 15:56:14.486708: step: 1500/530, loss: 0.009061519987881184
2023-01-22 15:56:15.520856: step: 1504/530, loss: 0.0018091071397066116
2023-01-22 15:56:16.564530: step: 1508/530, loss: 0.005445644725114107
2023-01-22 15:56:17.633475: step: 1512/530, loss: 0.001814851420931518
2023-01-22 15:56:18.684807: step: 1516/530, loss: 0.0014321933267638087
2023-01-22 15:56:19.737460: step: 1520/530, loss: 0.00572019862011075
2023-01-22 15:56:20.782211: step: 1524/530, loss: 0.012708782218396664
2023-01-22 15:56:21.830708: step: 1528/530, loss: 0.02738189697265625
2023-01-22 15:56:22.885454: step: 1532/530, loss: 0.003529068548232317
2023-01-22 15:56:23.934865: step: 1536/530, loss: 0.005960469599813223
2023-01-22 15:56:24.985914: step: 1540/530, loss: 0.046080682426691055
2023-01-22 15:56:26.045041: step: 1544/530, loss: 0.0028783243615180254
2023-01-22 15:56:27.096052: step: 1548/530, loss: 0.0029748750384896994
2023-01-22 15:56:28.151737: step: 1552/530, loss: 0.027270717546343803
2023-01-22 15:56:29.208886: step: 1556/530, loss: 0.01137593761086464
2023-01-22 15:56:30.265488: step: 1560/530, loss: 0.006451827008277178
2023-01-22 15:56:31.303862: step: 1564/530, loss: 0.0033235889859497547
2023-01-22 15:56:32.358637: step: 1568/530, loss: 0.008284997195005417
2023-01-22 15:56:33.400027: step: 1572/530, loss: 0.011531743220984936
2023-01-22 15:56:34.447758: step: 1576/530, loss: 0.021130923181772232
2023-01-22 15:56:35.482556: step: 1580/530, loss: 0.010799339041113853
2023-01-22 15:56:36.557925: step: 1584/530, loss: 0.003518350888043642
2023-01-22 15:56:37.621846: step: 1588/530, loss: 0.0009050051448866725
2023-01-22 15:56:38.649908: step: 1592/530, loss: 0.0030564155895262957
2023-01-22 15:56:39.681326: step: 1596/530, loss: 0.0033086545299738646
2023-01-22 15:56:40.733574: step: 1600/530, loss: 0.006984124891459942
2023-01-22 15:56:41.782613: step: 1604/530, loss: 0.005573161877691746
2023-01-22 15:56:42.817897: step: 1608/530, loss: 0.0024158877786248922
2023-01-22 15:56:43.866573: step: 1612/530, loss: 0.0025379215367138386
2023-01-22 15:56:44.914664: step: 1616/530, loss: 0.00045806291745975614
2023-01-22 15:56:45.970709: step: 1620/530, loss: 0.0020665458869189024
2023-01-22 15:56:47.013403: step: 1624/530, loss: 0.00010721674334490672
2023-01-22 15:56:48.066175: step: 1628/530, loss: 0.0020372758153826
2023-01-22 15:56:49.116881: step: 1632/530, loss: 0.0029343198984861374
2023-01-22 15:56:50.184732: step: 1636/530, loss: 0.02106183022260666
2023-01-22 15:56:51.246062: step: 1640/530, loss: 0.011678473092615604
2023-01-22 15:56:52.288704: step: 1644/530, loss: 4.8800025979289785e-05
2023-01-22 15:56:53.353984: step: 1648/530, loss: 0.0067364429123699665
2023-01-22 15:56:54.394420: step: 1652/530, loss: 0.02513057179749012
2023-01-22 15:56:55.428958: step: 1656/530, loss: 0.0007702919538132846
2023-01-22 15:56:56.467389: step: 1660/530, loss: 0.011085661128163338
2023-01-22 15:56:57.503417: step: 1664/530, loss: 0.018413681536912918
2023-01-22 15:56:58.542458: step: 1668/530, loss: 0.011836964637041092
2023-01-22 15:56:59.585580: step: 1672/530, loss: 0.02277711220085621
2023-01-22 15:57:00.632979: step: 1676/530, loss: 0.005979735404253006
2023-01-22 15:57:01.689320: step: 1680/530, loss: 0.007160399109125137
2023-01-22 15:57:02.758770: step: 1684/530, loss: 0.016264263540506363
2023-01-22 15:57:03.813729: step: 1688/530, loss: 0.03354169800877571
2023-01-22 15:57:04.864176: step: 1692/530, loss: 0.000819491920992732
2023-01-22 15:57:05.937001: step: 1696/530, loss: 0.0013716618996113539
2023-01-22 15:57:06.977542: step: 1700/530, loss: 0.0042462474666535854
2023-01-22 15:57:08.007160: step: 1704/530, loss: 0.0013388522202149034
2023-01-22 15:57:09.060963: step: 1708/530, loss: 0.01728525198996067
2023-01-22 15:57:10.125610: step: 1712/530, loss: 0.004231453873217106
2023-01-22 15:57:11.160485: step: 1716/530, loss: 0.007353954017162323
2023-01-22 15:57:12.220570: step: 1720/530, loss: 0.000880862062331289
2023-01-22 15:57:13.274497: step: 1724/530, loss: 0.004798652604222298
2023-01-22 15:57:14.321319: step: 1728/530, loss: 0.004262755159288645
2023-01-22 15:57:15.356646: step: 1732/530, loss: 0.004507008474320173
2023-01-22 15:57:16.404098: step: 1736/530, loss: 0.0017209872603416443
2023-01-22 15:57:17.438742: step: 1740/530, loss: 0.0009803662542253733
2023-01-22 15:57:18.472785: step: 1744/530, loss: 0.0034610687289386988
2023-01-22 15:57:19.508360: step: 1748/530, loss: 0.002741872565820813
2023-01-22 15:57:20.546574: step: 1752/530, loss: 0.00200418708845973
2023-01-22 15:57:21.582768: step: 1756/530, loss: 0.0001717911654850468
2023-01-22 15:57:22.617891: step: 1760/530, loss: 0.006707558874040842
2023-01-22 15:57:23.658568: step: 1764/530, loss: 0.009112262167036533
2023-01-22 15:57:24.700506: step: 1768/530, loss: 0.0028560529462993145
2023-01-22 15:57:25.746353: step: 1772/530, loss: 0.000468336307676509
2023-01-22 15:57:26.789182: step: 1776/530, loss: 0.003938440699130297
2023-01-22 15:57:27.813913: step: 1780/530, loss: 0.022959338501095772
2023-01-22 15:57:28.844766: step: 1784/530, loss: 0.003944477066397667
2023-01-22 15:57:29.881449: step: 1788/530, loss: 0.00030886937747709453
2023-01-22 15:57:30.926458: step: 1792/530, loss: 0.004274178296327591
2023-01-22 15:57:31.965209: step: 1796/530, loss: 0.006106200162321329
2023-01-22 15:57:33.012781: step: 1800/530, loss: 0.0010420207399874926
2023-01-22 15:57:34.082105: step: 1804/530, loss: 0.001296434667892754
2023-01-22 15:57:35.120043: step: 1808/530, loss: 0.0028293104842305183
2023-01-22 15:57:36.183749: step: 1812/530, loss: 0.0039056281093508005
2023-01-22 15:57:37.216656: step: 1816/530, loss: 0.007308308966457844
2023-01-22 15:57:38.258651: step: 1820/530, loss: 0.0011681515024974942
2023-01-22 15:57:39.296989: step: 1824/530, loss: 0.016207758337259293
2023-01-22 15:57:40.349456: step: 1828/530, loss: 0.009423826821148396
2023-01-22 15:57:41.395446: step: 1832/530, loss: 0.006282747723162174
2023-01-22 15:57:42.445050: step: 1836/530, loss: 0.012160269543528557
2023-01-22 15:57:43.495513: step: 1840/530, loss: 0.008822774514555931
2023-01-22 15:57:44.546481: step: 1844/530, loss: 0.02734699286520481
2023-01-22 15:57:45.578061: step: 1848/530, loss: 0.0004367501533124596
2023-01-22 15:57:46.644104: step: 1852/530, loss: 0.04016534239053726
2023-01-22 15:57:47.689644: step: 1856/530, loss: 0.01248511765152216
2023-01-22 15:57:48.741604: step: 1860/530, loss: 8.790144784143195e-05
2023-01-22 15:57:49.790229: step: 1864/530, loss: 0.007806339301168919
2023-01-22 15:57:50.835447: step: 1868/530, loss: 0.0162203311920166
2023-01-22 15:57:51.881434: step: 1872/530, loss: 0.004363378044217825
2023-01-22 15:57:52.937106: step: 1876/530, loss: 0.007265110034495592
2023-01-22 15:57:53.974410: step: 1880/530, loss: 0.00010416420991532505
2023-01-22 15:57:55.017505: step: 1884/530, loss: 0.02013254165649414
2023-01-22 15:57:56.069533: step: 1888/530, loss: 0.006840502377599478
2023-01-22 15:57:57.115696: step: 1892/530, loss: 0.008903981186449528
2023-01-22 15:57:58.153934: step: 1896/530, loss: 0.0036086742766201496
2023-01-22 15:57:59.203251: step: 1900/530, loss: 0.0035077142529189587
2023-01-22 15:58:00.254111: step: 1904/530, loss: 0.02203163132071495
2023-01-22 15:58:01.297061: step: 1908/530, loss: 0.0036880257539451122
2023-01-22 15:58:02.338027: step: 1912/530, loss: 0.0011350263375788927
2023-01-22 15:58:03.408883: step: 1916/530, loss: 0.042768143117427826
2023-01-22 15:58:04.460079: step: 1920/530, loss: 0.007512848824262619
2023-01-22 15:58:05.488994: step: 1924/530, loss: 0.0049897609278559685
2023-01-22 15:58:06.522382: step: 1928/530, loss: 0.006997285410761833
2023-01-22 15:58:07.563658: step: 1932/530, loss: 0.004432953894138336
2023-01-22 15:58:08.622037: step: 1936/530, loss: 0.002418037038296461
2023-01-22 15:58:09.667705: step: 1940/530, loss: 0.009223580360412598
2023-01-22 15:58:10.713917: step: 1944/530, loss: 0.000389400142012164
2023-01-22 15:58:11.748699: step: 1948/530, loss: 0.0002923975698649883
2023-01-22 15:58:12.797885: step: 1952/530, loss: 0.0007302080048248172
2023-01-22 15:58:13.826677: step: 1956/530, loss: 0.0123849306255579
2023-01-22 15:58:14.866618: step: 1960/530, loss: 0.00035092595499008894
2023-01-22 15:58:15.910730: step: 1964/530, loss: 0.01818850077688694
2023-01-22 15:58:16.970473: step: 1968/530, loss: 9.57259635470109e-06
2023-01-22 15:58:17.997102: step: 1972/530, loss: 0.029654745012521744
2023-01-22 15:58:19.028897: step: 1976/530, loss: 0.011064673773944378
2023-01-22 15:58:20.083252: step: 1980/530, loss: 0.0064434814266860485
2023-01-22 15:58:21.144337: step: 1984/530, loss: 0.00473420275375247
2023-01-22 15:58:22.183715: step: 1988/530, loss: 0.031124234199523926
2023-01-22 15:58:23.241170: step: 1992/530, loss: 0.00546392984688282
2023-01-22 15:58:24.288954: step: 1996/530, loss: 0.00029834589804522693
2023-01-22 15:58:25.314899: step: 2000/530, loss: 0.0008198019349947572
2023-01-22 15:58:26.364135: step: 2004/530, loss: 0.0074112857691943645
2023-01-22 15:58:27.405191: step: 2008/530, loss: 0.03172183036804199
2023-01-22 15:58:28.467080: step: 2012/530, loss: 0.00966847687959671
2023-01-22 15:58:29.508979: step: 2016/530, loss: 0.005522883962839842
2023-01-22 15:58:30.554899: step: 2020/530, loss: 0.010048533789813519
2023-01-22 15:58:31.600177: step: 2024/530, loss: 0.01874934323132038
2023-01-22 15:58:32.658541: step: 2028/530, loss: 0.021582117304205894
2023-01-22 15:58:33.711387: step: 2032/530, loss: 0.00030745184631086886
2023-01-22 15:58:34.758778: step: 2036/530, loss: 0.005826187320053577
2023-01-22 15:58:35.806984: step: 2040/530, loss: 0.00044487352715805173
2023-01-22 15:58:36.849933: step: 2044/530, loss: 0.004671136848628521
2023-01-22 15:58:37.912808: step: 2048/530, loss: 0.022065000608563423
2023-01-22 15:58:38.945824: step: 2052/530, loss: 0.0071199387311935425
2023-01-22 15:58:39.982024: step: 2056/530, loss: 0.005276544950902462
2023-01-22 15:58:41.014366: step: 2060/530, loss: 0.006164137274026871
2023-01-22 15:58:42.071384: step: 2064/530, loss: 0.0046063382178545
2023-01-22 15:58:43.108730: step: 2068/530, loss: 0.004582513589411974
2023-01-22 15:58:44.138122: step: 2072/530, loss: 5.838310607941821e-05
2023-01-22 15:58:45.189867: step: 2076/530, loss: 0.013666230253875256
2023-01-22 15:58:46.234883: step: 2080/530, loss: 0.004349856171756983
2023-01-22 15:58:47.284809: step: 2084/530, loss: 0.002444185083732009
2023-01-22 15:58:48.311810: step: 2088/530, loss: 0.00016139236686285585
2023-01-22 15:58:49.361142: step: 2092/530, loss: 0.0032693196553736925
2023-01-22 15:58:50.412026: step: 2096/530, loss: 0.0036651529371738434
2023-01-22 15:58:51.457251: step: 2100/530, loss: 0.013309440575540066
2023-01-22 15:58:52.500713: step: 2104/530, loss: 0.026972614228725433
2023-01-22 15:58:53.553819: step: 2108/530, loss: 0.0032702982425689697
2023-01-22 15:58:54.603481: step: 2112/530, loss: 0.010360381565988064
2023-01-22 15:58:55.648468: step: 2116/530, loss: 0.00747764203697443
2023-01-22 15:58:56.688309: step: 2120/530, loss: 0.003745673457160592
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34193588469184893, 'r': 0.32636385199240986, 'f1': 0.33396844660194175}, 'combined': 0.24608201328564128, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35884987380290667, 'r': 0.40667453529318376, 'f1': 0.38126832778887026}, 'combined': 0.29552856029567937, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31241818834922896, 'r': 0.325460313859064, 'f1': 0.3188059208247709}, 'combined': 0.2349096258708838, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3584439244700117, 'r': 0.4078617449392229, 'f1': 0.3815593968133057}, 'combined': 0.29575417360648576, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3248582479550524, 'r': 0.33657040490219853, 'f1': 0.33061063072406077}, 'combined': 0.2436078331650974, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3589558839996734, 'r': 0.38633946706214845, 'f1': 0.37214461280532757}, 'combined': 0.28845658982996686, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:01:24.763907: step: 4/530, loss: 0.0007372562540695071
2023-01-22 16:01:25.804132: step: 8/530, loss: 0.0023943197447806597
2023-01-22 16:01:26.844484: step: 12/530, loss: 0.00902405846863985
2023-01-22 16:01:27.885803: step: 16/530, loss: 0.0017045838758349419
2023-01-22 16:01:28.928958: step: 20/530, loss: 0.001977020176127553
2023-01-22 16:01:29.979885: step: 24/530, loss: 0.008408475667238235
2023-01-22 16:01:31.027382: step: 28/530, loss: 0.0114920474588871
2023-01-22 16:01:32.071840: step: 32/530, loss: 0.011747323907911777
2023-01-22 16:01:33.132875: step: 36/530, loss: 0.004281261470168829
2023-01-22 16:01:34.188159: step: 40/530, loss: 0.0032921512611210346
2023-01-22 16:01:35.239986: step: 44/530, loss: 0.008866902440786362
2023-01-22 16:01:36.295451: step: 48/530, loss: 0.018904125317931175
2023-01-22 16:01:37.336842: step: 52/530, loss: 0.0033392130862921476
2023-01-22 16:01:38.392358: step: 56/530, loss: 0.005421266425400972
2023-01-22 16:01:39.435518: step: 60/530, loss: 0.009067226201295853
2023-01-22 16:01:40.482682: step: 64/530, loss: 0.0065969983115792274
2023-01-22 16:01:41.526705: step: 68/530, loss: 0.008009317331016064
2023-01-22 16:01:42.586444: step: 72/530, loss: 0.013463177718222141
2023-01-22 16:01:43.626826: step: 76/530, loss: 0.0029160326812416315
2023-01-22 16:01:44.654229: step: 80/530, loss: 0.004672999959439039
2023-01-22 16:01:45.724867: step: 84/530, loss: 0.01176483929157257
2023-01-22 16:01:46.758717: step: 88/530, loss: 0.007886665873229504
2023-01-22 16:01:47.811243: step: 92/530, loss: 0.00021173500863369554
2023-01-22 16:01:48.849782: step: 96/530, loss: 0.019204547628760338
2023-01-22 16:01:49.887141: step: 100/530, loss: 0.003048920538276434
2023-01-22 16:01:50.934964: step: 104/530, loss: 0.0022282360587269068
2023-01-22 16:01:51.985538: step: 108/530, loss: 0.004905399866402149
2023-01-22 16:01:53.025395: step: 112/530, loss: 0.005961662624031305
2023-01-22 16:01:54.081721: step: 116/530, loss: 0.007057271432131529
2023-01-22 16:01:55.122883: step: 120/530, loss: 0.002001353772357106
2023-01-22 16:01:56.178189: step: 124/530, loss: 0.0018433105433359742
2023-01-22 16:01:57.202899: step: 128/530, loss: 0.011630582623183727
2023-01-22 16:01:58.230162: step: 132/530, loss: 0.0029869202990084887
2023-01-22 16:01:59.269667: step: 136/530, loss: 0.0011986852623522282
2023-01-22 16:02:00.310458: step: 140/530, loss: 0.002449146704748273
2023-01-22 16:02:01.345353: step: 144/530, loss: 0.020743252709507942
2023-01-22 16:02:02.373423: step: 148/530, loss: 0.0008950207848101854
2023-01-22 16:02:03.453318: step: 152/530, loss: 0.0034274004865437746
2023-01-22 16:02:04.482883: step: 156/530, loss: 0.0014131536008790135
2023-01-22 16:02:05.525893: step: 160/530, loss: 0.0008916228543967009
2023-01-22 16:02:06.558494: step: 164/530, loss: 2.6459583750693128e-05
2023-01-22 16:02:07.606052: step: 168/530, loss: 0.00015481121954508126
2023-01-22 16:02:08.659212: step: 172/530, loss: 0.004595068283379078
2023-01-22 16:02:09.705784: step: 176/530, loss: 0.00030887030879966915
2023-01-22 16:02:10.741588: step: 180/530, loss: 0.008959001861512661
2023-01-22 16:02:11.789130: step: 184/530, loss: 0.002212352119386196
2023-01-22 16:02:12.820589: step: 188/530, loss: 0.010870103724300861
2023-01-22 16:02:13.863691: step: 192/530, loss: 0.0008116374956443906
2023-01-22 16:02:14.909966: step: 196/530, loss: 0.004199315793812275
2023-01-22 16:02:15.960621: step: 200/530, loss: 0.0035693382378667593
2023-01-22 16:02:17.015347: step: 204/530, loss: 0.004782579839229584
2023-01-22 16:02:18.062362: step: 208/530, loss: 0.00366653292439878
2023-01-22 16:02:19.112228: step: 212/530, loss: 0.00039043338620103896
2023-01-22 16:02:20.157979: step: 216/530, loss: 0.00421998230740428
2023-01-22 16:02:21.204945: step: 220/530, loss: 0.0039749848656356335
2023-01-22 16:02:22.280367: step: 224/530, loss: 0.0033849908504635096
2023-01-22 16:02:23.335309: step: 228/530, loss: 0.0027289630379527807
2023-01-22 16:02:24.386181: step: 232/530, loss: 0.00621890788897872
2023-01-22 16:02:25.425361: step: 236/530, loss: 0.010404416359961033
2023-01-22 16:02:26.463044: step: 240/530, loss: 0.003086398122832179
2023-01-22 16:02:27.516500: step: 244/530, loss: 0.007119441404938698
2023-01-22 16:02:28.554837: step: 248/530, loss: 0.0016671937191858888
2023-01-22 16:02:29.600571: step: 252/530, loss: 0.00987583864480257
2023-01-22 16:02:30.643738: step: 256/530, loss: 4.836375592276454e-05
2023-01-22 16:02:31.686423: step: 260/530, loss: 0.0005254087154753506
2023-01-22 16:02:32.739878: step: 264/530, loss: 0.01092437468469143
2023-01-22 16:02:33.785617: step: 268/530, loss: 0.0032315377611666918
2023-01-22 16:02:34.842362: step: 272/530, loss: 0.016228090971708298
2023-01-22 16:02:35.864701: step: 276/530, loss: 0.0008727370295673609
2023-01-22 16:02:36.916598: step: 280/530, loss: 0.005138714332133532
2023-01-22 16:02:37.952952: step: 284/530, loss: 0.006291618105024099
2023-01-22 16:02:39.017808: step: 288/530, loss: 0.0036444435827434063
2023-01-22 16:02:40.076623: step: 292/530, loss: 0.0034987344406545162
2023-01-22 16:02:41.145495: step: 296/530, loss: 0.001284444355405867
2023-01-22 16:02:42.198717: step: 300/530, loss: 0.0034343083389103413
2023-01-22 16:02:43.259414: step: 304/530, loss: 0.0031063039787113667
2023-01-22 16:02:44.311504: step: 308/530, loss: 0.0008699197787791491
2023-01-22 16:02:45.361047: step: 312/530, loss: 0.0006428711931221187
2023-01-22 16:02:46.411220: step: 316/530, loss: 0.008117156103253365
2023-01-22 16:02:47.452885: step: 320/530, loss: 0.005441263318061829
2023-01-22 16:02:48.524674: step: 324/530, loss: 0.005114181432873011
2023-01-22 16:02:49.610921: step: 328/530, loss: 0.003404296236112714
2023-01-22 16:02:50.663199: step: 332/530, loss: 0.005627663806080818
2023-01-22 16:02:51.722005: step: 336/530, loss: 0.011175437830388546
2023-01-22 16:02:52.795294: step: 340/530, loss: 0.0010454534785822034
2023-01-22 16:02:53.848821: step: 344/530, loss: 0.004417550750076771
2023-01-22 16:02:54.890896: step: 348/530, loss: 5.890388274565339e-05
2023-01-22 16:02:55.936632: step: 352/530, loss: 0.009437691420316696
2023-01-22 16:02:56.979889: step: 356/530, loss: 0.0017233914695680141
2023-01-22 16:02:58.029387: step: 360/530, loss: 0.0013881383929401636
2023-01-22 16:02:59.064982: step: 364/530, loss: 0.0013716183602809906
2023-01-22 16:03:00.108583: step: 368/530, loss: 0.004239580128341913
2023-01-22 16:03:01.170366: step: 372/530, loss: 0.0029596728272736073
2023-01-22 16:03:02.250215: step: 376/530, loss: 0.002328514354303479
2023-01-22 16:03:03.303199: step: 380/530, loss: 0.005114738829433918
2023-01-22 16:03:04.354257: step: 384/530, loss: 0.016595415771007538
2023-01-22 16:03:05.409731: step: 388/530, loss: 0.006054204888641834
2023-01-22 16:03:06.459241: step: 392/530, loss: 0.00011971151980105788
2023-01-22 16:03:07.497276: step: 396/530, loss: 0.003062792122364044
2023-01-22 16:03:08.559158: step: 400/530, loss: 0.004000066313892603
2023-01-22 16:03:09.614415: step: 404/530, loss: 0.0009041042649187148
2023-01-22 16:03:10.670924: step: 408/530, loss: 0.004386028740555048
2023-01-22 16:03:11.712704: step: 412/530, loss: 0.004916968289762735
2023-01-22 16:03:12.766100: step: 416/530, loss: 0.011079824529588223
2023-01-22 16:03:13.828290: step: 420/530, loss: 0.004672501236200333
2023-01-22 16:03:14.884885: step: 424/530, loss: 0.0028045445214957
2023-01-22 16:03:15.932211: step: 428/530, loss: 0.0009784386493265629
2023-01-22 16:03:16.982492: step: 432/530, loss: 0.0013245128793641925
2023-01-22 16:03:18.013768: step: 436/530, loss: 0.0038161959964782
2023-01-22 16:03:19.070581: step: 440/530, loss: 0.00876330491155386
2023-01-22 16:03:20.115695: step: 444/530, loss: 0.0029141767881810665
2023-01-22 16:03:21.167311: step: 448/530, loss: 0.00021813716739416122
2023-01-22 16:03:22.224285: step: 452/530, loss: 0.0003300993994344026
2023-01-22 16:03:23.280770: step: 456/530, loss: 0.0012417059624567628
2023-01-22 16:03:24.331066: step: 460/530, loss: 0.00444937776774168
2023-01-22 16:03:25.370635: step: 464/530, loss: 0.001703589572571218
2023-01-22 16:03:26.427858: step: 468/530, loss: 0.02460644207894802
2023-01-22 16:03:27.470317: step: 472/530, loss: 0.005276022478938103
2023-01-22 16:03:28.514465: step: 476/530, loss: 0.00010200202814303339
2023-01-22 16:03:29.571575: step: 480/530, loss: 0.0036124333273619413
2023-01-22 16:03:30.616873: step: 484/530, loss: 0.003638251917436719
2023-01-22 16:03:31.670117: step: 488/530, loss: 0.003780804108828306
2023-01-22 16:03:32.710835: step: 492/530, loss: 0.0005541572463698685
2023-01-22 16:03:33.759513: step: 496/530, loss: 0.0037358610425144434
2023-01-22 16:03:34.805463: step: 500/530, loss: 0.0033541028387844563
2023-01-22 16:03:35.853930: step: 504/530, loss: 9.332134504802525e-05
2023-01-22 16:03:36.898840: step: 508/530, loss: 0.0
2023-01-22 16:03:37.941500: step: 512/530, loss: 0.0035010657738894224
2023-01-22 16:03:39.008829: step: 516/530, loss: 0.0036441602278500795
2023-01-22 16:03:40.069708: step: 520/530, loss: 0.002572100842371583
2023-01-22 16:03:41.143067: step: 524/530, loss: 0.00015868218906689435
2023-01-22 16:03:42.217876: step: 528/530, loss: 0.00010934688179986551
2023-01-22 16:03:43.260772: step: 532/530, loss: 0.008732899092137814
2023-01-22 16:03:44.313769: step: 536/530, loss: 0.005267515778541565
2023-01-22 16:03:45.372618: step: 540/530, loss: 0.0009832335636019707
2023-01-22 16:03:46.427865: step: 544/530, loss: 0.005033475812524557
2023-01-22 16:03:47.465028: step: 548/530, loss: 0.0020362003706395626
2023-01-22 16:03:48.528647: step: 552/530, loss: 0.002050328068435192
2023-01-22 16:03:49.585686: step: 556/530, loss: 0.008932351134717464
2023-01-22 16:03:50.636557: step: 560/530, loss: 0.00048724692896939814
2023-01-22 16:03:51.675634: step: 564/530, loss: 0.00021071318769827485
2023-01-22 16:03:52.721682: step: 568/530, loss: 0.0001415097212884575
2023-01-22 16:03:53.766284: step: 572/530, loss: 0.009318580850958824
2023-01-22 16:03:54.817576: step: 576/530, loss: 0.004937023855745792
2023-01-22 16:03:55.864598: step: 580/530, loss: 0.036102116107940674
2023-01-22 16:03:56.922361: step: 584/530, loss: 0.0007588112493976951
2023-01-22 16:03:57.957288: step: 588/530, loss: 0.009392837062478065
2023-01-22 16:03:59.008903: step: 592/530, loss: 0.02177371084690094
2023-01-22 16:04:00.053505: step: 596/530, loss: 0.006736889481544495
2023-01-22 16:04:01.102257: step: 600/530, loss: 0.004126775544136763
2023-01-22 16:04:02.164541: step: 604/530, loss: 0.006093895528465509
2023-01-22 16:04:03.231241: step: 608/530, loss: 0.01033114455640316
2023-01-22 16:04:04.270851: step: 612/530, loss: 0.0054052588529884815
2023-01-22 16:04:05.315010: step: 616/530, loss: 0.018098486587405205
2023-01-22 16:04:06.367928: step: 620/530, loss: 0.01095607690513134
2023-01-22 16:04:07.424813: step: 624/530, loss: 0.004884735681116581
2023-01-22 16:04:08.466869: step: 628/530, loss: 0.003965138923376799
2023-01-22 16:04:09.519479: step: 632/530, loss: 0.002264399314299226
2023-01-22 16:04:10.565736: step: 636/530, loss: 0.00013817149738315493
2023-01-22 16:04:11.615662: step: 640/530, loss: 0.00026588892797008157
2023-01-22 16:04:12.663778: step: 644/530, loss: 0.001550157438032329
2023-01-22 16:04:13.736778: step: 648/530, loss: 0.008443762548267841
2023-01-22 16:04:14.790608: step: 652/530, loss: 0.005830992478877306
2023-01-22 16:04:15.827017: step: 656/530, loss: 0.0004329170915298164
2023-01-22 16:04:16.874025: step: 660/530, loss: 0.02213708870112896
2023-01-22 16:04:17.964291: step: 664/530, loss: 0.005303644575178623
2023-01-22 16:04:19.019890: step: 668/530, loss: 0.0039398204535245895
2023-01-22 16:04:20.062636: step: 672/530, loss: 0.005339667666703463
2023-01-22 16:04:21.141377: step: 676/530, loss: 0.005549273919314146
2023-01-22 16:04:22.190101: step: 680/530, loss: 0.014439555816352367
2023-01-22 16:04:23.224084: step: 684/530, loss: 0.0005124564049765468
2023-01-22 16:04:24.281686: step: 688/530, loss: 0.0043865228071808815
2023-01-22 16:04:25.332008: step: 692/530, loss: 0.0019238080130890012
2023-01-22 16:04:26.395567: step: 696/530, loss: 5.780091214546701e-06
2023-01-22 16:04:27.427089: step: 700/530, loss: 0.004060221835970879
2023-01-22 16:04:28.472708: step: 704/530, loss: 0.0030003520660102367
2023-01-22 16:04:29.514964: step: 708/530, loss: 0.004450484178960323
2023-01-22 16:04:30.563249: step: 712/530, loss: 0.002015204168856144
2023-01-22 16:04:31.645075: step: 716/530, loss: 0.007801043801009655
2023-01-22 16:04:32.686529: step: 720/530, loss: 0.002182956086471677
2023-01-22 16:04:33.729042: step: 724/530, loss: 1.6539946955163032e-05
2023-01-22 16:04:34.774201: step: 728/530, loss: 0.002252360340207815
2023-01-22 16:04:35.828793: step: 732/530, loss: 0.0020012168679386377
2023-01-22 16:04:36.890531: step: 736/530, loss: 0.00020705978386104107
2023-01-22 16:04:37.947164: step: 740/530, loss: 0.0033514276146888733
2023-01-22 16:04:38.998289: step: 744/530, loss: 0.006716678384691477
2023-01-22 16:04:40.042338: step: 748/530, loss: 0.00016646439325995743
2023-01-22 16:04:41.100666: step: 752/530, loss: 0.042862117290496826
2023-01-22 16:04:42.140929: step: 756/530, loss: 0.005601138342171907
2023-01-22 16:04:43.183523: step: 760/530, loss: 0.005318896844983101
2023-01-22 16:04:44.221867: step: 764/530, loss: 0.0002570927026681602
2023-01-22 16:04:45.292376: step: 768/530, loss: 0.00429547531530261
2023-01-22 16:04:46.335865: step: 772/530, loss: 0.01953442580997944
2023-01-22 16:04:47.379211: step: 776/530, loss: 0.005533652845770121
2023-01-22 16:04:48.413686: step: 780/530, loss: 0.003615013090893626
2023-01-22 16:04:49.475835: step: 784/530, loss: 0.0027866351883858442
2023-01-22 16:04:50.525366: step: 788/530, loss: 0.003989127930253744
2023-01-22 16:04:51.575775: step: 792/530, loss: 0.009449250064790249
2023-01-22 16:04:52.634122: step: 796/530, loss: 0.007280644029378891
2023-01-22 16:04:53.692152: step: 800/530, loss: 0.010848934762179852
2023-01-22 16:04:54.742555: step: 804/530, loss: 0.005052474793046713
2023-01-22 16:04:55.787717: step: 808/530, loss: 0.0037409246433526278
2023-01-22 16:04:56.839185: step: 812/530, loss: 0.005573755595833063
2023-01-22 16:04:57.887165: step: 816/530, loss: 0.0037045818753540516
2023-01-22 16:04:58.918507: step: 820/530, loss: 0.000529707467649132
2023-01-22 16:04:59.965608: step: 824/530, loss: 0.01829605922102928
2023-01-22 16:05:01.016752: step: 828/530, loss: 0.0022317995317280293
2023-01-22 16:05:02.048519: step: 832/530, loss: 0.00036393056507222354
2023-01-22 16:05:03.086640: step: 836/530, loss: 0.0003764189314097166
2023-01-22 16:05:04.122028: step: 840/530, loss: 0.004179711919277906
2023-01-22 16:05:05.185875: step: 844/530, loss: 0.0017930822214111686
2023-01-22 16:05:06.232673: step: 848/530, loss: 0.0009661811636760831
2023-01-22 16:05:07.308876: step: 852/530, loss: 0.019975047558546066
2023-01-22 16:05:08.347046: step: 856/530, loss: 0.0006106731598265469
2023-01-22 16:05:09.394329: step: 860/530, loss: 0.01782960072159767
2023-01-22 16:05:10.439189: step: 864/530, loss: 0.0004105751577299088
2023-01-22 16:05:11.480687: step: 868/530, loss: 0.005054058041423559
2023-01-22 16:05:12.524679: step: 872/530, loss: 0.007396685890853405
2023-01-22 16:05:13.582215: step: 876/530, loss: 0.001772705465555191
2023-01-22 16:05:14.619969: step: 880/530, loss: 0.000585298053920269
2023-01-22 16:05:15.656325: step: 884/530, loss: 0.0138911884278059
2023-01-22 16:05:16.727723: step: 888/530, loss: 0.014687693677842617
2023-01-22 16:05:17.766775: step: 892/530, loss: 0.01384313777089119
2023-01-22 16:05:18.808391: step: 896/530, loss: 0.001359553774818778
2023-01-22 16:05:19.852492: step: 900/530, loss: 0.005595955066382885
2023-01-22 16:05:20.894854: step: 904/530, loss: 0.012071708217263222
2023-01-22 16:05:21.955950: step: 908/530, loss: 0.004334148485213518
2023-01-22 16:05:23.015119: step: 912/530, loss: 0.001883754157461226
2023-01-22 16:05:24.068458: step: 916/530, loss: 0.008667264133691788
2023-01-22 16:05:25.116622: step: 920/530, loss: 0.03686615452170372
2023-01-22 16:05:26.166262: step: 924/530, loss: 0.0029824068769812584
2023-01-22 16:05:27.209172: step: 928/530, loss: 0.003981342539191246
2023-01-22 16:05:28.274148: step: 932/530, loss: 0.027510561048984528
2023-01-22 16:05:29.340295: step: 936/530, loss: 0.022754797711968422
2023-01-22 16:05:30.398333: step: 940/530, loss: 0.003511945018544793
2023-01-22 16:05:31.462209: step: 944/530, loss: 0.0035397843457758427
2023-01-22 16:05:32.496089: step: 948/530, loss: 0.004075996577739716
2023-01-22 16:05:33.546776: step: 952/530, loss: 0.0020581826101988554
2023-01-22 16:05:34.605669: step: 956/530, loss: 0.00868846196681261
2023-01-22 16:05:35.645582: step: 960/530, loss: 0.003406491596251726
2023-01-22 16:05:36.696156: step: 964/530, loss: 0.005959927104413509
2023-01-22 16:05:37.746851: step: 968/530, loss: 0.006768408697098494
2023-01-22 16:05:38.796748: step: 972/530, loss: 0.00593695929273963
2023-01-22 16:05:39.848997: step: 976/530, loss: 0.010021916590631008
2023-01-22 16:05:40.888684: step: 980/530, loss: 0.00379653531126678
2023-01-22 16:05:41.929361: step: 984/530, loss: 0.0011425334960222244
2023-01-22 16:05:42.971623: step: 988/530, loss: 0.046871911734342575
2023-01-22 16:05:44.024310: step: 992/530, loss: 0.02045295387506485
2023-01-22 16:05:45.073162: step: 996/530, loss: 0.0010991408489644527
2023-01-22 16:05:46.119352: step: 1000/530, loss: 0.008956157602369785
2023-01-22 16:05:47.164198: step: 1004/530, loss: 0.0007103080279193819
2023-01-22 16:05:48.196024: step: 1008/530, loss: 0.003950471989810467
2023-01-22 16:05:49.246209: step: 1012/530, loss: 0.005394541192799807
2023-01-22 16:05:50.270375: step: 1016/530, loss: 0.006424236577004194
2023-01-22 16:05:51.313397: step: 1020/530, loss: 0.005007125437259674
2023-01-22 16:05:52.367513: step: 1024/530, loss: 0.009094523265957832
2023-01-22 16:05:53.410545: step: 1028/530, loss: 0.014116130769252777
2023-01-22 16:05:54.445022: step: 1032/530, loss: 9.635881724534556e-06
2023-01-22 16:05:55.485953: step: 1036/530, loss: 0.0007864705985412002
2023-01-22 16:05:56.541060: step: 1040/530, loss: 0.0021402963902801275
2023-01-22 16:05:57.589354: step: 1044/530, loss: 0.009299227967858315
2023-01-22 16:05:58.621593: step: 1048/530, loss: 0.00010648762690834701
2023-01-22 16:05:59.673046: step: 1052/530, loss: 0.0003820595738943666
2023-01-22 16:06:00.705825: step: 1056/530, loss: 0.013246774673461914
2023-01-22 16:06:01.739623: step: 1060/530, loss: 0.009429216384887695
2023-01-22 16:06:02.776754: step: 1064/530, loss: 1.1052250101784011e-06
2023-01-22 16:06:03.836467: step: 1068/530, loss: 0.010297033004462719
2023-01-22 16:06:04.877728: step: 1072/530, loss: 0.0019000115571543574
2023-01-22 16:06:05.928651: step: 1076/530, loss: 0.008428475819528103
2023-01-22 16:06:06.987635: step: 1080/530, loss: 0.002425176789984107
2023-01-22 16:06:08.034812: step: 1084/530, loss: 0.00487297959625721
2023-01-22 16:06:09.061400: step: 1088/530, loss: 0.00514750462025404
2023-01-22 16:06:10.092485: step: 1092/530, loss: 0.012974259443581104
2023-01-22 16:06:11.134825: step: 1096/530, loss: 0.0005095039959996939
2023-01-22 16:06:12.187385: step: 1100/530, loss: 0.011658834293484688
2023-01-22 16:06:13.234007: step: 1104/530, loss: 0.002302357694134116
2023-01-22 16:06:14.290542: step: 1108/530, loss: 0.0030269830022007227
2023-01-22 16:06:15.340644: step: 1112/530, loss: 0.01093481294810772
2023-01-22 16:06:16.387315: step: 1116/530, loss: 0.0019961956422775984
2023-01-22 16:06:17.439053: step: 1120/530, loss: 0.019439103081822395
2023-01-22 16:06:18.483202: step: 1124/530, loss: 0.01040840707719326
2023-01-22 16:06:19.540160: step: 1128/530, loss: 0.008950133807957172
2023-01-22 16:06:20.573707: step: 1132/530, loss: 0.002671079942956567
2023-01-22 16:06:21.626310: step: 1136/530, loss: 0.01244097575545311
2023-01-22 16:06:22.667369: step: 1140/530, loss: 0.0014234735863283277
2023-01-22 16:06:23.717769: step: 1144/530, loss: 0.001032823696732521
2023-01-22 16:06:24.768129: step: 1148/530, loss: 0.0031111338175833225
2023-01-22 16:06:25.804076: step: 1152/530, loss: 0.00020250941452104598
2023-01-22 16:06:26.861680: step: 1156/530, loss: 0.005391637794673443
2023-01-22 16:06:27.902756: step: 1160/530, loss: 0.005741727538406849
2023-01-22 16:06:28.953134: step: 1164/530, loss: 0.0009992264676839113
2023-01-22 16:06:29.986181: step: 1168/530, loss: 0.00014529972395393997
2023-01-22 16:06:31.023661: step: 1172/530, loss: 0.002177294110879302
2023-01-22 16:06:32.069349: step: 1176/530, loss: 0.00029257911955937743
2023-01-22 16:06:33.103566: step: 1180/530, loss: 0.0
2023-01-22 16:06:34.159484: step: 1184/530, loss: 0.0031331698410212994
2023-01-22 16:06:35.201563: step: 1188/530, loss: 0.008023147471249104
2023-01-22 16:06:36.245233: step: 1192/530, loss: 0.00203211628831923
2023-01-22 16:06:37.310729: step: 1196/530, loss: 0.000991905340924859
2023-01-22 16:06:38.350611: step: 1200/530, loss: 0.005070593673735857
2023-01-22 16:06:39.390646: step: 1204/530, loss: 0.004027171526104212
2023-01-22 16:06:40.446269: step: 1208/530, loss: 0.004472642205655575
2023-01-22 16:06:41.515932: step: 1212/530, loss: 0.01647268608212471
2023-01-22 16:06:42.544716: step: 1216/530, loss: 0.0056014154106378555
2023-01-22 16:06:43.596672: step: 1220/530, loss: 0.00035225055762566626
2023-01-22 16:06:44.648529: step: 1224/530, loss: 0.0021586057264357805
2023-01-22 16:06:45.698586: step: 1228/530, loss: 0.0012377829989418387
2023-01-22 16:06:46.748703: step: 1232/530, loss: 0.0023653607349842787
2023-01-22 16:06:47.800084: step: 1236/530, loss: 0.0005897342343814671
2023-01-22 16:06:48.845502: step: 1240/530, loss: 0.005260581616312265
2023-01-22 16:06:49.897526: step: 1244/530, loss: 0.002286014147102833
2023-01-22 16:06:50.956214: step: 1248/530, loss: 0.0027143657207489014
2023-01-22 16:06:51.992399: step: 1252/530, loss: 0.003995587583631277
2023-01-22 16:06:53.024475: step: 1256/530, loss: 0.004028848838061094
2023-01-22 16:06:54.070071: step: 1260/530, loss: 0.00884984340518713
2023-01-22 16:06:55.127971: step: 1264/530, loss: 7.619905227329582e-05
2023-01-22 16:06:56.184895: step: 1268/530, loss: 0.003528781235218048
2023-01-22 16:06:57.223274: step: 1272/530, loss: 0.002885366789996624
2023-01-22 16:06:58.264115: step: 1276/530, loss: 0.0005106826429255307
2023-01-22 16:06:59.311685: step: 1280/530, loss: 0.031529735773801804
2023-01-22 16:07:00.348524: step: 1284/530, loss: 0.009394584223628044
2023-01-22 16:07:01.383234: step: 1288/530, loss: 0.0074567291885614395
2023-01-22 16:07:02.433751: step: 1292/530, loss: 0.010632209479808807
2023-01-22 16:07:03.478490: step: 1296/530, loss: 0.0037001834716647863
2023-01-22 16:07:04.518452: step: 1300/530, loss: 0.0012172827264294028
2023-01-22 16:07:05.549239: step: 1304/530, loss: 0.006315297447144985
2023-01-22 16:07:06.597960: step: 1308/530, loss: 0.001121440902352333
2023-01-22 16:07:07.662653: step: 1312/530, loss: 0.0015420080162584782
2023-01-22 16:07:08.729281: step: 1316/530, loss: 0.01011837087571621
2023-01-22 16:07:09.792490: step: 1320/530, loss: 0.0065863714553415775
2023-01-22 16:07:10.835256: step: 1324/530, loss: 0.006901334505528212
2023-01-22 16:07:11.881041: step: 1328/530, loss: 0.0003939066082239151
2023-01-22 16:07:12.920020: step: 1332/530, loss: 0.001131982309743762
2023-01-22 16:07:13.981474: step: 1336/530, loss: 0.0014619502471759915
2023-01-22 16:07:15.033731: step: 1340/530, loss: 0.008542369119822979
2023-01-22 16:07:16.082590: step: 1344/530, loss: 0.003910900093615055
2023-01-22 16:07:17.122919: step: 1348/530, loss: 0.004884009715169668
2023-01-22 16:07:18.162229: step: 1352/530, loss: 0.0007372616673819721
2023-01-22 16:07:19.197946: step: 1356/530, loss: 0.0012824038276448846
2023-01-22 16:07:20.251685: step: 1360/530, loss: 0.0023664666805416346
2023-01-22 16:07:21.288001: step: 1364/530, loss: 0.003511996241286397
2023-01-22 16:07:22.333654: step: 1368/530, loss: 0.0006677159108221531
2023-01-22 16:07:23.385760: step: 1372/530, loss: 0.01030261442065239
2023-01-22 16:07:24.436277: step: 1376/530, loss: 0.021198581904172897
2023-01-22 16:07:25.482641: step: 1380/530, loss: 0.003374363761395216
2023-01-22 16:07:26.524496: step: 1384/530, loss: 0.002790069906041026
2023-01-22 16:07:27.568098: step: 1388/530, loss: 0.010399678722023964
2023-01-22 16:07:28.603653: step: 1392/530, loss: 7.802563777659088e-05
2023-01-22 16:07:29.645818: step: 1396/530, loss: 0.0025065478403121233
2023-01-22 16:07:30.685693: step: 1400/530, loss: 0.002675700467079878
2023-01-22 16:07:31.725921: step: 1404/530, loss: 0.001919111586175859
2023-01-22 16:07:32.769693: step: 1408/530, loss: 0.003553468734025955
2023-01-22 16:07:33.813492: step: 1412/530, loss: 0.007829018868505955
2023-01-22 16:07:34.872572: step: 1416/530, loss: 0.0024773040786385536
2023-01-22 16:07:35.911810: step: 1420/530, loss: 0.006798421498388052
2023-01-22 16:07:36.938914: step: 1424/530, loss: 0.0011663369368761778
2023-01-22 16:07:37.980497: step: 1428/530, loss: 0.0018892490770667791
2023-01-22 16:07:39.031648: step: 1432/530, loss: 0.0055986130610108376
2023-01-22 16:07:40.085019: step: 1436/530, loss: 0.004060044884681702
2023-01-22 16:07:41.107180: step: 1440/530, loss: 0.0001568841253174469
2023-01-22 16:07:42.160256: step: 1444/530, loss: 0.010481741279363632
2023-01-22 16:07:43.209041: step: 1448/530, loss: 0.008694391697645187
2023-01-22 16:07:44.243638: step: 1452/530, loss: 0.008683069609105587
2023-01-22 16:07:45.279592: step: 1456/530, loss: 0.01155092753469944
2023-01-22 16:07:46.345131: step: 1460/530, loss: 0.008806398138403893
2023-01-22 16:07:47.384189: step: 1464/530, loss: 0.0004797578149009496
2023-01-22 16:07:48.428795: step: 1468/530, loss: 0.0009437146945856512
2023-01-22 16:07:49.472627: step: 1472/530, loss: 0.007920672185719013
2023-01-22 16:07:50.522804: step: 1476/530, loss: 0.00047152131446637213
2023-01-22 16:07:51.573809: step: 1480/530, loss: 0.004473808221518993
2023-01-22 16:07:52.621585: step: 1484/530, loss: 5.9020785556640476e-05
2023-01-22 16:07:53.659696: step: 1488/530, loss: 0.017084959894418716
2023-01-22 16:07:54.709897: step: 1492/530, loss: 0.010353378020226955
2023-01-22 16:07:55.759388: step: 1496/530, loss: 0.005473766475915909
2023-01-22 16:07:56.810882: step: 1500/530, loss: 0.010242610238492489
2023-01-22 16:07:57.842470: step: 1504/530, loss: 0.01161864772439003
2023-01-22 16:07:58.869102: step: 1508/530, loss: 0.01610509864985943
2023-01-22 16:07:59.905060: step: 1512/530, loss: 0.006201563868671656
2023-01-22 16:08:00.939636: step: 1516/530, loss: 0.003785045351833105
2023-01-22 16:08:01.986498: step: 1520/530, loss: 0.013776431791484356
2023-01-22 16:08:03.050779: step: 1524/530, loss: 0.002174972789362073
2023-01-22 16:08:04.087140: step: 1528/530, loss: 0.012499798089265823
2023-01-22 16:08:05.134303: step: 1532/530, loss: 0.007475248537957668
2023-01-22 16:08:06.175748: step: 1536/530, loss: 0.004212602507323027
2023-01-22 16:08:07.205707: step: 1540/530, loss: 0.0007367205107584596
2023-01-22 16:08:08.245235: step: 1544/530, loss: 0.005895259790122509
2023-01-22 16:08:09.278927: step: 1548/530, loss: 0.0001304114266531542
2023-01-22 16:08:10.340135: step: 1552/530, loss: 0.00027391480398364365
2023-01-22 16:08:11.396814: step: 1556/530, loss: 0.011168625205755234
2023-01-22 16:08:12.439314: step: 1560/530, loss: 2.434478301438503e-05
2023-01-22 16:08:13.508610: step: 1564/530, loss: 0.0012131110997870564
2023-01-22 16:08:14.549652: step: 1568/530, loss: 0.008057406172156334
2023-01-22 16:08:15.607189: step: 1572/530, loss: 0.0012467375490814447
2023-01-22 16:08:16.650717: step: 1576/530, loss: 0.0026619932614266872
2023-01-22 16:08:17.683180: step: 1580/530, loss: 0.004614337347447872
2023-01-22 16:08:18.731898: step: 1584/530, loss: 0.011366119608283043
2023-01-22 16:08:19.779042: step: 1588/530, loss: 0.005403272807598114
2023-01-22 16:08:20.829410: step: 1592/530, loss: 0.002521159127354622
2023-01-22 16:08:21.868849: step: 1596/530, loss: 0.0016460123006254435
2023-01-22 16:08:22.910290: step: 1600/530, loss: 0.002360695041716099
2023-01-22 16:08:23.960187: step: 1604/530, loss: 0.01360092032700777
2023-01-22 16:08:24.989124: step: 1608/530, loss: 0.00018616866145748645
2023-01-22 16:08:26.030052: step: 1612/530, loss: 0.004114161245524883
2023-01-22 16:08:27.085795: step: 1616/530, loss: 0.0011856280034407973
2023-01-22 16:08:28.128214: step: 1620/530, loss: 0.004183993209153414
2023-01-22 16:08:29.189847: step: 1624/530, loss: 0.004463567398488522
2023-01-22 16:08:30.234025: step: 1628/530, loss: 0.0063022952526807785
2023-01-22 16:08:31.275949: step: 1632/530, loss: 0.003606413723900914
2023-01-22 16:08:32.338736: step: 1636/530, loss: 0.023998545482754707
2023-01-22 16:08:33.406755: step: 1640/530, loss: 0.007433038670569658
2023-01-22 16:08:34.447603: step: 1644/530, loss: 0.009414362721145153
2023-01-22 16:08:35.488277: step: 1648/530, loss: 0.006173159461468458
2023-01-22 16:08:36.556200: step: 1652/530, loss: 0.0019051269628107548
2023-01-22 16:08:37.612955: step: 1656/530, loss: 0.0010178512893617153
2023-01-22 16:08:38.665254: step: 1660/530, loss: 0.012921225279569626
2023-01-22 16:08:39.727167: step: 1664/530, loss: 0.0008176472620107234
2023-01-22 16:08:40.774817: step: 1668/530, loss: 0.00013474744628183544
2023-01-22 16:08:41.823366: step: 1672/530, loss: 0.018266238272190094
2023-01-22 16:08:42.872630: step: 1676/530, loss: 0.0055892253294587135
2023-01-22 16:08:43.904124: step: 1680/530, loss: 0.022537048906087875
2023-01-22 16:08:44.940857: step: 1684/530, loss: 0.006122391205281019
2023-01-22 16:08:45.981699: step: 1688/530, loss: 0.0018234685994684696
2023-01-22 16:08:47.032056: step: 1692/530, loss: 0.001576649839989841
2023-01-22 16:08:48.076285: step: 1696/530, loss: 0.006582121830433607
2023-01-22 16:08:49.140178: step: 1700/530, loss: 0.003203270025551319
2023-01-22 16:08:50.196671: step: 1704/530, loss: 0.010848253965377808
2023-01-22 16:08:51.231164: step: 1708/530, loss: 0.004285692237317562
2023-01-22 16:08:52.283971: step: 1712/530, loss: 0.002168471459299326
2023-01-22 16:08:53.348088: step: 1716/530, loss: 0.010917812585830688
2023-01-22 16:08:54.386695: step: 1720/530, loss: 0.006417870055884123
2023-01-22 16:08:55.443563: step: 1724/530, loss: 0.006473662331700325
2023-01-22 16:08:56.507690: step: 1728/530, loss: 0.005470762494951487
2023-01-22 16:08:57.539820: step: 1732/530, loss: 0.0010238197864964604
2023-01-22 16:08:58.588223: step: 1736/530, loss: 0.0012448985362425447
2023-01-22 16:08:59.625079: step: 1740/530, loss: 0.0032532766927033663
2023-01-22 16:09:00.662432: step: 1744/530, loss: 0.006570354104042053
2023-01-22 16:09:01.703289: step: 1748/530, loss: 0.005573190748691559
2023-01-22 16:09:02.762488: step: 1752/530, loss: 0.0013920385390520096
2023-01-22 16:09:03.801335: step: 1756/530, loss: 0.005858817137777805
2023-01-22 16:09:04.837765: step: 1760/530, loss: 0.009732052683830261
2023-01-22 16:09:05.890078: step: 1764/530, loss: 0.00013912632130086422
2023-01-22 16:09:06.942302: step: 1768/530, loss: 0.029803238809108734
2023-01-22 16:09:07.989911: step: 1772/530, loss: 0.0030895352829247713
2023-01-22 16:09:09.069896: step: 1776/530, loss: 0.0022360854782164097
2023-01-22 16:09:10.126036: step: 1780/530, loss: 0.0047850823029875755
2023-01-22 16:09:11.154628: step: 1784/530, loss: 0.0059539941139519215
2023-01-22 16:09:12.197440: step: 1788/530, loss: 0.003803499508649111
2023-01-22 16:09:13.231040: step: 1792/530, loss: 0.004736559931188822
2023-01-22 16:09:14.281468: step: 1796/530, loss: 0.007367157377302647
2023-01-22 16:09:15.336651: step: 1800/530, loss: 0.002435927977785468
2023-01-22 16:09:16.386009: step: 1804/530, loss: 0.013856090605258942
2023-01-22 16:09:17.413664: step: 1808/530, loss: 0.006727796047925949
2023-01-22 16:09:18.463736: step: 1812/530, loss: 0.0030597266741096973
2023-01-22 16:09:19.519256: step: 1816/530, loss: 0.013682817108929157
2023-01-22 16:09:20.597188: step: 1820/530, loss: 0.01180302631109953
2023-01-22 16:09:21.643101: step: 1824/530, loss: 0.009305909276008606
2023-01-22 16:09:22.690381: step: 1828/530, loss: 0.0026737151201814413
2023-01-22 16:09:23.759979: step: 1832/530, loss: 0.01087513379752636
2023-01-22 16:09:24.812575: step: 1836/530, loss: 0.0030264933593571186
2023-01-22 16:09:25.858067: step: 1840/530, loss: 0.00417698360979557
2023-01-22 16:09:26.916421: step: 1844/530, loss: 0.022523457184433937
2023-01-22 16:09:27.969591: step: 1848/530, loss: 0.011807015165686607
2023-01-22 16:09:29.006741: step: 1852/530, loss: 0.004986438434571028
2023-01-22 16:09:30.045045: step: 1856/530, loss: 0.003538735443726182
2023-01-22 16:09:31.097714: step: 1860/530, loss: 0.003975627478212118
2023-01-22 16:09:32.143714: step: 1864/530, loss: 0.000582256936468184
2023-01-22 16:09:33.189625: step: 1868/530, loss: 0.00802086666226387
2023-01-22 16:09:34.234651: step: 1872/530, loss: 0.003350243903696537
2023-01-22 16:09:35.289455: step: 1876/530, loss: 0.006374271586537361
2023-01-22 16:09:36.336398: step: 1880/530, loss: 0.01305426750332117
2023-01-22 16:09:37.374970: step: 1884/530, loss: 0.005892110522836447
2023-01-22 16:09:38.440904: step: 1888/530, loss: 0.007200535852462053
2023-01-22 16:09:39.487430: step: 1892/530, loss: 0.0033678426407277584
2023-01-22 16:09:40.520606: step: 1896/530, loss: 0.018373841419816017
2023-01-22 16:09:41.567697: step: 1900/530, loss: 0.012094561010599136
2023-01-22 16:09:42.602754: step: 1904/530, loss: 0.024464663118124008
2023-01-22 16:09:43.684609: step: 1908/530, loss: 0.008913002908229828
2023-01-22 16:09:44.734018: step: 1912/530, loss: 0.006913756486028433
2023-01-22 16:09:45.766103: step: 1916/530, loss: 0.011059180833399296
2023-01-22 16:09:46.818895: step: 1920/530, loss: 0.006965978071093559
2023-01-22 16:09:47.856808: step: 1924/530, loss: 0.013344147242605686
2023-01-22 16:09:48.908930: step: 1928/530, loss: 0.0020171429496258497
2023-01-22 16:09:49.959725: step: 1932/530, loss: 0.0006166796083562076
2023-01-22 16:09:51.007882: step: 1936/530, loss: 0.006823674309998751
2023-01-22 16:09:52.039772: step: 1940/530, loss: 0.04783971607685089
2023-01-22 16:09:53.088595: step: 1944/530, loss: 0.003408369841054082
2023-01-22 16:09:54.127096: step: 1948/530, loss: 0.0006025812472216785
2023-01-22 16:09:55.174808: step: 1952/530, loss: 0.0001309165236307308
2023-01-22 16:09:56.201071: step: 1956/530, loss: 0.005067429039627314
2023-01-22 16:09:57.244012: step: 1960/530, loss: 0.0029683129396289587
2023-01-22 16:09:58.282964: step: 1964/530, loss: 0.00875820778310299
2023-01-22 16:09:59.324075: step: 1968/530, loss: 0.013712255284190178
2023-01-22 16:10:00.390677: step: 1972/530, loss: 0.04200352355837822
2023-01-22 16:10:01.455812: step: 1976/530, loss: 0.009647498838603497
2023-01-22 16:10:02.536059: step: 1980/530, loss: 0.06462786346673965
2023-01-22 16:10:03.579749: step: 1984/530, loss: 0.0012632659636437893
2023-01-22 16:10:04.616509: step: 1988/530, loss: 0.0013457417953759432
2023-01-22 16:10:05.651012: step: 1992/530, loss: 0.0013004661304876208
2023-01-22 16:10:06.726697: step: 1996/530, loss: 0.0040257591754198074
2023-01-22 16:10:07.796417: step: 2000/530, loss: 0.006593342870473862
2023-01-22 16:10:08.828944: step: 2004/530, loss: 0.006676852703094482
2023-01-22 16:10:09.874883: step: 2008/530, loss: 0.0016754663083702326
2023-01-22 16:10:10.922395: step: 2012/530, loss: 0.03920523822307587
2023-01-22 16:10:11.976726: step: 2016/530, loss: 0.0031775333918631077
2023-01-22 16:10:13.012749: step: 2020/530, loss: 0.003625443670898676
2023-01-22 16:10:14.045363: step: 2024/530, loss: 0.00023560876434203237
2023-01-22 16:10:15.090307: step: 2028/530, loss: 0.008078127168118954
2023-01-22 16:10:16.148467: step: 2032/530, loss: 0.00219753198325634
2023-01-22 16:10:17.202244: step: 2036/530, loss: 0.003684427822008729
2023-01-22 16:10:18.244661: step: 2040/530, loss: 0.0031191271264106035
2023-01-22 16:10:19.290053: step: 2044/530, loss: 0.015231509692966938
2023-01-22 16:10:20.330075: step: 2048/530, loss: 9.349261381430551e-05
2023-01-22 16:10:21.389525: step: 2052/530, loss: 0.005056777037680149
2023-01-22 16:10:22.434665: step: 2056/530, loss: 0.0019268053583800793
2023-01-22 16:10:23.500243: step: 2060/530, loss: 0.005498030688613653
2023-01-22 16:10:24.562819: step: 2064/530, loss: 0.003108419943600893
2023-01-22 16:10:25.597948: step: 2068/530, loss: 0.0227563064545393
2023-01-22 16:10:26.642215: step: 2072/530, loss: 0.0005292192217893898
2023-01-22 16:10:27.672253: step: 2076/530, loss: 0.007405600976198912
2023-01-22 16:10:28.719193: step: 2080/530, loss: 0.015298421494662762
2023-01-22 16:10:29.754071: step: 2084/530, loss: 0.007334030698984861
2023-01-22 16:10:30.818622: step: 2088/530, loss: 0.005176838021725416
2023-01-22 16:10:31.859724: step: 2092/530, loss: 0.005447547882795334
2023-01-22 16:10:32.891836: step: 2096/530, loss: 0.005433876533061266
2023-01-22 16:10:33.961436: step: 2100/530, loss: 0.0005200489540584385
2023-01-22 16:10:35.003755: step: 2104/530, loss: 0.0005241096368990839
2023-01-22 16:10:36.059913: step: 2108/530, loss: 0.0036094901151955128
2023-01-22 16:10:37.095173: step: 2112/530, loss: 0.0028713929932564497
2023-01-22 16:10:38.159846: step: 2116/530, loss: 0.003516589989885688
2023-01-22 16:10:39.201357: step: 2120/530, loss: 0.002706417115405202
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33976934523809527, 'r': 0.32494070208728654, 'f1': 0.3321896217264792}, 'combined': 0.244771300219511, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3612151249182718, 'r': 0.41035100588141904, 'f1': 0.38421849776160405}, 'combined': 0.2978152949156931, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3049587208171763, 'r': 0.3142174296085896, 'f1': 0.3095188512219191}, 'combined': 0.22806652195299298, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3584366092320277, 'r': 0.41015953905686997, 'f1': 0.38255771838309005}, 'combined': 0.29652799223952436, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33035275344955795, 'r': 0.34226300452269187, 'f1': 0.3362024294193078}, 'combined': 0.24772810588791097, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3591303912955931, 'r': 0.3881777023562661, 'f1': 0.3730895231127363}, 'combined': 0.28918900834575734, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:13:08.910234: step: 4/530, loss: 0.014732468873262405
