Command that produces this log: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024])
>>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024])
>>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024])
>>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024])
>>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.pooler.dense.weight: torch.Size([1024, 1024])
>>> xlmr.pooler.dense.bias: torch.Size([1024])
>>> type_embedding.weight: torch.Size([123, 100])
>>> trans_rep.weight: torch.Size([1024, 1124])
>>> trans_rep.bias: torch.Size([1024])
>>> coref_type_ffn.weight: torch.Size([3, 4096])
>>> coref_type_ffn.bias: torch.Size([3])
n_trainable_params: 561067023, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:19:26.349064: step: 4/529, loss: 0.020952977240085602
2023-01-24 07:19:27.454203: step: 8/529, loss: 0.021386858075857162
2023-01-24 07:19:28.560601: step: 12/529, loss: 0.10582775622606277
2023-01-24 07:19:29.677531: step: 16/529, loss: 0.015845540910959244
2023-01-24 07:19:30.774786: step: 20/529, loss: 0.020487669855356216
2023-01-24 07:19:31.881822: step: 24/529, loss: 0.01992269977927208
2023-01-24 07:19:32.980389: step: 28/529, loss: 0.021042712032794952
2023-01-24 07:19:34.078188: step: 32/529, loss: 0.015479862689971924
2023-01-24 07:19:35.193824: step: 36/529, loss: 0.01939421147108078
2023-01-24 07:19:36.284842: step: 40/529, loss: 0.024981655180454254
2023-01-24 07:19:37.370515: step: 44/529, loss: 0.05722786486148834
2023-01-24 07:19:38.473690: step: 48/529, loss: 0.017989467829465866
2023-01-24 07:19:39.561698: step: 52/529, loss: 0.020983770489692688
2023-01-24 07:19:40.668510: step: 56/529, loss: 0.06493190675973892
2023-01-24 07:19:41.781323: step: 60/529, loss: 0.017172398045659065
2023-01-24 07:19:42.872784: step: 64/529, loss: 0.01399940811097622
2023-01-24 07:19:43.998172: step: 68/529, loss: 0.005797416903078556
2023-01-24 07:19:45.099763: step: 72/529, loss: 0.057554345577955246
2023-01-24 07:19:46.219762: step: 76/529, loss: 0.016582118347287178
2023-01-24 07:19:47.302168: step: 80/529, loss: 0.01060114149004221
2023-01-24 07:19:48.419232: step: 84/529, loss: 0.016607947647571564
2023-01-24 07:19:49.522046: step: 88/529, loss: 0.04210435226559639
2023-01-24 07:19:50.623502: step: 92/529, loss: 0.015180429443717003
2023-01-24 07:19:51.741324: step: 96/529, loss: 0.019517146050930023
2023-01-24 07:19:52.832473: step: 100/529, loss: 0.05744655430316925
2023-01-24 07:19:53.968088: step: 104/529, loss: 0.023722369223833084
2023-01-24 07:19:55.071720: step: 108/529, loss: 0.016381805762648582
2023-01-24 07:19:56.158260: step: 112/529, loss: 0.01025377493351698
2023-01-24 07:19:57.252716: step: 116/529, loss: 0.014802636578679085
2023-01-24 07:19:58.351751: step: 120/529, loss: 0.014737598598003387
2023-01-24 07:19:59.462573: step: 124/529, loss: 0.011493614874780178
2023-01-24 07:20:00.581700: step: 128/529, loss: 0.019774504005908966
2023-01-24 07:20:01.716160: step: 132/529, loss: 0.009261373430490494
2023-01-24 07:20:02.827488: step: 136/529, loss: 0.020293032750487328
2023-01-24 07:20:03.924707: step: 140/529, loss: 0.020239634439349174
2023-01-24 07:20:05.038135: step: 144/529, loss: 0.01102185808122158
2023-01-24 07:20:06.135866: step: 148/529, loss: 0.011839834973216057
2023-01-24 07:20:07.235213: step: 152/529, loss: 0.01189011987298727
2023-01-24 07:20:08.327989: step: 156/529, loss: 0.010195641778409481
2023-01-24 07:20:09.459024: step: 160/529, loss: 0.011982514522969723
2023-01-24 07:20:10.567969: step: 164/529, loss: 0.03768981620669365
2023-01-24 07:20:11.687304: step: 168/529, loss: 0.057141996920108795
2023-01-24 07:20:12.778827: step: 172/529, loss: 0.06138473376631737
2023-01-24 07:20:13.912214: step: 176/529, loss: 0.02281174063682556
2023-01-24 07:20:15.018864: step: 180/529, loss: 0.0857110396027565
2023-01-24 07:20:16.150676: step: 184/529, loss: 0.02645503729581833
2023-01-24 07:20:17.287561: step: 188/529, loss: 0.009832601994276047
2023-01-24 07:20:18.391031: step: 192/529, loss: 0.015928616747260094
2023-01-24 07:20:19.486671: step: 196/529, loss: 0.07065419852733612
2023-01-24 07:20:20.619968: step: 200/529, loss: 0.05971941351890564
2023-01-24 07:20:21.722834: step: 204/529, loss: 0.046089768409729004
2023-01-24 07:20:22.841286: step: 208/529, loss: 0.07824447005987167
2023-01-24 07:20:23.944410: step: 212/529, loss: 0.08715863525867462
2023-01-24 07:20:25.055510: step: 216/529, loss: 0.020826468244194984
2023-01-24 07:20:26.159992: step: 220/529, loss: 0.01940343715250492
2023-01-24 07:20:27.277015: step: 224/529, loss: 0.012001829221844673
2023-01-24 07:20:28.376711: step: 228/529, loss: 0.014780465513467789
2023-01-24 07:20:29.494711: step: 232/529, loss: 0.024281956255435944
2023-01-24 07:20:30.587373: step: 236/529, loss: 0.029330244287848473
2023-01-24 07:20:31.709068: step: 240/529, loss: 0.024107133969664574
2023-01-24 07:20:32.817812: step: 244/529, loss: 0.042314548045396805
2023-01-24 07:20:33.941480: step: 248/529, loss: 0.05584156513214111
2023-01-24 07:20:35.023277: step: 252/529, loss: 0.011207744479179382
2023-01-24 07:20:36.118357: step: 256/529, loss: 0.008659057319164276
2023-01-24 07:20:37.209371: step: 260/529, loss: 0.0022084370721131563
2023-01-24 07:20:38.355949: step: 264/529, loss: 0.03535834699869156
2023-01-24 07:20:39.457280: step: 268/529, loss: 0.04234807565808296
2023-01-24 07:20:40.601393: step: 272/529, loss: 0.014030973426997662
2023-01-24 07:20:41.708482: step: 276/529, loss: 0.01415281742811203
2023-01-24 07:20:42.807293: step: 280/529, loss: 0.07230215519666672
2023-01-24 07:20:43.920578: step: 284/529, loss: 0.03130822256207466
2023-01-24 07:20:45.017493: step: 288/529, loss: 0.014295052736997604
2023-01-24 07:20:46.127301: step: 292/529, loss: 0.007630824111402035
2023-01-24 07:20:47.226961: step: 296/529, loss: 0.016019055619835854
2023-01-24 07:20:48.320714: step: 300/529, loss: 0.010471394285559654
2023-01-24 07:20:49.433155: step: 304/529, loss: 0.04447510093450546
2023-01-24 07:20:50.521885: step: 308/529, loss: 0.044086236506700516
2023-01-24 07:20:51.608431: step: 312/529, loss: 0.012051809579133987
2023-01-24 07:20:52.716860: step: 316/529, loss: 0.02167813666164875
2023-01-24 07:20:53.823437: step: 320/529, loss: 0.015795966610312462
2023-01-24 07:20:54.955519: step: 324/529, loss: 0.04795869067311287
2023-01-24 07:20:56.069266: step: 328/529, loss: 0.010937169194221497
2023-01-24 07:20:57.190931: step: 332/529, loss: 0.0289393849670887
2023-01-24 07:20:58.314926: step: 336/529, loss: 0.017226209864020348
2023-01-24 07:20:59.434551: step: 340/529, loss: 0.0026177058462053537
2023-01-24 07:21:00.538855: step: 344/529, loss: 0.061795152723789215
2023-01-24 07:21:01.667531: step: 348/529, loss: 0.04654068872332573
2023-01-24 07:21:02.753929: step: 352/529, loss: 0.013378329575061798
2023-01-24 07:21:03.851916: step: 356/529, loss: 0.01938771642744541
2023-01-24 07:21:04.955955: step: 360/529, loss: 0.06321952491998672
2023-01-24 07:21:06.062907: step: 364/529, loss: 0.01659737154841423
2023-01-24 07:21:07.177655: step: 368/529, loss: 0.0530363991856575
2023-01-24 07:21:08.300147: step: 372/529, loss: 0.009072350338101387
2023-01-24 07:21:09.412083: step: 376/529, loss: 0.021112382411956787
2023-01-24 07:21:10.546988: step: 380/529, loss: 0.01962769217789173
2023-01-24 07:21:11.634630: step: 384/529, loss: 0.010405797511339188
2023-01-24 07:21:12.728031: step: 388/529, loss: 0.014076856896281242
2023-01-24 07:21:13.835282: step: 392/529, loss: 0.030933909118175507
2023-01-24 07:21:14.935629: step: 396/529, loss: 0.008482190780341625
2023-01-24 07:21:16.089538: step: 400/529, loss: 0.06148520112037659
2023-01-24 07:21:17.186604: step: 404/529, loss: 0.01498035155236721
2023-01-24 07:21:18.271605: step: 408/529, loss: 0.03137366846203804
2023-01-24 07:21:19.378306: step: 412/529, loss: 0.02093784138560295
2023-01-24 07:21:20.485280: step: 416/529, loss: 0.04966895282268524
2023-01-24 07:21:21.596927: step: 420/529, loss: 0.015933359041810036
2023-01-24 07:21:22.698159: step: 424/529, loss: 0.010265989229083061
2023-01-24 07:21:23.795612: step: 428/529, loss: 0.0232231467962265
2023-01-24 07:21:24.894966: step: 432/529, loss: 0.007650516927242279
2023-01-24 07:21:26.018247: step: 436/529, loss: 0.04336594417691231
2023-01-24 07:21:27.127171: step: 440/529, loss: 0.01494787260890007
2023-01-24 07:21:28.249468: step: 444/529, loss: 0.011679081246256828
2023-01-24 07:21:29.362285: step: 448/529, loss: 0.009621374309062958
2023-01-24 07:21:30.489282: step: 452/529, loss: 0.0628841444849968
2023-01-24 07:21:31.592543: step: 456/529, loss: 0.055795762687921524
2023-01-24 07:21:32.702370: step: 460/529, loss: 0.01230174582451582
2023-01-24 07:21:33.839240: step: 464/529, loss: 0.014860456809401512
2023-01-24 07:21:34.946802: step: 468/529, loss: 0.016787512227892876
2023-01-24 07:21:36.060025: step: 472/529, loss: 0.009318117052316666
2023-01-24 07:21:37.176182: step: 476/529, loss: 0.05141838267445564
2023-01-24 07:21:38.284053: step: 480/529, loss: 0.05433141067624092
2023-01-24 07:21:39.387767: step: 484/529, loss: 0.013388474471867085
2023-01-24 07:21:40.494806: step: 488/529, loss: 0.021288836374878883
2023-01-24 07:21:41.604769: step: 492/529, loss: 0.007459423039108515
2023-01-24 07:21:42.715762: step: 496/529, loss: 0.018024513497948647
2023-01-24 07:21:43.816107: step: 500/529, loss: 0.04020198434591293
2023-01-24 07:21:44.929839: step: 504/529, loss: 0.011004272848367691
2023-01-24 07:21:46.037176: step: 508/529, loss: 0.019049495458602905
2023-01-24 07:21:47.133717: step: 512/529, loss: 0.011073805391788483
2023-01-24 07:21:48.232211: step: 516/529, loss: 0.012309662997722626
2023-01-24 07:21:49.337813: step: 520/529, loss: 0.019298497587442398
2023-01-24 07:21:50.450351: step: 524/529, loss: 0.009093203581869602
2023-01-24 07:21:51.569040: step: 528/529, loss: 0.049984339624643326
2023-01-24 07:21:52.670957: step: 532/529, loss: 0.0069755008444190025
2023-01-24 07:21:53.774264: step: 536/529, loss: 0.03837039694190025
2023-01-24 07:21:54.886923: step: 540/529, loss: 0.019973745569586754
2023-01-24 07:21:56.003189: step: 544/529, loss: 0.006918622180819511
2023-01-24 07:21:57.127999: step: 548/529, loss: 0.07209032773971558
2023-01-24 07:21:58.267137: step: 552/529, loss: 0.025990018621087074
2023-01-24 07:21:59.385924: step: 556/529, loss: 0.035474564880132675
2023-01-24 07:22:00.504426: step: 560/529, loss: 0.005015677306801081
2023-01-24 07:22:01.623569: step: 564/529, loss: 0.039763789623975754
2023-01-24 07:22:02.756042: step: 568/529, loss: 0.01683920808136463
2023-01-24 07:22:03.869028: step: 572/529, loss: 0.00900550652295351
2023-01-24 07:22:04.992563: step: 576/529, loss: 0.010347955860197544
2023-01-24 07:22:06.091923: step: 580/529, loss: 0.034257613122463226
2023-01-24 07:22:07.230811: step: 584/529, loss: 0.05989512428641319
2023-01-24 07:22:08.336738: step: 588/529, loss: 0.005079173948615789
2023-01-24 07:22:09.458664: step: 592/529, loss: 0.01228341180831194
2023-01-24 07:22:10.592646: step: 596/529, loss: 0.01969623938202858
2023-01-24 07:22:11.705911: step: 600/529, loss: 0.007306233048439026
2023-01-24 07:22:12.814691: step: 604/529, loss: 0.04246971383690834
2023-01-24 07:22:13.899528: step: 608/529, loss: 0.007234849035739899
2023-01-24 07:22:15.011425: step: 612/529, loss: 0.017757266759872437
2023-01-24 07:22:16.107406: step: 616/529, loss: 0.025516996160149574
2023-01-24 07:22:17.229950: step: 620/529, loss: 0.009780902415513992
2023-01-24 07:22:18.319967: step: 624/529, loss: 0.008429944515228271
2023-01-24 07:22:19.425971: step: 628/529, loss: 0.014212721027433872
2023-01-24 07:22:20.562711: step: 632/529, loss: 0.02208278514444828
2023-01-24 07:22:21.679330: step: 636/529, loss: 0.011896387673914433
2023-01-24 07:22:22.776490: step: 640/529, loss: 0.03608326613903046
2023-01-24 07:22:23.891768: step: 644/529, loss: 0.028295794501900673
2023-01-24 07:22:25.020489: step: 648/529, loss: 0.01289941743016243
2023-01-24 07:22:26.141234: step: 652/529, loss: 0.013526106253266335
2023-01-24 07:22:27.229459: step: 656/529, loss: 0.009791851975023746
2023-01-24 07:22:28.306198: step: 660/529, loss: 0.03181343525648117
2023-01-24 07:22:29.419971: step: 664/529, loss: 0.005321584176272154
2023-01-24 07:22:30.548286: step: 668/529, loss: 0.024067873135209084
2023-01-24 07:22:31.648355: step: 672/529, loss: 0.009189567528665066
2023-01-24 07:22:32.736275: step: 676/529, loss: 0.01442819181829691
2023-01-24 07:22:33.855780: step: 680/529, loss: 0.06329543888568878
2023-01-24 07:22:34.966905: step: 684/529, loss: 0.012628337368369102
2023-01-24 07:22:36.067783: step: 688/529, loss: 0.041375380009412766
2023-01-24 07:22:37.175049: step: 692/529, loss: 0.06202450767159462
2023-01-24 07:22:38.301674: step: 696/529, loss: 0.012929446995258331
2023-01-24 07:22:39.395346: step: 700/529, loss: 0.01191332470625639
2023-01-24 07:22:40.503465: step: 704/529, loss: 0.007510307244956493
2023-01-24 07:22:41.602882: step: 708/529, loss: 0.011398904025554657
2023-01-24 07:22:42.704194: step: 712/529, loss: 0.06264317780733109
2023-01-24 07:22:43.819218: step: 716/529, loss: 0.00883929431438446
2023-01-24 07:22:44.908951: step: 720/529, loss: 0.0035735294222831726
2023-01-24 07:22:46.009424: step: 724/529, loss: 0.01408221386373043
2023-01-24 07:22:47.146622: step: 728/529, loss: 0.009267706423997879
2023-01-24 07:22:48.246981: step: 732/529, loss: 0.05647723749279976
2023-01-24 07:22:49.359101: step: 736/529, loss: 0.03602517023682594
2023-01-24 07:22:50.469924: step: 740/529, loss: 0.027513524517416954
2023-01-24 07:22:51.587387: step: 744/529, loss: 0.00937287975102663
2023-01-24 07:22:52.677949: step: 748/529, loss: 0.009648159146308899
2023-01-24 07:22:53.764214: step: 752/529, loss: 0.028540313243865967
2023-01-24 07:22:54.894286: step: 756/529, loss: 0.012167789973318577
2023-01-24 07:22:55.978410: step: 760/529, loss: 0.011136372573673725
2023-01-24 07:22:57.094814: step: 764/529, loss: 0.0290359053760767
2023-01-24 07:22:58.199801: step: 768/529, loss: 0.042235083878040314
2023-01-24 07:22:59.290589: step: 772/529, loss: 0.001173180527985096
2023-01-24 07:23:00.383192: step: 776/529, loss: 0.024135831743478775
2023-01-24 07:23:01.496325: step: 780/529, loss: 0.027562784031033516
2023-01-24 07:23:02.616686: step: 784/529, loss: 0.00653240317478776
2023-01-24 07:23:03.741668: step: 788/529, loss: 0.0821525901556015
2023-01-24 07:23:04.849970: step: 792/529, loss: 0.032976217567920685
2023-01-24 07:23:05.955587: step: 796/529, loss: 0.012385495007038116
2023-01-24 07:23:07.072568: step: 800/529, loss: 0.010210997425019741
2023-01-24 07:23:08.196228: step: 804/529, loss: 0.011432819068431854
2023-01-24 07:23:09.290185: step: 808/529, loss: 0.008386366069316864
2023-01-24 07:23:10.385358: step: 812/529, loss: 0.012356234714388847
2023-01-24 07:23:11.492606: step: 816/529, loss: 0.0057090348564088345
2023-01-24 07:23:12.635781: step: 820/529, loss: 0.037322089076042175
2023-01-24 07:23:13.747128: step: 824/529, loss: 0.06033607944846153
2023-01-24 07:23:14.852668: step: 828/529, loss: 0.008338105864822865
2023-01-24 07:23:15.975511: step: 832/529, loss: 0.060262203216552734
2023-01-24 07:23:17.068104: step: 836/529, loss: 0.006627920549362898
2023-01-24 07:23:18.171482: step: 840/529, loss: 0.01432175561785698
2023-01-24 07:23:19.259099: step: 844/529, loss: 0.04478072747588158
2023-01-24 07:23:20.351079: step: 848/529, loss: 0.021244077011942863
2023-01-24 07:23:21.479520: step: 852/529, loss: 0.014454500749707222
2023-01-24 07:23:22.592719: step: 856/529, loss: 0.017993612214922905
2023-01-24 07:23:23.692582: step: 860/529, loss: 0.016988826915621758
2023-01-24 07:23:24.808019: step: 864/529, loss: 0.0051475767977535725
2023-01-24 07:23:25.902819: step: 868/529, loss: 0.016883045434951782
2023-01-24 07:23:26.998739: step: 872/529, loss: 0.0372672975063324
2023-01-24 07:23:28.096734: step: 876/529, loss: 0.010639122687280178
2023-01-24 07:23:29.212991: step: 880/529, loss: 0.0074227373115718365
2023-01-24 07:23:30.315911: step: 884/529, loss: 0.00881099235266447
2023-01-24 07:23:31.430308: step: 888/529, loss: 0.013152114115655422
2023-01-24 07:23:32.579229: step: 892/529, loss: 0.015497894026339054
2023-01-24 07:23:33.667333: step: 896/529, loss: 0.006738824304193258
2023-01-24 07:23:34.769971: step: 900/529, loss: 0.04644390568137169
2023-01-24 07:23:35.926775: step: 904/529, loss: 0.014287744648754597
2023-01-24 07:23:37.045434: step: 908/529, loss: 0.02299402467906475
2023-01-24 07:23:38.144178: step: 912/529, loss: 0.015505899675190449
2023-01-24 07:23:39.285626: step: 916/529, loss: 0.007542851381003857
2023-01-24 07:23:40.404339: step: 920/529, loss: 0.05951913446187973
2023-01-24 07:23:41.520927: step: 924/529, loss: 0.015890389680862427
2023-01-24 07:23:42.638530: step: 928/529, loss: 0.03368136286735535
2023-01-24 07:23:43.763182: step: 932/529, loss: 0.01791762188076973
2023-01-24 07:23:44.865411: step: 936/529, loss: 0.0779389888048172
2023-01-24 07:23:45.970059: step: 940/529, loss: 0.005780879873782396
2023-01-24 07:23:47.099476: step: 944/529, loss: 0.05669904500246048
2023-01-24 07:23:48.205634: step: 948/529, loss: 0.007478095591068268
2023-01-24 07:23:49.335723: step: 952/529, loss: 0.015467693097889423
2023-01-24 07:23:50.446681: step: 956/529, loss: 0.04223593324422836
2023-01-24 07:23:51.549923: step: 960/529, loss: 0.00645859818905592
2023-01-24 07:23:52.673177: step: 964/529, loss: 0.009627575054764748
2023-01-24 07:23:53.793504: step: 968/529, loss: 0.007642344105988741
2023-01-24 07:23:54.909622: step: 972/529, loss: 0.0061698853969573975
2023-01-24 07:23:56.028833: step: 976/529, loss: 0.020721925422549248
2023-01-24 07:23:57.143128: step: 980/529, loss: 0.023703668266534805
2023-01-24 07:23:58.252068: step: 984/529, loss: 0.01573798805475235
2023-01-24 07:23:59.378006: step: 988/529, loss: 0.009059869684278965
2023-01-24 07:24:00.495273: step: 992/529, loss: 0.030040360987186432
2023-01-24 07:24:01.594512: step: 996/529, loss: 0.02443655952811241
2023-01-24 07:24:02.715839: step: 1000/529, loss: 0.007026128005236387
2023-01-24 07:24:03.841669: step: 1004/529, loss: 0.005020439624786377
2023-01-24 07:24:04.959970: step: 1008/529, loss: 0.028834665194153786
2023-01-24 07:24:06.076835: step: 1012/529, loss: 0.006580329034477472
2023-01-24 07:24:07.186448: step: 1016/529, loss: 0.008372098207473755
2023-01-24 07:24:08.318595: step: 1020/529, loss: 0.03315599262714386
2023-01-24 07:24:09.419103: step: 1024/529, loss: 0.009761552326381207
2023-01-24 07:24:10.526196: step: 1028/529, loss: 0.00852805282920599
2023-01-24 07:24:11.638226: step: 1032/529, loss: 0.025692827999591827
2023-01-24 07:24:12.752144: step: 1036/529, loss: 0.01296450849622488
2023-01-24 07:24:13.850117: step: 1040/529, loss: 0.02006562426686287
2023-01-24 07:24:14.954159: step: 1044/529, loss: 0.00819639302790165
2023-01-24 07:24:16.047719: step: 1048/529, loss: 0.0060485126450657845
2023-01-24 07:24:17.155354: step: 1052/529, loss: 0.010531513020396233
2023-01-24 07:24:18.303577: step: 1056/529, loss: 0.03217656910419464
2023-01-24 07:24:19.415119: step: 1060/529, loss: 0.01268327422440052
2023-01-24 07:24:20.580697: step: 1064/529, loss: 0.05135943740606308
2023-01-24 07:24:21.698879: step: 1068/529, loss: 0.019594566896557808
2023-01-24 07:24:22.827846: step: 1072/529, loss: 0.012082871980965137
2023-01-24 07:24:23.945819: step: 1076/529, loss: 0.07165084034204483
2023-01-24 07:24:25.074623: step: 1080/529, loss: 0.00775414053350687
2023-01-24 07:24:26.188969: step: 1084/529, loss: 0.019090984016656876
2023-01-24 07:24:27.283886: step: 1088/529, loss: 0.015492795035243034
2023-01-24 07:24:28.400701: step: 1092/529, loss: 0.009958931244909763
2023-01-24 07:24:29.514241: step: 1096/529, loss: 0.005504067987203598
2023-01-24 07:24:30.625355: step: 1100/529, loss: 0.01356101781129837
2023-01-24 07:24:31.731152: step: 1104/529, loss: 0.02976878546178341
2023-01-24 07:24:32.864626: step: 1108/529, loss: 0.009017725475132465
2023-01-24 07:24:33.976495: step: 1112/529, loss: 0.031317565590143204
2023-01-24 07:24:35.088001: step: 1116/529, loss: 0.04354654252529144
2023-01-24 07:24:36.225635: step: 1120/529, loss: 0.04566562920808792
2023-01-24 07:24:37.350429: step: 1124/529, loss: 0.02474207431077957
2023-01-24 07:24:38.487078: step: 1128/529, loss: 0.025392092764377594
2023-01-24 07:24:39.591237: step: 1132/529, loss: 0.008057104423642159
2023-01-24 07:24:40.693136: step: 1136/529, loss: 0.009960835799574852
2023-01-24 07:24:41.792934: step: 1140/529, loss: 0.06002819910645485
2023-01-24 07:24:42.908512: step: 1144/529, loss: 0.0075718313455581665
2023-01-24 07:24:43.997199: step: 1148/529, loss: 0.011741343885660172
2023-01-24 07:24:45.110233: step: 1152/529, loss: 0.010663824155926704
2023-01-24 07:24:46.237428: step: 1156/529, loss: 0.01787198893725872
2023-01-24 07:24:47.374642: step: 1160/529, loss: 0.029899438843131065
2023-01-24 07:24:48.470768: step: 1164/529, loss: 0.008893690072000027
2023-01-24 07:24:49.589886: step: 1168/529, loss: 0.012354403734207153
2023-01-24 07:24:50.690147: step: 1172/529, loss: 0.012204738333821297
2023-01-24 07:24:51.800059: step: 1176/529, loss: 0.03429974615573883
2023-01-24 07:24:52.933251: step: 1180/529, loss: 0.021606411784887314
2023-01-24 07:24:54.053708: step: 1184/529, loss: 0.011130974628031254
2023-01-24 07:24:55.179974: step: 1188/529, loss: 0.00621484499424696
2023-01-24 07:24:56.286866: step: 1192/529, loss: 0.014379750937223434
2023-01-24 07:24:57.412268: step: 1196/529, loss: 0.007328517735004425
2023-01-24 07:24:58.512564: step: 1200/529, loss: 0.0319802463054657
2023-01-24 07:24:59.622546: step: 1204/529, loss: 0.009026180021464825
2023-01-24 07:25:00.720199: step: 1208/529, loss: 0.009286165237426758
2023-01-24 07:25:01.877185: step: 1212/529, loss: 0.023003151640295982
2023-01-24 07:25:03.007502: step: 1216/529, loss: 0.05612075328826904
2023-01-24 07:25:04.098637: step: 1220/529, loss: 0.011093712411820889
2023-01-24 07:25:05.199039: step: 1224/529, loss: 0.020905502140522003
2023-01-24 07:25:06.320328: step: 1228/529, loss: 0.012027262710034847
2023-01-24 07:25:07.433073: step: 1232/529, loss: 0.036563143134117126
2023-01-24 07:25:08.532149: step: 1236/529, loss: 0.006464777514338493
2023-01-24 07:25:09.636312: step: 1240/529, loss: 0.008525123819708824
2023-01-24 07:25:10.716754: step: 1244/529, loss: 0.007257360499352217
2023-01-24 07:25:11.843041: step: 1248/529, loss: 0.009333458729088306
2023-01-24 07:25:12.961067: step: 1252/529, loss: 0.018762996420264244
2023-01-24 07:25:14.078046: step: 1256/529, loss: 0.028781188651919365
2023-01-24 07:25:15.199815: step: 1260/529, loss: 0.017822491005063057
2023-01-24 07:25:16.338588: step: 1264/529, loss: 0.005475801881402731
2023-01-24 07:25:17.461160: step: 1268/529, loss: 0.00771291321143508
2023-01-24 07:25:18.557767: step: 1272/529, loss: 0.013042115606367588
2023-01-24 07:25:19.698956: step: 1276/529, loss: 0.01129109039902687
2023-01-24 07:25:20.795653: step: 1280/529, loss: 0.002599012339487672
2023-01-24 07:25:21.908257: step: 1284/529, loss: 0.007883195765316486
2023-01-24 07:25:23.034158: step: 1288/529, loss: 0.018795518204569817
2023-01-24 07:25:24.155562: step: 1292/529, loss: 0.01176285371184349
2023-01-24 07:25:25.276158: step: 1296/529, loss: 0.020236041396856308
2023-01-24 07:25:26.415511: step: 1300/529, loss: 0.0050763231702148914
2023-01-24 07:25:27.518015: step: 1304/529, loss: 0.03246217966079712
2023-01-24 07:25:28.633895: step: 1308/529, loss: 0.04050830379128456
2023-01-24 07:25:29.741791: step: 1312/529, loss: 0.013893981464207172
2023-01-24 07:25:30.835938: step: 1316/529, loss: 0.005745646543800831
2023-01-24 07:25:31.951378: step: 1320/529, loss: 0.03940330818295479
2023-01-24 07:25:33.057990: step: 1324/529, loss: 0.043045010417699814
2023-01-24 07:25:34.166651: step: 1328/529, loss: 0.011276856996119022
2023-01-24 07:25:35.293468: step: 1332/529, loss: 0.008583548478782177
2023-01-24 07:25:36.408384: step: 1336/529, loss: 0.024562150239944458
2023-01-24 07:25:37.528450: step: 1340/529, loss: 0.030079036951065063
2023-01-24 07:25:38.633565: step: 1344/529, loss: 0.015479600988328457
2023-01-24 07:25:39.730213: step: 1348/529, loss: 0.0029222567100077868
2023-01-24 07:25:40.831134: step: 1352/529, loss: 0.003567111911252141
2023-01-24 07:25:41.947219: step: 1356/529, loss: 0.028687715530395508
2023-01-24 07:25:43.071722: step: 1360/529, loss: 0.014020870439708233
2023-01-24 07:25:44.211677: step: 1364/529, loss: 0.010144067928195
2023-01-24 07:25:45.317327: step: 1368/529, loss: 0.06696517020463943
2023-01-24 07:25:46.403903: step: 1372/529, loss: 0.009632857516407967
2023-01-24 07:25:47.520261: step: 1376/529, loss: 0.01684681512415409
2023-01-24 07:25:48.621863: step: 1380/529, loss: 0.03911769762635231
2023-01-24 07:25:49.724748: step: 1384/529, loss: 0.042949378490448
2023-01-24 07:25:50.827252: step: 1388/529, loss: 0.012359624728560448
2023-01-24 07:25:51.939424: step: 1392/529, loss: 0.02868887409567833
2023-01-24 07:25:53.065787: step: 1396/529, loss: 0.013364430516958237
2023-01-24 07:25:54.173452: step: 1400/529, loss: 0.021869942545890808
2023-01-24 07:25:55.286199: step: 1404/529, loss: 0.01448669284582138
2023-01-24 07:25:56.414709: step: 1408/529, loss: 0.01271969173103571
2023-01-24 07:25:57.524242: step: 1412/529, loss: 0.020677125081419945
2023-01-24 07:25:58.666354: step: 1416/529, loss: 0.011627142317593098
2023-01-24 07:25:59.764370: step: 1420/529, loss: 0.013595512136816978
2023-01-24 07:26:00.868304: step: 1424/529, loss: 0.023199519142508507
2023-01-24 07:26:01.976404: step: 1428/529, loss: 0.01161238644272089
2023-01-24 07:26:03.083022: step: 1432/529, loss: 0.010114002972841263
2023-01-24 07:26:04.191001: step: 1436/529, loss: 0.0066328695975244045
2023-01-24 07:26:05.285622: step: 1440/529, loss: 0.014511281624436378
2023-01-24 07:26:06.409740: step: 1444/529, loss: 0.016472142189741135
2023-01-24 07:26:07.521896: step: 1448/529, loss: 0.0473119392991066
2023-01-24 07:26:08.664375: step: 1452/529, loss: 0.008408170193433762
2023-01-24 07:26:09.775394: step: 1456/529, loss: 0.0062958537600934505
2023-01-24 07:26:10.901182: step: 1460/529, loss: 0.013939841650426388
2023-01-24 07:26:11.999954: step: 1464/529, loss: 0.01662561669945717
2023-01-24 07:26:13.115359: step: 1468/529, loss: 0.0005799630889669061
2023-01-24 07:26:14.203736: step: 1472/529, loss: 0.02928600087761879
2023-01-24 07:26:15.319605: step: 1476/529, loss: 0.004867796786129475
2023-01-24 07:26:16.441506: step: 1480/529, loss: 0.018991462886333466
2023-01-24 07:26:17.534288: step: 1484/529, loss: 0.011524781584739685
2023-01-24 07:26:18.651821: step: 1488/529, loss: 0.03889041393995285
2023-01-24 07:26:19.770571: step: 1492/529, loss: 0.013699166476726532
2023-01-24 07:26:20.879752: step: 1496/529, loss: 0.004785880912095308
2023-01-24 07:26:21.990597: step: 1500/529, loss: 0.0132296746596694
2023-01-24 07:26:23.099018: step: 1504/529, loss: 0.004941858351230621
2023-01-24 07:26:24.216198: step: 1508/529, loss: 0.01335514709353447
2023-01-24 07:26:25.321570: step: 1512/529, loss: 0.010904469527304173
2023-01-24 07:26:26.431773: step: 1516/529, loss: 0.009224246256053448
2023-01-24 07:26:27.544510: step: 1520/529, loss: 0.004448066931217909
2023-01-24 07:26:28.634372: step: 1524/529, loss: 0.009903236292302608
2023-01-24 07:26:29.746573: step: 1528/529, loss: 0.013837488368153572
2023-01-24 07:26:30.878337: step: 1532/529, loss: 0.034371789544820786
2023-01-24 07:26:32.006675: step: 1536/529, loss: 0.01723404787480831
2023-01-24 07:26:33.119549: step: 1540/529, loss: 0.01081811636686325
2023-01-24 07:26:34.252725: step: 1544/529, loss: 0.006913135293871164
2023-01-24 07:26:35.347781: step: 1548/529, loss: 0.004861879628151655
2023-01-24 07:26:36.471929: step: 1552/529, loss: 0.022660069167613983
2023-01-24 07:26:37.601269: step: 1556/529, loss: 0.024209827184677124
2023-01-24 07:26:38.719574: step: 1560/529, loss: 0.005939995404332876
2023-01-24 07:26:39.842753: step: 1564/529, loss: 0.010164082050323486
2023-01-24 07:26:40.961090: step: 1568/529, loss: 0.05731247738003731
2023-01-24 07:26:42.065143: step: 1572/529, loss: 0.03543375805020332
2023-01-24 07:26:43.190650: step: 1576/529, loss: 0.008039611391723156
2023-01-24 07:26:44.301132: step: 1580/529, loss: 0.018727675080299377
2023-01-24 07:26:45.412061: step: 1584/529, loss: 0.020055225118994713
2023-01-24 07:26:46.538269: step: 1588/529, loss: 0.0066964756697416306
2023-01-24 07:26:47.641642: step: 1592/529, loss: 0.006271496415138245
2023-01-24 07:26:48.757123: step: 1596/529, loss: 0.016917379572987556
2023-01-24 07:26:49.868590: step: 1600/529, loss: 0.01939815655350685
2023-01-24 07:26:50.981605: step: 1604/529, loss: 0.024073787033557892
2023-01-24 07:26:52.105045: step: 1608/529, loss: 0.029335562139749527
2023-01-24 07:26:53.234560: step: 1612/529, loss: 0.00727007444947958
2023-01-24 07:26:54.344570: step: 1616/529, loss: 0.010016110725700855
2023-01-24 07:26:55.449392: step: 1620/529, loss: 0.013527818955481052
2023-01-24 07:26:56.555975: step: 1624/529, loss: 0.015339715406298637
2023-01-24 07:26:57.662248: step: 1628/529, loss: 0.03363961726427078
2023-01-24 07:26:58.751399: step: 1632/529, loss: 0.035570330917835236
2023-01-24 07:26:59.860903: step: 1636/529, loss: 0.007140653673559427
2023-01-24 07:27:00.993437: step: 1640/529, loss: 0.042375851422548294
2023-01-24 07:27:02.124242: step: 1644/529, loss: 0.009680777788162231
2023-01-24 07:27:03.219552: step: 1648/529, loss: 0.031028874218463898
2023-01-24 07:27:04.338657: step: 1652/529, loss: 0.01726185716688633
2023-01-24 07:27:05.423153: step: 1656/529, loss: 0.023695921525359154
2023-01-24 07:27:06.526303: step: 1660/529, loss: 0.06343021988868713
2023-01-24 07:27:07.664549: step: 1664/529, loss: 0.011768014170229435
2023-01-24 07:27:08.758855: step: 1668/529, loss: 0.007082835771143436
2023-01-24 07:27:09.856550: step: 1672/529, loss: 0.01287764124572277
2023-01-24 07:27:10.969208: step: 1676/529, loss: 0.04795419052243233
2023-01-24 07:27:12.075834: step: 1680/529, loss: 0.004884667694568634
2023-01-24 07:27:13.179597: step: 1684/529, loss: 0.009261339902877808
2023-01-24 07:27:14.293380: step: 1688/529, loss: 0.016716046258807182
2023-01-24 07:27:15.410807: step: 1692/529, loss: 0.005059296730905771
2023-01-24 07:27:16.521957: step: 1696/529, loss: 0.05374990403652191
2023-01-24 07:27:17.618225: step: 1700/529, loss: 0.04184979200363159
2023-01-24 07:27:18.738867: step: 1704/529, loss: 0.006443860474973917
2023-01-24 07:27:19.851433: step: 1708/529, loss: 0.016054097563028336
2023-01-24 07:27:20.963710: step: 1712/529, loss: 0.012395386584103107
2023-01-24 07:27:22.071404: step: 1716/529, loss: 0.03141835704445839
2023-01-24 07:27:23.170530: step: 1720/529, loss: 0.012311109341681004
2023-01-24 07:27:24.258697: step: 1724/529, loss: 0.05921533331274986
2023-01-24 07:27:25.380322: step: 1728/529, loss: 0.009985635988414288
2023-01-24 07:27:26.476155: step: 1732/529, loss: 0.025756413117051125
2023-01-24 07:27:27.589547: step: 1736/529, loss: 0.040602754801511765
2023-01-24 07:27:28.688176: step: 1740/529, loss: 0.03853137791156769
2023-01-24 07:27:29.803937: step: 1744/529, loss: 0.009843072853982449
2023-01-24 07:27:30.905505: step: 1748/529, loss: 0.012607881799340248
2023-01-24 07:27:32.008698: step: 1752/529, loss: 0.004900872707366943
2023-01-24 07:27:33.134218: step: 1756/529, loss: 0.010372872464358807
2023-01-24 07:27:34.229164: step: 1760/529, loss: 0.00687371427193284
2023-01-24 07:27:35.333320: step: 1764/529, loss: 0.033669162541627884
2023-01-24 07:27:36.451837: step: 1768/529, loss: 0.012714053504168987
2023-01-24 07:27:37.552313: step: 1772/529, loss: 0.04491034895181656
2023-01-24 07:27:38.669578: step: 1776/529, loss: 0.011299021542072296
2023-01-24 07:27:39.812198: step: 1780/529, loss: 0.029356691986322403
2023-01-24 07:27:40.923270: step: 1784/529, loss: 0.0052626049146056175
2023-01-24 07:27:42.016182: step: 1788/529, loss: 0.00784127414226532
2023-01-24 07:27:43.115375: step: 1792/529, loss: 0.009773041121661663
2023-01-24 07:27:44.229379: step: 1796/529, loss: 0.005785140208899975
2023-01-24 07:27:45.331770: step: 1800/529, loss: 0.007336001843214035
2023-01-24 07:27:46.441684: step: 1804/529, loss: 0.00700216693803668
2023-01-24 07:27:47.532606: step: 1808/529, loss: 0.004095433745533228
2023-01-24 07:27:48.623422: step: 1812/529, loss: 0.009905686601996422
2023-01-24 07:27:49.733840: step: 1816/529, loss: 0.0322563536465168
2023-01-24 07:27:50.876571: step: 1820/529, loss: 0.035683341324329376
2023-01-24 07:27:51.992962: step: 1824/529, loss: 0.0065209995955228806
2023-01-24 07:27:53.107486: step: 1828/529, loss: 0.011323463171720505
2023-01-24 07:27:54.213815: step: 1832/529, loss: 0.004791976418346167
2023-01-24 07:27:55.346322: step: 1836/529, loss: 0.0074640363454818726
2023-01-24 07:27:56.459197: step: 1840/529, loss: 0.008063922636210918
2023-01-24 07:27:57.576501: step: 1844/529, loss: 0.02339182235300541
2023-01-24 07:27:58.691746: step: 1848/529, loss: 0.01143765076994896
2023-01-24 07:27:59.807707: step: 1852/529, loss: 0.02925294078886509
2023-01-24 07:28:00.906225: step: 1856/529, loss: 0.00841628760099411
2023-01-24 07:28:02.015752: step: 1860/529, loss: 0.09265927970409393
2023-01-24 07:28:03.127357: step: 1864/529, loss: 0.009392473846673965
2023-01-24 07:28:04.240149: step: 1868/529, loss: 0.009746620431542397
2023-01-24 07:28:05.340071: step: 1872/529, loss: 0.00464861374348402
2023-01-24 07:28:06.411842: step: 1876/529, loss: 0.002670533489435911
2023-01-24 07:28:07.527018: step: 1880/529, loss: 0.015554034151136875
2023-01-24 07:28:08.622007: step: 1884/529, loss: 0.07675477862358093
2023-01-24 07:28:09.740282: step: 1888/529, loss: 0.006999322213232517
2023-01-24 07:28:10.852614: step: 1892/529, loss: 0.006108852569013834
2023-01-24 07:28:11.963459: step: 1896/529, loss: 0.012979681603610516
2023-01-24 07:28:13.072096: step: 1900/529, loss: 0.012842020951211452
2023-01-24 07:28:14.180928: step: 1904/529, loss: 0.07957916706800461
2023-01-24 07:28:15.268368: step: 1908/529, loss: 0.011200874112546444
2023-01-24 07:28:16.385186: step: 1912/529, loss: 0.03606186434626579
2023-01-24 07:28:17.491909: step: 1916/529, loss: 0.0678335428237915
2023-01-24 07:28:18.594459: step: 1920/529, loss: 0.03621261194348335
2023-01-24 07:28:19.699610: step: 1924/529, loss: 0.042195264250040054
2023-01-24 07:28:20.802247: step: 1928/529, loss: 0.01831630803644657
2023-01-24 07:28:21.940200: step: 1932/529, loss: 0.006913109216839075
2023-01-24 07:28:23.067925: step: 1936/529, loss: 0.007291656453162432
2023-01-24 07:28:24.158599: step: 1940/529, loss: 0.009371194988489151
2023-01-24 07:28:25.258487: step: 1944/529, loss: 0.051772184669971466
2023-01-24 07:28:26.370174: step: 1948/529, loss: 0.009605119936168194
2023-01-24 07:28:27.483474: step: 1952/529, loss: 0.007756783626973629
2023-01-24 07:28:28.598061: step: 1956/529, loss: 0.049256373196840286
2023-01-24 07:28:29.695278: step: 1960/529, loss: 0.01514006033539772
2023-01-24 07:28:30.811395: step: 1964/529, loss: 0.021082337945699692
2023-01-24 07:28:31.936747: step: 1968/529, loss: 0.011226071044802666
2023-01-24 07:28:33.044218: step: 1972/529, loss: 0.03969605267047882
2023-01-24 07:28:34.135855: step: 1976/529, loss: 0.005889580585062504
2023-01-24 07:28:35.251532: step: 1980/529, loss: 0.011329768225550652
2023-01-24 07:28:36.335161: step: 1984/529, loss: 0.01765243336558342
2023-01-24 07:28:37.456485: step: 1988/529, loss: 0.04848553612828255
2023-01-24 07:28:38.554916: step: 1992/529, loss: 0.025547156110405922
2023-01-24 07:28:39.693376: step: 1996/529, loss: 0.030630121007561684
2023-01-24 07:28:40.775157: step: 2000/529, loss: 0.02028278447687626
2023-01-24 07:28:41.878643: step: 2004/529, loss: 0.00895814411342144
2023-01-24 07:28:42.979978: step: 2008/529, loss: 0.010160822421312332
2023-01-24 07:28:44.105465: step: 2012/529, loss: 0.007527889683842659
2023-01-24 07:28:45.211488: step: 2016/529, loss: 0.011715550906956196
2023-01-24 07:28:46.325295: step: 2020/529, loss: 0.009545152075588703
2023-01-24 07:28:47.451685: step: 2024/529, loss: 0.008271112106740475
2023-01-24 07:28:48.564794: step: 2028/529, loss: 0.038071177899837494
2023-01-24 07:28:49.671764: step: 2032/529, loss: 0.013420408591628075
2023-01-24 07:28:50.764833: step: 2036/529, loss: 0.05669183284044266
2023-01-24 07:28:51.864544: step: 2040/529, loss: 0.005937928333878517
2023-01-24 07:28:52.975879: step: 2044/529, loss: 0.005604805890470743
2023-01-24 07:28:54.081321: step: 2048/529, loss: 0.008186708204448223
2023-01-24 07:28:55.219131: step: 2052/529, loss: 0.006400682032108307
2023-01-24 07:28:56.311377: step: 2056/529, loss: 0.010630583390593529
2023-01-24 07:28:57.402652: step: 2060/529, loss: 0.013762875460088253
2023-01-24 07:28:58.521386: step: 2064/529, loss: 0.0062905061058700085
2023-01-24 07:28:59.633761: step: 2068/529, loss: 0.01811828650534153
2023-01-24 07:29:00.726683: step: 2072/529, loss: 0.00411311024799943
2023-01-24 07:29:01.871839: step: 2076/529, loss: 0.012253466062247753
2023-01-24 07:29:02.974955: step: 2080/529, loss: 0.02685640938580036
2023-01-24 07:29:04.086064: step: 2084/529, loss: 0.05459235608577728
2023-01-24 07:29:05.206418: step: 2088/529, loss: 0.0383254699409008
2023-01-24 07:29:06.320086: step: 2092/529, loss: 0.011927919462323189
2023-01-24 07:29:07.412211: step: 2096/529, loss: 0.0065722474828362465
2023-01-24 07:29:08.531996: step: 2100/529, loss: 0.024399179965257645
2023-01-24 07:29:09.638452: step: 2104/529, loss: 0.012021117843687534
2023-01-24 07:29:10.743919: step: 2108/529, loss: 0.008413835428655148
2023-01-24 07:29:11.872000: step: 2112/529, loss: 0.0459437295794487
2023-01-24 07:29:12.976818: step: 2116/529, loss: 0.007205226458609104
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3672496118012422, 'r': 0.3205594334507996, 'f1': 0.34231980026052977}, 'combined': 0.25223564229723244, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38591511836755776, 'r': 0.28701392785950836, 'f1': 0.3291967097097638}, 'combined': 0.2023355386508792, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34818675325186665, 'r': 0.3290265713841169, 'f1': 0.3383356158427895}, 'combined': 0.24929992746310803, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37036539443333555, 'r': 0.29462342468787006, 'f1': 0.3281809190056004}, 'combined': 0.20171119899856416, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39043010752688173, 'r': 0.3444971537001898, 'f1': 0.3660282258064516}, 'combined': 0.26970500848896434, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3917725999302115, 'r': 0.29026479457567667, 'f1': 0.3334649805279551}, 'combined': 0.205963664443737, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.358695652173913, 'f1': 0.375}, 'combined': 0.1875, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, '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': 0.3672496118012422, 'r': 0.3205594334507996, 'f1': 0.34231980026052977}, 'combined': 0.25223564229723244, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38591511836755776, 'r': 0.28701392785950836, 'f1': 0.3291967097097638}, 'combined': 0.2023355386508792, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34818675325186665, 'r': 0.3290265713841169, 'f1': 0.3383356158427895}, 'combined': 0.24929992746310803, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37036539443333555, 'r': 0.29462342468787006, 'f1': 0.3281809190056004}, 'combined': 0.20171119899856416, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.358695652173913, 'f1': 0.375}, 'combined': 0.1875, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39043010752688173, 'r': 0.3444971537001898, 'f1': 0.3660282258064516}, 'combined': 0.26970500848896434, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3917725999302115, 'r': 0.29026479457567667, 'f1': 0.3334649805279551}, 'combined': 0.205963664443737, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:31:57.782369: step: 4/529, loss: 0.021916856989264488
2023-01-24 07:31:58.888750: step: 8/529, loss: 0.011044525541365147
2023-01-24 07:32:00.035235: step: 12/529, loss: 0.005311714950948954
2023-01-24 07:32:01.172799: step: 16/529, loss: 0.004606260918080807
2023-01-24 07:32:02.276338: step: 20/529, loss: 0.004426587838679552
2023-01-24 07:32:03.349502: step: 24/529, loss: 0.03157786652445793
2023-01-24 07:32:04.466132: step: 28/529, loss: 0.019223518669605255
2023-01-24 07:32:05.570220: step: 32/529, loss: 0.02830389514565468
2023-01-24 07:32:06.688296: step: 36/529, loss: 0.0038713307585567236
2023-01-24 07:32:07.786976: step: 40/529, loss: 0.006225733086466789
2023-01-24 07:32:08.856793: step: 44/529, loss: 0.0046651423908770084
2023-01-24 07:32:09.952520: step: 48/529, loss: 0.039311476051807404
2023-01-24 07:32:11.041557: step: 52/529, loss: 0.010235447436571121
2023-01-24 07:32:12.145123: step: 56/529, loss: 0.01629253849387169
2023-01-24 07:32:13.279167: step: 60/529, loss: 0.011247687041759491
2023-01-24 07:32:14.395751: step: 64/529, loss: 0.009514960460364819
2023-01-24 07:32:15.523256: step: 68/529, loss: 0.028238818049430847
2023-01-24 07:32:16.627913: step: 72/529, loss: 0.005100684706121683
2023-01-24 07:32:17.785780: step: 76/529, loss: 0.011901361867785454
2023-01-24 07:32:18.882764: step: 80/529, loss: 0.024363839998841286
2023-01-24 07:32:20.009975: step: 84/529, loss: 0.02609892748296261
2023-01-24 07:32:21.099119: step: 88/529, loss: 0.017716793343424797
2023-01-24 07:32:22.224135: step: 92/529, loss: 0.00783140491694212
2023-01-24 07:32:23.327392: step: 96/529, loss: 0.007628799416124821
2023-01-24 07:32:24.432980: step: 100/529, loss: 0.0015609943075105548
2023-01-24 07:32:25.538050: step: 104/529, loss: 0.025129221379756927
2023-01-24 07:32:26.645745: step: 108/529, loss: 0.00945216417312622
2023-01-24 07:32:27.754495: step: 112/529, loss: 0.0084123145788908
2023-01-24 07:32:28.847284: step: 116/529, loss: 0.00691334018483758
2023-01-24 07:32:29.948245: step: 120/529, loss: 0.006969493348151445
2023-01-24 07:32:31.042761: step: 124/529, loss: 0.004777539521455765
2023-01-24 07:32:32.186237: step: 128/529, loss: 0.049693766981363297
2023-01-24 07:32:33.301981: step: 132/529, loss: 0.000980474054813385
2023-01-24 07:32:34.391126: step: 136/529, loss: 0.008576666936278343
2023-01-24 07:32:35.529988: step: 140/529, loss: 0.0054633659310638905
2023-01-24 07:32:36.628334: step: 144/529, loss: 0.022170914337038994
2023-01-24 07:32:37.737439: step: 148/529, loss: 0.021785352379083633
2023-01-24 07:32:38.842985: step: 152/529, loss: 0.008628305979073048
2023-01-24 07:32:39.955511: step: 156/529, loss: 0.01366341020911932
2023-01-24 07:32:41.075353: step: 160/529, loss: 0.009315998293459415
2023-01-24 07:32:42.212113: step: 164/529, loss: 0.015487903729081154
2023-01-24 07:32:43.325264: step: 168/529, loss: 0.0075741903856396675
2023-01-24 07:32:44.432238: step: 172/529, loss: 0.005317441653460264
2023-01-24 07:32:45.535192: step: 176/529, loss: 0.012066704221069813
2023-01-24 07:32:46.636017: step: 180/529, loss: 0.10282935202121735
2023-01-24 07:32:47.727681: step: 184/529, loss: 0.021517092362046242
2023-01-24 07:32:48.823270: step: 188/529, loss: 0.007219498977065086
2023-01-24 07:32:49.947946: step: 192/529, loss: 0.022852858528494835
2023-01-24 07:32:51.050887: step: 196/529, loss: 0.010436865501105785
2023-01-24 07:32:52.171418: step: 200/529, loss: 0.010775558650493622
2023-01-24 07:32:53.269637: step: 204/529, loss: 0.07135234028100967
2023-01-24 07:32:54.391789: step: 208/529, loss: 0.007811805699020624
2023-01-24 07:32:55.491905: step: 212/529, loss: 0.01022158283740282
2023-01-24 07:32:56.586466: step: 216/529, loss: 0.018166281282901764
2023-01-24 07:32:57.677140: step: 220/529, loss: 0.010322998277842999
2023-01-24 07:32:58.790610: step: 224/529, loss: 0.04177597537636757
2023-01-24 07:32:59.897157: step: 228/529, loss: 0.02162901870906353
2023-01-24 07:33:01.009456: step: 232/529, loss: 0.004620315972715616
2023-01-24 07:33:02.121927: step: 236/529, loss: 0.014923829585313797
2023-01-24 07:33:03.238599: step: 240/529, loss: 0.006562465336173773
2023-01-24 07:33:04.339491: step: 244/529, loss: 0.007545576896518469
2023-01-24 07:33:05.430618: step: 248/529, loss: 0.003948131110519171
2023-01-24 07:33:06.528824: step: 252/529, loss: 0.011165970005095005
2023-01-24 07:33:07.638083: step: 256/529, loss: 0.017482131719589233
2023-01-24 07:33:08.738247: step: 260/529, loss: 0.014062904752790928
2023-01-24 07:33:09.844037: step: 264/529, loss: 0.020463835448026657
2023-01-24 07:33:10.958234: step: 268/529, loss: 0.007404504809528589
2023-01-24 07:33:12.064930: step: 272/529, loss: 0.0030040584970265627
2023-01-24 07:33:13.163027: step: 276/529, loss: 0.0
2023-01-24 07:33:14.278994: step: 280/529, loss: 0.06010463461279869
2023-01-24 07:33:15.405346: step: 284/529, loss: 0.016965633258223534
2023-01-24 07:33:16.507564: step: 288/529, loss: 0.006219563074409962
2023-01-24 07:33:17.626696: step: 292/529, loss: 0.004653458949178457
2023-01-24 07:33:18.734388: step: 296/529, loss: 0.008565942756831646
2023-01-24 07:33:19.827755: step: 300/529, loss: 0.012844175100326538
2023-01-24 07:33:20.937082: step: 304/529, loss: 0.008220589719712734
2023-01-24 07:33:22.040939: step: 308/529, loss: 0.04331209510564804
2023-01-24 07:33:23.150273: step: 312/529, loss: 0.0030146182980388403
2023-01-24 07:33:24.264485: step: 316/529, loss: 0.0468660406768322
2023-01-24 07:33:25.353710: step: 320/529, loss: 0.016729986295104027
2023-01-24 07:33:26.478787: step: 324/529, loss: 0.004962988197803497
2023-01-24 07:33:27.589875: step: 328/529, loss: 0.024184400215744972
2023-01-24 07:33:28.699060: step: 332/529, loss: 0.022226804867386818
2023-01-24 07:33:29.800513: step: 336/529, loss: 0.010644815862178802
2023-01-24 07:33:30.927152: step: 340/529, loss: 0.004353120923042297
2023-01-24 07:33:32.075440: step: 344/529, loss: 0.040854379534721375
2023-01-24 07:33:33.208132: step: 348/529, loss: 0.04305291920900345
2023-01-24 07:33:34.317672: step: 352/529, loss: 0.013636622577905655
2023-01-24 07:33:35.409350: step: 356/529, loss: 0.0040465048514306545
2023-01-24 07:33:36.518431: step: 360/529, loss: 0.012581290677189827
2023-01-24 07:33:37.622125: step: 364/529, loss: 0.004859903361648321
2023-01-24 07:33:38.744275: step: 368/529, loss: 0.015072670765221119
2023-01-24 07:33:39.859973: step: 372/529, loss: 0.00809277594089508
2023-01-24 07:33:40.942088: step: 376/529, loss: 0.009031995199620724
2023-01-24 07:33:42.059673: step: 380/529, loss: 0.00619395449757576
2023-01-24 07:33:43.158400: step: 384/529, loss: 0.02816014178097248
2023-01-24 07:33:44.285247: step: 388/529, loss: 0.03250144422054291
2023-01-24 07:33:45.385101: step: 392/529, loss: 0.009218337014317513
2023-01-24 07:33:46.497219: step: 396/529, loss: 0.006811859551817179
2023-01-24 07:33:47.592104: step: 400/529, loss: 0.030372116714715958
2023-01-24 07:33:48.717693: step: 404/529, loss: 0.011055875569581985
2023-01-24 07:33:49.836550: step: 408/529, loss: 0.009250106289982796
2023-01-24 07:33:50.937583: step: 412/529, loss: 0.01222851313650608
2023-01-24 07:33:52.065206: step: 416/529, loss: 0.009741735644638538
2023-01-24 07:33:53.178520: step: 420/529, loss: 0.00820836890488863
2023-01-24 07:33:54.281170: step: 424/529, loss: 0.009705927222967148
2023-01-24 07:33:55.393319: step: 428/529, loss: 0.004971783608198166
2023-01-24 07:33:56.503503: step: 432/529, loss: 0.009303607977926731
2023-01-24 07:33:57.622053: step: 436/529, loss: 0.026462413370609283
2023-01-24 07:33:58.732605: step: 440/529, loss: 0.003007612656801939
2023-01-24 07:33:59.843693: step: 444/529, loss: 0.007574520073831081
2023-01-24 07:34:00.989094: step: 448/529, loss: 0.0124023063108325
2023-01-24 07:34:02.117983: step: 452/529, loss: 0.012094407342374325
2023-01-24 07:34:03.236112: step: 456/529, loss: 0.010857230052351952
2023-01-24 07:34:04.352953: step: 460/529, loss: 0.009426238015294075
2023-01-24 07:34:05.478991: step: 464/529, loss: 0.00946289487183094
2023-01-24 07:34:06.596635: step: 468/529, loss: 0.04993095621466637
2023-01-24 07:34:07.742282: step: 472/529, loss: 0.008180856704711914
2023-01-24 07:34:08.860329: step: 476/529, loss: 0.007782386150211096
2023-01-24 07:34:09.995097: step: 480/529, loss: 0.012876303866505623
2023-01-24 07:34:11.107334: step: 484/529, loss: 0.0029120012186467648
2023-01-24 07:34:12.208101: step: 488/529, loss: 0.008031805977225304
2023-01-24 07:34:13.342286: step: 492/529, loss: 0.016908133402466774
2023-01-24 07:34:14.448889: step: 496/529, loss: 0.007961700670421124
2023-01-24 07:34:15.569002: step: 500/529, loss: 0.00820307619869709
2023-01-24 07:34:16.669683: step: 504/529, loss: 0.006375925615429878
2023-01-24 07:34:17.767296: step: 508/529, loss: 0.005103034898638725
2023-01-24 07:34:18.887407: step: 512/529, loss: 0.03152255341410637
2023-01-24 07:34:20.005263: step: 516/529, loss: 0.028367677703499794
2023-01-24 07:34:21.122965: step: 520/529, loss: 0.006421062164008617
2023-01-24 07:34:22.241781: step: 524/529, loss: 0.005070759914815426
2023-01-24 07:34:23.347456: step: 528/529, loss: 0.0734584778547287
2023-01-24 07:34:24.469745: step: 532/529, loss: 0.006186713930219412
2023-01-24 07:34:25.585203: step: 536/529, loss: 0.00510924868285656
2023-01-24 07:34:26.693272: step: 540/529, loss: 0.0038213462103158236
2023-01-24 07:34:27.795088: step: 544/529, loss: 0.025778640061616898
2023-01-24 07:34:28.897935: step: 548/529, loss: 0.059537455439567566
2023-01-24 07:34:30.014688: step: 552/529, loss: 0.04153849929571152
2023-01-24 07:34:31.121410: step: 556/529, loss: 0.006779353599995375
2023-01-24 07:34:32.210809: step: 560/529, loss: 0.0036809067241847515
2023-01-24 07:34:33.334639: step: 564/529, loss: 0.03398386016488075
2023-01-24 07:34:34.461849: step: 568/529, loss: 0.005276466719806194
2023-01-24 07:34:35.565979: step: 572/529, loss: 0.0028425143100321293
2023-01-24 07:34:36.669477: step: 576/529, loss: 0.009706833399832249
2023-01-24 07:34:37.772738: step: 580/529, loss: 0.010437401942908764
2023-01-24 07:34:38.882723: step: 584/529, loss: 0.00651808176189661
2023-01-24 07:34:39.974948: step: 588/529, loss: 0.012304767034947872
2023-01-24 07:34:41.085004: step: 592/529, loss: 0.0046713827177882195
2023-01-24 07:34:42.187534: step: 596/529, loss: 0.02026529423892498
2023-01-24 07:34:43.295674: step: 600/529, loss: 0.015400368720293045
2023-01-24 07:34:44.399575: step: 604/529, loss: 0.0
2023-01-24 07:34:45.541071: step: 608/529, loss: 0.0044232867658138275
2023-01-24 07:34:46.636000: step: 612/529, loss: 0.0017095786752179265
2023-01-24 07:34:47.764298: step: 616/529, loss: 0.007761573418974876
2023-01-24 07:34:48.854105: step: 620/529, loss: 0.011994373984634876
2023-01-24 07:34:49.979593: step: 624/529, loss: 0.00995255634188652
2023-01-24 07:34:51.116926: step: 628/529, loss: 0.010592106729745865
2023-01-24 07:34:52.210618: step: 632/529, loss: 0.013124264776706696
2023-01-24 07:34:53.307251: step: 636/529, loss: 0.01579657942056656
2023-01-24 07:34:54.411577: step: 640/529, loss: 0.007024318911135197
2023-01-24 07:34:55.503465: step: 644/529, loss: 0.013561829924583435
2023-01-24 07:34:56.617584: step: 648/529, loss: 0.007875878363847733
2023-01-24 07:34:57.734873: step: 652/529, loss: 0.006561497692018747
2023-01-24 07:34:58.857612: step: 656/529, loss: 0.020171910524368286
2023-01-24 07:34:59.971824: step: 660/529, loss: 0.026801681146025658
2023-01-24 07:35:01.076565: step: 664/529, loss: 0.0040346658788621426
2023-01-24 07:35:02.194710: step: 668/529, loss: 0.010607567615807056
2023-01-24 07:35:03.301964: step: 672/529, loss: 0.00720202038064599
2023-01-24 07:35:04.396611: step: 676/529, loss: 0.007663401775062084
2023-01-24 07:35:05.518961: step: 680/529, loss: 0.00843114499002695
2023-01-24 07:35:06.634449: step: 684/529, loss: 0.028987901285290718
2023-01-24 07:35:07.736415: step: 688/529, loss: 0.021602654829621315
2023-01-24 07:35:08.830539: step: 692/529, loss: 0.00838488806039095
2023-01-24 07:35:09.915293: step: 696/529, loss: 0.005438137799501419
2023-01-24 07:35:11.041778: step: 700/529, loss: 0.02256591059267521
2023-01-24 07:35:12.141606: step: 704/529, loss: 0.01812754012644291
2023-01-24 07:35:13.255199: step: 708/529, loss: 0.006764445919543505
2023-01-24 07:35:14.353926: step: 712/529, loss: 0.04464699700474739
2023-01-24 07:35:15.450922: step: 716/529, loss: 0.020541075617074966
2023-01-24 07:35:16.561483: step: 720/529, loss: 0.0046661836095154285
2023-01-24 07:35:17.678573: step: 724/529, loss: 0.006169058848172426
2023-01-24 07:35:18.770313: step: 728/529, loss: 0.0071898698806762695
2023-01-24 07:35:19.875480: step: 732/529, loss: 0.03490616753697395
2023-01-24 07:35:20.989980: step: 736/529, loss: 0.003926218021661043
2023-01-24 07:35:22.089505: step: 740/529, loss: 0.010022901929914951
2023-01-24 07:35:23.202778: step: 744/529, loss: 0.022787563502788544
2023-01-24 07:35:24.299987: step: 748/529, loss: 0.005251681432127953
2023-01-24 07:35:25.407433: step: 752/529, loss: 0.006961153354495764
2023-01-24 07:35:26.501911: step: 756/529, loss: 0.006728820037096739
2023-01-24 07:35:27.630382: step: 760/529, loss: 0.02350759692490101
2023-01-24 07:35:28.729128: step: 764/529, loss: 0.030634228140115738
2023-01-24 07:35:29.857584: step: 768/529, loss: 0.005208211950957775
2023-01-24 07:35:30.974943: step: 772/529, loss: 0.009751081466674805
2023-01-24 07:35:32.097218: step: 776/529, loss: 0.00818828959017992
2023-01-24 07:35:33.204677: step: 780/529, loss: 0.016989491879940033
2023-01-24 07:35:34.314292: step: 784/529, loss: 0.006734752561897039
2023-01-24 07:35:35.441096: step: 788/529, loss: 0.004802794195711613
2023-01-24 07:35:36.549642: step: 792/529, loss: 0.030767805874347687
2023-01-24 07:35:37.647486: step: 796/529, loss: 0.008174249902367592
2023-01-24 07:35:38.747852: step: 800/529, loss: 0.03600287437438965
2023-01-24 07:35:39.851168: step: 804/529, loss: 0.015916625037789345
2023-01-24 07:35:40.978122: step: 808/529, loss: 0.03856165334582329
2023-01-24 07:35:42.105242: step: 812/529, loss: 0.005122302565723658
2023-01-24 07:35:43.198318: step: 816/529, loss: 0.01365729235112667
2023-01-24 07:35:44.296908: step: 820/529, loss: 0.0024407037999480963
2023-01-24 07:35:45.426171: step: 824/529, loss: 0.01446897815912962
2023-01-24 07:35:46.553848: step: 828/529, loss: 0.01769627258181572
2023-01-24 07:35:47.667512: step: 832/529, loss: 0.024822115898132324
2023-01-24 07:35:48.759054: step: 836/529, loss: 0.03964380547404289
2023-01-24 07:35:49.875244: step: 840/529, loss: 0.025744302198290825
2023-01-24 07:35:50.992333: step: 844/529, loss: 0.03316003084182739
2023-01-24 07:35:52.089266: step: 848/529, loss: 0.0027758243959397078
2023-01-24 07:35:53.204637: step: 852/529, loss: 0.038947537541389465
2023-01-24 07:35:54.325685: step: 856/529, loss: 0.03559670224785805
2023-01-24 07:35:55.438523: step: 860/529, loss: 0.004581565503031015
2023-01-24 07:35:56.550290: step: 864/529, loss: 0.009412151761353016
2023-01-24 07:35:57.658636: step: 868/529, loss: 0.006614048499614
2023-01-24 07:35:58.761837: step: 872/529, loss: 0.0059139481745660305
2023-01-24 07:35:59.881151: step: 876/529, loss: 0.03860270977020264
2023-01-24 07:36:01.004630: step: 880/529, loss: 0.005993709899485111
2023-01-24 07:36:02.130086: step: 884/529, loss: 0.004429427906870842
2023-01-24 07:36:03.250073: step: 888/529, loss: 0.06381593644618988
2023-01-24 07:36:04.360544: step: 892/529, loss: 0.05742922052741051
2023-01-24 07:36:05.456670: step: 896/529, loss: 0.004541744943708181
2023-01-24 07:36:06.572722: step: 900/529, loss: 0.01731082610785961
2023-01-24 07:36:07.708113: step: 904/529, loss: 0.003912780433893204
2023-01-24 07:36:08.807281: step: 908/529, loss: 0.015212543308734894
2023-01-24 07:36:09.932304: step: 912/529, loss: 0.028064537793397903
2023-01-24 07:36:11.047611: step: 916/529, loss: 0.004164090845733881
2023-01-24 07:36:12.141360: step: 920/529, loss: 0.024902500212192535
2023-01-24 07:36:13.258798: step: 924/529, loss: 0.007549820467829704
2023-01-24 07:36:14.369113: step: 928/529, loss: 0.01531895436346531
2023-01-24 07:36:15.497678: step: 932/529, loss: 0.01943441480398178
2023-01-24 07:36:16.626580: step: 936/529, loss: 0.008244885131716728
2023-01-24 07:36:17.717527: step: 940/529, loss: 0.01422719657421112
2023-01-24 07:36:18.818547: step: 944/529, loss: 0.00490589952096343
2023-01-24 07:36:19.960048: step: 948/529, loss: 0.014141133986413479
2023-01-24 07:36:21.101566: step: 952/529, loss: 0.043286994099617004
2023-01-24 07:36:22.229838: step: 956/529, loss: 0.03698762506246567
2023-01-24 07:36:23.329628: step: 960/529, loss: 0.0031352443620562553
2023-01-24 07:36:24.421793: step: 964/529, loss: 0.022375736385583878
2023-01-24 07:36:25.509248: step: 968/529, loss: 0.010876361280679703
2023-01-24 07:36:26.616215: step: 972/529, loss: 0.00666898675262928
2023-01-24 07:36:27.728609: step: 976/529, loss: 0.0071960752829909325
2023-01-24 07:36:28.830265: step: 980/529, loss: 0.006525927688926458
2023-01-24 07:36:29.928591: step: 984/529, loss: 0.030511315912008286
2023-01-24 07:36:31.025089: step: 988/529, loss: 0.012112803757190704
2023-01-24 07:36:32.150589: step: 992/529, loss: 0.07843738049268723
2023-01-24 07:36:33.274931: step: 996/529, loss: 0.016512110829353333
2023-01-24 07:36:34.376996: step: 1000/529, loss: 0.003049770137295127
2023-01-24 07:36:35.510497: step: 1004/529, loss: 0.04512205719947815
2023-01-24 07:36:36.623639: step: 1008/529, loss: 0.007197485771030188
2023-01-24 07:36:37.733951: step: 1012/529, loss: 0.05175314098596573
2023-01-24 07:36:38.846781: step: 1016/529, loss: 0.024995850399136543
2023-01-24 07:36:39.955863: step: 1020/529, loss: 0.019134696573019028
2023-01-24 07:36:41.053368: step: 1024/529, loss: 0.003969466779381037
2023-01-24 07:36:42.154040: step: 1028/529, loss: 0.016748148947954178
2023-01-24 07:36:43.246813: step: 1032/529, loss: 0.010121073573827744
2023-01-24 07:36:44.336259: step: 1036/529, loss: 0.003607254009693861
2023-01-24 07:36:45.454011: step: 1040/529, loss: 0.0025053697172552347
2023-01-24 07:36:46.543503: step: 1044/529, loss: 0.1172996312379837
2023-01-24 07:36:47.661131: step: 1048/529, loss: 0.015168258920311928
2023-01-24 07:36:48.760467: step: 1052/529, loss: 0.00747688626870513
2023-01-24 07:36:49.896489: step: 1056/529, loss: 0.013755887746810913
2023-01-24 07:36:51.030459: step: 1060/529, loss: 0.011706928722560406
2023-01-24 07:36:52.110399: step: 1064/529, loss: 0.010267854668200016
2023-01-24 07:36:53.215548: step: 1068/529, loss: 0.021065551787614822
2023-01-24 07:36:54.309441: step: 1072/529, loss: 0.008091267198324203
2023-01-24 07:36:55.402301: step: 1076/529, loss: 0.009658264927566051
2023-01-24 07:36:56.503775: step: 1080/529, loss: 0.0066797793842852116
2023-01-24 07:36:57.598274: step: 1084/529, loss: 0.006737333722412586
2023-01-24 07:36:58.717417: step: 1088/529, loss: 0.0060395351611077785
2023-01-24 07:36:59.829101: step: 1092/529, loss: 0.02207772620022297
2023-01-24 07:37:00.973018: step: 1096/529, loss: 0.028347786515951157
2023-01-24 07:37:02.096839: step: 1100/529, loss: 0.01743381842970848
2023-01-24 07:37:03.208408: step: 1104/529, loss: 0.006190153304487467
2023-01-24 07:37:04.315710: step: 1108/529, loss: 0.005800239741802216
2023-01-24 07:37:05.448825: step: 1112/529, loss: 0.005582496523857117
2023-01-24 07:37:06.572598: step: 1116/529, loss: 0.007586284540593624
2023-01-24 07:37:07.678562: step: 1120/529, loss: 0.00489607872441411
2023-01-24 07:37:08.794717: step: 1124/529, loss: 0.009180678054690361
2023-01-24 07:37:09.910993: step: 1128/529, loss: 0.01565048284828663
2023-01-24 07:37:11.021208: step: 1132/529, loss: 0.01631510630249977
2023-01-24 07:37:12.121626: step: 1136/529, loss: 0.004433012567460537
2023-01-24 07:37:13.229782: step: 1140/529, loss: 0.037556763738393784
2023-01-24 07:37:14.339342: step: 1144/529, loss: 0.003132070880383253
2023-01-24 07:37:15.455010: step: 1148/529, loss: 0.008190575987100601
2023-01-24 07:37:16.568681: step: 1152/529, loss: 0.026660114526748657
2023-01-24 07:37:17.669576: step: 1156/529, loss: 0.029099665582180023
2023-01-24 07:37:18.767504: step: 1160/529, loss: 0.004278501961380243
2023-01-24 07:37:19.872089: step: 1164/529, loss: 0.004865444730967283
2023-01-24 07:37:20.998925: step: 1168/529, loss: 0.0708141028881073
2023-01-24 07:37:22.089945: step: 1172/529, loss: 0.006155682262033224
2023-01-24 07:37:23.195975: step: 1176/529, loss: 0.03570152074098587
2023-01-24 07:37:24.300873: step: 1180/529, loss: 0.006735211703926325
2023-01-24 07:37:25.394427: step: 1184/529, loss: 0.010107604786753654
2023-01-24 07:37:26.512792: step: 1188/529, loss: 0.0065239532850682735
2023-01-24 07:37:27.624620: step: 1192/529, loss: 0.009267025627195835
2023-01-24 07:37:28.728652: step: 1196/529, loss: 0.04032520949840546
2023-01-24 07:37:29.830474: step: 1200/529, loss: 0.007525768131017685
2023-01-24 07:37:30.943217: step: 1204/529, loss: 0.008084542118012905
2023-01-24 07:37:32.027473: step: 1208/529, loss: 0.03704090416431427
2023-01-24 07:37:33.134886: step: 1212/529, loss: 0.01188336405903101
2023-01-24 07:37:34.251861: step: 1216/529, loss: 0.009477616287767887
2023-01-24 07:37:35.352370: step: 1220/529, loss: 0.006158227566629648
2023-01-24 07:37:36.428332: step: 1224/529, loss: 0.009339524433016777
2023-01-24 07:37:37.533252: step: 1228/529, loss: 0.0031968860421329737
2023-01-24 07:37:38.638768: step: 1232/529, loss: 0.0013618320226669312
2023-01-24 07:37:39.742627: step: 1236/529, loss: 0.008826510049402714
2023-01-24 07:37:40.861966: step: 1240/529, loss: 0.004346330184489489
2023-01-24 07:37:41.974608: step: 1244/529, loss: 0.0046552191488444805
2023-01-24 07:37:43.086908: step: 1248/529, loss: 0.021449366584420204
2023-01-24 07:37:44.193394: step: 1252/529, loss: 0.0045154886320233345
2023-01-24 07:37:45.304375: step: 1256/529, loss: 0.0041392166167497635
2023-01-24 07:37:46.448855: step: 1260/529, loss: 0.0197648573666811
2023-01-24 07:37:47.566891: step: 1264/529, loss: 0.006410130765289068
2023-01-24 07:37:48.679552: step: 1268/529, loss: 0.05202331766486168
2023-01-24 07:37:49.811243: step: 1272/529, loss: 0.010371005162596703
2023-01-24 07:37:50.913694: step: 1276/529, loss: 0.00724055664613843
2023-01-24 07:37:52.025782: step: 1280/529, loss: 0.005425448529422283
2023-01-24 07:37:53.129012: step: 1284/529, loss: 0.022026075050234795
2023-01-24 07:37:54.225074: step: 1288/529, loss: 0.009289804846048355
2023-01-24 07:37:55.311513: step: 1292/529, loss: 0.031058356165885925
2023-01-24 07:37:56.423364: step: 1296/529, loss: 0.04024272412061691
2023-01-24 07:37:57.536836: step: 1300/529, loss: 0.012366924434900284
2023-01-24 07:37:58.642996: step: 1304/529, loss: 0.00781036913394928
2023-01-24 07:37:59.738717: step: 1308/529, loss: 0.022240594029426575
2023-01-24 07:38:00.840566: step: 1312/529, loss: 0.01822182536125183
2023-01-24 07:38:01.967909: step: 1316/529, loss: 0.012602580711245537
2023-01-24 07:38:03.060936: step: 1320/529, loss: 0.007978048175573349
2023-01-24 07:38:04.155467: step: 1324/529, loss: 0.020835481584072113
2023-01-24 07:38:05.252377: step: 1328/529, loss: 0.009168798103928566
2023-01-24 07:38:06.351860: step: 1332/529, loss: 0.008838258683681488
2023-01-24 07:38:07.467653: step: 1336/529, loss: 0.009219838306307793
2023-01-24 07:38:08.575894: step: 1340/529, loss: 0.028161942958831787
2023-01-24 07:38:09.688639: step: 1344/529, loss: 0.01361114252358675
2023-01-24 07:38:10.827295: step: 1348/529, loss: 0.001649112906306982
2023-01-24 07:38:11.954888: step: 1352/529, loss: 0.01526301447302103
2023-01-24 07:38:13.071102: step: 1356/529, loss: 0.005494388286024332
2023-01-24 07:38:14.187893: step: 1360/529, loss: 0.01168822031468153
2023-01-24 07:38:15.287285: step: 1364/529, loss: 0.05306252837181091
2023-01-24 07:38:16.434557: step: 1368/529, loss: 0.07980557531118393
2023-01-24 07:38:17.541557: step: 1372/529, loss: 0.0138575229793787
2023-01-24 07:38:18.656334: step: 1376/529, loss: 0.0192241370677948
2023-01-24 07:38:19.773492: step: 1380/529, loss: 0.005999465007334948
2023-01-24 07:38:20.880772: step: 1384/529, loss: 0.00927741639316082
2023-01-24 07:38:22.006581: step: 1388/529, loss: 0.023513052612543106
2023-01-24 07:38:23.100958: step: 1392/529, loss: 0.005822577513754368
2023-01-24 07:38:24.200315: step: 1396/529, loss: 0.00830264762043953
2023-01-24 07:38:25.310810: step: 1400/529, loss: 0.037708207964897156
2023-01-24 07:38:26.431349: step: 1404/529, loss: 0.006134921219199896
2023-01-24 07:38:27.533247: step: 1408/529, loss: 0.009257950820028782
2023-01-24 07:38:28.630503: step: 1412/529, loss: 0.032635655254125595
2023-01-24 07:38:29.734999: step: 1416/529, loss: 0.016022369265556335
2023-01-24 07:38:30.848294: step: 1420/529, loss: 0.0049875951372087
2023-01-24 07:38:31.947771: step: 1424/529, loss: 0.0034779945854097605
2023-01-24 07:38:33.056142: step: 1428/529, loss: 0.004835793748497963
2023-01-24 07:38:34.159623: step: 1432/529, loss: 0.005195547826588154
2023-01-24 07:38:35.260718: step: 1436/529, loss: 0.009680205024778843
2023-01-24 07:38:36.369318: step: 1440/529, loss: 0.01889902912080288
2023-01-24 07:38:37.501181: step: 1444/529, loss: 0.012766159139573574
2023-01-24 07:38:38.620773: step: 1448/529, loss: 0.009224303998053074
2023-01-24 07:38:39.712184: step: 1452/529, loss: 0.003969091456383467
2023-01-24 07:38:40.815739: step: 1456/529, loss: 0.009867843240499496
2023-01-24 07:38:41.945429: step: 1460/529, loss: 0.021405458450317383
2023-01-24 07:38:43.067283: step: 1464/529, loss: 0.02739710360765457
2023-01-24 07:38:44.163983: step: 1468/529, loss: 0.00500906677916646
2023-01-24 07:38:45.285972: step: 1472/529, loss: 0.016404489055275917
2023-01-24 07:38:46.415314: step: 1476/529, loss: 0.007989022880792618
2023-01-24 07:38:47.514443: step: 1480/529, loss: 0.004829435609281063
2023-01-24 07:38:48.634193: step: 1484/529, loss: 0.02073470689356327
2023-01-24 07:38:49.749023: step: 1488/529, loss: 0.09473828971385956
2023-01-24 07:38:50.867292: step: 1492/529, loss: 0.0077597894705832005
2023-01-24 07:38:52.004929: step: 1496/529, loss: 0.007753786165267229
2023-01-24 07:38:53.113436: step: 1500/529, loss: 0.011193129234015942
2023-01-24 07:38:54.234865: step: 1504/529, loss: 0.006865547504276037
2023-01-24 07:38:55.336317: step: 1508/529, loss: 0.008532942272722721
2023-01-24 07:38:56.438131: step: 1512/529, loss: 0.0017727493541315198
2023-01-24 07:38:57.550658: step: 1516/529, loss: 0.008294845931231976
2023-01-24 07:38:58.632138: step: 1520/529, loss: 0.0044218674302101135
2023-01-24 07:38:59.756722: step: 1524/529, loss: 0.06720639765262604
2023-01-24 07:39:00.864602: step: 1528/529, loss: 0.07407580316066742
2023-01-24 07:39:01.991944: step: 1532/529, loss: 0.009495191276073456
2023-01-24 07:39:03.106422: step: 1536/529, loss: 0.00949164293706417
2023-01-24 07:39:04.225112: step: 1540/529, loss: 0.008992256596684456
2023-01-24 07:39:05.347076: step: 1544/529, loss: 0.00832844153046608
2023-01-24 07:39:06.486022: step: 1548/529, loss: 0.01784440129995346
2023-01-24 07:39:07.596285: step: 1552/529, loss: 0.009815354831516743
2023-01-24 07:39:08.715597: step: 1556/529, loss: 0.03531704470515251
2023-01-24 07:39:09.826849: step: 1560/529, loss: 0.024419886991381645
2023-01-24 07:39:10.937747: step: 1564/529, loss: 0.011316888965666294
2023-01-24 07:39:12.052615: step: 1568/529, loss: 0.008468734100461006
2023-01-24 07:39:13.201559: step: 1572/529, loss: 0.018856732174754143
2023-01-24 07:39:14.311694: step: 1576/529, loss: 0.010021758265793324
2023-01-24 07:39:15.424224: step: 1580/529, loss: 0.006564375013113022
2023-01-24 07:39:16.526796: step: 1584/529, loss: 0.009300853125751019
2023-01-24 07:39:17.622576: step: 1588/529, loss: 0.03209228813648224
2023-01-24 07:39:18.738814: step: 1592/529, loss: 0.011788084171712399
2023-01-24 07:39:19.853929: step: 1596/529, loss: 0.007834677584469318
2023-01-24 07:39:20.944384: step: 1600/529, loss: 0.0005344073288142681
2023-01-24 07:39:22.056423: step: 1604/529, loss: 0.009042621590197086
2023-01-24 07:39:23.172798: step: 1608/529, loss: 0.011133428663015366
2023-01-24 07:39:24.279606: step: 1612/529, loss: 0.011527447029948235
2023-01-24 07:39:25.393469: step: 1616/529, loss: 0.0632004514336586
2023-01-24 07:39:26.511881: step: 1620/529, loss: 0.0006157772149890661
2023-01-24 07:39:27.599019: step: 1624/529, loss: 0.005812895484268665
2023-01-24 07:39:28.724255: step: 1628/529, loss: 0.05044638738036156
2023-01-24 07:39:29.827098: step: 1632/529, loss: 0.025022072717547417
2023-01-24 07:39:30.905899: step: 1636/529, loss: 0.025674128904938698
2023-01-24 07:39:32.023149: step: 1640/529, loss: 0.00849166139960289
2023-01-24 07:39:33.134403: step: 1644/529, loss: 0.008506173267960548
2023-01-24 07:39:34.256117: step: 1648/529, loss: 0.005333370994776487
2023-01-24 07:39:35.369002: step: 1652/529, loss: 0.002690615365281701
2023-01-24 07:39:36.471518: step: 1656/529, loss: 0.022898681461811066
2023-01-24 07:39:37.595563: step: 1660/529, loss: 0.006212149281054735
2023-01-24 07:39:38.715818: step: 1664/529, loss: 0.007051804102957249
2023-01-24 07:39:39.826536: step: 1668/529, loss: 0.0026209489442408085
2023-01-24 07:39:40.915395: step: 1672/529, loss: 0.011211784556508064
2023-01-24 07:39:42.032519: step: 1676/529, loss: 0.008433562703430653
2023-01-24 07:39:43.149540: step: 1680/529, loss: 0.025189196690917015
2023-01-24 07:39:44.244515: step: 1684/529, loss: 0.003636155743151903
2023-01-24 07:39:45.378815: step: 1688/529, loss: 0.009845258668065071
2023-01-24 07:39:46.465388: step: 1692/529, loss: 0.03183900937438011
2023-01-24 07:39:47.574988: step: 1696/529, loss: 0.003094209125265479
2023-01-24 07:39:48.679510: step: 1700/529, loss: 0.02190120331943035
2023-01-24 07:39:49.803652: step: 1704/529, loss: 0.002687569009140134
2023-01-24 07:39:50.907415: step: 1708/529, loss: 0.009060143493115902
2023-01-24 07:39:52.014630: step: 1712/529, loss: 0.02194773405790329
2023-01-24 07:39:53.105029: step: 1716/529, loss: 0.034944772720336914
2023-01-24 07:39:54.224553: step: 1720/529, loss: 0.009142527356743813
2023-01-24 07:39:55.360733: step: 1724/529, loss: 0.01273645181208849
2023-01-24 07:39:56.470145: step: 1728/529, loss: 0.007472269237041473
2023-01-24 07:39:57.575024: step: 1732/529, loss: 0.009180750697851181
2023-01-24 07:39:58.662538: step: 1736/529, loss: 0.004138650372624397
2023-01-24 07:39:59.757731: step: 1740/529, loss: 0.004630414303392172
2023-01-24 07:40:00.854531: step: 1744/529, loss: 0.0065904478542506695
2023-01-24 07:40:01.971608: step: 1748/529, loss: 0.010466614738106728
2023-01-24 07:40:03.092554: step: 1752/529, loss: 0.04151769354939461
2023-01-24 07:40:04.188521: step: 1756/529, loss: 0.02589283511042595
2023-01-24 07:40:05.309023: step: 1760/529, loss: 0.01761699840426445
2023-01-24 07:40:06.406260: step: 1764/529, loss: 0.03993140161037445
2023-01-24 07:40:07.510908: step: 1768/529, loss: 0.006331652402877808
2023-01-24 07:40:08.610216: step: 1772/529, loss: 0.018918009474873543
2023-01-24 07:40:09.731215: step: 1776/529, loss: 0.02306489273905754
2023-01-24 07:40:10.846456: step: 1780/529, loss: 0.006211545318365097
2023-01-24 07:40:11.946671: step: 1784/529, loss: 0.003728611394762993
2023-01-24 07:40:13.054859: step: 1788/529, loss: 0.005016469396650791
2023-01-24 07:40:14.155290: step: 1792/529, loss: 0.004680269863456488
2023-01-24 07:40:15.270845: step: 1796/529, loss: 0.007269581779837608
2023-01-24 07:40:16.376235: step: 1800/529, loss: 0.022171501070261
2023-01-24 07:40:17.499403: step: 1804/529, loss: 0.009929131716489792
2023-01-24 07:40:18.606080: step: 1808/529, loss: 0.057336192578077316
2023-01-24 07:40:19.709790: step: 1812/529, loss: 0.008408146910369396
2023-01-24 07:40:20.836358: step: 1816/529, loss: 0.0034600687213242054
2023-01-24 07:40:21.944090: step: 1820/529, loss: 0.010800952091813087
2023-01-24 07:40:23.035871: step: 1824/529, loss: 0.005716582294553518
2023-01-24 07:40:24.152230: step: 1828/529, loss: 0.00797891803085804
2023-01-24 07:40:25.243434: step: 1832/529, loss: 0.02174191176891327
2023-01-24 07:40:26.346664: step: 1836/529, loss: 0.006099015474319458
2023-01-24 07:40:27.455368: step: 1840/529, loss: 0.0033705770038068295
2023-01-24 07:40:28.559711: step: 1844/529, loss: 0.002841704525053501
2023-01-24 07:40:29.659407: step: 1848/529, loss: 0.014144199900329113
2023-01-24 07:40:30.775201: step: 1852/529, loss: 0.008648702874779701
2023-01-24 07:40:31.929915: step: 1856/529, loss: 0.0062553295865654945
2023-01-24 07:40:33.029348: step: 1860/529, loss: 0.004111865069717169
2023-01-24 07:40:34.135324: step: 1864/529, loss: 0.004711200017482042
2023-01-24 07:40:35.244266: step: 1868/529, loss: 0.005292634945362806
2023-01-24 07:40:36.345308: step: 1872/529, loss: 5.4861877288203686e-05
2023-01-24 07:40:37.437561: step: 1876/529, loss: 0.00027760709053836763
2023-01-24 07:40:38.541046: step: 1880/529, loss: 0.01562339998781681
2023-01-24 07:40:39.642638: step: 1884/529, loss: 0.014251288957893848
2023-01-24 07:40:40.756808: step: 1888/529, loss: 0.02519753947854042
2023-01-24 07:40:41.892303: step: 1892/529, loss: 0.02733030542731285
2023-01-24 07:40:42.999423: step: 1896/529, loss: 0.005994006525725126
2023-01-24 07:40:44.108645: step: 1900/529, loss: 0.005048609338700771
2023-01-24 07:40:45.213858: step: 1904/529, loss: 0.003010928863659501
2023-01-24 07:40:46.317759: step: 1908/529, loss: 0.009821907617151737
2023-01-24 07:40:47.423217: step: 1912/529, loss: 0.02399621158838272
2023-01-24 07:40:48.511408: step: 1916/529, loss: 0.01810375601053238
2023-01-24 07:40:49.618911: step: 1920/529, loss: 0.012408771552145481
2023-01-24 07:40:50.722166: step: 1924/529, loss: 0.004833292681723833
2023-01-24 07:40:51.813090: step: 1928/529, loss: 0.007213070057332516
2023-01-24 07:40:52.909697: step: 1932/529, loss: 0.00512283481657505
2023-01-24 07:40:54.014588: step: 1936/529, loss: 0.029104046523571014
2023-01-24 07:40:55.122021: step: 1940/529, loss: 0.008731608279049397
2023-01-24 07:40:56.204743: step: 1944/529, loss: 0.0018308151047676802
2023-01-24 07:40:57.300147: step: 1948/529, loss: 0.016262350603938103
2023-01-24 07:40:58.425702: step: 1952/529, loss: 0.0015288363210856915
2023-01-24 07:40:59.543925: step: 1956/529, loss: 0.011807559989392757
2023-01-24 07:41:00.648876: step: 1960/529, loss: 0.002348709851503372
2023-01-24 07:41:01.750499: step: 1964/529, loss: 0.003221815684810281
2023-01-24 07:41:02.892704: step: 1968/529, loss: 0.00016679333930369467
2023-01-24 07:41:03.992598: step: 1972/529, loss: 0.01722387783229351
2023-01-24 07:41:05.099844: step: 1976/529, loss: 0.01304915826767683
2023-01-24 07:41:06.176510: step: 1980/529, loss: 0.008372940123081207
2023-01-24 07:41:07.285359: step: 1984/529, loss: 0.008127515204250813
2023-01-24 07:41:08.396999: step: 1988/529, loss: 0.008517141453921795
2023-01-24 07:41:09.526760: step: 1992/529, loss: 0.026112094521522522
2023-01-24 07:41:10.636133: step: 1996/529, loss: 0.013220422901213169
2023-01-24 07:41:11.728142: step: 2000/529, loss: 0.0030801587272435427
2023-01-24 07:41:12.847663: step: 2004/529, loss: 0.007968481630086899
2023-01-24 07:41:13.940940: step: 2008/529, loss: 0.0016047836979851127
2023-01-24 07:41:15.087650: step: 2012/529, loss: 0.0065104663372039795
2023-01-24 07:41:16.221349: step: 2016/529, loss: 0.00422339141368866
2023-01-24 07:41:17.332661: step: 2020/529, loss: 0.009648089297115803
2023-01-24 07:41:18.425357: step: 2024/529, loss: 0.011106958612799644
2023-01-24 07:41:19.543894: step: 2028/529, loss: 0.007304979022592306
2023-01-24 07:41:20.651462: step: 2032/529, loss: 0.010854221880435944
2023-01-24 07:41:21.775165: step: 2036/529, loss: 0.007544748485088348
2023-01-24 07:41:22.893829: step: 2040/529, loss: 0.006136166863143444
2023-01-24 07:41:24.010141: step: 2044/529, loss: 0.004133906215429306
2023-01-24 07:41:25.127320: step: 2048/529, loss: 0.011073668487370014
2023-01-24 07:41:26.244597: step: 2052/529, loss: 0.005836395546793938
2023-01-24 07:41:27.319512: step: 2056/529, loss: 0.009044923819601536
2023-01-24 07:41:28.423507: step: 2060/529, loss: 0.00556538812816143
2023-01-24 07:41:29.538169: step: 2064/529, loss: 0.014669734053313732
2023-01-24 07:41:30.644250: step: 2068/529, loss: 0.010857461020350456
2023-01-24 07:41:31.765938: step: 2072/529, loss: 0.007249240763485432
2023-01-24 07:41:32.871804: step: 2076/529, loss: 0.007566243410110474
2023-01-24 07:41:34.011053: step: 2080/529, loss: 0.006541979964822531
2023-01-24 07:41:35.130331: step: 2084/529, loss: 0.0038325912319123745
2023-01-24 07:41:36.245829: step: 2088/529, loss: 0.01036426518112421
2023-01-24 07:41:37.347327: step: 2092/529, loss: 0.003651689039543271
2023-01-24 07:41:38.433560: step: 2096/529, loss: 0.015157479792833328
2023-01-24 07:41:39.538258: step: 2100/529, loss: 0.02793698012828827
2023-01-24 07:41:40.637232: step: 2104/529, loss: 0.008867218159139156
2023-01-24 07:41:41.746028: step: 2108/529, loss: 0.027072349563241005
2023-01-24 07:41:42.865657: step: 2112/529, loss: 0.014590988866984844
2023-01-24 07:41:43.945657: step: 2116/529, loss: 0.004477841779589653
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3659688861398954, 'r': 0.33471917100461024, 'f1': 0.34964718160441943}, 'combined': 0.2576347653927301, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37513546916738133, 'r': 0.28899084236551303, 'f1': 0.326476193920511}, 'combined': 0.20066341675114335, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4087527352297593, 'r': 0.35445920303605316, 'f1': 0.3796747967479675}, 'combined': 0.27976037655113395, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3935884290148207, 'r': 0.2837656611268032, 'f1': 0.3297739908764661}, 'combined': 0.20368393554134676, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3659688861398954, 'r': 0.33471917100461024, 'f1': 0.34964718160441943}, 'combined': 0.2576347653927301, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37513546916738133, 'r': 0.28899084236551303, 'f1': 0.326476193920511}, 'combined': 0.20066341675114335, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4087527352297593, 'r': 0.35445920303605316, 'f1': 0.3796747967479675}, 'combined': 0.27976037655113395, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3935884290148207, 'r': 0.2837656611268032, 'f1': 0.3297739908764661}, 'combined': 0.20368393554134676, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:44:33.384644: step: 4/529, loss: 0.009641360491514206
2023-01-24 07:44:34.478747: step: 8/529, loss: 0.004441812634468079
2023-01-24 07:44:35.578435: step: 12/529, loss: 0.009472782723605633
2023-01-24 07:44:36.677625: step: 16/529, loss: 0.013659856282174587
2023-01-24 07:44:37.766298: step: 20/529, loss: 0.07212577760219574
2023-01-24 07:44:38.860779: step: 24/529, loss: 0.008560748770833015
2023-01-24 07:44:39.947836: step: 28/529, loss: 0.018241802230477333
2023-01-24 07:44:41.036349: step: 32/529, loss: 0.015703311190009117
2023-01-24 07:44:42.119631: step: 36/529, loss: 0.026424825191497803
2023-01-24 07:44:43.205684: step: 40/529, loss: 0.005716434679925442
2023-01-24 07:44:44.317784: step: 44/529, loss: 0.007539636921137571
2023-01-24 07:44:45.445971: step: 48/529, loss: 0.00743406405672431
2023-01-24 07:44:46.561212: step: 52/529, loss: 0.029411813244223595
2023-01-24 07:44:47.657144: step: 56/529, loss: 0.015271333046257496
2023-01-24 07:44:48.755739: step: 60/529, loss: 0.02746458165347576
2023-01-24 07:44:49.855090: step: 64/529, loss: 0.025568468496203423
2023-01-24 07:44:50.964860: step: 68/529, loss: 0.011672289110720158
2023-01-24 07:44:52.057323: step: 72/529, loss: 0.010656093247234821
2023-01-24 07:44:53.178015: step: 76/529, loss: 0.0061738379299640656
2023-01-24 07:44:54.278232: step: 80/529, loss: 0.0052688331343233585
2023-01-24 07:44:55.396399: step: 84/529, loss: 0.007690116297453642
2023-01-24 07:44:56.512333: step: 88/529, loss: 0.010369677096605301
2023-01-24 07:44:57.628352: step: 92/529, loss: 0.004477673210203648
2023-01-24 07:44:58.739068: step: 96/529, loss: 0.02245650812983513
2023-01-24 07:44:59.844588: step: 100/529, loss: 0.02555593103170395
2023-01-24 07:45:00.976971: step: 104/529, loss: 0.0033164224587380886
2023-01-24 07:45:02.094162: step: 108/529, loss: 0.005291598383337259
2023-01-24 07:45:03.236277: step: 112/529, loss: 0.015692410990595818
2023-01-24 07:45:04.320089: step: 116/529, loss: 0.006268255412578583
2023-01-24 07:45:05.432349: step: 120/529, loss: 0.00944138877093792
2023-01-24 07:45:06.540842: step: 124/529, loss: 0.005227590445429087
2023-01-24 07:45:07.643827: step: 128/529, loss: 0.03279861807823181
2023-01-24 07:45:08.738553: step: 132/529, loss: 0.002848308067768812
2023-01-24 07:45:09.825374: step: 136/529, loss: 0.00799502246081829
2023-01-24 07:45:10.917981: step: 140/529, loss: 0.0037851601373404264
2023-01-24 07:45:12.029160: step: 144/529, loss: 0.005079436115920544
2023-01-24 07:45:13.153312: step: 148/529, loss: 0.008446757681667805
2023-01-24 07:45:14.269255: step: 152/529, loss: 0.0068071456626057625
2023-01-24 07:45:15.365925: step: 156/529, loss: 0.005443734582513571
2023-01-24 07:45:16.461452: step: 160/529, loss: 0.006948627065867186
2023-01-24 07:45:17.584291: step: 164/529, loss: 0.02039605751633644
2023-01-24 07:45:18.687868: step: 168/529, loss: 0.002671348163858056
2023-01-24 07:45:19.798446: step: 172/529, loss: 0.03272193297743797
2023-01-24 07:45:20.915042: step: 176/529, loss: 0.014596843160688877
2023-01-24 07:45:22.057028: step: 180/529, loss: 0.0107597466558218
2023-01-24 07:45:23.145946: step: 184/529, loss: 0.02122785523533821
2023-01-24 07:45:24.235686: step: 188/529, loss: 0.0005063194548711181
2023-01-24 07:45:25.338697: step: 192/529, loss: 0.028680510818958282
2023-01-24 07:45:26.449602: step: 196/529, loss: 0.004366212524473667
2023-01-24 07:45:27.548248: step: 200/529, loss: 0.006697970442473888
2023-01-24 07:45:28.624821: step: 204/529, loss: 0.00811207015067339
2023-01-24 07:45:29.764119: step: 208/529, loss: 0.006754192523658276
2023-01-24 07:45:30.867658: step: 212/529, loss: 0.0032824159134179354
2023-01-24 07:45:31.977917: step: 216/529, loss: 0.02449607476592064
2023-01-24 07:45:33.085529: step: 220/529, loss: 0.005415010266005993
2023-01-24 07:45:34.175720: step: 224/529, loss: 0.014032186940312386
2023-01-24 07:45:35.280358: step: 228/529, loss: 0.013815222308039665
2023-01-24 07:45:36.388965: step: 232/529, loss: 0.005068039521574974
2023-01-24 07:45:37.528854: step: 236/529, loss: 0.003798120655119419
2023-01-24 07:45:38.647385: step: 240/529, loss: 0.01475275494158268
2023-01-24 07:45:39.751091: step: 244/529, loss: 0.004754318855702877
2023-01-24 07:45:40.859947: step: 248/529, loss: 0.014115816913545132
2023-01-24 07:45:41.990897: step: 252/529, loss: 0.0043961177580058575
2023-01-24 07:45:43.089159: step: 256/529, loss: 0.05555802583694458
2023-01-24 07:45:44.199883: step: 260/529, loss: 0.005500257946550846
2023-01-24 07:45:45.314200: step: 264/529, loss: 0.00768198212608695
2023-01-24 07:45:46.423242: step: 268/529, loss: 0.0022405358031392097
2023-01-24 07:45:47.558835: step: 272/529, loss: 0.0062119620852172375
2023-01-24 07:45:48.659826: step: 276/529, loss: 0.008880898356437683
2023-01-24 07:45:49.792438: step: 280/529, loss: 0.0029047697316855192
2023-01-24 07:45:50.879944: step: 284/529, loss: 0.001257889554835856
2023-01-24 07:45:51.981313: step: 288/529, loss: 0.008901875466108322
2023-01-24 07:45:53.106780: step: 292/529, loss: 0.00875263661146164
2023-01-24 07:45:54.224121: step: 296/529, loss: 0.003783109365031123
2023-01-24 07:45:55.345409: step: 300/529, loss: 0.01430480182170868
2023-01-24 07:45:56.432072: step: 304/529, loss: 0.014848808757960796
2023-01-24 07:45:57.560647: step: 308/529, loss: 0.04041906073689461
2023-01-24 07:45:58.647399: step: 312/529, loss: 0.005450076889246702
2023-01-24 07:45:59.756986: step: 316/529, loss: 0.00969383679330349
2023-01-24 07:46:00.849282: step: 320/529, loss: 0.017713718116283417
2023-01-24 07:46:01.964670: step: 324/529, loss: 0.0012562504271045327
2023-01-24 07:46:03.083798: step: 328/529, loss: 0.004226832650601864
2023-01-24 07:46:04.204585: step: 332/529, loss: 0.0089768311008811
2023-01-24 07:46:05.301164: step: 336/529, loss: 0.008501342497766018
2023-01-24 07:46:06.434797: step: 340/529, loss: 0.006809744518250227
2023-01-24 07:46:07.563150: step: 344/529, loss: 0.02093273214995861
2023-01-24 07:46:08.670882: step: 348/529, loss: 0.004513650666922331
2023-01-24 07:46:09.774966: step: 352/529, loss: 0.047725610435009
2023-01-24 07:46:10.897241: step: 356/529, loss: 0.012137938290834427
2023-01-24 07:46:12.014362: step: 360/529, loss: 0.05070371925830841
2023-01-24 07:46:13.120634: step: 364/529, loss: 0.006101368926465511
2023-01-24 07:46:14.227707: step: 368/529, loss: 0.008855664171278477
2023-01-24 07:46:15.329463: step: 372/529, loss: 0.013434840366244316
2023-01-24 07:46:16.433668: step: 376/529, loss: 0.011459002271294594
2023-01-24 07:46:17.550149: step: 380/529, loss: 0.008011535741388798
2023-01-24 07:46:18.652450: step: 384/529, loss: 0.0021826692391186953
2023-01-24 07:46:19.772362: step: 388/529, loss: 0.01060234010219574
2023-01-24 07:46:20.886362: step: 392/529, loss: 0.012082225643098354
2023-01-24 07:46:22.011459: step: 396/529, loss: 0.00652723666280508
2023-01-24 07:46:23.132023: step: 400/529, loss: 0.008234438486397266
2023-01-24 07:46:24.249646: step: 404/529, loss: 0.009681366384029388
2023-01-24 07:46:25.356200: step: 408/529, loss: 0.014691675081849098
2023-01-24 07:46:26.456697: step: 412/529, loss: 0.007199740037322044
2023-01-24 07:46:27.558169: step: 416/529, loss: 0.009227920323610306
2023-01-24 07:46:28.642876: step: 420/529, loss: 0.0388481430709362
2023-01-24 07:46:29.777094: step: 424/529, loss: 0.004231669940054417
2023-01-24 07:46:30.884143: step: 428/529, loss: 0.013324777595698833
2023-01-24 07:46:31.991178: step: 432/529, loss: 0.007496025413274765
2023-01-24 07:46:33.088289: step: 436/529, loss: 0.008432712405920029
2023-01-24 07:46:34.209915: step: 440/529, loss: 0.007808873429894447
2023-01-24 07:46:35.304653: step: 444/529, loss: 0.0038969856686890125
2023-01-24 07:46:36.441049: step: 448/529, loss: 0.004537766333669424
2023-01-24 07:46:37.572675: step: 452/529, loss: 0.009573286399245262
2023-01-24 07:46:38.656709: step: 456/529, loss: 0.0009919755393639207
2023-01-24 07:46:39.766428: step: 460/529, loss: 0.025337519124150276
2023-01-24 07:46:40.860385: step: 464/529, loss: 0.0064736115746200085
2023-01-24 07:46:41.963578: step: 468/529, loss: 0.0006390097551047802
2023-01-24 07:46:43.074223: step: 472/529, loss: 0.009323996491730213
2023-01-24 07:46:44.175584: step: 476/529, loss: 0.015452204272150993
2023-01-24 07:46:45.302266: step: 480/529, loss: 0.009421534836292267
2023-01-24 07:46:46.405775: step: 484/529, loss: 0.013899240642786026
2023-01-24 07:46:47.518989: step: 488/529, loss: 0.011518577113747597
2023-01-24 07:46:48.622191: step: 492/529, loss: 0.003829505294561386
2023-01-24 07:46:49.740866: step: 496/529, loss: 0.013258215971291065
2023-01-24 07:46:50.845632: step: 500/529, loss: 0.005263965111225843
2023-01-24 07:46:51.957636: step: 504/529, loss: 0.004052682314068079
2023-01-24 07:46:53.072393: step: 508/529, loss: 0.0056071230210363865
2023-01-24 07:46:54.219600: step: 512/529, loss: 0.004304805770516396
2023-01-24 07:46:55.328970: step: 516/529, loss: 0.0063183666206896305
2023-01-24 07:46:56.444107: step: 520/529, loss: 0.002637613797560334
2023-01-24 07:46:57.565736: step: 524/529, loss: 0.059482354670763016
2023-01-24 07:46:58.669242: step: 528/529, loss: 0.006300800479948521
2023-01-24 07:46:59.783465: step: 532/529, loss: 0.007320732809603214
2023-01-24 07:47:00.864430: step: 536/529, loss: 0.005531124770641327
2023-01-24 07:47:01.996252: step: 540/529, loss: 0.0034939455799758434
2023-01-24 07:47:03.116183: step: 544/529, loss: 0.015622791834175587
2023-01-24 07:47:04.209854: step: 548/529, loss: 0.005549120716750622
2023-01-24 07:47:05.296936: step: 552/529, loss: 0.016137877479195595
2023-01-24 07:47:06.396570: step: 556/529, loss: 0.0037536765448749065
2023-01-24 07:47:07.493910: step: 560/529, loss: 0.045435480773448944
2023-01-24 07:47:08.592194: step: 564/529, loss: 0.0032697119750082493
2023-01-24 07:47:09.700112: step: 568/529, loss: 0.0029958945233374834
2023-01-24 07:47:10.823212: step: 572/529, loss: 0.006128557026386261
2023-01-24 07:47:11.962665: step: 576/529, loss: 0.01146414503455162
2023-01-24 07:47:13.075430: step: 580/529, loss: 0.011514389887452126
2023-01-24 07:47:14.194982: step: 584/529, loss: 0.010104053653776646
2023-01-24 07:47:15.291804: step: 588/529, loss: 0.0045713214203715324
2023-01-24 07:47:16.403640: step: 592/529, loss: 0.0031343260779976845
2023-01-24 07:47:17.497894: step: 596/529, loss: 0.0013217005180194974
2023-01-24 07:47:18.607051: step: 600/529, loss: 0.0084649957716465
2023-01-24 07:47:19.721499: step: 604/529, loss: 0.002616363810375333
2023-01-24 07:47:20.826985: step: 608/529, loss: 0.006268291734158993
2023-01-24 07:47:21.937157: step: 612/529, loss: 0.01747487485408783
2023-01-24 07:47:23.041354: step: 616/529, loss: 0.003503649728372693
2023-01-24 07:47:24.142627: step: 620/529, loss: 0.008101007901132107
2023-01-24 07:47:25.243960: step: 624/529, loss: 0.004939237143844366
2023-01-24 07:47:26.331398: step: 628/529, loss: 0.0021369410678744316
2023-01-24 07:47:27.430385: step: 632/529, loss: 0.011247859336435795
2023-01-24 07:47:28.551120: step: 636/529, loss: 0.0004374111595097929
2023-01-24 07:47:29.690386: step: 640/529, loss: 0.010549647733569145
2023-01-24 07:47:30.792470: step: 644/529, loss: 0.015212802216410637
2023-01-24 07:47:31.928703: step: 648/529, loss: 0.006264748051762581
2023-01-24 07:47:33.049241: step: 652/529, loss: 0.02324860729277134
2023-01-24 07:47:34.153036: step: 656/529, loss: 0.038062259554862976
2023-01-24 07:47:35.269996: step: 660/529, loss: 0.0011836693156510592
2023-01-24 07:47:36.397332: step: 664/529, loss: 0.024853048846125603
2023-01-24 07:47:37.499180: step: 668/529, loss: 0.005200129467993975
2023-01-24 07:47:38.610030: step: 672/529, loss: 0.034896500408649445
2023-01-24 07:47:39.710702: step: 676/529, loss: 0.007174786180257797
2023-01-24 07:47:40.814450: step: 680/529, loss: 0.010199270211160183
2023-01-24 07:47:41.919546: step: 684/529, loss: 0.01871129311621189
2023-01-24 07:47:43.026993: step: 688/529, loss: 0.003652912098914385
2023-01-24 07:47:44.139242: step: 692/529, loss: 0.002312375232577324
2023-01-24 07:47:45.247936: step: 696/529, loss: 0.004668534733355045
2023-01-24 07:47:46.371203: step: 700/529, loss: 0.004981716629117727
2023-01-24 07:47:47.470121: step: 704/529, loss: 0.005026285070925951
2023-01-24 07:47:48.572519: step: 708/529, loss: 0.009788201190531254
2023-01-24 07:47:49.715380: step: 712/529, loss: 0.00438581220805645
2023-01-24 07:47:50.826939: step: 716/529, loss: 0.011837158352136612
2023-01-24 07:47:51.934844: step: 720/529, loss: 0.007928390987217426
2023-01-24 07:47:53.064405: step: 724/529, loss: 0.00782644934952259
2023-01-24 07:47:54.164075: step: 728/529, loss: 0.002891362411901355
2023-01-24 07:47:55.265306: step: 732/529, loss: 0.006322226021438837
2023-01-24 07:47:56.373606: step: 736/529, loss: 0.009860877878963947
2023-01-24 07:47:57.494573: step: 740/529, loss: 0.006312456447631121
2023-01-24 07:47:58.615164: step: 744/529, loss: 0.00543206324800849
2023-01-24 07:47:59.716148: step: 748/529, loss: 0.006809452082961798
2023-01-24 07:48:00.810856: step: 752/529, loss: 0.0028538559563457966
2023-01-24 07:48:01.954328: step: 756/529, loss: 0.046533554792404175
2023-01-24 07:48:03.065960: step: 760/529, loss: 0.025042230263352394
2023-01-24 07:48:04.176078: step: 764/529, loss: 0.00444047013297677
2023-01-24 07:48:05.279353: step: 768/529, loss: 0.061612099409103394
2023-01-24 07:48:06.396232: step: 772/529, loss: 0.03046591766178608
2023-01-24 07:48:07.532714: step: 776/529, loss: 0.010338617488741875
2023-01-24 07:48:08.663841: step: 780/529, loss: 0.0014948428142815828
2023-01-24 07:48:09.764979: step: 784/529, loss: 0.01369453314691782
2023-01-24 07:48:10.885442: step: 788/529, loss: 0.015225487761199474
2023-01-24 07:48:11.997780: step: 792/529, loss: 0.013376264832913876
2023-01-24 07:48:13.129977: step: 796/529, loss: 0.00604973454028368
2023-01-24 07:48:14.259908: step: 800/529, loss: 0.00472157122567296
2023-01-24 07:48:15.350582: step: 804/529, loss: 0.006451881490647793
2023-01-24 07:48:16.455188: step: 808/529, loss: 0.005709907505661249
2023-01-24 07:48:17.564575: step: 812/529, loss: 0.018158137798309326
2023-01-24 07:48:18.653988: step: 816/529, loss: 0.011198919266462326
2023-01-24 07:48:19.763851: step: 820/529, loss: 0.004058819729834795
2023-01-24 07:48:20.881188: step: 824/529, loss: 0.004995932802557945
2023-01-24 07:48:22.009662: step: 828/529, loss: 0.009096013382077217
2023-01-24 07:48:23.107794: step: 832/529, loss: 0.007504155859351158
2023-01-24 07:48:24.216898: step: 836/529, loss: 0.025504272431135178
2023-01-24 07:48:25.336684: step: 840/529, loss: 0.09928291290998459
2023-01-24 07:48:26.421002: step: 844/529, loss: 0.007400807924568653
2023-01-24 07:48:27.550564: step: 848/529, loss: 0.006773261819034815
2023-01-24 07:48:28.666179: step: 852/529, loss: 0.003998809959739447
2023-01-24 07:48:29.777505: step: 856/529, loss: 0.015541048720479012
2023-01-24 07:48:30.893455: step: 860/529, loss: 0.007549144793301821
2023-01-24 07:48:32.004905: step: 864/529, loss: 0.008947948925197124
2023-01-24 07:48:33.094724: step: 868/529, loss: 0.005314873997122049
2023-01-24 07:48:34.193886: step: 872/529, loss: 0.00538831390440464
2023-01-24 07:48:35.313485: step: 876/529, loss: 0.007756073493510485
2023-01-24 07:48:36.422281: step: 880/529, loss: 0.009078223258256912
2023-01-24 07:48:37.538832: step: 884/529, loss: 0.0029895331244915724
2023-01-24 07:48:38.636645: step: 888/529, loss: 0.008503108285367489
2023-01-24 07:48:39.761985: step: 892/529, loss: 0.022897157818078995
2023-01-24 07:48:40.847370: step: 896/529, loss: 0.004998879972845316
2023-01-24 07:48:41.953470: step: 900/529, loss: 0.0013441942865028977
2023-01-24 07:48:43.062916: step: 904/529, loss: 0.004468087572604418
2023-01-24 07:48:44.196071: step: 908/529, loss: 0.026423035189509392
2023-01-24 07:48:45.310182: step: 912/529, loss: 0.02764108218252659
2023-01-24 07:48:46.406255: step: 916/529, loss: 0.005134744103997946
2023-01-24 07:48:47.539072: step: 920/529, loss: 0.013258428312838078
2023-01-24 07:48:48.659883: step: 924/529, loss: 0.027975497767329216
2023-01-24 07:48:49.782683: step: 928/529, loss: 0.007095934823155403
2023-01-24 07:48:50.892535: step: 932/529, loss: 0.03519057482481003
2023-01-24 07:48:52.027761: step: 936/529, loss: 0.009730612859129906
2023-01-24 07:48:53.136918: step: 940/529, loss: 0.007331518922001123
2023-01-24 07:48:54.240417: step: 944/529, loss: 0.011907260864973068
2023-01-24 07:48:55.370742: step: 948/529, loss: 0.01262362115085125
2023-01-24 07:48:56.467304: step: 952/529, loss: 0.018554141744971275
2023-01-24 07:48:57.573464: step: 956/529, loss: 0.00550667941570282
2023-01-24 07:48:58.714366: step: 960/529, loss: 0.003585243131965399
2023-01-24 07:48:59.838848: step: 964/529, loss: 0.005864799953997135
2023-01-24 07:49:00.955917: step: 968/529, loss: 0.025149207562208176
2023-01-24 07:49:02.089877: step: 972/529, loss: 0.02100159041583538
2023-01-24 07:49:03.215373: step: 976/529, loss: 0.019026894122362137
2023-01-24 07:49:04.339552: step: 980/529, loss: 0.008776872418820858
2023-01-24 07:49:05.452021: step: 984/529, loss: 0.013381061144173145
2023-01-24 07:49:06.577310: step: 988/529, loss: 0.06794261187314987
2023-01-24 07:49:07.671195: step: 992/529, loss: 0.01260827761143446
2023-01-24 07:49:08.765210: step: 996/529, loss: 0.023017434403300285
2023-01-24 07:49:09.873161: step: 1000/529, loss: 0.012222422286868095
2023-01-24 07:49:10.988388: step: 1004/529, loss: 0.016505379229784012
2023-01-24 07:49:12.094750: step: 1008/529, loss: 0.006892653647810221
2023-01-24 07:49:13.198111: step: 1012/529, loss: 0.00251356465741992
2023-01-24 07:49:14.302430: step: 1016/529, loss: 0.004167493432760239
2023-01-24 07:49:15.429589: step: 1020/529, loss: 0.0063850898295640945
2023-01-24 07:49:16.557081: step: 1024/529, loss: 0.007139180321246386
2023-01-24 07:49:17.671762: step: 1028/529, loss: 0.017031438648700714
2023-01-24 07:49:18.776246: step: 1032/529, loss: 0.014146663248538971
2023-01-24 07:49:19.914410: step: 1036/529, loss: 0.008736012503504753
2023-01-24 07:49:21.031015: step: 1040/529, loss: 0.007704694755375385
2023-01-24 07:49:22.134839: step: 1044/529, loss: 0.004681042395532131
