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 14:28:27.926989: step: 4/530, loss: 0.014989728108048439
2023-01-22 14:28:28.995384: step: 8/530, loss: 0.0631004273891449
2023-01-22 14:28:30.063895: step: 12/530, loss: 0.057484276592731476
2023-01-22 14:28:31.133606: step: 16/530, loss: 0.014185488224029541
2023-01-22 14:28:32.194897: step: 20/530, loss: 0.023343700915575027
2023-01-22 14:28:33.259427: step: 24/530, loss: 0.023431705310940742
2023-01-22 14:28:34.322640: step: 28/530, loss: 0.06438823789358139
2023-01-22 14:28:35.406110: step: 32/530, loss: 0.017993750050663948
2023-01-22 14:28:36.461297: step: 36/530, loss: 0.014256988652050495
2023-01-22 14:28:37.525157: step: 40/530, loss: 0.04799354448914528
2023-01-22 14:28:38.587757: step: 44/530, loss: 0.016878558322787285
2023-01-22 14:28:39.641582: step: 48/530, loss: 0.06278853863477707
2023-01-22 14:28:40.708846: step: 52/530, loss: 0.058966729789972305
2023-01-22 14:28:41.780992: step: 56/530, loss: 0.01668539270758629
2023-01-22 14:28:42.844720: step: 60/530, loss: 0.01358208991587162
2023-01-22 14:28:43.988309: step: 64/530, loss: 0.06512077152729034
2023-01-22 14:28:45.044578: step: 68/530, loss: 0.01546466164290905
2023-01-22 14:28:46.112720: step: 72/530, loss: 0.04142314940690994
2023-01-22 14:28:47.178413: step: 76/530, loss: 0.07824798673391342
2023-01-22 14:28:48.231394: step: 80/530, loss: 0.015071926638484001
2023-01-22 14:28:49.277537: step: 84/530, loss: 0.010939154773950577
2023-01-22 14:28:50.347800: step: 88/530, loss: 0.11303721368312836
2023-01-22 14:28:51.406218: step: 92/530, loss: 0.021797168999910355
2023-01-22 14:28:52.462503: step: 96/530, loss: 0.032301679253578186
2023-01-22 14:28:53.542720: step: 100/530, loss: 0.010300903581082821
2023-01-22 14:28:54.600185: step: 104/530, loss: 0.028085211291909218
2023-01-22 14:28:55.643996: step: 108/530, loss: 0.04559174180030823
2023-01-22 14:28:56.716065: step: 112/530, loss: 0.01224962342530489
2023-01-22 14:28:57.779161: step: 116/530, loss: 0.024140994995832443
2023-01-22 14:28:58.818452: step: 120/530, loss: 0.005567555315792561
2023-01-22 14:28:59.885237: step: 124/530, loss: 0.029240408912301064
2023-01-22 14:29:00.947843: step: 128/530, loss: 0.05285908281803131
2023-01-22 14:29:02.004217: step: 132/530, loss: 0.010322146117687225
2023-01-22 14:29:03.089710: step: 136/530, loss: 0.029455265030264854
2023-01-22 14:29:04.146124: step: 140/530, loss: 0.007066186983138323
2023-01-22 14:29:05.224672: step: 144/530, loss: 0.011972458101809025
2023-01-22 14:29:06.276661: step: 148/530, loss: 0.1084207221865654
2023-01-22 14:29:07.349012: step: 152/530, loss: 0.01110046822577715
2023-01-22 14:29:08.400399: step: 156/530, loss: 0.02329319156706333
2023-01-22 14:29:09.467956: step: 160/530, loss: 0.05925683677196503
2023-01-22 14:29:10.529453: step: 164/530, loss: 0.04935720935463905
2023-01-22 14:29:11.587569: step: 168/530, loss: 0.05298709124326706
2023-01-22 14:29:12.635166: step: 172/530, loss: 0.012919852510094643
2023-01-22 14:29:13.685908: step: 176/530, loss: 0.02422485686838627
2023-01-22 14:29:14.759435: step: 180/530, loss: 0.017603116109967232
2023-01-22 14:29:15.820242: step: 184/530, loss: 0.06705053895711899
2023-01-22 14:29:16.859012: step: 188/530, loss: 0.0136328199878335
2023-01-22 14:29:17.914907: step: 192/530, loss: 0.015436515212059021
2023-01-22 14:29:18.967059: step: 196/530, loss: 0.009641746990382671
2023-01-22 14:29:20.016150: step: 200/530, loss: 0.01774834841489792
2023-01-22 14:29:21.083940: step: 204/530, loss: 0.028291190043091774
2023-01-22 14:29:22.146148: step: 208/530, loss: 0.05181780084967613
2023-01-22 14:29:23.198934: step: 212/530, loss: 0.013797377236187458
2023-01-22 14:29:24.225741: step: 216/530, loss: 0.020691271871328354
2023-01-22 14:29:25.286467: step: 220/530, loss: 0.043441515415906906
2023-01-22 14:29:26.349639: step: 224/530, loss: 0.01866997219622135
2023-01-22 14:29:27.393649: step: 228/530, loss: 0.018745601177215576
2023-01-22 14:29:28.457352: step: 232/530, loss: 0.07132137566804886
2023-01-22 14:29:29.520806: step: 236/530, loss: 0.054921817034482956
2023-01-22 14:29:30.580836: step: 240/530, loss: 0.009442034177482128
2023-01-22 14:29:31.627608: step: 244/530, loss: 0.007842033170163631
2023-01-22 14:29:32.677519: step: 248/530, loss: 0.0603717677295208
2023-01-22 14:29:33.752295: step: 252/530, loss: 0.01621413044631481
2023-01-22 14:29:34.806066: step: 256/530, loss: 0.05394862964749336
2023-01-22 14:29:35.856155: step: 260/530, loss: 0.0104429442435503
2023-01-22 14:29:36.910317: step: 264/530, loss: 0.0564584918320179
2023-01-22 14:29:37.983236: step: 268/530, loss: 0.019484298303723335
2023-01-22 14:29:39.027386: step: 272/530, loss: 0.019629139453172684
2023-01-22 14:29:40.068271: step: 276/530, loss: 0.021460773423314095
2023-01-22 14:29:41.111979: step: 280/530, loss: 0.05503295361995697
2023-01-22 14:29:42.176314: step: 284/530, loss: 0.009837611578404903
2023-01-22 14:29:43.232535: step: 288/530, loss: 0.011039389297366142
2023-01-22 14:29:44.291028: step: 292/530, loss: 0.057780586183071136
2023-01-22 14:29:45.350629: step: 296/530, loss: 0.014904126524925232
2023-01-22 14:29:46.399651: step: 300/530, loss: 0.016140734776854515
2023-01-22 14:29:47.484559: step: 304/530, loss: 0.009469042532145977
2023-01-22 14:29:48.523693: step: 308/530, loss: 0.009803948923945427
2023-01-22 14:29:49.580458: step: 312/530, loss: 0.01831057481467724
2023-01-22 14:29:50.633442: step: 316/530, loss: 0.021061651408672333
2023-01-22 14:29:51.686179: step: 320/530, loss: 0.009302419610321522
2023-01-22 14:29:52.734257: step: 324/530, loss: 0.014836013317108154
2023-01-22 14:29:53.799307: step: 328/530, loss: 0.01203369814902544
2023-01-22 14:29:54.850566: step: 332/530, loss: 0.01554011832922697
2023-01-22 14:29:55.900580: step: 336/530, loss: 0.01864892616868019
2023-01-22 14:29:56.961048: step: 340/530, loss: 0.020686931908130646
2023-01-22 14:29:58.002576: step: 344/530, loss: 0.054095566272735596
2023-01-22 14:29:59.065261: step: 348/530, loss: 0.01348794437944889
2023-01-22 14:30:00.122045: step: 352/530, loss: 0.03215435519814491
2023-01-22 14:30:01.185502: step: 356/530, loss: 0.0546780526638031
2023-01-22 14:30:02.245326: step: 360/530, loss: 0.015380472876131535
2023-01-22 14:30:03.308458: step: 364/530, loss: 0.042847588658332825
2023-01-22 14:30:04.361019: step: 368/530, loss: 0.04920646920800209
2023-01-22 14:30:05.405152: step: 372/530, loss: 0.0374562032520771
2023-01-22 14:30:06.484894: step: 376/530, loss: 0.008779056370258331
2023-01-22 14:30:07.535433: step: 380/530, loss: 0.020624835044145584
2023-01-22 14:30:08.597219: step: 384/530, loss: 0.02881811000406742
2023-01-22 14:30:09.664420: step: 388/530, loss: 0.010995946824550629
2023-01-22 14:30:10.715791: step: 392/530, loss: 0.01900155283510685
2023-01-22 14:30:11.781084: step: 396/530, loss: 0.010911948047578335
2023-01-22 14:30:12.831994: step: 400/530, loss: 0.012622319161891937
2023-01-22 14:30:13.904308: step: 404/530, loss: 0.0487946979701519
2023-01-22 14:30:14.960827: step: 408/530, loss: 0.017283709719777107
2023-01-22 14:30:16.026518: step: 412/530, loss: 0.023072047159075737
2023-01-22 14:30:17.078359: step: 416/530, loss: 0.011532754637300968
2023-01-22 14:30:18.136943: step: 420/530, loss: 0.034171223640441895
2023-01-22 14:30:19.206745: step: 424/530, loss: 0.011274424381554127
2023-01-22 14:30:20.265687: step: 428/530, loss: 0.012324047274887562
2023-01-22 14:30:21.324415: step: 432/530, loss: 0.024326754733920097
2023-01-22 14:30:22.376697: step: 436/530, loss: 0.007780241314321756
2023-01-22 14:30:23.444454: step: 440/530, loss: 0.01872764155268669
2023-01-22 14:30:24.505137: step: 444/530, loss: 0.011733146384358406
2023-01-22 14:30:25.571829: step: 448/530, loss: 0.047770146280527115
2023-01-22 14:30:26.624316: step: 452/530, loss: 0.016551673412322998
2023-01-22 14:30:27.688549: step: 456/530, loss: 0.02890522964298725
2023-01-22 14:30:28.745160: step: 460/530, loss: 0.013094899244606495
2023-01-22 14:30:29.789946: step: 464/530, loss: 0.04893617704510689
2023-01-22 14:30:30.836405: step: 468/530, loss: 0.01000905130058527
2023-01-22 14:30:31.906252: step: 472/530, loss: 0.03276755288243294
2023-01-22 14:30:32.956246: step: 476/530, loss: 0.011166263371706009
2023-01-22 14:30:34.014955: step: 480/530, loss: 0.00775465602055192
2023-01-22 14:30:35.063894: step: 484/530, loss: 0.01759321428835392
2023-01-22 14:30:36.111909: step: 488/530, loss: 0.015101979486644268
2023-01-22 14:30:37.187517: step: 492/530, loss: 0.06601301580667496
2023-01-22 14:30:38.251972: step: 496/530, loss: 0.019960390403866768
2023-01-22 14:30:39.314542: step: 500/530, loss: 0.01699841395020485
2023-01-22 14:30:40.371963: step: 504/530, loss: 0.03768926113843918
2023-01-22 14:30:41.427307: step: 508/530, loss: 0.00735285971313715
2023-01-22 14:30:42.485513: step: 512/530, loss: 0.05614430457353592
2023-01-22 14:30:43.536708: step: 516/530, loss: 0.012637794949114323
2023-01-22 14:30:44.606484: step: 520/530, loss: 0.057916633784770966
2023-01-22 14:30:45.659524: step: 524/530, loss: 0.010749287903308868
2023-01-22 14:30:46.702953: step: 528/530, loss: 0.008063401095569134
2023-01-22 14:30:47.758166: step: 532/530, loss: 0.02903282269835472
2023-01-22 14:30:48.812645: step: 536/530, loss: 0.023172693327069283
2023-01-22 14:30:49.885833: step: 540/530, loss: 0.015488462522625923
2023-01-22 14:30:50.939746: step: 544/530, loss: 0.026907317340373993
2023-01-22 14:30:51.991890: step: 548/530, loss: 0.045936115086078644
2023-01-22 14:30:53.067421: step: 552/530, loss: 0.011412173509597778
2023-01-22 14:30:54.127458: step: 556/530, loss: 0.04243732988834381
2023-01-22 14:30:55.180787: step: 560/530, loss: 0.04376460239291191
2023-01-22 14:30:56.241678: step: 564/530, loss: 0.026789255440235138
2023-01-22 14:30:57.309108: step: 568/530, loss: 0.012236343696713448
2023-01-22 14:30:58.375749: step: 572/530, loss: 0.012834625318646431
2023-01-22 14:30:59.422985: step: 576/530, loss: 0.016574393957853317
2023-01-22 14:31:00.474551: step: 580/530, loss: 0.009535718709230423
2023-01-22 14:31:01.538403: step: 584/530, loss: 0.012673421762883663
2023-01-22 14:31:02.609223: step: 588/530, loss: 0.018470723181962967
2023-01-22 14:31:03.653388: step: 592/530, loss: 0.0056436434388160706
2023-01-22 14:31:04.724169: step: 596/530, loss: 0.016215182840824127
2023-01-22 14:31:05.782173: step: 600/530, loss: 0.0062405942007899284
2023-01-22 14:31:06.842144: step: 604/530, loss: 0.00820606853812933
2023-01-22 14:31:07.910490: step: 608/530, loss: 0.03268307074904442
2023-01-22 14:31:08.980236: step: 612/530, loss: 0.009284308180212975
2023-01-22 14:31:10.042055: step: 616/530, loss: 0.0331835076212883
2023-01-22 14:31:11.103610: step: 620/530, loss: 0.007031688001006842
2023-01-22 14:31:12.183733: step: 624/530, loss: 0.06537856161594391
2023-01-22 14:31:13.241075: step: 628/530, loss: 0.02514232136309147
2023-01-22 14:31:14.282011: step: 632/530, loss: 0.00874092523008585
2023-01-22 14:31:15.332965: step: 636/530, loss: 0.06390761584043503
2023-01-22 14:31:16.378715: step: 640/530, loss: 0.034691959619522095
2023-01-22 14:31:17.424546: step: 644/530, loss: 0.05095821991562843
2023-01-22 14:31:18.482213: step: 648/530, loss: 0.012088949792087078
2023-01-22 14:31:19.575391: step: 652/530, loss: 0.014043556526303291
2023-01-22 14:31:20.628975: step: 656/530, loss: 0.012328085489571095
2023-01-22 14:31:21.671268: step: 660/530, loss: 0.03906030207872391
2023-01-22 14:31:22.717500: step: 664/530, loss: 0.015492179431021214
2023-01-22 14:31:23.775565: step: 668/530, loss: 0.01013824064284563
2023-01-22 14:31:24.823781: step: 672/530, loss: 0.008601384237408638
2023-01-22 14:31:25.866130: step: 676/530, loss: 0.014922229573130608
2023-01-22 14:31:26.912235: step: 680/530, loss: 0.009068300947546959
2023-01-22 14:31:27.965839: step: 684/530, loss: 0.0280601903796196
2023-01-22 14:31:29.034830: step: 688/530, loss: 0.05199253559112549
2023-01-22 14:31:30.081888: step: 692/530, loss: 0.009235409088432789
2023-01-22 14:31:31.138766: step: 696/530, loss: 0.02695978619158268
2023-01-22 14:31:32.191875: step: 700/530, loss: 0.006813299376517534
2023-01-22 14:31:33.260097: step: 704/530, loss: 0.010859019123017788
2023-01-22 14:31:34.317343: step: 708/530, loss: 0.051554251462221146
2023-01-22 14:31:35.380363: step: 712/530, loss: 0.01295298058539629
2023-01-22 14:31:36.456546: step: 716/530, loss: 0.019465964287519455
2023-01-22 14:31:37.513729: step: 720/530, loss: 0.01544218510389328
2023-01-22 14:31:38.573011: step: 724/530, loss: 0.03997999429702759
2023-01-22 14:31:39.637015: step: 728/530, loss: 0.05005812272429466
2023-01-22 14:31:40.680251: step: 732/530, loss: 0.014670837670564651
2023-01-22 14:31:41.733229: step: 736/530, loss: 0.00936712697148323
2023-01-22 14:31:42.811546: step: 740/530, loss: 0.1010412722826004
2023-01-22 14:31:43.879521: step: 744/530, loss: 0.035943444818258286
2023-01-22 14:31:44.944335: step: 748/530, loss: 0.024367138743400574
2023-01-22 14:31:46.000304: step: 752/530, loss: 0.00898853037506342
2023-01-22 14:31:47.057782: step: 756/530, loss: 0.0656907930970192
2023-01-22 14:31:48.111316: step: 760/530, loss: 0.003028588369488716
2023-01-22 14:31:49.158165: step: 764/530, loss: 0.020819412544369698
2023-01-22 14:31:50.224025: step: 768/530, loss: 0.0076109240762889385
2023-01-22 14:31:51.277944: step: 772/530, loss: 0.005995367653667927
2023-01-22 14:31:52.345174: step: 776/530, loss: 0.011457452550530434
2023-01-22 14:31:53.399920: step: 780/530, loss: 0.01923304609954357
2023-01-22 14:31:54.434417: step: 784/530, loss: 0.004144433420151472
2023-01-22 14:31:55.483485: step: 788/530, loss: 0.0
2023-01-22 14:31:56.546118: step: 792/530, loss: 0.01116340234875679
2023-01-22 14:31:57.604091: step: 796/530, loss: 0.0073156291618943214
2023-01-22 14:31:58.676296: step: 800/530, loss: 0.03794460371136665
2023-01-22 14:31:59.748962: step: 804/530, loss: 0.02856852486729622
2023-01-22 14:32:00.813876: step: 808/530, loss: 0.007266498636454344
2023-01-22 14:32:01.881493: step: 812/530, loss: 0.010797679424285889
2023-01-22 14:32:02.923704: step: 816/530, loss: 0.053594592958688736
2023-01-22 14:32:03.987413: step: 820/530, loss: 0.004362649284303188
2023-01-22 14:32:05.028574: step: 824/530, loss: 0.013535166159272194
2023-01-22 14:32:06.079116: step: 828/530, loss: 0.013190332800149918
2023-01-22 14:32:07.132979: step: 832/530, loss: 0.010341054759919643
2023-01-22 14:32:08.183142: step: 836/530, loss: 0.010193286463618279
2023-01-22 14:32:09.229700: step: 840/530, loss: 0.021329592913389206
2023-01-22 14:32:10.291264: step: 844/530, loss: 0.007516507524996996
2023-01-22 14:32:11.336911: step: 848/530, loss: 0.011846790090203285
2023-01-22 14:32:12.395071: step: 852/530, loss: 0.011247259564697742
2023-01-22 14:32:13.456873: step: 856/530, loss: 0.05322021245956421
2023-01-22 14:32:14.517944: step: 860/530, loss: 0.010131759569048882
2023-01-22 14:32:15.578334: step: 864/530, loss: 0.04282288998365402
2023-01-22 14:32:16.642053: step: 868/530, loss: 0.008373168297111988
2023-01-22 14:32:17.719735: step: 872/530, loss: 0.05640947073698044
2023-01-22 14:32:18.783088: step: 876/530, loss: 0.006427661050111055
2023-01-22 14:32:19.840586: step: 880/530, loss: 0.018995806574821472
2023-01-22 14:32:20.884017: step: 884/530, loss: 0.03825213760137558
2023-01-22 14:32:21.937812: step: 888/530, loss: 0.00936310738325119
2023-01-22 14:32:22.982639: step: 892/530, loss: 0.010521425865590572
2023-01-22 14:32:24.041937: step: 896/530, loss: 0.01497871708124876
2023-01-22 14:32:25.077997: step: 900/530, loss: 0.006770298816263676
2023-01-22 14:32:26.120060: step: 904/530, loss: 0.013842870481312275
2023-01-22 14:32:27.169671: step: 908/530, loss: 0.016851462423801422
2023-01-22 14:32:28.224427: step: 912/530, loss: 0.04374687001109123
2023-01-22 14:32:29.270397: step: 916/530, loss: 0.06402844935655594
2023-01-22 14:32:30.348720: step: 920/530, loss: 0.007186340168118477
2023-01-22 14:32:31.406404: step: 924/530, loss: 0.006947611458599567
2023-01-22 14:32:32.462893: step: 928/530, loss: 0.010150546208024025
2023-01-22 14:32:33.536907: step: 932/530, loss: 0.03677567094564438
2023-01-22 14:32:34.599707: step: 936/530, loss: 0.046463266015052795
2023-01-22 14:32:35.656401: step: 940/530, loss: 0.03405112773180008
2023-01-22 14:32:36.715213: step: 944/530, loss: 0.035727210342884064
2023-01-22 14:32:37.776065: step: 948/530, loss: 0.01393832266330719
2023-01-22 14:32:38.833360: step: 952/530, loss: 0.00514913210645318
2023-01-22 14:32:39.890515: step: 956/530, loss: 0.0049138423055410385
2023-01-22 14:32:40.955149: step: 960/530, loss: 0.014473812654614449
2023-01-22 14:32:41.997305: step: 964/530, loss: 0.01810336485505104
2023-01-22 14:32:43.063403: step: 968/530, loss: 0.06051211804151535
2023-01-22 14:32:44.116514: step: 972/530, loss: 0.025683708488941193
2023-01-22 14:32:45.167216: step: 976/530, loss: 0.04642287641763687
2023-01-22 14:32:46.227934: step: 980/530, loss: 0.007159307133406401
2023-01-22 14:32:47.310915: step: 984/530, loss: 0.01314071100205183
2023-01-22 14:32:48.366283: step: 988/530, loss: 0.008624155074357986
2023-01-22 14:32:49.423308: step: 992/530, loss: 0.011762621812522411
2023-01-22 14:32:50.480651: step: 996/530, loss: 0.002586920280009508
2023-01-22 14:32:51.541453: step: 1000/530, loss: 0.004858341533690691
2023-01-22 14:32:52.594531: step: 1004/530, loss: 0.011473674327135086
2023-01-22 14:32:53.650566: step: 1008/530, loss: 0.012196864932775497
2023-01-22 14:32:54.708337: step: 1012/530, loss: 0.03536411374807358
2023-01-22 14:32:55.767470: step: 1016/530, loss: 0.04359541833400726
2023-01-22 14:32:56.827336: step: 1020/530, loss: 0.010759529657661915
2023-01-22 14:32:57.876346: step: 1024/530, loss: 0.0
2023-01-22 14:32:58.926668: step: 1028/530, loss: 0.007376645691692829
2023-01-22 14:32:59.967919: step: 1032/530, loss: 0.016261782497167587
2023-01-22 14:33:01.030178: step: 1036/530, loss: 0.007587794214487076
2023-01-22 14:33:02.108063: step: 1040/530, loss: 0.012331432662904263
2023-01-22 14:33:03.169922: step: 1044/530, loss: 0.0559673085808754
2023-01-22 14:33:04.257837: step: 1048/530, loss: 0.010683332569897175
2023-01-22 14:33:05.304644: step: 1052/530, loss: 0.01462164893746376
2023-01-22 14:33:06.365627: step: 1056/530, loss: 0.010988554917275906
2023-01-22 14:33:07.448013: step: 1060/530, loss: 0.007587789092212915
2023-01-22 14:33:08.493885: step: 1064/530, loss: 0.04696919396519661
2023-01-22 14:33:09.544112: step: 1068/530, loss: 0.01268306840211153
2023-01-22 14:33:10.601879: step: 1072/530, loss: 0.01825232431292534
2023-01-22 14:33:11.662059: step: 1076/530, loss: 0.0070555065758526325
2023-01-22 14:33:12.720664: step: 1080/530, loss: 0.006043289788067341
2023-01-22 14:33:13.778606: step: 1084/530, loss: 0.012065306305885315
2023-01-22 14:33:14.838739: step: 1088/530, loss: 0.007906339131295681
2023-01-22 14:33:15.890514: step: 1092/530, loss: 0.010578767396509647
2023-01-22 14:33:16.930109: step: 1096/530, loss: 0.014258671551942825
2023-01-22 14:33:17.988914: step: 1100/530, loss: 0.005523975472897291
2023-01-22 14:33:19.051417: step: 1104/530, loss: 0.006160045508295298
2023-01-22 14:33:20.115690: step: 1108/530, loss: 0.019277600571513176
2023-01-22 14:33:21.189341: step: 1112/530, loss: 0.022061079740524292
2023-01-22 14:33:22.237636: step: 1116/530, loss: 0.004279881715774536
2023-01-22 14:33:23.300177: step: 1120/530, loss: 0.027891699224710464
2023-01-22 14:33:24.357222: step: 1124/530, loss: 0.05023053660988808
2023-01-22 14:33:25.425062: step: 1128/530, loss: 0.0016466941451653838
2023-01-22 14:33:26.494838: step: 1132/530, loss: 0.0240631066262722
2023-01-22 14:33:27.545587: step: 1136/530, loss: 0.005580810364335775
2023-01-22 14:33:28.590516: step: 1140/530, loss: 0.0032665585167706013
2023-01-22 14:33:29.652658: step: 1144/530, loss: 0.004518146626651287
2023-01-22 14:33:30.716433: step: 1148/530, loss: 0.008799486793577671
2023-01-22 14:33:31.776872: step: 1152/530, loss: 0.006526159588247538
2023-01-22 14:33:32.832453: step: 1156/530, loss: 0.0445825457572937
2023-01-22 14:33:33.899735: step: 1160/530, loss: 0.04344402253627777
2023-01-22 14:33:34.957048: step: 1164/530, loss: 0.01872437447309494
2023-01-22 14:33:36.028338: step: 1168/530, loss: 0.0625322237610817
2023-01-22 14:33:37.079365: step: 1172/530, loss: 0.007066223304718733
2023-01-22 14:33:38.128974: step: 1176/530, loss: 0.03241466358304024
2023-01-22 14:33:39.201204: step: 1180/530, loss: 0.0055928598158061504
2023-01-22 14:33:40.251914: step: 1184/530, loss: 0.05248646065592766
2023-01-22 14:33:41.307441: step: 1188/530, loss: 0.02023748867213726
2023-01-22 14:33:42.363203: step: 1192/530, loss: 0.0369214229285717
2023-01-22 14:33:43.413000: step: 1196/530, loss: 0.022305499762296677
2023-01-22 14:33:44.481566: step: 1200/530, loss: 0.015122110955417156
2023-01-22 14:33:45.526189: step: 1204/530, loss: 0.01642940565943718
2023-01-22 14:33:46.574995: step: 1208/530, loss: 0.006676771212369204
2023-01-22 14:33:47.642118: step: 1212/530, loss: 0.004971812013536692
2023-01-22 14:33:48.678529: step: 1216/530, loss: 0.01663142256438732
2023-01-22 14:33:49.748307: step: 1220/530, loss: 0.015099186450242996
2023-01-22 14:33:50.801870: step: 1224/530, loss: 0.00491509260609746
2023-01-22 14:33:51.866121: step: 1228/530, loss: 0.050172943621873856
2023-01-22 14:33:52.909957: step: 1232/530, loss: 0.07353024184703827
2023-01-22 14:33:53.979899: step: 1236/530, loss: 0.05253772437572479
2023-01-22 14:33:55.046782: step: 1240/530, loss: 0.07221702486276627
2023-01-22 14:33:56.096027: step: 1244/530, loss: 0.08229915052652359
2023-01-22 14:33:57.145352: step: 1248/530, loss: 0.008013667538762093
2023-01-22 14:33:58.202574: step: 1252/530, loss: 0.008296540938317776
2023-01-22 14:33:59.264684: step: 1256/530, loss: 0.013247084803879261
2023-01-22 14:34:00.321192: step: 1260/530, loss: 0.039408937096595764
2023-01-22 14:34:01.386052: step: 1264/530, loss: 0.022857001051306725
2023-01-22 14:34:02.455681: step: 1268/530, loss: 0.09486035257577896
2023-01-22 14:34:03.500156: step: 1272/530, loss: 0.006343443412333727
2023-01-22 14:34:04.548970: step: 1276/530, loss: 0.006245467346161604
2023-01-22 14:34:05.611372: step: 1280/530, loss: 0.011517812497913837
2023-01-22 14:34:06.690058: step: 1284/530, loss: 0.027390016242861748
2023-01-22 14:34:07.751919: step: 1288/530, loss: 0.05465123429894447
2023-01-22 14:34:08.834397: step: 1292/530, loss: 0.029385672882199287
2023-01-22 14:34:09.910972: step: 1296/530, loss: 0.011082857847213745
2023-01-22 14:34:10.970877: step: 1300/530, loss: 0.010165059007704258
2023-01-22 14:34:12.020670: step: 1304/530, loss: 0.009124458767473698
2023-01-22 14:34:13.085160: step: 1308/530, loss: 0.0709029883146286
2023-01-22 14:34:14.137555: step: 1312/530, loss: 0.017112143337726593
2023-01-22 14:34:15.203270: step: 1316/530, loss: 0.018398692831397057
2023-01-22 14:34:16.269011: step: 1320/530, loss: 0.009186377748847008
2023-01-22 14:34:17.350630: step: 1324/530, loss: 0.0165835153311491
2023-01-22 14:34:18.417356: step: 1328/530, loss: 0.05665843188762665
2023-01-22 14:34:19.464738: step: 1332/530, loss: 0.010099775157868862
2023-01-22 14:34:20.530362: step: 1336/530, loss: 0.009929196909070015
2023-01-22 14:34:21.590689: step: 1340/530, loss: 0.011640582233667374
2023-01-22 14:34:22.651849: step: 1344/530, loss: 0.009187677875161171
2023-01-22 14:34:23.720135: step: 1348/530, loss: 0.05760704725980759
2023-01-22 14:34:24.782728: step: 1352/530, loss: 0.0032530431635677814
2023-01-22 14:34:25.855316: step: 1356/530, loss: 0.010160473175346851
2023-01-22 14:34:26.932794: step: 1360/530, loss: 0.010763449594378471
2023-01-22 14:34:27.998690: step: 1364/530, loss: 0.024489203467965126
2023-01-22 14:34:29.069581: step: 1368/530, loss: 0.044015008956193924
2023-01-22 14:34:30.129228: step: 1372/530, loss: 0.011772742494940758
2023-01-22 14:34:31.199641: step: 1376/530, loss: 0.010082654654979706
2023-01-22 14:34:32.262766: step: 1380/530, loss: 0.011007610708475113
2023-01-22 14:34:33.324355: step: 1384/530, loss: 0.04948361590504646
2023-01-22 14:34:34.389365: step: 1388/530, loss: 0.03764904662966728
2023-01-22 14:34:35.450824: step: 1392/530, loss: 0.015111290849745274
2023-01-22 14:34:36.515658: step: 1396/530, loss: 0.04680466651916504
2023-01-22 14:34:37.587903: step: 1400/530, loss: 0.06037868559360504
2023-01-22 14:34:38.672774: step: 1404/530, loss: 0.0025439017917960882
2023-01-22 14:34:39.746624: step: 1408/530, loss: 0.013582988642156124
2023-01-22 14:34:40.804862: step: 1412/530, loss: 0.011048753745853901
2023-01-22 14:34:41.875616: step: 1416/530, loss: 0.032101117074489594
2023-01-22 14:34:42.923257: step: 1420/530, loss: 0.01761852391064167
2023-01-22 14:34:43.988738: step: 1424/530, loss: 0.05801999941468239
2023-01-22 14:34:45.051950: step: 1428/530, loss: 0.0034850211814045906
2023-01-22 14:34:46.116639: step: 1432/530, loss: 0.006018470507115126
2023-01-22 14:34:47.160533: step: 1436/530, loss: 0.016149142757058144
2023-01-22 14:34:48.231981: step: 1440/530, loss: 0.022863702848553658
2023-01-22 14:34:49.292034: step: 1444/530, loss: 0.012102514505386353
2023-01-22 14:34:50.355933: step: 1448/530, loss: 0.09349612146615982
2023-01-22 14:34:51.424533: step: 1452/530, loss: 0.009717483073472977
2023-01-22 14:34:52.478191: step: 1456/530, loss: 0.007673966232687235
2023-01-22 14:34:53.519125: step: 1460/530, loss: 0.010607304982841015
2023-01-22 14:34:54.582769: step: 1464/530, loss: 0.028118545189499855
2023-01-22 14:34:55.647549: step: 1468/530, loss: 0.05583770573139191
2023-01-22 14:34:56.709599: step: 1472/530, loss: 0.03914321959018707
2023-01-22 14:34:57.777174: step: 1476/530, loss: 0.04705042764544487
2023-01-22 14:34:58.858112: step: 1480/530, loss: 0.011493569239974022
2023-01-22 14:34:59.904585: step: 1484/530, loss: 0.01587658002972603
2023-01-22 14:35:00.971596: step: 1488/530, loss: 0.033804040402173996
2023-01-22 14:35:02.040777: step: 1492/530, loss: 0.038401950150728226
2023-01-22 14:35:03.123657: step: 1496/530, loss: 0.015206553973257542
2023-01-22 14:35:04.193967: step: 1500/530, loss: 0.015448298305273056
2023-01-22 14:35:05.264120: step: 1504/530, loss: 0.0
2023-01-22 14:35:06.311456: step: 1508/530, loss: 0.014555639587342739
2023-01-22 14:35:07.358864: step: 1512/530, loss: 0.01882525533437729
2023-01-22 14:35:08.405703: step: 1516/530, loss: 0.007516829762607813
2023-01-22 14:35:09.467800: step: 1520/530, loss: 0.011755396611988544
2023-01-22 14:35:10.542871: step: 1524/530, loss: 0.04681158438324928
2023-01-22 14:35:11.605498: step: 1528/530, loss: 0.029220009222626686
2023-01-22 14:35:12.664067: step: 1532/530, loss: 0.012017552740871906
2023-01-22 14:35:13.731288: step: 1536/530, loss: 0.049115028232336044
2023-01-22 14:35:14.803671: step: 1540/530, loss: 0.04238603264093399
2023-01-22 14:35:15.864034: step: 1544/530, loss: 0.022604364901781082
2023-01-22 14:35:16.921910: step: 1548/530, loss: 0.06295600533485413
2023-01-22 14:35:17.966363: step: 1552/530, loss: 0.029475726187229156
2023-01-22 14:35:19.027488: step: 1556/530, loss: 0.006206018850207329
2023-01-22 14:35:20.083704: step: 1560/530, loss: 0.0006113530835136771
2023-01-22 14:35:21.145735: step: 1564/530, loss: 0.026363978162407875
2023-01-22 14:35:22.209745: step: 1568/530, loss: 0.005621196702122688
2023-01-22 14:35:23.287303: step: 1572/530, loss: 0.010632461868226528
2023-01-22 14:35:24.356271: step: 1576/530, loss: 0.008851172402501106
2023-01-22 14:35:25.417021: step: 1580/530, loss: 0.007686966098845005
2023-01-22 14:35:26.497580: step: 1584/530, loss: 0.010417128913104534
2023-01-22 14:35:27.559722: step: 1588/530, loss: 0.009220454841852188
2023-01-22 14:35:28.613777: step: 1592/530, loss: 0.04846467077732086
2023-01-22 14:35:29.680748: step: 1596/530, loss: 0.008378441445529461
2023-01-22 14:35:30.739941: step: 1600/530, loss: 0.010829788632690907
2023-01-22 14:35:31.809472: step: 1604/530, loss: 0.05643141269683838
2023-01-22 14:35:32.886929: step: 1608/530, loss: 0.005940014496445656
2023-01-22 14:35:33.960257: step: 1612/530, loss: 0.009098365902900696
2023-01-22 14:35:34.998912: step: 1616/530, loss: 0.005947449244558811
2023-01-22 14:35:36.037373: step: 1620/530, loss: 0.007603847421705723
2023-01-22 14:35:37.093779: step: 1624/530, loss: 0.015103227458894253
2023-01-22 14:35:38.166775: step: 1628/530, loss: 0.03847254812717438
2023-01-22 14:35:39.229923: step: 1632/530, loss: 0.014274196699261665
2023-01-22 14:35:40.277899: step: 1636/530, loss: 0.0012899849098175764
2023-01-22 14:35:41.334638: step: 1640/530, loss: 0.013747187331318855
2023-01-22 14:35:42.386271: step: 1644/530, loss: 0.008819185197353363
2023-01-22 14:35:43.437392: step: 1648/530, loss: 0.013215270824730396
2023-01-22 14:35:44.494238: step: 1652/530, loss: 0.004616389982402325
2023-01-22 14:35:45.546094: step: 1656/530, loss: 0.007974857464432716
2023-01-22 14:35:46.596748: step: 1660/530, loss: 0.0667194351553917
2023-01-22 14:35:47.651098: step: 1664/530, loss: 0.015447521582245827
2023-01-22 14:35:48.709363: step: 1668/530, loss: 0.01486852765083313
2023-01-22 14:35:49.767655: step: 1672/530, loss: 0.015161690302193165
2023-01-22 14:35:50.806541: step: 1676/530, loss: 0.04072938114404678
2023-01-22 14:35:51.874713: step: 1680/530, loss: 0.031799569725990295
2023-01-22 14:35:52.924134: step: 1684/530, loss: 0.017142189666628838
2023-01-22 14:35:54.000056: step: 1688/530, loss: 0.009336385875940323
2023-01-22 14:35:55.062993: step: 1692/530, loss: 0.00813746452331543
2023-01-22 14:35:56.114424: step: 1696/530, loss: 0.02112860605120659
2023-01-22 14:35:57.173381: step: 1700/530, loss: 0.007506415713578463
2023-01-22 14:35:58.230767: step: 1704/530, loss: 0.013389104045927525
2023-01-22 14:35:59.268976: step: 1708/530, loss: 0.011649283580482006
2023-01-22 14:36:00.350132: step: 1712/530, loss: 0.015604037791490555
2023-01-22 14:36:01.389511: step: 1716/530, loss: 0.015770137310028076
2023-01-22 14:36:02.447674: step: 1720/530, loss: 0.003947843797504902
2023-01-22 14:36:03.492483: step: 1724/530, loss: 0.0032538867089897394
2023-01-22 14:36:04.551297: step: 1728/530, loss: 0.006099522579461336
2023-01-22 14:36:05.613357: step: 1732/530, loss: 0.041710905730724335
2023-01-22 14:36:06.663281: step: 1736/530, loss: 0.008037427440285683
2023-01-22 14:36:07.715019: step: 1740/530, loss: 0.00854603759944439
2023-01-22 14:36:08.781197: step: 1744/530, loss: 0.010882861912250519
2023-01-22 14:36:09.833357: step: 1748/530, loss: 0.012188882566988468
2023-01-22 14:36:10.915702: step: 1752/530, loss: 0.0063628642819821835
2023-01-22 14:36:11.973602: step: 1756/530, loss: 0.009983053430914879
2023-01-22 14:36:13.033838: step: 1760/530, loss: 0.007224540691822767
2023-01-22 14:36:14.082032: step: 1764/530, loss: 0.013252705335617065
2023-01-22 14:36:15.148518: step: 1768/530, loss: 0.006915170233696699
2023-01-22 14:36:16.191871: step: 1772/530, loss: 0.004516227636486292
2023-01-22 14:36:17.255045: step: 1776/530, loss: 0.00857698917388916
2023-01-22 14:36:18.314587: step: 1780/530, loss: 0.007978210225701332
2023-01-22 14:36:19.369204: step: 1784/530, loss: 0.028052492067217827
2023-01-22 14:36:20.419149: step: 1788/530, loss: 0.015040180645883083
2023-01-22 14:36:21.470646: step: 1792/530, loss: 0.004561109934002161
2023-01-22 14:36:22.530483: step: 1796/530, loss: 0.0024614883586764336
2023-01-22 14:36:23.575359: step: 1800/530, loss: 0.012629399076104164
2023-01-22 14:36:24.637496: step: 1804/530, loss: 0.026167742908000946
2023-01-22 14:36:25.697296: step: 1808/530, loss: 0.013068159110844135
2023-01-22 14:36:26.757700: step: 1812/530, loss: 0.02562149241566658
2023-01-22 14:36:27.824450: step: 1816/530, loss: 0.03479331359267235
2023-01-22 14:36:28.865716: step: 1820/530, loss: 0.009271216578781605
2023-01-22 14:36:29.922672: step: 1824/530, loss: 0.02221786603331566
2023-01-22 14:36:31.006770: step: 1828/530, loss: 0.04992489144206047
2023-01-22 14:36:32.096272: step: 1832/530, loss: 0.0033437497913837433
2023-01-22 14:36:33.140356: step: 1836/530, loss: 0.006941276602447033
2023-01-22 14:36:34.194547: step: 1840/530, loss: 0.008557932451367378
2023-01-22 14:36:35.252442: step: 1844/530, loss: 0.00855118315666914
2023-01-22 14:36:36.320980: step: 1848/530, loss: 0.011229374445974827
2023-01-22 14:36:37.382039: step: 1852/530, loss: 0.010633961297571659
2023-01-22 14:36:38.428240: step: 1856/530, loss: 0.004392093513160944
2023-01-22 14:36:39.495834: step: 1860/530, loss: 0.029662800952792168
2023-01-22 14:36:40.561274: step: 1864/530, loss: 0.04898121580481529
2023-01-22 14:36:41.614353: step: 1868/530, loss: 0.029796553775668144
2023-01-22 14:36:42.658753: step: 1872/530, loss: 0.005181239452213049
2023-01-22 14:36:43.701937: step: 1876/530, loss: 0.012479596771299839
2023-01-22 14:36:44.753753: step: 1880/530, loss: 0.02138441987335682
2023-01-22 14:36:45.815187: step: 1884/530, loss: 0.006832160521298647
2023-01-22 14:36:46.875699: step: 1888/530, loss: 0.027198806405067444
2023-01-22 14:36:47.937023: step: 1892/530, loss: 0.026703640818595886
2023-01-22 14:36:48.986071: step: 1896/530, loss: 0.013256896287202835
2023-01-22 14:36:50.051436: step: 1900/530, loss: 0.015921026468276978
2023-01-22 14:36:51.121848: step: 1904/530, loss: 0.045949023216962814
2023-01-22 14:36:52.193547: step: 1908/530, loss: 0.020568108186125755
2023-01-22 14:36:53.243566: step: 1912/530, loss: 0.0072805872187018394
2023-01-22 14:36:54.292412: step: 1916/530, loss: 0.0062551070004701614
2023-01-22 14:36:55.357872: step: 1920/530, loss: 0.005042138509452343
2023-01-22 14:36:56.413168: step: 1924/530, loss: 0.07306154817342758
2023-01-22 14:36:57.460050: step: 1928/530, loss: 0.013020550832152367
2023-01-22 14:36:58.502579: step: 1932/530, loss: 0.04458221420645714
2023-01-22 14:36:59.553179: step: 1936/530, loss: 0.025175368413329124
2023-01-22 14:37:00.621479: step: 1940/530, loss: 0.03908427804708481
2023-01-22 14:37:01.674257: step: 1944/530, loss: 0.00235062837600708
2023-01-22 14:37:02.734470: step: 1948/530, loss: 0.010473492555320263
2023-01-22 14:37:03.802064: step: 1952/530, loss: 0.015861013904213905
2023-01-22 14:37:04.851488: step: 1956/530, loss: 0.011858519166707993
2023-01-22 14:37:05.934422: step: 1960/530, loss: 0.004690627567470074
2023-01-22 14:37:07.015533: step: 1964/530, loss: 0.06279172003269196
2023-01-22 14:37:08.084054: step: 1968/530, loss: 0.008779163472354412
2023-01-22 14:37:09.134512: step: 1972/530, loss: 0.013341370970010757
2023-01-22 14:37:10.191802: step: 1976/530, loss: 0.013894190080463886
2023-01-22 14:37:11.249718: step: 1980/530, loss: 0.011428681202232838
2023-01-22 14:37:12.313961: step: 1984/530, loss: 0.005652864463627338
2023-01-22 14:37:13.365190: step: 1988/530, loss: 0.003783381776884198
2023-01-22 14:37:14.423826: step: 1992/530, loss: 0.008703182451426983
2023-01-22 14:37:15.470850: step: 1996/530, loss: 0.03581368550658226
2023-01-22 14:37:16.523878: step: 2000/530, loss: 0.039116986095905304
2023-01-22 14:37:17.580774: step: 2004/530, loss: 0.025204267352819443
2023-01-22 14:37:18.653784: step: 2008/530, loss: 0.008481459692120552
2023-01-22 14:37:19.708357: step: 2012/530, loss: 0.010920289903879166
2023-01-22 14:37:20.771867: step: 2016/530, loss: 0.03312116861343384
2023-01-22 14:37:21.815718: step: 2020/530, loss: 0.06590596586465836
2023-01-22 14:37:22.874536: step: 2024/530, loss: 0.006403861101716757
2023-01-22 14:37:23.932252: step: 2028/530, loss: 0.11277373880147934
2023-01-22 14:37:24.997378: step: 2032/530, loss: 0.012116530910134315
2023-01-22 14:37:26.035671: step: 2036/530, loss: 0.009762010537087917
2023-01-22 14:37:27.087296: step: 2040/530, loss: 0.004549986682832241
2023-01-22 14:37:28.147288: step: 2044/530, loss: 0.00924845039844513
2023-01-22 14:37:29.203271: step: 2048/530, loss: 0.006644858978688717
2023-01-22 14:37:30.275610: step: 2052/530, loss: 0.01775205321609974
2023-01-22 14:37:31.327014: step: 2056/530, loss: 0.014122726395726204
2023-01-22 14:37:32.399961: step: 2060/530, loss: 0.03510434925556183
2023-01-22 14:37:33.474135: step: 2064/530, loss: 0.004604725632816553
2023-01-22 14:37:34.516544: step: 2068/530, loss: 0.007574012037366629
2023-01-22 14:37:35.582535: step: 2072/530, loss: 0.04657677933573723
2023-01-22 14:37:36.647059: step: 2076/530, loss: 0.01097668893635273
2023-01-22 14:37:37.724843: step: 2080/530, loss: 0.032615937292575836
2023-01-22 14:37:38.773116: step: 2084/530, loss: 0.013918210752308369
2023-01-22 14:37:39.836124: step: 2088/530, loss: 0.008181863464415073
2023-01-22 14:37:40.916840: step: 2092/530, loss: 0.008173602633178234
2023-01-22 14:37:41.986473: step: 2096/530, loss: 0.006773681379854679
2023-01-22 14:37:43.070065: step: 2100/530, loss: 0.011949355714023113
2023-01-22 14:37:44.113612: step: 2104/530, loss: 0.014399792067706585
2023-01-22 14:37:45.170085: step: 2108/530, loss: 0.004463918041437864
2023-01-22 14:37:46.215200: step: 2112/530, loss: 0.009530861862003803
2023-01-22 14:37:47.284082: step: 2116/530, loss: 0.010738905519247055
2023-01-22 14:37:48.331543: step: 2120/530, loss: 0.010884009301662445
==================================================
Loss: 0.023
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3539948191791955, 'r': 0.2874948436597641, 'f1': 0.31729797404962445}, 'combined': 0.2337985071944601, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3327229658912983, 'r': 0.23081040947075393, 'f1': 0.27255146671075275}, 'combined': 0.18075952196360803, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3136233135239319, 'r': 0.3368326289460066, 'f1': 0.32481389836147384}, 'combined': 0.23933655668740175, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3436080546157674, 'r': 0.3331956893243805, 'f1': 0.3383217768524479}, 'combined': 0.2243792095187219, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, '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': 0.3539948191791955, 'r': 0.2874948436597641, 'f1': 0.31729797404962445}, 'combined': 0.2337985071944601, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3327229658912983, 'r': 0.23081040947075393, 'f1': 0.27255146671075275}, 'combined': 0.18075952196360803, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3136233135239319, 'r': 0.3368326289460066, 'f1': 0.32481389836147384}, 'combined': 0.23933655668740175, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3436080546157674, 'r': 0.3331956893243805, 'f1': 0.3383217768524479}, 'combined': 0.2243792095187219, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, '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 14:40:39.652308: step: 4/530, loss: 0.012812042608857155
2023-01-22 14:40:40.701600: step: 8/530, loss: 0.004968743771314621
2023-01-22 14:40:41.748548: step: 12/530, loss: 0.010268469341099262
2023-01-22 14:40:42.823336: step: 16/530, loss: 0.012009065598249435
2023-01-22 14:40:43.876600: step: 20/530, loss: 0.006858623120933771
2023-01-22 14:40:44.944656: step: 24/530, loss: 0.017393426969647408
2023-01-22 14:40:45.983041: step: 28/530, loss: 0.04978247731924057
2023-01-22 14:40:47.036189: step: 32/530, loss: 0.006134674418717623
2023-01-22 14:40:48.091439: step: 36/530, loss: 0.012436299584805965
2023-01-22 14:40:49.146288: step: 40/530, loss: 0.015423350967466831
2023-01-22 14:40:50.198213: step: 44/530, loss: 0.015263188630342484
2023-01-22 14:40:51.249079: step: 48/530, loss: 0.042472150176763535
2023-01-22 14:40:52.290116: step: 52/530, loss: 0.00825263001024723
2023-01-22 14:40:53.357505: step: 56/530, loss: 0.006008844822645187
2023-01-22 14:40:54.413073: step: 60/530, loss: 0.03330196812748909
2023-01-22 14:40:55.485067: step: 64/530, loss: 0.024792250245809555
2023-01-22 14:40:56.546092: step: 68/530, loss: 0.023035090416669846
2023-01-22 14:40:57.627298: step: 72/530, loss: 0.0663604587316513
2023-01-22 14:40:58.707542: step: 76/530, loss: 0.004709298722445965
2023-01-22 14:40:59.757868: step: 80/530, loss: 0.07829374074935913
2023-01-22 14:41:00.823894: step: 84/530, loss: 0.0570572130382061
2023-01-22 14:41:01.881755: step: 88/530, loss: 0.015392381697893143
2023-01-22 14:41:02.964682: step: 92/530, loss: 0.0054253642447292805
2023-01-22 14:41:04.030165: step: 96/530, loss: 0.04380722716450691
2023-01-22 14:41:05.100748: step: 100/530, loss: 0.004719903226941824
2023-01-22 14:41:06.149247: step: 104/530, loss: 0.015461036935448647
2023-01-22 14:41:07.188383: step: 108/530, loss: 0.001330893486738205
2023-01-22 14:41:08.246212: step: 112/530, loss: 0.017028087750077248
2023-01-22 14:41:09.316594: step: 116/530, loss: 0.02221495658159256
2023-01-22 14:41:10.378488: step: 120/530, loss: 0.0018862797878682613
2023-01-22 14:41:11.431830: step: 124/530, loss: 0.049547310918569565
2023-01-22 14:41:12.483496: step: 128/530, loss: 0.011584346182644367
2023-01-22 14:41:13.544874: step: 132/530, loss: 0.006693420931696892
2023-01-22 14:41:14.600530: step: 136/530, loss: 0.014537774957716465
2023-01-22 14:41:15.655009: step: 140/530, loss: 0.003021225333213806
2023-01-22 14:41:16.702965: step: 144/530, loss: 0.01263433787971735
2023-01-22 14:41:17.751969: step: 148/530, loss: 0.005211420822888613
2023-01-22 14:41:18.817925: step: 152/530, loss: 0.011436636559665203
2023-01-22 14:41:19.871077: step: 156/530, loss: 0.01299082487821579
2023-01-22 14:41:20.939274: step: 160/530, loss: 0.009490937925875187
2023-01-22 14:41:22.006915: step: 164/530, loss: 0.009561149403452873
2023-01-22 14:41:23.074113: step: 168/530, loss: 0.024382170289754868
2023-01-22 14:41:24.126887: step: 172/530, loss: 0.013156569562852383
2023-01-22 14:41:25.193955: step: 176/530, loss: 0.05021173134446144
2023-01-22 14:41:26.257093: step: 180/530, loss: 0.02146018296480179
2023-01-22 14:41:27.340919: step: 184/530, loss: 0.014445621520280838
2023-01-22 14:41:28.384354: step: 188/530, loss: 0.008759626187384129
2023-01-22 14:41:29.436078: step: 192/530, loss: 0.01410683523863554
2023-01-22 14:41:30.500631: step: 196/530, loss: 0.010141275823116302
2023-01-22 14:41:31.555396: step: 200/530, loss: 0.047538917511701584
2023-01-22 14:41:32.651604: step: 204/530, loss: 0.018930921331048012
2023-01-22 14:41:33.704833: step: 208/530, loss: 0.01452831644564867
2023-01-22 14:41:34.761612: step: 212/530, loss: 0.001628898666240275
2023-01-22 14:41:35.822041: step: 216/530, loss: 0.01716967485845089
2023-01-22 14:41:36.895160: step: 220/530, loss: 0.008422736078500748
2023-01-22 14:41:37.952358: step: 224/530, loss: 0.03254485875368118
2023-01-22 14:41:39.010991: step: 228/530, loss: 0.005184277892112732
2023-01-22 14:41:40.090273: step: 232/530, loss: 0.012165513820946217
2023-01-22 14:41:41.153361: step: 236/530, loss: 0.0011299249017611146
2023-01-22 14:41:42.205108: step: 240/530, loss: 0.010626495815813541
2023-01-22 14:41:43.272214: step: 244/530, loss: 0.0330374501645565
2023-01-22 14:41:44.357673: step: 248/530, loss: 0.013683048076927662
2023-01-22 14:41:45.425203: step: 252/530, loss: 0.018541518598794937
2023-01-22 14:41:46.486891: step: 256/530, loss: 0.006146200932562351
2023-01-22 14:41:47.578617: step: 260/530, loss: 0.03574364259839058
2023-01-22 14:41:48.638902: step: 264/530, loss: 0.013680302537977695
2023-01-22 14:41:49.709903: step: 268/530, loss: 0.01754814386367798
2023-01-22 14:41:50.795853: step: 272/530, loss: 0.011144958436489105
2023-01-22 14:41:51.863474: step: 276/530, loss: 0.007970360107719898
2023-01-22 14:41:52.932110: step: 280/530, loss: 0.005459174048155546
2023-01-22 14:41:54.018550: step: 284/530, loss: 0.008446728810667992
2023-01-22 14:41:55.075804: step: 288/530, loss: 0.0038400490302592516
2023-01-22 14:41:56.151682: step: 292/530, loss: 0.052778203040361404
2023-01-22 14:41:57.206582: step: 296/530, loss: 0.012762574478983879
2023-01-22 14:41:58.261660: step: 300/530, loss: 0.015266292728483677
2023-01-22 14:41:59.315055: step: 304/530, loss: 0.027815166860818863
2023-01-22 14:42:00.378318: step: 308/530, loss: 0.011306829750537872
2023-01-22 14:42:01.447989: step: 312/530, loss: 0.010101128369569778
2023-01-22 14:42:02.501132: step: 316/530, loss: 0.012637332081794739
2023-01-22 14:42:03.563398: step: 320/530, loss: 0.012996125034987926
2023-01-22 14:42:04.620728: step: 324/530, loss: 0.012186801992356777
2023-01-22 14:42:05.694989: step: 328/530, loss: 0.02957739681005478
2023-01-22 14:42:06.758097: step: 332/530, loss: 0.014164001680910587
2023-01-22 14:42:07.815614: step: 336/530, loss: 0.006234884262084961
2023-01-22 14:42:08.875243: step: 340/530, loss: 0.009840351529419422
2023-01-22 14:42:09.932363: step: 344/530, loss: 0.006597005296498537
2023-01-22 14:42:11.004065: step: 348/530, loss: 0.012403731234371662
2023-01-22 14:42:12.089279: step: 352/530, loss: 0.007966849952936172
2023-01-22 14:42:13.157189: step: 356/530, loss: 0.022204235196113586
2023-01-22 14:42:14.207837: step: 360/530, loss: 0.004735025577247143
2023-01-22 14:42:15.285914: step: 364/530, loss: 0.009826652705669403
2023-01-22 14:42:16.354494: step: 368/530, loss: 0.006812600884586573
2023-01-22 14:42:17.417893: step: 372/530, loss: 0.007569643668830395
2023-01-22 14:42:18.478046: step: 376/530, loss: 0.022164801135659218
2023-01-22 14:42:19.537073: step: 380/530, loss: 0.006721922196447849
2023-01-22 14:42:20.628164: step: 384/530, loss: 0.01070920005440712
2023-01-22 14:42:21.691227: step: 388/530, loss: 0.028800206258893013
2023-01-22 14:42:22.758511: step: 392/530, loss: 0.018672818318009377
2023-01-22 14:42:23.840452: step: 396/530, loss: 0.033573850989341736
2023-01-22 14:42:24.924513: step: 400/530, loss: 0.035121940076351166
2023-01-22 14:42:26.005997: step: 404/530, loss: 0.02438824251294136
2023-01-22 14:42:27.074837: step: 408/530, loss: 0.007556359749287367
2023-01-22 14:42:28.134947: step: 412/530, loss: 0.05502595752477646
2023-01-22 14:42:29.208375: step: 416/530, loss: 0.017103854566812515
2023-01-22 14:42:30.268920: step: 420/530, loss: 0.006410283036530018
2023-01-22 14:42:31.338057: step: 424/530, loss: 0.010382283478975296
2023-01-22 14:42:32.400899: step: 428/530, loss: 0.0422479584813118
2023-01-22 14:42:33.469553: step: 432/530, loss: 0.0054764412343502045
2023-01-22 14:42:34.531881: step: 436/530, loss: 0.004924156703054905
2023-01-22 14:42:35.599716: step: 440/530, loss: 0.006357597652822733
2023-01-22 14:42:36.653310: step: 444/530, loss: 0.01100998930633068
2023-01-22 14:42:37.725183: step: 448/530, loss: 0.00651451013982296
2023-01-22 14:42:38.805512: step: 452/530, loss: 0.006748924497514963
2023-01-22 14:42:39.892604: step: 456/530, loss: 0.028487294912338257
2023-01-22 14:42:40.954852: step: 460/530, loss: 0.02687118947505951
2023-01-22 14:42:42.048762: step: 464/530, loss: 0.010269289836287498
2023-01-22 14:42:43.116963: step: 468/530, loss: 0.015467138029634953
2023-01-22 14:42:44.180277: step: 472/530, loss: 0.006644831970334053
2023-01-22 14:42:45.244871: step: 476/530, loss: 0.015359615907073021
2023-01-22 14:42:46.317762: step: 480/530, loss: 0.01289144903421402
2023-01-22 14:42:47.398767: step: 484/530, loss: 0.03765174746513367
2023-01-22 14:42:48.443632: step: 488/530, loss: 0.005087241996079683
2023-01-22 14:42:49.518204: step: 492/530, loss: 0.04189470037817955
2023-01-22 14:42:50.584241: step: 496/530, loss: 0.002288535237312317
2023-01-22 14:42:51.654074: step: 500/530, loss: 0.006644130684435368
2023-01-22 14:42:52.706607: step: 504/530, loss: 0.013283337466418743
2023-01-22 14:42:53.781499: step: 508/530, loss: 0.010525096207857132
2023-01-22 14:42:54.857360: step: 512/530, loss: 0.009191962890326977
2023-01-22 14:42:55.926404: step: 516/530, loss: 0.02919941395521164
2023-01-22 14:42:57.009316: step: 520/530, loss: 0.013844375498592854
2023-01-22 14:42:58.058488: step: 524/530, loss: 0.011457065120339394
2023-01-22 14:42:59.115676: step: 528/530, loss: 0.009924969635903835
2023-01-22 14:43:00.172479: step: 532/530, loss: 0.004485252778977156
2023-01-22 14:43:01.242161: step: 536/530, loss: 0.01095918845385313
2023-01-22 14:43:02.327214: step: 540/530, loss: 0.00705690449103713
2023-01-22 14:43:03.391837: step: 544/530, loss: 0.005855096038430929
2023-01-22 14:43:04.472428: step: 548/530, loss: 0.00876110140234232
2023-01-22 14:43:05.536032: step: 552/530, loss: 0.0048134238459169865
2023-01-22 14:43:06.593751: step: 556/530, loss: 0.021427888423204422
2023-01-22 14:43:07.649728: step: 560/530, loss: 0.034591518342494965
2023-01-22 14:43:08.725367: step: 564/530, loss: 0.016187012195587158
2023-01-22 14:43:09.791119: step: 568/530, loss: 0.0035373871214687824
2023-01-22 14:43:10.870036: step: 572/530, loss: 0.0032281121239066124
2023-01-22 14:43:11.927342: step: 576/530, loss: 0.009938967414200306
2023-01-22 14:43:12.995448: step: 580/530, loss: 0.00673109432682395
2023-01-22 14:43:14.065378: step: 584/530, loss: 0.005051737651228905
2023-01-22 14:43:15.127125: step: 588/530, loss: 0.003959218971431255
2023-01-22 14:43:16.205130: step: 592/530, loss: 0.0253533236682415
2023-01-22 14:43:17.278863: step: 596/530, loss: 0.018933676183223724
2023-01-22 14:43:18.348109: step: 600/530, loss: 0.018184704706072807
2023-01-22 14:43:19.404726: step: 604/530, loss: 0.040191859006881714
2023-01-22 14:43:20.464992: step: 608/530, loss: 0.005946453660726547
2023-01-22 14:43:21.525325: step: 612/530, loss: 0.016042513772845268
2023-01-22 14:43:22.596935: step: 616/530, loss: 0.009394089691340923
2023-01-22 14:43:23.648447: step: 620/530, loss: 0.00918502826243639
2023-01-22 14:43:24.689560: step: 624/530, loss: 0.008218417875468731
2023-01-22 14:43:25.786143: step: 628/530, loss: 0.0075278691947460175
2023-01-22 14:43:26.829226: step: 632/530, loss: 0.04501500353217125
2023-01-22 14:43:27.897295: step: 636/530, loss: 0.04866698384284973
2023-01-22 14:43:28.961175: step: 640/530, loss: 0.004906733054667711
2023-01-22 14:43:30.025744: step: 644/530, loss: 0.007191901095211506
2023-01-22 14:43:31.089189: step: 648/530, loss: 0.004166802857071161
2023-01-22 14:43:32.158482: step: 652/530, loss: 0.008952178992331028
2023-01-22 14:43:33.210791: step: 656/530, loss: 0.0032867658883333206
2023-01-22 14:43:34.267056: step: 660/530, loss: 0.008846216835081577
2023-01-22 14:43:35.331386: step: 664/530, loss: 0.034426044672727585
2023-01-22 14:43:36.380273: step: 668/530, loss: 0.016851428896188736
2023-01-22 14:43:37.443543: step: 672/530, loss: 0.001728835399262607
2023-01-22 14:43:38.511854: step: 676/530, loss: 0.003514292184263468
2023-01-22 14:43:39.578234: step: 680/530, loss: 0.0014241851167753339
2023-01-22 14:43:40.633313: step: 684/530, loss: 0.011632991954684258
2023-01-22 14:43:41.702570: step: 688/530, loss: 0.0031677905935794115
2023-01-22 14:43:42.767718: step: 692/530, loss: 0.006295075174421072
2023-01-22 14:43:43.826631: step: 696/530, loss: 0.012672558426856995
2023-01-22 14:43:44.883865: step: 700/530, loss: 0.016729509457945824
2023-01-22 14:43:45.950441: step: 704/530, loss: 0.005609654821455479
2023-01-22 14:43:47.016117: step: 708/530, loss: 0.025184353813529015
2023-01-22 14:43:48.064502: step: 712/530, loss: 0.011834022589027882
2023-01-22 14:43:49.121014: step: 716/530, loss: 0.012000779621303082
2023-01-22 14:43:50.171018: step: 720/530, loss: 0.024266935884952545
2023-01-22 14:43:51.232632: step: 724/530, loss: 0.008076450787484646
2023-01-22 14:43:52.276434: step: 728/530, loss: 0.05895301699638367
2023-01-22 14:43:53.334843: step: 732/530, loss: 0.004399893339723349
2023-01-22 14:43:54.397327: step: 736/530, loss: 0.011770348995923996
2023-01-22 14:43:55.445167: step: 740/530, loss: 0.013988112099468708
2023-01-22 14:43:56.491932: step: 744/530, loss: 0.0073435502126812935
2023-01-22 14:43:57.555472: step: 748/530, loss: 0.015257966704666615
2023-01-22 14:43:58.609530: step: 752/530, loss: 0.0061120279133319855
2023-01-22 14:43:59.688497: step: 756/530, loss: 0.038767073303461075
2023-01-22 14:44:00.762480: step: 760/530, loss: 0.009704644791781902
2023-01-22 14:44:01.809909: step: 764/530, loss: 0.026901721954345703
2023-01-22 14:44:02.883773: step: 768/530, loss: 0.004168699029833078
2023-01-22 14:44:03.941550: step: 772/530, loss: 0.041097331792116165
2023-01-22 14:44:04.990702: step: 776/530, loss: 0.03344521299004555
2023-01-22 14:44:06.033697: step: 780/530, loss: 0.03974912688136101
2023-01-22 14:44:07.089664: step: 784/530, loss: 0.005475970916450024
2023-01-22 14:44:08.146075: step: 788/530, loss: 0.011025716550648212
2023-01-22 14:44:09.191854: step: 792/530, loss: 0.0031101240310817957
2023-01-22 14:44:10.237975: step: 796/530, loss: 0.0029792720451951027
2023-01-22 14:44:11.306586: step: 800/530, loss: 0.0446191169321537
2023-01-22 14:44:12.359919: step: 804/530, loss: 0.00830955058336258
2023-01-22 14:44:13.420511: step: 808/530, loss: 0.01628958247601986
2023-01-22 14:44:14.478664: step: 812/530, loss: 0.004423732869327068
2023-01-22 14:44:15.539931: step: 816/530, loss: 0.011006618849933147
2023-01-22 14:44:16.594992: step: 820/530, loss: 0.008579405955970287
2023-01-22 14:44:17.655631: step: 824/530, loss: 0.018149664625525475
2023-01-22 14:44:18.707566: step: 828/530, loss: 0.00688356626778841
2023-01-22 14:44:19.780418: step: 832/530, loss: 0.01976776123046875
2023-01-22 14:44:20.834812: step: 836/530, loss: 0.023456206545233727
2023-01-22 14:44:21.907386: step: 840/530, loss: 0.029343977570533752
2023-01-22 14:44:22.964489: step: 844/530, loss: 0.018927250057458878
2023-01-22 14:44:24.039142: step: 848/530, loss: 0.07061655819416046
2023-01-22 14:44:25.104109: step: 852/530, loss: 0.015483235940337181
2023-01-22 14:44:26.159529: step: 856/530, loss: 0.01061968319118023
2023-01-22 14:44:27.222617: step: 860/530, loss: 0.031189650297164917
2023-01-22 14:44:28.282927: step: 864/530, loss: 0.006935350596904755
2023-01-22 14:44:29.331885: step: 868/530, loss: 0.009298883378505707
2023-01-22 14:44:30.382161: step: 872/530, loss: 0.007129035424441099
2023-01-22 14:44:31.451790: step: 876/530, loss: 0.006253466941416264
2023-01-22 14:44:32.507918: step: 880/530, loss: 0.006499452516436577
2023-01-22 14:44:33.563945: step: 884/530, loss: 0.033299557864665985
2023-01-22 14:44:34.623364: step: 888/530, loss: 0.008984018117189407
2023-01-22 14:44:35.682523: step: 892/530, loss: 0.005039960145950317
2023-01-22 14:44:36.733785: step: 896/530, loss: 0.012044877745211124
2023-01-22 14:44:37.805725: step: 900/530, loss: 0.005887978710234165
2023-01-22 14:44:38.852432: step: 904/530, loss: 0.012302116490900517
2023-01-22 14:44:39.906124: step: 908/530, loss: 0.015675431117415428
2023-01-22 14:44:40.960821: step: 912/530, loss: 0.04208158329129219
2023-01-22 14:44:42.013264: step: 916/530, loss: 0.03659065440297127
2023-01-22 14:44:43.065216: step: 920/530, loss: 0.03763337805867195
2023-01-22 14:44:44.125415: step: 924/530, loss: 0.042064789682626724
2023-01-22 14:44:45.189798: step: 928/530, loss: 0.01969834417104721
2023-01-22 14:44:46.235014: step: 932/530, loss: 0.005926787853240967
2023-01-22 14:44:47.286743: step: 936/530, loss: 0.05853027477860451
2023-01-22 14:44:48.344408: step: 940/530, loss: 0.02152705378830433
2023-01-22 14:44:49.403204: step: 944/530, loss: 0.0007766132475808263
2023-01-22 14:44:50.464412: step: 948/530, loss: 0.010369432158768177
2023-01-22 14:44:51.515858: step: 952/530, loss: 0.005706869065761566
2023-01-22 14:44:52.572877: step: 956/530, loss: 0.02654355764389038
2023-01-22 14:44:53.653324: step: 960/530, loss: 0.02683834172785282
2023-01-22 14:44:54.734901: step: 964/530, loss: 0.011238583363592625
2023-01-22 14:44:55.791792: step: 968/530, loss: 0.012049898505210876
2023-01-22 14:44:56.868745: step: 972/530, loss: 0.06265122443437576
2023-01-22 14:44:57.936180: step: 976/530, loss: 0.013216791674494743
2023-01-22 14:44:58.997308: step: 980/530, loss: 0.014446182176470757
2023-01-22 14:45:00.061379: step: 984/530, loss: 0.008719599805772305
2023-01-22 14:45:01.113502: step: 988/530, loss: 0.012663358822464943
2023-01-22 14:45:02.158441: step: 992/530, loss: 0.004608609713613987
2023-01-22 14:45:03.215688: step: 996/530, loss: 0.023968590423464775
2023-01-22 14:45:04.270399: step: 1000/530, loss: 0.005979705136269331
2023-01-22 14:45:05.347427: step: 1004/530, loss: 0.03635064512491226
2023-01-22 14:45:06.405571: step: 1008/530, loss: 0.05162810534238815
2023-01-22 14:45:07.479886: step: 1012/530, loss: 0.003428681753575802
2023-01-22 14:45:08.541626: step: 1016/530, loss: 0.004650312941521406
2023-01-22 14:45:09.591997: step: 1020/530, loss: 0.0049728392623364925
2023-01-22 14:45:10.650947: step: 1024/530, loss: 0.026036269962787628
2023-01-22 14:45:11.708996: step: 1028/530, loss: 0.010332313366234303
2023-01-22 14:45:12.760878: step: 1032/530, loss: 0.010391296818852425
2023-01-22 14:45:13.817787: step: 1036/530, loss: 0.039661698043346405
2023-01-22 14:45:14.884659: step: 1040/530, loss: 0.009535130113363266
2023-01-22 14:45:15.934648: step: 1044/530, loss: 0.007928818464279175
2023-01-22 14:45:16.991361: step: 1048/530, loss: 0.0036535130348056555
2023-01-22 14:45:18.052996: step: 1052/530, loss: 0.004927432630211115
2023-01-22 14:45:19.104051: step: 1056/530, loss: 0.015324579551815987
2023-01-22 14:45:20.156373: step: 1060/530, loss: 0.050229042768478394
2023-01-22 14:45:21.226396: step: 1064/530, loss: 0.03010651469230652
2023-01-22 14:45:22.287790: step: 1068/530, loss: 0.01899755746126175
2023-01-22 14:45:23.346685: step: 1072/530, loss: 0.01033230870962143
2023-01-22 14:45:24.403377: step: 1076/530, loss: 0.0022809014189988375
2023-01-22 14:45:25.457434: step: 1080/530, loss: 0.005062357522547245
2023-01-22 14:45:26.534127: step: 1084/530, loss: 0.0034568000119179487
2023-01-22 14:45:27.589317: step: 1088/530, loss: 0.00892782025039196
2023-01-22 14:45:28.651696: step: 1092/530, loss: 0.010207334533333778
2023-01-22 14:45:29.707627: step: 1096/530, loss: 0.002616593847051263
2023-01-22 14:45:30.785519: step: 1100/530, loss: 0.005376041866838932
2023-01-22 14:45:31.853703: step: 1104/530, loss: 0.036779046058654785
2023-01-22 14:45:32.914668: step: 1108/530, loss: 0.05293755978345871
2023-01-22 14:45:33.975916: step: 1112/530, loss: 0.0558176189661026
2023-01-22 14:45:35.023691: step: 1116/530, loss: 0.02545098215341568
2023-01-22 14:45:36.090527: step: 1120/530, loss: 0.013991013169288635
2023-01-22 14:45:37.144217: step: 1124/530, loss: 0.006213500164449215
2023-01-22 14:45:38.213198: step: 1128/530, loss: 0.005669683218002319
2023-01-22 14:45:39.297041: step: 1132/530, loss: 0.024124665185809135
2023-01-22 14:45:40.352582: step: 1136/530, loss: 0.04454462230205536
2023-01-22 14:45:41.400471: step: 1140/530, loss: 0.04345531761646271
2023-01-22 14:45:42.448579: step: 1144/530, loss: 0.0588107593357563
2023-01-22 14:45:43.501440: step: 1148/530, loss: 0.0048675453290343285
2023-01-22 14:45:44.564064: step: 1152/530, loss: 0.0032255600672215223
2023-01-22 14:45:45.623408: step: 1156/530, loss: 0.010823904536664486
2023-01-22 14:45:46.679260: step: 1160/530, loss: 0.002180259209126234
2023-01-22 14:45:47.730466: step: 1164/530, loss: 0.002328141126781702
2023-01-22 14:45:48.805232: step: 1168/530, loss: 0.010505598038434982
2023-01-22 14:45:49.867252: step: 1172/530, loss: 0.03759091719985008
2023-01-22 14:45:50.943017: step: 1176/530, loss: 0.0307106152176857
2023-01-22 14:45:51.984206: step: 1180/530, loss: 0.01974612846970558
2023-01-22 14:45:53.080866: step: 1184/530, loss: 0.1052195206284523
2023-01-22 14:45:54.147254: step: 1188/530, loss: 0.08044582605361938
2023-01-22 14:45:55.224793: step: 1192/530, loss: 0.0010620774701237679
2023-01-22 14:45:56.281661: step: 1196/530, loss: 0.00456416979432106
2023-01-22 14:45:57.350030: step: 1200/530, loss: 0.006161686033010483
2023-01-22 14:45:58.410940: step: 1204/530, loss: 0.009766052477061749
2023-01-22 14:45:59.459600: step: 1208/530, loss: 0.03169477730989456
2023-01-22 14:46:00.520990: step: 1212/530, loss: 0.033149056136608124
2023-01-22 14:46:01.577033: step: 1216/530, loss: 0.02226412482559681
2023-01-22 14:46:02.638516: step: 1220/530, loss: 0.0304978396743536
2023-01-22 14:46:03.705294: step: 1224/530, loss: 0.03233238682150841
2023-01-22 14:46:04.764394: step: 1228/530, loss: 0.010222124867141247
2023-01-22 14:46:05.809166: step: 1232/530, loss: 0.00840659812092781
2023-01-22 14:46:06.855460: step: 1236/530, loss: 0.0036301854997873306
2023-01-22 14:46:07.916200: step: 1240/530, loss: 0.0092863654717803
2023-01-22 14:46:08.975132: step: 1244/530, loss: 0.016449958086013794
2023-01-22 14:46:10.019576: step: 1248/530, loss: 0.023955509066581726
2023-01-22 14:46:11.060004: step: 1252/530, loss: 0.013684744946658611
2023-01-22 14:46:12.110312: step: 1256/530, loss: 0.005129117984324694
2023-01-22 14:46:13.196477: step: 1260/530, loss: 0.007209953386336565
2023-01-22 14:46:14.253858: step: 1264/530, loss: 0.014008361846208572
2023-01-22 14:46:15.317701: step: 1268/530, loss: 0.007906931452453136
2023-01-22 14:46:16.364312: step: 1272/530, loss: 0.00965550635010004
2023-01-22 14:46:17.415615: step: 1276/530, loss: 0.037895385175943375
2023-01-22 14:46:18.473043: step: 1280/530, loss: 0.002878161845728755
2023-01-22 14:46:19.557350: step: 1284/530, loss: 0.0038605646695941687
2023-01-22 14:46:20.616160: step: 1288/530, loss: 0.003913390450179577
2023-01-22 14:46:21.693100: step: 1292/530, loss: 0.010950553230941296
2023-01-22 14:46:22.737709: step: 1296/530, loss: 0.005906758364289999
2023-01-22 14:46:23.792712: step: 1300/530, loss: 0.01570514589548111
2023-01-22 14:46:24.854248: step: 1304/530, loss: 0.006531259510666132
2023-01-22 14:46:25.904628: step: 1308/530, loss: 0.041600823402404785
2023-01-22 14:46:26.960195: step: 1312/530, loss: 0.011881793849170208
2023-01-22 14:46:28.004973: step: 1316/530, loss: 0.004571493715047836
2023-01-22 14:46:29.051207: step: 1320/530, loss: 0.08933065831661224
2023-01-22 14:46:30.102423: step: 1324/530, loss: 0.0023517468944191933
2023-01-22 14:46:31.164591: step: 1328/530, loss: 0.020870709791779518
2023-01-22 14:46:32.202599: step: 1332/530, loss: 0.023828677833080292
2023-01-22 14:46:33.253216: step: 1336/530, loss: 0.013462623581290245
2023-01-22 14:46:34.306228: step: 1340/530, loss: 0.010673563927412033
2023-01-22 14:46:35.368884: step: 1344/530, loss: 0.012909299694001675
2023-01-22 14:46:36.428980: step: 1348/530, loss: 0.019762424752116203
2023-01-22 14:46:37.482864: step: 1352/530, loss: 0.005482145585119724
2023-01-22 14:46:38.536708: step: 1356/530, loss: 0.0038648806512355804
2023-01-22 14:46:39.586263: step: 1360/530, loss: 0.004831406287848949
2023-01-22 14:46:40.647215: step: 1364/530, loss: 0.008477620780467987
2023-01-22 14:46:41.707012: step: 1368/530, loss: 0.03622875735163689
2023-01-22 14:46:42.790838: step: 1372/530, loss: 0.05545927584171295
2023-01-22 14:46:43.855748: step: 1376/530, loss: 0.03655295446515083
2023-01-22 14:46:44.919437: step: 1380/530, loss: 0.00972758885473013
2023-01-22 14:46:45.976557: step: 1384/530, loss: 0.03709084913134575
2023-01-22 14:46:47.059912: step: 1388/530, loss: 0.019992642104625702
2023-01-22 14:46:48.103116: step: 1392/530, loss: 0.009150903671979904
2023-01-22 14:46:49.177170: step: 1396/530, loss: 0.002793791936710477
2023-01-22 14:46:50.233333: step: 1400/530, loss: 0.0053272368386387825
2023-01-22 14:46:51.304603: step: 1404/530, loss: 0.005243889056146145
2023-01-22 14:46:52.354641: step: 1408/530, loss: 0.007246647495776415
2023-01-22 14:46:53.420662: step: 1412/530, loss: 0.050715476274490356
2023-01-22 14:46:54.479075: step: 1416/530, loss: 0.051959238946437836
2023-01-22 14:46:55.540590: step: 1420/530, loss: 0.02455473132431507
2023-01-22 14:46:56.601433: step: 1424/530, loss: 0.010326489806175232
2023-01-22 14:46:57.646636: step: 1428/530, loss: 0.009924548678100109
2023-01-22 14:46:58.696113: step: 1432/530, loss: 0.046050846576690674
2023-01-22 14:46:59.755887: step: 1436/530, loss: 0.026995949447155
2023-01-22 14:47:00.805716: step: 1440/530, loss: 0.006940201856195927
2023-01-22 14:47:01.871891: step: 1444/530, loss: 0.01798749342560768
2023-01-22 14:47:02.927302: step: 1448/530, loss: 0.011770684272050858
2023-01-22 14:47:04.001514: step: 1452/530, loss: 0.01490066573023796
2023-01-22 14:47:05.068513: step: 1456/530, loss: 0.02012314833700657
2023-01-22 14:47:06.131075: step: 1460/530, loss: 0.003994438797235489
2023-01-22 14:47:07.191513: step: 1464/530, loss: 0.008913468569517136
2023-01-22 14:47:08.248347: step: 1468/530, loss: 0.007337390910834074
2023-01-22 14:47:09.305505: step: 1472/530, loss: 0.007791111711412668
2023-01-22 14:47:10.350353: step: 1476/530, loss: 0.003587437095120549
2023-01-22 14:47:11.412388: step: 1480/530, loss: 0.026287341490387917
2023-01-22 14:47:12.484502: step: 1484/530, loss: 0.006763038691133261
2023-01-22 14:47:13.544167: step: 1488/530, loss: 0.0037788902409374714
2023-01-22 14:47:14.602820: step: 1492/530, loss: 0.01408185064792633
2023-01-22 14:47:15.654185: step: 1496/530, loss: 0.00588175980374217
2023-01-22 14:47:16.713328: step: 1500/530, loss: 0.009197527542710304
2023-01-22 14:47:17.758415: step: 1504/530, loss: 0.005064733326435089
2023-01-22 14:47:18.808869: step: 1508/530, loss: 0.009162355214357376
2023-01-22 14:47:19.868534: step: 1512/530, loss: 0.010994878597557545
2023-01-22 14:47:20.920215: step: 1516/530, loss: 0.007520737126469612
2023-01-22 14:47:21.970333: step: 1520/530, loss: 0.011643494479358196
2023-01-22 14:47:23.023416: step: 1524/530, loss: 0.006474689580500126
2023-01-22 14:47:24.077569: step: 1528/530, loss: 0.006219760049134493
2023-01-22 14:47:25.123251: step: 1532/530, loss: 0.057099130004644394
2023-01-22 14:47:26.167203: step: 1536/530, loss: 0.009170408360660076
2023-01-22 14:47:27.220254: step: 1540/530, loss: 0.022626172751188278
2023-01-22 14:47:28.266945: step: 1544/530, loss: 0.04263249412178993
2023-01-22 14:47:29.336693: step: 1548/530, loss: 0.005704390350729227
2023-01-22 14:47:30.381681: step: 1552/530, loss: 0.008012990467250347
2023-01-22 14:47:31.447510: step: 1556/530, loss: 0.02050148695707321
2023-01-22 14:47:32.526769: step: 1560/530, loss: 0.03643443435430527
2023-01-22 14:47:33.598825: step: 1564/530, loss: 0.005676362197846174
2023-01-22 14:47:34.656544: step: 1568/530, loss: 0.002216193126514554
2023-01-22 14:47:35.710545: step: 1572/530, loss: 0.03826082870364189
2023-01-22 14:47:36.774721: step: 1576/530, loss: 0.03358278423547745
2023-01-22 14:47:37.838095: step: 1580/530, loss: 0.020951375365257263
2023-01-22 14:47:38.892079: step: 1584/530, loss: 0.010042297653853893
2023-01-22 14:47:39.968016: step: 1588/530, loss: 0.048121415078639984
2023-01-22 14:47:41.034209: step: 1592/530, loss: 0.0379815548658371
2023-01-22 14:47:42.083207: step: 1596/530, loss: 0.008974720723927021
2023-01-22 14:47:43.134003: step: 1600/530, loss: 0.006458432879298925
2023-01-22 14:47:44.187912: step: 1604/530, loss: 0.04805876314640045
2023-01-22 14:47:45.237982: step: 1608/530, loss: 0.005108897108584642
2023-01-22 14:47:46.298653: step: 1612/530, loss: 0.006622752640396357
2023-01-22 14:47:47.345398: step: 1616/530, loss: 0.00990348681807518
2023-01-22 14:47:48.413834: step: 1620/530, loss: 0.014538360759615898
2023-01-22 14:47:49.482237: step: 1624/530, loss: 0.008196043781936169
2023-01-22 14:47:50.547606: step: 1628/530, loss: 0.04106898978352547
2023-01-22 14:47:51.587017: step: 1632/530, loss: 0.0017260070890188217
2023-01-22 14:47:52.659248: step: 1636/530, loss: 0.0043150316923856735
2023-01-22 14:47:53.713316: step: 1640/530, loss: 0.009698811918497086
2023-01-22 14:47:54.771498: step: 1644/530, loss: 0.007644013501703739
2023-01-22 14:47:55.821738: step: 1648/530, loss: 0.0069054607301950455
2023-01-22 14:47:56.880125: step: 1652/530, loss: 0.005940628703683615
2023-01-22 14:47:57.931798: step: 1656/530, loss: 0.018340660259127617
2023-01-22 14:47:58.991298: step: 1660/530, loss: 0.007820161059498787
2023-01-22 14:48:00.048541: step: 1664/530, loss: 0.0076900371350348
2023-01-22 14:48:01.103859: step: 1668/530, loss: 0.005237432196736336
2023-01-22 14:48:02.167011: step: 1672/530, loss: 0.001233618357218802
2023-01-22 14:48:03.228922: step: 1676/530, loss: 0.013445669785141945
2023-01-22 14:48:04.290815: step: 1680/530, loss: 0.009576022624969482
2023-01-22 14:48:05.340079: step: 1684/530, loss: 0.006483124103397131
2023-01-22 14:48:06.395964: step: 1688/530, loss: 0.013715866953134537
2023-01-22 14:48:07.453840: step: 1692/530, loss: 0.0030313965398818254
2023-01-22 14:48:08.527205: step: 1696/530, loss: 0.045827221125364304
2023-01-22 14:48:09.574178: step: 1700/530, loss: 0.016571419313549995
2023-01-22 14:48:10.626325: step: 1704/530, loss: 0.11035176366567612
2023-01-22 14:48:11.692999: step: 1708/530, loss: 0.026345668360590935
2023-01-22 14:48:12.753459: step: 1712/530, loss: 0.036703646183013916
2023-01-22 14:48:13.801069: step: 1716/530, loss: 0.052943695336580276
2023-01-22 14:48:14.853805: step: 1720/530, loss: 0.02062053792178631
2023-01-22 14:48:15.900302: step: 1724/530, loss: 0.0069045559503138065
2023-01-22 14:48:16.972489: step: 1728/530, loss: 0.008250270038843155
2023-01-22 14:48:18.015823: step: 1732/530, loss: 0.007133954670280218
2023-01-22 14:48:19.084970: step: 1736/530, loss: 0.008840522728860378
2023-01-22 14:48:20.139259: step: 1740/530, loss: 0.007804329041391611
2023-01-22 14:48:21.198746: step: 1744/530, loss: 0.013568085618317127
2023-01-22 14:48:22.255126: step: 1748/530, loss: 0.006300191394984722
2023-01-22 14:48:23.315287: step: 1752/530, loss: 0.008131958544254303
2023-01-22 14:48:24.372868: step: 1756/530, loss: 0.00818594265729189
2023-01-22 14:48:25.413669: step: 1760/530, loss: 0.008316697552800179
2023-01-22 14:48:26.461949: step: 1764/530, loss: 0.008807742968201637
2023-01-22 14:48:27.505879: step: 1768/530, loss: 0.0018822801066562533
2023-01-22 14:48:28.547169: step: 1772/530, loss: 0.013648509979248047
2023-01-22 14:48:29.611431: step: 1776/530, loss: 0.017972175031900406
2023-01-22 14:48:30.670698: step: 1780/530, loss: 0.05904356762766838
2023-01-22 14:48:31.729576: step: 1784/530, loss: 0.019957704469561577
2023-01-22 14:48:32.817869: step: 1788/530, loss: 0.015411603264510632
2023-01-22 14:48:33.878578: step: 1792/530, loss: 0.0024024546146392822
2023-01-22 14:48:34.950335: step: 1796/530, loss: 0.0007687581819482148
2023-01-22 14:48:36.007477: step: 1800/530, loss: 0.006707440130412579
2023-01-22 14:48:37.063306: step: 1804/530, loss: 0.00202168058604002
2023-01-22 14:48:38.119300: step: 1808/530, loss: 0.0043829320929944515
2023-01-22 14:48:39.183341: step: 1812/530, loss: 0.005272049456834793
2023-01-22 14:48:40.243357: step: 1816/530, loss: 0.008434496819972992
2023-01-22 14:48:41.306545: step: 1820/530, loss: 0.006302823778241873
2023-01-22 14:48:42.360304: step: 1824/530, loss: 0.009139463305473328
2023-01-22 14:48:43.416796: step: 1828/530, loss: 0.02131139300763607
2023-01-22 14:48:44.458443: step: 1832/530, loss: 0.007144282106310129
2023-01-22 14:48:45.522339: step: 1836/530, loss: 0.102424256503582
2023-01-22 14:48:46.599425: step: 1840/530, loss: 0.044889748096466064
2023-01-22 14:48:47.648922: step: 1844/530, loss: 0.04495002701878548
2023-01-22 14:48:48.717188: step: 1848/530, loss: 0.03323684260249138
2023-01-22 14:48:49.763006: step: 1852/530, loss: 0.005998342763632536
2023-01-22 14:48:50.826167: step: 1856/530, loss: 0.01888926513493061
2023-01-22 14:48:51.884573: step: 1860/530, loss: 0.005591218359768391
2023-01-22 14:48:52.948455: step: 1864/530, loss: 0.02288639359176159
2023-01-22 14:48:54.018700: step: 1868/530, loss: 0.010034807026386261
2023-01-22 14:48:55.081485: step: 1872/530, loss: 0.013417620211839676
2023-01-22 14:48:56.132771: step: 1876/530, loss: 0.003257042495533824
2023-01-22 14:48:57.179557: step: 1880/530, loss: 0.013652905821800232
2023-01-22 14:48:58.228715: step: 1884/530, loss: 0.007731796707957983
2023-01-22 14:48:59.304345: step: 1888/530, loss: 0.03888445720076561
2023-01-22 14:49:00.392643: step: 1892/530, loss: 0.04473840445280075
2023-01-22 14:49:01.450598: step: 1896/530, loss: 0.004404390696436167
2023-01-22 14:49:02.537570: step: 1900/530, loss: 0.013368918560445309
2023-01-22 14:49:03.590893: step: 1904/530, loss: 0.03038119710981846
2023-01-22 14:49:04.642535: step: 1908/530, loss: 0.01971774734556675
2023-01-22 14:49:05.721792: step: 1912/530, loss: 0.003974567167460918
2023-01-22 14:49:06.785937: step: 1916/530, loss: 0.0059807682409882545
2023-01-22 14:49:07.842744: step: 1920/530, loss: 0.006222272291779518
2023-01-22 14:49:08.900102: step: 1924/530, loss: 0.008543187752366066
2023-01-22 14:49:09.964244: step: 1928/530, loss: 0.04808853939175606
2023-01-22 14:49:11.002809: step: 1932/530, loss: 0.0070057157427072525
2023-01-22 14:49:12.079272: step: 1936/530, loss: 0.006611945573240519
2023-01-22 14:49:13.126070: step: 1940/530, loss: 0.0022709087934345007
2023-01-22 14:49:14.179922: step: 1944/530, loss: 0.013978000730276108
2023-01-22 14:49:15.244927: step: 1948/530, loss: 0.007095608394593
2023-01-22 14:49:16.304163: step: 1952/530, loss: 0.0037037008441984653
2023-01-22 14:49:17.376055: step: 1956/530, loss: 0.018672939389944077
2023-01-22 14:49:18.454403: step: 1960/530, loss: 0.03146198019385338
2023-01-22 14:49:19.507839: step: 1964/530, loss: 0.007368862628936768
2023-01-22 14:49:20.569488: step: 1968/530, loss: 0.006628585048019886
2023-01-22 14:49:21.610622: step: 1972/530, loss: 0.009114941582083702
2023-01-22 14:49:22.672186: step: 1976/530, loss: 0.006100182421505451
2023-01-22 14:49:23.723300: step: 1980/530, loss: 0.024046972393989563
2023-01-22 14:49:24.794641: step: 1984/530, loss: 0.03565197065472603
2023-01-22 14:49:25.844478: step: 1988/530, loss: 0.006098717916756868
2023-01-22 14:49:26.894627: step: 1992/530, loss: 0.0014652959071099758
2023-01-22 14:49:27.981720: step: 1996/530, loss: 0.02639559842646122
2023-01-22 14:49:29.045564: step: 2000/530, loss: 0.002592522883787751
2023-01-22 14:49:30.103369: step: 2004/530, loss: 0.005869527813047171
2023-01-22 14:49:31.174039: step: 2008/530, loss: 0.0055039809085428715
2023-01-22 14:49:32.235621: step: 2012/530, loss: 0.0528530478477478
2023-01-22 14:49:33.295827: step: 2016/530, loss: 0.020423760637640953
2023-01-22 14:49:34.359273: step: 2020/530, loss: 0.01448429748415947
2023-01-22 14:49:35.416983: step: 2024/530, loss: 0.049726247787475586
2023-01-22 14:49:36.469979: step: 2028/530, loss: 0.011955785565078259
2023-01-22 14:49:37.520961: step: 2032/530, loss: 0.012852472253143787
2023-01-22 14:49:38.563898: step: 2036/530, loss: 0.01504012756049633
2023-01-22 14:49:39.610348: step: 2040/530, loss: 0.012194959446787834
2023-01-22 14:49:40.687697: step: 2044/530, loss: 0.017821162939071655
2023-01-22 14:49:41.742049: step: 2048/530, loss: 0.0016942271031439304
2023-01-22 14:49:42.808404: step: 2052/530, loss: 0.00821102224290371
2023-01-22 14:49:43.862552: step: 2056/530, loss: 0.007043834775686264
2023-01-22 14:49:44.921851: step: 2060/530, loss: 0.0022062095813453197
2023-01-22 14:49:46.000334: step: 2064/530, loss: 0.013299858197569847
2023-01-22 14:49:47.055284: step: 2068/530, loss: 0.00624550087377429
2023-01-22 14:49:48.119335: step: 2072/530, loss: 0.005537162069231272
2023-01-22 14:49:49.168599: step: 2076/530, loss: 0.04955968260765076
2023-01-22 14:49:50.228639: step: 2080/530, loss: 0.00856846198439598
2023-01-22 14:49:51.272220: step: 2084/530, loss: 0.012305052950978279
2023-01-22 14:49:52.336884: step: 2088/530, loss: 0.021465018391609192
2023-01-22 14:49:53.391416: step: 2092/530, loss: 0.01626303605735302
2023-01-22 14:49:54.454669: step: 2096/530, loss: 0.025284258648753166
2023-01-22 14:49:55.520564: step: 2100/530, loss: 0.0010533814784139395
2023-01-22 14:49:56.570113: step: 2104/530, loss: 0.010778271593153477
2023-01-22 14:49:57.621200: step: 2108/530, loss: 0.035653628408908844
2023-01-22 14:49:58.691779: step: 2112/530, loss: 0.019491948187351227
2023-01-22 14:49:59.763397: step: 2116/530, loss: 0.007639611605554819
2023-01-22 14:50:00.812067: step: 2120/530, loss: 0.025413960218429565
==================================================
Loss: 0.017
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3515308181176234, 'r': 0.2874948436597641, 'f1': 0.31630434782608696}, 'combined': 0.23306636155606406, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.34969136484179975, 'r': 0.23534017651130615, 'f1': 0.28134013881031855}, 'combined': 0.18658827858922677, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3149284757250946, 'r': 0.29107025786713286, 'f1': 0.30252971683827984}, 'combined': 0.20168647789218655, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.39053712859932777, 'r': 0.3191304265764004, 'f1': 0.3512413087927192}, 'combined': 0.2292311699489325, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3052017799098249, 'r': 0.3347374360301305, 'f1': 0.31928801590566297}, 'combined': 0.23526485382522533, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35350048122775574, 'r': 0.3314640875927788, 'f1': 0.3421278115904017}, 'combined': 0.22690341908586223, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3517156862745098, 'r': 0.3416666666666666, 'f1': 0.34661835748792263}, 'combined': 0.23107890499194841, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5694444444444444, 'r': 0.44565217391304346, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 1}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3539948191791955, 'r': 0.2874948436597641, 'f1': 0.31729797404962445}, 'combined': 0.2337985071944601, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3327229658912983, 'r': 0.23081040947075393, 'f1': 0.27255146671075275}, 'combined': 0.18075952196360803, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3136233135239319, 'r': 0.3368326289460066, 'f1': 0.32481389836147384}, 'combined': 0.23933655668740175, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3436080546157674, 'r': 0.3331956893243805, 'f1': 0.3383217768524479}, 'combined': 0.2243792095187219, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 14:52:33.400720: step: 4/530, loss: 0.03830849751830101
2023-01-22 14:52:34.463014: step: 8/530, loss: 0.004272417165338993
2023-01-22 14:52:35.510522: step: 12/530, loss: 0.00348020251840353
2023-01-22 14:52:36.554987: step: 16/530, loss: 0.003912493120878935
2023-01-22 14:52:37.612540: step: 20/530, loss: 0.015317593701183796
2023-01-22 14:52:38.682315: step: 24/530, loss: 0.006323241163045168
2023-01-22 14:52:39.736582: step: 28/530, loss: 0.012455908581614494
2023-01-22 14:52:40.786535: step: 32/530, loss: 0.004830619785934687
2023-01-22 14:52:41.862346: step: 36/530, loss: 0.04608432576060295
2023-01-22 14:52:42.916111: step: 40/530, loss: 0.006739404052495956
2023-01-22 14:52:43.974584: step: 44/530, loss: 0.00015774389612488449
2023-01-22 14:52:45.020219: step: 48/530, loss: 0.006800433155149221
2023-01-22 14:52:46.076211: step: 52/530, loss: 0.005926321726292372
2023-01-22 14:52:47.119267: step: 56/530, loss: 0.00492703914642334
2023-01-22 14:52:48.171978: step: 60/530, loss: 0.016003718599677086
2023-01-22 14:52:49.229061: step: 64/530, loss: 0.011791661381721497
2023-01-22 14:52:50.280428: step: 68/530, loss: 0.007783927954733372
2023-01-22 14:52:51.358030: step: 72/530, loss: 0.010496499016880989
2023-01-22 14:52:52.401818: step: 76/530, loss: 0.024391213431954384
2023-01-22 14:52:53.474182: step: 80/530, loss: 0.008913041092455387
2023-01-22 14:52:54.531517: step: 84/530, loss: 0.019941633567214012
2023-01-22 14:52:55.590329: step: 88/530, loss: 0.006277988199144602
2023-01-22 14:52:56.645859: step: 92/530, loss: 0.0052498579025268555
2023-01-22 14:52:57.703572: step: 96/530, loss: 0.008977203629910946
2023-01-22 14:52:58.749505: step: 100/530, loss: 0.0009111884282901883
2023-01-22 14:52:59.819356: step: 104/530, loss: 0.00698726624250412
2023-01-22 14:53:00.867898: step: 108/530, loss: 0.002838561777025461
2023-01-22 14:53:01.923723: step: 112/530, loss: 0.027512403205037117
2023-01-22 14:53:02.993673: step: 116/530, loss: 0.004172388464212418
2023-01-22 14:53:04.058966: step: 120/530, loss: 0.005863985512405634
2023-01-22 14:53:05.117754: step: 124/530, loss: 0.01308408658951521
2023-01-22 14:53:06.175037: step: 128/530, loss: 0.00741575937718153
2023-01-22 14:53:07.237559: step: 132/530, loss: 0.003897832939401269
2023-01-22 14:53:08.292073: step: 136/530, loss: 0.016058480367064476
2023-01-22 14:53:09.341932: step: 140/530, loss: 0.0027992348186671734
2023-01-22 14:53:10.407978: step: 144/530, loss: 0.00595830986276269
2023-01-22 14:53:11.462074: step: 148/530, loss: 0.0018581663025543094
2023-01-22 14:53:12.528733: step: 152/530, loss: 0.009636035189032555
2023-01-22 14:53:13.594030: step: 156/530, loss: 0.01135893166065216
2023-01-22 14:53:14.646556: step: 160/530, loss: 0.022958068177103996
2023-01-22 14:53:15.712834: step: 164/530, loss: 0.015002578496932983
2023-01-22 14:53:16.773803: step: 168/530, loss: 0.0028302313294261694
2023-01-22 14:53:17.838319: step: 172/530, loss: 0.0030597480945289135
2023-01-22 14:53:18.904312: step: 176/530, loss: 0.008101699873805046
2023-01-22 14:53:19.956585: step: 180/530, loss: 0.008104205131530762
2023-01-22 14:53:21.023674: step: 184/530, loss: 0.0036568562500178814
2023-01-22 14:53:22.109426: step: 188/530, loss: 0.002451567677780986
2023-01-22 14:53:23.159889: step: 192/530, loss: 0.007346960250288248
2023-01-22 14:53:24.206454: step: 196/530, loss: 0.005959811620414257
2023-01-22 14:53:25.255913: step: 200/530, loss: 0.0035565511789172888
2023-01-22 14:53:26.309248: step: 204/530, loss: 0.0018945239717140794
2023-01-22 14:53:27.371719: step: 208/530, loss: 0.040351562201976776
2023-01-22 14:53:28.435797: step: 212/530, loss: 0.006793188862502575
2023-01-22 14:53:29.493955: step: 216/530, loss: 0.0429779551923275
2023-01-22 14:53:30.567818: step: 220/530, loss: 0.021766873076558113
2023-01-22 14:53:31.624308: step: 224/530, loss: 0.0067368075251579285
2023-01-22 14:53:32.675668: step: 228/530, loss: 0.011793391779065132
2023-01-22 14:53:33.724632: step: 232/530, loss: 0.016362538561224937
2023-01-22 14:53:34.779454: step: 236/530, loss: 0.01306929625570774
2023-01-22 14:53:35.843134: step: 240/530, loss: 0.04366306960582733
2023-01-22 14:53:36.901704: step: 244/530, loss: 0.011362576857209206
2023-01-22 14:53:37.955593: step: 248/530, loss: 0.006602996960282326
2023-01-22 14:53:39.017250: step: 252/530, loss: 0.0026361204218119383
2023-01-22 14:53:40.066641: step: 256/530, loss: 0.0072457618080079556
2023-01-22 14:53:41.121516: step: 260/530, loss: 0.0031088402029126883
2023-01-22 14:53:42.187150: step: 264/530, loss: 0.006078782491385937
2023-01-22 14:53:43.237654: step: 268/530, loss: 0.005344335455447435
2023-01-22 14:53:44.304097: step: 272/530, loss: 0.015432574786245823
2023-01-22 14:53:45.364799: step: 276/530, loss: 0.06276095658540726
2023-01-22 14:53:46.425521: step: 280/530, loss: 0.008786395192146301
2023-01-22 14:53:47.486555: step: 284/530, loss: 0.037227388471364975
2023-01-22 14:53:48.544066: step: 288/530, loss: 0.009415870532393456
2023-01-22 14:53:49.613799: step: 292/530, loss: 0.009040523320436478
2023-01-22 14:53:50.663099: step: 296/530, loss: 0.014838225208222866
2023-01-22 14:53:51.743460: step: 300/530, loss: 0.005100354086607695
2023-01-22 14:53:52.812498: step: 304/530, loss: 0.011318660341203213
2023-01-22 14:53:53.892664: step: 308/530, loss: 0.022383419796824455
2023-01-22 14:53:54.964643: step: 312/530, loss: 0.026665139943361282
2023-01-22 14:53:56.031683: step: 316/530, loss: 0.011003552004694939
2023-01-22 14:53:57.105994: step: 320/530, loss: 0.007331583183258772
2023-01-22 14:53:58.177031: step: 324/530, loss: 0.013284152373671532
2023-01-22 14:53:59.237175: step: 328/530, loss: 0.00047639376134611666
2023-01-22 14:54:00.293487: step: 332/530, loss: 0.01065723318606615
2023-01-22 14:54:01.367837: step: 336/530, loss: 0.009985333308577538
2023-01-22 14:54:02.438347: step: 340/530, loss: 0.01382972951978445
2023-01-22 14:54:03.499492: step: 344/530, loss: 0.00889263954013586
2023-01-22 14:54:04.583670: step: 348/530, loss: 0.0050600310787558556
2023-01-22 14:54:05.669550: step: 352/530, loss: 0.014898564666509628
2023-01-22 14:54:06.729184: step: 356/530, loss: 0.0014267188962548971
2023-01-22 14:54:07.804669: step: 360/530, loss: 0.035885490477085114
2023-01-22 14:54:08.876093: step: 364/530, loss: 0.015636736527085304
2023-01-22 14:54:09.935758: step: 368/530, loss: 0.00255257124081254
2023-01-22 14:54:11.000251: step: 372/530, loss: 0.03656373172998428
2023-01-22 14:54:12.052361: step: 376/530, loss: 0.01856282912194729
2023-01-22 14:54:13.129306: step: 380/530, loss: 0.008967249654233456
2023-01-22 14:54:14.184634: step: 384/530, loss: 0.0033324859105050564
2023-01-22 14:54:15.239652: step: 388/530, loss: 0.009601646102964878
2023-01-22 14:54:16.295097: step: 392/530, loss: 0.01912969909608364
2023-01-22 14:54:17.355339: step: 396/530, loss: 0.04187491908669472
2023-01-22 14:54:18.411069: step: 400/530, loss: 0.024936838075518608
2023-01-22 14:54:19.477188: step: 404/530, loss: 0.021949777379631996
2023-01-22 14:54:20.544130: step: 408/530, loss: 0.0026543322019279003
2023-01-22 14:54:21.598367: step: 412/530, loss: 0.019496483728289604
2023-01-22 14:54:22.663153: step: 416/530, loss: 0.016112327575683594
2023-01-22 14:54:23.727073: step: 420/530, loss: 0.0018655316671356559
2023-01-22 14:54:24.792132: step: 424/530, loss: 0.00506379920989275
2023-01-22 14:54:25.876295: step: 428/530, loss: 0.007076523266732693
2023-01-22 14:54:26.962022: step: 432/530, loss: 0.004724256694316864
2023-01-22 14:54:28.022717: step: 436/530, loss: 0.0009300881647504866
2023-01-22 14:54:29.077272: step: 440/530, loss: 0.01967928558588028
2023-01-22 14:54:30.154441: step: 444/530, loss: 0.03559243679046631
2023-01-22 14:54:31.225245: step: 448/530, loss: 0.009139588102698326
2023-01-22 14:54:32.312291: step: 452/530, loss: 0.0041012391448020935
2023-01-22 14:54:33.380533: step: 456/530, loss: 0.005966047290712595
2023-01-22 14:54:34.435364: step: 460/530, loss: 0.007415559142827988
2023-01-22 14:54:35.490674: step: 464/530, loss: 0.021157141774892807
2023-01-22 14:54:36.559881: step: 468/530, loss: 0.08053687959909439
2023-01-22 14:54:37.632218: step: 472/530, loss: 0.01863412745296955
2023-01-22 14:54:38.676658: step: 476/530, loss: 0.002944591222330928
2023-01-22 14:54:39.740286: step: 480/530, loss: 0.0009802079293876886
2023-01-22 14:54:40.793807: step: 484/530, loss: 0.02424168772995472
2023-01-22 14:54:41.840229: step: 488/530, loss: 0.007077371701598167
2023-01-22 14:54:42.897663: step: 492/530, loss: 0.00805947557091713
2023-01-22 14:54:43.982556: step: 496/530, loss: 0.0027319644577801228
2023-01-22 14:54:45.048683: step: 500/530, loss: 0.034257207065820694
2023-01-22 14:54:46.125067: step: 504/530, loss: 0.033649932593107224
2023-01-22 14:54:47.176748: step: 508/530, loss: 0.006967397406697273
2023-01-22 14:54:48.228553: step: 512/530, loss: 0.010623359121382236
2023-01-22 14:54:49.295240: step: 516/530, loss: 0.009382132440805435
2023-01-22 14:54:50.364694: step: 520/530, loss: 0.04060875624418259
2023-01-22 14:54:51.439744: step: 524/530, loss: 0.010053067468106747
2023-01-22 14:54:52.497255: step: 528/530, loss: 0.010939398780465126
2023-01-22 14:54:53.559246: step: 532/530, loss: 0.012207222171127796
2023-01-22 14:54:54.613695: step: 536/530, loss: 0.009608657099306583
2023-01-22 14:54:55.679731: step: 540/530, loss: 0.0790538638830185
2023-01-22 14:54:56.737057: step: 544/530, loss: 0.002581463661044836
2023-01-22 14:54:57.788589: step: 548/530, loss: 0.014704625122249126
2023-01-22 14:54:58.849726: step: 552/530, loss: 0.005571231245994568
2023-01-22 14:54:59.915750: step: 556/530, loss: 0.0032217407133430243
2023-01-22 14:55:00.970940: step: 560/530, loss: 0.018742961809039116
2023-01-22 14:55:02.046211: step: 564/530, loss: 0.02074114792048931
2023-01-22 14:55:03.149981: step: 568/530, loss: 0.004272344522178173
2023-01-22 14:55:04.207417: step: 572/530, loss: 0.007194372359663248
2023-01-22 14:55:05.266735: step: 576/530, loss: 0.005343187600374222
2023-01-22 14:55:06.315957: step: 580/530, loss: 0.04343001917004585
2023-01-22 14:55:07.370958: step: 584/530, loss: 0.025682929903268814
2023-01-22 14:55:08.442165: step: 588/530, loss: 0.022661201655864716
2023-01-22 14:55:09.505278: step: 592/530, loss: 0.006161550059914589
2023-01-22 14:55:10.570713: step: 596/530, loss: 0.004233218729496002
2023-01-22 14:55:11.634476: step: 600/530, loss: 0.02702989988029003
2023-01-22 14:55:12.694796: step: 604/530, loss: 0.011828666552901268
2023-01-22 14:55:13.751905: step: 608/530, loss: 0.0019650631584227085
2023-01-22 14:55:14.804706: step: 612/530, loss: 0.018269114196300507
2023-01-22 14:55:15.852489: step: 616/530, loss: 0.07163850963115692
2023-01-22 14:55:16.909401: step: 620/530, loss: 0.0191291943192482
2023-01-22 14:55:17.983485: step: 624/530, loss: 0.0045981816947460175
2023-01-22 14:55:19.033714: step: 628/530, loss: 0.01305360533297062
2023-01-22 14:55:20.094008: step: 632/530, loss: 0.006944219581782818
2023-01-22 14:55:21.151910: step: 636/530, loss: 0.043573424220085144
2023-01-22 14:55:22.213519: step: 640/530, loss: 0.004806590732187033
2023-01-22 14:55:23.261001: step: 644/530, loss: 0.004089280962944031
2023-01-22 14:55:24.303175: step: 648/530, loss: 0.0021924462635070086
2023-01-22 14:55:25.367602: step: 652/530, loss: 0.027001388370990753
2023-01-22 14:55:26.432342: step: 656/530, loss: 0.009096109308302402
2023-01-22 14:55:27.475377: step: 660/530, loss: 0.005412059370428324
2023-01-22 14:55:28.536157: step: 664/530, loss: 0.0038483578246086836
2023-01-22 14:55:29.591334: step: 668/530, loss: 0.012189789675176144
2023-01-22 14:55:30.678516: step: 672/530, loss: 0.00406645005568862
2023-01-22 14:55:31.734862: step: 676/530, loss: 0.002935217460617423
2023-01-22 14:55:32.834227: step: 680/530, loss: 0.005596601869910955
2023-01-22 14:55:33.884033: step: 684/530, loss: 0.008266955614089966
2023-01-22 14:55:34.937344: step: 688/530, loss: 0.00819226261228323
2023-01-22 14:55:35.998251: step: 692/530, loss: 0.00271823862567544
2023-01-22 14:55:37.047654: step: 696/530, loss: 0.02649662271142006
2023-01-22 14:55:38.119543: step: 700/530, loss: 0.0025134568568319082
2023-01-22 14:55:39.188454: step: 704/530, loss: 0.026998931542038918
2023-01-22 14:55:40.265737: step: 708/530, loss: 0.07398656010627747
2023-01-22 14:55:41.315614: step: 712/530, loss: 0.004583791829645634
2023-01-22 14:55:42.391378: step: 716/530, loss: 0.011217488907277584
2023-01-22 14:55:43.454784: step: 720/530, loss: 0.005903860088437796
2023-01-22 14:55:44.524224: step: 724/530, loss: 0.01827486790716648
2023-01-22 14:55:45.572768: step: 728/530, loss: 0.0011834341567009687
2023-01-22 14:55:46.615276: step: 732/530, loss: 0.009780907072126865
2023-01-22 14:55:47.677676: step: 736/530, loss: 0.014985663816332817
2023-01-22 14:55:48.746794: step: 740/530, loss: 0.005799142178148031
2023-01-22 14:55:49.814839: step: 744/530, loss: 0.03446214646100998
2023-01-22 14:55:50.863747: step: 748/530, loss: 0.007220752537250519
2023-01-22 14:55:51.952671: step: 752/530, loss: 0.006901652552187443
2023-01-22 14:55:53.014882: step: 756/530, loss: 0.007248778827488422
2023-01-22 14:55:54.083679: step: 760/530, loss: 0.020982099696993828
2023-01-22 14:55:55.164470: step: 764/530, loss: 0.0064823743887245655
2023-01-22 14:55:56.219616: step: 768/530, loss: 0.028136756271123886
2023-01-22 14:55:57.278657: step: 772/530, loss: 0.01176868099719286
2023-01-22 14:55:58.333241: step: 776/530, loss: 0.025836462154984474
2023-01-22 14:55:59.413354: step: 780/530, loss: 0.011618404649198055
2023-01-22 14:56:00.478640: step: 784/530, loss: 0.0043899924494326115
2023-01-22 14:56:01.551630: step: 788/530, loss: 0.03393419086933136
2023-01-22 14:56:02.633198: step: 792/530, loss: 0.047133918851614
2023-01-22 14:56:03.690336: step: 796/530, loss: 0.004061580635607243
2023-01-22 14:56:04.747626: step: 800/530, loss: 0.015773583203554153
2023-01-22 14:56:05.787691: step: 804/530, loss: 0.0127754220739007
2023-01-22 14:56:06.843744: step: 808/530, loss: 0.003339008428156376
2023-01-22 14:56:07.923133: step: 812/530, loss: 0.00044267220073379576
2023-01-22 14:56:08.994435: step: 816/530, loss: 0.009378723800182343
2023-01-22 14:56:10.056650: step: 820/530, loss: 0.002209109254181385
2023-01-22 14:56:11.114580: step: 824/530, loss: 0.009332009591162205
2023-01-22 14:56:12.176406: step: 828/530, loss: 0.007360921707004309
2023-01-22 14:56:13.258581: step: 832/530, loss: 0.00873157475143671
2023-01-22 14:56:14.308759: step: 836/530, loss: 0.0046147494576871395
2023-01-22 14:56:15.372192: step: 840/530, loss: 0.03381947800517082
2023-01-22 14:56:16.438223: step: 844/530, loss: 0.00823169108480215
2023-01-22 14:56:17.520181: step: 848/530, loss: 0.012753130868077278
2023-01-22 14:56:18.577281: step: 852/530, loss: 0.0015375040238723159
2023-01-22 14:56:19.665244: step: 856/530, loss: 0.0038569860626012087
2023-01-22 14:56:20.753536: step: 860/530, loss: 0.028392739593982697
2023-01-22 14:56:21.822058: step: 864/530, loss: 0.007941746152937412
2023-01-22 14:56:22.877218: step: 868/530, loss: 0.03349953144788742
2023-01-22 14:56:23.928706: step: 872/530, loss: 0.004938963800668716
2023-01-22 14:56:24.997216: step: 876/530, loss: 0.005563479848206043
2023-01-22 14:56:26.058180: step: 880/530, loss: 0.0005900624673813581
2023-01-22 14:56:27.115675: step: 884/530, loss: 0.0037981749046593904
2023-01-22 14:56:28.172956: step: 888/530, loss: 0.05201589688658714
2023-01-22 14:56:29.220655: step: 892/530, loss: 0.08416608721017838
2023-01-22 14:56:30.278993: step: 896/530, loss: 0.0034238682128489017
2023-01-22 14:56:31.340869: step: 900/530, loss: 0.016306059435009956
2023-01-22 14:56:32.405212: step: 904/530, loss: 0.0248987078666687
2023-01-22 14:56:33.469583: step: 908/530, loss: 0.00760595453903079
2023-01-22 14:56:34.544526: step: 912/530, loss: 0.008105680346488953
2023-01-22 14:56:35.599828: step: 916/530, loss: 0.026912283152341843
2023-01-22 14:56:36.667930: step: 920/530, loss: 0.015558757819235325
2023-01-22 14:56:37.718529: step: 924/530, loss: 0.007810003124177456
2023-01-22 14:56:38.771575: step: 928/530, loss: 0.008646205067634583
2023-01-22 14:56:39.841824: step: 932/530, loss: 0.009670023806393147
2023-01-22 14:56:40.931252: step: 936/530, loss: 0.00692980969324708
2023-01-22 14:56:41.968650: step: 940/530, loss: 0.007936788722872734
2023-01-22 14:56:43.028419: step: 944/530, loss: 0.005081878509372473
2023-01-22 14:56:44.088241: step: 948/530, loss: 0.02534194476902485
2023-01-22 14:56:45.146132: step: 952/530, loss: 0.0066781374625861645
2023-01-22 14:56:46.195532: step: 956/530, loss: 0.017519844695925713
2023-01-22 14:56:47.251042: step: 960/530, loss: 0.0042097545228898525
2023-01-22 14:56:48.314587: step: 964/530, loss: 0.010341073386371136
2023-01-22 14:56:49.360905: step: 968/530, loss: 0.016094431281089783
2023-01-22 14:56:50.441317: step: 972/530, loss: 0.005197430960834026
2023-01-22 14:56:51.479449: step: 976/530, loss: 0.0024263649247586727
2023-01-22 14:56:52.537494: step: 980/530, loss: 0.013275329023599625
2023-01-22 14:56:53.619518: step: 984/530, loss: 0.0313597097992897
2023-01-22 14:56:54.671581: step: 988/530, loss: 0.008750798180699348
2023-01-22 14:56:55.749691: step: 992/530, loss: 0.013497157022356987
2023-01-22 14:56:56.802374: step: 996/530, loss: 0.011439335532486439
2023-01-22 14:56:57.857016: step: 1000/530, loss: 0.0008156416588462889
2023-01-22 14:56:58.902365: step: 1004/530, loss: 0.0024146183859556913
2023-01-22 14:56:59.967115: step: 1008/530, loss: 0.024139579385519028
2023-01-22 14:57:01.036245: step: 1012/530, loss: 0.011094674468040466
2023-01-22 14:57:02.110995: step: 1016/530, loss: 0.000186296776519157
2023-01-22 14:57:03.170648: step: 1020/530, loss: 0.012830633670091629
2023-01-22 14:57:04.233250: step: 1024/530, loss: 0.012097098864614964
2023-01-22 14:57:05.304876: step: 1028/530, loss: 0.07429162412881851
2023-01-22 14:57:06.371356: step: 1032/530, loss: 0.003023487748578191
2023-01-22 14:57:07.431107: step: 1036/530, loss: 0.007510166149586439
2023-01-22 14:57:08.486738: step: 1040/530, loss: 0.030068377032876015
2023-01-22 14:57:09.541442: step: 1044/530, loss: 0.0052937413565814495
2023-01-22 14:57:10.598228: step: 1048/530, loss: 0.023958610370755196
2023-01-22 14:57:11.638270: step: 1052/530, loss: 0.008688181638717651
2023-01-22 14:57:12.678192: step: 1056/530, loss: 0.0022241228725761175
2023-01-22 14:57:13.734173: step: 1060/530, loss: 0.023824557662010193
2023-01-22 14:57:14.817340: step: 1064/530, loss: 0.007908256724476814
2023-01-22 14:57:15.855448: step: 1068/530, loss: 0.008151470683515072
2023-01-22 14:57:16.911189: step: 1072/530, loss: 0.004998909309506416
2023-01-22 14:57:17.984142: step: 1076/530, loss: 0.002809560624882579
2023-01-22 14:57:19.023934: step: 1080/530, loss: 0.006118217017501593
2023-01-22 14:57:20.073716: step: 1084/530, loss: 0.0016347829950973392