2023-01-22 16:13:09.970565: step: 8/530, loss: 0.0028864946216344833
2023-01-22 16:13:11.006197: step: 12/530, loss: 0.0020161960273981094
2023-01-22 16:13:12.056206: step: 16/530, loss: 0.006533683743327856
2023-01-22 16:13:13.101735: step: 20/530, loss: 0.0011061799013987184
2023-01-22 16:13:14.146674: step: 24/530, loss: 0.0022972780279815197
2023-01-22 16:13:15.184334: step: 28/530, loss: 0.013753408566117287
2023-01-22 16:13:16.215821: step: 32/530, loss: 0.0010170890018343925
2023-01-22 16:13:17.251070: step: 36/530, loss: 0.0029799004551023245
2023-01-22 16:13:18.288023: step: 40/530, loss: 0.004848646931350231
2023-01-22 16:13:19.332956: step: 44/530, loss: 0.013234319165349007
2023-01-22 16:13:20.404992: step: 48/530, loss: 0.0018025626195594668
2023-01-22 16:13:21.453710: step: 52/530, loss: 0.0023839380592107773
2023-01-22 16:13:22.504425: step: 56/530, loss: 0.005948647856712341
2023-01-22 16:13:23.561052: step: 60/530, loss: 0.0006430851062759757
2023-01-22 16:13:24.581783: step: 64/530, loss: 0.017871620133519173
2023-01-22 16:13:25.622513: step: 68/530, loss: 0.0011540284613147378
2023-01-22 16:13:26.675590: step: 72/530, loss: 0.002732044318690896
2023-01-22 16:13:27.729218: step: 76/530, loss: 0.009911269880831242
2023-01-22 16:13:28.785723: step: 80/530, loss: 0.007694334723055363
2023-01-22 16:13:29.831015: step: 84/530, loss: 0.0046738870441913605
2023-01-22 16:13:30.892609: step: 88/530, loss: 0.002184328157454729
2023-01-22 16:13:31.931659: step: 92/530, loss: 0.001338479807600379
2023-01-22 16:13:32.993398: step: 96/530, loss: 0.00044118042569607496
2023-01-22 16:13:34.046751: step: 100/530, loss: 0.006144620478153229
2023-01-22 16:13:35.087502: step: 104/530, loss: 0.0008150660432875156
2023-01-22 16:13:36.132249: step: 108/530, loss: 0.0009665843099355698
2023-01-22 16:13:37.166367: step: 112/530, loss: 0.0027098958380520344
2023-01-22 16:13:38.199833: step: 116/530, loss: 0.003707784228026867
2023-01-22 16:13:39.259685: step: 120/530, loss: 0.005503206048160791
2023-01-22 16:13:40.294313: step: 124/530, loss: 6.726011633872986e-05
2023-01-22 16:13:41.337353: step: 128/530, loss: 0.006648343056440353
2023-01-22 16:13:42.389756: step: 132/530, loss: 0.005515591241419315
2023-01-22 16:13:43.428948: step: 136/530, loss: 0.003134507220238447
2023-01-22 16:13:44.483402: step: 140/530, loss: 0.0019207580480724573
2023-01-22 16:13:45.526848: step: 144/530, loss: 0.0049347528256475925
2023-01-22 16:13:46.567124: step: 148/530, loss: 0.0008868713048286736
2023-01-22 16:13:47.618367: step: 152/530, loss: 0.004488816950470209
2023-01-22 16:13:48.682049: step: 156/530, loss: 0.0003686470736283809
2023-01-22 16:13:49.748420: step: 160/530, loss: 0.00496239960193634
2023-01-22 16:13:50.805971: step: 164/530, loss: 0.007017552852630615
2023-01-22 16:13:51.861979: step: 168/530, loss: 0.006619418039917946
2023-01-22 16:13:52.904717: step: 172/530, loss: 0.00120442733168602
2023-01-22 16:13:53.950674: step: 176/530, loss: 0.003372407518327236
2023-01-22 16:13:54.988198: step: 180/530, loss: 0.0007262969156727195
2023-01-22 16:13:56.043100: step: 184/530, loss: 0.0002291992277605459
2023-01-22 16:13:57.095447: step: 188/530, loss: 0.006633590906858444
2023-01-22 16:13:58.168460: step: 192/530, loss: 0.013781595043838024
2023-01-22 16:13:59.211160: step: 196/530, loss: 0.00397269893437624
2023-01-22 16:14:00.270039: step: 200/530, loss: 0.003798141609877348
2023-01-22 16:14:01.321440: step: 204/530, loss: 7.607981387991458e-05
2023-01-22 16:14:02.366044: step: 208/530, loss: 0.006034656427800655
2023-01-22 16:14:03.432336: step: 212/530, loss: 0.006624757777899504
2023-01-22 16:14:04.489873: step: 216/530, loss: 0.004910145420581102
2023-01-22 16:14:05.550055: step: 220/530, loss: 0.007574915885925293
2023-01-22 16:14:06.582415: step: 224/530, loss: 0.0004487109836190939
2023-01-22 16:14:07.654863: step: 228/530, loss: 0.005052222870290279
2023-01-22 16:14:08.701444: step: 232/530, loss: 0.003695308230817318
2023-01-22 16:14:09.743179: step: 236/530, loss: 0.005169919226318598
2023-01-22 16:14:10.794756: step: 240/530, loss: 0.0016193906776607037
2023-01-22 16:14:11.840660: step: 244/530, loss: 0.010608610697090626
2023-01-22 16:14:12.877474: step: 248/530, loss: 0.0003077667788602412
2023-01-22 16:14:13.931797: step: 252/530, loss: 0.0021962961181998253
2023-01-22 16:14:14.983980: step: 256/530, loss: 0.0013021163176745176
2023-01-22 16:14:16.044776: step: 260/530, loss: 0.00019832153338938951
2023-01-22 16:14:17.088909: step: 264/530, loss: 0.0001702180306892842
2023-01-22 16:14:18.161582: step: 268/530, loss: 0.0016734946984797716
2023-01-22 16:14:19.235323: step: 272/530, loss: 0.004190403502434492
2023-01-22 16:14:20.278715: step: 276/530, loss: 0.0017102285055443645
2023-01-22 16:14:21.308119: step: 280/530, loss: 0.003818391589447856
2023-01-22 16:14:22.346843: step: 284/530, loss: 0.0009121823241002858
2023-01-22 16:14:23.395813: step: 288/530, loss: 0.004632391035556793
2023-01-22 16:14:24.453105: step: 292/530, loss: 0.0039497497491538525
2023-01-22 16:14:25.504878: step: 296/530, loss: 0.0010743652237579226
2023-01-22 16:14:26.547045: step: 300/530, loss: 0.005997119937092066
2023-01-22 16:14:27.600388: step: 304/530, loss: 0.0011809875722974539
2023-01-22 16:14:28.651933: step: 308/530, loss: 0.0005545815220102668
2023-01-22 16:14:29.689312: step: 312/530, loss: 0.003112263511866331
2023-01-22 16:14:30.730135: step: 316/530, loss: 0.0022529102861881256
2023-01-22 16:14:31.787763: step: 320/530, loss: 0.0014832214219495654
2023-01-22 16:14:32.821861: step: 324/530, loss: 0.00045701867202296853
2023-01-22 16:14:33.906018: step: 328/530, loss: 0.002436557086184621
2023-01-22 16:14:34.955356: step: 332/530, loss: 0.004066962283104658
2023-01-22 16:14:36.003767: step: 336/530, loss: 0.00031431170646101236
2023-01-22 16:14:37.037566: step: 340/530, loss: 0.005977662745863199
2023-01-22 16:14:38.091468: step: 344/530, loss: 0.018425919115543365
2023-01-22 16:14:39.141184: step: 348/530, loss: 0.009702183306217194
2023-01-22 16:14:40.191754: step: 352/530, loss: 0.007989713922142982
2023-01-22 16:14:41.232541: step: 356/530, loss: 0.006221592891961336
2023-01-22 16:14:42.289644: step: 360/530, loss: 0.0003509514208417386
2023-01-22 16:14:43.357616: step: 364/530, loss: 0.02458922192454338
2023-01-22 16:14:44.415889: step: 368/530, loss: 0.004374512936919928
2023-01-22 16:14:45.472975: step: 372/530, loss: 0.0014963810099288821
2023-01-22 16:14:46.524091: step: 376/530, loss: 0.006841498427093029
2023-01-22 16:14:47.570053: step: 380/530, loss: 0.001976480707526207
2023-01-22 16:14:48.615071: step: 384/530, loss: 0.006298382300883532
2023-01-22 16:14:49.655439: step: 388/530, loss: 0.0032454037573188543
2023-01-22 16:14:50.701523: step: 392/530, loss: 0.00010955317702610046
2023-01-22 16:14:51.758469: step: 396/530, loss: 0.008563480339944363
2023-01-22 16:14:52.784722: step: 400/530, loss: 2.296617367392173e-06
2023-01-22 16:14:53.819076: step: 404/530, loss: 0.0125796590000391
2023-01-22 16:14:54.893145: step: 408/530, loss: 0.006920378189533949
2023-01-22 16:14:55.921511: step: 412/530, loss: 2.2984605152487347e-07
2023-01-22 16:14:56.981984: step: 416/530, loss: 0.011919056065380573
2023-01-22 16:14:58.034154: step: 420/530, loss: 0.005392361897975206
2023-01-22 16:14:59.083832: step: 424/530, loss: 0.00046365190064534545
2023-01-22 16:15:00.135732: step: 428/530, loss: 4.5761949877487496e-05
2023-01-22 16:15:01.172453: step: 432/530, loss: 0.00209265248849988
2023-01-22 16:15:02.204444: step: 436/530, loss: 0.00043662512325681746
2023-01-22 16:15:03.272730: step: 440/530, loss: 0.0016920986818149686
2023-01-22 16:15:04.326577: step: 444/530, loss: 0.0062765441834926605
2023-01-22 16:15:05.369285: step: 448/530, loss: 0.004424261394888163
2023-01-22 16:15:06.429824: step: 452/530, loss: 3.123496935586445e-05
2023-01-22 16:15:07.478395: step: 456/530, loss: 0.009037133306264877
2023-01-22 16:15:08.514786: step: 460/530, loss: 0.005026660859584808
2023-01-22 16:15:09.552430: step: 464/530, loss: 0.019944775849580765
2023-01-22 16:15:10.600940: step: 468/530, loss: 0.00170858611818403
2023-01-22 16:15:11.650616: step: 472/530, loss: 0.002845579292625189
2023-01-22 16:15:12.712364: step: 476/530, loss: 7.603465746797156e-06
2023-01-22 16:15:13.751448: step: 480/530, loss: 0.002625692170113325
2023-01-22 16:15:14.805933: step: 484/530, loss: 0.010671021416783333
2023-01-22 16:15:15.857325: step: 488/530, loss: 0.0012438567355275154
2023-01-22 16:15:16.899093: step: 492/530, loss: 0.0005785999237559736
2023-01-22 16:15:17.949329: step: 496/530, loss: 0.00040261042886413634
2023-01-22 16:15:19.000813: step: 500/530, loss: 0.0013927269028499722
2023-01-22 16:15:20.048104: step: 504/530, loss: 0.013707629404962063
2023-01-22 16:15:21.093407: step: 508/530, loss: 0.033509571105241776
2023-01-22 16:15:22.166624: step: 512/530, loss: 0.0035408353433012962
2023-01-22 16:15:23.197445: step: 516/530, loss: 0.004781695548444986
2023-01-22 16:15:24.244801: step: 520/530, loss: 0.01198268961161375
2023-01-22 16:15:25.287539: step: 524/530, loss: 0.0027435270603746176
2023-01-22 16:15:26.337229: step: 528/530, loss: 0.005994144827127457
2023-01-22 16:15:27.378821: step: 532/530, loss: 0.0030710676219314337
2023-01-22 16:15:28.415338: step: 536/530, loss: 0.005427483003586531
2023-01-22 16:15:29.471436: step: 540/530, loss: 0.006961643695831299
2023-01-22 16:15:30.513337: step: 544/530, loss: 0.008791901171207428
2023-01-22 16:15:31.552448: step: 548/530, loss: 0.01079469732940197
2023-01-22 16:15:32.602435: step: 552/530, loss: 0.004237785469740629
2023-01-22 16:15:33.656536: step: 556/530, loss: 0.0012691307347267866
2023-01-22 16:15:34.716028: step: 560/530, loss: 0.0028314045630395412
2023-01-22 16:15:35.754223: step: 564/530, loss: 0.006784523371607065
2023-01-22 16:15:36.848540: step: 568/530, loss: 0.0025259586982429028
2023-01-22 16:15:37.875380: step: 572/530, loss: 0.00791935808956623
2023-01-22 16:15:38.926213: step: 576/530, loss: 0.011753004975616932
2023-01-22 16:15:39.974730: step: 580/530, loss: 0.0011276863515377045
2023-01-22 16:15:41.024604: step: 584/530, loss: 0.0020637616980820894
2023-01-22 16:15:42.084839: step: 588/530, loss: 0.0011130035854876041
2023-01-22 16:15:43.120879: step: 592/530, loss: 0.0008342540240846574
2023-01-22 16:15:44.174942: step: 596/530, loss: 0.0031309123151004314
2023-01-22 16:15:45.222916: step: 600/530, loss: 0.00013287067122291774
2023-01-22 16:15:46.288989: step: 604/530, loss: 0.0010609551100060344
2023-01-22 16:15:47.333673: step: 608/530, loss: 0.0010218010284006596
2023-01-22 16:15:48.378662: step: 612/530, loss: 0.0026290242094546556
2023-01-22 16:15:49.449349: step: 616/530, loss: 0.004376406781375408
2023-01-22 16:15:50.504080: step: 620/530, loss: 0.007087917998433113
2023-01-22 16:15:51.542800: step: 624/530, loss: 0.0009887524647638202
2023-01-22 16:15:52.586794: step: 628/530, loss: 0.001968992408365011
2023-01-22 16:15:53.643513: step: 632/530, loss: 0.005853585433214903
2023-01-22 16:15:54.683019: step: 636/530, loss: 0.0028284352738410234
2023-01-22 16:15:55.748812: step: 640/530, loss: 0.0052115130238235
2023-01-22 16:15:56.810297: step: 644/530, loss: 0.0021591002587229013
2023-01-22 16:15:57.855688: step: 648/530, loss: 0.0015258598141372204
2023-01-22 16:15:58.907311: step: 652/530, loss: 0.0013785124756395817
2023-01-22 16:15:59.964213: step: 656/530, loss: 0.0057843835093081
2023-01-22 16:16:01.008619: step: 660/530, loss: 0.0005512493080459535
2023-01-22 16:16:02.044401: step: 664/530, loss: 0.0026957234367728233
2023-01-22 16:16:03.106339: step: 668/530, loss: 0.0016912787687033415
2023-01-22 16:16:04.160813: step: 672/530, loss: 0.000615813594777137
2023-01-22 16:16:05.207253: step: 676/530, loss: 0.0016245465958490968
2023-01-22 16:16:06.260092: step: 680/530, loss: 0.00029056810308247805
2023-01-22 16:16:07.308788: step: 684/530, loss: 0.009288286790251732
2023-01-22 16:16:08.359278: step: 688/530, loss: 0.0038950475864112377
2023-01-22 16:16:09.417063: step: 692/530, loss: 0.014622300863265991
2023-01-22 16:16:10.478463: step: 696/530, loss: 0.000449638202553615
2023-01-22 16:16:11.515454: step: 700/530, loss: 0.0030872058123350143
2023-01-22 16:16:12.543408: step: 704/530, loss: 0.010924331843852997
2023-01-22 16:16:13.609571: step: 708/530, loss: 0.021274017170071602
2023-01-22 16:16:14.664630: step: 712/530, loss: 0.002134650945663452
2023-01-22 16:16:15.706627: step: 716/530, loss: 0.007354495581239462
2023-01-22 16:16:16.766067: step: 720/530, loss: 0.0027587036602199078
2023-01-22 16:16:17.808644: step: 724/530, loss: 0.0041638207621872425
2023-01-22 16:16:18.845016: step: 728/530, loss: 0.004001552704721689
2023-01-22 16:16:19.901208: step: 732/530, loss: 0.019353656098246574
2023-01-22 16:16:20.963362: step: 736/530, loss: 0.016189612448215485
2023-01-22 16:16:22.019746: step: 740/530, loss: 0.0039147185161709785
2023-01-22 16:16:23.070768: step: 744/530, loss: 0.002381126396358013
2023-01-22 16:16:24.111020: step: 748/530, loss: 0.007057988550513983
2023-01-22 16:16:25.166203: step: 752/530, loss: 0.0011352099245414138
2023-01-22 16:16:26.202409: step: 756/530, loss: 0.0017084140563383698
2023-01-22 16:16:27.256013: step: 760/530, loss: 0.00591560173779726
2023-01-22 16:16:28.301534: step: 764/530, loss: 0.0031700143590569496
2023-01-22 16:16:29.348492: step: 768/530, loss: 0.005508203990757465
2023-01-22 16:16:30.382935: step: 772/530, loss: 0.003756421385332942
2023-01-22 16:16:31.440224: step: 776/530, loss: 0.004410235211253166
2023-01-22 16:16:32.476779: step: 780/530, loss: 0.005047455430030823
2023-01-22 16:16:33.556450: step: 784/530, loss: 0.02436165325343609
2023-01-22 16:16:34.609113: step: 788/530, loss: 0.004335152916610241
2023-01-22 16:16:35.656572: step: 792/530, loss: 2.823642546445626e-07
2023-01-22 16:16:36.719211: step: 796/530, loss: 0.005086805205792189
2023-01-22 16:16:37.773735: step: 800/530, loss: 0.03161008283495903
2023-01-22 16:16:38.814857: step: 804/530, loss: 0.006230564787983894
2023-01-22 16:16:39.894983: step: 808/530, loss: 0.04716207832098007
2023-01-22 16:16:40.940444: step: 812/530, loss: 0.0014297384768724442
2023-01-22 16:16:41.981606: step: 816/530, loss: 0.005765952169895172
2023-01-22 16:16:43.023115: step: 820/530, loss: 0.013006582856178284
2023-01-22 16:16:44.071722: step: 824/530, loss: 0.005235032178461552
2023-01-22 16:16:45.120087: step: 828/530, loss: 0.0016357704298570752
2023-01-22 16:16:46.162992: step: 832/530, loss: 0.006815879140049219
2023-01-22 16:16:47.201893: step: 836/530, loss: 0.004032469354569912
2023-01-22 16:16:48.264503: step: 840/530, loss: 0.002506756689399481
2023-01-22 16:16:49.326041: step: 844/530, loss: 0.004679025150835514
2023-01-22 16:16:50.381460: step: 848/530, loss: 0.00025164702674373984
2023-01-22 16:16:51.423566: step: 852/530, loss: 0.002013260265812278
2023-01-22 16:16:52.472676: step: 856/530, loss: 0.0005976912216283381
2023-01-22 16:16:53.528763: step: 860/530, loss: 0.013096915557980537
2023-01-22 16:16:54.589588: step: 864/530, loss: 0.007861674763262272
2023-01-22 16:16:55.630563: step: 868/530, loss: 0.007597321644425392
2023-01-22 16:16:56.658955: step: 872/530, loss: 0.001777428900822997
2023-01-22 16:16:57.710893: step: 876/530, loss: 0.014843094162642956
2023-01-22 16:16:58.776524: step: 880/530, loss: 0.026443898677825928
2023-01-22 16:16:59.823427: step: 884/530, loss: 0.0011534770019352436
2023-01-22 16:17:00.870027: step: 888/530, loss: 0.00039898071554489434
2023-01-22 16:17:01.912175: step: 892/530, loss: 0.006618919316679239
2023-01-22 16:17:02.986720: step: 896/530, loss: 0.008538229390978813
2023-01-22 16:17:04.027905: step: 900/530, loss: 0.005873043555766344
2023-01-22 16:17:05.101299: step: 904/530, loss: 0.012603625655174255
2023-01-22 16:17:06.162478: step: 908/530, loss: 0.004822163376957178
2023-01-22 16:17:07.208836: step: 912/530, loss: 0.0022861638572067022
2023-01-22 16:17:08.247394: step: 916/530, loss: 0.009433708153665066
2023-01-22 16:17:09.300661: step: 920/530, loss: 0.0018214863957837224
2023-01-22 16:17:10.349113: step: 924/530, loss: 0.001309029757976532
2023-01-22 16:17:11.444652: step: 928/530, loss: 0.03557188808917999
2023-01-22 16:17:12.487012: step: 932/530, loss: 0.007164108566939831
2023-01-22 16:17:13.536663: step: 936/530, loss: 0.0006070815143175423
2023-01-22 16:17:14.581267: step: 940/530, loss: 0.005502901040017605
2023-01-22 16:17:15.616662: step: 944/530, loss: 0.0027077256236225367
2023-01-22 16:17:16.655967: step: 948/530, loss: 0.004954319912940264
2023-01-22 16:17:17.716544: step: 952/530, loss: 0.005388965364545584
2023-01-22 16:17:18.757715: step: 956/530, loss: 0.005542172584682703
2023-01-22 16:17:19.809157: step: 960/530, loss: 0.006731236819177866
2023-01-22 16:17:20.850438: step: 964/530, loss: 0.006250726990401745
2023-01-22 16:17:21.904652: step: 968/530, loss: 0.010224927216768265
2023-01-22 16:17:22.977781: step: 972/530, loss: 0.009152201004326344
2023-01-22 16:17:24.035431: step: 976/530, loss: 0.0055384766310453415
2023-01-22 16:17:25.082610: step: 980/530, loss: 1.5087374549693777e-07
2023-01-22 16:17:26.142252: step: 984/530, loss: 0.005073467269539833
2023-01-22 16:17:27.187404: step: 988/530, loss: 0.002183017088100314
2023-01-22 16:17:28.231364: step: 992/530, loss: 0.004343661945313215
2023-01-22 16:17:29.288476: step: 996/530, loss: 0.0021708407439291477
2023-01-22 16:17:30.342444: step: 1000/530, loss: 0.0024626783560961485
2023-01-22 16:17:31.388602: step: 1004/530, loss: 0.0016927821561694145
2023-01-22 16:17:32.441801: step: 1008/530, loss: 0.0043599558994174
2023-01-22 16:17:33.497352: step: 1012/530, loss: 0.0026770462282001972
2023-01-22 16:17:34.539681: step: 1016/530, loss: 0.002781082410365343
2023-01-22 16:17:35.589938: step: 1020/530, loss: 0.004273316357284784
2023-01-22 16:17:36.632472: step: 1024/530, loss: 0.00024193669378291816
2023-01-22 16:17:37.702466: step: 1028/530, loss: 0.00485656363889575
2023-01-22 16:17:38.756276: step: 1032/530, loss: 0.004452936816960573
2023-01-22 16:17:39.803421: step: 1036/530, loss: 0.0025070100091397762
2023-01-22 16:17:40.854915: step: 1040/530, loss: 0.001395134488120675
2023-01-22 16:17:41.903934: step: 1044/530, loss: 0.00028120604110881686
2023-01-22 16:17:42.954900: step: 1048/530, loss: 0.0003076897992286831
2023-01-22 16:17:44.007856: step: 1052/530, loss: 0.0025341338478028774
2023-01-22 16:17:45.056441: step: 1056/530, loss: 0.006551379803568125
2023-01-22 16:17:46.095770: step: 1060/530, loss: 0.005033473484218121
2023-01-22 16:17:47.134386: step: 1064/530, loss: 0.008835405111312866
2023-01-22 16:17:48.201530: step: 1068/530, loss: 0.0028214084450155497
2023-01-22 16:17:49.251036: step: 1072/530, loss: 0.008950789459049702
2023-01-22 16:17:50.286966: step: 1076/530, loss: 0.0014356850879266858
2023-01-22 16:17:51.320963: step: 1080/530, loss: 0.00247561139985919
2023-01-22 16:17:52.374131: step: 1084/530, loss: 0.01638169027864933
2023-01-22 16:17:53.427495: step: 1088/530, loss: 0.0026480292435735464
2023-01-22 16:17:54.516047: step: 1092/530, loss: 0.005513367708772421
2023-01-22 16:17:55.553058: step: 1096/530, loss: 0.0071080029010772705
2023-01-22 16:17:56.590749: step: 1100/530, loss: 0.008038556203246117
2023-01-22 16:17:57.633595: step: 1104/530, loss: 0.0076973047107458115
2023-01-22 16:17:58.672372: step: 1108/530, loss: 0.006864570081233978
2023-01-22 16:17:59.715941: step: 1112/530, loss: 0.006138910073786974
2023-01-22 16:18:00.756225: step: 1116/530, loss: 0.003295325906947255
2023-01-22 16:18:01.805637: step: 1120/530, loss: 0.0032680127769708633
2023-01-22 16:18:02.845539: step: 1124/530, loss: 0.0033776836935430765
2023-01-22 16:18:03.916844: step: 1128/530, loss: 7.359675691986922e-06
2023-01-22 16:18:04.959133: step: 1132/530, loss: 0.00015860758139751852
2023-01-22 16:18:05.990750: step: 1136/530, loss: 0.0003294216876383871
2023-01-22 16:18:07.046939: step: 1140/530, loss: 0.003498536068946123
2023-01-22 16:18:08.101157: step: 1144/530, loss: 0.0031569499988108873
2023-01-22 16:18:09.152873: step: 1148/530, loss: 0.0011496113147586584
2023-01-22 16:18:10.208744: step: 1152/530, loss: 0.001786165637895465
2023-01-22 16:18:11.246842: step: 1156/530, loss: 0.004533456638455391
2023-01-22 16:18:12.284734: step: 1160/530, loss: 0.013620489276945591
2023-01-22 16:18:13.328104: step: 1164/530, loss: 0.0005204153130762279
2023-01-22 16:18:14.363972: step: 1168/530, loss: 0.0036813293118029833
2023-01-22 16:18:15.412521: step: 1172/530, loss: 0.0005867261788807809
2023-01-22 16:18:16.471120: step: 1176/530, loss: 0.0030796497594565153
2023-01-22 16:18:17.512424: step: 1180/530, loss: 0.0002512074715923518
2023-01-22 16:18:18.566410: step: 1184/530, loss: 0.03189973533153534
2023-01-22 16:18:19.614725: step: 1188/530, loss: 0.0011992198415100574
2023-01-22 16:18:20.657426: step: 1192/530, loss: 0.010631580837070942
2023-01-22 16:18:21.693625: step: 1196/530, loss: 0.009094943292438984
2023-01-22 16:18:22.728473: step: 1200/530, loss: 0.0006700368248857558
2023-01-22 16:18:23.777647: step: 1204/530, loss: 0.003930522594600916
2023-01-22 16:18:24.822012: step: 1208/530, loss: 0.002903315704315901
2023-01-22 16:18:25.863677: step: 1212/530, loss: 0.004415900446474552
2023-01-22 16:18:26.902980: step: 1216/530, loss: 0.0010305369505658746
2023-01-22 16:18:27.959526: step: 1220/530, loss: 0.006731036584824324
2023-01-22 16:18:29.004997: step: 1224/530, loss: 0.00722704129293561
2023-01-22 16:18:30.047655: step: 1228/530, loss: 0.018307218328118324
2023-01-22 16:18:31.111395: step: 1232/530, loss: 0.05539613589644432
2023-01-22 16:18:32.154381: step: 1236/530, loss: 0.0029454559553414583
2023-01-22 16:18:33.229975: step: 1240/530, loss: 0.007397875189781189
2023-01-22 16:18:34.290068: step: 1244/530, loss: 0.0032214312814176083
2023-01-22 16:18:35.341144: step: 1248/530, loss: 0.003888509701937437
2023-01-22 16:18:36.382902: step: 1252/530, loss: 0.009760660119354725
2023-01-22 16:18:37.417085: step: 1256/530, loss: 0.007573803421109915
2023-01-22 16:18:38.472936: step: 1260/530, loss: 0.022202182561159134
2023-01-22 16:18:39.522077: step: 1264/530, loss: 0.005713118240237236
2023-01-22 16:18:40.567619: step: 1268/530, loss: 0.004170641303062439
2023-01-22 16:18:41.636627: step: 1272/530, loss: 0.004473092500120401
2023-01-22 16:18:42.682320: step: 1276/530, loss: 0.011876476928591728
2023-01-22 16:18:43.725936: step: 1280/530, loss: 0.005746433511376381
2023-01-22 16:18:44.775762: step: 1284/530, loss: 0.0008601548615843058
2023-01-22 16:18:45.821361: step: 1288/530, loss: 0.005444884765893221
2023-01-22 16:18:46.876114: step: 1292/530, loss: 0.024241046980023384
2023-01-22 16:18:47.930899: step: 1296/530, loss: 0.0017819450004026294
2023-01-22 16:18:48.970963: step: 1300/530, loss: 0.01759078912436962
2023-01-22 16:18:50.014009: step: 1304/530, loss: 0.0006419402780011296
2023-01-22 16:18:51.051294: step: 1308/530, loss: 0.009541204199194908
2023-01-22 16:18:52.102728: step: 1312/530, loss: 0.00030007094028405845
2023-01-22 16:18:53.155504: step: 1316/530, loss: 0.004012543708086014
2023-01-22 16:18:54.185303: step: 1320/530, loss: 0.003850433975458145
2023-01-22 16:18:55.225406: step: 1324/530, loss: 0.001178127247840166
2023-01-22 16:18:56.274348: step: 1328/530, loss: 0.007947556674480438
2023-01-22 16:18:57.334233: step: 1332/530, loss: 0.004746435675770044
2023-01-22 16:18:58.368950: step: 1336/530, loss: 0.003821619786322117
2023-01-22 16:18:59.406808: step: 1340/530, loss: 0.0006737510557286441
2023-01-22 16:19:00.447258: step: 1344/530, loss: 0.015957266092300415
2023-01-22 16:19:01.485397: step: 1348/530, loss: 0.005501211155205965
2023-01-22 16:19:02.533393: step: 1352/530, loss: 0.0033074773382395506
2023-01-22 16:19:03.574360: step: 1356/530, loss: 0.0009623094229027629
2023-01-22 16:19:04.609030: step: 1360/530, loss: 0.000806731462944299
2023-01-22 16:19:05.662379: step: 1364/530, loss: 0.0020697119180113077
2023-01-22 16:19:06.709520: step: 1368/530, loss: 0.0010327850468456745
2023-01-22 16:19:07.736694: step: 1372/530, loss: 0.0012403945438563824
2023-01-22 16:19:08.792748: step: 1376/530, loss: 0.001363015966489911
2023-01-22 16:19:09.840159: step: 1380/530, loss: 0.0006392548675648868
2023-01-22 16:19:10.887963: step: 1384/530, loss: 0.0020197764970362186
2023-01-22 16:19:11.936769: step: 1388/530, loss: 0.0009072396787814796
2023-01-22 16:19:12.993110: step: 1392/530, loss: 0.0030043385922908783
2023-01-22 16:19:14.043578: step: 1396/530, loss: 0.009019937366247177
2023-01-22 16:19:15.096545: step: 1400/530, loss: 0.004924031440168619
2023-01-22 16:19:16.145816: step: 1404/530, loss: 0.010605115443468094
2023-01-22 16:19:17.214635: step: 1408/530, loss: 0.0039377338252961636
2023-01-22 16:19:18.261865: step: 1412/530, loss: 0.005646178964525461
2023-01-22 16:19:19.316737: step: 1416/530, loss: 0.0025246378500014544
2023-01-22 16:19:20.360349: step: 1420/530, loss: 0.0012028859928250313
2023-01-22 16:19:21.402822: step: 1424/530, loss: 0.0008891834877431393
2023-01-22 16:19:22.461721: step: 1428/530, loss: 0.003501572646200657
2023-01-22 16:19:23.502059: step: 1432/530, loss: 0.0033416440710425377
2023-01-22 16:19:24.545223: step: 1436/530, loss: 0.004756961949169636
2023-01-22 16:19:25.599494: step: 1440/530, loss: 0.0018819908145815134
2023-01-22 16:19:26.649544: step: 1444/530, loss: 0.002732961205765605
2023-01-22 16:19:27.698879: step: 1448/530, loss: 0.002800561022013426
2023-01-22 16:19:28.745711: step: 1452/530, loss: 0.0005214640987105668
2023-01-22 16:19:29.817081: step: 1456/530, loss: 0.006584409158676863
2023-01-22 16:19:30.857303: step: 1460/530, loss: 0.0034163668751716614
2023-01-22 16:19:31.917483: step: 1464/530, loss: 0.009226624853909016
2023-01-22 16:19:32.992005: step: 1468/530, loss: 0.00355134648270905
2023-01-22 16:19:34.043815: step: 1472/530, loss: 0.0009333228226751089
2023-01-22 16:19:35.089478: step: 1476/530, loss: 0.0017866671551018953
2023-01-22 16:19:36.136762: step: 1480/530, loss: 0.015849852934479713
2023-01-22 16:19:37.192240: step: 1484/530, loss: 0.0033516413532197475
2023-01-22 16:19:38.247633: step: 1488/530, loss: 0.0004385552601888776
2023-01-22 16:19:39.311359: step: 1492/530, loss: 0.003435111604630947
2023-01-22 16:19:40.366581: step: 1496/530, loss: 0.0068300343118608
2023-01-22 16:19:41.403420: step: 1500/530, loss: 0.0062282937578856945
2023-01-22 16:19:42.453679: step: 1504/530, loss: 0.007188333664089441
2023-01-22 16:19:43.488088: step: 1508/530, loss: 0.0021044963505119085
2023-01-22 16:19:44.529908: step: 1512/530, loss: 0.0014146534958854318
2023-01-22 16:19:45.572373: step: 1516/530, loss: 0.000188202437129803
2023-01-22 16:19:46.607694: step: 1520/530, loss: 0.0015249266289174557
2023-01-22 16:19:47.645917: step: 1524/530, loss: 0.019841352477669716
2023-01-22 16:19:48.700791: step: 1528/530, loss: 0.013087257742881775
2023-01-22 16:19:49.742437: step: 1532/530, loss: 0.0031631398014724255
2023-01-22 16:19:50.789879: step: 1536/530, loss: 0.004450693726539612
2023-01-22 16:19:51.837907: step: 1540/530, loss: 0.00632547028362751
2023-01-22 16:19:52.885626: step: 1544/530, loss: 0.0056480467319488525
2023-01-22 16:19:53.917539: step: 1548/530, loss: 0.017980292439460754
2023-01-22 16:19:54.957748: step: 1552/530, loss: 0.006080025341361761
2023-01-22 16:19:56.026681: step: 1556/530, loss: 0.002057814970612526
2023-01-22 16:19:57.070345: step: 1560/530, loss: 0.00877632386982441
2023-01-22 16:19:58.113565: step: 1564/530, loss: 1.4071784789848607e-05
2023-01-22 16:19:59.159393: step: 1568/530, loss: 0.003770629409700632
2023-01-22 16:20:00.195544: step: 1572/530, loss: 0.001053656218573451
2023-01-22 16:20:01.257970: step: 1576/530, loss: 0.0025587636046111584
2023-01-22 16:20:02.302831: step: 1580/530, loss: 0.005507788620889187
2023-01-22 16:20:03.350752: step: 1584/530, loss: 0.01527484506368637
2023-01-22 16:20:04.398041: step: 1588/530, loss: 0.01617465354502201
2023-01-22 16:20:05.446409: step: 1592/530, loss: 0.0035356669686734676
2023-01-22 16:20:06.500006: step: 1596/530, loss: 0.002311212010681629
2023-01-22 16:20:07.533927: step: 1600/530, loss: 0.0016364060575142503
2023-01-22 16:20:08.572696: step: 1604/530, loss: 0.0013877179007977247
2023-01-22 16:20:09.645532: step: 1608/530, loss: 0.0070881107822060585
2023-01-22 16:20:10.697486: step: 1612/530, loss: 1.250940294994507e-05
2023-01-22 16:20:11.745861: step: 1616/530, loss: 0.01038957666605711
2023-01-22 16:20:12.804705: step: 1620/530, loss: 0.001286824350245297
2023-01-22 16:20:13.869157: step: 1624/530, loss: 0.009222668595612049
2023-01-22 16:20:14.926633: step: 1628/530, loss: 0.0006454787217080593
2023-01-22 16:20:15.981735: step: 1632/530, loss: 0.006494362372905016
2023-01-22 16:20:17.018448: step: 1636/530, loss: 0.0015890697250142694
2023-01-22 16:20:18.072243: step: 1640/530, loss: 0.0045647588558495045
2023-01-22 16:20:19.113810: step: 1644/530, loss: 0.0002089084155159071
2023-01-22 16:20:20.173807: step: 1648/530, loss: 0.004456041846424341
2023-01-22 16:20:21.216925: step: 1652/530, loss: 0.00011728770914487541
2023-01-22 16:20:22.253310: step: 1656/530, loss: 0.002299683867022395
2023-01-22 16:20:23.293128: step: 1660/530, loss: 0.0023643369786441326
2023-01-22 16:20:24.325978: step: 1664/530, loss: 0.0036206389777362347
2023-01-22 16:20:25.391888: step: 1668/530, loss: 0.006230282597243786
2023-01-22 16:20:26.434570: step: 1672/530, loss: 0.0019537578336894512
2023-01-22 16:20:27.483260: step: 1676/530, loss: 6.323368870653212e-05
2023-01-22 16:20:28.549712: step: 1680/530, loss: 0.005761615000665188
2023-01-22 16:20:29.581561: step: 1684/530, loss: 0.00046067178482189775
2023-01-22 16:20:30.627069: step: 1688/530, loss: 0.0036656286101788282
2023-01-22 16:20:31.689098: step: 1692/530, loss: 0.012993012554943562
2023-01-22 16:20:32.736529: step: 1696/530, loss: 0.002271597972139716
2023-01-22 16:20:33.778304: step: 1700/530, loss: 0.0034315655939280987
2023-01-22 16:20:34.812451: step: 1704/530, loss: 0.0003701582318171859
2023-01-22 16:20:35.855104: step: 1708/530, loss: 0.014921503141522408
2023-01-22 16:20:36.885765: step: 1712/530, loss: 0.0035794973373413086
2023-01-22 16:20:37.916149: step: 1716/530, loss: 0.013946876861155033
2023-01-22 16:20:38.950924: step: 1720/530, loss: 0.004493516869843006
2023-01-22 16:20:39.995170: step: 1724/530, loss: 0.000817067688331008
2023-01-22 16:20:41.042878: step: 1728/530, loss: 0.006036113481968641
2023-01-22 16:20:42.083353: step: 1732/530, loss: 0.004596680868417025
2023-01-22 16:20:43.121294: step: 1736/530, loss: 0.0007401639595627785
2023-01-22 16:20:44.173250: step: 1740/530, loss: 0.006351632997393608
2023-01-22 16:20:45.220660: step: 1744/530, loss: 8.505427103955299e-05
2023-01-22 16:20:46.272749: step: 1748/530, loss: 0.00013968886923976243
2023-01-22 16:20:47.327235: step: 1752/530, loss: 0.004467634949833155
2023-01-22 16:20:48.367160: step: 1756/530, loss: 0.005428646225482225
2023-01-22 16:20:49.424601: step: 1760/530, loss: 0.027409780770540237
2023-01-22 16:20:50.462510: step: 1764/530, loss: 0.0029004737734794617
2023-01-22 16:20:51.493835: step: 1768/530, loss: 3.3422054457332706e-06
2023-01-22 16:20:52.550259: step: 1772/530, loss: 0.0032002448569983244
2023-01-22 16:20:53.599490: step: 1776/530, loss: 0.006825991906225681
2023-01-22 16:20:54.664065: step: 1780/530, loss: 0.014038383960723877
2023-01-22 16:20:55.714957: step: 1784/530, loss: 0.003744417568668723
2023-01-22 16:20:56.761307: step: 1788/530, loss: 0.004952542949467897
2023-01-22 16:20:57.810637: step: 1792/530, loss: 0.003103705821558833
2023-01-22 16:20:58.858635: step: 1796/530, loss: 0.01318169105798006
2023-01-22 16:20:59.900104: step: 1800/530, loss: 0.0002455712528899312
2023-01-22 16:21:00.935206: step: 1804/530, loss: 0.0026007883716374636
2023-01-22 16:21:02.000135: step: 1808/530, loss: 0.0029576849192380905
2023-01-22 16:21:03.043391: step: 1812/530, loss: 0.003828586544841528
2023-01-22 16:21:04.086508: step: 1816/530, loss: 0.004853245336562395
2023-01-22 16:21:05.119964: step: 1820/530, loss: 0.003916988614946604
2023-01-22 16:21:06.173028: step: 1824/530, loss: 0.0003066852514166385
2023-01-22 16:21:07.215884: step: 1828/530, loss: 0.004145803861320019
2023-01-22 16:21:08.271242: step: 1832/530, loss: 0.0013616053620353341
2023-01-22 16:21:09.331462: step: 1836/530, loss: 0.005522761959582567
2023-01-22 16:21:10.384266: step: 1840/530, loss: 0.0035444784443825483
2023-01-22 16:21:11.441866: step: 1844/530, loss: 0.0006922088796272874
2023-01-22 16:21:12.480248: step: 1848/530, loss: 0.00549279572442174
2023-01-22 16:21:13.524044: step: 1852/530, loss: 0.005062986630946398
2023-01-22 16:21:14.589421: step: 1856/530, loss: 0.0011594189563766122
2023-01-22 16:21:15.613136: step: 1860/530, loss: 8.112152136163786e-05
2023-01-22 16:21:16.659756: step: 1864/530, loss: 0.030368462204933167
2023-01-22 16:21:17.707988: step: 1868/530, loss: 0.005716988351196051
2023-01-22 16:21:18.738946: step: 1872/530, loss: 0.009531802497804165
2023-01-22 16:21:19.782397: step: 1876/530, loss: 0.003937490750104189
2023-01-22 16:21:20.813157: step: 1880/530, loss: 0.0015087856445461512
2023-01-22 16:21:21.847401: step: 1884/530, loss: 0.008050847798585892
2023-01-22 16:21:22.913697: step: 1888/530, loss: 0.013968897983431816
2023-01-22 16:21:23.968492: step: 1892/530, loss: 0.008272671140730381
2023-01-22 16:21:25.021270: step: 1896/530, loss: 0.0004494102322496474
2023-01-22 16:21:26.063226: step: 1900/530, loss: 0.0029197088442742825
2023-01-22 16:21:27.091005: step: 1904/530, loss: 0.0011335788294672966
2023-01-22 16:21:28.127510: step: 1908/530, loss: 0.020606601610779762
2023-01-22 16:21:29.163102: step: 1912/530, loss: 0.0009659072384238243
2023-01-22 16:21:30.197170: step: 1916/530, loss: 0.005238627549260855
2023-01-22 16:21:31.257614: step: 1920/530, loss: 0.03141063451766968
2023-01-22 16:21:32.308562: step: 1924/530, loss: 0.004119644407182932
2023-01-22 16:21:33.341764: step: 1928/530, loss: 0.004491072613745928
2023-01-22 16:21:34.387352: step: 1932/530, loss: 0.003926880192011595
2023-01-22 16:21:35.421629: step: 1936/530, loss: 0.0037270341999828815
2023-01-22 16:21:36.456628: step: 1940/530, loss: 0.00832485593855381
2023-01-22 16:21:37.501719: step: 1944/530, loss: 0.0034805391915142536
2023-01-22 16:21:38.560220: step: 1948/530, loss: 0.007315187249332666
2023-01-22 16:21:39.578748: step: 1952/530, loss: 0.007283097133040428
2023-01-22 16:21:40.627943: step: 1956/530, loss: 0.0072958446107804775
2023-01-22 16:21:41.689815: step: 1960/530, loss: 0.0042175170965492725
2023-01-22 16:21:42.717701: step: 1964/530, loss: 5.311781569616869e-05
2023-01-22 16:21:43.748003: step: 1968/530, loss: 0.0035744302440434694
2023-01-22 16:21:44.787468: step: 1972/530, loss: 0.0010876110754907131
2023-01-22 16:21:45.833033: step: 1976/530, loss: 0.002590608550235629
2023-01-22 16:21:46.884921: step: 1980/530, loss: 0.00675234803929925
2023-01-22 16:21:47.948213: step: 1984/530, loss: 0.02603055350482464
2023-01-22 16:21:48.985469: step: 1988/530, loss: 0.005563122685998678
2023-01-22 16:21:50.021109: step: 1992/530, loss: 0.00038442268851213157
2023-01-22 16:21:51.056436: step: 1996/530, loss: 0.000415379909100011
2023-01-22 16:21:52.082519: step: 2000/530, loss: 0.007721236906945705
2023-01-22 16:21:53.112084: step: 2004/530, loss: 0.005578874610364437
2023-01-22 16:21:54.168444: step: 2008/530, loss: 0.001538212993182242
2023-01-22 16:21:55.218823: step: 2012/530, loss: 0.0018273445311933756
2023-01-22 16:21:56.272809: step: 2016/530, loss: 0.0002353592572035268
2023-01-22 16:21:57.317937: step: 2020/530, loss: 0.003976296167820692
2023-01-22 16:21:58.355213: step: 2024/530, loss: 0.0030448297038674355
2023-01-22 16:21:59.424607: step: 2028/530, loss: 0.006004220340400934
2023-01-22 16:22:00.468387: step: 2032/530, loss: 0.0221035648137331
2023-01-22 16:22:01.504478: step: 2036/530, loss: 5.662008697981946e-05
2023-01-22 16:22:02.554533: step: 2040/530, loss: 0.008959939703345299
2023-01-22 16:22:03.584186: step: 2044/530, loss: 0.002308865077793598
2023-01-22 16:22:04.638645: step: 2048/530, loss: 0.004059710539877415
2023-01-22 16:22:05.698054: step: 2052/530, loss: 0.004756842274218798
2023-01-22 16:22:06.744395: step: 2056/530, loss: 0.0013233455829322338
2023-01-22 16:22:07.788512: step: 2060/530, loss: 0.008637331426143646
2023-01-22 16:22:08.841248: step: 2064/530, loss: 0.0036857964005321264
2023-01-22 16:22:09.881162: step: 2068/530, loss: 0.00605457928031683
2023-01-22 16:22:10.914908: step: 2072/530, loss: 0.011533870361745358
2023-01-22 16:22:11.947621: step: 2076/530, loss: 0.01579107902944088
2023-01-22 16:22:13.005345: step: 2080/530, loss: 0.0031185075640678406
2023-01-22 16:22:14.047412: step: 2084/530, loss: 0.0025394295807927847
2023-01-22 16:22:15.098849: step: 2088/530, loss: 0.002315706806257367
2023-01-22 16:22:16.165024: step: 2092/530, loss: 0.001849551685154438
2023-01-22 16:22:17.222919: step: 2096/530, loss: 0.010271499864757061
2023-01-22 16:22:18.265229: step: 2100/530, loss: 0.0006917126011103392
2023-01-22 16:22:19.293245: step: 2104/530, loss: 0.004060756415128708
2023-01-22 16:22:20.332924: step: 2108/530, loss: 0.0023847725242376328
2023-01-22 16:22:21.365546: step: 2112/530, loss: 0.002044428139925003
2023-01-22 16:22:22.419901: step: 2116/530, loss: 0.0037294221110641956
2023-01-22 16:22:23.466915: step: 2120/530, loss: 0.00868659932166338
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3389043522267206, 'r': 0.3176826375711575, 'f1': 0.3279505386875612}, 'combined': 0.24164776534872928, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3605145719861433, 'r': 0.4069043147049485, 'f1': 0.3823073354049948}, 'combined': 0.29633391548138355, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31370334345267176, 'r': 0.3178701810317395, 'f1': 0.3157730167836508}, 'combined': 0.2326748544721637, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3616463472075635, 'r': 0.40884651384678594, 'f1': 0.3838006963462494}, 'combined': 0.2974914488425474, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32593009978216564, 'r': 0.3308778052817052, 'f1': 0.32838531710632507}, 'combined': 0.24196812839413426, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3614947306788858, 'r': 0.3884074817680308, 'f1': 0.37446817914365754}, 'combined': 0.29025763168072977, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 12
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:24:51.716304: step: 4/530, loss: 0.0002098134864354506
2023-01-22 16:24:52.752852: step: 8/530, loss: 0.033779583871364594
2023-01-22 16:24:53.792457: step: 12/530, loss: 0.0023955267388373613
2023-01-22 16:24:54.836405: step: 16/530, loss: 0.000597143720369786
2023-01-22 16:24:55.883629: step: 20/530, loss: 0.0015304861590266228
2023-01-22 16:24:56.926993: step: 24/530, loss: 0.004038474056869745
2023-01-22 16:24:57.977026: step: 28/530, loss: 0.0035547122824937105
2023-01-22 16:24:59.044801: step: 32/530, loss: 8.435960626229644e-05
2023-01-22 16:25:00.075529: step: 36/530, loss: 6.203541943250457e-06
2023-01-22 16:25:01.134000: step: 40/530, loss: 0.006693084258586168
2023-01-22 16:25:02.190311: step: 44/530, loss: 0.013135098852217197
2023-01-22 16:25:03.254379: step: 48/530, loss: 0.0016470348928123713
2023-01-22 16:25:04.312456: step: 52/530, loss: 0.0039216866716742516
2023-01-22 16:25:05.349972: step: 56/530, loss: 9.481578672421165e-06
2023-01-22 16:25:06.401789: step: 60/530, loss: 0.0037431931123137474
2023-01-22 16:25:07.435130: step: 64/530, loss: 0.007498991210013628
2023-01-22 16:25:08.469290: step: 68/530, loss: 0.002700318116694689
2023-01-22 16:25:09.503251: step: 72/530, loss: 0.008197540417313576
2023-01-22 16:25:10.542502: step: 76/530, loss: 0.0007971164304763079
2023-01-22 16:25:11.558409: step: 80/530, loss: 0.0027596834115684032
2023-01-22 16:25:12.595222: step: 84/530, loss: 0.009794579818844795
2023-01-22 16:25:13.636695: step: 88/530, loss: 0.0028697459492832422
2023-01-22 16:25:14.679536: step: 92/530, loss: 0.009943623095750809
2023-01-22 16:25:15.733255: step: 96/530, loss: 0.03528591990470886
2023-01-22 16:25:16.781524: step: 100/530, loss: 0.0034879918675869703
2023-01-22 16:25:17.836055: step: 104/530, loss: 0.00262234965339303
2023-01-22 16:25:18.892731: step: 108/530, loss: 0.0032907037530094385
2023-01-22 16:25:19.954165: step: 112/530, loss: 0.00034220938687212765
2023-01-22 16:25:20.987875: step: 116/530, loss: 2.608080285426695e-05
2023-01-22 16:25:22.024315: step: 120/530, loss: 0.006654891185462475
2023-01-22 16:25:23.067922: step: 124/530, loss: 0.003869660198688507
2023-01-22 16:25:24.109058: step: 128/530, loss: 0.0020381638314574957
2023-01-22 16:25:25.162093: step: 132/530, loss: 0.0001978184300241992
2023-01-22 16:25:26.211937: step: 136/530, loss: 0.00815041083842516
2023-01-22 16:25:27.254897: step: 140/530, loss: 0.0018543227342888713
2023-01-22 16:25:28.321658: step: 144/530, loss: 0.0017679610755294561
2023-01-22 16:25:29.415034: step: 148/530, loss: 0.002873451681807637
2023-01-22 16:25:30.473273: step: 152/530, loss: 0.0010104554239660501
2023-01-22 16:25:31.519264: step: 156/530, loss: 0.001551167108118534
2023-01-22 16:25:32.583298: step: 160/530, loss: 0.0031594280153512955
2023-01-22 16:25:33.652176: step: 164/530, loss: 0.011970771476626396
2023-01-22 16:25:34.730010: step: 168/530, loss: 0.009992629289627075
2023-01-22 16:25:35.773510: step: 172/530, loss: 0.004959688056260347
2023-01-22 16:25:36.824993: step: 176/530, loss: 0.001493844436481595
2023-01-22 16:25:37.910413: step: 180/530, loss: 0.007817437872290611
2023-01-22 16:25:38.946132: step: 184/530, loss: 0.002572344383224845
2023-01-22 16:25:39.991871: step: 188/530, loss: 0.0009903431637212634
2023-01-22 16:25:41.048313: step: 192/530, loss: 0.0005465737194754183
2023-01-22 16:25:42.099939: step: 196/530, loss: 0.002872624434530735
2023-01-22 16:25:43.155689: step: 200/530, loss: 0.0024414220824837685
2023-01-22 16:25:44.213240: step: 204/530, loss: 0.0009540935861878097
2023-01-22 16:25:45.257134: step: 208/530, loss: 0.0010491018183529377
2023-01-22 16:25:46.302322: step: 212/530, loss: 0.0054084244184195995
2023-01-22 16:25:47.345814: step: 216/530, loss: 2.3314871214097366e-05
2023-01-22 16:25:48.403626: step: 220/530, loss: 0.005042777396738529
2023-01-22 16:25:49.452698: step: 224/530, loss: 0.001870562438853085
2023-01-22 16:25:50.505750: step: 228/530, loss: 0.010852418839931488
2023-01-22 16:25:51.554949: step: 232/530, loss: 0.006877579260617495
2023-01-22 16:25:52.589780: step: 236/530, loss: 0.0007135175983421504
2023-01-22 16:25:53.629745: step: 240/530, loss: 0.0014545349404215813
2023-01-22 16:25:54.694403: step: 244/530, loss: 0.0016862108604982495
2023-01-22 16:25:55.758081: step: 248/530, loss: 0.0029115641955286264
2023-01-22 16:25:56.802216: step: 252/530, loss: 0.0021626609377563
2023-01-22 16:25:57.848652: step: 256/530, loss: 0.005136611871421337
2023-01-22 16:25:58.884926: step: 260/530, loss: 0.012904365547001362
2023-01-22 16:25:59.934208: step: 264/530, loss: 0.005243342369794846
2023-01-22 16:26:00.989087: step: 268/530, loss: 3.0413202694035135e-06
2023-01-22 16:26:02.038276: step: 272/530, loss: 0.005616612732410431
2023-01-22 16:26:03.095205: step: 276/530, loss: 0.0077189975418150425
2023-01-22 16:26:04.144535: step: 280/530, loss: 0.0020084225106984377
2023-01-22 16:26:05.163962: step: 284/530, loss: 0.000200699592824094
2023-01-22 16:26:06.206761: step: 288/530, loss: 0.0007427338277921081
2023-01-22 16:26:07.246218: step: 292/530, loss: 0.0035736786667257547
2023-01-22 16:26:08.305390: step: 296/530, loss: 0.0026529652532190084
2023-01-22 16:26:09.351274: step: 300/530, loss: 0.0012337294174358249
2023-01-22 16:26:10.403787: step: 304/530, loss: 0.00526558980345726
2023-01-22 16:26:11.445823: step: 308/530, loss: 0.002192672109231353
2023-01-22 16:26:12.493395: step: 312/530, loss: 0.0008886989089660347
2023-01-22 16:26:13.547365: step: 316/530, loss: 0.003497776575386524
2023-01-22 16:26:14.597875: step: 320/530, loss: 0.0018555395072326064
2023-01-22 16:26:15.641864: step: 324/530, loss: 0.004081949591636658
2023-01-22 16:26:16.695298: step: 328/530, loss: 0.0022255147341638803
2023-01-22 16:26:17.742346: step: 332/530, loss: 0.00015214842278510332
2023-01-22 16:26:18.804836: step: 336/530, loss: 0.0017819913337007165
2023-01-22 16:26:19.855096: step: 340/530, loss: 0.0015917300479486585
2023-01-22 16:26:20.903644: step: 344/530, loss: 0.00018158002058044076
2023-01-22 16:26:21.940843: step: 348/530, loss: 0.00040777577669359744
2023-01-22 16:26:22.996393: step: 352/530, loss: 0.0012022678274661303
2023-01-22 16:26:24.025845: step: 356/530, loss: 0.008302228525280952
2023-01-22 16:26:25.071571: step: 360/530, loss: 0.002529502846300602
2023-01-22 16:26:26.113380: step: 364/530, loss: 0.0023683158215135336
2023-01-22 16:26:27.156766: step: 368/530, loss: 0.015279468148946762
2023-01-22 16:26:28.209703: step: 372/530, loss: 0.0036307775881141424
2023-01-22 16:26:29.274385: step: 376/530, loss: 0.003783815773203969
2023-01-22 16:26:30.314062: step: 380/530, loss: 0.004744145553559065
2023-01-22 16:26:31.371808: step: 384/530, loss: 0.001663829549215734
2023-01-22 16:26:32.443134: step: 388/530, loss: 0.0013454323634505272
2023-01-22 16:26:33.491580: step: 392/530, loss: 0.002568910364061594
2023-01-22 16:26:34.548539: step: 396/530, loss: 0.011700435541570187
2023-01-22 16:26:35.597955: step: 400/530, loss: 0.0002411395835224539
2023-01-22 16:26:36.658794: step: 404/530, loss: 0.007561087608337402
2023-01-22 16:26:37.687054: step: 408/530, loss: 7.613570573994366e-07
2023-01-22 16:26:38.728491: step: 412/530, loss: 6.0423910326790065e-05
2023-01-22 16:26:39.785789: step: 416/530, loss: 0.005288333166390657
2023-01-22 16:26:40.839194: step: 420/530, loss: 0.0037153270095586777
2023-01-22 16:26:41.885064: step: 424/530, loss: 0.004138066899031401
2023-01-22 16:26:42.929693: step: 428/530, loss: 0.011536558158695698
2023-01-22 16:26:43.966159: step: 432/530, loss: 0.000436519825598225
2023-01-22 16:26:45.032124: step: 436/530, loss: 0.006147042382508516
2023-01-22 16:26:46.086621: step: 440/530, loss: 0.0058008343912661076
2023-01-22 16:26:47.119034: step: 444/530, loss: 5.1854538469342515e-05
2023-01-22 16:26:48.174061: step: 448/530, loss: 0.0025187800638377666
2023-01-22 16:26:49.247157: step: 452/530, loss: 0.006841473747044802
2023-01-22 16:26:50.288924: step: 456/530, loss: 0.00014648000069428235
2023-01-22 16:26:51.325854: step: 460/530, loss: 6.161403871374205e-05
2023-01-22 16:26:52.367147: step: 464/530, loss: 0.004762462805956602
2023-01-22 16:26:53.419965: step: 468/530, loss: 0.004971724934875965
2023-01-22 16:26:54.486314: step: 472/530, loss: 0.0063550760969519615
2023-01-22 16:26:55.524766: step: 476/530, loss: 0.00108983158133924
2023-01-22 16:26:56.579975: step: 480/530, loss: 0.0016724548768252134
2023-01-22 16:26:57.626254: step: 484/530, loss: 0.00010766657942440361
2023-01-22 16:26:58.668496: step: 488/530, loss: 0.011752878315746784
2023-01-22 16:26:59.732767: step: 492/530, loss: 0.0019836928695440292
2023-01-22 16:27:00.796741: step: 496/530, loss: 0.001976546598598361
2023-01-22 16:27:01.863442: step: 500/530, loss: 0.004593879450112581
2023-01-22 16:27:02.939152: step: 504/530, loss: 0.0018722822424024343
2023-01-22 16:27:03.992265: step: 508/530, loss: 0.0005927394377067685
2023-01-22 16:27:05.039441: step: 512/530, loss: 0.004643979016691446
2023-01-22 16:27:06.075366: step: 516/530, loss: 0.0007006069645285606
2023-01-22 16:27:07.116683: step: 520/530, loss: 0.004949643276631832
2023-01-22 16:27:08.180545: step: 524/530, loss: 0.009754087775945663
2023-01-22 16:27:09.231996: step: 528/530, loss: 0.004312986508011818
2023-01-22 16:27:10.276849: step: 532/530, loss: 0.009008606895804405
2023-01-22 16:27:11.325211: step: 536/530, loss: 0.0003606323734857142
2023-01-22 16:27:12.388342: step: 540/530, loss: 0.0027230042032897472
2023-01-22 16:27:13.439431: step: 544/530, loss: 0.013823960907757282
2023-01-22 16:27:14.504052: step: 548/530, loss: 0.015406623482704163
2023-01-22 16:27:15.552028: step: 552/530, loss: 0.0053239911794662476
2023-01-22 16:27:16.602172: step: 556/530, loss: 0.017090929672122
2023-01-22 16:27:17.668398: step: 560/530, loss: 0.005778525024652481
2023-01-22 16:27:18.730932: step: 564/530, loss: 0.006856540683656931
2023-01-22 16:27:19.794536: step: 568/530, loss: 0.003494675038382411
2023-01-22 16:27:20.837850: step: 572/530, loss: 0.0002908333844970912
2023-01-22 16:27:21.886974: step: 576/530, loss: 0.00804196111857891
2023-01-22 16:27:22.935611: step: 580/530, loss: 0.003090738086029887
2023-01-22 16:27:23.981665: step: 584/530, loss: 0.004739857278764248
2023-01-22 16:27:25.031399: step: 588/530, loss: 0.005519860424101353
2023-01-22 16:27:26.069196: step: 592/530, loss: 0.0008785635000094771
2023-01-22 16:27:27.118894: step: 596/530, loss: 0.008111746981739998
2023-01-22 16:27:28.166281: step: 600/530, loss: 0.014484434388577938
2023-01-22 16:27:29.208279: step: 604/530, loss: 0.005458177998661995
2023-01-22 16:27:30.250360: step: 608/530, loss: 0.002368542132899165
2023-01-22 16:27:31.294066: step: 612/530, loss: 0.0012129952665418386
2023-01-22 16:27:32.337141: step: 616/530, loss: 0.00016289466293528676
2023-01-22 16:27:33.395063: step: 620/530, loss: 0.0018954677507281303
2023-01-22 16:27:34.443367: step: 624/530, loss: 0.007410240825265646
2023-01-22 16:27:35.505401: step: 628/530, loss: 0.0035863411612808704
2023-01-22 16:27:36.552109: step: 632/530, loss: 0.00589687330648303
2023-01-22 16:27:37.609549: step: 636/530, loss: 0.0027452362701296806
2023-01-22 16:27:38.646753: step: 640/530, loss: 0.0008080213447101414
2023-01-22 16:27:39.693481: step: 644/530, loss: 0.0007217864622361958
2023-01-22 16:27:40.742535: step: 648/530, loss: 0.005689879413694143