2023-01-24 07:49:23.238553: step: 1048/529, loss: 0.021567480638623238
2023-01-24 07:49:24.346308: step: 1052/529, loss: 0.007028264459222555
2023-01-24 07:49:25.453447: step: 1056/529, loss: 0.011092476546764374
2023-01-24 07:49:26.562770: step: 1060/529, loss: 0.0042023384012281895
2023-01-24 07:49:27.671278: step: 1064/529, loss: 0.0019346660701557994
2023-01-24 07:49:28.759508: step: 1068/529, loss: 0.008626299910247326
2023-01-24 07:49:29.878704: step: 1072/529, loss: 0.016826190054416656
2023-01-24 07:49:30.975859: step: 1076/529, loss: 0.0037418168503791094
2023-01-24 07:49:32.120268: step: 1080/529, loss: 0.005875915288925171
2023-01-24 07:49:33.230329: step: 1084/529, loss: 0.01041338685899973
2023-01-24 07:49:34.353824: step: 1088/529, loss: 0.014791525900363922
2023-01-24 07:49:35.478018: step: 1092/529, loss: 0.010074746794998646
2023-01-24 07:49:36.597537: step: 1096/529, loss: 0.019177494570612907
2023-01-24 07:49:37.710812: step: 1100/529, loss: 0.0068747433833777905
2023-01-24 07:49:38.846989: step: 1104/529, loss: 0.012249616906046867
2023-01-24 07:49:39.967629: step: 1108/529, loss: 0.033043939620256424
2023-01-24 07:49:41.056906: step: 1112/529, loss: 0.010264253243803978
2023-01-24 07:49:42.165558: step: 1116/529, loss: 0.012172569520771503
2023-01-24 07:49:43.274556: step: 1120/529, loss: 0.0053809951059520245
2023-01-24 07:49:44.385791: step: 1124/529, loss: 0.01343944389373064
2023-01-24 07:49:45.535040: step: 1128/529, loss: 0.0034981858916580677
2023-01-24 07:49:46.640686: step: 1132/529, loss: 0.010491401888430119
2023-01-24 07:49:47.785270: step: 1136/529, loss: 0.008148564957082272
2023-01-24 07:49:48.919634: step: 1140/529, loss: 0.07247122377157211
2023-01-24 07:49:50.021506: step: 1144/529, loss: 0.08388296514749527
2023-01-24 07:49:51.134429: step: 1148/529, loss: 0.0010937309125438333
2023-01-24 07:49:52.261716: step: 1152/529, loss: 0.008527462370693684
2023-01-24 07:49:53.389013: step: 1156/529, loss: 0.008171889930963516
2023-01-24 07:49:54.514180: step: 1160/529, loss: 0.029753003269433975
2023-01-24 07:49:55.628872: step: 1164/529, loss: 0.03420832380652428
2023-01-24 07:49:56.749422: step: 1168/529, loss: 0.00933653861284256
2023-01-24 07:49:57.863897: step: 1172/529, loss: 0.008758390322327614
2023-01-24 07:49:59.000986: step: 1176/529, loss: 0.026053432375192642
2023-01-24 07:50:00.104417: step: 1180/529, loss: 0.004718575160950422
2023-01-24 07:50:01.222439: step: 1184/529, loss: 0.0029533659107983112
2023-01-24 07:50:02.365385: step: 1188/529, loss: 0.01955961436033249
2023-01-24 07:50:03.469880: step: 1192/529, loss: 0.006807827390730381
2023-01-24 07:50:04.600787: step: 1196/529, loss: 0.004869374912232161
2023-01-24 07:50:05.699434: step: 1200/529, loss: 0.008376733399927616
2023-01-24 07:50:06.823955: step: 1204/529, loss: 0.02058805711567402
2023-01-24 07:50:07.918438: step: 1208/529, loss: 0.008160156197845936
2023-01-24 07:50:09.054645: step: 1212/529, loss: 0.027654292061924934
2023-01-24 07:50:10.146809: step: 1216/529, loss: 0.04118898883461952
2023-01-24 07:50:11.261271: step: 1220/529, loss: 0.05720268562436104
2023-01-24 07:50:12.392351: step: 1224/529, loss: 0.021895918995141983
2023-01-24 07:50:13.497995: step: 1228/529, loss: 0.017520206049084663
2023-01-24 07:50:14.620846: step: 1232/529, loss: 0.005347408354282379
2023-01-24 07:50:15.713883: step: 1236/529, loss: 0.004857045132666826
2023-01-24 07:50:16.804133: step: 1240/529, loss: 0.0069295079447329044
2023-01-24 07:50:17.920154: step: 1244/529, loss: 0.008177652023732662
2023-01-24 07:50:19.018937: step: 1248/529, loss: 0.006703739985823631
2023-01-24 07:50:20.103481: step: 1252/529, loss: 0.006869058590382338
2023-01-24 07:50:21.213498: step: 1256/529, loss: 0.0031312317587435246
2023-01-24 07:50:22.314521: step: 1260/529, loss: 0.013160737231373787
2023-01-24 07:50:23.422700: step: 1264/529, loss: 0.014743266627192497
2023-01-24 07:50:24.552064: step: 1268/529, loss: 0.006623721681535244
2023-01-24 07:50:25.670447: step: 1272/529, loss: 0.004435283597558737
2023-01-24 07:50:26.776594: step: 1276/529, loss: 0.012515711598098278
2023-01-24 07:50:27.870832: step: 1280/529, loss: 0.006792957428842783
2023-01-24 07:50:28.986052: step: 1284/529, loss: 0.00042178278090432286
2023-01-24 07:50:30.111460: step: 1288/529, loss: 0.0008767183753661811
2023-01-24 07:50:31.230457: step: 1292/529, loss: 0.0032390186097472906
2023-01-24 07:50:32.355492: step: 1296/529, loss: 0.007119619753211737
2023-01-24 07:50:33.472292: step: 1300/529, loss: 0.013750935904681683
2023-01-24 07:50:34.606692: step: 1304/529, loss: 0.01803460158407688
2023-01-24 07:50:35.700126: step: 1308/529, loss: 0.0052917650900781155
2023-01-24 07:50:36.794129: step: 1312/529, loss: 0.0075826882384717464
2023-01-24 07:50:37.938132: step: 1316/529, loss: 0.000660874240566045
2023-01-24 07:50:39.043242: step: 1320/529, loss: 0.008228098042309284
2023-01-24 07:50:40.148284: step: 1324/529, loss: 0.0008065270376391709
2023-01-24 07:50:41.251148: step: 1328/529, loss: 0.002440697979182005
2023-01-24 07:50:42.360242: step: 1332/529, loss: 0.03231841325759888
2023-01-24 07:50:43.485181: step: 1336/529, loss: 0.0051038372330367565
2023-01-24 07:50:44.572123: step: 1340/529, loss: 0.014039299450814724
2023-01-24 07:50:45.667802: step: 1344/529, loss: 0.004389962647110224
2023-01-24 07:50:46.781033: step: 1348/529, loss: 0.04818470776081085
2023-01-24 07:50:47.883468: step: 1352/529, loss: 0.024557804688811302
2023-01-24 07:50:48.971333: step: 1356/529, loss: 0.0022025639191269875
2023-01-24 07:50:50.092430: step: 1360/529, loss: 0.005134823266416788
2023-01-24 07:50:51.195792: step: 1364/529, loss: 0.002588310744613409
2023-01-24 07:50:52.299831: step: 1368/529, loss: 0.008885812014341354
2023-01-24 07:50:53.412351: step: 1372/529, loss: 0.012739752419292927
2023-01-24 07:50:54.529109: step: 1376/529, loss: 0.013755069114267826
2023-01-24 07:50:55.643712: step: 1380/529, loss: 0.005059142131358385
2023-01-24 07:50:56.759742: step: 1384/529, loss: 0.011433500796556473
2023-01-24 07:50:57.867776: step: 1388/529, loss: 0.016240177676081657
2023-01-24 07:50:58.986385: step: 1392/529, loss: 0.005287688225507736
2023-01-24 07:51:00.089184: step: 1396/529, loss: 0.011790314689278603
2023-01-24 07:51:01.208125: step: 1400/529, loss: 0.008412167429924011
2023-01-24 07:51:02.352538: step: 1404/529, loss: 0.02273290604352951
2023-01-24 07:51:03.459795: step: 1408/529, loss: 0.011153369210660458
2023-01-24 07:51:04.563091: step: 1412/529, loss: 0.0152726536616683
2023-01-24 07:51:05.640479: step: 1416/529, loss: 0.017236515879631042
2023-01-24 07:51:06.754912: step: 1420/529, loss: 0.04717542231082916
2023-01-24 07:51:07.862027: step: 1424/529, loss: 0.00706536415964365
2023-01-24 07:51:08.963348: step: 1428/529, loss: 0.02329491265118122
2023-01-24 07:51:10.073718: step: 1432/529, loss: 0.061748966574668884
2023-01-24 07:51:11.205279: step: 1436/529, loss: 0.0029622793663293123
2023-01-24 07:51:12.302123: step: 1440/529, loss: 0.007936941459774971
2023-01-24 07:51:13.424579: step: 1444/529, loss: 0.009801620617508888
2023-01-24 07:51:14.518199: step: 1448/529, loss: 0.0049109929241240025
2023-01-24 07:51:15.625430: step: 1452/529, loss: 0.00910202506929636
2023-01-24 07:51:16.745681: step: 1456/529, loss: 0.058633070439100266
2023-01-24 07:51:17.849251: step: 1460/529, loss: 0.04007187858223915
2023-01-24 07:51:18.977866: step: 1464/529, loss: 0.02339683473110199
2023-01-24 07:51:20.090076: step: 1468/529, loss: 0.00334138423204422
2023-01-24 07:51:21.200819: step: 1472/529, loss: 0.019261814653873444
2023-01-24 07:51:22.345106: step: 1476/529, loss: 0.014432044699788094
2023-01-24 07:51:23.440341: step: 1480/529, loss: 0.007782378233969212
2023-01-24 07:51:24.546641: step: 1484/529, loss: 0.03022390976548195
2023-01-24 07:51:25.663086: step: 1488/529, loss: 0.05246228724718094
2023-01-24 07:51:26.775525: step: 1492/529, loss: 0.004392694216221571
2023-01-24 07:51:27.859653: step: 1496/529, loss: 0.02190680056810379
2023-01-24 07:51:28.965326: step: 1500/529, loss: 0.0034517559688538313
2023-01-24 07:51:30.086034: step: 1504/529, loss: 0.027647580951452255
2023-01-24 07:51:31.213149: step: 1508/529, loss: 0.009321940131485462
2023-01-24 07:51:32.350731: step: 1512/529, loss: 0.0009504520567134023
2023-01-24 07:51:33.494099: step: 1516/529, loss: 0.009871454909443855
2023-01-24 07:51:34.602647: step: 1520/529, loss: 0.005512171890586615
2023-01-24 07:51:35.711000: step: 1524/529, loss: 0.008579273708164692
2023-01-24 07:51:36.816030: step: 1528/529, loss: 0.0034248565789312124
2023-01-24 07:51:37.943111: step: 1532/529, loss: 0.01708158291876316
2023-01-24 07:51:39.050026: step: 1536/529, loss: 0.007246970199048519
2023-01-24 07:51:40.144418: step: 1540/529, loss: 0.04061109572649002
2023-01-24 07:51:41.261001: step: 1544/529, loss: 0.023712685331702232
2023-01-24 07:51:42.383339: step: 1548/529, loss: 0.004205163102596998
2023-01-24 07:51:43.506202: step: 1552/529, loss: 0.003635575994849205
2023-01-24 07:51:44.615037: step: 1556/529, loss: 0.010479738935828209
2023-01-24 07:51:45.732308: step: 1560/529, loss: 0.007649003528058529
2023-01-24 07:51:46.830079: step: 1564/529, loss: 0.0029864495154470205
2023-01-24 07:51:47.982462: step: 1568/529, loss: 0.006535951513797045
2023-01-24 07:51:49.094887: step: 1572/529, loss: 0.032627858221530914
2023-01-24 07:51:50.218423: step: 1576/529, loss: 0.012394534423947334
2023-01-24 07:51:51.336988: step: 1580/529, loss: 0.003876542439684272
2023-01-24 07:51:52.437701: step: 1584/529, loss: 0.005604331381618977
2023-01-24 07:51:53.538671: step: 1588/529, loss: 0.008362029679119587
2023-01-24 07:51:54.624813: step: 1592/529, loss: 0.0012405200395733118
2023-01-24 07:51:55.736962: step: 1596/529, loss: 0.0321798212826252
2023-01-24 07:51:56.833850: step: 1600/529, loss: 0.0382835790514946
2023-01-24 07:51:57.942492: step: 1604/529, loss: 0.007573469076305628
2023-01-24 07:51:59.051602: step: 1608/529, loss: 0.0048532807268202305
2023-01-24 07:52:00.166526: step: 1612/529, loss: 0.008612043224275112
2023-01-24 07:52:01.272000: step: 1616/529, loss: 0.004876828286796808
2023-01-24 07:52:02.361146: step: 1620/529, loss: 0.00716797448694706
2023-01-24 07:52:03.487300: step: 1624/529, loss: 0.01805017702281475
2023-01-24 07:52:04.602414: step: 1628/529, loss: 0.00673112366348505
2023-01-24 07:52:05.714459: step: 1632/529, loss: 0.010313460603356361
2023-01-24 07:52:06.829380: step: 1636/529, loss: 0.006847405340522528
2023-01-24 07:52:07.953731: step: 1640/529, loss: 0.007045113481581211
2023-01-24 07:52:09.076536: step: 1644/529, loss: 0.0062449024990201
2023-01-24 07:52:10.205671: step: 1648/529, loss: 0.006150367669761181
2023-01-24 07:52:11.311677: step: 1652/529, loss: 0.0369860902428627
2023-01-24 07:52:12.408626: step: 1656/529, loss: 0.009792941622436047
2023-01-24 07:52:13.514729: step: 1660/529, loss: 0.002108693588525057
2023-01-24 07:52:14.627403: step: 1664/529, loss: 0.0040407944470644
2023-01-24 07:52:15.737425: step: 1668/529, loss: 0.0072971126064658165
2023-01-24 07:52:16.853392: step: 1672/529, loss: 0.006971732713282108
2023-01-24 07:52:17.957864: step: 1676/529, loss: 0.004379850812256336
2023-01-24 07:52:19.065696: step: 1680/529, loss: 0.04694787412881851
2023-01-24 07:52:20.163071: step: 1684/529, loss: 0.017130527645349503
2023-01-24 07:52:21.291855: step: 1688/529, loss: 0.022409014403820038
2023-01-24 07:52:22.405803: step: 1692/529, loss: 0.00207091448828578
2023-01-24 07:52:23.512454: step: 1696/529, loss: 0.003941686823964119
2023-01-24 07:52:24.629147: step: 1700/529, loss: 0.008076979778707027
2023-01-24 07:52:25.719407: step: 1704/529, loss: 0.005978000350296497
2023-01-24 07:52:26.803326: step: 1708/529, loss: 0.009553679265081882
2023-01-24 07:52:27.904106: step: 1712/529, loss: 0.0050934068858623505
2023-01-24 07:52:29.020416: step: 1716/529, loss: 0.02730417251586914
2023-01-24 07:52:30.136929: step: 1720/529, loss: 0.02408521994948387
2023-01-24 07:52:31.274030: step: 1724/529, loss: 0.02619338408112526
2023-01-24 07:52:32.388372: step: 1728/529, loss: 0.00833680760115385
2023-01-24 07:52:33.482590: step: 1732/529, loss: 0.06240164116024971
2023-01-24 07:52:34.600853: step: 1736/529, loss: 0.006684586405754089
2023-01-24 07:52:35.736685: step: 1740/529, loss: 0.017560744658112526
2023-01-24 07:52:36.836666: step: 1744/529, loss: 0.030718432739377022
2023-01-24 07:52:37.964172: step: 1748/529, loss: 0.00947144441306591
2023-01-24 07:52:39.053771: step: 1752/529, loss: 0.004039314109832048
2023-01-24 07:52:40.160331: step: 1756/529, loss: 0.00732135446742177
2023-01-24 07:52:41.287457: step: 1760/529, loss: 0.005373631604015827
2023-01-24 07:52:42.423744: step: 1764/529, loss: 0.028778599575161934
2023-01-24 07:52:43.513415: step: 1768/529, loss: 0.03334533050656319
2023-01-24 07:52:44.615680: step: 1772/529, loss: 0.05198327824473381
2023-01-24 07:52:45.707478: step: 1776/529, loss: 0.014782276935875416
2023-01-24 07:52:46.805574: step: 1780/529, loss: 0.014527741819620132
2023-01-24 07:52:47.916872: step: 1784/529, loss: 0.003307939739897847
2023-01-24 07:52:49.044712: step: 1788/529, loss: 0.002842556219547987
2023-01-24 07:52:50.157379: step: 1792/529, loss: 0.04601949453353882
2023-01-24 07:52:51.254324: step: 1796/529, loss: 0.004989521577954292
2023-01-24 07:52:52.352333: step: 1800/529, loss: 0.001036455505527556
2023-01-24 07:52:53.436566: step: 1804/529, loss: 0.005468796472996473
2023-01-24 07:52:54.522538: step: 1808/529, loss: 0.007337305229157209
2023-01-24 07:52:55.617701: step: 1812/529, loss: 0.0070394789800047874
2023-01-24 07:52:56.723673: step: 1816/529, loss: 0.02285398729145527
2023-01-24 07:52:57.829575: step: 1820/529, loss: 0.006979189347475767
2023-01-24 07:52:58.961592: step: 1824/529, loss: 0.0027024359442293644
2023-01-24 07:53:00.076554: step: 1828/529, loss: 0.005601800978183746
2023-01-24 07:53:01.175453: step: 1832/529, loss: 0.003892092499881983
2023-01-24 07:53:02.283065: step: 1836/529, loss: 0.003860777011141181
2023-01-24 07:53:03.392955: step: 1840/529, loss: 0.011268729344010353
2023-01-24 07:53:04.493517: step: 1844/529, loss: 0.0013628269080072641
2023-01-24 07:53:05.608645: step: 1848/529, loss: 0.003899089526385069
2023-01-24 07:53:06.721977: step: 1852/529, loss: 0.017781587317585945
2023-01-24 07:53:07.822674: step: 1856/529, loss: 0.0024549432564526796
2023-01-24 07:53:08.939938: step: 1860/529, loss: 0.0070040058344602585
2023-01-24 07:53:10.070505: step: 1864/529, loss: 0.01735086180269718
2023-01-24 07:53:11.180006: step: 1868/529, loss: 0.010106250643730164
2023-01-24 07:53:12.296531: step: 1872/529, loss: 0.009298549965023994
2023-01-24 07:53:13.396557: step: 1876/529, loss: 0.004831044003367424
2023-01-24 07:53:14.520568: step: 1880/529, loss: 0.0043725017458200455
2023-01-24 07:53:15.622746: step: 1884/529, loss: 0.004446262493729591
2023-01-24 07:53:16.741460: step: 1888/529, loss: 0.011983290314674377
2023-01-24 07:53:17.824341: step: 1892/529, loss: 0.026223337277770042
2023-01-24 07:53:18.945917: step: 1896/529, loss: 0.010880104266107082
2023-01-24 07:53:20.066247: step: 1900/529, loss: 0.010207395069301128
2023-01-24 07:53:21.180048: step: 1904/529, loss: 0.010739650577306747
2023-01-24 07:53:22.339235: step: 1908/529, loss: 0.006706821732223034
2023-01-24 07:53:23.465709: step: 1912/529, loss: 0.03068714588880539
2023-01-24 07:53:24.580144: step: 1916/529, loss: 0.020680204033851624
2023-01-24 07:53:25.670808: step: 1920/529, loss: 0.004508965648710728
2023-01-24 07:53:26.773339: step: 1924/529, loss: 0.011241476982831955
2023-01-24 07:53:27.874330: step: 1928/529, loss: 0.01198605727404356
2023-01-24 07:53:28.971852: step: 1932/529, loss: 0.005279011093080044
2023-01-24 07:53:30.084962: step: 1936/529, loss: 0.0047566844150424
2023-01-24 07:53:31.201149: step: 1940/529, loss: 0.0025826264172792435
2023-01-24 07:53:32.308126: step: 1944/529, loss: 0.02051517367362976
2023-01-24 07:53:33.423810: step: 1948/529, loss: 0.020873727276921272
2023-01-24 07:53:34.546377: step: 1952/529, loss: 0.010530680418014526
2023-01-24 07:53:35.655952: step: 1956/529, loss: 0.008664194494485855
2023-01-24 07:53:36.752134: step: 1960/529, loss: 0.003982482943683863
2023-01-24 07:53:37.874967: step: 1964/529, loss: 0.0030286768451333046
2023-01-24 07:53:38.979741: step: 1968/529, loss: 0.004773780237883329
2023-01-24 07:53:40.098083: step: 1972/529, loss: 0.028166964650154114
2023-01-24 07:53:41.206211: step: 1976/529, loss: 0.005442872177809477
2023-01-24 07:53:42.334814: step: 1980/529, loss: 0.014951172284781933
2023-01-24 07:53:43.453653: step: 1984/529, loss: 0.012404645793139935
2023-01-24 07:53:44.567780: step: 1988/529, loss: 0.002578714629635215
2023-01-24 07:53:45.680973: step: 1992/529, loss: 0.015002608299255371
2023-01-24 07:53:46.776361: step: 1996/529, loss: 0.04005063325166702
2023-01-24 07:53:47.877263: step: 2000/529, loss: 0.026735400781035423
2023-01-24 07:53:48.982257: step: 2004/529, loss: 0.002559252083301544
2023-01-24 07:53:50.075586: step: 2008/529, loss: 0.00400884822010994
2023-01-24 07:53:51.181496: step: 2012/529, loss: 0.004970897920429707
2023-01-24 07:53:52.275841: step: 2016/529, loss: 0.004061634186655283
2023-01-24 07:53:53.393582: step: 2020/529, loss: 0.025842580944299698
2023-01-24 07:53:54.522206: step: 2024/529, loss: 0.017473995685577393
2023-01-24 07:53:55.640315: step: 2028/529, loss: 0.006059217732399702
2023-01-24 07:53:56.740152: step: 2032/529, loss: 0.001296793925575912
2023-01-24 07:53:57.833606: step: 2036/529, loss: 0.010043682530522346
2023-01-24 07:53:58.970234: step: 2040/529, loss: 0.04651513323187828
2023-01-24 07:54:00.063279: step: 2044/529, loss: 0.014005985110998154
2023-01-24 07:54:01.180963: step: 2048/529, loss: 0.025531034916639328
2023-01-24 07:54:02.300669: step: 2052/529, loss: 0.007653862237930298
2023-01-24 07:54:03.427015: step: 2056/529, loss: 0.00987324956804514
2023-01-24 07:54:04.543085: step: 2060/529, loss: 0.007379939779639244
2023-01-24 07:54:05.668171: step: 2064/529, loss: 0.045019522309303284
2023-01-24 07:54:06.764549: step: 2068/529, loss: 0.013427437283098698
2023-01-24 07:54:07.885461: step: 2072/529, loss: 0.0011129326885566115
2023-01-24 07:54:09.041719: step: 2076/529, loss: 0.008066978305578232
2023-01-24 07:54:10.144106: step: 2080/529, loss: 0.002326990244910121
2023-01-24 07:54:11.256299: step: 2084/529, loss: 0.021870005875825882
2023-01-24 07:54:12.361015: step: 2088/529, loss: 0.005908648017793894
2023-01-24 07:54:13.456212: step: 2092/529, loss: 0.014179644174873829
2023-01-24 07:54:14.594542: step: 2096/529, loss: 0.002904726890847087
2023-01-24 07:54:15.704225: step: 2100/529, loss: 0.013198090717196465
2023-01-24 07:54:16.840585: step: 2104/529, loss: 0.003708828240633011
2023-01-24 07:54:17.964403: step: 2108/529, loss: 0.002924456726759672
2023-01-24 07:54:19.062617: step: 2112/529, loss: 0.0072814770974218845
2023-01-24 07:54:20.179532: step: 2116/529, loss: 0.004571731202304363
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37817438369152967, 'r': 0.32435449986446185, 'f1': 0.3492029038377352}, 'combined': 0.2573074028278049, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.40103037128054736, 'r': 0.28679747764305813, 'f1': 0.3344281541420819}, 'combined': 0.20555096303366985, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40476718403547673, 'r': 0.3463946869070209, 'f1': 0.37331288343558283}, 'combined': 0.2750726509525347, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.40190690979333843, 'r': 0.2859320389430943, 'f1': 0.33414235234463885}, 'combined': 0.20638204115404168, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 2}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4087527352297593, 'r': 0.35445920303605316, 'f1': 0.3796747967479675}, 'combined': 0.27976037655113395, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3935884290148207, 'r': 0.2837656611268032, 'f1': 0.3297739908764661}, 'combined': 0.20368393554134676, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:56:51.158943: step: 4/529, loss: 0.0059234509244561195
2023-01-24 07:56:52.284315: step: 8/529, loss: 0.047783784568309784
2023-01-24 07:56:53.390828: step: 12/529, loss: 0.004723140504211187
2023-01-24 07:56:54.477587: step: 16/529, loss: 0.00337740289978683
2023-01-24 07:56:55.562591: step: 20/529, loss: 0.00963030755519867
2023-01-24 07:56:56.667248: step: 24/529, loss: 0.010311869904398918
2023-01-24 07:56:57.753259: step: 28/529, loss: 0.002681407844647765
2023-01-24 07:56:58.876777: step: 32/529, loss: 0.0065170335583388805
2023-01-24 07:56:59.982050: step: 36/529, loss: 0.06748323887586594
2023-01-24 07:57:01.102180: step: 40/529, loss: 0.004744097124785185
2023-01-24 07:57:02.215646: step: 44/529, loss: 0.006203114055097103
2023-01-24 07:57:03.310809: step: 48/529, loss: 0.029021665453910828
2023-01-24 07:57:04.403627: step: 52/529, loss: 0.007526801899075508
2023-01-24 07:57:05.522737: step: 56/529, loss: 0.009098030626773834
2023-01-24 07:57:06.632911: step: 60/529, loss: 0.006834360305219889
2023-01-24 07:57:07.772304: step: 64/529, loss: 0.003728195559233427
2023-01-24 07:57:08.868444: step: 68/529, loss: 0.04285121709108353
2023-01-24 07:57:09.976980: step: 72/529, loss: 0.010816344991326332
2023-01-24 07:57:11.073973: step: 76/529, loss: 0.00485533382743597
2023-01-24 07:57:12.179171: step: 80/529, loss: 0.004176477901637554
2023-01-24 07:57:13.301189: step: 84/529, loss: 0.01737510971724987
2023-01-24 07:57:14.406594: step: 88/529, loss: 0.019195539876818657
2023-01-24 07:57:15.522819: step: 92/529, loss: 0.0071071540005505085
2023-01-24 07:57:16.654857: step: 96/529, loss: 0.0227601770311594
2023-01-24 07:57:17.748617: step: 100/529, loss: 0.009289607405662537
2023-01-24 07:57:18.843790: step: 104/529, loss: 0.0017559470143169165
2023-01-24 07:57:19.944693: step: 108/529, loss: 0.005618312396109104
2023-01-24 07:57:21.048536: step: 112/529, loss: 0.001144988345913589
2023-01-24 07:57:22.146671: step: 116/529, loss: 0.01226304192095995
2023-01-24 07:57:23.260189: step: 120/529, loss: 0.029561394825577736
2023-01-24 07:57:24.403004: step: 124/529, loss: 0.009273933246731758
2023-01-24 07:57:25.529696: step: 128/529, loss: 0.010077221319079399
2023-01-24 07:57:26.646719: step: 132/529, loss: 0.026895513758063316
2023-01-24 07:57:27.753749: step: 136/529, loss: 0.006875411607325077
2023-01-24 07:57:28.868172: step: 140/529, loss: 0.003585230093449354
2023-01-24 07:57:29.983549: step: 144/529, loss: 0.006437341682612896
2023-01-24 07:57:31.107687: step: 148/529, loss: 0.0018976558931171894
2023-01-24 07:57:32.231264: step: 152/529, loss: 0.007295002229511738
2023-01-24 07:57:33.334765: step: 156/529, loss: 0.008417168632149696
2023-01-24 07:57:34.446385: step: 160/529, loss: 0.009102290496230125
2023-01-24 07:57:35.571585: step: 164/529, loss: 0.035625748336315155
2023-01-24 07:57:36.678916: step: 168/529, loss: 0.004699665121734142
2023-01-24 07:57:37.801091: step: 172/529, loss: 0.0003505774075165391
2023-01-24 07:57:38.902599: step: 176/529, loss: 0.0005696056759916246
2023-01-24 07:57:40.027322: step: 180/529, loss: 0.03324306011199951
2023-01-24 07:57:41.144968: step: 184/529, loss: 0.0051491158083081245
2023-01-24 07:57:42.250459: step: 188/529, loss: 0.00684776296839118
2023-01-24 07:57:43.354464: step: 192/529, loss: 0.009571096859872341
2023-01-24 07:57:44.465154: step: 196/529, loss: 0.004485643468797207
2023-01-24 07:57:45.564077: step: 200/529, loss: 0.011714925058186054
2023-01-24 07:57:46.664002: step: 204/529, loss: 0.022249605506658554
2023-01-24 07:57:47.760996: step: 208/529, loss: 0.023388579487800598
2023-01-24 07:57:48.864509: step: 212/529, loss: 0.001695031300187111
2023-01-24 07:57:49.950521: step: 216/529, loss: 0.006146294996142387
2023-01-24 07:57:51.052461: step: 220/529, loss: 0.007970155216753483
2023-01-24 07:57:52.174001: step: 224/529, loss: 0.006544598378241062
2023-01-24 07:57:53.284333: step: 228/529, loss: 0.024190906435251236
2023-01-24 07:57:54.375314: step: 232/529, loss: 0.007148230914026499
2023-01-24 07:57:55.477345: step: 236/529, loss: 0.006680634804069996
2023-01-24 07:57:56.593088: step: 240/529, loss: 0.008441604673862457
2023-01-24 07:57:57.693201: step: 244/529, loss: 0.0035221076104789972
2023-01-24 07:57:58.789210: step: 248/529, loss: 0.002338084625080228
2023-01-24 07:57:59.915017: step: 252/529, loss: 0.0025429283268749714
2023-01-24 07:58:01.039823: step: 256/529, loss: 0.0032992931082844734
2023-01-24 07:58:02.191768: step: 260/529, loss: 0.00871511921286583
2023-01-24 07:58:03.290770: step: 264/529, loss: 0.00823371671140194
2023-01-24 07:58:04.400869: step: 268/529, loss: 0.027829378843307495
2023-01-24 07:58:05.496522: step: 272/529, loss: 0.010504011996090412
2023-01-24 07:58:06.589871: step: 276/529, loss: 0.0091888178139925
2023-01-24 07:58:07.721736: step: 280/529, loss: 0.019369134679436684
2023-01-24 07:58:08.816081: step: 284/529, loss: 0.020222444087266922
2023-01-24 07:58:09.917025: step: 288/529, loss: 0.009242132306098938
2023-01-24 07:58:11.036973: step: 292/529, loss: 0.0031274028588086367
2023-01-24 07:58:12.144477: step: 296/529, loss: 0.0022235142532736063
2023-01-24 07:58:13.274600: step: 300/529, loss: 0.01660131849348545
2023-01-24 07:58:14.407624: step: 304/529, loss: 0.0023003313690423965
2023-01-24 07:58:15.526398: step: 308/529, loss: 0.006474396679550409
2023-01-24 07:58:16.649248: step: 312/529, loss: 0.0065093738958239555
2023-01-24 07:58:17.745355: step: 316/529, loss: 0.007061909418553114
2023-01-24 07:58:18.900372: step: 320/529, loss: 0.04676046967506409
2023-01-24 07:58:20.036454: step: 324/529, loss: 0.009776496328413486
2023-01-24 07:58:21.121404: step: 328/529, loss: 0.001634639105759561
2023-01-24 07:58:22.235010: step: 332/529, loss: 0.008967863395810127
2023-01-24 07:58:23.351325: step: 336/529, loss: 0.01077272742986679
2023-01-24 07:58:24.445912: step: 340/529, loss: 0.010361066088080406
2023-01-24 07:58:25.544268: step: 344/529, loss: 0.006212722044438124
2023-01-24 07:58:26.650785: step: 348/529, loss: 0.0037770308554172516
2023-01-24 07:58:27.777185: step: 352/529, loss: 0.003101285081356764
2023-01-24 07:58:28.880252: step: 356/529, loss: 0.007602039258927107
2023-01-24 07:58:29.993946: step: 360/529, loss: 0.002098478376865387
2023-01-24 07:58:31.121319: step: 364/529, loss: 0.014492744579911232
2023-01-24 07:58:32.281129: step: 368/529, loss: 0.017801519483327866
2023-01-24 07:58:33.384215: step: 372/529, loss: 0.01312556304037571
2023-01-24 07:58:34.500827: step: 376/529, loss: 0.007660937495529652
2023-01-24 07:58:35.586853: step: 380/529, loss: 0.012426088564097881
2023-01-24 07:58:36.712359: step: 384/529, loss: 0.0033366484567523003
2023-01-24 07:58:37.821684: step: 388/529, loss: 0.0269781481474638
2023-01-24 07:58:38.952162: step: 392/529, loss: 0.011076470836997032
2023-01-24 07:58:40.058173: step: 396/529, loss: 0.0033511200454086065
2023-01-24 07:58:41.174106: step: 400/529, loss: 0.02930506132543087
2023-01-24 07:58:42.314178: step: 404/529, loss: 0.011032543145120144
2023-01-24 07:58:43.418149: step: 408/529, loss: 0.004598382860422134
2023-01-24 07:58:44.540818: step: 412/529, loss: 0.006473167799413204
2023-01-24 07:58:45.644001: step: 416/529, loss: 0.005065383855253458
2023-01-24 07:58:46.753983: step: 420/529, loss: 0.017824824899435043
2023-01-24 07:58:47.853406: step: 424/529, loss: 0.029513027518987656
2023-01-24 07:58:48.941677: step: 428/529, loss: 0.011568554677069187
2023-01-24 07:58:50.044119: step: 432/529, loss: 0.01351325772702694
2023-01-24 07:58:51.162301: step: 436/529, loss: 0.011314324103295803
2023-01-24 07:58:52.289885: step: 440/529, loss: 0.0018535078270360827
2023-01-24 07:58:53.390354: step: 444/529, loss: 0.00917566753923893
2023-01-24 07:58:54.496275: step: 448/529, loss: 0.004006459377706051
2023-01-24 07:58:55.595448: step: 452/529, loss: 0.007178399711847305
2023-01-24 07:58:56.706039: step: 456/529, loss: 0.018362870439887047
2023-01-24 07:58:57.815882: step: 460/529, loss: 0.0007383043994195759
2023-01-24 07:58:58.908822: step: 464/529, loss: 0.016009826213121414
2023-01-24 07:59:00.055146: step: 468/529, loss: 0.10536003112792969
2023-01-24 07:59:01.171359: step: 472/529, loss: 0.02493038773536682
2023-01-24 07:59:02.284040: step: 476/529, loss: 0.01624736562371254
2023-01-24 07:59:03.385318: step: 480/529, loss: 0.009674545377492905
2023-01-24 07:59:04.494330: step: 484/529, loss: 0.008204970508813858
2023-01-24 07:59:05.612373: step: 488/529, loss: 0.026262089610099792
2023-01-24 07:59:06.731242: step: 492/529, loss: 0.017736749723553658
2023-01-24 07:59:07.841482: step: 496/529, loss: 0.009284062311053276
2023-01-24 07:59:08.971556: step: 500/529, loss: 0.0026390322018414736
2023-01-24 07:59:10.077610: step: 504/529, loss: 0.009106617420911789
2023-01-24 07:59:11.180133: step: 508/529, loss: 0.005013694055378437
2023-01-24 07:59:12.296989: step: 512/529, loss: 0.003496789839118719
2023-01-24 07:59:13.412885: step: 516/529, loss: 0.014424193650484085
2023-01-24 07:59:14.516009: step: 520/529, loss: 0.005190179217606783
2023-01-24 07:59:15.639602: step: 524/529, loss: 0.004365604370832443
2023-01-24 07:59:16.745722: step: 528/529, loss: 0.030612310394644737
2023-01-24 07:59:17.869012: step: 532/529, loss: 0.009976319968700409
2023-01-24 07:59:18.968699: step: 536/529, loss: 0.005136997438967228
2023-01-24 07:59:20.073357: step: 540/529, loss: 0.0431562103331089
2023-01-24 07:59:21.202792: step: 544/529, loss: 0.016987593844532967
2023-01-24 07:59:22.299100: step: 548/529, loss: 0.006357799284160137
2023-01-24 07:59:23.392220: step: 552/529, loss: 0.02931724302470684
2023-01-24 07:59:24.514080: step: 556/529, loss: 0.0063680848106741905
2023-01-24 07:59:25.611936: step: 560/529, loss: 0.07104165852069855
2023-01-24 07:59:26.724764: step: 564/529, loss: 0.007566351443529129
2023-01-24 07:59:27.816620: step: 568/529, loss: 0.005318984389305115
2023-01-24 07:59:28.925889: step: 572/529, loss: 0.0033264204394072294
2023-01-24 07:59:30.016737: step: 576/529, loss: 0.0061906673945486546
2023-01-24 07:59:31.125552: step: 580/529, loss: 0.0015148785896599293
2023-01-24 07:59:32.224515: step: 584/529, loss: 0.005580266937613487
2023-01-24 07:59:33.349891: step: 588/529, loss: 0.005269291810691357
2023-01-24 07:59:34.463543: step: 592/529, loss: 0.010836911387741566
2023-01-24 07:59:35.564478: step: 596/529, loss: 0.007093312684446573
2023-01-24 07:59:36.665985: step: 600/529, loss: 0.00394090823829174
2023-01-24 07:59:37.788738: step: 604/529, loss: 0.025229722261428833
2023-01-24 07:59:38.890160: step: 608/529, loss: 0.007404191419482231
2023-01-24 07:59:40.005852: step: 612/529, loss: 0.006746270693838596
2023-01-24 07:59:41.087250: step: 616/529, loss: 0.004486020654439926
2023-01-24 07:59:42.190782: step: 620/529, loss: 0.006292097270488739
2023-01-24 07:59:43.294720: step: 624/529, loss: 0.003894990775734186
2023-01-24 07:59:44.413062: step: 628/529, loss: 0.003883993485942483
2023-01-24 07:59:45.539569: step: 632/529, loss: 0.010636607185006142
2023-01-24 07:59:46.642990: step: 636/529, loss: 0.003698068903759122
2023-01-24 07:59:47.741480: step: 640/529, loss: 0.0007454185979440808
2023-01-24 07:59:48.837911: step: 644/529, loss: 0.006561399903148413
2023-01-24 07:59:49.929939: step: 648/529, loss: 0.002798452042043209
2023-01-24 07:59:51.061106: step: 652/529, loss: 0.01471537072211504
2023-01-24 07:59:52.169668: step: 656/529, loss: 0.0004220718110445887
2023-01-24 07:59:53.266160: step: 660/529, loss: 0.013086855411529541
2023-01-24 07:59:54.386623: step: 664/529, loss: 0.010682719759643078
2023-01-24 07:59:55.486705: step: 668/529, loss: 0.003999470267444849
2023-01-24 07:59:56.593682: step: 672/529, loss: 0.010561957955360413
2023-01-24 07:59:57.708753: step: 676/529, loss: 0.00589521462097764
2023-01-24 07:59:58.819819: step: 680/529, loss: 0.007122252136468887
2023-01-24 07:59:59.931126: step: 684/529, loss: 0.012555491179227829
2023-01-24 08:00:01.033449: step: 688/529, loss: 0.02013995870947838
2023-01-24 08:00:02.138299: step: 692/529, loss: 0.015481523238122463
2023-01-24 08:00:03.254430: step: 696/529, loss: 0.007118125446140766
2023-01-24 08:00:04.361334: step: 700/529, loss: 0.005167075898498297
2023-01-24 08:00:05.468667: step: 704/529, loss: 0.047261595726013184
2023-01-24 08:00:06.542956: step: 708/529, loss: 0.007963101379573345
2023-01-24 08:00:07.669359: step: 712/529, loss: 0.0034525517839938402
2023-01-24 08:00:08.777033: step: 716/529, loss: 0.0016437385929748416
2023-01-24 08:00:09.889603: step: 720/529, loss: 0.009101164527237415
2023-01-24 08:00:10.993165: step: 724/529, loss: 0.005738244391977787
2023-01-24 08:00:12.119613: step: 728/529, loss: 0.018488379195332527
2023-01-24 08:00:13.270042: step: 732/529, loss: 0.007038819137960672
2023-01-24 08:00:14.365513: step: 736/529, loss: 0.006071228533983231
2023-01-24 08:00:15.477237: step: 740/529, loss: 0.005023562349379063
2023-01-24 08:00:16.578637: step: 744/529, loss: 0.004617659375071526
2023-01-24 08:00:17.691084: step: 748/529, loss: 0.007815138436853886
2023-01-24 08:00:18.777087: step: 752/529, loss: 0.01970025524497032
2023-01-24 08:00:19.895003: step: 756/529, loss: 0.006991046480834484
2023-01-24 08:00:21.021856: step: 760/529, loss: 0.011613264679908752
2023-01-24 08:00:22.126242: step: 764/529, loss: 0.0006045643822290003
2023-01-24 08:00:23.226118: step: 768/529, loss: 0.027163978666067123
2023-01-24 08:00:24.339378: step: 772/529, loss: 0.01495275367051363
2023-01-24 08:00:25.453569: step: 776/529, loss: 0.02189851738512516
2023-01-24 08:00:26.564036: step: 780/529, loss: 0.007105804048478603
2023-01-24 08:00:27.673308: step: 784/529, loss: 0.0036675743758678436
2023-01-24 08:00:28.769301: step: 788/529, loss: 0.013794896192848682
2023-01-24 08:00:29.852075: step: 792/529, loss: 0.0014850583393126726
2023-01-24 08:00:30.945974: step: 796/529, loss: 0.0075757154263556
2023-01-24 08:00:32.050347: step: 800/529, loss: 0.011147506535053253
2023-01-24 08:00:33.175515: step: 804/529, loss: 0.032947223633527756
2023-01-24 08:00:34.289919: step: 808/529, loss: 0.005446398630738258
2023-01-24 08:00:35.383191: step: 812/529, loss: 0.0034685619175434113
2023-01-24 08:00:36.507985: step: 816/529, loss: 0.007180335465818644
2023-01-24 08:00:37.598704: step: 820/529, loss: 0.024265587329864502
2023-01-24 08:00:38.709800: step: 824/529, loss: 0.008386551402509212
2023-01-24 08:00:39.844779: step: 828/529, loss: 0.007402473594993353
2023-01-24 08:00:40.940758: step: 832/529, loss: 0.01185094565153122
2023-01-24 08:00:42.016663: step: 836/529, loss: 0.012170891277492046
2023-01-24 08:00:43.146959: step: 840/529, loss: 0.010631968267261982
2023-01-24 08:00:44.259994: step: 844/529, loss: 0.003322591306641698
2023-01-24 08:00:45.362929: step: 848/529, loss: 0.033631227910518646
2023-01-24 08:00:46.509189: step: 852/529, loss: 0.0030285348184406757
2023-01-24 08:00:47.607554: step: 856/529, loss: 0.02448822371661663
2023-01-24 08:00:48.711806: step: 860/529, loss: 0.0011358704650774598
2023-01-24 08:00:49.815383: step: 864/529, loss: 0.0034448835067451
2023-01-24 08:00:50.911940: step: 868/529, loss: 0.004241591785103083
2023-01-24 08:00:52.006227: step: 872/529, loss: 0.005275551229715347
2023-01-24 08:00:53.111900: step: 876/529, loss: 0.02770281955599785
2023-01-24 08:00:54.229201: step: 880/529, loss: 0.011750437319278717
2023-01-24 08:00:55.350288: step: 884/529, loss: 0.02568661794066429
2023-01-24 08:00:56.444198: step: 888/529, loss: 0.004655956290662289
2023-01-24 08:00:57.538059: step: 892/529, loss: 0.006035744212567806
2023-01-24 08:00:58.642364: step: 896/529, loss: 0.008791065774857998
2023-01-24 08:00:59.759325: step: 900/529, loss: 0.010015271604061127
2023-01-24 08:01:00.842617: step: 904/529, loss: 0.0024109173100441694
2023-01-24 08:01:01.948859: step: 908/529, loss: 0.019569136202335358
2023-01-24 08:01:03.072954: step: 912/529, loss: 0.004561732057482004
2023-01-24 08:01:04.174911: step: 916/529, loss: 0.0037367860786616802
2023-01-24 08:01:05.262148: step: 920/529, loss: 0.010635183192789555
2023-01-24 08:01:06.356312: step: 924/529, loss: 0.008983165957033634
2023-01-24 08:01:07.477886: step: 928/529, loss: 0.007565532345324755
2023-01-24 08:01:08.591461: step: 932/529, loss: 0.0017121994169428945
2023-01-24 08:01:09.709439: step: 936/529, loss: 0.0076131694950163364
2023-01-24 08:01:10.811281: step: 940/529, loss: 0.011468220502138138
2023-01-24 08:01:11.910474: step: 944/529, loss: 0.036546703428030014
2023-01-24 08:01:13.002001: step: 948/529, loss: 0.00682549923658371
2023-01-24 08:01:14.090232: step: 952/529, loss: 0.0024943973403424025
2023-01-24 08:01:15.201111: step: 956/529, loss: 0.002746598096564412
2023-01-24 08:01:16.321799: step: 960/529, loss: 0.009136325679719448
2023-01-24 08:01:17.424844: step: 964/529, loss: 0.009686806239187717
2023-01-24 08:01:18.544321: step: 968/529, loss: 0.009747578762471676
2023-01-24 08:01:19.672573: step: 972/529, loss: 0.002793676685541868
2023-01-24 08:01:20.810319: step: 976/529, loss: 0.006567907985299826
2023-01-24 08:01:21.896602: step: 980/529, loss: 0.0014695754507556558
2023-01-24 08:01:22.996873: step: 984/529, loss: 0.008628619834780693
2023-01-24 08:01:24.100355: step: 988/529, loss: 0.011440317146480083
2023-01-24 08:01:25.200384: step: 992/529, loss: 0.031265582889318466
2023-01-24 08:01:26.299172: step: 996/529, loss: 0.049090299755334854
2023-01-24 08:01:27.406329: step: 1000/529, loss: 0.00949549488723278
2023-01-24 08:01:28.545012: step: 1004/529, loss: 0.005003900267183781
2023-01-24 08:01:29.658536: step: 1008/529, loss: 0.014957522973418236
2023-01-24 08:01:30.770694: step: 1012/529, loss: 0.006984794978052378
2023-01-24 08:01:31.862758: step: 1016/529, loss: 0.006630700081586838
2023-01-24 08:01:32.959286: step: 1020/529, loss: 0.008829296566545963
2023-01-24 08:01:34.077670: step: 1024/529, loss: 0.013563680462539196
2023-01-24 08:01:35.200000: step: 1028/529, loss: 0.013646767474710941
2023-01-24 08:01:36.316884: step: 1032/529, loss: 0.017026502639055252
2023-01-24 08:01:37.407042: step: 1036/529, loss: 0.005695422179996967
2023-01-24 08:01:38.514355: step: 1040/529, loss: 0.07065655291080475
2023-01-24 08:01:39.600260: step: 1044/529, loss: 0.008288687095046043
2023-01-24 08:01:40.713227: step: 1048/529, loss: 0.02265295386314392
2023-01-24 08:01:41.808688: step: 1052/529, loss: 0.011016628704965115
2023-01-24 08:01:42.909915: step: 1056/529, loss: 0.0072325230576097965
2023-01-24 08:01:44.018826: step: 1060/529, loss: 0.03593211621046066
2023-01-24 08:01:45.143885: step: 1064/529, loss: 0.02738920785486698
2023-01-24 08:01:46.280898: step: 1068/529, loss: 0.022856106981635094
2023-01-24 08:01:47.401711: step: 1072/529, loss: 0.0017097165109589696
2023-01-24 08:01:48.502479: step: 1076/529, loss: 0.01007858943194151
2023-01-24 08:01:49.599014: step: 1080/529, loss: 0.016430934891104698
2023-01-24 08:01:50.704918: step: 1084/529, loss: 0.02392333745956421
2023-01-24 08:01:51.815721: step: 1088/529, loss: 0.003210279857739806
2023-01-24 08:01:52.901707: step: 1092/529, loss: 0.03804733231663704
2023-01-24 08:01:54.021467: step: 1096/529, loss: 0.006736402865499258
2023-01-24 08:01:55.143140: step: 1100/529, loss: 0.00113061279989779
2023-01-24 08:01:56.238622: step: 1104/529, loss: 0.009493349120020866
2023-01-24 08:01:57.353035: step: 1108/529, loss: 0.005395055748522282
2023-01-24 08:01:58.461987: step: 1112/529, loss: 0.0
2023-01-24 08:01:59.579795: step: 1116/529, loss: 0.003971834667026997
2023-01-24 08:02:00.677157: step: 1120/529, loss: 0.006149261724203825
2023-01-24 08:02:01.802931: step: 1124/529, loss: 0.0067004370503127575
2023-01-24 08:02:02.949622: step: 1128/529, loss: 0.008645967580378056
2023-01-24 08:02:04.054482: step: 1132/529, loss: 0.007671167608350515
2023-01-24 08:02:05.128099: step: 1136/529, loss: 0.004762822762131691
2023-01-24 08:02:06.224416: step: 1140/529, loss: 0.004212038591504097
2023-01-24 08:02:07.331703: step: 1144/529, loss: 0.0052347611635923386
2023-01-24 08:02:08.411873: step: 1148/529, loss: 0.003539025317877531
2023-01-24 08:02:09.497550: step: 1152/529, loss: 0.03307104855775833
2023-01-24 08:02:10.605420: step: 1156/529, loss: 0.0350826270878315
2023-01-24 08:02:11.709003: step: 1160/529, loss: 0.006120604462921619
2023-01-24 08:02:12.790551: step: 1164/529, loss: 0.010355891659855843
2023-01-24 08:02:13.894399: step: 1168/529, loss: 0.0020980248227715492
2023-01-24 08:02:15.024958: step: 1172/529, loss: 0.0010193908819928765
2023-01-24 08:02:16.145514: step: 1176/529, loss: 0.007296436931937933
2023-01-24 08:02:17.236387: step: 1180/529, loss: 0.01590452715754509
2023-01-24 08:02:18.352370: step: 1184/529, loss: 0.01501762680709362
2023-01-24 08:02:19.462504: step: 1188/529, loss: 0.006405299063771963
2023-01-24 08:02:20.571974: step: 1192/529, loss: 0.034896738827228546
2023-01-24 08:02:21.685991: step: 1196/529, loss: 0.00830760132521391
2023-01-24 08:02:22.791616: step: 1200/529, loss: 0.003155040554702282
2023-01-24 08:02:23.894871: step: 1204/529, loss: 0.015755338594317436
2023-01-24 08:02:24.993860: step: 1208/529, loss: 0.009930795058608055
2023-01-24 08:02:26.096496: step: 1212/529, loss: 0.007268515881150961
2023-01-24 08:02:27.215369: step: 1216/529, loss: 0.014256534166634083
2023-01-24 08:02:28.335166: step: 1220/529, loss: 0.0023033777251839638
2023-01-24 08:02:29.428668: step: 1224/529, loss: 0.00286106183193624
2023-01-24 08:02:30.546732: step: 1228/529, loss: 0.009225982241332531
2023-01-24 08:02:31.643341: step: 1232/529, loss: 0.02584785781800747
2023-01-24 08:02:32.736039: step: 1236/529, loss: 0.0029287950601428747
2023-01-24 08:02:33.870193: step: 1240/529, loss: 0.008580446243286133
2023-01-24 08:02:34.952319: step: 1244/529, loss: 0.0029004202224314213
2023-01-24 08:02:36.084835: step: 1248/529, loss: 0.00072190206265077
2023-01-24 08:02:37.181114: step: 1252/529, loss: 0.008647261187434196
2023-01-24 08:02:38.292899: step: 1256/529, loss: 0.0038553958293050528
2023-01-24 08:02:39.380794: step: 1260/529, loss: 0.0035050292499363422
2023-01-24 08:02:40.508029: step: 1264/529, loss: 0.004807660356163979
2023-01-24 08:02:41.619572: step: 1268/529, loss: 0.013294756412506104
2023-01-24 08:02:42.735926: step: 1272/529, loss: 0.02997460588812828
2023-01-24 08:02:43.864182: step: 1276/529, loss: 0.006026304326951504
2023-01-24 08:02:44.957562: step: 1280/529, loss: 0.009825173765420914
2023-01-24 08:02:46.041739: step: 1284/529, loss: 0.003956271335482597
2023-01-24 08:02:47.152924: step: 1288/529, loss: 0.009954909794032574
2023-01-24 08:02:48.241618: step: 1292/529, loss: 0.0039692954160273075
2023-01-24 08:02:49.339826: step: 1296/529, loss: 0.00824042409658432
2023-01-24 08:02:50.456467: step: 1300/529, loss: 0.006427253130823374
2023-01-24 08:02:51.538434: step: 1304/529, loss: 0.0066772447898983955
2023-01-24 08:02:52.644702: step: 1308/529, loss: 0.01631542108952999
2023-01-24 08:02:53.800625: step: 1312/529, loss: 0.008065924048423767
2023-01-24 08:02:54.909156: step: 1316/529, loss: 0.009312838315963745
2023-01-24 08:02:56.033349: step: 1320/529, loss: 0.05190780758857727
2023-01-24 08:02:57.128386: step: 1324/529, loss: 0.005823833867907524
2023-01-24 08:02:58.237455: step: 1328/529, loss: 0.007591616362333298
2023-01-24 08:02:59.369033: step: 1332/529, loss: 0.006703960243612528
2023-01-24 08:03:00.485079: step: 1336/529, loss: 0.018768370151519775
2023-01-24 08:03:01.566332: step: 1340/529, loss: 0.024526676163077354
2023-01-24 08:03:02.705292: step: 1344/529, loss: 0.006300970911979675
2023-01-24 08:03:03.810224: step: 1348/529, loss: 0.010336175560951233
2023-01-24 08:03:04.949807: step: 1352/529, loss: 0.02772681973874569
2023-01-24 08:03:06.043817: step: 1356/529, loss: 0.03407607972621918
2023-01-24 08:03:07.134435: step: 1360/529, loss: 0.014773945324122906
2023-01-24 08:03:08.266748: step: 1364/529, loss: 0.1562815010547638
2023-01-24 08:03:09.367123: step: 1368/529, loss: 0.028557730838656425
2023-01-24 08:03:10.486335: step: 1372/529, loss: 0.01858489215373993
2023-01-24 08:03:11.570075: step: 1376/529, loss: 0.009563828818500042
2023-01-24 08:03:12.672515: step: 1380/529, loss: 0.01983632519841194
2023-01-24 08:03:13.814210: step: 1384/529, loss: 0.007155098021030426
2023-01-24 08:03:14.927089: step: 1388/529, loss: 0.026392385363578796
2023-01-24 08:03:16.063777: step: 1392/529, loss: 0.004741833079606295
2023-01-24 08:03:17.200210: step: 1396/529, loss: 0.0076646204106509686
2023-01-24 08:03:18.323937: step: 1400/529, loss: 0.008497913368046284
2023-01-24 08:03:19.419546: step: 1404/529, loss: 0.00710978964343667
2023-01-24 08:03:20.517267: step: 1408/529, loss: 0.002102840691804886
2023-01-24 08:03:21.608778: step: 1412/529, loss: 0.04014722257852554
2023-01-24 08:03:22.705291: step: 1416/529, loss: 0.017644071951508522
2023-01-24 08:03:23.797939: step: 1420/529, loss: 0.0036111820954829454
2023-01-24 08:03:24.911047: step: 1424/529, loss: 0.008191789500415325
2023-01-24 08:03:26.024973: step: 1428/529, loss: 0.007937217131257057
2023-01-24 08:03:27.120538: step: 1432/529, loss: 0.00306039210408926
2023-01-24 08:03:28.243546: step: 1436/529, loss: 0.011342877522110939
2023-01-24 08:03:29.357723: step: 1440/529, loss: 0.0025729602202773094
2023-01-24 08:03:30.475716: step: 1444/529, loss: 0.0063449786975979805
2023-01-24 08:03:31.587380: step: 1448/529, loss: 0.004742337390780449
2023-01-24 08:03:32.702456: step: 1452/529, loss: 0.028842899948358536
2023-01-24 08:03:33.793948: step: 1456/529, loss: 0.010683379136025906
2023-01-24 08:03:34.886705: step: 1460/529, loss: 0.009811916388571262
2023-01-24 08:03:36.013258: step: 1464/529, loss: 0.013648955151438713
2023-01-24 08:03:37.107972: step: 1468/529, loss: 0.009029221720993519
2023-01-24 08:03:38.212394: step: 1472/529, loss: 0.009125969372689724
2023-01-24 08:03:39.313889: step: 1476/529, loss: 0.005447356030344963
2023-01-24 08:03:40.412417: step: 1480/529, loss: 0.00017932680202648044
2023-01-24 08:03:41.513561: step: 1484/529, loss: 0.016321277245879173
2023-01-24 08:03:42.597826: step: 1488/529, loss: 0.015126307494938374
2023-01-24 08:03:43.703475: step: 1492/529, loss: 0.020544061437249184
2023-01-24 08:03:44.843334: step: 1496/529, loss: 0.007624355610460043
2023-01-24 08:03:45.947506: step: 1500/529, loss: 0.010923942551016808
2023-01-24 08:03:47.057707: step: 1504/529, loss: 0.008334414102137089
2023-01-24 08:03:48.134073: step: 1508/529, loss: 0.005844576749950647
2023-01-24 08:03:49.252298: step: 1512/529, loss: 0.004947004374116659
2023-01-24 08:03:50.350934: step: 1516/529, loss: 0.012654013931751251
2023-01-24 08:03:51.462391: step: 1520/529, loss: 0.007389873266220093
2023-01-24 08:03:52.591964: step: 1524/529, loss: 0.008271020837128162
2023-01-24 08:03:53.703295: step: 1528/529, loss: 0.006278053391724825
2023-01-24 08:03:54.817172: step: 1532/529, loss: 0.00804481003433466
2023-01-24 08:03:55.938707: step: 1536/529, loss: 0.00594293512403965
2023-01-24 08:03:57.032743: step: 1540/529, loss: 0.0064170872792601585
2023-01-24 08:03:58.150394: step: 1544/529, loss: 0.0012547632213681936
2023-01-24 08:03:59.239537: step: 1548/529, loss: 0.016787130385637283
2023-01-24 08:04:00.333308: step: 1552/529, loss: 0.014671772718429565
2023-01-24 08:04:01.443867: step: 1556/529, loss: 0.01921709254384041
2023-01-24 08:04:02.555794: step: 1560/529, loss: 0.011923871003091335
2023-01-24 08:04:03.650463: step: 1564/529, loss: 0.0192636139690876
2023-01-24 08:04:04.754174: step: 1568/529, loss: 0.002478834008798003
2023-01-24 08:04:05.863080: step: 1572/529, loss: 0.030554722994565964
2023-01-24 08:04:06.947514: step: 1576/529, loss: 0.0007834086427465081
2023-01-24 08:04:08.044960: step: 1580/529, loss: 0.0061339400708675385
2023-01-24 08:04:09.144672: step: 1584/529, loss: 0.011207625269889832
2023-01-24 08:04:10.242475: step: 1588/529, loss: 0.010608324781060219
2023-01-24 08:04:11.414464: step: 1592/529, loss: 0.014916323125362396
2023-01-24 08:04:12.520549: step: 1596/529, loss: 0.005108105484396219
2023-01-24 08:04:13.637693: step: 1600/529, loss: 0.00430460786446929
2023-01-24 08:04:14.761595: step: 1604/529, loss: 0.007633857429027557
2023-01-24 08:04:15.856490: step: 1608/529, loss: 0.004318347666412592
2023-01-24 08:04:16.983635: step: 1612/529, loss: 0.0016345756594091654
2023-01-24 08:04:18.086345: step: 1616/529, loss: 0.00565393315628171
2023-01-24 08:04:19.198034: step: 1620/529, loss: 0.03454332426190376
2023-01-24 08:04:20.299488: step: 1624/529, loss: 0.01870276778936386
2023-01-24 08:04:21.417717: step: 1628/529, loss: 0.0046154349111020565
2023-01-24 08:04:22.521517: step: 1632/529, loss: 0.018332835286855698
2023-01-24 08:04:23.632144: step: 1636/529, loss: 0.020688025280833244
2023-01-24 08:04:24.724670: step: 1640/529, loss: 0.01965653896331787
2023-01-24 08:04:25.830254: step: 1644/529, loss: 0.008216667920351028
2023-01-24 08:04:26.949883: step: 1648/529, loss: 0.0105309272184968
2023-01-24 08:04:28.078656: step: 1652/529, loss: 0.013985680416226387
2023-01-24 08:04:29.168985: step: 1656/529, loss: 0.0044655888341367245
2023-01-24 08:04:30.262460: step: 1660/529, loss: 0.004166341852396727
2023-01-24 08:04:31.372887: step: 1664/529, loss: 0.0057730115950107574
2023-01-24 08:04:32.487736: step: 1668/529, loss: 0.03798156604170799
2023-01-24 08:04:33.610466: step: 1672/529, loss: 0.010853929445147514
2023-01-24 08:04:34.701512: step: 1676/529, loss: 0.0026412634178996086
2023-01-24 08:04:35.825564: step: 1680/529, loss: 0.007113948464393616
2023-01-24 08:04:36.918702: step: 1684/529, loss: 0.011505438014864922
2023-01-24 08:04:38.053847: step: 1688/529, loss: 0.06450343132019043
2023-01-24 08:04:39.146968: step: 1692/529, loss: 0.0046125007793307304
2023-01-24 08:04:40.275135: step: 1696/529, loss: 0.006554285064339638
2023-01-24 08:04:41.376016: step: 1700/529, loss: 0.01852637156844139
2023-01-24 08:04:42.484296: step: 1704/529, loss: 0.0076111555099487305
2023-01-24 08:04:43.596071: step: 1708/529, loss: 0.033805493265390396
2023-01-24 08:04:44.709609: step: 1712/529, loss: 0.006822461262345314
2023-01-24 08:04:45.817119: step: 1716/529, loss: 0.0046230158768594265
2023-01-24 08:04:46.929735: step: 1720/529, loss: 0.004459755960851908
2023-01-24 08:04:48.022531: step: 1724/529, loss: 0.004157426301389933
2023-01-24 08:04:49.133146: step: 1728/529, loss: 0.0014901006361469626
2023-01-24 08:04:50.222678: step: 1732/529, loss: 0.005487402435392141
2023-01-24 08:04:51.329338: step: 1736/529, loss: 0.009611217305064201
2023-01-24 08:04:52.443925: step: 1740/529, loss: 0.010116838850080967
2023-01-24 08:04:53.538321: step: 1744/529, loss: 0.005602534860372543
2023-01-24 08:04:54.653807: step: 1748/529, loss: 0.0036284972447901964
2023-01-24 08:04:55.799173: step: 1752/529, loss: 0.01792565919458866
2023-01-24 08:04:56.923834: step: 1756/529, loss: 0.00588710093870759
2023-01-24 08:04:58.077029: step: 1760/529, loss: 0.0032751059625297785
2023-01-24 08:04:59.161149: step: 1764/529, loss: 0.007404741831123829
2023-01-24 08:05:00.265746: step: 1768/529, loss: 0.0009137190645560622
2023-01-24 08:05:01.377419: step: 1772/529, loss: 0.009999031201004982
2023-01-24 08:05:02.472375: step: 1776/529, loss: 0.02776346169412136
2023-01-24 08:05:03.599561: step: 1780/529, loss: 0.02876080758869648
2023-01-24 08:05:04.723707: step: 1784/529, loss: 0.11931665986776352
2023-01-24 08:05:05.815605: step: 1788/529, loss: 0.00244296551682055
2023-01-24 08:05:06.908087: step: 1792/529, loss: 0.003958273213356733
2023-01-24 08:05:08.049186: step: 1796/529, loss: 0.0045238640159368515
2023-01-24 08:05:09.147682: step: 1800/529, loss: 0.028285330161452293
2023-01-24 08:05:10.251414: step: 1804/529, loss: 0.009077048860490322
2023-01-24 08:05:11.365996: step: 1808/529, loss: 0.04064033925533295
2023-01-24 08:05:12.478769: step: 1812/529, loss: 0.006792752537876368
2023-01-24 08:05:13.577829: step: 1816/529, loss: 0.003269175998866558
2023-01-24 08:05:14.683368: step: 1820/529, loss: 0.006556231994181871
2023-01-24 08:05:15.793259: step: 1824/529, loss: 0.0054048895835876465
2023-01-24 08:05:16.904979: step: 1828/529, loss: 0.007066300604492426
2023-01-24 08:05:17.987327: step: 1832/529, loss: 0.036295562982559204
2023-01-24 08:05:19.110353: step: 1836/529, loss: 0.006278666201978922
2023-01-24 08:05:20.217840: step: 1840/529, loss: 0.01597563736140728
2023-01-24 08:05:21.349759: step: 1844/529, loss: 0.0073672104626894
2023-01-24 08:05:22.445349: step: 1848/529, loss: 0.011774738319218159
2023-01-24 08:05:23.539400: step: 1852/529, loss: 0.0035159094259142876
2023-01-24 08:05:24.661517: step: 1856/529, loss: 0.004620057996362448
2023-01-24 08:05:25.771216: step: 1860/529, loss: 0.0062436931766569614
2023-01-24 08:05:26.890259: step: 1864/529, loss: 0.007321196608245373
2023-01-24 08:05:28.008811: step: 1868/529, loss: 0.006461309734731913
2023-01-24 08:05:29.114470: step: 1872/529, loss: 0.04484855756163597
2023-01-24 08:05:30.205190: step: 1876/529, loss: 0.005174992606043816
2023-01-24 08:05:31.337694: step: 1880/529, loss: 0.003563453909009695
2023-01-24 08:05:32.449175: step: 1884/529, loss: 0.0046882592141628265
2023-01-24 08:05:33.552010: step: 1888/529, loss: 0.01261555589735508
2023-01-24 08:05:34.654302: step: 1892/529, loss: 0.0034093556459993124
2023-01-24 08:05:35.772551: step: 1896/529, loss: 0.010241791605949402
2023-01-24 08:05:36.868314: step: 1900/529, loss: 0.0015312704490497708
2023-01-24 08:05:37.975167: step: 1904/529, loss: 0.025107678025960922
2023-01-24 08:05:39.092210: step: 1908/529, loss: 0.007371546234935522
2023-01-24 08:05:40.194322: step: 1912/529, loss: 0.0
2023-01-24 08:05:41.302491: step: 1916/529, loss: 0.0038481811061501503
2023-01-24 08:05:42.428908: step: 1920/529, loss: 0.008993173949420452
2023-01-24 08:05:43.530417: step: 1924/529, loss: 0.0033240830525755882
2023-01-24 08:05:44.652050: step: 1928/529, loss: 0.008125894702970982
2023-01-24 08:05:45.780876: step: 1932/529, loss: 0.001147898961789906
2023-01-24 08:05:46.906905: step: 1936/529, loss: 0.0077410549856722355
2023-01-24 08:05:48.025749: step: 1940/529, loss: 0.009782909415662289
2023-01-24 08:05:49.113131: step: 1944/529, loss: 0.025076620280742645
2023-01-24 08:05:50.210152: step: 1948/529, loss: 0.01597674936056137
2023-01-24 08:05:51.324190: step: 1952/529, loss: 0.0004735524416901171
2023-01-24 08:05:52.439658: step: 1956/529, loss: 0.0005445539718493819
2023-01-24 08:05:53.569327: step: 1960/529, loss: 0.006779307499527931
2023-01-24 08:05:54.638247: step: 1964/529, loss: 0.0014635936822742224
2023-01-24 08:05:55.726589: step: 1968/529, loss: 0.003631761996075511
2023-01-24 08:05:56.837956: step: 1972/529, loss: 0.008415826596319675
2023-01-24 08:05:57.967815: step: 1976/529, loss: 0.007191472686827183
2023-01-24 08:05:59.071148: step: 1980/529, loss: 0.008011182770133018
2023-01-24 08:06:00.182759: step: 1984/529, loss: 0.011564129032194614
2023-01-24 08:06:01.282208: step: 1988/529, loss: 4.088526839041151e-05
2023-01-24 08:06:02.395752: step: 1992/529, loss: 0.0044421181082725525
2023-01-24 08:06:03.517371: step: 1996/529, loss: 0.00152040075045079
2023-01-24 08:06:04.618486: step: 2000/529, loss: 0.0023216786794364452
2023-01-24 08:06:05.715941: step: 2004/529, loss: 0.0036217004526406527
2023-01-24 08:06:06.826660: step: 2008/529, loss: 0.009130951948463917
2023-01-24 08:06:07.929280: step: 2012/529, loss: 0.009823904372751713
2023-01-24 08:06:09.040184: step: 2016/529, loss: 0.0022416035644710064
2023-01-24 08:06:10.137983: step: 2020/529, loss: 0.0052179298363626
2023-01-24 08:06:11.261591: step: 2024/529, loss: 0.004806553013622761
2023-01-24 08:06:12.347102: step: 2028/529, loss: 0.007773983757942915
2023-01-24 08:06:13.449462: step: 2032/529, loss: 0.006831275764852762
2023-01-24 08:06:14.550478: step: 2036/529, loss: 0.007376746274530888
2023-01-24 08:06:15.672218: step: 2040/529, loss: 0.024378931149840355
2023-01-24 08:06:16.760176: step: 2044/529, loss: 0.0035203720908612013
2023-01-24 08:06:17.887776: step: 2048/529, loss: 0.0027153335977345705
2023-01-24 08:06:18.990258: step: 2052/529, loss: 0.014825323596596718
2023-01-24 08:06:20.102566: step: 2056/529, loss: 0.003668862860649824
2023-01-24 08:06:21.197181: step: 2060/529, loss: 0.00796460174024105
2023-01-24 08:06:22.317232: step: 2064/529, loss: 0.027771560475230217
2023-01-24 08:06:23.424301: step: 2068/529, loss: 0.03683504834771156
2023-01-24 08:06:24.559909: step: 2072/529, loss: 0.00495346961542964
2023-01-24 08:06:25.665063: step: 2076/529, loss: 0.010131757706403732
2023-01-24 08:06:26.772467: step: 2080/529, loss: 0.02494375966489315
2023-01-24 08:06:27.903614: step: 2084/529, loss: 0.0012241617077961564
2023-01-24 08:06:29.003689: step: 2088/529, loss: 0.023943539708852768
2023-01-24 08:06:30.094846: step: 2092/529, loss: 0.0031378851272165775
2023-01-24 08:06:31.228157: step: 2096/529, loss: 0.004842622671276331
2023-01-24 08:06:32.357018: step: 2100/529, loss: 0.005990363657474518
2023-01-24 08:06:33.470145: step: 2104/529, loss: 0.005425291135907173
2023-01-24 08:06:34.570556: step: 2108/529, loss: 0.004704763647168875
2023-01-24 08:06:35.677400: step: 2112/529, loss: 0.004776051267981529
2023-01-24 08:06:36.801416: step: 2116/529, loss: 0.0035173268988728523
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38273608429858424, 'r': 0.32245696665763074, 'f1': 0.35002022951302036}, 'combined': 0.25790964279906764, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.4005487672478493, 'r': 0.2853129000673589, 'f1': 0.3332500877304981}, 'combined': 0.20482688319045247, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37990713416723454, 'r': 0.3337704044011947, 'f1': 0.3553474810493527}, 'combined': 0.2618349860363651, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3781340548970343, 'r': 0.28704110233085095, 'f1': 0.3263501793988197}, 'combined': 0.20058596392317699, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4092045454545455, 'r': 0.3416508538899431, 'f1': 0.37238883143743534}, 'combined': 0.2743917705328471, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39642578920868554, 'r': 0.2820325588737702, 'f1': 0.3295853903193223}, 'combined': 0.20356744696193443, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4087527352297593, 'r': 0.35445920303605316, 'f1': 0.3796747967479675}, 'combined': 0.27976037655113395, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3935884290148207, 'r': 0.2837656611268032, 'f1': 0.3297739908764661}, 'combined': 0.20368393554134676, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:09:00.317699: step: 4/529, loss: 0.0010277761612087488
2023-01-24 08:09:01.433376: step: 8/529, loss: 0.010806041769683361
2023-01-24 08:09:02.536201: step: 12/529, loss: 0.004061661195009947
2023-01-24 08:09:03.624794: step: 16/529, loss: 0.007979325950145721
2023-01-24 08:09:04.753333: step: 20/529, loss: 0.0207815021276474
2023-01-24 08:09:05.836897: step: 24/529, loss: 0.002433926332741976
2023-01-24 08:09:06.950941: step: 28/529, loss: 0.0009482248569838703
2023-01-24 08:09:08.044043: step: 32/529, loss: 0.004135242663323879
2023-01-24 08:09:09.146708: step: 36/529, loss: 0.011053194291889668
2023-01-24 08:09:10.249826: step: 40/529, loss: 0.007244446314871311
2023-01-24 08:09:11.357861: step: 44/529, loss: 0.039158716797828674
2023-01-24 08:09:12.440554: step: 48/529, loss: 0.018788348883390427
2023-01-24 08:09:13.541434: step: 52/529, loss: 0.0009543916676193476
2023-01-24 08:09:14.640837: step: 56/529, loss: 0.00402290653437376
2023-01-24 08:09:15.762198: step: 60/529, loss: 0.004691957496106625
2023-01-24 08:09:16.855918: step: 64/529, loss: 0.014238426461815834
2023-01-24 08:09:17.960295: step: 68/529, loss: 0.01219252310693264
2023-01-24 08:09:19.055609: step: 72/529, loss: 0.010191323235630989
2023-01-24 08:09:20.172106: step: 76/529, loss: 0.017158569768071175
2023-01-24 08:09:21.250697: step: 80/529, loss: 0.005863894708454609
2023-01-24 08:09:22.340045: step: 84/529, loss: 0.014999204315245152
2023-01-24 08:09:23.457815: step: 88/529, loss: 0.009794222190976143
2023-01-24 08:09:24.563802: step: 92/529, loss: 0.00871590618044138
2023-01-24 08:09:25.675098: step: 96/529, loss: 0.014467458240687847
2023-01-24 08:09:26.793872: step: 100/529, loss: 0.01966398023068905
2023-01-24 08:09:27.898355: step: 104/529, loss: 0.004165752325206995
2023-01-24 08:09:29.007552: step: 108/529, loss: 0.00027261098148301244
2023-01-24 08:09:30.125864: step: 112/529, loss: 0.017045212909579277
2023-01-24 08:09:31.265147: step: 116/529, loss: 0.011953402310609818
2023-01-24 08:09:32.384178: step: 120/529, loss: 0.02382500097155571
2023-01-24 08:09:33.501608: step: 124/529, loss: 0.009406017139554024
2023-01-24 08:09:34.617670: step: 128/529, loss: 0.026710592210292816
2023-01-24 08:09:35.749476: step: 132/529, loss: 0.01230623759329319
2023-01-24 08:09:36.849979: step: 136/529, loss: 0.006661921739578247
2023-01-24 08:09:37.973802: step: 140/529, loss: 0.016752805560827255
2023-01-24 08:09:39.074625: step: 144/529, loss: 0.005688263103365898
2023-01-24 08:09:40.175295: step: 148/529, loss: 0.017508279532194138
2023-01-24 08:09:41.268736: step: 152/529, loss: 0.018228985369205475
2023-01-24 08:09:42.375742: step: 156/529, loss: 0.0026795410085469484
2023-01-24 08:09:43.503416: step: 160/529, loss: 0.0034972375724464655
2023-01-24 08:09:44.630822: step: 164/529, loss: 0.005714005324989557
2023-01-24 08:09:45.753465: step: 168/529, loss: 0.0073775555938482285
2023-01-24 08:09:46.851575: step: 172/529, loss: 0.0023705316707491875
2023-01-24 08:09:47.933992: step: 176/529, loss: 0.005095466505736113
2023-01-24 08:09:49.034462: step: 180/529, loss: 0.0193537138402462
2023-01-24 08:09:50.149791: step: 184/529, loss: 0.029033103957772255
2023-01-24 08:09:51.242433: step: 188/529, loss: 0.021615667268633842
2023-01-24 08:09:52.341702: step: 192/529, loss: 0.010073946788907051
2023-01-24 08:09:53.439265: step: 196/529, loss: 0.005494964774698019
2023-01-24 08:09:54.548547: step: 200/529, loss: 0.005054249428212643
2023-01-24 08:09:55.658283: step: 204/529, loss: 0.0051721613854169846
2023-01-24 08:09:56.763684: step: 208/529, loss: 0.008345655165612698
2023-01-24 08:09:57.868311: step: 212/529, loss: 0.023853175342082977
2023-01-24 08:09:58.968082: step: 216/529, loss: 0.005570420064032078
2023-01-24 08:10:00.094521: step: 220/529, loss: 5.236471406533383e-05
2023-01-24 08:10:01.209170: step: 224/529, loss: 0.001574378926306963
2023-01-24 08:10:02.350295: step: 228/529, loss: 0.008779872208833694
2023-01-24 08:10:03.467281: step: 232/529, loss: 0.008622650057077408
2023-01-24 08:10:04.571886: step: 236/529, loss: 0.0014193839160725474
2023-01-24 08:10:05.681515: step: 240/529, loss: 0.01752307079732418
2023-01-24 08:10:06.794508: step: 244/529, loss: 0.011145064607262611
2023-01-24 08:10:07.893835: step: 248/529, loss: 0.01546645350754261
2023-01-24 08:10:09.017595: step: 252/529, loss: 0.008975861594080925
2023-01-24 08:10:10.131697: step: 256/529, loss: 0.0033201894257217646
2023-01-24 08:10:11.251540: step: 260/529, loss: 0.005528888665139675
2023-01-24 08:10:12.352453: step: 264/529, loss: 0.004674576688557863
2023-01-24 08:10:13.469302: step: 268/529, loss: 0.009894490242004395
2023-01-24 08:10:14.574305: step: 272/529, loss: 0.007337674964219332
2023-01-24 08:10:15.685009: step: 276/529, loss: 0.009367755614221096
2023-01-24 08:10:16.793067: step: 280/529, loss: 0.0014483543345704675
2023-01-24 08:10:17.906385: step: 284/529, loss: 0.010304666124284267
2023-01-24 08:10:18.995451: step: 288/529, loss: 0.005490402691066265
2023-01-24 08:10:20.093914: step: 292/529, loss: 0.029745591804385185
2023-01-24 08:10:21.194945: step: 296/529, loss: 0.0025941135827451944
2023-01-24 08:10:22.333432: step: 300/529, loss: 0.012264592573046684
2023-01-24 08:10:23.480793: step: 304/529, loss: 0.004538606386631727
2023-01-24 08:10:24.612554: step: 308/529, loss: 0.020474176853895187
2023-01-24 08:10:25.698681: step: 312/529, loss: 0.0010937289334833622
2023-01-24 08:10:26.801074: step: 316/529, loss: 0.03347092494368553
2023-01-24 08:10:27.894256: step: 320/529, loss: 0.002895524725317955
2023-01-24 08:10:29.025144: step: 324/529, loss: 0.008518103510141373
2023-01-24 08:10:30.140338: step: 328/529, loss: 0.020794207230210304
2023-01-24 08:10:31.271875: step: 332/529, loss: 0.03317151591181755
2023-01-24 08:10:32.407668: step: 336/529, loss: 0.02144635282456875
2023-01-24 08:10:33.528028: step: 340/529, loss: 0.010164160281419754
2023-01-24 08:10:34.629167: step: 344/529, loss: 0.00684781838208437
2023-01-24 08:10:35.754550: step: 348/529, loss: 0.02203591726720333
2023-01-24 08:10:36.862207: step: 352/529, loss: 0.005991616286337376
2023-01-24 08:10:37.970176: step: 356/529, loss: 0.0473276823759079
2023-01-24 08:10:39.085943: step: 360/529, loss: 0.01721019484102726
2023-01-24 08:10:40.191245: step: 364/529, loss: 0.008875301107764244
2023-01-24 08:10:41.296378: step: 368/529, loss: 0.006471844855695963
2023-01-24 08:10:42.411156: step: 372/529, loss: 0.017932103946805
2023-01-24 08:10:43.501380: step: 376/529, loss: 0.03158516436815262
2023-01-24 08:10:44.605590: step: 380/529, loss: 0.010447031818330288
2023-01-24 08:10:45.743811: step: 384/529, loss: 0.0077856131829321384
2023-01-24 08:10:46.844224: step: 388/529, loss: 0.007280371617525816
2023-01-24 08:10:47.950530: step: 392/529, loss: 0.019415080547332764
2023-01-24 08:10:49.059884: step: 396/529, loss: 0.006431635934859514
2023-01-24 08:10:50.182140: step: 400/529, loss: 0.0004165937134530395
2023-01-24 08:10:51.320557: step: 404/529, loss: 0.023850802332162857
2023-01-24 08:10:52.436816: step: 408/529, loss: 0.022242402657866478
2023-01-24 08:10:53.532993: step: 412/529, loss: 0.0005607185303233564
2023-01-24 08:10:54.618141: step: 416/529, loss: 0.0031985067762434483
2023-01-24 08:10:55.718696: step: 420/529, loss: 0.0014394099125638604
2023-01-24 08:10:56.823778: step: 424/529, loss: 0.0044053951278328896
2023-01-24 08:10:57.924930: step: 428/529, loss: 0.007118708454072475
2023-01-24 08:10:59.004311: step: 432/529, loss: 0.016993161290884018
2023-01-24 08:11:00.091219: step: 436/529, loss: 0.009401665069162846
2023-01-24 08:11:01.183665: step: 440/529, loss: 0.0011328529799357057
2023-01-24 08:11:02.310575: step: 444/529, loss: 0.0026023162063211203
2023-01-24 08:11:03.439285: step: 448/529, loss: 0.016223173588514328
2023-01-24 08:11:04.552099: step: 452/529, loss: 0.009850227274000645
2023-01-24 08:11:05.674278: step: 456/529, loss: 0.007447805255651474
2023-01-24 08:11:06.796865: step: 460/529, loss: 0.0026509473100304604
2023-01-24 08:11:07.919575: step: 464/529, loss: 0.002980706049129367
2023-01-24 08:11:09.006769: step: 468/529, loss: 0.002533161547034979
2023-01-24 08:11:10.120094: step: 472/529, loss: 0.0053563425317406654
2023-01-24 08:11:11.212916: step: 476/529, loss: 0.0109642893075943
2023-01-24 08:11:12.328020: step: 480/529, loss: 0.040974292904138565
2023-01-24 08:11:13.421141: step: 484/529, loss: 0.006244489923119545
2023-01-24 08:11:14.536021: step: 488/529, loss: 0.0022297760006040335
2023-01-24 08:11:15.650259: step: 492/529, loss: 0.026245882734656334
2023-01-24 08:11:16.758054: step: 496/529, loss: 0.002393545815721154
2023-01-24 08:11:17.866838: step: 500/529, loss: 0.0007777800783514977
2023-01-24 08:11:18.986449: step: 504/529, loss: 0.00473775016143918
2023-01-24 08:11:20.104707: step: 508/529, loss: 0.026044726371765137
2023-01-24 08:11:21.227633: step: 512/529, loss: 0.01604190282523632
2023-01-24 08:11:22.309497: step: 516/529, loss: 0.0012831779895350337
2023-01-24 08:11:23.415631: step: 520/529, loss: 0.006340454798191786
2023-01-24 08:11:24.525522: step: 524/529, loss: 0.01106035802513361
2023-01-24 08:11:25.650305: step: 528/529, loss: 0.001452543423511088
2023-01-24 08:11:26.760423: step: 532/529, loss: 0.015412398613989353
2023-01-24 08:11:27.862205: step: 536/529, loss: 0.004751899279654026
2023-01-24 08:11:28.969861: step: 540/529, loss: 0.0032661445438861847
2023-01-24 08:11:30.075393: step: 544/529, loss: 0.0005853670882061124
2023-01-24 08:11:31.174907: step: 548/529, loss: 0.006554052233695984
2023-01-24 08:11:32.273790: step: 552/529, loss: 0.00837355200201273
2023-01-24 08:11:33.357991: step: 556/529, loss: 0.008125251159071922
2023-01-24 08:11:34.458908: step: 560/529, loss: 0.0009894382674247026
2023-01-24 08:11:35.585952: step: 564/529, loss: 0.04186941683292389
2023-01-24 08:11:36.738653: step: 568/529, loss: 0.009356123395264149
2023-01-24 08:11:37.833362: step: 572/529, loss: 0.0006051416276022792
2023-01-24 08:11:38.953649: step: 576/529, loss: 0.21576407551765442
2023-01-24 08:11:40.074094: step: 580/529, loss: 0.011934589594602585
2023-01-24 08:11:41.172742: step: 584/529, loss: 0.009236830286681652
2023-01-24 08:11:42.291529: step: 588/529, loss: 0.00466415099799633
2023-01-24 08:11:43.406825: step: 592/529, loss: 0.0016343441093340516
2023-01-24 08:11:44.517456: step: 596/529, loss: 0.026625338941812515
2023-01-24 08:11:45.616077: step: 600/529, loss: 0.004493574611842632
2023-01-24 08:11:46.731406: step: 604/529, loss: 0.006767883896827698
2023-01-24 08:11:47.872065: step: 608/529, loss: 0.011909508146345615
2023-01-24 08:11:48.977495: step: 612/529, loss: 0.001967308111488819
2023-01-24 08:11:50.077594: step: 616/529, loss: 0.0036473397631198168
2023-01-24 08:11:51.190350: step: 620/529, loss: 0.010080767795443535
2023-01-24 08:11:52.313116: step: 624/529, loss: 0.0036771828308701515
2023-01-24 08:11:53.440598: step: 628/529, loss: 0.014914165250957012
2023-01-24 08:11:54.557844: step: 632/529, loss: 0.014681203290820122
2023-01-24 08:11:55.683657: step: 636/529, loss: 0.004522932693362236
2023-01-24 08:11:56.785705: step: 640/529, loss: 0.004725313279777765
2023-01-24 08:11:57.896430: step: 644/529, loss: 0.019719386473298073
2023-01-24 08:11:59.004125: step: 648/529, loss: 0.015340156853199005
2023-01-24 08:12:00.094777: step: 652/529, loss: 0.0007406998774968088
2023-01-24 08:12:01.221901: step: 656/529, loss: 0.02902970276772976
2023-01-24 08:12:02.349335: step: 660/529, loss: 0.007650643587112427
2023-01-24 08:12:03.447787: step: 664/529, loss: 0.00830087997019291
2023-01-24 08:12:04.563282: step: 668/529, loss: 0.015173443593084812
2023-01-24 08:12:05.670247: step: 672/529, loss: 0.012100734747946262
2023-01-24 08:12:06.787063: step: 676/529, loss: 0.006625749170780182
2023-01-24 08:12:07.893881: step: 680/529, loss: 0.006128285545855761
2023-01-24 08:12:08.985428: step: 684/529, loss: 0.013691570609807968
2023-01-24 08:12:10.087662: step: 688/529, loss: 0.0033774354960769415
2023-01-24 08:12:11.200928: step: 692/529, loss: 0.007560168858617544
2023-01-24 08:12:12.296927: step: 696/529, loss: 0.001372764934785664
2023-01-24 08:12:13.439797: step: 700/529, loss: 0.0024722497910261154
2023-01-24 08:12:14.564706: step: 704/529, loss: 0.005930012557655573
2023-01-24 08:12:15.681828: step: 708/529, loss: 0.012372095137834549
2023-01-24 08:12:16.789113: step: 712/529, loss: 0.01303862128406763
2023-01-24 08:12:17.900093: step: 716/529, loss: 0.004747738596051931
2023-01-24 08:12:19.003428: step: 720/529, loss: 0.009267057292163372
2023-01-24 08:12:20.111136: step: 724/529, loss: 0.01605737954378128
2023-01-24 08:12:21.225629: step: 728/529, loss: 0.038729555904865265
2023-01-24 08:12:22.356937: step: 732/529, loss: 0.008422422222793102
2023-01-24 08:12:23.503626: step: 736/529, loss: 0.03169281408190727
2023-01-24 08:12:24.596646: step: 740/529, loss: 0.00846653152257204
2023-01-24 08:12:25.687020: step: 744/529, loss: 0.015459591522812843
2023-01-24 08:12:26.774977: step: 748/529, loss: 0.004907554015517235
2023-01-24 08:12:27.883398: step: 752/529, loss: 0.015004247426986694
2023-01-24 08:12:28.966784: step: 756/529, loss: 0.012084837071597576
2023-01-24 08:12:30.063465: step: 760/529, loss: 0.005137275438755751
2023-01-24 08:12:31.187476: step: 764/529, loss: 0.004976230673491955
2023-01-24 08:12:32.298408: step: 768/529, loss: 0.005279588047415018
2023-01-24 08:12:33.399878: step: 772/529, loss: 0.018384218215942383
2023-01-24 08:12:34.520092: step: 776/529, loss: 0.007088427897542715
2023-01-24 08:12:35.632844: step: 780/529, loss: 0.02659505233168602
2023-01-24 08:12:36.733612: step: 784/529, loss: 0.008689891546964645
2023-01-24 08:12:37.851241: step: 788/529, loss: 0.014384131878614426
2023-01-24 08:12:38.964397: step: 792/529, loss: 0.014415809884667397
2023-01-24 08:12:40.075887: step: 796/529, loss: 0.007281031459569931
2023-01-24 08:12:41.182877: step: 800/529, loss: 0.0013218119274824858
2023-01-24 08:12:42.279449: step: 804/529, loss: 0.004758133087307215
2023-01-24 08:12:43.383861: step: 808/529, loss: 0.004000222310423851
2023-01-24 08:12:44.503638: step: 812/529, loss: 0.0016594043700024486
2023-01-24 08:12:45.602578: step: 816/529, loss: 0.005027247127145529
2023-01-24 08:12:46.706652: step: 820/529, loss: 0.0020168223418295383
2023-01-24 08:12:47.834386: step: 824/529, loss: 0.0061863805167376995
2023-01-24 08:12:48.964577: step: 828/529, loss: 0.0468766875565052
2023-01-24 08:12:50.072207: step: 832/529, loss: 0.01615077815949917
2023-01-24 08:12:51.172082: step: 836/529, loss: 0.0018825752194970846
2023-01-24 08:12:52.289247: step: 840/529, loss: 0.007199371699243784
2023-01-24 08:12:53.395342: step: 844/529, loss: 0.023867301642894745
2023-01-24 08:12:54.524991: step: 848/529, loss: 0.0033928307238966227
2023-01-24 08:12:55.613448: step: 852/529, loss: 0.007349400315433741
2023-01-24 08:12:56.701984: step: 856/529, loss: 0.0052449582144618034
2023-01-24 08:12:57.837564: step: 860/529, loss: 0.047246553003787994
2023-01-24 08:12:58.956283: step: 864/529, loss: 0.016368074342608452
2023-01-24 08:13:00.041497: step: 868/529, loss: 0.0006732017500326037
2023-01-24 08:13:01.161751: step: 872/529, loss: 0.0006092994590289891
2023-01-24 08:13:02.266264: step: 876/529, loss: 0.007539412006735802
2023-01-24 08:13:03.378804: step: 880/529, loss: 0.00515257753431797
2023-01-24 08:13:04.485399: step: 884/529, loss: 0.006033609621226788
2023-01-24 08:13:05.603130: step: 888/529, loss: 0.02253161370754242
2023-01-24 08:13:06.700229: step: 892/529, loss: 0.011741726659238338
2023-01-24 08:13:07.827511: step: 896/529, loss: 0.023104097694158554
2023-01-24 08:13:08.945106: step: 900/529, loss: 0.001843949081376195
2023-01-24 08:13:10.059590: step: 904/529, loss: 0.011249789968132973
2023-01-24 08:13:11.177033: step: 908/529, loss: 0.011782222427427769
2023-01-24 08:13:12.274228: step: 912/529, loss: 0.0015654019080102444
2023-01-24 08:13:13.389824: step: 916/529, loss: 0.0006320729153230786
2023-01-24 08:13:14.516276: step: 920/529, loss: 0.0006103994674049318
2023-01-24 08:13:15.625392: step: 924/529, loss: 0.0006619783816859126
2023-01-24 08:13:16.756396: step: 928/529, loss: 0.04173458367586136
2023-01-24 08:13:17.852542: step: 932/529, loss: 0.0018200431950390339
2023-01-24 08:13:18.951894: step: 936/529, loss: 0.003070810344070196
2023-01-24 08:13:20.080496: step: 940/529, loss: 0.027826832607388496
2023-01-24 08:13:21.176110: step: 944/529, loss: 0.004700905177742243
2023-01-24 08:13:22.272310: step: 948/529, loss: 0.003204314038157463
2023-01-24 08:13:23.355996: step: 952/529, loss: 0.007695063482969999
2023-01-24 08:13:24.448838: step: 956/529, loss: 0.015621177852153778
2023-01-24 08:13:25.552979: step: 960/529, loss: 0.0019094145391136408
2023-01-24 08:13:26.687929: step: 964/529, loss: 0.009083282202482224
2023-01-24 08:13:27.783529: step: 968/529, loss: 0.043462857604026794
2023-01-24 08:13:28.895163: step: 972/529, loss: 0.009487127885222435
2023-01-24 08:13:30.013772: step: 976/529, loss: 0.006757418625056744
2023-01-24 08:13:31.118197: step: 980/529, loss: 0.002615052741020918
2023-01-24 08:13:32.237039: step: 984/529, loss: 0.027554383501410484
2023-01-24 08:13:33.339206: step: 988/529, loss: 0.006075514946132898
2023-01-24 08:13:34.440760: step: 992/529, loss: 0.0023503857664763927
2023-01-24 08:13:35.587336: step: 996/529, loss: 0.011985625140368938
2023-01-24 08:13:36.700746: step: 1000/529, loss: 0.002787108300253749
2023-01-24 08:13:37.780308: step: 1004/529, loss: 0.002494698390364647
2023-01-24 08:13:38.882421: step: 1008/529, loss: 0.011006790213286877
2023-01-24 08:13:40.009203: step: 1012/529, loss: 0.009234877303242683
2023-01-24 08:13:41.120085: step: 1016/529, loss: 0.017534397542476654
2023-01-24 08:13:42.220011: step: 1020/529, loss: 0.0049636405892670155
2023-01-24 08:13:43.313403: step: 1024/529, loss: 0.014070157893002033
2023-01-24 08:13:44.398197: step: 1028/529, loss: 0.004322945140302181
2023-01-24 08:13:45.480559: step: 1032/529, loss: 0.005822870414704084
2023-01-24 08:13:46.592731: step: 1036/529, loss: 0.0006528922822326422
2023-01-24 08:13:47.719995: step: 1040/529, loss: 0.012215661816298962
2023-01-24 08:13:48.858834: step: 1044/529, loss: 0.0034096734598279
2023-01-24 08:13:49.944508: step: 1048/529, loss: 0.029845722019672394
2023-01-24 08:13:51.076671: step: 1052/529, loss: 0.0019420747412368655
2023-01-24 08:13:52.190128: step: 1056/529, loss: 0.004109000787138939
2023-01-24 08:13:53.313206: step: 1060/529, loss: 0.0018830562476068735
2023-01-24 08:13:54.445952: step: 1064/529, loss: 0.010879752226173878
2023-01-24 08:13:55.549482: step: 1068/529, loss: 0.004755171947181225
2023-01-24 08:13:56.655602: step: 1072/529, loss: 0.003979586996138096
2023-01-24 08:13:57.759189: step: 1076/529, loss: 0.0029039925429970026
2023-01-24 08:13:58.849885: step: 1080/529, loss: 0.023646049201488495
2023-01-24 08:13:59.933004: step: 1084/529, loss: 0.005364066921174526
2023-01-24 08:14:01.054295: step: 1088/529, loss: 0.022765837609767914
2023-01-24 08:14:02.180957: step: 1092/529, loss: 0.003873299341648817
2023-01-24 08:14:03.290038: step: 1096/529, loss: 0.07777158170938492
2023-01-24 08:14:04.409459: step: 1100/529, loss: 0.004754194524139166
2023-01-24 08:14:05.504205: step: 1104/529, loss: 0.003386830212548375
2023-01-24 08:14:06.622016: step: 1108/529, loss: 0.004941062536090612
2023-01-24 08:14:07.710571: step: 1112/529, loss: 0.0022608221042901278
2023-01-24 08:14:08.798898: step: 1116/529, loss: 0.00821454543620348
2023-01-24 08:14:09.899491: step: 1120/529, loss: 0.0009982504416257143
2023-01-24 08:14:11.000245: step: 1124/529, loss: 0.010671604424715042
2023-01-24 08:14:12.097917: step: 1128/529, loss: 0.008055897429585457
2023-01-24 08:14:13.201752: step: 1132/529, loss: 0.003617270849645138
2023-01-24 08:14:14.320166: step: 1136/529, loss: 0.005921605974435806
2023-01-24 08:14:15.430359: step: 1140/529, loss: 0.009792027063667774
2023-01-24 08:14:16.535488: step: 1144/529, loss: 0.00025737128453329206
2023-01-24 08:14:17.645428: step: 1148/529, loss: 0.018879905343055725
2023-01-24 08:14:18.750275: step: 1152/529, loss: 0.0023168388288468122
2023-01-24 08:14:19.870066: step: 1156/529, loss: 0.00943329930305481
2023-01-24 08:14:20.958220: step: 1160/529, loss: 0.004371060524135828
2023-01-24 08:14:22.062021: step: 1164/529, loss: 0.029411058872938156
2023-01-24 08:14:23.193458: step: 1168/529, loss: 0.006453365087509155
2023-01-24 08:14:24.301121: step: 1172/529, loss: 0.0024740700609982014
2023-01-24 08:14:25.406160: step: 1176/529, loss: 0.0055062188766896725
2023-01-24 08:14:26.536876: step: 1180/529, loss: 0.003045261837542057
2023-01-24 08:14:27.629687: step: 1184/529, loss: 0.009807714261114597
2023-01-24 08:14:28.744346: step: 1188/529, loss: 0.0062722801230847836
2023-01-24 08:14:29.852718: step: 1192/529, loss: 0.01675247959792614
2023-01-24 08:14:30.981860: step: 1196/529, loss: 0.012035599909722805
2023-01-24 08:14:32.102208: step: 1200/529, loss: 0.005240924656391144
2023-01-24 08:14:33.210388: step: 1204/529, loss: 0.0027321672532707453
2023-01-24 08:14:34.322242: step: 1208/529, loss: 0.01981533132493496
2023-01-24 08:14:35.448226: step: 1212/529, loss: 0.00643549719825387
2023-01-24 08:14:36.547362: step: 1216/529, loss: 0.00613400200381875
2023-01-24 08:14:37.665151: step: 1220/529, loss: 0.03553798794746399
2023-01-24 08:14:38.773391: step: 1224/529, loss: 0.005869312211871147
2023-01-24 08:14:39.888686: step: 1228/529, loss: 0.005721408873796463
2023-01-24 08:14:41.017140: step: 1232/529, loss: 0.0073846555314958096
2023-01-24 08:14:42.114089: step: 1236/529, loss: 0.005948214791715145
2023-01-24 08:14:43.222239: step: 1240/529, loss: 0.01719503290951252
2023-01-24 08:14:44.318037: step: 1244/529, loss: 0.003266494255512953
2023-01-24 08:14:45.406771: step: 1248/529, loss: 0.005929171573370695
2023-01-24 08:14:46.516375: step: 1252/529, loss: 0.012173418886959553
2023-01-24 08:14:47.615130: step: 1256/529, loss: 0.0011466162977740169
2023-01-24 08:14:48.735113: step: 1260/529, loss: 0.03339709714055061
2023-01-24 08:14:49.836199: step: 1264/529, loss: 0.0028979526832699776
2023-01-24 08:14:50.954578: step: 1268/529, loss: 0.0034387765917927027
2023-01-24 08:14:52.072358: step: 1272/529, loss: 0.007735791150480509
2023-01-24 08:14:53.162352: step: 1276/529, loss: 0.0007798764854669571
2023-01-24 08:14:54.264625: step: 1280/529, loss: 0.0102445799857378
2023-01-24 08:14:55.394159: step: 1284/529, loss: 0.024405132979154587
2023-01-24 08:14:56.496945: step: 1288/529, loss: 0.02438303641974926
2023-01-24 08:14:57.615553: step: 1292/529, loss: 0.005531249567866325
2023-01-24 08:14:58.728052: step: 1296/529, loss: 0.009823341853916645
2023-01-24 08:14:59.847954: step: 1300/529, loss: 0.013877890072762966
2023-01-24 08:15:00.952265: step: 1304/529, loss: 0.013430802151560783
2023-01-24 08:15:02.107917: step: 1308/529, loss: 0.001124147092923522
2023-01-24 08:15:03.213743: step: 1312/529, loss: 0.005993430502712727
2023-01-24 08:15:04.316237: step: 1316/529, loss: 0.008682730607688427
2023-01-24 08:15:05.425838: step: 1320/529, loss: 0.007739542983472347
2023-01-24 08:15:06.550188: step: 1324/529, loss: 0.014505354687571526
2023-01-24 08:15:07.664596: step: 1328/529, loss: 0.01330857165157795
2023-01-24 08:15:08.760165: step: 1332/529, loss: 0.005377857945859432
2023-01-24 08:15:09.899287: step: 1336/529, loss: 0.00721074640750885
2023-01-24 08:15:10.994015: step: 1340/529, loss: 0.010000079870223999
2023-01-24 08:15:12.115533: step: 1344/529, loss: 0.0793629065155983
2023-01-24 08:15:13.242504: step: 1348/529, loss: 0.01986638642847538
2023-01-24 08:15:14.370647: step: 1352/529, loss: 0.009433782659471035
2023-01-24 08:15:15.501522: step: 1356/529, loss: 0.013776114210486412
2023-01-24 08:15:16.605890: step: 1360/529, loss: 0.008588962256908417
2023-01-24 08:15:17.701148: step: 1364/529, loss: 0.01841878890991211
2023-01-24 08:15:18.824442: step: 1368/529, loss: 0.011485453695058823
2023-01-24 08:15:19.954465: step: 1372/529, loss: 0.006351157557219267
2023-01-24 08:15:21.079504: step: 1376/529, loss: 0.004423793870955706
2023-01-24 08:15:22.196661: step: 1380/529, loss: 0.0011480154935270548
2023-01-24 08:15:23.319504: step: 1384/529, loss: 0.0015239579370245337
2023-01-24 08:15:24.429379: step: 1388/529, loss: 0.00700216693803668
2023-01-24 08:15:25.550605: step: 1392/529, loss: 0.0028549358248710632
2023-01-24 08:15:26.699339: step: 1396/529, loss: 0.0052362107671797276
2023-01-24 08:15:27.783280: step: 1400/529, loss: 0.013613940216600895
2023-01-24 08:15:28.905546: step: 1404/529, loss: 0.00564269395545125
2023-01-24 08:15:29.998318: step: 1408/529, loss: 0.0034030135720968246
2023-01-24 08:15:31.107822: step: 1412/529, loss: 0.037433601915836334
2023-01-24 08:15:32.191853: step: 1416/529, loss: 0.007563753519207239
2023-01-24 08:15:33.299356: step: 1420/529, loss: 0.010072696954011917
2023-01-24 08:15:34.405498: step: 1424/529, loss: 0.05938692390918732
2023-01-24 08:15:35.505126: step: 1428/529, loss: 0.003408244112506509
2023-01-24 08:15:36.665516: step: 1432/529, loss: 0.0016683181747794151
2023-01-24 08:15:37.784712: step: 1436/529, loss: 0.025166237726807594
2023-01-24 08:15:38.908926: step: 1440/529, loss: 0.011587515473365784
2023-01-24 08:15:40.008635: step: 1444/529, loss: 0.0030882249120622873
2023-01-24 08:15:41.142649: step: 1448/529, loss: 0.01331456657499075
2023-01-24 08:15:42.254957: step: 1452/529, loss: 0.004248378798365593
2023-01-24 08:15:43.365813: step: 1456/529, loss: 0.009153674356639385
2023-01-24 08:15:44.471092: step: 1460/529, loss: 0.0015225185779854655
2023-01-24 08:15:45.562916: step: 1464/529, loss: 0.0013907576212659478
2023-01-24 08:15:46.673940: step: 1468/529, loss: 0.021544748917222023
2023-01-24 08:15:47.763647: step: 1472/529, loss: 0.006420893594622612
2023-01-24 08:15:48.890987: step: 1476/529, loss: 0.026873959228396416
2023-01-24 08:15:50.008895: step: 1480/529, loss: 0.007260599639266729
2023-01-24 08:15:51.117819: step: 1484/529, loss: 0.008032262325286865
2023-01-24 08:15:52.218957: step: 1488/529, loss: 0.012603539042174816
2023-01-24 08:15:53.304745: step: 1492/529, loss: 0.02796679362654686
2023-01-24 08:15:54.412210: step: 1496/529, loss: 0.04258495196700096
2023-01-24 08:15:55.495094: step: 1500/529, loss: 0.002948765642940998
2023-01-24 08:15:56.588193: step: 1504/529, loss: 0.010979026556015015
2023-01-24 08:15:57.691479: step: 1508/529, loss: 0.02838038094341755
2023-01-24 08:15:58.808835: step: 1512/529, loss: 0.0045903087593615055
2023-01-24 08:15:59.952465: step: 1516/529, loss: 0.0034501003101468086
2023-01-24 08:16:01.076656: step: 1520/529, loss: 0.009295562282204628
2023-01-24 08:16:02.185509: step: 1524/529, loss: 0.007982209324836731
2023-01-24 08:16:03.324624: step: 1528/529, loss: 0.009216131642460823
2023-01-24 08:16:04.429149: step: 1532/529, loss: 0.0062230974435806274
2023-01-24 08:16:05.532818: step: 1536/529, loss: 0.007723563816398382
2023-01-24 08:16:06.624977: step: 1540/529, loss: 0.02216295152902603
2023-01-24 08:16:07.751942: step: 1544/529, loss: 0.012259969487786293
2023-01-24 08:16:08.876397: step: 1548/529, loss: 0.006923162844032049
2023-01-24 08:16:09.980393: step: 1552/529, loss: 0.0070540281012654305
2023-01-24 08:16:11.095192: step: 1556/529, loss: 0.007882323116064072
2023-01-24 08:16:12.223942: step: 1560/529, loss: 0.011779258027672768
2023-01-24 08:16:13.355226: step: 1564/529, loss: 0.01809048093855381
2023-01-24 08:16:14.464970: step: 1568/529, loss: 0.006148052867501974
2023-01-24 08:16:15.571859: step: 1572/529, loss: 0.008603012189269066
2023-01-24 08:16:16.700936: step: 1576/529, loss: 0.013636457733809948
2023-01-24 08:16:17.807747: step: 1580/529, loss: 0.011089447885751724
2023-01-24 08:16:18.955724: step: 1584/529, loss: 0.0035017789341509342
2023-01-24 08:16:20.087590: step: 1588/529, loss: 0.005013898015022278
2023-01-24 08:16:21.212522: step: 1592/529, loss: 0.02697349712252617
2023-01-24 08:16:22.326582: step: 1596/529, loss: 0.00529640493914485
2023-01-24 08:16:23.432558: step: 1600/529, loss: 0.0013109358260408044
2023-01-24 08:16:24.524695: step: 1604/529, loss: 0.016566354781389236
2023-01-24 08:16:25.646279: step: 1608/529, loss: 0.0010960629442706704
2023-01-24 08:16:26.758139: step: 1612/529, loss: 0.023096466436982155
2023-01-24 08:16:27.846394: step: 1616/529, loss: 0.010913442820310593
2023-01-24 08:16:28.973433: step: 1620/529, loss: 0.003063932992517948
2023-01-24 08:16:30.066073: step: 1624/529, loss: 0.025128396227955818
2023-01-24 08:16:31.166629: step: 1628/529, loss: 0.002802146365866065
2023-01-24 08:16:32.297364: step: 1632/529, loss: 0.005906732752919197
2023-01-24 08:16:33.399562: step: 1636/529, loss: 0.00568888895213604
2023-01-24 08:16:34.493115: step: 1640/529, loss: 0.004543485585600138
2023-01-24 08:16:35.609070: step: 1644/529, loss: 0.008256948553025723
2023-01-24 08:16:36.747225: step: 1648/529, loss: 0.007747428957372904
2023-01-24 08:16:37.848753: step: 1652/529, loss: 0.10541478544473648
2023-01-24 08:16:38.962735: step: 1656/529, loss: 0.006871631368994713
2023-01-24 08:16:40.076962: step: 1660/529, loss: 0.025203751400113106
2023-01-24 08:16:41.198889: step: 1664/529, loss: 0.007733407896012068
2023-01-24 08:16:42.313175: step: 1668/529, loss: 0.04675344377756119
2023-01-24 08:16:43.427809: step: 1672/529, loss: 0.005513573531061411
2023-01-24 08:16:44.554719: step: 1676/529, loss: 0.07805713266134262
2023-01-24 08:16:45.672471: step: 1680/529, loss: 0.003588608233258128
2023-01-24 08:16:46.813330: step: 1684/529, loss: 0.012582805007696152
2023-01-24 08:16:47.908211: step: 1688/529, loss: 0.013945032842457294
2023-01-24 08:16:49.085261: step: 1692/529, loss: 0.009176121093332767
2023-01-24 08:16:50.187878: step: 1696/529, loss: 0.0031222852412611246
2023-01-24 08:16:51.320383: step: 1700/529, loss: 0.00455207284539938
2023-01-24 08:16:52.423080: step: 1704/529, loss: 0.020229320973157883
2023-01-24 08:16:53.535446: step: 1708/529, loss: 0.019096320495009422
2023-01-24 08:16:54.649616: step: 1712/529, loss: 0.002913964679464698
2023-01-24 08:16:55.776984: step: 1716/529, loss: 0.004774861503392458
2023-01-24 08:16:56.911396: step: 1720/529, loss: 0.01010191347450018
2023-01-24 08:16:58.021537: step: 1724/529, loss: 0.006422301754355431
2023-01-24 08:16:59.106932: step: 1728/529, loss: 0.0012197574833407998
2023-01-24 08:17:00.223408: step: 1732/529, loss: 0.03624510392546654
2023-01-24 08:17:01.333126: step: 1736/529, loss: 0.0015528395306318998
2023-01-24 08:17:02.445644: step: 1740/529, loss: 0.030464252457022667
2023-01-24 08:17:03.561177: step: 1744/529, loss: 0.007331118918955326
2023-01-24 08:17:04.675180: step: 1748/529, loss: 0.004446009639650583
2023-01-24 08:17:05.778873: step: 1752/529, loss: 0.013871542178094387
2023-01-24 08:17:06.870487: step: 1756/529, loss: 0.00801624171435833
2023-01-24 08:17:07.998338: step: 1760/529, loss: 0.009121090173721313
2023-01-24 08:17:09.117542: step: 1764/529, loss: 0.013125907629728317
2023-01-24 08:17:10.218039: step: 1768/529, loss: 0.003242954146116972
2023-01-24 08:17:11.308169: step: 1772/529, loss: 0.00848349928855896
2023-01-24 08:17:12.421263: step: 1776/529, loss: 0.0009747439180500805
2023-01-24 08:17:13.529465: step: 1780/529, loss: 0.005255571566522121
2023-01-24 08:17:14.628775: step: 1784/529, loss: 0.010217031463980675
2023-01-24 08:17:15.752983: step: 1788/529, loss: 0.004849220160394907
2023-01-24 08:17:16.860036: step: 1792/529, loss: 0.008044778369367123
2023-01-24 08:17:17.968107: step: 1796/529, loss: 0.004802039358764887
2023-01-24 08:17:19.067012: step: 1800/529, loss: 0.00802613515406847
2023-01-24 08:17:20.183159: step: 1804/529, loss: 0.024547182023525238
2023-01-24 08:17:21.308645: step: 1808/529, loss: 0.002114079426974058
2023-01-24 08:17:22.394813: step: 1812/529, loss: 0.0035180984996259212
2023-01-24 08:17:23.556928: step: 1816/529, loss: 0.004937905818223953
2023-01-24 08:17:24.684612: step: 1820/529, loss: 0.0801788792014122
2023-01-24 08:17:25.795428: step: 1824/529, loss: 0.006303454749286175
2023-01-24 08:17:26.898544: step: 1828/529, loss: 0.01919054053723812
2023-01-24 08:17:28.007941: step: 1832/529, loss: 0.010505234822630882
2023-01-24 08:17:29.104629: step: 1836/529, loss: 0.007829022593796253
2023-01-24 08:17:30.209432: step: 1840/529, loss: 0.004391024820506573
2023-01-24 08:17:31.358274: step: 1844/529, loss: 0.009637479670345783
2023-01-24 08:17:32.450519: step: 1848/529, loss: 0.004310734570026398
2023-01-24 08:17:33.562322: step: 1852/529, loss: 0.004676748067140579
2023-01-24 08:17:34.681445: step: 1856/529, loss: 0.011473938822746277
2023-01-24 08:17:35.811563: step: 1860/529, loss: 0.036824990063905716
2023-01-24 08:17:36.923217: step: 1864/529, loss: 0.04672694578766823
2023-01-24 08:17:38.016553: step: 1868/529, loss: 0.006650257855653763
2023-01-24 08:17:39.126264: step: 1872/529, loss: 0.008425585925579071
2023-01-24 08:17:40.224358: step: 1876/529, loss: 0.01584876887500286
2023-01-24 08:17:41.323503: step: 1880/529, loss: 0.01270376332104206
2023-01-24 08:17:42.445484: step: 1884/529, loss: 0.03829373046755791
2023-01-24 08:17:43.542813: step: 1888/529, loss: 0.007096637040376663
2023-01-24 08:17:44.637039: step: 1892/529, loss: 0.0025302814319729805
2023-01-24 08:17:45.752114: step: 1896/529, loss: 0.00885958131402731
2023-01-24 08:17:46.850960: step: 1900/529, loss: 0.00826589297503233
2023-01-24 08:17:47.983590: step: 1904/529, loss: 0.004876809194684029
2023-01-24 08:17:49.098601: step: 1908/529, loss: 0.009124829433858395
2023-01-24 08:17:50.230083: step: 1912/529, loss: 0.02632630430161953
2023-01-24 08:17:51.345013: step: 1916/529, loss: 0.026951950043439865
2023-01-24 08:17:52.451511: step: 1920/529, loss: 0.0031709198374301195
2023-01-24 08:17:53.535072: step: 1924/529, loss: 0.01729685068130493
2023-01-24 08:17:54.639266: step: 1928/529, loss: 0.012684958055615425
2023-01-24 08:17:55.732842: step: 1932/529, loss: 0.023566385731101036
2023-01-24 08:17:56.827802: step: 1936/529, loss: 0.0077592674642801285
2023-01-24 08:17:57.952284: step: 1940/529, loss: 0.00289820390753448
2023-01-24 08:17:59.070931: step: 1944/529, loss: 0.006311857141554356
2023-01-24 08:18:00.172023: step: 1948/529, loss: 0.011788878589868546
2023-01-24 08:18:01.268423: step: 1952/529, loss: 0.01812565326690674
2023-01-24 08:18:02.362679: step: 1956/529, loss: 0.006139983888715506
2023-01-24 08:18:03.496942: step: 1960/529, loss: 0.018636690452694893
2023-01-24 08:18:04.603257: step: 1964/529, loss: 0.01315061654895544
2023-01-24 08:18:05.705362: step: 1968/529, loss: 0.021629182621836662
2023-01-24 08:18:06.826015: step: 1972/529, loss: 0.008680710569024086
2023-01-24 08:18:07.938143: step: 1976/529, loss: 0.017384130507707596
2023-01-24 08:18:09.056824: step: 1980/529, loss: 0.010095778852701187
2023-01-24 08:18:10.151251: step: 1984/529, loss: 0.007660235278308392
2023-01-24 08:18:11.260963: step: 1988/529, loss: 0.0465189553797245
2023-01-24 08:18:12.378146: step: 1992/529, loss: 0.01181329507380724
2023-01-24 08:18:13.475122: step: 1996/529, loss: 0.016556112095713615
2023-01-24 08:18:14.584720: step: 2000/529, loss: 0.011529793031513691
2023-01-24 08:18:15.687907: step: 2004/529, loss: 0.007618979085236788
2023-01-24 08:18:16.807307: step: 2008/529, loss: 0.0010885146912187338
2023-01-24 08:18:17.917970: step: 2012/529, loss: 0.004776259884238243
2023-01-24 08:18:19.045213: step: 2016/529, loss: 0.008826421573758125
2023-01-24 08:18:20.166716: step: 2020/529, loss: 0.008537566289305687
2023-01-24 08:18:21.236558: step: 2024/529, loss: 0.005056292749941349
2023-01-24 08:18:22.347780: step: 2028/529, loss: 0.051317837089300156
2023-01-24 08:18:23.453999: step: 2032/529, loss: 0.003719034604728222
2023-01-24 08:18:24.574001: step: 2036/529, loss: 0.00966801866889
2023-01-24 08:18:25.696608: step: 2040/529, loss: 0.027603691443800926
2023-01-24 08:18:26.805937: step: 2044/529, loss: 0.003011699067428708
2023-01-24 08:18:27.910332: step: 2048/529, loss: 0.004103096202015877
2023-01-24 08:18:29.019840: step: 2052/529, loss: 0.023153744637966156
2023-01-24 08:18:30.128396: step: 2056/529, loss: 0.004259122535586357
2023-01-24 08:18:31.248582: step: 2060/529, loss: 0.009866988286376
2023-01-24 08:18:32.362808: step: 2064/529, loss: 0.042463310062885284
2023-01-24 08:18:33.495592: step: 2068/529, loss: 0.01186918094754219
2023-01-24 08:18:34.609139: step: 2072/529, loss: 0.007165533024817705
2023-01-24 08:18:35.729218: step: 2076/529, loss: 0.005914414767175913
2023-01-24 08:18:36.836363: step: 2080/529, loss: 0.042310621589422226
2023-01-24 08:18:37.935405: step: 2084/529, loss: 0.018507735803723335
2023-01-24 08:18:39.054092: step: 2088/529, loss: 0.004264832008630037
2023-01-24 08:18:40.153248: step: 2092/529, loss: 0.0018066433258354664
2023-01-24 08:18:41.236389: step: 2096/529, loss: 0.004704984836280346
2023-01-24 08:18:42.347078: step: 2100/529, loss: 0.0033289070706814528
2023-01-24 08:18:43.447001: step: 2104/529, loss: 0.010304669849574566
2023-01-24 08:18:44.556636: step: 2108/529, loss: 0.0009273941395804286
2023-01-24 08:18:45.656904: step: 2112/529, loss: 0.031020477414131165
2023-01-24 08:18:46.779857: step: 2116/529, loss: 0.006843178067356348
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3775162337662338, 'r': 0.3230736649498509, 'f1': 0.34817959392345893}, 'combined': 0.25655338499623287, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.39866636732734484, 'r': 0.28466298672247153, 'f1': 0.3321547893606998}, 'combined': 0.20415367541194232, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36687876265428987, 'r': 0.33207053090340843, 'f1': 0.3486079079404308}, 'combined': 0.25686898479821213, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37854997962434817, 'r': 0.2883409290206257, 'f1': 0.32734425193290906}, 'combined': 0.2011969548465685, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 5
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:21:22.496740: step: 4/529, loss: 0.005944020580500364
2023-01-24 08:21:23.578170: step: 8/529, loss: 0.011787398718297482