2023-01-22 14:57:21.128617: step: 1088/530, loss: 0.007763545960187912
2023-01-22 14:57:22.190441: step: 1092/530, loss: 0.008073820732533932
2023-01-22 14:57:23.231949: step: 1096/530, loss: 0.008089671842753887
2023-01-22 14:57:24.304049: step: 1100/530, loss: 0.002720301505178213
2023-01-22 14:57:25.355631: step: 1104/530, loss: 0.0006606941460631788
2023-01-22 14:57:26.420583: step: 1108/530, loss: 0.008163864724338055
2023-01-22 14:57:27.471593: step: 1112/530, loss: 0.003537238808348775
2023-01-22 14:57:28.526307: step: 1116/530, loss: 0.036442194133996964
2023-01-22 14:57:29.580418: step: 1120/530, loss: 0.0036111362278461456
2023-01-22 14:57:30.639374: step: 1124/530, loss: 0.00657380186021328
2023-01-22 14:57:31.696098: step: 1128/530, loss: 0.012925221584737301
2023-01-22 14:57:32.787620: step: 1132/530, loss: 0.002254266757518053
2023-01-22 14:57:33.841355: step: 1136/530, loss: 0.0030186926014721394
2023-01-22 14:57:34.905683: step: 1140/530, loss: 0.0038074322510510683
2023-01-22 14:57:35.962616: step: 1144/530, loss: 0.02031356655061245
2023-01-22 14:57:37.027192: step: 1148/530, loss: 0.009060061536729336
2023-01-22 14:57:38.102943: step: 1152/530, loss: 0.015726851299405098
2023-01-22 14:57:39.155657: step: 1156/530, loss: 0.015478361397981644
2023-01-22 14:57:40.211046: step: 1160/530, loss: 0.01580202579498291
2023-01-22 14:57:41.263920: step: 1164/530, loss: 0.0048694615252316
2023-01-22 14:57:42.327231: step: 1168/530, loss: 0.0008425582200288773
2023-01-22 14:57:43.388125: step: 1172/530, loss: 0.004964488558471203
2023-01-22 14:57:44.453697: step: 1176/530, loss: 0.003799163270741701
2023-01-22 14:57:45.506419: step: 1180/530, loss: 0.0036438065581023693
2023-01-22 14:57:46.565934: step: 1184/530, loss: 0.009946513921022415
2023-01-22 14:57:47.621476: step: 1188/530, loss: 0.006146504543721676
2023-01-22 14:57:48.692021: step: 1192/530, loss: 0.008281688205897808
2023-01-22 14:57:49.751575: step: 1196/530, loss: 0.008926140144467354
2023-01-22 14:57:50.814706: step: 1200/530, loss: 0.0032253882382065058
2023-01-22 14:57:51.878163: step: 1204/530, loss: 0.005319916643202305
2023-01-22 14:57:52.934689: step: 1208/530, loss: 0.01882709190249443
2023-01-22 14:57:53.973823: step: 1212/530, loss: 0.015157544054090977
2023-01-22 14:57:55.038534: step: 1216/530, loss: 0.028837790712714195
2023-01-22 14:57:56.118384: step: 1220/530, loss: 0.009084654040634632
2023-01-22 14:57:57.183150: step: 1224/530, loss: 0.002967196051031351
2023-01-22 14:57:58.259302: step: 1228/530, loss: 0.005479846149682999
2023-01-22 14:57:59.317370: step: 1232/530, loss: 0.011456901207566261
2023-01-22 14:58:00.375555: step: 1236/530, loss: 0.026058072224259377
2023-01-22 14:58:01.424440: step: 1240/530, loss: 0.009730237536132336
2023-01-22 14:58:02.481137: step: 1244/530, loss: 0.004938570782542229
2023-01-22 14:58:03.524428: step: 1248/530, loss: 0.015716299414634705
2023-01-22 14:58:04.593400: step: 1252/530, loss: 0.005117656663060188
2023-01-22 14:58:05.649737: step: 1256/530, loss: 0.005445735529065132
2023-01-22 14:58:06.711516: step: 1260/530, loss: 0.006621215026825666
2023-01-22 14:58:07.781196: step: 1264/530, loss: 0.003206484019756317
2023-01-22 14:58:08.845662: step: 1268/530, loss: 0.009009724482893944
2023-01-22 14:58:09.907949: step: 1272/530, loss: 0.005450892727822065
2023-01-22 14:58:10.980056: step: 1276/530, loss: 0.004926885012537241
2023-01-22 14:58:12.044444: step: 1280/530, loss: 0.0067573431879282
2023-01-22 14:58:13.101408: step: 1284/530, loss: 0.007508815266191959
2023-01-22 14:58:14.152450: step: 1288/530, loss: 0.006166575010865927
2023-01-22 14:58:15.208224: step: 1292/530, loss: 0.019608868286013603
2023-01-22 14:58:16.278097: step: 1296/530, loss: 0.007370079401880503
2023-01-22 14:58:17.326869: step: 1300/530, loss: 0.008584137074649334
2023-01-22 14:58:18.369163: step: 1304/530, loss: 0.008251721039414406
2023-01-22 14:58:19.428056: step: 1308/530, loss: 0.014559527859091759
2023-01-22 14:58:20.496274: step: 1312/530, loss: 0.00041204720037057996
2023-01-22 14:58:21.560925: step: 1316/530, loss: 0.013654079288244247
2023-01-22 14:58:22.622855: step: 1320/530, loss: 0.011036711744964123
2023-01-22 14:58:23.693640: step: 1324/530, loss: 0.006787970196455717
2023-01-22 14:58:24.748880: step: 1328/530, loss: 0.0062184385024011135
2023-01-22 14:58:25.812541: step: 1332/530, loss: 0.011185524985194206
2023-01-22 14:58:26.858314: step: 1336/530, loss: 0.0020422926172614098
2023-01-22 14:58:27.928034: step: 1340/530, loss: 0.026611292734742165
2023-01-22 14:58:28.992983: step: 1344/530, loss: 0.011061306111514568
2023-01-22 14:58:30.058821: step: 1348/530, loss: 0.002936841920018196
2023-01-22 14:58:31.108948: step: 1352/530, loss: 0.006053184159100056
2023-01-22 14:58:32.176248: step: 1356/530, loss: 0.0078385379165411
2023-01-22 14:58:33.227794: step: 1360/530, loss: 0.027981672435998917
2023-01-22 14:58:34.294100: step: 1364/530, loss: 0.005899256560951471
2023-01-22 14:58:35.338168: step: 1368/530, loss: 0.009277153760194778
2023-01-22 14:58:36.414226: step: 1372/530, loss: 0.013136857189238071
2023-01-22 14:58:37.475384: step: 1376/530, loss: 0.006779379677027464
2023-01-22 14:58:38.526085: step: 1380/530, loss: 0.021974775940179825
2023-01-22 14:58:39.577911: step: 1384/530, loss: 0.017812388017773628
2023-01-22 14:58:40.628160: step: 1388/530, loss: 0.02791920118033886
2023-01-22 14:58:41.678000: step: 1392/530, loss: 0.07180716842412949
2023-01-22 14:58:42.740245: step: 1396/530, loss: 0.029926147311925888
2023-01-22 14:58:43.807425: step: 1400/530, loss: 0.03330957889556885
2023-01-22 14:58:44.849299: step: 1404/530, loss: 0.02639223262667656
2023-01-22 14:58:45.903284: step: 1408/530, loss: 0.006298288702964783
2023-01-22 14:58:46.979517: step: 1412/530, loss: 0.005772239528596401
2023-01-22 14:58:48.045252: step: 1416/530, loss: 0.006503175012767315
2023-01-22 14:58:49.105234: step: 1420/530, loss: 0.007208044640719891
2023-01-22 14:58:50.149127: step: 1424/530, loss: 0.00667016115039587
2023-01-22 14:58:51.199972: step: 1428/530, loss: 0.013332558795809746
2023-01-22 14:58:52.249869: step: 1432/530, loss: 0.007782561704516411
2023-01-22 14:58:53.334453: step: 1436/530, loss: 0.061735544353723526
2023-01-22 14:58:54.398789: step: 1440/530, loss: 0.007760784588754177
2023-01-22 14:58:55.436668: step: 1444/530, loss: 0.00817782711237669
2023-01-22 14:58:56.487645: step: 1448/530, loss: 0.02130030281841755
2023-01-22 14:58:57.535312: step: 1452/530, loss: 0.00745581416413188
2023-01-22 14:58:58.605912: step: 1456/530, loss: 0.006255841813981533
2023-01-22 14:58:59.659081: step: 1460/530, loss: 0.007619886193424463
2023-01-22 14:59:00.710173: step: 1464/530, loss: 0.0015675349859520793
2023-01-22 14:59:01.772977: step: 1468/530, loss: 0.01031919289380312
2023-01-22 14:59:02.826993: step: 1472/530, loss: 0.014294839464128017
2023-01-22 14:59:03.876328: step: 1476/530, loss: 0.03906090930104256
2023-01-22 14:59:04.942551: step: 1480/530, loss: 0.006507217884063721
2023-01-22 14:59:05.995960: step: 1484/530, loss: 0.006505871657282114
2023-01-22 14:59:07.049072: step: 1488/530, loss: 0.006274168845266104
2023-01-22 14:59:08.116801: step: 1492/530, loss: 0.010776106268167496
2023-01-22 14:59:09.174100: step: 1496/530, loss: 0.043974798172712326
2023-01-22 14:59:10.231834: step: 1500/530, loss: 0.018454229459166527
2023-01-22 14:59:11.283924: step: 1504/530, loss: 0.0304866936057806
2023-01-22 14:59:12.344837: step: 1508/530, loss: 0.00503520667552948
2023-01-22 14:59:13.420125: step: 1512/530, loss: 0.05261845141649246
2023-01-22 14:59:14.476858: step: 1516/530, loss: 0.003172110766172409
2023-01-22 14:59:15.547837: step: 1520/530, loss: 0.01669536717236042
2023-01-22 14:59:16.607979: step: 1524/530, loss: 0.022329892963171005
2023-01-22 14:59:17.672186: step: 1528/530, loss: 0.00934907142072916
2023-01-22 14:59:18.734015: step: 1532/530, loss: 0.04218725115060806
2023-01-22 14:59:19.781620: step: 1536/530, loss: 0.001676251762546599
2023-01-22 14:59:20.819367: step: 1540/530, loss: 0.0014983321307227015
2023-01-22 14:59:21.860980: step: 1544/530, loss: 0.002265576971694827
2023-01-22 14:59:22.910277: step: 1548/530, loss: 0.008929194882512093
2023-01-22 14:59:23.974701: step: 1552/530, loss: 0.026078056544065475
2023-01-22 14:59:25.046543: step: 1556/530, loss: 0.05054396018385887
2023-01-22 14:59:26.104443: step: 1560/530, loss: 0.0002468690217938274
2023-01-22 14:59:27.168172: step: 1564/530, loss: 0.014086265116930008
2023-01-22 14:59:28.209361: step: 1568/530, loss: 0.007441191468387842
2023-01-22 14:59:29.272435: step: 1572/530, loss: 0.010648136958479881
2023-01-22 14:59:30.335426: step: 1576/530, loss: 0.005768632981926203
2023-01-22 14:59:31.402515: step: 1580/530, loss: 0.0056974077597260475
2023-01-22 14:59:32.450843: step: 1584/530, loss: 0.00878769438713789
2023-01-22 14:59:33.496103: step: 1588/530, loss: 0.004455979913473129
2023-01-22 14:59:34.554844: step: 1592/530, loss: 0.006661464460194111
2023-01-22 14:59:35.621143: step: 1596/530, loss: 0.01725512370467186
2023-01-22 14:59:36.674331: step: 1600/530, loss: 0.0038942231331020594
2023-01-22 14:59:37.740982: step: 1604/530, loss: 0.019099723547697067
2023-01-22 14:59:38.812612: step: 1608/530, loss: 0.004966052249073982
2023-01-22 14:59:39.879901: step: 1612/530, loss: 0.008269388228654861
2023-01-22 14:59:40.932901: step: 1616/530, loss: 0.006289573386311531
2023-01-22 14:59:41.991035: step: 1620/530, loss: 0.0017546447925269604
2023-01-22 14:59:43.048387: step: 1624/530, loss: 0.03393048793077469
2023-01-22 14:59:44.104183: step: 1628/530, loss: 0.0001804940402507782
2023-01-22 14:59:45.172566: step: 1632/530, loss: 0.003419894725084305
2023-01-22 14:59:46.235026: step: 1636/530, loss: 0.006542523857206106
2023-01-22 14:59:47.280308: step: 1640/530, loss: 0.007139252498745918
2023-01-22 14:59:48.333099: step: 1644/530, loss: 0.043527040630578995
2023-01-22 14:59:49.395304: step: 1648/530, loss: 0.008953775279223919
2023-01-22 14:59:50.444551: step: 1652/530, loss: 0.011791087687015533
2023-01-22 14:59:51.501525: step: 1656/530, loss: 0.021676769480109215
2023-01-22 14:59:52.553720: step: 1660/530, loss: 0.023910125717520714
2023-01-22 14:59:53.606084: step: 1664/530, loss: 0.006911794655025005
2023-01-22 14:59:54.665447: step: 1668/530, loss: 0.0026613674126565456
2023-01-22 14:59:55.719701: step: 1672/530, loss: 0.006056721322238445
2023-01-22 14:59:56.801046: step: 1676/530, loss: 0.07970339059829712
2023-01-22 14:59:57.875964: step: 1680/530, loss: 0.004163119941949844
2023-01-22 14:59:58.922329: step: 1684/530, loss: 0.003548156004399061
2023-01-22 14:59:59.980212: step: 1688/530, loss: 0.01911993883550167
2023-01-22 15:00:01.042462: step: 1692/530, loss: 0.003821560414507985
2023-01-22 15:00:02.116227: step: 1696/530, loss: 0.12350290268659592
2023-01-22 15:00:03.178936: step: 1700/530, loss: 0.008791505359113216
2023-01-22 15:00:04.239068: step: 1704/530, loss: 0.0035048595163971186
2023-01-22 15:00:05.303265: step: 1708/530, loss: 0.022502902895212173
2023-01-22 15:00:06.354275: step: 1712/530, loss: 0.0037889645900577307
2023-01-22 15:00:07.418071: step: 1716/530, loss: 0.006935343146324158
2023-01-22 15:00:08.475271: step: 1720/530, loss: 0.0023403456434607506
2023-01-22 15:00:09.514790: step: 1724/530, loss: 0.035330191254615784
2023-01-22 15:00:10.576109: step: 1728/530, loss: 0.006118969991803169
2023-01-22 15:00:11.630154: step: 1732/530, loss: 0.0026141973212361336
2023-01-22 15:00:12.690177: step: 1736/530, loss: 0.00577622652053833
2023-01-22 15:00:13.767722: step: 1740/530, loss: 0.014890418387949467
2023-01-22 15:00:14.845393: step: 1744/530, loss: 0.0020099061075598
2023-01-22 15:00:15.915791: step: 1748/530, loss: 0.007750468794256449
2023-01-22 15:00:16.978002: step: 1752/530, loss: 0.003517107106745243
2023-01-22 15:00:18.047148: step: 1756/530, loss: 0.0046921223402023315
2023-01-22 15:00:19.096920: step: 1760/530, loss: 0.009625013917684555
2023-01-22 15:00:20.142340: step: 1764/530, loss: 0.00412908848375082
2023-01-22 15:00:21.199158: step: 1768/530, loss: 0.006479433737695217
2023-01-22 15:00:22.261633: step: 1772/530, loss: 0.0018711936427280307
2023-01-22 15:00:23.308650: step: 1776/530, loss: 0.007243666332215071
2023-01-22 15:00:24.382737: step: 1780/530, loss: 0.0015129816019907594
2023-01-22 15:00:25.436510: step: 1784/530, loss: 0.0033547296188771725
2023-01-22 15:00:26.502423: step: 1788/530, loss: 0.007298785727471113
2023-01-22 15:00:27.564264: step: 1792/530, loss: 0.004780021030455828
2023-01-22 15:00:28.635714: step: 1796/530, loss: 0.007903102785348892
2023-01-22 15:00:29.702103: step: 1800/530, loss: 0.0066921161487698555
2023-01-22 15:00:30.774074: step: 1804/530, loss: 0.007224877830594778
2023-01-22 15:00:31.845270: step: 1808/530, loss: 0.049612417817115784
2023-01-22 15:00:32.908200: step: 1812/530, loss: 0.006026745308190584
2023-01-22 15:00:33.952680: step: 1816/530, loss: 0.007636575493961573
2023-01-22 15:00:35.013639: step: 1820/530, loss: 0.047898758202791214
2023-01-22 15:00:36.069291: step: 1824/530, loss: 0.009506751783192158
2023-01-22 15:00:37.123488: step: 1828/530, loss: 0.002883909735828638
2023-01-22 15:00:38.191819: step: 1832/530, loss: 0.003468463895842433
2023-01-22 15:00:39.253914: step: 1836/530, loss: 0.00988856516778469
2023-01-22 15:00:40.320332: step: 1840/530, loss: 0.006861596833914518
2023-01-22 15:00:41.378859: step: 1844/530, loss: 0.003527782391756773
2023-01-22 15:00:42.434138: step: 1848/530, loss: 0.0543820858001709
2023-01-22 15:00:43.502296: step: 1852/530, loss: 0.11515577137470245
2023-01-22 15:00:44.564503: step: 1856/530, loss: 0.020946340635418892
2023-01-22 15:00:45.630570: step: 1860/530, loss: 0.0030384231358766556
2023-01-22 15:00:46.694097: step: 1864/530, loss: 0.013064228929579258
2023-01-22 15:00:47.760342: step: 1868/530, loss: 0.006417909637093544
2023-01-22 15:00:48.822935: step: 1872/530, loss: 0.007266604341566563
2023-01-22 15:00:49.892829: step: 1876/530, loss: 0.021571720018982887
2023-01-22 15:00:50.939049: step: 1880/530, loss: 0.03572744503617287
2023-01-22 15:00:51.988981: step: 1884/530, loss: 0.006688064429908991
2023-01-22 15:00:53.060959: step: 1888/530, loss: 0.005250208079814911
2023-01-22 15:00:54.123625: step: 1892/530, loss: 0.011587629094719887
2023-01-22 15:00:55.179899: step: 1896/530, loss: 0.017239123582839966
2023-01-22 15:00:56.228124: step: 1900/530, loss: 0.006558561697602272
2023-01-22 15:00:57.285315: step: 1904/530, loss: 0.005606526974588633
2023-01-22 15:00:58.346239: step: 1908/530, loss: 0.0046849376522004604
2023-01-22 15:00:59.413625: step: 1912/530, loss: 0.012632392346858978
2023-01-22 15:01:00.466936: step: 1916/530, loss: 0.026876933872699738
2023-01-22 15:01:01.518567: step: 1920/530, loss: 0.0023346610832959414
2023-01-22 15:01:02.587158: step: 1924/530, loss: 0.010086340829730034
2023-01-22 15:01:03.645891: step: 1928/530, loss: 0.0017842890229076147
2023-01-22 15:01:04.695460: step: 1932/530, loss: 0.0038866931572556496
2023-01-22 15:01:05.748475: step: 1936/530, loss: 0.01015001256018877
2023-01-22 15:01:06.801975: step: 1940/530, loss: 0.0034856589045375586
2023-01-22 15:01:07.867689: step: 1944/530, loss: 0.006604752037674189
2023-01-22 15:01:08.937862: step: 1948/530, loss: 0.002270351629704237
2023-01-22 15:01:09.992406: step: 1952/530, loss: 0.012573856860399246
2023-01-22 15:01:11.044679: step: 1956/530, loss: 0.0074013033881783485
2023-01-22 15:01:12.092360: step: 1960/530, loss: 0.013016174547374249
2023-01-22 15:01:13.169786: step: 1964/530, loss: 0.013574600219726562
2023-01-22 15:01:14.237451: step: 1968/530, loss: 0.005106010939925909
2023-01-22 15:01:15.309684: step: 1972/530, loss: 0.008784103207290173
2023-01-22 15:01:16.364542: step: 1976/530, loss: 0.011794948019087315
2023-01-22 15:01:17.416354: step: 1980/530, loss: 0.00013226176088210195
2023-01-22 15:01:18.494514: step: 1984/530, loss: 0.05984872207045555
2023-01-22 15:01:19.572959: step: 1988/530, loss: 0.008299821056425571
2023-01-22 15:01:20.630271: step: 1992/530, loss: 0.018250426277518272
2023-01-22 15:01:21.690832: step: 1996/530, loss: 0.003169644856825471
2023-01-22 15:01:22.764297: step: 2000/530, loss: 0.0028978537302464247
2023-01-22 15:01:23.804835: step: 2004/530, loss: 0.015240422450006008
2023-01-22 15:01:24.865301: step: 2008/530, loss: 0.01981269009411335
2023-01-22 15:01:25.928808: step: 2012/530, loss: 0.005478852428495884
2023-01-22 15:01:26.982207: step: 2016/530, loss: 0.005599991884082556
2023-01-22 15:01:28.054159: step: 2020/530, loss: 0.04507221654057503
2023-01-22 15:01:29.095582: step: 2024/530, loss: 0.006508946884423494
2023-01-22 15:01:30.163954: step: 2028/530, loss: 0.006777461618185043
2023-01-22 15:01:31.224201: step: 2032/530, loss: 0.07480142265558243
2023-01-22 15:01:32.314490: step: 2036/530, loss: 0.01196820754557848
2023-01-22 15:01:33.380441: step: 2040/530, loss: 0.015166237950325012
2023-01-22 15:01:34.437912: step: 2044/530, loss: 0.014804341830313206
2023-01-22 15:01:35.499623: step: 2048/530, loss: 0.019065821543335915
2023-01-22 15:01:36.569896: step: 2052/530, loss: 0.0065493276342749596
2023-01-22 15:01:37.630435: step: 2056/530, loss: 0.004938547033816576
2023-01-22 15:01:38.678550: step: 2060/530, loss: 0.009212430566549301
2023-01-22 15:01:39.746517: step: 2064/530, loss: 0.009946984238922596
2023-01-22 15:01:40.792596: step: 2068/530, loss: 0.01027000229805708
2023-01-22 15:01:41.845189: step: 2072/530, loss: 0.02830147184431553
2023-01-22 15:01:42.912443: step: 2076/530, loss: 0.007420471403747797
2023-01-22 15:01:43.975147: step: 2080/530, loss: 0.003855427959933877
2023-01-22 15:01:45.051753: step: 2084/530, loss: 0.007408120669424534
2023-01-22 15:01:46.112980: step: 2088/530, loss: 0.02598283626139164
2023-01-22 15:01:47.153233: step: 2092/530, loss: 0.035861238837242126
2023-01-22 15:01:48.212476: step: 2096/530, loss: 0.0021612956188619137
2023-01-22 15:01:49.288283: step: 2100/530, loss: 0.005045238416641951
2023-01-22 15:01:50.344647: step: 2104/530, loss: 0.045358043164014816
2023-01-22 15:01:51.406500: step: 2108/530, loss: 0.018878471106290817
2023-01-22 15:01:52.460126: step: 2112/530, loss: 0.02493632212281227
2023-01-22 15:01:53.509553: step: 2116/530, loss: 0.005564841907471418
2023-01-22 15:01:54.587789: step: 2120/530, loss: 0.0032987850718200207
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.322190977261732, 'r': 0.29107025786713286, 'f1': 0.30584098737083815}, 'combined': 0.20389399158055876, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4054079660563421, 'r': 0.31913602864296825, 'f1': 0.3571357687427602}, 'combined': 0.2330780806531698, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31902969426406924, 'r': 0.33900688574550053, 'f1': 0.3287150483677622}, 'combined': 0.24221108827098267, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3612497835096116, 'r': 0.3305982867269779, 'f1': 0.3452450462655149}, 'combined': 0.2289708078859373, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 2}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31902969426406924, 'r': 0.33900688574550053, 'f1': 0.3287150483677622}, 'combined': 0.24221108827098267, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3612497835096116, 'r': 0.3305982867269779, 'f1': 0.3452450462655149}, 'combined': 0.2289708078859373, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, '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 15:04:37.800885: step: 4/530, loss: 0.011037388816475868
2023-01-22 15:04:38.857821: step: 8/530, loss: 0.0033637695014476776
2023-01-22 15:04:39.900837: step: 12/530, loss: 0.008236338384449482
2023-01-22 15:04:40.949883: step: 16/530, loss: 0.015659745782613754
2023-01-22 15:04:41.997004: step: 20/530, loss: 0.004246231634169817
2023-01-22 15:04:43.049159: step: 24/530, loss: 0.04262460768222809
2023-01-22 15:04:44.116336: step: 28/530, loss: 0.015363809652626514
2023-01-22 15:04:45.154775: step: 32/530, loss: 0.005669242236763239
2023-01-22 15:04:46.203502: step: 36/530, loss: 0.008920131251215935
2023-01-22 15:04:47.255348: step: 40/530, loss: 0.00026123650604858994
2023-01-22 15:04:48.310082: step: 44/530, loss: 0.0073133972473442554
2023-01-22 15:04:49.370850: step: 48/530, loss: 0.013548020273447037
2023-01-22 15:04:50.458718: step: 52/530, loss: 0.003861045464873314
2023-01-22 15:04:51.513292: step: 56/530, loss: 0.0004149958258494735
2023-01-22 15:04:52.572069: step: 60/530, loss: 0.0045206788927316666
2023-01-22 15:04:53.635008: step: 64/530, loss: 0.004160593263804913
2023-01-22 15:04:54.687455: step: 68/530, loss: 0.00907068606466055
2023-01-22 15:04:55.755576: step: 72/530, loss: 0.004222220741212368
2023-01-22 15:04:56.830877: step: 76/530, loss: 0.020256709307432175
2023-01-22 15:04:57.888559: step: 80/530, loss: 0.0011152509832754731
2023-01-22 15:04:58.935540: step: 84/530, loss: 0.006435273215174675
2023-01-22 15:05:00.001354: step: 88/530, loss: 0.00909146573394537
2023-01-22 15:05:01.062495: step: 92/530, loss: 0.001261822646483779
2023-01-22 15:05:02.153324: step: 96/530, loss: 0.004590814001858234
2023-01-22 15:05:03.214636: step: 100/530, loss: 0.040884312242269516
2023-01-22 15:05:04.280151: step: 104/530, loss: 0.007825865410268307
2023-01-22 15:05:05.367099: step: 108/530, loss: 0.022045956924557686
2023-01-22 15:05:06.407800: step: 112/530, loss: 0.014647656120359898
2023-01-22 15:05:07.471008: step: 116/530, loss: 0.010261126793920994
2023-01-22 15:05:08.518740: step: 120/530, loss: 0.003943182528018951
2023-01-22 15:05:09.582866: step: 124/530, loss: 0.006213707383722067
2023-01-22 15:05:10.660011: step: 128/530, loss: 0.0036695185117423534
2023-01-22 15:05:11.726783: step: 132/530, loss: 0.0017012088792398572
2023-01-22 15:05:12.785192: step: 136/530, loss: 0.004110084380954504
2023-01-22 15:05:13.826857: step: 140/530, loss: 0.00849941372871399
2023-01-22 15:05:14.880999: step: 144/530, loss: 0.0022331341169774532
2023-01-22 15:05:15.950155: step: 148/530, loss: 0.029051270335912704
2023-01-22 15:05:17.022147: step: 152/530, loss: 0.003926887642592192
2023-01-22 15:05:18.074241: step: 156/530, loss: 0.0014680703170597553
2023-01-22 15:05:19.147420: step: 160/530, loss: 0.022338997572660446
2023-01-22 15:05:20.208530: step: 164/530, loss: 0.009017284028232098
2023-01-22 15:05:21.263779: step: 168/530, loss: 0.020901868119835854
2023-01-22 15:05:22.313616: step: 172/530, loss: 0.007785148452967405
2023-01-22 15:05:23.384422: step: 176/530, loss: 0.003316078335046768
2023-01-22 15:05:24.434957: step: 180/530, loss: 0.02714390866458416
2023-01-22 15:05:25.502244: step: 184/530, loss: 0.003139380132779479
2023-01-22 15:05:26.561590: step: 188/530, loss: 0.015847723931074142
2023-01-22 15:05:27.607139: step: 192/530, loss: 0.004920356906950474
2023-01-22 15:05:28.690287: step: 196/530, loss: 0.002030257834121585
2023-01-22 15:05:29.741534: step: 200/530, loss: 0.005298843141645193
2023-01-22 15:05:30.808403: step: 204/530, loss: 0.001879102666862309
2023-01-22 15:05:31.873648: step: 208/530, loss: 0.008480825461447239
2023-01-22 15:05:32.929447: step: 212/530, loss: 0.01110406406223774
2023-01-22 15:05:33.997972: step: 216/530, loss: 0.014026210643351078
2023-01-22 15:05:35.048024: step: 220/530, loss: 0.020209141075611115
2023-01-22 15:05:36.104012: step: 224/530, loss: 0.003900995245203376
2023-01-22 15:05:37.154819: step: 228/530, loss: 0.008825898170471191
2023-01-22 15:05:38.244343: step: 232/530, loss: 0.019566548988223076
2023-01-22 15:05:39.318041: step: 236/530, loss: 0.011993246152997017
2023-01-22 15:05:40.388820: step: 240/530, loss: 0.0035306632053107023
2023-01-22 15:05:41.449278: step: 244/530, loss: 0.0027248694095760584
2023-01-22 15:05:42.511305: step: 248/530, loss: 0.0
2023-01-22 15:05:43.583269: step: 252/530, loss: 0.03269648551940918
2023-01-22 15:05:44.641315: step: 256/530, loss: 0.0423007607460022
2023-01-22 15:05:45.703206: step: 260/530, loss: 0.002230660989880562
2023-01-22 15:05:46.767248: step: 264/530, loss: 0.003565023886039853
2023-01-22 15:05:47.836765: step: 268/530, loss: 0.003463475266471505
2023-01-22 15:05:48.915939: step: 272/530, loss: 0.03006424941122532
2023-01-22 15:05:49.972429: step: 276/530, loss: 0.0862032026052475
2023-01-22 15:05:51.032321: step: 280/530, loss: 0.008791036903858185
2023-01-22 15:05:52.110402: step: 284/530, loss: 0.015088467858731747
2023-01-22 15:05:53.167633: step: 288/530, loss: 0.010249665006995201
2023-01-22 15:05:54.246293: step: 292/530, loss: 0.003982336260378361
2023-01-22 15:05:55.313234: step: 296/530, loss: 0.0072026741690933704
2023-01-22 15:05:56.388318: step: 300/530, loss: 0.0024888236075639725
2023-01-22 15:05:57.448806: step: 304/530, loss: 0.002039859304204583
2023-01-22 15:05:58.515788: step: 308/530, loss: 0.008997428230941296
2023-01-22 15:05:59.581870: step: 312/530, loss: 0.03330908715724945
2023-01-22 15:06:00.647025: step: 316/530, loss: 0.0025614972691982985
2023-01-22 15:06:01.715978: step: 320/530, loss: 0.011851364746689796
2023-01-22 15:06:02.800194: step: 324/530, loss: 0.00228997808881104
2023-01-22 15:06:03.852774: step: 328/530, loss: 0.005612990818917751
2023-01-22 15:06:04.925340: step: 332/530, loss: 4.688867193181068e-05
2023-01-22 15:06:05.997799: step: 336/530, loss: 0.004641333594918251
2023-01-22 15:06:07.076914: step: 340/530, loss: 0.018352488055825233
2023-01-22 15:06:08.144017: step: 344/530, loss: 0.0033210974652320147
2023-01-22 15:06:09.200792: step: 348/530, loss: 0.0003681909875012934
2023-01-22 15:06:10.270651: step: 352/530, loss: 0.013355430215597153
2023-01-22 15:06:11.334971: step: 356/530, loss: 0.0031212226022034883
2023-01-22 15:06:12.404705: step: 360/530, loss: 0.004224149975925684
2023-01-22 15:06:13.456268: step: 364/530, loss: 0.0008212754619307816
2023-01-22 15:06:14.528060: step: 368/530, loss: 0.0314108207821846
2023-01-22 15:06:15.595359: step: 372/530, loss: 0.013997214846313
2023-01-22 15:06:16.659227: step: 376/530, loss: 0.0045465137809515
2023-01-22 15:06:17.729739: step: 380/530, loss: 0.006799365859478712
2023-01-22 15:06:18.821576: step: 384/530, loss: 0.02998686023056507
2023-01-22 15:06:19.890793: step: 388/530, loss: 0.027556203305721283
2023-01-22 15:06:20.960885: step: 392/530, loss: 0.007255799137055874
2023-01-22 15:06:22.018817: step: 396/530, loss: 0.006641027517616749
2023-01-22 15:06:23.096023: step: 400/530, loss: 0.004792897496372461
2023-01-22 15:06:24.176982: step: 404/530, loss: 0.000260567496297881
2023-01-22 15:06:25.239728: step: 408/530, loss: 0.0021445187740027905
2023-01-22 15:06:26.299076: step: 412/530, loss: 0.0063408794812858105
2023-01-22 15:06:27.371686: step: 416/530, loss: 0.010694291442632675
2023-01-22 15:06:28.431919: step: 420/530, loss: 0.010802110657095909
2023-01-22 15:06:29.493032: step: 424/530, loss: 0.013180532492697239
2023-01-22 15:06:30.549754: step: 428/530, loss: 0.025315187871456146
2023-01-22 15:06:31.623138: step: 432/530, loss: 0.011261899024248123
2023-01-22 15:06:32.686703: step: 436/530, loss: 0.0028815572150051594
2023-01-22 15:06:33.760046: step: 440/530, loss: 0.009346085600554943
2023-01-22 15:06:34.818376: step: 444/530, loss: 0.003573495429009199
2023-01-22 15:06:35.886080: step: 448/530, loss: 0.017670979723334312
2023-01-22 15:06:36.940080: step: 452/530, loss: 0.0010958461789414287
2023-01-22 15:06:38.007045: step: 456/530, loss: 0.00663788104429841
2023-01-22 15:06:39.061794: step: 460/530, loss: 0.0039746398106217384
2023-01-22 15:06:40.135745: step: 464/530, loss: 0.01288523618131876
2023-01-22 15:06:41.196285: step: 468/530, loss: 0.009165334515273571
2023-01-22 15:06:42.263072: step: 472/530, loss: 0.005334069021046162
2023-01-22 15:06:43.336684: step: 476/530, loss: 0.0032492908649146557
2023-01-22 15:06:44.420865: step: 480/530, loss: 0.050877418369054794
2023-01-22 15:06:45.487607: step: 484/530, loss: 0.009450084529817104
2023-01-22 15:06:46.545017: step: 488/530, loss: 0.012341488152742386
2023-01-22 15:06:47.592436: step: 492/530, loss: 0.004724924918264151
2023-01-22 15:06:48.666880: step: 496/530, loss: 0.010934805497527122
2023-01-22 15:06:49.733457: step: 500/530, loss: 0.0072773960418999195
2023-01-22 15:06:50.792149: step: 504/530, loss: 0.010864170268177986
2023-01-22 15:06:51.857213: step: 508/530, loss: 0.0032583444844931364
2023-01-22 15:06:52.919600: step: 512/530, loss: 0.0021338053047657013
2023-01-22 15:06:53.996418: step: 516/530, loss: 0.005343111697584391
2023-01-22 15:06:55.056065: step: 520/530, loss: 0.03936883062124252
2023-01-22 15:06:56.121187: step: 524/530, loss: 0.010429543443024158
2023-01-22 15:06:57.203141: step: 528/530, loss: 0.0032462028320878744
2023-01-22 15:06:58.267428: step: 532/530, loss: 0.01072680577635765
2023-01-22 15:06:59.331661: step: 536/530, loss: 0.0034480090253055096
2023-01-22 15:07:00.379420: step: 540/530, loss: 0.003447337308898568
2023-01-22 15:07:01.448948: step: 544/530, loss: 0.0023496400099247694
2023-01-22 15:07:02.508132: step: 548/530, loss: 0.0031386411283165216
2023-01-22 15:07:03.581169: step: 552/530, loss: 0.03646097704768181
2023-01-22 15:07:04.657512: step: 556/530, loss: 0.007688587531447411
2023-01-22 15:07:05.720532: step: 560/530, loss: 0.02421599067747593
2023-01-22 15:07:06.778373: step: 564/530, loss: 0.015163530595600605
2023-01-22 15:07:07.843298: step: 568/530, loss: 0.0033448932226747274
2023-01-22 15:07:08.925141: step: 572/530, loss: 0.007094004191458225
2023-01-22 15:07:09.991140: step: 576/530, loss: 0.007009049411863089
2023-01-22 15:07:11.067742: step: 580/530, loss: 0.012880155816674232
2023-01-22 15:07:12.124984: step: 584/530, loss: 0.0003849291242659092
2023-01-22 15:07:13.194733: step: 588/530, loss: 0.0022306242026388645
2023-01-22 15:07:14.247769: step: 592/530, loss: 0.01841331645846367
2023-01-22 15:07:15.310559: step: 596/530, loss: 0.009699378162622452
2023-01-22 15:07:16.366600: step: 600/530, loss: 0.03915206342935562
2023-01-22 15:07:17.420485: step: 604/530, loss: 0.007383402436971664
2023-01-22 15:07:18.479268: step: 608/530, loss: 0.04035816714167595
2023-01-22 15:07:19.535866: step: 612/530, loss: 0.004178424831479788
2023-01-22 15:07:20.597415: step: 616/530, loss: 0.00608796114102006
2023-01-22 15:07:21.655231: step: 620/530, loss: 4.822748087462969e-05
2023-01-22 15:07:22.718000: step: 624/530, loss: 0.025153009220957756
2023-01-22 15:07:23.772431: step: 628/530, loss: 0.003475462319329381
2023-01-22 15:07:24.826776: step: 632/530, loss: 0.01671851985156536
2023-01-22 15:07:25.874736: step: 636/530, loss: 0.013008121401071548
2023-01-22 15:07:26.927164: step: 640/530, loss: 0.006886472925543785
2023-01-22 15:07:27.999603: step: 644/530, loss: 0.010398788377642632
2023-01-22 15:07:29.047151: step: 648/530, loss: 0.010683867149055004
2023-01-22 15:07:30.116792: step: 652/530, loss: 0.03578527271747589
2023-01-22 15:07:31.187886: step: 656/530, loss: 0.005705519579350948
2023-01-22 15:07:32.254340: step: 660/530, loss: 0.011778861284255981
2023-01-22 15:07:33.296214: step: 664/530, loss: 0.015576585195958614
2023-01-22 15:07:34.339833: step: 668/530, loss: 0.005611783359199762
2023-01-22 15:07:35.409640: step: 672/530, loss: 0.0058884210884571075
2023-01-22 15:07:36.475665: step: 676/530, loss: 0.005941211711615324
2023-01-22 15:07:37.540769: step: 680/530, loss: 0.0032191656064242125
2023-01-22 15:07:38.617400: step: 684/530, loss: 0.007754352409392595
2023-01-22 15:07:39.681548: step: 688/530, loss: 0.036522481590509415
2023-01-22 15:07:40.744806: step: 692/530, loss: 0.013598271645605564
2023-01-22 15:07:41.810359: step: 696/530, loss: 0.01127624697983265
2023-01-22 15:07:42.869606: step: 700/530, loss: 0.02059212327003479
2023-01-22 15:07:43.940977: step: 704/530, loss: 0.0027184211649000645
2023-01-22 15:07:44.978645: step: 708/530, loss: 0.002099111909046769
2023-01-22 15:07:46.028103: step: 712/530, loss: 0.003149627475067973
2023-01-22 15:07:47.098303: step: 716/530, loss: 0.005665400065481663
2023-01-22 15:07:48.164052: step: 720/530, loss: 0.0025026474613696337
2023-01-22 15:07:49.227476: step: 724/530, loss: 0.006083074491471052
2023-01-22 15:07:50.302471: step: 728/530, loss: 0.016948169097304344
2023-01-22 15:07:51.371362: step: 732/530, loss: 0.003166420152410865
2023-01-22 15:07:52.428306: step: 736/530, loss: 0.02376437559723854
2023-01-22 15:07:53.481774: step: 740/530, loss: 0.0045867301523685455
2023-01-22 15:07:54.532968: step: 744/530, loss: 0.007157029118388891
2023-01-22 15:07:55.609443: step: 748/530, loss: 0.007166692521423101
2023-01-22 15:07:56.669150: step: 752/530, loss: 0.009258009493350983
2023-01-22 15:07:57.719180: step: 756/530, loss: 0.003960905130952597
2023-01-22 15:07:58.776770: step: 760/530, loss: 0.006320791784673929
2023-01-22 15:07:59.827114: step: 764/530, loss: 0.004994504153728485
2023-01-22 15:08:00.879691: step: 768/530, loss: 0.00482734153047204
2023-01-22 15:08:01.946358: step: 772/530, loss: 0.01570260524749756
2023-01-22 15:08:03.005520: step: 776/530, loss: 9.763549314811826e-05
2023-01-22 15:08:04.072251: step: 780/530, loss: 0.0007025782251730561
2023-01-22 15:08:05.134848: step: 784/530, loss: 0.042397499084472656
2023-01-22 15:08:06.197130: step: 788/530, loss: 0.0076088677160441875
2023-01-22 15:08:07.270573: step: 792/530, loss: 0.010872351005673409
2023-01-22 15:08:08.331628: step: 796/530, loss: 0.0024664278607815504
2023-01-22 15:08:09.372306: step: 800/530, loss: 0.0028902709018439054
2023-01-22 15:08:10.418425: step: 804/530, loss: 0.0033354151528328657
2023-01-22 15:08:11.468101: step: 808/530, loss: 0.007622275035828352
2023-01-22 15:08:12.539307: step: 812/530, loss: 0.006796710193157196
2023-01-22 15:08:13.584544: step: 816/530, loss: 0.009624737314879894
2023-01-22 15:08:14.633292: step: 820/530, loss: 0.013294020667672157
2023-01-22 15:08:15.691128: step: 824/530, loss: 0.03378332406282425
2023-01-22 15:08:16.752597: step: 828/530, loss: 0.0011465639108791947
2023-01-22 15:08:17.817237: step: 832/530, loss: 0.012301189824938774
2023-01-22 15:08:18.860872: step: 836/530, loss: 0.009738078340888023
2023-01-22 15:08:19.902024: step: 840/530, loss: 0.0
2023-01-22 15:08:20.968724: step: 844/530, loss: 0.09453134983778
2023-01-22 15:08:22.023441: step: 848/530, loss: 0.002112054266035557
2023-01-22 15:08:23.079856: step: 852/530, loss: 0.012722463347017765
2023-01-22 15:08:24.139762: step: 856/530, loss: 0.0016223612474277616
2023-01-22 15:08:25.192065: step: 860/530, loss: 0.0022139057982712984
2023-01-22 15:08:26.239445: step: 864/530, loss: 0.00583189632743597
2023-01-22 15:08:27.291300: step: 868/530, loss: 0.008090543560683727
2023-01-22 15:08:28.346101: step: 872/530, loss: 0.003102633636444807
2023-01-22 15:08:29.408415: step: 876/530, loss: 0.02183203212916851
2023-01-22 15:08:30.466146: step: 880/530, loss: 0.0050342814065515995
2023-01-22 15:08:31.545704: step: 884/530, loss: 0.014628928154706955
2023-01-22 15:08:32.626816: step: 888/530, loss: 0.000386589381378144
2023-01-22 15:08:33.683446: step: 892/530, loss: 0.00914692785590887
2023-01-22 15:08:34.754484: step: 896/530, loss: 0.013114671222865582
2023-01-22 15:08:35.805020: step: 900/530, loss: 0.005152002442628145
2023-01-22 15:08:36.879971: step: 904/530, loss: 0.003002758137881756
2023-01-22 15:08:37.985429: step: 908/530, loss: 0.006310395430773497
2023-01-22 15:08:39.035874: step: 912/530, loss: 0.005064757075160742
2023-01-22 15:08:40.138542: step: 916/530, loss: 0.010090429335832596
2023-01-22 15:08:41.197034: step: 920/530, loss: 0.012094387784600258
2023-01-22 15:08:42.273538: step: 924/530, loss: 0.005336686968803406
2023-01-22 15:08:43.342248: step: 928/530, loss: 0.016629178076982498
2023-01-22 15:08:44.398252: step: 932/530, loss: 0.06720240414142609
2023-01-22 15:08:45.443250: step: 936/530, loss: 0.005368458107113838
2023-01-22 15:08:46.493245: step: 940/530, loss: 0.012415033765137196
2023-01-22 15:08:47.539529: step: 944/530, loss: 0.005118426866829395
2023-01-22 15:08:48.592672: step: 948/530, loss: 0.0072637032717466354
2023-01-22 15:08:49.649489: step: 952/530, loss: 0.005285314284265041
2023-01-22 15:08:50.712278: step: 956/530, loss: 0.005225133150815964
2023-01-22 15:08:51.783223: step: 960/530, loss: 0.024208493530750275
2023-01-22 15:08:52.835752: step: 964/530, loss: 0.016217226162552834
2023-01-22 15:08:53.924076: step: 968/530, loss: 0.006129337474703789
2023-01-22 15:08:54.984997: step: 972/530, loss: 0.002516029169782996
2023-01-22 15:08:56.058864: step: 976/530, loss: 0.014980847015976906
2023-01-22 15:08:57.133942: step: 980/530, loss: 0.008146249689161777
2023-01-22 15:08:58.200789: step: 984/530, loss: 0.005085770506411791
2023-01-22 15:08:59.279714: step: 988/530, loss: 0.011522888205945492
2023-01-22 15:09:00.339556: step: 992/530, loss: 0.009969355538487434
2023-01-22 15:09:01.397615: step: 996/530, loss: 0.007449327036738396
2023-01-22 15:09:02.447960: step: 1000/530, loss: 0.0039265332743525505
2023-01-22 15:09:03.515381: step: 1004/530, loss: 0.03362823277711868
2023-01-22 15:09:04.568469: step: 1008/530, loss: 0.05037984997034073
2023-01-22 15:09:05.632420: step: 1012/530, loss: 0.0037533349823206663
2023-01-22 15:09:06.690458: step: 1016/530, loss: 0.01805172860622406
2023-01-22 15:09:07.741826: step: 1020/530, loss: 0.04467471316456795
2023-01-22 15:09:08.787218: step: 1024/530, loss: 0.001675801700912416
2023-01-22 15:09:09.847683: step: 1028/530, loss: 0.00896263774484396
2023-01-22 15:09:10.902902: step: 1032/530, loss: 0.01173726748675108
2023-01-22 15:09:11.961829: step: 1036/530, loss: 0.005703124217689037
2023-01-22 15:09:13.022361: step: 1040/530, loss: 0.00407000444829464
2023-01-22 15:09:14.074145: step: 1044/530, loss: 0.020006271079182625
2023-01-22 15:09:15.130061: step: 1048/530, loss: 0.008091367781162262
2023-01-22 15:09:16.178303: step: 1052/530, loss: 0.004765871446579695
2023-01-22 15:09:17.221720: step: 1056/530, loss: 0.006092479918152094
2023-01-22 15:09:18.275768: step: 1060/530, loss: 0.012051582336425781
2023-01-22 15:09:19.328445: step: 1064/530, loss: 0.013594712130725384
2023-01-22 15:09:20.404730: step: 1068/530, loss: 0.013948970474302769
2023-01-22 15:09:21.446271: step: 1072/530, loss: 0.014910435304045677
2023-01-22 15:09:22.514856: step: 1076/530, loss: 0.0058980342000722885
2023-01-22 15:09:23.577751: step: 1080/530, loss: 0.001361884642392397
2023-01-22 15:09:24.636031: step: 1084/530, loss: 0.011824761517345905
2023-01-22 15:09:25.673364: step: 1088/530, loss: 0.0015725716948509216
2023-01-22 15:09:26.731638: step: 1092/530, loss: 0.013768719509243965
2023-01-22 15:09:27.781204: step: 1096/530, loss: 0.014387240633368492
2023-01-22 15:09:28.829217: step: 1100/530, loss: 0.01927429437637329
2023-01-22 15:09:29.874252: step: 1104/530, loss: 0.005005765240639448
2023-01-22 15:09:30.912802: step: 1108/530, loss: 0.003512695897370577
2023-01-22 15:09:31.961540: step: 1112/530, loss: 0.0004614564822986722
2023-01-22 15:09:33.074260: step: 1116/530, loss: 0.011719648726284504
2023-01-22 15:09:34.126606: step: 1120/530, loss: 0.012000378221273422
2023-01-22 15:09:35.183758: step: 1124/530, loss: 0.022113250568509102
2023-01-22 15:09:36.236828: step: 1128/530, loss: 0.005927121266722679
2023-01-22 15:09:37.299438: step: 1132/530, loss: 0.013145627453923225
2023-01-22 15:09:38.358308: step: 1136/530, loss: 0.009920405223965645
2023-01-22 15:09:39.414420: step: 1140/530, loss: 0.0025121313519775867
2023-01-22 15:09:40.477880: step: 1144/530, loss: 0.022408949211239815
2023-01-22 15:09:41.540628: step: 1148/530, loss: 0.009907946921885014
2023-01-22 15:09:42.585739: step: 1152/530, loss: 0.027946049347519875
2023-01-22 15:09:43.645470: step: 1156/530, loss: 0.023580309003591537
2023-01-22 15:09:44.708635: step: 1160/530, loss: 0.007074342574924231
2023-01-22 15:09:45.779045: step: 1164/530, loss: 0.04781348630785942
2023-01-22 15:09:46.834381: step: 1168/530, loss: 0.01629355549812317
2023-01-22 15:09:47.892768: step: 1172/530, loss: 0.024237146601080894
2023-01-22 15:09:48.947878: step: 1176/530, loss: 0.005001645069569349
2023-01-22 15:09:49.988933: step: 1180/530, loss: 0.013264560140669346
2023-01-22 15:09:51.053550: step: 1184/530, loss: 0.00472449092194438
2023-01-22 15:09:52.125794: step: 1188/530, loss: 0.0008861303795129061
2023-01-22 15:09:53.172526: step: 1192/530, loss: 0.0016576367197558284
2023-01-22 15:09:54.229541: step: 1196/530, loss: 0.0021313801407814026
2023-01-22 15:09:55.310067: step: 1200/530, loss: 0.003909954335540533
2023-01-22 15:09:56.367644: step: 1204/530, loss: 0.017153365537524223
2023-01-22 15:09:57.419128: step: 1208/530, loss: 0.00652704294770956
2023-01-22 15:09:58.461227: step: 1212/530, loss: 0.009187408722937107
2023-01-22 15:09:59.526316: step: 1216/530, loss: 0.006367970257997513
2023-01-22 15:10:00.584841: step: 1220/530, loss: 0.00884553138166666
2023-01-22 15:10:01.643317: step: 1224/530, loss: 0.0034300806000828743
2023-01-22 15:10:02.693133: step: 1228/530, loss: 0.004335857927799225
2023-01-22 15:10:03.766032: step: 1232/530, loss: 0.004962536506354809
2023-01-22 15:10:04.828596: step: 1236/530, loss: 0.004654952324926853
2023-01-22 15:10:05.881261: step: 1240/530, loss: 0.00821628700941801
2023-01-22 15:10:06.932082: step: 1244/530, loss: 0.010016443207859993
2023-01-22 15:10:07.986695: step: 1248/530, loss: 0.013293548487126827
2023-01-22 15:10:09.034235: step: 1252/530, loss: 0.0034096897579729557
2023-01-22 15:10:10.117573: step: 1256/530, loss: 0.11217693239450455
2023-01-22 15:10:11.165694: step: 1260/530, loss: 0.0040709488093853
2023-01-22 15:10:12.238961: step: 1264/530, loss: 0.0040858471766114235
2023-01-22 15:10:13.299350: step: 1268/530, loss: 0.0019328842172399163
2023-01-22 15:10:14.349263: step: 1272/530, loss: 0.0063474178314208984
2023-01-22 15:10:15.409680: step: 1276/530, loss: 0.00012823025463148952
2023-01-22 15:10:16.475677: step: 1280/530, loss: 0.009802342392504215
2023-01-22 15:10:17.522160: step: 1284/530, loss: 0.0645652487874031
2023-01-22 15:10:18.575264: step: 1288/530, loss: 0.010666261427104473
2023-01-22 15:10:19.629088: step: 1292/530, loss: 0.005917792208492756
2023-01-22 15:10:20.689626: step: 1296/530, loss: 0.00842365249991417
2023-01-22 15:10:21.743441: step: 1300/530, loss: 0.0009731862228363752
2023-01-22 15:10:22.786011: step: 1304/530, loss: 0.0032120600808411837
2023-01-22 15:10:23.875108: step: 1308/530, loss: 0.03412623330950737
2023-01-22 15:10:24.941797: step: 1312/530, loss: 0.017298497259616852
2023-01-22 15:10:26.015337: step: 1316/530, loss: 0.012309487909078598
2023-01-22 15:10:27.067221: step: 1320/530, loss: 0.002919018268585205
2023-01-22 15:10:28.116306: step: 1324/530, loss: 0.005242897197604179
2023-01-22 15:10:29.177536: step: 1328/530, loss: 0.027444595471024513
2023-01-22 15:10:30.233618: step: 1332/530, loss: 0.0411381721496582
2023-01-22 15:10:31.302712: step: 1336/530, loss: 0.024505717679858208
2023-01-22 15:10:32.355058: step: 1340/530, loss: 0.005025478545576334
2023-01-22 15:10:33.429982: step: 1344/530, loss: 0.038513533771038055
2023-01-22 15:10:34.488491: step: 1348/530, loss: 0.0034771100617945194
2023-01-22 15:10:35.553527: step: 1352/530, loss: 0.018608078360557556
2023-01-22 15:10:36.605627: step: 1356/530, loss: 0.01439326349645853
2023-01-22 15:10:37.654914: step: 1360/530, loss: 0.01232139952480793
2023-01-22 15:10:38.710498: step: 1364/530, loss: 0.009235356003046036
2023-01-22 15:10:39.754641: step: 1368/530, loss: 0.023434307426214218
2023-01-22 15:10:40.824106: step: 1372/530, loss: 0.0028404712211340666
2023-01-22 15:10:41.870504: step: 1376/530, loss: 0.01623358577489853
2023-01-22 15:10:42.917113: step: 1380/530, loss: 0.012981625273823738
2023-01-22 15:10:43.960452: step: 1384/530, loss: 0.006055581849068403
2023-01-22 15:10:45.015953: step: 1388/530, loss: 0.00852600485086441
2023-01-22 15:10:46.084630: step: 1392/530, loss: 0.015775974839925766
2023-01-22 15:10:47.149326: step: 1396/530, loss: 0.002838095184415579
2023-01-22 15:10:48.225908: step: 1400/530, loss: 0.012099510990083218
2023-01-22 15:10:49.299465: step: 1404/530, loss: 0.006254035513848066
2023-01-22 15:10:50.352035: step: 1408/530, loss: 0.003088791389018297
2023-01-22 15:10:51.403686: step: 1412/530, loss: 0.0022640274837613106
2023-01-22 15:10:52.470008: step: 1416/530, loss: 0.004288996569812298
2023-01-22 15:10:53.535858: step: 1420/530, loss: 0.005868943408131599
2023-01-22 15:10:54.584963: step: 1424/530, loss: 0.010310453362762928
2023-01-22 15:10:55.634715: step: 1428/530, loss: 0.04777528718113899
2023-01-22 15:10:56.690222: step: 1432/530, loss: 0.0029129551257938147
2023-01-22 15:10:57.759127: step: 1436/530, loss: 0.004396195523440838
2023-01-22 15:10:58.799349: step: 1440/530, loss: 0.0026751141995191574
2023-01-22 15:10:59.863989: step: 1444/530, loss: 0.002124643651768565
2023-01-22 15:11:00.932398: step: 1448/530, loss: 0.008699733763933182
2023-01-22 15:11:01.987355: step: 1452/530, loss: 0.004703194834291935
2023-01-22 15:11:03.070247: step: 1456/530, loss: 0.0023235317785292864
2023-01-22 15:11:04.127245: step: 1460/530, loss: 0.003502794075757265
2023-01-22 15:11:05.180467: step: 1464/530, loss: 0.002956230426207185
2023-01-22 15:11:06.249132: step: 1468/530, loss: 0.005893892142921686
2023-01-22 15:11:07.322993: step: 1472/530, loss: 0.05266788229346275
2023-01-22 15:11:08.381586: step: 1476/530, loss: 0.018919985741376877
2023-01-22 15:11:09.447777: step: 1480/530, loss: 0.012196439318358898
2023-01-22 15:11:10.512226: step: 1484/530, loss: 0.004680344834923744
2023-01-22 15:11:11.573416: step: 1488/530, loss: 0.007560653146356344
2023-01-22 15:11:12.628049: step: 1492/530, loss: 0.007548678666353226
2023-01-22 15:11:13.679298: step: 1496/530, loss: 0.004957258701324463
2023-01-22 15:11:14.734009: step: 1500/530, loss: 0.00321231409907341
2023-01-22 15:11:15.783562: step: 1504/530, loss: 0.007621142081916332
2023-01-22 15:11:16.869907: step: 1508/530, loss: 0.0048268819227814674
2023-01-22 15:11:17.913334: step: 1512/530, loss: 0.013526175171136856
2023-01-22 15:11:18.980787: step: 1516/530, loss: 0.012672184966504574
2023-01-22 15:11:20.049890: step: 1520/530, loss: 0.00571331474930048
2023-01-22 15:11:21.101962: step: 1524/530, loss: 0.003061615163460374
2023-01-22 15:11:22.155698: step: 1528/530, loss: 0.02636868692934513
2023-01-22 15:11:23.209489: step: 1532/530, loss: 0.01025893073529005
2023-01-22 15:11:24.264365: step: 1536/530, loss: 0.004355986602604389
2023-01-22 15:11:25.329544: step: 1540/530, loss: 0.007915707305073738
2023-01-22 15:11:26.374179: step: 1544/530, loss: 0.006532545667141676
2023-01-22 15:11:27.445186: step: 1548/530, loss: 0.01847263239324093
2023-01-22 15:11:28.505997: step: 1552/530, loss: 0.003102448768913746
2023-01-22 15:11:29.563568: step: 1556/530, loss: 0.06924397498369217
2023-01-22 15:11:30.628671: step: 1560/530, loss: 0.00920573715120554
2023-01-22 15:11:31.687279: step: 1564/530, loss: 0.0028577041812241077
2023-01-22 15:11:32.748158: step: 1568/530, loss: 0.026675723493099213
2023-01-22 15:11:33.799315: step: 1572/530, loss: 0.013881134800612926
2023-01-22 15:11:34.855927: step: 1576/530, loss: 0.004702684469521046
2023-01-22 15:11:35.900707: step: 1580/530, loss: 0.013468734920024872
2023-01-22 15:11:36.968045: step: 1584/530, loss: 0.04919878765940666
2023-01-22 15:11:38.037645: step: 1588/530, loss: 0.052308760583400726
2023-01-22 15:11:39.103086: step: 1592/530, loss: 0.004034318961203098
2023-01-22 15:11:40.158040: step: 1596/530, loss: 0.011949100531637669
2023-01-22 15:11:41.216921: step: 1600/530, loss: 0.015437108464539051
2023-01-22 15:11:42.287790: step: 1604/530, loss: 0.0021641866769641638
2023-01-22 15:11:43.349374: step: 1608/530, loss: 0.012281359173357487
2023-01-22 15:11:44.409428: step: 1612/530, loss: 0.00956805795431137
2023-01-22 15:11:45.470535: step: 1616/530, loss: 0.00560244033113122
2023-01-22 15:11:46.517369: step: 1620/530, loss: 0.005779684521257877
2023-01-22 15:11:47.568241: step: 1624/530, loss: 0.01142224669456482
2023-01-22 15:11:48.641994: step: 1628/530, loss: 0.02249796688556671
2023-01-22 15:11:49.692319: step: 1632/530, loss: 0.017319761216640472
2023-01-22 15:11:50.741132: step: 1636/530, loss: 0.005452349316328764
2023-01-22 15:11:51.801962: step: 1640/530, loss: 0.02802310697734356
2023-01-22 15:11:52.842367: step: 1644/530, loss: 0.010926993563771248
2023-01-22 15:11:53.913853: step: 1648/530, loss: 0.009614617563784122
2023-01-22 15:11:54.970153: step: 1652/530, loss: 0.0312640517950058
2023-01-22 15:11:56.020984: step: 1656/530, loss: 0.011161825619637966
2023-01-22 15:11:57.088328: step: 1660/530, loss: 0.010059613734483719
2023-01-22 15:11:58.144455: step: 1664/530, loss: 0.00916595570743084
2023-01-22 15:11:59.214634: step: 1668/530, loss: 0.0011666493955999613
2023-01-22 15:12:00.255123: step: 1672/530, loss: 0.018669545650482178
2023-01-22 15:12:01.318242: step: 1676/530, loss: 0.024517547339200974
2023-01-22 15:12:02.403125: step: 1680/530, loss: 0.009119664318859577
2023-01-22 15:12:03.447083: step: 1684/530, loss: 0.002078716177493334
2023-01-22 15:12:04.507719: step: 1688/530, loss: 0.004737490322440863
2023-01-22 15:12:05.556232: step: 1692/530, loss: 0.0035940019879490137
2023-01-22 15:12:06.616869: step: 1696/530, loss: 0.006481850519776344
2023-01-22 15:12:07.681488: step: 1700/530, loss: 0.0066940574906766415
2023-01-22 15:12:08.733264: step: 1704/530, loss: 0.0036061364226043224
2023-01-22 15:12:09.785751: step: 1708/530, loss: 0.005528014153242111
2023-01-22 15:12:10.840505: step: 1712/530, loss: 0.000989230116829276
2023-01-22 15:12:11.903086: step: 1716/530, loss: 0.0024887125473469496
2023-01-22 15:12:12.962525: step: 1720/530, loss: 0.00038045382825657725
2023-01-22 15:12:14.015226: step: 1724/530, loss: 0.005280985962599516
2023-01-22 15:12:15.072007: step: 1728/530, loss: 0.04039860516786575
2023-01-22 15:12:16.142318: step: 1732/530, loss: 0.003629072802141309
2023-01-22 15:12:17.187961: step: 1736/530, loss: 0.045726411044597626
2023-01-22 15:12:18.251378: step: 1740/530, loss: 0.012084231711924076
2023-01-22 15:12:19.310019: step: 1744/530, loss: 0.0011039696400985122
2023-01-22 15:12:20.367175: step: 1748/530, loss: 0.003871541703119874
2023-01-22 15:12:21.427113: step: 1752/530, loss: 0.007040179800242186
2023-01-22 15:12:22.502555: step: 1756/530, loss: 0.003478290745988488
2023-01-22 15:12:23.580023: step: 1760/530, loss: 0.0040003955364227295
2023-01-22 15:12:24.644835: step: 1764/530, loss: 0.004138328600674868
2023-01-22 15:12:25.713979: step: 1768/530, loss: 0.021170681342482567
2023-01-22 15:12:26.792843: step: 1772/530, loss: 0.016243066638708115
2023-01-22 15:12:27.868173: step: 1776/530, loss: 0.004305277951061726
2023-01-22 15:12:28.932151: step: 1780/530, loss: 0.014048103243112564
2023-01-22 15:12:29.996153: step: 1784/530, loss: 0.0247513260692358
2023-01-22 15:12:31.058990: step: 1788/530, loss: 0.003777140751481056
2023-01-22 15:12:32.153077: step: 1792/530, loss: 0.04273241013288498
2023-01-22 15:12:33.216868: step: 1796/530, loss: 0.00622946210205555
2023-01-22 15:12:34.277578: step: 1800/530, loss: 0.01790163852274418
2023-01-22 15:12:35.359121: step: 1804/530, loss: 0.014463473111391068
2023-01-22 15:12:36.421883: step: 1808/530, loss: 0.0037626056000590324
2023-01-22 15:12:37.482249: step: 1812/530, loss: 0.00474170595407486
2023-01-22 15:12:38.533251: step: 1816/530, loss: 0.0031185441184788942
2023-01-22 15:12:39.600720: step: 1820/530, loss: 0.04505028575658798
2023-01-22 15:12:40.653007: step: 1824/530, loss: 0.01430468074977398
2023-01-22 15:12:41.715202: step: 1828/530, loss: 0.005075530149042606
2023-01-22 15:12:42.789848: step: 1832/530, loss: 0.009478818625211716
2023-01-22 15:12:43.840433: step: 1836/530, loss: 0.009214231744408607
2023-01-22 15:12:44.900278: step: 1840/530, loss: 0.00033458220423199236
2023-01-22 15:12:45.959457: step: 1844/530, loss: 0.06962233036756516
2023-01-22 15:12:47.020191: step: 1848/530, loss: 0.010475759394466877
2023-01-22 15:12:48.076565: step: 1852/530, loss: 0.05261128395795822
2023-01-22 15:12:49.122096: step: 1856/530, loss: 0.006615791469812393
2023-01-22 15:12:50.199665: step: 1860/530, loss: 0.03412812575697899
2023-01-22 15:12:51.255685: step: 1864/530, loss: 0.007931055501103401
2023-01-22 15:12:52.317166: step: 1868/530, loss: 0.006649984046816826
2023-01-22 15:12:53.380583: step: 1872/530, loss: 0.06735583394765854
2023-01-22 15:12:54.432739: step: 1876/530, loss: 0.014200116507709026
2023-01-22 15:12:55.484191: step: 1880/530, loss: 0.018247291445732117
2023-01-22 15:12:56.539369: step: 1884/530, loss: 0.010077846236526966
2023-01-22 15:12:57.599864: step: 1888/530, loss: 0.052197154611349106
2023-01-22 15:12:58.644915: step: 1892/530, loss: 0.005303631071001291
2023-01-22 15:12:59.686496: step: 1896/530, loss: 0.002336485544219613
2023-01-22 15:13:00.730262: step: 1900/530, loss: 0.028202222660183907
2023-01-22 15:13:01.789737: step: 1904/530, loss: 0.02427256479859352
2023-01-22 15:13:02.847479: step: 1908/530, loss: 0.008046003989875317
2023-01-22 15:13:03.903843: step: 1912/530, loss: 0.012446272186934948
2023-01-22 15:13:04.972743: step: 1916/530, loss: 0.0050819870084524155
2023-01-22 15:13:06.047411: step: 1920/530, loss: 0.00651470897719264
2023-01-22 15:13:07.119013: step: 1924/530, loss: 0.0051939948461949825
2023-01-22 15:13:08.181373: step: 1928/530, loss: 0.008553149178624153
2023-01-22 15:13:09.243607: step: 1932/530, loss: 0.011007853783667088
2023-01-22 15:13:10.276162: step: 1936/530, loss: 0.011660592630505562
2023-01-22 15:13:11.332213: step: 1940/530, loss: 0.004830527119338512
2023-01-22 15:13:12.403561: step: 1944/530, loss: 0.007369286846369505
2023-01-22 15:13:13.453980: step: 1948/530, loss: 0.0076780496165156364
2023-01-22 15:13:14.511024: step: 1952/530, loss: 0.0041919369250535965
2023-01-22 15:13:15.581060: step: 1956/530, loss: 0.07779137045145035
2023-01-22 15:13:16.666977: step: 1960/530, loss: 0.02050156518816948
2023-01-22 15:13:17.723936: step: 1964/530, loss: 0.007081665098667145
2023-01-22 15:13:18.772250: step: 1968/530, loss: 0.0021032914519309998
2023-01-22 15:13:19.826914: step: 1972/530, loss: 0.009371479973196983
2023-01-22 15:13:20.869236: step: 1976/530, loss: 0.0004164410347584635
2023-01-22 15:13:21.927564: step: 1980/530, loss: 0.00537485396489501
2023-01-22 15:13:22.990081: step: 1984/530, loss: 0.01088883075863123
2023-01-22 15:13:24.042540: step: 1988/530, loss: 0.006430459674447775
2023-01-22 15:13:25.101985: step: 1992/530, loss: 0.007853731513023376
2023-01-22 15:13:26.169691: step: 1996/530, loss: 0.011508864350616932
2023-01-22 15:13:27.220567: step: 2000/530, loss: 0.05309774726629257
2023-01-22 15:13:28.265484: step: 2004/530, loss: 0.030090630054473877
2023-01-22 15:13:29.353556: step: 2008/530, loss: 0.008893055841326714
2023-01-22 15:13:30.413573: step: 2012/530, loss: 0.06681640446186066
2023-01-22 15:13:31.463391: step: 2016/530, loss: 0.0010769636137410998
2023-01-22 15:13:32.551878: step: 2020/530, loss: 0.0020682504400610924
2023-01-22 15:13:33.608334: step: 2024/530, loss: 0.002563395304605365
2023-01-22 15:13:34.682712: step: 2028/530, loss: 0.006997863296419382
2023-01-22 15:13:35.740809: step: 2032/530, loss: 0.05591948702931404
2023-01-22 15:13:36.815371: step: 2036/530, loss: 0.03244248032569885
2023-01-22 15:13:37.857550: step: 2040/530, loss: 0.001269844244234264
2023-01-22 15:13:38.905161: step: 2044/530, loss: 0.0016195080243051052
2023-01-22 15:13:39.936573: step: 2048/530, loss: 0.0018853244837373495
2023-01-22 15:13:40.988870: step: 2052/530, loss: 0.028843555599451065
2023-01-22 15:13:42.051907: step: 2056/530, loss: 0.06822147965431213
2023-01-22 15:13:43.103836: step: 2060/530, loss: 0.0009727854048833251
2023-01-22 15:13:44.151231: step: 2064/530, loss: 0.011867367662489414
2023-01-22 15:13:45.217847: step: 2068/530, loss: 0.005429359618574381
2023-01-22 15:13:46.293997: step: 2072/530, loss: 0.002079221187159419
2023-01-22 15:13:47.347396: step: 2076/530, loss: 0.05388302728533745
2023-01-22 15:13:48.391621: step: 2080/530, loss: 0.000665469968225807
2023-01-22 15:13:49.443460: step: 2084/530, loss: 0.00513417599722743
2023-01-22 15:13:50.496397: step: 2088/530, loss: 0.008952285163104534
2023-01-22 15:13:51.556456: step: 2092/530, loss: 0.07183483988046646
2023-01-22 15:13:52.612956: step: 2096/530, loss: 0.0047781262546777725
2023-01-22 15:13:53.654006: step: 2100/530, loss: 0.00354943354614079
2023-01-22 15:13:54.707425: step: 2104/530, loss: 0.011749199591577053
2023-01-22 15:13:55.774509: step: 2108/530, loss: 0.014387881383299828
2023-01-22 15:13:56.826375: step: 2112/530, loss: 0.004152303095906973
2023-01-22 15:13:57.882555: step: 2116/530, loss: 0.009463369846343994
2023-01-22 15:13:58.938555: step: 2120/530, loss: 0.0057126665487885475
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3648559392552528, 'r': 0.2893923768665952, 'f1': 0.32277202668507016}, 'combined': 0.23783201966268325, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35682442404312675, 'r': 0.2335578048282284, 'f1': 0.28232262122093543}, 'combined': 0.18723987314134574, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32144251314924394, 'r': 0.2849149548368298, 'f1': 0.3020785063330244}, 'combined': 0.20138567088868292, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40195502109411846, 'r': 0.3150270321031759, 'f1': 0.35322138614090337}, 'combined': 0.23052343095511585, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.36237373737373735, 'r': 0.3416666666666666, 'f1': 0.3517156862745098}, 'combined': 0.2344771241830065, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, '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': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, '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 15:16:31.776869: step: 4/530, loss: 0.006242005620151758
2023-01-22 15:16:32.836721: step: 8/530, loss: 0.008245788514614105
2023-01-22 15:16:33.894301: step: 12/530, loss: 0.020505303516983986
2023-01-22 15:16:34.939401: step: 16/530, loss: 0.012723291292786598
2023-01-22 15:16:35.991873: step: 20/530, loss: 0.006476703565567732
2023-01-22 15:16:37.056977: step: 24/530, loss: 0.005096540320664644
2023-01-22 15:16:38.116506: step: 28/530, loss: 0.005278478842228651
2023-01-22 15:16:39.171038: step: 32/530, loss: 0.008071999065577984
2023-01-22 15:16:40.217400: step: 36/530, loss: 0.011847801506519318
2023-01-22 15:16:41.280606: step: 40/530, loss: 0.037519242614507675
2023-01-22 15:16:42.334429: step: 44/530, loss: 0.003702266840264201
2023-01-22 15:16:43.401249: step: 48/530, loss: 0.0025951655115932226
2023-01-22 15:16:44.444662: step: 52/530, loss: 0.028691096231341362
2023-01-22 15:16:45.483344: step: 56/530, loss: 0.004881665110588074
2023-01-22 15:16:46.524133: step: 60/530, loss: 0.023504680022597313
2023-01-22 15:16:47.571365: step: 64/530, loss: 0.033218350261449814
2023-01-22 15:16:48.626747: step: 68/530, loss: 0.02339085564017296
2023-01-22 15:16:49.663914: step: 72/530, loss: 0.005363741889595985
2023-01-22 15:16:50.715871: step: 76/530, loss: 0.01806650124490261
2023-01-22 15:16:51.776574: step: 80/530, loss: 0.007291574031114578
2023-01-22 15:16:52.825395: step: 84/530, loss: 0.000939376070164144
2023-01-22 15:16:53.875531: step: 88/530, loss: 0.00256658298894763
2023-01-22 15:16:54.928578: step: 92/530, loss: 0.0036157474387437105
2023-01-22 15:16:55.983405: step: 96/530, loss: 0.0009154801955446601
2023-01-22 15:16:57.060394: step: 100/530, loss: 0.012248910032212734
2023-01-22 15:16:58.116909: step: 104/530, loss: 0.006855723913758993
2023-01-22 15:16:59.157256: step: 108/530, loss: 0.017865311354398727
2023-01-22 15:17:00.215861: step: 112/530, loss: 0.01491771824657917
2023-01-22 15:17:01.265753: step: 116/530, loss: 0.004171750042587519
2023-01-22 15:17:02.325735: step: 120/530, loss: 0.020960237830877304
2023-01-22 15:17:03.393093: step: 124/530, loss: 0.008451152592897415
2023-01-22 15:17:04.456495: step: 128/530, loss: 0.12183654308319092
2023-01-22 15:17:05.532392: step: 132/530, loss: 0.0005778635386377573
2023-01-22 15:17:06.589248: step: 136/530, loss: 0.017487315461039543
2023-01-22 15:17:07.649543: step: 140/530, loss: 0.019294297322630882
2023-01-22 15:17:08.709920: step: 144/530, loss: 0.0061052716337144375
2023-01-22 15:17:09.774887: step: 148/530, loss: 0.007047742605209351
2023-01-22 15:17:10.844795: step: 152/530, loss: 0.010840174742043018
2023-01-22 15:17:11.892937: step: 156/530, loss: 0.006134039256721735
2023-01-22 15:17:12.947515: step: 160/530, loss: 0.03142046555876732
2023-01-22 15:17:14.005397: step: 164/530, loss: 0.026667138561606407
2023-01-22 15:17:15.066929: step: 168/530, loss: 0.012985733337700367
2023-01-22 15:17:16.131746: step: 172/530, loss: 0.0085452850908041
2023-01-22 15:17:17.185118: step: 176/530, loss: 0.001029927283525467
2023-01-22 15:17:18.239187: step: 180/530, loss: 0.002813845407217741
2023-01-22 15:17:19.299834: step: 184/530, loss: 0.0048736161552369595
2023-01-22 15:17:20.357284: step: 188/530, loss: 0.006364193744957447
2023-01-22 15:17:21.416993: step: 192/530, loss: 0.004597123712301254
2023-01-22 15:17:22.474740: step: 196/530, loss: 0.00558228325098753
2023-01-22 15:17:23.528642: step: 200/530, loss: 0.028867751359939575
2023-01-22 15:17:24.593836: step: 204/530, loss: 0.011359620839357376
2023-01-22 15:17:25.662616: step: 208/530, loss: 0.01429405901581049
2023-01-22 15:17:26.715654: step: 212/530, loss: 0.001351762330159545
2023-01-22 15:17:27.791626: step: 216/530, loss: 0.006379213649779558
2023-01-22 15:17:28.851324: step: 220/530, loss: 0.004810844082385302
2023-01-22 15:17:29.912736: step: 224/530, loss: 0.0009049431537277997
2023-01-22 15:17:30.988814: step: 228/530, loss: 0.009955755434930325
2023-01-22 15:17:32.042906: step: 232/530, loss: 0.00444530975073576
2023-01-22 15:17:33.133735: step: 236/530, loss: 0.008952903561294079
2023-01-22 15:17:34.198513: step: 240/530, loss: 0.029141144827008247
2023-01-22 15:17:35.259458: step: 244/530, loss: 0.010878726840019226
2023-01-22 15:17:36.348094: step: 248/530, loss: 0.0283419918268919
2023-01-22 15:17:37.418886: step: 252/530, loss: 0.010638169944286346
2023-01-22 15:17:38.486926: step: 256/530, loss: 0.0236524548381567
2023-01-22 15:17:39.541723: step: 260/530, loss: 0.012847517617046833
2023-01-22 15:17:40.609281: step: 264/530, loss: 0.007505145389586687
2023-01-22 15:17:41.689178: step: 268/530, loss: 0.006469777785241604
2023-01-22 15:17:42.749985: step: 272/530, loss: 0.0013294623931869864
2023-01-22 15:17:43.817221: step: 276/530, loss: 0.02256803959608078
2023-01-22 15:17:44.889502: step: 280/530, loss: 0.05706414952874184
2023-01-22 15:17:45.969128: step: 284/530, loss: 0.05866808071732521
2023-01-22 15:17:47.051950: step: 288/530, loss: 0.006458036135882139
2023-01-22 15:17:48.104078: step: 292/530, loss: 0.009204602800309658
2023-01-22 15:17:49.165656: step: 296/530, loss: 0.0023934594355523586
2023-01-22 15:17:50.220381: step: 300/530, loss: 0.0013017728924751282
2023-01-22 15:17:51.291119: step: 304/530, loss: 0.034436073154211044
2023-01-22 15:17:52.371805: step: 308/530, loss: 0.008031786419451237
2023-01-22 15:17:53.442118: step: 312/530, loss: 0.009900466538965702
2023-01-22 15:17:54.500514: step: 316/530, loss: 0.02373206615447998
2023-01-22 15:17:55.584174: step: 320/530, loss: 0.005910777486860752
2023-01-22 15:17:56.644435: step: 324/530, loss: 0.0029667767230421305
2023-01-22 15:17:57.691374: step: 328/530, loss: 0.015294224955141544
2023-01-22 15:17:58.754048: step: 332/530, loss: 0.005187895614653826
2023-01-22 15:17:59.835861: step: 336/530, loss: 0.0024590082466602325
2023-01-22 15:18:00.892245: step: 340/530, loss: 0.003060111775994301
2023-01-22 15:18:01.952860: step: 344/530, loss: 0.014445329084992409
2023-01-22 15:18:03.050369: step: 348/530, loss: 0.011925291270017624
2023-01-22 15:18:04.099994: step: 352/530, loss: 0.004153455141931772
2023-01-22 15:18:05.154020: step: 356/530, loss: 0.014013927429914474
2023-01-22 15:18:06.217950: step: 360/530, loss: 0.003234388306736946
2023-01-22 15:18:07.288278: step: 364/530, loss: 0.01944483071565628
2023-01-22 15:18:08.363760: step: 368/530, loss: 0.005889624822884798
2023-01-22 15:18:09.414995: step: 372/530, loss: 0.0011207029456272721
2023-01-22 15:18:10.484996: step: 376/530, loss: 0.00833882112056017
2023-01-22 15:18:11.557042: step: 380/530, loss: 0.014100892469286919
2023-01-22 15:18:12.616195: step: 384/530, loss: 0.0016534379683434963
2023-01-22 15:18:13.672557: step: 388/530, loss: 0.027605213224887848
2023-01-22 15:18:14.724390: step: 392/530, loss: 0.008122763596475124
2023-01-22 15:18:15.779580: step: 396/530, loss: 0.009683061391115189
2023-01-22 15:18:16.844877: step: 400/530, loss: 0.007796324789524078
2023-01-22 15:18:17.917598: step: 404/530, loss: 0.007705798372626305
2023-01-22 15:18:18.983113: step: 408/530, loss: 0.025324424728751183
2023-01-22 15:18:20.046490: step: 412/530, loss: 0.008328518830239773
2023-01-22 15:18:21.099562: step: 416/530, loss: 0.00972798652946949
2023-01-22 15:18:22.162933: step: 420/530, loss: 0.027181345969438553
2023-01-22 15:18:23.246169: step: 424/530, loss: 0.005988021846860647
2023-01-22 15:18:24.309250: step: 428/530, loss: 0.004521721042692661
2023-01-22 15:18:25.374898: step: 432/530, loss: 0.019364219158887863
2023-01-22 15:18:26.435155: step: 436/530, loss: 0.016134416684508324
2023-01-22 15:18:27.505221: step: 440/530, loss: 0.012655304744839668
2023-01-22 15:18:28.573588: step: 444/530, loss: 0.006167694926261902
2023-01-22 15:18:29.630999: step: 448/530, loss: 0.002977717434987426
2023-01-22 15:18:30.695527: step: 452/530, loss: 0.0
2023-01-22 15:18:31.762530: step: 456/530, loss: 0.004797186236828566
2023-01-22 15:18:32.839182: step: 460/530, loss: 0.0030766879208385944
2023-01-22 15:18:33.898452: step: 464/530, loss: 0.009997088462114334
2023-01-22 15:18:34.961649: step: 468/530, loss: 0.005181621294468641
2023-01-22 15:18:36.029199: step: 472/530, loss: 0.01957887038588524
2023-01-22 15:18:37.098773: step: 476/530, loss: 0.0034870256204158068
2023-01-22 15:18:38.175631: step: 480/530, loss: 0.007872162386775017
2023-01-22 15:18:39.248930: step: 484/530, loss: 0.013051114045083523
2023-01-22 15:18:40.305198: step: 488/530, loss: 0.0017560621490702033
2023-01-22 15:18:41.380263: step: 492/530, loss: 0.006403603125363588
2023-01-22 15:18:42.441230: step: 496/530, loss: 0.013495389372110367
2023-01-22 15:18:43.521103: step: 500/530, loss: 0.006978723220527172
2023-01-22 15:18:44.560679: step: 504/530, loss: 0.0043045454658567905
2023-01-22 15:18:45.632130: step: 508/530, loss: 0.004011874552816153
2023-01-22 15:18:46.701231: step: 512/530, loss: 0.006005128845572472
2023-01-22 15:18:47.744985: step: 516/530, loss: 0.012899733148515224
2023-01-22 15:18:48.825708: step: 520/530, loss: 0.014143591746687889
2023-01-22 15:18:49.892597: step: 524/530, loss: 0.0012672512093558908
2023-01-22 15:18:50.954200: step: 528/530, loss: 0.013819774612784386
2023-01-22 15:18:52.002961: step: 532/530, loss: 0.0007218388491310179
2023-01-22 15:18:53.075686: step: 536/530, loss: 0.0054780421778559685
2023-01-22 15:18:54.125402: step: 540/530, loss: 0.00671600503847003
2023-01-22 15:18:55.206256: step: 544/530, loss: 0.03400363028049469
2023-01-22 15:18:56.273047: step: 548/530, loss: 0.0061050113290548325
2023-01-22 15:18:57.338632: step: 552/530, loss: 0.005579057149589062
2023-01-22 15:18:58.403103: step: 556/530, loss: 0.007945558056235313
2023-01-22 15:18:59.466964: step: 560/530, loss: 0.004668138921260834
2023-01-22 15:19:00.515912: step: 564/530, loss: 0.0
2023-01-22 15:19:01.581712: step: 568/530, loss: 0.004641253035515547
2023-01-22 15:19:02.643495: step: 572/530, loss: 0.026194512844085693
2023-01-22 15:19:03.706907: step: 576/530, loss: 0.001386706717312336
2023-01-22 15:19:04.778764: step: 580/530, loss: 0.001689742668531835
2023-01-22 15:19:05.861201: step: 584/530, loss: 0.009312448091804981
2023-01-22 15:19:06.932026: step: 588/530, loss: 0.019898012280464172
2023-01-22 15:19:08.007808: step: 592/530, loss: 0.005733053665608168
2023-01-22 15:19:09.069487: step: 596/530, loss: 0.022558318451046944
2023-01-22 15:19:10.142775: step: 600/530, loss: 0.00781612005084753
2023-01-22 15:19:11.216635: step: 604/530, loss: 0.004504181910306215
2023-01-22 15:19:12.256793: step: 608/530, loss: 0.0025639899540692568
2023-01-22 15:19:13.314879: step: 612/530, loss: 0.006530654616653919
2023-01-22 15:19:14.392910: step: 616/530, loss: 0.005104152951389551
2023-01-22 15:19:15.476317: step: 620/530, loss: 0.023183520883321762
2023-01-22 15:19:16.524964: step: 624/530, loss: 0.005528166890144348
2023-01-22 15:19:17.608206: step: 628/530, loss: 0.010733848437666893
2023-01-22 15:19:18.663638: step: 632/530, loss: 0.008726513013243675
2023-01-22 15:19:19.711625: step: 636/530, loss: 0.016137996688485146
2023-01-22 15:19:20.775130: step: 640/530, loss: 0.018039697781205177
2023-01-22 15:19:21.827618: step: 644/530, loss: 0.015495195053517818
2023-01-22 15:19:22.883865: step: 648/530, loss: 0.005310748238116503
2023-01-22 15:19:23.950205: step: 652/530, loss: 0.0043844678439199924
2023-01-22 15:19:24.992221: step: 656/530, loss: 0.002531700534746051
2023-01-22 15:19:26.062256: step: 660/530, loss: 0.013699260540306568
2023-01-22 15:19:27.132550: step: 664/530, loss: 0.009461941197514534
2023-01-22 15:19:28.202990: step: 668/530, loss: 0.009556401520967484
2023-01-22 15:19:29.256768: step: 672/530, loss: 0.003004271537065506
2023-01-22 15:19:30.327788: step: 676/530, loss: 0.0029664342291653156
2023-01-22 15:19:31.388606: step: 680/530, loss: 0.011705353856086731
2023-01-22 15:19:32.445437: step: 684/530, loss: 0.007695301435887814
2023-01-22 15:19:33.517303: step: 688/530, loss: 0.02052067220211029
2023-01-22 15:19:34.588275: step: 692/530, loss: 0.005934314336627722
2023-01-22 15:19:35.644305: step: 696/530, loss: 0.01766117289662361
2023-01-22 15:19:36.700938: step: 700/530, loss: 0.02639213763177395
2023-01-22 15:19:37.748514: step: 704/530, loss: 0.0032621584832668304
2023-01-22 15:19:38.807611: step: 708/530, loss: 0.004292854107916355
2023-01-22 15:19:39.877723: step: 712/530, loss: 0.00577222416177392
2023-01-22 15:19:40.942287: step: 716/530, loss: 0.004950164817273617
2023-01-22 15:19:42.006003: step: 720/530, loss: 0.0
2023-01-22 15:19:43.076795: step: 724/530, loss: 0.032266657799482346
2023-01-22 15:19:44.152345: step: 728/530, loss: 0.014548217877745628
2023-01-22 15:19:45.234562: step: 732/530, loss: 0.0009167836396954954
2023-01-22 15:19:46.300870: step: 736/530, loss: 0.017958497628569603
2023-01-22 15:19:47.353131: step: 740/530, loss: 0.04028197005391121
2023-01-22 15:19:48.425094: step: 744/530, loss: 0.003354680724442005
2023-01-22 15:19:49.505297: step: 748/530, loss: 0.0012453513918444514
2023-01-22 15:19:50.558115: step: 752/530, loss: 0.016027182340621948
2023-01-22 15:19:51.634586: step: 756/530, loss: 0.008633469231426716
2023-01-22 15:19:52.701716: step: 760/530, loss: 0.0021633554715663195
2023-01-22 15:19:53.746220: step: 764/530, loss: 0.0004952848539687693
2023-01-22 15:19:54.805639: step: 768/530, loss: 0.007033390458673239
2023-01-22 15:19:55.843067: step: 772/530, loss: 0.0005101479473523796
2023-01-22 15:19:56.912106: step: 776/530, loss: 0.03941182792186737
2023-01-22 15:19:57.986048: step: 780/530, loss: 0.003551010973751545
2023-01-22 15:19:59.053668: step: 784/530, loss: 0.05433085933327675
2023-01-22 15:20:00.102832: step: 788/530, loss: 0.011746729724109173
2023-01-22 15:20:01.181345: step: 792/530, loss: 0.006218962837010622
2023-01-22 15:20:02.238690: step: 796/530, loss: 0.010618261992931366
2023-01-22 15:20:03.296206: step: 800/530, loss: 0.010474246926605701
2023-01-22 15:20:04.353982: step: 804/530, loss: 0.007073442917317152
2023-01-22 15:20:05.428523: step: 808/530, loss: 0.006373879034072161
2023-01-22 15:20:06.473558: step: 812/530, loss: 0.013071115128695965
2023-01-22 15:20:07.533083: step: 816/530, loss: 0.015331631526350975
2023-01-22 15:20:08.577930: step: 820/530, loss: 0.013652443885803223
2023-01-22 15:20:09.644585: step: 824/530, loss: 0.014215467497706413
2023-01-22 15:20:10.721108: step: 828/530, loss: 0.0013818696606904268
2023-01-22 15:20:11.782697: step: 832/530, loss: 0.04369104653596878
2023-01-22 15:20:12.841786: step: 836/530, loss: 0.008813643828034401
2023-01-22 15:20:13.918081: step: 840/530, loss: 0.004462223034352064
2023-01-22 15:20:14.980096: step: 844/530, loss: 0.005348137114197016
2023-01-22 15:20:16.042502: step: 848/530, loss: 0.0015604892978444695
2023-01-22 15:20:17.102547: step: 852/530, loss: 0.0038257630076259375
2023-01-22 15:20:18.158045: step: 856/530, loss: 0.004403373692184687
2023-01-22 15:20:19.228323: step: 860/530, loss: 0.02417404018342495
2023-01-22 15:20:20.304726: step: 864/530, loss: 0.007416969630867243
2023-01-22 15:20:21.372722: step: 868/530, loss: 0.011917450465261936
2023-01-22 15:20:22.448392: step: 872/530, loss: 0.010866710916161537
2023-01-22 15:20:23.506497: step: 876/530, loss: 0.02389059029519558
2023-01-22 15:20:24.570852: step: 880/530, loss: 0.004505249205976725
2023-01-22 15:20:25.632981: step: 884/530, loss: 0.0030617699958384037
2023-01-22 15:20:26.694338: step: 888/530, loss: 0.026835212484002113
2023-01-22 15:20:27.743233: step: 892/530, loss: 0.008420026861131191
2023-01-22 15:20:28.801202: step: 896/530, loss: 0.0017731849802657962
2023-01-22 15:20:29.848177: step: 900/530, loss: 0.015313559211790562
2023-01-22 15:20:30.916123: step: 904/530, loss: 0.00431819399818778
2023-01-22 15:20:31.967300: step: 908/530, loss: 0.014738948084414005
2023-01-22 15:20:33.062126: step: 912/530, loss: 0.004687153734266758
2023-01-22 15:20:34.129753: step: 916/530, loss: 0.007876251824200153
2023-01-22 15:20:35.187595: step: 920/530, loss: 0.014783699065446854
2023-01-22 15:20:36.232597: step: 924/530, loss: 0.014318344183266163
2023-01-22 15:20:37.312098: step: 928/530, loss: 0.005068703088909388
2023-01-22 15:20:38.368578: step: 932/530, loss: 0.0008260238100774586
2023-01-22 15:20:39.419058: step: 936/530, loss: 0.005578598007559776
2023-01-22 15:20:40.480651: step: 940/530, loss: 0.005648624151945114
2023-01-22 15:20:41.546237: step: 944/530, loss: 0.01434145588427782
2023-01-22 15:20:42.594892: step: 948/530, loss: 0.05064533278346062
2023-01-22 15:20:43.660162: step: 952/530, loss: 0.045840006321668625
2023-01-22 15:20:44.728205: step: 956/530, loss: 0.008977357298135757
2023-01-22 15:20:45.787532: step: 960/530, loss: 0.006057981867343187
2023-01-22 15:20:46.849477: step: 964/530, loss: 0.020661020651459694
2023-01-22 15:20:47.911388: step: 968/530, loss: 0.01445910893380642
2023-01-22 15:20:48.983051: step: 972/530, loss: 0.0033617669250816107
2023-01-22 15:20:50.053299: step: 976/530, loss: 0.016689447686076164
2023-01-22 15:20:51.115539: step: 980/530, loss: 0.0020662483293563128
2023-01-22 15:20:52.196562: step: 984/530, loss: 0.015391046181321144
2023-01-22 15:20:53.246341: step: 988/530, loss: 0.008390625938773155
2023-01-22 15:20:54.287800: step: 992/530, loss: 0.012587555684149265
2023-01-22 15:20:55.345304: step: 996/530, loss: 0.003015401540324092
2023-01-22 15:20:56.397155: step: 1000/530, loss: 0.010146197862923145
2023-01-22 15:20:57.478143: step: 1004/530, loss: 0.025247910991311073
2023-01-22 15:20:58.543386: step: 1008/530, loss: 0.012767870910465717
2023-01-22 15:20:59.601258: step: 1012/530, loss: 0.0054501621052622795
2023-01-22 15:21:00.655826: step: 1016/530, loss: 0.0035274086985737085
2023-01-22 15:21:01.714139: step: 1020/530, loss: 0.007923038676381111
2023-01-22 15:21:02.814226: step: 1024/530, loss: 0.010635482147336006
2023-01-22 15:21:03.877766: step: 1028/530, loss: 0.008455418981611729
2023-01-22 15:21:04.928070: step: 1032/530, loss: 0.014862230978906155
2023-01-22 15:21:05.995164: step: 1036/530, loss: 0.0020091694314032793
2023-01-22 15:21:07.068876: step: 1040/530, loss: 0.009307769127190113
2023-01-22 15:21:08.127769: step: 1044/530, loss: 0.017452873289585114
2023-01-22 15:21:09.180106: step: 1048/530, loss: 0.012057536281645298
2023-01-22 15:21:10.240420: step: 1052/530, loss: 0.004280124790966511
2023-01-22 15:21:11.308212: step: 1056/530, loss: 0.008585563860833645
2023-01-22 15:21:12.368264: step: 1060/530, loss: 0.004593647085130215
2023-01-22 15:21:13.418883: step: 1064/530, loss: 0.009818469174206257
2023-01-22 15:21:14.502988: step: 1068/530, loss: 0.006922057364135981
2023-01-22 15:21:15.576287: step: 1072/530, loss: 0.0005158171406947076
2023-01-22 15:21:16.633435: step: 1076/530, loss: 0.008251353166997433
2023-01-22 15:21:17.697828: step: 1080/530, loss: 0.030195636674761772
2023-01-22 15:21:18.751707: step: 1084/530, loss: 0.010877580381929874
2023-01-22 15:21:19.812125: step: 1088/530, loss: 0.008826928213238716
2023-01-22 15:21:20.864998: step: 1092/530, loss: 0.005178998690098524
2023-01-22 15:21:21.928968: step: 1096/530, loss: 0.018378067761659622
2023-01-22 15:21:22.976451: step: 1100/530, loss: 0.007682143244892359
2023-01-22 15:21:24.064438: step: 1104/530, loss: 0.010484902188181877
2023-01-22 15:21:25.132890: step: 1108/530, loss: 0.005770792253315449
2023-01-22 15:21:26.203726: step: 1112/530, loss: 0.02715153805911541
2023-01-22 15:21:27.268638: step: 1116/530, loss: 0.00442056218162179
2023-01-22 15:21:28.344537: step: 1120/530, loss: 0.011488735675811768
2023-01-22 15:21:29.422223: step: 1124/530, loss: 0.007717338856309652
2023-01-22 15:21:30.481668: step: 1128/530, loss: 0.004458797629922628
2023-01-22 15:21:31.546649: step: 1132/530, loss: 0.007859314791858196
2023-01-22 15:21:32.646268: step: 1136/530, loss: 0.009439071640372276
2023-01-22 15:21:33.711208: step: 1140/530, loss: 0.0018428913317620754
2023-01-22 15:21:34.771656: step: 1144/530, loss: 0.016932310536503792
2023-01-22 15:21:35.830537: step: 1148/530, loss: 0.023681361228227615
2023-01-22 15:21:36.886350: step: 1152/530, loss: 0.005086707416921854
2023-01-22 15:21:37.943050: step: 1156/530, loss: 0.03885640203952789
2023-01-22 15:21:39.004379: step: 1160/530, loss: 0.008410545065999031
2023-01-22 15:21:40.051331: step: 1164/530, loss: 0.005495981313288212
2023-01-22 15:21:41.122569: step: 1168/530, loss: 0.0044034128077328205
2023-01-22 15:21:42.184225: step: 1172/530, loss: 0.008320998400449753
2023-01-22 15:21:43.245676: step: 1176/530, loss: 0.002126403385773301
2023-01-22 15:21:44.306692: step: 1180/530, loss: 0.008534141816198826
2023-01-22 15:21:45.370308: step: 1184/530, loss: 0.02552216500043869
2023-01-22 15:21:46.420577: step: 1188/530, loss: 0.008856154046952724
2023-01-22 15:21:47.482746: step: 1192/530, loss: 0.014329968020319939
2023-01-22 15:21:48.544453: step: 1196/530, loss: 0.0038457768969237804
2023-01-22 15:21:49.631625: step: 1200/530, loss: 0.004001577850431204
2023-01-22 15:21:50.690617: step: 1204/530, loss: 0.06063881516456604
2023-01-22 15:21:51.769481: step: 1208/530, loss: 0.001852215500548482
2023-01-22 15:21:52.818336: step: 1212/530, loss: 0.000265490758465603
2023-01-22 15:21:53.884934: step: 1216/530, loss: 0.005868783686310053
2023-01-22 15:21:54.960963: step: 1220/530, loss: 0.004784947726875544
2023-01-22 15:21:56.011869: step: 1224/530, loss: 0.0056470236741006374
2023-01-22 15:21:57.086168: step: 1228/530, loss: 0.003379441797733307
2023-01-22 15:21:58.150410: step: 1232/530, loss: 0.017595067620277405
2023-01-22 15:21:59.207665: step: 1236/530, loss: 0.0006823059520684183
2023-01-22 15:22:00.278706: step: 1240/530, loss: 0.02957821637392044
2023-01-22 15:22:01.346576: step: 1244/530, loss: 0.015399551950395107
2023-01-22 15:22:02.413786: step: 1248/530, loss: 0.03496057540178299
2023-01-22 15:22:03.475148: step: 1252/530, loss: 0.013075352646410465
2023-01-22 15:22:04.530416: step: 1256/530, loss: 0.006731557659804821
2023-01-22 15:22:05.602461: step: 1260/530, loss: 0.007542350795120001
2023-01-22 15:22:06.644924: step: 1264/530, loss: 0.0067122201435267925
2023-01-22 15:22:07.699192: step: 1268/530, loss: 0.006860585417598486
2023-01-22 15:22:08.760395: step: 1272/530, loss: 0.0018497022101655602
2023-01-22 15:22:09.818577: step: 1276/530, loss: 0.0029727229848504066
2023-01-22 15:22:10.886303: step: 1280/530, loss: 5.198213693802245e-05
2023-01-22 15:22:11.948612: step: 1284/530, loss: 0.002206278033554554
2023-01-22 15:22:13.008306: step: 1288/530, loss: 0.003800337901338935
2023-01-22 15:22:14.061583: step: 1292/530, loss: 0.0039053261280059814
2023-01-22 15:22:15.116881: step: 1296/530, loss: 0.007492515724152327
2023-01-22 15:22:16.182928: step: 1300/530, loss: 0.003310520900413394
2023-01-22 15:22:17.265241: step: 1304/530, loss: 0.04276058077812195
2023-01-22 15:22:18.320228: step: 1308/530, loss: 0.0019689034670591354
2023-01-22 15:22:19.385294: step: 1312/530, loss: 0.03961724415421486
2023-01-22 15:22:20.435924: step: 1316/530, loss: 0.026304567232728004
2023-01-22 15:22:21.508596: step: 1320/530, loss: 0.008821340277791023
2023-01-22 15:22:22.564340: step: 1324/530, loss: 0.004957039840519428
2023-01-22 15:22:23.623883: step: 1328/530, loss: 0.00439384113997221
2023-01-22 15:22:24.682474: step: 1332/530, loss: 0.006095076445490122
2023-01-22 15:22:25.743613: step: 1336/530, loss: 0.016416115686297417
2023-01-22 15:22:26.808302: step: 1340/530, loss: 0.012799358926713467
2023-01-22 15:22:27.863059: step: 1344/530, loss: 0.008660982362926006
2023-01-22 15:22:28.916908: step: 1348/530, loss: 0.01265436876565218
2023-01-22 15:22:29.980375: step: 1352/530, loss: 0.0047734021209180355
2023-01-22 15:22:31.033731: step: 1356/530, loss: 0.0072492496110498905
2023-01-22 15:22:32.108272: step: 1360/530, loss: 0.0038048243150115013
2023-01-22 15:22:33.153981: step: 1364/530, loss: 0.006910310126841068
2023-01-22 15:22:34.214258: step: 1368/530, loss: 0.0016836374998092651
2023-01-22 15:22:35.285086: step: 1372/530, loss: 0.0009233251912519336
2023-01-22 15:22:36.346806: step: 1376/530, loss: 0.004404107108712196
2023-01-22 15:22:37.406289: step: 1380/530, loss: 0.007357460912317038
2023-01-22 15:22:38.464073: step: 1384/530, loss: 0.005947975441813469
2023-01-22 15:22:39.517127: step: 1388/530, loss: 0.012318219058215618
2023-01-22 15:22:40.572623: step: 1392/530, loss: 0.012129281647503376
2023-01-22 15:22:41.628561: step: 1396/530, loss: 0.007892495952546597
2023-01-22 15:22:42.677501: step: 1400/530, loss: 0.010094028897583485
2023-01-22 15:22:43.734708: step: 1404/530, loss: 0.0077353776432573795
2023-01-22 15:22:44.788810: step: 1408/530, loss: 0.008069127798080444
2023-01-22 15:22:45.852425: step: 1412/530, loss: 0.005870666354894638
2023-01-22 15:22:46.910904: step: 1416/530, loss: 0.0031757953111082315
2023-01-22 15:22:47.992201: step: 1420/530, loss: 0.004836983047425747
2023-01-22 15:22:49.054190: step: 1424/530, loss: 0.023214153945446014
2023-01-22 15:22:50.114497: step: 1428/530, loss: 0.007668032310903072
2023-01-22 15:22:51.181912: step: 1432/530, loss: 0.0025659494567662477
2023-01-22 15:22:52.243350: step: 1436/530, loss: 0.0055738226510584354
2023-01-22 15:22:53.313340: step: 1440/530, loss: 0.012087934650480747
2023-01-22 15:22:54.377477: step: 1444/530, loss: 0.023460447788238525
2023-01-22 15:22:55.458441: step: 1448/530, loss: 0.02299894392490387
2023-01-22 15:22:56.537006: step: 1452/530, loss: 0.006333088967949152
2023-01-22 15:22:57.591674: step: 1456/530, loss: 0.017905397340655327
2023-01-22 15:22:58.643219: step: 1460/530, loss: 0.00876712892204523
2023-01-22 15:22:59.702104: step: 1464/530, loss: 0.0016122671077027917
2023-01-22 15:23:00.767050: step: 1468/530, loss: 0.007536186836659908
2023-01-22 15:23:01.836129: step: 1472/530, loss: 0.009219365194439888
2023-01-22 15:23:02.899612: step: 1476/530, loss: 0.0021594411227852106
2023-01-22 15:23:03.946347: step: 1480/530, loss: 0.0007112565799616277
2023-01-22 15:23:04.999853: step: 1484/530, loss: 0.05744333192706108
2023-01-22 15:23:06.069070: step: 1488/530, loss: 0.007184475660324097
2023-01-22 15:23:07.116430: step: 1492/530, loss: 0.005146166775375605
2023-01-22 15:23:08.190203: step: 1496/530, loss: 0.016744514927268028
2023-01-22 15:23:09.256638: step: 1500/530, loss: 0.0015380110125988722
2023-01-22 15:23:10.309722: step: 1504/530, loss: 0.01818438246846199
2023-01-22 15:23:11.365370: step: 1508/530, loss: 0.011860612779855728
2023-01-22 15:23:12.408717: step: 1512/530, loss: 0.022063730284571648
2023-01-22 15:23:13.469935: step: 1516/530, loss: 0.014161950908601284
2023-01-22 15:23:14.531401: step: 1520/530, loss: 0.006098361685872078
2023-01-22 15:23:15.600557: step: 1524/530, loss: 0.00678757019340992
2023-01-22 15:23:16.668081: step: 1528/530, loss: 0.004313177894800901
2023-01-22 15:23:17.754389: step: 1532/530, loss: 0.00238241720944643
2023-01-22 15:23:18.829943: step: 1536/530, loss: 0.04220748692750931
2023-01-22 15:23:19.884496: step: 1540/530, loss: 0.012493353337049484
2023-01-22 15:23:20.951490: step: 1544/530, loss: 0.014141512103378773
2023-01-22 15:23:22.006704: step: 1548/530, loss: 0.004078235477209091
2023-01-22 15:23:23.062774: step: 1552/530, loss: 0.010623589158058167
2023-01-22 15:23:24.131528: step: 1556/530, loss: 0.0028034208808094263
2023-01-22 15:23:25.202056: step: 1560/530, loss: 0.009858282282948494
2023-01-22 15:23:26.257054: step: 1564/530, loss: 0.06619033217430115
2023-01-22 15:23:27.315575: step: 1568/530, loss: 0.009783020243048668
2023-01-22 15:23:28.386724: step: 1572/530, loss: 0.008144106715917587
2023-01-22 15:23:29.455281: step: 1576/530, loss: 0.0033767693676054478
2023-01-22 15:23:30.519403: step: 1580/530, loss: 0.004536899738013744
2023-01-22 15:23:31.572465: step: 1584/530, loss: 0.008173903450369835
2023-01-22 15:23:32.650325: step: 1588/530, loss: 0.024307049810886383
2023-01-22 15:23:33.726112: step: 1592/530, loss: 0.007734532933682203
2023-01-22 15:23:34.783572: step: 1596/530, loss: 0.00324499374255538
2023-01-22 15:23:35.841842: step: 1600/530, loss: 0.004094294272363186
2023-01-22 15:23:36.919195: step: 1604/530, loss: 0.004557468928396702
2023-01-22 15:23:37.988015: step: 1608/530, loss: 0.006858260370790958
2023-01-22 15:23:39.045202: step: 1612/530, loss: 0.0020906715653836727
2023-01-22 15:23:40.116186: step: 1616/530, loss: 0.002209588885307312
2023-01-22 15:23:41.186279: step: 1620/530, loss: 0.0023509562015533447
2023-01-22 15:23:42.252828: step: 1624/530, loss: 0.02091505005955696
2023-01-22 15:23:43.323304: step: 1628/530, loss: 0.0033287617843598127
2023-01-22 15:23:44.390373: step: 1632/530, loss: 0.027823925018310547
2023-01-22 15:23:45.446004: step: 1636/530, loss: 0.02562517672777176
2023-01-22 15:23:46.497726: step: 1640/530, loss: 0.01110796257853508
2023-01-22 15:23:47.570598: step: 1644/530, loss: 0.0017457891954109073
2023-01-22 15:23:48.625108: step: 1648/530, loss: 0.01001239288598299
2023-01-22 15:23:49.694399: step: 1652/530, loss: 0.003693507518619299
2023-01-22 15:23:50.763051: step: 1656/530, loss: 0.008189893327653408
2023-01-22 15:23:51.836315: step: 1660/530, loss: 0.035926755517721176
2023-01-22 15:23:52.903923: step: 1664/530, loss: 0.006128427106887102
2023-01-22 15:23:53.961344: step: 1668/530, loss: 0.0005784844397567213
2023-01-22 15:23:55.026494: step: 1672/530, loss: 0.0011727223172783852
2023-01-22 15:23:56.093400: step: 1676/530, loss: 0.010610333643853664
2023-01-22 15:23:57.152799: step: 1680/530, loss: 0.007845600135624409
2023-01-22 15:23:58.224227: step: 1684/530, loss: 0.005412606988102198
2023-01-22 15:23:59.299104: step: 1688/530, loss: 0.006073933560401201
2023-01-22 15:24:00.377332: step: 1692/530, loss: 0.00578222144395113
2023-01-22 15:24:01.430199: step: 1696/530, loss: 0.004798486828804016
2023-01-22 15:24:02.505526: step: 1700/530, loss: 0.011088644154369831
2023-01-22 15:24:03.573174: step: 1704/530, loss: 0.00423861388117075
2023-01-22 15:24:04.627498: step: 1708/530, loss: 0.00791157130151987
2023-01-22 15:24:05.679687: step: 1712/530, loss: 0.008814826607704163
2023-01-22 15:24:06.743525: step: 1716/530, loss: 0.008338840678334236
2023-01-22 15:24:07.804097: step: 1720/530, loss: 0.010151728056371212
2023-01-22 15:24:08.885570: step: 1724/530, loss: 0.014455659314990044
2023-01-22 15:24:09.940013: step: 1728/530, loss: 0.019922861829400063
2023-01-22 15:24:10.984497: step: 1732/530, loss: 6.145249790279195e-05
2023-01-22 15:24:12.036869: step: 1736/530, loss: 0.013147489167749882
2023-01-22 15:24:13.087029: step: 1740/530, loss: 0.0057413214817643166
2023-01-22 15:24:14.147162: step: 1744/530, loss: 0.008017082698643208
2023-01-22 15:24:15.203093: step: 1748/530, loss: 0.0007139178924262524
2023-01-22 15:24:16.261359: step: 1752/530, loss: 0.002503437688574195
2023-01-22 15:24:17.313356: step: 1756/530, loss: 0.0018652512226253748
2023-01-22 15:24:18.387873: step: 1760/530, loss: 0.017183799296617508
2023-01-22 15:24:19.449555: step: 1764/530, loss: 0.004516208544373512
2023-01-22 15:24:20.510719: step: 1768/530, loss: 0.005358563270419836
2023-01-22 15:24:21.574484: step: 1772/530, loss: 0.013709604740142822
2023-01-22 15:24:22.645562: step: 1776/530, loss: 0.0068265474401414394
2023-01-22 15:24:23.713854: step: 1780/530, loss: 0.004847349599003792
2023-01-22 15:24:24.793560: step: 1784/530, loss: 0.003198120975866914
2023-01-22 15:24:25.866566: step: 1788/530, loss: 0.008180898614227772
2023-01-22 15:24:26.929526: step: 1792/530, loss: 0.009698394685983658
2023-01-22 15:24:28.010336: step: 1796/530, loss: 0.0013855216093361378
2023-01-22 15:24:29.062079: step: 1800/530, loss: 0.007150870282202959
2023-01-22 15:24:30.106717: step: 1804/530, loss: 0.024808460846543312
2023-01-22 15:24:31.179752: step: 1808/530, loss: 0.015996579080820084
2023-01-22 15:24:32.248814: step: 1812/530, loss: 0.0029417264740914106
2023-01-22 15:24:33.311515: step: 1816/530, loss: 0.02527133747935295
2023-01-22 15:24:34.372500: step: 1820/530, loss: 0.013187081553041935
2023-01-22 15:24:35.436736: step: 1824/530, loss: 0.003960073925554752
2023-01-22 15:24:36.509462: step: 1828/530, loss: 0.007379563990980387
2023-01-22 15:24:37.573995: step: 1832/530, loss: 0.003773181466385722
2023-01-22 15:24:38.621495: step: 1836/530, loss: 0.005938406102359295
2023-01-22 15:24:39.669752: step: 1840/530, loss: 0.00595604395493865
2023-01-22 15:24:40.717237: step: 1844/530, loss: 0.0023852570448070765
2023-01-22 15:24:41.795886: step: 1848/530, loss: 0.018418559804558754
2023-01-22 15:24:42.876922: step: 1852/530, loss: 0.04562212526798248
2023-01-22 15:24:43.946740: step: 1856/530, loss: 0.0052809021435678005
2023-01-22 15:24:45.002648: step: 1860/530, loss: 0.0029443902894854546
2023-01-22 15:24:46.076816: step: 1864/530, loss: 0.002488562371581793
2023-01-22 15:24:47.138393: step: 1868/530, loss: 0.012983922846615314
2023-01-22 15:24:48.218065: step: 1872/530, loss: 0.004306327551603317
2023-01-22 15:24:49.281075: step: 1876/530, loss: 0.030934635549783707
2023-01-22 15:24:50.353504: step: 1880/530, loss: 0.006068444810807705
2023-01-22 15:24:51.400065: step: 1884/530, loss: 0.005163372959941626
2023-01-22 15:24:52.458919: step: 1888/530, loss: 0.00963459350168705
2023-01-22 15:24:53.508893: step: 1892/530, loss: 0.10993104428052902
2023-01-22 15:24:54.567840: step: 1896/530, loss: 0.06135942041873932
2023-01-22 15:24:55.624640: step: 1900/530, loss: 0.00996585376560688
2023-01-22 15:24:56.673965: step: 1904/530, loss: 0.029266109690070152
2023-01-22 15:24:57.740336: step: 1908/530, loss: 0.021553490310907364
2023-01-22 15:24:58.797890: step: 1912/530, loss: 0.0070451395586133
2023-01-22 15:24:59.851419: step: 1916/530, loss: 0.00193988683167845
2023-01-22 15:25:00.918017: step: 1920/530, loss: 0.002844336209818721
2023-01-22 15:25:01.995211: step: 1924/530, loss: 0.007136641535907984
2023-01-22 15:25:03.091946: step: 1928/530, loss: 0.012044382281601429
2023-01-22 15:25:04.168450: step: 1932/530, loss: 0.005350827239453793
2023-01-22 15:25:05.247543: step: 1936/530, loss: 0.018192842602729797
2023-01-22 15:25:06.311445: step: 1940/530, loss: 0.041843391954898834
2023-01-22 15:25:07.401225: step: 1944/530, loss: 0.008060367777943611
2023-01-22 15:25:08.460956: step: 1948/530, loss: 0.005534703377634287
2023-01-22 15:25:09.510741: step: 1952/530, loss: 0.03554369509220123
2023-01-22 15:25:10.557203: step: 1956/530, loss: 0.024810925126075745
2023-01-22 15:25:11.626418: step: 1960/530, loss: 0.006485390942543745
2023-01-22 15:25:12.672524: step: 1964/530, loss: 0.003931231796741486
2023-01-22 15:25:13.741365: step: 1968/530, loss: 0.011343972757458687
2023-01-22 15:25:14.805105: step: 1972/530, loss: 0.02099820412695408
2023-01-22 15:25:15.898882: step: 1976/530, loss: 0.01283063180744648
2023-01-22 15:25:16.961711: step: 1980/530, loss: 0.026479102671146393
2023-01-22 15:25:18.021663: step: 1984/530, loss: 0.010106467641890049
2023-01-22 15:25:19.078888: step: 1988/530, loss: 0.009236016310751438
2023-01-22 15:25:20.133760: step: 1992/530, loss: 0.0019562605302780867
2023-01-22 15:25:21.197417: step: 1996/530, loss: 0.01028294675052166
2023-01-22 15:25:22.267055: step: 2000/530, loss: 0.004261597525328398
2023-01-22 15:25:23.336378: step: 2004/530, loss: 0.008500543422996998
2023-01-22 15:25:24.397374: step: 2008/530, loss: 0.009794317185878754
2023-01-22 15:25:25.450031: step: 2012/530, loss: 4.980359153705649e-05
2023-01-22 15:25:26.505524: step: 2016/530, loss: 0.00123411207459867
2023-01-22 15:25:27.565006: step: 2020/530, loss: 0.006054098252207041
2023-01-22 15:25:28.627692: step: 2024/530, loss: 0.008578311651945114
2023-01-22 15:25:29.688440: step: 2028/530, loss: 0.004066891502588987
2023-01-22 15:25:30.730314: step: 2032/530, loss: 0.002634467324241996
2023-01-22 15:25:31.781485: step: 2036/530, loss: 0.0039508286863565445
2023-01-22 15:25:32.829051: step: 2040/530, loss: 0.006239681039005518
2023-01-22 15:25:33.888064: step: 2044/530, loss: 0.009295599535107613
2023-01-22 15:25:34.961772: step: 2048/530, loss: 0.0029509584419429302
2023-01-22 15:25:36.024444: step: 2052/530, loss: 0.05808558315038681
2023-01-22 15:25:37.080525: step: 2056/530, loss: 0.01467252615839243
2023-01-22 15:25:38.132835: step: 2060/530, loss: 0.0001521360536571592
2023-01-22 15:25:39.187937: step: 2064/530, loss: 0.004247903823852539
2023-01-22 15:25:40.250642: step: 2068/530, loss: 0.0015431370120495558
2023-01-22 15:25:41.307581: step: 2072/530, loss: 0.024780839681625366
2023-01-22 15:25:42.358466: step: 2076/530, loss: 0.0015181649941951036
2023-01-22 15:25:43.435656: step: 2080/530, loss: 0.042880065739154816
2023-01-22 15:25:44.496218: step: 2084/530, loss: 0.02523890882730484
2023-01-22 15:25:45.576524: step: 2088/530, loss: 0.0056461491622030735
2023-01-22 15:25:46.632750: step: 2092/530, loss: 0.027111073955893517
2023-01-22 15:25:47.703990: step: 2096/530, loss: 0.01819942519068718
2023-01-22 15:25:48.761445: step: 2100/530, loss: 0.010223278775811195
2023-01-22 15:25:49.814597: step: 2104/530, loss: 0.008036882616579533
2023-01-22 15:25:50.883679: step: 2108/530, loss: 0.003609987674281001
2023-01-22 15:25:51.966413: step: 2112/530, loss: 0.0016776188276708126
2023-01-22 15:25:53.029462: step: 2116/530, loss: 0.013583243824541569
2023-01-22 15:25:54.098864: step: 2120/530, loss: 0.009458120912313461
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36420620819398, 'r': 0.2874948436597641, 'f1': 0.32133570012448714}, 'combined': 0.2367736737759379, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3584778631965659, 'r': 0.23464005591047948, 'f1': 0.28363083681486534}, 'combined': 0.188107497991206, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32357926528599606, 'r': 0.2868088942307692, 'f1': 0.30408653846153844}, 'combined': 0.20272435897435895, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40312085078680454, 'r': 0.31524329507895443, 'f1': 0.353807037972108}, 'combined': 0.23090564583442835, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3256116492796821, 'r': 0.3392045454545455, 'f1': 0.3322691365326124}, 'combined': 0.24482989007666178, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3602121124468901, 'r': 0.3249705810992723, 'f1': 0.3416850443055616}, 'combined': 0.22660977031664187, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 4}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, '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 15:28:19.145913: step: 4/530, loss: 0.003517056116834283
2023-01-22 15:28:20.200227: step: 8/530, loss: 0.009012565016746521
2023-01-22 15:28:21.279517: step: 12/530, loss: 0.00028308710898272693
2023-01-22 15:28:22.323566: step: 16/530, loss: 0.010990330949425697
2023-01-22 15:28:23.381676: step: 20/530, loss: 0.005436756648123264
2023-01-22 15:28:24.433691: step: 24/530, loss: 0.021109772846102715
2023-01-22 15:28:25.480109: step: 28/530, loss: 0.003288938896730542
2023-01-22 15:28:26.528133: step: 32/530, loss: 0.002336812438443303
2023-01-22 15:28:27.583625: step: 36/530, loss: 0.009832453913986683
