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([122, 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: 561066923, 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 07:09:34.078096: step: 4/533, loss: 0.01594550721347332
2023-01-24 07:09:35.161723: step: 8/533, loss: 0.01623973436653614
2023-01-24 07:09:36.227821: step: 12/533, loss: 0.025600062683224678
2023-01-24 07:09:37.302074: step: 16/533, loss: 0.04417184367775917
2023-01-24 07:09:38.385550: step: 20/533, loss: 0.06865813583135605
2023-01-24 07:09:39.452876: step: 24/533, loss: 0.04775005206465721
2023-01-24 07:09:40.528210: step: 28/533, loss: 0.01723719947040081
2023-01-24 07:09:41.623703: step: 32/533, loss: 0.020858611911535263
2023-01-24 07:09:42.719452: step: 36/533, loss: 0.0168582946062088
2023-01-24 07:09:43.828002: step: 40/533, loss: 0.016195565462112427
2023-01-24 07:09:44.962997: step: 44/533, loss: 0.013944416306912899
2023-01-24 07:09:46.046714: step: 48/533, loss: 0.01876860111951828
2023-01-24 07:09:47.120256: step: 52/533, loss: 0.06417802721261978
2023-01-24 07:09:48.229499: step: 56/533, loss: 0.03598829358816147
2023-01-24 07:09:49.322674: step: 60/533, loss: 0.030301397666335106
2023-01-24 07:09:50.437801: step: 64/533, loss: 0.01978672668337822
2023-01-24 07:09:51.516000: step: 68/533, loss: 0.05278826877474785
2023-01-24 07:09:52.595819: step: 72/533, loss: 0.006483330857008696
2023-01-24 07:09:53.677669: step: 76/533, loss: 0.048134855926036835
2023-01-24 07:09:54.761918: step: 80/533, loss: 0.019971700385212898
2023-01-24 07:09:55.872334: step: 84/533, loss: 0.014037557877600193
2023-01-24 07:09:56.961541: step: 88/533, loss: 0.05830860882997513
2023-01-24 07:09:58.056734: step: 92/533, loss: 0.053832344710826874
2023-01-24 07:09:59.130359: step: 96/533, loss: 0.025877904146909714
2023-01-24 07:10:00.224948: step: 100/533, loss: 0.010820673778653145
2023-01-24 07:10:01.311061: step: 104/533, loss: 0.02344861999154091
2023-01-24 07:10:02.391815: step: 108/533, loss: 0.02452809363603592
2023-01-24 07:10:03.487071: step: 112/533, loss: 0.026574421674013138
2023-01-24 07:10:04.557057: step: 116/533, loss: 0.018311357125639915
2023-01-24 07:10:05.652679: step: 120/533, loss: 0.01614903286099434
2023-01-24 07:10:06.726767: step: 124/533, loss: 0.014634843915700912
2023-01-24 07:10:07.803930: step: 128/533, loss: 0.013529905118048191
2023-01-24 07:10:08.896332: step: 132/533, loss: 0.057390667498111725
2023-01-24 07:10:09.990784: step: 136/533, loss: 0.01302299927920103
2023-01-24 07:10:11.080715: step: 140/533, loss: 0.015509441494941711
2023-01-24 07:10:12.161006: step: 144/533, loss: 0.01691310480237007
2023-01-24 07:10:13.233751: step: 148/533, loss: 0.0
2023-01-24 07:10:14.310644: step: 152/533, loss: 0.037468478083610535
2023-01-24 07:10:15.375634: step: 156/533, loss: 0.016779234632849693
2023-01-24 07:10:16.436736: step: 160/533, loss: 0.01217052061110735
2023-01-24 07:10:17.537124: step: 164/533, loss: 0.011917327530682087
2023-01-24 07:10:18.627127: step: 168/533, loss: 0.01307509746402502
2023-01-24 07:10:19.713940: step: 172/533, loss: 0.03886246681213379
2023-01-24 07:10:20.807341: step: 176/533, loss: 0.026157686486840248
2023-01-24 07:10:21.913692: step: 180/533, loss: 0.016990577802062035
2023-01-24 07:10:22.988892: step: 184/533, loss: 0.014245955273509026
2023-01-24 07:10:24.070091: step: 188/533, loss: 0.013696500100195408
2023-01-24 07:10:25.191311: step: 192/533, loss: 0.08603041619062424
2023-01-24 07:10:26.313829: step: 196/533, loss: 0.03828587755560875
2023-01-24 07:10:27.406626: step: 200/533, loss: 0.018191803246736526
2023-01-24 07:10:28.503752: step: 204/533, loss: 0.06008240580558777
2023-01-24 07:10:29.581705: step: 208/533, loss: 0.05548308417201042
2023-01-24 07:10:30.680886: step: 212/533, loss: 0.024112559854984283
2023-01-24 07:10:31.773267: step: 216/533, loss: 0.01636626571416855
2023-01-24 07:10:32.867761: step: 220/533, loss: 0.018532846122980118
2023-01-24 07:10:33.944151: step: 224/533, loss: 0.02115771174430847
2023-01-24 07:10:35.047848: step: 228/533, loss: 0.03492189571261406
2023-01-24 07:10:36.129604: step: 232/533, loss: 0.007193278521299362
2023-01-24 07:10:37.226856: step: 236/533, loss: 0.009550342336297035
2023-01-24 07:10:38.309134: step: 240/533, loss: 0.06778249889612198
2023-01-24 07:10:39.378812: step: 244/533, loss: 0.02128215692937374
2023-01-24 07:10:40.454051: step: 248/533, loss: 0.011629464104771614
2023-01-24 07:10:41.556365: step: 252/533, loss: 0.01152625773102045
2023-01-24 07:10:42.653562: step: 256/533, loss: 0.030918773263692856
2023-01-24 07:10:43.746912: step: 260/533, loss: 0.01586327701807022
2023-01-24 07:10:44.816388: step: 264/533, loss: 0.017985232174396515
2023-01-24 07:10:45.899653: step: 268/533, loss: 0.016134044155478477
2023-01-24 07:10:46.987163: step: 272/533, loss: 0.017573989927768707
2023-01-24 07:10:48.080076: step: 276/533, loss: 0.12894156575202942
2023-01-24 07:10:49.192749: step: 280/533, loss: 0.013384195044636726
2023-01-24 07:10:50.276293: step: 284/533, loss: 0.03833853453397751
2023-01-24 07:10:51.373278: step: 288/533, loss: 0.03186187893152237
2023-01-24 07:10:52.477134: step: 292/533, loss: 0.0245597492903471
2023-01-24 07:10:53.553513: step: 296/533, loss: 0.015201129950582981
2023-01-24 07:10:54.636161: step: 300/533, loss: 0.0454351082444191
2023-01-24 07:10:55.737599: step: 304/533, loss: 0.058753274381160736
2023-01-24 07:10:56.849881: step: 308/533, loss: 0.05572102591395378
2023-01-24 07:10:57.948949: step: 312/533, loss: 0.018142374232411385
2023-01-24 07:10:59.045831: step: 316/533, loss: 0.012502665631473064
2023-01-24 07:11:00.141677: step: 320/533, loss: 0.06353705376386642
2023-01-24 07:11:01.233491: step: 324/533, loss: 0.07839985936880112
2023-01-24 07:11:02.310475: step: 328/533, loss: 0.049963563680648804
2023-01-24 07:11:03.408198: step: 332/533, loss: 0.012806715443730354
2023-01-24 07:11:04.497772: step: 336/533, loss: 0.009461612440645695
2023-01-24 07:11:05.588590: step: 340/533, loss: 0.013769224286079407
2023-01-24 07:11:06.685420: step: 344/533, loss: 0.03596681356430054
2023-01-24 07:11:07.783107: step: 348/533, loss: 0.013126334175467491
2023-01-24 07:11:08.883601: step: 352/533, loss: 0.04650581628084183
2023-01-24 07:11:09.978484: step: 356/533, loss: 0.01901560090482235
2023-01-24 07:11:11.081275: step: 360/533, loss: 0.019694849848747253
2023-01-24 07:11:12.163513: step: 364/533, loss: 0.01667892560362816
2023-01-24 07:11:13.254118: step: 368/533, loss: 0.014500715769827366
2023-01-24 07:11:14.369062: step: 372/533, loss: 0.07043975591659546
2023-01-24 07:11:15.471033: step: 376/533, loss: 0.012630096636712551
2023-01-24 07:11:16.563216: step: 380/533, loss: 0.05359623581171036
2023-01-24 07:11:17.642892: step: 384/533, loss: 0.010712051764130592
2023-01-24 07:11:18.723085: step: 388/533, loss: 0.013953730463981628
2023-01-24 07:11:19.808860: step: 392/533, loss: 0.049763984978199005
2023-01-24 07:11:20.883003: step: 396/533, loss: 0.023058507591485977
2023-01-24 07:11:21.991070: step: 400/533, loss: 0.0220797136425972
2023-01-24 07:11:23.078818: step: 404/533, loss: 0.03378187492489815
2023-01-24 07:11:24.156572: step: 408/533, loss: 0.04932564124464989
2023-01-24 07:11:25.253212: step: 412/533, loss: 0.04368259385228157
2023-01-24 07:11:26.352322: step: 416/533, loss: 0.01589009538292885
2023-01-24 07:11:27.428099: step: 420/533, loss: 0.013841111212968826
2023-01-24 07:11:28.518946: step: 424/533, loss: 0.007664002478122711
2023-01-24 07:11:29.615213: step: 428/533, loss: 0.008571386337280273
2023-01-24 07:11:30.701230: step: 432/533, loss: 0.03587321564555168
2023-01-24 07:11:31.766659: step: 436/533, loss: 0.05509749799966812
2023-01-24 07:11:32.853619: step: 440/533, loss: 0.013623368926346302
2023-01-24 07:11:33.937214: step: 444/533, loss: 0.00893553625792265
2023-01-24 07:11:35.013020: step: 448/533, loss: 0.04643327742815018
2023-01-24 07:11:36.126289: step: 452/533, loss: 0.009403081610798836
2023-01-24 07:11:37.218985: step: 456/533, loss: 0.0585842989385128
2023-01-24 07:11:38.337225: step: 460/533, loss: 0.014009098522365093
2023-01-24 07:11:39.434618: step: 464/533, loss: 0.014628607779741287
2023-01-24 07:11:40.523029: step: 468/533, loss: 0.008291634730994701
2023-01-24 07:11:41.605567: step: 472/533, loss: 0.011228042654693127
2023-01-24 07:11:42.683726: step: 476/533, loss: 0.024613995105028152
2023-01-24 07:11:43.768484: step: 480/533, loss: 0.01312523614615202
2023-01-24 07:11:44.842299: step: 484/533, loss: 0.01068204641342163
2023-01-24 07:11:45.978247: step: 488/533, loss: 0.0446341447532177
2023-01-24 07:11:47.058512: step: 492/533, loss: 0.009662832133471966
2023-01-24 07:11:48.131339: step: 496/533, loss: 0.022391293197870255
2023-01-24 07:11:49.219976: step: 500/533, loss: 0.01502079889178276
2023-01-24 07:11:50.323434: step: 504/533, loss: 0.014822776429355145
2023-01-24 07:11:51.424993: step: 508/533, loss: 0.010265301913022995
2023-01-24 07:11:52.529941: step: 512/533, loss: 0.019270094111561775
2023-01-24 07:11:53.606333: step: 516/533, loss: 0.017036855220794678
2023-01-24 07:11:54.742266: step: 520/533, loss: 0.036090970039367676
2023-01-24 07:11:55.829826: step: 524/533, loss: 0.007205290719866753
2023-01-24 07:11:56.910305: step: 528/533, loss: 0.010381779633462429
2023-01-24 07:11:58.027149: step: 532/533, loss: 0.009772643446922302
2023-01-24 07:11:59.126934: step: 536/533, loss: 0.006553178187459707
2023-01-24 07:12:00.236868: step: 540/533, loss: 0.01546100340783596
2023-01-24 07:12:01.318279: step: 544/533, loss: 0.03761184215545654
2023-01-24 07:12:02.414226: step: 548/533, loss: 0.05195557326078415
2023-01-24 07:12:03.495179: step: 552/533, loss: 0.008721227757632732
2023-01-24 07:12:04.575294: step: 556/533, loss: 0.043604906648397446
2023-01-24 07:12:05.655241: step: 560/533, loss: 0.061946433037519455
2023-01-24 07:12:06.750521: step: 564/533, loss: 0.009984291158616543
2023-01-24 07:12:07.853629: step: 568/533, loss: 0.010358656756579876
2023-01-24 07:12:08.956700: step: 572/533, loss: 0.027664847671985626
2023-01-24 07:12:10.068283: step: 576/533, loss: 0.016084466129541397
2023-01-24 07:12:11.169174: step: 580/533, loss: 0.0022245210129767656
2023-01-24 07:12:12.256948: step: 584/533, loss: 0.020262613892555237
2023-01-24 07:12:13.334315: step: 588/533, loss: 0.01354117039591074
2023-01-24 07:12:14.433312: step: 592/533, loss: 0.04978485032916069
2023-01-24 07:12:15.524273: step: 596/533, loss: 0.01026873104274273
2023-01-24 07:12:16.603256: step: 600/533, loss: 0.008875931613147259
2023-01-24 07:12:17.687231: step: 604/533, loss: 0.017024287953972816
2023-01-24 07:12:18.764235: step: 608/533, loss: 0.013755924999713898
2023-01-24 07:12:19.859314: step: 612/533, loss: 0.05518774315714836
2023-01-24 07:12:20.941914: step: 616/533, loss: 0.0161385890096426
2023-01-24 07:12:22.023062: step: 620/533, loss: 0.013520707376301289
2023-01-24 07:12:23.117840: step: 624/533, loss: 0.036341942846775055
2023-01-24 07:12:24.200921: step: 628/533, loss: 0.015753421932458878
2023-01-24 07:12:25.309472: step: 632/533, loss: 0.03309519588947296
2023-01-24 07:12:26.398610: step: 636/533, loss: 0.03799267113208771
2023-01-24 07:12:27.472127: step: 640/533, loss: 0.008471294306218624
2023-01-24 07:12:28.548583: step: 644/533, loss: 0.029864558950066566
2023-01-24 07:12:29.647339: step: 648/533, loss: 0.037011321634054184
2023-01-24 07:12:30.734672: step: 652/533, loss: 0.013239260762929916
2023-01-24 07:12:31.824891: step: 656/533, loss: 0.0035461753141134977
2023-01-24 07:12:32.932746: step: 660/533, loss: 0.022695209830999374
2023-01-24 07:12:34.020405: step: 664/533, loss: 0.009942811913788319
2023-01-24 07:12:35.091810: step: 668/533, loss: 0.05884157866239548
2023-01-24 07:12:36.202574: step: 672/533, loss: 0.038355376571416855
2023-01-24 07:12:37.274102: step: 676/533, loss: 0.010683365166187286
2023-01-24 07:12:38.365545: step: 680/533, loss: 0.10095253586769104
2023-01-24 07:12:39.461398: step: 684/533, loss: 0.009038984775543213
2023-01-24 07:12:40.549272: step: 688/533, loss: 0.027139971032738686
2023-01-24 07:12:41.677285: step: 692/533, loss: 0.01258578710258007
2023-01-24 07:12:42.768825: step: 696/533, loss: 0.00844421423971653
2023-01-24 07:12:43.848719: step: 700/533, loss: 0.011624434031546116
2023-01-24 07:12:44.951922: step: 704/533, loss: 0.01921788975596428
2023-01-24 07:12:46.041997: step: 708/533, loss: 0.023436591029167175
2023-01-24 07:12:47.148886: step: 712/533, loss: 0.03221143037080765
2023-01-24 07:12:48.246793: step: 716/533, loss: 0.008329442702233791
2023-01-24 07:12:49.337258: step: 720/533, loss: 0.0020313686691224575
2023-01-24 07:12:50.434543: step: 724/533, loss: 0.06754942238330841
2023-01-24 07:12:51.539080: step: 728/533, loss: 0.02158988267183304
2023-01-24 07:12:52.642417: step: 732/533, loss: 0.08073949813842773
2023-01-24 07:12:53.731674: step: 736/533, loss: 0.010897660627961159
2023-01-24 07:12:54.849225: step: 740/533, loss: 0.044490743428468704
2023-01-24 07:12:55.925305: step: 744/533, loss: 0.01984536275267601
2023-01-24 07:12:57.058793: step: 748/533, loss: 0.010430199094116688
2023-01-24 07:12:58.152761: step: 752/533, loss: 0.06072988733649254
2023-01-24 07:12:59.230791: step: 756/533, loss: 0.01221085712313652
2023-01-24 07:13:00.309840: step: 760/533, loss: 0.0648007020354271
2023-01-24 07:13:01.404931: step: 764/533, loss: 0.019192948937416077
2023-01-24 07:13:02.499685: step: 768/533, loss: 0.014133261516690254
2023-01-24 07:13:03.598760: step: 772/533, loss: 0.014667399227619171
2023-01-24 07:13:04.679425: step: 776/533, loss: 0.004726926796138287
2023-01-24 07:13:05.776470: step: 780/533, loss: 0.05146340653300285
2023-01-24 07:13:06.850063: step: 784/533, loss: 0.008362147957086563
2023-01-24 07:13:07.944514: step: 788/533, loss: 0.004807041957974434
2023-01-24 07:13:09.035312: step: 792/533, loss: 0.0443873405456543
2023-01-24 07:13:10.137645: step: 796/533, loss: 0.013109874911606312
2023-01-24 07:13:11.227605: step: 800/533, loss: 0.01260485127568245
2023-01-24 07:13:12.323163: step: 804/533, loss: 0.012299302034080029
2023-01-24 07:13:13.416532: step: 808/533, loss: 0.023661024868488312
2023-01-24 07:13:14.522562: step: 812/533, loss: 0.008686655201017857
2023-01-24 07:13:15.621482: step: 816/533, loss: 0.006012697238475084
2023-01-24 07:13:16.708039: step: 820/533, loss: 0.02251603826880455
2023-01-24 07:13:17.796749: step: 824/533, loss: 0.016256058588624
2023-01-24 07:13:18.912580: step: 828/533, loss: 0.004223429597914219
2023-01-24 07:13:20.001588: step: 832/533, loss: 0.010521873831748962
2023-01-24 07:13:21.103647: step: 836/533, loss: 0.025704102590680122
2023-01-24 07:13:22.186303: step: 840/533, loss: 0.011306677013635635
2023-01-24 07:13:23.280129: step: 844/533, loss: 0.025942904874682426
2023-01-24 07:13:24.383498: step: 848/533, loss: 0.01663108915090561
2023-01-24 07:13:25.472359: step: 852/533, loss: 0.03758041188120842
2023-01-24 07:13:26.572900: step: 856/533, loss: 0.011881772428750992
2023-01-24 07:13:27.679125: step: 860/533, loss: 0.012492097914218903
2023-01-24 07:13:28.789428: step: 864/533, loss: 0.06700002402067184
2023-01-24 07:13:29.886077: step: 868/533, loss: 0.04401533305644989
2023-01-24 07:13:30.977791: step: 872/533, loss: 0.009267843328416348
2023-01-24 07:13:32.080949: step: 876/533, loss: 0.014800194650888443
2023-01-24 07:13:33.165469: step: 880/533, loss: 0.01819654181599617
2023-01-24 07:13:34.243718: step: 884/533, loss: 0.019947953522205353
2023-01-24 07:13:35.321205: step: 888/533, loss: 0.00857956800609827
2023-01-24 07:13:36.388714: step: 892/533, loss: 0.006512962281703949
2023-01-24 07:13:37.477278: step: 896/533, loss: 0.05075188726186752
2023-01-24 07:13:38.557237: step: 900/533, loss: 0.03060637228190899
2023-01-24 07:13:39.660138: step: 904/533, loss: 0.012079216539859772
2023-01-24 07:13:40.732038: step: 908/533, loss: 0.008230199106037617
2023-01-24 07:13:41.826069: step: 912/533, loss: 0.007888578809797764
2023-01-24 07:13:42.904158: step: 916/533, loss: 0.023600688204169273
2023-01-24 07:13:44.005513: step: 920/533, loss: 0.020242273807525635
2023-01-24 07:13:45.090126: step: 924/533, loss: 0.012885221280157566
2023-01-24 07:13:46.172695: step: 928/533, loss: 0.055731192231178284
2023-01-24 07:13:47.250342: step: 932/533, loss: 0.013757705688476562
2023-01-24 07:13:48.333157: step: 936/533, loss: 0.011107505299150944
2023-01-24 07:13:49.426091: step: 940/533, loss: 0.018321719020605087
2023-01-24 07:13:50.528094: step: 944/533, loss: 0.01166111696511507
2023-01-24 07:13:51.625969: step: 948/533, loss: 0.04753773286938667
2023-01-24 07:13:52.697966: step: 952/533, loss: 0.008567269891500473
2023-01-24 07:13:53.794168: step: 956/533, loss: 0.04113031178712845
2023-01-24 07:13:54.883498: step: 960/533, loss: 0.011874553747475147
2023-01-24 07:13:55.958818: step: 964/533, loss: 0.010472199879586697
2023-01-24 07:13:57.033320: step: 968/533, loss: 0.03212105855345726
2023-01-24 07:13:58.143156: step: 972/533, loss: 0.018843937665224075
2023-01-24 07:13:59.239886: step: 976/533, loss: 0.008022463880479336
2023-01-24 07:14:00.318319: step: 980/533, loss: 0.010757801122963428
2023-01-24 07:14:01.394301: step: 984/533, loss: 0.016277750954031944
2023-01-24 07:14:02.498656: step: 988/533, loss: 0.051602788269519806
2023-01-24 07:14:03.581371: step: 992/533, loss: 0.011717583984136581
2023-01-24 07:14:04.685460: step: 996/533, loss: 0.013772377744317055
2023-01-24 07:14:05.793824: step: 1000/533, loss: 0.023755326867103577
2023-01-24 07:14:06.891526: step: 1004/533, loss: 0.01009039580821991
2023-01-24 07:14:08.013604: step: 1008/533, loss: 0.005220043007284403
2023-01-24 07:14:09.098542: step: 1012/533, loss: 0.0058016544207930565
2023-01-24 07:14:10.192742: step: 1016/533, loss: 0.041087113320827484
2023-01-24 07:14:11.261942: step: 1020/533, loss: 0.01604340597987175
2023-01-24 07:14:12.328081: step: 1024/533, loss: 0.03404732793569565
2023-01-24 07:14:13.442105: step: 1028/533, loss: 0.011191300116479397
2023-01-24 07:14:14.528034: step: 1032/533, loss: 0.0059611620381474495
2023-01-24 07:14:15.611065: step: 1036/533, loss: 0.055433738976716995
2023-01-24 07:14:16.694790: step: 1040/533, loss: 0.017789214849472046
2023-01-24 07:14:17.781703: step: 1044/533, loss: 0.011357159353792667
2023-01-24 07:14:18.895514: step: 1048/533, loss: 0.05060678347945213
2023-01-24 07:14:19.990094: step: 1052/533, loss: 0.010508159175515175
2023-01-24 07:14:21.072643: step: 1056/533, loss: 0.008604254573583603
2023-01-24 07:14:22.173461: step: 1060/533, loss: 0.006093201693147421
2023-01-24 07:14:23.276357: step: 1064/533, loss: 0.044833723455667496
2023-01-24 07:14:24.377445: step: 1068/533, loss: 0.049959197640419006
2023-01-24 07:14:25.440582: step: 1072/533, loss: 0.009037730284035206
2023-01-24 07:14:26.516990: step: 1076/533, loss: 0.03558586910367012
2023-01-24 07:14:27.633303: step: 1080/533, loss: 0.012874887324869633
2023-01-24 07:14:28.717072: step: 1084/533, loss: 0.044012732803821564
2023-01-24 07:14:29.809722: step: 1088/533, loss: 0.07905545830726624
2023-01-24 07:14:30.909947: step: 1092/533, loss: 0.01607437990605831
2023-01-24 07:14:32.000466: step: 1096/533, loss: 0.014090060256421566
2023-01-24 07:14:33.097578: step: 1100/533, loss: 0.01583777740597725
2023-01-24 07:14:34.169200: step: 1104/533, loss: 0.01360901165753603
2023-01-24 07:14:35.267662: step: 1108/533, loss: 0.01037066150456667
2023-01-24 07:14:36.351617: step: 1112/533, loss: 0.009823258966207504
2023-01-24 07:14:37.442709: step: 1116/533, loss: 0.025182589888572693
2023-01-24 07:14:38.540950: step: 1120/533, loss: 0.007517727091908455
2023-01-24 07:14:39.648917: step: 1124/533, loss: 0.0158709529787302
2023-01-24 07:14:40.744655: step: 1128/533, loss: 0.015840407460927963
2023-01-24 07:14:41.813214: step: 1132/533, loss: 0.0510435588657856
2023-01-24 07:14:42.910136: step: 1136/533, loss: 0.021922774612903595
2023-01-24 07:14:43.995233: step: 1140/533, loss: 0.009434031322598457
2023-01-24 07:14:45.080245: step: 1144/533, loss: 0.010468150489032269
2023-01-24 07:14:46.177220: step: 1148/533, loss: 0.01804952882230282
2023-01-24 07:14:47.259315: step: 1152/533, loss: 0.05072910338640213
2023-01-24 07:14:48.380080: step: 1156/533, loss: 0.06464947760105133
2023-01-24 07:14:49.467357: step: 1160/533, loss: 0.016536487266421318
2023-01-24 07:14:50.585718: step: 1164/533, loss: 0.028511976823210716
2023-01-24 07:14:51.650402: step: 1168/533, loss: 0.006800743285566568
2023-01-24 07:14:52.743256: step: 1172/533, loss: 0.038277629762887955
2023-01-24 07:14:53.813013: step: 1176/533, loss: 0.008436434902250767
2023-01-24 07:14:54.929086: step: 1180/533, loss: 0.06570687144994736
2023-01-24 07:14:56.030548: step: 1184/533, loss: 0.040889672935009
2023-01-24 07:14:57.123228: step: 1188/533, loss: 0.004861390683799982
2023-01-24 07:14:58.212705: step: 1192/533, loss: 0.014111604541540146
2023-01-24 07:14:59.330282: step: 1196/533, loss: 0.010974625125527382
2023-01-24 07:15:00.410950: step: 1200/533, loss: 0.005597899202257395
2023-01-24 07:15:01.515614: step: 1204/533, loss: 0.00976946298032999
2023-01-24 07:15:02.599870: step: 1208/533, loss: 0.007208252791315317
2023-01-24 07:15:03.682447: step: 1212/533, loss: 0.0031363293528556824
2023-01-24 07:15:04.765291: step: 1216/533, loss: 0.013956178911030293
2023-01-24 07:15:05.860048: step: 1220/533, loss: 0.010982777923345566
2023-01-24 07:15:06.934169: step: 1224/533, loss: 0.02406073734164238
2023-01-24 07:15:08.039475: step: 1228/533, loss: 0.02114749699831009
2023-01-24 07:15:09.128101: step: 1232/533, loss: 0.020083541050553322
2023-01-24 07:15:10.221277: step: 1236/533, loss: 0.006492003332823515
2023-01-24 07:15:11.298925: step: 1240/533, loss: 0.017302969470620155
2023-01-24 07:15:12.396854: step: 1244/533, loss: 0.012112781405448914
2023-01-24 07:15:13.498854: step: 1248/533, loss: 0.009047483094036579
2023-01-24 07:15:14.580918: step: 1252/533, loss: 0.010445504449307919
2023-01-24 07:15:15.678013: step: 1256/533, loss: 0.00498929200693965
2023-01-24 07:15:16.765929: step: 1260/533, loss: 0.009748070500791073
2023-01-24 07:15:17.865549: step: 1264/533, loss: 0.027679728344082832
2023-01-24 07:15:18.963487: step: 1268/533, loss: 0.008537578396499157
2023-01-24 07:15:20.055687: step: 1272/533, loss: 0.006342281587421894
2023-01-24 07:15:21.143050: step: 1276/533, loss: 0.00981914158910513
2023-01-24 07:15:22.232693: step: 1280/533, loss: 0.03996405377984047
2023-01-24 07:15:23.345240: step: 1284/533, loss: 0.00966727826744318
2023-01-24 07:15:24.419304: step: 1288/533, loss: 0.008135600946843624
2023-01-24 07:15:25.509944: step: 1292/533, loss: 0.008073159493505955
2023-01-24 07:15:26.608674: step: 1296/533, loss: 0.014329371973872185
2023-01-24 07:15:27.711754: step: 1300/533, loss: 0.008889544755220413
2023-01-24 07:15:28.792177: step: 1304/533, loss: 0.07610899209976196
2023-01-24 07:15:29.865920: step: 1308/533, loss: 0.01661599986255169
2023-01-24 07:15:30.942827: step: 1312/533, loss: 0.010576597414910793
2023-01-24 07:15:32.040283: step: 1316/533, loss: 0.005682086572051048
2023-01-24 07:15:33.141725: step: 1320/533, loss: 0.041883524507284164
2023-01-24 07:15:34.222516: step: 1324/533, loss: 0.012618999928236008
2023-01-24 07:15:35.325490: step: 1328/533, loss: 0.06422930955886841
2023-01-24 07:15:36.414911: step: 1332/533, loss: 0.05344794690608978
2023-01-24 07:15:37.525674: step: 1336/533, loss: 0.016741331666707993
2023-01-24 07:15:38.628424: step: 1340/533, loss: 0.011511317454278469
2023-01-24 07:15:39.737309: step: 1344/533, loss: 0.06317970901727676
2023-01-24 07:15:40.816658: step: 1348/533, loss: 0.0070836711674928665
2023-01-24 07:15:41.925958: step: 1352/533, loss: 0.04140499606728554
2023-01-24 07:15:43.032935: step: 1356/533, loss: 0.007597205229103565
2023-01-24 07:15:44.130159: step: 1360/533, loss: 0.007210825104266405
2023-01-24 07:15:45.219718: step: 1364/533, loss: 0.018754880875349045
2023-01-24 07:15:46.302426: step: 1368/533, loss: 0.019920868799090385
2023-01-24 07:15:47.418640: step: 1372/533, loss: 0.04888672009110451
2023-01-24 07:15:48.513687: step: 1376/533, loss: 0.03360056132078171
2023-01-24 07:15:49.625915: step: 1380/533, loss: 0.020786672830581665
2023-01-24 07:15:50.727535: step: 1384/533, loss: 0.038574960082769394
2023-01-24 07:15:51.813133: step: 1388/533, loss: 0.009738821536302567
2023-01-24 07:15:52.886715: step: 1392/533, loss: 0.004805063828825951
2023-01-24 07:15:53.982176: step: 1396/533, loss: 0.006448970176279545
2023-01-24 07:15:55.098134: step: 1400/533, loss: 0.038339950144290924
2023-01-24 07:15:56.207183: step: 1404/533, loss: 0.007654563523828983
2023-01-24 07:15:57.294664: step: 1408/533, loss: 0.010259542614221573
2023-01-24 07:15:58.415189: step: 1412/533, loss: 0.01623718999326229
2023-01-24 07:15:59.509350: step: 1416/533, loss: 0.014163188636302948
2023-01-24 07:16:00.593517: step: 1420/533, loss: 0.009330200031399727
2023-01-24 07:16:01.672874: step: 1424/533, loss: 0.02008504420518875
2023-01-24 07:16:02.753187: step: 1428/533, loss: 0.008662853389978409
2023-01-24 07:16:03.868226: step: 1432/533, loss: 0.04573655501008034
2023-01-24 07:16:04.967900: step: 1436/533, loss: 0.009107109159231186
2023-01-24 07:16:06.086690: step: 1440/533, loss: 0.006593978963792324
2023-01-24 07:16:07.189246: step: 1444/533, loss: 0.01476842537522316
2023-01-24 07:16:08.283272: step: 1448/533, loss: 0.01119696069508791
2023-01-24 07:16:09.373896: step: 1452/533, loss: 0.06139640882611275
2023-01-24 07:16:10.486304: step: 1456/533, loss: 0.012749544344842434
2023-01-24 07:16:11.578162: step: 1460/533, loss: 0.00825601164251566
2023-01-24 07:16:12.682196: step: 1464/533, loss: 0.014513211324810982
2023-01-24 07:16:13.781017: step: 1468/533, loss: 0.022862115874886513
2023-01-24 07:16:14.884833: step: 1472/533, loss: 0.0071062324568629265
2023-01-24 07:16:15.974369: step: 1476/533, loss: 0.01253710500895977
2023-01-24 07:16:17.061865: step: 1480/533, loss: 0.01281536091119051
2023-01-24 07:16:18.146595: step: 1484/533, loss: 0.008709692396223545
2023-01-24 07:16:19.244276: step: 1488/533, loss: 0.012691261246800423
2023-01-24 07:16:20.319348: step: 1492/533, loss: 0.017040710896253586
2023-01-24 07:16:21.446234: step: 1496/533, loss: 0.0008615574333816767
2023-01-24 07:16:22.527492: step: 1500/533, loss: 0.016135990619659424
2023-01-24 07:16:23.610177: step: 1504/533, loss: 0.016571009531617165
2023-01-24 07:16:24.702335: step: 1508/533, loss: 0.018696913495659828
2023-01-24 07:16:25.820113: step: 1512/533, loss: 0.004675515461713076
2023-01-24 07:16:26.945052: step: 1516/533, loss: 0.007222931366413832
2023-01-24 07:16:28.038066: step: 1520/533, loss: 0.01710495725274086
2023-01-24 07:16:29.151004: step: 1524/533, loss: 0.02974708564579487
2023-01-24 07:16:30.239032: step: 1528/533, loss: 0.005800000857561827
2023-01-24 07:16:31.336956: step: 1532/533, loss: 0.020921112969517708
2023-01-24 07:16:32.433875: step: 1536/533, loss: 0.006851104088127613
2023-01-24 07:16:33.533745: step: 1540/533, loss: 0.01091989129781723
2023-01-24 07:16:34.660292: step: 1544/533, loss: 0.009013384580612183
2023-01-24 07:16:35.750076: step: 1548/533, loss: 0.003497521160170436
2023-01-24 07:16:36.818384: step: 1552/533, loss: 0.009167495183646679
2023-01-24 07:16:37.926108: step: 1556/533, loss: 0.03354962170124054
2023-01-24 07:16:39.023227: step: 1560/533, loss: 0.03983305022120476
2023-01-24 07:16:40.116052: step: 1564/533, loss: 0.011866360902786255
2023-01-24 07:16:41.196747: step: 1568/533, loss: 0.015298436395823956
2023-01-24 07:16:42.308885: step: 1572/533, loss: 0.0059750620275735855
2023-01-24 07:16:43.425457: step: 1576/533, loss: 0.016493136063218117
2023-01-24 07:16:44.527280: step: 1580/533, loss: 0.011474487371742725
2023-01-24 07:16:45.619943: step: 1584/533, loss: 0.0072156270034611225
2023-01-24 07:16:46.731201: step: 1588/533, loss: 0.04844214394688606
2023-01-24 07:16:47.823528: step: 1592/533, loss: 0.048341382294893265
2023-01-24 07:16:48.916102: step: 1596/533, loss: 0.006165795028209686
2023-01-24 07:16:50.019617: step: 1600/533, loss: 0.01480008289217949
2023-01-24 07:16:51.113618: step: 1604/533, loss: 0.024683600291609764
2023-01-24 07:16:52.218806: step: 1608/533, loss: 0.016722355037927628
2023-01-24 07:16:53.329720: step: 1612/533, loss: 0.011787992902100086
2023-01-24 07:16:54.416980: step: 1616/533, loss: 0.015091774053871632
2023-01-24 07:16:55.501697: step: 1620/533, loss: 0.006417169701308012
2023-01-24 07:16:56.550714: step: 1624/533, loss: 0.01806468702852726
2023-01-24 07:16:57.620094: step: 1628/533, loss: 0.010624691843986511
2023-01-24 07:16:58.696775: step: 1632/533, loss: 0.012124743312597275
2023-01-24 07:16:59.799135: step: 1636/533, loss: 0.0067804791033267975
2023-01-24 07:17:00.895386: step: 1640/533, loss: 0.023889632895588875
2023-01-24 07:17:01.970466: step: 1644/533, loss: 0.00952153094112873
2023-01-24 07:17:03.101331: step: 1648/533, loss: 0.012334941886365414
2023-01-24 07:17:04.229126: step: 1652/533, loss: 0.011717134155333042
2023-01-24 07:17:05.321780: step: 1656/533, loss: 0.0055471849627792835
2023-01-24 07:17:06.424223: step: 1660/533, loss: 0.010411684401333332
2023-01-24 07:17:07.563009: step: 1664/533, loss: 0.031117409467697144
2023-01-24 07:17:08.677902: step: 1668/533, loss: 0.01255433913320303
2023-01-24 07:17:09.782982: step: 1672/533, loss: 0.031448844820261
2023-01-24 07:17:10.868087: step: 1676/533, loss: 0.004290777258574963
2023-01-24 07:17:11.975056: step: 1680/533, loss: 0.009934306144714355
2023-01-24 07:17:13.078851: step: 1684/533, loss: 0.009225849062204361
2023-01-24 07:17:14.177674: step: 1688/533, loss: 0.007756582461297512
2023-01-24 07:17:15.288216: step: 1692/533, loss: 0.02128407172858715
2023-01-24 07:17:16.392644: step: 1696/533, loss: 0.022385496646165848
2023-01-24 07:17:17.490369: step: 1700/533, loss: 0.013403598219156265
2023-01-24 07:17:18.617209: step: 1704/533, loss: 0.0141100799664855
2023-01-24 07:17:19.758437: step: 1708/533, loss: 0.016555318608880043
2023-01-24 07:17:20.873130: step: 1712/533, loss: 0.007286285050213337
2023-01-24 07:17:21.963831: step: 1716/533, loss: 0.015398475341498852
2023-01-24 07:17:23.067759: step: 1720/533, loss: 0.006275469437241554
2023-01-24 07:17:24.159635: step: 1724/533, loss: 0.014816278591752052
2023-01-24 07:17:25.255583: step: 1728/533, loss: 0.03165755793452263
2023-01-24 07:17:26.344757: step: 1732/533, loss: 0.011096123605966568
2023-01-24 07:17:27.452739: step: 1736/533, loss: 0.0065680621191859245
2023-01-24 07:17:28.539414: step: 1740/533, loss: 0.007600780576467514
2023-01-24 07:17:29.616658: step: 1744/533, loss: 0.008735504932701588
2023-01-24 07:17:30.713769: step: 1748/533, loss: 0.007815550081431866
2023-01-24 07:17:31.804449: step: 1752/533, loss: 0.010598676279187202
2023-01-24 07:17:32.905151: step: 1756/533, loss: 0.009456527419388294
2023-01-24 07:17:33.991105: step: 1760/533, loss: 0.007084310986101627
2023-01-24 07:17:35.095808: step: 1764/533, loss: 0.0
2023-01-24 07:17:36.223096: step: 1768/533, loss: 0.009452968835830688
2023-01-24 07:17:37.306052: step: 1772/533, loss: 0.008064905181527138
2023-01-24 07:17:38.432265: step: 1776/533, loss: 0.016719559207558632
2023-01-24 07:17:39.530292: step: 1780/533, loss: 0.01680837944149971
2023-01-24 07:17:40.624468: step: 1784/533, loss: 0.0068550980649888515
2023-01-24 07:17:41.726121: step: 1788/533, loss: 0.027965400367975235
2023-01-24 07:17:42.819832: step: 1792/533, loss: 0.0015603190986439586
2023-01-24 07:17:43.921781: step: 1796/533, loss: 0.009419466368854046
2023-01-24 07:17:45.031798: step: 1800/533, loss: 0.013402135111391544
2023-01-24 07:17:46.117687: step: 1804/533, loss: 0.013771142810583115
2023-01-24 07:17:47.216182: step: 1808/533, loss: 0.057813484221696854
2023-01-24 07:17:48.334283: step: 1812/533, loss: 0.014227626845240593
2023-01-24 07:17:49.420727: step: 1816/533, loss: 0.004887161776423454
2023-01-24 07:17:50.533011: step: 1820/533, loss: 0.04112822562456131
2023-01-24 07:17:51.633046: step: 1824/533, loss: 0.015044288709759712
2023-01-24 07:17:52.789119: step: 1828/533, loss: 0.017685730010271072
2023-01-24 07:17:53.877146: step: 1832/533, loss: 0.005706385709345341
2023-01-24 07:17:54.984911: step: 1836/533, loss: 0.02949630469083786
2023-01-24 07:17:56.079742: step: 1840/533, loss: 0.00394033407792449
2023-01-24 07:17:57.175816: step: 1844/533, loss: 0.006914061028510332
2023-01-24 07:17:58.284643: step: 1848/533, loss: 0.02550038881599903
2023-01-24 07:17:59.393554: step: 1852/533, loss: 0.008674263022840023
2023-01-24 07:18:00.491625: step: 1856/533, loss: 0.02656950056552887
2023-01-24 07:18:01.601477: step: 1860/533, loss: 0.008736667223274708
2023-01-24 07:18:02.702849: step: 1864/533, loss: 0.08847321569919586
2023-01-24 07:18:03.799024: step: 1868/533, loss: 0.012927834875881672
2023-01-24 07:18:04.878945: step: 1872/533, loss: 0.0009801897685974836
2023-01-24 07:18:05.965880: step: 1876/533, loss: 0.05433003604412079
2023-01-24 07:18:07.069622: step: 1880/533, loss: 0.010582808405160904
2023-01-24 07:18:08.159942: step: 1884/533, loss: 0.008794862776994705
2023-01-24 07:18:09.269770: step: 1888/533, loss: 0.04107755422592163
2023-01-24 07:18:10.377413: step: 1892/533, loss: 0.024445341899991035
2023-01-24 07:18:11.470291: step: 1896/533, loss: 0.011122948490083218
2023-01-24 07:18:12.604397: step: 1900/533, loss: 0.0302229393273592
2023-01-24 07:18:13.700277: step: 1904/533, loss: 0.006792495027184486
2023-01-24 07:18:14.797838: step: 1908/533, loss: 0.01251665223389864
2023-01-24 07:18:15.905596: step: 1912/533, loss: 0.046664897352457047
2023-01-24 07:18:17.020947: step: 1916/533, loss: 0.044249892234802246
2023-01-24 07:18:18.121440: step: 1920/533, loss: 0.008466018363833427
2023-01-24 07:18:19.241082: step: 1924/533, loss: 0.028148703277111053
2023-01-24 07:18:20.353422: step: 1928/533, loss: 0.0255095474421978
2023-01-24 07:18:21.440631: step: 1932/533, loss: 0.010918544605374336
2023-01-24 07:18:22.564295: step: 1936/533, loss: 0.005810788832604885
2023-01-24 07:18:23.677279: step: 1940/533, loss: 0.061996083706617355
2023-01-24 07:18:24.795280: step: 1944/533, loss: 0.0060608782805502415
2023-01-24 07:18:25.876172: step: 1948/533, loss: 0.01125352457165718
2023-01-24 07:18:26.967888: step: 1952/533, loss: 0.02412468194961548
2023-01-24 07:18:28.065980: step: 1956/533, loss: 0.004431331064552069
2023-01-24 07:18:29.180960: step: 1960/533, loss: 0.03832579404115677
2023-01-24 07:18:30.273612: step: 1964/533, loss: 0.010433322750031948
2023-01-24 07:18:31.374168: step: 1968/533, loss: 0.018249930813908577
2023-01-24 07:18:32.499392: step: 1972/533, loss: 0.013660329394042492
2023-01-24 07:18:33.606696: step: 1976/533, loss: 0.011202868074178696
2023-01-24 07:18:34.704249: step: 1980/533, loss: 0.015651913359761238
2023-01-24 07:18:35.786706: step: 1984/533, loss: 0.05221601948142052
2023-01-24 07:18:36.892499: step: 1988/533, loss: 0.007966392673552036
2023-01-24 07:18:37.988358: step: 1992/533, loss: 0.006035948172211647
2023-01-24 07:18:39.092408: step: 1996/533, loss: 0.000829281925689429
2023-01-24 07:18:40.177994: step: 2000/533, loss: 0.04328630492091179
2023-01-24 07:18:41.276600: step: 2004/533, loss: 0.048432111740112305
2023-01-24 07:18:42.351718: step: 2008/533, loss: 0.00907258503139019
2023-01-24 07:18:43.468394: step: 2012/533, loss: 0.026627948507666588
2023-01-24 07:18:44.576701: step: 2016/533, loss: 0.006006287876516581
2023-01-24 07:18:45.674049: step: 2020/533, loss: 0.03545968979597092
2023-01-24 07:18:46.761487: step: 2024/533, loss: 0.0053750029765069485
2023-01-24 07:18:47.848091: step: 2028/533, loss: 0.024792838841676712
2023-01-24 07:18:48.926524: step: 2032/533, loss: 0.03346027061343193
2023-01-24 07:18:50.040895: step: 2036/533, loss: 0.03992001339793205
2023-01-24 07:18:51.134252: step: 2040/533, loss: 0.04616117477416992
2023-01-24 07:18:52.228328: step: 2044/533, loss: 0.014946511946618557
2023-01-24 07:18:53.323928: step: 2048/533, loss: 0.030672762542963028
2023-01-24 07:18:54.413549: step: 2052/533, loss: 0.010912436991930008
2023-01-24 07:18:55.513725: step: 2056/533, loss: 0.03719894960522652
2023-01-24 07:18:56.618461: step: 2060/533, loss: 0.004531790968030691
2023-01-24 07:18:57.744980: step: 2064/533, loss: 0.024654746055603027
2023-01-24 07:18:58.888350: step: 2068/533, loss: 0.014481114223599434
2023-01-24 07:18:59.975443: step: 2072/533, loss: 0.03695772960782051
2023-01-24 07:19:01.076318: step: 2076/533, loss: 0.012480844743549824
2023-01-24 07:19:02.188256: step: 2080/533, loss: 0.006541540380567312
2023-01-24 07:19:03.311204: step: 2084/533, loss: 0.024730829522013664
2023-01-24 07:19:04.413715: step: 2088/533, loss: 0.026747513562440872
2023-01-24 07:19:05.515779: step: 2092/533, loss: 0.012856218963861465
2023-01-24 07:19:06.602953: step: 2096/533, loss: 0.03269417583942413
2023-01-24 07:19:07.698108: step: 2100/533, loss: 0.062488213181495667
2023-01-24 07:19:08.803352: step: 2104/533, loss: 0.004493589047342539
2023-01-24 07:19:09.912167: step: 2108/533, loss: 0.006249538157135248
2023-01-24 07:19:11.040608: step: 2112/533, loss: 0.006704983301460743
2023-01-24 07:19:12.142208: step: 2116/533, loss: 0.00742362579330802
2023-01-24 07:19:13.258724: step: 2120/533, loss: 0.007133388426154852
2023-01-24 07:19:14.368249: step: 2124/533, loss: 0.009088111110031605
2023-01-24 07:19:15.434931: step: 2128/533, loss: 0.006826450582593679
2023-01-24 07:19:16.532560: step: 2132/533, loss: 0.01824604906141758
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36348914565826335, 'r': 0.32831277672359266, 'f1': 0.34500664672648723}, 'combined': 0.2542154239037274, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3713051406297631, 'r': 0.3516688110772275, 'f1': 0.3612203096496955}, 'combined': 0.2408135397664636, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34471358320042533, 'r': 0.31789525889071485, 'f1': 0.33076170076092143}, 'combined': 0.2437191479291, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.36901034771369867, 'r': 0.3054979897898986, 'f1': 0.33426397620357134}, 'combined': 0.22284265080238086, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.332348475827578, 'r': 0.3115372809465342, 'f1': 0.32160655643256325}, 'combined': 0.2369732521082045, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3616920744977294, 'r': 0.3436074707728429, 'f1': 0.35241791874137735}, 'combined': 0.23494527916091817, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7307692307692307, 'r': 0.41304347826086957, 'f1': 0.5277777777777778}, 'combined': 0.35185185185185186, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, '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': 0.36348914565826335, 'r': 0.32831277672359266, 'f1': 0.34500664672648723}, 'combined': 0.2542154239037274, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3713051406297631, 'r': 0.3516688110772275, 'f1': 0.3612203096496955}, 'combined': 0.2408135397664636, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34471358320042533, 'r': 0.31789525889071485, 'f1': 0.33076170076092143}, 'combined': 0.2437191479291, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.36901034771369867, 'r': 0.3054979897898986, 'f1': 0.33426397620357134}, 'combined': 0.22284265080238086, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7307692307692307, 'r': 0.41304347826086957, 'f1': 0.5277777777777778}, 'combined': 0.35185185185185186, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.332348475827578, 'r': 0.3115372809465342, 'f1': 0.32160655643256325}, 'combined': 0.2369732521082045, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3616920744977294, 'r': 0.3436074707728429, 'f1': 0.35241791874137735}, 'combined': 0.23494527916091817, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, '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 07:22:06.346158: step: 4/533, loss: 0.008925613947212696
2023-01-24 07:22:07.425365: step: 8/533, loss: 0.011093520559370518
2023-01-24 07:22:08.523636: step: 12/533, loss: 0.0058023459278047085
2023-01-24 07:22:09.601649: step: 16/533, loss: 0.0254288911819458
2023-01-24 07:22:10.695637: step: 20/533, loss: 0.01613426022231579
2023-01-24 07:22:11.799148: step: 24/533, loss: 0.022490452975034714
2023-01-24 07:22:12.883751: step: 28/533, loss: 0.026726754382252693
2023-01-24 07:22:13.972126: step: 32/533, loss: 0.0064178332686424255
2023-01-24 07:22:15.046307: step: 36/533, loss: 0.007065150421112776
2023-01-24 07:22:16.130871: step: 40/533, loss: 0.005126288626343012
2023-01-24 07:22:17.212681: step: 44/533, loss: 0.0175628624856472
2023-01-24 07:22:18.273003: step: 48/533, loss: 0.003506530076265335
2023-01-24 07:22:19.337620: step: 52/533, loss: 0.01116432435810566
2023-01-24 07:22:20.444036: step: 56/533, loss: 0.024234648793935776
2023-01-24 07:22:21.524947: step: 60/533, loss: 0.02434203401207924
2023-01-24 07:22:22.615725: step: 64/533, loss: 0.012589383870363235
2023-01-24 07:22:23.680684: step: 68/533, loss: 0.03491578623652458
2023-01-24 07:22:24.765212: step: 72/533, loss: 0.017968161031603813
2023-01-24 07:22:25.851264: step: 76/533, loss: 0.01611667312681675
2023-01-24 07:22:26.920675: step: 80/533, loss: 0.0032249377109110355
2023-01-24 07:22:28.015012: step: 84/533, loss: 0.03869962692260742
2023-01-24 07:22:29.096436: step: 88/533, loss: 0.008260197006165981
2023-01-24 07:22:30.181721: step: 92/533, loss: 0.03007417358458042
2023-01-24 07:22:31.247050: step: 96/533, loss: 0.0388333722949028
2023-01-24 07:22:32.320631: step: 100/533, loss: 0.00821117963641882
2023-01-24 07:22:33.405151: step: 104/533, loss: 0.013922277837991714
2023-01-24 07:22:34.495301: step: 108/533, loss: 0.015692410990595818
2023-01-24 07:22:35.579884: step: 112/533, loss: 0.015286232344806194
2023-01-24 07:22:36.677831: step: 116/533, loss: 0.010069034062325954
2023-01-24 07:22:37.766195: step: 120/533, loss: 0.024279817938804626
2023-01-24 07:22:38.855281: step: 124/533, loss: 0.004837061744183302
2023-01-24 07:22:39.950031: step: 128/533, loss: 0.018335094675421715
2023-01-24 07:22:41.051078: step: 132/533, loss: 0.04698308929800987
2023-01-24 07:22:42.138696: step: 136/533, loss: 0.007336444687098265
2023-01-24 07:22:43.246448: step: 140/533, loss: 0.010608860291540623
2023-01-24 07:22:44.334778: step: 144/533, loss: 0.03679569810628891
2023-01-24 07:22:45.437216: step: 148/533, loss: 0.010398210026323795
2023-01-24 07:22:46.528575: step: 152/533, loss: 0.009912537410855293
2023-01-24 07:22:47.612455: step: 156/533, loss: 0.012385787442326546
2023-01-24 07:22:48.729059: step: 160/533, loss: 0.051133185625076294
2023-01-24 07:22:49.810424: step: 164/533, loss: 0.002025886904448271
2023-01-24 07:22:50.909546: step: 168/533, loss: 0.01717594638466835
2023-01-24 07:22:51.984725: step: 172/533, loss: 0.016960248351097107
2023-01-24 07:22:53.089439: step: 176/533, loss: 0.008156201802194118
2023-01-24 07:22:54.163677: step: 180/533, loss: 0.005672939121723175
2023-01-24 07:22:55.263679: step: 184/533, loss: 0.013414998538792133
2023-01-24 07:22:56.341772: step: 188/533, loss: 0.016220100224018097
2023-01-24 07:22:57.433811: step: 192/533, loss: 0.003968982491642237
2023-01-24 07:22:58.498217: step: 196/533, loss: 0.01731756702065468
2023-01-24 07:22:59.588006: step: 200/533, loss: 0.010059109888970852
2023-01-24 07:23:00.674642: step: 204/533, loss: 0.016753770411014557
2023-01-24 07:23:01.746244: step: 208/533, loss: 0.00759066641330719
2023-01-24 07:23:02.821278: step: 212/533, loss: 0.008445285260677338
2023-01-24 07:23:03.914025: step: 216/533, loss: 0.04048917070031166
2023-01-24 07:23:05.018352: step: 220/533, loss: 0.013726937584578991
2023-01-24 07:23:06.121583: step: 224/533, loss: 0.003849520580843091
2023-01-24 07:23:07.201809: step: 228/533, loss: 0.01220738422125578
2023-01-24 07:23:08.297141: step: 232/533, loss: 0.03621504455804825
2023-01-24 07:23:09.368273: step: 236/533, loss: 0.01172435749322176
2023-01-24 07:23:10.449138: step: 240/533, loss: 0.006699166260659695
2023-01-24 07:23:11.527912: step: 244/533, loss: 0.011525461450219154
2023-01-24 07:23:12.621247: step: 248/533, loss: 0.029795458540320396
2023-01-24 07:23:13.722983: step: 252/533, loss: 0.012900792062282562
2023-01-24 07:23:14.797149: step: 256/533, loss: 0.007308041211217642
2023-01-24 07:23:15.888437: step: 260/533, loss: 0.012591083534061909
2023-01-24 07:23:17.004163: step: 264/533, loss: 0.004951964132487774
2023-01-24 07:23:18.077784: step: 268/533, loss: 0.014783511869609356