2023-01-22 16:27:41.792671: step: 652/530, loss: 5.123640221427195e-05
2023-01-22 16:27:42.839217: step: 656/530, loss: 0.004865794442594051
2023-01-22 16:27:43.877016: step: 660/530, loss: 3.063065742026083e-05
2023-01-22 16:27:44.929728: step: 664/530, loss: 0.0009470180375501513
2023-01-22 16:27:45.974087: step: 668/530, loss: 0.002904303604736924
2023-01-22 16:27:47.025648: step: 672/530, loss: 0.006766879931092262
2023-01-22 16:27:48.050063: step: 676/530, loss: 0.0010938975028693676
2023-01-22 16:27:49.078071: step: 680/530, loss: 0.0005955899832770228
2023-01-22 16:27:50.128838: step: 684/530, loss: 0.011389659717679024
2023-01-22 16:27:51.166534: step: 688/530, loss: 0.0029171837959438562
2023-01-22 16:27:52.194902: step: 692/530, loss: 0.00016324837633874267
2023-01-22 16:27:53.235205: step: 696/530, loss: 0.0028112668078392744
2023-01-22 16:27:54.264183: step: 700/530, loss: 0.0013409480452537537
2023-01-22 16:27:55.306547: step: 704/530, loss: 0.008898143656551838
2023-01-22 16:27:56.352524: step: 708/530, loss: 0.004181708209216595
2023-01-22 16:27:57.394665: step: 712/530, loss: 0.0019403608748689294
2023-01-22 16:27:58.431621: step: 716/530, loss: 0.004969300702214241
2023-01-22 16:27:59.472534: step: 720/530, loss: 0.00036568247014656663
2023-01-22 16:28:00.527691: step: 724/530, loss: 0.0012061306042596698
2023-01-22 16:28:01.586742: step: 728/530, loss: 0.0020278675947338343
2023-01-22 16:28:02.620508: step: 732/530, loss: 0.001116099301725626
2023-01-22 16:28:03.657615: step: 736/530, loss: 0.0037191968876868486
2023-01-22 16:28:04.704843: step: 740/530, loss: 0.008039727807044983
2023-01-22 16:28:05.740277: step: 744/530, loss: 2.126537037838716e-05
2023-01-22 16:28:06.785651: step: 748/530, loss: 0.002352700103074312
2023-01-22 16:28:07.808616: step: 752/530, loss: 0.023162314668297768
2023-01-22 16:28:08.864355: step: 756/530, loss: 0.003155795158818364
2023-01-22 16:28:09.909241: step: 760/530, loss: 0.0060104867443442345
2023-01-22 16:28:10.957323: step: 764/530, loss: 0.006539924070239067
2023-01-22 16:28:11.991581: step: 768/530, loss: 0.031132902950048447
2023-01-22 16:28:13.041682: step: 772/530, loss: 7.505480607505888e-05
2023-01-22 16:28:14.101727: step: 776/530, loss: 0.012613949365913868
2023-01-22 16:28:15.147289: step: 780/530, loss: 0.01499087642878294
2023-01-22 16:28:16.192297: step: 784/530, loss: 0.010055623017251492
2023-01-22 16:28:17.222840: step: 788/530, loss: 0.001072186278179288
2023-01-22 16:28:18.242968: step: 792/530, loss: 0.002134459326043725
2023-01-22 16:28:19.290509: step: 796/530, loss: 0.0011044758139178157
2023-01-22 16:28:20.338775: step: 800/530, loss: 0.00104897515848279
2023-01-22 16:28:21.365173: step: 804/530, loss: 0.003274880815297365
2023-01-22 16:28:22.409072: step: 808/530, loss: 0.00865128356963396
2023-01-22 16:28:23.448709: step: 812/530, loss: 0.006183304358273745
2023-01-22 16:28:24.490991: step: 816/530, loss: 0.00017106109589803964
2023-01-22 16:28:25.527309: step: 820/530, loss: 0.00031705936999060214
2023-01-22 16:28:26.552680: step: 824/530, loss: 0.0022580043878406286
2023-01-22 16:28:27.606225: step: 828/530, loss: 9.106863581109792e-05
2023-01-22 16:28:28.643676: step: 832/530, loss: 0.0025899119209498167
2023-01-22 16:28:29.694189: step: 836/530, loss: 0.004209454637020826
2023-01-22 16:28:30.750432: step: 840/530, loss: 0.0011600167490541935
2023-01-22 16:28:31.794268: step: 844/530, loss: 0.012773072347044945
2023-01-22 16:28:32.837894: step: 848/530, loss: 6.810516788391396e-05
2023-01-22 16:28:33.881659: step: 852/530, loss: 0.0033851061016321182
2023-01-22 16:28:34.925464: step: 856/530, loss: 1.8227445252705365e-05
2023-01-22 16:28:35.987695: step: 860/530, loss: 0.0021093892864882946
2023-01-22 16:28:37.040095: step: 864/530, loss: 0.0023472122848033905
2023-01-22 16:28:38.082005: step: 868/530, loss: 0.003328170860186219
2023-01-22 16:28:39.117539: step: 872/530, loss: 0.0007086084224283695
2023-01-22 16:28:40.143056: step: 876/530, loss: 0.0012577767483890057
2023-01-22 16:28:41.171758: step: 880/530, loss: 0.002273960504680872
2023-01-22 16:28:42.205467: step: 884/530, loss: 0.0019835445564240217
2023-01-22 16:28:43.255314: step: 888/530, loss: 0.00939200259745121
2023-01-22 16:28:44.299022: step: 892/530, loss: 0.001002413802780211
2023-01-22 16:28:45.336836: step: 896/530, loss: 0.002918391954153776
2023-01-22 16:28:46.376012: step: 900/530, loss: 0.006270183715969324
2023-01-22 16:28:47.393201: step: 904/530, loss: 0.0003226775152143091
2023-01-22 16:28:48.437820: step: 908/530, loss: 0.0002985780010931194
2023-01-22 16:28:49.488119: step: 912/530, loss: 0.00126753025688231
2023-01-22 16:28:50.523995: step: 916/530, loss: 0.002424656180664897
2023-01-22 16:28:51.557099: step: 920/530, loss: 0.001331451116129756
2023-01-22 16:28:52.588726: step: 924/530, loss: 0.0037289857864379883
2023-01-22 16:28:53.660759: step: 928/530, loss: 0.008709922432899475
2023-01-22 16:28:54.703527: step: 932/530, loss: 4.713838643510826e-05
2023-01-22 16:28:55.755035: step: 936/530, loss: 0.0006879171123728156
2023-01-22 16:28:56.806923: step: 940/530, loss: 0.0015554639976471663
2023-01-22 16:28:57.844480: step: 944/530, loss: 0.006880404427647591
2023-01-22 16:28:58.885199: step: 948/530, loss: 0.002029820578172803
2023-01-22 16:28:59.926864: step: 952/530, loss: 0.005209110211580992
2023-01-22 16:29:00.984397: step: 956/530, loss: 0.006262167356908321
2023-01-22 16:29:02.040425: step: 960/530, loss: 0.0005445873248390853
2023-01-22 16:29:03.091154: step: 964/530, loss: 0.009287801571190357
2023-01-22 16:29:04.128756: step: 968/530, loss: 0.0017832937883213162
2023-01-22 16:29:05.184268: step: 972/530, loss: 0.0066197956912219524
2023-01-22 16:29:06.222521: step: 976/530, loss: 0.0031681323889642954
2023-01-22 16:29:07.281838: step: 980/530, loss: 0.00193797389511019
2023-01-22 16:29:08.327446: step: 984/530, loss: 0.0006818838883191347
2023-01-22 16:29:09.382580: step: 988/530, loss: 0.005947432946413755
2023-01-22 16:29:10.435576: step: 992/530, loss: 0.00014374639431480318
2023-01-22 16:29:11.465484: step: 996/530, loss: 0.0027578489389270544
2023-01-22 16:29:12.525397: step: 1000/530, loss: 0.00670988904312253
2023-01-22 16:29:13.586181: step: 1004/530, loss: 0.0037533906288444996
2023-01-22 16:29:14.627259: step: 1008/530, loss: 0.007830151356756687
2023-01-22 16:29:15.658393: step: 1012/530, loss: 0.0010340377921238542
2023-01-22 16:29:16.706576: step: 1016/530, loss: 0.0038095011841505766
2023-01-22 16:29:17.735757: step: 1020/530, loss: 0.00020850585133302957
2023-01-22 16:29:18.767717: step: 1024/530, loss: 0.0
2023-01-22 16:29:19.809338: step: 1028/530, loss: 0.014278216287493706
2023-01-22 16:29:20.853312: step: 1032/530, loss: 0.001539278426207602
2023-01-22 16:29:21.885011: step: 1036/530, loss: 0.004220576956868172
2023-01-22 16:29:22.940701: step: 1040/530, loss: 0.006350742653012276
2023-01-22 16:29:24.000050: step: 1044/530, loss: 0.002821509260684252
2023-01-22 16:29:25.058934: step: 1048/530, loss: 0.002168116858229041
2023-01-22 16:29:26.099463: step: 1052/530, loss: 0.0009608911350369453
2023-01-22 16:29:27.141336: step: 1056/530, loss: 0.0005167686031199992
2023-01-22 16:29:28.195632: step: 1060/530, loss: 0.00890722218900919
2023-01-22 16:29:29.234180: step: 1064/530, loss: 0.002377914497628808
2023-01-22 16:29:30.278452: step: 1068/530, loss: 0.005166775081306696
2023-01-22 16:29:31.322068: step: 1072/530, loss: 0.004172053653746843
2023-01-22 16:29:32.393411: step: 1076/530, loss: 0.0006449891370721161
2023-01-22 16:29:33.426206: step: 1080/530, loss: 0.001498655998148024
2023-01-22 16:29:34.475028: step: 1084/530, loss: 0.005240730941295624
2023-01-22 16:29:35.514031: step: 1088/530, loss: 0.0029189996421337128
2023-01-22 16:29:36.552225: step: 1092/530, loss: 0.0036901573184877634
2023-01-22 16:29:37.580123: step: 1096/530, loss: 0.0030313222669065
2023-01-22 16:29:38.615462: step: 1100/530, loss: 0.0019233659841120243
2023-01-22 16:29:39.666406: step: 1104/530, loss: 0.0004474167653825134
2023-01-22 16:29:40.728053: step: 1108/530, loss: 0.00304612098261714
2023-01-22 16:29:41.773130: step: 1112/530, loss: 0.008172928355634212
2023-01-22 16:29:42.825938: step: 1116/530, loss: 0.0007721254951320589
2023-01-22 16:29:43.866804: step: 1120/530, loss: 9.270858572563156e-05
2023-01-22 16:29:44.916330: step: 1124/530, loss: 0.0010874532163143158
2023-01-22 16:29:45.988872: step: 1128/530, loss: 0.009353571571409702
2023-01-22 16:29:47.030364: step: 1132/530, loss: 0.007798335049301386
2023-01-22 16:29:48.071724: step: 1136/530, loss: 1.560855162097141e-05
2023-01-22 16:29:49.109793: step: 1140/530, loss: 0.0004388349479995668
2023-01-22 16:29:50.163445: step: 1144/530, loss: 0.0017336965538561344
2023-01-22 16:29:51.205884: step: 1148/530, loss: 0.0002440254029352218
2023-01-22 16:29:52.234322: step: 1152/530, loss: 0.013340502977371216
2023-01-22 16:29:53.276397: step: 1156/530, loss: 0.025634698569774628
2023-01-22 16:29:54.338728: step: 1160/530, loss: 0.008832289837300777
2023-01-22 16:29:55.391849: step: 1164/530, loss: 0.0037085632793605328
2023-01-22 16:29:56.417274: step: 1168/530, loss: 0.002268877113237977
2023-01-22 16:29:57.464953: step: 1172/530, loss: 0.002775707747787237
2023-01-22 16:29:58.542730: step: 1176/530, loss: 0.005364735145121813
2023-01-22 16:29:59.590872: step: 1180/530, loss: 0.0016359073342755437
2023-01-22 16:30:00.628438: step: 1184/530, loss: 0.00252917455509305
2023-01-22 16:30:01.680400: step: 1188/530, loss: 0.0025797623675316572
2023-01-22 16:30:02.737482: step: 1192/530, loss: 0.0
2023-01-22 16:30:03.819209: step: 1196/530, loss: 0.007662640418857336
2023-01-22 16:30:04.885271: step: 1200/530, loss: 0.005358402151614428
2023-01-22 16:30:05.938946: step: 1204/530, loss: 0.0046693007461726665
2023-01-22 16:30:06.992385: step: 1208/530, loss: 0.006806109566241503
2023-01-22 16:30:08.036267: step: 1212/530, loss: 0.003967630676925182
2023-01-22 16:30:09.068306: step: 1216/530, loss: 0.001612030086107552
2023-01-22 16:30:10.122318: step: 1220/530, loss: 0.0044658915139734745
2023-01-22 16:30:11.166561: step: 1224/530, loss: 0.004679975565522909
2023-01-22 16:30:12.206774: step: 1228/530, loss: 8.977941615739837e-05
2023-01-22 16:30:13.226799: step: 1232/530, loss: 0.0017979200929403305
2023-01-22 16:30:14.286543: step: 1236/530, loss: 0.0020674855913966894
2023-01-22 16:30:15.358624: step: 1240/530, loss: 0.0010735800024122
2023-01-22 16:30:16.395329: step: 1244/530, loss: 0.0045592705719172955
2023-01-22 16:30:17.444281: step: 1248/530, loss: 0.00034399895230308175
2023-01-22 16:30:18.491672: step: 1252/530, loss: 0.0008495797519572079
2023-01-22 16:30:19.542624: step: 1256/530, loss: 0.0054959505796432495
2023-01-22 16:30:20.597078: step: 1260/530, loss: 0.0004950312431901693
2023-01-22 16:30:21.638672: step: 1264/530, loss: 0.008217941038310528
2023-01-22 16:30:22.673669: step: 1268/530, loss: 0.007245768792927265
2023-01-22 16:30:23.734066: step: 1272/530, loss: 0.0027825292199850082
2023-01-22 16:30:24.778489: step: 1276/530, loss: 0.005645498633384705
2023-01-22 16:30:25.829799: step: 1280/530, loss: 0.0021553447004407644
2023-01-22 16:30:26.883413: step: 1284/530, loss: 0.003945991396903992
2023-01-22 16:30:27.925025: step: 1288/530, loss: 0.004809791687875986
2023-01-22 16:30:28.973673: step: 1292/530, loss: 0.002229788340628147
2023-01-22 16:30:30.012273: step: 1296/530, loss: 0.005427020136266947
2023-01-22 16:30:31.049044: step: 1300/530, loss: 0.004163031466305256
2023-01-22 16:30:32.086886: step: 1304/530, loss: 0.0010832385160028934
2023-01-22 16:30:33.163048: step: 1308/530, loss: 0.003033717628568411
2023-01-22 16:30:34.218151: step: 1312/530, loss: 0.014169587753713131
2023-01-22 16:30:35.276370: step: 1316/530, loss: 0.009973904117941856
2023-01-22 16:30:36.327092: step: 1320/530, loss: 0.006365509703755379
2023-01-22 16:30:37.364598: step: 1324/530, loss: 0.004413762129843235
2023-01-22 16:30:38.455338: step: 1328/530, loss: 0.003817374352365732
2023-01-22 16:30:39.514918: step: 1332/530, loss: 0.00264952564612031
2023-01-22 16:30:40.571128: step: 1336/530, loss: 0.0036176862195134163
2023-01-22 16:30:41.624198: step: 1340/530, loss: 0.001303567667491734
2023-01-22 16:30:42.666806: step: 1344/530, loss: 0.008924799039959908
2023-01-22 16:30:43.708504: step: 1348/530, loss: 0.009997577406466007
2023-01-22 16:30:44.760300: step: 1352/530, loss: 0.005217531230300665
2023-01-22 16:30:45.809586: step: 1356/530, loss: 0.004641849081963301
2023-01-22 16:30:46.867380: step: 1360/530, loss: 0.0008019140805117786
2023-01-22 16:30:47.922705: step: 1364/530, loss: 0.003105561016127467
2023-01-22 16:30:48.981990: step: 1368/530, loss: 0.004437734838575125
2023-01-22 16:30:50.039880: step: 1372/530, loss: 0.001108279568143189
2023-01-22 16:30:51.088483: step: 1376/530, loss: 0.0011244243942201138
2023-01-22 16:30:52.149913: step: 1380/530, loss: 0.0003110711113549769
2023-01-22 16:30:53.186517: step: 1384/530, loss: 0.0006829272606410086
2023-01-22 16:30:54.234517: step: 1388/530, loss: 0.0016583200776949525
2023-01-22 16:30:55.269603: step: 1392/530, loss: 0.001666699186898768
2023-01-22 16:30:56.313100: step: 1396/530, loss: 0.0020556470844894648
2023-01-22 16:30:57.347996: step: 1400/530, loss: 0.0001240190613316372
2023-01-22 16:30:58.396654: step: 1404/530, loss: 3.0134942790027708e-05
2023-01-22 16:30:59.446397: step: 1408/530, loss: 0.009231225587427616
2023-01-22 16:31:00.497720: step: 1412/530, loss: 0.0013545748079195619
2023-01-22 16:31:01.529179: step: 1416/530, loss: 2.4635108275106177e-05
2023-01-22 16:31:02.573061: step: 1420/530, loss: 0.013833350501954556
2023-01-22 16:31:03.646678: step: 1424/530, loss: 0.0015261200023815036
2023-01-22 16:31:04.689869: step: 1428/530, loss: 0.006960385479032993
2023-01-22 16:31:05.739699: step: 1432/530, loss: 1.0679212891773204e-06
2023-01-22 16:31:06.771491: step: 1436/530, loss: 0.010158493183553219
2023-01-22 16:31:07.810253: step: 1440/530, loss: 0.00017221782763954252
2023-01-22 16:31:08.851577: step: 1444/530, loss: 0.0034154686145484447
2023-01-22 16:31:09.907028: step: 1448/530, loss: 0.00013024620420765132
2023-01-22 16:31:10.963839: step: 1452/530, loss: 0.03434533625841141
2023-01-22 16:31:12.004284: step: 1456/530, loss: 0.00020123642752878368
2023-01-22 16:31:13.046750: step: 1460/530, loss: 0.010088873095810413
2023-01-22 16:31:14.106771: step: 1464/530, loss: 0.004612664692103863
2023-01-22 16:31:15.169636: step: 1468/530, loss: 0.03448980674147606
2023-01-22 16:31:16.203052: step: 1472/530, loss: 0.0001364069030387327
2023-01-22 16:31:17.241876: step: 1476/530, loss: 0.006621548905968666
2023-01-22 16:31:18.290273: step: 1480/530, loss: 0.0016558353090658784
2023-01-22 16:31:19.343574: step: 1484/530, loss: 0.0005234894924797118
2023-01-22 16:31:20.394648: step: 1488/530, loss: 0.010724452324211597
2023-01-22 16:31:21.441116: step: 1492/530, loss: 0.00606974633410573
2023-01-22 16:31:22.480245: step: 1496/530, loss: 0.00652778334915638
2023-01-22 16:31:23.517590: step: 1500/530, loss: 0.0005637799040414393
2023-01-22 16:31:24.576761: step: 1504/530, loss: 0.001750711351633072
2023-01-22 16:31:25.600124: step: 1508/530, loss: 0.008610162883996964
2023-01-22 16:31:26.643542: step: 1512/530, loss: 0.00014456934877671301
2023-01-22 16:31:27.700151: step: 1516/530, loss: 0.0009633276495151222
2023-01-22 16:31:28.742453: step: 1520/530, loss: 0.0002715626615099609
2023-01-22 16:31:29.789403: step: 1524/530, loss: 0.016622448340058327
2023-01-22 16:31:30.837647: step: 1528/530, loss: 0.018680144101381302
2023-01-22 16:31:31.884353: step: 1532/530, loss: 0.00033977319253608584
2023-01-22 16:31:32.947756: step: 1536/530, loss: 0.006149570923298597
2023-01-22 16:31:33.986492: step: 1540/530, loss: 0.005944901145994663
2023-01-22 16:31:35.025520: step: 1544/530, loss: 0.0068020387552678585
2023-01-22 16:31:36.064536: step: 1548/530, loss: 0.006000378634780645
2023-01-22 16:31:37.119108: step: 1552/530, loss: 0.005835102871060371
2023-01-22 16:31:38.148957: step: 1556/530, loss: 0.001768456189893186
2023-01-22 16:31:39.204274: step: 1560/530, loss: 0.0017500862013548613
2023-01-22 16:31:40.258989: step: 1564/530, loss: 0.004923265427350998
2023-01-22 16:31:41.310562: step: 1568/530, loss: 0.0028214200865477324
2023-01-22 16:31:42.340337: step: 1572/530, loss: 2.5458388336119242e-05
2023-01-22 16:31:43.385081: step: 1576/530, loss: 0.0007640895782969892
2023-01-22 16:31:44.420260: step: 1580/530, loss: 0.0015298749785870314
2023-01-22 16:31:45.456545: step: 1584/530, loss: 0.0024504277389496565
2023-01-22 16:31:46.486712: step: 1588/530, loss: 0.0002578197745606303
2023-01-22 16:31:47.533037: step: 1592/530, loss: 0.006138334050774574
2023-01-22 16:31:48.569725: step: 1596/530, loss: 0.000377841352019459
2023-01-22 16:31:49.606376: step: 1600/530, loss: 0.01051326934248209
2023-01-22 16:31:50.641363: step: 1604/530, loss: 0.0025168282445520163
2023-01-22 16:31:51.704884: step: 1608/530, loss: 0.0026044489350169897
2023-01-22 16:31:52.752368: step: 1612/530, loss: 0.00027407993911765516
2023-01-22 16:31:53.793074: step: 1616/530, loss: 0.012971087358891964
2023-01-22 16:31:54.830468: step: 1620/530, loss: 0.00045866359141655266
2023-01-22 16:31:55.879101: step: 1624/530, loss: 0.001111815683543682
2023-01-22 16:31:56.918849: step: 1628/530, loss: 0.004980051424354315
2023-01-22 16:31:57.959472: step: 1632/530, loss: 0.0003353085194248706
2023-01-22 16:31:59.002641: step: 1636/530, loss: 0.0007205993169918656
2023-01-22 16:32:00.058923: step: 1640/530, loss: 0.004817973356693983
2023-01-22 16:32:01.087960: step: 1644/530, loss: 0.002096210839226842
2023-01-22 16:32:02.128565: step: 1648/530, loss: 0.0009020436555147171
2023-01-22 16:32:03.179631: step: 1652/530, loss: 0.0016669457545503974
2023-01-22 16:32:04.226892: step: 1656/530, loss: 0.0023536181543022394
2023-01-22 16:32:05.270534: step: 1660/530, loss: 0.002634019125252962
2023-01-22 16:32:06.303482: step: 1664/530, loss: 0.0004650855262298137
2023-01-22 16:32:07.330283: step: 1668/530, loss: 3.0767869247938506e-06
2023-01-22 16:32:08.369380: step: 1672/530, loss: 0.0020296969451010227
2023-01-22 16:32:09.408842: step: 1676/530, loss: 0.010251333005726337
2023-01-22 16:32:10.464198: step: 1680/530, loss: 0.0019116174662485719
2023-01-22 16:32:11.507587: step: 1684/530, loss: 0.002041993662714958
2023-01-22 16:32:12.541055: step: 1688/530, loss: 0.0005865368293598294
2023-01-22 16:32:13.586083: step: 1692/530, loss: 0.006311272270977497
2023-01-22 16:32:14.637196: step: 1696/530, loss: 0.001400873064994812
2023-01-22 16:32:15.673024: step: 1700/530, loss: 0.00434342073276639
2023-01-22 16:32:16.725813: step: 1704/530, loss: 0.025829633697867393
2023-01-22 16:32:17.791093: step: 1708/530, loss: 0.0006744025740772486
2023-01-22 16:32:18.840781: step: 1712/530, loss: 0.03393099457025528
2023-01-22 16:32:19.887927: step: 1716/530, loss: 0.0016020622570067644
2023-01-22 16:32:20.927622: step: 1720/530, loss: 0.0051536038517951965
2023-01-22 16:32:21.971713: step: 1724/530, loss: 0.0013604526175186038
2023-01-22 16:32:23.015863: step: 1728/530, loss: 0.002191638108342886
2023-01-22 16:32:24.057043: step: 1732/530, loss: 0.004143086262047291
2023-01-22 16:32:25.090809: step: 1736/530, loss: 0.001980945933610201
2023-01-22 16:32:26.134679: step: 1740/530, loss: 0.0033146373461931944
2023-01-22 16:32:27.191016: step: 1744/530, loss: 0.0008635398116894066
2023-01-22 16:32:28.249721: step: 1748/530, loss: 0.0007993154576979578
2023-01-22 16:32:29.288083: step: 1752/530, loss: 0.007476922124624252
2023-01-22 16:32:30.309140: step: 1756/530, loss: 0.0017271970864385366
2023-01-22 16:32:31.354771: step: 1760/530, loss: 0.0036569773219525814
2023-01-22 16:32:32.406737: step: 1764/530, loss: 0.012102874927222729
2023-01-22 16:32:33.475088: step: 1768/530, loss: 0.0029134931974112988
2023-01-22 16:32:34.514807: step: 1772/530, loss: 0.004788354970514774
2023-01-22 16:32:35.573023: step: 1776/530, loss: 0.005316424183547497
2023-01-22 16:32:36.608900: step: 1780/530, loss: 0.0001454366574762389
2023-01-22 16:32:37.661641: step: 1784/530, loss: 0.0022293354850262403
2023-01-22 16:32:38.725610: step: 1788/530, loss: 0.002906629117205739
2023-01-22 16:32:39.763115: step: 1792/530, loss: 0.0021648481488227844
2023-01-22 16:32:40.806733: step: 1796/530, loss: 0.004671917762607336
2023-01-22 16:32:41.850066: step: 1800/530, loss: 0.0009187126997858286
2023-01-22 16:32:42.894081: step: 1804/530, loss: 2.7696472898242064e-05
2023-01-22 16:32:43.934289: step: 1808/530, loss: 3.3388175779691665e-06
2023-01-22 16:32:44.979383: step: 1812/530, loss: 0.0053504277020692825
2023-01-22 16:32:46.021475: step: 1816/530, loss: 0.017988860607147217
2023-01-22 16:32:47.074270: step: 1820/530, loss: 0.014643198810517788
2023-01-22 16:32:48.106309: step: 1824/530, loss: 0.0002301150670973584
2023-01-22 16:32:49.164631: step: 1828/530, loss: 0.0004803269694093615
2023-01-22 16:32:50.220009: step: 1832/530, loss: 0.002894968492910266
2023-01-22 16:32:51.256326: step: 1836/530, loss: 0.0004744551260955632
2023-01-22 16:32:52.293778: step: 1840/530, loss: 0.006309863179922104
2023-01-22 16:32:53.331475: step: 1844/530, loss: 0.0023878691717982292
2023-01-22 16:32:54.370098: step: 1848/530, loss: 0.004327582661062479
2023-01-22 16:32:55.428098: step: 1852/530, loss: 0.0008615344413556159
2023-01-22 16:32:56.472324: step: 1856/530, loss: 0.0060831839218735695
2023-01-22 16:32:57.515354: step: 1860/530, loss: 0.009197462350130081
2023-01-22 16:32:58.578938: step: 1864/530, loss: 0.011733553372323513
2023-01-22 16:32:59.633684: step: 1868/530, loss: 0.0011479125823825598
2023-01-22 16:33:00.697391: step: 1872/530, loss: 0.0035104809794574976
2023-01-22 16:33:01.751853: step: 1876/530, loss: 0.0014737641904503107
2023-01-22 16:33:02.790738: step: 1880/530, loss: 0.0024089596699923277
2023-01-22 16:33:03.831522: step: 1884/530, loss: 0.0022961804643273354
2023-01-22 16:33:04.873174: step: 1888/530, loss: 0.00016385501658078283
2023-01-22 16:33:05.918158: step: 1892/530, loss: 0.00033712349249981344
2023-01-22 16:33:06.958230: step: 1896/530, loss: 0.003500109538435936
2023-01-22 16:33:07.982490: step: 1900/530, loss: 0.0007390539976768196
2023-01-22 16:33:09.021658: step: 1904/530, loss: 0.0025128498673439026
2023-01-22 16:33:10.053592: step: 1908/530, loss: 0.0035820286720991135
2023-01-22 16:33:11.108859: step: 1912/530, loss: 0.002480883616954088
2023-01-22 16:33:12.162577: step: 1916/530, loss: 0.00043412024388089776
2023-01-22 16:33:13.201621: step: 1920/530, loss: 0.004388145636767149
2023-01-22 16:33:14.257363: step: 1924/530, loss: 0.004806217737495899
2023-01-22 16:33:15.323374: step: 1928/530, loss: 0.001881759730167687
2023-01-22 16:33:16.356689: step: 1932/530, loss: 0.0013274835655465722
2023-01-22 16:33:17.402677: step: 1936/530, loss: 0.004924659617245197
2023-01-22 16:33:18.473366: step: 1940/530, loss: 0.0043535600416362286
2023-01-22 16:33:19.541583: step: 1944/530, loss: 0.0009400070994161069
2023-01-22 16:33:20.575933: step: 1948/530, loss: 0.0029635753016918898
2023-01-22 16:33:21.627573: step: 1952/530, loss: 0.016656367108225822
2023-01-22 16:33:22.663613: step: 1956/530, loss: 0.007154458202421665
2023-01-22 16:33:23.706834: step: 1960/530, loss: 0.004404411185532808
2023-01-22 16:33:24.766167: step: 1964/530, loss: 0.019092516973614693
2023-01-22 16:33:25.812553: step: 1968/530, loss: 0.0008912922930903733
2023-01-22 16:33:26.853920: step: 1972/530, loss: 0.007620178163051605
2023-01-22 16:33:27.896885: step: 1976/530, loss: 0.009262746199965477
2023-01-22 16:33:28.934942: step: 1980/530, loss: 0.001222970080561936
2023-01-22 16:33:29.986826: step: 1984/530, loss: 0.02876569703221321
2023-01-22 16:33:31.038273: step: 1988/530, loss: 0.012764384038746357
2023-01-22 16:33:32.076882: step: 1992/530, loss: 0.0068854037672281265
2023-01-22 16:33:33.135693: step: 1996/530, loss: 0.0028152288869023323
2023-01-22 16:33:34.177384: step: 2000/530, loss: 0.008710321970283985
2023-01-22 16:33:35.223422: step: 2004/530, loss: 0.010089727118611336
2023-01-22 16:33:36.273085: step: 2008/530, loss: 0.0015571370022371411
2023-01-22 16:33:37.336200: step: 2012/530, loss: 0.0030157379806041718
2023-01-22 16:33:38.373315: step: 2016/530, loss: 0.003949727397412062
2023-01-22 16:33:39.416854: step: 2020/530, loss: 0.012688472867012024
2023-01-22 16:33:40.450046: step: 2024/530, loss: 0.007030210457742214
2023-01-22 16:33:41.516752: step: 2028/530, loss: 0.0010272155050188303
2023-01-22 16:33:42.572660: step: 2032/530, loss: 0.001649027573876083
2023-01-22 16:33:43.604051: step: 2036/530, loss: 0.001951180980540812
2023-01-22 16:33:44.637782: step: 2040/530, loss: 0.01001209206879139
2023-01-22 16:33:45.681897: step: 2044/530, loss: 0.012277515605092049
2023-01-22 16:33:46.715864: step: 2048/530, loss: 0.0004959240322932601
2023-01-22 16:33:47.752887: step: 2052/530, loss: 0.0002777222834993154
2023-01-22 16:33:48.797684: step: 2056/530, loss: 0.00783250480890274
2023-01-22 16:33:49.851836: step: 2060/530, loss: 0.008940855041146278
2023-01-22 16:33:50.893578: step: 2064/530, loss: 0.006159218028187752
2023-01-22 16:33:51.930302: step: 2068/530, loss: 0.005878178868442774
2023-01-22 16:33:52.953528: step: 2072/530, loss: 0.0003231469017919153
2023-01-22 16:33:54.003592: step: 2076/530, loss: 0.0013630922185257077
2023-01-22 16:33:55.040798: step: 2080/530, loss: 0.0007030994165688753
2023-01-22 16:33:56.077261: step: 2084/530, loss: 1.783264087862335e-05
2023-01-22 16:33:57.104864: step: 2088/530, loss: 0.003977149724960327
2023-01-22 16:33:58.141086: step: 2092/530, loss: 0.004377401899546385
2023-01-22 16:33:59.186738: step: 2096/530, loss: 0.004633416887372732
2023-01-22 16:34:00.224588: step: 2100/530, loss: 0.011995643377304077
2023-01-22 16:34:01.278882: step: 2104/530, loss: 0.0018599849427118897
2023-01-22 16:34:02.326610: step: 2108/530, loss: 0.00544124748557806
2023-01-22 16:34:03.392150: step: 2112/530, loss: 0.0022559345234185457
2023-01-22 16:34:04.449700: step: 2116/530, loss: 0.0004722154699265957
2023-01-22 16:34:05.490078: step: 2120/530, loss: 0.0026975416112691164
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34625994035785285, 'r': 0.3304909867172675, 'f1': 0.33819174757281545}, 'combined': 0.2491939192641798, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35884987380290667, 'r': 0.40667453529318376, 'f1': 0.38126832778887026}, 'combined': 0.29552856029567937, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3135604851987691, 'r': 0.325460313859064, 'f1': 0.3193996003793793}, 'combined': 0.23534707396375315, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35882166544811855, 'r': 0.4076319655274582, 'f1': 0.3816726148828524}, 'combined': 0.2958419311532158, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32869088208660335, 'r': 0.34178862122098413, 'f1': 0.33511182024829517}, 'combined': 0.24692449913032274, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35957000869428357, 'r': 0.38633946706214845, 'f1': 0.37247438206789324}, 'combined': 0.28871220045453927, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 13
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:36:32.268015: step: 4/530, loss: 0.0015571422409266233
2023-01-22 16:36:33.302289: step: 8/530, loss: 0.030922045931220055
2023-01-22 16:36:34.338997: step: 12/530, loss: 1.8962708054459654e-05
2023-01-22 16:36:35.379044: step: 16/530, loss: 0.0021634192671626806
2023-01-22 16:36:36.426882: step: 20/530, loss: 0.0017400651704519987
2023-01-22 16:36:37.477924: step: 24/530, loss: 0.0016387642826884985
2023-01-22 16:36:38.511350: step: 28/530, loss: 0.0032358199823647738
2023-01-22 16:36:39.552776: step: 32/530, loss: 0.014631346799433231
2023-01-22 16:36:40.578962: step: 36/530, loss: 4.699534838437103e-05
2023-01-22 16:36:41.611164: step: 40/530, loss: 0.005617233458906412
2023-01-22 16:36:42.653318: step: 44/530, loss: 0.011924831196665764
2023-01-22 16:36:43.707061: step: 48/530, loss: 0.011535929515957832
2023-01-22 16:36:44.746813: step: 52/530, loss: 0.0016216832445934415
2023-01-22 16:36:45.781154: step: 56/530, loss: 0.004749161656945944
2023-01-22 16:36:46.822204: step: 60/530, loss: 0.004102516453713179
2023-01-22 16:36:47.863863: step: 64/530, loss: 0.013086911290884018
2023-01-22 16:36:48.892950: step: 68/530, loss: 0.0016393022378906608
2023-01-22 16:36:49.927478: step: 72/530, loss: 0.024492744356393814
2023-01-22 16:36:50.959857: step: 76/530, loss: 0.0016527425032109022
2023-01-22 16:36:52.010379: step: 80/530, loss: 0.0040021478198468685
2023-01-22 16:36:53.055555: step: 84/530, loss: 0.003007357008755207
2023-01-22 16:36:54.102025: step: 88/530, loss: 0.028197692707180977
2023-01-22 16:36:55.146122: step: 92/530, loss: 0.0030906435567885637
2023-01-22 16:36:56.188247: step: 96/530, loss: 0.07146855443716049
2023-01-22 16:36:57.231244: step: 100/530, loss: 0.01033016201108694
2023-01-22 16:36:58.294398: step: 104/530, loss: 0.0035208845511078835
2023-01-22 16:36:59.342864: step: 108/530, loss: 0.006997973658144474
2023-01-22 16:37:00.377694: step: 112/530, loss: 0.0059784636832773685
2023-01-22 16:37:01.428797: step: 116/530, loss: 0.0007764868787489831
2023-01-22 16:37:02.467441: step: 120/530, loss: 8.146424806909636e-05
2023-01-22 16:37:03.512955: step: 124/530, loss: 0.001662105438299477
2023-01-22 16:37:04.585580: step: 128/530, loss: 0.0019530060235410929
2023-01-22 16:37:05.617340: step: 132/530, loss: 0.0004900959902442992
2023-01-22 16:37:06.668231: step: 136/530, loss: 0.009724903851747513
2023-01-22 16:37:07.691545: step: 140/530, loss: 0.0027151990216225386
2023-01-22 16:37:08.728579: step: 144/530, loss: 0.011689571663737297
2023-01-22 16:37:09.758292: step: 148/530, loss: 2.2507805624627508e-05
2023-01-22 16:37:10.794191: step: 152/530, loss: 0.027585100382566452
2023-01-22 16:37:11.832441: step: 156/530, loss: 0.012612810358405113
2023-01-22 16:37:12.871707: step: 160/530, loss: 5.1878818339901045e-05
2023-01-22 16:37:13.896783: step: 164/530, loss: 0.00010572845349088311
2023-01-22 16:37:14.960085: step: 168/530, loss: 0.00020160217536613345
2023-01-22 16:37:16.017495: step: 172/530, loss: 0.00018560784519650042
2023-01-22 16:37:17.067074: step: 176/530, loss: 0.0031576049514114857
2023-01-22 16:37:18.117708: step: 180/530, loss: 0.00018232775619253516
2023-01-22 16:37:19.173998: step: 184/530, loss: 0.00476881442591548
2023-01-22 16:37:20.226101: step: 188/530, loss: 0.003823744598776102
2023-01-22 16:37:21.287442: step: 192/530, loss: 0.004184453282505274
2023-01-22 16:37:22.352861: step: 196/530, loss: 0.0010865589138120413
2023-01-22 16:37:23.385346: step: 200/530, loss: 0.004469935782253742
2023-01-22 16:37:24.436108: step: 204/530, loss: 0.005355439148843288
2023-01-22 16:37:25.463466: step: 208/530, loss: 0.00020306215446908027
2023-01-22 16:37:26.510999: step: 212/530, loss: 5.8835062191064935e-06
2023-01-22 16:37:27.553676: step: 216/530, loss: 0.0001871240237960592
2023-01-22 16:37:28.585763: step: 220/530, loss: 0.003004108788445592
2023-01-22 16:37:29.613524: step: 224/530, loss: 0.0036614355631172657
2023-01-22 16:37:30.649143: step: 228/530, loss: 0.00044466930557973683
2023-01-22 16:37:31.703743: step: 232/530, loss: 0.006003792863339186
2023-01-22 16:37:32.747660: step: 236/530, loss: 0.0056213694624602795
2023-01-22 16:37:33.792008: step: 240/530, loss: 0.00015426550817210227
2023-01-22 16:37:34.858394: step: 244/530, loss: 0.010886418633162975
2023-01-22 16:37:35.908541: step: 248/530, loss: 0.0052109649404883385
2023-01-22 16:37:36.947993: step: 252/530, loss: 0.0008735673618502915
2023-01-22 16:37:38.025748: step: 256/530, loss: 0.0027040031272917986
2023-01-22 16:37:39.075756: step: 260/530, loss: 0.0026758236344903708
2023-01-22 16:37:40.134446: step: 264/530, loss: 0.005143734626471996
2023-01-22 16:37:41.175596: step: 268/530, loss: 0.00439074169844389
2023-01-22 16:37:42.225270: step: 272/530, loss: 0.007239020429551601
2023-01-22 16:37:43.260462: step: 276/530, loss: 0.0026030123699456453
2023-01-22 16:37:44.304981: step: 280/530, loss: 0.012737544253468513
2023-01-22 16:37:45.347055: step: 284/530, loss: 0.0033456054516136646
2023-01-22 16:37:46.383507: step: 288/530, loss: 0.002196643501520157
2023-01-22 16:37:47.448680: step: 292/530, loss: 0.024431556463241577
2023-01-22 16:37:48.502139: step: 296/530, loss: 0.0022198008373379707
2023-01-22 16:37:49.554593: step: 300/530, loss: 0.0013652290217578411
2023-01-22 16:37:50.604310: step: 304/530, loss: 0.0040387618355453014
2023-01-22 16:37:51.666510: step: 308/530, loss: 0.00270672794431448
2023-01-22 16:37:52.732507: step: 312/530, loss: 0.006156936287879944
2023-01-22 16:37:53.783738: step: 316/530, loss: 0.0027480567805469036
2023-01-22 16:37:54.853311: step: 320/530, loss: 0.009938803501427174
2023-01-22 16:37:55.903841: step: 324/530, loss: 0.0029265740886330605
2023-01-22 16:37:56.970692: step: 328/530, loss: 0.00048030042671598494
2023-01-22 16:37:58.046157: step: 332/530, loss: 0.00372222438454628
2023-01-22 16:37:59.093087: step: 336/530, loss: 0.0003657924826256931
2023-01-22 16:38:00.142701: step: 340/530, loss: 0.011882190592586994
2023-01-22 16:38:01.184437: step: 344/530, loss: 0.003404736053198576
2023-01-22 16:38:02.255846: step: 348/530, loss: 0.0014219387667253613
2023-01-22 16:38:03.298086: step: 352/530, loss: 0.004031968303024769
2023-01-22 16:38:04.334384: step: 356/530, loss: 0.00036041345447301865
2023-01-22 16:38:05.393586: step: 360/530, loss: 0.005119792185723782
2023-01-22 16:38:06.442949: step: 364/530, loss: 0.0006487190839834511
2023-01-22 16:38:07.494206: step: 368/530, loss: 0.005295685958117247
2023-01-22 16:38:08.532054: step: 372/530, loss: 0.005596744827926159
2023-01-22 16:38:09.576530: step: 376/530, loss: 0.00036253826692700386
2023-01-22 16:38:10.622166: step: 380/530, loss: 0.0029514955822378397
2023-01-22 16:38:11.659489: step: 384/530, loss: 0.0002344045788049698
2023-01-22 16:38:12.700853: step: 388/530, loss: 0.006339217536151409
2023-01-22 16:38:13.761256: step: 392/530, loss: 0.001686254283413291
2023-01-22 16:38:14.810872: step: 396/530, loss: 0.0006472884560935199
2023-01-22 16:38:15.841247: step: 400/530, loss: 0.0028015095740556717
2023-01-22 16:38:16.879454: step: 404/530, loss: 0.0003446325717959553
2023-01-22 16:38:17.928335: step: 408/530, loss: 0.0030051255598664284
2023-01-22 16:38:18.960223: step: 412/530, loss: 0.0007342534954659641
2023-01-22 16:38:20.009317: step: 416/530, loss: 0.002018393948674202
2023-01-22 16:38:21.063084: step: 420/530, loss: 0.002326158806681633
2023-01-22 16:38:22.105582: step: 424/530, loss: 0.003065238008275628
2023-01-22 16:38:23.147533: step: 428/530, loss: 0.0031415680423378944
2023-01-22 16:38:24.224310: step: 432/530, loss: 0.0014777034521102905
2023-01-22 16:38:25.251696: step: 436/530, loss: 0.028326740488409996
2023-01-22 16:38:26.295670: step: 440/530, loss: 0.001052691601216793
2023-01-22 16:38:27.321425: step: 444/530, loss: 2.937482531706337e-05
2023-01-22 16:38:28.375231: step: 448/530, loss: 0.0043033454567193985
2023-01-22 16:38:29.430753: step: 452/530, loss: 0.0016315453685820103
2023-01-22 16:38:30.475503: step: 456/530, loss: 0.0039023798890411854
2023-01-22 16:38:31.538414: step: 460/530, loss: 0.001634332467801869
2023-01-22 16:38:32.585354: step: 464/530, loss: 0.0034528980031609535
2023-01-22 16:38:33.660317: step: 468/530, loss: 0.0026262092869728804
2023-01-22 16:38:34.701707: step: 472/530, loss: 0.0005942652933299541
2023-01-22 16:38:35.739565: step: 476/530, loss: 0.0017140927957370877
2023-01-22 16:38:36.774785: step: 480/530, loss: 0.00020897998183500022
2023-01-22 16:38:37.818446: step: 484/530, loss: 0.00015195251035038382
2023-01-22 16:38:38.870904: step: 488/530, loss: 0.008661547675728798
2023-01-22 16:38:39.921506: step: 492/530, loss: 0.006288343574851751
2023-01-22 16:38:40.970358: step: 496/530, loss: 1.9588105715229176e-05
2023-01-22 16:38:42.007642: step: 500/530, loss: 0.002119549550116062
2023-01-22 16:38:43.038757: step: 504/530, loss: 0.0059881326742470264
2023-01-22 16:38:44.089198: step: 508/530, loss: 0.01731732115149498
2023-01-22 16:38:45.129114: step: 512/530, loss: 0.00010866344382520765
2023-01-22 16:38:46.170806: step: 516/530, loss: 0.005246803164482117
2023-01-22 16:38:47.214600: step: 520/530, loss: 5.6141274399124086e-05
2023-01-22 16:38:48.265614: step: 524/530, loss: 0.003649590304121375
2023-01-22 16:38:49.320905: step: 528/530, loss: 0.015118328854441643
2023-01-22 16:38:50.358714: step: 532/530, loss: 0.001896945759654045
2023-01-22 16:38:51.420318: step: 536/530, loss: 0.0010516990441828966
2023-01-22 16:38:52.460835: step: 540/530, loss: 0.004235134460031986
2023-01-22 16:38:53.505100: step: 544/530, loss: 0.0001383834023727104
2023-01-22 16:38:54.560443: step: 548/530, loss: 0.005883309990167618
2023-01-22 16:38:55.599549: step: 552/530, loss: 0.003881060052663088
2023-01-22 16:38:56.645586: step: 556/530, loss: 0.002632217714563012
2023-01-22 16:38:57.683627: step: 560/530, loss: 0.0011256864527240396
2023-01-22 16:38:58.741000: step: 564/530, loss: 0.004862012807279825
2023-01-22 16:38:59.794897: step: 568/530, loss: 3.28724090650212e-05
2023-01-22 16:39:00.825865: step: 572/530, loss: 0.002916815457865596
2023-01-22 16:39:01.869438: step: 576/530, loss: 0.019314512610435486
2023-01-22 16:39:02.938434: step: 580/530, loss: 0.027455750852823257
2023-01-22 16:39:03.992971: step: 584/530, loss: 0.002586080925539136
2023-01-22 16:39:05.053909: step: 588/530, loss: 0.024136962369084358
2023-01-22 16:39:06.104834: step: 592/530, loss: 0.002513302257284522
2023-01-22 16:39:07.156909: step: 596/530, loss: 0.006390607450157404
2023-01-22 16:39:08.206369: step: 600/530, loss: 0.014459188096225262
2023-01-22 16:39:09.263775: step: 604/530, loss: 0.000182782590854913
2023-01-22 16:39:10.303082: step: 608/530, loss: 0.0016076830215752125
2023-01-22 16:39:11.345789: step: 612/530, loss: 0.00020894815679639578
2023-01-22 16:39:12.398864: step: 616/530, loss: 0.004454677924513817
2023-01-22 16:39:13.438400: step: 620/530, loss: 0.0024761175736784935
2023-01-22 16:39:14.490264: step: 624/530, loss: 0.00029460518271662295
2023-01-22 16:39:15.538891: step: 628/530, loss: 0.005864573642611504
2023-01-22 16:39:16.583939: step: 632/530, loss: 0.01079725194722414
2023-01-22 16:39:17.628331: step: 636/530, loss: 0.00878931488841772
2023-01-22 16:39:18.679039: step: 640/530, loss: 0.0002955848758574575
2023-01-22 16:39:19.718733: step: 644/530, loss: 0.00409247912466526
2023-01-22 16:39:20.761744: step: 648/530, loss: 0.0009163686190731823
2023-01-22 16:39:21.818494: step: 652/530, loss: 0.004951812792569399
2023-01-22 16:39:22.856254: step: 656/530, loss: 0.0007211221382021904
2023-01-22 16:39:23.903860: step: 660/530, loss: 0.015389836393296719
2023-01-22 16:39:24.956715: step: 664/530, loss: 0.0035710122901946306
2023-01-22 16:39:25.983374: step: 668/530, loss: 0.0041391681879758835
2023-01-22 16:39:27.027615: step: 672/530, loss: 0.001492330222390592
2023-01-22 16:39:28.076116: step: 676/530, loss: 0.0006232345476746559
2023-01-22 16:39:29.110976: step: 680/530, loss: 0.00012105554924346507
2023-01-22 16:39:30.143446: step: 684/530, loss: 0.007195714395493269
2023-01-22 16:39:31.178784: step: 688/530, loss: 0.004221584182232618
2023-01-22 16:39:32.206038: step: 692/530, loss: 0.00195950735360384
2023-01-22 16:39:33.262984: step: 696/530, loss: 0.00378425233066082
2023-01-22 16:39:34.314779: step: 700/530, loss: 0.000283784611383453
2023-01-22 16:39:35.355155: step: 704/530, loss: 0.007826127111911774
2023-01-22 16:39:36.401926: step: 708/530, loss: 0.0004190918989479542
2023-01-22 16:39:37.445472: step: 712/530, loss: 0.0010957118356600404
2023-01-22 16:39:38.470889: step: 716/530, loss: 0.0013870338443666697
2023-01-22 16:39:39.518304: step: 720/530, loss: 0.014821946620941162
2023-01-22 16:39:40.568033: step: 724/530, loss: 0.0030724769458174706
2023-01-22 16:39:41.609729: step: 728/530, loss: 0.003331148996949196
2023-01-22 16:39:42.661676: step: 732/530, loss: 0.0018085388001054525
2023-01-22 16:39:43.697365: step: 736/530, loss: 0.0015410431660711765
2023-01-22 16:39:44.733969: step: 740/530, loss: 0.0004999007796868682
2023-01-22 16:39:45.783307: step: 744/530, loss: 0.007473272737115622
2023-01-22 16:39:46.841588: step: 748/530, loss: 0.0010935214813798666
2023-01-22 16:39:47.887257: step: 752/530, loss: 7.650296174688265e-05
2023-01-22 16:39:48.937831: step: 756/530, loss: 0.001337980735115707
2023-01-22 16:39:49.990901: step: 760/530, loss: 0.0056527829729020596
2023-01-22 16:39:51.055717: step: 764/530, loss: 3.669329089461826e-05
2023-01-22 16:39:52.096756: step: 768/530, loss: 0.008626979775726795
2023-01-22 16:39:53.152984: step: 772/530, loss: 0.0051635438576340675
2023-01-22 16:39:54.206957: step: 776/530, loss: 0.008310437202453613
2023-01-22 16:39:55.245264: step: 780/530, loss: 0.0001906199031509459
2023-01-22 16:39:56.309977: step: 784/530, loss: 0.002033921657130122
2023-01-22 16:39:57.347004: step: 788/530, loss: 0.0045344773679971695
2023-01-22 16:39:58.397834: step: 792/530, loss: 0.05590024217963219
2023-01-22 16:39:59.428132: step: 796/530, loss: 1.7934558854904026e-05
2023-01-22 16:40:00.478541: step: 800/530, loss: 0.0006921774474903941
2023-01-22 16:40:01.535670: step: 804/530, loss: 0.004721867851912975
2023-01-22 16:40:02.567260: step: 808/530, loss: 0.003283181693404913
2023-01-22 16:40:03.627084: step: 812/530, loss: 0.004787980578839779
2023-01-22 16:40:04.677074: step: 816/530, loss: 0.02432870678603649
2023-01-22 16:40:05.712272: step: 820/530, loss: 0.000611655879765749
2023-01-22 16:40:06.759532: step: 824/530, loss: 0.002131052315235138
2023-01-22 16:40:07.799440: step: 828/530, loss: 0.0027392380870878696
2023-01-22 16:40:08.839336: step: 832/530, loss: 0.022219443693757057
2023-01-22 16:40:09.884684: step: 836/530, loss: 0.00564951915293932
2023-01-22 16:40:10.928476: step: 840/530, loss: 0.0034556053578853607
2023-01-22 16:40:11.976146: step: 844/530, loss: 0.0027208374813199043
2023-01-22 16:40:13.024620: step: 848/530, loss: 0.005269872955977917
2023-01-22 16:40:14.070027: step: 852/530, loss: 0.01046881452202797
2023-01-22 16:40:15.127174: step: 856/530, loss: 0.005150248762220144
2023-01-22 16:40:16.178399: step: 860/530, loss: 0.00027264413074590266
2023-01-22 16:40:17.229295: step: 864/530, loss: 0.002326930407434702
2023-01-22 16:40:18.283024: step: 868/530, loss: 0.0020518675446510315
2023-01-22 16:40:19.335046: step: 872/530, loss: 2.2392792743630707e-05
2023-01-22 16:40:20.381834: step: 876/530, loss: 0.020775049924850464
2023-01-22 16:40:21.425618: step: 880/530, loss: 0.004205694422125816
2023-01-22 16:40:22.465160: step: 884/530, loss: 0.006371791008859873
2023-01-22 16:40:23.486601: step: 888/530, loss: 0.00424738647416234
2023-01-22 16:40:24.532670: step: 892/530, loss: 8.481772965751588e-06
2023-01-22 16:40:25.580538: step: 896/530, loss: 0.0003902267199009657
2023-01-22 16:40:26.636965: step: 900/530, loss: 0.008825684897601604
2023-01-22 16:40:27.686083: step: 904/530, loss: 0.004071269650012255
2023-01-22 16:40:28.742391: step: 908/530, loss: 0.004793594591319561
2023-01-22 16:40:29.797800: step: 912/530, loss: 0.003112341742962599
2023-01-22 16:40:30.835448: step: 916/530, loss: 0.015471885912120342
2023-01-22 16:40:31.910689: step: 920/530, loss: 0.0035965389106422663
2023-01-22 16:40:32.983179: step: 924/530, loss: 0.001437822007574141
2023-01-22 16:40:34.026122: step: 928/530, loss: 0.004162083379924297
2023-01-22 16:40:35.068353: step: 932/530, loss: 0.001630387851037085
2023-01-22 16:40:36.128484: step: 936/530, loss: 0.0011927802115678787
2023-01-22 16:40:37.168582: step: 940/530, loss: 0.001629486447200179
2023-01-22 16:40:38.216304: step: 944/530, loss: 0.0002522141730878502
2023-01-22 16:40:39.252449: step: 948/530, loss: 0.004102247301489115
2023-01-22 16:40:40.303170: step: 952/530, loss: 0.00547128776088357
2023-01-22 16:40:41.340507: step: 956/530, loss: 0.004373923409730196
2023-01-22 16:40:42.376881: step: 960/530, loss: 0.006631750147789717
2023-01-22 16:40:43.425361: step: 964/530, loss: 0.0028928297106176615
2023-01-22 16:40:44.455200: step: 968/530, loss: 0.002853579353541136
2023-01-22 16:40:45.496949: step: 972/530, loss: 0.04011954739689827
2023-01-22 16:40:46.539390: step: 976/530, loss: 0.01069098711013794
2023-01-22 16:40:47.585947: step: 980/530, loss: 0.0030946913175284863
2023-01-22 16:40:48.630732: step: 984/530, loss: 0.0003545731015037745
2023-01-22 16:40:49.684077: step: 988/530, loss: 0.006341470871120691
2023-01-22 16:40:50.732696: step: 992/530, loss: 0.00206725369207561
2023-01-22 16:40:51.774476: step: 996/530, loss: 0.00016413701814599335
2023-01-22 16:40:52.810562: step: 1000/530, loss: 0.006029443349689245
2023-01-22 16:40:53.849677: step: 1004/530, loss: 0.0014888123841956258
2023-01-22 16:40:54.879567: step: 1008/530, loss: 0.0010760299628600478
2023-01-22 16:40:55.925727: step: 1012/530, loss: 0.00012965213682036847
2023-01-22 16:40:56.969789: step: 1016/530, loss: 0.0073159015737473965
2023-01-22 16:40:58.012950: step: 1020/530, loss: 0.03320840001106262
2023-01-22 16:40:59.062091: step: 1024/530, loss: 0.001997166546061635
2023-01-22 16:41:00.122054: step: 1028/530, loss: 0.0015836649108678102
2023-01-22 16:41:01.148977: step: 1032/530, loss: 0.0006292597972787917
2023-01-22 16:41:02.196910: step: 1036/530, loss: 0.004962176084518433
2023-01-22 16:41:03.242472: step: 1040/530, loss: 0.002139468677341938
2023-01-22 16:41:04.292613: step: 1044/530, loss: 0.00261810515075922
2023-01-22 16:41:05.349366: step: 1048/530, loss: 0.00012861681170761585
2023-01-22 16:41:06.403846: step: 1052/530, loss: 0.009888764470815659
2023-01-22 16:41:07.454845: step: 1056/530, loss: 0.002490539336577058
2023-01-22 16:41:08.490954: step: 1060/530, loss: 0.0007864373619668186
2023-01-22 16:41:09.532531: step: 1064/530, loss: 0.0013424664502963424
2023-01-22 16:41:10.578864: step: 1068/530, loss: 0.0022708941251039505
2023-01-22 16:41:11.633413: step: 1072/530, loss: 0.0012711402960121632
2023-01-22 16:41:12.676299: step: 1076/530, loss: 0.0021786584984511137
2023-01-22 16:41:13.728309: step: 1080/530, loss: 0.013784159906208515
2023-01-22 16:41:14.769808: step: 1084/530, loss: 0.00919702835381031
2023-01-22 16:41:15.817760: step: 1088/530, loss: 0.003673143684864044
2023-01-22 16:41:16.869804: step: 1092/530, loss: 0.0008947818423621356
2023-01-22 16:41:17.925983: step: 1096/530, loss: 0.00632647518068552
2023-01-22 16:41:18.975237: step: 1100/530, loss: 0.0008677636506035924
2023-01-22 16:41:20.016678: step: 1104/530, loss: 0.003444284200668335
2023-01-22 16:41:21.069310: step: 1108/530, loss: 0.002046301495283842
2023-01-22 16:41:22.116838: step: 1112/530, loss: 0.004305703099817038
2023-01-22 16:41:23.146296: step: 1116/530, loss: 0.0027629919350147247
2023-01-22 16:41:24.182026: step: 1120/530, loss: 0.0011827803682535887
2023-01-22 16:41:25.217053: step: 1124/530, loss: 0.0020097398664802313
2023-01-22 16:41:26.251476: step: 1128/530, loss: 0.007096866611391306
2023-01-22 16:41:27.299801: step: 1132/530, loss: 0.0035088739823549986
2023-01-22 16:41:28.347389: step: 1136/530, loss: 0.048875074833631516
2023-01-22 16:41:29.392942: step: 1140/530, loss: 0.004634476266801357
2023-01-22 16:41:30.425692: step: 1144/530, loss: 0.006554277613759041
2023-01-22 16:41:31.492306: step: 1148/530, loss: 0.008395140990614891
2023-01-22 16:41:32.520681: step: 1152/530, loss: 0.020909395068883896
2023-01-22 16:41:33.563953: step: 1156/530, loss: 0.009959312155842781
2023-01-22 16:41:34.608221: step: 1160/530, loss: 0.00084947410505265
2023-01-22 16:41:35.640959: step: 1164/530, loss: 0.0018255636096000671
2023-01-22 16:41:36.681888: step: 1168/530, loss: 0.0016596734058111906
2023-01-22 16:41:37.726328: step: 1172/530, loss: 0.010130630806088448
2023-01-22 16:41:38.774431: step: 1176/530, loss: 0.012636475265026093
2023-01-22 16:41:39.819682: step: 1180/530, loss: 0.001632831641472876
2023-01-22 16:41:40.866330: step: 1184/530, loss: 0.0021776848006993532
2023-01-22 16:41:41.931374: step: 1188/530, loss: 0.004113419447094202
2023-01-22 16:41:42.958020: step: 1192/530, loss: 0.001228248467668891
2023-01-22 16:41:43.993482: step: 1196/530, loss: 0.0026793447323143482
2023-01-22 16:41:45.035975: step: 1200/530, loss: 0.0011773507576435804
2023-01-22 16:41:46.065610: step: 1204/530, loss: 0.006706334184855223
2023-01-22 16:41:47.098473: step: 1208/530, loss: 0.0030336366035044193
2023-01-22 16:41:48.133282: step: 1212/530, loss: 0.00010942178778350353
2023-01-22 16:41:49.182573: step: 1216/530, loss: 0.0059114741161465645
2023-01-22 16:41:50.221184: step: 1220/530, loss: 0.0011902586556971073
2023-01-22 16:41:51.241572: step: 1224/530, loss: 0.00015489596989937127
2023-01-22 16:41:52.300319: step: 1228/530, loss: 0.003276297589763999
2023-01-22 16:41:53.374410: step: 1232/530, loss: 0.009583234786987305
2023-01-22 16:41:54.408381: step: 1236/530, loss: 0.0025826788041740656
2023-01-22 16:41:55.447683: step: 1240/530, loss: 0.0003689672448672354
2023-01-22 16:41:56.492971: step: 1244/530, loss: 0.012525648809969425
2023-01-22 16:41:57.552621: step: 1248/530, loss: 0.0009635971509851515
2023-01-22 16:41:58.607103: step: 1252/530, loss: 0.011210901662707329
2023-01-22 16:41:59.651101: step: 1256/530, loss: 0.0628322884440422
2023-01-22 16:42:00.700381: step: 1260/530, loss: 0.00035624243901111186
2023-01-22 16:42:01.759637: step: 1264/530, loss: 0.008533705957233906
2023-01-22 16:42:02.808650: step: 1268/530, loss: 0.0076182191260159016
2023-01-22 16:42:03.894660: step: 1272/530, loss: 0.01421476248651743
2023-01-22 16:42:04.959719: step: 1276/530, loss: 0.0002834429033100605
2023-01-22 16:42:05.998604: step: 1280/530, loss: 0.0006229953723959625
2023-01-22 16:42:07.038475: step: 1284/530, loss: 0.03549204766750336
2023-01-22 16:42:08.061204: step: 1288/530, loss: 0.005786415189504623
2023-01-22 16:42:09.106574: step: 1292/530, loss: 0.005944854114204645
2023-01-22 16:42:10.158446: step: 1296/530, loss: 0.006631250958889723
2023-01-22 16:42:11.206251: step: 1300/530, loss: 0.00032243935856968164
2023-01-22 16:42:12.246423: step: 1304/530, loss: 0.00040961033664643764