2023-01-22 15:28:28.626331: step: 40/530, loss: 0.018044572323560715
2023-01-22 15:28:29.693607: step: 44/530, loss: 0.007544408086687326
2023-01-22 15:28:30.726066: step: 48/530, loss: 0.032098546624183655
2023-01-22 15:28:31.779623: step: 52/530, loss: 0.0007190116448327899
2023-01-22 15:28:32.838530: step: 56/530, loss: 0.003889210056513548
2023-01-22 15:28:33.908616: step: 60/530, loss: 0.01738993264734745
2023-01-22 15:28:34.971017: step: 64/530, loss: 0.0037156001199036837
2023-01-22 15:28:36.032994: step: 68/530, loss: 0.005493334028869867
2023-01-22 15:28:37.097864: step: 72/530, loss: 0.004966928623616695
2023-01-22 15:28:38.151344: step: 76/530, loss: 0.007253916468471289
2023-01-22 15:28:39.214722: step: 80/530, loss: 0.003153383731842041
2023-01-22 15:28:40.270689: step: 84/530, loss: 0.026970524340867996
2023-01-22 15:28:41.337734: step: 88/530, loss: 0.011001601815223694
2023-01-22 15:28:42.406113: step: 92/530, loss: 0.004383791703730822
2023-01-22 15:28:43.472632: step: 96/530, loss: 0.0033736806362867355
2023-01-22 15:28:44.544523: step: 100/530, loss: 0.021164245903491974
2023-01-22 15:28:45.607583: step: 104/530, loss: 0.002601813990622759
2023-01-22 15:28:46.669340: step: 108/530, loss: 0.0058281091041862965
2023-01-22 15:28:47.718238: step: 112/530, loss: 0.00868514459580183
2023-01-22 15:28:48.771380: step: 116/530, loss: 0.008433165960013866
2023-01-22 15:28:49.819922: step: 120/530, loss: 0.015177004970610142
2023-01-22 15:28:50.883489: step: 124/530, loss: 0.009002325125038624
2023-01-22 15:28:51.946064: step: 128/530, loss: 0.004818087909370661
2023-01-22 15:28:53.012313: step: 132/530, loss: 0.004497187212109566
2023-01-22 15:28:54.083403: step: 136/530, loss: 0.007404958829283714
2023-01-22 15:28:55.154652: step: 140/530, loss: 0.014937268570065498
2023-01-22 15:28:56.205590: step: 144/530, loss: 0.005882255733013153
2023-01-22 15:28:57.269795: step: 148/530, loss: 0.0081249438226223
2023-01-22 15:28:58.322544: step: 152/530, loss: 0.007643163204193115
2023-01-22 15:28:59.375536: step: 156/530, loss: 0.00040769053157418966
2023-01-22 15:29:00.427996: step: 160/530, loss: 0.00029486906714737415
2023-01-22 15:29:01.490105: step: 164/530, loss: 0.00803198292851448
2023-01-22 15:29:02.572037: step: 168/530, loss: 0.013935316354036331
2023-01-22 15:29:03.639375: step: 172/530, loss: 0.008148878812789917
2023-01-22 15:29:04.709971: step: 176/530, loss: 0.0004398757591843605
2023-01-22 15:29:05.784277: step: 180/530, loss: 0.004782336764037609
2023-01-22 15:29:06.858077: step: 184/530, loss: 0.11121557652950287
2023-01-22 15:29:07.936372: step: 188/530, loss: 0.009383085183799267
2023-01-22 15:29:09.001304: step: 192/530, loss: 0.0029649357311427593
2023-01-22 15:29:10.063397: step: 196/530, loss: 0.008337763138115406
2023-01-22 15:29:11.115549: step: 200/530, loss: 0.019029203802347183
2023-01-22 15:29:12.190662: step: 204/530, loss: 0.006065669469535351
2023-01-22 15:29:13.258431: step: 208/530, loss: 0.013527128845453262
2023-01-22 15:29:14.324804: step: 212/530, loss: 0.009829903021454811
2023-01-22 15:29:15.394812: step: 216/530, loss: 0.010944330133497715
2023-01-22 15:29:16.459235: step: 220/530, loss: 0.0014201614540070295
2023-01-22 15:29:17.543393: step: 224/530, loss: 0.010446802712976933
2023-01-22 15:29:18.624640: step: 228/530, loss: 0.004078686702996492
2023-01-22 15:29:19.674276: step: 232/530, loss: 0.009651732631027699
2023-01-22 15:29:20.710003: step: 236/530, loss: 0.0052575827576220036
2023-01-22 15:29:21.762207: step: 240/530, loss: 0.02713359333574772
2023-01-22 15:29:22.826281: step: 244/530, loss: 0.004265827126801014
2023-01-22 15:29:23.898091: step: 248/530, loss: 0.007725822273641825
2023-01-22 15:29:24.975939: step: 252/530, loss: 0.010921169072389603
2023-01-22 15:29:26.033708: step: 256/530, loss: 0.011113790795207024
2023-01-22 15:29:27.087306: step: 260/530, loss: 0.040320515632629395
2023-01-22 15:29:28.154309: step: 264/530, loss: 0.055253371596336365
2023-01-22 15:29:29.226742: step: 268/530, loss: 0.010644634254276752
2023-01-22 15:29:30.316460: step: 272/530, loss: 0.007393367122858763
2023-01-22 15:29:31.392536: step: 276/530, loss: 0.0014513102360069752
2023-01-22 15:29:32.453228: step: 280/530, loss: 0.019039904698729515
2023-01-22 15:29:33.507171: step: 284/530, loss: 0.054256342351436615
2023-01-22 15:29:34.564255: step: 288/530, loss: 0.01008105743676424
2023-01-22 15:29:35.626095: step: 292/530, loss: 0.0030834078788757324
2023-01-22 15:29:36.700680: step: 296/530, loss: 0.005493767559528351
2023-01-22 15:29:37.787414: step: 300/530, loss: 0.018559183925390244
2023-01-22 15:29:38.848764: step: 304/530, loss: 0.005808869376778603
2023-01-22 15:29:39.910837: step: 308/530, loss: 0.003038781927898526
2023-01-22 15:29:40.970234: step: 312/530, loss: 0.012369743548333645
2023-01-22 15:29:42.031348: step: 316/530, loss: 0.020224418491125107
2023-01-22 15:29:43.096749: step: 320/530, loss: 0.008415408432483673
2023-01-22 15:29:44.163499: step: 324/530, loss: 0.008500777184963226
2023-01-22 15:29:45.240445: step: 328/530, loss: 0.004227547440677881
2023-01-22 15:29:46.309897: step: 332/530, loss: 0.004737782292068005
2023-01-22 15:29:47.390748: step: 336/530, loss: 0.05515721067786217
2023-01-22 15:29:48.456176: step: 340/530, loss: 0.016539499163627625
2023-01-22 15:29:49.529570: step: 344/530, loss: 0.018101219087839127
2023-01-22 15:29:50.602781: step: 348/530, loss: 0.051545072346925735
2023-01-22 15:29:51.661602: step: 352/530, loss: 0.00850539281964302
2023-01-22 15:29:52.749055: step: 356/530, loss: 0.002685853745788336
2023-01-22 15:29:53.815559: step: 360/530, loss: 0.029639797285199165
2023-01-22 15:29:54.874270: step: 364/530, loss: 0.03649447113275528
2023-01-22 15:29:55.942166: step: 368/530, loss: 0.019114157184958458
2023-01-22 15:29:57.019967: step: 372/530, loss: 0.005436555948108435
2023-01-22 15:29:58.092033: step: 376/530, loss: 0.0022181563545018435
2023-01-22 15:29:59.152869: step: 380/530, loss: 0.015655457973480225
2023-01-22 15:30:00.218083: step: 384/530, loss: 0.0010982543462887406
2023-01-22 15:30:01.293025: step: 388/530, loss: 0.002683042548596859
2023-01-22 15:30:02.370377: step: 392/530, loss: 0.03194204717874527
2023-01-22 15:30:03.442352: step: 396/530, loss: 0.01111543644219637
2023-01-22 15:30:04.502964: step: 400/530, loss: 0.024194257333874702
2023-01-22 15:30:05.574659: step: 404/530, loss: 0.0008462219266220927
2023-01-22 15:30:06.645502: step: 408/530, loss: 0.014340794645249844
2023-01-22 15:30:07.700583: step: 412/530, loss: 0.006390500348061323
2023-01-22 15:30:08.767005: step: 416/530, loss: 0.0028179651126265526
2023-01-22 15:30:09.819632: step: 420/530, loss: 0.008723265491425991
2023-01-22 15:30:10.884993: step: 424/530, loss: 0.028755221515893936
2023-01-22 15:30:11.950751: step: 428/530, loss: 0.007391304709017277
2023-01-22 15:30:13.007369: step: 432/530, loss: 0.004387681372463703
2023-01-22 15:30:14.071700: step: 436/530, loss: 0.005039957817643881
2023-01-22 15:30:15.137010: step: 440/530, loss: 0.002497607609257102
2023-01-22 15:30:16.200781: step: 444/530, loss: 0.005696254316717386
2023-01-22 15:30:17.265986: step: 448/530, loss: 0.03760283812880516
2023-01-22 15:30:18.336171: step: 452/530, loss: 0.02391895279288292
2023-01-22 15:30:19.396907: step: 456/530, loss: 0.037628401070833206
2023-01-22 15:30:20.458767: step: 460/530, loss: 0.0896049216389656
2023-01-22 15:30:21.533654: step: 464/530, loss: 0.005308789666742086
2023-01-22 15:30:22.599966: step: 468/530, loss: 0.006673626601696014
2023-01-22 15:30:23.654139: step: 472/530, loss: 0.002351192058995366
2023-01-22 15:30:24.728791: step: 476/530, loss: 0.02134312130510807
2023-01-22 15:30:25.791111: step: 480/530, loss: 0.0056860544718801975
2023-01-22 15:30:26.855958: step: 484/530, loss: 0.008009308949112892
2023-01-22 15:30:27.926603: step: 488/530, loss: 0.009529204107820988
2023-01-22 15:30:28.997164: step: 492/530, loss: 0.012569320388138294
2023-01-22 15:30:30.068142: step: 496/530, loss: 0.011845407076179981
2023-01-22 15:30:31.145630: step: 500/530, loss: 0.002635406795889139
2023-01-22 15:30:32.198987: step: 504/530, loss: 0.005635532084852457
2023-01-22 15:30:33.263913: step: 508/530, loss: 0.0004423644859343767
2023-01-22 15:30:34.327186: step: 512/530, loss: 0.014786526560783386
2023-01-22 15:30:35.396599: step: 516/530, loss: 0.0066650379449129105
2023-01-22 15:30:36.459360: step: 520/530, loss: 0.0490175299346447
2023-01-22 15:30:37.524324: step: 524/530, loss: 0.0055488767102360725
2023-01-22 15:30:38.592556: step: 528/530, loss: 0.011376290582120419
2023-01-22 15:30:39.654052: step: 532/530, loss: 0.010135767981410027
2023-01-22 15:30:40.708170: step: 536/530, loss: 0.032854098826646805
2023-01-22 15:30:41.759469: step: 540/530, loss: 0.005537951830774546
2023-01-22 15:30:42.830671: step: 544/530, loss: 0.0034554556477814913
2023-01-22 15:30:43.900961: step: 548/530, loss: 0.015101026743650436
2023-01-22 15:30:44.961871: step: 552/530, loss: 0.0055346256121993065
2023-01-22 15:30:46.029111: step: 556/530, loss: 0.003905024379491806
2023-01-22 15:30:47.084270: step: 560/530, loss: 0.010141531005501747
2023-01-22 15:30:48.141576: step: 564/530, loss: 0.007455743383616209
2023-01-22 15:30:49.200448: step: 568/530, loss: 0.0037887238431721926
2023-01-22 15:30:50.270863: step: 572/530, loss: 0.002884421031922102
2023-01-22 15:30:51.339909: step: 576/530, loss: 0.004631417337805033
2023-01-22 15:30:52.394410: step: 580/530, loss: 0.0054386756382882595
2023-01-22 15:30:53.480477: step: 584/530, loss: 0.018852079287171364
2023-01-22 15:30:54.523001: step: 588/530, loss: 0.004346480593085289
2023-01-22 15:30:55.576325: step: 592/530, loss: 0.0036986065097153187
2023-01-22 15:30:56.625188: step: 596/530, loss: 0.008397475816309452
2023-01-22 15:30:57.685896: step: 600/530, loss: 0.0032148140016943216
2023-01-22 15:30:58.739015: step: 604/530, loss: 0.0035250037908554077
2023-01-22 15:30:59.798821: step: 608/530, loss: 0.009142866358160973
2023-01-22 15:31:00.856225: step: 612/530, loss: 0.005431356839835644
2023-01-22 15:31:01.911025: step: 616/530, loss: 0.018363559618592262
2023-01-22 15:31:02.981769: step: 620/530, loss: 0.0006756098591722548
2023-01-22 15:31:04.045399: step: 624/530, loss: 0.003582867095246911
2023-01-22 15:31:05.098295: step: 628/530, loss: 0.001773180440068245
2023-01-22 15:31:06.155006: step: 632/530, loss: 0.007147999480366707
2023-01-22 15:31:07.219735: step: 636/530, loss: 0.0022949762642383575
2023-01-22 15:31:08.269026: step: 640/530, loss: 0.03320471942424774
2023-01-22 15:31:09.327367: step: 644/530, loss: 0.00910720881074667
2023-01-22 15:31:10.395287: step: 648/530, loss: 0.007070349995046854
2023-01-22 15:31:11.450140: step: 652/530, loss: 0.005009678658097982
2023-01-22 15:31:12.503864: step: 656/530, loss: 0.0004368265508674085
2023-01-22 15:31:13.566032: step: 660/530, loss: 0.0630410760641098
2023-01-22 15:31:14.623006: step: 664/530, loss: 0.006882937625050545
2023-01-22 15:31:15.682290: step: 668/530, loss: 0.004937580320984125
2023-01-22 15:31:16.725939: step: 672/530, loss: 0.0011543085565790534
2023-01-22 15:31:17.776354: step: 676/530, loss: 0.006621150765568018
2023-01-22 15:31:18.838496: step: 680/530, loss: 0.007325129117816687
2023-01-22 15:31:19.896922: step: 684/530, loss: 0.0074560800567269325
2023-01-22 15:31:20.970362: step: 688/530, loss: 0.050486091524362564
2023-01-22 15:31:22.038203: step: 692/530, loss: 0.004529129713773727
2023-01-22 15:31:23.104602: step: 696/530, loss: 0.007007180713117123
2023-01-22 15:31:24.156253: step: 700/530, loss: 0.009266283363103867
2023-01-22 15:31:25.229861: step: 704/530, loss: 0.02546180598437786
2023-01-22 15:31:26.293618: step: 708/530, loss: 0.010309465229511261
2023-01-22 15:31:27.379018: step: 712/530, loss: 0.0032385371159762144
2023-01-22 15:31:28.438468: step: 716/530, loss: 0.019539283588528633
2023-01-22 15:31:29.518549: step: 720/530, loss: 0.02405500039458275
2023-01-22 15:31:30.569119: step: 724/530, loss: 3.7575437090708874e-06
2023-01-22 15:31:31.623681: step: 728/530, loss: 0.0005081840790808201
2023-01-22 15:31:32.682508: step: 732/530, loss: 0.007044833153486252
2023-01-22 15:31:33.749083: step: 736/530, loss: 0.0045994967222213745
2023-01-22 15:31:34.848793: step: 740/530, loss: 0.011359893716871738
2023-01-22 15:31:35.912854: step: 744/530, loss: 0.0037036314606666565
2023-01-22 15:31:36.969283: step: 748/530, loss: 0.002331929048523307
2023-01-22 15:31:38.024240: step: 752/530, loss: 0.0009123159688897431
2023-01-22 15:31:39.081306: step: 756/530, loss: 0.002318986691534519
2023-01-22 15:31:40.142556: step: 760/530, loss: 0.036909136921167374
2023-01-22 15:31:41.221767: step: 764/530, loss: 0.011546503752470016
2023-01-22 15:31:42.273883: step: 768/530, loss: 0.00661019841209054
2023-01-22 15:31:43.335388: step: 772/530, loss: 0.005355306901037693
2023-01-22 15:31:44.416494: step: 776/530, loss: 0.004799014423042536
2023-01-22 15:31:45.488450: step: 780/530, loss: 0.0015085495542734861
2023-01-22 15:31:46.543511: step: 784/530, loss: 0.009989234618842602
2023-01-22 15:31:47.605163: step: 788/530, loss: 0.0036725574173033237
2023-01-22 15:31:48.678201: step: 792/530, loss: 0.005716994404792786
2023-01-22 15:31:49.751939: step: 796/530, loss: 0.001757194520905614
2023-01-22 15:31:50.808704: step: 800/530, loss: 0.015330669470131397
2023-01-22 15:31:51.872937: step: 804/530, loss: 0.002205889904871583
2023-01-22 15:31:52.943779: step: 808/530, loss: 0.0068893954157829285
2023-01-22 15:31:54.007538: step: 812/530, loss: 0.0077874320559203625
2023-01-22 15:31:55.093807: step: 816/530, loss: 0.016964871436357498
2023-01-22 15:31:56.146554: step: 820/530, loss: 0.004929469898343086
2023-01-22 15:31:57.225935: step: 824/530, loss: 0.004375232849270105
2023-01-22 15:31:58.282558: step: 828/530, loss: 0.011272136121988297
2023-01-22 15:31:59.347671: step: 832/530, loss: 0.01298808678984642
2023-01-22 15:32:00.417009: step: 836/530, loss: 0.032257985323667526
2023-01-22 15:32:01.471886: step: 840/530, loss: 0.013422680087387562
2023-01-22 15:32:02.568736: step: 844/530, loss: 0.005984754767268896
2023-01-22 15:32:03.626403: step: 848/530, loss: 0.004423861857503653
2023-01-22 15:32:04.695946: step: 852/530, loss: 0.003647006116807461
2023-01-22 15:32:05.763094: step: 856/530, loss: 0.0011500094551593065
2023-01-22 15:32:06.852067: step: 860/530, loss: 0.003454555757343769
2023-01-22 15:32:07.904749: step: 864/530, loss: 0.004963899031281471
2023-01-22 15:32:08.982237: step: 868/530, loss: 0.013316702097654343
2023-01-22 15:32:10.040670: step: 872/530, loss: 0.019177105277776718
2023-01-22 15:32:11.116168: step: 876/530, loss: 0.0023701488971710205
2023-01-22 15:32:12.179840: step: 880/530, loss: 0.0029713427647948265
2023-01-22 15:32:13.244164: step: 884/530, loss: 0.008309753611683846
2023-01-22 15:32:14.312803: step: 888/530, loss: 0.016241425648331642
2023-01-22 15:32:15.376214: step: 892/530, loss: 0.007308730389922857
2023-01-22 15:32:16.446070: step: 896/530, loss: 0.04044658690690994
2023-01-22 15:32:17.525923: step: 900/530, loss: 0.011886515654623508
2023-01-22 15:32:18.588420: step: 904/530, loss: 0.006381236016750336
2023-01-22 15:32:19.668769: step: 908/530, loss: 0.004408490844070911
2023-01-22 15:32:20.726468: step: 912/530, loss: 0.004806546028703451
2023-01-22 15:32:21.792831: step: 916/530, loss: 0.005159028805792332
2023-01-22 15:32:22.872915: step: 920/530, loss: 0.005976864602416754
2023-01-22 15:32:23.962838: step: 924/530, loss: 0.005223964340984821
2023-01-22 15:32:25.020410: step: 928/530, loss: 0.005659719929099083
2023-01-22 15:32:26.094753: step: 932/530, loss: 0.013088217005133629
2023-01-22 15:32:27.171199: step: 936/530, loss: 0.0021140507888048887
2023-01-22 15:32:28.234179: step: 940/530, loss: 0.00842966977506876
2023-01-22 15:32:29.296470: step: 944/530, loss: 0.00021945053595118225
2023-01-22 15:32:30.356884: step: 948/530, loss: 0.007516163866966963
2023-01-22 15:32:31.424645: step: 952/530, loss: 0.022173110395669937
2023-01-22 15:32:32.530023: step: 956/530, loss: 0.0868389680981636
2023-01-22 15:32:33.594573: step: 960/530, loss: 0.0025863992050290108
2023-01-22 15:32:34.668371: step: 964/530, loss: 0.005571173969656229
2023-01-22 15:32:35.737810: step: 968/530, loss: 0.006155728362500668
2023-01-22 15:32:36.785727: step: 972/530, loss: 0.004272026475518942
2023-01-22 15:32:37.859204: step: 976/530, loss: 0.002964085666462779
2023-01-22 15:32:38.945011: step: 980/530, loss: 0.0028430030215531588
2023-01-22 15:32:40.004756: step: 984/530, loss: 0.008368617855012417
2023-01-22 15:32:41.062995: step: 988/530, loss: 0.03369031101465225
2023-01-22 15:32:42.130908: step: 992/530, loss: 0.01347421109676361
2023-01-22 15:32:43.194576: step: 996/530, loss: 0.004713854752480984
2023-01-22 15:32:44.262158: step: 1000/530, loss: 0.018790025264024734
2023-01-22 15:32:45.331355: step: 1004/530, loss: 0.021689891815185547
2023-01-22 15:32:46.398591: step: 1008/530, loss: 0.0023492074105888605
2023-01-22 15:32:47.453469: step: 1012/530, loss: 0.01468432042747736
2023-01-22 15:32:48.513361: step: 1016/530, loss: 0.00424958998337388
2023-01-22 15:32:49.570299: step: 1020/530, loss: 0.01432398147881031
2023-01-22 15:32:50.624758: step: 1024/530, loss: 0.0032544690184295177
2023-01-22 15:32:51.699946: step: 1028/530, loss: 0.011772519908845425
2023-01-22 15:32:52.756174: step: 1032/530, loss: 0.005709446035325527
2023-01-22 15:32:53.812767: step: 1036/530, loss: 0.009214820340275764
2023-01-22 15:32:54.870707: step: 1040/530, loss: 0.005603351630270481
2023-01-22 15:32:55.939836: step: 1044/530, loss: 0.029960831627249718
2023-01-22 15:32:57.027289: step: 1048/530, loss: 0.007764473557472229
2023-01-22 15:32:58.088436: step: 1052/530, loss: 0.007633398286998272
2023-01-22 15:32:59.146928: step: 1056/530, loss: 0.002183147706091404
2023-01-22 15:33:00.202404: step: 1060/530, loss: 0.006642820313572884
2023-01-22 15:33:01.274018: step: 1064/530, loss: 0.0033487691543996334
2023-01-22 15:33:02.340660: step: 1068/530, loss: 0.0028577228076756
2023-01-22 15:33:03.410446: step: 1072/530, loss: 0.0036148016806691885
2023-01-22 15:33:04.471719: step: 1076/530, loss: 0.006393277086317539
2023-01-22 15:33:05.532900: step: 1080/530, loss: 0.004756600596010685
2023-01-22 15:33:06.601259: step: 1084/530, loss: 0.0045590270310640335
2023-01-22 15:33:07.658673: step: 1088/530, loss: 0.03936564549803734
2023-01-22 15:33:08.707144: step: 1092/530, loss: 0.00040857470594346523
2023-01-22 15:33:09.745345: step: 1096/530, loss: 0.017735375091433525
2023-01-22 15:33:10.814715: step: 1100/530, loss: 0.009191764518618584
2023-01-22 15:33:11.884453: step: 1104/530, loss: 0.01862039789557457
2023-01-22 15:33:12.945566: step: 1108/530, loss: 0.008660403080284595
2023-01-22 15:33:13.999470: step: 1112/530, loss: 0.0008322783978655934
2023-01-22 15:33:15.054899: step: 1116/530, loss: 0.009353626519441605
2023-01-22 15:33:16.140676: step: 1120/530, loss: 0.005847702268511057
2023-01-22 15:33:17.202366: step: 1124/530, loss: 0.03231755271553993
2023-01-22 15:33:18.278239: step: 1128/530, loss: 0.03832541033625603
2023-01-22 15:33:19.329761: step: 1132/530, loss: 0.0021001286804676056
2023-01-22 15:33:20.378138: step: 1136/530, loss: 0.033331554383039474
2023-01-22 15:33:21.459018: step: 1140/530, loss: 0.022505968809127808
2023-01-22 15:33:22.528258: step: 1144/530, loss: 0.009933141991496086
2023-01-22 15:33:23.576133: step: 1148/530, loss: 0.00809610728174448
2023-01-22 15:33:24.627887: step: 1152/530, loss: 0.059753648936748505
2023-01-22 15:33:25.681298: step: 1156/530, loss: 0.030689775943756104
2023-01-22 15:33:26.744241: step: 1160/530, loss: 0.012817854061722755
2023-01-22 15:33:27.802272: step: 1164/530, loss: 0.016397599130868912
2023-01-22 15:33:28.869259: step: 1168/530, loss: 0.02847987972199917
2023-01-22 15:33:29.920114: step: 1172/530, loss: 0.012905584648251534
2023-01-22 15:33:30.981253: step: 1176/530, loss: 0.004862555302679539
2023-01-22 15:33:32.038404: step: 1180/530, loss: 0.008750325068831444
2023-01-22 15:33:33.092357: step: 1184/530, loss: 0.043315429240465164
2023-01-22 15:33:34.140008: step: 1188/530, loss: 0.01485416479408741
2023-01-22 15:33:35.193405: step: 1192/530, loss: 0.0025665347930043936
2023-01-22 15:33:36.253804: step: 1196/530, loss: 0.002824236173182726
2023-01-22 15:33:37.305306: step: 1200/530, loss: 0.030294490978121758
2023-01-22 15:33:38.382447: step: 1204/530, loss: 0.004747746046632528
2023-01-22 15:33:39.451696: step: 1208/530, loss: 0.011875168420374393
2023-01-22 15:33:40.526413: step: 1212/530, loss: 0.004423817154020071
2023-01-22 15:33:41.579933: step: 1216/530, loss: 0.008163546212017536
2023-01-22 15:33:42.638379: step: 1220/530, loss: 0.009794938378036022
2023-01-22 15:33:43.688902: step: 1224/530, loss: 0.015955302864313126
2023-01-22 15:33:44.753378: step: 1228/530, loss: 0.008795671164989471
2023-01-22 15:33:45.802403: step: 1232/530, loss: 0.07126534730195999
2023-01-22 15:33:46.869472: step: 1236/530, loss: 0.04979224130511284
2023-01-22 15:33:47.937845: step: 1240/530, loss: 0.003912405576556921
2023-01-22 15:33:48.987377: step: 1244/530, loss: 0.0049399458803236485
2023-01-22 15:33:50.045611: step: 1248/530, loss: 0.006058188620954752
2023-01-22 15:33:51.112392: step: 1252/530, loss: 0.0007667996105737984
2023-01-22 15:33:52.175839: step: 1256/530, loss: 0.0057192277163267136
2023-01-22 15:33:53.233197: step: 1260/530, loss: 0.00622472632676363
2023-01-22 15:33:54.288708: step: 1264/530, loss: 0.002794084371998906
2023-01-22 15:33:55.346812: step: 1268/530, loss: 0.005455076228827238
2023-01-22 15:33:56.392905: step: 1272/530, loss: 0.006627157796174288
2023-01-22 15:33:57.447472: step: 1276/530, loss: 0.03485396131873131
2023-01-22 15:33:58.499733: step: 1280/530, loss: 0.03075513243675232
2023-01-22 15:33:59.553923: step: 1284/530, loss: 0.0027068809140473604
2023-01-22 15:34:00.599854: step: 1288/530, loss: 0.007979771122336388
2023-01-22 15:34:01.662295: step: 1292/530, loss: 0.004088948480784893
2023-01-22 15:34:02.720907: step: 1296/530, loss: 0.008268347010016441
2023-01-22 15:34:03.777210: step: 1300/530, loss: 0.008342672139406204
2023-01-22 15:34:04.842002: step: 1304/530, loss: 0.004666406661272049
2023-01-22 15:34:05.894081: step: 1308/530, loss: 0.009865745902061462
2023-01-22 15:34:06.950221: step: 1312/530, loss: 0.0034520637709647417
2023-01-22 15:34:08.038901: step: 1316/530, loss: 0.024848198518157005
2023-01-22 15:34:09.100265: step: 1320/530, loss: 0.0052132029086351395
2023-01-22 15:34:10.146676: step: 1324/530, loss: 0.06313329935073853
2023-01-22 15:34:11.210645: step: 1328/530, loss: 0.0016254446236416698
2023-01-22 15:34:12.267454: step: 1332/530, loss: 0.0056574163027107716
2023-01-22 15:34:13.330539: step: 1336/530, loss: 0.005067254416644573
2023-01-22 15:34:14.386480: step: 1340/530, loss: 0.00024287166888825595
2023-01-22 15:34:15.430169: step: 1344/530, loss: 0.03414236754179001
2023-01-22 15:34:16.498885: step: 1348/530, loss: 0.008662113919854164
2023-01-22 15:34:17.561577: step: 1352/530, loss: 0.0074186003766953945
2023-01-22 15:34:18.614350: step: 1356/530, loss: 0.0050832428969442844
2023-01-22 15:34:19.687783: step: 1360/530, loss: 0.01904802955687046
2023-01-22 15:34:20.739487: step: 1364/530, loss: 0.0051752435974776745
2023-01-22 15:34:21.802298: step: 1368/530, loss: 0.010146742686629295
2023-01-22 15:34:22.864496: step: 1372/530, loss: 0.06443759799003601
2023-01-22 15:34:23.919505: step: 1376/530, loss: 0.007404040079563856
2023-01-22 15:34:24.998849: step: 1380/530, loss: 0.03164595365524292
2023-01-22 15:34:26.053081: step: 1384/530, loss: 0.0308536309748888
2023-01-22 15:34:27.101181: step: 1388/530, loss: 0.0007203335408121347
2023-01-22 15:34:28.159330: step: 1392/530, loss: 0.0030600244645029306
2023-01-22 15:34:29.203309: step: 1396/530, loss: 0.00735328858718276
2023-01-22 15:34:30.269417: step: 1400/530, loss: 0.03782516345381737
2023-01-22 15:34:31.328426: step: 1404/530, loss: 0.005687171593308449
2023-01-22 15:34:32.400727: step: 1408/530, loss: 0.007961194030940533
2023-01-22 15:34:33.458740: step: 1412/530, loss: 0.008044837974011898
2023-01-22 15:34:34.506315: step: 1416/530, loss: 0.010571010410785675
2023-01-22 15:34:35.566619: step: 1420/530, loss: 0.011312278918921947
2023-01-22 15:34:36.646783: step: 1424/530, loss: 0.01273477915674448
2023-01-22 15:34:37.702448: step: 1428/530, loss: 0.008418474346399307
2023-01-22 15:34:38.760801: step: 1432/530, loss: 0.00903947651386261
2023-01-22 15:34:39.816589: step: 1436/530, loss: 0.006529093720018864
2023-01-22 15:34:40.881743: step: 1440/530, loss: 0.03223242610692978
2023-01-22 15:34:41.930246: step: 1444/530, loss: 0.01048089936375618
2023-01-22 15:34:43.004751: step: 1448/530, loss: 0.013730064034461975
2023-01-22 15:34:44.069477: step: 1452/530, loss: 0.03295912966132164
2023-01-22 15:34:45.125740: step: 1456/530, loss: 0.006297646556049585
2023-01-22 15:34:46.188982: step: 1460/530, loss: 0.014950539916753769
2023-01-22 15:34:47.243406: step: 1464/530, loss: 0.002351527102291584
2023-01-22 15:34:48.293261: step: 1468/530, loss: 0.009170595556497574
2023-01-22 15:34:49.357393: step: 1472/530, loss: 0.004258336499333382
2023-01-22 15:34:50.431840: step: 1476/530, loss: 0.015216046944260597
2023-01-22 15:34:51.467457: step: 1480/530, loss: 0.0055315312929451466
2023-01-22 15:34:52.527867: step: 1484/530, loss: 0.0017328830435872078
2023-01-22 15:34:53.588728: step: 1488/530, loss: 0.004406601656228304
2023-01-22 15:34:54.644780: step: 1492/530, loss: 0.004037209786474705
2023-01-22 15:34:55.704143: step: 1496/530, loss: 0.006016279570758343
2023-01-22 15:34:56.747746: step: 1500/530, loss: 0.002808723133057356
2023-01-22 15:34:57.818094: step: 1504/530, loss: 0.02563599869608879
2023-01-22 15:34:58.869228: step: 1508/530, loss: 0.011710327118635178
2023-01-22 15:34:59.923546: step: 1512/530, loss: 0.005440083798021078
2023-01-22 15:35:00.990458: step: 1516/530, loss: 0.08998735249042511
2023-01-22 15:35:02.031942: step: 1520/530, loss: 0.006538390181958675
2023-01-22 15:35:03.076725: step: 1524/530, loss: 0.002666729735210538
2023-01-22 15:35:04.131724: step: 1528/530, loss: 0.003731057047843933
2023-01-22 15:35:05.186409: step: 1532/530, loss: 0.0054165152832865715
2023-01-22 15:35:06.239022: step: 1536/530, loss: 0.010040711611509323
2023-01-22 15:35:07.315595: step: 1540/530, loss: 0.02920636162161827
2023-01-22 15:35:08.369752: step: 1544/530, loss: 0.013925306499004364
2023-01-22 15:35:09.425170: step: 1548/530, loss: 0.013019642792642117
2023-01-22 15:35:10.474032: step: 1552/530, loss: 0.015582763589918613
2023-01-22 15:35:11.527688: step: 1556/530, loss: 0.011520355008542538
2023-01-22 15:35:12.589001: step: 1560/530, loss: 0.0043084206990897655
2023-01-22 15:35:13.652863: step: 1564/530, loss: 0.00961390696465969
2023-01-22 15:35:14.703834: step: 1568/530, loss: 0.0016335458494722843
2023-01-22 15:35:15.757371: step: 1572/530, loss: 0.003929502330720425
2023-01-22 15:35:16.824047: step: 1576/530, loss: 0.001233261777088046
2023-01-22 15:35:17.873942: step: 1580/530, loss: 0.012667790055274963
2023-01-22 15:35:18.935523: step: 1584/530, loss: 0.0026889867149293423
2023-01-22 15:35:19.978860: step: 1588/530, loss: 0.009532587602734566
2023-01-22 15:35:21.022171: step: 1592/530, loss: 0.0021155548747628927
2023-01-22 15:35:22.077043: step: 1596/530, loss: 0.007182436529546976
2023-01-22 15:35:23.133178: step: 1600/530, loss: 0.03723154589533806
2023-01-22 15:35:24.189844: step: 1604/530, loss: 0.0076673575676977634
2023-01-22 15:35:25.258765: step: 1608/530, loss: 0.015933748334646225
2023-01-22 15:35:26.326567: step: 1612/530, loss: 0.019861871376633644
2023-01-22 15:35:27.404831: step: 1616/530, loss: 0.006957708392292261
2023-01-22 15:35:28.455713: step: 1620/530, loss: 0.0017674921546131372
2023-01-22 15:35:29.517364: step: 1624/530, loss: 0.003526045475155115
2023-01-22 15:35:30.599023: step: 1628/530, loss: 0.012933246791362762
2023-01-22 15:35:31.653938: step: 1632/530, loss: 0.012411696836352348
2023-01-22 15:35:32.718295: step: 1636/530, loss: 0.014215086586773396
2023-01-22 15:35:33.794645: step: 1640/530, loss: 0.0036534839309751987
2023-01-22 15:35:34.847578: step: 1644/530, loss: 0.00822637602686882
2023-01-22 15:35:35.904749: step: 1648/530, loss: 0.0028788570780307055
2023-01-22 15:35:36.956860: step: 1652/530, loss: 0.008850933983922005
2023-01-22 15:35:38.022795: step: 1656/530, loss: 0.012631809338927269
2023-01-22 15:35:39.078380: step: 1660/530, loss: 0.008418691344559193
2023-01-22 15:35:40.126556: step: 1664/530, loss: 0.014639188535511494
2023-01-22 15:35:41.192404: step: 1668/530, loss: 0.0032683995086699724
2023-01-22 15:35:42.249132: step: 1672/530, loss: 0.004973691888153553
2023-01-22 15:35:43.307783: step: 1676/530, loss: 0.00462028244510293
2023-01-22 15:35:44.360021: step: 1680/530, loss: 0.07903909683227539
2023-01-22 15:35:45.411243: step: 1684/530, loss: 0.015505899675190449
2023-01-22 15:35:46.484616: step: 1688/530, loss: 0.019500674679875374
2023-01-22 15:35:47.535627: step: 1692/530, loss: 0.016083436086773872
2023-01-22 15:35:48.602993: step: 1696/530, loss: 0.007053493056446314
2023-01-22 15:35:49.658190: step: 1700/530, loss: 0.004030758515000343
2023-01-22 15:35:50.706510: step: 1704/530, loss: 0.006347734481096268
2023-01-22 15:35:51.778228: step: 1708/530, loss: 0.03831996023654938
2023-01-22 15:35:52.835936: step: 1712/530, loss: 0.012755157425999641
2023-01-22 15:35:53.887937: step: 1716/530, loss: 0.006069265305995941
2023-01-22 15:35:54.948803: step: 1720/530, loss: 0.008358371444046497
2023-01-22 15:35:56.010566: step: 1724/530, loss: 0.010149398818612099
2023-01-22 15:35:57.080442: step: 1728/530, loss: 0.0172977764159441
2023-01-22 15:35:58.124375: step: 1732/530, loss: 0.03618042171001434
2023-01-22 15:35:59.188270: step: 1736/530, loss: 0.007877811789512634
2023-01-22 15:36:00.244711: step: 1740/530, loss: 0.005684498697519302
2023-01-22 15:36:01.307406: step: 1744/530, loss: 0.0075081633403897285
2023-01-22 15:36:02.381368: step: 1748/530, loss: 0.0067033008672297
2023-01-22 15:36:03.430464: step: 1752/530, loss: 0.005355026572942734
2023-01-22 15:36:04.479377: step: 1756/530, loss: 0.0036875305231660604
2023-01-22 15:36:05.576718: step: 1760/530, loss: 0.007830041460692883
2023-01-22 15:36:06.642185: step: 1764/530, loss: 0.009110311977565289
2023-01-22 15:36:07.687077: step: 1768/530, loss: 0.007872947491705418
2023-01-22 15:36:08.787541: step: 1772/530, loss: 0.015335457399487495
2023-01-22 15:36:09.859501: step: 1776/530, loss: 0.05458350107073784
2023-01-22 15:36:10.909304: step: 1780/530, loss: 0.004223008640110493
2023-01-22 15:36:11.975788: step: 1784/530, loss: 0.005835706368088722
2023-01-22 15:36:13.030586: step: 1788/530, loss: 0.003655042964965105
2023-01-22 15:36:14.097508: step: 1792/530, loss: 0.016403520479798317
2023-01-22 15:36:15.158774: step: 1796/530, loss: 0.007521182764321566
2023-01-22 15:36:16.211124: step: 1800/530, loss: 0.016147593036293983
2023-01-22 15:36:17.270536: step: 1804/530, loss: 0.001990591175854206
2023-01-22 15:36:18.323751: step: 1808/530, loss: 0.004318589810281992
2023-01-22 15:36:19.376388: step: 1812/530, loss: 0.011621844954788685
2023-01-22 15:36:20.431294: step: 1816/530, loss: 0.0073912786319851875
2023-01-22 15:36:21.488870: step: 1820/530, loss: 0.004409641958773136
2023-01-22 15:36:22.559514: step: 1824/530, loss: 0.009205885231494904
2023-01-22 15:36:23.608793: step: 1828/530, loss: 0.006221571005880833
2023-01-22 15:36:24.660417: step: 1832/530, loss: 0.007805989123880863
2023-01-22 15:36:25.714534: step: 1836/530, loss: 0.006754001136869192
2023-01-22 15:36:26.763230: step: 1840/530, loss: 0.015085451304912567
2023-01-22 15:36:27.832902: step: 1844/530, loss: 0.019204866141080856
2023-01-22 15:36:28.895973: step: 1848/530, loss: 0.008780100382864475
2023-01-22 15:36:29.946155: step: 1852/530, loss: 0.005356362089514732
2023-01-22 15:36:31.017311: step: 1856/530, loss: 0.05792039632797241
2023-01-22 15:36:32.097468: step: 1860/530, loss: 0.0031712681520730257
2023-01-22 15:36:33.160797: step: 1864/530, loss: 0.009036014787852764
2023-01-22 15:36:34.199191: step: 1868/530, loss: 0.005058670416474342
2023-01-22 15:36:35.265397: step: 1872/530, loss: 0.00928338523954153
2023-01-22 15:36:36.321745: step: 1876/530, loss: 0.0011984192533418536
2023-01-22 15:36:37.380866: step: 1880/530, loss: 0.006535263732075691
2023-01-22 15:36:38.438737: step: 1884/530, loss: 0.010922207497060299
2023-01-22 15:36:39.484867: step: 1888/530, loss: 0.005120576359331608
2023-01-22 15:36:40.526290: step: 1892/530, loss: 0.004358522593975067
2023-01-22 15:36:41.559380: step: 1896/530, loss: 0.004579307045787573
2023-01-22 15:36:42.629389: step: 1900/530, loss: 0.007241895888000727
2023-01-22 15:36:43.677489: step: 1904/530, loss: 0.02510642074048519
2023-01-22 15:36:44.738934: step: 1908/530, loss: 0.008431936614215374
2023-01-22 15:36:45.809108: step: 1912/530, loss: 0.04638499766588211
2023-01-22 15:36:46.870125: step: 1916/530, loss: 0.02039339207112789
2023-01-22 15:36:47.904996: step: 1920/530, loss: 0.0005136327818036079
2023-01-22 15:36:48.943284: step: 1924/530, loss: 0.005467600654810667
2023-01-22 15:36:49.993199: step: 1928/530, loss: 0.008041586726903915
2023-01-22 15:36:51.036155: step: 1932/530, loss: 0.02065209671854973
2023-01-22 15:36:52.088607: step: 1936/530, loss: 0.00567570561543107
2023-01-22 15:36:53.144200: step: 1940/530, loss: 0.017883440479636192
2023-01-22 15:36:54.191716: step: 1944/530, loss: 0.003423431422561407
2023-01-22 15:36:55.239436: step: 1948/530, loss: 0.001592633780092001
2023-01-22 15:36:56.293887: step: 1952/530, loss: 0.0023013055324554443
2023-01-22 15:36:57.363029: step: 1956/530, loss: 0.0026466110721230507
2023-01-22 15:36:58.411107: step: 1960/530, loss: 0.0021058772690594196
2023-01-22 15:36:59.470269: step: 1964/530, loss: 0.006164945662021637
2023-01-22 15:37:00.543980: step: 1968/530, loss: 0.03140567988157272
2023-01-22 15:37:01.597782: step: 1972/530, loss: 0.009208698756992817
2023-01-22 15:37:02.652319: step: 1976/530, loss: 0.006094716489315033
2023-01-22 15:37:03.707441: step: 1980/530, loss: 0.008501475676894188
2023-01-22 15:37:04.782457: step: 1984/530, loss: 0.007851428352296352
2023-01-22 15:37:05.851255: step: 1988/530, loss: 0.00667061610147357
2023-01-22 15:37:06.900458: step: 1992/530, loss: 0.002443542703986168
2023-01-22 15:37:07.959746: step: 1996/530, loss: 0.0016685378504917026
2023-01-22 15:37:09.027620: step: 2000/530, loss: 0.0025370209477841854
2023-01-22 15:37:10.073208: step: 2004/530, loss: 0.0051748743280768394
2023-01-22 15:37:11.139670: step: 2008/530, loss: 0.0007593446644023061
2023-01-22 15:37:12.197763: step: 2012/530, loss: 0.01518605463206768
2023-01-22 15:37:13.267030: step: 2016/530, loss: 0.009732052683830261
2023-01-22 15:37:14.319780: step: 2020/530, loss: 0.011828409507870674
2023-01-22 15:37:15.371685: step: 2024/530, loss: 0.0031107300892472267
2023-01-22 15:37:16.426960: step: 2028/530, loss: 0.00406709173694253
2023-01-22 15:37:17.473498: step: 2032/530, loss: 0.005738048814237118
2023-01-22 15:37:18.554506: step: 2036/530, loss: 0.008668201975524426
2023-01-22 15:37:19.615147: step: 2040/530, loss: 0.011014391668140888
2023-01-22 15:37:20.654697: step: 2044/530, loss: 0.008107154630124569
2023-01-22 15:37:21.726905: step: 2048/530, loss: 0.004370998591184616
2023-01-22 15:37:22.797284: step: 2052/530, loss: 0.010136863216757774
2023-01-22 15:37:23.850301: step: 2056/530, loss: 0.005771184340119362
2023-01-22 15:37:24.903282: step: 2060/530, loss: 0.02169601246714592
2023-01-22 15:37:25.980620: step: 2064/530, loss: 0.007024338468909264
2023-01-22 15:37:27.037681: step: 2068/530, loss: 0.001197601668536663
2023-01-22 15:37:28.089456: step: 2072/530, loss: 0.00965450331568718
2023-01-22 15:37:29.154536: step: 2076/530, loss: 0.0038245441392064095
2023-01-22 15:37:30.212129: step: 2080/530, loss: 0.025288328528404236
2023-01-22 15:37:31.265485: step: 2084/530, loss: 0.009369452483952045
2023-01-22 15:37:32.323499: step: 2088/530, loss: 0.0016892123967409134
2023-01-22 15:37:33.383977: step: 2092/530, loss: 0.0044386195950210094
2023-01-22 15:37:34.466190: step: 2096/530, loss: 0.03561408072710037
2023-01-22 15:37:35.523293: step: 2100/530, loss: 0.00871810782700777
2023-01-22 15:37:36.580486: step: 2104/530, loss: 0.008738541975617409
2023-01-22 15:37:37.647622: step: 2108/530, loss: 0.000607248512096703
2023-01-22 15:37:38.698987: step: 2112/530, loss: 0.004152113106101751
2023-01-22 15:37:39.746992: step: 2116/530, loss: 0.002932887291535735
2023-01-22 15:37:40.787933: step: 2120/530, loss: 0.005966485477983952
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3590279208736864, 'r': 0.2874948436597641, 'f1': 0.31930407293718793}, 'combined': 0.23527668532213847, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35072443598005676, 'r': 0.23361455097204817, 'f1': 0.2804342460658766}, 'combined': 0.18598747925612538, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32151825085742286, 'r': 0.2868088942307692, 'f1': 0.3031733656733657}, 'combined': 0.20211557711557715, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.39811271737038356, 'r': 0.3162803548233056, 'f1': 0.35250966564646824}, 'combined': 0.23005893968506347, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3149131576084, 'r': 0.3328399028232994, 'f1': 0.32362846639830034}, 'combined': 0.23846308050401077, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35638354277429873, 'r': 0.32583638196507314, 'f1': 0.34042607070977793}, 'combined': 0.22577480337228792, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 6
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 15:40:07.455373: step: 4/530, loss: 0.002935008844360709
2023-01-22 15:40:08.504064: step: 8/530, loss: 0.00553450733423233
2023-01-22 15:40:09.546196: step: 12/530, loss: 0.0036238685715943575
2023-01-22 15:40:10.588051: step: 16/530, loss: 0.009448220022022724
2023-01-22 15:40:11.644327: step: 20/530, loss: 0.003173980861902237
2023-01-22 15:40:12.696867: step: 24/530, loss: 0.010232631117105484
2023-01-22 15:40:13.747630: step: 28/530, loss: 0.010038836859166622
2023-01-22 15:40:14.795981: step: 32/530, loss: 0.000773742503952235
2023-01-22 15:40:15.856732: step: 36/530, loss: 0.008045186288654804
2023-01-22 15:40:16.902445: step: 40/530, loss: 0.0057647330686450005
2023-01-22 15:40:17.986554: step: 44/530, loss: 0.04628004878759384
2023-01-22 15:40:19.050109: step: 48/530, loss: 0.019980663433670998
2023-01-22 15:40:20.118598: step: 52/530, loss: 0.030836906284093857
2023-01-22 15:40:21.165906: step: 56/530, loss: 0.014333067461848259
2023-01-22 15:40:22.211920: step: 60/530, loss: 0.022833118215203285
2023-01-22 15:40:23.265226: step: 64/530, loss: 0.04708084836602211
2023-01-22 15:40:24.320602: step: 68/530, loss: 0.014588503167033195
2023-01-22 15:40:25.382812: step: 72/530, loss: 0.015138708986341953
2023-01-22 15:40:26.425907: step: 76/530, loss: 0.006230298895388842
2023-01-22 15:40:27.493542: step: 80/530, loss: 0.012939664535224438
2023-01-22 15:40:28.554251: step: 84/530, loss: 0.008656331337988377
2023-01-22 15:40:29.621195: step: 88/530, loss: 0.001773890689946711
2023-01-22 15:40:30.677677: step: 92/530, loss: 0.0038941162638366222
2023-01-22 15:40:31.724230: step: 96/530, loss: 0.001993746729567647
2023-01-22 15:40:32.799064: step: 100/530, loss: 0.004627324640750885
2023-01-22 15:40:33.839446: step: 104/530, loss: 0.006845708470791578
2023-01-22 15:40:34.883208: step: 108/530, loss: 0.002246327232569456
2023-01-22 15:40:35.937732: step: 112/530, loss: 0.0014962865971028805
2023-01-22 15:40:37.005988: step: 116/530, loss: 0.026668353006243706
2023-01-22 15:40:38.081318: step: 120/530, loss: 0.00611648615449667
2023-01-22 15:40:39.124203: step: 124/530, loss: 0.001448789844289422
2023-01-22 15:40:40.181562: step: 128/530, loss: 0.001396888867020607
2023-01-22 15:40:41.235532: step: 132/530, loss: 0.0010024980874732137
2023-01-22 15:40:42.294350: step: 136/530, loss: 0.012518187053501606
2023-01-22 15:40:43.357645: step: 140/530, loss: 0.004129523411393166
2023-01-22 15:40:44.400894: step: 144/530, loss: 0.0331420823931694
2023-01-22 15:40:45.443582: step: 148/530, loss: 0.06676769256591797
2023-01-22 15:40:46.491577: step: 152/530, loss: 0.0006281499518081546
2023-01-22 15:40:47.549733: step: 156/530, loss: 0.014255334623157978
2023-01-22 15:40:48.613530: step: 160/530, loss: 0.011756670661270618
2023-01-22 15:40:49.683283: step: 164/530, loss: 0.007124690804630518
2023-01-22 15:40:50.753467: step: 168/530, loss: 0.007193358615040779
2023-01-22 15:40:51.821488: step: 172/530, loss: 0.0037883929908275604
2023-01-22 15:40:52.892186: step: 176/530, loss: 0.005635456647723913
2023-01-22 15:40:53.959972: step: 180/530, loss: 0.004862099885940552
2023-01-22 15:40:55.013743: step: 184/530, loss: 0.0012532506370916963
2023-01-22 15:40:56.059314: step: 188/530, loss: 0.003170378040522337
2023-01-22 15:40:57.120368: step: 192/530, loss: 0.0036637848243117332
2023-01-22 15:40:58.176143: step: 196/530, loss: 0.004866126459091902
2023-01-22 15:40:59.224012: step: 200/530, loss: 0.0031893854029476643
2023-01-22 15:41:00.274879: step: 204/530, loss: 0.002500726841390133
2023-01-22 15:41:01.342879: step: 208/530, loss: 0.012587991543114185
2023-01-22 15:41:02.415274: step: 212/530, loss: 0.019643208011984825
2023-01-22 15:41:03.491497: step: 216/530, loss: 0.011613375507295132
2023-01-22 15:41:04.550642: step: 220/530, loss: 0.007276271935552359
2023-01-22 15:41:05.620692: step: 224/530, loss: 0.012464502826333046
2023-01-22 15:41:06.690014: step: 228/530, loss: 0.10264579206705093
2023-01-22 15:41:07.762423: step: 232/530, loss: 0.03704299405217171
2023-01-22 15:41:08.829500: step: 236/530, loss: 0.004660559818148613
2023-01-22 15:41:09.894437: step: 240/530, loss: 0.0017231680685654283
2023-01-22 15:41:10.961860: step: 244/530, loss: 0.0038283290341496468
2023-01-22 15:41:12.033029: step: 248/530, loss: 0.00805477425456047
2023-01-22 15:41:13.084611: step: 252/530, loss: 0.019948381930589676
2023-01-22 15:41:14.160092: step: 256/530, loss: 0.02022450603544712
2023-01-22 15:41:15.255120: step: 260/530, loss: 0.014648928306996822
2023-01-22 15:41:16.334691: step: 264/530, loss: 0.001241735415533185
2023-01-22 15:41:17.394632: step: 268/530, loss: 0.0006190391723066568
2023-01-22 15:41:18.473919: step: 272/530, loss: 0.0002878374943975359
2023-01-22 15:41:19.552163: step: 276/530, loss: 0.011928042396903038
2023-01-22 15:41:20.640520: step: 280/530, loss: 0.002198312198743224
2023-01-22 15:41:21.696590: step: 284/530, loss: 0.03147488832473755
2023-01-22 15:41:22.749326: step: 288/530, loss: 0.0010817664442583919
2023-01-22 15:41:23.840849: step: 292/530, loss: 0.0057760486379265785
2023-01-22 15:41:24.897706: step: 296/530, loss: 0.005818071309477091
2023-01-22 15:41:25.985919: step: 300/530, loss: 0.010569863021373749
2023-01-22 15:41:27.028062: step: 304/530, loss: 0.0035836913157254457
2023-01-22 15:41:28.083473: step: 308/530, loss: 0.0013431876432150602
2023-01-22 15:41:29.148954: step: 312/530, loss: 0.00991650391370058
2023-01-22 15:41:30.215486: step: 316/530, loss: 0.04024288058280945
2023-01-22 15:41:31.268613: step: 320/530, loss: 0.007050373591482639
2023-01-22 15:41:32.325428: step: 324/530, loss: 0.0062559545040130615
2023-01-22 15:41:33.395394: step: 328/530, loss: 0.002456584945321083
2023-01-22 15:41:34.462001: step: 332/530, loss: 0.020340995863080025
2023-01-22 15:41:35.516220: step: 336/530, loss: 0.009060685522854328
2023-01-22 15:41:36.566856: step: 340/530, loss: 0.009002921171486378
2023-01-22 15:41:37.645988: step: 344/530, loss: 0.002297008875757456
2023-01-22 15:41:38.714110: step: 348/530, loss: 0.007203955668956041
2023-01-22 15:41:39.770449: step: 352/530, loss: 0.0009175653103739023
2023-01-22 15:41:40.835177: step: 356/530, loss: 0.011200152337551117
2023-01-22 15:41:41.894606: step: 360/530, loss: 0.002791506005451083
2023-01-22 15:41:42.972405: step: 364/530, loss: 0.015113864094018936
2023-01-22 15:41:44.035020: step: 368/530, loss: 0.0012664305977523327
2023-01-22 15:41:45.136294: step: 372/530, loss: 0.00632602721452713
2023-01-22 15:41:46.197189: step: 376/530, loss: 0.002704090904444456
2023-01-22 15:41:47.263354: step: 380/530, loss: 0.002333748620003462
2023-01-22 15:41:48.327467: step: 384/530, loss: 0.003553990740329027
2023-01-22 15:41:49.393574: step: 388/530, loss: 0.021430572494864464
2023-01-22 15:41:50.459301: step: 392/530, loss: 0.003722083754837513
2023-01-22 15:41:51.519836: step: 396/530, loss: 0.002973325317725539
2023-01-22 15:41:52.603336: step: 400/530, loss: 0.0028017768636345863
2023-01-22 15:41:53.674596: step: 404/530, loss: 0.00537716643884778
2023-01-22 15:41:54.720836: step: 408/530, loss: 0.014416931197047234
2023-01-22 15:41:55.786633: step: 412/530, loss: 0.0015526312636211514
2023-01-22 15:41:56.845613: step: 416/530, loss: 0.005448088515549898
2023-01-22 15:41:57.902843: step: 420/530, loss: 0.002743306802585721
2023-01-22 15:41:58.958383: step: 424/530, loss: 0.0010752518428489566
2023-01-22 15:42:00.026402: step: 428/530, loss: 0.014399430714547634
2023-01-22 15:42:01.069254: step: 432/530, loss: 0.002354689408093691
2023-01-22 15:42:02.152721: step: 436/530, loss: 0.021478183567523956
2023-01-22 15:42:03.220565: step: 440/530, loss: 0.026265544816851616
2023-01-22 15:42:04.288874: step: 444/530, loss: 0.0015635223826393485
2023-01-22 15:42:05.362094: step: 448/530, loss: 0.00818532146513462
2023-01-22 15:42:06.404368: step: 452/530, loss: 0.0004785509081557393
2023-01-22 15:42:07.475452: step: 456/530, loss: 0.009481661021709442
2023-01-22 15:42:08.542827: step: 460/530, loss: 0.005708055570721626
2023-01-22 15:42:09.614447: step: 464/530, loss: 0.010962888598442078
2023-01-22 15:42:10.670088: step: 468/530, loss: 0.017835110425949097
2023-01-22 15:42:11.744873: step: 472/530, loss: 0.006975238677114248
2023-01-22 15:42:12.820025: step: 476/530, loss: 0.014720846898853779
2023-01-22 15:42:13.894082: step: 480/530, loss: 0.017656855285167694
2023-01-22 15:42:14.960111: step: 484/530, loss: 0.0036886150483042
2023-01-22 15:42:16.020747: step: 488/530, loss: 0.004657586105167866
2023-01-22 15:42:17.085118: step: 492/530, loss: 0.029611514881253242
2023-01-22 15:42:18.159449: step: 496/530, loss: 0.002924734726548195
2023-01-22 15:42:19.232051: step: 500/530, loss: 0.0038471685256808996
2023-01-22 15:42:20.310014: step: 504/530, loss: 0.002278828527778387
2023-01-22 15:42:21.386674: step: 508/530, loss: 0.014040910638868809
2023-01-22 15:42:22.448479: step: 512/530, loss: 0.001243583974428475
2023-01-22 15:42:23.502372: step: 516/530, loss: 0.008267502300441265
2023-01-22 15:42:24.569162: step: 520/530, loss: 0.005858213175088167
2023-01-22 15:42:25.624906: step: 524/530, loss: 0.02089940570294857
2023-01-22 15:42:26.681257: step: 528/530, loss: 0.0022993097081780434
2023-01-22 15:42:27.754509: step: 532/530, loss: 0.004143647849559784
2023-01-22 15:42:28.823379: step: 536/530, loss: 0.019484344869852066
2023-01-22 15:42:29.891146: step: 540/530, loss: 0.005829899106174707
2023-01-22 15:42:30.942650: step: 544/530, loss: 0.023752352222800255
2023-01-22 15:42:32.006758: step: 548/530, loss: 0.004406374413520098
2023-01-22 15:42:33.066907: step: 552/530, loss: 0.021138319745659828
2023-01-22 15:42:34.116730: step: 556/530, loss: 0.0108731584623456
2023-01-22 15:42:35.182554: step: 560/530, loss: 0.008291509933769703
2023-01-22 15:42:36.240830: step: 564/530, loss: 0.007430888246744871
2023-01-22 15:42:37.280980: step: 568/530, loss: 0.002242419868707657
2023-01-22 15:42:38.350138: step: 572/530, loss: 0.007153162267059088
2023-01-22 15:42:39.418593: step: 576/530, loss: 0.00153370073530823
2023-01-22 15:42:40.472104: step: 580/530, loss: 0.021514829248189926
2023-01-22 15:42:41.532422: step: 584/530, loss: 0.012931182980537415
2023-01-22 15:42:42.611309: step: 588/530, loss: 0.01066757831722498
2023-01-22 15:42:43.688187: step: 592/530, loss: 0.004547076765447855
2023-01-22 15:42:44.745797: step: 596/530, loss: 0.0018678150372579694
2023-01-22 15:42:45.826760: step: 600/530, loss: 0.061334703117609024
2023-01-22 15:42:46.896715: step: 604/530, loss: 0.00036601736792363226
2023-01-22 15:42:47.939333: step: 608/530, loss: 3.519013989716768e-05
2023-01-22 15:42:49.023653: step: 612/530, loss: 0.005283213220536709
2023-01-22 15:42:50.101123: step: 616/530, loss: 0.002885697176679969
2023-01-22 15:42:51.149730: step: 620/530, loss: 0.003819693811237812
2023-01-22 15:42:52.227905: step: 624/530, loss: 0.0026370843406766653
2023-01-22 15:42:53.303284: step: 628/530, loss: 0.015561898238956928
2023-01-22 15:42:54.398948: step: 632/530, loss: 0.007443511392921209
2023-01-22 15:42:55.459516: step: 636/530, loss: 0.033750295639038086
2023-01-22 15:42:56.530982: step: 640/530, loss: 0.015521280467510223
2023-01-22 15:42:57.605866: step: 644/530, loss: 0.023418111726641655
2023-01-22 15:42:58.682559: step: 648/530, loss: 0.003972249571233988
2023-01-22 15:42:59.743555: step: 652/530, loss: 1.3918206605012529e-05
2023-01-22 15:43:00.814957: step: 656/530, loss: 0.0073442705906927586
2023-01-22 15:43:01.886833: step: 660/530, loss: 0.0070203267969191074
2023-01-22 15:43:02.957624: step: 664/530, loss: 0.007446333300322294
2023-01-22 15:43:04.017141: step: 668/530, loss: 0.0017605950124561787
2023-01-22 15:43:05.079391: step: 672/530, loss: 0.005377999506890774
2023-01-22 15:43:06.143261: step: 676/530, loss: 0.0012440556893125176
2023-01-22 15:43:07.199266: step: 680/530, loss: 0.009946336038410664
2023-01-22 15:43:08.270790: step: 684/530, loss: 0.005002099554985762
2023-01-22 15:43:09.329434: step: 688/530, loss: 0.014016013592481613
2023-01-22 15:43:10.396382: step: 692/530, loss: 0.0008377187186852098
2023-01-22 15:43:11.448783: step: 696/530, loss: 0.0028977743349969387
2023-01-22 15:43:12.515595: step: 700/530, loss: 0.007128594908863306
2023-01-22 15:43:13.575851: step: 704/530, loss: 0.005335237365216017
2023-01-22 15:43:14.639259: step: 708/530, loss: 0.007555581629276276
2023-01-22 15:43:15.680226: step: 712/530, loss: 0.001965835690498352
2023-01-22 15:43:16.732044: step: 716/530, loss: 0.0018483292078599334
2023-01-22 15:43:17.790831: step: 720/530, loss: 0.014079613611102104
2023-01-22 15:43:18.840314: step: 724/530, loss: 0.009324528276920319
2023-01-22 15:43:19.892532: step: 728/530, loss: 0.007066858932375908
2023-01-22 15:43:20.948197: step: 732/530, loss: 0.019413722679018974
2023-01-22 15:43:22.008203: step: 736/530, loss: 0.0062380400486290455
2023-01-22 15:43:23.057596: step: 740/530, loss: 0.0024765871930867434
2023-01-22 15:43:24.107003: step: 744/530, loss: 0.0005940993432886899
2023-01-22 15:43:25.170895: step: 748/530, loss: 0.04270133003592491
2023-01-22 15:43:26.223219: step: 752/530, loss: 0.009178146719932556
2023-01-22 15:43:27.294761: step: 756/530, loss: 0.007826559245586395
2023-01-22 15:43:28.354589: step: 760/530, loss: 0.003232432994991541
2023-01-22 15:43:29.415079: step: 764/530, loss: 0.006229587830603123
2023-01-22 15:43:30.474072: step: 768/530, loss: 0.012369930744171143
2023-01-22 15:43:31.533291: step: 772/530, loss: 0.015480311587452888
2023-01-22 15:43:32.590801: step: 776/530, loss: 0.005448880605399609
2023-01-22 15:43:33.642392: step: 780/530, loss: 0.005266676191240549
2023-01-22 15:43:34.696427: step: 784/530, loss: 0.010284190066158772
2023-01-22 15:43:35.757586: step: 788/530, loss: 0.011885513551533222
2023-01-22 15:43:36.801697: step: 792/530, loss: 0.0125502310693264
2023-01-22 15:43:37.865458: step: 796/530, loss: 0.01250625029206276
2023-01-22 15:43:38.923382: step: 800/530, loss: 0.058051660656929016
2023-01-22 15:43:39.983548: step: 804/530, loss: 0.005431478843092918
2023-01-22 15:43:41.055002: step: 808/530, loss: 0.004475806839764118
2023-01-22 15:43:42.102167: step: 812/530, loss: 0.01590234600007534
2023-01-22 15:43:43.151199: step: 816/530, loss: 0.0037732599303126335
2023-01-22 15:43:44.207762: step: 820/530, loss: 0.0012804219732061028
2023-01-22 15:43:45.268274: step: 824/530, loss: 0.02562713250517845
2023-01-22 15:43:46.327614: step: 828/530, loss: 0.003869742387905717
2023-01-22 15:43:47.386016: step: 832/530, loss: 0.01133052259683609
2023-01-22 15:43:48.442793: step: 836/530, loss: 0.003731081960722804
2023-01-22 15:43:49.484235: step: 840/530, loss: 0.02150881662964821
2023-01-22 15:43:50.543508: step: 844/530, loss: 0.0125171709805727
2023-01-22 15:43:51.598039: step: 848/530, loss: 0.0021820201072841883
2023-01-22 15:43:52.664321: step: 852/530, loss: 0.007116499822586775
2023-01-22 15:43:53.718035: step: 856/530, loss: 8.16404281067662e-05
2023-01-22 15:43:54.776474: step: 860/530, loss: 0.027179615572094917
2023-01-22 15:43:55.861474: step: 864/530, loss: 0.0028818680439144373
2023-01-22 15:43:56.937687: step: 868/530, loss: 0.005046400241553783
2023-01-22 15:43:58.004948: step: 872/530, loss: 0.029310790821909904
2023-01-22 15:43:59.058374: step: 876/530, loss: 0.002894083270803094
2023-01-22 15:44:00.133638: step: 880/530, loss: 0.01013959851115942
2023-01-22 15:44:01.201989: step: 884/530, loss: 0.0022927518002688885
2023-01-22 15:44:02.287520: step: 888/530, loss: 0.011974267661571503
2023-01-22 15:44:03.337498: step: 892/530, loss: 0.0037686966825276613
2023-01-22 15:44:04.378351: step: 896/530, loss: 0.0012438582489266992
2023-01-22 15:44:05.451509: step: 900/530, loss: 0.018747396767139435
2023-01-22 15:44:06.508619: step: 904/530, loss: 0.03753173351287842
2023-01-22 15:44:07.576492: step: 908/530, loss: 0.0037961772177368402
2023-01-22 15:44:08.636220: step: 912/530, loss: 0.0002140506258001551
2023-01-22 15:44:09.698035: step: 916/530, loss: 9.290588786825538e-05
2023-01-22 15:44:10.795719: step: 920/530, loss: 0.013624818064272404
2023-01-22 15:44:11.847964: step: 924/530, loss: 0.005930694751441479
2023-01-22 15:44:12.922187: step: 928/530, loss: 0.0030376899521797895
2023-01-22 15:44:13.989396: step: 932/530, loss: 0.011940033175051212
2023-01-22 15:44:15.071482: step: 936/530, loss: 0.004891168791800737
2023-01-22 15:44:16.132949: step: 940/530, loss: 0.018233217298984528
2023-01-22 15:44:17.179598: step: 944/530, loss: 0.0002812612510751933
2023-01-22 15:44:18.236259: step: 948/530, loss: 0.0096819419413805
2023-01-22 15:44:19.318395: step: 952/530, loss: 0.010757689364254475
2023-01-22 15:44:20.392198: step: 956/530, loss: 0.003954260144382715
2023-01-22 15:44:21.454262: step: 960/530, loss: 0.006567119620740414
2023-01-22 15:44:22.517767: step: 964/530, loss: 0.0039191520772874355
2023-01-22 15:44:23.577221: step: 968/530, loss: 0.02667185105383396
2023-01-22 15:44:24.640741: step: 972/530, loss: 0.0038634252268821
2023-01-22 15:44:25.710367: step: 976/530, loss: 0.020103279501199722
2023-01-22 15:44:26.757119: step: 980/530, loss: 9.14368501980789e-05
2023-01-22 15:44:27.817483: step: 984/530, loss: 0.012991974130272865
2023-01-22 15:44:28.891464: step: 988/530, loss: 0.005785475950688124
2023-01-22 15:44:29.965221: step: 992/530, loss: 0.01604420319199562
2023-01-22 15:44:31.020506: step: 996/530, loss: 0.02683783508837223
2023-01-22 15:44:32.108214: step: 1000/530, loss: 0.0038679251447319984
2023-01-22 15:44:33.168721: step: 1004/530, loss: 0.004743065685033798
2023-01-22 15:44:34.244141: step: 1008/530, loss: 0.015931354835629463
2023-01-22 15:44:35.310882: step: 1012/530, loss: 0.018804019317030907
2023-01-22 15:44:36.368703: step: 1016/530, loss: 0.007097493391484022
2023-01-22 15:44:37.440813: step: 1020/530, loss: 0.014133797027170658
2023-01-22 15:44:38.491329: step: 1024/530, loss: 0.008046402595937252
2023-01-22 15:44:39.538150: step: 1028/530, loss: 0.0003183053049724549
2023-01-22 15:44:40.594037: step: 1032/530, loss: 0.0
2023-01-22 15:44:41.671469: step: 1036/530, loss: 0.004290013574063778
2023-01-22 15:44:42.729960: step: 1040/530, loss: 0.009799295105040073
2023-01-22 15:44:43.809685: step: 1044/530, loss: 0.004885335452854633
2023-01-22 15:44:44.870576: step: 1048/530, loss: 0.0013348229695111513
2023-01-22 15:44:45.926484: step: 1052/530, loss: 0.00038746907375752926
2023-01-22 15:44:46.977383: step: 1056/530, loss: 0.011195574887096882
2023-01-22 15:44:48.045610: step: 1060/530, loss: 0.00456309923902154
2023-01-22 15:44:49.089421: step: 1064/530, loss: 0.01606837846338749
2023-01-22 15:44:50.159662: step: 1068/530, loss: 0.007236562669277191
2023-01-22 15:44:51.245086: step: 1072/530, loss: 0.0012436611577868462
2023-01-22 15:44:52.297007: step: 1076/530, loss: 0.01422815676778555
2023-01-22 15:44:53.348110: step: 1080/530, loss: 0.0030606589280068874
2023-01-22 15:44:54.389176: step: 1084/530, loss: 0.0028565924149006605
2023-01-22 15:44:55.474692: step: 1088/530, loss: 0.005879318807274103
2023-01-22 15:44:56.524400: step: 1092/530, loss: 0.001622932031750679
2023-01-22 15:44:57.596950: step: 1096/530, loss: 0.012155161239206791
2023-01-22 15:44:58.647008: step: 1100/530, loss: 0.018030766397714615
2023-01-22 15:44:59.703880: step: 1104/530, loss: 0.013453183695673943
2023-01-22 15:45:00.778386: step: 1108/530, loss: 0.004948226734995842
2023-01-22 15:45:01.841938: step: 1112/530, loss: 0.002874464727938175
2023-01-22 15:45:02.915674: step: 1116/530, loss: 0.050375789403915405
2023-01-22 15:45:03.973473: step: 1120/530, loss: 0.019457241520285606
2023-01-22 15:45:05.030719: step: 1124/530, loss: 0.04155614972114563
2023-01-22 15:45:06.111035: step: 1128/530, loss: 0.04811040684580803
2023-01-22 15:45:07.184061: step: 1132/530, loss: 0.005900775548070669
2023-01-22 15:45:08.250008: step: 1136/530, loss: 0.0046536545269191265
2023-01-22 15:45:09.321613: step: 1140/530, loss: 0.011202199384570122
2023-01-22 15:45:10.378635: step: 1144/530, loss: 0.0012106720823794603
2023-01-22 15:45:11.429874: step: 1148/530, loss: 0.008635424077510834
2023-01-22 15:45:12.480805: step: 1152/530, loss: 0.027918661013245583
2023-01-22 15:45:13.535908: step: 1156/530, loss: 0.04734714329242706
2023-01-22 15:45:14.612636: step: 1160/530, loss: 0.000833917991258204
2023-01-22 15:45:15.695504: step: 1164/530, loss: 0.011002247221767902
2023-01-22 15:45:16.745393: step: 1168/530, loss: 0.05000299960374832
2023-01-22 15:45:17.802265: step: 1172/530, loss: 0.005127518437802792
2023-01-22 15:45:18.861562: step: 1176/530, loss: 0.0029571533668786287
2023-01-22 15:45:19.928919: step: 1180/530, loss: 0.03149858117103577
2023-01-22 15:45:20.979124: step: 1184/530, loss: 0.002711329609155655
2023-01-22 15:45:22.028911: step: 1188/530, loss: 0.013199533335864544
2023-01-22 15:45:23.101874: step: 1192/530, loss: 0.015927262604236603
2023-01-22 15:45:24.154112: step: 1196/530, loss: 0.007734857499599457
2023-01-22 15:45:25.208641: step: 1200/530, loss: 0.018418120220303535
2023-01-22 15:45:26.257935: step: 1204/530, loss: 0.0024743482936173677
2023-01-22 15:45:27.318339: step: 1208/530, loss: 0.0034468930680304766
2023-01-22 15:45:28.379455: step: 1212/530, loss: 0.020393524318933487
2023-01-22 15:45:29.463165: step: 1216/530, loss: 0.01308753527700901
2023-01-22 15:45:30.531257: step: 1220/530, loss: 0.007994313724339008
2023-01-22 15:45:31.591202: step: 1224/530, loss: 0.0035022906959056854
2023-01-22 15:45:32.647627: step: 1228/530, loss: 0.010835937224328518
2023-01-22 15:45:33.698185: step: 1232/530, loss: 0.000707242579665035
2023-01-22 15:45:34.753399: step: 1236/530, loss: 0.005404041148722172
2023-01-22 15:45:35.819541: step: 1240/530, loss: 0.0065835705026984215
2023-01-22 15:45:36.881841: step: 1244/530, loss: 0.003519100369885564
2023-01-22 15:45:37.932048: step: 1248/530, loss: 0.005717897322028875
2023-01-22 15:45:38.984411: step: 1252/530, loss: 0.0008940945845097303
2023-01-22 15:45:40.040439: step: 1256/530, loss: 0.0010296402033418417
2023-01-22 15:45:41.104821: step: 1260/530, loss: 0.002223445102572441
2023-01-22 15:45:42.169274: step: 1264/530, loss: 0.02873888984322548
2023-01-22 15:45:43.244127: step: 1268/530, loss: 0.004704189021140337
2023-01-22 15:45:44.293563: step: 1272/530, loss: 0.04207101836800575
2023-01-22 15:45:45.369661: step: 1276/530, loss: 0.003507298184558749
2023-01-22 15:45:46.430593: step: 1280/530, loss: 0.004845779854804277
2023-01-22 15:45:47.514199: step: 1284/530, loss: 0.009277509525418282
2023-01-22 15:45:48.590995: step: 1288/530, loss: 0.001853696652688086
2023-01-22 15:45:49.653258: step: 1292/530, loss: 0.004756136331707239
2023-01-22 15:45:50.697926: step: 1296/530, loss: 0.011717579327523708
2023-01-22 15:45:51.748587: step: 1300/530, loss: 0.017659898847341537
2023-01-22 15:45:52.807764: step: 1304/530, loss: 0.03367912024259567
2023-01-22 15:45:53.871820: step: 1308/530, loss: 0.005786130670458078
2023-01-22 15:45:54.933228: step: 1312/530, loss: 0.0024127408396452665
2023-01-22 15:45:55.996258: step: 1316/530, loss: 0.008533951826393604
2023-01-22 15:45:57.064314: step: 1320/530, loss: 0.011065351776778698
2023-01-22 15:45:58.141139: step: 1324/530, loss: 0.001868952065706253
2023-01-22 15:45:59.210139: step: 1328/530, loss: 0.01387058012187481
2023-01-22 15:46:00.263764: step: 1332/530, loss: 0.001901100855320692
2023-01-22 15:46:01.308620: step: 1336/530, loss: 0.0005004171398468316
2023-01-22 15:46:02.395313: step: 1340/530, loss: 0.006409507244825363
2023-01-22 15:46:03.447339: step: 1344/530, loss: 0.0021359717939049006
2023-01-22 15:46:04.499454: step: 1348/530, loss: 0.002240303438156843
2023-01-22 15:46:05.567674: step: 1352/530, loss: 0.0023708504159003496
2023-01-22 15:46:06.634503: step: 1356/530, loss: 0.0002888084854930639
2023-01-22 15:46:07.700488: step: 1360/530, loss: 0.014817366376519203
2023-01-22 15:46:08.769380: step: 1364/530, loss: 0.029927879571914673
2023-01-22 15:46:09.836494: step: 1368/530, loss: 0.00268600438721478
2023-01-22 15:46:10.905126: step: 1372/530, loss: 0.01663109101355076
2023-01-22 15:46:11.965765: step: 1376/530, loss: 0.0
2023-01-22 15:46:13.030258: step: 1380/530, loss: 0.009185770526528358
2023-01-22 15:46:14.069642: step: 1384/530, loss: 0.010320502333343029
2023-01-22 15:46:15.152214: step: 1388/530, loss: 0.011841828003525734
2023-01-22 15:46:16.219312: step: 1392/530, loss: 0.001995900645852089
2023-01-22 15:46:17.281685: step: 1396/530, loss: 0.012550605461001396
2023-01-22 15:46:18.334447: step: 1400/530, loss: 0.03100932389497757
2023-01-22 15:46:19.403932: step: 1404/530, loss: 0.008636459708213806
2023-01-22 15:46:20.458735: step: 1408/530, loss: 0.01020064577460289
2023-01-22 15:46:21.540616: step: 1412/530, loss: 0.028234366327524185
2023-01-22 15:46:22.606706: step: 1416/530, loss: 0.010167238302528858
2023-01-22 15:46:23.685210: step: 1420/530, loss: 0.010518955998122692
2023-01-22 15:46:24.745576: step: 1424/530, loss: 0.005865598563104868
2023-01-22 15:46:25.799437: step: 1428/530, loss: 0.014418727718293667
2023-01-22 15:46:26.875495: step: 1432/530, loss: 0.004344608169049025
2023-01-22 15:46:27.937887: step: 1436/530, loss: 0.004507642239332199
2023-01-22 15:46:29.013674: step: 1440/530, loss: 0.004870147444307804
2023-01-22 15:46:30.076598: step: 1444/530, loss: 0.009045331738889217
2023-01-22 15:46:31.151812: step: 1448/530, loss: 0.030946195125579834
2023-01-22 15:46:32.224239: step: 1452/530, loss: 0.004933202639222145
2023-01-22 15:46:33.278425: step: 1456/530, loss: 0.01915445178747177
2023-01-22 15:46:34.344850: step: 1460/530, loss: 0.002927019027993083
2023-01-22 15:46:35.406157: step: 1464/530, loss: 0.004657906945794821
2023-01-22 15:46:36.466914: step: 1468/530, loss: 0.007095067761838436
2023-01-22 15:46:37.527248: step: 1472/530, loss: 0.003370932536199689
2023-01-22 15:46:38.586001: step: 1476/530, loss: 0.006741188932210207
2023-01-22 15:46:39.660095: step: 1480/530, loss: 0.013289038091897964
2023-01-22 15:46:40.721375: step: 1484/530, loss: 0.0026068103034049273
2023-01-22 15:46:41.790530: step: 1488/530, loss: 0.010774119757115841
2023-01-22 15:46:42.844123: step: 1492/530, loss: 0.02800523117184639
2023-01-22 15:46:43.911246: step: 1496/530, loss: 0.0021110419183969498
2023-01-22 15:46:44.979385: step: 1500/530, loss: 0.005094290245324373
2023-01-22 15:46:46.030997: step: 1504/530, loss: 0.0016411175020039082
2023-01-22 15:46:47.085499: step: 1508/530, loss: 0.006435022689402103
2023-01-22 15:46:48.144346: step: 1512/530, loss: 0.0038271802477538586
2023-01-22 15:46:49.198450: step: 1516/530, loss: 0.04329176992177963
2023-01-22 15:46:50.281253: step: 1520/530, loss: 0.008502860553562641
2023-01-22 15:46:51.340433: step: 1524/530, loss: 0.0012858954723924398
2023-01-22 15:46:52.390990: step: 1528/530, loss: 0.0023873939644545317
2023-01-22 15:46:53.447653: step: 1532/530, loss: 0.0034275217913091183
2023-01-22 15:46:54.509917: step: 1536/530, loss: 0.0029062544927001
2023-01-22 15:46:55.575077: step: 1540/530, loss: 0.006031538359820843
2023-01-22 15:46:56.645080: step: 1544/530, loss: 0.009023847058415413
2023-01-22 15:46:57.698269: step: 1548/530, loss: 0.005828891880810261
2023-01-22 15:46:58.763313: step: 1552/530, loss: 0.0025264055002480745
2023-01-22 15:46:59.824561: step: 1556/530, loss: 0.005130165256559849
2023-01-22 15:47:00.884668: step: 1560/530, loss: 0.006263383198529482
2023-01-22 15:47:01.953853: step: 1564/530, loss: 0.0036543160676956177
2023-01-22 15:47:03.068735: step: 1568/530, loss: 0.005106837954372168
2023-01-22 15:47:04.128296: step: 1572/530, loss: 0.009351509623229504
2023-01-22 15:47:05.178517: step: 1576/530, loss: 0.0005123890587128699
2023-01-22 15:47:06.247536: step: 1580/530, loss: 0.004762763623148203
2023-01-22 15:47:07.309705: step: 1584/530, loss: 0.011701364070177078
2023-01-22 15:47:08.370928: step: 1588/530, loss: 0.00974379200488329
2023-01-22 15:47:09.450126: step: 1592/530, loss: 0.01635259948670864
2023-01-22 15:47:10.514974: step: 1596/530, loss: 0.013899075798690319
2023-01-22 15:47:11.565688: step: 1600/530, loss: 0.004284922033548355
2023-01-22 15:47:12.624951: step: 1604/530, loss: 0.00440248055383563
2023-01-22 15:47:13.679013: step: 1608/530, loss: 0.005738194100558758
2023-01-22 15:47:14.733440: step: 1612/530, loss: 0.0051477085798978806
2023-01-22 15:47:15.806981: step: 1616/530, loss: 0.009126820601522923
2023-01-22 15:47:16.867467: step: 1620/530, loss: 0.005962767638266087
2023-01-22 15:47:17.947670: step: 1624/530, loss: 0.004526323173195124
2023-01-22 15:47:19.007117: step: 1628/530, loss: 0.0004168787563685328
2023-01-22 15:47:20.079564: step: 1632/530, loss: 0.003620957024395466
2023-01-22 15:47:21.143230: step: 1636/530, loss: 0.01084889005869627
2023-01-22 15:47:22.219794: step: 1640/530, loss: 0.002801034366711974
2023-01-22 15:47:23.266255: step: 1644/530, loss: 0.0
2023-01-22 15:47:24.317719: step: 1648/530, loss: 0.003452253295108676
2023-01-22 15:47:25.391164: step: 1652/530, loss: 0.007097299676388502
2023-01-22 15:47:26.466119: step: 1656/530, loss: 0.002154362155124545
2023-01-22 15:47:27.525635: step: 1660/530, loss: 0.018424391746520996
2023-01-22 15:47:28.612444: step: 1664/530, loss: 0.002080699661746621
2023-01-22 15:47:29.675408: step: 1668/530, loss: 0.005140418652445078
2023-01-22 15:47:30.751291: step: 1672/530, loss: 0.0026606512255966663
2023-01-22 15:47:31.809894: step: 1676/530, loss: 0.002993499394506216
2023-01-22 15:47:32.890155: step: 1680/530, loss: 0.007442861795425415
2023-01-22 15:47:33.953385: step: 1684/530, loss: 0.001975010382011533
2023-01-22 15:47:35.009657: step: 1688/530, loss: 0.0045084343291819096
2023-01-22 15:47:36.084496: step: 1692/530, loss: 0.0069546024315059185
2023-01-22 15:47:37.139972: step: 1696/530, loss: 0.0026663776952773333
2023-01-22 15:47:38.201188: step: 1700/530, loss: 0.018228016793727875
2023-01-22 15:47:39.259848: step: 1704/530, loss: 0.006329392082989216
2023-01-22 15:47:40.336623: step: 1708/530, loss: 0.015090257860720158
2023-01-22 15:47:41.374252: step: 1712/530, loss: 0.002329648472368717
2023-01-22 15:47:42.434202: step: 1716/530, loss: 0.0018962910398840904
2023-01-22 15:47:43.499834: step: 1720/530, loss: 0.0035224477760493755
2023-01-22 15:47:44.558726: step: 1724/530, loss: 0.02298874221742153
2023-01-22 15:47:45.617991: step: 1728/530, loss: 0.003752456046640873
2023-01-22 15:47:46.680606: step: 1732/530, loss: 8.231526589952409e-05
2023-01-22 15:47:47.740365: step: 1736/530, loss: 0.008032851852476597
2023-01-22 15:47:48.801445: step: 1740/530, loss: 0.003820925485342741
2023-01-22 15:47:49.866466: step: 1744/530, loss: 0.01569504290819168
2023-01-22 15:47:50.918608: step: 1748/530, loss: 0.01494849193841219
2023-01-22 15:47:51.991691: step: 1752/530, loss: 0.009397715330123901
2023-01-22 15:47:53.055088: step: 1756/530, loss: 0.007003241218626499
2023-01-22 15:47:54.099176: step: 1760/530, loss: 0.0
2023-01-22 15:47:55.146935: step: 1764/530, loss: 0.0054090735502541065
2023-01-22 15:47:56.203967: step: 1768/530, loss: 0.007713343482464552
2023-01-22 15:47:57.263161: step: 1772/530, loss: 0.02815413661301136
2023-01-22 15:47:58.311944: step: 1776/530, loss: 0.005441877990961075
2023-01-22 15:47:59.375539: step: 1780/530, loss: 0.0009378030081279576
2023-01-22 15:48:00.436250: step: 1784/530, loss: 0.0057209632359445095
2023-01-22 15:48:01.510629: step: 1788/530, loss: 0.008506428450345993
2023-01-22 15:48:02.563791: step: 1792/530, loss: 0.000548729149159044
2023-01-22 15:48:03.617326: step: 1796/530, loss: 0.0037240025121718645
2023-01-22 15:48:04.681109: step: 1800/530, loss: 0.02908029407262802
2023-01-22 15:48:05.734043: step: 1804/530, loss: 0.007563740015029907
2023-01-22 15:48:06.783378: step: 1808/530, loss: 0.0029163400176912546
2023-01-22 15:48:07.844702: step: 1812/530, loss: 0.000839012092910707
2023-01-22 15:48:08.908276: step: 1816/530, loss: 0.003897731890901923
2023-01-22 15:48:09.973249: step: 1820/530, loss: 0.011289495974779129
2023-01-22 15:48:11.028648: step: 1824/530, loss: 0.007079458795487881
2023-01-22 15:48:12.085376: step: 1828/530, loss: 0.0010993704199790955
2023-01-22 15:48:13.156345: step: 1832/530, loss: 0.005862667690962553
2023-01-22 15:48:14.223937: step: 1836/530, loss: 0.0045527806505560875
2023-01-22 15:48:15.279428: step: 1840/530, loss: 0.0007549830479547381
2023-01-22 15:48:16.353149: step: 1844/530, loss: 0.009025884792208672
2023-01-22 15:48:17.404259: step: 1848/530, loss: 0.013387002982199192
2023-01-22 15:48:18.464625: step: 1852/530, loss: 0.0036910264752805233
2023-01-22 15:48:19.525742: step: 1856/530, loss: 0.006511569023132324
2023-01-22 15:48:20.610836: step: 1860/530, loss: 0.005079867783933878
2023-01-22 15:48:21.671173: step: 1864/530, loss: 0.005769079085439444
2023-01-22 15:48:22.761298: step: 1868/530, loss: 0.007010573986917734
2023-01-22 15:48:23.837022: step: 1872/530, loss: 0.004105666186660528
2023-01-22 15:48:24.903676: step: 1876/530, loss: 0.006187903229147196
2023-01-22 15:48:25.961848: step: 1880/530, loss: 0.03970840945839882
2023-01-22 15:48:27.009146: step: 1884/530, loss: 0.012673421762883663
2023-01-22 15:48:28.060667: step: 1888/530, loss: 0.007877575233578682
2023-01-22 15:48:29.140634: step: 1892/530, loss: 0.00033618404995650053
2023-01-22 15:48:30.189438: step: 1896/530, loss: 0.0006555045256391168
2023-01-22 15:48:31.248201: step: 1900/530, loss: 0.019070345908403397
2023-01-22 15:48:32.329554: step: 1904/530, loss: 0.016332026571035385
2023-01-22 15:48:33.398843: step: 1908/530, loss: 0.002249857410788536
2023-01-22 15:48:34.452427: step: 1912/530, loss: 0.01717446930706501
2023-01-22 15:48:35.509900: step: 1916/530, loss: 0.02588737942278385
2023-01-22 15:48:36.568979: step: 1920/530, loss: 0.004456314258277416
2023-01-22 15:48:37.639964: step: 1924/530, loss: 0.019870944321155548
2023-01-22 15:48:38.698911: step: 1928/530, loss: 0.009163443930447102
2023-01-22 15:48:39.752806: step: 1932/530, loss: 0.007564948871731758
2023-01-22 15:48:40.819894: step: 1936/530, loss: 0.027656367048621178
2023-01-22 15:48:41.864141: step: 1940/530, loss: 0.013094200752675533
2023-01-22 15:48:42.930875: step: 1944/530, loss: 0.004170201253145933
2023-01-22 15:48:43.993313: step: 1948/530, loss: 0.012527740560472012
2023-01-22 15:48:45.062594: step: 1952/530, loss: 0.014081531204283237
2023-01-22 15:48:46.136468: step: 1956/530, loss: 0.04590287059545517
2023-01-22 15:48:47.196547: step: 1960/530, loss: 0.018450524657964706
2023-01-22 15:48:48.254867: step: 1964/530, loss: 0.0062479362823069096
2023-01-22 15:48:49.306950: step: 1968/530, loss: 0.003046920755878091
2023-01-22 15:48:50.363448: step: 1972/530, loss: 0.005486463662236929
2023-01-22 15:48:51.421269: step: 1976/530, loss: 0.0023590759374201298
2023-01-22 15:48:52.499508: step: 1980/530, loss: 0.008467772044241428
2023-01-22 15:48:53.554434: step: 1984/530, loss: 0.002321891952306032
2023-01-22 15:48:54.617323: step: 1988/530, loss: 0.002070195507258177
2023-01-22 15:48:55.673357: step: 1992/530, loss: 0.0007618216332048178
2023-01-22 15:48:56.737339: step: 1996/530, loss: 0.002311565214768052
2023-01-22 15:48:57.808414: step: 2000/530, loss: 0.020710498094558716
2023-01-22 15:48:58.888079: step: 2004/530, loss: 0.0038332317490130663
2023-01-22 15:48:59.958023: step: 2008/530, loss: 0.0010175377829000354
2023-01-22 15:49:01.019054: step: 2012/530, loss: 0.012994120828807354
2023-01-22 15:49:02.105154: step: 2016/530, loss: 0.0054857260547578335
2023-01-22 15:49:03.138705: step: 2020/530, loss: 0.007855881005525589
2023-01-22 15:49:04.195981: step: 2024/530, loss: 0.006128398701548576
2023-01-22 15:49:05.260884: step: 2028/530, loss: 0.005347241647541523
2023-01-22 15:49:06.331320: step: 2032/530, loss: 0.006799470167607069
2023-01-22 15:49:07.386049: step: 2036/530, loss: 0.003383493283763528
2023-01-22 15:49:08.440218: step: 2040/530, loss: 0.002997984178364277
2023-01-22 15:49:09.496721: step: 2044/530, loss: 0.004079834092408419
2023-01-22 15:49:10.570039: step: 2048/530, loss: 0.00022045538935344666
2023-01-22 15:49:11.635932: step: 2052/530, loss: 0.005013130605220795
2023-01-22 15:49:12.692702: step: 2056/530, loss: 0.010318366810679436
2023-01-22 15:49:13.757497: step: 2060/530, loss: 0.01189111452549696
2023-01-22 15:49:14.812884: step: 2064/530, loss: 0.012210406363010406
2023-01-22 15:49:15.866941: step: 2068/530, loss: 0.002377450466156006
2023-01-22 15:49:16.914661: step: 2072/530, loss: 2.3413569579133764e-05
2023-01-22 15:49:17.984447: step: 2076/530, loss: 0.0010762023739516735
2023-01-22 15:49:19.043855: step: 2080/530, loss: 0.0015593904536217451
2023-01-22 15:49:20.135084: step: 2084/530, loss: 0.007034834939986467
2023-01-22 15:49:21.198292: step: 2088/530, loss: 0.0084341149777174
2023-01-22 15:49:22.253511: step: 2092/530, loss: 0.0060415565967559814
2023-01-22 15:49:23.314944: step: 2096/530, loss: 0.01563962548971176
2023-01-22 15:49:24.379013: step: 2100/530, loss: 0.0489777997136116
2023-01-22 15:49:25.462436: step: 2104/530, loss: 0.0018306478159502149
2023-01-22 15:49:26.523615: step: 2108/530, loss: 0.0017658383585512638
2023-01-22 15:49:27.586391: step: 2112/530, loss: 0.00671767583116889
2023-01-22 15:49:28.642334: step: 2116/530, loss: 0.012136721052229404
2023-01-22 15:49:29.698176: step: 2120/530, loss: 0.013112825341522694
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3488341159379631, 'r': 0.2307439520143756, 'f1': 0.2777584831439331}, 'combined': 0.18421288001255665, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32009454120303177, 'r': 0.28917631847319347, 'f1': 0.3038509376195943}, 'combined': 0.2025672917463962, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3999148639040771, 'r': 0.32000108054608245, 'f1': 0.3555225844413949}, 'combined': 0.23202526563543663, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3180153810835629, 'r': 0.3385325024437928, 'f1': 0.3279533617424243}, 'combined': 0.24164984549441787, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35953322840941015, 'r': 0.3327627888914801, 'f1': 0.34563041472091677}, 'combined': 0.22922638903770642, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3517156862745098, 'r': 0.3416666666666666, 'f1': 0.34661835748792263}, 'combined': 0.23107890499194841, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5277777777777778, 'r': 0.41304347826086957, 'f1': 0.4634146341463415}, 'combined': 0.3089430894308943, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 7
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 15:52:01.096597: step: 4/530, loss: 0.012904105708003044
2023-01-22 15:52:02.155105: step: 8/530, loss: 0.005067820660769939
2023-01-22 15:52:03.197663: step: 12/530, loss: 0.015916386619210243
2023-01-22 15:52:04.247638: step: 16/530, loss: 0.0021385247819125652
2023-01-22 15:52:05.280627: step: 20/530, loss: 0.0002824341063387692
2023-01-22 15:52:06.349873: step: 24/530, loss: 0.004916571546345949
2023-01-22 15:52:07.414422: step: 28/530, loss: 0.003122350899502635
2023-01-22 15:52:08.466548: step: 32/530, loss: 0.0025584313552826643
2023-01-22 15:52:09.527465: step: 36/530, loss: 0.0014077366795390844
2023-01-22 15:52:10.570615: step: 40/530, loss: 0.0010288550984114408
2023-01-22 15:52:11.627734: step: 44/530, loss: 0.0017241687746718526
2023-01-22 15:52:12.667063: step: 48/530, loss: 0.0023961246479302645
2023-01-22 15:52:13.737626: step: 52/530, loss: 0.0018241873476654291
2023-01-22 15:52:14.801402: step: 56/530, loss: 0.017092470079660416
2023-01-22 15:52:15.860184: step: 60/530, loss: 0.0035566191654652357
2023-01-22 15:52:16.915831: step: 64/530, loss: 0.00324407871812582
2023-01-22 15:52:17.970667: step: 68/530, loss: 0.038889750838279724
2023-01-22 15:52:19.048076: step: 72/530, loss: 0.008168782107532024
2023-01-22 15:52:20.116749: step: 76/530, loss: 0.006335677113384008
2023-01-22 15:52:21.190494: step: 80/530, loss: 0.0049591949209570885
2023-01-22 15:52:22.240610: step: 84/530, loss: 0.011235124431550503
2023-01-22 15:52:23.319917: step: 88/530, loss: 0.01831236481666565
2023-01-22 15:52:24.381149: step: 92/530, loss: 0.002687113592401147
2023-01-22 15:52:25.451148: step: 96/530, loss: 0.0
2023-01-22 15:52:26.518891: step: 100/530, loss: 0.030802110210061073
2023-01-22 15:52:27.592051: step: 104/530, loss: 0.005285268183797598
2023-01-22 15:52:28.659066: step: 108/530, loss: 0.014542270451784134
2023-01-22 15:52:29.745873: step: 112/530, loss: 0.014644518494606018
2023-01-22 15:52:30.793535: step: 116/530, loss: 0.00613078847527504
2023-01-22 15:52:31.852769: step: 120/530, loss: 0.00600211089476943
2023-01-22 15:52:32.911191: step: 124/530, loss: 0.014048912562429905
2023-01-22 15:52:33.966682: step: 128/530, loss: 0.0056924158707261086
2023-01-22 15:52:35.026557: step: 132/530, loss: 0.001396678388118744
2023-01-22 15:52:36.086912: step: 136/530, loss: 0.008538402616977692
2023-01-22 15:52:37.153355: step: 140/530, loss: 0.003192254574969411
2023-01-22 15:52:38.211923: step: 144/530, loss: 0.0006173851434141397
2023-01-22 15:52:39.300931: step: 148/530, loss: 0.0032596508972346783
2023-01-22 15:52:40.345775: step: 152/530, loss: 0.0031438961159437895
2023-01-22 15:52:41.424031: step: 156/530, loss: 0.0072922599501907825
2023-01-22 15:52:42.503162: step: 160/530, loss: 0.008476948365569115
2023-01-22 15:52:43.567204: step: 164/530, loss: 0.0038286589551717043
2023-01-22 15:52:44.661800: step: 168/530, loss: 0.0012812173226848245
2023-01-22 15:52:45.721472: step: 172/530, loss: 0.004581693094223738
2023-01-22 15:52:46.790894: step: 176/530, loss: 0.0022015050053596497
2023-01-22 15:52:47.850047: step: 180/530, loss: 0.001324501819908619
2023-01-22 15:52:48.898817: step: 184/530, loss: 0.001952095190063119
2023-01-22 15:52:49.959794: step: 188/530, loss: 0.007655243389308453
2023-01-22 15:52:51.018514: step: 192/530, loss: 0.0010749392677098513
2023-01-22 15:52:52.077982: step: 196/530, loss: 0.01239064708352089
2023-01-22 15:52:53.150073: step: 200/530, loss: 0.003231559181585908
2023-01-22 15:52:54.224331: step: 204/530, loss: 0.006389062386006117
2023-01-22 15:52:55.291941: step: 208/530, loss: 0.004245605319738388
2023-01-22 15:52:56.366348: step: 212/530, loss: 0.004515692126005888
2023-01-22 15:52:57.426555: step: 216/530, loss: 0.004583229776471853
2023-01-22 15:52:58.497915: step: 220/530, loss: 0.007102194242179394
2023-01-22 15:52:59.566785: step: 224/530, loss: 0.006297165062278509
2023-01-22 15:53:00.638003: step: 228/530, loss: 0.009628817439079285
2023-01-22 15:53:01.707739: step: 232/530, loss: 0.006603987887501717
2023-01-22 15:53:02.809795: step: 236/530, loss: 0.010194784961640835
2023-01-22 15:53:03.868314: step: 240/530, loss: 0.008824080228805542
2023-01-22 15:53:04.921326: step: 244/530, loss: 0.01042764913290739
2023-01-22 15:53:05.979774: step: 248/530, loss: 0.004633546806871891
2023-01-22 15:53:07.051934: step: 252/530, loss: 0.010123567655682564
2023-01-22 15:53:08.124201: step: 256/530, loss: 0.020633762702345848
2023-01-22 15:53:09.184245: step: 260/530, loss: 0.0023980350233614445
2023-01-22 15:53:10.239843: step: 264/530, loss: 0.0012815964873880148
2023-01-22 15:53:11.304267: step: 268/530, loss: 0.010310189798474312
2023-01-22 15:53:12.371319: step: 272/530, loss: 0.002342581283301115
2023-01-22 15:53:13.450564: step: 276/530, loss: 0.0034466953948140144
2023-01-22 15:53:14.520461: step: 280/530, loss: 0.002751181134954095
2023-01-22 15:53:15.592689: step: 284/530, loss: 0.004417013842612505
2023-01-22 15:53:16.649949: step: 288/530, loss: 0.005342142190784216
2023-01-22 15:53:17.712506: step: 292/530, loss: 0.005873918998986483
2023-01-22 15:53:18.774324: step: 296/530, loss: 0.011275001801550388
2023-01-22 15:53:19.842052: step: 300/530, loss: 0.011495187878608704
2023-01-22 15:53:20.901258: step: 304/530, loss: 0.009805244393646717
2023-01-22 15:53:21.983553: step: 308/530, loss: 0.003248715540394187
2023-01-22 15:53:23.038841: step: 312/530, loss: 0.0065356031991541386
2023-01-22 15:53:24.115963: step: 316/530, loss: 0.003382806433364749
2023-01-22 15:53:25.175993: step: 320/530, loss: 0.00671713100746274
2023-01-22 15:53:26.255827: step: 324/530, loss: 0.0053423685021698475
2023-01-22 15:53:27.331576: step: 328/530, loss: 0.001692821504548192
2023-01-22 15:53:28.395764: step: 332/530, loss: 0.012422880157828331
2023-01-22 15:53:29.454182: step: 336/530, loss: 0.001950218342244625
2023-01-22 15:53:30.526734: step: 340/530, loss: 0.0024267653934657574
2023-01-22 15:53:31.595309: step: 344/530, loss: 0.005435770843178034
2023-01-22 15:53:32.667697: step: 348/530, loss: 0.022459276020526886
2023-01-22 15:53:33.732804: step: 352/530, loss: 0.0018614979926496744
2023-01-22 15:53:34.807804: step: 356/530, loss: 0.0009028096683323383
2023-01-22 15:53:35.861833: step: 360/530, loss: 0.002556337509304285
2023-01-22 15:53:36.918416: step: 364/530, loss: 0.0510033443570137
2023-01-22 15:53:37.985540: step: 368/530, loss: 0.0023674292024224997
2023-01-22 15:53:39.049473: step: 372/530, loss: 0.05592985451221466
2023-01-22 15:53:40.116845: step: 376/530, loss: 0.0016794638941064477
2023-01-22 15:53:41.184966: step: 380/530, loss: 0.024966318160295486
2023-01-22 15:53:42.273619: step: 384/530, loss: 0.0001337281719315797
2023-01-22 15:53:43.339098: step: 388/530, loss: 0.0019478683825582266
2023-01-22 15:53:44.416235: step: 392/530, loss: 0.004590095020830631
2023-01-22 15:53:45.488038: step: 396/530, loss: 0.01947448030114174
2023-01-22 15:53:46.542579: step: 400/530, loss: 0.015301542356610298
2023-01-22 15:53:47.620403: step: 404/530, loss: 0.035488683730363846
2023-01-22 15:53:48.679131: step: 408/530, loss: 0.0064904834143817425
2023-01-22 15:53:49.742827: step: 412/530, loss: 0.011119185015559196
2023-01-22 15:53:50.812383: step: 416/530, loss: 0.003027132246643305
2023-01-22 15:53:51.887719: step: 420/530, loss: 0.003070536069571972
2023-01-22 15:53:52.952400: step: 424/530, loss: 0.0030290079303085804
2023-01-22 15:53:54.004554: step: 428/530, loss: 0.0005432139150798321
2023-01-22 15:53:55.067905: step: 432/530, loss: 0.021225526928901672
2023-01-22 15:53:56.139862: step: 436/530, loss: 0.00808823574334383
2023-01-22 15:53:57.196729: step: 440/530, loss: 0.008005386218428612
2023-01-22 15:53:58.266762: step: 444/530, loss: 0.009824836626648903
2023-01-22 15:53:59.318609: step: 448/530, loss: 0.0042246426455676556
2023-01-22 15:54:00.398474: step: 452/530, loss: 0.031005358323454857
2023-01-22 15:54:01.451368: step: 456/530, loss: 0.03189140185713768
2023-01-22 15:54:02.505792: step: 460/530, loss: 0.001855664188042283
2023-01-22 15:54:03.569108: step: 464/530, loss: 0.005303407087922096
2023-01-22 15:54:04.632429: step: 468/530, loss: 0.05523635819554329
2023-01-22 15:54:05.712243: step: 472/530, loss: 0.012483274564146996
2023-01-22 15:54:06.773117: step: 476/530, loss: 0.008177315816283226
2023-01-22 15:54:07.839205: step: 480/530, loss: 0.015551341697573662
2023-01-22 15:54:08.917352: step: 484/530, loss: 0.00317129073664546
2023-01-22 15:54:10.006770: step: 488/530, loss: 0.001939623849466443
2023-01-22 15:54:11.048069: step: 492/530, loss: 0.0018678940832614899
2023-01-22 15:54:12.102506: step: 496/530, loss: 0.009696511551737785
2023-01-22 15:54:13.142802: step: 500/530, loss: 0.003025406738743186
2023-01-22 15:54:14.191521: step: 504/530, loss: 0.00014251504035200924
2023-01-22 15:54:15.260086: step: 508/530, loss: 0.0023462758399546146
2023-01-22 15:54:16.312483: step: 512/530, loss: 0.027908792719244957
2023-01-22 15:54:17.384533: step: 516/530, loss: 0.007968349382281303
2023-01-22 15:54:18.447407: step: 520/530, loss: 0.0037046605721116066
2023-01-22 15:54:19.507876: step: 524/530, loss: 0.0023662070743739605
2023-01-22 15:54:20.561541: step: 528/530, loss: 0.0029715863056480885
2023-01-22 15:54:21.620003: step: 532/530, loss: 0.04702230542898178
2023-01-22 15:54:22.674675: step: 536/530, loss: 0.00636184262111783
2023-01-22 15:54:23.727585: step: 540/530, loss: 3.735798236448318e-05
2023-01-22 15:54:24.803941: step: 544/530, loss: 0.006046726834028959
2023-01-22 15:54:25.880428: step: 548/530, loss: 0.006030308548361063
2023-01-22 15:54:26.942548: step: 552/530, loss: 0.007691062521189451
2023-01-22 15:54:28.022939: step: 556/530, loss: 0.02658338099718094
2023-01-22 15:54:29.088473: step: 560/530, loss: 0.036318786442279816
2023-01-22 15:54:30.155145: step: 564/530, loss: 0.004370391834527254
2023-01-22 15:54:31.209610: step: 568/530, loss: 0.0057694693095982075
2023-01-22 15:54:32.287609: step: 572/530, loss: 0.003114042803645134
2023-01-22 15:54:33.362940: step: 576/530, loss: 0.0017646457999944687
2023-01-22 15:54:34.429621: step: 580/530, loss: 0.003796191653236747
2023-01-22 15:54:35.496500: step: 584/530, loss: 0.006735880393534899
2023-01-22 15:54:36.556961: step: 588/530, loss: 0.010164310224354267
2023-01-22 15:54:37.619998: step: 592/530, loss: 0.00375041039660573
2023-01-22 15:54:38.671370: step: 596/530, loss: 0.0026225331239402294
2023-01-22 15:54:39.731074: step: 600/530, loss: 0.050829388201236725
2023-01-22 15:54:40.797607: step: 604/530, loss: 0.024402683600783348
2023-01-22 15:54:41.855818: step: 608/530, loss: 0.0009690559236332774
2023-01-22 15:54:42.914864: step: 612/530, loss: 0.006643539760261774
2023-01-22 15:54:43.959732: step: 616/530, loss: 0.012132334522902966
2023-01-22 15:54:45.029847: step: 620/530, loss: 0.0003877042618114501
2023-01-22 15:54:46.082120: step: 624/530, loss: 0.0047241211868822575
2023-01-22 15:54:47.126688: step: 628/530, loss: 4.4548753066919744e-05
2023-01-22 15:54:48.181260: step: 632/530, loss: 0.0058892713859677315
2023-01-22 15:54:49.248908: step: 636/530, loss: 0.0022245515137910843
2023-01-22 15:54:50.295086: step: 640/530, loss: 0.004287480376660824
2023-01-22 15:54:51.347574: step: 644/530, loss: 0.003160599386319518
2023-01-22 15:54:52.400812: step: 648/530, loss: 0.0025158494245260954
2023-01-22 15:54:53.464793: step: 652/530, loss: 0.009907666593790054
2023-01-22 15:54:54.518150: step: 656/530, loss: 0.0027273886371403933
2023-01-22 15:54:55.577255: step: 660/530, loss: 0.001808274770155549
2023-01-22 15:54:56.628098: step: 664/530, loss: 0.005245785228908062
2023-01-22 15:54:57.695492: step: 668/530, loss: 0.004788743332028389
2023-01-22 15:54:58.769632: step: 672/530, loss: 0.018536105751991272
2023-01-22 15:54:59.827813: step: 676/530, loss: 0.007577091455459595
2023-01-22 15:55:00.877428: step: 680/530, loss: 0.0031659400556236506
2023-01-22 15:55:01.927304: step: 684/530, loss: 0.005192521959543228
2023-01-22 15:55:02.976198: step: 688/530, loss: 0.005204837769269943
2023-01-22 15:55:04.048975: step: 692/530, loss: 0.008573825471103191
2023-01-22 15:55:05.089290: step: 696/530, loss: 0.005474900361150503
2023-01-22 15:55:06.129113: step: 700/530, loss: 0.0
2023-01-22 15:55:07.193306: step: 704/530, loss: 0.015217592008411884
2023-01-22 15:55:08.238561: step: 708/530, loss: 0.009809939190745354
2023-01-22 15:55:09.284294: step: 712/530, loss: 0.00041440516361035407
2023-01-22 15:55:10.341442: step: 716/530, loss: 0.02617962658405304
2023-01-22 15:55:11.386981: step: 720/530, loss: 0.0044184052385389805
2023-01-22 15:55:12.427926: step: 724/530, loss: 0.011346045881509781
2023-01-22 15:55:13.491672: step: 728/530, loss: 0.001319524715654552
2023-01-22 15:55:14.544516: step: 732/530, loss: 0.0015738967340439558
2023-01-22 15:55:15.597368: step: 736/530, loss: 0.008715679869055748
2023-01-22 15:55:16.637958: step: 740/530, loss: 0.007780200801789761
2023-01-22 15:55:17.690754: step: 744/530, loss: 0.005790016148239374
2023-01-22 15:55:18.745787: step: 748/530, loss: 0.01184441801160574
2023-01-22 15:55:19.812958: step: 752/530, loss: 0.003115267725661397
2023-01-22 15:55:20.863259: step: 756/530, loss: 0.005785453598946333
2023-01-22 15:55:21.926774: step: 760/530, loss: 0.002017201855778694
2023-01-22 15:55:22.982643: step: 764/530, loss: 0.012541850097477436
2023-01-22 15:55:24.036088: step: 768/530, loss: 0.0011365872342139482
2023-01-22 15:55:25.100922: step: 772/530, loss: 0.0036238234024494886
2023-01-22 15:55:26.180527: step: 776/530, loss: 0.001991682220250368
2023-01-22 15:55:27.240147: step: 780/530, loss: 0.0025727893225848675
2023-01-22 15:55:28.308811: step: 784/530, loss: 0.01745470240712166
2023-01-22 15:55:29.369747: step: 788/530, loss: 0.009576544165611267
2023-01-22 15:55:30.429777: step: 792/530, loss: 0.04621589183807373
2023-01-22 15:55:31.476356: step: 796/530, loss: 0.0475594699382782
2023-01-22 15:55:32.564318: step: 800/530, loss: 0.03216009587049484
2023-01-22 15:55:33.615374: step: 804/530, loss: 0.004361926577985287
2023-01-22 15:55:34.667311: step: 808/530, loss: 0.0081463772803545
2023-01-22 15:55:35.728166: step: 812/530, loss: 0.004009263124316931
2023-01-22 15:55:36.797115: step: 816/530, loss: 0.010621353052556515
2023-01-22 15:55:37.866447: step: 820/530, loss: 0.006909035611897707
2023-01-22 15:55:38.933182: step: 824/530, loss: 0.02500341273844242
2023-01-22 15:55:39.997253: step: 828/530, loss: 0.0038473554886877537
2023-01-22 15:55:41.064754: step: 832/530, loss: 0.04069630801677704
2023-01-22 15:55:42.112997: step: 836/530, loss: 0.00748397596180439
2023-01-22 15:55:43.172777: step: 840/530, loss: 0.005101094022393227
2023-01-22 15:55:44.216163: step: 844/530, loss: 0.001419269130565226
2023-01-22 15:55:45.255685: step: 848/530, loss: 0.003133500926196575
2023-01-22 15:55:46.312633: step: 852/530, loss: 0.002805163152515888
2023-01-22 15:55:47.373710: step: 856/530, loss: 0.05616255849599838
2023-01-22 15:55:48.440686: step: 860/530, loss: 0.0016153290634974837
2023-01-22 15:55:49.505707: step: 864/530, loss: 0.010885132476687431
2023-01-22 15:55:50.560161: step: 868/530, loss: 0.0019322059815749526
2023-01-22 15:55:51.625835: step: 872/530, loss: 0.018347369506955147
2023-01-22 15:55:52.682155: step: 876/530, loss: 0.001710647949948907
2023-01-22 15:55:53.733389: step: 880/530, loss: 0.01850125752389431
2023-01-22 15:55:54.806533: step: 884/530, loss: 0.006420777644962072
2023-01-22 15:55:55.875776: step: 888/530, loss: 0.0037274400237947702
2023-01-22 15:55:56.934543: step: 892/530, loss: 0.005759004037827253
2023-01-22 15:55:58.002384: step: 896/530, loss: 0.00858496967703104
2023-01-22 15:55:59.054451: step: 900/530, loss: 0.002263988833874464
2023-01-22 15:56:00.123055: step: 904/530, loss: 0.004606558941304684
2023-01-22 15:56:01.173303: step: 908/530, loss: 0.011999404057860374
2023-01-22 15:56:02.218271: step: 912/530, loss: 0.00040746081504039466
2023-01-22 15:56:03.286954: step: 916/530, loss: 0.012960116378962994
2023-01-22 15:56:04.364297: step: 920/530, loss: 0.010739731602370739
2023-01-22 15:56:05.424242: step: 924/530, loss: 0.0057163783349096775
2023-01-22 15:56:06.481624: step: 928/530, loss: 0.013862252235412598
2023-01-22 15:56:07.551007: step: 932/530, loss: 0.00449756346642971
2023-01-22 15:56:08.610997: step: 936/530, loss: 0.009259038604795933
2023-01-22 15:56:09.664556: step: 940/530, loss: 0.0039864107966423035
2023-01-22 15:56:10.703817: step: 944/530, loss: 0.007436931598931551
2023-01-22 15:56:11.766345: step: 948/530, loss: 0.007982431910932064
2023-01-22 15:56:12.821523: step: 952/530, loss: 0.007112680934369564
2023-01-22 15:56:13.869405: step: 956/530, loss: 0.0008695446304045618
2023-01-22 15:56:14.912200: step: 960/530, loss: 0.009062324650585651
2023-01-22 15:56:15.961555: step: 964/530, loss: 0.006572019774466753
2023-01-22 15:56:17.022481: step: 968/530, loss: 0.0035677673295140266
2023-01-22 15:56:18.087044: step: 972/530, loss: 0.00997459888458252
2023-01-22 15:56:19.140367: step: 976/530, loss: 0.0007607873412780464
2023-01-22 15:56:20.196892: step: 980/530, loss: 2.6377915673947427e-06
2023-01-22 15:56:21.257801: step: 984/530, loss: 0.017499951645731926
2023-01-22 15:56:22.327492: step: 988/530, loss: 0.00032129904138855636
2023-01-22 15:56:23.370245: step: 992/530, loss: 0.0006807407480664551
2023-01-22 15:56:24.427424: step: 996/530, loss: 0.0020977805834263563
2023-01-22 15:56:25.487814: step: 1000/530, loss: 0.0011637582210823894
2023-01-22 15:56:26.529821: step: 1004/530, loss: 0.016961470246315002
2023-01-22 15:56:27.583645: step: 1008/530, loss: 0.0008916959050111473
2023-01-22 15:56:28.628057: step: 1012/530, loss: 0.003647858975455165
2023-01-22 15:56:29.679883: step: 1016/530, loss: 0.006677701137959957
2023-01-22 15:56:30.728468: step: 1020/530, loss: 0.008406870067119598
2023-01-22 15:56:31.791463: step: 1024/530, loss: 0.006686127278953791
2023-01-22 15:56:32.886870: step: 1028/530, loss: 0.013231586664915085
2023-01-22 15:56:33.971444: step: 1032/530, loss: 0.0056766970083117485
2023-01-22 15:56:35.030449: step: 1036/530, loss: 0.0028293116483837366
2023-01-22 15:56:36.101182: step: 1040/530, loss: 0.0027113750111311674
2023-01-22 15:56:37.148102: step: 1044/530, loss: 0.002102357568219304
2023-01-22 15:56:38.207694: step: 1048/530, loss: 0.01977359689772129
2023-01-22 15:56:39.268986: step: 1052/530, loss: 0.005200549028813839
2023-01-22 15:56:40.312719: step: 1056/530, loss: 0.006588608957827091
2023-01-22 15:56:41.352951: step: 1060/530, loss: 0.00048009876627475023
2023-01-22 15:56:42.409011: step: 1064/530, loss: 0.002921079285442829
2023-01-22 15:56:43.472258: step: 1068/530, loss: 0.011613957583904266
2023-01-22 15:56:44.550054: step: 1072/530, loss: 0.03153498098254204
2023-01-22 15:56:45.618001: step: 1076/530, loss: 0.0016926953103393316
2023-01-22 15:56:46.676909: step: 1080/530, loss: 0.0016742394072934985
2023-01-22 15:56:47.734763: step: 1084/530, loss: 0.0006963239284232259
2023-01-22 15:56:48.804157: step: 1088/530, loss: 0.004912762902677059
2023-01-22 15:56:49.863135: step: 1092/530, loss: 0.005121821537613869
2023-01-22 15:56:50.916634: step: 1096/530, loss: 0.006460888776928186
2023-01-22 15:56:51.975122: step: 1100/530, loss: 0.009416701272130013
2023-01-22 15:56:53.026699: step: 1104/530, loss: 0.004715762101113796
2023-01-22 15:56:54.086980: step: 1108/530, loss: 0.005383270792663097
2023-01-22 15:56:55.144834: step: 1112/530, loss: 0.00024060183204710484
2023-01-22 15:56:56.200785: step: 1116/530, loss: 0.015338758006691933
2023-01-22 15:56:57.254448: step: 1120/530, loss: 0.006366773042827845
2023-01-22 15:56:58.319360: step: 1124/530, loss: 0.008398651145398617
2023-01-22 15:56:59.374763: step: 1128/530, loss: 0.024653512984514236
2023-01-22 15:57:00.405357: step: 1132/530, loss: 0.022243818268179893
2023-01-22 15:57:01.460308: step: 1136/530, loss: 0.02027847059071064
2023-01-22 15:57:02.542739: step: 1140/530, loss: 0.015282757580280304
2023-01-22 15:57:03.580397: step: 1144/530, loss: 0.002276965416967869
2023-01-22 15:57:04.654624: step: 1148/530, loss: 0.006992966402322054
2023-01-22 15:57:05.705363: step: 1152/530, loss: 0.018796036019921303
2023-01-22 15:57:06.753926: step: 1156/530, loss: 0.02710900828242302
2023-01-22 15:57:07.829658: step: 1160/530, loss: 0.0007463073707185686
2023-01-22 15:57:08.889940: step: 1164/530, loss: 0.008168252184987068
2023-01-22 15:57:09.948361: step: 1168/530, loss: 9.817934187594801e-05