2023-01-24 08:21:24.702475: step: 12/529, loss: 0.019872264936566353
2023-01-24 08:21:25.788566: step: 16/529, loss: 0.006311553996056318
2023-01-24 08:21:26.902937: step: 20/529, loss: 0.008970057591795921
2023-01-24 08:21:28.020054: step: 24/529, loss: 0.008300280198454857
2023-01-24 08:21:29.123911: step: 28/529, loss: 0.06833744049072266
2023-01-24 08:21:30.234043: step: 32/529, loss: 0.007676275447010994
2023-01-24 08:21:31.338614: step: 36/529, loss: 0.003142870496958494
2023-01-24 08:21:32.465533: step: 40/529, loss: 0.0048203133046627045
2023-01-24 08:21:33.595321: step: 44/529, loss: 0.02962135709822178
2023-01-24 08:21:34.704628: step: 48/529, loss: 0.005699853878468275
2023-01-24 08:21:35.837622: step: 52/529, loss: 0.004656209610402584
2023-01-24 08:21:36.934928: step: 56/529, loss: 0.0052919150330126286
2023-01-24 08:21:38.039550: step: 60/529, loss: 0.0022464075591415167
2023-01-24 08:21:39.128020: step: 64/529, loss: 0.01805340126156807
2023-01-24 08:21:40.219952: step: 68/529, loss: 0.002308015478774905
2023-01-24 08:21:41.308573: step: 72/529, loss: 0.010844535194337368
2023-01-24 08:21:42.419988: step: 76/529, loss: 0.0033897694665938616
2023-01-24 08:21:43.527272: step: 80/529, loss: 0.0011145416647195816
2023-01-24 08:21:44.633808: step: 84/529, loss: 0.003024139441549778
2023-01-24 08:21:45.756336: step: 88/529, loss: 0.004455516114830971
2023-01-24 08:21:46.843987: step: 92/529, loss: 0.00550863379612565
2023-01-24 08:21:47.963257: step: 96/529, loss: 0.02512248605489731
2023-01-24 08:21:49.087409: step: 100/529, loss: 0.000620989827439189
2023-01-24 08:21:50.200457: step: 104/529, loss: 0.002236340194940567
2023-01-24 08:21:51.296427: step: 108/529, loss: 0.004120348487049341
2023-01-24 08:21:52.403150: step: 112/529, loss: 0.005151495337486267
2023-01-24 08:21:53.503009: step: 116/529, loss: 0.013392942026257515
2023-01-24 08:21:54.615184: step: 120/529, loss: 0.009640827775001526
2023-01-24 08:21:55.716340: step: 124/529, loss: 0.009736905805766582
2023-01-24 08:21:56.830213: step: 128/529, loss: 0.002396953059360385
2023-01-24 08:21:57.930350: step: 132/529, loss: 0.007673532702028751
2023-01-24 08:21:59.047312: step: 136/529, loss: 0.013402070850133896
2023-01-24 08:22:00.164153: step: 140/529, loss: 0.01039112638682127
2023-01-24 08:22:01.291661: step: 144/529, loss: 0.002605579560622573
2023-01-24 08:22:02.392048: step: 148/529, loss: 0.0053550610318779945
2023-01-24 08:22:03.482720: step: 152/529, loss: 0.012103062123060226
2023-01-24 08:22:04.596305: step: 156/529, loss: 0.005834732670336962
2023-01-24 08:22:05.712533: step: 160/529, loss: 0.0028534966986626387
2023-01-24 08:22:06.818461: step: 164/529, loss: 0.0037074636202305555
2023-01-24 08:22:07.924047: step: 168/529, loss: 0.014147473499178886
2023-01-24 08:22:09.031399: step: 172/529, loss: 0.0016528520500287414
2023-01-24 08:22:10.157305: step: 176/529, loss: 0.003087915712967515
2023-01-24 08:22:11.273134: step: 180/529, loss: 0.006248785182833672
2023-01-24 08:22:12.394634: step: 184/529, loss: 0.0022147647105157375
2023-01-24 08:22:13.503845: step: 188/529, loss: 0.004827729891985655
2023-01-24 08:22:14.622174: step: 192/529, loss: 0.004445627331733704
2023-01-24 08:22:15.712641: step: 196/529, loss: 0.01315377838909626
2023-01-24 08:22:16.849555: step: 200/529, loss: 0.012174738571047783
2023-01-24 08:22:17.925844: step: 204/529, loss: 0.017549565061926842
2023-01-24 08:22:19.063289: step: 208/529, loss: 0.025793110951781273
2023-01-24 08:22:20.188743: step: 212/529, loss: 0.029153136536478996
2023-01-24 08:22:21.325476: step: 216/529, loss: 0.011854974552989006
2023-01-24 08:22:22.438985: step: 220/529, loss: 0.009827900677919388
2023-01-24 08:22:23.549153: step: 224/529, loss: 0.005242019891738892
2023-01-24 08:22:24.671129: step: 228/529, loss: 0.003118621651083231
2023-01-24 08:22:25.812145: step: 232/529, loss: 0.030991079285740852
2023-01-24 08:22:26.944292: step: 236/529, loss: 0.012195030227303505
2023-01-24 08:22:28.055627: step: 240/529, loss: 0.0043490249663591385
2023-01-24 08:22:29.188098: step: 244/529, loss: 0.0078894617035985
2023-01-24 08:22:30.304391: step: 248/529, loss: 0.011463350616395473
2023-01-24 08:22:31.441293: step: 252/529, loss: 0.007622966542840004
2023-01-24 08:22:32.561251: step: 256/529, loss: 0.006223446689546108
2023-01-24 08:22:33.668533: step: 260/529, loss: 0.015137385576963425
2023-01-24 08:22:34.769868: step: 264/529, loss: 0.00604736665263772
2023-01-24 08:22:35.898898: step: 268/529, loss: 0.00420906487852335
2023-01-24 08:22:36.988663: step: 272/529, loss: 0.0071423714980483055
2023-01-24 08:22:38.081885: step: 276/529, loss: 0.0020656504202634096
2023-01-24 08:22:39.185337: step: 280/529, loss: 0.008240027353167534
2023-01-24 08:22:40.286738: step: 284/529, loss: 0.021565720438957214
2023-01-24 08:22:41.440803: step: 288/529, loss: 0.019359055906534195
2023-01-24 08:22:42.563207: step: 292/529, loss: 0.007886834442615509
2023-01-24 08:22:43.654862: step: 296/529, loss: 0.0012284136610105634
2023-01-24 08:22:44.766551: step: 300/529, loss: 0.005962691735476255
2023-01-24 08:22:45.878998: step: 304/529, loss: 0.0025677671656012535
2023-01-24 08:22:47.000173: step: 308/529, loss: 0.010364501737058163
2023-01-24 08:22:48.118154: step: 312/529, loss: 0.019816305488348007
2023-01-24 08:22:49.230375: step: 316/529, loss: 0.011486060917377472
2023-01-24 08:22:50.338461: step: 320/529, loss: 0.00010884933726629242
2023-01-24 08:22:51.444766: step: 324/529, loss: 0.008167089894413948
2023-01-24 08:22:52.538594: step: 328/529, loss: 0.004088517278432846
2023-01-24 08:22:53.631888: step: 332/529, loss: 0.010634136386215687
2023-01-24 08:22:54.749907: step: 336/529, loss: 0.003961325157433748
2023-01-24 08:22:55.848471: step: 340/529, loss: 0.0021540720481425524
2023-01-24 08:22:56.959748: step: 344/529, loss: 0.0035539381206035614
2023-01-24 08:22:58.070154: step: 348/529, loss: 0.0037011802196502686
2023-01-24 08:22:59.173129: step: 352/529, loss: 0.006871826481074095
2023-01-24 08:23:00.284426: step: 356/529, loss: 0.004165771417319775
2023-01-24 08:23:01.401899: step: 360/529, loss: 0.008932098746299744
2023-01-24 08:23:02.496631: step: 364/529, loss: 0.011896781623363495
2023-01-24 08:23:03.602976: step: 368/529, loss: 0.0013712149811908603
2023-01-24 08:23:04.712577: step: 372/529, loss: 0.008989798836410046
2023-01-24 08:23:05.828716: step: 376/529, loss: 0.00463844882324338
2023-01-24 08:23:06.947630: step: 380/529, loss: 0.005348381120711565
2023-01-24 08:23:08.070019: step: 384/529, loss: 0.0030955979600548744
2023-01-24 08:23:09.160248: step: 388/529, loss: 0.004573538433760405
2023-01-24 08:23:10.262852: step: 392/529, loss: 0.0
2023-01-24 08:23:11.369191: step: 396/529, loss: 0.0076035400852561
2023-01-24 08:23:12.489072: step: 400/529, loss: 0.0024134861305356026
2023-01-24 08:23:13.606811: step: 404/529, loss: 0.006922394968569279
2023-01-24 08:23:14.703833: step: 408/529, loss: 0.0057018413208425045
2023-01-24 08:23:15.806190: step: 412/529, loss: 0.017347754910588264
2023-01-24 08:23:16.915850: step: 416/529, loss: 0.04166816920042038
2023-01-24 08:23:18.033283: step: 420/529, loss: 0.0021120202727615833
2023-01-24 08:23:19.134990: step: 424/529, loss: 0.0009686889825388789
2023-01-24 08:23:20.251867: step: 428/529, loss: 0.02227970026433468
2023-01-24 08:23:21.335771: step: 432/529, loss: 0.012530308216810226
2023-01-24 08:23:22.419515: step: 436/529, loss: 0.0006451040389947593
2023-01-24 08:23:23.544531: step: 440/529, loss: 0.01064095925539732
2023-01-24 08:23:24.622842: step: 444/529, loss: 0.0058979131281375885
2023-01-24 08:23:25.730828: step: 448/529, loss: 0.008687878027558327
2023-01-24 08:23:26.860363: step: 452/529, loss: 0.0018891702638939023
2023-01-24 08:23:27.966776: step: 456/529, loss: 0.0035672204103320837
2023-01-24 08:23:29.080034: step: 460/529, loss: 0.014552082866430283
2023-01-24 08:23:30.180875: step: 464/529, loss: 0.03941059112548828
2023-01-24 08:23:31.273694: step: 468/529, loss: 0.006344751454889774
2023-01-24 08:23:32.373284: step: 472/529, loss: 0.012980048544704914
2023-01-24 08:23:33.508021: step: 476/529, loss: 0.00494886701926589
2023-01-24 08:23:34.648760: step: 480/529, loss: 0.020085686817765236
2023-01-24 08:23:35.761382: step: 484/529, loss: 0.002725489903241396
2023-01-24 08:23:36.864550: step: 488/529, loss: 0.01815321296453476
2023-01-24 08:23:37.971139: step: 492/529, loss: 0.002221002709120512
2023-01-24 08:23:39.059617: step: 496/529, loss: 8.186974446289241e-05
2023-01-24 08:23:40.177570: step: 500/529, loss: 0.03334472328424454
2023-01-24 08:23:41.280236: step: 504/529, loss: 0.01682993210852146
2023-01-24 08:23:42.381648: step: 508/529, loss: 0.004078906495124102
2023-01-24 08:23:43.463638: step: 512/529, loss: 0.039665382355451584
2023-01-24 08:23:44.567001: step: 516/529, loss: 0.028239037841558456
2023-01-24 08:23:45.686168: step: 520/529, loss: 0.020282002165913582
2023-01-24 08:23:46.799801: step: 524/529, loss: 0.0018099588342010975
2023-01-24 08:23:47.892855: step: 528/529, loss: 0.002890066709369421
2023-01-24 08:23:48.984634: step: 532/529, loss: 0.005001302808523178
2023-01-24 08:23:50.094695: step: 536/529, loss: 0.004335480742156506
2023-01-24 08:23:51.199259: step: 540/529, loss: 0.010238793678581715
2023-01-24 08:23:52.310270: step: 544/529, loss: 0.0036698170006275177
2023-01-24 08:23:53.422490: step: 548/529, loss: 0.010645860806107521
2023-01-24 08:23:54.534050: step: 552/529, loss: 0.039910122752189636
2023-01-24 08:23:55.621385: step: 556/529, loss: 0.0036725865211337805
2023-01-24 08:23:56.711705: step: 560/529, loss: 0.03352321311831474
2023-01-24 08:23:57.827295: step: 564/529, loss: 0.01813039928674698
2023-01-24 08:23:58.934401: step: 568/529, loss: 0.01357536856085062
2023-01-24 08:24:00.023158: step: 572/529, loss: 0.006745693739503622
2023-01-24 08:24:01.139544: step: 576/529, loss: 0.0040192389860749245
2023-01-24 08:24:02.243142: step: 580/529, loss: 0.007827007211744785
2023-01-24 08:24:03.362418: step: 584/529, loss: 0.0016290126368403435
2023-01-24 08:24:04.478176: step: 588/529, loss: 0.02934255823493004
2023-01-24 08:24:05.572448: step: 592/529, loss: 0.03686949983239174
2023-01-24 08:24:06.685280: step: 596/529, loss: 0.011240099556744099
2023-01-24 08:24:07.797364: step: 600/529, loss: 0.0019065714441239834
2023-01-24 08:24:08.890094: step: 604/529, loss: 0.004999896045774221
2023-01-24 08:24:10.000815: step: 608/529, loss: 0.04072859510779381
2023-01-24 08:24:11.120480: step: 612/529, loss: 0.0171133391559124
2023-01-24 08:24:12.221190: step: 616/529, loss: 0.006937309168279171
2023-01-24 08:24:13.317194: step: 620/529, loss: 0.014709793031215668
2023-01-24 08:24:14.415592: step: 624/529, loss: 0.00959252379834652
2023-01-24 08:24:15.558204: step: 628/529, loss: 0.02299790270626545
2023-01-24 08:24:16.666569: step: 632/529, loss: 0.0024731531739234924
2023-01-24 08:24:17.782610: step: 636/529, loss: 0.012275369837880135
2023-01-24 08:24:18.897689: step: 640/529, loss: 0.006461271550506353
2023-01-24 08:24:20.022831: step: 644/529, loss: 0.007846472784876823
2023-01-24 08:24:21.122318: step: 648/529, loss: 0.007151693105697632
2023-01-24 08:24:22.213764: step: 652/529, loss: 0.002280886285007
2023-01-24 08:24:23.315612: step: 656/529, loss: 0.0048790681175887585
2023-01-24 08:24:24.422943: step: 660/529, loss: 0.06166310980916023
2023-01-24 08:24:25.534957: step: 664/529, loss: 0.012223022058606148
2023-01-24 08:24:26.645302: step: 668/529, loss: 0.004073896445333958
2023-01-24 08:24:27.759794: step: 672/529, loss: 0.04534912109375
2023-01-24 08:24:28.855159: step: 676/529, loss: 0.00784063246101141
2023-01-24 08:24:29.945940: step: 680/529, loss: 0.00543764466419816
2023-01-24 08:24:31.062166: step: 684/529, loss: 0.017082558944821358
2023-01-24 08:24:32.156763: step: 688/529, loss: 0.0033302265219390392
2023-01-24 08:24:33.280543: step: 692/529, loss: 0.01859324239194393
2023-01-24 08:24:34.407112: step: 696/529, loss: 0.005464591085910797
2023-01-24 08:24:35.491897: step: 700/529, loss: 0.004670901224017143
2023-01-24 08:24:36.601094: step: 704/529, loss: 0.019552048295736313
2023-01-24 08:24:37.713792: step: 708/529, loss: 0.01808786392211914
2023-01-24 08:24:38.834909: step: 712/529, loss: 0.002900754800066352
2023-01-24 08:24:39.925263: step: 716/529, loss: 0.0007903499063104391
2023-01-24 08:24:41.048672: step: 720/529, loss: 0.012239975854754448
2023-01-24 08:24:42.141170: step: 724/529, loss: 0.008969036862254143
2023-01-24 08:24:43.241924: step: 728/529, loss: 0.0053934622555971146
2023-01-24 08:24:44.347913: step: 732/529, loss: 0.019142204895615578
2023-01-24 08:24:45.438557: step: 736/529, loss: 0.007520847953855991
2023-01-24 08:24:46.573129: step: 740/529, loss: 0.011696289293467999
2023-01-24 08:24:47.674410: step: 744/529, loss: 0.04023462533950806
2023-01-24 08:24:48.805306: step: 748/529, loss: 0.005143493413925171
2023-01-24 08:24:49.908010: step: 752/529, loss: 0.012811396270990372
2023-01-24 08:24:51.035700: step: 756/529, loss: 0.0027981214225292206
2023-01-24 08:24:52.156170: step: 760/529, loss: 1.410916775057558e-05
2023-01-24 08:24:53.260755: step: 764/529, loss: 0.02011924237012863
2023-01-24 08:24:54.363371: step: 768/529, loss: 0.001113583450205624
2023-01-24 08:24:55.494301: step: 772/529, loss: 0.0010251770727336407
2023-01-24 08:24:56.607367: step: 776/529, loss: 0.03435317799448967
2023-01-24 08:24:57.715889: step: 780/529, loss: 0.020054392516613007
2023-01-24 08:24:58.798686: step: 784/529, loss: 0.0007251350907608867
2023-01-24 08:24:59.895405: step: 788/529, loss: 0.004094707313925028
2023-01-24 08:25:00.993982: step: 792/529, loss: 0.0008153258240781724
2023-01-24 08:25:02.121363: step: 796/529, loss: 0.03480057045817375
2023-01-24 08:25:03.228316: step: 800/529, loss: 0.01276328694075346
2023-01-24 08:25:04.348606: step: 804/529, loss: 0.0058260331861674786
2023-01-24 08:25:05.439015: step: 808/529, loss: 0.014401491731405258
2023-01-24 08:25:06.526854: step: 812/529, loss: 0.0006542746559716761
2023-01-24 08:25:07.613224: step: 816/529, loss: 0.006432477850466967
2023-01-24 08:25:08.700958: step: 820/529, loss: 0.00623157387599349
2023-01-24 08:25:09.800437: step: 824/529, loss: 0.09228091686964035
2023-01-24 08:25:10.911568: step: 828/529, loss: 0.011270182207226753
2023-01-24 08:25:12.016844: step: 832/529, loss: 0.012300697155296803
2023-01-24 08:25:13.126868: step: 836/529, loss: 0.0032369368709623814
2023-01-24 08:25:14.216634: step: 840/529, loss: 0.015315155498683453
2023-01-24 08:25:15.324891: step: 844/529, loss: 0.0059449211694300175
2023-01-24 08:25:16.419067: step: 848/529, loss: 0.004831463564187288
2023-01-24 08:25:17.538797: step: 852/529, loss: 0.007845873013138771
2023-01-24 08:25:18.645751: step: 856/529, loss: 0.0031097382307052612
2023-01-24 08:25:19.764069: step: 860/529, loss: 0.009619108401238918
2023-01-24 08:25:20.875512: step: 864/529, loss: 0.00813919585198164
2023-01-24 08:25:22.001213: step: 868/529, loss: 0.0012072770623490214
2023-01-24 08:25:23.111594: step: 872/529, loss: 0.0077570960856974125
2023-01-24 08:25:24.242717: step: 876/529, loss: 0.01115875132381916
2023-01-24 08:25:25.365100: step: 880/529, loss: 0.04828742891550064
2023-01-24 08:25:26.497857: step: 884/529, loss: 0.00378294731490314
2023-01-24 08:25:27.619814: step: 888/529, loss: 0.005132909864187241
2023-01-24 08:25:28.724619: step: 892/529, loss: 0.021029513329267502
2023-01-24 08:25:29.836357: step: 896/529, loss: 0.00169015780556947
2023-01-24 08:25:30.930195: step: 900/529, loss: 0.01202309038490057
2023-01-24 08:25:32.023675: step: 904/529, loss: 0.027538206428289413
2023-01-24 08:25:33.111131: step: 908/529, loss: 0.007902281358838081
2023-01-24 08:25:34.217086: step: 912/529, loss: 0.0072731212712824345
2023-01-24 08:25:35.334129: step: 916/529, loss: 0.0025516508612781763
2023-01-24 08:25:36.432808: step: 920/529, loss: 0.009487972594797611
2023-01-24 08:25:37.527205: step: 924/529, loss: 0.0033455428201705217
2023-01-24 08:25:38.614241: step: 928/529, loss: 0.005422177724540234
2023-01-24 08:25:39.749567: step: 932/529, loss: 0.016131406649947166
2023-01-24 08:25:40.838805: step: 936/529, loss: 0.046241506934165955
2023-01-24 08:25:41.942126: step: 940/529, loss: 0.0024307575076818466
2023-01-24 08:25:43.056220: step: 944/529, loss: 0.0016261221608147025
2023-01-24 08:25:44.160467: step: 948/529, loss: 0.032790955156087875
2023-01-24 08:25:45.249208: step: 952/529, loss: 0.011490444652736187
2023-01-24 08:25:46.379584: step: 956/529, loss: 0.014561083167791367
2023-01-24 08:25:47.481409: step: 960/529, loss: 0.025195373222231865
2023-01-24 08:25:48.612269: step: 964/529, loss: 0.003199903294444084
2023-01-24 08:25:49.702923: step: 968/529, loss: 0.004980687517672777
2023-01-24 08:25:50.800912: step: 972/529, loss: 0.004482956137508154
2023-01-24 08:25:51.916248: step: 976/529, loss: 0.004602277185767889
2023-01-24 08:25:53.047390: step: 980/529, loss: 0.012132798321545124
2023-01-24 08:25:54.162637: step: 984/529, loss: 0.023986024782061577
2023-01-24 08:25:55.301549: step: 988/529, loss: 0.005697285756468773
2023-01-24 08:25:56.386034: step: 992/529, loss: 0.0015940701123327017
2023-01-24 08:25:57.488540: step: 996/529, loss: 0.006752361543476582
2023-01-24 08:25:58.617308: step: 1000/529, loss: 0.007739895489066839
2023-01-24 08:25:59.729648: step: 1004/529, loss: 0.015170280821621418
2023-01-24 08:26:00.833460: step: 1008/529, loss: 0.003680730937048793
2023-01-24 08:26:01.960069: step: 1012/529, loss: 0.005778642371296883
2023-01-24 08:26:03.065403: step: 1016/529, loss: 0.007206473033875227
2023-01-24 08:26:04.176687: step: 1020/529, loss: 0.0047554741613566875
2023-01-24 08:26:05.264448: step: 1024/529, loss: 0.03196348622441292
2023-01-24 08:26:06.365411: step: 1028/529, loss: 0.011443670839071274
2023-01-24 08:26:07.480883: step: 1032/529, loss: 0.012728915549814701
2023-01-24 08:26:08.573807: step: 1036/529, loss: 0.00030084195896051824
2023-01-24 08:26:09.671720: step: 1040/529, loss: 0.0028281589038670063
2023-01-24 08:26:10.795242: step: 1044/529, loss: 0.007238818798214197
2023-01-24 08:26:11.903110: step: 1048/529, loss: 0.008840660564601421
2023-01-24 08:26:13.038501: step: 1052/529, loss: 0.01645452156662941
2023-01-24 08:26:14.120222: step: 1056/529, loss: 0.010672023519873619
2023-01-24 08:26:15.232293: step: 1060/529, loss: 0.08599682152271271
2023-01-24 08:26:16.325632: step: 1064/529, loss: 0.014405096881091595
2023-01-24 08:26:17.440535: step: 1068/529, loss: 0.008899947628378868
2023-01-24 08:26:18.557518: step: 1072/529, loss: 0.008222026750445366
2023-01-24 08:26:19.651983: step: 1076/529, loss: 0.00418322067707777
2023-01-24 08:26:20.750593: step: 1080/529, loss: 0.009708245284855366
2023-01-24 08:26:21.837732: step: 1084/529, loss: 0.028555525466799736
2023-01-24 08:26:22.940937: step: 1088/529, loss: 0.0147315738722682
2023-01-24 08:26:24.050759: step: 1092/529, loss: 0.007116028107702732
2023-01-24 08:26:25.177926: step: 1096/529, loss: 0.02818264439702034
2023-01-24 08:26:26.295804: step: 1100/529, loss: 0.0023795946035534143
2023-01-24 08:26:27.432924: step: 1104/529, loss: 0.011722657829523087
2023-01-24 08:26:28.514241: step: 1108/529, loss: 0.010309661738574505
2023-01-24 08:26:29.602883: step: 1112/529, loss: 0.015570037066936493
2023-01-24 08:26:30.707083: step: 1116/529, loss: 0.00650654174387455
2023-01-24 08:26:31.816325: step: 1120/529, loss: 0.007435745093971491
2023-01-24 08:26:32.929017: step: 1124/529, loss: 0.05043143406510353
2023-01-24 08:26:34.028298: step: 1128/529, loss: 0.02381957322359085
2023-01-24 08:26:35.146920: step: 1132/529, loss: 0.015333091840147972
2023-01-24 08:26:36.242269: step: 1136/529, loss: 0.007082587573677301
2023-01-24 08:26:37.354931: step: 1140/529, loss: 0.01254449225962162
2023-01-24 08:26:38.455589: step: 1144/529, loss: 0.009702915325760841
2023-01-24 08:26:39.558338: step: 1148/529, loss: 0.011501430533826351
2023-01-24 08:26:40.652758: step: 1152/529, loss: 0.008191782981157303
2023-01-24 08:26:41.750375: step: 1156/529, loss: 0.007531412877142429
2023-01-24 08:26:42.872664: step: 1160/529, loss: 0.036406949162483215
2023-01-24 08:26:43.979902: step: 1164/529, loss: 0.01686202920973301
2023-01-24 08:26:45.084442: step: 1168/529, loss: 0.08043814450502396
2023-01-24 08:26:46.212859: step: 1172/529, loss: 0.002022986300289631
2023-01-24 08:26:47.307785: step: 1176/529, loss: 0.0037562139332294464
2023-01-24 08:26:48.388549: step: 1180/529, loss: 0.001928901532664895
2023-01-24 08:26:49.488818: step: 1184/529, loss: 0.0026344051584601402
2023-01-24 08:26:50.652783: step: 1188/529, loss: 0.012846373952925205
2023-01-24 08:26:51.757433: step: 1192/529, loss: 0.0033279662020504475
2023-01-24 08:26:52.876715: step: 1196/529, loss: 0.005176838953047991
2023-01-24 08:26:53.985953: step: 1200/529, loss: 0.007989929988980293
2023-01-24 08:26:55.097874: step: 1204/529, loss: 0.00819362886250019
2023-01-24 08:26:56.200949: step: 1208/529, loss: 0.005794148426502943
2023-01-24 08:26:57.320929: step: 1212/529, loss: 0.015545502305030823
2023-01-24 08:26:58.452394: step: 1216/529, loss: 0.002302897395566106
2023-01-24 08:26:59.556953: step: 1220/529, loss: 0.002769102808088064
2023-01-24 08:27:00.669213: step: 1224/529, loss: 0.007388010621070862
2023-01-24 08:27:01.767275: step: 1228/529, loss: 0.03529055789113045
2023-01-24 08:27:02.913428: step: 1232/529, loss: 0.018408609554171562
2023-01-24 08:27:04.032443: step: 1236/529, loss: 0.010375368408858776
2023-01-24 08:27:05.131523: step: 1240/529, loss: 0.006846352480351925
2023-01-24 08:27:06.228072: step: 1244/529, loss: 0.010709736496210098
2023-01-24 08:27:07.332366: step: 1248/529, loss: 0.005159872584044933
2023-01-24 08:27:08.438765: step: 1252/529, loss: 0.004337864462286234
2023-01-24 08:27:09.540785: step: 1256/529, loss: 0.040999140590429306
2023-01-24 08:27:10.654348: step: 1260/529, loss: 0.0399836003780365
2023-01-24 08:27:11.797102: step: 1264/529, loss: 0.033606402575969696
2023-01-24 08:27:12.883889: step: 1268/529, loss: 0.003775114892050624
2023-01-24 08:27:13.991014: step: 1272/529, loss: 0.002228394616395235
2023-01-24 08:27:15.102434: step: 1276/529, loss: 0.007961426861584187
2023-01-24 08:27:16.202962: step: 1280/529, loss: 0.006111622788012028
2023-01-24 08:27:17.313856: step: 1284/529, loss: 0.004772203974425793
2023-01-24 08:27:18.409259: step: 1288/529, loss: 0.021087775006890297
2023-01-24 08:27:19.534706: step: 1292/529, loss: 0.02013617940247059
2023-01-24 08:27:20.647982: step: 1296/529, loss: 0.0033751027658581734
2023-01-24 08:27:21.748736: step: 1300/529, loss: 0.0056016636081039906
2023-01-24 08:27:22.869028: step: 1304/529, loss: 0.004481578711420298
2023-01-24 08:27:23.984745: step: 1308/529, loss: 0.047987911850214005
2023-01-24 08:27:25.087757: step: 1312/529, loss: 0.005470435135066509
2023-01-24 08:27:26.182169: step: 1316/529, loss: 0.0074748448096215725
2023-01-24 08:27:27.306884: step: 1320/529, loss: 0.01324130967259407
2023-01-24 08:27:28.427062: step: 1324/529, loss: 0.0027180227916687727
2023-01-24 08:27:29.531899: step: 1328/529, loss: 0.0033113453537225723
2023-01-24 08:27:30.641214: step: 1332/529, loss: 0.005601783748716116
2023-01-24 08:27:31.747096: step: 1336/529, loss: 0.06927123665809631
2023-01-24 08:27:32.890052: step: 1340/529, loss: 0.003348682541400194
2023-01-24 08:27:33.987599: step: 1344/529, loss: 0.007403103169053793
2023-01-24 08:27:35.128441: step: 1348/529, loss: 0.0058478242717683315
2023-01-24 08:27:36.238635: step: 1352/529, loss: 0.007413605228066444
2023-01-24 08:27:37.361707: step: 1356/529, loss: 0.004356472287327051
2023-01-24 08:27:38.464962: step: 1360/529, loss: 0.0012251229491084814
2023-01-24 08:27:39.570656: step: 1364/529, loss: 0.009137889370322227
2023-01-24 08:27:40.671815: step: 1368/529, loss: 0.00401352858170867
2023-01-24 08:27:41.774828: step: 1372/529, loss: 0.01571653038263321
2023-01-24 08:27:42.890876: step: 1376/529, loss: 0.006919472478330135
2023-01-24 08:27:43.996256: step: 1380/529, loss: 0.009047403931617737
2023-01-24 08:27:45.121226: step: 1384/529, loss: 0.004000944551080465
2023-01-24 08:27:46.221256: step: 1388/529, loss: 0.0016980344662442803
2023-01-24 08:27:47.347931: step: 1392/529, loss: 0.004459714982658625
2023-01-24 08:27:48.448501: step: 1396/529, loss: 0.0028377303387969732
2023-01-24 08:27:49.559608: step: 1400/529, loss: 0.0
2023-01-24 08:27:50.661214: step: 1404/529, loss: 0.005838384386152029
2023-01-24 08:27:51.762798: step: 1408/529, loss: 0.004882547073066235
2023-01-24 08:27:52.876454: step: 1412/529, loss: 0.006299017928540707
2023-01-24 08:27:53.979695: step: 1416/529, loss: 0.006627513561397791
2023-01-24 08:27:55.081479: step: 1420/529, loss: 0.0
2023-01-24 08:27:56.193361: step: 1424/529, loss: 0.0052241915836930275
2023-01-24 08:27:57.281953: step: 1428/529, loss: 0.0
2023-01-24 08:27:58.405679: step: 1432/529, loss: 0.006132422015070915
2023-01-24 08:27:59.544736: step: 1436/529, loss: 0.00824801716953516
2023-01-24 08:28:00.662495: step: 1440/529, loss: 0.01043170690536499
2023-01-24 08:28:01.759328: step: 1444/529, loss: 0.011481354013085365
2023-01-24 08:28:02.882483: step: 1448/529, loss: 0.009087396785616875
2023-01-24 08:28:03.977120: step: 1452/529, loss: 0.0005475827492773533
2023-01-24 08:28:05.083217: step: 1456/529, loss: 0.021182693541049957
2023-01-24 08:28:06.176292: step: 1460/529, loss: 0.0019548223353922367
2023-01-24 08:28:07.314331: step: 1464/529, loss: 0.06760632991790771
2023-01-24 08:28:08.412817: step: 1468/529, loss: 0.010388791561126709
2023-01-24 08:28:09.519116: step: 1472/529, loss: 0.006924397777765989
2023-01-24 08:28:10.625293: step: 1476/529, loss: 0.01615745760500431
2023-01-24 08:28:11.704481: step: 1480/529, loss: 0.0034435386769473553
2023-01-24 08:28:12.807763: step: 1484/529, loss: 0.005169328302145004
2023-01-24 08:28:13.916424: step: 1488/529, loss: 0.0073610697872936726
2023-01-24 08:28:15.047926: step: 1492/529, loss: 0.020026110112667084
2023-01-24 08:28:16.139888: step: 1496/529, loss: 0.012640643864870071
2023-01-24 08:28:17.235641: step: 1500/529, loss: 0.004735766910016537
2023-01-24 08:28:18.386017: step: 1504/529, loss: 0.005756611004471779
2023-01-24 08:28:19.520328: step: 1508/529, loss: 0.0024541865568608046
2023-01-24 08:28:20.615038: step: 1512/529, loss: 0.005774150602519512
2023-01-24 08:28:21.730320: step: 1516/529, loss: 0.03664577379822731
2023-01-24 08:28:22.840980: step: 1520/529, loss: 0.010698582977056503
2023-01-24 08:28:23.928445: step: 1524/529, loss: 0.0069966986775398254
2023-01-24 08:28:25.061000: step: 1528/529, loss: 0.03440531715750694
2023-01-24 08:28:26.182531: step: 1532/529, loss: 0.01456489972770214
2023-01-24 08:28:27.271819: step: 1536/529, loss: 0.018541404977440834
2023-01-24 08:28:28.364070: step: 1540/529, loss: 0.018075400963425636
2023-01-24 08:28:29.492528: step: 1544/529, loss: 0.005095444619655609
2023-01-24 08:28:30.592816: step: 1548/529, loss: 0.003705532755702734
2023-01-24 08:28:31.731304: step: 1552/529, loss: 0.002478782320395112
2023-01-24 08:28:32.871001: step: 1556/529, loss: 0.005461443215608597
2023-01-24 08:28:33.970254: step: 1560/529, loss: 0.1274636834859848
2023-01-24 08:28:35.065465: step: 1564/529, loss: 0.003411645768210292
2023-01-24 08:28:36.163223: step: 1568/529, loss: 0.009192973375320435
2023-01-24 08:28:37.274905: step: 1572/529, loss: 0.008603168651461601
2023-01-24 08:28:38.373193: step: 1576/529, loss: 0.005672864615917206
2023-01-24 08:28:39.498610: step: 1580/529, loss: 0.013235931284725666
2023-01-24 08:28:40.594156: step: 1584/529, loss: 0.006756671238690615
2023-01-24 08:28:41.692083: step: 1588/529, loss: 0.00015990881365723908
2023-01-24 08:28:42.784242: step: 1592/529, loss: 0.009757466614246368
2023-01-24 08:28:43.902592: step: 1596/529, loss: 0.004599540028721094
2023-01-24 08:28:44.991561: step: 1600/529, loss: 0.0033793197944760323
2023-01-24 08:28:46.091669: step: 1604/529, loss: 0.0013420956674963236
2023-01-24 08:28:47.176213: step: 1608/529, loss: 0.01148051768541336
2023-01-24 08:28:48.316874: step: 1612/529, loss: 0.0010839785682037473
2023-01-24 08:28:49.418139: step: 1616/529, loss: 0.006117976736277342
2023-01-24 08:28:50.540639: step: 1620/529, loss: 0.006065054796636105
2023-01-24 08:28:51.641962: step: 1624/529, loss: 0.01303850393742323
2023-01-24 08:28:52.756694: step: 1628/529, loss: 0.006825159303843975
2023-01-24 08:28:53.850503: step: 1632/529, loss: 0.039214178919792175
2023-01-24 08:28:54.929632: step: 1636/529, loss: 0.02118976041674614
2023-01-24 08:28:56.037792: step: 1640/529, loss: 0.004901760257780552
2023-01-24 08:28:57.135080: step: 1644/529, loss: 0.017291145399212837
2023-01-24 08:28:58.232533: step: 1648/529, loss: 0.013679240830242634
2023-01-24 08:28:59.339613: step: 1652/529, loss: 0.005540389567613602
2023-01-24 08:29:00.435531: step: 1656/529, loss: 0.0013256166130304337
2023-01-24 08:29:01.538752: step: 1660/529, loss: 0.07681383192539215
2023-01-24 08:29:02.638316: step: 1664/529, loss: 0.02331751212477684
2023-01-24 08:29:03.746695: step: 1668/529, loss: 0.0029005850665271282
2023-01-24 08:29:04.866081: step: 1672/529, loss: 0.0011654160916805267
2023-01-24 08:29:05.997411: step: 1676/529, loss: 0.0011839760700240731
2023-01-24 08:29:07.135058: step: 1680/529, loss: 0.028308244422078133
2023-01-24 08:29:08.247799: step: 1684/529, loss: 0.0032881482038646936
2023-01-24 08:29:09.349662: step: 1688/529, loss: 0.0014153735246509314
2023-01-24 08:29:10.454149: step: 1692/529, loss: 0.011508672498166561
2023-01-24 08:29:11.568463: step: 1696/529, loss: 0.008085059002041817
2023-01-24 08:29:12.662248: step: 1700/529, loss: 0.011574369855225086
2023-01-24 08:29:13.783006: step: 1704/529, loss: 0.03143833950161934
2023-01-24 08:29:14.898157: step: 1708/529, loss: 0.004696979187428951
2023-01-24 08:29:16.023873: step: 1712/529, loss: 0.006900436244904995
2023-01-24 08:29:17.155417: step: 1716/529, loss: 0.0028517390601336956
2023-01-24 08:29:18.268518: step: 1720/529, loss: 0.0016723640728741884
2023-01-24 08:29:19.366619: step: 1724/529, loss: 0.0006003755843266845
2023-01-24 08:29:20.453158: step: 1728/529, loss: 0.001794571871869266
2023-01-24 08:29:21.561608: step: 1732/529, loss: 0.004456062335520983
2023-01-24 08:29:22.662797: step: 1736/529, loss: 0.016209375113248825
2023-01-24 08:29:23.782697: step: 1740/529, loss: 0.010823754593729973
2023-01-24 08:29:24.920337: step: 1744/529, loss: 0.011083311401307583
2023-01-24 08:29:26.030204: step: 1748/529, loss: 0.00016748525376897305
2023-01-24 08:29:27.158643: step: 1752/529, loss: 0.01249956525862217
2023-01-24 08:29:28.297426: step: 1756/529, loss: 0.0006623414810746908
2023-01-24 08:29:29.383774: step: 1760/529, loss: 0.00020094467618037015
2023-01-24 08:29:30.468462: step: 1764/529, loss: 0.0019419906893745065
2023-01-24 08:29:31.568606: step: 1768/529, loss: 0.06702131778001785
2023-01-24 08:29:32.702069: step: 1772/529, loss: 0.01007301639765501
2023-01-24 08:29:33.827625: step: 1776/529, loss: 0.04495028406381607
2023-01-24 08:29:34.940631: step: 1780/529, loss: 0.001488852663896978
2023-01-24 08:29:36.066788: step: 1784/529, loss: 0.004896989557892084
2023-01-24 08:29:37.176944: step: 1788/529, loss: 0.003095545805990696
2023-01-24 08:29:38.252302: step: 1792/529, loss: 0.002195939887315035
2023-01-24 08:29:39.340108: step: 1796/529, loss: 0.0036110514774918556
2023-01-24 08:29:40.485160: step: 1800/529, loss: 0.0278365109115839
2023-01-24 08:29:41.600070: step: 1804/529, loss: 0.00488294055685401
2023-01-24 08:29:42.703237: step: 1808/529, loss: 0.08174276351928711
2023-01-24 08:29:43.792530: step: 1812/529, loss: 0.0004541809903457761
2023-01-24 08:29:44.951399: step: 1816/529, loss: 0.007615325972437859
2023-01-24 08:29:46.050812: step: 1820/529, loss: 0.04389224573969841
2023-01-24 08:29:47.150852: step: 1824/529, loss: 0.021634459495544434
2023-01-24 08:29:48.276597: step: 1828/529, loss: 0.00733558926731348
2023-01-24 08:29:49.384096: step: 1832/529, loss: 0.020841460675001144
2023-01-24 08:29:50.492043: step: 1836/529, loss: 0.0019189510494470596
2023-01-24 08:29:51.609562: step: 1840/529, loss: 0.02001775987446308
2023-01-24 08:29:52.702811: step: 1844/529, loss: 0.008444736711680889
2023-01-24 08:29:53.813884: step: 1848/529, loss: 0.0018344405107200146
2023-01-24 08:29:54.888874: step: 1852/529, loss: 0.015778839588165283
2023-01-24 08:29:55.999506: step: 1856/529, loss: 0.0066888462752103806
2023-01-24 08:29:57.111964: step: 1860/529, loss: 0.02231615222990513
2023-01-24 08:29:58.198337: step: 1864/529, loss: 0.00994773581624031
2023-01-24 08:29:59.307321: step: 1868/529, loss: 0.0008641586755402386
2023-01-24 08:30:00.419048: step: 1872/529, loss: 0.006874522659927607
2023-01-24 08:30:01.518024: step: 1876/529, loss: 0.0026030277367681265
2023-01-24 08:30:02.667370: step: 1880/529, loss: 0.06523173302412033
2023-01-24 08:30:03.777861: step: 1884/529, loss: 0.002486263168975711
2023-01-24 08:30:04.883017: step: 1888/529, loss: 0.018967991694808006
2023-01-24 08:30:05.975951: step: 1892/529, loss: 0.005981970578432083
2023-01-24 08:30:07.101748: step: 1896/529, loss: 0.01120185200124979
2023-01-24 08:30:08.200369: step: 1900/529, loss: 0.004858768079429865
2023-01-24 08:30:09.300265: step: 1904/529, loss: 0.036857277154922485
2023-01-24 08:30:10.405963: step: 1908/529, loss: 0.01874036341905594
2023-01-24 08:30:11.499024: step: 1912/529, loss: 0.00855395570397377
2023-01-24 08:30:12.612077: step: 1916/529, loss: 0.005791983101516962
2023-01-24 08:30:13.735575: step: 1920/529, loss: 0.005590052343904972
2023-01-24 08:30:14.868387: step: 1924/529, loss: 0.0035764267668128014
2023-01-24 08:30:15.969919: step: 1928/529, loss: 0.0007121971575543284
2023-01-24 08:30:17.088512: step: 1932/529, loss: 0.006333343684673309
2023-01-24 08:30:18.212804: step: 1936/529, loss: 0.0018290726002305746
2023-01-24 08:30:19.307004: step: 1940/529, loss: 0.020614778622984886
2023-01-24 08:30:20.423237: step: 1944/529, loss: 0.015153782442212105
2023-01-24 08:30:21.502885: step: 1948/529, loss: 0.007827503606677055
2023-01-24 08:30:22.591185: step: 1952/529, loss: 0.004643795546144247
2023-01-24 08:30:23.696372: step: 1956/529, loss: 0.045869313180446625
2023-01-24 08:30:24.796976: step: 1960/529, loss: 0.0068098013289272785
2023-01-24 08:30:25.894110: step: 1964/529, loss: 0.002404472790658474
2023-01-24 08:30:26.997697: step: 1968/529, loss: 0.001679004984907806
2023-01-24 08:30:28.108537: step: 1972/529, loss: 0.003071703715249896
2023-01-24 08:30:29.228084: step: 1976/529, loss: 0.006801737006753683
2023-01-24 08:30:30.325415: step: 1980/529, loss: 0.004793296102434397
2023-01-24 08:30:31.435165: step: 1984/529, loss: 0.009354254230856895
2023-01-24 08:30:32.529095: step: 1988/529, loss: 0.01072611566632986
2023-01-24 08:30:33.631531: step: 1992/529, loss: 0.0031407487113028765
2023-01-24 08:30:34.758361: step: 1996/529, loss: 0.005848722532391548
2023-01-24 08:30:35.882799: step: 2000/529, loss: 0.010853058658540249
2023-01-24 08:30:36.994056: step: 2004/529, loss: 0.005025187041610479
2023-01-24 08:30:38.083496: step: 2008/529, loss: 0.0029536725487560034
2023-01-24 08:30:39.193081: step: 2012/529, loss: 0.05910155177116394
2023-01-24 08:30:40.288164: step: 2016/529, loss: 0.010073854587972164
2023-01-24 08:30:41.387177: step: 2020/529, loss: 0.003368824953213334
2023-01-24 08:30:42.514612: step: 2024/529, loss: 0.0011643996695056558
2023-01-24 08:30:43.612733: step: 2028/529, loss: 0.0022635748609900475
2023-01-24 08:30:44.725189: step: 2032/529, loss: 0.008298167027533054
2023-01-24 08:30:45.823856: step: 2036/529, loss: 0.0030539599247276783
2023-01-24 08:30:46.921800: step: 2040/529, loss: 0.020333029329776764
2023-01-24 08:30:48.022083: step: 2044/529, loss: 0.0022788713686168194
2023-01-24 08:30:49.129736: step: 2048/529, loss: 0.025013364851474762
2023-01-24 08:30:50.223358: step: 2052/529, loss: 0.005531164351850748
2023-01-24 08:30:51.324673: step: 2056/529, loss: 0.005339278373867273
2023-01-24 08:30:52.416539: step: 2060/529, loss: 0.010453582741320133
2023-01-24 08:30:53.563691: step: 2064/529, loss: 0.053581543266773224
2023-01-24 08:30:54.695934: step: 2068/529, loss: 0.010096881538629532
2023-01-24 08:30:55.796269: step: 2072/529, loss: 0.01938735507428646
2023-01-24 08:30:56.925382: step: 2076/529, loss: 0.00021988751541357487
2023-01-24 08:30:58.037178: step: 2080/529, loss: 0.004157444927841425
2023-01-24 08:30:59.160972: step: 2084/529, loss: 0.003393003484234214
2023-01-24 08:31:00.261595: step: 2088/529, loss: 0.0045474013313651085
2023-01-24 08:31:01.362201: step: 2092/529, loss: 0.033529434353113174
2023-01-24 08:31:02.450744: step: 2096/529, loss: 0.0008140570134855807
2023-01-24 08:31:03.554437: step: 2100/529, loss: 0.006187839899212122
2023-01-24 08:31:04.690744: step: 2104/529, loss: 0.004368227906525135
2023-01-24 08:31:05.809344: step: 2108/529, loss: 0.012259622104465961
2023-01-24 08:31:06.941436: step: 2112/529, loss: 0.027089525014162064
2023-01-24 08:31:08.065745: step: 2116/529, loss: 0.05032616853713989
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3779171969455934, 'r': 0.32198258335592306, 'f1': 0.3477147980093677}, 'combined': 0.2562109037963762, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3939407111245238, 'r': 0.2816300577796639, 'f1': 0.3284498096793655}, 'combined': 0.20187646838829293, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3739808168857774, 'r': 0.3328216377977791, 'f1': 0.35220281750889476}, 'combined': 0.2595178655328698, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3805408783729261, 'r': 0.2898573934920295, 'f1': 0.3290658456367949}, 'combined': 0.2022551051231032, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4067873303167421, 'r': 0.3411764705882353, 'f1': 0.37110423116615066}, 'combined': 0.27344522296453205, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3968028797819549, 'r': 0.28333238556354495, 'f1': 0.3306021971085246}, 'combined': 0.20419547468467703, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 6
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:33:30.391745: step: 4/529, loss: 0.005305708386003971
2023-01-24 08:33:31.521457: step: 8/529, loss: 0.006093189120292664
2023-01-24 08:33:32.630364: step: 12/529, loss: 0.007629713974893093
2023-01-24 08:33:33.731397: step: 16/529, loss: 0.005305420607328415
2023-01-24 08:33:34.826454: step: 20/529, loss: 0.01621827483177185
2023-01-24 08:33:35.921225: step: 24/529, loss: 0.012369094416499138
2023-01-24 08:33:37.046861: step: 28/529, loss: 0.0037875082343816757
2023-01-24 08:33:38.137408: step: 32/529, loss: 0.006324531510472298
2023-01-24 08:33:39.245398: step: 36/529, loss: 0.0042244186624884605
2023-01-24 08:33:40.343825: step: 40/529, loss: 0.006109151057898998
2023-01-24 08:33:41.458371: step: 44/529, loss: 0.0071633318439126015
2023-01-24 08:33:42.570107: step: 48/529, loss: 0.009522320702672005
2023-01-24 08:33:43.665064: step: 52/529, loss: 0.006063740700483322
2023-01-24 08:33:44.769113: step: 56/529, loss: 0.0026602260768413544
2023-01-24 08:33:45.869759: step: 60/529, loss: 0.004821986425668001
2023-01-24 08:33:46.991097: step: 64/529, loss: 0.005420095287263393
2023-01-24 08:33:48.082987: step: 68/529, loss: 0.009220386855304241
2023-01-24 08:33:49.198679: step: 72/529, loss: 0.004033449571579695
2023-01-24 08:33:50.318083: step: 76/529, loss: 0.028109779581427574
2023-01-24 08:33:51.391290: step: 80/529, loss: 0.0012292263563722372
2023-01-24 08:33:52.493041: step: 84/529, loss: 0.001076428801752627
2023-01-24 08:33:53.577669: step: 88/529, loss: 0.0036951242946088314
2023-01-24 08:33:54.664701: step: 92/529, loss: 0.009567310102283955
2023-01-24 08:33:55.750811: step: 96/529, loss: 0.009079602546989918
2023-01-24 08:33:56.861929: step: 100/529, loss: 0.011921736411750317
2023-01-24 08:33:57.988017: step: 104/529, loss: 0.005667198449373245
2023-01-24 08:33:59.096110: step: 108/529, loss: 0.005825122818350792
2023-01-24 08:34:00.227574: step: 112/529, loss: 0.00235575158149004
2023-01-24 08:34:01.323884: step: 116/529, loss: 0.04373656585812569
2023-01-24 08:34:02.452534: step: 120/529, loss: 0.012989873997867107
2023-01-24 08:34:03.570511: step: 124/529, loss: 0.007287052925676107
2023-01-24 08:34:04.681677: step: 128/529, loss: 0.006580047309398651
2023-01-24 08:34:05.795519: step: 132/529, loss: 0.011693893000483513
2023-01-24 08:34:06.891560: step: 136/529, loss: 0.007187485229223967
2023-01-24 08:34:07.998115: step: 140/529, loss: 0.007349448278546333
2023-01-24 08:34:09.110442: step: 144/529, loss: 0.009007965214550495
2023-01-24 08:34:10.219749: step: 148/529, loss: 0.045606840401887894
2023-01-24 08:34:11.333449: step: 152/529, loss: 0.010001951828598976
2023-01-24 08:34:12.450373: step: 156/529, loss: 0.006817980203777552
2023-01-24 08:34:13.555601: step: 160/529, loss: 0.003874080488458276
2023-01-24 08:34:14.690517: step: 164/529, loss: 0.007783068343997002
2023-01-24 08:34:15.793680: step: 168/529, loss: 0.005335921887308359
2023-01-24 08:34:16.897346: step: 172/529, loss: 0.0020430851727724075
2023-01-24 08:34:18.018587: step: 176/529, loss: 0.04033869504928589
2023-01-24 08:34:19.134688: step: 180/529, loss: 0.0034851818345487118
2023-01-24 08:34:20.236487: step: 184/529, loss: 0.007983280345797539
2023-01-24 08:34:21.355958: step: 188/529, loss: 0.0017792755970731378
2023-01-24 08:34:22.471668: step: 192/529, loss: 0.001871102605946362
2023-01-24 08:34:23.569237: step: 196/529, loss: 0.02657787688076496
2023-01-24 08:34:24.696173: step: 200/529, loss: 0.006426504347473383
2023-01-24 08:34:25.810711: step: 204/529, loss: 0.006066290196031332
2023-01-24 08:34:26.922015: step: 208/529, loss: 0.0011546644382178783
2023-01-24 08:34:28.058868: step: 212/529, loss: 0.006882756017148495
2023-01-24 08:34:29.177505: step: 216/529, loss: 0.007010776083916426
2023-01-24 08:34:30.291613: step: 220/529, loss: 0.007206588983535767
2023-01-24 08:34:31.391348: step: 224/529, loss: 0.006268988363444805
2023-01-24 08:34:32.501239: step: 228/529, loss: 0.019737256690859795
2023-01-24 08:34:33.625996: step: 232/529, loss: 0.00629029655829072
2023-01-24 08:34:34.705474: step: 236/529, loss: 0.006087011191993952
2023-01-24 08:34:35.832418: step: 240/529, loss: 0.003464686218649149
2023-01-24 08:34:36.925950: step: 244/529, loss: 0.0019196582725271583
2023-01-24 08:34:38.059785: step: 248/529, loss: 0.008158623240888119
2023-01-24 08:34:39.199849: step: 252/529, loss: 0.007937573827803135
2023-01-24 08:34:40.326007: step: 256/529, loss: 0.006093911826610565
2023-01-24 08:34:41.437884: step: 260/529, loss: 0.011993014253675938
2023-01-24 08:34:42.539641: step: 264/529, loss: 0.0046798307448625565
2023-01-24 08:34:43.637747: step: 268/529, loss: 0.004838019609451294
2023-01-24 08:34:44.750625: step: 272/529, loss: 0.005612580105662346
2023-01-24 08:34:45.863873: step: 276/529, loss: 0.003289461135864258
2023-01-24 08:34:46.948550: step: 280/529, loss: 0.0008001339738257229
2023-01-24 08:34:48.087731: step: 284/529, loss: 0.010058913379907608
2023-01-24 08:34:49.215084: step: 288/529, loss: 0.027089452371001244
2023-01-24 08:34:50.317129: step: 292/529, loss: 0.0019319587154313922
2023-01-24 08:34:51.438101: step: 296/529, loss: 0.02260185033082962
2023-01-24 08:34:52.564565: step: 300/529, loss: 0.016764825209975243
2023-01-24 08:34:53.679745: step: 304/529, loss: 0.015785498544573784
2023-01-24 08:34:54.800264: step: 308/529, loss: 0.027940809726715088
2023-01-24 08:34:55.914404: step: 312/529, loss: 0.007339327596127987
2023-01-24 08:34:57.042711: step: 316/529, loss: 0.009754262864589691
2023-01-24 08:34:58.149681: step: 320/529, loss: 0.009043138474225998
2023-01-24 08:34:59.261874: step: 324/529, loss: 0.014477244578301907
2023-01-24 08:35:00.393432: step: 328/529, loss: 0.006711823400110006
2023-01-24 08:35:01.506265: step: 332/529, loss: 0.0010740314610302448
2023-01-24 08:35:02.614990: step: 336/529, loss: 0.011390362866222858
2023-01-24 08:35:03.727528: step: 340/529, loss: 0.00804499164223671
2023-01-24 08:35:04.849272: step: 344/529, loss: 0.001907942583784461
2023-01-24 08:35:05.958132: step: 348/529, loss: 0.013106828555464745
2023-01-24 08:35:07.095966: step: 352/529, loss: 0.0017678738804534078
2023-01-24 08:35:08.202878: step: 356/529, loss: 0.005667952820658684
2023-01-24 08:35:09.330041: step: 360/529, loss: 0.0069861216470599174
2023-01-24 08:35:10.432741: step: 364/529, loss: 0.011109267361462116
2023-01-24 08:35:11.556722: step: 368/529, loss: 0.005532680079340935
2023-01-24 08:35:12.683322: step: 372/529, loss: 0.00781653355807066
2023-01-24 08:35:13.811732: step: 376/529, loss: 0.012174945324659348
2023-01-24 08:35:14.919831: step: 380/529, loss: 0.0015434130327776074
2023-01-24 08:35:16.040864: step: 384/529, loss: 0.02806060202419758
2023-01-24 08:35:17.158777: step: 388/529, loss: 0.0021952311508357525
2023-01-24 08:35:18.277638: step: 392/529, loss: 0.009764987975358963
2023-01-24 08:35:19.378146: step: 396/529, loss: 0.007892412133514881
2023-01-24 08:35:20.492076: step: 400/529, loss: 0.002366431523114443
2023-01-24 08:35:21.613476: step: 404/529, loss: 0.012028719298541546
2023-01-24 08:35:22.708480: step: 408/529, loss: 0.00608090590685606
2023-01-24 08:35:23.820483: step: 412/529, loss: 0.014038904570043087
2023-01-24 08:35:24.931143: step: 416/529, loss: 0.011369108222424984
2023-01-24 08:35:26.030812: step: 420/529, loss: 0.011203082278370857
2023-01-24 08:35:27.154573: step: 424/529, loss: 0.06550873816013336
2023-01-24 08:35:28.246244: step: 428/529, loss: 0.0039025964215397835
2023-01-24 08:35:29.340701: step: 432/529, loss: 0.0033832304179668427
2023-01-24 08:35:30.451699: step: 436/529, loss: 0.0053379652090370655
2023-01-24 08:35:31.569465: step: 440/529, loss: 0.02753600664436817
2023-01-24 08:35:32.704830: step: 444/529, loss: 0.008254663087427616
2023-01-24 08:35:33.801323: step: 448/529, loss: 0.002607951872050762
2023-01-24 08:35:34.958636: step: 452/529, loss: 0.014489099383354187
2023-01-24 08:35:36.075824: step: 456/529, loss: 0.023807143792510033
2023-01-24 08:35:37.177824: step: 460/529, loss: 0.002194441156461835
2023-01-24 08:35:38.289303: step: 464/529, loss: 0.007039714138954878
2023-01-24 08:35:39.391800: step: 468/529, loss: 0.010733935981988907
2023-01-24 08:35:40.479444: step: 472/529, loss: 0.02351614274084568
2023-01-24 08:35:41.557892: step: 476/529, loss: 0.004978803917765617
2023-01-24 08:35:42.684307: step: 480/529, loss: 0.006381789688020945
2023-01-24 08:35:43.781376: step: 484/529, loss: 0.014700474217534065
2023-01-24 08:35:44.911791: step: 488/529, loss: 0.012882917188107967
2023-01-24 08:35:46.033399: step: 492/529, loss: 0.012605691328644753
2023-01-24 08:35:47.145886: step: 496/529, loss: 0.007123208604753017
2023-01-24 08:35:48.251192: step: 500/529, loss: 0.002348636044189334
2023-01-24 08:35:49.393979: step: 504/529, loss: 0.0015904400497674942
2023-01-24 08:35:50.510958: step: 508/529, loss: 0.0019640130922198296
2023-01-24 08:35:51.611342: step: 512/529, loss: 0.01146282721310854
2023-01-24 08:35:52.699935: step: 516/529, loss: 0.010517077520489693
2023-01-24 08:35:53.807948: step: 520/529, loss: 0.008044732734560966
2023-01-24 08:35:54.926326: step: 524/529, loss: 0.005586392246186733
2023-01-24 08:35:56.029429: step: 528/529, loss: 0.010143124498426914
2023-01-24 08:35:57.169015: step: 532/529, loss: 0.00445580156520009
2023-01-24 08:35:58.263658: step: 536/529, loss: 0.002814148785546422
2023-01-24 08:35:59.365350: step: 540/529, loss: 0.007910819724202156
2023-01-24 08:36:00.462122: step: 544/529, loss: 0.004795929882675409
2023-01-24 08:36:01.560741: step: 548/529, loss: 0.003995841834694147
2023-01-24 08:36:02.670062: step: 552/529, loss: 0.005644669756293297
2023-01-24 08:36:03.785906: step: 556/529, loss: 0.0033773272298276424
2023-01-24 08:36:04.906314: step: 560/529, loss: 8.530495688319206e-05
2023-01-24 08:36:06.009810: step: 564/529, loss: 0.0038765519857406616
2023-01-24 08:36:07.115251: step: 568/529, loss: 0.0009553500567562878
2023-01-24 08:36:08.218593: step: 572/529, loss: 0.006487762089818716
2023-01-24 08:36:09.313845: step: 576/529, loss: 0.0039129070937633514
2023-01-24 08:36:10.413181: step: 580/529, loss: 0.00626823864877224
2023-01-24 08:36:11.509788: step: 584/529, loss: 0.01893220655620098
2023-01-24 08:36:12.611758: step: 588/529, loss: 0.0023820495698601007
2023-01-24 08:36:13.708996: step: 592/529, loss: 0.004280897788703442
2023-01-24 08:36:14.837392: step: 596/529, loss: 0.004197548609226942
2023-01-24 08:36:15.922879: step: 600/529, loss: 0.003984412178397179
2023-01-24 08:36:17.029328: step: 604/529, loss: 0.004340028390288353
2023-01-24 08:36:18.144763: step: 608/529, loss: 0.0048962910659611225
2023-01-24 08:36:19.255152: step: 612/529, loss: 0.024945199489593506
2023-01-24 08:36:20.360951: step: 616/529, loss: 0.0054998514242470264
2023-01-24 08:36:21.489080: step: 620/529, loss: 0.002281581051647663
2023-01-24 08:36:22.582684: step: 624/529, loss: 0.008889270015060902
2023-01-24 08:36:23.698019: step: 628/529, loss: 0.026520676910877228
2023-01-24 08:36:24.803819: step: 632/529, loss: 0.0068703144788742065
2023-01-24 08:36:25.926048: step: 636/529, loss: 0.006307255011051893
2023-01-24 08:36:27.060676: step: 640/529, loss: 0.0048749265260994434
2023-01-24 08:36:28.164167: step: 644/529, loss: 0.0028190717566758394
2023-01-24 08:36:29.269064: step: 648/529, loss: 0.014694026671350002
2023-01-24 08:36:30.369434: step: 652/529, loss: 0.0014744563959538937
2023-01-24 08:36:31.486736: step: 656/529, loss: 0.003851824440062046
2023-01-24 08:36:32.651229: step: 660/529, loss: 0.0055006761103868484
2023-01-24 08:36:33.774116: step: 664/529, loss: 0.0433463454246521
2023-01-24 08:36:34.881767: step: 668/529, loss: 0.005329366773366928
2023-01-24 08:36:36.021173: step: 672/529, loss: 0.005724288523197174
2023-01-24 08:36:37.126343: step: 676/529, loss: 0.002345007611438632
2023-01-24 08:36:38.227874: step: 680/529, loss: 0.003112499602138996
2023-01-24 08:36:39.372093: step: 684/529, loss: 0.00028195566846989095
2023-01-24 08:36:40.471697: step: 688/529, loss: 0.002822271781042218
2023-01-24 08:36:41.586595: step: 692/529, loss: 0.005992645863443613
2023-01-24 08:36:42.720960: step: 696/529, loss: 0.0057897260412573814
2023-01-24 08:36:43.856824: step: 700/529, loss: 0.012225686572492123
2023-01-24 08:36:44.952862: step: 704/529, loss: 0.0027927816845476627
2023-01-24 08:36:46.063232: step: 708/529, loss: 0.017846500501036644
2023-01-24 08:36:47.226214: step: 712/529, loss: 0.05046258866786957
2023-01-24 08:36:48.361304: step: 716/529, loss: 0.0012455973774194717
2023-01-24 08:36:49.453566: step: 720/529, loss: 0.0068160658702254295
2023-01-24 08:36:50.564371: step: 724/529, loss: 0.005377395078539848
2023-01-24 08:36:51.688887: step: 728/529, loss: 0.006648749113082886
2023-01-24 08:36:52.777977: step: 732/529, loss: 0.023196039721369743
2023-01-24 08:36:53.897244: step: 736/529, loss: 0.021718859672546387
2023-01-24 08:36:54.981642: step: 740/529, loss: 0.007760044187307358
2023-01-24 08:36:56.109159: step: 744/529, loss: 0.0010392244439572096
2023-01-24 08:36:57.215530: step: 748/529, loss: 0.006531145423650742
2023-01-24 08:36:58.314885: step: 752/529, loss: 0.008210964500904083
2023-01-24 08:36:59.422449: step: 756/529, loss: 0.036858491599559784
2023-01-24 08:37:00.526765: step: 760/529, loss: 0.0012899063294753432
2023-01-24 08:37:01.632392: step: 764/529, loss: 0.00021576260041911155
2023-01-24 08:37:02.719378: step: 768/529, loss: 0.0008020169334486127
2023-01-24 08:37:03.831575: step: 772/529, loss: 0.0072806584648787975
2023-01-24 08:37:04.933387: step: 776/529, loss: 0.0036610804963856936
2023-01-24 08:37:06.035799: step: 780/529, loss: 0.005994501058012247
2023-01-24 08:37:07.142000: step: 784/529, loss: 0.0062747919000685215
2023-01-24 08:37:08.248929: step: 788/529, loss: 0.006858598906546831
2023-01-24 08:37:09.348821: step: 792/529, loss: 0.007317975163459778
2023-01-24 08:37:10.447938: step: 796/529, loss: 0.018855173140764236
2023-01-24 08:37:11.555951: step: 800/529, loss: 0.003291010158136487
2023-01-24 08:37:12.672763: step: 804/529, loss: 0.026685452088713646
2023-01-24 08:37:13.770450: step: 808/529, loss: 0.004708230495452881
2023-01-24 08:37:14.878421: step: 812/529, loss: 0.05527876317501068
2023-01-24 08:37:15.983113: step: 816/529, loss: 0.006717084441334009
2023-01-24 08:37:17.099933: step: 820/529, loss: 0.038744643330574036
2023-01-24 08:37:18.215563: step: 824/529, loss: 0.046610649675130844
2023-01-24 08:37:19.342983: step: 828/529, loss: 0.0054276264272630215
2023-01-24 08:37:20.471976: step: 832/529, loss: 0.031156649813055992
2023-01-24 08:37:21.557259: step: 836/529, loss: 0.007855386473238468
2023-01-24 08:37:22.656904: step: 840/529, loss: 0.0017032561590895057
2023-01-24 08:37:23.784395: step: 844/529, loss: 0.008952956646680832
2023-01-24 08:37:24.908964: step: 848/529, loss: 0.002339595463126898
2023-01-24 08:37:26.016517: step: 852/529, loss: 0.0059345318004488945
2023-01-24 08:37:27.116841: step: 856/529, loss: 0.006251884624361992
2023-01-24 08:37:28.213011: step: 860/529, loss: 0.00011411734885768965
2023-01-24 08:37:29.297647: step: 864/529, loss: 0.062095288187265396
2023-01-24 08:37:30.429750: step: 868/529, loss: 0.009423395618796349
2023-01-24 08:37:31.554374: step: 872/529, loss: 0.038906171917915344
2023-01-24 08:37:32.685718: step: 876/529, loss: 0.02318127453327179
2023-01-24 08:37:33.797057: step: 880/529, loss: 0.0064411889761686325
2023-01-24 08:37:34.894478: step: 884/529, loss: 0.02866014838218689
2023-01-24 08:37:36.000190: step: 888/529, loss: 0.009514992125332355
2023-01-24 08:37:37.113528: step: 892/529, loss: 0.006461628712713718
2023-01-24 08:37:38.212003: step: 896/529, loss: 0.003239220008254051
2023-01-24 08:37:39.348090: step: 900/529, loss: 0.021247822791337967
2023-01-24 08:37:40.477535: step: 904/529, loss: 0.0050697955302894115
2023-01-24 08:37:41.602551: step: 908/529, loss: 0.0012252520537003875
2023-01-24 08:37:42.697640: step: 912/529, loss: 0.006530306302011013
2023-01-24 08:37:43.816212: step: 916/529, loss: 0.009525244124233723
2023-01-24 08:37:44.920628: step: 920/529, loss: 0.003942673560231924
2023-01-24 08:37:46.040445: step: 924/529, loss: 0.029574938118457794
2023-01-24 08:37:47.168810: step: 928/529, loss: 0.0008766837418079376
2023-01-24 08:37:48.267927: step: 932/529, loss: 0.010835814289748669
2023-01-24 08:37:49.368686: step: 936/529, loss: 0.0033007157035171986
2023-01-24 08:37:50.475651: step: 940/529, loss: 0.00879733171314001
2023-01-24 08:37:51.569450: step: 944/529, loss: 0.02690090425312519
2023-01-24 08:37:52.671317: step: 948/529, loss: 0.010351556353271008
2023-01-24 08:37:53.788250: step: 952/529, loss: 0.00414371769875288
2023-01-24 08:37:54.875021: step: 956/529, loss: 0.004672827199101448
2023-01-24 08:37:55.972445: step: 960/529, loss: 0.005142142064869404
2023-01-24 08:37:57.064144: step: 964/529, loss: 0.007731347344815731
2023-01-24 08:37:58.168009: step: 968/529, loss: 0.0029873691964894533
2023-01-24 08:37:59.285716: step: 972/529, loss: 0.0059210131876170635
2023-01-24 08:38:00.392490: step: 976/529, loss: 0.013368169777095318
2023-01-24 08:38:01.509104: step: 980/529, loss: 0.026535727083683014
2023-01-24 08:38:02.625369: step: 984/529, loss: 0.009639458730816841
2023-01-24 08:38:03.744704: step: 988/529, loss: 0.015243644826114178
2023-01-24 08:38:04.865565: step: 992/529, loss: 0.004069318063557148
2023-01-24 08:38:05.974045: step: 996/529, loss: 0.006744795944541693
2023-01-24 08:38:07.094693: step: 1000/529, loss: 0.0044373259879648685
2023-01-24 08:38:08.190586: step: 1004/529, loss: 0.006861021742224693
2023-01-24 08:38:09.326827: step: 1008/529, loss: 0.009816762991249561
2023-01-24 08:38:10.423930: step: 1012/529, loss: 0.0045770020224153996
2023-01-24 08:38:11.508534: step: 1016/529, loss: 0.0018444191664457321
2023-01-24 08:38:12.605313: step: 1020/529, loss: 0.0036486079916357994
2023-01-24 08:38:13.706547: step: 1024/529, loss: 0.006663595791906118
2023-01-24 08:38:14.821160: step: 1028/529, loss: 0.0068853083066642284
2023-01-24 08:38:15.913337: step: 1032/529, loss: 0.016710858792066574
2023-01-24 08:38:17.043870: step: 1036/529, loss: 0.01309026125818491
2023-01-24 08:38:18.138087: step: 1040/529, loss: 0.047220248728990555
2023-01-24 08:38:19.235704: step: 1044/529, loss: 0.00925512332469225
2023-01-24 08:38:20.366359: step: 1048/529, loss: 0.03308819234371185
2023-01-24 08:38:21.461232: step: 1052/529, loss: 0.0033879652619361877
2023-01-24 08:38:22.569006: step: 1056/529, loss: 0.00047140775131992996
2023-01-24 08:38:23.684848: step: 1060/529, loss: 0.007818601094186306
2023-01-24 08:38:24.781140: step: 1064/529, loss: 0.0001789512170944363
2023-01-24 08:38:25.872293: step: 1068/529, loss: 0.003873070701956749
2023-01-24 08:38:26.978380: step: 1072/529, loss: 0.029652584344148636
2023-01-24 08:38:28.088686: step: 1076/529, loss: 0.02211040072143078
2023-01-24 08:38:29.196219: step: 1080/529, loss: 0.005249269772320986
2023-01-24 08:38:30.300178: step: 1084/529, loss: 0.01418808102607727
2023-01-24 08:38:31.404266: step: 1088/529, loss: 0.018592024222016335
2023-01-24 08:38:32.522853: step: 1092/529, loss: 0.008901447989046574
2023-01-24 08:38:33.614610: step: 1096/529, loss: 0.04650983586907387
2023-01-24 08:38:34.703158: step: 1100/529, loss: 0.01016843318939209
2023-01-24 08:38:35.819469: step: 1104/529, loss: 0.0009103661868721247
2023-01-24 08:38:36.941393: step: 1108/529, loss: 0.015927115455269814
2023-01-24 08:38:38.054012: step: 1112/529, loss: 0.003786415560171008
2023-01-24 08:38:39.173661: step: 1116/529, loss: 0.005481277592480183
2023-01-24 08:38:40.277420: step: 1120/529, loss: 0.019856378436088562
2023-01-24 08:38:41.366076: step: 1124/529, loss: 0.06672421842813492
2023-01-24 08:38:42.454076: step: 1128/529, loss: 0.004589391406625509
2023-01-24 08:38:43.560170: step: 1132/529, loss: 0.04602415859699249
2023-01-24 08:38:44.665761: step: 1136/529, loss: 0.012788642197847366
2023-01-24 08:38:45.797261: step: 1140/529, loss: 0.030948707833886147
2023-01-24 08:38:46.880960: step: 1144/529, loss: 0.019195549190044403
2023-01-24 08:38:47.968891: step: 1148/529, loss: 0.057643767446279526
2023-01-24 08:38:49.054083: step: 1152/529, loss: 0.005220762453973293
2023-01-24 08:38:50.184990: step: 1156/529, loss: 0.011224639602005482
2023-01-24 08:38:51.285380: step: 1160/529, loss: 0.0016792897367849946
2023-01-24 08:38:52.385706: step: 1164/529, loss: 0.01700332574546337
2023-01-24 08:38:53.492808: step: 1168/529, loss: 0.004716961644589901
2023-01-24 08:38:54.597486: step: 1172/529, loss: 0.0006620117928832769
2023-01-24 08:38:55.693816: step: 1176/529, loss: 0.002469106810167432
2023-01-24 08:38:56.811179: step: 1180/529, loss: 0.023486923426389694
2023-01-24 08:38:57.918015: step: 1184/529, loss: 0.03730182722210884
2023-01-24 08:38:59.032292: step: 1188/529, loss: 0.005834262818098068
2023-01-24 08:39:00.130064: step: 1192/529, loss: 0.0055563002824783325
2023-01-24 08:39:01.244215: step: 1196/529, loss: 0.0059983497485518456
2023-01-24 08:39:02.370294: step: 1200/529, loss: 0.031246904283761978
2023-01-24 08:39:03.482554: step: 1204/529, loss: 0.0033794923219829798
2023-01-24 08:39:04.586333: step: 1208/529, loss: 0.002044606488198042
2023-01-24 08:39:05.717820: step: 1212/529, loss: 0.01928640343248844
2023-01-24 08:39:06.830200: step: 1216/529, loss: 0.009126346558332443
2023-01-24 08:39:07.929885: step: 1220/529, loss: 0.024784620851278305
2023-01-24 08:39:09.042367: step: 1224/529, loss: 0.00625180546194315
2023-01-24 08:39:10.143412: step: 1228/529, loss: 0.019677041098475456
2023-01-24 08:39:11.268583: step: 1232/529, loss: 0.008510519750416279
2023-01-24 08:39:12.394129: step: 1236/529, loss: 0.014463532716035843
2023-01-24 08:39:13.500966: step: 1240/529, loss: 0.0019503699149936438
2023-01-24 08:39:14.616469: step: 1244/529, loss: 0.008476648479700089
2023-01-24 08:39:15.745611: step: 1248/529, loss: 0.0016467832028865814
2023-01-24 08:39:16.860377: step: 1252/529, loss: 0.011762903071939945
2023-01-24 08:39:17.963242: step: 1256/529, loss: 0.022418145090341568
2023-01-24 08:39:19.080578: step: 1260/529, loss: 0.03791734576225281
2023-01-24 08:39:20.227239: step: 1264/529, loss: 0.0024281104560941458
2023-01-24 08:39:21.333867: step: 1268/529, loss: 0.003130145836621523
2023-01-24 08:39:22.444678: step: 1272/529, loss: 0.005850307643413544
2023-01-24 08:39:23.549509: step: 1276/529, loss: 0.010025348514318466
2023-01-24 08:39:24.674037: step: 1280/529, loss: 0.0015392365166917443
2023-01-24 08:39:25.790079: step: 1284/529, loss: 0.09602412581443787
2023-01-24 08:39:26.909185: step: 1288/529, loss: 0.004956912714987993
2023-01-24 08:39:28.009032: step: 1292/529, loss: 0.01091617438942194
2023-01-24 08:39:29.107637: step: 1296/529, loss: 0.004811576101928949
2023-01-24 08:39:30.235299: step: 1300/529, loss: 0.0041037858463823795
2023-01-24 08:39:31.330201: step: 1304/529, loss: 0.005641773343086243
2023-01-24 08:39:32.475889: step: 1308/529, loss: 0.006840884685516357
2023-01-24 08:39:33.589947: step: 1312/529, loss: 0.02102852612733841
2023-01-24 08:39:34.708858: step: 1316/529, loss: 0.013571326620876789
2023-01-24 08:39:35.828276: step: 1320/529, loss: 0.01271682046353817
2023-01-24 08:39:36.939936: step: 1324/529, loss: 0.008418488316237926
2023-01-24 08:39:38.044152: step: 1328/529, loss: 0.021897785365581512
2023-01-24 08:39:39.139411: step: 1332/529, loss: 0.006459553726017475
2023-01-24 08:39:40.247005: step: 1336/529, loss: 0.0351315401494503
2023-01-24 08:39:41.353169: step: 1340/529, loss: 0.01350568700581789
2023-01-24 08:39:42.452358: step: 1344/529, loss: 0.0046593365259468555
2023-01-24 08:39:43.562259: step: 1348/529, loss: 0.016990235075354576
2023-01-24 08:39:44.667399: step: 1352/529, loss: 0.001244245795533061
2023-01-24 08:39:45.774060: step: 1356/529, loss: 0.0010579493828117847
2023-01-24 08:39:46.888464: step: 1360/529, loss: 0.0009354364592581987
2023-01-24 08:39:48.006443: step: 1364/529, loss: 0.013501330278813839
2023-01-24 08:39:49.104731: step: 1368/529, loss: 0.011196371167898178
2023-01-24 08:39:50.213389: step: 1372/529, loss: 0.010294260457158089
2023-01-24 08:39:51.321897: step: 1376/529, loss: 0.010214634239673615
2023-01-24 08:39:52.435433: step: 1380/529, loss: 0.006198344752192497
2023-01-24 08:39:53.530928: step: 1384/529, loss: 0.008807285688817501
2023-01-24 08:39:54.641913: step: 1388/529, loss: 0.006719553377479315
2023-01-24 08:39:55.741461: step: 1392/529, loss: 0.005882189143449068
2023-01-24 08:39:56.832136: step: 1396/529, loss: 0.005123903043568134
2023-01-24 08:39:57.928922: step: 1400/529, loss: 8.376445475732908e-05
2023-01-24 08:39:59.049413: step: 1404/529, loss: 0.002987247658893466
2023-01-24 08:40:00.172196: step: 1408/529, loss: 0.005623606964945793
2023-01-24 08:40:01.276463: step: 1412/529, loss: 0.008316478691995144
2023-01-24 08:40:02.401010: step: 1416/529, loss: 0.0110525693744421
2023-01-24 08:40:03.500807: step: 1420/529, loss: 0.014707077294588089
2023-01-24 08:40:04.633424: step: 1424/529, loss: 0.009544271975755692
2023-01-24 08:40:05.741376: step: 1428/529, loss: 0.010115514509379864
2023-01-24 08:40:06.845818: step: 1432/529, loss: 0.037536054849624634
2023-01-24 08:40:07.953132: step: 1436/529, loss: 0.005475954618304968
2023-01-24 08:40:09.043351: step: 1440/529, loss: 0.007395019289106131
2023-01-24 08:40:10.163045: step: 1444/529, loss: 0.02025020122528076
2023-01-24 08:40:11.283155: step: 1448/529, loss: 0.015663426369428635
2023-01-24 08:40:12.373174: step: 1452/529, loss: 0.0006771829794161022
2023-01-24 08:40:13.476624: step: 1456/529, loss: 0.009414381347596645
2023-01-24 08:40:14.570837: step: 1460/529, loss: 0.0007117522764019668
2023-01-24 08:40:15.691064: step: 1464/529, loss: 0.015193939208984375
2023-01-24 08:40:16.837158: step: 1468/529, loss: 0.023331169039011
2023-01-24 08:40:17.958627: step: 1472/529, loss: 0.013729014433920383
2023-01-24 08:40:19.073591: step: 1476/529, loss: 0.10108592361211777
2023-01-24 08:40:20.189737: step: 1480/529, loss: 0.006191513501107693
2023-01-24 08:40:21.293549: step: 1484/529, loss: 0.0033932547084987164
2023-01-24 08:40:22.393946: step: 1488/529, loss: 0.0005136637482792139
2023-01-24 08:40:23.492937: step: 1492/529, loss: 0.001695052022114396
2023-01-24 08:40:24.614426: step: 1496/529, loss: 0.0025329450145363808
2023-01-24 08:40:25.704738: step: 1500/529, loss: 0.06505904346704483
2023-01-24 08:40:26.798509: step: 1504/529, loss: 0.0009990466060116887
2023-01-24 08:40:27.888780: step: 1508/529, loss: 0.001257079653441906
2023-01-24 08:40:29.003379: step: 1512/529, loss: 0.010051651857793331
2023-01-24 08:40:30.131048: step: 1516/529, loss: 0.005372804589569569
2023-01-24 08:40:31.239366: step: 1520/529, loss: 0.0012749641900882125
2023-01-24 08:40:32.354092: step: 1524/529, loss: 0.0033251801505684853
2023-01-24 08:40:33.456050: step: 1528/529, loss: 0.03823993727564812
2023-01-24 08:40:34.576308: step: 1532/529, loss: 0.00402421411126852
2023-01-24 08:40:35.713830: step: 1536/529, loss: 0.001792093156836927
2023-01-24 08:40:36.824171: step: 1540/529, loss: 0.01689228042960167
2023-01-24 08:40:37.916032: step: 1544/529, loss: 0.01427196990698576
2023-01-24 08:40:39.019576: step: 1548/529, loss: 0.011329120956361294
2023-01-24 08:40:40.133878: step: 1552/529, loss: 0.0033109106589108706
2023-01-24 08:40:41.266111: step: 1556/529, loss: 0.0016857982845976949
2023-01-24 08:40:42.365550: step: 1560/529, loss: 0.0032844559755176306
2023-01-24 08:40:43.470144: step: 1564/529, loss: 0.005794933997094631
2023-01-24 08:40:44.574558: step: 1568/529, loss: 0.003992067649960518
2023-01-24 08:40:45.692616: step: 1572/529, loss: 0.009744444862008095
2023-01-24 08:40:46.804860: step: 1576/529, loss: 0.006623596418648958
2023-01-24 08:40:47.923947: step: 1580/529, loss: 0.016973726451396942
2023-01-24 08:40:49.035614: step: 1584/529, loss: 0.002122956793755293
2023-01-24 08:40:50.137400: step: 1588/529, loss: 0.003243247279897332
2023-01-24 08:40:51.278787: step: 1592/529, loss: 0.001763826236128807
2023-01-24 08:40:52.389125: step: 1596/529, loss: 0.0013744751922786236
2023-01-24 08:40:53.483732: step: 1600/529, loss: 0.008129049092531204
2023-01-24 08:40:54.584133: step: 1604/529, loss: 0.04044123366475105
2023-01-24 08:40:55.693434: step: 1608/529, loss: 0.015696074813604355
2023-01-24 08:40:56.817148: step: 1612/529, loss: 0.016748961061239243
2023-01-24 08:40:57.941358: step: 1616/529, loss: 0.04168316349387169
2023-01-24 08:40:59.036860: step: 1620/529, loss: 0.024754514917731285
2023-01-24 08:41:00.145617: step: 1624/529, loss: 0.009901798330247402
2023-01-24 08:41:01.268049: step: 1628/529, loss: 0.0010433894349262118
2023-01-24 08:41:02.358161: step: 1632/529, loss: 0.0022630058228969574
2023-01-24 08:41:03.470504: step: 1636/529, loss: 0.005433759652078152
2023-01-24 08:41:04.577027: step: 1640/529, loss: 0.004507997073233128
2023-01-24 08:41:05.674384: step: 1644/529, loss: 0.0015100986929610372
2023-01-24 08:41:06.819676: step: 1648/529, loss: 0.011910167522728443
2023-01-24 08:41:07.927570: step: 1652/529, loss: 0.004427351988852024
2023-01-24 08:41:09.033554: step: 1656/529, loss: 0.005018251948058605
2023-01-24 08:41:10.126555: step: 1660/529, loss: 0.005804268177598715
2023-01-24 08:41:11.196018: step: 1664/529, loss: 0.02130913734436035
2023-01-24 08:41:12.293211: step: 1668/529, loss: 0.0015406433958560228
2023-01-24 08:41:13.389562: step: 1672/529, loss: 0.003071944694966078
2023-01-24 08:41:14.504960: step: 1676/529, loss: 0.001010268577374518
2023-01-24 08:41:15.635419: step: 1680/529, loss: 0.00027104635955765843
2023-01-24 08:41:16.762333: step: 1684/529, loss: 0.012311664409935474
2023-01-24 08:41:17.838162: step: 1688/529, loss: 0.0005201937165111303
2023-01-24 08:41:18.948598: step: 1692/529, loss: 0.010430201888084412
2023-01-24 08:41:20.069843: step: 1696/529, loss: 0.009044974111020565
2023-01-24 08:41:21.184288: step: 1700/529, loss: 0.02239764668047428
2023-01-24 08:41:22.291783: step: 1704/529, loss: 0.02251269854605198
2023-01-24 08:41:23.402163: step: 1708/529, loss: 0.005508198402822018
2023-01-24 08:41:24.512710: step: 1712/529, loss: 0.014079774729907513
2023-01-24 08:41:25.633571: step: 1716/529, loss: 0.023932337760925293
2023-01-24 08:41:26.762240: step: 1720/529, loss: 0.0025198282673954964
2023-01-24 08:41:27.874445: step: 1724/529, loss: 0.0054346430115401745
2023-01-24 08:41:29.025983: step: 1728/529, loss: 0.016678204759955406
2023-01-24 08:41:30.115591: step: 1732/529, loss: 0.005527746398001909
2023-01-24 08:41:31.223967: step: 1736/529, loss: 0.024834997951984406
2023-01-24 08:41:32.358062: step: 1740/529, loss: 0.027903374284505844
2023-01-24 08:41:33.449716: step: 1744/529, loss: 0.0011577687691897154
2023-01-24 08:41:34.537796: step: 1748/529, loss: 0.017095379531383514
2023-01-24 08:41:35.639736: step: 1752/529, loss: 0.003511288436129689
2023-01-24 08:41:36.753574: step: 1756/529, loss: 0.0049431780353188515
2023-01-24 08:41:37.863000: step: 1760/529, loss: 0.00928831472992897
2023-01-24 08:41:38.961377: step: 1764/529, loss: 0.005988477263599634
2023-01-24 08:41:40.045207: step: 1768/529, loss: 0.010179761797189713
2023-01-24 08:41:41.141988: step: 1772/529, loss: 0.010879379697144032
2023-01-24 08:41:42.250088: step: 1776/529, loss: 0.006690423935651779
2023-01-24 08:41:43.357668: step: 1780/529, loss: 0.007379619404673576
2023-01-24 08:41:44.469364: step: 1784/529, loss: 0.014838037081062794
2023-01-24 08:41:45.575793: step: 1788/529, loss: 0.007637612521648407
2023-01-24 08:41:46.692893: step: 1792/529, loss: 0.003951916936784983
2023-01-24 08:41:47.791179: step: 1796/529, loss: 0.007001466117799282
2023-01-24 08:41:48.899203: step: 1800/529, loss: 0.0009166442323476076
2023-01-24 08:41:49.987952: step: 1804/529, loss: 0.0013012280687689781
2023-01-24 08:41:51.099550: step: 1808/529, loss: 0.002779993461444974
2023-01-24 08:41:52.202352: step: 1812/529, loss: 0.015612097457051277
2023-01-24 08:41:53.316744: step: 1816/529, loss: 0.0012944986810907722
2023-01-24 08:41:54.435240: step: 1820/529, loss: 0.012227851897478104
2023-01-24 08:41:55.527961: step: 1824/529, loss: 0.013243754394352436
2023-01-24 08:41:56.622202: step: 1828/529, loss: 0.004501806106418371
2023-01-24 08:41:57.707096: step: 1832/529, loss: 0.003766302252188325
2023-01-24 08:41:58.833246: step: 1836/529, loss: 0.01177501492202282
2023-01-24 08:41:59.944284: step: 1840/529, loss: 0.004233608953654766
2023-01-24 08:42:01.040764: step: 1844/529, loss: 0.012065853923559189
2023-01-24 08:42:02.135359: step: 1848/529, loss: 0.01186690665781498
2023-01-24 08:42:03.241873: step: 1852/529, loss: 0.007836073637008667
2023-01-24 08:42:04.335942: step: 1856/529, loss: 0.0040960488840937614
2023-01-24 08:42:05.452755: step: 1860/529, loss: 0.0016701840795576572
2023-01-24 08:42:06.593150: step: 1864/529, loss: 0.007522040046751499
2023-01-24 08:42:07.711102: step: 1868/529, loss: 0.007356657646596432
2023-01-24 08:42:08.837739: step: 1872/529, loss: 0.01644561067223549
2023-01-24 08:42:09.926967: step: 1876/529, loss: 0.0
2023-01-24 08:42:11.006053: step: 1880/529, loss: 0.0005244215135462582
2023-01-24 08:42:12.134770: step: 1884/529, loss: 0.02792527712881565
2023-01-24 08:42:13.261638: step: 1888/529, loss: 0.020295726135373116
2023-01-24 08:42:14.359639: step: 1892/529, loss: 0.007545561529695988
2023-01-24 08:42:15.474040: step: 1896/529, loss: 0.007613576017320156
2023-01-24 08:42:16.563754: step: 1900/529, loss: 0.006284275557845831
2023-01-24 08:42:17.660252: step: 1904/529, loss: 0.003373147686943412
2023-01-24 08:42:18.757186: step: 1908/529, loss: 0.008601627312600613
2023-01-24 08:42:19.841457: step: 1912/529, loss: 0.005692754406481981
2023-01-24 08:42:20.932802: step: 1916/529, loss: 0.007508687674999237
2023-01-24 08:42:22.070289: step: 1920/529, loss: 0.010715275071561337
2023-01-24 08:42:23.175459: step: 1924/529, loss: 0.014799711294472218
2023-01-24 08:42:24.280603: step: 1928/529, loss: 0.03008132614195347
2023-01-24 08:42:25.415191: step: 1932/529, loss: 0.0021488473284989595
2023-01-24 08:42:26.527055: step: 1936/529, loss: 0.00580828869715333
2023-01-24 08:42:27.636386: step: 1940/529, loss: 0.0005442879046313465
2023-01-24 08:42:28.739548: step: 1944/529, loss: 0.0023842223454266787
2023-01-24 08:42:29.855275: step: 1948/529, loss: 0.010349349118769169
2023-01-24 08:42:30.964382: step: 1952/529, loss: 0.005742854438722134
2023-01-24 08:42:32.100447: step: 1956/529, loss: 0.005746699869632721
2023-01-24 08:42:33.191121: step: 1960/529, loss: 0.0030572963878512383
2023-01-24 08:42:34.285006: step: 1964/529, loss: 0.002705326536670327
2023-01-24 08:42:35.430123: step: 1968/529, loss: 0.0017700176686048508
2023-01-24 08:42:36.523745: step: 1972/529, loss: 0.0073394086211919785
2023-01-24 08:42:37.641311: step: 1976/529, loss: 0.006702421233057976
2023-01-24 08:42:38.724542: step: 1980/529, loss: 0.00996773038059473
2023-01-24 08:42:39.820366: step: 1984/529, loss: 0.0006468212814070284
2023-01-24 08:42:40.925130: step: 1988/529, loss: 0.010966029949486256
2023-01-24 08:42:42.019166: step: 1992/529, loss: 0.017896467819809914
2023-01-24 08:42:43.130024: step: 1996/529, loss: 0.005553707480430603
2023-01-24 08:42:44.242097: step: 2000/529, loss: 0.001417280058376491
2023-01-24 08:42:45.337093: step: 2004/529, loss: 0.002545019146054983
2023-01-24 08:42:46.444104: step: 2008/529, loss: 0.008214138448238373
2023-01-24 08:42:47.554315: step: 2012/529, loss: 0.004287917632609606
2023-01-24 08:42:48.661301: step: 2016/529, loss: 0.001959157409146428
2023-01-24 08:42:49.760001: step: 2020/529, loss: 0.009076257236301899
2023-01-24 08:42:50.851023: step: 2024/529, loss: 0.0019160517258569598
2023-01-24 08:42:51.958628: step: 2028/529, loss: 0.0029994845390319824
2023-01-24 08:42:53.104999: step: 2032/529, loss: 0.019224248826503754
2023-01-24 08:42:54.227884: step: 2036/529, loss: 0.0018323797266930342
2023-01-24 08:42:55.337002: step: 2040/529, loss: 0.008813927881419659
2023-01-24 08:42:56.443261: step: 2044/529, loss: 0.0007864231592975557
2023-01-24 08:42:57.553243: step: 2048/529, loss: 0.009530700743198395
2023-01-24 08:42:58.649232: step: 2052/529, loss: 0.005855603143572807
2023-01-24 08:42:59.753845: step: 2056/529, loss: 0.0010591085301712155
2023-01-24 08:43:00.852299: step: 2060/529, loss: 0.015139475464820862
2023-01-24 08:43:01.967874: step: 2064/529, loss: 0.014226407743990421
2023-01-24 08:43:03.083345: step: 2068/529, loss: 0.005667650606483221
2023-01-24 08:43:04.192311: step: 2072/529, loss: 0.008938327431678772
2023-01-24 08:43:05.304964: step: 2076/529, loss: 0.059929583221673965
2023-01-24 08:43:06.411611: step: 2080/529, loss: 0.01760035566985607
2023-01-24 08:43:07.542665: step: 2084/529, loss: 0.004652060568332672
2023-01-24 08:43:08.629578: step: 2088/529, loss: 0.0022942896466702223
2023-01-24 08:43:09.744019: step: 2092/529, loss: 0.009372753091156483
2023-01-24 08:43:10.836474: step: 2096/529, loss: 0.011929132975637913
2023-01-24 08:43:11.935391: step: 2100/529, loss: 0.003926228266209364
2023-01-24 08:43:13.064457: step: 2104/529, loss: 0.03250231221318245
2023-01-24 08:43:14.169028: step: 2108/529, loss: 0.021480895578861237
2023-01-24 08:43:15.252771: step: 2112/529, loss: 0.0008534525986760855
2023-01-24 08:43:16.357068: step: 2116/529, loss: 0.002471882151439786
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37737096516458934, 'r': 0.3200850501490919, 'f1': 0.34637540334408917}, 'combined': 0.2552239814114341, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.4008477468896398, 'r': 0.28701392785950836, 'f1': 0.334511691904876}, 'combined': 0.20560230819519207, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3708004312514429, 'r': 0.3313984878926558, 'f1': 0.34999399422731386}, 'combined': 0.25789031153591546, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3806509412780566, 'r': 0.2915904957450624, 'f1': 0.33022122874367227}, 'combined': 0.2029652430326961, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40853932584269664, 'r': 0.34497153700189753, 'f1': 0.37407407407407406}, 'combined': 0.2756335282651072, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3985091460632015, 'r': 0.2859320389430943, 'f1': 0.33296223303766986}, 'combined': 0.20565314393503142, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 7
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:45:42.559758: step: 4/529, loss: 0.0030545054469257593
2023-01-24 08:45:43.679259: step: 8/529, loss: 3.35619188263081e-05
2023-01-24 08:45:44.746503: step: 12/529, loss: 0.0008464528946205974
2023-01-24 08:45:45.902838: step: 16/529, loss: 0.0038379754405468702
2023-01-24 08:45:47.011042: step: 20/529, loss: 0.021549325436353683
2023-01-24 08:45:48.135582: step: 24/529, loss: 0.0104114580899477
2023-01-24 08:45:49.261166: step: 28/529, loss: 0.011546680703759193
2023-01-24 08:45:50.354794: step: 32/529, loss: 0.0034092096611857414
2023-01-24 08:45:51.451022: step: 36/529, loss: 0.002887334441766143
2023-01-24 08:45:52.572335: step: 40/529, loss: 0.0013238664250820875
2023-01-24 08:45:53.697625: step: 44/529, loss: 0.00871653389185667
2023-01-24 08:45:54.824934: step: 48/529, loss: 0.008016478270292282
2023-01-24 08:45:55.935724: step: 52/529, loss: 0.009020499885082245
2023-01-24 08:45:57.030685: step: 56/529, loss: 0.007172887679189444
2023-01-24 08:45:58.124181: step: 60/529, loss: 0.007009623106569052
2023-01-24 08:45:59.233662: step: 64/529, loss: 0.0005968121695332229
2023-01-24 08:46:00.340819: step: 68/529, loss: 0.0018050582148134708
2023-01-24 08:46:01.450015: step: 72/529, loss: 0.0016797339776530862
2023-01-24 08:46:02.551605: step: 76/529, loss: 0.007626965641975403
2023-01-24 08:46:03.656515: step: 80/529, loss: 0.010014185681939125
2023-01-24 08:46:04.773200: step: 84/529, loss: 0.003433970967307687
2023-01-24 08:46:05.874961: step: 88/529, loss: 0.004399940371513367
2023-01-24 08:46:06.943844: step: 92/529, loss: 0.0033530103974044323
2023-01-24 08:46:08.044361: step: 96/529, loss: 0.00021855183877050877
2023-01-24 08:46:09.146496: step: 100/529, loss: 0.0024746328126639128
2023-01-24 08:46:10.226543: step: 104/529, loss: 4.1829844121821225e-05
2023-01-24 08:46:11.303176: step: 108/529, loss: 0.0035631083883345127
2023-01-24 08:46:12.411138: step: 112/529, loss: 0.05124026536941528
2023-01-24 08:46:13.535763: step: 116/529, loss: 0.010831589810550213
2023-01-24 08:46:14.662805: step: 120/529, loss: 0.022203927859663963
2023-01-24 08:46:15.782433: step: 124/529, loss: 0.0019304860616102815
2023-01-24 08:46:16.888842: step: 128/529, loss: 0.0015121285105124116
2023-01-24 08:46:18.005284: step: 132/529, loss: 0.0012433846713975072
2023-01-24 08:46:19.105441: step: 136/529, loss: 0.007195828948169947
2023-01-24 08:46:20.236649: step: 140/529, loss: 0.051155611872673035
2023-01-24 08:46:21.358749: step: 144/529, loss: 0.022610561922192574
2023-01-24 08:46:22.464136: step: 148/529, loss: 0.015706732869148254
2023-01-24 08:46:23.586975: step: 152/529, loss: 0.009368144907057285
2023-01-24 08:46:24.722600: step: 156/529, loss: 0.021543605253100395
2023-01-24 08:46:25.841830: step: 160/529, loss: 0.007966682314872742
2023-01-24 08:46:26.949764: step: 164/529, loss: 0.0033177065197378397
2023-01-24 08:46:28.065755: step: 168/529, loss: 0.0019967108964920044
2023-01-24 08:46:29.171507: step: 172/529, loss: 0.007210269570350647
2023-01-24 08:46:30.288653: step: 176/529, loss: 0.004201869014650583
2023-01-24 08:46:31.428933: step: 180/529, loss: 0.003667253302410245
2023-01-24 08:46:32.544214: step: 184/529, loss: 0.015110588632524014
2023-01-24 08:46:33.653026: step: 188/529, loss: 0.006328313611447811
2023-01-24 08:46:34.748535: step: 192/529, loss: 0.00014509470202028751
2023-01-24 08:46:35.865946: step: 196/529, loss: 0.006437382660806179
2023-01-24 08:46:36.982142: step: 200/529, loss: 0.01717740297317505
2023-01-24 08:46:38.088841: step: 204/529, loss: 0.016561701893806458
2023-01-24 08:46:39.213309: step: 208/529, loss: 0.004435568116605282
2023-01-24 08:46:40.328971: step: 212/529, loss: 0.0149191003292799
2023-01-24 08:46:41.432869: step: 216/529, loss: 0.012894520536065102
2023-01-24 08:46:42.547409: step: 220/529, loss: 0.0027414702344685793
2023-01-24 08:46:43.654853: step: 224/529, loss: 0.0025472422130405903
2023-01-24 08:46:44.746751: step: 228/529, loss: 0.020510386675596237
2023-01-24 08:46:45.846299: step: 232/529, loss: 0.00802549161016941
2023-01-24 08:46:46.952699: step: 236/529, loss: 0.015726827085018158
2023-01-24 08:46:48.065536: step: 240/529, loss: 0.010865849442780018
2023-01-24 08:46:49.157692: step: 244/529, loss: 0.008605439215898514
2023-01-24 08:46:50.258973: step: 248/529, loss: 0.009382029995322227
2023-01-24 08:46:51.372475: step: 252/529, loss: 0.007287350948899984
2023-01-24 08:46:52.468633: step: 256/529, loss: 0.007945645600557327
2023-01-24 08:46:53.568979: step: 260/529, loss: 0.0009632874862290919
2023-01-24 08:46:54.685497: step: 264/529, loss: 0.005275438539683819
2023-01-24 08:46:55.799961: step: 268/529, loss: 0.0007581347017548978
2023-01-24 08:46:56.911856: step: 272/529, loss: 0.015828052535653114
2023-01-24 08:46:58.018773: step: 276/529, loss: 0.006983165629208088
2023-01-24 08:46:59.133550: step: 280/529, loss: 0.010498067364096642
2023-01-24 08:47:00.232925: step: 284/529, loss: 0.007609185762703419
2023-01-24 08:47:01.339497: step: 288/529, loss: 0.007381083443760872
2023-01-24 08:47:02.437075: step: 292/529, loss: 0.0025392977986484766
2023-01-24 08:47:03.550957: step: 296/529, loss: 0.0058061471208930016
2023-01-24 08:47:04.660624: step: 300/529, loss: 0.022824106737971306
2023-01-24 08:47:05.791089: step: 304/529, loss: 0.004457931034266949
2023-01-24 08:47:06.903129: step: 308/529, loss: 0.007100955583155155
2023-01-24 08:47:08.023310: step: 312/529, loss: 0.009412058629095554
2023-01-24 08:47:09.147961: step: 316/529, loss: 0.013740717433393002
2023-01-24 08:47:10.277207: step: 320/529, loss: 0.0007836969452910125
2023-01-24 08:47:11.385665: step: 324/529, loss: 0.0025598241481930017
2023-01-24 08:47:12.490527: step: 328/529, loss: 0.00013891237904317677
2023-01-24 08:47:13.593686: step: 332/529, loss: 0.029512524604797363
2023-01-24 08:47:14.697981: step: 336/529, loss: 0.0036302239168435335
2023-01-24 08:47:15.792699: step: 340/529, loss: 0.0012657804181799293
2023-01-24 08:47:16.912905: step: 344/529, loss: 0.006451549474149942
2023-01-24 08:47:18.017374: step: 348/529, loss: 0.0017815489554777741
2023-01-24 08:47:19.117842: step: 352/529, loss: 0.0008167997002601624
2023-01-24 08:47:20.216512: step: 356/529, loss: 0.0016680710250511765
2023-01-24 08:47:21.360418: step: 360/529, loss: 0.006359196733683348
2023-01-24 08:47:22.449806: step: 364/529, loss: 0.003547897795215249
2023-01-24 08:47:23.581896: step: 368/529, loss: 0.018223920837044716
2023-01-24 08:47:24.696364: step: 372/529, loss: 0.0040784962475299835
2023-01-24 08:47:25.821710: step: 376/529, loss: 0.002145932288840413
2023-01-24 08:47:26.937229: step: 380/529, loss: 0.009615127928555012
2023-01-24 08:47:28.061656: step: 384/529, loss: 0.022602489218115807
2023-01-24 08:47:29.164188: step: 388/529, loss: 0.005098290741443634
2023-01-24 08:47:30.284464: step: 392/529, loss: 0.010976966470479965
2023-01-24 08:47:31.384624: step: 396/529, loss: 0.013189560733735561
2023-01-24 08:47:32.480679: step: 400/529, loss: 0.007032593712210655
2023-01-24 08:47:33.584826: step: 404/529, loss: 0.019586682319641113
2023-01-24 08:47:34.689823: step: 408/529, loss: 0.006527661345899105
2023-01-24 08:47:35.810360: step: 412/529, loss: 0.013549278490245342
2023-01-24 08:47:36.922928: step: 416/529, loss: 0.025871869176626205
2023-01-24 08:47:38.039164: step: 420/529, loss: 0.0035328990779817104
2023-01-24 08:47:39.164993: step: 424/529, loss: 0.013496090658009052
2023-01-24 08:47:40.273277: step: 428/529, loss: 0.04311005398631096
2023-01-24 08:47:41.388733: step: 432/529, loss: 0.004175006877630949
2023-01-24 08:47:42.488745: step: 436/529, loss: 0.011185020208358765
2023-01-24 08:47:43.600379: step: 440/529, loss: 0.022860603407025337
2023-01-24 08:47:44.688477: step: 444/529, loss: 0.00024456216488033533
2023-01-24 08:47:45.777149: step: 448/529, loss: 0.0033862697891891003
2023-01-24 08:47:46.898959: step: 452/529, loss: 0.0021403245627880096
2023-01-24 08:47:48.009286: step: 456/529, loss: 0.003632894018664956
2023-01-24 08:47:49.115091: step: 460/529, loss: 0.016885651275515556
2023-01-24 08:47:50.226220: step: 464/529, loss: 0.0039877681992948055
2023-01-24 08:47:51.345308: step: 468/529, loss: 0.004039587918668985
2023-01-24 08:47:52.454617: step: 472/529, loss: 0.003896596608683467
2023-01-24 08:47:53.597487: step: 476/529, loss: 0.0023756225127726793
2023-01-24 08:47:54.705485: step: 480/529, loss: 0.018946556374430656
2023-01-24 08:47:55.803231: step: 484/529, loss: 0.0030556556303054094
2023-01-24 08:47:56.928354: step: 488/529, loss: 0.012143340893089771
2023-01-24 08:47:58.050165: step: 492/529, loss: 0.014629404060542583
2023-01-24 08:47:59.162531: step: 496/529, loss: 0.003899217117577791
2023-01-24 08:48:00.251044: step: 500/529, loss: 0.0001421123306499794
2023-01-24 08:48:01.379451: step: 504/529, loss: 0.0795435756444931
2023-01-24 08:48:02.483215: step: 508/529, loss: 0.0029668051283806562
2023-01-24 08:48:03.569083: step: 512/529, loss: 0.006415557116270065
2023-01-24 08:48:04.681724: step: 516/529, loss: 0.0025698819663375616
2023-01-24 08:48:05.797628: step: 520/529, loss: 0.05516723170876503
2023-01-24 08:48:06.893958: step: 524/529, loss: 0.005604919046163559
2023-01-24 08:48:08.007105: step: 528/529, loss: 0.002612817334011197
2023-01-24 08:48:09.106696: step: 532/529, loss: 0.003561482299119234
2023-01-24 08:48:10.178374: step: 536/529, loss: 0.018908070400357246
2023-01-24 08:48:11.290999: step: 540/529, loss: 0.00021792951156385243
2023-01-24 08:48:12.421129: step: 544/529, loss: 0.006110842805355787
2023-01-24 08:48:13.535286: step: 548/529, loss: 0.03918713703751564
2023-01-24 08:48:14.652090: step: 552/529, loss: 0.050406988710165024
2023-01-24 08:48:15.769064: step: 556/529, loss: 0.0017296071164309978
2023-01-24 08:48:16.862243: step: 560/529, loss: 0.00035165162989869714
2023-01-24 08:48:18.013752: step: 564/529, loss: 0.008679358288645744
2023-01-24 08:48:19.126787: step: 568/529, loss: 0.007770695257931948
2023-01-24 08:48:20.219225: step: 572/529, loss: 0.0034984855446964502
2023-01-24 08:48:21.326678: step: 576/529, loss: 0.0037792366929352283
2023-01-24 08:48:22.469969: step: 580/529, loss: 0.008669867180287838
2023-01-24 08:48:23.574589: step: 584/529, loss: 0.007455957587808371
2023-01-24 08:48:24.679254: step: 588/529, loss: 0.003013304201886058
2023-01-24 08:48:25.765560: step: 592/529, loss: 0.007323120720684528
2023-01-24 08:48:26.865524: step: 596/529, loss: 0.031962260603904724
2023-01-24 08:48:27.969794: step: 600/529, loss: 0.01004704274237156
2023-01-24 08:48:29.079617: step: 604/529, loss: 0.0027537778951227665
2023-01-24 08:48:30.167048: step: 608/529, loss: 0.002929972717538476
2023-01-24 08:48:31.274105: step: 612/529, loss: 0.005249975249171257
2023-01-24 08:48:32.371598: step: 616/529, loss: 0.009610047563910484
2023-01-24 08:48:33.480647: step: 620/529, loss: 0.007955987937748432
2023-01-24 08:48:34.597486: step: 624/529, loss: 0.03379003331065178
2023-01-24 08:48:35.696144: step: 628/529, loss: 0.002837971318513155
2023-01-24 08:48:36.802230: step: 632/529, loss: 0.0021671061404049397
2023-01-24 08:48:37.903898: step: 636/529, loss: 0.004177336115390062
2023-01-24 08:48:39.027587: step: 640/529, loss: 0.0038862500805407763
2023-01-24 08:48:40.132747: step: 644/529, loss: 0.02319229766726494
2023-01-24 08:48:41.234616: step: 648/529, loss: 0.017669769003987312
2023-01-24 08:48:42.332511: step: 652/529, loss: 0.0007057110778987408
2023-01-24 08:48:43.448367: step: 656/529, loss: 0.0055283447727561
2023-01-24 08:48:44.548287: step: 660/529, loss: 0.006416219752281904
2023-01-24 08:48:45.656424: step: 664/529, loss: 0.005335769150406122
2023-01-24 08:48:46.766525: step: 668/529, loss: 0.004108957014977932
2023-01-24 08:48:47.866149: step: 672/529, loss: 0.03745479881763458
2023-01-24 08:48:48.966466: step: 676/529, loss: 0.0017263751942664385
2023-01-24 08:48:50.064574: step: 680/529, loss: 0.017309946939349174
2023-01-24 08:48:51.174448: step: 684/529, loss: 0.0035648455377668142
2023-01-24 08:48:52.277791: step: 688/529, loss: 0.0004801817412953824
2023-01-24 08:48:53.373202: step: 692/529, loss: 0.006715321913361549
2023-01-24 08:48:54.479877: step: 696/529, loss: 0.014194621704518795
2023-01-24 08:48:55.595202: step: 700/529, loss: 0.0041891890577971935
2023-01-24 08:48:56.698654: step: 704/529, loss: 0.018518999218940735
2023-01-24 08:48:57.816396: step: 708/529, loss: 0.0025279333349317312
2023-01-24 08:48:58.915609: step: 712/529, loss: 0.0013000944163650274
2023-01-24 08:49:00.027749: step: 716/529, loss: 0.017144083976745605
2023-01-24 08:49:01.151533: step: 720/529, loss: 0.00548380333930254
2023-01-24 08:49:02.245239: step: 724/529, loss: 0.02012791484594345
2023-01-24 08:49:03.351028: step: 728/529, loss: 0.0026749796234071255
2023-01-24 08:49:04.478112: step: 732/529, loss: 0.06688763201236725
2023-01-24 08:49:05.580813: step: 736/529, loss: 0.0020136148668825626
2023-01-24 08:49:06.677890: step: 740/529, loss: 0.006192317232489586
2023-01-24 08:49:07.796686: step: 744/529, loss: 0.0007998402579687536
2023-01-24 08:49:08.907936: step: 748/529, loss: 0.0008538974216207862
2023-01-24 08:49:10.010627: step: 752/529, loss: 0.01586047187447548
2023-01-24 08:49:11.116310: step: 756/529, loss: 0.005411903373897076
2023-01-24 08:49:12.229073: step: 760/529, loss: 0.014611969701945782
2023-01-24 08:49:13.348399: step: 764/529, loss: 0.00531504862010479
2023-01-24 08:49:14.444842: step: 768/529, loss: 0.008997040800750256
2023-01-24 08:49:15.555013: step: 772/529, loss: 0.007737362757325172
2023-01-24 08:49:16.656376: step: 776/529, loss: 0.01996825635433197
2023-01-24 08:49:17.758143: step: 780/529, loss: 0.006075692363083363
2023-01-24 08:49:18.867315: step: 784/529, loss: 0.007126900367438793
2023-01-24 08:49:19.963137: step: 788/529, loss: 0.006055962294340134
2023-01-24 08:49:21.074800: step: 792/529, loss: 0.00789804756641388
2023-01-24 08:49:22.179514: step: 796/529, loss: 0.006226102355867624
2023-01-24 08:49:23.301816: step: 800/529, loss: 0.008890541270375252
2023-01-24 08:49:24.390694: step: 804/529, loss: 0.0018181040650233626
2023-01-24 08:49:25.513594: step: 808/529, loss: 0.03955285623669624
2023-01-24 08:49:26.632997: step: 812/529, loss: 0.0028145357500761747
2023-01-24 08:49:27.731011: step: 816/529, loss: 0.0006396938697434962
2023-01-24 08:49:28.830278: step: 820/529, loss: 0.001901389448903501
2023-01-24 08:49:29.948670: step: 824/529, loss: 0.0016176918288692832
2023-01-24 08:49:31.062437: step: 828/529, loss: 0.003536874894052744
2023-01-24 08:49:32.179012: step: 832/529, loss: 0.015310823917388916
2023-01-24 08:49:33.255115: step: 836/529, loss: 0.0036519435234367847
2023-01-24 08:49:34.330738: step: 840/529, loss: 0.0005294833099469543
2023-01-24 08:49:35.429606: step: 844/529, loss: 0.0041089183650910854
2023-01-24 08:49:36.529455: step: 848/529, loss: 0.008666718378663063
2023-01-24 08:49:37.619934: step: 852/529, loss: 0.003968899138271809
2023-01-24 08:49:38.720390: step: 856/529, loss: 0.012749884277582169
2023-01-24 08:49:39.807423: step: 860/529, loss: 0.008709506131708622
2023-01-24 08:49:40.919342: step: 864/529, loss: 0.041848987340927124
2023-01-24 08:49:42.004861: step: 868/529, loss: 0.0026900023221969604
2023-01-24 08:49:43.127557: step: 872/529, loss: 0.037015657871961594
2023-01-24 08:49:44.232896: step: 876/529, loss: 0.004798011854290962
2023-01-24 08:49:45.346685: step: 880/529, loss: 0.0014959161635488272
2023-01-24 08:49:46.454104: step: 884/529, loss: 0.006169901229441166
2023-01-24 08:49:47.571636: step: 888/529, loss: 0.011533129960298538
2023-01-24 08:49:48.678134: step: 892/529, loss: 0.01700163260102272
2023-01-24 08:49:49.780349: step: 896/529, loss: 0.0006934865959919989
2023-01-24 08:49:50.911017: step: 900/529, loss: 0.049045197665691376
2023-01-24 08:49:52.015869: step: 904/529, loss: 0.009306986816227436
2023-01-24 08:49:53.157199: step: 908/529, loss: 0.0069193728268146515
2023-01-24 08:49:54.275292: step: 912/529, loss: 0.004257889464497566
2023-01-24 08:49:55.381098: step: 916/529, loss: 0.0010051759891211987
2023-01-24 08:49:56.482470: step: 920/529, loss: 0.006709117908030748
2023-01-24 08:49:57.607890: step: 924/529, loss: 0.00445249117910862
2023-01-24 08:49:58.721790: step: 928/529, loss: 0.003797889454290271
2023-01-24 08:49:59.841751: step: 932/529, loss: 0.01634194888174534
2023-01-24 08:50:00.956465: step: 936/529, loss: 0.006429014727473259
2023-01-24 08:50:02.089889: step: 940/529, loss: 0.000796058913692832
2023-01-24 08:50:03.195694: step: 944/529, loss: 0.012223836965858936
2023-01-24 08:50:04.310650: step: 948/529, loss: 0.0038601565174758434
2023-01-24 08:50:05.425466: step: 952/529, loss: 0.010627320036292076
2023-01-24 08:50:06.553108: step: 956/529, loss: 0.005791979841887951
2023-01-24 08:50:07.652923: step: 960/529, loss: 0.0020676245912909508
2023-01-24 08:50:08.756032: step: 964/529, loss: 0.002595597179606557
2023-01-24 08:50:09.842738: step: 968/529, loss: 0.011650782078504562
2023-01-24 08:50:10.937937: step: 972/529, loss: 0.023557884618639946
2023-01-24 08:50:12.028722: step: 976/529, loss: 0.0024959726724773645
2023-01-24 08:50:13.153367: step: 980/529, loss: 0.009766514413058758
2023-01-24 08:50:14.273849: step: 984/529, loss: 0.008665000088512897
2023-01-24 08:50:15.380069: step: 988/529, loss: 0.012160072103142738
2023-01-24 08:50:16.492874: step: 992/529, loss: 0.003717874875292182
2023-01-24 08:50:17.610389: step: 996/529, loss: 0.0007553992327302694
2023-01-24 08:50:18.720504: step: 1000/529, loss: 0.0009899020660668612
2023-01-24 08:50:19.822405: step: 1004/529, loss: 0.00651220278814435
2023-01-24 08:50:20.927180: step: 1008/529, loss: 0.004271156154572964
2023-01-24 08:50:22.023740: step: 1012/529, loss: 0.0027377386577427387
2023-01-24 08:50:23.128141: step: 1016/529, loss: 0.0012419747654348612
2023-01-24 08:50:24.219627: step: 1020/529, loss: 0.005044716876000166
2023-01-24 08:50:25.329803: step: 1024/529, loss: 0.003990651108324528
2023-01-24 08:50:26.451077: step: 1028/529, loss: 0.004522216971963644
2023-01-24 08:50:27.566872: step: 1032/529, loss: 0.010923494584858418
2023-01-24 08:50:28.665685: step: 1036/529, loss: 0.0027218852192163467
2023-01-24 08:50:29.761216: step: 1040/529, loss: 0.001818226301111281
2023-01-24 08:50:30.852929: step: 1044/529, loss: 0.021147651597857475
2023-01-24 08:50:31.955761: step: 1048/529, loss: 0.008560696616768837
2023-01-24 08:50:33.044525: step: 1052/529, loss: 0.00042288025724701583
2023-01-24 08:50:34.138317: step: 1056/529, loss: 0.003587961196899414
2023-01-24 08:50:35.252245: step: 1060/529, loss: 0.004614383447915316
2023-01-24 08:50:36.353127: step: 1064/529, loss: 0.001856955816037953
2023-01-24 08:50:37.429352: step: 1068/529, loss: 0.0
2023-01-24 08:50:38.549914: step: 1072/529, loss: 0.022344503551721573
2023-01-24 08:50:39.676492: step: 1076/529, loss: 0.00451620202511549
2023-01-24 08:50:40.798167: step: 1080/529, loss: 0.020677490159869194
2023-01-24 08:50:41.911395: step: 1084/529, loss: 0.021734872832894325
2023-01-24 08:50:43.000734: step: 1088/529, loss: 0.01625116914510727
2023-01-24 08:50:44.125121: step: 1092/529, loss: 0.002873418852686882
2023-01-24 08:50:45.230418: step: 1096/529, loss: 0.003447467228397727
2023-01-24 08:50:46.343473: step: 1100/529, loss: 0.00568568566814065
2023-01-24 08:50:47.431433: step: 1104/529, loss: 0.013935388997197151
2023-01-24 08:50:48.532179: step: 1108/529, loss: 0.0036689352709800005
2023-01-24 08:50:49.658794: step: 1112/529, loss: 0.008914774283766747
2023-01-24 08:50:50.749812: step: 1116/529, loss: 0.0038859290070831776
2023-01-24 08:50:51.854592: step: 1120/529, loss: 0.005843544378876686
2023-01-24 08:50:52.964748: step: 1124/529, loss: 0.0038129333406686783
2023-01-24 08:50:54.065595: step: 1128/529, loss: 0.018381819128990173
2023-01-24 08:50:55.154992: step: 1132/529, loss: 0.0043317642994225025
2023-01-24 08:50:56.268154: step: 1136/529, loss: 0.0008181605953723192
2023-01-24 08:50:57.362338: step: 1140/529, loss: 0.033095523715019226
2023-01-24 08:50:58.466132: step: 1144/529, loss: 0.008096587844192982
2023-01-24 08:50:59.567665: step: 1148/529, loss: 0.010569499805569649
2023-01-24 08:51:00.653876: step: 1152/529, loss: 0.005974179599434137