2023-01-24 07:23:19.157203: step: 272/533, loss: 0.022247154265642166
2023-01-24 07:23:20.241227: step: 276/533, loss: 0.014170602895319462
2023-01-24 07:23:21.314435: step: 280/533, loss: 0.006533030420541763
2023-01-24 07:23:22.407759: step: 284/533, loss: 0.009323183447122574
2023-01-24 07:23:23.514407: step: 288/533, loss: 0.03841555863618851
2023-01-24 07:23:24.603036: step: 292/533, loss: 0.0021806550212204456
2023-01-24 07:23:25.676252: step: 296/533, loss: 0.023267842829227448
2023-01-24 07:23:26.754228: step: 300/533, loss: 0.005537248682230711
2023-01-24 07:23:27.823825: step: 304/533, loss: 0.011080612428486347
2023-01-24 07:23:28.905182: step: 308/533, loss: 0.011464636772871017
2023-01-24 07:23:29.995620: step: 312/533, loss: 0.011529198847711086
2023-01-24 07:23:31.092063: step: 316/533, loss: 0.009971776977181435
2023-01-24 07:23:32.171913: step: 320/533, loss: 0.012636848725378513
2023-01-24 07:23:33.266258: step: 324/533, loss: 0.006611999124288559
2023-01-24 07:23:34.350801: step: 328/533, loss: 0.03487914055585861
2023-01-24 07:23:35.439453: step: 332/533, loss: 0.011139449663460255
2023-01-24 07:23:36.538238: step: 336/533, loss: 0.010063005611300468
2023-01-24 07:23:37.623871: step: 340/533, loss: 0.009021430276334286
2023-01-24 07:23:38.739588: step: 344/533, loss: 0.014709413051605225
2023-01-24 07:23:39.802249: step: 348/533, loss: 0.028703078627586365
2023-01-24 07:23:40.873330: step: 352/533, loss: 0.009137424640357494
2023-01-24 07:23:41.966671: step: 356/533, loss: 0.005573668982833624
2023-01-24 07:23:43.056773: step: 360/533, loss: 0.030432390049099922
2023-01-24 07:23:44.143430: step: 364/533, loss: 0.010921692475676537
2023-01-24 07:23:45.227749: step: 368/533, loss: 0.00629640556871891
2023-01-24 07:23:46.321391: step: 372/533, loss: 0.011271798051893711
2023-01-24 07:23:47.405163: step: 376/533, loss: 0.031551189720630646
2023-01-24 07:23:48.510918: step: 380/533, loss: 0.006694453302770853
2023-01-24 07:23:49.590086: step: 384/533, loss: 0.00836116448044777
2023-01-24 07:23:50.689824: step: 388/533, loss: 0.021361079066991806
2023-01-24 07:23:51.793905: step: 392/533, loss: 0.00994281005114317
2023-01-24 07:23:52.894724: step: 396/533, loss: 0.004525742493569851
2023-01-24 07:23:53.990610: step: 400/533, loss: 0.004288197495043278
2023-01-24 07:23:55.063571: step: 404/533, loss: 0.034830134361982346
2023-01-24 07:23:56.160437: step: 408/533, loss: 0.021062446758151054
2023-01-24 07:23:57.229382: step: 412/533, loss: 0.03264647722244263
2023-01-24 07:23:58.336353: step: 416/533, loss: 0.005878729280084372
2023-01-24 07:23:59.430625: step: 420/533, loss: 0.0061667487025260925
2023-01-24 07:24:00.504333: step: 424/533, loss: 0.014203639701008797
2023-01-24 07:24:01.591909: step: 428/533, loss: 0.031891848891973495
2023-01-24 07:24:02.688826: step: 432/533, loss: 0.015588675625622272
2023-01-24 07:24:03.772280: step: 436/533, loss: 0.012439212761819363
2023-01-24 07:24:04.884500: step: 440/533, loss: 0.04775090515613556
2023-01-24 07:24:05.972484: step: 444/533, loss: 0.014180255122482777
2023-01-24 07:24:07.057848: step: 448/533, loss: 0.01566915214061737
2023-01-24 07:24:08.140876: step: 452/533, loss: 0.01565147191286087
2023-01-24 07:24:09.229771: step: 456/533, loss: 0.009835238568484783
2023-01-24 07:24:10.361660: step: 460/533, loss: 0.005634940695017576
2023-01-24 07:24:11.480903: step: 464/533, loss: 0.013527895323932171
2023-01-24 07:24:12.616344: step: 468/533, loss: 0.007232138887047768
2023-01-24 07:24:13.718616: step: 472/533, loss: 0.005645276978611946
2023-01-24 07:24:14.804263: step: 476/533, loss: 0.00942808948457241
2023-01-24 07:24:15.879599: step: 480/533, loss: 0.02817002311348915
2023-01-24 07:24:16.968441: step: 484/533, loss: 0.005511586554348469
2023-01-24 07:24:18.046015: step: 488/533, loss: 0.0095926932990551
2023-01-24 07:24:19.157388: step: 492/533, loss: 0.041165996342897415
2023-01-24 07:24:20.250980: step: 496/533, loss: 0.018384834751486778
2023-01-24 07:24:21.370512: step: 500/533, loss: 0.006295149214565754
2023-01-24 07:24:22.485110: step: 504/533, loss: 0.009075933136045933
2023-01-24 07:24:23.574993: step: 508/533, loss: 0.03459804505109787
2023-01-24 07:24:24.649906: step: 512/533, loss: 0.010590721853077412
2023-01-24 07:24:25.728305: step: 516/533, loss: 0.011437548324465752
2023-01-24 07:24:26.833687: step: 520/533, loss: 0.004229051060974598
2023-01-24 07:24:27.921922: step: 524/533, loss: 0.022210363298654556
2023-01-24 07:24:29.026605: step: 528/533, loss: 0.003922032192349434
2023-01-24 07:24:30.112199: step: 532/533, loss: 0.019950641319155693
2023-01-24 07:24:31.202866: step: 536/533, loss: 0.022808806970715523
2023-01-24 07:24:32.291443: step: 540/533, loss: 0.0014436112251132727
2023-01-24 07:24:33.375707: step: 544/533, loss: 0.014141925610601902
2023-01-24 07:24:34.454349: step: 548/533, loss: 0.012821177020668983
2023-01-24 07:24:35.546403: step: 552/533, loss: 0.01623542234301567
2023-01-24 07:24:36.655623: step: 556/533, loss: 0.006309705786406994
2023-01-24 07:24:37.737900: step: 560/533, loss: 0.029209788888692856
2023-01-24 07:24:38.818614: step: 564/533, loss: 0.008930402807891369
2023-01-24 07:24:39.914196: step: 568/533, loss: 0.0056000202894210815
2023-01-24 07:24:40.996935: step: 572/533, loss: 0.022733649238944054
2023-01-24 07:24:42.054496: step: 576/533, loss: 0.005594725254923105
2023-01-24 07:24:43.132769: step: 580/533, loss: 0.0038018396589905024
2023-01-24 07:24:44.223348: step: 584/533, loss: 0.009740735404193401
2023-01-24 07:24:45.319863: step: 588/533, loss: 0.011428650468587875
2023-01-24 07:24:46.399481: step: 592/533, loss: 0.05814409255981445
2023-01-24 07:24:47.511560: step: 596/533, loss: 0.09873968362808228
2023-01-24 07:24:48.576996: step: 600/533, loss: 0.011110356077551842
2023-01-24 07:24:49.672676: step: 604/533, loss: 0.004199073649942875
2023-01-24 07:24:50.774370: step: 608/533, loss: 0.016400018706917763
2023-01-24 07:24:51.864101: step: 612/533, loss: 0.043520767241716385
2023-01-24 07:24:52.959233: step: 616/533, loss: 0.0034728357568383217
2023-01-24 07:24:54.054049: step: 620/533, loss: 0.004987440072000027
2023-01-24 07:24:55.147909: step: 624/533, loss: 0.03634863346815109
2023-01-24 07:24:56.234904: step: 628/533, loss: 0.033024080097675323
2023-01-24 07:24:57.337260: step: 632/533, loss: 0.04103824123740196
2023-01-24 07:24:58.428656: step: 636/533, loss: 0.027138726785779
2023-01-24 07:24:59.528505: step: 640/533, loss: 0.03234970569610596
2023-01-24 07:25:00.614399: step: 644/533, loss: 0.047655124217271805
2023-01-24 07:25:01.719066: step: 648/533, loss: 0.05748002976179123
2023-01-24 07:25:02.820997: step: 652/533, loss: 0.008228065446019173
2023-01-24 07:25:03.920507: step: 656/533, loss: 0.016573339700698853
2023-01-24 07:25:04.997683: step: 660/533, loss: 0.005543990526348352
2023-01-24 07:25:06.089860: step: 664/533, loss: 0.0066401418298482895
2023-01-24 07:25:07.197317: step: 668/533, loss: 0.006095356307923794
2023-01-24 07:25:08.274862: step: 672/533, loss: 0.024907980114221573
2023-01-24 07:25:09.356601: step: 676/533, loss: 0.004693935159593821
2023-01-24 07:25:10.443096: step: 680/533, loss: 0.016910288482904434
2023-01-24 07:25:11.525974: step: 684/533, loss: 0.03568674996495247
2023-01-24 07:25:12.615799: step: 688/533, loss: 0.006058427505195141
2023-01-24 07:25:13.697759: step: 692/533, loss: 0.06406237185001373
2023-01-24 07:25:14.785907: step: 696/533, loss: 0.007241168990731239
2023-01-24 07:25:15.869867: step: 700/533, loss: 0.012354905717074871
2023-01-24 07:25:16.959665: step: 704/533, loss: 0.018679505214095116
2023-01-24 07:25:18.054890: step: 708/533, loss: 0.005419182125478983
2023-01-24 07:25:19.167883: step: 712/533, loss: 0.019503310322761536
2023-01-24 07:25:20.269465: step: 716/533, loss: 0.01600051298737526
2023-01-24 07:25:21.376289: step: 720/533, loss: 0.007699155248701572
2023-01-24 07:25:22.466506: step: 724/533, loss: 0.00482341879978776
2023-01-24 07:25:23.561774: step: 728/533, loss: 0.019026000052690506
2023-01-24 07:25:24.667212: step: 732/533, loss: 0.02634083852171898
2023-01-24 07:25:25.747971: step: 736/533, loss: 0.05907056853175163
2023-01-24 07:25:26.833173: step: 740/533, loss: 0.08109515905380249
2023-01-24 07:25:27.922246: step: 744/533, loss: 0.005308034364134073
2023-01-24 07:25:29.019429: step: 748/533, loss: 0.046959392726421356
2023-01-24 07:25:30.089644: step: 752/533, loss: 0.011808075942099094
2023-01-24 07:25:31.171689: step: 756/533, loss: 0.03541991859674454
2023-01-24 07:25:32.258540: step: 760/533, loss: 0.006159640848636627
2023-01-24 07:25:33.378598: step: 764/533, loss: 0.02843761444091797
2023-01-24 07:25:34.469797: step: 768/533, loss: 0.00233129458501935
2023-01-24 07:25:35.559433: step: 772/533, loss: 0.035656556487083435
2023-01-24 07:25:36.662830: step: 776/533, loss: 0.03360661491751671
2023-01-24 07:25:37.746100: step: 780/533, loss: 0.007703785318881273
2023-01-24 07:25:38.826738: step: 784/533, loss: 0.012355204671621323
2023-01-24 07:25:39.916152: step: 788/533, loss: 0.01141770463436842
2023-01-24 07:25:40.994937: step: 792/533, loss: 0.010619927197694778
2023-01-24 07:25:42.108669: step: 796/533, loss: 0.008327803574502468
2023-01-24 07:25:43.207522: step: 800/533, loss: 0.014103076420724392
2023-01-24 07:25:44.299790: step: 804/533, loss: 0.051497168838977814
2023-01-24 07:25:45.377835: step: 808/533, loss: 0.020746290683746338
2023-01-24 07:25:46.472446: step: 812/533, loss: 0.002470416948199272
2023-01-24 07:25:47.568195: step: 816/533, loss: 0.010753748007118702
2023-01-24 07:25:48.680729: step: 820/533, loss: 0.014591149985790253
2023-01-24 07:25:49.751889: step: 824/533, loss: 0.01518035214394331
2023-01-24 07:25:50.865178: step: 828/533, loss: 0.0417749248445034
2023-01-24 07:25:51.958149: step: 832/533, loss: 0.009555557742714882
2023-01-24 07:25:53.047839: step: 836/533, loss: 0.008642081171274185
2023-01-24 07:25:54.134310: step: 840/533, loss: 0.05746659263968468
2023-01-24 07:25:55.239061: step: 844/533, loss: 0.0027747510466724634
2023-01-24 07:25:56.334506: step: 848/533, loss: 0.011802561581134796
2023-01-24 07:25:57.442564: step: 852/533, loss: 0.00964966882020235
2023-01-24 07:25:58.520483: step: 856/533, loss: 0.04255588352680206
2023-01-24 07:25:59.616414: step: 860/533, loss: 0.021322228014469147
2023-01-24 07:26:00.711589: step: 864/533, loss: 0.01150614582002163
2023-01-24 07:26:01.811123: step: 868/533, loss: 0.020424969494342804
2023-01-24 07:26:02.892230: step: 872/533, loss: 0.01587420515716076
2023-01-24 07:26:03.975206: step: 876/533, loss: 0.015274500474333763
2023-01-24 07:26:05.084600: step: 880/533, loss: 0.002101684920489788
2023-01-24 07:26:06.154936: step: 884/533, loss: 0.00220762868411839
2023-01-24 07:26:07.238416: step: 888/533, loss: 0.01109248399734497
2023-01-24 07:26:08.350640: step: 892/533, loss: 0.01444181241095066
2023-01-24 07:26:09.439915: step: 896/533, loss: 0.014774741604924202
2023-01-24 07:26:10.532380: step: 900/533, loss: 0.00579412467777729
2023-01-24 07:26:11.599061: step: 904/533, loss: 0.00621021119877696
2023-01-24 07:26:12.722867: step: 908/533, loss: 0.004264539107680321
2023-01-24 07:26:13.838008: step: 912/533, loss: 0.07819143682718277
2023-01-24 07:26:14.925189: step: 916/533, loss: 0.011373464949429035
2023-01-24 07:26:16.043592: step: 920/533, loss: 0.015380415134131908
2023-01-24 07:26:17.124844: step: 924/533, loss: 0.02404681220650673
2023-01-24 07:26:18.214679: step: 928/533, loss: 0.008432273752987385
2023-01-24 07:26:19.291570: step: 932/533, loss: 0.04816380515694618
2023-01-24 07:26:20.387302: step: 936/533, loss: 0.0032615098170936108
2023-01-24 07:26:21.489112: step: 940/533, loss: 0.005723059177398682
2023-01-24 07:26:22.579524: step: 944/533, loss: 0.013308648020029068
2023-01-24 07:26:23.668795: step: 948/533, loss: 0.006898361258208752
2023-01-24 07:26:24.749292: step: 952/533, loss: 0.0268127229064703
2023-01-24 07:26:25.842232: step: 956/533, loss: 0.005686312913894653
2023-01-24 07:26:26.943133: step: 960/533, loss: 0.04237457737326622
2023-01-24 07:26:28.045367: step: 964/533, loss: 0.02490498125553131
2023-01-24 07:26:29.125928: step: 968/533, loss: 0.014365775510668755
2023-01-24 07:26:30.203348: step: 972/533, loss: 0.007850486785173416
2023-01-24 07:26:31.284816: step: 976/533, loss: 0.012416807003319263
2023-01-24 07:26:32.375585: step: 980/533, loss: 0.0034069353714585304
2023-01-24 07:26:33.469450: step: 984/533, loss: 0.0281415693461895
2023-01-24 07:26:34.550690: step: 988/533, loss: 0.015958987176418304
2023-01-24 07:26:35.659071: step: 992/533, loss: 0.011150212027132511
2023-01-24 07:26:36.748068: step: 996/533, loss: 0.008381768129765987
2023-01-24 07:26:37.845190: step: 1000/533, loss: 0.016811953857541084
2023-01-24 07:26:38.956608: step: 1004/533, loss: 0.008414200507104397
2023-01-24 07:26:40.062838: step: 1008/533, loss: 0.03560592979192734
2023-01-24 07:26:41.137113: step: 1012/533, loss: 0.0062303701415658
2023-01-24 07:26:42.210958: step: 1016/533, loss: 0.0024646995589137077
2023-01-24 07:26:43.297811: step: 1020/533, loss: 0.038395971059799194
2023-01-24 07:26:44.382388: step: 1024/533, loss: 0.005241533275693655
2023-01-24 07:26:45.467508: step: 1028/533, loss: 0.0069887530989944935
2023-01-24 07:26:46.586149: step: 1032/533, loss: 0.008667053654789925
2023-01-24 07:26:47.671614: step: 1036/533, loss: 0.003115372033789754
2023-01-24 07:26:48.784336: step: 1040/533, loss: 0.0341968834400177
2023-01-24 07:26:49.878259: step: 1044/533, loss: 0.0
2023-01-24 07:26:50.977589: step: 1048/533, loss: 0.03794778138399124
2023-01-24 07:26:52.065907: step: 1052/533, loss: 0.08537909388542175
2023-01-24 07:26:53.148211: step: 1056/533, loss: 0.018842177465558052
2023-01-24 07:26:54.226324: step: 1060/533, loss: 0.011245747096836567
2023-01-24 07:26:55.317196: step: 1064/533, loss: 0.020408974960446358
2023-01-24 07:26:56.406942: step: 1068/533, loss: 0.013045798987150192
2023-01-24 07:26:57.504666: step: 1072/533, loss: 0.021844634786248207
2023-01-24 07:26:58.592450: step: 1076/533, loss: 0.0075671738013625145
2023-01-24 07:26:59.679737: step: 1080/533, loss: 0.008715600706636906
2023-01-24 07:27:00.747179: step: 1084/533, loss: 0.04451737180352211
2023-01-24 07:27:01.829926: step: 1088/533, loss: 0.006853511091321707
2023-01-24 07:27:02.907330: step: 1092/533, loss: 0.0015571132535114884
2023-01-24 07:27:04.011620: step: 1096/533, loss: 0.002805503783747554
2023-01-24 07:27:05.101491: step: 1100/533, loss: 0.005748588126152754
2023-01-24 07:27:06.197416: step: 1104/533, loss: 0.008831224404275417
2023-01-24 07:27:07.309178: step: 1108/533, loss: 0.0013629422755911946
2023-01-24 07:27:08.395546: step: 1112/533, loss: 0.04705285280942917
2023-01-24 07:27:09.453731: step: 1116/533, loss: 0.007837486453354359
2023-01-24 07:27:10.548589: step: 1120/533, loss: 0.0032384663354605436
2023-01-24 07:27:11.615412: step: 1124/533, loss: 0.011592747643589973
2023-01-24 07:27:12.697384: step: 1128/533, loss: 0.005072848871350288
2023-01-24 07:27:13.785778: step: 1132/533, loss: 0.031061384826898575
2023-01-24 07:27:14.877703: step: 1136/533, loss: 0.009369976818561554
2023-01-24 07:27:15.956346: step: 1140/533, loss: 0.011183694005012512
2023-01-24 07:27:17.023757: step: 1144/533, loss: 0.003200326580554247
2023-01-24 07:27:18.108383: step: 1148/533, loss: 0.0077477023005485535
2023-01-24 07:27:19.193512: step: 1152/533, loss: 0.007399132940918207
2023-01-24 07:27:20.325101: step: 1156/533, loss: 0.011876900680363178
2023-01-24 07:27:21.416260: step: 1160/533, loss: 0.004952153656631708
2023-01-24 07:27:22.521360: step: 1164/533, loss: 0.013890908099710941
2023-01-24 07:27:23.629052: step: 1168/533, loss: 0.013034052215516567
2023-01-24 07:27:24.720195: step: 1172/533, loss: 0.011917910538613796
2023-01-24 07:27:25.804788: step: 1176/533, loss: 0.004274799022823572
2023-01-24 07:27:26.886309: step: 1180/533, loss: 0.007342600263655186
2023-01-24 07:27:27.967209: step: 1184/533, loss: 0.0021191914565861225
2023-01-24 07:27:29.050383: step: 1188/533, loss: 0.009192829951643944
2023-01-24 07:27:30.142647: step: 1192/533, loss: 0.03928673267364502
2023-01-24 07:27:31.241479: step: 1196/533, loss: 0.0055250064469873905
2023-01-24 07:27:32.316816: step: 1200/533, loss: 0.019327865913510323
2023-01-24 07:27:33.419241: step: 1204/533, loss: 0.014316604472696781
2023-01-24 07:27:34.499786: step: 1208/533, loss: 0.0019721314311027527
2023-01-24 07:27:35.589194: step: 1212/533, loss: 0.0225637499243021
2023-01-24 07:27:36.682712: step: 1216/533, loss: 0.00505601242184639
2023-01-24 07:27:37.754329: step: 1220/533, loss: 0.054867424070835114
2023-01-24 07:27:38.898998: step: 1224/533, loss: 0.004886872600764036
2023-01-24 07:27:40.008274: step: 1228/533, loss: 0.011014881543815136
2023-01-24 07:27:41.101138: step: 1232/533, loss: 0.007566630840301514
2023-01-24 07:27:42.181292: step: 1236/533, loss: 0.02089790068566799
2023-01-24 07:27:43.299964: step: 1240/533, loss: 0.008350999094545841
2023-01-24 07:27:44.383999: step: 1244/533, loss: 0.010961202904582024
2023-01-24 07:27:45.479368: step: 1248/533, loss: 0.027240445837378502
2023-01-24 07:27:46.585380: step: 1252/533, loss: 0.021779421716928482
2023-01-24 07:27:47.682773: step: 1256/533, loss: 0.04111041501164436
2023-01-24 07:27:48.766354: step: 1260/533, loss: 0.020230380818247795
2023-01-24 07:27:49.847838: step: 1264/533, loss: 0.029437899589538574
2023-01-24 07:27:50.949279: step: 1268/533, loss: 0.050302885472774506
2023-01-24 07:27:52.081485: step: 1272/533, loss: 0.05923996865749359
2023-01-24 07:27:53.175603: step: 1276/533, loss: 0.0068550799041986465
2023-01-24 07:27:54.259517: step: 1280/533, loss: 0.00029076560167595744
2023-01-24 07:27:55.372923: step: 1284/533, loss: 0.010229308158159256
2023-01-24 07:27:56.445172: step: 1288/533, loss: 0.055063337087631226
2023-01-24 07:27:57.537856: step: 1292/533, loss: 0.0035267339553683996
2023-01-24 07:27:58.630364: step: 1296/533, loss: 0.009123510681092739
2023-01-24 07:27:59.714910: step: 1300/533, loss: 0.0038117847871035337
2023-01-24 07:28:00.837184: step: 1304/533, loss: 0.0029906199779361486
2023-01-24 07:28:01.952557: step: 1308/533, loss: 0.011358625255525112
2023-01-24 07:28:03.029210: step: 1312/533, loss: 0.03628367558121681
2023-01-24 07:28:04.123203: step: 1316/533, loss: 0.007179169915616512
2023-01-24 07:28:05.220750: step: 1320/533, loss: 0.008094103075563908
2023-01-24 07:28:06.323858: step: 1324/533, loss: 0.028030727058649063
2023-01-24 07:28:07.419453: step: 1328/533, loss: 0.008527093566954136
2023-01-24 07:28:08.520703: step: 1332/533, loss: 0.02082739770412445
2023-01-24 07:28:09.627791: step: 1336/533, loss: 0.014704165048897266
2023-01-24 07:28:10.715634: step: 1340/533, loss: 0.011326384730637074
2023-01-24 07:28:11.838600: step: 1344/533, loss: 0.011415835469961166
2023-01-24 07:28:12.952023: step: 1348/533, loss: 0.022344104945659637
2023-01-24 07:28:14.042778: step: 1352/533, loss: 0.006475296337157488
2023-01-24 07:28:15.107058: step: 1356/533, loss: 0.004845849238336086
2023-01-24 07:28:16.196287: step: 1360/533, loss: 0.00635699275881052
2023-01-24 07:28:17.290521: step: 1364/533, loss: 0.05521085113286972
2023-01-24 07:28:18.392402: step: 1368/533, loss: 0.005095184780657291
2023-01-24 07:28:19.476323: step: 1372/533, loss: 0.0037074252031743526
2023-01-24 07:28:20.557767: step: 1376/533, loss: 0.01019546389579773
2023-01-24 07:28:21.657777: step: 1380/533, loss: 0.021380798891186714
2023-01-24 07:28:22.761395: step: 1384/533, loss: 0.04180828481912613
2023-01-24 07:28:23.864365: step: 1388/533, loss: 0.02912544086575508
2023-01-24 07:28:24.953768: step: 1392/533, loss: 0.0059900544583797455
2023-01-24 07:28:26.035154: step: 1396/533, loss: 0.009176409803330898
2023-01-24 07:28:27.139229: step: 1400/533, loss: 0.025094222277402878
2023-01-24 07:28:28.229408: step: 1404/533, loss: 0.003887948114424944
2023-01-24 07:28:29.343464: step: 1408/533, loss: 0.0069276876747608185
2023-01-24 07:28:30.440696: step: 1412/533, loss: 0.03354548290371895
2023-01-24 07:28:31.551456: step: 1416/533, loss: 0.012077408842742443
2023-01-24 07:28:32.666257: step: 1420/533, loss: 0.015202338807284832
2023-01-24 07:28:33.752949: step: 1424/533, loss: 0.0213848315179348
2023-01-24 07:28:34.833851: step: 1428/533, loss: 0.00997061375528574
2023-01-24 07:28:35.938053: step: 1432/533, loss: 0.02448503114283085
2023-01-24 07:28:37.035262: step: 1436/533, loss: 0.010743062011897564
2023-01-24 07:28:38.121850: step: 1440/533, loss: 0.011644295416772366
2023-01-24 07:28:39.213036: step: 1444/533, loss: 0.007209083065390587
2023-01-24 07:28:40.310512: step: 1448/533, loss: 0.00923768151551485
2023-01-24 07:28:41.411848: step: 1452/533, loss: 0.01466023176908493
2023-01-24 07:28:42.486780: step: 1456/533, loss: 0.023172680288553238
2023-01-24 07:28:43.586095: step: 1460/533, loss: 0.032273199409246445
2023-01-24 07:28:44.687883: step: 1464/533, loss: 0.053501833230257034
2023-01-24 07:28:45.792836: step: 1468/533, loss: 0.05315322428941727
2023-01-24 07:28:46.880380: step: 1472/533, loss: 0.044286470860242844
2023-01-24 07:28:48.018133: step: 1476/533, loss: 0.00724642351269722
2023-01-24 07:28:49.114060: step: 1480/533, loss: 0.0035075454507023096
2023-01-24 07:28:50.239151: step: 1484/533, loss: 0.07574257999658585
2023-01-24 07:28:51.344103: step: 1488/533, loss: 0.02287207916378975
2023-01-24 07:28:52.424113: step: 1492/533, loss: 0.049778617918491364
2023-01-24 07:28:53.515871: step: 1496/533, loss: 0.008154568262398243
2023-01-24 07:28:54.606129: step: 1500/533, loss: 0.025839634239673615
2023-01-24 07:28:55.685423: step: 1504/533, loss: 0.026096895337104797
2023-01-24 07:28:56.767925: step: 1508/533, loss: 0.01595170982182026
2023-01-24 07:28:57.844644: step: 1512/533, loss: 0.009852842427790165
2023-01-24 07:28:58.943181: step: 1516/533, loss: 0.005769921932369471
2023-01-24 07:29:00.032661: step: 1520/533, loss: 0.010454357601702213
2023-01-24 07:29:01.125612: step: 1524/533, loss: 0.00987264234572649
2023-01-24 07:29:02.240985: step: 1528/533, loss: 0.03630882129073143
2023-01-24 07:29:03.359049: step: 1532/533, loss: 0.003901050426065922
2023-01-24 07:29:04.457600: step: 1536/533, loss: 0.011978207156062126
2023-01-24 07:29:05.568321: step: 1540/533, loss: 0.00884245429188013
2023-01-24 07:29:06.670021: step: 1544/533, loss: 0.009602317586541176
2023-01-24 07:29:07.773292: step: 1548/533, loss: 0.029825082048773766
2023-01-24 07:29:08.899105: step: 1552/533, loss: 0.006534433923661709
2023-01-24 07:29:09.990937: step: 1556/533, loss: 0.0547732338309288
2023-01-24 07:29:11.084812: step: 1560/533, loss: 0.008808031678199768
2023-01-24 07:29:12.187772: step: 1564/533, loss: 0.0069520603865385056
2023-01-24 07:29:13.311591: step: 1568/533, loss: 0.007622621953487396
2023-01-24 07:29:14.418980: step: 1572/533, loss: 0.0411258190870285
2023-01-24 07:29:15.520878: step: 1576/533, loss: 0.007049611769616604
2023-01-24 07:29:16.622925: step: 1580/533, loss: 0.028327833861112595
2023-01-24 07:29:17.732740: step: 1584/533, loss: 0.009556399658322334
2023-01-24 07:29:18.819718: step: 1588/533, loss: 0.022109180688858032
2023-01-24 07:29:19.934286: step: 1592/533, loss: 0.006933972239494324
2023-01-24 07:29:21.032852: step: 1596/533, loss: 0.008853824809193611
2023-01-24 07:29:22.145635: step: 1600/533, loss: 0.04165737330913544
2023-01-24 07:29:23.231397: step: 1604/533, loss: 0.017674963921308517
2023-01-24 07:29:24.315876: step: 1608/533, loss: 0.009653130546212196
2023-01-24 07:29:25.392284: step: 1612/533, loss: 0.0032906457781791687
2023-01-24 07:29:26.535049: step: 1616/533, loss: 0.06782279163599014
2023-01-24 07:29:27.631766: step: 1620/533, loss: 0.019513968378305435
2023-01-24 07:29:28.718271: step: 1624/533, loss: 0.00859641283750534
2023-01-24 07:29:29.806486: step: 1628/533, loss: 0.03269661217927933
2023-01-24 07:29:30.877388: step: 1632/533, loss: 0.016636256128549576
2023-01-24 07:29:31.990610: step: 1636/533, loss: 0.004539536312222481
2023-01-24 07:29:33.093857: step: 1640/533, loss: 0.02281329780817032
2023-01-24 07:29:34.207399: step: 1644/533, loss: 0.015804894268512726
2023-01-24 07:29:35.299259: step: 1648/533, loss: 0.013316814787685871
2023-01-24 07:29:36.391188: step: 1652/533, loss: 0.013073669746518135
2023-01-24 07:29:37.500272: step: 1656/533, loss: 0.01558060571551323
2023-01-24 07:29:38.621099: step: 1660/533, loss: 0.04010102152824402
2023-01-24 07:29:39.722563: step: 1664/533, loss: 0.007026083767414093
2023-01-24 07:29:40.810398: step: 1668/533, loss: 0.0055320607498288155
2023-01-24 07:29:41.905842: step: 1672/533, loss: 0.00664052739739418
2023-01-24 07:29:42.984803: step: 1676/533, loss: 0.004452748689800501
2023-01-24 07:29:44.067948: step: 1680/533, loss: 0.006865574046969414
2023-01-24 07:29:45.153370: step: 1684/533, loss: 0.008633121848106384
2023-01-24 07:29:46.258424: step: 1688/533, loss: 0.00979382824152708
2023-01-24 07:29:47.369770: step: 1692/533, loss: 0.004290101118385792
2023-01-24 07:29:48.466076: step: 1696/533, loss: 0.008509436622262001
2023-01-24 07:29:49.568023: step: 1700/533, loss: 0.005751847289502621
2023-01-24 07:29:50.694138: step: 1704/533, loss: 0.00995751190930605
2023-01-24 07:29:51.798567: step: 1708/533, loss: 0.017905499786138535
2023-01-24 07:29:52.887618: step: 1712/533, loss: 0.003714309073984623
2023-01-24 07:29:53.976030: step: 1716/533, loss: 0.03903310373425484
2023-01-24 07:29:55.066909: step: 1720/533, loss: 0.005910523235797882
2023-01-24 07:29:56.165736: step: 1724/533, loss: 0.012380363419651985
2023-01-24 07:29:57.265889: step: 1728/533, loss: 0.005427168682217598
2023-01-24 07:29:58.358220: step: 1732/533, loss: 0.007450432050973177
2023-01-24 07:29:59.493335: step: 1736/533, loss: 0.06731580197811127
2023-01-24 07:30:00.593442: step: 1740/533, loss: 0.007790098432451487
2023-01-24 07:30:01.682557: step: 1744/533, loss: 0.008770889602601528
2023-01-24 07:30:02.787764: step: 1748/533, loss: 0.011013220064342022
2023-01-24 07:30:03.871844: step: 1752/533, loss: 0.008153360337018967
2023-01-24 07:30:04.969707: step: 1756/533, loss: 0.020969144999980927
2023-01-24 07:30:06.056221: step: 1760/533, loss: 0.010635321028530598
2023-01-24 07:30:07.140309: step: 1764/533, loss: 0.005536994896829128
2023-01-24 07:30:08.245642: step: 1768/533, loss: 0.01389839593321085
2023-01-24 07:30:09.353502: step: 1772/533, loss: 0.005563698243349791
2023-01-24 07:30:10.476992: step: 1776/533, loss: 0.003085100557655096
2023-01-24 07:30:11.592718: step: 1780/533, loss: 0.011299679055809975
2023-01-24 07:30:12.682379: step: 1784/533, loss: 0.0077589950524270535
2023-01-24 07:30:13.776574: step: 1788/533, loss: 0.004612649325281382
2023-01-24 07:30:14.878732: step: 1792/533, loss: 0.034109704196453094
2023-01-24 07:30:15.972894: step: 1796/533, loss: 0.00584327382966876
2023-01-24 07:30:17.060008: step: 1800/533, loss: 0.003515771823003888
2023-01-24 07:30:18.149586: step: 1804/533, loss: 0.004595890175551176
2023-01-24 07:30:19.237893: step: 1808/533, loss: 0.004432844929397106
2023-01-24 07:30:20.339350: step: 1812/533, loss: 0.004281031899154186
2023-01-24 07:30:21.432907: step: 1816/533, loss: 0.027832726016640663
2023-01-24 07:30:22.518651: step: 1820/533, loss: 0.008137507364153862
2023-01-24 07:30:23.605857: step: 1824/533, loss: 0.030173610895872116
2023-01-24 07:30:24.710882: step: 1828/533, loss: 0.00615853164345026
2023-01-24 07:30:25.808743: step: 1832/533, loss: 0.005501364823430777
2023-01-24 07:30:26.892760: step: 1836/533, loss: 0.010705860331654549
2023-01-24 07:30:27.972586: step: 1840/533, loss: 0.0012563667260110378
2023-01-24 07:30:29.107983: step: 1844/533, loss: 0.014464114792644978
2023-01-24 07:30:30.201442: step: 1848/533, loss: 0.004503981675952673
2023-01-24 07:30:31.284945: step: 1852/533, loss: 0.012309740297496319
2023-01-24 07:30:32.413686: step: 1856/533, loss: 0.006218461319804192
2023-01-24 07:30:33.517973: step: 1860/533, loss: 0.014311340637505054
2023-01-24 07:30:34.622750: step: 1864/533, loss: 0.023816652595996857
2023-01-24 07:30:35.710859: step: 1868/533, loss: 0.00803129281848669
2023-01-24 07:30:36.781396: step: 1872/533, loss: 0.01694415509700775
2023-01-24 07:30:37.879077: step: 1876/533, loss: 0.0550045408308506
2023-01-24 07:30:38.969998: step: 1880/533, loss: 0.008916349150240421
2023-01-24 07:30:40.063106: step: 1884/533, loss: 0.007531862240284681
2023-01-24 07:30:41.151833: step: 1888/533, loss: 0.007989827543497086
2023-01-24 07:30:42.238871: step: 1892/533, loss: 0.03825875371694565
2023-01-24 07:30:43.321363: step: 1896/533, loss: 0.010656577534973621
2023-01-24 07:30:44.407879: step: 1900/533, loss: 0.002253742655739188
2023-01-24 07:30:45.519900: step: 1904/533, loss: 0.041025061160326004
2023-01-24 07:30:46.633734: step: 1908/533, loss: 0.01935526356101036
2023-01-24 07:30:47.713631: step: 1912/533, loss: 0.002935813507065177
2023-01-24 07:30:48.786521: step: 1916/533, loss: 0.019959282130002975
2023-01-24 07:30:49.866408: step: 1920/533, loss: 0.005920074880123138
2023-01-24 07:30:50.965212: step: 1924/533, loss: 0.0035745338536798954
2023-01-24 07:30:52.052654: step: 1928/533, loss: 0.02764144539833069
2023-01-24 07:30:53.139812: step: 1932/533, loss: 0.013049495406448841
2023-01-24 07:30:54.245568: step: 1936/533, loss: 0.007185091730207205
2023-01-24 07:30:55.322962: step: 1940/533, loss: 0.01010767463594675
2023-01-24 07:30:56.404583: step: 1944/533, loss: 0.0068223485723137856
2023-01-24 07:30:57.507947: step: 1948/533, loss: 0.00973474606871605
2023-01-24 07:30:58.605505: step: 1952/533, loss: 0.009427509270608425
2023-01-24 07:30:59.683097: step: 1956/533, loss: 0.03984740003943443
2023-01-24 07:31:00.788857: step: 1960/533, loss: 0.011379594914615154
2023-01-24 07:31:01.899542: step: 1964/533, loss: 0.041487812995910645
2023-01-24 07:31:03.014830: step: 1968/533, loss: 0.010327148251235485
2023-01-24 07:31:04.090568: step: 1972/533, loss: 0.010539263486862183
2023-01-24 07:31:05.160686: step: 1976/533, loss: 0.004065783228725195
2023-01-24 07:31:06.256813: step: 1980/533, loss: 0.0056487261317670345
2023-01-24 07:31:07.361502: step: 1984/533, loss: 0.005893161986023188
2023-01-24 07:31:08.463563: step: 1988/533, loss: 0.005986033007502556
2023-01-24 07:31:09.551942: step: 1992/533, loss: 0.007133099716156721
2023-01-24 07:31:10.635349: step: 1996/533, loss: 0.007295568007975817
2023-01-24 07:31:11.746381: step: 2000/533, loss: 0.07170341908931732
2023-01-24 07:31:12.822580: step: 2004/533, loss: 0.001890211016871035
2023-01-24 07:31:13.914442: step: 2008/533, loss: 0.006241047754883766
2023-01-24 07:31:15.010649: step: 2012/533, loss: 0.010247474536299706
2023-01-24 07:31:16.089406: step: 2016/533, loss: 0.00493429321795702
2023-01-24 07:31:17.179348: step: 2020/533, loss: 0.007579256314784288
2023-01-24 07:31:18.270491: step: 2024/533, loss: 0.039033062756061554
2023-01-24 07:31:19.377252: step: 2028/533, loss: 0.04566526785492897
2023-01-24 07:31:20.470165: step: 2032/533, loss: 0.008977861143648624
2023-01-24 07:31:21.568896: step: 2036/533, loss: 0.004118893761187792
2023-01-24 07:31:22.655601: step: 2040/533, loss: 0.008037014864385128
2023-01-24 07:31:23.753808: step: 2044/533, loss: 0.0704910084605217
2023-01-24 07:31:24.863886: step: 2048/533, loss: 0.018464455381035805
2023-01-24 07:31:25.946789: step: 2052/533, loss: 0.006822636816650629
2023-01-24 07:31:27.027836: step: 2056/533, loss: 0.007116106804460287
2023-01-24 07:31:28.096518: step: 2060/533, loss: 0.010958656668663025
2023-01-24 07:31:29.216700: step: 2064/533, loss: 0.016052599996328354
2023-01-24 07:31:30.302636: step: 2068/533, loss: 0.0020786316599696875
2023-01-24 07:31:31.383095: step: 2072/533, loss: 0.008314988575875759
2023-01-24 07:31:32.458898: step: 2076/533, loss: 0.017723323777318
2023-01-24 07:31:33.555057: step: 2080/533, loss: 0.0037312619388103485
2023-01-24 07:31:34.633028: step: 2084/533, loss: 0.009290730580687523
2023-01-24 07:31:35.704918: step: 2088/533, loss: 0.01150690671056509
2023-01-24 07:31:36.779065: step: 2092/533, loss: 0.027441728860139847
2023-01-24 07:31:37.859004: step: 2096/533, loss: 0.0028937114402651787
2023-01-24 07:31:38.943258: step: 2100/533, loss: 0.006101224105805159
2023-01-24 07:31:40.012657: step: 2104/533, loss: 0.01195582840591669
2023-01-24 07:31:41.101741: step: 2108/533, loss: 0.009777838364243507
2023-01-24 07:31:42.185645: step: 2112/533, loss: 0.03552310913801193
2023-01-24 07:31:43.292938: step: 2116/533, loss: 0.003615034045651555
2023-01-24 07:31:44.383905: step: 2120/533, loss: 0.005735160317271948
2023-01-24 07:31:45.478905: step: 2124/533, loss: 0.027683071792125702
2023-01-24 07:31:46.560232: step: 2128/533, loss: 0.02342553436756134
2023-01-24 07:31:47.640150: step: 2132/533, loss: 0.004547464195638895
==================================================
Loss: 0.017
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35947315314039474, 'r': 0.3226390919077926, 'f1': 0.34006160287081344}, 'combined': 0.2505717073784941, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38738492625485954, 'r': 0.30618308594374477, 'f1': 0.34203051491030567}, 'combined': 0.22802034327353707, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6730769230769231, 'r': 0.3804347826086957, 'f1': 0.48611111111111116}, 'combined': 0.32407407407407407, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34471358320042533, 'r': 0.31789525889071485, 'f1': 0.33076170076092143}, 'combined': 0.2437191479291, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.36901034771369867, 'r': 0.3054979897898986, 'f1': 0.33426397620357134}, 'combined': 0.22284265080238086, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7307692307692307, 'r': 0.41304347826086957, 'f1': 0.5277777777777778}, 'combined': 0.35185185185185186, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, '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 07:34:21.371861: step: 4/533, loss: 0.03143540024757385
2023-01-24 07:34:22.460163: step: 8/533, loss: 0.007290362846106291
2023-01-24 07:34:23.562566: step: 12/533, loss: 0.05290674790740013
2023-01-24 07:34:24.659044: step: 16/533, loss: 0.030136551707983017
2023-01-24 07:34:25.745895: step: 20/533, loss: 0.004592083394527435
2023-01-24 07:34:26.842451: step: 24/533, loss: 0.002864312846213579
2023-01-24 07:34:27.935605: step: 28/533, loss: 0.00025884315255098045
2023-01-24 07:34:29.017446: step: 32/533, loss: 0.0036720414645969868
2023-01-24 07:34:30.102614: step: 36/533, loss: 0.008596212603151798
2023-01-24 07:34:31.190819: step: 40/533, loss: 0.049139782786369324
2023-01-24 07:34:32.285516: step: 44/533, loss: 0.01291133277118206
2023-01-24 07:34:33.369376: step: 48/533, loss: 0.006683246698230505
2023-01-24 07:34:34.423448: step: 52/533, loss: 0.04288350045681
2023-01-24 07:34:35.492503: step: 56/533, loss: 0.01680571213364601
2023-01-24 07:34:36.590243: step: 60/533, loss: 0.004482606891542673
2023-01-24 07:34:37.676381: step: 64/533, loss: 0.008595411665737629
2023-01-24 07:34:38.761013: step: 68/533, loss: 0.005513062234967947
2023-01-24 07:34:39.846989: step: 72/533, loss: 0.017828622832894325
2023-01-24 07:34:40.926582: step: 76/533, loss: 0.00782066024839878
2023-01-24 07:34:42.012776: step: 80/533, loss: 0.006408941466361284
2023-01-24 07:34:43.077460: step: 84/533, loss: 0.0036198075395077467
2023-01-24 07:34:44.139789: step: 88/533, loss: 0.01893874630331993
2023-01-24 07:34:45.224182: step: 92/533, loss: 0.012946904636919498
2023-01-24 07:34:46.300263: step: 96/533, loss: 0.034745074808597565
2023-01-24 07:34:47.377872: step: 100/533, loss: 0.003039517905563116
2023-01-24 07:34:48.450003: step: 104/533, loss: 0.0
2023-01-24 07:34:49.556183: step: 108/533, loss: 0.00045108553604222834
2023-01-24 07:34:50.675237: step: 112/533, loss: 0.02059978060424328
2023-01-24 07:34:51.765169: step: 116/533, loss: 0.006527471821755171
2023-01-24 07:34:52.851118: step: 120/533, loss: 0.037255242466926575
2023-01-24 07:34:53.939127: step: 124/533, loss: 0.01731891743838787
2023-01-24 07:34:55.038622: step: 128/533, loss: 0.008575621992349625
2023-01-24 07:34:56.129939: step: 132/533, loss: 0.011498386971652508
2023-01-24 07:34:57.207533: step: 136/533, loss: 0.011816848069429398
2023-01-24 07:34:58.290676: step: 140/533, loss: 0.004683245904743671
2023-01-24 07:34:59.381852: step: 144/533, loss: 0.008969353511929512
2023-01-24 07:35:00.473285: step: 148/533, loss: 0.007163285277783871
2023-01-24 07:35:01.562940: step: 152/533, loss: 0.0037118778564035892
2023-01-24 07:35:02.659931: step: 156/533, loss: 0.005938536487519741
2023-01-24 07:35:03.756092: step: 160/533, loss: 0.0073188054375350475
2023-01-24 07:35:04.860685: step: 164/533, loss: 0.02381749078631401
2023-01-24 07:35:05.938001: step: 168/533, loss: 0.04931014031171799
2023-01-24 07:35:07.038580: step: 172/533, loss: 0.0024933486711233854
2023-01-24 07:35:08.144714: step: 176/533, loss: 0.006205394398421049
2023-01-24 07:35:09.255819: step: 180/533, loss: 0.006418520584702492
2023-01-24 07:35:10.333294: step: 184/533, loss: 0.011980396695435047
2023-01-24 07:35:11.425779: step: 188/533, loss: 0.011190742254257202
2023-01-24 07:35:12.500058: step: 192/533, loss: 0.017391767352819443
2023-01-24 07:35:13.577622: step: 196/533, loss: 0.004236615262925625
2023-01-24 07:35:14.675663: step: 200/533, loss: 0.012163491919636726
2023-01-24 07:35:15.768652: step: 204/533, loss: 0.006327173672616482
2023-01-24 07:35:16.866130: step: 208/533, loss: 0.005510473623871803
2023-01-24 07:35:17.966598: step: 212/533, loss: 0.005834348499774933
2023-01-24 07:35:19.064972: step: 216/533, loss: 0.00440135458484292
2023-01-24 07:35:20.179599: step: 220/533, loss: 0.004853852093219757
2023-01-24 07:35:21.273879: step: 224/533, loss: 0.005192887969315052
2023-01-24 07:35:22.366715: step: 228/533, loss: 0.00664374977350235
2023-01-24 07:35:23.457181: step: 232/533, loss: 0.007884320802986622
2023-01-24 07:35:24.545536: step: 236/533, loss: 0.008248616941273212
2023-01-24 07:35:25.630446: step: 240/533, loss: 0.013699514791369438
2023-01-24 07:35:26.731468: step: 244/533, loss: 0.016546521335840225
2023-01-24 07:35:27.830351: step: 248/533, loss: 0.004130684770643711
2023-01-24 07:35:28.937978: step: 252/533, loss: 0.009633234702050686
2023-01-24 07:35:30.042132: step: 256/533, loss: 0.027422703802585602
2023-01-24 07:35:31.127571: step: 260/533, loss: 0.005947364494204521
2023-01-24 07:35:32.199927: step: 264/533, loss: 0.0081117432564497
2023-01-24 07:35:33.273451: step: 268/533, loss: 0.006476367823779583
2023-01-24 07:35:34.356951: step: 272/533, loss: 0.004160203970968723
2023-01-24 07:35:35.460447: step: 276/533, loss: 0.012318079359829426
2023-01-24 07:35:36.529410: step: 280/533, loss: 0.011149939149618149
2023-01-24 07:35:37.609393: step: 284/533, loss: 0.008003066293895245
2023-01-24 07:35:38.689230: step: 288/533, loss: 0.00974404439330101
2023-01-24 07:35:39.821380: step: 292/533, loss: 0.0058694640174508095
2023-01-24 07:35:40.907895: step: 296/533, loss: 0.009975536726415157
2023-01-24 07:35:41.986184: step: 300/533, loss: 0.018420135602355003
2023-01-24 07:35:43.066584: step: 304/533, loss: 0.010691123083233833
2023-01-24 07:35:44.158874: step: 308/533, loss: 0.01665141060948372
2023-01-24 07:35:45.281861: step: 312/533, loss: 0.003338320879265666
2023-01-24 07:35:46.400670: step: 316/533, loss: 0.011709248647093773
2023-01-24 07:35:47.500599: step: 320/533, loss: 0.006270202342420816
2023-01-24 07:35:48.608697: step: 324/533, loss: 0.005804487504065037
2023-01-24 07:35:49.690979: step: 328/533, loss: 0.005920395255088806
2023-01-24 07:35:50.772747: step: 332/533, loss: 0.0020027682185173035
2023-01-24 07:35:51.861440: step: 336/533, loss: 0.0036866022273898125
2023-01-24 07:35:52.952076: step: 340/533, loss: 0.005470162723213434
2023-01-24 07:35:54.035742: step: 344/533, loss: 0.003237447002902627
2023-01-24 07:35:55.106325: step: 348/533, loss: 0.01068158820271492
2023-01-24 07:35:56.181062: step: 352/533, loss: 0.014397768303751945
2023-01-24 07:35:57.265734: step: 356/533, loss: 0.019023533910512924
2023-01-24 07:35:58.358321: step: 360/533, loss: 0.015253226272761822
2023-01-24 07:35:59.458934: step: 364/533, loss: 0.006832933984696865
2023-01-24 07:36:00.536118: step: 368/533, loss: 0.010551640763878822
2023-01-24 07:36:01.612014: step: 372/533, loss: 0.004681070800870657
2023-01-24 07:36:02.688515: step: 376/533, loss: 0.05827747657895088
2023-01-24 07:36:03.777278: step: 380/533, loss: 0.019183877855539322
2023-01-24 07:36:04.860520: step: 384/533, loss: 0.008916245773434639
2023-01-24 07:36:05.957041: step: 388/533, loss: 0.015328424982726574
2023-01-24 07:36:07.034516: step: 392/533, loss: 0.007892209105193615
2023-01-24 07:36:08.112105: step: 396/533, loss: 0.006977444048970938
2023-01-24 07:36:09.207035: step: 400/533, loss: 0.009565283544361591
2023-01-24 07:36:10.288761: step: 404/533, loss: 0.0036076803226023912
2023-01-24 07:36:11.373677: step: 408/533, loss: 0.005722390487790108
2023-01-24 07:36:12.456036: step: 412/533, loss: 0.034901220351457596
2023-01-24 07:36:13.549013: step: 416/533, loss: 0.003244719933718443
2023-01-24 07:36:14.652118: step: 420/533, loss: 0.011517805978655815
2023-01-24 07:36:15.748122: step: 424/533, loss: 0.007823131047189236
2023-01-24 07:36:16.810363: step: 428/533, loss: 0.004583883564919233
2023-01-24 07:36:17.931583: step: 432/533, loss: 0.020031999796628952
2023-01-24 07:36:19.006272: step: 436/533, loss: 0.00542818196117878
2023-01-24 07:36:20.083286: step: 440/533, loss: 0.004846257623285055
2023-01-24 07:36:21.198865: step: 444/533, loss: 0.015640348196029663
2023-01-24 07:36:22.294685: step: 448/533, loss: 0.0028899298049509525
2023-01-24 07:36:23.377676: step: 452/533, loss: 0.03152679651975632
2023-01-24 07:36:24.496736: step: 456/533, loss: 0.018906928598880768
2023-01-24 07:36:25.585985: step: 460/533, loss: 0.014965725131332874
2023-01-24 07:36:26.662704: step: 464/533, loss: 0.02057889848947525
2023-01-24 07:36:27.769616: step: 468/533, loss: 0.019665833562612534
2023-01-24 07:36:28.842364: step: 472/533, loss: 0.0073335799388587475
2023-01-24 07:36:29.950907: step: 476/533, loss: 0.0044280048459768295
2023-01-24 07:36:31.043364: step: 480/533, loss: 0.020294252783060074
2023-01-24 07:36:32.146148: step: 484/533, loss: 0.008550722151994705
2023-01-24 07:36:33.250879: step: 488/533, loss: 0.003183335065841675
2023-01-24 07:36:34.348655: step: 492/533, loss: 0.000815436476841569
2023-01-24 07:36:35.421293: step: 496/533, loss: 0.005482346285134554
2023-01-24 07:36:36.526316: step: 500/533, loss: 0.013066351413726807
2023-01-24 07:36:37.612519: step: 504/533, loss: 0.00689847394824028
2023-01-24 07:36:38.698918: step: 508/533, loss: 0.02621537446975708
2023-01-24 07:36:39.822521: step: 512/533, loss: 0.003458647057414055
2023-01-24 07:36:40.922259: step: 516/533, loss: 0.004116411320865154
2023-01-24 07:36:42.021475: step: 520/533, loss: 0.005164094269275665
2023-01-24 07:36:43.115101: step: 524/533, loss: 0.022609392181038857
2023-01-24 07:36:44.201427: step: 528/533, loss: 0.023363104090094566
2023-01-24 07:36:45.278684: step: 532/533, loss: 0.005277535412460566
2023-01-24 07:36:46.372407: step: 536/533, loss: 0.0020729824900627136
2023-01-24 07:36:47.477397: step: 540/533, loss: 0.00665440084412694
2023-01-24 07:36:48.561157: step: 544/533, loss: 0.024406228214502335
2023-01-24 07:36:49.644111: step: 548/533, loss: 0.007575994823127985
2023-01-24 07:36:50.744508: step: 552/533, loss: 0.012080642394721508
2023-01-24 07:36:51.808119: step: 556/533, loss: 0.020412802696228027
2023-01-24 07:36:52.891937: step: 560/533, loss: 0.004277101252228022
2023-01-24 07:36:53.974292: step: 564/533, loss: 0.00527096027508378
2023-01-24 07:36:55.083496: step: 568/533, loss: 0.0021309838630259037
2023-01-24 07:36:56.174497: step: 572/533, loss: 0.005911529064178467
2023-01-24 07:36:57.265791: step: 576/533, loss: 0.012290279380977154
2023-01-24 07:36:58.377915: step: 580/533, loss: 0.1478431671857834
2023-01-24 07:36:59.465264: step: 584/533, loss: 0.029301557689905167
2023-01-24 07:37:00.592131: step: 588/533, loss: 0.009973284788429737
2023-01-24 07:37:01.690228: step: 592/533, loss: 0.010667902417480946
2023-01-24 07:37:02.760026: step: 596/533, loss: 0.004778855945914984
2023-01-24 07:37:03.861016: step: 600/533, loss: 0.0064847939647734165
2023-01-24 07:37:04.950038: step: 604/533, loss: 0.004565545357763767
2023-01-24 07:37:06.044055: step: 608/533, loss: 0.013621721416711807
2023-01-24 07:37:07.146318: step: 612/533, loss: 0.008003424853086472