2023-01-22 15:57:11.008093: step: 1172/530, loss: 0.0032565046567469835
2023-01-22 15:57:12.061708: step: 1176/530, loss: 0.002056768862530589
2023-01-22 15:57:13.133315: step: 1180/530, loss: 0.007122029550373554
2023-01-22 15:57:14.175838: step: 1184/530, loss: 0.02258075401186943
2023-01-22 15:57:15.231670: step: 1188/530, loss: 0.005497555714100599
2023-01-22 15:57:16.303277: step: 1192/530, loss: 0.004634596407413483
2023-01-22 15:57:17.354815: step: 1196/530, loss: 0.013754631392657757
2023-01-22 15:57:18.413779: step: 1200/530, loss: 0.0027307530399411917
2023-01-22 15:57:19.476083: step: 1204/530, loss: 0.010373775847256184
2023-01-22 15:57:20.526406: step: 1208/530, loss: 0.005817357916384935
2023-01-22 15:57:21.596728: step: 1212/530, loss: 0.006713941227644682
2023-01-22 15:57:22.657025: step: 1216/530, loss: 0.0033358752261847258
2023-01-22 15:57:23.710386: step: 1220/530, loss: 0.03016490489244461
2023-01-22 15:57:24.764117: step: 1224/530, loss: 0.0023159629199653864
2023-01-22 15:57:25.838271: step: 1228/530, loss: 0.0030180870089679956
2023-01-22 15:57:26.877457: step: 1232/530, loss: 0.0021962819155305624
2023-01-22 15:57:27.923627: step: 1236/530, loss: 0.0034712275955826044
2023-01-22 15:57:28.963427: step: 1240/530, loss: 0.00037702632835134864
2023-01-22 15:57:30.031210: step: 1244/530, loss: 0.0068137929774820805
2023-01-22 15:57:31.086436: step: 1248/530, loss: 0.0032415043096989393
2023-01-22 15:57:32.169624: step: 1252/530, loss: 0.0017898931400850415
2023-01-22 15:57:33.218972: step: 1256/530, loss: 0.008937662467360497
2023-01-22 15:57:34.278814: step: 1260/530, loss: 0.0034522786736488342
2023-01-22 15:57:35.338169: step: 1264/530, loss: 0.005720811430364847
2023-01-22 15:57:36.406806: step: 1268/530, loss: 0.0021059010177850723
2023-01-22 15:57:37.465674: step: 1272/530, loss: 0.007279111072421074
2023-01-22 15:57:38.524140: step: 1276/530, loss: 0.0011908162850886583
2023-01-22 15:57:39.569220: step: 1280/530, loss: 0.008065180853009224
2023-01-22 15:57:40.633493: step: 1284/530, loss: 0.0037832267116755247
2023-01-22 15:57:41.690270: step: 1288/530, loss: 0.0033239414915442467
2023-01-22 15:57:42.749668: step: 1292/530, loss: 0.0021119078155606985
2023-01-22 15:57:43.791912: step: 1296/530, loss: 0.0018069943180307746
2023-01-22 15:57:44.845059: step: 1300/530, loss: 0.006026848219335079
2023-01-22 15:57:45.901599: step: 1304/530, loss: 0.028940873220562935
2023-01-22 15:57:46.960721: step: 1308/530, loss: 0.008290654048323631
2023-01-22 15:57:48.000539: step: 1312/530, loss: 0.002408804837614298
2023-01-22 15:57:49.063852: step: 1316/530, loss: 0.0018591956468299031
2023-01-22 15:57:50.135645: step: 1320/530, loss: 0.010862033814191818
2023-01-22 15:57:51.217825: step: 1324/530, loss: 0.004676288925111294
2023-01-22 15:57:52.253786: step: 1328/530, loss: 0.0024421392008662224
2023-01-22 15:57:53.307362: step: 1332/530, loss: 0.03992559388279915
2023-01-22 15:57:54.374878: step: 1336/530, loss: 0.01180842611938715
2023-01-22 15:57:55.415102: step: 1340/530, loss: 0.0010115193435922265
2023-01-22 15:57:56.482898: step: 1344/530, loss: 0.004760029260069132
2023-01-22 15:57:57.565947: step: 1348/530, loss: 0.016330109909176826
2023-01-22 15:57:58.617023: step: 1352/530, loss: 0.003918833564966917
2023-01-22 15:57:59.685707: step: 1356/530, loss: 0.0017765170196071267
2023-01-22 15:58:00.742974: step: 1360/530, loss: 0.002537443535402417
2023-01-22 15:58:01.798402: step: 1364/530, loss: 7.210003968793899e-05
2023-01-22 15:58:02.867029: step: 1368/530, loss: 0.004111791029572487
2023-01-22 15:58:03.928396: step: 1372/530, loss: 0.0003961895708926022
2023-01-22 15:58:04.973975: step: 1376/530, loss: 0.0004833767598029226
2023-01-22 15:58:06.040334: step: 1380/530, loss: 0.017606612294912338
2023-01-22 15:58:07.104770: step: 1384/530, loss: 0.008703544735908508
2023-01-22 15:58:08.172403: step: 1388/530, loss: 0.06903694570064545
2023-01-22 15:58:09.234103: step: 1392/530, loss: 0.0013172316830605268
2023-01-22 15:58:10.291591: step: 1396/530, loss: 0.01568344421684742
2023-01-22 15:58:11.349409: step: 1400/530, loss: 0.0026344992220401764
2023-01-22 15:58:12.421027: step: 1404/530, loss: 0.0025941431522369385
2023-01-22 15:58:13.479544: step: 1408/530, loss: 0.0031603167299181223
2023-01-22 15:58:14.532642: step: 1412/530, loss: 0.002356140874326229
2023-01-22 15:58:15.591003: step: 1416/530, loss: 0.0015014453092589974
2023-01-22 15:58:16.657981: step: 1420/530, loss: 0.005683632101863623
2023-01-22 15:58:17.716922: step: 1424/530, loss: 0.010207446292042732
2023-01-22 15:58:18.785728: step: 1428/530, loss: 0.02254438027739525
2023-01-22 15:58:19.841855: step: 1432/530, loss: 0.002547829644754529
2023-01-22 15:58:20.899506: step: 1436/530, loss: 0.007191289681941271
2023-01-22 15:58:21.959400: step: 1440/530, loss: 0.005497679114341736
2023-01-22 15:58:23.020228: step: 1444/530, loss: 0.007208880037069321
2023-01-22 15:58:24.079473: step: 1448/530, loss: 0.002145032398402691
2023-01-22 15:58:25.158137: step: 1452/530, loss: 0.018444523215293884
2023-01-22 15:58:26.209085: step: 1456/530, loss: 0.008600176312029362
2023-01-22 15:58:27.274300: step: 1460/530, loss: 0.0028127594850957394
2023-01-22 15:58:28.336849: step: 1464/530, loss: 0.0006874918472021818
2023-01-22 15:58:29.416322: step: 1468/530, loss: 0.0009059992735274136
2023-01-22 15:58:30.485259: step: 1472/530, loss: 0.0056143710389733315
2023-01-22 15:58:31.566461: step: 1476/530, loss: 0.006656808778643608
2023-01-22 15:58:32.636676: step: 1480/530, loss: 0.010336926206946373
2023-01-22 15:58:33.690745: step: 1484/530, loss: 0.028912924230098724
2023-01-22 15:58:34.753810: step: 1488/530, loss: 0.0036904446315020323
2023-01-22 15:58:35.804152: step: 1492/530, loss: 0.0042575360275805
2023-01-22 15:58:36.874607: step: 1496/530, loss: 0.01029388327151537
2023-01-22 15:58:37.942696: step: 1500/530, loss: 0.026503583416342735
2023-01-22 15:58:39.018531: step: 1504/530, loss: 0.00550204748287797
2023-01-22 15:58:40.075162: step: 1508/530, loss: 0.001588418148458004
2023-01-22 15:58:41.136710: step: 1512/530, loss: 0.008536091074347496
2023-01-22 15:58:42.178380: step: 1516/530, loss: 0.006836900487542152
2023-01-22 15:58:43.233014: step: 1520/530, loss: 0.005467474926263094
2023-01-22 15:58:44.305033: step: 1524/530, loss: 0.01290533784776926
2023-01-22 15:58:45.354334: step: 1528/530, loss: 0.0031274205539375544
2023-01-22 15:58:46.419886: step: 1532/530, loss: 0.006203757598996162
2023-01-22 15:58:47.466681: step: 1536/530, loss: 0.00351705146022141
2023-01-22 15:58:48.517102: step: 1540/530, loss: 0.005592579487711191
2023-01-22 15:58:49.570226: step: 1544/530, loss: 0.01513136737048626
2023-01-22 15:58:50.624814: step: 1548/530, loss: 0.01994616910815239
2023-01-22 15:58:51.678476: step: 1552/530, loss: 0.02527095191180706
2023-01-22 15:58:52.745319: step: 1556/530, loss: 0.07543681561946869
2023-01-22 15:58:53.802367: step: 1560/530, loss: 0.005595947150141001
2023-01-22 15:58:54.869742: step: 1564/530, loss: 0.0009166815434582531
2023-01-22 15:58:55.927856: step: 1568/530, loss: 0.013642624020576477
2023-01-22 15:58:56.982523: step: 1572/530, loss: 0.022438788786530495
2023-01-22 15:58:58.040375: step: 1576/530, loss: 0.0005717214662581682
2023-01-22 15:58:59.104255: step: 1580/530, loss: 0.005219507496803999
2023-01-22 15:59:00.170859: step: 1584/530, loss: 0.005995392799377441
2023-01-22 15:59:01.213852: step: 1588/530, loss: 0.01081122923642397
2023-01-22 15:59:02.314877: step: 1592/530, loss: 0.004115510266274214
2023-01-22 15:59:03.371712: step: 1596/530, loss: 0.0038880843203514814
2023-01-22 15:59:04.428041: step: 1600/530, loss: 0.005178489722311497
2023-01-22 15:59:05.499973: step: 1604/530, loss: 0.006016201805323362
2023-01-22 15:59:06.548223: step: 1608/530, loss: 0.009906507097184658
2023-01-22 15:59:07.602248: step: 1612/530, loss: 0.0063696312718093395
2023-01-22 15:59:08.654627: step: 1616/530, loss: 3.598132389015518e-05
2023-01-22 15:59:09.704204: step: 1620/530, loss: 0.0108889639377594
2023-01-22 15:59:10.758912: step: 1624/530, loss: 0.0015007598558440804
2023-01-22 15:59:11.818397: step: 1628/530, loss: 0.0036919787526130676
2023-01-22 15:59:12.866826: step: 1632/530, loss: 0.006333977449685335
2023-01-22 15:59:13.913609: step: 1636/530, loss: 0.004862017463892698
2023-01-22 15:59:14.971155: step: 1640/530, loss: 0.006857108324766159
2023-01-22 15:59:16.029724: step: 1644/530, loss: 0.0006810321356169879
2023-01-22 15:59:17.086564: step: 1648/530, loss: 0.0006151502020657063
2023-01-22 15:59:18.133919: step: 1652/530, loss: 0.0008619756554253399
2023-01-22 15:59:19.214335: step: 1656/530, loss: 0.0022198238875716925
2023-01-22 15:59:20.293353: step: 1660/530, loss: 0.0010134903714060783
2023-01-22 15:59:21.371575: step: 1664/530, loss: 0.006010419689118862
2023-01-22 15:59:22.421474: step: 1668/530, loss: 0.05877001956105232
2023-01-22 15:59:23.478025: step: 1672/530, loss: 0.010641299188137054
2023-01-22 15:59:24.544243: step: 1676/530, loss: 0.002878132276237011
2023-01-22 15:59:25.605766: step: 1680/530, loss: 0.02457360364496708
2023-01-22 15:59:26.659211: step: 1684/530, loss: 0.009073033928871155
2023-01-22 15:59:27.713295: step: 1688/530, loss: 0.0010165708372369409
2023-01-22 15:59:28.778559: step: 1692/530, loss: 0.005371278617531061
2023-01-22 15:59:29.835079: step: 1696/530, loss: 0.004141046199947596
2023-01-22 15:59:30.893500: step: 1700/530, loss: 0.0
2023-01-22 15:59:31.959750: step: 1704/530, loss: 0.009293717332184315
2023-01-22 15:59:33.045732: step: 1708/530, loss: 0.005547970533370972
2023-01-22 15:59:34.107002: step: 1712/530, loss: 0.008700049482285976
2023-01-22 15:59:35.149717: step: 1716/530, loss: 0.008054769597947598
2023-01-22 15:59:36.231340: step: 1720/530, loss: 0.001258236006833613
2023-01-22 15:59:37.266077: step: 1724/530, loss: 0.008488127961754799
2023-01-22 15:59:38.342742: step: 1728/530, loss: 0.029200317338109016
2023-01-22 15:59:39.398436: step: 1732/530, loss: 0.016749313101172447
2023-01-22 15:59:40.456604: step: 1736/530, loss: 0.007692796643823385
2023-01-22 15:59:41.499617: step: 1740/530, loss: 0.013126224279403687
2023-01-22 15:59:42.548306: step: 1744/530, loss: 0.001301880576647818
2023-01-22 15:59:43.600351: step: 1748/530, loss: 0.005355332046747208
2023-01-22 15:59:44.642656: step: 1752/530, loss: 0.02250639535486698
2023-01-22 15:59:45.704405: step: 1756/530, loss: 0.008386602625250816
2023-01-22 15:59:46.756769: step: 1760/530, loss: 0.005702165886759758
2023-01-22 15:59:47.804617: step: 1764/530, loss: 0.008322526700794697
2023-01-22 15:59:48.851926: step: 1768/530, loss: 0.0058671566657722
2023-01-22 15:59:49.908003: step: 1772/530, loss: 0.00073309923755005
2023-01-22 15:59:50.959020: step: 1776/530, loss: 0.010479552671313286
2023-01-22 15:59:52.003854: step: 1780/530, loss: 0.005352622829377651
2023-01-22 15:59:53.067221: step: 1784/530, loss: 0.032972633838653564
2023-01-22 15:59:54.129802: step: 1788/530, loss: 0.0074201771058142185
2023-01-22 15:59:55.198522: step: 1792/530, loss: 0.016771988943219185
2023-01-22 15:59:56.279112: step: 1796/530, loss: 0.031335145235061646
2023-01-22 15:59:57.334251: step: 1800/530, loss: 0.0029944139532744884
2023-01-22 15:59:58.389892: step: 1804/530, loss: 0.004832638893276453
2023-01-22 15:59:59.448474: step: 1808/530, loss: 0.01707667112350464
2023-01-22 16:00:00.521270: step: 1812/530, loss: 0.002868467476218939
2023-01-22 16:00:01.576114: step: 1816/530, loss: 0.009555457159876823
2023-01-22 16:00:02.644824: step: 1820/530, loss: 0.0014934046193957329
2023-01-22 16:00:03.706325: step: 1824/530, loss: 0.016105249524116516
2023-01-22 16:00:04.762226: step: 1828/530, loss: 0.0009161548223346472
2023-01-22 16:00:05.807080: step: 1832/530, loss: 0.006872161291539669
2023-01-22 16:00:06.854941: step: 1836/530, loss: 0.018346259370446205
2023-01-22 16:00:07.921917: step: 1840/530, loss: 0.0011875653872266412
2023-01-22 16:00:08.996837: step: 1844/530, loss: 0.007434564642608166
2023-01-22 16:00:10.076328: step: 1848/530, loss: 0.015627963468432426
2023-01-22 16:00:11.158264: step: 1852/530, loss: 0.0075806668028235435
2023-01-22 16:00:12.208431: step: 1856/530, loss: 0.005289080552756786
2023-01-22 16:00:13.254810: step: 1860/530, loss: 0.006550746038556099
2023-01-22 16:00:14.319755: step: 1864/530, loss: 0.01285226084291935
2023-01-22 16:00:15.396753: step: 1868/530, loss: 0.028356308117508888
2023-01-22 16:00:16.456340: step: 1872/530, loss: 0.006177104078233242
2023-01-22 16:00:17.502805: step: 1876/530, loss: 0.005874236114323139
2023-01-22 16:00:18.549461: step: 1880/530, loss: 0.002133819507434964
2023-01-22 16:00:19.615207: step: 1884/530, loss: 0.0016121327644214034
2023-01-22 16:00:20.679140: step: 1888/530, loss: 0.0014566682511940598
2023-01-22 16:00:21.737495: step: 1892/530, loss: 0.003723465371876955
2023-01-22 16:00:22.778224: step: 1896/530, loss: 0.002977007068693638
2023-01-22 16:00:23.847647: step: 1900/530, loss: 0.0012824763543903828
2023-01-22 16:00:24.889116: step: 1904/530, loss: 0.0015486414777114987
2023-01-22 16:00:25.953614: step: 1908/530, loss: 0.008708218112587929
2023-01-22 16:00:27.020769: step: 1912/530, loss: 0.015091648325324059
2023-01-22 16:00:28.065704: step: 1916/530, loss: 0.011505119502544403
2023-01-22 16:00:29.105798: step: 1920/530, loss: 0.0031264491844922304
2023-01-22 16:00:30.160113: step: 1924/530, loss: 0.012557929381728172
2023-01-22 16:00:31.236433: step: 1928/530, loss: 0.007312506437301636
2023-01-22 16:00:32.318903: step: 1932/530, loss: 0.004234807565808296
2023-01-22 16:00:33.375545: step: 1936/530, loss: 0.007357989903539419
2023-01-22 16:00:34.441567: step: 1940/530, loss: 0.01080083567649126
2023-01-22 16:00:35.483514: step: 1944/530, loss: 0.0027293264865875244
2023-01-22 16:00:36.558259: step: 1948/530, loss: 0.009540950879454613
2023-01-22 16:00:37.633150: step: 1952/530, loss: 0.005311830434948206
2023-01-22 16:00:38.699733: step: 1956/530, loss: 0.0022345108445733786
2023-01-22 16:00:39.758639: step: 1960/530, loss: 0.008572908118367195
2023-01-22 16:00:40.818199: step: 1964/530, loss: 0.003876825561746955
2023-01-22 16:00:41.906176: step: 1968/530, loss: 0.0035365927033126354
2023-01-22 16:00:42.950720: step: 1972/530, loss: 0.0030830225441604853
2023-01-22 16:00:43.993439: step: 1976/530, loss: 0.0024644872173666954
2023-01-22 16:00:45.064950: step: 1980/530, loss: 0.006964856758713722
2023-01-22 16:00:46.110327: step: 1984/530, loss: 0.017210956662893295
2023-01-22 16:00:47.172668: step: 1988/530, loss: 0.0011903017293661833
2023-01-22 16:00:48.236842: step: 1992/530, loss: 0.002029990078881383
2023-01-22 16:00:49.293545: step: 1996/530, loss: 0.00775444321334362
2023-01-22 16:00:50.341332: step: 2000/530, loss: 0.012881227768957615
2023-01-22 16:00:51.402928: step: 2004/530, loss: 0.005271740257740021
2023-01-22 16:00:52.457744: step: 2008/530, loss: 0.015584379434585571
2023-01-22 16:00:53.506672: step: 2012/530, loss: 0.002974665490910411
2023-01-22 16:00:54.555223: step: 2016/530, loss: 0.003269895678386092
2023-01-22 16:00:55.611867: step: 2020/530, loss: 0.010840609669685364
2023-01-22 16:00:56.675718: step: 2024/530, loss: 0.016084840521216393
2023-01-22 16:00:57.751945: step: 2028/530, loss: 0.004212565254420042
2023-01-22 16:00:58.808937: step: 2032/530, loss: 0.00749535858631134
2023-01-22 16:00:59.874149: step: 2036/530, loss: 0.029413238167762756
2023-01-22 16:01:00.944538: step: 2040/530, loss: 0.006110089831054211
2023-01-22 16:01:01.996630: step: 2044/530, loss: 0.007431995123624802
2023-01-22 16:01:03.077784: step: 2048/530, loss: 0.005208600778132677
2023-01-22 16:01:04.127437: step: 2052/530, loss: 0.044159021228551865
2023-01-22 16:01:05.193982: step: 2056/530, loss: 0.043648310005664825
2023-01-22 16:01:06.257305: step: 2060/530, loss: 0.013246748596429825
2023-01-22 16:01:07.316012: step: 2064/530, loss: 0.01302739605307579
2023-01-22 16:01:08.382967: step: 2068/530, loss: 0.010749460197985172
2023-01-22 16:01:09.440501: step: 2072/530, loss: 5.5180520575959235e-05
2023-01-22 16:01:10.516213: step: 2076/530, loss: 0.0023341933265328407
2023-01-22 16:01:11.622512: step: 2080/530, loss: 0.0076659321784973145
2023-01-22 16:01:12.682581: step: 2084/530, loss: 0.03867116943001747
2023-01-22 16:01:13.743412: step: 2088/530, loss: 0.021886657923460007
2023-01-22 16:01:14.802274: step: 2092/530, loss: 0.0023359856568276882
2023-01-22 16:01:15.860334: step: 2096/530, loss: 0.006516108289361
2023-01-22 16:01:16.945557: step: 2100/530, loss: 0.018510611727833748
2023-01-22 16:01:17.998224: step: 2104/530, loss: 0.0019100788049399853
2023-01-22 16:01:19.070064: step: 2108/530, loss: 0.019090835005044937
2023-01-22 16:01:20.129821: step: 2112/530, loss: 0.02267684042453766
2023-01-22 16:01:21.184563: step: 2116/530, loss: 0.003943257033824921
2023-01-22 16:01:22.251573: step: 2120/530, loss: 0.008389642462134361
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3537181593974042, 'r': 0.2346930669340844, 'f1': 0.2821672869051907}, 'combined': 0.18713685349152542, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32364139310795365, 'r': 0.2887028336247086, 'f1': 0.3051753676753677}, 'combined': 0.2034502451169118, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40355184485480056, 'r': 0.3223514736437739, 'f1': 0.3584100762885934}, 'combined': 0.23390973399887144, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3198392710892711, 'r': 0.3368326289460066, 'f1': 0.3281160729289196}, 'combined': 0.24176973794762494, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615625787108744, 'r': 0.3327627888914801, 'f1': 0.3465653932999635}, 'combined': 0.22984647845800685, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.36237373737373735, 'r': 0.3416666666666666, 'f1': 0.3517156862745098}, 'combined': 0.2344771241830065, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.59375, 'r': 0.41304347826086957, 'f1': 0.4871794871794871}, 'combined': 0.32478632478632474, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 8
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:03:52.467633: step: 4/530, loss: 0.001578222494572401
2023-01-22 16:03:53.505136: step: 8/530, loss: 0.000899963139090687
2023-01-22 16:03:54.548056: step: 12/530, loss: 0.008029366843402386
2023-01-22 16:03:55.612045: step: 16/530, loss: 0.022720078006386757
2023-01-22 16:03:56.670762: step: 20/530, loss: 0.01804449036717415
2023-01-22 16:03:57.728290: step: 24/530, loss: 0.003947988618165255
2023-01-22 16:03:58.789491: step: 28/530, loss: 0.00310538406483829
2023-01-22 16:03:59.860667: step: 32/530, loss: 0.004651452414691448
2023-01-22 16:04:00.912885: step: 36/530, loss: 0.0140745360404253
2023-01-22 16:04:01.977533: step: 40/530, loss: 0.0012586034135892987
2023-01-22 16:04:03.058316: step: 44/530, loss: 0.00970130879431963
2023-01-22 16:04:04.113714: step: 48/530, loss: 0.024466238915920258
2023-01-22 16:04:05.178426: step: 52/530, loss: 0.018754877150058746
2023-01-22 16:04:06.235613: step: 56/530, loss: 0.003244738793000579
2023-01-22 16:04:07.278564: step: 60/530, loss: 0.002220563357695937
2023-01-22 16:04:08.322114: step: 64/530, loss: 0.015442682430148125
2023-01-22 16:04:09.381476: step: 68/530, loss: 0.003957618493586779
2023-01-22 16:04:10.434477: step: 72/530, loss: 0.007866286672651768
2023-01-22 16:04:11.504918: step: 76/530, loss: 0.0008116963435895741
2023-01-22 16:04:12.570904: step: 80/530, loss: 0.0035716306883841753
2023-01-22 16:04:13.628846: step: 84/530, loss: 0.0002185688354074955
2023-01-22 16:04:14.685328: step: 88/530, loss: 0.0044698044657707214
2023-01-22 16:04:15.734675: step: 92/530, loss: 0.011758637614548206
2023-01-22 16:04:16.797045: step: 96/530, loss: 0.005662843585014343
2023-01-22 16:04:17.858944: step: 100/530, loss: 0.004792902618646622
2023-01-22 16:04:18.906511: step: 104/530, loss: 1.8417009414406493e-05
2023-01-22 16:04:19.955055: step: 108/530, loss: 0.0015699961222708225
2023-01-22 16:04:21.004395: step: 112/530, loss: 0.002671522554010153
2023-01-22 16:04:22.059251: step: 116/530, loss: 0.002577098784968257
2023-01-22 16:04:23.118667: step: 120/530, loss: 0.003473773133009672
2023-01-22 16:04:24.174758: step: 124/530, loss: 0.011938536539673805
2023-01-22 16:04:25.231996: step: 128/530, loss: 0.006991213653236628
2023-01-22 16:04:26.284439: step: 132/530, loss: 0.000358393182978034
2023-01-22 16:04:27.332539: step: 136/530, loss: 0.010971558280289173
2023-01-22 16:04:28.383351: step: 140/530, loss: 0.004337462596595287
2023-01-22 16:04:29.435442: step: 144/530, loss: 0.0005295031587593257
2023-01-22 16:04:30.484042: step: 148/530, loss: 0.0009479966829530895
2023-01-22 16:04:31.539315: step: 152/530, loss: 0.0017000744119286537
2023-01-22 16:04:32.582622: step: 156/530, loss: 0.0006047465722076595
2023-01-22 16:04:33.656897: step: 160/530, loss: 0.003590860404074192
2023-01-22 16:04:34.721957: step: 164/530, loss: 0.00035557817318476737
2023-01-22 16:04:35.781198: step: 168/530, loss: 3.231114897062071e-05
2023-01-22 16:04:36.820618: step: 172/530, loss: 0.0009216041653417051
2023-01-22 16:04:37.874657: step: 176/530, loss: 0.002186810364946723
2023-01-22 16:04:38.933886: step: 180/530, loss: 0.024899797514081
2023-01-22 16:04:39.998838: step: 184/530, loss: 0.009470392018556595
2023-01-22 16:04:41.057389: step: 188/530, loss: 0.005112182814627886
2023-01-22 16:04:42.133022: step: 192/530, loss: 0.003691369667649269
2023-01-22 16:04:43.197860: step: 196/530, loss: 0.013270733878016472
2023-01-22 16:04:44.250307: step: 200/530, loss: 0.006272920873016119
2023-01-22 16:04:45.319988: step: 204/530, loss: 0.02067854441702366
2023-01-22 16:04:46.391592: step: 208/530, loss: 0.008375195786356926
2023-01-22 16:04:47.442256: step: 212/530, loss: 0.0010385076748207211
2023-01-22 16:04:48.503982: step: 216/530, loss: 0.0023643074091523886
2023-01-22 16:04:49.558831: step: 220/530, loss: 0.013027149252593517
2023-01-22 16:04:50.621012: step: 224/530, loss: 0.0066559505648911
2023-01-22 16:04:51.692450: step: 228/530, loss: 0.023444408550858498
2023-01-22 16:04:52.776465: step: 232/530, loss: 0.004703290294855833
2023-01-22 16:04:53.836963: step: 236/530, loss: 0.01591780036687851
2023-01-22 16:04:54.911638: step: 240/530, loss: 0.02737894095480442
2023-01-22 16:04:55.950305: step: 244/530, loss: 0.0018430290510877967
2023-01-22 16:04:57.017043: step: 248/530, loss: 0.007181955501437187
2023-01-22 16:04:58.087630: step: 252/530, loss: 0.01720271073281765
2023-01-22 16:04:59.143222: step: 256/530, loss: 0.0031290033366531134
2023-01-22 16:05:00.202733: step: 260/530, loss: 9.991229308070615e-05
2023-01-22 16:05:01.258828: step: 264/530, loss: 0.004231417551636696
2023-01-22 16:05:02.329126: step: 268/530, loss: 0.0006702316459268332
2023-01-22 16:05:03.405042: step: 272/530, loss: 0.00019239106040913612
2023-01-22 16:05:04.466883: step: 276/530, loss: 0.005118575878441334
2023-01-22 16:05:05.526335: step: 280/530, loss: 0.004971566144376993
2023-01-22 16:05:06.585267: step: 284/530, loss: 0.0003004439640790224
2023-01-22 16:05:07.638376: step: 288/530, loss: 0.0041951751336455345
2023-01-22 16:05:08.712388: step: 292/530, loss: 0.01582016982138157
2023-01-22 16:05:09.786880: step: 296/530, loss: 0.006762396078556776
2023-01-22 16:05:10.855975: step: 300/530, loss: 4.750323932967149e-05
2023-01-22 16:05:11.916036: step: 304/530, loss: 0.008418899029493332
2023-01-22 16:05:12.982285: step: 308/530, loss: 0.006618069484829903
2023-01-22 16:05:14.073484: step: 312/530, loss: 0.004107459913939238
2023-01-22 16:05:15.136297: step: 316/530, loss: 0.009810952469706535
2023-01-22 16:05:16.198625: step: 320/530, loss: 0.009370585903525352
2023-01-22 16:05:17.275918: step: 324/530, loss: 0.0019693318754434586
2023-01-22 16:05:18.339067: step: 328/530, loss: 0.0050402795895934105
2023-01-22 16:05:19.396481: step: 332/530, loss: 0.0027141098398715258
2023-01-22 16:05:20.462805: step: 336/530, loss: 0.024775249883532524
2023-01-22 16:05:21.525786: step: 340/530, loss: 0.002051254967227578
2023-01-22 16:05:22.585527: step: 344/530, loss: 0.0008156161056831479
2023-01-22 16:05:23.644178: step: 348/530, loss: 0.010663973167538643
2023-01-22 16:05:24.713056: step: 352/530, loss: 0.0047533828765153885
2023-01-22 16:05:25.787696: step: 356/530, loss: 0.006912748795002699
2023-01-22 16:05:26.849253: step: 360/530, loss: 0.001605372759513557
2023-01-22 16:05:27.908441: step: 364/530, loss: 0.007916337810456753
2023-01-22 16:05:28.951957: step: 368/530, loss: 0.0011368439299985766
2023-01-22 16:05:30.019543: step: 372/530, loss: 0.015500892885029316
2023-01-22 16:05:31.076249: step: 376/530, loss: 0.009428277611732483
2023-01-22 16:05:32.152795: step: 380/530, loss: 0.010872173123061657
2023-01-22 16:05:33.230884: step: 384/530, loss: 0.002144044265151024
2023-01-22 16:05:34.301579: step: 388/530, loss: 0.005862843245267868
2023-01-22 16:05:35.371135: step: 392/530, loss: 0.002543897368013859
2023-01-22 16:05:36.440648: step: 396/530, loss: 0.002472938969731331
2023-01-22 16:05:37.501797: step: 400/530, loss: 0.0008193214307539165
2023-01-22 16:05:38.576943: step: 404/530, loss: 0.005421883426606655
2023-01-22 16:05:39.643137: step: 408/530, loss: 0.006072331219911575
2023-01-22 16:05:40.708641: step: 412/530, loss: 0.002236895263195038
2023-01-22 16:05:41.798741: step: 416/530, loss: 0.0036221640184521675
2023-01-22 16:05:42.866445: step: 420/530, loss: 0.0042864917777478695
2023-01-22 16:05:43.926290: step: 424/530, loss: 0.0004260396817699075
2023-01-22 16:05:44.998629: step: 428/530, loss: 0.0012707824353128672
2023-01-22 16:05:46.049151: step: 432/530, loss: 0.0012458136770874262
2023-01-22 16:05:47.110674: step: 436/530, loss: 0.009500917978584766
2023-01-22 16:05:48.160904: step: 440/530, loss: 0.0011804746463894844
2023-01-22 16:05:49.224698: step: 444/530, loss: 0.006803330034017563
2023-01-22 16:05:50.285837: step: 448/530, loss: 0.0038335993885993958
2023-01-22 16:05:51.353307: step: 452/530, loss: 0.041306860744953156
2023-01-22 16:05:52.415362: step: 456/530, loss: 0.00015529927622992545
2023-01-22 16:05:53.477973: step: 460/530, loss: 0.009807570837438107
2023-01-22 16:05:54.526202: step: 464/530, loss: 0.0015617129392921925
2023-01-22 16:05:55.587746: step: 468/530, loss: 0.000826411007437855
2023-01-22 16:05:56.648228: step: 472/530, loss: 0.00410790229216218
2023-01-22 16:05:57.714499: step: 476/530, loss: 0.0035296306014060974
2023-01-22 16:05:58.791105: step: 480/530, loss: 0.004457561299204826
2023-01-22 16:05:59.867631: step: 484/530, loss: 0.018837295472621918
2023-01-22 16:06:00.931442: step: 488/530, loss: 0.0052842795848846436
2023-01-22 16:06:01.998426: step: 492/530, loss: 0.0011642472818493843
2023-01-22 16:06:03.077064: step: 496/530, loss: 0.0015510981902480125
2023-01-22 16:06:04.142098: step: 500/530, loss: 0.003408548654988408
2023-01-22 16:06:05.221618: step: 504/530, loss: 0.0033200138714164495
2023-01-22 16:06:06.298423: step: 508/530, loss: 0.007814311422407627
2023-01-22 16:06:07.367834: step: 512/530, loss: 0.001283789984881878
2023-01-22 16:06:08.422957: step: 516/530, loss: 0.0032652714289724827
2023-01-22 16:06:09.492953: step: 520/530, loss: 0.012143399566411972
2023-01-22 16:06:10.525433: step: 524/530, loss: 0.00014721114712301642
2023-01-22 16:06:11.582853: step: 528/530, loss: 0.016877857968211174
2023-01-22 16:06:12.656660: step: 532/530, loss: 0.0013240206753835082
2023-01-22 16:06:13.720310: step: 536/530, loss: 0.004016508813947439
2023-01-22 16:06:14.797275: step: 540/530, loss: 0.02041524276137352
2023-01-22 16:06:15.850914: step: 544/530, loss: 0.0017077726079151034
2023-01-22 16:06:16.916135: step: 548/530, loss: 0.0037660400848835707
2023-01-22 16:06:17.989128: step: 552/530, loss: 0.0057712760753929615
2023-01-22 16:06:19.064952: step: 556/530, loss: 0.002878459170460701
2023-01-22 16:06:20.139770: step: 560/530, loss: 0.0017273627454414964
2023-01-22 16:06:21.196428: step: 564/530, loss: 0.004351409617811441
2023-01-22 16:06:22.259952: step: 568/530, loss: 0.0036845330614596605
2023-01-22 16:06:23.311241: step: 572/530, loss: 0.00444047711789608
2023-01-22 16:06:24.369384: step: 576/530, loss: 0.0006759187672287226
2023-01-22 16:06:25.421913: step: 580/530, loss: 0.0048767393454909325
2023-01-22 16:06:26.484722: step: 584/530, loss: 0.0027554964181035757
2023-01-22 16:06:27.539347: step: 588/530, loss: 0.0029018798377364874
2023-01-22 16:06:28.604419: step: 592/530, loss: 0.004838711582124233
2023-01-22 16:06:29.682686: step: 596/530, loss: 0.001147024449892342
2023-01-22 16:06:30.755997: step: 600/530, loss: 0.0013574139447882771
2023-01-22 16:06:31.817060: step: 604/530, loss: 0.01001831702888012
2023-01-22 16:06:32.895153: step: 608/530, loss: 0.004788985010236502
2023-01-22 16:06:33.949038: step: 612/530, loss: 0.0014081747503951192
2023-01-22 16:06:34.999212: step: 616/530, loss: 0.0016465570079162717
2023-01-22 16:06:36.053565: step: 620/530, loss: 0.005801419261842966
2023-01-22 16:06:37.108154: step: 624/530, loss: 0.03987366333603859
2023-01-22 16:06:38.157835: step: 628/530, loss: 0.003176118014380336
2023-01-22 16:06:39.219022: step: 632/530, loss: 0.0008934763609431684
2023-01-22 16:06:40.294287: step: 636/530, loss: 0.005749239586293697
2023-01-22 16:06:41.351539: step: 640/530, loss: 0.004555360414087772
2023-01-22 16:06:42.406181: step: 644/530, loss: 0.0
2023-01-22 16:06:43.458949: step: 648/530, loss: 0.00025537374312989414
2023-01-22 16:06:44.518491: step: 652/530, loss: 0.009222530759871006
2023-01-22 16:06:45.580591: step: 656/530, loss: 0.005340136121958494
2023-01-22 16:06:46.640397: step: 660/530, loss: 0.005938283633440733
2023-01-22 16:06:47.690398: step: 664/530, loss: 0.006589628756046295
2023-01-22 16:06:48.753846: step: 668/530, loss: 0.0024793867487460375
2023-01-22 16:06:49.813301: step: 672/530, loss: 0.00016749647329561412
2023-01-22 16:06:50.888943: step: 676/530, loss: 0.002509690821170807
2023-01-22 16:06:51.957533: step: 680/530, loss: 0.00983802042901516
2023-01-22 16:06:53.032971: step: 684/530, loss: 0.005732954014092684
2023-01-22 16:06:54.106923: step: 688/530, loss: 0.009008189663290977
2023-01-22 16:06:55.180017: step: 692/530, loss: 0.006726323626935482
2023-01-22 16:06:56.222139: step: 696/530, loss: 0.0019366192864254117
2023-01-22 16:06:57.284232: step: 700/530, loss: 0.010213913396000862
2023-01-22 16:06:58.348547: step: 704/530, loss: 0.0014466455904766917
2023-01-22 16:06:59.418525: step: 708/530, loss: 0.003334656823426485
2023-01-22 16:07:00.491212: step: 712/530, loss: 0.0048185852356255054
2023-01-22 16:07:01.540655: step: 716/530, loss: 0.0024992600083351135
2023-01-22 16:07:02.599891: step: 720/530, loss: 0.001594380009919405
2023-01-22 16:07:03.658817: step: 724/530, loss: 0.01058395579457283
2023-01-22 16:07:04.714292: step: 728/530, loss: 0.004823962226510048
2023-01-22 16:07:05.796562: step: 732/530, loss: 0.005900415126234293
2023-01-22 16:07:06.859165: step: 736/530, loss: 0.004103643354028463
2023-01-22 16:07:07.922837: step: 740/530, loss: 0.020892757922410965
2023-01-22 16:07:08.985727: step: 744/530, loss: 0.0016669811448082328
2023-01-22 16:07:10.057753: step: 748/530, loss: 0.0039565060287714005
2023-01-22 16:07:11.118237: step: 752/530, loss: 0.011750808916985989
2023-01-22 16:07:12.179423: step: 756/530, loss: 0.0044591231271624565
2023-01-22 16:07:13.239978: step: 760/530, loss: 0.005317573435604572
2023-01-22 16:07:14.293542: step: 764/530, loss: 0.002158926334232092
2023-01-22 16:07:15.349261: step: 768/530, loss: 0.013807006180286407
2023-01-22 16:07:16.425704: step: 772/530, loss: 0.0006345547735691071
2023-01-22 16:07:17.492568: step: 776/530, loss: 0.02323751337826252
2023-01-22 16:07:18.543646: step: 780/530, loss: 0.008334612473845482
2023-01-22 16:07:19.605697: step: 784/530, loss: 0.010491586290299892
2023-01-22 16:07:20.696510: step: 788/530, loss: 0.01413573045283556
2023-01-22 16:07:21.750314: step: 792/530, loss: 0.008251430466771126
2023-01-22 16:07:22.797205: step: 796/530, loss: 0.011630561202764511
2023-01-22 16:07:23.856572: step: 800/530, loss: 0.0021440545096993446
2023-01-22 16:07:24.911830: step: 804/530, loss: 0.005057157948613167
2023-01-22 16:07:25.970413: step: 808/530, loss: 0.0052289413288235664
2023-01-22 16:07:27.025913: step: 812/530, loss: 0.0038129761815071106
2023-01-22 16:07:28.073871: step: 816/530, loss: 0.0001373779959976673
2023-01-22 16:07:29.122443: step: 820/530, loss: 0.0025319266133010387
2023-01-22 16:07:30.200031: step: 824/530, loss: 0.004143928177654743
2023-01-22 16:07:31.261321: step: 828/530, loss: 0.006298021413385868
2023-01-22 16:07:32.341321: step: 832/530, loss: 0.0037713563069701195
2023-01-22 16:07:33.408134: step: 836/530, loss: 0.003089392092078924
2023-01-22 16:07:34.468551: step: 840/530, loss: 0.0039008057210594416
2023-01-22 16:07:35.528980: step: 844/530, loss: 0.003434424754232168
2023-01-22 16:07:36.597292: step: 848/530, loss: 0.006872132886201143
2023-01-22 16:07:37.659330: step: 852/530, loss: 0.0035184407606720924
2023-01-22 16:07:38.719439: step: 856/530, loss: 0.006169327534735203
2023-01-22 16:07:39.780056: step: 860/530, loss: 0.0015827324241399765
2023-01-22 16:07:40.835154: step: 864/530, loss: 0.008262558840215206
2023-01-22 16:07:41.887888: step: 868/530, loss: 0.006411949638277292
2023-01-22 16:07:42.961098: step: 872/530, loss: 0.000947563792578876
2023-01-22 16:07:44.025011: step: 876/530, loss: 0.011106381192803383
2023-01-22 16:07:45.091497: step: 880/530, loss: 0.0016223759157583117
2023-01-22 16:07:46.144697: step: 884/530, loss: 0.01957591436803341
2023-01-22 16:07:47.194482: step: 888/530, loss: 0.006975620985031128
2023-01-22 16:07:48.253698: step: 892/530, loss: 0.0011496235383674502
2023-01-22 16:07:49.299009: step: 896/530, loss: 0.0003228428540751338
2023-01-22 16:07:50.356552: step: 900/530, loss: 0.010430501773953438
2023-01-22 16:07:51.401688: step: 904/530, loss: 0.005505760665982962
2023-01-22 16:07:52.455450: step: 908/530, loss: 0.004160992801189423
2023-01-22 16:07:53.517546: step: 912/530, loss: 0.00787445716559887
2023-01-22 16:07:54.596746: step: 916/530, loss: 0.016685495153069496
2023-01-22 16:07:55.642554: step: 920/530, loss: 0.005118233617395163
2023-01-22 16:07:56.712752: step: 924/530, loss: 0.00031529227271676064
2023-01-22 16:07:57.773030: step: 928/530, loss: 0.0005196065758354962
2023-01-22 16:07:58.814858: step: 932/530, loss: 0.0033208897802978754
2023-01-22 16:07:59.880293: step: 936/530, loss: 0.013224363327026367
2023-01-22 16:08:00.939916: step: 940/530, loss: 0.008918027393519878
2023-01-22 16:08:02.011403: step: 944/530, loss: 0.005305406637489796
2023-01-22 16:08:03.073933: step: 948/530, loss: 0.001953817205503583
2023-01-22 16:08:04.127080: step: 952/530, loss: 0.0027615586295723915
2023-01-22 16:08:05.188428: step: 956/530, loss: 0.007874968461692333
2023-01-22 16:08:06.259507: step: 960/530, loss: 0.005785588640719652
2023-01-22 16:08:07.318615: step: 964/530, loss: 0.0031078369356691837
2023-01-22 16:08:08.400252: step: 968/530, loss: 0.0004704507300630212
2023-01-22 16:08:09.456467: step: 972/530, loss: 0.004142599646002054
2023-01-22 16:08:10.525462: step: 976/530, loss: 0.01403866708278656
2023-01-22 16:08:11.577631: step: 980/530, loss: 0.016708463430404663
2023-01-22 16:08:12.648558: step: 984/530, loss: 0.006009605713188648
2023-01-22 16:08:13.697199: step: 988/530, loss: 0.0030958850402384996
2023-01-22 16:08:14.760007: step: 992/530, loss: 0.005048592574894428
2023-01-22 16:08:15.811942: step: 996/530, loss: 9.777664672583342e-05
2023-01-22 16:08:16.867125: step: 1000/530, loss: 0.004117369651794434
2023-01-22 16:08:17.921109: step: 1004/530, loss: 0.002292782999575138
2023-01-22 16:08:18.989056: step: 1008/530, loss: 0.0036601070314645767
2023-01-22 16:08:20.047695: step: 1012/530, loss: 0.013988976366817951
2023-01-22 16:08:21.109073: step: 1016/530, loss: 0.003988346550613642
2023-01-22 16:08:22.160987: step: 1020/530, loss: 0.005626540165394545
2023-01-22 16:08:23.230349: step: 1024/530, loss: 0.011585342697799206
2023-01-22 16:08:24.285546: step: 1028/530, loss: 0.009907795116305351
2023-01-22 16:08:25.338243: step: 1032/530, loss: 0.0012083154870197177
2023-01-22 16:08:26.424381: step: 1036/530, loss: 0.0024685675743967295
2023-01-22 16:08:27.488621: step: 1040/530, loss: 0.005400072317570448
2023-01-22 16:08:28.536747: step: 1044/530, loss: 0.0015769656747579575
2023-01-22 16:08:29.583740: step: 1048/530, loss: 0.0038196684326976538
2023-01-22 16:08:30.639803: step: 1052/530, loss: 0.013219322077929974
2023-01-22 16:08:31.699932: step: 1056/530, loss: 0.012918712571263313
2023-01-22 16:08:32.771918: step: 1060/530, loss: 0.010488973930478096
2023-01-22 16:08:33.843951: step: 1064/530, loss: 0.005757351405918598
2023-01-22 16:08:34.895265: step: 1068/530, loss: 0.00045643607154488564
2023-01-22 16:08:35.948648: step: 1072/530, loss: 0.016330217942595482
2023-01-22 16:08:37.003098: step: 1076/530, loss: 0.011616937816143036
2023-01-22 16:08:38.069594: step: 1080/530, loss: 0.00924005638808012
2023-01-22 16:08:39.153723: step: 1084/530, loss: 0.002475353190675378
2023-01-22 16:08:40.219738: step: 1088/530, loss: 0.002158066490665078
2023-01-22 16:08:41.274397: step: 1092/530, loss: 0.0036438305396586657
2023-01-22 16:08:42.349793: step: 1096/530, loss: 0.02925151027739048
2023-01-22 16:08:43.415768: step: 1100/530, loss: 0.002680625766515732
2023-01-22 16:08:44.485187: step: 1104/530, loss: 0.004278386477380991
2023-01-22 16:08:45.536008: step: 1108/530, loss: 0.0017597271362319589
2023-01-22 16:08:46.594245: step: 1112/530, loss: 0.017071500420570374
2023-01-22 16:08:47.650207: step: 1116/530, loss: 0.0023383672814816236
2023-01-22 16:08:48.694267: step: 1120/530, loss: 0.0005948357284069061
2023-01-22 16:08:49.771458: step: 1124/530, loss: 0.023053156211972237
2023-01-22 16:08:50.827326: step: 1128/530, loss: 0.002723283600062132
2023-01-22 16:08:51.890463: step: 1132/530, loss: 0.0012084601912647486
2023-01-22 16:08:52.956865: step: 1136/530, loss: 0.0049757156521081924
2023-01-22 16:08:54.036661: step: 1140/530, loss: 0.027197297662496567
2023-01-22 16:08:55.078583: step: 1144/530, loss: 0.0009958151495084167
2023-01-22 16:08:56.163908: step: 1148/530, loss: 0.009862146340310574
2023-01-22 16:08:57.227886: step: 1152/530, loss: 0.00027023901930078864
2023-01-22 16:08:58.305210: step: 1156/530, loss: 0.0012597389286383986
2023-01-22 16:08:59.353458: step: 1160/530, loss: 0.01348771434277296
2023-01-22 16:09:00.405564: step: 1164/530, loss: 0.004374179523438215
2023-01-22 16:09:01.474239: step: 1168/530, loss: 0.00842099916189909
2023-01-22 16:09:02.564044: step: 1172/530, loss: 0.015802482143044472
2023-01-22 16:09:03.622202: step: 1176/530, loss: 0.0063231815584003925
2023-01-22 16:09:04.677248: step: 1180/530, loss: 0.0027391796465963125
2023-01-22 16:09:05.727450: step: 1184/530, loss: 0.00445235101506114
2023-01-22 16:09:06.785580: step: 1188/530, loss: 0.003377283923327923
2023-01-22 16:09:07.847741: step: 1192/530, loss: 0.016094859689474106
2023-01-22 16:09:08.916414: step: 1196/530, loss: 0.003858909010887146
2023-01-22 16:09:09.989142: step: 1200/530, loss: 0.004194995388388634
2023-01-22 16:09:11.057933: step: 1204/530, loss: 0.009948239661753178
2023-01-22 16:09:12.126088: step: 1208/530, loss: 0.007313582114875317
2023-01-22 16:09:13.176560: step: 1212/530, loss: 0.0032310641836375
2023-01-22 16:09:14.241653: step: 1216/530, loss: 0.02269793674349785
2023-01-22 16:09:15.297249: step: 1220/530, loss: 0.0008559832349419594
2023-01-22 16:09:16.356846: step: 1224/530, loss: 0.004275730811059475
2023-01-22 16:09:17.419024: step: 1228/530, loss: 0.0054108458571136
2023-01-22 16:09:18.470193: step: 1232/530, loss: 0.0036550445947796106
2023-01-22 16:09:19.525606: step: 1236/530, loss: 0.010995370335876942
2023-01-22 16:09:20.596420: step: 1240/530, loss: 0.009659373201429844
2023-01-22 16:09:21.659124: step: 1244/530, loss: 0.017616888508200645
2023-01-22 16:09:22.711243: step: 1248/530, loss: 0.007949767634272575
2023-01-22 16:09:23.775686: step: 1252/530, loss: 0.003466795664280653
2023-01-22 16:09:24.833030: step: 1256/530, loss: 0.008696061559021473
2023-01-22 16:09:25.899420: step: 1260/530, loss: 0.00022204924607649446
2023-01-22 16:09:26.952628: step: 1264/530, loss: 0.005940826144069433
2023-01-22 16:09:28.020995: step: 1268/530, loss: 0.015793664380908012
2023-01-22 16:09:29.085824: step: 1272/530, loss: 0.0030650380067527294
2023-01-22 16:09:30.149891: step: 1276/530, loss: 0.0020106001757085323
2023-01-22 16:09:31.213206: step: 1280/530, loss: 0.007168071810156107
2023-01-22 16:09:32.311083: step: 1284/530, loss: 0.005691030062735081
2023-01-22 16:09:33.379557: step: 1288/530, loss: 0.006314897909760475
2023-01-22 16:09:34.443000: step: 1292/530, loss: 0.0027939819265156984
2023-01-22 16:09:35.491315: step: 1296/530, loss: 0.0034941197372972965
2023-01-22 16:09:36.554533: step: 1300/530, loss: 0.002159245079383254
2023-01-22 16:09:37.613180: step: 1304/530, loss: 0.003573112888261676
2023-01-22 16:09:38.704095: step: 1308/530, loss: 0.042730607092380524
2023-01-22 16:09:39.767963: step: 1312/530, loss: 0.004080480895936489
2023-01-22 16:09:40.815668: step: 1316/530, loss: 0.010974136181175709
2023-01-22 16:09:41.866968: step: 1320/530, loss: 0.0033737365156412125
2023-01-22 16:09:42.918658: step: 1324/530, loss: 0.00639167008921504
2023-01-22 16:09:43.964134: step: 1328/530, loss: 0.011457026936113834
2023-01-22 16:09:45.046164: step: 1332/530, loss: 0.003620082512497902
2023-01-22 16:09:46.100185: step: 1336/530, loss: 0.009034446440637112
2023-01-22 16:09:47.169775: step: 1340/530, loss: 0.005224709864705801
2023-01-22 16:09:48.221501: step: 1344/530, loss: 0.0026099500246345997
2023-01-22 16:09:49.281608: step: 1348/530, loss: 0.008253741078078747
2023-01-22 16:09:50.346775: step: 1352/530, loss: 0.00010915151506196707
2023-01-22 16:09:51.423179: step: 1356/530, loss: 0.04658046364784241
2023-01-22 16:09:52.488077: step: 1360/530, loss: 0.0009694582549855113
2023-01-22 16:09:53.551822: step: 1364/530, loss: 0.01308530941605568
2023-01-22 16:09:54.618473: step: 1368/530, loss: 0.0041906097903847694
2023-01-22 16:09:55.680676: step: 1372/530, loss: 0.0029759081080555916
2023-01-22 16:09:56.732357: step: 1376/530, loss: 0.0021879486739635468
2023-01-22 16:09:57.797071: step: 1380/530, loss: 0.006069571245461702
2023-01-22 16:09:58.845680: step: 1384/530, loss: 0.02840854786336422
2023-01-22 16:09:59.899977: step: 1388/530, loss: 0.001358837354928255
2023-01-22 16:10:00.953526: step: 1392/530, loss: 0.002851101104170084
2023-01-22 16:10:02.027847: step: 1396/530, loss: 0.010881209746003151
2023-01-22 16:10:03.089283: step: 1400/530, loss: 0.00044142352999188006
2023-01-22 16:10:04.157289: step: 1404/530, loss: 0.0081596365198493
2023-01-22 16:10:05.240407: step: 1408/530, loss: 0.01634400151669979
2023-01-22 16:10:06.317227: step: 1412/530, loss: 0.018973123282194138
2023-01-22 16:10:07.410261: step: 1416/530, loss: 0.0029034828767180443
2023-01-22 16:10:08.474669: step: 1420/530, loss: 0.006434266921132803
2023-01-22 16:10:09.538950: step: 1424/530, loss: 0.004963258747011423
2023-01-22 16:10:10.602892: step: 1428/530, loss: 0.0014174885582178831
2023-01-22 16:10:11.667626: step: 1432/530, loss: 0.003842024365440011
2023-01-22 16:10:12.723394: step: 1436/530, loss: 0.007931889966130257
2023-01-22 16:10:13.785796: step: 1440/530, loss: 0.012513709254562855
2023-01-22 16:10:14.835758: step: 1444/530, loss: 0.006279796827584505
2023-01-22 16:10:15.903147: step: 1448/530, loss: 0.017553262412548065
2023-01-22 16:10:16.970142: step: 1452/530, loss: 0.009306592866778374
2023-01-22 16:10:18.048826: step: 1456/530, loss: 0.00352174392901361
2023-01-22 16:10:19.108900: step: 1460/530, loss: 0.0006553736748173833
2023-01-22 16:10:20.181389: step: 1464/530, loss: 0.005264295730739832
2023-01-22 16:10:21.241119: step: 1468/530, loss: 0.0030810050666332245
2023-01-22 16:10:22.308953: step: 1472/530, loss: 0.0030453705694526434
2023-01-22 16:10:23.358646: step: 1476/530, loss: 0.0072273691184818745
2023-01-22 16:10:24.414011: step: 1480/530, loss: 0.007053266745060682
2023-01-22 16:10:25.496076: step: 1484/530, loss: 0.005382508505135775
2023-01-22 16:10:26.556318: step: 1488/530, loss: 0.0011377789778634906
2023-01-22 16:10:27.620798: step: 1492/530, loss: 0.01101296953856945
2023-01-22 16:10:28.699297: step: 1496/530, loss: 0.008875487372279167
2023-01-22 16:10:29.757502: step: 1500/530, loss: 0.0034963919315487146
2023-01-22 16:10:30.817421: step: 1504/530, loss: 0.002814267994835973
2023-01-22 16:10:31.883046: step: 1508/530, loss: 0.002155342372134328
2023-01-22 16:10:32.950496: step: 1512/530, loss: 0.004510057158768177
2023-01-22 16:10:34.018972: step: 1516/530, loss: 0.005277504678815603
2023-01-22 16:10:35.075918: step: 1520/530, loss: 0.009193949401378632
2023-01-22 16:10:36.128643: step: 1524/530, loss: 0.005815129727125168
2023-01-22 16:10:37.194536: step: 1528/530, loss: 0.0026261107996106148
2023-01-22 16:10:38.256275: step: 1532/530, loss: 0.00044258078560233116
2023-01-22 16:10:39.314485: step: 1536/530, loss: 0.008945046924054623
2023-01-22 16:10:40.362105: step: 1540/530, loss: 0.012445696629583836
2023-01-22 16:10:41.434352: step: 1544/530, loss: 0.03725799545645714
2023-01-22 16:10:42.494659: step: 1548/530, loss: 0.0006237589986994863
2023-01-22 16:10:43.547344: step: 1552/530, loss: 0.034031230956315994
2023-01-22 16:10:44.615121: step: 1556/530, loss: 0.004464354831725359
2023-01-22 16:10:45.686828: step: 1560/530, loss: 0.0005066364537924528
2023-01-22 16:10:46.737404: step: 1564/530, loss: 0.009633711539208889
2023-01-22 16:10:47.796975: step: 1568/530, loss: 0.003609366249293089
2023-01-22 16:10:48.857503: step: 1572/530, loss: 0.011584056541323662
2023-01-22 16:10:49.927505: step: 1576/530, loss: 0.007297593168914318
2023-01-22 16:10:50.979464: step: 1580/530, loss: 0.022794876247644424
2023-01-22 16:10:52.031183: step: 1584/530, loss: 0.013751774094998837
2023-01-22 16:10:53.092779: step: 1588/530, loss: 0.006564836483448744
2023-01-22 16:10:54.151767: step: 1592/530, loss: 0.00834104884415865
2023-01-22 16:10:55.225010: step: 1596/530, loss: 0.01275724545121193
2023-01-22 16:10:56.288423: step: 1600/530, loss: 0.006590662058442831
2023-01-22 16:10:57.346076: step: 1604/530, loss: 0.0052870032377541065
2023-01-22 16:10:58.431326: step: 1608/530, loss: 0.044110264629125595
2023-01-22 16:10:59.489339: step: 1612/530, loss: 0.0027077083941549063
2023-01-22 16:11:00.536393: step: 1616/530, loss: 0.0067832572385668755
2023-01-22 16:11:01.594080: step: 1620/530, loss: 0.021005775779485703
2023-01-22 16:11:02.663364: step: 1624/530, loss: 0.0028020518366247416
2023-01-22 16:11:03.725103: step: 1628/530, loss: 0.020514514297246933
2023-01-22 16:11:04.797002: step: 1632/530, loss: 0.013297458179295063
2023-01-22 16:11:05.852541: step: 1636/530, loss: 0.0037885697092860937
2023-01-22 16:11:06.899555: step: 1640/530, loss: 0.0019260881235823035
2023-01-22 16:11:07.943718: step: 1644/530, loss: 0.02238306775689125
2023-01-22 16:11:08.999453: step: 1648/530, loss: 0.006170709151774645
2023-01-22 16:11:10.061283: step: 1652/530, loss: 0.010011142119765282
2023-01-22 16:11:11.123455: step: 1656/530, loss: 0.0015578616876155138
2023-01-22 16:11:12.195193: step: 1660/530, loss: 0.005705316551029682
2023-01-22 16:11:13.247601: step: 1664/530, loss: 0.004996040370315313
2023-01-22 16:11:14.291464: step: 1668/530, loss: 0.004244686104357243
2023-01-22 16:11:15.334182: step: 1672/530, loss: 0.0077867936342954636
2023-01-22 16:11:16.414770: step: 1676/530, loss: 0.006771698594093323
2023-01-22 16:11:17.466362: step: 1680/530, loss: 0.0009493294637650251
2023-01-22 16:11:18.525717: step: 1684/530, loss: 0.003962224815040827
2023-01-22 16:11:19.620531: step: 1688/530, loss: 0.0056709847413003445
2023-01-22 16:11:20.679997: step: 1692/530, loss: 0.013474286533892155
2023-01-22 16:11:21.734278: step: 1696/530, loss: 0.004022576846182346
2023-01-22 16:11:22.780973: step: 1700/530, loss: 0.0048307375982403755
2023-01-22 16:11:23.839114: step: 1704/530, loss: 0.006834511179476976
2023-01-22 16:11:24.899159: step: 1708/530, loss: 0.005257416982203722
2023-01-22 16:11:25.964210: step: 1712/530, loss: 0.014350980520248413
2023-01-22 16:11:27.028669: step: 1716/530, loss: 0.018000328913331032
2023-01-22 16:11:28.079072: step: 1720/530, loss: 0.0003532406408339739
2023-01-22 16:11:29.147468: step: 1724/530, loss: 0.009978021495044231
2023-01-22 16:11:30.199854: step: 1728/530, loss: 0.0007069700513966382
2023-01-22 16:11:31.247336: step: 1732/530, loss: 0.0015021860599517822
2023-01-22 16:11:32.325643: step: 1736/530, loss: 0.017386864870786667
2023-01-22 16:11:33.399908: step: 1740/530, loss: 0.017184417694807053
2023-01-22 16:11:34.460782: step: 1744/530, loss: 0.0067120324820280075
2023-01-22 16:11:35.541084: step: 1748/530, loss: 0.04484333097934723
2023-01-22 16:11:36.589965: step: 1752/530, loss: 0.0033254765439778566
2023-01-22 16:11:37.653063: step: 1756/530, loss: 0.00354401976801455
2023-01-22 16:11:38.718764: step: 1760/530, loss: 0.006634449120610952
2023-01-22 16:11:39.778100: step: 1764/530, loss: 0.0009382428252138197
2023-01-22 16:11:40.835878: step: 1768/530, loss: 0.0018498455174267292
2023-01-22 16:11:41.909738: step: 1772/530, loss: 0.0027881842106580734
2023-01-22 16:11:42.963157: step: 1776/530, loss: 0.0008231662795878947
2023-01-22 16:11:44.028451: step: 1780/530, loss: 0.004137236624956131
2023-01-22 16:11:45.121830: step: 1784/530, loss: 0.00973699614405632
2023-01-22 16:11:46.184412: step: 1788/530, loss: 0.0026099937967956066
2023-01-22 16:11:47.266052: step: 1792/530, loss: 0.002436611568555236
2023-01-22 16:11:48.314885: step: 1796/530, loss: 0.0022602351382374763
2023-01-22 16:11:49.380564: step: 1800/530, loss: 0.0018043058225885034
2023-01-22 16:11:50.470974: step: 1804/530, loss: 0.008009007200598717
2023-01-22 16:11:51.525986: step: 1808/530, loss: 0.005099027883261442
2023-01-22 16:11:52.580927: step: 1812/530, loss: 0.004789561033248901
2023-01-22 16:11:53.646722: step: 1816/530, loss: 0.0005448472802527249
2023-01-22 16:11:54.697046: step: 1820/530, loss: 0.008643064647912979
2023-01-22 16:11:55.762426: step: 1824/530, loss: 0.0017157766269519925
2023-01-22 16:11:56.826173: step: 1828/530, loss: 0.005277327261865139
2023-01-22 16:11:57.894024: step: 1832/530, loss: 0.010374607518315315
2023-01-22 16:11:58.942958: step: 1836/530, loss: 0.0017752469284459949
2023-01-22 16:12:00.010638: step: 1840/530, loss: 0.010292110964655876
2023-01-22 16:12:01.065511: step: 1844/530, loss: 0.03987564519047737
2023-01-22 16:12:02.152632: step: 1848/530, loss: 0.007781487423926592
2023-01-22 16:12:03.213759: step: 1852/530, loss: 0.017869969829916954
2023-01-22 16:12:04.278146: step: 1856/530, loss: 0.003552844049409032
2023-01-22 16:12:05.348673: step: 1860/530, loss: 0.0013825483620166779
2023-01-22 16:12:06.418219: step: 1864/530, loss: 0.02778548188507557
2023-01-22 16:12:07.468662: step: 1868/530, loss: 0.0021867360919713974
2023-01-22 16:12:08.529735: step: 1872/530, loss: 0.009883199818432331
2023-01-22 16:12:09.616630: step: 1876/530, loss: 0.00491854315623641
2023-01-22 16:12:10.686807: step: 1880/530, loss: 0.004421879071742296
2023-01-22 16:12:11.741724: step: 1884/530, loss: 0.005779049824923277
2023-01-22 16:12:12.813228: step: 1888/530, loss: 0.005704408977180719
2023-01-22 16:12:13.877705: step: 1892/530, loss: 0.018534252420067787
2023-01-22 16:12:14.935919: step: 1896/530, loss: 0.006822432857006788
2023-01-22 16:12:15.995487: step: 1900/530, loss: 0.007705484051257372
2023-01-22 16:12:17.071730: step: 1904/530, loss: 0.0028729026671499014
2023-01-22 16:12:18.141708: step: 1908/530, loss: 0.0026009564753621817
2023-01-22 16:12:19.194013: step: 1912/530, loss: 0.007517572026699781
2023-01-22 16:12:20.255412: step: 1916/530, loss: 0.026851356029510498
2023-01-22 16:12:21.325190: step: 1920/530, loss: 0.003632955253124237
2023-01-22 16:12:22.394035: step: 1924/530, loss: 0.01801270991563797
2023-01-22 16:12:23.432907: step: 1928/530, loss: 0.015021150931715965
2023-01-22 16:12:24.490080: step: 1932/530, loss: 0.001532773021608591
2023-01-22 16:12:25.538827: step: 1936/530, loss: 0.002741945208981633
2023-01-22 16:12:26.591379: step: 1940/530, loss: 0.005579810123890638
2023-01-22 16:12:27.657259: step: 1944/530, loss: 0.0036730861756950617
2023-01-22 16:12:28.721739: step: 1948/530, loss: 0.019181568175554276
2023-01-22 16:12:29.776431: step: 1952/530, loss: 0.05246738716959953
2023-01-22 16:12:30.832622: step: 1956/530, loss: 0.012826553545892239
2023-01-22 16:12:31.889176: step: 1960/530, loss: 0.00749613530933857
2023-01-22 16:12:32.939023: step: 1964/530, loss: 0.0021970057860016823
2023-01-22 16:12:33.995976: step: 1968/530, loss: 0.0033430519979447126
2023-01-22 16:12:35.054686: step: 1972/530, loss: 0.014233284629881382
2023-01-22 16:12:36.127272: step: 1976/530, loss: 0.006610978860408068
2023-01-22 16:12:37.185449: step: 1980/530, loss: 0.004730131011456251
2023-01-22 16:12:38.248132: step: 1984/530, loss: 0.0243196040391922
2023-01-22 16:12:39.314948: step: 1988/530, loss: 0.0034956117160618305
2023-01-22 16:12:40.375476: step: 1992/530, loss: 0.01712939701974392
2023-01-22 16:12:41.444411: step: 1996/530, loss: 0.0041745854541659355
2023-01-22 16:12:42.516423: step: 2000/530, loss: 0.04020633175969124
2023-01-22 16:12:43.573181: step: 2004/530, loss: 0.01455580722540617
2023-01-22 16:12:44.635044: step: 2008/530, loss: 0.00015746141434647143
2023-01-22 16:12:45.702696: step: 2012/530, loss: 0.009296857751905918
2023-01-22 16:12:46.767175: step: 2016/530, loss: 0.04265981912612915
2023-01-22 16:12:47.823276: step: 2020/530, loss: 0.005813135765492916
2023-01-22 16:12:48.903227: step: 2024/530, loss: 0.004123806953430176
2023-01-22 16:12:49.980236: step: 2028/530, loss: 0.0077259354293346405
2023-01-22 16:12:51.033479: step: 2032/530, loss: 0.007799016311764717
2023-01-22 16:12:52.094118: step: 2036/530, loss: 0.000558257510419935
2023-01-22 16:12:53.151464: step: 2040/530, loss: 0.0023471165914088488
2023-01-22 16:12:54.212765: step: 2044/530, loss: 0.02511187456548214
2023-01-22 16:12:55.251953: step: 2048/530, loss: 0.010988562367856503
2023-01-22 16:12:56.319097: step: 2052/530, loss: 0.002913655247539282
2023-01-22 16:12:57.374648: step: 2056/530, loss: 0.006095722317695618
2023-01-22 16:12:58.429948: step: 2060/530, loss: 0.007117302622646093
2023-01-22 16:12:59.502401: step: 2064/530, loss: 0.01098459493368864
2023-01-22 16:13:00.573700: step: 2068/530, loss: 0.024153364822268486
2023-01-22 16:13:01.641299: step: 2072/530, loss: 0.0010887591633945704
2023-01-22 16:13:02.711455: step: 2076/530, loss: 0.019949011504650116
2023-01-22 16:13:03.763835: step: 2080/530, loss: 0.09003783762454987
2023-01-22 16:13:04.833367: step: 2084/530, loss: 0.004630534444004297
2023-01-22 16:13:05.892544: step: 2088/530, loss: 0.0029297247529029846
2023-01-22 16:13:06.963738: step: 2092/530, loss: 0.006283792667090893
2023-01-22 16:13:08.014298: step: 2096/530, loss: 0.005687047727406025
2023-01-22 16:13:09.086925: step: 2100/530, loss: 0.005041434895247221
2023-01-22 16:13:10.161619: step: 2104/530, loss: 0.009113487787544727
2023-01-22 16:13:11.225479: step: 2108/530, loss: 0.0020749259274452925
2023-01-22 16:13:12.289424: step: 2112/530, loss: 0.0012578677851706743
2023-01-22 16:13:13.364054: step: 2116/530, loss: 0.0004785159835591912
2023-01-22 16:13:14.433854: step: 2120/530, loss: 0.005833215545862913
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3607375776397516, 'r': 0.2874948436597641, 'f1': 0.3199784215600754}, 'combined': 0.23577357378110816, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3593053201264448, 'r': 0.23685009885815686, 'f1': 0.285501055201876}, 'combined': 0.1893478500820732, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31948332521908474, 'r': 0.2868088942307692, 'f1': 0.3022656609857209}, 'combined': 0.20151044065714724, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4010068296298047, 'r': 0.3182317858727418, 'f1': 0.35485614033972085}, 'combined': 0.23159032316908096, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3234960492016944, 'r': 0.3425252285665, 'f1': 0.33273879346459995}, 'combined': 0.2451759530791789, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3598019158006251, 'r': 0.32865023477892596, 'f1': 0.34352128612638866}, 'combined': 0.22782758872630954, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.453125, 'r': 0.25, 'f1': 0.32222222222222224}, 'combined': 0.21481481481481482, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:15:43.395296: step: 4/530, loss: 0.015453999862074852
2023-01-22 16:15:44.429064: step: 8/530, loss: 0.007492606993764639
2023-01-22 16:15:45.473884: step: 12/530, loss: 0.00014246927457861602
2023-01-22 16:15:46.517008: step: 16/530, loss: 0.011854852549731731
2023-01-22 16:15:47.575497: step: 20/530, loss: 0.0029151272028684616
2023-01-22 16:15:48.627552: step: 24/530, loss: 0.018363848328590393
2023-01-22 16:15:49.665766: step: 28/530, loss: 0.0013391694519668818
2023-01-22 16:15:50.717652: step: 32/530, loss: 0.006418815813958645
2023-01-22 16:15:51.775041: step: 36/530, loss: 0.0024502796586602926
2023-01-22 16:15:52.829641: step: 40/530, loss: 0.002085303422063589
2023-01-22 16:15:53.880367: step: 44/530, loss: 0.004141415003687143
2023-01-22 16:15:54.939921: step: 48/530, loss: 0.0027567066717892885
2023-01-22 16:15:55.988996: step: 52/530, loss: 0.007397840265184641
2023-01-22 16:15:57.043848: step: 56/530, loss: 0.004578541498631239
2023-01-22 16:15:58.091370: step: 60/530, loss: 0.0007039898191578686
2023-01-22 16:15:59.140212: step: 64/530, loss: 0.001355127664282918
2023-01-22 16:16:00.187910: step: 68/530, loss: 0.00461657764390111
2023-01-22 16:16:01.234469: step: 72/530, loss: 0.004640455823391676
2023-01-22 16:16:02.309884: step: 76/530, loss: 0.012126055546104908
2023-01-22 16:16:03.389412: step: 80/530, loss: 0.0030512565281242132
2023-01-22 16:16:04.442634: step: 84/530, loss: 0.008379384875297546
2023-01-22 16:16:05.505030: step: 88/530, loss: 0.006320971064269543
2023-01-22 16:16:06.568779: step: 92/530, loss: 0.008114654570817947
2023-01-22 16:16:07.621400: step: 96/530, loss: 0.0004159668169450015
2023-01-22 16:16:08.681476: step: 100/530, loss: 0.0027421661652624607
2023-01-22 16:16:09.744433: step: 104/530, loss: 0.002439852338284254
2023-01-22 16:16:10.811053: step: 108/530, loss: 0.009213601239025593
2023-01-22 16:16:11.891724: step: 112/530, loss: 0.013362675905227661
2023-01-22 16:16:12.943823: step: 116/530, loss: 0.0008297545136883855
2023-01-22 16:16:14.000507: step: 120/530, loss: 0.006370811257511377
2023-01-22 16:16:15.068936: step: 124/530, loss: 0.005854370538145304
2023-01-22 16:16:16.133454: step: 128/530, loss: 0.003679548157379031
2023-01-22 16:16:17.214945: step: 132/530, loss: 0.0009568792302161455
2023-01-22 16:16:18.283552: step: 136/530, loss: 0.004784580320119858
2023-01-22 16:16:19.349561: step: 140/530, loss: 0.0058162580244243145
2023-01-22 16:16:20.418341: step: 144/530, loss: 0.0008889066521078348
2023-01-22 16:16:21.475036: step: 148/530, loss: 0.007078120484948158
2023-01-22 16:16:22.524979: step: 152/530, loss: 0.00599098764359951
2023-01-22 16:16:23.594494: step: 156/530, loss: 0.06296837329864502
2023-01-22 16:16:24.649503: step: 160/530, loss: 0.003585967468097806
2023-01-22 16:16:25.710232: step: 164/530, loss: 0.00626272801309824
2023-01-22 16:16:26.778336: step: 168/530, loss: 0.0049561080522835255
2023-01-22 16:16:27.828375: step: 172/530, loss: 0.0030540090519934893
2023-01-22 16:16:28.899026: step: 176/530, loss: 0.0015736365457996726
2023-01-22 16:16:29.947638: step: 180/530, loss: 0.0030348163563758135
2023-01-22 16:16:31.016689: step: 184/530, loss: 0.0036298318300396204
2023-01-22 16:16:32.113168: step: 188/530, loss: 0.026296341791749
2023-01-22 16:16:33.170914: step: 192/530, loss: 0.003975518047809601
2023-01-22 16:16:34.236109: step: 196/530, loss: 0.0022665925789624453
2023-01-22 16:16:35.301171: step: 200/530, loss: 0.012239893898367882
2023-01-22 16:16:36.376626: step: 204/530, loss: 0.008207200095057487
2023-01-22 16:16:37.434095: step: 208/530, loss: 0.004619590938091278
2023-01-22 16:16:38.497858: step: 212/530, loss: 0.005163558758795261
2023-01-22 16:16:39.554729: step: 216/530, loss: 0.009994187392294407
2023-01-22 16:16:40.603922: step: 220/530, loss: 0.045528192073106766
2023-01-22 16:16:41.652209: step: 224/530, loss: 0.0012525701895356178
2023-01-22 16:16:42.708580: step: 228/530, loss: 0.0006718150107190013
2023-01-22 16:16:43.764638: step: 232/530, loss: 0.000846226466819644
2023-01-22 16:16:44.822230: step: 236/530, loss: 0.0026339988689869642
2023-01-22 16:16:45.891627: step: 240/530, loss: 0.0029404209926724434
2023-01-22 16:16:46.965160: step: 244/530, loss: 0.0028495085425674915
2023-01-22 16:16:48.039611: step: 248/530, loss: 0.004417273681610823
2023-01-22 16:16:49.101615: step: 252/530, loss: 0.006803040858358145
2023-01-22 16:16:50.161638: step: 256/530, loss: 0.005339222028851509
2023-01-22 16:16:51.231660: step: 260/530, loss: 0.011898625642061234
2023-01-22 16:16:52.302746: step: 264/530, loss: 0.008732391521334648
2023-01-22 16:16:53.370395: step: 268/530, loss: 0.006564145442098379
2023-01-22 16:16:54.444870: step: 272/530, loss: 0.004995036404579878
2023-01-22 16:16:55.503341: step: 276/530, loss: 0.012199289165437222
2023-01-22 16:16:56.569974: step: 280/530, loss: 0.0018923735478892922
2023-01-22 16:16:57.616046: step: 284/530, loss: 0.0011896748328581452
2023-01-22 16:16:58.678535: step: 288/530, loss: 0.00014055822975933552
2023-01-22 16:16:59.727202: step: 292/530, loss: 0.0016469121910631657
2023-01-22 16:17:00.788094: step: 296/530, loss: 0.0032895649783313274
2023-01-22 16:17:01.857607: step: 300/530, loss: 0.04233624413609505
2023-01-22 16:17:02.911524: step: 304/530, loss: 0.0010820298921316862
2023-01-22 16:17:03.971015: step: 308/530, loss: 0.004549311473965645
2023-01-22 16:17:05.044655: step: 312/530, loss: 0.0067084794864058495
2023-01-22 16:17:06.116621: step: 316/530, loss: 0.0011970365885645151
2023-01-22 16:17:07.181890: step: 320/530, loss: 0.00020241158199496567
2023-01-22 16:17:08.241833: step: 324/530, loss: 0.004127122927457094
2023-01-22 16:17:09.302649: step: 328/530, loss: 0.0014319818001240492
2023-01-22 16:17:10.357248: step: 332/530, loss: 0.0004152162582613528
2023-01-22 16:17:11.423738: step: 336/530, loss: 0.0036277943290770054
2023-01-22 16:17:12.504348: step: 340/530, loss: 0.03309885412454605
2023-01-22 16:17:13.574422: step: 344/530, loss: 0.0026101842522621155
2023-01-22 16:17:14.645001: step: 348/530, loss: 0.007072480395436287
2023-01-22 16:17:15.720009: step: 352/530, loss: 0.02057088539004326
2023-01-22 16:17:16.771013: step: 356/530, loss: 0.000909652968402952
2023-01-22 16:17:17.827434: step: 360/530, loss: 0.0030061097349971533
2023-01-22 16:17:18.890716: step: 364/530, loss: 0.0027174167335033417
2023-01-22 16:17:19.976271: step: 368/530, loss: 0.011390430852770805
2023-01-22 16:17:21.054234: step: 372/530, loss: 0.004826629534363747
2023-01-22 16:17:22.129610: step: 376/530, loss: 0.019450442865490913
2023-01-22 16:17:23.193009: step: 380/530, loss: 0.003957065753638744
2023-01-22 16:17:24.253001: step: 384/530, loss: 0.0004515479377005249
2023-01-22 16:17:25.317651: step: 388/530, loss: 0.007636076305061579
2023-01-22 16:17:26.365528: step: 392/530, loss: 0.0028993040323257446
2023-01-22 16:17:27.425103: step: 396/530, loss: 0.0002904027933254838
2023-01-22 16:17:28.480824: step: 400/530, loss: 0.0
2023-01-22 16:17:29.530052: step: 404/530, loss: 2.7460991987027228e-05
2023-01-22 16:17:30.581482: step: 408/530, loss: 0.03271704912185669
2023-01-22 16:17:31.631004: step: 412/530, loss: 0.003774759592488408
2023-01-22 16:17:32.682176: step: 416/530, loss: 0.0030925965402275324
2023-01-22 16:17:33.729678: step: 420/530, loss: 0.004614985082298517
2023-01-22 16:17:34.798783: step: 424/530, loss: 0.005455093923956156
2023-01-22 16:17:35.843693: step: 428/530, loss: 0.006341665051877499
2023-01-22 16:17:36.904222: step: 432/530, loss: 0.017181839793920517
2023-01-22 16:17:37.946495: step: 436/530, loss: 0.002694448223337531
2023-01-22 16:17:39.010177: step: 440/530, loss: 0.05161819979548454
2023-01-22 16:17:40.082899: step: 444/530, loss: 0.0013058632612228394
2023-01-22 16:17:41.150245: step: 448/530, loss: 0.0029132997151464224
2023-01-22 16:17:42.218366: step: 452/530, loss: 0.004522283561527729
2023-01-22 16:17:43.289648: step: 456/530, loss: 0.0010106154950335622
2023-01-22 16:17:44.364578: step: 460/530, loss: 0.005339529365301132
2023-01-22 16:17:45.431497: step: 464/530, loss: 0.0026368643157184124
2023-01-22 16:17:46.475327: step: 468/530, loss: 0.009323693811893463
2023-01-22 16:17:47.537681: step: 472/530, loss: 0.013810019940137863
2023-01-22 16:17:48.591320: step: 476/530, loss: 0.011116879060864449
2023-01-22 16:17:49.661427: step: 480/530, loss: 0.002194151049479842
2023-01-22 16:17:50.718730: step: 484/530, loss: 0.006756369024515152
2023-01-22 16:17:51.786625: step: 488/530, loss: 0.0003016063419636339
2023-01-22 16:17:52.865224: step: 492/530, loss: 0.006293751765042543
2023-01-22 16:17:53.916307: step: 496/530, loss: 0.0029896721243858337
2023-01-22 16:17:54.984104: step: 500/530, loss: 0.006648496259003878
2023-01-22 16:17:56.052208: step: 504/530, loss: 0.00203089346177876
2023-01-22 16:17:57.125999: step: 508/530, loss: 0.005479095969349146
2023-01-22 16:17:58.179141: step: 512/530, loss: 0.0015512114623561502
2023-01-22 16:17:59.235890: step: 516/530, loss: 0.006149264983832836
2023-01-22 16:18:00.299294: step: 520/530, loss: 0.013237375766038895
2023-01-22 16:18:01.359460: step: 524/530, loss: 0.007827612571418285
2023-01-22 16:18:02.416555: step: 528/530, loss: 0.016051651909947395
2023-01-22 16:18:03.475366: step: 532/530, loss: 0.003809115616604686
2023-01-22 16:18:04.529556: step: 536/530, loss: 0.0007821884355507791
2023-01-22 16:18:05.583693: step: 540/530, loss: 0.003712996141985059
2023-01-22 16:18:06.647237: step: 544/530, loss: 0.005278317723423243
2023-01-22 16:18:07.702408: step: 548/530, loss: 3.0008284738869406e-05
2023-01-22 16:18:08.766234: step: 552/530, loss: 0.004711154382675886
2023-01-22 16:18:09.845015: step: 556/530, loss: 0.004152313806116581
2023-01-22 16:18:10.921049: step: 560/530, loss: 0.0036589601077139378
2023-01-22 16:18:11.990796: step: 564/530, loss: 0.0008431334281340241
2023-01-22 16:18:13.049050: step: 568/530, loss: 0.005460687913000584
2023-01-22 16:18:14.128104: step: 572/530, loss: 0.08068236708641052
2023-01-22 16:18:15.170954: step: 576/530, loss: 0.0027963733300566673
2023-01-22 16:18:16.223754: step: 580/530, loss: 0.006012422032654285
2023-01-22 16:18:17.292481: step: 584/530, loss: 0.01018478348851204
2023-01-22 16:18:18.380660: step: 588/530, loss: 0.004423086065798998
2023-01-22 16:18:19.450547: step: 592/530, loss: 0.0031773997470736504
2023-01-22 16:18:20.527172: step: 596/530, loss: 0.030890708789229393
2023-01-22 16:18:21.579573: step: 600/530, loss: 0.028727402910590172
2023-01-22 16:18:22.648831: step: 604/530, loss: 0.002231570426374674
2023-01-22 16:18:23.704978: step: 608/530, loss: 0.003950521815568209
2023-01-22 16:18:24.776138: step: 612/530, loss: 0.012898269109427929
2023-01-22 16:18:25.855159: step: 616/530, loss: 0.004336596932262182
2023-01-22 16:18:26.922136: step: 620/530, loss: 0.002114019123837352
2023-01-22 16:18:27.998206: step: 624/530, loss: 0.02313615195453167
2023-01-22 16:18:29.051671: step: 628/530, loss: 0.008622352033853531
2023-01-22 16:18:30.119126: step: 632/530, loss: 0.007752744480967522
2023-01-22 16:18:31.191540: step: 636/530, loss: 0.0032598418183624744
2023-01-22 16:18:32.240576: step: 640/530, loss: 0.0012892093509435654
2023-01-22 16:18:33.297251: step: 644/530, loss: 0.0027099954895675182
2023-01-22 16:18:34.360055: step: 648/530, loss: 0.0035064304247498512
2023-01-22 16:18:35.405750: step: 652/530, loss: 0.0016977464547380805
2023-01-22 16:18:36.466643: step: 656/530, loss: 0.0031078618485480547
2023-01-22 16:18:37.517709: step: 660/530, loss: 0.011553210206329823
2023-01-22 16:18:38.599410: step: 664/530, loss: 0.10066927224397659
2023-01-22 16:18:39.667820: step: 668/530, loss: 0.0072242445312440395
2023-01-22 16:18:40.732160: step: 672/530, loss: 0.0024160207249224186
2023-01-22 16:18:41.801843: step: 676/530, loss: 0.010552321560680866
2023-01-22 16:18:42.853497: step: 680/530, loss: 0.0035529660526663065
2023-01-22 16:18:43.909433: step: 684/530, loss: 0.0023826996330171824
2023-01-22 16:18:44.962249: step: 688/530, loss: 0.0022004724014550447
2023-01-22 16:18:46.028643: step: 692/530, loss: 0.0024364585988223553
2023-01-22 16:18:47.086627: step: 696/530, loss: 0.012206265702843666
2023-01-22 16:18:48.176133: step: 700/530, loss: 0.00589038897305727
2023-01-22 16:18:49.232885: step: 704/530, loss: 0.004035803955048323
2023-01-22 16:18:50.282034: step: 708/530, loss: 0.002244410803541541
2023-01-22 16:18:51.373068: step: 712/530, loss: 0.004526213277131319
2023-01-22 16:18:52.435080: step: 716/530, loss: 0.004469079896807671
2023-01-22 16:18:53.487663: step: 720/530, loss: 0.00046579272020608187
2023-01-22 16:18:54.570203: step: 724/530, loss: 0.003095470368862152
2023-01-22 16:18:55.627473: step: 728/530, loss: 0.002439818112179637
2023-01-22 16:18:56.683194: step: 732/530, loss: 0.005467942915856838
2023-01-22 16:18:57.730875: step: 736/530, loss: 0.001995539991185069
2023-01-22 16:18:58.794850: step: 740/530, loss: 0.0030730287544429302
2023-01-22 16:18:59.851511: step: 744/530, loss: 0.0012522361939772964
2023-01-22 16:19:00.911371: step: 748/530, loss: 0.002423665951937437
2023-01-22 16:19:01.975017: step: 752/530, loss: 0.006869632750749588
2023-01-22 16:19:03.043282: step: 756/530, loss: 0.0001799451420083642
2023-01-22 16:19:04.103269: step: 760/530, loss: 0.0029497332870960236
2023-01-22 16:19:05.173946: step: 764/530, loss: 0.002520194509997964
2023-01-22 16:19:06.230674: step: 768/530, loss: 0.003950153011828661
2023-01-22 16:19:07.297325: step: 772/530, loss: 0.0004641618288587779
2023-01-22 16:19:08.365076: step: 776/530, loss: 0.00600142776966095
2023-01-22 16:19:09.439192: step: 780/530, loss: 0.007325040176510811
2023-01-22 16:19:10.493854: step: 784/530, loss: 0.0017829153221100569
2023-01-22 16:19:11.543790: step: 788/530, loss: 3.85610073863063e-05
2023-01-22 16:19:12.604485: step: 792/530, loss: 0.03337559476494789
2023-01-22 16:19:13.688288: step: 796/530, loss: 0.003583089681342244
2023-01-22 16:19:14.746276: step: 800/530, loss: 0.004981456324458122
2023-01-22 16:19:15.807855: step: 804/530, loss: 0.0207794439047575
2023-01-22 16:19:16.873972: step: 808/530, loss: 0.0010892957216128707
2023-01-22 16:19:17.933142: step: 812/530, loss: 0.0027127661742269993
2023-01-22 16:19:18.991956: step: 816/530, loss: 0.001927546109072864
2023-01-22 16:19:20.028408: step: 820/530, loss: 1.3253365978016518e-05
2023-01-22 16:19:21.094688: step: 824/530, loss: 0.00104722217656672
2023-01-22 16:19:22.174223: step: 828/530, loss: 0.008881953544914722
2023-01-22 16:19:23.250866: step: 832/530, loss: 0.000970495748333633
2023-01-22 16:19:24.308404: step: 836/530, loss: 0.0029569535981863737
2023-01-22 16:19:25.395217: step: 840/530, loss: 0.003989328630268574
2023-01-22 16:19:26.476331: step: 844/530, loss: 0.001307170488871634
2023-01-22 16:19:27.547026: step: 848/530, loss: 0.002456264803186059
2023-01-22 16:19:28.602700: step: 852/530, loss: 0.004593417048454285
2023-01-22 16:19:29.661047: step: 856/530, loss: 0.002916011493653059
2023-01-22 16:19:30.725057: step: 860/530, loss: 0.003267683321610093
2023-01-22 16:19:31.783413: step: 864/530, loss: 0.00366516993381083
2023-01-22 16:19:32.842189: step: 868/530, loss: 0.0005363342352211475
2023-01-22 16:19:33.895935: step: 872/530, loss: 0.0031091896817088127
2023-01-22 16:19:34.964865: step: 876/530, loss: 0.004570943769067526
2023-01-22 16:19:36.023036: step: 880/530, loss: 0.0002666552609298378
2023-01-22 16:19:37.076880: step: 884/530, loss: 0.0
2023-01-22 16:19:38.140624: step: 888/530, loss: 0.005018032155930996
2023-01-22 16:19:39.191363: step: 892/530, loss: 0.0034780981950461864
2023-01-22 16:19:40.255535: step: 896/530, loss: 0.031597428023815155
2023-01-22 16:19:41.314848: step: 900/530, loss: 0.011771705001592636
2023-01-22 16:19:42.372944: step: 904/530, loss: 0.02103698067367077
2023-01-22 16:19:43.444909: step: 908/530, loss: 0.008566686883568764
2023-01-22 16:19:44.518403: step: 912/530, loss: 0.0006476959679275751
2023-01-22 16:19:45.583623: step: 916/530, loss: 0.017150847241282463
2023-01-22 16:19:46.655385: step: 920/530, loss: 0.0008063833811320364
2023-01-22 16:19:47.710631: step: 924/530, loss: 0.0003461026353761554
2023-01-22 16:19:48.786952: step: 928/530, loss: 0.007730963174253702
2023-01-22 16:19:49.858939: step: 932/530, loss: 0.005475018639117479
2023-01-22 16:19:50.896410: step: 936/530, loss: 0.00197156285867095
2023-01-22 16:19:51.952623: step: 940/530, loss: 0.006250013597309589
2023-01-22 16:19:53.017657: step: 944/530, loss: 0.007999706082046032
2023-01-22 16:19:54.074093: step: 948/530, loss: 0.016621405258774757
2023-01-22 16:19:55.143686: step: 952/530, loss: 0.010028475895524025
2023-01-22 16:19:56.207718: step: 956/530, loss: 0.03006618842482567
2023-01-22 16:19:57.283553: step: 960/530, loss: 0.0018241485813632607
2023-01-22 16:19:58.346492: step: 964/530, loss: 0.0054228161461651325
2023-01-22 16:19:59.408452: step: 968/530, loss: 0.0029113006312400103
2023-01-22 16:20:00.460589: step: 972/530, loss: 0.006533229257911444
2023-01-22 16:20:01.519911: step: 976/530, loss: 0.0004995585768483579
2023-01-22 16:20:02.583506: step: 980/530, loss: 0.010044052265584469
2023-01-22 16:20:03.663295: step: 984/530, loss: 0.004120043013244867
2023-01-22 16:20:04.730673: step: 988/530, loss: 0.011376149952411652
2023-01-22 16:20:05.792937: step: 992/530, loss: 0.012200153432786465
2023-01-22 16:20:06.849867: step: 996/530, loss: 0.0024647866375744343
2023-01-22 16:20:07.911652: step: 1000/530, loss: 0.00512643251568079
2023-01-22 16:20:08.963426: step: 1004/530, loss: 0.0031221136450767517
2023-01-22 16:20:10.011924: step: 1008/530, loss: 0.0029007140547037125
2023-01-22 16:20:11.064669: step: 1012/530, loss: 0.023068975657224655
2023-01-22 16:20:12.122485: step: 1016/530, loss: 0.047838084399700165
2023-01-22 16:20:13.192330: step: 1020/530, loss: 0.01036304421722889
2023-01-22 16:20:14.245268: step: 1024/530, loss: 0.0007745142211206257
2023-01-22 16:20:15.299275: step: 1028/530, loss: 0.004627063404768705
2023-01-22 16:20:16.364912: step: 1032/530, loss: 0.03404998779296875
2023-01-22 16:20:17.423213: step: 1036/530, loss: 0.005893825087696314
2023-01-22 16:20:18.499667: step: 1040/530, loss: 0.003592468798160553
2023-01-22 16:20:19.558004: step: 1044/530, loss: 0.031811878085136414
2023-01-22 16:20:20.610456: step: 1048/530, loss: 0.000999869778752327
2023-01-22 16:20:21.675006: step: 1052/530, loss: 0.0028399198781698942
2023-01-22 16:20:22.728815: step: 1056/530, loss: 0.0024975307751446962
2023-01-22 16:20:23.798692: step: 1060/530, loss: 0.006558599416166544
2023-01-22 16:20:24.862397: step: 1064/530, loss: 0.0022379420697689056
2023-01-22 16:20:25.927173: step: 1068/530, loss: 0.00027735999901778996
2023-01-22 16:20:26.987645: step: 1072/530, loss: 0.0037738613318651915
2023-01-22 16:20:28.038686: step: 1076/530, loss: 0.0014299798058345914
2023-01-22 16:20:29.097321: step: 1080/530, loss: 0.00029566450393758714
2023-01-22 16:20:30.160973: step: 1084/530, loss: 0.0005588725907728076
2023-01-22 16:20:31.215769: step: 1088/530, loss: 0.006791661959141493
2023-01-22 16:20:32.305815: step: 1092/530, loss: 0.0004303640453144908
2023-01-22 16:20:33.342649: step: 1096/530, loss: 0.0012932104291394353
2023-01-22 16:20:34.413354: step: 1100/530, loss: 0.010163214057683945
2023-01-22 16:20:35.461880: step: 1104/530, loss: 0.00528957461938262
2023-01-22 16:20:36.542238: step: 1108/530, loss: 0.0036679564509540796
2023-01-22 16:20:37.605964: step: 1112/530, loss: 0.003352685598656535
2023-01-22 16:20:38.653027: step: 1116/530, loss: 0.010087912902235985
2023-01-22 16:20:39.722281: step: 1120/530, loss: 0.00860240962356329
2023-01-22 16:20:40.794304: step: 1124/530, loss: 0.015045109204947948
2023-01-22 16:20:41.855714: step: 1128/530, loss: 0.03174243122339249
2023-01-22 16:20:42.912290: step: 1132/530, loss: 0.003598960116505623
2023-01-22 16:20:43.965206: step: 1136/530, loss: 0.001524300780147314
2023-01-22 16:20:45.023904: step: 1140/530, loss: 0.03787195682525635
2023-01-22 16:20:46.115942: step: 1144/530, loss: 0.006270979065448046
2023-01-22 16:20:47.163513: step: 1148/530, loss: 0.037914324551820755
2023-01-22 16:20:48.231137: step: 1152/530, loss: 0.005124355666339397
2023-01-22 16:20:49.296731: step: 1156/530, loss: 0.002639026613906026
2023-01-22 16:20:50.356249: step: 1160/530, loss: 0.001762067317031324
2023-01-22 16:20:51.439695: step: 1164/530, loss: 0.004346344619989395
2023-01-22 16:20:52.524844: step: 1168/530, loss: 0.004185069818049669
2023-01-22 16:20:53.579642: step: 1172/530, loss: 0.005861604120582342
2023-01-22 16:20:54.648026: step: 1176/530, loss: 0.00017850550648290664
2023-01-22 16:20:55.703601: step: 1180/530, loss: 0.0061139194294810295
2023-01-22 16:20:56.767945: step: 1184/530, loss: 0.0057471212930977345
2023-01-22 16:20:57.818289: step: 1188/530, loss: 0.000685409118887037
2023-01-22 16:20:58.878406: step: 1192/530, loss: 0.0029984633438289165
2023-01-22 16:20:59.943983: step: 1196/530, loss: 0.04240376129746437
2023-01-22 16:21:01.010347: step: 1200/530, loss: 0.003919998649507761
2023-01-22 16:21:02.093416: step: 1204/530, loss: 0.005296318791806698
2023-01-22 16:21:03.141722: step: 1208/530, loss: 0.0004119572404306382
2023-01-22 16:21:04.199069: step: 1212/530, loss: 0.0044286539778113365
2023-01-22 16:21:05.257840: step: 1216/530, loss: 0.02172204479575157
2023-01-22 16:21:06.333994: step: 1220/530, loss: 0.007352832239121199
2023-01-22 16:21:07.392620: step: 1224/530, loss: 0.01899542845785618
2023-01-22 16:21:08.451005: step: 1228/530, loss: 0.0027936678379774094
2023-01-22 16:21:09.504909: step: 1232/530, loss: 0.003451894037425518
2023-01-22 16:21:10.575068: step: 1236/530, loss: 0.0018620435148477554
2023-01-22 16:21:11.645611: step: 1240/530, loss: 0.002224933123216033
2023-01-22 16:21:12.729686: step: 1244/530, loss: 0.007762577384710312
2023-01-22 16:21:13.799325: step: 1248/530, loss: 0.017033562064170837
2023-01-22 16:21:14.847902: step: 1252/530, loss: 0.004851041827350855
2023-01-22 16:21:15.912664: step: 1256/530, loss: 0.0036906248424202204
2023-01-22 16:21:16.993222: step: 1260/530, loss: 0.004080755636096001
2023-01-22 16:21:18.063278: step: 1264/530, loss: 0.022719234228134155
2023-01-22 16:21:19.121793: step: 1268/530, loss: 0.005870419088751078
2023-01-22 16:21:20.178200: step: 1272/530, loss: 0.0017245433991774917
2023-01-22 16:21:21.225478: step: 1276/530, loss: 0.0006084832129999995
2023-01-22 16:21:22.282748: step: 1280/530, loss: 0.006511473562568426
2023-01-22 16:21:23.345460: step: 1284/530, loss: 0.004114076495170593
2023-01-22 16:21:24.393674: step: 1288/530, loss: 0.026190178468823433
2023-01-22 16:21:25.458281: step: 1292/530, loss: 0.014754963107407093
2023-01-22 16:21:26.510882: step: 1296/530, loss: 0.022561874240636826
2023-01-22 16:21:27.642405: step: 1300/530, loss: 0.005654872395098209
2023-01-22 16:21:28.704345: step: 1304/530, loss: 0.005959267262369394
2023-01-22 16:21:29.765101: step: 1308/530, loss: 0.004220210015773773
2023-01-22 16:21:30.835968: step: 1312/530, loss: 0.0037146471440792084
2023-01-22 16:21:31.891985: step: 1316/530, loss: 0.005266808904707432
2023-01-22 16:21:32.952495: step: 1320/530, loss: 0.01826951652765274
2023-01-22 16:21:34.030909: step: 1324/530, loss: 0.0056020235642790794
2023-01-22 16:21:35.083948: step: 1328/530, loss: 0.0016568299615755677
2023-01-22 16:21:36.171480: step: 1332/530, loss: 0.01378651149570942
2023-01-22 16:21:37.224773: step: 1336/530, loss: 0.0017705034697428346
2023-01-22 16:21:38.295461: step: 1340/530, loss: 0.009712358005344868
2023-01-22 16:21:39.341330: step: 1344/530, loss: 0.003285177517682314
2023-01-22 16:21:40.427158: step: 1348/530, loss: 0.004849891643971205
2023-01-22 16:21:41.503274: step: 1352/530, loss: 0.0017801231006160378
2023-01-22 16:21:42.560577: step: 1356/530, loss: 0.0005661412724293768
2023-01-22 16:21:43.612116: step: 1360/530, loss: 0.001966212410479784
2023-01-22 16:21:44.664943: step: 1364/530, loss: 0.001030753250233829
2023-01-22 16:21:45.724213: step: 1368/530, loss: 0.006670091766864061
2023-01-22 16:21:46.776773: step: 1372/530, loss: 0.004116909112781286
2023-01-22 16:21:47.834062: step: 1376/530, loss: 0.004152644891291857
2023-01-22 16:21:48.896631: step: 1380/530, loss: 0.023611480370163918
2023-01-22 16:21:49.966662: step: 1384/530, loss: 0.0012033339589834213
2023-01-22 16:21:51.029708: step: 1388/530, loss: 0.01597212813794613
2023-01-22 16:21:52.114940: step: 1392/530, loss: 0.004310728516429663
2023-01-22 16:21:53.180887: step: 1396/530, loss: 0.0
2023-01-22 16:21:54.236196: step: 1400/530, loss: 0.007765563670545816
2023-01-22 16:21:55.290913: step: 1404/530, loss: 0.002658066339790821
2023-01-22 16:21:56.347285: step: 1408/530, loss: 0.00451562087982893
2023-01-22 16:21:57.409524: step: 1412/530, loss: 0.0007149119628593326
2023-01-22 16:21:58.465128: step: 1416/530, loss: 0.0023501284886151552
2023-01-22 16:21:59.532887: step: 1420/530, loss: 0.0010535606415942311
2023-01-22 16:22:00.583756: step: 1424/530, loss: 0.0032468412537127733
2023-01-22 16:22:01.651617: step: 1428/530, loss: 0.0017454884946346283
2023-01-22 16:22:02.711817: step: 1432/530, loss: 0.0031624729745090008
2023-01-22 16:22:03.763599: step: 1436/530, loss: 0.0014564775628969073
2023-01-22 16:22:04.830065: step: 1440/530, loss: 0.001146955182775855
2023-01-22 16:22:05.890695: step: 1444/530, loss: 0.0021946232300251722
2023-01-22 16:22:06.952872: step: 1448/530, loss: 0.0005177851999178529
2023-01-22 16:22:08.009581: step: 1452/530, loss: 0.003388088196516037
2023-01-22 16:22:09.086289: step: 1456/530, loss: 0.0035457343328744173
2023-01-22 16:22:10.147010: step: 1460/530, loss: 0.0037906935904175043
2023-01-22 16:22:11.209855: step: 1464/530, loss: 0.017454415559768677
2023-01-22 16:22:12.266251: step: 1468/530, loss: 2.6523704946157522e-05
2023-01-22 16:22:13.329041: step: 1472/530, loss: 0.0074873254634439945
2023-01-22 16:22:14.382689: step: 1476/530, loss: 0.00312393088825047
2023-01-22 16:22:15.428751: step: 1480/530, loss: 0.0010542598320171237
2023-01-22 16:22:16.511078: step: 1484/530, loss: 0.007353622000664473
2023-01-22 16:22:17.566470: step: 1488/530, loss: 0.0031232002656906843
2023-01-22 16:22:18.628623: step: 1492/530, loss: 0.0025893906131386757
2023-01-22 16:22:19.708369: step: 1496/530, loss: 0.0038539941888302565
2023-01-22 16:22:20.760590: step: 1500/530, loss: 0.0005502093117684126
2023-01-22 16:22:21.825288: step: 1504/530, loss: 0.004979806952178478
2023-01-22 16:22:22.872271: step: 1508/530, loss: 0.0071946061216294765
2023-01-22 16:22:23.946516: step: 1512/530, loss: 0.004448692314326763
2023-01-22 16:22:25.011380: step: 1516/530, loss: 0.008576873689889908
2023-01-22 16:22:26.062035: step: 1520/530, loss: 0.010550213046371937
2023-01-22 16:22:27.127434: step: 1524/530, loss: 0.002015024423599243
2023-01-22 16:22:28.190142: step: 1528/530, loss: 0.0003246348933316767
2023-01-22 16:22:29.250152: step: 1532/530, loss: 0.001094534993171692
2023-01-22 16:22:30.295925: step: 1536/530, loss: 7.546626147814095e-05
2023-01-22 16:22:31.348909: step: 1540/530, loss: 0.01880665309727192
2023-01-22 16:22:32.439390: step: 1544/530, loss: 0.0005597545532509685
2023-01-22 16:22:33.489004: step: 1548/530, loss: 0.0004759436706081033
2023-01-22 16:22:34.558436: step: 1552/530, loss: 0.0021646360401064157
2023-01-22 16:22:35.605195: step: 1556/530, loss: 0.003993749152868986
2023-01-22 16:22:36.667392: step: 1560/530, loss: 0.016274502500891685
2023-01-22 16:22:37.742239: step: 1564/530, loss: 0.00545907998457551
2023-01-22 16:22:38.812065: step: 1568/530, loss: 0.002751567866653204
2023-01-22 16:22:39.875813: step: 1572/530, loss: 0.0025406652130186558
2023-01-22 16:22:40.932881: step: 1576/530, loss: 0.007754336576908827
2023-01-22 16:22:41.990332: step: 1580/530, loss: 0.0018910899525508285
2023-01-22 16:22:43.061271: step: 1584/530, loss: 0.0033316491171717644
2023-01-22 16:22:44.125873: step: 1588/530, loss: 0.004890511743724346
2023-01-22 16:22:45.185933: step: 1592/530, loss: 0.0029237642884254456
2023-01-22 16:22:46.258703: step: 1596/530, loss: 0.0047064004465937614
2023-01-22 16:22:47.314538: step: 1600/530, loss: 0.012439337559044361
2023-01-22 16:22:48.377934: step: 1604/530, loss: 0.004547871649265289
2023-01-22 16:22:49.428803: step: 1608/530, loss: 0.007630421780049801
2023-01-22 16:22:50.498346: step: 1612/530, loss: 0.003931929357349873
2023-01-22 16:22:51.555620: step: 1616/530, loss: 0.0010509529383853078
2023-01-22 16:22:52.616251: step: 1620/530, loss: 1.1811276635853574e-05
2023-01-22 16:22:53.681584: step: 1624/530, loss: 0.006874265149235725
2023-01-22 16:22:54.740259: step: 1628/530, loss: 0.0033264446537941694
2023-01-22 16:22:55.818765: step: 1632/530, loss: 0.011376772075891495
2023-01-22 16:22:56.882417: step: 1636/530, loss: 0.0079652676358819
2023-01-22 16:22:57.946227: step: 1640/530, loss: 0.011988547630608082
2023-01-22 16:22:59.001165: step: 1644/530, loss: 0.001716411323286593
2023-01-22 16:23:00.068766: step: 1648/530, loss: 0.006442325189709663
2023-01-22 16:23:01.119688: step: 1652/530, loss: 0.004815125837922096
2023-01-22 16:23:02.176184: step: 1656/530, loss: 0.0030966070480644703
2023-01-22 16:23:03.218739: step: 1660/530, loss: 0.0030099775176495314
2023-01-22 16:23:04.295013: step: 1664/530, loss: 0.016650628298521042
2023-01-22 16:23:05.358658: step: 1668/530, loss: 0.005719719920307398
2023-01-22 16:23:06.427503: step: 1672/530, loss: 0.006935207638889551
2023-01-22 16:23:07.511781: step: 1676/530, loss: 0.00628667650744319
2023-01-22 16:23:08.570438: step: 1680/530, loss: 0.002305967966094613
2023-01-22 16:23:09.637068: step: 1684/530, loss: 0.020011622458696365
2023-01-22 16:23:10.680068: step: 1688/530, loss: 6.817995017627254e-05
2023-01-22 16:23:11.740792: step: 1692/530, loss: 0.0026268830988556147
2023-01-22 16:23:12.805408: step: 1696/530, loss: 0.01031313743442297
2023-01-22 16:23:13.863633: step: 1700/530, loss: 0.008934480138123035
2023-01-22 16:23:14.954035: step: 1704/530, loss: 0.009671562351286411
2023-01-22 16:23:16.007077: step: 1708/530, loss: 0.007136296946555376
2023-01-22 16:23:17.077605: step: 1712/530, loss: 0.0012411527568474412
2023-01-22 16:23:18.138245: step: 1716/530, loss: 0.002238886198028922
2023-01-22 16:23:19.197166: step: 1720/530, loss: 0.004407891537994146
2023-01-22 16:23:20.252827: step: 1724/530, loss: 0.0024260831996798515
2023-01-22 16:23:21.331615: step: 1728/530, loss: 0.0027922929730266333
2023-01-22 16:23:22.384564: step: 1732/530, loss: 0.0013444084906950593
2023-01-22 16:23:23.452807: step: 1736/530, loss: 0.003485999070107937
2023-01-22 16:23:24.521188: step: 1740/530, loss: 0.0022258758544921875
2023-01-22 16:23:25.590591: step: 1744/530, loss: 0.005299723707139492
2023-01-22 16:23:26.662142: step: 1748/530, loss: 0.0040181661024689674
2023-01-22 16:23:27.720586: step: 1752/530, loss: 0.00608889851719141
2023-01-22 16:23:28.790622: step: 1756/530, loss: 0.008787447586655617
2023-01-22 16:23:29.853321: step: 1760/530, loss: 0.00335937412455678
2023-01-22 16:23:30.905650: step: 1764/530, loss: 0.0006332100601866841
2023-01-22 16:23:31.963947: step: 1768/530, loss: 0.0026157693937420845
2023-01-22 16:23:33.066426: step: 1772/530, loss: 0.012421693652868271
2023-01-22 16:23:34.133118: step: 1776/530, loss: 0.014119272120296955
2023-01-22 16:23:35.190170: step: 1780/530, loss: 0.004634774290025234
2023-01-22 16:23:36.257798: step: 1784/530, loss: 0.004941467195749283
2023-01-22 16:23:37.312657: step: 1788/530, loss: 0.009459305554628372
2023-01-22 16:23:38.367779: step: 1792/530, loss: 0.0013591843890026212
2023-01-22 16:23:39.417145: step: 1796/530, loss: 0.0013900460908189416
2023-01-22 16:23:40.479821: step: 1800/530, loss: 0.0014651138335466385
2023-01-22 16:23:41.555796: step: 1804/530, loss: 0.004790878389030695
2023-01-22 16:23:42.614843: step: 1808/530, loss: 0.0011318136239424348
2023-01-22 16:23:43.676479: step: 1812/530, loss: 0.0114417290315032
2023-01-22 16:23:44.742641: step: 1816/530, loss: 0.0011340589262545109
2023-01-22 16:23:45.812446: step: 1820/530, loss: 0.002051965333521366
2023-01-22 16:23:46.854376: step: 1824/530, loss: 0.009309789165854454
2023-01-22 16:23:47.915011: step: 1828/530, loss: 0.008583464659750462
2023-01-22 16:23:48.967343: step: 1832/530, loss: 0.007632608059793711
2023-01-22 16:23:50.032833: step: 1836/530, loss: 0.0067378380335867405
2023-01-22 16:23:51.089783: step: 1840/530, loss: 0.005021728575229645
2023-01-22 16:23:52.140206: step: 1844/530, loss: 0.00027121329912915826
2023-01-22 16:23:53.206847: step: 1848/530, loss: 4.9419384595239535e-05
2023-01-22 16:23:54.259478: step: 1852/530, loss: 0.003072956344112754
2023-01-22 16:23:55.321453: step: 1856/530, loss: 0.013318224810063839
2023-01-22 16:23:56.376357: step: 1860/530, loss: 0.00018171007104683667
2023-01-22 16:23:57.433301: step: 1864/530, loss: 0.005385766737163067
2023-01-22 16:23:58.491137: step: 1868/530, loss: 0.011189702898263931
2023-01-22 16:23:59.550392: step: 1872/530, loss: 0.00024802316329441965
2023-01-22 16:24:00.607083: step: 1876/530, loss: 0.004605870693922043
2023-01-22 16:24:01.648658: step: 1880/530, loss: 0.0006274774787016213
2023-01-22 16:24:02.712321: step: 1884/530, loss: 0.0008639899315312505
2023-01-22 16:24:03.779134: step: 1888/530, loss: 0.015022809617221355
2023-01-22 16:24:04.856551: step: 1892/530, loss: 0.01180972345173359
2023-01-22 16:24:05.913551: step: 1896/530, loss: 0.0068591078743338585
2023-01-22 16:24:06.969293: step: 1900/530, loss: 0.0009627597755752504
2023-01-22 16:24:08.033942: step: 1904/530, loss: 0.00474949786439538
2023-01-22 16:24:09.108985: step: 1908/530, loss: 0.009530254639685154
2023-01-22 16:24:10.167281: step: 1912/530, loss: 0.008258212357759476
2023-01-22 16:24:11.229906: step: 1916/530, loss: 0.001977296080440283
2023-01-22 16:24:12.295637: step: 1920/530, loss: 0.0033020772971212864
2023-01-22 16:24:13.366027: step: 1924/530, loss: 0.007882621139287949
2023-01-22 16:24:14.440778: step: 1928/530, loss: 0.0013385629281401634
2023-01-22 16:24:15.496071: step: 1932/530, loss: 0.0016821427270770073
2023-01-22 16:24:16.552574: step: 1936/530, loss: 0.005206750705838203
2023-01-22 16:24:17.607084: step: 1940/530, loss: 0.0021994311828166246
2023-01-22 16:24:18.669921: step: 1944/530, loss: 0.0020676536951214075
2023-01-22 16:24:19.732916: step: 1948/530, loss: 1.5307270587072708e-05
2023-01-22 16:24:20.810633: step: 1952/530, loss: 0.012561663053929806
2023-01-22 16:24:21.865820: step: 1956/530, loss: 0.00014406019181478769
2023-01-22 16:24:22.914104: step: 1960/530, loss: 0.0021386772859841585
2023-01-22 16:24:23.978558: step: 1964/530, loss: 0.0024375899229198694
2023-01-22 16:24:25.044336: step: 1968/530, loss: 0.005967001896351576
2023-01-22 16:24:26.107128: step: 1972/530, loss: 0.002499812515452504
2023-01-22 16:24:27.162992: step: 1976/530, loss: 0.011896908283233643
2023-01-22 16:24:28.227257: step: 1980/530, loss: 0.026470324024558067
2023-01-22 16:24:29.294779: step: 1984/530, loss: 0.002903343178331852
2023-01-22 16:24:30.354176: step: 1988/530, loss: 0.005702989175915718
2023-01-22 16:24:31.429876: step: 1992/530, loss: 0.004622644279152155
2023-01-22 16:24:32.484680: step: 1996/530, loss: 0.005409538745880127
2023-01-22 16:24:33.546293: step: 2000/530, loss: 0.028159616515040398
2023-01-22 16:24:34.607586: step: 2004/530, loss: 0.007374122738838196
2023-01-22 16:24:35.671043: step: 2008/530, loss: 0.02760150283575058
2023-01-22 16:24:36.729179: step: 2012/530, loss: 0.0006752068875357509
2023-01-22 16:24:37.781480: step: 2016/530, loss: 0.0023797007743269205
2023-01-22 16:24:38.837692: step: 2020/530, loss: 0.00374113698489964
2023-01-22 16:24:39.904698: step: 2024/530, loss: 0.020107867196202278
2023-01-22 16:24:40.974196: step: 2028/530, loss: 0.025108661502599716
2023-01-22 16:24:42.046908: step: 2032/530, loss: 0.0013643424026668072
2023-01-22 16:24:43.125746: step: 2036/530, loss: 0.02076365426182747
2023-01-22 16:24:44.176714: step: 2040/530, loss: 1.422083005309105e-05
2023-01-22 16:24:45.232967: step: 2044/530, loss: 0.0027981242164969444
2023-01-22 16:24:46.290500: step: 2048/530, loss: 0.00246158754453063
2023-01-22 16:24:47.347288: step: 2052/530, loss: 0.005010621156543493
2023-01-22 16:24:48.416386: step: 2056/530, loss: 0.003826865227892995
2023-01-22 16:24:49.475747: step: 2060/530, loss: 0.027288202196359634
2023-01-22 16:24:50.536809: step: 2064/530, loss: 0.005993329919874668
2023-01-22 16:24:51.610716: step: 2068/530, loss: 0.005882537458091974
2023-01-22 16:24:52.664275: step: 2072/530, loss: 0.005566827952861786
2023-01-22 16:24:53.735258: step: 2076/530, loss: 0.02576258033514023
2023-01-22 16:24:54.794917: step: 2080/530, loss: 0.0036768531426787376
2023-01-22 16:24:55.852878: step: 2084/530, loss: 0.019224215298891068
2023-01-22 16:24:56.916872: step: 2088/530, loss: 0.005851175170391798
2023-01-22 16:24:57.987290: step: 2092/530, loss: 0.007477684877812862
2023-01-22 16:24:59.049405: step: 2096/530, loss: 0.0010198538657277822
2023-01-22 16:25:00.099350: step: 2100/530, loss: 0.02209564484655857
2023-01-22 16:25:01.148400: step: 2104/530, loss: 0.007262577768415213
2023-01-22 16:25:02.221439: step: 2108/530, loss: 0.020717797800898552
2023-01-22 16:25:03.295032: step: 2112/530, loss: 0.016722410917282104
2023-01-22 16:25:04.364965: step: 2116/530, loss: 0.015207355841994286
2023-01-22 16:25:05.414401: step: 2120/530, loss: 0.0026982848066836596
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3483990510665856, 'r': 0.23377425504467864, 'f1': 0.2798023467115066}, 'combined': 0.1855683957464914, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32151825085742286, 'r': 0.2868088942307692, 'f1': 0.3031733656733657}, 'combined': 0.20211557711557715, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4032017770595596, 'r': 0.32367755113431773, 'f1': 0.3590894905098573}, 'combined': 0.2343531411748542, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3206798353571819, 'r': 0.3371093525386694, 'f1': 0.328689414963698}, 'combined': 0.24219220049956694, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3600568696828141, 'r': 0.3344943906230818, 'f1': 0.3468052254664807}, 'combined': 0.23000553813320995, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.36237373737373735, 'r': 0.3416666666666666, 'f1': 0.3517156862745098}, 'combined': 0.2344771241830065, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:27:33.544377: step: 4/530, loss: 0.005412028171122074
2023-01-22 16:27:34.594700: step: 8/530, loss: 0.00799354538321495
2023-01-22 16:27:35.643571: step: 12/530, loss: 0.0029653378296643496
2023-01-22 16:27:36.695232: step: 16/530, loss: 0.0020137429237365723
2023-01-22 16:27:37.757170: step: 20/530, loss: 0.005955493077635765
2023-01-22 16:27:38.823903: step: 24/530, loss: 0.0054463790729641914
2023-01-22 16:27:39.873739: step: 28/530, loss: 0.012393060140311718
2023-01-22 16:27:40.919793: step: 32/530, loss: 0.011158104054629803
2023-01-22 16:27:41.966449: step: 36/530, loss: 0.00027762309764511883
2023-01-22 16:27:43.030898: step: 40/530, loss: 0.007811457850039005
2023-01-22 16:27:44.093350: step: 44/530, loss: 0.003230190835893154
2023-01-22 16:27:45.145638: step: 48/530, loss: 0.001531480811536312
2023-01-22 16:27:46.222065: step: 52/530, loss: 0.007215119898319244
2023-01-22 16:27:47.295844: step: 56/530, loss: 0.003241087542846799
2023-01-22 16:27:48.342951: step: 60/530, loss: 0.008438044227659702
2023-01-22 16:27:49.387161: step: 64/530, loss: 0.000715838628821075
2023-01-22 16:27:50.438504: step: 68/530, loss: 0.009207389317452908
2023-01-22 16:27:51.495502: step: 72/530, loss: 0.002230619313195348
2023-01-22 16:27:52.550250: step: 76/530, loss: 0.004442438017576933
2023-01-22 16:27:53.606779: step: 80/530, loss: 0.004486694000661373
2023-01-22 16:27:54.672565: step: 84/530, loss: 0.0038605076260864735
2023-01-22 16:27:55.742848: step: 88/530, loss: 0.006671932991594076
2023-01-22 16:27:56.828592: step: 92/530, loss: 0.004980923607945442
2023-01-22 16:27:57.890241: step: 96/530, loss: 0.006761566270142794
2023-01-22 16:27:58.969278: step: 100/530, loss: 0.008938229642808437