2023-01-24 08:51:01.760001: step: 1156/529, loss: 0.0011172093218192458
2023-01-24 08:51:02.853100: step: 1160/529, loss: 0.0009726683492772281
2023-01-24 08:51:03.952432: step: 1164/529, loss: 0.007001920137554407
2023-01-24 08:51:05.066553: step: 1168/529, loss: 0.018469376489520073
2023-01-24 08:51:06.178006: step: 1172/529, loss: 0.004775014240294695
2023-01-24 08:51:07.267490: step: 1176/529, loss: 0.0003716326900757849
2023-01-24 08:51:08.405449: step: 1180/529, loss: 0.009061123244464397
2023-01-24 08:51:09.511785: step: 1184/529, loss: 0.007884989492595196
2023-01-24 08:51:10.597614: step: 1188/529, loss: 0.005078867077827454
2023-01-24 08:51:11.706722: step: 1192/529, loss: 0.003576371818780899
2023-01-24 08:51:12.806304: step: 1196/529, loss: 0.002088880632072687
2023-01-24 08:51:13.915141: step: 1200/529, loss: 0.0030322414822876453
2023-01-24 08:51:15.002235: step: 1204/529, loss: 0.004681067541241646
2023-01-24 08:51:16.086117: step: 1208/529, loss: 0.0013306960463523865
2023-01-24 08:51:17.173034: step: 1212/529, loss: 0.004194363951683044
2023-01-24 08:51:18.272032: step: 1216/529, loss: 0.016724074259400368
2023-01-24 08:51:19.365375: step: 1220/529, loss: 0.013624606654047966
2023-01-24 08:51:20.477756: step: 1224/529, loss: 0.002238082466647029
2023-01-24 08:51:21.566373: step: 1228/529, loss: 0.012839583680033684
2023-01-24 08:51:22.670370: step: 1232/529, loss: 0.0002458159578964114
2023-01-24 08:51:23.790862: step: 1236/529, loss: 0.038128044456243515
2023-01-24 08:51:24.882546: step: 1240/529, loss: 0.0018575232243165374
2023-01-24 08:51:25.985930: step: 1244/529, loss: 0.010543646290898323
2023-01-24 08:51:27.111466: step: 1248/529, loss: 0.00048154941760003567
2023-01-24 08:51:28.197368: step: 1252/529, loss: 0.03804149478673935
2023-01-24 08:51:29.291101: step: 1256/529, loss: 0.00981319323182106
2023-01-24 08:51:30.388570: step: 1260/529, loss: 0.00769336661323905
2023-01-24 08:51:31.502435: step: 1264/529, loss: 0.010434003546833992
2023-01-24 08:51:32.622312: step: 1268/529, loss: 0.016274206340312958
2023-01-24 08:51:33.730890: step: 1272/529, loss: 0.006919366307556629
2023-01-24 08:51:34.822343: step: 1276/529, loss: 0.0007365404744632542
2023-01-24 08:51:35.928504: step: 1280/529, loss: 0.006953903939574957
2023-01-24 08:51:37.036371: step: 1284/529, loss: 0.004470301792025566
2023-01-24 08:51:38.168364: step: 1288/529, loss: 0.005321430508047342
2023-01-24 08:51:39.259346: step: 1292/529, loss: 0.01020444743335247
2023-01-24 08:51:40.334556: step: 1296/529, loss: 0.00046618375927209854
2023-01-24 08:51:41.461546: step: 1300/529, loss: 0.003094441257417202
2023-01-24 08:51:42.556629: step: 1304/529, loss: 0.015473908744752407
2023-01-24 08:51:43.673129: step: 1308/529, loss: 0.006819084752351046
2023-01-24 08:51:44.820065: step: 1312/529, loss: 0.008944142609834671
2023-01-24 08:51:45.939320: step: 1316/529, loss: 0.00334442057646811
2023-01-24 08:51:47.035674: step: 1320/529, loss: 0.005131879821419716
2023-01-24 08:51:48.133774: step: 1324/529, loss: 0.011224307119846344
2023-01-24 08:51:49.250416: step: 1328/529, loss: 0.0012206730898469687
2023-01-24 08:51:50.362498: step: 1332/529, loss: 0.00507092522457242
2023-01-24 08:51:51.467615: step: 1336/529, loss: 0.0077430796809494495
2023-01-24 08:51:52.568286: step: 1340/529, loss: 0.02381853014230728
2023-01-24 08:51:53.678665: step: 1344/529, loss: 0.003044499782845378
2023-01-24 08:51:54.779048: step: 1348/529, loss: 0.008158575743436813
2023-01-24 08:51:55.894394: step: 1352/529, loss: 0.006804183125495911
2023-01-24 08:51:56.992143: step: 1356/529, loss: 0.008868962526321411
2023-01-24 08:51:58.097895: step: 1360/529, loss: 0.0007548411376774311
2023-01-24 08:51:59.223451: step: 1364/529, loss: 0.0022392296232283115
2023-01-24 08:52:00.335524: step: 1368/529, loss: 0.0010228336323052645
2023-01-24 08:52:01.435501: step: 1372/529, loss: 0.0018546622013673186
2023-01-24 08:52:02.540622: step: 1376/529, loss: 0.0013475528685376048
2023-01-24 08:52:03.630878: step: 1380/529, loss: 0.02138546295464039
2023-01-24 08:52:04.722989: step: 1384/529, loss: 0.01893160119652748
2023-01-24 08:52:05.834123: step: 1388/529, loss: 0.004333828575909138
2023-01-24 08:52:06.933396: step: 1392/529, loss: 0.0010282692965120077
2023-01-24 08:52:08.059093: step: 1396/529, loss: 0.005786009132862091
2023-01-24 08:52:09.156045: step: 1400/529, loss: 0.01035977154970169
2023-01-24 08:52:10.264017: step: 1404/529, loss: 0.003354752669110894
2023-01-24 08:52:11.355746: step: 1408/529, loss: 0.0026946559082716703
2023-01-24 08:52:12.439032: step: 1412/529, loss: 0.006450484041124582
2023-01-24 08:52:13.542104: step: 1416/529, loss: 0.011759447865188122
2023-01-24 08:52:14.670532: step: 1420/529, loss: 0.041142694652080536
2023-01-24 08:52:15.808310: step: 1424/529, loss: 0.050200410187244415
2023-01-24 08:52:16.908377: step: 1428/529, loss: 0.002981449943035841
2023-01-24 08:52:18.063264: step: 1432/529, loss: 0.0008520122501067817
2023-01-24 08:52:19.202209: step: 1436/529, loss: 0.013236681930720806
2023-01-24 08:52:20.302804: step: 1440/529, loss: 0.005776203237473965
2023-01-24 08:52:21.392933: step: 1444/529, loss: 0.0004227413155604154
2023-01-24 08:52:22.515871: step: 1448/529, loss: 0.010980979539453983
2023-01-24 08:52:23.657525: step: 1452/529, loss: 0.0011604557512328029
2023-01-24 08:52:24.764091: step: 1456/529, loss: 0.0015585614601150155
2023-01-24 08:52:25.870529: step: 1460/529, loss: 0.004838043358176947
2023-01-24 08:52:26.982523: step: 1464/529, loss: 0.013198030181229115
2023-01-24 08:52:28.070019: step: 1468/529, loss: 0.0022277210373431444
2023-01-24 08:52:29.170040: step: 1472/529, loss: 0.06916091591119766
2023-01-24 08:52:30.278507: step: 1476/529, loss: 0.008894179947674274
2023-01-24 08:52:31.402895: step: 1480/529, loss: 0.0009989392710849643
2023-01-24 08:52:32.496603: step: 1484/529, loss: 0.004288040567189455
2023-01-24 08:52:33.624263: step: 1488/529, loss: 0.005061854142695665
2023-01-24 08:52:34.727290: step: 1492/529, loss: 0.008063099347054958
2023-01-24 08:52:35.843640: step: 1496/529, loss: 0.00906107947230339
2023-01-24 08:52:36.939423: step: 1500/529, loss: 0.0030321567319333553
2023-01-24 08:52:38.037911: step: 1504/529, loss: 0.02668239176273346
2023-01-24 08:52:39.153979: step: 1508/529, loss: 0.0029460571240633726
2023-01-24 08:52:40.260570: step: 1512/529, loss: 0.00484667532145977
2023-01-24 08:52:41.357772: step: 1516/529, loss: 0.011024574749171734
2023-01-24 08:52:42.474532: step: 1520/529, loss: 0.007701247930526733
2023-01-24 08:52:43.590635: step: 1524/529, loss: 0.027079027146100998
2023-01-24 08:52:44.720551: step: 1528/529, loss: 0.002607388189062476
2023-01-24 08:52:45.807633: step: 1532/529, loss: 0.000754452426917851
2023-01-24 08:52:46.911171: step: 1536/529, loss: 0.002925124019384384
2023-01-24 08:52:47.994093: step: 1540/529, loss: 0.00450309831649065
2023-01-24 08:52:49.117509: step: 1544/529, loss: 0.003333688247948885
2023-01-24 08:52:50.203643: step: 1548/529, loss: 0.005743012297898531
2023-01-24 08:52:51.315331: step: 1552/529, loss: 0.012968389317393303
2023-01-24 08:52:52.431919: step: 1556/529, loss: 0.00378986494615674
2023-01-24 08:52:53.550424: step: 1560/529, loss: 0.0026724375784397125
2023-01-24 08:52:54.631725: step: 1564/529, loss: 0.0018774084746837616
2023-01-24 08:52:55.742507: step: 1568/529, loss: 0.015226670540869236
2023-01-24 08:52:56.813822: step: 1572/529, loss: 0.003603462828323245
2023-01-24 08:52:57.915154: step: 1576/529, loss: 0.01170405838638544
2023-01-24 08:52:59.056131: step: 1580/529, loss: 0.00882007461041212
2023-01-24 08:53:00.172146: step: 1584/529, loss: 0.0019141166703775525
2023-01-24 08:53:01.295022: step: 1588/529, loss: 0.016407420858740807
2023-01-24 08:53:02.396402: step: 1592/529, loss: 0.001737741520628333
2023-01-24 08:53:03.518812: step: 1596/529, loss: 0.0017130805645138025
2023-01-24 08:53:04.624883: step: 1600/529, loss: 0.006675695069134235
2023-01-24 08:53:05.739744: step: 1604/529, loss: 0.0036178254522383213
2023-01-24 08:53:06.835551: step: 1608/529, loss: 0.004487319383770227
2023-01-24 08:53:07.980491: step: 1612/529, loss: 0.005593766923993826
2023-01-24 08:53:09.097244: step: 1616/529, loss: 0.002983157057315111
2023-01-24 08:53:10.210880: step: 1620/529, loss: 0.01660698466002941
2023-01-24 08:53:11.312166: step: 1624/529, loss: 0.006098631769418716
2023-01-24 08:53:12.401936: step: 1628/529, loss: 0.06224154308438301
2023-01-24 08:53:13.510994: step: 1632/529, loss: 0.012845651246607304
2023-01-24 08:53:14.606938: step: 1636/529, loss: 0.0028631037566810846
2023-01-24 08:53:15.726145: step: 1640/529, loss: 0.0020831632427871227
2023-01-24 08:53:16.834712: step: 1644/529, loss: 0.007122849114239216
2023-01-24 08:53:17.951781: step: 1648/529, loss: 0.029846210032701492
2023-01-24 08:53:19.044456: step: 1652/529, loss: 0.012220275588333607
2023-01-24 08:53:20.156459: step: 1656/529, loss: 0.010339400731027126
2023-01-24 08:53:21.283857: step: 1660/529, loss: 0.004446351435035467
2023-01-24 08:53:22.368015: step: 1664/529, loss: 3.9849554013926536e-05
2023-01-24 08:53:23.480409: step: 1668/529, loss: 0.010926641523838043
2023-01-24 08:53:24.578798: step: 1672/529, loss: 0.009528790600597858
2023-01-24 08:53:25.669936: step: 1676/529, loss: 0.0038331919349730015
2023-01-24 08:53:26.782879: step: 1680/529, loss: 0.0112329525873065
2023-01-24 08:53:27.870646: step: 1684/529, loss: 0.0011112805223092437
2023-01-24 08:53:28.960765: step: 1688/529, loss: 0.005715968552976847
2023-01-24 08:53:30.057411: step: 1692/529, loss: 0.006637838669121265
2023-01-24 08:53:31.164567: step: 1696/529, loss: 0.01248794887214899
2023-01-24 08:53:32.266506: step: 1700/529, loss: 0.0009806236485019326
2023-01-24 08:53:33.389725: step: 1704/529, loss: 0.0025035240687429905
2023-01-24 08:53:34.488056: step: 1708/529, loss: 0.023603204637765884
2023-01-24 08:53:35.608523: step: 1712/529, loss: 0.0027091698721051216
2023-01-24 08:53:36.713745: step: 1716/529, loss: 0.015486306510865688
2023-01-24 08:53:37.829824: step: 1720/529, loss: 0.005725586786866188
2023-01-24 08:53:38.942634: step: 1724/529, loss: 0.003215622389689088
2023-01-24 08:53:40.042178: step: 1728/529, loss: 0.0015625227242708206
2023-01-24 08:53:41.127110: step: 1732/529, loss: 0.00022542999067809433
2023-01-24 08:53:42.239769: step: 1736/529, loss: 0.0006033622776158154
2023-01-24 08:53:43.331188: step: 1740/529, loss: 0.0012999210739508271
2023-01-24 08:53:44.434428: step: 1744/529, loss: 0.007129587698727846
2023-01-24 08:53:45.559135: step: 1748/529, loss: 0.004076377488672733
2023-01-24 08:53:46.658548: step: 1752/529, loss: 0.004623218439519405
2023-01-24 08:53:47.774416: step: 1756/529, loss: 0.0037794874515384436
2023-01-24 08:53:48.903566: step: 1760/529, loss: 0.0014138724654912949
2023-01-24 08:53:50.000040: step: 1764/529, loss: 0.00626613013446331
2023-01-24 08:53:51.110974: step: 1768/529, loss: 0.009518090635538101
2023-01-24 08:53:52.215257: step: 1772/529, loss: 0.0045984480530023575
2023-01-24 08:53:53.305388: step: 1776/529, loss: 0.004752174485474825
2023-01-24 08:53:54.409386: step: 1780/529, loss: 0.027641193941235542
2023-01-24 08:53:55.509858: step: 1784/529, loss: 0.019016485661268234
2023-01-24 08:53:56.618082: step: 1788/529, loss: 0.027889788150787354
2023-01-24 08:53:57.714467: step: 1792/529, loss: 0.0035197893157601357
2023-01-24 08:53:58.844345: step: 1796/529, loss: 0.006892375648021698
2023-01-24 08:53:59.961850: step: 1800/529, loss: 0.0014207635540515184
2023-01-24 08:54:01.053494: step: 1804/529, loss: 0.0018155979923903942
2023-01-24 08:54:02.176220: step: 1808/529, loss: 0.003822892904281616
2023-01-24 08:54:03.274105: step: 1812/529, loss: 0.026996824890375137
2023-01-24 08:54:04.376366: step: 1816/529, loss: 0.007372335530817509
2023-01-24 08:54:05.530494: step: 1820/529, loss: 0.011459797620773315
2023-01-24 08:54:06.635946: step: 1824/529, loss: 0.0035965193528681993
2023-01-24 08:54:07.729682: step: 1828/529, loss: 0.005146507173776627
2023-01-24 08:54:08.821378: step: 1832/529, loss: 0.0039470563642680645
2023-01-24 08:54:09.944154: step: 1836/529, loss: 0.006077685859054327
2023-01-24 08:54:11.067892: step: 1840/529, loss: 0.010810391046106815
2023-01-24 08:54:12.164828: step: 1844/529, loss: 0.007124264724552631
2023-01-24 08:54:13.272957: step: 1848/529, loss: 0.002527458593249321
2023-01-24 08:54:14.373793: step: 1852/529, loss: 0.031402889639139175
2023-01-24 08:54:15.493346: step: 1856/529, loss: 0.00225332984700799
2023-01-24 08:54:16.582064: step: 1860/529, loss: 0.00868365727365017
2023-01-24 08:54:17.679069: step: 1864/529, loss: 0.010610532015562057
2023-01-24 08:54:18.792225: step: 1868/529, loss: 0.006207606755197048
2023-01-24 08:54:19.900588: step: 1872/529, loss: 0.008675008080899715
2023-01-24 08:54:21.005798: step: 1876/529, loss: 0.0021586900111287832
2023-01-24 08:54:22.102631: step: 1880/529, loss: 0.005463351029902697
2023-01-24 08:54:23.214115: step: 1884/529, loss: 0.00015167509263847023
2023-01-24 08:54:24.342126: step: 1888/529, loss: 0.01060989685356617
2023-01-24 08:54:25.440830: step: 1892/529, loss: 0.0019999961368739605
2023-01-24 08:54:26.550197: step: 1896/529, loss: 0.017775509506464005
2023-01-24 08:54:27.665568: step: 1900/529, loss: 0.003965908195823431
2023-01-24 08:54:28.747586: step: 1904/529, loss: 0.0018829237669706345
2023-01-24 08:54:29.844320: step: 1908/529, loss: 0.0032470521982759237
2023-01-24 08:54:30.947012: step: 1912/529, loss: 0.021635238081216812
2023-01-24 08:54:32.082393: step: 1916/529, loss: 0.0054940590634942055
2023-01-24 08:54:33.195167: step: 1920/529, loss: 0.006706266663968563
2023-01-24 08:54:34.296295: step: 1924/529, loss: 0.00026026403065770864
2023-01-24 08:54:35.386912: step: 1928/529, loss: 0.0032187732867896557
2023-01-24 08:54:36.489973: step: 1932/529, loss: 0.005245766136795282
2023-01-24 08:54:37.580841: step: 1936/529, loss: 0.0030085307080298662
2023-01-24 08:54:38.702669: step: 1940/529, loss: 0.00255844509229064
2023-01-24 08:54:39.817419: step: 1944/529, loss: 0.0038450192660093307
2023-01-24 08:54:40.929418: step: 1948/529, loss: 0.05609880015254021
2023-01-24 08:54:42.025921: step: 1952/529, loss: 0.017728636041283607
2023-01-24 08:54:43.143435: step: 1956/529, loss: 0.010679494589567184
2023-01-24 08:54:44.228514: step: 1960/529, loss: 0.003283848287537694
2023-01-24 08:54:45.344961: step: 1964/529, loss: 0.006431478075683117
2023-01-24 08:54:46.439825: step: 1968/529, loss: 0.008664300665259361
2023-01-24 08:54:47.544100: step: 1972/529, loss: 0.0038368417881429195
2023-01-24 08:54:48.651873: step: 1976/529, loss: 0.007292424328625202
2023-01-24 08:54:49.750172: step: 1980/529, loss: 0.0028334050439298153
2023-01-24 08:54:50.853360: step: 1984/529, loss: 0.008170985616743565
2023-01-24 08:54:51.959054: step: 1988/529, loss: 0.04894591495394707
2023-01-24 08:54:53.078348: step: 1992/529, loss: 0.019697679206728935
2023-01-24 08:54:54.193095: step: 1996/529, loss: 0.0083999615162611
2023-01-24 08:54:55.301947: step: 2000/529, loss: 0.008980633690953255
2023-01-24 08:54:56.408980: step: 2004/529, loss: 0.009917245246469975
2023-01-24 08:54:57.505531: step: 2008/529, loss: 0.013036241754889488
2023-01-24 08:54:58.631043: step: 2012/529, loss: 0.009323484264314175
2023-01-24 08:54:59.743265: step: 2016/529, loss: 0.02634882926940918
2023-01-24 08:55:00.875238: step: 2020/529, loss: 0.012787842191755772
2023-01-24 08:55:01.974472: step: 2024/529, loss: 0.0032681659795343876
2023-01-24 08:55:03.087270: step: 2028/529, loss: 0.010101065039634705
2023-01-24 08:55:04.193019: step: 2032/529, loss: 0.0034691786859184504
2023-01-24 08:55:05.295668: step: 2036/529, loss: 0.035090502351522446
2023-01-24 08:55:06.410233: step: 2040/529, loss: 0.009759358130395412
2023-01-24 08:55:07.541003: step: 2044/529, loss: 0.010804848745465279
2023-01-24 08:55:08.639224: step: 2048/529, loss: 0.01250616554170847
2023-01-24 08:55:09.719166: step: 2052/529, loss: 0.004521224647760391
2023-01-24 08:55:10.808691: step: 2056/529, loss: 0.004803786985576153
2023-01-24 08:55:11.907820: step: 2060/529, loss: 0.006789981387555599
2023-01-24 08:55:12.988523: step: 2064/529, loss: 0.06477535516023636
2023-01-24 08:55:14.078913: step: 2068/529, loss: 0.004640466999262571
2023-01-24 08:55:15.166103: step: 2072/529, loss: 0.009149201214313507
2023-01-24 08:55:16.269550: step: 2076/529, loss: 0.009796473197638988
2023-01-24 08:55:17.369178: step: 2080/529, loss: 0.012918299064040184
2023-01-24 08:55:18.470467: step: 2084/529, loss: 0.007878929376602173
2023-01-24 08:55:19.568239: step: 2088/529, loss: 0.005031415726989508
2023-01-24 08:55:20.674538: step: 2092/529, loss: 4.6794557420071214e-05
2023-01-24 08:55:21.765074: step: 2096/529, loss: 0.005519380327314138
2023-01-24 08:55:22.858195: step: 2100/529, loss: 0.001372506027109921
2023-01-24 08:55:23.949928: step: 2104/529, loss: 0.012617439031600952
2023-01-24 08:55:25.052581: step: 2108/529, loss: 0.011319011449813843
2023-01-24 08:55:26.161664: step: 2112/529, loss: 0.0026188690681010485
2023-01-24 08:55:27.272719: step: 2116/529, loss: 0.002033472992479801
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3764138561883551, 'r': 0.320701748441312, 'f1': 0.3463316012880562}, 'combined': 0.2551917062122519, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.39842936720402916, 'r': 0.285529537848988, 'f1': 0.3326613696897851}, 'combined': 0.20446503698006305, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3668100841143684, 'r': 0.3292242310931618, 'f1': 0.34700233957219256}, 'combined': 0.2556859344216156, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38194714198615437, 'r': 0.2915904957450624, 'f1': 0.33070804136589876}, 'combined': 0.20326445469318655, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4031390134529148, 'r': 0.3411764705882353, 'f1': 0.3695786228160329}, 'combined': 0.2723210904960242, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39881107843035124, 'r': 0.28614867672472344, 'f1': 0.33321450347157505}, 'combined': 0.2058089580265611, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.358695652173913, 'f1': 0.375}, 'combined': 0.1875, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 8
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:57:49.424061: step: 4/529, loss: 0.010119680315256119
2023-01-24 08:57:50.524094: step: 8/529, loss: 0.005893799476325512
2023-01-24 08:57:51.621761: step: 12/529, loss: 0.004199305549263954
2023-01-24 08:57:52.734765: step: 16/529, loss: 0.005066265352070332
2023-01-24 08:57:53.818328: step: 20/529, loss: 0.004055889323353767
2023-01-24 08:57:54.901029: step: 24/529, loss: 0.0013050538254901767
2023-01-24 08:57:56.015582: step: 28/529, loss: 0.0009191795834340155
2023-01-24 08:57:57.100233: step: 32/529, loss: 0.012659515254199505
2023-01-24 08:57:58.200581: step: 36/529, loss: 0.00026151465135626495
2023-01-24 08:57:59.308355: step: 40/529, loss: 0.004720237571746111
2023-01-24 08:58:00.408378: step: 44/529, loss: 0.00812650378793478
2023-01-24 08:58:01.506867: step: 48/529, loss: 0.001217373413965106
2023-01-24 08:58:02.616370: step: 52/529, loss: 0.0032107161823660135
2023-01-24 08:58:03.711117: step: 56/529, loss: 0.0020576557144522667
2023-01-24 08:58:04.813518: step: 60/529, loss: 0.006836101412773132
2023-01-24 08:58:05.928686: step: 64/529, loss: 0.0418306328356266
2023-01-24 08:58:07.032206: step: 68/529, loss: 0.0013350642984732985
2023-01-24 08:58:08.120390: step: 72/529, loss: 0.0017905108397826552
2023-01-24 08:58:09.241104: step: 76/529, loss: 0.0018587341764941812
2023-01-24 08:58:10.339185: step: 80/529, loss: 0.0032744163181632757
2023-01-24 08:58:11.420675: step: 84/529, loss: 0.002595275640487671
2023-01-24 08:58:12.518499: step: 88/529, loss: 0.012285172939300537
2023-01-24 08:58:13.651812: step: 92/529, loss: 0.00601964583620429
2023-01-24 08:58:14.743960: step: 96/529, loss: 0.011044785380363464
2023-01-24 08:58:15.855654: step: 100/529, loss: 0.01676752045750618
2023-01-24 08:58:16.980835: step: 104/529, loss: 0.010028683580458164
2023-01-24 08:58:18.116319: step: 108/529, loss: 0.007332808803766966
2023-01-24 08:58:19.209556: step: 112/529, loss: 0.004588474985212088
2023-01-24 08:58:20.294708: step: 116/529, loss: 0.001440213294699788
2023-01-24 08:58:21.389646: step: 120/529, loss: 0.010107388719916344
2023-01-24 08:58:22.480270: step: 124/529, loss: 0.014141440391540527
2023-01-24 08:58:23.570133: step: 128/529, loss: 0.0010853768326342106
2023-01-24 08:58:24.663314: step: 132/529, loss: 0.0005682872142642736
2023-01-24 08:58:25.745994: step: 136/529, loss: 0.002661020727828145
2023-01-24 08:58:26.847951: step: 140/529, loss: 0.0005171256489120424
2023-01-24 08:58:27.949765: step: 144/529, loss: 0.005109234247356653
2023-01-24 08:58:29.044004: step: 148/529, loss: 0.018681224435567856
2023-01-24 08:58:30.124784: step: 152/529, loss: 0.00661963177844882
2023-01-24 08:58:31.244761: step: 156/529, loss: 0.0007853424758650362
2023-01-24 08:58:32.362231: step: 160/529, loss: 0.006194726563990116
2023-01-24 08:58:33.470656: step: 164/529, loss: 0.009804238565266132
2023-01-24 08:58:34.573156: step: 168/529, loss: 0.009070285595953465
2023-01-24 08:58:35.672747: step: 172/529, loss: 0.006323863286525011
2023-01-24 08:58:36.783994: step: 176/529, loss: 0.005981122609227896
2023-01-24 08:58:37.897556: step: 180/529, loss: 0.0038628876209259033
2023-01-24 08:58:38.995074: step: 184/529, loss: 0.001554613932967186
2023-01-24 08:58:40.075774: step: 188/529, loss: 0.00015930060180835426
2023-01-24 08:58:41.192468: step: 192/529, loss: 0.004268538672477007
2023-01-24 08:58:42.277043: step: 196/529, loss: 0.009430995211005211
2023-01-24 08:58:43.349140: step: 200/529, loss: 0.008636308833956718
2023-01-24 08:58:44.450878: step: 204/529, loss: 0.004446480888873339
2023-01-24 08:58:45.560121: step: 208/529, loss: 0.009354028850793839
2023-01-24 08:58:46.679103: step: 212/529, loss: 0.00013394693087320775
2023-01-24 08:58:47.770359: step: 216/529, loss: 0.0018775715725496411
2023-01-24 08:58:48.885384: step: 220/529, loss: 0.005348735488951206
2023-01-24 08:58:50.006145: step: 224/529, loss: 0.002338995458558202
2023-01-24 08:58:51.083551: step: 228/529, loss: 0.0
2023-01-24 08:58:52.161247: step: 232/529, loss: 0.007684392388910055
2023-01-24 08:58:53.250283: step: 236/529, loss: 0.000983944395557046
2023-01-24 08:58:54.344809: step: 240/529, loss: 0.005075910594314337
2023-01-24 08:58:55.461663: step: 244/529, loss: 0.007581962738186121
2023-01-24 08:58:56.548651: step: 248/529, loss: 0.007029070518910885
2023-01-24 08:58:57.630815: step: 252/529, loss: 0.012074478901922703
2023-01-24 08:58:58.739645: step: 256/529, loss: 0.006531259045004845
2023-01-24 08:58:59.848833: step: 260/529, loss: 0.002120832446962595
2023-01-24 08:59:00.960476: step: 264/529, loss: 0.0016957768239080906
2023-01-24 08:59:02.064182: step: 268/529, loss: 0.0282749030739069
2023-01-24 08:59:03.151247: step: 272/529, loss: 0.0012005006428807974
2023-01-24 08:59:04.237211: step: 276/529, loss: 0.0022363727912306786
2023-01-24 08:59:05.344550: step: 280/529, loss: 0.012153119780123234
2023-01-24 08:59:06.456355: step: 284/529, loss: 0.008582841604948044
2023-01-24 08:59:07.560877: step: 288/529, loss: 0.010345152579247952
2023-01-24 08:59:08.656556: step: 292/529, loss: 0.0053466204553842545
2023-01-24 08:59:09.753855: step: 296/529, loss: 0.003791054943576455
2023-01-24 08:59:10.841071: step: 300/529, loss: 0.004288640804588795
2023-01-24 08:59:11.951413: step: 304/529, loss: 0.012499445118010044
2023-01-24 08:59:13.057745: step: 308/529, loss: 0.008475806564092636
2023-01-24 08:59:14.143843: step: 312/529, loss: 0.0037184483371675014
2023-01-24 08:59:15.239157: step: 316/529, loss: 0.004467348102480173
2023-01-24 08:59:16.338873: step: 320/529, loss: 0.006024380214512348
2023-01-24 08:59:17.443612: step: 324/529, loss: 0.004249947145581245
2023-01-24 08:59:18.547882: step: 328/529, loss: 0.04182042181491852
2023-01-24 08:59:19.657590: step: 332/529, loss: 0.005245944485068321
2023-01-24 08:59:20.763954: step: 336/529, loss: 0.0010759185533970594
2023-01-24 08:59:21.872040: step: 340/529, loss: 0.009408141486346722
2023-01-24 08:59:22.955204: step: 344/529, loss: 0.0018801884725689888
2023-01-24 08:59:24.084368: step: 348/529, loss: 0.020278364419937134
2023-01-24 08:59:25.186930: step: 352/529, loss: 0.00014065821596886963
2023-01-24 08:59:26.273975: step: 356/529, loss: 0.0013568383874371648
2023-01-24 08:59:27.368526: step: 360/529, loss: 3.261092570028268e-05
2023-01-24 08:59:28.453321: step: 364/529, loss: 0.00794623326510191
2023-01-24 08:59:29.616451: step: 368/529, loss: 0.010475981049239635
2023-01-24 08:59:30.729488: step: 372/529, loss: 0.006949152797460556
2023-01-24 08:59:31.848512: step: 376/529, loss: 0.0028570599388331175
2023-01-24 08:59:32.937838: step: 380/529, loss: 0.008676288649439812
2023-01-24 08:59:34.033764: step: 384/529, loss: 0.008295878767967224
2023-01-24 08:59:35.137595: step: 388/529, loss: 0.00838957168161869
2023-01-24 08:59:36.236760: step: 392/529, loss: 0.003047575941309333
2023-01-24 08:59:37.322260: step: 396/529, loss: 0.0005909263854846358
2023-01-24 08:59:38.449576: step: 400/529, loss: 0.002323870314285159
2023-01-24 08:59:39.548483: step: 404/529, loss: 0.04494519904255867
2023-01-24 08:59:40.662532: step: 408/529, loss: 0.012526496313512325
2023-01-24 08:59:41.763969: step: 412/529, loss: 0.00234247581101954
2023-01-24 08:59:42.877027: step: 416/529, loss: 0.00038808339741081
2023-01-24 08:59:44.011930: step: 420/529, loss: 0.005925024393945932
2023-01-24 08:59:45.119425: step: 424/529, loss: 0.005720778834074736
2023-01-24 08:59:46.222704: step: 428/529, loss: 0.0039130826480686665
2023-01-24 08:59:47.327025: step: 432/529, loss: 0.001470521790906787
2023-01-24 08:59:48.461221: step: 436/529, loss: 0.002171593252569437
2023-01-24 08:59:49.567989: step: 440/529, loss: 0.008871885016560555
2023-01-24 08:59:50.655268: step: 444/529, loss: 7.68634636187926e-05
2023-01-24 08:59:51.745760: step: 448/529, loss: 0.002398934680968523
2023-01-24 08:59:52.833068: step: 452/529, loss: 0.00535996537655592
2023-01-24 08:59:53.957948: step: 456/529, loss: 0.009155374951660633
2023-01-24 08:59:55.054938: step: 460/529, loss: 0.008391357026994228
2023-01-24 08:59:56.144931: step: 464/529, loss: 0.014014866203069687
2023-01-24 08:59:57.254990: step: 468/529, loss: 0.005233097355812788
2023-01-24 08:59:58.347770: step: 472/529, loss: 0.00426349276676774
2023-01-24 08:59:59.451025: step: 476/529, loss: 0.007027878891676664
2023-01-24 09:00:00.560250: step: 480/529, loss: 0.011404664255678654
2023-01-24 09:00:01.683824: step: 484/529, loss: 0.030552171170711517
2023-01-24 09:00:02.786159: step: 488/529, loss: 0.01040281355381012
2023-01-24 09:00:03.890815: step: 492/529, loss: 0.010576466098427773
2023-01-24 09:00:04.978378: step: 496/529, loss: 0.011815064586699009
2023-01-24 09:00:06.090183: step: 500/529, loss: 0.0030642158817499876
2023-01-24 09:00:07.188565: step: 504/529, loss: 0.003776549594476819
2023-01-24 09:00:08.279972: step: 508/529, loss: 0.0048186518251895905
2023-01-24 09:00:09.401595: step: 512/529, loss: 0.013100002892315388
2023-01-24 09:00:10.492961: step: 516/529, loss: 0.003193611279129982
2023-01-24 09:00:11.608316: step: 520/529, loss: 5.077326477476163e-06
2023-01-24 09:00:12.714704: step: 524/529, loss: 0.011406700126826763
2023-01-24 09:00:13.821658: step: 528/529, loss: 0.011409236118197441
2023-01-24 09:00:14.936237: step: 532/529, loss: 0.002291899174451828
2023-01-24 09:00:16.039900: step: 536/529, loss: 0.001981314504519105
2023-01-24 09:00:17.135091: step: 540/529, loss: 0.0023756574373692274
2023-01-24 09:00:18.255404: step: 544/529, loss: 0.0034676450304687023
2023-01-24 09:00:19.374614: step: 548/529, loss: 0.0017041319515556097
2023-01-24 09:00:20.481643: step: 552/529, loss: 0.005051422398537397
2023-01-24 09:00:21.588962: step: 556/529, loss: 0.028502410277724266
2023-01-24 09:00:22.720803: step: 560/529, loss: 0.018700528889894485
2023-01-24 09:00:23.810620: step: 564/529, loss: 0.0024653091095387936
2023-01-24 09:00:24.911056: step: 568/529, loss: 0.003245433559641242
2023-01-24 09:00:26.011607: step: 572/529, loss: 0.00032193041988648474
2023-01-24 09:00:27.117655: step: 576/529, loss: 0.004998068790882826
2023-01-24 09:00:28.204767: step: 580/529, loss: 0.005314449314028025
2023-01-24 09:00:29.317743: step: 584/529, loss: 0.0021088221110403538
2023-01-24 09:00:30.427468: step: 588/529, loss: 0.0008396217599511147
2023-01-24 09:00:31.558058: step: 592/529, loss: 0.0019381141755729914
2023-01-24 09:00:32.703171: step: 596/529, loss: 0.00046278350055217743
2023-01-24 09:00:33.797000: step: 600/529, loss: 0.0039575002156198025
2023-01-24 09:00:34.908567: step: 604/529, loss: 0.007890153676271439
2023-01-24 09:00:36.017489: step: 608/529, loss: 0.016897959634661674
2023-01-24 09:00:37.120234: step: 612/529, loss: 0.03406417369842529
2023-01-24 09:00:38.208630: step: 616/529, loss: 0.0012760208919644356
2023-01-24 09:00:39.313137: step: 620/529, loss: 0.026287732645869255
2023-01-24 09:00:40.419099: step: 624/529, loss: 0.015432106330990791
2023-01-24 09:00:41.515121: step: 628/529, loss: 0.005200305953621864
2023-01-24 09:00:42.637055: step: 632/529, loss: 0.021572012454271317
2023-01-24 09:00:43.745380: step: 636/529, loss: 0.005489361472427845
2023-01-24 09:00:44.832699: step: 640/529, loss: 0.012023410759866238
2023-01-24 09:00:45.925979: step: 644/529, loss: 0.007949097082018852
2023-01-24 09:00:47.040096: step: 648/529, loss: 0.0016418035374954343
2023-01-24 09:00:48.152210: step: 652/529, loss: 0.0005466703441925347
2023-01-24 09:00:49.254655: step: 656/529, loss: 0.001666917116381228
2023-01-24 09:00:50.347561: step: 660/529, loss: 0.005398231092840433
2023-01-24 09:00:51.461175: step: 664/529, loss: 0.002538684755563736
2023-01-24 09:00:52.542158: step: 668/529, loss: 0.00783788412809372
2023-01-24 09:00:53.624147: step: 672/529, loss: 0.0008194351685233414
2023-01-24 09:00:54.730745: step: 676/529, loss: 0.005514910910278559
2023-01-24 09:00:55.838525: step: 680/529, loss: 0.0030528572387993336
2023-01-24 09:00:56.954998: step: 684/529, loss: 0.004789189901202917
2023-01-24 09:00:58.070714: step: 688/529, loss: 0.008657111786305904
2023-01-24 09:00:59.186703: step: 692/529, loss: 0.0079760467633605
2023-01-24 09:01:00.315510: step: 696/529, loss: 0.07318770885467529
2023-01-24 09:01:01.423056: step: 700/529, loss: 0.004092132207006216
2023-01-24 09:01:02.521094: step: 704/529, loss: 0.0018960719462484121
2023-01-24 09:01:03.625879: step: 708/529, loss: 0.006012339610606432
2023-01-24 09:01:04.747877: step: 712/529, loss: 0.002216975437477231
2023-01-24 09:01:05.860494: step: 716/529, loss: 0.00660129776224494
2023-01-24 09:01:06.959197: step: 720/529, loss: 0.003538223449140787
2023-01-24 09:01:08.052510: step: 724/529, loss: 0.006321675609797239
2023-01-24 09:01:09.158706: step: 728/529, loss: 0.00013304193271324039
2023-01-24 09:01:10.228112: step: 732/529, loss: 6.925478373887017e-05
2023-01-24 09:01:11.356929: step: 736/529, loss: 0.006495039444416761
2023-01-24 09:01:12.443872: step: 740/529, loss: 0.006380516570061445
2023-01-24 09:01:13.533650: step: 744/529, loss: 0.013447131030261517
2023-01-24 09:01:14.632929: step: 748/529, loss: 0.00013909900735598058
2023-01-24 09:01:15.715650: step: 752/529, loss: 0.0011064481223002076
2023-01-24 09:01:16.837711: step: 756/529, loss: 0.007094236556440592
2023-01-24 09:01:17.950313: step: 760/529, loss: 0.002531299600377679
2023-01-24 09:01:19.044254: step: 764/529, loss: 0.004947530571371317
2023-01-24 09:01:20.182521: step: 768/529, loss: 0.00331061240285635
2023-01-24 09:01:21.267914: step: 772/529, loss: 0.0004600965476129204
2023-01-24 09:01:22.347720: step: 776/529, loss: 0.005410581827163696
2023-01-24 09:01:23.426642: step: 780/529, loss: 0.00030218143365345895
2023-01-24 09:01:24.509901: step: 784/529, loss: 0.005493725184351206
2023-01-24 09:01:25.621017: step: 788/529, loss: 0.003168599447235465
2023-01-24 09:01:26.727936: step: 792/529, loss: 0.005202501080930233
2023-01-24 09:01:27.811099: step: 796/529, loss: 0.005630144849419594
2023-01-24 09:01:28.914443: step: 800/529, loss: 0.0019438144518062472
2023-01-24 09:01:30.035931: step: 804/529, loss: 0.002969382330775261
2023-01-24 09:01:31.145184: step: 808/529, loss: 0.0007965315016917884
2023-01-24 09:01:32.263475: step: 812/529, loss: 0.0021448356565088034
2023-01-24 09:01:33.349400: step: 816/529, loss: 0.0044776624999940395
2023-01-24 09:01:34.448812: step: 820/529, loss: 0.008589869365096092
2023-01-24 09:01:35.567558: step: 824/529, loss: 0.0013891683192923665
2023-01-24 09:01:36.673436: step: 828/529, loss: 0.003999660257250071
2023-01-24 09:01:37.782951: step: 832/529, loss: 3.5043980460613966e-05
2023-01-24 09:01:38.905746: step: 836/529, loss: 0.009071200154721737
2023-01-24 09:01:40.006979: step: 840/529, loss: 0.004447650630027056
2023-01-24 09:01:41.117383: step: 844/529, loss: 0.002736475318670273
2023-01-24 09:01:42.194331: step: 848/529, loss: 0.002411683788523078
2023-01-24 09:01:43.303928: step: 852/529, loss: 0.00021431082859635353
2023-01-24 09:01:44.396272: step: 856/529, loss: 0.014097589999437332
2023-01-24 09:01:45.483428: step: 860/529, loss: 0.006544869858771563
2023-01-24 09:01:46.565036: step: 864/529, loss: 0.0072073000483214855
2023-01-24 09:01:47.669955: step: 868/529, loss: 0.01216262299567461
2023-01-24 09:01:48.748397: step: 872/529, loss: 0.004361768718808889
2023-01-24 09:01:49.858463: step: 876/529, loss: 0.0006993083516135812
2023-01-24 09:01:50.981868: step: 880/529, loss: 0.0013722070725634694
2023-01-24 09:01:52.086269: step: 884/529, loss: 0.010257489047944546
2023-01-24 09:01:53.182387: step: 888/529, loss: 0.00771905155852437
2023-01-24 09:01:54.298002: step: 892/529, loss: 0.0034532530698925257
2023-01-24 09:01:55.413318: step: 896/529, loss: 0.003750961972400546
2023-01-24 09:01:56.544865: step: 900/529, loss: 0.004235539119690657
2023-01-24 09:01:57.656472: step: 904/529, loss: 0.01876828633248806
2023-01-24 09:01:58.766850: step: 908/529, loss: 0.01389996986836195
2023-01-24 09:01:59.881412: step: 912/529, loss: 0.004842726048082113
2023-01-24 09:02:00.984336: step: 916/529, loss: 0.026237189769744873
2023-01-24 09:02:02.098687: step: 920/529, loss: 0.007675171829760075
2023-01-24 09:02:03.232444: step: 924/529, loss: 0.004274559672921896
2023-01-24 09:02:04.328870: step: 928/529, loss: 0.0020656881388276815
2023-01-24 09:02:05.421562: step: 932/529, loss: 5.031748059991514e-06
2023-01-24 09:02:06.530986: step: 936/529, loss: 0.004031971096992493
2023-01-24 09:02:07.631214: step: 940/529, loss: 0.0024676888715475798
2023-01-24 09:02:08.719574: step: 944/529, loss: 0.019141731783747673
2023-01-24 09:02:09.837431: step: 948/529, loss: 0.0019298330880701542
2023-01-24 09:02:10.926539: step: 952/529, loss: 0.0012369854375720024
2023-01-24 09:02:12.035099: step: 956/529, loss: 0.01196899265050888
2023-01-24 09:02:13.138137: step: 960/529, loss: 0.0028338537085801363
2023-01-24 09:02:14.230831: step: 964/529, loss: 0.0011622555321082473
2023-01-24 09:02:15.353434: step: 968/529, loss: 0.0030543047469109297
2023-01-24 09:02:16.446329: step: 972/529, loss: 0.002496180823072791
2023-01-24 09:02:17.544284: step: 976/529, loss: 0.01589144580066204
2023-01-24 09:02:18.647627: step: 980/529, loss: 0.0027341567911207676
2023-01-24 09:02:19.737102: step: 984/529, loss: 0.007058282848447561
2023-01-24 09:02:20.852617: step: 988/529, loss: 0.012735437601804733
2023-01-24 09:02:21.975580: step: 992/529, loss: 0.005443592555820942
2023-01-24 09:02:23.099421: step: 996/529, loss: 0.012711774557828903
2023-01-24 09:02:24.211144: step: 1000/529, loss: 0.0022652146872133017
2023-01-24 09:02:25.333522: step: 1004/529, loss: 0.0033271366264671087
2023-01-24 09:02:26.418850: step: 1008/529, loss: 0.0035942820832133293
2023-01-24 09:02:27.513765: step: 1012/529, loss: 0.0007693001534789801
2023-01-24 09:02:28.631389: step: 1016/529, loss: 0.0026533822529017925
2023-01-24 09:02:29.740301: step: 1020/529, loss: 0.004491900093853474
2023-01-24 09:02:30.841068: step: 1024/529, loss: 0.005299916956573725
2023-01-24 09:02:31.949401: step: 1028/529, loss: 0.005103908479213715
2023-01-24 09:02:33.066487: step: 1032/529, loss: 0.0008068275637924671
2023-01-24 09:02:34.174491: step: 1036/529, loss: 0.0026617106050252914
2023-01-24 09:02:35.279040: step: 1040/529, loss: 0.002513264771550894
2023-01-24 09:02:36.376006: step: 1044/529, loss: 0.004923961125314236
2023-01-24 09:02:37.497686: step: 1048/529, loss: 0.01862596906721592
2023-01-24 09:02:38.611685: step: 1052/529, loss: 0.011417374014854431
2023-01-24 09:02:39.706582: step: 1056/529, loss: 0.01099475659430027
2023-01-24 09:02:40.809388: step: 1060/529, loss: 0.004778279922902584
2023-01-24 09:02:41.908139: step: 1064/529, loss: 0.011101208627223969
2023-01-24 09:02:43.005268: step: 1068/529, loss: 0.014456914737820625
2023-01-24 09:02:44.113593: step: 1072/529, loss: 0.0037627792917191982
2023-01-24 09:02:45.246790: step: 1076/529, loss: 0.002306982409209013
2023-01-24 09:02:46.362551: step: 1080/529, loss: 0.005412676837295294
2023-01-24 09:02:47.434200: step: 1084/529, loss: 0.008773085661232471
2023-01-24 09:02:48.543506: step: 1088/529, loss: 0.012251120992004871
2023-01-24 09:02:49.662109: step: 1092/529, loss: 0.006224720738828182
2023-01-24 09:02:50.749315: step: 1096/529, loss: 0.009956118650734425
2023-01-24 09:02:51.866277: step: 1100/529, loss: 0.021415360271930695
2023-01-24 09:02:52.990715: step: 1104/529, loss: 0.0013100974028930068
2023-01-24 09:02:54.086162: step: 1108/529, loss: 0.00012982427142560482
2023-01-24 09:02:55.199725: step: 1112/529, loss: 0.009698528796434402
2023-01-24 09:02:56.316473: step: 1116/529, loss: 0.0028295607771724463
2023-01-24 09:02:57.428833: step: 1120/529, loss: 0.005183225963264704
2023-01-24 09:02:58.527466: step: 1124/529, loss: 0.007370187900960445
2023-01-24 09:02:59.643024: step: 1128/529, loss: 0.0038984548300504684
2023-01-24 09:03:00.750642: step: 1132/529, loss: 0.016510816290974617
2023-01-24 09:03:01.885518: step: 1136/529, loss: 0.04182136058807373
2023-01-24 09:03:02.978383: step: 1140/529, loss: 0.011409271508455276
2023-01-24 09:03:04.052604: step: 1144/529, loss: 7.113488209142815e-06
2023-01-24 09:03:05.154527: step: 1148/529, loss: 0.0065594385378062725
2023-01-24 09:03:06.263757: step: 1152/529, loss: 0.007482252549380064
2023-01-24 09:03:07.387139: step: 1156/529, loss: 0.0004910477437078953
2023-01-24 09:03:08.508119: step: 1160/529, loss: 0.001266395440325141
2023-01-24 09:03:09.598565: step: 1164/529, loss: 0.0022375599946826696
2023-01-24 09:03:10.700377: step: 1168/529, loss: 0.0012515420094132423
2023-01-24 09:03:11.823900: step: 1172/529, loss: 0.016432879492640495
2023-01-24 09:03:12.920500: step: 1176/529, loss: 0.0018286400008946657
2023-01-24 09:03:14.024241: step: 1180/529, loss: 0.004006275441497564
2023-01-24 09:03:15.124204: step: 1184/529, loss: 0.015635188668966293
2023-01-24 09:03:16.225377: step: 1188/529, loss: 0.013672055676579475
2023-01-24 09:03:17.332228: step: 1192/529, loss: 0.006033264100551605
2023-01-24 09:03:18.444068: step: 1196/529, loss: 0.000723105447832495
2023-01-24 09:03:19.561532: step: 1200/529, loss: 0.0071470164693892
2023-01-24 09:03:20.659182: step: 1204/529, loss: 0.0019975490868091583
2023-01-24 09:03:21.773220: step: 1208/529, loss: 0.045328289270401
2023-01-24 09:03:22.875245: step: 1212/529, loss: 0.0010167284635826945
2023-01-24 09:03:23.983674: step: 1216/529, loss: 0.004742552060633898
2023-01-24 09:03:25.102107: step: 1220/529, loss: 0.02452757954597473
2023-01-24 09:03:26.187413: step: 1224/529, loss: 0.0064271967858076096
2023-01-24 09:03:27.312114: step: 1228/529, loss: 0.00568555248901248
2023-01-24 09:03:28.412163: step: 1232/529, loss: 0.012515513226389885
2023-01-24 09:03:29.513254: step: 1236/529, loss: 0.00309370388276875
2023-01-24 09:03:30.623547: step: 1240/529, loss: 0.01939237490296364
2023-01-24 09:03:31.725267: step: 1244/529, loss: 0.007814579643309116
2023-01-24 09:03:32.855784: step: 1248/529, loss: 0.006513823289424181
2023-01-24 09:03:33.982629: step: 1252/529, loss: 0.004988866858184338
2023-01-24 09:03:35.106181: step: 1256/529, loss: 0.005829906091094017
2023-01-24 09:03:36.215630: step: 1260/529, loss: 0.04851846769452095
2023-01-24 09:03:37.319150: step: 1264/529, loss: 0.000664384919218719
2023-01-24 09:03:38.431593: step: 1268/529, loss: 0.0003752862976398319
2023-01-24 09:03:39.525319: step: 1272/529, loss: 0.015612095594406128
2023-01-24 09:03:40.616147: step: 1276/529, loss: 9.446031981497072e-06
2023-01-24 09:03:41.726275: step: 1280/529, loss: 0.003517782548442483
2023-01-24 09:03:42.827090: step: 1284/529, loss: 0.001117116305977106
2023-01-24 09:03:43.926091: step: 1288/529, loss: 0.0030756795313209295
2023-01-24 09:03:45.025265: step: 1292/529, loss: 0.004678931552916765
2023-01-24 09:03:46.144516: step: 1296/529, loss: 0.0003312908811494708
2023-01-24 09:03:47.239107: step: 1300/529, loss: 0.01911284774541855
2023-01-24 09:03:48.332991: step: 1304/529, loss: 0.0010765891056507826
2023-01-24 09:03:49.462226: step: 1308/529, loss: 0.0017226110212504864
2023-01-24 09:03:50.560431: step: 1312/529, loss: 0.01661721058189869
2023-01-24 09:03:51.681993: step: 1316/529, loss: 0.014970474876463413
2023-01-24 09:03:52.780396: step: 1320/529, loss: 0.00523312296718359
2023-01-24 09:03:53.877085: step: 1324/529, loss: 0.014798336662352085
2023-01-24 09:03:54.995114: step: 1328/529, loss: 0.006073483265936375
2023-01-24 09:03:56.126326: step: 1332/529, loss: 0.013157440349459648
2023-01-24 09:03:57.254458: step: 1336/529, loss: 0.0037649902515113354
2023-01-24 09:03:58.350840: step: 1340/529, loss: 0.003918703645467758
2023-01-24 09:03:59.473621: step: 1344/529, loss: 0.015555571764707565
2023-01-24 09:04:00.598022: step: 1348/529, loss: 0.025919701904058456
2023-01-24 09:04:01.712658: step: 1352/529, loss: 0.008317217230796814
2023-01-24 09:04:02.823248: step: 1356/529, loss: 0.015770718455314636
2023-01-24 09:04:03.926525: step: 1360/529, loss: 0.016272801905870438
2023-01-24 09:04:05.026999: step: 1364/529, loss: 0.01836567558348179
2023-01-24 09:04:06.120324: step: 1368/529, loss: 0.015131909400224686
2023-01-24 09:04:07.218994: step: 1372/529, loss: 0.0033577620051801205
2023-01-24 09:04:08.309605: step: 1376/529, loss: 0.00923423282802105
2023-01-24 09:04:09.405798: step: 1380/529, loss: 0.004627783317118883
2023-01-24 09:04:10.509778: step: 1384/529, loss: 0.0006984298233874142
2023-01-24 09:04:11.640560: step: 1388/529, loss: 0.001548895612359047
2023-01-24 09:04:12.742542: step: 1392/529, loss: 0.03049153834581375
2023-01-24 09:04:13.858624: step: 1396/529, loss: 0.0013241315027698874
2023-01-24 09:04:14.955705: step: 1400/529, loss: 0.002538112923502922
2023-01-24 09:04:16.081833: step: 1404/529, loss: 0.0011562154395505786
2023-01-24 09:04:17.155613: step: 1408/529, loss: 0.003173451405018568
2023-01-24 09:04:18.260130: step: 1412/529, loss: 0.004766612313687801
2023-01-24 09:04:19.357498: step: 1416/529, loss: 0.0015264734392985702
2023-01-24 09:04:20.489861: step: 1420/529, loss: 0.004329460673034191
2023-01-24 09:04:21.602218: step: 1424/529, loss: 0.014855623245239258
2023-01-24 09:04:22.697478: step: 1428/529, loss: 0.031332649290561676
2023-01-24 09:04:23.807767: step: 1432/529, loss: 0.006972219329327345
2023-01-24 09:04:24.901171: step: 1436/529, loss: 0.023841822519898415
2023-01-24 09:04:25.994842: step: 1440/529, loss: 0.004149661399424076
2023-01-24 09:04:27.125684: step: 1444/529, loss: 0.005571763031184673
2023-01-24 09:04:28.217169: step: 1448/529, loss: 0.003978666849434376
2023-01-24 09:04:29.328342: step: 1452/529, loss: 0.0069182622246444225
2023-01-24 09:04:30.413970: step: 1456/529, loss: 0.0008632629178464413
2023-01-24 09:04:31.512603: step: 1460/529, loss: 0.003161513712257147
2023-01-24 09:04:32.630753: step: 1464/529, loss: 0.0020406313706189394
2023-01-24 09:04:33.739180: step: 1468/529, loss: 0.0010959033388644457
2023-01-24 09:04:34.862783: step: 1472/529, loss: 0.0032862797379493713
2023-01-24 09:04:35.965199: step: 1476/529, loss: 0.0025266262236982584
2023-01-24 09:04:37.072001: step: 1480/529, loss: 0.003277143696323037
2023-01-24 09:04:38.172389: step: 1484/529, loss: 0.004762754775583744
2023-01-24 09:04:39.293893: step: 1488/529, loss: 0.0004464202211238444
2023-01-24 09:04:40.424327: step: 1492/529, loss: 0.0007594140479341149
2023-01-24 09:04:41.546071: step: 1496/529, loss: 0.00411064550280571
2023-01-24 09:04:42.629853: step: 1500/529, loss: 9.792173659661785e-05
2023-01-24 09:04:43.718716: step: 1504/529, loss: 0.0042410958558321
2023-01-24 09:04:44.841329: step: 1508/529, loss: 0.008341701701283455
2023-01-24 09:04:45.909899: step: 1512/529, loss: 0.00592674408107996
2023-01-24 09:04:47.011230: step: 1516/529, loss: 0.014140663668513298
2023-01-24 09:04:48.144215: step: 1520/529, loss: 0.0008491849876008928
2023-01-24 09:04:49.242505: step: 1524/529, loss: 0.007004720624536276
2023-01-24 09:04:50.357845: step: 1528/529, loss: 0.0004268204793334007
2023-01-24 09:04:51.480885: step: 1532/529, loss: 0.03574948385357857
2023-01-24 09:04:52.579069: step: 1536/529, loss: 0.006179031915962696
2023-01-24 09:04:53.706213: step: 1540/529, loss: 0.007838006131350994
2023-01-24 09:04:54.806572: step: 1544/529, loss: 0.008983041159808636
2023-01-24 09:04:55.905563: step: 1548/529, loss: 0.00875949952751398
2023-01-24 09:04:57.026085: step: 1552/529, loss: 0.005664760712534189
2023-01-24 09:04:58.121737: step: 1556/529, loss: 0.022366249933838844
2023-01-24 09:04:59.201818: step: 1560/529, loss: 0.0013862333726137877
2023-01-24 09:05:00.307987: step: 1564/529, loss: 0.0022592064924538136
2023-01-24 09:05:01.409038: step: 1568/529, loss: 0.01212913915514946
2023-01-24 09:05:02.523505: step: 1572/529, loss: 0.008453449234366417
2023-01-24 09:05:03.624965: step: 1576/529, loss: 0.0037377227563410997
2023-01-24 09:05:04.714311: step: 1580/529, loss: 0.0001311369560426101
2023-01-24 09:05:05.815146: step: 1584/529, loss: 0.0007882571080699563
2023-01-24 09:05:06.907444: step: 1588/529, loss: 0.00010435284639243037
2023-01-24 09:05:08.006412: step: 1592/529, loss: 0.00039552515954710543
2023-01-24 09:05:09.094434: step: 1596/529, loss: 0.004523188807070255
2023-01-24 09:05:10.219416: step: 1600/529, loss: 0.0017764779040589929
2023-01-24 09:05:11.324631: step: 1604/529, loss: 0.0060484642162919044
2023-01-24 09:05:12.434745: step: 1608/529, loss: 0.008821922354400158
2023-01-24 09:05:13.553218: step: 1612/529, loss: 0.004837465472519398
2023-01-24 09:05:14.649844: step: 1616/529, loss: 0.003824402578175068
2023-01-24 09:05:15.761335: step: 1620/529, loss: 0.013101443648338318
2023-01-24 09:05:16.848829: step: 1624/529, loss: 0.008894307538866997
2023-01-24 09:05:17.946190: step: 1628/529, loss: 0.0024431536439806223
2023-01-24 09:05:19.052325: step: 1632/529, loss: 0.008759829215705395
2023-01-24 09:05:20.148221: step: 1636/529, loss: 0.004570564720779657
2023-01-24 09:05:21.240426: step: 1640/529, loss: 0.01350428257137537
2023-01-24 09:05:22.353268: step: 1644/529, loss: 0.006743482779711485
2023-01-24 09:05:23.461640: step: 1648/529, loss: 0.0009088098886422813
2023-01-24 09:05:24.568809: step: 1652/529, loss: 0.0013909143162891269
2023-01-24 09:05:25.672520: step: 1656/529, loss: 0.006951337214559317
2023-01-24 09:05:26.780205: step: 1660/529, loss: 0.011399917304515839
2023-01-24 09:05:27.882248: step: 1664/529, loss: 0.0023579145781695843
2023-01-24 09:05:28.989749: step: 1668/529, loss: 0.008432172238826752
2023-01-24 09:05:30.074437: step: 1672/529, loss: 0.0033959040883928537
2023-01-24 09:05:31.165544: step: 1676/529, loss: 0.006625001784414053
2023-01-24 09:05:32.279853: step: 1680/529, loss: 0.006230037193745375
2023-01-24 09:05:33.374053: step: 1684/529, loss: 0.004751909989863634
2023-01-24 09:05:34.506949: step: 1688/529, loss: 0.007471776567399502
2023-01-24 09:05:35.622946: step: 1692/529, loss: 0.003270291956141591
2023-01-24 09:05:36.743713: step: 1696/529, loss: 0.00880468264222145
2023-01-24 09:05:37.821774: step: 1700/529, loss: 0.011734520085155964
2023-01-24 09:05:38.959335: step: 1704/529, loss: 0.002255986910313368
2023-01-24 09:05:40.081609: step: 1708/529, loss: 0.004465277306735516
2023-01-24 09:05:41.173204: step: 1712/529, loss: 0.0020688881631940603
2023-01-24 09:05:42.260629: step: 1716/529, loss: 0.0008904458954930305
2023-01-24 09:05:43.347539: step: 1720/529, loss: 0.002547086915001273
2023-01-24 09:05:44.436514: step: 1724/529, loss: 0.005983465816825628
2023-01-24 09:05:45.565512: step: 1728/529, loss: 0.030051473528146744
2023-01-24 09:05:46.685426: step: 1732/529, loss: 0.012958361767232418
2023-01-24 09:05:47.783179: step: 1736/529, loss: 0.003839613404124975
2023-01-24 09:05:48.885705: step: 1740/529, loss: 0.008171058259904385
2023-01-24 09:05:49.995969: step: 1744/529, loss: 0.005781652871519327
2023-01-24 09:05:51.104507: step: 1748/529, loss: 0.0033688365947455168
2023-01-24 09:05:52.201186: step: 1752/529, loss: 0.0029633932281285524
2023-01-24 09:05:53.314688: step: 1756/529, loss: 0.008164803497493267
2023-01-24 09:05:54.398425: step: 1760/529, loss: 0.000297634833259508
2023-01-24 09:05:55.516065: step: 1764/529, loss: 0.00467092078179121
2023-01-24 09:05:56.634088: step: 1768/529, loss: 0.006810002028942108
2023-01-24 09:05:57.741671: step: 1772/529, loss: 0.0042831869795918465
2023-01-24 09:05:58.855522: step: 1776/529, loss: 0.013637793250381947
2023-01-24 09:05:59.964579: step: 1780/529, loss: 0.002816260326653719
2023-01-24 09:06:01.065900: step: 1784/529, loss: 0.0038292035460472107
2023-01-24 09:06:02.177828: step: 1788/529, loss: 0.007115884218364954
2023-01-24 09:06:03.270375: step: 1792/529, loss: 0.009606112726032734
2023-01-24 09:06:04.385459: step: 1796/529, loss: 0.005211938638240099
2023-01-24 09:06:05.470512: step: 1800/529, loss: 0.023559128865599632
2023-01-24 09:06:06.564094: step: 1804/529, loss: 0.0031590706203132868
2023-01-24 09:06:07.654742: step: 1808/529, loss: 0.011790262535214424
2023-01-24 09:06:08.750620: step: 1812/529, loss: 0.0020895814523100853
2023-01-24 09:06:09.850838: step: 1816/529, loss: 0.010864565148949623
2023-01-24 09:06:10.952099: step: 1820/529, loss: 0.008166816085577011
2023-01-24 09:06:12.079242: step: 1824/529, loss: 0.019291039556264877
2023-01-24 09:06:13.162781: step: 1828/529, loss: 0.0005839415825903416
2023-01-24 09:06:14.286818: step: 1832/529, loss: 0.013008509762585163
2023-01-24 09:06:15.407752: step: 1836/529, loss: 0.0059598283842206
2023-01-24 09:06:16.515997: step: 1840/529, loss: 0.02035428211092949
2023-01-24 09:06:17.628541: step: 1844/529, loss: 0.0016842653276398778
2023-01-24 09:06:18.738824: step: 1848/529, loss: 0.0023054194170981646
2023-01-24 09:06:19.826273: step: 1852/529, loss: 0.000536528299562633
2023-01-24 09:06:20.936534: step: 1856/529, loss: 0.00028577970806509256
2023-01-24 09:06:22.042047: step: 1860/529, loss: 0.021707382053136826
2023-01-24 09:06:23.147054: step: 1864/529, loss: 0.004447434563189745
2023-01-24 09:06:24.255077: step: 1868/529, loss: 0.017727050930261612
2023-01-24 09:06:25.343360: step: 1872/529, loss: 0.0029900369700044394
2023-01-24 09:06:26.449744: step: 1876/529, loss: 0.012091061100363731
2023-01-24 09:06:27.548136: step: 1880/529, loss: 0.007277886848896742
2023-01-24 09:06:28.626592: step: 1884/529, loss: 0.006311463657766581
2023-01-24 09:06:29.737514: step: 1888/529, loss: 0.011168006807565689
2023-01-24 09:06:30.878243: step: 1892/529, loss: 0.046983376145362854
2023-01-24 09:06:31.980377: step: 1896/529, loss: 0.011099531315267086
2023-01-24 09:06:33.099068: step: 1900/529, loss: 0.009420022368431091
2023-01-24 09:06:34.204577: step: 1904/529, loss: 0.005504069849848747
2023-01-24 09:06:35.334449: step: 1908/529, loss: 0.0008501311531290412
2023-01-24 09:06:36.462969: step: 1912/529, loss: 0.0037150210700929165
2023-01-24 09:06:37.572785: step: 1916/529, loss: 0.011345190927386284
2023-01-24 09:06:38.685011: step: 1920/529, loss: 0.009494204074144363
2023-01-24 09:06:39.809763: step: 1924/529, loss: 0.00693238852545619
2023-01-24 09:06:40.906209: step: 1928/529, loss: 0.0013735938118770719
2023-01-24 09:06:42.016822: step: 1932/529, loss: 0.0016123269451782107
2023-01-24 09:06:43.111924: step: 1936/529, loss: 0.003117071697488427
2023-01-24 09:06:44.232156: step: 1940/529, loss: 0.022922208532691002
2023-01-24 09:06:45.341399: step: 1944/529, loss: 0.002638646401464939
2023-01-24 09:06:46.431408: step: 1948/529, loss: 0.00040953143616206944
2023-01-24 09:06:47.528389: step: 1952/529, loss: 0.001016639405861497
2023-01-24 09:06:48.642247: step: 1956/529, loss: 0.003975257743149996
2023-01-24 09:06:49.807919: step: 1960/529, loss: 0.006373354699462652
2023-01-24 09:06:50.907043: step: 1964/529, loss: 0.0010295009706169367
2023-01-24 09:06:52.039282: step: 1968/529, loss: 0.007885849103331566
2023-01-24 09:06:53.146801: step: 1972/529, loss: 0.0020311139523983
2023-01-24 09:06:54.253747: step: 1976/529, loss: 0.01220087893307209
2023-01-24 09:06:55.361364: step: 1980/529, loss: 0.007413088344037533
2023-01-24 09:06:56.477236: step: 1984/529, loss: 0.004888553638011217
2023-01-24 09:06:57.581840: step: 1988/529, loss: 0.014558098278939724
2023-01-24 09:06:58.685179: step: 1992/529, loss: 0.009451298043131828
2023-01-24 09:06:59.775571: step: 1996/529, loss: 0.005956432782113552
2023-01-24 09:07:00.875214: step: 2000/529, loss: 0.004337357357144356
2023-01-24 09:07:01.965965: step: 2004/529, loss: 0.002232165774330497
2023-01-24 09:07:03.085692: step: 2008/529, loss: 0.0025686766020953655
2023-01-24 09:07:04.187420: step: 2012/529, loss: 0.0014873025938868523
2023-01-24 09:07:05.279220: step: 2016/529, loss: 0.005499100778251886
2023-01-24 09:07:06.391930: step: 2020/529, loss: 0.038545068353414536
2023-01-24 09:07:07.482167: step: 2024/529, loss: 0.023336559534072876
2023-01-24 09:07:08.583292: step: 2028/529, loss: 0.005675704218447208
2023-01-24 09:07:09.694927: step: 2032/529, loss: 0.004638324957340956
2023-01-24 09:07:10.792629: step: 2036/529, loss: 0.006674089003354311
2023-01-24 09:07:11.890607: step: 2040/529, loss: 0.00048447161680087447
2023-01-24 09:07:13.025232: step: 2044/529, loss: 0.0025183423422276974
2023-01-24 09:07:14.120529: step: 2048/529, loss: 0.005090930499136448
2023-01-24 09:07:15.226399: step: 2052/529, loss: 0.0075054531916975975
2023-01-24 09:07:16.345057: step: 2056/529, loss: 0.0031944126822054386
2023-01-24 09:07:17.473833: step: 2060/529, loss: 0.023951824754476547
2023-01-24 09:07:18.593788: step: 2064/529, loss: 0.005172196310013533
2023-01-24 09:07:19.687497: step: 2068/529, loss: 0.005661047529429197
2023-01-24 09:07:20.806791: step: 2072/529, loss: 0.0016060305060818791
2023-01-24 09:07:21.916742: step: 2076/529, loss: 0.005676075350493193
2023-01-24 09:07:23.012533: step: 2080/529, loss: 0.007122858427464962
2023-01-24 09:07:24.117942: step: 2084/529, loss: 0.01702049747109413
2023-01-24 09:07:25.209257: step: 2088/529, loss: 0.020898722112178802
2023-01-24 09:07:26.285326: step: 2092/529, loss: 0.04448986053466797
2023-01-24 09:07:27.419099: step: 2096/529, loss: 0.0036965468898415565
2023-01-24 09:07:28.517877: step: 2100/529, loss: 0.0017909681191667914
2023-01-24 09:07:29.613117: step: 2104/529, loss: 0.006705079693347216
2023-01-24 09:07:30.721324: step: 2108/529, loss: 0.011283526197075844
2023-01-24 09:07:31.807335: step: 2112/529, loss: 0.01771441660821438
2023-01-24 09:07:32.905864: step: 2116/529, loss: 0.01893550530076027
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37254905808477234, 'r': 0.3216505150447276, 'f1': 0.3452338521966832}, 'combined': 0.2543828384607139, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3945185776850204, 'r': 0.2868293645387627, 'f1': 0.33216365948593285}, 'combined': 0.20415912729379287, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36031169028061083, 'r': 0.3315961476017007, 'f1': 0.3453580430555262}, 'combined': 0.25447434751459824, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37443686617165406, 'r': 0.29072394461854595, 'f1': 0.32731261667297756}, 'combined': 0.2011775107355862, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40087719298245617, 'r': 0.34686907020872865, 'f1': 0.37192268565615466}, 'combined': 0.2740482946940087, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38871665436725544, 'r': 0.28463221225331964, 'f1': 0.328629887884273}, 'combined': 0.20297728369322748, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:10:01.059729: step: 4/529, loss: 0.00414487486705184
2023-01-24 09:10:02.188659: step: 8/529, loss: 0.002066281856968999
2023-01-24 09:10:03.306297: step: 12/529, loss: 0.004331429488956928
2023-01-24 09:10:04.417789: step: 16/529, loss: 0.008557716384530067
2023-01-24 09:10:05.495742: step: 20/529, loss: 0.0053951493464410305
2023-01-24 09:10:06.595383: step: 24/529, loss: 0.014109299518167973
2023-01-24 09:10:07.693768: step: 28/529, loss: 0.01493789441883564
2023-01-24 09:10:08.787981: step: 32/529, loss: 0.0017501991242170334
2023-01-24 09:10:09.877556: step: 36/529, loss: 0.006952761206775904
2023-01-24 09:10:10.967734: step: 40/529, loss: 0.002125214785337448
2023-01-24 09:10:12.070191: step: 44/529, loss: 0.005766458343714476
2023-01-24 09:10:13.181576: step: 48/529, loss: 0.00222352659329772
2023-01-24 09:10:14.280261: step: 52/529, loss: 0.006024430971592665
2023-01-24 09:10:15.365313: step: 56/529, loss: 0.004829976242035627
2023-01-24 09:10:16.473703: step: 60/529, loss: 0.012165335938334465
2023-01-24 09:10:17.571434: step: 64/529, loss: 0.0006877960986457765
2023-01-24 09:10:18.660579: step: 68/529, loss: 0.0019286986207589507
2023-01-24 09:10:19.762146: step: 72/529, loss: 0.0030915564857423306
2023-01-24 09:10:20.880941: step: 76/529, loss: 0.025230253115296364
2023-01-24 09:10:21.975553: step: 80/529, loss: 0.0005667478544637561
2023-01-24 09:10:23.062331: step: 84/529, loss: 0.0013361324090510607
2023-01-24 09:10:24.186926: step: 88/529, loss: 0.02095462754368782
2023-01-24 09:10:25.270135: step: 92/529, loss: 0.009107070043683052
2023-01-24 09:10:26.390018: step: 96/529, loss: 0.004378173034638166
2023-01-24 09:10:27.512288: step: 100/529, loss: 0.0033493824303150177
2023-01-24 09:10:28.597984: step: 104/529, loss: 0.005826561711728573
2023-01-24 09:10:29.679608: step: 108/529, loss: 0.00200914335437119
2023-01-24 09:10:30.784480: step: 112/529, loss: 0.010383873246610165
2023-01-24 09:10:31.942014: step: 116/529, loss: 0.018977833911776543
2023-01-24 09:10:33.030330: step: 120/529, loss: 0.0004841686168219894
2023-01-24 09:10:34.160187: step: 124/529, loss: 0.002106103580445051
2023-01-24 09:10:35.242935: step: 128/529, loss: 0.00032513117184862494
2023-01-24 09:10:36.347759: step: 132/529, loss: 0.005869721528142691
2023-01-24 09:10:37.439267: step: 136/529, loss: 0.006620506290346384
2023-01-24 09:10:38.545704: step: 140/529, loss: 0.0020251385867595673
2023-01-24 09:10:39.642218: step: 144/529, loss: 0.0034202842507511377
2023-01-24 09:10:40.753949: step: 148/529, loss: 0.0014481099788099527
2023-01-24 09:10:41.828288: step: 152/529, loss: 0.0
2023-01-24 09:10:42.923604: step: 156/529, loss: 0.0008477833471260965
2023-01-24 09:10:44.044458: step: 160/529, loss: 0.005983901210129261
2023-01-24 09:10:45.158085: step: 164/529, loss: 0.009541898965835571
2023-01-24 09:10:46.268749: step: 168/529, loss: 0.010809199884533882
2023-01-24 09:10:47.362977: step: 172/529, loss: 0.004650185350328684
2023-01-24 09:10:48.465621: step: 176/529, loss: 0.011558866128325462
2023-01-24 09:10:49.556525: step: 180/529, loss: 0.005416307598352432
2023-01-24 09:10:50.656416: step: 184/529, loss: 0.007540030870586634
2023-01-24 09:10:51.745945: step: 188/529, loss: 0.0005049585015513003
2023-01-24 09:10:52.841543: step: 192/529, loss: 0.0009229168645106256
2023-01-24 09:10:53.949876: step: 196/529, loss: 0.004483763128519058
2023-01-24 09:10:55.039683: step: 200/529, loss: 0.00019230988982599229
2023-01-24 09:10:56.131283: step: 204/529, loss: 0.003221993101760745
2023-01-24 09:10:57.249314: step: 208/529, loss: 0.0013136722845956683
2023-01-24 09:10:58.354256: step: 212/529, loss: 0.00852738693356514
2023-01-24 09:10:59.480643: step: 216/529, loss: 0.0005509539623744786
2023-01-24 09:11:00.587264: step: 220/529, loss: 0.011330599896609783
2023-01-24 09:11:01.693968: step: 224/529, loss: 0.026606164872646332
2023-01-24 09:11:02.806639: step: 228/529, loss: 0.007711793761700392
2023-01-24 09:11:03.906959: step: 232/529, loss: 0.008934825658798218
2023-01-24 09:11:04.995576: step: 236/529, loss: 0.005774942692369223
2023-01-24 09:11:06.117407: step: 240/529, loss: 0.0008422565879300237
2023-01-24 09:11:07.238678: step: 244/529, loss: 0.002665509469807148
2023-01-24 09:11:08.362468: step: 248/529, loss: 0.003581276163458824
2023-01-24 09:11:09.460539: step: 252/529, loss: 0.009856889955699444
2023-01-24 09:11:10.568069: step: 256/529, loss: 0.004116377327591181
2023-01-24 09:11:11.675814: step: 260/529, loss: 0.011990280821919441
2023-01-24 09:11:12.770910: step: 264/529, loss: 0.0026049900334328413
2023-01-24 09:11:13.864478: step: 268/529, loss: 3.9648999518249184e-05
2023-01-24 09:11:14.985834: step: 272/529, loss: 0.0002796795160975307
2023-01-24 09:11:16.138064: step: 276/529, loss: 0.009639749303460121
2023-01-24 09:11:17.230752: step: 280/529, loss: 0.0067772273905575275
2023-01-24 09:11:18.335393: step: 284/529, loss: 0.0005912405904382467
2023-01-24 09:11:19.410997: step: 288/529, loss: 0.00014372813166119158
2023-01-24 09:11:20.514932: step: 292/529, loss: 0.00173787004314363
2023-01-24 09:11:21.609131: step: 296/529, loss: 0.006105820182710886
2023-01-24 09:11:22.706230: step: 300/529, loss: 0.004554436542093754
2023-01-24 09:11:23.820130: step: 304/529, loss: 0.006808524020016193
2023-01-24 09:11:24.947506: step: 308/529, loss: 0.018997371196746826
2023-01-24 09:11:26.042481: step: 312/529, loss: 0.009039481170475483
2023-01-24 09:11:27.134660: step: 316/529, loss: 0.0018510365625843406
2023-01-24 09:11:28.260413: step: 320/529, loss: 0.0039311740547418594
2023-01-24 09:11:29.352690: step: 324/529, loss: 0.0
2023-01-24 09:11:30.447349: step: 328/529, loss: 0.000220126734348014
2023-01-24 09:11:31.581492: step: 332/529, loss: 0.015490574762225151
2023-01-24 09:11:32.695361: step: 336/529, loss: 0.00874862540513277
2023-01-24 09:11:33.784006: step: 340/529, loss: 0.004412591457366943
2023-01-24 09:11:34.889781: step: 344/529, loss: 0.00694803474470973
2023-01-24 09:11:35.990817: step: 348/529, loss: 3.25481996696908e-05
2023-01-24 09:11:37.089778: step: 352/529, loss: 0.0010647244052961469
2023-01-24 09:11:38.194973: step: 356/529, loss: 0.0011962694115936756
2023-01-24 09:11:39.278036: step: 360/529, loss: 0.00199749949388206
2023-01-24 09:11:40.381613: step: 364/529, loss: 0.0052075800485908985
2023-01-24 09:11:41.475781: step: 368/529, loss: 0.005952970124781132
2023-01-24 09:11:42.586511: step: 372/529, loss: 0.002065795473754406
2023-01-24 09:11:43.694071: step: 376/529, loss: 0.04618256539106369
2023-01-24 09:11:44.816581: step: 380/529, loss: 0.0067822812125086784
2023-01-24 09:11:45.948800: step: 384/529, loss: 0.010984989814460278
2023-01-24 09:11:47.032853: step: 388/529, loss: 0.0020203085150569677
2023-01-24 09:11:48.149534: step: 392/529, loss: 0.0024973878171294928
2023-01-24 09:11:49.302979: step: 396/529, loss: 0.007390706334263086
2023-01-24 09:11:50.393265: step: 400/529, loss: 0.026156747713685036
2023-01-24 09:11:51.504759: step: 404/529, loss: 0.010489759035408497
2023-01-24 09:11:52.622456: step: 408/529, loss: 0.007646896410733461
2023-01-24 09:11:53.734010: step: 412/529, loss: 0.012465310283005238
2023-01-24 09:11:54.820074: step: 416/529, loss: 0.000603461405262351
2023-01-24 09:11:55.940295: step: 420/529, loss: 0.0025774831883609295
2023-01-24 09:11:57.050995: step: 424/529, loss: 0.004329221323132515
2023-01-24 09:11:58.155128: step: 428/529, loss: 0.008298619650304317
2023-01-24 09:11:59.258807: step: 432/529, loss: 0.00048650981625542045
2023-01-24 09:12:00.341510: step: 436/529, loss: 0.005668371915817261
2023-01-24 09:12:01.464520: step: 440/529, loss: 0.00552634010091424
2023-01-24 09:12:02.607455: step: 444/529, loss: 0.011496046558022499
2023-01-24 09:12:03.706782: step: 448/529, loss: 0.0002006281865760684
2023-01-24 09:12:04.792654: step: 452/529, loss: 0.0033039164263755083
2023-01-24 09:12:05.918308: step: 456/529, loss: 0.002336034318432212
2023-01-24 09:12:07.024223: step: 460/529, loss: 0.0026862837839871645
2023-01-24 09:12:08.152929: step: 464/529, loss: 0.0040974910371005535
2023-01-24 09:12:09.247096: step: 468/529, loss: 0.00464132335036993
2023-01-24 09:12:10.347308: step: 472/529, loss: 0.000561471504624933
2023-01-24 09:12:11.457163: step: 476/529, loss: 0.00554230622947216
2023-01-24 09:12:12.552297: step: 480/529, loss: 0.005267248954623938
2023-01-24 09:12:13.644837: step: 484/529, loss: 0.007264274638146162
2023-01-24 09:12:14.761307: step: 488/529, loss: 0.0027749843429774046
2023-01-24 09:12:15.848403: step: 492/529, loss: 0.00032936056959442794
2023-01-24 09:12:16.952531: step: 496/529, loss: 0.01107385940849781
2023-01-24 09:12:18.058765: step: 500/529, loss: 0.022173600271344185
2023-01-24 09:12:19.153196: step: 504/529, loss: 0.004900334868580103
2023-01-24 09:12:20.233222: step: 508/529, loss: 0.0056189619936048985
2023-01-24 09:12:21.340776: step: 512/529, loss: 0.007474112324416637
2023-01-24 09:12:22.456272: step: 516/529, loss: 9.483334724791348e-05
2023-01-24 09:12:23.575380: step: 520/529, loss: 0.0020297919400036335
2023-01-24 09:12:24.677595: step: 524/529, loss: 0.008607524447143078
2023-01-24 09:12:25.772680: step: 528/529, loss: 0.01237131841480732
2023-01-24 09:12:26.865981: step: 532/529, loss: 0.0021569342352449894
2023-01-24 09:12:27.952580: step: 536/529, loss: 0.0033774443436414003
2023-01-24 09:12:29.063644: step: 540/529, loss: 0.012475697323679924
2023-01-24 09:12:30.161701: step: 544/529, loss: 0.0007182147237472236
2023-01-24 09:12:31.250577: step: 548/529, loss: 0.0003945502976421267
2023-01-24 09:12:32.369760: step: 552/529, loss: 0.003738230559974909
2023-01-24 09:12:33.481885: step: 556/529, loss: 0.006862856447696686
2023-01-24 09:12:34.577600: step: 560/529, loss: 0.006230687256902456
2023-01-24 09:12:35.662878: step: 564/529, loss: 0.00483669014647603
2023-01-24 09:12:36.747715: step: 568/529, loss: 0.0014557491522282362
2023-01-24 09:12:37.836274: step: 572/529, loss: 0.001094767707400024
2023-01-24 09:12:38.942124: step: 576/529, loss: 0.0032514336053282022
2023-01-24 09:12:40.047080: step: 580/529, loss: 0.001310235122218728
2023-01-24 09:12:41.205747: step: 584/529, loss: 0.021781522780656815
2023-01-24 09:12:42.339110: step: 588/529, loss: 0.0032963836565613747
2023-01-24 09:12:43.442716: step: 592/529, loss: 0.01116613857448101
2023-01-24 09:12:44.549281: step: 596/529, loss: 0.010423549450933933
2023-01-24 09:12:45.665140: step: 600/529, loss: 0.0019972852896898985
2023-01-24 09:12:46.779412: step: 604/529, loss: 0.002582851331681013
2023-01-24 09:12:47.903811: step: 608/529, loss: 0.004633565898984671
2023-01-24 09:12:49.015258: step: 612/529, loss: 0.009637289680540562
2023-01-24 09:12:50.107779: step: 616/529, loss: 0.0003890860825777054
2023-01-24 09:12:51.238544: step: 620/529, loss: 0.0015760910464450717
2023-01-24 09:12:52.316251: step: 624/529, loss: 0.0034791354555636644
2023-01-24 09:12:53.429104: step: 628/529, loss: 0.002584443660452962
2023-01-24 09:12:54.508405: step: 632/529, loss: 0.004601211287081242
2023-01-24 09:12:55.600306: step: 636/529, loss: 0.002178665716201067
2023-01-24 09:12:56.690924: step: 640/529, loss: 0.0008391987648792565
2023-01-24 09:12:57.785700: step: 644/529, loss: 0.005405292846262455
2023-01-24 09:12:58.888347: step: 648/529, loss: 0.0726286843419075
2023-01-24 09:13:00.008227: step: 652/529, loss: 0.0053447457030415535
2023-01-24 09:13:01.117504: step: 656/529, loss: 0.0003974978462792933
2023-01-24 09:13:02.205094: step: 660/529, loss: 0.0037565017119050026
2023-01-24 09:13:03.300407: step: 664/529, loss: 0.003937878645956516
2023-01-24 09:13:04.418489: step: 668/529, loss: 0.01446220837533474
2023-01-24 09:13:05.547956: step: 672/529, loss: 0.0008877164218574762
2023-01-24 09:13:06.681175: step: 676/529, loss: 0.01086584571748972
2023-01-24 09:13:07.784834: step: 680/529, loss: 0.00027775357011705637
2023-01-24 09:13:08.886013: step: 684/529, loss: 0.000326420966302976
2023-01-24 09:13:10.027281: step: 688/529, loss: 0.014666769653558731
2023-01-24 09:13:11.168200: step: 692/529, loss: 0.020226916298270226
2023-01-24 09:13:12.265455: step: 696/529, loss: 0.0022267738822847605
2023-01-24 09:13:13.381592: step: 700/529, loss: 0.002878149040043354
2023-01-24 09:13:14.483471: step: 704/529, loss: 0.0013113577151671052
2023-01-24 09:13:15.596305: step: 708/529, loss: 0.009311271831393242
2023-01-24 09:13:16.700264: step: 712/529, loss: 0.010569063946604729
2023-01-24 09:13:17.809084: step: 716/529, loss: 0.0005601709708571434
2023-01-24 09:13:18.908132: step: 720/529, loss: 1.091440935852006e-05
2023-01-24 09:13:20.021741: step: 724/529, loss: 0.010182461701333523
2023-01-24 09:13:21.115001: step: 728/529, loss: 0.0004533478058874607
2023-01-24 09:13:22.237804: step: 732/529, loss: 0.0013494596350938082
2023-01-24 09:13:23.386372: step: 736/529, loss: 0.005440648645162582
2023-01-24 09:13:24.484815: step: 740/529, loss: 0.00649876007810235
2023-01-24 09:13:25.609616: step: 744/529, loss: 0.009621547535061836
2023-01-24 09:13:26.711792: step: 748/529, loss: 0.013323670253157616
2023-01-24 09:13:27.814072: step: 752/529, loss: 0.003264613915234804
2023-01-24 09:13:28.952866: step: 756/529, loss: 0.004687939770519733
2023-01-24 09:13:30.058238: step: 760/529, loss: 0.0005088684265501797
2023-01-24 09:13:31.164841: step: 764/529, loss: 0.004500416107475758
2023-01-24 09:13:32.316032: step: 768/529, loss: 0.016622252762317657
2023-01-24 09:13:33.426648: step: 772/529, loss: 0.0030898733530193567
2023-01-24 09:13:34.520975: step: 776/529, loss: 0.029359664767980576
2023-01-24 09:13:35.616684: step: 780/529, loss: 0.006753432564437389
2023-01-24 09:13:36.723981: step: 784/529, loss: 0.004939466714859009
2023-01-24 09:13:37.818876: step: 788/529, loss: 0.01325714960694313
2023-01-24 09:13:38.932992: step: 792/529, loss: 0.01342522632330656
2023-01-24 09:13:40.049197: step: 796/529, loss: 0.04887712746858597
2023-01-24 09:13:41.147039: step: 800/529, loss: 1.631297095627815e-06
2023-01-24 09:13:42.245125: step: 804/529, loss: 0.0006498720613308251
2023-01-24 09:13:43.339179: step: 808/529, loss: 0.003923764917999506
2023-01-24 09:13:44.463572: step: 812/529, loss: 0.03379932790994644
2023-01-24 09:13:45.600258: step: 816/529, loss: 0.00025219074450433254
2023-01-24 09:13:46.713754: step: 820/529, loss: 0.0008926524315029383
2023-01-24 09:13:47.834291: step: 824/529, loss: 0.0005559226265177131
2023-01-24 09:13:48.938849: step: 828/529, loss: 0.009458750486373901
2023-01-24 09:13:50.071838: step: 832/529, loss: 0.0012705448316410184
2023-01-24 09:13:51.184991: step: 836/529, loss: 0.0027521993033587933
2023-01-24 09:13:52.327840: step: 840/529, loss: 0.0005377698689699173
2023-01-24 09:13:53.434400: step: 844/529, loss: 0.005243862979114056
2023-01-24 09:13:54.532660: step: 848/529, loss: 0.006307366769760847
2023-01-24 09:13:55.660968: step: 852/529, loss: 0.02259444259107113
2023-01-24 09:13:56.764497: step: 856/529, loss: 0.00029475154587998986
2023-01-24 09:13:57.877749: step: 860/529, loss: 0.018171200528740883
2023-01-24 09:13:58.979303: step: 864/529, loss: 0.014193836599588394
2023-01-24 09:14:00.103570: step: 868/529, loss: 0.017552636563777924
2023-01-24 09:14:01.201639: step: 872/529, loss: 0.005190863739699125
2023-01-24 09:14:02.333152: step: 876/529, loss: 0.011153382249176502
2023-01-24 09:14:03.448967: step: 880/529, loss: 0.004842577967792749
2023-01-24 09:14:04.550692: step: 884/529, loss: 0.0062121800146996975
2023-01-24 09:14:05.682991: step: 888/529, loss: 0.01323642022907734
2023-01-24 09:14:06.802361: step: 892/529, loss: 0.015374289825558662
2023-01-24 09:14:07.898365: step: 896/529, loss: 0.0006335610523819923
2023-01-24 09:14:08.995738: step: 900/529, loss: 0.0008593490347266197
2023-01-24 09:14:10.085741: step: 904/529, loss: 0.0026908060535788536
2023-01-24 09:14:11.230584: step: 908/529, loss: 0.0017181062139570713
2023-01-24 09:14:12.337203: step: 912/529, loss: 0.00039353594183921814
2023-01-24 09:14:13.432773: step: 916/529, loss: 0.011335449293255806
2023-01-24 09:14:14.569709: step: 920/529, loss: 0.0061332546174526215
2023-01-24 09:14:15.703600: step: 924/529, loss: 0.0045195990242064
2023-01-24 09:14:16.811765: step: 928/529, loss: 0.00182430655695498
2023-01-24 09:14:17.912421: step: 932/529, loss: 0.009797133505344391
2023-01-24 09:14:19.030622: step: 936/529, loss: 0.0018056317931041121
2023-01-24 09:14:20.122668: step: 940/529, loss: 0.0021196717862039804
2023-01-24 09:14:21.258052: step: 944/529, loss: 0.038824744522571564
2023-01-24 09:14:22.361764: step: 948/529, loss: 0.016484001651406288
2023-01-24 09:14:23.448493: step: 952/529, loss: 0.0025689927861094475
2023-01-24 09:14:24.545807: step: 956/529, loss: 0.002180657582357526
2023-01-24 09:14:25.634540: step: 960/529, loss: 0.004588786978274584
2023-01-24 09:14:26.774902: step: 964/529, loss: 0.0012917533749714494
2023-01-24 09:14:27.893095: step: 968/529, loss: 0.01603994332253933
2023-01-24 09:14:28.991092: step: 972/529, loss: 0.00025173340691253543
2023-01-24 09:14:30.096272: step: 976/529, loss: 0.003559976350516081
2023-01-24 09:14:31.211015: step: 980/529, loss: 0.011127837002277374
2023-01-24 09:14:32.349078: step: 984/529, loss: 0.002899858169257641
2023-01-24 09:14:33.433042: step: 988/529, loss: 0.0003040945448447019
2023-01-24 09:14:34.537833: step: 992/529, loss: 0.0014891703613102436
2023-01-24 09:14:35.639232: step: 996/529, loss: 0.0091707156971097
2023-01-24 09:14:36.764699: step: 1000/529, loss: 0.00819131638854742
2023-01-24 09:14:37.850700: step: 1004/529, loss: 0.003619322320446372
2023-01-24 09:14:38.961763: step: 1008/529, loss: 0.015467430464923382
2023-01-24 09:14:40.062756: step: 1012/529, loss: 0.0
2023-01-24 09:14:41.156315: step: 1016/529, loss: 0.0004135034396313131
2023-01-24 09:14:42.273963: step: 1020/529, loss: 0.0007961735827848315
2023-01-24 09:14:43.368748: step: 1024/529, loss: 0.0030170453246682882
2023-01-24 09:14:44.494102: step: 1028/529, loss: 0.008891111239790916
2023-01-24 09:14:45.588962: step: 1032/529, loss: 0.028812071308493614
2023-01-24 09:14:46.696740: step: 1036/529, loss: 0.001309006940573454
2023-01-24 09:14:47.800653: step: 1040/529, loss: 0.0021758500952273607
2023-01-24 09:14:48.897709: step: 1044/529, loss: 0.016453970223665237
2023-01-24 09:14:50.004154: step: 1048/529, loss: 0.006567211821675301
2023-01-24 09:14:51.103381: step: 1052/529, loss: 0.00442207045853138
2023-01-24 09:14:52.191382: step: 1056/529, loss: 0.007647641934454441
2023-01-24 09:14:53.300494: step: 1060/529, loss: 0.0018164472421631217
2023-01-24 09:14:54.408549: step: 1064/529, loss: 0.0031214046757668257
2023-01-24 09:14:55.504715: step: 1068/529, loss: 0.0011373583693057299
2023-01-24 09:14:56.608760: step: 1072/529, loss: 2.2035350411897525e-05
2023-01-24 09:14:57.697531: step: 1076/529, loss: 5.894828791497275e-05
2023-01-24 09:14:58.804755: step: 1080/529, loss: 0.0053973328322172165
2023-01-24 09:14:59.918300: step: 1084/529, loss: 0.005806416273117065
2023-01-24 09:15:01.037567: step: 1088/529, loss: 0.003591387765482068
2023-01-24 09:15:02.124417: step: 1092/529, loss: 0.0004339154402259737
2023-01-24 09:15:03.208894: step: 1096/529, loss: 0.010434546507894993
2023-01-24 09:15:04.320276: step: 1100/529, loss: 0.0004758901195600629
2023-01-24 09:15:05.446097: step: 1104/529, loss: 0.004990661516785622
2023-01-24 09:15:06.565907: step: 1108/529, loss: 0.0016362224705517292
2023-01-24 09:15:07.731215: step: 1112/529, loss: 0.0032431031577289104
2023-01-24 09:15:08.843923: step: 1116/529, loss: 0.002160650212317705
2023-01-24 09:15:09.983973: step: 1120/529, loss: 0.008366209454834461
2023-01-24 09:15:11.099471: step: 1124/529, loss: 0.004021232016384602
2023-01-24 09:15:12.208804: step: 1128/529, loss: 0.006672700867056847
2023-01-24 09:15:13.351855: step: 1132/529, loss: 0.008496283553540707
2023-01-24 09:15:14.459371: step: 1136/529, loss: 0.003757246071472764
2023-01-24 09:15:15.575225: step: 1140/529, loss: 0.003016631817445159
2023-01-24 09:15:16.693505: step: 1144/529, loss: 0.004463598132133484
2023-01-24 09:15:17.800252: step: 1148/529, loss: 0.006736485753208399
2023-01-24 09:15:18.902332: step: 1152/529, loss: 0.008964328095316887
2023-01-24 09:15:19.979513: step: 1156/529, loss: 0.0049659074284136295
2023-01-24 09:15:21.104805: step: 1160/529, loss: 0.010895629413425922
2023-01-24 09:15:22.216565: step: 1164/529, loss: 0.010083192028105259
2023-01-24 09:15:23.309300: step: 1168/529, loss: 0.0060403067618608475
2023-01-24 09:15:24.409441: step: 1172/529, loss: 0.0014959246618673205
2023-01-24 09:15:25.520428: step: 1176/529, loss: 0.007001032587140799
2023-01-24 09:15:26.627431: step: 1180/529, loss: 0.02842397801578045
2023-01-24 09:15:27.751097: step: 1184/529, loss: 0.00036816977080889046
2023-01-24 09:15:28.884857: step: 1188/529, loss: 0.005977166350930929
2023-01-24 09:15:30.013071: step: 1192/529, loss: 0.006570525001734495
2023-01-24 09:15:31.114548: step: 1196/529, loss: 0.011007840745151043
2023-01-24 09:15:32.204519: step: 1200/529, loss: 0.01480249222368002
2023-01-24 09:15:33.289250: step: 1204/529, loss: 0.008009331300854683
2023-01-24 09:15:34.395140: step: 1208/529, loss: 0.002041494706645608
2023-01-24 09:15:35.485763: step: 1212/529, loss: 0.008568771183490753
2023-01-24 09:15:36.579438: step: 1216/529, loss: 0.00023385141685139388
2023-01-24 09:15:37.702946: step: 1220/529, loss: 0.0006642532534897327
2023-01-24 09:15:38.784585: step: 1224/529, loss: 0.004000767599791288
2023-01-24 09:15:39.874996: step: 1228/529, loss: 0.004966043867170811
2023-01-24 09:15:40.966893: step: 1232/529, loss: 0.007257959805428982
2023-01-24 09:15:42.075142: step: 1236/529, loss: 0.0028047217056155205
2023-01-24 09:15:43.154170: step: 1240/529, loss: 0.022721443325281143
2023-01-24 09:15:44.295207: step: 1244/529, loss: 0.012151169590651989
2023-01-24 09:15:45.401085: step: 1248/529, loss: 0.009717456065118313
2023-01-24 09:15:46.504102: step: 1252/529, loss: 0.0021035117097198963
2023-01-24 09:15:47.603192: step: 1256/529, loss: 0.0022540895733982325
2023-01-24 09:15:48.706896: step: 1260/529, loss: 0.004127219319343567
2023-01-24 09:15:49.811379: step: 1264/529, loss: 0.00014807403204031289
2023-01-24 09:15:50.919646: step: 1268/529, loss: 0.003077795496210456
2023-01-24 09:15:52.035790: step: 1272/529, loss: 0.004435978829860687
2023-01-24 09:15:53.128426: step: 1276/529, loss: 7.443239155691117e-05
2023-01-24 09:15:54.244882: step: 1280/529, loss: 0.006930656731128693
2023-01-24 09:15:55.332583: step: 1284/529, loss: 0.00949372723698616
2023-01-24 09:15:56.419572: step: 1288/529, loss: 0.008394051343202591
2023-01-24 09:15:57.511578: step: 1292/529, loss: 0.0007678737747482955
2023-01-24 09:15:58.587004: step: 1296/529, loss: 0.00044750425149686635
2023-01-24 09:15:59.700918: step: 1300/529, loss: 0.006408497225493193
2023-01-24 09:16:00.789081: step: 1304/529, loss: 0.005615501664578915
2023-01-24 09:16:01.923088: step: 1308/529, loss: 0.004020937718451023
2023-01-24 09:16:03.023036: step: 1312/529, loss: 0.008426829241216183
2023-01-24 09:16:04.110418: step: 1316/529, loss: 0.00027023834991268814
2023-01-24 09:16:05.219757: step: 1320/529, loss: 0.003480748739093542
2023-01-24 09:16:06.321529: step: 1324/529, loss: 0.013082791119813919
2023-01-24 09:16:07.420576: step: 1328/529, loss: 0.0084109827876091
2023-01-24 09:16:08.514467: step: 1332/529, loss: 0.007231859490275383
2023-01-24 09:16:09.619567: step: 1336/529, loss: 0.006308066193014383
2023-01-24 09:16:10.752060: step: 1340/529, loss: 0.008806136436760426
2023-01-24 09:16:11.861418: step: 1344/529, loss: 0.0019393779803067446
2023-01-24 09:16:12.984612: step: 1348/529, loss: 0.003081943839788437
2023-01-24 09:16:14.089018: step: 1352/529, loss: 0.003209242830052972
2023-01-24 09:16:15.202702: step: 1356/529, loss: 0.006779505871236324
2023-01-24 09:16:16.334823: step: 1360/529, loss: 0.0030315180774778128
2023-01-24 09:16:17.452175: step: 1364/529, loss: 0.005632452201098204
2023-01-24 09:16:18.570539: step: 1368/529, loss: 0.0014330879785120487
2023-01-24 09:16:19.681739: step: 1372/529, loss: 0.003500144463032484
2023-01-24 09:16:20.777825: step: 1376/529, loss: 0.00019482402421999723
2023-01-24 09:16:21.887367: step: 1380/529, loss: 0.0023417675402015448
2023-01-24 09:16:22.996533: step: 1384/529, loss: 0.003628364996984601
2023-01-24 09:16:24.110234: step: 1388/529, loss: 0.0008343298104591668
2023-01-24 09:16:25.228760: step: 1392/529, loss: 0.0007469439296983182
2023-01-24 09:16:26.333109: step: 1396/529, loss: 0.006617559120059013
2023-01-24 09:16:27.437200: step: 1400/529, loss: 0.003707305993884802
2023-01-24 09:16:28.578547: step: 1404/529, loss: 0.011335399001836777
2023-01-24 09:16:29.686666: step: 1408/529, loss: 0.03631199896335602
2023-01-24 09:16:30.787136: step: 1412/529, loss: 0.0039132460951805115
2023-01-24 09:16:31.889573: step: 1416/529, loss: 0.009202838875353336
2023-01-24 09:16:33.016536: step: 1420/529, loss: 0.012749945744872093
2023-01-24 09:16:34.115169: step: 1424/529, loss: 0.0005176840350031853
2023-01-24 09:16:35.220634: step: 1428/529, loss: 0.007134643383324146
2023-01-24 09:16:36.342343: step: 1432/529, loss: 0.015709972009062767
2023-01-24 09:16:37.467642: step: 1436/529, loss: 0.03329239413142204
2023-01-24 09:16:38.565062: step: 1440/529, loss: 0.017335517331957817
2023-01-24 09:16:39.664518: step: 1444/529, loss: 0.008728752844035625
2023-01-24 09:16:40.746115: step: 1448/529, loss: 0.008029668591916561
2023-01-24 09:16:41.842683: step: 1452/529, loss: 0.00221322663128376
2023-01-24 09:16:42.958835: step: 1456/529, loss: 9.519590821582824e-05
2023-01-24 09:16:44.054480: step: 1460/529, loss: 0.0008156742551364005
2023-01-24 09:16:45.159485: step: 1464/529, loss: 0.006727467756718397
2023-01-24 09:16:46.256596: step: 1468/529, loss: 0.027762891724705696
2023-01-24 09:16:47.358118: step: 1472/529, loss: 0.033658042550086975
2023-01-24 09:16:48.466110: step: 1476/529, loss: 0.0025946490932255983
2023-01-24 09:16:49.547353: step: 1480/529, loss: 0.00903841108083725
2023-01-24 09:16:50.634666: step: 1484/529, loss: 0.0021163439378142357
2023-01-24 09:16:51.733139: step: 1488/529, loss: 0.000791509635746479
2023-01-24 09:16:52.823733: step: 1492/529, loss: 0.00154003722127527
2023-01-24 09:16:53.915891: step: 1496/529, loss: 0.003983136732131243
2023-01-24 09:16:55.013780: step: 1500/529, loss: 0.006082726176828146
2023-01-24 09:16:56.118874: step: 1504/529, loss: 0.0028926811646670103
2023-01-24 09:16:57.209678: step: 1508/529, loss: 0.0001696194231044501
2023-01-24 09:16:58.334918: step: 1512/529, loss: 0.0024253271985799074
2023-01-24 09:16:59.458103: step: 1516/529, loss: 0.007770913653075695
2023-01-24 09:17:00.575461: step: 1520/529, loss: 0.012699322775006294
2023-01-24 09:17:01.672282: step: 1524/529, loss: 0.017201188951730728
2023-01-24 09:17:02.761846: step: 1528/529, loss: 0.009002854116261005
2023-01-24 09:17:03.860477: step: 1532/529, loss: 0.008372846059501171
2023-01-24 09:17:04.946065: step: 1536/529, loss: 0.003935167100280523
2023-01-24 09:17:06.047998: step: 1540/529, loss: 0.0019512263825163245
2023-01-24 09:17:07.171338: step: 1544/529, loss: 0.005391594022512436
2023-01-24 09:17:08.273379: step: 1548/529, loss: 0.00509494636207819
2023-01-24 09:17:09.387071: step: 1552/529, loss: 0.003335651708766818
2023-01-24 09:17:10.482755: step: 1556/529, loss: 0.0032638385891914368
2023-01-24 09:17:11.597196: step: 1560/529, loss: 0.007019201293587685
2023-01-24 09:17:12.708644: step: 1564/529, loss: 0.016559820622205734
2023-01-24 09:17:13.803299: step: 1568/529, loss: 0.0037013862747699022
2023-01-24 09:17:14.900289: step: 1572/529, loss: 0.003973239101469517
2023-01-24 09:17:15.999669: step: 1576/529, loss: 0.0024306594859808683
2023-01-24 09:17:17.091925: step: 1580/529, loss: 0.0065403287298977375
2023-01-24 09:17:18.210998: step: 1584/529, loss: 0.004244917072355747
2023-01-24 09:17:19.320931: step: 1588/529, loss: 0.01420369278639555
2023-01-24 09:17:20.422227: step: 1592/529, loss: 0.0041676415130496025
2023-01-24 09:17:21.530450: step: 1596/529, loss: 0.010674137622117996
2023-01-24 09:17:22.612909: step: 1600/529, loss: 0.0014914104249328375
2023-01-24 09:17:23.721021: step: 1604/529, loss: 0.0036897300742566586
2023-01-24 09:17:24.828955: step: 1608/529, loss: 0.007229203823953867
2023-01-24 09:17:25.909166: step: 1612/529, loss: 0.0019751908257603645
2023-01-24 09:17:27.021240: step: 1616/529, loss: 0.009596874006092548
2023-01-24 09:17:28.122002: step: 1620/529, loss: 0.004519632551819086
2023-01-24 09:17:29.226578: step: 1624/529, loss: 0.011144997552037239
2023-01-24 09:17:30.337271: step: 1628/529, loss: 0.005563520826399326
2023-01-24 09:17:31.423138: step: 1632/529, loss: 0.027692407369613647
2023-01-24 09:17:32.531968: step: 1636/529, loss: 0.0023939991369843483
2023-01-24 09:17:33.635008: step: 1640/529, loss: 0.0012472938979044557
2023-01-24 09:17:34.732139: step: 1644/529, loss: 0.011303827166557312
2023-01-24 09:17:35.824426: step: 1648/529, loss: 0.010501573793590069
2023-01-24 09:17:36.935255: step: 1652/529, loss: 0.004100640304386616
2023-01-24 09:17:38.030467: step: 1656/529, loss: 0.008339384570717812
2023-01-24 09:17:39.124960: step: 1660/529, loss: 0.011582618579268456
2023-01-24 09:17:40.249163: step: 1664/529, loss: 0.005339955445379019
2023-01-24 09:17:41.339696: step: 1668/529, loss: 0.0023792346473783255
2023-01-24 09:17:42.446508: step: 1672/529, loss: 0.00461668660864234
2023-01-24 09:17:43.552712: step: 1676/529, loss: 0.03551819920539856
2023-01-24 09:17:44.658431: step: 1680/529, loss: 0.00201983074657619
2023-01-24 09:17:45.742523: step: 1684/529, loss: 0.007052142638713121
2023-01-24 09:17:46.852573: step: 1688/529, loss: 0.007040137890726328
2023-01-24 09:17:47.965815: step: 1692/529, loss: 0.0031473380513489246
2023-01-24 09:17:49.060710: step: 1696/529, loss: 0.014354725368320942
2023-01-24 09:17:50.194443: step: 1700/529, loss: 0.001469269162043929
2023-01-24 09:17:51.289128: step: 1704/529, loss: 0.003306277096271515
2023-01-24 09:17:52.363927: step: 1708/529, loss: 6.649853457929567e-05
2023-01-24 09:17:53.484353: step: 1712/529, loss: 0.0029305091593414545
2023-01-24 09:17:54.572363: step: 1716/529, loss: 0.06696254014968872
2023-01-24 09:17:55.677527: step: 1720/529, loss: 0.0056436811573803425
2023-01-24 09:17:56.782596: step: 1724/529, loss: 0.007862314581871033
2023-01-24 09:17:57.890951: step: 1728/529, loss: 0.001981362234801054
2023-01-24 09:17:59.023173: step: 1732/529, loss: 0.0005357115296646953
2023-01-24 09:18:00.128449: step: 1736/529, loss: 0.0020502007100731134
2023-01-24 09:18:01.224793: step: 1740/529, loss: 0.0066886888816952705
2023-01-24 09:18:02.373176: step: 1744/529, loss: 0.008874895982444286
2023-01-24 09:18:03.508776: step: 1748/529, loss: 0.0013597782235592604
2023-01-24 09:18:04.601954: step: 1752/529, loss: 0.002254927298054099
2023-01-24 09:18:05.706229: step: 1756/529, loss: 0.002668507397174835
2023-01-24 09:18:06.800432: step: 1760/529, loss: 0.004951762966811657
2023-01-24 09:18:07.897232: step: 1764/529, loss: 0.0053134518675506115
2023-01-24 09:18:09.024152: step: 1768/529, loss: 0.008444095030426979
2023-01-24 09:18:10.125112: step: 1772/529, loss: 0.0048981402069330215
2023-01-24 09:18:11.213916: step: 1776/529, loss: 0.002013629302382469
2023-01-24 09:18:12.292303: step: 1780/529, loss: 0.006046490743756294
2023-01-24 09:18:13.409867: step: 1784/529, loss: 0.0023891483433544636
2023-01-24 09:18:14.532765: step: 1788/529, loss: 0.006254952400922775
2023-01-24 09:18:15.631431: step: 1792/529, loss: 0.0017275239806622267
2023-01-24 09:18:16.760505: step: 1796/529, loss: 0.002768761944025755
2023-01-24 09:18:17.868945: step: 1800/529, loss: 0.01100082416087389
2023-01-24 09:18:18.973712: step: 1804/529, loss: 0.0097651407122612
2023-01-24 09:18:20.078774: step: 1808/529, loss: 0.009489976800978184
2023-01-24 09:18:21.190017: step: 1812/529, loss: 0.0043052989058196545
2023-01-24 09:18:22.317909: step: 1816/529, loss: 0.003355396678671241
2023-01-24 09:18:23.434133: step: 1820/529, loss: 0.009334057569503784
2023-01-24 09:18:24.556619: step: 1824/529, loss: 0.009333780035376549
2023-01-24 09:18:25.670572: step: 1828/529, loss: 0.005161263979971409
2023-01-24 09:18:26.757991: step: 1832/529, loss: 0.00623353524133563
2023-01-24 09:18:27.870275: step: 1836/529, loss: 0.014610852114856243
2023-01-24 09:18:28.948966: step: 1840/529, loss: 0.0091658104211092
2023-01-24 09:18:30.067238: step: 1844/529, loss: 0.018840985372662544
2023-01-24 09:18:31.164081: step: 1848/529, loss: 0.006212329957634211
2023-01-24 09:18:32.253927: step: 1852/529, loss: 0.002447352511808276
2023-01-24 09:18:33.356263: step: 1856/529, loss: 0.016949230805039406
2023-01-24 09:18:34.458430: step: 1860/529, loss: 0.005489578004926443
2023-01-24 09:18:35.552197: step: 1864/529, loss: 0.008976762183010578
2023-01-24 09:18:36.630160: step: 1868/529, loss: 0.003297926625236869
2023-01-24 09:18:37.729459: step: 1872/529, loss: 0.005246599670499563
2023-01-24 09:18:38.856687: step: 1876/529, loss: 0.010308386757969856
2023-01-24 09:18:39.949767: step: 1880/529, loss: 0.00042239148751832545
2023-01-24 09:18:41.065418: step: 1884/529, loss: 0.009330831468105316
2023-01-24 09:18:42.175488: step: 1888/529, loss: 0.0014277645386755466
2023-01-24 09:18:43.285348: step: 1892/529, loss: 0.004763399716466665
2023-01-24 09:18:44.400080: step: 1896/529, loss: 0.011139397509396076
2023-01-24 09:18:45.513381: step: 1900/529, loss: 0.005003584083169699
2023-01-24 09:18:46.611434: step: 1904/529, loss: 0.006582403089851141
2023-01-24 09:18:47.717482: step: 1908/529, loss: 0.0018480712315067649
2023-01-24 09:18:48.799962: step: 1912/529, loss: 0.0008753414731472731
2023-01-24 09:18:49.875879: step: 1916/529, loss: 0.0014442336978390813
2023-01-24 09:18:50.978968: step: 1920/529, loss: 0.01727409102022648
2023-01-24 09:18:52.080805: step: 1924/529, loss: 0.011511181481182575
2023-01-24 09:18:53.173058: step: 1928/529, loss: 0.00012517809227574617
2023-01-24 09:18:54.262616: step: 1932/529, loss: 0.004393650684505701
2023-01-24 09:18:55.359442: step: 1936/529, loss: 0.006960937287658453
2023-01-24 09:18:56.476108: step: 1940/529, loss: 0.002801342634484172
2023-01-24 09:18:57.577595: step: 1944/529, loss: 0.005089263431727886
2023-01-24 09:18:58.684600: step: 1948/529, loss: 0.008249325677752495
2023-01-24 09:18:59.791788: step: 1952/529, loss: 0.009227005764842033
2023-01-24 09:19:00.898774: step: 1956/529, loss: 0.003623245283961296
2023-01-24 09:19:02.009308: step: 1960/529, loss: 0.03922535479068756
2023-01-24 09:19:03.119360: step: 1964/529, loss: 0.004454377572983503
2023-01-24 09:19:04.219875: step: 1968/529, loss: 0.047634806483983994
2023-01-24 09:19:05.329750: step: 1972/529, loss: 0.007287457585334778
2023-01-24 09:19:06.434004: step: 1976/529, loss: 0.013993768952786922
2023-01-24 09:19:07.525476: step: 1980/529, loss: 0.0004196054651401937
2023-01-24 09:19:08.622023: step: 1984/529, loss: 0.003994377329945564
2023-01-24 09:19:09.728359: step: 1988/529, loss: 0.013684292323887348
2023-01-24 09:19:10.829031: step: 1992/529, loss: 0.012142702005803585
2023-01-24 09:19:11.926420: step: 1996/529, loss: 0.004128783941268921
2023-01-24 09:19:13.030869: step: 2000/529, loss: 0.006840996909886599
2023-01-24 09:19:14.121039: step: 2004/529, loss: 0.024897616356611252
2023-01-24 09:19:15.242843: step: 2008/529, loss: 0.0038118695374578238
2023-01-24 09:19:16.337427: step: 2012/529, loss: 0.000697502342518419
2023-01-24 09:19:17.434715: step: 2016/529, loss: 0.004093602299690247
2023-01-24 09:19:18.519334: step: 2020/529, loss: 0.0002405818522674963
2023-01-24 09:19:19.612957: step: 2024/529, loss: 0.0002203623007517308
2023-01-24 09:19:20.714037: step: 2028/529, loss: 0.008386366069316864
2023-01-24 09:19:21.815956: step: 2032/529, loss: 0.010255941189825535
2023-01-24 09:19:22.924777: step: 2036/529, loss: 0.001848246669396758
2023-01-24 09:19:24.040448: step: 2040/529, loss: 0.0015120984753593802
2023-01-24 09:19:25.140292: step: 2044/529, loss: 0.0016965073300525546
2023-01-24 09:19:26.244244: step: 2048/529, loss: 0.0006703918916173279
2023-01-24 09:19:27.346751: step: 2052/529, loss: 0.019006190821528435
2023-01-24 09:19:28.449196: step: 2056/529, loss: 0.012485519051551819
2023-01-24 09:19:29.571803: step: 2060/529, loss: 0.0028193420730531216
2023-01-24 09:19:30.678406: step: 2064/529, loss: 0.0033545701298862696
2023-01-24 09:19:31.800665: step: 2068/529, loss: 0.0016799798468127847
2023-01-24 09:19:32.900647: step: 2072/529, loss: 0.0003219117352273315
2023-01-24 09:19:34.008798: step: 2076/529, loss: 0.0012330266181379557
2023-01-24 09:19:35.138377: step: 2080/529, loss: 0.008077512495219707
2023-01-24 09:19:36.247120: step: 2084/529, loss: 0.0036298127379268408
2023-01-24 09:19:37.348777: step: 2088/529, loss: 0.003100254572927952
2023-01-24 09:19:38.434250: step: 2092/529, loss: 0.00027639689506031573
2023-01-24 09:19:39.519370: step: 2096/529, loss: 0.000616960518527776
2023-01-24 09:19:40.624395: step: 2100/529, loss: 0.017584307119250298
2023-01-24 09:19:41.708247: step: 2104/529, loss: 0.0077926889061927795
2023-01-24 09:19:42.805165: step: 2108/529, loss: 0.00510401651263237
2023-01-24 09:19:43.892672: step: 2112/529, loss: 0.06850270181894302
2023-01-24 09:19:45.004159: step: 2116/529, loss: 0.005144988186657429
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3790129078238834, 'r': 0.32435449986446185, 'f1': 0.34955996202161843}, 'combined': 0.25757049833171886, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.39976120849667723, 'r': 0.2885624667917956, 'f1': 0.3351797550857898}, 'combined': 0.20601292263809518, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37294105919879916, 'r': 0.33614232090973356, 'f1': 0.35358683257371176}, 'combined': 0.2605376661069455, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3815140953399116, 'r': 0.2915904957450624, 'f1': 0.33054561109017877}, 'combined': 0.20316461949932937, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40829646017699117, 'r': 0.35018975332068314, 'f1': 0.3770173646578141}, 'combined': 0.27780226869523145, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.4009873764410785, 'r': 0.2870152278512399, 'f1': 0.33456118478821295}, 'combined': 0.2066407317809551, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:22:09.907650: step: 4/529, loss: 0.00014066699077375233
2023-01-24 09:22:10.996171: step: 8/529, loss: 6.804722215747461e-05
2023-01-24 09:22:12.079933: step: 12/529, loss: 0.007144611328840256
2023-01-24 09:22:13.163749: step: 16/529, loss: 0.0002006435242947191
2023-01-24 09:22:14.282676: step: 20/529, loss: 0.008061826229095459
2023-01-24 09:22:15.378845: step: 24/529, loss: 0.005260359030216932
2023-01-24 09:22:16.500896: step: 28/529, loss: 0.0011097720125690103
2023-01-24 09:22:17.625809: step: 32/529, loss: 0.002329524839296937
2023-01-24 09:22:18.712245: step: 36/529, loss: 4.7850655391812325e-05
2023-01-24 09:22:19.802562: step: 40/529, loss: 0.00406494690105319
2023-01-24 09:22:20.909802: step: 44/529, loss: 0.0009985339129343629
2023-01-24 09:22:21.983939: step: 48/529, loss: 0.006624714005738497
2023-01-24 09:22:23.074992: step: 52/529, loss: 0.00023740004689898342
2023-01-24 09:22:24.177165: step: 56/529, loss: 0.01133043970912695
2023-01-24 09:22:25.280905: step: 60/529, loss: 0.0026419993955641985
2023-01-24 09:22:26.351028: step: 64/529, loss: 0.0002959644771181047
2023-01-24 09:22:27.464423: step: 68/529, loss: 0.002906143432483077
2023-01-24 09:22:28.579934: step: 72/529, loss: 0.0004793589760083705
2023-01-24 09:22:29.669980: step: 76/529, loss: 0.009128259494900703
2023-01-24 09:22:30.806713: step: 80/529, loss: 0.0033187370281666517
2023-01-24 09:22:31.908998: step: 84/529, loss: 0.001691467477940023
2023-01-24 09:22:33.011007: step: 88/529, loss: 0.00849154032766819
2023-01-24 09:22:34.108752: step: 92/529, loss: 0.01052180491387844
2023-01-24 09:22:35.198109: step: 96/529, loss: 0.027855128049850464