2023-01-24 07:37:08.243506: step: 616/533, loss: 0.05185984447598457
2023-01-24 07:37:09.336066: step: 620/533, loss: 0.01074344851076603
2023-01-24 07:37:10.423528: step: 624/533, loss: 0.007197429891675711
2023-01-24 07:37:11.528224: step: 628/533, loss: 0.012690722942352295
2023-01-24 07:37:12.594995: step: 632/533, loss: 0.0031639900989830494
2023-01-24 07:37:13.675661: step: 636/533, loss: 0.0021190994884818792
2023-01-24 07:37:14.760290: step: 640/533, loss: 0.0095035620033741
2023-01-24 07:37:15.845713: step: 644/533, loss: 0.009052561596035957
2023-01-24 07:37:16.923989: step: 648/533, loss: 0.02644641324877739
2023-01-24 07:37:18.004218: step: 652/533, loss: 0.004775867331773043
2023-01-24 07:37:19.093515: step: 656/533, loss: 0.004322954919189215
2023-01-24 07:37:20.179596: step: 660/533, loss: 0.0017892587929964066
2023-01-24 07:37:21.265584: step: 664/533, loss: 0.032562047243118286
2023-01-24 07:37:22.349458: step: 668/533, loss: 0.006532198283821344
2023-01-24 07:37:23.423712: step: 672/533, loss: 0.005284937564283609
2023-01-24 07:37:24.507421: step: 676/533, loss: 0.00776162464171648
2023-01-24 07:37:25.571078: step: 680/533, loss: 0.01250469870865345
2023-01-24 07:37:26.653073: step: 684/533, loss: 0.009527524933218956
2023-01-24 07:37:27.751282: step: 688/533, loss: 0.01906448043882847
2023-01-24 07:37:28.848293: step: 692/533, loss: 0.04905780032277107
2023-01-24 07:37:29.937583: step: 696/533, loss: 0.00746331037953496
2023-01-24 07:37:31.017835: step: 700/533, loss: 0.005055660381913185
2023-01-24 07:37:32.095520: step: 704/533, loss: 0.009620510041713715
2023-01-24 07:37:33.194097: step: 708/533, loss: 0.006037093698978424
2023-01-24 07:37:34.269291: step: 712/533, loss: 0.018835173919796944
2023-01-24 07:37:35.353792: step: 716/533, loss: 0.03065245784819126
2023-01-24 07:37:36.458537: step: 720/533, loss: 0.015692785382270813
2023-01-24 07:37:37.545986: step: 724/533, loss: 0.00310829421505332
2023-01-24 07:37:38.631994: step: 728/533, loss: 0.006041796412318945
2023-01-24 07:37:39.763731: step: 732/533, loss: 0.0027411954943090677
2023-01-24 07:37:40.870388: step: 736/533, loss: 0.007090037688612938
2023-01-24 07:37:41.972480: step: 740/533, loss: 0.003693882841616869
2023-01-24 07:37:43.078612: step: 744/533, loss: 0.014240190386772156
2023-01-24 07:37:44.174666: step: 748/533, loss: 0.029635991901159286
2023-01-24 07:37:45.260186: step: 752/533, loss: 0.024593954905867577
2023-01-24 07:37:46.344628: step: 756/533, loss: 0.0072605423629283905
2023-01-24 07:37:47.429483: step: 760/533, loss: 0.021155603229999542
2023-01-24 07:37:48.514919: step: 764/533, loss: 0.0008442546240985394
2023-01-24 07:37:49.612869: step: 768/533, loss: 0.002843779744580388
2023-01-24 07:37:50.700938: step: 772/533, loss: 0.0
2023-01-24 07:37:51.779953: step: 776/533, loss: 0.0042098453268408775
2023-01-24 07:37:52.877793: step: 780/533, loss: 0.014037761837244034
2023-01-24 07:37:53.980948: step: 784/533, loss: 0.011157218366861343
2023-01-24 07:37:55.058535: step: 788/533, loss: 0.0074334233067929745
2023-01-24 07:37:56.151871: step: 792/533, loss: 0.005933855660259724
2023-01-24 07:37:57.225531: step: 796/533, loss: 0.018789594992995262
2023-01-24 07:37:58.328620: step: 800/533, loss: 0.007686153054237366
2023-01-24 07:37:59.423504: step: 804/533, loss: 0.00516678998246789
2023-01-24 07:38:00.503457: step: 808/533, loss: 0.026426780968904495
2023-01-24 07:38:01.611452: step: 812/533, loss: 0.0035205024760216475
2023-01-24 07:38:02.699016: step: 816/533, loss: 0.018345776945352554
2023-01-24 07:38:03.758188: step: 820/533, loss: 0.0026903992984443903
2023-01-24 07:38:04.847749: step: 824/533, loss: 0.00849522091448307
2023-01-24 07:38:05.917276: step: 828/533, loss: 0.00024266712716780603
2023-01-24 07:38:07.025040: step: 832/533, loss: 0.004328001290559769
2023-01-24 07:38:08.149157: step: 836/533, loss: 0.013686156831681728
2023-01-24 07:38:09.241123: step: 840/533, loss: 0.028534643352031708
2023-01-24 07:38:10.323860: step: 844/533, loss: 0.009142156690359116
2023-01-24 07:38:11.401777: step: 848/533, loss: 0.043152861297130585
2023-01-24 07:38:12.489343: step: 852/533, loss: 0.04180504381656647
2023-01-24 07:38:13.572370: step: 856/533, loss: 0.01873677968978882
2023-01-24 07:38:14.650682: step: 860/533, loss: 0.012232224456965923
2023-01-24 07:38:15.758691: step: 864/533, loss: 0.03122578375041485
2023-01-24 07:38:16.882618: step: 868/533, loss: 0.02284267544746399
2023-01-24 07:38:17.969128: step: 872/533, loss: 0.005114917643368244
2023-01-24 07:38:19.034572: step: 876/533, loss: 0.003608610015362501
2023-01-24 07:38:20.124215: step: 880/533, loss: 0.022983195260167122
2023-01-24 07:38:21.212685: step: 884/533, loss: 0.011115807108581066
2023-01-24 07:38:22.312113: step: 888/533, loss: 0.007405625656247139
2023-01-24 07:38:23.420545: step: 892/533, loss: 0.011830934323370457
2023-01-24 07:38:24.518680: step: 896/533, loss: 0.011407998390495777
2023-01-24 07:38:25.600521: step: 900/533, loss: 0.002506178803741932
2023-01-24 07:38:26.715594: step: 904/533, loss: 0.007663481868803501
2023-01-24 07:38:27.813936: step: 908/533, loss: 0.009060348384082317
2023-01-24 07:38:28.907137: step: 912/533, loss: 0.008394896984100342
2023-01-24 07:38:29.972036: step: 916/533, loss: 0.004666364286094904
2023-01-24 07:38:31.071754: step: 920/533, loss: 0.02784525416791439
2023-01-24 07:38:32.158396: step: 924/533, loss: 0.0032175423111766577
2023-01-24 07:38:33.233387: step: 928/533, loss: 0.004276135470718145
2023-01-24 07:38:34.323093: step: 932/533, loss: 0.01193176954984665
2023-01-24 07:38:35.401250: step: 936/533, loss: 0.006394187454134226
2023-01-24 07:38:36.477527: step: 940/533, loss: 0.011017643846571445
2023-01-24 07:38:37.561601: step: 944/533, loss: 0.003448704956099391
2023-01-24 07:38:38.647630: step: 948/533, loss: 0.0011138966074213386
2023-01-24 07:38:39.747579: step: 952/533, loss: 0.02269626595079899
2023-01-24 07:38:40.843096: step: 956/533, loss: 0.00867333635687828
2023-01-24 07:38:41.930247: step: 960/533, loss: 0.012057257816195488
2023-01-24 07:38:43.026548: step: 964/533, loss: 0.0028111450374126434
2023-01-24 07:38:44.111944: step: 968/533, loss: 0.003028042847290635
2023-01-24 07:38:45.186992: step: 972/533, loss: 0.0003705882409121841
2023-01-24 07:38:46.298843: step: 976/533, loss: 0.0076306890696287155
2023-01-24 07:38:47.402390: step: 980/533, loss: 0.006001919507980347
2023-01-24 07:38:48.464679: step: 984/533, loss: 0.0024036907125264406
2023-01-24 07:38:49.532887: step: 988/533, loss: 0.0006804695003665984
2023-01-24 07:38:50.626709: step: 992/533, loss: 0.008289298042654991
2023-01-24 07:38:51.711509: step: 996/533, loss: 0.05045729875564575
2023-01-24 07:38:52.810515: step: 1000/533, loss: 0.012132973410189152
2023-01-24 07:38:53.922466: step: 1004/533, loss: 0.00616392120718956
2023-01-24 07:38:55.006272: step: 1008/533, loss: 0.004644361790269613
2023-01-24 07:38:56.081900: step: 1012/533, loss: 0.006192962173372507
2023-01-24 07:38:57.172387: step: 1016/533, loss: 0.010288700461387634
2023-01-24 07:38:58.279061: step: 1020/533, loss: 0.0170535109937191
2023-01-24 07:38:59.368929: step: 1024/533, loss: 0.04445505142211914
2023-01-24 07:39:00.467622: step: 1028/533, loss: 0.008840791881084442
2023-01-24 07:39:01.549085: step: 1032/533, loss: 0.013872926123440266
2023-01-24 07:39:02.633851: step: 1036/533, loss: 0.03146233782172203
2023-01-24 07:39:03.716131: step: 1040/533, loss: 0.05298042297363281
2023-01-24 07:39:04.808216: step: 1044/533, loss: 0.005206727888435125
2023-01-24 07:39:05.890004: step: 1048/533, loss: 0.004956633318215609
2023-01-24 07:39:07.008676: step: 1052/533, loss: 0.04634881019592285
2023-01-24 07:39:08.117047: step: 1056/533, loss: 0.0393965058028698
2023-01-24 07:39:09.193997: step: 1060/533, loss: 0.011618509888648987
2023-01-24 07:39:10.284681: step: 1064/533, loss: 0.003678616601973772
2023-01-24 07:39:11.370139: step: 1068/533, loss: 0.005601240321993828
2023-01-24 07:39:12.467916: step: 1072/533, loss: 0.0068100872449576855
2023-01-24 07:39:13.584955: step: 1076/533, loss: 0.009597988799214363
2023-01-24 07:39:14.686689: step: 1080/533, loss: 0.008503307588398457
2023-01-24 07:39:15.754837: step: 1084/533, loss: 0.01531152706593275
2023-01-24 07:39:16.834600: step: 1088/533, loss: 0.0026673744432628155
2023-01-24 07:39:17.914270: step: 1092/533, loss: 0.0025334900710731745
2023-01-24 07:39:19.049191: step: 1096/533, loss: 0.0071305204182863235
2023-01-24 07:39:20.187242: step: 1100/533, loss: 0.011470625177025795
2023-01-24 07:39:21.301631: step: 1104/533, loss: 0.00866924412548542
2023-01-24 07:39:22.402825: step: 1108/533, loss: 0.013297321274876595
2023-01-24 07:39:23.494343: step: 1112/533, loss: 0.029257912188768387
2023-01-24 07:39:24.614581: step: 1116/533, loss: 0.0039297533221542835
2023-01-24 07:39:25.697537: step: 1120/533, loss: 0.007797276601195335
2023-01-24 07:39:26.780997: step: 1124/533, loss: 0.003927475772798061
2023-01-24 07:39:27.861913: step: 1128/533, loss: 0.011094893328845501
2023-01-24 07:39:28.942791: step: 1132/533, loss: 0.010308323428034782
2023-01-24 07:39:30.006902: step: 1136/533, loss: 0.01924131065607071
2023-01-24 07:39:31.098576: step: 1140/533, loss: 0.007669389247894287
2023-01-24 07:39:32.204296: step: 1144/533, loss: 0.03659879416227341
2023-01-24 07:39:33.279292: step: 1148/533, loss: 0.036211684346199036
2023-01-24 07:39:34.391263: step: 1152/533, loss: 0.0032197199761867523
2023-01-24 07:39:35.475273: step: 1156/533, loss: 0.009942148812115192
2023-01-24 07:39:36.576965: step: 1160/533, loss: 0.03760348632931709
2023-01-24 07:39:37.690377: step: 1164/533, loss: 0.009087193757295609
2023-01-24 07:39:38.783308: step: 1168/533, loss: 0.006520627997815609
2023-01-24 07:39:39.889322: step: 1172/533, loss: 0.007842054590582848
2023-01-24 07:39:40.973325: step: 1176/533, loss: 0.02118450589478016
2023-01-24 07:39:42.067641: step: 1180/533, loss: 0.002092203591018915
2023-01-24 07:39:43.160584: step: 1184/533, loss: 0.008313585072755814
2023-01-24 07:39:44.245176: step: 1188/533, loss: 0.015645988285541534
2023-01-24 07:39:45.345884: step: 1192/533, loss: 0.018593642860651016
2023-01-24 07:39:46.449374: step: 1196/533, loss: 0.049543894827365875
2023-01-24 07:39:47.538008: step: 1200/533, loss: 0.021710002794861794
2023-01-24 07:39:48.677400: step: 1204/533, loss: 0.00868787057697773
2023-01-24 07:39:49.765296: step: 1208/533, loss: 0.0015336856013163924
2023-01-24 07:39:50.864071: step: 1212/533, loss: 0.00531360087916255
2023-01-24 07:39:51.945749: step: 1216/533, loss: 0.004147379659116268
2023-01-24 07:39:53.060878: step: 1220/533, loss: 0.005360549781471491
2023-01-24 07:39:54.163919: step: 1224/533, loss: 0.0031740490812808275
2023-01-24 07:39:55.247709: step: 1228/533, loss: 0.002876545302569866
2023-01-24 07:39:56.345633: step: 1232/533, loss: 0.0034809508360922337
2023-01-24 07:39:57.423606: step: 1236/533, loss: 0.003415369661524892
2023-01-24 07:39:58.528525: step: 1240/533, loss: 0.0038287120405584574
2023-01-24 07:39:59.631065: step: 1244/533, loss: 0.008860662579536438
2023-01-24 07:40:00.723198: step: 1248/533, loss: 0.007989543490111828
2023-01-24 07:40:01.834880: step: 1252/533, loss: 0.019805900752544403
2023-01-24 07:40:02.927955: step: 1256/533, loss: 0.00515039311721921
2023-01-24 07:40:04.031627: step: 1260/533, loss: 0.005152449943125248
2023-01-24 07:40:05.130030: step: 1264/533, loss: 0.06558722257614136
2023-01-24 07:40:06.237666: step: 1268/533, loss: 0.046278487890958786
2023-01-24 07:40:07.344925: step: 1272/533, loss: 0.0010448063258081675
2023-01-24 07:40:08.435570: step: 1276/533, loss: 0.015850402414798737
2023-01-24 07:40:09.531384: step: 1280/533, loss: 0.007296034134924412
2023-01-24 07:40:10.633205: step: 1284/533, loss: 0.012302565388381481
2023-01-24 07:40:11.756704: step: 1288/533, loss: 0.015379000455141068
2023-01-24 07:40:12.844972: step: 1292/533, loss: 0.003552776761353016
2023-01-24 07:40:13.937063: step: 1296/533, loss: 0.004709901288151741
2023-01-24 07:40:15.082061: step: 1300/533, loss: 0.009566957131028175
2023-01-24 07:40:16.198440: step: 1304/533, loss: 0.007086416240781546
2023-01-24 07:40:17.319609: step: 1308/533, loss: 0.008032411336898804
2023-01-24 07:40:18.411796: step: 1312/533, loss: 0.016809573397040367
2023-01-24 07:40:19.506000: step: 1316/533, loss: 0.006960244849324226
2023-01-24 07:40:20.623882: step: 1320/533, loss: 0.008412796072661877
2023-01-24 07:40:21.714861: step: 1324/533, loss: 0.01985945738852024
2023-01-24 07:40:22.779832: step: 1328/533, loss: 0.00668836385011673
2023-01-24 07:40:23.876041: step: 1332/533, loss: 0.011092136614024639
2023-01-24 07:40:24.977323: step: 1336/533, loss: 0.019724303856492043
2023-01-24 07:40:26.081625: step: 1340/533, loss: 0.014218992553651333
2023-01-24 07:40:27.151981: step: 1344/533, loss: 0.0051703364588320255
2023-01-24 07:40:28.252548: step: 1348/533, loss: 0.022777661681175232
2023-01-24 07:40:29.341803: step: 1352/533, loss: 0.01124496664851904
2023-01-24 07:40:30.448357: step: 1356/533, loss: 0.003010059939697385
2023-01-24 07:40:31.524909: step: 1360/533, loss: 9.990805119741708e-05
2023-01-24 07:40:32.650768: step: 1364/533, loss: 0.13131920993328094
2023-01-24 07:40:33.737335: step: 1368/533, loss: 0.006658780388534069
2023-01-24 07:40:34.827178: step: 1372/533, loss: 0.0027997377328574657
2023-01-24 07:40:35.946060: step: 1376/533, loss: 0.003025772050023079
2023-01-24 07:40:37.038060: step: 1380/533, loss: 0.02321680821478367
2023-01-24 07:40:38.110196: step: 1384/533, loss: 0.006161246448755264
2023-01-24 07:40:39.196308: step: 1388/533, loss: 0.04634488746523857
2023-01-24 07:40:40.311339: step: 1392/533, loss: 0.039342641830444336
2023-01-24 07:40:41.389692: step: 1396/533, loss: 0.005271706264466047
2023-01-24 07:40:42.507931: step: 1400/533, loss: 0.012976311147212982
2023-01-24 07:40:43.590907: step: 1404/533, loss: 0.02522117644548416
2023-01-24 07:40:44.681059: step: 1408/533, loss: 0.0011854091426357627
2023-01-24 07:40:45.797722: step: 1412/533, loss: 0.007242171093821526
2023-01-24 07:40:46.915352: step: 1416/533, loss: 0.020117472857236862
2023-01-24 07:40:47.996801: step: 1420/533, loss: 0.0024570454843342304
2023-01-24 07:40:49.087170: step: 1424/533, loss: 0.01508256234228611
2023-01-24 07:40:50.197541: step: 1428/533, loss: 0.008756075985729694
2023-01-24 07:40:51.306827: step: 1432/533, loss: 0.05218510329723358
2023-01-24 07:40:52.401707: step: 1436/533, loss: 0.00331392721273005
2023-01-24 07:40:53.503757: step: 1440/533, loss: 0.03263251855969429
2023-01-24 07:40:54.603176: step: 1444/533, loss: 0.0024689650163054466
2023-01-24 07:40:55.683789: step: 1448/533, loss: 0.0253375805914402
2023-01-24 07:40:56.750935: step: 1452/533, loss: 0.002268520649522543
2023-01-24 07:40:57.854880: step: 1456/533, loss: 0.004827665630728006
2023-01-24 07:40:58.945541: step: 1460/533, loss: 0.006237417459487915
2023-01-24 07:41:00.028791: step: 1464/533, loss: 0.00014382951485458761
2023-01-24 07:41:01.132898: step: 1468/533, loss: 0.00486094830557704
2023-01-24 07:41:02.220169: step: 1472/533, loss: 0.04403218626976013
2023-01-24 07:41:03.301578: step: 1476/533, loss: 0.014394745230674744
2023-01-24 07:41:04.423321: step: 1480/533, loss: 0.0038502493407577276
2023-01-24 07:41:05.545814: step: 1484/533, loss: 0.045383159071207047
2023-01-24 07:41:06.640935: step: 1488/533, loss: 0.005117606837302446
2023-01-24 07:41:07.709714: step: 1492/533, loss: 0.012705131433904171
2023-01-24 07:41:08.794243: step: 1496/533, loss: 0.007967768236994743
2023-01-24 07:41:09.924703: step: 1500/533, loss: 0.004682290833443403
2023-01-24 07:41:11.038081: step: 1504/533, loss: 0.009044085629284382
2023-01-24 07:41:12.144534: step: 1508/533, loss: 0.006957775913178921
2023-01-24 07:41:13.268658: step: 1512/533, loss: 0.019410034641623497
2023-01-24 07:41:14.366410: step: 1516/533, loss: 0.004025113303214312
2023-01-24 07:41:15.462588: step: 1520/533, loss: 0.00955499242991209
2023-01-24 07:41:16.555901: step: 1524/533, loss: 0.0032078090589493513
2023-01-24 07:41:17.636045: step: 1528/533, loss: 0.012096481397747993
2023-01-24 07:41:18.725764: step: 1532/533, loss: 0.00980396382510662
2023-01-24 07:41:19.804801: step: 1536/533, loss: 0.008564702235162258
2023-01-24 07:41:20.904501: step: 1540/533, loss: 0.005391808692365885
2023-01-24 07:41:21.991496: step: 1544/533, loss: 0.011811736971139908
2023-01-24 07:41:23.103487: step: 1548/533, loss: 0.0108191454783082
2023-01-24 07:41:24.207565: step: 1552/533, loss: 0.016230449080467224
2023-01-24 07:41:25.323314: step: 1556/533, loss: 0.01917206309735775
2023-01-24 07:41:26.426450: step: 1560/533, loss: 0.0550706572830677
2023-01-24 07:41:27.521389: step: 1564/533, loss: 0.022763971239328384
2023-01-24 07:41:28.603066: step: 1568/533, loss: 0.05063802748918533
2023-01-24 07:41:29.682000: step: 1572/533, loss: 0.0033643366768956184
2023-01-24 07:41:30.796894: step: 1576/533, loss: 0.011849500238895416
2023-01-24 07:41:31.878153: step: 1580/533, loss: 0.015039131976664066
2023-01-24 07:41:32.972877: step: 1584/533, loss: 0.0115304971113801
2023-01-24 07:41:34.047205: step: 1588/533, loss: 0.03327210247516632
2023-01-24 07:41:35.134930: step: 1592/533, loss: 0.04944057762622833
2023-01-24 07:41:36.253483: step: 1596/533, loss: 0.003279433585703373
2023-01-24 07:41:37.342913: step: 1600/533, loss: 0.025889927521348
2023-01-24 07:41:38.439889: step: 1604/533, loss: 0.02431720308959484
2023-01-24 07:41:39.538096: step: 1608/533, loss: 0.0035580049734562635
2023-01-24 07:41:40.626293: step: 1612/533, loss: 0.04366450756788254
2023-01-24 07:41:41.687148: step: 1616/533, loss: 0.006052530836313963
2023-01-24 07:41:42.791457: step: 1620/533, loss: 0.004718201234936714
2023-01-24 07:41:43.904164: step: 1624/533, loss: 0.005541189108043909
2023-01-24 07:41:45.008956: step: 1628/533, loss: 0.022559255361557007
2023-01-24 07:41:46.082546: step: 1632/533, loss: 0.0030557774007320404
2023-01-24 07:41:47.179338: step: 1636/533, loss: 0.0031941935885697603
2023-01-24 07:41:48.253733: step: 1640/533, loss: 0.032286107540130615
2023-01-24 07:41:49.340441: step: 1644/533, loss: 0.01288547646254301
2023-01-24 07:41:50.444759: step: 1648/533, loss: 0.0324203222990036
2023-01-24 07:41:51.559521: step: 1652/533, loss: 0.01815786026418209
2023-01-24 07:41:52.642164: step: 1656/533, loss: 0.0030658592004328966
2023-01-24 07:41:53.747472: step: 1660/533, loss: 0.011343155987560749
2023-01-24 07:41:54.830147: step: 1664/533, loss: 0.04429861158132553
2023-01-24 07:41:55.900335: step: 1668/533, loss: 0.040128305554389954
2023-01-24 07:41:57.001357: step: 1672/533, loss: 0.02402816340327263
2023-01-24 07:41:58.066995: step: 1676/533, loss: 0.008525453507900238
2023-01-24 07:41:59.165096: step: 1680/533, loss: 0.006685083266347647
2023-01-24 07:42:00.259223: step: 1684/533, loss: 0.007844367064535618
2023-01-24 07:42:01.353959: step: 1688/533, loss: 0.007832643575966358
2023-01-24 07:42:02.470275: step: 1692/533, loss: 0.004194962326437235
2023-01-24 07:42:03.550404: step: 1696/533, loss: 0.032262254506349564
2023-01-24 07:42:04.630111: step: 1700/533, loss: 0.003400145098567009
2023-01-24 07:42:05.715488: step: 1704/533, loss: 0.0009522699983790517
2023-01-24 07:42:06.787011: step: 1708/533, loss: 0.004328962415456772
2023-01-24 07:42:07.874215: step: 1712/533, loss: 0.006999302189797163
2023-01-24 07:42:08.960594: step: 1716/533, loss: 0.03462019935250282
2023-01-24 07:42:10.047753: step: 1720/533, loss: 0.007934191264212132
2023-01-24 07:42:11.129481: step: 1724/533, loss: 0.003215558361262083
2023-01-24 07:42:12.204016: step: 1728/533, loss: 0.009598280303180218
2023-01-24 07:42:13.303621: step: 1732/533, loss: 0.01051761582493782
2023-01-24 07:42:14.404413: step: 1736/533, loss: 0.008793285116553307
2023-01-24 07:42:15.494520: step: 1740/533, loss: 0.03755160793662071
2023-01-24 07:42:16.585420: step: 1744/533, loss: 0.0059037464670836926
2023-01-24 07:42:17.661355: step: 1748/533, loss: 0.01763204112648964
2023-01-24 07:42:18.739997: step: 1752/533, loss: 0.004869242198765278
2023-01-24 07:42:19.842042: step: 1756/533, loss: 0.0204867385327816
2023-01-24 07:42:20.979493: step: 1760/533, loss: 0.01927819289267063
2023-01-24 07:42:22.071673: step: 1764/533, loss: 0.008497917093336582
2023-01-24 07:42:23.157897: step: 1768/533, loss: 0.01967719942331314
2023-01-24 07:42:24.259722: step: 1772/533, loss: 0.01026396919041872
2023-01-24 07:42:25.351683: step: 1776/533, loss: 0.009747178293764591
2023-01-24 07:42:26.431412: step: 1780/533, loss: 0.008214064873754978
2023-01-24 07:42:27.542264: step: 1784/533, loss: 0.011278131045401096
2023-01-24 07:42:28.615370: step: 1788/533, loss: 0.002063516993075609
2023-01-24 07:42:29.690057: step: 1792/533, loss: 0.0049217925406992435
2023-01-24 07:42:30.761968: step: 1796/533, loss: 0.006757997442036867
2023-01-24 07:42:31.842196: step: 1800/533, loss: 0.005304411519318819
2023-01-24 07:42:32.915871: step: 1804/533, loss: 0.005524369888007641
2023-01-24 07:42:33.993323: step: 1808/533, loss: 0.0043591964058578014
2023-01-24 07:42:35.090267: step: 1812/533, loss: 0.005527167115360498
2023-01-24 07:42:36.221301: step: 1816/533, loss: 0.0012076223501935601
2023-01-24 07:42:37.316919: step: 1820/533, loss: 0.005785842891782522
2023-01-24 07:42:38.398447: step: 1824/533, loss: 0.004105211701244116
2023-01-24 07:42:39.487308: step: 1828/533, loss: 0.004222516436129808
2023-01-24 07:42:40.606619: step: 1832/533, loss: 0.004418256226927042
2023-01-24 07:42:41.689441: step: 1836/533, loss: 0.041285619139671326
2023-01-24 07:42:42.799085: step: 1840/533, loss: 0.016255760565400124
2023-01-24 07:42:43.886702: step: 1844/533, loss: 0.0197307076305151
2023-01-24 07:42:44.988765: step: 1848/533, loss: 0.00717965979129076
2023-01-24 07:42:46.111021: step: 1852/533, loss: 0.002646778244525194
2023-01-24 07:42:47.197253: step: 1856/533, loss: 0.004496172070503235
2023-01-24 07:42:48.302925: step: 1860/533, loss: 0.0
2023-01-24 07:42:49.375783: step: 1864/533, loss: 0.005795794073492289
2023-01-24 07:42:50.459617: step: 1868/533, loss: 0.006320510059595108
2023-01-24 07:42:51.545370: step: 1872/533, loss: 0.016980808228254318
2023-01-24 07:42:52.648417: step: 1876/533, loss: 0.005338101182132959
2023-01-24 07:42:53.721452: step: 1880/533, loss: 0.00944259762763977
2023-01-24 07:42:54.815144: step: 1884/533, loss: 0.03274943307042122
2023-01-24 07:42:55.910773: step: 1888/533, loss: 0.00997642520815134
2023-01-24 07:42:56.983533: step: 1892/533, loss: 0.011471475474536419
2023-01-24 07:42:58.066936: step: 1896/533, loss: 0.049139637500047684
2023-01-24 07:42:59.162395: step: 1900/533, loss: 0.021872928366065025
2023-01-24 07:43:00.258957: step: 1904/533, loss: 0.06302835792303085
2023-01-24 07:43:01.345605: step: 1908/533, loss: 0.006007536314427853
2023-01-24 07:43:02.434140: step: 1912/533, loss: 0.0024438921827822924
2023-01-24 07:43:03.554178: step: 1916/533, loss: 0.010214175097644329
2023-01-24 07:43:04.644355: step: 1920/533, loss: 0.0046677179634571075
2023-01-24 07:43:05.741417: step: 1924/533, loss: 0.05119301751255989
2023-01-24 07:43:06.816894: step: 1928/533, loss: 0.04630490392446518
2023-01-24 07:43:07.877085: step: 1932/533, loss: 0.008938384242355824
2023-01-24 07:43:08.948993: step: 1936/533, loss: 0.0023452634923160076
2023-01-24 07:43:10.034751: step: 1940/533, loss: 0.012061899527907372
2023-01-24 07:43:11.126848: step: 1944/533, loss: 0.001767926150932908
2023-01-24 07:43:12.213103: step: 1948/533, loss: 0.012360285967588425
2023-01-24 07:43:13.282653: step: 1952/533, loss: 0.0
2023-01-24 07:43:14.373807: step: 1956/533, loss: 0.0023477603681385517
2023-01-24 07:43:15.466109: step: 1960/533, loss: 0.006072998046875
2023-01-24 07:43:16.530892: step: 1964/533, loss: 0.003919502720236778
2023-01-24 07:43:17.624752: step: 1968/533, loss: 0.028778675943613052
2023-01-24 07:43:18.707278: step: 1972/533, loss: 0.034383125603199005
2023-01-24 07:43:19.781921: step: 1976/533, loss: 0.012687686830759048
2023-01-24 07:43:20.870432: step: 1980/533, loss: 0.004013726953417063
2023-01-24 07:43:21.964900: step: 1984/533, loss: 0.010451177135109901
2023-01-24 07:43:23.059126: step: 1988/533, loss: 0.028546396642923355
2023-01-24 07:43:24.163093: step: 1992/533, loss: 0.007834750227630138
2023-01-24 07:43:25.243606: step: 1996/533, loss: 0.004984743893146515
2023-01-24 07:43:26.321747: step: 2000/533, loss: 0.0025992675218731165
2023-01-24 07:43:27.402867: step: 2004/533, loss: 0.008354171179234982
2023-01-24 07:43:28.493679: step: 2008/533, loss: 0.004161530639976263
2023-01-24 07:43:29.606189: step: 2012/533, loss: 0.01729007251560688
2023-01-24 07:43:30.715847: step: 2016/533, loss: 0.00826201867312193
2023-01-24 07:43:31.822067: step: 2020/533, loss: 0.010691187344491482
2023-01-24 07:43:32.920442: step: 2024/533, loss: 0.012293037958443165
2023-01-24 07:43:34.006531: step: 2028/533, loss: 0.00669980188831687
2023-01-24 07:43:35.095475: step: 2032/533, loss: 0.008339215070009232
2023-01-24 07:43:36.158175: step: 2036/533, loss: 0.008101447485387325
2023-01-24 07:43:37.236787: step: 2040/533, loss: 0.011891918256878853
2023-01-24 07:43:38.332695: step: 2044/533, loss: 0.0028681030962616205
2023-01-24 07:43:39.442602: step: 2048/533, loss: 0.004154633264988661
2023-01-24 07:43:40.560884: step: 2052/533, loss: 0.011444714851677418
2023-01-24 07:43:41.660748: step: 2056/533, loss: 0.002444903366267681
2023-01-24 07:43:42.737480: step: 2060/533, loss: 0.0024637796450406313
2023-01-24 07:43:43.837269: step: 2064/533, loss: 0.021893378347158432
2023-01-24 07:43:44.938249: step: 2068/533, loss: 0.03138197213411331
2023-01-24 07:43:46.007888: step: 2072/533, loss: 0.007837554439902306
2023-01-24 07:43:47.108255: step: 2076/533, loss: 0.021593725308775902
2023-01-24 07:43:48.209395: step: 2080/533, loss: 0.009193711914122105
2023-01-24 07:43:49.296559: step: 2084/533, loss: 0.030949680134654045
2023-01-24 07:43:50.367882: step: 2088/533, loss: 0.012239341624081135
2023-01-24 07:43:51.456934: step: 2092/533, loss: 0.0032441166695207357
2023-01-24 07:43:52.551806: step: 2096/533, loss: 0.01511298306286335
2023-01-24 07:43:53.628691: step: 2100/533, loss: 0.009002127684652805
2023-01-24 07:43:54.713129: step: 2104/533, loss: 0.00991628598421812
2023-01-24 07:43:55.787417: step: 2108/533, loss: 0.010405694134533405
2023-01-24 07:43:56.856119: step: 2112/533, loss: 0.007527598179876804
2023-01-24 07:43:57.945263: step: 2116/533, loss: 0.009916670620441437
2023-01-24 07:43:59.029499: step: 2120/533, loss: 0.003793783951550722
2023-01-24 07:44:00.108431: step: 2124/533, loss: 0.009720972739160061
2023-01-24 07:44:01.190932: step: 2128/533, loss: 0.006419558543711901
2023-01-24 07:44:02.278310: step: 2132/533, loss: 0.011602982878684998
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3806268601190476, 'r': 0.3235689437065149, 'f1': 0.3497863247863248}, 'combined': 0.25773729194781825, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3936489524781401, 'r': 0.3573121260955425, 'f1': 0.3746014225195204}, 'combined': 0.2497342816796802, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661572385213968, 'r': 0.3216903253043771, 'f1': 0.34248646754627615}, 'combined': 0.2523584497709403, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38773270130457727, 'r': 0.30906770132836014, 'f1': 0.34395977461904176}, 'combined': 0.22930651641269445, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34506414267834795, 'r': 0.307742214532872, 'f1': 0.3253363030267272}, 'combined': 0.23972148644074637, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3818537244484197, 'r': 0.34697285538822753, 'f1': 0.36357860917255075}, 'combined': 0.2423857394483671, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, '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': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661572385213968, 'r': 0.3216903253043771, 'f1': 0.34248646754627615}, 'combined': 0.2523584497709403, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38773270130457727, 'r': 0.30906770132836014, 'f1': 0.34395977461904176}, 'combined': 0.22930651641269445, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, '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 07:46:28.980273: step: 4/533, loss: 0.019785407930612564
2023-01-24 07:46:30.062385: step: 8/533, loss: 0.008834699168801308
2023-01-24 07:46:31.153860: step: 12/533, loss: 0.04044332727789879
2023-01-24 07:46:32.236073: step: 16/533, loss: 0.00864275824278593
2023-01-24 07:46:33.316481: step: 20/533, loss: 0.0058207763358950615
2023-01-24 07:46:34.397810: step: 24/533, loss: 0.0055914935655891895
2023-01-24 07:46:35.494252: step: 28/533, loss: 0.014423523098230362
2023-01-24 07:46:36.565641: step: 32/533, loss: 0.011726121418178082
2023-01-24 07:46:37.650569: step: 36/533, loss: 0.03022661805152893
2023-01-24 07:46:38.747310: step: 40/533, loss: 0.010017065331339836
2023-01-24 07:46:39.823263: step: 44/533, loss: 0.004880513530224562
2023-01-24 07:46:40.914010: step: 48/533, loss: 0.005141949746757746
2023-01-24 07:46:41.970117: step: 52/533, loss: 0.011345162987709045
2023-01-24 07:46:43.107768: step: 56/533, loss: 0.002265559509396553
2023-01-24 07:46:44.196669: step: 60/533, loss: 0.009184245951473713
2023-01-24 07:46:45.273398: step: 64/533, loss: 0.005899631418287754
2023-01-24 07:46:46.333981: step: 68/533, loss: 0.002384330378845334
2023-01-24 07:46:47.443276: step: 72/533, loss: 0.00546554010361433
2023-01-24 07:46:48.529292: step: 76/533, loss: 0.016767462715506554
2023-01-24 07:46:49.617669: step: 80/533, loss: 0.001538037322461605
2023-01-24 07:46:50.686002: step: 84/533, loss: 0.001590040628798306
2023-01-24 07:46:51.777826: step: 88/533, loss: 0.012247830629348755
2023-01-24 07:46:52.867561: step: 92/533, loss: 0.005605048034340143
2023-01-24 07:46:53.963549: step: 96/533, loss: 0.004035628866404295
2023-01-24 07:46:55.040342: step: 100/533, loss: 0.008381348103284836
2023-01-24 07:46:56.135595: step: 104/533, loss: 0.04524129256606102
2023-01-24 07:46:57.233722: step: 108/533, loss: 0.015328234992921352
2023-01-24 07:46:58.328530: step: 112/533, loss: 0.01447850652039051
2023-01-24 07:46:59.409463: step: 116/533, loss: 0.00547801936045289
2023-01-24 07:47:00.485044: step: 120/533, loss: 0.0011207701172679663
2023-01-24 07:47:01.601474: step: 124/533, loss: 0.015340255573391914
2023-01-24 07:47:02.699997: step: 128/533, loss: 0.010511495172977448
2023-01-24 07:47:03.784893: step: 132/533, loss: 0.025884846225380898
2023-01-24 07:47:04.885819: step: 136/533, loss: 0.034192122519016266
2023-01-24 07:47:05.969520: step: 140/533, loss: 0.003836854360997677
2023-01-24 07:47:07.059353: step: 144/533, loss: 0.018498845398426056
2023-01-24 07:47:08.149987: step: 148/533, loss: 0.004545849282294512
2023-01-24 07:47:09.242718: step: 152/533, loss: 0.049304451793432236
2023-01-24 07:47:10.332190: step: 156/533, loss: 0.03242575749754906
2023-01-24 07:47:11.402915: step: 160/533, loss: 0.013990412466228008
2023-01-24 07:47:12.493426: step: 164/533, loss: 0.001236859941855073
2023-01-24 07:47:13.592557: step: 168/533, loss: 0.008966365829110146
2023-01-24 07:47:14.651160: step: 172/533, loss: 0.02538546547293663
2023-01-24 07:47:15.752715: step: 176/533, loss: 0.005340164992958307
2023-01-24 07:47:16.835735: step: 180/533, loss: 0.00801701657474041
2023-01-24 07:47:17.924827: step: 184/533, loss: 0.009291823022067547
2023-01-24 07:47:19.018805: step: 188/533, loss: 0.004135197959840298
2023-01-24 07:47:20.131444: step: 192/533, loss: 0.0028509534895420074
2023-01-24 07:47:21.211437: step: 196/533, loss: 0.005956828128546476
2023-01-24 07:47:22.303936: step: 200/533, loss: 0.008419383317232132
2023-01-24 07:47:23.385495: step: 204/533, loss: 0.010486624203622341
2023-01-24 07:47:24.485376: step: 208/533, loss: 0.0063066682778298855
2023-01-24 07:47:25.574098: step: 212/533, loss: 0.004328104201704264
2023-01-24 07:47:26.665133: step: 216/533, loss: 0.008425510488450527
2023-01-24 07:47:27.765155: step: 220/533, loss: 0.017431972548365593
2023-01-24 07:47:28.840217: step: 224/533, loss: 0.0028881507460027933
2023-01-24 07:47:29.943759: step: 228/533, loss: 0.03586730360984802
2023-01-24 07:47:31.007408: step: 232/533, loss: 0.0028233323246240616
2023-01-24 07:47:32.092943: step: 236/533, loss: 0.019967176020145416
2023-01-24 07:47:33.180726: step: 240/533, loss: 0.011158160865306854
2023-01-24 07:47:34.250358: step: 244/533, loss: 0.016418736428022385
2023-01-24 07:47:35.337406: step: 248/533, loss: 0.020819276571273804
2023-01-24 07:47:36.483478: step: 252/533, loss: 0.03559008985757828
2023-01-24 07:47:37.568780: step: 256/533, loss: 0.0032762340269982815
2023-01-24 07:47:38.695803: step: 260/533, loss: 0.02113506942987442
2023-01-24 07:47:39.794195: step: 264/533, loss: 0.010592309758067131
2023-01-24 07:47:40.885014: step: 268/533, loss: 0.004146403167396784
2023-01-24 07:47:41.971837: step: 272/533, loss: 0.031006405130028725
2023-01-24 07:47:43.072676: step: 276/533, loss: 0.0066801318898797035
2023-01-24 07:47:44.158561: step: 280/533, loss: 0.009795870631933212
2023-01-24 07:47:45.240664: step: 284/533, loss: 0.010162828490138054
2023-01-24 07:47:46.319014: step: 288/533, loss: 0.019395077601075172
2023-01-24 07:47:47.404703: step: 292/533, loss: 0.004740373697131872
2023-01-24 07:47:48.493912: step: 296/533, loss: 0.010147646069526672
2023-01-24 07:47:49.564410: step: 300/533, loss: 0.008269835263490677
2023-01-24 07:47:50.656547: step: 304/533, loss: 0.007108567748218775
2023-01-24 07:47:51.716062: step: 308/533, loss: 0.016474859789013863
2023-01-24 07:47:52.825715: step: 312/533, loss: 0.03139971196651459
2023-01-24 07:47:53.912455: step: 316/533, loss: 0.00891653448343277
2023-01-24 07:47:54.984503: step: 320/533, loss: 0.10364659130573273
2023-01-24 07:47:56.080769: step: 324/533, loss: 0.0020467143040150404
2023-01-24 07:47:57.163039: step: 328/533, loss: 0.0065290238708257675
2023-01-24 07:47:58.246334: step: 332/533, loss: 0.007630597334355116
2023-01-24 07:47:59.328870: step: 336/533, loss: 0.0009685212280601263
2023-01-24 07:48:00.406839: step: 340/533, loss: 0.017589043825864792
2023-01-24 07:48:01.472158: step: 344/533, loss: 0.02336869016289711
2023-01-24 07:48:02.563538: step: 348/533, loss: 0.0066375937312841415
2023-01-24 07:48:03.658255: step: 352/533, loss: 0.01869174651801586
2023-01-24 07:48:04.738851: step: 356/533, loss: 0.018765443935990334
2023-01-24 07:48:05.817148: step: 360/533, loss: 0.0075482516549527645
2023-01-24 07:48:06.942507: step: 364/533, loss: 0.005454219412058592
2023-01-24 07:48:08.035226: step: 368/533, loss: 0.0060280803591012955
2023-01-24 07:48:09.127467: step: 372/533, loss: 0.0013944548554718494
2023-01-24 07:48:10.236938: step: 376/533, loss: 0.0037936121225357056
2023-01-24 07:48:11.325152: step: 380/533, loss: 0.009686058387160301
2023-01-24 07:48:12.391925: step: 384/533, loss: 0.0021069576032459736
2023-01-24 07:48:13.511591: step: 388/533, loss: 0.0062700374983251095
2023-01-24 07:48:14.601237: step: 392/533, loss: 0.026763249188661575
2023-01-24 07:48:15.689163: step: 396/533, loss: 0.00148481922224164
2023-01-24 07:48:16.792210: step: 400/533, loss: 0.020205896347761154
2023-01-24 07:48:17.865841: step: 404/533, loss: 0.014058677479624748
2023-01-24 07:48:18.936865: step: 408/533, loss: 0.0027305094990879297
2023-01-24 07:48:20.017533: step: 412/533, loss: 0.03378647193312645
2023-01-24 07:48:21.099567: step: 416/533, loss: 0.0115120904520154
2023-01-24 07:48:22.213785: step: 420/533, loss: 0.002769434591755271
2023-01-24 07:48:23.324233: step: 424/533, loss: 0.0025395879056304693
2023-01-24 07:48:24.406343: step: 428/533, loss: 0.0020111119374632835
2023-01-24 07:48:25.508727: step: 432/533, loss: 0.007499020546674728
2023-01-24 07:48:26.602097: step: 436/533, loss: 0.017854854464530945
2023-01-24 07:48:27.689894: step: 440/533, loss: 0.0022442967165261507
2023-01-24 07:48:28.796615: step: 444/533, loss: 0.005493619944900274
2023-01-24 07:48:29.887145: step: 448/533, loss: 0.000748045218642801
2023-01-24 07:48:30.962804: step: 452/533, loss: 0.010802623815834522
2023-01-24 07:48:32.063846: step: 456/533, loss: 0.011210617609322071
2023-01-24 07:48:33.147293: step: 460/533, loss: 0.005676065105944872
2023-01-24 07:48:34.224967: step: 464/533, loss: 0.008160173892974854
2023-01-24 07:48:35.328429: step: 468/533, loss: 0.017338406294584274
2023-01-24 07:48:36.404005: step: 472/533, loss: 0.03503654524683952
2023-01-24 07:48:37.501399: step: 476/533, loss: 0.002766652964055538
2023-01-24 07:48:38.582892: step: 480/533, loss: 0.024751000106334686
2023-01-24 07:48:39.699869: step: 484/533, loss: 0.007595252711325884
2023-01-24 07:48:40.794256: step: 488/533, loss: 0.007115254644304514
2023-01-24 07:48:41.876618: step: 492/533, loss: 0.008035124279558659
2023-01-24 07:48:42.959107: step: 496/533, loss: 0.000606152752880007
2023-01-24 07:48:44.047228: step: 500/533, loss: 0.011197914369404316
2023-01-24 07:48:45.129520: step: 504/533, loss: 0.001796756754629314
2023-01-24 07:48:46.230896: step: 508/533, loss: 0.06403633952140808
2023-01-24 07:48:47.325131: step: 512/533, loss: 0.008075940422713757
2023-01-24 07:48:48.418641: step: 516/533, loss: 0.004524885211139917
2023-01-24 07:48:49.503943: step: 520/533, loss: 0.016752688214182854
2023-01-24 07:48:50.592592: step: 524/533, loss: 0.0495634526014328
2023-01-24 07:48:51.678191: step: 528/533, loss: 0.012546583078801632
2023-01-24 07:48:52.761153: step: 532/533, loss: 0.008381716907024384
2023-01-24 07:48:53.864318: step: 536/533, loss: 0.010563232935965061
2023-01-24 07:48:54.967919: step: 540/533, loss: 0.06316495686769485
2023-01-24 07:48:56.062812: step: 544/533, loss: 0.005608910229057074
2023-01-24 07:48:57.131748: step: 548/533, loss: 0.004749912768602371
2023-01-24 07:48:58.218521: step: 552/533, loss: 0.002985211554914713
2023-01-24 07:48:59.308986: step: 556/533, loss: 0.016863428056240082
2023-01-24 07:49:00.403915: step: 560/533, loss: 0.002502736635506153
2023-01-24 07:49:01.500930: step: 564/533, loss: 0.0087685352191329
2023-01-24 07:49:02.602769: step: 568/533, loss: 0.05230855569243431
2023-01-24 07:49:03.681519: step: 572/533, loss: 0.0369056798517704
2023-01-24 07:49:04.759470: step: 576/533, loss: 0.0019238191889598966
2023-01-24 07:49:05.879017: step: 580/533, loss: 0.008822652511298656
2023-01-24 07:49:06.989305: step: 584/533, loss: 0.003855739254504442
2023-01-24 07:49:08.054410: step: 588/533, loss: 0.006072859279811382
2023-01-24 07:49:09.138377: step: 592/533, loss: 0.014833386987447739
2023-01-24 07:49:10.225746: step: 596/533, loss: 0.02735028974711895
2023-01-24 07:49:11.320147: step: 600/533, loss: 0.02051885984838009
2023-01-24 07:49:12.406598: step: 604/533, loss: 0.026613913476467133
2023-01-24 07:49:13.493003: step: 608/533, loss: 0.018812501803040504
2023-01-24 07:49:14.563315: step: 612/533, loss: 0.005550116300582886
2023-01-24 07:49:15.656070: step: 616/533, loss: 0.008146124891936779
2023-01-24 07:49:16.761340: step: 620/533, loss: 0.009698961861431599
2023-01-24 07:49:17.851899: step: 624/533, loss: 0.007738974876701832
2023-01-24 07:49:18.943142: step: 628/533, loss: 0.006716960109770298
2023-01-24 07:49:20.023344: step: 632/533, loss: 0.005915610119700432
2023-01-24 07:49:21.085596: step: 636/533, loss: 0.019196484237909317
2023-01-24 07:49:22.168494: step: 640/533, loss: 0.013522887602448463
2023-01-24 07:49:23.261573: step: 644/533, loss: 0.009341304190456867
2023-01-24 07:49:24.344565: step: 648/533, loss: 0.0030906270258128643
2023-01-24 07:49:25.419777: step: 652/533, loss: 0.007012924645096064
2023-01-24 07:49:26.505589: step: 656/533, loss: 0.004091677721589804
2023-01-24 07:49:27.619647: step: 660/533, loss: 0.006708969362080097
2023-01-24 07:49:28.707433: step: 664/533, loss: 0.006482037249952555
2023-01-24 07:49:29.803062: step: 668/533, loss: 0.06035410240292549
2023-01-24 07:49:30.882912: step: 672/533, loss: 0.004388671834021807
2023-01-24 07:49:31.965578: step: 676/533, loss: 0.0014628873905166984
2023-01-24 07:49:33.054521: step: 680/533, loss: 0.002062723506242037
2023-01-24 07:49:34.138913: step: 684/533, loss: 0.016022607684135437
2023-01-24 07:49:35.218176: step: 688/533, loss: 0.005059634801000357
2023-01-24 07:49:36.311379: step: 692/533, loss: 0.010387328453361988
2023-01-24 07:49:37.400409: step: 696/533, loss: 0.04407833144068718
2023-01-24 07:49:38.479772: step: 700/533, loss: 0.056503284722566605
2023-01-24 07:49:39.606624: step: 704/533, loss: 0.008421840146183968
2023-01-24 07:49:40.704556: step: 708/533, loss: 0.006201980169862509
2023-01-24 07:49:41.799245: step: 712/533, loss: 0.01876814290881157
2023-01-24 07:49:42.902039: step: 716/533, loss: 0.006805907469242811
2023-01-24 07:49:43.981833: step: 720/533, loss: 0.016562238335609436
2023-01-24 07:49:45.068877: step: 724/533, loss: 0.013674861751496792
2023-01-24 07:49:46.148763: step: 728/533, loss: 0.0085408054292202
2023-01-24 07:49:47.206334: step: 732/533, loss: 0.001919376547448337
2023-01-24 07:49:48.297781: step: 736/533, loss: 0.0031047966331243515
2023-01-24 07:49:49.386111: step: 740/533, loss: 0.09166798740625381
2023-01-24 07:49:50.476059: step: 744/533, loss: 0.010998266749083996
2023-01-24 07:49:51.617899: step: 748/533, loss: 0.004682193510234356
2023-01-24 07:49:52.697995: step: 752/533, loss: 0.012383788824081421
2023-01-24 07:49:53.785443: step: 756/533, loss: 0.013988488353788853
2023-01-24 07:49:54.869698: step: 760/533, loss: 0.006095197983086109
2023-01-24 07:49:55.946571: step: 764/533, loss: 0.0411936417222023
2023-01-24 07:49:57.038396: step: 768/533, loss: 0.0034410892985761166
2023-01-24 07:49:58.117073: step: 772/533, loss: 0.003722698660567403
2023-01-24 07:49:59.209620: step: 776/533, loss: 0.008891209959983826
2023-01-24 07:50:00.317955: step: 780/533, loss: 0.005485209636390209
2023-01-24 07:50:01.402100: step: 784/533, loss: 0.005428653210401535
2023-01-24 07:50:02.502261: step: 788/533, loss: 0.014379622414708138
2023-01-24 07:50:03.579825: step: 792/533, loss: 0.013255629688501358
2023-01-24 07:50:04.649582: step: 796/533, loss: 0.007215674966573715
2023-01-24 07:50:05.718456: step: 800/533, loss: 0.009258829988539219
2023-01-24 07:50:06.807489: step: 804/533, loss: 0.005187138449400663
2023-01-24 07:50:07.867841: step: 808/533, loss: 0.008381625637412071
2023-01-24 07:50:08.965315: step: 812/533, loss: 0.00783654022961855
2023-01-24 07:50:10.059877: step: 816/533, loss: 0.013116221874952316
2023-01-24 07:50:11.146738: step: 820/533, loss: 0.0029683150351047516
2023-01-24 07:50:12.236943: step: 824/533, loss: 0.0033360840752720833
2023-01-24 07:50:13.313628: step: 828/533, loss: 0.009928572922945023
2023-01-24 07:50:14.394776: step: 832/533, loss: 0.011970486491918564
2023-01-24 07:50:15.443230: step: 836/533, loss: 0.0038144271820783615
2023-01-24 07:50:16.533488: step: 840/533, loss: 0.006491237785667181
2023-01-24 07:50:17.609171: step: 844/533, loss: 0.0072013274766504765
2023-01-24 07:50:18.712027: step: 848/533, loss: 0.005187408998608589
2023-01-24 07:50:19.801730: step: 852/533, loss: 0.01962147280573845
2023-01-24 07:50:20.867248: step: 856/533, loss: 0.0058624339289963245
2023-01-24 07:50:21.944086: step: 860/533, loss: 0.01800714060664177
2023-01-24 07:50:23.015034: step: 864/533, loss: 0.013569089584052563
2023-01-24 07:50:24.107671: step: 868/533, loss: 0.0454418919980526
2023-01-24 07:50:25.191704: step: 872/533, loss: 0.03172663226723671
2023-01-24 07:50:26.292882: step: 876/533, loss: 0.008131345734000206
2023-01-24 07:50:27.398576: step: 880/533, loss: 0.02247590757906437
2023-01-24 07:50:28.500525: step: 884/533, loss: 0.008749552071094513
2023-01-24 07:50:29.606215: step: 888/533, loss: 0.03661145642399788
2023-01-24 07:50:30.700537: step: 892/533, loss: 0.007461726665496826
2023-01-24 07:50:31.786078: step: 896/533, loss: 0.009096470661461353
2023-01-24 07:50:32.874450: step: 900/533, loss: 0.010061981156468391
2023-01-24 07:50:33.986244: step: 904/533, loss: 0.029065396636724472
2023-01-24 07:50:35.079573: step: 908/533, loss: 0.006230898201465607
2023-01-24 07:50:36.154063: step: 912/533, loss: 0.03358886390924454
2023-01-24 07:50:37.232158: step: 916/533, loss: 0.011223207227885723
2023-01-24 07:50:38.315812: step: 920/533, loss: 0.020267879590392113
2023-01-24 07:50:39.402927: step: 924/533, loss: 0.00562011543661356
2023-01-24 07:50:40.487318: step: 928/533, loss: 0.01638759858906269
2023-01-24 07:50:41.555040: step: 932/533, loss: 0.02466198429465294
2023-01-24 07:50:42.654922: step: 936/533, loss: 0.007056646980345249