2023-01-22 16:28:00.037748: step: 104/530, loss: 0.0012818132527172565
2023-01-22 16:28:01.114146: step: 108/530, loss: 0.0050885300152003765
2023-01-22 16:28:02.176489: step: 112/530, loss: 0.0027815958019346
2023-01-22 16:28:03.240036: step: 116/530, loss: 0.00494090560823679
2023-01-22 16:28:04.322539: step: 120/530, loss: 0.00021240457135718316
2023-01-22 16:28:05.368964: step: 124/530, loss: 0.0010529932333156466
2023-01-22 16:28:06.418713: step: 128/530, loss: 0.004356097895652056
2023-01-22 16:28:07.478621: step: 132/530, loss: 0.0007834674906916916
2023-01-22 16:28:08.538789: step: 136/530, loss: 0.00023933756165206432
2023-01-22 16:28:09.612590: step: 140/530, loss: 0.002770785940811038
2023-01-22 16:28:10.686151: step: 144/530, loss: 0.0031675801146775484
2023-01-22 16:28:11.748889: step: 148/530, loss: 0.0037156403996050358
2023-01-22 16:28:12.814170: step: 152/530, loss: 0.009367075748741627
2023-01-22 16:28:13.854878: step: 156/530, loss: 0.0020011523738503456
2023-01-22 16:28:14.916970: step: 160/530, loss: 0.008942898362874985
2023-01-22 16:28:15.977867: step: 164/530, loss: 0.0025392426177859306
2023-01-22 16:28:17.041606: step: 168/530, loss: 0.0016115570906549692
2023-01-22 16:28:18.102179: step: 172/530, loss: 0.001309082144871354
2023-01-22 16:28:19.168643: step: 176/530, loss: 0.006817675661295652
2023-01-22 16:28:20.231621: step: 180/530, loss: 0.010326175019145012
2023-01-22 16:28:21.288552: step: 184/530, loss: 0.008611856028437614
2023-01-22 16:28:22.348297: step: 188/530, loss: 0.001145673100836575
2023-01-22 16:28:23.415523: step: 192/530, loss: 0.000756487890612334
2023-01-22 16:28:24.490237: step: 196/530, loss: 0.001342158648185432
2023-01-22 16:28:25.541981: step: 200/530, loss: 0.00012038677232339978
2023-01-22 16:28:26.609052: step: 204/530, loss: 2.525281706766691e-05
2023-01-22 16:28:27.681471: step: 208/530, loss: 0.011847678571939468
2023-01-22 16:28:28.750017: step: 212/530, loss: 0.0037661634851247072
2023-01-22 16:28:29.826650: step: 216/530, loss: 0.012080597691237926
2023-01-22 16:28:30.891675: step: 220/530, loss: 0.008036069571971893
2023-01-22 16:28:31.955755: step: 224/530, loss: 0.0011363114463165402
2023-01-22 16:28:33.049393: step: 228/530, loss: 0.004003074485808611
2023-01-22 16:28:34.104163: step: 232/530, loss: 0.011443397961556911
2023-01-22 16:28:35.174958: step: 236/530, loss: 0.004135990981012583
2023-01-22 16:28:36.247961: step: 240/530, loss: 0.00223351432941854
2023-01-22 16:28:37.304575: step: 244/530, loss: 0.019779633730649948
2023-01-22 16:28:38.354835: step: 248/530, loss: 0.0012376937083899975
2023-01-22 16:28:39.422150: step: 252/530, loss: 0.0026815005112439394
2023-01-22 16:28:40.479517: step: 256/530, loss: 0.0013566955458372831
2023-01-22 16:28:41.540523: step: 260/530, loss: 0.003945737611502409
2023-01-22 16:28:42.600947: step: 264/530, loss: 0.0039780898950994015
2023-01-22 16:28:43.673180: step: 268/530, loss: 0.0025932311546057463
2023-01-22 16:28:44.742936: step: 272/530, loss: 0.005599125754088163
2023-01-22 16:28:45.792032: step: 276/530, loss: 0.005882116965949535
2023-01-22 16:28:46.863523: step: 280/530, loss: 0.004954581148922443
2023-01-22 16:28:47.923618: step: 284/530, loss: 0.0007497848710045218
2023-01-22 16:28:48.958514: step: 288/530, loss: 0.028717370703816414
2023-01-22 16:28:50.013170: step: 292/530, loss: 0.012738501653075218
2023-01-22 16:28:51.078505: step: 296/530, loss: 0.0017897089710459113
2023-01-22 16:28:52.144976: step: 300/530, loss: 0.0008936472004279494
2023-01-22 16:28:53.208217: step: 304/530, loss: 0.002889385214075446
2023-01-22 16:28:54.272978: step: 308/530, loss: 0.01940256729722023
2023-01-22 16:28:55.341287: step: 312/530, loss: 0.0032737015280872583
2023-01-22 16:28:56.402425: step: 316/530, loss: 0.0023911716416478157
2023-01-22 16:28:57.470493: step: 320/530, loss: 0.009060151875019073
2023-01-22 16:28:58.576759: step: 324/530, loss: 0.008702633902430534
2023-01-22 16:28:59.630895: step: 328/530, loss: 0.0012962038163095713
2023-01-22 16:29:00.683667: step: 332/530, loss: 0.003141292603686452
2023-01-22 16:29:01.734494: step: 336/530, loss: 0.02390456199645996
2023-01-22 16:29:02.811240: step: 340/530, loss: 0.002323173452168703
2023-01-22 16:29:03.853585: step: 344/530, loss: 0.0007194870850071311
2023-01-22 16:29:04.918037: step: 348/530, loss: 0.010091970674693584
2023-01-22 16:29:05.971024: step: 352/530, loss: 0.008088504895567894
2023-01-22 16:29:07.018579: step: 356/530, loss: 0.007213442120701075
2023-01-22 16:29:08.106855: step: 360/530, loss: 0.005028596147894859
2023-01-22 16:29:09.159516: step: 364/530, loss: 0.028195269405841827
2023-01-22 16:29:10.220501: step: 368/530, loss: 0.0008819270879030228
2023-01-22 16:29:11.274689: step: 372/530, loss: 0.002613019198179245
2023-01-22 16:29:12.321189: step: 376/530, loss: 0.0042737871408462524
2023-01-22 16:29:13.390525: step: 380/530, loss: 0.0020033158361911774
2023-01-22 16:29:14.464812: step: 384/530, loss: 0.008950011804699898
2023-01-22 16:29:15.548506: step: 388/530, loss: 0.03141036257147789
2023-01-22 16:29:16.620540: step: 392/530, loss: 0.002115897135809064
2023-01-22 16:29:17.686277: step: 396/530, loss: 0.007330651860684156
2023-01-22 16:29:18.766866: step: 400/530, loss: 0.00850588083267212
2023-01-22 16:29:19.829201: step: 404/530, loss: 0.007080476265400648
2023-01-22 16:29:20.890157: step: 408/530, loss: 0.027313269674777985
2023-01-22 16:29:21.942382: step: 412/530, loss: 0.004629465285688639
2023-01-22 16:29:23.008707: step: 416/530, loss: 0.0057193925604224205
2023-01-22 16:29:24.069257: step: 420/530, loss: 0.002772792475298047
2023-01-22 16:29:25.133681: step: 424/530, loss: 0.005171502940356731
2023-01-22 16:29:26.206942: step: 428/530, loss: 0.004835939966142178
2023-01-22 16:29:27.273161: step: 432/530, loss: 0.0023077453952282667
2023-01-22 16:29:28.329123: step: 436/530, loss: 0.00010802211181726307
2023-01-22 16:29:29.402064: step: 440/530, loss: 0.010833747684955597
2023-01-22 16:29:30.453769: step: 444/530, loss: 0.00038866957766003907
2023-01-22 16:29:31.500081: step: 448/530, loss: 0.0002362951636314392
2023-01-22 16:29:32.566369: step: 452/530, loss: 0.005280998535454273
2023-01-22 16:29:33.628698: step: 456/530, loss: 0.012531696818768978
2023-01-22 16:29:34.675932: step: 460/530, loss: 0.001054047723300755
2023-01-22 16:29:35.714077: step: 464/530, loss: 0.00017180261784233153
2023-01-22 16:29:36.800281: step: 468/530, loss: 0.026325508952140808
2023-01-22 16:29:37.867896: step: 472/530, loss: 0.015517164953052998
2023-01-22 16:29:38.925227: step: 476/530, loss: 0.004619554150849581
2023-01-22 16:29:39.987564: step: 480/530, loss: 0.0022884318605065346
2023-01-22 16:29:41.063117: step: 484/530, loss: 0.009126914665102959
2023-01-22 16:29:42.125776: step: 488/530, loss: 0.007223417051136494
2023-01-22 16:29:43.183517: step: 492/530, loss: 0.0011125747114419937
2023-01-22 16:29:44.246026: step: 496/530, loss: 0.002948937937617302
2023-01-22 16:29:45.300322: step: 500/530, loss: 0.0010918269399553537
2023-01-22 16:29:46.366595: step: 504/530, loss: 0.0006206376128830016
2023-01-22 16:29:47.440942: step: 508/530, loss: 0.004366508685052395
2023-01-22 16:29:48.502656: step: 512/530, loss: 0.0027248221449553967
2023-01-22 16:29:49.560214: step: 516/530, loss: 0.003083973890170455
2023-01-22 16:29:50.633118: step: 520/530, loss: 0.006019479129463434
2023-01-22 16:29:51.705972: step: 524/530, loss: 0.004589051939547062
2023-01-22 16:29:52.767033: step: 528/530, loss: 0.03312420845031738
2023-01-22 16:29:53.817741: step: 532/530, loss: 0.0002147872728528455
2023-01-22 16:29:54.890611: step: 536/530, loss: 0.004653861280530691
2023-01-22 16:29:55.945536: step: 540/530, loss: 0.005667768884450197
2023-01-22 16:29:57.014143: step: 544/530, loss: 0.008122372440993786
2023-01-22 16:29:58.069321: step: 548/530, loss: 0.0036178031004965305
2023-01-22 16:29:59.140086: step: 552/530, loss: 0.0012721389066427946
2023-01-22 16:30:00.202653: step: 556/530, loss: 0.006121991667896509
2023-01-22 16:30:01.265600: step: 560/530, loss: 0.0004973919130861759
2023-01-22 16:30:02.337116: step: 564/530, loss: 0.0072229038923978806
2023-01-22 16:30:03.410085: step: 568/530, loss: 0.003401955356821418
2023-01-22 16:30:04.478762: step: 572/530, loss: 0.0019759531132876873
2023-01-22 16:30:05.542811: step: 576/530, loss: 0.007179000414907932
2023-01-22 16:30:06.591033: step: 580/530, loss: 0.01063327956944704
2023-01-22 16:30:07.658001: step: 584/530, loss: 0.005065048113465309
2023-01-22 16:30:08.717846: step: 588/530, loss: 0.008108510635793209
2023-01-22 16:30:09.776098: step: 592/530, loss: 0.00701938197016716
2023-01-22 16:30:10.853209: step: 596/530, loss: 0.0002842854300979525
2023-01-22 16:30:11.914288: step: 600/530, loss: 0.0016940321074798703
2023-01-22 16:30:12.970444: step: 604/530, loss: 0.025617994368076324
2023-01-22 16:30:14.027691: step: 608/530, loss: 4.666324457502924e-05
2023-01-22 16:30:15.110927: step: 612/530, loss: 0.005088458303362131
2023-01-22 16:30:16.161096: step: 616/530, loss: 0.008997460827231407
2023-01-22 16:30:17.225435: step: 620/530, loss: 0.002423650585114956
2023-01-22 16:30:18.277628: step: 624/530, loss: 0.056079424917697906
2023-01-22 16:30:19.342666: step: 628/530, loss: 0.012369221076369286
2023-01-22 16:30:20.399851: step: 632/530, loss: 0.0015017739497125149
2023-01-22 16:30:21.463010: step: 636/530, loss: 0.007779762148857117
2023-01-22 16:30:22.515685: step: 640/530, loss: 0.00034266404691152275
2023-01-22 16:30:23.586974: step: 644/530, loss: 0.008342042565345764
2023-01-22 16:30:24.648856: step: 648/530, loss: 0.00013007245433982462
2023-01-22 16:30:25.733075: step: 652/530, loss: 0.0007750781951472163
2023-01-22 16:30:26.786135: step: 656/530, loss: 0.0018715604674071074
2023-01-22 16:30:27.848605: step: 660/530, loss: 0.0016354137333109975
2023-01-22 16:30:28.934194: step: 664/530, loss: 0.0012279903749004006
2023-01-22 16:30:30.013029: step: 668/530, loss: 0.009681175462901592
2023-01-22 16:30:31.080365: step: 672/530, loss: 0.003347435500472784
2023-01-22 16:30:32.158055: step: 676/530, loss: 0.011745578609406948
2023-01-22 16:30:33.220933: step: 680/530, loss: 0.00831012986600399
2023-01-22 16:30:34.277394: step: 684/530, loss: 0.001262263860553503
2023-01-22 16:30:35.353146: step: 688/530, loss: 0.0048485505394637585
2023-01-22 16:30:36.407263: step: 692/530, loss: 0.014339500106871128
2023-01-22 16:30:37.465941: step: 696/530, loss: 0.007572287227958441
2023-01-22 16:30:38.536111: step: 700/530, loss: 0.010303635150194168
2023-01-22 16:30:39.595046: step: 704/530, loss: 0.00027843870338983834
2023-01-22 16:30:40.649495: step: 708/530, loss: 0.01371452771127224
2023-01-22 16:30:41.709172: step: 712/530, loss: 0.00042528987978585064
2023-01-22 16:30:42.762536: step: 716/530, loss: 0.0005616341950371861
2023-01-22 16:30:43.825754: step: 720/530, loss: 0.0028855102136731148
2023-01-22 16:30:44.901052: step: 724/530, loss: 0.001164730405434966
2023-01-22 16:30:45.947009: step: 728/530, loss: 0.0011211609235033393
2023-01-22 16:30:47.018614: step: 732/530, loss: 0.015907419845461845
2023-01-22 16:30:48.085468: step: 736/530, loss: 0.08569792658090591
2023-01-22 16:30:49.152826: step: 740/530, loss: 0.023858193308115005
2023-01-22 16:30:50.201934: step: 744/530, loss: 0.0037874882109463215
2023-01-22 16:30:51.280979: step: 748/530, loss: 0.0006449953652918339
2023-01-22 16:30:52.336934: step: 752/530, loss: 9.023010534292553e-06
2023-01-22 16:30:53.374174: step: 756/530, loss: 0.0008476577349938452
2023-01-22 16:30:54.426057: step: 760/530, loss: 0.00924161821603775
2023-01-22 16:30:55.476059: step: 764/530, loss: 0.0001442963257431984
2023-01-22 16:30:56.522893: step: 768/530, loss: 0.015980752184987068
2023-01-22 16:30:57.585552: step: 772/530, loss: 5.119547495269217e-06
2023-01-22 16:30:58.658702: step: 776/530, loss: 0.00010676019883248955
2023-01-22 16:30:59.716425: step: 780/530, loss: 0.0024200999177992344
2023-01-22 16:31:00.778057: step: 784/530, loss: 0.003979182336479425
2023-01-22 16:31:01.835719: step: 788/530, loss: 0.0018113116966560483
2023-01-22 16:31:02.908161: step: 792/530, loss: 0.008732148446142673
2023-01-22 16:31:03.978016: step: 796/530, loss: 0.003172091208398342
2023-01-22 16:31:05.039218: step: 800/530, loss: 0.004854040220379829
2023-01-22 16:31:06.125201: step: 804/530, loss: 0.004063732456415892
2023-01-22 16:31:07.199488: step: 808/530, loss: 0.0013634428614750504
2023-01-22 16:31:08.258962: step: 812/530, loss: 0.005167086608707905
2023-01-22 16:31:09.310584: step: 816/530, loss: 0.012295229360461235
2023-01-22 16:31:10.364612: step: 820/530, loss: 0.006900577340275049
2023-01-22 16:31:11.427325: step: 824/530, loss: 5.419595981948078e-05
2023-01-22 16:31:12.506016: step: 828/530, loss: 0.006632449571043253
2023-01-22 16:31:13.569569: step: 832/530, loss: 0.0017331892158836126
2023-01-22 16:31:14.623018: step: 836/530, loss: 0.0006142915808595717
2023-01-22 16:31:15.674176: step: 840/530, loss: 0.0037633369211107492
2023-01-22 16:31:16.725728: step: 844/530, loss: 0.0010070562129840255
2023-01-22 16:31:17.779116: step: 848/530, loss: 0.002478070789948106
2023-01-22 16:31:18.842857: step: 852/530, loss: 0.003714849939569831
2023-01-22 16:31:19.896705: step: 856/530, loss: 0.0009307508589699864
2023-01-22 16:31:20.952561: step: 860/530, loss: 0.0010487677063792944
2023-01-22 16:31:22.015547: step: 864/530, loss: 0.0012491183588281274
2023-01-22 16:31:23.095364: step: 868/530, loss: 0.007583253085613251
2023-01-22 16:31:24.180512: step: 872/530, loss: 0.005695600062608719
2023-01-22 16:31:25.240056: step: 876/530, loss: 0.003532192436978221
2023-01-22 16:31:26.292573: step: 880/530, loss: 0.028896501287817955
2023-01-22 16:31:27.352128: step: 884/530, loss: 0.0018249228596687317
2023-01-22 16:31:28.418897: step: 888/530, loss: 0.006584419868886471
2023-01-22 16:31:29.462889: step: 892/530, loss: 0.004012554418295622
2023-01-22 16:31:30.548065: step: 896/530, loss: 0.021657193079590797
2023-01-22 16:31:31.617244: step: 900/530, loss: 0.003510869573801756
2023-01-22 16:31:32.664604: step: 904/530, loss: 9.504158515483141e-05
2023-01-22 16:31:33.738197: step: 908/530, loss: 0.015397016890347004
2023-01-22 16:31:34.818087: step: 912/530, loss: 0.050935372710227966
2023-01-22 16:31:35.896143: step: 916/530, loss: 0.005209668073803186
2023-01-22 16:31:36.949334: step: 920/530, loss: 0.0015431750798597932
2023-01-22 16:31:38.018927: step: 924/530, loss: 0.004369240254163742
2023-01-22 16:31:39.077734: step: 928/530, loss: 0.03550203517079353
2023-01-22 16:31:40.143564: step: 932/530, loss: 0.006693502422422171
2023-01-22 16:31:41.218916: step: 936/530, loss: 0.00041917807538993657
2023-01-22 16:31:42.276009: step: 940/530, loss: 0.0028434705454856157
2023-01-22 16:31:43.354411: step: 944/530, loss: 0.002211144659668207
2023-01-22 16:31:44.407348: step: 948/530, loss: 0.006492828484624624
2023-01-22 16:31:45.483873: step: 952/530, loss: 0.02865644358098507
2023-01-22 16:31:46.550225: step: 956/530, loss: 0.007353669963777065
2023-01-22 16:31:47.590923: step: 960/530, loss: 0.004926623776555061
2023-01-22 16:31:48.644581: step: 964/530, loss: 0.0020286948420107365
2023-01-22 16:31:49.720854: step: 968/530, loss: 0.002209634752944112
2023-01-22 16:31:50.790676: step: 972/530, loss: 0.0023933867923915386
2023-01-22 16:31:51.844456: step: 976/530, loss: 0.0006421073921956122
2023-01-22 16:31:52.909859: step: 980/530, loss: 0.0014324311632663012
2023-01-22 16:31:53.965448: step: 984/530, loss: 0.0019344848114997149
2023-01-22 16:31:55.043033: step: 988/530, loss: 0.05040892958641052
2023-01-22 16:31:56.104716: step: 992/530, loss: 0.0019419536693021655
2023-01-22 16:31:57.161021: step: 996/530, loss: 0.001619693823158741
2023-01-22 16:31:58.230704: step: 1000/530, loss: 0.014715269207954407
2023-01-22 16:31:59.298471: step: 1004/530, loss: 0.030769888311624527
2023-01-22 16:32:00.388359: step: 1008/530, loss: 0.0016084014205262065
2023-01-22 16:32:01.454980: step: 1012/530, loss: 0.007312459871172905
2023-01-22 16:32:02.508188: step: 1016/530, loss: 0.005628805607557297
2023-01-22 16:32:03.564902: step: 1020/530, loss: 0.0025717057287693024
2023-01-22 16:32:04.624839: step: 1024/530, loss: 0.00790424831211567
2023-01-22 16:32:05.676818: step: 1028/530, loss: 0.003198872087523341
2023-01-22 16:32:06.728953: step: 1032/530, loss: 0.011551324278116226
2023-01-22 16:32:07.794516: step: 1036/530, loss: 0.0030645655933767557
2023-01-22 16:32:08.877565: step: 1040/530, loss: 0.005343732889741659
2023-01-22 16:32:09.939856: step: 1044/530, loss: 0.00837535411119461
2023-01-22 16:32:11.005979: step: 1048/530, loss: 0.00354607030749321
2023-01-22 16:32:12.065073: step: 1052/530, loss: 0.0015075349947437644
2023-01-22 16:32:13.120141: step: 1056/530, loss: 0.003086197655647993
2023-01-22 16:32:14.167586: step: 1060/530, loss: 0.0021570981480181217
2023-01-22 16:32:15.230508: step: 1064/530, loss: 0.00012293148029129952
2023-01-22 16:32:16.297777: step: 1068/530, loss: 0.0034800937864929438
2023-01-22 16:32:17.351398: step: 1072/530, loss: 0.030885253101587296
2023-01-22 16:32:18.416426: step: 1076/530, loss: 0.006151766516268253
2023-01-22 16:32:19.502237: step: 1080/530, loss: 0.0034379761200398207
2023-01-22 16:32:20.559869: step: 1084/530, loss: 0.001509494730271399
2023-01-22 16:32:21.628862: step: 1088/530, loss: 0.0024860992562025785
2023-01-22 16:32:22.682752: step: 1092/530, loss: 5.1756880566244945e-05
2023-01-22 16:32:23.755441: step: 1096/530, loss: 0.025292042642831802
2023-01-22 16:32:24.830670: step: 1100/530, loss: 0.0009208132396452129
2023-01-22 16:32:25.890328: step: 1104/530, loss: 0.0038977907970547676
2023-01-22 16:32:26.945177: step: 1108/530, loss: 0.005086773540824652
2023-01-22 16:32:28.003205: step: 1112/530, loss: 0.0033402193803340197
2023-01-22 16:32:29.061395: step: 1116/530, loss: 0.0027043165173381567
2023-01-22 16:32:30.141948: step: 1120/530, loss: 0.012632989324629307
2023-01-22 16:32:31.203329: step: 1124/530, loss: 0.006464587990194559
2023-01-22 16:32:32.258999: step: 1128/530, loss: 0.009527401067316532
2023-01-22 16:32:33.316040: step: 1132/530, loss: 0.0022216616198420525
2023-01-22 16:32:34.385960: step: 1136/530, loss: 0.002615844365209341
2023-01-22 16:32:35.441752: step: 1140/530, loss: 0.006682222709059715
2023-01-22 16:32:36.538517: step: 1144/530, loss: 0.0048462203703820705
2023-01-22 16:32:37.586917: step: 1148/530, loss: 0.0007670805207453668
2023-01-22 16:32:38.664342: step: 1152/530, loss: 0.009593291208148003
2023-01-22 16:32:39.721347: step: 1156/530, loss: 0.0004975621704943478
2023-01-22 16:32:40.787516: step: 1160/530, loss: 0.009345789439976215
2023-01-22 16:32:41.845926: step: 1164/530, loss: 0.0008754830923862755
2023-01-22 16:32:42.915544: step: 1168/530, loss: 0.011169680394232273
2023-01-22 16:32:43.972609: step: 1172/530, loss: 0.0026201759465038776
2023-01-22 16:32:45.035527: step: 1176/530, loss: 0.011243724264204502
2023-01-22 16:32:46.088439: step: 1180/530, loss: 0.0019960992503911257
2023-01-22 16:32:47.156040: step: 1184/530, loss: 1.4583305528503843e-05
2023-01-22 16:32:48.219747: step: 1188/530, loss: 0.007272704038769007
2023-01-22 16:32:49.278627: step: 1192/530, loss: 0.002686869353055954
2023-01-22 16:32:50.342170: step: 1196/530, loss: 0.005081926006823778
2023-01-22 16:32:51.396824: step: 1200/530, loss: 0.001307943370193243
2023-01-22 16:32:52.452252: step: 1204/530, loss: 0.0031069398391991854
2023-01-22 16:32:53.505154: step: 1208/530, loss: 0.0005948446341790259
2023-01-22 16:32:54.562963: step: 1212/530, loss: 1.0914909580606036e-06
2023-01-22 16:32:55.622225: step: 1216/530, loss: 0.0038150139153003693
2023-01-22 16:32:56.687529: step: 1220/530, loss: 0.0026223729364573956
2023-01-22 16:32:57.736441: step: 1224/530, loss: 0.004283602349460125
2023-01-22 16:32:58.812313: step: 1228/530, loss: 0.0072454530745744705
2023-01-22 16:32:59.860570: step: 1232/530, loss: 0.009494572877883911
2023-01-22 16:33:00.902136: step: 1236/530, loss: 0.0005140142166055739
2023-01-22 16:33:01.950414: step: 1240/530, loss: 0.0007592645124532282
2023-01-22 16:33:03.036490: step: 1244/530, loss: 0.0071346634067595005
2023-01-22 16:33:04.113162: step: 1248/530, loss: 0.0038870633579790592
2023-01-22 16:33:05.194790: step: 1252/530, loss: 0.0030153635889291763
2023-01-22 16:33:06.242654: step: 1256/530, loss: 0.001416281796991825
2023-01-22 16:33:07.307009: step: 1260/530, loss: 0.0018125182250514627
2023-01-22 16:33:08.382622: step: 1264/530, loss: 0.010289902798831463
2023-01-22 16:33:09.465418: step: 1268/530, loss: 0.0031385901384055614
2023-01-22 16:33:10.527475: step: 1272/530, loss: 0.003156331367790699
2023-01-22 16:33:11.593856: step: 1276/530, loss: 0.005723380483686924
2023-01-22 16:33:12.644740: step: 1280/530, loss: 0.01197907142341137
2023-01-22 16:33:13.692144: step: 1284/530, loss: 0.007802318315953016
2023-01-22 16:33:14.750174: step: 1288/530, loss: 0.01617361046373844
2023-01-22 16:33:15.800591: step: 1292/530, loss: 0.009799396619200706
2023-01-22 16:33:16.853915: step: 1296/530, loss: 0.02666343003511429
2023-01-22 16:33:17.920762: step: 1300/530, loss: 0.0029205642640590668
2023-01-22 16:33:18.991345: step: 1304/530, loss: 0.008449913933873177
2023-01-22 16:33:20.046525: step: 1308/530, loss: 0.012554100714623928
2023-01-22 16:33:21.113281: step: 1312/530, loss: 0.002242621034383774
2023-01-22 16:33:22.177030: step: 1316/530, loss: 0.005994822364300489
2023-01-22 16:33:23.246054: step: 1320/530, loss: 0.003377022221684456
2023-01-22 16:33:24.320844: step: 1324/530, loss: 0.005406593903899193
2023-01-22 16:33:25.386573: step: 1328/530, loss: 0.01103257667273283
2023-01-22 16:33:26.464094: step: 1332/530, loss: 0.002860089996829629
2023-01-22 16:33:27.542110: step: 1336/530, loss: 0.0015651839785277843
2023-01-22 16:33:28.598904: step: 1340/530, loss: 0.005619209725409746
2023-01-22 16:33:29.689156: step: 1344/530, loss: 0.007609691470861435
2023-01-22 16:33:30.741937: step: 1348/530, loss: 0.0023679123260080814
2023-01-22 16:33:31.808852: step: 1352/530, loss: 0.0014374775346368551
2023-01-22 16:33:32.887728: step: 1356/530, loss: 0.004368546884506941
2023-01-22 16:33:33.955691: step: 1360/530, loss: 0.00044674932723864913
2023-01-22 16:33:35.024490: step: 1364/530, loss: 0.007170870900154114
2023-01-22 16:33:36.070482: step: 1368/530, loss: 0.0070548150688409805
2023-01-22 16:33:37.127048: step: 1372/530, loss: 0.0036726747639477253
2023-01-22 16:33:38.168844: step: 1376/530, loss: 0.0034284647554159164
2023-01-22 16:33:39.231448: step: 1380/530, loss: 0.0032980607356876135
2023-01-22 16:33:40.296318: step: 1384/530, loss: 0.008908475749194622
2023-01-22 16:33:41.354595: step: 1388/530, loss: 4.6096618461888283e-05
2023-01-22 16:33:42.401047: step: 1392/530, loss: 0.00038111634785309434
2023-01-22 16:33:43.461295: step: 1396/530, loss: 0.002776114968582988
2023-01-22 16:33:44.560616: step: 1400/530, loss: 0.013103046454489231
2023-01-22 16:33:45.611511: step: 1404/530, loss: 0.012746206484735012
2023-01-22 16:33:46.667929: step: 1408/530, loss: 0.0025733094662427902
2023-01-22 16:33:47.735646: step: 1412/530, loss: 0.007026394363492727
2023-01-22 16:33:48.789274: step: 1416/530, loss: 0.004523235838860273
2023-01-22 16:33:49.850346: step: 1420/530, loss: 0.0043120249174535275
2023-01-22 16:33:50.899266: step: 1424/530, loss: 0.001962050097063184
2023-01-22 16:33:51.943858: step: 1428/530, loss: 0.0013175873318687081
2023-01-22 16:33:53.000565: step: 1432/530, loss: 0.008567588403820992
2023-01-22 16:33:54.061535: step: 1436/530, loss: 0.015097937546670437
2023-01-22 16:33:55.120310: step: 1440/530, loss: 0.005013413727283478
2023-01-22 16:33:56.186712: step: 1444/530, loss: 0.0019324166933074594
2023-01-22 16:33:57.247552: step: 1448/530, loss: 0.0024225011002272367
2023-01-22 16:33:58.296864: step: 1452/530, loss: 0.0022114012390375137
2023-01-22 16:33:59.343347: step: 1456/530, loss: 0.004004094284027815
2023-01-22 16:34:00.430553: step: 1460/530, loss: 0.010377401486039162
2023-01-22 16:34:01.497801: step: 1464/530, loss: 0.005856323521584272
2023-01-22 16:34:02.564970: step: 1468/530, loss: 0.0006262914394028485
2023-01-22 16:34:03.615952: step: 1472/530, loss: 0.004930655471980572
2023-01-22 16:34:04.674817: step: 1476/530, loss: 0.00011783480294980109
2023-01-22 16:34:05.743907: step: 1480/530, loss: 0.0012534589041024446
2023-01-22 16:34:06.798287: step: 1484/530, loss: 0.006297635845839977
2023-01-22 16:34:07.853425: step: 1488/530, loss: 0.001348702935501933
2023-01-22 16:34:08.912086: step: 1492/530, loss: 0.002381858415901661
2023-01-22 16:34:09.958958: step: 1496/530, loss: 0.0017556046368554235
2023-01-22 16:34:11.030552: step: 1500/530, loss: 0.0036560851149260998
2023-01-22 16:34:12.072894: step: 1504/530, loss: 0.00041475845500826836
2023-01-22 16:34:13.119398: step: 1508/530, loss: 0.02395522966980934
2023-01-22 16:34:14.184449: step: 1512/530, loss: 0.0092427097260952
2023-01-22 16:34:15.232859: step: 1516/530, loss: 0.0
2023-01-22 16:34:16.295555: step: 1520/530, loss: 0.0024025836028158665
2023-01-22 16:34:17.341787: step: 1524/530, loss: 0.0044045038521289825
2023-01-22 16:34:18.406715: step: 1528/530, loss: 0.0007563966792076826
2023-01-22 16:34:19.469902: step: 1532/530, loss: 0.0017078659730032086
2023-01-22 16:34:20.541209: step: 1536/530, loss: 0.0018770396709442139
2023-01-22 16:34:21.604244: step: 1540/530, loss: 0.0038097607903182507
2023-01-22 16:34:22.662581: step: 1544/530, loss: 0.0037790362257510424
2023-01-22 16:34:23.719934: step: 1548/530, loss: 0.01185193657875061
2023-01-22 16:34:24.766063: step: 1552/530, loss: 0.0014775642193853855
2023-01-22 16:34:25.845597: step: 1556/530, loss: 0.004230780992656946
2023-01-22 16:34:26.905666: step: 1560/530, loss: 0.005669799167662859
2023-01-22 16:34:27.978540: step: 1564/530, loss: 0.008223684504628181
2023-01-22 16:34:29.029742: step: 1568/530, loss: 0.0006993726710788906
2023-01-22 16:34:30.092696: step: 1572/530, loss: 0.012956804595887661
2023-01-22 16:34:31.130716: step: 1576/530, loss: 0.019530994817614555
2023-01-22 16:34:32.198660: step: 1580/530, loss: 0.015981880947947502
2023-01-22 16:34:33.255571: step: 1584/530, loss: 0.028154440224170685
2023-01-22 16:34:34.301458: step: 1588/530, loss: 0.0001211744238389656
2023-01-22 16:34:35.362084: step: 1592/530, loss: 0.002829579869285226
2023-01-22 16:34:36.424451: step: 1596/530, loss: 0.008065136149525642
2023-01-22 16:34:37.497009: step: 1600/530, loss: 0.004729262553155422
2023-01-22 16:34:38.548520: step: 1604/530, loss: 0.0032550536561757326
2023-01-22 16:34:39.604623: step: 1608/530, loss: 0.00024565367493778467
2023-01-22 16:34:40.657856: step: 1612/530, loss: 0.0001351367827737704
2023-01-22 16:34:41.721017: step: 1616/530, loss: 0.03533303365111351
2023-01-22 16:34:42.808765: step: 1620/530, loss: 0.002575187012553215
2023-01-22 16:34:43.861751: step: 1624/530, loss: 0.005571381654590368
2023-01-22 16:34:44.907174: step: 1628/530, loss: 0.019285814836621284
2023-01-22 16:34:45.961507: step: 1632/530, loss: 0.005768598057329655
2023-01-22 16:34:47.015071: step: 1636/530, loss: 0.009555893950164318
2023-01-22 16:34:48.097125: step: 1640/530, loss: 0.032931383699178696
2023-01-22 16:34:49.166308: step: 1644/530, loss: 0.007134437561035156
2023-01-22 16:34:50.233294: step: 1648/530, loss: 0.003770155366510153
2023-01-22 16:34:51.280566: step: 1652/530, loss: 0.0008252543630078435
2023-01-22 16:34:52.338724: step: 1656/530, loss: 0.008655122481286526
2023-01-22 16:34:53.389252: step: 1660/530, loss: 1.3274970115162432e-05
2023-01-22 16:34:54.455556: step: 1664/530, loss: 0.013387207873165607
2023-01-22 16:34:55.516014: step: 1668/530, loss: 0.00020029177539981902
2023-01-22 16:34:56.583129: step: 1672/530, loss: 0.0022071530111134052
2023-01-22 16:34:57.659853: step: 1676/530, loss: 0.008076482452452183
2023-01-22 16:34:58.725106: step: 1680/530, loss: 0.0030460453126579523
2023-01-22 16:34:59.779664: step: 1684/530, loss: 0.0002496523957233876
2023-01-22 16:35:00.839724: step: 1688/530, loss: 4.8003726988099515e-05
2023-01-22 16:35:01.920450: step: 1692/530, loss: 0.008199339732527733
2023-01-22 16:35:02.981191: step: 1696/530, loss: 0.0032098277006298304
2023-01-22 16:35:04.051504: step: 1700/530, loss: 0.023149412125349045
2023-01-22 16:35:05.106132: step: 1704/530, loss: 0.009380985051393509
2023-01-22 16:35:06.156642: step: 1708/530, loss: 0.0038052101153880358
2023-01-22 16:35:07.213995: step: 1712/530, loss: 0.0014844831312075257
2023-01-22 16:35:08.271086: step: 1716/530, loss: 0.00926840677857399
2023-01-22 16:35:09.331594: step: 1720/530, loss: 0.03820732235908508
2023-01-22 16:35:10.396045: step: 1724/530, loss: 0.00701737217605114
2023-01-22 16:35:11.460422: step: 1728/530, loss: 0.013338825665414333
2023-01-22 16:35:12.518880: step: 1732/530, loss: 0.01182057335972786
2023-01-22 16:35:13.588222: step: 1736/530, loss: 0.003039284609258175
2023-01-22 16:35:14.644617: step: 1740/530, loss: 0.0039274804294109344
2023-01-22 16:35:15.688592: step: 1744/530, loss: 0.007153353653848171
2023-01-22 16:35:16.726056: step: 1748/530, loss: 0.006228177342563868
2023-01-22 16:35:17.793314: step: 1752/530, loss: 0.0013471595011651516
2023-01-22 16:35:18.846818: step: 1756/530, loss: 0.0014786750543862581
2023-01-22 16:35:19.903763: step: 1760/530, loss: 0.007056983653455973
2023-01-22 16:35:20.961224: step: 1764/530, loss: 0.016859661787748337
2023-01-22 16:35:22.020140: step: 1768/530, loss: 0.029031939804553986
2023-01-22 16:35:23.093126: step: 1772/530, loss: 0.0014349292032420635
2023-01-22 16:35:24.172634: step: 1776/530, loss: 0.0005414266488514841
2023-01-22 16:35:25.228470: step: 1780/530, loss: 0.0001226823078468442
2023-01-22 16:35:26.300202: step: 1784/530, loss: 0.008234023116528988
2023-01-22 16:35:27.376596: step: 1788/530, loss: 0.013443831354379654
2023-01-22 16:35:28.430716: step: 1792/530, loss: 0.008219048380851746
2023-01-22 16:35:29.498075: step: 1796/530, loss: 0.002434235531836748
2023-01-22 16:35:30.550256: step: 1800/530, loss: 0.0038213038351386786
2023-01-22 16:35:31.594896: step: 1804/530, loss: 0.0005589558277279139
2023-01-22 16:35:32.655048: step: 1808/530, loss: 0.025622064247727394
2023-01-22 16:35:33.726739: step: 1812/530, loss: 0.0028967352118343115
2023-01-22 16:35:34.811833: step: 1816/530, loss: 0.004630516283214092
2023-01-22 16:35:35.887207: step: 1820/530, loss: 0.0023333700373768806
2023-01-22 16:35:36.933326: step: 1824/530, loss: 0.0002672844857443124
2023-01-22 16:35:37.995566: step: 1828/530, loss: 0.011140204966068268
2023-01-22 16:35:39.054792: step: 1832/530, loss: 0.010136320255696774
2023-01-22 16:35:40.121593: step: 1836/530, loss: 0.004595352802425623
2023-01-22 16:35:41.186343: step: 1840/530, loss: 0.0032366826198995113
2023-01-22 16:35:42.239802: step: 1844/530, loss: 0.0003080504829995334
2023-01-22 16:35:43.306080: step: 1848/530, loss: 0.0024106702767312527
2023-01-22 16:35:44.354961: step: 1852/530, loss: 0.0012788112508133054
2023-01-22 16:35:45.435118: step: 1856/530, loss: 0.0005130224162712693
2023-01-22 16:35:46.504518: step: 1860/530, loss: 0.005843916442245245
2023-01-22 16:35:47.545097: step: 1864/530, loss: 0.0002107807667925954
2023-01-22 16:35:48.607892: step: 1868/530, loss: 0.003569738008081913
2023-01-22 16:35:49.659211: step: 1872/530, loss: 0.007909591309726238
2023-01-22 16:35:50.707538: step: 1876/530, loss: 2.0655966181948315e-06
2023-01-22 16:35:51.782150: step: 1880/530, loss: 0.005712231155484915
2023-01-22 16:35:52.831794: step: 1884/530, loss: 0.00027401791885495186
2023-01-22 16:35:53.893106: step: 1888/530, loss: 0.008661773055791855
2023-01-22 16:35:54.960751: step: 1892/530, loss: 0.0005759687046520412
2023-01-22 16:35:56.022369: step: 1896/530, loss: 0.0021990234963595867
2023-01-22 16:35:57.088414: step: 1900/530, loss: 0.003655859036371112
2023-01-22 16:35:58.158165: step: 1904/530, loss: 0.006165719125419855
2023-01-22 16:35:59.211144: step: 1908/530, loss: 0.005128706339746714
2023-01-22 16:36:00.256415: step: 1912/530, loss: 0.00694511691108346
2023-01-22 16:36:01.319666: step: 1916/530, loss: 0.005738366395235062
2023-01-22 16:36:02.404152: step: 1920/530, loss: 0.002607991686090827
2023-01-22 16:36:03.477164: step: 1924/530, loss: 0.0027916536200791597
2023-01-22 16:36:04.542719: step: 1928/530, loss: 0.0044531007297337055
2023-01-22 16:36:05.611291: step: 1932/530, loss: 0.0023015339393168688
2023-01-22 16:36:06.675940: step: 1936/530, loss: 0.009302242659032345
2023-01-22 16:36:07.741691: step: 1940/530, loss: 0.0015341931721195579
2023-01-22 16:36:08.808777: step: 1944/530, loss: 0.01171820517629385
2023-01-22 16:36:09.862759: step: 1948/530, loss: 0.008585739880800247
2023-01-22 16:36:10.925027: step: 1952/530, loss: 0.0031274575740098953
2023-01-22 16:36:11.985469: step: 1956/530, loss: 0.0018474524840712547
2023-01-22 16:36:13.039267: step: 1960/530, loss: 0.003800723236054182
2023-01-22 16:36:14.090098: step: 1964/530, loss: 0.0033009557519108057
2023-01-22 16:36:15.151683: step: 1968/530, loss: 0.0005532049108296633
2023-01-22 16:36:16.211563: step: 1972/530, loss: 2.481062983861193e-05
2023-01-22 16:36:17.272182: step: 1976/530, loss: 0.0029250739607959986
2023-01-22 16:36:18.329168: step: 1980/530, loss: 0.014450984075665474
2023-01-22 16:36:19.382408: step: 1984/530, loss: 0.002528311451897025
2023-01-22 16:36:20.434335: step: 1988/530, loss: 0.0035096043720841408
2023-01-22 16:36:21.503494: step: 1992/530, loss: 0.0005530567723326385
2023-01-22 16:36:22.554274: step: 1996/530, loss: 0.002930987160652876
2023-01-22 16:36:23.602501: step: 2000/530, loss: 0.0007623318233527243
2023-01-22 16:36:24.665374: step: 2004/530, loss: 0.013793833553791046
2023-01-22 16:36:25.717260: step: 2008/530, loss: 0.006455506198108196
2023-01-22 16:36:26.779385: step: 2012/530, loss: 0.00045024670544080436
2023-01-22 16:36:27.836533: step: 2016/530, loss: 0.0024875919334590435
2023-01-22 16:36:28.891174: step: 2020/530, loss: 0.003820327576249838
2023-01-22 16:36:29.963097: step: 2024/530, loss: 0.0027273381128907204
2023-01-22 16:36:31.022302: step: 2028/530, loss: 0.012514801695942879
2023-01-22 16:36:32.099173: step: 2032/530, loss: 0.0038836959283798933
2023-01-22 16:36:33.146715: step: 2036/530, loss: 0.0006056068232282996
2023-01-22 16:36:34.212572: step: 2040/530, loss: 0.006492273882031441
2023-01-22 16:36:35.275744: step: 2044/530, loss: 0.006946875248104334
2023-01-22 16:36:36.327676: step: 2048/530, loss: 0.006958520971238613
2023-01-22 16:36:37.376626: step: 2052/530, loss: 0.0009556170552968979
2023-01-22 16:36:38.436269: step: 2056/530, loss: 0.004036551341414452
2023-01-22 16:36:39.493700: step: 2060/530, loss: 0.01723671704530716
2023-01-22 16:36:40.542469: step: 2064/530, loss: 0.0015155597357079387
2023-01-22 16:36:41.618154: step: 2068/530, loss: 0.009895886294543743
2023-01-22 16:36:42.671470: step: 2072/530, loss: 0.004562380723655224
2023-01-22 16:36:43.714949: step: 2076/530, loss: 0.008926686830818653
2023-01-22 16:36:44.767094: step: 2080/530, loss: 0.003324170596897602
2023-01-22 16:36:45.819269: step: 2084/530, loss: 0.0008891146862879395
2023-01-22 16:36:46.888160: step: 2088/530, loss: 0.001414359314367175
2023-01-22 16:36:47.948492: step: 2092/530, loss: 0.00538351247087121
2023-01-22 16:36:49.024373: step: 2096/530, loss: 0.0008270586840808392
2023-01-22 16:36:50.090717: step: 2100/530, loss: 0.0028769485652446747
2023-01-22 16:36:51.174987: step: 2104/530, loss: 0.002638063160702586
2023-01-22 16:36:52.231813: step: 2108/530, loss: 0.0010600145906209946
2023-01-22 16:36:53.299848: step: 2112/530, loss: 0.007189236581325531
2023-01-22 16:36:54.367034: step: 2116/530, loss: 0.013191532343626022
2023-01-22 16:36:55.428585: step: 2120/530, loss: 0.008546882309019566
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3633328120112606, 'r': 0.2874948436597641, 'f1': 0.3209953021370671}, 'combined': 0.23652285420625996, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3570147442102144, 'r': 0.236155207425631, 'f1': 0.2842722924195975}, 'combined': 0.1885329193249144, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32357926528599606, 'r': 0.2868088942307692, 'f1': 0.30408653846153844}, 'combined': 0.20272435897435895, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40270673506163346, 'r': 0.3180547137640755, 'f1': 0.35540961731394033}, 'combined': 0.2319515397206768, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32501200867369345, 'r': 0.3404300356506239, 'f1': 0.33254240739180496}, 'combined': 0.24503124755185626, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.36439260567458126, 'r': 0.3318969880256792, 'f1': 0.34738651669203396}, 'combined': 0.23039105770248883, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:39:19.902826: step: 4/530, loss: 0.015927644446492195
2023-01-22 16:39:20.941168: step: 8/530, loss: 0.0008314985316246748
2023-01-22 16:39:21.987655: step: 12/530, loss: 0.0005987015319988132
2023-01-22 16:39:23.049814: step: 16/530, loss: 0.010028494521975517
2023-01-22 16:39:24.101460: step: 20/530, loss: 0.006948505993932486
2023-01-22 16:39:25.153355: step: 24/530, loss: 0.00400298647582531
2023-01-22 16:39:26.208241: step: 28/530, loss: 0.006426467094570398
2023-01-22 16:39:27.272440: step: 32/530, loss: 0.005779062397778034
2023-01-22 16:39:28.322060: step: 36/530, loss: 0.007021808531135321
2023-01-22 16:39:29.404576: step: 40/530, loss: 0.0023366441018879414
2023-01-22 16:39:30.479626: step: 44/530, loss: 0.12267465144395828
2023-01-22 16:39:31.563575: step: 48/530, loss: 0.0029192203655838966
2023-01-22 16:39:32.648460: step: 52/530, loss: 0.004540501162409782
2023-01-22 16:39:33.711562: step: 56/530, loss: 0.004050453193485737
2023-01-22 16:39:34.767734: step: 60/530, loss: 0.008094841614365578
2023-01-22 16:39:35.827539: step: 64/530, loss: 0.005523865111172199
2023-01-22 16:39:36.887647: step: 68/530, loss: 0.002569005358964205
2023-01-22 16:39:37.948136: step: 72/530, loss: 0.0015843015862628818
2023-01-22 16:39:39.008771: step: 76/530, loss: 0.0051142075099051
2023-01-22 16:39:40.062446: step: 80/530, loss: 0.004364377819001675
2023-01-22 16:39:41.112704: step: 84/530, loss: 0.006407077889889479
2023-01-22 16:39:42.145275: step: 88/530, loss: 0.004744573030620813
2023-01-22 16:39:43.204766: step: 92/530, loss: 0.006140295881778002
2023-01-22 16:39:44.280744: step: 96/530, loss: 0.005057979840785265
2023-01-22 16:39:45.332296: step: 100/530, loss: 0.0040791695937514305
2023-01-22 16:39:46.403399: step: 104/530, loss: 0.004173126071691513
2023-01-22 16:39:47.470535: step: 108/530, loss: 0.0037336116656661034
2023-01-22 16:39:48.532972: step: 112/530, loss: 0.006566036958247423
2023-01-22 16:39:49.586617: step: 116/530, loss: 0.0008445894345641136
2023-01-22 16:39:50.648882: step: 120/530, loss: 0.006509669125080109
2023-01-22 16:39:51.705419: step: 124/530, loss: 0.00409277668222785
2023-01-22 16:39:52.775006: step: 128/530, loss: 0.010612607933580875
2023-01-22 16:39:53.838279: step: 132/530, loss: 0.005248177796602249
2023-01-22 16:39:54.899169: step: 136/530, loss: 0.006438387557864189
2023-01-22 16:39:55.969911: step: 140/530, loss: 0.004107519518584013
2023-01-22 16:39:57.030154: step: 144/530, loss: 0.0032958744559437037
2023-01-22 16:39:58.082692: step: 148/530, loss: 0.0006733645568601787
2023-01-22 16:39:59.135683: step: 152/530, loss: 0.00517798587679863
2023-01-22 16:40:00.202876: step: 156/530, loss: 0.0001367157674394548
2023-01-22 16:40:01.244018: step: 160/530, loss: 0.00021519158326555043
2023-01-22 16:40:02.319649: step: 164/530, loss: 0.00035449492861516774
2023-01-22 16:40:03.390885: step: 168/530, loss: 0.016030261293053627
2023-01-22 16:40:04.456774: step: 172/530, loss: 0.0023506467696279287
2023-01-22 16:40:05.529904: step: 176/530, loss: 0.004691210109740496
2023-01-22 16:40:06.580714: step: 180/530, loss: 0.02522299252450466
2023-01-22 16:40:07.632112: step: 184/530, loss: 0.0034060394391417503
2023-01-22 16:40:08.707904: step: 188/530, loss: 0.002211774466559291
2023-01-22 16:40:09.775564: step: 192/530, loss: 0.0043431916274130344
2023-01-22 16:40:10.842663: step: 196/530, loss: 0.01457833219319582
2023-01-22 16:40:11.903671: step: 200/530, loss: 0.002763106720522046
2023-01-22 16:40:12.980591: step: 204/530, loss: 0.004409968387335539
2023-01-22 16:40:14.048140: step: 208/530, loss: 0.0028461955953389406
2023-01-22 16:40:15.128856: step: 212/530, loss: 0.0014478196389973164
2023-01-22 16:40:16.180931: step: 216/530, loss: 0.00030926355975680053
2023-01-22 16:40:17.222255: step: 220/530, loss: 0.002106926403939724
2023-01-22 16:40:18.284859: step: 224/530, loss: 0.0014854887267574668
2023-01-22 16:40:19.357033: step: 228/530, loss: 0.0343819335103035
2023-01-22 16:40:20.415595: step: 232/530, loss: 0.0038134222850203514
2023-01-22 16:40:21.498053: step: 236/530, loss: 0.004319116938859224
2023-01-22 16:40:22.574427: step: 240/530, loss: 0.0007618785602971911
2023-01-22 16:40:23.631403: step: 244/530, loss: 0.005231081508100033
2023-01-22 16:40:24.676193: step: 248/530, loss: 0.00034870783565565944
2023-01-22 16:40:25.728604: step: 252/530, loss: 0.006212800275534391
2023-01-22 16:40:26.775113: step: 256/530, loss: 0.0002306024543941021
2023-01-22 16:40:27.839954: step: 260/530, loss: 0.0005440199165605009
2023-01-22 16:40:28.906115: step: 264/530, loss: 0.00894810352474451
2023-01-22 16:40:29.969940: step: 268/530, loss: 0.033572353422641754
2023-01-22 16:40:31.031952: step: 272/530, loss: 0.01326671801507473
2023-01-22 16:40:32.108624: step: 276/530, loss: 0.0032431071158498526
2023-01-22 16:40:33.161818: step: 280/530, loss: 0.00031948211835697293
2023-01-22 16:40:34.223319: step: 284/530, loss: 0.0036425578873604536
2023-01-22 16:40:35.291770: step: 288/530, loss: 0.007322228513658047
2023-01-22 16:40:36.346023: step: 292/530, loss: 0.005125284194946289
2023-01-22 16:40:37.411402: step: 296/530, loss: 0.009313278831541538
2023-01-22 16:40:38.476849: step: 300/530, loss: 0.004412886220961809
2023-01-22 16:40:39.534752: step: 304/530, loss: 0.0070163654163479805
2023-01-22 16:40:40.591191: step: 308/530, loss: 8.047714800341055e-05
2023-01-22 16:40:41.639548: step: 312/530, loss: 0.0023837205953896046
2023-01-22 16:40:42.715491: step: 316/530, loss: 0.0054130093194544315
2023-01-22 16:40:43.769895: step: 320/530, loss: 0.0029596390668302774
2023-01-22 16:40:44.837818: step: 324/530, loss: 0.0002044261054834351
2023-01-22 16:40:45.903862: step: 328/530, loss: 0.24544937908649445
2023-01-22 16:40:46.967770: step: 332/530, loss: 0.001435103709809482
2023-01-22 16:40:48.032643: step: 336/530, loss: 0.001408419688232243
2023-01-22 16:40:49.088154: step: 340/530, loss: 0.0001884626253740862
2023-01-22 16:40:50.160045: step: 344/530, loss: 0.008062949404120445
2023-01-22 16:40:51.224328: step: 348/530, loss: 0.004432308487594128
2023-01-22 16:40:52.271338: step: 352/530, loss: 0.00018615700537338853
2023-01-22 16:40:53.327506: step: 356/530, loss: 0.03113900125026703
2023-01-22 16:40:54.387566: step: 360/530, loss: 0.0012075015110895038
2023-01-22 16:40:55.444846: step: 364/530, loss: 0.007036595139652491
2023-01-22 16:40:56.497369: step: 368/530, loss: 0.0027034436352550983
2023-01-22 16:40:57.552996: step: 372/530, loss: 0.0030246013775467873
2023-01-22 16:40:58.613441: step: 376/530, loss: 0.018699076026678085
2023-01-22 16:40:59.667636: step: 380/530, loss: 0.0009343913989141583
2023-01-22 16:41:00.738549: step: 384/530, loss: 0.003655866254121065
2023-01-22 16:41:01.805552: step: 388/530, loss: 0.004558792803436518
2023-01-22 16:41:02.878970: step: 392/530, loss: 7.05994461895898e-05
2023-01-22 16:41:03.936732: step: 396/530, loss: 0.004327529575675726
2023-01-22 16:41:04.992761: step: 400/530, loss: 0.005280277691781521
2023-01-22 16:41:06.051816: step: 404/530, loss: 0.00345603353343904
2023-01-22 16:41:07.122387: step: 408/530, loss: 0.027603723108768463
2023-01-22 16:41:08.177840: step: 412/530, loss: 0.009201932698488235
2023-01-22 16:41:09.257118: step: 416/530, loss: 0.024548783898353577
2023-01-22 16:41:10.336140: step: 420/530, loss: 0.004014628008008003
2023-01-22 16:41:11.408289: step: 424/530, loss: 0.005797058343887329
2023-01-22 16:41:12.466649: step: 428/530, loss: 0.0009839124977588654
2023-01-22 16:41:13.510649: step: 432/530, loss: 0.0021490410435944796
2023-01-22 16:41:14.590202: step: 436/530, loss: 0.006196657661348581
2023-01-22 16:41:15.635131: step: 440/530, loss: 0.007675060071051121
2023-01-22 16:41:16.702686: step: 444/530, loss: 0.014316799119114876
2023-01-22 16:41:17.760220: step: 448/530, loss: 0.009575974196195602
2023-01-22 16:41:18.825173: step: 452/530, loss: 0.013419738039374352
2023-01-22 16:41:19.893168: step: 456/530, loss: 0.003999773878604174
2023-01-22 16:41:20.958574: step: 460/530, loss: 0.004203292075544596
2023-01-22 16:41:22.004137: step: 464/530, loss: 0.0028406099881976843
2023-01-22 16:41:23.065101: step: 468/530, loss: 0.0010555546032264829
2023-01-22 16:41:24.113991: step: 472/530, loss: 0.0012232547160238028
2023-01-22 16:41:25.173118: step: 476/530, loss: 0.01999991200864315
2023-01-22 16:41:26.240430: step: 480/530, loss: 0.007830601185560226
2023-01-22 16:41:27.305172: step: 484/530, loss: 0.0031262922566384077
2023-01-22 16:41:28.366928: step: 488/530, loss: 0.006909772753715515
2023-01-22 16:41:29.449532: step: 492/530, loss: 0.008000316098332405
2023-01-22 16:41:30.511077: step: 496/530, loss: 0.005164084490388632
2023-01-22 16:41:31.584689: step: 500/530, loss: 0.00842166319489479
2023-01-22 16:41:32.654545: step: 504/530, loss: 0.00445551285520196
2023-01-22 16:41:33.738464: step: 508/530, loss: 0.03764331340789795
2023-01-22 16:41:34.798832: step: 512/530, loss: 0.0024514200631529093
2023-01-22 16:41:35.851214: step: 516/530, loss: 0.0033493717201054096
2023-01-22 16:41:36.897828: step: 520/530, loss: 0.0019446861697360873
2023-01-22 16:41:37.956891: step: 524/530, loss: 0.0011561862193048
2023-01-22 16:41:39.005301: step: 528/530, loss: 1.3254373698146082e-05
2023-01-22 16:41:40.065492: step: 532/530, loss: 0.0013337228447198868
2023-01-22 16:41:41.144292: step: 536/530, loss: 0.004951189737766981
2023-01-22 16:41:42.205080: step: 540/530, loss: 0.008516372181475163
2023-01-22 16:41:43.244828: step: 544/530, loss: 0.006416157819330692
2023-01-22 16:41:44.326031: step: 548/530, loss: 0.001722979242913425
2023-01-22 16:41:45.378340: step: 552/530, loss: 0.003638720139861107
2023-01-22 16:41:46.438013: step: 556/530, loss: 0.018069975078105927
2023-01-22 16:41:47.517687: step: 560/530, loss: 0.0002427633007755503
2023-01-22 16:41:48.572908: step: 564/530, loss: 0.009420906193554401
2023-01-22 16:41:49.626331: step: 568/530, loss: 0.0045921290293335915
2023-01-22 16:41:50.704626: step: 572/530, loss: 0.0005713204154744744
2023-01-22 16:41:51.756192: step: 576/530, loss: 0.006289421580731869
2023-01-22 16:41:52.819999: step: 580/530, loss: 0.004684799816459417
2023-01-22 16:41:53.870897: step: 584/530, loss: 0.0006750068860128522
2023-01-22 16:41:54.927825: step: 588/530, loss: 4.2831211430893745e-06
2023-01-22 16:41:55.994386: step: 592/530, loss: 0.019326431676745415
2023-01-22 16:41:57.051419: step: 596/530, loss: 0.004922597203403711
2023-01-22 16:41:58.114397: step: 600/530, loss: 0.0009555994183756411
2023-01-22 16:41:59.187746: step: 604/530, loss: 0.0
2023-01-22 16:42:00.255195: step: 608/530, loss: 0.0018904495518654585
2023-01-22 16:42:01.321182: step: 612/530, loss: 0.0006573530263267457
2023-01-22 16:42:02.401983: step: 616/530, loss: 0.007349018007516861
2023-01-22 16:42:03.472936: step: 620/530, loss: 0.00732880225405097
2023-01-22 16:42:04.527273: step: 624/530, loss: 0.007181914057582617
2023-01-22 16:42:05.584359: step: 628/530, loss: 0.005422661546617746
2023-01-22 16:42:06.652584: step: 632/530, loss: 0.00471876934170723
2023-01-22 16:42:07.717993: step: 636/530, loss: 0.0037823922466486692
2023-01-22 16:42:08.799288: step: 640/530, loss: 0.023475103080272675
2023-01-22 16:42:09.869199: step: 644/530, loss: 0.001388481934554875
2023-01-22 16:42:10.932029: step: 648/530, loss: 0.0012594583677127957
2023-01-22 16:42:11.988899: step: 652/530, loss: 0.004343141335994005
2023-01-22 16:42:13.054706: step: 656/530, loss: 0.006917532999068499
2023-01-22 16:42:14.115763: step: 660/530, loss: 0.0031417841091752052
2023-01-22 16:42:15.171186: step: 664/530, loss: 0.005103804636746645
2023-01-22 16:42:16.233814: step: 668/530, loss: 0.0013484611408784986
2023-01-22 16:42:17.296785: step: 672/530, loss: 0.00772235868498683
2023-01-22 16:42:18.342651: step: 676/530, loss: 0.0031657651998102665
2023-01-22 16:42:19.416300: step: 680/530, loss: 0.03739647567272186
2023-01-22 16:42:20.491755: step: 684/530, loss: 0.0238046832382679
2023-01-22 16:42:21.554906: step: 688/530, loss: 0.004072646144777536
2023-01-22 16:42:22.616703: step: 692/530, loss: 0.0007109611760824919
2023-01-22 16:42:23.682024: step: 696/530, loss: 0.006285248789936304
2023-01-22 16:42:24.735325: step: 700/530, loss: 0.010502849705517292
2023-01-22 16:42:25.812328: step: 704/530, loss: 0.004541243426501751
2023-01-22 16:42:26.865818: step: 708/530, loss: 0.019364066421985626
2023-01-22 16:42:27.925754: step: 712/530, loss: 0.003215125761926174
2023-01-22 16:42:29.018622: step: 716/530, loss: 0.004471972119063139
2023-01-22 16:42:30.083620: step: 720/530, loss: 0.00035115217906422913
2023-01-22 16:42:31.133145: step: 724/530, loss: 0.0019015392754226923
2023-01-22 16:42:32.188658: step: 728/530, loss: 0.010658822022378445
2023-01-22 16:42:33.254825: step: 732/530, loss: 0.0025435646530240774
2023-01-22 16:42:34.317053: step: 736/530, loss: 0.0009237733902409673
2023-01-22 16:42:35.387318: step: 740/530, loss: 0.002559992950409651
2023-01-22 16:42:36.447662: step: 744/530, loss: 0.027732260525226593
2023-01-22 16:42:37.519489: step: 748/530, loss: 0.011358147487044334
2023-01-22 16:42:38.605313: step: 752/530, loss: 0.0031314108055084944
2023-01-22 16:42:39.660206: step: 756/530, loss: 0.0029461474623531103
2023-01-22 16:42:40.721123: step: 760/530, loss: 0.0009313707705587149
2023-01-22 16:42:41.779045: step: 764/530, loss: 0.012383795343339443
2023-01-22 16:42:42.839615: step: 768/530, loss: 0.00035698837018571794
2023-01-22 16:42:43.900340: step: 772/530, loss: 0.0014801776269450784
2023-01-22 16:42:44.971351: step: 776/530, loss: 0.04260542243719101
2023-01-22 16:42:46.059688: step: 780/530, loss: 0.008443552069365978
2023-01-22 16:42:47.116743: step: 784/530, loss: 0.009735611267387867
2023-01-22 16:42:48.196201: step: 788/530, loss: 0.0008686337387189269
2023-01-22 16:42:49.247275: step: 792/530, loss: 0.002671161200851202
2023-01-22 16:42:50.333425: step: 796/530, loss: 0.002173204207792878
2023-01-22 16:42:51.401742: step: 800/530, loss: 0.01370356697589159
2023-01-22 16:42:52.467555: step: 804/530, loss: 0.0017238699365407228
2023-01-22 16:42:53.530046: step: 808/530, loss: 0.02576804719865322
2023-01-22 16:42:54.586436: step: 812/530, loss: 0.006545905955135822
2023-01-22 16:42:55.634501: step: 816/530, loss: 0.003871291410177946
2023-01-22 16:42:56.697681: step: 820/530, loss: 0.018059369176626205
2023-01-22 16:42:57.760587: step: 824/530, loss: 0.0037166739348322153
2023-01-22 16:42:58.827122: step: 828/530, loss: 0.0030634873546659946
2023-01-22 16:42:59.907268: step: 832/530, loss: 0.0036304688546806574
2023-01-22 16:43:00.972272: step: 836/530, loss: 0.0020787473767995834
2023-01-22 16:43:02.039860: step: 840/530, loss: 0.0031391947995871305
2023-01-22 16:43:03.109455: step: 844/530, loss: 0.007681672461330891
2023-01-22 16:43:04.178758: step: 848/530, loss: 0.002553332829847932
2023-01-22 16:43:05.223312: step: 852/530, loss: 0.004553305450826883
2023-01-22 16:43:06.315358: step: 856/530, loss: 0.0016303982120007277
2023-01-22 16:43:07.363719: step: 860/530, loss: 5.975810836389428e-06
2023-01-22 16:43:08.417103: step: 864/530, loss: 0.0005275781149975955
2023-01-22 16:43:09.467427: step: 868/530, loss: 0.04236587509512901
2023-01-22 16:43:10.520505: step: 872/530, loss: 0.00021000744891352952
2023-01-22 16:43:11.586240: step: 876/530, loss: 0.004119101911783218
2023-01-22 16:43:12.636948: step: 880/530, loss: 0.0002598412102088332
2023-01-22 16:43:13.696007: step: 884/530, loss: 0.00025763074518181384
2023-01-22 16:43:14.747261: step: 888/530, loss: 0.002313523320481181
2023-01-22 16:43:15.787314: step: 892/530, loss: 0.00018398166866973042
2023-01-22 16:43:16.847027: step: 896/530, loss: 0.005753064062446356
2023-01-22 16:43:17.907187: step: 900/530, loss: 0.0010670917108654976
2023-01-22 16:43:18.953737: step: 904/530, loss: 0.0011302694911137223
2023-01-22 16:43:20.034633: step: 908/530, loss: 0.013157066889107227
2023-01-22 16:43:21.092205: step: 912/530, loss: 0.0026933434419333935
2023-01-22 16:43:22.163832: step: 916/530, loss: 0.0068700178526341915
2023-01-22 16:43:23.235843: step: 920/530, loss: 0.00660925917327404
2023-01-22 16:43:24.307812: step: 924/530, loss: 0.02645551785826683
2023-01-22 16:43:25.394626: step: 928/530, loss: 0.028280384838581085
2023-01-22 16:43:26.457367: step: 932/530, loss: 0.00302509730681777
2023-01-22 16:43:27.520911: step: 936/530, loss: 0.026667091995477676
2023-01-22 16:43:28.581458: step: 940/530, loss: 0.003322065807878971
2023-01-22 16:43:29.647321: step: 944/530, loss: 0.0018791877664625645
2023-01-22 16:43:30.723914: step: 948/530, loss: 0.00295850308611989
2023-01-22 16:43:31.806499: step: 952/530, loss: 0.011943128891289234
2023-01-22 16:43:32.899071: step: 956/530, loss: 0.009050185792148113
2023-01-22 16:43:33.971513: step: 960/530, loss: 0.012569201178848743
2023-01-22 16:43:35.032292: step: 964/530, loss: 0.004016493912786245
2023-01-22 16:43:36.103064: step: 968/530, loss: 0.002299533924087882
2023-01-22 16:43:37.162187: step: 972/530, loss: 0.0026719390880316496
2023-01-22 16:43:38.212252: step: 976/530, loss: 0.011718140915036201
2023-01-22 16:43:39.267931: step: 980/530, loss: 0.0014752658316865563
2023-01-22 16:43:40.336443: step: 984/530, loss: 0.004211958963423967
2023-01-22 16:43:41.390821: step: 988/530, loss: 0.0
2023-01-22 16:43:42.440628: step: 992/530, loss: 0.0001493980671511963
2023-01-22 16:43:43.503111: step: 996/530, loss: 0.0008119151461869478
2023-01-22 16:43:44.569027: step: 1000/530, loss: 0.003098259447142482
2023-01-22 16:43:45.619117: step: 1004/530, loss: 0.002368541434407234
2023-01-22 16:43:46.680035: step: 1008/530, loss: 0.007792165037244558
2023-01-22 16:43:47.737165: step: 1012/530, loss: 0.0014715869911015034
2023-01-22 16:43:48.805403: step: 1016/530, loss: 0.0015814263606444001
2023-01-22 16:43:49.862382: step: 1020/530, loss: 0.0010000880574807525
2023-01-22 16:43:50.914965: step: 1024/530, loss: 0.0005833122995682061
2023-01-22 16:43:51.988594: step: 1028/530, loss: 0.0034772504586726427
2023-01-22 16:43:53.054923: step: 1032/530, loss: 0.01191109512001276
2023-01-22 16:43:54.108934: step: 1036/530, loss: 0.002839866327121854
2023-01-22 16:43:55.174895: step: 1040/530, loss: 0.0007197019876912236
2023-01-22 16:43:56.253002: step: 1044/530, loss: 0.001009781495667994
2023-01-22 16:43:57.326104: step: 1048/530, loss: 0.002634261269122362
2023-01-22 16:43:58.405541: step: 1052/530, loss: 0.0025090479757636786
2023-01-22 16:43:59.449963: step: 1056/530, loss: 0.0006466375198215246
2023-01-22 16:44:00.508509: step: 1060/530, loss: 0.009640929289162159
2023-01-22 16:44:01.566498: step: 1064/530, loss: 0.0007870576228015125
2023-01-22 16:44:02.663400: step: 1068/530, loss: 0.0062566520646214485
2023-01-22 16:44:03.726687: step: 1072/530, loss: 0.0021695138420909643
2023-01-22 16:44:04.773280: step: 1076/530, loss: 0.004995639435946941
2023-01-22 16:44:05.843984: step: 1080/530, loss: 0.024274542927742004
2023-01-22 16:44:06.908512: step: 1084/530, loss: 0.006547966506332159
2023-01-22 16:44:07.990812: step: 1088/530, loss: 0.005423553287982941
2023-01-22 16:44:09.055452: step: 1092/530, loss: 0.0009255635086447
2023-01-22 16:44:10.126968: step: 1096/530, loss: 0.001235869713127613
2023-01-22 16:44:11.171771: step: 1100/530, loss: 0.0034246433060616255
2023-01-22 16:44:12.224114: step: 1104/530, loss: 0.010006594471633434
2023-01-22 16:44:13.268272: step: 1108/530, loss: 0.001413852209225297
2023-01-22 16:44:14.316660: step: 1112/530, loss: 0.005569763481616974
2023-01-22 16:44:15.359323: step: 1116/530, loss: 0.0006357765523716807
2023-01-22 16:44:16.412173: step: 1120/530, loss: 0.00542420381680131
2023-01-22 16:44:17.469398: step: 1124/530, loss: 0.0020649973303079605
2023-01-22 16:44:18.547192: step: 1128/530, loss: 0.0008013544720597565
2023-01-22 16:44:19.595668: step: 1132/530, loss: 3.835871393675916e-05
2023-01-22 16:44:20.649009: step: 1136/530, loss: 0.0020174754317849874
2023-01-22 16:44:21.697640: step: 1140/530, loss: 0.0005846507847309113
2023-01-22 16:44:22.774234: step: 1144/530, loss: 0.006800536997616291
2023-01-22 16:44:23.823798: step: 1148/530, loss: 0.0003378924448043108
2023-01-22 16:44:24.875542: step: 1152/530, loss: 0.001740907202474773
2023-01-22 16:44:25.930967: step: 1156/530, loss: 0.005147941410541534
2023-01-22 16:44:27.000520: step: 1160/530, loss: 0.006817403249442577
2023-01-22 16:44:28.066306: step: 1164/530, loss: 0.02316501922905445
2023-01-22 16:44:29.135131: step: 1168/530, loss: 0.002055207034572959
2023-01-22 16:44:30.203126: step: 1172/530, loss: 0.0021133250556886196
2023-01-22 16:44:31.259242: step: 1176/530, loss: 0.009937414899468422
2023-01-22 16:44:32.318271: step: 1180/530, loss: 7.805306267982814e-06
2023-01-22 16:44:33.385417: step: 1184/530, loss: 0.063641257584095
2023-01-22 16:44:34.452761: step: 1188/530, loss: 0.00038742704782634974
2023-01-22 16:44:35.503722: step: 1192/530, loss: 0.0032423243392258883
2023-01-22 16:44:36.567391: step: 1196/530, loss: 0.004681752994656563
2023-01-22 16:44:37.618070: step: 1200/530, loss: 0.0027724565006792545
2023-01-22 16:44:38.683967: step: 1204/530, loss: 0.014422204345464706
2023-01-22 16:44:39.742830: step: 1208/530, loss: 0.0007912633591331542
2023-01-22 16:44:40.809683: step: 1212/530, loss: 0.008981010876595974
2023-01-22 16:44:41.877832: step: 1216/530, loss: 0.00025331697543151677
2023-01-22 16:44:42.934541: step: 1220/530, loss: 0.009442894719541073
2023-01-22 16:44:43.988192: step: 1224/530, loss: 0.0033431989140808582
2023-01-22 16:44:45.047804: step: 1228/530, loss: 0.0010546607663854957
2023-01-22 16:44:46.115792: step: 1232/530, loss: 0.010316262021660805
2023-01-22 16:44:47.186446: step: 1236/530, loss: 0.01360830757766962
2023-01-22 16:44:48.262080: step: 1240/530, loss: 0.0015769846504554152
2023-01-22 16:44:49.329521: step: 1244/530, loss: 0.002931649563834071
2023-01-22 16:44:50.394108: step: 1248/530, loss: 0.011826610192656517
2023-01-22 16:44:51.450958: step: 1252/530, loss: 0.031738314777612686
2023-01-22 16:44:52.499649: step: 1256/530, loss: 0.007316206116229296
2023-01-22 16:44:53.573807: step: 1260/530, loss: 0.00010550727893132716
2023-01-22 16:44:54.644334: step: 1264/530, loss: 0.007459431886672974
2023-01-22 16:44:55.697033: step: 1268/530, loss: 0.00347651494666934
2023-01-22 16:44:56.755481: step: 1272/530, loss: 0.0053300149738788605
2023-01-22 16:44:57.810437: step: 1276/530, loss: 0.00813503097742796
2023-01-22 16:44:58.865939: step: 1280/530, loss: 0.0032836797181516886
2023-01-22 16:44:59.911645: step: 1284/530, loss: 5.7676017604535446e-05
2023-01-22 16:45:00.958200: step: 1288/530, loss: 0.007579579018056393
2023-01-22 16:45:02.021215: step: 1292/530, loss: 0.00030347672873176634
2023-01-22 16:45:03.071388: step: 1296/530, loss: 0.009218649938702583
2023-01-22 16:45:04.127005: step: 1300/530, loss: 0.003888055682182312
2023-01-22 16:45:05.196043: step: 1304/530, loss: 0.004083716776221991
2023-01-22 16:45:06.248694: step: 1308/530, loss: 0.006607308052480221
2023-01-22 16:45:07.313628: step: 1312/530, loss: 0.015921570360660553
2023-01-22 16:45:08.377873: step: 1316/530, loss: 0.0011330116540193558
2023-01-22 16:45:09.435140: step: 1320/530, loss: 0.005118370521813631
2023-01-22 16:45:10.497281: step: 1324/530, loss: 0.009682781994342804
2023-01-22 16:45:11.553818: step: 1328/530, loss: 0.0
2023-01-22 16:45:12.625486: step: 1332/530, loss: 0.010913779027760029
2023-01-22 16:45:13.691956: step: 1336/530, loss: 0.0012872458901256323
2023-01-22 16:45:14.757170: step: 1340/530, loss: 0.0005801309598609805
2023-01-22 16:45:15.809040: step: 1344/530, loss: 0.004209278617054224
2023-01-22 16:45:16.864598: step: 1348/530, loss: 0.00030627899104729295
2023-01-22 16:45:17.912731: step: 1352/530, loss: 0.00452372245490551
2023-01-22 16:45:18.969515: step: 1356/530, loss: 0.007813968695700169
2023-01-22 16:45:20.027525: step: 1360/530, loss: 0.006410367786884308
2023-01-22 16:45:21.073168: step: 1364/530, loss: 0.00013037113239988685
2023-01-22 16:45:22.151954: step: 1368/530, loss: 0.006338878534734249
2023-01-22 16:45:23.218512: step: 1372/530, loss: 0.007964469492435455
2023-01-22 16:45:24.268849: step: 1376/530, loss: 0.007284740451723337
2023-01-22 16:45:25.337863: step: 1380/530, loss: 0.0032373496796935797
2023-01-22 16:45:26.405041: step: 1384/530, loss: 0.003451686352491379
2023-01-22 16:45:27.468415: step: 1388/530, loss: 0.001442793756723404
2023-01-22 16:45:28.528521: step: 1392/530, loss: 0.0004326379857957363
2023-01-22 16:45:29.592588: step: 1396/530, loss: 0.007162436842918396
2023-01-22 16:45:30.685004: step: 1400/530, loss: 0.007310534827411175
2023-01-22 16:45:31.763872: step: 1404/530, loss: 0.00580007117241621
2023-01-22 16:45:32.825742: step: 1408/530, loss: 0.001106907962821424
2023-01-22 16:45:33.890502: step: 1412/530, loss: 0.0003788106550928205
2023-01-22 16:45:34.952373: step: 1416/530, loss: 0.001676419167779386
2023-01-22 16:45:36.021645: step: 1420/530, loss: 0.00019797220011241734
2023-01-22 16:45:37.072895: step: 1424/530, loss: 0.001173590775579214
2023-01-22 16:45:38.117040: step: 1428/530, loss: 0.0011421255767345428
2023-01-22 16:45:39.166464: step: 1432/530, loss: 0.0020894964691251516
2023-01-22 16:45:40.220412: step: 1436/530, loss: 0.0011938372626900673
2023-01-22 16:45:41.284136: step: 1440/530, loss: 0.005563205573707819
2023-01-22 16:45:42.351915: step: 1444/530, loss: 0.003811065573245287
2023-01-22 16:45:43.390769: step: 1448/530, loss: 0.00515342503786087
2023-01-22 16:45:44.451026: step: 1452/530, loss: 0.003028250765055418
2023-01-22 16:45:45.506209: step: 1456/530, loss: 0.010524586774408817
2023-01-22 16:45:46.561111: step: 1460/530, loss: 0.0016798849683254957
2023-01-22 16:45:47.620967: step: 1464/530, loss: 0.01206453051418066
2023-01-22 16:45:48.680809: step: 1468/530, loss: 0.0017865870613604784
2023-01-22 16:45:49.734840: step: 1472/530, loss: 0.0026840041391551495
2023-01-22 16:45:50.783437: step: 1476/530, loss: 7.70620463299565e-05
2023-01-22 16:45:51.849766: step: 1480/530, loss: 0.00045172072714194655
2023-01-22 16:45:52.922356: step: 1484/530, loss: 0.00787447951734066
2023-01-22 16:45:53.977977: step: 1488/530, loss: 0.00321327056735754
2023-01-22 16:45:55.039729: step: 1492/530, loss: 0.006025717593729496
2023-01-22 16:45:56.096822: step: 1496/530, loss: 0.00025547249242663383
2023-01-22 16:45:57.161029: step: 1500/530, loss: 0.0001262098376173526
2023-01-22 16:45:58.230274: step: 1504/530, loss: 0.003317362628877163
2023-01-22 16:45:59.314741: step: 1508/530, loss: 0.0278952457010746
2023-01-22 16:46:00.393590: step: 1512/530, loss: 0.0003014483954757452
2023-01-22 16:46:01.443740: step: 1516/530, loss: 0.013164707459509373
2023-01-22 16:46:02.527704: step: 1520/530, loss: 0.00140077352989465
2023-01-22 16:46:03.577289: step: 1524/530, loss: 0.0013717414112761617
2023-01-22 16:46:04.636526: step: 1528/530, loss: 0.002023855457082391
2023-01-22 16:46:05.693371: step: 1532/530, loss: 0.004170695319771767
2023-01-22 16:46:06.756852: step: 1536/530, loss: 0.00061720673693344
2023-01-22 16:46:07.807001: step: 1540/530, loss: 0.000912063813302666
2023-01-22 16:46:08.862844: step: 1544/530, loss: 0.0032152016647160053
2023-01-22 16:46:09.922019: step: 1548/530, loss: 0.002805764554068446
2023-01-22 16:46:10.973390: step: 1552/530, loss: 0.0008888099691830575
2023-01-22 16:46:12.016740: step: 1556/530, loss: 0.004206516779959202
2023-01-22 16:46:13.095378: step: 1560/530, loss: 0.00432842830196023
2023-01-22 16:46:14.161895: step: 1564/530, loss: 0.001752279931679368
2023-01-22 16:46:15.220226: step: 1568/530, loss: 0.0009820128325372934
2023-01-22 16:46:16.279937: step: 1572/530, loss: 0.00031587018747814
2023-01-22 16:46:17.342296: step: 1576/530, loss: 0.0003350767365191132
2023-01-22 16:46:18.395676: step: 1580/530, loss: 0.01824451982975006
2023-01-22 16:46:19.446542: step: 1584/530, loss: 0.000544765149243176
2023-01-22 16:46:20.501652: step: 1588/530, loss: 0.016581397503614426
2023-01-22 16:46:21.564557: step: 1592/530, loss: 0.0027360336389392614
2023-01-22 16:46:22.620630: step: 1596/530, loss: 3.345218715367082e-07
2023-01-22 16:46:23.674940: step: 1600/530, loss: 0.0003424906462896615
2023-01-22 16:46:24.740161: step: 1604/530, loss: 0.0003842185251414776
2023-01-22 16:46:25.794197: step: 1608/530, loss: 0.003292701207101345
2023-01-22 16:46:26.875844: step: 1612/530, loss: 0.0030974324326962233
2023-01-22 16:46:27.949867: step: 1616/530, loss: 0.08294067531824112
2023-01-22 16:46:29.025456: step: 1620/530, loss: 0.0010433156276121736
2023-01-22 16:46:30.086838: step: 1624/530, loss: 7.316777919186279e-05
2023-01-22 16:46:31.148908: step: 1628/530, loss: 0.00175048119854182
2023-01-22 16:46:32.227298: step: 1632/530, loss: 0.02194075472652912
2023-01-22 16:46:33.298383: step: 1636/530, loss: 0.0022982191294431686
2023-01-22 16:46:34.363150: step: 1640/530, loss: 0.0034323742147535086
2023-01-22 16:46:35.439024: step: 1644/530, loss: 0.006930475123226643
2023-01-22 16:46:36.490993: step: 1648/530, loss: 0.00407805060967803
2023-01-22 16:46:37.564961: step: 1652/530, loss: 0.0014996958198025823
2023-01-22 16:46:38.606283: step: 1656/530, loss: 0.005112234503030777
2023-01-22 16:46:39.671513: step: 1660/530, loss: 0.008222192525863647
2023-01-22 16:46:40.720083: step: 1664/530, loss: 0.00886036641895771
2023-01-22 16:46:41.781633: step: 1668/530, loss: 0.0004207780584692955
2023-01-22 16:46:42.854754: step: 1672/530, loss: 0.0012578913010656834
2023-01-22 16:46:43.906782: step: 1676/530, loss: 0.0003702753456309438
2023-01-22 16:46:44.962787: step: 1680/530, loss: 0.00027476067771203816
2023-01-22 16:46:46.015015: step: 1684/530, loss: 0.00023447100829798728
2023-01-22 16:46:47.098383: step: 1688/530, loss: 0.009226815775036812
2023-01-22 16:46:48.162938: step: 1692/530, loss: 0.007423891220241785
2023-01-22 16:46:49.220669: step: 1696/530, loss: 0.004156404174864292
2023-01-22 16:46:50.279580: step: 1700/530, loss: 0.002900763414800167
2023-01-22 16:46:51.337889: step: 1704/530, loss: 0.002932594157755375
2023-01-22 16:46:52.396316: step: 1708/530, loss: 0.009009765461087227
2023-01-22 16:46:53.459253: step: 1712/530, loss: 0.00167070550378412
2023-01-22 16:46:54.514857: step: 1716/530, loss: 0.0011218409053981304
2023-01-22 16:46:55.568327: step: 1720/530, loss: 0.0010735613759607077
2023-01-22 16:46:56.619194: step: 1724/530, loss: 0.0027676960453391075
2023-01-22 16:46:57.678867: step: 1728/530, loss: 0.004438402596861124
2023-01-22 16:46:58.716258: step: 1732/530, loss: 6.169595872052014e-05
2023-01-22 16:46:59.779638: step: 1736/530, loss: 0.011559482663869858
2023-01-22 16:47:00.855690: step: 1740/530, loss: 0.004667510744184256
2023-01-22 16:47:01.925979: step: 1744/530, loss: 0.0001360240567009896
2023-01-22 16:47:02.991734: step: 1748/530, loss: 0.03332662582397461
2023-01-22 16:47:04.059995: step: 1752/530, loss: 0.005930274724960327
2023-01-22 16:47:05.145064: step: 1756/530, loss: 0.0652540922164917
2023-01-22 16:47:06.190994: step: 1760/530, loss: 0.004535254556685686
2023-01-22 16:47:07.248096: step: 1764/530, loss: 0.002991259563714266
2023-01-22 16:47:08.291695: step: 1768/530, loss: 0.0008298219763673842
2023-01-22 16:47:09.370754: step: 1772/530, loss: 0.008967505767941475
2023-01-22 16:47:10.477199: step: 1776/530, loss: 0.003104770788922906
2023-01-22 16:47:11.531117: step: 1780/530, loss: 0.0010101236402988434
2023-01-22 16:47:12.595699: step: 1784/530, loss: 0.0008991596987470984
2023-01-22 16:47:13.659925: step: 1788/530, loss: 0.001970746321603656
2023-01-22 16:47:14.718135: step: 1792/530, loss: 0.0022328312043100595
2023-01-22 16:47:15.783720: step: 1796/530, loss: 0.00284550990909338
2023-01-22 16:47:16.847859: step: 1800/530, loss: 0.0032706218771636486
2023-01-22 16:47:17.918237: step: 1804/530, loss: 0.0001248436456080526
2023-01-22 16:47:18.983220: step: 1808/530, loss: 0.0003272875037509948
2023-01-22 16:47:20.043535: step: 1812/530, loss: 0.009997248649597168
2023-01-22 16:47:21.101076: step: 1816/530, loss: 0.0008368525886908174
2023-01-22 16:47:22.147491: step: 1820/530, loss: 0.0015876280376687646
2023-01-22 16:47:23.219212: step: 1824/530, loss: 0.002629116177558899
2023-01-22 16:47:24.282533: step: 1828/530, loss: 0.004525650758296251
2023-01-22 16:47:25.360106: step: 1832/530, loss: 0.02819177694618702
2023-01-22 16:47:26.417129: step: 1836/530, loss: 0.005889588035643101
2023-01-22 16:47:27.479123: step: 1840/530, loss: 0.0006788388127461076
2023-01-22 16:47:28.537464: step: 1844/530, loss: 0.0006677304627373815
2023-01-22 16:47:29.594367: step: 1848/530, loss: 0.008282354101538658
2023-01-22 16:47:30.652352: step: 1852/530, loss: 0.0008350508287549019
2023-01-22 16:47:31.712972: step: 1856/530, loss: 0.014092615805566311
2023-01-22 16:47:32.799106: step: 1860/530, loss: 0.00304342620074749
2023-01-22 16:47:33.858462: step: 1864/530, loss: 0.0005976548418402672
2023-01-22 16:47:34.926705: step: 1868/530, loss: 0.005507944617420435
2023-01-22 16:47:36.003862: step: 1872/530, loss: 0.006886770948767662
2023-01-22 16:47:37.067946: step: 1876/530, loss: 0.004653391428291798
2023-01-22 16:47:38.140457: step: 1880/530, loss: 0.009824220091104507
2023-01-22 16:47:39.198138: step: 1884/530, loss: 0.01097895111888647
2023-01-22 16:47:40.251880: step: 1888/530, loss: 0.008392523042857647
2023-01-22 16:47:41.314741: step: 1892/530, loss: 0.011279174126684666
2023-01-22 16:47:42.375851: step: 1896/530, loss: 0.002961927792057395
2023-01-22 16:47:43.449488: step: 1900/530, loss: 0.006292080506682396
2023-01-22 16:47:44.506739: step: 1904/530, loss: 0.0016209312016144395
2023-01-22 16:47:45.554577: step: 1908/530, loss: 0.001214727875776589
2023-01-22 16:47:46.633923: step: 1912/530, loss: 0.0003028415667358786
2023-01-22 16:47:47.695200: step: 1916/530, loss: 0.004107190761715174
2023-01-22 16:47:48.734510: step: 1920/530, loss: 0.00702214241027832
2023-01-22 16:47:49.780826: step: 1924/530, loss: 0.007610386703163385
2023-01-22 16:47:50.825379: step: 1928/530, loss: 0.0034361856523901224
2023-01-22 16:47:51.898450: step: 1932/530, loss: 0.002816550899296999
2023-01-22 16:47:52.956452: step: 1936/530, loss: 0.003611439373344183
2023-01-22 16:47:54.013777: step: 1940/530, loss: 0.007487880997359753
2023-01-22 16:47:55.076806: step: 1944/530, loss: 0.003865041770040989
2023-01-22 16:47:56.138494: step: 1948/530, loss: 0.001151856267824769
2023-01-22 16:47:57.189397: step: 1952/530, loss: 0.0038708734791725874
2023-01-22 16:47:58.239639: step: 1956/530, loss: 1.4826046935922932e-05
2023-01-22 16:47:59.290220: step: 1960/530, loss: 0.011877520941197872
2023-01-22 16:48:00.351018: step: 1964/530, loss: 0.016567381098866463
2023-01-22 16:48:01.393796: step: 1968/530, loss: 0.006150108762085438
2023-01-22 16:48:02.446473: step: 1972/530, loss: 0.003371666418388486
2023-01-22 16:48:03.503610: step: 1976/530, loss: 0.009631413966417313
2023-01-22 16:48:04.559385: step: 1980/530, loss: 0.001984379952773452
2023-01-22 16:48:05.625706: step: 1984/530, loss: 0.021570490673184395
2023-01-22 16:48:06.691771: step: 1988/530, loss: 0.004815895576030016
2023-01-22 16:48:07.753737: step: 1992/530, loss: 0.001309867831878364
2023-01-22 16:48:08.800729: step: 1996/530, loss: 0.005153494421392679
2023-01-22 16:48:09.867197: step: 2000/530, loss: 0.0022641292307525873
2023-01-22 16:48:10.928362: step: 2004/530, loss: 0.003979336004704237
2023-01-22 16:48:11.997099: step: 2008/530, loss: 0.007276598829776049
2023-01-22 16:48:13.064741: step: 2012/530, loss: 0.0030632787384092808
2023-01-22 16:48:14.122063: step: 2016/530, loss: 0.0013041881611570716
2023-01-22 16:48:15.194567: step: 2020/530, loss: 0.0005160032887943089
2023-01-22 16:48:16.270812: step: 2024/530, loss: 0.0013672898057848215
2023-01-22 16:48:17.327961: step: 2028/530, loss: 0.0049277967773377895
2023-01-22 16:48:18.384720: step: 2032/530, loss: 0.0016568928258493543
2023-01-22 16:48:19.442972: step: 2036/530, loss: 0.0031998734921216965
2023-01-22 16:48:20.517978: step: 2040/530, loss: 0.00034540813066996634
2023-01-22 16:48:21.586425: step: 2044/530, loss: 0.0014932570047676563
2023-01-22 16:48:22.632689: step: 2048/530, loss: 0.005445054266601801
2023-01-22 16:48:23.694826: step: 2052/530, loss: 0.002347063273191452
2023-01-22 16:48:24.744664: step: 2056/530, loss: 0.006142171565443277
2023-01-22 16:48:25.807354: step: 2060/530, loss: 0.0036080344580113888
2023-01-22 16:48:26.873894: step: 2064/530, loss: 0.008136573247611523
2023-01-22 16:48:27.945095: step: 2068/530, loss: 0.004509699065238237
2023-01-22 16:48:28.999905: step: 2072/530, loss: 6.327142909867689e-05
2023-01-22 16:48:30.064120: step: 2076/530, loss: 0.009542361833155155
2023-01-22 16:48:31.107513: step: 2080/530, loss: 0.0006430309149436653
2023-01-22 16:48:32.157444: step: 2084/530, loss: 0.0005659364978782833
2023-01-22 16:48:33.214662: step: 2088/530, loss: 0.00048064705333672464
2023-01-22 16:48:34.277510: step: 2092/530, loss: 0.008232426829636097
2023-01-22 16:48:35.352597: step: 2096/530, loss: 0.005026193335652351
2023-01-22 16:48:36.407848: step: 2100/530, loss: 0.00412242254242301
2023-01-22 16:48:37.464032: step: 2104/530, loss: 0.003266087267547846
2023-01-22 16:48:38.517543: step: 2108/530, loss: 0.00027584817144088447
2023-01-22 16:48:39.594324: step: 2112/530, loss: 0.0018737884238362312
2023-01-22 16:48:40.652031: step: 2116/530, loss: 0.00425515603274107
2023-01-22 16:48:41.712972: step: 2120/530, loss: 0.006231745705008507
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36246359475764517, 'r': 0.2874948436597641, 'f1': 0.32065562456866803}, 'combined': 0.23627256547165013, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3567795855145911, 'r': 0.2342616605492699, 'f1': 0.282822150600629}, 'combined': 0.18757116723772282, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3215930298604349, 'r': 0.2887028336247086, 'f1': 0.3042616689697528}, 'combined': 0.20284111264650187, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40270673506163346, 'r': 0.3186059351050878, 'f1': 0.35575350663886923}, 'combined': 0.23217597275378832, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32228149991839405, 'r': 0.3406276953596688, 'f1': 0.33120072962093267}, 'combined': 0.24404264287858196, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3561824396688653, 'r': 0.3262692823979736, 'f1': 0.34057028573850834}, 'combined': 0.22587044857268943, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.59375, 'r': 0.41304347826086957, 'f1': 0.4871794871794871}, 'combined': 0.32478632478632474, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622560156976144, 'r': 0.2893923768665952, 'f1': 0.3217505962208769}, 'combined': 0.2370793866890672, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3556552028564354, 'r': 0.23464005591047948, 'f1': 0.2827431033663055}, 'combined': 0.1875187421289487, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 12
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 16:51:10.579696: step: 4/530, loss: 0.0021094956900924444
2023-01-22 16:51:11.631099: step: 8/530, loss: 0.01311890222132206
2023-01-22 16:51:12.676580: step: 12/530, loss: 5.68782415939495e-05
2023-01-22 16:51:13.728077: step: 16/530, loss: 0.0013302834704518318
2023-01-22 16:51:14.794533: step: 20/530, loss: 0.007437954656779766
2023-01-22 16:51:15.849260: step: 24/530, loss: 0.022962521761655807
2023-01-22 16:51:16.899566: step: 28/530, loss: 0.0009972292464226484
2023-01-22 16:51:17.948179: step: 32/530, loss: 0.00037892538239248097
2023-01-22 16:51:19.020537: step: 36/530, loss: 0.0007030340493656695
2023-01-22 16:51:20.085476: step: 40/530, loss: 0.007828260771930218
2023-01-22 16:51:21.143396: step: 44/530, loss: 0.004577526822686195
2023-01-22 16:51:22.200073: step: 48/530, loss: 0.00975757371634245
2023-01-22 16:51:23.252669: step: 52/530, loss: 0.0036127290222793818
2023-01-22 16:51:24.320821: step: 56/530, loss: 0.002661227248609066
2023-01-22 16:51:25.391528: step: 60/530, loss: 1.735929686219606e-06
2023-01-22 16:51:26.444657: step: 64/530, loss: 0.005232215393334627
2023-01-22 16:51:27.504257: step: 68/530, loss: 0.002060589613392949
2023-01-22 16:51:28.556460: step: 72/530, loss: 0.00871964544057846
2023-01-22 16:51:29.606568: step: 76/530, loss: 0.008005631156265736
2023-01-22 16:51:30.649141: step: 80/530, loss: 0.0041761561296880245
2023-01-22 16:51:31.700061: step: 84/530, loss: 0.00016803358448669314
2023-01-22 16:51:32.743497: step: 88/530, loss: 0.0021858823020011187
2023-01-22 16:51:33.787421: step: 92/530, loss: 0.008031019009649754
2023-01-22 16:51:34.839263: step: 96/530, loss: 0.019964169710874557
2023-01-22 16:51:35.903980: step: 100/530, loss: 0.0006089920061640441
2023-01-22 16:51:36.956916: step: 104/530, loss: 0.00021269729768391699
2023-01-22 16:51:38.007448: step: 108/530, loss: 0.015228603966534138
2023-01-22 16:51:39.064443: step: 112/530, loss: 0.010490295477211475
2023-01-22 16:51:40.131044: step: 116/530, loss: 0.00946330837905407
2023-01-22 16:51:41.186134: step: 120/530, loss: 0.0055718692019581795
2023-01-22 16:51:42.246019: step: 124/530, loss: 0.0025457674637436867
2023-01-22 16:51:43.303395: step: 128/530, loss: 0.0012628454715013504
2023-01-22 16:51:44.363010: step: 132/530, loss: 0.0018173173302784562
2023-01-22 16:51:45.419550: step: 136/530, loss: 0.003521144622936845
2023-01-22 16:51:46.463541: step: 140/530, loss: 4.411282134242356e-05
2023-01-22 16:51:47.515216: step: 144/530, loss: 0.0013732301304116845
2023-01-22 16:51:48.562771: step: 148/530, loss: 0.00035474516334943473
2023-01-22 16:51:49.630715: step: 152/530, loss: 0.00474494369700551
2023-01-22 16:51:50.681952: step: 156/530, loss: 0.009792686440050602
2023-01-22 16:51:51.743699: step: 160/530, loss: 0.002052793512120843
2023-01-22 16:51:52.787429: step: 164/530, loss: 0.004068868234753609
2023-01-22 16:51:53.858864: step: 168/530, loss: 8.105426968540996e-05
2023-01-22 16:51:54.906837: step: 172/530, loss: 0.0036880180705338717
2023-01-22 16:51:55.966872: step: 176/530, loss: 0.0011073502246290445
2023-01-22 16:51:57.033820: step: 180/530, loss: 0.003766452195122838
2023-01-22 16:51:58.082771: step: 184/530, loss: 0.0005020612734369934
2023-01-22 16:51:59.145620: step: 188/530, loss: 0.012637553736567497
2023-01-22 16:52:00.198644: step: 192/530, loss: 0.0007634004577994347
2023-01-22 16:52:01.274223: step: 196/530, loss: 0.0008837177301757038
2023-01-22 16:52:02.327631: step: 200/530, loss: 0.002109450288116932
2023-01-22 16:52:03.393644: step: 204/530, loss: 0.006022005807608366
2023-01-22 16:52:04.449868: step: 208/530, loss: 0.004695853218436241
2023-01-22 16:52:05.505086: step: 212/530, loss: 0.002789364429190755
2023-01-22 16:52:06.561951: step: 216/530, loss: 0.00016741837316658348
2023-01-22 16:52:07.638251: step: 220/530, loss: 0.001817410346120596
2023-01-22 16:52:08.692923: step: 224/530, loss: 0.0037393856327980757
2023-01-22 16:52:09.760436: step: 228/530, loss: 0.007606687489897013
2023-01-22 16:52:10.842727: step: 232/530, loss: 0.000278868421446532
2023-01-22 16:52:11.892852: step: 236/530, loss: 0.00959752406924963
2023-01-22 16:52:12.953560: step: 240/530, loss: 0.0002712109999265522
2023-01-22 16:52:14.027566: step: 244/530, loss: 0.002412226051092148
2023-01-22 16:52:15.097550: step: 248/530, loss: 0.00445058848708868
2023-01-22 16:52:16.158729: step: 252/530, loss: 0.001412743586115539
2023-01-22 16:52:17.216641: step: 256/530, loss: 0.0006932559190317988
2023-01-22 16:52:18.274555: step: 260/530, loss: 0.0005659185699187219
2023-01-22 16:52:19.329150: step: 264/530, loss: 0.001991112483665347
2023-01-22 16:52:20.396052: step: 268/530, loss: 0.008442804217338562
2023-01-22 16:52:21.465151: step: 272/530, loss: 0.0014403002569451928
2023-01-22 16:52:22.511686: step: 276/530, loss: 0.0
2023-01-22 16:52:23.571261: step: 280/530, loss: 0.007657312788069248
2023-01-22 16:52:24.640859: step: 284/530, loss: 3.607563121477142e-05
2023-01-22 16:52:25.705438: step: 288/530, loss: 0.002834174083545804
2023-01-22 16:52:26.757862: step: 292/530, loss: 0.0027063863817602396
2023-01-22 16:52:27.825891: step: 296/530, loss: 0.0022629655431956053
2023-01-22 16:52:28.883250: step: 300/530, loss: 0.0012459707213565707
2023-01-22 16:52:29.932510: step: 304/530, loss: 0.00220873998478055
2023-01-22 16:52:30.995211: step: 308/530, loss: 0.004601443186402321
2023-01-22 16:52:32.091917: step: 312/530, loss: 0.00023372155555989593
2023-01-22 16:52:33.151893: step: 316/530, loss: 0.001204905565828085
2023-01-22 16:52:34.208966: step: 320/530, loss: 0.0012778834206983447
2023-01-22 16:52:35.264292: step: 324/530, loss: 2.5372843083459884e-05
2023-01-22 16:52:36.315288: step: 328/530, loss: 0.0021881035063415766
2023-01-22 16:52:37.377569: step: 332/530, loss: 0.0008263842319138348
2023-01-22 16:52:38.446030: step: 336/530, loss: 0.004658328369259834
2023-01-22 16:52:39.514596: step: 340/530, loss: 0.005119822919368744
2023-01-22 16:52:40.585523: step: 344/530, loss: 0.004938906989991665
2023-01-22 16:52:41.648837: step: 348/530, loss: 0.007177949883043766
2023-01-22 16:52:42.701659: step: 352/530, loss: 0.0011792953591793776
2023-01-22 16:52:43.772123: step: 356/530, loss: 0.006008140277117491
2023-01-22 16:52:44.835102: step: 360/530, loss: 0.003989999648183584
2023-01-22 16:52:45.912574: step: 364/530, loss: 0.010769250802695751
2023-01-22 16:52:46.966804: step: 368/530, loss: 0.008618909865617752
2023-01-22 16:52:48.032727: step: 372/530, loss: 0.0006336081423796713
2023-01-22 16:52:49.103636: step: 376/530, loss: 0.0014145129825919867
2023-01-22 16:52:50.147522: step: 380/530, loss: 0.0007761603919789195
2023-01-22 16:52:51.224612: step: 384/530, loss: 0.0005060825496912003
2023-01-22 16:52:52.284252: step: 388/530, loss: 0.0012338366359472275
2023-01-22 16:52:53.355751: step: 392/530, loss: 0.02588936872780323
2023-01-22 16:52:54.426864: step: 396/530, loss: 1.960390727617778e-05
2023-01-22 16:52:55.488087: step: 400/530, loss: 0.0029859195929020643
2023-01-22 16:52:56.551955: step: 404/530, loss: 0.0025051666889339685
2023-01-22 16:52:57.604860: step: 408/530, loss: 0.0028211469762027264
2023-01-22 16:52:58.649370: step: 412/530, loss: 0.004626823123544455
2023-01-22 16:52:59.716717: step: 416/530, loss: 0.007663717959076166
2023-01-22 16:53:00.763004: step: 420/530, loss: 0.005124426446855068
2023-01-22 16:53:01.836399: step: 424/530, loss: 0.0013528214767575264
2023-01-22 16:53:02.897796: step: 428/530, loss: 0.0014767188113182783
2023-01-22 16:53:03.951101: step: 432/530, loss: 0.001254978938959539
2023-01-22 16:53:05.002066: step: 436/530, loss: 0.01409226469695568
2023-01-22 16:53:06.048840: step: 440/530, loss: 0.00011738141620298848
2023-01-22 16:53:07.102559: step: 444/530, loss: 0.00019990344299003482
2023-01-22 16:53:08.153433: step: 448/530, loss: 0.011193651705980301
2023-01-22 16:53:09.219173: step: 452/530, loss: 0.006073852069675922
2023-01-22 16:53:10.273663: step: 456/530, loss: 0.0028117834590375423
2023-01-22 16:53:11.345380: step: 460/530, loss: 0.003322468139231205
2023-01-22 16:53:12.409604: step: 464/530, loss: 0.0007779276929795742
2023-01-22 16:53:13.493748: step: 468/530, loss: 0.004181955941021442
2023-01-22 16:53:14.539372: step: 472/530, loss: 6.901913729961962e-05
2023-01-22 16:53:15.605915: step: 476/530, loss: 0.012137278914451599
2023-01-22 16:53:16.684095: step: 480/530, loss: 5.6343269534409046e-05
2023-01-22 16:53:17.739348: step: 484/530, loss: 0.010861517861485481
2023-01-22 16:53:18.806017: step: 488/530, loss: 0.024029167369008064
2023-01-22 16:53:19.867117: step: 492/530, loss: 0.00993871409446001
2023-01-22 16:53:20.931634: step: 496/530, loss: 0.003906929399818182
2023-01-22 16:53:22.011202: step: 500/530, loss: 0.001860091113485396
2023-01-22 16:53:23.063344: step: 504/530, loss: 0.003279547905549407
2023-01-22 16:53:24.120972: step: 508/530, loss: 0.004254957661032677
2023-01-22 16:53:25.205491: step: 512/530, loss: 0.0016864299541339278
2023-01-22 16:53:26.277352: step: 516/530, loss: 0.0035776819568127394
2023-01-22 16:53:27.348422: step: 520/530, loss: 0.01032742578536272
2023-01-22 16:53:28.416624: step: 524/530, loss: 0.0018546065548434854
2023-01-22 16:53:29.465485: step: 528/530, loss: 0.0006155781447887421
2023-01-22 16:53:30.516783: step: 532/530, loss: 0.0005933456122875214
2023-01-22 16:53:31.591226: step: 536/530, loss: 0.009491799399256706
2023-01-22 16:53:32.666555: step: 540/530, loss: 0.015153428539633751
2023-01-22 16:53:33.727027: step: 544/530, loss: 0.0011128297774121165
2023-01-22 16:53:34.790472: step: 548/530, loss: 0.005828630179166794
2023-01-22 16:53:35.858860: step: 552/530, loss: 0.0003642754163593054
2023-01-22 16:53:36.921108: step: 556/530, loss: 0.01035226508975029
2023-01-22 16:53:37.995445: step: 560/530, loss: 0.025892533361911774
2023-01-22 16:53:39.057932: step: 564/530, loss: 0.010160128585994244
2023-01-22 16:53:40.117611: step: 568/530, loss: 0.006989937741309404
2023-01-22 16:53:41.181396: step: 572/530, loss: 0.008228665217757225
2023-01-22 16:53:42.249324: step: 576/530, loss: 0.0011891174362972379
2023-01-22 16:53:43.315281: step: 580/530, loss: 0.0011885742424055934
2023-01-22 16:53:44.379028: step: 584/530, loss: 0.01902218721807003
2023-01-22 16:53:45.433977: step: 588/530, loss: 0.002112123416736722
2023-01-22 16:53:46.497470: step: 592/530, loss: 0.0014739600010216236
2023-01-22 16:53:47.567462: step: 596/530, loss: 0.003994252532720566
2023-01-22 16:53:48.626165: step: 600/530, loss: 6.639136245212285e-07
2023-01-22 16:53:49.673809: step: 604/530, loss: 0.010039624758064747
2023-01-22 16:53:50.735035: step: 608/530, loss: 0.000832458958029747
2023-01-22 16:53:51.774237: step: 612/530, loss: 0.004489888437092304
2023-01-22 16:53:52.840316: step: 616/530, loss: 0.007010675501078367
2023-01-22 16:53:53.910707: step: 620/530, loss: 8.574331332056317e-06
2023-01-22 16:53:54.986679: step: 624/530, loss: 0.002068987349048257
2023-01-22 16:53:56.050440: step: 628/530, loss: 0.0007186959264799953
2023-01-22 16:53:57.116117: step: 632/530, loss: 0.009036572650074959
2023-01-22 16:53:58.186206: step: 636/530, loss: 0.000980931450612843
2023-01-22 16:53:59.240531: step: 640/530, loss: 0.0005726184463128448
2023-01-22 16:54:00.303997: step: 644/530, loss: 0.008107513189315796
2023-01-22 16:54:01.360608: step: 648/530, loss: 0.0014254581183195114
2023-01-22 16:54:02.424866: step: 652/530, loss: 0.010879823938012123
2023-01-22 16:54:03.478069: step: 656/530, loss: 0.002156768925487995
2023-01-22 16:54:04.549515: step: 660/530, loss: 0.018113087862730026
2023-01-22 16:54:05.612609: step: 664/530, loss: 0.0005491006304509938
2023-01-22 16:54:06.683623: step: 668/530, loss: 0.003203930100426078
2023-01-22 16:54:07.760574: step: 672/530, loss: 0.008084729313850403
2023-01-22 16:54:08.819030: step: 676/530, loss: 0.00035008369013667107
2023-01-22 16:54:09.881713: step: 680/530, loss: 0.011634944938123226
2023-01-22 16:54:10.929374: step: 684/530, loss: 0.003046165220439434
2023-01-22 16:54:11.981640: step: 688/530, loss: 0.003385255578905344
2023-01-22 16:54:13.044465: step: 692/530, loss: 0.001965835690498352
2023-01-22 16:54:14.096703: step: 696/530, loss: 0.001608905615285039
2023-01-22 16:54:15.141491: step: 700/530, loss: 0.0017961891135200858
2023-01-22 16:54:16.241027: step: 704/530, loss: 0.01001130510121584
2023-01-22 16:54:17.300558: step: 708/530, loss: 0.013646242208778858
2023-01-22 16:54:18.364181: step: 712/530, loss: 0.011228703893721104
2023-01-22 16:54:19.418753: step: 716/530, loss: 0.008186562918126583
2023-01-22 16:54:20.482081: step: 720/530, loss: 0.002894805744290352
2023-01-22 16:54:21.561999: step: 724/530, loss: 0.0039372979663312435
2023-01-22 16:54:22.623284: step: 728/530, loss: 0.002604193054139614
2023-01-22 16:54:23.679657: step: 732/530, loss: 0.0016125808469951153
2023-01-22 16:54:24.737632: step: 736/530, loss: 0.0024360036477446556
2023-01-22 16:54:25.804437: step: 740/530, loss: 0.010964752174913883
2023-01-22 16:54:26.871218: step: 744/530, loss: 0.018129222095012665
2023-01-22 16:54:27.931719: step: 748/530, loss: 0.00019537939806468785
2023-01-22 16:54:28.983621: step: 752/530, loss: 0.004652428440749645
2023-01-22 16:54:30.045962: step: 756/530, loss: 0.011240316554903984
2023-01-22 16:54:31.105484: step: 760/530, loss: 0.003953434992581606
2023-01-22 16:54:32.162532: step: 764/530, loss: 0.01022385898977518
2023-01-22 16:54:33.208351: step: 768/530, loss: 0.004109564237296581
2023-01-22 16:54:34.275773: step: 772/530, loss: 0.0027495494578033686
2023-01-22 16:54:35.332569: step: 776/530, loss: 0.0020026029087603092
2023-01-22 16:54:36.400788: step: 780/530, loss: 0.0038549068849533796
2023-01-22 16:54:37.464913: step: 784/530, loss: 0.0016286814352497458
2023-01-22 16:54:38.521404: step: 788/530, loss: 0.0003526336804497987
2023-01-22 16:54:39.569546: step: 792/530, loss: 0.0037495382130146027
2023-01-22 16:54:40.630474: step: 796/530, loss: 0.0010510339634492993
2023-01-22 16:54:41.688442: step: 800/530, loss: 0.01007411815226078
2023-01-22 16:54:42.748571: step: 804/530, loss: 0.0002998080162797123
2023-01-22 16:54:43.797180: step: 808/530, loss: 5.281314952298999e-05
2023-01-22 16:54:44.857435: step: 812/530, loss: 0.006465135142207146
2023-01-22 16:54:45.907817: step: 816/530, loss: 0.004686877131462097
2023-01-22 16:54:46.986552: step: 820/530, loss: 0.004502084571868181
2023-01-22 16:54:48.044634: step: 824/530, loss: 0.017148464918136597
2023-01-22 16:54:49.107834: step: 828/530, loss: 0.004372735042124987
2023-01-22 16:54:50.170946: step: 832/530, loss: 0.01028257142752409
2023-01-22 16:54:51.232325: step: 836/530, loss: 0.002823252696543932
2023-01-22 16:54:52.289338: step: 840/530, loss: 0.002731231739744544
2023-01-22 16:54:53.342650: step: 844/530, loss: 0.006105278618633747
2023-01-22 16:54:54.393189: step: 848/530, loss: 0.016903437674045563
2023-01-22 16:54:55.453408: step: 852/530, loss: 0.0007305179606191814
2023-01-22 16:54:56.519755: step: 856/530, loss: 0.005039713345468044
2023-01-22 16:54:57.564291: step: 860/530, loss: 0.004273528233170509
2023-01-22 16:54:58.644186: step: 864/530, loss: 0.0023842991795390844
2023-01-22 16:54:59.694533: step: 868/530, loss: 0.0032738943118602037
2023-01-22 16:55:00.741462: step: 872/530, loss: 0.00440587243065238
2023-01-22 16:55:01.796999: step: 876/530, loss: 0.0022535305470228195
2023-01-22 16:55:02.856679: step: 880/530, loss: 0.0012918816646561027
2023-01-22 16:55:03.913630: step: 884/530, loss: 0.004441816359758377
2023-01-22 16:55:04.962879: step: 888/530, loss: 0.0014922457048669457
2023-01-22 16:55:06.041172: step: 892/530, loss: 0.00581457419320941
2023-01-22 16:55:07.102940: step: 896/530, loss: 0.006170479580760002
2023-01-22 16:55:08.161210: step: 900/530, loss: 0.015530979260802269
2023-01-22 16:55:09.221056: step: 904/530, loss: 0.005349037237465382
2023-01-22 16:55:10.283234: step: 908/530, loss: 0.006273407489061356
2023-01-22 16:55:11.362401: step: 912/530, loss: 0.008132955059409142
2023-01-22 16:55:12.425339: step: 916/530, loss: 0.0030964715406298637
2023-01-22 16:55:13.499125: step: 920/530, loss: 0.01400149054825306
2023-01-22 16:55:14.542246: step: 924/530, loss: 0.0028561505023390055
2023-01-22 16:55:15.636160: step: 928/530, loss: 0.029421506449580193
2023-01-22 16:55:16.678892: step: 932/530, loss: 0.001328668207861483
2023-01-22 16:55:17.740427: step: 936/530, loss: 6.479109288193285e-05
2023-01-22 16:55:18.798503: step: 940/530, loss: 0.0013753786915913224
2023-01-22 16:55:19.859596: step: 944/530, loss: 0.004724790342152119
2023-01-22 16:55:20.936998: step: 948/530, loss: 0.004426884464919567
2023-01-22 16:55:21.995617: step: 952/530, loss: 0.00037916458677500486
2023-01-22 16:55:23.072981: step: 956/530, loss: 0.006889330223202705
2023-01-22 16:55:24.141376: step: 960/530, loss: 0.006863574963063002
2023-01-22 16:55:25.201315: step: 964/530, loss: 0.0020583600271493196
2023-01-22 16:55:26.265164: step: 968/530, loss: 0.024703780189156532
2023-01-22 16:55:27.324828: step: 972/530, loss: 6.011876030243002e-05
2023-01-22 16:55:28.381214: step: 976/530, loss: 0.006502603646367788
2023-01-22 16:55:29.433614: step: 980/530, loss: 0.010413480922579765
2023-01-22 16:55:30.505799: step: 984/530, loss: 0.05847205966711044
2023-01-22 16:55:31.576498: step: 988/530, loss: 0.0022907813545316458
2023-01-22 16:55:32.633042: step: 992/530, loss: 0.0017779474146664143
2023-01-22 16:55:33.687063: step: 996/530, loss: 0.009272441267967224
2023-01-22 16:55:34.732087: step: 1000/530, loss: 0.0010802585165947676
2023-01-22 16:55:35.781321: step: 1004/530, loss: 0.008206567727029324
2023-01-22 16:55:36.833050: step: 1008/530, loss: 0.007077578920871019
2023-01-22 16:55:37.898565: step: 1012/530, loss: 0.005512617994099855
2023-01-22 16:55:38.957413: step: 1016/530, loss: 0.0031960357446223497
2023-01-22 16:55:40.007583: step: 1020/530, loss: 0.000671093468554318
2023-01-22 16:55:41.064727: step: 1024/530, loss: 0.0014497991651296616
2023-01-22 16:55:42.116065: step: 1028/530, loss: 0.005251995753496885
2023-01-22 16:55:43.174576: step: 1032/530, loss: 0.0006869861972518265
2023-01-22 16:55:44.226988: step: 1036/530, loss: 0.0003046881465706974
2023-01-22 16:55:45.304221: step: 1040/530, loss: 0.00020803413644898683
2023-01-22 16:55:46.372086: step: 1044/530, loss: 0.006651169154793024
2023-01-22 16:55:47.412946: step: 1048/530, loss: 0.0034765827003866434
2023-01-22 16:55:48.464459: step: 1052/530, loss: 0.004014601930975914
2023-01-22 16:55:49.521316: step: 1056/530, loss: 0.0021639573387801647
2023-01-22 16:55:50.572346: step: 1060/530, loss: 0.001757454709149897
2023-01-22 16:55:51.629112: step: 1064/530, loss: 0.00246369163505733
2023-01-22 16:55:52.707975: step: 1068/530, loss: 0.002517396816983819
2023-01-22 16:55:53.780309: step: 1072/530, loss: 0.0030611990951001644
2023-01-22 16:55:54.831308: step: 1076/530, loss: 0.002291389275342226
2023-01-22 16:55:55.885619: step: 1080/530, loss: 0.012959088198840618
2023-01-22 16:55:56.954611: step: 1084/530, loss: 0.020819442346692085
2023-01-22 16:55:58.016604: step: 1088/530, loss: 0.006599036045372486
2023-01-22 16:55:59.078663: step: 1092/530, loss: 0.0009701611124910414
2023-01-22 16:56:00.126248: step: 1096/530, loss: 0.0013894721632823348
2023-01-22 16:56:01.192542: step: 1100/530, loss: 0.006052486132830381
2023-01-22 16:56:02.238925: step: 1104/530, loss: 0.0004752454406116158
2023-01-22 16:56:03.296863: step: 1108/530, loss: 0.0039168051443994045
2023-01-22 16:56:04.351705: step: 1112/530, loss: 0.01796250231564045
2023-01-22 16:56:05.408294: step: 1116/530, loss: 0.008454777300357819
2023-01-22 16:56:06.451707: step: 1120/530, loss: 0.0003409204655326903
2023-01-22 16:56:07.524072: step: 1124/530, loss: 0.00257872580550611
2023-01-22 16:56:08.600150: step: 1128/530, loss: 0.0021439490374177694
2023-01-22 16:56:09.660490: step: 1132/530, loss: 0.00038046290865167975
2023-01-22 16:56:10.722336: step: 1136/530, loss: 0.019083842635154724
2023-01-22 16:56:11.767254: step: 1140/530, loss: 0.010760469362139702
2023-01-22 16:56:12.823332: step: 1144/530, loss: 0.012481419369578362
2023-01-22 16:56:13.889294: step: 1148/530, loss: 0.007176099810749292
2023-01-22 16:56:14.930179: step: 1152/530, loss: 0.007717461790889502
2023-01-22 16:56:15.996049: step: 1156/530, loss: 8.064800931606442e-05
2023-01-22 16:56:17.027073: step: 1160/530, loss: 8.959236583905295e-05
2023-01-22 16:56:18.084197: step: 1164/530, loss: 0.00043193131568841636
2023-01-22 16:56:19.141198: step: 1168/530, loss: 0.0027817648369818926
2023-01-22 16:56:20.195765: step: 1172/530, loss: 0.0002408848813502118
2023-01-22 16:56:21.237452: step: 1176/530, loss: 0.007526103872805834
2023-01-22 16:56:22.297390: step: 1180/530, loss: 0.007288565393537283
2023-01-22 16:56:23.360444: step: 1184/530, loss: 0.00638193404302001
2023-01-22 16:56:24.410149: step: 1188/530, loss: 0.005992783233523369
2023-01-22 16:56:25.462922: step: 1192/530, loss: 0.0013478028122335672
2023-01-22 16:56:26.523307: step: 1196/530, loss: 0.006875394843518734