2023-01-22 16:42:13.274535: step: 1308/530, loss: 5.458933810587041e-05
2023-01-22 16:42:14.324643: step: 1312/530, loss: 0.006803466472774744
2023-01-22 16:42:15.377534: step: 1316/530, loss: 0.019153432920575142
2023-01-22 16:42:16.420028: step: 1320/530, loss: 0.005157252307981253
2023-01-22 16:42:17.460388: step: 1324/530, loss: 0.002538437256589532
2023-01-22 16:42:18.510545: step: 1328/530, loss: 0.007687521632760763
2023-01-22 16:42:19.587834: step: 1332/530, loss: 0.003714543767273426
2023-01-22 16:42:20.642227: step: 1336/530, loss: 0.0004724572936538607
2023-01-22 16:42:21.662848: step: 1340/530, loss: 0.011397608555853367
2023-01-22 16:42:22.700260: step: 1344/530, loss: 0.0017039562808349729
2023-01-22 16:42:23.734981: step: 1348/530, loss: 0.00597368786111474
2023-01-22 16:42:24.764885: step: 1352/530, loss: 0.0006003369344398379
2023-01-22 16:42:25.808882: step: 1356/530, loss: 0.0037561943754553795
2023-01-22 16:42:26.851011: step: 1360/530, loss: 0.0009858902776613832
2023-01-22 16:42:27.888338: step: 1364/530, loss: 0.0031159569043666124
2023-01-22 16:42:28.941695: step: 1368/530, loss: 0.010406256653368473
2023-01-22 16:42:29.987091: step: 1372/530, loss: 0.0011819112114608288
2023-01-22 16:42:31.024606: step: 1376/530, loss: 0.0020991957280784845
2023-01-22 16:42:32.066842: step: 1380/530, loss: 1.8438924598740414e-05
2023-01-22 16:42:33.107094: step: 1384/530, loss: 0.011804255656898022
2023-01-22 16:42:34.139908: step: 1388/530, loss: 0.00108500593341887
2023-01-22 16:42:35.180706: step: 1392/530, loss: 0.0072795734740793705
2023-01-22 16:42:36.224681: step: 1396/530, loss: 0.009046620689332485
2023-01-22 16:42:37.269151: step: 1400/530, loss: 0.0010546050034463406
2023-01-22 16:42:38.305028: step: 1404/530, loss: 0.0017449066508561373
2023-01-22 16:42:39.330368: step: 1408/530, loss: 0.0054543218575417995
2023-01-22 16:42:40.366088: step: 1412/530, loss: 0.003199639730155468
2023-01-22 16:42:41.399184: step: 1416/530, loss: 0.01098174974322319
2023-01-22 16:42:42.441681: step: 1420/530, loss: 0.0005343706579878926
2023-01-22 16:42:43.476080: step: 1424/530, loss: 0.002258996246382594
2023-01-22 16:42:44.506230: step: 1428/530, loss: 0.0041306097991764545
2023-01-22 16:42:45.562148: step: 1432/530, loss: 0.0025656200014054775
2023-01-22 16:42:46.604337: step: 1436/530, loss: 0.00023132514616008848
2023-01-22 16:42:47.656357: step: 1440/530, loss: 0.015931788831949234
2023-01-22 16:42:48.709530: step: 1444/530, loss: 0.003699875669553876
2023-01-22 16:42:49.756651: step: 1448/530, loss: 0.00031317255343310535
2023-01-22 16:42:50.804378: step: 1452/530, loss: 0.004651620052754879
2023-01-22 16:42:51.847910: step: 1456/530, loss: 0.0044815391302108765
2023-01-22 16:42:52.883327: step: 1460/530, loss: 0.006552047561854124
2023-01-22 16:42:53.914743: step: 1464/530, loss: 0.014346626587212086
2023-01-22 16:42:54.966823: step: 1468/530, loss: 0.007444246206432581
2023-01-22 16:42:56.001481: step: 1472/530, loss: 0.000994421192444861
2023-01-22 16:42:57.041388: step: 1476/530, loss: 0.00458028819411993
2023-01-22 16:42:58.076036: step: 1480/530, loss: 0.017577188089489937
2023-01-22 16:42:59.146768: step: 1484/530, loss: 0.008681370876729488
2023-01-22 16:43:00.185186: step: 1488/530, loss: 0.005712204147130251
2023-01-22 16:43:01.232407: step: 1492/530, loss: 0.0025118859484791756
2023-01-22 16:43:02.268214: step: 1496/530, loss: 0.0019111614674329758
2023-01-22 16:43:03.308236: step: 1500/530, loss: 0.015634384006261826
2023-01-22 16:43:04.352999: step: 1504/530, loss: 6.193132139742374e-05
2023-01-22 16:43:05.394271: step: 1508/530, loss: 0.0022996177431195974
2023-01-22 16:43:06.433093: step: 1512/530, loss: 0.000562844390515238
2023-01-22 16:43:07.464618: step: 1516/530, loss: 0.0022139009088277817
2023-01-22 16:43:08.508639: step: 1520/530, loss: 0.004894523415714502
2023-01-22 16:43:09.549899: step: 1524/530, loss: 0.002735221991315484
2023-01-22 16:43:10.588658: step: 1528/530, loss: 0.0003832722140941769
2023-01-22 16:43:11.624300: step: 1532/530, loss: 5.590159707935527e-05
2023-01-22 16:43:12.687860: step: 1536/530, loss: 0.0008702100603841245
2023-01-22 16:43:13.730663: step: 1540/530, loss: 0.0027145619969815016
2023-01-22 16:43:14.756260: step: 1544/530, loss: 0.009531828574836254
2023-01-22 16:43:15.784816: step: 1548/530, loss: 0.0027640785556286573
2023-01-22 16:43:16.833878: step: 1552/530, loss: 0.0012578010791912675
2023-01-22 16:43:17.874092: step: 1556/530, loss: 0.0012349880998954177
2023-01-22 16:43:18.935540: step: 1560/530, loss: 0.007865747436881065
2023-01-22 16:43:19.982143: step: 1564/530, loss: 6.35531687294133e-05
2023-01-22 16:43:21.030687: step: 1568/530, loss: 0.002713732188567519
2023-01-22 16:43:22.071178: step: 1572/530, loss: 0.012991324067115784
2023-01-22 16:43:23.113384: step: 1576/530, loss: 0.0036734689492732286
2023-01-22 16:43:24.165892: step: 1580/530, loss: 0.003625119337812066
2023-01-22 16:43:25.213099: step: 1584/530, loss: 0.006219614762812853
2023-01-22 16:43:26.258097: step: 1588/530, loss: 0.004824534524232149
2023-01-22 16:43:27.314684: step: 1592/530, loss: 0.001988767646253109
2023-01-22 16:43:28.353021: step: 1596/530, loss: 0.0018592308042570949
2023-01-22 16:43:29.393266: step: 1600/530, loss: 0.00017500405374448746
2023-01-22 16:43:30.442355: step: 1604/530, loss: 0.0003702268295455724
2023-01-22 16:43:31.493906: step: 1608/530, loss: 0.0009201056091114879
2023-01-22 16:43:32.551605: step: 1612/530, loss: 0.002125175204128027
2023-01-22 16:43:33.631104: step: 1616/530, loss: 0.0005968852783553302
2023-01-22 16:43:34.704935: step: 1620/530, loss: 0.004435297567397356
2023-01-22 16:43:35.748488: step: 1624/530, loss: 0.0012423850130289793
2023-01-22 16:43:36.786606: step: 1628/530, loss: 0.003851365763694048
2023-01-22 16:43:37.835563: step: 1632/530, loss: 0.002519437577575445
2023-01-22 16:43:38.887671: step: 1636/530, loss: 0.0018792204791679978
2023-01-22 16:43:39.941304: step: 1640/530, loss: 0.010292806662619114
2023-01-22 16:43:40.983178: step: 1644/530, loss: 0.00264140241779387
2023-01-22 16:43:42.017697: step: 1648/530, loss: 0.01529796700924635
2023-01-22 16:43:43.053576: step: 1652/530, loss: 7.053388253552839e-05
2023-01-22 16:43:44.101782: step: 1656/530, loss: 0.002264065435156226
2023-01-22 16:43:45.151594: step: 1660/530, loss: 0.008241772651672363
2023-01-22 16:43:46.195376: step: 1664/530, loss: 0.0135966707020998
2023-01-22 16:43:47.260346: step: 1668/530, loss: 0.001481459359638393
2023-01-22 16:43:48.312165: step: 1672/530, loss: 0.001255618641152978
2023-01-22 16:43:49.349290: step: 1676/530, loss: 1.674937993811909e-05
2023-01-22 16:43:50.380060: step: 1680/530, loss: 0.000871616299264133
2023-01-22 16:43:51.419752: step: 1684/530, loss: 0.006060166284441948
2023-01-22 16:43:52.459342: step: 1688/530, loss: 0.002602911554276943
2023-01-22 16:43:53.503757: step: 1692/530, loss: 0.008479427546262741
2023-01-22 16:43:54.547590: step: 1696/530, loss: 0.004388756118714809
2023-01-22 16:43:55.599722: step: 1700/530, loss: 0.0019102790392935276
2023-01-22 16:43:56.620909: step: 1704/530, loss: 0.0028448302764445543
2023-01-22 16:43:57.656667: step: 1708/530, loss: 0.001294395886361599
2023-01-22 16:43:58.716815: step: 1712/530, loss: 0.0010381778702139854
2023-01-22 16:43:59.765787: step: 1716/530, loss: 5.277915988699533e-05
2023-01-22 16:44:00.803605: step: 1720/530, loss: 0.00370697770267725
2023-01-22 16:44:01.856096: step: 1724/530, loss: 0.00488363578915596
2023-01-22 16:44:02.920996: step: 1728/530, loss: 0.00016378391592297703
2023-01-22 16:44:03.954788: step: 1732/530, loss: 0.00869457982480526
2023-01-22 16:44:05.016527: step: 1736/530, loss: 0.0037480397149920464
2023-01-22 16:44:06.065628: step: 1740/530, loss: 0.0014802840305492282
2023-01-22 16:44:07.102714: step: 1744/530, loss: 0.004918827209621668
2023-01-22 16:44:08.153492: step: 1748/530, loss: 0.00018765602726489305
2023-01-22 16:44:09.181853: step: 1752/530, loss: 0.003437806386500597
2023-01-22 16:44:10.228329: step: 1756/530, loss: 0.008813544176518917
2023-01-22 16:44:11.275648: step: 1760/530, loss: 0.0030842965934425592
2023-01-22 16:44:12.326011: step: 1764/530, loss: 0.0016851763939484954
2023-01-22 16:44:13.360578: step: 1768/530, loss: 0.005564452148973942
2023-01-22 16:44:14.414572: step: 1772/530, loss: 0.001565176760777831
2023-01-22 16:44:15.465280: step: 1776/530, loss: 0.0032003254164010286
2023-01-22 16:44:16.504128: step: 1780/530, loss: 0.00029246561462059617
2023-01-22 16:44:17.554287: step: 1784/530, loss: 0.003704949514940381
2023-01-22 16:44:18.592322: step: 1788/530, loss: 0.0005255469004623592
2023-01-22 16:44:19.623367: step: 1792/530, loss: 7.619876851094887e-05
2023-01-22 16:44:20.664885: step: 1796/530, loss: 7.677255780436099e-05
2023-01-22 16:44:21.710267: step: 1800/530, loss: 0.007118364796042442
2023-01-22 16:44:22.732262: step: 1804/530, loss: 0.012570079416036606
2023-01-22 16:44:23.775392: step: 1808/530, loss: 0.0025873431004583836
2023-01-22 16:44:24.801276: step: 1812/530, loss: 0.008247978053987026
2023-01-22 16:44:25.863722: step: 1816/530, loss: 0.002031999407336116
2023-01-22 16:44:26.908669: step: 1820/530, loss: 0.00504956254735589
2023-01-22 16:44:27.942815: step: 1824/530, loss: 0.00272430875338614
2023-01-22 16:44:28.979519: step: 1828/530, loss: 0.013086101971566677
2023-01-22 16:44:30.031008: step: 1832/530, loss: 0.004631635267287493
2023-01-22 16:44:31.088810: step: 1836/530, loss: 0.0031072490382939577
2023-01-22 16:44:32.111576: step: 1840/530, loss: 0.0022203095722943544
2023-01-22 16:44:33.166002: step: 1844/530, loss: 0.0038919190410524607
2023-01-22 16:44:34.208171: step: 1848/530, loss: 0.008435151539742947
2023-01-22 16:44:35.261875: step: 1852/530, loss: 0.0022114517632871866
2023-01-22 16:44:36.347030: step: 1856/530, loss: 0.005317586474120617
2023-01-22 16:44:37.387242: step: 1860/530, loss: 0.003897308837622404
2023-01-22 16:44:38.421860: step: 1864/530, loss: 0.0029801796190440655
2023-01-22 16:44:39.482888: step: 1868/530, loss: 0.003196819219738245
2023-01-22 16:44:40.519751: step: 1872/530, loss: 0.01514542754739523
2023-01-22 16:44:41.566281: step: 1876/530, loss: 0.012041516602039337
2023-01-22 16:44:42.619657: step: 1880/530, loss: 0.0013830275274813175
2023-01-22 16:44:43.658044: step: 1884/530, loss: 0.0024755746126174927
2023-01-22 16:44:44.712593: step: 1888/530, loss: 0.00011815586185548455
2023-01-22 16:44:45.761221: step: 1892/530, loss: 0.0077399080619215965
2023-01-22 16:44:46.809539: step: 1896/530, loss: 0.0023121931590139866
2023-01-22 16:44:47.849813: step: 1900/530, loss: 0.002192003885284066
2023-01-22 16:44:48.909047: step: 1904/530, loss: 0.006345229689031839
2023-01-22 16:44:49.993303: step: 1908/530, loss: 0.003066601697355509
2023-01-22 16:44:51.051294: step: 1912/530, loss: 0.000866037153173238
2023-01-22 16:44:52.094640: step: 1916/530, loss: 0.004744301084429026
2023-01-22 16:44:53.151992: step: 1920/530, loss: 0.004265100695192814
2023-01-22 16:44:54.217439: step: 1924/530, loss: 0.007012082729488611
2023-01-22 16:44:55.269169: step: 1928/530, loss: 0.0028661706019192934
2023-01-22 16:44:56.323370: step: 1932/530, loss: 0.004779900424182415
2023-01-22 16:44:57.366021: step: 1936/530, loss: 0.0011881329119205475
2023-01-22 16:44:58.422622: step: 1940/530, loss: 0.0048606423661112785
2023-01-22 16:44:59.475664: step: 1944/530, loss: 0.0021390379406511784
2023-01-22 16:45:00.548631: step: 1948/530, loss: 0.0009323130361735821
2023-01-22 16:45:01.587571: step: 1952/530, loss: 0.007452195044606924
2023-01-22 16:45:02.641917: step: 1956/530, loss: 0.008301799185574055
2023-01-22 16:45:03.719352: step: 1960/530, loss: 0.0032623056322336197
2023-01-22 16:45:04.773987: step: 1964/530, loss: 0.01720890775322914
2023-01-22 16:45:05.833733: step: 1968/530, loss: 0.0022893399000167847
2023-01-22 16:45:06.873452: step: 1972/530, loss: 0.000980921322479844
2023-01-22 16:45:07.922128: step: 1976/530, loss: 0.007523497100919485
2023-01-22 16:45:08.987342: step: 1980/530, loss: 0.001996350474655628
2023-01-22 16:45:10.040017: step: 1984/530, loss: 0.0012559270253404975
2023-01-22 16:45:11.103412: step: 1988/530, loss: 0.0014231265522539616
2023-01-22 16:45:12.155903: step: 1992/530, loss: 0.0010474895825609565
2023-01-22 16:45:13.190447: step: 1996/530, loss: 2.2794338292442262e-06
2023-01-22 16:45:14.237508: step: 2000/530, loss: 0.005295241251587868
2023-01-22 16:45:15.300184: step: 2004/530, loss: 0.005369522608816624
2023-01-22 16:45:16.352790: step: 2008/530, loss: 0.011288786306977272
2023-01-22 16:45:17.389193: step: 2012/530, loss: 0.0031512388959527016
2023-01-22 16:45:18.420188: step: 2016/530, loss: 0.013702718541026115
2023-01-22 16:45:19.453360: step: 2020/530, loss: 0.0023090012837201357
2023-01-22 16:45:20.499705: step: 2024/530, loss: 0.009029623121023178
2023-01-22 16:45:21.537702: step: 2028/530, loss: 0.0007019104668870568
2023-01-22 16:45:22.560028: step: 2032/530, loss: 3.0366447845153743e-06
2023-01-22 16:45:23.587275: step: 2036/530, loss: 0.011007311753928661
2023-01-22 16:45:24.618228: step: 2040/530, loss: 0.0033145921770483255
2023-01-22 16:45:25.666652: step: 2044/530, loss: 0.007975262589752674
2023-01-22 16:45:26.701994: step: 2048/530, loss: 0.005696276668459177
2023-01-22 16:45:27.735965: step: 2052/530, loss: 0.0048665269277989864
2023-01-22 16:45:28.792947: step: 2056/530, loss: 0.010040553286671638
2023-01-22 16:45:29.819634: step: 2060/530, loss: 0.004857656545937061
2023-01-22 16:45:30.870760: step: 2064/530, loss: 0.0018951552920043468
2023-01-22 16:45:31.921739: step: 2068/530, loss: 0.017786642536520958
2023-01-22 16:45:32.992918: step: 2072/530, loss: 0.0007790344534441829
2023-01-22 16:45:34.030375: step: 2076/530, loss: 0.0
2023-01-22 16:45:35.082683: step: 2080/530, loss: 0.021734651178121567
2023-01-22 16:45:36.145949: step: 2084/530, loss: 0.00227438029833138
2023-01-22 16:45:37.192215: step: 2088/530, loss: 0.002077819313853979
2023-01-22 16:45:38.235658: step: 2092/530, loss: 0.008677537553012371
2023-01-22 16:45:39.267617: step: 2096/530, loss: 0.01600026711821556
2023-01-22 16:45:40.322380: step: 2100/530, loss: 0.0011597075499594212
2023-01-22 16:45:41.359544: step: 2104/530, loss: 1.347493252978893e-05
2023-01-22 16:45:42.393219: step: 2108/530, loss: 0.006810830440372229
2023-01-22 16:45:43.441677: step: 2112/530, loss: 0.005150188226252794
2023-01-22 16:45:44.470834: step: 2116/530, loss: 0.010339801199734211
2023-01-22 16:45:45.510281: step: 2120/530, loss: 0.00022283566067926586
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34074851778656123, 'r': 0.3271703036053131, 'f1': 0.3338213939980639}, 'combined': 0.24597365873541546, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3625300933107536, 'r': 0.4085127705873014, 'f1': 0.38415029766550035}, 'combined': 0.2977624316833065, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31116347701409985, 'r': 0.3235627806522329, 'f1': 0.3172420193557706}, 'combined': 0.2337572774200415, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3600764336808553, 'r': 0.41137408737619774, 'f1': 0.3840197400817702}, 'combined': 0.2976612339389798, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33218425528105977, 'r': 0.344160537729523, 'f1': 0.3380663623177234}, 'combined': 0.2491015301288488, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36090139826395357, 'r': 0.3890968200033249, 'f1': 0.37446912000319993}, 'combined': 0.29025836095941815, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:48:12.310253: step: 4/530, loss: 0.0016346677439287305
2023-01-22 16:48:13.383809: step: 8/530, loss: 0.003675297601148486
2023-01-22 16:48:14.421764: step: 12/530, loss: 8.963190339272842e-05
2023-01-22 16:48:15.452771: step: 16/530, loss: 0.00565005699172616
2023-01-22 16:48:16.493150: step: 20/530, loss: 0.009837971068918705
2023-01-22 16:48:17.521425: step: 24/530, loss: 0.0021390339825302362
2023-01-22 16:48:18.572175: step: 28/530, loss: 0.007885076105594635
2023-01-22 16:48:19.616300: step: 32/530, loss: 0.002843404421582818
2023-01-22 16:48:20.666814: step: 36/530, loss: 0.00521209929138422
2023-01-22 16:48:21.710226: step: 40/530, loss: 0.003777820384129882
2023-01-22 16:48:22.758261: step: 44/530, loss: 0.0025085266679525375
2023-01-22 16:48:23.802530: step: 48/530, loss: 0.004044826608151197
2023-01-22 16:48:24.851808: step: 52/530, loss: 0.018876822665333748
2023-01-22 16:48:25.901391: step: 56/530, loss: 0.005854184273630381
2023-01-22 16:48:26.933278: step: 60/530, loss: 0.0013494621962308884
2023-01-22 16:48:27.995064: step: 64/530, loss: 0.021728720515966415
2023-01-22 16:48:29.019531: step: 68/530, loss: 4.5802142267348245e-05
2023-01-22 16:48:30.079239: step: 72/530, loss: 0.004853399936109781
2023-01-22 16:48:31.113892: step: 76/530, loss: 0.0018106414936482906
2023-01-22 16:48:32.167775: step: 80/530, loss: 0.0008266663062386215
2023-01-22 16:48:33.200236: step: 84/530, loss: 0.005835749674588442
2023-01-22 16:48:34.236257: step: 88/530, loss: 0.004660235717892647
2023-01-22 16:48:35.286016: step: 92/530, loss: 0.009952348656952381
2023-01-22 16:48:36.353147: step: 96/530, loss: 0.007610968314111233
2023-01-22 16:48:37.385409: step: 100/530, loss: 0.0013420917093753815
2023-01-22 16:48:38.423704: step: 104/530, loss: 0.0026530746836215258
2023-01-22 16:48:39.470841: step: 108/530, loss: 0.003011272056028247
2023-01-22 16:48:40.512956: step: 112/530, loss: 0.02391926944255829
2023-01-22 16:48:41.557248: step: 116/530, loss: 0.00021972099784761667
2023-01-22 16:48:42.594270: step: 120/530, loss: 0.002886492758989334
2023-01-22 16:48:43.631400: step: 124/530, loss: 0.006241063587367535
2023-01-22 16:48:44.673018: step: 128/530, loss: 0.00011348125553922728
2023-01-22 16:48:45.707593: step: 132/530, loss: 0.006708416156470776
2023-01-22 16:48:46.754609: step: 136/530, loss: 0.024093803018331528
2023-01-22 16:48:47.801368: step: 140/530, loss: 0.00023168597545009106
2023-01-22 16:48:48.844277: step: 144/530, loss: 0.0026332861743867397
2023-01-22 16:48:49.884612: step: 148/530, loss: 0.0036725481040775776
2023-01-22 16:48:50.936340: step: 152/530, loss: 0.004245490301400423
2023-01-22 16:48:51.998305: step: 156/530, loss: 0.0014050767058506608
2023-01-22 16:48:53.040592: step: 160/530, loss: 0.019012991338968277
2023-01-22 16:48:54.074886: step: 164/530, loss: 0.00023355062876362354
2023-01-22 16:48:55.119462: step: 168/530, loss: 0.041325975209474564
2023-01-22 16:48:56.179935: step: 172/530, loss: 0.0006953369593247771
2023-01-22 16:48:57.212779: step: 176/530, loss: 0.043282415717840195
2023-01-22 16:48:58.248939: step: 180/530, loss: 0.00044354505371302366
2023-01-22 16:48:59.290107: step: 184/530, loss: 0.0016363575123250484
2023-01-22 16:49:00.332796: step: 188/530, loss: 0.0019133525202050805
2023-01-22 16:49:01.381827: step: 192/530, loss: 0.005224434658885002
2023-01-22 16:49:02.434398: step: 196/530, loss: 0.0006499649025499821
2023-01-22 16:49:03.483613: step: 200/530, loss: 0.0036496578250080347
2023-01-22 16:49:04.525231: step: 204/530, loss: 0.0025979732163250446
2023-01-22 16:49:05.582467: step: 208/530, loss: 0.0006325413123704493
2023-01-22 16:49:06.634235: step: 212/530, loss: 0.024446314200758934
2023-01-22 16:49:07.673694: step: 216/530, loss: 0.000326610985212028
2023-01-22 16:49:08.720816: step: 220/530, loss: 0.0028669715393334627
2023-01-22 16:49:09.752986: step: 224/530, loss: 0.01616206020116806
2023-01-22 16:49:10.792226: step: 228/530, loss: 0.003300365526229143
2023-01-22 16:49:11.837550: step: 232/530, loss: 0.0007692713406868279
2023-01-22 16:49:12.887195: step: 236/530, loss: 0.006896074861288071
2023-01-22 16:49:13.922763: step: 240/530, loss: 0.0038489573635160923
2023-01-22 16:49:14.955836: step: 244/530, loss: 0.003974266815930605
2023-01-22 16:49:15.997685: step: 248/530, loss: 0.0008489040192216635
2023-01-22 16:49:17.044171: step: 252/530, loss: 0.005472026765346527
2023-01-22 16:49:18.075205: step: 256/530, loss: 3.281903673268971e-07
2023-01-22 16:49:19.126494: step: 260/530, loss: 0.030663231387734413
2023-01-22 16:49:20.173482: step: 264/530, loss: 0.0011019647354260087
2023-01-22 16:49:21.224859: step: 268/530, loss: 0.009593290276825428
2023-01-22 16:49:22.259326: step: 272/530, loss: 0.0049520437605679035
2023-01-22 16:49:23.313286: step: 276/530, loss: 0.003528180532157421
2023-01-22 16:49:24.350293: step: 280/530, loss: 0.001853889785706997
2023-01-22 16:49:25.377228: step: 284/530, loss: 0.0008176437695510685
2023-01-22 16:49:26.432736: step: 288/530, loss: 0.0020257695578038692
2023-01-22 16:49:27.480146: step: 292/530, loss: 0.001921321265399456
2023-01-22 16:49:28.531820: step: 296/530, loss: 0.010214938782155514
2023-01-22 16:49:29.587895: step: 300/530, loss: 0.002811092184856534
2023-01-22 16:49:30.627088: step: 304/530, loss: 0.00010787619248731062
2023-01-22 16:49:31.675256: step: 308/530, loss: 0.0029250311199575663
2023-01-22 16:49:32.725224: step: 312/530, loss: 0.0023454746697098017
2023-01-22 16:49:33.766794: step: 316/530, loss: 0.012640808708965778
2023-01-22 16:49:34.826783: step: 320/530, loss: 0.0015858152182772756
2023-01-22 16:49:35.879787: step: 324/530, loss: 0.0035949964076280594
2023-01-22 16:49:36.929533: step: 328/530, loss: 0.005279530771076679
2023-01-22 16:49:37.981259: step: 332/530, loss: 0.008063623681664467
2023-01-22 16:49:39.027449: step: 336/530, loss: 0.000725615827832371
2023-01-22 16:49:40.088055: step: 340/530, loss: 0.00016533599409740418
2023-01-22 16:49:41.147036: step: 344/530, loss: 0.0020527879241853952
2023-01-22 16:49:42.180430: step: 348/530, loss: 0.00041898328345268965
2023-01-22 16:49:43.225599: step: 352/530, loss: 0.0023069726303219795
2023-01-22 16:49:44.279870: step: 356/530, loss: 0.006121960002928972
2023-01-22 16:49:45.312920: step: 360/530, loss: 1.2996922123420518e-05
2023-01-22 16:49:46.352185: step: 364/530, loss: 2.8845883207395673e-05
2023-01-22 16:49:47.392271: step: 368/530, loss: 0.0035502160899341106
2023-01-22 16:49:48.434917: step: 372/530, loss: 0.00973084382712841
2023-01-22 16:49:49.485365: step: 376/530, loss: 0.0008423366816714406
2023-01-22 16:49:50.533032: step: 380/530, loss: 0.0028338225092738867
2023-01-22 16:49:51.581022: step: 384/530, loss: 0.0005899100797250867
2023-01-22 16:49:52.649119: step: 388/530, loss: 0.010503212921321392
2023-01-22 16:49:53.692860: step: 392/530, loss: 0.00513524329289794
2023-01-22 16:49:54.726287: step: 396/530, loss: 0.016411567106842995
2023-01-22 16:49:55.763301: step: 400/530, loss: 0.00012324421550147235
2023-01-22 16:49:56.818281: step: 404/530, loss: 0.005968338809907436
2023-01-22 16:49:57.869982: step: 408/530, loss: 0.0038618259131908417
2023-01-22 16:49:58.911800: step: 412/530, loss: 0.009258364327251911
2023-01-22 16:49:59.972686: step: 416/530, loss: 0.021530913189053535
2023-01-22 16:50:01.027308: step: 420/530, loss: 0.007830331102013588
2023-01-22 16:50:02.081084: step: 424/530, loss: 0.007883569225668907
2023-01-22 16:50:03.159329: step: 428/530, loss: 0.01603441871702671
2023-01-22 16:50:04.198607: step: 432/530, loss: 0.008814103901386261
2023-01-22 16:50:05.242333: step: 436/530, loss: 0.0035951256286352873
2023-01-22 16:50:06.292793: step: 440/530, loss: 0.00854410044848919
2023-01-22 16:50:07.346766: step: 444/530, loss: 0.0014864866388961673
2023-01-22 16:50:08.407791: step: 448/530, loss: 0.002587459748610854
2023-01-22 16:50:09.441168: step: 452/530, loss: 0.00239950162358582
2023-01-22 16:50:10.473033: step: 456/530, loss: 4.5807395508745685e-05
2023-01-22 16:50:11.493344: step: 460/530, loss: 0.0013485102681443095
2023-01-22 16:50:12.533257: step: 464/530, loss: 0.0008352117147296667
2023-01-22 16:50:13.588213: step: 468/530, loss: 0.01152646541595459
2023-01-22 16:50:14.630794: step: 472/530, loss: 0.021400773897767067
2023-01-22 16:50:15.676293: step: 476/530, loss: 0.0020851807203143835
2023-01-22 16:50:16.745972: step: 480/530, loss: 0.006133920978754759
2023-01-22 16:50:17.796219: step: 484/530, loss: 0.021603532135486603
2023-01-22 16:50:18.852188: step: 488/530, loss: 0.001309685525484383
2023-01-22 16:50:19.906162: step: 492/530, loss: 0.0016548128332942724
2023-01-22 16:50:20.946806: step: 496/530, loss: 8.88724607648328e-05
2023-01-22 16:50:21.984994: step: 500/530, loss: 0.0006548142991960049
2023-01-22 16:50:23.043451: step: 504/530, loss: 0.0004508278507273644
2023-01-22 16:50:24.083206: step: 508/530, loss: 0.0
2023-01-22 16:50:25.137342: step: 512/530, loss: 0.006211565341800451
2023-01-22 16:50:26.180088: step: 516/530, loss: 0.0003564735525287688
2023-01-22 16:50:27.229575: step: 520/530, loss: 0.0068017481826245785
2023-01-22 16:50:28.286398: step: 524/530, loss: 0.00040756972157396376
2023-01-22 16:50:29.317028: step: 528/530, loss: 0.0023978622630238533
2023-01-22 16:50:30.349339: step: 532/530, loss: 0.005935546476393938
2023-01-22 16:50:31.398260: step: 536/530, loss: 0.017470233142375946
2023-01-22 16:50:32.442344: step: 540/530, loss: 0.009147955104708672
2023-01-22 16:50:33.480575: step: 544/530, loss: 0.0031279607210308313
2023-01-22 16:50:34.520445: step: 548/530, loss: 0.0004049708950333297
2023-01-22 16:50:35.571586: step: 552/530, loss: 0.0024942634627223015
2023-01-22 16:50:36.630379: step: 556/530, loss: 0.012339996173977852
2023-01-22 16:50:37.677593: step: 560/530, loss: 0.0007899929187260568
2023-01-22 16:50:38.721897: step: 564/530, loss: 0.0006798647809773684
2023-01-22 16:50:39.773024: step: 568/530, loss: 0.0012958283768966794
2023-01-22 16:50:40.822488: step: 572/530, loss: 0.005314614158123732
2023-01-22 16:50:41.871221: step: 576/530, loss: 1.1772711332014296e-05
2023-01-22 16:50:42.900167: step: 580/530, loss: 0.0008427457069046795
2023-01-22 16:50:43.945864: step: 584/530, loss: 0.0007043863879516721
2023-01-22 16:50:44.995713: step: 588/530, loss: 0.006046108435839415
2023-01-22 16:50:46.027218: step: 592/530, loss: 0.0016927807591855526
2023-01-22 16:50:47.087351: step: 596/530, loss: 0.009806297719478607
2023-01-22 16:50:48.140676: step: 600/530, loss: 0.0049317367374897
2023-01-22 16:50:49.194184: step: 604/530, loss: 0.0012931310338899493
2023-01-22 16:50:50.240264: step: 608/530, loss: 0.02182329073548317
2023-01-22 16:50:51.285597: step: 612/530, loss: 0.0027955302502959967
2023-01-22 16:50:52.334055: step: 616/530, loss: 0.0018680758075788617
2023-01-22 16:50:53.364026: step: 620/530, loss: 0.00029663185705430806
2023-01-22 16:50:54.400711: step: 624/530, loss: 0.002389618894085288
2023-01-22 16:50:55.448305: step: 628/530, loss: 0.006171109154820442
2023-01-22 16:50:56.508650: step: 632/530, loss: 0.0007514026365242898
2023-01-22 16:50:57.555133: step: 636/530, loss: 0.003579250071197748
2023-01-22 16:50:58.611110: step: 640/530, loss: 0.0014014053158462048
2023-01-22 16:50:59.659085: step: 644/530, loss: 0.0031395924743264914
2023-01-22 16:51:00.711642: step: 648/530, loss: 0.001203692751005292
2023-01-22 16:51:01.765304: step: 652/530, loss: 0.002001269022002816
2023-01-22 16:51:02.793850: step: 656/530, loss: 0.0008503199787810445
2023-01-22 16:51:03.832261: step: 660/530, loss: 0.0016651725163683295
2023-01-22 16:51:04.875543: step: 664/530, loss: 0.0044419714249670506
2023-01-22 16:51:05.911281: step: 668/530, loss: 0.0044181267730891705
2023-01-22 16:51:06.962314: step: 672/530, loss: 0.0015515610575675964
2023-01-22 16:51:08.015751: step: 676/530, loss: 1.1240268577239476e-05
2023-01-22 16:51:09.051587: step: 680/530, loss: 0.0005631298990920186
2023-01-22 16:51:10.105630: step: 684/530, loss: 0.0015676140319555998
2023-01-22 16:51:11.153512: step: 688/530, loss: 0.0007023405050858855
2023-01-22 16:51:12.199183: step: 692/530, loss: 0.00863282848149538
2023-01-22 16:51:13.236544: step: 696/530, loss: 0.0004379982710815966
2023-01-22 16:51:14.291835: step: 700/530, loss: 0.005205802619457245
2023-01-22 16:51:15.321826: step: 704/530, loss: 0.003251198213547468
2023-01-22 16:51:16.357126: step: 708/530, loss: 0.0013841241598129272
2023-01-22 16:51:17.394064: step: 712/530, loss: 0.003165752161294222
2023-01-22 16:51:18.456454: step: 716/530, loss: 0.0013279749546200037
2023-01-22 16:51:19.497871: step: 720/530, loss: 0.0034479363821446896
2023-01-22 16:51:20.569460: step: 724/530, loss: 0.0029910055454820395
2023-01-22 16:51:21.606480: step: 728/530, loss: 0.0004792314430233091
2023-01-22 16:51:22.678340: step: 732/530, loss: 0.0015904501779004931
2023-01-22 16:51:23.713684: step: 736/530, loss: 0.006513257510960102
2023-01-22 16:51:24.767062: step: 740/530, loss: 0.00045964971650391817
2023-01-22 16:51:25.804189: step: 744/530, loss: 1.1577099030546378e-06
2023-01-22 16:51:26.849000: step: 748/530, loss: 0.00016964190581347793
2023-01-22 16:51:27.901606: step: 752/530, loss: 0.00014626690244767815
2023-01-22 16:51:28.951101: step: 756/530, loss: 0.0017723914934322238
2023-01-22 16:51:30.004811: step: 760/530, loss: 0.0031594065949320793
2023-01-22 16:51:31.050922: step: 764/530, loss: 0.0025188724976032972
2023-01-22 16:51:32.086768: step: 768/530, loss: 0.0005355093744583428
2023-01-22 16:51:33.156561: step: 772/530, loss: 0.0029823577497154474
2023-01-22 16:51:34.207423: step: 776/530, loss: 0.0007006157538853586
2023-01-22 16:51:35.257362: step: 780/530, loss: 0.001940453890711069
2023-01-22 16:51:36.307815: step: 784/530, loss: 0.0003366061137057841
2023-01-22 16:51:37.361379: step: 788/530, loss: 0.002615744946524501
2023-01-22 16:51:38.413431: step: 792/530, loss: 0.003225903259590268
2023-01-22 16:51:39.455984: step: 796/530, loss: 0.0014087334275245667
2023-01-22 16:51:40.496555: step: 800/530, loss: 0.0014808470150455832
2023-01-22 16:51:41.544959: step: 804/530, loss: 0.00101218291092664
2023-01-22 16:51:42.590067: step: 808/530, loss: 0.000100733719591517
2023-01-22 16:51:43.637821: step: 812/530, loss: 0.00043810647912323475
2023-01-22 16:51:44.681793: step: 816/530, loss: 0.0033638705499470234
2023-01-22 16:51:45.731969: step: 820/530, loss: 0.0016776984557509422
2023-01-22 16:51:46.764951: step: 824/530, loss: 0.0011634697439149022
2023-01-22 16:51:47.831226: step: 828/530, loss: 0.006496155634522438
2023-01-22 16:51:48.875500: step: 832/530, loss: 0.009308735840022564
2023-01-22 16:51:49.949214: step: 836/530, loss: 0.001778215984813869
2023-01-22 16:51:51.004038: step: 840/530, loss: 0.0025846268981695175
2023-01-22 16:51:52.053757: step: 844/530, loss: 0.031112458556890488
2023-01-22 16:51:53.091431: step: 848/530, loss: 0.0006541639450006187
2023-01-22 16:51:54.134613: step: 852/530, loss: 0.00017527453019283712
2023-01-22 16:51:55.179239: step: 856/530, loss: 0.0044852364808321
2023-01-22 16:51:56.228440: step: 860/530, loss: 0.005102625582367182
2023-01-22 16:51:57.289007: step: 864/530, loss: 0.0032032590825110674
2023-01-22 16:51:58.348573: step: 868/530, loss: 0.004433238413184881
2023-01-22 16:51:59.381885: step: 872/530, loss: 0.0007703463779762387
2023-01-22 16:52:00.429279: step: 876/530, loss: 0.003734318073838949
2023-01-22 16:52:01.481075: step: 880/530, loss: 0.011195659637451172
2023-01-22 16:52:02.517111: step: 884/530, loss: 0.010753174312412739
2023-01-22 16:52:03.550345: step: 888/530, loss: 0.0008762682555243373
2023-01-22 16:52:04.613225: step: 892/530, loss: 0.004485843703150749
2023-01-22 16:52:05.658519: step: 896/530, loss: 0.0036895328667014837
2023-01-22 16:52:06.706145: step: 900/530, loss: 0.00019181902462150902
2023-01-22 16:52:07.743776: step: 904/530, loss: 0.0001848454267019406
2023-01-22 16:52:08.787284: step: 908/530, loss: 0.0006472284439951181
2023-01-22 16:52:09.838398: step: 912/530, loss: 0.0056353467516601086
2023-01-22 16:52:10.899887: step: 916/530, loss: 4.909193648927612e-06
2023-01-22 16:52:11.933471: step: 920/530, loss: 0.016644641757011414
2023-01-22 16:52:12.957911: step: 924/530, loss: 0.0016755490796640515
2023-01-22 16:52:13.985865: step: 928/530, loss: 8.314847218571231e-05
2023-01-22 16:52:15.039853: step: 932/530, loss: 0.003018605289980769
2023-01-22 16:52:16.098433: step: 936/530, loss: 0.004783610347658396
2023-01-22 16:52:17.125264: step: 940/530, loss: 0.0028378639835864305
2023-01-22 16:52:18.192961: step: 944/530, loss: 0.008646524511277676
2023-01-22 16:52:19.244562: step: 948/530, loss: 0.0016284373123198748
2023-01-22 16:52:20.272969: step: 952/530, loss: 0.006739044561982155
2023-01-22 16:52:21.327380: step: 956/530, loss: 0.0017372049624100327
2023-01-22 16:52:22.365671: step: 960/530, loss: 0.003786595305427909
2023-01-22 16:52:23.409238: step: 964/530, loss: 0.00020437585772015154
2023-01-22 16:52:24.454570: step: 968/530, loss: 0.0005733373109251261
2023-01-22 16:52:25.496430: step: 972/530, loss: 7.953478780109435e-05
2023-01-22 16:52:26.537614: step: 976/530, loss: 0.0005118280532769859
2023-01-22 16:52:27.584718: step: 980/530, loss: 0.004252298269420862
2023-01-22 16:52:28.626904: step: 984/530, loss: 0.0030935704708099365
2023-01-22 16:52:29.666241: step: 988/530, loss: 0.006477537099272013
2023-01-22 16:52:30.726985: step: 992/530, loss: 0.013364238664507866
2023-01-22 16:52:31.771192: step: 996/530, loss: 0.0014077663654461503
2023-01-22 16:52:32.820207: step: 1000/530, loss: 0.003003102960065007
2023-01-22 16:52:33.891328: step: 1004/530, loss: 0.0015073404647409916
2023-01-22 16:52:34.940883: step: 1008/530, loss: 0.0008681311155669391
2023-01-22 16:52:35.981794: step: 1012/530, loss: 0.002079136436805129
2023-01-22 16:52:37.014900: step: 1016/530, loss: 0.0004659243568312377
2023-01-22 16:52:38.065159: step: 1020/530, loss: 0.005345776677131653
2023-01-22 16:52:39.093201: step: 1024/530, loss: 0.0021580331958830357
2023-01-22 16:52:40.125761: step: 1028/530, loss: 0.007207970600575209
2023-01-22 16:52:41.160176: step: 1032/530, loss: 2.518750261515379e-05
2023-01-22 16:52:42.195182: step: 1036/530, loss: 0.005891777109354734
2023-01-22 16:52:43.228966: step: 1040/530, loss: 0.01195522677153349
2023-01-22 16:52:44.271733: step: 1044/530, loss: 0.00037829522625543177
2023-01-22 16:52:45.304442: step: 1048/530, loss: 0.0003775592485908419
2023-01-22 16:52:46.334299: step: 1052/530, loss: 0.0024395822547376156
2023-01-22 16:52:47.364975: step: 1056/530, loss: 0.0011896878713741899
2023-01-22 16:52:48.428426: step: 1060/530, loss: 0.0027918650303035975
2023-01-22 16:52:49.477249: step: 1064/530, loss: 0.00016347611381206661
2023-01-22 16:52:50.516217: step: 1068/530, loss: 0.0054471734911203384
2023-01-22 16:52:51.562975: step: 1072/530, loss: 0.0013330650981515646
2023-01-22 16:52:52.617507: step: 1076/530, loss: 0.0008108783513307571
2023-01-22 16:52:53.659005: step: 1080/530, loss: 0.002921827370300889
2023-01-22 16:52:54.725626: step: 1084/530, loss: 0.0006199057679623365
2023-01-22 16:52:55.765334: step: 1088/530, loss: 0.007223739754408598
2023-01-22 16:52:56.825778: step: 1092/530, loss: 0.00037254771450534463
2023-01-22 16:52:57.871735: step: 1096/530, loss: 0.006985718384385109
2023-01-22 16:52:58.911941: step: 1100/530, loss: 0.00378967821598053
2023-01-22 16:52:59.952686: step: 1104/530, loss: 0.009589145891368389
2023-01-22 16:53:01.010239: step: 1108/530, loss: 2.0393277736729942e-05
2023-01-22 16:53:02.053091: step: 1112/530, loss: 0.0083364462479949
2023-01-22 16:53:03.086235: step: 1116/530, loss: 0.0023572510108351707
2023-01-22 16:53:04.135079: step: 1120/530, loss: 0.00036582129541784525
2023-01-22 16:53:05.168278: step: 1124/530, loss: 0.009437032975256443
2023-01-22 16:53:06.219502: step: 1128/530, loss: 0.0021231600549072027
2023-01-22 16:53:07.275813: step: 1132/530, loss: 0.0014759768964722753
2023-01-22 16:53:08.333252: step: 1136/530, loss: 0.0016669026808813214
2023-01-22 16:53:09.386635: step: 1140/530, loss: 0.000987692386843264
2023-01-22 16:53:10.438287: step: 1144/530, loss: 0.0006102340994402766
2023-01-22 16:53:11.480071: step: 1148/530, loss: 0.0050750416703522205
2023-01-22 16:53:12.526863: step: 1152/530, loss: 0.004148300737142563
2023-01-22 16:53:13.579545: step: 1156/530, loss: 8.818758215056732e-05
2023-01-22 16:53:14.627643: step: 1160/530, loss: 0.00031680401298217475
2023-01-22 16:53:15.676462: step: 1164/530, loss: 0.005485094152390957
2023-01-22 16:53:16.710414: step: 1168/530, loss: 0.001176755758933723
2023-01-22 16:53:17.758458: step: 1172/530, loss: 0.01726360246539116
2023-01-22 16:53:18.796104: step: 1176/530, loss: 0.00626567006111145
2023-01-22 16:53:19.842450: step: 1180/530, loss: 0.005810895003378391
2023-01-22 16:53:20.874809: step: 1184/530, loss: 0.00011842435196740553
2023-01-22 16:53:21.930407: step: 1188/530, loss: 0.03415227681398392
2023-01-22 16:53:22.972142: step: 1192/530, loss: 0.004371089395135641
2023-01-22 16:53:24.010767: step: 1196/530, loss: 0.013393866829574108
2023-01-22 16:53:25.063130: step: 1200/530, loss: 0.003492301795631647
2023-01-22 16:53:26.116795: step: 1204/530, loss: 0.027621056884527206
2023-01-22 16:53:27.176827: step: 1208/530, loss: 0.006727175787091255
2023-01-22 16:53:28.228859: step: 1212/530, loss: 0.016643723472952843
2023-01-22 16:53:29.273845: step: 1216/530, loss: 0.0009906409541144967
2023-01-22 16:53:30.310971: step: 1220/530, loss: 0.002239114372059703
2023-01-22 16:53:31.350752: step: 1224/530, loss: 0.002180964918807149
2023-01-22 16:53:32.394397: step: 1228/530, loss: 0.007498615887016058
2023-01-22 16:53:33.439832: step: 1232/530, loss: 7.95206051407149e-06
2023-01-22 16:53:34.480460: step: 1236/530, loss: 0.0028945051599293947
2023-01-22 16:53:35.521025: step: 1240/530, loss: 0.0017162695294246078
2023-01-22 16:53:36.579433: step: 1244/530, loss: 0.0003706467105075717
2023-01-22 16:53:37.629631: step: 1248/530, loss: 0.0062610381282866
2023-01-22 16:53:38.677794: step: 1252/530, loss: 0.008994611911475658
2023-01-22 16:53:39.734776: step: 1256/530, loss: 0.001414175727404654
2023-01-22 16:53:40.769748: step: 1260/530, loss: 0.010115209966897964
2023-01-22 16:53:41.812587: step: 1264/530, loss: 0.002679947530850768
2023-01-22 16:53:42.853035: step: 1268/530, loss: 0.0018600476905703545
2023-01-22 16:53:43.894560: step: 1272/530, loss: 0.0004839859320782125
2023-01-22 16:53:44.941392: step: 1276/530, loss: 0.0006661342922598124
2023-01-22 16:53:46.004184: step: 1280/530, loss: 0.0004133051843382418
2023-01-22 16:53:47.054385: step: 1284/530, loss: 0.01169020589441061
2023-01-22 16:53:48.117799: step: 1288/530, loss: 0.0038833527360111475
2023-01-22 16:53:49.151343: step: 1292/530, loss: 0.0001987712166737765
2023-01-22 16:53:50.194965: step: 1296/530, loss: 0.004742329008877277
2023-01-22 16:53:51.244985: step: 1300/530, loss: 0.00645976047962904
2023-01-22 16:53:52.274917: step: 1304/530, loss: 0.0025145760737359524
2023-01-22 16:53:53.322699: step: 1308/530, loss: 0.00340718450024724
2023-01-22 16:53:54.351267: step: 1312/530, loss: 3.2552591164858313e-06
2023-01-22 16:53:55.387638: step: 1316/530, loss: 3.858712443616241e-05
2023-01-22 16:53:56.446646: step: 1320/530, loss: 0.10316751897335052
2023-01-22 16:53:57.484885: step: 1324/530, loss: 0.01041797362267971
2023-01-22 16:53:58.538619: step: 1328/530, loss: 0.021871104836463928
2023-01-22 16:53:59.580836: step: 1332/530, loss: 0.004269781522452831
2023-01-22 16:54:00.625057: step: 1336/530, loss: 0.0006900060107000172
2023-01-22 16:54:01.670787: step: 1340/530, loss: 0.007187479175627232
2023-01-22 16:54:02.704294: step: 1344/530, loss: 0.0028446244541555643
2023-01-22 16:54:03.778908: step: 1348/530, loss: 0.027358926832675934
2023-01-22 16:54:04.824630: step: 1352/530, loss: 0.0019490565173327923
2023-01-22 16:54:05.874790: step: 1356/530, loss: 0.01167477946728468
2023-01-22 16:54:06.930392: step: 1360/530, loss: 0.008325232192873955
2023-01-22 16:54:07.974757: step: 1364/530, loss: 0.006251713261008263
2023-01-22 16:54:09.025481: step: 1368/530, loss: 1.9401213648961857e-06
2023-01-22 16:54:10.068649: step: 1372/530, loss: 0.005534324795007706
2023-01-22 16:54:11.122893: step: 1376/530, loss: 0.01440263818949461
2023-01-22 16:54:12.170954: step: 1380/530, loss: 0.008540664799511433
2023-01-22 16:54:13.226342: step: 1384/530, loss: 0.0006516218418255448
2023-01-22 16:54:14.284091: step: 1388/530, loss: 0.02173752896487713
2023-01-22 16:54:15.321391: step: 1392/530, loss: 0.0027636161539703608
2023-01-22 16:54:16.351981: step: 1396/530, loss: 0.00596939492970705
2023-01-22 16:54:17.390750: step: 1400/530, loss: 0.010441185906529427
2023-01-22 16:54:18.432359: step: 1404/530, loss: 0.014863350428640842
2023-01-22 16:54:19.476010: step: 1408/530, loss: 0.001951046520844102
2023-01-22 16:54:20.526875: step: 1412/530, loss: 0.005583907011896372
2023-01-22 16:54:21.555997: step: 1416/530, loss: 0.002855088096112013
2023-01-22 16:54:22.588065: step: 1420/530, loss: 0.0049894885160028934
2023-01-22 16:54:23.634254: step: 1424/530, loss: 0.0006128315581008792
2023-01-22 16:54:24.664326: step: 1428/530, loss: 0.00333867478184402
2023-01-22 16:54:25.714912: step: 1432/530, loss: 0.016556404531002045
2023-01-22 16:54:26.772269: step: 1436/530, loss: 0.015891462564468384
2023-01-22 16:54:27.815489: step: 1440/530, loss: 0.0013385652564466
2023-01-22 16:54:28.851773: step: 1444/530, loss: 0.0011590908979997039
2023-01-22 16:54:29.886452: step: 1448/530, loss: 2.591070256130479e-07
2023-01-22 16:54:30.932406: step: 1452/530, loss: 0.0024300680961459875
2023-01-22 16:54:31.982683: step: 1456/530, loss: 0.0007945887045934796
2023-01-22 16:54:33.022485: step: 1460/530, loss: 0.0009450240177102387
2023-01-22 16:54:34.057750: step: 1464/530, loss: 0.01220585498958826
2023-01-22 16:54:35.087467: step: 1468/530, loss: 0.00014535269292537123
2023-01-22 16:54:36.125183: step: 1472/530, loss: 0.003059492679312825
2023-01-22 16:54:37.185592: step: 1476/530, loss: 0.005597684998065233
2023-01-22 16:54:38.221673: step: 1480/530, loss: 0.0032327519729733467
2023-01-22 16:54:39.269852: step: 1484/530, loss: 0.005534071940928698
2023-01-22 16:54:40.319498: step: 1488/530, loss: 0.009242421016097069
2023-01-22 16:54:41.359251: step: 1492/530, loss: 0.0017967646708711982
2023-01-22 16:54:42.384601: step: 1496/530, loss: 0.0014293482527136803
2023-01-22 16:54:43.438045: step: 1500/530, loss: 0.0018570758402347565
2023-01-22 16:54:44.478654: step: 1504/530, loss: 0.0012327064760029316
2023-01-22 16:54:45.531184: step: 1508/530, loss: 0.0006538216257467866
2023-01-22 16:54:46.576132: step: 1512/530, loss: 0.002998492680490017
2023-01-22 16:54:47.610324: step: 1516/530, loss: 0.0007727608899585903
2023-01-22 16:54:48.657769: step: 1520/530, loss: 0.0029330395627766848
2023-01-22 16:54:49.707252: step: 1524/530, loss: 0.00407476257532835
2023-01-22 16:54:50.755310: step: 1528/530, loss: 0.0021292457822710276
2023-01-22 16:54:51.794305: step: 1532/530, loss: 0.00473290029913187
2023-01-22 16:54:52.851021: step: 1536/530, loss: 0.007184077054262161
2023-01-22 16:54:53.901531: step: 1540/530, loss: 0.005728963762521744
2023-01-22 16:54:54.927410: step: 1544/530, loss: 0.00018021403229795396
2023-01-22 16:54:55.981306: step: 1548/530, loss: 0.03402888774871826
2023-01-22 16:54:57.022035: step: 1552/530, loss: 0.005641507916152477
2023-01-22 16:54:58.077357: step: 1556/530, loss: 0.006954981479793787
2023-01-22 16:54:59.122769: step: 1560/530, loss: 0.002068853471428156
2023-01-22 16:55:00.156805: step: 1564/530, loss: 7.593764166813344e-05
2023-01-22 16:55:01.228547: step: 1568/530, loss: 0.003554497379809618
2023-01-22 16:55:02.280821: step: 1572/530, loss: 0.0005778810009360313
2023-01-22 16:55:03.350399: step: 1576/530, loss: 0.0022768541239202023
2023-01-22 16:55:04.392770: step: 1580/530, loss: 0.0015208704862743616
2023-01-22 16:55:05.437913: step: 1584/530, loss: 0.005875979550182819
2023-01-22 16:55:06.482625: step: 1588/530, loss: 0.005047973711043596
2023-01-22 16:55:07.520849: step: 1592/530, loss: 0.011728701181709766
2023-01-22 16:55:08.576577: step: 1596/530, loss: 0.0011360831558704376
2023-01-22 16:55:09.621770: step: 1600/530, loss: 2.102630560329999e-06
2023-01-22 16:55:10.673304: step: 1604/530, loss: 0.003437940962612629
2023-01-22 16:55:11.723892: step: 1608/530, loss: 0.003398310160264373
2023-01-22 16:55:12.751772: step: 1612/530, loss: 4.358696605777368e-05
2023-01-22 16:55:13.805042: step: 1616/530, loss: 0.0004393762210384011
2023-01-22 16:55:14.891002: step: 1620/530, loss: 0.0056333960965275764
2023-01-22 16:55:15.943101: step: 1624/530, loss: 0.001232057809829712
2023-01-22 16:55:16.977707: step: 1628/530, loss: 0.005570483393967152
2023-01-22 16:55:18.023442: step: 1632/530, loss: 0.005351976025849581
2023-01-22 16:55:19.063348: step: 1636/530, loss: 0.0009466410847380757
2023-01-22 16:55:20.106023: step: 1640/530, loss: 0.0029156797099858522
2023-01-22 16:55:21.144340: step: 1644/530, loss: 0.00151121208909899
2023-01-22 16:55:22.199690: step: 1648/530, loss: 0.007095366716384888
2023-01-22 16:55:23.247907: step: 1652/530, loss: 0.0005021628458052874
2023-01-22 16:55:24.288158: step: 1656/530, loss: 8.454511407762766e-05
2023-01-22 16:55:25.346657: step: 1660/530, loss: 0.008493185043334961
2023-01-22 16:55:26.384477: step: 1664/530, loss: 0.0021600769832730293
2023-01-22 16:55:27.433044: step: 1668/530, loss: 0.004124830476939678
2023-01-22 16:55:28.482273: step: 1672/530, loss: 0.0038572305347770452
2023-01-22 16:55:29.515518: step: 1676/530, loss: 0.0003642990777734667
2023-01-22 16:55:30.576491: step: 1680/530, loss: 0.0005445689894258976
2023-01-22 16:55:31.617478: step: 1684/530, loss: 0.005153903737664223
2023-01-22 16:55:32.713978: step: 1688/530, loss: 0.007264290004968643
2023-01-22 16:55:33.760256: step: 1692/530, loss: 0.0027415661606937647
2023-01-22 16:55:34.808672: step: 1696/530, loss: 0.00010127613495569676
2023-01-22 16:55:35.857375: step: 1700/530, loss: 0.0060294982977211475
2023-01-22 16:55:36.909736: step: 1704/530, loss: 0.008547945879399776
2023-01-22 16:55:37.968132: step: 1708/530, loss: 0.00027285379474051297
2023-01-22 16:55:39.008674: step: 1712/530, loss: 0.0028091531712561846
2023-01-22 16:55:40.055327: step: 1716/530, loss: 6.0254136769799516e-05
2023-01-22 16:55:41.106858: step: 1720/530, loss: 0.003719775006175041
2023-01-22 16:55:42.156845: step: 1724/530, loss: 0.001921151066198945
2023-01-22 16:55:43.196573: step: 1728/530, loss: 0.0026825922541320324
2023-01-22 16:55:44.240818: step: 1732/530, loss: 0.00022626893769484013
2023-01-22 16:55:45.279811: step: 1736/530, loss: 0.0005456481594592333
2023-01-22 16:55:46.309721: step: 1740/530, loss: 0.00511472811922431
2023-01-22 16:55:47.355998: step: 1744/530, loss: 0.011158404871821404
2023-01-22 16:55:48.406431: step: 1748/530, loss: 5.462756234919652e-06
2023-01-22 16:55:49.455737: step: 1752/530, loss: 0.0012531798565760255
2023-01-22 16:55:50.493809: step: 1756/530, loss: 0.0013562203384935856
2023-01-22 16:55:51.536625: step: 1760/530, loss: 0.0006840457790531218
2023-01-22 16:55:52.585255: step: 1764/530, loss: 1.9554627215256914e-05
2023-01-22 16:55:53.629822: step: 1768/530, loss: 0.0064858742989599705
2023-01-22 16:55:54.671910: step: 1772/530, loss: 0.0017773398431017995
2023-01-22 16:55:55.694752: step: 1776/530, loss: 0.010962901636958122
2023-01-22 16:55:56.734654: step: 1780/530, loss: 0.0016993449535220861
2023-01-22 16:55:57.776216: step: 1784/530, loss: 0.000713059795089066
2023-01-22 16:55:58.830610: step: 1788/530, loss: 0.001429026946425438
2023-01-22 16:55:59.864816: step: 1792/530, loss: 0.0017729275859892368
2023-01-22 16:56:00.924101: step: 1796/530, loss: 0.006913549266755581
2023-01-22 16:56:01.972461: step: 1800/530, loss: 0.028466973453760147
2023-01-22 16:56:03.004537: step: 1804/530, loss: 0.005895878188312054
2023-01-22 16:56:04.049092: step: 1808/530, loss: 0.0002944791631307453
2023-01-22 16:56:05.101870: step: 1812/530, loss: 0.0014753293944522738
2023-01-22 16:56:06.138105: step: 1816/530, loss: 4.284674650989473e-05
2023-01-22 16:56:07.172904: step: 1820/530, loss: 0.004026878625154495
2023-01-22 16:56:08.203147: step: 1824/530, loss: 0.0038042047526687384
2023-01-22 16:56:09.233014: step: 1828/530, loss: 0.000867285649292171
2023-01-22 16:56:10.289212: step: 1832/530, loss: 0.004134317394345999
2023-01-22 16:56:11.333874: step: 1836/530, loss: 0.002293369034305215
2023-01-22 16:56:12.387441: step: 1840/530, loss: 0.006302934139966965
2023-01-22 16:56:13.418454: step: 1844/530, loss: 0.0001471473806304857
2023-01-22 16:56:14.466264: step: 1848/530, loss: 0.008634034544229507
2023-01-22 16:56:15.512162: step: 1852/530, loss: 0.0008669691160321236
2023-01-22 16:56:16.564561: step: 1856/530, loss: 0.0010020699119195342
2023-01-22 16:56:17.625529: step: 1860/530, loss: 0.0005832889582961798
2023-01-22 16:56:18.669296: step: 1864/530, loss: 0.010718967765569687
2023-01-22 16:56:19.717608: step: 1868/530, loss: 0.000633514893706888
2023-01-22 16:56:20.756485: step: 1872/530, loss: 0.0030884321313351393
2023-01-22 16:56:21.808940: step: 1876/530, loss: 0.004053754266351461
2023-01-22 16:56:22.852227: step: 1880/530, loss: 0.004757086746394634
2023-01-22 16:56:23.896700: step: 1884/530, loss: 0.012511016800999641
2023-01-22 16:56:24.920198: step: 1888/530, loss: 2.1465699319378473e-05
2023-01-22 16:56:25.946989: step: 1892/530, loss: 0.0010633196216076612
2023-01-22 16:56:27.004327: step: 1896/530, loss: 0.010909922420978546
2023-01-22 16:56:28.047272: step: 1900/530, loss: 0.0042119137942790985
2023-01-22 16:56:29.086660: step: 1904/530, loss: 0.0013723624870181084
2023-01-22 16:56:30.140821: step: 1908/530, loss: 5.691273327101953e-05
2023-01-22 16:56:31.177721: step: 1912/530, loss: 0.003312408924102783
2023-01-22 16:56:32.246245: step: 1916/530, loss: 0.0020297765731811523
2023-01-22 16:56:33.301255: step: 1920/530, loss: 0.018630992621183395
2023-01-22 16:56:34.346432: step: 1924/530, loss: 0.002299703424796462
2023-01-22 16:56:35.372322: step: 1928/530, loss: 0.01734558679163456
2023-01-22 16:56:36.417742: step: 1932/530, loss: 0.008692233823239803
2023-01-22 16:56:37.442973: step: 1936/530, loss: 0.009354210458695889
2023-01-22 16:56:38.481840: step: 1940/530, loss: 0.0015004929155111313
2023-01-22 16:56:39.527389: step: 1944/530, loss: 0.003547100583091378
2023-01-22 16:56:40.560783: step: 1948/530, loss: 0.0008395725744776428
2023-01-22 16:56:41.597482: step: 1952/530, loss: 0.007419206667691469
2023-01-22 16:56:42.640778: step: 1956/530, loss: 0.0030893306247889996
2023-01-22 16:56:43.697548: step: 1960/530, loss: 1.90397822734667e-05