2023-01-24 07:50:43.750165: step: 940/533, loss: 0.0037607301492244005
2023-01-24 07:50:44.835964: step: 944/533, loss: 0.01203781645745039
2023-01-24 07:50:45.909697: step: 948/533, loss: 0.000839382701087743
2023-01-24 07:50:46.987408: step: 952/533, loss: 0.008387229405343533
2023-01-24 07:50:48.085163: step: 956/533, loss: 0.004501097835600376
2023-01-24 07:50:49.151636: step: 960/533, loss: 0.0007914869929663837
2023-01-24 07:50:50.250147: step: 964/533, loss: 0.009441477246582508
2023-01-24 07:50:51.312911: step: 968/533, loss: 0.006029711104929447
2023-01-24 07:50:52.385818: step: 972/533, loss: 0.018475864082574844
2023-01-24 07:50:53.464669: step: 976/533, loss: 0.08189209550619125
2023-01-24 07:50:54.574943: step: 980/533, loss: 0.00442163459956646
2023-01-24 07:50:55.650966: step: 984/533, loss: 0.03158276155591011
2023-01-24 07:50:56.745218: step: 988/533, loss: 0.006678879726678133
2023-01-24 07:50:57.814871: step: 992/533, loss: 0.009193651378154755
2023-01-24 07:50:58.896811: step: 996/533, loss: 0.006920246873050928
2023-01-24 07:50:59.979159: step: 1000/533, loss: 0.007714168634265661
2023-01-24 07:51:01.080029: step: 1004/533, loss: 0.007885174825787544
2023-01-24 07:51:02.175652: step: 1008/533, loss: 0.013390271924436092
2023-01-24 07:51:03.287041: step: 1012/533, loss: 0.006427218206226826
2023-01-24 07:51:04.365187: step: 1016/533, loss: 0.009281372651457787
2023-01-24 07:51:05.454303: step: 1020/533, loss: 0.033141978085041046
2023-01-24 07:51:06.523036: step: 1024/533, loss: 0.008014637045562267
2023-01-24 07:51:07.609571: step: 1028/533, loss: 0.0012689844006672502
2023-01-24 07:51:08.724005: step: 1032/533, loss: 0.021523283794522285
2023-01-24 07:51:09.814021: step: 1036/533, loss: 0.019975125789642334
2023-01-24 07:51:10.894717: step: 1040/533, loss: 0.048224445432424545
2023-01-24 07:51:11.971167: step: 1044/533, loss: 0.008634217083454132
2023-01-24 07:51:13.054637: step: 1048/533, loss: 0.013484351336956024
2023-01-24 07:51:14.145829: step: 1052/533, loss: 0.006713654845952988
2023-01-24 07:51:15.255581: step: 1056/533, loss: 0.008519914932549
2023-01-24 07:51:16.349235: step: 1060/533, loss: 0.001409336575306952
2023-01-24 07:51:17.440270: step: 1064/533, loss: 0.0023896540515124798
2023-01-24 07:51:18.552297: step: 1068/533, loss: 0.002898162230849266
2023-01-24 07:51:19.656608: step: 1072/533, loss: 0.028564363718032837
2023-01-24 07:51:20.748793: step: 1076/533, loss: 0.008736660704016685
2023-01-24 07:51:21.845769: step: 1080/533, loss: 0.06765034794807434
2023-01-24 07:51:22.931712: step: 1084/533, loss: 0.005534728057682514
2023-01-24 07:51:24.025946: step: 1088/533, loss: 0.007092440966516733
2023-01-24 07:51:25.122177: step: 1092/533, loss: 0.010129721835255623
2023-01-24 07:51:26.215378: step: 1096/533, loss: 0.006367466412484646
2023-01-24 07:51:27.320941: step: 1100/533, loss: 0.0030758508946746588
2023-01-24 07:51:28.410788: step: 1104/533, loss: 0.005794058088213205
2023-01-24 07:51:29.498034: step: 1108/533, loss: 0.010895210318267345
2023-01-24 07:51:30.579974: step: 1112/533, loss: 0.012222161516547203
2023-01-24 07:51:31.674681: step: 1116/533, loss: 0.0031701589468866587
2023-01-24 07:51:32.750977: step: 1120/533, loss: 0.01825866661965847
2023-01-24 07:51:33.831458: step: 1124/533, loss: 0.005355457309633493
2023-01-24 07:51:34.949491: step: 1128/533, loss: 0.021032366901636124
2023-01-24 07:51:36.049516: step: 1132/533, loss: 0.00813103374093771
2023-01-24 07:51:37.137394: step: 1136/533, loss: 0.005408735945820808
2023-01-24 07:51:38.228758: step: 1140/533, loss: 0.009486299939453602
2023-01-24 07:51:39.348248: step: 1144/533, loss: 0.005787566304206848
2023-01-24 07:51:40.442972: step: 1148/533, loss: 0.014773734845221043
2023-01-24 07:51:41.531159: step: 1152/533, loss: 0.01191593986004591
2023-01-24 07:51:42.630603: step: 1156/533, loss: 0.0128027880564332
2023-01-24 07:51:43.732092: step: 1160/533, loss: 0.00017970184853766114
2023-01-24 07:51:44.832504: step: 1164/533, loss: 0.004873278085142374
2023-01-24 07:51:45.911139: step: 1168/533, loss: 0.00539516843855381
2023-01-24 07:51:47.031999: step: 1172/533, loss: 0.006447415333241224
2023-01-24 07:51:48.123073: step: 1176/533, loss: 0.0013305455213412642
2023-01-24 07:51:49.206458: step: 1180/533, loss: 0.007610894739627838
2023-01-24 07:51:50.303876: step: 1184/533, loss: 0.00946690421551466
2023-01-24 07:51:51.386925: step: 1188/533, loss: 0.012101276777684689
2023-01-24 07:51:52.490983: step: 1192/533, loss: 0.07935052365064621
2023-01-24 07:51:53.586780: step: 1196/533, loss: 0.004620674531906843
2023-01-24 07:51:54.691877: step: 1200/533, loss: 0.008547567762434483
2023-01-24 07:51:55.790700: step: 1204/533, loss: 0.018869604915380478
2023-01-24 07:51:56.880396: step: 1208/533, loss: 0.010836940258741379
2023-01-24 07:51:57.980431: step: 1212/533, loss: 0.0347907617688179
2023-01-24 07:51:59.070250: step: 1216/533, loss: 0.0069478959776461124
2023-01-24 07:52:00.167524: step: 1220/533, loss: 0.00440057460218668
2023-01-24 07:52:01.278093: step: 1224/533, loss: 0.02581997960805893
2023-01-24 07:52:02.376703: step: 1228/533, loss: 0.003857546718791127
2023-01-24 07:52:03.476522: step: 1232/533, loss: 0.026437589898705482
2023-01-24 07:52:04.562876: step: 1236/533, loss: 0.004380182828754187
2023-01-24 07:52:05.657361: step: 1240/533, loss: 0.0027548708021640778
2023-01-24 07:52:06.767184: step: 1244/533, loss: 0.03899503871798515
2023-01-24 07:52:07.849736: step: 1248/533, loss: 0.0005177796119824052
2023-01-24 07:52:08.946376: step: 1252/533, loss: 0.07119035720825195
2023-01-24 07:52:10.063392: step: 1256/533, loss: 0.024905286729335785
2023-01-24 07:52:11.167816: step: 1260/533, loss: 0.012999058701097965
2023-01-24 07:52:12.297880: step: 1264/533, loss: 0.019257623702287674
2023-01-24 07:52:13.375603: step: 1268/533, loss: 0.011116347275674343
2023-01-24 07:52:14.487619: step: 1272/533, loss: 0.015144992619752884
2023-01-24 07:52:15.562890: step: 1276/533, loss: 0.003571860259398818
2023-01-24 07:52:16.667879: step: 1280/533, loss: 0.013191262260079384
2023-01-24 07:52:17.759268: step: 1284/533, loss: 0.030768388882279396
2023-01-24 07:52:18.847378: step: 1288/533, loss: 0.01102757453918457
2023-01-24 07:52:19.957573: step: 1292/533, loss: 0.008260789327323437
2023-01-24 07:52:21.063606: step: 1296/533, loss: 0.005273961927741766
2023-01-24 07:52:22.167185: step: 1300/533, loss: 0.007855161093175411
2023-01-24 07:52:23.273897: step: 1304/533, loss: 0.007613459601998329
2023-01-24 07:52:24.366798: step: 1308/533, loss: 0.011505414731800556
2023-01-24 07:52:25.481054: step: 1312/533, loss: 0.008307380601763725
2023-01-24 07:52:26.573114: step: 1316/533, loss: 0.01313697174191475
2023-01-24 07:52:27.673280: step: 1320/533, loss: 0.008631223812699318
2023-01-24 07:52:28.758743: step: 1324/533, loss: 0.003626447170972824
2023-01-24 07:52:29.859519: step: 1328/533, loss: 0.010879826731979847
2023-01-24 07:52:30.961135: step: 1332/533, loss: 0.004684393759816885
2023-01-24 07:52:32.088188: step: 1336/533, loss: 0.05761411413550377
2023-01-24 07:52:33.169114: step: 1340/533, loss: 0.009074469096958637
2023-01-24 07:52:34.254759: step: 1344/533, loss: 0.03926164656877518
2023-01-24 07:52:35.349056: step: 1348/533, loss: 0.06944506615400314
2023-01-24 07:52:36.457462: step: 1352/533, loss: 0.013494514860212803
2023-01-24 07:52:37.536633: step: 1356/533, loss: 0.003272457979619503
2023-01-24 07:52:38.616411: step: 1360/533, loss: 0.012874637730419636
2023-01-24 07:52:39.747673: step: 1364/533, loss: 0.05570206418633461
2023-01-24 07:52:40.834452: step: 1368/533, loss: 0.006081735249608755
2023-01-24 07:52:41.941352: step: 1372/533, loss: 0.002284733112901449
2023-01-24 07:52:43.026911: step: 1376/533, loss: 0.017964256927371025
2023-01-24 07:52:44.115406: step: 1380/533, loss: 0.0075315386056900024
2023-01-24 07:52:45.207094: step: 1384/533, loss: 0.008379555307328701
2023-01-24 07:52:46.303191: step: 1388/533, loss: 0.006798877380788326
2023-01-24 07:52:47.386241: step: 1392/533, loss: 0.023104483261704445
2023-01-24 07:52:48.492178: step: 1396/533, loss: 0.009130269289016724
2023-01-24 07:52:49.615655: step: 1400/533, loss: 0.00030300935031846166
2023-01-24 07:52:50.719105: step: 1404/533, loss: 0.0032140156254172325
2023-01-24 07:52:51.827488: step: 1408/533, loss: 0.002721281722187996
2023-01-24 07:52:52.934740: step: 1412/533, loss: 0.0859653651714325
2023-01-24 07:52:54.038694: step: 1416/533, loss: 0.0036304162349551916
2023-01-24 07:52:55.132364: step: 1420/533, loss: 0.005992305930703878
2023-01-24 07:52:56.216672: step: 1424/533, loss: 0.011765288189053535
2023-01-24 07:52:57.287254: step: 1428/533, loss: 0.004695615731179714
2023-01-24 07:52:58.402414: step: 1432/533, loss: 0.003510112641379237
2023-01-24 07:52:59.550674: step: 1436/533, loss: 0.02808522805571556
2023-01-24 07:53:00.645028: step: 1440/533, loss: 0.011902419850230217
2023-01-24 07:53:01.742498: step: 1444/533, loss: 0.011442963033914566
2023-01-24 07:53:02.847478: step: 1448/533, loss: 0.009232981130480766
2023-01-24 07:53:03.930772: step: 1452/533, loss: 0.00060331413988024
2023-01-24 07:53:05.028316: step: 1456/533, loss: 0.042728010565042496
2023-01-24 07:53:06.113509: step: 1460/533, loss: 0.012638411484658718
2023-01-24 07:53:07.188009: step: 1464/533, loss: 0.0004128985165152699
2023-01-24 07:53:08.290838: step: 1468/533, loss: 0.007322824560105801
2023-01-24 07:53:09.373454: step: 1472/533, loss: 0.007567626889795065
2023-01-24 07:53:10.468298: step: 1476/533, loss: 0.011948585510253906
2023-01-24 07:53:11.565419: step: 1480/533, loss: 0.015517042949795723
2023-01-24 07:53:12.648634: step: 1484/533, loss: 0.01891755871474743
2023-01-24 07:53:13.734222: step: 1488/533, loss: 0.028652187436819077
2023-01-24 07:53:14.837324: step: 1492/533, loss: 0.061982639133930206
2023-01-24 07:53:15.920013: step: 1496/533, loss: 0.008570175617933273
2023-01-24 07:53:17.028619: step: 1500/533, loss: 0.0078400494530797
2023-01-24 07:53:18.108640: step: 1504/533, loss: 0.002098329132422805
2023-01-24 07:53:19.210258: step: 1508/533, loss: 0.010785259306430817
2023-01-24 07:53:20.332886: step: 1512/533, loss: 0.00035577299422584474
2023-01-24 07:53:21.443987: step: 1516/533, loss: 0.006795202847570181
2023-01-24 07:53:22.543952: step: 1520/533, loss: 0.008559311740100384
2023-01-24 07:53:23.648343: step: 1524/533, loss: 0.01959984563291073
2023-01-24 07:53:24.774051: step: 1528/533, loss: 0.009077025577425957
2023-01-24 07:53:25.868332: step: 1532/533, loss: 0.007547692395746708
2023-01-24 07:53:26.969859: step: 1536/533, loss: 0.0059471637941896915
2023-01-24 07:53:28.063937: step: 1540/533, loss: 0.006906386464834213
2023-01-24 07:53:29.150457: step: 1544/533, loss: 0.006738240364938974
2023-01-24 07:53:30.231685: step: 1548/533, loss: 0.00710115022957325
2023-01-24 07:53:31.357800: step: 1552/533, loss: 0.02398555912077427
2023-01-24 07:53:32.461073: step: 1556/533, loss: 0.009739228524267673
2023-01-24 07:53:33.575827: step: 1560/533, loss: 0.0016047582030296326
2023-01-24 07:53:34.654082: step: 1564/533, loss: 0.000738625240046531
2023-01-24 07:53:35.738264: step: 1568/533, loss: 0.01675775647163391
2023-01-24 07:53:36.837847: step: 1572/533, loss: 0.017339885234832764
2023-01-24 07:53:37.918306: step: 1576/533, loss: 0.0013341400772333145
2023-01-24 07:53:39.004922: step: 1580/533, loss: 0.006760268472135067
2023-01-24 07:53:40.104437: step: 1584/533, loss: 0.02497795782983303
2023-01-24 07:53:41.200365: step: 1588/533, loss: 0.04317706078290939
2023-01-24 07:53:42.297285: step: 1592/533, loss: 0.02055390551686287
2023-01-24 07:53:43.389051: step: 1596/533, loss: 0.017693722620606422
2023-01-24 07:53:44.482268: step: 1600/533, loss: 0.013130513951182365
2023-01-24 07:53:45.587369: step: 1604/533, loss: 0.003152452874928713
2023-01-24 07:53:46.671949: step: 1608/533, loss: 0.0038737126160413027
2023-01-24 07:53:47.773921: step: 1612/533, loss: 0.005057984963059425
2023-01-24 07:53:48.858452: step: 1616/533, loss: 0.0057104104198515415
2023-01-24 07:53:49.974017: step: 1620/533, loss: 0.008295322768390179
2023-01-24 07:53:51.074920: step: 1624/533, loss: 0.008992264978587627
2023-01-24 07:53:52.170271: step: 1628/533, loss: 0.10579044371843338
2023-01-24 07:53:53.299819: step: 1632/533, loss: 0.0034959083423018456
2023-01-24 07:53:54.384287: step: 1636/533, loss: 0.03204210475087166
2023-01-24 07:53:55.474731: step: 1640/533, loss: 0.054161570966243744
2023-01-24 07:53:56.569001: step: 1644/533, loss: 0.0547289177775383
2023-01-24 07:53:57.658392: step: 1648/533, loss: 0.0640382394194603
2023-01-24 07:53:58.741432: step: 1652/533, loss: 0.0007965961121954024
2023-01-24 07:53:59.840847: step: 1656/533, loss: 0.0061475052498281
2023-01-24 07:54:00.901230: step: 1660/533, loss: 0.010066782124340534
2023-01-24 07:54:01.981290: step: 1664/533, loss: 0.04102420061826706
2023-01-24 07:54:03.058790: step: 1668/533, loss: 0.014459259808063507
2023-01-24 07:54:04.157598: step: 1672/533, loss: 0.01188446395099163
2023-01-24 07:54:05.234892: step: 1676/533, loss: 0.035680338740348816
2023-01-24 07:54:06.312330: step: 1680/533, loss: 0.0030750648584216833
2023-01-24 07:54:07.390718: step: 1684/533, loss: 0.011144126765429974
2023-01-24 07:54:08.507238: step: 1688/533, loss: 0.007644984871149063
2023-01-24 07:54:09.613604: step: 1692/533, loss: 0.006090614944696426
2023-01-24 07:54:10.697349: step: 1696/533, loss: 0.010756784118711948
2023-01-24 07:54:11.804600: step: 1700/533, loss: 0.017387885600328445
2023-01-24 07:54:12.902031: step: 1704/533, loss: 0.00014694785932078958
2023-01-24 07:54:13.970373: step: 1708/533, loss: 0.0033513489179313183
2023-01-24 07:54:15.060371: step: 1712/533, loss: 0.005525062792003155
2023-01-24 07:54:16.165772: step: 1716/533, loss: 0.006290477700531483
2023-01-24 07:54:17.258289: step: 1720/533, loss: 0.010108170099556446
2023-01-24 07:54:18.358729: step: 1724/533, loss: 0.008983224630355835
2023-01-24 07:54:19.449398: step: 1728/533, loss: 0.010739653371274471
2023-01-24 07:54:20.542401: step: 1732/533, loss: 0.0120456013828516
2023-01-24 07:54:21.631748: step: 1736/533, loss: 0.012414826080203056
2023-01-24 07:54:22.733456: step: 1740/533, loss: 0.025223063305020332
2023-01-24 07:54:23.831727: step: 1744/533, loss: 0.004391835071146488
2023-01-24 07:54:24.921445: step: 1748/533, loss: 0.010823922231793404
2023-01-24 07:54:26.023021: step: 1752/533, loss: 0.005766243673861027
2023-01-24 07:54:27.109043: step: 1756/533, loss: 0.015999481081962585
2023-01-24 07:54:28.183521: step: 1760/533, loss: 0.008858299814164639
2023-01-24 07:54:29.309942: step: 1764/533, loss: 0.004800991155207157
2023-01-24 07:54:30.382260: step: 1768/533, loss: 0.002692065667361021
2023-01-24 07:54:31.483930: step: 1772/533, loss: 0.007171342149376869
2023-01-24 07:54:32.577525: step: 1776/533, loss: 0.03131730481982231
2023-01-24 07:54:33.675920: step: 1780/533, loss: 0.02598007209599018
2023-01-24 07:54:34.755410: step: 1784/533, loss: 0.005670367274433374
2023-01-24 07:54:35.844994: step: 1788/533, loss: 0.004856581799685955
2023-01-24 07:54:36.947175: step: 1792/533, loss: 0.009854585863649845
2023-01-24 07:54:38.041845: step: 1796/533, loss: 0.0287217665463686
2023-01-24 07:54:39.137706: step: 1800/533, loss: 0.00953227374702692
2023-01-24 07:54:40.220706: step: 1804/533, loss: 0.05193336680531502
2023-01-24 07:54:41.319863: step: 1808/533, loss: 0.019408417865633965
2023-01-24 07:54:42.395417: step: 1812/533, loss: 0.01978333294391632
2023-01-24 07:54:43.482098: step: 1816/533, loss: 0.03363355994224548
2023-01-24 07:54:44.586305: step: 1820/533, loss: 0.05285438522696495
2023-01-24 07:54:45.690922: step: 1824/533, loss: 0.0009202565997838974
2023-01-24 07:54:46.793238: step: 1828/533, loss: 0.09499117732048035
2023-01-24 07:54:47.864845: step: 1832/533, loss: 0.008023594506084919
2023-01-24 07:54:48.962715: step: 1836/533, loss: 0.011658127419650555
2023-01-24 07:54:50.048375: step: 1840/533, loss: 0.02408243529498577
2023-01-24 07:54:51.170175: step: 1844/533, loss: 0.013036767020821571
2023-01-24 07:54:52.241963: step: 1848/533, loss: 0.0038451876025646925
2023-01-24 07:54:53.317524: step: 1852/533, loss: 0.012303756549954414
2023-01-24 07:54:54.400222: step: 1856/533, loss: 0.0007193373749032617
2023-01-24 07:54:55.500922: step: 1860/533, loss: 0.02884536050260067
2023-01-24 07:54:56.574849: step: 1864/533, loss: 0.005115872714668512
2023-01-24 07:54:57.645465: step: 1868/533, loss: 0.006894412916153669
2023-01-24 07:54:58.743939: step: 1872/533, loss: 0.025137515738606453
2023-01-24 07:54:59.823103: step: 1876/533, loss: 0.007791108451783657
2023-01-24 07:55:00.904986: step: 1880/533, loss: 0.007307817693799734
2023-01-24 07:55:01.986237: step: 1884/533, loss: 0.004271757788956165
2023-01-24 07:55:03.067255: step: 1888/533, loss: 0.03296555206179619
2023-01-24 07:55:04.188487: step: 1892/533, loss: 0.00362809537909925
2023-01-24 07:55:05.288322: step: 1896/533, loss: 0.02335933782160282
2023-01-24 07:55:06.381245: step: 1900/533, loss: 0.004958166275173426
2023-01-24 07:55:07.455205: step: 1904/533, loss: 0.013375964015722275
2023-01-24 07:55:08.551266: step: 1908/533, loss: 0.011064541526138783
2023-01-24 07:55:09.673549: step: 1912/533, loss: 0.012309594079852104
2023-01-24 07:55:10.769629: step: 1916/533, loss: 7.189044845290482e-05
2023-01-24 07:55:11.860419: step: 1920/533, loss: 0.005298960022628307
2023-01-24 07:55:12.932973: step: 1924/533, loss: 0.0024092737585306168
2023-01-24 07:55:14.031693: step: 1928/533, loss: 0.011046933010220528
2023-01-24 07:55:15.126295: step: 1932/533, loss: 0.006493415683507919
2023-01-24 07:55:16.241632: step: 1936/533, loss: 0.013179970905184746
2023-01-24 07:55:17.346618: step: 1940/533, loss: 0.06373078376054764
2023-01-24 07:55:18.445240: step: 1944/533, loss: 0.015654614195227623
2023-01-24 07:55:19.534851: step: 1948/533, loss: 0.014752114191651344
2023-01-24 07:55:20.627786: step: 1952/533, loss: 0.005928429774940014
2023-01-24 07:55:21.703597: step: 1956/533, loss: 0.01635819673538208
2023-01-24 07:55:22.846313: step: 1960/533, loss: 0.009875806048512459
2023-01-24 07:55:23.932460: step: 1964/533, loss: 0.01573099009692669
2023-01-24 07:55:25.014199: step: 1968/533, loss: 0.00857747346162796
2023-01-24 07:55:26.105175: step: 1972/533, loss: 0.009920096956193447
2023-01-24 07:55:27.209420: step: 1976/533, loss: 0.017151426523923874
2023-01-24 07:55:28.280675: step: 1980/533, loss: 0.004051075782626867
2023-01-24 07:55:29.361251: step: 1984/533, loss: 0.041023142635822296
2023-01-24 07:55:30.436063: step: 1988/533, loss: 0.004516015760600567
2023-01-24 07:55:31.542523: step: 1992/533, loss: 0.018290553241968155
2023-01-24 07:55:32.613184: step: 1996/533, loss: 0.0016235393704846501
2023-01-24 07:55:33.721474: step: 2000/533, loss: 0.014435991644859314
2023-01-24 07:55:34.812783: step: 2004/533, loss: 0.0091646583750844
2023-01-24 07:55:35.955041: step: 2008/533, loss: 0.031221458688378334
2023-01-24 07:55:37.064061: step: 2012/533, loss: 0.00213896157220006
2023-01-24 07:55:38.161595: step: 2016/533, loss: 0.006682281382381916
2023-01-24 07:55:39.242674: step: 2020/533, loss: 0.008288887329399586
2023-01-24 07:55:40.323872: step: 2024/533, loss: 0.0036747886333614588
2023-01-24 07:55:41.442298: step: 2028/533, loss: 0.04592045024037361
2023-01-24 07:55:42.550468: step: 2032/533, loss: 0.009508066810667515
2023-01-24 07:55:43.642234: step: 2036/533, loss: 0.005308781284838915
2023-01-24 07:55:44.753469: step: 2040/533, loss: 0.08955909311771393
2023-01-24 07:55:45.857908: step: 2044/533, loss: 0.011144822463393211
2023-01-24 07:55:46.949386: step: 2048/533, loss: 0.00375883630476892
2023-01-24 07:55:48.058438: step: 2052/533, loss: 0.012906655669212341
2023-01-24 07:55:49.143885: step: 2056/533, loss: 0.0036224566865712404
2023-01-24 07:55:50.278215: step: 2060/533, loss: 0.007885226979851723
2023-01-24 07:55:51.392834: step: 2064/533, loss: 0.005275092553347349
2023-01-24 07:55:52.494517: step: 2068/533, loss: 0.005307457409799099
2023-01-24 07:55:53.571442: step: 2072/533, loss: 0.005120756104588509
2023-01-24 07:55:54.665606: step: 2076/533, loss: 0.008543319068849087
2023-01-24 07:55:55.749365: step: 2080/533, loss: 0.015456680208444595
2023-01-24 07:55:56.847938: step: 2084/533, loss: 0.006942735519260168
2023-01-24 07:55:57.925982: step: 2088/533, loss: 0.012056090869009495
2023-01-24 07:55:59.034556: step: 2092/533, loss: 0.010902508161962032
2023-01-24 07:56:00.141753: step: 2096/533, loss: 0.006460400298237801
2023-01-24 07:56:01.213171: step: 2100/533, loss: 0.021020902320742607
2023-01-24 07:56:02.296505: step: 2104/533, loss: 0.005543981213122606
2023-01-24 07:56:03.383420: step: 2108/533, loss: 0.008076418191194534
2023-01-24 07:56:04.484619: step: 2112/533, loss: 0.01943342760205269
2023-01-24 07:56:05.566626: step: 2116/533, loss: 0.014753214083611965
2023-01-24 07:56:06.671311: step: 2120/533, loss: 0.008634351193904877
2023-01-24 07:56:07.759873: step: 2124/533, loss: 0.004395648837089539
2023-01-24 07:56:08.847814: step: 2128/533, loss: 0.003981213551014662
2023-01-24 07:56:09.946991: step: 2132/533, loss: 0.010721420869231224
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35987622036262207, 'r': 0.32641524351676154, 'f1': 0.34233001658374795}, 'combined': 0.2522431701143406, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38724649911091347, 'r': 0.3604371260955425, 'f1': 0.37336116647347034}, 'combined': 0.24890744431564685, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35276099882864465, 'r': 0.3226390919077926, 'f1': 0.33702834774114315}, 'combined': 0.24833667728294756, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38392019997815174, 'r': 0.31267347055912936, 'f1': 0.34465332207895555}, 'combined': 0.22976888138597032, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33738460172801515, 'r': 0.31817864717044314, 'f1': 0.3275002872242647}, 'combined': 0.24131600111261609, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3729077245126749, 'r': 0.3467324707728429, 'f1': 0.35934406537494434}, 'combined': 0.23956271024996284, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661572385213968, 'r': 0.3216903253043771, 'f1': 0.34248646754627615}, 'combined': 0.2523584497709403, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38773270130457727, 'r': 0.30906770132836014, 'f1': 0.34395977461904176}, 'combined': 0.22930651641269445, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, '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 07:58:35.871212: step: 4/533, loss: 0.03929833322763443
2023-01-24 07:58:36.953930: step: 8/533, loss: 0.004579861182719469
2023-01-24 07:58:38.040018: step: 12/533, loss: 0.009973995387554169
2023-01-24 07:58:39.134163: step: 16/533, loss: 0.02875964529812336
2023-01-24 07:58:40.199453: step: 20/533, loss: 0.011399959214031696
2023-01-24 07:58:41.303325: step: 24/533, loss: 0.009152397513389587
2023-01-24 07:58:42.387042: step: 28/533, loss: 0.004185824654996395
2023-01-24 07:58:43.484484: step: 32/533, loss: 0.017670201137661934
2023-01-24 07:58:44.566771: step: 36/533, loss: 0.016877561807632446
2023-01-24 07:58:45.649436: step: 40/533, loss: 0.006835806183516979
2023-01-24 07:58:46.722627: step: 44/533, loss: 0.002751064719632268
2023-01-24 07:58:47.801866: step: 48/533, loss: 0.005121206399053335
2023-01-24 07:58:48.866528: step: 52/533, loss: 0.003925796132534742
2023-01-24 07:58:49.973485: step: 56/533, loss: 0.004740580450743437
2023-01-24 07:58:51.052336: step: 60/533, loss: 0.03525589779019356
2023-01-24 07:58:52.139298: step: 64/533, loss: 0.0241148229688406
2023-01-24 07:58:53.226356: step: 68/533, loss: 0.004866495728492737
2023-01-24 07:58:54.351541: step: 72/533, loss: 0.029376909136772156
2023-01-24 07:58:55.441845: step: 76/533, loss: 0.04006674140691757
2023-01-24 07:58:56.522609: step: 80/533, loss: 0.01545947790145874
2023-01-24 07:58:57.608993: step: 84/533, loss: 0.000682312878780067
2023-01-24 07:58:58.702862: step: 88/533, loss: 0.0013596902135759592
2023-01-24 07:58:59.818233: step: 92/533, loss: 0.0002769369166344404
2023-01-24 07:59:00.898195: step: 96/533, loss: 0.002315398771315813
2023-01-24 07:59:01.983074: step: 100/533, loss: 0.002399020129814744
2023-01-24 07:59:03.045538: step: 104/533, loss: 0.013398027047514915
2023-01-24 07:59:04.127192: step: 108/533, loss: 0.018782099708914757
2023-01-24 07:59:05.208931: step: 112/533, loss: 0.010438687168061733
2023-01-24 07:59:06.289916: step: 116/533, loss: 0.0067239492200315
2023-01-24 07:59:07.369608: step: 120/533, loss: 0.007392051164060831
2023-01-24 07:59:08.454535: step: 124/533, loss: 0.003571520559489727
2023-01-24 07:59:09.568314: step: 128/533, loss: 0.04166841506958008
2023-01-24 07:59:10.633851: step: 132/533, loss: 0.005617179907858372
2023-01-24 07:59:11.730655: step: 136/533, loss: 0.0032482233364135027
2023-01-24 07:59:12.830645: step: 140/533, loss: 0.016901560127735138
2023-01-24 07:59:13.915979: step: 144/533, loss: 0.03144529089331627
2023-01-24 07:59:14.981754: step: 148/533, loss: 0.005158312618732452
2023-01-24 07:59:16.081509: step: 152/533, loss: 0.01275157555937767
2023-01-24 07:59:17.148869: step: 156/533, loss: 0.007741060573607683
2023-01-24 07:59:18.237144: step: 160/533, loss: 0.013053162023425102
2023-01-24 07:59:19.323820: step: 164/533, loss: 0.010975106619298458
2023-01-24 07:59:20.430839: step: 168/533, loss: 0.006460905075073242
2023-01-24 07:59:21.496575: step: 172/533, loss: 0.003966364078223705
2023-01-24 07:59:22.604906: step: 176/533, loss: 0.012807016260921955
2023-01-24 07:59:23.706634: step: 180/533, loss: 0.0051065729930996895
2023-01-24 07:59:24.805378: step: 184/533, loss: 0.012273533269762993
2023-01-24 07:59:25.887806: step: 188/533, loss: 0.002373267663642764
2023-01-24 07:59:26.960529: step: 192/533, loss: 0.00938892737030983
2023-01-24 07:59:28.054743: step: 196/533, loss: 0.01642984338104725
2023-01-24 07:59:29.138442: step: 200/533, loss: 0.008001258596777916
2023-01-24 07:59:30.218647: step: 204/533, loss: 0.008227764628827572
2023-01-24 07:59:31.314847: step: 208/533, loss: 0.004390839487314224
2023-01-24 07:59:32.418052: step: 212/533, loss: 0.0213148333132267
2023-01-24 07:59:33.487422: step: 216/533, loss: 0.002895868383347988
2023-01-24 07:59:34.570755: step: 220/533, loss: 0.0010733000235632062
2023-01-24 07:59:35.654793: step: 224/533, loss: 0.023110708221793175
2023-01-24 07:59:36.743293: step: 228/533, loss: 0.009598718956112862
2023-01-24 07:59:37.858897: step: 232/533, loss: 0.012249787338078022
2023-01-24 07:59:38.956342: step: 236/533, loss: 0.010002810508012772
2023-01-24 07:59:40.035600: step: 240/533, loss: 0.007966041564941406
2023-01-24 07:59:41.119473: step: 244/533, loss: 0.0039052562788128853
2023-01-24 07:59:42.208071: step: 248/533, loss: 0.00428518932312727
2023-01-24 07:59:43.303173: step: 252/533, loss: 0.01038496196269989
2023-01-24 07:59:44.390981: step: 256/533, loss: 0.0033634500578045845
2023-01-24 07:59:45.482947: step: 260/533, loss: 0.012601116672158241
2023-01-24 07:59:46.547840: step: 264/533, loss: 0.012740110978484154
2023-01-24 07:59:47.632429: step: 268/533, loss: 0.062176160514354706
2023-01-24 07:59:48.725630: step: 272/533, loss: 0.0075059924274683
2023-01-24 07:59:49.818967: step: 276/533, loss: 0.001901356503367424
2023-01-24 07:59:50.930575: step: 280/533, loss: 0.006692111492156982
2023-01-24 07:59:52.011959: step: 284/533, loss: 0.03224657103419304
2023-01-24 07:59:53.128520: step: 288/533, loss: 0.007354206405580044
2023-01-24 07:59:54.205855: step: 292/533, loss: 0.008419306017458439
2023-01-24 07:59:55.273555: step: 296/533, loss: 0.0078104096464812756
2023-01-24 07:59:56.346262: step: 300/533, loss: 0.0016621786635369062
2023-01-24 07:59:57.435988: step: 304/533, loss: 0.0303119495511055
2023-01-24 07:59:58.514916: step: 308/533, loss: 0.0020463052205741405
2023-01-24 07:59:59.612576: step: 312/533, loss: 0.0344405472278595
2023-01-24 08:00:00.709712: step: 316/533, loss: 0.03324500843882561
2023-01-24 08:00:01.797978: step: 320/533, loss: 0.008553696796298027
2023-01-24 08:00:02.888692: step: 324/533, loss: 0.010664846748113632
2023-01-24 08:00:03.976926: step: 328/533, loss: 0.004006653558462858
2023-01-24 08:00:05.047512: step: 332/533, loss: 0.0011468648444861174
2023-01-24 08:00:06.118723: step: 336/533, loss: 0.0033074987586587667
2023-01-24 08:00:07.219096: step: 340/533, loss: 0.01757623627781868
2023-01-24 08:00:08.316015: step: 344/533, loss: 0.0041780429892241955
2023-01-24 08:00:09.431937: step: 348/533, loss: 0.0
2023-01-24 08:00:10.524039: step: 352/533, loss: 0.01994781196117401
2023-01-24 08:00:11.605013: step: 356/533, loss: 0.015185005031526089
2023-01-24 08:00:12.703434: step: 360/533, loss: 0.0030008419416844845
2023-01-24 08:00:13.782962: step: 364/533, loss: 0.009492452256381512
2023-01-24 08:00:14.865596: step: 368/533, loss: 0.0071267965249717236
2023-01-24 08:00:15.976164: step: 372/533, loss: 0.011452874168753624
2023-01-24 08:00:17.051215: step: 376/533, loss: 0.0049600680358707905
2023-01-24 08:00:18.147881: step: 380/533, loss: 0.0032875356264412403
2023-01-24 08:00:19.213881: step: 384/533, loss: 0.026752851903438568
2023-01-24 08:00:20.288724: step: 388/533, loss: 0.0045652855187654495
2023-01-24 08:00:21.395179: step: 392/533, loss: 0.008298248052597046
2023-01-24 08:00:22.493909: step: 396/533, loss: 0.01071571372449398
2023-01-24 08:00:23.575278: step: 400/533, loss: 0.0363355353474617
2023-01-24 08:00:24.674335: step: 404/533, loss: 0.004939856939017773
2023-01-24 08:00:25.764930: step: 408/533, loss: 0.01663948781788349
2023-01-24 08:00:26.858513: step: 412/533, loss: 0.005658458918333054
2023-01-24 08:00:27.938524: step: 416/533, loss: 0.004852100275456905
2023-01-24 08:00:29.011700: step: 420/533, loss: 0.00893913209438324
2023-01-24 08:00:30.110388: step: 424/533, loss: 0.008618238382041454
2023-01-24 08:00:31.182966: step: 428/533, loss: 0.0021428419277071953
2023-01-24 08:00:32.255800: step: 432/533, loss: 0.002154327929019928
2023-01-24 08:00:33.341703: step: 436/533, loss: 0.004487314261496067
2023-01-24 08:00:34.427533: step: 440/533, loss: 0.0021680183708667755
2023-01-24 08:00:35.516696: step: 444/533, loss: 0.0037029413506388664
2023-01-24 08:00:36.602581: step: 448/533, loss: 0.007184694986790419
2023-01-24 08:00:37.731246: step: 452/533, loss: 0.003917887806892395
2023-01-24 08:00:38.814640: step: 456/533, loss: 0.0019463782664388418
2023-01-24 08:00:39.900417: step: 460/533, loss: 0.016821423545479774
2023-01-24 08:00:41.001909: step: 464/533, loss: 0.010699243284761906
2023-01-24 08:00:42.101900: step: 468/533, loss: 0.003053609747439623
2023-01-24 08:00:43.166203: step: 472/533, loss: 0.00020688770746346563
2023-01-24 08:00:44.254509: step: 476/533, loss: 0.032422684133052826
2023-01-24 08:00:45.374805: step: 480/533, loss: 0.0035675051622092724
2023-01-24 08:00:46.482891: step: 484/533, loss: 0.005465144291520119
2023-01-24 08:00:47.598371: step: 488/533, loss: 0.24219414591789246
2023-01-24 08:00:48.694215: step: 492/533, loss: 0.05272916704416275
2023-01-24 08:00:49.779196: step: 496/533, loss: 0.0034672338515520096
2023-01-24 08:00:50.843707: step: 500/533, loss: 0.008993754163384438
2023-01-24 08:00:51.923715: step: 504/533, loss: 0.03472108766436577
2023-01-24 08:00:53.018652: step: 508/533, loss: 0.024666227400302887
2023-01-24 08:00:54.135090: step: 512/533, loss: 0.003408091841265559
2023-01-24 08:00:55.227497: step: 516/533, loss: 0.003942261449992657
2023-01-24 08:00:56.347636: step: 520/533, loss: 0.016481764614582062
2023-01-24 08:00:57.438951: step: 524/533, loss: 0.002739404560998082
2023-01-24 08:00:58.517885: step: 528/533, loss: 0.003209500340744853
2023-01-24 08:00:59.640122: step: 532/533, loss: 0.015604358166456223
2023-01-24 08:01:00.762871: step: 536/533, loss: 0.004144397098571062
2023-01-24 08:01:01.849438: step: 540/533, loss: 0.002349136397242546
2023-01-24 08:01:02.939328: step: 544/533, loss: 0.02461756207048893
2023-01-24 08:01:04.044547: step: 548/533, loss: 0.0033908430486917496
2023-01-24 08:01:05.135926: step: 552/533, loss: 0.007412558421492577
2023-01-24 08:01:06.236150: step: 556/533, loss: 0.007802891079336405
2023-01-24 08:01:07.341061: step: 560/533, loss: 0.0028611994348466396
2023-01-24 08:01:08.461065: step: 564/533, loss: 0.01167475339025259
2023-01-24 08:01:09.558550: step: 568/533, loss: 0.0050392369739711285
2023-01-24 08:01:10.652851: step: 572/533, loss: 0.008902034722268581
2023-01-24 08:01:11.735097: step: 576/533, loss: 0.031191732734441757
2023-01-24 08:01:12.831644: step: 580/533, loss: 0.026524554938077927
2023-01-24 08:01:13.919911: step: 584/533, loss: 0.03122488036751747
2023-01-24 08:01:15.045826: step: 588/533, loss: 0.004829412326216698
2023-01-24 08:01:16.144471: step: 592/533, loss: 0.002528398996219039
2023-01-24 08:01:17.213738: step: 596/533, loss: 0.0096895731985569
2023-01-24 08:01:18.267585: step: 600/533, loss: 0.0013934092130512
2023-01-24 08:01:19.361403: step: 604/533, loss: 0.008349018171429634
2023-01-24 08:01:20.461334: step: 608/533, loss: 0.0477847196161747
2023-01-24 08:01:21.567518: step: 612/533, loss: 0.009311767295002937
2023-01-24 08:01:22.675788: step: 616/533, loss: 0.0033611636608839035
2023-01-24 08:01:23.768905: step: 620/533, loss: 0.004896032623946667
2023-01-24 08:01:24.857388: step: 624/533, loss: 0.03574500232934952
2023-01-24 08:01:25.927668: step: 628/533, loss: 0.006996012292802334
2023-01-24 08:01:27.014657: step: 632/533, loss: 0.0343448668718338
2023-01-24 08:01:28.135737: step: 636/533, loss: 0.005911068059504032
2023-01-24 08:01:29.204844: step: 640/533, loss: 0.015501603484153748
2023-01-24 08:01:30.308905: step: 644/533, loss: 0.020527837797999382
2023-01-24 08:01:31.401905: step: 648/533, loss: 0.005181065294891596
2023-01-24 08:01:32.502649: step: 652/533, loss: 0.008822758682072163
2023-01-24 08:01:33.592775: step: 656/533, loss: 0.0011894147610291839
2023-01-24 08:01:34.718683: step: 660/533, loss: 0.02778276801109314
2023-01-24 08:01:35.821934: step: 664/533, loss: 0.00669320672750473
2023-01-24 08:01:36.900798: step: 668/533, loss: 0.025330673903226852
2023-01-24 08:01:37.975492: step: 672/533, loss: 0.005043234676122665
2023-01-24 08:01:39.059288: step: 676/533, loss: 0.006952103227376938
2023-01-24 08:01:40.129021: step: 680/533, loss: 0.0042616524733603
2023-01-24 08:01:41.218375: step: 684/533, loss: 0.011878800578415394
2023-01-24 08:01:42.316220: step: 688/533, loss: 0.04167141392827034
2023-01-24 08:01:43.396114: step: 692/533, loss: 0.007142278365790844
2023-01-24 08:01:44.476517: step: 696/533, loss: 0.009722287766635418
2023-01-24 08:01:45.560742: step: 700/533, loss: 0.015389160253107548
2023-01-24 08:01:46.646930: step: 704/533, loss: 0.00674452492967248
2023-01-24 08:01:47.735598: step: 708/533, loss: 0.006241577677428722
2023-01-24 08:01:48.816953: step: 712/533, loss: 0.0017361755017191172
2023-01-24 08:01:49.944979: step: 716/533, loss: 0.005969520192593336
2023-01-24 08:01:51.052683: step: 720/533, loss: 0.005676220171153545
2023-01-24 08:01:52.134153: step: 724/533, loss: 0.0024193706922233105
2023-01-24 08:01:53.231681: step: 728/533, loss: 0.00606112414970994
2023-01-24 08:01:54.307919: step: 732/533, loss: 0.012141628190875053
2023-01-24 08:01:55.409690: step: 736/533, loss: 0.0029649250209331512
2023-01-24 08:01:56.496637: step: 740/533, loss: 0.011211933568120003
2023-01-24 08:01:57.577154: step: 744/533, loss: 0.010522447526454926
2023-01-24 08:01:58.652357: step: 748/533, loss: 0.0003025331534445286
2023-01-24 08:01:59.738512: step: 752/533, loss: 0.014596013352274895
2023-01-24 08:02:00.845242: step: 756/533, loss: 0.002287084935232997
2023-01-24 08:02:01.927481: step: 760/533, loss: 0.01843094266951084
2023-01-24 08:02:03.023581: step: 764/533, loss: 0.0037269967142492533
2023-01-24 08:02:04.091719: step: 768/533, loss: 0.021641166880726814
2023-01-24 08:02:05.161021: step: 772/533, loss: 0.008420098572969437
2023-01-24 08:02:06.239110: step: 776/533, loss: 0.004369289614260197
2023-01-24 08:02:07.339799: step: 780/533, loss: 0.01704583689570427
2023-01-24 08:02:08.427108: step: 784/533, loss: 0.020666614174842834
2023-01-24 08:02:09.499381: step: 788/533, loss: 0.010205930098891258
2023-01-24 08:02:10.574872: step: 792/533, loss: 0.003424484981223941
2023-01-24 08:02:11.664272: step: 796/533, loss: 0.0035102765541523695
2023-01-24 08:02:12.774124: step: 800/533, loss: 0.0057216426357626915
2023-01-24 08:02:13.871673: step: 804/533, loss: 0.005462408997118473
2023-01-24 08:02:14.961582: step: 808/533, loss: 0.006988579872995615
2023-01-24 08:02:16.058814: step: 812/533, loss: 0.001831869245506823
2023-01-24 08:02:17.141131: step: 816/533, loss: 0.016282182186841965
2023-01-24 08:02:18.234831: step: 820/533, loss: 0.002413458889350295
2023-01-24 08:02:19.319017: step: 824/533, loss: 0.004961107391864061
2023-01-24 08:02:20.421841: step: 828/533, loss: 0.003528157016262412
2023-01-24 08:02:21.502382: step: 832/533, loss: 0.0011598613345995545
2023-01-24 08:02:22.575169: step: 836/533, loss: 0.003587575862184167
2023-01-24 08:02:23.646398: step: 840/533, loss: 0.0013473420403897762
2023-01-24 08:02:24.752884: step: 844/533, loss: 0.004926305264234543
2023-01-24 08:02:25.844494: step: 848/533, loss: 0.007298493757843971
2023-01-24 08:02:26.943825: step: 852/533, loss: 0.00318435812368989
2023-01-24 08:02:28.033020: step: 856/533, loss: 0.007443076465278864
2023-01-24 08:02:29.148048: step: 860/533, loss: 0.00514489971101284
2023-01-24 08:02:30.240353: step: 864/533, loss: 0.002489294158294797
2023-01-24 08:02:31.348520: step: 868/533, loss: 0.0035843774676322937
2023-01-24 08:02:32.459407: step: 872/533, loss: 0.001534481649287045
2023-01-24 08:02:33.558405: step: 876/533, loss: 0.009734904393553734
2023-01-24 08:02:34.650113: step: 880/533, loss: 0.00502153392881155
2023-01-24 08:02:35.760786: step: 884/533, loss: 0.005431980360299349
2023-01-24 08:02:36.823628: step: 888/533, loss: 0.009807522408664227
2023-01-24 08:02:37.927322: step: 892/533, loss: 0.0052767544984817505
2023-01-24 08:02:39.036292: step: 896/533, loss: 0.004325535614043474
2023-01-24 08:02:40.127278: step: 900/533, loss: 0.007819817401468754
2023-01-24 08:02:41.203579: step: 904/533, loss: 0.0036278516054153442
2023-01-24 08:02:42.290098: step: 908/533, loss: 0.005739787593483925
2023-01-24 08:02:43.385577: step: 912/533, loss: 0.0035287390928715467
2023-01-24 08:02:44.454393: step: 916/533, loss: 0.0015303486725315452
2023-01-24 08:02:45.537960: step: 920/533, loss: 0.004625520668923855
2023-01-24 08:02:46.622584: step: 924/533, loss: 0.008053820580244064
2023-01-24 08:02:47.722135: step: 928/533, loss: 0.0034832938108593225
2023-01-24 08:02:48.830811: step: 932/533, loss: 0.016615066677331924
2023-01-24 08:02:49.977511: step: 936/533, loss: 0.02186109870672226
2023-01-24 08:02:51.073231: step: 940/533, loss: 0.0035701501183211803
2023-01-24 08:02:52.173958: step: 944/533, loss: 0.02518385276198387
2023-01-24 08:02:53.288621: step: 948/533, loss: 0.004158812575042248
2023-01-24 08:02:54.392256: step: 952/533, loss: 0.004635316785424948
2023-01-24 08:02:55.489572: step: 956/533, loss: 0.0006137829623185098
2023-01-24 08:02:56.579398: step: 960/533, loss: 0.03029099479317665
2023-01-24 08:02:57.677134: step: 964/533, loss: 0.013306541368365288
2023-01-24 08:02:58.779061: step: 968/533, loss: 0.012992017902433872
2023-01-24 08:02:59.860697: step: 972/533, loss: 0.0005603756289929152
2023-01-24 08:03:00.958138: step: 976/533, loss: 0.006862389389425516
2023-01-24 08:03:02.031693: step: 980/533, loss: 0.011134202592074871
2023-01-24 08:03:03.102424: step: 984/533, loss: 0.010399137623608112
2023-01-24 08:03:04.181557: step: 988/533, loss: 0.00479255523532629
2023-01-24 08:03:05.263871: step: 992/533, loss: 0.015647342428565025
2023-01-24 08:03:06.381846: step: 996/533, loss: 0.024185756221413612
2023-01-24 08:03:07.501524: step: 1000/533, loss: 0.007233445532619953
2023-01-24 08:03:08.596788: step: 1004/533, loss: 0.0013839867897331715
2023-01-24 08:03:09.682107: step: 1008/533, loss: 0.005240104626864195
2023-01-24 08:03:10.762584: step: 1012/533, loss: 0.0207773819565773
2023-01-24 08:03:11.891442: step: 1016/533, loss: 0.005388690624386072
2023-01-24 08:03:12.970921: step: 1020/533, loss: 0.0031075833830982447
2023-01-24 08:03:14.058600: step: 1024/533, loss: 0.013148265890777111
2023-01-24 08:03:15.163439: step: 1028/533, loss: 0.031926676630973816
2023-01-24 08:03:16.284123: step: 1032/533, loss: 0.006119645666331053
2023-01-24 08:03:17.384730: step: 1036/533, loss: 0.003224753774702549
2023-01-24 08:03:18.489979: step: 1040/533, loss: 0.01657811366021633
2023-01-24 08:03:19.598160: step: 1044/533, loss: 0.005960354581475258
2023-01-24 08:03:20.685643: step: 1048/533, loss: 0.0052272239699959755
2023-01-24 08:03:21.783621: step: 1052/533, loss: 0.0020503983832895756
2023-01-24 08:03:22.886563: step: 1056/533, loss: 0.005899838171899319
2023-01-24 08:03:24.003460: step: 1060/533, loss: 0.0037482779007405043
2023-01-24 08:03:25.111308: step: 1064/533, loss: 0.04139679670333862
2023-01-24 08:03:26.207661: step: 1068/533, loss: 0.015133384615182877
2023-01-24 08:03:27.330371: step: 1072/533, loss: 0.006530649960041046
2023-01-24 08:03:28.420057: step: 1076/533, loss: 0.004994932562112808
2023-01-24 08:03:29.496826: step: 1080/533, loss: 0.006301813758909702
2023-01-24 08:03:30.606103: step: 1084/533, loss: 0.029157210141420364
2023-01-24 08:03:31.703266: step: 1088/533, loss: 0.0021966532804071903
2023-01-24 08:03:32.786628: step: 1092/533, loss: 0.007731216493993998
2023-01-24 08:03:33.878764: step: 1096/533, loss: 0.015270187519490719
2023-01-24 08:03:34.948816: step: 1100/533, loss: 0.006028708070516586
2023-01-24 08:03:36.034400: step: 1104/533, loss: 0.004561856854707003
2023-01-24 08:03:37.140997: step: 1108/533, loss: 0.0036804776173084974
2023-01-24 08:03:38.245270: step: 1112/533, loss: 0.0046641151420772076
2023-01-24 08:03:39.346340: step: 1116/533, loss: 0.013350876979529858
2023-01-24 08:03:40.448125: step: 1120/533, loss: 0.019112523645162582
2023-01-24 08:03:41.555412: step: 1124/533, loss: 0.004853821359574795
2023-01-24 08:03:42.664648: step: 1128/533, loss: 0.03480241820216179
2023-01-24 08:03:43.754195: step: 1132/533, loss: 0.010547598823904991
2023-01-24 08:03:44.860387: step: 1136/533, loss: 0.005358375608921051
2023-01-24 08:03:45.991803: step: 1140/533, loss: 0.018934328109025955
2023-01-24 08:03:47.097830: step: 1144/533, loss: 0.001690707285888493
2023-01-24 08:03:48.201613: step: 1148/533, loss: 0.005338383838534355
2023-01-24 08:03:49.291923: step: 1152/533, loss: 0.002724283142015338
2023-01-24 08:03:50.385503: step: 1156/533, loss: 0.003441559849306941
2023-01-24 08:03:51.481662: step: 1160/533, loss: 0.01063911709934473
2023-01-24 08:03:52.572232: step: 1164/533, loss: 0.009723898954689503
2023-01-24 08:03:53.672676: step: 1168/533, loss: 0.017974551767110825
2023-01-24 08:03:54.748769: step: 1172/533, loss: 0.022459108382463455
2023-01-24 08:03:55.838025: step: 1176/533, loss: 0.004947408102452755
2023-01-24 08:03:56.941863: step: 1180/533, loss: 0.006979506462812424
2023-01-24 08:03:58.031656: step: 1184/533, loss: 0.019749751314520836
2023-01-24 08:03:59.129308: step: 1188/533, loss: 0.003764878027141094
2023-01-24 08:04:00.220998: step: 1192/533, loss: 0.01699109375476837
2023-01-24 08:04:01.324188: step: 1196/533, loss: 0.01475554145872593
2023-01-24 08:04:02.435030: step: 1200/533, loss: 0.005521553102880716
2023-01-24 08:04:03.512359: step: 1204/533, loss: 0.013580460101366043
2023-01-24 08:04:04.600247: step: 1208/533, loss: 0.02991221658885479
2023-01-24 08:04:05.709724: step: 1212/533, loss: 0.020943840965628624
2023-01-24 08:04:06.773792: step: 1216/533, loss: 0.002633114345371723
2023-01-24 08:04:07.875957: step: 1220/533, loss: 0.011062761768698692
2023-01-24 08:04:08.954679: step: 1224/533, loss: 0.0
2023-01-24 08:04:10.044088: step: 1228/533, loss: 0.02199055626988411
2023-01-24 08:04:11.152416: step: 1232/533, loss: 0.016655223444104195
2023-01-24 08:04:12.240526: step: 1236/533, loss: 0.007236640900373459
2023-01-24 08:04:13.349956: step: 1240/533, loss: 0.003622002899646759
2023-01-24 08:04:14.428586: step: 1244/533, loss: 0.0058493847027421
2023-01-24 08:04:15.521785: step: 1248/533, loss: 0.005607883911579847
2023-01-24 08:04:16.622295: step: 1252/533, loss: 0.007017327472567558
2023-01-24 08:04:17.743728: step: 1256/533, loss: 0.012884319759905338