2023-01-22 16:56:27.580933: step: 1200/530, loss: 0.0032173816580325365
2023-01-22 16:56:28.646087: step: 1204/530, loss: 0.0013164657866582274
2023-01-22 16:56:29.700005: step: 1208/530, loss: 0.0013198578963056207
2023-01-22 16:56:30.752588: step: 1212/530, loss: 0.00010920914064627141
2023-01-22 16:56:31.820115: step: 1216/530, loss: 0.0014433127362281084
2023-01-22 16:56:32.885974: step: 1220/530, loss: 0.0038386075757443905
2023-01-22 16:56:33.936238: step: 1224/530, loss: 0.010455395095050335
2023-01-22 16:56:34.979638: step: 1228/530, loss: 7.119439260350191e-09
2023-01-22 16:56:36.039959: step: 1232/530, loss: 0.010438834317028522
2023-01-22 16:56:37.100715: step: 1236/530, loss: 0.005345779471099377
2023-01-22 16:56:38.161361: step: 1240/530, loss: 0.00016140179650392383
2023-01-22 16:56:39.211243: step: 1244/530, loss: 0.0022262553684413433
2023-01-22 16:56:40.254429: step: 1248/530, loss: 0.0019818528089672327
2023-01-22 16:56:41.314646: step: 1252/530, loss: 0.00013990153092890978
2023-01-22 16:56:42.381406: step: 1256/530, loss: 0.008081446401774883
2023-01-22 16:56:43.455035: step: 1260/530, loss: 2.049219619948417e-05
2023-01-22 16:56:44.511826: step: 1264/530, loss: 0.008635352365672588
2023-01-22 16:56:45.556349: step: 1268/530, loss: 0.0005168033530935645
2023-01-22 16:56:46.625977: step: 1272/530, loss: 0.004564700648188591
2023-01-22 16:56:47.686837: step: 1276/530, loss: 0.0020665416959673166
2023-01-22 16:56:48.743329: step: 1280/530, loss: 0.001532746129669249
2023-01-22 16:56:49.790076: step: 1284/530, loss: 0.0020006042905151844
2023-01-22 16:56:50.845930: step: 1288/530, loss: 0.00018192874267697334
2023-01-22 16:56:51.902251: step: 1292/530, loss: 0.00016661809058859944
2023-01-22 16:56:52.968393: step: 1296/530, loss: 0.005625535733997822
2023-01-22 16:56:54.010429: step: 1300/530, loss: 0.0014008082216605544
2023-01-22 16:56:55.071593: step: 1304/530, loss: 0.00012441261787898839
2023-01-22 16:56:56.121337: step: 1308/530, loss: 0.002166094956919551
2023-01-22 16:56:57.164315: step: 1312/530, loss: 0.00018916135013569146
2023-01-22 16:56:58.227506: step: 1316/530, loss: 0.005777540151029825
2023-01-22 16:56:59.286044: step: 1320/530, loss: 0.005481211002916098
2023-01-22 16:57:00.339730: step: 1324/530, loss: 0.01034446619451046
2023-01-22 16:57:01.406147: step: 1328/530, loss: 0.00807970855385065
2023-01-22 16:57:02.464183: step: 1332/530, loss: 0.009156055748462677
2023-01-22 16:57:03.538422: step: 1336/530, loss: 0.0037293985951691866
2023-01-22 16:57:04.617445: step: 1340/530, loss: 0.0008094247314147651
2023-01-22 16:57:05.682300: step: 1344/530, loss: 0.0014338564360514283
2023-01-22 16:57:06.733538: step: 1348/530, loss: 0.0030299918726086617
2023-01-22 16:57:07.788905: step: 1352/530, loss: 0.001763385720551014
2023-01-22 16:57:08.849005: step: 1356/530, loss: 0.01738511584699154
2023-01-22 16:57:09.916225: step: 1360/530, loss: 0.0004947047564201057
2023-01-22 16:57:10.968761: step: 1364/530, loss: 0.00026786079979501665
2023-01-22 16:57:12.033817: step: 1368/530, loss: 0.0019334799144417048
2023-01-22 16:57:13.081661: step: 1372/530, loss: 3.631848449003883e-05
2023-01-22 16:57:14.140485: step: 1376/530, loss: 0.00024570233654230833
2023-01-22 16:57:15.196581: step: 1380/530, loss: 0.0009549768292345107
2023-01-22 16:57:16.243174: step: 1384/530, loss: 0.0011146035976707935
2023-01-22 16:57:17.298023: step: 1388/530, loss: 0.007656758185476065
2023-01-22 16:57:18.356661: step: 1392/530, loss: 0.0015436556423082948
2023-01-22 16:57:19.412583: step: 1396/530, loss: 0.0015269832219928503
2023-01-22 16:57:20.476873: step: 1400/530, loss: 0.005968090612441301
2023-01-22 16:57:21.541541: step: 1404/530, loss: 0.0006276214262470603
2023-01-22 16:57:22.593478: step: 1408/530, loss: 0.0004965476109646261
2023-01-22 16:57:23.654818: step: 1412/530, loss: 0.002950194524601102
2023-01-22 16:57:24.711141: step: 1416/530, loss: 0.0026596609968692064
2023-01-22 16:57:25.776962: step: 1420/530, loss: 0.0009486007620580494
2023-01-22 16:57:26.845987: step: 1424/530, loss: 0.007135091815143824
2023-01-22 16:57:27.896547: step: 1428/530, loss: 0.013007229194045067
2023-01-22 16:57:28.959710: step: 1432/530, loss: 0.008039118722081184
2023-01-22 16:57:29.999834: step: 1436/530, loss: 0.00043564659426920116
2023-01-22 16:57:31.050508: step: 1440/530, loss: 0.00016066610987763852
2023-01-22 16:57:32.149802: step: 1444/530, loss: 0.004876438062638044
2023-01-22 16:57:33.228388: step: 1448/530, loss: 0.013507763855159283
2023-01-22 16:57:34.297822: step: 1452/530, loss: 0.0037977967876940966
2023-01-22 16:57:35.354895: step: 1456/530, loss: 0.004352536518126726
2023-01-22 16:57:36.395882: step: 1460/530, loss: 0.00146788964048028
2023-01-22 16:57:37.460731: step: 1464/530, loss: 0.002133857225999236
2023-01-22 16:57:38.534132: step: 1468/530, loss: 0.0037330419290810823
2023-01-22 16:57:39.583530: step: 1472/530, loss: 0.0004797769943252206
2023-01-22 16:57:40.639894: step: 1476/530, loss: 0.008645614609122276
2023-01-22 16:57:41.687250: step: 1480/530, loss: 0.0021444440353661776
2023-01-22 16:57:42.752037: step: 1484/530, loss: 4.29782630817499e-05
2023-01-22 16:57:43.816774: step: 1488/530, loss: 0.0023098120000213385
2023-01-22 16:57:44.881959: step: 1492/530, loss: 0.004420808982104063
2023-01-22 16:57:45.935561: step: 1496/530, loss: 0.0077218953520059586
2023-01-22 16:57:46.994115: step: 1500/530, loss: 0.0022348875645548105
2023-01-22 16:57:48.053185: step: 1504/530, loss: 1.2686515219684225e-05
2023-01-22 16:57:49.123729: step: 1508/530, loss: 0.019776422530412674
2023-01-22 16:57:50.196415: step: 1512/530, loss: 0.02693009003996849
2023-01-22 16:57:51.267376: step: 1516/530, loss: 0.001665038405917585
2023-01-22 16:57:52.331949: step: 1520/530, loss: 0.006000143941491842
2023-01-22 16:57:53.389487: step: 1524/530, loss: 0.006056696642190218
2023-01-22 16:57:54.443760: step: 1528/530, loss: 0.0008812794694676995
2023-01-22 16:57:55.501298: step: 1532/530, loss: 0.002790366066619754
2023-01-22 16:57:56.556195: step: 1536/530, loss: 0.002530885860323906
2023-01-22 16:57:57.604179: step: 1540/530, loss: 0.00013026398664806038
2023-01-22 16:57:58.654787: step: 1544/530, loss: 0.0027537934947758913
2023-01-22 16:57:59.713957: step: 1548/530, loss: 0.006445032078772783
2023-01-22 16:58:00.766739: step: 1552/530, loss: 0.002408068859949708
2023-01-22 16:58:01.816155: step: 1556/530, loss: 0.002585968002676964
2023-01-22 16:58:02.878410: step: 1560/530, loss: 0.0020395778119564056
2023-01-22 16:58:03.951963: step: 1564/530, loss: 0.0022965550888329744
2023-01-22 16:58:04.999387: step: 1568/530, loss: 0.00021644317894242704
2023-01-22 16:58:06.054575: step: 1572/530, loss: 0.002595591591671109
2023-01-22 16:58:07.105754: step: 1576/530, loss: 0.019007235765457153
2023-01-22 16:58:08.167265: step: 1580/530, loss: 0.0025495353620499372
2023-01-22 16:58:09.228922: step: 1584/530, loss: 0.006664119195193052
2023-01-22 16:58:10.286859: step: 1588/530, loss: 0.0022273568902164698
2023-01-22 16:58:11.333708: step: 1592/530, loss: 0.010411778464913368
2023-01-22 16:58:12.388531: step: 1596/530, loss: 0.001893027569167316
2023-01-22 16:58:13.441425: step: 1600/530, loss: 2.3663549654884264e-05
2023-01-22 16:58:14.498521: step: 1604/530, loss: 0.005143004935234785
2023-01-22 16:58:15.553595: step: 1608/530, loss: 0.0007624438148923218
2023-01-22 16:58:16.624484: step: 1612/530, loss: 0.0005540741258300841
2023-01-22 16:58:17.678412: step: 1616/530, loss: 0.0016197680961340666
2023-01-22 16:58:18.724522: step: 1620/530, loss: 0.0016089766286313534
2023-01-22 16:58:19.782607: step: 1624/530, loss: 0.001013288157992065
2023-01-22 16:58:20.835560: step: 1628/530, loss: 0.0021637678146362305
2023-01-22 16:58:21.898327: step: 1632/530, loss: 0.003966888412833214
2023-01-22 16:58:22.964853: step: 1636/530, loss: 0.005445551592856646
2023-01-22 16:58:24.037867: step: 1640/530, loss: 0.0011840645456686616
2023-01-22 16:58:25.104291: step: 1644/530, loss: 0.00056924216914922
2023-01-22 16:58:26.161039: step: 1648/530, loss: 0.0016776478150859475
2023-01-22 16:58:27.233913: step: 1652/530, loss: 0.004186647478491068
2023-01-22 16:58:28.288151: step: 1656/530, loss: 0.0036190024111419916
2023-01-22 16:58:29.352818: step: 1660/530, loss: 0.001610213192179799
2023-01-22 16:58:30.431911: step: 1664/530, loss: 0.000516460626386106
2023-01-22 16:58:31.478114: step: 1668/530, loss: 0.0005445809219963849
2023-01-22 16:58:32.563224: step: 1672/530, loss: 0.004317122045904398
2023-01-22 16:58:33.616250: step: 1676/530, loss: 0.0005467144073918462
2023-01-22 16:58:34.666001: step: 1680/530, loss: 0.007170079741626978
2023-01-22 16:58:35.706402: step: 1684/530, loss: 0.0007546812994405627
2023-01-22 16:58:36.766580: step: 1688/530, loss: 0.0083444369956851
2023-01-22 16:58:37.814896: step: 1692/530, loss: 0.0031342809088528156
2023-01-22 16:58:38.856651: step: 1696/530, loss: 0.007302084006369114
2023-01-22 16:58:39.936301: step: 1700/530, loss: 0.0024414104409515858
2023-01-22 16:58:40.992502: step: 1704/530, loss: 0.011127714067697525
2023-01-22 16:58:42.064689: step: 1708/530, loss: 0.0053037721663713455
2023-01-22 16:58:43.117064: step: 1712/530, loss: 0.0007818203885108232
2023-01-22 16:58:44.158154: step: 1716/530, loss: 0.0033460850827395916
2023-01-22 16:58:45.230236: step: 1720/530, loss: 0.0031537010800093412
2023-01-22 16:58:46.274726: step: 1724/530, loss: 0.00017203677271027118
2023-01-22 16:58:47.333787: step: 1728/530, loss: 0.0004809864913113415
2023-01-22 16:58:48.387181: step: 1732/530, loss: 0.00078528409358114
2023-01-22 16:58:49.431318: step: 1736/530, loss: 0.0038315928541123867
2023-01-22 16:58:50.481513: step: 1740/530, loss: 0.010124877095222473
2023-01-22 16:58:51.542116: step: 1744/530, loss: 0.0016368799842894077
2023-01-22 16:58:52.603605: step: 1748/530, loss: 0.002827103016898036
2023-01-22 16:58:53.659413: step: 1752/530, loss: 0.003476216457784176
2023-01-22 16:58:54.716473: step: 1756/530, loss: 0.004301495850086212
2023-01-22 16:58:55.776230: step: 1760/530, loss: 0.0
2023-01-22 16:58:56.837814: step: 1764/530, loss: 0.006158389151096344
2023-01-22 16:58:57.907840: step: 1768/530, loss: 0.0020148418843746185
2023-01-22 16:58:58.969782: step: 1772/530, loss: 0.0007876895251683891
2023-01-22 16:59:00.026970: step: 1776/530, loss: 0.0011058927047997713
2023-01-22 16:59:01.089330: step: 1780/530, loss: 0.0018458337290212512
2023-01-22 16:59:02.153238: step: 1784/530, loss: 0.0030139549635350704
2023-01-22 16:59:03.196526: step: 1788/530, loss: 0.0011102540884166956
2023-01-22 16:59:04.267408: step: 1792/530, loss: 0.005093112587928772
2023-01-22 16:59:05.343550: step: 1796/530, loss: 0.0006039586733095348
2023-01-22 16:59:06.386550: step: 1800/530, loss: 0.0003881119773723185
2023-01-22 16:59:07.442691: step: 1804/530, loss: 0.000486546108732
2023-01-22 16:59:08.504748: step: 1808/530, loss: 0.01677919365465641
2023-01-22 16:59:09.572914: step: 1812/530, loss: 0.024995028972625732
2023-01-22 16:59:10.624467: step: 1816/530, loss: 0.006688401103019714
2023-01-22 16:59:11.674354: step: 1820/530, loss: 0.005299373529851437
2023-01-22 16:59:12.739069: step: 1824/530, loss: 0.001538599724881351
2023-01-22 16:59:13.792573: step: 1828/530, loss: 0.0022909792605787516
2023-01-22 16:59:14.853053: step: 1832/530, loss: 0.019943134859204292
2023-01-22 16:59:15.902577: step: 1836/530, loss: 0.00012144041829742491
2023-01-22 16:59:16.949114: step: 1840/530, loss: 0.0
2023-01-22 16:59:18.003891: step: 1844/530, loss: 0.0005485381698235869
2023-01-22 16:59:19.070182: step: 1848/530, loss: 0.009844658896327019
2023-01-22 16:59:20.120364: step: 1852/530, loss: 2.9308232114999555e-05
2023-01-22 16:59:21.179452: step: 1856/530, loss: 0.008227067068219185
2023-01-22 16:59:22.227317: step: 1860/530, loss: 0.003899388713762164
2023-01-22 16:59:23.278388: step: 1864/530, loss: 0.00796444807201624
2023-01-22 16:59:24.331942: step: 1868/530, loss: 0.004359161015599966
2023-01-22 16:59:25.389077: step: 1872/530, loss: 0.0009831773350015283
2023-01-22 16:59:26.464352: step: 1876/530, loss: 0.008360393345355988
2023-01-22 16:59:27.532521: step: 1880/530, loss: 0.005839694757014513
2023-01-22 16:59:28.595658: step: 1884/530, loss: 0.030147099867463112
2023-01-22 16:59:29.644395: step: 1888/530, loss: 0.0003252174938097596
2023-01-22 16:59:30.700697: step: 1892/530, loss: 0.0034150569699704647
2023-01-22 16:59:31.765781: step: 1896/530, loss: 0.08521401137113571
2023-01-22 16:59:32.812518: step: 1900/530, loss: 0.00020494101045187563
2023-01-22 16:59:33.891431: step: 1904/530, loss: 7.621472377650207e-07
2023-01-22 16:59:34.952693: step: 1908/530, loss: 0.007479064166545868
2023-01-22 16:59:36.015829: step: 1912/530, loss: 0.002421255921944976
2023-01-22 16:59:37.088420: step: 1916/530, loss: 0.0023866642732173204
2023-01-22 16:59:38.137570: step: 1920/530, loss: 0.0
2023-01-22 16:59:39.204618: step: 1924/530, loss: 2.1468096747412346e-05
2023-01-22 16:59:40.262440: step: 1928/530, loss: 0.003941888455301523
2023-01-22 16:59:41.316721: step: 1932/530, loss: 5.8215318858856335e-05
2023-01-22 16:59:42.385638: step: 1936/530, loss: 0.06962382048368454
2023-01-22 16:59:43.440741: step: 1940/530, loss: 0.005815138574689627
2023-01-22 16:59:44.509720: step: 1944/530, loss: 0.002845507813617587
2023-01-22 16:59:45.590504: step: 1948/530, loss: 0.0038012012373656034
2023-01-22 16:59:46.654775: step: 1952/530, loss: 0.00035948309232480824
2023-01-22 16:59:47.716664: step: 1956/530, loss: 0.004982306156307459
2023-01-22 16:59:48.777724: step: 1960/530, loss: 0.0037483167834579945
2023-01-22 16:59:49.833480: step: 1964/530, loss: 0.005964509677141905
2023-01-22 16:59:50.876215: step: 1968/530, loss: 0.004076770972460508
2023-01-22 16:59:51.948432: step: 1972/530, loss: 0.0019410912645980716
2023-01-22 16:59:53.005561: step: 1976/530, loss: 0.0037738399114459753
2023-01-22 16:59:54.051589: step: 1980/530, loss: 0.0007405421347357333
2023-01-22 16:59:55.120278: step: 1984/530, loss: 0.005200081970542669
2023-01-22 16:59:56.186884: step: 1988/530, loss: 0.021056078374385834
2023-01-22 16:59:57.248788: step: 1992/530, loss: 0.004166916012763977
2023-01-22 16:59:58.309631: step: 1996/530, loss: 0.00013920108904130757
2023-01-22 16:59:59.378747: step: 2000/530, loss: 2.0488516838668147e-06
2023-01-22 17:00:00.445746: step: 2004/530, loss: 0.00863782037049532
2023-01-22 17:00:01.507522: step: 2008/530, loss: 0.012423371896147728
2023-01-22 17:00:02.590886: step: 2012/530, loss: 0.0002685433137230575
2023-01-22 17:00:03.654996: step: 2016/530, loss: 0.0023049134761095047
2023-01-22 17:00:04.736476: step: 2020/530, loss: 0.0006565408548340201
2023-01-22 17:00:05.795357: step: 2024/530, loss: 0.000225957075599581
2023-01-22 17:00:06.861679: step: 2028/530, loss: 0.0017843234818428755
2023-01-22 17:00:07.913178: step: 2032/530, loss: 0.0014595558168366551
2023-01-22 17:00:08.980215: step: 2036/530, loss: 0.004431008826941252
2023-01-22 17:00:10.038132: step: 2040/530, loss: 0.0001075672116712667
2023-01-22 17:00:11.092031: step: 2044/530, loss: 0.0038190234918147326
2023-01-22 17:00:12.151027: step: 2048/530, loss: 0.0003169569536112249
2023-01-22 17:00:13.200180: step: 2052/530, loss: 0.000324446358717978
2023-01-22 17:00:14.272144: step: 2056/530, loss: 0.003834645263850689
2023-01-22 17:00:15.338932: step: 2060/530, loss: 0.0008672822150401771
2023-01-22 17:00:16.394252: step: 2064/530, loss: 0.0012764601269736886
2023-01-22 17:00:17.452133: step: 2068/530, loss: 0.001300034229643643
2023-01-22 17:00:18.510266: step: 2072/530, loss: 0.007917891256511211
2023-01-22 17:00:19.587495: step: 2076/530, loss: 0.00218352023512125
2023-01-22 17:00:20.644994: step: 2080/530, loss: 0.0020616771653294563
2023-01-22 17:00:21.685662: step: 2084/530, loss: 0.00010413958807475865
2023-01-22 17:00:22.744884: step: 2088/530, loss: 0.002087678061798215
2023-01-22 17:00:23.798346: step: 2092/530, loss: 0.009423180483281612
2023-01-22 17:00:24.846803: step: 2096/530, loss: 0.0011999638518318534
2023-01-22 17:00:25.907340: step: 2100/530, loss: 0.010037058964371681
2023-01-22 17:00:26.969159: step: 2104/530, loss: 0.004111235495656729
2023-01-22 17:00:28.032562: step: 2108/530, loss: 0.00021061539882794023
2023-01-22 17:00:29.093479: step: 2112/530, loss: 0.00044255657121539116
2023-01-22 17:00:30.161434: step: 2116/530, loss: 0.0031181317754089832
2023-01-22 17:00:31.212706: step: 2120/530, loss: 0.00498694134876132
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3226661587876791, 'r': 0.2853884396853147, 'f1': 0.30288461538461536}, 'combined': 0.2019230769230769, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4016026678772019, 'r': 0.3189197656671897, 'f1': 0.3555171158257197}, 'combined': 0.2320216966441539, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3248763630883884, 'r': 0.34090441895233164, 'f1': 0.33269746071829404}, 'combined': 0.24514549737137453, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35909101532669147, 'r': 0.3280008841295753, 'f1': 0.3428425530947145}, 'combined': 0.22737744453949973, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 12}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 13
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:03:04.032863: step: 4/530, loss: 0.0008320769411511719
2023-01-22 17:03:05.082207: step: 8/530, loss: 0.014367454685270786
2023-01-22 17:03:06.143666: step: 12/530, loss: 0.040785402059555054
2023-01-22 17:03:07.197219: step: 16/530, loss: 0.0021763211116194725
2023-01-22 17:03:08.250637: step: 20/530, loss: 0.00861972477287054
2023-01-22 17:03:09.311075: step: 24/530, loss: 0.0018987206276506186
2023-01-22 17:03:10.360670: step: 28/530, loss: 0.0013313519302755594
2023-01-22 17:03:11.410048: step: 32/530, loss: 0.0117793595418334
2023-01-22 17:03:12.465689: step: 36/530, loss: 0.0009330848697572947
2023-01-22 17:03:13.544805: step: 40/530, loss: 0.002755777444690466
2023-01-22 17:03:14.596295: step: 44/530, loss: 0.007323131896555424
2023-01-22 17:03:15.642992: step: 48/530, loss: 0.010742099024355412
2023-01-22 17:03:16.683557: step: 52/530, loss: 0.002013320568948984
2023-01-22 17:03:17.743708: step: 56/530, loss: 0.000884855689946562
2023-01-22 17:03:18.804544: step: 60/530, loss: 0.001123062102124095
2023-01-22 17:03:19.872221: step: 64/530, loss: 0.0009394078515470028
2023-01-22 17:03:20.926071: step: 68/530, loss: 0.00286126509308815
2023-01-22 17:03:21.999169: step: 72/530, loss: 0.008185154758393764
2023-01-22 17:03:23.059303: step: 76/530, loss: 0.00321989506483078
2023-01-22 17:03:24.126718: step: 80/530, loss: 0.0021773437038064003
2023-01-22 17:03:25.182861: step: 84/530, loss: 0.0010736762778833508
2023-01-22 17:03:26.237265: step: 88/530, loss: 0.000245375296799466
2023-01-22 17:03:27.291994: step: 92/530, loss: 0.0036642253398895264
2023-01-22 17:03:28.334852: step: 96/530, loss: 0.0018407822353765368
2023-01-22 17:03:29.384332: step: 100/530, loss: 0.0011522320564836264
2023-01-22 17:03:30.455617: step: 104/530, loss: 0.004422913305461407
2023-01-22 17:03:31.515135: step: 108/530, loss: 0.00038650084752589464
2023-01-22 17:03:32.583241: step: 112/530, loss: 0.000989661319181323
2023-01-22 17:03:33.648877: step: 116/530, loss: 0.006751012522727251
2023-01-22 17:03:34.727161: step: 120/530, loss: 0.004980576224625111
2023-01-22 17:03:35.774069: step: 124/530, loss: 1.8379096218268387e-05
2023-01-22 17:03:36.838484: step: 128/530, loss: 0.0003218639176338911
2023-01-22 17:03:37.909104: step: 132/530, loss: 0.0112758232280612
2023-01-22 17:03:38.977453: step: 136/530, loss: 0.009117452427744865
2023-01-22 17:03:40.035001: step: 140/530, loss: 0.0037655173800885677
2023-01-22 17:03:41.100993: step: 144/530, loss: 0.0030212050769478083
2023-01-22 17:03:42.160986: step: 148/530, loss: 0.0029100566171109676
2023-01-22 17:03:43.223267: step: 152/530, loss: 0.0013753143139183521
2023-01-22 17:03:44.282317: step: 156/530, loss: 0.00029679088038392365
2023-01-22 17:03:45.343663: step: 160/530, loss: 0.00014125104644335806
2023-01-22 17:03:46.393340: step: 164/530, loss: 0.0026432317681610584
2023-01-22 17:03:47.457988: step: 168/530, loss: 0.0011071398621425033
2023-01-22 17:03:48.517479: step: 172/530, loss: 0.001150714815594256
2023-01-22 17:03:49.587153: step: 176/530, loss: 0.0009518184815533459
2023-01-22 17:03:50.642276: step: 180/530, loss: 0.0030756117776036263
2023-01-22 17:03:51.699458: step: 184/530, loss: 0.004332979209721088
2023-01-22 17:03:52.748327: step: 188/530, loss: 0.0005897373775951564
2023-01-22 17:03:53.812868: step: 192/530, loss: 0.0009652886656112969
2023-01-22 17:03:54.868559: step: 196/530, loss: 0.003094347193837166
2023-01-22 17:03:55.917523: step: 200/530, loss: 0.0005280639161355793
2023-01-22 17:03:56.971901: step: 204/530, loss: 1.8843253201339394e-05
2023-01-22 17:03:58.023601: step: 208/530, loss: 0.0004711709334515035
2023-01-22 17:03:59.080970: step: 212/530, loss: 0.007090361788868904
2023-01-22 17:04:00.134590: step: 216/530, loss: 0.0006955088465474546
2023-01-22 17:04:01.194079: step: 220/530, loss: 0.0003505217900965363
2023-01-22 17:04:02.240890: step: 224/530, loss: 0.0009581840713508427
2023-01-22 17:04:03.310807: step: 228/530, loss: 0.00020301745098549873
2023-01-22 17:04:04.381364: step: 232/530, loss: 0.00123145233374089
2023-01-22 17:04:05.445019: step: 236/530, loss: 0.009180593304336071
2023-01-22 17:04:06.526608: step: 240/530, loss: 0.0010323997121304274
2023-01-22 17:04:07.594541: step: 244/530, loss: 0.0034350408241152763
2023-01-22 17:04:08.659254: step: 248/530, loss: 0.0056566656567156315
2023-01-22 17:04:09.725355: step: 252/530, loss: 0.003973392769694328
2023-01-22 17:04:10.782898: step: 256/530, loss: 0.004792486317455769
2023-01-22 17:04:11.843020: step: 260/530, loss: 0.000585669360589236
2023-01-22 17:04:12.896494: step: 264/530, loss: 0.0003002863086294383
2023-01-22 17:04:13.958637: step: 268/530, loss: 0.0005055919755250216
2023-01-22 17:04:15.014849: step: 272/530, loss: 0.021637700498104095
2023-01-22 17:04:16.082396: step: 276/530, loss: 0.0014909520978108048
2023-01-22 17:04:17.135482: step: 280/530, loss: 0.009958428330719471
2023-01-22 17:04:18.216716: step: 284/530, loss: 0.01677277311682701
2023-01-22 17:04:19.275706: step: 288/530, loss: 0.0002959614503197372
2023-01-22 17:04:20.369385: step: 292/530, loss: 0.021321265026926994
2023-01-22 17:04:21.435093: step: 296/530, loss: 0.0026408189442008734
2023-01-22 17:04:22.503659: step: 300/530, loss: 0.0009057041606865823
2023-01-22 17:04:23.567296: step: 304/530, loss: 0.0042593698017299175
2023-01-22 17:04:24.618280: step: 308/530, loss: 0.003941622097045183
2023-01-22 17:04:25.666169: step: 312/530, loss: 6.589168151549529e-06
2023-01-22 17:04:26.721426: step: 316/530, loss: 0.0005271020345389843
2023-01-22 17:04:27.809699: step: 320/530, loss: 0.003769570728763938
2023-01-22 17:04:28.875510: step: 324/530, loss: 0.002862769179046154
2023-01-22 17:04:29.942541: step: 328/530, loss: 0.003058553207665682
2023-01-22 17:04:31.025893: step: 332/530, loss: 0.004292203579097986
2023-01-22 17:04:32.107460: step: 336/530, loss: 0.011226531118154526
2023-01-22 17:04:33.156413: step: 340/530, loss: 0.00023230203078128397
2023-01-22 17:04:34.202824: step: 344/530, loss: 0.004742414690554142
2023-01-22 17:04:35.278687: step: 348/530, loss: 0.0006980329053476453
2023-01-22 17:04:36.335275: step: 352/530, loss: 0.001675250823609531
2023-01-22 17:04:37.375157: step: 356/530, loss: 0.0026135961525142193
2023-01-22 17:04:38.441758: step: 360/530, loss: 0.0057469625025987625
2023-01-22 17:04:39.500133: step: 364/530, loss: 0.003330593928694725
2023-01-22 17:04:40.580162: step: 368/530, loss: 0.003779633669182658
2023-01-22 17:04:41.659577: step: 372/530, loss: 0.017489172518253326
2023-01-22 17:04:42.699201: step: 376/530, loss: 0.006842587608844042
2023-01-22 17:04:43.782576: step: 380/530, loss: 0.012858384288847446
2023-01-22 17:04:44.835165: step: 384/530, loss: 0.0009603927610442042
2023-01-22 17:04:45.906985: step: 388/530, loss: 0.0038138707168400288
2023-01-22 17:04:46.977194: step: 392/530, loss: 0.0048032780177891254
2023-01-22 17:04:48.055073: step: 396/530, loss: 0.002552689053118229
2023-01-22 17:04:49.108215: step: 400/530, loss: 0.0014193045208230615
2023-01-22 17:04:50.162456: step: 404/530, loss: 0.0027619136963039637
2023-01-22 17:04:51.245142: step: 408/530, loss: 0.0024915006943047047
2023-01-22 17:04:52.300431: step: 412/530, loss: 0.00102722248993814
2023-01-22 17:04:53.375274: step: 416/530, loss: 0.0009601069032214582
2023-01-22 17:04:54.432246: step: 420/530, loss: 0.0022687669843435287
2023-01-22 17:04:55.498265: step: 424/530, loss: 0.0018105338094756007
2023-01-22 17:04:56.548798: step: 428/530, loss: 0.0033635010477155447
2023-01-22 17:04:57.615050: step: 432/530, loss: 0.0012814328074455261
2023-01-22 17:04:58.699727: step: 436/530, loss: 0.0005406891577877104
2023-01-22 17:04:59.759515: step: 440/530, loss: 0.005423763766884804
2023-01-22 17:05:00.830795: step: 444/530, loss: 0.0020923998672515154
2023-01-22 17:05:01.896924: step: 448/530, loss: 0.0006722522084601223
2023-01-22 17:05:02.960172: step: 452/530, loss: 0.02272350713610649
2023-01-22 17:05:04.028820: step: 456/530, loss: 0.0005271777044981718
2023-01-22 17:05:05.090440: step: 460/530, loss: 0.00429708743467927
2023-01-22 17:05:06.148935: step: 464/530, loss: 0.0014052659971639514
2023-01-22 17:05:07.217882: step: 468/530, loss: 0.0017484532436355948
2023-01-22 17:05:08.272650: step: 472/530, loss: 0.003103214083239436
2023-01-22 17:05:09.316918: step: 476/530, loss: 0.003538790624588728
2023-01-22 17:05:10.387181: step: 480/530, loss: 0.007891153916716576
2023-01-22 17:05:11.448957: step: 484/530, loss: 0.016561798751354218
2023-01-22 17:05:12.508266: step: 488/530, loss: 0.021601224318146706
2023-01-22 17:05:13.581907: step: 492/530, loss: 0.004168195649981499
2023-01-22 17:05:14.655187: step: 496/530, loss: 0.005666607990860939
2023-01-22 17:05:15.702191: step: 500/530, loss: 0.0035148924216628075
2023-01-22 17:05:16.740387: step: 504/530, loss: 0.00020331161795184016
2023-01-22 17:05:17.795163: step: 508/530, loss: 0.006514247972518206
2023-01-22 17:05:18.834989: step: 512/530, loss: 0.0015850355848670006
2023-01-22 17:05:19.896007: step: 516/530, loss: 0.0003407117328606546
2023-01-22 17:05:20.972550: step: 520/530, loss: 0.014483748003840446
2023-01-22 17:05:22.029342: step: 524/530, loss: 0.014640352688729763
2023-01-22 17:05:23.085348: step: 528/530, loss: 0.0002690246910788119
2023-01-22 17:05:24.140021: step: 532/530, loss: 0.006800653412938118
2023-01-22 17:05:25.211811: step: 536/530, loss: 0.0012988498201593757
2023-01-22 17:05:26.259475: step: 540/530, loss: 0.008248641155660152
2023-01-22 17:05:27.313345: step: 544/530, loss: 0.011483488604426384
2023-01-22 17:05:28.358220: step: 548/530, loss: 0.00792290735989809
2023-01-22 17:05:29.413698: step: 552/530, loss: 0.0002428980078548193
2023-01-22 17:05:30.474676: step: 556/530, loss: 0.0025394458789378405
2023-01-22 17:05:31.546509: step: 560/530, loss: 0.008252744562923908
2023-01-22 17:05:32.620976: step: 564/530, loss: 8.642394095659256e-05
2023-01-22 17:05:33.670236: step: 568/530, loss: 0.0009812781354412436
2023-01-22 17:05:34.727346: step: 572/530, loss: 0.0021326018031686544
2023-01-22 17:05:35.806720: step: 576/530, loss: 0.00280452286824584
2023-01-22 17:05:36.853824: step: 580/530, loss: 0.002680838108062744
2023-01-22 17:05:37.908847: step: 584/530, loss: 0.0009603391517885029
2023-01-22 17:05:38.972984: step: 588/530, loss: 0.0017605674220249057
2023-01-22 17:05:40.023591: step: 592/530, loss: 7.512886077165604e-05
2023-01-22 17:05:41.087899: step: 596/530, loss: 0.002198146190494299
2023-01-22 17:05:42.153409: step: 600/530, loss: 0.0003285809070803225
2023-01-22 17:05:43.205969: step: 604/530, loss: 0.002589072333648801
2023-01-22 17:05:44.257507: step: 608/530, loss: 0.019502662122249603
2023-01-22 17:05:45.322292: step: 612/530, loss: 0.0017936592921614647
2023-01-22 17:05:46.370505: step: 616/530, loss: 0.0005071019404567778
2023-01-22 17:05:47.422378: step: 620/530, loss: 0.0009245231631211936
2023-01-22 17:05:48.470892: step: 624/530, loss: 0.005336207803338766
2023-01-22 17:05:49.547429: step: 628/530, loss: 0.0006078645237721503
2023-01-22 17:05:50.624887: step: 632/530, loss: 0.006319988053292036
2023-01-22 17:05:51.668278: step: 636/530, loss: 0.0029545859433710575
2023-01-22 17:05:52.736663: step: 640/530, loss: 0.0002314333396498114
2023-01-22 17:05:53.795212: step: 644/530, loss: 0.004481207113713026
2023-01-22 17:05:54.845211: step: 648/530, loss: 0.00017579400446265936
2023-01-22 17:05:55.908141: step: 652/530, loss: 0.0053586214780807495
2023-01-22 17:05:56.979157: step: 656/530, loss: 0.0017509327735751867
2023-01-22 17:05:58.030630: step: 660/530, loss: 0.0017079696990549564
2023-01-22 17:05:59.085509: step: 664/530, loss: 0.0013236228842288256
2023-01-22 17:06:00.144209: step: 668/530, loss: 0.002056313445791602
2023-01-22 17:06:01.184316: step: 672/530, loss: 0.0038687021005898714
2023-01-22 17:06:02.257202: step: 676/530, loss: 0.005694231018424034
2023-01-22 17:06:03.322545: step: 680/530, loss: 0.005716739688068628
2023-01-22 17:06:04.401705: step: 684/530, loss: 0.002786272671073675
2023-01-22 17:06:05.448165: step: 688/530, loss: 0.0024394888896495104
2023-01-22 17:06:06.493109: step: 692/530, loss: 0.004570594523102045
2023-01-22 17:06:07.569881: step: 696/530, loss: 0.007836435921490192
2023-01-22 17:06:08.623588: step: 700/530, loss: 0.00041332971886731684
2023-01-22 17:06:09.682373: step: 704/530, loss: 0.0037523575592786074
2023-01-22 17:06:10.739211: step: 708/530, loss: 0.008568313904106617
2023-01-22 17:06:11.789844: step: 712/530, loss: 0.002507713856175542
2023-01-22 17:06:12.847064: step: 716/530, loss: 6.599714834010229e-05
2023-01-22 17:06:13.898056: step: 720/530, loss: 0.0016238060779869556
2023-01-22 17:06:14.955382: step: 724/530, loss: 0.0023533115163445473
2023-01-22 17:06:16.025268: step: 728/530, loss: 0.0006747259176336229
2023-01-22 17:06:17.085731: step: 732/530, loss: 0.0007141977548599243
2023-01-22 17:06:18.128904: step: 736/530, loss: 0.003219838486984372
2023-01-22 17:06:19.183474: step: 740/530, loss: 0.0015786078292876482
2023-01-22 17:06:20.244621: step: 744/530, loss: 0.0037862283643335104
2023-01-22 17:06:21.302351: step: 748/530, loss: 0.0016279892297461629
2023-01-22 17:06:22.351049: step: 752/530, loss: 0.0014700100291520357
2023-01-22 17:06:23.403051: step: 756/530, loss: 0.006723557133227587
2023-01-22 17:06:24.461820: step: 760/530, loss: 0.007349103689193726
2023-01-22 17:06:25.514146: step: 764/530, loss: 0.0006401078426279128
2023-01-22 17:06:26.566119: step: 768/530, loss: 0.008178593590855598
2023-01-22 17:06:27.636535: step: 772/530, loss: 0.0009549085516482592
2023-01-22 17:06:28.675530: step: 776/530, loss: 5.3505613323068246e-05
2023-01-22 17:06:29.734160: step: 780/530, loss: 8.332834113389254e-06
2023-01-22 17:06:30.776200: step: 784/530, loss: 0.0004199588729534298
2023-01-22 17:06:31.833331: step: 788/530, loss: 0.005242860410362482
2023-01-22 17:06:32.884137: step: 792/530, loss: 1.751254967530258e-05
2023-01-22 17:06:33.936446: step: 796/530, loss: 0.0038681384176015854
2023-01-22 17:06:34.995722: step: 800/530, loss: 0.0035651838406920433
2023-01-22 17:06:36.056900: step: 804/530, loss: 0.005050069186836481
2023-01-22 17:06:37.108858: step: 808/530, loss: 0.004731187131255865
2023-01-22 17:06:38.169943: step: 812/530, loss: 0.003956017084419727
2023-01-22 17:06:39.217573: step: 816/530, loss: 0.013566078618168831
2023-01-22 17:06:40.263649: step: 820/530, loss: 0.003332513850182295
2023-01-22 17:06:41.332945: step: 824/530, loss: 0.0077276979573071
2023-01-22 17:06:42.387295: step: 828/530, loss: 0.0010049307020381093
2023-01-22 17:06:43.444847: step: 832/530, loss: 0.00036363702383823693
2023-01-22 17:06:44.513102: step: 836/530, loss: 0.0028144861571490765
2023-01-22 17:06:45.570497: step: 840/530, loss: 0.004796306602656841
2023-01-22 17:06:46.631628: step: 844/530, loss: 0.009523033164441586
2023-01-22 17:06:47.691998: step: 848/530, loss: 2.0529869289021008e-05
2023-01-22 17:06:48.743470: step: 852/530, loss: 0.0025669445749372244
2023-01-22 17:06:49.794796: step: 856/530, loss: 5.4223983170231804e-05
2023-01-22 17:06:50.833985: step: 860/530, loss: 0.008463486097753048
2023-01-22 17:06:51.888884: step: 864/530, loss: 0.0005861074314452708
2023-01-22 17:06:52.941795: step: 868/530, loss: 0.022007029503583908
2023-01-22 17:06:53.994620: step: 872/530, loss: 0.03023066371679306
2023-01-22 17:06:55.039376: step: 876/530, loss: 0.0008784490055404603
2023-01-22 17:06:56.097388: step: 880/530, loss: 0.01051307562738657
2023-01-22 17:06:57.154193: step: 884/530, loss: 0.005714877508580685
2023-01-22 17:06:58.222890: step: 888/530, loss: 0.006544552743434906
2023-01-22 17:06:59.268456: step: 892/530, loss: 0.0050248634070158005
2023-01-22 17:07:00.327497: step: 896/530, loss: 0.010159206576645374
2023-01-22 17:07:01.385684: step: 900/530, loss: 0.0010611327597871423
2023-01-22 17:07:02.453976: step: 904/530, loss: 0.005536375101655722
2023-01-22 17:07:03.502474: step: 908/530, loss: 0.0040043070912361145
2023-01-22 17:07:04.556521: step: 912/530, loss: 0.002809088909998536
2023-01-22 17:07:05.620064: step: 916/530, loss: 0.003653450170531869
2023-01-22 17:07:06.676995: step: 920/530, loss: 0.015358002856373787
2023-01-22 17:07:07.735817: step: 924/530, loss: 0.008732953108847141
2023-01-22 17:07:08.790683: step: 928/530, loss: 0.0020503837149590254
2023-01-22 17:07:09.853634: step: 932/530, loss: 0.0007922257063910365
2023-01-22 17:07:10.905679: step: 936/530, loss: 3.98771844629664e-05
2023-01-22 17:07:11.966342: step: 940/530, loss: 0.009864992462098598
2023-01-22 17:07:13.023264: step: 944/530, loss: 0.008958365768194199
2023-01-22 17:07:14.092906: step: 948/530, loss: 0.0018235777970403433
2023-01-22 17:07:15.156013: step: 952/530, loss: 7.47388185118325e-05
2023-01-22 17:07:16.222643: step: 956/530, loss: 0.0055508483201265335
2023-01-22 17:07:17.282653: step: 960/530, loss: 0.000520433415658772
2023-01-22 17:07:18.358690: step: 964/530, loss: 0.002398409880697727
2023-01-22 17:07:19.413928: step: 968/530, loss: 0.003401942318305373
2023-01-22 17:07:20.467617: step: 972/530, loss: 0.004163446836173534
2023-01-22 17:07:21.511697: step: 976/530, loss: 0.00033889958285726607
2023-01-22 17:07:22.573709: step: 980/530, loss: 0.013147062622010708
2023-01-22 17:07:23.653304: step: 984/530, loss: 0.0016859377501532435
2023-01-22 17:07:24.703594: step: 988/530, loss: 0.004161641001701355
2023-01-22 17:07:25.759179: step: 992/530, loss: 0.0024572047404944897
2023-01-22 17:07:26.800239: step: 996/530, loss: 0.0002782403025776148
2023-01-22 17:07:27.853347: step: 1000/530, loss: 0.005075226072221994
2023-01-22 17:07:28.922064: step: 1004/530, loss: 0.004046840593218803
2023-01-22 17:07:29.970286: step: 1008/530, loss: 0.01393798552453518
2023-01-22 17:07:31.032871: step: 1012/530, loss: 0.0027777086943387985
2023-01-22 17:07:32.108147: step: 1016/530, loss: 0.0016684230649843812
2023-01-22 17:07:33.153923: step: 1020/530, loss: 0.008456406183540821
2023-01-22 17:07:34.220810: step: 1024/530, loss: 0.014498726464807987
2023-01-22 17:07:35.271342: step: 1028/530, loss: 4.467165854293853e-05
2023-01-22 17:07:36.327188: step: 1032/530, loss: 0.004397765267640352
2023-01-22 17:07:37.377140: step: 1036/530, loss: 0.011192373000085354
2023-01-22 17:07:38.443735: step: 1040/530, loss: 0.0002414122864138335
2023-01-22 17:07:39.509495: step: 1044/530, loss: 0.009831283241510391
2023-01-22 17:07:40.563206: step: 1048/530, loss: 0.0004700064309872687
2023-01-22 17:07:41.633753: step: 1052/530, loss: 0.001353634288534522
2023-01-22 17:07:42.691752: step: 1056/530, loss: 0.002589730080217123
2023-01-22 17:07:43.745853: step: 1060/530, loss: 0.001597752794623375
2023-01-22 17:07:44.793689: step: 1064/530, loss: 0.0028609249275177717
2023-01-22 17:07:45.848958: step: 1068/530, loss: 0.0007374901324510574
2023-01-22 17:07:46.913126: step: 1072/530, loss: 0.007631149608641863
2023-01-22 17:07:47.980621: step: 1076/530, loss: 0.005985576659440994
2023-01-22 17:07:49.039433: step: 1080/530, loss: 0.00020712753757834435
2023-01-22 17:07:50.098672: step: 1084/530, loss: 0.0009111129911616445
2023-01-22 17:07:51.171334: step: 1088/530, loss: 0.019185533747076988
2023-01-22 17:07:52.232975: step: 1092/530, loss: 0.0016105037648230791
2023-01-22 17:07:53.307261: step: 1096/530, loss: 0.00957140140235424
2023-01-22 17:07:54.366540: step: 1100/530, loss: 0.0010641703847795725
2023-01-22 17:07:55.428286: step: 1104/530, loss: 0.008787252940237522
2023-01-22 17:07:56.496982: step: 1108/530, loss: 0.0019633693154901266
2023-01-22 17:07:57.542814: step: 1112/530, loss: 0.0007620689575560391
2023-01-22 17:07:58.598776: step: 1116/530, loss: 0.005614517722278833
2023-01-22 17:07:59.641555: step: 1120/530, loss: 0.0010899496264755726
2023-01-22 17:08:00.680088: step: 1124/530, loss: 0.0006819992559030652
2023-01-22 17:08:01.737042: step: 1128/530, loss: 0.0002976080577354878
2023-01-22 17:08:02.844874: step: 1132/530, loss: 0.0024264827370643616
2023-01-22 17:08:03.904268: step: 1136/530, loss: 0.0004275397805031389
2023-01-22 17:08:04.964638: step: 1140/530, loss: 0.0010892460122704506
2023-01-22 17:08:06.024086: step: 1144/530, loss: 0.00582385016605258
2023-01-22 17:08:07.103047: step: 1148/530, loss: 1.1483742127893493e-05
2023-01-22 17:08:08.161121: step: 1152/530, loss: 0.019962813705205917
2023-01-22 17:08:09.209492: step: 1156/530, loss: 3.742724220501259e-05
2023-01-22 17:08:10.266242: step: 1160/530, loss: 2.1465788449859247e-05
2023-01-22 17:08:11.324195: step: 1164/530, loss: 0.0036628860980272293
2023-01-22 17:08:12.386652: step: 1168/530, loss: 0.0022252164781093597
2023-01-22 17:08:13.442587: step: 1172/530, loss: 0.00573334563523531
2023-01-22 17:08:14.501791: step: 1176/530, loss: 0.013025280088186264
2023-01-22 17:08:15.558564: step: 1180/530, loss: 0.006561050191521645
2023-01-22 17:08:16.599982: step: 1184/530, loss: 0.0005698238383047283
2023-01-22 17:08:17.667550: step: 1188/530, loss: 0.004795927554368973
2023-01-22 17:08:18.723953: step: 1192/530, loss: 0.003382658353075385
2023-01-22 17:08:19.773320: step: 1196/530, loss: 0.0014618497807532549
2023-01-22 17:08:20.818626: step: 1200/530, loss: 0.00024218717589974403
2023-01-22 17:08:21.868263: step: 1204/530, loss: 0.01129582617431879
2023-01-22 17:08:22.927139: step: 1208/530, loss: 0.006110831629484892
2023-01-22 17:08:23.990521: step: 1212/530, loss: 0.0067613385617733
2023-01-22 17:08:25.037176: step: 1216/530, loss: 6.554491392307682e-06
2023-01-22 17:08:26.090728: step: 1220/530, loss: 0.0007601960678584874
2023-01-22 17:08:27.150229: step: 1224/530, loss: 0.0058824834413826466
2023-01-22 17:08:28.202593: step: 1228/530, loss: 0.011657321825623512
2023-01-22 17:08:29.280931: step: 1232/530, loss: 0.012146913446485996
2023-01-22 17:08:30.351897: step: 1236/530, loss: 0.002405834849923849
2023-01-22 17:08:31.413507: step: 1240/530, loss: 0.004847335163503885
2023-01-22 17:08:32.482134: step: 1244/530, loss: 0.008989602327346802
2023-01-22 17:08:33.553392: step: 1248/530, loss: 0.012629348784685135
2023-01-22 17:08:34.603942: step: 1252/530, loss: 0.0033187069930136204
2023-01-22 17:08:35.653210: step: 1256/530, loss: 0.0035006855614483356
2023-01-22 17:08:36.711340: step: 1260/530, loss: 0.003410729579627514
2023-01-22 17:08:37.763911: step: 1264/530, loss: 0.00025031305267475545
2023-01-22 17:08:38.829672: step: 1268/530, loss: 0.0013060449855402112
2023-01-22 17:08:39.897970: step: 1272/530, loss: 0.005291915498673916
2023-01-22 17:08:40.958868: step: 1276/530, loss: 0.006256693508476019
2023-01-22 17:08:42.008398: step: 1280/530, loss: 0.008116258308291435
2023-01-22 17:08:43.070667: step: 1284/530, loss: 0.0034394909162074327
2023-01-22 17:08:44.117464: step: 1288/530, loss: 0.0008718370227143168
2023-01-22 17:08:45.177096: step: 1292/530, loss: 0.0017200798029080033
2023-01-22 17:08:46.236595: step: 1296/530, loss: 0.0033651867415755987
2023-01-22 17:08:47.297763: step: 1300/530, loss: 0.00204497785307467
2023-01-22 17:08:48.367301: step: 1304/530, loss: 0.008543741889297962
2023-01-22 17:08:49.408298: step: 1308/530, loss: 0.018549108877778053
2023-01-22 17:08:50.457691: step: 1312/530, loss: 0.007454019971191883
2023-01-22 17:08:51.512483: step: 1316/530, loss: 0.007118787616491318
2023-01-22 17:08:52.571227: step: 1320/530, loss: 0.004104725085198879
2023-01-22 17:08:53.613502: step: 1324/530, loss: 0.004213666543364525
2023-01-22 17:08:54.669083: step: 1328/530, loss: 0.007506143767386675
2023-01-22 17:08:55.729556: step: 1332/530, loss: 0.005709733348339796
2023-01-22 17:08:56.784614: step: 1336/530, loss: 0.0014935473445802927
2023-01-22 17:08:57.858013: step: 1340/530, loss: 0.0021362542174756527
2023-01-22 17:08:58.906139: step: 1344/530, loss: 0.03108602575957775
2023-01-22 17:08:59.964479: step: 1348/530, loss: 0.004666692577302456
2023-01-22 17:09:01.019640: step: 1352/530, loss: 0.00016875712026376277
2023-01-22 17:09:02.127130: step: 1356/530, loss: 0.000258055777521804
2023-01-22 17:09:03.179855: step: 1360/530, loss: 0.004876892548054457
2023-01-22 17:09:04.232824: step: 1364/530, loss: 0.009992648847401142
2023-01-22 17:09:05.270405: step: 1368/530, loss: 0.013313684612512589
2023-01-22 17:09:06.337003: step: 1372/530, loss: 0.007920022122561932
2023-01-22 17:09:07.413070: step: 1376/530, loss: 0.007979034446179867
2023-01-22 17:09:08.477611: step: 1380/530, loss: 0.003216430777683854
2023-01-22 17:09:09.521220: step: 1384/530, loss: 7.377401288977126e-06
2023-01-22 17:09:10.576325: step: 1388/530, loss: 0.002688719192519784
2023-01-22 17:09:11.634503: step: 1392/530, loss: 0.0019228315213695168
2023-01-22 17:09:12.686735: step: 1396/530, loss: 0.0019534912426024675
2023-01-22 17:09:13.735937: step: 1400/530, loss: 0.0034197440836578608
2023-01-22 17:09:14.782399: step: 1404/530, loss: 0.0047003235667943954
2023-01-22 17:09:15.824421: step: 1408/530, loss: 0.005180078558623791
2023-01-22 17:09:16.897273: step: 1412/530, loss: 0.0019711009226739407
2023-01-22 17:09:17.951476: step: 1416/530, loss: 0.0009574324358254671
2023-01-22 17:09:18.997366: step: 1420/530, loss: 0.004306775517761707
2023-01-22 17:09:20.058949: step: 1424/530, loss: 0.007848543114960194
2023-01-22 17:09:21.116755: step: 1428/530, loss: 0.0049766600131988525
2023-01-22 17:09:22.187628: step: 1432/530, loss: 0.00013813500117976218
2023-01-22 17:09:23.241554: step: 1436/530, loss: 0.009219067171216011
2023-01-22 17:09:24.289409: step: 1440/530, loss: 0.007901976816356182
2023-01-22 17:09:25.362538: step: 1444/530, loss: 0.0039823222905397415
2023-01-22 17:09:26.405457: step: 1448/530, loss: 3.9467883539145987e-07
2023-01-22 17:09:27.469250: step: 1452/530, loss: 0.0038937460631132126
2023-01-22 17:09:28.534098: step: 1456/530, loss: 0.0035226172767579556
2023-01-22 17:09:29.588114: step: 1460/530, loss: 0.0019560500513762236
2023-01-22 17:09:30.640459: step: 1464/530, loss: 0.0016298429109156132
2023-01-22 17:09:31.698323: step: 1468/530, loss: 0.00813937745988369
2023-01-22 17:09:32.770189: step: 1472/530, loss: 0.003750380128622055
2023-01-22 17:09:33.821971: step: 1476/530, loss: 0.0020555732771754265
2023-01-22 17:09:34.872741: step: 1480/530, loss: 0.003399333916604519
2023-01-22 17:09:35.917419: step: 1484/530, loss: 0.0015278421342372894
2023-01-22 17:09:36.972930: step: 1488/530, loss: 4.8100246203830466e-06
2023-01-22 17:09:38.030404: step: 1492/530, loss: 0.003036718349903822
2023-01-22 17:09:39.096309: step: 1496/530, loss: 0.00015581339539494365
2023-01-22 17:09:40.160400: step: 1500/530, loss: 0.015179021283984184
2023-01-22 17:09:41.207285: step: 1504/530, loss: 0.005659155081957579
2023-01-22 17:09:42.249938: step: 1508/530, loss: 0.002290590899065137
2023-01-22 17:09:43.305755: step: 1512/530, loss: 1.9928136680391617e-05
2023-01-22 17:09:44.371416: step: 1516/530, loss: 0.006302024703472853
2023-01-22 17:09:45.436216: step: 1520/530, loss: 0.002138543175533414
2023-01-22 17:09:46.504896: step: 1524/530, loss: 0.0023551583290100098
2023-01-22 17:09:47.570003: step: 1528/530, loss: 0.0051754252053797245
2023-01-22 17:09:48.623281: step: 1532/530, loss: 0.019789498299360275
2023-01-22 17:09:49.695758: step: 1536/530, loss: 0.0015414366498589516
2023-01-22 17:09:50.752758: step: 1540/530, loss: 0.0195549838244915
2023-01-22 17:09:51.809479: step: 1544/530, loss: 0.0013208319433033466
2023-01-22 17:09:52.866069: step: 1548/530, loss: 4.4737938878824934e-05
2023-01-22 17:09:53.933008: step: 1552/530, loss: 0.0003518607118166983
2023-01-22 17:09:54.992189: step: 1556/530, loss: 7.921305041236337e-06
2023-01-22 17:09:56.050265: step: 1560/530, loss: 0.0020726770162582397
2023-01-22 17:09:57.100579: step: 1564/530, loss: 2.9866330805816688e-05
2023-01-22 17:09:58.166476: step: 1568/530, loss: 0.008643691428005695
2023-01-22 17:09:59.237742: step: 1572/530, loss: 0.005970974452793598
2023-01-22 17:10:00.303370: step: 1576/530, loss: 0.00368315982632339
2023-01-22 17:10:01.358750: step: 1580/530, loss: 2.786415279842913e-05
2023-01-22 17:10:02.419486: step: 1584/530, loss: 0.0016321302391588688
2023-01-22 17:10:03.493511: step: 1588/530, loss: 0.006393588148057461
2023-01-22 17:10:04.551529: step: 1592/530, loss: 0.0043124244548380375
2023-01-22 17:10:05.601238: step: 1596/530, loss: 0.005268516950309277
2023-01-22 17:10:06.660616: step: 1600/530, loss: 0.0024041703436523676
2023-01-22 17:10:07.703980: step: 1604/530, loss: 0.0007791827665641904
2023-01-22 17:10:08.752459: step: 1608/530, loss: 0.0031291747000068426
2023-01-22 17:10:09.817491: step: 1612/530, loss: 0.0008868605364114046
2023-01-22 17:10:10.890065: step: 1616/530, loss: 0.0037790548522025347
2023-01-22 17:10:11.959573: step: 1620/530, loss: 0.0010254508815705776
2023-01-22 17:10:13.010626: step: 1624/530, loss: 8.481103577651083e-05
2023-01-22 17:10:14.067206: step: 1628/530, loss: 0.0008550605271011591
2023-01-22 17:10:15.136018: step: 1632/530, loss: 0.0038089745212346315
2023-01-22 17:10:16.195354: step: 1636/530, loss: 0.0059053897857666016
2023-01-22 17:10:17.248913: step: 1640/530, loss: 0.0004412377020344138
2023-01-22 17:10:18.313992: step: 1644/530, loss: 0.008484939113259315
2023-01-22 17:10:19.377591: step: 1648/530, loss: 0.0021386367734521627
2023-01-22 17:10:20.445949: step: 1652/530, loss: 0.0016081653302535415
2023-01-22 17:10:21.513157: step: 1656/530, loss: 0.006513381842523813
2023-01-22 17:10:22.576829: step: 1660/530, loss: 0.001056722947396338
2023-01-22 17:10:23.638631: step: 1664/530, loss: 0.028058689087629318
2023-01-22 17:10:24.699048: step: 1668/530, loss: 0.0004959757789038122
2023-01-22 17:10:25.757911: step: 1672/530, loss: 0.003795412601903081
2023-01-22 17:10:26.840019: step: 1676/530, loss: 0.009061677381396294
2023-01-22 17:10:27.930600: step: 1680/530, loss: 0.0026089122984558344
2023-01-22 17:10:28.987034: step: 1684/530, loss: 0.0057379938662052155
2023-01-22 17:10:30.039769: step: 1688/530, loss: 0.008395579643547535
2023-01-22 17:10:31.089587: step: 1692/530, loss: 0.0003318342787679285
2023-01-22 17:10:32.152844: step: 1696/530, loss: 0.0010075566824525595
2023-01-22 17:10:33.208960: step: 1700/530, loss: 0.008269023150205612
2023-01-22 17:10:34.271364: step: 1704/530, loss: 0.004361629486083984
2023-01-22 17:10:35.345101: step: 1708/530, loss: 0.007040684577077627
2023-01-22 17:10:36.384668: step: 1712/530, loss: 0.00014054319763090461
2023-01-22 17:10:37.431397: step: 1716/530, loss: 0.00010745009785750881
2023-01-22 17:10:38.480553: step: 1720/530, loss: 0.0018832228379324079
2023-01-22 17:10:39.552403: step: 1724/530, loss: 0.0012280558003112674
2023-01-22 17:10:40.621735: step: 1728/530, loss: 0.001697151456028223
2023-01-22 17:10:41.675176: step: 1732/530, loss: 0.0002664512721821666
2023-01-22 17:10:42.739399: step: 1736/530, loss: 0.003983442671597004
2023-01-22 17:10:43.799758: step: 1740/530, loss: 0.0023063533008098602
2023-01-22 17:10:44.854048: step: 1744/530, loss: 0.003796427743509412
2023-01-22 17:10:45.916801: step: 1748/530, loss: 0.00020887312712147832
2023-01-22 17:10:46.971827: step: 1752/530, loss: 0.0011428105644881725
2023-01-22 17:10:48.039112: step: 1756/530, loss: 0.00014010202721692622
2023-01-22 17:10:49.091964: step: 1760/530, loss: 0.0007599526434205472
2023-01-22 17:10:50.154628: step: 1764/530, loss: 0.0029602961149066687
2023-01-22 17:10:51.191318: step: 1768/530, loss: 0.00019839184824377298
2023-01-22 17:10:52.260144: step: 1772/530, loss: 0.006114319432526827
2023-01-22 17:10:53.324907: step: 1776/530, loss: 0.003739685984328389
2023-01-22 17:10:54.368896: step: 1780/530, loss: 0.0027159047313034534
2023-01-22 17:10:55.413010: step: 1784/530, loss: 9.57014417508617e-05
2023-01-22 17:10:56.464661: step: 1788/530, loss: 0.010722307488322258
2023-01-22 17:10:57.532392: step: 1792/530, loss: 0.005990995094180107
2023-01-22 17:10:58.607943: step: 1796/530, loss: 0.0002609161310829222
2023-01-22 17:10:59.660689: step: 1800/530, loss: 0.006569515448063612
2023-01-22 17:11:00.720544: step: 1804/530, loss: 0.0033165786880999804
2023-01-22 17:11:01.776339: step: 1808/530, loss: 0.0032061832025647163
2023-01-22 17:11:02.834780: step: 1812/530, loss: 0.014142590574920177
2023-01-22 17:11:03.892351: step: 1816/530, loss: 0.0018370056059211493
2023-01-22 17:11:04.930846: step: 1820/530, loss: 0.0022949185222387314
2023-01-22 17:11:05.980157: step: 1824/530, loss: 0.003224811516702175
2023-01-22 17:11:07.023964: step: 1828/530, loss: 0.006816777400672436
2023-01-22 17:11:08.058000: step: 1832/530, loss: 0.004744057077914476
2023-01-22 17:11:09.102798: step: 1836/530, loss: 0.0011790888383984566
2023-01-22 17:11:10.181318: step: 1840/530, loss: 7.049964915495366e-05
2023-01-22 17:11:11.249276: step: 1844/530, loss: 0.011590033769607544
2023-01-22 17:11:12.297049: step: 1848/530, loss: 0.002682075835764408
2023-01-22 17:11:13.361688: step: 1852/530, loss: 0.004180378746241331
2023-01-22 17:11:14.419697: step: 1856/530, loss: 0.0019671451300382614
2023-01-22 17:11:15.478441: step: 1860/530, loss: 0.0045006959699094296
2023-01-22 17:11:16.539913: step: 1864/530, loss: 3.1965690141078085e-05
2023-01-22 17:11:17.612146: step: 1868/530, loss: 0.003039903938770294
2023-01-22 17:11:18.679377: step: 1872/530, loss: 0.012033623643219471
2023-01-22 17:11:19.716528: step: 1876/530, loss: 0.0006262253155000508
2023-01-22 17:11:20.800832: step: 1880/530, loss: 0.002116111572831869
2023-01-22 17:11:21.845298: step: 1884/530, loss: 0.006007688120007515
2023-01-22 17:11:22.903445: step: 1888/530, loss: 0.0028912299312651157
2023-01-22 17:11:23.965630: step: 1892/530, loss: 0.0011746311793103814
2023-01-22 17:11:25.017924: step: 1896/530, loss: 0.0
2023-01-22 17:11:26.071838: step: 1900/530, loss: 0.0005869127344340086
2023-01-22 17:11:27.129649: step: 1904/530, loss: 0.0012781622353941202
2023-01-22 17:11:28.184335: step: 1908/530, loss: 0.0012501388555392623
2023-01-22 17:11:29.241068: step: 1912/530, loss: 0.0043746731244027615
2023-01-22 17:11:30.306853: step: 1916/530, loss: 0.00043803712469525635
2023-01-22 17:11:31.356958: step: 1920/530, loss: 0.0075974599458277225
2023-01-22 17:11:32.418558: step: 1924/530, loss: 0.010968511924147606
2023-01-22 17:11:33.482282: step: 1928/530, loss: 0.004631384275853634
2023-01-22 17:11:34.537387: step: 1932/530, loss: 0.009578884579241276
2023-01-22 17:11:35.582511: step: 1936/530, loss: 0.005059940740466118
2023-01-22 17:11:36.648104: step: 1940/530, loss: 0.00046195185859687626
2023-01-22 17:11:37.695788: step: 1944/530, loss: 0.002232220722362399
2023-01-22 17:11:38.782161: step: 1948/530, loss: 0.008636283688247204
2023-01-22 17:11:39.838991: step: 1952/530, loss: 0.0013060978380963206
2023-01-22 17:11:40.891234: step: 1956/530, loss: 0.0018417044775560498
2023-01-22 17:11:41.964749: step: 1960/530, loss: 0.0022587471175938845
2023-01-22 17:11:43.045659: step: 1964/530, loss: 0.0011911691399291158
2023-01-22 17:11:44.120833: step: 1968/530, loss: 0.0004273304366506636
2023-01-22 17:11:45.179105: step: 1972/530, loss: 0.001487808651290834
2023-01-22 17:11:46.241192: step: 1976/530, loss: 0.0051035829819738865
2023-01-22 17:11:47.291389: step: 1980/530, loss: 0.00016551661246921867
2023-01-22 17:11:48.342051: step: 1984/530, loss: 0.002814291976392269
2023-01-22 17:11:49.397045: step: 1988/530, loss: 0.0002734197478275746
2023-01-22 17:11:50.462473: step: 1992/530, loss: 0.0007374505512416363
2023-01-22 17:11:51.539615: step: 1996/530, loss: 0.012616774998605251
2023-01-22 17:11:52.590380: step: 2000/530, loss: 0.0017067051958292723
2023-01-22 17:11:53.638284: step: 2004/530, loss: 0.00023139607219491154
2023-01-22 17:11:54.698354: step: 2008/530, loss: 0.012642091140151024
2023-01-22 17:11:55.757280: step: 2012/530, loss: 0.0031683321576565504
2023-01-22 17:11:56.830607: step: 2016/530, loss: 0.0006153160938993096
2023-01-22 17:11:57.902540: step: 2020/530, loss: 0.014677880331873894
2023-01-22 17:11:58.958145: step: 2024/530, loss: 0.00584376510232687
2023-01-22 17:12:00.013948: step: 2028/530, loss: 0.0015228864504024386
2023-01-22 17:12:01.076404: step: 2032/530, loss: 0.0009278134675696492
2023-01-22 17:12:02.153800: step: 2036/530, loss: 0.0002502513234503567
2023-01-22 17:12:03.230393: step: 2040/530, loss: 0.0019562600646167994
2023-01-22 17:12:04.298152: step: 2044/530, loss: 0.0008782261284068227
2023-01-22 17:12:05.366384: step: 2048/530, loss: 1.352880644844845e-05
2023-01-22 17:12:06.414456: step: 2052/530, loss: 9.31391041376628e-05
2023-01-22 17:12:07.471070: step: 2056/530, loss: 0.00023792771389707923
2023-01-22 17:12:08.527188: step: 2060/530, loss: 1.8051039660349488e-05
2023-01-22 17:12:09.579139: step: 2064/530, loss: 0.009793025441467762
2023-01-22 17:12:10.626483: step: 2068/530, loss: 0.005851043853908777
2023-01-22 17:12:11.691846: step: 2072/530, loss: 0.0022626316640526056
2023-01-22 17:12:12.738796: step: 2076/530, loss: 0.002183223608881235
2023-01-22 17:12:13.802873: step: 2080/530, loss: 0.006486327853053808
2023-01-22 17:12:14.857251: step: 2084/530, loss: 0.0006909652147442102
2023-01-22 17:12:15.924020: step: 2088/530, loss: 2.8288905014051124e-06
2023-01-22 17:12:16.970832: step: 2092/530, loss: 0.0009959451854228973
2023-01-22 17:12:18.046148: step: 2096/530, loss: 0.006946542765945196
2023-01-22 17:12:19.106492: step: 2100/530, loss: 0.0064200120978057384
2023-01-22 17:12:20.168733: step: 2104/530, loss: 1.0432649105496239e-05
2023-01-22 17:12:21.219253: step: 2108/530, loss: 0.0073416028171777725
2023-01-22 17:12:22.255970: step: 2112/530, loss: 0.0038483100943267345
2023-01-22 17:12:23.307494: step: 2116/530, loss: 0.006809014827013016
2023-01-22 17:12:24.362812: step: 2120/530, loss: 0.001411612844094634
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3494918915170401, 'r': 0.23188892543279016, 'f1': 0.27879591761058486}, 'combined': 0.18490091945157958, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32213082688189754, 'r': 0.2849149548368298, 'f1': 0.30238210282180134}, 'combined': 0.20158806854786754, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4014872550013789, 'r': 0.320217343521861, 'f1': 0.3562764669020898}, 'combined': 0.23251727313610068, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3250647295742233, 'r': 0.3411020786613766, 'f1': 0.33289036195286204}, 'combined': 0.24528763512316148, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.36198396711016007, 'r': 0.3318969880256792, 'f1': 0.3462881853384458}, 'combined': 0.2296626306907827, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:14:49.773064: step: 4/530, loss: 0.002581825014203787
2023-01-22 17:14:50.832394: step: 8/530, loss: 0.006619778927415609
2023-01-22 17:14:51.873153: step: 12/530, loss: 0.0005360495997592807
2023-01-22 17:14:52.945023: step: 16/530, loss: 0.0016956243198364973
2023-01-22 17:14:54.016504: step: 20/530, loss: 0.006960383616387844
2023-01-22 17:14:55.068615: step: 24/530, loss: 0.0015290328301489353
2023-01-22 17:14:56.158398: step: 28/530, loss: 0.003123462898656726
2023-01-22 17:14:57.210976: step: 32/530, loss: 0.0022524131927639246
2023-01-22 17:14:58.270627: step: 36/530, loss: 0.00020455248886719346
2023-01-22 17:14:59.331486: step: 40/530, loss: 0.0036411837209016085
2023-01-22 17:15:00.384111: step: 44/530, loss: 3.546790321706794e-05
2023-01-22 17:15:01.451792: step: 48/530, loss: 0.001803272869437933
2023-01-22 17:15:02.506688: step: 52/530, loss: 0.0009551815455779433
2023-01-22 17:15:03.569763: step: 56/530, loss: 0.00025073063443414867
2023-01-22 17:15:04.622784: step: 60/530, loss: 0.004440452437847853
2023-01-22 17:15:05.690867: step: 64/530, loss: 0.013381106778979301
2023-01-22 17:15:06.765097: step: 68/530, loss: 0.0010746110929176211
2023-01-22 17:15:07.828797: step: 72/530, loss: 0.003233750117942691
2023-01-22 17:15:08.893657: step: 76/530, loss: 0.001029081642627716
2023-01-22 17:15:09.936596: step: 80/530, loss: 0.0025157034397125244
2023-01-22 17:15:11.002732: step: 84/530, loss: 0.005530400667339563
2023-01-22 17:15:12.058761: step: 88/530, loss: 0.01063416339457035
2023-01-22 17:15:13.123865: step: 92/530, loss: 0.00411126296967268
2023-01-22 17:15:14.202322: step: 96/530, loss: 0.0006830185302533209
2023-01-22 17:15:15.268800: step: 100/530, loss: 0.0022188322618603706
2023-01-22 17:15:16.336000: step: 104/530, loss: 1.4419346371141728e-05
2023-01-22 17:15:17.393192: step: 108/530, loss: 0.0030531820375472307
2023-01-22 17:15:18.457553: step: 112/530, loss: 4.8055200750241056e-05
2023-01-22 17:15:19.514216: step: 116/530, loss: 0.0029897962231189013
2023-01-22 17:15:20.577892: step: 120/530, loss: 7.18240044079721e-05
2023-01-22 17:15:21.633803: step: 124/530, loss: 0.00024895212845876813
2023-01-22 17:15:22.703468: step: 128/530, loss: 0.001364733325317502
2023-01-22 17:15:23.762365: step: 132/530, loss: 0.03680232912302017
2023-01-22 17:15:24.827113: step: 136/530, loss: 7.626634032931179e-05
2023-01-22 17:15:25.891795: step: 140/530, loss: 0.0018529273802414536
2023-01-22 17:15:26.946676: step: 144/530, loss: 0.004630149807780981
2023-01-22 17:15:28.006940: step: 148/530, loss: 0.0023875257465988398
2023-01-22 17:15:29.083307: step: 152/530, loss: 0.0001668501936364919
2023-01-22 17:15:30.129469: step: 156/530, loss: 0.002660535741597414
2023-01-22 17:15:31.194121: step: 160/530, loss: 0.006991139613091946
2023-01-22 17:15:32.294622: step: 164/530, loss: 0.008228965103626251
2023-01-22 17:15:33.351332: step: 168/530, loss: 9.058923023985699e-05
2023-01-22 17:15:34.420857: step: 172/530, loss: 0.0020049859303981066
2023-01-22 17:15:35.491603: step: 176/530, loss: 0.004972059745341539
2023-01-22 17:15:36.539387: step: 180/530, loss: 0.016794217750430107
2023-01-22 17:15:37.588395: step: 184/530, loss: 0.004986226558685303
2023-01-22 17:15:38.647465: step: 188/530, loss: 0.0055866544134914875
2023-01-22 17:15:39.698274: step: 192/530, loss: 0.0005941632553003728
2023-01-22 17:15:40.757983: step: 196/530, loss: 0.012751948088407516
2023-01-22 17:15:41.824190: step: 200/530, loss: 0.0026953136548399925
2023-01-22 17:15:42.882877: step: 204/530, loss: 0.0025713969953358173
2023-01-22 17:15:43.946526: step: 208/530, loss: 0.001725605921819806
2023-01-22 17:15:44.999592: step: 212/530, loss: 0.0018055252730846405
2023-01-22 17:15:46.067727: step: 216/530, loss: 0.00407212320715189
2023-01-22 17:15:47.139670: step: 220/530, loss: 0.0002567624324001372
2023-01-22 17:15:48.196351: step: 224/530, loss: 0.00971232634037733
2023-01-22 17:15:49.251259: step: 228/530, loss: 0.0003279975207988173
2023-01-22 17:15:50.307356: step: 232/530, loss: 0.0010163073893636465
2023-01-22 17:15:51.370232: step: 236/530, loss: 0.00034463824704289436
2023-01-22 17:15:52.426723: step: 240/530, loss: 0.006095506716519594
2023-01-22 17:15:53.528094: step: 244/530, loss: 0.0018111647805199027
2023-01-22 17:15:54.591121: step: 248/530, loss: 0.0017166829202324152
2023-01-22 17:15:55.657143: step: 252/530, loss: 0.0029127250891178846
2023-01-22 17:15:56.699662: step: 256/530, loss: 6.0145110182929784e-05
2023-01-22 17:15:57.754480: step: 260/530, loss: 0.0018024436431005597
2023-01-22 17:15:58.825544: step: 264/530, loss: 2.5659552193246782e-05
2023-01-22 17:15:59.875557: step: 268/530, loss: 0.002872179029509425
2023-01-22 17:16:00.924638: step: 272/530, loss: 0.0025366514455527067
2023-01-22 17:16:01.998391: step: 276/530, loss: 0.00363520928658545
2023-01-22 17:16:03.051032: step: 280/530, loss: 0.0010392050025984645
2023-01-22 17:16:04.109444: step: 284/530, loss: 0.003522642655298114
2023-01-22 17:16:05.169579: step: 288/530, loss: 0.00032669026404619217
2023-01-22 17:16:06.228418: step: 292/530, loss: 0.0007757392595522106
2023-01-22 17:16:07.280138: step: 296/530, loss: 9.982248593587428e-05
2023-01-22 17:16:08.341420: step: 300/530, loss: 0.0011167319025844336
2023-01-22 17:16:09.404306: step: 304/530, loss: 0.003380789887160063
2023-01-22 17:16:10.468817: step: 308/530, loss: 0.002762816147878766
2023-01-22 17:16:11.520388: step: 312/530, loss: 5.8911522501148283e-05
2023-01-22 17:16:12.573367: step: 316/530, loss: 0.005111285950988531
2023-01-22 17:16:13.629069: step: 320/530, loss: 1.0968845344905276e-05
2023-01-22 17:16:14.680817: step: 324/530, loss: 0.0012409324990585446
2023-01-22 17:16:15.746638: step: 328/530, loss: 0.00444065872579813
2023-01-22 17:16:16.812504: step: 332/530, loss: 0.0071311285719275475
2023-01-22 17:16:17.876815: step: 336/530, loss: 0.002979936311021447
2023-01-22 17:16:18.937956: step: 340/530, loss: 4.4204705773154274e-05
2023-01-22 17:16:20.016525: step: 344/530, loss: 0.005602729506790638
2023-01-22 17:16:21.077984: step: 348/530, loss: 0.010418785735964775
2023-01-22 17:16:22.144158: step: 352/530, loss: 0.007625289261341095
2023-01-22 17:16:23.207110: step: 356/530, loss: 0.005736652296036482
2023-01-22 17:16:24.264795: step: 360/530, loss: 9.349539027425635e-07
2023-01-22 17:16:25.308081: step: 364/530, loss: 0.0021775986533612013
2023-01-22 17:16:26.372969: step: 368/530, loss: 0.003915868699550629
2023-01-22 17:16:27.434258: step: 372/530, loss: 0.04896125942468643
2023-01-22 17:16:28.510644: step: 376/530, loss: 0.0001042205112753436
2023-01-22 17:16:29.579190: step: 380/530, loss: 0.0017008360009640455
2023-01-22 17:16:30.641050: step: 384/530, loss: 0.0029940218664705753
2023-01-22 17:16:31.725447: step: 388/530, loss: 0.0010300650028511882
2023-01-22 17:16:32.820781: step: 392/530, loss: 0.00015870867355260998
2023-01-22 17:16:33.877511: step: 396/530, loss: 0.006296739913523197
2023-01-22 17:16:34.949320: step: 400/530, loss: 0.003334162523970008
2023-01-22 17:16:36.012989: step: 404/530, loss: 3.72045069525484e-05
2023-01-22 17:16:37.077767: step: 408/530, loss: 0.008457803167402744
2023-01-22 17:16:38.141029: step: 412/530, loss: 0.007899478077888489
2023-01-22 17:16:39.194685: step: 416/530, loss: 0.0014235851122066379
2023-01-22 17:16:40.262480: step: 420/530, loss: 0.003728689858689904
2023-01-22 17:16:41.322896: step: 424/530, loss: 0.0022654810454696417
2023-01-22 17:16:42.401909: step: 428/530, loss: 0.02324497140944004
2023-01-22 17:16:43.463194: step: 432/530, loss: 0.0020368474069982767
2023-01-22 17:16:44.548629: step: 436/530, loss: 0.00020153888908680528
2023-01-22 17:16:45.618993: step: 440/530, loss: 4.303013702156022e-05
2023-01-22 17:16:46.685776: step: 444/530, loss: 0.0014824257232248783
2023-01-22 17:16:47.747188: step: 448/530, loss: 0.015982531011104584
2023-01-22 17:16:48.795547: step: 452/530, loss: 0.00019782452727667987
2023-01-22 17:16:49.850665: step: 456/530, loss: 0.0004076980403624475
2023-01-22 17:16:50.883788: step: 460/530, loss: 0.00018251534493174404
2023-01-22 17:16:51.948741: step: 464/530, loss: 0.01019479800015688
2023-01-22 17:16:53.009226: step: 468/530, loss: 0.0024552149698138237
2023-01-22 17:16:54.071709: step: 472/530, loss: 9.550879622111097e-05
2023-01-22 17:16:55.124818: step: 476/530, loss: 0.018162155523896217
2023-01-22 17:16:56.204708: step: 480/530, loss: 0.0061699082143604755
2023-01-22 17:16:57.259979: step: 484/530, loss: 0.00011448593431850895
2023-01-22 17:16:58.336757: step: 488/530, loss: 0.006930534727871418
2023-01-22 17:16:59.408574: step: 492/530, loss: 0.0024129217490553856
2023-01-22 17:17:00.477693: step: 496/530, loss: 0.0021330404561012983
2023-01-22 17:17:01.532339: step: 500/530, loss: 0.0
2023-01-22 17:17:02.577593: step: 504/530, loss: 2.8366664537315955e-06
2023-01-22 17:17:03.624918: step: 508/530, loss: 0.0035516696516424417
2023-01-22 17:17:04.666365: step: 512/530, loss: 0.0017698646988719702
2023-01-22 17:17:05.746304: step: 516/530, loss: 0.00905707385390997
2023-01-22 17:17:06.802196: step: 520/530, loss: 0.0007563039544038475
2023-01-22 17:17:07.861764: step: 524/530, loss: 0.003938170149922371
2023-01-22 17:17:08.905862: step: 528/530, loss: 0.0
2023-01-22 17:17:09.958440: step: 532/530, loss: 0.005788673646748066
2023-01-22 17:17:11.045813: step: 536/530, loss: 0.0055591338314116
2023-01-22 17:17:12.111307: step: 540/530, loss: 0.025313809514045715
2023-01-22 17:17:13.167226: step: 544/530, loss: 0.0012019500136375427
2023-01-22 17:17:14.211762: step: 548/530, loss: 0.0026905620470643044
2023-01-22 17:17:15.288123: step: 552/530, loss: 0.0035372653510421515
2023-01-22 17:17:16.344441: step: 556/530, loss: 0.0058954074047505856
2023-01-22 17:17:17.402160: step: 560/530, loss: 0.001668637036345899
2023-01-22 17:17:18.450320: step: 564/530, loss: 0.0048230416141450405
2023-01-22 17:17:19.510823: step: 568/530, loss: 0.0004215730878058821
2023-01-22 17:17:20.571031: step: 572/530, loss: 0.006306564435362816
2023-01-22 17:17:21.635772: step: 576/530, loss: 0.007425761315971613
2023-01-22 17:17:22.678911: step: 580/530, loss: 0.0012103727785870433
2023-01-22 17:17:23.725837: step: 584/530, loss: 0.013819319196045399
2023-01-22 17:17:24.806662: step: 588/530, loss: 0.0032062337268143892
2023-01-22 17:17:25.872001: step: 592/530, loss: 0.002507188357412815
2023-01-22 17:17:26.939488: step: 596/530, loss: 0.00642424076795578
2023-01-22 17:17:28.008774: step: 600/530, loss: 0.0026239582803100348
2023-01-22 17:17:29.082319: step: 604/530, loss: 0.002418368589133024
2023-01-22 17:17:30.151919: step: 608/530, loss: 0.0023264652118086815
2023-01-22 17:17:31.231434: step: 612/530, loss: 0.009183662943542004
2023-01-22 17:17:32.321487: step: 616/530, loss: 0.008495069108903408
2023-01-22 17:17:33.376856: step: 620/530, loss: 0.007957619614899158
2023-01-22 17:17:34.424031: step: 624/530, loss: 0.0016105532413348556
2023-01-22 17:17:35.480917: step: 628/530, loss: 0.005336131900548935
2023-01-22 17:17:36.554952: step: 632/530, loss: 0.0008452058536931872
2023-01-22 17:17:37.609836: step: 636/530, loss: 0.0021655745804309845
2023-01-22 17:17:38.681449: step: 640/530, loss: 2.5903731511789374e-05
2023-01-22 17:17:39.743442: step: 644/530, loss: 0.004575239960104227
2023-01-22 17:17:40.806534: step: 648/530, loss: 0.011776391416788101
2023-01-22 17:17:41.869816: step: 652/530, loss: 0.002930695889517665
2023-01-22 17:17:42.919956: step: 656/530, loss: 0.00041023746598511934
2023-01-22 17:17:43.974588: step: 660/530, loss: 0.0011043745325878263
2023-01-22 17:17:45.033730: step: 664/530, loss: 0.0008587486809119582
2023-01-22 17:17:46.098693: step: 668/530, loss: 0.0069945501163601875
2023-01-22 17:17:47.153004: step: 672/530, loss: 0.0027160656172782183
2023-01-22 17:17:48.217175: step: 676/530, loss: 0.0002792657760437578
2023-01-22 17:17:49.289560: step: 680/530, loss: 0.004578132648020983
2023-01-22 17:17:50.344798: step: 684/530, loss: 4.543236627796432e-06
2023-01-22 17:17:51.399893: step: 688/530, loss: 0.0037390990182757378
2023-01-22 17:17:52.451849: step: 692/530, loss: 6.106190994614735e-05
2023-01-22 17:17:53.504850: step: 696/530, loss: 0.0026797375176101923
2023-01-22 17:17:54.575948: step: 700/530, loss: 0.0033157041762024164
2023-01-22 17:17:55.619718: step: 704/530, loss: 0.004262496251612902
2023-01-22 17:17:56.689648: step: 708/530, loss: 0.05321928858757019
2023-01-22 17:17:57.736854: step: 712/530, loss: 0.004236577078700066
2023-01-22 17:17:58.797275: step: 716/530, loss: 0.0007178787491284311
2023-01-22 17:17:59.843750: step: 720/530, loss: 0.004924480337649584
2023-01-22 17:18:00.883820: step: 724/530, loss: 0.004528968129307032
2023-01-22 17:18:01.932466: step: 728/530, loss: 0.0017166959587484598
2023-01-22 17:18:02.983732: step: 732/530, loss: 0.002583642490208149
2023-01-22 17:18:04.048047: step: 736/530, loss: 0.0006176792667247355
2023-01-22 17:18:05.114490: step: 740/530, loss: 0.002775475149974227
2023-01-22 17:18:06.182556: step: 744/530, loss: 0.006214153952896595
2023-01-22 17:18:07.237285: step: 748/530, loss: 0.00022231538605410606
2023-01-22 17:18:08.280391: step: 752/530, loss: 0.00011115198867628351
2023-01-22 17:18:09.325099: step: 756/530, loss: 0.0014645750634372234
2023-01-22 17:18:10.391647: step: 760/530, loss: 0.0009270327282138169
2023-01-22 17:18:11.471517: step: 764/530, loss: 0.0028734307270497084
2023-01-22 17:18:12.521343: step: 768/530, loss: 0.01239060889929533
2023-01-22 17:18:13.568999: step: 772/530, loss: 0.0021370186004787683
2023-01-22 17:18:14.627137: step: 776/530, loss: 0.0018930728547275066
2023-01-22 17:18:15.683843: step: 780/530, loss: 0.009109108708798885
2023-01-22 17:18:16.738634: step: 784/530, loss: 0.0015687990235164762
2023-01-22 17:18:17.792497: step: 788/530, loss: 0.0
2023-01-22 17:18:18.847618: step: 792/530, loss: 0.011761723086237907
2023-01-22 17:18:19.900662: step: 796/530, loss: 0.0003380372072570026
2023-01-22 17:18:20.956967: step: 800/530, loss: 0.008242730051279068
2023-01-22 17:18:22.011905: step: 804/530, loss: 0.0008853185572661459
2023-01-22 17:18:23.062871: step: 808/530, loss: 0.0004365322820376605
2023-01-22 17:18:24.113111: step: 812/530, loss: 0.0004911092692054808
2023-01-22 17:18:25.142299: step: 816/530, loss: 0.0009347404120489955
2023-01-22 17:18:26.228074: step: 820/530, loss: 0.0013178896624594927
2023-01-22 17:18:27.287804: step: 824/530, loss: 0.0029908129945397377
2023-01-22 17:18:28.355563: step: 828/530, loss: 0.002864066045731306
2023-01-22 17:18:29.435596: step: 832/530, loss: 0.009295692667365074
2023-01-22 17:18:30.483188: step: 836/530, loss: 0.0021121858153492212
2023-01-22 17:18:31.524806: step: 840/530, loss: 0.0006936705904081464
2023-01-22 17:18:32.571377: step: 844/530, loss: 0.01071300357580185
2023-01-22 17:18:33.629003: step: 848/530, loss: 0.002960806479677558
2023-01-22 17:18:34.677160: step: 852/530, loss: 0.005278423428535461
2023-01-22 17:18:35.721681: step: 856/530, loss: 0.00425961846485734
2023-01-22 17:18:36.774891: step: 860/530, loss: 0.0057912892661988735
2023-01-22 17:18:37.821547: step: 864/530, loss: 0.0004971798625774682
2023-01-22 17:18:38.885281: step: 868/530, loss: 0.0035598990507423878
2023-01-22 17:18:39.929561: step: 872/530, loss: 0.0023684045299887657
2023-01-22 17:18:40.981392: step: 876/530, loss: 0.0002959244011435658
2023-01-22 17:18:42.037652: step: 880/530, loss: 0.0027957954443991184
2023-01-22 17:18:43.087755: step: 884/530, loss: 0.012473799288272858
2023-01-22 17:18:44.159843: step: 888/530, loss: 0.00181030691601336
2023-01-22 17:18:45.225595: step: 892/530, loss: 0.00269837467931211
2023-01-22 17:18:46.290307: step: 896/530, loss: 0.008018838241696358
2023-01-22 17:18:47.327365: step: 900/530, loss: 1.3784369002678432e-05
2023-01-22 17:18:48.376065: step: 904/530, loss: 0.009204037487506866
2023-01-22 17:18:49.416875: step: 908/530, loss: 7.278906559804454e-05
2023-01-22 17:18:50.456522: step: 912/530, loss: 0.0007557955104857683
2023-01-22 17:18:51.540511: step: 916/530, loss: 0.004523287061601877
2023-01-22 17:18:52.586504: step: 920/530, loss: 0.004014754667878151
2023-01-22 17:18:53.659785: step: 924/530, loss: 0.003916308283805847
2023-01-22 17:18:54.716855: step: 928/530, loss: 0.000837705738376826
2023-01-22 17:18:55.771039: step: 932/530, loss: 0.0013259451370686293
2023-01-22 17:18:56.823130: step: 936/530, loss: 0.00012868944031652063
2023-01-22 17:18:57.877734: step: 940/530, loss: 0.0040209353901445866
2023-01-22 17:18:58.946832: step: 944/530, loss: 0.0002446983999107033
2023-01-22 17:19:00.014850: step: 948/530, loss: 0.001639649854041636
2023-01-22 17:19:01.081484: step: 952/530, loss: 0.011721325106918812
2023-01-22 17:19:02.153627: step: 956/530, loss: 0.0011594862444326282
2023-01-22 17:19:03.214534: step: 960/530, loss: 0.0006356053636409342
2023-01-22 17:19:04.266552: step: 964/530, loss: 0.009116455912590027
2023-01-22 17:19:05.334695: step: 968/530, loss: 0.004880056716501713
2023-01-22 17:19:06.382306: step: 972/530, loss: 0.004856486339122057
2023-01-22 17:19:07.432001: step: 976/530, loss: 0.010619249194860458
2023-01-22 17:19:08.483911: step: 980/530, loss: 0.005518024787306786
2023-01-22 17:19:09.532492: step: 984/530, loss: 0.02494860626757145
2023-01-22 17:19:10.606653: step: 988/530, loss: 0.0003843820304609835
2023-01-22 17:19:11.655101: step: 992/530, loss: 5.3429052059073e-05
2023-01-22 17:19:12.709098: step: 996/530, loss: 0.010356186889111996
2023-01-22 17:19:13.762688: step: 1000/530, loss: 0.0023228719364851713
2023-01-22 17:19:14.818562: step: 1004/530, loss: 0.013973345048725605
2023-01-22 17:19:15.891051: step: 1008/530, loss: 0.0019040392944589257
2023-01-22 17:19:16.946634: step: 1012/530, loss: 0.0027658697217702866
2023-01-22 17:19:18.000152: step: 1016/530, loss: 0.0001303055469179526
2023-01-22 17:19:19.061986: step: 1020/530, loss: 0.00109787005931139
2023-01-22 17:19:20.127007: step: 1024/530, loss: 0.02494070678949356
2023-01-22 17:19:21.183569: step: 1028/530, loss: 0.002307172631844878
2023-01-22 17:19:22.245372: step: 1032/530, loss: 0.001349496771581471
2023-01-22 17:19:23.293920: step: 1036/530, loss: 0.0002724653750192374
2023-01-22 17:19:24.350026: step: 1040/530, loss: 0.011107711121439934
2023-01-22 17:19:25.413628: step: 1044/530, loss: 0.005380466114729643
2023-01-22 17:19:26.477021: step: 1048/530, loss: 0.006467881612479687
2023-01-22 17:19:27.549284: step: 1052/530, loss: 0.0008323421352542937
2023-01-22 17:19:28.623359: step: 1056/530, loss: 0.0030333863105624914
2023-01-22 17:19:29.681851: step: 1060/530, loss: 1.357122619083384e-05
2023-01-22 17:19:30.744867: step: 1064/530, loss: 0.005428476259112358
2023-01-22 17:19:31.802541: step: 1068/530, loss: 6.146852683741599e-06
2023-01-22 17:19:32.891446: step: 1072/530, loss: 8.115013770293444e-05
2023-01-22 17:19:33.952640: step: 1076/530, loss: 0.001163430861197412
2023-01-22 17:19:35.028421: step: 1080/530, loss: 3.33540556312073e-05
2023-01-22 17:19:36.090305: step: 1084/530, loss: 0.004403300583362579
2023-01-22 17:19:37.135671: step: 1088/530, loss: 0.002152044326066971
2023-01-22 17:19:38.186727: step: 1092/530, loss: 0.0005421810783445835
2023-01-22 17:19:39.248596: step: 1096/530, loss: 0.011456393636763096
2023-01-22 17:19:40.281068: step: 1100/530, loss: 0.0032643110025674105
2023-01-22 17:19:41.342374: step: 1104/530, loss: 0.0008727310341782868
2023-01-22 17:19:42.390505: step: 1108/530, loss: 0.0029799621552228928
2023-01-22 17:19:43.445951: step: 1112/530, loss: 0.001928052632138133
2023-01-22 17:19:44.511301: step: 1116/530, loss: 0.0030343958642333746
2023-01-22 17:19:45.562131: step: 1120/530, loss: 0.012347896583378315
2023-01-22 17:19:46.618617: step: 1124/530, loss: 0.003494786797091365
2023-01-22 17:19:47.675508: step: 1128/530, loss: 0.005212375894188881
2023-01-22 17:19:48.734449: step: 1132/530, loss: 0.030489826574921608
2023-01-22 17:19:49.810476: step: 1136/530, loss: 0.0030600493773818016
2023-01-22 17:19:50.877808: step: 1140/530, loss: 0.002947741886600852
2023-01-22 17:19:51.941239: step: 1144/530, loss: 0.00041754983249120414
2023-01-22 17:19:52.987976: step: 1148/530, loss: 0.006820475682616234
2023-01-22 17:19:54.037563: step: 1152/530, loss: 0.030965633690357208
2023-01-22 17:19:55.107006: step: 1156/530, loss: 0.0009975474094972014
2023-01-22 17:19:56.168494: step: 1160/530, loss: 0.00589167233556509
2023-01-22 17:19:57.223063: step: 1164/530, loss: 0.003530725836753845
2023-01-22 17:19:58.282648: step: 1168/530, loss: 0.0005125369061715901
2023-01-22 17:19:59.362554: step: 1172/530, loss: 0.005166999530047178
2023-01-22 17:20:00.414485: step: 1176/530, loss: 0.005154833663254976
2023-01-22 17:20:01.479366: step: 1180/530, loss: 0.0028606008272618055
2023-01-22 17:20:02.569531: step: 1184/530, loss: 0.00778200151398778
2023-01-22 17:20:03.617682: step: 1188/530, loss: 0.012655799277126789
2023-01-22 17:20:04.692461: step: 1192/530, loss: 0.00463914405554533
2023-01-22 17:20:05.757226: step: 1196/530, loss: 0.016776612028479576
2023-01-22 17:20:06.821222: step: 1200/530, loss: 0.0010947714326903224
2023-01-22 17:20:07.879174: step: 1204/530, loss: 0.004286728799343109
2023-01-22 17:20:08.936253: step: 1208/530, loss: 0.014476386830210686
2023-01-22 17:20:09.994763: step: 1212/530, loss: 0.00017879836377687752
2023-01-22 17:20:11.058213: step: 1216/530, loss: 0.0029981951229274273
2023-01-22 17:20:12.122119: step: 1220/530, loss: 0.0067831166088581085
2023-01-22 17:20:13.165539: step: 1224/530, loss: 0.0004000284825451672
2023-01-22 17:20:14.223094: step: 1228/530, loss: 0.004634473472833633
2023-01-22 17:20:15.293354: step: 1232/530, loss: 0.00031167708220891654
2023-01-22 17:20:16.353626: step: 1236/530, loss: 0.00014672642282675952
2023-01-22 17:20:17.417549: step: 1240/530, loss: 0.0001291943044634536
2023-01-22 17:20:18.476780: step: 1244/530, loss: 0.00040160107892006636
2023-01-22 17:20:19.548406: step: 1248/530, loss: 0.0027477906551212072
2023-01-22 17:20:20.603674: step: 1252/530, loss: 0.0026647248305380344
2023-01-22 17:20:21.655421: step: 1256/530, loss: 0.0050496975891292095
2023-01-22 17:20:22.715472: step: 1260/530, loss: 0.007349679246544838
2023-01-22 17:20:23.781453: step: 1264/530, loss: 0.002333305310457945
2023-01-22 17:20:24.841669: step: 1268/530, loss: 0.005892075132578611
2023-01-22 17:20:25.895054: step: 1272/530, loss: 3.1096162274479866e-05
2023-01-22 17:20:26.964495: step: 1276/530, loss: 0.00208910065703094
2023-01-22 17:20:28.017810: step: 1280/530, loss: 0.0013125840341672301
2023-01-22 17:20:29.066270: step: 1284/530, loss: 0.01049579307436943
2023-01-22 17:20:30.139074: step: 1288/530, loss: 0.00017735878645908087
2023-01-22 17:20:31.200270: step: 1292/530, loss: 0.0026174653321504593
2023-01-22 17:20:32.283324: step: 1296/530, loss: 0.004889457952231169
2023-01-22 17:20:33.351151: step: 1300/530, loss: 0.004436878953129053
2023-01-22 17:20:34.408494: step: 1304/530, loss: 0.04407677426934242
2023-01-22 17:20:35.466701: step: 1308/530, loss: 0.009135912172496319
2023-01-22 17:20:36.521771: step: 1312/530, loss: 0.00012033154780510813
2023-01-22 17:20:37.592154: step: 1316/530, loss: 0.0005741912173107266
2023-01-22 17:20:38.649869: step: 1320/530, loss: 0.000827984360512346
2023-01-22 17:20:39.694773: step: 1324/530, loss: 0.00039905644371174276
2023-01-22 17:20:40.748616: step: 1328/530, loss: 0.012761428020894527
2023-01-22 17:20:41.830384: step: 1332/530, loss: 0.003925918135792017
2023-01-22 17:20:42.883769: step: 1336/530, loss: 0.00011272216215729713
2023-01-22 17:20:43.936302: step: 1340/530, loss: 0.005644111894071102
2023-01-22 17:20:44.993103: step: 1344/530, loss: 0.002674018731340766
2023-01-22 17:20:46.054543: step: 1348/530, loss: 0.008589793927967548
2023-01-22 17:20:47.117251: step: 1352/530, loss: 0.001278763753362
2023-01-22 17:20:48.178920: step: 1356/530, loss: 0.0033858329989016056
2023-01-22 17:20:49.235917: step: 1360/530, loss: 0.0007215364603325725
2023-01-22 17:20:50.285736: step: 1364/530, loss: 0.0008494686335325241
2023-01-22 17:20:51.340358: step: 1368/530, loss: 0.0020682066679000854
2023-01-22 17:20:52.412923: step: 1372/530, loss: 0.0009404866141267121
2023-01-22 17:20:53.475271: step: 1376/530, loss: 0.014776553958654404
2023-01-22 17:20:54.532094: step: 1380/530, loss: 0.0024232049472630024
2023-01-22 17:20:55.578680: step: 1384/530, loss: 0.00016248329484369606
2023-01-22 17:20:56.639333: step: 1388/530, loss: 3.867230589094106e-06
2023-01-22 17:20:57.682727: step: 1392/530, loss: 0.012080510146915913
2023-01-22 17:20:58.735360: step: 1396/530, loss: 0.007514503318816423
2023-01-22 17:20:59.784989: step: 1400/530, loss: 0.0004357305879238993
2023-01-22 17:21:00.826854: step: 1404/530, loss: 0.0015582782216370106
2023-01-22 17:21:01.878728: step: 1408/530, loss: 0.0005134954117238522
2023-01-22 17:21:02.955348: step: 1412/530, loss: 0.005048430059105158
2023-01-22 17:21:04.036944: step: 1416/530, loss: 0.005916623864322901
2023-01-22 17:21:05.085636: step: 1420/530, loss: 0.0006959058227948844
2023-01-22 17:21:06.148411: step: 1424/530, loss: 0.00013622238475363702
2023-01-22 17:21:07.241370: step: 1428/530, loss: 0.00473270658403635
2023-01-22 17:21:08.293388: step: 1432/530, loss: 0.00217193691059947
2023-01-22 17:21:09.347953: step: 1436/530, loss: 0.0030863445717841387
2023-01-22 17:21:10.404987: step: 1440/530, loss: 0.0029959524981677532
2023-01-22 17:21:11.461599: step: 1444/530, loss: 0.004369216971099377
2023-01-22 17:21:12.492094: step: 1448/530, loss: 0.0002775027242023498
2023-01-22 17:21:13.538233: step: 1452/530, loss: 0.012105317786335945
2023-01-22 17:21:14.596644: step: 1456/530, loss: 0.0007738307467661798
2023-01-22 17:21:15.672771: step: 1460/530, loss: 0.0016105304239317775
2023-01-22 17:21:16.740348: step: 1464/530, loss: 0.0007385810022242367
2023-01-22 17:21:17.790891: step: 1468/530, loss: 0.010588613338768482
2023-01-22 17:21:18.840685: step: 1472/530, loss: 0.002354239346459508
2023-01-22 17:21:19.890638: step: 1476/530, loss: 0.004085084423422813
2023-01-22 17:21:20.945803: step: 1480/530, loss: 0.0014612242812290788
2023-01-22 17:21:21.995795: step: 1484/530, loss: 0.001157862483523786
2023-01-22 17:21:23.053483: step: 1488/530, loss: 0.00991156417876482
2023-01-22 17:21:24.100879: step: 1492/530, loss: 0.0013073643203824759
2023-01-22 17:21:25.150603: step: 1496/530, loss: 0.0008875157218426466
2023-01-22 17:21:26.214083: step: 1500/530, loss: 0.005048149731010199
2023-01-22 17:21:27.261103: step: 1504/530, loss: 0.0013094150926917791
2023-01-22 17:21:28.312289: step: 1508/530, loss: 0.009651774540543556
2023-01-22 17:21:29.368284: step: 1512/530, loss: 2.1703603124478832e-05
2023-01-22 17:21:30.407412: step: 1516/530, loss: 0.005784967914223671
2023-01-22 17:21:31.456393: step: 1520/530, loss: 0.003384597133845091
2023-01-22 17:21:32.540551: step: 1524/530, loss: 0.001116138300858438
2023-01-22 17:21:33.606979: step: 1528/530, loss: 0.0064106713980436325
2023-01-22 17:21:34.656704: step: 1532/530, loss: 0.00103941117413342
2023-01-22 17:21:35.728788: step: 1536/530, loss: 0.002000241307541728
2023-01-22 17:21:36.799891: step: 1540/530, loss: 0.003647992154583335
2023-01-22 17:21:37.852343: step: 1544/530, loss: 0.00013092538574710488
2023-01-22 17:21:38.897000: step: 1548/530, loss: 0.0021415052469819784
2023-01-22 17:21:39.975011: step: 1552/530, loss: 0.002189740538597107
2023-01-22 17:21:41.024823: step: 1556/530, loss: 0.004675908945500851
2023-01-22 17:21:42.081072: step: 1560/530, loss: 0.0064605651423335075
2023-01-22 17:21:43.148607: step: 1564/530, loss: 0.003457580925896764
2023-01-22 17:21:44.196925: step: 1568/530, loss: 0.002549791010096669
2023-01-22 17:21:45.262444: step: 1572/530, loss: 0.003073513275012374
2023-01-22 17:21:46.317403: step: 1576/530, loss: 0.0017663181060925126
2023-01-22 17:21:47.366137: step: 1580/530, loss: 0.004768700338900089
2023-01-22 17:21:48.416826: step: 1584/530, loss: 0.001490938593633473
2023-01-22 17:21:49.486580: step: 1588/530, loss: 0.0035764218773692846
2023-01-22 17:21:50.530171: step: 1592/530, loss: 0.002601673360913992
2023-01-22 17:21:51.590327: step: 1596/530, loss: 0.004360167309641838
2023-01-22 17:21:52.647869: step: 1600/530, loss: 0.0017813154263421893
2023-01-22 17:21:53.707914: step: 1604/530, loss: 0.0005115437088534236
2023-01-22 17:21:54.755817: step: 1608/530, loss: 0.0015580097679048777
2023-01-22 17:21:55.805158: step: 1612/530, loss: 0.0009313811897300184
2023-01-22 17:21:56.862168: step: 1616/530, loss: 0.003170141950249672
2023-01-22 17:21:57.922562: step: 1620/530, loss: 0.0066484976559877396
2023-01-22 17:21:58.972515: step: 1624/530, loss: 0.03129187598824501
2023-01-22 17:22:00.021908: step: 1628/530, loss: 0.0017491650069132447
2023-01-22 17:22:01.081747: step: 1632/530, loss: 0.005608345847576857
2023-01-22 17:22:02.152509: step: 1636/530, loss: 3.549307393768686e-06
2023-01-22 17:22:03.199700: step: 1640/530, loss: 0.002708329353481531
2023-01-22 17:22:04.269172: step: 1644/530, loss: 0.0030882530845701694
2023-01-22 17:22:05.314493: step: 1648/530, loss: 0.001372261205688119
2023-01-22 17:22:06.373526: step: 1652/530, loss: 0.004122499376535416
2023-01-22 17:22:07.433473: step: 1656/530, loss: 0.0012495401315391064
2023-01-22 17:22:08.526720: step: 1660/530, loss: 0.00310580269433558
2023-01-22 17:22:09.574278: step: 1664/530, loss: 0.003324440447613597
2023-01-22 17:22:10.639289: step: 1668/530, loss: 0.008820747956633568
2023-01-22 17:22:11.680781: step: 1672/530, loss: 0.0003008394851349294
2023-01-22 17:22:12.732272: step: 1676/530, loss: 0.00015873562369961292
2023-01-22 17:22:13.788682: step: 1680/530, loss: 0.0014639886794611812
2023-01-22 17:22:14.847886: step: 1684/530, loss: 0.0038634841330349445
2023-01-22 17:22:15.897693: step: 1688/530, loss: 0.0022937003523111343
2023-01-22 17:22:16.963027: step: 1692/530, loss: 0.0018387915333732963
2023-01-22 17:22:18.011293: step: 1696/530, loss: 0.000539447006303817
2023-01-22 17:22:19.069775: step: 1700/530, loss: 1.8636201275512576e-05
2023-01-22 17:22:20.129580: step: 1704/530, loss: 0.002009348012506962
2023-01-22 17:22:21.204154: step: 1708/530, loss: 0.003003309480845928
2023-01-22 17:22:22.260619: step: 1712/530, loss: 0.00573319336399436
2023-01-22 17:22:23.311096: step: 1716/530, loss: 2.1565016140812077e-05
2023-01-22 17:22:24.363688: step: 1720/530, loss: 0.0024107687640935183
2023-01-22 17:22:25.412974: step: 1724/530, loss: 0.0027836698573082685
2023-01-22 17:22:26.468949: step: 1728/530, loss: 0.013397029601037502
2023-01-22 17:22:27.520763: step: 1732/530, loss: 0.0029961131513118744
2023-01-22 17:22:28.580952: step: 1736/530, loss: 0.001511456212028861
2023-01-22 17:22:29.638458: step: 1740/530, loss: 0.002070426242426038
2023-01-22 17:22:30.690399: step: 1744/530, loss: 0.004805145785212517
2023-01-22 17:22:31.739928: step: 1748/530, loss: 0.00802450068295002
2023-01-22 17:22:32.826648: step: 1752/530, loss: 0.007181966211646795
2023-01-22 17:22:33.878366: step: 1756/530, loss: 0.0002228617377113551
2023-01-22 17:22:34.919993: step: 1760/530, loss: 0.0006234684260562062
2023-01-22 17:22:35.965726: step: 1764/530, loss: 0.011605664156377316
2023-01-22 17:22:37.018561: step: 1768/530, loss: 0.0024073508102446795
2023-01-22 17:22:38.074075: step: 1772/530, loss: 0.00016558643255848438
2023-01-22 17:22:39.130236: step: 1776/530, loss: 0.0038935376796871424
2023-01-22 17:22:40.179252: step: 1780/530, loss: 0.0018876600079238415
2023-01-22 17:22:41.250128: step: 1784/530, loss: 0.00028517073951661587
2023-01-22 17:22:42.303998: step: 1788/530, loss: 0.0016901235794648528
2023-01-22 17:22:43.357600: step: 1792/530, loss: 0.001723955268971622
2023-01-22 17:22:44.440235: step: 1796/530, loss: 0.007639243733137846
2023-01-22 17:22:45.502293: step: 1800/530, loss: 2.240624553451198e-06
2023-01-22 17:22:46.553343: step: 1804/530, loss: 0.0035283362958580256
2023-01-22 17:22:47.623924: step: 1808/530, loss: 0.00013449843390844762
2023-01-22 17:22:48.692848: step: 1812/530, loss: 0.00010105366527568549
2023-01-22 17:22:49.750065: step: 1816/530, loss: 0.020721998065710068
2023-01-22 17:22:50.808758: step: 1820/530, loss: 0.0004792529216501862
2023-01-22 17:22:51.866215: step: 1824/530, loss: 0.00237208791077137
2023-01-22 17:22:52.900870: step: 1828/530, loss: 0.000804501585662365
2023-01-22 17:22:53.955526: step: 1832/530, loss: 0.0017982082208618522
2023-01-22 17:22:55.016233: step: 1836/530, loss: 0.00035185753949917853
2023-01-22 17:22:56.076806: step: 1840/530, loss: 0.00035365656367503107
2023-01-22 17:22:57.144150: step: 1844/530, loss: 0.0028863309416919947
2023-01-22 17:22:58.192466: step: 1848/530, loss: 0.003302385099232197
2023-01-22 17:22:59.247759: step: 1852/530, loss: 0.004862851928919554
2023-01-22 17:23:00.303933: step: 1856/530, loss: 0.0013533816672861576
2023-01-22 17:23:01.369054: step: 1860/530, loss: 0.0017837887862697244
2023-01-22 17:23:02.425951: step: 1864/530, loss: 0.0010549998842179775
2023-01-22 17:23:03.485273: step: 1868/530, loss: 0.0033746499102562666
2023-01-22 17:23:04.556475: step: 1872/530, loss: 0.003407091833651066
2023-01-22 17:23:05.627079: step: 1876/530, loss: 0.0002877535589504987
2023-01-22 17:23:06.679600: step: 1880/530, loss: 0.008806528523564339
2023-01-22 17:23:07.730901: step: 1884/530, loss: 0.008145834319293499
2023-01-22 17:23:08.804198: step: 1888/530, loss: 0.02251402474939823
2023-01-22 17:23:09.857909: step: 1892/530, loss: 0.0033284134697169065
2023-01-22 17:23:10.908131: step: 1896/530, loss: 0.0007608557934872806
2023-01-22 17:23:11.960896: step: 1900/530, loss: 0.0035523436963558197
2023-01-22 17:23:13.030381: step: 1904/530, loss: 0.0019328538328409195
2023-01-22 17:23:14.091742: step: 1908/530, loss: 0.004374410957098007
2023-01-22 17:23:15.141694: step: 1912/530, loss: 0.0021371780894696712
2023-01-22 17:23:16.221689: step: 1916/530, loss: 0.0006871892837807536
2023-01-22 17:23:17.267977: step: 1920/530, loss: 0.016005143523216248
2023-01-22 17:23:18.331416: step: 1924/530, loss: 0.004985588602721691
2023-01-22 17:23:19.396133: step: 1928/530, loss: 0.002317729638889432
2023-01-22 17:23:20.455878: step: 1932/530, loss: 0.0018285639816895127
2023-01-22 17:23:21.504922: step: 1936/530, loss: 0.00011135570821352303
2023-01-22 17:23:22.546913: step: 1940/530, loss: 0.0018454341916367412
2023-01-22 17:23:23.601771: step: 1944/530, loss: 0.004229668527841568
2023-01-22 17:23:24.638022: step: 1948/530, loss: 7.189160533016548e-05
2023-01-22 17:23:25.689526: step: 1952/530, loss: 0.0024383391719311476
2023-01-22 17:23:26.745302: step: 1956/530, loss: 0.011738252826035023
2023-01-22 17:23:27.812144: step: 1960/530, loss: 0.005646354053169489
2023-01-22 17:23:28.868779: step: 1964/530, loss: 0.005883152596652508
2023-01-22 17:23:29.941986: step: 1968/530, loss: 0.014391114003956318
2023-01-22 17:23:30.998012: step: 1972/530, loss: 0.001084222225472331
2023-01-22 17:23:32.087975: step: 1976/530, loss: 0.0014072353951632977
2023-01-22 17:23:33.161413: step: 1980/530, loss: 0.006906730588525534
2023-01-22 17:23:34.211237: step: 1984/530, loss: 0.0017693625995889306
2023-01-22 17:23:35.274064: step: 1988/530, loss: 0.0013903853250667453
2023-01-22 17:23:36.353356: step: 1992/530, loss: 0.0021799863316118717
2023-01-22 17:23:37.393327: step: 1996/530, loss: 0.00016508408589288592
2023-01-22 17:23:38.449495: step: 2000/530, loss: 0.0038060236256569624
2023-01-22 17:23:39.506328: step: 2004/530, loss: 0.0005931927007623017
2023-01-22 17:23:40.544299: step: 2008/530, loss: 0.002115587005391717
2023-01-22 17:23:41.605539: step: 2012/530, loss: 0.015803448855876923
2023-01-22 17:23:42.671355: step: 2016/530, loss: 0.002373557770624757
2023-01-22 17:23:43.728609: step: 2020/530, loss: 4.712997542810626e-05
2023-01-22 17:23:44.782004: step: 2024/530, loss: 0.012704210355877876
2023-01-22 17:23:45.825802: step: 2028/530, loss: 0.005773926619440317
2023-01-22 17:23:46.867128: step: 2032/530, loss: 0.0030485300812870264
2023-01-22 17:23:47.914840: step: 2036/530, loss: 0.00439033005386591
2023-01-22 17:23:48.955956: step: 2040/530, loss: 0.0001475557655794546
2023-01-22 17:23:50.030770: step: 2044/530, loss: 0.0007186115835793316
2023-01-22 17:23:51.099068: step: 2048/530, loss: 0.005137973930686712
2023-01-22 17:23:52.149976: step: 2052/530, loss: 0.001257850555703044
2023-01-22 17:23:53.220551: step: 2056/530, loss: 0.0031440432649105787
2023-01-22 17:23:54.259347: step: 2060/530, loss: 0.02054126001894474
2023-01-22 17:23:55.317997: step: 2064/530, loss: 0.006343626417219639
2023-01-22 17:23:56.375695: step: 2068/530, loss: 0.00048386285197921097
2023-01-22 17:23:57.434043: step: 2072/530, loss: 0.004758656956255436
2023-01-22 17:23:58.489361: step: 2076/530, loss: 0.0004961027880199254
2023-01-22 17:23:59.560008: step: 2080/530, loss: 0.001984576229006052
2023-01-22 17:24:00.625151: step: 2084/530, loss: 0.005387153942137957
2023-01-22 17:24:01.676435: step: 2088/530, loss: 0.007111052051186562
2023-01-22 17:24:02.740432: step: 2092/530, loss: 0.014361165463924408
2023-01-22 17:24:03.793319: step: 2096/530, loss: 0.005159243941307068
2023-01-22 17:24:04.849968: step: 2100/530, loss: 0.01888951100409031
2023-01-22 17:24:05.911939: step: 2104/530, loss: 0.0012335758656263351
2023-01-22 17:24:06.966506: step: 2108/530, loss: 0.016428260132670403
2023-01-22 17:24:08.040315: step: 2112/530, loss: 0.010537414811551571
2023-01-22 17:24:09.085890: step: 2116/530, loss: 0.0018130127573385835
2023-01-22 17:24:10.159446: step: 2120/530, loss: 0.006279817782342434
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.363118530020704, 'r': 0.2893923768665952, 'f1': 0.32209035397823793}, 'combined': 0.23732973451028055, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3521063672468636, 'r': 0.23290845417887776, 'f1': 0.2803640068541989}, 'combined': 0.18594089573749975, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.324329991816694, 'r': 0.2887028336247086, 'f1': 0.30548115461692615}, 'combined': 0.20365410307795076, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40413968069294326, 'r': 0.31848723971563264, 'f1': 0.3562372995754923}, 'combined': 0.23249171130190022, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32564373427414944, 'r': 0.342327568857455, 'f1': 0.33377729655481736}, 'combined': 0.24594116588249698, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.362622052392839, 'r': 0.3305982867269779, 'f1': 0.345870490189909}, 'combined': 0.22938561007413652, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:26:34.639194: step: 4/530, loss: 0.0009386829333379865
2023-01-22 17:26:35.677619: step: 8/530, loss: 0.00021448858024086803
2023-01-22 17:26:36.731541: step: 12/530, loss: 0.002030710456892848
2023-01-22 17:26:37.796149: step: 16/530, loss: 0.007472326513379812
2023-01-22 17:26:38.852457: step: 20/530, loss: 0.0024618019815534353
2023-01-22 17:26:39.907991: step: 24/530, loss: 0.007355418987572193
2023-01-22 17:26:40.958170: step: 28/530, loss: 0.0018335689092054963
2023-01-22 17:26:42.010842: step: 32/530, loss: 0.005031111184507608
2023-01-22 17:26:43.068549: step: 36/530, loss: 0.0028262948617339134
2023-01-22 17:26:44.112984: step: 40/530, loss: 0.02769174799323082
2023-01-22 17:26:45.170284: step: 44/530, loss: 3.081093018408865e-05
2023-01-22 17:26:46.226886: step: 48/530, loss: 0.004454792011529207
2023-01-22 17:26:47.290661: step: 52/530, loss: 0.005327933933585882
2023-01-22 17:26:48.343221: step: 56/530, loss: 0.04255596920847893
2023-01-22 17:26:49.383321: step: 60/530, loss: 0.0041749305091798306
2023-01-22 17:26:50.445340: step: 64/530, loss: 0.0022202820982784033
2023-01-22 17:26:51.499848: step: 68/530, loss: 0.0018177309539169073
2023-01-22 17:26:52.555243: step: 72/530, loss: 0.00785097386687994
2023-01-22 17:26:53.627042: step: 76/530, loss: 0.0007124464609660208
2023-01-22 17:26:54.675650: step: 80/530, loss: 0.004217336419969797
2023-01-22 17:26:55.726408: step: 84/530, loss: 0.015137048438191414
2023-01-22 17:26:56.767475: step: 88/530, loss: 1.621049341338221e-05
2023-01-22 17:26:57.835577: step: 92/530, loss: 0.005527848843485117
2023-01-22 17:26:58.886740: step: 96/530, loss: 1.3223519090388436e-05
2023-01-22 17:26:59.951855: step: 100/530, loss: 0.007298769894987345
2023-01-22 17:27:01.029411: step: 104/530, loss: 0.0031019283924251795
2023-01-22 17:27:02.109176: step: 108/530, loss: 0.00399396475404501
2023-01-22 17:27:03.155599: step: 112/530, loss: 0.00026533877826295793
2023-01-22 17:27:04.198214: step: 116/530, loss: 0.008851900696754456
2023-01-22 17:27:05.247629: step: 120/530, loss: 0.011578517965972424
2023-01-22 17:27:06.309995: step: 124/530, loss: 0.001883233548142016
2023-01-22 17:27:07.369201: step: 128/530, loss: 0.006535989232361317
2023-01-22 17:27:08.432217: step: 132/530, loss: 0.00044140484533272684
2023-01-22 17:27:09.479687: step: 136/530, loss: 0.010019097477197647
2023-01-22 17:27:10.513993: step: 140/530, loss: 0.0022441791370511055
2023-01-22 17:27:11.585600: step: 144/530, loss: 0.0056763035245239735