2023-01-22 16:56:44.733699: step: 1964/530, loss: 0.0006726476131007075
2023-01-22 16:56:45.782778: step: 1968/530, loss: 0.002564217895269394
2023-01-22 16:56:46.818006: step: 1972/530, loss: 0.004953647032380104
2023-01-22 16:56:47.865739: step: 1976/530, loss: 0.00026036237250082195
2023-01-22 16:56:48.902692: step: 1980/530, loss: 0.003146646311506629
2023-01-22 16:56:49.967556: step: 1984/530, loss: 0.026527967303991318
2023-01-22 16:56:51.004359: step: 1988/530, loss: 0.003269575070589781
2023-01-22 16:56:52.064473: step: 1992/530, loss: 0.0112005565315485
2023-01-22 16:56:53.117959: step: 1996/530, loss: 0.0024370155297219753
2023-01-22 16:56:54.149419: step: 2000/530, loss: 0.0017816127510741353
2023-01-22 16:56:55.206866: step: 2004/530, loss: 0.0002463326964061707
2023-01-22 16:56:56.254777: step: 2008/530, loss: 0.025541674345731735
2023-01-22 16:56:57.290847: step: 2012/530, loss: 0.007038659881800413
2023-01-22 16:56:58.338560: step: 2016/530, loss: 0.0030720599461346865
2023-01-22 16:56:59.378698: step: 2020/530, loss: 0.01581084169447422
2023-01-22 16:57:00.420524: step: 2024/530, loss: 0.0034938957542181015
2023-01-22 16:57:01.471638: step: 2028/530, loss: 0.0050782994367182255
2023-01-22 16:57:02.529151: step: 2032/530, loss: 0.00661267526447773
2023-01-22 16:57:03.627727: step: 2036/530, loss: 0.0016580792143940926
2023-01-22 16:57:04.691071: step: 2040/530, loss: 0.0030666871462017298
2023-01-22 16:57:05.725950: step: 2044/530, loss: 0.00020061011309735477
2023-01-22 16:57:06.776003: step: 2048/530, loss: 0.0020251853857189417
2023-01-22 16:57:07.819514: step: 2052/530, loss: 0.0023325940128415823
2023-01-22 16:57:08.879979: step: 2056/530, loss: 0.004989034961909056
2023-01-22 16:57:09.917020: step: 2060/530, loss: 0.00042098373523913324
2023-01-22 16:57:10.947908: step: 2064/530, loss: 0.0002676958392839879
2023-01-22 16:57:11.997809: step: 2068/530, loss: 0.005194572266191244
2023-01-22 16:57:13.036533: step: 2072/530, loss: 0.011506150476634502
2023-01-22 16:57:14.066103: step: 2076/530, loss: 0.0025587156414985657
2023-01-22 16:57:15.121632: step: 2080/530, loss: 0.009145993739366531
2023-01-22 16:57:16.184119: step: 2084/530, loss: 0.008899924345314503
2023-01-22 16:57:17.230926: step: 2088/530, loss: 0.0058839889243245125
2023-01-22 16:57:18.284748: step: 2092/530, loss: 0.0015116475988179445
2023-01-22 16:57:19.335747: step: 2096/530, loss: 0.007068545091897249
2023-01-22 16:57:20.387452: step: 2100/530, loss: 0.004713758826255798
2023-01-22 16:57:21.442668: step: 2104/530, loss: 0.017527861520648003
2023-01-22 16:57:22.498505: step: 2108/530, loss: 0.006133155431598425
2023-01-22 16:57:23.568879: step: 2112/530, loss: 0.006350258830934763
2023-01-22 16:57:24.609555: step: 2116/530, loss: 0.0026042740792036057
2023-01-22 16:57:25.650577: step: 2120/530, loss: 0.00734981382265687
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34191831683168317, 'r': 0.32764468690702087, 'f1': 0.33462936046511627}, 'combined': 0.24656900244798038, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35899020582442065, 'r': 0.4078234323520073, 'f1': 0.38185188846728396}, 'combined': 0.2959808896253589, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31059669472445667, 'r': 0.3235627806522329, 'f1': 0.3169471847652913}, 'combined': 0.23354003087968833, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35917754687009174, 'r': 0.4119977743509876, 'f1': 0.383778748710509}, 'combined': 0.2974744367995333, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32380731879974156, 'r': 0.33609602160049074, 'f1': 0.3298372502485263}, 'combined': 0.24303797386733514, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35818805451454333, 'r': 0.387488364120972, 'f1': 0.37226255202085434}, 'combined': 0.2885480068295618, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3434636454183267, 'r': 0.3271703036053131, 'f1': 0.33511904761904765}, 'combined': 0.24692982456140353, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36157621298618825, 'r': 0.4094318882343602, 'f1': 0.3840188744818827}, 'combined': 0.29766056299552635, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:59:53.440742: step: 4/530, loss: 0.006728241220116615
2023-01-22 16:59:54.492680: step: 8/530, loss: 0.01092079933732748
2023-01-22 16:59:55.547398: step: 12/530, loss: 0.003687224816530943
2023-01-22 16:59:56.572955: step: 16/530, loss: 0.0019325496396049857
2023-01-22 16:59:57.619691: step: 20/530, loss: 0.0032276909332722425
2023-01-22 16:59:58.640936: step: 24/530, loss: 0.0020119063556194305
2023-01-22 16:59:59.685957: step: 28/530, loss: 0.003910745959728956
2023-01-22 17:00:00.724285: step: 32/530, loss: 0.007735200226306915
2023-01-22 17:00:01.761043: step: 36/530, loss: 0.0019700652919709682
2023-01-22 17:00:02.795112: step: 40/530, loss: 0.007898872718214989
2023-01-22 17:00:03.836942: step: 44/530, loss: 0.0018007050966843963
2023-01-22 17:00:04.872367: step: 48/530, loss: 0.06393536180257797
2023-01-22 17:00:05.909905: step: 52/530, loss: 0.003908275160938501
2023-01-22 17:00:06.941506: step: 56/530, loss: 0.0007549480069428682
2023-01-22 17:00:07.996697: step: 60/530, loss: 0.005105209536850452
2023-01-22 17:00:09.044047: step: 64/530, loss: 0.0015098523581400514
2023-01-22 17:00:10.082913: step: 68/530, loss: 1.981997411348857e-05
2023-01-22 17:00:11.131235: step: 72/530, loss: 0.0007663294090889394
2023-01-22 17:00:12.177861: step: 76/530, loss: 0.0018295961199328303
2023-01-22 17:00:13.221558: step: 80/530, loss: 0.003032487351447344
2023-01-22 17:00:14.257268: step: 84/530, loss: 0.005615803878754377
2023-01-22 17:00:15.318686: step: 88/530, loss: 0.000449291430413723
2023-01-22 17:00:16.361216: step: 92/530, loss: 0.002229244913905859
2023-01-22 17:00:17.394942: step: 96/530, loss: 0.0018482328159734607
2023-01-22 17:00:18.437594: step: 100/530, loss: 0.007176647428423166
2023-01-22 17:00:19.472106: step: 104/530, loss: 0.0023082057014107704
2023-01-22 17:00:20.537981: step: 108/530, loss: 0.005674582906067371
2023-01-22 17:00:21.574843: step: 112/530, loss: 0.003943182993680239
2023-01-22 17:00:22.619247: step: 116/530, loss: 0.005425735376775265
2023-01-22 17:00:23.667333: step: 120/530, loss: 0.001288491184823215
2023-01-22 17:00:24.721581: step: 124/530, loss: 0.0022611620370298624
2023-01-22 17:00:25.762309: step: 128/530, loss: 0.000500692636705935
2023-01-22 17:00:26.825358: step: 132/530, loss: 9.355145448353142e-05
2023-01-22 17:00:27.860290: step: 136/530, loss: 0.009377521462738514
2023-01-22 17:00:28.920665: step: 140/530, loss: 0.0005079037509858608
2023-01-22 17:00:29.962434: step: 144/530, loss: 0.0032796585001051426
2023-01-22 17:00:31.002394: step: 148/530, loss: 0.00315141212195158
2023-01-22 17:00:32.063824: step: 152/530, loss: 0.0002355034666834399
2023-01-22 17:00:33.107082: step: 156/530, loss: 0.006104033440351486
2023-01-22 17:00:34.156039: step: 160/530, loss: 0.005844739731401205
2023-01-22 17:00:35.210144: step: 164/530, loss: 0.003568240674212575
2023-01-22 17:00:36.234222: step: 168/530, loss: 0.0025225516874343157
2023-01-22 17:00:37.285918: step: 172/530, loss: 0.00638723885640502
2023-01-22 17:00:38.323573: step: 176/530, loss: 0.0003313054039608687
2023-01-22 17:00:39.353166: step: 180/530, loss: 0.0011914032511413097
2023-01-22 17:00:40.383287: step: 184/530, loss: 0.0013044987572357059
2023-01-22 17:00:41.417998: step: 188/530, loss: 9.945756755769253e-05
2023-01-22 17:00:42.456497: step: 192/530, loss: 6.864780516480096e-06
2023-01-22 17:00:43.493391: step: 196/530, loss: 0.002715484704822302
2023-01-22 17:00:44.531713: step: 200/530, loss: 0.0010256976820528507
2023-01-22 17:00:45.583129: step: 204/530, loss: 2.1096932414366165e-06
2023-01-22 17:00:46.618158: step: 208/530, loss: 0.008246565237641335
2023-01-22 17:00:47.668762: step: 212/530, loss: 0.012566031888127327
2023-01-22 17:00:48.716270: step: 216/530, loss: 0.0030449607875198126
2023-01-22 17:00:49.766616: step: 220/530, loss: 0.0015749752055853605
2023-01-22 17:00:50.799502: step: 224/530, loss: 0.0020285595674067736
2023-01-22 17:00:51.841296: step: 228/530, loss: 0.0001254546077689156
2023-01-22 17:00:52.914571: step: 232/530, loss: 0.005158832296729088
2023-01-22 17:00:53.958583: step: 236/530, loss: 0.00013074540765956044
2023-01-22 17:00:55.006311: step: 240/530, loss: 0.0013885352527722716
2023-01-22 17:00:56.049730: step: 244/530, loss: 0.003860518801957369
2023-01-22 17:00:57.105729: step: 248/530, loss: 0.010055194608867168
2023-01-22 17:00:58.141767: step: 252/530, loss: 0.0008981186547316611
2023-01-22 17:00:59.189639: step: 256/530, loss: 0.002441010670736432
2023-01-22 17:01:00.235360: step: 260/530, loss: 0.015143767930567265
2023-01-22 17:01:01.299840: step: 264/530, loss: 0.0032985215075314045
2023-01-22 17:01:02.352842: step: 268/530, loss: 0.02295239083468914
2023-01-22 17:01:03.395169: step: 272/530, loss: 0.00016630797472316772
2023-01-22 17:01:04.446323: step: 276/530, loss: 0.0017587675247341394
2023-01-22 17:01:05.497587: step: 280/530, loss: 0.002919380320236087
2023-01-22 17:01:06.556054: step: 284/530, loss: 0.005225224420428276
2023-01-22 17:01:07.594311: step: 288/530, loss: 0.00294761685654521
2023-01-22 17:01:08.637843: step: 292/530, loss: 0.004382021725177765
2023-01-22 17:01:09.685802: step: 296/530, loss: 0.00557662034407258
2023-01-22 17:01:10.730856: step: 300/530, loss: 0.004200521856546402
2023-01-22 17:01:11.782623: step: 304/530, loss: 0.005391261074692011
2023-01-22 17:01:12.836328: step: 308/530, loss: 0.0035750262904912233
2023-01-22 17:01:13.869129: step: 312/530, loss: 0.012020302005112171
2023-01-22 17:01:14.904693: step: 316/530, loss: 0.0011893701739609241
2023-01-22 17:01:15.946733: step: 320/530, loss: 0.004335054196417332
2023-01-22 17:01:17.011219: step: 324/530, loss: 0.004338924307376146
2023-01-22 17:01:18.043322: step: 328/530, loss: 0.0004685973981395364
2023-01-22 17:01:19.086534: step: 332/530, loss: 0.0003985729708801955
2023-01-22 17:01:20.135877: step: 336/530, loss: 0.0013948632404208183
2023-01-22 17:01:21.174973: step: 340/530, loss: 0.006275718100368977
2023-01-22 17:01:22.223228: step: 344/530, loss: 0.001678474247455597
2023-01-22 17:01:23.278736: step: 348/530, loss: 0.013294276781380177
2023-01-22 17:01:24.336924: step: 352/530, loss: 0.0016472446732223034
2023-01-22 17:01:25.371171: step: 356/530, loss: 0.00019753299420699477
2023-01-22 17:01:26.413624: step: 360/530, loss: 0.00040297757368534803
2023-01-22 17:01:27.462703: step: 364/530, loss: 0.002236692002043128
2023-01-22 17:01:28.506310: step: 368/530, loss: 1.7517317246529274e-05
2023-01-22 17:01:29.552686: step: 372/530, loss: 0.0028147606644779444
2023-01-22 17:01:30.589967: step: 376/530, loss: 0.00019868843082804233
2023-01-22 17:01:31.662252: step: 380/530, loss: 0.0013912011636421084
2023-01-22 17:01:32.709559: step: 384/530, loss: 0.0004567632277030498
2023-01-22 17:01:33.753163: step: 388/530, loss: 0.0024846189189702272
2023-01-22 17:01:34.795853: step: 392/530, loss: 0.0014706613728776574
2023-01-22 17:01:35.832384: step: 396/530, loss: 0.0025192908942699432
2023-01-22 17:01:36.854643: step: 400/530, loss: 1.0619334716466255e-05
2023-01-22 17:01:37.889943: step: 404/530, loss: 0.005221816711127758
2023-01-22 17:01:38.932750: step: 408/530, loss: 0.0032732728868722916
2023-01-22 17:01:39.978732: step: 412/530, loss: 0.0005614410038106143
2023-01-22 17:01:41.045784: step: 416/530, loss: 0.0005032513290643692
2023-01-22 17:01:42.101081: step: 420/530, loss: 0.00025666714645922184
2023-01-22 17:01:43.135883: step: 424/530, loss: 1.5104700651136227e-05
2023-01-22 17:01:44.193659: step: 428/530, loss: 0.004815563093870878
2023-01-22 17:01:45.233953: step: 432/530, loss: 0.007909965701401234
2023-01-22 17:01:46.285259: step: 436/530, loss: 0.008411350660026073
2023-01-22 17:01:47.332421: step: 440/530, loss: 0.006662989035248756
2023-01-22 17:01:48.402343: step: 444/530, loss: 0.0008969720802269876
2023-01-22 17:01:49.481746: step: 448/530, loss: 0.0075895884074270725
2023-01-22 17:01:50.524295: step: 452/530, loss: 0.00031008778023533523
2023-01-22 17:01:51.574231: step: 456/530, loss: 0.0025365797337144613
2023-01-22 17:01:52.629215: step: 460/530, loss: 0.0006420926656574011
2023-01-22 17:01:53.674958: step: 464/530, loss: 0.00015697900380473584
2023-01-22 17:01:54.708980: step: 468/530, loss: 0.0003105918294750154
2023-01-22 17:01:55.757724: step: 472/530, loss: 0.003746391274034977
2023-01-22 17:01:56.803531: step: 476/530, loss: 0.0019301745342090726
2023-01-22 17:01:57.851308: step: 480/530, loss: 0.001170346513390541
2023-01-22 17:01:58.900438: step: 484/530, loss: 0.0064259907230734825
2023-01-22 17:01:59.948436: step: 488/530, loss: 0.010905269533395767
2023-01-22 17:02:00.996490: step: 492/530, loss: 0.002635349752381444
2023-01-22 17:02:02.034414: step: 496/530, loss: 0.0010565104894340038
2023-01-22 17:02:03.094181: step: 500/530, loss: 0.0025665778666734695
2023-01-22 17:02:04.152909: step: 504/530, loss: 0.0015071381349116564
2023-01-22 17:02:05.202838: step: 508/530, loss: 0.004104041960090399
2023-01-22 17:02:06.270053: step: 512/530, loss: 0.0004766838683281094
2023-01-22 17:02:07.312990: step: 516/530, loss: 0.01006765104830265
2023-01-22 17:02:08.361709: step: 520/530, loss: 0.01131446287035942
2023-01-22 17:02:09.436898: step: 524/530, loss: 0.002806006232276559
2023-01-22 17:02:10.477802: step: 528/530, loss: 0.004344320390373468
2023-01-22 17:02:11.525749: step: 532/530, loss: 0.004885183647274971
2023-01-22 17:02:12.569522: step: 536/530, loss: 0.0044850255362689495
2023-01-22 17:02:13.624009: step: 540/530, loss: 0.0004967250279150903
2023-01-22 17:02:14.676929: step: 544/530, loss: 0.003474026918411255
2023-01-22 17:02:15.728470: step: 548/530, loss: 0.008976250886917114
2023-01-22 17:02:16.782847: step: 552/530, loss: 0.00419862475246191
2023-01-22 17:02:17.832297: step: 556/530, loss: 0.002195636974647641
2023-01-22 17:02:18.874466: step: 560/530, loss: 0.0006492839311249554
2023-01-22 17:02:19.912919: step: 564/530, loss: 0.0010503239464014769
2023-01-22 17:02:20.939582: step: 568/530, loss: 0.0020240566227585077
2023-01-22 17:02:22.004015: step: 572/530, loss: 0.0011131631908938289
2023-01-22 17:02:23.048522: step: 576/530, loss: 0.0005042792181484401
2023-01-22 17:02:24.076751: step: 580/530, loss: 0.0003557713935151696
2023-01-22 17:02:25.132654: step: 584/530, loss: 0.002478155307471752
2023-01-22 17:02:26.170847: step: 588/530, loss: 0.0017400953220203519
2023-01-22 17:02:27.209979: step: 592/530, loss: 0.004249389749020338
2023-01-22 17:02:28.257171: step: 596/530, loss: 0.000572758901398629
2023-01-22 17:02:29.306495: step: 600/530, loss: 0.0101140346378088
2023-01-22 17:02:30.373634: step: 604/530, loss: 0.01079687848687172
2023-01-22 17:02:31.410448: step: 608/530, loss: 7.842260674806312e-05
2023-01-22 17:02:32.456243: step: 612/530, loss: 0.006186159327626228
2023-01-22 17:02:33.501473: step: 616/530, loss: 0.0027700604405254126
2023-01-22 17:02:34.554537: step: 620/530, loss: 0.003830282250419259
2023-01-22 17:02:35.642352: step: 624/530, loss: 0.00231066788546741
2023-01-22 17:02:36.690596: step: 628/530, loss: 0.001095293671824038
2023-01-22 17:02:37.734397: step: 632/530, loss: 0.0016686319140717387
2023-01-22 17:02:38.791713: step: 636/530, loss: 0.004468643572181463
2023-01-22 17:02:39.845114: step: 640/530, loss: 0.00012007312761852518
2023-01-22 17:02:40.899640: step: 644/530, loss: 0.0038229916244745255
2023-01-22 17:02:41.969828: step: 648/530, loss: 0.004569799639284611
2023-01-22 17:02:43.014362: step: 652/530, loss: 0.02937786653637886
2023-01-22 17:02:44.056967: step: 656/530, loss: 0.0012135922443121672
2023-01-22 17:02:45.110601: step: 660/530, loss: 0.01783234067261219
2023-01-22 17:02:46.159798: step: 664/530, loss: 0.001534773618914187
2023-01-22 17:02:47.211607: step: 668/530, loss: 4.680583151639439e-05
2023-01-22 17:02:48.251838: step: 672/530, loss: 0.0006945506320334971
2023-01-22 17:02:49.291338: step: 676/530, loss: 0.001785916625522077
2023-01-22 17:02:50.345849: step: 680/530, loss: 0.0009097285801544785
2023-01-22 17:02:51.401930: step: 684/530, loss: 0.013617118820548058
2023-01-22 17:02:52.444123: step: 688/530, loss: 0.0075601497665047646
2023-01-22 17:02:53.495679: step: 692/530, loss: 0.0013596635544672608
2023-01-22 17:02:54.521825: step: 696/530, loss: 0.00110805022995919
2023-01-22 17:02:55.570547: step: 700/530, loss: 0.00022816112323198467
2023-01-22 17:02:56.609783: step: 704/530, loss: 0.00010371807729825377
2023-01-22 17:02:57.646232: step: 708/530, loss: 0.0001237311662407592
2023-01-22 17:02:58.687312: step: 712/530, loss: 0.00999809056520462
2023-01-22 17:02:59.721299: step: 716/530, loss: 0.0037813351955264807
2023-01-22 17:03:00.763201: step: 720/530, loss: 0.0007650508196093142
2023-01-22 17:03:01.839375: step: 724/530, loss: 0.0012556056026369333
2023-01-22 17:03:02.875122: step: 728/530, loss: 0.0018612620187923312
2023-01-22 17:03:03.923349: step: 732/530, loss: 0.0004626192676369101
2023-01-22 17:03:04.953464: step: 736/530, loss: 0.004837325308471918
2023-01-22 17:03:05.996410: step: 740/530, loss: 0.0045120855793356895
2023-01-22 17:03:07.043763: step: 744/530, loss: 0.0004809291276615113
2023-01-22 17:03:08.076041: step: 748/530, loss: 5.323910227161832e-05
2023-01-22 17:03:09.133694: step: 752/530, loss: 0.0017554813530296087
2023-01-22 17:03:10.181076: step: 756/530, loss: 0.0012749754823744297
2023-01-22 17:03:11.225682: step: 760/530, loss: 0.0012977682054042816
2023-01-22 17:03:12.282160: step: 764/530, loss: 3.463034227024764e-05
2023-01-22 17:03:13.329646: step: 768/530, loss: 0.0042152502574026585
2023-01-22 17:03:14.357695: step: 772/530, loss: 0.0019875760190188885
2023-01-22 17:03:15.388844: step: 776/530, loss: 0.002290158299729228
2023-01-22 17:03:16.422445: step: 780/530, loss: 0.00346802338026464
2023-01-22 17:03:17.463562: step: 784/530, loss: 0.0013296926626935601
2023-01-22 17:03:18.517437: step: 788/530, loss: 0.0002059193648165092
2023-01-22 17:03:19.554275: step: 792/530, loss: 0.0
2023-01-22 17:03:20.594189: step: 796/530, loss: 0.0033771954476833344
2023-01-22 17:03:21.649963: step: 800/530, loss: 0.002392198657616973
2023-01-22 17:03:22.701147: step: 804/530, loss: 0.0033652542624622583
2023-01-22 17:03:23.778186: step: 808/530, loss: 0.005677748937159777
2023-01-22 17:03:24.835913: step: 812/530, loss: 0.0010957029880955815
2023-01-22 17:03:25.870921: step: 816/530, loss: 0.001103114802390337
2023-01-22 17:03:26.925710: step: 820/530, loss: 0.00021666464454028755
2023-01-22 17:03:27.965766: step: 824/530, loss: 0.009038028307259083
2023-01-22 17:03:29.008815: step: 828/530, loss: 0.0003519484307616949
2023-01-22 17:03:30.073988: step: 832/530, loss: 0.001531408284790814
2023-01-22 17:03:31.122955: step: 836/530, loss: 0.002708738436922431
2023-01-22 17:03:32.172795: step: 840/530, loss: 0.0017759923357516527
2023-01-22 17:03:33.232813: step: 844/530, loss: 0.0012091611279174685
2023-01-22 17:03:34.264721: step: 848/530, loss: 0.00458544073626399
2023-01-22 17:03:35.294246: step: 852/530, loss: 0.0015374617651104927
2023-01-22 17:03:36.348054: step: 856/530, loss: 0.0013794736005365849
2023-01-22 17:03:37.388782: step: 860/530, loss: 0.009434523992240429
2023-01-22 17:03:38.429985: step: 864/530, loss: 0.002033942611888051
2023-01-22 17:03:39.464577: step: 868/530, loss: 0.0017239798326045275
2023-01-22 17:03:40.501721: step: 872/530, loss: 0.0002994116803165525
2023-01-22 17:03:41.542638: step: 876/530, loss: 0.0005237242439761758
2023-01-22 17:03:42.593957: step: 880/530, loss: 0.00527963088825345
2023-01-22 17:03:43.650216: step: 884/530, loss: 0.006941282190382481
2023-01-22 17:03:44.708345: step: 888/530, loss: 0.0008123686420731246
2023-01-22 17:03:45.757914: step: 892/530, loss: 7.46598161640577e-05
2023-01-22 17:03:46.804927: step: 896/530, loss: 0.0006259792717173696
2023-01-22 17:03:47.842970: step: 900/530, loss: 6.782382115488872e-05
2023-01-22 17:03:48.901333: step: 904/530, loss: 0.0014336572494357824
2023-01-22 17:03:49.933019: step: 908/530, loss: 0.006972672417759895
2023-01-22 17:03:50.977765: step: 912/530, loss: 0.004512323532253504
2023-01-22 17:03:52.036066: step: 916/530, loss: 1.4524814105243422e-05
2023-01-22 17:03:53.090281: step: 920/530, loss: 0.0013026637025177479
2023-01-22 17:03:54.138160: step: 924/530, loss: 0.0010842892806977034
2023-01-22 17:03:55.177314: step: 928/530, loss: 0.0010095477337017655
2023-01-22 17:03:56.247370: step: 932/530, loss: 0.006881438195705414
2023-01-22 17:03:57.308921: step: 936/530, loss: 0.0007780453306622803
2023-01-22 17:03:58.359279: step: 940/530, loss: 0.002386632142588496
2023-01-22 17:03:59.393090: step: 944/530, loss: 0.004146643448621035
2023-01-22 17:04:00.426073: step: 948/530, loss: 0.020527713000774384
2023-01-22 17:04:01.493308: step: 952/530, loss: 0.004596620332449675
2023-01-22 17:04:02.551821: step: 956/530, loss: 0.0013360029552131891
2023-01-22 17:04:03.620472: step: 960/530, loss: 0.003200882114470005
2023-01-22 17:04:04.674941: step: 964/530, loss: 0.004382890649139881
2023-01-22 17:04:05.720855: step: 968/530, loss: 0.004832218401134014
2023-01-22 17:04:06.754398: step: 972/530, loss: 9.911083907354623e-06
2023-01-22 17:04:07.790968: step: 976/530, loss: 0.0022042514756321907
2023-01-22 17:04:08.826610: step: 980/530, loss: 0.0018994336714968085
2023-01-22 17:04:09.864209: step: 984/530, loss: 0.004117816686630249
2023-01-22 17:04:10.909502: step: 988/530, loss: 0.011310254223644733
2023-01-22 17:04:11.971653: step: 992/530, loss: 0.006619452033191919
2023-01-22 17:04:13.030700: step: 996/530, loss: 0.0003443750028964132
2023-01-22 17:04:14.080699: step: 1000/530, loss: 0.003024142701178789
2023-01-22 17:04:15.137401: step: 1004/530, loss: 0.0006079613231122494
2023-01-22 17:04:16.173926: step: 1008/530, loss: 0.004931787960231304
2023-01-22 17:04:17.221230: step: 1012/530, loss: 0.00228464649990201
2023-01-22 17:04:18.254175: step: 1016/530, loss: 1.127155246649636e-05
2023-01-22 17:04:19.312214: step: 1020/530, loss: 0.007504436653107405
2023-01-22 17:04:20.354178: step: 1024/530, loss: 0.002850524615496397
2023-01-22 17:04:21.396845: step: 1028/530, loss: 0.003923813346773386
2023-01-22 17:04:22.460417: step: 1032/530, loss: 0.0017447317950427532
2023-01-22 17:04:23.507320: step: 1036/530, loss: 0.008256851695477962
2023-01-22 17:04:24.552750: step: 1040/530, loss: 0.00262592569924891
2023-01-22 17:04:25.610381: step: 1044/530, loss: 0.006396498531103134
2023-01-22 17:04:26.643106: step: 1048/530, loss: 7.4719591793837026e-06
2023-01-22 17:04:27.695580: step: 1052/530, loss: 0.007519092410802841
2023-01-22 17:04:28.737904: step: 1056/530, loss: 0.0030573117546737194
2023-01-22 17:04:29.798610: step: 1060/530, loss: 0.008097074925899506
2023-01-22 17:04:30.837518: step: 1064/530, loss: 0.006410520989447832
2023-01-22 17:04:31.891640: step: 1068/530, loss: 0.001324211130850017
2023-01-22 17:04:32.947713: step: 1072/530, loss: 0.0017862874083220959
2023-01-22 17:04:33.981410: step: 1076/530, loss: 0.00012042235175613314
2023-01-22 17:04:35.019514: step: 1080/530, loss: 0.004782073199748993
2023-01-22 17:04:36.064729: step: 1084/530, loss: 0.006423020735383034
2023-01-22 17:04:37.120183: step: 1088/530, loss: 0.006951035000383854
2023-01-22 17:04:38.187727: step: 1092/530, loss: 0.005228972993791103
2023-01-22 17:04:39.245121: step: 1096/530, loss: 0.002004253910854459
2023-01-22 17:04:40.287577: step: 1100/530, loss: 0.0004658708057831973
2023-01-22 17:04:41.319376: step: 1104/530, loss: 0.0015666185645386577
2023-01-22 17:04:42.363034: step: 1108/530, loss: 0.000201524788280949
2023-01-22 17:04:43.398984: step: 1112/530, loss: 0.004110785201191902
2023-01-22 17:04:44.443713: step: 1116/530, loss: 0.000454398657893762
2023-01-22 17:04:45.494894: step: 1120/530, loss: 1.807861917768605e-05
2023-01-22 17:04:46.533485: step: 1124/530, loss: 0.0013572170864790678
2023-01-22 17:04:47.589367: step: 1128/530, loss: 0.015525279566645622
2023-01-22 17:04:48.630981: step: 1132/530, loss: 0.0018248233245685697
2023-01-22 17:04:49.665824: step: 1136/530, loss: 0.0031671100296080112
2023-01-22 17:04:50.712824: step: 1140/530, loss: 0.0015235089231282473
2023-01-22 17:04:51.757749: step: 1144/530, loss: 0.0015720115043222904
2023-01-22 17:04:52.810475: step: 1148/530, loss: 0.003198369173333049
2023-01-22 17:04:53.848264: step: 1152/530, loss: 0.0075254314579069614
2023-01-22 17:04:54.885567: step: 1156/530, loss: 0.0025483807548880577
2023-01-22 17:04:55.922270: step: 1160/530, loss: 0.0008820623625069857
2023-01-22 17:04:56.969656: step: 1164/530, loss: 0.003434132318943739
2023-01-22 17:04:58.001242: step: 1168/530, loss: 0.001195478136651218
2023-01-22 17:04:59.054413: step: 1172/530, loss: 0.0008998954435810447
2023-01-22 17:05:00.098800: step: 1176/530, loss: 0.015672490000724792
2023-01-22 17:05:01.133548: step: 1180/530, loss: 1.0297398148395587e-05
2023-01-22 17:05:02.179403: step: 1184/530, loss: 8.247247933468316e-07
2023-01-22 17:05:03.238919: step: 1188/530, loss: 0.005459130275994539
2023-01-22 17:05:04.275562: step: 1192/530, loss: 0.0014366828836500645
2023-01-22 17:05:05.326897: step: 1196/530, loss: 0.009928080253303051
2023-01-22 17:05:06.381957: step: 1200/530, loss: 0.007221674080938101
2023-01-22 17:05:07.440409: step: 1204/530, loss: 0.0009354190551675856
2023-01-22 17:05:08.495373: step: 1208/530, loss: 0.00037409987999126315
2023-01-22 17:05:09.544007: step: 1212/530, loss: 0.0004136855131946504
2023-01-22 17:05:10.597341: step: 1216/530, loss: 0.006305725779384375
2023-01-22 17:05:11.647511: step: 1220/530, loss: 0.01098248828202486
2023-01-22 17:05:12.688818: step: 1224/530, loss: 0.006228860933333635
2023-01-22 17:05:13.731042: step: 1228/530, loss: 0.0011418212670832872
2023-01-22 17:05:14.784794: step: 1232/530, loss: 0.009525150060653687
2023-01-22 17:05:15.828064: step: 1236/530, loss: 0.001546103972941637
2023-01-22 17:05:16.849286: step: 1240/530, loss: 0.0011437057983130217
2023-01-22 17:05:17.888697: step: 1244/530, loss: 0.00028179859509691596
2023-01-22 17:05:18.933105: step: 1248/530, loss: 0.008376537822186947
2023-01-22 17:05:19.962769: step: 1252/530, loss: 0.003715341677889228
2023-01-22 17:05:20.982437: step: 1256/530, loss: 0.0007436055457219481
2023-01-22 17:05:22.018640: step: 1260/530, loss: 0.0003102657210547477
2023-01-22 17:05:23.076119: step: 1264/530, loss: 0.004909284878522158
2023-01-22 17:05:24.107000: step: 1268/530, loss: 0.0020371167920529842
2023-01-22 17:05:25.145423: step: 1272/530, loss: 0.0004898647894151509
2023-01-22 17:05:26.188022: step: 1276/530, loss: 0.0015563125489279628
2023-01-22 17:05:27.226173: step: 1280/530, loss: 0.00689957058057189
2023-01-22 17:05:28.287342: step: 1284/530, loss: 0.01408822275698185
2023-01-22 17:05:29.328250: step: 1288/530, loss: 0.0013574474724009633
2023-01-22 17:05:30.375378: step: 1292/530, loss: 0.0009641749784350395
2023-01-22 17:05:31.404692: step: 1296/530, loss: 0.0003385709715075791
2023-01-22 17:05:32.443807: step: 1300/530, loss: 0.0004961580852977931
2023-01-22 17:05:33.468548: step: 1304/530, loss: 0.00020141866116318852
2023-01-22 17:05:34.526944: step: 1308/530, loss: 5.165263428352773e-05
2023-01-22 17:05:35.560362: step: 1312/530, loss: 0.006631826050579548
2023-01-22 17:05:36.602993: step: 1316/530, loss: 0.0006990053225308657
2023-01-22 17:05:37.639128: step: 1320/530, loss: 0.007975384593009949
2023-01-22 17:05:38.676582: step: 1324/530, loss: 0.0028748069889843464
2023-01-22 17:05:39.719110: step: 1328/530, loss: 0.006206345744431019
2023-01-22 17:05:40.760740: step: 1332/530, loss: 0.0004804233321920037
2023-01-22 17:05:41.800224: step: 1336/530, loss: 6.444739847211167e-05
2023-01-22 17:05:42.852363: step: 1340/530, loss: 0.0003802002756856382
2023-01-22 17:05:43.869223: step: 1344/530, loss: 0.0006370485061779618
2023-01-22 17:05:44.917990: step: 1348/530, loss: 0.00022640205861534923
2023-01-22 17:05:45.951676: step: 1352/530, loss: 0.0003381062124390155
2023-01-22 17:05:46.992282: step: 1356/530, loss: 0.004661472514271736
2023-01-22 17:05:48.039922: step: 1360/530, loss: 0.00735260546207428
2023-01-22 17:05:49.081839: step: 1364/530, loss: 0.0018966750940307975
2023-01-22 17:05:50.127699: step: 1368/530, loss: 0.006832683924585581
2023-01-22 17:05:51.171895: step: 1372/530, loss: 0.0013224206632003188
2023-01-22 17:05:52.214632: step: 1376/530, loss: 0.00016277357644867152
2023-01-22 17:05:53.262368: step: 1380/530, loss: 0.0006611610297113657
2023-01-22 17:05:54.319382: step: 1384/530, loss: 0.012600972317159176
2023-01-22 17:05:55.370175: step: 1388/530, loss: 0.0026991211343556643
2023-01-22 17:05:56.409214: step: 1392/530, loss: 0.022808486595749855
2023-01-22 17:05:57.457590: step: 1396/530, loss: 0.004014855716377497
2023-01-22 17:05:58.506809: step: 1400/530, loss: 0.005654542241245508
2023-01-22 17:05:59.540972: step: 1404/530, loss: 0.0016142316162586212
2023-01-22 17:06:00.591813: step: 1408/530, loss: 0.00030001590494066477
2023-01-22 17:06:01.628378: step: 1412/530, loss: 9.525947098154575e-05
2023-01-22 17:06:02.677945: step: 1416/530, loss: 0.0052554854191839695
2023-01-22 17:06:03.727220: step: 1420/530, loss: 0.0031585076358169317
2023-01-22 17:06:04.788763: step: 1424/530, loss: 0.00024226700770668685
2023-01-22 17:06:05.834493: step: 1428/530, loss: 0.0002838248328771442
2023-01-22 17:06:06.896498: step: 1432/530, loss: 0.0018992993282154202
2023-01-22 17:06:07.929997: step: 1436/530, loss: 0.00041687930934131145
2023-01-22 17:06:08.965943: step: 1440/530, loss: 0.0003345505683682859
2023-01-22 17:06:09.999616: step: 1444/530, loss: 0.0004599524545483291
2023-01-22 17:06:11.038255: step: 1448/530, loss: 0.00152059574611485
2023-01-22 17:06:12.086633: step: 1452/530, loss: 0.0010197223164141178
2023-01-22 17:06:13.114340: step: 1456/530, loss: 3.068601927225245e-06
2023-01-22 17:06:14.154043: step: 1460/530, loss: 0.00119457533583045
2023-01-22 17:06:15.190566: step: 1464/530, loss: 0.004676337353885174
2023-01-22 17:06:16.219221: step: 1468/530, loss: 0.0012967294314876199
2023-01-22 17:06:17.266192: step: 1472/530, loss: 0.00697213364765048
2023-01-22 17:06:18.293773: step: 1476/530, loss: 5.374971806304529e-05
2023-01-22 17:06:19.335091: step: 1480/530, loss: 0.0007884575170464814
2023-01-22 17:06:20.386917: step: 1484/530, loss: 0.0026752299163490534
2023-01-22 17:06:21.441653: step: 1488/530, loss: 0.007478209678083658
2023-01-22 17:06:22.475601: step: 1492/530, loss: 0.008206604979932308
2023-01-22 17:06:23.508323: step: 1496/530, loss: 7.746687333565205e-05
2023-01-22 17:06:24.550535: step: 1500/530, loss: 0.0017835705075412989
2023-01-22 17:06:25.588942: step: 1504/530, loss: 0.0011131709907203913
2023-01-22 17:06:26.640270: step: 1508/530, loss: 0.00066353939473629
2023-01-22 17:06:27.692809: step: 1512/530, loss: 0.0008853027247823775
2023-01-22 17:06:28.741498: step: 1516/530, loss: 0.015615081414580345
2023-01-22 17:06:29.789765: step: 1520/530, loss: 0.001807558466680348
2023-01-22 17:06:30.830340: step: 1524/530, loss: 0.0009274403564631939
2023-01-22 17:06:31.891447: step: 1528/530, loss: 0.011650248430669308
2023-01-22 17:06:32.943450: step: 1532/530, loss: 0.0053371889516711235
2023-01-22 17:06:33.983827: step: 1536/530, loss: 0.012244739569723606
2023-01-22 17:06:35.032684: step: 1540/530, loss: 0.022946396842598915
2023-01-22 17:06:36.063725: step: 1544/530, loss: 0.003774950047954917
2023-01-22 17:06:37.124424: step: 1548/530, loss: 0.008275489322841167
2023-01-22 17:06:38.163209: step: 1552/530, loss: 0.006017662584781647
2023-01-22 17:06:39.235772: step: 1556/530, loss: 0.004965306259691715
2023-01-22 17:06:40.272957: step: 1560/530, loss: 0.01910923235118389
2023-01-22 17:06:41.321940: step: 1564/530, loss: 0.0017008964205160737
2023-01-22 17:06:42.374490: step: 1568/530, loss: 0.002094108145684004
2023-01-22 17:06:43.414227: step: 1572/530, loss: 0.013499675318598747
2023-01-22 17:06:44.464523: step: 1576/530, loss: 0.0012263128301128745
2023-01-22 17:06:45.519740: step: 1580/530, loss: 0.004750311840325594
2023-01-22 17:06:46.581961: step: 1584/530, loss: 0.0055891671217978
2023-01-22 17:06:47.627723: step: 1588/530, loss: 0.0003754783538170159
2023-01-22 17:06:48.678815: step: 1592/530, loss: 0.0022290972992777824
2023-01-22 17:06:49.730796: step: 1596/530, loss: 0.004460914526134729
2023-01-22 17:06:50.766093: step: 1600/530, loss: 0.0022637643851339817
2023-01-22 17:06:51.820244: step: 1604/530, loss: 0.004388181492686272
2023-01-22 17:06:52.870598: step: 1608/530, loss: 0.0027250046841800213
2023-01-22 17:06:53.914639: step: 1612/530, loss: 0.00166132056619972
2023-01-22 17:06:54.959020: step: 1616/530, loss: 0.0002281893539475277
2023-01-22 17:06:56.005391: step: 1620/530, loss: 0.0041305809281766415
2023-01-22 17:06:57.043167: step: 1624/530, loss: 0.003262830898165703
2023-01-22 17:06:58.077356: step: 1628/530, loss: 0.0064003304578363895
2023-01-22 17:06:59.127212: step: 1632/530, loss: 0.0025947396643459797
2023-01-22 17:07:00.171217: step: 1636/530, loss: 0.0004289246862754226
2023-01-22 17:07:01.227468: step: 1640/530, loss: 0.0015038494020700455
2023-01-22 17:07:02.272719: step: 1644/530, loss: 0.0022568402346223593
2023-01-22 17:07:03.308539: step: 1648/530, loss: 0.00014186625776346773
2023-01-22 17:07:04.340717: step: 1652/530, loss: 0.0025793511886149645
2023-01-22 17:07:05.382820: step: 1656/530, loss: 0.001760231563821435
2023-01-22 17:07:06.427021: step: 1660/530, loss: 0.005591913126409054
2023-01-22 17:07:07.475351: step: 1664/530, loss: 0.001139389001764357
2023-01-22 17:07:08.522959: step: 1668/530, loss: 0.001222749357111752
2023-01-22 17:07:09.575589: step: 1672/530, loss: 0.003349478356540203
2023-01-22 17:07:10.626463: step: 1676/530, loss: 0.008537529967725277
2023-01-22 17:07:11.670993: step: 1680/530, loss: 0.0171780027449131
2023-01-22 17:07:12.706674: step: 1684/530, loss: 0.0007790369563736022
2023-01-22 17:07:13.739666: step: 1688/530, loss: 0.0025134822353720665
2023-01-22 17:07:14.785899: step: 1692/530, loss: 0.00345806498080492
2023-01-22 17:07:15.817517: step: 1696/530, loss: 0.0006331720505841076
2023-01-22 17:07:16.874343: step: 1700/530, loss: 0.007373058702796698
2023-01-22 17:07:17.923399: step: 1704/530, loss: 0.002492961473762989
2023-01-22 17:07:18.964425: step: 1708/530, loss: 0.0017996786627918482
2023-01-22 17:07:19.994786: step: 1712/530, loss: 0.006417486350983381
2023-01-22 17:07:21.021861: step: 1716/530, loss: 0.006842451170086861
2023-01-22 17:07:22.058882: step: 1720/530, loss: 0.004541672766208649
2023-01-22 17:07:23.101845: step: 1724/530, loss: 9.892897651297972e-05
2023-01-22 17:07:24.138851: step: 1728/530, loss: 0.004635293036699295
2023-01-22 17:07:25.188394: step: 1732/530, loss: 0.00627547362819314
2023-01-22 17:07:26.222622: step: 1736/530, loss: 0.0007424906943924725
2023-01-22 17:07:27.260962: step: 1740/530, loss: 0.0013969799038022757
2023-01-22 17:07:28.311407: step: 1744/530, loss: 0.0008021194371394813
2023-01-22 17:07:29.350663: step: 1748/530, loss: 5.0191716582048684e-05
2023-01-22 17:07:30.390323: step: 1752/530, loss: 0.00019830631208606064
2023-01-22 17:07:31.433016: step: 1756/530, loss: 0.0036961957812309265
2023-01-22 17:07:32.481226: step: 1760/530, loss: 0.0029901741072535515
2023-01-22 17:07:33.504862: step: 1764/530, loss: 0.0009864509338513017
2023-01-22 17:07:34.548862: step: 1768/530, loss: 0.014718879945576191
2023-01-22 17:07:35.614122: step: 1772/530, loss: 0.0014967393362894654
2023-01-22 17:07:36.659465: step: 1776/530, loss: 4.8162855819100514e-05
2023-01-22 17:07:37.696205: step: 1780/530, loss: 0.0028091403655707836
2023-01-22 17:07:38.757533: step: 1784/530, loss: 0.0034796022810041904
2023-01-22 17:07:39.821339: step: 1788/530, loss: 0.0015455796383321285
2023-01-22 17:07:40.854824: step: 1792/530, loss: 0.0013961036456748843
2023-01-22 17:07:41.899874: step: 1796/530, loss: 2.421425620013906e-07
2023-01-22 17:07:42.952093: step: 1800/530, loss: 0.004253959283232689
2023-01-22 17:07:44.004133: step: 1804/530, loss: 0.030879884958267212
2023-01-22 17:07:45.045223: step: 1808/530, loss: 0.0007402389892376959
2023-01-22 17:07:46.087747: step: 1812/530, loss: 0.005029305815696716
2023-01-22 17:07:47.147742: step: 1816/530, loss: 0.003805961227044463
2023-01-22 17:07:48.184673: step: 1820/530, loss: 0.0009683383977971971
2023-01-22 17:07:49.227271: step: 1824/530, loss: 0.00042147599742747843
2023-01-22 17:07:50.273715: step: 1828/530, loss: 0.005095311440527439
2023-01-22 17:07:51.332431: step: 1832/530, loss: 0.0033117649145424366
2023-01-22 17:07:52.380430: step: 1836/530, loss: 0.0026411789003759623
2023-01-22 17:07:53.431280: step: 1840/530, loss: 0.0006687751156277955
2023-01-22 17:07:54.493200: step: 1844/530, loss: 0.004634995013475418
2023-01-22 17:07:55.543388: step: 1848/530, loss: 0.005392204038798809
2023-01-22 17:07:56.597105: step: 1852/530, loss: 0.0026288365479558706
2023-01-22 17:07:57.649203: step: 1856/530, loss: 0.00632264232262969
2023-01-22 17:07:58.701741: step: 1860/530, loss: 0.0009048838983289897
2023-01-22 17:07:59.752010: step: 1864/530, loss: 0.0012034325627610087
2023-01-22 17:08:00.796907: step: 1868/530, loss: 0.003303315956145525
2023-01-22 17:08:01.831232: step: 1872/530, loss: 0.00016991447773762047
2023-01-22 17:08:02.864293: step: 1876/530, loss: 0.0015578686725348234
2023-01-22 17:08:03.899857: step: 1880/530, loss: 0.0011157433036714792
2023-01-22 17:08:04.947538: step: 1884/530, loss: 0.00041672654333524406
2023-01-22 17:08:05.979161: step: 1888/530, loss: 0.0023167794570326805
2023-01-22 17:08:07.032588: step: 1892/530, loss: 0.002052611205726862
2023-01-22 17:08:08.083793: step: 1896/530, loss: 0.0033763970714062452
2023-01-22 17:08:09.123706: step: 1900/530, loss: 0.00025242497213184834
2023-01-22 17:08:10.181093: step: 1904/530, loss: 0.009918239898979664
2023-01-22 17:08:11.231960: step: 1908/530, loss: 0.0038157969247549772
2023-01-22 17:08:12.265819: step: 1912/530, loss: 7.49468085814442e-07
2023-01-22 17:08:13.338196: step: 1916/530, loss: 0.004472915083169937
2023-01-22 17:08:14.385810: step: 1920/530, loss: 0.0039259870536625385
2023-01-22 17:08:15.438439: step: 1924/530, loss: 0.001096860971301794
2023-01-22 17:08:16.487534: step: 1928/530, loss: 0.0014287614030763507
2023-01-22 17:08:17.531453: step: 1932/530, loss: 0.01082514226436615
2023-01-22 17:08:18.570889: step: 1936/530, loss: 0.0008983967709355056
2023-01-22 17:08:19.612736: step: 1940/530, loss: 0.0008533830987289548
2023-01-22 17:08:20.656298: step: 1944/530, loss: 0.006071763578802347
2023-01-22 17:08:21.721405: step: 1948/530, loss: 0.0013380680466070771
2023-01-22 17:08:22.781617: step: 1952/530, loss: 0.002897057216614485
2023-01-22 17:08:23.819298: step: 1956/530, loss: 7.528057903982699e-05
2023-01-22 17:08:24.856736: step: 1960/530, loss: 0.0166124626994133
2023-01-22 17:08:25.894390: step: 1964/530, loss: 0.00010313720122212544
2023-01-22 17:08:26.932964: step: 1968/530, loss: 0.005741137079894543
2023-01-22 17:08:27.969424: step: 1972/530, loss: 0.004160319920629263
2023-01-22 17:08:29.011684: step: 1976/530, loss: 0.0030549473594874144
2023-01-22 17:08:30.063416: step: 1980/530, loss: 0.009821810759603977
2023-01-22 17:08:31.123101: step: 1984/530, loss: 0.005508612375706434
2023-01-22 17:08:32.175907: step: 1988/530, loss: 0.0002229307865491137
2023-01-22 17:08:33.230347: step: 1992/530, loss: 0.0031040431931614876
2023-01-22 17:08:34.271937: step: 1996/530, loss: 0.007389459293335676
2023-01-22 17:08:35.319951: step: 2000/530, loss: 0.0053385659120976925
2023-01-22 17:08:36.379881: step: 2004/530, loss: 0.016554879024624825
2023-01-22 17:08:37.421801: step: 2008/530, loss: 0.0011714758584275842
2023-01-22 17:08:38.452811: step: 2012/530, loss: 0.0011744378134608269
2023-01-22 17:08:39.509918: step: 2016/530, loss: 0.00011427033314248547
2023-01-22 17:08:40.565433: step: 2020/530, loss: 0.0008475541253574193
2023-01-22 17:08:41.615201: step: 2024/530, loss: 2.2833064576843753e-05
2023-01-22 17:08:42.645578: step: 2028/530, loss: 5.888010127819143e-05
2023-01-22 17:08:43.693015: step: 2032/530, loss: 0.0005154501413926482
2023-01-22 17:08:44.744357: step: 2036/530, loss: 0.00427416292950511
2023-01-22 17:08:45.784515: step: 2040/530, loss: 6.227390986168757e-05
2023-01-22 17:08:46.831350: step: 2044/530, loss: 0.0053716301918029785
2023-01-22 17:08:47.870203: step: 2048/530, loss: 0.0017645315965637565
2023-01-22 17:08:48.901564: step: 2052/530, loss: 0.004234227351844311
2023-01-22 17:08:49.930981: step: 2056/530, loss: 0.00022972305305302143
2023-01-22 17:08:50.958433: step: 2060/530, loss: 0.0005670490209013224
2023-01-22 17:08:51.996939: step: 2064/530, loss: 4.39680752606364e-06
2023-01-22 17:08:53.051130: step: 2068/530, loss: 0.0014795800670981407
2023-01-22 17:08:54.094036: step: 2072/530, loss: 3.195781755493954e-05
2023-01-22 17:08:55.121943: step: 2076/530, loss: 0.00021024089073762298
2023-01-22 17:08:56.152994: step: 2080/530, loss: 0.0034581993240863085
2023-01-22 17:08:57.200959: step: 2084/530, loss: 0.0009797518141567707
2023-01-22 17:08:58.230690: step: 2088/530, loss: 0.00436271820217371
2023-01-22 17:08:59.280313: step: 2092/530, loss: 0.0048765395767986774
2023-01-22 17:09:00.320302: step: 2096/530, loss: 2.4802049665595405e-05
2023-01-22 17:09:01.362585: step: 2100/530, loss: 0.0007195995422080159
2023-01-22 17:09:02.405765: step: 2104/530, loss: 0.0010806828504428267
2023-01-22 17:09:03.465961: step: 2108/530, loss: 0.024447450414299965
2023-01-22 17:09:04.498250: step: 2112/530, loss: 0.005292092449963093
2023-01-22 17:09:05.558161: step: 2116/530, loss: 0.003660043003037572
2023-01-22 17:09:06.598021: step: 2120/530, loss: 0.0012359905522316694
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3462223895582329, 'r': 0.3271703036053131, 'f1': 0.33642682926829265}, 'combined': 0.24789345314505773, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.360310988924254, 'r': 0.40667453529318376, 'f1': 0.3820914459404006}, 'combined': 0.2961665753222244, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31034546114866796, 'r': 0.3197677142385706, 'f1': 0.31498614094154526}, 'combined': 0.23209505122008597, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36068836975312457, 'r': 0.4110786567039288, 'f1': 0.3842384694964558}, 'combined': 0.2978307753991667, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33217790678353337, 'r': 0.34226300452269187, 'f1': 0.33714505305319364}, 'combined': 0.24842267067077425, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35957000869428357, 'r': 0.38633946706214845, 'f1': 0.37247438206789324}, 'combined': 0.28871220045453927, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 15}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3462223895582329, 'r': 0.3271703036053131, 'f1': 0.33642682926829265}, 'combined': 0.24789345314505773, 'stategy': 1, 'epoch': 15}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.360310988924254, 'r': 0.40667453529318376, 'f1': 0.3820914459404006}, 'combined': 0.2961665753222244, 'stategy': 1, 'epoch': 15}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 15}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:11:39.112387: step: 4/530, loss: 9.7860254754778e-05
2023-01-22 17:11:40.165768: step: 8/530, loss: 0.00016962077643256634
2023-01-22 17:11:41.210940: step: 12/530, loss: 0.00167995342053473
2023-01-22 17:11:42.247244: step: 16/530, loss: 0.0009895809926092625
2023-01-22 17:11:43.282402: step: 20/530, loss: 0.0008334103040397167
2023-01-22 17:11:44.334123: step: 24/530, loss: 0.0017199110006913543
2023-01-22 17:11:45.370196: step: 28/530, loss: 0.0062159881927073
2023-01-22 17:11:46.448763: step: 32/530, loss: 0.06644850969314575
2023-01-22 17:11:47.484231: step: 36/530, loss: 0.0005407019634731114
2023-01-22 17:11:48.504451: step: 40/530, loss: 0.0012492379173636436
2023-01-22 17:11:49.533438: step: 44/530, loss: 0.0001143816189141944
2023-01-22 17:11:50.576239: step: 48/530, loss: 0.002293126657605171
2023-01-22 17:11:51.608740: step: 52/530, loss: 0.001609840546734631
2023-01-22 17:11:52.651233: step: 56/530, loss: 0.002481231465935707
2023-01-22 17:11:53.692940: step: 60/530, loss: 0.004079022910445929
2023-01-22 17:11:54.720889: step: 64/530, loss: 0.0015545889036729932
2023-01-22 17:11:55.772931: step: 68/530, loss: 0.0013371296226978302
2023-01-22 17:11:56.812585: step: 72/530, loss: 0.0033272304572165012
2023-01-22 17:11:57.867019: step: 76/530, loss: 0.00012407192843966186
2023-01-22 17:11:58.922360: step: 80/530, loss: 0.001283716526813805
2023-01-22 17:11:59.960343: step: 84/530, loss: 0.00013375292473938316
2023-01-22 17:12:01.010401: step: 88/530, loss: 0.012221149168908596
2023-01-22 17:12:02.067997: step: 92/530, loss: 3.227633351343684e-05
2023-01-22 17:12:03.140786: step: 96/530, loss: 0.0001579405361553654
2023-01-22 17:12:04.191533: step: 100/530, loss: 0.00021769414888694882
2023-01-22 17:12:05.263055: step: 104/530, loss: 0.01837671548128128
2023-01-22 17:12:06.299016: step: 108/530, loss: 0.0011274643475189805
2023-01-22 17:12:07.355689: step: 112/530, loss: 0.005027633160352707
2023-01-22 17:12:08.397576: step: 116/530, loss: 0.008041074499487877
2023-01-22 17:12:09.448263: step: 120/530, loss: 0.0029558383394032717
2023-01-22 17:12:10.487937: step: 124/530, loss: 9.197644249070436e-05
2023-01-22 17:12:11.538263: step: 128/530, loss: 0.000355173455318436
2023-01-22 17:12:12.587065: step: 132/530, loss: 0.011277411133050919
2023-01-22 17:12:13.640805: step: 136/530, loss: 0.005733049940317869
2023-01-22 17:12:14.667926: step: 140/530, loss: 0.0035273684188723564
2023-01-22 17:12:15.707554: step: 144/530, loss: 2.521784699638374e-05
2023-01-22 17:12:16.736285: step: 148/530, loss: 0.0005182532477192581
2023-01-22 17:12:17.803221: step: 152/530, loss: 0.002032036427408457
2023-01-22 17:12:18.836706: step: 156/530, loss: 0.005944725591689348
2023-01-22 17:12:19.883712: step: 160/530, loss: 0.003832010319456458
2023-01-22 17:12:20.925125: step: 164/530, loss: 0.0005498633836396039
2023-01-22 17:12:21.960663: step: 168/530, loss: 0.0001618832175154239
2023-01-22 17:12:23.007420: step: 172/530, loss: 0.004295145161449909
2023-01-22 17:12:24.040851: step: 176/530, loss: 0.02098417654633522
2023-01-22 17:12:25.073849: step: 180/530, loss: 0.00642936397343874
2023-01-22 17:12:26.124569: step: 184/530, loss: 0.002964233048260212
2023-01-22 17:12:27.172129: step: 188/530, loss: 0.01809658482670784
2023-01-22 17:12:28.214116: step: 192/530, loss: 0.024744180962443352
2023-01-22 17:12:29.254484: step: 196/530, loss: 0.003283710451796651
2023-01-22 17:12:30.288118: step: 200/530, loss: 0.004359710030257702
2023-01-22 17:12:31.339146: step: 204/530, loss: 0.002236847300082445
2023-01-22 17:12:32.374162: step: 208/530, loss: 0.0014879833906888962
2023-01-22 17:12:33.435165: step: 212/530, loss: 0.018451759591698647
2023-01-22 17:12:34.500007: step: 216/530, loss: 0.00911922100931406
2023-01-22 17:12:35.538660: step: 220/530, loss: 0.001353578525595367
2023-01-22 17:12:36.580618: step: 224/530, loss: 0.003076187102124095
2023-01-22 17:12:37.624906: step: 228/530, loss: 0.0009704912081360817
2023-01-22 17:12:38.657382: step: 232/530, loss: 0.01017417386174202
2023-01-22 17:12:39.690926: step: 236/530, loss: 0.0063122049905359745
2023-01-22 17:12:40.744469: step: 240/530, loss: 0.011784515343606472
2023-01-22 17:12:41.786318: step: 244/530, loss: 0.0014640557346865535
2023-01-22 17:12:42.826175: step: 248/530, loss: 0.00040300979162566364
2023-01-22 17:12:43.882770: step: 252/530, loss: 0.001958419568836689
2023-01-22 17:12:44.941033: step: 256/530, loss: 0.005494561977684498
2023-01-22 17:12:46.003478: step: 260/530, loss: 0.006518794223666191
2023-01-22 17:12:47.059554: step: 264/530, loss: 0.005981508642435074
2023-01-22 17:12:48.098542: step: 268/530, loss: 0.03490021079778671
2023-01-22 17:12:49.132134: step: 272/530, loss: 0.00037004746263846755
2023-01-22 17:12:50.183499: step: 276/530, loss: 0.0023455112241208553
2023-01-22 17:12:51.212682: step: 280/530, loss: 8.950916708272416e-06
2023-01-22 17:12:52.254778: step: 284/530, loss: 7.448644464602694e-05
2023-01-22 17:12:53.307713: step: 288/530, loss: 0.0005203859182074666
2023-01-22 17:12:54.339726: step: 292/530, loss: 0.002128622494637966
2023-01-22 17:12:55.391212: step: 296/530, loss: 0.00027579310699366033
2023-01-22 17:12:56.432477: step: 300/530, loss: 1.741411142575089e-05
2023-01-22 17:12:57.486232: step: 304/530, loss: 0.002726037288084626
2023-01-22 17:12:58.527825: step: 308/530, loss: 0.00011106010060757399
2023-01-22 17:12:59.567178: step: 312/530, loss: 0.0
2023-01-22 17:13:00.616292: step: 316/530, loss: 0.00028838327853009105
2023-01-22 17:13:01.660612: step: 320/530, loss: 0.004911091644316912
2023-01-22 17:13:02.714157: step: 324/530, loss: 0.0007996641797944903
2023-01-22 17:13:03.753071: step: 328/530, loss: 0.0012720789527520537
2023-01-22 17:13:04.812008: step: 332/530, loss: 0.008266856893897057
2023-01-22 17:13:05.863810: step: 336/530, loss: 0.00314516993239522
2023-01-22 17:13:06.897778: step: 340/530, loss: 9.839962876867503e-05
2023-01-22 17:13:07.953790: step: 344/530, loss: 0.001324623473919928
2023-01-22 17:13:09.009747: step: 348/530, loss: 0.0008112098439596593
2023-01-22 17:13:10.043164: step: 352/530, loss: 0.00011970206833211705
2023-01-22 17:13:11.103766: step: 356/530, loss: 0.007163750473409891
2023-01-22 17:13:12.169961: step: 360/530, loss: 0.0012658820487558842
2023-01-22 17:13:13.193130: step: 364/530, loss: 0.0008192802779376507
2023-01-22 17:13:14.249078: step: 368/530, loss: 0.001917996327392757
2023-01-22 17:13:15.286882: step: 372/530, loss: 0.0002513567160349339
2023-01-22 17:13:16.333396: step: 376/530, loss: 0.004647490102797747
2023-01-22 17:13:17.375059: step: 380/530, loss: 0.00022904870274942368
2023-01-22 17:13:18.431752: step: 384/530, loss: 0.0024287542328238487
2023-01-22 17:13:19.485889: step: 388/530, loss: 0.005864972248673439
2023-01-22 17:13:20.538188: step: 392/530, loss: 0.002683364087715745
2023-01-22 17:13:21.581171: step: 396/530, loss: 0.0025851340033113956
2023-01-22 17:13:22.628589: step: 400/530, loss: 0.0019618652295321226
2023-01-22 17:13:23.655622: step: 404/530, loss: 0.00022624812845606357