2023-01-24 09:22:36.307314: step: 100/529, loss: 0.000742443953640759
2023-01-24 09:22:37.455384: step: 104/529, loss: 0.0006658468046225607
2023-01-24 09:22:38.577998: step: 108/529, loss: 0.008926274254918098
2023-01-24 09:22:39.663912: step: 112/529, loss: 0.0021948402281850576
2023-01-24 09:22:40.775799: step: 116/529, loss: 0.004141767509281635
2023-01-24 09:22:41.884020: step: 120/529, loss: 0.016386695206165314
2023-01-24 09:22:42.972844: step: 124/529, loss: 0.0030487675685435534
2023-01-24 09:22:44.093744: step: 128/529, loss: 0.0036591063253581524
2023-01-24 09:22:45.211571: step: 132/529, loss: 0.006724723614752293
2023-01-24 09:22:46.391674: step: 136/529, loss: 0.0007174345082603395
2023-01-24 09:22:47.501631: step: 140/529, loss: 0.0014685202622786164
2023-01-24 09:22:48.592101: step: 144/529, loss: 0.0004873551370110363
2023-01-24 09:22:49.703842: step: 148/529, loss: 0.0033629818353801966
2023-01-24 09:22:50.835696: step: 152/529, loss: 0.00596148194745183
2023-01-24 09:22:51.937071: step: 156/529, loss: 0.002383374609053135
2023-01-24 09:22:53.032693: step: 160/529, loss: 0.008389468304812908
2023-01-24 09:22:54.149822: step: 164/529, loss: 0.0028305177111178637
2023-01-24 09:22:55.247704: step: 168/529, loss: 0.02574547380208969
2023-01-24 09:22:56.339214: step: 172/529, loss: 4.863203866989352e-05
2023-01-24 09:22:57.427078: step: 176/529, loss: 0.005315895192325115
2023-01-24 09:22:58.527773: step: 180/529, loss: 0.015754589810967445
2023-01-24 09:22:59.649691: step: 184/529, loss: 0.0009819060796871781
2023-01-24 09:23:00.740078: step: 188/529, loss: 0.011542145162820816
2023-01-24 09:23:01.866130: step: 192/529, loss: 0.011502913199365139
2023-01-24 09:23:02.980001: step: 196/529, loss: 0.001410657074302435
2023-01-24 09:23:04.088780: step: 200/529, loss: 0.004170591477304697
2023-01-24 09:23:05.185539: step: 204/529, loss: 0.002422420075163245
2023-01-24 09:23:06.292744: step: 208/529, loss: 0.007114346604794264
2023-01-24 09:23:07.404459: step: 212/529, loss: 0.018315928056836128
2023-01-24 09:23:08.512123: step: 216/529, loss: 0.005528508685529232
2023-01-24 09:23:09.624982: step: 220/529, loss: 0.007643497083336115
2023-01-24 09:23:10.736037: step: 224/529, loss: 0.0023897422943264246
2023-01-24 09:23:11.855244: step: 228/529, loss: 0.0034760087728500366
2023-01-24 09:23:12.947420: step: 232/529, loss: 0.011766092851758003
2023-01-24 09:23:14.028298: step: 236/529, loss: 0.0009508852963335812
2023-01-24 09:23:15.117639: step: 240/529, loss: 0.004056363832205534
2023-01-24 09:23:16.241422: step: 244/529, loss: 0.0011971058556810021
2023-01-24 09:23:17.351545: step: 248/529, loss: 0.011388525366783142
2023-01-24 09:23:18.426102: step: 252/529, loss: 0.0016499351477250457
2023-01-24 09:23:19.539738: step: 256/529, loss: 0.004142810590565205
2023-01-24 09:23:20.654262: step: 260/529, loss: 0.0025163902901113033
2023-01-24 09:23:21.780898: step: 264/529, loss: 0.005788113456219435
2023-01-24 09:23:22.892806: step: 268/529, loss: 0.006758593022823334
2023-01-24 09:23:23.992092: step: 272/529, loss: 0.00033913305378519
2023-01-24 09:23:25.103177: step: 276/529, loss: 0.007300782483071089
2023-01-24 09:23:26.216831: step: 280/529, loss: 0.013562587089836597
2023-01-24 09:23:27.322039: step: 284/529, loss: 0.0014538648538291454
2023-01-24 09:23:28.427297: step: 288/529, loss: 0.0005513126961886883
2023-01-24 09:23:29.524387: step: 292/529, loss: 0.004913745913654566
2023-01-24 09:23:30.643658: step: 296/529, loss: 0.009528543800115585
2023-01-24 09:23:31.712757: step: 300/529, loss: 0.0005764710949733853
2023-01-24 09:23:32.850353: step: 304/529, loss: 0.002948667388409376
2023-01-24 09:23:33.945211: step: 308/529, loss: 0.00105380080640316
2023-01-24 09:23:35.051154: step: 312/529, loss: 0.0009540129103697836
2023-01-24 09:23:36.154207: step: 316/529, loss: 0.005260543432086706
2023-01-24 09:23:37.272630: step: 320/529, loss: 0.003926956094801426
2023-01-24 09:23:38.347292: step: 324/529, loss: 0.0006715389317832887
2023-01-24 09:23:39.437125: step: 328/529, loss: 0.01817171461880207
2023-01-24 09:23:40.550394: step: 332/529, loss: 0.004444970283657312
2023-01-24 09:23:41.678540: step: 336/529, loss: 0.00256772106513381
2023-01-24 09:23:42.794541: step: 340/529, loss: 0.012765337713062763
2023-01-24 09:23:43.874502: step: 344/529, loss: 0.004169865977019072
2023-01-24 09:23:44.952587: step: 348/529, loss: 0.01905876398086548
2023-01-24 09:23:46.067784: step: 352/529, loss: 0.005085855722427368
2023-01-24 09:23:47.174127: step: 356/529, loss: 0.001628398080356419
2023-01-24 09:23:48.301164: step: 360/529, loss: 0.005859238561242819
2023-01-24 09:23:49.417373: step: 364/529, loss: 0.0018615691224113107
2023-01-24 09:23:50.511644: step: 368/529, loss: 0.0006174053996801376
2023-01-24 09:23:51.643027: step: 372/529, loss: 0.00788771454244852
2023-01-24 09:23:52.741488: step: 376/529, loss: 0.0025621491950005293
2023-01-24 09:23:53.836003: step: 380/529, loss: 0.0005735280574299395
2023-01-24 09:23:54.941858: step: 384/529, loss: 0.002404374536126852
2023-01-24 09:23:56.047589: step: 388/529, loss: 0.0036898041144013405
2023-01-24 09:23:57.139115: step: 392/529, loss: 0.00010659175313776359
2023-01-24 09:23:58.253255: step: 396/529, loss: 0.00033455833909101784
2023-01-24 09:23:59.349330: step: 400/529, loss: 0.0048098755069077015
2023-01-24 09:24:00.472938: step: 404/529, loss: 0.001305817742832005
2023-01-24 09:24:01.561360: step: 408/529, loss: 0.003557774471119046
2023-01-24 09:24:02.688639: step: 412/529, loss: 0.0022564949467778206
2023-01-24 09:24:03.802118: step: 416/529, loss: 0.004168667830526829
2023-01-24 09:24:04.896889: step: 420/529, loss: 0.0007751243538223207
2023-01-24 09:24:06.009751: step: 424/529, loss: 0.0010004036594182253
2023-01-24 09:24:07.114632: step: 428/529, loss: 0.000813534832559526
2023-01-24 09:24:08.224377: step: 432/529, loss: 0.010044993832707405
2023-01-24 09:24:09.359540: step: 436/529, loss: 0.0059012179262936115
2023-01-24 09:24:10.455691: step: 440/529, loss: 0.0020030431915074587
2023-01-24 09:24:11.559158: step: 444/529, loss: 0.0006674128817394376
2023-01-24 09:24:12.676059: step: 448/529, loss: 0.0025878131855279207
2023-01-24 09:24:13.798914: step: 452/529, loss: 0.003642268246039748
2023-01-24 09:24:14.916036: step: 456/529, loss: 0.007925009354948997
2023-01-24 09:24:16.034796: step: 460/529, loss: 8.282779162982479e-05
2023-01-24 09:24:17.132687: step: 464/529, loss: 0.006399889476597309
2023-01-24 09:24:18.251194: step: 468/529, loss: 0.002955260220915079
2023-01-24 09:24:19.348592: step: 472/529, loss: 0.0017032220494002104
2023-01-24 09:24:20.455140: step: 476/529, loss: 0.0058366963639855385
2023-01-24 09:24:21.551681: step: 480/529, loss: 0.0066220504231750965
2023-01-24 09:24:22.662903: step: 484/529, loss: 0.0007051354041323066
2023-01-24 09:24:23.773835: step: 488/529, loss: 0.003883779514580965
2023-01-24 09:24:24.905355: step: 492/529, loss: 0.008248812519013882
2023-01-24 09:24:26.014923: step: 496/529, loss: 0.0013648374006152153
2023-01-24 09:24:27.122519: step: 500/529, loss: 0.005969061050564051
2023-01-24 09:24:28.234364: step: 504/529, loss: 0.008295079693198204
2023-01-24 09:24:29.330066: step: 508/529, loss: 0.001758683705702424
2023-01-24 09:24:30.441522: step: 512/529, loss: 0.014007318764925003
2023-01-24 09:24:31.572951: step: 516/529, loss: 0.0018363615963608027
2023-01-24 09:24:32.699993: step: 520/529, loss: 0.005349340848624706
2023-01-24 09:24:33.812992: step: 524/529, loss: 0.0026836220640689135
2023-01-24 09:24:34.908901: step: 528/529, loss: 0.00022390381491277367
2023-01-24 09:24:36.045685: step: 532/529, loss: 0.002677630167454481
2023-01-24 09:24:37.125449: step: 536/529, loss: 0.0013838220620527864
2023-01-24 09:24:38.227952: step: 540/529, loss: 0.0008319858461618423
2023-01-24 09:24:39.331068: step: 544/529, loss: 0.0036801432725042105
2023-01-24 09:24:40.434823: step: 548/529, loss: 0.004043183755129576
2023-01-24 09:24:41.551157: step: 552/529, loss: 0.003895303001627326
2023-01-24 09:24:42.651571: step: 556/529, loss: 0.003321310505270958
2023-01-24 09:24:43.762988: step: 560/529, loss: 0.008743378333747387
2023-01-24 09:24:44.843653: step: 564/529, loss: 0.004023090936243534
2023-01-24 09:24:45.957836: step: 568/529, loss: 0.009847203269600868
2023-01-24 09:24:47.058698: step: 572/529, loss: 0.005047728773206472
2023-01-24 09:24:48.149935: step: 576/529, loss: 0.004513503052294254
2023-01-24 09:24:49.242248: step: 580/529, loss: 0.0016682291170582175
2023-01-24 09:24:50.359782: step: 584/529, loss: 0.001351230894215405
2023-01-24 09:24:51.468429: step: 588/529, loss: 0.0002922937856055796
2023-01-24 09:24:52.567700: step: 592/529, loss: 0.0061531090177595615
2023-01-24 09:24:53.669786: step: 596/529, loss: 0.0029740040190517902
2023-01-24 09:24:54.771995: step: 600/529, loss: 0.0024397841189056635
2023-01-24 09:24:55.869903: step: 604/529, loss: 0.001254424569196999
2023-01-24 09:24:56.968698: step: 608/529, loss: 0.0013636890798807144
2023-01-24 09:24:58.081315: step: 612/529, loss: 0.001084949355572462
2023-01-24 09:24:59.170389: step: 616/529, loss: 2.5542514777043834e-05
2023-01-24 09:25:00.289380: step: 620/529, loss: 0.002615207340568304
2023-01-24 09:25:01.395083: step: 624/529, loss: 0.00659587187692523
2023-01-24 09:25:02.519471: step: 628/529, loss: 0.0029926938004791737
2023-01-24 09:25:03.630089: step: 632/529, loss: 0.006990282330662012
2023-01-24 09:25:04.728307: step: 636/529, loss: 0.009059948846697807
2023-01-24 09:25:05.824905: step: 640/529, loss: 0.007853774353861809
2023-01-24 09:25:06.941554: step: 644/529, loss: 0.003246077336370945
2023-01-24 09:25:08.045488: step: 648/529, loss: 0.0021399124525487423
2023-01-24 09:25:09.159230: step: 652/529, loss: 0.0015789818717166781
2023-01-24 09:25:10.269087: step: 656/529, loss: 0.00551167456433177
2023-01-24 09:25:11.374895: step: 660/529, loss: 0.0038017481565475464
2023-01-24 09:25:12.479870: step: 664/529, loss: 0.015864379703998566
2023-01-24 09:25:13.584524: step: 668/529, loss: 0.02462594583630562
2023-01-24 09:25:14.676741: step: 672/529, loss: 0.0037727653980255127
2023-01-24 09:25:15.772272: step: 676/529, loss: 0.0011074565118178725
2023-01-24 09:25:16.899939: step: 680/529, loss: 0.0018161415355280042
2023-01-24 09:25:17.989678: step: 684/529, loss: 0.0012065795017406344
2023-01-24 09:25:19.079516: step: 688/529, loss: 0.0020751527044922113
2023-01-24 09:25:20.184936: step: 692/529, loss: 0.001213929965160787
2023-01-24 09:25:21.306868: step: 696/529, loss: 0.00249796942807734
2023-01-24 09:25:22.424292: step: 700/529, loss: 0.00019309222989249974
2023-01-24 09:25:23.518102: step: 704/529, loss: 0.0005429618177004158
2023-01-24 09:25:24.628601: step: 708/529, loss: 0.020188502967357635
2023-01-24 09:25:25.729121: step: 712/529, loss: 0.004486955236643553
2023-01-24 09:25:26.832336: step: 716/529, loss: 0.0032540129031986
2023-01-24 09:25:27.944228: step: 720/529, loss: 0.00016577863425482064
2023-01-24 09:25:29.040148: step: 724/529, loss: 0.003164031310006976
2023-01-24 09:25:30.142155: step: 728/529, loss: 0.0058807688765227795
2023-01-24 09:25:31.258822: step: 732/529, loss: 0.0024319204967468977
2023-01-24 09:25:32.358798: step: 736/529, loss: 0.0015095642302185297
2023-01-24 09:25:33.466538: step: 740/529, loss: 0.011623300611972809
2023-01-24 09:25:34.570957: step: 744/529, loss: 0.0029770415276288986
2023-01-24 09:25:35.658609: step: 748/529, loss: 0.0017354115843772888
2023-01-24 09:25:36.755112: step: 752/529, loss: 0.0014948470052331686
2023-01-24 09:25:37.874907: step: 756/529, loss: 0.008451261557638645
2023-01-24 09:25:38.953373: step: 760/529, loss: 0.01382976770401001
2023-01-24 09:25:40.079120: step: 764/529, loss: 0.006939781829714775
2023-01-24 09:25:41.212439: step: 768/529, loss: 0.03109847754240036
2023-01-24 09:25:42.323957: step: 772/529, loss: 0.004628642462193966
2023-01-24 09:25:43.409105: step: 776/529, loss: 0.006465520244091749
2023-01-24 09:25:44.504562: step: 780/529, loss: 0.0008791473228484392
2023-01-24 09:25:45.634544: step: 784/529, loss: 0.031057298183441162
2023-01-24 09:25:46.739587: step: 788/529, loss: 0.003810094902291894
2023-01-24 09:25:47.828621: step: 792/529, loss: 0.0015693034511059523
2023-01-24 09:25:48.930107: step: 796/529, loss: 0.0007189961615949869
2023-01-24 09:25:50.047202: step: 800/529, loss: 0.008132641203701496
2023-01-24 09:25:51.144323: step: 804/529, loss: 0.00201398110948503
2023-01-24 09:25:52.254023: step: 808/529, loss: 0.003772712778300047
2023-01-24 09:25:53.353878: step: 812/529, loss: 0.0010151639580726624
2023-01-24 09:25:54.458261: step: 816/529, loss: 0.00570036331191659
2023-01-24 09:25:55.591095: step: 820/529, loss: 0.0028964008670300245
2023-01-24 09:25:56.678803: step: 824/529, loss: 0.0010831697145476937
2023-01-24 09:25:57.781871: step: 828/529, loss: 0.0027090804651379585
2023-01-24 09:25:58.894541: step: 832/529, loss: 0.004136858507990837
2023-01-24 09:25:59.999252: step: 836/529, loss: 0.0049913739785552025
2023-01-24 09:26:01.104309: step: 840/529, loss: 0.0033293762244284153
2023-01-24 09:26:02.256128: step: 844/529, loss: 0.004989622626453638
2023-01-24 09:26:03.352210: step: 848/529, loss: 0.0046120393089950085
2023-01-24 09:26:04.472297: step: 852/529, loss: 0.00783604010939598
2023-01-24 09:26:05.585912: step: 856/529, loss: 0.008817343972623348
2023-01-24 09:26:06.689039: step: 860/529, loss: 0.0012536334106698632
2023-01-24 09:26:07.819113: step: 864/529, loss: 0.0007285188767127693
2023-01-24 09:26:08.939196: step: 868/529, loss: 0.011100014671683311
2023-01-24 09:26:10.036549: step: 872/529, loss: 0.012568839825689793
2023-01-24 09:26:11.151401: step: 876/529, loss: 0.003599324496462941
2023-01-24 09:26:12.263325: step: 880/529, loss: 0.0023192751687020063
2023-01-24 09:26:13.385297: step: 884/529, loss: 0.003987746778875589
2023-01-24 09:26:14.507607: step: 888/529, loss: 0.006785211153328419
2023-01-24 09:26:15.620586: step: 892/529, loss: 0.005245667416602373
2023-01-24 09:26:16.723279: step: 896/529, loss: 0.001611137529835105
2023-01-24 09:26:17.834517: step: 900/529, loss: 0.0020552293863147497
2023-01-24 09:26:18.921208: step: 904/529, loss: 0.03360049054026604
2023-01-24 09:26:20.041710: step: 908/529, loss: 0.009339140728116035
2023-01-24 09:26:21.135579: step: 912/529, loss: 0.0027816693764179945
2023-01-24 09:26:22.269047: step: 916/529, loss: 0.006510804872959852
2023-01-24 09:26:23.363565: step: 920/529, loss: 0.0011626067571341991
2023-01-24 09:26:24.471783: step: 924/529, loss: 0.006616579368710518
2023-01-24 09:26:25.597007: step: 928/529, loss: 0.001994227059185505
2023-01-24 09:26:26.695779: step: 932/529, loss: 0.004685595631599426
2023-01-24 09:26:27.786103: step: 936/529, loss: 0.00412451708689332
2023-01-24 09:26:28.891912: step: 940/529, loss: 0.0052533987909555435
2023-01-24 09:26:30.005715: step: 944/529, loss: 0.004642639309167862
2023-01-24 09:26:31.125369: step: 948/529, loss: 8.168735075742006e-05
2023-01-24 09:26:32.222301: step: 952/529, loss: 0.00092249148292467
2023-01-24 09:26:33.336264: step: 956/529, loss: 0.00235861842520535
2023-01-24 09:26:34.468423: step: 960/529, loss: 0.030054334551095963
2023-01-24 09:26:35.574435: step: 964/529, loss: 0.0011185595067217946
2023-01-24 09:26:36.679045: step: 968/529, loss: 0.0020445131231099367
2023-01-24 09:26:37.797225: step: 972/529, loss: 0.00395802641287446
2023-01-24 09:26:38.906190: step: 976/529, loss: 0.011483406648039818
2023-01-24 09:26:40.014965: step: 980/529, loss: 0.003362680319696665
2023-01-24 09:26:41.116116: step: 984/529, loss: 0.0029373872093856335
2023-01-24 09:26:42.219999: step: 988/529, loss: 0.0008233357220888138
2023-01-24 09:26:43.338798: step: 992/529, loss: 0.007795578800141811
2023-01-24 09:26:44.431825: step: 996/529, loss: 0.00022003796766512096
2023-01-24 09:26:45.566812: step: 1000/529, loss: 0.003951712045818567
2023-01-24 09:26:46.653511: step: 1004/529, loss: 0.006149396300315857
2023-01-24 09:26:47.761830: step: 1008/529, loss: 0.006995068397372961
2023-01-24 09:26:48.853470: step: 1012/529, loss: 0.009835072793066502
2023-01-24 09:26:49.964987: step: 1016/529, loss: 0.0022883054334670305
2023-01-24 09:26:51.074347: step: 1020/529, loss: 0.005302901845425367
2023-01-24 09:26:52.180900: step: 1024/529, loss: 0.03129454329609871
2023-01-24 09:26:53.272370: step: 1028/529, loss: 0.0014231225941330194
2023-01-24 09:26:54.366647: step: 1032/529, loss: 0.0003283943224232644
2023-01-24 09:26:55.475135: step: 1036/529, loss: 0.006184760015457869
2023-01-24 09:26:56.597589: step: 1040/529, loss: 0.006263521034270525
2023-01-24 09:26:57.700588: step: 1044/529, loss: 0.0016147817950695753
2023-01-24 09:26:58.825896: step: 1048/529, loss: 0.007773539982736111
2023-01-24 09:26:59.913015: step: 1052/529, loss: 0.01164105162024498
2023-01-24 09:27:01.016329: step: 1056/529, loss: 0.0048789698630571365
2023-01-24 09:27:02.105851: step: 1060/529, loss: 0.0010418322635814548
2023-01-24 09:27:03.227010: step: 1064/529, loss: 0.009207838214933872
2023-01-24 09:27:04.318338: step: 1068/529, loss: 0.007035735063254833
2023-01-24 09:27:05.412026: step: 1072/529, loss: 0.003296822775155306
2023-01-24 09:27:06.508391: step: 1076/529, loss: 2.4164819478755817e-05
2023-01-24 09:27:07.625362: step: 1080/529, loss: 0.0007315662805922329
2023-01-24 09:27:08.737113: step: 1084/529, loss: 0.0038923739921301603
2023-01-24 09:27:09.831124: step: 1088/529, loss: 0.006251499056816101
2023-01-24 09:27:10.930569: step: 1092/529, loss: 0.00013339155702851713
2023-01-24 09:27:12.022782: step: 1096/529, loss: 0.00040758305112831295
2023-01-24 09:27:13.138981: step: 1100/529, loss: 0.000778841960709542
2023-01-24 09:27:14.237720: step: 1104/529, loss: 0.008138620294630527
2023-01-24 09:27:15.338619: step: 1108/529, loss: 0.0003479059669189155
2023-01-24 09:27:16.444940: step: 1112/529, loss: 0.0006827504257671535
2023-01-24 09:27:17.517289: step: 1116/529, loss: 0.0015229344135150313
2023-01-24 09:27:18.607406: step: 1120/529, loss: 0.005617843009531498
2023-01-24 09:27:19.713065: step: 1124/529, loss: 0.0029102216940373182
2023-01-24 09:27:20.831997: step: 1128/529, loss: 0.0023615192621946335
2023-01-24 09:27:21.935601: step: 1132/529, loss: 0.003164583118632436
2023-01-24 09:27:23.032805: step: 1136/529, loss: 0.0028596746269613504
2023-01-24 09:27:24.132270: step: 1140/529, loss: 0.004839289467781782
2023-01-24 09:27:25.251247: step: 1144/529, loss: 0.005066284444183111
2023-01-24 09:27:26.357570: step: 1148/529, loss: 0.006997893564403057
2023-01-24 09:27:27.482467: step: 1152/529, loss: 0.0041889953427016735
2023-01-24 09:27:28.589740: step: 1156/529, loss: 0.0067227184772491455
2023-01-24 09:27:29.690091: step: 1160/529, loss: 0.011504698544740677
2023-01-24 09:27:30.789221: step: 1164/529, loss: 0.009526612237095833
2023-01-24 09:27:31.922674: step: 1168/529, loss: 0.0007159090018831193
2023-01-24 09:27:33.014929: step: 1172/529, loss: 0.002992949215695262
2023-01-24 09:27:34.118372: step: 1176/529, loss: 0.00432601198554039
2023-01-24 09:27:35.239110: step: 1180/529, loss: 0.004364124499261379
2023-01-24 09:27:36.350051: step: 1184/529, loss: 0.0006833907100372016
2023-01-24 09:27:37.451790: step: 1188/529, loss: 0.0032942513935267925
2023-01-24 09:27:38.554306: step: 1192/529, loss: 0.0069978623650968075
2023-01-24 09:27:39.681786: step: 1196/529, loss: 0.0009046870400197804
2023-01-24 09:27:40.780063: step: 1200/529, loss: 0.0021494224201887846
2023-01-24 09:27:41.891974: step: 1204/529, loss: 0.06519996374845505
2023-01-24 09:27:42.998193: step: 1208/529, loss: 0.00959350261837244
2023-01-24 09:27:44.089466: step: 1212/529, loss: 0.01464216411113739
2023-01-24 09:27:45.200496: step: 1216/529, loss: 0.011363436467945576
2023-01-24 09:27:46.336666: step: 1220/529, loss: 0.016761422157287598
2023-01-24 09:27:47.441830: step: 1224/529, loss: 0.01099938340485096
2023-01-24 09:27:48.537704: step: 1228/529, loss: 0.0030593248084187508
2023-01-24 09:27:49.646444: step: 1232/529, loss: 0.016539357602596283
2023-01-24 09:27:50.745132: step: 1236/529, loss: 0.05035647749900818
2023-01-24 09:27:51.852859: step: 1240/529, loss: 0.008927545510232449
2023-01-24 09:27:52.954412: step: 1244/529, loss: 0.0019050062401220202
2023-01-24 09:27:54.075733: step: 1248/529, loss: 0.007214971352368593
2023-01-24 09:27:55.187286: step: 1252/529, loss: 0.006051830481737852
2023-01-24 09:27:56.291714: step: 1256/529, loss: 0.0014903438277542591
2023-01-24 09:27:57.407241: step: 1260/529, loss: 0.00043756101513281465
2023-01-24 09:27:58.500084: step: 1264/529, loss: 0.0032073138281702995
2023-01-24 09:27:59.597060: step: 1268/529, loss: 0.0021619040053337812
2023-01-24 09:28:00.682743: step: 1272/529, loss: 7.138351065805182e-05
2023-01-24 09:28:01.802269: step: 1276/529, loss: 0.016567518934607506
2023-01-24 09:28:02.908783: step: 1280/529, loss: 0.0008126603788696229
2023-01-24 09:28:04.026380: step: 1284/529, loss: 0.0022804513573646545
2023-01-24 09:28:05.122089: step: 1288/529, loss: 0.007368456106632948
2023-01-24 09:28:06.238057: step: 1292/529, loss: 0.004361659288406372
2023-01-24 09:28:07.372098: step: 1296/529, loss: 0.0013874147552996874
2023-01-24 09:28:08.492682: step: 1300/529, loss: 0.0015606442466378212
2023-01-24 09:28:09.618328: step: 1304/529, loss: 0.004548514727503061
2023-01-24 09:28:10.732331: step: 1308/529, loss: 0.01393069326877594
2023-01-24 09:28:11.858218: step: 1312/529, loss: 0.00254705804400146
2023-01-24 09:28:12.948631: step: 1316/529, loss: 0.0019660783000290394
2023-01-24 09:28:14.020700: step: 1320/529, loss: 0.002159697934985161
2023-01-24 09:28:15.116775: step: 1324/529, loss: 0.0006825807504355907
2023-01-24 09:28:16.236110: step: 1328/529, loss: 0.0034086888190358877
2023-01-24 09:28:17.330365: step: 1332/529, loss: 0.002815220272168517
2023-01-24 09:28:18.479742: step: 1336/529, loss: 0.005541335325688124
2023-01-24 09:28:19.568418: step: 1340/529, loss: 0.012482447549700737
2023-01-24 09:28:20.688661: step: 1344/529, loss: 0.0077318670228123665
2023-01-24 09:28:21.785278: step: 1348/529, loss: 0.005491401068866253
2023-01-24 09:28:22.926024: step: 1352/529, loss: 0.014446879737079144
2023-01-24 09:28:24.026968: step: 1356/529, loss: 0.0033122741151601076
2023-01-24 09:28:25.127473: step: 1360/529, loss: 0.0002267425152240321
2023-01-24 09:28:26.237073: step: 1364/529, loss: 0.008907677605748177
2023-01-24 09:28:27.331498: step: 1368/529, loss: 0.004636609926819801
2023-01-24 09:28:28.425395: step: 1372/529, loss: 0.004368450026959181
2023-01-24 09:28:29.544058: step: 1376/529, loss: 0.001231278874911368
2023-01-24 09:28:30.655261: step: 1380/529, loss: 0.003768891328945756
2023-01-24 09:28:31.766285: step: 1384/529, loss: 0.005708478856831789
2023-01-24 09:28:32.873539: step: 1388/529, loss: 0.003974672872573137
2023-01-24 09:28:33.996386: step: 1392/529, loss: 0.0020599307026714087
2023-01-24 09:28:35.093429: step: 1396/529, loss: 0.0050084348767995834
2023-01-24 09:28:36.187123: step: 1400/529, loss: 0.004200869705528021
2023-01-24 09:28:37.274044: step: 1404/529, loss: 0.004128196742385626
2023-01-24 09:28:38.384700: step: 1408/529, loss: 0.0002895516809076071
2023-01-24 09:28:39.470429: step: 1412/529, loss: 0.0020509089808911085
2023-01-24 09:28:40.576271: step: 1416/529, loss: 0.005778855178505182
2023-01-24 09:28:41.666785: step: 1420/529, loss: 0.005256418604403734
2023-01-24 09:28:42.813843: step: 1424/529, loss: 0.04043223336338997
2023-01-24 09:28:43.916946: step: 1428/529, loss: 8.14585447983518e-08
2023-01-24 09:28:45.014236: step: 1432/529, loss: 0.005672309547662735
2023-01-24 09:28:46.136780: step: 1436/529, loss: 0.003921144176274538
2023-01-24 09:28:47.253748: step: 1440/529, loss: 0.01918674260377884
2023-01-24 09:28:48.353782: step: 1444/529, loss: 0.01670699007809162
2023-01-24 09:28:49.470060: step: 1448/529, loss: 0.0056404490023851395
2023-01-24 09:28:50.596760: step: 1452/529, loss: 0.006281205918639898
2023-01-24 09:28:51.705875: step: 1456/529, loss: 0.0015719493385404348
2023-01-24 09:28:52.801225: step: 1460/529, loss: 0.0008468436426483095
2023-01-24 09:28:53.932534: step: 1464/529, loss: 0.012255445122718811
2023-01-24 09:28:55.035544: step: 1468/529, loss: 0.012468352913856506
2023-01-24 09:28:56.143985: step: 1472/529, loss: 0.008524143137037754
2023-01-24 09:28:57.234903: step: 1476/529, loss: 0.011128108017146587
2023-01-24 09:28:58.342809: step: 1480/529, loss: 0.0017354199662804604
2023-01-24 09:28:59.438614: step: 1484/529, loss: 0.0018120865570381284
2023-01-24 09:29:00.523513: step: 1488/529, loss: 0.0022514646407216787
2023-01-24 09:29:01.641761: step: 1492/529, loss: 0.004379614256322384
2023-01-24 09:29:02.777706: step: 1496/529, loss: 0.002164768986403942
2023-01-24 09:29:03.877202: step: 1500/529, loss: 0.0024084909819066525
2023-01-24 09:29:04.988042: step: 1504/529, loss: 0.003927608486264944
2023-01-24 09:29:06.127824: step: 1508/529, loss: 0.0009050379740074277
2023-01-24 09:29:07.243437: step: 1512/529, loss: 0.002371875336393714
2023-01-24 09:29:08.347192: step: 1516/529, loss: 0.006972091738134623
2023-01-24 09:29:09.435443: step: 1520/529, loss: 0.015984030440449715
2023-01-24 09:29:10.550767: step: 1524/529, loss: 0.00791555643081665
2023-01-24 09:29:11.636516: step: 1528/529, loss: 3.0780862289248034e-05
2023-01-24 09:29:12.727518: step: 1532/529, loss: 0.005594571121037006
2023-01-24 09:29:13.831821: step: 1536/529, loss: 0.0028753369115293026
2023-01-24 09:29:14.930726: step: 1540/529, loss: 0.0027244416996836662
2023-01-24 09:29:16.026032: step: 1544/529, loss: 0.0006780403782613575
2023-01-24 09:29:17.116771: step: 1548/529, loss: 0.001308053731918335
2023-01-24 09:29:18.216974: step: 1552/529, loss: 0.005350498482584953
2023-01-24 09:29:19.315539: step: 1556/529, loss: 0.00045887118903920054
2023-01-24 09:29:20.417216: step: 1560/529, loss: 0.0008210574160329998
2023-01-24 09:29:21.527884: step: 1564/529, loss: 0.0014283667551353574
2023-01-24 09:29:22.630273: step: 1568/529, loss: 0.0033723702654242516
2023-01-24 09:29:23.730170: step: 1572/529, loss: 0.0003330713661853224
2023-01-24 09:29:24.834818: step: 1576/529, loss: 0.0032891619484871626
2023-01-24 09:29:25.930225: step: 1580/529, loss: 0.0007278310367837548
2023-01-24 09:29:27.021352: step: 1584/529, loss: 0.003239043988287449
2023-01-24 09:29:28.129341: step: 1588/529, loss: 0.0015649964334443212
2023-01-24 09:29:29.220958: step: 1592/529, loss: 0.0017161876894533634
2023-01-24 09:29:30.332168: step: 1596/529, loss: 0.0027427058666944504
2023-01-24 09:29:31.416173: step: 1600/529, loss: 0.000109870896267239
2023-01-24 09:29:32.537170: step: 1604/529, loss: 0.008840505965054035
2023-01-24 09:29:33.655610: step: 1608/529, loss: 0.0043314662761986256
2023-01-24 09:29:34.769135: step: 1612/529, loss: 0.00044054878526367247
2023-01-24 09:29:35.849994: step: 1616/529, loss: 3.8303591281874105e-05
2023-01-24 09:29:36.962756: step: 1620/529, loss: 0.015765313059091568
2023-01-24 09:29:38.049182: step: 1624/529, loss: 0.010190917178988457
2023-01-24 09:29:39.151373: step: 1628/529, loss: 0.003241418395191431
2023-01-24 09:29:40.247118: step: 1632/529, loss: 0.004772573243826628
2023-01-24 09:29:41.363694: step: 1636/529, loss: 0.001373734325170517
2023-01-24 09:29:42.481237: step: 1640/529, loss: 0.0017684214981272817
2023-01-24 09:29:43.586559: step: 1644/529, loss: 0.00039553537499159575
2023-01-24 09:29:44.692275: step: 1648/529, loss: 0.007489887531846762
2023-01-24 09:29:45.799940: step: 1652/529, loss: 0.006042259745299816
2023-01-24 09:29:46.908277: step: 1656/529, loss: 0.0007259639678522944
2023-01-24 09:29:48.009314: step: 1660/529, loss: 0.0008213031105697155
2023-01-24 09:29:49.106715: step: 1664/529, loss: 0.016987815499305725
2023-01-24 09:29:50.215157: step: 1668/529, loss: 0.02598005346953869
2023-01-24 09:29:51.323045: step: 1672/529, loss: 0.011696085333824158
2023-01-24 09:29:52.420534: step: 1676/529, loss: 0.007905970327556133
2023-01-24 09:29:53.548490: step: 1680/529, loss: 0.004529423546046019
2023-01-24 09:29:54.646638: step: 1684/529, loss: 0.003708254313096404
2023-01-24 09:29:55.757588: step: 1688/529, loss: 0.0033165302593261003
2023-01-24 09:29:56.885837: step: 1692/529, loss: 0.0038341544568538666
2023-01-24 09:29:58.029686: step: 1696/529, loss: 0.012603913433849812
2023-01-24 09:29:59.151380: step: 1700/529, loss: 0.0002838079526554793
2023-01-24 09:30:00.266020: step: 1704/529, loss: 0.0024313030298799276
2023-01-24 09:30:01.381624: step: 1708/529, loss: 0.0018001944990828633
2023-01-24 09:30:02.490430: step: 1712/529, loss: 0.013044815510511398
2023-01-24 09:30:03.594662: step: 1716/529, loss: 0.006613976322114468
2023-01-24 09:30:04.717732: step: 1720/529, loss: 0.0006235204637050629
2023-01-24 09:30:05.814814: step: 1724/529, loss: 0.004450184293091297
2023-01-24 09:30:06.931913: step: 1728/529, loss: 0.009699058718979359
2023-01-24 09:30:08.036994: step: 1732/529, loss: 0.015105639584362507
2023-01-24 09:30:09.130571: step: 1736/529, loss: 0.006358313374221325
2023-01-24 09:30:10.205902: step: 1740/529, loss: 0.010097693651914597
2023-01-24 09:30:11.323214: step: 1744/529, loss: 0.000390678527764976
2023-01-24 09:30:12.435745: step: 1748/529, loss: 0.0016387834912166
2023-01-24 09:30:13.544781: step: 1752/529, loss: 0.005541583988815546
2023-01-24 09:30:14.650858: step: 1756/529, loss: 0.0014011363964527845
2023-01-24 09:30:15.751217: step: 1760/529, loss: 0.0023862060625106096
2023-01-24 09:30:16.847101: step: 1764/529, loss: 0.012335315346717834
2023-01-24 09:30:17.961911: step: 1768/529, loss: 0.009803946129977703
2023-01-24 09:30:19.091676: step: 1772/529, loss: 0.0059935241006314754
2023-01-24 09:30:20.202139: step: 1776/529, loss: 0.0031732802744954824
2023-01-24 09:30:21.316163: step: 1780/529, loss: 0.0031303339637815952
2023-01-24 09:30:22.452460: step: 1784/529, loss: 0.013180905021727085
2023-01-24 09:30:23.563790: step: 1788/529, loss: 0.0035919812507927418
2023-01-24 09:30:24.670430: step: 1792/529, loss: 0.006066866219043732
2023-01-24 09:30:25.761171: step: 1796/529, loss: 0.0020214738324284554
2023-01-24 09:30:26.857102: step: 1800/529, loss: 0.004169781226664782
2023-01-24 09:30:27.968366: step: 1804/529, loss: 0.04999531805515289
2023-01-24 09:30:29.073195: step: 1808/529, loss: 0.0022171849850565195
2023-01-24 09:30:30.164654: step: 1812/529, loss: 7.562074461020529e-05
2023-01-24 09:30:31.266220: step: 1816/529, loss: 0.004359940066933632
2023-01-24 09:30:32.385774: step: 1820/529, loss: 0.0041817729361355305
2023-01-24 09:30:33.496639: step: 1824/529, loss: 0.0021923796739429235
2023-01-24 09:30:34.590287: step: 1828/529, loss: 0.0041497633792459965
2023-01-24 09:30:35.701246: step: 1832/529, loss: 0.0009777399245649576
2023-01-24 09:30:36.800157: step: 1836/529, loss: 0.0005270448164083064
2023-01-24 09:30:37.911983: step: 1840/529, loss: 0.009624544531106949
2023-01-24 09:30:39.030819: step: 1844/529, loss: 0.0005393408937379718
2023-01-24 09:30:40.158590: step: 1848/529, loss: 0.008533255197107792
2023-01-24 09:30:41.260154: step: 1852/529, loss: 0.0003352747007738799
2023-01-24 09:30:42.405264: step: 1856/529, loss: 0.0017396059120073915
2023-01-24 09:30:43.542161: step: 1860/529, loss: 0.054066430777311325
2023-01-24 09:30:44.655821: step: 1864/529, loss: 0.028022324666380882
2023-01-24 09:30:45.753018: step: 1868/529, loss: 0.004758719354867935
2023-01-24 09:30:46.875874: step: 1872/529, loss: 0.0066461097449064255
2023-01-24 09:30:47.993443: step: 1876/529, loss: 0.002942661289125681
2023-01-24 09:30:49.121280: step: 1880/529, loss: 0.0049504851922392845
2023-01-24 09:30:50.231852: step: 1884/529, loss: 0.0009159165783785284
2023-01-24 09:30:51.332929: step: 1888/529, loss: 0.010240484029054642
2023-01-24 09:30:52.443508: step: 1892/529, loss: 0.008234058506786823
2023-01-24 09:30:53.526852: step: 1896/529, loss: 0.004558432847261429
2023-01-24 09:30:54.634875: step: 1900/529, loss: 0.0018280777148902416
2023-01-24 09:30:55.752990: step: 1904/529, loss: 0.001706184702925384
2023-01-24 09:30:56.846551: step: 1908/529, loss: 0.0035248363856226206
2023-01-24 09:30:57.940418: step: 1912/529, loss: 0.0002554664679337293
2023-01-24 09:30:59.027174: step: 1916/529, loss: 0.001244658138602972
2023-01-24 09:31:00.135179: step: 1920/529, loss: 0.0012626301031559706
2023-01-24 09:31:01.261513: step: 1924/529, loss: 0.009176721796393394
2023-01-24 09:31:02.394818: step: 1928/529, loss: 0.0240730382502079
2023-01-24 09:31:03.513084: step: 1932/529, loss: 0.008625274524092674
2023-01-24 09:31:04.616644: step: 1936/529, loss: 0.008096283301711082
2023-01-24 09:31:05.725639: step: 1940/529, loss: 4.583534609992057e-05
2023-01-24 09:31:06.803312: step: 1944/529, loss: 0.008541249670088291
2023-01-24 09:31:07.890805: step: 1948/529, loss: 0.005415746942162514
2023-01-24 09:31:08.985136: step: 1952/529, loss: 0.002098322147503495
2023-01-24 09:31:10.082330: step: 1956/529, loss: 0.0053655002266168594
2023-01-24 09:31:11.192709: step: 1960/529, loss: 0.001825091545470059
2023-01-24 09:31:12.314581: step: 1964/529, loss: 0.004083148203790188
2023-01-24 09:31:13.434253: step: 1968/529, loss: 0.0052253492176532745
2023-01-24 09:31:14.537101: step: 1972/529, loss: 0.009055962786078453
2023-01-24 09:31:15.613944: step: 1976/529, loss: 1.0427392226119991e-05
2023-01-24 09:31:16.708382: step: 1980/529, loss: 0.010929914191365242
2023-01-24 09:31:17.782841: step: 1984/529, loss: 0.0027245418168604374
2023-01-24 09:31:18.882423: step: 1988/529, loss: 0.0027202703058719635
2023-01-24 09:31:19.985583: step: 1992/529, loss: 0.0028581772930920124
2023-01-24 09:31:21.094153: step: 1996/529, loss: 0.010418610647320747
2023-01-24 09:31:22.186358: step: 2000/529, loss: 0.001159005449153483
2023-01-24 09:31:23.303287: step: 2004/529, loss: 0.0027979742735624313
2023-01-24 09:31:24.442701: step: 2008/529, loss: 0.00393333425745368
2023-01-24 09:31:25.542766: step: 2012/529, loss: 0.007475843653082848
2023-01-24 09:31:26.628404: step: 2016/529, loss: 0.011700699105858803
2023-01-24 09:31:27.752137: step: 2020/529, loss: 0.002454961882904172
2023-01-24 09:31:28.849057: step: 2024/529, loss: 0.008408984169363976
2023-01-24 09:31:29.950042: step: 2028/529, loss: 0.03319612890481949
2023-01-24 09:31:31.030599: step: 2032/529, loss: 0.006548134610056877
2023-01-24 09:31:32.161242: step: 2036/529, loss: 0.018203601241111755
2023-01-24 09:31:33.255256: step: 2040/529, loss: 0.0025989694986492395
2023-01-24 09:31:34.347369: step: 2044/529, loss: 0.010249124839901924
2023-01-24 09:31:35.456592: step: 2048/529, loss: 0.0030631597619503736
2023-01-24 09:31:36.554673: step: 2052/529, loss: 0.004294148646295071
2023-01-24 09:31:37.659794: step: 2056/529, loss: 0.02513548918068409
2023-01-24 09:31:38.766151: step: 2060/529, loss: 0.0018500180449336767
2023-01-24 09:31:39.893216: step: 2064/529, loss: 0.0019697914831340313
2023-01-24 09:31:41.015074: step: 2068/529, loss: 0.011786270886659622
2023-01-24 09:31:42.113805: step: 2072/529, loss: 0.002880977699533105
2023-01-24 09:31:43.217291: step: 2076/529, loss: 0.0023447556886821985
2023-01-24 09:31:44.348768: step: 2080/529, loss: 0.010426324792206287
2023-01-24 09:31:45.469745: step: 2084/529, loss: 0.0038744681514799595
2023-01-24 09:31:46.569527: step: 2088/529, loss: 0.008821678347885609
2023-01-24 09:31:47.668247: step: 2092/529, loss: 0.0016580615192651749
2023-01-24 09:31:48.774958: step: 2096/529, loss: 0.005616358015686274
2023-01-24 09:31:49.883795: step: 2100/529, loss: 0.0034102166537195444
2023-01-24 09:31:50.988390: step: 2104/529, loss: 0.007788404822349548
2023-01-24 09:31:52.087593: step: 2108/529, loss: 0.0020257786381989717
2023-01-24 09:31:53.187070: step: 2112/529, loss: 0.006368610076606274
2023-01-24 09:31:54.299787: step: 2116/529, loss: 0.0063580297864973545
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3766960299744898, 'r': 0.3202273651396042, 'f1': 0.3461739926739926}, 'combined': 0.2550755735492577, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.398316590466585, 'r': 0.2868293645387627, 'f1': 0.33350235433524644}, 'combined': 0.20498193485971244, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3681459278187685, 'r': 0.3311217642999929, 'f1': 0.34865368588630624}, 'combined': 0.25690271591622565, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3815140953399116, 'r': 0.2915904957450624, 'f1': 0.33054561109017877}, 'combined': 0.20316461949932937, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4053811659192825, 'r': 0.3430740037950664, 'f1': 0.3716341212744091}, 'combined': 0.2738356683074593, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.40020020911769144, 'r': 0.2867985900696108, 'f1': 0.33413990200942034}, 'combined': 0.20638052771170085, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39473684210526316, 'r': 0.32608695652173914, 'f1': 0.35714285714285715}, 'combined': 0.17857142857142858, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:34:18.001324: step: 4/529, loss: 0.00844115111976862
2023-01-24 09:34:19.113483: step: 8/529, loss: 0.020979363471269608
2023-01-24 09:34:20.217561: step: 12/529, loss: 0.00579110998660326
2023-01-24 09:34:21.313935: step: 16/529, loss: 0.007949178107082844
2023-01-24 09:34:22.417023: step: 20/529, loss: 0.005044217221438885
2023-01-24 09:34:23.528155: step: 24/529, loss: 0.001715436577796936
2023-01-24 09:34:24.626892: step: 28/529, loss: 0.0029960733372718096
2023-01-24 09:34:25.729252: step: 32/529, loss: 0.004749746061861515
2023-01-24 09:34:26.843851: step: 36/529, loss: 0.001871377811767161
2023-01-24 09:34:27.959173: step: 40/529, loss: 0.006074720993638039
2023-01-24 09:34:29.061401: step: 44/529, loss: 0.0026944035198539495
2023-01-24 09:34:30.165564: step: 48/529, loss: 0.0011238680453971028
2023-01-24 09:34:31.241924: step: 52/529, loss: 0.0010088251437991858
2023-01-24 09:34:32.374168: step: 56/529, loss: 0.007105117663741112
2023-01-24 09:34:33.464611: step: 60/529, loss: 0.001084332587197423
2023-01-24 09:34:34.590940: step: 64/529, loss: 0.0013439208269119263
2023-01-24 09:34:35.711450: step: 68/529, loss: 0.0051331473514437675
2023-01-24 09:34:36.814063: step: 72/529, loss: 0.0011121021816506982
2023-01-24 09:34:37.925137: step: 76/529, loss: 0.0029541226103901863
2023-01-24 09:34:39.030387: step: 80/529, loss: 0.00561157101765275
2023-01-24 09:34:40.104244: step: 84/529, loss: 0.0002865288406610489
2023-01-24 09:34:41.184107: step: 88/529, loss: 0.010356693528592587
2023-01-24 09:34:42.270024: step: 92/529, loss: 0.00010010231198975816
2023-01-24 09:34:43.348405: step: 96/529, loss: 0.00020123893045820296
2023-01-24 09:34:44.426936: step: 100/529, loss: 0.0006299946107901633
2023-01-24 09:34:45.534519: step: 104/529, loss: 0.0013150712475180626
2023-01-24 09:34:46.632301: step: 108/529, loss: 0.0059531028382480145
2023-01-24 09:34:47.720073: step: 112/529, loss: 0.008020145818591118
2023-01-24 09:34:48.808025: step: 116/529, loss: 0.007236039265990257
2023-01-24 09:34:49.913462: step: 120/529, loss: 0.012774981558322906
2023-01-24 09:34:51.025113: step: 124/529, loss: 0.011293821968138218
2023-01-24 09:34:52.174183: step: 128/529, loss: 0.0026905222330242395
2023-01-24 09:34:53.274752: step: 132/529, loss: 0.0011036355281248689
2023-01-24 09:34:54.381305: step: 136/529, loss: 0.00019762357987929136
2023-01-24 09:34:55.483571: step: 140/529, loss: 0.01146754901856184
2023-01-24 09:34:56.590942: step: 144/529, loss: 0.005518396385014057
2023-01-24 09:34:57.703403: step: 148/529, loss: 0.0049437787383794785
2023-01-24 09:34:58.806348: step: 152/529, loss: 0.004379387479275465
2023-01-24 09:34:59.894674: step: 156/529, loss: 0.00446859747171402
2023-01-24 09:35:01.030312: step: 160/529, loss: 0.005369523540139198
2023-01-24 09:35:02.142123: step: 164/529, loss: 0.0011135268723592162
2023-01-24 09:35:03.254354: step: 168/529, loss: 0.003364636329934001
2023-01-24 09:35:04.363016: step: 172/529, loss: 0.0016140296356752515
2023-01-24 09:35:05.464681: step: 176/529, loss: 0.0006261312519200146
2023-01-24 09:35:06.577602: step: 180/529, loss: 0.0026179319247603416
2023-01-24 09:35:07.699918: step: 184/529, loss: 0.0022436040453612804
2023-01-24 09:35:08.822268: step: 188/529, loss: 0.0071028852835297585
2023-01-24 09:35:09.933371: step: 192/529, loss: 0.004583127796649933
2023-01-24 09:35:11.023779: step: 196/529, loss: 0.0014352560974657536
2023-01-24 09:35:12.123844: step: 200/529, loss: 0.003546495456248522
2023-01-24 09:35:13.218949: step: 204/529, loss: 0.0055420780554413795
2023-01-24 09:35:14.359349: step: 208/529, loss: 0.019877225160598755
2023-01-24 09:35:15.462142: step: 212/529, loss: 0.021463608369231224
2023-01-24 09:35:16.577010: step: 216/529, loss: 9.85792648862116e-05
2023-01-24 09:35:17.674099: step: 220/529, loss: 0.004329256247729063
2023-01-24 09:35:18.772481: step: 224/529, loss: 0.0010845923097804189
2023-01-24 09:35:19.872388: step: 228/529, loss: 0.0022307466715574265
2023-01-24 09:35:20.953304: step: 232/529, loss: 0.0007933827582746744
2023-01-24 09:35:22.046866: step: 236/529, loss: 0.005464385263621807
2023-01-24 09:35:23.147902: step: 240/529, loss: 4.0545080537413014e-07
2023-01-24 09:35:24.251949: step: 244/529, loss: 0.003553795162588358
2023-01-24 09:35:25.357886: step: 248/529, loss: 0.004247546195983887
2023-01-24 09:35:26.454364: step: 252/529, loss: 0.018267003819346428
2023-01-24 09:35:27.578264: step: 256/529, loss: 0.0031788437627255917
2023-01-24 09:35:28.690126: step: 260/529, loss: 0.01948254369199276
2023-01-24 09:35:29.822874: step: 264/529, loss: 0.004951623734086752
2023-01-24 09:35:30.915077: step: 268/529, loss: 0.0017793672159314156
2023-01-24 09:35:32.005817: step: 272/529, loss: 0.0019417222356423736
2023-01-24 09:35:33.122745: step: 276/529, loss: 1.5217972759273835e-05
2023-01-24 09:35:34.236248: step: 280/529, loss: 0.0020967256277799606
2023-01-24 09:35:35.343865: step: 284/529, loss: 0.003428031224757433
2023-01-24 09:35:36.451374: step: 288/529, loss: 0.001250486820936203
2023-01-24 09:35:37.532751: step: 292/529, loss: 0.006197906564921141
2023-01-24 09:35:38.631706: step: 296/529, loss: 0.007990062236785889
2023-01-24 09:35:39.746186: step: 300/529, loss: 0.008474033325910568
2023-01-24 09:35:40.854139: step: 304/529, loss: 0.014518667943775654
2023-01-24 09:35:41.977678: step: 308/529, loss: 0.00179564137943089
2023-01-24 09:35:43.101606: step: 312/529, loss: 0.004551586229354143
2023-01-24 09:35:44.200893: step: 316/529, loss: 0.022535188123583794
2023-01-24 09:35:45.297170: step: 320/529, loss: 0.022015513852238655
2023-01-24 09:35:46.404805: step: 324/529, loss: 0.014681173488497734
2023-01-24 09:35:47.526514: step: 328/529, loss: 0.0030733528546988964
2023-01-24 09:35:48.628428: step: 332/529, loss: 0.0018407984171062708
2023-01-24 09:35:49.724721: step: 336/529, loss: 0.01389398518949747
2023-01-24 09:35:50.824025: step: 340/529, loss: 0.0007159760571084917
2023-01-24 09:35:51.943760: step: 344/529, loss: 0.006780853029340506
2023-01-24 09:35:53.059719: step: 348/529, loss: 0.011438514105975628
2023-01-24 09:35:54.152626: step: 352/529, loss: 0.006648657843470573
2023-01-24 09:35:55.260553: step: 356/529, loss: 0.012801037169992924
2023-01-24 09:35:56.374173: step: 360/529, loss: 0.001693736296147108
2023-01-24 09:35:57.478911: step: 364/529, loss: 0.0030145260971039534
2023-01-24 09:35:58.609148: step: 368/529, loss: 0.005842269863933325
2023-01-24 09:35:59.703367: step: 372/529, loss: 0.0005585098406299949
2023-01-24 09:36:00.789875: step: 376/529, loss: 0.00034072474227286875
2023-01-24 09:36:01.916877: step: 380/529, loss: 0.0255210492759943
2023-01-24 09:36:03.027286: step: 384/529, loss: 0.00613732123747468
2023-01-24 09:36:04.133611: step: 388/529, loss: 0.007783234119415283
2023-01-24 09:36:05.238725: step: 392/529, loss: 0.004175110254436731
2023-01-24 09:36:06.326344: step: 396/529, loss: 0.004834686405956745
2023-01-24 09:36:07.444204: step: 400/529, loss: 0.007448016200214624
2023-01-24 09:36:08.563119: step: 404/529, loss: 0.00578970555216074
2023-01-24 09:36:09.648221: step: 408/529, loss: 0.0006020013242959976
2023-01-24 09:36:10.758244: step: 412/529, loss: 0.01662960648536682
2023-01-24 09:36:11.884598: step: 416/529, loss: 0.0017585533205419779
2023-01-24 09:36:12.989699: step: 420/529, loss: 0.0007989160949364305
2023-01-24 09:36:14.087358: step: 424/529, loss: 0.00858911219984293
2023-01-24 09:36:15.190702: step: 428/529, loss: 0.002652117982506752
2023-01-24 09:36:16.277347: step: 432/529, loss: 0.015698252245783806
2023-01-24 09:36:17.388463: step: 436/529, loss: 0.04495786130428314
2023-01-24 09:36:18.507318: step: 440/529, loss: 0.016684578731656075
2023-01-24 09:36:19.616265: step: 444/529, loss: 0.011736352927982807
2023-01-24 09:36:20.735631: step: 448/529, loss: 0.0004370490205474198
2023-01-24 09:36:21.822642: step: 452/529, loss: 0.00010130803275387734
2023-01-24 09:36:22.924350: step: 456/529, loss: 0.0010403740452602506
2023-01-24 09:36:24.036504: step: 460/529, loss: 0.01684565283358097
2023-01-24 09:36:25.144026: step: 464/529, loss: 0.00397358275949955
2023-01-24 09:36:26.238495: step: 468/529, loss: 0.006977117154747248
2023-01-24 09:36:27.356437: step: 472/529, loss: 0.00773286446928978
2023-01-24 09:36:28.449678: step: 476/529, loss: 0.004086590372025967
2023-01-24 09:36:29.560868: step: 480/529, loss: 0.0030200290493667126
2023-01-24 09:36:30.660672: step: 484/529, loss: 0.0013680586125701666
2023-01-24 09:36:31.753510: step: 488/529, loss: 0.002889792900532484
2023-01-24 09:36:32.902275: step: 492/529, loss: 0.015945566818118095
2023-01-24 09:36:33.996687: step: 496/529, loss: 0.0011217283317819238
2023-01-24 09:36:35.108938: step: 500/529, loss: 0.0055679152719676495
2023-01-24 09:36:36.214935: step: 504/529, loss: 0.008145378902554512
2023-01-24 09:36:37.322245: step: 508/529, loss: 0.005072348285466433
2023-01-24 09:36:38.442381: step: 512/529, loss: 0.002225040690973401
2023-01-24 09:36:39.541899: step: 516/529, loss: 0.009913398884236813
2023-01-24 09:36:40.640423: step: 520/529, loss: 0.0035862799268215895
2023-01-24 09:36:41.746455: step: 524/529, loss: 0.003490537405014038
2023-01-24 09:36:42.863642: step: 528/529, loss: 0.01014535129070282
2023-01-24 09:36:43.969192: step: 532/529, loss: 0.0011744301300495863
2023-01-24 09:36:45.073410: step: 536/529, loss: 0.0038102632388472557
2023-01-24 09:36:46.217084: step: 540/529, loss: 0.001190882408991456
2023-01-24 09:36:47.316602: step: 544/529, loss: 0.011781220324337482
2023-01-24 09:36:48.427872: step: 548/529, loss: 0.0049925874918699265
2023-01-24 09:36:49.510480: step: 552/529, loss: 0.0030839182436466217
2023-01-24 09:36:50.626839: step: 556/529, loss: 0.017217248678207397
2023-01-24 09:36:51.739575: step: 560/529, loss: 0.004445804748684168
2023-01-24 09:36:52.827306: step: 564/529, loss: 0.0009031649678945541
2023-01-24 09:36:53.964441: step: 568/529, loss: 0.0011117144022136927
2023-01-24 09:36:55.069935: step: 572/529, loss: 0.0021940015722066164
2023-01-24 09:36:56.186201: step: 576/529, loss: 0.003153864061459899
2023-01-24 09:36:57.301538: step: 580/529, loss: 0.0008436269126832485
2023-01-24 09:36:58.396922: step: 584/529, loss: 0.0033403721172362566
2023-01-24 09:36:59.497182: step: 588/529, loss: 0.004300093278288841
2023-01-24 09:37:00.609283: step: 592/529, loss: 0.00236880243755877
2023-01-24 09:37:01.718548: step: 596/529, loss: 0.017922911792993546
2023-01-24 09:37:02.832109: step: 600/529, loss: 0.0012190206907689571
2023-01-24 09:37:03.969735: step: 604/529, loss: 0.01166699081659317
2023-01-24 09:37:05.073999: step: 608/529, loss: 0.00715693598613143
2023-01-24 09:37:06.159690: step: 612/529, loss: 0.0020148113835603
2023-01-24 09:37:07.283533: step: 616/529, loss: 0.0009512178949080408
2023-01-24 09:37:08.380422: step: 620/529, loss: 0.001246428582817316
2023-01-24 09:37:09.513057: step: 624/529, loss: 0.004320949781686068
2023-01-24 09:37:10.595364: step: 628/529, loss: 0.0007918922347016633
2023-01-24 09:37:11.686219: step: 632/529, loss: 0.0016534344758838415
2023-01-24 09:37:12.772886: step: 636/529, loss: 0.0003141536726616323
2023-01-24 09:37:13.869229: step: 640/529, loss: 0.007538760546594858
2023-01-24 09:37:14.989918: step: 644/529, loss: 0.01648290455341339
2023-01-24 09:37:16.076894: step: 648/529, loss: 0.005710061173886061
2023-01-24 09:37:17.193016: step: 652/529, loss: 0.009857021272182465
2023-01-24 09:37:18.323142: step: 656/529, loss: 0.004674674943089485
2023-01-24 09:37:19.431285: step: 660/529, loss: 0.0016565866535529494
2023-01-24 09:37:20.534471: step: 664/529, loss: 0.004142623394727707
2023-01-24 09:37:21.620039: step: 668/529, loss: 0.021623900160193443
2023-01-24 09:37:22.723293: step: 672/529, loss: 0.0017556409584358335
2023-01-24 09:37:23.836534: step: 676/529, loss: 0.00033482073922641575
2023-01-24 09:37:24.933761: step: 680/529, loss: 0.0009201587527059019
2023-01-24 09:37:26.043514: step: 684/529, loss: 0.006340256426483393
2023-01-24 09:37:27.138518: step: 688/529, loss: 0.010735297575592995
2023-01-24 09:37:28.225900: step: 692/529, loss: 0.004740302916616201
2023-01-24 09:37:29.331661: step: 696/529, loss: 0.0018195533193647861
2023-01-24 09:37:30.440262: step: 700/529, loss: 0.0013502421788871288
2023-01-24 09:37:31.543379: step: 704/529, loss: 0.0009792293421924114
2023-01-24 09:37:32.641380: step: 708/529, loss: 0.00033946821349672973
2023-01-24 09:37:33.734326: step: 712/529, loss: 0.0025781760923564434
2023-01-24 09:37:34.844151: step: 716/529, loss: 0.006270202342420816
2023-01-24 09:37:35.923747: step: 720/529, loss: 9.889738521451363e-07
2023-01-24 09:37:37.029315: step: 724/529, loss: 0.005066626239567995
2023-01-24 09:37:38.127450: step: 728/529, loss: 0.0008674657437950373
2023-01-24 09:37:39.203635: step: 732/529, loss: 0.0007751052035018802
2023-01-24 09:37:40.321351: step: 736/529, loss: 0.004346473608165979
2023-01-24 09:37:41.438849: step: 740/529, loss: 0.0033800092060118914
2023-01-24 09:37:42.543136: step: 744/529, loss: 0.0029286060016602278
2023-01-24 09:37:43.649026: step: 748/529, loss: 0.00028459422173909843
2023-01-24 09:37:44.787176: step: 752/529, loss: 0.0024262836668640375
2023-01-24 09:37:45.905482: step: 756/529, loss: 0.0011191107332706451
2023-01-24 09:37:47.033761: step: 760/529, loss: 0.0012898595305159688
2023-01-24 09:37:48.161664: step: 764/529, loss: 0.0026762045454233885
2023-01-24 09:37:49.253386: step: 768/529, loss: 0.00328453560359776
2023-01-24 09:37:50.384672: step: 772/529, loss: 0.003801693907007575
2023-01-24 09:37:51.503391: step: 776/529, loss: 0.0012236833572387695
2023-01-24 09:37:52.638012: step: 780/529, loss: 0.006623003166168928
2023-01-24 09:37:53.768782: step: 784/529, loss: 0.003294985042884946
2023-01-24 09:37:54.873476: step: 788/529, loss: 0.025937139987945557
2023-01-24 09:37:55.967092: step: 792/529, loss: 0.0009773930069059134
2023-01-24 09:37:57.087080: step: 796/529, loss: 0.014964092522859573
2023-01-24 09:37:58.170635: step: 800/529, loss: 0.0012083734618499875
2023-01-24 09:37:59.291365: step: 804/529, loss: 0.0053486586548388
2023-01-24 09:38:00.395204: step: 808/529, loss: 0.01712695322930813
2023-01-24 09:38:01.481014: step: 812/529, loss: 0.0002649268717505038
2023-01-24 09:38:02.611037: step: 816/529, loss: 0.0020419349893927574
2023-01-24 09:38:03.728061: step: 820/529, loss: 0.0011201896704733372
2023-01-24 09:38:04.846626: step: 824/529, loss: 0.007399091497063637
2023-01-24 09:38:05.965919: step: 828/529, loss: 9.503376350039616e-05
2023-01-24 09:38:07.080696: step: 832/529, loss: 0.004010332748293877
2023-01-24 09:38:08.187100: step: 836/529, loss: 0.0012934714322909713
2023-01-24 09:38:09.295773: step: 840/529, loss: 0.003757230006158352
2023-01-24 09:38:10.399411: step: 844/529, loss: 0.017119761556386948
2023-01-24 09:38:11.532014: step: 848/529, loss: 0.004221073351800442
2023-01-24 09:38:12.658433: step: 852/529, loss: 0.00029825398814864457
2023-01-24 09:38:13.771907: step: 856/529, loss: 0.005733921192586422
2023-01-24 09:38:14.875381: step: 860/529, loss: 0.0035247572232037783
2023-01-24 09:38:15.956834: step: 864/529, loss: 0.006842564791440964
2023-01-24 09:38:17.041934: step: 868/529, loss: 3.855265731544932e-06
2023-01-24 09:38:18.136803: step: 872/529, loss: 0.001217746757902205
2023-01-24 09:38:19.220212: step: 876/529, loss: 0.005069629289209843
2023-01-24 09:38:20.319282: step: 880/529, loss: 0.0025810536462813616
2023-01-24 09:38:21.429867: step: 884/529, loss: 0.002445860533043742
2023-01-24 09:38:22.546981: step: 888/529, loss: 0.0017040508100762963
2023-01-24 09:38:23.660044: step: 892/529, loss: 0.006463023833930492
2023-01-24 09:38:24.781419: step: 896/529, loss: 0.0019293962977826595
2023-01-24 09:38:25.899916: step: 900/529, loss: 0.0011861694511026144
2023-01-24 09:38:26.995248: step: 904/529, loss: 0.03439740836620331
2023-01-24 09:38:28.095471: step: 908/529, loss: 0.0009568601381033659
2023-01-24 09:38:29.183321: step: 912/529, loss: 0.0023391391150653362
2023-01-24 09:38:30.294977: step: 916/529, loss: 0.0003876067348755896
2023-01-24 09:38:31.378048: step: 920/529, loss: 0.0018878539558500051
2023-01-24 09:38:32.493851: step: 924/529, loss: 0.003929265309125185
2023-01-24 09:38:33.601565: step: 928/529, loss: 0.002547285985201597
2023-01-24 09:38:34.698554: step: 932/529, loss: 0.05676935240626335
2023-01-24 09:38:35.799964: step: 936/529, loss: 0.0014037369983270764
2023-01-24 09:38:36.911306: step: 940/529, loss: 0.005906595382839441
2023-01-24 09:38:38.038793: step: 944/529, loss: 0.0024180065374821424
2023-01-24 09:38:39.162041: step: 948/529, loss: 0.004414003808051348
2023-01-24 09:38:40.269461: step: 952/529, loss: 0.002302455250173807
2023-01-24 09:38:41.385214: step: 956/529, loss: 0.00012025266914861277
2023-01-24 09:38:42.480993: step: 960/529, loss: 0.008000114932656288
2023-01-24 09:38:43.583905: step: 964/529, loss: 0.010300581343472004
2023-01-24 09:38:44.687177: step: 968/529, loss: 0.005171730183064938
2023-01-24 09:38:45.781841: step: 972/529, loss: 0.002349207177758217
2023-01-24 09:38:46.905147: step: 976/529, loss: 0.002971658017486334
2023-01-24 09:38:48.018696: step: 980/529, loss: 0.00809214822947979
2023-01-24 09:38:49.121392: step: 984/529, loss: 0.0005921954289078712
2023-01-24 09:38:50.207939: step: 988/529, loss: 0.0026468555442988873
2023-01-24 09:38:51.303964: step: 992/529, loss: 0.0002647619985509664
2023-01-24 09:38:52.413530: step: 996/529, loss: 0.005888370331376791
2023-01-24 09:38:53.525502: step: 1000/529, loss: 0.003267069347202778
2023-01-24 09:38:54.621063: step: 1004/529, loss: 7.504592940676957e-05
2023-01-24 09:38:55.755323: step: 1008/529, loss: 0.003062062431126833
2023-01-24 09:38:56.838341: step: 1012/529, loss: 0.0007736250408925116
2023-01-24 09:38:57.939288: step: 1016/529, loss: 0.00655006617307663
2023-01-24 09:38:59.054328: step: 1020/529, loss: 0.01732056960463524
2023-01-24 09:39:00.166227: step: 1024/529, loss: 0.0008451450848951936
2023-01-24 09:39:01.281819: step: 1028/529, loss: 0.0019260543631389737
2023-01-24 09:39:02.383763: step: 1032/529, loss: 0.005653090309351683
2023-01-24 09:39:03.491799: step: 1036/529, loss: 0.005015730392187834
2023-01-24 09:39:04.596637: step: 1040/529, loss: 0.006838577333837748
2023-01-24 09:39:05.696928: step: 1044/529, loss: 0.033377669751644135
2023-01-24 09:39:06.793515: step: 1048/529, loss: 0.0008285798830911517
2023-01-24 09:39:07.894670: step: 1052/529, loss: 0.0040962472558021545
2023-01-24 09:39:09.019209: step: 1056/529, loss: 0.007803542539477348
2023-01-24 09:39:10.116020: step: 1060/529, loss: 0.0013499382184818387
2023-01-24 09:39:11.221485: step: 1064/529, loss: 0.0019406476058065891
2023-01-24 09:39:12.311953: step: 1068/529, loss: 8.576701657148078e-05
2023-01-24 09:39:13.436108: step: 1072/529, loss: 0.004887906368821859
2023-01-24 09:39:14.557550: step: 1076/529, loss: 0.0021051515359431505
2023-01-24 09:39:15.669708: step: 1080/529, loss: 0.004105157684534788
2023-01-24 09:39:16.776362: step: 1084/529, loss: 0.0007092682644724846
2023-01-24 09:39:17.894749: step: 1088/529, loss: 0.005515716038644314
2023-01-24 09:39:19.000810: step: 1092/529, loss: 0.007160830311477184
2023-01-24 09:39:20.087297: step: 1096/529, loss: 0.00030613827402703464
2023-01-24 09:39:21.210470: step: 1100/529, loss: 0.005239086225628853
2023-01-24 09:39:22.314274: step: 1104/529, loss: 0.0023801024071872234
2023-01-24 09:39:23.436969: step: 1108/529, loss: 0.0058539560995996
2023-01-24 09:39:24.532136: step: 1112/529, loss: 0.0009661816875450313
2023-01-24 09:39:25.628689: step: 1116/529, loss: 0.00082486926112324
2023-01-24 09:39:26.721841: step: 1120/529, loss: 0.004162740893661976
2023-01-24 09:39:27.832472: step: 1124/529, loss: 0.0026770695112645626
2023-01-24 09:39:28.930133: step: 1128/529, loss: 0.0032701033633202314
2023-01-24 09:39:30.021996: step: 1132/529, loss: 0.016873609274625778
2023-01-24 09:39:31.143983: step: 1136/529, loss: 0.006976199336349964
2023-01-24 09:39:32.232008: step: 1140/529, loss: 0.008767476305365562
2023-01-24 09:39:33.340091: step: 1144/529, loss: 0.012852507643401623
2023-01-24 09:39:34.468930: step: 1148/529, loss: 0.0007530332659371197
2023-01-24 09:39:35.560485: step: 1152/529, loss: 0.0006995071889832616
2023-01-24 09:39:36.657798: step: 1156/529, loss: 0.007044769357889891
2023-01-24 09:39:37.764028: step: 1160/529, loss: 0.016497166827321053
2023-01-24 09:39:38.864176: step: 1164/529, loss: 0.00271224114112556
2023-01-24 09:39:39.974090: step: 1168/529, loss: 7.165854913182557e-05
2023-01-24 09:39:41.064848: step: 1172/529, loss: 0.0035616715904325247
2023-01-24 09:39:42.181252: step: 1176/529, loss: 0.0023160730488598347
2023-01-24 09:39:43.289604: step: 1180/529, loss: 0.020186278969049454
2023-01-24 09:39:44.406005: step: 1184/529, loss: 0.0025611594319343567
2023-01-24 09:39:45.528504: step: 1188/529, loss: 0.003797759534791112
2023-01-24 09:39:46.641122: step: 1192/529, loss: 0.005366635043174028
2023-01-24 09:39:47.737824: step: 1196/529, loss: 0.006503208074718714
2023-01-24 09:39:48.813101: step: 1200/529, loss: 0.0046144467778503895
2023-01-24 09:39:49.913600: step: 1204/529, loss: 0.0030831072945147753
2023-01-24 09:39:51.043741: step: 1208/529, loss: 0.017920056357979774
2023-01-24 09:39:52.147063: step: 1212/529, loss: 0.002440088428556919
2023-01-24 09:39:53.243628: step: 1216/529, loss: 0.006227685138583183
2023-01-24 09:39:54.345636: step: 1220/529, loss: 0.0028466784860938787
2023-01-24 09:39:55.440780: step: 1224/529, loss: 0.0053274682722985744
2023-01-24 09:39:56.529755: step: 1228/529, loss: 0.0010565445991232991
2023-01-24 09:39:57.629887: step: 1232/529, loss: 0.0015335481148213148
2023-01-24 09:39:58.763140: step: 1236/529, loss: 0.003924991469830275
2023-01-24 09:39:59.861434: step: 1240/529, loss: 0.0004750562075059861
2023-01-24 09:40:00.979406: step: 1244/529, loss: 0.0010517614427953959
2023-01-24 09:40:02.102675: step: 1248/529, loss: 0.0046148705296218395
2023-01-24 09:40:03.215568: step: 1252/529, loss: 0.0003543717903085053
2023-01-24 09:40:04.338336: step: 1256/529, loss: 0.0010193290654569864
2023-01-24 09:40:05.451759: step: 1260/529, loss: 0.012018855661153793
2023-01-24 09:40:06.565888: step: 1264/529, loss: 0.006649521645158529
2023-01-24 09:40:07.681881: step: 1268/529, loss: 5.692885315511376e-05
2023-01-24 09:40:08.786981: step: 1272/529, loss: 0.011772981844842434
2023-01-24 09:40:09.896248: step: 1276/529, loss: 0.009156133979558945
2023-01-24 09:40:10.978659: step: 1280/529, loss: 0.0020698204170912504
2023-01-24 09:40:12.066460: step: 1284/529, loss: 0.004424553830176592
2023-01-24 09:40:13.156547: step: 1288/529, loss: 0.00022289076878223568
2023-01-24 09:40:14.253906: step: 1292/529, loss: 0.007505868095904589
2023-01-24 09:40:15.342422: step: 1296/529, loss: 0.0029971294570714235
2023-01-24 09:40:16.454814: step: 1300/529, loss: 0.00896605383604765
2023-01-24 09:40:17.553909: step: 1304/529, loss: 0.0015668014530092478
2023-01-24 09:40:18.657086: step: 1308/529, loss: 0.0005669065285474062
2023-01-24 09:40:19.772644: step: 1312/529, loss: 0.026423176750540733
2023-01-24 09:40:20.872245: step: 1316/529, loss: 0.004049985203891993
2023-01-24 09:40:22.003880: step: 1320/529, loss: 0.004315638914704323
2023-01-24 09:40:23.127349: step: 1324/529, loss: 0.0035286752972751856
2023-01-24 09:40:24.239039: step: 1328/529, loss: 0.002237678272649646
2023-01-24 09:40:25.379675: step: 1332/529, loss: 0.0014509214088320732
2023-01-24 09:40:26.494891: step: 1336/529, loss: 0.003688718192279339
2023-01-24 09:40:27.593020: step: 1340/529, loss: 0.0017588643822818995
2023-01-24 09:40:28.696903: step: 1344/529, loss: 0.003400132292881608
2023-01-24 09:40:29.808261: step: 1348/529, loss: 0.004457415081560612
2023-01-24 09:40:30.925062: step: 1352/529, loss: 0.0012696267804130912
2023-01-24 09:40:32.036002: step: 1356/529, loss: 0.003029454266652465
2023-01-24 09:40:33.139052: step: 1360/529, loss: 0.005543313920497894
2023-01-24 09:40:34.228851: step: 1364/529, loss: 0.003372120438143611
2023-01-24 09:40:35.366204: step: 1368/529, loss: 0.03488500043749809
2023-01-24 09:40:36.456977: step: 1372/529, loss: 0.0015060494188219309
2023-01-24 09:40:37.576190: step: 1376/529, loss: 0.012768702581524849
2023-01-24 09:40:38.715268: step: 1380/529, loss: 0.0013559150975197554
2023-01-24 09:40:39.834154: step: 1384/529, loss: 0.012266425415873528
2023-01-24 09:40:40.934428: step: 1388/529, loss: 0.01115561556071043
2023-01-24 09:40:42.068260: step: 1392/529, loss: 0.002833722857758403
2023-01-24 09:40:43.216379: step: 1396/529, loss: 0.0012369280448183417
2023-01-24 09:40:44.334928: step: 1400/529, loss: 0.026487652212381363
2023-01-24 09:40:45.433416: step: 1404/529, loss: 0.0036454596556723118
2023-01-24 09:40:46.538123: step: 1408/529, loss: 0.006267383694648743
2023-01-24 09:40:47.660101: step: 1412/529, loss: 0.015909546986222267
2023-01-24 09:40:48.783505: step: 1416/529, loss: 0.011788478121161461
2023-01-24 09:40:49.879825: step: 1420/529, loss: 0.004515159875154495
2023-01-24 09:40:51.000929: step: 1424/529, loss: 0.011597182601690292
2023-01-24 09:40:52.111068: step: 1428/529, loss: 0.0002957967226393521
2023-01-24 09:40:53.223810: step: 1432/529, loss: 0.005916237831115723
2023-01-24 09:40:54.320685: step: 1436/529, loss: 0.002234724350273609
2023-01-24 09:40:55.434426: step: 1440/529, loss: 0.0019734741654247046
2023-01-24 09:40:56.526780: step: 1444/529, loss: 0.00026089372113347054
2023-01-24 09:40:57.622037: step: 1448/529, loss: 0.0071403454057872295
2023-01-24 09:40:58.741121: step: 1452/529, loss: 0.012803579680621624
2023-01-24 09:40:59.871427: step: 1456/529, loss: 0.007361842319369316
2023-01-24 09:41:00.949320: step: 1460/529, loss: 0.0003282254037912935
2023-01-24 09:41:02.038270: step: 1464/529, loss: 0.003516164608299732
2023-01-24 09:41:03.138541: step: 1468/529, loss: 0.0006904699257574975
2023-01-24 09:41:04.249549: step: 1472/529, loss: 0.006863766815513372
2023-01-24 09:41:05.347175: step: 1476/529, loss: 0.003444032510742545
2023-01-24 09:41:06.442299: step: 1480/529, loss: 0.0020606897305697203
2023-01-24 09:41:07.567957: step: 1484/529, loss: 0.006396012380719185
2023-01-24 09:41:08.684371: step: 1488/529, loss: 0.0004291832447052002
2023-01-24 09:41:09.785711: step: 1492/529, loss: 7.820609607733786e-05
2023-01-24 09:41:10.905172: step: 1496/529, loss: 0.0030667679384350777
2023-01-24 09:41:12.008256: step: 1500/529, loss: 0.000850684242323041
2023-01-24 09:41:13.146297: step: 1504/529, loss: 0.004149554762989283
2023-01-24 09:41:14.264018: step: 1508/529, loss: 0.0022297692485153675
2023-01-24 09:41:15.340927: step: 1512/529, loss: 0.0004538490029517561
2023-01-24 09:41:16.462636: step: 1516/529, loss: 0.006826519500464201
2023-01-24 09:41:17.546721: step: 1520/529, loss: 0.00019551030709408224
2023-01-24 09:41:18.655843: step: 1524/529, loss: 0.014934631064534187
2023-01-24 09:41:19.818464: step: 1528/529, loss: 0.014110477641224861
2023-01-24 09:41:20.914039: step: 1532/529, loss: 0.01045110635459423
2023-01-24 09:41:22.008861: step: 1536/529, loss: 0.0066744061186909676
2023-01-24 09:41:23.111019: step: 1540/529, loss: 0.0019012573175132275
2023-01-24 09:41:24.217580: step: 1544/529, loss: 0.003337307134643197
2023-01-24 09:41:25.338294: step: 1548/529, loss: 0.005773071199655533
2023-01-24 09:41:26.424721: step: 1552/529, loss: 0.0022756510879844427
2023-01-24 09:41:27.541544: step: 1556/529, loss: 0.012884018011391163
2023-01-24 09:41:28.652835: step: 1560/529, loss: 0.0054016620852053165
2023-01-24 09:41:29.754834: step: 1564/529, loss: 0.0017216844717040658
2023-01-24 09:41:30.858882: step: 1568/529, loss: 0.013849829323589802
2023-01-24 09:41:31.954354: step: 1572/529, loss: 0.007813731208443642
2023-01-24 09:41:33.064559: step: 1576/529, loss: 0.007207179442048073
2023-01-24 09:41:34.172518: step: 1580/529, loss: 0.004785093944519758
2023-01-24 09:41:35.244436: step: 1584/529, loss: 0.003768039168789983
2023-01-24 09:41:36.342661: step: 1588/529, loss: 0.004621509928256273
2023-01-24 09:41:37.455634: step: 1592/529, loss: 0.014007627964019775
2023-01-24 09:41:38.573412: step: 1596/529, loss: 0.009194851852953434
2023-01-24 09:41:39.687087: step: 1600/529, loss: 0.005072671454399824
2023-01-24 09:41:40.781569: step: 1604/529, loss: 0.00021289379219524562
2023-01-24 09:41:41.910025: step: 1608/529, loss: 0.0031537243630737066
2023-01-24 09:41:43.020799: step: 1612/529, loss: 0.019190721213817596
2023-01-24 09:41:44.125539: step: 1616/529, loss: 0.005900430027395487
2023-01-24 09:41:45.210241: step: 1620/529, loss: 0.007275173906236887
2023-01-24 09:41:46.310429: step: 1624/529, loss: 0.002585094887763262
2023-01-24 09:41:47.426733: step: 1628/529, loss: 0.0019110547145828605
2023-01-24 09:41:48.510917: step: 1632/529, loss: 5.253553536022082e-05
2023-01-24 09:41:49.618166: step: 1636/529, loss: 0.012486271560192108
2023-01-24 09:41:50.731775: step: 1640/529, loss: 0.003716852981597185
2023-01-24 09:41:51.872733: step: 1644/529, loss: 0.004231891594827175
2023-01-24 09:41:52.975670: step: 1648/529, loss: 0.003106782678514719
2023-01-24 09:41:54.068007: step: 1652/529, loss: 0.006548008881509304
2023-01-24 09:41:55.182850: step: 1656/529, loss: 0.007671670988202095
2023-01-24 09:41:56.306960: step: 1660/529, loss: 0.002767820144072175
2023-01-24 09:41:57.415353: step: 1664/529, loss: 0.0008777441107667983
2023-01-24 09:41:58.513593: step: 1668/529, loss: 0.001488186651840806
2023-01-24 09:41:59.614870: step: 1672/529, loss: 0.0011112248757854104
2023-01-24 09:42:00.741930: step: 1676/529, loss: 0.0005050413310527802
2023-01-24 09:42:01.884634: step: 1680/529, loss: 0.0009451690712012351
2023-01-24 09:42:02.982114: step: 1684/529, loss: 0.002810921985656023
2023-01-24 09:42:04.119326: step: 1688/529, loss: 0.001579177100211382
2023-01-24 09:42:05.219894: step: 1692/529, loss: 0.0155815863981843
2023-01-24 09:42:06.324479: step: 1696/529, loss: 0.0025179111398756504
2023-01-24 09:42:07.434062: step: 1700/529, loss: 0.0021014863159507513
2023-01-24 09:42:08.543590: step: 1704/529, loss: 0.0048246257938444614
2023-01-24 09:42:09.638551: step: 1708/529, loss: 0.017451664432883263
2023-01-24 09:42:10.748008: step: 1712/529, loss: 0.006588782649487257
2023-01-24 09:42:11.847161: step: 1716/529, loss: 1.5870620700297877e-05
2023-01-24 09:42:12.936576: step: 1720/529, loss: 0.005207560490816832
2023-01-24 09:42:14.045465: step: 1724/529, loss: 0.0010843047639355063
2023-01-24 09:42:15.146133: step: 1728/529, loss: 0.008674499578773975
2023-01-24 09:42:16.254949: step: 1732/529, loss: 0.0004631158953998238
2023-01-24 09:42:17.341697: step: 1736/529, loss: 0.01776072382926941
2023-01-24 09:42:18.435042: step: 1740/529, loss: 0.0024243418592959642
2023-01-24 09:42:19.568659: step: 1744/529, loss: 0.0016719745472073555
2023-01-24 09:42:20.675708: step: 1748/529, loss: 0.003435152815654874
2023-01-24 09:42:21.790313: step: 1752/529, loss: 0.005865814164280891
2023-01-24 09:42:22.906171: step: 1756/529, loss: 0.00036233774153515697
2023-01-24 09:42:24.024716: step: 1760/529, loss: 0.004737775307148695
2023-01-24 09:42:25.111901: step: 1764/529, loss: 0.005815178155899048
2023-01-24 09:42:26.244976: step: 1768/529, loss: 0.0004244623414706439
2023-01-24 09:42:27.346205: step: 1772/529, loss: 0.01204951573163271
2023-01-24 09:42:28.428270: step: 1776/529, loss: 0.004508337937295437
2023-01-24 09:42:29.517149: step: 1780/529, loss: 0.0009568501263856888
2023-01-24 09:42:30.627993: step: 1784/529, loss: 0.003377004526555538
2023-01-24 09:42:31.722662: step: 1788/529, loss: 0.048388440161943436
2023-01-24 09:42:32.845539: step: 1792/529, loss: 0.001426311326213181
2023-01-24 09:42:33.959723: step: 1796/529, loss: 0.008733781054615974
2023-01-24 09:42:35.052885: step: 1800/529, loss: 0.008310790173709393
2023-01-24 09:42:36.193116: step: 1804/529, loss: 0.004265836905688047
2023-01-24 09:42:37.293520: step: 1808/529, loss: 0.0001271079236175865
2023-01-24 09:42:38.415397: step: 1812/529, loss: 0.008557415567338467
2023-01-24 09:42:39.539602: step: 1816/529, loss: 0.003814536612480879
2023-01-24 09:42:40.623683: step: 1820/529, loss: 0.005167282652109861
2023-01-24 09:42:41.716847: step: 1824/529, loss: 0.004549714736640453
2023-01-24 09:42:42.840837: step: 1828/529, loss: 0.01032494567334652
2023-01-24 09:42:43.952961: step: 1832/529, loss: 0.0038686967454850674
2023-01-24 09:42:45.071053: step: 1836/529, loss: 0.0011009577428922057
2023-01-24 09:42:46.191350: step: 1840/529, loss: 0.0038741272874176502
2023-01-24 09:42:47.319000: step: 1844/529, loss: 0.0007635563379153609
2023-01-24 09:42:48.458397: step: 1848/529, loss: 0.012273360043764114
2023-01-24 09:42:49.554050: step: 1852/529, loss: 0.007692363578826189
2023-01-24 09:42:50.668582: step: 1856/529, loss: 0.00312973209656775
2023-01-24 09:42:51.787223: step: 1860/529, loss: 0.011812441051006317
2023-01-24 09:42:52.888101: step: 1864/529, loss: 0.003971350844949484
2023-01-24 09:42:53.980597: step: 1868/529, loss: 0.005851636175066233
2023-01-24 09:42:55.094253: step: 1872/529, loss: 0.004560678731650114
2023-01-24 09:42:56.189640: step: 1876/529, loss: 0.0021861877758055925
2023-01-24 09:42:57.296514: step: 1880/529, loss: 0.003824198618531227
2023-01-24 09:42:58.413383: step: 1884/529, loss: 0.004318365827202797
2023-01-24 09:42:59.521307: step: 1888/529, loss: 0.005066792480647564
2023-01-24 09:43:00.605905: step: 1892/529, loss: 0.0064278095960617065
2023-01-24 09:43:01.704817: step: 1896/529, loss: 0.006338384468108416
2023-01-24 09:43:02.846851: step: 1900/529, loss: 0.002471103798598051
2023-01-24 09:43:03.965620: step: 1904/529, loss: 0.005269594024866819
2023-01-24 09:43:05.061285: step: 1908/529, loss: 0.013808159157633781
2023-01-24 09:43:06.152995: step: 1912/529, loss: 0.028862416744232178
2023-01-24 09:43:07.249286: step: 1916/529, loss: 0.0035963926929980516
2023-01-24 09:43:08.341179: step: 1920/529, loss: 0.0001030353523674421
2023-01-24 09:43:09.462344: step: 1924/529, loss: 0.004442925099283457
2023-01-24 09:43:10.576855: step: 1928/529, loss: 0.0013091267319396138
2023-01-24 09:43:11.697939: step: 1932/529, loss: 0.0042597330175340176
2023-01-24 09:43:12.800063: step: 1936/529, loss: 0.0005841926904395223
2023-01-24 09:43:13.935067: step: 1940/529, loss: 0.002184335608035326
2023-01-24 09:43:15.029260: step: 1944/529, loss: 0.005775731522589922
2023-01-24 09:43:16.128080: step: 1948/529, loss: 0.0041688294149935246
2023-01-24 09:43:17.218552: step: 1952/529, loss: 0.0010458033066242933
2023-01-24 09:43:18.319067: step: 1956/529, loss: 0.021324271336197853
2023-01-24 09:43:19.428873: step: 1960/529, loss: 0.002240370027720928
2023-01-24 09:43:20.538046: step: 1964/529, loss: 0.0037174688186496496
2023-01-24 09:43:21.622064: step: 1968/529, loss: 0.0014703454216942191
2023-01-24 09:43:22.743546: step: 1972/529, loss: 0.012709921225905418
2023-01-24 09:43:23.825209: step: 1976/529, loss: 0.0007731486111879349
2023-01-24 09:43:24.923921: step: 1980/529, loss: 0.0006906954804435372
2023-01-24 09:43:26.027690: step: 1984/529, loss: 0.009930431842803955
2023-01-24 09:43:27.110146: step: 1988/529, loss: 8.848836296238005e-05
2023-01-24 09:43:28.222056: step: 1992/529, loss: 0.0059011559933424
2023-01-24 09:43:29.311176: step: 1996/529, loss: 0.0005378047353588045
2023-01-24 09:43:30.412829: step: 2000/529, loss: 0.01136679295450449
2023-01-24 09:43:31.509650: step: 2004/529, loss: 0.01261558011174202
2023-01-24 09:43:32.613363: step: 2008/529, loss: 0.00015609461115673184
2023-01-24 09:43:33.749514: step: 2012/529, loss: 0.003131320932880044
2023-01-24 09:43:34.823323: step: 2016/529, loss: 0.0002025125577347353
2023-01-24 09:43:35.929040: step: 2020/529, loss: 0.010645151138305664
2023-01-24 09:43:37.061366: step: 2024/529, loss: 0.002788886893540621
2023-01-24 09:43:38.191634: step: 2028/529, loss: 0.0005681856418959796
2023-01-24 09:43:39.299745: step: 2032/529, loss: 0.05632838234305382
2023-01-24 09:43:40.387475: step: 2036/529, loss: 0.0030708699487149715
2023-01-24 09:43:41.470789: step: 2040/529, loss: 0.002978625474497676
2023-01-24 09:43:42.570010: step: 2044/529, loss: 0.003536547301337123
2023-01-24 09:43:43.668431: step: 2048/529, loss: 0.004249243531376123
2023-01-24 09:43:44.776218: step: 2052/529, loss: 0.0016448420938104391
2023-01-24 09:43:45.866381: step: 2056/529, loss: 0.0033577769063413143
2023-01-24 09:43:46.983206: step: 2060/529, loss: 0.0013673026114702225
2023-01-24 09:43:48.086239: step: 2064/529, loss: 0.0045458669774234295
2023-01-24 09:43:49.190281: step: 2068/529, loss: 0.0006131752743385732
2023-01-24 09:43:50.312167: step: 2072/529, loss: 0.0015062569873407483
2023-01-24 09:43:51.409734: step: 2076/529, loss: 0.004423859063535929
2023-01-24 09:43:52.529459: step: 2080/529, loss: 0.0061938087455928326
2023-01-24 09:43:53.650366: step: 2084/529, loss: 0.0015077540883794427
2023-01-24 09:43:54.734775: step: 2088/529, loss: 0.00013401305477600545
2023-01-24 09:43:55.846580: step: 2092/529, loss: 0.0015274615725502372
2023-01-24 09:43:56.933132: step: 2096/529, loss: 0.00226380187086761
2023-01-24 09:43:58.028146: step: 2100/529, loss: 0.0007622981793247163
2023-01-24 09:43:59.132468: step: 2104/529, loss: 0.003061251249164343
2023-01-24 09:44:00.216120: step: 2108/529, loss: 0.0015172269195318222
2023-01-24 09:44:01.306364: step: 2112/529, loss: 0.001013267901726067
2023-01-24 09:44:02.432056: step: 2116/529, loss: 0.001493466435931623
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38292833280305444, 'r': 0.3262520330712931, 'f1': 0.35232545374707264}, 'combined': 0.2596082290767904, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.39857388823208545, 'r': 0.2863238763816281, 'f1': 0.33325038158789594}, 'combined': 0.20482706380524335, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37160382016828303, 'r': 0.3328216377977791, 'f1': 0.35114515139024943}, 'combined': 0.2587385326033417, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3832522005578611, 'r': 0.2915904957450624, 'f1': 0.3311962914269705}, 'combined': 0.20356454985267455, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40727069351230427, 'r': 0.3454459203036053, 'f1': 0.3738193018480493}, 'combined': 0.27544580136172053, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3976033489617522, 'r': 0.285282125598207, 'f1': 0.3322054217359544}, 'combined': 0.20518570166044248, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713773650302507, 'r': 0.33614232090973356, 'f1': 0.3528824763335251}, 'combined': 0.2600186667720711, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38298565307055027, 'r': 0.29072394461854595, 'f1': 0.3305373715170463}, 'combined': 0.2031595551763309, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 12
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:46:24.235702: step: 4/529, loss: 0.0027762765530496836
2023-01-24 09:46:25.328207: step: 8/529, loss: 0.0010462049394845963
2023-01-24 09:46:26.434511: step: 12/529, loss: 0.003816004376858473
2023-01-24 09:46:27.542668: step: 16/529, loss: 0.0034619285725057125
2023-01-24 09:46:28.624880: step: 20/529, loss: 0.0012335400097072124
2023-01-24 09:46:29.719321: step: 24/529, loss: 0.0009715323685668409
2023-01-24 09:46:30.824338: step: 28/529, loss: 8.888173033483326e-05
2023-01-24 09:46:31.927927: step: 32/529, loss: 9.12934137886623e-06
2023-01-24 09:46:33.021746: step: 36/529, loss: 0.0010657234815880656
2023-01-24 09:46:34.129028: step: 40/529, loss: 0.004928060807287693
2023-01-24 09:46:35.221191: step: 44/529, loss: 1.7358754121232778e-05
2023-01-24 09:46:36.320738: step: 48/529, loss: 0.005204554181545973
2023-01-24 09:46:37.422845: step: 52/529, loss: 0.005520981270819902
2023-01-24 09:46:38.525313: step: 56/529, loss: 0.009502717293798923
2023-01-24 09:46:39.632886: step: 60/529, loss: 0.003339269896969199
2023-01-24 09:46:40.723445: step: 64/529, loss: 0.012243479490280151
2023-01-24 09:46:41.822972: step: 68/529, loss: 0.000890921161044389
2023-01-24 09:46:42.921525: step: 72/529, loss: 5.428383701655548e-06
2023-01-24 09:46:44.013213: step: 76/529, loss: 0.006472372449934483
2023-01-24 09:46:45.118947: step: 80/529, loss: 0.00230636028572917
2023-01-24 09:46:46.220811: step: 84/529, loss: 0.0037265836726874113
2023-01-24 09:46:47.313482: step: 88/529, loss: 0.00020787192624993622
2023-01-24 09:46:48.403741: step: 92/529, loss: 0.0018673932645469904
2023-01-24 09:46:49.514698: step: 96/529, loss: 0.0038730923552066088
2023-01-24 09:46:50.632090: step: 100/529, loss: 0.016526632010936737
2023-01-24 09:46:51.766591: step: 104/529, loss: 0.0035179378464818
2023-01-24 09:46:52.883770: step: 108/529, loss: 0.0024837448727339506
2023-01-24 09:46:53.997449: step: 112/529, loss: 0.011297304183244705
2023-01-24 09:46:55.115710: step: 116/529, loss: 0.002900385297834873
2023-01-24 09:46:56.227527: step: 120/529, loss: 0.0032932006288319826
2023-01-24 09:46:57.305061: step: 124/529, loss: 0.00015768481534905732
2023-01-24 09:46:58.397086: step: 128/529, loss: 0.005349403712898493
2023-01-24 09:46:59.499412: step: 132/529, loss: 0.0018632753053680062
2023-01-24 09:47:00.625895: step: 136/529, loss: 0.014207469299435616
2023-01-24 09:47:01.725304: step: 140/529, loss: 0.0030285371467471123
2023-01-24 09:47:02.850735: step: 144/529, loss: 0.000701298238709569
2023-01-24 09:47:03.953219: step: 148/529, loss: 0.01561272144317627
2023-01-24 09:47:05.078668: step: 152/529, loss: 0.0022973588202148676
2023-01-24 09:47:06.168264: step: 156/529, loss: 0.0008811238221824169
2023-01-24 09:47:07.262740: step: 160/529, loss: 0.0033532651141285896
2023-01-24 09:47:08.368235: step: 164/529, loss: 0.011777253821492195
2023-01-24 09:47:09.464131: step: 168/529, loss: 4.221989868824494e-08
2023-01-24 09:47:10.557262: step: 172/529, loss: 0.0024700488429516554
2023-01-24 09:47:11.648888: step: 176/529, loss: 0.014778150245547295
2023-01-24 09:47:12.747218: step: 180/529, loss: 0.0006405175081454217
2023-01-24 09:47:13.835282: step: 184/529, loss: 0.0039296685717999935
2023-01-24 09:47:14.929350: step: 188/529, loss: 0.006972936913371086
2023-01-24 09:47:16.029108: step: 192/529, loss: 0.0008915242506191134
2023-01-24 09:47:17.131084: step: 196/529, loss: 0.0054492829367518425
2023-01-24 09:47:18.244430: step: 200/529, loss: 5.854661139892414e-05
2023-01-24 09:47:19.341767: step: 204/529, loss: 0.00039613962871953845
2023-01-24 09:47:20.431631: step: 208/529, loss: 0.004649805836379528
2023-01-24 09:47:21.535188: step: 212/529, loss: 0.0004632494237739593
2023-01-24 09:47:22.623166: step: 216/529, loss: 3.7326213941923925e-07
2023-01-24 09:47:23.745023: step: 220/529, loss: 0.001702315523289144
2023-01-24 09:47:24.841349: step: 224/529, loss: 0.0007884991355240345
2023-01-24 09:47:25.930164: step: 228/529, loss: 0.008432826958596706
2023-01-24 09:47:27.019103: step: 232/529, loss: 0.0029229691717773676
2023-01-24 09:47:28.117280: step: 236/529, loss: 0.00044485388207249343
2023-01-24 09:47:29.226180: step: 240/529, loss: 0.0033600148744881153
2023-01-24 09:47:30.345061: step: 244/529, loss: 8.977828110801056e-05
2023-01-24 09:47:31.437122: step: 248/529, loss: 0.00847327895462513
2023-01-24 09:47:32.551835: step: 252/529, loss: 0.0049040899612009525
2023-01-24 09:47:33.656118: step: 256/529, loss: 0.008703096769750118
2023-01-24 09:47:34.756202: step: 260/529, loss: 0.006281276699155569
2023-01-24 09:47:35.862699: step: 264/529, loss: 0.0020060474053025246
2023-01-24 09:47:36.994300: step: 268/529, loss: 0.005718177184462547
2023-01-24 09:47:38.092481: step: 272/529, loss: 0.004087462089955807
2023-01-24 09:47:39.198132: step: 276/529, loss: 0.0018782959086820483
2023-01-24 09:47:40.303465: step: 280/529, loss: 0.004205251578241587
2023-01-24 09:47:41.418418: step: 284/529, loss: 0.007965457625687122
2023-01-24 09:47:42.526489: step: 288/529, loss: 0.005605509039014578
2023-01-24 09:47:43.635771: step: 292/529, loss: 0.006963943596929312
2023-01-24 09:47:44.718542: step: 296/529, loss: 0.0009007885819301009
2023-01-24 09:47:45.825351: step: 300/529, loss: 0.0017291028052568436
2023-01-24 09:47:46.932883: step: 304/529, loss: 0.006150687579065561
2023-01-24 09:47:48.025084: step: 308/529, loss: 0.00046188855776563287
2023-01-24 09:47:49.107114: step: 312/529, loss: 0.002029713010415435
2023-01-24 09:47:50.206762: step: 316/529, loss: 0.0005733241559937596
2023-01-24 09:47:51.306806: step: 320/529, loss: 0.0016295771347358823
2023-01-24 09:47:52.432132: step: 324/529, loss: 0.0064054992981255054
2023-01-24 09:47:53.551140: step: 328/529, loss: 0.006284876260906458
2023-01-24 09:47:54.663854: step: 332/529, loss: 0.0009272422175854445
2023-01-24 09:47:55.771630: step: 336/529, loss: 0.002939266385510564
2023-01-24 09:47:56.864301: step: 340/529, loss: 0.002147701568901539
2023-01-24 09:47:57.974447: step: 344/529, loss: 0.00019012653501704335
2023-01-24 09:47:59.066100: step: 348/529, loss: 0.006655167322605848
2023-01-24 09:48:00.163048: step: 352/529, loss: 0.0004504171956796199
2023-01-24 09:48:01.311482: step: 356/529, loss: 0.007450321689248085
2023-01-24 09:48:02.427810: step: 360/529, loss: 0.06278450042009354
2023-01-24 09:48:03.518501: step: 364/529, loss: 9.735236380947754e-05
2023-01-24 09:48:04.632393: step: 368/529, loss: 0.0072176530957221985
2023-01-24 09:48:05.719808: step: 372/529, loss: 0.010108393616974354
2023-01-24 09:48:06.835444: step: 376/529, loss: 0.0003134808212053031
2023-01-24 09:48:07.933718: step: 380/529, loss: 0.0006017570267431438
2023-01-24 09:48:09.044125: step: 384/529, loss: 0.006629629526287317
2023-01-24 09:48:10.143638: step: 388/529, loss: 0.0012141151819378138
2023-01-24 09:48:11.245009: step: 392/529, loss: 0.006044619716703892
2023-01-24 09:48:12.347197: step: 396/529, loss: 0.0016516806790605187
2023-01-24 09:48:13.465607: step: 400/529, loss: 0.01478307880461216
2023-01-24 09:48:14.551425: step: 404/529, loss: 0.0020569320768117905
2023-01-24 09:48:15.679568: step: 408/529, loss: 0.023637816309928894
2023-01-24 09:48:16.778447: step: 412/529, loss: 0.012432195246219635
2023-01-24 09:48:17.875269: step: 416/529, loss: 0.008101772516965866
2023-01-24 09:48:18.967088: step: 420/529, loss: 0.0018454748205840588
2023-01-24 09:48:20.062201: step: 424/529, loss: 0.0051687536761164665
2023-01-24 09:48:21.167565: step: 428/529, loss: 0.0154078658670187
2023-01-24 09:48:22.269155: step: 432/529, loss: 0.003809664398431778
2023-01-24 09:48:23.352669: step: 436/529, loss: 0.0017395021859556437
2023-01-24 09:48:24.455298: step: 440/529, loss: 0.004277052357792854
2023-01-24 09:48:25.595591: step: 444/529, loss: 0.005925856996327639
2023-01-24 09:48:26.709022: step: 448/529, loss: 0.0009125491487793624
2023-01-24 09:48:27.821554: step: 452/529, loss: 0.002475291956216097
2023-01-24 09:48:28.916457: step: 456/529, loss: 0.002568066818639636
2023-01-24 09:48:30.001465: step: 460/529, loss: 0.010470638051629066
2023-01-24 09:48:31.090830: step: 464/529, loss: 1.4093047866481356e-05
2023-01-24 09:48:32.202919: step: 468/529, loss: 3.222980740247294e-05
2023-01-24 09:48:33.327470: step: 472/529, loss: 0.003734169527888298
2023-01-24 09:48:34.434342: step: 476/529, loss: 0.0018193547148257494
2023-01-24 09:48:35.537397: step: 480/529, loss: 0.014440534636378288
2023-01-24 09:48:36.634998: step: 484/529, loss: 0.001823248341679573
2023-01-24 09:48:37.731507: step: 488/529, loss: 0.004446464125066996
2023-01-24 09:48:38.821630: step: 492/529, loss: 0.0001428972027497366
2023-01-24 09:48:39.933553: step: 496/529, loss: 0.0004731105000246316
2023-01-24 09:48:41.045686: step: 500/529, loss: 0.005937726236879826
2023-01-24 09:48:42.152416: step: 504/529, loss: 0.006876176223158836
2023-01-24 09:48:43.241326: step: 508/529, loss: 0.006428639404475689
2023-01-24 09:48:44.342667: step: 512/529, loss: 0.00403979467228055
2023-01-24 09:48:45.449981: step: 516/529, loss: 0.001402258756570518
2023-01-24 09:48:46.550624: step: 520/529, loss: 0.007169619202613831
2023-01-24 09:48:47.641897: step: 524/529, loss: 0.0021410060580819845
2023-01-24 09:48:48.770457: step: 528/529, loss: 0.010816287249326706
2023-01-24 09:48:49.859061: step: 532/529, loss: 0.005744959227740765
2023-01-24 09:48:50.949339: step: 536/529, loss: 0.006379859521985054
2023-01-24 09:48:52.055363: step: 540/529, loss: 0.000716628332156688
2023-01-24 09:48:53.164749: step: 544/529, loss: 0.008350600488483906
2023-01-24 09:48:54.273774: step: 548/529, loss: 0.0005022928235121071
2023-01-24 09:48:55.395840: step: 552/529, loss: 0.006073886062949896
2023-01-24 09:48:56.487046: step: 556/529, loss: 1.9644396161311306e-05
2023-01-24 09:48:57.593701: step: 560/529, loss: 0.0033455078955739737
2023-01-24 09:48:58.687895: step: 564/529, loss: 0.0031072634737938643
2023-01-24 09:48:59.780603: step: 568/529, loss: 0.0002251608675578609
2023-01-24 09:49:00.874292: step: 572/529, loss: 0.000593160220887512
2023-01-24 09:49:01.970707: step: 576/529, loss: 0.000989574589766562
2023-01-24 09:49:03.083337: step: 580/529, loss: 0.010913743637502193
2023-01-24 09:49:04.173432: step: 584/529, loss: 0.0010446750093251467
2023-01-24 09:49:05.271797: step: 588/529, loss: 0.0008054329082369804
2023-01-24 09:49:06.378486: step: 592/529, loss: 0.005038390401750803
2023-01-24 09:49:07.463430: step: 596/529, loss: 0.0031528063118457794
2023-01-24 09:49:08.561698: step: 600/529, loss: 0.0009920148877426982
2023-01-24 09:49:09.670230: step: 604/529, loss: 0.0004315426049288362
2023-01-24 09:49:10.765996: step: 608/529, loss: 0.0019793694373220205
2023-01-24 09:49:11.866288: step: 612/529, loss: 0.004922003485262394
2023-01-24 09:49:12.978858: step: 616/529, loss: 0.005950198974460363
2023-01-24 09:49:14.073705: step: 620/529, loss: 0.0022428338415920734
2023-01-24 09:49:15.175862: step: 624/529, loss: 0.0020557651296257973
2023-01-24 09:49:16.274163: step: 628/529, loss: 0.0024385626893490553
2023-01-24 09:49:17.379041: step: 632/529, loss: 0.004152493551373482
2023-01-24 09:49:18.481285: step: 636/529, loss: 0.011170807294547558
2023-01-24 09:49:19.575546: step: 640/529, loss: 1.6699037587386556e-05
2023-01-24 09:49:20.679127: step: 644/529, loss: 0.00025188561994582415
2023-01-24 09:49:21.779708: step: 648/529, loss: 0.00864182785153389
2023-01-24 09:49:22.894613: step: 652/529, loss: 0.005259454715996981
2023-01-24 09:49:24.007409: step: 656/529, loss: 0.008205665275454521
2023-01-24 09:49:25.079988: step: 660/529, loss: 0.004176001064479351
2023-01-24 09:49:26.180380: step: 664/529, loss: 0.0049326494336128235
2023-01-24 09:49:27.281179: step: 668/529, loss: 0.0002073399955406785
2023-01-24 09:49:28.391918: step: 672/529, loss: 0.00042785776895470917
2023-01-24 09:49:29.483541: step: 676/529, loss: 0.0007630366017110646
2023-01-24 09:49:30.583721: step: 680/529, loss: 0.0040321857668459415
2023-01-24 09:49:31.684530: step: 684/529, loss: 0.008868553675711155
2023-01-24 09:49:32.752056: step: 688/529, loss: 0.006499852053821087
2023-01-24 09:49:33.860971: step: 692/529, loss: 0.0064085922203958035
2023-01-24 09:49:34.953370: step: 696/529, loss: 0.0006844301242381334
2023-01-24 09:49:36.069013: step: 700/529, loss: 0.005194731056690216
2023-01-24 09:49:37.187200: step: 704/529, loss: 0.0031888349913060665
2023-01-24 09:49:38.293609: step: 708/529, loss: 0.0038050925359129906
2023-01-24 09:49:39.407831: step: 712/529, loss: 0.004980681464076042
2023-01-24 09:49:40.489227: step: 716/529, loss: 0.0008619455038569868
2023-01-24 09:49:41.597276: step: 720/529, loss: 0.009143445640802383
2023-01-24 09:49:42.740737: step: 724/529, loss: 0.002914109267294407
2023-01-24 09:49:43.848448: step: 728/529, loss: 0.01674947515130043
2023-01-24 09:49:44.944386: step: 732/529, loss: 0.0027589236851781607
2023-01-24 09:49:46.064451: step: 736/529, loss: 0.00457782344892621
2023-01-24 09:49:47.175000: step: 740/529, loss: 0.0031165701802819967
2023-01-24 09:49:48.249891: step: 744/529, loss: 1.4442201972997282e-05
2023-01-24 09:49:49.351066: step: 748/529, loss: 0.025098251178860664
2023-01-24 09:49:50.471224: step: 752/529, loss: 0.0007629389874637127
2023-01-24 09:49:51.586358: step: 756/529, loss: 0.005204486660659313
2023-01-24 09:49:52.682829: step: 760/529, loss: 0.006737139075994492
2023-01-24 09:49:53.779161: step: 764/529, loss: 0.005380614660680294
2023-01-24 09:49:54.882647: step: 768/529, loss: 0.0002633388212416321
2023-01-24 09:49:55.998341: step: 772/529, loss: 0.0009019324206747115
2023-01-24 09:49:57.105150: step: 776/529, loss: 0.002258089603856206
2023-01-24 09:49:58.187163: step: 780/529, loss: 0.0011565203312784433
2023-01-24 09:49:59.291396: step: 784/529, loss: 0.0732300654053688
2023-01-24 09:50:00.406634: step: 788/529, loss: 0.003253780771046877
2023-01-24 09:50:01.487962: step: 792/529, loss: 0.002508033998310566
2023-01-24 09:50:02.644570: step: 796/529, loss: 0.004601568914949894
2023-01-24 09:50:03.746910: step: 800/529, loss: 0.0003843796730507165
2023-01-24 09:50:04.819771: step: 804/529, loss: 0.0008514925139024854
2023-01-24 09:50:05.913876: step: 808/529, loss: 0.002466159872710705
2023-01-24 09:50:07.023756: step: 812/529, loss: 0.004014667589217424
2023-01-24 09:50:08.119861: step: 816/529, loss: 0.005253095179796219
2023-01-24 09:50:09.236093: step: 820/529, loss: 0.023806003853678703
2023-01-24 09:50:10.353896: step: 824/529, loss: 0.0177925955504179
2023-01-24 09:50:11.468790: step: 828/529, loss: 0.006049338728189468
2023-01-24 09:50:12.570497: step: 832/529, loss: 7.290684879990295e-05
2023-01-24 09:50:13.661484: step: 836/529, loss: 0.0028248184826225042
2023-01-24 09:50:14.763013: step: 840/529, loss: 0.001416673301719129
2023-01-24 09:50:15.878250: step: 844/529, loss: 0.003167527262121439
2023-01-24 09:50:16.991795: step: 848/529, loss: 0.002980906283482909
2023-01-24 09:50:18.097312: step: 852/529, loss: 0.000622231513261795
2023-01-24 09:50:19.203104: step: 856/529, loss: 6.845410098321736e-05
2023-01-24 09:50:20.300612: step: 860/529, loss: 0.00825956929475069
2023-01-24 09:50:21.415908: step: 864/529, loss: 0.01506503950804472
2023-01-24 09:50:22.547387: step: 868/529, loss: 0.0025807705242186785
2023-01-24 09:50:23.640024: step: 872/529, loss: 0.003535150783136487
2023-01-24 09:50:24.740954: step: 876/529, loss: 0.000918049190659076
2023-01-24 09:50:25.831244: step: 880/529, loss: 0.0010378474835306406
2023-01-24 09:50:26.939718: step: 884/529, loss: 0.005866731982678175
2023-01-24 09:50:28.074039: step: 888/529, loss: 0.005037650465965271
2023-01-24 09:50:29.166884: step: 892/529, loss: 0.0061570582911372185
2023-01-24 09:50:30.295491: step: 896/529, loss: 0.0037480811588466167
2023-01-24 09:50:31.375066: step: 900/529, loss: 0.012541557662189007
2023-01-24 09:50:32.475255: step: 904/529, loss: 0.004607129376381636
2023-01-24 09:50:33.599134: step: 908/529, loss: 0.0018726926064118743
2023-01-24 09:50:34.688959: step: 912/529, loss: 0.02313421294093132
2023-01-24 09:50:35.804771: step: 916/529, loss: 0.0042212773114442825
2023-01-24 09:50:36.915252: step: 920/529, loss: 1.41079981403891e-05
2023-01-24 09:50:38.013557: step: 924/529, loss: 4.5843273710488575e-07
2023-01-24 09:50:39.142234: step: 928/529, loss: 0.0012715106131508946
2023-01-24 09:50:40.227586: step: 932/529, loss: 0.0013334781397134066
2023-01-24 09:50:41.346261: step: 936/529, loss: 0.008069056086242199
2023-01-24 09:50:42.441194: step: 940/529, loss: 0.00025343330344185233
2023-01-24 09:50:43.540445: step: 944/529, loss: 0.0007796770660206676
2023-01-24 09:50:44.626664: step: 948/529, loss: 0.0068210759200155735
2023-01-24 09:50:45.733693: step: 952/529, loss: 0.027938488870859146
2023-01-24 09:50:46.851016: step: 956/529, loss: 0.012449776753783226
2023-01-24 09:50:47.958400: step: 960/529, loss: 0.007851033471524715
2023-01-24 09:50:49.061056: step: 964/529, loss: 0.017245260998606682
2023-01-24 09:50:50.172760: step: 968/529, loss: 0.01738094352185726
2023-01-24 09:50:51.290646: step: 972/529, loss: 0.008785337209701538
2023-01-24 09:50:52.405934: step: 976/529, loss: 0.003211799543350935
2023-01-24 09:50:53.495858: step: 980/529, loss: 0.01256631314754486
2023-01-24 09:50:54.588630: step: 984/529, loss: 7.312333764275536e-05
2023-01-24 09:50:55.688381: step: 988/529, loss: 0.0003245885600335896
2023-01-24 09:50:56.819000: step: 992/529, loss: 0.011345455422997475
2023-01-24 09:50:57.911680: step: 996/529, loss: 0.003959354944527149
2023-01-24 09:50:59.027894: step: 1000/529, loss: 0.009822244755923748
2023-01-24 09:51:00.152080: step: 1004/529, loss: 0.005414898507297039
2023-01-24 09:51:01.253175: step: 1008/529, loss: 0.007246408145874739
2023-01-24 09:51:02.352580: step: 1012/529, loss: 0.00025633323821239173
2023-01-24 09:51:03.456064: step: 1016/529, loss: 0.012919302098453045
2023-01-24 09:51:04.534040: step: 1020/529, loss: 0.002659374149516225
2023-01-24 09:51:05.647748: step: 1024/529, loss: 0.003732177196070552
2023-01-24 09:51:06.750447: step: 1028/529, loss: 0.0009060488664545119
2023-01-24 09:51:07.848323: step: 1032/529, loss: 0.008955580182373524
2023-01-24 09:51:08.934717: step: 1036/529, loss: 0.005297385156154633
2023-01-24 09:51:10.033902: step: 1040/529, loss: 0.0021100337617099285
2023-01-24 09:51:11.141242: step: 1044/529, loss: 0.0015339320525527
2023-01-24 09:51:12.227437: step: 1048/529, loss: 0.0031962525099515915
2023-01-24 09:51:13.327628: step: 1052/529, loss: 0.00037727487506344914
2023-01-24 09:51:14.452743: step: 1056/529, loss: 0.0032557810191065073
2023-01-24 09:51:15.586086: step: 1060/529, loss: 0.0031550107523798943
2023-01-24 09:51:16.671630: step: 1064/529, loss: 0.004502748139202595
2023-01-24 09:51:17.756614: step: 1068/529, loss: 0.0024195455480366945
2023-01-24 09:51:18.881394: step: 1072/529, loss: 0.004258297849446535
2023-01-24 09:51:19.992647: step: 1076/529, loss: 0.00346053927205503
2023-01-24 09:51:21.157351: step: 1080/529, loss: 0.004028636496514082
2023-01-24 09:51:22.261201: step: 1084/529, loss: 0.0013401623582467437
2023-01-24 09:51:23.370331: step: 1088/529, loss: 0.00923909805715084
2023-01-24 09:51:24.478231: step: 1092/529, loss: 0.0016524532111361623
2023-01-24 09:51:25.605538: step: 1096/529, loss: 0.0036014998331665993
2023-01-24 09:51:26.701995: step: 1100/529, loss: 0.006009596865624189
2023-01-24 09:51:27.781524: step: 1104/529, loss: 0.0002660062746144831
2023-01-24 09:51:28.887417: step: 1108/529, loss: 0.01304792333394289
2023-01-24 09:51:29.996460: step: 1112/529, loss: 0.0018842763965949416
2023-01-24 09:51:31.081534: step: 1116/529, loss: 0.014432252384722233
2023-01-24 09:51:32.186820: step: 1120/529, loss: 0.00583024974912405
2023-01-24 09:51:33.316878: step: 1124/529, loss: 0.00019042934582103044
2023-01-24 09:51:34.412242: step: 1128/529, loss: 0.00012445123866200447
2023-01-24 09:51:35.508541: step: 1132/529, loss: 0.009986771270632744
2023-01-24 09:51:36.608596: step: 1136/529, loss: 0.0010908894473686814
2023-01-24 09:51:37.712425: step: 1140/529, loss: 0.0015294832410290837
2023-01-24 09:51:38.822815: step: 1144/529, loss: 0.008392107672989368
2023-01-24 09:51:39.909336: step: 1148/529, loss: 0.0020511711481958628
2023-01-24 09:51:41.007109: step: 1152/529, loss: 0.00610328046604991
2023-01-24 09:51:42.118080: step: 1156/529, loss: 0.0035546545404940844
2023-01-24 09:51:43.228142: step: 1160/529, loss: 0.03642532601952553
2023-01-24 09:51:44.319782: step: 1164/529, loss: 0.0006725058192387223
2023-01-24 09:51:45.414137: step: 1168/529, loss: 0.0018742317333817482
2023-01-24 09:51:46.527665: step: 1172/529, loss: 0.0066394745372235775
2023-01-24 09:51:47.637419: step: 1176/529, loss: 0.007165821734815836
2023-01-24 09:51:48.734288: step: 1180/529, loss: 0.0013178761582821608
2023-01-24 09:51:49.827084: step: 1184/529, loss: 0.0007705226307734847
2023-01-24 09:51:50.928806: step: 1188/529, loss: 2.0272864276194014e-06