2023-01-22 17:27:12.636383: step: 148/530, loss: 0.0002883502747863531
2023-01-22 17:27:13.710027: step: 152/530, loss: 0.004349716007709503
2023-01-22 17:27:14.754403: step: 156/530, loss: 4.808623270946555e-05
2023-01-22 17:27:15.827115: step: 160/530, loss: 0.0036020230036228895
2023-01-22 17:27:16.885150: step: 164/530, loss: 0.012690776959061623
2023-01-22 17:27:17.950396: step: 168/530, loss: 0.0038006429094821215
2023-01-22 17:27:19.024252: step: 172/530, loss: 0.00041007701656781137
2023-01-22 17:27:20.086958: step: 176/530, loss: 0.0014719851315021515
2023-01-22 17:27:21.144435: step: 180/530, loss: 0.001649768091738224
2023-01-22 17:27:22.201163: step: 184/530, loss: 0.0001243392180185765
2023-01-22 17:27:23.254955: step: 188/530, loss: 0.0003862860321532935
2023-01-22 17:27:24.311604: step: 192/530, loss: 3.218917845515534e-05
2023-01-22 17:27:25.401431: step: 196/530, loss: 0.009885952807962894
2023-01-22 17:27:26.463058: step: 200/530, loss: 0.0009832639480009675
2023-01-22 17:27:27.517373: step: 204/530, loss: 0.014232131652534008
2023-01-22 17:27:28.568707: step: 208/530, loss: 0.00450295303016901
2023-01-22 17:27:29.629906: step: 212/530, loss: 0.003632990876212716
2023-01-22 17:27:30.689509: step: 216/530, loss: 0.002428669948130846
2023-01-22 17:27:31.740668: step: 220/530, loss: 0.0012075200211256742
2023-01-22 17:27:32.802838: step: 224/530, loss: 0.001973214326426387
2023-01-22 17:27:33.859257: step: 228/530, loss: 0.0008062385604716837
2023-01-22 17:27:34.921724: step: 232/530, loss: 0.0019380688900128007
2023-01-22 17:27:35.969628: step: 236/530, loss: 0.003825535997748375
2023-01-22 17:27:37.010592: step: 240/530, loss: 5.544281066249823e-06
2023-01-22 17:27:38.101286: step: 244/530, loss: 0.004524745978415012
2023-01-22 17:27:39.162557: step: 248/530, loss: 0.0005649895174428821
2023-01-22 17:27:40.238421: step: 252/530, loss: 0.0007945309625938535
2023-01-22 17:27:41.312423: step: 256/530, loss: 0.004739412106573582
2023-01-22 17:27:42.356960: step: 260/530, loss: 0.009475553408265114
2023-01-22 17:27:43.418073: step: 264/530, loss: 0.005468673072755337
2023-01-22 17:27:44.489642: step: 268/530, loss: 0.045450951904058456
2023-01-22 17:27:45.589186: step: 272/530, loss: 0.004849474411457777
2023-01-22 17:27:46.670774: step: 276/530, loss: 0.0021401692647486925
2023-01-22 17:27:47.725414: step: 280/530, loss: 0.009155112318694592
2023-01-22 17:27:48.807274: step: 284/530, loss: 0.00668818736448884
2023-01-22 17:27:49.868950: step: 288/530, loss: 0.0021922269370406866
2023-01-22 17:27:50.913367: step: 292/530, loss: 0.002677822019904852
2023-01-22 17:27:51.976774: step: 296/530, loss: 0.002026274800300598
2023-01-22 17:27:53.026217: step: 300/530, loss: 0.0004909008857794106
2023-01-22 17:27:54.082481: step: 304/530, loss: 0.0018706420669332147
2023-01-22 17:27:55.150024: step: 308/530, loss: 0.005222581792622805
2023-01-22 17:27:56.214824: step: 312/530, loss: 0.0012957018334418535
2023-01-22 17:27:57.275713: step: 316/530, loss: 0.0007491899887099862
2023-01-22 17:27:58.345208: step: 320/530, loss: 0.0018411485943943262
2023-01-22 17:27:59.402626: step: 324/530, loss: 0.0009789136238396168
2023-01-22 17:28:00.496841: step: 328/530, loss: 0.006667387206107378
2023-01-22 17:28:01.551741: step: 332/530, loss: 0.0030638682655990124
2023-01-22 17:28:02.610109: step: 336/530, loss: 0.005697141867130995
2023-01-22 17:28:03.662455: step: 340/530, loss: 0.0005658336449414492
2023-01-22 17:28:04.721005: step: 344/530, loss: 0.004876302555203438
2023-01-22 17:28:05.768536: step: 348/530, loss: 0.0062772962264716625
2023-01-22 17:28:06.817635: step: 352/530, loss: 0.001867501880042255
2023-01-22 17:28:07.876463: step: 356/530, loss: 0.0002820830559358001
2023-01-22 17:28:08.939765: step: 360/530, loss: 0.0019512730650603771
2023-01-22 17:28:10.003622: step: 364/530, loss: 0.004519370384514332
2023-01-22 17:28:11.064154: step: 368/530, loss: 0.005315495189279318
2023-01-22 17:28:12.120656: step: 372/530, loss: 0.004027731716632843
2023-01-22 17:28:13.166397: step: 376/530, loss: 0.00014638186257798225
2023-01-22 17:28:14.224458: step: 380/530, loss: 0.00039292260771617293
2023-01-22 17:28:15.285880: step: 384/530, loss: 7.301506599333152e-08
2023-01-22 17:28:16.339977: step: 388/530, loss: 7.057004722810234e-07
2023-01-22 17:28:17.403582: step: 392/530, loss: 0.0014324997318908572
2023-01-22 17:28:18.460187: step: 396/530, loss: 0.011277749203145504
2023-01-22 17:28:19.512517: step: 400/530, loss: 0.002842929447069764
2023-01-22 17:28:20.593863: step: 404/530, loss: 0.005885696969926357
2023-01-22 17:28:21.649155: step: 408/530, loss: 0.0016754758544266224
2023-01-22 17:28:22.718334: step: 412/530, loss: 0.002650156384333968
2023-01-22 17:28:23.771196: step: 416/530, loss: 0.0065586562268435955
2023-01-22 17:28:24.845920: step: 420/530, loss: 0.0033050866331905127
2023-01-22 17:28:25.901710: step: 424/530, loss: 0.0026223042514175177
2023-01-22 17:28:26.950069: step: 428/530, loss: 0.0020132584031671286
2023-01-22 17:28:28.011007: step: 432/530, loss: 0.0009613293223083019
2023-01-22 17:28:29.074458: step: 436/530, loss: 0.0007674201624467969
2023-01-22 17:28:30.138915: step: 440/530, loss: 0.0019727502949535847
2023-01-22 17:28:31.204740: step: 444/530, loss: 0.003658716334030032
2023-01-22 17:28:32.315310: step: 448/530, loss: 0.0037849824875593185
2023-01-22 17:28:33.388565: step: 452/530, loss: 0.011315709911286831
2023-01-22 17:28:34.469475: step: 456/530, loss: 0.015622415579855442
2023-01-22 17:28:35.516670: step: 460/530, loss: 0.011789409443736076
2023-01-22 17:28:36.589447: step: 464/530, loss: 0.003437911393120885
2023-01-22 17:28:37.632329: step: 468/530, loss: 0.005939699709415436
2023-01-22 17:28:38.709772: step: 472/530, loss: 0.0016335212858393788
2023-01-22 17:28:39.785266: step: 476/530, loss: 0.0040862420573830605
2023-01-22 17:28:40.841495: step: 480/530, loss: 0.00496178911998868
2023-01-22 17:28:41.898473: step: 484/530, loss: 0.003899594768881798
2023-01-22 17:28:42.958294: step: 488/530, loss: 0.00574311101809144
2023-01-22 17:28:44.015637: step: 492/530, loss: 0.007534942589700222
2023-01-22 17:28:45.066217: step: 496/530, loss: 0.0028131166473031044
2023-01-22 17:28:46.133654: step: 500/530, loss: 0.001040592440403998
2023-01-22 17:28:47.215530: step: 504/530, loss: 0.0051602027378976345
2023-01-22 17:28:48.268144: step: 508/530, loss: 0.010511002503335476
2023-01-22 17:28:49.352647: step: 512/530, loss: 0.0028887316584587097
2023-01-22 17:28:50.403720: step: 516/530, loss: 0.000825155118945986
2023-01-22 17:28:51.468691: step: 520/530, loss: 0.0029051725286990404
2023-01-22 17:28:52.534723: step: 524/530, loss: 3.2719781302148476e-05
2023-01-22 17:28:53.609587: step: 528/530, loss: 0.025147877633571625
2023-01-22 17:28:54.673516: step: 532/530, loss: 0.003658863017335534
2023-01-22 17:28:55.725263: step: 536/530, loss: 0.007298395037651062
2023-01-22 17:28:56.776560: step: 540/530, loss: 0.004791155457496643
2023-01-22 17:28:57.834688: step: 544/530, loss: 0.0009713844629004598
2023-01-22 17:28:58.894424: step: 548/530, loss: 0.000187056211871095
2023-01-22 17:28:59.959268: step: 552/530, loss: 0.0031633852049708366
2023-01-22 17:29:01.029120: step: 556/530, loss: 0.0023610880598425865
2023-01-22 17:29:02.107574: step: 560/530, loss: 1.6934537825363805e-06
2023-01-22 17:29:03.168839: step: 564/530, loss: 0.006590954959392548
2023-01-22 17:29:04.225322: step: 568/530, loss: 0.00823607761412859
2023-01-22 17:29:05.290907: step: 572/530, loss: 0.000521054258570075
2023-01-22 17:29:06.343155: step: 576/530, loss: 0.0033228641841560602
2023-01-22 17:29:07.394060: step: 580/530, loss: 0.007264060899615288
2023-01-22 17:29:08.465085: step: 584/530, loss: 0.0006039158324711025
2023-01-22 17:29:09.526551: step: 588/530, loss: 0.00033796080970205367
2023-01-22 17:29:10.591990: step: 592/530, loss: 0.006586736999452114
2023-01-22 17:29:11.641775: step: 596/530, loss: 0.01144842617213726
2023-01-22 17:29:12.719739: step: 600/530, loss: 0.0010035395389422774
2023-01-22 17:29:13.773435: step: 604/530, loss: 0.003973324783146381
2023-01-22 17:29:14.837686: step: 608/530, loss: 5.2629133278969675e-05
2023-01-22 17:29:15.897703: step: 612/530, loss: 0.0010918211191892624
2023-01-22 17:29:16.955241: step: 616/530, loss: 0.0023431035224348307
2023-01-22 17:29:18.012558: step: 620/530, loss: 0.00015734006592538208
2023-01-22 17:29:19.065913: step: 624/530, loss: 0.00744766928255558
2023-01-22 17:29:20.123355: step: 628/530, loss: 0.0037689898163080215
2023-01-22 17:29:21.186518: step: 632/530, loss: 0.0036387047730386257
2023-01-22 17:29:22.245052: step: 636/530, loss: 0.0030482758302241564
2023-01-22 17:29:23.295229: step: 640/530, loss: 7.787552749505267e-05
2023-01-22 17:29:24.359999: step: 644/530, loss: 0.002574192127212882
2023-01-22 17:29:25.423009: step: 648/530, loss: 0.0011378563940525055
2023-01-22 17:29:26.491487: step: 652/530, loss: 0.0014655538834631443
2023-01-22 17:29:27.548577: step: 656/530, loss: 4.273462764103897e-05
2023-01-22 17:29:28.605170: step: 660/530, loss: 0.002614873694255948
2023-01-22 17:29:29.658754: step: 664/530, loss: 4.4426753447623923e-05
2023-01-22 17:29:30.725207: step: 668/530, loss: 0.0025797775015234947
2023-01-22 17:29:31.804856: step: 672/530, loss: 0.007049053907394409
2023-01-22 17:29:32.889968: step: 676/530, loss: 0.006039605475962162
2023-01-22 17:29:33.951034: step: 680/530, loss: 0.0002868953160941601
2023-01-22 17:29:35.012767: step: 684/530, loss: 0.003985260613262653
2023-01-22 17:29:36.066666: step: 688/530, loss: 0.004556918051093817
2023-01-22 17:29:37.118166: step: 692/530, loss: 0.004089372232556343
2023-01-22 17:29:38.176491: step: 696/530, loss: 0.0012868152698501945
2023-01-22 17:29:39.242298: step: 700/530, loss: 0.0004368739027995616
2023-01-22 17:29:40.304296: step: 704/530, loss: 0.00017612661758903414
2023-01-22 17:29:41.367162: step: 708/530, loss: 0.0006340441177599132
2023-01-22 17:29:42.424736: step: 712/530, loss: 0.0006080247112549841
2023-01-22 17:29:43.488943: step: 716/530, loss: 0.0025806252378970385
2023-01-22 17:29:44.556977: step: 720/530, loss: 0.0020334688015282154
2023-01-22 17:29:45.618642: step: 724/530, loss: 0.005636615213006735
2023-01-22 17:29:46.674677: step: 728/530, loss: 0.002521292772144079
2023-01-22 17:29:47.736218: step: 732/530, loss: 0.007601853925734758
2023-01-22 17:29:48.780675: step: 736/530, loss: 0.0007143801194615662
2023-01-22 17:29:49.833560: step: 740/530, loss: 0.0004314613761380315
2023-01-22 17:29:50.907761: step: 744/530, loss: 0.0007660879055038095
2023-01-22 17:29:51.950127: step: 748/530, loss: 0.002923080697655678
2023-01-22 17:29:53.020989: step: 752/530, loss: 0.001329029444605112
2023-01-22 17:29:54.072929: step: 756/530, loss: 0.0006486055790446699
2023-01-22 17:29:55.120563: step: 760/530, loss: 0.006709316745400429
2023-01-22 17:29:56.194290: step: 764/530, loss: 0.01356930285692215
2023-01-22 17:29:57.254267: step: 768/530, loss: 0.0009534488781355321
2023-01-22 17:29:58.306547: step: 772/530, loss: 0.003793965559452772
2023-01-22 17:29:59.361360: step: 776/530, loss: 0.0031500798650085926
2023-01-22 17:30:00.420547: step: 780/530, loss: 0.00013121060328558087
2023-01-22 17:30:01.477460: step: 784/530, loss: 0.000225961281103082
2023-01-22 17:30:02.561331: step: 788/530, loss: 0.002349739195778966
2023-01-22 17:30:03.608041: step: 792/530, loss: 0.0002679908648133278
2023-01-22 17:30:04.665088: step: 796/530, loss: 0.009738844819366932
2023-01-22 17:30:05.735968: step: 800/530, loss: 0.0044809612445533276
2023-01-22 17:30:06.784587: step: 804/530, loss: 3.349226972204633e-05
2023-01-22 17:30:07.828397: step: 808/530, loss: 0.0002546035102568567
2023-01-22 17:30:08.887187: step: 812/530, loss: 3.3927477488759905e-05
2023-01-22 17:30:09.944703: step: 816/530, loss: 0.003463677829131484
2023-01-22 17:30:11.016929: step: 820/530, loss: 0.002745649078860879
2023-01-22 17:30:12.078078: step: 824/530, loss: 0.0011064013233408332
2023-01-22 17:30:13.145221: step: 828/530, loss: 0.005074132699519396
2023-01-22 17:30:14.209810: step: 832/530, loss: 1.626579432922881e-05
2023-01-22 17:30:15.286700: step: 836/530, loss: 0.005866446997970343
2023-01-22 17:30:16.333970: step: 840/530, loss: 0.00099858024623245
2023-01-22 17:30:17.410766: step: 844/530, loss: 0.0027507091872394085
2023-01-22 17:30:18.469491: step: 848/530, loss: 0.0003187166294082999
2023-01-22 17:30:19.523385: step: 852/530, loss: 0.0035293144173920155
2023-01-22 17:30:20.579000: step: 856/530, loss: 0.0005090002669021487
2023-01-22 17:30:21.642265: step: 860/530, loss: 0.000783972383942455
2023-01-22 17:30:22.711979: step: 864/530, loss: 0.0016587880672886968
2023-01-22 17:30:23.774606: step: 868/530, loss: 1.529602400296426e-06
2023-01-22 17:30:24.826823: step: 872/530, loss: 5.782703374279663e-05
2023-01-22 17:30:25.870338: step: 876/530, loss: 6.204834789969027e-05
2023-01-22 17:30:26.946880: step: 880/530, loss: 0.0006993655697442591
2023-01-22 17:30:28.025162: step: 884/530, loss: 0.0017498458037152886
2023-01-22 17:30:29.060147: step: 888/530, loss: 0.007793949451297522
2023-01-22 17:30:30.118544: step: 892/530, loss: 0.00730760907754302
2023-01-22 17:30:31.160588: step: 896/530, loss: 0.006792369764298201
2023-01-22 17:30:32.220705: step: 900/530, loss: 0.004635286051779985
2023-01-22 17:30:33.281178: step: 904/530, loss: 0.0025487684179097414
2023-01-22 17:30:34.323645: step: 908/530, loss: 0.0011107393074780703
2023-01-22 17:30:35.369271: step: 912/530, loss: 0.01115464698523283
2023-01-22 17:30:36.414676: step: 916/530, loss: 0.0014674729900434613
2023-01-22 17:30:37.480791: step: 920/530, loss: 0.002353713382035494
2023-01-22 17:30:38.570040: step: 924/530, loss: 0.005914868786931038
2023-01-22 17:30:39.623595: step: 928/530, loss: 0.002360415877774358
2023-01-22 17:30:40.681846: step: 932/530, loss: 0.006875370629131794
2023-01-22 17:30:41.750118: step: 936/530, loss: 0.002805947558954358
2023-01-22 17:30:42.794499: step: 940/530, loss: 0.0009517442667856812
2023-01-22 17:30:43.847702: step: 944/530, loss: 0.012530175037682056
2023-01-22 17:30:44.917651: step: 948/530, loss: 0.001134154968895018
2023-01-22 17:30:45.961639: step: 952/530, loss: 0.07279449701309204
2023-01-22 17:30:47.023831: step: 956/530, loss: 0.00794054102152586
2023-01-22 17:30:48.091107: step: 960/530, loss: 0.0028819472063332796
2023-01-22 17:30:49.167204: step: 964/530, loss: 0.006080431863665581
2023-01-22 17:30:50.232616: step: 968/530, loss: 0.0005027989391237497
2023-01-22 17:30:51.284372: step: 972/530, loss: 0.003265087027102709
2023-01-22 17:30:52.339082: step: 976/530, loss: 0.004198809154331684
2023-01-22 17:30:53.394621: step: 980/530, loss: 0.006787418853491545
2023-01-22 17:30:54.451497: step: 984/530, loss: 0.006619878113269806
2023-01-22 17:30:55.485559: step: 988/530, loss: 0.00013095859321765602
2023-01-22 17:30:56.544305: step: 992/530, loss: 4.987631655239966e-06
2023-01-22 17:30:57.610939: step: 996/530, loss: 0.0016563341487199068
2023-01-22 17:30:58.662831: step: 1000/530, loss: 0.008938069455325603
2023-01-22 17:30:59.722672: step: 1004/530, loss: 0.00020557682728394866
2023-01-22 17:31:00.771447: step: 1008/530, loss: 0.004281255882233381
2023-01-22 17:31:01.838651: step: 1012/530, loss: 0.00846561137586832
2023-01-22 17:31:02.901951: step: 1016/530, loss: 0.008833480067551136
2023-01-22 17:31:03.965479: step: 1020/530, loss: 0.0008627060451544821
2023-01-22 17:31:05.042475: step: 1024/530, loss: 0.0017180436989292502
2023-01-22 17:31:06.089931: step: 1028/530, loss: 7.940216164570302e-05
2023-01-22 17:31:07.133094: step: 1032/530, loss: 0.005288590677082539
2023-01-22 17:31:08.191432: step: 1036/530, loss: 0.002299256157130003
2023-01-22 17:31:09.259760: step: 1040/530, loss: 0.004205361939966679
2023-01-22 17:31:10.306014: step: 1044/530, loss: 0.0010540197836235166
2023-01-22 17:31:11.372856: step: 1048/530, loss: 0.004733267240226269
2023-01-22 17:31:12.435112: step: 1052/530, loss: 0.0010042184730991721
2023-01-22 17:31:13.488187: step: 1056/530, loss: 0.007854187861084938
2023-01-22 17:31:14.556282: step: 1060/530, loss: 0.00882694497704506
2023-01-22 17:31:15.654148: step: 1064/530, loss: 0.005203136708587408
2023-01-22 17:31:16.727369: step: 1068/530, loss: 0.007038532756268978
2023-01-22 17:31:17.788241: step: 1072/530, loss: 0.0008152843220159411
2023-01-22 17:31:18.852764: step: 1076/530, loss: 0.009514098055660725
2023-01-22 17:31:19.914149: step: 1080/530, loss: 0.03624803572893143
2023-01-22 17:31:20.966976: step: 1084/530, loss: 0.00037415686529129744
2023-01-22 17:31:22.022706: step: 1088/530, loss: 0.002060860861092806
2023-01-22 17:31:23.085883: step: 1092/530, loss: 0.005768889561295509
2023-01-22 17:31:24.146501: step: 1096/530, loss: 0.0021620236802846193
2023-01-22 17:31:25.203301: step: 1100/530, loss: 0.0009779763640835881
2023-01-22 17:31:26.266192: step: 1104/530, loss: 0.0027924994938075542
2023-01-22 17:31:27.322326: step: 1108/530, loss: 0.00261816312558949
2023-01-22 17:31:28.373491: step: 1112/530, loss: 0.0007506689871661365
2023-01-22 17:31:29.422930: step: 1116/530, loss: 0.0007846153457649052
2023-01-22 17:31:30.484148: step: 1120/530, loss: 0.0005506880697794259
2023-01-22 17:31:31.542187: step: 1124/530, loss: 0.008922494947910309
2023-01-22 17:31:32.609106: step: 1128/530, loss: 0.0006309906602837145
2023-01-22 17:31:33.693279: step: 1132/530, loss: 0.001818582764826715
2023-01-22 17:31:34.741518: step: 1136/530, loss: 0.00010083736560773104
2023-01-22 17:31:35.800993: step: 1140/530, loss: 0.0019913718570023775
2023-01-22 17:31:36.859524: step: 1144/530, loss: 0.002719827927649021
2023-01-22 17:31:37.911909: step: 1148/530, loss: 0.0029059916269034147
2023-01-22 17:31:38.964917: step: 1152/530, loss: 0.0018283172976225615
2023-01-22 17:31:40.026507: step: 1156/530, loss: 0.0021711259614676237
2023-01-22 17:31:41.067435: step: 1160/530, loss: 0.0002222816547146067
2023-01-22 17:31:42.115680: step: 1164/530, loss: 0.004044365603476763
2023-01-22 17:31:43.173847: step: 1168/530, loss: 0.0010410137474536896
2023-01-22 17:31:44.229720: step: 1172/530, loss: 0.003217563033103943
2023-01-22 17:31:45.296343: step: 1176/530, loss: 0.014680308289825916
2023-01-22 17:31:46.351151: step: 1180/530, loss: 0.001965750940144062
2023-01-22 17:31:47.419783: step: 1184/530, loss: 0.0006287461728788912
2023-01-22 17:31:48.482964: step: 1188/530, loss: 0.0015455151442438364
2023-01-22 17:31:49.557592: step: 1192/530, loss: 0.0037629411090165377
2023-01-22 17:31:50.616139: step: 1196/530, loss: 0.020471738651394844
2023-01-22 17:31:51.681309: step: 1200/530, loss: 0.009383459575474262
2023-01-22 17:31:52.756450: step: 1204/530, loss: 4.2920266423607245e-05
2023-01-22 17:31:53.806430: step: 1208/530, loss: 0.002182356547564268
2023-01-22 17:31:54.855514: step: 1212/530, loss: 1.681403591646813e-05
2023-01-22 17:31:55.910192: step: 1216/530, loss: 6.735124043188989e-05
2023-01-22 17:31:56.973805: step: 1220/530, loss: 0.010192221961915493
2023-01-22 17:31:58.038404: step: 1224/530, loss: 0.0027165452484041452
2023-01-22 17:31:59.096193: step: 1228/530, loss: 0.01934061385691166
2023-01-22 17:32:00.165748: step: 1232/530, loss: 0.00330965593457222
2023-01-22 17:32:01.230599: step: 1236/530, loss: 0.0012744124978780746
2023-01-22 17:32:02.310504: step: 1240/530, loss: 0.0047326479107141495
2023-01-22 17:32:03.367347: step: 1244/530, loss: 0.010859795846045017
2023-01-22 17:32:04.415639: step: 1248/530, loss: 0.0033006141893565655
2023-01-22 17:32:05.472842: step: 1252/530, loss: 0.028408804908394814
2023-01-22 17:32:06.523670: step: 1256/530, loss: 0.0025512906722724438
2023-01-22 17:32:07.579179: step: 1260/530, loss: 9.052365385286976e-06
2023-01-22 17:32:08.628536: step: 1264/530, loss: 0.0008138024131767452
2023-01-22 17:32:09.688250: step: 1268/530, loss: 0.002259439555928111
2023-01-22 17:32:10.740929: step: 1272/530, loss: 0.00476970337331295
2023-01-22 17:32:11.787518: step: 1276/530, loss: 0.004920868668705225
2023-01-22 17:32:12.841680: step: 1280/530, loss: 0.0011291453847661614
2023-01-22 17:32:13.911109: step: 1284/530, loss: 0.0050354450941085815
2023-01-22 17:32:14.966372: step: 1288/530, loss: 0.004044852219521999
2023-01-22 17:32:16.015555: step: 1292/530, loss: 0.014269684441387653
2023-01-22 17:32:17.081598: step: 1296/530, loss: 0.008953960612416267
2023-01-22 17:32:18.128599: step: 1300/530, loss: 0.009656088426709175
2023-01-22 17:32:19.172331: step: 1304/530, loss: 0.0004117403586860746
2023-01-22 17:32:20.236917: step: 1308/530, loss: 0.0026506329886615276
2023-01-22 17:32:21.286201: step: 1312/530, loss: 0.0006844486342743039
2023-01-22 17:32:22.345806: step: 1316/530, loss: 0.0008493617060594261
2023-01-22 17:32:23.403495: step: 1320/530, loss: 0.007252085022628307
2023-01-22 17:32:24.477500: step: 1324/530, loss: 0.0040780045092105865
2023-01-22 17:32:25.536903: step: 1328/530, loss: 0.0041299546137452126
2023-01-22 17:32:26.592781: step: 1332/530, loss: 0.005475865676999092
2023-01-22 17:32:27.657128: step: 1336/530, loss: 0.0008960633422248065
2023-01-22 17:32:28.717114: step: 1340/530, loss: 0.0003693457110784948
2023-01-22 17:32:29.766713: step: 1344/530, loss: 0.006004272494465113
2023-01-22 17:32:30.812425: step: 1348/530, loss: 0.0055852667428553104
2023-01-22 17:32:31.872631: step: 1352/530, loss: 0.0005606253980658948
2023-01-22 17:32:32.923397: step: 1356/530, loss: 0.015660429373383522
2023-01-22 17:32:33.995499: step: 1360/530, loss: 0.006589094176888466
2023-01-22 17:32:35.052580: step: 1364/530, loss: 0.0006552804261445999
2023-01-22 17:32:36.107875: step: 1368/530, loss: 0.0018360433168709278
2023-01-22 17:32:37.170879: step: 1372/530, loss: 0.0008776461472734809
2023-01-22 17:32:38.236969: step: 1376/530, loss: 0.00030968282953836024
2023-01-22 17:32:39.281608: step: 1380/530, loss: 0.002020672196522355
2023-01-22 17:32:40.347706: step: 1384/530, loss: 0.0008043415145948529
2023-01-22 17:32:41.405413: step: 1388/530, loss: 0.000731975887902081
2023-01-22 17:32:42.477952: step: 1392/530, loss: 0.00030642494675703347
2023-01-22 17:32:43.548995: step: 1396/530, loss: 0.005770261865109205
2023-01-22 17:32:44.611018: step: 1400/530, loss: 0.0033982235472649336
2023-01-22 17:32:45.688846: step: 1404/530, loss: 0.005668317433446646
2023-01-22 17:32:46.756743: step: 1408/530, loss: 0.002456605900079012
2023-01-22 17:32:47.818404: step: 1412/530, loss: 0.0006804352160543203
2023-01-22 17:32:48.878819: step: 1416/530, loss: 0.0038925365079194307
2023-01-22 17:32:49.961734: step: 1420/530, loss: 0.009606541134417057
2023-01-22 17:32:51.017006: step: 1424/530, loss: 0.0043859235011041164
2023-01-22 17:32:52.085774: step: 1428/530, loss: 0.0015504687326028943
2023-01-22 17:32:53.125870: step: 1432/530, loss: 0.0007106783450581133
2023-01-22 17:32:54.178724: step: 1436/530, loss: 0.0004182421544101089
2023-01-22 17:32:55.237891: step: 1440/530, loss: 4.3359714254620485e-06
2023-01-22 17:32:56.305246: step: 1444/530, loss: 0.0009537481237202883
2023-01-22 17:32:57.362342: step: 1448/530, loss: 0.002968014217913151
2023-01-22 17:32:58.406768: step: 1452/530, loss: 0.007387248799204826
2023-01-22 17:32:59.457040: step: 1456/530, loss: 0.004928029142320156
2023-01-22 17:33:00.520055: step: 1460/530, loss: 0.003396560437977314
2023-01-22 17:33:01.584016: step: 1464/530, loss: 0.0039823311381042
2023-01-22 17:33:02.650323: step: 1468/530, loss: 0.0003091523831244558
2023-01-22 17:33:03.703025: step: 1472/530, loss: 0.009883124381303787
2023-01-22 17:33:04.773025: step: 1476/530, loss: 0.005797490477561951
2023-01-22 17:33:05.838988: step: 1480/530, loss: 7.638749229954556e-05
2023-01-22 17:33:06.902328: step: 1484/530, loss: 0.002113157883286476
2023-01-22 17:33:07.957344: step: 1488/530, loss: 3.481158637441695e-05
2023-01-22 17:33:09.029294: step: 1492/530, loss: 0.032113559544086456
2023-01-22 17:33:10.086510: step: 1496/530, loss: 0.0008705498185008764
2023-01-22 17:33:11.160897: step: 1500/530, loss: 0.0005705328658223152
2023-01-22 17:33:12.217911: step: 1504/530, loss: 0.0012229810236021876
2023-01-22 17:33:13.262221: step: 1508/530, loss: 0.006625020876526833
2023-01-22 17:33:14.318866: step: 1512/530, loss: 0.00024427458993159235
2023-01-22 17:33:15.390538: step: 1516/530, loss: 0.0003933395491912961
2023-01-22 17:33:16.435590: step: 1520/530, loss: 0.00021803095296490937
2023-01-22 17:33:17.492084: step: 1524/530, loss: 0.0016110274009406567
2023-01-22 17:33:18.550048: step: 1528/530, loss: 0.00801507942378521
2023-01-22 17:33:19.595790: step: 1532/530, loss: 0.0022511526476591825
2023-01-22 17:33:20.675065: step: 1536/530, loss: 0.004053221549838781
2023-01-22 17:33:21.732060: step: 1540/530, loss: 8.856142812874168e-05
2023-01-22 17:33:22.773559: step: 1544/530, loss: 0.001768397749401629
2023-01-22 17:33:23.836527: step: 1548/530, loss: 0.0007420568726956844
2023-01-22 17:33:24.888956: step: 1552/530, loss: 0.0009184726513922215
2023-01-22 17:33:25.956042: step: 1556/530, loss: 0.007182806730270386
2023-01-22 17:33:27.022185: step: 1560/530, loss: 0.0013950478751212358
2023-01-22 17:33:28.081648: step: 1564/530, loss: 0.0002595543919596821
2023-01-22 17:33:29.143880: step: 1568/530, loss: 0.00802836287766695
2023-01-22 17:33:30.213149: step: 1572/530, loss: 0.0010372252436354756
2023-01-22 17:33:31.268903: step: 1576/530, loss: 0.008910938166081905
2023-01-22 17:33:32.324730: step: 1580/530, loss: 0.004611999727785587
2023-01-22 17:33:33.375660: step: 1584/530, loss: 0.0023956496734172106
2023-01-22 17:33:34.429621: step: 1588/530, loss: 0.0006668035639449954
2023-01-22 17:33:35.498612: step: 1592/530, loss: 0.0012624349910765886
2023-01-22 17:33:36.542579: step: 1596/530, loss: 0.004224380478262901
2023-01-22 17:33:37.602929: step: 1600/530, loss: 0.0
2023-01-22 17:33:38.657867: step: 1604/530, loss: 0.004453417845070362
2023-01-22 17:33:39.721016: step: 1608/530, loss: 0.0002074887161143124
2023-01-22 17:33:40.797993: step: 1612/530, loss: 0.0019296916434541345
2023-01-22 17:33:41.861669: step: 1616/530, loss: 0.003930032253265381
2023-01-22 17:33:42.907404: step: 1620/530, loss: 0.005718322936445475
2023-01-22 17:33:43.959668: step: 1624/530, loss: 0.007376953028142452
2023-01-22 17:33:45.016882: step: 1628/530, loss: 4.6544264478143305e-05
2023-01-22 17:33:46.071974: step: 1632/530, loss: 2.080125705106184e-05
2023-01-22 17:33:47.139378: step: 1636/530, loss: 0.00038969746674411
2023-01-22 17:33:48.201149: step: 1640/530, loss: 2.7635526294034207e-06
2023-01-22 17:33:49.246104: step: 1644/530, loss: 0.0018047861522063613
2023-01-22 17:33:50.313542: step: 1648/530, loss: 0.018415110185742378
2023-01-22 17:33:51.367660: step: 1652/530, loss: 0.006245397496968508
2023-01-22 17:33:52.429831: step: 1656/530, loss: 0.008730108849704266
2023-01-22 17:33:53.476300: step: 1660/530, loss: 0.0005476248916238546
2023-01-22 17:33:54.521598: step: 1664/530, loss: 0.005872698500752449
2023-01-22 17:33:55.579966: step: 1668/530, loss: 0.006725342478603125
2023-01-22 17:33:56.631364: step: 1672/530, loss: 0.002643076702952385
2023-01-22 17:33:57.714744: step: 1676/530, loss: 0.0018357306253165007
2023-01-22 17:33:58.775584: step: 1680/530, loss: 0.0025024511851370335
2023-01-22 17:33:59.835074: step: 1684/530, loss: 0.0017786616226658225
2023-01-22 17:34:00.913467: step: 1688/530, loss: 0.0014846071135252714
2023-01-22 17:34:01.952994: step: 1692/530, loss: 0.0043900697492063046
2023-01-22 17:34:03.050795: step: 1696/530, loss: 0.0005729013355448842
2023-01-22 17:34:04.105931: step: 1700/530, loss: 0.000537501648068428
2023-01-22 17:34:05.155324: step: 1704/530, loss: 0.00025959074264392257
2023-01-22 17:34:06.207358: step: 1708/530, loss: 0.0007950629806146026
2023-01-22 17:34:07.259626: step: 1712/530, loss: 0.000675673596560955
2023-01-22 17:34:08.323407: step: 1716/530, loss: 0.003960703033953905
2023-01-22 17:34:09.381266: step: 1720/530, loss: 0.0008025092538446188
2023-01-22 17:34:10.431835: step: 1724/530, loss: 9.509678784525022e-05
2023-01-22 17:34:11.484056: step: 1728/530, loss: 0.0008456521318294108
2023-01-22 17:34:12.548315: step: 1732/530, loss: 0.0012850385392084718
2023-01-22 17:34:13.616305: step: 1736/530, loss: 0.00015842165157664567
2023-01-22 17:34:14.675699: step: 1740/530, loss: 0.0028479828033596277
2023-01-22 17:34:15.735040: step: 1744/530, loss: 0.004899812396615744
2023-01-22 17:34:16.784131: step: 1748/530, loss: 0.0021729222498834133
2023-01-22 17:34:17.839898: step: 1752/530, loss: 0.0006834256928414106
2023-01-22 17:34:18.909033: step: 1756/530, loss: 0.0008538194815628231
2023-01-22 17:34:19.966843: step: 1760/530, loss: 0.003740330459550023
2023-01-22 17:34:21.022202: step: 1764/530, loss: 0.002530330792069435
2023-01-22 17:34:22.084267: step: 1768/530, loss: 0.0019842495676130056
2023-01-22 17:34:23.145511: step: 1772/530, loss: 0.0023462462704628706
2023-01-22 17:34:24.196969: step: 1776/530, loss: 0.0018969499506056309
2023-01-22 17:34:25.246441: step: 1780/530, loss: 0.00016835425049066544
2023-01-22 17:34:26.293881: step: 1784/530, loss: 0.00010306596232112497
2023-01-22 17:34:27.354425: step: 1788/530, loss: 0.0004965196712873876
2023-01-22 17:34:28.412162: step: 1792/530, loss: 0.004526231437921524
2023-01-22 17:34:29.473367: step: 1796/530, loss: 0.007723315618932247
2023-01-22 17:34:30.540746: step: 1800/530, loss: 0.022789280861616135
2023-01-22 17:34:31.594139: step: 1804/530, loss: 0.012160413898527622
2023-01-22 17:34:32.639125: step: 1808/530, loss: 7.116822234820575e-05
2023-01-22 17:34:33.711589: step: 1812/530, loss: 0.003039315342903137
2023-01-22 17:34:34.764787: step: 1816/530, loss: 0.003282669000327587
2023-01-22 17:34:35.839216: step: 1820/530, loss: 0.0035452661104500294
2023-01-22 17:34:36.879652: step: 1824/530, loss: 0.0012875092215836048
2023-01-22 17:34:37.930683: step: 1828/530, loss: 0.0011750131379812956
2023-01-22 17:34:38.985790: step: 1832/530, loss: 0.0004066886322107166
2023-01-22 17:34:40.039608: step: 1836/530, loss: 0.007107979152351618
2023-01-22 17:34:41.098257: step: 1840/530, loss: 0.06521487236022949
2023-01-22 17:34:42.153936: step: 1844/530, loss: 0.0008080429979600012
2023-01-22 17:34:43.215397: step: 1848/530, loss: 0.0002981397556141019
2023-01-22 17:34:44.254820: step: 1852/530, loss: 0.002167333848774433
2023-01-22 17:34:45.319563: step: 1856/530, loss: 0.005629674065858126
2023-01-22 17:34:46.377482: step: 1860/530, loss: 0.003950349520891905
2023-01-22 17:34:47.438880: step: 1864/530, loss: 0.027358174324035645
2023-01-22 17:34:48.485416: step: 1868/530, loss: 0.003266548039391637
2023-01-22 17:34:49.539758: step: 1872/530, loss: 0.009740294888615608
2023-01-22 17:34:50.584641: step: 1876/530, loss: 0.003349998500198126
2023-01-22 17:34:51.618073: step: 1880/530, loss: 0.029655758291482925
2023-01-22 17:34:52.682700: step: 1884/530, loss: 0.08274171501398087
2023-01-22 17:34:53.719018: step: 1888/530, loss: 0.007874841801822186
2023-01-22 17:34:54.787472: step: 1892/530, loss: 0.005087847355753183
2023-01-22 17:34:55.841012: step: 1896/530, loss: 0.013425260782241821
2023-01-22 17:34:56.881700: step: 1900/530, loss: 0.012691500596702099
2023-01-22 17:34:57.927057: step: 1904/530, loss: 0.006187261547893286
2023-01-22 17:34:58.986522: step: 1908/530, loss: 0.0008559083216823637
2023-01-22 17:35:00.045719: step: 1912/530, loss: 0.0035449869465082884
2023-01-22 17:35:01.109145: step: 1916/530, loss: 0.003675689222291112
2023-01-22 17:35:02.177912: step: 1920/530, loss: 0.003050812752917409
2023-01-22 17:35:03.226701: step: 1924/530, loss: 0.002955114236101508
2023-01-22 17:35:04.291278: step: 1928/530, loss: 0.012532936409115791
2023-01-22 17:35:05.334081: step: 1932/530, loss: 4.164597271483217e-07
2023-01-22 17:35:06.395270: step: 1936/530, loss: 0.0037662910763174295
2023-01-22 17:35:07.452257: step: 1940/530, loss: 0.00575527036562562
2023-01-22 17:35:08.508804: step: 1944/530, loss: 0.003928194288164377
2023-01-22 17:35:09.567205: step: 1948/530, loss: 0.0014893363695591688
2023-01-22 17:35:10.628572: step: 1952/530, loss: 0.006476827897131443
2023-01-22 17:35:11.692315: step: 1956/530, loss: 0.002577632898464799
2023-01-22 17:35:12.751825: step: 1960/530, loss: 0.01879754103720188
2023-01-22 17:35:13.807709: step: 1964/530, loss: 0.005210411734879017
2023-01-22 17:35:14.848297: step: 1968/530, loss: 0.004157794173806906
2023-01-22 17:35:15.908023: step: 1972/530, loss: 0.005670475773513317
2023-01-22 17:35:16.980391: step: 1976/530, loss: 0.00019238569075241685
2023-01-22 17:35:18.037900: step: 1980/530, loss: 0.0010525088291615248
2023-01-22 17:35:19.096807: step: 1984/530, loss: 0.007439812179654837
2023-01-22 17:35:20.169518: step: 1988/530, loss: 0.009524581953883171
2023-01-22 17:35:21.241277: step: 1992/530, loss: 0.00033826479921117425
2023-01-22 17:35:22.287430: step: 1996/530, loss: 0.00013386989303398877
2023-01-22 17:35:23.364595: step: 2000/530, loss: 0.001947549288161099
2023-01-22 17:35:24.416325: step: 2004/530, loss: 0.0036375918425619602
2023-01-22 17:35:25.471685: step: 2008/530, loss: 0.00015946265193633735
2023-01-22 17:35:26.529301: step: 2012/530, loss: 0.010268784128129482
2023-01-22 17:35:27.577483: step: 2016/530, loss: 0.0007080572540871799
2023-01-22 17:35:28.624565: step: 2020/530, loss: 0.0031804454047232866
2023-01-22 17:35:29.691973: step: 2024/530, loss: 4.408857421367429e-07
2023-01-22 17:35:30.745891: step: 2028/530, loss: 0.0021610078401863575
2023-01-22 17:35:31.824826: step: 2032/530, loss: 0.003540750127285719
2023-01-22 17:35:32.884844: step: 2036/530, loss: 7.505811663577333e-05
2023-01-22 17:35:33.941964: step: 2040/530, loss: 0.028510065749287605
2023-01-22 17:35:35.012278: step: 2044/530, loss: 0.00204320065677166
2023-01-22 17:35:36.050954: step: 2048/530, loss: 0.00035411937278695405
2023-01-22 17:35:37.121632: step: 2052/530, loss: 0.007907198742032051
2023-01-22 17:35:38.172001: step: 2056/530, loss: 0.01116646733134985
2023-01-22 17:35:39.209558: step: 2060/530, loss: 0.0043425001204013824
2023-01-22 17:35:40.246796: step: 2064/530, loss: 0.003712503472343087
2023-01-22 17:35:41.296320: step: 2068/530, loss: 0.0024377384688705206
2023-01-22 17:35:42.354347: step: 2072/530, loss: 0.004469151142984629
2023-01-22 17:35:43.407439: step: 2076/530, loss: 0.0001533506001578644
2023-01-22 17:35:44.459623: step: 2080/530, loss: 0.007181589026004076
2023-01-22 17:35:45.519353: step: 2084/530, loss: 9.24554933590116e-06
2023-01-22 17:35:46.575460: step: 2088/530, loss: 0.0080645140260458
2023-01-22 17:35:47.632176: step: 2092/530, loss: 0.00018640329653862864
2023-01-22 17:35:48.693279: step: 2096/530, loss: 0.006666557863354683
2023-01-22 17:35:49.750165: step: 2100/530, loss: 0.001275298185646534
2023-01-22 17:35:50.802261: step: 2104/530, loss: 0.0011793274898082018
2023-01-22 17:35:51.864981: step: 2108/530, loss: 0.0007606271537952125
2023-01-22 17:35:52.928352: step: 2112/530, loss: 0.0006227828562259674
2023-01-22 17:35:53.991878: step: 2116/530, loss: 0.00595064926892519
2023-01-22 17:35:55.048987: step: 2120/530, loss: 0.001748465234413743
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36159852651240015, 'r': 0.2874948436597641, 'f1': 0.32031666513466317}, 'combined': 0.23602280588869917, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35515529241745286, 'r': 0.236155207425631, 'f1': 0.28368098239896394}, 'combined': 0.18814075516615222, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32370273450178516, 'r': 0.29059677301864806, 'f1': 0.3062576769537848}, 'combined': 0.20417178463585653, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40122273621730786, 'r': 0.3182709767398541, 'f1': 0.3549650256741644}, 'combined': 0.23166138517682305, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3258721641912845, 'r': 0.3444227617733311, 'f1': 0.3348907665213016}, 'combined': 0.24676161743674854, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3592839822355278, 'r': 0.32973248586117704, 'f1': 0.3438745112141395}, 'combined': 0.2280618519969422, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.36237373737373735, 'r': 0.3416666666666666, 'f1': 0.3517156862745098}, 'combined': 0.2344771241830065, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.59375, 'r': 0.41304347826086957, 'f1': 0.4871794871794871}, 'combined': 0.32478632478632474, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:38:22.264732: step: 4/530, loss: 0.059192683547735214
2023-01-22 17:38:23.313891: step: 8/530, loss: 0.018978990614414215
2023-01-22 17:38:24.353173: step: 12/530, loss: 9.410739585291594e-05
2023-01-22 17:38:25.401155: step: 16/530, loss: 0.004438491538167
2023-01-22 17:38:26.448194: step: 20/530, loss: 0.006157925818115473
2023-01-22 17:38:27.501417: step: 24/530, loss: 0.018327059224247932
2023-01-22 17:38:28.546392: step: 28/530, loss: 0.00019550872093532234
2023-01-22 17:38:29.591482: step: 32/530, loss: 0.0012724412372335792
2023-01-22 17:38:30.651842: step: 36/530, loss: 0.002525192452594638
2023-01-22 17:38:31.708545: step: 40/530, loss: 0.001945075928233564
2023-01-22 17:38:32.771542: step: 44/530, loss: 0.0008830477017909288
2023-01-22 17:38:33.824411: step: 48/530, loss: 0.00800615455955267
2023-01-22 17:38:34.889083: step: 52/530, loss: 0.00035377449239604175
2023-01-22 17:38:35.962836: step: 56/530, loss: 0.0018717804923653603
2023-01-22 17:38:37.014382: step: 60/530, loss: 0.027395132929086685
2023-01-22 17:38:38.069176: step: 64/530, loss: 0.0031870929524302483
2023-01-22 17:38:39.118454: step: 68/530, loss: 0.00011143877782160416
2023-01-22 17:38:40.176594: step: 72/530, loss: 0.0002747525868471712
2023-01-22 17:38:41.228990: step: 76/530, loss: 0.000694293761625886
2023-01-22 17:38:42.303991: step: 80/530, loss: 0.00042259268229827285
2023-01-22 17:38:43.351749: step: 84/530, loss: 5.9114667237736285e-05
2023-01-22 17:38:44.416487: step: 88/530, loss: 0.004674218129366636
2023-01-22 17:38:45.469371: step: 92/530, loss: 0.052190858870744705
2023-01-22 17:38:46.531031: step: 96/530, loss: 0.00015036837430670857
2023-01-22 17:38:47.589284: step: 100/530, loss: 0.00038838229374960065
2023-01-22 17:38:48.647470: step: 104/530, loss: 0.0001253630471182987
2023-01-22 17:38:49.696028: step: 108/530, loss: 0.003455952275544405
2023-01-22 17:38:50.755172: step: 112/530, loss: 0.0035629766061902046
2023-01-22 17:38:51.818071: step: 116/530, loss: 0.001422525616362691
2023-01-22 17:38:52.889385: step: 120/530, loss: 0.0019508430268615484
2023-01-22 17:38:53.960534: step: 124/530, loss: 2.9280734452186152e-05
2023-01-22 17:38:55.008138: step: 128/530, loss: 0.0036827914882451296
2023-01-22 17:38:56.065675: step: 132/530, loss: 0.0029714140109717846
2023-01-22 17:38:57.140417: step: 136/530, loss: 0.0007055926253087819
2023-01-22 17:38:58.202172: step: 140/530, loss: 0.0022545759566128254
2023-01-22 17:38:59.265031: step: 144/530, loss: 0.0013193677878007293
2023-01-22 17:39:00.317594: step: 148/530, loss: 0.001877557602711022
2023-01-22 17:39:01.369994: step: 152/530, loss: 0.002412040950730443
2023-01-22 17:39:02.443380: step: 156/530, loss: 0.0014203011523932219
2023-01-22 17:39:03.494565: step: 160/530, loss: 0.0003093588165938854
2023-01-22 17:39:04.553888: step: 164/530, loss: 0.0015182859497144818
2023-01-22 17:39:05.612076: step: 168/530, loss: 0.0034255818463861942
2023-01-22 17:39:06.675153: step: 172/530, loss: 0.004508716054260731
2023-01-22 17:39:07.743428: step: 176/530, loss: 0.0077097536996006966
2023-01-22 17:39:08.792585: step: 180/530, loss: 0.0043347966857254505
2023-01-22 17:39:09.840543: step: 184/530, loss: 5.008099105907604e-05
2023-01-22 17:39:10.888897: step: 188/530, loss: 0.00194566382560879
2023-01-22 17:39:11.965716: step: 192/530, loss: 0.00796483177691698
2023-01-22 17:39:13.047341: step: 196/530, loss: 0.0011695085559040308
2023-01-22 17:39:14.107551: step: 200/530, loss: 0.0010574993211776018
2023-01-22 17:39:15.174820: step: 204/530, loss: 0.003104089293628931
2023-01-22 17:39:16.231420: step: 208/530, loss: 7.081463991198689e-05
2023-01-22 17:39:17.294329: step: 212/530, loss: 0.0027858209796249866
2023-01-22 17:39:18.352020: step: 216/530, loss: 6.906247290316969e-05
2023-01-22 17:39:19.417769: step: 220/530, loss: 0.00041725742630660534
2023-01-22 17:39:20.483998: step: 224/530, loss: 0.0024785296991467476
2023-01-22 17:39:21.554622: step: 228/530, loss: 3.743664638022892e-05
2023-01-22 17:39:22.636919: step: 232/530, loss: 0.0028732968494296074
2023-01-22 17:39:23.710520: step: 236/530, loss: 0.0007182710105553269
2023-01-22 17:39:24.777802: step: 240/530, loss: 0.00526081770658493
2023-01-22 17:39:25.838190: step: 244/530, loss: 0.00021167834347579628
2023-01-22 17:39:26.908542: step: 248/530, loss: 5.612459790427238e-05
2023-01-22 17:39:27.966454: step: 252/530, loss: 0.0019344433676451445
2023-01-22 17:39:29.023631: step: 256/530, loss: 0.0001750602386891842
2023-01-22 17:39:30.085920: step: 260/530, loss: 0.004162892699241638
2023-01-22 17:39:31.135373: step: 264/530, loss: 0.004696071147918701
2023-01-22 17:39:32.192220: step: 268/530, loss: 0.009673106484115124
2023-01-22 17:39:33.261145: step: 272/530, loss: 0.0001945290860021487
2023-01-22 17:39:34.322319: step: 276/530, loss: 0.0024551234673708677
2023-01-22 17:39:35.364476: step: 280/530, loss: 1.4490629837382585e-05
2023-01-22 17:39:36.438759: step: 284/530, loss: 0.006912935990840197
2023-01-22 17:39:37.511098: step: 288/530, loss: 0.0045605809427797794
2023-01-22 17:39:38.563058: step: 292/530, loss: 0.00010753023525467142
2023-01-22 17:39:39.646458: step: 296/530, loss: 0.002402425277978182
2023-01-22 17:39:40.710281: step: 300/530, loss: 0.004039755556732416
2023-01-22 17:39:41.783387: step: 304/530, loss: 0.0015180999180302024
2023-01-22 17:39:42.858905: step: 308/530, loss: 0.002066213171929121
2023-01-22 17:39:43.916676: step: 312/530, loss: 0.0009286271524615586
2023-01-22 17:39:44.999017: step: 316/530, loss: 0.0018390915356576443
2023-01-22 17:39:46.058842: step: 320/530, loss: 0.02612193487584591
2023-01-22 17:39:47.105704: step: 324/530, loss: 0.0024463869631290436
2023-01-22 17:39:48.171680: step: 328/530, loss: 0.00011146204633405432
2023-01-22 17:39:49.252652: step: 332/530, loss: 0.015038790181279182
2023-01-22 17:39:50.310776: step: 336/530, loss: 0.0002600799489300698
2023-01-22 17:39:51.377013: step: 340/530, loss: 0.0004936715704388916
2023-01-22 17:39:52.437373: step: 344/530, loss: 0.0001181312181870453
2023-01-22 17:39:53.491683: step: 348/530, loss: 0.0006630150019191206
2023-01-22 17:39:54.572061: step: 352/530, loss: 0.0006449768552556634
2023-01-22 17:39:55.635628: step: 356/530, loss: 0.00047739691217429936
2023-01-22 17:39:56.726659: step: 360/530, loss: 0.0056565250270068645
2023-01-22 17:39:57.788626: step: 364/530, loss: 0.026908257976174355
2023-01-22 17:39:58.860328: step: 368/530, loss: 0.015328820794820786
2023-01-22 17:39:59.904623: step: 372/530, loss: 0.0006343196728266776
2023-01-22 17:40:00.973557: step: 376/530, loss: 0.004836970940232277
2023-01-22 17:40:02.046999: step: 380/530, loss: 0.004707732703536749
2023-01-22 17:40:03.119312: step: 384/530, loss: 0.0003783739230129868
2023-01-22 17:40:04.176396: step: 388/530, loss: 0.001054164837114513
2023-01-22 17:40:05.248808: step: 392/530, loss: 3.850094071822241e-05
2023-01-22 17:40:06.300747: step: 396/530, loss: 0.00015232873556669801
2023-01-22 17:40:07.372898: step: 400/530, loss: 0.002443079836666584
2023-01-22 17:40:08.429779: step: 404/530, loss: 0.0010974782053381205
2023-01-22 17:40:09.481110: step: 408/530, loss: 0.0009960555471479893
2023-01-22 17:40:10.547772: step: 412/530, loss: 0.004391951486468315
2023-01-22 17:40:11.611745: step: 416/530, loss: 6.38125347904861e-05
2023-01-22 17:40:12.679675: step: 420/530, loss: 0.0028816601261496544
2023-01-22 17:40:13.732086: step: 424/530, loss: 2.3729235181235708e-05
2023-01-22 17:40:14.791847: step: 428/530, loss: 1.2100885214749724e-05
2023-01-22 17:40:15.849859: step: 432/530, loss: 0.006377737037837505
2023-01-22 17:40:16.915886: step: 436/530, loss: 0.00010560540977166966
2023-01-22 17:40:17.967612: step: 440/530, loss: 0.003498068079352379
2023-01-22 17:40:19.024227: step: 444/530, loss: 0.0036812257021665573
2023-01-22 17:40:20.076598: step: 448/530, loss: 0.0003007199557032436
2023-01-22 17:40:21.146207: step: 452/530, loss: 5.695580057363259e-06
2023-01-22 17:40:22.211872: step: 456/530, loss: 7.539513899246231e-05
2023-01-22 17:40:23.278900: step: 460/530, loss: 0.0001270364155061543
2023-01-22 17:40:24.343228: step: 464/530, loss: 0.0045892782509326935
2023-01-22 17:40:25.396015: step: 468/530, loss: 0.005200125277042389
2023-01-22 17:40:26.437237: step: 472/530, loss: 0.007242385298013687
2023-01-22 17:40:27.520047: step: 476/530, loss: 0.0016656728694215417
2023-01-22 17:40:28.595778: step: 480/530, loss: 0.003390140598639846
2023-01-22 17:40:29.659036: step: 484/530, loss: 0.00383104314096272
2023-01-22 17:40:30.708504: step: 488/530, loss: 0.0015725400298833847
2023-01-22 17:40:31.768084: step: 492/530, loss: 0.0016765035688877106
2023-01-22 17:40:32.842445: step: 496/530, loss: 3.927049419871764e-06
2023-01-22 17:40:33.907976: step: 500/530, loss: 0.00038760618190281093
2023-01-22 17:40:34.966639: step: 504/530, loss: 0.0019126972183585167
2023-01-22 17:40:36.016784: step: 508/530, loss: 3.307884526293492e-07
2023-01-22 17:40:37.074600: step: 512/530, loss: 0.0002243128401460126
2023-01-22 17:40:38.148197: step: 516/530, loss: 0.0016231201589107513
2023-01-22 17:40:39.212163: step: 520/530, loss: 0.00022361693845596164
2023-01-22 17:40:40.261403: step: 524/530, loss: 1.0578037290542852e-06
2023-01-22 17:40:41.344777: step: 528/530, loss: 0.000610057613812387
2023-01-22 17:40:42.430892: step: 532/530, loss: 0.02693955972790718
2023-01-22 17:40:43.496726: step: 536/530, loss: 0.0011799965286627412
2023-01-22 17:40:44.547579: step: 540/530, loss: 0.00018336896027904004
2023-01-22 17:40:45.623594: step: 544/530, loss: 0.0024420383851975203
2023-01-22 17:40:46.675601: step: 548/530, loss: 0.0002216171706095338
2023-01-22 17:40:47.747056: step: 552/530, loss: 0.00658275093883276
2023-01-22 17:40:48.808482: step: 556/530, loss: 0.003861658973619342
2023-01-22 17:40:49.859350: step: 560/530, loss: 5.7165570979123e-06
2023-01-22 17:40:50.914165: step: 564/530, loss: 0.00014908910088706762
2023-01-22 17:40:51.984932: step: 568/530, loss: 0.0011630464578047395
2023-01-22 17:40:53.028190: step: 572/530, loss: 0.0021871866192668676
2023-01-22 17:40:54.111121: step: 576/530, loss: 0.003597014583647251
2023-01-22 17:40:55.168597: step: 580/530, loss: 0.00036163374898023903
2023-01-22 17:40:56.229523: step: 584/530, loss: 0.0010645553702488542
2023-01-22 17:40:57.291532: step: 588/530, loss: 0.00039010285399854183
2023-01-22 17:40:58.337269: step: 592/530, loss: 0.00018555395945440978
2023-01-22 17:40:59.403840: step: 596/530, loss: 0.0017795072635635734
2023-01-22 17:41:00.460400: step: 600/530, loss: 0.0035783988423645496
2023-01-22 17:41:01.527976: step: 604/530, loss: 0.00029110696050338447
2023-01-22 17:41:02.587120: step: 608/530, loss: 1.0441685844853055e-05
2023-01-22 17:41:03.650224: step: 612/530, loss: 0.0014422353124246001
2023-01-22 17:41:04.708756: step: 616/530, loss: 0.0011893962509930134
2023-01-22 17:41:05.784127: step: 620/530, loss: 0.0061098914593458176
2023-01-22 17:41:06.835227: step: 624/530, loss: 0.0005330511485226452
2023-01-22 17:41:07.884820: step: 628/530, loss: 0.0008534502703696489
2023-01-22 17:41:08.928158: step: 632/530, loss: 0.0019492448773235083
2023-01-22 17:41:09.986507: step: 636/530, loss: 6.99654410709627e-05
2023-01-22 17:41:11.063847: step: 640/530, loss: 0.00010752879461506382
2023-01-22 17:41:12.131062: step: 644/530, loss: 0.004178246483206749
2023-01-22 17:41:13.190669: step: 648/530, loss: 6.285926065174863e-05
2023-01-22 17:41:14.256367: step: 652/530, loss: 0.0019955423194915056
2023-01-22 17:41:15.313560: step: 656/530, loss: 0.0033051460050046444
2023-01-22 17:41:16.355237: step: 660/530, loss: 0.0028750444762408733
2023-01-22 17:41:17.430494: step: 664/530, loss: 0.007834425196051598
2023-01-22 17:41:18.480670: step: 668/530, loss: 0.0015952582471072674
2023-01-22 17:41:19.540753: step: 672/530, loss: 0.013982315547764301
2023-01-22 17:41:20.595633: step: 676/530, loss: 0.0004253937513567507
2023-01-22 17:41:21.661585: step: 680/530, loss: 0.0013414053246378899
2023-01-22 17:41:22.737494: step: 684/530, loss: 0.0031976685859262943
2023-01-22 17:41:23.785379: step: 688/530, loss: 0.0023528647143393755
2023-01-22 17:41:24.836678: step: 692/530, loss: 0.00017307992675341666
2023-01-22 17:41:25.884255: step: 696/530, loss: 0.00038725489866919816
2023-01-22 17:41:26.936356: step: 700/530, loss: 0.000329225993482396
2023-01-22 17:41:28.000964: step: 704/530, loss: 0.0032823269721120596
2023-01-22 17:41:29.061738: step: 708/530, loss: 0.007279534358531237
2023-01-22 17:41:30.117697: step: 712/530, loss: 0.00010168641165364534
2023-01-22 17:41:31.174123: step: 716/530, loss: 0.0034339067060500383
2023-01-22 17:41:32.239266: step: 720/530, loss: 6.240996299311519e-05
2023-01-22 17:41:33.291264: step: 724/530, loss: 0.00193593162111938
2023-01-22 17:41:34.348482: step: 728/530, loss: 0.0016734879463911057
2023-01-22 17:41:35.416415: step: 732/530, loss: 0.0009187238174490631
2023-01-22 17:41:36.466881: step: 736/530, loss: 8.056082879193127e-05
2023-01-22 17:41:37.509133: step: 740/530, loss: 0.00010100848157890141
2023-01-22 17:41:38.587395: step: 744/530, loss: 8.939360122894868e-05
2023-01-22 17:41:39.636614: step: 748/530, loss: 0.0037521186750382185
2023-01-22 17:41:40.685783: step: 752/530, loss: 0.0014936678344383836
2023-01-22 17:41:41.745987: step: 756/530, loss: 0.0012043665628880262
2023-01-22 17:41:42.815807: step: 760/530, loss: 0.00025564085808582604
2023-01-22 17:41:43.860093: step: 764/530, loss: 0.000357006152626127
2023-01-22 17:41:44.915218: step: 768/530, loss: 0.00039656521403230727
2023-01-22 17:41:45.968219: step: 772/530, loss: 0.003564214101061225
2023-01-22 17:41:47.016436: step: 776/530, loss: 0.0007091726874932647
2023-01-22 17:41:48.063330: step: 780/530, loss: 0.003948886413127184
2023-01-22 17:41:49.113414: step: 784/530, loss: 0.00039099648711271584
2023-01-22 17:41:50.171387: step: 788/530, loss: 0.002238166518509388
2023-01-22 17:41:51.222884: step: 792/530, loss: 0.00766237685456872
2023-01-22 17:41:52.289331: step: 796/530, loss: 0.0028105962555855513
2023-01-22 17:41:53.341029: step: 800/530, loss: 0.00036568735959008336
2023-01-22 17:41:54.412285: step: 804/530, loss: 0.0015537930885329843
2023-01-22 17:41:55.456958: step: 808/530, loss: 0.005717322696000338
2023-01-22 17:41:56.502697: step: 812/530, loss: 0.0021680595818907022
2023-01-22 17:41:57.565697: step: 816/530, loss: 0.0010745642939582467
2023-01-22 17:41:58.619798: step: 820/530, loss: 0.00030915025854483247
2023-01-22 17:41:59.676735: step: 824/530, loss: 0.002057289471849799
2023-01-22 17:42:00.737009: step: 828/530, loss: 0.010349827818572521
2023-01-22 17:42:01.793230: step: 832/530, loss: 0.0056083351373672485
2023-01-22 17:42:02.864213: step: 836/530, loss: 0.0010183104313910007
2023-01-22 17:42:03.930044: step: 840/530, loss: 0.00018976262072101235
2023-01-22 17:42:04.985345: step: 844/530, loss: 0.0007217067177407444
2023-01-22 17:42:06.041736: step: 848/530, loss: 0.003354766871780157
2023-01-22 17:42:07.098162: step: 852/530, loss: 0.0035875998437404633
2023-01-22 17:42:08.155893: step: 856/530, loss: 3.900817682733759e-05
2023-01-22 17:42:09.220823: step: 860/530, loss: 1.2187253560114186e-05
2023-01-22 17:42:10.280169: step: 864/530, loss: 0.0016954968450590968
2023-01-22 17:42:11.336334: step: 868/530, loss: 0.00143439881503582
2023-01-22 17:42:12.404562: step: 872/530, loss: 0.0017256420105695724
2023-01-22 17:42:13.465897: step: 876/530, loss: 0.004252709448337555
2023-01-22 17:42:14.532895: step: 880/530, loss: 0.0013457630993798375
2023-01-22 17:42:15.606326: step: 884/530, loss: 0.0016396567225456238
2023-01-22 17:42:16.659256: step: 888/530, loss: 0.00033936084946617484
2023-01-22 17:42:17.697656: step: 892/530, loss: 0.0056954738683998585
2023-01-22 17:42:18.747104: step: 896/530, loss: 0.00223240302875638
2023-01-22 17:42:19.785958: step: 900/530, loss: 0.00028004436171613634
2023-01-22 17:42:20.856271: step: 904/530, loss: 0.002180548617616296
2023-01-22 17:42:21.908689: step: 908/530, loss: 3.755977377295494e-05
2023-01-22 17:42:22.997740: step: 912/530, loss: 0.0005344985402189195
2023-01-22 17:42:24.054413: step: 916/530, loss: 0.0016251313500106335
2023-01-22 17:42:25.101626: step: 920/530, loss: 3.0200213586795144e-05
2023-01-22 17:42:26.163375: step: 924/530, loss: 0.0026034389156848192
2023-01-22 17:42:27.209029: step: 928/530, loss: 3.562566689652158e-06
2023-01-22 17:42:28.248126: step: 932/530, loss: 0.002469759900122881
2023-01-22 17:42:29.287707: step: 936/530, loss: 0.0
2023-01-22 17:42:30.363671: step: 940/530, loss: 0.003475326346233487
2023-01-22 17:42:31.417708: step: 944/530, loss: 0.003895876230672002
2023-01-22 17:42:32.483866: step: 948/530, loss: 0.0014570595230907202
2023-01-22 17:42:33.536891: step: 952/530, loss: 0.0064370231702923775
2023-01-22 17:42:34.585860: step: 956/530, loss: 0.0008968209731392562
2023-01-22 17:42:35.657575: step: 960/530, loss: 0.004135685041546822
2023-01-22 17:42:36.727513: step: 964/530, loss: 0.0024486889597028494
2023-01-22 17:42:37.793751: step: 968/530, loss: 0.0005546585307456553
2023-01-22 17:42:38.870412: step: 972/530, loss: 0.002434910973533988
2023-01-22 17:42:39.916886: step: 976/530, loss: 0.0002758363843895495
2023-01-22 17:42:40.971956: step: 980/530, loss: 0.0034822560846805573
2023-01-22 17:42:42.042956: step: 984/530, loss: 0.005226087756454945
2023-01-22 17:42:43.091033: step: 988/530, loss: 0.01056690327823162
2023-01-22 17:42:44.156984: step: 992/530, loss: 0.006436006166040897
2023-01-22 17:42:45.215087: step: 996/530, loss: 0.002738002687692642
2023-01-22 17:42:46.275992: step: 1000/530, loss: 0.0009512731339782476
2023-01-22 17:42:47.330058: step: 1004/530, loss: 0.002380600431933999
2023-01-22 17:42:48.374191: step: 1008/530, loss: 0.0001242822763742879
2023-01-22 17:42:49.420120: step: 1012/530, loss: 5.010862878407352e-06
2023-01-22 17:42:50.479936: step: 1016/530, loss: 0.003960699774324894
2023-01-22 17:42:51.516260: step: 1020/530, loss: 0.00123043661005795
2023-01-22 17:42:52.599462: step: 1024/530, loss: 0.005833625327795744
2023-01-22 17:42:53.636168: step: 1028/530, loss: 0.0007101250812411308
2023-01-22 17:42:54.712349: step: 1032/530, loss: 0.00026671000523492694
2023-01-22 17:42:55.769160: step: 1036/530, loss: 0.0023285045754164457
2023-01-22 17:42:56.836333: step: 1040/530, loss: 0.003951370716094971
2023-01-22 17:42:57.882716: step: 1044/530, loss: 0.0002584291505627334
2023-01-22 17:42:58.937451: step: 1048/530, loss: 0.0021018036641180515
2023-01-22 17:43:00.005810: step: 1052/530, loss: 0.0052032009698450565
2023-01-22 17:43:01.047529: step: 1056/530, loss: 0.0011574843665584922
2023-01-22 17:43:02.130453: step: 1060/530, loss: 5.633717591990717e-05
2023-01-22 17:43:03.185783: step: 1064/530, loss: 0.005318668205291033
2023-01-22 17:43:04.230903: step: 1068/530, loss: 0.00034650444285944104
2023-01-22 17:43:05.295863: step: 1072/530, loss: 0.0007226613233797252
2023-01-22 17:43:06.342725: step: 1076/530, loss: 4.142200850765221e-05
2023-01-22 17:43:07.401623: step: 1080/530, loss: 1.4579084108845564e-06
2023-01-22 17:43:08.449006: step: 1084/530, loss: 0.01942112296819687
2023-01-22 17:43:09.494873: step: 1088/530, loss: 0.001533513073809445
2023-01-22 17:43:10.541639: step: 1092/530, loss: 0.004345688968896866
2023-01-22 17:43:11.601565: step: 1096/530, loss: 0.005718563683331013
2023-01-22 17:43:12.650292: step: 1100/530, loss: 8.072733908193186e-05
2023-01-22 17:43:13.697544: step: 1104/530, loss: 0.0013543821405619383
2023-01-22 17:43:14.772781: step: 1108/530, loss: 0.005944791249930859
2023-01-22 17:43:15.824249: step: 1112/530, loss: 0.0018408535979688168
2023-01-22 17:43:16.877535: step: 1116/530, loss: 0.003505851374939084
2023-01-22 17:43:17.928313: step: 1120/530, loss: 0.00042468865285627544
2023-01-22 17:43:19.005748: step: 1124/530, loss: 0.004140383563935757
2023-01-22 17:43:20.051063: step: 1128/530, loss: 0.0019997083581984043
2023-01-22 17:43:21.105972: step: 1132/530, loss: 0.0007268836488947272
2023-01-22 17:43:22.173675: step: 1136/530, loss: 0.0012896410189568996
2023-01-22 17:43:23.226221: step: 1140/530, loss: 0.00014028334408067167
2023-01-22 17:43:24.289425: step: 1144/530, loss: 0.0006800381815992296
2023-01-22 17:43:25.343399: step: 1148/530, loss: 9.279007713303145e-07
2023-01-22 17:43:26.397752: step: 1152/530, loss: 0.0012208139523863792
2023-01-22 17:43:27.446038: step: 1156/530, loss: 0.006226833909749985
2023-01-22 17:43:28.516999: step: 1160/530, loss: 0.014818019233644009
2023-01-22 17:43:29.570898: step: 1164/530, loss: 0.004462834447622299
2023-01-22 17:43:30.637116: step: 1168/530, loss: 0.00024710659636184573
2023-01-22 17:43:31.691293: step: 1172/530, loss: 0.0015258699422702193
2023-01-22 17:43:32.758316: step: 1176/530, loss: 0.0003391695208847523
2023-01-22 17:43:33.820319: step: 1180/530, loss: 0.001951267127878964
2023-01-22 17:43:34.875882: step: 1184/530, loss: 0.002194629516452551
2023-01-22 17:43:35.937685: step: 1188/530, loss: 0.0003462890163064003
2023-01-22 17:43:36.997989: step: 1192/530, loss: 0.00012193290604045615
2023-01-22 17:43:38.056145: step: 1196/530, loss: 0.0015159074682742357
2023-01-22 17:43:39.118355: step: 1200/530, loss: 0.009451931342482567
2023-01-22 17:43:40.185001: step: 1204/530, loss: 0.0008692930568940938
2023-01-22 17:43:41.236560: step: 1208/530, loss: 0.006785715464502573
2023-01-22 17:43:42.299352: step: 1212/530, loss: 5.553445953410119e-05
2023-01-22 17:43:43.354230: step: 1216/530, loss: 0.0009975282009691
2023-01-22 17:43:44.403000: step: 1220/530, loss: 0.017443593591451645
2023-01-22 17:43:45.471648: step: 1224/530, loss: 0.0062513891607522964
2023-01-22 17:43:46.539430: step: 1228/530, loss: 0.005552260670810938
2023-01-22 17:43:47.601678: step: 1232/530, loss: 0.005000651814043522
2023-01-22 17:43:48.649011: step: 1236/530, loss: 0.005314888432621956
2023-01-22 17:43:49.708460: step: 1240/530, loss: 0.0009264182881452143
2023-01-22 17:43:50.756854: step: 1244/530, loss: 0.0016931642312556505
2023-01-22 17:43:51.812139: step: 1248/530, loss: 0.003390031633898616
2023-01-22 17:43:52.860367: step: 1252/530, loss: 0.000913382216822356
2023-01-22 17:43:53.899176: step: 1256/530, loss: 5.861747558810748e-05
2023-01-22 17:43:54.966208: step: 1260/530, loss: 0.0018918963614851236
2023-01-22 17:43:56.014841: step: 1264/530, loss: 0.0035234461538493633
2023-01-22 17:43:57.079456: step: 1268/530, loss: 0.0037734070792794228
2023-01-22 17:43:58.122751: step: 1272/530, loss: 0.011028153821825981
2023-01-22 17:43:59.175974: step: 1276/530, loss: 0.011834010481834412
2023-01-22 17:44:00.232523: step: 1280/530, loss: 0.0032597710378468037
2023-01-22 17:44:01.302755: step: 1284/530, loss: 0.009212887845933437
2023-01-22 17:44:02.399984: step: 1288/530, loss: 0.001232433714903891
2023-01-22 17:44:03.463324: step: 1292/530, loss: 0.0013742693699896336
2023-01-22 17:44:04.507890: step: 1296/530, loss: 0.0017181668663397431
2023-01-22 17:44:05.556069: step: 1300/530, loss: 0.00022880798496771604
2023-01-22 17:44:06.597987: step: 1304/530, loss: 0.00033933110535144806
2023-01-22 17:44:07.652257: step: 1308/530, loss: 0.002581647364422679
2023-01-22 17:44:08.700615: step: 1312/530, loss: 0.000677432690281421
2023-01-22 17:44:09.752726: step: 1316/530, loss: 0.001540435361675918
2023-01-22 17:44:10.794945: step: 1320/530, loss: 0.0012464426690712571
2023-01-22 17:44:11.862937: step: 1324/530, loss: 0.0010704627493396401
2023-01-22 17:44:12.921384: step: 1328/530, loss: 0.003316232468932867
2023-01-22 17:44:13.975946: step: 1332/530, loss: 0.010116294026374817
2023-01-22 17:44:15.054692: step: 1336/530, loss: 0.000527312804479152
2023-01-22 17:44:16.106566: step: 1340/530, loss: 0.0008955479715950787
2023-01-22 17:44:17.158729: step: 1344/530, loss: 0.0014403837267309427
2023-01-22 17:44:18.208739: step: 1348/530, loss: 0.00608457624912262
2023-01-22 17:44:19.257738: step: 1352/530, loss: 0.00012017461995128542
2023-01-22 17:44:20.317552: step: 1356/530, loss: 0.005782244261354208
2023-01-22 17:44:21.373308: step: 1360/530, loss: 0.02346494235098362
2023-01-22 17:44:22.430556: step: 1364/530, loss: 0.0001532189198769629
2023-01-22 17:44:23.482364: step: 1368/530, loss: 0.002110595116391778
2023-01-22 17:44:24.560682: step: 1372/530, loss: 0.06614694744348526
2023-01-22 17:44:25.619371: step: 1376/530, loss: 1.986814446297558e-08
2023-01-22 17:44:26.694396: step: 1380/530, loss: 0.0025785844773054123
2023-01-22 17:44:27.764334: step: 1384/530, loss: 0.0021717411000281572
2023-01-22 17:44:28.838578: step: 1388/530, loss: 0.010472293943166733
2023-01-22 17:44:29.901363: step: 1392/530, loss: 0.001528059015981853
2023-01-22 17:44:30.945371: step: 1396/530, loss: 0.0036804266273975372
2023-01-22 17:44:31.978185: step: 1400/530, loss: 0.0016494496958330274
2023-01-22 17:44:33.058157: step: 1404/530, loss: 0.003875534050166607
2023-01-22 17:44:34.110963: step: 1408/530, loss: 7.9530400398653e-05
2023-01-22 17:44:35.151403: step: 1412/530, loss: 0.011152983643114567
2023-01-22 17:44:36.194007: step: 1416/530, loss: 0.0017858123173937201
2023-01-22 17:44:37.240570: step: 1420/530, loss: 0.0016966091934591532
2023-01-22 17:44:38.282556: step: 1424/530, loss: 0.0011043237755075097
2023-01-22 17:44:39.336658: step: 1428/530, loss: 0.0025296914391219616
2023-01-22 17:44:40.391174: step: 1432/530, loss: 0.0001698226697044447
2023-01-22 17:44:41.449226: step: 1436/530, loss: 0.0005540081183426082
2023-01-22 17:44:42.497685: step: 1440/530, loss: 0.0038423589430749416
2023-01-22 17:44:43.558648: step: 1444/530, loss: 0.0008583692833781242
2023-01-22 17:44:44.607568: step: 1448/530, loss: 0.002930636517703533
2023-01-22 17:44:45.648961: step: 1452/530, loss: 0.00040480177267454565
2023-01-22 17:44:46.709512: step: 1456/530, loss: 0.02402661181986332
2023-01-22 17:44:47.752644: step: 1460/530, loss: 1.8284675888935453e-06
2023-01-22 17:44:48.813341: step: 1464/530, loss: 0.00520919868722558
2023-01-22 17:44:49.854810: step: 1468/530, loss: 0.0003348229220137
2023-01-22 17:44:50.893280: step: 1472/530, loss: 0.0
2023-01-22 17:44:51.974192: step: 1476/530, loss: 0.021019157022237778
2023-01-22 17:44:53.033578: step: 1480/530, loss: 0.004463464021682739
2023-01-22 17:44:54.093338: step: 1484/530, loss: 0.0036678018514066935
2023-01-22 17:44:55.176057: step: 1488/530, loss: 0.03458976745605469
2023-01-22 17:44:56.222941: step: 1492/530, loss: 0.01479429379105568
2023-01-22 17:44:57.288602: step: 1496/530, loss: 0.011129218153655529
2023-01-22 17:44:58.340900: step: 1500/530, loss: 0.005471966695040464
2023-01-22 17:44:59.400496: step: 1504/530, loss: 0.012077328749001026
2023-01-22 17:45:00.455753: step: 1508/530, loss: 0.0044840550981462
2023-01-22 17:45:01.493400: step: 1512/530, loss: 0.00026452881866134703
2023-01-22 17:45:02.559990: step: 1516/530, loss: 0.00044833586434833705
2023-01-22 17:45:03.623722: step: 1520/530, loss: 0.000541728048119694
2023-01-22 17:45:04.666462: step: 1524/530, loss: 0.0007533407770097256
2023-01-22 17:45:05.723978: step: 1528/530, loss: 0.0
2023-01-22 17:45:06.779756: step: 1532/530, loss: 0.00019487006647977978
2023-01-22 17:45:07.826798: step: 1536/530, loss: 0.0006437512929551303
2023-01-22 17:45:08.880759: step: 1540/530, loss: 0.0014870183076709509
2023-01-22 17:45:09.935496: step: 1544/530, loss: 0.0015436818357557058
2023-01-22 17:45:10.979258: step: 1548/530, loss: 0.00519077992066741
2023-01-22 17:45:12.037011: step: 1552/530, loss: 0.0007815276039764285
2023-01-22 17:45:13.094908: step: 1556/530, loss: 0.003829352091997862
2023-01-22 17:45:14.150205: step: 1560/530, loss: 0.002531065372750163
2023-01-22 17:45:15.195492: step: 1564/530, loss: 0.0032826003152877092
2023-01-22 17:45:16.234299: step: 1568/530, loss: 0.0012569900136440992
2023-01-22 17:45:17.295884: step: 1572/530, loss: 0.0005269836401566863
2023-01-22 17:45:18.361891: step: 1576/530, loss: 0.0025522541254758835
2023-01-22 17:45:19.409474: step: 1580/530, loss: 0.0027215268928557634
2023-01-22 17:45:20.450579: step: 1584/530, loss: 0.0008277919259853661
2023-01-22 17:45:21.521587: step: 1588/530, loss: 0.00014382500376086682
2023-01-22 17:45:22.566256: step: 1592/530, loss: 0.002043931046500802
2023-01-22 17:45:23.614758: step: 1596/530, loss: 0.0010352483950555325
2023-01-22 17:45:24.677665: step: 1600/530, loss: 0.0022766483016312122
2023-01-22 17:45:25.736722: step: 1604/530, loss: 0.00511900894343853
2023-01-22 17:45:26.793851: step: 1608/530, loss: 0.0033122305758297443
2023-01-22 17:45:27.847730: step: 1612/530, loss: 0.0019924254156649113
2023-01-22 17:45:28.914196: step: 1616/530, loss: 0.0004986777203157544
2023-01-22 17:45:29.969981: step: 1620/530, loss: 8.124688406496716e-07
2023-01-22 17:45:31.028499: step: 1624/530, loss: 4.141549288760871e-05
2023-01-22 17:45:32.108124: step: 1628/530, loss: 0.001991770463064313
2023-01-22 17:45:33.151086: step: 1632/530, loss: 0.0001452805008739233
2023-01-22 17:45:34.223328: step: 1636/530, loss: 0.00014028162695467472
2023-01-22 17:45:35.280767: step: 1640/530, loss: 0.007117794826626778
2023-01-22 17:45:36.343643: step: 1644/530, loss: 0.007529959548264742
2023-01-22 17:45:37.404203: step: 1648/530, loss: 0.0012098860461264849
2023-01-22 17:45:38.454085: step: 1652/530, loss: 0.005414650775492191
2023-01-22 17:45:39.522694: step: 1656/530, loss: 0.005151515360921621
2023-01-22 17:45:40.579043: step: 1660/530, loss: 0.00044063912355341017
2023-01-22 17:45:41.659341: step: 1664/530, loss: 0.0018273539608344436
2023-01-22 17:45:42.725837: step: 1668/530, loss: 0.004269003868103027
2023-01-22 17:45:43.777705: step: 1672/530, loss: 0.0026084587443619967
2023-01-22 17:45:44.842746: step: 1676/530, loss: 0.0046369279734790325
2023-01-22 17:45:45.906761: step: 1680/530, loss: 0.003920101094990969
2023-01-22 17:45:46.971283: step: 1684/530, loss: 0.004268328659236431
2023-01-22 17:45:48.026942: step: 1688/530, loss: 0.0012724155094474554
2023-01-22 17:45:49.113942: step: 1692/530, loss: 0.00011943405115744099
2023-01-22 17:45:50.166359: step: 1696/530, loss: 0.00030443575815297663
2023-01-22 17:45:51.229036: step: 1700/530, loss: 0.007141844369471073
2023-01-22 17:45:52.288765: step: 1704/530, loss: 0.01584586687386036
2023-01-22 17:45:53.346584: step: 1708/530, loss: 0.0005249660462141037
2023-01-22 17:45:54.417639: step: 1712/530, loss: 0.0021053049713373184
2023-01-22 17:45:55.477420: step: 1716/530, loss: 0.003415602957829833
2023-01-22 17:45:56.536565: step: 1720/530, loss: 0.0027876971289515495
2023-01-22 17:45:57.590941: step: 1724/530, loss: 0.0023400920908898115
2023-01-22 17:45:58.631703: step: 1728/530, loss: 5.0695602112682536e-05
2023-01-22 17:45:59.690867: step: 1732/530, loss: 0.0014937978703528643
2023-01-22 17:46:00.742081: step: 1736/530, loss: 0.001036931062117219
2023-01-22 17:46:01.801111: step: 1740/530, loss: 0.001710493816062808
2023-01-22 17:46:02.878499: step: 1744/530, loss: 0.0009898740099743009
2023-01-22 17:46:03.916472: step: 1748/530, loss: 7.949067367007956e-05
2023-01-22 17:46:04.968123: step: 1752/530, loss: 0.0011929996544495225
2023-01-22 17:46:06.032738: step: 1756/530, loss: 0.018602391704916954
2023-01-22 17:46:07.093579: step: 1760/530, loss: 0.0025694086216390133
2023-01-22 17:46:08.169917: step: 1764/530, loss: 0.0025392230600118637
2023-01-22 17:46:09.220305: step: 1768/530, loss: 0.0021785683929920197
2023-01-22 17:46:10.284781: step: 1772/530, loss: 0.0007225180743262172
2023-01-22 17:46:11.337230: step: 1776/530, loss: 0.0017456581117585301
2023-01-22 17:46:12.385275: step: 1780/530, loss: 0.00014750612899661064
2023-01-22 17:46:13.439967: step: 1784/530, loss: 0.023750416934490204
2023-01-22 17:46:14.501596: step: 1788/530, loss: 0.010610049590468407
2023-01-22 17:46:15.599443: step: 1792/530, loss: 0.002239265711978078
2023-01-22 17:46:16.659022: step: 1796/530, loss: 0.0002765243989415467
2023-01-22 17:46:17.720016: step: 1800/530, loss: 0.0009584600920788944
2023-01-22 17:46:18.782037: step: 1804/530, loss: 0.0013351335655897856
2023-01-22 17:46:19.836266: step: 1808/530, loss: 0.0002709985710680485
2023-01-22 17:46:20.904668: step: 1812/530, loss: 0.008790990337729454
2023-01-22 17:46:21.961136: step: 1816/530, loss: 0.0031469326931983232
2023-01-22 17:46:22.998348: step: 1820/530, loss: 0.0008656151476316154
2023-01-22 17:46:24.051275: step: 1824/530, loss: 0.0007396457949653268
2023-01-22 17:46:25.097958: step: 1828/530, loss: 9.953258995665237e-05
2023-01-22 17:46:26.145670: step: 1832/530, loss: 0.017821967601776123
2023-01-22 17:46:27.196010: step: 1836/530, loss: 0.00010098525672219694
2023-01-22 17:46:28.277201: step: 1840/530, loss: 0.0051336647011339664
2023-01-22 17:46:29.339885: step: 1844/530, loss: 0.02245226874947548
2023-01-22 17:46:30.403001: step: 1848/530, loss: 0.006239595822989941
2023-01-22 17:46:31.452166: step: 1852/530, loss: 0.003103002905845642
2023-01-22 17:46:32.496573: step: 1856/530, loss: 0.012939448468387127
2023-01-22 17:46:33.559747: step: 1860/530, loss: 0.003480520797893405
2023-01-22 17:46:34.614201: step: 1864/530, loss: 0.005201444961130619
2023-01-22 17:46:35.671525: step: 1868/530, loss: 1.646712689762353e-06
2023-01-22 17:46:36.739466: step: 1872/530, loss: 0.0019753824453800917
2023-01-22 17:46:37.792817: step: 1876/530, loss: 0.0007966823759488761
2023-01-22 17:46:38.850518: step: 1880/530, loss: 0.004779266193509102
2023-01-22 17:46:39.900053: step: 1884/530, loss: 1.5865351087995805e-05
2023-01-22 17:46:40.960804: step: 1888/530, loss: 0.0030656461603939533
2023-01-22 17:46:42.005674: step: 1892/530, loss: 0.0031413172837346792
2023-01-22 17:46:43.075719: step: 1896/530, loss: 0.0026001152582466602
2023-01-22 17:46:44.122319: step: 1900/530, loss: 0.012475541792809963
2023-01-22 17:46:45.174825: step: 1904/530, loss: 0.002798421774059534
2023-01-22 17:46:46.245875: step: 1908/530, loss: 0.0011059010867029428
2023-01-22 17:46:47.297800: step: 1912/530, loss: 0.0032019491773098707
2023-01-22 17:46:48.360441: step: 1916/530, loss: 0.0014143269509077072
2023-01-22 17:46:49.421748: step: 1920/530, loss: 0.00516804214566946
2023-01-22 17:46:50.459709: step: 1924/530, loss: 0.0004980072844773531
2023-01-22 17:46:51.512168: step: 1928/530, loss: 0.0015539845917373896
2023-01-22 17:46:52.578049: step: 1932/530, loss: 0.007791064213961363
2023-01-22 17:46:53.637475: step: 1936/530, loss: 0.0029779367614537477
2023-01-22 17:46:54.680940: step: 1940/530, loss: 0.0002129616477759555
2023-01-22 17:46:55.730273: step: 1944/530, loss: 0.007697421591728926
2023-01-22 17:46:56.776895: step: 1948/530, loss: 8.336954124388285e-06
2023-01-22 17:46:57.823975: step: 1952/530, loss: 0.0
2023-01-22 17:46:58.900607: step: 1956/530, loss: 0.0016274317167699337
2023-01-22 17:46:59.947855: step: 1960/530, loss: 0.00016795731789898127
2023-01-22 17:47:01.000756: step: 1964/530, loss: 0.001051002531312406
2023-01-22 17:47:02.072600: step: 1968/530, loss: 5.956008317298256e-05
2023-01-22 17:47:03.112656: step: 1972/530, loss: 1.7269834643229842e-05
2023-01-22 17:47:04.156598: step: 1976/530, loss: 0.010293925181031227
2023-01-22 17:47:05.219284: step: 1980/530, loss: 2.021647378569469e-05
2023-01-22 17:47:06.287111: step: 1984/530, loss: 0.0010774305555969477
2023-01-22 17:47:07.333296: step: 1988/530, loss: 0.004185184836387634
2023-01-22 17:47:08.382568: step: 1992/530, loss: 0.0008530158083885908
2023-01-22 17:47:09.423320: step: 1996/530, loss: 0.00020995458180550486
2023-01-22 17:47:10.478148: step: 2000/530, loss: 0.0014600830618292093
2023-01-22 17:47:11.521328: step: 2004/530, loss: 0.010365885682404041
2023-01-22 17:47:12.588155: step: 2008/530, loss: 0.003824816783890128
2023-01-22 17:47:13.635432: step: 2012/530, loss: 0.00023553035862278193
2023-01-22 17:47:14.690537: step: 2016/530, loss: 0.0018162557389587164
2023-01-22 17:47:15.750694: step: 2020/530, loss: 1.6719199265935458e-05
2023-01-22 17:47:16.805765: step: 2024/530, loss: 0.002557012252509594
2023-01-22 17:47:17.865283: step: 2028/530, loss: 0.001878247712738812
2023-01-22 17:47:18.911927: step: 2032/530, loss: 0.0002744736848399043
2023-01-22 17:47:19.984006: step: 2036/530, loss: 0.0069994451478123665
2023-01-22 17:47:21.040931: step: 2040/530, loss: 0.00042627903167158365
2023-01-22 17:47:22.109172: step: 2044/530, loss: 0.0028313985094428062
2023-01-22 17:47:23.197547: step: 2048/530, loss: 0.008968052454292774
2023-01-22 17:47:24.240069: step: 2052/530, loss: 0.001041926210746169
2023-01-22 17:47:25.292420: step: 2056/530, loss: 0.0017015936318784952
2023-01-22 17:47:26.343011: step: 2060/530, loss: 2.1103512608533492e-06
2023-01-22 17:47:27.407072: step: 2064/530, loss: 0.0004375509452074766
2023-01-22 17:47:28.473726: step: 2068/530, loss: 0.0010493847075849771
2023-01-22 17:47:29.532199: step: 2072/530, loss: 0.00040845919284038246
2023-01-22 17:47:30.587633: step: 2076/530, loss: 0.0014651058008894324
2023-01-22 17:47:31.648551: step: 2080/530, loss: 0.0030638158787041903
2023-01-22 17:47:32.708397: step: 2084/530, loss: 0.00020849764405284077
2023-01-22 17:47:33.767973: step: 2088/530, loss: 0.00010747854685178027
2023-01-22 17:47:34.819082: step: 2092/530, loss: 0.0007673745276406407
2023-01-22 17:47:35.876814: step: 2096/530, loss: 9.36534779611975e-05
2023-01-22 17:47:36.945049: step: 2100/530, loss: 0.00384254171513021
2023-01-22 17:47:38.000607: step: 2104/530, loss: 0.013815202750265598
2023-01-22 17:47:39.079228: step: 2108/530, loss: 0.0030671143904328346
2023-01-22 17:47:40.147794: step: 2112/530, loss: 0.00277753546833992
2023-01-22 17:47:41.210904: step: 2116/530, loss: 0.007929054088890553
2023-01-22 17:47:42.257198: step: 2120/530, loss: 1.8626433728741176e-08
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.363118530020704, 'r': 0.2893923768665952, 'f1': 0.32209035397823793}, 'combined': 0.23732973451028055, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35196008386571925, 'r': 0.23464005591047948, 'f1': 0.28156806709257537}, 'combined': 0.18673944346036084, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.324329991816694, 'r': 0.2887028336247086, 'f1': 0.30548115461692615}, 'combined': 0.20365410307795076, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.39981203929487114, 'r': 0.3192270867380329, 'f1': 0.3550038598067975}, 'combined': 0.23168672955812045, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32228149991839405, 'r': 0.3406276953596688, 'f1': 0.33120072962093267}, 'combined': 0.24404264287858196, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3581682529790033, 'r': 0.32994893607762726, 'f1': 0.3434799650019464}, 'combined': 0.2278001840427416, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 17
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:50:12.034637: step: 4/530, loss: 0.0003250110021326691
2023-01-22 17:50:13.077971: step: 8/530, loss: 0.00010327000927645713
2023-01-22 17:50:14.125374: step: 12/530, loss: 0.0029094081837683916
2023-01-22 17:50:15.213761: step: 16/530, loss: 0.0
2023-01-22 17:50:16.253678: step: 20/530, loss: 0.00045091984793543816
2023-01-22 17:50:17.308684: step: 24/530, loss: 0.00033032710780389607
2023-01-22 17:50:18.350793: step: 28/530, loss: 0.0015701358206570148
2023-01-22 17:50:19.395756: step: 32/530, loss: 0.0036558376159518957
2023-01-22 17:50:20.443727: step: 36/530, loss: 2.623400359880179e-05
2023-01-22 17:50:21.503654: step: 40/530, loss: 0.00898011028766632
2023-01-22 17:50:22.543698: step: 44/530, loss: 0.0030468327458947897
2023-01-22 17:50:23.599428: step: 48/530, loss: 0.0067582339979708195
2023-01-22 17:50:24.643516: step: 52/530, loss: 0.0015654424205422401
2023-01-22 17:50:25.695333: step: 56/530, loss: 6.553632556460798e-05
2023-01-22 17:50:26.758480: step: 60/530, loss: 0.001344228396192193
2023-01-22 17:50:27.825297: step: 64/530, loss: 0.006579705514013767
2023-01-22 17:50:28.883053: step: 68/530, loss: 0.003154532518237829
2023-01-22 17:50:29.932083: step: 72/530, loss: 0.0008696566219441593
2023-01-22 17:50:30.977818: step: 76/530, loss: 0.033768150955438614
2023-01-22 17:50:32.015987: step: 80/530, loss: 7.055199375827215e-07
2023-01-22 17:50:33.051923: step: 84/530, loss: 0.00012695426994469017
2023-01-22 17:50:34.101489: step: 88/530, loss: 0.00019828276708722115
2023-01-22 17:50:35.164705: step: 92/530, loss: 9.579466131981462e-05
2023-01-22 17:50:36.232955: step: 96/530, loss: 0.00297187315300107
2023-01-22 17:50:37.284351: step: 100/530, loss: 0.0022006661165505648
2023-01-22 17:50:38.336861: step: 104/530, loss: 0.007217789068818092
2023-01-22 17:50:39.401729: step: 108/530, loss: 4.5530872739618644e-05
2023-01-22 17:50:40.443943: step: 112/530, loss: 1.4114721125224605e-05
2023-01-22 17:50:41.515820: step: 116/530, loss: 0.020827410742640495
2023-01-22 17:50:42.566694: step: 120/530, loss: 0.00043991932761855423
2023-01-22 17:50:43.642263: step: 124/530, loss: 0.008572726510465145
2023-01-22 17:50:44.686258: step: 128/530, loss: 0.0016485165106132627
2023-01-22 17:50:45.732424: step: 132/530, loss: 0.001300851465202868
2023-01-22 17:50:46.807290: step: 136/530, loss: 0.010175375267863274
2023-01-22 17:50:47.874186: step: 140/530, loss: 0.004779119044542313
2023-01-22 17:50:48.932205: step: 144/530, loss: 0.0004490238206926733
2023-01-22 17:50:49.993305: step: 148/530, loss: 0.0074737402610480785
2023-01-22 17:50:51.035764: step: 152/530, loss: 0.0009050205117091537
2023-01-22 17:50:52.088468: step: 156/530, loss: 0.0025042006745934486
2023-01-22 17:50:53.165539: step: 160/530, loss: 0.00015788176096975803
2023-01-22 17:50:54.232180: step: 164/530, loss: 0.004179377108812332
2023-01-22 17:50:55.307891: step: 168/530, loss: 0.006657128222286701
2023-01-22 17:50:56.375570: step: 172/530, loss: 0.0011968639446422458
2023-01-22 17:50:57.433201: step: 176/530, loss: 0.0019788455683737993
2023-01-22 17:50:58.492438: step: 180/530, loss: 0.004991799592971802
2023-01-22 17:50:59.550571: step: 184/530, loss: 0.003967749420553446
2023-01-22 17:51:00.604703: step: 188/530, loss: 0.000524609989952296
2023-01-22 17:51:01.657478: step: 192/530, loss: 0.0030326517298817635
2023-01-22 17:51:02.720059: step: 196/530, loss: 0.008878742344677448
2023-01-22 17:51:03.786031: step: 200/530, loss: 1.5498861102969386e-05
2023-01-22 17:51:04.837859: step: 204/530, loss: 0.0052151451818645
2023-01-22 17:51:05.891214: step: 208/530, loss: 0.0016239526448771358
2023-01-22 17:51:06.952986: step: 212/530, loss: 0.011361966840922832
2023-01-22 17:51:08.012330: step: 216/530, loss: 0.0081169493496418
2023-01-22 17:51:09.090689: step: 220/530, loss: 8.157993579516187e-05
2023-01-22 17:51:10.147171: step: 224/530, loss: 0.0002733671572059393
2023-01-22 17:51:11.213715: step: 228/530, loss: 0.0023612172808498144
2023-01-22 17:51:12.274150: step: 232/530, loss: 0.00019490058184601367
2023-01-22 17:51:13.347336: step: 236/530, loss: 0.0022635594941675663
2023-01-22 17:51:14.407225: step: 240/530, loss: 0.02954304963350296
2023-01-22 17:51:15.466711: step: 244/530, loss: 0.00023685931228101254
2023-01-22 17:51:16.531936: step: 248/530, loss: 0.0036271577700972557
2023-01-22 17:51:17.593404: step: 252/530, loss: 0.00201923749409616
2023-01-22 17:51:18.651082: step: 256/530, loss: 0.0019371494418010116
2023-01-22 17:51:19.723915: step: 260/530, loss: 0.00025146856205537915
2023-01-22 17:51:20.793454: step: 264/530, loss: 0.00024632373242639005
2023-01-22 17:51:21.841560: step: 268/530, loss: 0.012415675446391106
2023-01-22 17:51:22.893927: step: 272/530, loss: 0.0007977241184562445
2023-01-22 17:51:23.953154: step: 276/530, loss: 0.003661759663373232
2023-01-22 17:51:25.000540: step: 280/530, loss: 0.0016316329129040241
2023-01-22 17:51:26.056575: step: 284/530, loss: 0.005037873983383179
2023-01-22 17:51:27.103806: step: 288/530, loss: 0.00019436987349763513
2023-01-22 17:51:28.159952: step: 292/530, loss: 0.0022037222515791655
2023-01-22 17:51:29.211254: step: 296/530, loss: 1.2144417269155383e-05
2023-01-22 17:51:30.283185: step: 300/530, loss: 0.011175122112035751
2023-01-22 17:51:31.350857: step: 304/530, loss: 0.00039242859929800034
2023-01-22 17:51:32.416759: step: 308/530, loss: 0.004104190971702337
2023-01-22 17:51:33.488083: step: 312/530, loss: 0.0014982802094891667
2023-01-22 17:51:34.545689: step: 316/530, loss: 0.0002822606184054166
2023-01-22 17:51:35.612866: step: 320/530, loss: 0.0031672792974859476
2023-01-22 17:51:36.677654: step: 324/530, loss: 0.0014289245009422302
2023-01-22 17:51:37.739045: step: 328/530, loss: 0.0023983647115528584
2023-01-22 17:51:38.794021: step: 332/530, loss: 0.00016546070401091129
2023-01-22 17:51:39.853330: step: 336/530, loss: 0.0037717868108302355
2023-01-22 17:51:40.913675: step: 340/530, loss: 4.238985184201738e-06
2023-01-22 17:51:41.969731: step: 344/530, loss: 0.0024787706788629293
2023-01-22 17:51:43.036447: step: 348/530, loss: 0.001191026996821165
2023-01-22 17:51:44.112990: step: 352/530, loss: 0.0031788628548383713
2023-01-22 17:51:45.179649: step: 356/530, loss: 0.00018072384409606457
2023-01-22 17:51:46.245825: step: 360/530, loss: 0.031905610114336014
2023-01-22 17:51:47.308699: step: 364/530, loss: 0.0008393478346988559
2023-01-22 17:51:48.366813: step: 368/530, loss: 7.809021917637438e-05
2023-01-22 17:51:49.428920: step: 372/530, loss: 0.0009407387115061283
2023-01-22 17:51:50.486879: step: 376/530, loss: 0.0018041894072666764
2023-01-22 17:51:51.537904: step: 380/530, loss: 0.0010646820301190019
2023-01-22 17:51:52.607749: step: 384/530, loss: 0.0005362660740502179
2023-01-22 17:51:53.659423: step: 388/530, loss: 0.0017718817107379436
2023-01-22 17:51:54.738790: step: 392/530, loss: 0.001660363283008337
2023-01-22 17:51:55.805666: step: 396/530, loss: 4.280201028450392e-05
2023-01-22 17:51:56.853713: step: 400/530, loss: 0.0001180175386252813
2023-01-22 17:51:57.939186: step: 404/530, loss: 0.0034996657632291317
2023-01-22 17:51:59.009602: step: 408/530, loss: 0.0009065588237717748
2023-01-22 17:52:00.067835: step: 412/530, loss: 0.00014249492960516363
2023-01-22 17:52:01.123715: step: 416/530, loss: 0.007452043239027262
2023-01-22 17:52:02.194028: step: 420/530, loss: 3.975400613853708e-05
2023-01-22 17:52:03.253043: step: 424/530, loss: 0.0002114443777827546
2023-01-22 17:52:04.312909: step: 428/530, loss: 0.0010021415073424578
2023-01-22 17:52:05.366431: step: 432/530, loss: 0.0009182122303172946
2023-01-22 17:52:06.409879: step: 436/530, loss: 0.0015905495965853333
2023-01-22 17:52:07.472915: step: 440/530, loss: 0.0002427100553177297
2023-01-22 17:52:08.536273: step: 444/530, loss: 0.0030908097978681326
2023-01-22 17:52:09.584809: step: 448/530, loss: 0.008275626227259636
2023-01-22 17:52:10.656790: step: 452/530, loss: 0.0020911593455821276
2023-01-22 17:52:11.718436: step: 456/530, loss: 0.002013309160247445
2023-01-22 17:52:12.776058: step: 460/530, loss: 0.0005033549969084561
2023-01-22 17:52:13.828992: step: 464/530, loss: 0.001824121573008597
2023-01-22 17:52:14.895328: step: 468/530, loss: 0.003075605956837535
2023-01-22 17:52:15.960102: step: 472/530, loss: 0.002276838291436434
2023-01-22 17:52:17.017332: step: 476/530, loss: 0.006126571912318468
2023-01-22 17:52:18.068269: step: 480/530, loss: 0.003306641010567546
2023-01-22 17:52:19.125765: step: 484/530, loss: 0.0016706627793610096
2023-01-22 17:52:20.180989: step: 488/530, loss: 0.0010184097336605191
2023-01-22 17:52:21.221177: step: 492/530, loss: 0.0007417145534418523
2023-01-22 17:52:22.271794: step: 496/530, loss: 0.0032276702113449574
2023-01-22 17:52:23.325108: step: 500/530, loss: 0.0046856035478413105
2023-01-22 17:52:24.383326: step: 504/530, loss: 0.008639886043965816
2023-01-22 17:52:25.426285: step: 508/530, loss: 0.0005481612170115113
2023-01-22 17:52:26.479876: step: 512/530, loss: 0.008955665864050388
2023-01-22 17:52:27.529490: step: 516/530, loss: 0.0035444090608507395
2023-01-22 17:52:28.577298: step: 520/530, loss: 0.0004243760777171701
2023-01-22 17:52:29.626104: step: 524/530, loss: 0.0027096732519567013
2023-01-22 17:52:30.705304: step: 528/530, loss: 0.0042732576839625835
2023-01-22 17:52:31.764872: step: 532/530, loss: 0.002493184059858322
2023-01-22 17:52:32.829716: step: 536/530, loss: 0.0014989409828558564
2023-01-22 17:52:33.896022: step: 540/530, loss: 0.0009775498183444142
2023-01-22 17:52:34.948482: step: 544/530, loss: 0.003676595399156213
2023-01-22 17:52:36.001938: step: 548/530, loss: 0.0009262002422474325
2023-01-22 17:52:37.060259: step: 552/530, loss: 0.0005359672359190881
2023-01-22 17:52:38.112531: step: 556/530, loss: 3.6649249523179606e-05
2023-01-22 17:52:39.183579: step: 560/530, loss: 0.001422971487045288
2023-01-22 17:52:40.230051: step: 564/530, loss: 0.00014482016558758914
2023-01-22 17:52:41.273935: step: 568/530, loss: 8.522219286533073e-05
2023-01-22 17:52:42.336161: step: 572/530, loss: 0.00022604662808589637
2023-01-22 17:52:43.401868: step: 576/530, loss: 7.563818508060649e-05
2023-01-22 17:52:44.469387: step: 580/530, loss: 0.007900391705334187
2023-01-22 17:52:45.535437: step: 584/530, loss: 0.0036498778499662876
2023-01-22 17:52:46.610227: step: 588/530, loss: 0.0059960526414215565
2023-01-22 17:52:47.663902: step: 592/530, loss: 2.7462847356218845e-06
2023-01-22 17:52:48.719565: step: 596/530, loss: 0.001986027229577303
2023-01-22 17:52:49.768480: step: 600/530, loss: 0.0006223671953193843
2023-01-22 17:52:50.832147: step: 604/530, loss: 0.0006608201656490564
2023-01-22 17:52:51.891826: step: 608/530, loss: 0.002817604225128889
2023-01-22 17:52:52.956023: step: 612/530, loss: 0.0049211266450583935
2023-01-22 17:52:54.011076: step: 616/530, loss: 0.0011279383907094598
2023-01-22 17:52:55.065300: step: 620/530, loss: 0.0017556088278070092
2023-01-22 17:52:56.131685: step: 624/530, loss: 0.0036397427320480347
2023-01-22 17:52:57.197992: step: 628/530, loss: 0.0012460562866181135
2023-01-22 17:52:58.246880: step: 632/530, loss: 0.0012989867245778441
2023-01-22 17:52:59.304871: step: 636/530, loss: 0.010031579062342644
2023-01-22 17:53:00.368990: step: 640/530, loss: 0.00268359063193202
2023-01-22 17:53:01.444735: step: 644/530, loss: 0.0002749410050455481
2023-01-22 17:53:02.496801: step: 648/530, loss: 1.8663156708953466e-07
2023-01-22 17:53:03.553349: step: 652/530, loss: 2.0861405403138633e-07
2023-01-22 17:53:04.607343: step: 656/530, loss: 0.0016519913915544748
2023-01-22 17:53:05.674741: step: 660/530, loss: 0.00027360403328202665
2023-01-22 17:53:06.720719: step: 664/530, loss: 0.0020784749649465084
2023-01-22 17:53:07.766099: step: 668/530, loss: 0.001132887788116932
2023-01-22 17:53:08.821570: step: 672/530, loss: 8.980271377367899e-05
2023-01-22 17:53:09.886374: step: 676/530, loss: 0.003592818509787321
2023-01-22 17:53:10.961555: step: 680/530, loss: 0.0014212786918506026
2023-01-22 17:53:12.021384: step: 684/530, loss: 0.00031213992042467
2023-01-22 17:53:13.081754: step: 688/530, loss: 0.007671969477087259
2023-01-22 17:53:14.137866: step: 692/530, loss: 0.0007366955396719277
2023-01-22 17:53:15.199055: step: 696/530, loss: 0.007115547079592943
2023-01-22 17:53:16.258712: step: 700/530, loss: 0.001698613865301013
2023-01-22 17:53:17.330960: step: 704/530, loss: 0.002809738740324974
2023-01-22 17:53:18.404881: step: 708/530, loss: 2.667678563739173e-05
2023-01-22 17:53:19.458719: step: 712/530, loss: 0.0002682785561773926
2023-01-22 17:53:20.514814: step: 716/530, loss: 0.003121049841865897
2023-01-22 17:53:21.564406: step: 720/530, loss: 0.0020823145750910044
2023-01-22 17:53:22.633384: step: 724/530, loss: 0.001403205911628902
2023-01-22 17:53:23.712066: step: 728/530, loss: 0.0034690317697823048
2023-01-22 17:53:24.763879: step: 732/530, loss: 0.0003169336123391986
2023-01-22 17:53:25.836369: step: 736/530, loss: 0.0003119395696558058
2023-01-22 17:53:26.885106: step: 740/530, loss: 0.0017081854166463017
2023-01-22 17:53:27.947185: step: 744/530, loss: 0.001549523905850947
2023-01-22 17:53:29.011644: step: 748/530, loss: 3.537727388902567e-05
2023-01-22 17:53:30.086094: step: 752/530, loss: 0.004651418887078762
2023-01-22 17:53:31.147029: step: 756/530, loss: 0.005748758092522621
2023-01-22 17:53:32.210540: step: 760/530, loss: 0.003338283160701394
2023-01-22 17:53:33.274060: step: 764/530, loss: 0.002226133830845356
2023-01-22 17:53:34.340975: step: 768/530, loss: 3.279270822531544e-05
2023-01-22 17:53:35.400811: step: 772/530, loss: 0.0009650117135606706
2023-01-22 17:53:36.469600: step: 776/530, loss: 0.05621209368109703
2023-01-22 17:53:37.524379: step: 780/530, loss: 0.007143400609493256
2023-01-22 17:53:38.589534: step: 784/530, loss: 0.0015492329839617014
2023-01-22 17:53:39.663065: step: 788/530, loss: 4.681041173171252e-05
2023-01-22 17:53:40.716732: step: 792/530, loss: 0.0003306333674117923
2023-01-22 17:53:41.779290: step: 796/530, loss: 0.00036596370046027005
2023-01-22 17:53:42.833581: step: 800/530, loss: 0.00041176885133609176
2023-01-22 17:53:43.882578: step: 804/530, loss: 0.0019819489680230618
2023-01-22 17:53:44.940977: step: 808/530, loss: 0.00010756034316727892
2023-01-22 17:53:46.003198: step: 812/530, loss: 0.007222232408821583
2023-01-22 17:53:47.057391: step: 816/530, loss: 0.0004381787439342588
2023-01-22 17:53:48.112906: step: 820/530, loss: 0.0014265939826145768
2023-01-22 17:53:49.177635: step: 824/530, loss: 0.0034175862092524767
2023-01-22 17:53:50.241547: step: 828/530, loss: 0.0007666954770684242
2023-01-22 17:53:51.297749: step: 832/530, loss: 0.0026328640524297953
2023-01-22 17:53:52.371839: step: 836/530, loss: 0.0005103026051074266
2023-01-22 17:53:53.416010: step: 840/530, loss: 0.0021974763367325068
2023-01-22 17:53:54.476235: step: 844/530, loss: 0.0075005535036325455
2023-01-22 17:53:55.539882: step: 848/530, loss: 0.006352907046675682
2023-01-22 17:53:56.583528: step: 852/530, loss: 0.001549455919303
2023-01-22 17:53:57.645382: step: 856/530, loss: 0.0029803344514220953
2023-01-22 17:53:58.695658: step: 860/530, loss: 0.0010252937208861113
2023-01-22 17:53:59.755797: step: 864/530, loss: 6.62251768517308e-05
2023-01-22 17:54:00.802124: step: 868/530, loss: 0.0002176843408960849
2023-01-22 17:54:01.869682: step: 872/530, loss: 0.003625124227255583
2023-01-22 17:54:02.938915: step: 876/530, loss: 0.0008013990591280162
2023-01-22 17:54:03.994134: step: 880/530, loss: 0.00041871133726090193
2023-01-22 17:54:05.051971: step: 884/530, loss: 0.00020458332437556237
2023-01-22 17:54:06.127807: step: 888/530, loss: 5.5012726079439744e-05
2023-01-22 17:54:07.186061: step: 892/530, loss: 0.00031431164825335145
2023-01-22 17:54:08.254806: step: 896/530, loss: 0.0017172252992168069
2023-01-22 17:54:09.318922: step: 900/530, loss: 0.0024885099846869707
2023-01-22 17:54:10.371604: step: 904/530, loss: 0.0006603936199098825
2023-01-22 17:54:11.422434: step: 908/530, loss: 0.0005029587191529572
2023-01-22 17:54:12.487832: step: 912/530, loss: 0.0034463279880583286
2023-01-22 17:54:13.534591: step: 916/530, loss: 0.0029321303591132164
2023-01-22 17:54:14.583216: step: 920/530, loss: 0.007881742902100086
2023-01-22 17:54:15.645406: step: 924/530, loss: 0.0015492836246266961
2023-01-22 17:54:16.716420: step: 928/530, loss: 0.003039595205336809
2023-01-22 17:54:17.784450: step: 932/530, loss: 0.005576764233410358
2023-01-22 17:54:18.837059: step: 936/530, loss: 0.0055366335436701775
2023-01-22 17:54:19.889633: step: 940/530, loss: 0.0007363850600086153
2023-01-22 17:54:20.949262: step: 944/530, loss: 0.007611500099301338
2023-01-22 17:54:21.996940: step: 948/530, loss: 0.001019624643959105
2023-01-22 17:54:23.064249: step: 952/530, loss: 0.001155313802883029
2023-01-22 17:54:24.112449: step: 956/530, loss: 0.002034812467172742
2023-01-22 17:54:25.160189: step: 960/530, loss: 0.0004842204798478633
2023-01-22 17:54:26.229850: step: 964/530, loss: 6.876084626128431e-06
2023-01-22 17:54:27.279894: step: 968/530, loss: 0.0028653740882873535
2023-01-22 17:54:28.335654: step: 972/530, loss: 0.0021431182976812124
2023-01-22 17:54:29.374924: step: 976/530, loss: 0.00021729804575443268
2023-01-22 17:54:30.431352: step: 980/530, loss: 0.0007025641389191151
2023-01-22 17:54:31.497801: step: 984/530, loss: 0.005403316579759121
2023-01-22 17:54:32.566078: step: 988/530, loss: 7.84470648795832e-06
2023-01-22 17:54:33.621851: step: 992/530, loss: 0.003874309593811631
2023-01-22 17:54:34.676178: step: 996/530, loss: 0.0016382955946028233
2023-01-22 17:54:35.742681: step: 1000/530, loss: 0.0020589837804436684
2023-01-22 17:54:36.799246: step: 1004/530, loss: 0.0018492179224267602
2023-01-22 17:54:37.852552: step: 1008/530, loss: 5.34553182660602e-05
2023-01-22 17:54:38.909923: step: 1012/530, loss: 0.0030979823786765337
2023-01-22 17:54:39.952575: step: 1016/530, loss: 0.00023496735957451165
2023-01-22 17:54:41.010754: step: 1020/530, loss: 0.0012345234863460064
2023-01-22 17:54:42.055281: step: 1024/530, loss: 0.002092586364597082
2023-01-22 17:54:43.124956: step: 1028/530, loss: 0.0019468979444354773
2023-01-22 17:54:44.183872: step: 1032/530, loss: 0.001180277089588344
2023-01-22 17:54:45.240980: step: 1036/530, loss: 9.015834802994505e-05
2023-01-22 17:54:46.297907: step: 1040/530, loss: 0.012760174460709095
2023-01-22 17:54:47.369099: step: 1044/530, loss: 0.0012736788485199213
2023-01-22 17:54:48.455369: step: 1048/530, loss: 0.0026498460210859776
2023-01-22 17:54:49.517590: step: 1052/530, loss: 3.430072183618904e-06
2023-01-22 17:54:50.554199: step: 1056/530, loss: 0.002392443595454097
2023-01-22 17:54:51.616092: step: 1060/530, loss: 0.004322984255850315
2023-01-22 17:54:52.672472: step: 1064/530, loss: 0.0024266396649181843
2023-01-22 17:54:53.721494: step: 1068/530, loss: 0.00026486036949791014
2023-01-22 17:54:54.768068: step: 1072/530, loss: 0.0005378081696107984
2023-01-22 17:54:55.820001: step: 1076/530, loss: 6.746695726178586e-05
2023-01-22 17:54:56.875417: step: 1080/530, loss: 0.0024029582273215055
2023-01-22 17:54:57.947208: step: 1084/530, loss: 0.000427486898843199
2023-01-22 17:54:59.001902: step: 1088/530, loss: 2.8370410291245207e-05
2023-01-22 17:55:00.042284: step: 1092/530, loss: 0.00019718451949302107
2023-01-22 17:55:01.106823: step: 1096/530, loss: 0.0018824022263288498
2023-01-22 17:55:02.155675: step: 1100/530, loss: 5.85204288654495e-05
2023-01-22 17:55:03.197773: step: 1104/530, loss: 2.7342852604306245e-07
2023-01-22 17:55:04.255234: step: 1108/530, loss: 0.006888635456562042
2023-01-22 17:55:05.320283: step: 1112/530, loss: 0.000852369936183095
2023-01-22 17:55:06.358515: step: 1116/530, loss: 0.0003036827838514
2023-01-22 17:55:07.423443: step: 1120/530, loss: 0.0032860341016203165
2023-01-22 17:55:08.493339: step: 1124/530, loss: 0.01569513976573944
2023-01-22 17:55:09.536149: step: 1128/530, loss: 0.0033217757008969784
2023-01-22 17:55:10.613678: step: 1132/530, loss: 0.001954219304025173
2023-01-22 17:55:11.673816: step: 1136/530, loss: 0.006013811100274324
2023-01-22 17:55:12.742798: step: 1140/530, loss: 0.013793780468404293
2023-01-22 17:55:13.804177: step: 1144/530, loss: 0.0009063066099770367
2023-01-22 17:55:14.866717: step: 1148/530, loss: 0.003874919842928648
2023-01-22 17:55:15.938530: step: 1152/530, loss: 0.004496643785387278
2023-01-22 17:55:16.983071: step: 1156/530, loss: 0.001483607105910778
2023-01-22 17:55:18.037413: step: 1160/530, loss: 0.020650101825594902
2023-01-22 17:55:19.077634: step: 1164/530, loss: 0.00012711789167951792
2023-01-22 17:55:20.136056: step: 1168/530, loss: 0.0057564121671020985
2023-01-22 17:55:21.205268: step: 1172/530, loss: 9.468714415561408e-05
2023-01-22 17:55:22.259657: step: 1176/530, loss: 0.0037629269063472748
2023-01-22 17:55:23.323718: step: 1180/530, loss: 0.0032165481243282557
2023-01-22 17:55:24.370750: step: 1184/530, loss: 0.0007219966500997543
2023-01-22 17:55:25.416378: step: 1188/530, loss: 0.0012121982872486115
2023-01-22 17:55:26.465571: step: 1192/530, loss: 0.0017229666700586677
2023-01-22 17:55:27.519980: step: 1196/530, loss: 4.226937107887352e-06
2023-01-22 17:55:28.579637: step: 1200/530, loss: 0.0009013205417431891
2023-01-22 17:55:29.631637: step: 1204/530, loss: 0.0018238970078527927
2023-01-22 17:55:30.689818: step: 1208/530, loss: 0.01084953173995018
2023-01-22 17:55:31.741278: step: 1212/530, loss: 9.311814210377634e-05
2023-01-22 17:55:32.802122: step: 1216/530, loss: 0.00024655534070916474
2023-01-22 17:55:33.850209: step: 1220/530, loss: 0.007411518599838018
2023-01-22 17:55:34.908173: step: 1224/530, loss: 0.004581660032272339
2023-01-22 17:55:35.997574: step: 1228/530, loss: 0.0025393676478415728