2023-01-22 17:13:24.710698: step: 408/530, loss: 0.018268143758177757
2023-01-22 17:13:25.775070: step: 412/530, loss: 0.02802874520421028
2023-01-22 17:13:26.826795: step: 416/530, loss: 0.001407139003276825
2023-01-22 17:13:27.881913: step: 420/530, loss: 0.0010604221606627107
2023-01-22 17:13:28.943803: step: 424/530, loss: 0.02815191261470318
2023-01-22 17:13:29.983021: step: 428/530, loss: 0.004729295149445534
2023-01-22 17:13:31.012195: step: 432/530, loss: 1.0240033816444338e-06
2023-01-22 17:13:32.075727: step: 436/530, loss: 0.0020996921230107546
2023-01-22 17:13:33.147724: step: 440/530, loss: 0.005118421744555235
2023-01-22 17:13:34.187208: step: 444/530, loss: 0.008954851888120174
2023-01-22 17:13:35.228036: step: 448/530, loss: 0.0010439646430313587
2023-01-22 17:13:36.281005: step: 452/530, loss: 0.0184810608625412
2023-01-22 17:13:37.340924: step: 456/530, loss: 2.006214708671905e-05
2023-01-22 17:13:38.420828: step: 460/530, loss: 0.00010704037413233891
2023-01-22 17:13:39.459011: step: 464/530, loss: 0.005566218867897987
2023-01-22 17:13:40.521983: step: 468/530, loss: 0.004844698589295149
2023-01-22 17:13:41.559093: step: 472/530, loss: 2.3661985323997214e-05
2023-01-22 17:13:42.608202: step: 476/530, loss: 0.0012873137602582574
2023-01-22 17:13:43.649097: step: 480/530, loss: 0.008623218163847923
2023-01-22 17:13:44.679929: step: 484/530, loss: 0.0004824193601962179
2023-01-22 17:13:45.746819: step: 488/530, loss: 0.0022862600162625313
2023-01-22 17:13:46.781994: step: 492/530, loss: 0.0007822245243005455
2023-01-22 17:13:47.830589: step: 496/530, loss: 0.00011395986803108826
2023-01-22 17:13:48.876190: step: 500/530, loss: 0.00114940176717937
2023-01-22 17:13:49.922662: step: 504/530, loss: 0.0010633916826918721
2023-01-22 17:13:50.981267: step: 508/530, loss: 0.0013889521360397339
2023-01-22 17:13:52.031539: step: 512/530, loss: 0.0019547503907233477
2023-01-22 17:13:53.064029: step: 516/530, loss: 0.0003079283342231065
2023-01-22 17:13:54.108659: step: 520/530, loss: 0.002159843221306801
2023-01-22 17:13:55.155123: step: 524/530, loss: 0.0017030095914378762
2023-01-22 17:13:56.193685: step: 528/530, loss: 0.000291235774056986
2023-01-22 17:13:57.258307: step: 532/530, loss: 0.006097185425460339
2023-01-22 17:13:58.301206: step: 536/530, loss: 0.00015077170974109322
2023-01-22 17:13:59.347000: step: 540/530, loss: 0.0030064077582210302
2023-01-22 17:14:00.394532: step: 544/530, loss: 2.7563430194277316e-05
2023-01-22 17:14:01.437126: step: 548/530, loss: 6.067095000616973e-06
2023-01-22 17:14:02.482842: step: 552/530, loss: 0.007843291386961937
2023-01-22 17:14:03.521812: step: 556/530, loss: 0.00046633571037091315
2023-01-22 17:14:04.578279: step: 560/530, loss: 0.0091286301612854
2023-01-22 17:14:05.628841: step: 564/530, loss: 8.991173672256991e-05
2023-01-22 17:14:06.692716: step: 568/530, loss: 0.0002499464899301529
2023-01-22 17:14:07.744950: step: 572/530, loss: 0.00023953722848091274
2023-01-22 17:14:08.815730: step: 576/530, loss: 0.0010355343110859394
2023-01-22 17:14:09.848597: step: 580/530, loss: 0.013736139982938766
2023-01-22 17:14:10.890581: step: 584/530, loss: 0.006795480847358704
2023-01-22 17:14:11.918376: step: 588/530, loss: 0.0009801766136661172
2023-01-22 17:14:12.965772: step: 592/530, loss: 9.711627171782311e-06
2023-01-22 17:14:14.020073: step: 596/530, loss: 0.006025176029652357
2023-01-22 17:14:15.075886: step: 600/530, loss: 0.0006345068686641753
2023-01-22 17:14:16.110495: step: 604/530, loss: 0.00010796607239171863
2023-01-22 17:14:17.152298: step: 608/530, loss: 0.022064659744501114
2023-01-22 17:14:18.190859: step: 612/530, loss: 0.0009917536517605186
2023-01-22 17:14:19.238467: step: 616/530, loss: 0.0003969916724599898
2023-01-22 17:14:20.291598: step: 620/530, loss: 0.0009577947203069925
2023-01-22 17:14:21.323485: step: 624/530, loss: 0.004058992490172386
2023-01-22 17:14:22.361072: step: 628/530, loss: 0.009625842794775963
2023-01-22 17:14:23.405640: step: 632/530, loss: 0.014803934842348099
2023-01-22 17:14:24.447495: step: 636/530, loss: 0.00020036633941344917
2023-01-22 17:14:25.508028: step: 640/530, loss: 0.006165073253214359
2023-01-22 17:14:26.561373: step: 644/530, loss: 0.00221126526594162
2023-01-22 17:14:27.627245: step: 648/530, loss: 0.003091533202677965
2023-01-22 17:14:28.665011: step: 652/530, loss: 0.001056141685694456
2023-01-22 17:14:29.719084: step: 656/530, loss: 0.0006401028367690742
2023-01-22 17:14:30.773659: step: 660/530, loss: 0.005448830779641867
2023-01-22 17:14:31.826423: step: 664/530, loss: 0.0006278028595261276
2023-01-22 17:14:32.876920: step: 668/530, loss: 0.0010182765545323491
2023-01-22 17:14:33.927680: step: 672/530, loss: 0.011164749041199684
2023-01-22 17:14:34.983589: step: 676/530, loss: 0.0022408654913306236
2023-01-22 17:14:36.032854: step: 680/530, loss: 0.003817001124843955
2023-01-22 17:14:37.085150: step: 684/530, loss: 0.0014193993993103504
2023-01-22 17:14:38.124200: step: 688/530, loss: 0.00926503911614418
2023-01-22 17:14:39.169313: step: 692/530, loss: 0.003855099668726325
2023-01-22 17:14:40.215874: step: 696/530, loss: 9.615978342480958e-05
2023-01-22 17:14:41.258444: step: 700/530, loss: 0.00165564042981714
2023-01-22 17:14:42.290292: step: 704/530, loss: 0.00013659309479407966
2023-01-22 17:14:43.341318: step: 708/530, loss: 0.0037068959791213274
2023-01-22 17:14:44.385515: step: 712/530, loss: 0.000563675130251795
2023-01-22 17:14:45.419584: step: 716/530, loss: 0.0005859659286215901
2023-01-22 17:14:46.444631: step: 720/530, loss: 0.001557123614475131
2023-01-22 17:14:47.499466: step: 724/530, loss: 0.002455672947689891
2023-01-22 17:14:48.554839: step: 728/530, loss: 0.0017205079784616828
2023-01-22 17:14:49.606339: step: 732/530, loss: 0.0038072119932621717
2023-01-22 17:14:50.643393: step: 736/530, loss: 0.00026613465161062777
2023-01-22 17:14:51.676020: step: 740/530, loss: 1.336878995061852e-06
2023-01-22 17:14:52.715970: step: 744/530, loss: 0.0024368404410779476
2023-01-22 17:14:53.757611: step: 748/530, loss: 0.0022249529138207436
2023-01-22 17:14:54.810832: step: 752/530, loss: 0.002513074316084385
2023-01-22 17:14:55.833214: step: 756/530, loss: 0.002031650161370635
2023-01-22 17:14:56.879522: step: 760/530, loss: 0.026250595226883888
2023-01-22 17:14:57.921566: step: 764/530, loss: 0.0004051537252962589
2023-01-22 17:14:58.954962: step: 768/530, loss: 0.002396330703049898
2023-01-22 17:14:59.995239: step: 772/530, loss: 0.0019366589840501547
2023-01-22 17:15:01.035524: step: 776/530, loss: 6.119882982602576e-06
2023-01-22 17:15:02.067537: step: 780/530, loss: 6.379462865879759e-05
2023-01-22 17:15:03.136798: step: 784/530, loss: 0.002453408669680357
2023-01-22 17:15:04.167954: step: 788/530, loss: 0.0001453535951441154
2023-01-22 17:15:05.206726: step: 792/530, loss: 0.00013945973478257656
2023-01-22 17:15:06.242677: step: 796/530, loss: 0.0009795083897188306
2023-01-22 17:15:07.284728: step: 800/530, loss: 0.00011313698632875457
2023-01-22 17:15:08.334040: step: 804/530, loss: 0.00013916977331973612
2023-01-22 17:15:09.373472: step: 808/530, loss: 0.009145022369921207
2023-01-22 17:15:10.409568: step: 812/530, loss: 0.0067528486251831055
2023-01-22 17:15:11.463275: step: 816/530, loss: 3.819125777226873e-05
2023-01-22 17:15:12.489919: step: 820/530, loss: 0.0013857746962457895
2023-01-22 17:15:13.530969: step: 824/530, loss: 1.6716780010028742e-05
2023-01-22 17:15:14.571113: step: 828/530, loss: 7.969896250870079e-05
2023-01-22 17:15:15.617218: step: 832/530, loss: 0.00014966473099775612
2023-01-22 17:15:16.661885: step: 836/530, loss: 0.007192178629338741
2023-01-22 17:15:17.705290: step: 840/530, loss: 0.0028905433136969805
2023-01-22 17:15:18.763419: step: 844/530, loss: 0.0038011521100997925
2023-01-22 17:15:19.817470: step: 848/530, loss: 0.0009843989973887801
2023-01-22 17:15:20.866860: step: 852/530, loss: 0.0031939283944666386
2023-01-22 17:15:21.905835: step: 856/530, loss: 0.0076463669538497925
2023-01-22 17:15:22.963060: step: 860/530, loss: 0.023729044944047928
2023-01-22 17:15:24.019178: step: 864/530, loss: 0.0021684535313397646
2023-01-22 17:15:25.071852: step: 868/530, loss: 9.369548934046179e-05
2023-01-22 17:15:26.111868: step: 872/530, loss: 0.0015189633704721928
2023-01-22 17:15:27.160193: step: 876/530, loss: 0.008067240007221699
2023-01-22 17:15:28.219733: step: 880/530, loss: 0.0008739823824726045
2023-01-22 17:15:29.259725: step: 884/530, loss: 0.0015991192776709795
2023-01-22 17:15:30.309134: step: 888/530, loss: 0.0026988901663571596
2023-01-22 17:15:31.345088: step: 892/530, loss: 0.0003570735570974648
2023-01-22 17:15:32.380015: step: 896/530, loss: 0.0037768923211842775
2023-01-22 17:15:33.413314: step: 900/530, loss: 5.656315988744609e-05
2023-01-22 17:15:34.463268: step: 904/530, loss: 0.0004602005355991423
2023-01-22 17:15:35.508845: step: 908/530, loss: 0.012956167571246624
2023-01-22 17:15:36.544217: step: 912/530, loss: 0.00023429089924320579
2023-01-22 17:15:37.601121: step: 916/530, loss: 0.0005414508050307631
2023-01-22 17:15:38.642899: step: 920/530, loss: 0.003229925176128745
2023-01-22 17:15:39.687844: step: 924/530, loss: 0.00013546341506298631
2023-01-22 17:15:40.731893: step: 928/530, loss: 0.005035614129155874
2023-01-22 17:15:41.783935: step: 932/530, loss: 7.074460154399276e-05
2023-01-22 17:15:42.829219: step: 936/530, loss: 0.003970619756728411
2023-01-22 17:15:43.864419: step: 940/530, loss: 0.007547573186457157
2023-01-22 17:15:44.900485: step: 944/530, loss: 0.001952392398379743
2023-01-22 17:15:45.951276: step: 948/530, loss: 0.0017291156109422445
2023-01-22 17:15:46.999049: step: 952/530, loss: 1.3814047861160361e-06
2023-01-22 17:15:48.050106: step: 956/530, loss: 0.003911504987627268
2023-01-22 17:15:49.094428: step: 960/530, loss: 0.0007108685094863176
2023-01-22 17:15:50.131450: step: 964/530, loss: 0.002414074493572116
2023-01-22 17:15:51.165587: step: 968/530, loss: 0.005062845069915056
2023-01-22 17:15:52.233956: step: 972/530, loss: 0.00020350265549495816
2023-01-22 17:15:53.268257: step: 976/530, loss: 9.916456292557996e-06
2023-01-22 17:15:54.328150: step: 980/530, loss: 0.0009219230269081891
2023-01-22 17:15:55.376801: step: 984/530, loss: 0.0006482011522166431
2023-01-22 17:15:56.426735: step: 988/530, loss: 0.0004915453610010445
2023-01-22 17:15:57.474301: step: 992/530, loss: 0.00047927928972058
2023-01-22 17:15:58.516498: step: 996/530, loss: 0.001487908884882927
2023-01-22 17:15:59.566989: step: 1000/530, loss: 7.026194361969829e-05
2023-01-22 17:16:00.604022: step: 1004/530, loss: 3.7042158510303125e-05
2023-01-22 17:16:01.649939: step: 1008/530, loss: 0.0017732521519064903
2023-01-22 17:16:02.694932: step: 1012/530, loss: 0.0003932069812435657
2023-01-22 17:16:03.742387: step: 1016/530, loss: 0.00988938007503748
2023-01-22 17:16:04.787296: step: 1020/530, loss: 0.008849609643220901
2023-01-22 17:16:05.810868: step: 1024/530, loss: 9.164132279693149e-06
2023-01-22 17:16:06.848635: step: 1028/530, loss: 0.0019211875041946769
2023-01-22 17:16:07.904273: step: 1032/530, loss: 0.0007777855498716235
2023-01-22 17:16:08.939662: step: 1036/530, loss: 0.0002675313444342464
2023-01-22 17:16:10.009871: step: 1040/530, loss: 0.0037446871865540743
2023-01-22 17:16:11.060668: step: 1044/530, loss: 0.0003587371320463717
2023-01-22 17:16:12.087165: step: 1048/530, loss: 0.00118012516759336
2023-01-22 17:16:13.122043: step: 1052/530, loss: 0.0009117811569012702
2023-01-22 17:16:14.166406: step: 1056/530, loss: 0.010774577967822552
2023-01-22 17:16:15.210326: step: 1060/530, loss: 0.0003953362465836108
2023-01-22 17:16:16.241821: step: 1064/530, loss: 0.003877539886161685
2023-01-22 17:16:17.281757: step: 1068/530, loss: 2.943889921880327e-05
2023-01-22 17:16:18.335969: step: 1072/530, loss: 4.294289828976616e-05
2023-01-22 17:16:19.387343: step: 1076/530, loss: 0.00620786240324378
2023-01-22 17:16:20.422967: step: 1080/530, loss: 0.001447570277377963
2023-01-22 17:16:21.461359: step: 1084/530, loss: 0.0009011015063151717
2023-01-22 17:16:22.523413: step: 1088/530, loss: 1.031836859510804e-06
2023-01-22 17:16:23.572005: step: 1092/530, loss: 0.0024762984830886126
2023-01-22 17:16:24.613492: step: 1096/530, loss: 0.0009796727681532502
2023-01-22 17:16:25.663762: step: 1100/530, loss: 0.005562683567404747
2023-01-22 17:16:26.705347: step: 1104/530, loss: 9.833775402512401e-05
2023-01-22 17:16:27.739590: step: 1108/530, loss: 0.0005841218517161906
2023-01-22 17:16:28.788792: step: 1112/530, loss: 0.00743784848600626
2023-01-22 17:16:29.859890: step: 1116/530, loss: 0.026636315509676933
2023-01-22 17:16:30.898473: step: 1120/530, loss: 0.0007572905742563307
2023-01-22 17:16:31.957903: step: 1124/530, loss: 0.0006607124814763665
2023-01-22 17:16:32.998146: step: 1128/530, loss: 0.004514450207352638
2023-01-22 17:16:34.040988: step: 1132/530, loss: 0.0021646092645823956
2023-01-22 17:16:35.072886: step: 1136/530, loss: 0.0009013505768962204
2023-01-22 17:16:36.120134: step: 1140/530, loss: 0.002261790679767728
2023-01-22 17:16:37.159609: step: 1144/530, loss: 0.009272295981645584
2023-01-22 17:16:38.192230: step: 1148/530, loss: 0.001525578205473721
2023-01-22 17:16:39.229419: step: 1152/530, loss: 0.0025265717413276434
2023-01-22 17:16:40.284336: step: 1156/530, loss: 0.00033221999183297157
2023-01-22 17:16:41.321086: step: 1160/530, loss: 3.576509334379807e-05
2023-01-22 17:16:42.369616: step: 1164/530, loss: 0.0006343633285723627
2023-01-22 17:16:43.415412: step: 1168/530, loss: 0.010584630072116852
2023-01-22 17:16:44.456829: step: 1172/530, loss: 0.00030360708478838205
2023-01-22 17:16:45.514174: step: 1176/530, loss: 1.3866609833712573e-06
2023-01-22 17:16:46.546168: step: 1180/530, loss: 0.0016013794811442494
2023-01-22 17:16:47.587415: step: 1184/530, loss: 0.0001446597307221964
2023-01-22 17:16:48.643835: step: 1188/530, loss: 0.0014444533735513687
2023-01-22 17:16:49.676449: step: 1192/530, loss: 0.0006003277376294136
2023-01-22 17:16:50.716569: step: 1196/530, loss: 0.0015239645726978779
2023-01-22 17:16:51.759641: step: 1200/530, loss: 0.006915600039064884
2023-01-22 17:16:52.815183: step: 1204/530, loss: 0.0016340535366907716
2023-01-22 17:16:53.864007: step: 1208/530, loss: 0.005759651307016611
2023-01-22 17:16:54.914026: step: 1212/530, loss: 0.00025268254103139043
2023-01-22 17:16:55.971339: step: 1216/530, loss: 0.004989036358892918
2023-01-22 17:16:57.039645: step: 1220/530, loss: 0.004300558008253574
2023-01-22 17:16:58.090172: step: 1224/530, loss: 0.0009450926445424557
2023-01-22 17:16:59.171815: step: 1228/530, loss: 0.0010944271925836802
2023-01-22 17:17:00.230361: step: 1232/530, loss: 0.002427093219012022
2023-01-22 17:17:01.275869: step: 1236/530, loss: 0.000895948673132807
2023-01-22 17:17:02.317125: step: 1240/530, loss: 0.0011638362193480134
2023-01-22 17:17:03.362419: step: 1244/530, loss: 0.0026391472201794386
2023-01-22 17:17:04.425789: step: 1248/530, loss: 0.004858668893575668
2023-01-22 17:17:05.453404: step: 1252/530, loss: 0.0027947798371315002
2023-01-22 17:17:06.507920: step: 1256/530, loss: 0.0004653006326407194
2023-01-22 17:17:07.561363: step: 1260/530, loss: 0.0011524201836436987
2023-01-22 17:17:08.599827: step: 1264/530, loss: 0.002620370825752616
2023-01-22 17:17:09.650921: step: 1268/530, loss: 0.0065241591073572636
2023-01-22 17:17:10.688468: step: 1272/530, loss: 0.0035955074708908796
2023-01-22 17:17:11.733470: step: 1276/530, loss: 0.0005749856354668736
2023-01-22 17:17:12.799389: step: 1280/530, loss: 0.002244073897600174
2023-01-22 17:17:13.838691: step: 1284/530, loss: 0.0029421034269034863
2023-01-22 17:17:14.879754: step: 1288/530, loss: 0.002565886825323105
2023-01-22 17:17:15.915488: step: 1292/530, loss: 0.005780614446848631
2023-01-22 17:17:16.954832: step: 1296/530, loss: 0.0002358978526899591
2023-01-22 17:17:17.996291: step: 1300/530, loss: 0.003610714105889201
2023-01-22 17:17:19.037622: step: 1304/530, loss: 0.0023282982874661684
2023-01-22 17:17:20.088344: step: 1308/530, loss: 0.0001790036476450041
2023-01-22 17:17:21.130811: step: 1312/530, loss: 0.0048813773319125175
2023-01-22 17:17:22.198072: step: 1316/530, loss: 4.700659337686375e-05
2023-01-22 17:17:23.254797: step: 1320/530, loss: 0.0014433374162763357
2023-01-22 17:17:24.281632: step: 1324/530, loss: 0.00014284891949500889
2023-01-22 17:17:25.333453: step: 1328/530, loss: 0.0016807086067274213
2023-01-22 17:17:26.378778: step: 1332/530, loss: 0.004982365760952234
2023-01-22 17:17:27.433104: step: 1336/530, loss: 0.0050092837773263454
2023-01-22 17:17:28.467835: step: 1340/530, loss: 0.004040142055600882
2023-01-22 17:17:29.501529: step: 1344/530, loss: 0.0052107577212154865
2023-01-22 17:17:30.538280: step: 1348/530, loss: 0.0041431281715631485
2023-01-22 17:17:31.587218: step: 1352/530, loss: 0.0024121892638504505
2023-01-22 17:17:32.619858: step: 1356/530, loss: 0.008282479830086231
2023-01-22 17:17:33.680677: step: 1360/530, loss: 0.0006505693309009075
2023-01-22 17:17:34.726324: step: 1364/530, loss: 0.0016670534387230873
2023-01-22 17:17:35.755804: step: 1368/530, loss: 0.0010452264687046409
2023-01-22 17:17:36.800980: step: 1372/530, loss: 0.0008869652519933879
2023-01-22 17:17:37.856134: step: 1376/530, loss: 0.0010890167905017734
2023-01-22 17:17:38.893006: step: 1380/530, loss: 0.002823673654347658
2023-01-22 17:17:39.942996: step: 1384/530, loss: 0.006408573593944311
2023-01-22 17:17:41.008107: step: 1388/530, loss: 0.002019304782152176
2023-01-22 17:17:42.046896: step: 1392/530, loss: 0.001684128656052053
2023-01-22 17:17:43.091914: step: 1396/530, loss: 0.14118409156799316
2023-01-22 17:17:44.145269: step: 1400/530, loss: 0.006086037028580904
2023-01-22 17:17:45.184958: step: 1404/530, loss: 0.0029782152269035578
2023-01-22 17:17:46.207606: step: 1408/530, loss: 1.072677241609199e-05
2023-01-22 17:17:47.233098: step: 1412/530, loss: 0.0018608147511258721
2023-01-22 17:17:48.291691: step: 1416/530, loss: 0.0002685075451154262
2023-01-22 17:17:49.339802: step: 1420/530, loss: 0.017026811838150024
2023-01-22 17:17:50.384065: step: 1424/530, loss: 0.008269661106169224
2023-01-22 17:17:51.431394: step: 1428/530, loss: 4.369254384073429e-05
2023-01-22 17:17:52.451592: step: 1432/530, loss: 0.0007951008738018572
2023-01-22 17:17:53.485317: step: 1436/530, loss: 0.0016839754534885287
2023-01-22 17:17:54.526309: step: 1440/530, loss: 0.000541744870133698
2023-01-22 17:17:55.574896: step: 1444/530, loss: 3.0239729312597774e-05
2023-01-22 17:17:56.610369: step: 1448/530, loss: 0.00753433583304286
2023-01-22 17:17:57.643114: step: 1452/530, loss: 0.0019085907842963934
2023-01-22 17:17:58.685523: step: 1456/530, loss: 0.00901994202286005
2023-01-22 17:17:59.752763: step: 1460/530, loss: 0.007146323565393686
2023-01-22 17:18:00.796006: step: 1464/530, loss: 0.00172905414365232
2023-01-22 17:18:01.834427: step: 1468/530, loss: 0.005956052336841822
2023-01-22 17:18:02.869913: step: 1472/530, loss: 0.014158985577523708
2023-01-22 17:18:03.910506: step: 1476/530, loss: 0.0020066110882908106
2023-01-22 17:18:04.940869: step: 1480/530, loss: 4.1939885704778135e-05
2023-01-22 17:18:05.981120: step: 1484/530, loss: 7.217737584142014e-05
2023-01-22 17:18:07.029854: step: 1488/530, loss: 0.0016097412444651127
2023-01-22 17:18:08.067640: step: 1492/530, loss: 0.0010121164377778769
2023-01-22 17:18:09.108687: step: 1496/530, loss: 4.968651046510786e-05
2023-01-22 17:18:10.145419: step: 1500/530, loss: 0.00623213080689311
2023-01-22 17:18:11.181560: step: 1504/530, loss: 0.0002086248859995976
2023-01-22 17:18:12.222996: step: 1508/530, loss: 0.001149590709246695
2023-01-22 17:18:13.277523: step: 1512/530, loss: 0.006035902071744204
2023-01-22 17:18:14.308677: step: 1516/530, loss: 0.0028512482531368732
2023-01-22 17:18:15.372070: step: 1520/530, loss: 0.005742454435676336
2023-01-22 17:18:16.390612: step: 1524/530, loss: 0.0010509680723771453
2023-01-22 17:18:17.431641: step: 1528/530, loss: 0.00010907711111940444
2023-01-22 17:18:18.466085: step: 1532/530, loss: 0.004124751314520836
2023-01-22 17:18:19.498733: step: 1536/530, loss: 0.0012129239039495587
2023-01-22 17:18:20.534972: step: 1540/530, loss: 0.0009087308426387608
2023-01-22 17:18:21.569625: step: 1544/530, loss: 0.004887440241873264
2023-01-22 17:18:22.604421: step: 1548/530, loss: 0.0
2023-01-22 17:18:23.669698: step: 1552/530, loss: 0.003754856064915657
2023-01-22 17:18:24.710651: step: 1556/530, loss: 0.0009373383945785463
2023-01-22 17:18:25.769439: step: 1560/530, loss: 0.001886929851025343
2023-01-22 17:18:26.807119: step: 1564/530, loss: 0.005456239450722933
2023-01-22 17:18:27.865919: step: 1568/530, loss: 0.004966110922396183
2023-01-22 17:18:28.910744: step: 1572/530, loss: 0.0017675001872703433
2023-01-22 17:18:29.966171: step: 1576/530, loss: 0.0038811187259852886
2023-01-22 17:18:31.004524: step: 1580/530, loss: 0.006399739999324083
2023-01-22 17:18:32.038679: step: 1584/530, loss: 0.0018490948714315891
2023-01-22 17:18:33.073060: step: 1588/530, loss: 0.0029616185929626226
2023-01-22 17:18:34.118295: step: 1592/530, loss: 0.007141935173422098
2023-01-22 17:18:35.148913: step: 1596/530, loss: 0.00014484429266303778
2023-01-22 17:18:36.213557: step: 1600/530, loss: 0.01417284831404686
2023-01-22 17:18:37.244342: step: 1604/530, loss: 0.002109603490680456
2023-01-22 17:18:38.303654: step: 1608/530, loss: 0.005846297834068537
2023-01-22 17:18:39.342454: step: 1612/530, loss: 0.00015911986702121794
2023-01-22 17:18:40.385798: step: 1616/530, loss: 0.007112887222319841
2023-01-22 17:18:41.435474: step: 1620/530, loss: 0.018406052142381668
2023-01-22 17:18:42.521316: step: 1624/530, loss: 0.00012296879140194505
2023-01-22 17:18:43.554278: step: 1628/530, loss: 0.005481957923620939
2023-01-22 17:18:44.604386: step: 1632/530, loss: 0.0037433719262480736
2023-01-22 17:18:45.626964: step: 1636/530, loss: 0.0011715436121448874
2023-01-22 17:18:46.659330: step: 1640/530, loss: 4.916386023978703e-05
2023-01-22 17:18:47.713762: step: 1644/530, loss: 0.0015766690485179424
2023-01-22 17:18:48.745236: step: 1648/530, loss: 0.0032344404608011246
2023-01-22 17:18:49.781229: step: 1652/530, loss: 0.0077257719822227955
2023-01-22 17:18:50.834438: step: 1656/530, loss: 0.00023749937827233225
2023-01-22 17:18:51.872443: step: 1660/530, loss: 0.005592431407421827
2023-01-22 17:18:52.908587: step: 1664/530, loss: 0.0031693640630692244
2023-01-22 17:18:53.959463: step: 1668/530, loss: 0.0035397526808083057
2023-01-22 17:18:54.988788: step: 1672/530, loss: 0.0005305302329361439
2023-01-22 17:18:56.040327: step: 1676/530, loss: 0.0034351455979049206
2023-01-22 17:18:57.077533: step: 1680/530, loss: 0.0028322439175099134
2023-01-22 17:18:58.132473: step: 1684/530, loss: 0.0005825162515975535
2023-01-22 17:18:59.165003: step: 1688/530, loss: 0.006902835797518492
2023-01-22 17:19:00.205614: step: 1692/530, loss: 0.0014823701931163669
2023-01-22 17:19:01.262842: step: 1696/530, loss: 0.001065253745764494
2023-01-22 17:19:02.314355: step: 1700/530, loss: 0.01789345033466816
2023-01-22 17:19:03.372919: step: 1704/530, loss: 0.002103856299072504
2023-01-22 17:19:04.402725: step: 1708/530, loss: 0.0009596335585229099
2023-01-22 17:19:05.444081: step: 1712/530, loss: 0.00040444484329782426
2023-01-22 17:19:06.495448: step: 1716/530, loss: 0.0002746698446571827
2023-01-22 17:19:07.530613: step: 1720/530, loss: 0.0010927320690825582
2023-01-22 17:19:08.581041: step: 1724/530, loss: 6.922454485902563e-05
2023-01-22 17:19:09.614503: step: 1728/530, loss: 0.002970654983073473
2023-01-22 17:19:10.664504: step: 1732/530, loss: 0.0026557997334748507
2023-01-22 17:19:11.702046: step: 1736/530, loss: 0.005885441321879625
2023-01-22 17:19:12.736384: step: 1740/530, loss: 0.0031337642576545477
2023-01-22 17:19:13.774776: step: 1744/530, loss: 0.004391557537019253
2023-01-22 17:19:14.862125: step: 1748/530, loss: 0.01008619088679552
2023-01-22 17:19:15.885315: step: 1752/530, loss: 0.0005449464661069214
2023-01-22 17:19:16.923995: step: 1756/530, loss: 0.0004244691808708012
2023-01-22 17:19:17.956577: step: 1760/530, loss: 3.0600263016822282e-06
2023-01-22 17:19:18.994340: step: 1764/530, loss: 0.0009252700838260353
2023-01-22 17:19:20.042384: step: 1768/530, loss: 0.002439627656713128
2023-01-22 17:19:21.096772: step: 1772/530, loss: 0.0002417669747956097
2023-01-22 17:19:22.150054: step: 1776/530, loss: 0.004936986602842808
2023-01-22 17:19:23.185245: step: 1780/530, loss: 0.004176536109298468
2023-01-22 17:19:24.231526: step: 1784/530, loss: 0.0015248837880790234
2023-01-22 17:19:25.277241: step: 1788/530, loss: 0.0009485507034696639
2023-01-22 17:19:26.321323: step: 1792/530, loss: 0.000917789526283741
2023-01-22 17:19:27.368753: step: 1796/530, loss: 0.003934743348509073
2023-01-22 17:19:28.441569: step: 1800/530, loss: 0.0017367423279210925
2023-01-22 17:19:29.480921: step: 1804/530, loss: 0.00031899186433292925
2023-01-22 17:19:30.523065: step: 1808/530, loss: 0.0009279457735829055
2023-01-22 17:19:31.556509: step: 1812/530, loss: 0.007400153670459986
2023-01-22 17:19:32.605542: step: 1816/530, loss: 4.4409425754565746e-05
2023-01-22 17:19:33.650570: step: 1820/530, loss: 0.004460947588086128
2023-01-22 17:19:34.688806: step: 1824/530, loss: 3.0821589461993426e-05
2023-01-22 17:19:35.733909: step: 1828/530, loss: 0.002043446758762002
2023-01-22 17:19:36.777579: step: 1832/530, loss: 0.00819195806980133
2023-01-22 17:19:37.818385: step: 1836/530, loss: 0.000686023267917335
2023-01-22 17:19:38.859329: step: 1840/530, loss: 0.00717303017154336
2023-01-22 17:19:39.900211: step: 1844/530, loss: 0.0001378904707962647
2023-01-22 17:19:40.947478: step: 1848/530, loss: 0.000975067843683064
2023-01-22 17:19:42.002771: step: 1852/530, loss: 0.0031472533009946346
2023-01-22 17:19:43.058683: step: 1856/530, loss: 0.0085146464407444
2023-01-22 17:19:44.099022: step: 1860/530, loss: 1.5978568626451306e-05
2023-01-22 17:19:45.146708: step: 1864/530, loss: 0.0018684043316170573
2023-01-22 17:19:46.205541: step: 1868/530, loss: 0.0014190655201673508
2023-01-22 17:19:47.253531: step: 1872/530, loss: 0.00028407294303178787
2023-01-22 17:19:48.297414: step: 1876/530, loss: 0.003862496931105852
2023-01-22 17:19:49.349263: step: 1880/530, loss: 0.0007444398943334818
2023-01-22 17:19:50.388246: step: 1884/530, loss: 0.0008316596504300833
2023-01-22 17:19:51.442469: step: 1888/530, loss: 0.0024567798245698214
2023-01-22 17:19:52.495383: step: 1892/530, loss: 3.7581445212708786e-05
2023-01-22 17:19:53.553063: step: 1896/530, loss: 0.0005281384219415486
2023-01-22 17:19:54.592284: step: 1900/530, loss: 0.0015169217949733138
2023-01-22 17:19:55.636734: step: 1904/530, loss: 2.5921190172084607e-05
2023-01-22 17:19:56.674475: step: 1908/530, loss: 0.0028863977640867233
2023-01-22 17:19:57.724902: step: 1912/530, loss: 0.014135162346065044
2023-01-22 17:19:58.774751: step: 1916/530, loss: 0.0031662173569202423
2023-01-22 17:19:59.812657: step: 1920/530, loss: 0.005211448762565851
2023-01-22 17:20:00.842914: step: 1924/530, loss: 0.008082851767539978
2023-01-22 17:20:01.883156: step: 1928/530, loss: 0.0007151024765335023
2023-01-22 17:20:02.945463: step: 1932/530, loss: 0.021478649228811264
2023-01-22 17:20:03.966279: step: 1936/530, loss: 0.0
2023-01-22 17:20:05.003362: step: 1940/530, loss: 0.0015179453184828162
2023-01-22 17:20:06.040240: step: 1944/530, loss: 0.004567896015942097
2023-01-22 17:20:07.093138: step: 1948/530, loss: 0.00677313469350338
2023-01-22 17:20:08.151557: step: 1952/530, loss: 0.0017850816948339343
2023-01-22 17:20:09.192726: step: 1956/530, loss: 0.024138212203979492
2023-01-22 17:20:10.224697: step: 1960/530, loss: 0.005984392017126083
2023-01-22 17:20:11.271292: step: 1964/530, loss: 0.000849053671117872
2023-01-22 17:20:12.315784: step: 1968/530, loss: 0.00010138084326172248
2023-01-22 17:20:13.362524: step: 1972/530, loss: 0.004166722763329744
2023-01-22 17:20:14.419619: step: 1976/530, loss: 0.0022677145898342133
2023-01-22 17:20:15.458116: step: 1980/530, loss: 5.0635961088119075e-05
2023-01-22 17:20:16.517426: step: 1984/530, loss: 0.004011231940239668
2023-01-22 17:20:17.552474: step: 1988/530, loss: 0.015933707356452942
2023-01-22 17:20:18.598870: step: 1992/530, loss: 0.003142152912914753
2023-01-22 17:20:19.650751: step: 1996/530, loss: 0.0011389505816623569
2023-01-22 17:20:20.687381: step: 2000/530, loss: 0.00748224463313818
2023-01-22 17:20:21.746435: step: 2004/530, loss: 0.008931251242756844
2023-01-22 17:20:22.784181: step: 2008/530, loss: 0.00011959778203163296
2023-01-22 17:20:23.828519: step: 2012/530, loss: 0.005308498162776232
2023-01-22 17:20:24.868172: step: 2016/530, loss: 0.00034672507899813354
2023-01-22 17:20:25.904347: step: 2020/530, loss: 0.01122039183974266
2023-01-22 17:20:26.927583: step: 2024/530, loss: 0.00044637013343162835
2023-01-22 17:20:27.970384: step: 2028/530, loss: 0.0007838958990760148
2023-01-22 17:20:28.995709: step: 2032/530, loss: 0.0021932253148406744
2023-01-22 17:20:30.050902: step: 2036/530, loss: 0.00010908945114351809
2023-01-22 17:20:31.097839: step: 2040/530, loss: 0.0003816072130575776
2023-01-22 17:20:32.147392: step: 2044/530, loss: 0.004653113428503275
2023-01-22 17:20:33.191717: step: 2048/530, loss: 0.0012212434085085988
2023-01-22 17:20:34.245981: step: 2052/530, loss: 0.0019578351639211178
2023-01-22 17:20:35.281117: step: 2056/530, loss: 0.0010203371057286859
2023-01-22 17:20:36.335661: step: 2060/530, loss: 0.003280231961980462
2023-01-22 17:20:37.387679: step: 2064/530, loss: 0.004118583630770445
2023-01-22 17:20:38.427113: step: 2068/530, loss: 0.0024739992804825306
2023-01-22 17:20:39.478847: step: 2072/530, loss: 0.006869019940495491
2023-01-22 17:20:40.524697: step: 2076/530, loss: 0.006774529814720154
2023-01-22 17:20:41.565262: step: 2080/530, loss: 0.0034330282360315323
2023-01-22 17:20:42.617215: step: 2084/530, loss: 0.004724840633571148
2023-01-22 17:20:43.661465: step: 2088/530, loss: 0.0016951600555330515
2023-01-22 17:20:44.701917: step: 2092/530, loss: 0.0011921994155272841
2023-01-22 17:20:45.738049: step: 2096/530, loss: 0.00022403204638976604
2023-01-22 17:20:46.781419: step: 2100/530, loss: 0.0036077210679650307
2023-01-22 17:20:47.820771: step: 2104/530, loss: 0.0007157736108638346
2023-01-22 17:20:48.875124: step: 2108/530, loss: 0.001830795779824257
2023-01-22 17:20:49.919415: step: 2112/530, loss: 0.004905502311885357
2023-01-22 17:20:50.951366: step: 2116/530, loss: 2.134965507138986e-05
2023-01-22 17:20:51.981516: step: 2120/530, loss: 0.0008202884346246719
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34175347222222224, 'r': 0.32683823529411765, 'f1': 0.3341294859359845}, 'combined': 0.24620067384756752, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36171443262559866, 'r': 0.4075936529402426, 'f1': 0.38328599343040964}, 'combined': 0.2970924925154372, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30920657872243434, 'r': 0.3197677142385706, 'f1': 0.3143984802308334}, 'combined': 0.23166203806482458, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35963072693679166, 'r': 0.408551083174517, 'f1': 0.382533200080787}, 'combined': 0.2965089876224282, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.326371749327447, 'r': 0.3375191715056141, 'f1': 0.3318518719840646}, 'combined': 0.2445224319882581, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35923573644145335, 'r': 0.38565012882685434, 'f1': 0.37197459234363256}, 'combined': 0.2883248036347774, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4074074074074074, 'r': 0.4782608695652174, 'f1': 0.44000000000000006}, 'combined': 0.22000000000000003, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3462223895582329, 'r': 0.3271703036053131, 'f1': 0.33642682926829265}, 'combined': 0.24789345314505773, 'stategy': 1, 'epoch': 15}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.360310988924254, 'r': 0.40667453529318376, 'f1': 0.3820914459404006}, 'combined': 0.2961665753222244, 'stategy': 1, 'epoch': 15}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 15}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 17
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:23:17.752718: step: 4/530, loss: 0.0014743524370715022
2023-01-22 17:23:18.792511: step: 8/530, loss: 0.00660325912758708
2023-01-22 17:23:19.815788: step: 12/530, loss: 0.002118706936016679
2023-01-22 17:23:20.865118: step: 16/530, loss: 0.01160414982587099
2023-01-22 17:23:21.901117: step: 20/530, loss: 0.000995034002698958
2023-01-22 17:23:22.933570: step: 24/530, loss: 0.0025456808507442474
2023-01-22 17:23:23.974903: step: 28/530, loss: 0.0007189153111539781
2023-01-22 17:23:25.009858: step: 32/530, loss: 0.0004857582098338753
2023-01-22 17:23:26.047261: step: 36/530, loss: 0.0017247971845790744
2023-01-22 17:23:27.083791: step: 40/530, loss: 0.00021397563978098333
2023-01-22 17:23:28.119395: step: 44/530, loss: 0.004515861626714468
2023-01-22 17:23:29.145872: step: 48/530, loss: 0.0005723762442357838
2023-01-22 17:23:30.185505: step: 52/530, loss: 0.0005342873046174645
2023-01-22 17:23:31.212772: step: 56/530, loss: 0.0199979767203331
2023-01-22 17:23:32.246356: step: 60/530, loss: 0.004544694907963276
2023-01-22 17:23:33.299726: step: 64/530, loss: 0.0007314592367038131
2023-01-22 17:23:34.335213: step: 68/530, loss: 0.0029184159357100725
2023-01-22 17:23:35.381470: step: 72/530, loss: 0.0004968098364770412
2023-01-22 17:23:36.419944: step: 76/530, loss: 0.0031347903423011303
2023-01-22 17:23:37.468673: step: 80/530, loss: 0.0010143619729205966
2023-01-22 17:23:38.505926: step: 84/530, loss: 0.00048273411812260747
2023-01-22 17:23:39.544739: step: 88/530, loss: 2.379666329943575e-05
2023-01-22 17:23:40.575789: step: 92/530, loss: 0.0016256897943094373
2023-01-22 17:23:41.613093: step: 96/530, loss: 0.0015957856085151434
2023-01-22 17:23:42.655965: step: 100/530, loss: 0.007323454134166241
2023-01-22 17:23:43.691414: step: 104/530, loss: 0.002840333618223667
2023-01-22 17:23:44.724239: step: 108/530, loss: 0.008337774313986301
2023-01-22 17:23:45.766974: step: 112/530, loss: 0.0181791540235281
2023-01-22 17:23:46.811922: step: 116/530, loss: 5.583392703556456e-05
2023-01-22 17:23:47.843985: step: 120/530, loss: 6.064720309950644e-06
2023-01-22 17:23:48.905523: step: 124/530, loss: 0.005723145324736834
2023-01-22 17:23:49.956189: step: 128/530, loss: 0.017118489369750023
2023-01-22 17:23:51.014695: step: 132/530, loss: 0.021794024854898453
2023-01-22 17:23:52.076250: step: 136/530, loss: 0.010343911126255989
2023-01-22 17:23:53.125398: step: 140/530, loss: 5.1592636737041175e-05
2023-01-22 17:23:54.173982: step: 144/530, loss: 0.023200225085020065
2023-01-22 17:23:55.205697: step: 148/530, loss: 0.00417774822562933
2023-01-22 17:23:56.255400: step: 152/530, loss: 0.00023547696764580905
2023-01-22 17:23:57.295412: step: 156/530, loss: 0.003617009148001671
2023-01-22 17:23:58.329843: step: 160/530, loss: 0.0003376854583621025
2023-01-22 17:23:59.370501: step: 164/530, loss: 0.0007484745001420379
2023-01-22 17:24:00.416088: step: 168/530, loss: 0.00010161162936128676
2023-01-22 17:24:01.458182: step: 172/530, loss: 0.009199620224535465
2023-01-22 17:24:02.495134: step: 176/530, loss: 0.003756369696930051
2023-01-22 17:24:03.548170: step: 180/530, loss: 0.0032707166392356157
2023-01-22 17:24:04.608366: step: 184/530, loss: 0.0004229229816701263
2023-01-22 17:24:05.648603: step: 188/530, loss: 0.0023302605841308832
2023-01-22 17:24:06.691618: step: 192/530, loss: 0.0002956682874355465
2023-01-22 17:24:07.744519: step: 196/530, loss: 0.0005876939394511282
2023-01-22 17:24:08.786908: step: 200/530, loss: 0.004324890673160553
2023-01-22 17:24:09.839183: step: 204/530, loss: 0.0010831811232492328
2023-01-22 17:24:10.877444: step: 208/530, loss: 0.0015409933403134346
2023-01-22 17:24:11.938711: step: 212/530, loss: 0.015628740191459656
2023-01-22 17:24:12.980191: step: 216/530, loss: 4.612496923073195e-05
2023-01-22 17:24:14.029800: step: 220/530, loss: 0.0011591032380238175
2023-01-22 17:24:15.089258: step: 224/530, loss: 0.003789310809224844
2023-01-22 17:24:16.149708: step: 228/530, loss: 0.05970427766442299
2023-01-22 17:24:17.203371: step: 232/530, loss: 0.00018468995403964072
2023-01-22 17:24:18.259161: step: 236/530, loss: 0.0008769754786044359
2023-01-22 17:24:19.308895: step: 240/530, loss: 0.007567410357296467
2023-01-22 17:24:20.349102: step: 244/530, loss: 1.0661425221769605e-05
2023-01-22 17:24:21.392933: step: 248/530, loss: 0.00039061999996192753
2023-01-22 17:24:22.429278: step: 252/530, loss: 0.008116090670228004
2023-01-22 17:24:23.484938: step: 256/530, loss: 0.006383896805346012
2023-01-22 17:24:24.563412: step: 260/530, loss: 0.0008009921293705702
2023-01-22 17:24:25.630741: step: 264/530, loss: 0.006543674506247044
2023-01-22 17:24:26.678915: step: 268/530, loss: 0.0027854307554662228
2023-01-22 17:24:27.722066: step: 272/530, loss: 0.0022404994815587997
2023-01-22 17:24:28.764479: step: 276/530, loss: 8.202244498534128e-05
2023-01-22 17:24:29.813607: step: 280/530, loss: 0.00045637405128218234
2023-01-22 17:24:30.869442: step: 284/530, loss: 0.001067394157871604
2023-01-22 17:24:31.915864: step: 288/530, loss: 0.0037804178427904844
2023-01-22 17:24:32.975900: step: 292/530, loss: 0.002081147860735655
2023-01-22 17:24:34.052634: step: 296/530, loss: 0.005376341287046671
2023-01-22 17:24:35.118821: step: 300/530, loss: 0.0017974644433706999
2023-01-22 17:24:36.173892: step: 304/530, loss: 0.0035429177805781364
2023-01-22 17:24:37.205937: step: 308/530, loss: 0.0031821520533412695
2023-01-22 17:24:38.266732: step: 312/530, loss: 0.003984443377703428
2023-01-22 17:24:39.327850: step: 316/530, loss: 0.002903739921748638
2023-01-22 17:24:40.373556: step: 320/530, loss: 3.6114051908953115e-05
2023-01-22 17:24:41.426490: step: 324/530, loss: 0.001399812987074256
2023-01-22 17:24:42.486244: step: 328/530, loss: 0.0012534570414572954
2023-01-22 17:24:43.534162: step: 332/530, loss: 2.926984234363772e-05
2023-01-22 17:24:44.586185: step: 336/530, loss: 7.785757588862907e-06
2023-01-22 17:24:45.631115: step: 340/530, loss: 0.002381031634286046
2023-01-22 17:24:46.687877: step: 344/530, loss: 0.0032594960648566484
2023-01-22 17:24:47.734598: step: 348/530, loss: 0.00030655748560093343
2023-01-22 17:24:48.789681: step: 352/530, loss: 0.0011889704037457705
2023-01-22 17:24:49.838761: step: 356/530, loss: 0.001804513274691999
2023-01-22 17:24:50.881637: step: 360/530, loss: 0.0006564568029716611
2023-01-22 17:24:51.939951: step: 364/530, loss: 0.0011546405730769038
2023-01-22 17:24:53.001097: step: 368/530, loss: 0.0066480194218456745
2023-01-22 17:24:54.054032: step: 372/530, loss: 0.001040980452671647
2023-01-22 17:24:55.119895: step: 376/530, loss: 0.0015139712486416101
2023-01-22 17:24:56.168896: step: 380/530, loss: 0.004264846444129944
2023-01-22 17:24:57.225968: step: 384/530, loss: 0.002495660213753581
2023-01-22 17:24:58.277886: step: 388/530, loss: 0.001489577116444707
2023-01-22 17:24:59.320130: step: 392/530, loss: 0.0006889705546200275
2023-01-22 17:25:00.369388: step: 396/530, loss: 1.6155940102180466e-05
2023-01-22 17:25:01.410147: step: 400/530, loss: 0.0027616501320153475
2023-01-22 17:25:02.493986: step: 404/530, loss: 0.0005016099312342703
2023-01-22 17:25:03.535891: step: 408/530, loss: 5.982349466648884e-05
2023-01-22 17:25:04.577436: step: 412/530, loss: 0.0021680383943021297
2023-01-22 17:25:05.628424: step: 416/530, loss: 0.0008663540938869119
2023-01-22 17:25:06.667628: step: 420/530, loss: 0.004597248509526253
2023-01-22 17:25:07.718360: step: 424/530, loss: 0.02016008272767067
2023-01-22 17:25:08.782419: step: 428/530, loss: 0.0061422428116202354
2023-01-22 17:25:09.837351: step: 432/530, loss: 0.0020309591200202703
2023-01-22 17:25:10.881926: step: 436/530, loss: 0.0007287589833140373
2023-01-22 17:25:11.932355: step: 440/530, loss: 0.00010903603833867237
2023-01-22 17:25:12.982673: step: 444/530, loss: 0.0007346912170760334
2023-01-22 17:25:14.018052: step: 448/530, loss: 8.541832357877865e-05
2023-01-22 17:25:15.058965: step: 452/530, loss: 0.0005568701890297234
2023-01-22 17:25:16.109073: step: 456/530, loss: 0.002599509200081229
2023-01-22 17:25:17.145030: step: 460/530, loss: 0.006765200290828943
2023-01-22 17:25:18.199837: step: 464/530, loss: 0.004038615617901087
2023-01-22 17:25:19.264823: step: 468/530, loss: 0.0026833934243768454
2023-01-22 17:25:20.308861: step: 472/530, loss: 8.310659904964268e-05
2023-01-22 17:25:21.356758: step: 476/530, loss: 0.0036551819648593664
2023-01-22 17:25:22.416968: step: 480/530, loss: 0.0007989761070348322
2023-01-22 17:25:23.460608: step: 484/530, loss: 0.0016497164033353329
2023-01-22 17:25:24.515740: step: 488/530, loss: 0.009886185638606548
2023-01-22 17:25:25.563047: step: 492/530, loss: 0.0048872074112296104
2023-01-22 17:25:26.608647: step: 496/530, loss: 0.005567581858485937
2023-01-22 17:25:27.673780: step: 500/530, loss: 0.005139694083482027
2023-01-22 17:25:28.723549: step: 504/530, loss: 2.5667219233582728e-05
2023-01-22 17:25:29.768060: step: 508/530, loss: 0.00192461593542248
2023-01-22 17:25:30.817941: step: 512/530, loss: 0.00033468438778072596
2023-01-22 17:25:31.849796: step: 516/530, loss: 0.00022340647410601377
2023-01-22 17:25:32.885616: step: 520/530, loss: 0.0
2023-01-22 17:25:33.930475: step: 524/530, loss: 0.00043057568836957216
2023-01-22 17:25:34.990474: step: 528/530, loss: 0.008411814458668232
2023-01-22 17:25:36.039554: step: 532/530, loss: 0.001558232237584889
2023-01-22 17:25:37.093795: step: 536/530, loss: 0.00020881154341623187
2023-01-22 17:25:38.162387: step: 540/530, loss: 0.0002815257175825536
2023-01-22 17:25:39.215053: step: 544/530, loss: 0.004458381794393063
2023-01-22 17:25:40.270607: step: 548/530, loss: 0.0006919911247678101
2023-01-22 17:25:41.324161: step: 552/530, loss: 0.0032196755055338144
2023-01-22 17:25:42.395049: step: 556/530, loss: 0.014050937257707119
2023-01-22 17:25:43.427310: step: 560/530, loss: 0.00042544055031612515
2023-01-22 17:25:44.474353: step: 564/530, loss: 0.0019391147652640939
2023-01-22 17:25:45.508809: step: 568/530, loss: 0.006159898359328508
2023-01-22 17:25:46.542940: step: 572/530, loss: 4.290868673706427e-05
2023-01-22 17:25:47.593514: step: 576/530, loss: 0.02716648392379284
2023-01-22 17:25:48.639834: step: 580/530, loss: 0.004047059919685125
2023-01-22 17:25:49.686734: step: 584/530, loss: 0.030086390674114227
2023-01-22 17:25:50.795470: step: 588/530, loss: 0.006701093167066574
2023-01-22 17:25:51.835392: step: 592/530, loss: 0.010631301440298557
2023-01-22 17:25:52.892536: step: 596/530, loss: 0.0011468518059700727
2023-01-22 17:25:53.960689: step: 600/530, loss: 0.00012781946861650795
2023-01-22 17:25:55.007368: step: 604/530, loss: 0.0058357068337500095
2023-01-22 17:25:56.071579: step: 608/530, loss: 0.005029411055147648
2023-01-22 17:25:57.121829: step: 612/530, loss: 0.0014399680076166987
2023-01-22 17:25:58.178400: step: 616/530, loss: 0.022985175251960754
2023-01-22 17:25:59.217654: step: 620/530, loss: 0.0028079496696591377
2023-01-22 17:26:00.263206: step: 624/530, loss: 0.00388165982440114
2023-01-22 17:26:01.320981: step: 628/530, loss: 0.004202249925583601
2023-01-22 17:26:02.358487: step: 632/530, loss: 9.889141074381769e-05
2023-01-22 17:26:03.423004: step: 636/530, loss: 0.0028493842110037804
2023-01-22 17:26:04.464004: step: 640/530, loss: 0.013812733814120293
2023-01-22 17:26:05.515597: step: 644/530, loss: 0.0009513215045444667
2023-01-22 17:26:06.566739: step: 648/530, loss: 0.006368516478687525
2023-01-22 17:26:07.603819: step: 652/530, loss: 0.0006524188793264329
2023-01-22 17:26:08.659617: step: 656/530, loss: 0.0005199095467105508
2023-01-22 17:26:09.690498: step: 660/530, loss: 0.0009050218504853547
2023-01-22 17:26:10.723341: step: 664/530, loss: 0.0006994634750299156
2023-01-22 17:26:11.758187: step: 668/530, loss: 0.03267935663461685
2023-01-22 17:26:12.803448: step: 672/530, loss: 0.004737501032650471
2023-01-22 17:26:13.856246: step: 676/530, loss: 0.009582619182765484
2023-01-22 17:26:14.901715: step: 680/530, loss: 0.0015747654251754284
2023-01-22 17:26:15.952222: step: 684/530, loss: 0.00012585647345986217
2023-01-22 17:26:17.000478: step: 688/530, loss: 5.6749038776615635e-05
2023-01-22 17:26:18.048047: step: 692/530, loss: 0.002744994591921568
2023-01-22 17:26:19.100367: step: 696/530, loss: 0.00013972545275464654
2023-01-22 17:26:20.148505: step: 700/530, loss: 0.002954637398943305
2023-01-22 17:26:21.203341: step: 704/530, loss: 0.0026447754353284836
2023-01-22 17:26:22.259015: step: 708/530, loss: 0.0026327811647206545
2023-01-22 17:26:23.314070: step: 712/530, loss: 0.0020958720706403255
2023-01-22 17:26:24.353786: step: 716/530, loss: 0.0012459418503567576
2023-01-22 17:26:25.387110: step: 720/530, loss: 0.004910951945930719
2023-01-22 17:26:26.438620: step: 724/530, loss: 0.0011317277094349265
2023-01-22 17:26:27.484872: step: 728/530, loss: 0.0038981973193585873
2023-01-22 17:26:28.528804: step: 732/530, loss: 0.0024162873160094023
2023-01-22 17:26:29.561328: step: 736/530, loss: 0.002626921283081174
2023-01-22 17:26:30.599406: step: 740/530, loss: 5.8769681345438585e-05
2023-01-22 17:26:31.645543: step: 744/530, loss: 3.639415126599488e-06
2023-01-22 17:26:32.685880: step: 748/530, loss: 0.003267729887738824
2023-01-22 17:26:33.725776: step: 752/530, loss: 0.0011516103986650705
2023-01-22 17:26:34.784637: step: 756/530, loss: 0.008302648551762104
2023-01-22 17:26:35.833141: step: 760/530, loss: 0.002034844597801566
2023-01-22 17:26:36.883684: step: 764/530, loss: 0.0019169322913512588
2023-01-22 17:26:37.917397: step: 768/530, loss: 0.0002494501241017133
2023-01-22 17:26:38.995925: step: 772/530, loss: 0.0040806373581290245
2023-01-22 17:26:40.055557: step: 776/530, loss: 0.002027878537774086
2023-01-22 17:26:41.113456: step: 780/530, loss: 0.00392110412940383
2023-01-22 17:26:42.173076: step: 784/530, loss: 0.0017771513666957617
2023-01-22 17:26:43.240407: step: 788/530, loss: 0.0020230517257004976
2023-01-22 17:26:44.305339: step: 792/530, loss: 0.0038418262265622616
2023-01-22 17:26:45.376671: step: 796/530, loss: 0.0003984452341683209
2023-01-22 17:26:46.422633: step: 800/530, loss: 0.0006332120974548161
2023-01-22 17:26:47.460293: step: 804/530, loss: 0.0005243832711130381
2023-01-22 17:26:48.504497: step: 808/530, loss: 0.0011281610932201147
2023-01-22 17:26:49.537042: step: 812/530, loss: 0.00019324151799082756
2023-01-22 17:26:50.592003: step: 816/530, loss: 0.003829157678410411
2023-01-22 17:26:51.645841: step: 820/530, loss: 0.0007295019458979368
2023-01-22 17:26:52.685366: step: 824/530, loss: 0.000566175440326333
2023-01-22 17:26:53.737568: step: 828/530, loss: 2.1496136923815357e-06
2023-01-22 17:26:54.797296: step: 832/530, loss: 0.004715491086244583
2023-01-22 17:26:55.879975: step: 836/530, loss: 0.0002592035452835262
2023-01-22 17:26:56.940786: step: 840/530, loss: 0.005107673816382885
2023-01-22 17:26:57.985267: step: 844/530, loss: 1.848885767685715e-05
2023-01-22 17:26:59.030842: step: 848/530, loss: 0.018713941797614098
2023-01-22 17:27:00.084439: step: 852/530, loss: 0.00025651376927271485
2023-01-22 17:27:01.120703: step: 856/530, loss: 0.005111071281135082
2023-01-22 17:27:02.163325: step: 860/530, loss: 0.0030666294042021036
2023-01-22 17:27:03.225536: step: 864/530, loss: 7.297576303244568e-06
2023-01-22 17:27:04.276263: step: 868/530, loss: 6.415243842639029e-05
2023-01-22 17:27:05.320724: step: 872/530, loss: 2.8920791010023095e-05
2023-01-22 17:27:06.399671: step: 876/530, loss: 0.0132964001968503
2023-01-22 17:27:07.438167: step: 880/530, loss: 7.976187043823302e-05
2023-01-22 17:27:08.484845: step: 884/530, loss: 0.0013392781838774681
2023-01-22 17:27:09.530561: step: 888/530, loss: 0.00027853852952830493
2023-01-22 17:27:10.574709: step: 892/530, loss: 0.00486866245046258
2023-01-22 17:27:11.600039: step: 896/530, loss: 0.00013463993673212826
2023-01-22 17:27:12.635916: step: 900/530, loss: 0.00016759242862462997
2023-01-22 17:27:13.669541: step: 904/530, loss: 0.0003341655246913433
2023-01-22 17:27:14.724058: step: 908/530, loss: 0.013280771672725677
2023-01-22 17:27:15.789801: step: 912/530, loss: 0.0018408300820738077
2023-01-22 17:27:16.817418: step: 916/530, loss: 0.0037589133717119694
2023-01-22 17:27:17.871933: step: 920/530, loss: 0.00534787168726325
2023-01-22 17:27:18.911294: step: 924/530, loss: 0.005053365603089333
2023-01-22 17:27:19.942306: step: 928/530, loss: 0.006376977544277906
2023-01-22 17:27:20.996451: step: 932/530, loss: 0.0014519501710310578
2023-01-22 17:27:22.047896: step: 936/530, loss: 0.010115046985447407
2023-01-22 17:27:23.094529: step: 940/530, loss: 0.0023108532186597586
2023-01-22 17:27:24.142608: step: 944/530, loss: 0.002152229892089963
2023-01-22 17:27:25.184451: step: 948/530, loss: 0.0024788787122815847
2023-01-22 17:27:26.228188: step: 952/530, loss: 0.0013619255041703582
2023-01-22 17:27:27.271241: step: 956/530, loss: 0.000624710984993726
2023-01-22 17:27:28.312786: step: 960/530, loss: 0.00013595822383649647
2023-01-22 17:27:29.342659: step: 964/530, loss: 0.00014411963638849556
2023-01-22 17:27:30.410331: step: 968/530, loss: 0.0028496801387518644
2023-01-22 17:27:31.457916: step: 972/530, loss: 0.0010090307332575321
2023-01-22 17:27:32.489799: step: 976/530, loss: 3.6769513371837093e-06
2023-01-22 17:27:33.530710: step: 980/530, loss: 0.0012742517283186316
2023-01-22 17:27:34.561533: step: 984/530, loss: 2.5884797651087865e-05
2023-01-22 17:27:35.589807: step: 988/530, loss: 0.002917702542617917
2023-01-22 17:27:36.615715: step: 992/530, loss: 0.0004270431527402252
2023-01-22 17:27:37.676094: step: 996/530, loss: 0.007105897180736065
2023-01-22 17:27:38.726220: step: 1000/530, loss: 0.012625468894839287
2023-01-22 17:27:39.777094: step: 1004/530, loss: 0.0006448804051615298
2023-01-22 17:27:40.814930: step: 1008/530, loss: 8.455122952000238e-06
2023-01-22 17:27:41.857604: step: 1012/530, loss: 0.010775727219879627
2023-01-22 17:27:42.906523: step: 1016/530, loss: 0.015372917987406254
2023-01-22 17:27:43.968152: step: 1020/530, loss: 3.2752694096416235e-05
2023-01-22 17:27:45.005918: step: 1024/530, loss: 0.0005106040043756366