2023-01-24 09:51:52.077900: step: 1192/529, loss: 0.002795303473249078
2023-01-24 09:51:53.176847: step: 1196/529, loss: 0.013296723365783691
2023-01-24 09:51:54.267959: step: 1200/529, loss: 8.158142736647278e-05
2023-01-24 09:51:55.364162: step: 1204/529, loss: 0.0009482708992436528
2023-01-24 09:51:56.455615: step: 1208/529, loss: 0.0023630447685718536
2023-01-24 09:51:57.558676: step: 1212/529, loss: 0.0009397470275871456
2023-01-24 09:51:58.683278: step: 1216/529, loss: 0.03506022319197655
2023-01-24 09:51:59.810343: step: 1220/529, loss: 0.0057658851146698
2023-01-24 09:52:00.928445: step: 1224/529, loss: 0.007470401469618082
2023-01-24 09:52:02.030606: step: 1228/529, loss: 0.004173722583800554
2023-01-24 09:52:03.145311: step: 1232/529, loss: 0.06375173479318619
2023-01-24 09:52:04.242027: step: 1236/529, loss: 0.0022007934749126434
2023-01-24 09:52:05.340563: step: 1240/529, loss: 0.001349522382952273
2023-01-24 09:52:06.455817: step: 1244/529, loss: 0.0019629907328635454
2023-01-24 09:52:07.559189: step: 1248/529, loss: 0.002263437258079648
2023-01-24 09:52:08.650812: step: 1252/529, loss: 0.013698682188987732
2023-01-24 09:52:09.766919: step: 1256/529, loss: 0.0009694842738099396
2023-01-24 09:52:10.880332: step: 1260/529, loss: 0.001156351063400507
2023-01-24 09:52:11.978051: step: 1264/529, loss: 0.004087864421308041
2023-01-24 09:52:13.087622: step: 1268/529, loss: 9.240079816663638e-05
2023-01-24 09:52:14.195034: step: 1272/529, loss: 0.0028486757073551416
2023-01-24 09:52:15.278533: step: 1276/529, loss: 0.0068897828459739685
2023-01-24 09:52:16.411930: step: 1280/529, loss: 0.006369309965521097
2023-01-24 09:52:17.499926: step: 1284/529, loss: 0.0010332973906770349
2023-01-24 09:52:18.633076: step: 1288/529, loss: 0.0038308745715767145
2023-01-24 09:52:19.746537: step: 1292/529, loss: 0.005273086950182915
2023-01-24 09:52:20.854361: step: 1296/529, loss: 0.013699567876756191
2023-01-24 09:52:21.951839: step: 1300/529, loss: 0.002056204015389085
2023-01-24 09:52:23.045815: step: 1304/529, loss: 0.006813964806497097
2023-01-24 09:52:24.159445: step: 1308/529, loss: 0.003750395029783249
2023-01-24 09:52:25.261033: step: 1312/529, loss: 0.00574092660099268
2023-01-24 09:52:26.375827: step: 1316/529, loss: 3.545842628227547e-05
2023-01-24 09:52:27.475404: step: 1320/529, loss: 0.008565038442611694
2023-01-24 09:52:28.570926: step: 1324/529, loss: 0.004500707145780325
2023-01-24 09:52:29.675079: step: 1328/529, loss: 0.0008234553970396519
2023-01-24 09:52:30.797739: step: 1332/529, loss: 0.008897936902940273
2023-01-24 09:52:31.935539: step: 1336/529, loss: 0.0039969575591385365
2023-01-24 09:52:33.037652: step: 1340/529, loss: 3.910925079253502e-05
2023-01-24 09:52:34.156231: step: 1344/529, loss: 0.0026806683745235205
2023-01-24 09:52:35.257043: step: 1348/529, loss: 0.003770589828491211
2023-01-24 09:52:36.356872: step: 1352/529, loss: 0.0036758952774107456
2023-01-24 09:52:37.480450: step: 1356/529, loss: 0.006809667218476534
2023-01-24 09:52:38.597383: step: 1360/529, loss: 0.0037387895863503218
2023-01-24 09:52:39.714464: step: 1364/529, loss: 4.5424258132698014e-05
2023-01-24 09:52:40.819706: step: 1368/529, loss: 0.006170026026666164
2023-01-24 09:52:41.927799: step: 1372/529, loss: 0.005843598861247301
2023-01-24 09:52:43.032306: step: 1376/529, loss: 0.006097909528762102
2023-01-24 09:52:44.140173: step: 1380/529, loss: 0.00045167311327531934
2023-01-24 09:52:45.249277: step: 1384/529, loss: 0.0012006715405732393
2023-01-24 09:52:46.350259: step: 1388/529, loss: 0.001215904951095581
2023-01-24 09:52:47.452564: step: 1392/529, loss: 0.00017230652156285942
2023-01-24 09:52:48.541572: step: 1396/529, loss: 3.0342256650328636e-05
2023-01-24 09:52:49.656343: step: 1400/529, loss: 0.002087270375341177
2023-01-24 09:52:50.766056: step: 1404/529, loss: 0.0006398286786861718
2023-01-24 09:52:51.892741: step: 1408/529, loss: 0.004571040626615286
2023-01-24 09:52:53.005494: step: 1412/529, loss: 0.0037977604661136866
2023-01-24 09:52:54.094386: step: 1416/529, loss: 0.0
2023-01-24 09:52:55.192219: step: 1420/529, loss: 0.006175719201564789
2023-01-24 09:52:56.327828: step: 1424/529, loss: 0.00027760930242948234
2023-01-24 09:52:57.456476: step: 1428/529, loss: 0.003787989029660821
2023-01-24 09:52:58.562397: step: 1432/529, loss: 0.0024578107986599207
2023-01-24 09:52:59.671237: step: 1436/529, loss: 0.0030939143616706133
2023-01-24 09:53:00.798412: step: 1440/529, loss: 0.001311361906118691
2023-01-24 09:53:01.928582: step: 1444/529, loss: 0.0023455703631043434
2023-01-24 09:53:03.019224: step: 1448/529, loss: 0.0017849833238869905
2023-01-24 09:53:04.091474: step: 1452/529, loss: 0.0004918168415315449
2023-01-24 09:53:05.245826: step: 1456/529, loss: 6.398432742571458e-05
2023-01-24 09:53:06.354922: step: 1460/529, loss: 0.0005941387498751283
2023-01-24 09:53:07.468238: step: 1464/529, loss: 0.003601847914978862
2023-01-24 09:53:08.574399: step: 1468/529, loss: 0.00023561141279060394
2023-01-24 09:53:09.735366: step: 1472/529, loss: 0.0022896183654665947
2023-01-24 09:53:10.846979: step: 1476/529, loss: 0.0027066089678555727
2023-01-24 09:53:11.959158: step: 1480/529, loss: 0.013704094104468822
2023-01-24 09:53:13.054456: step: 1484/529, loss: 0.003100431989878416
2023-01-24 09:53:14.130801: step: 1488/529, loss: 0.0008488218300044537
2023-01-24 09:53:15.227552: step: 1492/529, loss: 0.0003397142281755805
2023-01-24 09:53:16.321853: step: 1496/529, loss: 0.004243710543960333
2023-01-24 09:53:17.442252: step: 1500/529, loss: 0.002570914104580879
2023-01-24 09:53:18.562297: step: 1504/529, loss: 0.00468383589759469
2023-01-24 09:53:19.652274: step: 1508/529, loss: 0.027202624827623367
2023-01-24 09:53:20.731706: step: 1512/529, loss: 0.0005272456910461187
2023-01-24 09:53:21.846752: step: 1516/529, loss: 0.009197598323225975
2023-01-24 09:53:22.960699: step: 1520/529, loss: 0.0020008489955216646
2023-01-24 09:53:24.065745: step: 1524/529, loss: 0.012477155774831772
2023-01-24 09:53:25.178753: step: 1528/529, loss: 0.0005014143534936011
2023-01-24 09:53:26.281396: step: 1532/529, loss: 0.0012618745677173138
2023-01-24 09:53:27.410978: step: 1536/529, loss: 0.0023072431795299053
2023-01-24 09:53:28.513706: step: 1540/529, loss: 0.001811041496694088
2023-01-24 09:53:29.628599: step: 1544/529, loss: 0.0018031415529549122
2023-01-24 09:53:30.731786: step: 1548/529, loss: 0.003972366917878389
2023-01-24 09:53:31.826485: step: 1552/529, loss: 0.008141478523612022
2023-01-24 09:53:32.973418: step: 1556/529, loss: 0.0010068807750940323
2023-01-24 09:53:34.133946: step: 1560/529, loss: 0.0021519185975193977
2023-01-24 09:53:35.210243: step: 1564/529, loss: 0.0018538638250902295
2023-01-24 09:53:36.297020: step: 1568/529, loss: 0.007912657223641872
2023-01-24 09:53:37.396696: step: 1572/529, loss: 0.003314683912321925
2023-01-24 09:53:38.515438: step: 1576/529, loss: 8.966632594820112e-05
2023-01-24 09:53:39.624612: step: 1580/529, loss: 0.012869778089225292
2023-01-24 09:53:40.743566: step: 1584/529, loss: 0.0020855716429650784
2023-01-24 09:53:41.848418: step: 1588/529, loss: 0.004303572233766317
2023-01-24 09:53:42.959225: step: 1592/529, loss: 0.0006219679489731789
2023-01-24 09:53:44.076005: step: 1596/529, loss: 0.00776786869391799
2023-01-24 09:53:45.182346: step: 1600/529, loss: 0.0009899999713525176
2023-01-24 09:53:46.317539: step: 1604/529, loss: 0.007224968168884516
2023-01-24 09:53:47.406493: step: 1608/529, loss: 0.00024036105605773628
2023-01-24 09:53:48.504160: step: 1612/529, loss: 0.00498131662607193
2023-01-24 09:53:49.629493: step: 1616/529, loss: 0.006104725878685713
2023-01-24 09:53:50.734342: step: 1620/529, loss: 0.005027460400015116
2023-01-24 09:53:51.835868: step: 1624/529, loss: 0.0059813326224684715
2023-01-24 09:53:52.921069: step: 1628/529, loss: 0.004766613710671663
2023-01-24 09:53:54.032993: step: 1632/529, loss: 0.0012144464999437332
2023-01-24 09:53:55.157245: step: 1636/529, loss: 0.0011972025968134403
2023-01-24 09:53:56.263564: step: 1640/529, loss: 0.002710269298404455
2023-01-24 09:53:57.369539: step: 1644/529, loss: 0.0037481330800801516
2023-01-24 09:53:58.469684: step: 1648/529, loss: 0.028278984129428864
2023-01-24 09:53:59.583663: step: 1652/529, loss: 0.003947314340621233
2023-01-24 09:54:00.689387: step: 1656/529, loss: 0.0066324397921562195
2023-01-24 09:54:01.815384: step: 1660/529, loss: 0.004012054763734341
2023-01-24 09:54:02.947450: step: 1664/529, loss: 0.0036920784041285515
2023-01-24 09:54:04.047562: step: 1668/529, loss: 0.004566891118884087
2023-01-24 09:54:05.169998: step: 1672/529, loss: 0.00865353737026453
2023-01-24 09:54:06.266495: step: 1676/529, loss: 0.026723137125372887
2023-01-24 09:54:07.382150: step: 1680/529, loss: 0.0040269517339766026
2023-01-24 09:54:08.513387: step: 1684/529, loss: 0.0004061144427396357
2023-01-24 09:54:09.625771: step: 1688/529, loss: 0.0010386602953076363
2023-01-24 09:54:10.755393: step: 1692/529, loss: 0.0006115996511653066
2023-01-24 09:54:11.867223: step: 1696/529, loss: 0.006431979592889547
2023-01-24 09:54:12.992204: step: 1700/529, loss: 0.0007895925082266331
2023-01-24 09:54:14.108305: step: 1704/529, loss: 0.006763428915292025
2023-01-24 09:54:15.211483: step: 1708/529, loss: 0.004503482487052679
2023-01-24 09:54:16.319775: step: 1712/529, loss: 0.0024288950953632593
2023-01-24 09:54:17.421892: step: 1716/529, loss: 0.0016698454273864627
2023-01-24 09:54:18.528878: step: 1720/529, loss: 0.008600680157542229
2023-01-24 09:54:19.629465: step: 1724/529, loss: 0.009262578561902046
2023-01-24 09:54:20.731673: step: 1728/529, loss: 0.005364392884075642
2023-01-24 09:54:21.817374: step: 1732/529, loss: 0.00012965862697456032
2023-01-24 09:54:22.940787: step: 1736/529, loss: 0.006011847872287035
2023-01-24 09:54:24.040516: step: 1740/529, loss: 0.00032434886088594794
2023-01-24 09:54:25.130448: step: 1744/529, loss: 0.0036722864024341106
2023-01-24 09:54:26.209446: step: 1748/529, loss: 0.00034246567520312965
2023-01-24 09:54:27.295124: step: 1752/529, loss: 0.006833645049482584
2023-01-24 09:54:28.392448: step: 1756/529, loss: 0.008699985221028328
2023-01-24 09:54:29.482148: step: 1760/529, loss: 0.008430399931967258
2023-01-24 09:54:30.606307: step: 1764/529, loss: 0.025292176753282547
2023-01-24 09:54:31.717661: step: 1768/529, loss: 0.0013584656408056617
2023-01-24 09:54:32.819588: step: 1772/529, loss: 0.0020845450926572084
2023-01-24 09:54:33.928199: step: 1776/529, loss: 0.005831795744597912
2023-01-24 09:54:35.043534: step: 1780/529, loss: 0.0007305140607059002
2023-01-24 09:54:36.132375: step: 1784/529, loss: 0.0005277474992908537
2023-01-24 09:54:37.251576: step: 1788/529, loss: 0.0026804453227669
2023-01-24 09:54:38.387664: step: 1792/529, loss: 0.0037544609513133764
2023-01-24 09:54:39.502014: step: 1796/529, loss: 0.002447819337248802
2023-01-24 09:54:40.606662: step: 1800/529, loss: 0.006819633301347494
2023-01-24 09:54:41.721365: step: 1804/529, loss: 0.014861439354717731
2023-01-24 09:54:42.811285: step: 1808/529, loss: 0.01005969475954771
2023-01-24 09:54:43.923448: step: 1812/529, loss: 0.0026143486611545086
2023-01-24 09:54:45.025440: step: 1816/529, loss: 0.0017141166608780622
2023-01-24 09:54:46.144114: step: 1820/529, loss: 0.00028625846607610583
2023-01-24 09:54:47.239146: step: 1824/529, loss: 0.009886933490633965
2023-01-24 09:54:48.348358: step: 1828/529, loss: 0.008462507277727127
2023-01-24 09:54:49.478607: step: 1832/529, loss: 0.002373362658545375
2023-01-24 09:54:50.592444: step: 1836/529, loss: 0.010799266397953033
2023-01-24 09:54:51.681859: step: 1840/529, loss: 0.0023878805804997683
2023-01-24 09:54:52.763309: step: 1844/529, loss: 0.00037746719317510724
2023-01-24 09:54:53.864461: step: 1848/529, loss: 0.002651546848937869
2023-01-24 09:54:54.953931: step: 1852/529, loss: 0.0016376536805182695
2023-01-24 09:54:56.064398: step: 1856/529, loss: 0.00024241811479441822
2023-01-24 09:54:57.159761: step: 1860/529, loss: 0.04234139248728752
2023-01-24 09:54:58.256854: step: 1864/529, loss: 0.012446251697838306
2023-01-24 09:54:59.340598: step: 1868/529, loss: 0.000920478836633265
2023-01-24 09:55:00.466633: step: 1872/529, loss: 0.007537745870649815
2023-01-24 09:55:01.580926: step: 1876/529, loss: 1.1320285011606757e-05
2023-01-24 09:55:02.704364: step: 1880/529, loss: 0.0031365377362817526
2023-01-24 09:55:03.808388: step: 1884/529, loss: 0.003990591503679752
2023-01-24 09:55:04.912853: step: 1888/529, loss: 0.009194576181471348
2023-01-24 09:55:06.005348: step: 1892/529, loss: 0.0014267516089603305
2023-01-24 09:55:07.113878: step: 1896/529, loss: 0.0035343386698514223
2023-01-24 09:55:08.189613: step: 1900/529, loss: 0.0096924202516675
2023-01-24 09:55:09.335818: step: 1904/529, loss: 0.003925623372197151
2023-01-24 09:55:10.438832: step: 1908/529, loss: 0.0009244598331861198
2023-01-24 09:55:11.560089: step: 1912/529, loss: 0.0001163346751127392
2023-01-24 09:55:12.656630: step: 1916/529, loss: 0.009144597686827183
2023-01-24 09:55:13.751979: step: 1920/529, loss: 0.013364441692829132
2023-01-24 09:55:14.846931: step: 1924/529, loss: 0.003969738259911537
2023-01-24 09:55:15.934697: step: 1928/529, loss: 0.006603530142456293
2023-01-24 09:55:17.041765: step: 1932/529, loss: 0.004993661306798458
2023-01-24 09:55:18.151844: step: 1936/529, loss: 0.0001218821998918429
2023-01-24 09:55:19.261141: step: 1940/529, loss: 0.004339583683758974
2023-01-24 09:55:20.355925: step: 1944/529, loss: 0.00029273389372974634
2023-01-24 09:55:21.489443: step: 1948/529, loss: 0.00806443765759468
2023-01-24 09:55:22.603791: step: 1952/529, loss: 0.0008818538044579327
2023-01-24 09:55:23.714460: step: 1956/529, loss: 0.0025958630722016096
2023-01-24 09:55:24.830059: step: 1960/529, loss: 0.0037159130442887545
2023-01-24 09:55:25.959323: step: 1964/529, loss: 0.0017035230994224548
2023-01-24 09:55:27.062164: step: 1968/529, loss: 0.0020899998489767313
2023-01-24 09:55:28.159833: step: 1972/529, loss: 0.0015551656251773238
2023-01-24 09:55:29.255016: step: 1976/529, loss: 0.0018237102776765823
2023-01-24 09:55:30.370839: step: 1980/529, loss: 0.005107039585709572
2023-01-24 09:55:31.463164: step: 1984/529, loss: 0.004629435949027538
2023-01-24 09:55:32.575947: step: 1988/529, loss: 0.006663202308118343
2023-01-24 09:55:33.691093: step: 1992/529, loss: 0.0038683104794472456
2023-01-24 09:55:34.768551: step: 1996/529, loss: 0.0008164198370650411
2023-01-24 09:55:35.859722: step: 2000/529, loss: 0.004791025537997484
2023-01-24 09:55:36.950605: step: 2004/529, loss: 0.004603276029229164
2023-01-24 09:55:38.056733: step: 2008/529, loss: 6.202576332725585e-05
2023-01-24 09:55:39.180398: step: 2012/529, loss: 0.0008024513372220099
2023-01-24 09:55:40.299567: step: 2016/529, loss: 0.0019630303140729666
2023-01-24 09:55:41.405480: step: 2020/529, loss: 0.0017096453811973333
2023-01-24 09:55:42.489010: step: 2024/529, loss: 2.481234332663007e-05
2023-01-24 09:55:43.604769: step: 2028/529, loss: 0.0018272375455126166
2023-01-24 09:55:44.706536: step: 2032/529, loss: 8.301223715534434e-06
2023-01-24 09:55:45.801929: step: 2036/529, loss: 0.002904096618294716
2023-01-24 09:55:46.934440: step: 2040/529, loss: 0.011072534136474133
2023-01-24 09:55:48.041426: step: 2044/529, loss: 0.004040045663714409
2023-01-24 09:55:49.155474: step: 2048/529, loss: 0.003164100693538785
2023-01-24 09:55:50.254743: step: 2052/529, loss: 0.003730867989361286
2023-01-24 09:55:51.351351: step: 2056/529, loss: 0.0008495133952237666
2023-01-24 09:55:52.449560: step: 2060/529, loss: 0.0006894392427057028
2023-01-24 09:55:53.593244: step: 2064/529, loss: 0.004105313681066036
2023-01-24 09:55:54.717482: step: 2068/529, loss: 0.005463628098368645
2023-01-24 09:55:55.806119: step: 2072/529, loss: 0.003398022847250104
2023-01-24 09:55:56.892238: step: 2076/529, loss: 0.012395462952554226
2023-01-24 09:55:57.990521: step: 2080/529, loss: 0.004758353810757399
2023-01-24 09:55:59.117802: step: 2084/529, loss: 0.0029524625279009342
2023-01-24 09:56:00.238261: step: 2088/529, loss: 0.0026175796519964933
2023-01-24 09:56:01.351998: step: 2092/529, loss: 0.0030490770004689693
2023-01-24 09:56:02.453445: step: 2096/529, loss: 0.002107314532622695
2023-01-24 09:56:03.558074: step: 2100/529, loss: 0.0012011931976303458
2023-01-24 09:56:04.651778: step: 2104/529, loss: 0.004759353119879961
2023-01-24 09:56:05.764042: step: 2108/529, loss: 0.002035393612459302
2023-01-24 09:56:06.855274: step: 2112/529, loss: 0.00014560946146957576
2023-01-24 09:56:07.963421: step: 2116/529, loss: 0.0034651432652026415
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38131420545746386, 'r': 0.321982583355923, 'f1': 0.3491457231040564}, 'combined': 0.25726526965562047, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.4010869561854429, 'r': 0.28812919122853736, 'f1': 0.3353515750657914}, 'combined': 0.20611852906482786, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3739808168857774, 'r': 0.3328216377977791, 'f1': 0.35220281750889476}, 'combined': 0.2595178655328698, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38254895335211175, 'r': 0.29072394461854595, 'f1': 0.3303746253961615}, 'combined': 0.2030595258532505, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40853932584269664, 'r': 0.34497153700189753, 'f1': 0.37407407407407406}, 'combined': 0.2756335282651072, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39808412689278216, 'r': 0.285282125598207, 'f1': 0.33237311755712357}, 'combined': 0.2052892784911646, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 12}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3739808168857774, 'r': 0.3328216377977791, 'f1': 0.35220281750889476}, 'combined': 0.2595178655328698, 'stategy': 1, 'epoch': 12}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38254895335211175, 'r': 0.29072394461854595, 'f1': 0.3303746253961615}, 'combined': 0.2030595258532505, 'stategy': 1, 'epoch': 12}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 13
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:58:34.713475: step: 4/529, loss: 0.0006948032532818615
2023-01-24 09:58:35.805741: step: 8/529, loss: 0.0001499262871220708
2023-01-24 09:58:36.919047: step: 12/529, loss: 0.0006850948557257652
2023-01-24 09:58:37.989572: step: 16/529, loss: 0.007784007582813501
2023-01-24 09:58:39.090224: step: 20/529, loss: 0.0006867876509204507
2023-01-24 09:58:40.190189: step: 24/529, loss: 0.0008491107728332281
2023-01-24 09:58:41.307403: step: 28/529, loss: 0.001975971506908536
2023-01-24 09:58:42.411271: step: 32/529, loss: 0.0033514846581965685
2023-01-24 09:58:43.506332: step: 36/529, loss: 0.0018445549067109823
2023-01-24 09:58:44.617317: step: 40/529, loss: 0.002414599061012268
2023-01-24 09:58:45.715103: step: 44/529, loss: 0.0045388913713395596
2023-01-24 09:58:46.815848: step: 48/529, loss: 0.00047159349196590483
2023-01-24 09:58:47.921184: step: 52/529, loss: 0.0036370062734931707
2023-01-24 09:58:49.017374: step: 56/529, loss: 0.0033063916489481926
2023-01-24 09:58:50.089818: step: 60/529, loss: 0.000929742818698287
2023-01-24 09:58:51.180851: step: 64/529, loss: 0.0016535071190446615
2023-01-24 09:58:52.285366: step: 68/529, loss: 0.0004412627313286066
2023-01-24 09:58:53.387873: step: 72/529, loss: 0.0034161717630922794
2023-01-24 09:58:54.481678: step: 76/529, loss: 0.00904846005141735
2023-01-24 09:58:55.583973: step: 80/529, loss: 0.00037185585824772716
2023-01-24 09:58:56.668027: step: 84/529, loss: 0.0009800201514735818
2023-01-24 09:58:57.770983: step: 88/529, loss: 0.0006961131002753973
2023-01-24 09:58:58.862615: step: 92/529, loss: 0.004999516066163778
2023-01-24 09:58:59.958056: step: 96/529, loss: 0.0010828980011865497
2023-01-24 09:59:01.084282: step: 100/529, loss: 0.0024024604354053736
2023-01-24 09:59:02.184428: step: 104/529, loss: 0.00323964050039649
2023-01-24 09:59:03.277480: step: 108/529, loss: 0.0012623514048755169
2023-01-24 09:59:04.371150: step: 112/529, loss: 0.003003516234457493
2023-01-24 09:59:05.461925: step: 116/529, loss: 0.0013126255944371223
2023-01-24 09:59:06.576050: step: 120/529, loss: 0.0034391535446047783
2023-01-24 09:59:07.679880: step: 124/529, loss: 0.0034552402794361115
2023-01-24 09:59:08.781896: step: 128/529, loss: 0.00046613425365649164
2023-01-24 09:59:09.865068: step: 132/529, loss: 0.003780502825975418
2023-01-24 09:59:10.973361: step: 136/529, loss: 0.000349131238181144
2023-01-24 09:59:12.082575: step: 140/529, loss: 5.621160994451202e-07
2023-01-24 09:59:13.180467: step: 144/529, loss: 0.00248551438562572
2023-01-24 09:59:14.294077: step: 148/529, loss: 0.0037998247426003218
2023-01-24 09:59:15.395593: step: 152/529, loss: 0.05563031882047653
2023-01-24 09:59:16.516994: step: 156/529, loss: 6.327210576273501e-05
2023-01-24 09:59:17.642183: step: 160/529, loss: 0.009362129494547844
2023-01-24 09:59:18.771005: step: 164/529, loss: 0.00032673621899448335
2023-01-24 09:59:19.883761: step: 168/529, loss: 0.008832283318042755
2023-01-24 09:59:20.999737: step: 172/529, loss: 0.0010492218425497413
2023-01-24 09:59:22.085760: step: 176/529, loss: 0.006012359168380499
2023-01-24 09:59:23.193870: step: 180/529, loss: 0.0029631650540977716
2023-01-24 09:59:24.290291: step: 184/529, loss: 0.007308172062039375
2023-01-24 09:59:25.401318: step: 188/529, loss: 0.004614134784787893
2023-01-24 09:59:26.490169: step: 192/529, loss: 2.1989408196532167e-06
2023-01-24 09:59:27.581889: step: 196/529, loss: 0.004140627104789019
2023-01-24 09:59:28.691518: step: 200/529, loss: 0.0024242205545306206
2023-01-24 09:59:29.810368: step: 204/529, loss: 0.0029170934576541185
2023-01-24 09:59:30.938349: step: 208/529, loss: 0.00487776892259717
2023-01-24 09:59:32.035625: step: 212/529, loss: 0.00011802694643847644
2023-01-24 09:59:33.148863: step: 216/529, loss: 0.005051000043749809
2023-01-24 09:59:34.276465: step: 220/529, loss: 0.01882794126868248
2023-01-24 09:59:35.380898: step: 224/529, loss: 0.026438212022185326
2023-01-24 09:59:36.494878: step: 228/529, loss: 0.0018311140593141317
2023-01-24 09:59:37.585758: step: 232/529, loss: 0.004033572040498257
2023-01-24 09:59:38.688702: step: 236/529, loss: 0.006434094626456499
2023-01-24 09:59:39.793512: step: 240/529, loss: 0.00786223541945219
2023-01-24 09:59:40.914987: step: 244/529, loss: 0.0021165211219340563
2023-01-24 09:59:41.993348: step: 248/529, loss: 0.0071181440725922585
2023-01-24 09:59:43.078152: step: 252/529, loss: 5.6450884585501626e-05
2023-01-24 09:59:44.175711: step: 256/529, loss: 0.004464322235435247
2023-01-24 09:59:45.264659: step: 260/529, loss: 0.003140700049698353
2023-01-24 09:59:46.369643: step: 264/529, loss: 0.0061014434322714806
2023-01-24 09:59:47.472409: step: 268/529, loss: 0.0012937269639223814
2023-01-24 09:59:48.559296: step: 272/529, loss: 0.00657568359747529
2023-01-24 09:59:49.644550: step: 276/529, loss: 0.00027721558581106365
2023-01-24 09:59:50.760155: step: 280/529, loss: 0.0029196091927587986
2023-01-24 09:59:51.872894: step: 284/529, loss: 0.0006043731118552387
2023-01-24 09:59:52.982744: step: 288/529, loss: 0.0011730119585990906
2023-01-24 09:59:54.102952: step: 292/529, loss: 0.0007926944526843727
2023-01-24 09:59:55.203084: step: 296/529, loss: 0.0007542414823547006
2023-01-24 09:59:56.370997: step: 300/529, loss: 0.0015026562614366412
2023-01-24 09:59:57.498006: step: 304/529, loss: 0.005537477787584066
2023-01-24 09:59:58.597145: step: 308/529, loss: 0.00019311800133436918
2023-01-24 09:59:59.695227: step: 312/529, loss: 0.0028398402500897646
2023-01-24 10:00:00.817968: step: 316/529, loss: 0.008974147029221058
2023-01-24 10:00:01.948138: step: 320/529, loss: 0.009728076867759228
2023-01-24 10:00:03.075465: step: 324/529, loss: 0.004854380618780851
2023-01-24 10:00:04.184880: step: 328/529, loss: 0.002332303673028946
2023-01-24 10:00:05.285346: step: 332/529, loss: 0.0008780196076259017
2023-01-24 10:00:06.378738: step: 336/529, loss: 0.0008499495452269912
2023-01-24 10:00:07.498128: step: 340/529, loss: 0.019866853952407837
2023-01-24 10:00:08.614568: step: 344/529, loss: 0.003416645573452115
2023-01-24 10:00:09.728490: step: 348/529, loss: 0.002405986189842224
2023-01-24 10:00:10.838575: step: 352/529, loss: 0.001651348895393312
2023-01-24 10:00:11.948841: step: 356/529, loss: 0.0022714484948664904
2023-01-24 10:00:13.058566: step: 360/529, loss: 0.003909091465175152
2023-01-24 10:00:14.170113: step: 364/529, loss: 0.001101157278753817
2023-01-24 10:00:15.282135: step: 368/529, loss: 0.0008100132690742612
2023-01-24 10:00:16.369457: step: 372/529, loss: 0.007777967490255833
2023-01-24 10:00:17.491061: step: 376/529, loss: 0.00048486358718946576
2023-01-24 10:00:18.610649: step: 380/529, loss: 0.0012975268764421344
2023-01-24 10:00:19.726868: step: 384/529, loss: 0.0018789772875607014
2023-01-24 10:00:20.827733: step: 388/529, loss: 0.0035135129000991583
2023-01-24 10:00:21.927776: step: 392/529, loss: 0.0006281780079007149
2023-01-24 10:00:23.026094: step: 396/529, loss: 0.00021168992680031806
2023-01-24 10:00:24.120420: step: 400/529, loss: 8.455010538455099e-05
2023-01-24 10:00:25.223937: step: 404/529, loss: 5.767868788097985e-05
2023-01-24 10:00:26.327779: step: 408/529, loss: 0.0007190883043222129
2023-01-24 10:00:27.427211: step: 412/529, loss: 0.0007240864797495306
2023-01-24 10:00:28.526320: step: 416/529, loss: 0.0005532549694180489
2023-01-24 10:00:29.632488: step: 420/529, loss: 0.0013095646863803267
2023-01-24 10:00:30.761702: step: 424/529, loss: 0.0037706487346440554
2023-01-24 10:00:31.880931: step: 428/529, loss: 0.011104962788522243
2023-01-24 10:00:32.972201: step: 432/529, loss: 0.0020567597821354866
2023-01-24 10:00:34.081724: step: 436/529, loss: 0.0046827602200210094
2023-01-24 10:00:35.171061: step: 440/529, loss: 0.008268962614238262
2023-01-24 10:00:36.263289: step: 444/529, loss: 0.0077894278801977634
2023-01-24 10:00:37.368346: step: 448/529, loss: 0.0022867717780172825
2023-01-24 10:00:38.467498: step: 452/529, loss: 0.00026830582646653056
2023-01-24 10:00:39.581737: step: 456/529, loss: 0.0026021983940154314
2023-01-24 10:00:40.662698: step: 460/529, loss: 0.018371181562542915
2023-01-24 10:00:41.783845: step: 464/529, loss: 0.013064390048384666
2023-01-24 10:00:42.870985: step: 468/529, loss: 0.009543689899146557
2023-01-24 10:00:43.989339: step: 472/529, loss: 0.009290165267884731
2023-01-24 10:00:45.079364: step: 476/529, loss: 0.0010082634398713708
2023-01-24 10:00:46.169216: step: 480/529, loss: 0.000775691878516227
2023-01-24 10:00:47.252665: step: 484/529, loss: 0.012369402684271336
2023-01-24 10:00:48.363137: step: 488/529, loss: 0.018461138010025024
2023-01-24 10:00:49.462204: step: 492/529, loss: 0.004069300834089518
2023-01-24 10:00:50.583244: step: 496/529, loss: 0.001836001523770392
2023-01-24 10:00:51.694769: step: 500/529, loss: 0.014671975746750832
2023-01-24 10:00:52.793821: step: 504/529, loss: 9.197022882290184e-05
2023-01-24 10:00:53.914995: step: 508/529, loss: 6.764496356481686e-05
2023-01-24 10:00:55.035534: step: 512/529, loss: 0.013049319386482239
2023-01-24 10:00:56.155214: step: 516/529, loss: 0.012440884485840797
2023-01-24 10:00:57.262429: step: 520/529, loss: 0.004193383734673262
2023-01-24 10:00:58.394644: step: 524/529, loss: 0.013714454136788845
2023-01-24 10:00:59.506679: step: 528/529, loss: 0.003881119191646576
2023-01-24 10:01:00.617262: step: 532/529, loss: 0.00396935036405921
2023-01-24 10:01:01.721934: step: 536/529, loss: 0.02821853756904602
2023-01-24 10:01:02.841122: step: 540/529, loss: 0.006639223080128431
2023-01-24 10:01:03.953540: step: 544/529, loss: 0.005402149632573128
2023-01-24 10:01:05.060121: step: 548/529, loss: 0.004063083324581385
2023-01-24 10:01:06.180917: step: 552/529, loss: 0.010244485922157764
2023-01-24 10:01:07.270482: step: 556/529, loss: 0.003431206103414297
2023-01-24 10:01:08.365906: step: 560/529, loss: 0.0006999879842624068
2023-01-24 10:01:09.482209: step: 564/529, loss: 0.015978271141648293
2023-01-24 10:01:10.592238: step: 568/529, loss: 0.015868045389652252
2023-01-24 10:01:11.691304: step: 572/529, loss: 0.0075306762009859085
2023-01-24 10:01:12.778035: step: 576/529, loss: 0.004426661413162947
2023-01-24 10:01:13.895492: step: 580/529, loss: 0.002008965704590082
2023-01-24 10:01:14.988167: step: 584/529, loss: 0.020740127190947533
2023-01-24 10:01:16.099741: step: 588/529, loss: 0.007090700324624777
2023-01-24 10:01:17.205638: step: 592/529, loss: 0.00010234750516247004
2023-01-24 10:01:18.305701: step: 596/529, loss: 0.00015524840273428708
2023-01-24 10:01:19.411540: step: 600/529, loss: 0.0001827776723075658
2023-01-24 10:01:20.530310: step: 604/529, loss: 0.003889684798195958
2023-01-24 10:01:21.639706: step: 608/529, loss: 0.0015885920729488134
2023-01-24 10:01:22.780754: step: 612/529, loss: 0.005676168482750654
2023-01-24 10:01:23.907934: step: 616/529, loss: 0.013380931690335274
2023-01-24 10:01:25.026335: step: 620/529, loss: 0.0006388660985976458
2023-01-24 10:01:26.175874: step: 624/529, loss: 0.01510299276560545
2023-01-24 10:01:27.282858: step: 628/529, loss: 0.0030728622805327177
2023-01-24 10:01:28.384071: step: 632/529, loss: 0.0009192724246531725
2023-01-24 10:01:29.479485: step: 636/529, loss: 0.003525824286043644
2023-01-24 10:01:30.563277: step: 640/529, loss: 0.0011931014014407992
2023-01-24 10:01:31.695315: step: 644/529, loss: 0.007567007560282946
2023-01-24 10:01:32.807115: step: 648/529, loss: 0.00481884041801095
2023-01-24 10:01:33.969359: step: 652/529, loss: 0.0004379861056804657
2023-01-24 10:01:35.103024: step: 656/529, loss: 0.00036360116791911423
2023-01-24 10:01:36.215059: step: 660/529, loss: 0.006468756124377251
2023-01-24 10:01:37.315204: step: 664/529, loss: 0.022208135575056076
2023-01-24 10:01:38.434792: step: 668/529, loss: 0.006527363322675228
2023-01-24 10:01:39.532524: step: 672/529, loss: 0.0002511840721126646
2023-01-24 10:01:40.631668: step: 676/529, loss: 0.0011463487753644586
2023-01-24 10:01:41.742789: step: 680/529, loss: 0.007166531402617693
2023-01-24 10:01:42.836472: step: 684/529, loss: 0.005786821246147156
2023-01-24 10:01:43.949942: step: 688/529, loss: 0.00015440903371199965
2023-01-24 10:01:45.074831: step: 692/529, loss: 0.01104927621781826
2023-01-24 10:01:46.203122: step: 696/529, loss: 0.012749074958264828
2023-01-24 10:01:47.308119: step: 700/529, loss: 0.0036831344477832317
2023-01-24 10:01:48.428812: step: 704/529, loss: 0.0009097973816096783
2023-01-24 10:01:49.554493: step: 708/529, loss: 4.9499318265588954e-05
2023-01-24 10:01:50.652947: step: 712/529, loss: 0.0315108560025692
2023-01-24 10:01:51.771741: step: 716/529, loss: 2.919686994573567e-05
2023-01-24 10:01:52.869590: step: 720/529, loss: 0.0025843854527920485
2023-01-24 10:01:53.990482: step: 724/529, loss: 0.004740494303405285
2023-01-24 10:01:55.112673: step: 728/529, loss: 0.010217221453785896
2023-01-24 10:01:56.210593: step: 732/529, loss: 0.0005563810700550675
2023-01-24 10:01:57.352301: step: 736/529, loss: 0.01862388104200363
2023-01-24 10:01:58.468137: step: 740/529, loss: 0.00048288985271938145
2023-01-24 10:01:59.558735: step: 744/529, loss: 0.00038192738429643214
2023-01-24 10:02:00.654589: step: 748/529, loss: 0.007242663763463497
2023-01-24 10:02:01.770232: step: 752/529, loss: 0.002760883653536439
2023-01-24 10:02:02.906469: step: 756/529, loss: 0.005144339520484209
2023-01-24 10:02:04.031019: step: 760/529, loss: 0.006629531271755695
2023-01-24 10:02:05.126846: step: 764/529, loss: 0.006685684900730848
2023-01-24 10:02:06.256457: step: 768/529, loss: 0.022398415952920914
2023-01-24 10:02:07.361500: step: 772/529, loss: 0.0007041774806566536
2023-01-24 10:02:08.467405: step: 776/529, loss: 1.6293995940941386e-05
2023-01-24 10:02:09.577128: step: 780/529, loss: 0.003203638596460223
2023-01-24 10:02:10.691121: step: 784/529, loss: 0.004283823538571596
2023-01-24 10:02:11.805725: step: 788/529, loss: 0.0075381905771791935
2023-01-24 10:02:12.917350: step: 792/529, loss: 0.0066542052663862705
2023-01-24 10:02:14.040745: step: 796/529, loss: 0.03295162320137024
2023-01-24 10:02:15.161789: step: 800/529, loss: 0.00010164460400119424
2023-01-24 10:02:16.275535: step: 804/529, loss: 1.910340870381333e-05
2023-01-24 10:02:17.385569: step: 808/529, loss: 0.004703650251030922
2023-01-24 10:02:18.495255: step: 812/529, loss: 0.0043242513202130795
2023-01-24 10:02:19.593440: step: 816/529, loss: 3.7775909731863067e-05
2023-01-24 10:02:20.708369: step: 820/529, loss: 0.003010609420016408
2023-01-24 10:02:21.821278: step: 824/529, loss: 0.006059859413653612
2023-01-24 10:02:22.966529: step: 828/529, loss: 0.00140922493301332
2023-01-24 10:02:24.097151: step: 832/529, loss: 0.004433562513440847
2023-01-24 10:02:25.203330: step: 836/529, loss: 0.00036265054950490594
2023-01-24 10:02:26.317499: step: 840/529, loss: 0.0013340807054191828
2023-01-24 10:02:27.432784: step: 844/529, loss: 0.0016003873897716403
2023-01-24 10:02:28.554301: step: 848/529, loss: 0.015481779351830482
2023-01-24 10:02:29.649191: step: 852/529, loss: 0.0020873250905424356
2023-01-24 10:02:30.761941: step: 856/529, loss: 0.010177010670304298
2023-01-24 10:02:31.883852: step: 860/529, loss: 0.0022814415860921144
2023-01-24 10:02:32.980940: step: 864/529, loss: 0.00021137519797775894
2023-01-24 10:02:34.097864: step: 868/529, loss: 0.0020440544467419386
2023-01-24 10:02:35.270450: step: 872/529, loss: 0.0017960197292268276
2023-01-24 10:02:36.381907: step: 876/529, loss: 0.00021832113270647824
2023-01-24 10:02:37.479208: step: 880/529, loss: 0.003966952674090862
2023-01-24 10:02:38.590279: step: 884/529, loss: 0.006781257223337889
2023-01-24 10:02:39.690856: step: 888/529, loss: 6.368824415403651e-06
2023-01-24 10:02:40.807078: step: 892/529, loss: 0.0010949590941891074
2023-01-24 10:02:41.923075: step: 896/529, loss: 0.006874303799122572
2023-01-24 10:02:43.034657: step: 900/529, loss: 0.00033875342342071235
2023-01-24 10:02:44.147836: step: 904/529, loss: 0.00014677204308100045
2023-01-24 10:02:45.244948: step: 908/529, loss: 0.00024912384105846286
2023-01-24 10:02:46.352086: step: 912/529, loss: 0.0001998598309000954
2023-01-24 10:02:47.470626: step: 916/529, loss: 0.012555522844195366
2023-01-24 10:02:48.585997: step: 920/529, loss: 0.06372683495283127
2023-01-24 10:02:49.695491: step: 924/529, loss: 0.0012132684933021665
2023-01-24 10:02:50.813628: step: 928/529, loss: 4.712116424343549e-05
2023-01-24 10:02:51.907215: step: 932/529, loss: 0.004622513893991709
2023-01-24 10:02:53.047131: step: 936/529, loss: 0.002345712622627616
2023-01-24 10:02:54.166426: step: 940/529, loss: 0.0024560585152357817
2023-01-24 10:02:55.285883: step: 944/529, loss: 0.008232715539634228
2023-01-24 10:02:56.407487: step: 948/529, loss: 0.01013212464749813
2023-01-24 10:02:57.504431: step: 952/529, loss: 0.005070831160992384
2023-01-24 10:02:58.657238: step: 956/529, loss: 0.008775657042860985
2023-01-24 10:02:59.754647: step: 960/529, loss: 0.008252574130892754
2023-01-24 10:03:00.870362: step: 964/529, loss: 0.007017153315246105
2023-01-24 10:03:01.980864: step: 968/529, loss: 0.0007136272615753114
2023-01-24 10:03:03.109476: step: 972/529, loss: 8.079919643932953e-05
2023-01-24 10:03:04.222280: step: 976/529, loss: 0.010866090655326843
2023-01-24 10:03:05.329465: step: 980/529, loss: 0.004205236677080393
2023-01-24 10:03:06.444493: step: 984/529, loss: 9.855058306129649e-05
2023-01-24 10:03:07.549960: step: 988/529, loss: 0.002479932038113475
2023-01-24 10:03:08.632266: step: 992/529, loss: 0.004178322851657867
2023-01-24 10:03:09.735137: step: 996/529, loss: 1.0259625923936255e-05
2023-01-24 10:03:10.834399: step: 1000/529, loss: 0.001369644422084093
2023-01-24 10:03:11.953730: step: 1004/529, loss: 0.000839556974824518
2023-01-24 10:03:13.061365: step: 1008/529, loss: 0.002839289605617523
2023-01-24 10:03:14.189159: step: 1012/529, loss: 0.005903448909521103
2023-01-24 10:03:15.296229: step: 1016/529, loss: 0.003977745305746794
2023-01-24 10:03:16.409227: step: 1020/529, loss: 0.00040159703348763287
2023-01-24 10:03:17.517498: step: 1024/529, loss: 0.00013529737771023065
2023-01-24 10:03:18.649511: step: 1028/529, loss: 0.003173396922647953
2023-01-24 10:03:19.773789: step: 1032/529, loss: 9.981417679227889e-05
2023-01-24 10:03:20.866725: step: 1036/529, loss: 0.004461656790226698
2023-01-24 10:03:21.970546: step: 1040/529, loss: 0.002025868743658066
2023-01-24 10:03:23.058935: step: 1044/529, loss: 0.00030859134858474135
2023-01-24 10:03:24.173146: step: 1048/529, loss: 0.0038641036953777075
2023-01-24 10:03:25.289826: step: 1052/529, loss: 0.005401624366641045
2023-01-24 10:03:26.412102: step: 1056/529, loss: 0.002669194247573614
2023-01-24 10:03:27.538872: step: 1060/529, loss: 0.00031682837288826704
2023-01-24 10:03:28.646380: step: 1064/529, loss: 0.004601342137902975
2023-01-24 10:03:29.744594: step: 1068/529, loss: 0.00548685435205698
2023-01-24 10:03:30.851179: step: 1072/529, loss: 0.0019524060189723969
2023-01-24 10:03:31.955245: step: 1076/529, loss: 0.0007251353235915303
2023-01-24 10:03:33.054249: step: 1080/529, loss: 0.007719394285231829
2023-01-24 10:03:34.156605: step: 1084/529, loss: 0.0036274902522563934
2023-01-24 10:03:35.244757: step: 1088/529, loss: 0.0010000169277191162
2023-01-24 10:03:36.367066: step: 1092/529, loss: 0.0020134553778916597
2023-01-24 10:03:37.478253: step: 1096/529, loss: 0.004333728924393654
2023-01-24 10:03:38.586965: step: 1100/529, loss: 0.010719121433794498
2023-01-24 10:03:39.691406: step: 1104/529, loss: 0.00137236132286489
2023-01-24 10:03:40.810609: step: 1108/529, loss: 0.005249538458883762
2023-01-24 10:03:41.926617: step: 1112/529, loss: 0.00045455145300365984
2023-01-24 10:03:43.028739: step: 1116/529, loss: 0.0009653582819737494
2023-01-24 10:03:44.115145: step: 1120/529, loss: 0.00039493918302468956
2023-01-24 10:03:45.258793: step: 1124/529, loss: 0.00794602744281292
2023-01-24 10:03:46.347332: step: 1128/529, loss: 0.003449873998761177
2023-01-24 10:03:47.485239: step: 1132/529, loss: 0.0024797539226710796
2023-01-24 10:03:48.598901: step: 1136/529, loss: 0.03432765230536461
2023-01-24 10:03:49.725854: step: 1140/529, loss: 0.007650433573871851
2023-01-24 10:03:50.826436: step: 1144/529, loss: 0.000994968693703413
2023-01-24 10:03:51.942927: step: 1148/529, loss: 0.0015026867622509599
2023-01-24 10:03:53.061771: step: 1152/529, loss: 0.0014761639758944511
2023-01-24 10:03:54.172125: step: 1156/529, loss: 0.004784488584846258
2023-01-24 10:03:55.288044: step: 1160/529, loss: 0.005220495630055666
2023-01-24 10:03:56.391872: step: 1164/529, loss: 3.091091275564395e-05
2023-01-24 10:03:57.515949: step: 1168/529, loss: 0.014425866305828094
2023-01-24 10:03:58.619576: step: 1172/529, loss: 0.00026621806318871677
2023-01-24 10:03:59.724109: step: 1176/529, loss: 0.011068666353821754
2023-01-24 10:04:00.841339: step: 1180/529, loss: 0.00034518170286901295
2023-01-24 10:04:01.951224: step: 1184/529, loss: 0.007991258054971695
2023-01-24 10:04:03.082181: step: 1188/529, loss: 0.004384639207273722
2023-01-24 10:04:04.204032: step: 1192/529, loss: 0.0009908170904964209
2023-01-24 10:04:05.336806: step: 1196/529, loss: 0.00015601824270561337
2023-01-24 10:04:06.439962: step: 1200/529, loss: 0.0038968706503510475
2023-01-24 10:04:07.546104: step: 1204/529, loss: 0.007342000026255846
2023-01-24 10:04:08.673701: step: 1208/529, loss: 0.0006651327712461352
2023-01-24 10:04:09.768190: step: 1212/529, loss: 0.0007706377655267715
2023-01-24 10:04:10.885650: step: 1216/529, loss: 8.94587064976804e-05
2023-01-24 10:04:11.982783: step: 1220/529, loss: 0.02960543893277645
2023-01-24 10:04:13.089811: step: 1224/529, loss: 0.001897280104458332
2023-01-24 10:04:14.191519: step: 1228/529, loss: 0.011684943921864033
2023-01-24 10:04:15.337707: step: 1232/529, loss: 0.001498076831921935
2023-01-24 10:04:16.455447: step: 1236/529, loss: 0.006867724470794201
2023-01-24 10:04:17.563834: step: 1240/529, loss: 0.0002791465085465461
2023-01-24 10:04:18.708252: step: 1244/529, loss: 0.010626512579619884
2023-01-24 10:04:19.803046: step: 1248/529, loss: 0.005484021268785
2023-01-24 10:04:20.924179: step: 1252/529, loss: 0.004931524395942688
2023-01-24 10:04:22.027274: step: 1256/529, loss: 0.02793239988386631
2023-01-24 10:04:23.139992: step: 1260/529, loss: 0.0033209649845957756
2023-01-24 10:04:24.245290: step: 1264/529, loss: 0.008885874412953854
2023-01-24 10:04:25.368665: step: 1268/529, loss: 0.004936038050800562
2023-01-24 10:04:26.471404: step: 1272/529, loss: 0.004901057109236717
2023-01-24 10:04:27.595100: step: 1276/529, loss: 0.001988119212910533
2023-01-24 10:04:28.704102: step: 1280/529, loss: 0.0009802528657019138
2023-01-24 10:04:29.824043: step: 1284/529, loss: 0.0013996611814945936
2023-01-24 10:04:30.929703: step: 1288/529, loss: 0.002583850407972932
2023-01-24 10:04:32.079953: step: 1292/529, loss: 0.006440429948270321
2023-01-24 10:04:33.160710: step: 1296/529, loss: 0.004300088156014681
2023-01-24 10:04:34.279354: step: 1300/529, loss: 0.005393211729824543
2023-01-24 10:04:35.404339: step: 1304/529, loss: 0.0017906812718138099
2023-01-24 10:04:36.515886: step: 1308/529, loss: 0.004659599158912897
2023-01-24 10:04:37.640017: step: 1312/529, loss: 0.005110634956508875
2023-01-24 10:04:38.765920: step: 1316/529, loss: 0.0057045090943574905
2023-01-24 10:04:39.880296: step: 1320/529, loss: 0.0021445073653012514
2023-01-24 10:04:40.988686: step: 1324/529, loss: 0.004785752389580011
2023-01-24 10:04:42.099734: step: 1328/529, loss: 0.0022379099391400814
2023-01-24 10:04:43.213271: step: 1332/529, loss: 0.024793200194835663
2023-01-24 10:04:44.346344: step: 1336/529, loss: 0.027622297406196594
2023-01-24 10:04:45.433127: step: 1340/529, loss: 0.0011838177451863885
2023-01-24 10:04:46.542484: step: 1344/529, loss: 0.007566556334495544
2023-01-24 10:04:47.655506: step: 1348/529, loss: 0.011250466108322144
2023-01-24 10:04:48.777235: step: 1352/529, loss: 0.0006066447240300477
2023-01-24 10:04:49.876586: step: 1356/529, loss: 0.0034677174407988787
2023-01-24 10:04:50.976939: step: 1360/529, loss: 0.011056795716285706
2023-01-24 10:04:52.107504: step: 1364/529, loss: 0.010419712401926517
2023-01-24 10:04:53.217129: step: 1368/529, loss: 3.5082746762782335e-05
2023-01-24 10:04:54.323323: step: 1372/529, loss: 0.0002436417416902259
2023-01-24 10:04:55.428919: step: 1376/529, loss: 0.013517429120838642
2023-01-24 10:04:56.531610: step: 1380/529, loss: 0.008008817210793495
2023-01-24 10:04:57.654361: step: 1384/529, loss: 0.015433688648045063
2023-01-24 10:04:58.759772: step: 1388/529, loss: 0.00700283283367753
2023-01-24 10:04:59.857025: step: 1392/529, loss: 0.00032517960062250495
2023-01-24 10:05:01.021923: step: 1396/529, loss: 0.007295718416571617
2023-01-24 10:05:02.137162: step: 1400/529, loss: 0.0061205471865832806
2023-01-24 10:05:03.262912: step: 1404/529, loss: 0.0005795481847599149
2023-01-24 10:05:04.383526: step: 1408/529, loss: 0.003091163234785199
2023-01-24 10:05:05.504845: step: 1412/529, loss: 0.00026308713131584227
2023-01-24 10:05:06.600516: step: 1416/529, loss: 0.002890215488150716
2023-01-24 10:05:07.718949: step: 1420/529, loss: 0.00016771670198068023
2023-01-24 10:05:08.861846: step: 1424/529, loss: 0.01871509477496147
2023-01-24 10:05:09.968483: step: 1428/529, loss: 0.00030465179588645697
2023-01-24 10:05:11.077855: step: 1432/529, loss: 0.0032001181971281767
2023-01-24 10:05:12.190542: step: 1436/529, loss: 0.002943756990134716
2023-01-24 10:05:13.302432: step: 1440/529, loss: 2.249479621241335e-06
2023-01-24 10:05:14.416169: step: 1444/529, loss: 1.8380209439783357e-05
2023-01-24 10:05:15.498907: step: 1448/529, loss: 0.00759240472689271
2023-01-24 10:05:16.591994: step: 1452/529, loss: 0.0138852559030056
2023-01-24 10:05:17.692663: step: 1456/529, loss: 0.0015683637466281652
2023-01-24 10:05:18.808876: step: 1460/529, loss: 0.02113204635679722
2023-01-24 10:05:19.931534: step: 1464/529, loss: 0.02652093954384327
2023-01-24 10:05:21.056628: step: 1468/529, loss: 0.003285401500761509
2023-01-24 10:05:22.173348: step: 1472/529, loss: 0.0012357857776805758
2023-01-24 10:05:23.278784: step: 1476/529, loss: 0.009123251773416996
2023-01-24 10:05:24.402364: step: 1480/529, loss: 0.00026756885927170515
2023-01-24 10:05:25.510877: step: 1484/529, loss: 0.003258280921727419
2023-01-24 10:05:26.609762: step: 1488/529, loss: 0.0022948661353439093
2023-01-24 10:05:27.735101: step: 1492/529, loss: 5.1069684559479356e-05
2023-01-24 10:05:28.842793: step: 1496/529, loss: 0.0007203823770396411
2023-01-24 10:05:29.956470: step: 1500/529, loss: 0.002969960682094097
2023-01-24 10:05:31.075904: step: 1504/529, loss: 0.0036475860979408026
2023-01-24 10:05:32.181694: step: 1508/529, loss: 0.001101042260415852
2023-01-24 10:05:33.307343: step: 1512/529, loss: 0.003134277882054448
2023-01-24 10:05:34.434546: step: 1516/529, loss: 0.0024678397458046675
2023-01-24 10:05:35.529420: step: 1520/529, loss: 0.006030470132827759
2023-01-24 10:05:36.643613: step: 1524/529, loss: 0.007488882169127464
2023-01-24 10:05:37.762878: step: 1528/529, loss: 0.0006192834116518497
2023-01-24 10:05:38.860137: step: 1532/529, loss: 0.0011881602695211768
2023-01-24 10:05:39.963170: step: 1536/529, loss: 0.0005812318413518369
2023-01-24 10:05:41.082254: step: 1540/529, loss: 0.0012676113983616233
2023-01-24 10:05:42.190133: step: 1544/529, loss: 0.0013949732528999448
2023-01-24 10:05:43.298623: step: 1548/529, loss: 0.008488287217915058
2023-01-24 10:05:44.390997: step: 1552/529, loss: 1.2618501386896241e-05
2023-01-24 10:05:45.495381: step: 1556/529, loss: 0.005794909317046404
2023-01-24 10:05:46.593174: step: 1560/529, loss: 0.0014684823108837008
2023-01-24 10:05:47.691338: step: 1564/529, loss: 0.0057525066658854485
2023-01-24 10:05:48.825603: step: 1568/529, loss: 0.005236676428467035
2023-01-24 10:05:49.947281: step: 1572/529, loss: 0.0036738950293511152
2023-01-24 10:05:51.041214: step: 1576/529, loss: 0.0008385474211536348
2023-01-24 10:05:52.140680: step: 1580/529, loss: 0.001723063993267715
2023-01-24 10:05:53.250662: step: 1584/529, loss: 0.008128863759338856
2023-01-24 10:05:54.353214: step: 1588/529, loss: 0.003797698300331831
2023-01-24 10:05:55.471463: step: 1592/529, loss: 0.008646626025438309
2023-01-24 10:05:56.564991: step: 1596/529, loss: 0.002870364813134074
2023-01-24 10:05:57.673803: step: 1600/529, loss: 0.00034339699777774513
2023-01-24 10:05:58.802798: step: 1604/529, loss: 0.0035608645994216204
2023-01-24 10:05:59.919450: step: 1608/529, loss: 0.007049956824630499
2023-01-24 10:06:01.029531: step: 1612/529, loss: 0.002489047357812524
2023-01-24 10:06:02.154116: step: 1616/529, loss: 0.020995063707232475
2023-01-24 10:06:03.279341: step: 1620/529, loss: 0.018273737281560898
2023-01-24 10:06:04.406542: step: 1624/529, loss: 0.0007087595877237618
2023-01-24 10:06:05.516945: step: 1628/529, loss: 0.008334141224622726
2023-01-24 10:06:06.628361: step: 1632/529, loss: 0.00499467458575964
2023-01-24 10:06:07.739131: step: 1636/529, loss: 0.0026572425849735737
2023-01-24 10:06:08.868763: step: 1640/529, loss: 0.004773653578013182
2023-01-24 10:06:09.970367: step: 1644/529, loss: 0.00435072835534811
2023-01-24 10:06:11.081464: step: 1648/529, loss: 0.00041979688103310764
2023-01-24 10:06:12.183864: step: 1652/529, loss: 0.003310898318886757
2023-01-24 10:06:13.295909: step: 1656/529, loss: 0.01849922351539135
2023-01-24 10:06:14.397656: step: 1660/529, loss: 0.0005802304367534816
2023-01-24 10:06:15.529227: step: 1664/529, loss: 0.003721635788679123
2023-01-24 10:06:16.633284: step: 1668/529, loss: 0.0036931943614035845
2023-01-24 10:06:17.759505: step: 1672/529, loss: 0.0017643123865127563
2023-01-24 10:06:18.859704: step: 1676/529, loss: 0.001096975291147828
2023-01-24 10:06:19.985143: step: 1680/529, loss: 0.027191104367375374
2023-01-24 10:06:21.102384: step: 1684/529, loss: 0.000802180846221745
2023-01-24 10:06:22.210541: step: 1688/529, loss: 0.009118456393480301
2023-01-24 10:06:23.315211: step: 1692/529, loss: 0.00022893202549312264
2023-01-24 10:06:24.431269: step: 1696/529, loss: 0.0023596887476742268
2023-01-24 10:06:25.549438: step: 1700/529, loss: 0.004643856082111597
2023-01-24 10:06:26.642954: step: 1704/529, loss: 0.0035202878061681986
2023-01-24 10:06:27.757593: step: 1708/529, loss: 0.0009159942273981869
2023-01-24 10:06:28.866669: step: 1712/529, loss: 5.7536151871318e-05
2023-01-24 10:06:29.984141: step: 1716/529, loss: 0.00593317486345768
2023-01-24 10:06:31.084102: step: 1720/529, loss: 0.0013714809902012348
2023-01-24 10:06:32.201832: step: 1724/529, loss: 0.009653424844145775
2023-01-24 10:06:33.316737: step: 1728/529, loss: 0.0015635871095582843
2023-01-24 10:06:34.415360: step: 1732/529, loss: 0.00043258399819023907
2023-01-24 10:06:35.531560: step: 1736/529, loss: 0.0036243880167603493
2023-01-24 10:06:36.646307: step: 1740/529, loss: 0.032035134732723236
2023-01-24 10:06:37.740986: step: 1744/529, loss: 0.0016696734819561243
2023-01-24 10:06:38.848686: step: 1748/529, loss: 0.00035671357181854546
2023-01-24 10:06:39.954897: step: 1752/529, loss: 0.0010831819381564856
2023-01-24 10:06:41.048625: step: 1756/529, loss: 0.002690880326554179
2023-01-24 10:06:42.137698: step: 1760/529, loss: 0.00019929495465476066
2023-01-24 10:06:43.269084: step: 1764/529, loss: 0.005031203385442495
2023-01-24 10:06:44.370056: step: 1768/529, loss: 0.006407430395483971
2023-01-24 10:06:45.482364: step: 1772/529, loss: 0.005499716382473707
2023-01-24 10:06:46.610439: step: 1776/529, loss: 0.034918952733278275
2023-01-24 10:06:47.701312: step: 1780/529, loss: 0.007672132924199104
2023-01-24 10:06:48.792343: step: 1784/529, loss: 0.0007506535039283335
2023-01-24 10:06:49.919074: step: 1788/529, loss: 0.002601213753223419
2023-01-24 10:06:51.006331: step: 1792/529, loss: 0.0023681249003857374
2023-01-24 10:06:52.123610: step: 1796/529, loss: 0.010361873544752598
2023-01-24 10:06:53.266390: step: 1800/529, loss: 0.004262631293386221
2023-01-24 10:06:54.384137: step: 1804/529, loss: 0.002712997840717435
2023-01-24 10:06:55.481773: step: 1808/529, loss: 0.002933068433776498
2023-01-24 10:06:56.596459: step: 1812/529, loss: 0.0049403076991438866
2023-01-24 10:06:57.696384: step: 1816/529, loss: 0.00030556172714568675
2023-01-24 10:06:58.840545: step: 1820/529, loss: 0.00022162875393405557
2023-01-24 10:06:59.957544: step: 1824/529, loss: 9.264702384825796e-05
2023-01-24 10:07:01.048325: step: 1828/529, loss: 0.0036450079642236233
2023-01-24 10:07:02.184446: step: 1832/529, loss: 0.004458323121070862
2023-01-24 10:07:03.302208: step: 1836/529, loss: 0.0023477349895983934
2023-01-24 10:07:04.414655: step: 1840/529, loss: 0.008056516759097576
2023-01-24 10:07:05.520019: step: 1844/529, loss: 0.006951354444026947
2023-01-24 10:07:06.629958: step: 1848/529, loss: 0.0019325959729030728
2023-01-24 10:07:07.743047: step: 1852/529, loss: 0.009846577420830727
2023-01-24 10:07:08.892268: step: 1856/529, loss: 0.0029493931215256453
2023-01-24 10:07:10.000967: step: 1860/529, loss: 0.00021619869221467525
2023-01-24 10:07:11.101986: step: 1864/529, loss: 0.000570410571526736
2023-01-24 10:07:12.209146: step: 1868/529, loss: 0.00903247483074665
2023-01-24 10:07:13.328041: step: 1872/529, loss: 0.0001422100467607379
2023-01-24 10:07:14.423848: step: 1876/529, loss: 0.001439129700884223
2023-01-24 10:07:15.535197: step: 1880/529, loss: 0.007189551368355751
2023-01-24 10:07:16.632002: step: 1884/529, loss: 0.0007763136527501047
2023-01-24 10:07:17.748870: step: 1888/529, loss: 0.000886360474396497
2023-01-24 10:07:18.850219: step: 1892/529, loss: 0.0068611567839980125
2023-01-24 10:07:19.964730: step: 1896/529, loss: 0.0014084739377722144
2023-01-24 10:07:21.058415: step: 1900/529, loss: 0.0006912951939739287
2023-01-24 10:07:22.163707: step: 1904/529, loss: 0.004323470406234264
2023-01-24 10:07:23.271992: step: 1908/529, loss: 0.007418234366923571
2023-01-24 10:07:24.367563: step: 1912/529, loss: 0.0005564384628087282
2023-01-24 10:07:25.476272: step: 1916/529, loss: 0.005541039165109396
2023-01-24 10:07:26.587027: step: 1920/529, loss: 0.0001588106097187847
2023-01-24 10:07:27.703180: step: 1924/529, loss: 0.0011011230526492
2023-01-24 10:07:28.826116: step: 1928/529, loss: 4.149424057686701e-06
2023-01-24 10:07:29.898244: step: 1932/529, loss: 0.00012599601177498698
2023-01-24 10:07:30.993097: step: 1936/529, loss: 0.0005975664826110005
2023-01-24 10:07:32.118022: step: 1940/529, loss: 0.010239941067993641
2023-01-24 10:07:33.252376: step: 1944/529, loss: 0.001049767597578466
2023-01-24 10:07:34.368611: step: 1948/529, loss: 0.007149444427341223
2023-01-24 10:07:35.468100: step: 1952/529, loss: 0.005090836901217699
2023-01-24 10:07:36.578927: step: 1956/529, loss: 0.0072985077276825905
2023-01-24 10:07:37.692380: step: 1960/529, loss: 0.006151984911412001
2023-01-24 10:07:38.813120: step: 1964/529, loss: 0.0016086878022179008
2023-01-24 10:07:39.929768: step: 1968/529, loss: 0.006416039075702429
2023-01-24 10:07:41.044566: step: 1972/529, loss: 0.0075052035972476006
2023-01-24 10:07:42.143145: step: 1976/529, loss: 0.0005445227143354714
2023-01-24 10:07:43.243875: step: 1980/529, loss: 0.0035929791629314423
2023-01-24 10:07:44.334909: step: 1984/529, loss: 2.261967892991379e-05
2023-01-24 10:07:45.432811: step: 1988/529, loss: 0.02420150674879551
2023-01-24 10:07:46.533427: step: 1992/529, loss: 0.0
2023-01-24 10:07:47.650870: step: 1996/529, loss: 0.003548518754541874
2023-01-24 10:07:48.786779: step: 2000/529, loss: 0.02597544901072979
2023-01-24 10:07:49.928304: step: 2004/529, loss: 0.002890253672376275
2023-01-24 10:07:51.032111: step: 2008/529, loss: 0.0014319369802251458
2023-01-24 10:07:52.149183: step: 2012/529, loss: 7.815883873263374e-05
2023-01-24 10:07:53.263837: step: 2016/529, loss: 0.001766129513271153
2023-01-24 10:07:54.409626: step: 2020/529, loss: 0.005064873490482569
2023-01-24 10:07:55.492728: step: 2024/529, loss: 0.0001890771818580106
2023-01-24 10:07:56.607187: step: 2028/529, loss: 0.0013856698060408235
2023-01-24 10:07:57.727214: step: 2032/529, loss: 0.0022560851648449898
2023-01-24 10:07:58.819275: step: 2036/529, loss: 0.001329240039922297
2023-01-24 10:07:59.932365: step: 2040/529, loss: 0.001558055286295712
2023-01-24 10:08:01.049604: step: 2044/529, loss: 0.0001524899562355131
2023-01-24 10:08:02.187024: step: 2048/529, loss: 0.006990751251578331
2023-01-24 10:08:03.291342: step: 2052/529, loss: 0.004695339128375053
2023-01-24 10:08:04.415564: step: 2056/529, loss: 0.05430683493614197
2023-01-24 10:08:05.530574: step: 2060/529, loss: 0.009949995204806328
2023-01-24 10:08:06.630238: step: 2064/529, loss: 0.0011440449161455035
2023-01-24 10:08:07.733179: step: 2068/529, loss: 0.0028380993753671646
2023-01-24 10:08:08.855749: step: 2072/529, loss: 0.00656010489910841
2023-01-24 10:08:09.976212: step: 2076/529, loss: 0.0033120117150247097
2023-01-24 10:08:11.057496: step: 2080/529, loss: 0.00010947092960122973
2023-01-24 10:08:12.167454: step: 2084/529, loss: 0.0005642026080749929
2023-01-24 10:08:13.259167: step: 2088/529, loss: 0.008556976914405823
2023-01-24 10:08:14.361915: step: 2092/529, loss: 8.561924187233672e-05
2023-01-24 10:08:15.452544: step: 2096/529, loss: 0.002317034639418125
2023-01-24 10:08:16.556818: step: 2100/529, loss: 0.0016840959433466196
2023-01-24 10:08:17.660225: step: 2104/529, loss: 0.0010007693199440837
2023-01-24 10:08:18.741004: step: 2108/529, loss: 0.002132132649421692
2023-01-24 10:08:19.873633: step: 2112/529, loss: 0.0031894545536488295
2023-01-24 10:08:20.986306: step: 2116/529, loss: 1.4975915291870479e-05
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3810197789878283, 'r': 0.32245696665763074, 'f1': 0.3493007634708559}, 'combined': 0.2573795099258938, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.39793570677731727, 'r': 0.2837964355959551, 'f1': 0.3313111650761074}, 'combined': 0.20363515511994895, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38065598957143076, 'r': 0.3380398541165647, 'f1': 0.358084428380763}, 'combined': 0.2638516840700359, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38025646426598636, 'r': 0.2896407557104004, 'f1': 0.3288199036790969}, 'combined': 0.20210394079788396, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4122747747747748, 'r': 0.34734345351043644, 'f1': 0.37703398558187434}, 'combined': 0.2778145156919074, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39753402780646163, 'r': 0.2841989366900614, 'f1': 0.3314457533505112}, 'combined': 0.20471649471649225, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.32608695652173914, 'f1': 0.3658536585365854}, 'combined': 0.1829268292682927, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3739808168857774, 'r': 0.3328216377977791, 'f1': 0.35220281750889476}, 'combined': 0.2595178655328698, 'stategy': 1, 'epoch': 12}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38254895335211175, 'r': 0.29072394461854595, 'f1': 0.3303746253961615}, 'combined': 0.2030595258532505, 'stategy': 1, 'epoch': 12}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 10:10:42.505029: step: 4/529, loss: 0.004017682746052742
2023-01-24 10:10:43.605991: step: 8/529, loss: 0.0009242295636795461
2023-01-24 10:10:44.681918: step: 12/529, loss: 0.006270421668887138
2023-01-24 10:10:45.781615: step: 16/529, loss: 0.0015395382652059197
2023-01-24 10:10:46.888418: step: 20/529, loss: 0.005934928078204393
2023-01-24 10:10:47.969861: step: 24/529, loss: 0.0001630986953387037
2023-01-24 10:10:49.083773: step: 28/529, loss: 0.000970147957559675
2023-01-24 10:10:50.183547: step: 32/529, loss: 0.01720673404633999
2023-01-24 10:10:51.293617: step: 36/529, loss: 0.0018050681101158261
2023-01-24 10:10:52.393206: step: 40/529, loss: 7.151860336307436e-05
2023-01-24 10:10:53.506251: step: 44/529, loss: 0.006344522815197706
2023-01-24 10:10:54.623067: step: 48/529, loss: 0.00037268741289153695
2023-01-24 10:10:55.764406: step: 52/529, loss: 0.01832570508122444
2023-01-24 10:10:56.853640: step: 56/529, loss: 0.0050773825496435165
2023-01-24 10:10:57.962346: step: 60/529, loss: 0.0004603034467436373
2023-01-24 10:10:59.058524: step: 64/529, loss: 0.0024300641380250454
2023-01-24 10:11:00.160799: step: 68/529, loss: 0.003232666989788413
2023-01-24 10:11:01.287498: step: 72/529, loss: 0.0031463447958230972
2023-01-24 10:11:02.395455: step: 76/529, loss: 0.00031368760392069817
2023-01-24 10:11:03.509001: step: 80/529, loss: 0.00574699928984046
2023-01-24 10:11:04.591290: step: 84/529, loss: 0.0033522658050060272
2023-01-24 10:11:05.711345: step: 88/529, loss: 0.012863255105912685
2023-01-24 10:11:06.820797: step: 92/529, loss: 0.0013765029143542051
2023-01-24 10:11:07.930347: step: 96/529, loss: 0.0008481140830554068
2023-01-24 10:11:09.026561: step: 100/529, loss: 0.002638123696669936
2023-01-24 10:11:10.148865: step: 104/529, loss: 0.00043326185550540686
2023-01-24 10:11:11.238165: step: 108/529, loss: 0.0025408542715013027
2023-01-24 10:11:12.363058: step: 112/529, loss: 0.010455128736793995
2023-01-24 10:11:13.465598: step: 116/529, loss: 0.00810779444873333
2023-01-24 10:11:14.552449: step: 120/529, loss: 0.0012793648056685925
2023-01-24 10:11:15.670901: step: 124/529, loss: 0.006055021192878485
2023-01-24 10:11:16.773800: step: 128/529, loss: 0.008519347757101059
2023-01-24 10:11:17.880953: step: 132/529, loss: 0.0017153981607407331
2023-01-24 10:11:19.003724: step: 136/529, loss: 0.011559495702385902
2023-01-24 10:11:20.113476: step: 140/529, loss: 0.007168784271925688
2023-01-24 10:11:21.192273: step: 144/529, loss: 0.0007770570227876306
2023-01-24 10:11:22.296411: step: 148/529, loss: 0.002134120324626565
2023-01-24 10:11:23.414408: step: 152/529, loss: 0.0033081024885177612
2023-01-24 10:11:24.514320: step: 156/529, loss: 0.012740008533000946
2023-01-24 10:11:25.609596: step: 160/529, loss: 0.003394529689103365
2023-01-24 10:11:26.726803: step: 164/529, loss: 0.005497364792972803
2023-01-24 10:11:27.834083: step: 168/529, loss: 0.0025131255388259888
2023-01-24 10:11:28.938274: step: 172/529, loss: 0.0007885585655458272
2023-01-24 10:11:30.033659: step: 176/529, loss: 0.004025578033179045
2023-01-24 10:11:31.137183: step: 180/529, loss: 0.0020649516955018044
2023-01-24 10:11:32.246649: step: 184/529, loss: 0.0015408031176775694
2023-01-24 10:11:33.346057: step: 188/529, loss: 0.0006245877593755722
2023-01-24 10:11:34.442055: step: 192/529, loss: 1.6311241779476404e-05
2023-01-24 10:11:35.538067: step: 196/529, loss: 0.00018585943325888366
2023-01-24 10:11:36.650728: step: 200/529, loss: 0.0026932486798614264
2023-01-24 10:11:37.752530: step: 204/529, loss: 0.004115288611501455
2023-01-24 10:11:38.871351: step: 208/529, loss: 0.0008540253038518131
2023-01-24 10:11:40.010256: step: 212/529, loss: 0.0013984618708491325
2023-01-24 10:11:41.132351: step: 216/529, loss: 0.008898225612938404
2023-01-24 10:11:42.240417: step: 220/529, loss: 0.004957273602485657
2023-01-24 10:11:43.362485: step: 224/529, loss: 0.00038612468051724136
2023-01-24 10:11:44.458499: step: 228/529, loss: 0.0015860882122069597
2023-01-24 10:11:45.568570: step: 232/529, loss: 0.0028882650658488274
2023-01-24 10:11:46.679323: step: 236/529, loss: 0.0007981908274814487
2023-01-24 10:11:47.763730: step: 240/529, loss: 0.012773731723427773
2023-01-24 10:11:48.849111: step: 244/529, loss: 0.0013330148067325354
2023-01-24 10:11:49.952254: step: 248/529, loss: 0.004262182861566544
2023-01-24 10:11:51.106289: step: 252/529, loss: 0.001346705132164061
2023-01-24 10:11:52.216128: step: 256/529, loss: 0.010781573131680489
2023-01-24 10:11:53.313750: step: 260/529, loss: 0.005327738355845213
2023-01-24 10:11:54.448305: step: 264/529, loss: 0.005056611727923155
2023-01-24 10:11:55.559073: step: 268/529, loss: 0.01770065352320671
2023-01-24 10:11:56.696018: step: 272/529, loss: 0.0015972615219652653
2023-01-24 10:11:57.813992: step: 276/529, loss: 0.012061548419296741
2023-01-24 10:11:58.921397: step: 280/529, loss: 0.001330185099504888
2023-01-24 10:12:00.027887: step: 284/529, loss: 0.0001306285266764462
2023-01-24 10:12:01.133027: step: 288/529, loss: 0.004532399587333202
2023-01-24 10:12:02.257996: step: 292/529, loss: 0.0007070941501297057
2023-01-24 10:12:03.368189: step: 296/529, loss: 0.0007744791219010949
2023-01-24 10:12:04.490400: step: 300/529, loss: 1.813436028896831e-05
2023-01-24 10:12:05.594273: step: 304/529, loss: 6.861891597509384e-05
2023-01-24 10:12:06.689426: step: 308/529, loss: 0.005068132653832436
2023-01-24 10:12:07.775301: step: 312/529, loss: 0.0022420270834118128
2023-01-24 10:12:08.866480: step: 316/529, loss: 0.0018985880305990577
2023-01-24 10:12:09.975861: step: 320/529, loss: 0.0017229585209861398
2023-01-24 10:12:11.090157: step: 324/529, loss: 0.006043081171810627
2023-01-24 10:12:12.194648: step: 328/529, loss: 0.0029211172368377447
2023-01-24 10:12:13.301308: step: 332/529, loss: 1.9933515886805253e-06
2023-01-24 10:12:14.417939: step: 336/529, loss: 0.00656077079474926
2023-01-24 10:12:15.517145: step: 340/529, loss: 0.0002971893409267068
2023-01-24 10:12:16.621580: step: 344/529, loss: 0.0012217750772833824
2023-01-24 10:12:17.748566: step: 348/529, loss: 0.003328346647322178
2023-01-24 10:12:18.842961: step: 352/529, loss: 0.0028509267140179873
2023-01-24 10:12:19.961587: step: 356/529, loss: 0.0023718641605228186
2023-01-24 10:12:21.063436: step: 360/529, loss: 0.000895620440132916
2023-01-24 10:12:22.171502: step: 364/529, loss: 0.000947058666497469
2023-01-24 10:12:23.290969: step: 368/529, loss: 0.01822621561586857
2023-01-24 10:12:24.404781: step: 372/529, loss: 0.002414952265098691
2023-01-24 10:12:25.533407: step: 376/529, loss: 0.0064300671219825745
2023-01-24 10:12:26.624697: step: 380/529, loss: 0.002475287299603224
2023-01-24 10:12:27.733626: step: 384/529, loss: 0.0016879403265193105
2023-01-24 10:12:28.821453: step: 388/529, loss: 0.0007610544562339783
2023-01-24 10:12:29.928284: step: 392/529, loss: 0.0009465606999583542
2023-01-24 10:12:31.040747: step: 396/529, loss: 0.00015459379937965423
2023-01-24 10:12:32.162530: step: 400/529, loss: 0.00617228215560317
2023-01-24 10:12:33.275041: step: 404/529, loss: 0.0
2023-01-24 10:12:34.384406: step: 408/529, loss: 0.0006017853738740087
2023-01-24 10:12:35.487188: step: 412/529, loss: 0.003774944692850113
2023-01-24 10:12:36.599133: step: 416/529, loss: 0.00046165072126314044
2023-01-24 10:12:37.702053: step: 420/529, loss: 0.00027317824424244463
2023-01-24 10:12:38.804695: step: 424/529, loss: 0.004298737272620201
2023-01-24 10:12:39.932243: step: 428/529, loss: 0.010374879464507103
2023-01-24 10:12:41.011824: step: 432/529, loss: 0.00047678101691417396
2023-01-24 10:12:42.115874: step: 436/529, loss: 0.00044412966235540807
2023-01-24 10:12:43.239511: step: 440/529, loss: 0.028463061898946762
2023-01-24 10:12:44.336159: step: 444/529, loss: 0.0014933921629562974
2023-01-24 10:12:45.440238: step: 448/529, loss: 0.0002521930728107691
2023-01-24 10:12:46.546036: step: 452/529, loss: 0.002302172826603055
2023-01-24 10:12:47.639414: step: 456/529, loss: 0.007455112412571907
2023-01-24 10:12:48.745975: step: 460/529, loss: 0.010368739254772663
2023-01-24 10:12:49.864692: step: 464/529, loss: 0.01615116186439991
2023-01-24 10:12:50.980369: step: 468/529, loss: 0.00352029618807137
2023-01-24 10:12:52.092912: step: 472/529, loss: 0.00747502688318491
2023-01-24 10:12:53.219280: step: 476/529, loss: 0.0015371283516287804
2023-01-24 10:12:54.342545: step: 480/529, loss: 0.004901760723441839
2023-01-24 10:12:55.452411: step: 484/529, loss: 0.013774470426142216
2023-01-24 10:12:56.568668: step: 488/529, loss: 0.0021839861292392015
2023-01-24 10:12:57.653634: step: 492/529, loss: 0.0003969954268541187
2023-01-24 10:12:58.750218: step: 496/529, loss: 0.004497201181948185
2023-01-24 10:12:59.888662: step: 500/529, loss: 0.0002066479210043326
2023-01-24 10:13:01.020425: step: 504/529, loss: 0.003468351671472192
2023-01-24 10:13:02.133065: step: 508/529, loss: 0.00557201961055398
2023-01-24 10:13:03.253216: step: 512/529, loss: 0.0183720663189888
2023-01-24 10:13:04.347074: step: 516/529, loss: 0.0032495451159775257
2023-01-24 10:13:05.464508: step: 520/529, loss: 0.0011680229799821973
2023-01-24 10:13:06.543919: step: 524/529, loss: 0.0007451308774761856
2023-01-24 10:13:07.648912: step: 528/529, loss: 0.010524425655603409
2023-01-24 10:13:08.752561: step: 532/529, loss: 0.007406124845147133
2023-01-24 10:13:09.877393: step: 536/529, loss: 0.013637742958962917
2023-01-24 10:13:10.979868: step: 540/529, loss: 0.00026450137374922633
2023-01-24 10:13:12.084426: step: 544/529, loss: 0.015263236127793789
2023-01-24 10:13:13.199520: step: 548/529, loss: 0.000903081614524126
2023-01-24 10:13:14.299130: step: 552/529, loss: 6.866855983389542e-05
2023-01-24 10:13:15.399068: step: 556/529, loss: 0.0006684183026663959
2023-01-24 10:13:16.526033: step: 560/529, loss: 0.0023486309219151735
2023-01-24 10:13:17.653844: step: 564/529, loss: 0.008993650786578655
2023-01-24 10:13:18.758120: step: 568/529, loss: 0.004085613414645195
2023-01-24 10:13:19.860512: step: 572/529, loss: 0.0003004330792464316
2023-01-24 10:13:20.965025: step: 576/529, loss: 0.001640260685235262
2023-01-24 10:13:22.124598: step: 580/529, loss: 0.0027144039049744606
2023-01-24 10:13:23.245037: step: 584/529, loss: 0.01900293119251728
2023-01-24 10:13:24.348324: step: 588/529, loss: 0.0005381632363423705
2023-01-24 10:13:25.479911: step: 592/529, loss: 0.00285432324744761
2023-01-24 10:13:26.604765: step: 596/529, loss: 0.0058250403963029385
2023-01-24 10:13:27.701973: step: 600/529, loss: 0.0029124896973371506
2023-01-24 10:13:28.826827: step: 604/529, loss: 0.03352838754653931
2023-01-24 10:13:29.950895: step: 608/529, loss: 0.013501377776265144
2023-01-24 10:13:31.054898: step: 612/529, loss: 0.015476818196475506
2023-01-24 10:13:32.179491: step: 616/529, loss: 0.029871920123696327
2023-01-24 10:13:33.299729: step: 620/529, loss: 0.00037643263931386173
2023-01-24 10:13:34.407166: step: 624/529, loss: 0.0020939160604029894
2023-01-24 10:13:35.529476: step: 628/529, loss: 0.0099239656701684
2023-01-24 10:13:36.660057: step: 632/529, loss: 0.0005623669712804258
2023-01-24 10:13:37.769762: step: 636/529, loss: 0.009362041018903255
2023-01-24 10:13:38.867731: step: 640/529, loss: 0.0028562480583786964
2023-01-24 10:13:39.980039: step: 644/529, loss: 0.003878779709339142
2023-01-24 10:13:41.099731: step: 648/529, loss: 0.011247131042182446
2023-01-24 10:13:42.210111: step: 652/529, loss: 0.021356847137212753
2023-01-24 10:13:43.329695: step: 656/529, loss: 0.011271699331700802
2023-01-24 10:13:44.441908: step: 660/529, loss: 0.005229650530964136
2023-01-24 10:13:45.568666: step: 664/529, loss: 0.0007825507782399654
2023-01-24 10:13:46.672439: step: 668/529, loss: 0.044641777873039246
2023-01-24 10:13:47.783981: step: 672/529, loss: 0.0012233637971803546
2023-01-24 10:13:48.886061: step: 676/529, loss: 0.0007903050282038748
2023-01-24 10:13:49.997948: step: 680/529, loss: 0.0025234618224203587
2023-01-24 10:13:51.095825: step: 684/529, loss: 0.0015214593149721622
2023-01-24 10:13:52.194629: step: 688/529, loss: 0.000100671750260517
2023-01-24 10:13:53.301604: step: 692/529, loss: 0.00117252126801759
2023-01-24 10:13:54.402878: step: 696/529, loss: 0.007785823196172714
2023-01-24 10:13:55.495233: step: 700/529, loss: 0.005848946049809456
2023-01-24 10:13:56.596063: step: 704/529, loss: 0.004434181842952967
2023-01-24 10:13:57.711754: step: 708/529, loss: 0.0005314656882546842
2023-01-24 10:13:58.814973: step: 712/529, loss: 0.001599497045390308
2023-01-24 10:13:59.922790: step: 716/529, loss: 0.006668953690677881
2023-01-24 10:14:01.050561: step: 720/529, loss: 0.007054932881146669
2023-01-24 10:14:02.185813: step: 724/529, loss: 0.0022631841711699963
2023-01-24 10:14:03.290527: step: 728/529, loss: 0.0038365251384675503
2023-01-24 10:14:04.397237: step: 732/529, loss: 0.004223325755447149
2023-01-24 10:14:05.515777: step: 736/529, loss: 0.0007428702665492892
2023-01-24 10:14:06.631792: step: 740/529, loss: 0.0010229283943772316
2023-01-24 10:14:07.739277: step: 744/529, loss: 0.009575918316841125
2023-01-24 10:14:08.854234: step: 748/529, loss: 0.006561367306858301
2023-01-24 10:14:09.960565: step: 752/529, loss: 0.0018939487636089325
2023-01-24 10:14:11.077903: step: 756/529, loss: 0.002845506649464369
2023-01-24 10:14:12.187529: step: 760/529, loss: 0.00011776803148677573
2023-01-24 10:14:13.277675: step: 764/529, loss: 0.0038699107244610786
2023-01-24 10:14:14.392966: step: 768/529, loss: 0.005368166137486696
2023-01-24 10:14:15.505854: step: 772/529, loss: 0.009277998469769955
2023-01-24 10:14:16.598051: step: 776/529, loss: 0.004776305519044399
2023-01-24 10:14:17.714999: step: 780/529, loss: 0.004130480345338583
2023-01-24 10:14:18.827277: step: 784/529, loss: 0.00017559003026690334
2023-01-24 10:14:19.940861: step: 788/529, loss: 0.0018009924096986651
2023-01-24 10:14:21.059041: step: 792/529, loss: 0.0011539142578840256
2023-01-24 10:14:22.149455: step: 796/529, loss: 0.005678319837898016
2023-01-24 10:14:23.234377: step: 800/529, loss: 0.00210260390304029
2023-01-24 10:14:24.362263: step: 804/529, loss: 0.0051914420910179615
2023-01-24 10:14:25.506560: step: 808/529, loss: 0.0024992600083351135
2023-01-24 10:14:26.603887: step: 812/529, loss: 0.0005710808909498155
2023-01-24 10:14:27.740495: step: 816/529, loss: 0.0038517708890140057
2023-01-24 10:14:28.870914: step: 820/529, loss: 0.003562731435522437
2023-01-24 10:14:29.979408: step: 824/529, loss: 0.00018203945364803076
2023-01-24 10:14:31.109858: step: 828/529, loss: 0.0038685575127601624
2023-01-24 10:14:32.205531: step: 832/529, loss: 0.0003838546108454466
2023-01-24 10:14:33.315251: step: 836/529, loss: 0.002460089512169361
2023-01-24 10:14:34.441830: step: 840/529, loss: 0.003453589743003249
2023-01-24 10:14:35.568659: step: 844/529, loss: 0.00018978604930453002
2023-01-24 10:14:36.690369: step: 848/529, loss: 0.0005749117117375135
2023-01-24 10:14:37.818577: step: 852/529, loss: 0.00022143925889395177
2023-01-24 10:14:38.942422: step: 856/529, loss: 0.00037597783375531435
2023-01-24 10:14:40.072238: step: 860/529, loss: 0.0033526206389069557
2023-01-24 10:14:41.186541: step: 864/529, loss: 0.0016919198678806424
2023-01-24 10:14:42.287774: step: 868/529, loss: 0.0013802197063341737
2023-01-24 10:14:43.389155: step: 872/529, loss: 0.006321109365671873
2023-01-24 10:14:44.503597: step: 876/529, loss: 0.004838189575821161
2023-01-24 10:14:45.633720: step: 880/529, loss: 0.012661442160606384
2023-01-24 10:14:46.743737: step: 884/529, loss: 0.0006348208989948034
2023-01-24 10:14:47.854891: step: 888/529, loss: 0.007669542450457811
2023-01-24 10:14:48.940296: step: 892/529, loss: 0.001546063693240285
2023-01-24 10:14:50.040783: step: 896/529, loss: 0.001893994864076376
2023-01-24 10:14:51.139435: step: 900/529, loss: 0.002007062779739499
2023-01-24 10:14:52.255005: step: 904/529, loss: 0.015635212883353233
2023-01-24 10:14:53.368222: step: 908/529, loss: 1.7594678638488404e-06
2023-01-24 10:14:54.494124: step: 912/529, loss: 0.03224106505513191
2023-01-24 10:14:55.586753: step: 916/529, loss: 0.0016301290597766638
2023-01-24 10:14:56.692745: step: 920/529, loss: 0.004916801117360592
2023-01-24 10:14:57.799332: step: 924/529, loss: 0.019051184877753258
2023-01-24 10:14:58.911146: step: 928/529, loss: 0.001486110151745379
2023-01-24 10:15:00.015771: step: 932/529, loss: 0.0009265593835152686
2023-01-24 10:15:01.154331: step: 936/529, loss: 0.0016251954948529601
2023-01-24 10:15:02.268604: step: 940/529, loss: 0.005804730579257011
2023-01-24 10:15:03.374214: step: 944/529, loss: 0.008127120323479176
2023-01-24 10:15:04.471577: step: 948/529, loss: 0.006725279148668051
2023-01-24 10:15:05.567022: step: 952/529, loss: 0.0013801433378830552
2023-01-24 10:15:06.672363: step: 956/529, loss: 0.005127770826220512
2023-01-24 10:15:07.778520: step: 960/529, loss: 0.016132310032844543
2023-01-24 10:15:08.901626: step: 964/529, loss: 0.0035112574696540833
2023-01-24 10:15:10.003413: step: 968/529, loss: 0.02039238251745701
2023-01-24 10:15:11.090627: step: 972/529, loss: 0.0004880115739069879
2023-01-24 10:15:12.229045: step: 976/529, loss: 0.00316818174906075
2023-01-24 10:15:13.344539: step: 980/529, loss: 0.008138158358633518
2023-01-24 10:15:14.480249: step: 984/529, loss: 0.007486666087061167
2023-01-24 10:15:15.597307: step: 988/529, loss: 0.003407453652471304
2023-01-24 10:15:16.700555: step: 992/529, loss: 0.000957888551056385
2023-01-24 10:15:17.818652: step: 996/529, loss: 0.0041221315041184425
2023-01-24 10:15:18.939038: step: 1000/529, loss: 0.0081532197073102
2023-01-24 10:15:20.049474: step: 1004/529, loss: 0.002281612018123269
2023-01-24 10:15:21.164981: step: 1008/529, loss: 0.0033546830527484417
2023-01-24 10:15:22.268085: step: 1012/529, loss: 0.004054310731589794
2023-01-24 10:15:23.366940: step: 1016/529, loss: 0.0037001371383666992
2023-01-24 10:15:24.498286: step: 1020/529, loss: 0.01609238050878048
2023-01-24 10:15:25.601805: step: 1024/529, loss: 0.003183288499712944
2023-01-24 10:15:26.716893: step: 1028/529, loss: 0.005319239571690559
2023-01-24 10:15:27.849223: step: 1032/529, loss: 0.006130259949713945
2023-01-24 10:15:28.980766: step: 1036/529, loss: 0.007439969573169947
2023-01-24 10:15:30.091063: step: 1040/529, loss: 0.005116703920066357
2023-01-24 10:15:31.221342: step: 1044/529, loss: 0.0030436678789556026
2023-01-24 10:15:32.336804: step: 1048/529, loss: 8.897004590835422e-05
2023-01-24 10:15:33.441170: step: 1052/529, loss: 0.0040328060276806355
2023-01-24 10:15:34.542821: step: 1056/529, loss: 0.0003829003544524312
2023-01-24 10:15:35.652258: step: 1060/529, loss: 0.001235216623172164
2023-01-24 10:15:36.787308: step: 1064/529, loss: 0.0004490836290642619
2023-01-24 10:15:37.898859: step: 1068/529, loss: 0.0005292270798236132
2023-01-24 10:15:39.005508: step: 1072/529, loss: 0.0014304673532024026
2023-01-24 10:15:40.098671: step: 1076/529, loss: 0.0005602949531748891
2023-01-24 10:15:41.203674: step: 1080/529, loss: 0.0006935730925761163
2023-01-24 10:15:42.310765: step: 1084/529, loss: 0.001220155507326126
2023-01-24 10:15:43.427101: step: 1088/529, loss: 0.002035715151578188
2023-01-24 10:15:44.530116: step: 1092/529, loss: 0.0
2023-01-24 10:15:45.642604: step: 1096/529, loss: 0.0023127312306314707
2023-01-24 10:15:46.750327: step: 1100/529, loss: 0.002316381549462676
2023-01-24 10:15:47.884196: step: 1104/529, loss: 0.0013327255146577954
2023-01-24 10:15:48.980996: step: 1108/529, loss: 0.00018317702051717788
2023-01-24 10:15:50.082339: step: 1112/529, loss: 0.0016799845034256577
2023-01-24 10:15:51.169461: step: 1116/529, loss: 0.0006235731998458505
2023-01-24 10:15:52.265575: step: 1120/529, loss: 0.0033945569302886724
2023-01-24 10:15:53.380479: step: 1124/529, loss: 0.0022695627994835377
2023-01-24 10:15:54.478409: step: 1128/529, loss: 0.0011129779741168022
2023-01-24 10:15:55.567785: step: 1132/529, loss: 8.847699064062908e-05
2023-01-24 10:15:56.693996: step: 1136/529, loss: 0.0036015366204082966
2023-01-24 10:15:57.802442: step: 1140/529, loss: 0.006102883722633123
2023-01-24 10:15:58.899563: step: 1144/529, loss: 0.0004643523716367781
2023-01-24 10:16:00.011459: step: 1148/529, loss: 0.0033088033087551594
2023-01-24 10:16:01.144706: step: 1152/529, loss: 0.005510775372385979
2023-01-24 10:16:02.253902: step: 1156/529, loss: 0.0017819063505157828
2023-01-24 10:16:03.387554: step: 1160/529, loss: 0.004066335968673229
2023-01-24 10:16:04.509227: step: 1164/529, loss: 0.0023045812267810106
2023-01-24 10:16:05.616843: step: 1168/529, loss: 0.0028221295215189457
2023-01-24 10:16:06.707696: step: 1172/529, loss: 0.0011922846315428615
2023-01-24 10:16:07.812653: step: 1176/529, loss: 0.00424084672704339
2023-01-24 10:16:08.922716: step: 1180/529, loss: 0.014814452268183231
2023-01-24 10:16:10.041317: step: 1184/529, loss: 0.0006933690747246146
2023-01-24 10:16:11.151024: step: 1188/529, loss: 9.850793867371976e-05
2023-01-24 10:16:12.266023: step: 1192/529, loss: 0.0046796114183962345
2023-01-24 10:16:13.379743: step: 1196/529, loss: 0.0018349813763052225
2023-01-24 10:16:14.504858: step: 1200/529, loss: 0.00014269088569562882
2023-01-24 10:16:15.608469: step: 1204/529, loss: 0.0031323202420026064
2023-01-24 10:16:16.704400: step: 1208/529, loss: 0.006606937386095524
2023-01-24 10:16:17.793092: step: 1212/529, loss: 0.0018760734237730503
2023-01-24 10:16:18.903985: step: 1216/529, loss: 3.755764555535279e-05
2023-01-24 10:16:20.023355: step: 1220/529, loss: 0.0013470997801050544
2023-01-24 10:16:21.145426: step: 1224/529, loss: 0.013409907929599285
2023-01-24 10:16:22.235944: step: 1228/529, loss: 0.010340589098632336
2023-01-24 10:16:23.356984: step: 1232/529, loss: 0.005958991125226021
2023-01-24 10:16:24.471552: step: 1236/529, loss: 7.232023926917464e-05
2023-01-24 10:16:25.575166: step: 1240/529, loss: 0.0022805503103882074
2023-01-24 10:16:26.711158: step: 1244/529, loss: 2.1513071260415018e-05
2023-01-24 10:16:27.842044: step: 1248/529, loss: 0.012328597716987133
2023-01-24 10:16:28.946344: step: 1252/529, loss: 0.004221243783831596
2023-01-24 10:16:30.048587: step: 1256/529, loss: 0.00807119719684124
2023-01-24 10:16:31.167890: step: 1260/529, loss: 2.4997354557854123e-05
2023-01-24 10:16:32.274287: step: 1264/529, loss: 0.0009072798420675099
2023-01-24 10:16:33.376848: step: 1268/529, loss: 0.00041539614903740585
2023-01-24 10:16:34.466798: step: 1272/529, loss: 0.003273399081081152
2023-01-24 10:16:35.563690: step: 1276/529, loss: 0.0009283280814997852
2023-01-24 10:16:36.651684: step: 1280/529, loss: 0.0028321912977844477
2023-01-24 10:16:37.768442: step: 1284/529, loss: 0.002910377224907279
2023-01-24 10:16:38.878525: step: 1288/529, loss: 0.0007328179781325161
2023-01-24 10:16:39.991033: step: 1292/529, loss: 0.00022568802523892373
2023-01-24 10:16:41.099773: step: 1296/529, loss: 0.0042230430990457535
2023-01-24 10:16:42.217910: step: 1300/529, loss: 0.00034572515869513154
2023-01-24 10:16:43.338021: step: 1304/529, loss: 0.0042604077607393265
2023-01-24 10:16:44.470143: step: 1308/529, loss: 0.0009138848981820047
2023-01-24 10:16:45.591269: step: 1312/529, loss: 0.0006869505159556866
2023-01-24 10:16:46.678581: step: 1316/529, loss: 0.0027945255860686302
2023-01-24 10:16:47.786075: step: 1320/529, loss: 0.001894089742563665
2023-01-24 10:16:48.902812: step: 1324/529, loss: 0.004271753132343292
2023-01-24 10:16:49.997161: step: 1328/529, loss: 0.0042986320331692696
2023-01-24 10:16:51.110456: step: 1332/529, loss: 0.004983176477253437
2023-01-24 10:16:52.225606: step: 1336/529, loss: 0.0007505838293582201
2023-01-24 10:16:53.339585: step: 1340/529, loss: 0.0036445839796215296
2023-01-24 10:16:54.432782: step: 1344/529, loss: 0.015335672535002232
2023-01-24 10:16:55.524543: step: 1348/529, loss: 0.003140975022688508
2023-01-24 10:16:56.612397: step: 1352/529, loss: 0.00034961881465278566
2023-01-24 10:16:57.719783: step: 1356/529, loss: 0.0019731668289750814
2023-01-24 10:16:58.826561: step: 1360/529, loss: 0.0015774405328556895
2023-01-24 10:16:59.921314: step: 1364/529, loss: 0.0002536348474677652
2023-01-24 10:17:01.029054: step: 1368/529, loss: 0.004726538434624672
2023-01-24 10:17:02.137657: step: 1372/529, loss: 0.0029401544015854597
2023-01-24 10:17:03.230839: step: 1376/529, loss: 0.00013591106107924134
2023-01-24 10:17:04.323215: step: 1380/529, loss: 0.00024330047017429024
2023-01-24 10:17:05.428032: step: 1384/529, loss: 0.005185817833989859
2023-01-24 10:17:06.538572: step: 1388/529, loss: 0.0015014735981822014
2023-01-24 10:17:07.675090: step: 1392/529, loss: 0.0016143311513587832
2023-01-24 10:17:08.806459: step: 1396/529, loss: 0.0026642659213393927
2023-01-24 10:17:09.916613: step: 1400/529, loss: 0.0004948779242113233
2023-01-24 10:17:11.013193: step: 1404/529, loss: 0.00017834542086347938
2023-01-24 10:17:12.118484: step: 1408/529, loss: 0.0012523995246738195
2023-01-24 10:17:13.223523: step: 1412/529, loss: 0.0064910054206848145
2023-01-24 10:17:14.332608: step: 1416/529, loss: 0.00016557337949052453
2023-01-24 10:17:15.427989: step: 1420/529, loss: 0.00013977393973618746
2023-01-24 10:17:16.526824: step: 1424/529, loss: 0.003239166457206011
2023-01-24 10:17:17.628561: step: 1428/529, loss: 0.00019846379291266203
2023-01-24 10:17:18.773450: step: 1432/529, loss: 0.0009895035764202476
2023-01-24 10:17:19.879900: step: 1436/529, loss: 6.420422141673043e-05
2023-01-24 10:17:21.018486: step: 1440/529, loss: 0.0037464520428329706
2023-01-24 10:17:22.116516: step: 1444/529, loss: 0.0007337971474044025
2023-01-24 10:17:23.228174: step: 1448/529, loss: 0.0030959288123995066
2023-01-24 10:17:24.305384: step: 1452/529, loss: 0.0057845087721943855
2023-01-24 10:17:25.407786: step: 1456/529, loss: 2.4277517240989255e-06
2023-01-24 10:17:26.511633: step: 1460/529, loss: 0.002861048560589552
2023-01-24 10:17:27.627540: step: 1464/529, loss: 0.025103222578763962
2023-01-24 10:17:28.749744: step: 1468/529, loss: 0.0005867995787411928
2023-01-24 10:17:29.851866: step: 1472/529, loss: 0.0018123721238225698
2023-01-24 10:17:30.986556: step: 1476/529, loss: 0.00454313401132822
2023-01-24 10:17:32.110924: step: 1480/529, loss: 0.007734512910246849
2023-01-24 10:17:33.226269: step: 1484/529, loss: 0.0008463799022138119
2023-01-24 10:17:34.315051: step: 1488/529, loss: 0.0025026723742485046
2023-01-24 10:17:35.413960: step: 1492/529, loss: 0.002344332169741392
2023-01-24 10:17:36.539575: step: 1496/529, loss: 0.022468727082014084
2023-01-24 10:17:37.654202: step: 1500/529, loss: 0.001937435707077384
2023-01-24 10:17:38.782178: step: 1504/529, loss: 0.004542469047009945
2023-01-24 10:17:39.877052: step: 1508/529, loss: 0.00027558536385186017
2023-01-24 10:17:41.008949: step: 1512/529, loss: 0.00039425372960977256
2023-01-24 10:17:42.119403: step: 1516/529, loss: 0.002080772537738085
2023-01-24 10:17:43.215130: step: 1520/529, loss: 0.0005550920031964779
2023-01-24 10:17:44.349514: step: 1524/529, loss: 0.001061206916347146
2023-01-24 10:17:45.431321: step: 1528/529, loss: 0.0032434735912829638
2023-01-24 10:17:46.537298: step: 1532/529, loss: 0.0002451745676808059
2023-01-24 10:17:47.635948: step: 1536/529, loss: 0.001608675578609109
2023-01-24 10:17:48.757036: step: 1540/529, loss: 0.00017154146917164326
2023-01-24 10:17:49.866481: step: 1544/529, loss: 0.0007907557883299887
2023-01-24 10:17:51.006494: step: 1548/529, loss: 0.003614268731325865
2023-01-24 10:17:52.129205: step: 1552/529, loss: 0.0022618568036705256
2023-01-24 10:17:53.238845: step: 1556/529, loss: 0.0068869260139763355
2023-01-24 10:17:54.359367: step: 1560/529, loss: 0.007398021407425404
2023-01-24 10:17:55.474200: step: 1564/529, loss: 0.0059370240196585655
2023-01-24 10:17:56.623843: step: 1568/529, loss: 0.007094777189195156
2023-01-24 10:17:57.735890: step: 1572/529, loss: 0.0007351635140366852
2023-01-24 10:17:58.821778: step: 1576/529, loss: 0.004753817338496447
2023-01-24 10:17:59.936969: step: 1580/529, loss: 0.0010637149680405855
2023-01-24 10:18:01.075464: step: 1584/529, loss: 3.296718932688236e-05
2023-01-24 10:18:02.189514: step: 1588/529, loss: 0.001035338151268661
2023-01-24 10:18:03.280416: step: 1592/529, loss: 0.002007863251492381
2023-01-24 10:18:04.397136: step: 1596/529, loss: 0.010607047006487846
2023-01-24 10:18:05.499428: step: 1600/529, loss: 0.002998506184667349
2023-01-24 10:18:06.606007: step: 1604/529, loss: 0.0006424991879612207
2023-01-24 10:18:07.711920: step: 1608/529, loss: 0.003501034574583173
2023-01-24 10:18:08.816931: step: 1612/529, loss: 0.0025091341231018305
2023-01-24 10:18:09.929493: step: 1616/529, loss: 0.0004386629443615675
2023-01-24 10:18:11.036578: step: 1620/529, loss: 0.008217046037316322
2023-01-24 10:18:12.129005: step: 1624/529, loss: 0.005666786339133978
2023-01-24 10:18:13.216331: step: 1628/529, loss: 0.003978584427386522
2023-01-24 10:18:14.319457: step: 1632/529, loss: 0.003186688758432865
2023-01-24 10:18:15.455546: step: 1636/529, loss: 0.00022075467859394848
2023-01-24 10:18:16.546561: step: 1640/529, loss: 0.0002991705550812185
2023-01-24 10:18:17.656421: step: 1644/529, loss: 0.004022225271910429
2023-01-24 10:18:18.751095: step: 1648/529, loss: 0.0012513544643297791
2023-01-24 10:18:19.836641: step: 1652/529, loss: 0.003747907467186451
2023-01-24 10:18:20.931488: step: 1656/529, loss: 6.074237899156287e-05
2023-01-24 10:18:22.045035: step: 1660/529, loss: 0.0006146800587885082
2023-01-24 10:18:23.160571: step: 1664/529, loss: 0.005680084228515625
2023-01-24 10:18:24.259628: step: 1668/529, loss: 0.002186031546443701
2023-01-24 10:18:25.365814: step: 1672/529, loss: 0.00376828177832067
2023-01-24 10:18:26.463037: step: 1676/529, loss: 0.0013247650349512696
2023-01-24 10:18:27.565507: step: 1680/529, loss: 0.000754302367568016
2023-01-24 10:18:28.667284: step: 1684/529, loss: 0.007850531488656998
2023-01-24 10:18:29.790741: step: 1688/529, loss: 7.819827442290261e-05
2023-01-24 10:18:30.896815: step: 1692/529, loss: 2.714921356528066e-05
2023-01-24 10:18:32.011973: step: 1696/529, loss: 0.003312834072858095
2023-01-24 10:18:33.123778: step: 1700/529, loss: 0.004837794695049524
2023-01-24 10:18:34.252746: step: 1704/529, loss: 0.005805597640573978
2023-01-24 10:18:35.368266: step: 1708/529, loss: 0.002504920121282339
2023-01-24 10:18:36.460871: step: 1712/529, loss: 0.0016883322969079018
2023-01-24 10:18:37.572737: step: 1716/529, loss: 0.002296832390129566
2023-01-24 10:18:38.700784: step: 1720/529, loss: 0.004409465938806534
2023-01-24 10:18:39.815353: step: 1724/529, loss: 0.00982142798602581
2023-01-24 10:18:40.927299: step: 1728/529, loss: 0.006684282328933477
2023-01-24 10:18:42.026756: step: 1732/529, loss: 0.00036657426971942186
2023-01-24 10:18:43.151444: step: 1736/529, loss: 0.022729065269231796
2023-01-24 10:18:44.271972: step: 1740/529, loss: 0.00011018678924301639
2023-01-24 10:18:45.398061: step: 1744/529, loss: 0.0002326670364709571
2023-01-24 10:18:46.484112: step: 1748/529, loss: 0.002289942465722561
2023-01-24 10:18:47.609059: step: 1752/529, loss: 0.011409563943743706
2023-01-24 10:18:48.712632: step: 1756/529, loss: 0.0027784693520516157
2023-01-24 10:18:49.803318: step: 1760/529, loss: 0.0020392381120473146
2023-01-24 10:18:50.910094: step: 1764/529, loss: 0.0032472293823957443
2023-01-24 10:18:52.020634: step: 1768/529, loss: 0.006544557400047779
2023-01-24 10:18:53.133053: step: 1772/529, loss: 0.004073138814419508
2023-01-24 10:18:54.224206: step: 1776/529, loss: 0.0037605254910886288
2023-01-24 10:18:55.326356: step: 1780/529, loss: 0.003962155431509018
2023-01-24 10:18:56.455750: step: 1784/529, loss: 0.0020130721386522055
2023-01-24 10:18:57.556412: step: 1788/529, loss: 0.0030737388879060745
2023-01-24 10:18:58.664068: step: 1792/529, loss: 0.0002566327166277915
2023-01-24 10:18:59.766800: step: 1796/529, loss: 0.004707719199359417
2023-01-24 10:19:00.892208: step: 1800/529, loss: 0.00910465233027935
2023-01-24 10:19:02.019899: step: 1804/529, loss: 0.0006960343453101814
2023-01-24 10:19:03.110508: step: 1808/529, loss: 0.005849251989275217
2023-01-24 10:19:04.220189: step: 1812/529, loss: 0.005141881760209799
2023-01-24 10:19:05.320541: step: 1816/529, loss: 0.00015971447282936424
2023-01-24 10:19:06.425851: step: 1820/529, loss: 4.826217991649173e-05
2023-01-24 10:19:07.534305: step: 1824/529, loss: 9.297313954448327e-05
2023-01-24 10:19:08.625913: step: 1828/529, loss: 0.0008544176816940308
2023-01-24 10:19:09.732122: step: 1832/529, loss: 0.001272372668609023
2023-01-24 10:19:10.865946: step: 1836/529, loss: 0.002373679308220744
2023-01-24 10:19:11.949478: step: 1840/529, loss: 0.009036741219460964
2023-01-24 10:19:13.061756: step: 1844/529, loss: 0.00551905483007431
2023-01-24 10:19:14.201296: step: 1848/529, loss: 0.000178137473994866
2023-01-24 10:19:15.302314: step: 1852/529, loss: 9.45411557040643e-06
2023-01-24 10:19:16.424819: step: 1856/529, loss: 0.0002576617116574198
2023-01-24 10:19:17.548951: step: 1860/529, loss: 0.001806303858757019
2023-01-24 10:19:18.672735: step: 1864/529, loss: 0.002440019743517041
2023-01-24 10:19:19.790463: step: 1868/529, loss: 0.003919581882655621
2023-01-24 10:19:20.898710: step: 1872/529, loss: 0.002197820693254471
2023-01-24 10:19:22.012304: step: 1876/529, loss: 0.007047176361083984
2023-01-24 10:19:23.124819: step: 1880/529, loss: 0.00910390354692936
2023-01-24 10:19:24.243213: step: 1884/529, loss: 0.014309889636933804
2023-01-24 10:19:25.366486: step: 1888/529, loss: 0.00014088246098253876
2023-01-24 10:19:26.467645: step: 1892/529, loss: 0.0004975051851943135
2023-01-24 10:19:27.600407: step: 1896/529, loss: 0.0011556170647963881
2023-01-24 10:19:28.716278: step: 1900/529, loss: 0.007840687409043312
2023-01-24 10:19:29.830498: step: 1904/529, loss: 0.018665466457605362
2023-01-24 10:19:30.952079: step: 1908/529, loss: 0.004070708993822336
2023-01-24 10:19:32.083366: step: 1912/529, loss: 0.002608062233775854
2023-01-24 10:19:33.183364: step: 1916/529, loss: 0.006647141650319099
2023-01-24 10:19:34.268309: step: 1920/529, loss: 0.0009569816756993532
2023-01-24 10:19:35.369211: step: 1924/529, loss: 0.00476759672164917
2023-01-24 10:19:36.499440: step: 1928/529, loss: 0.0040803831070661545
2023-01-24 10:19:37.613320: step: 1932/529, loss: 0.0036367676220834255
2023-01-24 10:19:38.725771: step: 1936/529, loss: 0.010478099808096886
2023-01-24 10:19:39.832721: step: 1940/529, loss: 0.0038589893374592066
2023-01-24 10:19:40.933469: step: 1944/529, loss: 0.0007154970080591738
2023-01-24 10:19:42.039291: step: 1948/529, loss: 0.0011981292627751827
2023-01-24 10:19:43.141160: step: 1952/529, loss: 0.005452464800328016
2023-01-24 10:19:44.248958: step: 1956/529, loss: 0.0004163089324720204
2023-01-24 10:19:45.331766: step: 1960/529, loss: 0.004430715925991535
2023-01-24 10:19:46.439343: step: 1964/529, loss: 0.0038386895321309566
2023-01-24 10:19:47.534498: step: 1968/529, loss: 0.006286457646638155
2023-01-24 10:19:48.633899: step: 1972/529, loss: 0.007337962742894888
2023-01-24 10:19:49.774163: step: 1976/529, loss: 0.003538707038387656
2023-01-24 10:19:50.915389: step: 1980/529, loss: 0.04257753863930702
2023-01-24 10:19:52.028407: step: 1984/529, loss: 0.003906108206138015
2023-01-24 10:19:53.117843: step: 1988/529, loss: 0.0028025375213474035
2023-01-24 10:19:54.224822: step: 1992/529, loss: 0.0004601016116794199
2023-01-24 10:19:55.328789: step: 1996/529, loss: 0.0002046436711680144
2023-01-24 10:19:56.437604: step: 2000/529, loss: 1.3262655556900427e-05
2023-01-24 10:19:57.540826: step: 2004/529, loss: 0.00196659192442894
2023-01-24 10:19:58.665526: step: 2008/529, loss: 0.0038509811274707317
2023-01-24 10:19:59.775489: step: 2012/529, loss: 0.005182947032153606
2023-01-24 10:20:00.891263: step: 2016/529, loss: 0.004308459348976612
2023-01-24 10:20:02.015559: step: 2020/529, loss: 0.004337576683610678
2023-01-24 10:20:03.113142: step: 2024/529, loss: 0.0009445503819733858
2023-01-24 10:20:04.219706: step: 2028/529, loss: 0.006655809003859758
2023-01-24 10:20:05.325522: step: 2032/529, loss: 0.002387002110481262
2023-01-24 10:20:06.432906: step: 2036/529, loss: 0.0008364159148186445
2023-01-24 10:20:07.552806: step: 2040/529, loss: 0.0003520515456330031
2023-01-24 10:20:08.672038: step: 2044/529, loss: 0.0003551412373781204
2023-01-24 10:20:09.789058: step: 2048/529, loss: 0.002720827702432871
2023-01-24 10:20:10.904846: step: 2052/529, loss: 0.011590850539505482
2023-01-24 10:20:12.030638: step: 2056/529, loss: 0.0007229375187307596
2023-01-24 10:20:13.163695: step: 2060/529, loss: 0.0027340345550328493
2023-01-24 10:20:14.297377: step: 2064/529, loss: 0.0039020460098981857
2023-01-24 10:20:15.408270: step: 2068/529, loss: 0.0023356035817414522
2023-01-24 10:20:16.512943: step: 2072/529, loss: 0.0012758683878928423
2023-01-24 10:20:17.612319: step: 2076/529, loss: 0.003053620457649231
2023-01-24 10:20:18.720448: step: 2080/529, loss: 0.02930067852139473
2023-01-24 10:20:19.821648: step: 2084/529, loss: 0.0010876203887164593
2023-01-24 10:20:20.925535: step: 2088/529, loss: 0.001289432868361473
2023-01-24 10:20:22.034459: step: 2092/529, loss: 0.0017837306950241327
2023-01-24 10:20:23.153061: step: 2096/529, loss: 0.015498174354434013
2023-01-24 10:20:24.265596: step: 2100/529, loss: 0.006176387891173363
2023-01-24 10:20:25.365433: step: 2104/529, loss: 0.004790736827999353
2023-01-24 10:20:26.452150: step: 2108/529, loss: 0.003857166040688753
2023-01-24 10:20:27.552886: step: 2112/529, loss: 0.017585232853889465
2023-01-24 10:20:28.657135: step: 2116/529, loss: 0.01703360117971897
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37842817896389325, 'r': 0.3267264163730008, 'f1': 0.3506819173697992}, 'combined': 0.2583972022724836, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.39802761564322026, 'r': 0.2883458290101665, 'f1': 0.3344232026911881}, 'combined': 0.20554791970287659, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40264317180616743, 'r': 0.34686907020872865, 'f1': 0.37268093781855255}, 'combined': 0.2746070068136703, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39833000354684056, 'r': 0.28614867672472344, 'f1': 0.3330464679176307}, 'combined': 0.2057051713608896, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 14}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 10:22:59.176581: step: 4/529, loss: 0.0025931207928806543
2023-01-24 10:23:00.272479: step: 8/529, loss: 0.002882205881178379
2023-01-24 10:23:01.366294: step: 12/529, loss: 0.0019329885253682733
2023-01-24 10:23:02.457310: step: 16/529, loss: 0.004193895496428013
2023-01-24 10:23:03.552741: step: 20/529, loss: 0.00379492761567235
2023-01-24 10:23:04.634089: step: 24/529, loss: 0.0005721582565456629
2023-01-24 10:23:05.743867: step: 28/529, loss: 0.00034021068131551147
2023-01-24 10:23:06.845073: step: 32/529, loss: 0.0014818633208051324
2023-01-24 10:23:07.953709: step: 36/529, loss: 0.0024233476724475622
2023-01-24 10:23:09.081557: step: 40/529, loss: 0.01127456035465002
2023-01-24 10:23:10.203474: step: 44/529, loss: 0.0026036002673208714
2023-01-24 10:23:11.326791: step: 48/529, loss: 0.009529824368655682
2023-01-24 10:23:12.432722: step: 52/529, loss: 0.003497038036584854
2023-01-24 10:23:13.526321: step: 56/529, loss: 1.0660816087693092e-06
2023-01-24 10:23:14.616672: step: 60/529, loss: 0.0006411707727238536
2023-01-24 10:23:15.707512: step: 64/529, loss: 0.0019496476743370295
2023-01-24 10:23:16.804538: step: 68/529, loss: 8.146338223014027e-05
2023-01-24 10:23:17.902652: step: 72/529, loss: 0.001929825753904879
2023-01-24 10:23:19.015899: step: 76/529, loss: 0.005785155110061169
2023-01-24 10:23:20.105182: step: 80/529, loss: 0.003134605474770069