2023-01-24 08:04:18.844808: step: 1260/533, loss: 0.020614035427570343
2023-01-24 08:04:19.971878: step: 1264/533, loss: 0.011642556637525558
2023-01-24 08:04:21.063973: step: 1268/533, loss: 0.0038022594526410103
2023-01-24 08:04:22.165809: step: 1272/533, loss: 1.7780985217541456e-05
2023-01-24 08:04:23.257768: step: 1276/533, loss: 0.009115871973335743
2023-01-24 08:04:24.336458: step: 1280/533, loss: 0.009227434173226357
2023-01-24 08:04:25.430637: step: 1284/533, loss: 0.004574194550514221
2023-01-24 08:04:26.547707: step: 1288/533, loss: 0.001888015540316701
2023-01-24 08:04:27.647091: step: 1292/533, loss: 0.005479399114847183
2023-01-24 08:04:28.727080: step: 1296/533, loss: 0.002016686834394932
2023-01-24 08:04:29.813515: step: 1300/533, loss: 0.033453069627285004
2023-01-24 08:04:30.929092: step: 1304/533, loss: 0.0033390424214303493
2023-01-24 08:04:32.012575: step: 1308/533, loss: 0.003878022776916623
2023-01-24 08:04:33.107731: step: 1312/533, loss: 0.001905364915728569
2023-01-24 08:04:34.209801: step: 1316/533, loss: 0.03276413679122925
2023-01-24 08:04:35.282256: step: 1320/533, loss: 0.008004125207662582
2023-01-24 08:04:36.385266: step: 1324/533, loss: 0.004857903812080622
2023-01-24 08:04:37.485096: step: 1328/533, loss: 0.010702898725867271
2023-01-24 08:04:38.581285: step: 1332/533, loss: 0.0263019148260355
2023-01-24 08:04:39.681901: step: 1336/533, loss: 0.006677114404737949
2023-01-24 08:04:40.782002: step: 1340/533, loss: 0.02341143600642681
2023-01-24 08:04:41.873866: step: 1344/533, loss: 0.025410303846001625
2023-01-24 08:04:42.981843: step: 1348/533, loss: 0.00855476874858141
2023-01-24 08:04:44.084180: step: 1352/533, loss: 0.016370724886655807
2023-01-24 08:04:45.182615: step: 1356/533, loss: 0.012565397657454014
2023-01-24 08:04:46.241164: step: 1360/533, loss: 0.00848792027682066
2023-01-24 08:04:47.341962: step: 1364/533, loss: 0.005698624067008495
2023-01-24 08:04:48.435558: step: 1368/533, loss: 0.004290240816771984
2023-01-24 08:04:49.537408: step: 1372/533, loss: 0.002481536939740181
2023-01-24 08:04:50.639899: step: 1376/533, loss: 0.00687165604904294
2023-01-24 08:04:51.739817: step: 1380/533, loss: 0.0003868505300488323
2023-01-24 08:04:52.829106: step: 1384/533, loss: 0.006653728894889355
2023-01-24 08:04:53.937966: step: 1388/533, loss: 0.0033031166531145573
2023-01-24 08:04:55.024759: step: 1392/533, loss: 0.013717702589929104
2023-01-24 08:04:56.110803: step: 1396/533, loss: 0.03350502997636795
2023-01-24 08:04:57.234239: step: 1400/533, loss: 0.005749749485403299
2023-01-24 08:04:58.345432: step: 1404/533, loss: 0.01148066483438015
2023-01-24 08:04:59.451545: step: 1408/533, loss: 0.005329596344381571
2023-01-24 08:05:00.540195: step: 1412/533, loss: 0.0038734914269298315
2023-01-24 08:05:01.649523: step: 1416/533, loss: 0.07039173692464828
2023-01-24 08:05:02.767931: step: 1420/533, loss: 0.009375953115522861
2023-01-24 08:05:03.847150: step: 1424/533, loss: 0.011942364275455475
2023-01-24 08:05:04.952798: step: 1428/533, loss: 0.0208677239716053
2023-01-24 08:05:06.033800: step: 1432/533, loss: 0.021593406796455383
2023-01-24 08:05:07.151957: step: 1436/533, loss: 0.009666201658546925
2023-01-24 08:05:08.272617: step: 1440/533, loss: 0.007203944027423859
2023-01-24 08:05:09.374914: step: 1444/533, loss: 0.002148986328393221
2023-01-24 08:05:10.492503: step: 1448/533, loss: 0.005678969901055098
2023-01-24 08:05:11.598307: step: 1452/533, loss: 0.006171806249767542
2023-01-24 08:05:12.705311: step: 1456/533, loss: 0.002123665064573288
2023-01-24 08:05:13.791324: step: 1460/533, loss: 0.012814301997423172
2023-01-24 08:05:14.889407: step: 1464/533, loss: 0.004906698130071163
2023-01-24 08:05:15.985365: step: 1468/533, loss: 0.007200340740382671
2023-01-24 08:05:17.073271: step: 1472/533, loss: 0.00914101954549551
2023-01-24 08:05:18.190931: step: 1476/533, loss: 0.0035846089012920856
2023-01-24 08:05:19.274751: step: 1480/533, loss: 0.010124698281288147
2023-01-24 08:05:20.373376: step: 1484/533, loss: 0.0010136242490261793
2023-01-24 08:05:21.476904: step: 1488/533, loss: 0.007838346995413303
2023-01-24 08:05:22.574894: step: 1492/533, loss: 0.009874928742647171
2023-01-24 08:05:23.679839: step: 1496/533, loss: 0.01711534708738327
2023-01-24 08:05:24.774591: step: 1500/533, loss: 0.02209588699042797
2023-01-24 08:05:25.870088: step: 1504/533, loss: 0.008125667460262775
2023-01-24 08:05:26.963016: step: 1508/533, loss: 0.00764577928930521
2023-01-24 08:05:28.057378: step: 1512/533, loss: 0.024623941630125046
2023-01-24 08:05:29.159521: step: 1516/533, loss: 0.004712450318038464
2023-01-24 08:05:30.236682: step: 1520/533, loss: 0.020869504660367966
2023-01-24 08:05:31.339326: step: 1524/533, loss: 0.028407348319888115
2023-01-24 08:05:32.427157: step: 1528/533, loss: 0.026450295001268387
2023-01-24 08:05:33.520907: step: 1532/533, loss: 0.020668277516961098
2023-01-24 08:05:34.641429: step: 1536/533, loss: 0.0048571377992630005
2023-01-24 08:05:35.731536: step: 1540/533, loss: 0.007164777256548405
2023-01-24 08:05:36.839298: step: 1544/533, loss: 0.004358699545264244
2023-01-24 08:05:37.929972: step: 1548/533, loss: 0.003896551439538598
2023-01-24 08:05:39.051829: step: 1552/533, loss: 0.007377780508249998
2023-01-24 08:05:40.151524: step: 1556/533, loss: 0.02802693471312523
2023-01-24 08:05:41.240185: step: 1560/533, loss: 0.010750660672783852
2023-01-24 08:05:42.338893: step: 1564/533, loss: 0.04232978820800781
2023-01-24 08:05:43.434511: step: 1568/533, loss: 0.010732121765613556
2023-01-24 08:05:44.533584: step: 1572/533, loss: 0.008679371327161789
2023-01-24 08:05:45.630043: step: 1576/533, loss: 0.027130166068673134
2023-01-24 08:05:46.722483: step: 1580/533, loss: 0.005654449574649334
2023-01-24 08:05:47.809503: step: 1584/533, loss: 1.24131302072783e-05
2023-01-24 08:05:48.894091: step: 1588/533, loss: 0.005636162124574184
2023-01-24 08:05:50.002913: step: 1592/533, loss: 0.013538737781345844
2023-01-24 08:05:51.105912: step: 1596/533, loss: 0.005067549180239439
2023-01-24 08:05:52.212068: step: 1600/533, loss: 0.006231638137251139
2023-01-24 08:05:53.287456: step: 1604/533, loss: 0.0244497898966074
2023-01-24 08:05:54.439611: step: 1608/533, loss: 0.0124687934294343
2023-01-24 08:05:55.529399: step: 1612/533, loss: 0.005244281142950058
2023-01-24 08:05:56.613364: step: 1616/533, loss: 0.014378638938069344
2023-01-24 08:05:57.721100: step: 1620/533, loss: 0.03503953292965889
2023-01-24 08:05:58.805849: step: 1624/533, loss: 0.00837680697441101
2023-01-24 08:05:59.904078: step: 1628/533, loss: 0.010938954539597034
2023-01-24 08:06:01.004227: step: 1632/533, loss: 0.008443423546850681
2023-01-24 08:06:02.086609: step: 1636/533, loss: 0.0017980743432417512
2023-01-24 08:06:03.170123: step: 1640/533, loss: 0.05701809376478195
2023-01-24 08:06:04.259159: step: 1644/533, loss: 0.006378853227943182
2023-01-24 08:06:05.349679: step: 1648/533, loss: 0.012250455096364021
2023-01-24 08:06:06.412409: step: 1652/533, loss: 0.007852061651647091
2023-01-24 08:06:07.493959: step: 1656/533, loss: 0.001622378476895392
2023-01-24 08:06:08.595896: step: 1660/533, loss: 0.0021492657251656055
2023-01-24 08:06:09.691898: step: 1664/533, loss: 0.006042564287781715
2023-01-24 08:06:10.804937: step: 1668/533, loss: 0.04170599952340126
2023-01-24 08:06:11.888175: step: 1672/533, loss: 0.005317021161317825
2023-01-24 08:06:12.993338: step: 1676/533, loss: 0.008128211833536625
2023-01-24 08:06:14.084757: step: 1680/533, loss: 0.015514682047069073
2023-01-24 08:06:15.173870: step: 1684/533, loss: 0.021694255992770195
2023-01-24 08:06:16.265689: step: 1688/533, loss: 0.015570846386253834
2023-01-24 08:06:17.351351: step: 1692/533, loss: 0.005852662492543459
2023-01-24 08:06:18.441623: step: 1696/533, loss: 0.008632319048047066
2023-01-24 08:06:19.518799: step: 1700/533, loss: 0.0102683175355196
2023-01-24 08:06:20.609833: step: 1704/533, loss: 0.0033798974473029375
2023-01-24 08:06:21.721289: step: 1708/533, loss: 0.003317369380965829
2023-01-24 08:06:22.804486: step: 1712/533, loss: 0.006965213920921087
2023-01-24 08:06:23.887182: step: 1716/533, loss: 0.007277839817106724
2023-01-24 08:06:24.973976: step: 1720/533, loss: 0.003988957032561302
2023-01-24 08:06:26.073244: step: 1724/533, loss: 0.01025779265910387
2023-01-24 08:06:27.165202: step: 1728/533, loss: 0.030859338119626045
2023-01-24 08:06:28.248259: step: 1732/533, loss: 0.032617464661598206
2023-01-24 08:06:29.337873: step: 1736/533, loss: 0.06978877633810043
2023-01-24 08:06:30.442032: step: 1740/533, loss: 0.01247323676943779
2023-01-24 08:06:31.540317: step: 1744/533, loss: 0.010734924115240574
2023-01-24 08:06:32.629385: step: 1748/533, loss: 0.007815291173756123
2023-01-24 08:06:33.701035: step: 1752/533, loss: 0.0035402055364102125
2023-01-24 08:06:34.787981: step: 1756/533, loss: 0.00825725868344307
2023-01-24 08:06:35.885753: step: 1760/533, loss: 0.004831753671169281
2023-01-24 08:06:36.954169: step: 1764/533, loss: 0.002410843502730131
2023-01-24 08:06:38.041759: step: 1768/533, loss: 0.00724309915676713
2023-01-24 08:06:39.126145: step: 1772/533, loss: 0.0080685680732131
2023-01-24 08:06:40.215468: step: 1776/533, loss: 0.026344316080212593
2023-01-24 08:06:41.301207: step: 1780/533, loss: 0.0037751970812678337
2023-01-24 08:06:42.413610: step: 1784/533, loss: 0.004773533903062344
2023-01-24 08:06:43.505286: step: 1788/533, loss: 0.03126657009124756
2023-01-24 08:06:44.600667: step: 1792/533, loss: 0.005114969331771135
2023-01-24 08:06:45.691080: step: 1796/533, loss: 0.0280037522315979
2023-01-24 08:06:46.791304: step: 1800/533, loss: 0.003085387870669365
2023-01-24 08:06:47.863068: step: 1804/533, loss: 0.00014113936049398035
2023-01-24 08:06:48.948453: step: 1808/533, loss: 0.0024417585227638483
2023-01-24 08:06:50.048745: step: 1812/533, loss: 0.024346772581338882
2023-01-24 08:06:51.126741: step: 1816/533, loss: 0.02519110031425953
2023-01-24 08:06:52.243829: step: 1820/533, loss: 0.003077474422752857
2023-01-24 08:06:53.330906: step: 1824/533, loss: 0.029844406992197037
2023-01-24 08:06:54.418191: step: 1828/533, loss: 0.0022204124834388494
2023-01-24 08:06:55.493355: step: 1832/533, loss: 0.007574114482849836
2023-01-24 08:06:56.585208: step: 1836/533, loss: 0.0023016398772597313
2023-01-24 08:06:57.673674: step: 1840/533, loss: 0.003939008805900812
2023-01-24 08:06:58.794589: step: 1844/533, loss: 0.004076794721186161
2023-01-24 08:06:59.868810: step: 1848/533, loss: 0.003787125227972865
2023-01-24 08:07:00.938873: step: 1852/533, loss: 0.0120763648301363
2023-01-24 08:07:02.026699: step: 1856/533, loss: 0.006844178307801485
2023-01-24 08:07:03.120698: step: 1860/533, loss: 0.008054911158978939
2023-01-24 08:07:04.205183: step: 1864/533, loss: 0.009468642994761467
2023-01-24 08:07:05.279644: step: 1868/533, loss: 0.0005204747430980206
2023-01-24 08:07:06.376516: step: 1872/533, loss: 0.007144060917198658
2023-01-24 08:07:07.452074: step: 1876/533, loss: 0.007820152677595615
2023-01-24 08:07:08.552878: step: 1880/533, loss: 1.852072455221787e-05
2023-01-24 08:07:09.639045: step: 1884/533, loss: 0.02055438421666622
2023-01-24 08:07:10.716654: step: 1888/533, loss: 0.005572780501097441
2023-01-24 08:07:11.792578: step: 1892/533, loss: 0.02796160615980625
2023-01-24 08:07:12.903888: step: 1896/533, loss: 0.029087990522384644
2023-01-24 08:07:14.031372: step: 1900/533, loss: 0.0018518344732001424
2023-01-24 08:07:15.125766: step: 1904/533, loss: 0.08440016955137253
2023-01-24 08:07:16.239993: step: 1908/533, loss: 0.032915063202381134
2023-01-24 08:07:17.324085: step: 1912/533, loss: 0.023450899869203568
2023-01-24 08:07:18.427059: step: 1916/533, loss: 0.007282149512320757
2023-01-24 08:07:19.501920: step: 1920/533, loss: 0.002920210827142
2023-01-24 08:07:20.597110: step: 1924/533, loss: 0.008617345243692398
2023-01-24 08:07:21.661627: step: 1928/533, loss: 0.0012135501019656658
2023-01-24 08:07:22.771981: step: 1932/533, loss: 0.004121087491512299
2023-01-24 08:07:23.849283: step: 1936/533, loss: 0.00879327766597271
2023-01-24 08:07:24.917745: step: 1940/533, loss: 0.02194022759795189
2023-01-24 08:07:26.000128: step: 1944/533, loss: 0.00814549345523119
2023-01-24 08:07:27.101793: step: 1948/533, loss: 0.021304121240973473
2023-01-24 08:07:28.188965: step: 1952/533, loss: 0.008557677268981934
2023-01-24 08:07:29.283889: step: 1956/533, loss: 0.0119905611500144
2023-01-24 08:07:30.370329: step: 1960/533, loss: 0.008927566930651665
2023-01-24 08:07:31.469297: step: 1964/533, loss: 0.0025087001267820597
2023-01-24 08:07:32.571691: step: 1968/533, loss: 0.0013108127750456333
2023-01-24 08:07:33.651536: step: 1972/533, loss: 0.0009924937039613724
2023-01-24 08:07:34.733861: step: 1976/533, loss: 0.0018065645126625896
2023-01-24 08:07:35.805802: step: 1980/533, loss: 0.03862901031970978
2023-01-24 08:07:36.914330: step: 1984/533, loss: 0.0031474733259528875
2023-01-24 08:07:38.029996: step: 1988/533, loss: 0.003286575200036168
2023-01-24 08:07:39.099198: step: 1992/533, loss: 0.012860802002251148
2023-01-24 08:07:40.188409: step: 1996/533, loss: 0.003689703531563282
2023-01-24 08:07:41.342148: step: 2000/533, loss: 0.007333775982260704
2023-01-24 08:07:42.435223: step: 2004/533, loss: 0.009007471613585949
2023-01-24 08:07:43.543547: step: 2008/533, loss: 0.03407568484544754
2023-01-24 08:07:44.641787: step: 2012/533, loss: 0.008431987836956978
2023-01-24 08:07:45.716644: step: 2016/533, loss: 0.011754711158573627
2023-01-24 08:07:46.785739: step: 2020/533, loss: 0.013363792560994625
2023-01-24 08:07:47.883213: step: 2024/533, loss: 0.008650312200188637
2023-01-24 08:07:48.989982: step: 2028/533, loss: 0.009226815775036812
2023-01-24 08:07:50.061472: step: 2032/533, loss: 0.010545005090534687
2023-01-24 08:07:51.137740: step: 2036/533, loss: 0.011040829122066498
2023-01-24 08:07:52.216252: step: 2040/533, loss: 0.0058244261890649796
2023-01-24 08:07:53.290808: step: 2044/533, loss: 0.007543090730905533
2023-01-24 08:07:54.381032: step: 2048/533, loss: 0.0005435586208477616
2023-01-24 08:07:55.483909: step: 2052/533, loss: 0.0020058746449649334
2023-01-24 08:07:56.595249: step: 2056/533, loss: 0.006126420572400093
2023-01-24 08:07:57.691618: step: 2060/533, loss: 0.003061454277485609
2023-01-24 08:07:58.788306: step: 2064/533, loss: 0.008496993221342564
2023-01-24 08:07:59.901530: step: 2068/533, loss: 0.01656826213002205
2023-01-24 08:08:01.008591: step: 2072/533, loss: 0.035908933728933334
2023-01-24 08:08:02.120369: step: 2076/533, loss: 0.027338489890098572
2023-01-24 08:08:03.178333: step: 2080/533, loss: 0.0037684012204408646
2023-01-24 08:08:04.256802: step: 2084/533, loss: 0.01840551756322384
2023-01-24 08:08:05.324194: step: 2088/533, loss: 0.009876434691250324
2023-01-24 08:08:06.435202: step: 2092/533, loss: 0.0009512269170954823
2023-01-24 08:08:07.511582: step: 2096/533, loss: 0.08871321380138397
2023-01-24 08:08:08.598960: step: 2100/533, loss: 0.061504628509283066
2023-01-24 08:08:09.702189: step: 2104/533, loss: 0.0020137433893978596
2023-01-24 08:08:10.831961: step: 2108/533, loss: 0.005197510123252869
2023-01-24 08:08:11.929490: step: 2112/533, loss: 1.8626450382086546e-09
2023-01-24 08:08:13.043546: step: 2116/533, loss: 0.020732207223773003
2023-01-24 08:08:14.119013: step: 2120/533, loss: 0.00786447711288929
2023-01-24 08:08:15.204462: step: 2124/533, loss: 0.057812418788671494
2023-01-24 08:08:16.294233: step: 2128/533, loss: 0.03479022905230522
2023-01-24 08:08:17.381780: step: 2132/533, loss: 0.01223223377019167
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3802196804647785, 'r': 0.33115907653383936, 'f1': 0.3539976335361731}, 'combined': 0.26084036155296964, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39334525490419053, 'r': 0.35779289532631176, 'f1': 0.3747277050748884}, 'combined': 0.24981847004992555, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3563806346008562, 'r': 0.3212159420026693, 'f1': 0.33788583120839666}, 'combined': 0.248968507206187, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3858378754629788, 'r': 0.30570231671297554, 'f1': 0.34112704869259075}, 'combined': 0.22741803246172712, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3389169730392157, 'r': 0.30869098113628757, 'f1': 0.32309860389041417}, 'combined': 0.2380726554981999, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3785430968327237, 'r': 0.34432862461899677, 'f1': 0.3606261526724639}, 'combined': 0.24041743511497587, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 4}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661572385213968, 'r': 0.3216903253043771, 'f1': 0.34248646754627615}, 'combined': 0.2523584497709403, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38773270130457727, 'r': 0.30906770132836014, 'f1': 0.34395977461904176}, 'combined': 0.22930651641269445, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 08:10:36.248722: step: 4/533, loss: 0.0007551109883934259
2023-01-24 08:10:37.339990: step: 8/533, loss: 0.009131946600973606
2023-01-24 08:10:38.448512: step: 12/533, loss: 0.006865665782243013
2023-01-24 08:10:39.556037: step: 16/533, loss: 0.002961123827844858
2023-01-24 08:10:40.649087: step: 20/533, loss: 0.008520145900547504
2023-01-24 08:10:41.709243: step: 24/533, loss: 0.006750363390892744
2023-01-24 08:10:42.798492: step: 28/533, loss: 0.008328010328114033
2023-01-24 08:10:43.905710: step: 32/533, loss: 0.010191800072789192
2023-01-24 08:10:45.000050: step: 36/533, loss: 0.007571295835077763
2023-01-24 08:10:46.086155: step: 40/533, loss: 0.0084233982488513
2023-01-24 08:10:47.158237: step: 44/533, loss: 0.007606784347444773
2023-01-24 08:10:48.242946: step: 48/533, loss: 0.01564018987119198
2023-01-24 08:10:49.347393: step: 52/533, loss: 0.010779350996017456
2023-01-24 08:10:50.462467: step: 56/533, loss: 0.05301357060670853
2023-01-24 08:10:51.538133: step: 60/533, loss: 0.0072830128483474255
2023-01-24 08:10:52.628333: step: 64/533, loss: 0.01075737364590168
2023-01-24 08:10:53.716002: step: 68/533, loss: 0.0063059888780117035
2023-01-24 08:10:54.816594: step: 72/533, loss: 0.012445087544620037
2023-01-24 08:10:55.904087: step: 76/533, loss: 0.0593702495098114
2023-01-24 08:10:56.979390: step: 80/533, loss: 0.01368139311671257
2023-01-24 08:10:58.082420: step: 84/533, loss: 0.003547293832525611
2023-01-24 08:10:59.173503: step: 88/533, loss: 0.007324452046304941
2023-01-24 08:11:00.247450: step: 92/533, loss: 0.007374919950962067
2023-01-24 08:11:01.321182: step: 96/533, loss: 0.00013728153135161847
2023-01-24 08:11:02.398430: step: 100/533, loss: 0.0030247271060943604
2023-01-24 08:11:03.480775: step: 104/533, loss: 0.01076459139585495
2023-01-24 08:11:04.556616: step: 108/533, loss: 0.016691410914063454
2023-01-24 08:11:05.676210: step: 112/533, loss: 0.004396319855004549
2023-01-24 08:11:06.757446: step: 116/533, loss: 0.014012383297085762
2023-01-24 08:11:07.886548: step: 120/533, loss: 0.004451670218259096
2023-01-24 08:11:08.979517: step: 124/533, loss: 0.004460465162992477
2023-01-24 08:11:10.060927: step: 128/533, loss: 0.0067672887817025185
2023-01-24 08:11:11.165375: step: 132/533, loss: 0.029781276360154152
2023-01-24 08:11:12.254104: step: 136/533, loss: 0.008580082096159458
2023-01-24 08:11:13.361665: step: 140/533, loss: 0.00997120514512062
2023-01-24 08:11:14.450939: step: 144/533, loss: 0.0036679820623248816
2023-01-24 08:11:15.538884: step: 148/533, loss: 0.010006271302700043
2023-01-24 08:11:16.618327: step: 152/533, loss: 0.003410019213333726
2023-01-24 08:11:17.709831: step: 156/533, loss: 0.007201639469712973
2023-01-24 08:11:18.789556: step: 160/533, loss: 0.006598993204534054
2023-01-24 08:11:19.866118: step: 164/533, loss: 0.0051563810557127
2023-01-24 08:11:20.942277: step: 168/533, loss: 0.000999772222712636
2023-01-24 08:11:22.048821: step: 172/533, loss: 0.0051381755620241165
2023-01-24 08:11:23.149873: step: 176/533, loss: 0.004783525597304106
2023-01-24 08:11:24.239366: step: 180/533, loss: 0.011992523446679115
2023-01-24 08:11:25.331051: step: 184/533, loss: 0.0024093957617878914
2023-01-24 08:11:26.417832: step: 188/533, loss: 0.009371072053909302
2023-01-24 08:11:27.515851: step: 192/533, loss: 0.04988864064216614
2023-01-24 08:11:28.598150: step: 196/533, loss: 0.00402576569467783
2023-01-24 08:11:29.701965: step: 200/533, loss: 0.01821981929242611
2023-01-24 08:11:30.776705: step: 204/533, loss: 0.002901453524827957
2023-01-24 08:11:31.860749: step: 208/533, loss: 0.015090865083038807
2023-01-24 08:11:32.955154: step: 212/533, loss: 0.008486540988087654
2023-01-24 08:11:34.035829: step: 216/533, loss: 0.07841666042804718
2023-01-24 08:11:35.112725: step: 220/533, loss: 0.001086511299945414
2023-01-24 08:11:36.193545: step: 224/533, loss: 0.003243681276217103
2023-01-24 08:11:37.294972: step: 228/533, loss: 0.04481763392686844
2023-01-24 08:11:38.379135: step: 232/533, loss: 0.02366301603615284
2023-01-24 08:11:39.464858: step: 236/533, loss: 0.019568853080272675
2023-01-24 08:11:40.575044: step: 240/533, loss: 0.010225391015410423
2023-01-24 08:11:41.662924: step: 244/533, loss: 0.01111523900181055
2023-01-24 08:11:42.771203: step: 248/533, loss: 0.015461784787476063
2023-01-24 08:11:43.860617: step: 252/533, loss: 0.003268641186878085
2023-01-24 08:11:44.937140: step: 256/533, loss: 0.0021661315113306046
2023-01-24 08:11:46.024278: step: 260/533, loss: 0.01108383946120739
2023-01-24 08:11:47.104764: step: 264/533, loss: 0.0048946719616651535
2023-01-24 08:11:48.179951: step: 268/533, loss: 0.004755276255309582
2023-01-24 08:11:49.251030: step: 272/533, loss: 0.002824681345373392
2023-01-24 08:11:50.351534: step: 276/533, loss: 0.00028676027432084084
2023-01-24 08:11:51.435591: step: 280/533, loss: 0.014417405240237713
2023-01-24 08:11:52.525695: step: 284/533, loss: 0.004882168024778366
2023-01-24 08:11:53.652352: step: 288/533, loss: 0.0469631664454937
2023-01-24 08:11:54.749680: step: 292/533, loss: 0.003423175308853388
2023-01-24 08:11:55.834048: step: 296/533, loss: 0.009292228147387505
2023-01-24 08:11:56.908437: step: 300/533, loss: 0.0017952942289412022
2023-01-24 08:11:58.004455: step: 304/533, loss: 0.013330611400306225
2023-01-24 08:11:59.078647: step: 308/533, loss: 0.001183902844786644
2023-01-24 08:12:00.173836: step: 312/533, loss: 0.02030462957918644
2023-01-24 08:12:01.259273: step: 316/533, loss: 0.0080390190705657
2023-01-24 08:12:02.366747: step: 320/533, loss: 0.02139441668987274
2023-01-24 08:12:03.478779: step: 324/533, loss: 0.008822084404528141
2023-01-24 08:12:04.563477: step: 328/533, loss: 0.01829041913151741
2023-01-24 08:12:05.669863: step: 332/533, loss: 0.004993399139493704
2023-01-24 08:12:06.790361: step: 336/533, loss: 0.07752680778503418
2023-01-24 08:12:07.871779: step: 340/533, loss: 0.009331941604614258
2023-01-24 08:12:08.967994: step: 344/533, loss: 0.0038133293855935335
2023-01-24 08:12:10.064353: step: 348/533, loss: 0.006413063500076532
2023-01-24 08:12:11.155928: step: 352/533, loss: 0.019196489825844765
2023-01-24 08:12:12.228664: step: 356/533, loss: 0.005220616236329079
2023-01-24 08:12:13.305624: step: 360/533, loss: 0.014016113243997097
2023-01-24 08:12:14.425438: step: 364/533, loss: 0.015840046107769012
2023-01-24 08:12:15.507445: step: 368/533, loss: 0.03182314336299896
2023-01-24 08:12:16.606113: step: 372/533, loss: 0.009287862107157707
2023-01-24 08:12:17.696415: step: 376/533, loss: 0.006681022699922323
2023-01-24 08:12:18.788102: step: 380/533, loss: 0.021675948053598404
2023-01-24 08:12:19.866028: step: 384/533, loss: 0.0025858336593955755
2023-01-24 08:12:20.945841: step: 388/533, loss: 0.012044733390212059
2023-01-24 08:12:22.021099: step: 392/533, loss: 0.003693317761644721
2023-01-24 08:12:23.104678: step: 396/533, loss: 0.025676537305116653
2023-01-24 08:12:24.202658: step: 400/533, loss: 0.0011439429363235831
2023-01-24 08:12:25.302190: step: 404/533, loss: 0.004564960487186909
2023-01-24 08:12:26.395649: step: 408/533, loss: 0.002120059682056308
2023-01-24 08:12:27.511182: step: 412/533, loss: 0.01261175237596035
2023-01-24 08:12:28.607102: step: 416/533, loss: 0.003792945761233568
2023-01-24 08:12:29.686081: step: 420/533, loss: 0.00949700828641653
2023-01-24 08:12:30.771856: step: 424/533, loss: 0.0016378756845369935
2023-01-24 08:12:31.878356: step: 428/533, loss: 0.014885187149047852
2023-01-24 08:12:32.967342: step: 432/533, loss: 0.005739917978644371
2023-01-24 08:12:34.069623: step: 436/533, loss: 0.0018585376674309373
2023-01-24 08:12:35.171617: step: 440/533, loss: 0.003024968085810542
2023-01-24 08:12:36.249024: step: 444/533, loss: 0.01498447172343731
2023-01-24 08:12:37.315835: step: 448/533, loss: 0.006435797084122896
2023-01-24 08:12:38.407398: step: 452/533, loss: 0.02514447644352913
2023-01-24 08:12:39.507519: step: 456/533, loss: 0.030124597251415253
2023-01-24 08:12:40.585227: step: 460/533, loss: 0.0048998580314219
2023-01-24 08:12:41.661802: step: 464/533, loss: 0.00821394007652998
2023-01-24 08:12:42.746810: step: 468/533, loss: 0.0054454621858894825
2023-01-24 08:12:43.829491: step: 472/533, loss: 0.0
2023-01-24 08:12:44.913641: step: 476/533, loss: 0.004547933116555214
2023-01-24 08:12:46.021868: step: 480/533, loss: 0.006784550845623016
2023-01-24 08:12:47.095931: step: 484/533, loss: 0.00262479018419981
2023-01-24 08:12:48.197258: step: 488/533, loss: 0.012091008946299553
2023-01-24 08:12:49.296286: step: 492/533, loss: 0.03988064453005791
2023-01-24 08:12:50.375845: step: 496/533, loss: 0.006687619723379612
2023-01-24 08:12:51.460225: step: 500/533, loss: 0.004328427370637655
2023-01-24 08:12:52.546740: step: 504/533, loss: 0.001687680371105671
2023-01-24 08:12:53.618820: step: 508/533, loss: 0.004831582307815552
2023-01-24 08:12:54.719047: step: 512/533, loss: 0.007520508486777544
2023-01-24 08:12:55.825694: step: 516/533, loss: 0.004362734034657478
2023-01-24 08:12:56.925704: step: 520/533, loss: 0.011355751194059849
2023-01-24 08:12:58.004309: step: 524/533, loss: 0.006438610143959522
2023-01-24 08:12:59.099843: step: 528/533, loss: 0.001572894980199635
2023-01-24 08:13:00.214268: step: 532/533, loss: 0.0168845746666193
2023-01-24 08:13:01.297000: step: 536/533, loss: 0.0033984382171183825
2023-01-24 08:13:02.382181: step: 540/533, loss: 0.004026008304208517
2023-01-24 08:13:03.464067: step: 544/533, loss: 0.08271807432174683
2023-01-24 08:13:04.536265: step: 548/533, loss: 0.0
2023-01-24 08:13:05.622826: step: 552/533, loss: 0.022685714066028595
2023-01-24 08:13:06.697846: step: 556/533, loss: 0.0035779932513833046
2023-01-24 08:13:07.781279: step: 560/533, loss: 0.014204185456037521
2023-01-24 08:13:08.858629: step: 564/533, loss: 0.004578195512294769
2023-01-24 08:13:09.948762: step: 568/533, loss: 0.0026493913028389215
2023-01-24 08:13:11.021494: step: 572/533, loss: 0.01879737339913845
2023-01-24 08:13:12.124055: step: 576/533, loss: 0.008209940046072006
2023-01-24 08:13:13.214911: step: 580/533, loss: 2.7603438866208307e-05
2023-01-24 08:13:14.287912: step: 584/533, loss: 0.002565101021900773
2023-01-24 08:13:15.386276: step: 588/533, loss: 0.012940261512994766
2023-01-24 08:13:16.495875: step: 592/533, loss: 0.01265196967869997
2023-01-24 08:13:17.570954: step: 596/533, loss: 0.03662845119833946
2023-01-24 08:13:18.654388: step: 600/533, loss: 0.05154214799404144
2023-01-24 08:13:19.721308: step: 604/533, loss: 0.00671547744423151
2023-01-24 08:13:20.801400: step: 608/533, loss: 0.09750492870807648
2023-01-24 08:13:21.892662: step: 612/533, loss: 0.0025679757818579674
2023-01-24 08:13:22.948186: step: 616/533, loss: 0.01318467315286398
2023-01-24 08:13:24.045819: step: 620/533, loss: 0.004093879833817482
2023-01-24 08:13:25.133886: step: 624/533, loss: 0.00793090183287859
2023-01-24 08:13:26.214929: step: 628/533, loss: 0.018158812075853348
2023-01-24 08:13:27.339987: step: 632/533, loss: 0.0008498517563566566
2023-01-24 08:13:28.403207: step: 636/533, loss: 0.004989811219274998
2023-01-24 08:13:29.489632: step: 640/533, loss: 0.012738947756588459
2023-01-24 08:13:30.611267: step: 644/533, loss: 0.011965632438659668
2023-01-24 08:13:31.692073: step: 648/533, loss: 0.0150686576962471
2023-01-24 08:13:32.791070: step: 652/533, loss: 0.010413565672934055
2023-01-24 08:13:33.887882: step: 656/533, loss: 0.0038079784717410803
2023-01-24 08:13:34.971561: step: 660/533, loss: 0.004775348585098982
2023-01-24 08:13:36.045346: step: 664/533, loss: 0.009004087187349796
2023-01-24 08:13:37.157892: step: 668/533, loss: 0.02605695277452469
2023-01-24 08:13:38.233560: step: 672/533, loss: 0.005324473604559898
2023-01-24 08:13:39.310026: step: 676/533, loss: 0.01214715838432312
2023-01-24 08:13:40.390255: step: 680/533, loss: 0.0076166680082678795
2023-01-24 08:13:41.483444: step: 684/533, loss: 0.008222264237701893
2023-01-24 08:13:42.569001: step: 688/533, loss: 0.008068449795246124
2023-01-24 08:13:43.708606: step: 692/533, loss: 0.007884918712079525
2023-01-24 08:13:44.778120: step: 696/533, loss: 0.005655281245708466
2023-01-24 08:13:45.874945: step: 700/533, loss: 7.599528117907539e-08
2023-01-24 08:13:46.971291: step: 704/533, loss: 0.00448933569714427
2023-01-24 08:13:48.093181: step: 708/533, loss: 0.0017199950525537133
2023-01-24 08:13:49.174420: step: 712/533, loss: 0.006901200395077467
2023-01-24 08:13:50.264649: step: 716/533, loss: 0.007201744243502617
2023-01-24 08:13:51.357367: step: 720/533, loss: 0.007238611578941345
2023-01-24 08:13:52.475174: step: 724/533, loss: 0.004089057445526123
2023-01-24 08:13:53.567486: step: 728/533, loss: 0.0018101702444255352
2023-01-24 08:13:54.672516: step: 732/533, loss: 0.01639533042907715
2023-01-24 08:13:55.743739: step: 736/533, loss: 0.04284370690584183
2023-01-24 08:13:56.829468: step: 740/533, loss: 0.0013677622191607952
2023-01-24 08:13:57.901092: step: 744/533, loss: 0.01772523857653141
2023-01-24 08:13:58.999506: step: 748/533, loss: 0.007380790077149868
2023-01-24 08:14:00.085218: step: 752/533, loss: 0.010165845975279808
2023-01-24 08:14:01.217026: step: 756/533, loss: 0.0005097741959616542
2023-01-24 08:14:02.298944: step: 760/533, loss: 0.01813513971865177
2023-01-24 08:14:03.404830: step: 764/533, loss: 0.055379778146743774
2023-01-24 08:14:04.480077: step: 768/533, loss: 0.0031746630556881428
2023-01-24 08:14:05.566905: step: 772/533, loss: 0.0015801142435520887
2023-01-24 08:14:06.653558: step: 776/533, loss: 0.008942753076553345
2023-01-24 08:14:07.733254: step: 780/533, loss: 0.005612513516098261
2023-01-24 08:14:08.834976: step: 784/533, loss: 0.004932578653097153
2023-01-24 08:14:09.932094: step: 788/533, loss: 0.010133543983101845
2023-01-24 08:14:11.020267: step: 792/533, loss: 0.01880340836942196
2023-01-24 08:14:12.107295: step: 796/533, loss: 0.0237873587757349
2023-01-24 08:14:13.190785: step: 800/533, loss: 0.0036403308622539043
2023-01-24 08:14:14.306636: step: 804/533, loss: 0.009461178444325924
2023-01-24 08:14:15.429713: step: 808/533, loss: 0.03249937295913696
2023-01-24 08:14:16.523849: step: 812/533, loss: 0.0040216906927526
2023-01-24 08:14:17.629190: step: 816/533, loss: 0.010346551425755024
2023-01-24 08:14:18.749414: step: 820/533, loss: 0.005972577258944511
2023-01-24 08:14:19.833234: step: 824/533, loss: 0.0062993247993290424
2023-01-24 08:14:20.956529: step: 828/533, loss: 0.010317746549844742
2023-01-24 08:14:22.046890: step: 832/533, loss: 0.0007205819711089134
2023-01-24 08:14:23.132203: step: 836/533, loss: 0.002655689138919115
2023-01-24 08:14:24.233568: step: 840/533, loss: 0.01409895345568657
2023-01-24 08:14:25.317889: step: 844/533, loss: 0.008418608456850052
2023-01-24 08:14:26.440595: step: 848/533, loss: 0.012787293642759323
2023-01-24 08:14:27.520146: step: 852/533, loss: 0.006266147363930941
2023-01-24 08:14:28.594776: step: 856/533, loss: 0.009576423093676567
2023-01-24 08:14:29.694696: step: 860/533, loss: 0.0016222902340814471
2023-01-24 08:14:30.806393: step: 864/533, loss: 0.01291507575660944
2023-01-24 08:14:31.897090: step: 868/533, loss: 0.04869794100522995
2023-01-24 08:14:32.998911: step: 872/533, loss: 0.0008633933030068874
2023-01-24 08:14:34.078742: step: 876/533, loss: 0.0043952674604952335
2023-01-24 08:14:35.183140: step: 880/533, loss: 0.003307093633338809
2023-01-24 08:14:36.277335: step: 884/533, loss: 0.027536166831851006
2023-01-24 08:14:37.362147: step: 888/533, loss: 0.004719241987913847
2023-01-24 08:14:38.448200: step: 892/533, loss: 0.01783471554517746
2023-01-24 08:14:39.564574: step: 896/533, loss: 0.029167108237743378
2023-01-24 08:14:40.682308: step: 900/533, loss: 0.051411792635917664
2023-01-24 08:14:41.814650: step: 904/533, loss: 0.0011303196661174297
2023-01-24 08:14:42.898962: step: 908/533, loss: 0.0072664725594222546
2023-01-24 08:14:43.993023: step: 912/533, loss: 0.09090390056371689
2023-01-24 08:14:45.085396: step: 916/533, loss: 0.007610222324728966
2023-01-24 08:14:46.178576: step: 920/533, loss: 0.0030238484032452106
2023-01-24 08:14:47.304422: step: 924/533, loss: 0.013914983719587326
2023-01-24 08:14:48.418619: step: 928/533, loss: 0.0053182137198746204
2023-01-24 08:14:49.499048: step: 932/533, loss: 0.0072957915253937244
2023-01-24 08:14:50.624697: step: 936/533, loss: 0.0030679546762257814
2023-01-24 08:14:51.789349: step: 940/533, loss: 0.006759508512914181
2023-01-24 08:14:52.879335: step: 944/533, loss: 0.04646512120962143
2023-01-24 08:14:53.975456: step: 948/533, loss: 0.006401832681149244
2023-01-24 08:14:55.066707: step: 952/533, loss: 0.02256207913160324
2023-01-24 08:14:56.162036: step: 956/533, loss: 0.005829138215631247
2023-01-24 08:14:57.249815: step: 960/533, loss: 0.0047987885773181915
2023-01-24 08:14:58.352921: step: 964/533, loss: 0.00843134056776762
2023-01-24 08:14:59.461089: step: 968/533, loss: 0.0028845462948083878
2023-01-24 08:15:00.575878: step: 972/533, loss: 0.017788851633667946
2023-01-24 08:15:01.677247: step: 976/533, loss: 0.016036653891205788
2023-01-24 08:15:02.779387: step: 980/533, loss: 0.03561963513493538
2023-01-24 08:15:03.875032: step: 984/533, loss: 0.007881824858486652
2023-01-24 08:15:04.957591: step: 988/533, loss: 0.006367035675793886
2023-01-24 08:15:06.046831: step: 992/533, loss: 0.01699044555425644
2023-01-24 08:15:07.142903: step: 996/533, loss: 0.01269744336605072
2023-01-24 08:15:08.238101: step: 1000/533, loss: 0.01384057104587555
2023-01-24 08:15:09.339391: step: 1004/533, loss: 0.015242956578731537
2023-01-24 08:15:10.448674: step: 1008/533, loss: 0.003861885517835617
2023-01-24 08:15:11.542344: step: 1012/533, loss: 0.006242334842681885
2023-01-24 08:15:12.645088: step: 1016/533, loss: 0.015875181183218956
2023-01-24 08:15:13.728697: step: 1020/533, loss: 0.012970470823347569
2023-01-24 08:15:14.806287: step: 1024/533, loss: 0.007985343225300312
2023-01-24 08:15:15.926267: step: 1028/533, loss: 0.02278217114508152
2023-01-24 08:15:17.009138: step: 1032/533, loss: 0.005219914950430393
2023-01-24 08:15:18.099013: step: 1036/533, loss: 0.010149966925382614
2023-01-24 08:15:19.197864: step: 1040/533, loss: 0.024402273818850517
2023-01-24 08:15:20.312139: step: 1044/533, loss: 0.017547093331813812
2023-01-24 08:15:21.405193: step: 1048/533, loss: 0.002070634625852108
2023-01-24 08:15:22.513907: step: 1052/533, loss: 0.004792963620275259
2023-01-24 08:15:23.617916: step: 1056/533, loss: 0.00537159712985158
2023-01-24 08:15:24.720069: step: 1060/533, loss: 0.007971642538905144
2023-01-24 08:15:25.863612: step: 1064/533, loss: 0.01195265632122755
2023-01-24 08:15:26.978346: step: 1068/533, loss: 0.00710755679756403
2023-01-24 08:15:28.073045: step: 1072/533, loss: 0.0015213295118883252
2023-01-24 08:15:29.160014: step: 1076/533, loss: 0.011571662500500679
2023-01-24 08:15:30.259715: step: 1080/533, loss: 0.01009734533727169
2023-01-24 08:15:31.350151: step: 1084/533, loss: 0.04460177198052406
2023-01-24 08:15:32.458886: step: 1088/533, loss: 0.05456147715449333
2023-01-24 08:15:33.559911: step: 1092/533, loss: 0.006602631416171789
2023-01-24 08:15:34.636705: step: 1096/533, loss: 0.0034087791573256254
2023-01-24 08:15:35.733618: step: 1100/533, loss: 0.009997441433370113
2023-01-24 08:15:36.820016: step: 1104/533, loss: 0.004041710402816534
2023-01-24 08:15:37.907385: step: 1108/533, loss: 0.0009225867688655853
2023-01-24 08:15:38.999506: step: 1112/533, loss: 0.004119543358683586
2023-01-24 08:15:40.109682: step: 1116/533, loss: 0.01776583306491375
2023-01-24 08:15:41.201392: step: 1120/533, loss: 0.00242403126321733
2023-01-24 08:15:42.298578: step: 1124/533, loss: 0.027964867651462555
2023-01-24 08:15:43.400878: step: 1128/533, loss: 0.020853832364082336
2023-01-24 08:15:44.508405: step: 1132/533, loss: 0.0012194177834317088
2023-01-24 08:15:45.600942: step: 1136/533, loss: 0.0027888696640729904
2023-01-24 08:15:46.687217: step: 1140/533, loss: 0.014469102025032043
2023-01-24 08:15:47.791852: step: 1144/533, loss: 0.004536394961178303
2023-01-24 08:15:48.884725: step: 1148/533, loss: 0.006887476425617933
2023-01-24 08:15:49.987733: step: 1152/533, loss: 0.0057589211501181126
2023-01-24 08:15:51.070855: step: 1156/533, loss: 0.0023355635348707438
2023-01-24 08:15:52.182191: step: 1160/533, loss: 0.010729964822530746
2023-01-24 08:15:53.278355: step: 1164/533, loss: 0.003621844807639718
2023-01-24 08:15:54.375378: step: 1168/533, loss: 0.006075295154005289
2023-01-24 08:15:55.448731: step: 1172/533, loss: 0.008334466256201267
2023-01-24 08:15:56.546723: step: 1176/533, loss: 0.02813330665230751
2023-01-24 08:15:57.651607: step: 1180/533, loss: 0.002646566601470113
2023-01-24 08:15:58.746772: step: 1184/533, loss: 0.003045485122129321
2023-01-24 08:15:59.848917: step: 1188/533, loss: 0.002894983859732747
2023-01-24 08:16:00.927095: step: 1192/533, loss: 0.013667531311511993
2023-01-24 08:16:02.027574: step: 1196/533, loss: 0.016994155943393707
2023-01-24 08:16:03.109775: step: 1200/533, loss: 0.007841471582651138
2023-01-24 08:16:04.186691: step: 1204/533, loss: 0.0022775083780288696
2023-01-24 08:16:05.268526: step: 1208/533, loss: 0.007749130018055439
2023-01-24 08:16:06.367006: step: 1212/533, loss: 0.01659064181149006
2023-01-24 08:16:07.454186: step: 1216/533, loss: 0.004767129663378
2023-01-24 08:16:08.557962: step: 1220/533, loss: 0.025283457711338997
2023-01-24 08:16:09.634733: step: 1224/533, loss: 0.001398331020027399
2023-01-24 08:16:10.731524: step: 1228/533, loss: 0.004438719246536493
2023-01-24 08:16:11.832041: step: 1232/533, loss: 0.004003491718322039
2023-01-24 08:16:12.930259: step: 1236/533, loss: 0.008333342149853706
2023-01-24 08:16:14.008991: step: 1240/533, loss: 0.005376702640205622
2023-01-24 08:16:15.091820: step: 1244/533, loss: 0.003026180434972048
2023-01-24 08:16:16.179546: step: 1248/533, loss: 0.003610180923715234
2023-01-24 08:16:17.252591: step: 1252/533, loss: 0.006409183610230684
2023-01-24 08:16:18.333767: step: 1256/533, loss: 0.0012000921415165067
2023-01-24 08:16:19.417484: step: 1260/533, loss: 0.0028714321088045835
2023-01-24 08:16:20.521481: step: 1264/533, loss: 0.030790209770202637
2023-01-24 08:16:21.592449: step: 1268/533, loss: 0.006383778527379036
2023-01-24 08:16:22.700380: step: 1272/533, loss: 0.009273141622543335
2023-01-24 08:16:23.802996: step: 1276/533, loss: 0.01485514733940363
2023-01-24 08:16:24.922104: step: 1280/533, loss: 0.05400495603680611
2023-01-24 08:16:26.021899: step: 1284/533, loss: 0.03348050266504288
2023-01-24 08:16:27.126607: step: 1288/533, loss: 0.01482237409800291
2023-01-24 08:16:28.196376: step: 1292/533, loss: 0.0024793152697384357
2023-01-24 08:16:29.298925: step: 1296/533, loss: 0.011894671246409416
2023-01-24 08:16:30.387589: step: 1300/533, loss: 0.0010026311501860619
2023-01-24 08:16:31.471612: step: 1304/533, loss: 0.0018173770513385534
2023-01-24 08:16:32.581247: step: 1308/533, loss: 0.003887358820065856
2023-01-24 08:16:33.679077: step: 1312/533, loss: 0.01800333522260189
2023-01-24 08:16:34.778492: step: 1316/533, loss: 0.013860628008842468
2023-01-24 08:16:35.852537: step: 1320/533, loss: 0.012722854502499104
2023-01-24 08:16:36.947929: step: 1324/533, loss: 0.005807468667626381
2023-01-24 08:16:38.060863: step: 1328/533, loss: 0.02572508715093136
2023-01-24 08:16:39.172692: step: 1332/533, loss: 0.012476389296352863
2023-01-24 08:16:40.271460: step: 1336/533, loss: 0.0187993086874485
2023-01-24 08:16:41.367890: step: 1340/533, loss: 0.009972560219466686
2023-01-24 08:16:42.461241: step: 1344/533, loss: 0.054831624031066895
2023-01-24 08:16:43.564560: step: 1348/533, loss: 0.0006232161540538073
2023-01-24 08:16:44.688423: step: 1352/533, loss: 0.0024109482765197754
2023-01-24 08:16:45.782910: step: 1356/533, loss: 0.0016754211392253637
2023-01-24 08:16:46.866875: step: 1360/533, loss: 0.004227450117468834
2023-01-24 08:16:47.962652: step: 1364/533, loss: 0.0017481001559644938
2023-01-24 08:16:49.061530: step: 1368/533, loss: 0.010335489176213741
2023-01-24 08:16:50.206649: step: 1372/533, loss: 0.0208204984664917
2023-01-24 08:16:51.306236: step: 1376/533, loss: 0.006125627551227808
2023-01-24 08:16:52.428652: step: 1380/533, loss: 0.012600325979292393
2023-01-24 08:16:53.526108: step: 1384/533, loss: 0.0057562366127967834
2023-01-24 08:16:54.600832: step: 1388/533, loss: 0.005263154394924641
2023-01-24 08:16:55.721400: step: 1392/533, loss: 0.013659077696502209
2023-01-24 08:16:56.818651: step: 1396/533, loss: 0.006890839897096157
2023-01-24 08:16:57.910608: step: 1400/533, loss: 0.016358209773898125
2023-01-24 08:16:59.011910: step: 1404/533, loss: 0.003469881135970354
2023-01-24 08:17:00.116240: step: 1408/533, loss: 0.014844954945147038
2023-01-24 08:17:01.208192: step: 1412/533, loss: 0.021121418103575706
2023-01-24 08:17:02.276990: step: 1416/533, loss: 0.01531422883272171
2023-01-24 08:17:03.345852: step: 1420/533, loss: 0.01510761957615614
2023-01-24 08:17:04.427627: step: 1424/533, loss: 0.001659837202169001
2023-01-24 08:17:05.505677: step: 1428/533, loss: 0.0030489119235426188
2023-01-24 08:17:06.610833: step: 1432/533, loss: 0.002888002432882786
2023-01-24 08:17:07.692839: step: 1436/533, loss: 0.0025662321131676435
2023-01-24 08:17:08.782699: step: 1440/533, loss: 0.011100434698164463
2023-01-24 08:17:09.855051: step: 1444/533, loss: 0.008652008138597012
2023-01-24 08:17:10.927717: step: 1448/533, loss: 0.004274295177310705
2023-01-24 08:17:12.011032: step: 1452/533, loss: 0.002951131435111165
2023-01-24 08:17:13.109700: step: 1456/533, loss: 0.005508929491043091
2023-01-24 08:17:14.206843: step: 1460/533, loss: 0.004893087316304445
2023-01-24 08:17:15.314808: step: 1464/533, loss: 0.031034359708428383
2023-01-24 08:17:16.402184: step: 1468/533, loss: 0.009330875240266323
2023-01-24 08:17:17.495059: step: 1472/533, loss: 0.002547855954617262
2023-01-24 08:17:18.581398: step: 1476/533, loss: 0.017821015790104866
2023-01-24 08:17:19.683158: step: 1480/533, loss: 0.0032664756290614605
2023-01-24 08:17:20.813164: step: 1484/533, loss: 0.08953147381544113
2023-01-24 08:17:21.903845: step: 1488/533, loss: 0.012028161436319351
2023-01-24 08:17:22.988669: step: 1492/533, loss: 0.009311381727457047
2023-01-24 08:17:24.088786: step: 1496/533, loss: 0.009731288067996502
2023-01-24 08:17:25.167274: step: 1500/533, loss: 0.009244767017662525
2023-01-24 08:17:26.262415: step: 1504/533, loss: 0.021575085818767548
2023-01-24 08:17:27.361747: step: 1508/533, loss: 0.0067066713236272335
2023-01-24 08:17:28.421470: step: 1512/533, loss: 0.007125556468963623
2023-01-24 08:17:29.497864: step: 1516/533, loss: 0.0044940863735973835
2023-01-24 08:17:30.587610: step: 1520/533, loss: 0.0008360797655768692
2023-01-24 08:17:31.669076: step: 1524/533, loss: 0.012486093677580357
2023-01-24 08:17:32.778947: step: 1528/533, loss: 0.013509373180568218
2023-01-24 08:17:33.878019: step: 1532/533, loss: 0.005887346342206001
2023-01-24 08:17:34.955824: step: 1536/533, loss: 0.0015015056123957038
2023-01-24 08:17:36.036121: step: 1540/533, loss: 0.03592641279101372
2023-01-24 08:17:37.150475: step: 1544/533, loss: 0.00670719426125288
2023-01-24 08:17:38.231592: step: 1548/533, loss: 0.0038861618377268314
2023-01-24 08:17:39.342197: step: 1552/533, loss: 0.007190596777945757
2023-01-24 08:17:40.459938: step: 1556/533, loss: 0.0038659535348415375
2023-01-24 08:17:41.549870: step: 1560/533, loss: 0.03024999424815178
2023-01-24 08:17:42.627853: step: 1564/533, loss: 0.006581324618309736
2023-01-24 08:17:43.719600: step: 1568/533, loss: 0.0016658571548759937
2023-01-24 08:17:44.821853: step: 1572/533, loss: 0.005830282345414162
2023-01-24 08:17:45.911601: step: 1576/533, loss: 0.02194531448185444