2023-01-22 17:27:46.051685: step: 1028/530, loss: 0.004319041967391968
2023-01-22 17:27:47.101297: step: 1032/530, loss: 0.0005803979001939297
2023-01-22 17:27:48.159352: step: 1036/530, loss: 0.007393084466457367
2023-01-22 17:27:49.204971: step: 1040/530, loss: 0.002379234414547682
2023-01-22 17:27:50.254824: step: 1044/530, loss: 1.481946947023971e-05
2023-01-22 17:27:51.299328: step: 1048/530, loss: 0.002936218399554491
2023-01-22 17:27:52.348347: step: 1052/530, loss: 0.00012736863573081791
2023-01-22 17:27:53.376044: step: 1056/530, loss: 0.0031776016112416983
2023-01-22 17:27:54.418343: step: 1060/530, loss: 0.0005582341109402478
2023-01-22 17:27:55.449111: step: 1064/530, loss: 7.450579597723106e-10
2023-01-22 17:27:56.515903: step: 1068/530, loss: 0.00015753437764942646
2023-01-22 17:27:57.580406: step: 1072/530, loss: 0.0001855352020356804
2023-01-22 17:27:58.618673: step: 1076/530, loss: 0.0002511170459911227
2023-01-22 17:27:59.672613: step: 1080/530, loss: 0.0008574594976380467
2023-01-22 17:28:00.753187: step: 1084/530, loss: 0.002710574772208929
2023-01-22 17:28:01.798363: step: 1088/530, loss: 0.002738569863140583
2023-01-22 17:28:02.853524: step: 1092/530, loss: 0.0011903155827894807
2023-01-22 17:28:03.898839: step: 1096/530, loss: 0.0020000950898975134
2023-01-22 17:28:04.944063: step: 1100/530, loss: 0.0005451919860206544
2023-01-22 17:28:05.992941: step: 1104/530, loss: 0.0007610819302499294
2023-01-22 17:28:07.053875: step: 1108/530, loss: 0.0018874533707275987
2023-01-22 17:28:08.098727: step: 1112/530, loss: 0.0027790465392172337
2023-01-22 17:28:09.141053: step: 1116/530, loss: 0.0008909351308830082
2023-01-22 17:28:10.172490: step: 1120/530, loss: 0.00036288020783104
2023-01-22 17:28:11.206956: step: 1124/530, loss: 0.00010466423555044457
2023-01-22 17:28:12.259459: step: 1128/530, loss: 0.0023218560963869095
2023-01-22 17:28:13.303793: step: 1132/530, loss: 0.0005401301896199584
2023-01-22 17:28:14.341336: step: 1136/530, loss: 0.012105298228561878
2023-01-22 17:28:15.395727: step: 1140/530, loss: 0.001272443332709372
2023-01-22 17:28:16.431062: step: 1144/530, loss: 9.497204700892325e-06
2023-01-22 17:28:17.482575: step: 1148/530, loss: 0.005656037945300341
2023-01-22 17:28:18.542007: step: 1152/530, loss: 2.7103656975668855e-05
2023-01-22 17:28:19.624982: step: 1156/530, loss: 0.0023644412867724895
2023-01-22 17:28:20.687138: step: 1160/530, loss: 0.0036779786460101604
2023-01-22 17:28:21.741975: step: 1164/530, loss: 3.727248986251652e-05
2023-01-22 17:28:22.808281: step: 1168/530, loss: 0.0007619143580086529
2023-01-22 17:28:23.854758: step: 1172/530, loss: 0.0024293025489896536
2023-01-22 17:28:24.890716: step: 1176/530, loss: 0.0017884676344692707
2023-01-22 17:28:25.931069: step: 1180/530, loss: 3.6654913060374383e-07
2023-01-22 17:28:27.000657: step: 1184/530, loss: 0.004959250334650278
2023-01-22 17:28:28.048251: step: 1188/530, loss: 6.564982322743163e-05
2023-01-22 17:28:29.131371: step: 1192/530, loss: 0.0008088112226687372
2023-01-22 17:28:30.194705: step: 1196/530, loss: 0.00635934341698885
2023-01-22 17:28:31.262140: step: 1200/530, loss: 0.0006574150756932795
2023-01-22 17:28:32.321793: step: 1204/530, loss: 0.004455378279089928
2023-01-22 17:28:33.404513: step: 1208/530, loss: 0.007044309284538031
2023-01-22 17:28:34.459129: step: 1212/530, loss: 0.0062496899627149105
2023-01-22 17:28:35.502917: step: 1216/530, loss: 0.0003697865759022534
2023-01-22 17:28:36.542083: step: 1220/530, loss: 0.003998305648565292
2023-01-22 17:28:37.596701: step: 1224/530, loss: 1.3274652701511513e-05
2023-01-22 17:28:38.648768: step: 1228/530, loss: 2.0823786144319456e-06
2023-01-22 17:28:39.694031: step: 1232/530, loss: 0.0029414610471576452
2023-01-22 17:28:40.743912: step: 1236/530, loss: 0.0066087194718420506
2023-01-22 17:28:41.786766: step: 1240/530, loss: 0.0093551529571414
2023-01-22 17:28:42.825268: step: 1244/530, loss: 4.7026074753375724e-05
2023-01-22 17:28:43.868314: step: 1248/530, loss: 0.0009934622794389725
2023-01-22 17:28:44.890831: step: 1252/530, loss: 0.0014768776018172503
2023-01-22 17:28:45.928759: step: 1256/530, loss: 0.005098074674606323
2023-01-22 17:28:46.983013: step: 1260/530, loss: 0.0029661257285624743
2023-01-22 17:28:48.044230: step: 1264/530, loss: 0.008504141122102737
2023-01-22 17:28:49.080050: step: 1268/530, loss: 0.007768355775624514
2023-01-22 17:28:50.114101: step: 1272/530, loss: 0.009733738377690315
2023-01-22 17:28:51.152193: step: 1276/530, loss: 0.006573773920536041
2023-01-22 17:28:52.206383: step: 1280/530, loss: 0.0030824884306639433
2023-01-22 17:28:53.247902: step: 1284/530, loss: 0.00023663269530516118
2023-01-22 17:28:54.309994: step: 1288/530, loss: 0.00348040834069252
2023-01-22 17:28:55.347128: step: 1292/530, loss: 0.0002557382686063647
2023-01-22 17:28:56.399155: step: 1296/530, loss: 0.0077478475868701935
2023-01-22 17:28:57.435026: step: 1300/530, loss: 3.6717724469781388e-06
2023-01-22 17:28:58.483278: step: 1304/530, loss: 0.01011281181126833
2023-01-22 17:28:59.524926: step: 1308/530, loss: 0.00012698242790065706
2023-01-22 17:29:00.572132: step: 1312/530, loss: 0.0010995978955179453
2023-01-22 17:29:01.620903: step: 1316/530, loss: 0.006591064855456352
2023-01-22 17:29:02.663695: step: 1320/530, loss: 0.0014081959379836917
2023-01-22 17:29:03.719749: step: 1324/530, loss: 0.00040577526669949293
2023-01-22 17:29:04.768712: step: 1328/530, loss: 0.00079535529948771
2023-01-22 17:29:05.807033: step: 1332/530, loss: 0.017213430255651474
2023-01-22 17:29:06.861256: step: 1336/530, loss: 0.003896152600646019
2023-01-22 17:29:07.904501: step: 1340/530, loss: 0.0015305011766031384
2023-01-22 17:29:08.959719: step: 1344/530, loss: 0.0011044359998777509
2023-01-22 17:29:10.020088: step: 1348/530, loss: 0.0010472419671714306
2023-01-22 17:29:11.057250: step: 1352/530, loss: 1.4220464436220936e-05
2023-01-22 17:29:12.106554: step: 1356/530, loss: 0.0015217718901112676
2023-01-22 17:29:13.157818: step: 1360/530, loss: 0.004007177427411079
2023-01-22 17:29:14.211936: step: 1364/530, loss: 0.0004316438571549952
2023-01-22 17:29:15.262836: step: 1368/530, loss: 2.871344804589171e-05
2023-01-22 17:29:16.295700: step: 1372/530, loss: 0.004065626300871372
2023-01-22 17:29:17.337618: step: 1376/530, loss: 0.0023687719367444515
2023-01-22 17:29:18.417390: step: 1380/530, loss: 0.020276281982660294
2023-01-22 17:29:19.481895: step: 1384/530, loss: 0.00659647723659873
2023-01-22 17:29:20.517307: step: 1388/530, loss: 0.0038783797062933445
2023-01-22 17:29:21.549506: step: 1392/530, loss: 0.00040550841367803514
2023-01-22 17:29:22.601513: step: 1396/530, loss: 0.0013393174158409238
2023-01-22 17:29:23.634344: step: 1400/530, loss: 0.0014298626920208335
2023-01-22 17:29:24.674164: step: 1404/530, loss: 0.0005542111466638744
2023-01-22 17:29:25.716543: step: 1408/530, loss: 0.000135309252073057
2023-01-22 17:29:26.776542: step: 1412/530, loss: 0.0005626199417747557
2023-01-22 17:29:27.829225: step: 1416/530, loss: 2.960778510896489e-05
2023-01-22 17:29:28.884298: step: 1420/530, loss: 0.0037976473104208708
2023-01-22 17:29:29.948752: step: 1424/530, loss: 0.001377007574774325
2023-01-22 17:29:30.989446: step: 1428/530, loss: 0.0018332034815102816
2023-01-22 17:29:32.054463: step: 1432/530, loss: 0.007953077554702759
2023-01-22 17:29:33.089820: step: 1436/530, loss: 0.0052063949406147
2023-01-22 17:29:34.142124: step: 1440/530, loss: 0.0015658732736483216
2023-01-22 17:29:35.188578: step: 1444/530, loss: 0.002678680932149291
2023-01-22 17:29:36.237747: step: 1448/530, loss: 0.00779002346098423
2023-01-22 17:29:37.260784: step: 1452/530, loss: 0.00023047183640301228
2023-01-22 17:29:38.301026: step: 1456/530, loss: 0.001487205969169736
2023-01-22 17:29:39.346904: step: 1460/530, loss: 0.0004775534034706652
2023-01-22 17:29:40.376066: step: 1464/530, loss: 0.0004770010127685964
2023-01-22 17:29:41.438156: step: 1468/530, loss: 0.006879845168441534
2023-01-22 17:29:42.489509: step: 1472/530, loss: 0.00727675249800086
2023-01-22 17:29:43.530884: step: 1476/530, loss: 0.0021079510916024446
2023-01-22 17:29:44.584371: step: 1480/530, loss: 0.00044240037095732987
2023-01-22 17:29:45.635462: step: 1484/530, loss: 0.024879442527890205
2023-01-22 17:29:46.667910: step: 1488/530, loss: 0.0005003334954380989
2023-01-22 17:29:47.698143: step: 1492/530, loss: 0.0004626781155820936
2023-01-22 17:29:48.745561: step: 1496/530, loss: 0.0029468259308487177
2023-01-22 17:29:49.776420: step: 1500/530, loss: 0.00016428811068180948
2023-01-22 17:29:50.813580: step: 1504/530, loss: 0.002816026797518134
2023-01-22 17:29:51.865486: step: 1508/530, loss: 0.002994521288201213
2023-01-22 17:29:52.920775: step: 1512/530, loss: 0.0026726245414465666
2023-01-22 17:29:53.968261: step: 1516/530, loss: 0.0006311832694336772
2023-01-22 17:29:55.021736: step: 1520/530, loss: 0.003284927923232317
2023-01-22 17:29:56.067497: step: 1524/530, loss: 0.00898159109055996
2023-01-22 17:29:57.126176: step: 1528/530, loss: 2.0823752322485234e-07
2023-01-22 17:29:58.192371: step: 1532/530, loss: 3.719169399118982e-05
2023-01-22 17:29:59.237728: step: 1536/530, loss: 0.0058005014434456825
2023-01-22 17:30:00.278098: step: 1540/530, loss: 0.0009148807148449123
2023-01-22 17:30:01.314685: step: 1544/530, loss: 0.0020848149433732033
2023-01-22 17:30:02.354457: step: 1548/530, loss: 0.0022066296078264713
2023-01-22 17:30:03.404201: step: 1552/530, loss: 0.0039602844044566154
2023-01-22 17:30:04.430738: step: 1556/530, loss: 0.0038585748989135027
2023-01-22 17:30:05.470981: step: 1560/530, loss: 7.122480747057125e-05
2023-01-22 17:30:06.533346: step: 1564/530, loss: 0.004375799093395472
2023-01-22 17:30:07.564211: step: 1568/530, loss: 0.00020374795712996274
2023-01-22 17:30:08.590644: step: 1572/530, loss: 0.0003176661266479641
2023-01-22 17:30:09.629705: step: 1576/530, loss: 0.0013383544282987714
2023-01-22 17:30:10.662270: step: 1580/530, loss: 0.001447192276827991
2023-01-22 17:30:11.707565: step: 1584/530, loss: 0.0007889055996201932
2023-01-22 17:30:12.766744: step: 1588/530, loss: 0.00020421612134668976
2023-01-22 17:30:13.808086: step: 1592/530, loss: 0.003952106926590204
2023-01-22 17:30:14.862606: step: 1596/530, loss: 0.006382076535373926
2023-01-22 17:30:15.905335: step: 1600/530, loss: 0.006570099852979183
2023-01-22 17:30:16.956326: step: 1604/530, loss: 0.015949079766869545
2023-01-22 17:30:18.001084: step: 1608/530, loss: 4.006120889243903e-06
2023-01-22 17:30:19.055718: step: 1612/530, loss: 0.00044259443529881537
2023-01-22 17:30:20.106630: step: 1616/530, loss: 0.005342657212167978
2023-01-22 17:30:21.148320: step: 1620/530, loss: 0.0004579670785460621
2023-01-22 17:30:22.186671: step: 1624/530, loss: 4.0859784348867834e-05
2023-01-22 17:30:23.233664: step: 1628/530, loss: 4.779320443049073e-05
2023-01-22 17:30:24.262186: step: 1632/530, loss: 0.005063971038907766
2023-01-22 17:30:25.306573: step: 1636/530, loss: 0.0002617494319565594
2023-01-22 17:30:26.346614: step: 1640/530, loss: 0.0023489685263484716
2023-01-22 17:30:27.419766: step: 1644/530, loss: 0.0011899148812517524
2023-01-22 17:30:28.458242: step: 1648/530, loss: 0.0027415677905082703
2023-01-22 17:30:29.499995: step: 1652/530, loss: 0.0017388095147907734
2023-01-22 17:30:30.576225: step: 1656/530, loss: 0.005948937032371759
2023-01-22 17:30:31.634980: step: 1660/530, loss: 0.00978368055075407
2023-01-22 17:30:32.669876: step: 1664/530, loss: 0.002595794154331088
2023-01-22 17:30:33.725018: step: 1668/530, loss: 0.002223603194579482
2023-01-22 17:30:34.781741: step: 1672/530, loss: 5.623222477879608e-06
2023-01-22 17:30:35.832032: step: 1676/530, loss: 8.900025568436831e-05
2023-01-22 17:30:36.898769: step: 1680/530, loss: 0.00045209366362541914
2023-01-22 17:30:37.939461: step: 1684/530, loss: 0.000723404111340642
2023-01-22 17:30:38.980165: step: 1688/530, loss: 0.00010239532275591046
2023-01-22 17:30:40.031072: step: 1692/530, loss: 0.0004662133869715035
2023-01-22 17:30:41.092922: step: 1696/530, loss: 0.0013345240149646997
2023-01-22 17:30:42.146995: step: 1700/530, loss: 0.0016835578717291355
2023-01-22 17:30:43.199362: step: 1704/530, loss: 0.004374376963824034
2023-01-22 17:30:44.230566: step: 1708/530, loss: 0.0007663400028832257
2023-01-22 17:30:45.306625: step: 1712/530, loss: 0.0030346272978931665
2023-01-22 17:30:46.350068: step: 1716/530, loss: 0.00024776384816505015
2023-01-22 17:30:47.391122: step: 1720/530, loss: 0.008117184974253178
2023-01-22 17:30:48.447419: step: 1724/530, loss: 0.0002365930558880791
2023-01-22 17:30:49.480481: step: 1728/530, loss: 0.00017739305621944368
2023-01-22 17:30:50.535143: step: 1732/530, loss: 0.0006980485050007701
2023-01-22 17:30:51.576486: step: 1736/530, loss: 0.00016968268027994782
2023-01-22 17:30:52.627816: step: 1740/530, loss: 1.7430177194910357e-06
2023-01-22 17:30:53.680288: step: 1744/530, loss: 0.00795839074999094
2023-01-22 17:30:54.728876: step: 1748/530, loss: 0.000318115227855742
2023-01-22 17:30:55.779253: step: 1752/530, loss: 2.864673547264829e-07
2023-01-22 17:30:56.820408: step: 1756/530, loss: 0.0045907762832939625
2023-01-22 17:30:57.854401: step: 1760/530, loss: 0.006999340374022722
2023-01-22 17:30:58.902361: step: 1764/530, loss: 0.003867608727887273
2023-01-22 17:30:59.950769: step: 1768/530, loss: 6.396664684871212e-05
2023-01-22 17:31:00.992022: step: 1772/530, loss: 6.110750837251544e-05
2023-01-22 17:31:02.028873: step: 1776/530, loss: 4.9452672101324424e-05
2023-01-22 17:31:03.078192: step: 1780/530, loss: 0.0018139004241675138
2023-01-22 17:31:04.120004: step: 1784/530, loss: 0.0018237457843497396
2023-01-22 17:31:05.188034: step: 1788/530, loss: 0.0001298043061979115
2023-01-22 17:31:06.234569: step: 1792/530, loss: 0.0010824294295161963
2023-01-22 17:31:07.278131: step: 1796/530, loss: 0.004212304949760437
2023-01-22 17:31:08.324411: step: 1800/530, loss: 0.0006548843230120838
2023-01-22 17:31:09.377256: step: 1804/530, loss: 0.001118526328355074
2023-01-22 17:31:10.414372: step: 1808/530, loss: 0.005350269842892885
2023-01-22 17:31:11.463333: step: 1812/530, loss: 0.000562014989554882
2023-01-22 17:31:12.494753: step: 1816/530, loss: 0.00014336747699417174
2023-01-22 17:31:13.540661: step: 1820/530, loss: 0.0007651003543287516
2023-01-22 17:31:14.589699: step: 1824/530, loss: 0.0036428223829716444
2023-01-22 17:31:15.650652: step: 1828/530, loss: 0.0010677709942683578
2023-01-22 17:31:16.696607: step: 1832/530, loss: 0.002514310646802187
2023-01-22 17:31:17.751434: step: 1836/530, loss: 0.007211413234472275
2023-01-22 17:31:18.804165: step: 1840/530, loss: 0.0011656152782961726
2023-01-22 17:31:19.857100: step: 1844/530, loss: 0.0015326207503676414
2023-01-22 17:31:20.907439: step: 1848/530, loss: 0.014549612067639828
2023-01-22 17:31:21.953320: step: 1852/530, loss: 0.004234924912452698
2023-01-22 17:31:22.980980: step: 1856/530, loss: 0.0012708451831713319
2023-01-22 17:31:24.023379: step: 1860/530, loss: 0.00010736639524111524
2023-01-22 17:31:25.063839: step: 1864/530, loss: 0.00038453502929769456
2023-01-22 17:31:26.109615: step: 1868/530, loss: 0.00033335923217236996
2023-01-22 17:31:27.171515: step: 1872/530, loss: 0.01160730142146349
2023-01-22 17:31:28.228642: step: 1876/530, loss: 0.0037386224139481783
2023-01-22 17:31:29.267263: step: 1880/530, loss: 0.0007540821679867804
2023-01-22 17:31:30.320281: step: 1884/530, loss: 0.0008770199492573738
2023-01-22 17:31:31.364572: step: 1888/530, loss: 0.00011683989578159526
2023-01-22 17:31:32.404245: step: 1892/530, loss: 0.0030918132979422808
2023-01-22 17:31:33.439753: step: 1896/530, loss: 0.0007490574498660862
2023-01-22 17:31:34.488743: step: 1900/530, loss: 0.010304059833288193
2023-01-22 17:31:35.513116: step: 1904/530, loss: 7.208468014141545e-05
2023-01-22 17:31:36.558878: step: 1908/530, loss: 0.001376252039335668
2023-01-22 17:31:37.613927: step: 1912/530, loss: 0.003604793455451727
2023-01-22 17:31:38.666576: step: 1916/530, loss: 0.00017001554078888148
2023-01-22 17:31:39.703939: step: 1920/530, loss: 0.002414959715679288
2023-01-22 17:31:40.730306: step: 1924/530, loss: 0.0002481439441908151
2023-01-22 17:31:41.755123: step: 1928/530, loss: 0.0007361792959272861
2023-01-22 17:31:42.794566: step: 1932/530, loss: 0.009654955007135868
2023-01-22 17:31:43.840277: step: 1936/530, loss: 0.010741261765360832
2023-01-22 17:31:44.899636: step: 1940/530, loss: 0.005340594798326492
2023-01-22 17:31:45.940034: step: 1944/530, loss: 0.00021494003885891289
2023-01-22 17:31:46.976884: step: 1948/530, loss: 7.968128193169832e-05
2023-01-22 17:31:48.011035: step: 1952/530, loss: 0.00030087080085650086
2023-01-22 17:31:49.063159: step: 1956/530, loss: 4.224270742270164e-05
2023-01-22 17:31:50.130429: step: 1960/530, loss: 0.0006958569283597171
2023-01-22 17:31:51.201225: step: 1964/530, loss: 0.006141295190900564
2023-01-22 17:31:52.239040: step: 1968/530, loss: 0.0004534491163212806
2023-01-22 17:31:53.291766: step: 1972/530, loss: 0.001550563727505505
2023-01-22 17:31:54.320385: step: 1976/530, loss: 0.0028260506223887205
2023-01-22 17:31:55.359255: step: 1980/530, loss: 0.000257304054684937
2023-01-22 17:31:56.403014: step: 1984/530, loss: 0.0008961333660408854
2023-01-22 17:31:57.454429: step: 1988/530, loss: 0.0019929525442421436
2023-01-22 17:31:58.498342: step: 1992/530, loss: 0.0027199238538742065
2023-01-22 17:31:59.556907: step: 1996/530, loss: 0.0005656854482367635
2023-01-22 17:32:00.581417: step: 2000/530, loss: 0.0019591753371059895
2023-01-22 17:32:01.622822: step: 2004/530, loss: 0.001346637844108045
2023-01-22 17:32:02.652075: step: 2008/530, loss: 0.0040557608008384705
2023-01-22 17:32:03.718414: step: 2012/530, loss: 0.0010384107008576393
2023-01-22 17:32:04.785074: step: 2016/530, loss: 0.000618373800534755
2023-01-22 17:32:05.815288: step: 2020/530, loss: 0.004166426602751017
2023-01-22 17:32:06.852139: step: 2024/530, loss: 3.0647854146081954e-05
2023-01-22 17:32:07.902693: step: 2028/530, loss: 0.0025109269190579653
2023-01-22 17:32:08.955755: step: 2032/530, loss: 0.009793415665626526
2023-01-22 17:32:09.991855: step: 2036/530, loss: 0.0012217836920171976
2023-01-22 17:32:11.032689: step: 2040/530, loss: 0.013063976541161537
2023-01-22 17:32:12.082640: step: 2044/530, loss: 0.011299300007522106
2023-01-22 17:32:13.108469: step: 2048/530, loss: 0.0023629171773791313
2023-01-22 17:32:14.156951: step: 2052/530, loss: 4.836311563849449e-05
2023-01-22 17:32:15.205619: step: 2056/530, loss: 0.0007346873753704131
2023-01-22 17:32:16.255777: step: 2060/530, loss: 0.0003823303268291056
2023-01-22 17:32:17.302651: step: 2064/530, loss: 0.009841508232057095
2023-01-22 17:32:18.355427: step: 2068/530, loss: 0.005745592061430216
2023-01-22 17:32:19.426893: step: 2072/530, loss: 0.0028223213739693165
2023-01-22 17:32:20.479329: step: 2076/530, loss: 0.001286366255953908
2023-01-22 17:32:21.526661: step: 2080/530, loss: 0.005680242087692022
2023-01-22 17:32:22.584698: step: 2084/530, loss: 0.007327405735850334
2023-01-22 17:32:23.620335: step: 2088/530, loss: 0.002581064123660326
2023-01-22 17:32:24.689102: step: 2092/530, loss: 0.0060972184874117374
2023-01-22 17:32:25.739655: step: 2096/530, loss: 0.010546141304075718
2023-01-22 17:32:26.780406: step: 2100/530, loss: 0.003040348645299673
2023-01-22 17:32:27.828669: step: 2104/530, loss: 0.00012009617785224691
2023-01-22 17:32:28.877965: step: 2108/530, loss: 0.0007949028513394296
2023-01-22 17:32:29.924492: step: 2112/530, loss: 0.005056140013039112
2023-01-22 17:32:30.968635: step: 2116/530, loss: 0.005843624472618103
2023-01-22 17:32:32.035094: step: 2120/530, loss: 0.030014971271157265
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33994781312127237, 'r': 0.32446631878557874, 'f1': 0.33202669902912624}, 'combined': 0.24465125191619827, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3579467319895116, 'r': 0.4082829911755367, 'f1': 0.3814614808063408}, 'combined': 0.29567827698864696, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30864026630719177, 'r': 0.3197677142385706, 'f1': 0.3141054713955764}, 'combined': 0.2314461368177931, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573759697774976, 'r': 0.4076319655274582, 'f1': 0.3808532232665303}, 'combined': 0.2952068046372149, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3292694915137107, 'r': 0.33989108801415296, 'f1': 0.3344959913790077}, 'combined': 0.24647073048979515, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3552814057270258, 'r': 0.38565012882685434, 'f1': 0.369843402524123}, 'combined': 0.2866728765976456, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3462223895582329, 'r': 0.3271703036053131, 'f1': 0.33642682926829265}, 'combined': 0.24789345314505773, 'stategy': 1, 'epoch': 15}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.360310988924254, 'r': 0.40667453529318376, 'f1': 0.3820914459404006}, 'combined': 0.2961665753222244, 'stategy': 1, 'epoch': 15}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 15}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 18
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:35:02.020502: step: 4/530, loss: 0.0011004514526575804
2023-01-22 17:35:03.061900: step: 8/530, loss: 0.0015485460171476007
2023-01-22 17:35:04.127003: step: 12/530, loss: 0.004476394969969988
2023-01-22 17:35:05.161087: step: 16/530, loss: 0.0007204785943031311
2023-01-22 17:35:06.192024: step: 20/530, loss: 0.0021424717269837856
2023-01-22 17:35:07.221522: step: 24/530, loss: 0.0010343339527025819
2023-01-22 17:35:08.257658: step: 28/530, loss: 0.00013786889030598104
2023-01-22 17:35:09.298364: step: 32/530, loss: 0.0020042869728058577
2023-01-22 17:35:10.332631: step: 36/530, loss: 9.873901581158862e-05
2023-01-22 17:35:11.380018: step: 40/530, loss: 0.0003586667007766664
2023-01-22 17:35:12.412416: step: 44/530, loss: 0.0003571257402654737
2023-01-22 17:35:13.449768: step: 48/530, loss: 0.005025750026106834
2023-01-22 17:35:14.478320: step: 52/530, loss: 0.0014080420369282365
2023-01-22 17:35:15.533874: step: 56/530, loss: 0.0006306511932052672
2023-01-22 17:35:16.592434: step: 60/530, loss: 0.0035294953268021345
2023-01-22 17:35:17.624048: step: 64/530, loss: 0.0007785228081047535
2023-01-22 17:35:18.667894: step: 68/530, loss: 0.0005311129498295486
2023-01-22 17:35:19.732162: step: 72/530, loss: 6.244205724215135e-05
2023-01-22 17:35:20.768540: step: 76/530, loss: 0.0004511222941800952
2023-01-22 17:35:21.816134: step: 80/530, loss: 0.003255607094615698
2023-01-22 17:35:22.848747: step: 84/530, loss: 0.0001986724091693759
2023-01-22 17:35:23.899723: step: 88/530, loss: 0.00021972335525788367
2023-01-22 17:35:24.943845: step: 92/530, loss: 0.003665995318442583
2023-01-22 17:35:25.983269: step: 96/530, loss: 0.006084507331252098
2023-01-22 17:35:27.031461: step: 100/530, loss: 0.003251165384426713
2023-01-22 17:35:28.074658: step: 104/530, loss: 0.0005306070088408887
2023-01-22 17:35:29.121413: step: 108/530, loss: 0.0014637029962614179
2023-01-22 17:35:30.192100: step: 112/530, loss: 0.00017656983982305974
2023-01-22 17:35:31.236440: step: 116/530, loss: 0.005251055583357811
2023-01-22 17:35:32.281119: step: 120/530, loss: 0.0030476185493171215
2023-01-22 17:35:33.332837: step: 124/530, loss: 0.0013223965652287006
2023-01-22 17:35:34.369319: step: 128/530, loss: 0.003072301624342799
2023-01-22 17:35:35.405086: step: 132/530, loss: 0.0011979241389781237
2023-01-22 17:35:36.433400: step: 136/530, loss: 0.0
2023-01-22 17:35:37.469058: step: 140/530, loss: 0.0008933464996516705
2023-01-22 17:35:38.521415: step: 144/530, loss: 0.003278773743659258
2023-01-22 17:35:39.587514: step: 148/530, loss: 0.02431190386414528
2023-01-22 17:35:40.632234: step: 152/530, loss: 0.003205099841579795
2023-01-22 17:35:41.681742: step: 156/530, loss: 0.006427126005291939
2023-01-22 17:35:42.725390: step: 160/530, loss: 0.0006028419593349099
2023-01-22 17:35:43.769295: step: 164/530, loss: 0.0026085705030709505
2023-01-22 17:35:44.815451: step: 168/530, loss: 0.007286405190825462
2023-01-22 17:35:45.843173: step: 172/530, loss: 0.003637277288362384
2023-01-22 17:35:46.896638: step: 176/530, loss: 0.015096787363290787
2023-01-22 17:35:47.953153: step: 180/530, loss: 0.002204600954428315
2023-01-22 17:35:48.999767: step: 184/530, loss: 0.0010545180412009358
2023-01-22 17:35:50.041818: step: 188/530, loss: 0.00032845730311237276
2023-01-22 17:35:51.087493: step: 192/530, loss: 0.007657136768102646
2023-01-22 17:35:52.132007: step: 196/530, loss: 0.0009592468850314617
2023-01-22 17:35:53.176929: step: 200/530, loss: 0.0003860020078718662
2023-01-22 17:35:54.235307: step: 204/530, loss: 0.00011319531040498987
2023-01-22 17:35:55.282832: step: 208/530, loss: 0.002827430609613657
2023-01-22 17:35:56.343148: step: 212/530, loss: 0.001291204709559679
2023-01-22 17:35:57.380702: step: 216/530, loss: 0.006179413292557001
2023-01-22 17:35:58.427699: step: 220/530, loss: 0.0010054472368210554
2023-01-22 17:35:59.470123: step: 224/530, loss: 0.002646689536049962
2023-01-22 17:36:00.529208: step: 228/530, loss: 0.0005621419404633343
2023-01-22 17:36:01.582847: step: 232/530, loss: 0.007815116085112095
2023-01-22 17:36:02.624446: step: 236/530, loss: 0.02903848886489868
2023-01-22 17:36:03.668283: step: 240/530, loss: 3.8449732528533787e-05
2023-01-22 17:36:04.734865: step: 244/530, loss: 0.002362427767366171
2023-01-22 17:36:05.786511: step: 248/530, loss: 0.00012775677896570414
2023-01-22 17:36:06.824079: step: 252/530, loss: 0.0031440667808055878
2023-01-22 17:36:07.866298: step: 256/530, loss: 0.0001841807534219697
2023-01-22 17:36:08.907501: step: 260/530, loss: 0.0024066418409347534
2023-01-22 17:36:09.956727: step: 264/530, loss: 1.691768193268217e-05
2023-01-22 17:36:10.992953: step: 268/530, loss: 0.0007133395993150771
2023-01-22 17:36:12.063193: step: 272/530, loss: 0.0034632175229489803
2023-01-22 17:36:13.112431: step: 276/530, loss: 0.001298890681937337
2023-01-22 17:36:14.157364: step: 280/530, loss: 0.0002496509987395257
2023-01-22 17:36:15.262707: step: 284/530, loss: 0.001698222360573709
2023-01-22 17:36:16.331215: step: 288/530, loss: 1.8486880435375497e-05
2023-01-22 17:36:17.376549: step: 292/530, loss: 0.004569863434880972
2023-01-22 17:36:18.440726: step: 296/530, loss: 0.0034067442175000906
2023-01-22 17:36:19.498988: step: 300/530, loss: 0.0033893371000885963
2023-01-22 17:36:20.556328: step: 304/530, loss: 0.0003980577166657895
2023-01-22 17:36:21.611718: step: 308/530, loss: 0.0017462796531617641
2023-01-22 17:36:22.645059: step: 312/530, loss: 0.0014805826358497143
2023-01-22 17:36:23.701173: step: 316/530, loss: 0.003357308218255639
2023-01-22 17:36:24.760758: step: 320/530, loss: 0.0020128062460571527
2023-01-22 17:36:25.817914: step: 324/530, loss: 0.0026554614305496216
2023-01-22 17:36:26.874767: step: 328/530, loss: 0.00028746630414389074
2023-01-22 17:36:27.918333: step: 332/530, loss: 0.0010810262756422162
2023-01-22 17:36:28.981537: step: 336/530, loss: 0.003787329187616706
2023-01-22 17:36:30.003199: step: 340/530, loss: 0.00011475924111437052
2023-01-22 17:36:31.054643: step: 344/530, loss: 0.002529539866372943
2023-01-22 17:36:32.101798: step: 348/530, loss: 0.0013885658700019121
2023-01-22 17:36:33.163695: step: 352/530, loss: 0.00025244380231015384
2023-01-22 17:36:34.216235: step: 356/530, loss: 4.8076704842969775e-05
2023-01-22 17:36:35.262775: step: 360/530, loss: 5.0577531510498375e-05
2023-01-22 17:36:36.306998: step: 364/530, loss: 0.003146706148982048
2023-01-22 17:36:37.369534: step: 368/530, loss: 0.002765948185697198
2023-01-22 17:36:38.441479: step: 372/530, loss: 0.019216468557715416
2023-01-22 17:36:39.496634: step: 376/530, loss: 0.0019286295864731073
2023-01-22 17:36:40.541489: step: 380/530, loss: 0.020308448001742363
2023-01-22 17:36:41.579778: step: 384/530, loss: 0.0008033043704926968
2023-01-22 17:36:42.642696: step: 388/530, loss: 0.0004372689872980118
2023-01-22 17:36:43.692908: step: 392/530, loss: 0.0022435521241277456
2023-01-22 17:36:44.735866: step: 396/530, loss: 0.0028211530297994614
2023-01-22 17:36:45.796218: step: 400/530, loss: 0.0020552356727421284
2023-01-22 17:36:46.848072: step: 404/530, loss: 0.020023638382554054
2023-01-22 17:36:47.881534: step: 408/530, loss: 0.003318340750411153
2023-01-22 17:36:48.933196: step: 412/530, loss: 9.33839510253165e-06
2023-01-22 17:36:49.982023: step: 416/530, loss: 0.0015107261715456843
2023-01-22 17:36:51.035248: step: 420/530, loss: 0.0017514704959467053
2023-01-22 17:36:52.085572: step: 424/530, loss: 0.004567578434944153
2023-01-22 17:36:53.132422: step: 428/530, loss: 0.0007843594648875296
2023-01-22 17:36:54.179826: step: 432/530, loss: 1.6937028703978285e-05
2023-01-22 17:36:55.238941: step: 436/530, loss: 0.007142952643334866
2023-01-22 17:36:56.271683: step: 440/530, loss: 0.006755193695425987
2023-01-22 17:36:57.337270: step: 444/530, loss: 0.0008685367647558451
2023-01-22 17:36:58.375263: step: 448/530, loss: 6.131079862825572e-05
2023-01-22 17:36:59.439038: step: 452/530, loss: 0.0010961712105199695
2023-01-22 17:37:00.480049: step: 456/530, loss: 0.0023356121964752674
2023-01-22 17:37:01.518845: step: 460/530, loss: 0.004038605373352766
2023-01-22 17:37:02.571924: step: 464/530, loss: 9.342426346847787e-05
2023-01-22 17:37:03.644195: step: 468/530, loss: 0.0017812468577176332
2023-01-22 17:37:04.682512: step: 472/530, loss: 0.002060752362012863
2023-01-22 17:37:05.760520: step: 476/530, loss: 0.016233494505286217
2023-01-22 17:37:06.801113: step: 480/530, loss: 0.002346508903428912
2023-01-22 17:37:07.851838: step: 484/530, loss: 0.003929595462977886
2023-01-22 17:37:08.908792: step: 488/530, loss: 4.709040240413742e-06
2023-01-22 17:37:09.966801: step: 492/530, loss: 0.0031084208749234676
2023-01-22 17:37:11.030595: step: 496/530, loss: 0.0015573048731312156
2023-01-22 17:37:12.079331: step: 500/530, loss: 0.0
2023-01-22 17:37:13.119027: step: 504/530, loss: 0.010353624820709229
2023-01-22 17:37:14.165164: step: 508/530, loss: 0.0030232262797653675
2023-01-22 17:37:15.201786: step: 512/530, loss: 3.566694795154035e-05
2023-01-22 17:37:16.241168: step: 516/530, loss: 0.00011833704047603533
2023-01-22 17:37:17.285071: step: 520/530, loss: 0.00042011140612885356
2023-01-22 17:37:18.347559: step: 524/530, loss: 0.004647030029445887
2023-01-22 17:37:19.409119: step: 528/530, loss: 0.003184481291100383
2023-01-22 17:37:20.467654: step: 532/530, loss: 0.006225524935871363
2023-01-22 17:37:21.512877: step: 536/530, loss: 1.5952678950270638e-05
2023-01-22 17:37:22.571459: step: 540/530, loss: 0.0018279047217220068
2023-01-22 17:37:23.646762: step: 544/530, loss: 0.0007364078774116933
2023-01-22 17:37:24.687353: step: 548/530, loss: 0.0005492193740792572
2023-01-22 17:37:25.749215: step: 552/530, loss: 0.00013014712021686137
2023-01-22 17:37:26.792040: step: 556/530, loss: 0.0002371767332078889
2023-01-22 17:37:27.858027: step: 560/530, loss: 0.004101587459445
2023-01-22 17:37:28.919117: step: 564/530, loss: 0.0008924608118832111
2023-01-22 17:37:29.983732: step: 568/530, loss: 0.005209341645240784
2023-01-22 17:37:31.047166: step: 572/530, loss: 0.0003104804491158575
2023-01-22 17:37:32.098252: step: 576/530, loss: 0.001576914801262319
2023-01-22 17:37:33.162318: step: 580/530, loss: 0.012157829478383064
2023-01-22 17:37:34.189331: step: 584/530, loss: 0.0005354807362891734
2023-01-22 17:37:35.248766: step: 588/530, loss: 0.001497014076448977
2023-01-22 17:37:36.296675: step: 592/530, loss: 0.00017277183360420167
2023-01-22 17:37:37.336014: step: 596/530, loss: 0.00026166453608311713
2023-01-22 17:37:38.369235: step: 600/530, loss: 8.671941759530455e-05
2023-01-22 17:37:39.426179: step: 604/530, loss: 0.0006945659406483173
2023-01-22 17:37:40.477239: step: 608/530, loss: 0.0021995774004608393
2023-01-22 17:37:41.525443: step: 612/530, loss: 0.0015054685063660145
2023-01-22 17:37:42.567511: step: 616/530, loss: 0.004471979103982449
2023-01-22 17:37:43.615579: step: 620/530, loss: 0.0004085471446160227
2023-01-22 17:37:44.681045: step: 624/530, loss: 0.027030890807509422
2023-01-22 17:37:45.737479: step: 628/530, loss: 0.0006588977412320673
2023-01-22 17:37:46.786998: step: 632/530, loss: 0.001884608413092792
2023-01-22 17:37:47.828263: step: 636/530, loss: 0.0035075899213552475
2023-01-22 17:37:48.875970: step: 640/530, loss: 0.0033492667134851217
2023-01-22 17:37:49.910616: step: 644/530, loss: 9.604650404071435e-05
2023-01-22 17:37:50.951624: step: 648/530, loss: 0.0001633965439395979
2023-01-22 17:37:52.004377: step: 652/530, loss: 0.015823418274521828
2023-01-22 17:37:53.036394: step: 656/530, loss: 0.0025312898214906454
2023-01-22 17:37:54.104646: step: 660/530, loss: 0.0014884265838190913
2023-01-22 17:37:55.147496: step: 664/530, loss: 0.011327198706567287
2023-01-22 17:37:56.191519: step: 668/530, loss: 0.00017987831961363554
2023-01-22 17:37:57.237922: step: 672/530, loss: 0.001282813143916428
2023-01-22 17:37:58.282437: step: 676/530, loss: 0.0002611135132610798
2023-01-22 17:37:59.340745: step: 680/530, loss: 0.00012419302947819233
2023-01-22 17:38:00.386081: step: 684/530, loss: 0.00012041210720781237
2023-01-22 17:38:01.432605: step: 688/530, loss: 0.010376348160207272
2023-01-22 17:38:02.468688: step: 692/530, loss: 0.000801779911853373
2023-01-22 17:38:03.516057: step: 696/530, loss: 0.0016834231792017817
2023-01-22 17:38:04.552931: step: 700/530, loss: 6.791386840632185e-05
2023-01-22 17:38:05.583069: step: 704/530, loss: 0.0006431415094994009
2023-01-22 17:38:06.627690: step: 708/530, loss: 0.0027060690335929394
2023-01-22 17:38:07.676087: step: 712/530, loss: 0.0005142366862855852
2023-01-22 17:38:08.731439: step: 716/530, loss: 3.365147495060228e-05
2023-01-22 17:38:09.784915: step: 720/530, loss: 4.157410148764029e-05
2023-01-22 17:38:10.838659: step: 724/530, loss: 0.0019096104661002755
2023-01-22 17:38:11.878135: step: 728/530, loss: 0.005891962442547083
2023-01-22 17:38:12.920816: step: 732/530, loss: 0.004786570090800524
2023-01-22 17:38:13.959836: step: 736/530, loss: 0.0018507546046748757
2023-01-22 17:38:15.000399: step: 740/530, loss: 0.002836151747033
2023-01-22 17:38:16.055476: step: 744/530, loss: 9.455605322727934e-05
2023-01-22 17:38:17.098190: step: 748/530, loss: 0.0007701213471591473
2023-01-22 17:38:18.144364: step: 752/530, loss: 0.0030247115064412355
2023-01-22 17:38:19.208395: step: 756/530, loss: 0.00036444346187636256
2023-01-22 17:38:20.245769: step: 760/530, loss: 0.005743666086345911
2023-01-22 17:38:21.315635: step: 764/530, loss: 0.0004152635810896754
2023-01-22 17:38:22.349846: step: 768/530, loss: 0.000717329268809408
2023-01-22 17:38:23.383952: step: 772/530, loss: 0.005131026729941368
2023-01-22 17:38:24.426877: step: 776/530, loss: 0.004881407134234905
2023-01-22 17:38:25.464005: step: 780/530, loss: 0.0005614030524156988
2023-01-22 17:38:26.515212: step: 784/530, loss: 8.126455213641748e-05
2023-01-22 17:38:27.553540: step: 788/530, loss: 5.395114840212045e-06
2023-01-22 17:38:28.583650: step: 792/530, loss: 0.0017774271545931697
2023-01-22 17:38:29.635584: step: 796/530, loss: 0.0032857637852430344
2023-01-22 17:38:30.679264: step: 800/530, loss: 0.0011514577781781554
2023-01-22 17:38:31.728922: step: 804/530, loss: 0.004085666965693235
2023-01-22 17:38:32.790884: step: 808/530, loss: 0.0011021267855539918
2023-01-22 17:38:33.847207: step: 812/530, loss: 0.005500006955116987
2023-01-22 17:38:34.882667: step: 816/530, loss: 0.003999566659331322
2023-01-22 17:38:35.929387: step: 820/530, loss: 0.00016524360398761928
2023-01-22 17:38:36.964162: step: 824/530, loss: 3.676371488836594e-05
2023-01-22 17:38:38.046270: step: 828/530, loss: 0.0012608644319698215
2023-01-22 17:38:39.096293: step: 832/530, loss: 7.187816663645208e-05
2023-01-22 17:38:40.132338: step: 836/530, loss: 0.0
2023-01-22 17:38:41.175035: step: 840/530, loss: 0.027074512094259262
2023-01-22 17:38:42.239585: step: 844/530, loss: 0.00029827214893884957
2023-01-22 17:38:43.286567: step: 848/530, loss: 0.002746318932622671
2023-01-22 17:38:44.323752: step: 852/530, loss: 1.5612386050634086e-05
2023-01-22 17:38:45.365047: step: 856/530, loss: 0.00023588014300912619
2023-01-22 17:38:46.405587: step: 860/530, loss: 0.0009852091316133738
2023-01-22 17:38:47.446737: step: 864/530, loss: 0.0002751785214059055
2023-01-22 17:38:48.498478: step: 868/530, loss: 0.0048138173297047615
2023-01-22 17:38:49.543455: step: 872/530, loss: 0.00011382075899746269
2023-01-22 17:38:50.621859: step: 876/530, loss: 0.017650412395596504
2023-01-22 17:38:51.664397: step: 880/530, loss: 0.002988304477185011
2023-01-22 17:38:52.729329: step: 884/530, loss: 0.004262375645339489
2023-01-22 17:38:53.784331: step: 888/530, loss: 0.00027263202355243266
2023-01-22 17:38:54.837475: step: 892/530, loss: 5.511665949597955e-05
2023-01-22 17:38:55.884404: step: 896/530, loss: 0.0027193748392164707
2023-01-22 17:38:56.933931: step: 900/530, loss: 0.0068252175115048885
2023-01-22 17:38:57.975046: step: 904/530, loss: 0.020413950085639954
2023-01-22 17:38:59.017272: step: 908/530, loss: 3.381617716513574e-05
2023-01-22 17:39:00.057953: step: 912/530, loss: 0.0034264703281223774
2023-01-22 17:39:01.091619: step: 916/530, loss: 0.0005429537850432098
2023-01-22 17:39:02.122638: step: 920/530, loss: 0.004208940081298351
2023-01-22 17:39:03.165115: step: 924/530, loss: 0.005512853618711233
2023-01-22 17:39:04.204529: step: 928/530, loss: 0.002475880552083254
2023-01-22 17:39:05.232721: step: 932/530, loss: 0.001978884916752577
2023-01-22 17:39:06.276682: step: 936/530, loss: 5.936039428888762e-07
2023-01-22 17:39:07.304431: step: 940/530, loss: 0.002239610766991973
2023-01-22 17:39:08.337824: step: 944/530, loss: 0.0002142765006283298
2023-01-22 17:39:09.387658: step: 948/530, loss: 4.619327143018381e-08
2023-01-22 17:39:10.445520: step: 952/530, loss: 0.022329814732074738
2023-01-22 17:39:11.480509: step: 956/530, loss: 0.00011196551349712536
2023-01-22 17:39:12.536777: step: 960/530, loss: 0.022696807980537415
2023-01-22 17:39:13.570091: step: 964/530, loss: 0.0002388124557910487
2023-01-22 17:39:14.612497: step: 968/530, loss: 0.0027538160793483257
2023-01-22 17:39:15.682406: step: 972/530, loss: 0.012065545655786991
2023-01-22 17:39:16.721295: step: 976/530, loss: 3.42013081535697e-05
2023-01-22 17:39:17.771579: step: 980/530, loss: 6.307618605205789e-05
2023-01-22 17:39:18.815292: step: 984/530, loss: 0.0020277961157262325
2023-01-22 17:39:19.862111: step: 988/530, loss: 0.000552874116692692
2023-01-22 17:39:20.905634: step: 992/530, loss: 0.0049505983479321
2023-01-22 17:39:21.941765: step: 996/530, loss: 0.001882542739622295
2023-01-22 17:39:22.983943: step: 1000/530, loss: 0.0011978696566075087
2023-01-22 17:39:24.045789: step: 1004/530, loss: 0.0012127527734264731
2023-01-22 17:39:25.082499: step: 1008/530, loss: 0.0007783604087308049
2023-01-22 17:39:26.134860: step: 1012/530, loss: 0.002449911553412676
2023-01-22 17:39:27.177281: step: 1016/530, loss: 0.0762534812092781
2023-01-22 17:39:28.237703: step: 1020/530, loss: 0.0033033364452421665
2023-01-22 17:39:29.282874: step: 1024/530, loss: 6.077212219679495e-06
2023-01-22 17:39:30.330363: step: 1028/530, loss: 0.0016020482871681452
2023-01-22 17:39:31.367260: step: 1032/530, loss: 2.6438903660164215e-05
2023-01-22 17:39:32.411819: step: 1036/530, loss: 0.0029201656579971313
2023-01-22 17:39:33.472683: step: 1040/530, loss: 0.0055586895905435085
2023-01-22 17:39:34.513326: step: 1044/530, loss: 0.000632832758128643
2023-01-22 17:39:35.554820: step: 1048/530, loss: 0.0015257126651704311
2023-01-22 17:39:36.607242: step: 1052/530, loss: 0.0008503880235366523
2023-01-22 17:39:37.655975: step: 1056/530, loss: 0.0015724987024441361
2023-01-22 17:39:38.687536: step: 1060/530, loss: 1.4856231246085372e-05
2023-01-22 17:39:39.756833: step: 1064/530, loss: 6.583302456419915e-05
2023-01-22 17:39:40.794701: step: 1068/530, loss: 0.002436942420899868
2023-01-22 17:39:41.833283: step: 1072/530, loss: 0.00032046635169535875
2023-01-22 17:39:42.887516: step: 1076/530, loss: 0.00012110287207178771
2023-01-22 17:39:43.935769: step: 1080/530, loss: 0.002372728195041418
2023-01-22 17:39:44.993307: step: 1084/530, loss: 0.00012288035941310227
2023-01-22 17:39:46.038832: step: 1088/530, loss: 0.007364585995674133
2023-01-22 17:39:47.122343: step: 1092/530, loss: 3.62734826921951e-05
2023-01-22 17:39:48.172235: step: 1096/530, loss: 0.00015792572230566293
2023-01-22 17:39:49.213125: step: 1100/530, loss: 0.003984449431300163
2023-01-22 17:39:50.248971: step: 1104/530, loss: 0.0005640694871544838
2023-01-22 17:39:51.291584: step: 1108/530, loss: 5.598976349574514e-05
2023-01-22 17:39:52.353158: step: 1112/530, loss: 0.00042962294537574053
2023-01-22 17:39:53.393322: step: 1116/530, loss: 0.00016251549823209643
2023-01-22 17:39:54.467009: step: 1120/530, loss: 0.001281069708056748
2023-01-22 17:39:55.519590: step: 1124/530, loss: 0.005847966764122248
2023-01-22 17:39:56.556028: step: 1128/530, loss: 0.0019878402817994356
2023-01-22 17:39:57.618706: step: 1132/530, loss: 0.0025314881931990385
2023-01-22 17:39:58.671113: step: 1136/530, loss: 0.002351641422137618
2023-01-22 17:39:59.737797: step: 1140/530, loss: 0.0010337227722629905
2023-01-22 17:40:00.794724: step: 1144/530, loss: 0.0038619504775851965
2023-01-22 17:40:01.864963: step: 1148/530, loss: 0.0032300916500389576
2023-01-22 17:40:02.933347: step: 1152/530, loss: 0.0011425962438806891
2023-01-22 17:40:03.949438: step: 1156/530, loss: 0.001927337609231472
2023-01-22 17:40:04.985379: step: 1160/530, loss: 0.0006717698997817934
2023-01-22 17:40:06.044011: step: 1164/530, loss: 0.004957296419888735
2023-01-22 17:40:07.121252: step: 1168/530, loss: 0.003051629988476634
2023-01-22 17:40:08.173179: step: 1172/530, loss: 0.004967954475432634
2023-01-22 17:40:09.231581: step: 1176/530, loss: 0.003258374985307455
2023-01-22 17:40:10.306565: step: 1180/530, loss: 0.0009223743691109121
2023-01-22 17:40:11.344910: step: 1184/530, loss: 0.0003745995636563748
2023-01-22 17:40:12.382597: step: 1188/530, loss: 1.7748557468166837e-07
2023-01-22 17:40:13.428601: step: 1192/530, loss: 0.007866685278713703
2023-01-22 17:40:14.491004: step: 1196/530, loss: 0.000192342879017815
2023-01-22 17:40:15.558955: step: 1200/530, loss: 0.006477084942162037
2023-01-22 17:40:16.608824: step: 1204/530, loss: 0.0021790049504488707
2023-01-22 17:40:17.660633: step: 1208/530, loss: 0.002990493318066001
2023-01-22 17:40:18.713918: step: 1212/530, loss: 0.00032539491076022387
2023-01-22 17:40:19.771033: step: 1216/530, loss: 0.00024139491142705083
2023-01-22 17:40:20.853580: step: 1220/530, loss: 0.00062701350543648
2023-01-22 17:40:21.892152: step: 1224/530, loss: 3.0145847631501965e-05
2023-01-22 17:40:22.925258: step: 1228/530, loss: 0.0022818471770733595
2023-01-22 17:40:23.962879: step: 1232/530, loss: 0.00014814484165981412
2023-01-22 17:40:25.020597: step: 1236/530, loss: 0.0012805273290723562
2023-01-22 17:40:26.052585: step: 1240/530, loss: 0.00665692426264286
2023-01-22 17:40:27.093740: step: 1244/530, loss: 0.004849271383136511
2023-01-22 17:40:28.138145: step: 1248/530, loss: 0.001766684465110302
2023-01-22 17:40:29.202198: step: 1252/530, loss: 0.0010257732355967164
2023-01-22 17:40:30.242754: step: 1256/530, loss: 0.0001357453438686207
2023-01-22 17:40:31.269839: step: 1260/530, loss: 9.690555452834815e-05
2023-01-22 17:40:32.319672: step: 1264/530, loss: 0.0018626991659402847
2023-01-22 17:40:33.399343: step: 1268/530, loss: 4.063325468450785e-05
2023-01-22 17:40:34.447401: step: 1272/530, loss: 0.006159180775284767
2023-01-22 17:40:35.496456: step: 1276/530, loss: 0.042420193552970886
2023-01-22 17:40:36.545183: step: 1280/530, loss: 0.004204066004604101
2023-01-22 17:40:37.584342: step: 1284/530, loss: 0.0021976048592478037
2023-01-22 17:40:38.653412: step: 1288/530, loss: 6.468210631283e-05
2023-01-22 17:40:39.695191: step: 1292/530, loss: 0.00013075563765596598
2023-01-22 17:40:40.749714: step: 1296/530, loss: 0.0013294767122715712
2023-01-22 17:40:41.795478: step: 1300/530, loss: 0.0012069130316376686
2023-01-22 17:40:42.841650: step: 1304/530, loss: 0.003489164402708411
2023-01-22 17:40:43.881985: step: 1308/530, loss: 0.0019300506683066487
2023-01-22 17:40:44.929066: step: 1312/530, loss: 0.0025566101539880037
2023-01-22 17:40:45.976403: step: 1316/530, loss: 0.0035837392788380384
2023-01-22 17:40:47.004412: step: 1320/530, loss: 0.0004616178630385548
2023-01-22 17:40:48.037920: step: 1324/530, loss: 0.0003901587915606797
2023-01-22 17:40:49.090939: step: 1328/530, loss: 0.0015194857260212302
2023-01-22 17:40:50.134262: step: 1332/530, loss: 0.004413897171616554
2023-01-22 17:40:51.181360: step: 1336/530, loss: 4.1017559851752594e-05
2023-01-22 17:40:52.222554: step: 1340/530, loss: 0.004024730995297432
2023-01-22 17:40:53.282455: step: 1344/530, loss: 0.0012902431190013885
2023-01-22 17:40:54.335182: step: 1348/530, loss: 0.0027972920797765255
2023-01-22 17:40:55.378519: step: 1352/530, loss: 0.0007918868213891983
2023-01-22 17:40:56.438285: step: 1356/530, loss: 0.0005870192544534802
2023-01-22 17:40:57.479741: step: 1360/530, loss: 0.010433397255837917
2023-01-22 17:40:58.525916: step: 1364/530, loss: 0.0018087269272655249
2023-01-22 17:40:59.572299: step: 1368/530, loss: 0.001361538888886571
2023-01-22 17:41:00.617088: step: 1372/530, loss: 0.001256853574886918
2023-01-22 17:41:01.664634: step: 1376/530, loss: 0.001649790327064693
2023-01-22 17:41:02.720724: step: 1380/530, loss: 0.0021032148506492376
2023-01-22 17:41:03.771623: step: 1384/530, loss: 0.0005936964298598468
2023-01-22 17:41:04.824939: step: 1388/530, loss: 0.0005221807514317334
2023-01-22 17:41:05.911561: step: 1392/530, loss: 0.002304880181327462
2023-01-22 17:41:06.967748: step: 1396/530, loss: 0.005782202817499638
2023-01-22 17:41:08.036398: step: 1400/530, loss: 8.772419823799282e-05
2023-01-22 17:41:09.103960: step: 1404/530, loss: 0.0023764390498399734
2023-01-22 17:41:10.156717: step: 1408/530, loss: 0.004591720644384623
2023-01-22 17:41:11.196870: step: 1412/530, loss: 0.011562719009816647
2023-01-22 17:41:12.242182: step: 1416/530, loss: 9.731941827340052e-05
2023-01-22 17:41:13.295558: step: 1420/530, loss: 0.0044642239809036255
2023-01-22 17:41:14.324180: step: 1424/530, loss: 0.0024879854172468185
2023-01-22 17:41:15.360807: step: 1428/530, loss: 0.003250701352953911
2023-01-22 17:41:16.418870: step: 1432/530, loss: 0.006288027390837669
2023-01-22 17:41:17.469203: step: 1436/530, loss: 0.008314261212944984
2023-01-22 17:41:18.503935: step: 1440/530, loss: 0.003559113945811987
2023-01-22 17:41:19.545816: step: 1444/530, loss: 0.00010053793084807694
2023-01-22 17:41:20.575671: step: 1448/530, loss: 0.0019314768724143505
2023-01-22 17:41:21.614675: step: 1452/530, loss: 0.0005177659913897514
2023-01-22 17:41:22.667393: step: 1456/530, loss: 0.002462890697643161
2023-01-22 17:41:23.724018: step: 1460/530, loss: 0.00042663421481847763
2023-01-22 17:41:24.777102: step: 1464/530, loss: 0.004815227817744017
2023-01-22 17:41:25.809420: step: 1468/530, loss: 0.0014055515639483929
2023-01-22 17:41:26.853178: step: 1472/530, loss: 0.003134963335469365
2023-01-22 17:41:27.899476: step: 1476/530, loss: 0.004921565297991037
2023-01-22 17:41:28.959729: step: 1480/530, loss: 0.056693241000175476
2023-01-22 17:41:30.012062: step: 1484/530, loss: 3.8686055631842464e-05
2023-01-22 17:41:31.056066: step: 1488/530, loss: 0.0009435339597985148
2023-01-22 17:41:32.114321: step: 1492/530, loss: 0.0005153658566996455
2023-01-22 17:41:33.155737: step: 1496/530, loss: 3.112934427917935e-05
2023-01-22 17:41:34.207918: step: 1500/530, loss: 0.00027460220735520124
2023-01-22 17:41:35.247301: step: 1504/530, loss: 0.007785177789628506
2023-01-22 17:41:36.282597: step: 1508/530, loss: 0.0012664251262322068
2023-01-22 17:41:37.342136: step: 1512/530, loss: 0.0008438891964033246
2023-01-22 17:41:38.393866: step: 1516/530, loss: 0.008209994062781334
2023-01-22 17:41:39.453083: step: 1520/530, loss: 0.003996571060270071
2023-01-22 17:41:40.501762: step: 1524/530, loss: 1.397158939653309e-05
2023-01-22 17:41:41.539386: step: 1528/530, loss: 0.017526045441627502
2023-01-22 17:41:42.601101: step: 1532/530, loss: 3.1790787033969536e-05
2023-01-22 17:41:43.653594: step: 1536/530, loss: 0.0020459555089473724
2023-01-22 17:41:44.673370: step: 1540/530, loss: 0.001474827527999878
2023-01-22 17:41:45.724251: step: 1544/530, loss: 0.0005123792798258364
2023-01-22 17:41:46.784340: step: 1548/530, loss: 0.0005639170994982123
2023-01-22 17:41:47.825766: step: 1552/530, loss: 0.00745109049603343
2023-01-22 17:41:48.878173: step: 1556/530, loss: 0.00184642372187227
2023-01-22 17:41:49.934136: step: 1560/530, loss: 0.00014419754734262824
2023-01-22 17:41:50.981309: step: 1564/530, loss: 0.005999063607305288
2023-01-22 17:41:52.052715: step: 1568/530, loss: 0.00016644630522932857
2023-01-22 17:41:53.098764: step: 1572/530, loss: 3.279771044617519e-05
2023-01-22 17:41:54.140002: step: 1576/530, loss: 0.0014099200488999486
2023-01-22 17:41:55.191911: step: 1580/530, loss: 0.0031581914518028498
2023-01-22 17:41:56.242930: step: 1584/530, loss: 0.004766381345689297
2023-01-22 17:41:57.310007: step: 1588/530, loss: 0.0009192170691676438
2023-01-22 17:41:58.343222: step: 1592/530, loss: 8.551339851692319e-05
2023-01-22 17:41:59.381586: step: 1596/530, loss: 0.0020264198537915945
2023-01-22 17:42:00.425439: step: 1600/530, loss: 0.0021216089371591806
2023-01-22 17:42:01.465658: step: 1604/530, loss: 8.622062887297943e-05
2023-01-22 17:42:02.516843: step: 1608/530, loss: 0.0016236110823228955
2023-01-22 17:42:03.564846: step: 1612/530, loss: 5.186088674236089e-05
2023-01-22 17:42:04.612558: step: 1616/530, loss: 0.00019308857736177742
2023-01-22 17:42:05.669118: step: 1620/530, loss: 0.0006649705464951694
2023-01-22 17:42:06.724074: step: 1624/530, loss: 0.0007954604225233197
2023-01-22 17:42:07.787608: step: 1628/530, loss: 0.002592288190498948
2023-01-22 17:42:08.847840: step: 1632/530, loss: 4.619293576979544e-06
2023-01-22 17:42:09.900049: step: 1636/530, loss: 4.082791565451771e-05
2023-01-22 17:42:10.950831: step: 1640/530, loss: 0.0015390218468382955
2023-01-22 17:42:11.996940: step: 1644/530, loss: 0.001659642904996872