2023-01-24 10:23:21.215257: step: 84/529, loss: 4.341760813986184e-06
2023-01-24 10:23:22.350876: step: 88/529, loss: 0.008819718845188618
2023-01-24 10:23:23.441816: step: 92/529, loss: 0.0016645672731101513
2023-01-24 10:23:24.553755: step: 96/529, loss: 0.0
2023-01-24 10:23:25.653978: step: 100/529, loss: 0.0015565308276563883
2023-01-24 10:23:26.787597: step: 104/529, loss: 0.004332202486693859
2023-01-24 10:23:27.896202: step: 108/529, loss: 0.011444944888353348
2023-01-24 10:23:28.987889: step: 112/529, loss: 0.00030909196357242763
2023-01-24 10:23:30.100029: step: 116/529, loss: 0.0016193374758586287
2023-01-24 10:23:31.210873: step: 120/529, loss: 0.0003048228973057121
2023-01-24 10:23:32.320907: step: 124/529, loss: 0.00768269831314683
2023-01-24 10:23:33.442560: step: 128/529, loss: 0.002439528238028288
2023-01-24 10:23:34.561731: step: 132/529, loss: 0.0016832355177029967
2023-01-24 10:23:35.658793: step: 136/529, loss: 0.007965903729200363
2023-01-24 10:23:36.765422: step: 140/529, loss: 0.00942944921553135
2023-01-24 10:23:37.849092: step: 144/529, loss: 0.01987425424158573
2023-01-24 10:23:38.951337: step: 148/529, loss: 0.0010225827572867274
2023-01-24 10:23:40.038025: step: 152/529, loss: 0.0005653511034324765
2023-01-24 10:23:41.137687: step: 156/529, loss: 0.00024072726955637336
2023-01-24 10:23:42.213128: step: 160/529, loss: 0.0017016800120472908
2023-01-24 10:23:43.317498: step: 164/529, loss: 0.0008846782729960978
2023-01-24 10:23:44.443418: step: 168/529, loss: 0.01710948720574379
2023-01-24 10:23:45.583373: step: 172/529, loss: 0.0028305889572948217
2023-01-24 10:23:46.681162: step: 176/529, loss: 0.0014025341952219605
2023-01-24 10:23:47.787692: step: 180/529, loss: 0.0015463435556739569
2023-01-24 10:23:48.921157: step: 184/529, loss: 0.006373053882271051
2023-01-24 10:23:50.042021: step: 188/529, loss: 0.0009270533919334412
2023-01-24 10:23:51.165602: step: 192/529, loss: 0.0024236892350018024
2023-01-24 10:23:52.257980: step: 196/529, loss: 0.0032860967330634594
2023-01-24 10:23:53.383042: step: 200/529, loss: 0.007065056823194027
2023-01-24 10:23:54.480979: step: 204/529, loss: 0.0011449287412688136
2023-01-24 10:23:55.601011: step: 208/529, loss: 0.0018164193024858832
2023-01-24 10:23:56.730545: step: 212/529, loss: 0.0077828397043049335
2023-01-24 10:23:57.838512: step: 216/529, loss: 0.0019382606260478497
2023-01-24 10:23:58.958754: step: 220/529, loss: 0.00045744821545667946
2023-01-24 10:24:00.060161: step: 224/529, loss: 0.003052780171856284
2023-01-24 10:24:01.189697: step: 228/529, loss: 0.0009677736088633537
2023-01-24 10:24:02.292435: step: 232/529, loss: 0.0010485561797395349
2023-01-24 10:24:03.402578: step: 236/529, loss: 0.004682354629039764
2023-01-24 10:24:04.551419: step: 240/529, loss: 0.0010485638631507754
2023-01-24 10:24:05.654528: step: 244/529, loss: 0.0005701185436919332
2023-01-24 10:24:06.756499: step: 248/529, loss: 0.0077110594138503075
2023-01-24 10:24:07.884691: step: 252/529, loss: 0.004379655700176954
2023-01-24 10:24:08.978529: step: 256/529, loss: 0.0002996704715769738
2023-01-24 10:24:10.088481: step: 260/529, loss: 0.0031712246127426624
2023-01-24 10:24:11.213028: step: 264/529, loss: 0.002312564058229327
2023-01-24 10:24:12.326682: step: 268/529, loss: 0.0011986871249973774
2023-01-24 10:24:13.433596: step: 272/529, loss: 0.001462261425331235
2023-01-24 10:24:14.564844: step: 276/529, loss: 0.0013160841772332788
2023-01-24 10:24:15.665996: step: 280/529, loss: 0.020053409039974213
2023-01-24 10:24:16.782888: step: 284/529, loss: 0.0011960159754380584
2023-01-24 10:24:17.881353: step: 288/529, loss: 0.0027911916840821505
2023-01-24 10:24:18.980847: step: 292/529, loss: 0.0005166210466995835
2023-01-24 10:24:20.096709: step: 296/529, loss: 0.001611589454114437
2023-01-24 10:24:21.214378: step: 300/529, loss: 0.008736606687307358
2023-01-24 10:24:22.320417: step: 304/529, loss: 0.0021758999209851027
2023-01-24 10:24:23.414946: step: 308/529, loss: 0.00048054257058538496
2023-01-24 10:24:24.509224: step: 312/529, loss: 0.0006689963047392666
2023-01-24 10:24:25.595370: step: 316/529, loss: 0.00018199862097389996
2023-01-24 10:24:26.681572: step: 320/529, loss: 0.001530970330350101
2023-01-24 10:24:27.774031: step: 324/529, loss: 0.0016844660276547074
2023-01-24 10:24:28.884289: step: 328/529, loss: 0.0002713404828682542
2023-01-24 10:24:29.992455: step: 332/529, loss: 0.0018338896334171295
2023-01-24 10:24:31.116941: step: 336/529, loss: 0.011477985419332981
2023-01-24 10:24:32.222956: step: 340/529, loss: 0.003239257726818323
2023-01-24 10:24:33.300943: step: 344/529, loss: 0.0018541333265602589
2023-01-24 10:24:34.399211: step: 348/529, loss: 0.007821747101843357
2023-01-24 10:24:35.494150: step: 352/529, loss: 0.0037999227643013
2023-01-24 10:24:36.614474: step: 356/529, loss: 0.0011009207228198647
2023-01-24 10:24:37.718853: step: 360/529, loss: 8.387991692870855e-05
2023-01-24 10:24:38.841078: step: 364/529, loss: 0.0031167457345873117
2023-01-24 10:24:39.981366: step: 368/529, loss: 0.0050917682237923145
2023-01-24 10:24:41.082255: step: 372/529, loss: 0.0006687749992124736
2023-01-24 10:24:42.196220: step: 376/529, loss: 0.0038873106241226196
2023-01-24 10:24:43.310165: step: 380/529, loss: 0.0040429700165987015
2023-01-24 10:24:44.468112: step: 384/529, loss: 0.012457926757633686
2023-01-24 10:24:45.571944: step: 388/529, loss: 0.005165906623005867
2023-01-24 10:24:46.679316: step: 392/529, loss: 9.569324902258813e-05
2023-01-24 10:24:47.769422: step: 396/529, loss: 0.00024494295939803123
2023-01-24 10:24:48.897342: step: 400/529, loss: 0.0033263189252465963
2023-01-24 10:24:50.051744: step: 404/529, loss: 0.0007285865140147507
2023-01-24 10:24:51.137402: step: 408/529, loss: 4.938764959661057e-06
2023-01-24 10:24:52.268338: step: 412/529, loss: 0.002756058005616069
2023-01-24 10:24:53.379941: step: 416/529, loss: 0.0026710699312388897
2023-01-24 10:24:54.487346: step: 420/529, loss: 0.0003971263358835131
2023-01-24 10:24:55.583088: step: 424/529, loss: 0.004400121513754129
2023-01-24 10:24:56.690470: step: 428/529, loss: 0.004421007353812456
2023-01-24 10:24:57.797070: step: 432/529, loss: 2.6119578251382336e-05
2023-01-24 10:24:58.902052: step: 436/529, loss: 0.0026272854302078485
2023-01-24 10:25:00.006984: step: 440/529, loss: 0.006672269199043512
2023-01-24 10:25:01.093756: step: 444/529, loss: 0.00010470183042343706
2023-01-24 10:25:02.182798: step: 448/529, loss: 7.937334885355085e-05
2023-01-24 10:25:03.295388: step: 452/529, loss: 0.001821152283810079
2023-01-24 10:25:04.406031: step: 456/529, loss: 0.00498504051938653
2023-01-24 10:25:05.539887: step: 460/529, loss: 0.004358218517154455
2023-01-24 10:25:06.658032: step: 464/529, loss: 8.644044282846153e-05
2023-01-24 10:25:07.749580: step: 468/529, loss: 0.0026828604750335217
2023-01-24 10:25:08.875795: step: 472/529, loss: 0.002760467818006873
2023-01-24 10:25:09.979904: step: 476/529, loss: 0.003166378941386938
2023-01-24 10:25:11.086858: step: 480/529, loss: 0.005208566784858704
2023-01-24 10:25:12.189138: step: 484/529, loss: 0.003407896962016821
2023-01-24 10:25:13.306724: step: 488/529, loss: 1.0104229659191333e-05
2023-01-24 10:25:14.413756: step: 492/529, loss: 0.002344684675335884
2023-01-24 10:25:15.523750: step: 496/529, loss: 0.006681410130113363
2023-01-24 10:25:16.633256: step: 500/529, loss: 0.010459478944540024
2023-01-24 10:25:17.754714: step: 504/529, loss: 0.004894265905022621
2023-01-24 10:25:18.851895: step: 508/529, loss: 0.0005904762074351311
2023-01-24 10:25:19.967845: step: 512/529, loss: 0.0008682598127052188
2023-01-24 10:25:21.100905: step: 516/529, loss: 0.005269668530672789
2023-01-24 10:25:22.220662: step: 520/529, loss: 0.00030751971644349396
2023-01-24 10:25:23.333252: step: 524/529, loss: 0.004326560068875551
2023-01-24 10:25:24.462330: step: 528/529, loss: 7.450662815244868e-05
2023-01-24 10:25:25.572696: step: 532/529, loss: 0.0028433911502361298
2023-01-24 10:25:26.677215: step: 536/529, loss: 0.001040037488564849
2023-01-24 10:25:27.784596: step: 540/529, loss: 0.00033004762372002006
2023-01-24 10:25:28.876561: step: 544/529, loss: 0.0007799130980856717
2023-01-24 10:25:30.003426: step: 548/529, loss: 0.00200090603902936
2023-01-24 10:25:31.118451: step: 552/529, loss: 0.0035005605313926935
2023-01-24 10:25:32.207742: step: 556/529, loss: 1.3783548524770595e-08
2023-01-24 10:25:33.323756: step: 560/529, loss: 0.004007306415587664
2023-01-24 10:25:34.442058: step: 564/529, loss: 0.0006187392864376307
2023-01-24 10:25:35.566247: step: 568/529, loss: 0.01276328507810831
2023-01-24 10:25:36.667880: step: 572/529, loss: 0.002960295882076025
2023-01-24 10:25:37.778628: step: 576/529, loss: 8.483040437567979e-05
2023-01-24 10:25:38.894547: step: 580/529, loss: 1.692560726951342e-05
2023-01-24 10:25:39.992613: step: 584/529, loss: 0.002499618800356984
2023-01-24 10:25:41.093126: step: 588/529, loss: 0.0022299056872725487
2023-01-24 10:25:42.191432: step: 592/529, loss: 0.0022444468922913074
2023-01-24 10:25:43.315814: step: 596/529, loss: 0.004373785108327866
2023-01-24 10:25:44.429382: step: 600/529, loss: 0.001633203704841435
2023-01-24 10:25:45.543739: step: 604/529, loss: 0.001125205191783607
2023-01-24 10:25:46.650011: step: 608/529, loss: 0.00473776925355196
2023-01-24 10:25:47.752803: step: 612/529, loss: 0.007133645936846733
2023-01-24 10:25:48.892456: step: 616/529, loss: 0.001407354837283492
2023-01-24 10:25:49.995385: step: 620/529, loss: 0.003916764631867409
2023-01-24 10:25:51.092000: step: 624/529, loss: 0.0006860258872620761
2023-01-24 10:25:52.208998: step: 628/529, loss: 0.0005836035707034171
2023-01-24 10:25:53.315545: step: 632/529, loss: 5.0458707846701145e-05
2023-01-24 10:25:54.437596: step: 636/529, loss: 0.02299467660486698
2023-01-24 10:25:55.563387: step: 640/529, loss: 0.005951618775725365
2023-01-24 10:25:56.672562: step: 644/529, loss: 0.00011345349776092917
2023-01-24 10:25:57.803969: step: 648/529, loss: 0.005091405473649502
2023-01-24 10:25:58.921102: step: 652/529, loss: 0.0007573122857138515
2023-01-24 10:26:00.040699: step: 656/529, loss: 0.000507863238453865
2023-01-24 10:26:01.159710: step: 660/529, loss: 0.0010490842396393418
2023-01-24 10:26:02.290134: step: 664/529, loss: 0.007440539542585611
2023-01-24 10:26:03.417785: step: 668/529, loss: 0.0006416182150132954
2023-01-24 10:26:04.519888: step: 672/529, loss: 0.006349744275212288
2023-01-24 10:26:05.626337: step: 676/529, loss: 0.0023344228975474834
2023-01-24 10:26:06.747376: step: 680/529, loss: 1.2900488400191534e-05
2023-01-24 10:26:07.870076: step: 684/529, loss: 5.103509920445504e-06
2023-01-24 10:26:08.983241: step: 688/529, loss: 0.0015895896358415484
2023-01-24 10:26:10.075791: step: 692/529, loss: 0.0
2023-01-24 10:26:11.181883: step: 696/529, loss: 0.006037390325218439
2023-01-24 10:26:12.301864: step: 700/529, loss: 3.3256092137889937e-05
2023-01-24 10:26:13.400428: step: 704/529, loss: 5.813862571812933e-06
2023-01-24 10:26:14.541168: step: 708/529, loss: 0.007634587585926056
2023-01-24 10:26:15.645480: step: 712/529, loss: 0.0051072873175144196
2023-01-24 10:26:16.749052: step: 716/529, loss: 0.004017191007733345
2023-01-24 10:26:17.867592: step: 720/529, loss: 0.006503316108137369
2023-01-24 10:26:18.960901: step: 724/529, loss: 0.005251658149063587
2023-01-24 10:26:20.081848: step: 728/529, loss: 0.0019055964658036828
2023-01-24 10:26:21.183355: step: 732/529, loss: 0.002239476889371872
2023-01-24 10:26:22.293658: step: 736/529, loss: 0.005064769182354212
2023-01-24 10:26:23.402542: step: 740/529, loss: 0.0077932653948664665
2023-01-24 10:26:24.503235: step: 744/529, loss: 0.003636268898844719
2023-01-24 10:26:25.645606: step: 748/529, loss: 0.004603404551744461
2023-01-24 10:26:26.735462: step: 752/529, loss: 0.006758167874068022
2023-01-24 10:26:27.836706: step: 756/529, loss: 0.002927799941971898
2023-01-24 10:26:28.928574: step: 760/529, loss: 0.0018717690836638212
2023-01-24 10:26:30.030524: step: 764/529, loss: 0.00028159821522422135
2023-01-24 10:26:31.146838: step: 768/529, loss: 0.010703489184379578
2023-01-24 10:26:32.257535: step: 772/529, loss: 0.009481514804065228
2023-01-24 10:26:33.382112: step: 776/529, loss: 0.0008355171303264797
2023-01-24 10:26:34.502454: step: 780/529, loss: 0.0051216003485023975
2023-01-24 10:26:35.596199: step: 784/529, loss: 0.0047023966908454895
2023-01-24 10:26:36.718594: step: 788/529, loss: 0.003678713459521532
2023-01-24 10:26:37.821830: step: 792/529, loss: 0.004792946390807629
2023-01-24 10:26:38.946570: step: 796/529, loss: 0.003073078813031316
2023-01-24 10:26:40.084581: step: 800/529, loss: 0.00048310161218978465
2023-01-24 10:26:41.184661: step: 804/529, loss: 0.004600821062922478
2023-01-24 10:26:42.281900: step: 808/529, loss: 1.5896202967269346e-05
2023-01-24 10:26:43.372839: step: 812/529, loss: 0.02302611619234085
2023-01-24 10:26:44.471946: step: 816/529, loss: 0.0013681501150131226
2023-01-24 10:26:45.582130: step: 820/529, loss: 0.005964048206806183
2023-01-24 10:26:46.688558: step: 824/529, loss: 0.0037615399342030287
2023-01-24 10:26:47.820660: step: 828/529, loss: 0.0024312094319611788
2023-01-24 10:26:48.943559: step: 832/529, loss: 0.00256152031943202
2023-01-24 10:26:50.049151: step: 836/529, loss: 0.01198567170649767
2023-01-24 10:26:51.161362: step: 840/529, loss: 0.0008322140201926231
2023-01-24 10:26:52.262020: step: 844/529, loss: 0.001330302213318646
2023-01-24 10:26:53.392689: step: 848/529, loss: 0.00021860735432710499
2023-01-24 10:26:54.500996: step: 852/529, loss: 0.0007062862860038877
2023-01-24 10:26:55.620701: step: 856/529, loss: 0.00025333184748888016
2023-01-24 10:26:56.726255: step: 860/529, loss: 0.00178387516643852
2023-01-24 10:26:57.810563: step: 864/529, loss: 0.004562384448945522
2023-01-24 10:26:58.923661: step: 868/529, loss: 0.0013166420394554734
2023-01-24 10:27:00.029977: step: 872/529, loss: 0.0011279626050963998
2023-01-24 10:27:01.144912: step: 876/529, loss: 0.0037275163922458887
2023-01-24 10:27:02.230252: step: 880/529, loss: 0.0012887457851320505
2023-01-24 10:27:03.348569: step: 884/529, loss: 0.015079370699822903
2023-01-24 10:27:04.442911: step: 888/529, loss: 0.0024891633074730635
2023-01-24 10:27:05.543267: step: 892/529, loss: 0.008975147269666195
2023-01-24 10:27:06.666995: step: 896/529, loss: 0.008496423251926899
2023-01-24 10:27:07.777215: step: 900/529, loss: 0.0013733908999711275
2023-01-24 10:27:08.877264: step: 904/529, loss: 1.4562931028194726e-05
2023-01-24 10:27:10.011271: step: 908/529, loss: 0.0004261470749042928
2023-01-24 10:27:11.104486: step: 912/529, loss: 0.004404229111969471
2023-01-24 10:27:12.189378: step: 916/529, loss: 0.00046006691991351545
2023-01-24 10:27:13.275619: step: 920/529, loss: 7.002323400229216e-05
2023-01-24 10:27:14.403494: step: 924/529, loss: 0.010251963511109352
2023-01-24 10:27:15.515911: step: 928/529, loss: 0.0015799937536939979
2023-01-24 10:27:16.629981: step: 932/529, loss: 0.006481474731117487
2023-01-24 10:27:17.748804: step: 936/529, loss: 0.006786048877984285
2023-01-24 10:27:18.869095: step: 940/529, loss: 0.02876487374305725
2023-01-24 10:27:19.969200: step: 944/529, loss: 0.0009365540463477373
2023-01-24 10:27:21.061982: step: 948/529, loss: 0.003659546375274658
2023-01-24 10:27:22.159564: step: 952/529, loss: 0.002510154852643609
2023-01-24 10:27:23.260267: step: 956/529, loss: 0.0020188719499856234
2023-01-24 10:27:24.366671: step: 960/529, loss: 0.003070984035730362
2023-01-24 10:27:25.472558: step: 964/529, loss: 0.0010389360832050443
2023-01-24 10:27:26.559770: step: 968/529, loss: 0.0008549040067009628
2023-01-24 10:27:27.674439: step: 972/529, loss: 0.002145325532183051
2023-01-24 10:27:28.785453: step: 976/529, loss: 0.0019552281592041254
2023-01-24 10:27:29.892904: step: 980/529, loss: 0.0033176466822624207
2023-01-24 10:27:31.007498: step: 984/529, loss: 0.002010810188949108
2023-01-24 10:27:32.117739: step: 988/529, loss: 0.007342258468270302
2023-01-24 10:27:33.224343: step: 992/529, loss: 0.0005395688349381089
2023-01-24 10:27:34.346425: step: 996/529, loss: 0.0006495625129900873
2023-01-24 10:27:35.472523: step: 1000/529, loss: 0.0011287410743534565
2023-01-24 10:27:36.609732: step: 1004/529, loss: 0.016856012865900993
2023-01-24 10:27:37.720470: step: 1008/529, loss: 0.0013029822148382664
2023-01-24 10:27:38.823697: step: 1012/529, loss: 0.00048373700701631606
2023-01-24 10:27:39.922207: step: 1016/529, loss: 0.001640502130612731
2023-01-24 10:27:41.061600: step: 1020/529, loss: 0.003887023078277707
2023-01-24 10:27:42.158827: step: 1024/529, loss: 0.00039018431561999023
2023-01-24 10:27:43.283904: step: 1028/529, loss: 0.001211483497172594
2023-01-24 10:27:44.375562: step: 1032/529, loss: 0.00016706189489923418
2023-01-24 10:27:45.489470: step: 1036/529, loss: 0.0021371752955019474
2023-01-24 10:27:46.590368: step: 1040/529, loss: 0.0003996858431492001
2023-01-24 10:27:47.699285: step: 1044/529, loss: 0.0077988081611692905
2023-01-24 10:27:48.837782: step: 1048/529, loss: 0.0009308267035521567
2023-01-24 10:27:49.927600: step: 1052/529, loss: 0.0010225848527625203
2023-01-24 10:27:51.026775: step: 1056/529, loss: 0.0012509291991591454
2023-01-24 10:27:52.124959: step: 1060/529, loss: 0.0005226831999607384
2023-01-24 10:27:53.232452: step: 1064/529, loss: 0.0020150465425103903
2023-01-24 10:27:54.347805: step: 1068/529, loss: 0.0009939377196133137
2023-01-24 10:27:55.484494: step: 1072/529, loss: 0.003210749477148056
2023-01-24 10:27:56.614994: step: 1076/529, loss: 0.0006924484041519463
2023-01-24 10:27:57.720433: step: 1080/529, loss: 0.002885144203901291
2023-01-24 10:27:58.825838: step: 1084/529, loss: 0.0006250622100196779
2023-01-24 10:27:59.935542: step: 1088/529, loss: 0.0024558138102293015
2023-01-24 10:28:01.044278: step: 1092/529, loss: 0.004348600283265114
2023-01-24 10:28:02.169428: step: 1096/529, loss: 3.741820719938005e-08
2023-01-24 10:28:03.277698: step: 1100/529, loss: 0.0008665123605169356
2023-01-24 10:28:04.407734: step: 1104/529, loss: 0.0005608962965197861
2023-01-24 10:28:05.520491: step: 1108/529, loss: 0.019587049260735512
2023-01-24 10:28:06.617064: step: 1112/529, loss: 0.0008584687602706254
2023-01-24 10:28:07.716206: step: 1116/529, loss: 0.00013510460848920047
2023-01-24 10:28:08.812210: step: 1120/529, loss: 0.002296841936185956
2023-01-24 10:28:09.923514: step: 1124/529, loss: 1.9500680537021253e-06
2023-01-24 10:28:11.045831: step: 1128/529, loss: 0.003928482066839933
2023-01-24 10:28:12.166749: step: 1132/529, loss: 0.0007335945847444236
2023-01-24 10:28:13.287441: step: 1136/529, loss: 0.0018274959875270724
2023-01-24 10:28:14.427724: step: 1140/529, loss: 0.002051910385489464
2023-01-24 10:28:15.542716: step: 1144/529, loss: 0.0007606869330629706
2023-01-24 10:28:16.659121: step: 1148/529, loss: 3.3471686037955806e-05
2023-01-24 10:28:17.774943: step: 1152/529, loss: 0.005596863105893135
2023-01-24 10:28:18.881502: step: 1156/529, loss: 0.0036388859152793884
2023-01-24 10:28:19.976061: step: 1160/529, loss: 0.008118441328406334
2023-01-24 10:28:21.074547: step: 1164/529, loss: 0.003701305016875267
2023-01-24 10:28:22.169535: step: 1168/529, loss: 0.0008934138459153473
2023-01-24 10:28:23.258565: step: 1172/529, loss: 3.5706798371393234e-05
2023-01-24 10:28:24.362308: step: 1176/529, loss: 0.0002724910154938698
2023-01-24 10:28:25.471094: step: 1180/529, loss: 8.002180402399972e-05
2023-01-24 10:28:26.581807: step: 1184/529, loss: 0.007702495437115431
2023-01-24 10:28:27.689191: step: 1188/529, loss: 0.0159918200224638
2023-01-24 10:28:28.806528: step: 1192/529, loss: 3.4223314287373796e-05
2023-01-24 10:28:29.889037: step: 1196/529, loss: 0.002196255372837186
2023-01-24 10:28:30.986684: step: 1200/529, loss: 0.0018897982081398368
2023-01-24 10:28:32.117026: step: 1204/529, loss: 0.00416538817808032
2023-01-24 10:28:33.220299: step: 1208/529, loss: 0.0022185135167092085
2023-01-24 10:28:34.315269: step: 1212/529, loss: 0.00011258741142228246
2023-01-24 10:28:35.434679: step: 1216/529, loss: 0.0036868834868073463
2023-01-24 10:28:36.522704: step: 1220/529, loss: 0.0037335033994168043
2023-01-24 10:28:37.643749: step: 1224/529, loss: 0.0033380205277353525
2023-01-24 10:28:38.738742: step: 1228/529, loss: 0.00019725643505807966
2023-01-24 10:28:39.848725: step: 1232/529, loss: 0.0014699926832690835
2023-01-24 10:28:40.951500: step: 1236/529, loss: 0.002882779110223055
2023-01-24 10:28:42.055594: step: 1240/529, loss: 0.0003042803145945072
2023-01-24 10:28:43.172812: step: 1244/529, loss: 0.011927705258131027
2023-01-24 10:28:44.279173: step: 1248/529, loss: 0.0030136331915855408
2023-01-24 10:28:45.382667: step: 1252/529, loss: 0.00015892813098616898
2023-01-24 10:28:46.478302: step: 1256/529, loss: 0.0017119103576987982
2023-01-24 10:28:47.586638: step: 1260/529, loss: 0.003564529586583376
2023-01-24 10:28:48.686294: step: 1264/529, loss: 0.0008605823968537152
2023-01-24 10:28:49.814717: step: 1268/529, loss: 0.0070954738184809685
2023-01-24 10:28:50.948274: step: 1272/529, loss: 8.67826456669718e-05
2023-01-24 10:28:52.059024: step: 1276/529, loss: 0.0005311279091984034
2023-01-24 10:28:53.168836: step: 1280/529, loss: 0.00010013549763243645
2023-01-24 10:28:54.257958: step: 1284/529, loss: 0.0022027790546417236
2023-01-24 10:28:55.378772: step: 1288/529, loss: 0.001970133511349559
2023-01-24 10:28:56.488835: step: 1292/529, loss: 0.0006838677218183875
2023-01-24 10:28:57.591474: step: 1296/529, loss: 0.0027949821669608355
2023-01-24 10:28:58.699060: step: 1300/529, loss: 0.006945587694644928
2023-01-24 10:28:59.792692: step: 1304/529, loss: 0.001283031771890819
2023-01-24 10:29:00.943594: step: 1308/529, loss: 0.00043243009713478386
2023-01-24 10:29:02.077622: step: 1312/529, loss: 0.013830320909619331
2023-01-24 10:29:03.195211: step: 1316/529, loss: 0.006659200880676508
2023-01-24 10:29:04.309333: step: 1320/529, loss: 0.0018646640237420797
2023-01-24 10:29:05.419927: step: 1324/529, loss: 0.001095268176868558
2023-01-24 10:29:06.540230: step: 1328/529, loss: 0.00030951350345276296
2023-01-24 10:29:07.646802: step: 1332/529, loss: 0.00019956431060563773
2023-01-24 10:29:08.755544: step: 1336/529, loss: 0.00010064123489428312
2023-01-24 10:29:09.857307: step: 1340/529, loss: 0.0020738719031214714
2023-01-24 10:29:10.959369: step: 1344/529, loss: 0.006960752420127392
2023-01-24 10:29:12.081694: step: 1348/529, loss: 0.0045841834507882595
2023-01-24 10:29:13.183114: step: 1352/529, loss: 0.0003511657996568829
2023-01-24 10:29:14.279079: step: 1356/529, loss: 0.02579730562865734
2023-01-24 10:29:15.397786: step: 1360/529, loss: 0.0030574908014386892
2023-01-24 10:29:16.497747: step: 1364/529, loss: 0.001733759418129921
2023-01-24 10:29:17.615288: step: 1368/529, loss: 0.012433758936822414
2023-01-24 10:29:18.725795: step: 1372/529, loss: 0.007851693779230118
2023-01-24 10:29:19.822047: step: 1376/529, loss: 0.002105548046529293
2023-01-24 10:29:20.915986: step: 1380/529, loss: 0.017192499712109566
2023-01-24 10:29:22.005251: step: 1384/529, loss: 0.009983750060200691
2023-01-24 10:29:23.098465: step: 1388/529, loss: 0.0007768319337628782
2023-01-24 10:29:24.201248: step: 1392/529, loss: 0.04422217607498169
2023-01-24 10:29:25.301463: step: 1396/529, loss: 2.0303315977798775e-05
2023-01-24 10:29:26.406599: step: 1400/529, loss: 0.006508501712232828
2023-01-24 10:29:27.515449: step: 1404/529, loss: 0.0009816022356972098
2023-01-24 10:29:28.610831: step: 1408/529, loss: 0.011447586119174957
2023-01-24 10:29:29.727462: step: 1412/529, loss: 0.008318210020661354
2023-01-24 10:29:30.835670: step: 1416/529, loss: 3.976057269028388e-05
2023-01-24 10:29:31.952419: step: 1420/529, loss: 0.000183207041118294
2023-01-24 10:29:33.060776: step: 1424/529, loss: 0.012049549259245396
2023-01-24 10:29:34.155255: step: 1428/529, loss: 0.0006835930398665369
2023-01-24 10:29:35.284678: step: 1432/529, loss: 0.0036181756295263767
2023-01-24 10:29:36.383271: step: 1436/529, loss: 0.0009957838337868452
2023-01-24 10:29:37.528396: step: 1440/529, loss: 0.005574852228164673
2023-01-24 10:29:38.642843: step: 1444/529, loss: 0.00015191009151749313
2023-01-24 10:29:39.753661: step: 1448/529, loss: 7.421468762913719e-05
2023-01-24 10:29:40.862540: step: 1452/529, loss: 0.008800877258181572
2023-01-24 10:29:41.973472: step: 1456/529, loss: 0.00680225295946002
2023-01-24 10:29:43.088287: step: 1460/529, loss: 0.0058050998486578465
2023-01-24 10:29:44.211981: step: 1464/529, loss: 0.00039776417543180287
2023-01-24 10:29:45.342195: step: 1468/529, loss: 0.0008068532915785909
2023-01-24 10:29:46.455032: step: 1472/529, loss: 0.006469424348324537
2023-01-24 10:29:47.566929: step: 1476/529, loss: 0.001826525549404323
2023-01-24 10:29:48.681848: step: 1480/529, loss: 0.00032020191429182887
2023-01-24 10:29:49.767863: step: 1484/529, loss: 2.783198760880623e-05
2023-01-24 10:29:50.883988: step: 1488/529, loss: 3.538999067131954e-07
2023-01-24 10:29:52.014704: step: 1492/529, loss: 0.00319074303843081
2023-01-24 10:29:53.137165: step: 1496/529, loss: 0.0022088005207479
2023-01-24 10:29:54.229704: step: 1500/529, loss: 6.174926966195926e-05
2023-01-24 10:29:55.358397: step: 1504/529, loss: 0.05603187903761864
2023-01-24 10:29:56.470575: step: 1508/529, loss: 0.004804931115359068
2023-01-24 10:29:57.573672: step: 1512/529, loss: 0.0020182293374091387
2023-01-24 10:29:58.705276: step: 1516/529, loss: 0.0029437632765620947
2023-01-24 10:29:59.821408: step: 1520/529, loss: 0.006930566858500242
2023-01-24 10:30:00.943104: step: 1524/529, loss: 0.007187227252870798
2023-01-24 10:30:02.106970: step: 1528/529, loss: 0.001824341481551528
2023-01-24 10:30:03.236534: step: 1532/529, loss: 0.003785027889534831
2023-01-24 10:30:04.337509: step: 1536/529, loss: 0.0008193620597012341
2023-01-24 10:30:05.433573: step: 1540/529, loss: 0.00029365732916630805
2023-01-24 10:30:06.553907: step: 1544/529, loss: 0.01056717149913311
2023-01-24 10:30:07.630159: step: 1548/529, loss: 0.0022380375303328037
2023-01-24 10:30:08.771046: step: 1552/529, loss: 0.00021056804689578712
2023-01-24 10:30:09.882845: step: 1556/529, loss: 0.0010288369376212358
2023-01-24 10:30:11.009726: step: 1560/529, loss: 0.021586881950497627
2023-01-24 10:30:12.136394: step: 1564/529, loss: 0.005324484780430794
2023-01-24 10:30:13.242219: step: 1568/529, loss: 0.0009446726180613041
2023-01-24 10:30:14.351606: step: 1572/529, loss: 0.005531106609851122
2023-01-24 10:30:15.444163: step: 1576/529, loss: 0.0044586253352463245
2023-01-24 10:30:16.543085: step: 1580/529, loss: 0.00010495177411939949
2023-01-24 10:30:17.657905: step: 1584/529, loss: 0.0014270716346800327
2023-01-24 10:30:18.765716: step: 1588/529, loss: 5.585437065747101e-06
2023-01-24 10:30:19.880956: step: 1592/529, loss: 0.020020265132188797
2023-01-24 10:30:20.993777: step: 1596/529, loss: 0.019138479605317116
2023-01-24 10:30:22.129604: step: 1600/529, loss: 0.0021841011475771666
2023-01-24 10:30:23.237011: step: 1604/529, loss: 0.0018570291576907039
2023-01-24 10:30:24.370660: step: 1608/529, loss: 0.02626653015613556
2023-01-24 10:30:25.479138: step: 1612/529, loss: 0.0031333270017057657
2023-01-24 10:30:26.580209: step: 1616/529, loss: 0.0030078766867518425
2023-01-24 10:30:27.693466: step: 1620/529, loss: 0.003790183225646615
2023-01-24 10:30:28.790251: step: 1624/529, loss: 0.006445739883929491
2023-01-24 10:30:29.897416: step: 1628/529, loss: 3.877152721543098e-06
2023-01-24 10:30:31.009858: step: 1632/529, loss: 0.0006510972161777318
2023-01-24 10:30:32.118790: step: 1636/529, loss: 0.004444780293852091
2023-01-24 10:30:33.230656: step: 1640/529, loss: 0.0033888453617691994
2023-01-24 10:30:34.338043: step: 1644/529, loss: 0.006991660688072443
2023-01-24 10:30:35.434823: step: 1648/529, loss: 0.002052286406978965
2023-01-24 10:30:36.565281: step: 1652/529, loss: 0.0015124494675546885
2023-01-24 10:30:37.687756: step: 1656/529, loss: 0.0024441606365144253
2023-01-24 10:30:38.798454: step: 1660/529, loss: 2.2919744878890924e-05
2023-01-24 10:30:39.906541: step: 1664/529, loss: 0.0
2023-01-24 10:30:41.012546: step: 1668/529, loss: 0.049203429371118546
2023-01-24 10:30:42.107057: step: 1672/529, loss: 0.0005132881924510002
2023-01-24 10:30:43.208521: step: 1676/529, loss: 0.006499791517853737
2023-01-24 10:30:44.317999: step: 1680/529, loss: 0.00040859272121451795
2023-01-24 10:30:45.425793: step: 1684/529, loss: 0.0
2023-01-24 10:30:46.543813: step: 1688/529, loss: 0.006004152353852987
2023-01-24 10:30:47.652861: step: 1692/529, loss: 0.00030455252272076905
2023-01-24 10:30:48.743207: step: 1696/529, loss: 0.0008103943546302617
2023-01-24 10:30:49.861379: step: 1700/529, loss: 9.840609709499404e-05
2023-01-24 10:30:50.973536: step: 1704/529, loss: 0.006235078908503056
2023-01-24 10:30:52.081243: step: 1708/529, loss: 0.0004101524828001857
2023-01-24 10:30:53.183414: step: 1712/529, loss: 0.003382493741810322
2023-01-24 10:30:54.275432: step: 1716/529, loss: 0.000858451530802995
2023-01-24 10:30:55.384190: step: 1720/529, loss: 0.001419850392267108
2023-01-24 10:30:56.506813: step: 1724/529, loss: 6.0203879002074245e-06
2023-01-24 10:30:57.631520: step: 1728/529, loss: 3.298646697658114e-05
2023-01-24 10:30:58.743131: step: 1732/529, loss: 0.002509482204914093
2023-01-24 10:30:59.840840: step: 1736/529, loss: 0.004608344752341509
2023-01-24 10:31:00.980674: step: 1740/529, loss: 0.00459503848105669
2023-01-24 10:31:02.100618: step: 1744/529, loss: 0.0004937076009809971
2023-01-24 10:31:03.223045: step: 1748/529, loss: 0.0008771317079663277
2023-01-24 10:31:04.343037: step: 1752/529, loss: 0.0012682134984061122
2023-01-24 10:31:05.430059: step: 1756/529, loss: 0.0038723472971469164
2023-01-24 10:31:06.538417: step: 1760/529, loss: 0.00032535448553971946
2023-01-24 10:31:07.680961: step: 1764/529, loss: 0.007817676290869713
2023-01-24 10:31:08.775372: step: 1768/529, loss: 0.0019246513256803155
2023-01-24 10:31:09.888971: step: 1772/529, loss: 1.6376350686186925e-05
2023-01-24 10:31:10.991540: step: 1776/529, loss: 0.00045206412323750556
2023-01-24 10:31:12.114294: step: 1780/529, loss: 0.008600435219705105
2023-01-24 10:31:13.236109: step: 1784/529, loss: 0.0011514080688357353
2023-01-24 10:31:14.350544: step: 1788/529, loss: 0.00010648132592905313
2023-01-24 10:31:15.473146: step: 1792/529, loss: 0.0056484839878976345
2023-01-24 10:31:16.585986: step: 1796/529, loss: 0.013872471638023853
2023-01-24 10:31:17.735622: step: 1800/529, loss: 0.028201404958963394
2023-01-24 10:31:18.862583: step: 1804/529, loss: 0.0005001375102438033
2023-01-24 10:31:19.987948: step: 1808/529, loss: 0.0016479961341246963
2023-01-24 10:31:21.072517: step: 1812/529, loss: 0.0006181947537697852
2023-01-24 10:31:22.182235: step: 1816/529, loss: 0.004524826537817717
2023-01-24 10:31:23.294118: step: 1820/529, loss: 0.006089237052947283
2023-01-24 10:31:24.387698: step: 1824/529, loss: 0.01219960767775774
2023-01-24 10:31:25.490739: step: 1828/529, loss: 0.0004694901581387967
2023-01-24 10:31:26.588421: step: 1832/529, loss: 0.001699551590718329
2023-01-24 10:31:27.678682: step: 1836/529, loss: 0.0028385822661221027
2023-01-24 10:31:28.793373: step: 1840/529, loss: 0.005240814294666052
2023-01-24 10:31:29.901248: step: 1844/529, loss: 0.0035254876129329205
2023-01-24 10:31:30.988966: step: 1848/529, loss: 0.0013566554989665747
2023-01-24 10:31:32.102797: step: 1852/529, loss: 0.0005813108873553574
2023-01-24 10:31:33.218189: step: 1856/529, loss: 0.004426232539117336
2023-01-24 10:31:34.318530: step: 1860/529, loss: 0.001520061050541699
2023-01-24 10:31:35.421690: step: 1864/529, loss: 0.00017613093950785697
2023-01-24 10:31:36.546045: step: 1868/529, loss: 0.0035004280507564545
2023-01-24 10:31:37.659443: step: 1872/529, loss: 0.0010813449043780565
2023-01-24 10:31:38.763841: step: 1876/529, loss: 0.000825048889964819
2023-01-24 10:31:39.883575: step: 1880/529, loss: 0.0018010709900408983
2023-01-24 10:31:40.995768: step: 1884/529, loss: 0.0009285819251090288
2023-01-24 10:31:42.089892: step: 1888/529, loss: 0.00694962777197361
2023-01-24 10:31:43.190021: step: 1892/529, loss: 0.0015481164446100593
2023-01-24 10:31:44.292226: step: 1896/529, loss: 0.002436800394207239
2023-01-24 10:31:45.413054: step: 1900/529, loss: 0.0025722808204591274
2023-01-24 10:31:46.515900: step: 1904/529, loss: 0.0008329510455951095
2023-01-24 10:31:47.635021: step: 1908/529, loss: 5.622550816042349e-06
2023-01-24 10:31:48.712883: step: 1912/529, loss: 0.0020916699431836605
2023-01-24 10:31:49.831473: step: 1916/529, loss: 0.003578364383429289
2023-01-24 10:31:50.954728: step: 1920/529, loss: 0.002008066512644291
2023-01-24 10:31:52.069445: step: 1924/529, loss: 0.0015959724551066756
2023-01-24 10:31:53.178510: step: 1928/529, loss: 0.0024582366459071636
2023-01-24 10:31:54.290245: step: 1932/529, loss: 0.0039808014407753944
2023-01-24 10:31:55.387592: step: 1936/529, loss: 0.0038154874928295612
2023-01-24 10:31:56.493016: step: 1940/529, loss: 0.0017936573131009936
2023-01-24 10:31:57.614659: step: 1944/529, loss: 0.006269370671361685
2023-01-24 10:31:58.720845: step: 1948/529, loss: 6.442765425163088e-06
2023-01-24 10:31:59.835625: step: 1952/529, loss: 0.003060055896639824
2023-01-24 10:32:00.956587: step: 1956/529, loss: 0.00048185596824623644
2023-01-24 10:32:02.093916: step: 1960/529, loss: 0.005622961092740297
2023-01-24 10:32:03.185066: step: 1964/529, loss: 0.001580380485393107
2023-01-24 10:32:04.275052: step: 1968/529, loss: 0.005638332571834326
2023-01-24 10:32:05.370572: step: 1972/529, loss: 0.000876721809618175
2023-01-24 10:32:06.483840: step: 1976/529, loss: 0.019188644364476204
2023-01-24 10:32:07.579564: step: 1980/529, loss: 0.0018977447180077434
2023-01-24 10:32:08.709089: step: 1984/529, loss: 0.001158860744908452
2023-01-24 10:32:09.822408: step: 1988/529, loss: 0.0007904989179223776
2023-01-24 10:32:10.922656: step: 1992/529, loss: 0.0016090063145384192
2023-01-24 10:32:12.034970: step: 1996/529, loss: 0.01789737492799759
2023-01-24 10:32:13.135525: step: 2000/529, loss: 0.0014934086939319968
2023-01-24 10:32:14.255916: step: 2004/529, loss: 0.002243906259536743
2023-01-24 10:32:15.342249: step: 2008/529, loss: 2.849778582003637e-07
2023-01-24 10:32:16.456492: step: 2012/529, loss: 0.0020887048449367285
2023-01-24 10:32:17.585868: step: 2016/529, loss: 0.001315893605351448
2023-01-24 10:32:18.690793: step: 2020/529, loss: 0.003274239832535386
2023-01-24 10:32:19.816541: step: 2024/529, loss: 0.0005489022587426007
2023-01-24 10:32:20.951503: step: 2028/529, loss: 0.00046275195199996233
2023-01-24 10:32:22.066435: step: 2032/529, loss: 0.0018420395208522677
2023-01-24 10:32:23.163219: step: 2036/529, loss: 0.00461282953619957
2023-01-24 10:32:24.281924: step: 2040/529, loss: 0.0030570137314498425
2023-01-24 10:32:25.384317: step: 2044/529, loss: 0.0013270860072225332
2023-01-24 10:32:26.493308: step: 2048/529, loss: 0.0018468780908733606
2023-01-24 10:32:27.608842: step: 2052/529, loss: 0.0014235669514164329
2023-01-24 10:32:28.705023: step: 2056/529, loss: 2.238736669823993e-05
2023-01-24 10:32:29.800561: step: 2060/529, loss: 0.005863823927938938
2023-01-24 10:32:30.905871: step: 2064/529, loss: 0.00011247234942857176
2023-01-24 10:32:31.993054: step: 2068/529, loss: 0.000238575812545605
2023-01-24 10:32:33.105331: step: 2072/529, loss: 0.004164265934377909
2023-01-24 10:32:34.221476: step: 2076/529, loss: 0.011432450264692307
2023-01-24 10:32:35.325802: step: 2080/529, loss: 0.0035359500907361507
2023-01-24 10:32:36.453773: step: 2084/529, loss: 0.004473648499697447
2023-01-24 10:32:37.579248: step: 2088/529, loss: 0.00015654756862204522
2023-01-24 10:32:38.707514: step: 2092/529, loss: 0.01265480276197195
2023-01-24 10:32:39.822220: step: 2096/529, loss: 0.0002174990513594821
2023-01-24 10:32:40.930094: step: 2100/529, loss: 0.004461659584194422
2023-01-24 10:32:42.050355: step: 2104/529, loss: 0.002759193303063512
2023-01-24 10:32:43.186331: step: 2108/529, loss: 0.002610048046335578
2023-01-24 10:32:44.295706: step: 2112/529, loss: 0.00429393770173192
2023-01-24 10:32:45.424352: step: 2116/529, loss: 0.0006658345810137689
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3811603156887755, 'r': 0.3240224315532665, 'f1': 0.3502765567765568}, 'combined': 0.25809851551956814, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3992775472590255, 'r': 0.2868293645387627, 'f1': 0.33383871576170665}, 'combined': 0.205188674077927, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3718245122586785, 'r': 0.333019297506824, 'f1': 0.35135369326545796}, 'combined': 0.25889219503770583, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38281619122844374, 'r': 0.2915904957450624, 'f1': 0.3310333812983788}, 'combined': 0.2034644197248572, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40762331838565025, 'r': 0.34497153700189753, 'f1': 0.3736896197327852}, 'combined': 0.27535024611889436, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3985660689350252, 'r': 0.285282125598207, 'f1': 0.332540982768011}, 'combined': 0.205392959944948, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 10:35:07.520021: step: 4/529, loss: 0.0025717103853821754
2023-01-24 10:35:08.611187: step: 8/529, loss: 0.0016217614756897092
2023-01-24 10:35:09.715701: step: 12/529, loss: 0.003504799911752343
2023-01-24 10:35:10.821354: step: 16/529, loss: 0.00043105706572532654
2023-01-24 10:35:11.922483: step: 20/529, loss: 0.002535943640395999
2023-01-24 10:35:13.043510: step: 24/529, loss: 0.0012586342636495829
2023-01-24 10:35:14.134445: step: 28/529, loss: 0.0006895728874951601
2023-01-24 10:35:15.233957: step: 32/529, loss: 0.004079557955265045
2023-01-24 10:35:16.318322: step: 36/529, loss: 0.0005014987546019256
2023-01-24 10:35:17.417836: step: 40/529, loss: 0.0006685298285447061
2023-01-24 10:35:18.517190: step: 44/529, loss: 0.040392834693193436
2023-01-24 10:35:19.596687: step: 48/529, loss: 7.436522992065875e-06
2023-01-24 10:35:20.679501: step: 52/529, loss: 0.00010179962555412203
2023-01-24 10:35:21.782429: step: 56/529, loss: 7.468424882972613e-05
2023-01-24 10:35:22.879704: step: 60/529, loss: 0.01771727204322815
2023-01-24 10:35:23.989537: step: 64/529, loss: 9.653410234022886e-05
2023-01-24 10:35:25.098726: step: 68/529, loss: 0.0009888324420899153
2023-01-24 10:35:26.191630: step: 72/529, loss: 0.0014579963171854615
2023-01-24 10:35:27.293409: step: 76/529, loss: 0.004563336726278067
2023-01-24 10:35:28.385734: step: 80/529, loss: 0.00041388042154721916
2023-01-24 10:35:29.512240: step: 84/529, loss: 0.0013286015018820763
2023-01-24 10:35:30.611144: step: 88/529, loss: 0.0016371209640055895
2023-01-24 10:35:31.696974: step: 92/529, loss: 0.009889336302876472
2023-01-24 10:35:32.800927: step: 96/529, loss: 0.0017702560871839523
2023-01-24 10:35:33.901097: step: 100/529, loss: 0.0018194892909377813
2023-01-24 10:35:34.993023: step: 104/529, loss: 0.0012557179434224963
2023-01-24 10:35:36.091924: step: 108/529, loss: 8.531152707291767e-05
2023-01-24 10:35:37.197684: step: 112/529, loss: 0.016231495887041092
2023-01-24 10:35:38.293779: step: 116/529, loss: 0.00014289762475527823
2023-01-24 10:35:39.408124: step: 120/529, loss: 0.003986806608736515
2023-01-24 10:35:40.512641: step: 124/529, loss: 0.0019169404404237866
2023-01-24 10:35:41.622502: step: 128/529, loss: 0.004707092419266701
2023-01-24 10:35:42.723079: step: 132/529, loss: 0.0001334083644906059
2023-01-24 10:35:43.834575: step: 136/529, loss: 2.7819431124953553e-05
2023-01-24 10:35:44.963954: step: 140/529, loss: 0.0011797597398981452
2023-01-24 10:35:46.067424: step: 144/529, loss: 0.0025056852027773857
2023-01-24 10:35:47.146620: step: 148/529, loss: 0.0002327734255231917
2023-01-24 10:35:48.252140: step: 152/529, loss: 6.277415195654612e-06
2023-01-24 10:35:49.359764: step: 156/529, loss: 0.0027574326377362013
2023-01-24 10:35:50.457284: step: 160/529, loss: 0.0002734310401137918
2023-01-24 10:35:51.574043: step: 164/529, loss: 0.002487284131348133
2023-01-24 10:35:52.694370: step: 168/529, loss: 0.00038747413782402873
2023-01-24 10:35:53.795153: step: 172/529, loss: 0.0020659728907048702
2023-01-24 10:35:54.893718: step: 176/529, loss: 0.005030474159866571
2023-01-24 10:35:56.002735: step: 180/529, loss: 0.0026897662319242954
2023-01-24 10:35:57.111099: step: 184/529, loss: 0.004474503919482231
2023-01-24 10:35:58.213104: step: 188/529, loss: 0.0014012272004038095
2023-01-24 10:35:59.319869: step: 192/529, loss: 4.27848644903861e-05
2023-01-24 10:36:00.416078: step: 196/529, loss: 0.00022527102555613965
2023-01-24 10:36:01.506870: step: 200/529, loss: 0.004181277472525835
2023-01-24 10:36:02.638218: step: 204/529, loss: 0.0021777034271508455
2023-01-24 10:36:03.741563: step: 208/529, loss: 0.0035605314187705517
2023-01-24 10:36:04.859132: step: 212/529, loss: 0.001920978887937963
2023-01-24 10:36:05.941121: step: 216/529, loss: 0.0005725663504563272
2023-01-24 10:36:07.039487: step: 220/529, loss: 0.0014089654432609677
2023-01-24 10:36:08.164940: step: 224/529, loss: 0.0018161915941163898
2023-01-24 10:36:09.271652: step: 228/529, loss: 0.0004696142568718642
2023-01-24 10:36:10.399542: step: 232/529, loss: 0.003012617351487279
2023-01-24 10:36:11.528699: step: 236/529, loss: 0.011388827115297318
2023-01-24 10:36:12.651160: step: 240/529, loss: 0.00019995970069430768
2023-01-24 10:36:13.780274: step: 244/529, loss: 0.0034648762084543705
2023-01-24 10:36:14.879112: step: 248/529, loss: 0.0004728827625513077
2023-01-24 10:36:16.006093: step: 252/529, loss: 0.0006246794364415109
2023-01-24 10:36:17.119156: step: 256/529, loss: 0.0010714423842728138
2023-01-24 10:36:18.230473: step: 260/529, loss: 0.004186289384961128
2023-01-24 10:36:19.336491: step: 264/529, loss: 0.002878075698390603
2023-01-24 10:36:20.467777: step: 268/529, loss: 0.0013346533523872495
2023-01-24 10:36:21.602365: step: 272/529, loss: 0.0009790181647986174
2023-01-24 10:36:22.720972: step: 276/529, loss: 0.0002003751287702471
2023-01-24 10:36:23.830353: step: 280/529, loss: 0.018165085464715958
2023-01-24 10:36:24.940461: step: 284/529, loss: 0.002499673515558243
2023-01-24 10:36:26.070345: step: 288/529, loss: 0.006944416556507349
2023-01-24 10:36:27.206484: step: 292/529, loss: 0.006225381512194872
2023-01-24 10:36:28.321105: step: 296/529, loss: 2.106585270666983e-06
2023-01-24 10:36:29.414399: step: 300/529, loss: 0.0017619356513023376
2023-01-24 10:36:30.528647: step: 304/529, loss: 3.752469638129696e-05
2023-01-24 10:36:31.636637: step: 308/529, loss: 0.002547516953200102
2023-01-24 10:36:32.738751: step: 312/529, loss: 0.008872703649103642
2023-01-24 10:36:33.881054: step: 316/529, loss: 0.0004699170822277665
2023-01-24 10:36:34.994455: step: 320/529, loss: 0.0008881079847924411
2023-01-24 10:36:36.118085: step: 324/529, loss: 0.005238465033471584
2023-01-24 10:36:37.232077: step: 328/529, loss: 0.0028358467388898134
2023-01-24 10:36:38.352636: step: 332/529, loss: 0.0029785530641674995
2023-01-24 10:36:39.457867: step: 336/529, loss: 0.0022968652192503214
2023-01-24 10:36:40.581415: step: 340/529, loss: 0.0015114392153918743
2023-01-24 10:36:41.693266: step: 344/529, loss: 0.004083684179931879
2023-01-24 10:36:42.819378: step: 348/529, loss: 0.00100581138394773
2023-01-24 10:36:43.933770: step: 352/529, loss: 0.004071209579706192
2023-01-24 10:36:45.036230: step: 356/529, loss: 0.000570578733459115
2023-01-24 10:36:46.150040: step: 360/529, loss: 0.00019343972962815315
2023-01-24 10:36:47.248345: step: 364/529, loss: 0.008024826645851135
2023-01-24 10:36:48.343748: step: 368/529, loss: 0.0009940324816852808
2023-01-24 10:36:49.472612: step: 372/529, loss: 0.0017598633421584964
2023-01-24 10:36:50.588629: step: 376/529, loss: 0.008202673867344856
2023-01-24 10:36:51.698958: step: 380/529, loss: 0.0035658571869134903
2023-01-24 10:36:52.824475: step: 384/529, loss: 0.0003102307382505387
2023-01-24 10:36:53.953916: step: 388/529, loss: 0.003027574857696891
2023-01-24 10:36:55.076239: step: 392/529, loss: 3.983555143349804e-05
2023-01-24 10:36:56.186966: step: 396/529, loss: 0.0027810626197606325
2023-01-24 10:36:57.296640: step: 400/529, loss: 0.0006278423243202269
2023-01-24 10:36:58.421826: step: 404/529, loss: 0.0012888809433206916
2023-01-24 10:36:59.528885: step: 408/529, loss: 0.00023472230532206595
2023-01-24 10:37:00.634454: step: 412/529, loss: 0.0004988639848306775
2023-01-24 10:37:01.751284: step: 416/529, loss: 0.003025470767170191
2023-01-24 10:37:02.874392: step: 420/529, loss: 0.0005897580995224416
2023-01-24 10:37:03.988360: step: 424/529, loss: 0.008364231325685978
2023-01-24 10:37:05.097219: step: 428/529, loss: 0.0004518415662460029
2023-01-24 10:37:06.203324: step: 432/529, loss: 0.00026974562206305563
2023-01-24 10:37:07.321978: step: 436/529, loss: 0.0011700447648763657
2023-01-24 10:37:08.434752: step: 440/529, loss: 0.0005974172963760793
2023-01-24 10:37:09.539656: step: 444/529, loss: 0.00010823405318660662
2023-01-24 10:37:10.679387: step: 448/529, loss: 0.0013988834107294679
2023-01-24 10:37:11.811942: step: 452/529, loss: 0.000743257172871381
2023-01-24 10:37:12.915393: step: 456/529, loss: 0.0011069908505305648
2023-01-24 10:37:14.033068: step: 460/529, loss: 0.004662766121327877
2023-01-24 10:37:15.162064: step: 464/529, loss: 0.002533667255192995
2023-01-24 10:37:16.267206: step: 468/529, loss: 0.0009867676999419928
2023-01-24 10:37:17.408051: step: 472/529, loss: 0.0014385950053110719
2023-01-24 10:37:18.531985: step: 476/529, loss: 7.025834929663688e-05
2023-01-24 10:37:19.634928: step: 480/529, loss: 9.569383109919727e-05
2023-01-24 10:37:20.754098: step: 484/529, loss: 3.856765397358686e-05
2023-01-24 10:37:21.869270: step: 488/529, loss: 0.009324731305241585
2023-01-24 10:37:22.968859: step: 492/529, loss: 0.0010695349192246795
2023-01-24 10:37:24.061349: step: 496/529, loss: 0.0005988930934108794
2023-01-24 10:37:25.150665: step: 500/529, loss: 0.00403359392657876
2023-01-24 10:37:26.248868: step: 504/529, loss: 0.002551810350269079
2023-01-24 10:37:27.396225: step: 508/529, loss: 0.002722994890064001
2023-01-24 10:37:28.510929: step: 512/529, loss: 0.011934717185795307
2023-01-24 10:37:29.602353: step: 516/529, loss: 4.795699715032242e-05
2023-01-24 10:37:30.719271: step: 520/529, loss: 0.0013721531722694635
2023-01-24 10:37:31.854398: step: 524/529, loss: 0.0005579236894845963
2023-01-24 10:37:32.950151: step: 528/529, loss: 0.000680211465805769
2023-01-24 10:37:34.045522: step: 532/529, loss: 0.0019231747137382627
2023-01-24 10:37:35.153265: step: 536/529, loss: 0.0002036273363046348
2023-01-24 10:37:36.285951: step: 540/529, loss: 0.005133314523845911
2023-01-24 10:37:37.392591: step: 544/529, loss: 6.001493602525443e-05
2023-01-24 10:37:38.499433: step: 548/529, loss: 0.005198904313147068
2023-01-24 10:37:39.602281: step: 552/529, loss: 0.0007563154795207083
2023-01-24 10:37:40.696853: step: 556/529, loss: 0.022020190954208374
2023-01-24 10:37:41.817041: step: 560/529, loss: 0.00046537353773601353
2023-01-24 10:37:42.924747: step: 564/529, loss: 5.7559747801860794e-05
2023-01-24 10:37:44.040626: step: 568/529, loss: 0.006687423679977655
2023-01-24 10:37:45.146865: step: 572/529, loss: 0.0019201354589313269
2023-01-24 10:37:46.266048: step: 576/529, loss: 0.0036018716637045145
2023-01-24 10:37:47.381342: step: 580/529, loss: 0.0004896539030596614
2023-01-24 10:37:48.503786: step: 584/529, loss: 0.00024399592075496912
2023-01-24 10:37:49.610476: step: 588/529, loss: 0.0013536252081394196
2023-01-24 10:37:50.711376: step: 592/529, loss: 0.0045783184468746185
2023-01-24 10:37:51.830926: step: 596/529, loss: 0.0018999966559931636
2023-01-24 10:37:52.943899: step: 600/529, loss: 0.0021603796631097794
2023-01-24 10:37:54.088127: step: 604/529, loss: 0.0009288553847000003
2023-01-24 10:37:55.203462: step: 608/529, loss: 0.004257046617567539
2023-01-24 10:37:56.337521: step: 612/529, loss: 0.0009372093481943011
2023-01-24 10:37:57.424398: step: 616/529, loss: 0.00114144803956151
2023-01-24 10:37:58.543765: step: 620/529, loss: 0.0003124178620055318
2023-01-24 10:37:59.641426: step: 624/529, loss: 0.0026176832616329193
2023-01-24 10:38:00.789276: step: 628/529, loss: 0.0003139113250654191
2023-01-24 10:38:01.927687: step: 632/529, loss: 0.0021293589379638433
2023-01-24 10:38:03.052270: step: 636/529, loss: 0.0026612153742462397
2023-01-24 10:38:04.189371: step: 640/529, loss: 0.0033271510619670153
2023-01-24 10:38:05.314133: step: 644/529, loss: 0.00028579297941178083
2023-01-24 10:38:06.417300: step: 648/529, loss: 0.002534478669986129
2023-01-24 10:38:07.518783: step: 652/529, loss: 0.0004078938509337604
2023-01-24 10:38:08.629198: step: 656/529, loss: 0.0014979442348703742
2023-01-24 10:38:09.717384: step: 660/529, loss: 0.0006495776469819248
2023-01-24 10:38:10.859219: step: 664/529, loss: 0.004062824882566929
2023-01-24 10:38:11.950972: step: 668/529, loss: 0.00154287985060364
2023-01-24 10:38:13.085030: step: 672/529, loss: 0.00017719483003020287
2023-01-24 10:38:14.203958: step: 676/529, loss: 0.0006408290937542915
2023-01-24 10:38:15.310388: step: 680/529, loss: 0.002912107389420271
2023-01-24 10:38:16.413773: step: 684/529, loss: 0.006114633288234472
2023-01-24 10:38:17.556633: step: 688/529, loss: 0.0022857736330479383
2023-01-24 10:38:18.669425: step: 692/529, loss: 0.00444071926176548
2023-01-24 10:38:19.769127: step: 696/529, loss: 0.006485359743237495
2023-01-24 10:38:20.884646: step: 700/529, loss: 0.00012675090692937374
2023-01-24 10:38:21.978882: step: 704/529, loss: 0.0010553061729297042
2023-01-24 10:38:23.084934: step: 708/529, loss: 0.001653305604122579
2023-01-24 10:38:24.222208: step: 712/529, loss: 0.0031169711146503687
2023-01-24 10:38:25.345933: step: 716/529, loss: 0.00026145848096348345
2023-01-24 10:38:26.458765: step: 720/529, loss: 0.000716778333298862
2023-01-24 10:38:27.563328: step: 724/529, loss: 0.0003580014163162559
2023-01-24 10:38:28.666741: step: 728/529, loss: 0.0002108634653268382
2023-01-24 10:38:29.778898: step: 732/529, loss: 0.0013621096732094884
2023-01-24 10:38:30.898745: step: 736/529, loss: 0.0008688176749274135
2023-01-24 10:38:32.022709: step: 740/529, loss: 0.0005605376791208982
2023-01-24 10:38:33.129713: step: 744/529, loss: 0.00018265502876602113
2023-01-24 10:38:34.248549: step: 748/529, loss: 0.0025329648051410913
2023-01-24 10:38:35.362832: step: 752/529, loss: 0.004075721371918917
2023-01-24 10:38:36.495969: step: 756/529, loss: 0.004107451532036066
2023-01-24 10:38:37.595350: step: 760/529, loss: 0.0068987091071903706
2023-01-24 10:38:38.716049: step: 764/529, loss: 0.0007107718265615404
2023-01-24 10:38:39.827807: step: 768/529, loss: 0.00033213067217729986
2023-01-24 10:38:40.924571: step: 772/529, loss: 0.001406683586537838
2023-01-24 10:38:42.032045: step: 776/529, loss: 0.0009597904863767326
2023-01-24 10:38:43.175047: step: 780/529, loss: 0.0014973916113376617
2023-01-24 10:38:44.294242: step: 784/529, loss: 0.0041592796333134174
2023-01-24 10:38:45.419520: step: 788/529, loss: 0.000729519291780889
2023-01-24 10:38:46.524671: step: 792/529, loss: 0.004153810907155275
2023-01-24 10:38:47.635427: step: 796/529, loss: 0.009740411303937435
2023-01-24 10:38:48.753855: step: 800/529, loss: 0.00046480135642923415
2023-01-24 10:38:49.855283: step: 804/529, loss: 0.00025526570971123874
2023-01-24 10:38:50.962577: step: 808/529, loss: 0.00787463691085577
2023-01-24 10:38:52.066289: step: 812/529, loss: 0.002262952271848917
2023-01-24 10:38:53.179868: step: 816/529, loss: 0.00037824231549166143
2023-01-24 10:38:54.283401: step: 820/529, loss: 9.79991682470427e-07
2023-01-24 10:38:55.397833: step: 824/529, loss: 0.0011657316936179996
2023-01-24 10:38:56.503365: step: 828/529, loss: 3.5719421020985465e-07
2023-01-24 10:38:57.628293: step: 832/529, loss: 0.0005574448150582612
2023-01-24 10:38:58.743178: step: 836/529, loss: 0.0014753448776900768
2023-01-24 10:38:59.844022: step: 840/529, loss: 0.0022536753676831722
2023-01-24 10:39:00.952365: step: 844/529, loss: 0.0001820512698031962
2023-01-24 10:39:02.090288: step: 848/529, loss: 0.00017026931163854897
2023-01-24 10:39:03.209981: step: 852/529, loss: 0.004859400913119316
2023-01-24 10:39:04.297427: step: 856/529, loss: 0.005671901162713766
2023-01-24 10:39:05.407165: step: 860/529, loss: 0.00024869319167919457
2023-01-24 10:39:06.493673: step: 864/529, loss: 0.002023492008447647
2023-01-24 10:39:07.595121: step: 868/529, loss: 0.006473453715443611
2023-01-24 10:39:08.698573: step: 872/529, loss: 0.0005887337028980255
2023-01-24 10:39:09.807250: step: 876/529, loss: 2.011167089221999e-05
2023-01-24 10:39:10.926130: step: 880/529, loss: 0.0011151591315865517
2023-01-24 10:39:12.047200: step: 884/529, loss: 0.0005417157080955803
2023-01-24 10:39:13.150083: step: 888/529, loss: 0.005306778009980917
2023-01-24 10:39:14.271195: step: 892/529, loss: 0.00022178111248649657
2023-01-24 10:39:15.382987: step: 896/529, loss: 2.738489638431929e-05
2023-01-24 10:39:16.482414: step: 900/529, loss: 0.00855159293860197
2023-01-24 10:39:17.591959: step: 904/529, loss: 0.0006855662213638425
2023-01-24 10:39:18.707983: step: 908/529, loss: 0.0021421255078166723
2023-01-24 10:39:19.823256: step: 912/529, loss: 0.00046271344763226807
2023-01-24 10:39:20.930313: step: 916/529, loss: 0.001973553327843547
2023-01-24 10:39:22.047675: step: 920/529, loss: 0.0021304951515048742
2023-01-24 10:39:23.137669: step: 924/529, loss: 1.0877601198444609e-05
2023-01-24 10:39:24.234773: step: 928/529, loss: 0.002393420087173581
2023-01-24 10:39:25.327916: step: 932/529, loss: 0.02360234595835209
2023-01-24 10:39:26.446770: step: 936/529, loss: 0.004511687438935041
2023-01-24 10:39:27.547385: step: 940/529, loss: 0.009144485928118229
2023-01-24 10:39:28.676012: step: 944/529, loss: 0.0012210506247356534
2023-01-24 10:39:29.803546: step: 948/529, loss: 0.011008385568857193
2023-01-24 10:39:30.941821: step: 952/529, loss: 0.009567197412252426
2023-01-24 10:39:32.064935: step: 956/529, loss: 0.015011078678071499
2023-01-24 10:39:33.183486: step: 960/529, loss: 0.00015445654571522027
2023-01-24 10:39:34.309236: step: 964/529, loss: 0.0002223147894255817
2023-01-24 10:39:35.423599: step: 968/529, loss: 0.0004964654217474163
2023-01-24 10:39:36.535074: step: 972/529, loss: 0.0007797619327902794
2023-01-24 10:39:37.631221: step: 976/529, loss: 0.007512143347412348
2023-01-24 10:39:38.733604: step: 980/529, loss: 0.0027293802704662085
2023-01-24 10:39:39.855174: step: 984/529, loss: 0.01302841305732727
2023-01-24 10:39:40.997820: step: 988/529, loss: 0.0036742209922522306
2023-01-24 10:39:42.135844: step: 992/529, loss: 0.0022326421458274126
2023-01-24 10:39:43.261087: step: 996/529, loss: 5.598732514044968e-06
2023-01-24 10:39:44.378045: step: 1000/529, loss: 0.0024760281667113304
2023-01-24 10:39:45.512200: step: 1004/529, loss: 0.002352792536839843
2023-01-24 10:39:46.607387: step: 1008/529, loss: 0.006052291486412287
2023-01-24 10:39:47.731129: step: 1012/529, loss: 0.0010685940505936742
2023-01-24 10:39:48.836901: step: 1016/529, loss: 0.02471635676920414
2023-01-24 10:39:49.929283: step: 1020/529, loss: 0.00010453932191012427
2023-01-24 10:39:51.058932: step: 1024/529, loss: 0.007075488567352295
2023-01-24 10:39:52.177410: step: 1028/529, loss: 3.012677734659519e-05
2023-01-24 10:39:53.279063: step: 1032/529, loss: 7.301749428734183e-05
2023-01-24 10:39:54.387726: step: 1036/529, loss: 0.00026503007393330336
2023-01-24 10:39:55.483693: step: 1040/529, loss: 6.0722768466803245e-06
2023-01-24 10:39:56.611983: step: 1044/529, loss: 0.0003353578213136643
2023-01-24 10:39:57.732203: step: 1048/529, loss: 0.012445072643458843
2023-01-24 10:39:58.832771: step: 1052/529, loss: 0.0013299036072567105
2023-01-24 10:39:59.936388: step: 1056/529, loss: 0.0008099142578430474
2023-01-24 10:40:01.063566: step: 1060/529, loss: 0.0017548257019370794
2023-01-24 10:40:02.198833: step: 1064/529, loss: 0.002090941881760955
2023-01-24 10:40:03.332536: step: 1068/529, loss: 0.002166630467399955
2023-01-24 10:40:04.424019: step: 1072/529, loss: 0.002670489251613617
2023-01-24 10:40:05.522303: step: 1076/529, loss: 0.0024005977902561426
2023-01-24 10:40:06.622014: step: 1080/529, loss: 0.0003803379076998681
2023-01-24 10:40:07.733397: step: 1084/529, loss: 0.00048365857219323516
2023-01-24 10:40:08.854493: step: 1088/529, loss: 0.00013517634943127632
2023-01-24 10:40:09.965978: step: 1092/529, loss: 0.0015151374973356724
2023-01-24 10:40:11.079834: step: 1096/529, loss: 0.017995454370975494
2023-01-24 10:40:12.204947: step: 1100/529, loss: 1.8497863493394107e-05
2023-01-24 10:40:13.307796: step: 1104/529, loss: 0.006020611617714167
2023-01-24 10:40:14.415677: step: 1108/529, loss: 0.005534281954169273
2023-01-24 10:40:15.521367: step: 1112/529, loss: 0.014497381635010242
2023-01-24 10:40:16.621245: step: 1116/529, loss: 0.0007071839063428342
2023-01-24 10:40:17.729406: step: 1120/529, loss: 0.00246590469032526
2023-01-24 10:40:18.830959: step: 1124/529, loss: 0.0008053151541389525
2023-01-24 10:40:19.957810: step: 1128/529, loss: 0.002608046168461442
2023-01-24 10:40:21.051930: step: 1132/529, loss: 0.0
2023-01-24 10:40:22.149934: step: 1136/529, loss: 0.001271700719371438
2023-01-24 10:40:23.266641: step: 1140/529, loss: 9.087454600376077e-06
2023-01-24 10:40:24.355397: step: 1144/529, loss: 0.003951581660658121
2023-01-24 10:40:25.465604: step: 1148/529, loss: 0.013444422744214535
2023-01-24 10:40:26.590570: step: 1152/529, loss: 0.005554639734327793
2023-01-24 10:40:27.692155: step: 1156/529, loss: 0.00020550722547341138
2023-01-24 10:40:28.796026: step: 1160/529, loss: 5.013829650124535e-05
2023-01-24 10:40:29.924587: step: 1164/529, loss: 0.00479420181363821
2023-01-24 10:40:31.040605: step: 1168/529, loss: 0.006586549803614616
2023-01-24 10:40:32.180453: step: 1172/529, loss: 0.003172085853293538
2023-01-24 10:40:33.303027: step: 1176/529, loss: 0.0005119149573147297
2023-01-24 10:40:34.415825: step: 1180/529, loss: 0.0021032614167779684
2023-01-24 10:40:35.531734: step: 1184/529, loss: 0.004429087974131107
2023-01-24 10:40:36.643172: step: 1188/529, loss: 0.0002172814420191571
2023-01-24 10:40:37.738091: step: 1192/529, loss: 3.550000826635369e-07
2023-01-24 10:40:38.875889: step: 1196/529, loss: 0.002764068776741624
2023-01-24 10:40:39.991138: step: 1200/529, loss: 0.014618205837905407
2023-01-24 10:40:41.098764: step: 1204/529, loss: 0.0005840667872689664
2023-01-24 10:40:42.201627: step: 1208/529, loss: 7.298124842236575e-07
2023-01-24 10:40:43.316296: step: 1212/529, loss: 3.1651381959818536e-06
2023-01-24 10:40:44.430011: step: 1216/529, loss: 0.0030513079836964607
2023-01-24 10:40:45.524391: step: 1220/529, loss: 0.00013405506615526974
2023-01-24 10:40:46.643004: step: 1224/529, loss: 0.002724012592807412
2023-01-24 10:40:47.773450: step: 1228/529, loss: 0.04596179351210594
2023-01-24 10:40:48.871415: step: 1232/529, loss: 0.003376100677996874
2023-01-24 10:40:49.963358: step: 1236/529, loss: 7.784303306834772e-05
2023-01-24 10:40:51.068058: step: 1240/529, loss: 0.004986348561942577
2023-01-24 10:40:52.172107: step: 1244/529, loss: 0.008363432250916958
2023-01-24 10:40:53.291907: step: 1248/529, loss: 0.006280216854065657
2023-01-24 10:40:54.396175: step: 1252/529, loss: 0.0028854506090283394
2023-01-24 10:40:55.516256: step: 1256/529, loss: 7.14949201210402e-05
2023-01-24 10:40:56.610833: step: 1260/529, loss: 0.00020437205967027694
2023-01-24 10:40:57.697215: step: 1264/529, loss: 0.006827040109783411
2023-01-24 10:40:58.802188: step: 1268/529, loss: 0.007519053295254707
2023-01-24 10:40:59.911582: step: 1272/529, loss: 0.003101873444393277
2023-01-24 10:41:01.022765: step: 1276/529, loss: 0.0054717520251870155
2023-01-24 10:41:02.130303: step: 1280/529, loss: 0.006468202918767929
2023-01-24 10:41:03.249811: step: 1284/529, loss: 8.075428195297718e-05
2023-01-24 10:41:04.381753: step: 1288/529, loss: 0.017948390915989876
2023-01-24 10:41:05.501878: step: 1292/529, loss: 0.011312011629343033
2023-01-24 10:41:06.605377: step: 1296/529, loss: 0.0011688899248838425
2023-01-24 10:41:07.717042: step: 1300/529, loss: 0.01398471649736166
2023-01-24 10:41:08.811019: step: 1304/529, loss: 0.017319250851869583
2023-01-24 10:41:09.928456: step: 1308/529, loss: 0.0036821505054831505
2023-01-24 10:41:11.068169: step: 1312/529, loss: 3.2012172596296296e-05
2023-01-24 10:41:12.185984: step: 1316/529, loss: 0.00039172705146484077
2023-01-24 10:41:13.292034: step: 1320/529, loss: 0.0003688477154355496
2023-01-24 10:41:14.370594: step: 1324/529, loss: 0.0052772280760109425
2023-01-24 10:41:15.481408: step: 1328/529, loss: 0.005271188449114561
2023-01-24 10:41:16.590079: step: 1332/529, loss: 0.0037537061143666506
2023-01-24 10:41:17.700649: step: 1336/529, loss: 0.0016629727324470878
2023-01-24 10:41:18.813547: step: 1340/529, loss: 0.015550857409834862
2023-01-24 10:41:19.928070: step: 1344/529, loss: 0.0012086856877431273
2023-01-24 10:41:21.047533: step: 1348/529, loss: 0.0014340326888486743
2023-01-24 10:41:22.167025: step: 1352/529, loss: 0.00011742690548999235
2023-01-24 10:41:23.275826: step: 1356/529, loss: 0.0019932363647967577
2023-01-24 10:41:24.402463: step: 1360/529, loss: 0.0026363031938672066
2023-01-24 10:41:25.542503: step: 1364/529, loss: 0.010177216492593288
2023-01-24 10:41:26.633104: step: 1368/529, loss: 0.000787214026786387
2023-01-24 10:41:27.753183: step: 1372/529, loss: 8.542211617168505e-06
2023-01-24 10:41:28.865925: step: 1376/529, loss: 0.0031283865682780743
2023-01-24 10:41:29.982480: step: 1380/529, loss: 0.0038915451150387526
2023-01-24 10:41:31.092976: step: 1384/529, loss: 0.0017911266768351197
2023-01-24 10:41:32.210383: step: 1388/529, loss: 0.010370921343564987
2023-01-24 10:41:33.320125: step: 1392/529, loss: 0.0003778987447731197
2023-01-24 10:41:34.415876: step: 1396/529, loss: 0.0020700907334685326
2023-01-24 10:41:35.525412: step: 1400/529, loss: 0.0030397188384085894
2023-01-24 10:41:36.641237: step: 1404/529, loss: 0.00019207820878364146
2023-01-24 10:41:37.754227: step: 1408/529, loss: 0.0002488569589331746
2023-01-24 10:41:38.853251: step: 1412/529, loss: 9.417583896720316e-06
2023-01-24 10:41:39.967835: step: 1416/529, loss: 0.005500449799001217
2023-01-24 10:41:41.102762: step: 1420/529, loss: 0.0014790159184485674
2023-01-24 10:41:42.200973: step: 1424/529, loss: 0.00037380136200226843
2023-01-24 10:41:43.308382: step: 1428/529, loss: 0.00012191581481602043
2023-01-24 10:41:44.445134: step: 1432/529, loss: 0.013326038606464863
2023-01-24 10:41:45.579162: step: 1436/529, loss: 0.00698620080947876
2023-01-24 10:41:46.695341: step: 1440/529, loss: 0.002983787329867482
2023-01-24 10:41:47.806253: step: 1444/529, loss: 0.012154568918049335
2023-01-24 10:41:48.963475: step: 1448/529, loss: 0.0009631587308831513
2023-01-24 10:41:50.085867: step: 1452/529, loss: 0.005241477862000465
2023-01-24 10:41:51.202679: step: 1456/529, loss: 0.01132657378911972
2023-01-24 10:41:52.301449: step: 1460/529, loss: 0.005407418590039015
2023-01-24 10:41:53.397989: step: 1464/529, loss: 0.0002528067270759493
2023-01-24 10:41:54.491737: step: 1468/529, loss: 0.000685123261064291
2023-01-24 10:41:55.619476: step: 1472/529, loss: 0.0019333910895511508
2023-01-24 10:41:56.716289: step: 1476/529, loss: 0.00017044621927198023
2023-01-24 10:41:57.825179: step: 1480/529, loss: 6.857896369183436e-05
2023-01-24 10:41:58.931499: step: 1484/529, loss: 0.0020964026916772127
2023-01-24 10:42:00.065956: step: 1488/529, loss: 0.003285354934632778
2023-01-24 10:42:01.202909: step: 1492/529, loss: 0.012821413576602936
2023-01-24 10:42:02.352972: step: 1496/529, loss: 0.003961324226111174
2023-01-24 10:42:03.441012: step: 1500/529, loss: 0.01072637364268303
2023-01-24 10:42:04.563113: step: 1504/529, loss: 0.0047032516449689865
2023-01-24 10:42:05.652729: step: 1508/529, loss: 0.0005648515070788562
2023-01-24 10:42:06.766292: step: 1512/529, loss: 0.0013442575000226498
2023-01-24 10:42:07.880209: step: 1516/529, loss: 0.003088304540142417
2023-01-24 10:42:09.021061: step: 1520/529, loss: 0.012935384176671505
2023-01-24 10:42:10.140119: step: 1524/529, loss: 0.008348672650754452
2023-01-24 10:42:11.243962: step: 1528/529, loss: 0.0009352019988000393
2023-01-24 10:42:12.345699: step: 1532/529, loss: 0.008988582529127598
2023-01-24 10:42:13.470832: step: 1536/529, loss: 0.009629667736589909
2023-01-24 10:42:14.582840: step: 1540/529, loss: 7.732255471637473e-05
2023-01-24 10:42:15.686203: step: 1544/529, loss: 3.29173963109497e-05
2023-01-24 10:42:16.802447: step: 1548/529, loss: 5.4681873734807596e-05
2023-01-24 10:42:17.926653: step: 1552/529, loss: 0.004037510138005018
2023-01-24 10:42:19.055345: step: 1556/529, loss: 0.0022664403077214956
2023-01-24 10:42:20.167867: step: 1560/529, loss: 0.0018641222268342972
2023-01-24 10:42:21.284990: step: 1564/529, loss: 0.014384686946868896
2023-01-24 10:42:22.398619: step: 1568/529, loss: 0.0005332435248419642
2023-01-24 10:42:23.527817: step: 1572/529, loss: 0.004419991280883551
2023-01-24 10:42:24.652904: step: 1576/529, loss: 0.002452877815812826
2023-01-24 10:42:25.756818: step: 1580/529, loss: 2.536845329359494e-07
2023-01-24 10:42:26.883113: step: 1584/529, loss: 0.00212467135861516
2023-01-24 10:42:28.033200: step: 1588/529, loss: 0.001354173757135868
2023-01-24 10:42:29.137468: step: 1592/529, loss: 0.004622694570571184
2023-01-24 10:42:30.242991: step: 1596/529, loss: 0.0048582786694169044
2023-01-24 10:42:31.336087: step: 1600/529, loss: 0.0009130860562436283
2023-01-24 10:42:32.475919: step: 1604/529, loss: 0.0002408235741313547
2023-01-24 10:42:33.557891: step: 1608/529, loss: 0.0017662514001131058
2023-01-24 10:42:34.682335: step: 1612/529, loss: 0.016860710456967354
2023-01-24 10:42:35.805722: step: 1616/529, loss: 0.002983630634844303
2023-01-24 10:42:36.949624: step: 1620/529, loss: 2.401376150373835e-05
2023-01-24 10:42:38.025945: step: 1624/529, loss: 8.327971954713576e-06
2023-01-24 10:42:39.123891: step: 1628/529, loss: 0.0019038262544199824
2023-01-24 10:42:40.232276: step: 1632/529, loss: 0.004824307281523943
2023-01-24 10:42:41.352518: step: 1636/529, loss: 0.013162682764232159
2023-01-24 10:42:42.474350: step: 1640/529, loss: 0.00248154578730464
2023-01-24 10:42:43.595531: step: 1644/529, loss: 0.0015662814257666469
2023-01-24 10:42:44.705941: step: 1648/529, loss: 0.00095345638692379
2023-01-24 10:42:45.864450: step: 1652/529, loss: 0.002873386489227414
2023-01-24 10:42:46.978705: step: 1656/529, loss: 0.0009884893661364913
2023-01-24 10:42:48.109544: step: 1660/529, loss: 9.475088882027194e-05
2023-01-24 10:42:49.238371: step: 1664/529, loss: 0.003958193119615316
2023-01-24 10:42:50.338743: step: 1668/529, loss: 8.166748557414394e-06
2023-01-24 10:42:51.450326: step: 1672/529, loss: 0.0006217619520612061
2023-01-24 10:42:52.572552: step: 1676/529, loss: 0.005632845219224691
2023-01-24 10:42:53.698361: step: 1680/529, loss: 0.003930183127522469
2023-01-24 10:42:54.810891: step: 1684/529, loss: 0.00913216732442379
2023-01-24 10:42:55.917620: step: 1688/529, loss: 0.006910240277647972
2023-01-24 10:42:57.030745: step: 1692/529, loss: 0.00016234745271503925
2023-01-24 10:42:58.133989: step: 1696/529, loss: 0.0012153625721111894
2023-01-24 10:42:59.245712: step: 1700/529, loss: 0.0005787490517832339
2023-01-24 10:43:00.334148: step: 1704/529, loss: 0.008278287947177887
2023-01-24 10:43:01.446428: step: 1708/529, loss: 0.004330865107476711
2023-01-24 10:43:02.586026: step: 1712/529, loss: 0.0007008537650108337
2023-01-24 10:43:03.671850: step: 1716/529, loss: 0.003996940329670906
2023-01-24 10:43:04.786969: step: 1720/529, loss: 0.0009753562626428902
2023-01-24 10:43:05.935058: step: 1724/529, loss: 0.002494469750672579
2023-01-24 10:43:07.075673: step: 1728/529, loss: 0.0013603457482531667
2023-01-24 10:43:08.203858: step: 1732/529, loss: 0.000192040839465335
2023-01-24 10:43:09.323171: step: 1736/529, loss: 0.006484419107437134
2023-01-24 10:43:10.419862: step: 1740/529, loss: 0.005956148263067007
2023-01-24 10:43:11.525149: step: 1744/529, loss: 0.003528010565787554
2023-01-24 10:43:12.612637: step: 1748/529, loss: 0.0008659429149702191
2023-01-24 10:43:13.719329: step: 1752/529, loss: 0.01451429445296526
2023-01-24 10:43:14.824697: step: 1756/529, loss: 0.005417460575699806
2023-01-24 10:43:15.944390: step: 1760/529, loss: 0.0035941393580287695
2023-01-24 10:43:17.047885: step: 1764/529, loss: 0.0005939627299085259
2023-01-24 10:43:18.187356: step: 1768/529, loss: 0.012622364796698093
2023-01-24 10:43:19.272364: step: 1772/529, loss: 0.004787984769791365
2023-01-24 10:43:20.364452: step: 1776/529, loss: 0.00033332998282276094
2023-01-24 10:43:21.472639: step: 1780/529, loss: 0.00048649084055796266
2023-01-24 10:43:22.565333: step: 1784/529, loss: 1.278424520023691e-06
2023-01-24 10:43:23.691001: step: 1788/529, loss: 0.03201339766383171
2023-01-24 10:43:24.816783: step: 1792/529, loss: 0.0031452695839107037
2023-01-24 10:43:25.921411: step: 1796/529, loss: 0.020724741742014885
2023-01-24 10:43:27.029157: step: 1800/529, loss: 3.638499401859008e-05
2023-01-24 10:43:28.119812: step: 1804/529, loss: 0.0011949206236749887
2023-01-24 10:43:29.210801: step: 1808/529, loss: 0.001425070920959115
2023-01-24 10:43:30.316992: step: 1812/529, loss: 0.002037449972704053
2023-01-24 10:43:31.459020: step: 1816/529, loss: 6.524845957756042e-05
2023-01-24 10:43:32.563991: step: 1820/529, loss: 0.004529165104031563
2023-01-24 10:43:33.668181: step: 1824/529, loss: 0.0010282231960445642
2023-01-24 10:43:34.781572: step: 1828/529, loss: 0.0004265310999471694
2023-01-24 10:43:35.878448: step: 1832/529, loss: 0.0016007713275030255
2023-01-24 10:43:37.002315: step: 1836/529, loss: 0.00508074602112174
2023-01-24 10:43:38.140425: step: 1840/529, loss: 0.0005789457354694605
2023-01-24 10:43:39.232385: step: 1844/529, loss: 0.0002382405218668282
2023-01-24 10:43:40.375318: step: 1848/529, loss: 0.012829668819904327
2023-01-24 10:43:41.478668: step: 1852/529, loss: 0.0017798638436943293
2023-01-24 10:43:42.569593: step: 1856/529, loss: 0.00040473564877174795
2023-01-24 10:43:43.664169: step: 1860/529, loss: 0.009256916120648384
2023-01-24 10:43:44.755534: step: 1864/529, loss: 0.0017262959154322743
2023-01-24 10:43:45.845547: step: 1868/529, loss: 0.00021897396072745323
2023-01-24 10:43:46.956687: step: 1872/529, loss: 9.250151151718455e-07
2023-01-24 10:43:48.052153: step: 1876/529, loss: 0.0030344012193381786
2023-01-24 10:43:49.142087: step: 1880/529, loss: 0.0024779189843684435
2023-01-24 10:43:50.274464: step: 1884/529, loss: 0.006793782114982605
2023-01-24 10:43:51.399008: step: 1888/529, loss: 0.05012780427932739
2023-01-24 10:43:52.515038: step: 1892/529, loss: 0.00020729619427584112
2023-01-24 10:43:53.597396: step: 1896/529, loss: 0.0001832045236369595
2023-01-24 10:43:54.710228: step: 1900/529, loss: 0.00016050761041697115
2023-01-24 10:43:55.818591: step: 1904/529, loss: 0.000865721027366817
2023-01-24 10:43:56.921469: step: 1908/529, loss: 4.1270704969065264e-05
2023-01-24 10:43:58.024781: step: 1912/529, loss: 0.007097072433680296
2023-01-24 10:43:59.132440: step: 1916/529, loss: 0.0032081049866974354
2023-01-24 10:44:00.225255: step: 1920/529, loss: 2.236555519630201e-05
2023-01-24 10:44:01.343893: step: 1924/529, loss: 0.0019974568858742714
2023-01-24 10:44:02.453168: step: 1928/529, loss: 0.00019547744886949658
2023-01-24 10:44:03.552992: step: 1932/529, loss: 0.003426668467000127
2023-01-24 10:44:04.659795: step: 1936/529, loss: 0.0005806394619867206
2023-01-24 10:44:05.760769: step: 1940/529, loss: 3.138881947961636e-05
2023-01-24 10:44:06.870993: step: 1944/529, loss: 0.003389429533854127
2023-01-24 10:44:07.981078: step: 1948/529, loss: 0.006837824825197458
2023-01-24 10:44:09.098833: step: 1952/529, loss: 0.007986797951161861
2023-01-24 10:44:10.231801: step: 1956/529, loss: 0.003349900711327791
2023-01-24 10:44:11.328973: step: 1960/529, loss: 0.0003063087642658502
2023-01-24 10:44:12.439636: step: 1964/529, loss: 0.005714362487196922
2023-01-24 10:44:13.547732: step: 1968/529, loss: 0.004642103798687458
2023-01-24 10:44:14.665596: step: 1972/529, loss: 0.0008072683122009039
2023-01-24 10:44:15.769704: step: 1976/529, loss: 0.0020159438718110323
2023-01-24 10:44:16.875190: step: 1980/529, loss: 0.01622905395925045
2023-01-24 10:44:17.977419: step: 1984/529, loss: 0.015225408598780632
2023-01-24 10:44:19.083757: step: 1988/529, loss: 3.215541255485732e-06
2023-01-24 10:44:20.184503: step: 1992/529, loss: 1.694218190095853e-05
2023-01-24 10:44:21.298586: step: 1996/529, loss: 0.020186154171824455
2023-01-24 10:44:22.413650: step: 2000/529, loss: 0.0015899355057626963
2023-01-24 10:44:23.510244: step: 2004/529, loss: 0.005919893737882376
2023-01-24 10:44:24.608889: step: 2008/529, loss: 0.003038746304810047
2023-01-24 10:44:25.723670: step: 2012/529, loss: 0.005171437747776508
2023-01-24 10:44:26.832583: step: 2016/529, loss: 0.033187203109264374
2023-01-24 10:44:27.955607: step: 2020/529, loss: 0.004756687209010124
2023-01-24 10:44:29.075489: step: 2024/529, loss: 0.001483099302276969
2023-01-24 10:44:30.187127: step: 2028/529, loss: 0.022782351821660995
2023-01-24 10:44:31.314618: step: 2032/529, loss: 0.0024399918038398027
2023-01-24 10:44:32.439154: step: 2036/529, loss: 0.010848412290215492
2023-01-24 10:44:33.528507: step: 2040/529, loss: 0.0027393903583288193
2023-01-24 10:44:34.656923: step: 2044/529, loss: 0.015717091038823128
2023-01-24 10:44:35.751001: step: 2048/529, loss: 0.0004864544316660613
2023-01-24 10:44:36.855737: step: 2052/529, loss: 0.0007158090593293309
2023-01-24 10:44:37.987813: step: 2056/529, loss: 0.0589098259806633
2023-01-24 10:44:39.092004: step: 2060/529, loss: 0.011942675337195396
2023-01-24 10:44:40.208007: step: 2064/529, loss: 0.005726232659071684
2023-01-24 10:44:41.304688: step: 2068/529, loss: 0.006156877148896456
2023-01-24 10:44:42.414496: step: 2072/529, loss: 0.0008565317839384079
2023-01-24 10:44:43.519952: step: 2076/529, loss: 0.004122385289520025
2023-01-24 10:44:44.623575: step: 2080/529, loss: 0.0035586629528552294
2023-01-24 10:44:45.718690: step: 2084/529, loss: 0.005014989525079727
2023-01-24 10:44:46.818759: step: 2088/529, loss: 0.0069040898233652115
2023-01-24 10:44:47.943768: step: 2092/529, loss: 0.003997378516942263
2023-01-24 10:44:49.053267: step: 2096/529, loss: 0.00020126454182900488
2023-01-24 10:44:50.146864: step: 2100/529, loss: 0.005807209759950638
2023-01-24 10:44:51.272921: step: 2104/529, loss: 0.029458560049533844
2023-01-24 10:44:52.387150: step: 2108/529, loss: 0.012660758569836617
2023-01-24 10:44:53.506746: step: 2112/529, loss: 0.00018169004761148244
2023-01-24 10:44:54.615196: step: 2116/529, loss: 0.0032339480239897966
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3778121014030612, 'r': 0.3211761317430198, 'f1': 0.3471996336996337}, 'combined': 0.2558313090418353, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3982606082565812, 'r': 0.2872303780759586, 'f1': 0.33375360832769835}, 'combined': 0.205136364142878, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3708183468328374, 'r': 0.33633998061877846, 'f1': 0.35273864634049007}, 'combined': 0.2599126867772032, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37993834134440907, 'r': 0.2913738579634333, 'f1': 0.32981405795959}, 'combined': 0.20271498196540655, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40524553571428573, 'r': 0.3444971537001898, 'f1': 0.37241025641025644}, 'combined': 0.2744075573549258, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39705275174374194, 'r': 0.2841989366900614, 'f1': 0.33127835650538473}, 'combined': 0.20461310254744355, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.39285714285714285, 'r': 0.358695652173913, 'f1': 0.375}, 'combined': 0.1875, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 17
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 10:47:18.560292: step: 4/529, loss: 0.004842862486839294
2023-01-24 10:47:19.693987: step: 8/529, loss: 0.0013065881794318557
2023-01-24 10:47:20.784482: step: 12/529, loss: 0.0008216652786359191
2023-01-24 10:47:21.881800: step: 16/529, loss: 0.00631116796284914
2023-01-24 10:47:22.985990: step: 20/529, loss: 0.0005788739654235542
2023-01-24 10:47:24.099653: step: 24/529, loss: 0.00842339638620615
2023-01-24 10:47:25.200335: step: 28/529, loss: 0.002067488618195057
2023-01-24 10:47:26.310673: step: 32/529, loss: 0.0230601504445076
2023-01-24 10:47:27.418513: step: 36/529, loss: 0.00253194198012352
2023-01-24 10:47:28.512098: step: 40/529, loss: 3.39060316036921e-05
2023-01-24 10:47:29.605305: step: 44/529, loss: 0.001684749498963356
2023-01-24 10:47:30.710538: step: 48/529, loss: 0.0008815735927782953
2023-01-24 10:47:31.867484: step: 52/529, loss: 0.0007355580455623567
2023-01-24 10:47:32.949868: step: 56/529, loss: 0.005363018251955509
2023-01-24 10:47:34.048439: step: 60/529, loss: 0.004475701134651899
2023-01-24 10:47:35.151330: step: 64/529, loss: 0.00017663068138062954
2023-01-24 10:47:36.229961: step: 68/529, loss: 0.0006882011657580733
2023-01-24 10:47:37.311187: step: 72/529, loss: 0.017513057217001915
2023-01-24 10:47:38.393757: step: 76/529, loss: 0.0004277905682101846
2023-01-24 10:47:39.500025: step: 80/529, loss: 0.0017915782518684864
2023-01-24 10:47:40.582300: step: 84/529, loss: 1.4102542081673164e-05
2023-01-24 10:47:41.703346: step: 88/529, loss: 0.004560803063213825
2023-01-24 10:47:42.802940: step: 92/529, loss: 0.00026091779000125825
2023-01-24 10:47:43.884583: step: 96/529, loss: 0.0002933715586550534
2023-01-24 10:47:44.996886: step: 100/529, loss: 0.008458208292722702
2023-01-24 10:47:46.079799: step: 104/529, loss: 2.250103534606751e-05
2023-01-24 10:47:47.192518: step: 108/529, loss: 0.010581783019006252
2023-01-24 10:47:48.294950: step: 112/529, loss: 0.0004243151342961937
2023-01-24 10:47:49.390597: step: 116/529, loss: 9.317338481196202e-06
2023-01-24 10:47:50.464274: step: 120/529, loss: 0.0007180918473750353
2023-01-24 10:47:51.574017: step: 124/529, loss: 4.099328361917287e-05
2023-01-24 10:47:52.656508: step: 128/529, loss: 0.006259743589907885
2023-01-24 10:47:53.744853: step: 132/529, loss: 0.008147217333316803
2023-01-24 10:47:54.839263: step: 136/529, loss: 0.005116383545100689
2023-01-24 10:47:55.921833: step: 140/529, loss: 0.001340121147222817
2023-01-24 10:47:57.022632: step: 144/529, loss: 6.617392500629649e-05
2023-01-24 10:47:58.130854: step: 148/529, loss: 0.0013248852919787169
2023-01-24 10:47:59.270294: step: 152/529, loss: 0.005398974753916264
2023-01-24 10:48:00.394355: step: 156/529, loss: 0.004535573534667492
2023-01-24 10:48:01.491404: step: 160/529, loss: 0.0013997707283124328
2023-01-24 10:48:02.630353: step: 164/529, loss: 0.0009759881650097668
2023-01-24 10:48:03.741323: step: 168/529, loss: 0.0012534017441794276
2023-01-24 10:48:04.860044: step: 172/529, loss: 0.00011824766988866031
2023-01-24 10:48:05.972327: step: 176/529, loss: 3.819718403974548e-05
2023-01-24 10:48:07.095982: step: 180/529, loss: 0.004169910680502653
2023-01-24 10:48:08.214692: step: 184/529, loss: 0.003646740224212408
2023-01-24 10:48:09.311203: step: 188/529, loss: 0.0016268719919025898
2023-01-24 10:48:10.419272: step: 192/529, loss: 0.00851054210215807
2023-01-24 10:48:11.522882: step: 196/529, loss: 3.417914194869809e-05
2023-01-24 10:48:12.639335: step: 200/529, loss: 0.000303057546261698
2023-01-24 10:48:13.742058: step: 204/529, loss: 0.00034946054802276194
2023-01-24 10:48:14.845236: step: 208/529, loss: 0.02442433312535286
2023-01-24 10:48:15.945345: step: 212/529, loss: 6.038112019268738e-07
2023-01-24 10:48:17.054133: step: 216/529, loss: 9.669896826380864e-06
2023-01-24 10:48:18.158019: step: 220/529, loss: 0.0004079095961060375
2023-01-24 10:48:19.263127: step: 224/529, loss: 0.004064992535859346
2023-01-24 10:48:20.368541: step: 228/529, loss: 0.0016780701698735356
2023-01-24 10:48:21.508477: step: 232/529, loss: 0.0067963982000947
2023-01-24 10:48:22.612902: step: 236/529, loss: 0.004488798789680004
2023-01-24 10:48:23.713554: step: 240/529, loss: 0.0002451825712341815
2023-01-24 10:48:24.861210: step: 244/529, loss: 0.002494280692189932
2023-01-24 10:48:25.959514: step: 248/529, loss: 0.010256784036755562
2023-01-24 10:48:27.053228: step: 252/529, loss: 0.0052529508247971535
2023-01-24 10:48:28.189995: step: 256/529, loss: 0.0012607721146196127
2023-01-24 10:48:29.295204: step: 260/529, loss: 0.0013416233705356717
2023-01-24 10:48:30.430755: step: 264/529, loss: 6.637816841248423e-05
2023-01-24 10:48:31.525058: step: 268/529, loss: 0.003095069667324424
2023-01-24 10:48:32.621118: step: 272/529, loss: 0.0009119241731241345
2023-01-24 10:48:33.723341: step: 276/529, loss: 0.00046433028182946146
2023-01-24 10:48:34.855139: step: 280/529, loss: 0.0086233364418149
2023-01-24 10:48:35.963553: step: 284/529, loss: 0.002165513811632991
2023-01-24 10:48:37.065881: step: 288/529, loss: 0.0063567450270056725
2023-01-24 10:48:38.178931: step: 292/529, loss: 0.005430347286164761
2023-01-24 10:48:39.292682: step: 296/529, loss: 7.967089914018288e-05
2023-01-24 10:48:40.400865: step: 300/529, loss: 0.0026248586364090443
2023-01-24 10:48:41.511500: step: 304/529, loss: 0.0022789975628256798
2023-01-24 10:48:42.654198: step: 308/529, loss: 0.002096510259434581
2023-01-24 10:48:43.769945: step: 312/529, loss: 0.00257171131670475
2023-01-24 10:48:44.869906: step: 316/529, loss: 0.003633307060226798
2023-01-24 10:48:46.007001: step: 320/529, loss: 0.005026757717132568
2023-01-24 10:48:47.110132: step: 324/529, loss: 0.0029491554014384747
2023-01-24 10:48:48.216376: step: 328/529, loss: 0.0005399062647484243
2023-01-24 10:48:49.327821: step: 332/529, loss: 0.00029754708521068096
2023-01-24 10:48:50.432672: step: 336/529, loss: 0.00021151950932107866
2023-01-24 10:48:51.541478: step: 340/529, loss: 0.002199131064116955
2023-01-24 10:48:52.668215: step: 344/529, loss: 0.005828639958053827
2023-01-24 10:48:53.771011: step: 348/529, loss: 0.0037635453045368195
2023-01-24 10:48:54.885037: step: 352/529, loss: 0.00010130817099707201
2023-01-24 10:48:55.998755: step: 356/529, loss: 0.0024575141724199057
2023-01-24 10:48:57.090948: step: 360/529, loss: 9.871380461845547e-05
2023-01-24 10:48:58.241666: step: 364/529, loss: 0.0003700211236719042
2023-01-24 10:48:59.373772: step: 368/529, loss: 0.002996712224557996
2023-01-24 10:49:00.471937: step: 372/529, loss: 0.0016520009376108646
2023-01-24 10:49:01.573539: step: 376/529, loss: 0.0014316708547994494
2023-01-24 10:49:02.692847: step: 380/529, loss: 0.0003067987854592502
2023-01-24 10:49:03.786868: step: 384/529, loss: 0.0015367676969617605
2023-01-24 10:49:04.900037: step: 388/529, loss: 0.0012711893068626523
2023-01-24 10:49:05.997657: step: 392/529, loss: 3.714159902301617e-06
2023-01-24 10:49:07.100138: step: 396/529, loss: 0.0005633296095766127
2023-01-24 10:49:08.218193: step: 400/529, loss: 0.004472360946238041
2023-01-24 10:49:09.325739: step: 404/529, loss: 0.0008045222493819892
2023-01-24 10:49:10.418180: step: 408/529, loss: 4.425403312779963e-05
2023-01-24 10:49:11.525929: step: 412/529, loss: 0.0006614141166210175
2023-01-24 10:49:12.634650: step: 416/529, loss: 0.0010520628420636058
2023-01-24 10:49:13.757957: step: 420/529, loss: 0.0005907361046411097
2023-01-24 10:49:14.874034: step: 424/529, loss: 0.011500018648803234
2023-01-24 10:49:15.984378: step: 428/529, loss: 0.00042872282210737467
2023-01-24 10:49:17.108071: step: 432/529, loss: 0.0005655869608744979
2023-01-24 10:49:18.206624: step: 436/529, loss: 0.0015152685809880495
2023-01-24 10:49:19.339470: step: 440/529, loss: 0.0053876349702477455
2023-01-24 10:49:20.445051: step: 444/529, loss: 0.0013738598208874464
2023-01-24 10:49:21.576447: step: 448/529, loss: 9.07934590941295e-05
2023-01-24 10:49:22.691422: step: 452/529, loss: 0.0020978262182325125
2023-01-24 10:49:23.818625: step: 456/529, loss: 0.0002569102216511965
2023-01-24 10:49:24.921855: step: 460/529, loss: 0.002703198464587331
2023-01-24 10:49:26.032971: step: 464/529, loss: 0.002207329263910651
2023-01-24 10:49:27.133441: step: 468/529, loss: 0.0037500066682696342
2023-01-24 10:49:28.262332: step: 472/529, loss: 0.0015458130510523915
2023-01-24 10:49:29.376317: step: 476/529, loss: 0.004095096606761217
2023-01-24 10:49:30.508639: step: 480/529, loss: 0.0002553914673626423
2023-01-24 10:49:31.631288: step: 484/529, loss: 0.003892685053870082
2023-01-24 10:49:32.746749: step: 488/529, loss: 0.001569662126712501
2023-01-24 10:49:33.851283: step: 492/529, loss: 0.00350784114561975
2023-01-24 10:49:34.967061: step: 496/529, loss: 0.004785964265465736
2023-01-24 10:49:36.085276: step: 500/529, loss: 3.7438718436533236e-07
2023-01-24 10:49:37.179914: step: 504/529, loss: 0.0015258623752743006
2023-01-24 10:49:38.289635: step: 508/529, loss: 0.007629902567714453
2023-01-24 10:49:39.409396: step: 512/529, loss: 0.0021656774915754795
2023-01-24 10:49:40.514007: step: 516/529, loss: 0.0007478527841158211
2023-01-24 10:49:41.637651: step: 520/529, loss: 0.001216594479046762
2023-01-24 10:49:42.734490: step: 524/529, loss: 0.0009485668269917369
2023-01-24 10:49:43.823471: step: 528/529, loss: 0.0016025895019993186
2023-01-24 10:49:44.942675: step: 532/529, loss: 0.004400855861604214
2023-01-24 10:49:46.042407: step: 536/529, loss: 0.0213177353143692
2023-01-24 10:49:47.148118: step: 540/529, loss: 0.0005097773973830044
2023-01-24 10:49:48.265555: step: 544/529, loss: 0.004329289309680462
2023-01-24 10:49:49.374036: step: 548/529, loss: 0.006629013456404209
2023-01-24 10:49:50.487744: step: 552/529, loss: 0.0022842606995254755
2023-01-24 10:49:51.609203: step: 556/529, loss: 0.00010522679804125801
2023-01-24 10:49:52.727951: step: 560/529, loss: 0.001462854677811265
2023-01-24 10:49:53.833433: step: 564/529, loss: 0.004420223645865917
2023-01-24 10:49:54.927675: step: 568/529, loss: 0.0016169159207493067
2023-01-24 10:49:56.061652: step: 572/529, loss: 0.0032117897644639015
2023-01-24 10:49:57.182405: step: 576/529, loss: 0.012943688780069351
2023-01-24 10:49:58.290643: step: 580/529, loss: 0.0014955911319702864
2023-01-24 10:49:59.400568: step: 584/529, loss: 0.001204931759275496
2023-01-24 10:50:00.529961: step: 588/529, loss: 0.01061182003468275
2023-01-24 10:50:01.662753: step: 592/529, loss: 2.112128640874289e-05
2023-01-24 10:50:02.774261: step: 596/529, loss: 0.004705323372036219
2023-01-24 10:50:03.871615: step: 600/529, loss: 0.003961293958127499
2023-01-24 10:50:04.980208: step: 604/529, loss: 1.799284655135125e-05
2023-01-24 10:50:06.125798: step: 608/529, loss: 5.442715701065026e-05
2023-01-24 10:50:07.244838: step: 612/529, loss: 0.013039590790867805
2023-01-24 10:50:08.365558: step: 616/529, loss: 0.0018619053298607469
2023-01-24 10:50:09.500237: step: 620/529, loss: 0.00030513707315549254
2023-01-24 10:50:10.596856: step: 624/529, loss: 0.018637683242559433
2023-01-24 10:50:11.719371: step: 628/529, loss: 0.00048135354882106185
2023-01-24 10:50:12.836831: step: 632/529, loss: 0.0030350699089467525
2023-01-24 10:50:13.954401: step: 636/529, loss: 0.0024508938658982515
2023-01-24 10:50:15.074943: step: 640/529, loss: 0.0015894307289272547
2023-01-24 10:50:16.180894: step: 644/529, loss: 5.209509617998265e-05
2023-01-24 10:50:17.292063: step: 648/529, loss: 0.004141865763813257
2023-01-24 10:50:18.415704: step: 652/529, loss: 0.008144120685756207
2023-01-24 10:50:19.515254: step: 656/529, loss: 0.0008340466883964837
2023-01-24 10:50:20.639078: step: 660/529, loss: 1.1782837646023836e-05
2023-01-24 10:50:21.765395: step: 664/529, loss: 0.008086221292614937
2023-01-24 10:50:22.888272: step: 668/529, loss: 0.005556774791330099
2023-01-24 10:50:24.011907: step: 672/529, loss: 0.002798590576276183
2023-01-24 10:50:25.123670: step: 676/529, loss: 7.790603558532894e-05
2023-01-24 10:50:26.231204: step: 680/529, loss: 0.00020661650341935456
2023-01-24 10:50:27.337721: step: 684/529, loss: 0.0002519770059734583
2023-01-24 10:50:28.453481: step: 688/529, loss: 0.019149700179696083
2023-01-24 10:50:29.606059: step: 692/529, loss: 0.016743633896112442
2023-01-24 10:50:30.702432: step: 696/529, loss: 8.994508243631572e-05
2023-01-24 10:50:31.812116: step: 700/529, loss: 0.0001768928050296381
2023-01-24 10:50:32.951070: step: 704/529, loss: 0.0016931819263845682
2023-01-24 10:50:34.082649: step: 708/529, loss: 0.0005771567230112851
2023-01-24 10:50:35.187024: step: 712/529, loss: 0.0004616595106199384
2023-01-24 10:50:36.291244: step: 716/529, loss: 0.006313301622867584
2023-01-24 10:50:37.412363: step: 720/529, loss: 0.0011104469886049628
2023-01-24 10:50:38.551641: step: 724/529, loss: 0.0007758499123156071
2023-01-24 10:50:39.670503: step: 728/529, loss: 0.0031370592769235373
2023-01-24 10:50:40.799317: step: 732/529, loss: 0.005197873339056969
2023-01-24 10:50:41.914883: step: 736/529, loss: 0.0002873981720767915
2023-01-24 10:50:43.011579: step: 740/529, loss: 0.01272734347730875
2023-01-24 10:50:44.108544: step: 744/529, loss: 0.0023828912526369095
2023-01-24 10:50:45.224078: step: 748/529, loss: 0.0005365267861634493
2023-01-24 10:50:46.333553: step: 752/529, loss: 9.01796156540513e-05
2023-01-24 10:50:47.445483: step: 756/529, loss: 0.004060475621372461
2023-01-24 10:50:48.542988: step: 760/529, loss: 5.4697760788258165e-05
2023-01-24 10:50:49.648300: step: 764/529, loss: 0.00575790973380208
2023-01-24 10:50:50.768652: step: 768/529, loss: 0.0002694547001738101
2023-01-24 10:50:51.910791: step: 772/529, loss: 0.00958300568163395
2023-01-24 10:50:53.023290: step: 776/529, loss: 0.003376395907253027
2023-01-24 10:50:54.130138: step: 780/529, loss: 0.00019196349603589624
2023-01-24 10:50:55.247277: step: 784/529, loss: 0.0001764356711646542
2023-01-24 10:50:56.332867: step: 788/529, loss: 2.554372940721805e-06
2023-01-24 10:50:57.439076: step: 792/529, loss: 0.00010924295929726213
2023-01-24 10:50:58.552797: step: 796/529, loss: 0.004579189699143171
2023-01-24 10:50:59.646825: step: 800/529, loss: 0.0007217475795187056
2023-01-24 10:51:00.761924: step: 804/529, loss: 0.004084922838956118
2023-01-24 10:51:01.883887: step: 808/529, loss: 0.0045270659029483795
2023-01-24 10:51:03.023430: step: 812/529, loss: 0.002601429121568799
2023-01-24 10:51:04.128937: step: 816/529, loss: 0.0006457374547608197
2023-01-24 10:51:05.263476: step: 820/529, loss: 0.0026850211434066296
2023-01-24 10:51:06.366896: step: 824/529, loss: 0.0027529338840395212
2023-01-24 10:51:07.480910: step: 828/529, loss: 7.03255645930767e-05
2023-01-24 10:51:08.581315: step: 832/529, loss: 0.00843383651226759
2023-01-24 10:51:09.672402: step: 836/529, loss: 0.004879856947809458
2023-01-24 10:51:10.813350: step: 840/529, loss: 0.0002433170157019049
2023-01-24 10:51:11.921900: step: 844/529, loss: 3.3025737593561644e-06
2023-01-24 10:51:13.049248: step: 848/529, loss: 0.003937841858714819
2023-01-24 10:51:14.162696: step: 852/529, loss: 0.001690792734734714
2023-01-24 10:51:15.267122: step: 856/529, loss: 0.002304457128047943
2023-01-24 10:51:16.377337: step: 860/529, loss: 0.0001353982515865937
2023-01-24 10:51:17.484668: step: 864/529, loss: 0.0001049014535965398
2023-01-24 10:51:18.604400: step: 868/529, loss: 0.0010351944947615266
2023-01-24 10:51:19.697059: step: 872/529, loss: 0.000902494415640831
2023-01-24 10:51:20.833008: step: 876/529, loss: 0.001930189784616232
2023-01-24 10:51:21.931137: step: 880/529, loss: 0.004650223534554243
2023-01-24 10:51:23.042818: step: 884/529, loss: 0.0032582019921392202
2023-01-24 10:51:24.151570: step: 888/529, loss: 1.6641257388982922e-05
2023-01-24 10:51:25.240209: step: 892/529, loss: 0.0037625913973897696
2023-01-24 10:51:26.348370: step: 896/529, loss: 0.01676514931023121
2023-01-24 10:51:27.443138: step: 900/529, loss: 0.0005613972898572683
2023-01-24 10:51:28.558555: step: 904/529, loss: 0.0031099531333893538
2023-01-24 10:51:29.664743: step: 908/529, loss: 0.0079199792817235
2023-01-24 10:51:30.784160: step: 912/529, loss: 0.0034890854731202126
2023-01-24 10:51:31.918710: step: 916/529, loss: 0.002971596084535122
2023-01-24 10:51:33.028384: step: 920/529, loss: 0.003686824580654502
2023-01-24 10:51:34.125647: step: 924/529, loss: 0.000566520553547889
2023-01-24 10:51:35.257382: step: 928/529, loss: 0.0025627606082707644
2023-01-24 10:51:36.376564: step: 932/529, loss: 2.4445507733616978e-05
2023-01-24 10:51:37.470085: step: 936/529, loss: 0.0010556881316006184
2023-01-24 10:51:38.577301: step: 940/529, loss: 0.0012016561813652515
2023-01-24 10:51:39.682922: step: 944/529, loss: 0.021858874708414078
2023-01-24 10:51:40.801877: step: 948/529, loss: 7.777874202474777e-07
2023-01-24 10:51:41.934316: step: 952/529, loss: 0.003460739040747285
2023-01-24 10:51:43.065008: step: 956/529, loss: 0.008115353062748909
2023-01-24 10:51:44.180059: step: 960/529, loss: 0.00017997785471379757
2023-01-24 10:51:45.302023: step: 964/529, loss: 0.000490328820887953
2023-01-24 10:51:46.433753: step: 968/529, loss: 0.0020036338828504086
2023-01-24 10:51:47.554935: step: 972/529, loss: 2.4875193048501387e-05
2023-01-24 10:51:48.648863: step: 976/529, loss: 4.555863881705591e-07
2023-01-24 10:51:49.761651: step: 980/529, loss: 0.0001349975063931197
2023-01-24 10:51:50.867942: step: 984/529, loss: 0.0005957207176834345
2023-01-24 10:51:51.966475: step: 988/529, loss: 3.2971909149637213e-06
2023-01-24 10:51:53.079416: step: 992/529, loss: 0.0005863956757821143
2023-01-24 10:51:54.195124: step: 996/529, loss: 0.0010767682688310742
2023-01-24 10:51:55.293140: step: 1000/529, loss: 0.00014322737115435302
2023-01-24 10:51:56.394418: step: 1004/529, loss: 0.0008324292721226811
2023-01-24 10:51:57.512965: step: 1008/529, loss: 0.0010548168793320656
2023-01-24 10:51:58.627277: step: 1012/529, loss: 0.0015078600263223052
2023-01-24 10:51:59.764961: step: 1016/529, loss: 0.004221107345074415
2023-01-24 10:52:00.910339: step: 1020/529, loss: 0.0022938824258744717
2023-01-24 10:52:02.020856: step: 1024/529, loss: 0.001261079334653914
2023-01-24 10:52:03.108243: step: 1028/529, loss: 0.003426574170589447
2023-01-24 10:52:04.204229: step: 1032/529, loss: 9.506597052677535e-06
2023-01-24 10:52:05.322941: step: 1036/529, loss: 2.8146615704827127e-08
2023-01-24 10:52:06.435036: step: 1040/529, loss: 0.0006548360106535256
2023-01-24 10:52:07.568810: step: 1044/529, loss: 0.0025682817213237286
2023-01-24 10:52:08.675005: step: 1048/529, loss: 0.006028341129422188
2023-01-24 10:52:09.806566: step: 1052/529, loss: 0.004621574655175209
2023-01-24 10:52:10.942607: step: 1056/529, loss: 0.004412304610013962
2023-01-24 10:52:12.024518: step: 1060/529, loss: 0.002328735077753663
2023-01-24 10:52:13.145768: step: 1064/529, loss: 0.001587068778462708
2023-01-24 10:52:14.265340: step: 1068/529, loss: 0.002503716852515936
2023-01-24 10:52:15.398591: step: 1072/529, loss: 0.0031970012933015823
2023-01-24 10:52:16.496500: step: 1076/529, loss: 0.005187684204429388
2023-01-24 10:52:17.599437: step: 1080/529, loss: 0.0017413236200809479
2023-01-24 10:52:18.715477: step: 1084/529, loss: 0.0012308568693697453
2023-01-24 10:52:19.813188: step: 1088/529, loss: 0.0026968386955559254
2023-01-24 10:52:20.935960: step: 1092/529, loss: 0.028410574421286583
2023-01-24 10:52:22.041875: step: 1096/529, loss: 0.00022049243852961808
2023-01-24 10:52:23.147224: step: 1100/529, loss: 0.012427431531250477
2023-01-24 10:52:24.258739: step: 1104/529, loss: 0.00017834726895671338
2023-01-24 10:52:25.347907: step: 1108/529, loss: 0.00025669208844192326
2023-01-24 10:52:26.460059: step: 1112/529, loss: 0.004500517621636391
2023-01-24 10:52:27.577321: step: 1116/529, loss: 0.0016848616069182754
2023-01-24 10:52:28.687469: step: 1120/529, loss: 0.004901230800896883
2023-01-24 10:52:29.799436: step: 1124/529, loss: 0.0004051732539664954
2023-01-24 10:52:30.904472: step: 1128/529, loss: 0.0015182949136942625
2023-01-24 10:52:32.026441: step: 1132/529, loss: 0.0011976333335042
2023-01-24 10:52:33.136579: step: 1136/529, loss: 4.3804629967780784e-05
2023-01-24 10:52:34.236576: step: 1140/529, loss: 0.0009048219071701169
2023-01-24 10:52:35.346853: step: 1144/529, loss: 0.001745416666381061
2023-01-24 10:52:36.440989: step: 1148/529, loss: 0.0002892347692977637
2023-01-24 10:52:37.540032: step: 1152/529, loss: 0.001442312728613615
2023-01-24 10:52:38.665823: step: 1156/529, loss: 0.00014769818517379463
2023-01-24 10:52:39.767329: step: 1160/529, loss: 0.00017743515491019934
2023-01-24 10:52:40.898377: step: 1164/529, loss: 0.0009452521335333586
2023-01-24 10:52:42.015834: step: 1168/529, loss: 0.000552690529730171
2023-01-24 10:52:43.110237: step: 1172/529, loss: 0.0003607508260756731
2023-01-24 10:52:44.232224: step: 1176/529, loss: 0.0001325576740782708