2023-01-24 08:17:47.032318: step: 1580/533, loss: 0.025519341230392456
2023-01-24 08:17:48.141107: step: 1584/533, loss: 0.024048345163464546
2023-01-24 08:17:49.240016: step: 1588/533, loss: 0.006131421308964491
2023-01-24 08:17:50.333144: step: 1592/533, loss: 0.0562850758433342
2023-01-24 08:17:51.422390: step: 1596/533, loss: 0.006182355340570211
2023-01-24 08:17:52.504885: step: 1600/533, loss: 0.0062120635993778706
2023-01-24 08:17:53.573752: step: 1604/533, loss: 0.012998807244002819
2023-01-24 08:17:54.678488: step: 1608/533, loss: 0.0055077821016311646
2023-01-24 08:17:55.767185: step: 1612/533, loss: 0.032626401633024216
2023-01-24 08:17:56.864440: step: 1616/533, loss: 0.03618546947836876
2023-01-24 08:17:57.936965: step: 1620/533, loss: 0.0005495875957421958
2023-01-24 08:17:59.017860: step: 1624/533, loss: 0.011219627223908901
2023-01-24 08:18:00.120102: step: 1628/533, loss: 0.001955438405275345
2023-01-24 08:18:01.203920: step: 1632/533, loss: 0.004372759256511927
2023-01-24 08:18:02.319216: step: 1636/533, loss: 0.03696160018444061
2023-01-24 08:18:03.422834: step: 1640/533, loss: 0.02016080729663372
2023-01-24 08:18:04.522502: step: 1644/533, loss: 0.00342387892305851
2023-01-24 08:18:05.624034: step: 1648/533, loss: 0.028682585805654526
2023-01-24 08:18:06.704597: step: 1652/533, loss: 0.0019071135902777314
2023-01-24 08:18:07.797787: step: 1656/533, loss: 0.00048230349784716964
2023-01-24 08:18:08.872349: step: 1660/533, loss: 0.006506726145744324
2023-01-24 08:18:09.937737: step: 1664/533, loss: 0.00538865989074111
2023-01-24 08:18:11.030675: step: 1668/533, loss: 0.017150238156318665
2023-01-24 08:18:12.148703: step: 1672/533, loss: 0.019712068140506744
2023-01-24 08:18:13.237593: step: 1676/533, loss: 0.0014251236570999026
2023-01-24 08:18:14.327562: step: 1680/533, loss: 0.025041021406650543
2023-01-24 08:18:15.425556: step: 1684/533, loss: 0.010722142644226551
2023-01-24 08:18:16.513726: step: 1688/533, loss: 0.0009135586442425847
2023-01-24 08:18:17.597354: step: 1692/533, loss: 0.01583823189139366
2023-01-24 08:18:18.686998: step: 1696/533, loss: 0.016500385478138924
2023-01-24 08:18:19.780450: step: 1700/533, loss: 0.002881655702367425
2023-01-24 08:18:20.863499: step: 1704/533, loss: 0.004424570128321648
2023-01-24 08:18:21.932374: step: 1708/533, loss: 0.012988843955099583
2023-01-24 08:18:23.035359: step: 1712/533, loss: 0.0036379729863256216
2023-01-24 08:18:24.116619: step: 1716/533, loss: 0.009609940461814404
2023-01-24 08:18:25.209907: step: 1720/533, loss: 0.020214049145579338
2023-01-24 08:18:26.318898: step: 1724/533, loss: 0.0060326773673295975
2023-01-24 08:18:27.419593: step: 1728/533, loss: 0.006149508524686098
2023-01-24 08:18:28.498855: step: 1732/533, loss: 0.02201077528297901
2023-01-24 08:18:29.565713: step: 1736/533, loss: 0.009319156408309937
2023-01-24 08:18:30.674830: step: 1740/533, loss: 0.004853575956076384
2023-01-24 08:18:31.767698: step: 1744/533, loss: 0.009596007876098156
2023-01-24 08:18:32.842536: step: 1748/533, loss: 0.013250434771180153
2023-01-24 08:18:33.909660: step: 1752/533, loss: 0.0007667145109735429
2023-01-24 08:18:35.000676: step: 1756/533, loss: 0.004410861991345882
2023-01-24 08:18:36.089264: step: 1760/533, loss: 0.019429393112659454
2023-01-24 08:18:37.196425: step: 1764/533, loss: 0.013458466157317162
2023-01-24 08:18:38.281725: step: 1768/533, loss: 0.0033470415510237217
2023-01-24 08:18:39.375928: step: 1772/533, loss: 0.002207280835136771
2023-01-24 08:18:40.457759: step: 1776/533, loss: 0.054352328181266785
2023-01-24 08:18:41.545397: step: 1780/533, loss: 0.005992678459733725
2023-01-24 08:18:42.635508: step: 1784/533, loss: 0.009483505971729755
2023-01-24 08:18:43.730844: step: 1788/533, loss: 0.004651589319109917
2023-01-24 08:18:44.845678: step: 1792/533, loss: 0.003098882269114256
2023-01-24 08:18:45.983153: step: 1796/533, loss: 0.005809679627418518
2023-01-24 08:18:47.083316: step: 1800/533, loss: 0.007387698162347078
2023-01-24 08:18:48.160679: step: 1804/533, loss: 0.015346543863415718
2023-01-24 08:18:49.290841: step: 1808/533, loss: 0.004910643678158522
2023-01-24 08:18:50.435050: step: 1812/533, loss: 0.002572157420217991
2023-01-24 08:18:51.525362: step: 1816/533, loss: 0.008712773211300373
2023-01-24 08:18:52.623962: step: 1820/533, loss: 0.008130164816975594
2023-01-24 08:18:53.722745: step: 1824/533, loss: 0.004625942092388868
2023-01-24 08:18:54.808508: step: 1828/533, loss: 0.016395874321460724
2023-01-24 08:18:55.939192: step: 1832/533, loss: 0.022853326052427292
2023-01-24 08:18:57.036534: step: 1836/533, loss: 0.017586994916200638
2023-01-24 08:18:58.120236: step: 1840/533, loss: 0.0026833820156753063
2023-01-24 08:18:59.187237: step: 1844/533, loss: 0.010254009626805782
2023-01-24 08:19:00.306959: step: 1848/533, loss: 0.0066741034388542175
2023-01-24 08:19:01.426360: step: 1852/533, loss: 0.001241902937181294
2023-01-24 08:19:02.509521: step: 1856/533, loss: 0.008381583727896214
2023-01-24 08:19:03.592991: step: 1860/533, loss: 0.013632186688482761
2023-01-24 08:19:04.679708: step: 1864/533, loss: 0.0006973329000174999
2023-01-24 08:19:05.761621: step: 1868/533, loss: 0.012881873175501823
2023-01-24 08:19:06.862958: step: 1872/533, loss: 0.007904918864369392
2023-01-24 08:19:07.937485: step: 1876/533, loss: 0.0223371684551239
2023-01-24 08:19:09.034097: step: 1880/533, loss: 0.0038004990201443434
2023-01-24 08:19:10.143689: step: 1884/533, loss: 0.028727946802973747
2023-01-24 08:19:11.241880: step: 1888/533, loss: 0.0008570475620217621
2023-01-24 08:19:12.321543: step: 1892/533, loss: 0.007574040442705154
2023-01-24 08:19:13.419394: step: 1896/533, loss: 0.03412792459130287
2023-01-24 08:19:14.507608: step: 1900/533, loss: 0.008673141710460186
2023-01-24 08:19:15.594191: step: 1904/533, loss: 0.0032855565659701824
2023-01-24 08:19:16.688371: step: 1908/533, loss: 0.004900189116597176
2023-01-24 08:19:17.788911: step: 1912/533, loss: 0.006026383955031633
2023-01-24 08:19:18.877481: step: 1916/533, loss: 0.0024595772847533226
2023-01-24 08:19:19.973273: step: 1920/533, loss: 0.00784789863973856
2023-01-24 08:19:21.084851: step: 1924/533, loss: 0.04226364567875862
2023-01-24 08:19:22.156121: step: 1928/533, loss: 0.005798889324069023
2023-01-24 08:19:23.269502: step: 1932/533, loss: 0.011572135612368584
2023-01-24 08:19:24.356692: step: 1936/533, loss: 0.0029936532955616713
2023-01-24 08:19:25.446404: step: 1940/533, loss: 0.006660048384219408
2023-01-24 08:19:26.531332: step: 1944/533, loss: 0.023693865165114403
2023-01-24 08:19:27.618909: step: 1948/533, loss: 0.000359441211912781
2023-01-24 08:19:28.720537: step: 1952/533, loss: 0.01215211022645235
2023-01-24 08:19:29.801914: step: 1956/533, loss: 0.0030970489606261253
2023-01-24 08:19:30.898622: step: 1960/533, loss: 0.020191142335534096
2023-01-24 08:19:31.985477: step: 1964/533, loss: 0.00471978634595871
2023-01-24 08:19:33.111430: step: 1968/533, loss: 0.02101767435669899
2023-01-24 08:19:34.201253: step: 1972/533, loss: 0.006548277568072081
2023-01-24 08:19:35.283047: step: 1976/533, loss: 0.00957560259848833
2023-01-24 08:19:36.372669: step: 1980/533, loss: 0.0051421839743852615
2023-01-24 08:19:37.471376: step: 1984/533, loss: 0.005786658264696598
2023-01-24 08:19:38.555769: step: 1988/533, loss: 0.004714953247457743
2023-01-24 08:19:39.646277: step: 1992/533, loss: 0.0006178878247737885
2023-01-24 08:19:40.728940: step: 1996/533, loss: 0.013418581336736679
2023-01-24 08:19:41.832506: step: 2000/533, loss: 0.0064127943478524685
2023-01-24 08:19:42.940345: step: 2004/533, loss: 0.01495274156332016
2023-01-24 08:19:44.054898: step: 2008/533, loss: 0.02997070923447609
2023-01-24 08:19:45.134868: step: 2012/533, loss: 0.0010538314236328006
2023-01-24 08:19:46.226271: step: 2016/533, loss: 0.005071071442216635
2023-01-24 08:19:47.324700: step: 2020/533, loss: 0.05412726104259491
2023-01-24 08:19:48.410611: step: 2024/533, loss: 0.007501085754483938
2023-01-24 08:19:49.496580: step: 2028/533, loss: 0.0032494449988007545
2023-01-24 08:19:50.568659: step: 2032/533, loss: 0.011328439228236675
2023-01-24 08:19:51.656322: step: 2036/533, loss: 0.017803924158215523
2023-01-24 08:19:52.758245: step: 2040/533, loss: 0.02297670766711235
2023-01-24 08:19:53.845960: step: 2044/533, loss: 0.018049150705337524
2023-01-24 08:19:54.971003: step: 2048/533, loss: 0.00646524503827095
2023-01-24 08:19:56.073213: step: 2052/533, loss: 0.02366437390446663
2023-01-24 08:19:57.168500: step: 2056/533, loss: 0.01950335130095482
2023-01-24 08:19:58.263260: step: 2060/533, loss: 0.025677703320980072
2023-01-24 08:19:59.359698: step: 2064/533, loss: 0.011715452186763287
2023-01-24 08:20:00.457432: step: 2068/533, loss: 0.002163659082725644
2023-01-24 08:20:01.561807: step: 2072/533, loss: 0.002846771851181984
2023-01-24 08:20:02.669707: step: 2076/533, loss: 0.006615984719246626
2023-01-24 08:20:03.740932: step: 2080/533, loss: 0.002533852821215987
2023-01-24 08:20:04.794762: step: 2084/533, loss: 0.008282288908958435
2023-01-24 08:20:05.860293: step: 2088/533, loss: 0.0073960525915026665
2023-01-24 08:20:06.937952: step: 2092/533, loss: 0.013367313891649246
2023-01-24 08:20:08.018907: step: 2096/533, loss: 0.011628908105194569
2023-01-24 08:20:09.100673: step: 2100/533, loss: 0.002715301001444459
2023-01-24 08:20:10.201566: step: 2104/533, loss: 0.0024887502659112215
2023-01-24 08:20:11.320048: step: 2108/533, loss: 0.03204505890607834
2023-01-24 08:20:12.413408: step: 2112/533, loss: 0.009765367954969406
2023-01-24 08:20:13.486625: step: 2116/533, loss: 0.0029028039425611496
2023-01-24 08:20:14.553647: step: 2120/533, loss: 0.0037991839926689863
2023-01-24 08:20:15.643121: step: 2124/533, loss: 0.03498809039592743
2023-01-24 08:20:16.767899: step: 2128/533, loss: 0.00894905161112547
2023-01-24 08:20:17.863811: step: 2132/533, loss: 0.0363033264875412
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37804103122730576, 'r': 0.32926154332700824, 'f1': 0.3519692359702502}, 'combined': 0.25934575282018435, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39961188873303155, 'r': 0.36080342646184294, 'f1': 0.3792173456496378}, 'combined': 0.25281156376642516, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3563019057831009, 'r': 0.31979279209754596, 'f1': 0.3370616028708135}, 'combined': 0.24836118106270466, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38969369305163376, 'r': 0.308382605174514, 'f1': 0.34430264023778273}, 'combined': 0.2295350934918551, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3447013341419042, 'r': 0.31722988056702756, 'f1': 0.33039554754708206}, 'combined': 0.24344935082416572, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38418992479033826, 'r': 0.34577093231130446, 'f1': 0.363969402432952}, 'combined': 0.24264626828863461, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661572385213968, 'r': 0.3216903253043771, 'f1': 0.34248646754627615}, 'combined': 0.2523584497709403, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38773270130457727, 'r': 0.30906770132836014, 'f1': 0.34395977461904176}, 'combined': 0.22930651641269445, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 08:22:39.478256: step: 4/533, loss: 0.005596387665718794
2023-01-24 08:22:40.567417: step: 8/533, loss: 0.005377475172281265
2023-01-24 08:22:41.629037: step: 12/533, loss: 0.0032591684721410275
2023-01-24 08:22:42.706892: step: 16/533, loss: 0.005660451482981443
2023-01-24 08:22:43.811951: step: 20/533, loss: 0.004405792336910963
2023-01-24 08:22:44.922316: step: 24/533, loss: 0.014254656620323658
2023-01-24 08:22:46.006905: step: 28/533, loss: 0.008085072971880436
2023-01-24 08:22:47.079916: step: 32/533, loss: 0.002043369458988309
2023-01-24 08:22:48.153919: step: 36/533, loss: 0.025876155123114586
2023-01-24 08:22:49.234703: step: 40/533, loss: 0.01665867120027542
2023-01-24 08:22:50.302874: step: 44/533, loss: 0.05542600527405739
2023-01-24 08:22:51.381050: step: 48/533, loss: 0.00433550076559186
2023-01-24 08:22:52.478874: step: 52/533, loss: 0.006948303896933794
2023-01-24 08:22:53.552549: step: 56/533, loss: 0.004050250165164471
2023-01-24 08:22:54.626904: step: 60/533, loss: 0.003909015562385321
2023-01-24 08:22:55.717901: step: 64/533, loss: 0.006339604500681162
2023-01-24 08:22:56.808151: step: 68/533, loss: 0.005573740694671869
2023-01-24 08:22:57.901189: step: 72/533, loss: 0.0076233744621276855
2023-01-24 08:22:58.999844: step: 76/533, loss: 0.02359524928033352
2023-01-24 08:23:00.095125: step: 80/533, loss: 0.003957529552280903
2023-01-24 08:23:01.183890: step: 84/533, loss: 0.02181381545960903
2023-01-24 08:23:02.285098: step: 88/533, loss: 0.006510388571768999
2023-01-24 08:23:03.369014: step: 92/533, loss: 0.020020242780447006
2023-01-24 08:23:04.446308: step: 96/533, loss: 0.0013689942425116897
2023-01-24 08:23:05.531089: step: 100/533, loss: 0.004831534810364246
2023-01-24 08:23:06.633154: step: 104/533, loss: 0.01687484420835972
2023-01-24 08:23:07.706054: step: 108/533, loss: 0.00807182677090168
2023-01-24 08:23:08.804568: step: 112/533, loss: 0.003870889078825712
2023-01-24 08:23:09.898026: step: 116/533, loss: 0.0057237762957811356
2023-01-24 08:23:10.993671: step: 120/533, loss: 0.05570525676012039
2023-01-24 08:23:12.096554: step: 124/533, loss: 0.007711918093264103
2023-01-24 08:23:13.184403: step: 128/533, loss: 0.0065986537374556065
2023-01-24 08:23:14.302011: step: 132/533, loss: 0.010324192233383656
2023-01-24 08:23:15.384245: step: 136/533, loss: 0.009526516310870647
2023-01-24 08:23:16.480947: step: 140/533, loss: 0.033194370567798615
2023-01-24 08:23:17.551252: step: 144/533, loss: 0.007208303082734346
2023-01-24 08:23:18.653015: step: 148/533, loss: 0.0018813872011378407
2023-01-24 08:23:19.767723: step: 152/533, loss: 0.012987309135496616
2023-01-24 08:23:20.847379: step: 156/533, loss: 0.010280108079314232
2023-01-24 08:23:21.915081: step: 160/533, loss: 0.007783348206430674
2023-01-24 08:23:22.988592: step: 164/533, loss: 0.0018562147160992026
2023-01-24 08:23:24.067115: step: 168/533, loss: 0.007721239700913429
2023-01-24 08:23:25.153527: step: 172/533, loss: 0.003967213444411755
2023-01-24 08:23:26.237393: step: 176/533, loss: 0.0047073145397007465
2023-01-24 08:23:27.337009: step: 180/533, loss: 0.013793588615953922
2023-01-24 08:23:28.448273: step: 184/533, loss: 0.008345799520611763
2023-01-24 08:23:29.541574: step: 188/533, loss: 0.009712041355669498
2023-01-24 08:23:30.611103: step: 192/533, loss: 0.000989193213172257
2023-01-24 08:23:31.697712: step: 196/533, loss: 0.004998192191123962
2023-01-24 08:23:32.776661: step: 200/533, loss: 0.03494611382484436
2023-01-24 08:23:33.841659: step: 204/533, loss: 0.009611524641513824
2023-01-24 08:23:34.913328: step: 208/533, loss: 0.0036592117976397276
2023-01-24 08:23:36.009958: step: 212/533, loss: 0.0022119844797998667
2023-01-24 08:23:37.121209: step: 216/533, loss: 0.0014852340100333095
2023-01-24 08:23:38.207321: step: 220/533, loss: 0.006640386302024126
2023-01-24 08:23:39.280622: step: 224/533, loss: 0.004020139575004578
2023-01-24 08:23:40.363172: step: 228/533, loss: 0.002810112200677395
2023-01-24 08:23:41.457644: step: 232/533, loss: 0.026952246204018593
2023-01-24 08:23:42.524135: step: 236/533, loss: 0.002027825452387333
2023-01-24 08:23:43.614035: step: 240/533, loss: 0.005763750057667494
2023-01-24 08:23:44.699271: step: 244/533, loss: 0.02421431615948677
2023-01-24 08:23:45.792948: step: 248/533, loss: 0.006338620092719793
2023-01-24 08:23:46.877879: step: 252/533, loss: 0.0006665757391601801
2023-01-24 08:23:47.952141: step: 256/533, loss: 0.0029698768630623817
2023-01-24 08:23:49.038197: step: 260/533, loss: 0.02270670048892498
2023-01-24 08:23:50.130988: step: 264/533, loss: 0.0008987932233139873
2023-01-24 08:23:51.241249: step: 268/533, loss: 0.002710937988013029
2023-01-24 08:23:52.317025: step: 272/533, loss: 0.006249002180993557
2023-01-24 08:23:53.394593: step: 276/533, loss: 0.012404322624206543
2023-01-24 08:23:54.484478: step: 280/533, loss: 0.003951958380639553
2023-01-24 08:23:55.573096: step: 284/533, loss: 0.006505305878818035
2023-01-24 08:23:56.690260: step: 288/533, loss: 0.02204527147114277
2023-01-24 08:23:57.775792: step: 292/533, loss: 0.006597038824111223
2023-01-24 08:23:58.860749: step: 296/533, loss: 0.011179288849234581
2023-01-24 08:23:59.953006: step: 300/533, loss: 0.011946807615458965
2023-01-24 08:24:01.041316: step: 304/533, loss: 0.0014094279613345861
2023-01-24 08:24:02.126602: step: 308/533, loss: 0.0004991274327039719
2023-01-24 08:24:03.204787: step: 312/533, loss: 0.0009096853900700808
2023-01-24 08:24:04.278141: step: 316/533, loss: 0.020998656749725342
2023-01-24 08:24:05.383041: step: 320/533, loss: 0.0007388515514321625
2023-01-24 08:24:06.476190: step: 324/533, loss: 0.0018155931029468775
2023-01-24 08:24:07.555084: step: 328/533, loss: 0.005851041059941053
2023-01-24 08:24:08.648910: step: 332/533, loss: 0.013595889322459698
2023-01-24 08:24:09.725946: step: 336/533, loss: 0.0029455001931637526
2023-01-24 08:24:10.815272: step: 340/533, loss: 1.6316580797592906e-07
2023-01-24 08:24:11.926265: step: 344/533, loss: 0.003907398320734501
2023-01-24 08:24:13.016601: step: 348/533, loss: 0.0040290080942213535
2023-01-24 08:24:14.090147: step: 352/533, loss: 0.007264419458806515
2023-01-24 08:24:15.170148: step: 356/533, loss: 0.0015635094605386257
2023-01-24 08:24:16.271050: step: 360/533, loss: 0.0010443388018757105
2023-01-24 08:24:17.351825: step: 364/533, loss: 0.007906801998615265
2023-01-24 08:24:18.428125: step: 368/533, loss: 0.002589157782495022
2023-01-24 08:24:19.503823: step: 372/533, loss: 0.0037559508346021175
2023-01-24 08:24:20.602429: step: 376/533, loss: 0.010838030837476254
2023-01-24 08:24:21.685525: step: 380/533, loss: 0.0032494384795427322
2023-01-24 08:24:22.776106: step: 384/533, loss: 0.027592262253165245
2023-01-24 08:24:23.855823: step: 388/533, loss: 0.02054150030016899
2023-01-24 08:24:24.946406: step: 392/533, loss: 0.0037845491897314787
2023-01-24 08:24:26.021264: step: 396/533, loss: 0.010702591389417648
2023-01-24 08:24:27.124874: step: 400/533, loss: 0.007268610876053572
2023-01-24 08:24:28.202701: step: 404/533, loss: 0.021076245233416557
2023-01-24 08:24:29.275680: step: 408/533, loss: 0.05968830734491348
2023-01-24 08:24:30.349125: step: 412/533, loss: 0.008256598375737667
2023-01-24 08:24:31.446667: step: 416/533, loss: 0.003635730128735304
2023-01-24 08:24:32.533336: step: 420/533, loss: 0.019012466073036194
2023-01-24 08:24:33.618517: step: 424/533, loss: 0.010594429448246956
2023-01-24 08:24:34.726440: step: 428/533, loss: 0.00933141727000475
2023-01-24 08:24:35.824335: step: 432/533, loss: 0.009580621495842934
2023-01-24 08:24:36.903664: step: 436/533, loss: 0.004615973215550184
2023-01-24 08:24:38.003588: step: 440/533, loss: 0.01551726832985878
2023-01-24 08:24:39.094946: step: 444/533, loss: 0.06207980588078499
2023-01-24 08:24:40.179827: step: 448/533, loss: 0.004943095147609711
2023-01-24 08:24:41.262973: step: 452/533, loss: 0.004004658665508032
2023-01-24 08:24:42.369832: step: 456/533, loss: 0.013017025776207447
2023-01-24 08:24:43.443375: step: 460/533, loss: 0.0024607970844954252
2023-01-24 08:24:44.520563: step: 464/533, loss: 0.0005329413688741624
2023-01-24 08:24:45.625169: step: 468/533, loss: 0.004500649403780699
2023-01-24 08:24:46.737402: step: 472/533, loss: 0.010763419792056084
2023-01-24 08:24:47.840427: step: 476/533, loss: 0.03020641952753067
2023-01-24 08:24:48.939316: step: 480/533, loss: 0.0038034175522625446
2023-01-24 08:24:50.045022: step: 484/533, loss: 0.013111729174852371
2023-01-24 08:24:51.159076: step: 488/533, loss: 0.00949406810104847
2023-01-24 08:24:52.268469: step: 492/533, loss: 0.01425307709723711
2023-01-24 08:24:53.371799: step: 496/533, loss: 0.04016595706343651
2023-01-24 08:24:54.463394: step: 500/533, loss: 0.002001472981646657
2023-01-24 08:24:55.537343: step: 504/533, loss: 0.0021822196431457996
2023-01-24 08:24:56.627421: step: 508/533, loss: 0.0052075982093811035
2023-01-24 08:24:57.723727: step: 512/533, loss: 0.0038549606688320637
2023-01-24 08:24:58.800889: step: 516/533, loss: 0.022307712584733963
2023-01-24 08:24:59.900936: step: 520/533, loss: 0.011536641977727413
2023-01-24 08:25:01.004018: step: 524/533, loss: 0.028450852259993553
2023-01-24 08:25:02.088528: step: 528/533, loss: 0.028910255059599876
2023-01-24 08:25:03.188523: step: 532/533, loss: 0.007241892162710428
2023-01-24 08:25:04.276952: step: 536/533, loss: 0.004333202727138996
2023-01-24 08:25:05.379029: step: 540/533, loss: 0.0001953363389475271
2023-01-24 08:25:06.470171: step: 544/533, loss: 0.005799734499305487
2023-01-24 08:25:07.537083: step: 548/533, loss: 0.005460209213197231
2023-01-24 08:25:08.689422: step: 552/533, loss: 0.026669692248106003
2023-01-24 08:25:09.755016: step: 556/533, loss: 0.0012451065704226494
2023-01-24 08:25:10.856971: step: 560/533, loss: 0.010906836949288845
2023-01-24 08:25:11.957209: step: 564/533, loss: 0.009552073664963245
2023-01-24 08:25:13.042282: step: 568/533, loss: 0.0029021769296377897
2023-01-24 08:25:14.121077: step: 572/533, loss: 0.039164453744888306
2023-01-24 08:25:15.205940: step: 576/533, loss: 0.002445882186293602
2023-01-24 08:25:16.308821: step: 580/533, loss: 0.014920282177627087
2023-01-24 08:25:17.387323: step: 584/533, loss: 0.0039942022413015366
2023-01-24 08:25:18.467438: step: 588/533, loss: 0.03420380875468254
2023-01-24 08:25:19.563781: step: 592/533, loss: 0.012045162729918957
2023-01-24 08:25:20.690001: step: 596/533, loss: 0.007223254535347223
2023-01-24 08:25:21.811947: step: 600/533, loss: 0.02152221091091633
2023-01-24 08:25:22.892020: step: 604/533, loss: 0.007932500913739204
2023-01-24 08:25:24.019422: step: 608/533, loss: 0.0055467127822339535
2023-01-24 08:25:25.101225: step: 612/533, loss: 0.0033045741729438305
2023-01-24 08:25:26.168119: step: 616/533, loss: 0.013936072587966919
2023-01-24 08:25:27.254656: step: 620/533, loss: 0.0026706838980317116
2023-01-24 08:25:28.332013: step: 624/533, loss: 0.005123530514538288
2023-01-24 08:25:29.397439: step: 628/533, loss: 0.0037463540211319923
2023-01-24 08:25:30.485473: step: 632/533, loss: 0.009614874608814716
2023-01-24 08:25:31.560021: step: 636/533, loss: 0.02132567949593067
2023-01-24 08:25:32.631021: step: 640/533, loss: 0.0027393768541514874
2023-01-24 08:25:33.718284: step: 644/533, loss: 0.016210276633501053
2023-01-24 08:25:34.829508: step: 648/533, loss: 0.012738527730107307
2023-01-24 08:25:35.903613: step: 652/533, loss: 0.010193035006523132
2023-01-24 08:25:36.988750: step: 656/533, loss: 0.00481856893748045
2023-01-24 08:25:38.066066: step: 660/533, loss: 0.00676585640758276
2023-01-24 08:25:39.144862: step: 664/533, loss: 0.0100246611982584
2023-01-24 08:25:40.226414: step: 668/533, loss: 0.00726846419274807
2023-01-24 08:25:41.312421: step: 672/533, loss: 0.004991927184164524
2023-01-24 08:25:42.422973: step: 676/533, loss: 0.027233706787228584
2023-01-24 08:25:43.503315: step: 680/533, loss: 0.005383920390158892
2023-01-24 08:25:44.563118: step: 684/533, loss: 0.029323343187570572
2023-01-24 08:25:45.660657: step: 688/533, loss: 0.0028290997724980116
2023-01-24 08:25:46.744301: step: 692/533, loss: 0.004101135767996311
2023-01-24 08:25:47.839655: step: 696/533, loss: 0.0049935877323150635
2023-01-24 08:25:48.915556: step: 700/533, loss: 0.005816805176436901
2023-01-24 08:25:50.015925: step: 704/533, loss: 0.0024590485263615847
2023-01-24 08:25:51.118689: step: 708/533, loss: 0.030980601906776428
2023-01-24 08:25:52.195883: step: 712/533, loss: 0.005929720588028431
2023-01-24 08:25:53.290610: step: 716/533, loss: 0.015265916474163532
2023-01-24 08:25:54.386596: step: 720/533, loss: 0.00011998967966064811
2023-01-24 08:25:55.469713: step: 724/533, loss: 0.007259550970047712
2023-01-24 08:25:56.616636: step: 728/533, loss: 0.009263886138796806
2023-01-24 08:25:57.697323: step: 732/533, loss: 0.0023758821189403534
2023-01-24 08:25:58.780664: step: 736/533, loss: 0.022718803957104683
2023-01-24 08:25:59.870661: step: 740/533, loss: 0.013849307782948017
2023-01-24 08:26:00.970092: step: 744/533, loss: 4.21817931055557e-05
2023-01-24 08:26:02.044452: step: 748/533, loss: 0.008088736794888973
2023-01-24 08:26:03.156340: step: 752/533, loss: 0.0025932397693395615
2023-01-24 08:26:04.261199: step: 756/533, loss: 0.004731516353785992
2023-01-24 08:26:05.362270: step: 760/533, loss: 0.010027549229562283
2023-01-24 08:26:06.444032: step: 764/533, loss: 0.012738917022943497
2023-01-24 08:26:07.535290: step: 768/533, loss: 0.008570468053221703
2023-01-24 08:26:08.629285: step: 772/533, loss: 0.0005830472218804061
2023-01-24 08:26:09.709594: step: 776/533, loss: 0.007536714896559715
2023-01-24 08:26:10.784400: step: 780/533, loss: 0.018076088279485703
2023-01-24 08:26:11.860355: step: 784/533, loss: 0.018761400133371353
2023-01-24 08:26:12.959008: step: 788/533, loss: 0.0071996948681771755
2023-01-24 08:26:14.050641: step: 792/533, loss: 0.0034827087074518204
2023-01-24 08:26:15.138462: step: 796/533, loss: 0.004589133895933628
2023-01-24 08:26:16.217765: step: 800/533, loss: 0.005144144408404827
2023-01-24 08:26:17.310997: step: 804/533, loss: 0.0031147152185440063
2023-01-24 08:26:18.399164: step: 808/533, loss: 0.012437690980732441
2023-01-24 08:26:19.472851: step: 812/533, loss: 0.01405649445950985
2023-01-24 08:26:20.567293: step: 816/533, loss: 0.0016192349139600992
2023-01-24 08:26:21.646781: step: 820/533, loss: 0.009139442816376686
2023-01-24 08:26:22.724899: step: 824/533, loss: 0.004961365833878517
2023-01-24 08:26:23.812589: step: 828/533, loss: 0.007307286374270916
2023-01-24 08:26:24.925860: step: 832/533, loss: 0.004729915875941515
2023-01-24 08:26:26.024225: step: 836/533, loss: 0.006135339383035898
2023-01-24 08:26:27.086454: step: 840/533, loss: 0.0006457378622144461
2023-01-24 08:26:28.172195: step: 844/533, loss: 0.010008290410041809
2023-01-24 08:26:29.276347: step: 848/533, loss: 0.011330689303576946
2023-01-24 08:26:30.372761: step: 852/533, loss: 0.018207315355539322
2023-01-24 08:26:31.468194: step: 856/533, loss: 0.010344750247895718
2023-01-24 08:26:32.574285: step: 860/533, loss: 0.00390635384246707
2023-01-24 08:26:33.649289: step: 864/533, loss: 0.00618093553930521
2023-01-24 08:26:34.764149: step: 868/533, loss: 0.007923630997538567
2023-01-24 08:26:35.873528: step: 872/533, loss: 0.004267644602805376
2023-01-24 08:26:36.980605: step: 876/533, loss: 0.005757149774581194
2023-01-24 08:26:38.055910: step: 880/533, loss: 0.023051157593727112
2023-01-24 08:26:39.142492: step: 884/533, loss: 0.005366581492125988
2023-01-24 08:26:40.224286: step: 888/533, loss: 0.006548753939568996
2023-01-24 08:26:41.327725: step: 892/533, loss: 0.014345170930027962
2023-01-24 08:26:42.424316: step: 896/533, loss: 0.00283396290615201
2023-01-24 08:26:43.536033: step: 900/533, loss: 0.002197330817580223
2023-01-24 08:26:44.608199: step: 904/533, loss: 0.05032861605286598
2023-01-24 08:26:45.720765: step: 908/533, loss: 0.019203299656510353
2023-01-24 08:26:46.830437: step: 912/533, loss: 0.0005616630078293383
2023-01-24 08:26:47.939491: step: 916/533, loss: 0.013257335871458054
2023-01-24 08:26:49.010008: step: 920/533, loss: 0.0013968197163194418
2023-01-24 08:26:50.127380: step: 924/533, loss: 0.029280195012688637
2023-01-24 08:26:51.221033: step: 928/533, loss: 0.019959937781095505
2023-01-24 08:26:52.344158: step: 932/533, loss: 0.005733666475862265
2023-01-24 08:26:53.414951: step: 936/533, loss: 0.00016776329721324146
2023-01-24 08:26:54.510767: step: 940/533, loss: 0.0021690980065613985
2023-01-24 08:26:55.590402: step: 944/533, loss: 0.0020090490579605103
2023-01-24 08:26:56.673310: step: 948/533, loss: 0.004883905407041311
2023-01-24 08:26:57.790056: step: 952/533, loss: 0.005792809650301933
2023-01-24 08:26:58.886452: step: 956/533, loss: 0.007793085183948278
2023-01-24 08:26:59.976092: step: 960/533, loss: 0.002148953964933753
2023-01-24 08:27:01.068279: step: 964/533, loss: 0.0012523698387667537
2023-01-24 08:27:02.161953: step: 968/533, loss: 0.008532264269888401
2023-01-24 08:27:03.271809: step: 972/533, loss: 0.008883078582584858
2023-01-24 08:27:04.365700: step: 976/533, loss: 0.005629494320601225
2023-01-24 08:27:05.447077: step: 980/533, loss: 0.0015945230843499303
2023-01-24 08:27:06.550297: step: 984/533, loss: 0.0020702581387013197
2023-01-24 08:27:07.641932: step: 988/533, loss: 0.008012320846319199
2023-01-24 08:27:08.766182: step: 992/533, loss: 0.011799241416156292
2023-01-24 08:27:09.875380: step: 996/533, loss: 0.0012229245621711016
2023-01-24 08:27:10.956720: step: 1000/533, loss: 0.00800988357514143
2023-01-24 08:27:12.072301: step: 1004/533, loss: 0.007943312637507915
2023-01-24 08:27:13.169794: step: 1008/533, loss: 0.04623910412192345
2023-01-24 08:27:14.260875: step: 1012/533, loss: 0.00466503482311964
2023-01-24 08:27:15.367670: step: 1016/533, loss: 0.000698310264851898
2023-01-24 08:27:16.465448: step: 1020/533, loss: 0.005334882531315088
2023-01-24 08:27:17.585723: step: 1024/533, loss: 0.012350591830909252
2023-01-24 08:27:18.676793: step: 1028/533, loss: 0.00384082761593163
2023-01-24 08:27:19.783241: step: 1032/533, loss: 0.012336905114352703
2023-01-24 08:27:20.921624: step: 1036/533, loss: 0.010879453271627426
2023-01-24 08:27:22.021885: step: 1040/533, loss: 0.011665110476315022
2023-01-24 08:27:23.105869: step: 1044/533, loss: 0.007613239344209433
2023-01-24 08:27:24.179970: step: 1048/533, loss: 0.002896494697779417
2023-01-24 08:27:25.279648: step: 1052/533, loss: 0.021656379103660583
2023-01-24 08:27:26.389451: step: 1056/533, loss: 0.0021020332351326942
2023-01-24 08:27:27.476210: step: 1060/533, loss: 0.028636520728468895
2023-01-24 08:27:28.572561: step: 1064/533, loss: 0.002981869736686349
2023-01-24 08:27:29.660037: step: 1068/533, loss: 0.007148182950913906
2023-01-24 08:27:30.788009: step: 1072/533, loss: 0.009110729210078716
2023-01-24 08:27:31.895592: step: 1076/533, loss: 0.007338237017393112
2023-01-24 08:27:33.009777: step: 1080/533, loss: 0.003439634572714567
2023-01-24 08:27:34.099577: step: 1084/533, loss: 0.003643183270469308
2023-01-24 08:27:35.221574: step: 1088/533, loss: 0.004822505172342062
2023-01-24 08:27:36.318787: step: 1092/533, loss: 0.0036062696017324924
2023-01-24 08:27:37.415163: step: 1096/533, loss: 0.004828851204365492
2023-01-24 08:27:38.513475: step: 1100/533, loss: 0.006414342671632767
2023-01-24 08:27:39.624104: step: 1104/533, loss: 0.015717972069978714
2023-01-24 08:27:40.723916: step: 1108/533, loss: 0.0008058499661274254
2023-01-24 08:27:41.795058: step: 1112/533, loss: 0.009140096604824066
2023-01-24 08:27:42.887381: step: 1116/533, loss: 0.006217277608811855
2023-01-24 08:27:43.979439: step: 1120/533, loss: 0.012731713242828846
2023-01-24 08:27:45.074764: step: 1124/533, loss: 0.0033069264609366655
2023-01-24 08:27:46.170767: step: 1128/533, loss: 0.0038175538647919893
2023-01-24 08:27:47.271208: step: 1132/533, loss: 0.010678107850253582
2023-01-24 08:27:48.372895: step: 1136/533, loss: 0.006202307064086199
2023-01-24 08:27:49.472081: step: 1140/533, loss: 0.029471317306160927
2023-01-24 08:27:50.558647: step: 1144/533, loss: 0.005225008819252253
2023-01-24 08:27:51.642744: step: 1148/533, loss: 0.005130003672093153
2023-01-24 08:27:52.732851: step: 1152/533, loss: 0.013055561110377312
2023-01-24 08:27:53.859636: step: 1156/533, loss: 0.0021532850805670023
2023-01-24 08:27:54.964398: step: 1160/533, loss: 0.002151101129129529
2023-01-24 08:27:56.041599: step: 1164/533, loss: 0.014443822205066681
2023-01-24 08:27:57.142630: step: 1168/533, loss: 0.0065402137115597725
2023-01-24 08:27:58.253976: step: 1172/533, loss: 0.0009595786104910076
2023-01-24 08:27:59.381000: step: 1176/533, loss: 0.007435441017150879
2023-01-24 08:28:00.516113: step: 1180/533, loss: 0.01176536176353693
2023-01-24 08:28:01.640284: step: 1184/533, loss: 1.5313562471419573e-05
2023-01-24 08:28:02.737399: step: 1188/533, loss: 0.0151371406391263
2023-01-24 08:28:03.813768: step: 1192/533, loss: 0.00420265132561326
2023-01-24 08:28:04.898959: step: 1196/533, loss: 0.002507680095732212
2023-01-24 08:28:05.988737: step: 1200/533, loss: 0.0058892872184515
2023-01-24 08:28:07.074799: step: 1204/533, loss: 0.0005234710406512022
2023-01-24 08:28:08.150477: step: 1208/533, loss: 0.0032060297671705484
2023-01-24 08:28:09.239761: step: 1212/533, loss: 0.004621167667210102
2023-01-24 08:28:10.351518: step: 1216/533, loss: 0.0023800686467438936
2023-01-24 08:28:11.444152: step: 1220/533, loss: 0.069223552942276
2023-01-24 08:28:12.542045: step: 1224/533, loss: 0.010387963615357876
2023-01-24 08:28:13.675102: step: 1228/533, loss: 0.00984850712120533
2023-01-24 08:28:14.758488: step: 1232/533, loss: 0.0078807407990098
2023-01-24 08:28:15.878317: step: 1236/533, loss: 0.006970199756324291
2023-01-24 08:28:16.986087: step: 1240/533, loss: 0.020852871239185333
2023-01-24 08:28:18.057198: step: 1244/533, loss: 0.002000416861847043
2023-01-24 08:28:19.154123: step: 1248/533, loss: 0.0030045327730476856
2023-01-24 08:28:20.250419: step: 1252/533, loss: 0.007621146272867918
2023-01-24 08:28:21.331722: step: 1256/533, loss: 0.011967865750193596
2023-01-24 08:28:22.425533: step: 1260/533, loss: 0.007369248196482658
2023-01-24 08:28:23.519574: step: 1264/533, loss: 6.287153519224375e-05
2023-01-24 08:28:24.632709: step: 1268/533, loss: 0.007249994203448296
2023-01-24 08:28:25.732774: step: 1272/533, loss: 0.00931045226752758
2023-01-24 08:28:26.833615: step: 1276/533, loss: 0.0074598887003958225
2023-01-24 08:28:27.934858: step: 1280/533, loss: 0.004224805627018213
2023-01-24 08:28:29.017511: step: 1284/533, loss: 0.013409566134214401
2023-01-24 08:28:30.128622: step: 1288/533, loss: 0.004040799103677273
2023-01-24 08:28:31.218959: step: 1292/533, loss: 0.015040739439427853
2023-01-24 08:28:32.326366: step: 1296/533, loss: 2.1065779947093688e-05
2023-01-24 08:28:33.429930: step: 1300/533, loss: 0.0060523576103150845
2023-01-24 08:28:34.517792: step: 1304/533, loss: 0.007462130859494209
2023-01-24 08:28:35.612184: step: 1308/533, loss: 0.017871258780360222
2023-01-24 08:28:36.706653: step: 1312/533, loss: 0.002482824958860874
2023-01-24 08:28:37.769724: step: 1316/533, loss: 0.0008269812096841633
2023-01-24 08:28:38.866430: step: 1320/533, loss: 0.007946299389004707
2023-01-24 08:28:39.984512: step: 1324/533, loss: 0.004606822971254587
2023-01-24 08:28:41.078847: step: 1328/533, loss: 0.004066638182848692
2023-01-24 08:28:42.189417: step: 1332/533, loss: 0.013679180294275284
2023-01-24 08:28:43.280179: step: 1336/533, loss: 0.06453981250524521
2023-01-24 08:28:44.380949: step: 1340/533, loss: 0.003248006571084261
2023-01-24 08:28:45.476466: step: 1344/533, loss: 0.0127334576100111
2023-01-24 08:28:46.578582: step: 1348/533, loss: 0.010535718873143196
2023-01-24 08:28:47.668867: step: 1352/533, loss: 0.008955178782343864
2023-01-24 08:28:48.748230: step: 1356/533, loss: 0.06981603801250458
2023-01-24 08:28:49.829431: step: 1360/533, loss: 0.0262322798371315
2023-01-24 08:28:50.948010: step: 1364/533, loss: 0.11751559376716614
2023-01-24 08:28:52.060240: step: 1368/533, loss: 0.00695620384067297
2023-01-24 08:28:53.168825: step: 1372/533, loss: 0.0003830206405837089
2023-01-24 08:28:54.263160: step: 1376/533, loss: 0.003644073149189353
2023-01-24 08:28:55.362938: step: 1380/533, loss: 0.009202844463288784
2023-01-24 08:28:56.455798: step: 1384/533, loss: 0.004145620856434107
2023-01-24 08:28:57.554597: step: 1388/533, loss: 0.007446944713592529
2023-01-24 08:28:58.641686: step: 1392/533, loss: 0.006633382756263018
2023-01-24 08:28:59.720473: step: 1396/533, loss: 0.04786726459860802
2023-01-24 08:29:00.804816: step: 1400/533, loss: 0.0011410362785682082
2023-01-24 08:29:01.913491: step: 1404/533, loss: 0.0034577178303152323
2023-01-24 08:29:03.015193: step: 1408/533, loss: 0.001996818231418729
2023-01-24 08:29:04.137592: step: 1412/533, loss: 0.014832454733550549
2023-01-24 08:29:05.219434: step: 1416/533, loss: 0.013181988149881363
2023-01-24 08:29:06.289585: step: 1420/533, loss: 0.007742798887193203
2023-01-24 08:29:07.430134: step: 1424/533, loss: 0.04517185315489769
2023-01-24 08:29:08.522990: step: 1428/533, loss: 0.007829529233276844
2023-01-24 08:29:09.601148: step: 1432/533, loss: 0.012384737841784954
2023-01-24 08:29:10.713757: step: 1436/533, loss: 0.011942601762712002
2023-01-24 08:29:11.814901: step: 1440/533, loss: 0.006711332593113184
2023-01-24 08:29:12.893632: step: 1444/533, loss: 0.01913359947502613
2023-01-24 08:29:13.977892: step: 1448/533, loss: 0.010137129575014114
2023-01-24 08:29:15.066926: step: 1452/533, loss: 0.007127038203179836
2023-01-24 08:29:16.145731: step: 1456/533, loss: 0.02841912768781185
2023-01-24 08:29:17.222759: step: 1460/533, loss: 0.008540666662156582
2023-01-24 08:29:18.314952: step: 1464/533, loss: 0.0019144922262057662
2023-01-24 08:29:19.407223: step: 1468/533, loss: 0.0073351310566067696
2023-01-24 08:29:20.503247: step: 1472/533, loss: 0.006193164270371199
2023-01-24 08:29:21.597448: step: 1476/533, loss: 0.004911424126476049
2023-01-24 08:29:22.690831: step: 1480/533, loss: 0.008170459419488907
2023-01-24 08:29:23.779884: step: 1484/533, loss: 0.008595525287091732
2023-01-24 08:29:24.884801: step: 1488/533, loss: 0.00874514039605856
2023-01-24 08:29:25.950927: step: 1492/533, loss: 0.009293623268604279
2023-01-24 08:29:27.042194: step: 1496/533, loss: 0.014566043391823769
2023-01-24 08:29:28.113951: step: 1500/533, loss: 0.019961152225732803
2023-01-24 08:29:29.215746: step: 1504/533, loss: 0.006007041782140732
2023-01-24 08:29:30.318353: step: 1508/533, loss: 0.008839351125061512
2023-01-24 08:29:31.395440: step: 1512/533, loss: 0.003231944516301155
2023-01-24 08:29:32.489994: step: 1516/533, loss: 6.585566006833687e-05
2023-01-24 08:29:33.579325: step: 1520/533, loss: 0.017773063853383064
2023-01-24 08:29:34.669683: step: 1524/533, loss: 0.00040056323632597923
2023-01-24 08:29:35.794238: step: 1528/533, loss: 0.00805804505944252
2023-01-24 08:29:36.880181: step: 1532/533, loss: 0.01381621602922678
2023-01-24 08:29:37.972376: step: 1536/533, loss: 0.014407510869204998
2023-01-24 08:29:39.056837: step: 1540/533, loss: 0.004196155350655317
2023-01-24 08:29:40.155586: step: 1544/533, loss: 0.015520529821515083
2023-01-24 08:29:41.252832: step: 1548/533, loss: 0.0006441440200433135
2023-01-24 08:29:42.350455: step: 1552/533, loss: 0.009747505187988281
2023-01-24 08:29:43.430374: step: 1556/533, loss: 0.022432971745729446
2023-01-24 08:29:44.514542: step: 1560/533, loss: 0.02289796620607376
2023-01-24 08:29:45.598091: step: 1564/533, loss: 0.012817814946174622
2023-01-24 08:29:46.696702: step: 1568/533, loss: 0.002060966333374381
2023-01-24 08:29:47.778648: step: 1572/533, loss: 0.0031738271936774254
2023-01-24 08:29:48.852699: step: 1576/533, loss: 0.009219926781952381
2023-01-24 08:29:49.962754: step: 1580/533, loss: 0.0008039276581257582
2023-01-24 08:29:51.035640: step: 1584/533, loss: 0.007807258982211351
2023-01-24 08:29:52.118520: step: 1588/533, loss: 0.0004191139596514404
2023-01-24 08:29:53.210519: step: 1592/533, loss: 0.003712521633133292
2023-01-24 08:29:54.280262: step: 1596/533, loss: 0.0020694562699645758
2023-01-24 08:29:55.356759: step: 1600/533, loss: 0.0029528846498578787
2023-01-24 08:29:56.437845: step: 1604/533, loss: 0.005635757464915514
2023-01-24 08:29:57.506365: step: 1608/533, loss: 0.0015668179839849472
2023-01-24 08:29:58.594664: step: 1612/533, loss: 0.02344406396150589
2023-01-24 08:29:59.678772: step: 1616/533, loss: 0.003390647005289793
2023-01-24 08:30:00.779266: step: 1620/533, loss: 0.010656052269041538
2023-01-24 08:30:01.865568: step: 1624/533, loss: 0.00897624809294939
2023-01-24 08:30:02.954348: step: 1628/533, loss: 0.5037548542022705
2023-01-24 08:30:04.050700: step: 1632/533, loss: 0.02160961739718914
2023-01-24 08:30:05.143664: step: 1636/533, loss: 0.005211865529417992
2023-01-24 08:30:06.230260: step: 1640/533, loss: 0.0032133758068084717
2023-01-24 08:30:07.322722: step: 1644/533, loss: 0.005215062294155359
2023-01-24 08:30:08.422052: step: 1648/533, loss: 0.008202360942959785
2023-01-24 08:30:09.507548: step: 1652/533, loss: 0.021905438974499702
2023-01-24 08:30:10.620360: step: 1656/533, loss: 0.014565154910087585
2023-01-24 08:30:11.696222: step: 1660/533, loss: 0.0033631641417741776
2023-01-24 08:30:12.796058: step: 1664/533, loss: 0.017117174342274666
2023-01-24 08:30:13.929594: step: 1668/533, loss: 0.0217277854681015
2023-01-24 08:30:15.021928: step: 1672/533, loss: 0.004690199159085751
2023-01-24 08:30:16.132007: step: 1676/533, loss: 0.00572905084118247
2023-01-24 08:30:17.210051: step: 1680/533, loss: 0.008707641623914242
2023-01-24 08:30:18.296954: step: 1684/533, loss: 0.005363733973354101
2023-01-24 08:30:19.379657: step: 1688/533, loss: 0.0001943397946888581
2023-01-24 08:30:20.472468: step: 1692/533, loss: 0.007281597703695297
2023-01-24 08:30:21.545358: step: 1696/533, loss: 0.0017045268323272467
2023-01-24 08:30:22.612864: step: 1700/533, loss: 0.004236613400280476
2023-01-24 08:30:23.693865: step: 1704/533, loss: 0.01945505477488041
2023-01-24 08:30:24.805434: step: 1708/533, loss: 0.05078817158937454
2023-01-24 08:30:25.908004: step: 1712/533, loss: 0.0049336692318320274
2023-01-24 08:30:27.023984: step: 1716/533, loss: 0.015100253745913506
2023-01-24 08:30:28.105547: step: 1720/533, loss: 0.05677539482712746
2023-01-24 08:30:29.223776: step: 1724/533, loss: 0.010190844535827637
2023-01-24 08:30:30.330279: step: 1728/533, loss: 0.008998706005513668
2023-01-24 08:30:31.442528: step: 1732/533, loss: 0.011095398105680943
2023-01-24 08:30:32.555472: step: 1736/533, loss: 0.004247514996677637
2023-01-24 08:30:33.665098: step: 1740/533, loss: 0.012786713428795338
2023-01-24 08:30:34.788607: step: 1744/533, loss: 0.004105247091501951
2023-01-24 08:30:35.891852: step: 1748/533, loss: 0.006403415463864803
2023-01-24 08:30:36.975318: step: 1752/533, loss: 0.025865264236927032
2023-01-24 08:30:38.100942: step: 1756/533, loss: 0.007779261097311974
2023-01-24 08:30:39.222752: step: 1760/533, loss: 0.009999880567193031
2023-01-24 08:30:40.325317: step: 1764/533, loss: 0.005238991230726242
2023-01-24 08:30:41.407901: step: 1768/533, loss: 0.010284045711159706
2023-01-24 08:30:42.506928: step: 1772/533, loss: 0.005169834941625595
2023-01-24 08:30:43.581650: step: 1776/533, loss: 0.0024976152926683426
2023-01-24 08:30:44.688576: step: 1780/533, loss: 0.00045306183164939284
2023-01-24 08:30:45.776790: step: 1784/533, loss: 0.005821184255182743
2023-01-24 08:30:46.869640: step: 1788/533, loss: 0.018045464530587196
2023-01-24 08:30:47.985089: step: 1792/533, loss: 0.011091144755482674
2023-01-24 08:30:49.076146: step: 1796/533, loss: 0.030824551358819008
2023-01-24 08:30:50.171143: step: 1800/533, loss: 0.004466402344405651
2023-01-24 08:30:51.248803: step: 1804/533, loss: 0.008466042578220367
2023-01-24 08:30:52.351728: step: 1808/533, loss: 0.015544356778264046
2023-01-24 08:30:53.445996: step: 1812/533, loss: 0.0034515478182584047
2023-01-24 08:30:54.557026: step: 1816/533, loss: 0.022414803504943848
2023-01-24 08:30:55.631056: step: 1820/533, loss: 0.0033936735708266497
2023-01-24 08:30:56.721026: step: 1824/533, loss: 0.008542832918465137
2023-01-24 08:30:57.823048: step: 1828/533, loss: 0.005387830547988415
2023-01-24 08:30:58.906262: step: 1832/533, loss: 0.003324429504573345
2023-01-24 08:30:59.983680: step: 1836/533, loss: 0.02862391248345375
2023-01-24 08:31:01.075278: step: 1840/533, loss: 0.0024993368424475193
2023-01-24 08:31:02.164305: step: 1844/533, loss: 0.017555812373757362
2023-01-24 08:31:03.253633: step: 1848/533, loss: 0.0038940501399338245
2023-01-24 08:31:04.354257: step: 1852/533, loss: 0.01883249171078205
2023-01-24 08:31:05.439822: step: 1856/533, loss: 0.0008555574459023774
2023-01-24 08:31:06.526912: step: 1860/533, loss: 0.0024488780181854963
2023-01-24 08:31:07.653878: step: 1864/533, loss: 0.005075226072221994
2023-01-24 08:31:08.739036: step: 1868/533, loss: 0.00033264042576774955
2023-01-24 08:31:09.820576: step: 1872/533, loss: 0.0056279669515788555
2023-01-24 08:31:10.930858: step: 1876/533, loss: 0.0077282446436584
2023-01-24 08:31:12.025987: step: 1880/533, loss: 0.0691063180565834
2023-01-24 08:31:13.146370: step: 1884/533, loss: 0.002962135011330247
2023-01-24 08:31:14.216852: step: 1888/533, loss: 0.02480354905128479
2023-01-24 08:31:15.308858: step: 1892/533, loss: 0.04752205312252045
2023-01-24 08:31:16.386730: step: 1896/533, loss: 0.010196289978921413