2023-01-22 17:42:13.054624: step: 1648/530, loss: 0.002143438206985593
2023-01-22 17:42:14.090869: step: 1652/530, loss: 0.0008224029443226755
2023-01-22 17:42:15.126039: step: 1656/530, loss: 0.004564713686704636
2023-01-22 17:42:16.170300: step: 1660/530, loss: 0.00493394723162055
2023-01-22 17:42:17.234030: step: 1664/530, loss: 0.0021117799915373325
2023-01-22 17:42:18.280656: step: 1668/530, loss: 0.00011618063581408933
2023-01-22 17:42:19.331230: step: 1672/530, loss: 0.00149440485984087
2023-01-22 17:42:20.387200: step: 1676/530, loss: 0.0038263064343482256
2023-01-22 17:42:21.437844: step: 1680/530, loss: 0.00539175420999527
2023-01-22 17:42:22.474912: step: 1684/530, loss: 0.008887311443686485
2023-01-22 17:42:23.501864: step: 1688/530, loss: 2.9132600047887536e-06
2023-01-22 17:42:24.545834: step: 1692/530, loss: 0.003699810244143009
2023-01-22 17:42:25.596225: step: 1696/530, loss: 5.02561579196481e-06
2023-01-22 17:42:26.627066: step: 1700/530, loss: 0.010473739355802536
2023-01-22 17:42:27.693905: step: 1704/530, loss: 0.0027329218573868275
2023-01-22 17:42:28.739917: step: 1708/530, loss: 0.00011836125486297533
2023-01-22 17:42:29.804165: step: 1712/530, loss: 0.035101570188999176
2023-01-22 17:42:30.854051: step: 1716/530, loss: 0.00040708636515773833
2023-01-22 17:42:31.896275: step: 1720/530, loss: 0.004286528564989567
2023-01-22 17:42:32.948653: step: 1724/530, loss: 0.004051835276186466
2023-01-22 17:42:33.979353: step: 1728/530, loss: 0.0030248307157307863
2023-01-22 17:42:35.036440: step: 1732/530, loss: 3.635800749179907e-05
2023-01-22 17:42:36.070384: step: 1736/530, loss: 0.0011479301610961556
2023-01-22 17:42:37.134337: step: 1740/530, loss: 0.004842640366405249
2023-01-22 17:42:38.166383: step: 1744/530, loss: 0.00036109256325289607
2023-01-22 17:42:39.196142: step: 1748/530, loss: 0.00037143705412745476
2023-01-22 17:42:40.239078: step: 1752/530, loss: 6.472118548117578e-05
2023-01-22 17:42:41.294434: step: 1756/530, loss: 0.0007849947432987392
2023-01-22 17:42:42.330853: step: 1760/530, loss: 8.931572665460408e-05
2023-01-22 17:42:43.383726: step: 1764/530, loss: 0.0060320147313177586
2023-01-22 17:42:44.440959: step: 1768/530, loss: 0.0016902574570849538
2023-01-22 17:42:45.466293: step: 1772/530, loss: 0.0012195459567010403
2023-01-22 17:42:46.504695: step: 1776/530, loss: 0.005039629060775042
2023-01-22 17:42:47.561420: step: 1780/530, loss: 0.0013716467656195164
2023-01-22 17:42:48.607411: step: 1784/530, loss: 0.00011016071221092716
2023-01-22 17:42:49.653368: step: 1788/530, loss: 1.3999451766721904e-05
2023-01-22 17:42:50.710234: step: 1792/530, loss: 0.0007266805623658001
2023-01-22 17:42:51.768511: step: 1796/530, loss: 0.003449204843491316
2023-01-22 17:42:52.799831: step: 1800/530, loss: 0.000335844699293375
2023-01-22 17:42:53.832600: step: 1804/530, loss: 0.0018640717025846243
2023-01-22 17:42:54.890347: step: 1808/530, loss: 0.00794154778122902
2023-01-22 17:42:55.924962: step: 1812/530, loss: 0.00024242194194812328
2023-01-22 17:42:56.966211: step: 1816/530, loss: 0.001151465461589396
2023-01-22 17:42:58.004740: step: 1820/530, loss: 0.017692919820547104
2023-01-22 17:42:59.060457: step: 1824/530, loss: 0.0011846307897940278
2023-01-22 17:43:00.109692: step: 1828/530, loss: 2.58858926827088e-06
2023-01-22 17:43:01.161909: step: 1832/530, loss: 0.0022339913994073868
2023-01-22 17:43:02.205404: step: 1836/530, loss: 0.013790315017104149
2023-01-22 17:43:03.247703: step: 1840/530, loss: 0.0008367117843590677
2023-01-22 17:43:04.292780: step: 1844/530, loss: 0.0022090678103268147
2023-01-22 17:43:05.324491: step: 1848/530, loss: 0.0011798989726230502
2023-01-22 17:43:06.369843: step: 1852/530, loss: 5.579032949754037e-05
2023-01-22 17:43:07.409369: step: 1856/530, loss: 1.1214691767236218e-05
2023-01-22 17:43:08.440910: step: 1860/530, loss: 0.0021004825830459595
2023-01-22 17:43:09.495993: step: 1864/530, loss: 0.0024329901207238436
2023-01-22 17:43:10.537424: step: 1868/530, loss: 0.00197086320258677
2023-01-22 17:43:11.593676: step: 1872/530, loss: 0.0037525813095271587
2023-01-22 17:43:12.631015: step: 1876/530, loss: 0.0024905495811253786
2023-01-22 17:43:13.682171: step: 1880/530, loss: 0.00043110395199619234
2023-01-22 17:43:14.726428: step: 1884/530, loss: 0.004796598106622696
2023-01-22 17:43:15.775819: step: 1888/530, loss: 0.000504016992636025
2023-01-22 17:43:16.813573: step: 1892/530, loss: 0.0006832245853729546
2023-01-22 17:43:17.868489: step: 1896/530, loss: 0.0025829202495515347
2023-01-22 17:43:18.914035: step: 1900/530, loss: 0.0009293968323618174
2023-01-22 17:43:19.950494: step: 1904/530, loss: 1.6700187188689597e-05
2023-01-22 17:43:21.003682: step: 1908/530, loss: 0.0074868230149149895
2023-01-22 17:43:22.065654: step: 1912/530, loss: 0.017092956230044365
2023-01-22 17:43:23.105288: step: 1916/530, loss: 0.0016801649471744895
2023-01-22 17:43:24.148152: step: 1920/530, loss: 0.0006731111207045615
2023-01-22 17:43:25.217123: step: 1924/530, loss: 0.01573982462286949
2023-01-22 17:43:26.261225: step: 1928/530, loss: 0.005498635116964579
2023-01-22 17:43:27.313852: step: 1932/530, loss: 0.0031591299921274185
2023-01-22 17:43:28.362368: step: 1936/530, loss: 0.002266906201839447
2023-01-22 17:43:29.424508: step: 1940/530, loss: 0.00015798679669387639
2023-01-22 17:43:30.472283: step: 1944/530, loss: 0.00024810314062051475
2023-01-22 17:43:31.519699: step: 1948/530, loss: 0.0012339941458776593
2023-01-22 17:43:32.565132: step: 1952/530, loss: 0.0024772698525339365
2023-01-22 17:43:33.634010: step: 1956/530, loss: 0.006872924044728279
2023-01-22 17:43:34.667493: step: 1960/530, loss: 0.0005999120767228305
2023-01-22 17:43:35.712178: step: 1964/530, loss: 0.0002524539886508137
2023-01-22 17:43:36.746401: step: 1968/530, loss: 0.004628421273082495
2023-01-22 17:43:37.782511: step: 1972/530, loss: 0.00041213203803636134
2023-01-22 17:43:38.847743: step: 1976/530, loss: 2.120855953080536e-07
2023-01-22 17:43:39.900325: step: 1980/530, loss: 1.5685640391893685e-05
2023-01-22 17:43:40.937869: step: 1984/530, loss: 0.000372269656509161
2023-01-22 17:43:41.982802: step: 1988/530, loss: 0.0003649625869002193
2023-01-22 17:43:43.048151: step: 1992/530, loss: 0.007205056492239237
2023-01-22 17:43:44.079146: step: 1996/530, loss: 0.006570196710526943
2023-01-22 17:43:45.121417: step: 2000/530, loss: 0.013084542006254196
2023-01-22 17:43:46.174990: step: 2004/530, loss: 0.007469133008271456
2023-01-22 17:43:47.207406: step: 2008/530, loss: 0.0
2023-01-22 17:43:48.238273: step: 2012/530, loss: 0.00013008693349547684
2023-01-22 17:43:49.283348: step: 2016/530, loss: 0.00021896997350268066
2023-01-22 17:43:50.348075: step: 2020/530, loss: 0.0021309363655745983
2023-01-22 17:43:51.390394: step: 2024/530, loss: 0.0029911391902714968
2023-01-22 17:43:52.438072: step: 2028/530, loss: 0.005834572017192841
2023-01-22 17:43:53.493696: step: 2032/530, loss: 0.004073398187756538
2023-01-22 17:43:54.537065: step: 2036/530, loss: 0.00503756757825613
2023-01-22 17:43:55.600311: step: 2040/530, loss: 0.0012076168786734343
2023-01-22 17:43:56.635692: step: 2044/530, loss: 1.8324577695238986e-06
2023-01-22 17:43:57.689968: step: 2048/530, loss: 0.0027322161477059126
2023-01-22 17:43:58.735315: step: 2052/530, loss: 0.001722295070067048
2023-01-22 17:43:59.765240: step: 2056/530, loss: 0.00016037047316785902
2023-01-22 17:44:00.797651: step: 2060/530, loss: 0.000477560271974653
2023-01-22 17:44:01.840564: step: 2064/530, loss: 0.001003615790978074
2023-01-22 17:44:02.896499: step: 2068/530, loss: 0.008078647777438164
2023-01-22 17:44:03.976677: step: 2072/530, loss: 0.003271593013778329
2023-01-22 17:44:05.012546: step: 2076/530, loss: 0.004478019196540117
2023-01-22 17:44:06.070179: step: 2080/530, loss: 0.006007687654346228
2023-01-22 17:44:07.135847: step: 2084/530, loss: 0.0033141088206321
2023-01-22 17:44:08.187689: step: 2088/530, loss: 0.004116765223443508
2023-01-22 17:44:09.247863: step: 2092/530, loss: 0.010699407197535038
2023-01-22 17:44:10.289482: step: 2096/530, loss: 0.0010037511819973588
2023-01-22 17:44:11.339463: step: 2100/530, loss: 0.0009823129512369633
2023-01-22 17:44:12.381936: step: 2104/530, loss: 0.0011538874823600054
2023-01-22 17:44:13.425934: step: 2108/530, loss: 0.0014359421329572797
2023-01-22 17:44:14.483344: step: 2112/530, loss: 0.01336933858692646
2023-01-22 17:44:15.534269: step: 2116/530, loss: 0.001752842334099114
2023-01-22 17:44:16.576342: step: 2120/530, loss: 3.47580571542494e-05
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34044483101391654, 'r': 0.32494070208728654, 'f1': 0.33251213592233014}, 'combined': 0.24500894225855904, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3628260362440685, 'r': 0.4085127705873014, 'f1': 0.38431638080327185}, 'combined': 0.29789116598148346, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30991284081567416, 'r': 0.31991002922908296, 'f1': 0.3148320922571928}, 'combined': 0.23198154166319465, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36027148060397335, 'r': 0.4086167344350212, 'f1': 0.38292420935857285}, 'combined': 0.296812066584157, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3272891805201076, 'r': 0.33846793810902964, 'f1': 0.3327847078049601}, 'combined': 0.24520978469839164, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3615671871043032, 'r': 0.387488364120972, 'f1': 0.3740792725497937}, 'combined': 0.2899561825505578, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3462223895582329, 'r': 0.3271703036053131, 'f1': 0.33642682926829265}, 'combined': 0.24789345314505773, 'stategy': 1, 'epoch': 15}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.360310988924254, 'r': 0.40667453529318376, 'f1': 0.3820914459404006}, 'combined': 0.2961665753222244, 'stategy': 1, 'epoch': 15}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 15}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:46:46.738242: step: 4/530, loss: 0.005626446567475796
2023-01-22 17:46:47.786951: step: 8/530, loss: 0.00014369042764883488
2023-01-22 17:46:48.831131: step: 12/530, loss: 0.010451801121234894
2023-01-22 17:46:49.866657: step: 16/530, loss: 3.443231435085181e-06
2023-01-22 17:46:50.925598: step: 20/530, loss: 0.00022170107695274055
2023-01-22 17:46:51.966066: step: 24/530, loss: 0.001158897764980793
2023-01-22 17:46:53.015265: step: 28/530, loss: 0.0005250044632703066
2023-01-22 17:46:54.054514: step: 32/530, loss: 0.0002517616958357394
2023-01-22 17:46:55.103642: step: 36/530, loss: 0.00015325793356169015
2023-01-22 17:46:56.147661: step: 40/530, loss: 0.0004214466898702085
2023-01-22 17:46:57.190812: step: 44/530, loss: 5.444366252049804e-05
2023-01-22 17:46:58.263803: step: 48/530, loss: 0.0020414115861058235
2023-01-22 17:46:59.310532: step: 52/530, loss: 0.0015358494129031897
2023-01-22 17:47:00.352260: step: 56/530, loss: 0.0013440109323710203
2023-01-22 17:47:01.404010: step: 60/530, loss: 0.00280355429276824
2023-01-22 17:47:02.439887: step: 64/530, loss: 0.0018657094333320856
2023-01-22 17:47:03.482501: step: 68/530, loss: 0.002636269200593233
2023-01-22 17:47:04.526977: step: 72/530, loss: 0.003890024730935693
2023-01-22 17:47:05.589027: step: 76/530, loss: 6.129233224783093e-05
2023-01-22 17:47:06.627508: step: 80/530, loss: 6.516681605717167e-05
2023-01-22 17:47:07.680007: step: 84/530, loss: 0.00024245383974630386
2023-01-22 17:47:08.724509: step: 88/530, loss: 0.0038589711766690016
2023-01-22 17:47:09.774340: step: 92/530, loss: 0.002299490850418806
2023-01-22 17:47:10.806093: step: 96/530, loss: 9.911660526995547e-06
2023-01-22 17:47:11.850670: step: 100/530, loss: 0.00015212695871014148
2023-01-22 17:47:12.892932: step: 104/530, loss: 0.0030536558479070663
2023-01-22 17:47:13.935505: step: 108/530, loss: 0.0023492123000323772
2023-01-22 17:47:14.989227: step: 112/530, loss: 0.003406766103580594
2023-01-22 17:47:16.037975: step: 116/530, loss: 0.0026423195376992226
2023-01-22 17:47:17.096110: step: 120/530, loss: 0.00137248111423105
2023-01-22 17:47:18.128311: step: 124/530, loss: 0.001738875056616962
2023-01-22 17:47:19.183069: step: 128/530, loss: 0.0015760643873363733
2023-01-22 17:47:20.228919: step: 132/530, loss: 0.0004440586781129241
2023-01-22 17:47:21.280341: step: 136/530, loss: 0.0036454659420996904
2023-01-22 17:47:22.324833: step: 140/530, loss: 0.0005197924911044538
2023-01-22 17:47:23.371410: step: 144/530, loss: 0.013064837083220482
2023-01-22 17:47:24.409494: step: 148/530, loss: 0.004167779814451933
2023-01-22 17:47:25.459250: step: 152/530, loss: 0.00935199111700058
2023-01-22 17:47:26.516030: step: 156/530, loss: 0.006484498269855976
2023-01-22 17:47:27.560369: step: 160/530, loss: 0.025635844096541405
2023-01-22 17:47:28.595342: step: 164/530, loss: 1.6109053149193642e-06
2023-01-22 17:47:29.630292: step: 168/530, loss: 1.649110345169902e-05
2023-01-22 17:47:30.679754: step: 172/530, loss: 0.004525516647845507
2023-01-22 17:47:31.724575: step: 176/530, loss: 0.007596456445753574
2023-01-22 17:47:32.767903: step: 180/530, loss: 0.0022685991134494543
2023-01-22 17:47:33.813550: step: 184/530, loss: 0.000429784064181149
2023-01-22 17:47:34.839279: step: 188/530, loss: 0.0015707494458183646
2023-01-22 17:47:35.881652: step: 192/530, loss: 0.003487711539492011
2023-01-22 17:47:36.915936: step: 196/530, loss: 0.00016858085291460156
2023-01-22 17:47:37.962025: step: 200/530, loss: 0.010343965142965317
2023-01-22 17:47:39.015450: step: 204/530, loss: 0.001973228296265006
2023-01-22 17:47:40.064901: step: 208/530, loss: 0.0
2023-01-22 17:47:41.108278: step: 212/530, loss: 0.006910588126629591
2023-01-22 17:47:42.157741: step: 216/530, loss: 1.8952407117467374e-05
2023-01-22 17:47:43.209305: step: 220/530, loss: 0.00035080115776509047
2023-01-22 17:47:44.264771: step: 224/530, loss: 0.001980482367798686
2023-01-22 17:47:45.304666: step: 228/530, loss: 5.317779505276121e-05
2023-01-22 17:47:46.349044: step: 232/530, loss: 0.004836398642510176
2023-01-22 17:47:47.400402: step: 236/530, loss: 0.0056937807239592075
2023-01-22 17:47:48.440464: step: 240/530, loss: 0.002523608971387148
2023-01-22 17:47:49.493241: step: 244/530, loss: 0.00043353429646231234
2023-01-22 17:47:50.543293: step: 248/530, loss: 6.026616716781064e-08
2023-01-22 17:47:51.573908: step: 252/530, loss: 0.0026329131796956062
2023-01-22 17:47:52.619054: step: 256/530, loss: 0.00041145726572722197
2023-01-22 17:47:53.674723: step: 260/530, loss: 0.0027066851034760475
2023-01-22 17:47:54.723289: step: 264/530, loss: 0.00023460002557840198
2023-01-22 17:47:55.776241: step: 268/530, loss: 0.002958378056064248
2023-01-22 17:47:56.812203: step: 272/530, loss: 2.5870322133414447e-05
2023-01-22 17:47:57.890500: step: 276/530, loss: 0.008892868645489216
2023-01-22 17:47:58.945583: step: 280/530, loss: 9.65287399594672e-05
2023-01-22 17:47:59.989458: step: 284/530, loss: 0.0010161735117435455
2023-01-22 17:48:01.037878: step: 288/530, loss: 0.0008460739045403898
2023-01-22 17:48:02.070972: step: 292/530, loss: 0.006211341358721256
2023-01-22 17:48:03.136617: step: 296/530, loss: 0.005600426346063614
2023-01-22 17:48:04.204031: step: 300/530, loss: 1.3914585679231095e-06
2023-01-22 17:48:05.261014: step: 304/530, loss: 0.0029889405705034733
2023-01-22 17:48:06.307727: step: 308/530, loss: 3.432559196880902e-07
2023-01-22 17:48:07.350486: step: 312/530, loss: 6.819624900344934e-07
2023-01-22 17:48:08.388016: step: 316/530, loss: 1.9061630155192688e-05
2023-01-22 17:48:09.468555: step: 320/530, loss: 0.002788847777992487
2023-01-22 17:48:10.515290: step: 324/530, loss: 0.00019209779566153884
2023-01-22 17:48:11.564438: step: 328/530, loss: 6.264240073505789e-05
2023-01-22 17:48:12.628155: step: 332/530, loss: 0.005913532339036465
2023-01-22 17:48:13.663183: step: 336/530, loss: 2.0686725292762276e-06
2023-01-22 17:48:14.711662: step: 340/530, loss: 0.0016512090805917978
2023-01-22 17:48:15.759193: step: 344/530, loss: 0.00014736366574652493
2023-01-22 17:48:16.811042: step: 348/530, loss: 0.0013936960604041815
2023-01-22 17:48:17.873290: step: 352/530, loss: 0.00015973685367498547
2023-01-22 17:48:18.914757: step: 356/530, loss: 0.0017561035929247737
2023-01-22 17:48:19.954051: step: 360/530, loss: 0.0007700967253185809
2023-01-22 17:48:21.009618: step: 364/530, loss: 0.005132708232849836
2023-01-22 17:48:22.055727: step: 368/530, loss: 0.0008344475063495338
2023-01-22 17:48:23.096993: step: 372/530, loss: 0.0010486284736543894
2023-01-22 17:48:24.155312: step: 376/530, loss: 2.4150840545189567e-05
2023-01-22 17:48:25.206449: step: 380/530, loss: 0.0018868526676669717
2023-01-22 17:48:26.258851: step: 384/530, loss: 0.0005680397152900696
2023-01-22 17:48:27.300288: step: 388/530, loss: 0.0001443260844098404
2023-01-22 17:48:28.347311: step: 392/530, loss: 0.00017575845413375646
2023-01-22 17:48:29.393592: step: 396/530, loss: 0.005213476717472076
2023-01-22 17:48:30.441189: step: 400/530, loss: 0.0011082661803811789
2023-01-22 17:48:31.482593: step: 404/530, loss: 0.003028241917490959
2023-01-22 17:48:32.527586: step: 408/530, loss: 0.0023756646551191807
2023-01-22 17:48:33.579133: step: 412/530, loss: 0.00290953298099339
2023-01-22 17:48:34.629618: step: 416/530, loss: 3.7953264836687595e-05
2023-01-22 17:48:35.683667: step: 420/530, loss: 0.013020087033510208
2023-01-22 17:48:36.739765: step: 424/530, loss: 0.00021397035743575543
2023-01-22 17:48:37.782996: step: 428/530, loss: 9.09421214601025e-06
2023-01-22 17:48:38.823646: step: 432/530, loss: 0.004044977482408285
2023-01-22 17:48:39.889204: step: 436/530, loss: 0.000284249079413712
2023-01-22 17:48:40.960981: step: 440/530, loss: 0.0008995109819807112
2023-01-22 17:48:42.018113: step: 444/530, loss: 0.0006774552166461945
2023-01-22 17:48:43.069522: step: 448/530, loss: 0.000935703341383487
2023-01-22 17:48:44.121235: step: 452/530, loss: 0.004483042284846306
2023-01-22 17:48:45.171981: step: 456/530, loss: 0.00899346824735403
2023-01-22 17:48:46.236091: step: 460/530, loss: 1.3523878806154244e-05
2023-01-22 17:48:47.282823: step: 464/530, loss: 0.0031942466739565134
2023-01-22 17:48:48.339464: step: 468/530, loss: 0.00030736022745259106
2023-01-22 17:48:49.369042: step: 472/530, loss: 0.00269091734662652
2023-01-22 17:48:50.413375: step: 476/530, loss: 0.0034265455324202776
2023-01-22 17:48:51.460578: step: 480/530, loss: 0.004724216181784868
2023-01-22 17:48:52.520169: step: 484/530, loss: 0.0055031911469995975
2023-01-22 17:48:53.581734: step: 488/530, loss: 0.004729169420897961
2023-01-22 17:48:54.636724: step: 492/530, loss: 0.005532048176974058
2023-01-22 17:48:55.692764: step: 496/530, loss: 1.925692595250439e-05
2023-01-22 17:48:56.745421: step: 500/530, loss: 0.0018275126349180937
2023-01-22 17:48:57.802214: step: 504/530, loss: 0.0008080166298896074
2023-01-22 17:48:58.857754: step: 508/530, loss: 0.0010295987594872713
2023-01-22 17:48:59.904795: step: 512/530, loss: 0.0007535787299275398
2023-01-22 17:49:00.966362: step: 516/530, loss: 0.00426517566666007
2023-01-22 17:49:02.011925: step: 520/530, loss: 0.0005689088138751686
2023-01-22 17:49:03.068107: step: 524/530, loss: 0.0015364977298304439
2023-01-22 17:49:04.105655: step: 528/530, loss: 0.0021460126154124737
2023-01-22 17:49:05.148308: step: 532/530, loss: 0.0008248817175626755
2023-01-22 17:49:06.214449: step: 536/530, loss: 0.0001414690923411399
2023-01-22 17:49:07.249082: step: 540/530, loss: 0.0011817824561148882
2023-01-22 17:49:08.306531: step: 544/530, loss: 0.0007488696137443185
2023-01-22 17:49:09.373787: step: 548/530, loss: 0.003530869958922267
2023-01-22 17:49:10.437846: step: 552/530, loss: 0.00010069393465528265
2023-01-22 17:49:11.480349: step: 556/530, loss: 3.1637435427001037e-07
2023-01-22 17:49:12.527280: step: 560/530, loss: 2.0649536963901483e-05
2023-01-22 17:49:13.567973: step: 564/530, loss: 0.000263277324847877
2023-01-22 17:49:14.620824: step: 568/530, loss: 0.0031225415877997875
2023-01-22 17:49:15.676565: step: 572/530, loss: 0.0017694475827738643
2023-01-22 17:49:16.730807: step: 576/530, loss: 8.599702414358035e-05
2023-01-22 17:49:17.788812: step: 580/530, loss: 0.0014183823950588703
2023-01-22 17:49:18.835886: step: 584/530, loss: 0.0019364558393135667
2023-01-22 17:49:19.889504: step: 588/530, loss: 0.002726313890889287
2023-01-22 17:49:20.941358: step: 592/530, loss: 0.008177314884960651
2023-01-22 17:49:21.980742: step: 596/530, loss: 0.0003128675161860883
2023-01-22 17:49:23.047183: step: 600/530, loss: 0.00030083622550591826
2023-01-22 17:49:24.118528: step: 604/530, loss: 0.00013375611160881817
2023-01-22 17:49:25.160723: step: 608/530, loss: 0.00041740009328350425
2023-01-22 17:49:26.209812: step: 612/530, loss: 0.0022147924173623323
2023-01-22 17:49:27.282717: step: 616/530, loss: 0.001118602929636836
2023-01-22 17:49:28.326356: step: 620/530, loss: 4.026249735034071e-05
2023-01-22 17:49:29.379351: step: 624/530, loss: 0.0009214036981575191
2023-01-22 17:49:30.450486: step: 628/530, loss: 0.0006902736495248973
2023-01-22 17:49:31.486019: step: 632/530, loss: 0.005331212654709816
2023-01-22 17:49:32.535814: step: 636/530, loss: 0.005170522257685661
2023-01-22 17:49:33.587022: step: 640/530, loss: 0.0009643434314057231
2023-01-22 17:49:34.633743: step: 644/530, loss: 1.0169541383220349e-05
2023-01-22 17:49:35.693648: step: 648/530, loss: 0.002622185042127967
2023-01-22 17:49:36.732008: step: 652/530, loss: 0.001706407405436039
2023-01-22 17:49:37.771439: step: 656/530, loss: 0.0002552588121034205
2023-01-22 17:49:38.834818: step: 660/530, loss: 0.0011450779857113957
2023-01-22 17:49:39.872939: step: 664/530, loss: 0.0007268712506629527
2023-01-22 17:49:40.916311: step: 668/530, loss: 8.73974640853703e-05
2023-01-22 17:49:41.979634: step: 672/530, loss: 0.0011688433587551117
2023-01-22 17:49:43.085060: step: 676/530, loss: 0.001862452831119299
2023-01-22 17:49:44.136369: step: 680/530, loss: 0.0006581024499610066
2023-01-22 17:49:45.181130: step: 684/530, loss: 0.008058595471084118
2023-01-22 17:49:46.227664: step: 688/530, loss: 0.0001351031387457624
2023-01-22 17:49:47.280517: step: 692/530, loss: 0.0024865635205060244
2023-01-22 17:49:48.351247: step: 696/530, loss: 1.6259475160040893e-05
2023-01-22 17:49:49.387949: step: 700/530, loss: 0.0016584255499765277
2023-01-22 17:49:50.432383: step: 704/530, loss: 1.6649722965667024e-05
2023-01-22 17:49:51.478620: step: 708/530, loss: 0.0019168462604284286
2023-01-22 17:49:52.532155: step: 712/530, loss: 4.232570790918544e-05
2023-01-22 17:49:53.577215: step: 716/530, loss: 0.0002777922782115638
2023-01-22 17:49:54.630741: step: 720/530, loss: 0.0002649379603099078
2023-01-22 17:49:55.672758: step: 724/530, loss: 0.0010126122506335378
2023-01-22 17:49:56.722172: step: 728/530, loss: 3.378981273272075e-05
2023-01-22 17:49:57.774927: step: 732/530, loss: 0.009026461280882359
2023-01-22 17:49:58.824586: step: 736/530, loss: 0.0019466986414045095
2023-01-22 17:49:59.878971: step: 740/530, loss: 0.0003420878201723099
2023-01-22 17:50:00.931717: step: 744/530, loss: 0.00219076219946146
2023-01-22 17:50:01.973822: step: 748/530, loss: 8.032878395169973e-05
2023-01-22 17:50:03.011114: step: 752/530, loss: 0.00026065041311085224
2023-01-22 17:50:04.074789: step: 756/530, loss: 0.0050124977715313435
2023-01-22 17:50:05.141970: step: 760/530, loss: 0.0017083699349313974
2023-01-22 17:50:06.195464: step: 764/530, loss: 0.0024439250119030476
2023-01-22 17:50:07.238885: step: 768/530, loss: 0.0020100956317037344
2023-01-22 17:50:08.280868: step: 772/530, loss: 2.3693635739618912e-05
2023-01-22 17:50:09.349756: step: 776/530, loss: 0.000990989850834012
2023-01-22 17:50:10.409047: step: 780/530, loss: 8.82792937773047e-06
2023-01-22 17:50:11.441568: step: 784/530, loss: 0.006131125148385763
2023-01-22 17:50:12.497246: step: 788/530, loss: 0.0003794836811721325
2023-01-22 17:50:13.557279: step: 792/530, loss: 0.0008318485924974084
2023-01-22 17:50:14.608533: step: 796/530, loss: 0.0004544957191683352
2023-01-22 17:50:15.647499: step: 800/530, loss: 0.00012144893844379112
2023-01-22 17:50:16.698417: step: 804/530, loss: 0.0013561670202761889
2023-01-22 17:50:17.747804: step: 808/530, loss: 0.0019005938665941358
2023-01-22 17:50:18.788511: step: 812/530, loss: 0.0024295980110764503
2023-01-22 17:50:19.839046: step: 816/530, loss: 0.0023929672315716743
2023-01-22 17:50:20.886854: step: 820/530, loss: 0.0005442625842988491
2023-01-22 17:50:21.928300: step: 824/530, loss: 0.005113847553730011
2023-01-22 17:50:22.975477: step: 828/530, loss: 0.00027917444822378457
2023-01-22 17:50:24.017263: step: 832/530, loss: 0.0007879415643401444
2023-01-22 17:50:25.070771: step: 836/530, loss: 0.0010107087437063456
2023-01-22 17:50:26.129457: step: 840/530, loss: 0.0006676812190562487
2023-01-22 17:50:27.179999: step: 844/530, loss: 0.0002876889775507152
2023-01-22 17:50:28.212449: step: 848/530, loss: 0.0011974034132435918
2023-01-22 17:50:29.266558: step: 852/530, loss: 0.0017826578114181757
2023-01-22 17:50:30.327178: step: 856/530, loss: 0.0002193367254221812
2023-01-22 17:50:31.371883: step: 860/530, loss: 0.002746338490396738
2023-01-22 17:50:32.415454: step: 864/530, loss: 0.003912175539880991
2023-01-22 17:50:33.484874: step: 868/530, loss: 2.355910328333266e-05
2023-01-22 17:50:34.527526: step: 872/530, loss: 0.005852560047060251
2023-01-22 17:50:35.565619: step: 876/530, loss: 2.7279505957267247e-05
2023-01-22 17:50:36.610504: step: 880/530, loss: 0.006939339451491833
2023-01-22 17:50:37.655955: step: 884/530, loss: 9.038711141329259e-06
2023-01-22 17:50:38.712055: step: 888/530, loss: 0.008145336993038654
2023-01-22 17:50:39.762593: step: 892/530, loss: 0.0004597233491949737
2023-01-22 17:50:40.817384: step: 896/530, loss: 0.00010788706276798621
2023-01-22 17:50:41.860993: step: 900/530, loss: 0.0011391089065000415
2023-01-22 17:50:42.907456: step: 904/530, loss: 0.006249002646654844
2023-01-22 17:50:43.946330: step: 908/530, loss: 0.00013312860392034054
2023-01-22 17:50:44.992412: step: 912/530, loss: 1.7742576119417208e-06
2023-01-22 17:50:46.041848: step: 916/530, loss: 3.2327850476576714e-06
2023-01-22 17:50:47.079547: step: 920/530, loss: 0.014845973812043667
2023-01-22 17:50:48.113451: step: 924/530, loss: 8.19013348518638e-06
2023-01-22 17:50:49.165606: step: 928/530, loss: 0.0017061250982806087
2023-01-22 17:50:50.215511: step: 932/530, loss: 0.0003770788316614926
2023-01-22 17:50:51.259040: step: 936/530, loss: 0.0002954646770376712
2023-01-22 17:50:52.321906: step: 940/530, loss: 0.0008622297318652272
2023-01-22 17:50:53.381621: step: 944/530, loss: 0.0012343886774033308
2023-01-22 17:50:54.434687: step: 948/530, loss: 0.0010636313818395138
2023-01-22 17:50:55.487101: step: 952/530, loss: 1.2405379493429791e-05
2023-01-22 17:50:56.538022: step: 956/530, loss: 0.0007470149430446327
2023-01-22 17:50:57.587841: step: 960/530, loss: 0.001472724019549787
2023-01-22 17:50:58.643632: step: 964/530, loss: 0.0018367304001003504
2023-01-22 17:50:59.692739: step: 968/530, loss: 0.003949539735913277
2023-01-22 17:51:00.753937: step: 972/530, loss: 0.003995168022811413
2023-01-22 17:51:01.798172: step: 976/530, loss: 0.00022083039220888168
2023-01-22 17:51:02.846612: step: 980/530, loss: 0.002190894214436412
2023-01-22 17:51:03.893702: step: 984/530, loss: 3.09558272419963e-05
2023-01-22 17:51:04.949899: step: 988/530, loss: 0.0006759811658412218
2023-01-22 17:51:05.989896: step: 992/530, loss: 0.003623665077611804
2023-01-22 17:51:07.041916: step: 996/530, loss: 0.0014246400678530335
2023-01-22 17:51:08.082049: step: 1000/530, loss: 0.0017691166140139103
2023-01-22 17:51:09.121265: step: 1004/530, loss: 0.0010221840348094702
2023-01-22 17:51:10.184309: step: 1008/530, loss: 0.0018256825860589743
2023-01-22 17:51:11.236666: step: 1012/530, loss: 0.00019149246509186924
2023-01-22 17:51:12.274920: step: 1016/530, loss: 0.00151846616063267
2023-01-22 17:51:13.316733: step: 1020/530, loss: 0.00743184145539999
2023-01-22 17:51:14.374369: step: 1024/530, loss: 0.010206153616309166
2023-01-22 17:51:15.420862: step: 1028/530, loss: 7.514876779168844e-05
2023-01-22 17:51:16.468862: step: 1032/530, loss: 0.002149930689483881
2023-01-22 17:51:17.518229: step: 1036/530, loss: 0.0023523711133748293
2023-01-22 17:51:18.553681: step: 1040/530, loss: 0.000745853059925139
2023-01-22 17:51:19.596046: step: 1044/530, loss: 0.0012126355431973934
2023-01-22 17:51:20.661975: step: 1048/530, loss: 0.0017065427964553237
2023-01-22 17:51:21.705357: step: 1052/530, loss: 5.352330481400713e-05
2023-01-22 17:51:22.763349: step: 1056/530, loss: 0.003741718828678131
2023-01-22 17:51:23.793808: step: 1060/530, loss: 0.00025653469492681324
2023-01-22 17:51:24.851719: step: 1064/530, loss: 0.003100144909694791
2023-01-22 17:51:25.892575: step: 1068/530, loss: 0.00930363405495882
2023-01-22 17:51:26.939923: step: 1072/530, loss: 0.0038777559529989958
2023-01-22 17:51:27.975184: step: 1076/530, loss: 0.004641006235033274
2023-01-22 17:51:29.025086: step: 1080/530, loss: 0.0009079177980311215
2023-01-22 17:51:30.070279: step: 1084/530, loss: 0.004109915345907211
2023-01-22 17:51:31.121765: step: 1088/530, loss: 0.00040428826468996704
2023-01-22 17:51:32.180811: step: 1092/530, loss: 1.1030459063476883e-05
2023-01-22 17:51:33.226241: step: 1096/530, loss: 0.007341318763792515
2023-01-22 17:51:34.275723: step: 1100/530, loss: 0.003847693093121052
2023-01-22 17:51:35.323868: step: 1104/530, loss: 0.0004101607482880354
2023-01-22 17:51:36.381654: step: 1108/530, loss: 0.01341897714883089
2023-01-22 17:51:37.456556: step: 1112/530, loss: 0.024929696694016457
2023-01-22 17:51:38.507851: step: 1116/530, loss: 0.008607692085206509
2023-01-22 17:51:39.587729: step: 1120/530, loss: 0.001027898513711989
2023-01-22 17:51:40.630206: step: 1124/530, loss: 0.0032819602638483047
2023-01-22 17:51:41.675809: step: 1128/530, loss: 0.002644893480464816
2023-01-22 17:51:42.728524: step: 1132/530, loss: 0.0008560423157177866
2023-01-22 17:51:43.791959: step: 1136/530, loss: 0.006139503791928291
2023-01-22 17:51:44.842826: step: 1140/530, loss: 0.0020366166718304157
2023-01-22 17:51:45.873285: step: 1144/530, loss: 0.002872372744604945
2023-01-22 17:51:46.914354: step: 1148/530, loss: 0.00046451052185148
2023-01-22 17:51:47.966846: step: 1152/530, loss: 0.0019574458710849285
2023-01-22 17:51:49.001488: step: 1156/530, loss: 0.0006437331321649253
2023-01-22 17:51:50.036621: step: 1160/530, loss: 2.329449671378825e-05
2023-01-22 17:51:51.095925: step: 1164/530, loss: 0.0019324080785736442
2023-01-22 17:51:52.138445: step: 1168/530, loss: 0.011647249571979046
2023-01-22 17:51:53.183680: step: 1172/530, loss: 0.000496596738230437
2023-01-22 17:51:54.231662: step: 1176/530, loss: 0.0005437369109131396
2023-01-22 17:51:55.276773: step: 1180/530, loss: 0.01833151839673519
2023-01-22 17:51:56.323065: step: 1184/530, loss: 0.010786481201648712
2023-01-22 17:51:57.365726: step: 1188/530, loss: 0.0006603167857974768
2023-01-22 17:51:58.407740: step: 1192/530, loss: 7.851884583942592e-05
2023-01-22 17:51:59.451346: step: 1196/530, loss: 0.0007735260878689587
2023-01-22 17:52:00.500523: step: 1200/530, loss: 2.752328555288841e-06
2023-01-22 17:52:01.533191: step: 1204/530, loss: 0.00020667779608629644
2023-01-22 17:52:02.562446: step: 1208/530, loss: 0.003709016367793083
2023-01-22 17:52:03.623653: step: 1212/530, loss: 0.013338254764676094
2023-01-22 17:52:04.672029: step: 1216/530, loss: 0.008043644949793816
2023-01-22 17:52:05.717955: step: 1220/530, loss: 0.0032047561835497618
2023-01-22 17:52:06.763550: step: 1224/530, loss: 3.533139897626825e-05
2023-01-22 17:52:07.827942: step: 1228/530, loss: 0.004353194963186979
2023-01-22 17:52:08.897975: step: 1232/530, loss: 0.0011323824292048812
2023-01-22 17:52:09.964107: step: 1236/530, loss: 0.00013187172589823604
2023-01-22 17:52:11.025960: step: 1240/530, loss: 0.000815546081867069
2023-01-22 17:52:12.085918: step: 1244/530, loss: 0.004494329448789358
2023-01-22 17:52:13.125902: step: 1248/530, loss: 0.00019237086235079914
2023-01-22 17:52:14.162474: step: 1252/530, loss: 0.0023239210713654757
2023-01-22 17:52:15.229351: step: 1256/530, loss: 0.001449662260711193
2023-01-22 17:52:16.262569: step: 1260/530, loss: 9.828144357015844e-06
2023-01-22 17:52:17.321052: step: 1264/530, loss: 0.006015796214342117
2023-01-22 17:52:18.383631: step: 1268/530, loss: 0.0027719291392713785
2023-01-22 17:52:19.428206: step: 1272/530, loss: 0.0003320998512208462
2023-01-22 17:52:20.482148: step: 1276/530, loss: 0.0001519552170066163
2023-01-22 17:52:21.517033: step: 1280/530, loss: 5.461227192427032e-05
2023-01-22 17:52:22.572984: step: 1284/530, loss: 0.002218343084678054
2023-01-22 17:52:23.626042: step: 1288/530, loss: 7.999590889085084e-05
2023-01-22 17:52:24.670793: step: 1292/530, loss: 0.002180244540795684
2023-01-22 17:52:25.711502: step: 1296/530, loss: 0.0031195455230772495
2023-01-22 17:52:26.762027: step: 1300/530, loss: 0.00729980506002903
2023-01-22 17:52:27.811393: step: 1304/530, loss: 0.0004911327268928289
2023-01-22 17:52:28.851548: step: 1308/530, loss: 0.004196009133011103
2023-01-22 17:52:29.892255: step: 1312/530, loss: 0.0036911985371261835
2023-01-22 17:52:30.931722: step: 1316/530, loss: 0.0025881011970341206
2023-01-22 17:52:31.987008: step: 1320/530, loss: 8.970306953415275e-05
2023-01-22 17:52:33.045939: step: 1324/530, loss: 0.0012659200001507998
2023-01-22 17:52:34.092221: step: 1328/530, loss: 0.00011973016808042303
2023-01-22 17:52:35.157617: step: 1332/530, loss: 1.3773040336673148e-05
2023-01-22 17:52:36.193006: step: 1336/530, loss: 0.0023343595676124096
2023-01-22 17:52:37.237750: step: 1340/530, loss: 0.005378260277211666
2023-01-22 17:52:38.266701: step: 1344/530, loss: 1.0857224879146088e-06
2023-01-22 17:52:39.300295: step: 1348/530, loss: 0.0007610554457642138
2023-01-22 17:52:40.342272: step: 1352/530, loss: 9.709344885777682e-05
2023-01-22 17:52:41.385062: step: 1356/530, loss: 0.0
2023-01-22 17:52:42.431557: step: 1360/530, loss: 1.2003538074623066e-07
2023-01-22 17:52:43.485530: step: 1364/530, loss: 0.0001666335592744872
2023-01-22 17:52:44.535711: step: 1368/530, loss: 0.005986809730529785
2023-01-22 17:52:45.583698: step: 1372/530, loss: 0.0008152473019436002
2023-01-22 17:52:46.632753: step: 1376/530, loss: 6.772181677661138e-07
2023-01-22 17:52:47.678258: step: 1380/530, loss: 0.016878999769687653
2023-01-22 17:52:48.724227: step: 1384/530, loss: 0.0006100684404373169
2023-01-22 17:52:49.783082: step: 1388/530, loss: 0.0013175173662602901
2023-01-22 17:52:50.824366: step: 1392/530, loss: 0.000431124703027308
2023-01-22 17:52:51.872176: step: 1396/530, loss: 1.8923074094345793e-06
2023-01-22 17:52:52.913232: step: 1400/530, loss: 0.0026847615372389555
2023-01-22 17:52:53.953569: step: 1404/530, loss: 0.0049303616397082806
2023-01-22 17:52:54.987704: step: 1408/530, loss: 0.0003786585293710232
2023-01-22 17:52:56.036411: step: 1412/530, loss: 0.0028419815935194492
2023-01-22 17:52:57.072885: step: 1416/530, loss: 0.0011984541779384017
2023-01-22 17:52:58.124277: step: 1420/530, loss: 7.219785038614646e-05
2023-01-22 17:52:59.166847: step: 1424/530, loss: 0.004033208824694157
2023-01-22 17:53:00.221086: step: 1428/530, loss: 0.02244948036968708
2023-01-22 17:53:01.266800: step: 1432/530, loss: 0.007330878637731075
2023-01-22 17:53:02.313379: step: 1436/530, loss: 0.004972193855792284
2023-01-22 17:53:03.380394: step: 1440/530, loss: 4.1494113247608766e-05
2023-01-22 17:53:04.455357: step: 1444/530, loss: 0.0028021596372127533
2023-01-22 17:53:05.509383: step: 1448/530, loss: 0.0029528236482292414
2023-01-22 17:53:06.540252: step: 1452/530, loss: 0.0008357432670891285
2023-01-22 17:53:07.582815: step: 1456/530, loss: 0.0011378773488104343
2023-01-22 17:53:08.621208: step: 1460/530, loss: 0.009751907549798489
2023-01-22 17:53:09.663525: step: 1464/530, loss: 0.0014992222422733903
2023-01-22 17:53:10.719679: step: 1468/530, loss: 0.002464254852384329
2023-01-22 17:53:11.771171: step: 1472/530, loss: 3.395184830878861e-05
2023-01-22 17:53:12.838133: step: 1476/530, loss: 0.004051372408866882
2023-01-22 17:53:13.875498: step: 1480/530, loss: 0.0015022637089714408
2023-01-22 17:53:14.916134: step: 1484/530, loss: 0.004045954905450344
2023-01-22 17:53:15.971838: step: 1488/530, loss: 0.004026063717901707
2023-01-22 17:53:17.016194: step: 1492/530, loss: 2.733970177359879e-05
2023-01-22 17:53:18.072704: step: 1496/530, loss: 0.005752569530159235
2023-01-22 17:53:19.138224: step: 1500/530, loss: 0.0016751571092754602
2023-01-22 17:53:20.197734: step: 1504/530, loss: 0.002858343068510294
2023-01-22 17:53:21.237570: step: 1508/530, loss: 0.0002025643625529483
2023-01-22 17:53:22.276880: step: 1512/530, loss: 0.004421581048518419
2023-01-22 17:53:23.341881: step: 1516/530, loss: 0.00011061177065130323
2023-01-22 17:53:24.376675: step: 1520/530, loss: 0.0016932482831180096
2023-01-22 17:53:25.415171: step: 1524/530, loss: 0.00027803966077044606
2023-01-22 17:53:26.444743: step: 1528/530, loss: 0.001186358043923974
2023-01-22 17:53:27.483392: step: 1532/530, loss: 0.0011938621755689383
2023-01-22 17:53:28.525999: step: 1536/530, loss: 0.0001307249185629189
2023-01-22 17:53:29.568385: step: 1540/530, loss: 0.000702088582329452
2023-01-22 17:53:30.611645: step: 1544/530, loss: 0.0026872078888118267
2023-01-22 17:53:31.653363: step: 1548/530, loss: 0.00996373686939478
2023-01-22 17:53:32.695641: step: 1552/530, loss: 0.0012249033898115158
2023-01-22 17:53:33.739704: step: 1556/530, loss: 0.0033129968214780092
2023-01-22 17:53:34.792204: step: 1560/530, loss: 0.0001788036315701902
2023-01-22 17:53:35.822351: step: 1564/530, loss: 0.0005180523148737848
2023-01-22 17:53:36.865595: step: 1568/530, loss: 0.008451927453279495
2023-01-22 17:53:37.905771: step: 1572/530, loss: 5.736790598120933e-08
2023-01-22 17:53:38.967042: step: 1576/530, loss: 0.00038226452306844294
2023-01-22 17:53:40.026176: step: 1580/530, loss: 0.0011892697075381875
2023-01-22 17:53:41.072824: step: 1584/530, loss: 1.6682479326846078e-05
2023-01-22 17:53:42.112820: step: 1588/530, loss: 0.0036256397143006325
2023-01-22 17:53:43.149577: step: 1592/530, loss: 5.045654688728973e-06
2023-01-22 17:53:44.183649: step: 1596/530, loss: 0.0005896550719626248
2023-01-22 17:53:45.221368: step: 1600/530, loss: 0.005167139694094658
2023-01-22 17:53:46.262194: step: 1604/530, loss: 0.009650243446230888
2023-01-22 17:53:47.316858: step: 1608/530, loss: 0.0011538421967998147
2023-01-22 17:53:48.373964: step: 1612/530, loss: 0.0001134164776885882
2023-01-22 17:53:49.427676: step: 1616/530, loss: 0.002002834342420101
2023-01-22 17:53:50.464084: step: 1620/530, loss: 0.0014718525344505906
2023-01-22 17:53:51.493307: step: 1624/530, loss: 0.00032226493931375444
2023-01-22 17:53:52.557831: step: 1628/530, loss: 0.006582689471542835
2023-01-22 17:53:53.593429: step: 1632/530, loss: 1.0673220458556898e-05
2023-01-22 17:53:54.655844: step: 1636/530, loss: 0.005204511806368828
2023-01-22 17:53:55.714034: step: 1640/530, loss: 0.0005761709180660546
2023-01-22 17:53:56.774562: step: 1644/530, loss: 0.00013568585563916713
2023-01-22 17:53:57.845912: step: 1648/530, loss: 0.002421013545244932
2023-01-22 17:53:58.877618: step: 1652/530, loss: 0.0002153374080080539
2023-01-22 17:53:59.914533: step: 1656/530, loss: 0.001389373210258782
2023-01-22 17:54:00.963053: step: 1660/530, loss: 0.001180328894406557
2023-01-22 17:54:02.026504: step: 1664/530, loss: 0.004765115678310394
2023-01-22 17:54:03.058728: step: 1668/530, loss: 0.011473272927105427
2023-01-22 17:54:04.131382: step: 1672/530, loss: 0.00356234866194427
2023-01-22 17:54:05.180717: step: 1676/530, loss: 0.007072188891470432
2023-01-22 17:54:06.224750: step: 1680/530, loss: 0.0021764098200947046
2023-01-22 17:54:07.276190: step: 1684/530, loss: 0.00010520782961975783
2023-01-22 17:54:08.319126: step: 1688/530, loss: 0.001124878996051848
2023-01-22 17:54:09.363609: step: 1692/530, loss: 0.0007139877998270094
2023-01-22 17:54:10.401948: step: 1696/530, loss: 0.0
2023-01-22 17:54:11.466779: step: 1700/530, loss: 0.0017955448711290956
2023-01-22 17:54:12.517787: step: 1704/530, loss: 9.446531294088345e-06
2023-01-22 17:54:13.573506: step: 1708/530, loss: 3.950011887354776e-05
2023-01-22 17:54:14.631472: step: 1712/530, loss: 0.00271967938169837
2023-01-22 17:54:15.659251: step: 1716/530, loss: 0.0005915315705351532
2023-01-22 17:54:16.718348: step: 1720/530, loss: 8.707438973942772e-05
2023-01-22 17:54:17.778758: step: 1724/530, loss: 0.001272302703000605
2023-01-22 17:54:18.828254: step: 1728/530, loss: 0.00048801334924064577
2023-01-22 17:54:19.871876: step: 1732/530, loss: 0.0005772834992967546
2023-01-22 17:54:20.929008: step: 1736/530, loss: 0.0004037150356452912
2023-01-22 17:54:21.972104: step: 1740/530, loss: 0.0006433365633711219
2023-01-22 17:54:23.000783: step: 1744/530, loss: 0.0009077931172214448
2023-01-22 17:54:24.052842: step: 1748/530, loss: 0.00032269800431095064
2023-01-22 17:54:25.094743: step: 1752/530, loss: 0.0003715303319040686
2023-01-22 17:54:26.146824: step: 1756/530, loss: 0.032732587307691574
2023-01-22 17:54:27.188696: step: 1760/530, loss: 0.0027986119966953993
2023-01-22 17:54:28.246788: step: 1764/530, loss: 0.00505076115950942
2023-01-22 17:54:29.290943: step: 1768/530, loss: 0.0034972019493579865
2023-01-22 17:54:30.350625: step: 1772/530, loss: 0.010578633286058903
2023-01-22 17:54:31.408658: step: 1776/530, loss: 0.003582973964512348
2023-01-22 17:54:32.499066: step: 1780/530, loss: 0.006506519857794046
2023-01-22 17:54:33.542765: step: 1784/530, loss: 0.0018352270126342773
2023-01-22 17:54:34.587268: step: 1788/530, loss: 0.0013394705019891262
2023-01-22 17:54:35.639867: step: 1792/530, loss: 0.0013189377496019006
2023-01-22 17:54:36.676401: step: 1796/530, loss: 0.00013744382886216044
2023-01-22 17:54:37.724615: step: 1800/530, loss: 0.005391889251768589
2023-01-22 17:54:38.772402: step: 1804/530, loss: 0.011479792185127735
2023-01-22 17:54:39.820672: step: 1808/530, loss: 5.284298458718695e-05
2023-01-22 17:54:40.860193: step: 1812/530, loss: 0.0025754254311323166
2023-01-22 17:54:41.881606: step: 1816/530, loss: 0.00801665149629116
2023-01-22 17:54:42.934897: step: 1820/530, loss: 0.0005745472153648734
2023-01-22 17:54:43.995573: step: 1824/530, loss: 0.006258128676563501
2023-01-22 17:54:45.037977: step: 1828/530, loss: 0.0145878279581666
2023-01-22 17:54:46.105114: step: 1832/530, loss: 0.004535536281764507
2023-01-22 17:54:47.135563: step: 1836/530, loss: 0.0010435067815706134
2023-01-22 17:54:48.192521: step: 1840/530, loss: 0.0018674947787076235
2023-01-22 17:54:49.245094: step: 1844/530, loss: 0.014176220633089542
2023-01-22 17:54:50.294692: step: 1848/530, loss: 0.0014461047248914838
2023-01-22 17:54:51.345223: step: 1852/530, loss: 0.004165360704064369
2023-01-22 17:54:52.378514: step: 1856/530, loss: 0.005053696688264608
2023-01-22 17:54:53.442367: step: 1860/530, loss: 1.737669481371995e-05
2023-01-22 17:54:54.476977: step: 1864/530, loss: 0.0047654276713728905
2023-01-22 17:54:55.517092: step: 1868/530, loss: 0.0006152056157588959
2023-01-22 17:54:56.555554: step: 1872/530, loss: 0.0002627117501106113
2023-01-22 17:54:57.611623: step: 1876/530, loss: 0.0010582341346889734
2023-01-22 17:54:58.664932: step: 1880/530, loss: 1.377479321718056e-07
2023-01-22 17:54:59.713990: step: 1884/530, loss: 6.542880328197498e-06
2023-01-22 17:55:00.739902: step: 1888/530, loss: 0.01235949993133545
2023-01-22 17:55:01.782165: step: 1892/530, loss: 0.00010742411541286856
2023-01-22 17:55:02.833043: step: 1896/530, loss: 0.00777466082945466
2023-01-22 17:55:03.869010: step: 1900/530, loss: 0.0027790055610239506
2023-01-22 17:55:04.918733: step: 1904/530, loss: 0.0025619480293244123
2023-01-22 17:55:05.967409: step: 1908/530, loss: 0.0007179515087045729
2023-01-22 17:55:07.012819: step: 1912/530, loss: 0.0018334188498556614
2023-01-22 17:55:08.059073: step: 1916/530, loss: 0.0034390143118798733
2023-01-22 17:55:09.116216: step: 1920/530, loss: 0.0011282347841188312
2023-01-22 17:55:10.167080: step: 1924/530, loss: 0.020094776526093483
2023-01-22 17:55:11.198338: step: 1928/530, loss: 0.00018194942094851285
2023-01-22 17:55:12.251360: step: 1932/530, loss: 1.9138960851705633e-05
2023-01-22 17:55:13.306835: step: 1936/530, loss: 0.0009774244390428066
2023-01-22 17:55:14.343091: step: 1940/530, loss: 0.0002496328379493207
2023-01-22 17:55:15.378267: step: 1944/530, loss: 0.017487987875938416
2023-01-22 17:55:16.430687: step: 1948/530, loss: 0.000737216672860086
2023-01-22 17:55:17.477614: step: 1952/530, loss: 0.016520904377102852
2023-01-22 17:55:18.545837: step: 1956/530, loss: 0.01425775233656168
2023-01-22 17:55:19.592413: step: 1960/530, loss: 1.270201028091833e-05
2023-01-22 17:55:20.660446: step: 1964/530, loss: 0.050946805626153946
2023-01-22 17:55:21.709605: step: 1968/530, loss: 0.007083595730364323
2023-01-22 17:55:22.776169: step: 1972/530, loss: 0.00011740416084649041
2023-01-22 17:55:23.828868: step: 1976/530, loss: 0.0014218618161976337
2023-01-22 17:55:24.869238: step: 1980/530, loss: 0.00011127001198474318
2023-01-22 17:55:25.917535: step: 1984/530, loss: 0.0009608388063497841
2023-01-22 17:55:26.958724: step: 1988/530, loss: 0.017436038702726364
2023-01-22 17:55:28.026667: step: 1992/530, loss: 0.0
2023-01-22 17:55:29.081725: step: 1996/530, loss: 0.005568573717027903
2023-01-22 17:55:30.121477: step: 2000/530, loss: 0.005121793132275343
2023-01-22 17:55:31.156782: step: 2004/530, loss: 0.001218840479850769
2023-01-22 17:55:32.204652: step: 2008/530, loss: 0.0003862846933770925
2023-01-22 17:55:33.234610: step: 2012/530, loss: 0.0006322905537672341
2023-01-22 17:55:34.277243: step: 2016/530, loss: 0.0014480248792096972
2023-01-22 17:55:35.342606: step: 2020/530, loss: 0.0038923274260014296
2023-01-22 17:55:36.395412: step: 2024/530, loss: 0.0040010022930800915
2023-01-22 17:55:37.434716: step: 2028/530, loss: 0.011293146759271622
2023-01-22 17:55:38.488988: step: 2032/530, loss: 0.0035857250913977623
2023-01-22 17:55:39.532620: step: 2036/530, loss: 0.0004058224440086633
2023-01-22 17:55:40.585903: step: 2040/530, loss: 0.0037106696981936693
2023-01-22 17:55:41.625967: step: 2044/530, loss: 0.00032576799276284873
2023-01-22 17:55:42.676770: step: 2048/530, loss: 1.199520482941807e-07
2023-01-22 17:55:43.726266: step: 2052/530, loss: 0.0009816251695156097
2023-01-22 17:55:44.772762: step: 2056/530, loss: 0.0001089588986360468
2023-01-22 17:55:45.823686: step: 2060/530, loss: 0.0029616826213896275
2023-01-22 17:55:46.858781: step: 2064/530, loss: 0.02165575884282589
2023-01-22 17:55:47.897091: step: 2068/530, loss: 0.0021646814420819283
2023-01-22 17:55:48.937239: step: 2072/530, loss: 0.0010730999056249857
2023-01-22 17:55:49.978634: step: 2076/530, loss: 0.0001871632266556844
2023-01-22 17:55:51.016971: step: 2080/530, loss: 0.0014424140099436045
2023-01-22 17:55:52.055984: step: 2084/530, loss: 0.0009144091163761914
2023-01-22 17:55:53.105737: step: 2088/530, loss: 0.002994795562699437
2023-01-22 17:55:54.155827: step: 2092/530, loss: 0.00024580780882388353
2023-01-22 17:55:55.196390: step: 2096/530, loss: 0.00043128005927428603
2023-01-22 17:55:56.232328: step: 2100/530, loss: 0.00038046660483814776
2023-01-22 17:55:57.280869: step: 2104/530, loss: 0.006865813862532377
2023-01-22 17:55:58.324502: step: 2108/530, loss: 3.880581971316133e-06
2023-01-22 17:55:59.366300: step: 2112/530, loss: 0.0022267343010753393
2023-01-22 17:56:00.396732: step: 2116/530, loss: 0.02534710057079792
2023-01-22 17:56:01.426964: step: 2120/530, loss: 0.0003853960952255875
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33962898406374503, 'r': 0.3235175521821632, 'f1': 0.33137755102040817}, 'combined': 0.24417293233082707, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.36092311592480514, 'r': 0.41035100588141904, 'f1': 0.3840532424937496}, 'combined': 0.29768720231572937, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31116347701409985, 'r': 0.3235627806522329, 'f1': 0.3172420193557706}, 'combined': 0.2337572774200415, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3592719284515713, 'r': 0.41045496972913886, 'f1': 0.38316173922376934}, 'combined': 0.29699618064234756, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33035275344955795, 'r': 0.34226300452269187, 'f1': 0.3362024294193078}, 'combined': 0.24772810588791097, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35974219775435906, 'r': 0.3881777023562661, 'f1': 0.3734193989068237}, 'combined': 0.2894447015450021, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32926829268292684, 'r': 0.38571428571428573, 'f1': 0.35526315789473684}, 'combined': 0.23684210526315788, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.4782608695652174, 'f1': 0.4313725490196078}, 'combined': 0.2156862745098039, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3462223895582329, 'r': 0.3271703036053131, 'f1': 0.33642682926829265}, 'combined': 0.24789345314505773, 'stategy': 1, 'epoch': 15}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.360310988924254, 'r': 0.40667453529318376, 'f1': 0.3820914459404006}, 'combined': 0.2961665753222244, 'stategy': 1, 'epoch': 15}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.38571428571428573, 'f1': 0.36}, 'combined': 0.24, 'stategy': 1, 'epoch': 15}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30694612711305264, 'r': 0.31801249602225184, 'f1': 0.3123813334645419}, 'combined': 0.2301757193949256, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.35172756716862835, 'r': 0.4070082785526683, 'f1': 0.37735407504499624}, 'combined': 0.2924945462071263, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41964285714285715, 'r': 0.5108695652173914, 'f1': 0.46078431372549017}, 'combined': 0.23039215686274508, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3329480866242388, 'r': 0.34558368763464636, 'f1': 0.3391482372131445}, 'combined': 0.24989870110442228, 'stategy': 1, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.3573997786742909, 'r': 0.38565012882685434, 'f1': 0.37098792233741607}, 'combined': 0.2875600163572316, 'stategy': 1, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5131578947368421, 'r': 0.33620689655172414, 'f1': 0.40625}, 'combined': 0.2708333333333333, 'stategy': 1, 'epoch': 6}