2023-01-24 10:52:45.335492: step: 1180/529, loss: 0.0005411426536738873
2023-01-24 10:52:46.423093: step: 1184/529, loss: 1.0884667744903709e-06
2023-01-24 10:52:47.531816: step: 1188/529, loss: 0.0008633073302917182
2023-01-24 10:52:48.662323: step: 1192/529, loss: 0.005612978246062994
2023-01-24 10:52:49.777071: step: 1196/529, loss: 0.00011484552669571713
2023-01-24 10:52:50.894090: step: 1200/529, loss: 0.0016376245766878128
2023-01-24 10:52:52.003236: step: 1204/529, loss: 0.0061323875561356544
2023-01-24 10:52:53.107369: step: 1208/529, loss: 0.0005072249914519489
2023-01-24 10:52:54.205962: step: 1212/529, loss: 0.005355267319828272
2023-01-24 10:52:55.316903: step: 1216/529, loss: 0.0009103429038077593
2023-01-24 10:52:56.425581: step: 1220/529, loss: 0.007965240627527237
2023-01-24 10:52:57.522059: step: 1224/529, loss: 0.0028630553279072046
2023-01-24 10:52:58.633458: step: 1228/529, loss: 0.0010408902307972312
2023-01-24 10:52:59.769785: step: 1232/529, loss: 0.0006647447589784861
2023-01-24 10:53:00.859658: step: 1236/529, loss: 0.003027283353731036
2023-01-24 10:53:01.961980: step: 1240/529, loss: 0.009570627473294735
2023-01-24 10:53:03.074426: step: 1244/529, loss: 0.0022376119159162045
2023-01-24 10:53:04.199425: step: 1248/529, loss: 1.4767417269467842e-05
2023-01-24 10:53:05.314878: step: 1252/529, loss: 0.00483459560200572
2023-01-24 10:53:06.425497: step: 1256/529, loss: 6.593961734324694e-05
2023-01-24 10:53:07.537113: step: 1260/529, loss: 4.537775384960696e-05
2023-01-24 10:53:08.627829: step: 1264/529, loss: 0.0008101099519990385
2023-01-24 10:53:09.749095: step: 1268/529, loss: 7.064333476591855e-05
2023-01-24 10:53:10.865904: step: 1272/529, loss: 0.004025885835289955
2023-01-24 10:53:11.955280: step: 1276/529, loss: 0.0002958209370262921
2023-01-24 10:53:13.071771: step: 1280/529, loss: 0.03730766847729683
2023-01-24 10:53:14.206082: step: 1284/529, loss: 0.00138117338065058
2023-01-24 10:53:15.315461: step: 1288/529, loss: 0.0011050221510231495
2023-01-24 10:53:16.408789: step: 1292/529, loss: 0.0023243525065481663
2023-01-24 10:53:17.526328: step: 1296/529, loss: 0.0044762128964066505
2023-01-24 10:53:18.646653: step: 1300/529, loss: 0.0013400429161265492
2023-01-24 10:53:19.781098: step: 1304/529, loss: 0.00716488528996706
2023-01-24 10:53:20.925297: step: 1308/529, loss: 8.381266525248066e-05
2023-01-24 10:53:22.064263: step: 1312/529, loss: 0.0010223159333691
2023-01-24 10:53:23.175707: step: 1316/529, loss: 3.6384084523888305e-05
2023-01-24 10:53:24.283979: step: 1320/529, loss: 4.647351670428179e-05
2023-01-24 10:53:25.389364: step: 1324/529, loss: 0.0027985365595668554
2023-01-24 10:53:26.497033: step: 1328/529, loss: 0.0005342587828636169
2023-01-24 10:53:27.609150: step: 1332/529, loss: 0.0009523624903522432
2023-01-24 10:53:28.695657: step: 1336/529, loss: 0.004285859875380993
2023-01-24 10:53:29.819583: step: 1340/529, loss: 0.00176473509054631
2023-01-24 10:53:30.951823: step: 1344/529, loss: 0.013424423523247242
2023-01-24 10:53:32.090373: step: 1348/529, loss: 0.00224280240945518
2023-01-24 10:53:33.200817: step: 1352/529, loss: 0.04319550469517708
2023-01-24 10:53:34.320853: step: 1356/529, loss: 0.0005823468090966344
2023-01-24 10:53:35.417348: step: 1360/529, loss: 2.7107134883408435e-05
2023-01-24 10:53:36.499324: step: 1364/529, loss: 0.0008044968126341701
2023-01-24 10:53:37.597471: step: 1368/529, loss: 0.0037706904113292694
2023-01-24 10:53:38.717360: step: 1372/529, loss: 0.0016748812049627304
2023-01-24 10:53:39.846927: step: 1376/529, loss: 0.0030256675090640783
2023-01-24 10:53:40.950619: step: 1380/529, loss: 0.0036881982814520597
2023-01-24 10:53:42.052144: step: 1384/529, loss: 0.005889815744012594
2023-01-24 10:53:43.149393: step: 1388/529, loss: 2.2178968720254488e-05
2023-01-24 10:53:44.244878: step: 1392/529, loss: 0.0002895708894357085
2023-01-24 10:53:45.362433: step: 1396/529, loss: 0.0044743092730641365
2023-01-24 10:53:46.473312: step: 1400/529, loss: 0.0013484794180840254
2023-01-24 10:53:47.597777: step: 1404/529, loss: 0.0009658017661422491
2023-01-24 10:53:48.706919: step: 1408/529, loss: 1.1041333891625982e-05
2023-01-24 10:53:49.827486: step: 1412/529, loss: 0.0024962471798062325
2023-01-24 10:53:50.943505: step: 1416/529, loss: 0.0006889337091706693
2023-01-24 10:53:52.078476: step: 1420/529, loss: 0.006573179271072149
2023-01-24 10:53:53.195759: step: 1424/529, loss: 0.004180037882179022
2023-01-24 10:53:54.290009: step: 1428/529, loss: 0.00026228599017485976
2023-01-24 10:53:55.409341: step: 1432/529, loss: 0.01669810526072979
2023-01-24 10:53:56.547260: step: 1436/529, loss: 0.0023220593575388193
2023-01-24 10:53:57.653825: step: 1440/529, loss: 0.008205053396522999
2023-01-24 10:53:58.743433: step: 1444/529, loss: 0.001476453966461122
2023-01-24 10:53:59.865166: step: 1448/529, loss: 0.0014017869252711535
2023-01-24 10:54:00.995616: step: 1452/529, loss: 0.011860202066600323
2023-01-24 10:54:02.133343: step: 1456/529, loss: 0.008682110346853733
2023-01-24 10:54:03.243375: step: 1460/529, loss: 0.0003301669785287231
2023-01-24 10:54:04.363729: step: 1464/529, loss: 0.006509534083306789
2023-01-24 10:54:05.463669: step: 1468/529, loss: 0.001540094381198287
2023-01-24 10:54:06.573400: step: 1472/529, loss: 0.006667236797511578
2023-01-24 10:54:07.686164: step: 1476/529, loss: 0.0024610089603811502
2023-01-24 10:54:08.783697: step: 1480/529, loss: 0.006118292920291424
2023-01-24 10:54:09.902756: step: 1484/529, loss: 0.001566186547279358
2023-01-24 10:54:11.000458: step: 1488/529, loss: 0.003366619348526001
2023-01-24 10:54:12.118090: step: 1492/529, loss: 0.0007743968744762242
2023-01-24 10:54:13.247047: step: 1496/529, loss: 0.011823554523289204
2023-01-24 10:54:14.351297: step: 1500/529, loss: 0.0015897094272077084
2023-01-24 10:54:15.444614: step: 1504/529, loss: 0.0020350294653326273
2023-01-24 10:54:16.552669: step: 1508/529, loss: 0.0005968995974399149
2023-01-24 10:54:17.643492: step: 1512/529, loss: 0.008535264059901237
2023-01-24 10:54:18.745617: step: 1516/529, loss: 4.37927374150604e-05
2023-01-24 10:54:19.826764: step: 1520/529, loss: 3.8118469092296436e-05
2023-01-24 10:54:20.932778: step: 1524/529, loss: 3.7810514186276123e-07
2023-01-24 10:54:22.063706: step: 1528/529, loss: 0.00646359845995903
2023-01-24 10:54:23.179562: step: 1532/529, loss: 0.007307383231818676
2023-01-24 10:54:24.297917: step: 1536/529, loss: 0.0006296445499174297
2023-01-24 10:54:25.416624: step: 1540/529, loss: 0.0043194969184696674
2023-01-24 10:54:26.537666: step: 1544/529, loss: 0.005620845127850771
2023-01-24 10:54:27.636215: step: 1548/529, loss: 9.999622852774337e-05
2023-01-24 10:54:28.748161: step: 1552/529, loss: 0.0013472764985635877
2023-01-24 10:54:29.843922: step: 1556/529, loss: 0.0020863700192421675
2023-01-24 10:54:30.936014: step: 1560/529, loss: 6.865925388410687e-05
2023-01-24 10:54:32.039409: step: 1564/529, loss: 0.0009123941999860108
2023-01-24 10:54:33.168117: step: 1568/529, loss: 8.940681084368407e-08
2023-01-24 10:54:34.275112: step: 1572/529, loss: 0.00021895303507335484
2023-01-24 10:54:35.391120: step: 1576/529, loss: 0.002487305784597993
2023-01-24 10:54:36.500689: step: 1580/529, loss: 0.0066758678294718266
2023-01-24 10:54:37.613498: step: 1584/529, loss: 0.002572353696450591
2023-01-24 10:54:38.733650: step: 1588/529, loss: 0.0033786918502300978
2023-01-24 10:54:39.826715: step: 1592/529, loss: 0.0010435506701469421
2023-01-24 10:54:40.936467: step: 1596/529, loss: 0.0017752464627847075
2023-01-24 10:54:42.048440: step: 1600/529, loss: 4.545158390101278e-06
2023-01-24 10:54:43.143544: step: 1604/529, loss: 0.000978256925009191
2023-01-24 10:54:44.260949: step: 1608/529, loss: 0.0003334286739118397
2023-01-24 10:54:45.373440: step: 1612/529, loss: 0.006702768616378307
2023-01-24 10:54:46.480488: step: 1616/529, loss: 0.005314180627465248
2023-01-24 10:54:47.604105: step: 1620/529, loss: 0.0015515672275796533
2023-01-24 10:54:48.706845: step: 1624/529, loss: 0.002230458427220583
2023-01-24 10:54:49.818375: step: 1628/529, loss: 0.0021412870846688747
2023-01-24 10:54:50.928393: step: 1632/529, loss: 0.004244758281856775
2023-01-24 10:54:52.004552: step: 1636/529, loss: 0.003596663475036621
2023-01-24 10:54:53.107224: step: 1640/529, loss: 0.00011061842815252021
2023-01-24 10:54:54.201152: step: 1644/529, loss: 3.9888294850243255e-05
2023-01-24 10:54:55.299498: step: 1648/529, loss: 0.0011892083566635847
2023-01-24 10:54:56.430207: step: 1652/529, loss: 0.0068849679082632065
2023-01-24 10:54:57.542800: step: 1656/529, loss: 0.0009346719016321003
2023-01-24 10:54:58.634736: step: 1660/529, loss: 0.003459784435108304
2023-01-24 10:54:59.727932: step: 1664/529, loss: 0.014529464766383171
2023-01-24 10:55:00.823656: step: 1668/529, loss: 0.0025603496469557285
2023-01-24 10:55:01.925385: step: 1672/529, loss: 0.004857127089053392
2023-01-24 10:55:03.046779: step: 1676/529, loss: 0.002069678856059909
2023-01-24 10:55:04.162809: step: 1680/529, loss: 0.004493404179811478
2023-01-24 10:55:05.261404: step: 1684/529, loss: 0.001952928607352078
2023-01-24 10:55:06.364029: step: 1688/529, loss: 0.0003742296830751002
2023-01-24 10:55:07.498751: step: 1692/529, loss: 0.003166137496009469
2023-01-24 10:55:08.626092: step: 1696/529, loss: 0.0013262351276353002
2023-01-24 10:55:09.717880: step: 1700/529, loss: 0.000526068324688822
2023-01-24 10:55:10.827080: step: 1704/529, loss: 0.0011728373356163502
2023-01-24 10:55:11.944372: step: 1708/529, loss: 0.0034445219207555056
2023-01-24 10:55:13.020579: step: 1712/529, loss: 1.594904279045295e-05
2023-01-24 10:55:14.132079: step: 1716/529, loss: 0.005798977334052324
2023-01-24 10:55:15.234869: step: 1720/529, loss: 0.0011578064877539873
2023-01-24 10:55:16.322496: step: 1724/529, loss: 9.41987891565077e-05
2023-01-24 10:55:17.439595: step: 1728/529, loss: 9.05502474779496e-06
2023-01-24 10:55:18.543714: step: 1732/529, loss: 0.0005693563725799322
2023-01-24 10:55:19.625321: step: 1736/529, loss: 0.0018227536929771304
2023-01-24 10:55:20.719534: step: 1740/529, loss: 0.009879037737846375
2023-01-24 10:55:21.836359: step: 1744/529, loss: 0.0022984629031270742
2023-01-24 10:55:22.944918: step: 1748/529, loss: 1.9943654478993267e-05
2023-01-24 10:55:24.040151: step: 1752/529, loss: 0.00018051273946184665
2023-01-24 10:55:25.150582: step: 1756/529, loss: 0.004394138231873512
2023-01-24 10:55:26.271829: step: 1760/529, loss: 0.007042685989290476
2023-01-24 10:55:27.402203: step: 1764/529, loss: 0.003101650159806013
2023-01-24 10:55:28.501429: step: 1768/529, loss: 0.007048295810818672
2023-01-24 10:55:29.628103: step: 1772/529, loss: 0.007986396551132202
2023-01-24 10:55:30.758164: step: 1776/529, loss: 0.0014402285451069474
2023-01-24 10:55:31.888553: step: 1780/529, loss: 0.0004337396239861846
2023-01-24 10:55:32.982423: step: 1784/529, loss: 0.0002032618212979287
2023-01-24 10:55:34.108442: step: 1788/529, loss: 0.0010365210473537445
2023-01-24 10:55:35.214372: step: 1792/529, loss: 0.0006470062653534114
2023-01-24 10:55:36.314300: step: 1796/529, loss: 0.0062573617324233055
2023-01-24 10:55:37.412912: step: 1800/529, loss: 0.004604674875736237
2023-01-24 10:55:38.545755: step: 1804/529, loss: 0.00022221812105271965
2023-01-24 10:55:39.643662: step: 1808/529, loss: 0.0007624908466823399
2023-01-24 10:55:40.750887: step: 1812/529, loss: 0.006311080418527126
2023-01-24 10:55:41.856749: step: 1816/529, loss: 0.00019560764485504478
2023-01-24 10:55:42.962527: step: 1820/529, loss: 2.190223676734604e-05
2023-01-24 10:55:44.076462: step: 1824/529, loss: 0.00048868014710024
2023-01-24 10:55:45.187214: step: 1828/529, loss: 0.01333986222743988
2023-01-24 10:55:46.287483: step: 1832/529, loss: 0.0012826237361878157
2023-01-24 10:55:47.387733: step: 1836/529, loss: 0.00435735983774066
2023-01-24 10:55:48.483601: step: 1840/529, loss: 0.0010146528948098421
2023-01-24 10:55:49.584637: step: 1844/529, loss: 0.007904020138084888
2023-01-24 10:55:50.680413: step: 1848/529, loss: 0.010664430446922779
2023-01-24 10:55:51.813978: step: 1852/529, loss: 0.015014898031949997
2023-01-24 10:55:52.936439: step: 1856/529, loss: 0.00012321044050622731
2023-01-24 10:55:54.040138: step: 1860/529, loss: 0.0026684151962399483
2023-01-24 10:55:55.148647: step: 1864/529, loss: 0.0013764566974714398
2023-01-24 10:55:56.268059: step: 1868/529, loss: 1.3779986147710588e-05
2023-01-24 10:55:57.394570: step: 1872/529, loss: 0.003624596633017063
2023-01-24 10:55:58.490421: step: 1876/529, loss: 0.010003188624978065
2023-01-24 10:55:59.598751: step: 1880/529, loss: 0.0003086858778260648
2023-01-24 10:56:00.711274: step: 1884/529, loss: 0.0012069636723026633
2023-01-24 10:56:01.867147: step: 1888/529, loss: 0.03438347950577736
2023-01-24 10:56:02.969659: step: 1892/529, loss: 0.012207458727061749
2023-01-24 10:56:04.073239: step: 1896/529, loss: 0.005559282843023539
2023-01-24 10:56:05.166281: step: 1900/529, loss: 0.002000851323828101
2023-01-24 10:56:06.293306: step: 1904/529, loss: 0.015440421178936958
2023-01-24 10:56:07.382920: step: 1908/529, loss: 0.002642447827383876
2023-01-24 10:56:08.494850: step: 1912/529, loss: 0.006181693635880947
2023-01-24 10:56:09.615339: step: 1916/529, loss: 0.004210350103676319
2023-01-24 10:56:10.720873: step: 1920/529, loss: 0.0025464389473199844
2023-01-24 10:56:11.823452: step: 1924/529, loss: 0.001145868911407888
2023-01-24 10:56:12.916346: step: 1928/529, loss: 0.00023305659124162048
2023-01-24 10:56:14.010045: step: 1932/529, loss: 5.066372921191942e-08
2023-01-24 10:56:15.117497: step: 1936/529, loss: 0.0004435488663148135
2023-01-24 10:56:16.224163: step: 1940/529, loss: 0.003970756661146879
2023-01-24 10:56:17.346945: step: 1944/529, loss: 0.0027187990490347147
2023-01-24 10:56:18.451514: step: 1948/529, loss: 0.02167487144470215
2023-01-24 10:56:19.564022: step: 1952/529, loss: 0.0005582596641033888
2023-01-24 10:56:20.683637: step: 1956/529, loss: 9.770326141733676e-05
2023-01-24 10:56:21.781687: step: 1960/529, loss: 1.2801962839148473e-05
2023-01-24 10:56:22.889705: step: 1964/529, loss: 0.002035159384831786
2023-01-24 10:56:23.989158: step: 1968/529, loss: 0.0045582628808915615
2023-01-24 10:56:25.096770: step: 1972/529, loss: 0.0003882398596033454
2023-01-24 10:56:26.200140: step: 1976/529, loss: 0.0017868814757093787
2023-01-24 10:56:27.319074: step: 1980/529, loss: 0.010101956315338612
2023-01-24 10:56:28.413441: step: 1984/529, loss: 0.004891541320830584
2023-01-24 10:56:29.515948: step: 1988/529, loss: 7.464100781362504e-05
2023-01-24 10:56:30.620954: step: 1992/529, loss: 0.000726512516848743
2023-01-24 10:56:31.734526: step: 1996/529, loss: 0.0005451508332043886
2023-01-24 10:56:32.879949: step: 2000/529, loss: 0.0024449219927191734
2023-01-24 10:56:33.990798: step: 2004/529, loss: 0.004650231916457415
2023-01-24 10:56:35.104472: step: 2008/529, loss: 0.0001269980421056971
2023-01-24 10:56:36.215249: step: 2012/529, loss: 0.0017350054113194346
2023-01-24 10:56:37.302191: step: 2016/529, loss: 3.4396216506138444e-05
2023-01-24 10:56:38.408058: step: 2020/529, loss: 6.057574410078814e-06
2023-01-24 10:56:39.497845: step: 2024/529, loss: 0.0005801632069051266
2023-01-24 10:56:40.604711: step: 2028/529, loss: 0.0032070535235106945
2023-01-24 10:56:41.705718: step: 2032/529, loss: 0.004249269608408213
2023-01-24 10:56:42.836746: step: 2036/529, loss: 0.00044874960440211
2023-01-24 10:56:43.954066: step: 2040/529, loss: 0.0022949082776904106
2023-01-24 10:56:45.042679: step: 2044/529, loss: 0.007284983526915312
2023-01-24 10:56:46.149973: step: 2048/529, loss: 0.0013661193661391735
2023-01-24 10:56:47.241045: step: 2052/529, loss: 0.00013617941294796765
2023-01-24 10:56:48.324415: step: 2056/529, loss: 0.0016213099006563425
2023-01-24 10:56:49.428683: step: 2060/529, loss: 0.0213764738291502
2023-01-24 10:56:50.540879: step: 2064/529, loss: 0.004255141131579876
2023-01-24 10:56:51.630612: step: 2068/529, loss: 0.003251240588724613
2023-01-24 10:56:52.741681: step: 2072/529, loss: 0.009862186387181282
2023-01-24 10:56:53.853586: step: 2076/529, loss: 0.0055041927844285965
2023-01-24 10:56:54.974390: step: 2080/529, loss: 9.721294190967456e-05
2023-01-24 10:56:56.067883: step: 2084/529, loss: 0.004663102328777313
2023-01-24 10:56:57.174017: step: 2088/529, loss: 0.0009821791900321841
2023-01-24 10:56:58.333803: step: 2092/529, loss: 0.00024189826217480004
2023-01-24 10:56:59.476982: step: 2096/529, loss: 0.011187217198312283
2023-01-24 10:57:00.599054: step: 2100/529, loss: 0.00202218652702868
2023-01-24 10:57:01.717221: step: 2104/529, loss: 0.0006239673239178956
2023-01-24 10:57:02.804917: step: 2108/529, loss: 0.0010713990777730942
2023-01-24 10:57:03.933048: step: 2112/529, loss: 0.0006448101485148072
2023-01-24 10:57:05.036720: step: 2116/529, loss: 0.015399581752717495
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37696191004117835, 'r': 0.3225992816481431, 'f1': 0.3476683464796962}, 'combined': 0.2561766763534603, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3985908859885564, 'r': 0.2897900808876939, 'f1': 0.33559232648710363}, 'combined': 0.20626650310914663, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3663546536396148, 'r': 0.3315961476017007, 'f1': 0.3481098999723033}, 'combined': 0.25650203155853923, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38106828484723393, 'r': 0.29224040908994975, 'f1': 0.3307949309365395}, 'combined': 0.2033178599902633, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40739514348785877, 'r': 0.35018975332068314, 'f1': 0.3766326530612245}, 'combined': 0.2775187969924812, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.39648991978508474, 'r': 0.287231865632869, 'f1': 0.3331312290857596}, 'combined': 0.20575752384708684, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.358695652173913, 'r': 0.358695652173913, 'f1': 0.358695652173913}, 'combined': 0.1793478260869565, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 18
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 10:59:31.428990: step: 4/529, loss: 0.005106932483613491
2023-01-24 10:59:32.515979: step: 8/529, loss: 0.003267749911174178
2023-01-24 10:59:33.642261: step: 12/529, loss: 0.0031423766631633043
2023-01-24 10:59:34.738515: step: 16/529, loss: 0.0069333529099822044
2023-01-24 10:59:35.843637: step: 20/529, loss: 0.005248202942311764
2023-01-24 10:59:36.919728: step: 24/529, loss: 3.232617018511519e-05
2023-01-24 10:59:38.012148: step: 28/529, loss: 0.039188578724861145
2023-01-24 10:59:39.111822: step: 32/529, loss: 0.008622698485851288
2023-01-24 10:59:40.232617: step: 36/529, loss: 0.0001221944548888132
2023-01-24 10:59:41.329051: step: 40/529, loss: 0.0001730604999465868
2023-01-24 10:59:42.432332: step: 44/529, loss: 0.00037821251316927373
2023-01-24 10:59:43.521021: step: 48/529, loss: 0.0001407468516845256
2023-01-24 10:59:44.603939: step: 52/529, loss: 0.003944792784750462
2023-01-24 10:59:45.710774: step: 56/529, loss: 0.0006200163043104112
2023-01-24 10:59:46.788809: step: 60/529, loss: 0.0011825788533315063
2023-01-24 10:59:47.860655: step: 64/529, loss: 0.00036721606738865376
2023-01-24 10:59:48.954308: step: 68/529, loss: 9.044127364177257e-05
2023-01-24 10:59:50.054680: step: 72/529, loss: 0.0022320484276860952
2023-01-24 10:59:51.134502: step: 76/529, loss: 0.00011526072194101289
2023-01-24 10:59:52.255382: step: 80/529, loss: 0.006719253957271576
2023-01-24 10:59:53.359182: step: 84/529, loss: 0.004242526367306709
2023-01-24 10:59:54.457219: step: 88/529, loss: 4.265863390173763e-05
2023-01-24 10:59:55.562104: step: 92/529, loss: 8.658689330331981e-05
2023-01-24 10:59:56.676217: step: 96/529, loss: 1.9944891391787678e-05
2023-01-24 10:59:57.792547: step: 100/529, loss: 0.0044161598198115826
2023-01-24 10:59:58.895663: step: 104/529, loss: 0.0012425644090399146
2023-01-24 11:00:00.024282: step: 108/529, loss: 2.4390041289734654e-05
2023-01-24 11:00:01.145235: step: 112/529, loss: 0.0029318369925022125
2023-01-24 11:00:02.243489: step: 116/529, loss: 1.213944506162079e-05
2023-01-24 11:00:03.377973: step: 120/529, loss: 0.0011261332547292113
2023-01-24 11:00:04.492769: step: 124/529, loss: 0.0033326521515846252
2023-01-24 11:00:05.584444: step: 128/529, loss: 0.00011628385254880413
2023-01-24 11:00:06.715565: step: 132/529, loss: 0.009727424941956997
2023-01-24 11:00:07.823076: step: 136/529, loss: 0.00048684608191251755
2023-01-24 11:00:08.915694: step: 140/529, loss: 9.700184818939306e-06
2023-01-24 11:00:10.025146: step: 144/529, loss: 0.00033302439260296524
2023-01-24 11:00:11.122205: step: 148/529, loss: 0.0008136171963997185
2023-01-24 11:00:12.245331: step: 152/529, loss: 0.002355230040848255
2023-01-24 11:00:13.358374: step: 156/529, loss: 0.0035317454021424055
2023-01-24 11:00:14.468961: step: 160/529, loss: 0.004527253098785877
2023-01-24 11:00:15.574107: step: 164/529, loss: 0.00010868141544051468
2023-01-24 11:00:16.690008: step: 168/529, loss: 0.001424109097570181
2023-01-24 11:00:17.820468: step: 172/529, loss: 8.110309863695875e-05
2023-01-24 11:00:18.932223: step: 176/529, loss: 0.004578886087983847
2023-01-24 11:00:20.036061: step: 180/529, loss: 0.002410543616861105
2023-01-24 11:00:21.141441: step: 184/529, loss: 0.0005429271259345114
2023-01-24 11:00:22.259281: step: 188/529, loss: 0.0018217784818261862
2023-01-24 11:00:23.372505: step: 192/529, loss: 0.009847326204180717
2023-01-24 11:00:24.466373: step: 196/529, loss: 0.00021384851424954832
2023-01-24 11:00:25.572866: step: 200/529, loss: 0.0008671731338836253
2023-01-24 11:00:26.665855: step: 204/529, loss: 0.0010139402002096176
2023-01-24 11:00:27.763808: step: 208/529, loss: 0.002458571456372738
2023-01-24 11:00:28.895590: step: 212/529, loss: 0.0037513214629143476
2023-01-24 11:00:30.014721: step: 216/529, loss: 0.0011582538718357682
2023-01-24 11:00:31.122918: step: 220/529, loss: 0.0023672557435929775
2023-01-24 11:00:32.222112: step: 224/529, loss: 6.956825382076204e-05
2023-01-24 11:00:33.338039: step: 228/529, loss: 0.003049969905987382
2023-01-24 11:00:34.443729: step: 232/529, loss: 1.3972776287118904e-06
2023-01-24 11:00:35.564944: step: 236/529, loss: 0.00615348294377327
2023-01-24 11:00:36.665290: step: 240/529, loss: 0.001702405046671629
2023-01-24 11:00:37.787052: step: 244/529, loss: 0.0005352931912057102
2023-01-24 11:00:38.894614: step: 248/529, loss: 5.640329618472606e-05
2023-01-24 11:00:40.023387: step: 252/529, loss: 0.0008387555135414004
2023-01-24 11:00:41.141383: step: 256/529, loss: 0.007005666848272085
2023-01-24 11:00:42.242472: step: 260/529, loss: 0.00030807958682999015
2023-01-24 11:00:43.343511: step: 264/529, loss: 0.0024762593675404787
2023-01-24 11:00:44.459316: step: 268/529, loss: 0.00018462726438883692
2023-01-24 11:00:45.559832: step: 272/529, loss: 0.006993254646658897
2023-01-24 11:00:46.676872: step: 276/529, loss: 0.014611868187785149
2023-01-24 11:00:47.774501: step: 280/529, loss: 0.004979503341019154
2023-01-24 11:00:48.873775: step: 284/529, loss: 0.0018948083743453026
2023-01-24 11:00:49.968181: step: 288/529, loss: 0.0008982406579889357
2023-01-24 11:00:51.066995: step: 292/529, loss: 0.006685532629489899
2023-01-24 11:00:52.184085: step: 296/529, loss: 0.00034208057331852615
2023-01-24 11:00:53.289101: step: 300/529, loss: 0.0028365645557641983
2023-01-24 11:00:54.406799: step: 304/529, loss: 0.0027116844430565834
2023-01-24 11:00:55.537002: step: 308/529, loss: 0.00469971913844347
2023-01-24 11:00:56.642272: step: 312/529, loss: 0.0026702755130827427
2023-01-24 11:00:57.766982: step: 316/529, loss: 3.436918996158056e-05
2023-01-24 11:00:58.869071: step: 320/529, loss: 0.0004892255528829992
2023-01-24 11:01:00.009453: step: 324/529, loss: 0.0006125149666331708
2023-01-24 11:01:01.115743: step: 328/529, loss: 0.004796868190169334
2023-01-24 11:01:02.230774: step: 332/529, loss: 0.0001806049549486488
2023-01-24 11:01:03.356241: step: 336/529, loss: 0.01030789501965046
2023-01-24 11:01:04.460215: step: 340/529, loss: 0.001344239222817123
2023-01-24 11:01:05.589621: step: 344/529, loss: 0.008899343200027943
2023-01-24 11:01:06.711558: step: 348/529, loss: 0.007085543591529131
2023-01-24 11:01:07.832825: step: 352/529, loss: 0.0006947821821086109
2023-01-24 11:01:08.937879: step: 356/529, loss: 0.0036569712683558464
2023-01-24 11:01:10.047833: step: 360/529, loss: 4.1255018004449084e-05
2023-01-24 11:01:11.165449: step: 364/529, loss: 0.004831678234040737
2023-01-24 11:01:12.292790: step: 368/529, loss: 7.885137165430933e-06
2023-01-24 11:01:13.419042: step: 372/529, loss: 0.011029841378331184
2023-01-24 11:01:14.518984: step: 376/529, loss: 0.001048399950377643
2023-01-24 11:01:15.628386: step: 380/529, loss: 0.0010899422923102975
2023-01-24 11:01:16.742278: step: 384/529, loss: 0.0016569980653002858
2023-01-24 11:01:17.869112: step: 388/529, loss: 0.003423633985221386
2023-01-24 11:01:18.984520: step: 392/529, loss: 0.0063781579956412315
2023-01-24 11:01:20.078431: step: 396/529, loss: 2.6601039735396625e-06
2023-01-24 11:01:21.189781: step: 400/529, loss: 0.00027619063621386886
2023-01-24 11:01:22.308390: step: 404/529, loss: 0.0022866709623485804
2023-01-24 11:01:23.420364: step: 408/529, loss: 0.0001205329317599535
2023-01-24 11:01:24.507630: step: 412/529, loss: 0.0007061202195473015
2023-01-24 11:01:25.631844: step: 416/529, loss: 0.0023702888283878565
2023-01-24 11:01:26.724160: step: 420/529, loss: 0.0038488905411213636
2023-01-24 11:01:27.831239: step: 424/529, loss: 0.002321971347555518
2023-01-24 11:01:28.931797: step: 428/529, loss: 0.0011883003171533346
2023-01-24 11:01:30.034866: step: 432/529, loss: 0.00013296572433318943
2023-01-24 11:01:31.150565: step: 436/529, loss: 0.008017114363610744
2023-01-24 11:01:32.240872: step: 440/529, loss: 0.0010055091697722673
2023-01-24 11:01:33.348675: step: 444/529, loss: 0.0005035348585806787
2023-01-24 11:01:34.486640: step: 448/529, loss: 0.029983503744006157
2023-01-24 11:01:35.601123: step: 452/529, loss: 0.000848477182444185
2023-01-24 11:01:36.717147: step: 456/529, loss: 0.0005775055033154786
2023-01-24 11:01:37.836764: step: 460/529, loss: 7.234374606923666e-06
2023-01-24 11:01:38.970606: step: 464/529, loss: 0.004597551189363003
2023-01-24 11:01:40.075020: step: 468/529, loss: 0.00011185939365532249
2023-01-24 11:01:41.189623: step: 472/529, loss: 0.014785099774599075
2023-01-24 11:01:42.294720: step: 476/529, loss: 0.0021692917216569185
2023-01-24 11:01:43.440747: step: 480/529, loss: 1.0873933433686034e-06
2023-01-24 11:01:44.553579: step: 484/529, loss: 0.0007050866261124611
2023-01-24 11:01:45.666824: step: 488/529, loss: 4.188654202152975e-05
2023-01-24 11:01:46.769907: step: 492/529, loss: 0.0036822918336838484
2023-01-24 11:01:47.862586: step: 496/529, loss: 0.004835766740143299
2023-01-24 11:01:48.960849: step: 500/529, loss: 0.001007765531539917
2023-01-24 11:01:50.069888: step: 504/529, loss: 0.0021588648669421673
2023-01-24 11:01:51.184675: step: 508/529, loss: 0.0013948113191872835
2023-01-24 11:01:52.286861: step: 512/529, loss: 0.00453182402998209
2023-01-24 11:01:53.400965: step: 516/529, loss: 6.869457138236612e-05
2023-01-24 11:01:54.514204: step: 520/529, loss: 0.008398565463721752
2023-01-24 11:01:55.630179: step: 524/529, loss: 0.004977534059435129
2023-01-24 11:01:56.722879: step: 528/529, loss: 3.146576773360721e-06
2023-01-24 11:01:57.836877: step: 532/529, loss: 0.00215600011870265
2023-01-24 11:01:58.934113: step: 536/529, loss: 0.00429950887337327
2023-01-24 11:02:00.056541: step: 540/529, loss: 0.0013584947446361184
2023-01-24 11:02:01.200268: step: 544/529, loss: 0.007589603308588266
2023-01-24 11:02:02.358022: step: 548/529, loss: 0.0031090250704437494
2023-01-24 11:02:03.453895: step: 552/529, loss: 0.0013651290209963918
2023-01-24 11:02:04.576186: step: 556/529, loss: 0.002238328568637371
2023-01-24 11:02:05.689659: step: 560/529, loss: 0.001540915691293776
2023-01-24 11:02:06.794967: step: 564/529, loss: 0.0011681547621265054
2023-01-24 11:02:07.908339: step: 568/529, loss: 0.0008219557348638773
2023-01-24 11:02:09.029260: step: 572/529, loss: 0.00010092512093251571
2023-01-24 11:02:10.130719: step: 576/529, loss: 0.0007694021915085614
2023-01-24 11:02:11.259472: step: 580/529, loss: 0.004103308077901602
2023-01-24 11:02:12.379433: step: 584/529, loss: 0.001777102705091238
2023-01-24 11:02:13.494079: step: 588/529, loss: 0.0024286648258566856
2023-01-24 11:02:14.593202: step: 592/529, loss: 0.0028878971934318542
2023-01-24 11:02:15.697820: step: 596/529, loss: 0.001692973542958498
2023-01-24 11:02:16.820247: step: 600/529, loss: 0.001142262713983655
2023-01-24 11:02:17.927222: step: 604/529, loss: 0.001316947746090591
2023-01-24 11:02:19.034303: step: 608/529, loss: 0.013509968295693398
2023-01-24 11:02:20.148230: step: 612/529, loss: 5.352353400667198e-05
2023-01-24 11:02:21.263634: step: 616/529, loss: 0.0003583582874853164
2023-01-24 11:02:22.356243: step: 620/529, loss: 0.0010619476670399308
2023-01-24 11:02:23.435670: step: 624/529, loss: 4.98524332215311e-06
2023-01-24 11:02:24.566055: step: 628/529, loss: 0.003712043631821871
2023-01-24 11:02:25.669915: step: 632/529, loss: 1.645502015890088e-05
2023-01-24 11:02:26.756420: step: 636/529, loss: 0.0005195161211304367
2023-01-24 11:02:27.865576: step: 640/529, loss: 9.147680248133838e-05
2023-01-24 11:02:28.962787: step: 644/529, loss: 0.0006765939178876579
2023-01-24 11:02:30.086597: step: 648/529, loss: 0.010582037270069122
2023-01-24 11:02:31.237430: step: 652/529, loss: 0.009574136696755886
2023-01-24 11:02:32.362287: step: 656/529, loss: 0.0003639789065346122
2023-01-24 11:02:33.458979: step: 660/529, loss: 0.018032602965831757
2023-01-24 11:02:34.572756: step: 664/529, loss: 0.004070539493113756
2023-01-24 11:02:35.672189: step: 668/529, loss: 4.918778358842246e-05
2023-01-24 11:02:36.780355: step: 672/529, loss: 0.005503579042851925
2023-01-24 11:02:37.910586: step: 676/529, loss: 0.005368916783481836
2023-01-24 11:02:39.042573: step: 680/529, loss: 0.0029425546526908875
2023-01-24 11:02:40.158255: step: 684/529, loss: 0.0016450523398816586
2023-01-24 11:02:41.255334: step: 688/529, loss: 0.001709225121885538
2023-01-24 11:02:42.357745: step: 692/529, loss: 0.0037631175946444273
2023-01-24 11:02:43.491892: step: 696/529, loss: 0.002494571730494499
2023-01-24 11:02:44.611344: step: 700/529, loss: 0.0022283089347183704
2023-01-24 11:02:45.728220: step: 704/529, loss: 0.0002642963663674891
2023-01-24 11:02:46.843157: step: 708/529, loss: 0.007430787663906813
2023-01-24 11:02:47.957173: step: 712/529, loss: 0.0003395665262360126
2023-01-24 11:02:49.061262: step: 716/529, loss: 0.008697547018527985
2023-01-24 11:02:50.165264: step: 720/529, loss: 1.3025874977756757e-05
2023-01-24 11:02:51.299005: step: 724/529, loss: 0.018177006393671036
2023-01-24 11:02:52.394156: step: 728/529, loss: 0.0010303236776962876
2023-01-24 11:02:53.496466: step: 732/529, loss: 0.006078480742871761
2023-01-24 11:02:54.601545: step: 736/529, loss: 0.0
2023-01-24 11:02:55.724358: step: 740/529, loss: 0.0017693494446575642
2023-01-24 11:02:56.824504: step: 744/529, loss: 2.5048311727005057e-05
2023-01-24 11:02:57.960121: step: 748/529, loss: 0.00029898740467615426
2023-01-24 11:02:59.071297: step: 752/529, loss: 0.00018677431216929108
2023-01-24 11:03:00.190480: step: 756/529, loss: 0.0004084084939677268
2023-01-24 11:03:01.315455: step: 760/529, loss: 0.0027451668865978718
2023-01-24 11:03:02.430660: step: 764/529, loss: 0.0017125324811786413
2023-01-24 11:03:03.545364: step: 768/529, loss: 0.0001601610129000619
2023-01-24 11:03:04.656289: step: 772/529, loss: 0.0008451167959719896
2023-01-24 11:03:05.750774: step: 776/529, loss: 0.004501692485064268
2023-01-24 11:03:06.858743: step: 780/529, loss: 0.003973223268985748
2023-01-24 11:03:07.940011: step: 784/529, loss: 0.000528763746842742
2023-01-24 11:03:09.030843: step: 788/529, loss: 0.008562888950109482
2023-01-24 11:03:10.148620: step: 792/529, loss: 0.0010988907888531685
2023-01-24 11:03:11.270243: step: 796/529, loss: 0.00361588760279119
2023-01-24 11:03:12.373370: step: 800/529, loss: 0.0018999911844730377
2023-01-24 11:03:13.477571: step: 804/529, loss: 0.0041298349387943745
2023-01-24 11:03:14.579875: step: 808/529, loss: 1.4402733540919144e-05
2023-01-24 11:03:15.691633: step: 812/529, loss: 0.0009572546696290374
2023-01-24 11:03:16.798031: step: 816/529, loss: 0.010263328440487385
2023-01-24 11:03:17.905617: step: 820/529, loss: 0.0022119341883808374
2023-01-24 11:03:19.033564: step: 824/529, loss: 0.00024054963432718068
2023-01-24 11:03:20.152495: step: 828/529, loss: 0.0017124079167842865
2023-01-24 11:03:21.264235: step: 832/529, loss: 0.003546376945450902
2023-01-24 11:03:22.356468: step: 836/529, loss: 0.0018881323048844934
2023-01-24 11:03:23.462400: step: 840/529, loss: 0.0010882930364459753
2023-01-24 11:03:24.549608: step: 844/529, loss: 0.0008502752752974629
2023-01-24 11:03:25.658702: step: 848/529, loss: 0.00039398297667503357
2023-01-24 11:03:26.795124: step: 852/529, loss: 0.003617528360337019
2023-01-24 11:03:27.886570: step: 856/529, loss: 7.243848085636273e-05
2023-01-24 11:03:29.037607: step: 860/529, loss: 0.0009569402900524437
2023-01-24 11:03:30.164564: step: 864/529, loss: 0.0003646343247964978
2023-01-24 11:03:31.243797: step: 868/529, loss: 0.0003610481508076191
2023-01-24 11:03:32.373051: step: 872/529, loss: 0.0004116895725019276
2023-01-24 11:03:33.481354: step: 876/529, loss: 0.005916376132518053
2023-01-24 11:03:34.591140: step: 880/529, loss: 0.0031686441507190466
2023-01-24 11:03:35.704065: step: 884/529, loss: 0.0004516146727837622
2023-01-24 11:03:36.803431: step: 888/529, loss: 0.007660240400582552
2023-01-24 11:03:37.895956: step: 892/529, loss: 0.01721937209367752
2023-01-24 11:03:39.013246: step: 896/529, loss: 0.005537746008485556
2023-01-24 11:03:40.139106: step: 900/529, loss: 0.006335179787129164
2023-01-24 11:03:41.226300: step: 904/529, loss: 7.450579597723106e-10
2023-01-24 11:03:42.346648: step: 908/529, loss: 0.01355667132884264
2023-01-24 11:03:43.468556: step: 912/529, loss: 0.000181439274456352
2023-01-24 11:03:44.566238: step: 916/529, loss: 0.004046508576720953
2023-01-24 11:03:45.710242: step: 920/529, loss: 0.003777015721425414
2023-01-24 11:03:46.811881: step: 924/529, loss: 0.002511204918846488
2023-01-24 11:03:47.917616: step: 928/529, loss: 0.0005360101931728423
2023-01-24 11:03:49.030075: step: 932/529, loss: 0.0024796377401798964
2023-01-24 11:03:50.131765: step: 936/529, loss: 0.012718910351395607
2023-01-24 11:03:51.249144: step: 940/529, loss: 0.0012683564564213157
2023-01-24 11:03:52.356013: step: 944/529, loss: 0.0006419944693334401
2023-01-24 11:03:53.449747: step: 948/529, loss: 0.0005474080098792911
2023-01-24 11:03:54.566363: step: 952/529, loss: 0.00010657100938260555
2023-01-24 11:03:55.727589: step: 956/529, loss: 0.0025238357484340668
2023-01-24 11:03:56.842700: step: 960/529, loss: 0.0017542983405292034
2023-01-24 11:03:57.946800: step: 964/529, loss: 0.000137905910378322
2023-01-24 11:03:59.054569: step: 968/529, loss: 3.4363692975603044e-05
2023-01-24 11:04:00.145425: step: 972/529, loss: 0.00024384722928516567
2023-01-24 11:04:01.266491: step: 976/529, loss: 0.0032568054739385843
2023-01-24 11:04:02.370704: step: 980/529, loss: 0.0012569173704832792
2023-01-24 11:04:03.477706: step: 984/529, loss: 0.00011453461047494784
2023-01-24 11:04:04.579643: step: 988/529, loss: 0.0051637813448905945
2023-01-24 11:04:05.685058: step: 992/529, loss: 0.001042092451825738
2023-01-24 11:04:06.815143: step: 996/529, loss: 0.005345347803086042
2023-01-24 11:04:07.912158: step: 1000/529, loss: 0.0013013023417443037
2023-01-24 11:04:09.021363: step: 1004/529, loss: 0.00014702248154208064
2023-01-24 11:04:10.148711: step: 1008/529, loss: 7.827518129488453e-05
2023-01-24 11:04:11.274858: step: 1012/529, loss: 0.007932577282190323
2023-01-24 11:04:12.375295: step: 1016/529, loss: 0.01244633924216032
2023-01-24 11:04:13.482372: step: 1020/529, loss: 0.0005064822034910321
2023-01-24 11:04:14.587803: step: 1024/529, loss: 0.00787703599780798
2023-01-24 11:04:15.736886: step: 1028/529, loss: 0.0034599213395267725
2023-01-24 11:04:16.839954: step: 1032/529, loss: 0.00022355469991452992
2023-01-24 11:04:17.940536: step: 1036/529, loss: 0.01336802076548338
2023-01-24 11:04:19.067831: step: 1040/529, loss: 0.007297166623175144
2023-01-24 11:04:20.159859: step: 1044/529, loss: 0.0017687611980363727
2023-01-24 11:04:21.282463: step: 1048/529, loss: 0.0019895865116268396
2023-01-24 11:04:22.400093: step: 1052/529, loss: 0.0004506449040491134
2023-01-24 11:04:23.522336: step: 1056/529, loss: 0.006986568216234446
2023-01-24 11:04:24.651338: step: 1060/529, loss: 0.00833398662507534
2023-01-24 11:04:25.744679: step: 1064/529, loss: 0.003777771722525358
2023-01-24 11:04:26.845399: step: 1068/529, loss: 0.003777691861614585
2023-01-24 11:04:27.951143: step: 1072/529, loss: 5.398679604695644e-06
2023-01-24 11:04:29.067233: step: 1076/529, loss: 0.00018647620163392276
2023-01-24 11:04:30.165092: step: 1080/529, loss: 2.152389377840791e-09
2023-01-24 11:04:31.269732: step: 1084/529, loss: 0.001387969241477549
2023-01-24 11:04:32.376597: step: 1088/529, loss: 0.0002159702853532508
2023-01-24 11:04:33.491547: step: 1092/529, loss: 0.0013747360790148377
2023-01-24 11:04:34.598253: step: 1096/529, loss: 0.003941033501178026
2023-01-24 11:04:35.709757: step: 1100/529, loss: 0.0008925424772314727
2023-01-24 11:04:36.811413: step: 1104/529, loss: 0.02873014099895954
2023-01-24 11:04:37.913134: step: 1108/529, loss: 0.006290366407483816
2023-01-24 11:04:39.022350: step: 1112/529, loss: 0.002604166278615594
2023-01-24 11:04:40.121133: step: 1116/529, loss: 0.0058943526819348335
2023-01-24 11:04:41.242917: step: 1120/529, loss: 0.0010798239381983876
2023-01-24 11:04:42.356783: step: 1124/529, loss: 8.350842108484358e-05
2023-01-24 11:04:43.523358: step: 1128/529, loss: 0.0006921535823494196
2023-01-24 11:04:44.646024: step: 1132/529, loss: 2.462251541146543e-05
2023-01-24 11:04:45.796296: step: 1136/529, loss: 0.02378924749791622
2023-01-24 11:04:46.914181: step: 1140/529, loss: 0.00030874309595674276
2023-01-24 11:04:48.030938: step: 1144/529, loss: 0.0075066969729959965
2023-01-24 11:04:49.145118: step: 1148/529, loss: 0.007054154761135578
2023-01-24 11:04:50.261437: step: 1152/529, loss: 0.0021517996210604906
2023-01-24 11:04:51.392186: step: 1156/529, loss: 0.0
2023-01-24 11:04:52.513328: step: 1160/529, loss: 0.010792912915349007
2023-01-24 11:04:53.613710: step: 1164/529, loss: 0.002899391343817115
2023-01-24 11:04:54.720627: step: 1168/529, loss: 0.0005356438341550529
2023-01-24 11:04:55.837453: step: 1172/529, loss: 0.0021522645838558674
2023-01-24 11:04:56.965351: step: 1176/529, loss: 0.00047265118337236345
2023-01-24 11:04:58.078987: step: 1180/529, loss: 6.62273735851926e-10
2023-01-24 11:04:59.198612: step: 1184/529, loss: 0.00042347016278654337
2023-01-24 11:05:00.294632: step: 1188/529, loss: 2.6224442990496755e-06
2023-01-24 11:05:01.395761: step: 1192/529, loss: 0.00701815215870738
2023-01-24 11:05:02.489641: step: 1196/529, loss: 0.00039482529973611236
2023-01-24 11:05:03.606602: step: 1200/529, loss: 2.4107577701215632e-05
2023-01-24 11:05:04.717833: step: 1204/529, loss: 0.00021021347492933273
2023-01-24 11:05:05.822306: step: 1208/529, loss: 0.0024844338186085224
2023-01-24 11:05:06.922431: step: 1212/529, loss: 0.0014012468745931983
2023-01-24 11:05:08.021190: step: 1216/529, loss: 3.5549594031181186e-05
2023-01-24 11:05:09.127939: step: 1220/529, loss: 0.0014988539041951299
2023-01-24 11:05:10.241041: step: 1224/529, loss: 0.001629492617212236
2023-01-24 11:05:11.325919: step: 1228/529, loss: 1.7556576494826004e-05
2023-01-24 11:05:12.430658: step: 1232/529, loss: 0.00043667052523232996
2023-01-24 11:05:13.535743: step: 1236/529, loss: 0.0016298576956614852
2023-01-24 11:05:14.664948: step: 1240/529, loss: 0.0023908300790935755
2023-01-24 11:05:15.786779: step: 1244/529, loss: 0.005823827814310789
2023-01-24 11:05:16.885498: step: 1248/529, loss: 0.0006173073779791594
2023-01-24 11:05:17.990157: step: 1252/529, loss: 0.0047931005246937275
2023-01-24 11:05:19.091407: step: 1256/529, loss: 0.00042521071736700833
2023-01-24 11:05:20.193532: step: 1260/529, loss: 0.0023424094542860985
2023-01-24 11:05:21.306620: step: 1264/529, loss: 0.000747110927477479
2023-01-24 11:05:22.425999: step: 1268/529, loss: 0.0023369446862488985
2023-01-24 11:05:23.554617: step: 1272/529, loss: 0.0026558798272162676
2023-01-24 11:05:24.645991: step: 1276/529, loss: 0.00027887432952411473
2023-01-24 11:05:25.749921: step: 1280/529, loss: 0.005888211075216532
2023-01-24 11:05:26.844611: step: 1284/529, loss: 0.0002677658631000668
2023-01-24 11:05:27.951080: step: 1288/529, loss: 3.101287438767031e-05
2023-01-24 11:05:29.072451: step: 1292/529, loss: 0.012007524259388447
2023-01-24 11:05:30.220733: step: 1296/529, loss: 6.227909761946648e-05
2023-01-24 11:05:31.357858: step: 1300/529, loss: 0.0014958962565287948
2023-01-24 11:05:32.467467: step: 1304/529, loss: 0.0022140732035040855
2023-01-24 11:05:33.587242: step: 1308/529, loss: 0.0008412807364948094
2023-01-24 11:05:34.694978: step: 1312/529, loss: 0.00641833059489727
2023-01-24 11:05:35.820367: step: 1316/529, loss: 0.005048653576523066
2023-01-24 11:05:36.924513: step: 1320/529, loss: 0.0004380790051072836
2023-01-24 11:05:38.020682: step: 1324/529, loss: 0.006967420689761639
2023-01-24 11:05:39.124229: step: 1328/529, loss: 7.749811629764736e-06
2023-01-24 11:05:40.204627: step: 1332/529, loss: 0.0014396198093891144
2023-01-24 11:05:41.316396: step: 1336/529, loss: 1.9668295863084495e-06
2023-01-24 11:05:42.424061: step: 1340/529, loss: 0.00012819372932426631
2023-01-24 11:05:43.544090: step: 1344/529, loss: 0.011958047747612
2023-01-24 11:05:44.647917: step: 1348/529, loss: 9.598223550710827e-05
2023-01-24 11:05:45.751380: step: 1352/529, loss: 9.899453289108351e-05
2023-01-24 11:05:46.845110: step: 1356/529, loss: 0.0005260020843707025
2023-01-24 11:05:47.954655: step: 1360/529, loss: 0.00037924887146800756
2023-01-24 11:05:49.058312: step: 1364/529, loss: 0.0055696601048111916
2023-01-24 11:05:50.163136: step: 1368/529, loss: 0.004669132176786661
2023-01-24 11:05:51.291983: step: 1372/529, loss: 0.02317608892917633
2023-01-24 11:05:52.408453: step: 1376/529, loss: 0.000990790082141757
2023-01-24 11:05:53.514846: step: 1380/529, loss: 0.0005190148367546499
2023-01-24 11:05:54.653538: step: 1384/529, loss: 0.00034910690737888217
2023-01-24 11:05:55.771185: step: 1388/529, loss: 0.00723663717508316
2023-01-24 11:05:56.875449: step: 1392/529, loss: 0.0031363654416054487
2023-01-24 11:05:57.998906: step: 1396/529, loss: 0.0014973653014749289
2023-01-24 11:05:59.108489: step: 1400/529, loss: 0.004554419312626123
2023-01-24 11:06:00.203378: step: 1404/529, loss: 0.001191581366583705
2023-01-24 11:06:01.308477: step: 1408/529, loss: 0.0031554142478853464
2023-01-24 11:06:02.440769: step: 1412/529, loss: 0.0024024993181228638
2023-01-24 11:06:03.543607: step: 1416/529, loss: 4.039910709252581e-05
2023-01-24 11:06:04.641260: step: 1420/529, loss: 3.621993073466001e-06
2023-01-24 11:06:05.769707: step: 1424/529, loss: 0.0008595092222094536
2023-01-24 11:06:06.913525: step: 1428/529, loss: 0.0011222291504964232
2023-01-24 11:06:08.028442: step: 1432/529, loss: 0.00663272337988019
2023-01-24 11:06:09.129138: step: 1436/529, loss: 0.00023140531266108155
2023-01-24 11:06:10.237775: step: 1440/529, loss: 0.005525258369743824
2023-01-24 11:06:11.335050: step: 1444/529, loss: 0.00027046544710174203
2023-01-24 11:06:12.435653: step: 1448/529, loss: 0.006597304716706276
2023-01-24 11:06:13.524681: step: 1452/529, loss: 0.0035685747861862183
2023-01-24 11:06:14.614045: step: 1456/529, loss: 0.007696566637605429
2023-01-24 11:06:15.712225: step: 1460/529, loss: 0.002407173393294215
2023-01-24 11:06:16.805576: step: 1464/529, loss: 0.0002496056549716741
2023-01-24 11:06:17.953232: step: 1468/529, loss: 0.008003685623407364
2023-01-24 11:06:19.064411: step: 1472/529, loss: 0.013193624094128609
2023-01-24 11:06:20.173384: step: 1476/529, loss: 0.012404588051140308
2023-01-24 11:06:21.280573: step: 1480/529, loss: 6.139960078144213e-06
2023-01-24 11:06:22.415705: step: 1484/529, loss: 0.0014080528635531664
2023-01-24 11:06:23.517724: step: 1488/529, loss: 0.01132181566208601
2023-01-24 11:06:24.615234: step: 1492/529, loss: 0.0034367458429187536
2023-01-24 11:06:25.700122: step: 1496/529, loss: 0.001738079241476953
2023-01-24 11:06:26.811937: step: 1500/529, loss: 1.3410723340712138e-06
2023-01-24 11:06:27.914165: step: 1504/529, loss: 0.0011472956975921988
2023-01-24 11:06:29.042014: step: 1508/529, loss: 0.0015708596911281347
2023-01-24 11:06:30.147005: step: 1512/529, loss: 0.029905790463089943
2023-01-24 11:06:31.240980: step: 1516/529, loss: 7.69003527238965e-05
2023-01-24 11:06:32.370483: step: 1520/529, loss: 0.0021961203310638666
2023-01-24 11:06:33.478636: step: 1524/529, loss: 0.002474252600222826
2023-01-24 11:06:34.577934: step: 1528/529, loss: 0.0004506809636950493
2023-01-24 11:06:35.682603: step: 1532/529, loss: 0.023818355053663254
2023-01-24 11:06:36.819774: step: 1536/529, loss: 0.005450800992548466
2023-01-24 11:06:37.926935: step: 1540/529, loss: 7.33259366825223e-05
2023-01-24 11:06:39.023144: step: 1544/529, loss: 0.004254105035215616
2023-01-24 11:06:40.125799: step: 1548/529, loss: 0.0004345346533227712
2023-01-24 11:06:41.233846: step: 1552/529, loss: 0.0038340215105563402
2023-01-24 11:06:42.327053: step: 1556/529, loss: 0.0022109763231128454
2023-01-24 11:06:43.452772: step: 1560/529, loss: 0.0007847670349292457
2023-01-24 11:06:44.568312: step: 1564/529, loss: 0.001727790106087923
2023-01-24 11:06:45.688662: step: 1568/529, loss: 0.0025347520131617785
2023-01-24 11:06:46.818850: step: 1572/529, loss: 0.0019236218649894
2023-01-24 11:06:47.923843: step: 1576/529, loss: 0.004714879672974348
2023-01-24 11:06:49.046742: step: 1580/529, loss: 0.014267808757722378
2023-01-24 11:06:50.141580: step: 1584/529, loss: 0.0004281363799236715
2023-01-24 11:06:51.227309: step: 1588/529, loss: 0.0004321748565416783
2023-01-24 11:06:52.343079: step: 1592/529, loss: 0.008390305563807487
2023-01-24 11:06:53.444527: step: 1596/529, loss: 0.00016875458823051304
2023-01-24 11:06:54.544757: step: 1600/529, loss: 0.0016817706637084484
2023-01-24 11:06:55.659570: step: 1604/529, loss: 0.0001106054987758398
2023-01-24 11:06:56.782189: step: 1608/529, loss: 0.006818888708949089
2023-01-24 11:06:57.891609: step: 1612/529, loss: 0.0015413295477628708
2023-01-24 11:06:58.986921: step: 1616/529, loss: 0.0073048085905611515
2023-01-24 11:07:00.128810: step: 1620/529, loss: 0.009429523721337318
2023-01-24 11:07:01.244033: step: 1624/529, loss: 0.00010864871001103893
2023-01-24 11:07:02.360038: step: 1628/529, loss: 0.007236195728182793
2023-01-24 11:07:03.476631: step: 1632/529, loss: 0.0015033911913633347
2023-01-24 11:07:04.586148: step: 1636/529, loss: 0.0007201815024018288
2023-01-24 11:07:05.702961: step: 1640/529, loss: 0.0026269180234521627
2023-01-24 11:07:06.815080: step: 1644/529, loss: 8.526886813342571e-05
2023-01-24 11:07:07.911659: step: 1648/529, loss: 0.003903640666976571
2023-01-24 11:07:09.028026: step: 1652/529, loss: 0.006479987408965826
2023-01-24 11:07:10.116883: step: 1656/529, loss: 0.0025715434458106756
2023-01-24 11:07:11.222632: step: 1660/529, loss: 0.006629056762903929
2023-01-24 11:07:12.332002: step: 1664/529, loss: 0.003756292164325714
2023-01-24 11:07:13.425663: step: 1668/529, loss: 0.001194830983877182
2023-01-24 11:07:14.538575: step: 1672/529, loss: 0.001242537167854607
2023-01-24 11:07:15.639129: step: 1676/529, loss: 1.0659944564395119e-05
2023-01-24 11:07:16.763415: step: 1680/529, loss: 0.000265802867943421
2023-01-24 11:07:17.865763: step: 1684/529, loss: 0.0035039852373301983
2023-01-24 11:07:18.989846: step: 1688/529, loss: 0.0009754839702509344
2023-01-24 11:07:20.108926: step: 1692/529, loss: 0.0010972573654726148
2023-01-24 11:07:21.217091: step: 1696/529, loss: 0.011874500662088394
2023-01-24 11:07:22.315539: step: 1700/529, loss: 0.00017801755166146904
2023-01-24 11:07:23.441269: step: 1704/529, loss: 0.0002987853076774627
2023-01-24 11:07:24.563185: step: 1708/529, loss: 0.00041551829781383276
2023-01-24 11:07:25.656079: step: 1712/529, loss: 0.004074069205671549
2023-01-24 11:07:26.758688: step: 1716/529, loss: 5.343437078408897e-05
2023-01-24 11:07:27.861137: step: 1720/529, loss: 0.0005563742597587407
2023-01-24 11:07:28.973307: step: 1724/529, loss: 0.00021904589084442705
2023-01-24 11:07:30.079960: step: 1728/529, loss: 0.040065109729766846
2023-01-24 11:07:31.208050: step: 1732/529, loss: 0.002059804741293192
2023-01-24 11:07:32.307042: step: 1736/529, loss: 0.00015123550838325173
2023-01-24 11:07:33.421102: step: 1740/529, loss: 0.0014656054554507136
2023-01-24 11:07:34.507925: step: 1744/529, loss: 9.985613723983988e-05
2023-01-24 11:07:35.632420: step: 1748/529, loss: 0.0033528830390423536
2023-01-24 11:07:36.739105: step: 1752/529, loss: 0.0006387518951669335
2023-01-24 11:07:37.845940: step: 1756/529, loss: 0.0006074150442145765
2023-01-24 11:07:38.974794: step: 1760/529, loss: 0.00014634014223702252
2023-01-24 11:07:40.112822: step: 1764/529, loss: 0.009260040707886219
2023-01-24 11:07:41.242148: step: 1768/529, loss: 0.008568689227104187
2023-01-24 11:07:42.377743: step: 1772/529, loss: 0.00338767864741385
2023-01-24 11:07:43.488809: step: 1776/529, loss: 0.011118866503238678
2023-01-24 11:07:44.579547: step: 1780/529, loss: 0.00253043370321393
2023-01-24 11:07:45.688248: step: 1784/529, loss: 5.990063800709322e-05
2023-01-24 11:07:46.786849: step: 1788/529, loss: 0.0011806016555055976
2023-01-24 11:07:47.896333: step: 1792/529, loss: 0.0006642257212661207
2023-01-24 11:07:49.037522: step: 1796/529, loss: 0.0026716822758316994
2023-01-24 11:07:50.148754: step: 1800/529, loss: 0.001467812224291265
2023-01-24 11:07:51.257526: step: 1804/529, loss: 0.0006074644043110311
2023-01-24 11:07:52.362127: step: 1808/529, loss: 0.00014966275193728507
2023-01-24 11:07:53.472776: step: 1812/529, loss: 0.0002217055152868852
2023-01-24 11:07:54.605919: step: 1816/529, loss: 0.0028299265541136265
2023-01-24 11:07:55.697364: step: 1820/529, loss: 0.00036575336707755923
2023-01-24 11:07:56.810323: step: 1824/529, loss: 0.005601867102086544
2023-01-24 11:07:57.933394: step: 1828/529, loss: 0.0033093367237597704
2023-01-24 11:07:59.036536: step: 1832/529, loss: 0.0013408302329480648
2023-01-24 11:08:00.148463: step: 1836/529, loss: 0.0020322424825280905
2023-01-24 11:08:01.250607: step: 1840/529, loss: 8.737322059459984e-05
2023-01-24 11:08:02.365099: step: 1844/529, loss: 0.0016424552304670215
2023-01-24 11:08:03.483055: step: 1848/529, loss: 0.001924059703014791
2023-01-24 11:08:04.586377: step: 1852/529, loss: 0.01038040779531002
2023-01-24 11:08:05.694257: step: 1856/529, loss: 0.0006261649541556835
2023-01-24 11:08:06.802404: step: 1860/529, loss: 0.005430380813777447
2023-01-24 11:08:07.900198: step: 1864/529, loss: 0.0007014241418801248
2023-01-24 11:08:08.991957: step: 1868/529, loss: 0.003927120007574558
2023-01-24 11:08:10.090224: step: 1872/529, loss: 0.0032344588544219732
2023-01-24 11:08:11.193337: step: 1876/529, loss: 0.005915793590247631
2023-01-24 11:08:12.313652: step: 1880/529, loss: 0.0015853213844820857
2023-01-24 11:08:13.409831: step: 1884/529, loss: 0.0008371626609005034
2023-01-24 11:08:14.504144: step: 1888/529, loss: 3.7464698834810406e-05
2023-01-24 11:08:15.598859: step: 1892/529, loss: 0.00044671224895864725
2023-01-24 11:08:16.695015: step: 1896/529, loss: 0.0032978130038827658
2023-01-24 11:08:17.804888: step: 1900/529, loss: 0.013345971703529358
2023-01-24 11:08:18.939426: step: 1904/529, loss: 0.0030009010806679726
2023-01-24 11:08:20.041315: step: 1908/529, loss: 0.0051575833931565285
2023-01-24 11:08:21.136229: step: 1912/529, loss: 0.000202733906917274
2023-01-24 11:08:22.248968: step: 1916/529, loss: 0.00024003082944545895
2023-01-24 11:08:23.372502: step: 1920/529, loss: 0.0038450672291219234
2023-01-24 11:08:24.464190: step: 1924/529, loss: 0.0006042091408744454
2023-01-24 11:08:25.601025: step: 1928/529, loss: 0.0026508679147809744
2023-01-24 11:08:26.708452: step: 1932/529, loss: 0.0020235839765518904
2023-01-24 11:08:27.819302: step: 1936/529, loss: 0.0012606607051566243
2023-01-24 11:08:28.930162: step: 1940/529, loss: 7.13535919203423e-05
2023-01-24 11:08:30.040812: step: 1944/529, loss: 0.0018203085055574775
2023-01-24 11:08:31.165313: step: 1948/529, loss: 0.00024992728140205145
2023-01-24 11:08:32.278647: step: 1952/529, loss: 0.009224295616149902
2023-01-24 11:08:33.370602: step: 1956/529, loss: 0.009138788096606731
2023-01-24 11:08:34.477044: step: 1960/529, loss: 7.363649638136849e-05
2023-01-24 11:08:35.607963: step: 1964/529, loss: 0.003996581770479679
2023-01-24 11:08:36.719723: step: 1968/529, loss: 0.010586723685264587
2023-01-24 11:08:37.811696: step: 1972/529, loss: 0.012198311276733875
2023-01-24 11:08:38.906663: step: 1976/529, loss: 0.002869725227355957
2023-01-24 11:08:40.026030: step: 1980/529, loss: 0.0027939460705965757
2023-01-24 11:08:41.127024: step: 1984/529, loss: 0.0009033445967361331
2023-01-24 11:08:42.233266: step: 1988/529, loss: 0.00034655132913030684
2023-01-24 11:08:43.357005: step: 1992/529, loss: 0.00034546529059298337
2023-01-24 11:08:44.487848: step: 1996/529, loss: 9.472626697970554e-05
2023-01-24 11:08:45.596314: step: 2000/529, loss: 0.00038750257226638496
2023-01-24 11:08:46.703790: step: 2004/529, loss: 0.00010098198254127055
2023-01-24 11:08:47.798098: step: 2008/529, loss: 0.0017523944843560457
2023-01-24 11:08:48.916750: step: 2012/529, loss: 0.009964141063392162
2023-01-24 11:08:50.047687: step: 2016/529, loss: 0.0016769433859735727
2023-01-24 11:08:51.177753: step: 2020/529, loss: 0.001277985400520265
2023-01-24 11:08:52.283086: step: 2024/529, loss: 0.0010931261349469423
2023-01-24 11:08:53.395241: step: 2028/529, loss: 4.800800888915546e-05
2023-01-24 11:08:54.521912: step: 2032/529, loss: 0.005852019879966974
2023-01-24 11:08:55.649841: step: 2036/529, loss: 0.0009272924507968128
2023-01-24 11:08:56.756810: step: 2040/529, loss: 0.0001120223241741769
2023-01-24 11:08:57.863676: step: 2044/529, loss: 0.03466195985674858
2023-01-24 11:08:58.967707: step: 2048/529, loss: 0.0005804647807963192
2023-01-24 11:09:00.069340: step: 2052/529, loss: 0.0002751439460553229
2023-01-24 11:09:01.186091: step: 2056/529, loss: 0.004888801369816065
2023-01-24 11:09:02.334520: step: 2060/529, loss: 0.001083503826521337
2023-01-24 11:09:03.453738: step: 2064/529, loss: 2.0044752091052942e-05
2023-01-24 11:09:04.561600: step: 2068/529, loss: 0.0023963588755577803
2023-01-24 11:09:05.668231: step: 2072/529, loss: 0.00373524846509099
2023-01-24 11:09:06.777001: step: 2076/529, loss: 0.007982109673321247
2023-01-24 11:09:07.883321: step: 2080/529, loss: 0.00391481863334775
2023-01-24 11:09:08.990774: step: 2084/529, loss: 0.006526434328407049
2023-01-24 11:09:10.108355: step: 2088/529, loss: 0.0016728973714634776
2023-01-24 11:09:11.220267: step: 2092/529, loss: 0.0007696745451539755
2023-01-24 11:09:12.340298: step: 2096/529, loss: 0.000559842272195965
2023-01-24 11:09:13.430421: step: 2100/529, loss: 0.001780455932021141
2023-01-24 11:09:14.534614: step: 2104/529, loss: 5.166012851987034e-05
2023-01-24 11:09:15.630633: step: 2108/529, loss: 0.00043957686284556985
2023-01-24 11:09:16.737512: step: 2112/529, loss: 1.769682057783939e-05
2023-01-24 11:09:17.823528: step: 2116/529, loss: 0.0025839582085609436
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3837830835459184, 'r': 0.3262520330712931, 'f1': 0.3526868131868132}, 'combined': 0.2598744939271255, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.40012164461820954, 'r': 0.28812919122853736, 'f1': 0.3350136893478409}, 'combined': 0.2059108529650144, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3747799211953624, 'r': 0.3328216377977791, 'f1': 0.35255679018980823}, 'combined': 0.25977868750827976, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38570981247279185, 'r': 0.2927918507159148, 'f1': 0.3328884686957297}, 'combined': 0.20460461978371677, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4059417040358745, 'r': 0.3435483870967742, 'f1': 0.3721479958890031}, 'combined': 0.27421431276031805, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3970932564565994, 'r': 0.28388382718950994, 'f1': 0.3310782582887261}, 'combined': 0.20448951247244854, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 11:11:40.099666: step: 4/529, loss: 0.002515129279345274
2023-01-24 11:11:41.240949: step: 8/529, loss: 0.042117588222026825
2023-01-24 11:11:42.347599: step: 12/529, loss: 0.003714257152751088
2023-01-24 11:11:43.489795: step: 16/529, loss: 0.001972219906747341
2023-01-24 11:11:44.586654: step: 20/529, loss: 6.963654595892876e-05
2023-01-24 11:11:45.685341: step: 24/529, loss: 0.003289313055574894
2023-01-24 11:11:46.787255: step: 28/529, loss: 0.0014585135504603386
2023-01-24 11:11:47.883047: step: 32/529, loss: 0.0010562982643023133
2023-01-24 11:11:48.973524: step: 36/529, loss: 2.54580590990372e-05
2023-01-24 11:11:50.048425: step: 40/529, loss: 0.0003981192712672055
2023-01-24 11:11:51.131820: step: 44/529, loss: 2.651472095749341e-05
2023-01-24 11:11:52.225669: step: 48/529, loss: 0.0005120172281749547
2023-01-24 11:11:53.320731: step: 52/529, loss: 5.1424027333268896e-05
2023-01-24 11:11:54.411666: step: 56/529, loss: 0.004901376087218523
2023-01-24 11:11:55.507175: step: 60/529, loss: 4.443858779268339e-05
2023-01-24 11:11:56.594364: step: 64/529, loss: 4.93349798489362e-05
2023-01-24 11:11:57.677441: step: 68/529, loss: 0.0034470469690859318
2023-01-24 11:11:58.783172: step: 72/529, loss: 0.004224816337227821
2023-01-24 11:11:59.908489: step: 76/529, loss: 0.002208239631727338
2023-01-24 11:12:01.036902: step: 80/529, loss: 0.008191767148673534
2023-01-24 11:12:02.121470: step: 84/529, loss: 0.001234333380125463
2023-01-24 11:12:03.230027: step: 88/529, loss: 0.0028308320324867964
2023-01-24 11:12:04.349272: step: 92/529, loss: 0.0010667319875210524
2023-01-24 11:12:05.474565: step: 96/529, loss: 0.003692012745887041
2023-01-24 11:12:06.563720: step: 100/529, loss: 0.00035669319913722575
2023-01-24 11:12:07.674805: step: 104/529, loss: 0.001542495796456933
2023-01-24 11:12:08.772468: step: 108/529, loss: 0.0021627629175782204
2023-01-24 11:12:09.877092: step: 112/529, loss: 0.00427895225584507
2023-01-24 11:12:10.993607: step: 116/529, loss: 0.002256552455946803
2023-01-24 11:12:12.105403: step: 120/529, loss: 0.006322585977613926
2023-01-24 11:12:13.217658: step: 124/529, loss: 0.003680649446323514
2023-01-24 11:12:14.326740: step: 128/529, loss: 3.325544821564108e-05
2023-01-24 11:12:15.424637: step: 132/529, loss: 0.0007309284410439432
2023-01-24 11:12:16.522621: step: 136/529, loss: 0.0005317345494404435
2023-01-24 11:12:17.618841: step: 140/529, loss: 6.787503025407204e-06
2023-01-24 11:12:18.719259: step: 144/529, loss: 5.30331271875184e-06
2023-01-24 11:12:19.828440: step: 148/529, loss: 0.0012661494547501206
2023-01-24 11:12:20.943251: step: 152/529, loss: 1.0934447345789522e-05
2023-01-24 11:12:22.045620: step: 156/529, loss: 0.0017589119961485267
2023-01-24 11:12:23.150542: step: 160/529, loss: 0.0024684083182364702
2023-01-24 11:12:24.238331: step: 164/529, loss: 0.005677887704223394
2023-01-24 11:12:25.349388: step: 168/529, loss: 9.003043714983505e-07
2023-01-24 11:12:26.456788: step: 172/529, loss: 0.005994025152176619
2023-01-24 11:12:27.562534: step: 176/529, loss: 0.0002197103458456695
2023-01-24 11:12:28.678022: step: 180/529, loss: 0.0005711939302273095
2023-01-24 11:12:29.789719: step: 184/529, loss: 0.0010891571873798966
2023-01-24 11:12:30.882409: step: 188/529, loss: 0.0015627671964466572
2023-01-24 11:12:31.997049: step: 192/529, loss: 0.0008933567441999912
2023-01-24 11:12:33.125267: step: 196/529, loss: 0.011484578251838684
2023-01-24 11:12:34.242899: step: 200/529, loss: 0.03009461797773838
2023-01-24 11:12:35.363720: step: 204/529, loss: 0.0018042160663753748
2023-01-24 11:12:36.490712: step: 208/529, loss: 0.002897471422329545
2023-01-24 11:12:37.598572: step: 212/529, loss: 0.0006291003664955497
2023-01-24 11:12:38.716636: step: 216/529, loss: 0.003515898482874036
2023-01-24 11:12:39.827960: step: 220/529, loss: 0.009037968702614307
2023-01-24 11:12:40.955155: step: 224/529, loss: 7.412202648993116e-06
2023-01-24 11:12:42.069565: step: 228/529, loss: 1.423345224793593e-06
2023-01-24 11:12:43.194298: step: 232/529, loss: 0.0181756392121315
2023-01-24 11:12:44.296089: step: 236/529, loss: 0.00011489960161270574
2023-01-24 11:12:45.414964: step: 240/529, loss: 0.003495260374620557
2023-01-24 11:12:46.527827: step: 244/529, loss: 0.0008709641988389194
2023-01-24 11:12:47.619486: step: 248/529, loss: 0.00031230662716552615
2023-01-24 11:12:48.734000: step: 252/529, loss: 0.001761759864166379
2023-01-24 11:12:49.838941: step: 256/529, loss: 6.900924290675903e-06
2023-01-24 11:12:50.950932: step: 260/529, loss: 0.011513270437717438
2023-01-24 11:12:52.055492: step: 264/529, loss: 0.0017682992620393634
2023-01-24 11:12:53.175170: step: 268/529, loss: 0.009417731314897537
2023-01-24 11:12:54.280018: step: 272/529, loss: 0.000323099346132949
2023-01-24 11:12:55.397544: step: 276/529, loss: 0.040628932416439056
2023-01-24 11:12:56.511121: step: 280/529, loss: 9.981498806155287e-06
2023-01-24 11:12:57.643040: step: 284/529, loss: 0.0041883266530931
2023-01-24 11:12:58.743763: step: 288/529, loss: 0.0012143495259806514
2023-01-24 11:12:59.877752: step: 292/529, loss: 0.0012636932078748941
2023-01-24 11:13:00.980410: step: 296/529, loss: 0.002426756080240011
2023-01-24 11:13:02.096544: step: 300/529, loss: 0.0023101866245269775
2023-01-24 11:13:03.193406: step: 304/529, loss: 0.0038914510514587164
2023-01-24 11:13:04.296954: step: 308/529, loss: 0.000198359542991966
2023-01-24 11:13:05.398142: step: 312/529, loss: 0.0015133768320083618
2023-01-24 11:13:06.494637: step: 316/529, loss: 2.5509900297038257e-05
2023-01-24 11:13:07.611906: step: 320/529, loss: 0.0005425954586826265
2023-01-24 11:13:08.722818: step: 324/529, loss: 0.004145944491028786
2023-01-24 11:13:09.817287: step: 328/529, loss: 0.008070851676166058
2023-01-24 11:13:10.926307: step: 332/529, loss: 0.00023014192993286997
2023-01-24 11:13:12.030261: step: 336/529, loss: 0.0021311254240572453
2023-01-24 11:13:13.124481: step: 340/529, loss: 0.005042993929237127
2023-01-24 11:13:14.223449: step: 344/529, loss: 0.0029296439606696367
2023-01-24 11:13:15.338771: step: 348/529, loss: 0.004642107989639044
2023-01-24 11:13:16.464465: step: 352/529, loss: 0.01388418860733509
2023-01-24 11:13:17.577494: step: 356/529, loss: 0.0027632839046418667
2023-01-24 11:13:18.699347: step: 360/529, loss: 0.0001689031341811642
2023-01-24 11:13:19.795969: step: 364/529, loss: 0.006203958764672279
2023-01-24 11:13:20.912126: step: 368/529, loss: 0.0038964394479990005
2023-01-24 11:13:22.016620: step: 372/529, loss: 0.003068020800128579
2023-01-24 11:13:23.116458: step: 376/529, loss: 0.006584575865417719
2023-01-24 11:13:24.209364: step: 380/529, loss: 0.006145960185676813
2023-01-24 11:13:25.312637: step: 384/529, loss: 0.004592226818203926
2023-01-24 11:13:26.433341: step: 388/529, loss: 0.003500356338918209
2023-01-24 11:13:27.568954: step: 392/529, loss: 0.0023840356152504683
2023-01-24 11:13:28.670599: step: 396/529, loss: 0.0011784323723986745
2023-01-24 11:13:29.770077: step: 400/529, loss: 0.006961505394428968
2023-01-24 11:13:30.853752: step: 404/529, loss: 0.0030000151600688696
2023-01-24 11:13:31.965134: step: 408/529, loss: 0.0008716362644918263
2023-01-24 11:13:33.057966: step: 412/529, loss: 0.0019585415720939636
2023-01-24 11:13:34.171006: step: 416/529, loss: 0.0015604370273649693
2023-01-24 11:13:35.293540: step: 420/529, loss: 0.007060790900141001
2023-01-24 11:13:36.411917: step: 424/529, loss: 0.0002206896460847929
2023-01-24 11:13:37.520746: step: 428/529, loss: 0.005229902919381857
2023-01-24 11:13:38.630009: step: 432/529, loss: 6.697853677906096e-05
2023-01-24 11:13:39.723666: step: 436/529, loss: 0.0004602751287166029
2023-01-24 11:13:40.865115: step: 440/529, loss: 0.0016866980586200953
2023-01-24 11:13:41.967274: step: 444/529, loss: 0.002020878717303276
2023-01-24 11:13:43.092244: step: 448/529, loss: 0.002414423506706953
2023-01-24 11:13:44.174704: step: 452/529, loss: 1.9656768927234225e-05
2023-01-24 11:13:45.298651: step: 456/529, loss: 0.00245417351834476
2023-01-24 11:13:46.430424: step: 460/529, loss: 0.0016583745600655675
2023-01-24 11:13:47.523712: step: 464/529, loss: 0.00048096911632455885
2023-01-24 11:13:48.612867: step: 468/529, loss: 0.00027440875419415534
2023-01-24 11:13:49.730440: step: 472/529, loss: 0.0024998849257826805
2023-01-24 11:13:50.836128: step: 476/529, loss: 0.006224286276847124
2023-01-24 11:13:51.952785: step: 480/529, loss: 0.0019229919416829944
2023-01-24 11:13:53.053047: step: 484/529, loss: 8.527380487066694e-06
2023-01-24 11:13:54.167871: step: 488/529, loss: 0.0027839643880724907
2023-01-24 11:13:55.266461: step: 492/529, loss: 7.896906754467636e-05
2023-01-24 11:13:56.374148: step: 496/529, loss: 0.0017764586955308914
2023-01-24 11:13:57.469883: step: 500/529, loss: 0.0022709884215146303
2023-01-24 11:13:58.576885: step: 504/529, loss: 0.006108562927693129
2023-01-24 11:13:59.673452: step: 508/529, loss: 0.004134563263505697
2023-01-24 11:14:00.776092: step: 512/529, loss: 0.012196128256618977
2023-01-24 11:14:01.908371: step: 516/529, loss: 0.00013790398952551186
2023-01-24 11:14:03.040631: step: 520/529, loss: 2.9570426704594865e-05
2023-01-24 11:14:04.174385: step: 524/529, loss: 0.0010324257891625166
2023-01-24 11:14:05.285336: step: 528/529, loss: 9.28020745050162e-06
2023-01-24 11:14:06.394123: step: 532/529, loss: 0.00012021453585475683
2023-01-24 11:14:07.516921: step: 536/529, loss: 0.016974138095974922
2023-01-24 11:14:08.622062: step: 540/529, loss: 0.029024222865700722
2023-01-24 11:14:09.742978: step: 544/529, loss: 0.004723994992673397
2023-01-24 11:14:10.852406: step: 548/529, loss: 0.0007895179442130029
2023-01-24 11:14:11.965081: step: 552/529, loss: 0.0004907877300865948
2023-01-24 11:14:13.058548: step: 556/529, loss: 0.0010578130604699254
2023-01-24 11:14:14.165614: step: 560/529, loss: 6.065434718038887e-06
2023-01-24 11:14:15.277956: step: 564/529, loss: 0.0006848315824754536
2023-01-24 11:14:16.384222: step: 568/529, loss: 0.008157975971698761
2023-01-24 11:14:17.491222: step: 572/529, loss: 0.0017022100510075688
2023-01-24 11:14:18.596721: step: 576/529, loss: 0.0028045426588505507
2023-01-24 11:14:19.713324: step: 580/529, loss: 0.0014142559375613928
2023-01-24 11:14:20.828395: step: 584/529, loss: 0.004144781269133091
2023-01-24 11:14:21.950354: step: 588/529, loss: 0.0007218053215183318
2023-01-24 11:14:23.054267: step: 592/529, loss: 0.0013224389404058456
2023-01-24 11:14:24.168514: step: 596/529, loss: 0.00015425431774929166
2023-01-24 11:14:25.289105: step: 600/529, loss: 2.098843287967611e-05
2023-01-24 11:14:26.414135: step: 604/529, loss: 0.0001713370147626847
2023-01-24 11:14:27.528791: step: 608/529, loss: 0.00221316353417933
2023-01-24 11:14:28.649779: step: 612/529, loss: 0.004469534382224083
2023-01-24 11:14:29.753467: step: 616/529, loss: 0.0008708247332833707
2023-01-24 11:14:30.869354: step: 620/529, loss: 0.013388365507125854
2023-01-24 11:14:31.971796: step: 624/529, loss: 0.0007657025707885623
2023-01-24 11:14:33.078592: step: 628/529, loss: 0.009786712005734444
2023-01-24 11:14:34.189840: step: 632/529, loss: 0.007056476082652807
2023-01-24 11:14:35.288927: step: 636/529, loss: 0.0005588439526036382
2023-01-24 11:14:36.406449: step: 640/529, loss: 0.00920840073376894
2023-01-24 11:14:37.508821: step: 644/529, loss: 3.497383659123443e-05
2023-01-24 11:14:38.628141: step: 648/529, loss: 0.001605254365131259
2023-01-24 11:14:39.768466: step: 652/529, loss: 0.005136909428983927
2023-01-24 11:14:40.878969: step: 656/529, loss: 0.011881612241268158
2023-01-24 11:14:41.996828: step: 660/529, loss: 0.0009909030050039291
2023-01-24 11:14:43.133940: step: 664/529, loss: 0.001475058263167739
2023-01-24 11:14:44.231456: step: 668/529, loss: 0.008074665442109108
2023-01-24 11:14:45.348512: step: 672/529, loss: 0.00788902398198843
2023-01-24 11:14:46.454662: step: 676/529, loss: 0.0013463061768561602
2023-01-24 11:14:47.570792: step: 680/529, loss: 0.0012964956695213914
2023-01-24 11:14:48.691550: step: 684/529, loss: 0.0011892806505784392
2023-01-24 11:14:49.795270: step: 688/529, loss: 0.004064568784087896
2023-01-24 11:14:50.922861: step: 692/529, loss: 0.0038937286008149385
2023-01-24 11:14:52.011362: step: 696/529, loss: 0.00021936155098956078
2023-01-24 11:14:53.135937: step: 700/529, loss: 0.003658293979242444
2023-01-24 11:14:54.253256: step: 704/529, loss: 2.2889800675329752e-05
2023-01-24 11:14:55.378830: step: 708/529, loss: 0.0003839272540062666
2023-01-24 11:14:56.473645: step: 712/529, loss: 0.0026701060123741627
2023-01-24 11:14:57.576491: step: 716/529, loss: 0.0003877747803926468
2023-01-24 11:14:58.696907: step: 720/529, loss: 0.0018111772369593382
2023-01-24 11:14:59.801819: step: 724/529, loss: 0.002418719232082367
2023-01-24 11:15:00.916895: step: 728/529, loss: 1.604023782419972e-05
2023-01-24 11:15:02.023433: step: 732/529, loss: 0.0035579788964241743
2023-01-24 11:15:03.137049: step: 736/529, loss: 0.0015203305520117283
2023-01-24 11:15:04.272660: step: 740/529, loss: 0.0013580997474491596
2023-01-24 11:15:05.375180: step: 744/529, loss: 2.207766920037102e-05
2023-01-24 11:15:06.480008: step: 748/529, loss: 0.0005680155009031296
2023-01-24 11:15:07.594446: step: 752/529, loss: 0.00043688464211300015
2023-01-24 11:15:08.709481: step: 756/529, loss: 6.899232539581135e-05
2023-01-24 11:15:09.818128: step: 760/529, loss: 0.005713443737477064
2023-01-24 11:15:10.961420: step: 764/529, loss: 0.0022997490596026182
2023-01-24 11:15:12.076192: step: 768/529, loss: 0.014577297493815422
2023-01-24 11:15:13.184555: step: 772/529, loss: 0.0013613359769806266
2023-01-24 11:15:14.282747: step: 776/529, loss: 0.00018187775276601315
2023-01-24 11:15:15.390236: step: 780/529, loss: 0.003970622550696135
2023-01-24 11:15:16.520344: step: 784/529, loss: 0.024156101047992706
2023-01-24 11:15:17.635437: step: 788/529, loss: 0.000991825945675373
2023-01-24 11:15:18.730757: step: 792/529, loss: 0.0002483031712472439
2023-01-24 11:15:19.839795: step: 796/529, loss: 0.0021235086023807526
2023-01-24 11:15:20.965407: step: 800/529, loss: 0.0012124486966058612
2023-01-24 11:15:22.071442: step: 804/529, loss: 0.0022717094980180264
2023-01-24 11:15:23.198686: step: 808/529, loss: 0.002715103793889284
2023-01-24 11:15:24.307578: step: 812/529, loss: 0.00012125296052545309
2023-01-24 11:15:25.419533: step: 816/529, loss: 0.003937737084925175
2023-01-24 11:15:26.508162: step: 820/529, loss: 0.008904669433832169
2023-01-24 11:15:27.617863: step: 824/529, loss: 0.000734749948605895
2023-01-24 11:15:28.708439: step: 828/529, loss: 1.0322844900656492e-05
2023-01-24 11:15:29.819586: step: 832/529, loss: 0.004629488103091717
2023-01-24 11:15:30.922397: step: 836/529, loss: 0.00599862914532423
2023-01-24 11:15:32.016472: step: 840/529, loss: 4.157593866693787e-05
2023-01-24 11:15:33.132425: step: 844/529, loss: 0.0039885928854346275
2023-01-24 11:15:34.248095: step: 848/529, loss: 0.003461960470303893
2023-01-24 11:15:35.363387: step: 852/529, loss: 0.004900790750980377
2023-01-24 11:15:36.456949: step: 856/529, loss: 0.0024634823203086853
2023-01-24 11:15:37.552111: step: 860/529, loss: 0.00343673350289464
2023-01-24 11:15:38.678109: step: 864/529, loss: 0.012906216084957123
2023-01-24 11:15:39.789047: step: 868/529, loss: 0.0062122950330376625
2023-01-24 11:15:40.895488: step: 872/529, loss: 1.521968101769744e-06
2023-01-24 11:15:42.003500: step: 876/529, loss: 0.0002512185601517558
2023-01-24 11:15:43.129391: step: 880/529, loss: 0.0039969272911548615
2023-01-24 11:15:44.223801: step: 884/529, loss: 1.0799634765135124e-05
2023-01-24 11:15:45.341897: step: 888/529, loss: 0.010927834548056126
2023-01-24 11:15:46.461742: step: 892/529, loss: 0.00017552435747347772
2023-01-24 11:15:47.568373: step: 896/529, loss: 7.884536898927763e-05
2023-01-24 11:15:48.703024: step: 900/529, loss: 0.0024376928340643644
2023-01-24 11:15:49.825104: step: 904/529, loss: 0.01575223170220852
2023-01-24 11:15:50.938014: step: 908/529, loss: 0.008317980915307999
2023-01-24 11:15:52.041275: step: 912/529, loss: 0.0005217691068537533
2023-01-24 11:15:53.176456: step: 916/529, loss: 0.00591327203437686
2023-01-24 11:15:54.281875: step: 920/529, loss: 0.03702763095498085
2023-01-24 11:15:55.390394: step: 924/529, loss: 0.00031593296444043517
2023-01-24 11:15:56.562057: step: 928/529, loss: 8.674946002429351e-05
2023-01-24 11:15:57.645322: step: 932/529, loss: 3.282969601059449e-06
2023-01-24 11:15:58.741483: step: 936/529, loss: 0.0012404134031385183
2023-01-24 11:15:59.869538: step: 940/529, loss: 0.006008796393871307
2023-01-24 11:16:00.985956: step: 944/529, loss: 0.002160663018003106
2023-01-24 11:16:02.103187: step: 948/529, loss: 0.0008952803909778595
2023-01-24 11:16:03.197035: step: 952/529, loss: 0.002350547816604376
2023-01-24 11:16:04.315084: step: 956/529, loss: 0.0011286986991763115
2023-01-24 11:16:05.434314: step: 960/529, loss: 0.0002235923457192257
2023-01-24 11:16:06.547957: step: 964/529, loss: 0.0002552682999521494
2023-01-24 11:16:07.648528: step: 968/529, loss: 0.0029484282713383436
2023-01-24 11:16:08.776681: step: 972/529, loss: 0.0025193053297698498
2023-01-24 11:16:09.907085: step: 976/529, loss: 0.00493354257196188
2023-01-24 11:16:11.012709: step: 980/529, loss: 0.002164387609809637
2023-01-24 11:16:12.142757: step: 984/529, loss: 0.0020205946639180183
2023-01-24 11:16:13.239549: step: 988/529, loss: 0.0010405535576865077
2023-01-24 11:16:14.358061: step: 992/529, loss: 0.00023080004029907286
2023-01-24 11:16:15.471874: step: 996/529, loss: 0.004372393246740103
2023-01-24 11:16:16.565021: step: 1000/529, loss: 7.599623495480046e-05
2023-01-24 11:16:17.680486: step: 1004/529, loss: 8.600207365816459e-05
2023-01-24 11:16:18.793883: step: 1008/529, loss: 0.001264549675397575
2023-01-24 11:16:19.938364: step: 1012/529, loss: 0.0015926676569506526
2023-01-24 11:16:21.055412: step: 1016/529, loss: 3.2328262022929266e-05
2023-01-24 11:16:22.161374: step: 1020/529, loss: 0.00256981304846704
2023-01-24 11:16:23.254668: step: 1024/529, loss: 0.00014677700528409332
2023-01-24 11:16:24.364345: step: 1028/529, loss: 0.0010209884494543076
2023-01-24 11:16:25.487928: step: 1032/529, loss: 0.09078031778335571
2023-01-24 11:16:26.616878: step: 1036/529, loss: 5.396077176555991e-05
2023-01-24 11:16:27.726346: step: 1040/529, loss: 0.0020750206895172596
2023-01-24 11:16:28.860417: step: 1044/529, loss: 0.002354108728468418
2023-01-24 11:16:29.976214: step: 1048/529, loss: 0.0007027073879726231
2023-01-24 11:16:31.100462: step: 1052/529, loss: 0.0030362012330442667
2023-01-24 11:16:32.201419: step: 1056/529, loss: 0.005776799283921719
2023-01-24 11:16:33.312211: step: 1060/529, loss: 0.0031625377014279366
2023-01-24 11:16:34.406108: step: 1064/529, loss: 4.4993535993853584e-05
2023-01-24 11:16:35.515696: step: 1068/529, loss: 0.003949759993702173
2023-01-24 11:16:36.630171: step: 1072/529, loss: 0.0009441837319172919
2023-01-24 11:16:37.743555: step: 1076/529, loss: 0.00033297622576355934
2023-01-24 11:16:38.859874: step: 1080/529, loss: 0.002375268144533038
2023-01-24 11:16:39.954643: step: 1084/529, loss: 0.0003824633313342929
2023-01-24 11:16:41.061734: step: 1088/529, loss: 0.011141564697027206
2023-01-24 11:16:42.157895: step: 1092/529, loss: 0.01226444635540247
2023-01-24 11:16:43.264830: step: 1096/529, loss: 0.001025436446070671
2023-01-24 11:16:44.384333: step: 1100/529, loss: 0.0001177908998215571
2023-01-24 11:16:45.504531: step: 1104/529, loss: 0.0011987262405455112
2023-01-24 11:16:46.612332: step: 1108/529, loss: 6.334928002615925e-06
2023-01-24 11:16:47.734409: step: 1112/529, loss: 0.0022149020805954933
2023-01-24 11:16:48.854594: step: 1116/529, loss: 7.053666195133701e-05
2023-01-24 11:16:49.954586: step: 1120/529, loss: 0.0026090338360518217
2023-01-24 11:16:51.059378: step: 1124/529, loss: 0.004320600535720587
2023-01-24 11:16:52.159710: step: 1128/529, loss: 1.1652815373963676e-05
2023-01-24 11:16:53.281290: step: 1132/529, loss: 0.0015827511670067906
2023-01-24 11:16:54.379287: step: 1136/529, loss: 0.0005357727641239762
2023-01-24 11:16:55.488249: step: 1140/529, loss: 0.004198629874736071
2023-01-24 11:16:56.602402: step: 1144/529, loss: 0.005446875002235174
2023-01-24 11:16:57.725470: step: 1148/529, loss: 0.0017383525846526027
2023-01-24 11:16:58.856084: step: 1152/529, loss: 0.0011263630585744977
2023-01-24 11:16:59.962077: step: 1156/529, loss: 0.0014643777394667268
2023-01-24 11:17:01.042481: step: 1160/529, loss: 0.0021422095596790314
2023-01-24 11:17:02.156190: step: 1164/529, loss: 0.0005390482838265598
2023-01-24 11:17:03.275517: step: 1168/529, loss: 0.0011096819071099162
2023-01-24 11:17:04.412443: step: 1172/529, loss: 0.004362502600997686
2023-01-24 11:17:05.524774: step: 1176/529, loss: 1.7825493614509469e-06
2023-01-24 11:17:06.621901: step: 1180/529, loss: 0.0035751163959503174
2023-01-24 11:17:07.726257: step: 1184/529, loss: 0.010183860547840595
2023-01-24 11:17:08.829528: step: 1188/529, loss: 0.005394357722252607
2023-01-24 11:17:09.931739: step: 1192/529, loss: 0.0011433775071054697
2023-01-24 11:17:11.024739: step: 1196/529, loss: 0.0001433080469723791
2023-01-24 11:17:12.138404: step: 1200/529, loss: 0.0010919515043497086
2023-01-24 11:17:13.250008: step: 1204/529, loss: 0.008285412564873695
2023-01-24 11:17:14.345455: step: 1208/529, loss: 0.003191579831764102
2023-01-24 11:17:15.480233: step: 1212/529, loss: 0.0002722078934311867
2023-01-24 11:17:16.613373: step: 1216/529, loss: 0.0010823936900123954
2023-01-24 11:17:17.707232: step: 1220/529, loss: 0.0019861948676407337
2023-01-24 11:17:18.783498: step: 1224/529, loss: 0.0049724578857421875
2023-01-24 11:17:19.897308: step: 1228/529, loss: 8.940689966152604e-09
2023-01-24 11:17:21.018867: step: 1232/529, loss: 0.04660915583372116
2023-01-24 11:17:22.133599: step: 1236/529, loss: 0.002036280930042267
2023-01-24 11:17:23.246873: step: 1240/529, loss: 0.0007337016868405044
2023-01-24 11:17:24.350757: step: 1244/529, loss: 0.00013954381574876606
2023-01-24 11:17:25.440323: step: 1248/529, loss: 0.0001331036473857239
2023-01-24 11:17:26.528330: step: 1252/529, loss: 0.0007688223267905414
2023-01-24 11:17:27.634636: step: 1256/529, loss: 0.0006111471448093653
2023-01-24 11:17:28.767163: step: 1260/529, loss: 0.00044723015162162483
2023-01-24 11:17:29.866113: step: 1264/529, loss: 0.000637308054137975
2023-01-24 11:17:30.975740: step: 1268/529, loss: 0.00019118207274004817
2023-01-24 11:17:32.097132: step: 1272/529, loss: 0.0009755234350450337
2023-01-24 11:17:33.218891: step: 1276/529, loss: 0.003899776376783848
2023-01-24 11:17:34.325842: step: 1280/529, loss: 0.0022934211883693933
2023-01-24 11:17:35.467684: step: 1284/529, loss: 1.9409029846428894e-05
2023-01-24 11:17:36.578453: step: 1288/529, loss: 0.004870065022259951
2023-01-24 11:17:37.700918: step: 1292/529, loss: 0.0005327885155566037
2023-01-24 11:17:38.801973: step: 1296/529, loss: 0.00042267024400644004
2023-01-24 11:17:39.902427: step: 1300/529, loss: 0.006611426826566458
2023-01-24 11:17:40.991664: step: 1304/529, loss: 0.0002100148267345503
2023-01-24 11:17:42.094382: step: 1308/529, loss: 6.575922452611849e-05
2023-01-24 11:17:43.227756: step: 1312/529, loss: 1.5208149306999985e-05
2023-01-24 11:17:44.332813: step: 1316/529, loss: 0.0025981476064771414
2023-01-24 11:17:45.465882: step: 1320/529, loss: 0.0020401678048074245
2023-01-24 11:17:46.568158: step: 1324/529, loss: 6.701559323119e-05
2023-01-24 11:17:47.695895: step: 1328/529, loss: 0.0055059571750462055
2023-01-24 11:17:48.795402: step: 1332/529, loss: 0.0004269076162017882
2023-01-24 11:17:49.893969: step: 1336/529, loss: 0.003423511516302824
2023-01-24 11:17:51.013939: step: 1340/529, loss: 0.0005998878623358905
2023-01-24 11:17:52.139771: step: 1344/529, loss: 0.047127023339271545
2023-01-24 11:17:53.256591: step: 1348/529, loss: 0.0013119399081915617
2023-01-24 11:17:54.366058: step: 1352/529, loss: 0.009838234633207321
2023-01-24 11:17:55.496851: step: 1356/529, loss: 2.9159928089939058e-05
2023-01-24 11:17:56.589036: step: 1360/529, loss: 0.00336446356959641
2023-01-24 11:17:57.689979: step: 1364/529, loss: 0.005810531787574291
2023-01-24 11:17:58.798802: step: 1368/529, loss: 0.01106372568756342
2023-01-24 11:17:59.910791: step: 1372/529, loss: 0.0050170691683888435
2023-01-24 11:18:01.002221: step: 1376/529, loss: 5.2270799642428756e-05
2023-01-24 11:18:02.114711: step: 1380/529, loss: 0.05188421532511711
2023-01-24 11:18:03.223923: step: 1384/529, loss: 0.007389829494059086
2023-01-24 11:18:04.341701: step: 1388/529, loss: 0.0012455395190045238
2023-01-24 11:18:05.453186: step: 1392/529, loss: 0.0072115156799554825
2023-01-24 11:18:06.565278: step: 1396/529, loss: 0.02572551555931568
2023-01-24 11:18:07.662147: step: 1400/529, loss: 0.0066342600621283054
2023-01-24 11:18:08.748283: step: 1404/529, loss: 0.0031778954435139894
2023-01-24 11:18:09.841025: step: 1408/529, loss: 0.005597598850727081
2023-01-24 11:18:10.948002: step: 1412/529, loss: 0.0044565461575984955
2023-01-24 11:18:12.064010: step: 1416/529, loss: 7.092933083185926e-05
2023-01-24 11:18:13.151581: step: 1420/529, loss: 0.0016181654063984752
2023-01-24 11:18:14.258320: step: 1424/529, loss: 0.004665218759328127
2023-01-24 11:18:15.385925: step: 1428/529, loss: 0.0011610727524384856
2023-01-24 11:18:16.509478: step: 1432/529, loss: 0.005263286177068949
2023-01-24 11:18:17.626144: step: 1436/529, loss: 0.0006570618716068566
2023-01-24 11:18:18.733457: step: 1440/529, loss: 0.0006696152267977595
2023-01-24 11:18:19.849279: step: 1444/529, loss: 0.0006329510360956192
2023-01-24 11:18:20.962498: step: 1448/529, loss: 3.4138480259571224e-05
2023-01-24 11:18:22.074636: step: 1452/529, loss: 0.0002547826443333179
2023-01-24 11:18:23.187409: step: 1456/529, loss: 0.01591784879565239
2023-01-24 11:18:24.295399: step: 1460/529, loss: 0.001227688160724938
2023-01-24 11:18:25.394258: step: 1464/529, loss: 0.0003774031938519329
2023-01-24 11:18:26.517789: step: 1468/529, loss: 0.0011182804591953754
2023-01-24 11:18:27.629066: step: 1472/529, loss: 0.015542536973953247
2023-01-24 11:18:28.733729: step: 1476/529, loss: 0.0003420463763177395
2023-01-24 11:18:29.868393: step: 1480/529, loss: 0.0018965578638017178
2023-01-24 11:18:30.966779: step: 1484/529, loss: 0.00140009552706033
2023-01-24 11:18:32.083124: step: 1488/529, loss: 0.0001720975269563496
2023-01-24 11:18:33.172661: step: 1492/529, loss: 4.1165876609738916e-05
2023-01-24 11:18:34.284245: step: 1496/529, loss: 0.00021411824855022132
2023-01-24 11:18:35.401669: step: 1500/529, loss: 0.020264215767383575
2023-01-24 11:18:36.508503: step: 1504/529, loss: 3.779512917390093e-05
2023-01-24 11:18:37.632629: step: 1508/529, loss: 0.0029182955622673035
2023-01-24 11:18:38.748946: step: 1512/529, loss: 0.0006796749075874686
2023-01-24 11:18:39.854669: step: 1516/529, loss: 0.0005390775622799993
2023-01-24 11:18:41.014216: step: 1520/529, loss: 0.0003339150862302631
2023-01-24 11:18:42.129288: step: 1524/529, loss: 0.004776553250849247
2023-01-24 11:18:43.263934: step: 1528/529, loss: 0.004782753065228462
2023-01-24 11:18:44.369614: step: 1532/529, loss: 7.556027412647381e-05
2023-01-24 11:18:45.478648: step: 1536/529, loss: 8.260748290922493e-05
2023-01-24 11:18:46.586469: step: 1540/529, loss: 0.002633172320201993
2023-01-24 11:18:47.715566: step: 1544/529, loss: 0.0031153487507253885
2023-01-24 11:18:48.835069: step: 1548/529, loss: 0.0002114608942065388
2023-01-24 11:18:49.950310: step: 1552/529, loss: 0.02373434789478779
2023-01-24 11:18:51.041332: step: 1556/529, loss: 0.0009980922332033515
2023-01-24 11:18:52.140250: step: 1560/529, loss: 0.004760845098644495
2023-01-24 11:18:53.244106: step: 1564/529, loss: 3.7880527088418603e-06
2023-01-24 11:18:54.380018: step: 1568/529, loss: 0.0019359186990186572
2023-01-24 11:18:55.492829: step: 1572/529, loss: 0.0001558828225824982
2023-01-24 11:18:56.609048: step: 1576/529, loss: 5.598276402452029e-05
2023-01-24 11:18:57.723544: step: 1580/529, loss: 0.00197223131544888
2023-01-24 11:18:58.835100: step: 1584/529, loss: 0.0009332557092420757
2023-01-24 11:18:59.939462: step: 1588/529, loss: 2.346081964788027e-05
2023-01-24 11:19:01.028488: step: 1592/529, loss: 0.002634502248838544
2023-01-24 11:19:02.157961: step: 1596/529, loss: 0.0070084757171571255
2023-01-24 11:19:03.274854: step: 1600/529, loss: 0.0015014380915090442
2023-01-24 11:19:04.395636: step: 1604/529, loss: 0.0024020092096179724
2023-01-24 11:19:05.503593: step: 1608/529, loss: 0.0010112121235579252
2023-01-24 11:19:06.637257: step: 1612/529, loss: 0.008827624842524529
2023-01-24 11:19:07.739189: step: 1616/529, loss: 0.00023526264703832567
2023-01-24 11:19:08.848886: step: 1620/529, loss: 0.0007089654100127518
2023-01-24 11:19:09.960548: step: 1624/529, loss: 0.002622129861265421
2023-01-24 11:19:11.070272: step: 1628/529, loss: 0.005837226752191782
2023-01-24 11:19:12.194037: step: 1632/529, loss: 0.0005664409836754203
2023-01-24 11:19:13.309266: step: 1636/529, loss: 0.00015801946574356407
2023-01-24 11:19:14.412196: step: 1640/529, loss: 0.0006514594424515963
2023-01-24 11:19:15.525854: step: 1644/529, loss: 0.0019710755441337824
2023-01-24 11:19:16.646933: step: 1648/529, loss: 2.5102790459641255e-05
2023-01-24 11:19:17.752209: step: 1652/529, loss: 0.0053861928172409534
2023-01-24 11:19:18.864767: step: 1656/529, loss: 0.0008697125012986362
2023-01-24 11:19:19.978329: step: 1660/529, loss: 0.0011428359430283308
2023-01-24 11:19:21.089973: step: 1664/529, loss: 0.0008945821318775415
2023-01-24 11:19:22.215821: step: 1668/529, loss: 0.006410997360944748
2023-01-24 11:19:23.345788: step: 1672/529, loss: 2.273559039167594e-05
2023-01-24 11:19:24.484422: step: 1676/529, loss: 0.0028206754941493273
2023-01-24 11:19:25.611812: step: 1680/529, loss: 2.4876862880773842e-05
2023-01-24 11:19:26.726026: step: 1684/529, loss: 0.0021191395353525877
2023-01-24 11:19:27.818789: step: 1688/529, loss: 6.235543423827039e-06
2023-01-24 11:19:28.935448: step: 1692/529, loss: 0.004005727358162403
2023-01-24 11:19:30.036589: step: 1696/529, loss: 0.000275185564532876
2023-01-24 11:19:31.148093: step: 1700/529, loss: 0.0028727923054248095
2023-01-24 11:19:32.309352: step: 1704/529, loss: 0.0038915870245546103
2023-01-24 11:19:33.425986: step: 1708/529, loss: 0.0008150855428539217
2023-01-24 11:19:34.560703: step: 1712/529, loss: 0.00023460510419681668
2023-01-24 11:19:35.674036: step: 1716/529, loss: 0.00017404998652637005
2023-01-24 11:19:36.747600: step: 1720/529, loss: 0.012200117111206055
2023-01-24 11:19:37.837128: step: 1724/529, loss: 2.4797329842840554e-06
2023-01-24 11:19:38.930857: step: 1728/529, loss: 0.00195849291048944
2023-01-24 11:19:40.041745: step: 1732/529, loss: 0.0002815011248458177
2023-01-24 11:19:41.149982: step: 1736/529, loss: 0.00023537929519079626
2023-01-24 11:19:42.244213: step: 1740/529, loss: 0.0011688710656017065
2023-01-24 11:19:43.343095: step: 1744/529, loss: 3.492762698442675e-05
2023-01-24 11:19:44.441429: step: 1748/529, loss: 0.0023557599633932114
2023-01-24 11:19:45.557045: step: 1752/529, loss: 0.00015541866014245898
2023-01-24 11:19:46.663556: step: 1756/529, loss: 0.0002262130001327023
2023-01-24 11:19:47.753123: step: 1760/529, loss: 0.00022248901950661093
2023-01-24 11:19:48.850935: step: 1764/529, loss: 0.00015608487592544407
2023-01-24 11:19:49.955771: step: 1768/529, loss: 0.0010604705894365907
2023-01-24 11:19:51.041233: step: 1772/529, loss: 0.0001499402424087748
2023-01-24 11:19:52.174328: step: 1776/529, loss: 0.010341660119593143
2023-01-24 11:19:53.291440: step: 1780/529, loss: 0.0013549277791753411
2023-01-24 11:19:54.410377: step: 1784/529, loss: 0.00013977581693325192
2023-01-24 11:19:55.514986: step: 1788/529, loss: 2.3025436348689254e-06
2023-01-24 11:19:56.612833: step: 1792/529, loss: 0.0017215120606124401
2023-01-24 11:19:57.721056: step: 1796/529, loss: 0.00048215489368885756
2023-01-24 11:19:58.857775: step: 1800/529, loss: 0.001176641322672367
2023-01-24 11:19:59.945133: step: 1804/529, loss: 0.0008501983247697353
2023-01-24 11:20:01.049709: step: 1808/529, loss: 0.00026085422723554075
2023-01-24 11:20:02.168261: step: 1812/529, loss: 0.00016341837181244045
2023-01-24 11:20:03.265525: step: 1816/529, loss: 0.003964359872043133
2023-01-24 11:20:04.368334: step: 1820/529, loss: 0.00013518851483240724
2023-01-24 11:20:05.460422: step: 1824/529, loss: 0.00016970177239272743
2023-01-24 11:20:06.571374: step: 1828/529, loss: 0.0009307496366091073
2023-01-24 11:20:07.702031: step: 1832/529, loss: 0.0003689092700369656
2023-01-24 11:20:08.809223: step: 1836/529, loss: 6.277789361774921e-05
2023-01-24 11:20:09.918986: step: 1840/529, loss: 0.004234683699905872
2023-01-24 11:20:11.034845: step: 1844/529, loss: 0.0023572933860123158
2023-01-24 11:20:12.128890: step: 1848/529, loss: 0.0015700494404882193
2023-01-24 11:20:13.231128: step: 1852/529, loss: 6.459199539676774e-06
2023-01-24 11:20:14.347482: step: 1856/529, loss: 0.008039561100304127
2023-01-24 11:20:15.448025: step: 1860/529, loss: 0.00024027626204770058
2023-01-24 11:20:16.571842: step: 1864/529, loss: 0.0021593887358903885
2023-01-24 11:20:17.666891: step: 1868/529, loss: 0.0004813428095076233
2023-01-24 11:20:18.802702: step: 1872/529, loss: 0.004609021358191967
2023-01-24 11:20:19.920561: step: 1876/529, loss: 0.0011405982077121735
2023-01-24 11:20:21.032689: step: 1880/529, loss: 0.001695619081147015
2023-01-24 11:20:22.139721: step: 1884/529, loss: 8.133264054777101e-05
2023-01-24 11:20:23.262899: step: 1888/529, loss: 1.111825622501783e-05
2023-01-24 11:20:24.409000: step: 1892/529, loss: 0.0006777423550374806
2023-01-24 11:20:25.497946: step: 1896/529, loss: 6.837446107965661e-06
2023-01-24 11:20:26.610546: step: 1900/529, loss: 0.000639311911072582
2023-01-24 11:20:27.731623: step: 1904/529, loss: 0.007955932058393955
2023-01-24 11:20:28.823536: step: 1908/529, loss: 0.0039582024328410625
2023-01-24 11:20:29.914240: step: 1912/529, loss: 0.0005224067135713995
2023-01-24 11:20:31.025676: step: 1916/529, loss: 0.001513217343017459
2023-01-24 11:20:32.136342: step: 1920/529, loss: 0.0008355839527212083
2023-01-24 11:20:33.213707: step: 1924/529, loss: 0.0035183136351406574
2023-01-24 11:20:34.312772: step: 1928/529, loss: 0.0009953314438462257
2023-01-24 11:20:35.417289: step: 1932/529, loss: 0.0002983025333378464
2023-01-24 11:20:36.522961: step: 1936/529, loss: 0.0002993101952597499
2023-01-24 11:20:37.639679: step: 1940/529, loss: 0.01194830983877182
2023-01-24 11:20:38.754631: step: 1944/529, loss: 0.0015975891146808863
2023-01-24 11:20:39.864435: step: 1948/529, loss: 7.630797335878015e-05
2023-01-24 11:20:41.002387: step: 1952/529, loss: 0.0005793973687104881
2023-01-24 11:20:42.108064: step: 1956/529, loss: 0.0002117531403200701
2023-01-24 11:20:43.220917: step: 1960/529, loss: 0.0050086332485079765
2023-01-24 11:20:44.320981: step: 1964/529, loss: 8.809321298031136e-05
2023-01-24 11:20:45.414559: step: 1968/529, loss: 0.0036579458974301815
2023-01-24 11:20:46.516113: step: 1972/529, loss: 0.0018649366684257984
2023-01-24 11:20:47.626239: step: 1976/529, loss: 0.00021319091320037842
2023-01-24 11:20:48.738310: step: 1980/529, loss: 0.0008732384885661304
2023-01-24 11:20:49.845950: step: 1984/529, loss: 0.004350434523075819
2023-01-24 11:20:50.946133: step: 1988/529, loss: 2.229947131127119e-05
2023-01-24 11:20:52.016134: step: 1992/529, loss: 0.00038746881182305515
2023-01-24 11:20:53.128077: step: 1996/529, loss: 0.008658532053232193
2023-01-24 11:20:54.241592: step: 2000/529, loss: 0.002401188015937805
2023-01-24 11:20:55.365048: step: 2004/529, loss: 4.3907028157263994e-05
2023-01-24 11:20:56.476777: step: 2008/529, loss: 8.565664757043123e-05
2023-01-24 11:20:57.555094: step: 2012/529, loss: 0.0002656480355653912
2023-01-24 11:20:58.672042: step: 2016/529, loss: 3.524524800013751e-05
2023-01-24 11:20:59.774787: step: 2020/529, loss: 0.0004568536824081093
2023-01-24 11:21:00.894728: step: 2024/529, loss: 0.0015852776123210788
2023-01-24 11:21:01.994830: step: 2028/529, loss: 2.808785666275071e-07
2023-01-24 11:21:03.133116: step: 2032/529, loss: 0.0023403314407914877
2023-01-24 11:21:04.241023: step: 2036/529, loss: 0.000985249993391335
2023-01-24 11:21:05.349517: step: 2040/529, loss: 0.0001393989659845829
2023-01-24 11:21:06.465569: step: 2044/529, loss: 0.00012857021647505462
2023-01-24 11:21:07.568235: step: 2048/529, loss: 0.0010407324880361557
2023-01-24 11:21:08.678923: step: 2052/529, loss: 0.003112394129857421
2023-01-24 11:21:09.790456: step: 2056/529, loss: 0.001054321532137692
2023-01-24 11:21:10.929472: step: 2060/529, loss: 0.0043740528635680676
2023-01-24 11:21:12.036997: step: 2064/529, loss: 0.004248266573995352
2023-01-24 11:21:13.184409: step: 2068/529, loss: 0.0008075248915702105
2023-01-24 11:21:14.291821: step: 2072/529, loss: 0.007001884281635284
2023-01-24 11:21:15.398731: step: 2076/529, loss: 4.380242171464488e-05
2023-01-24 11:21:16.505537: step: 2080/529, loss: 0.011050237342715263
2023-01-24 11:21:17.623099: step: 2084/529, loss: 0.004162667319178581
2023-01-24 11:21:18.713136: step: 2088/529, loss: 0.0002774244057945907
2023-01-24 11:21:19.817040: step: 2092/529, loss: 0.0007167458534240723
2023-01-24 11:21:20.962599: step: 2096/529, loss: 0.0033906185999512672
2023-01-24 11:21:22.056899: step: 2100/529, loss: 0.0011811114381998777
2023-01-24 11:21:23.159350: step: 2104/529, loss: 9.449777280678973e-05
2023-01-24 11:21:24.259652: step: 2108/529, loss: 0.007078575436025858
2023-01-24 11:21:25.407856: step: 2112/529, loss: 0.00020052571198903024
2023-01-24 11:21:26.518801: step: 2116/529, loss: 0.0016548684798181057
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3808681991727649, 'r': 0.3244968148549742, 'f1': 0.3504299619437939}, 'combined': 0.2582115509059534, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.4003025140695568, 'r': 0.28791255344690825, 'f1': 0.33493053092513314}, 'combined': 0.2058597409588623, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3713104847807938, 'r': 0.33396806411023955, 'f1': 0.3516506888833092}, 'combined': 0.2591110339140173, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.38099406582230977, 'r': 0.289542283991478, 'f1': 0.32903180278302874}, 'combined': 0.20223418122273962, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4108647450110865, 'r': 0.35161290322580646, 'f1': 0.37893660531697343}, 'combined': 0.279216446023033, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3992933167355875, 'r': 0.28614867672472344, 'f1': 0.33338270867272174}, 'combined': 0.20591284947432817, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4125, 'r': 0.358695652173913, 'f1': 0.3837209302325581}, 'combined': 0.19186046511627905, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38400182134938227, 'r': 0.3286239495798319, 'f1': 0.3541611890154835}, 'combined': 0.260960876116672, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3942784176840146, 'r': 0.28357979781432596, 'f1': 0.32989020834448807}, 'combined': 0.20276178659222194, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.455, 'r': 0.325, 'f1': 0.37916666666666665}, 'combined': 0.25277777777777777, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36935197333215236, 'r': 0.33851423741827247, 'f1': 0.35326139231570214}, 'combined': 0.2602978680220963, 'stategy': 1, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3797808919930203, 'r': 0.29224040908994975, 'f1': 0.33030894426033497}, 'combined': 0.203019155984401, 'stategy': 1, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4342105263157895, 'r': 0.358695652173913, 'f1': 0.3928571428571429}, 'combined': 0.19642857142857145, 'stategy': 1, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4138084632516704, 'r': 0.35256166982922205, 'f1': 0.3807377049180328}, 'combined': 0.2805435720448663, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3948859576574044, 'r': 0.28333238556354495, 'f1': 0.3299349878308081}, 'combined': 0.20378337483667563, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'stategy': 1, 'epoch': 4}