2023-01-24 08:31:17.508851: step: 1900/533, loss: 0.027523363009095192
2023-01-24 08:31:18.600277: step: 1904/533, loss: 0.0008730306290090084
2023-01-24 08:31:19.688245: step: 1908/533, loss: 0.005531039088964462
2023-01-24 08:31:20.786119: step: 1912/533, loss: 0.0053479946218431
2023-01-24 08:31:21.868698: step: 1916/533, loss: 0.00028163965907879174
2023-01-24 08:31:22.955702: step: 1920/533, loss: 0.0012347124284133315
2023-01-24 08:31:24.047293: step: 1924/533, loss: 0.01590345799922943
2023-01-24 08:31:25.126048: step: 1928/533, loss: 0.012775103561580181
2023-01-24 08:31:26.236082: step: 1932/533, loss: 0.006243525072932243
2023-01-24 08:31:27.333388: step: 1936/533, loss: 0.00498352013528347
2023-01-24 08:31:28.418370: step: 1940/533, loss: 0.004675451200455427
2023-01-24 08:31:29.496090: step: 1944/533, loss: 0.06111850216984749
2023-01-24 08:31:30.561973: step: 1948/533, loss: 0.0066849589347839355
2023-01-24 08:31:31.660177: step: 1952/533, loss: 0.0013787515927106142
2023-01-24 08:31:32.734532: step: 1956/533, loss: 0.005368220154196024
2023-01-24 08:31:33.826231: step: 1960/533, loss: 0.008241712115705013
2023-01-24 08:31:34.917220: step: 1964/533, loss: 0.008337819017469883
2023-01-24 08:31:35.986337: step: 1968/533, loss: 0.0453915037214756
2023-01-24 08:31:37.082990: step: 1972/533, loss: 0.0029817766044288874
2023-01-24 08:31:38.189997: step: 1976/533, loss: 0.006813200190663338
2023-01-24 08:31:39.289063: step: 1980/533, loss: 0.01197411585599184
2023-01-24 08:31:40.383633: step: 1984/533, loss: 3.603210279834457e-05
2023-01-24 08:31:41.461815: step: 1988/533, loss: 0.010874934494495392
2023-01-24 08:31:42.553308: step: 1992/533, loss: 0.010197240859270096
2023-01-24 08:31:43.666299: step: 1996/533, loss: 0.0054798065684735775
2023-01-24 08:31:44.739580: step: 2000/533, loss: 0.0030605988577008247
2023-01-24 08:31:45.853169: step: 2004/533, loss: 0.00787048414349556
2023-01-24 08:31:46.933927: step: 2008/533, loss: 0.009772655554115772
2023-01-24 08:31:48.024818: step: 2012/533, loss: 0.0020878168288618326
2023-01-24 08:31:49.106394: step: 2016/533, loss: 0.010122595354914665
2023-01-24 08:31:50.202819: step: 2020/533, loss: 0.010408248752355576
2023-01-24 08:31:51.299211: step: 2024/533, loss: 0.01898432895541191
2023-01-24 08:31:52.396705: step: 2028/533, loss: 0.015994079411029816
2023-01-24 08:31:53.483848: step: 2032/533, loss: 0.005987475160509348
2023-01-24 08:31:54.554965: step: 2036/533, loss: 0.018822794780135155
2023-01-24 08:31:55.641067: step: 2040/533, loss: 0.030720332637429237
2023-01-24 08:31:56.735514: step: 2044/533, loss: 0.0073183635249733925
2023-01-24 08:31:57.833674: step: 2048/533, loss: 0.0005022716941311955
2023-01-24 08:31:58.912850: step: 2052/533, loss: 0.011391906067728996
2023-01-24 08:31:59.996624: step: 2056/533, loss: 0.007715482264757156
2023-01-24 08:32:01.116821: step: 2060/533, loss: 0.013402309268712997
2023-01-24 08:32:02.226327: step: 2064/533, loss: 0.005680052563548088
2023-01-24 08:32:03.315684: step: 2068/533, loss: 0.007821696810424328
2023-01-24 08:32:04.411348: step: 2072/533, loss: 0.004698383621871471
2023-01-24 08:32:05.474510: step: 2076/533, loss: 0.00032328395172953606
2023-01-24 08:32:06.558631: step: 2080/533, loss: 0.015442375093698502
2023-01-24 08:32:07.643893: step: 2084/533, loss: 0.014472700655460358
2023-01-24 08:32:08.720555: step: 2088/533, loss: 0.00486370176076889
2023-01-24 08:32:09.798452: step: 2092/533, loss: 0.004756824113428593
2023-01-24 08:32:10.881436: step: 2096/533, loss: 0.008221405558288097
2023-01-24 08:32:11.995070: step: 2100/533, loss: 0.010863452218472958
2023-01-24 08:32:13.100903: step: 2104/533, loss: 0.007649326231330633
2023-01-24 08:32:14.199878: step: 2108/533, loss: 0.0021940923761576414
2023-01-24 08:32:15.285723: step: 2112/533, loss: 0.0007222890853881836
2023-01-24 08:32:16.374270: step: 2116/533, loss: 0.02949761413037777
2023-01-24 08:32:17.451589: step: 2120/533, loss: 0.008427060209214687
2023-01-24 08:32:18.540257: step: 2124/533, loss: 0.0008449953165836632
2023-01-24 08:32:19.625575: step: 2128/533, loss: 0.005732063204050064
2023-01-24 08:32:20.739762: step: 2132/533, loss: 0.001361346454359591
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38214155749636103, 'r': 0.33210784313725494, 'f1': 0.3553722504230119}, 'combined': 0.2618532371537982, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3986876829708791, 'r': 0.3638025107109272, 'f1': 0.38044707002449896}, 'combined': 0.25363138001633256, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3580442583732058, 'r': 0.31931840879583817, 'f1': 0.3375743258483585}, 'combined': 0.24873897694089572, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38714549865402476, 'r': 0.30934414363605245, 'f1': 0.34389942210742336}, 'combined': 0.22926628140494884, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34399612355402415, 'r': 0.312011664248242, 'f1': 0.3272241732513902}, 'combined': 0.24111254871155066, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38361890383378366, 'r': 0.3467324707728429, 'f1': 0.36424421172096627}, 'combined': 0.24282947448064413, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661572385213968, 'r': 0.3216903253043771, 'f1': 0.34248646754627615}, 'combined': 0.2523584497709403, 'stategy': 1, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38773270130457727, 'r': 0.30906770132836014, 'f1': 0.34395977461904176}, 'combined': 0.22930651641269445, 'stategy': 1, 'epoch': 2}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 08:34:39.127328: step: 4/533, loss: 0.006118770223110914
2023-01-24 08:34:40.211680: step: 8/533, loss: 0.014703663066029549
2023-01-24 08:34:41.300099: step: 12/533, loss: 0.0046440716832876205
2023-01-24 08:34:42.397098: step: 16/533, loss: 0.005283764563500881
2023-01-24 08:34:43.455871: step: 20/533, loss: 0.015359664335846901
2023-01-24 08:34:44.520017: step: 24/533, loss: 0.00010607547301333398
2023-01-24 08:34:45.604045: step: 28/533, loss: 0.008900669403374195
2023-01-24 08:34:46.688797: step: 32/533, loss: 0.005448069889098406
2023-01-24 08:34:47.769830: step: 36/533, loss: 0.01261278335005045
2023-01-24 08:34:48.856564: step: 40/533, loss: 0.003998877480626106
2023-01-24 08:34:49.958999: step: 44/533, loss: 0.030507847666740417
2023-01-24 08:34:51.037648: step: 48/533, loss: 0.0004062847583554685
2023-01-24 08:34:52.123186: step: 52/533, loss: 0.00399383157491684
2023-01-24 08:34:53.202049: step: 56/533, loss: 0.011441242881119251
2023-01-24 08:34:54.292467: step: 60/533, loss: 0.013541151769459248
2023-01-24 08:34:55.373331: step: 64/533, loss: 0.0020209867507219315
2023-01-24 08:34:56.489895: step: 68/533, loss: 0.012853285297751427
2023-01-24 08:34:57.603533: step: 72/533, loss: 0.005656687542796135
2023-01-24 08:34:58.684175: step: 76/533, loss: 0.008628097362816334
2023-01-24 08:34:59.783655: step: 80/533, loss: 0.007806643843650818
2023-01-24 08:35:00.877789: step: 84/533, loss: 0.02048680931329727
2023-01-24 08:35:01.960801: step: 88/533, loss: 0.041220538318157196
2023-01-24 08:35:03.046186: step: 92/533, loss: 0.002415992319583893
2023-01-24 08:35:04.125974: step: 96/533, loss: 0.011897149495780468
2023-01-24 08:35:05.227276: step: 100/533, loss: 0.0030667551327496767
2023-01-24 08:35:06.314631: step: 104/533, loss: 0.021796705201268196
2023-01-24 08:35:07.396143: step: 108/533, loss: 0.007715755142271519
2023-01-24 08:35:08.492705: step: 112/533, loss: 0.003449289361014962
2023-01-24 08:35:09.597275: step: 116/533, loss: 0.001858592964708805
2023-01-24 08:35:10.669468: step: 120/533, loss: 0.027058057487010956
2023-01-24 08:35:11.747175: step: 124/533, loss: 0.00010196872608503327
2023-01-24 08:35:12.837583: step: 128/533, loss: 0.014292423613369465
2023-01-24 08:35:13.927014: step: 132/533, loss: 0.0046984474174678326
2023-01-24 08:35:14.984355: step: 136/533, loss: 0.0022962249349802732
2023-01-24 08:35:16.078953: step: 140/533, loss: 0.006350645795464516
2023-01-24 08:35:17.185017: step: 144/533, loss: 0.014933697879314423
2023-01-24 08:35:18.275030: step: 148/533, loss: 0.007846811786293983
2023-01-24 08:35:19.351997: step: 152/533, loss: 0.0009497525170445442
2023-01-24 08:35:20.445937: step: 156/533, loss: 0.0006582781206816435
2023-01-24 08:35:21.539650: step: 160/533, loss: 0.017970813438296318
2023-01-24 08:35:22.623020: step: 164/533, loss: 0.0
2023-01-24 08:35:23.709393: step: 168/533, loss: 0.0009659319184720516
2023-01-24 08:35:24.794522: step: 172/533, loss: 0.0024468316696584225
2023-01-24 08:35:25.885801: step: 176/533, loss: 0.0005613568355329335
2023-01-24 08:35:26.972779: step: 180/533, loss: 0.010789608582854271
2023-01-24 08:35:28.051556: step: 184/533, loss: 0.004244900308549404
2023-01-24 08:35:29.169632: step: 188/533, loss: 0.005197590682655573
2023-01-24 08:35:30.260318: step: 192/533, loss: 0.004591850563883781
2023-01-24 08:35:31.375937: step: 196/533, loss: 0.004987283144146204
2023-01-24 08:35:32.458054: step: 200/533, loss: 0.004888602532446384
2023-01-24 08:35:33.545912: step: 204/533, loss: 0.0025193295441567898
2023-01-24 08:35:34.639780: step: 208/533, loss: 0.0030347593128681183
2023-01-24 08:35:35.740693: step: 212/533, loss: 0.0025758726987987757
2023-01-24 08:35:36.857426: step: 216/533, loss: 0.007303591817617416
2023-01-24 08:35:37.943543: step: 220/533, loss: 0.013987819664180279
2023-01-24 08:35:39.016048: step: 224/533, loss: 0.003534137737005949
2023-01-24 08:35:40.104228: step: 228/533, loss: 0.004555874038487673
2023-01-24 08:35:41.219266: step: 232/533, loss: 0.0344444178044796
2023-01-24 08:35:42.293782: step: 236/533, loss: 0.0011114792432636023
2023-01-24 08:35:43.393107: step: 240/533, loss: 0.023959483951330185
2023-01-24 08:35:44.463420: step: 244/533, loss: 0.024899600073695183
2023-01-24 08:35:45.556651: step: 248/533, loss: 0.003945876378566027
2023-01-24 08:35:46.655017: step: 252/533, loss: 0.014026496559381485
2023-01-24 08:35:47.769332: step: 256/533, loss: 0.000552118755877018
2023-01-24 08:35:48.865975: step: 260/533, loss: 0.007553809322416782
2023-01-24 08:35:49.981732: step: 264/533, loss: 0.0009558791061863303
2023-01-24 08:35:51.074211: step: 268/533, loss: 0.0037639797665178776
2023-01-24 08:35:52.144600: step: 272/533, loss: 0.016110433265566826
2023-01-24 08:35:53.240089: step: 276/533, loss: 0.0051015461795032024
2023-01-24 08:35:54.307851: step: 280/533, loss: 0.0025733630172908306
2023-01-24 08:35:55.401006: step: 284/533, loss: 0.0002571088552940637
2023-01-24 08:35:56.481483: step: 288/533, loss: 0.009741226211190224
2023-01-24 08:35:57.581478: step: 292/533, loss: 0.002804717281833291
2023-01-24 08:35:58.658611: step: 296/533, loss: 0.0044760676100850105
2023-01-24 08:35:59.763493: step: 300/533, loss: 0.005719127599149942
2023-01-24 08:36:00.874599: step: 304/533, loss: 0.002969194669276476
2023-01-24 08:36:01.949591: step: 308/533, loss: 0.02568025514483452
2023-01-24 08:36:03.033041: step: 312/533, loss: 0.0017932357732206583
2023-01-24 08:36:04.126765: step: 316/533, loss: 0.004485869314521551
2023-01-24 08:36:05.203601: step: 320/533, loss: 0.00326410960406065
2023-01-24 08:36:06.314392: step: 324/533, loss: 0.00024074445536825806
2023-01-24 08:36:07.397953: step: 328/533, loss: 0.005698962602764368
2023-01-24 08:36:08.484972: step: 332/533, loss: 0.007035334128886461
2023-01-24 08:36:09.587281: step: 336/533, loss: 0.0006184560479596257
2023-01-24 08:36:10.700535: step: 340/533, loss: 0.007783230394124985
2023-01-24 08:36:11.782266: step: 344/533, loss: 0.0034678690135478973
2023-01-24 08:36:12.866686: step: 348/533, loss: 6.758084055036306e-05
2023-01-24 08:36:13.946776: step: 352/533, loss: 0.0022649713791906834
2023-01-24 08:36:15.017427: step: 356/533, loss: 0.01242430042475462
2023-01-24 08:36:16.107394: step: 360/533, loss: 0.013250239193439484
2023-01-24 08:36:17.203157: step: 364/533, loss: 0.0021397678647190332
2023-01-24 08:36:18.284363: step: 368/533, loss: 0.007774724159389734
2023-01-24 08:36:19.365237: step: 372/533, loss: 0.005237084347754717
2023-01-24 08:36:20.427164: step: 376/533, loss: 0.005033636465668678
2023-01-24 08:36:21.528118: step: 380/533, loss: 0.004198496229946613
2023-01-24 08:36:22.611317: step: 384/533, loss: 0.01605236530303955
2023-01-24 08:36:23.708731: step: 388/533, loss: 0.002660319209098816
2023-01-24 08:36:24.786726: step: 392/533, loss: 0.0006361760897561908
2023-01-24 08:36:25.877682: step: 396/533, loss: 0.0006277816719375551
2023-01-24 08:36:26.993846: step: 400/533, loss: 0.00720903929322958
2023-01-24 08:36:28.075745: step: 404/533, loss: 0.005955609027296305
2023-01-24 08:36:29.147828: step: 408/533, loss: 0.0005824522813782096
2023-01-24 08:36:30.252418: step: 412/533, loss: 0.0024764530826359987
2023-01-24 08:36:31.393567: step: 416/533, loss: 0.00775839714333415
2023-01-24 08:36:32.498015: step: 420/533, loss: 0.0013018302852287889
2023-01-24 08:36:33.592135: step: 424/533, loss: 0.01108357310295105
2023-01-24 08:36:34.676796: step: 428/533, loss: 0.029821692034602165
2023-01-24 08:36:35.765274: step: 432/533, loss: 0.007652286905795336
2023-01-24 08:36:36.870679: step: 436/533, loss: 0.0066063725389540195
2023-01-24 08:36:37.948246: step: 440/533, loss: 0.008683830499649048
2023-01-24 08:36:39.036850: step: 444/533, loss: 0.002310235286131501
2023-01-24 08:36:40.159087: step: 448/533, loss: 0.011088509112596512
2023-01-24 08:36:41.239854: step: 452/533, loss: 0.012481455691158772
2023-01-24 08:36:42.332192: step: 456/533, loss: 0.005370802711695433
2023-01-24 08:36:43.420053: step: 460/533, loss: 0.0012968775117769837
2023-01-24 08:36:44.505486: step: 464/533, loss: 0.01297498308122158
2023-01-24 08:36:45.593983: step: 468/533, loss: 0.004560941830277443
2023-01-24 08:36:46.674238: step: 472/533, loss: 0.024240905418992043
2023-01-24 08:36:47.764591: step: 476/533, loss: 0.003770707407966256
2023-01-24 08:36:48.849881: step: 480/533, loss: 0.004520080983638763
2023-01-24 08:36:49.960865: step: 484/533, loss: 0.0009275188785977662
2023-01-24 08:36:51.049975: step: 488/533, loss: 0.007845600135624409
2023-01-24 08:36:52.136062: step: 492/533, loss: 0.006349322851747274
2023-01-24 08:36:53.202063: step: 496/533, loss: 0.000252217665547505
2023-01-24 08:36:54.303796: step: 500/533, loss: 0.006873534992337227
2023-01-24 08:36:55.384547: step: 504/533, loss: 0.006984577979892492
2023-01-24 08:36:56.485115: step: 508/533, loss: 0.01819751225411892
2023-01-24 08:36:57.576819: step: 512/533, loss: 0.0003609473060350865
2023-01-24 08:36:58.657375: step: 516/533, loss: 0.008734301663935184
2023-01-24 08:36:59.735733: step: 520/533, loss: 0.0009985660435631871
2023-01-24 08:37:00.819631: step: 524/533, loss: 0.00890253484249115
2023-01-24 08:37:01.916382: step: 528/533, loss: 0.013230997137725353
2023-01-24 08:37:03.032584: step: 532/533, loss: 0.01895740069448948
2023-01-24 08:37:04.130113: step: 536/533, loss: 0.014239400625228882
2023-01-24 08:37:05.206836: step: 540/533, loss: 0.008985381573438644
2023-01-24 08:37:06.286869: step: 544/533, loss: 0.0010546232806518674
2023-01-24 08:37:07.396325: step: 548/533, loss: 0.005269261542707682
2023-01-24 08:37:08.474952: step: 552/533, loss: 0.006399022415280342
2023-01-24 08:37:09.533123: step: 556/533, loss: 0.0037339474074542522
2023-01-24 08:37:10.626979: step: 560/533, loss: 0.014510486274957657
2023-01-24 08:37:11.733873: step: 564/533, loss: 0.001337043591775
2023-01-24 08:37:12.831129: step: 568/533, loss: 0.0044184112921357155
2023-01-24 08:37:13.928387: step: 572/533, loss: 0.013236208818852901
2023-01-24 08:37:15.032097: step: 576/533, loss: 0.004236114211380482
2023-01-24 08:37:16.131741: step: 580/533, loss: 0.0006864868919365108
2023-01-24 08:37:17.227221: step: 584/533, loss: 0.01933201216161251
2023-01-24 08:37:18.305178: step: 588/533, loss: 0.02179069072008133
2023-01-24 08:37:19.417597: step: 592/533, loss: 0.0031849825754761696
2023-01-24 08:37:20.517773: step: 596/533, loss: 0.003139243694022298
2023-01-24 08:37:21.601021: step: 600/533, loss: 0.012803075835108757
2023-01-24 08:37:22.707499: step: 604/533, loss: 0.008528721518814564
2023-01-24 08:37:23.794443: step: 608/533, loss: 0.001875127898529172
2023-01-24 08:37:24.891314: step: 612/533, loss: 0.007499920669943094
2023-01-24 08:37:25.985332: step: 616/533, loss: 0.005314612295478582
2023-01-24 08:37:27.085465: step: 620/533, loss: 0.008847314864397049
2023-01-24 08:37:28.161226: step: 624/533, loss: 0.02933959849178791
2023-01-24 08:37:29.288366: step: 628/533, loss: 0.013531472533941269
2023-01-24 08:37:30.385682: step: 632/533, loss: 0.0037702934350818396
2023-01-24 08:37:31.494334: step: 636/533, loss: 0.0009399430127814412
2023-01-24 08:37:32.598026: step: 640/533, loss: 0.00299697439186275
2023-01-24 08:37:33.698098: step: 644/533, loss: 0.01007540337741375
2023-01-24 08:37:34.783298: step: 648/533, loss: 0.00026676637935452163
2023-01-24 08:37:35.869276: step: 652/533, loss: 0.0173114612698555
2023-01-24 08:37:36.949308: step: 656/533, loss: 0.013586419634521008
2023-01-24 08:37:38.032301: step: 660/533, loss: 0.003772606374695897
2023-01-24 08:37:39.126512: step: 664/533, loss: 0.0008949270122684538
2023-01-24 08:37:40.226311: step: 668/533, loss: 0.004481630399823189
2023-01-24 08:37:41.309727: step: 672/533, loss: 0.00285608833655715
2023-01-24 08:37:42.416278: step: 676/533, loss: 0.004511387087404728
2023-01-24 08:37:43.516377: step: 680/533, loss: 0.00862230733036995
2023-01-24 08:37:44.605788: step: 684/533, loss: 0.0015266514383256435
2023-01-24 08:37:45.696728: step: 688/533, loss: 0.002528828103095293
2023-01-24 08:37:46.786748: step: 692/533, loss: 0.00457037752494216
2023-01-24 08:37:47.872988: step: 696/533, loss: 0.002812292193993926
2023-01-24 08:37:48.977158: step: 700/533, loss: 0.0035629933699965477
2023-01-24 08:37:50.084859: step: 704/533, loss: 0.004719170276075602
2023-01-24 08:37:51.186691: step: 708/533, loss: 0.006282598711550236
2023-01-24 08:37:52.273935: step: 712/533, loss: 0.0001030673593049869
2023-01-24 08:37:53.378751: step: 716/533, loss: 0.025101160630583763
2023-01-24 08:37:54.461905: step: 720/533, loss: 0.003503191750496626
2023-01-24 08:37:55.576073: step: 724/533, loss: 0.007284685969352722
2023-01-24 08:37:56.654905: step: 728/533, loss: 0.007369487080723047
2023-01-24 08:37:57.767835: step: 732/533, loss: 0.00882403738796711
2023-01-24 08:37:58.870506: step: 736/533, loss: 0.018489371985197067
2023-01-24 08:37:59.940449: step: 740/533, loss: 0.0010913822334259748
2023-01-24 08:38:01.066691: step: 744/533, loss: 0.004477705340832472
2023-01-24 08:38:02.149100: step: 748/533, loss: 0.00014462527178693563
2023-01-24 08:38:03.228529: step: 752/533, loss: 0.0018365528667345643
2023-01-24 08:38:04.297410: step: 756/533, loss: 0.005957454908639193
2023-01-24 08:38:05.382787: step: 760/533, loss: 0.01390497013926506
2023-01-24 08:38:06.467719: step: 764/533, loss: 0.00043903334881179035
2023-01-24 08:38:07.537340: step: 768/533, loss: 0.011076758615672588
2023-01-24 08:38:08.637772: step: 772/533, loss: 0.005151447840034962
2023-01-24 08:38:09.728129: step: 776/533, loss: 0.010366384871304035
2023-01-24 08:38:10.805689: step: 780/533, loss: 0.0005746734095737338
2023-01-24 08:38:11.884215: step: 784/533, loss: 0.012791788205504417
2023-01-24 08:38:13.006440: step: 788/533, loss: 0.007419717498123646
2023-01-24 08:38:14.112518: step: 792/533, loss: 0.013677547685801983
2023-01-24 08:38:15.223677: step: 796/533, loss: 0.006773319561034441
2023-01-24 08:38:16.319266: step: 800/533, loss: 0.00592442462220788
2023-01-24 08:38:17.410121: step: 804/533, loss: 0.0017089222092181444
2023-01-24 08:38:18.503932: step: 808/533, loss: 0.008174057118594646
2023-01-24 08:38:19.612839: step: 812/533, loss: 0.00758172245696187
2023-01-24 08:38:20.711250: step: 816/533, loss: 0.0034943795762956142
2023-01-24 08:38:21.801153: step: 820/533, loss: 0.008244850672781467
2023-01-24 08:38:22.878628: step: 824/533, loss: 0.006884617730975151
2023-01-24 08:38:23.976241: step: 828/533, loss: 0.01602698676288128
2023-01-24 08:38:25.069773: step: 832/533, loss: 0.010964437387883663
2023-01-24 08:38:26.210674: step: 836/533, loss: 0.006394014228135347
2023-01-24 08:38:27.301413: step: 840/533, loss: 0.01050159614533186
2023-01-24 08:38:28.410136: step: 844/533, loss: 0.0035872897133231163
2023-01-24 08:38:29.500366: step: 848/533, loss: 0.0014508324675261974
2023-01-24 08:38:30.588941: step: 852/533, loss: 0.015373904258012772
2023-01-24 08:38:31.690420: step: 856/533, loss: 0.003416240680962801
2023-01-24 08:38:32.793792: step: 860/533, loss: 0.004588097333908081
2023-01-24 08:38:33.872393: step: 864/533, loss: 0.005256480537354946
2023-01-24 08:38:34.958958: step: 868/533, loss: 0.005975024774670601
2023-01-24 08:38:36.096700: step: 872/533, loss: 0.010174739174544811
2023-01-24 08:38:37.232806: step: 876/533, loss: 0.007150118704885244
2023-01-24 08:38:38.340297: step: 880/533, loss: 0.017615733668208122
2023-01-24 08:38:39.469171: step: 884/533, loss: 0.0036849896423518658
2023-01-24 08:38:40.592703: step: 888/533, loss: 0.0053284368477761745
2023-01-24 08:38:41.683325: step: 892/533, loss: 0.0034503138158470392
2023-01-24 08:38:42.773943: step: 896/533, loss: 0.004910253919661045
2023-01-24 08:38:43.899248: step: 900/533, loss: 0.0038117968942970037
2023-01-24 08:38:44.990071: step: 904/533, loss: 0.00020632223458960652
2023-01-24 08:38:46.068068: step: 908/533, loss: 0.019284116104245186
2023-01-24 08:38:47.175820: step: 912/533, loss: 0.00373491900973022
2023-01-24 08:38:48.273948: step: 916/533, loss: 0.0030482320580631495
2023-01-24 08:38:49.362404: step: 920/533, loss: 0.00017934052448254079
2023-01-24 08:38:50.451494: step: 924/533, loss: 0.0055897473357617855
2023-01-24 08:38:51.561289: step: 928/533, loss: 0.01252665277570486
2023-01-24 08:38:52.648829: step: 932/533, loss: 0.004019405692815781
2023-01-24 08:38:53.774224: step: 936/533, loss: 0.0028561933431774378
2023-01-24 08:38:54.865659: step: 940/533, loss: 0.016749074682593346
2023-01-24 08:38:55.958630: step: 944/533, loss: 0.0022937788162380457
2023-01-24 08:38:57.074934: step: 948/533, loss: 0.03329522907733917
2023-01-24 08:38:58.171800: step: 952/533, loss: 0.006107631605118513
2023-01-24 08:38:59.264121: step: 956/533, loss: 0.00467244628816843
2023-01-24 08:39:00.356590: step: 960/533, loss: 0.004061570856720209
2023-01-24 08:39:01.474118: step: 964/533, loss: 0.0002557274419814348
2023-01-24 08:39:02.567473: step: 968/533, loss: 0.009036673232913017
2023-01-24 08:39:03.669136: step: 972/533, loss: 0.008398909121751785
2023-01-24 08:39:04.768556: step: 976/533, loss: 0.0043978760950267315
2023-01-24 08:39:05.870165: step: 980/533, loss: 0.012404527515172958
2023-01-24 08:39:06.970776: step: 984/533, loss: 0.003445059759542346
2023-01-24 08:39:08.059173: step: 988/533, loss: 0.0067526958882808685
2023-01-24 08:39:09.133997: step: 992/533, loss: 0.004129042848944664
2023-01-24 08:39:10.227354: step: 996/533, loss: 0.0043664718978106976
2023-01-24 08:39:11.334971: step: 1000/533, loss: 0.002662316430360079
2023-01-24 08:39:12.450535: step: 1004/533, loss: 0.0048017436638474464
2023-01-24 08:39:13.529927: step: 1008/533, loss: 0.018005434423685074
2023-01-24 08:39:14.631001: step: 1012/533, loss: 2.0456895072129555e-05
2023-01-24 08:39:15.721847: step: 1016/533, loss: 0.002695696661248803
2023-01-24 08:39:16.813906: step: 1020/533, loss: 0.0007003230275586247
2023-01-24 08:39:17.899750: step: 1024/533, loss: 0.0024069342762231827
2023-01-24 08:39:18.983987: step: 1028/533, loss: 0.022311022505164146
2023-01-24 08:39:20.101125: step: 1032/533, loss: 0.0034088718239217997
2023-01-24 08:39:21.190488: step: 1036/533, loss: 0.008243647404015064
2023-01-24 08:39:22.300678: step: 1040/533, loss: 0.007827239111065865
2023-01-24 08:39:23.401142: step: 1044/533, loss: 0.014136862009763718
2023-01-24 08:39:24.492977: step: 1048/533, loss: 0.002621372928842902
2023-01-24 08:39:25.584244: step: 1052/533, loss: 0.003932988736778498
2023-01-24 08:39:26.678735: step: 1056/533, loss: 0.0006086034700274467
2023-01-24 08:39:27.781220: step: 1060/533, loss: 0.004324476700276136
2023-01-24 08:39:28.860584: step: 1064/533, loss: 0.005558311007916927
2023-01-24 08:39:29.970393: step: 1068/533, loss: 0.0024682015646249056
2023-01-24 08:39:31.053846: step: 1072/533, loss: 0.008652478456497192
2023-01-24 08:39:32.151470: step: 1076/533, loss: 0.02330758050084114
2023-01-24 08:39:33.228276: step: 1080/533, loss: 0.0029788215178996325
2023-01-24 08:39:34.321493: step: 1084/533, loss: 0.0036552995443344116
2023-01-24 08:39:35.403084: step: 1088/533, loss: 0.014255226589739323
2023-01-24 08:39:36.498574: step: 1092/533, loss: 0.0058103869669139385
2023-01-24 08:39:37.588668: step: 1096/533, loss: 0.0029024004470556974
2023-01-24 08:39:38.669461: step: 1100/533, loss: 0.00426998408511281
2023-01-24 08:39:39.756095: step: 1104/533, loss: 0.006839405745267868
2023-01-24 08:39:40.863523: step: 1108/533, loss: 0.0003819543053396046
2023-01-24 08:39:41.967908: step: 1112/533, loss: 0.01025199145078659
2023-01-24 08:39:43.082906: step: 1116/533, loss: 0.0032708370126783848
2023-01-24 08:39:44.175781: step: 1120/533, loss: 0.007165829185396433
2023-01-24 08:39:45.276292: step: 1124/533, loss: 0.003947507590055466
2023-01-24 08:39:46.377487: step: 1128/533, loss: 0.00737884733825922
2023-01-24 08:39:47.483084: step: 1132/533, loss: 0.0024132365360856056
2023-01-24 08:39:48.567800: step: 1136/533, loss: 0.0007556846248917282
2023-01-24 08:39:49.669389: step: 1140/533, loss: 0.009593079797923565
2023-01-24 08:39:50.768754: step: 1144/533, loss: 0.0008375486359000206
2023-01-24 08:39:51.877290: step: 1148/533, loss: 0.005098543129861355
2023-01-24 08:39:52.987358: step: 1152/533, loss: 0.0057932473719120026
2023-01-24 08:39:54.076259: step: 1156/533, loss: 0.003219339530915022
2023-01-24 08:39:55.200186: step: 1160/533, loss: 0.0103001045063138
2023-01-24 08:39:56.293147: step: 1164/533, loss: 0.014477171935141087
2023-01-24 08:39:57.375913: step: 1168/533, loss: 0.0029288416262716055
2023-01-24 08:39:58.483190: step: 1172/533, loss: 0.004327130038291216
2023-01-24 08:39:59.596029: step: 1176/533, loss: 0.009184123948216438
2023-01-24 08:40:00.684520: step: 1180/533, loss: 0.004049127455800772
2023-01-24 08:40:01.767681: step: 1184/533, loss: 0.0019646643195301294
2023-01-24 08:40:02.853948: step: 1188/533, loss: 0.009145606309175491
2023-01-24 08:40:03.952735: step: 1192/533, loss: 0.006427613086998463
2023-01-24 08:40:05.050098: step: 1196/533, loss: 0.003301502438262105
2023-01-24 08:40:06.140413: step: 1200/533, loss: 0.002541302004829049
2023-01-24 08:40:07.272018: step: 1204/533, loss: 1.916007386171259e-05
2023-01-24 08:40:08.367736: step: 1208/533, loss: 0.008729702793061733
2023-01-24 08:40:09.481996: step: 1212/533, loss: 0.0033568318467587233
2023-01-24 08:40:10.583970: step: 1216/533, loss: 0.002816008636727929
2023-01-24 08:40:11.692311: step: 1220/533, loss: 0.020496660843491554
2023-01-24 08:40:12.793453: step: 1224/533, loss: 0.021671690046787262
2023-01-24 08:40:13.901519: step: 1228/533, loss: 0.0075273653492331505
2023-01-24 08:40:15.000456: step: 1232/533, loss: 0.01445021852850914
2023-01-24 08:40:16.103721: step: 1236/533, loss: 0.0010652759810909629
2023-01-24 08:40:17.232104: step: 1240/533, loss: 0.006056542973965406
2023-01-24 08:40:18.338187: step: 1244/533, loss: 0.0017354234587401152
2023-01-24 08:40:19.445282: step: 1248/533, loss: 0.004889714531600475
2023-01-24 08:40:20.529402: step: 1252/533, loss: 0.013424985110759735
2023-01-24 08:40:21.611357: step: 1256/533, loss: 0.006447637919336557
2023-01-24 08:40:22.707305: step: 1260/533, loss: 0.005103058181703091
2023-01-24 08:40:23.813699: step: 1264/533, loss: 0.020652005448937416
2023-01-24 08:40:24.888071: step: 1268/533, loss: 0.00011853661271743476
2023-01-24 08:40:25.984460: step: 1272/533, loss: 0.004768815822899342
2023-01-24 08:40:27.081287: step: 1276/533, loss: 0.021360091865062714
2023-01-24 08:40:28.176195: step: 1280/533, loss: 0.00641510309651494
2023-01-24 08:40:29.279257: step: 1284/533, loss: 0.006437957286834717
2023-01-24 08:40:30.383830: step: 1288/533, loss: 0.005619360599666834
2023-01-24 08:40:31.473429: step: 1292/533, loss: 0.00680390652269125
2023-01-24 08:40:32.578289: step: 1296/533, loss: 0.006998311262577772
2023-01-24 08:40:33.664714: step: 1300/533, loss: 0.010151376947760582
2023-01-24 08:40:34.774162: step: 1304/533, loss: 0.0027686208486557007
2023-01-24 08:40:35.873121: step: 1308/533, loss: 0.009506271220743656
2023-01-24 08:40:36.998009: step: 1312/533, loss: 0.03914010524749756
2023-01-24 08:40:38.097932: step: 1316/533, loss: 0.021128041669726372
2023-01-24 08:40:39.193157: step: 1320/533, loss: 0.06894227862358093
2023-01-24 08:40:40.282256: step: 1324/533, loss: 0.0016821441240608692
2023-01-24 08:40:41.354151: step: 1328/533, loss: 0.0015956539427861571
2023-01-24 08:40:42.436462: step: 1332/533, loss: 0.003911303356289864
2023-01-24 08:40:43.524498: step: 1336/533, loss: 0.002362772123888135
2023-01-24 08:40:44.612878: step: 1340/533, loss: 0.013242014683783054
2023-01-24 08:40:45.727429: step: 1344/533, loss: 0.004504440817981958
2023-01-24 08:40:46.836604: step: 1348/533, loss: 0.0029446992557495832
2023-01-24 08:40:47.916290: step: 1352/533, loss: 0.0010684371227398515
2023-01-24 08:40:48.988736: step: 1356/533, loss: 0.0008310745470225811
2023-01-24 08:40:50.075528: step: 1360/533, loss: 0.0006593861035071313
2023-01-24 08:40:51.171653: step: 1364/533, loss: 0.002829943550750613
2023-01-24 08:40:52.255308: step: 1368/533, loss: 0.0020500230602920055
2023-01-24 08:40:53.345393: step: 1372/533, loss: 0.05598868057131767
2023-01-24 08:40:54.434224: step: 1376/533, loss: 0.006958023179322481
2023-01-24 08:40:55.538792: step: 1380/533, loss: 0.004977173637598753
2023-01-24 08:40:56.629332: step: 1384/533, loss: 0.0011519653489813209
2023-01-24 08:40:57.724283: step: 1388/533, loss: 0.002281143795698881
2023-01-24 08:40:58.781952: step: 1392/533, loss: 0.005517764948308468
2023-01-24 08:40:59.876811: step: 1396/533, loss: 0.05155668780207634
2023-01-24 08:41:00.968409: step: 1400/533, loss: 0.0050522321835160255
2023-01-24 08:41:02.061596: step: 1404/533, loss: 0.008300606161355972
2023-01-24 08:41:03.170575: step: 1408/533, loss: 0.0007963587995618582
2023-01-24 08:41:04.274794: step: 1412/533, loss: 0.0231663566082716
2023-01-24 08:41:05.343771: step: 1416/533, loss: 0.00030525788315571845
2023-01-24 08:41:06.437340: step: 1420/533, loss: 0.006735802628099918
2023-01-24 08:41:07.513955: step: 1424/533, loss: 2.628778020152822e-05
2023-01-24 08:41:08.589375: step: 1428/533, loss: 0.025969797745347023
2023-01-24 08:41:09.671983: step: 1432/533, loss: 0.015516713261604309
2023-01-24 08:41:10.750151: step: 1436/533, loss: 0.002037522615864873
2023-01-24 08:41:11.836730: step: 1440/533, loss: 0.011240845546126366
2023-01-24 08:41:12.933444: step: 1444/533, loss: 0.03290315344929695
2023-01-24 08:41:14.016726: step: 1448/533, loss: 0.012349468655884266
2023-01-24 08:41:15.099546: step: 1452/533, loss: 0.0029007738921791315
2023-01-24 08:41:16.173280: step: 1456/533, loss: 0.0010479079792276025
2023-01-24 08:41:17.257007: step: 1460/533, loss: 0.00859646312892437
2023-01-24 08:41:18.336592: step: 1464/533, loss: 0.006012363359332085
2023-01-24 08:41:19.429689: step: 1468/533, loss: 0.01829303428530693
2023-01-24 08:41:20.539894: step: 1472/533, loss: 0.0133949751034379
2023-01-24 08:41:21.635927: step: 1476/533, loss: 0.01250108890235424
2023-01-24 08:41:22.714635: step: 1480/533, loss: 0.0034800132270902395
2023-01-24 08:41:23.790783: step: 1484/533, loss: 0.003503877203911543
2023-01-24 08:41:24.884644: step: 1488/533, loss: 0.0018718772334977984
2023-01-24 08:41:25.981996: step: 1492/533, loss: 0.006180421449244022
2023-01-24 08:41:27.083850: step: 1496/533, loss: 0.006235035136342049
2023-01-24 08:41:28.160752: step: 1500/533, loss: 0.0050415764562785625
2023-01-24 08:41:29.277710: step: 1504/533, loss: 0.01797347515821457
2023-01-24 08:41:30.371861: step: 1508/533, loss: 0.003465191926807165
2023-01-24 08:41:31.445780: step: 1512/533, loss: 0.002340065548196435
2023-01-24 08:41:32.528935: step: 1516/533, loss: 0.008006882853806019
2023-01-24 08:41:33.644025: step: 1520/533, loss: 0.00556136155501008
2023-01-24 08:41:34.727622: step: 1524/533, loss: 0.0034258151426911354
2023-01-24 08:41:35.822632: step: 1528/533, loss: 0.0039782472886145115
2023-01-24 08:41:36.907509: step: 1532/533, loss: 0.003978567663580179
2023-01-24 08:41:38.001139: step: 1536/533, loss: 0.007631443440914154
2023-01-24 08:41:39.074947: step: 1540/533, loss: 0.001794452895410359
2023-01-24 08:41:40.166703: step: 1544/533, loss: 0.003593339817598462
2023-01-24 08:41:41.248391: step: 1548/533, loss: 0.032946694642305374
2023-01-24 08:41:42.335130: step: 1552/533, loss: 0.006304963491857052
2023-01-24 08:41:43.411324: step: 1556/533, loss: 0.0030131370294839144
2023-01-24 08:41:44.487867: step: 1560/533, loss: 0.0030088811181485653
2023-01-24 08:41:45.566240: step: 1564/533, loss: 0.01915140263736248
2023-01-24 08:41:46.667313: step: 1568/533, loss: 0.004320234060287476
2023-01-24 08:41:47.778273: step: 1572/533, loss: 0.009488495998084545
2023-01-24 08:41:48.865524: step: 1576/533, loss: 0.014919362030923367
2023-01-24 08:41:49.973939: step: 1580/533, loss: 0.008647113107144833
2023-01-24 08:41:51.058522: step: 1584/533, loss: 0.006102592684328556
2023-01-24 08:41:52.160597: step: 1588/533, loss: 0.009958094917237759
2023-01-24 08:41:53.239641: step: 1592/533, loss: 0.007886388339102268
2023-01-24 08:41:54.324639: step: 1596/533, loss: 0.0007296421099454165
2023-01-24 08:41:55.415986: step: 1600/533, loss: 0.006275109015405178
2023-01-24 08:41:56.485330: step: 1604/533, loss: 0.005593858193606138
2023-01-24 08:41:57.568919: step: 1608/533, loss: 0.01968730054795742
2023-01-24 08:41:58.647953: step: 1612/533, loss: 0.00010807048238348216
2023-01-24 08:41:59.738004: step: 1616/533, loss: 0.015806401148438454
2023-01-24 08:42:00.829910: step: 1620/533, loss: 0.004950875882059336
2023-01-24 08:42:01.915657: step: 1624/533, loss: 0.016570355743169785
2023-01-24 08:42:02.999228: step: 1628/533, loss: 0.005157575476914644
2023-01-24 08:42:04.082063: step: 1632/533, loss: 0.042462389916181564
2023-01-24 08:42:05.182081: step: 1636/533, loss: 0.01654944382607937
2023-01-24 08:42:06.270854: step: 1640/533, loss: 0.0007500236970372498
2023-01-24 08:42:07.372203: step: 1644/533, loss: 0.0092721376568079
2023-01-24 08:42:08.467096: step: 1648/533, loss: 0.0039471969939768314
2023-01-24 08:42:09.562447: step: 1652/533, loss: 0.026660315692424774
2023-01-24 08:42:10.656437: step: 1656/533, loss: 0.00249173934571445
2023-01-24 08:42:11.740736: step: 1660/533, loss: 0.004514952655881643
2023-01-24 08:42:12.837640: step: 1664/533, loss: 0.013130570761859417
2023-01-24 08:42:13.909814: step: 1668/533, loss: 0.011569567956030369
2023-01-24 08:42:14.984592: step: 1672/533, loss: 0.0005908270832151175
2023-01-24 08:42:16.084620: step: 1676/533, loss: 0.01880650222301483
2023-01-24 08:42:17.157402: step: 1680/533, loss: 0.01821639947593212
2023-01-24 08:42:18.263007: step: 1684/533, loss: 0.0023419761564582586
2023-01-24 08:42:19.368290: step: 1688/533, loss: 0.015104874037206173
2023-01-24 08:42:20.485646: step: 1692/533, loss: 0.0047705043107271194
2023-01-24 08:42:21.585076: step: 1696/533, loss: 0.018475843593478203
2023-01-24 08:42:22.698079: step: 1700/533, loss: 0.01846594363451004
2023-01-24 08:42:23.837699: step: 1704/533, loss: 0.012007299810647964
2023-01-24 08:42:24.915674: step: 1708/533, loss: 0.0074058882892131805
2023-01-24 08:42:26.009871: step: 1712/533, loss: 0.009702470153570175
2023-01-24 08:42:27.094572: step: 1716/533, loss: 0.009651672095060349
2023-01-24 08:42:28.176958: step: 1720/533, loss: 0.0034497189335525036
2023-01-24 08:42:29.273324: step: 1724/533, loss: 0.007449607830494642
2023-01-24 08:42:30.348470: step: 1728/533, loss: 0.0005752560682594776
2023-01-24 08:42:31.420621: step: 1732/533, loss: 0.0028307302854955196
2023-01-24 08:42:32.525290: step: 1736/533, loss: 0.0008027728763408959
2023-01-24 08:42:33.601649: step: 1740/533, loss: 0.00040449720108881593
2023-01-24 08:42:34.680017: step: 1744/533, loss: 0.00977577269077301
2023-01-24 08:42:35.768237: step: 1748/533, loss: 0.006107380148023367
2023-01-24 08:42:36.879671: step: 1752/533, loss: 0.007383768446743488
2023-01-24 08:42:37.957234: step: 1756/533, loss: 0.0005774148157797754
2023-01-24 08:42:39.029562: step: 1760/533, loss: 0.005461470223963261
2023-01-24 08:42:40.130557: step: 1764/533, loss: 0.0053816600702703
2023-01-24 08:42:41.257899: step: 1768/533, loss: 0.0033561561722308397
2023-01-24 08:42:42.361873: step: 1772/533, loss: 0.00463836407288909
2023-01-24 08:42:43.453634: step: 1776/533, loss: 0.01170443743467331
2023-01-24 08:42:44.534929: step: 1780/533, loss: 0.003978255204856396
2023-01-24 08:42:45.618432: step: 1784/533, loss: 0.001089594908989966
2023-01-24 08:42:46.691987: step: 1788/533, loss: 0.0039631957188248634
2023-01-24 08:42:47.789445: step: 1792/533, loss: 0.002254391787573695
2023-01-24 08:42:48.872133: step: 1796/533, loss: 0.011081273667514324
2023-01-24 08:42:49.969205: step: 1800/533, loss: 0.0019431202672421932
2023-01-24 08:42:51.044131: step: 1804/533, loss: 2.114465360136819e-06
2023-01-24 08:42:52.146123: step: 1808/533, loss: 0.003680634079501033
2023-01-24 08:42:53.227427: step: 1812/533, loss: 0.0021562143228948116
2023-01-24 08:42:54.310299: step: 1816/533, loss: 3.011751232406823e-06
2023-01-24 08:42:55.407662: step: 1820/533, loss: 0.0048723588697612286
2023-01-24 08:42:56.499273: step: 1824/533, loss: 0.005195962730795145
2023-01-24 08:42:57.606718: step: 1828/533, loss: 0.00637830700725317
2023-01-24 08:42:58.704739: step: 1832/533, loss: 0.02500009536743164
2023-01-24 08:42:59.790917: step: 1836/533, loss: 0.0018688564887270331
2023-01-24 08:43:00.876519: step: 1840/533, loss: 0.0032864133827388287
2023-01-24 08:43:01.965844: step: 1844/533, loss: 0.012967799790203571
2023-01-24 08:43:03.042489: step: 1848/533, loss: 0.0033037157263606787
2023-01-24 08:43:04.149950: step: 1852/533, loss: 0.0018350753234699368
2023-01-24 08:43:05.244112: step: 1856/533, loss: 0.01018961239606142
2023-01-24 08:43:06.307421: step: 1860/533, loss: 0.0009189764386974275
2023-01-24 08:43:07.391105: step: 1864/533, loss: 0.005585324484854937
2023-01-24 08:43:08.509740: step: 1868/533, loss: 0.03817899152636528
2023-01-24 08:43:09.587883: step: 1872/533, loss: 0.005320045165717602
2023-01-24 08:43:10.658880: step: 1876/533, loss: 0.004431431647390127
2023-01-24 08:43:11.747289: step: 1880/533, loss: 0.0021602867636829615
2023-01-24 08:43:12.832773: step: 1884/533, loss: 0.0022551752626895905
2023-01-24 08:43:13.914154: step: 1888/533, loss: 0.006444781087338924
2023-01-24 08:43:15.038098: step: 1892/533, loss: 0.002778214169666171
2023-01-24 08:43:16.136955: step: 1896/533, loss: 0.01585339941084385
2023-01-24 08:43:17.211978: step: 1900/533, loss: 0.0072467755526304245
2023-01-24 08:43:18.295702: step: 1904/533, loss: 0.005385952070355415
2023-01-24 08:43:19.373023: step: 1908/533, loss: 0.0016109381103888154
2023-01-24 08:43:20.467068: step: 1912/533, loss: 0.0027919600252062082
2023-01-24 08:43:21.549515: step: 1916/533, loss: 0.042550936341285706
2023-01-24 08:43:22.665604: step: 1920/533, loss: 0.004527815151959658
2023-01-24 08:43:23.751809: step: 1924/533, loss: 0.00558610400184989
2023-01-24 08:43:24.838058: step: 1928/533, loss: 0.0030414336360991
2023-01-24 08:43:25.920417: step: 1932/533, loss: 0.005380496848374605
2023-01-24 08:43:27.024695: step: 1936/533, loss: 0.005139159969985485
2023-01-24 08:43:28.128948: step: 1940/533, loss: 0.009158797562122345
2023-01-24 08:43:29.219301: step: 1944/533, loss: 0.008846565149724483
2023-01-24 08:43:30.305693: step: 1948/533, loss: 0.01884392276406288
2023-01-24 08:43:31.378344: step: 1952/533, loss: 0.003659372217953205
2023-01-24 08:43:32.468177: step: 1956/533, loss: 0.02050234191119671
2023-01-24 08:43:33.552849: step: 1960/533, loss: 0.005719813983887434
2023-01-24 08:43:34.625745: step: 1964/533, loss: 0.007795623503625393
2023-01-24 08:43:35.710335: step: 1968/533, loss: 0.008747796528041363
2023-01-24 08:43:36.791991: step: 1972/533, loss: 0.0015983424382284284
2023-01-24 08:43:37.883822: step: 1976/533, loss: 0.0005910166655667126
2023-01-24 08:43:38.968628: step: 1980/533, loss: 0.021268483251333237
2023-01-24 08:43:40.040592: step: 1984/533, loss: 0.008855757303535938
2023-01-24 08:43:41.124898: step: 1988/533, loss: 0.007414797320961952
2023-01-24 08:43:42.232504: step: 1992/533, loss: 0.003300964832305908
2023-01-24 08:43:43.320268: step: 1996/533, loss: 0.0012925462797284126
2023-01-24 08:43:44.402577: step: 2000/533, loss: 0.028059467673301697
2023-01-24 08:43:45.522335: step: 2004/533, loss: 0.005706259980797768
2023-01-24 08:43:46.615538: step: 2008/533, loss: 0.03375755622982979
2023-01-24 08:43:47.702965: step: 2012/533, loss: 0.0538766123354435
2023-01-24 08:43:48.778294: step: 2016/533, loss: 0.007815389893949032
2023-01-24 08:43:49.909052: step: 2020/533, loss: 0.007740525994449854
2023-01-24 08:43:51.009870: step: 2024/533, loss: 0.0004611621843650937
2023-01-24 08:43:52.110067: step: 2028/533, loss: 0.0051615252159535885
2023-01-24 08:43:53.193277: step: 2032/533, loss: 0.028289979323744774
2023-01-24 08:43:54.288119: step: 2036/533, loss: 0.004400012549012899
2023-01-24 08:43:55.387057: step: 2040/533, loss: 0.00048461073311045766
2023-01-24 08:43:56.476300: step: 2044/533, loss: 0.023785987868905067
2023-01-24 08:43:57.566602: step: 2048/533, loss: 0.00661376491189003
2023-01-24 08:43:58.646994: step: 2052/533, loss: 0.001602706266567111
2023-01-24 08:43:59.752406: step: 2056/533, loss: 0.008613202720880508
2023-01-24 08:44:00.846070: step: 2060/533, loss: 4.7966888814698905e-05
2023-01-24 08:44:01.949239: step: 2064/533, loss: 0.06272292137145996
2023-01-24 08:44:03.034604: step: 2068/533, loss: 0.0035249157808721066
2023-01-24 08:44:04.120093: step: 2072/533, loss: 0.004211323335766792
2023-01-24 08:44:05.240309: step: 2076/533, loss: 0.011132516898214817
2023-01-24 08:44:06.311889: step: 2080/533, loss: 0.004223801661282778
2023-01-24 08:44:07.385629: step: 2084/533, loss: 0.0063947043381631374
2023-01-24 08:44:08.479635: step: 2088/533, loss: 0.003493483643978834
2023-01-24 08:44:09.575859: step: 2092/533, loss: 0.012005641125142574
2023-01-24 08:44:10.652490: step: 2096/533, loss: 0.00722093740478158
2023-01-24 08:44:11.734890: step: 2100/533, loss: 0.06519872695207596
2023-01-24 08:44:12.821368: step: 2104/533, loss: 0.010979428887367249
2023-01-24 08:44:13.911313: step: 2108/533, loss: 0.0433858223259449
2023-01-24 08:44:15.006580: step: 2112/533, loss: 0.03175589442253113
2023-01-24 08:44:16.104144: step: 2116/533, loss: 0.024869756773114204
2023-01-24 08:44:17.190502: step: 2120/533, loss: 0.007395964115858078
2023-01-24 08:44:18.262298: step: 2124/533, loss: 0.0016167076537385583
2023-01-24 08:44:19.342935: step: 2128/533, loss: 0.0006540884496644139
2023-01-24 08:44:20.450462: step: 2132/533, loss: 0.003451521508395672
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38389564896755163, 'r': 0.32926154332700824, 'f1': 0.3544858699353081}, 'combined': 0.26120011468917437, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3962121913882097, 'r': 0.3565909722493887, 'f1': 0.37535891815725125}, 'combined': 0.25023927877150076, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34326995129261895, 'r': 0.3067934479294564, 'f1': 0.3240083107391253}, 'combined': 0.2387429658077765, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3823516841242024, 'r': 0.34264593231130447, 'f1': 0.3614115310382927}, 'combined': 0.24094102069219508, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 7}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 08:46:39.117503: step: 4/533, loss: 0.005249379202723503
2023-01-24 08:46:40.207980: step: 8/533, loss: 0.02717798948287964
2023-01-24 08:46:41.270477: step: 12/533, loss: 0.0013143207179382443
2023-01-24 08:46:42.372441: step: 16/533, loss: 0.011745155788958073
2023-01-24 08:46:43.446875: step: 20/533, loss: 0.02244809828698635
2023-01-24 08:46:44.552494: step: 24/533, loss: 0.009188465774059296
2023-01-24 08:46:45.625594: step: 28/533, loss: 0.01151268370449543
2023-01-24 08:46:46.695968: step: 32/533, loss: 0.037299081683158875
2023-01-24 08:46:47.782835: step: 36/533, loss: 0.004297119565308094