2023-01-22 17:55:37.057558: step: 1232/530, loss: 0.00494487676769495
2023-01-22 17:55:38.126601: step: 1236/530, loss: 0.00782996416091919
2023-01-22 17:55:39.180435: step: 1240/530, loss: 0.0075223809108138084
2023-01-22 17:55:40.227903: step: 1244/530, loss: 0.0014412979362532496
2023-01-22 17:55:41.279330: step: 1248/530, loss: 0.0028542662039399147
2023-01-22 17:55:42.351757: step: 1252/530, loss: 0.0012522474862635136
2023-01-22 17:55:43.410779: step: 1256/530, loss: 0.0010438697645440698
2023-01-22 17:55:44.478596: step: 1260/530, loss: 0.0018528149230405688
2023-01-22 17:55:45.539679: step: 1264/530, loss: 0.0036280627828091383
2023-01-22 17:55:46.605773: step: 1268/530, loss: 0.005273927003145218
2023-01-22 17:55:47.670379: step: 1272/530, loss: 0.015992240980267525
2023-01-22 17:55:48.729845: step: 1276/530, loss: 0.005024413578212261
2023-01-22 17:55:49.787564: step: 1280/530, loss: 0.01363756787031889
2023-01-22 17:55:50.852854: step: 1284/530, loss: 0.009442714974284172
2023-01-22 17:55:51.911653: step: 1288/530, loss: 0.0003609588020481169
2023-01-22 17:55:52.959918: step: 1292/530, loss: 0.0020176107063889503
2023-01-22 17:55:54.022252: step: 1296/530, loss: 0.00019862435874529183
2023-01-22 17:55:55.068974: step: 1300/530, loss: 0.00012516188144218177
2023-01-22 17:55:56.130422: step: 1304/530, loss: 0.0028694551438093185
2023-01-22 17:55:57.163396: step: 1308/530, loss: 0.0004534932959359139
2023-01-22 17:55:58.219307: step: 1312/530, loss: 0.0034714879002422094
2023-01-22 17:55:59.324497: step: 1316/530, loss: 0.003963474649935961
2023-01-22 17:56:00.374973: step: 1320/530, loss: 0.005531396716833115
2023-01-22 17:56:01.418709: step: 1324/530, loss: 0.0017692631809040904
2023-01-22 17:56:02.481234: step: 1328/530, loss: 0.004140998236835003
2023-01-22 17:56:03.538148: step: 1332/530, loss: 0.00028991670114919543
2023-01-22 17:56:04.594907: step: 1336/530, loss: 0.0005217614816501737
2023-01-22 17:56:05.671194: step: 1340/530, loss: 0.001401195302605629
2023-01-22 17:56:06.724985: step: 1344/530, loss: 0.0015678979689255357
2023-01-22 17:56:07.798468: step: 1348/530, loss: 0.019129017367959023
2023-01-22 17:56:08.856949: step: 1352/530, loss: 0.005313987378031015
2023-01-22 17:56:09.914514: step: 1356/530, loss: 0.00037107185926288366
2023-01-22 17:56:10.983077: step: 1360/530, loss: 0.013496131636202335
2023-01-22 17:56:12.046764: step: 1364/530, loss: 0.013313413597643375
2023-01-22 17:56:13.086403: step: 1368/530, loss: 0.0002980967110488564
2023-01-22 17:56:14.166657: step: 1372/530, loss: 0.003133540041744709
2023-01-22 17:56:15.206763: step: 1376/530, loss: 0.0021681066136807203
2023-01-22 17:56:16.262764: step: 1380/530, loss: 0.0034840391017496586
2023-01-22 17:56:17.329257: step: 1384/530, loss: 0.001007427810691297
2023-01-22 17:56:18.388772: step: 1388/530, loss: 0.00429577799513936
2023-01-22 17:56:19.449186: step: 1392/530, loss: 0.0018511416856199503
2023-01-22 17:56:20.494349: step: 1396/530, loss: 0.0013401811011135578
2023-01-22 17:56:21.543467: step: 1400/530, loss: 0.0040626623667776585
2023-01-22 17:56:22.608559: step: 1404/530, loss: 0.018888691440224648
2023-01-22 17:56:23.647368: step: 1408/530, loss: 1.6510579371242784e-05
2023-01-22 17:56:24.708827: step: 1412/530, loss: 4.73581712867599e-05
2023-01-22 17:56:25.756960: step: 1416/530, loss: 0.0003874922695104033
2023-01-22 17:56:26.821001: step: 1420/530, loss: 0.0016836185241118073
2023-01-22 17:56:27.868419: step: 1424/530, loss: 0.003717202227562666
2023-01-22 17:56:28.937817: step: 1428/530, loss: 0.0021370332688093185
2023-01-22 17:56:29.981735: step: 1432/530, loss: 0.000662588223349303
2023-01-22 17:56:31.027531: step: 1436/530, loss: 0.00035708450013771653
2023-01-22 17:56:32.107556: step: 1440/530, loss: 0.0006263340474106371
2023-01-22 17:56:33.161940: step: 1444/530, loss: 8.564797462895513e-05
2023-01-22 17:56:34.202688: step: 1448/530, loss: 0.00959504023194313
2023-01-22 17:56:35.263947: step: 1452/530, loss: 8.74536344781518e-05
2023-01-22 17:56:36.315272: step: 1456/530, loss: 0.0033525987528264523
2023-01-22 17:56:37.366136: step: 1460/530, loss: 0.0035980045795440674
2023-01-22 17:56:38.418427: step: 1464/530, loss: 0.0029600048437714577
2023-01-22 17:56:39.494702: step: 1468/530, loss: 0.004253932274878025
2023-01-22 17:56:40.564043: step: 1472/530, loss: 0.05450672283768654
2023-01-22 17:56:41.623899: step: 1476/530, loss: 0.0010646131122484803
2023-01-22 17:56:42.668541: step: 1480/530, loss: 0.0006881079752929509
2023-01-22 17:56:43.712683: step: 1484/530, loss: 0.01149194035679102
2023-01-22 17:56:44.777400: step: 1488/530, loss: 0.00024345077690668404
2023-01-22 17:56:45.833359: step: 1492/530, loss: 0.0002043069980572909
2023-01-22 17:56:46.880510: step: 1496/530, loss: 0.0013637623051181436
2023-01-22 17:56:47.937577: step: 1500/530, loss: 0.014276815578341484
2023-01-22 17:56:49.005441: step: 1504/530, loss: 0.04338778555393219
2023-01-22 17:56:50.053829: step: 1508/530, loss: 3.986604860983789e-05
2023-01-22 17:56:51.118682: step: 1512/530, loss: 7.127715070964769e-05
2023-01-22 17:56:52.190083: step: 1516/530, loss: 0.0028541740030050278
2023-01-22 17:56:53.267335: step: 1520/530, loss: 0.00022994137543719262
2023-01-22 17:56:54.311599: step: 1524/530, loss: 0.00358932395465672
2023-01-22 17:56:55.364490: step: 1528/530, loss: 0.004346812143921852
2023-01-22 17:56:56.432124: step: 1532/530, loss: 0.004899824503809214
2023-01-22 17:56:57.487675: step: 1536/530, loss: 0.006737318355590105
2023-01-22 17:56:58.546003: step: 1540/530, loss: 0.004996676463633776
2023-01-22 17:56:59.610873: step: 1544/530, loss: 0.002813290571793914
2023-01-22 17:57:00.673060: step: 1548/530, loss: 0.006961551960557699
2023-01-22 17:57:01.719517: step: 1552/530, loss: 4.238111068843864e-05
2023-01-22 17:57:02.794592: step: 1556/530, loss: 0.010405754670500755
2023-01-22 17:57:03.856994: step: 1560/530, loss: 0.0030532919336110353
2023-01-22 17:57:04.925618: step: 1564/530, loss: 0.0027179024182260036
2023-01-22 17:57:06.004935: step: 1568/530, loss: 0.001679647364653647
2023-01-22 17:57:07.056947: step: 1572/530, loss: 0.0047917854972183704
2023-01-22 17:57:08.116893: step: 1576/530, loss: 0.00747528625652194
2023-01-22 17:57:09.201668: step: 1580/530, loss: 0.003177801612764597
2023-01-22 17:57:10.250373: step: 1584/530, loss: 2.820929694280494e-05
2023-01-22 17:57:11.309522: step: 1588/530, loss: 0.00019561413500923663
2023-01-22 17:57:12.362326: step: 1592/530, loss: 0.00038614243385381997
2023-01-22 17:57:13.442465: step: 1596/530, loss: 0.0035345363430678844
2023-01-22 17:57:14.497429: step: 1600/530, loss: 0.00246001360937953
2023-01-22 17:57:15.554451: step: 1604/530, loss: 0.0001315363188041374
2023-01-22 17:57:16.614873: step: 1608/530, loss: 0.0019230565521866083
2023-01-22 17:57:17.675500: step: 1612/530, loss: 0.0019322532461956143
2023-01-22 17:57:18.732316: step: 1616/530, loss: 0.0010026090312749147
2023-01-22 17:57:19.797182: step: 1620/530, loss: 0.004481487907469273
2023-01-22 17:57:20.851622: step: 1624/530, loss: 2.8371416192385368e-05
2023-01-22 17:57:21.913210: step: 1628/530, loss: 0.0006140859331935644
2023-01-22 17:57:22.972771: step: 1632/530, loss: 0.0018426628084853292
2023-01-22 17:57:24.046827: step: 1636/530, loss: 0.0007340333540923893
2023-01-22 17:57:25.107976: step: 1640/530, loss: 0.0005867245490662754
2023-01-22 17:57:26.162712: step: 1644/530, loss: 0.004103363025933504
2023-01-22 17:57:27.219581: step: 1648/530, loss: 0.0010689737973734736
2023-01-22 17:57:28.269751: step: 1652/530, loss: 0.0013210683828219771
2023-01-22 17:57:29.323154: step: 1656/530, loss: 0.004026887938380241
2023-01-22 17:57:30.386058: step: 1660/530, loss: 0.005119039677083492
2023-01-22 17:57:31.440825: step: 1664/530, loss: 0.0027865655720233917
2023-01-22 17:57:32.526995: step: 1668/530, loss: 0.004173601046204567
2023-01-22 17:57:33.580570: step: 1672/530, loss: 0.00014177977573126554
2023-01-22 17:57:34.625373: step: 1676/530, loss: 7.248708425322548e-05
2023-01-22 17:57:35.679290: step: 1680/530, loss: 0.0018180040642619133
2023-01-22 17:57:36.742940: step: 1684/530, loss: 0.002683144062757492
2023-01-22 17:57:37.802275: step: 1688/530, loss: 0.002299362327903509
2023-01-22 17:57:38.884986: step: 1692/530, loss: 0.00463888980448246
2023-01-22 17:57:39.945371: step: 1696/530, loss: 0.005600419361144304
2023-01-22 17:57:40.995505: step: 1700/530, loss: 0.00019638679805211723
2023-01-22 17:57:42.052351: step: 1704/530, loss: 0.0021644234657287598
2023-01-22 17:57:43.104430: step: 1708/530, loss: 0.03413008898496628
2023-01-22 17:57:44.157326: step: 1712/530, loss: 0.001362007693387568
2023-01-22 17:57:45.211124: step: 1716/530, loss: 0.0007608101004734635
2023-01-22 17:57:46.287086: step: 1720/530, loss: 0.0023260891903191805
2023-01-22 17:57:47.347731: step: 1724/530, loss: 0.00019812978280242532
2023-01-22 17:57:48.412069: step: 1728/530, loss: 0.00020771523122675717
2023-01-22 17:57:49.460438: step: 1732/530, loss: 0.003942670300602913
2023-01-22 17:57:50.503569: step: 1736/530, loss: 0.0027706718537956476
2023-01-22 17:57:51.584516: step: 1740/530, loss: 0.00036004491266794503
2023-01-22 17:57:52.638947: step: 1744/530, loss: 0.0038998809177428484
2023-01-22 17:57:53.706796: step: 1748/530, loss: 0.0010251781204715371
2023-01-22 17:57:54.755604: step: 1752/530, loss: 0.0075123608112335205
2023-01-22 17:57:55.823437: step: 1756/530, loss: 0.003972136415541172
2023-01-22 17:57:56.890777: step: 1760/530, loss: 0.007886619307100773
2023-01-22 17:57:57.931794: step: 1764/530, loss: 0.006952735595405102
2023-01-22 17:57:58.975763: step: 1768/530, loss: 0.0053995330817997456
2023-01-22 17:58:00.032304: step: 1772/530, loss: 0.010685128159821033
2023-01-22 17:58:01.086572: step: 1776/530, loss: 0.00011691226973198354
2023-01-22 17:58:02.154220: step: 1780/530, loss: 1.5086674238773412e-06
2023-01-22 17:58:03.199228: step: 1784/530, loss: 0.005432500038295984
2023-01-22 17:58:04.256744: step: 1788/530, loss: 3.687410207930952e-05
2023-01-22 17:58:05.329661: step: 1792/530, loss: 0.0005185672198422253
2023-01-22 17:58:06.380314: step: 1796/530, loss: 0.0019357283599674702
2023-01-22 17:58:07.435242: step: 1800/530, loss: 0.01091307494789362
2023-01-22 17:58:08.491449: step: 1804/530, loss: 0.007589819375425577
2023-01-22 17:58:09.545480: step: 1808/530, loss: 0.013362376019358635
2023-01-22 17:58:10.615538: step: 1812/530, loss: 0.0018293482717126608
2023-01-22 17:58:11.670219: step: 1816/530, loss: 0.0003368749166838825
2023-01-22 17:58:12.739964: step: 1820/530, loss: 0.004391562193632126
2023-01-22 17:58:13.796378: step: 1824/530, loss: 0.0012822910211980343
2023-01-22 17:58:14.851402: step: 1828/530, loss: 0.00024131685495376587
2023-01-22 17:58:15.907470: step: 1832/530, loss: 0.010517972521483898
2023-01-22 17:58:16.983290: step: 1836/530, loss: 0.0025146042462438345
2023-01-22 17:58:18.055864: step: 1840/530, loss: 0.001509475172497332
2023-01-22 17:58:19.123078: step: 1844/530, loss: 0.005089438054710627
2023-01-22 17:58:20.177552: step: 1848/530, loss: 8.90941282705171e-06
2023-01-22 17:58:21.230131: step: 1852/530, loss: 0.002184090204536915
2023-01-22 17:58:22.291749: step: 1856/530, loss: 0.0047272187657654285
2023-01-22 17:58:23.335208: step: 1860/530, loss: 9.413125371793285e-05
2023-01-22 17:58:24.388735: step: 1864/530, loss: 0.008647437207400799
2023-01-22 17:58:25.464166: step: 1868/530, loss: 0.0008382656960748136
2023-01-22 17:58:26.512061: step: 1872/530, loss: 6.864711758680642e-05
2023-01-22 17:58:27.554471: step: 1876/530, loss: 0.004007184877991676
2023-01-22 17:58:28.604922: step: 1880/530, loss: 0.0005845247651450336
2023-01-22 17:58:29.653868: step: 1884/530, loss: 0.0008356075850315392
2023-01-22 17:58:30.706408: step: 1888/530, loss: 0.00012236642942298204
2023-01-22 17:58:31.777815: step: 1892/530, loss: 0.0055170198902487755
2023-01-22 17:58:32.829801: step: 1896/530, loss: 0.000331994699081406
2023-01-22 17:58:33.878343: step: 1900/530, loss: 0.000142114789923653
2023-01-22 17:58:34.913445: step: 1904/530, loss: 0.0016532046720385551
2023-01-22 17:58:35.976290: step: 1908/530, loss: 7.965428267198149e-06
2023-01-22 17:58:37.041121: step: 1912/530, loss: 0.004498992580920458
2023-01-22 17:58:38.106608: step: 1916/530, loss: 0.0007155256462283432
2023-01-22 17:58:39.173634: step: 1920/530, loss: 0.00512723159044981
2023-01-22 17:58:40.228087: step: 1924/530, loss: 0.00016985174443107098
2023-01-22 17:58:41.282798: step: 1928/530, loss: 0.005829189904034138
2023-01-22 17:58:42.335066: step: 1932/530, loss: 0.009337147697806358
2023-01-22 17:58:43.395184: step: 1936/530, loss: 0.00381950824521482
2023-01-22 17:58:44.454951: step: 1940/530, loss: 7.528157584602013e-05
2023-01-22 17:58:45.504328: step: 1944/530, loss: 0.0036042584106326103
2023-01-22 17:58:46.575165: step: 1948/530, loss: 7.970676233526319e-05
2023-01-22 17:58:47.635344: step: 1952/530, loss: 0.0019424905767664313
2023-01-22 17:58:48.683374: step: 1956/530, loss: 0.0010044575901702046
2023-01-22 17:58:49.733636: step: 1960/530, loss: 6.521415343740955e-06
2023-01-22 17:58:50.788792: step: 1964/530, loss: 0.0030489973723888397
2023-01-22 17:58:51.839673: step: 1968/530, loss: 0.004461432341486216
2023-01-22 17:58:52.883948: step: 1972/530, loss: 4.626946247299202e-05
2023-01-22 17:58:53.952844: step: 1976/530, loss: 0.0030204516369849443
2023-01-22 17:58:55.001337: step: 1980/530, loss: 0.001155806239694357
2023-01-22 17:58:56.059150: step: 1984/530, loss: 0.00499724643304944
2023-01-22 17:58:57.124892: step: 1988/530, loss: 0.003911454696208239
2023-01-22 17:58:58.180020: step: 1992/530, loss: 0.0007650654297322035
2023-01-22 17:58:59.241856: step: 1996/530, loss: 1.7457738067605533e-05
2023-01-22 17:59:00.294892: step: 2000/530, loss: 0.0015691019361838698
2023-01-22 17:59:01.362051: step: 2004/530, loss: 0.009454813785851002
2023-01-22 17:59:02.418747: step: 2008/530, loss: 0.0009072218672372401
2023-01-22 17:59:03.480846: step: 2012/530, loss: 0.0026456110645085573
2023-01-22 17:59:04.534042: step: 2016/530, loss: 0.0021392330527305603
2023-01-22 17:59:05.591711: step: 2020/530, loss: 0.009899473749101162
2023-01-22 17:59:06.644484: step: 2024/530, loss: 0.00014786029350943863
2023-01-22 17:59:07.710212: step: 2028/530, loss: 0.005883692763745785
2023-01-22 17:59:08.767182: step: 2032/530, loss: 0.00018104046466760337
2023-01-22 17:59:09.819302: step: 2036/530, loss: 0.005610117223113775
2023-01-22 17:59:10.885290: step: 2040/530, loss: 0.049600813537836075
2023-01-22 17:59:11.945183: step: 2044/530, loss: 0.0004004179500043392
2023-01-22 17:59:12.993890: step: 2048/530, loss: 0.00449847336858511
2023-01-22 17:59:14.035781: step: 2052/530, loss: 0.00216514035128057
2023-01-22 17:59:15.100108: step: 2056/530, loss: 0.00015487248310819268
2023-01-22 17:59:16.155165: step: 2060/530, loss: 0.0025290220510214567
2023-01-22 17:59:17.226611: step: 2064/530, loss: 0.0018151961266994476
2023-01-22 17:59:18.291882: step: 2068/530, loss: 0.005314223002642393
2023-01-22 17:59:19.341039: step: 2072/530, loss: 1.5052189155539963e-05
2023-01-22 17:59:20.387430: step: 2076/530, loss: 0.004058415070176125
2023-01-22 17:59:21.447812: step: 2080/530, loss: 0.0026998277753591537
2023-01-22 17:59:22.496625: step: 2084/530, loss: 0.005886686034500599
2023-01-22 17:59:23.547746: step: 2088/530, loss: 3.8928203139221296e-05
2023-01-22 17:59:24.585744: step: 2092/530, loss: 3.731488322955556e-05
2023-01-22 17:59:25.637350: step: 2096/530, loss: 0.008258545771241188
2023-01-22 17:59:26.690802: step: 2100/530, loss: 0.01345754973590374
2023-01-22 17:59:27.745103: step: 2104/530, loss: 0.0013605003478005528
2023-01-22 17:59:28.804811: step: 2108/530, loss: 0.00012094646808691323
2023-01-22 17:59:29.854254: step: 2112/530, loss: 0.008695867843925953
2023-01-22 17:59:30.917345: step: 2116/530, loss: 0.0035952930338680744
2023-01-22 17:59:31.985771: step: 2120/530, loss: 0.003573654219508171
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3633328120112606, 'r': 0.2874948436597641, 'f1': 0.3209953021370671}, 'combined': 0.23652285420625996, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3520329394740597, 'r': 0.23377425504467864, 'f1': 0.28096697666660125}, 'combined': 0.1863407928151552, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3282198212235526, 'r': 0.2915437427156177, 'f1': 0.30879658205385385}, 'combined': 0.20586438803590257, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.40112803546062203, 'r': 0.31576687912557616, 'f1': 0.3533654523418838}, 'combined': 0.23061745310733467, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3240267065966525, 'r': 0.3406276953596688, 'f1': 0.33211988058195274}, 'combined': 0.24471991200775464, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3607497830992033, 'r': 0.3295160356447268, 'f1': 0.34442626350195427}, 'combined': 0.22842778097538932, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6785714285714286, 'r': 0.41304347826086957, 'f1': 0.5135135135135135}, 'combined': 0.3423423423423423, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 18
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:01:57.248308: step: 4/530, loss: 0.001752302865497768
2023-01-22 18:01:58.316241: step: 8/530, loss: 0.0016389511292800307
2023-01-22 18:01:59.374573: step: 12/530, loss: 0.006602039095014334
2023-01-22 18:02:00.443728: step: 16/530, loss: 0.0006128773675300181
2023-01-22 18:02:01.493334: step: 20/530, loss: 0.0015524306800216436
2023-01-22 18:02:02.557149: step: 24/530, loss: 0.001283848425373435
2023-01-22 18:02:03.616434: step: 28/530, loss: 0.00037966444506309927
2023-01-22 18:02:04.675605: step: 32/530, loss: 0.040175192058086395
2023-01-22 18:02:05.734684: step: 36/530, loss: 0.0063542937859892845
2023-01-22 18:02:06.798406: step: 40/530, loss: 0.0001701469300314784
2023-01-22 18:02:07.866039: step: 44/530, loss: 3.2335567084373906e-05
2023-01-22 18:02:08.923177: step: 48/530, loss: 0.020908227190375328
2023-01-22 18:02:09.978488: step: 52/530, loss: 2.1651270799338818e-05
2023-01-22 18:02:11.044336: step: 56/530, loss: 0.0004686538886744529
2023-01-22 18:02:12.100121: step: 60/530, loss: 0.018815917894244194
2023-01-22 18:02:13.146758: step: 64/530, loss: 0.0006118938326835632
2023-01-22 18:02:14.196825: step: 68/530, loss: 0.01032250840216875
2023-01-22 18:02:15.239342: step: 72/530, loss: 0.005057737696915865
2023-01-22 18:02:16.287313: step: 76/530, loss: 0.0005119513371028006
2023-01-22 18:02:17.336994: step: 80/530, loss: 0.013875901699066162
2023-01-22 18:02:18.385658: step: 84/530, loss: 0.007181371096521616
2023-01-22 18:02:19.435629: step: 88/530, loss: 0.009162049740552902
2023-01-22 18:02:20.490389: step: 92/530, loss: 0.00541257718577981
2023-01-22 18:02:21.544428: step: 96/530, loss: 0.0005214555421844125
2023-01-22 18:02:22.617350: step: 100/530, loss: 1.9868207079554168e-09
2023-01-22 18:02:23.669340: step: 104/530, loss: 0.005176474805921316
2023-01-22 18:02:24.742493: step: 108/530, loss: 0.0151984179392457
2023-01-22 18:02:25.797915: step: 112/530, loss: 0.003376663662493229
2023-01-22 18:02:26.862005: step: 116/530, loss: 0.0008604144095443189
2023-01-22 18:02:27.916657: step: 120/530, loss: 7.793185795890167e-05
2023-01-22 18:02:28.966069: step: 124/530, loss: 4.572741119091006e-08
2023-01-22 18:02:30.016694: step: 128/530, loss: 0.0053338948637247086
2023-01-22 18:02:31.082779: step: 132/530, loss: 0.004737090785056353
2023-01-22 18:02:32.158182: step: 136/530, loss: 3.977471715188585e-05
2023-01-22 18:02:33.205803: step: 140/530, loss: 8.840263944875915e-06
2023-01-22 18:02:34.263451: step: 144/530, loss: 0.0013821236789226532
2023-01-22 18:02:35.326836: step: 148/530, loss: 0.0006252435850910842
2023-01-22 18:02:36.396904: step: 152/530, loss: 0.0017567923059687018
2023-01-22 18:02:37.458558: step: 156/530, loss: 0.0019348494242876768
2023-01-22 18:02:38.518414: step: 160/530, loss: 0.00154181569814682
2023-01-22 18:02:39.578194: step: 164/530, loss: 0.0
2023-01-22 18:02:40.620933: step: 168/530, loss: 6.259909241634887e-06
2023-01-22 18:02:41.678064: step: 172/530, loss: 7.605681457789615e-05
2023-01-22 18:02:42.754569: step: 176/530, loss: 0.0058680991642177105
2023-01-22 18:02:43.826440: step: 180/530, loss: 0.004403875675052404
2023-01-22 18:02:44.889729: step: 184/530, loss: 0.0035206452012062073
2023-01-22 18:02:45.955166: step: 188/530, loss: 0.0004406616499181837
2023-01-22 18:02:47.009004: step: 192/530, loss: 0.00164504861459136
2023-01-22 18:02:48.065796: step: 196/530, loss: 5.073590045867604e-07
2023-01-22 18:02:49.128315: step: 200/530, loss: 0.00026435221661813557
2023-01-22 18:02:50.186180: step: 204/530, loss: 9.625990787753835e-05
2023-01-22 18:02:51.250758: step: 208/530, loss: 0.0012669884599745274
2023-01-22 18:02:52.312855: step: 212/530, loss: 0.00018781240214593709
2023-01-22 18:02:53.372503: step: 216/530, loss: 0.0002451986656524241
2023-01-22 18:02:54.422116: step: 220/530, loss: 0.00016452287673018873
2023-01-22 18:02:55.483349: step: 224/530, loss: 0.009959731251001358
2023-01-22 18:02:56.561166: step: 228/530, loss: 0.0007803167682141066
2023-01-22 18:02:57.621038: step: 232/530, loss: 0.001685862080194056
2023-01-22 18:02:58.677604: step: 236/530, loss: 0.0
2023-01-22 18:02:59.740721: step: 240/530, loss: 0.0012693736935034394
2023-01-22 18:03:00.798455: step: 244/530, loss: 0.00279949395917356
2023-01-22 18:03:01.869461: step: 248/530, loss: 0.0009765727445483208
2023-01-22 18:03:02.925923: step: 252/530, loss: 0.0016541201621294022
2023-01-22 18:03:03.997416: step: 256/530, loss: 0.009226897731423378
2023-01-22 18:03:05.064729: step: 260/530, loss: 0.004949219524860382
2023-01-22 18:03:06.129651: step: 264/530, loss: 0.0024971093516796827
2023-01-22 18:03:07.181784: step: 268/530, loss: 0.0025289629120379686
2023-01-22 18:03:08.250012: step: 272/530, loss: 0.001997048733755946
2023-01-22 18:03:09.323370: step: 276/530, loss: 0.0027037053368985653
2023-01-22 18:03:10.383880: step: 280/530, loss: 0.0035312389954924583
2023-01-22 18:03:11.452958: step: 284/530, loss: 8.356961916433647e-05
2023-01-22 18:03:12.508236: step: 288/530, loss: 0.0007067765691317618
2023-01-22 18:03:13.569590: step: 292/530, loss: 0.002174037043005228
2023-01-22 18:03:14.634251: step: 296/530, loss: 0.003014680929481983
2023-01-22 18:03:15.694240: step: 300/530, loss: 8.532369247404858e-05
2023-01-22 18:03:16.743347: step: 304/530, loss: 0.0003013579989783466
2023-01-22 18:03:17.806779: step: 308/530, loss: 0.0011720972834154963
2023-01-22 18:03:18.874275: step: 312/530, loss: 0.0030178409069776535
2023-01-22 18:03:19.938857: step: 316/530, loss: 0.0023797014728188515
2023-01-22 18:03:21.007807: step: 320/530, loss: 0.003959394060075283
2023-01-22 18:03:22.068341: step: 324/530, loss: 0.013838368467986584
2023-01-22 18:03:23.163370: step: 328/530, loss: 0.0031495261937379837
2023-01-22 18:03:24.218181: step: 332/530, loss: 0.005242731422185898
2023-01-22 18:03:25.281146: step: 336/530, loss: 0.00033640279434621334
2023-01-22 18:03:26.337851: step: 340/530, loss: 0.0034763794392347336
2023-01-22 18:03:27.402038: step: 344/530, loss: 0.00017940586258191615
2023-01-22 18:03:28.442021: step: 348/530, loss: 0.003981929738074541
2023-01-22 18:03:29.487315: step: 352/530, loss: 0.005513024050742388
2023-01-22 18:03:30.552735: step: 356/530, loss: 0.000940346100833267
2023-01-22 18:03:31.618429: step: 360/530, loss: 0.014222263358533382
2023-01-22 18:03:32.683856: step: 364/530, loss: 0.0033718652557581663
2023-01-22 18:03:33.742273: step: 368/530, loss: 0.00012514233822003007
2023-01-22 18:03:34.820410: step: 372/530, loss: 7.972505409270525e-05
2023-01-22 18:03:35.884061: step: 376/530, loss: 0.0019516331376507878
2023-01-22 18:03:36.936589: step: 380/530, loss: 0.0011451207101345062
2023-01-22 18:03:37.998698: step: 384/530, loss: 0.00444561755284667
2023-01-22 18:03:39.069898: step: 388/530, loss: 0.0024688197299838066
2023-01-22 18:03:40.136429: step: 392/530, loss: 0.004034331068396568
2023-01-22 18:03:41.200044: step: 396/530, loss: 0.0006795467925257981
2023-01-22 18:03:42.266099: step: 400/530, loss: 8.253064879681915e-05
2023-01-22 18:03:43.332249: step: 404/530, loss: 0.00033168913796544075
2023-01-22 18:03:44.391431: step: 408/530, loss: 0.00021120651217643172
2023-01-22 18:03:45.452018: step: 412/530, loss: 0.0004992078174836934
2023-01-22 18:03:46.516898: step: 416/530, loss: 6.285808922257274e-05
2023-01-22 18:03:47.575345: step: 420/530, loss: 0.003226697212085128
2023-01-22 18:03:48.624038: step: 424/530, loss: 0.00013692451466340572
2023-01-22 18:03:49.695060: step: 428/530, loss: 0.006708402186632156
2023-01-22 18:03:50.768143: step: 432/530, loss: 0.004447572864592075
2023-01-22 18:03:51.828141: step: 436/530, loss: 0.007740409579128027
2023-01-22 18:03:52.898386: step: 440/530, loss: 0.002659456105902791
2023-01-22 18:03:53.980566: step: 444/530, loss: 0.00010265692253597081
2023-01-22 18:03:55.058662: step: 448/530, loss: 0.0027501555159687996
2023-01-22 18:03:56.143629: step: 452/530, loss: 1.460834300814895e-05
2023-01-22 18:03:57.221292: step: 456/530, loss: 0.00573878875002265
2023-01-22 18:03:58.291946: step: 460/530, loss: 0.002819736022502184
2023-01-22 18:03:59.351400: step: 464/530, loss: 1.0765440492832568e-05
2023-01-22 18:04:00.424693: step: 468/530, loss: 0.008204531855881214
2023-01-22 18:04:01.473807: step: 472/530, loss: 4.598198938765563e-05
2023-01-22 18:04:02.573246: step: 476/530, loss: 0.0004426180967129767
2023-01-22 18:04:03.640246: step: 480/530, loss: 0.0029682456515729427
2023-01-22 18:04:04.689419: step: 484/530, loss: 3.419702920837153e-07
2023-01-22 18:04:05.756058: step: 488/530, loss: 0.001659355009905994
2023-01-22 18:04:06.825760: step: 492/530, loss: 0.00994129665195942
2023-01-22 18:04:07.890830: step: 496/530, loss: 0.004415545146912336
2023-01-22 18:04:08.949349: step: 500/530, loss: 0.0001393342827213928
2023-01-22 18:04:10.020753: step: 504/530, loss: 0.004157865419983864
2023-01-22 18:04:11.085071: step: 508/530, loss: 0.0005262452177703381
2023-01-22 18:04:12.184168: step: 512/530, loss: 0.020847121253609657
2023-01-22 18:04:13.254035: step: 516/530, loss: 0.005480272229760885
2023-01-22 18:04:14.305291: step: 520/530, loss: 0.00218738941475749
2023-01-22 18:04:15.373628: step: 524/530, loss: 0.003092500614002347
2023-01-22 18:04:16.448666: step: 528/530, loss: 0.028495432808995247
2023-01-22 18:04:17.500795: step: 532/530, loss: 0.006432359106838703
2023-01-22 18:04:18.574972: step: 536/530, loss: 0.012999472208321095
2023-01-22 18:04:19.639667: step: 540/530, loss: 0.0020123906433582306
2023-01-22 18:04:20.697366: step: 544/530, loss: 0.0013998314971104264
2023-01-22 18:04:21.782778: step: 548/530, loss: 0.0016724411398172379
2023-01-22 18:04:22.824873: step: 552/530, loss: 8.652758651805925e-07
2023-01-22 18:04:23.895829: step: 556/530, loss: 0.003603859804570675
2023-01-22 18:04:24.973408: step: 560/530, loss: 0.00787485670298338
2023-01-22 18:04:26.029359: step: 564/530, loss: 0.003121920395642519
2023-01-22 18:04:27.102699: step: 568/530, loss: 0.009287911467254162
2023-01-22 18:04:28.185098: step: 572/530, loss: 3.983230271842331e-06
2023-01-22 18:04:29.244605: step: 576/530, loss: 0.003140023909509182
2023-01-22 18:04:30.322127: step: 580/530, loss: 2.6439010980539024e-05
2023-01-22 18:04:31.396888: step: 584/530, loss: 0.004500710871070623
2023-01-22 18:04:32.455950: step: 588/530, loss: 0.001247038715519011
2023-01-22 18:04:33.511691: step: 592/530, loss: 3.1810628570383415e-05
2023-01-22 18:04:34.571926: step: 596/530, loss: 0.0036331121809780598
2023-01-22 18:04:35.632347: step: 600/530, loss: 5.078564299765276e-06
2023-01-22 18:04:36.716817: step: 604/530, loss: 0.0017249556258320808
2023-01-22 18:04:37.781332: step: 608/530, loss: 6.259195652091876e-05
2023-01-22 18:04:38.851575: step: 612/530, loss: 0.0014514377107843757
2023-01-22 18:04:39.910739: step: 616/530, loss: 0.0002850772289093584
2023-01-22 18:04:40.960248: step: 620/530, loss: 0.0005553573137149215
2023-01-22 18:04:42.021709: step: 624/530, loss: 0.012637272477149963
2023-01-22 18:04:43.077404: step: 628/530, loss: 9.784231224330142e-05
2023-01-22 18:04:44.142403: step: 632/530, loss: 0.0040410771034657955
2023-01-22 18:04:45.190070: step: 636/530, loss: 0.001638334128074348
2023-01-22 18:04:46.230356: step: 640/530, loss: 5.00682472193148e-05
2023-01-22 18:04:47.313569: step: 644/530, loss: 6.940359162399545e-05
2023-01-22 18:04:48.361679: step: 648/530, loss: 0.0006881205481477082
2023-01-22 18:04:49.417065: step: 652/530, loss: 0.0029281096067279577
2023-01-22 18:04:50.460670: step: 656/530, loss: 0.0
2023-01-22 18:04:51.521703: step: 660/530, loss: 0.004639377351850271
2023-01-22 18:04:52.570127: step: 664/530, loss: 0.004380300175398588
2023-01-22 18:04:53.616817: step: 668/530, loss: 0.00012675949255935848
2023-01-22 18:04:54.673839: step: 672/530, loss: 0.0006016083061695099
2023-01-22 18:04:55.755328: step: 676/530, loss: 0.011187789030373096
2023-01-22 18:04:56.816184: step: 680/530, loss: 0.003848572727292776
2023-01-22 18:04:57.883462: step: 684/530, loss: 0.004137535113841295
2023-01-22 18:04:58.952236: step: 688/530, loss: 0.0028142426162958145
2023-01-22 18:05:00.011635: step: 692/530, loss: 0.0007270050118677318
2023-01-22 18:05:01.078070: step: 696/530, loss: 3.770620241994038e-05
2023-01-22 18:05:02.152872: step: 700/530, loss: 0.022405892610549927
2023-01-22 18:05:03.221457: step: 704/530, loss: 0.0024828980676829815
2023-01-22 18:05:04.280164: step: 708/530, loss: 0.0014510038308799267
2023-01-22 18:05:05.344956: step: 712/530, loss: 0.000299901730613783
2023-01-22 18:05:06.395662: step: 716/530, loss: 0.002773511689156294
2023-01-22 18:05:07.465617: step: 720/530, loss: 0.007063380908221006
2023-01-22 18:05:08.520514: step: 724/530, loss: 0.0016142678214237094
2023-01-22 18:05:09.576761: step: 728/530, loss: 0.0038000394124537706
2023-01-22 18:05:10.630900: step: 732/530, loss: 0.00038545799907296896
2023-01-22 18:05:11.684124: step: 736/530, loss: 1.4375986211234704e-05
2023-01-22 18:05:12.754735: step: 740/530, loss: 0.024682098999619484
2023-01-22 18:05:13.813471: step: 744/530, loss: 9.876345757220406e-06
2023-01-22 18:05:14.870093: step: 748/530, loss: 3.379245026735589e-05
2023-01-22 18:05:15.922968: step: 752/530, loss: 0.005003856960684061
2023-01-22 18:05:17.007781: step: 756/530, loss: 0.003168597584590316
2023-01-22 18:05:18.081155: step: 760/530, loss: 0.0068447170779109
2023-01-22 18:05:19.153203: step: 764/530, loss: 0.0038939560763537884
2023-01-22 18:05:20.227422: step: 768/530, loss: 1.3161532478989102e-05
2023-01-22 18:05:21.293085: step: 772/530, loss: 0.0009245398687198758
2023-01-22 18:05:22.353594: step: 776/530, loss: 0.00034620013320818543
2023-01-22 18:05:23.415823: step: 780/530, loss: 0.004762914497405291
2023-01-22 18:05:24.484460: step: 784/530, loss: 0.007647800724953413
2023-01-22 18:05:25.528291: step: 788/530, loss: 0.0005343404482118785
2023-01-22 18:05:26.589642: step: 792/530, loss: 0.004137787036597729
2023-01-22 18:05:27.651943: step: 796/530, loss: 0.00023037564824335277
2023-01-22 18:05:28.703350: step: 800/530, loss: 0.007016750518232584
2023-01-22 18:05:29.755569: step: 804/530, loss: 0.00936032086610794
2023-01-22 18:05:30.838004: step: 808/530, loss: 0.004378096200525761
2023-01-22 18:05:31.909461: step: 812/530, loss: 0.0002547816256992519
2023-01-22 18:05:32.978748: step: 816/530, loss: 0.00659840926527977
2023-01-22 18:05:34.026273: step: 820/530, loss: 2.0800029233214445e-05
2023-01-22 18:05:35.081688: step: 824/530, loss: 0.017561456188559532
2023-01-22 18:05:36.151028: step: 828/530, loss: 0.0009880434954538941
2023-01-22 18:05:37.209201: step: 832/530, loss: 3.384624142199755e-05
2023-01-22 18:05:38.282988: step: 836/530, loss: 0.0017293887212872505
2023-01-22 18:05:39.355065: step: 840/530, loss: 0.012923546135425568
2023-01-22 18:05:40.405205: step: 844/530, loss: 0.004564765375107527
2023-01-22 18:05:41.476574: step: 848/530, loss: 0.001028168830089271
2023-01-22 18:05:42.539538: step: 852/530, loss: 0.0009403776493854821
2023-01-22 18:05:43.593309: step: 856/530, loss: 0.001699383370578289
2023-01-22 18:05:44.663382: step: 860/530, loss: 0.0027443207800388336
2023-01-22 18:05:45.729278: step: 864/530, loss: 0.008542467840015888
2023-01-22 18:05:46.792828: step: 868/530, loss: 0.006661437451839447
2023-01-22 18:05:47.848505: step: 872/530, loss: 0.008112785406410694
2023-01-22 18:05:48.922792: step: 876/530, loss: 0.008347105234861374
2023-01-22 18:05:49.976462: step: 880/530, loss: 0.000577003404032439
2023-01-22 18:05:51.046617: step: 884/530, loss: 6.859995482955128e-05
2023-01-22 18:05:52.112410: step: 888/530, loss: 0.005183335859328508
2023-01-22 18:05:53.166003: step: 892/530, loss: 0.005544007755815983
2023-01-22 18:05:54.233280: step: 896/530, loss: 0.0013655393850058317
2023-01-22 18:05:55.290857: step: 900/530, loss: 0.0010157300857827067
2023-01-22 18:05:56.338182: step: 904/530, loss: 0.000509263074491173
2023-01-22 18:05:57.398690: step: 908/530, loss: 9.949225932359695e-05
2023-01-22 18:05:58.455003: step: 912/530, loss: 0.00041577493539080024
2023-01-22 18:05:59.521840: step: 916/530, loss: 0.003287137486040592
2023-01-22 18:06:00.582079: step: 920/530, loss: 0.0052236150950193405
2023-01-22 18:06:01.654072: step: 924/530, loss: 1.2356086699583102e-05
2023-01-22 18:06:02.707833: step: 928/530, loss: 0.00040745915612205863
2023-01-22 18:06:03.766087: step: 932/530, loss: 0.00033783091930672526
2023-01-22 18:06:04.837131: step: 936/530, loss: 0.006726912688463926
2023-01-22 18:06:05.893814: step: 940/530, loss: 0.003163578687235713
2023-01-22 18:06:06.963003: step: 944/530, loss: 0.0010459624463692307
2023-01-22 18:06:08.037035: step: 948/530, loss: 1.7605721950531006e-05
2023-01-22 18:06:09.100148: step: 952/530, loss: 6.035666956449859e-06
2023-01-22 18:06:10.162123: step: 956/530, loss: 0.00016880819748621434
2023-01-22 18:06:11.218456: step: 960/530, loss: 0.000227796655963175
2023-01-22 18:06:12.277755: step: 964/530, loss: 0.0010014348663389683
2023-01-22 18:06:13.331759: step: 968/530, loss: 0.0013350655790418386
2023-01-22 18:06:14.380865: step: 972/530, loss: 0.0005010308232158422
2023-01-22 18:06:15.431191: step: 976/530, loss: 0.0006129872053861618
2023-01-22 18:06:16.500853: step: 980/530, loss: 0.0011787122348323464
2023-01-22 18:06:17.555136: step: 984/530, loss: 0.002530441852286458
2023-01-22 18:06:18.619033: step: 988/530, loss: 0.013662178069353104
2023-01-22 18:06:19.678656: step: 992/530, loss: 0.019461173564195633
2023-01-22 18:06:20.731249: step: 996/530, loss: 0.0019518026383593678
2023-01-22 18:06:21.788178: step: 1000/530, loss: 0.0004617640806827694
2023-01-22 18:06:22.848150: step: 1004/530, loss: 0.0014622590970247984
2023-01-22 18:06:23.903393: step: 1008/530, loss: 7.19355302862823e-05
2023-01-22 18:06:24.977969: step: 1012/530, loss: 0.002228764584288001
2023-01-22 18:06:26.043035: step: 1016/530, loss: 0.056037988513708115
2023-01-22 18:06:27.099459: step: 1020/530, loss: 0.0010082368971779943
2023-01-22 18:06:28.159615: step: 1024/530, loss: 0.0022039019968360662
2023-01-22 18:06:29.221842: step: 1028/530, loss: 0.0007634743233211339
2023-01-22 18:06:30.284554: step: 1032/530, loss: 0.001595959416590631
2023-01-22 18:06:31.339200: step: 1036/530, loss: 0.0009367107995785773
2023-01-22 18:06:32.404167: step: 1040/530, loss: 0.0002886794973164797
2023-01-22 18:06:33.448656: step: 1044/530, loss: 0.0008652876131236553
2023-01-22 18:06:34.502267: step: 1048/530, loss: 0.020551834255456924
2023-01-22 18:06:35.558483: step: 1052/530, loss: 0.027009015902876854
2023-01-22 18:06:36.627827: step: 1056/530, loss: 0.008178578689694405
2023-01-22 18:06:37.672949: step: 1060/530, loss: 0.006356274709105492
2023-01-22 18:06:38.735976: step: 1064/530, loss: 0.0008796472102403641
2023-01-22 18:06:39.786492: step: 1068/530, loss: 0.004666866268962622
2023-01-22 18:06:40.855947: step: 1072/530, loss: 0.0017187492921948433
2023-01-22 18:06:41.911275: step: 1076/530, loss: 0.0015398325631394982
2023-01-22 18:06:42.963528: step: 1080/530, loss: 0.0002882368862628937
2023-01-22 18:06:44.038621: step: 1084/530, loss: 0.003046171274036169
2023-01-22 18:06:45.110502: step: 1088/530, loss: 0.0006463193567469716
2023-01-22 18:06:46.202097: step: 1092/530, loss: 0.00010992652823915705
2023-01-22 18:06:47.246515: step: 1096/530, loss: 0.001654975931160152
2023-01-22 18:06:48.318492: step: 1100/530, loss: 0.012699581682682037
2023-01-22 18:06:49.382433: step: 1104/530, loss: 0.00716777890920639
2023-01-22 18:06:50.456232: step: 1108/530, loss: 0.00681094778701663
2023-01-22 18:06:51.523217: step: 1112/530, loss: 0.000222817572648637
2023-01-22 18:06:52.619778: step: 1116/530, loss: 0.009048809297382832
2023-01-22 18:06:53.662239: step: 1120/530, loss: 0.0006711932946927845
2023-01-22 18:06:54.716882: step: 1124/530, loss: 0.0015377732925117016
2023-01-22 18:06:55.777843: step: 1128/530, loss: 7.38136877771467e-05
2023-01-22 18:06:56.840373: step: 1132/530, loss: 0.0014566653408110142
2023-01-22 18:06:57.898368: step: 1136/530, loss: 3.048654798476491e-05
2023-01-22 18:06:58.960088: step: 1140/530, loss: 1.8965063645737246e-05
2023-01-22 18:07:00.013747: step: 1144/530, loss: 0.004442988894879818
2023-01-22 18:07:01.061813: step: 1148/530, loss: 0.003879878204315901
2023-01-22 18:07:02.155042: step: 1152/530, loss: 3.460418520262465e-05
2023-01-22 18:07:03.222011: step: 1156/530, loss: 0.0026914526242762804
2023-01-22 18:07:04.273456: step: 1160/530, loss: 0.000454261782579124
2023-01-22 18:07:05.323648: step: 1164/530, loss: 0.0012476884294301271
2023-01-22 18:07:06.384998: step: 1168/530, loss: 0.007799950893968344
2023-01-22 18:07:07.461187: step: 1172/530, loss: 0.0012154633877798915
2023-01-22 18:07:08.540131: step: 1176/530, loss: 0.00908190943300724
2023-01-22 18:07:09.598622: step: 1180/530, loss: 4.060582068632357e-05
2023-01-22 18:07:10.658202: step: 1184/530, loss: 8.804251592664514e-06
2023-01-22 18:07:11.710272: step: 1188/530, loss: 0.00040031614480540156
2023-01-22 18:07:12.753602: step: 1192/530, loss: 0.00599023187533021
2023-01-22 18:07:13.809214: step: 1196/530, loss: 0.002464772667735815
2023-01-22 18:07:14.854513: step: 1200/530, loss: 5.606355898635229e-06
2023-01-22 18:07:15.896955: step: 1204/530, loss: 0.0004145588318351656
2023-01-22 18:07:16.949925: step: 1208/530, loss: 0.00013903662329539657
2023-01-22 18:07:18.009135: step: 1212/530, loss: 0.0014565952587872744
2023-01-22 18:07:19.069194: step: 1216/530, loss: 0.0036121434532105923
2023-01-22 18:07:20.131378: step: 1220/530, loss: 0.0003554648137651384
2023-01-22 18:07:21.200283: step: 1224/530, loss: 0.0021264769602566957
2023-01-22 18:07:22.252088: step: 1228/530, loss: 5.610079097095877e-05
2023-01-22 18:07:23.312658: step: 1232/530, loss: 0.0004236284294165671
2023-01-22 18:07:24.394134: step: 1236/530, loss: 6.0965485317865387e-05
2023-01-22 18:07:25.461798: step: 1240/530, loss: 5.6363460316788405e-05
2023-01-22 18:07:26.506497: step: 1244/530, loss: 0.004429629538208246
2023-01-22 18:07:27.552333: step: 1248/530, loss: 4.690885543823242e-05
2023-01-22 18:07:28.615758: step: 1252/530, loss: 0.00017911115719471127
2023-01-22 18:07:29.683695: step: 1256/530, loss: 0.0023545955773442984
2023-01-22 18:07:30.740532: step: 1260/530, loss: 0.0016902872594073415
2023-01-22 18:07:31.805839: step: 1264/530, loss: 7.412501145154238e-05
2023-01-22 18:07:32.906898: step: 1268/530, loss: 2.3037136998027563e-05
2023-01-22 18:07:33.977186: step: 1272/530, loss: 6.271031452342868e-05
2023-01-22 18:07:35.064995: step: 1276/530, loss: 8.948436516220681e-07
2023-01-22 18:07:36.111456: step: 1280/530, loss: 0.001532075461000204
2023-01-22 18:07:37.179531: step: 1284/530, loss: 0.0004931019502691925
2023-01-22 18:07:38.245221: step: 1288/530, loss: 0.00395149365067482
2023-01-22 18:07:39.316573: step: 1292/530, loss: 5.169353971723467e-05
2023-01-22 18:07:40.391857: step: 1296/530, loss: 0.010782415978610516
2023-01-22 18:07:41.449874: step: 1300/530, loss: 0.0004477275360841304
2023-01-22 18:07:42.497647: step: 1304/530, loss: 0.0008825917611829937
2023-01-22 18:07:43.553817: step: 1308/530, loss: 0.020749520510435104
2023-01-22 18:07:44.622784: step: 1312/530, loss: 5.01430404256098e-05
2023-01-22 18:07:45.687746: step: 1316/530, loss: 0.0025758296251296997
2023-01-22 18:07:46.735338: step: 1320/530, loss: 2.5561619622749276e-05
2023-01-22 18:07:47.815784: step: 1324/530, loss: 0.00024029469932429492
2023-01-22 18:07:48.876952: step: 1328/530, loss: 3.0458546461886726e-05
2023-01-22 18:07:49.923492: step: 1332/530, loss: 0.004547671880573034
2023-01-22 18:07:50.980895: step: 1336/530, loss: 0.00048235684516839683
2023-01-22 18:07:52.032809: step: 1340/530, loss: 0.002156138652935624
2023-01-22 18:07:53.115530: step: 1344/530, loss: 0.005517592653632164
2023-01-22 18:07:54.163311: step: 1348/530, loss: 2.982908881676849e-05
2023-01-22 18:07:55.229668: step: 1352/530, loss: 0.001281043398194015
2023-01-22 18:07:56.299164: step: 1356/530, loss: 0.0006219832575879991
2023-01-22 18:07:57.363522: step: 1360/530, loss: 0.021388936787843704
2023-01-22 18:07:58.420634: step: 1364/530, loss: 0.0014244536869227886
2023-01-22 18:07:59.467649: step: 1368/530, loss: 0.0022719851695001125
2023-01-22 18:08:00.535489: step: 1372/530, loss: 0.0009321668767370284
2023-01-22 18:08:01.595285: step: 1376/530, loss: 4.062427251483314e-05
2023-01-22 18:08:02.648124: step: 1380/530, loss: 0.004758135881274939
2023-01-22 18:08:03.706226: step: 1384/530, loss: 0.0063188043422997
2023-01-22 18:08:04.755200: step: 1388/530, loss: 0.004103731829673052
2023-01-22 18:08:05.805286: step: 1392/530, loss: 0.004832057747989893
2023-01-22 18:08:06.878614: step: 1396/530, loss: 0.0037866709753870964
2023-01-22 18:08:07.943924: step: 1400/530, loss: 0.004212132655084133
2023-01-22 18:08:08.999265: step: 1404/530, loss: 0.00500048091635108
2023-01-22 18:08:10.067092: step: 1408/530, loss: 4.953197276336141e-06
2023-01-22 18:08:11.142783: step: 1412/530, loss: 0.004411301575601101
2023-01-22 18:08:12.209201: step: 1416/530, loss: 0.0017443530960008502
2023-01-22 18:08:13.273204: step: 1420/530, loss: 1.373694703943329e-05
2023-01-22 18:08:14.342853: step: 1424/530, loss: 0.0044926670379936695
2023-01-22 18:08:15.395392: step: 1428/530, loss: 0.003479141043499112
2023-01-22 18:08:16.461839: step: 1432/530, loss: 0.0018363717244938016
2023-01-22 18:08:17.524146: step: 1436/530, loss: 0.009559924714267254
2023-01-22 18:08:18.574199: step: 1440/530, loss: 0.0005628743092529476
2023-01-22 18:08:19.633980: step: 1444/530, loss: 0.005261993035674095
2023-01-22 18:08:20.690702: step: 1448/530, loss: 0.0006315595237538218
2023-01-22 18:08:21.750748: step: 1452/530, loss: 0.004621594678610563
2023-01-22 18:08:22.794723: step: 1456/530, loss: 8.12647704151459e-05
2023-01-22 18:08:23.843114: step: 1460/530, loss: 6.221111448212469e-07
2023-01-22 18:08:24.908599: step: 1464/530, loss: 0.00024380855029448867
2023-01-22 18:08:25.970607: step: 1468/530, loss: 0.006493727210909128
2023-01-22 18:08:27.028358: step: 1472/530, loss: 0.0019776339177042246
2023-01-22 18:08:28.104746: step: 1476/530, loss: 0.0011832970194518566
2023-01-22 18:08:29.169873: step: 1480/530, loss: 0.006625242996960878
2023-01-22 18:08:30.213200: step: 1484/530, loss: 0.0006374718504957855
2023-01-22 18:08:31.265506: step: 1488/530, loss: 0.0009573863353580236
2023-01-22 18:08:32.332099: step: 1492/530, loss: 0.00025285579613409936
2023-01-22 18:08:33.397733: step: 1496/530, loss: 0.002323656575754285
2023-01-22 18:08:34.460509: step: 1500/530, loss: 0.003548703622072935
2023-01-22 18:08:35.524154: step: 1504/530, loss: 0.008402667008340359
2023-01-22 18:08:36.577515: step: 1508/530, loss: 0.00010735232353908941
2023-01-22 18:08:37.645001: step: 1512/530, loss: 0.0029170061461627483
2023-01-22 18:08:38.696610: step: 1516/530, loss: 0.003136037616059184
2023-01-22 18:08:39.749395: step: 1520/530, loss: 0.0005236623110249639
2023-01-22 18:08:40.822528: step: 1524/530, loss: 2.936218152171932e-05
2023-01-22 18:08:41.882470: step: 1528/530, loss: 4.369170346762985e-05
2023-01-22 18:08:42.957181: step: 1532/530, loss: 0.000450140330940485
2023-01-22 18:08:44.021199: step: 1536/530, loss: 0.0032530699390918016
2023-01-22 18:08:45.082834: step: 1540/530, loss: 7.536407792940736e-06
2023-01-22 18:08:46.139767: step: 1544/530, loss: 0.00036497111432254314
2023-01-22 18:08:47.200606: step: 1548/530, loss: 0.003464294131845236
2023-01-22 18:08:48.236989: step: 1552/530, loss: 2.537953207593091e-07
2023-01-22 18:08:49.286997: step: 1556/530, loss: 4.48406717623584e-06
2023-01-22 18:08:50.345391: step: 1560/530, loss: 0.00012007732584606856
2023-01-22 18:08:51.392752: step: 1564/530, loss: 0.0010876161977648735
2023-01-22 18:08:52.464518: step: 1568/530, loss: 0.00012068310752511024
2023-01-22 18:08:53.530153: step: 1572/530, loss: 7.002367055974901e-06
2023-01-22 18:08:54.578824: step: 1576/530, loss: 0.002143105026334524
2023-01-22 18:08:55.651214: step: 1580/530, loss: 0.004553679376840591
2023-01-22 18:08:56.712023: step: 1584/530, loss: 0.0006215042667463422
2023-01-22 18:08:57.769458: step: 1588/530, loss: 4.3228345020907e-05
2023-01-22 18:08:58.825401: step: 1592/530, loss: 0.0002511601778678596
2023-01-22 18:08:59.888566: step: 1596/530, loss: 0.00047809912939555943
2023-01-22 18:09:00.944923: step: 1600/530, loss: 0.001023935736157
2023-01-22 18:09:02.007066: step: 1604/530, loss: 5.057837915956043e-05
2023-01-22 18:09:03.078045: step: 1608/530, loss: 0.000748688296880573
2023-01-22 18:09:04.135942: step: 1612/530, loss: 0.00024229013069998473
2023-01-22 18:09:05.193975: step: 1616/530, loss: 1.9422168406890705e-06
2023-01-22 18:09:06.235999: step: 1620/530, loss: 3.119130997220054e-05
2023-01-22 18:09:07.287855: step: 1624/530, loss: 0.0003685960255097598
2023-01-22 18:09:08.358496: step: 1628/530, loss: 0.00042629207018762827
2023-01-22 18:09:09.439004: step: 1632/530, loss: 0.0030993702821433544
2023-01-22 18:09:10.487616: step: 1636/530, loss: 0.001755658071488142
2023-01-22 18:09:11.544167: step: 1640/530, loss: 0.00043842277955263853
2023-01-22 18:09:12.602375: step: 1644/530, loss: 0.0028608699794858694
2023-01-22 18:09:13.663983: step: 1648/530, loss: 0.009217122569680214
2023-01-22 18:09:14.735875: step: 1652/530, loss: 0.00317751569673419
2023-01-22 18:09:15.792854: step: 1656/530, loss: 0.0011297761229798198
2023-01-22 18:09:16.844751: step: 1660/530, loss: 1.0433981515234336e-05
2023-01-22 18:09:17.916164: step: 1664/530, loss: 0.0004397172888275236
2023-01-22 18:09:18.986999: step: 1668/530, loss: 0.002238500863313675
2023-01-22 18:09:20.057175: step: 1672/530, loss: 0.0022370817605406046
2023-01-22 18:09:21.113991: step: 1676/530, loss: 0.0035973885096609592
2023-01-22 18:09:22.169796: step: 1680/530, loss: 8.798352791927755e-05
2023-01-22 18:09:23.222657: step: 1684/530, loss: 0.00458543049171567
2023-01-22 18:09:24.295488: step: 1688/530, loss: 0.0029092200566083193
2023-01-22 18:09:25.341045: step: 1692/530, loss: 1.9163313481840305e-05
2023-01-22 18:09:26.408497: step: 1696/530, loss: 0.0016301489667966962
2023-01-22 18:09:27.475605: step: 1700/530, loss: 0.002227955497801304
2023-01-22 18:09:28.532114: step: 1704/530, loss: 0.0010239663533866405
2023-01-22 18:09:29.581210: step: 1708/530, loss: 0.0010610586032271385
2023-01-22 18:09:30.635220: step: 1712/530, loss: 0.00018567325605545193
2023-01-22 18:09:31.690853: step: 1716/530, loss: 7.646896119695157e-05
2023-01-22 18:09:32.745702: step: 1720/530, loss: 1.054508720699232e-05
2023-01-22 18:09:33.805642: step: 1724/530, loss: 0.0005834304611198604
2023-01-22 18:09:34.866973: step: 1728/530, loss: 0.00032743901829235256
2023-01-22 18:09:35.927648: step: 1732/530, loss: 0.010699824430048466
2023-01-22 18:09:36.977511: step: 1736/530, loss: 0.0001258936244994402
2023-01-22 18:09:38.045229: step: 1740/530, loss: 0.00025616458151489496
2023-01-22 18:09:39.133927: step: 1744/530, loss: 0.00027458544354885817
2023-01-22 18:09:40.180915: step: 1748/530, loss: 6.776011787223979e-07
2023-01-22 18:09:41.236520: step: 1752/530, loss: 3.7080109905218706e-05
2023-01-22 18:09:42.286608: step: 1756/530, loss: 0.004809232894331217
2023-01-22 18:09:43.327830: step: 1760/530, loss: 0.000706952647306025
2023-01-22 18:09:44.392471: step: 1764/530, loss: 0.0028235595673322678
2023-01-22 18:09:45.442457: step: 1768/530, loss: 0.0016812203684821725
2023-01-22 18:09:46.476525: step: 1772/530, loss: 8.328335388796404e-05
2023-01-22 18:09:47.535064: step: 1776/530, loss: 0.0018091369420289993
2023-01-22 18:09:48.591780: step: 1780/530, loss: 0.013767399825155735
2023-01-22 18:09:49.658545: step: 1784/530, loss: 0.0005033770576119423
2023-01-22 18:09:50.717284: step: 1788/530, loss: 2.011625110753812e-05
2023-01-22 18:09:51.785412: step: 1792/530, loss: 7.018488395260647e-05
2023-01-22 18:09:52.838917: step: 1796/530, loss: 0.004645438864827156
2023-01-22 18:09:53.908247: step: 1800/530, loss: 0.0003077214059885591
2023-01-22 18:09:54.967856: step: 1804/530, loss: 6.319866952253506e-05
2023-01-22 18:09:56.024307: step: 1808/530, loss: 6.23879095655866e-05
2023-01-22 18:09:57.086769: step: 1812/530, loss: 0.006554232910275459
2023-01-22 18:09:58.126135: step: 1816/530, loss: 0.00044025102397426963
2023-01-22 18:09:59.198539: step: 1820/530, loss: 0.00025310626369901
2023-01-22 18:10:00.291356: step: 1824/530, loss: 0.0015613521682098508
2023-01-22 18:10:01.353016: step: 1828/530, loss: 0.0210096538066864
2023-01-22 18:10:02.421728: step: 1832/530, loss: 1.633365172892809e-05
2023-01-22 18:10:03.486614: step: 1836/530, loss: 0.005266386549919844
2023-01-22 18:10:04.545295: step: 1840/530, loss: 0.06566346436738968
2023-01-22 18:10:05.600356: step: 1844/530, loss: 0.0016165070701390505
2023-01-22 18:10:06.647929: step: 1848/530, loss: 0.004166364204138517
2023-01-22 18:10:07.712429: step: 1852/530, loss: 0.00019329850329086185
2023-01-22 18:10:08.775042: step: 1856/530, loss: 0.0032499053049832582
2023-01-22 18:10:09.835915: step: 1860/530, loss: 0.020395835861563683
2023-01-22 18:10:10.872769: step: 1864/530, loss: 0.00029200062272138894
2023-01-22 18:10:11.922432: step: 1868/530, loss: 0.0010121092200279236
2023-01-22 18:10:12.961876: step: 1872/530, loss: 0.009185848757624626
2023-01-22 18:10:14.016371: step: 1876/530, loss: 0.007306584157049656
2023-01-22 18:10:15.065836: step: 1880/530, loss: 0.0009480341104790568
2023-01-22 18:10:16.137629: step: 1884/530, loss: 0.004072495736181736
2023-01-22 18:10:17.195479: step: 1888/530, loss: 0.006742303259670734
2023-01-22 18:10:18.251724: step: 1892/530, loss: 0.00236950209364295
2023-01-22 18:10:19.302640: step: 1896/530, loss: 2.604699567143598e-08
2023-01-22 18:10:20.382913: step: 1900/530, loss: 0.00043559985351748765
2023-01-22 18:10:21.437677: step: 1904/530, loss: 0.00042992053204216063
2023-01-22 18:10:22.485140: step: 1908/530, loss: 0.00659569725394249
2023-01-22 18:10:23.527162: step: 1912/530, loss: 6.511341325676767e-06
2023-01-22 18:10:24.602094: step: 1916/530, loss: 0.013887734152376652
2023-01-22 18:10:25.652242: step: 1920/530, loss: 0.003350155660882592
2023-01-22 18:10:26.718011: step: 1924/530, loss: 0.0015852149808779359
2023-01-22 18:10:27.796013: step: 1928/530, loss: 0.0007855534204281867
2023-01-22 18:10:28.869065: step: 1932/530, loss: 6.717738142469898e-05
2023-01-22 18:10:29.937131: step: 1936/530, loss: 1.2404269000398926e-05
2023-01-22 18:10:31.011744: step: 1940/530, loss: 0.003950254060328007
2023-01-22 18:10:32.100098: step: 1944/530, loss: 0.0008896337240003049
2023-01-22 18:10:33.149979: step: 1948/530, loss: 0.002133734757080674
2023-01-22 18:10:34.205628: step: 1952/530, loss: 0.0023981048725545406
2023-01-22 18:10:35.264227: step: 1956/530, loss: 0.004024495370686054
2023-01-22 18:10:36.309617: step: 1960/530, loss: 0.001832007197663188
2023-01-22 18:10:37.368291: step: 1964/530, loss: 0.00044516808702610433
2023-01-22 18:10:38.401832: step: 1968/530, loss: 0.0005577250849455595
2023-01-22 18:10:39.456181: step: 1972/530, loss: 0.00012662411609198898
2023-01-22 18:10:40.515659: step: 1976/530, loss: 0.0005612174863927066
2023-01-22 18:10:41.567745: step: 1980/530, loss: 4.664589596359292e-06
2023-01-22 18:10:42.629659: step: 1984/530, loss: 0.0003954134590458125
2023-01-22 18:10:43.684988: step: 1988/530, loss: 0.0028227027505636215
2023-01-22 18:10:44.750052: step: 1992/530, loss: 0.0032181960996240377
2023-01-22 18:10:45.821241: step: 1996/530, loss: 0.006779888179153204
2023-01-22 18:10:46.860032: step: 2000/530, loss: 0.005467736627906561
2023-01-22 18:10:47.928893: step: 2004/530, loss: 0.013756637461483479
2023-01-22 18:10:48.984072: step: 2008/530, loss: 0.0007858102326281369
2023-01-22 18:10:50.037755: step: 2012/530, loss: 1.3361885748963687e-06
2023-01-22 18:10:51.106786: step: 2016/530, loss: 0.005576764699071646
2023-01-22 18:10:52.173603: step: 2020/530, loss: 0.000756444875150919
2023-01-22 18:10:53.245917: step: 2024/530, loss: 0.0013267290778458118
2023-01-22 18:10:54.306649: step: 2028/530, loss: 0.0017476563807576895
2023-01-22 18:10:55.367226: step: 2032/530, loss: 0.0017575218807905912
2023-01-22 18:10:56.418431: step: 2036/530, loss: 0.003545111045241356
2023-01-22 18:10:57.479066: step: 2040/530, loss: 9.358391253044829e-05
2023-01-22 18:10:58.526451: step: 2044/530, loss: 0.0011822226224467158
2023-01-22 18:10:59.572176: step: 2048/530, loss: 0.0008207531645894051
2023-01-22 18:11:00.644368: step: 2052/530, loss: 0.003093077102676034
2023-01-22 18:11:01.721979: step: 2056/530, loss: 0.008489741012454033
2023-01-22 18:11:02.817892: step: 2060/530, loss: 0.0007912173750810325
2023-01-22 18:11:03.885402: step: 2064/530, loss: 0.00011926981096621603
2023-01-22 18:11:04.933518: step: 2068/530, loss: 0.00023459186195395887
2023-01-22 18:11:05.985555: step: 2072/530, loss: 0.0018284308025613427
2023-01-22 18:11:07.045383: step: 2076/530, loss: 0.00011667969374684617
2023-01-22 18:11:08.102679: step: 2080/530, loss: 0.00277364207431674
2023-01-22 18:11:09.160518: step: 2084/530, loss: 0.00027282341034151614
2023-01-22 18:11:10.214507: step: 2088/530, loss: 0.0037249084562063217
2023-01-22 18:11:11.276291: step: 2092/530, loss: 0.01464503537863493
2023-01-22 18:11:12.318530: step: 2096/530, loss: 3.0795246857451275e-05
2023-01-22 18:11:13.379284: step: 2100/530, loss: 4.297842679079622e-05
2023-01-22 18:11:14.452997: step: 2104/530, loss: 0.000861082982737571
2023-01-22 18:11:15.540409: step: 2108/530, loss: 0.003851526416838169
2023-01-22 18:11:16.617072: step: 2112/530, loss: 0.0066820536740124226
2023-01-22 18:11:17.682043: step: 2116/530, loss: 0.0022826846688985825
2023-01-22 18:11:18.747392: step: 2120/530, loss: 0.012766195461153984
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35157456325078623, 'r': 0.23377425504467864, 'f1': 0.2808208679943877}, 'combined': 0.1862438917268478, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32417217867058634, 'r': 0.28917631847319347, 'f1': 0.30567586817586817}, 'combined': 0.20378391211724545, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4048319662418266, 'r': 0.3204336064976396, 'f1': 0.357722114062068}, 'combined': 0.23346074812471804, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32267379278395464, 'r': 0.3404300356506239, 'f1': 0.3313141805870338}, 'combined': 0.24412623832728808, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35968111116618956, 'r': 0.33103118715987834, 'f1': 0.3447619667895938}, 'combined': 0.22865042357030052, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6333333333333333, 'r': 0.41304347826086957, 'f1': 0.5}, 'combined': 0.3333333333333333, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3639851613572689, 'r': 0.2893923768665952, 'f1': 0.3224308300395258}, 'combined': 0.23758061160807162, 'stategy': 1, 'epoch': 12}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.35111737916333396, 'r': 0.23377425504467864, 'f1': 0.2806749112022909}, 'combined': 0.18614709136732244, 'stategy': 1, 'epoch': 12}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:13:45.936429: step: 4/530, loss: 4.358332807896659e-05
2023-01-22 18:13:47.002317: step: 8/530, loss: 0.0001222815626533702
2023-01-22 18:13:48.044902: step: 12/530, loss: 0.00037242783582769334
2023-01-22 18:13:49.096828: step: 16/530, loss: 0.00019953807350248098
2023-01-22 18:13:50.174262: step: 20/530, loss: 0.0015346790896728635
2023-01-22 18:13:51.226364: step: 24/530, loss: 0.0005334898014552891
2023-01-22 18:13:52.283408: step: 28/530, loss: 0.0003760063846129924
2023-01-22 18:13:53.349160: step: 32/530, loss: 0.0001605412835488096
2023-01-22 18:13:54.399944: step: 36/530, loss: 0.0007944625103846192
2023-01-22 18:13:55.469104: step: 40/530, loss: 0.003619913011789322
2023-01-22 18:13:56.516321: step: 44/530, loss: 0.000696202798280865
2023-01-22 18:13:57.569179: step: 48/530, loss: 6.0909369494766e-05
2023-01-22 18:13:58.630711: step: 52/530, loss: 0.0011853754986077547
2023-01-22 18:13:59.696339: step: 56/530, loss: 0.0029107267037034035
2023-01-22 18:14:00.753378: step: 60/530, loss: 0.0012074995320290327
2023-01-22 18:14:01.815165: step: 64/530, loss: 0.0
2023-01-22 18:14:02.875631: step: 68/530, loss: 2.6410196369397454e-05
2023-01-22 18:14:03.949425: step: 72/530, loss: 0.0011837774654850364
2023-01-22 18:14:04.998420: step: 76/530, loss: 7.056760750856483e-06
2023-01-22 18:14:06.050290: step: 80/530, loss: 0.00019833551777992398
2023-01-22 18:14:07.100409: step: 84/530, loss: 0.0021719750948250294
2023-01-22 18:14:08.148891: step: 88/530, loss: 0.022907907143235207
2023-01-22 18:14:09.207209: step: 92/530, loss: 0.0030612957198172808
2023-01-22 18:14:10.265074: step: 96/530, loss: 1.803574377845507e-05
2023-01-22 18:14:11.315471: step: 100/530, loss: 0.00017038150690495968
2023-01-22 18:14:12.368529: step: 104/530, loss: 0.0011330187553539872
2023-01-22 18:14:13.429433: step: 108/530, loss: 0.0041223010048270226
2023-01-22 18:14:14.491636: step: 112/530, loss: 0.003346719779074192
2023-01-22 18:14:15.549800: step: 116/530, loss: 0.00016849975509103388
2023-01-22 18:14:16.623208: step: 120/530, loss: 0.0007259040721692145
2023-01-22 18:14:17.686071: step: 124/530, loss: 0.00664887111634016
2023-01-22 18:14:18.739331: step: 128/530, loss: 0.00209051207639277
2023-01-22 18:14:19.815497: step: 132/530, loss: 0.00332703092135489
2023-01-22 18:14:20.871118: step: 136/530, loss: 0.0027179408352822065
2023-01-22 18:14:21.934230: step: 140/530, loss: 0.0005587544874288142
2023-01-22 18:14:23.010451: step: 144/530, loss: 0.0028140260837972164
2023-01-22 18:14:24.071454: step: 148/530, loss: 0.0019028286915272474
2023-01-22 18:14:25.135174: step: 152/530, loss: 0.0031918652821332216
2023-01-22 18:14:26.179662: step: 156/530, loss: 0.0008683777996338904
2023-01-22 18:14:27.235910: step: 160/530, loss: 5.054091161582619e-05
2023-01-22 18:14:28.295785: step: 164/530, loss: 0.004312948789447546
2023-01-22 18:14:29.363392: step: 168/530, loss: 0.0012752775801345706
2023-01-22 18:14:30.418595: step: 172/530, loss: 0.0002565025060903281
2023-01-22 18:14:31.486429: step: 176/530, loss: 0.0006659210775978863
2023-01-22 18:14:32.562827: step: 180/530, loss: 7.552302849944681e-05
2023-01-22 18:14:33.619724: step: 184/530, loss: 0.00293757114559412
2023-01-22 18:14:34.683461: step: 188/530, loss: 0.0085314204916358
2023-01-22 18:14:35.749060: step: 192/530, loss: 9.237771882908419e-05
2023-01-22 18:14:36.803218: step: 196/530, loss: 0.0006973854033276439
2023-01-22 18:14:37.854139: step: 200/530, loss: 0.005273876246064901
2023-01-22 18:14:38.918872: step: 204/530, loss: 0.0009348890744149685
2023-01-22 18:14:39.981459: step: 208/530, loss: 0.0007975925109349191
2023-01-22 18:14:41.041369: step: 212/530, loss: 0.0047297729179263115
2023-01-22 18:14:42.094258: step: 216/530, loss: 1.019892079057172e-05
2023-01-22 18:14:43.161904: step: 220/530, loss: 0.0040236846543848515
2023-01-22 18:14:44.236959: step: 224/530, loss: 0.0074284435249865055
2023-01-22 18:14:45.321872: step: 228/530, loss: 0.0002129941276507452
2023-01-22 18:14:46.396810: step: 232/530, loss: 0.0024064898025244474
2023-01-22 18:14:47.448547: step: 236/530, loss: 0.0029794531874358654
2023-01-22 18:14:48.496151: step: 240/530, loss: 0.00036643038038164377
2023-01-22 18:14:49.563815: step: 244/530, loss: 0.0010701948776841164
2023-01-22 18:14:50.614644: step: 248/530, loss: 0.0036041669081896544
2023-01-22 18:14:51.665606: step: 252/530, loss: 4.41591655544471e-05
2023-01-22 18:14:52.719034: step: 256/530, loss: 0.0005571102374233305
2023-01-22 18:14:53.769527: step: 260/530, loss: 0.0005424362607300282
2023-01-22 18:14:54.817748: step: 264/530, loss: 0.002520616864785552
2023-01-22 18:14:55.888599: step: 268/530, loss: 0.0010175707284361124
2023-01-22 18:14:56.950287: step: 272/530, loss: 6.816221684857737e-06
2023-01-22 18:14:57.993380: step: 276/530, loss: 0.002496181521564722
2023-01-22 18:14:59.080355: step: 280/530, loss: 0.0010457811877131462
2023-01-22 18:15:00.120439: step: 284/530, loss: 1.5459572466625104e-07
2023-01-22 18:15:01.170188: step: 288/530, loss: 0.0018196814926341176
2023-01-22 18:15:02.243329: step: 292/530, loss: 0.00687964865937829
2023-01-22 18:15:03.312134: step: 296/530, loss: 6.041045708116144e-06
2023-01-22 18:15:04.365076: step: 300/530, loss: 0.0007787408540025353
2023-01-22 18:15:05.438457: step: 304/530, loss: 0.004605806432664394
2023-01-22 18:15:06.500349: step: 308/530, loss: 0.002598462626338005
2023-01-22 18:15:07.563402: step: 312/530, loss: 0.0005670848186127841
2023-01-22 18:15:08.641455: step: 316/530, loss: 0.006672226823866367
2023-01-22 18:15:09.704609: step: 320/530, loss: 0.0065813204273581505
2023-01-22 18:15:10.751542: step: 324/530, loss: 5.380020957090892e-05
2023-01-22 18:15:11.824254: step: 328/530, loss: 0.0037262907717376947
2023-01-22 18:15:12.900292: step: 332/530, loss: 0.0003701312525663525
2023-01-22 18:15:13.967311: step: 336/530, loss: 0.00015366739535238594
2023-01-22 18:15:15.029872: step: 340/530, loss: 0.00253116968087852
2023-01-22 18:15:16.088287: step: 344/530, loss: 0.0003403834125492722
2023-01-22 18:15:17.163606: step: 348/530, loss: 0.0015883836895227432
2023-01-22 18:15:18.230298: step: 352/530, loss: 0.002112868707627058
2023-01-22 18:15:19.290417: step: 356/530, loss: 0.001961903879418969
2023-01-22 18:15:20.331981: step: 360/530, loss: 0.0015745072159916162
2023-01-22 18:15:21.400596: step: 364/530, loss: 1.5377738236566074e-05
2023-01-22 18:15:22.460944: step: 368/530, loss: 0.0009542052284814417
2023-01-22 18:15:23.530841: step: 372/530, loss: 3.190553979948163e-05
2023-01-22 18:15:24.591552: step: 376/530, loss: 0.00013872676936443895
2023-01-22 18:15:25.658442: step: 380/530, loss: 0.0003621930372901261
2023-01-22 18:15:26.727429: step: 384/530, loss: 0.0018190853297710419
2023-01-22 18:15:27.792741: step: 388/530, loss: 0.00251941429451108
2023-01-22 18:15:28.853300: step: 392/530, loss: 7.396494765998796e-05
2023-01-22 18:15:29.898011: step: 396/530, loss: 0.00039291175198741257
2023-01-22 18:15:30.956665: step: 400/530, loss: 0.0031388038769364357
2023-01-22 18:15:32.016592: step: 404/530, loss: 0.0055846828036010265
2023-01-22 18:15:33.089628: step: 408/530, loss: 0.00625471118837595
2023-01-22 18:15:34.146268: step: 412/530, loss: 0.004725403152406216
2023-01-22 18:15:35.201842: step: 416/530, loss: 0.0
2023-01-22 18:15:36.260126: step: 420/530, loss: 1.6092570149339736e-05
2023-01-22 18:15:37.340142: step: 424/530, loss: 0.0005232045077718794
2023-01-22 18:15:38.397389: step: 428/530, loss: 0.0007933232118375599
2023-01-22 18:15:39.464768: step: 432/530, loss: 6.643269443884492e-05
2023-01-22 18:15:40.524209: step: 436/530, loss: 0.013064311817288399
2023-01-22 18:15:41.587665: step: 440/530, loss: 0.0010323922615498304
2023-01-22 18:15:42.634310: step: 444/530, loss: 9.289631270803511e-05
2023-01-22 18:15:43.696348: step: 448/530, loss: 0.001928345998749137
2023-01-22 18:15:44.769239: step: 452/530, loss: 0.0031566466204822063
2023-01-22 18:15:45.827391: step: 456/530, loss: 6.839210982434452e-06
2023-01-22 18:15:46.898195: step: 460/530, loss: 0.0008118044934235513
2023-01-22 18:15:47.960613: step: 464/530, loss: 0.0063606128096580505
2023-01-22 18:15:49.020562: step: 468/530, loss: 0.000748766993638128
2023-01-22 18:15:50.086734: step: 472/530, loss: 0.00223116809502244
2023-01-22 18:15:51.141996: step: 476/530, loss: 0.005639788694679737
2023-01-22 18:15:52.224940: step: 480/530, loss: 0.00019345695909578353
2023-01-22 18:15:53.276588: step: 484/530, loss: 0.0015198041219264269
2023-01-22 18:15:54.349452: step: 488/530, loss: 0.003536706557497382
2023-01-22 18:15:55.415604: step: 492/530, loss: 0.0008151055662892759
2023-01-22 18:15:56.483738: step: 496/530, loss: 3.203093365300447e-05
2023-01-22 18:15:57.548454: step: 500/530, loss: 0.003479176666587591
2023-01-22 18:15:58.617915: step: 504/530, loss: 0.0008451720350421965
2023-01-22 18:15:59.665295: step: 508/530, loss: 3.2402367651229724e-05
2023-01-22 18:16:00.727771: step: 512/530, loss: 0.000926514680031687
2023-01-22 18:16:01.786939: step: 516/530, loss: 0.0022055639419704676
2023-01-22 18:16:02.839851: step: 520/530, loss: 6.625810783589259e-05
2023-01-22 18:16:03.893288: step: 524/530, loss: 0.0022769938223063946
2023-01-22 18:16:04.948278: step: 528/530, loss: 7.696865213802084e-05
2023-01-22 18:16:06.062509: step: 532/530, loss: 0.006276157684624195
2023-01-22 18:16:07.117476: step: 536/530, loss: 0.00013256288366392255
2023-01-22 18:16:08.166854: step: 540/530, loss: 1.2412041542120278e-05
2023-01-22 18:16:09.233750: step: 544/530, loss: 0.00023237848654389381
2023-01-22 18:16:10.288258: step: 548/530, loss: 0.0012774645583704114
2023-01-22 18:16:11.370864: step: 552/530, loss: 0.0011081855045631528
2023-01-22 18:16:12.439138: step: 556/530, loss: 0.00021407069289125502
2023-01-22 18:16:13.499017: step: 560/530, loss: 2.156742311854032e-06
2023-01-22 18:16:14.572411: step: 564/530, loss: 7.0766827775514685e-06
2023-01-22 18:16:15.632461: step: 568/530, loss: 0.0007736588013358414
2023-01-22 18:16:16.704313: step: 572/530, loss: 0.0018381121335551143
2023-01-22 18:16:17.769774: step: 576/530, loss: 0.04918888211250305
2023-01-22 18:16:18.835199: step: 580/530, loss: 0.0008418259094469249
2023-01-22 18:16:19.900806: step: 584/530, loss: 0.0017115594819188118
2023-01-22 18:16:20.946030: step: 588/530, loss: 0.0037227999418973923
2023-01-22 18:16:22.010809: step: 592/530, loss: 0.01742004230618477
2023-01-22 18:16:23.074396: step: 596/530, loss: 0.0006874825339764357
2023-01-22 18:16:24.123045: step: 600/530, loss: 0.0021324604749679565
2023-01-22 18:16:25.173278: step: 604/530, loss: 0.006022090557962656
2023-01-22 18:16:26.236255: step: 608/530, loss: 0.0004250803904142231
2023-01-22 18:16:27.311461: step: 612/530, loss: 0.002226212527602911
2023-01-22 18:16:28.377987: step: 616/530, loss: 0.012614063918590546
2023-01-22 18:16:29.428251: step: 620/530, loss: 0.0003680614463519305
2023-01-22 18:16:30.489538: step: 624/530, loss: 0.0007466141832992435
2023-01-22 18:16:31.557560: step: 628/530, loss: 0.0003385867166798562
2023-01-22 18:16:32.651042: step: 632/530, loss: 0.00013613130431622267
2023-01-22 18:16:33.699717: step: 636/530, loss: 7.823104830606553e-09
2023-01-22 18:16:34.761742: step: 640/530, loss: 1.2813528655897244e-06
2023-01-22 18:16:35.839780: step: 644/530, loss: 0.004567637573927641
2023-01-22 18:16:36.891784: step: 648/530, loss: 0.0025851507671177387
2023-01-22 18:16:37.949179: step: 652/530, loss: 0.007685238961130381
2023-01-22 18:16:39.007011: step: 656/530, loss: 7.399920377793023e-06
2023-01-22 18:16:40.075872: step: 660/530, loss: 0.0012012807419523597
2023-01-22 18:16:41.128891: step: 664/530, loss: 0.0005388844874687493
2023-01-22 18:16:42.182551: step: 668/530, loss: 0.0004091424052603543
2023-01-22 18:16:43.255529: step: 672/530, loss: 0.004368112422525883
2023-01-22 18:16:44.309374: step: 676/530, loss: 0.004165349528193474
2023-01-22 18:16:45.367641: step: 680/530, loss: 0.0014751310227438807
2023-01-22 18:16:46.442676: step: 684/530, loss: 0.004650105256587267
2023-01-22 18:16:47.498281: step: 688/530, loss: 0.0005390184815041721
2023-01-22 18:16:48.564303: step: 692/530, loss: 0.000247360352659598
2023-01-22 18:16:49.610792: step: 696/530, loss: 0.0036877612583339214
2023-01-22 18:16:50.678687: step: 700/530, loss: 0.004171156324446201
2023-01-22 18:16:51.754460: step: 704/530, loss: 0.02749238722026348
2023-01-22 18:16:52.812629: step: 708/530, loss: 0.0005593261448666453
2023-01-22 18:16:53.875816: step: 712/530, loss: 0.002645747270435095
2023-01-22 18:16:54.928807: step: 716/530, loss: 0.0038409684784710407
2023-01-22 18:16:55.991546: step: 720/530, loss: 0.006444224622100592
2023-01-22 18:16:57.030986: step: 724/530, loss: 0.00019817698921542615
2023-01-22 18:16:58.109630: step: 728/530, loss: 0.010310865007340908
2023-01-22 18:16:59.193499: step: 732/530, loss: 1.1548365819180617e-07
2023-01-22 18:17:00.268836: step: 736/530, loss: 0.0008617074345238507
2023-01-22 18:17:01.335854: step: 740/530, loss: 0.004651867784559727
2023-01-22 18:17:02.402714: step: 744/530, loss: 0.002701647114008665
2023-01-22 18:17:03.457487: step: 748/530, loss: 1.1392212400096469e-06
2023-01-22 18:17:04.513753: step: 752/530, loss: 8.342586079379544e-05
2023-01-22 18:17:05.576905: step: 756/530, loss: 0.0
2023-01-22 18:17:06.648088: step: 760/530, loss: 0.0024088951759040356
2023-01-22 18:17:07.719010: step: 764/530, loss: 0.004983244463801384
2023-01-22 18:17:08.771975: step: 768/530, loss: 0.0034380133729428053
2023-01-22 18:17:09.844917: step: 772/530, loss: 0.002349910093471408
2023-01-22 18:17:10.900011: step: 776/530, loss: 0.000318461301503703
2023-01-22 18:17:11.951555: step: 780/530, loss: 0.0014323717914521694
2023-01-22 18:17:13.015601: step: 784/530, loss: 0.0031647919677197933
2023-01-22 18:17:14.065758: step: 788/530, loss: 0.003769282018765807
2023-01-22 18:17:15.128598: step: 792/530, loss: 0.004636148922145367
2023-01-22 18:17:16.176358: step: 796/530, loss: 3.136169834760949e-05
2023-01-22 18:17:17.232519: step: 800/530, loss: 0.001004164689220488
2023-01-22 18:17:18.295228: step: 804/530, loss: 0.0023598624393343925
2023-01-22 18:17:19.346842: step: 808/530, loss: 0.00020291241526138037
2023-01-22 18:17:20.416601: step: 812/530, loss: 0.0016126090195029974
2023-01-22 18:17:21.485142: step: 816/530, loss: 4.961536319569859e-07
2023-01-22 18:17:22.545326: step: 820/530, loss: 0.002547695068642497
2023-01-22 18:17:23.614707: step: 824/530, loss: 0.010903198271989822
2023-01-22 18:17:24.674657: step: 828/530, loss: 0.0006640401552431285
2023-01-22 18:17:25.765251: step: 832/530, loss: 0.00965951383113861
2023-01-22 18:17:26.833762: step: 836/530, loss: 0.008431728929281235
2023-01-22 18:17:27.897705: step: 840/530, loss: 0.00041934216278605163
2023-01-22 18:17:28.940865: step: 844/530, loss: 2.2771193471271545e-05
2023-01-22 18:17:30.006618: step: 848/530, loss: 0.002858812687918544
2023-01-22 18:17:31.058587: step: 852/530, loss: 9.671240695752203e-05
2023-01-22 18:17:32.150641: step: 856/530, loss: 1.9999399228254333e-05
2023-01-22 18:17:33.202876: step: 860/530, loss: 0.0015814757207408547
2023-01-22 18:17:34.259662: step: 864/530, loss: 0.0038441878277808428
2023-01-22 18:17:35.322927: step: 868/530, loss: 0.003081025555729866
2023-01-22 18:17:36.369951: step: 872/530, loss: 0.006502851378172636
2023-01-22 18:17:37.420396: step: 876/530, loss: 0.0036619931925088167
2023-01-22 18:17:38.484782: step: 880/530, loss: 0.004631872288882732
2023-01-22 18:17:39.558935: step: 884/530, loss: 0.0006069493247196078
2023-01-22 18:17:40.628951: step: 888/530, loss: 0.0002082035061903298
2023-01-22 18:17:41.684362: step: 892/530, loss: 0.0013439744943752885
2023-01-22 18:17:42.740950: step: 896/530, loss: 0.00020763858628924936
2023-01-22 18:17:43.817036: step: 900/530, loss: 0.00020743614004459232
2023-01-22 18:17:44.879621: step: 904/530, loss: 0.0014298639725893736
2023-01-22 18:17:45.935836: step: 908/530, loss: 0.00015233505109790713
2023-01-22 18:17:46.992622: step: 912/530, loss: 1.6949562677837093e-06
2023-01-22 18:17:48.052352: step: 916/530, loss: 0.0029666146729141474
2023-01-22 18:17:49.116991: step: 920/530, loss: 0.0038765030913054943
2023-01-22 18:17:50.175304: step: 924/530, loss: 0.0006100321188569069
2023-01-22 18:17:51.237495: step: 928/530, loss: 9.341269105789252e-06
2023-01-22 18:17:52.316225: step: 932/530, loss: 9.834764205152169e-05
2023-01-22 18:17:53.366159: step: 936/530, loss: 0.0001672635698923841
2023-01-22 18:17:54.426869: step: 940/530, loss: 0.00016907465760596097
2023-01-22 18:17:55.477337: step: 944/530, loss: 4.353276835900033e-06
2023-01-22 18:17:56.546565: step: 948/530, loss: 0.001261532655917108
2023-01-22 18:17:57.605439: step: 952/530, loss: 0.00028174096951261163
2023-01-22 18:17:58.663823: step: 956/530, loss: 2.0496001525316387e-05
2023-01-22 18:17:59.749281: step: 960/530, loss: 0.0011348148109391332
2023-01-22 18:18:00.828070: step: 964/530, loss: 0.003016910282894969
2023-01-22 18:18:01.876365: step: 968/530, loss: 6.167294486658648e-06
2023-01-22 18:18:02.944578: step: 972/530, loss: 0.0020489676389843225
2023-01-22 18:18:04.023567: step: 976/530, loss: 0.0005256329895928502
2023-01-22 18:18:05.090058: step: 980/530, loss: 0.002442756202071905
2023-01-22 18:18:06.149214: step: 984/530, loss: 0.0012856120010837913
2023-01-22 18:18:07.229671: step: 988/530, loss: 0.00038124556886032224
2023-01-22 18:18:08.306461: step: 992/530, loss: 0.0017621335573494434
2023-01-22 18:18:09.365883: step: 996/530, loss: 0.001312508713454008
2023-01-22 18:18:10.418396: step: 1000/530, loss: 2.6656339358055448e-08
2023-01-22 18:18:11.467370: step: 1004/530, loss: 0.003280250821262598
2023-01-22 18:18:12.526693: step: 1008/530, loss: 4.267723124939948e-05
2023-01-22 18:18:13.589193: step: 1012/530, loss: 5.9973299357807264e-05
2023-01-22 18:18:14.635526: step: 1016/530, loss: 0.00016806698113214225
2023-01-22 18:18:15.708999: step: 1020/530, loss: 0.0076988753862679005
2023-01-22 18:18:16.779123: step: 1024/530, loss: 0.0017748448299244046
2023-01-22 18:18:17.852149: step: 1028/530, loss: 7.556439959444106e-05
2023-01-22 18:18:18.913654: step: 1032/530, loss: 0.0007024398073554039
2023-01-22 18:18:19.964949: step: 1036/530, loss: 0.0002144437748938799
2023-01-22 18:18:21.031704: step: 1040/530, loss: 0.002975761890411377
2023-01-22 18:18:22.096747: step: 1044/530, loss: 0.00018304727564100176
2023-01-22 18:18:23.168000: step: 1048/530, loss: 0.0013600110542029142
2023-01-22 18:18:24.219664: step: 1052/530, loss: 1.528535221950733e-06
2023-01-22 18:18:25.278946: step: 1056/530, loss: 0.0011544511653482914
2023-01-22 18:18:26.335689: step: 1060/530, loss: 5.596477785729803e-05
2023-01-22 18:18:27.393033: step: 1064/530, loss: 0.00022398446162696928
2023-01-22 18:18:28.462922: step: 1068/530, loss: 0.0025621468666940928
2023-01-22 18:18:29.512968: step: 1072/530, loss: 0.0022698238026350737
2023-01-22 18:18:30.569540: step: 1076/530, loss: 0.002758368384093046
2023-01-22 18:18:31.651223: step: 1080/530, loss: 0.023883560672402382
2023-01-22 18:18:32.713312: step: 1084/530, loss: 0.0003798389807343483
2023-01-22 18:18:33.778338: step: 1088/530, loss: 0.011034381575882435
2023-01-22 18:18:34.840903: step: 1092/530, loss: 8.343707804669975e-07
2023-01-22 18:18:35.886792: step: 1096/530, loss: 3.8988386222627014e-05
2023-01-22 18:18:36.946464: step: 1100/530, loss: 0.009063157252967358
2023-01-22 18:18:37.986840: step: 1104/530, loss: 0.003054446540772915
2023-01-22 18:18:39.045222: step: 1108/530, loss: 0.004694691859185696
2023-01-22 18:18:40.111938: step: 1112/530, loss: 0.002871186938136816
2023-01-22 18:18:41.183072: step: 1116/530, loss: 0.00413478771224618
2023-01-22 18:18:42.235130: step: 1120/530, loss: 0.0037038077134639025
2023-01-22 18:18:43.305302: step: 1124/530, loss: 0.001354366890154779
2023-01-22 18:18:44.372032: step: 1128/530, loss: 0.010890726000070572
2023-01-22 18:18:45.417226: step: 1132/530, loss: 0.002016516635194421
2023-01-22 18:18:46.466713: step: 1136/530, loss: 0.000916333228815347
2023-01-22 18:18:47.544581: step: 1140/530, loss: 0.006287013180553913
2023-01-22 18:18:48.597783: step: 1144/530, loss: 0.0013387412764132023
2023-01-22 18:18:49.668509: step: 1148/530, loss: 0.0
2023-01-22 18:18:50.749999: step: 1152/530, loss: 0.0005171552766114473
2023-01-22 18:18:51.813472: step: 1156/530, loss: 0.0017185205360874534
2023-01-22 18:18:52.868105: step: 1160/530, loss: 0.0003559146716725081
2023-01-22 18:18:53.932414: step: 1164/530, loss: 0.000423509773099795
2023-01-22 18:18:54.990861: step: 1168/530, loss: 0.00029431929579004645
2023-01-22 18:18:56.031972: step: 1172/530, loss: 0.001086080214008689
2023-01-22 18:18:57.087953: step: 1176/530, loss: 0.0009367995662614703
2023-01-22 18:18:58.138836: step: 1180/530, loss: 0.016340885311365128
2023-01-22 18:18:59.198263: step: 1184/530, loss: 0.0018556666327640414
2023-01-22 18:19:00.262676: step: 1188/530, loss: 0.0019157781498506665
2023-01-22 18:19:01.321882: step: 1192/530, loss: 0.000545868300832808
2023-01-22 18:19:02.413029: step: 1196/530, loss: 0.0022360514849424362
2023-01-22 18:19:03.477630: step: 1200/530, loss: 0.0006502094329334795
2023-01-22 18:19:04.531872: step: 1204/530, loss: 2.955450145236682e-05
2023-01-22 18:19:05.587222: step: 1208/530, loss: 0.005296939052641392
2023-01-22 18:19:06.633971: step: 1212/530, loss: 2.97556853183778e-05
2023-01-22 18:19:07.689596: step: 1216/530, loss: 0.004185340367257595
2023-01-22 18:19:08.752857: step: 1220/530, loss: 0.0014158920384943485
2023-01-22 18:19:09.814475: step: 1224/530, loss: 0.0016025553923100233
2023-01-22 18:19:10.867564: step: 1228/530, loss: 0.01026669517159462
2023-01-22 18:19:11.915991: step: 1232/530, loss: 0.0005135299870744348
2023-01-22 18:19:12.989180: step: 1236/530, loss: 4.446384991751984e-05
2023-01-22 18:19:14.040579: step: 1240/530, loss: 0.00016691209748387337
2023-01-22 18:19:15.108265: step: 1244/530, loss: 0.0014156574616208673
2023-01-22 18:19:16.180235: step: 1248/530, loss: 0.00014650814409833401
2023-01-22 18:19:17.243967: step: 1252/530, loss: 0.0006092636613175273
2023-01-22 18:19:18.301861: step: 1256/530, loss: 0.0019875189755111933
2023-01-22 18:19:19.376773: step: 1260/530, loss: 0.0006706563872285187
2023-01-22 18:19:20.444022: step: 1264/530, loss: 0.0016247257590293884
2023-01-22 18:19:21.499051: step: 1268/530, loss: 1.8511378584662452e-05
2023-01-22 18:19:22.560777: step: 1272/530, loss: 0.00027250946732237935
2023-01-22 18:19:23.611735: step: 1276/530, loss: 0.0032922381069511175
2023-01-22 18:19:24.661383: step: 1280/530, loss: 0.0008868347504176199
2023-01-22 18:19:25.729095: step: 1284/530, loss: 0.0013795640552416444
2023-01-22 18:19:26.789553: step: 1288/530, loss: 0.004981372971087694
2023-01-22 18:19:27.844215: step: 1292/530, loss: 0.0003823238948825747
2023-01-22 18:19:28.889716: step: 1296/530, loss: 0.0048320177011191845
2023-01-22 18:19:29.945624: step: 1300/530, loss: 0.01629387028515339
2023-01-22 18:19:31.015412: step: 1304/530, loss: 0.0005811612354591489
2023-01-22 18:19:32.107570: step: 1308/530, loss: 2.5535851818858646e-05
2023-01-22 18:19:33.165534: step: 1312/530, loss: 0.0021639582701027393
2023-01-22 18:19:34.226751: step: 1316/530, loss: 0.0001765547349350527
2023-01-22 18:19:35.291571: step: 1320/530, loss: 0.0021695985924452543
2023-01-22 18:19:36.344702: step: 1324/530, loss: 0.00022371923842001706
2023-01-22 18:19:37.417241: step: 1328/530, loss: 4.400361888201587e-07
2023-01-22 18:19:38.466099: step: 1332/530, loss: 1.7383737827003642e-07
2023-01-22 18:19:39.517503: step: 1336/530, loss: 0.0002773888409137726
2023-01-22 18:19:40.587438: step: 1340/530, loss: 0.007211625576019287
2023-01-22 18:19:41.658459: step: 1344/530, loss: 0.0002806336560752243
2023-01-22 18:19:42.728662: step: 1348/530, loss: 0.0029637389816343784
2023-01-22 18:19:43.786851: step: 1352/530, loss: 0.00015604398504365236
2023-01-22 18:19:44.859414: step: 1356/530, loss: 0.004185238387435675
2023-01-22 18:19:45.907524: step: 1360/530, loss: 0.012260166928172112
2023-01-22 18:19:46.952780: step: 1364/530, loss: 9.475841943640262e-05
2023-01-22 18:19:47.999524: step: 1368/530, loss: 7.681493298150599e-05
2023-01-22 18:19:49.051150: step: 1372/530, loss: 3.408749080335838e-06
2023-01-22 18:19:50.125405: step: 1376/530, loss: 0.0001385969517286867
2023-01-22 18:19:51.191211: step: 1380/530, loss: 0.001058325171470642
2023-01-22 18:19:52.258766: step: 1384/530, loss: 0.0030905918683856726
2023-01-22 18:19:53.310228: step: 1388/530, loss: 8.95018019946292e-05
2023-01-22 18:19:54.375519: step: 1392/530, loss: 0.004047696944326162
2023-01-22 18:19:55.422331: step: 1396/530, loss: 0.00015116769645828754
2023-01-22 18:19:56.496076: step: 1400/530, loss: 0.000206448879907839
2023-01-22 18:19:57.550804: step: 1404/530, loss: 8.953497854236048e-06
2023-01-22 18:19:58.611409: step: 1408/530, loss: 0.0025303333532065153
2023-01-22 18:19:59.671035: step: 1412/530, loss: 0.0001910560531541705
2023-01-22 18:20:00.745711: step: 1416/530, loss: 3.147565439576283e-05
2023-01-22 18:20:01.810455: step: 1420/530, loss: 0.0036020714323967695
2023-01-22 18:20:02.890382: step: 1424/530, loss: 0.00024343312543351203
2023-01-22 18:20:03.936381: step: 1428/530, loss: 0.0016813600668683648
2023-01-22 18:20:05.006605: step: 1432/530, loss: 0.007239566184580326
2023-01-22 18:20:06.053470: step: 1436/530, loss: 1.7316924640908837e-05
2023-01-22 18:20:07.121517: step: 1440/530, loss: 0.0053115058690309525
2023-01-22 18:20:08.199451: step: 1444/530, loss: 0.003082724055275321
2023-01-22 18:20:09.261504: step: 1448/530, loss: 0.0006793970824219286
2023-01-22 18:20:10.312659: step: 1452/530, loss: 0.00024168261734303087
2023-01-22 18:20:11.370796: step: 1456/530, loss: 7.014258881099522e-05
2023-01-22 18:20:12.438861: step: 1460/530, loss: 1.3151779057807289e-05
2023-01-22 18:20:13.516556: step: 1464/530, loss: 0.0012929317308589816
2023-01-22 18:20:14.564485: step: 1468/530, loss: 0.00027637367020361125
2023-01-22 18:20:15.621549: step: 1472/530, loss: 0.001176758436486125
2023-01-22 18:20:16.673813: step: 1476/530, loss: 2.7925574613618664e-05
2023-01-22 18:20:17.737857: step: 1480/530, loss: 0.0008473570342175663
2023-01-22 18:20:18.792693: step: 1484/530, loss: 7.32930566300638e-05
2023-01-22 18:20:19.842176: step: 1488/530, loss: 0.002474632579833269
2023-01-22 18:20:20.902825: step: 1492/530, loss: 0.0016974069876596332
2023-01-22 18:20:21.964063: step: 1496/530, loss: 0.007753693498671055
2023-01-22 18:20:23.026795: step: 1500/530, loss: 0.0005194901605136693
2023-01-22 18:20:24.077746: step: 1504/530, loss: 0.0016985370311886072
2023-01-22 18:20:25.134316: step: 1508/530, loss: 0.0027572494000196457
2023-01-22 18:20:26.178216: step: 1512/530, loss: 0.0043540699407458305
2023-01-22 18:20:27.224301: step: 1516/530, loss: 0.0005303248763084412
2023-01-22 18:20:28.287269: step: 1520/530, loss: 0.006779911927878857
2023-01-22 18:20:29.337702: step: 1524/530, loss: 0.0032566606532782316
2023-01-22 18:20:30.387173: step: 1528/530, loss: 1.0943324923573527e-05
2023-01-22 18:20:31.432241: step: 1532/530, loss: 5.825030257256003e-06
2023-01-22 18:20:32.508128: step: 1536/530, loss: 0.0052016787230968475
2023-01-22 18:20:33.582527: step: 1540/530, loss: 0.0030401197727769613
2023-01-22 18:20:34.627719: step: 1544/530, loss: 0.001184574794024229
2023-01-22 18:20:35.688845: step: 1548/530, loss: 0.0002245716896140948
2023-01-22 18:20:36.737059: step: 1552/530, loss: 0.0058486429043114185
2023-01-22 18:20:37.794287: step: 1556/530, loss: 0.0002876336802728474
2023-01-22 18:20:38.862640: step: 1560/530, loss: 0.0022663280833512545
2023-01-22 18:20:39.926414: step: 1564/530, loss: 0.000839273096062243
2023-01-22 18:20:40.985011: step: 1568/530, loss: 0.0032593607902526855
2023-01-22 18:20:42.045761: step: 1572/530, loss: 0.008406402543187141
2023-01-22 18:20:43.098208: step: 1576/530, loss: 0.00025903346249833703
2023-01-22 18:20:44.165341: step: 1580/530, loss: 3.8040841900510713e-05
2023-01-22 18:20:45.224851: step: 1584/530, loss: 0.0007708763005211949
2023-01-22 18:20:46.297575: step: 1588/530, loss: 0.0016108440468087792
2023-01-22 18:20:47.362283: step: 1592/530, loss: 0.0004349317750893533
2023-01-22 18:20:48.410102: step: 1596/530, loss: 1.9772909581661224e-05
2023-01-22 18:20:49.463537: step: 1600/530, loss: 5.2032377425348386e-05
2023-01-22 18:20:50.537611: step: 1604/530, loss: 0.002038426697254181
2023-01-22 18:20:51.608827: step: 1608/530, loss: 0.0009587907115928829
2023-01-22 18:20:52.672557: step: 1612/530, loss: 0.003981547895818949
2023-01-22 18:20:53.733682: step: 1616/530, loss: 0.0011710278922691941
2023-01-22 18:20:54.795302: step: 1620/530, loss: 0.0007438991451635957
2023-01-22 18:20:55.859204: step: 1624/530, loss: 0.0018043600721284747
2023-01-22 18:20:56.925859: step: 1628/530, loss: 0.0015680512879043818
2023-01-22 18:20:57.973597: step: 1632/530, loss: 0.0010865392396226525
2023-01-22 18:20:59.041389: step: 1636/530, loss: 0.001785994740203023
2023-01-22 18:21:00.099452: step: 1640/530, loss: 4.9126210797112435e-05
2023-01-22 18:21:01.161764: step: 1644/530, loss: 3.431293953326531e-05
2023-01-22 18:21:02.215428: step: 1648/530, loss: 3.208514317520894e-05
2023-01-22 18:21:03.275614: step: 1652/530, loss: 0.004645385779440403
2023-01-22 18:21:04.341401: step: 1656/530, loss: 0.005052377935498953
2023-01-22 18:21:05.394910: step: 1660/530, loss: 0.006233102176338434
2023-01-22 18:21:06.463274: step: 1664/530, loss: 0.0032794878352433443
2023-01-22 18:21:07.534467: step: 1668/530, loss: 0.003302312921732664
2023-01-22 18:21:08.594148: step: 1672/530, loss: 7.185374852269888e-05
2023-01-22 18:21:09.658682: step: 1676/530, loss: 6.818242400186136e-05
2023-01-22 18:21:10.706517: step: 1680/530, loss: 0.0009039552533067763
2023-01-22 18:21:11.773055: step: 1684/530, loss: 0.0016256526578217745
2023-01-22 18:21:12.825609: step: 1688/530, loss: 0.0015177977038547397
2023-01-22 18:21:13.886010: step: 1692/530, loss: 2.727987157413736e-05
2023-01-22 18:21:14.939976: step: 1696/530, loss: 0.00011824251123471186
2023-01-22 18:21:16.023405: step: 1700/530, loss: 0.0009916438721120358
2023-01-22 18:21:17.087712: step: 1704/530, loss: 9.497692190052476e-06
2023-01-22 18:21:18.158204: step: 1708/530, loss: 0.00812023226171732
2023-01-22 18:21:19.226593: step: 1712/530, loss: 8.056111983023584e-05
2023-01-22 18:21:20.291495: step: 1716/530, loss: 0.00035489178844727576
2023-01-22 18:21:21.339643: step: 1720/530, loss: 0.0001230276538990438
2023-01-22 18:21:22.400176: step: 1724/530, loss: 0.0056683882139623165
2023-01-22 18:21:23.444125: step: 1728/530, loss: 0.0003738945524673909
2023-01-22 18:21:24.498299: step: 1732/530, loss: 0.0005729576223529875
2023-01-22 18:21:25.566658: step: 1736/530, loss: 0.0008201290620490909
2023-01-22 18:21:26.623895: step: 1740/530, loss: 0.001202728133648634
2023-01-22 18:21:27.681279: step: 1744/530, loss: 0.0017263969639316201
2023-01-22 18:21:28.752472: step: 1748/530, loss: 0.0021032593213021755
2023-01-22 18:21:29.811367: step: 1752/530, loss: 0.003257678123190999
2023-01-22 18:21:30.863945: step: 1756/530, loss: 8.008502845768817e-06
2023-01-22 18:21:31.919442: step: 1760/530, loss: 2.317342114110943e-05
2023-01-22 18:21:32.974764: step: 1764/530, loss: 0.001302529708482325
2023-01-22 18:21:34.034956: step: 1768/530, loss: 0.01977110467851162
2023-01-22 18:21:35.095851: step: 1772/530, loss: 0.0033850783947855234
2023-01-22 18:21:36.151306: step: 1776/530, loss: 0.00316097354516387
2023-01-22 18:21:37.226362: step: 1780/530, loss: 0.0034116278402507305
2023-01-22 18:21:38.289755: step: 1784/530, loss: 0.0005083832074888051
2023-01-22 18:21:39.337953: step: 1788/530, loss: 0.0027566407807171345
2023-01-22 18:21:40.402372: step: 1792/530, loss: 0.0017061693361029029
2023-01-22 18:21:41.464862: step: 1796/530, loss: 9.384921577293426e-05
2023-01-22 18:21:42.523712: step: 1800/530, loss: 6.57826240058057e-05
2023-01-22 18:21:43.572602: step: 1804/530, loss: 0.007787159178406
2023-01-22 18:21:44.636759: step: 1808/530, loss: 0.00397125631570816
2023-01-22 18:21:45.691933: step: 1812/530, loss: 0.0001655475643929094
2023-01-22 18:21:46.740401: step: 1816/530, loss: 1.7508815730593597e-08
2023-01-22 18:21:47.794733: step: 1820/530, loss: 2.2891772459843196e-05
2023-01-22 18:21:48.853620: step: 1824/530, loss: 0.00040441000601276755
2023-01-22 18:21:49.912949: step: 1828/530, loss: 2.132779627572745e-05
2023-01-22 18:21:50.966656: step: 1832/530, loss: 0.00047313820687122643
2023-01-22 18:21:52.019429: step: 1836/530, loss: 1.781730679795146e-05
2023-01-22 18:21:53.081496: step: 1840/530, loss: 2.5383496904396452e-05
2023-01-22 18:21:54.145836: step: 1844/530, loss: 0.0005910950712859631
2023-01-22 18:21:55.215636: step: 1848/530, loss: 0.0001238746044691652
2023-01-22 18:21:56.255974: step: 1852/530, loss: 0.007283177226781845
2023-01-22 18:21:57.333219: step: 1856/530, loss: 0.006267290096729994
2023-01-22 18:21:58.396125: step: 1860/530, loss: 0.003503653919324279
2023-01-22 18:21:59.464425: step: 1864/530, loss: 0.002001160988584161
2023-01-22 18:22:00.519471: step: 1868/530, loss: 1.126896975733871e-08
2023-01-22 18:22:01.582230: step: 1872/530, loss: 8.465792780043557e-05
2023-01-22 18:22:02.651649: step: 1876/530, loss: 0.003231597598642111
2023-01-22 18:22:03.716628: step: 1880/530, loss: 0.0001995859493035823
2023-01-22 18:22:04.778527: step: 1884/530, loss: 0.010597738437354565
2023-01-22 18:22:05.833252: step: 1888/530, loss: 0.005382729694247246
2023-01-22 18:22:06.873438: step: 1892/530, loss: 0.00167090876493603
2023-01-22 18:22:07.941738: step: 1896/530, loss: 7.297228876268491e-05
2023-01-22 18:22:09.010399: step: 1900/530, loss: 0.008068029768764973
2023-01-22 18:22:10.069102: step: 1904/530, loss: 0.0005959459813311696
2023-01-22 18:22:11.133180: step: 1908/530, loss: 0.000444756296928972
2023-01-22 18:22:12.187479: step: 1912/530, loss: 4.090618313057348e-05
2023-01-22 18:22:13.252977: step: 1916/530, loss: 0.00695403665304184
2023-01-22 18:22:14.323777: step: 1920/530, loss: 0.0002737498434726149
2023-01-22 18:22:15.406500: step: 1924/530, loss: 5.258370492811082e-06
2023-01-22 18:22:16.465577: step: 1928/530, loss: 0.0008209809311665595
2023-01-22 18:22:17.513943: step: 1932/530, loss: 3.482078682282008e-05
2023-01-22 18:22:18.573529: step: 1936/530, loss: 7.039401680231094e-05
2023-01-22 18:22:19.631507: step: 1940/530, loss: 0.0022663441486656666
2023-01-22 18:22:20.701202: step: 1944/530, loss: 7.089827704476193e-05
2023-01-22 18:22:21.746183: step: 1948/530, loss: 0.003127817530184984
2023-01-22 18:22:22.800124: step: 1952/530, loss: 0.0023610026109963655
2023-01-22 18:22:23.846406: step: 1956/530, loss: 7.367778920297496e-08
2023-01-22 18:22:24.909887: step: 1960/530, loss: 0.00044750398956239223
2023-01-22 18:22:25.967877: step: 1964/530, loss: 0.0002953125222120434
2023-01-22 18:22:27.023930: step: 1968/530, loss: 0.0032857945188879967
2023-01-22 18:22:28.097396: step: 1972/530, loss: 0.000277798215392977
2023-01-22 18:22:29.150405: step: 1976/530, loss: 0.003090447746217251
2023-01-22 18:22:30.238222: step: 1980/530, loss: 0.0045261383056640625
2023-01-22 18:22:31.306053: step: 1984/530, loss: 0.0002901342522818595
2023-01-22 18:22:32.375974: step: 1988/530, loss: 0.001559880212880671
2023-01-22 18:22:33.454833: step: 1992/530, loss: 0.0010950490832328796
2023-01-22 18:22:34.500428: step: 1996/530, loss: 0.0001488328562118113
2023-01-22 18:22:35.561208: step: 2000/530, loss: 0.0023567762691527605
2023-01-22 18:22:36.617144: step: 2004/530, loss: 0.0008475448121316731
2023-01-22 18:22:37.668933: step: 2008/530, loss: 2.2833859475213103e-05
2023-01-22 18:22:38.728477: step: 2012/530, loss: 0.0005100523703731596
2023-01-22 18:22:39.781162: step: 2016/530, loss: 0.01809227094054222
2023-01-22 18:22:40.850059: step: 2020/530, loss: 0.006908607669174671
2023-01-22 18:22:41.903191: step: 2024/530, loss: 0.0006793041247874498
2023-01-22 18:22:42.946878: step: 2028/530, loss: 7.700379683228675e-06
2023-01-22 18:22:44.000356: step: 2032/530, loss: 0.0017141217831522226
2023-01-22 18:22:45.051268: step: 2036/530, loss: 0.0023029486183077097
2023-01-22 18:22:46.117656: step: 2040/530, loss: 8.715346484677866e-05
2023-01-22 18:22:47.189425: step: 2044/530, loss: 0.001045835204422474
2023-01-22 18:22:48.240203: step: 2048/530, loss: 9.370435691380408e-06
2023-01-22 18:22:49.283529: step: 2052/530, loss: 0.001589095452800393
2023-01-22 18:22:50.334501: step: 2056/530, loss: 0.00012409732153173536
2023-01-22 18:22:51.381525: step: 2060/530, loss: 0.004516906570643187
2023-01-22 18:22:52.430495: step: 2064/530, loss: 0.005698220804333687
2023-01-22 18:22:53.493080: step: 2068/530, loss: 0.00023478364164475352
2023-01-22 18:22:54.544985: step: 2072/530, loss: 0.0012739752419292927
2023-01-22 18:22:55.603735: step: 2076/530, loss: 0.003576847957447171
2023-01-22 18:22:56.662122: step: 2080/530, loss: 0.002340570092201233
2023-01-22 18:22:57.748327: step: 2084/530, loss: 0.002400406636297703
2023-01-22 18:22:58.812193: step: 2088/530, loss: 2.1095705960760824e-05
2023-01-22 18:22:59.868356: step: 2092/530, loss: 0.0019320037681609392
2023-01-22 18:23:00.930291: step: 2096/530, loss: 0.00022332361550070345
2023-01-22 18:23:01.998520: step: 2100/530, loss: 0.0001658980909269303
2023-01-22 18:23:03.059167: step: 2104/530, loss: 0.0015217919135466218
2023-01-22 18:23:04.123333: step: 2108/530, loss: 0.003103397088125348
2023-01-22 18:23:05.167362: step: 2112/530, loss: 0.0008773942245170474
2023-01-22 18:23:06.227081: step: 2116/530, loss: 7.185334106907248e-05
2023-01-22 18:23:07.299316: step: 2120/530, loss: 0.00010265658784192055
==================================================
Loss: 0.002
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3635524296675192, 'r': 0.2931874432802574, 'f1': 0.32460038363171356}, 'combined': 0.23917923004442052, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3501411687036225, 'r': 0.2338302541644554, 'f1': 0.2804027569338891}, 'combined': 0.1859665952722166, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3215169375603476, 'r': 0.29107025786713286, 'f1': 0.3055369704847836}, 'combined': 0.2036913136565224, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.4004026563028973, 'r': 0.3199057617948625, 'f1': 0.35565630935575276}, 'combined': 0.23211253873743862, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3239904596587545, 'r': 0.34612263527111725, 'f1': 0.3346910619961079}, 'combined': 0.24661446673397422, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3590356337110211, 'r': 0.331680537809229, 'f1': 0.3448164006927628}, 'combined': 0.22868652481178048, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.59375, 'r': 0.41304347826086957, 'f1': 0.4871794871794871}, 'combined': 0.32478632478632474, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.25862068965517243, 'f1': 0.33333333333333337}, 'combined': 0.22222222222222224, 'stategy': 1, 'epoch': 19}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3635524296675192, 'r': 0.2931874432802574, 'f1': 0.32460038363171356}, 'combined': 0.23917923004442052, 'stategy': 1, 'epoch': 19}
Test for Chinese: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3501411687036225, 'r': 0.2338302541644554, 'f1': 0.2804027569338891}, 'combined': 0.1859665952722166, 'stategy': 1, 'epoch': 19}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.37369791666666663, 'r': 0.3416666666666666, 'f1': 0.35696517412935314}, 'combined': 0.23797678275290207, 'stategy': 1, 'epoch': 19}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31747399612965654, 'r': 0.2868088942307692, 'f1': 0.3013633754305396}, 'combined': 0.20090891695369306, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.96875, 'r': 0.49206349206349204, 'f1': 0.6526315789473683}, 'slot': {'p': 0.3785765844514869, 'r': 0.32346318220898274, 'f1': 0.3488565535225851}, 'combined': 0.22767480335158183, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.640625, 'r': 0.44565217391304346, 'f1': 0.5256410256410257}, 'combined': 0.3504273504273504, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32879926312303365, 'r': 0.3425252285665, 'f1': 0.33552192463670166}, 'combined': 0.24722668131125383, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9552238805970149, 'r': 0.5079365079365079, 'f1': 0.6632124352331605}, 'slot': {'p': 0.3615408946479653, 'r': 0.3292995854282766, 'f1': 0.3446678941274667}, 'combined': 0.22858803341096232, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.25862068965517243, 'f1': 0.34090909090909094}, 'combined': 0.2272727272727273, 'stategy': 1, 'epoch': 3}