2023-01-24 08:46:48.899732: step: 40/533, loss: 0.008495884947478771
2023-01-24 08:46:49.982198: step: 44/533, loss: 0.039093267172575
2023-01-24 08:46:51.047784: step: 48/533, loss: 0.0011962443822994828
2023-01-24 08:46:52.143495: step: 52/533, loss: 0.0020853623282164335
2023-01-24 08:46:53.211482: step: 56/533, loss: 0.0004416855226736516
2023-01-24 08:46:54.292893: step: 60/533, loss: 0.0036940628197044134
2023-01-24 08:46:55.377782: step: 64/533, loss: 0.0012819693656638265
2023-01-24 08:46:56.449755: step: 68/533, loss: 0.013342026621103287
2023-01-24 08:46:57.525588: step: 72/533, loss: 0.006309949327260256
2023-01-24 08:46:58.605151: step: 76/533, loss: 0.0062163458205759525
2023-01-24 08:46:59.690892: step: 80/533, loss: 0.0030418774113059044
2023-01-24 08:47:00.792837: step: 84/533, loss: 0.0012933422112837434
2023-01-24 08:47:01.892677: step: 88/533, loss: 0.014808179810643196
2023-01-24 08:47:02.979381: step: 92/533, loss: 0.0043863882310688496
2023-01-24 08:47:04.058675: step: 96/533, loss: 0.003485084045678377
2023-01-24 08:47:05.144834: step: 100/533, loss: 0.001207785215228796
2023-01-24 08:47:06.231531: step: 104/533, loss: 0.005311430431902409
2023-01-24 08:47:07.330440: step: 108/533, loss: 0.004902905318886042
2023-01-24 08:47:08.413514: step: 112/533, loss: 0.001555718365125358
2023-01-24 08:47:09.499870: step: 116/533, loss: 0.016502005979418755
2023-01-24 08:47:10.566215: step: 120/533, loss: 0.002862087218090892
2023-01-24 08:47:11.628945: step: 124/533, loss: 0.0021539744921028614
2023-01-24 08:47:12.703782: step: 128/533, loss: 0.006692501250654459
2023-01-24 08:47:13.787838: step: 132/533, loss: 0.010683120228350163
2023-01-24 08:47:14.889600: step: 136/533, loss: 0.005056118126958609
2023-01-24 08:47:15.966718: step: 140/533, loss: 0.004376737400889397
2023-01-24 08:47:17.058847: step: 144/533, loss: 0.0017941271653398871
2023-01-24 08:47:18.161629: step: 148/533, loss: 0.01713050901889801
2023-01-24 08:47:19.251654: step: 152/533, loss: 0.03292477875947952
2023-01-24 08:47:20.341402: step: 156/533, loss: 0.025690073147416115
2023-01-24 08:47:21.437729: step: 160/533, loss: 0.005690411664545536
2023-01-24 08:47:22.523545: step: 164/533, loss: 0.01601775735616684
2023-01-24 08:47:23.611339: step: 168/533, loss: 0.009190009906888008
2023-01-24 08:47:24.691130: step: 172/533, loss: 0.004364284686744213
2023-01-24 08:47:25.811303: step: 176/533, loss: 0.00106194952968508
2023-01-24 08:47:26.913362: step: 180/533, loss: 0.002408855129033327
2023-01-24 08:47:28.002461: step: 184/533, loss: 0.005993539001792669
2023-01-24 08:47:29.107898: step: 188/533, loss: 0.024437174201011658
2023-01-24 08:47:30.186266: step: 192/533, loss: 0.005332297179847956
2023-01-24 08:47:31.275394: step: 196/533, loss: 0.00735313817858696
2023-01-24 08:47:32.340154: step: 200/533, loss: 0.00814378447830677
2023-01-24 08:47:33.443097: step: 204/533, loss: 0.008899964392185211
2023-01-24 08:47:34.529821: step: 208/533, loss: 0.00597912585362792
2023-01-24 08:47:35.615338: step: 212/533, loss: 0.0009504983318038285
2023-01-24 08:47:36.723887: step: 216/533, loss: 0.0011360086500644684
2023-01-24 08:47:37.809196: step: 220/533, loss: 0.004233801271766424
2023-01-24 08:47:38.903386: step: 224/533, loss: 0.0009695746703073382
2023-01-24 08:47:39.981477: step: 228/533, loss: 0.002407326130196452
2023-01-24 08:47:41.085522: step: 232/533, loss: 0.00991263147443533
2023-01-24 08:47:42.161554: step: 236/533, loss: 0.0006847230833955109
2023-01-24 08:47:43.233786: step: 240/533, loss: 0.006141482852399349
2023-01-24 08:47:44.327763: step: 244/533, loss: 0.0005096436943858862
2023-01-24 08:47:45.407938: step: 248/533, loss: 0.01810450851917267
2023-01-24 08:47:46.498887: step: 252/533, loss: 0.00483328104019165
2023-01-24 08:47:47.573029: step: 256/533, loss: 0.0012495523551478982
2023-01-24 08:47:48.653429: step: 260/533, loss: 0.026187710464000702
2023-01-24 08:47:49.715983: step: 264/533, loss: 0.0032103857956826687
2023-01-24 08:47:50.778885: step: 268/533, loss: 0.0074015515856444836
2023-01-24 08:47:51.886687: step: 272/533, loss: 0.008791127242147923
2023-01-24 08:47:52.983374: step: 276/533, loss: 0.003997386433184147
2023-01-24 08:47:54.045451: step: 280/533, loss: 0.004095685668289661
2023-01-24 08:47:55.120152: step: 284/533, loss: 0.000609873968642205
2023-01-24 08:47:56.219954: step: 288/533, loss: 0.002906915731728077
2023-01-24 08:47:57.310511: step: 292/533, loss: 0.0029417944606393576
2023-01-24 08:47:58.390735: step: 296/533, loss: 0.007994541898369789
2023-01-24 08:47:59.477641: step: 300/533, loss: 0.008671739138662815
2023-01-24 08:48:00.563108: step: 304/533, loss: 0.04782881960272789
2023-01-24 08:48:01.641974: step: 308/533, loss: 0.010904687456786633
2023-01-24 08:48:02.734954: step: 312/533, loss: 0.006811152677983046
2023-01-24 08:48:03.820261: step: 316/533, loss: 0.005835515912622213
2023-01-24 08:48:04.889106: step: 320/533, loss: 0.004463518969714642
2023-01-24 08:48:06.032646: step: 324/533, loss: 0.014461101964116096
2023-01-24 08:48:07.160321: step: 328/533, loss: 0.0014187475899234414
2023-01-24 08:48:08.251941: step: 332/533, loss: 0.006132980342954397
2023-01-24 08:48:09.347948: step: 336/533, loss: 0.03877866268157959
2023-01-24 08:48:10.455781: step: 340/533, loss: 0.008044762536883354
2023-01-24 08:48:11.562655: step: 344/533, loss: 0.004156401846557856
2023-01-24 08:48:12.651642: step: 348/533, loss: 0.0039445217698812485
2023-01-24 08:48:13.751148: step: 352/533, loss: 0.043261636048555374
2023-01-24 08:48:14.841498: step: 356/533, loss: 0.004361663479357958
2023-01-24 08:48:15.918605: step: 360/533, loss: 0.006413300056010485
2023-01-24 08:48:16.990392: step: 364/533, loss: 0.005128518678247929
2023-01-24 08:48:18.079724: step: 368/533, loss: 0.0013102301163598895
2023-01-24 08:48:19.162805: step: 372/533, loss: 0.010988717898726463
2023-01-24 08:48:20.284180: step: 376/533, loss: 0.0029831479769200087
2023-01-24 08:48:21.366922: step: 380/533, loss: 0.007152992766350508
2023-01-24 08:48:22.445443: step: 384/533, loss: 0.0007476542377844453
2023-01-24 08:48:23.553328: step: 388/533, loss: 0.013452471233904362
2023-01-24 08:48:24.632237: step: 392/533, loss: 0.0025484906509518623
2023-01-24 08:48:25.748095: step: 396/533, loss: 0.010383798740804195
2023-01-24 08:48:26.850921: step: 400/533, loss: 2.048154601652641e-05
2023-01-24 08:48:27.937229: step: 404/533, loss: 0.00010543518874328583
2023-01-24 08:48:29.016841: step: 408/533, loss: 0.000335466320393607
2023-01-24 08:48:30.085282: step: 412/533, loss: 6.819127884227782e-05
2023-01-24 08:48:31.181771: step: 416/533, loss: 0.0062447465024888515
2023-01-24 08:48:32.262963: step: 420/533, loss: 0.0
2023-01-24 08:48:33.355584: step: 424/533, loss: 0.017432456836104393
2023-01-24 08:48:34.446363: step: 428/533, loss: 0.008801615796983242
2023-01-24 08:48:35.530846: step: 432/533, loss: 0.0049865031614899635
2023-01-24 08:48:36.610800: step: 436/533, loss: 0.004701325669884682
2023-01-24 08:48:37.702055: step: 440/533, loss: 0.006395828910171986
2023-01-24 08:48:38.805576: step: 444/533, loss: 0.003602000419050455
2023-01-24 08:48:39.896040: step: 448/533, loss: 0.016034141182899475
2023-01-24 08:48:40.994362: step: 452/533, loss: 0.01455223374068737
2023-01-24 08:48:42.067283: step: 456/533, loss: 0.001727889757603407
2023-01-24 08:48:43.145868: step: 460/533, loss: 0.028863996267318726
2023-01-24 08:48:44.238704: step: 464/533, loss: 0.0005787370027974248
2023-01-24 08:48:45.331618: step: 468/533, loss: 0.041078899055719376
2023-01-24 08:48:46.434582: step: 472/533, loss: 0.008162932470440865
2023-01-24 08:48:47.518363: step: 476/533, loss: 0.002208846854045987
2023-01-24 08:48:48.589467: step: 480/533, loss: 0.0041587878949940205
2023-01-24 08:48:49.661929: step: 484/533, loss: 0.009223563596606255
2023-01-24 08:48:50.734944: step: 488/533, loss: 0.0026763505302369595
2023-01-24 08:48:51.807843: step: 492/533, loss: 0.0064230021089315414
2023-01-24 08:48:52.895110: step: 496/533, loss: 0.004400408826768398
2023-01-24 08:48:53.978665: step: 500/533, loss: 0.0019789563957601786
2023-01-24 08:48:55.057883: step: 504/533, loss: 0.007279530167579651
2023-01-24 08:48:56.137161: step: 508/533, loss: 0.0008090517367236316
2023-01-24 08:48:57.240430: step: 512/533, loss: 0.0059615508653223515
2023-01-24 08:48:58.319751: step: 516/533, loss: 0.0025427495129406452
2023-01-24 08:48:59.400661: step: 520/533, loss: 3.683703107526526e-05
2023-01-24 08:49:00.523067: step: 524/533, loss: 0.01321234181523323
2023-01-24 08:49:01.612557: step: 528/533, loss: 0.001563543570227921
2023-01-24 08:49:02.707634: step: 532/533, loss: 0.0005107247270643711
2023-01-24 08:49:03.801185: step: 536/533, loss: 0.0030291685834527016
2023-01-24 08:49:04.915317: step: 540/533, loss: 0.005612237844616175
2023-01-24 08:49:06.045866: step: 544/533, loss: 0.005739589687436819
2023-01-24 08:49:07.161855: step: 548/533, loss: 0.0045088548213243484
2023-01-24 08:49:08.256626: step: 552/533, loss: 0.001761264749802649
2023-01-24 08:49:09.352204: step: 556/533, loss: 0.003352956147864461
2023-01-24 08:49:10.447718: step: 560/533, loss: 0.004020297434180975
2023-01-24 08:49:11.559421: step: 564/533, loss: 0.0015249793650582433
2023-01-24 08:49:12.659570: step: 568/533, loss: 0.009567636996507645
2023-01-24 08:49:13.735849: step: 572/533, loss: 0.0037367120385169983
2023-01-24 08:49:14.824302: step: 576/533, loss: 0.0013232874916866422
2023-01-24 08:49:15.911984: step: 580/533, loss: 0.0004429060791153461
2023-01-24 08:49:16.991879: step: 584/533, loss: 0.006899785716086626
2023-01-24 08:49:18.088533: step: 588/533, loss: 0.001119287684559822
2023-01-24 08:49:19.154395: step: 592/533, loss: 0.005298289004713297
2023-01-24 08:49:20.229377: step: 596/533, loss: 0.008825436234474182
2023-01-24 08:49:21.318579: step: 600/533, loss: 0.001737233018502593
2023-01-24 08:49:22.400294: step: 604/533, loss: 0.0030218034517019987
2023-01-24 08:49:23.509012: step: 608/533, loss: 0.0013766500633209944
2023-01-24 08:49:24.598083: step: 612/533, loss: 0.0020046327263116837
2023-01-24 08:49:25.683583: step: 616/533, loss: 0.001755993813276291
2023-01-24 08:49:26.797432: step: 620/533, loss: 0.010348653420805931
2023-01-24 08:49:27.884645: step: 624/533, loss: 0.003982510417699814
2023-01-24 08:49:28.974028: step: 628/533, loss: 0.0004166417638771236
2023-01-24 08:49:30.073107: step: 632/533, loss: 0.007323587778955698
2023-01-24 08:49:31.153476: step: 636/533, loss: 0.00337967649102211
2023-01-24 08:49:32.244188: step: 640/533, loss: 0.01224120706319809
2023-01-24 08:49:33.364190: step: 644/533, loss: 0.0006919448496773839
2023-01-24 08:49:34.477494: step: 648/533, loss: 0.004899231716990471
2023-01-24 08:49:35.573535: step: 652/533, loss: 0.014138549566268921
2023-01-24 08:49:36.653366: step: 656/533, loss: 0.0010706440079957247
2023-01-24 08:49:37.746046: step: 660/533, loss: 0.007540279999375343
2023-01-24 08:49:38.826347: step: 664/533, loss: 0.01565730758011341
2023-01-24 08:49:39.903982: step: 668/533, loss: 0.0050035081803798676
2023-01-24 08:49:41.018965: step: 672/533, loss: 0.003442303743213415
2023-01-24 08:49:42.115833: step: 676/533, loss: 0.0008812638116069138
2023-01-24 08:49:43.215153: step: 680/533, loss: 0.003272061003372073
2023-01-24 08:49:44.334673: step: 684/533, loss: 0.007341769058257341
2023-01-24 08:49:45.440498: step: 688/533, loss: 0.013348238542675972
2023-01-24 08:49:46.550690: step: 692/533, loss: 0.010641495697200298
2023-01-24 08:49:47.640468: step: 696/533, loss: 0.010797315277159214
2023-01-24 08:49:48.730332: step: 700/533, loss: 0.025707313790917397
2023-01-24 08:49:49.817838: step: 704/533, loss: 0.00094632338732481
2023-01-24 08:49:50.925940: step: 708/533, loss: 0.003612558590248227
2023-01-24 08:49:52.026908: step: 712/533, loss: 0.0050622145645320415
2023-01-24 08:49:53.097127: step: 716/533, loss: 0.0014958102256059647
2023-01-24 08:49:54.185343: step: 720/533, loss: 0.003247668966650963
2023-01-24 08:49:55.280440: step: 724/533, loss: 0.0023528679739683867
2023-01-24 08:49:56.365028: step: 728/533, loss: 0.0005104643641971052
2023-01-24 08:49:57.460280: step: 732/533, loss: 0.0031228698790073395
2023-01-24 08:49:58.574144: step: 736/533, loss: 0.007958031259477139
2023-01-24 08:49:59.655044: step: 740/533, loss: 0.002941937418654561
2023-01-24 08:50:00.771640: step: 744/533, loss: 0.0010700232814997435
2023-01-24 08:50:01.862177: step: 748/533, loss: 0.0047234827652573586
2023-01-24 08:50:02.983075: step: 752/533, loss: 0.008779534138739109
2023-01-24 08:50:04.084638: step: 756/533, loss: 0.0010987770510837436
2023-01-24 08:50:05.184698: step: 760/533, loss: 0.009902727790176868
2023-01-24 08:50:06.273218: step: 764/533, loss: 0.005006842315196991
2023-01-24 08:50:07.364029: step: 768/533, loss: 0.019273463636636734
2023-01-24 08:50:08.475537: step: 772/533, loss: 0.0009585210937075317
2023-01-24 08:50:09.558637: step: 776/533, loss: 0.00010592594480840489
2023-01-24 08:50:10.645144: step: 780/533, loss: 0.008154898881912231
2023-01-24 08:50:11.761780: step: 784/533, loss: 0.09804784506559372
2023-01-24 08:50:12.862561: step: 788/533, loss: 0.0022379502188414335
2023-01-24 08:50:13.961298: step: 792/533, loss: 0.007496790960431099
2023-01-24 08:50:15.070636: step: 796/533, loss: 0.014628211036324501
2023-01-24 08:50:16.167042: step: 800/533, loss: 0.0018047261983156204
2023-01-24 08:50:17.273318: step: 804/533, loss: 0.005961553193628788
2023-01-24 08:50:18.388518: step: 808/533, loss: 0.011363291181623936
2023-01-24 08:50:19.489662: step: 812/533, loss: 0.005051954183727503
2023-01-24 08:50:20.583302: step: 816/533, loss: 0.019671769812703133
2023-01-24 08:50:21.708831: step: 820/533, loss: 0.008919669315218925
2023-01-24 08:50:22.813283: step: 824/533, loss: 0.0015705516561865807
2023-01-24 08:50:23.907243: step: 828/533, loss: 0.007347135338932276
2023-01-24 08:50:25.006385: step: 832/533, loss: 0.003985587041825056
2023-01-24 08:50:26.089481: step: 836/533, loss: 0.0025114277377724648
2023-01-24 08:50:27.182616: step: 840/533, loss: 0.00027836926165036857
2023-01-24 08:50:28.288900: step: 844/533, loss: 0.004363665357232094
2023-01-24 08:50:29.387186: step: 848/533, loss: 0.002893194556236267
2023-01-24 08:50:30.478151: step: 852/533, loss: 0.023106494918465614
2023-01-24 08:50:31.555980: step: 856/533, loss: 0.003195855300873518
2023-01-24 08:50:32.646321: step: 860/533, loss: 0.004711388144642115
2023-01-24 08:50:33.740293: step: 864/533, loss: 0.009734667837619781
2023-01-24 08:50:34.861203: step: 868/533, loss: 0.028660353273153305
2023-01-24 08:50:35.961525: step: 872/533, loss: 0.002049898263067007
2023-01-24 08:50:37.048300: step: 876/533, loss: 0.00048800770309753716
2023-01-24 08:50:38.163990: step: 880/533, loss: 0.0005497939419001341
2023-01-24 08:50:39.234330: step: 884/533, loss: 0.0006295564235188067
2023-01-24 08:50:40.311367: step: 888/533, loss: 0.0028045475482940674
2023-01-24 08:50:41.408702: step: 892/533, loss: 0.009637998417019844
2023-01-24 08:50:42.513221: step: 896/533, loss: 0.0028578536584973335
2023-01-24 08:50:43.608051: step: 900/533, loss: 0.013800792396068573
2023-01-24 08:50:44.704197: step: 904/533, loss: 0.008736660704016685
2023-01-24 08:50:45.809054: step: 908/533, loss: 0.003585047321394086
2023-01-24 08:50:46.911832: step: 912/533, loss: 0.006556927226483822
2023-01-24 08:50:48.011192: step: 916/533, loss: 0.00036475571687333286
2023-01-24 08:50:49.131776: step: 920/533, loss: 0.0067588286474347115
2023-01-24 08:50:50.234494: step: 924/533, loss: 0.008606631308794022
2023-01-24 08:50:51.331387: step: 928/533, loss: 0.0036774459294974804
2023-01-24 08:50:52.449176: step: 932/533, loss: 0.002531594829633832
2023-01-24 08:50:53.540107: step: 936/533, loss: 0.0021334413904696703
2023-01-24 08:50:54.632326: step: 940/533, loss: 0.005211210809648037
2023-01-24 08:50:55.745356: step: 944/533, loss: 0.0006536747678183019
2023-01-24 08:50:56.840464: step: 948/533, loss: 0.0059220511466264725
2023-01-24 08:50:57.917434: step: 952/533, loss: 0.0016828544903546572
2023-01-24 08:50:59.011068: step: 956/533, loss: 0.00040878556319512427
2023-01-24 08:51:00.122333: step: 960/533, loss: 0.00785578228533268
2023-01-24 08:51:01.221628: step: 964/533, loss: 0.005232781171798706
2023-01-24 08:51:02.311785: step: 968/533, loss: 0.001559586264193058
2023-01-24 08:51:03.400681: step: 972/533, loss: 0.014040013775229454
2023-01-24 08:51:04.508734: step: 976/533, loss: 0.0029886129777878523
2023-01-24 08:51:05.602350: step: 980/533, loss: 0.004523587878793478
2023-01-24 08:51:06.692772: step: 984/533, loss: 0.00975818745791912
2023-01-24 08:51:07.790881: step: 988/533, loss: 0.01279185339808464
2023-01-24 08:51:08.884154: step: 992/533, loss: 0.002337245736271143
2023-01-24 08:51:09.987178: step: 996/533, loss: 0.0015856764512136579
2023-01-24 08:51:11.068363: step: 1000/533, loss: 0.0017005671979859471
2023-01-24 08:51:12.172508: step: 1004/533, loss: 0.014009525068104267
2023-01-24 08:51:13.275004: step: 1008/533, loss: 0.003128057112917304
2023-01-24 08:51:14.363741: step: 1012/533, loss: 0.011239174753427505
2023-01-24 08:51:15.456616: step: 1016/533, loss: 0.0027386066503822803
2023-01-24 08:51:16.546386: step: 1020/533, loss: 0.002692683134227991
2023-01-24 08:51:17.655412: step: 1024/533, loss: 0.0060019418597221375
2023-01-24 08:51:18.764116: step: 1028/533, loss: 0.0023629339411854744
2023-01-24 08:51:19.858230: step: 1032/533, loss: 0.014438263140618801
2023-01-24 08:51:20.960350: step: 1036/533, loss: 0.013047436252236366
2023-01-24 08:51:22.061962: step: 1040/533, loss: 0.01755254901945591
2023-01-24 08:51:23.213389: step: 1044/533, loss: 0.006016198080033064
2023-01-24 08:51:24.304281: step: 1048/533, loss: 0.0019738178234547377
2023-01-24 08:51:25.396089: step: 1052/533, loss: 0.002990863984450698
2023-01-24 08:51:26.513499: step: 1056/533, loss: 0.0013177901273593307
2023-01-24 08:51:27.601812: step: 1060/533, loss: 0.0020369328558444977
2023-01-24 08:51:28.704870: step: 1064/533, loss: 6.230492726899683e-05
2023-01-24 08:51:29.803962: step: 1068/533, loss: 0.043604735285043716
2023-01-24 08:51:30.894247: step: 1072/533, loss: 0.011398346163332462
2023-01-24 08:51:31.980643: step: 1076/533, loss: 0.009931047447025776
2023-01-24 08:51:33.086176: step: 1080/533, loss: 0.0014707804657518864
2023-01-24 08:51:34.194115: step: 1084/533, loss: 0.04008682444691658
2023-01-24 08:51:35.305143: step: 1088/533, loss: 0.0053562442772090435
2023-01-24 08:51:36.396657: step: 1092/533, loss: 0.0026741831097751856
2023-01-24 08:51:37.506327: step: 1096/533, loss: 0.007792543154209852
2023-01-24 08:51:38.610926: step: 1100/533, loss: 0.011065896600484848
2023-01-24 08:51:39.701634: step: 1104/533, loss: 0.009719486348330975
2023-01-24 08:51:40.795132: step: 1108/533, loss: 0.006095575168728828
2023-01-24 08:51:41.896349: step: 1112/533, loss: 0.00032889231806620955
2023-01-24 08:51:43.003297: step: 1116/533, loss: 0.017231125384569168
2023-01-24 08:51:44.094990: step: 1120/533, loss: 0.0029326179064810276
2023-01-24 08:51:45.226395: step: 1124/533, loss: 0.006469757296144962
2023-01-24 08:51:46.321692: step: 1128/533, loss: 0.0
2023-01-24 08:51:47.410896: step: 1132/533, loss: 0.007963589392602444
2023-01-24 08:51:48.503391: step: 1136/533, loss: 0.0016151249874383211
2023-01-24 08:51:49.611994: step: 1140/533, loss: 0.010954807512462139
2023-01-24 08:51:50.753512: step: 1144/533, loss: 0.015712017193436623
2023-01-24 08:51:51.848555: step: 1148/533, loss: 0.043820571154356
2023-01-24 08:51:52.960435: step: 1152/533, loss: 0.003531244583427906
2023-01-24 08:51:54.052411: step: 1156/533, loss: 0.002932775067165494
2023-01-24 08:51:55.152034: step: 1160/533, loss: 0.009078729897737503
2023-01-24 08:51:56.234376: step: 1164/533, loss: 0.005752953700721264
2023-01-24 08:51:57.333785: step: 1168/533, loss: 0.006322478875517845
2023-01-24 08:51:58.452009: step: 1172/533, loss: 0.0062135010957717896
2023-01-24 08:51:59.544268: step: 1176/533, loss: 0.0016601241659373045
2023-01-24 08:52:00.683609: step: 1180/533, loss: 0.009125364013016224
2023-01-24 08:52:01.782780: step: 1184/533, loss: 0.024827122688293457
2023-01-24 08:52:02.882990: step: 1188/533, loss: 0.011182512156665325
2023-01-24 08:52:03.979451: step: 1192/533, loss: 0.003148494055494666
2023-01-24 08:52:05.073451: step: 1196/533, loss: 0.0047131371684372425
2023-01-24 08:52:06.163490: step: 1200/533, loss: 0.004512054845690727
2023-01-24 08:52:07.276208: step: 1204/533, loss: 0.00837039016187191
2023-01-24 08:52:08.372092: step: 1208/533, loss: 0.0023953639902174473
2023-01-24 08:52:09.478058: step: 1212/533, loss: 0.008604638278484344
2023-01-24 08:52:10.576926: step: 1216/533, loss: 0.003706409363076091
2023-01-24 08:52:11.709164: step: 1220/533, loss: 0.04464596137404442
2023-01-24 08:52:12.795065: step: 1224/533, loss: 0.0018305457197129726
2023-01-24 08:52:13.916452: step: 1228/533, loss: 0.0027644075453281403
2023-01-24 08:52:15.018343: step: 1232/533, loss: 0.013169413432478905
2023-01-24 08:52:16.131078: step: 1236/533, loss: 0.0015159911708906293
2023-01-24 08:52:17.216808: step: 1240/533, loss: 0.007040312048047781
2023-01-24 08:52:18.315687: step: 1244/533, loss: 0.041597042232751846
2023-01-24 08:52:19.449836: step: 1248/533, loss: 0.02915377914905548
2023-01-24 08:52:20.540298: step: 1252/533, loss: 0.0004469371633604169
2023-01-24 08:52:21.627448: step: 1256/533, loss: 0.025852367281913757
2023-01-24 08:52:22.731133: step: 1260/533, loss: 0.0019374104449525476
2023-01-24 08:52:23.816805: step: 1264/533, loss: 0.0018881597789004445
2023-01-24 08:52:24.902052: step: 1268/533, loss: 9.2108100943733e-05
2023-01-24 08:52:26.006277: step: 1272/533, loss: 0.0025785898324102163
2023-01-24 08:52:27.110545: step: 1276/533, loss: 0.002596919657662511
2023-01-24 08:52:28.209312: step: 1280/533, loss: 0.015051121823489666
2023-01-24 08:52:29.331817: step: 1284/533, loss: 0.0028953866567462683
2023-01-24 08:52:30.433350: step: 1288/533, loss: 0.011016204953193665
2023-01-24 08:52:31.523165: step: 1292/533, loss: 0.025215810164809227
2023-01-24 08:52:32.623605: step: 1296/533, loss: 0.00851037260144949
2023-01-24 08:52:33.691728: step: 1300/533, loss: 0.002397343050688505
2023-01-24 08:52:34.805490: step: 1304/533, loss: 0.014483104459941387
2023-01-24 08:52:35.902106: step: 1308/533, loss: 0.00463872728869319
2023-01-24 08:52:36.979892: step: 1312/533, loss: 0.0016911705024540424
2023-01-24 08:52:38.073101: step: 1316/533, loss: 0.0071425000205636024
2023-01-24 08:52:39.191361: step: 1320/533, loss: 0.006537670735269785
2023-01-24 08:52:40.303048: step: 1324/533, loss: 0.008998294360935688
2023-01-24 08:52:41.400009: step: 1328/533, loss: 0.0005253157578408718
2023-01-24 08:52:42.498583: step: 1332/533, loss: 0.017109747976064682
2023-01-24 08:52:43.619155: step: 1336/533, loss: 0.004587200004607439
2023-01-24 08:52:44.724127: step: 1340/533, loss: 0.011954165063798428
2023-01-24 08:52:45.836982: step: 1344/533, loss: 0.018814438953995705
2023-01-24 08:52:46.948850: step: 1348/533, loss: 0.010027550160884857
2023-01-24 08:52:48.032727: step: 1352/533, loss: 0.0019050685223191977
2023-01-24 08:52:49.127990: step: 1356/533, loss: 0.006193800829350948
2023-01-24 08:52:50.215753: step: 1360/533, loss: 0.006874831393361092
2023-01-24 08:52:51.311638: step: 1364/533, loss: 0.0005124494200572371
2023-01-24 08:52:52.394712: step: 1368/533, loss: 0.012303628027439117
2023-01-24 08:52:53.485912: step: 1372/533, loss: 0.011555241420865059
2023-01-24 08:52:54.595541: step: 1376/533, loss: 0.012710102833807468
2023-01-24 08:52:55.685245: step: 1380/533, loss: 0.002921733306720853
2023-01-24 08:52:56.767428: step: 1384/533, loss: 0.0008448977605439723
2023-01-24 08:52:57.882695: step: 1388/533, loss: 0.005312242545187473
2023-01-24 08:52:58.979866: step: 1392/533, loss: 0.003918334376066923
2023-01-24 08:53:00.108879: step: 1396/533, loss: 0.0058342162519693375
2023-01-24 08:53:01.199155: step: 1400/533, loss: 0.0003641228540800512
2023-01-24 08:53:02.288331: step: 1404/533, loss: 0.0013128860155120492
2023-01-24 08:53:03.398546: step: 1408/533, loss: 0.003786712419241667
2023-01-24 08:53:04.502963: step: 1412/533, loss: 0.005443256348371506
2023-01-24 08:53:05.587637: step: 1416/533, loss: 0.00476022670045495
2023-01-24 08:53:06.694597: step: 1420/533, loss: 0.031223053112626076
2023-01-24 08:53:07.779074: step: 1424/533, loss: 0.003228371264412999
2023-01-24 08:53:08.901117: step: 1428/533, loss: 0.0017820476787164807
2023-01-24 08:53:09.992257: step: 1432/533, loss: 0.014501793310046196
2023-01-24 08:53:11.085727: step: 1436/533, loss: 0.04808024317026138
2023-01-24 08:53:12.198420: step: 1440/533, loss: 0.026095476001501083
2023-01-24 08:53:13.287913: step: 1444/533, loss: 0.004972186405211687
2023-01-24 08:53:14.386672: step: 1448/533, loss: 0.029300637543201447
2023-01-24 08:53:15.482477: step: 1452/533, loss: 0.014796960167586803
2023-01-24 08:53:16.611966: step: 1456/533, loss: 0.013414903543889523
2023-01-24 08:53:17.706636: step: 1460/533, loss: 0.00024643438518978655
2023-01-24 08:53:18.778213: step: 1464/533, loss: 8.458051888737828e-05
2023-01-24 08:53:19.864219: step: 1468/533, loss: 0.00035235032555647194
2023-01-24 08:53:20.987353: step: 1472/533, loss: 0.013724063523113728
2023-01-24 08:53:22.114876: step: 1476/533, loss: 0.01712869107723236
2023-01-24 08:53:23.223796: step: 1480/533, loss: 0.010543960146605968
2023-01-24 08:53:24.316722: step: 1484/533, loss: 0.0038480551447719336
2023-01-24 08:53:25.398093: step: 1488/533, loss: 0.015564242377877235
2023-01-24 08:53:26.496351: step: 1492/533, loss: 0.00237546325661242
2023-01-24 08:53:27.588852: step: 1496/533, loss: 0.10694282501935959
2023-01-24 08:53:28.685932: step: 1500/533, loss: 0.00011319861368974671
2023-01-24 08:53:29.797906: step: 1504/533, loss: 0.004381597973406315
2023-01-24 08:53:30.873453: step: 1508/533, loss: 0.011814670637249947
2023-01-24 08:53:31.960653: step: 1512/533, loss: 0.005869499407708645
2023-01-24 08:53:33.051735: step: 1516/533, loss: 0.001592606888152659
2023-01-24 08:53:34.171786: step: 1520/533, loss: 0.003022108692675829
2023-01-24 08:53:35.268107: step: 1524/533, loss: 0.0032440898939967155
2023-01-24 08:53:36.368160: step: 1528/533, loss: 0.01155521348118782
2023-01-24 08:53:37.477897: step: 1532/533, loss: 0.008105257526040077
2023-01-24 08:53:38.551522: step: 1536/533, loss: 0.011355393566191196
2023-01-24 08:53:39.657607: step: 1540/533, loss: 0.004415782634168863
2023-01-24 08:53:40.759287: step: 1544/533, loss: 0.0047016688622534275
2023-01-24 08:53:41.858763: step: 1548/533, loss: 0.002924850909039378
2023-01-24 08:53:42.953167: step: 1552/533, loss: 0.007394969463348389
2023-01-24 08:53:44.060058: step: 1556/533, loss: 0.0027372310869395733
2023-01-24 08:53:45.160145: step: 1560/533, loss: 0.0026968077290803194
2023-01-24 08:53:46.274347: step: 1564/533, loss: 0.003279851982370019
2023-01-24 08:53:47.365649: step: 1568/533, loss: 0.004792093764990568
2023-01-24 08:53:48.453523: step: 1572/533, loss: 0.0027194940485060215
2023-01-24 08:53:49.539765: step: 1576/533, loss: 0.0036545952316373587
2023-01-24 08:53:50.627147: step: 1580/533, loss: 0.0022662775591015816
2023-01-24 08:53:51.711783: step: 1584/533, loss: 0.007889804430305958
2023-01-24 08:53:52.810615: step: 1588/533, loss: 0.007080371957272291
2023-01-24 08:53:53.904525: step: 1592/533, loss: 0.00440849456936121
2023-01-24 08:53:54.991659: step: 1596/533, loss: 0.011857797391712666
2023-01-24 08:53:56.085775: step: 1600/533, loss: 0.0007987859426066279
2023-01-24 08:53:57.200513: step: 1604/533, loss: 0.0882827490568161
2023-01-24 08:53:58.322764: step: 1608/533, loss: 0.005485246889293194
2023-01-24 08:53:59.424927: step: 1612/533, loss: 0.0030960068106651306
2023-01-24 08:54:00.508864: step: 1616/533, loss: 0.0004921854706481099
2023-01-24 08:54:01.593873: step: 1620/533, loss: 6.117281009210274e-05
2023-01-24 08:54:02.695332: step: 1624/533, loss: 0.004769583232700825
2023-01-24 08:54:03.795210: step: 1628/533, loss: 0.0015641445061191916
2023-01-24 08:54:04.882219: step: 1632/533, loss: 0.006158333271741867
2023-01-24 08:54:05.976785: step: 1636/533, loss: 0.01336375717073679
2023-01-24 08:54:07.060002: step: 1640/533, loss: 0.0023002787493169308
2023-01-24 08:54:08.151322: step: 1644/533, loss: 0.004818696994334459
2023-01-24 08:54:09.251755: step: 1648/533, loss: 0.02102450095117092
2023-01-24 08:54:10.330851: step: 1652/533, loss: 0.00599298533052206
2023-01-24 08:54:11.413439: step: 1656/533, loss: 0.0012852358631789684
2023-01-24 08:54:12.510733: step: 1660/533, loss: 0.011177683249115944
2023-01-24 08:54:13.617511: step: 1664/533, loss: 0.000373769347788766
2023-01-24 08:54:14.702606: step: 1668/533, loss: 0.00021471429499797523
2023-01-24 08:54:15.775627: step: 1672/533, loss: 0.004304229281842709
2023-01-24 08:54:16.918645: step: 1676/533, loss: 1.0136563105334062e-05
2023-01-24 08:54:18.026486: step: 1680/533, loss: 0.008711111731827259
2023-01-24 08:54:19.159041: step: 1684/533, loss: 0.0010663928696885705
2023-01-24 08:54:20.225206: step: 1688/533, loss: 0.0005230159149505198
2023-01-24 08:54:21.326948: step: 1692/533, loss: 0.007364340126514435
2023-01-24 08:54:22.429798: step: 1696/533, loss: 0.005680179689079523
2023-01-24 08:54:23.536086: step: 1700/533, loss: 0.02089054137468338
2023-01-24 08:54:24.624018: step: 1704/533, loss: 0.019231703132390976
2023-01-24 08:54:25.724741: step: 1708/533, loss: 0.005474445875734091
2023-01-24 08:54:26.815030: step: 1712/533, loss: 0.008084924891591072
2023-01-24 08:54:27.908502: step: 1716/533, loss: 0.002768693957477808
2023-01-24 08:54:29.014796: step: 1720/533, loss: 0.014212113805115223
2023-01-24 08:54:30.095837: step: 1724/533, loss: 0.0033264115918427706
2023-01-24 08:54:31.223861: step: 1728/533, loss: 0.008695663884282112
2023-01-24 08:54:32.312473: step: 1732/533, loss: 0.005512503441423178
2023-01-24 08:54:33.410085: step: 1736/533, loss: 0.03652891144156456
2023-01-24 08:54:34.524051: step: 1740/533, loss: 0.015053706243634224
2023-01-24 08:54:35.622521: step: 1744/533, loss: 0.007915947586297989
2023-01-24 08:54:36.719456: step: 1748/533, loss: 0.002607039175927639
2023-01-24 08:54:37.815822: step: 1752/533, loss: 0.016437146812677383
2023-01-24 08:54:38.915540: step: 1756/533, loss: 0.01767098344862461
2023-01-24 08:54:40.005232: step: 1760/533, loss: 0.0010719188721850514
2023-01-24 08:54:41.096201: step: 1764/533, loss: 0.0001669189950916916
2023-01-24 08:54:42.204227: step: 1768/533, loss: 0.006290544755756855
2023-01-24 08:54:43.282601: step: 1772/533, loss: 0.006269357167184353
2023-01-24 08:54:44.371569: step: 1776/533, loss: 0.011985464952886105
2023-01-24 08:54:45.451719: step: 1780/533, loss: 0.0033792792819440365
2023-01-24 08:54:46.544525: step: 1784/533, loss: 0.0023374990560114384
2023-01-24 08:54:47.663102: step: 1788/533, loss: 0.02134382352232933
2023-01-24 08:54:48.761338: step: 1792/533, loss: 0.0007348886574618518
2023-01-24 08:54:49.860415: step: 1796/533, loss: 0.008609292097389698
2023-01-24 08:54:50.966493: step: 1800/533, loss: 0.0013138758949935436
2023-01-24 08:54:52.072732: step: 1804/533, loss: 0.010954592376947403
2023-01-24 08:54:53.173708: step: 1808/533, loss: 0.0030859936960041523
2023-01-24 08:54:54.270358: step: 1812/533, loss: 0.003896699519827962
2023-01-24 08:54:55.362275: step: 1816/533, loss: 0.005270422901958227
2023-01-24 08:54:56.451289: step: 1820/533, loss: 0.0013283853186294436
2023-01-24 08:54:57.537187: step: 1824/533, loss: 0.005658590700477362
2023-01-24 08:54:58.615089: step: 1828/533, loss: 0.009983023628592491
2023-01-24 08:54:59.733082: step: 1832/533, loss: 0.007567564025521278
2023-01-24 08:55:00.846877: step: 1836/533, loss: 0.016609076410531998
2023-01-24 08:55:01.968839: step: 1840/533, loss: 0.00350781949236989
2023-01-24 08:55:03.070760: step: 1844/533, loss: 0.01849285699427128
2023-01-24 08:55:04.154157: step: 1848/533, loss: 0.00760242622345686
2023-01-24 08:55:05.262403: step: 1852/533, loss: 0.006122324615716934
2023-01-24 08:55:06.367044: step: 1856/533, loss: 0.02912355214357376
2023-01-24 08:55:07.458655: step: 1860/533, loss: 0.0048894635401666164
2023-01-24 08:55:08.523847: step: 1864/533, loss: 0.004061616957187653
2023-01-24 08:55:09.595693: step: 1868/533, loss: 0.0
2023-01-24 08:55:10.708463: step: 1872/533, loss: 0.011394157074391842
2023-01-24 08:55:11.822932: step: 1876/533, loss: 0.06692633777856827
2023-01-24 08:55:12.939262: step: 1880/533, loss: 0.021115107461810112
2023-01-24 08:55:14.037972: step: 1884/533, loss: 0.0012587320525199175
2023-01-24 08:55:15.154266: step: 1888/533, loss: 0.0033073595259338617
2023-01-24 08:55:16.243908: step: 1892/533, loss: 0.0016683087451383471
2023-01-24 08:55:17.339218: step: 1896/533, loss: 0.0010048741241917014
2023-01-24 08:55:18.423960: step: 1900/533, loss: 0.008184080012142658
2023-01-24 08:55:19.514210: step: 1904/533, loss: 0.01158436480909586
2023-01-24 08:55:20.602110: step: 1908/533, loss: 0.009815320372581482
2023-01-24 08:55:21.695036: step: 1912/533, loss: 0.00589628703892231
2023-01-24 08:55:22.781008: step: 1916/533, loss: 0.002905899425968528
2023-01-24 08:55:23.899191: step: 1920/533, loss: 0.005486018490046263
2023-01-24 08:55:24.982013: step: 1924/533, loss: 0.005946985445916653
2023-01-24 08:55:26.076346: step: 1928/533, loss: 0.00693084392696619
2023-01-24 08:55:27.172905: step: 1932/533, loss: 0.05407232791185379
2023-01-24 08:55:28.256450: step: 1936/533, loss: 0.006372224073857069
2023-01-24 08:55:29.363008: step: 1940/533, loss: 0.011805874295532703
2023-01-24 08:55:30.439364: step: 1944/533, loss: 0.009651374071836472
2023-01-24 08:55:31.524761: step: 1948/533, loss: 0.0033436291851103306
2023-01-24 08:55:32.640383: step: 1952/533, loss: 0.002652287483215332
2023-01-24 08:55:33.734184: step: 1956/533, loss: 0.003925856668502092
2023-01-24 08:55:34.844243: step: 1960/533, loss: 0.00996479019522667
2023-01-24 08:55:35.952749: step: 1964/533, loss: 0.025731075555086136
2023-01-24 08:55:37.033184: step: 1968/533, loss: 0.01339354645460844
2023-01-24 08:55:38.133950: step: 1972/533, loss: 0.005591157823801041
2023-01-24 08:55:39.206067: step: 1976/533, loss: 0.04489227384328842
2023-01-24 08:55:40.311290: step: 1980/533, loss: 0.004731369204819202
2023-01-24 08:55:41.410804: step: 1984/533, loss: 0.005167987663298845
2023-01-24 08:55:42.497739: step: 1988/533, loss: 0.004274760838598013
2023-01-24 08:55:43.594871: step: 1992/533, loss: 0.012759899720549583
2023-01-24 08:55:44.690528: step: 1996/533, loss: 0.007577588781714439
2023-01-24 08:55:45.775949: step: 2000/533, loss: 0.0032336099538952112
2023-01-24 08:55:46.876765: step: 2004/533, loss: 0.01635519228875637
2023-01-24 08:55:47.981225: step: 2008/533, loss: 0.0020041693933308125
2023-01-24 08:55:49.096348: step: 2012/533, loss: 0.005461503751575947
2023-01-24 08:55:50.214573: step: 2016/533, loss: 0.0018998273881152272
2023-01-24 08:55:51.313112: step: 2020/533, loss: 0.0012614296283572912
2023-01-24 08:55:52.401694: step: 2024/533, loss: 0.012206554412841797
2023-01-24 08:55:53.516560: step: 2028/533, loss: 0.003837649943307042
2023-01-24 08:55:54.629796: step: 2032/533, loss: 0.0041660587303340435
2023-01-24 08:55:55.732154: step: 2036/533, loss: 0.013192184269428253
2023-01-24 08:55:56.838345: step: 2040/533, loss: 0.0040780119597911835
2023-01-24 08:55:57.922263: step: 2044/533, loss: 0.005574874579906464
2023-01-24 08:55:59.023753: step: 2048/533, loss: 0.0023403160739690065
2023-01-24 08:56:00.117756: step: 2052/533, loss: 0.00020570206106640399
2023-01-24 08:56:01.217633: step: 2056/533, loss: 0.011446843855082989
2023-01-24 08:56:02.327938: step: 2060/533, loss: 0.04210711270570755
2023-01-24 08:56:03.439961: step: 2064/533, loss: 0.01391694601625204
2023-01-24 08:56:04.529923: step: 2068/533, loss: 0.0002552485675550997
2023-01-24 08:56:05.608032: step: 2072/533, loss: 9.97346724034287e-05
2023-01-24 08:56:06.700346: step: 2076/533, loss: 0.012867281213402748
2023-01-24 08:56:07.798207: step: 2080/533, loss: 0.010916683822870255
2023-01-24 08:56:08.898652: step: 2084/533, loss: 0.0002604224137030542
2023-01-24 08:56:09.992656: step: 2088/533, loss: 0.019600987434387207
2023-01-24 08:56:11.098068: step: 2092/533, loss: 0.0
2023-01-24 08:56:12.218834: step: 2096/533, loss: 0.043158065527677536
2023-01-24 08:56:13.323672: step: 2100/533, loss: 0.007059065625071526
2023-01-24 08:56:14.391477: step: 2104/533, loss: 0.004457531031221151
2023-01-24 08:56:15.503228: step: 2108/533, loss: 0.006039119325578213
2023-01-24 08:56:16.594595: step: 2112/533, loss: 0.012618289329111576
2023-01-24 08:56:17.699954: step: 2116/533, loss: 0.01104326918721199
2023-01-24 08:56:18.789612: step: 2120/533, loss: 0.004811106249690056
2023-01-24 08:56:19.885060: step: 2124/533, loss: 0.010927721858024597
2023-01-24 08:56:20.996112: step: 2128/533, loss: 0.0035034874454140663
2023-01-24 08:56:22.091105: step: 2132/533, loss: 0.010465511120855808
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3823983297022513, 'r': 0.3330566097406705, 'f1': 0.356026031102096}, 'combined': 0.2623349702857549, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3974177519951048, 'r': 0.3618794337878502, 'f1': 0.3788169211266877}, 'combined': 0.2525446140844584, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3585761732668228, 'r': 0.31979279209754596, 'f1': 0.33807583036189914}, 'combined': 0.24910850658245198, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38968498723737327, 'r': 0.3117479897898986, 'f1': 0.3463866553221096}, 'combined': 0.23092443688140635, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33995863970588236, 'r': 0.3096397477397031, 'f1': 0.32409165254979844}, 'combined': 0.23880437556300937, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38331755254635236, 'r': 0.347934393849766, 'f1': 0.364769929036045}, 'combined': 0.24317995269069662, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7, 'r': 0.45652173913043476, 'f1': 0.5526315789473684}, 'combined': 0.36842105263157887, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 08:58:43.621673: step: 4/533, loss: 0.004447500221431255
2023-01-24 08:58:44.699063: step: 8/533, loss: 0.004033980891108513
2023-01-24 08:58:45.784891: step: 12/533, loss: 0.01291695423424244
2023-01-24 08:58:46.887894: step: 16/533, loss: 0.0064631314016878605
2023-01-24 08:58:47.970827: step: 20/533, loss: 0.0024380034301429987
2023-01-24 08:58:49.050659: step: 24/533, loss: 0.0070867398753762245
2023-01-24 08:58:50.159657: step: 28/533, loss: 0.0036327652633190155
2023-01-24 08:58:51.249101: step: 32/533, loss: 0.006728563457727432
2023-01-24 08:58:52.320042: step: 36/533, loss: 0.006138360593467951
2023-01-24 08:58:53.410556: step: 40/533, loss: 0.00254973117262125
2023-01-24 08:58:54.530789: step: 44/533, loss: 0.0019513671286404133
2023-01-24 08:58:55.632725: step: 48/533, loss: 0.00039474424556829035
2023-01-24 08:58:56.750369: step: 52/533, loss: 0.0013782986206933856
2023-01-24 08:58:57.828721: step: 56/533, loss: 0.007451360579580069
2023-01-24 08:58:58.903361: step: 60/533, loss: 0.0007388924132101238
2023-01-24 08:58:59.992288: step: 64/533, loss: 0.02586313895881176
2023-01-24 08:59:01.086823: step: 68/533, loss: 0.00021200953051447868
2023-01-24 08:59:02.160537: step: 72/533, loss: 0.0013075160095468163
2023-01-24 08:59:03.259191: step: 76/533, loss: 0.0028310136403888464
2023-01-24 08:59:04.350929: step: 80/533, loss: 0.015095578506588936
2023-01-24 08:59:05.445416: step: 84/533, loss: 0.0051685962826013565
2023-01-24 08:59:06.535020: step: 88/533, loss: 0.01386050134897232
2023-01-24 08:59:07.619867: step: 92/533, loss: 0.009046928957104683
2023-01-24 08:59:08.703821: step: 96/533, loss: 0.0060607269406318665
2023-01-24 08:59:09.796154: step: 100/533, loss: 0.0025557056069374084
2023-01-24 08:59:10.881173: step: 104/533, loss: 0.004500706680119038
2023-01-24 08:59:11.968325: step: 108/533, loss: 0.016192726790905
2023-01-24 08:59:13.057277: step: 112/533, loss: 0.0012671042932197452
2023-01-24 08:59:14.167858: step: 116/533, loss: 0.0037938253954052925
2023-01-24 08:59:15.269872: step: 120/533, loss: 0.02181459404528141
2023-01-24 08:59:16.359964: step: 124/533, loss: 0.006349644623696804
2023-01-24 08:59:17.426992: step: 128/533, loss: 0.0008374135941267014
2023-01-24 08:59:18.522567: step: 132/533, loss: 0.004961616359651089
2023-01-24 08:59:19.608932: step: 136/533, loss: 0.00988875050097704
2023-01-24 08:59:20.702632: step: 140/533, loss: 0.010686461813747883
2023-01-24 08:59:21.822030: step: 144/533, loss: 0.002266448922455311
2023-01-24 08:59:22.896856: step: 148/533, loss: 0.005843724124133587
2023-01-24 08:59:23.992766: step: 152/533, loss: 0.0034335602540522814
2023-01-24 08:59:25.108568: step: 156/533, loss: 0.011346620507538319
2023-01-24 08:59:26.214063: step: 160/533, loss: 0.0030025688465684652
2023-01-24 08:59:27.321088: step: 164/533, loss: 0.0036450009793043137
2023-01-24 08:59:28.412936: step: 168/533, loss: 0.0032430686987936497
2023-01-24 08:59:29.504437: step: 172/533, loss: 0.0005804214742965996
2023-01-24 08:59:30.591752: step: 176/533, loss: 0.015424397774040699
2023-01-24 08:59:31.681648: step: 180/533, loss: 0.0006544165080413222
2023-01-24 08:59:32.766464: step: 184/533, loss: 0.0018037620466202497
2023-01-24 08:59:33.830921: step: 188/533, loss: 0.0005743266665376723
2023-01-24 08:59:34.926110: step: 192/533, loss: 0.02911525033414364
2023-01-24 08:59:36.008876: step: 196/533, loss: 0.006998760160058737
2023-01-24 08:59:37.114569: step: 200/533, loss: 0.0048640999011695385
2023-01-24 08:59:38.235070: step: 204/533, loss: 0.017984434962272644
2023-01-24 08:59:39.309132: step: 208/533, loss: 0.007989230565726757
2023-01-24 08:59:40.403701: step: 212/533, loss: 0.0034898854792118073
2023-01-24 08:59:41.490699: step: 216/533, loss: 0.0032801413908600807
2023-01-24 08:59:42.577595: step: 220/533, loss: 0.004153369460254908
2023-01-24 08:59:43.705124: step: 224/533, loss: 0.006170108448714018
2023-01-24 08:59:44.796997: step: 228/533, loss: 0.0139542231336236
2023-01-24 08:59:45.898989: step: 232/533, loss: 0.001191560528241098
2023-01-24 08:59:47.003441: step: 236/533, loss: 0.008644324727356434
2023-01-24 08:59:48.093953: step: 240/533, loss: 0.004598593804985285
2023-01-24 08:59:49.208433: step: 244/533, loss: 0.0055726976133883
2023-01-24 08:59:50.309315: step: 248/533, loss: 0.0053550926968455315
2023-01-24 08:59:51.395253: step: 252/533, loss: 0.006058293394744396
2023-01-24 08:59:52.507601: step: 256/533, loss: 0.0016646251315250993
2023-01-24 08:59:53.627337: step: 260/533, loss: 0.0032590499613434076
2023-01-24 08:59:54.707362: step: 264/533, loss: 0.004504061304032803
2023-01-24 08:59:55.806382: step: 268/533, loss: 0.00015476290718652308
2023-01-24 08:59:56.906183: step: 272/533, loss: 0.001774217002093792
2023-01-24 08:59:58.005682: step: 276/533, loss: 0.004481937736272812
2023-01-24 08:59:59.106144: step: 280/533, loss: 0.0050707668997347355
2023-01-24 09:00:00.192096: step: 284/533, loss: 0.002164736855775118
2023-01-24 09:00:01.294864: step: 288/533, loss: 0.0010915184393525124
2023-01-24 09:00:02.395351: step: 292/533, loss: 0.01757996343076229
2023-01-24 09:00:03.488088: step: 296/533, loss: 0.010798174887895584
2023-01-24 09:00:04.553130: step: 300/533, loss: 0.01701868511736393
2023-01-24 09:00:05.665035: step: 304/533, loss: 0.0074485600925982
2023-01-24 09:00:06.754100: step: 308/533, loss: 0.00029262370662763715
2023-01-24 09:00:07.863830: step: 312/533, loss: 0.01605493761599064
2023-01-24 09:00:08.963247: step: 316/533, loss: 0.019888075068593025
2023-01-24 09:00:10.064398: step: 320/533, loss: 0.004066215828061104
2023-01-24 09:00:11.156662: step: 324/533, loss: 0.005125802475959063
2023-01-24 09:00:12.268435: step: 328/533, loss: 0.006534371990710497
2023-01-24 09:00:13.384878: step: 332/533, loss: 0.015143843367695808
2023-01-24 09:00:14.486638: step: 336/533, loss: 0.00750946206972003
2023-01-24 09:00:15.586308: step: 340/533, loss: 0.01986277848482132
2023-01-24 09:00:16.689383: step: 344/533, loss: 0.01897282339632511
2023-01-24 09:00:17.783305: step: 348/533, loss: 0.005868928506970406
2023-01-24 09:00:18.904580: step: 352/533, loss: 0.011256398633122444
2023-01-24 09:00:19.987984: step: 356/533, loss: 0.01055065356194973
2023-01-24 09:00:21.095976: step: 360/533, loss: 0.0020836670882999897
2023-01-24 09:00:22.204628: step: 364/533, loss: 0.004595848731696606
2023-01-24 09:00:23.301675: step: 368/533, loss: 0.008897059597074986
2023-01-24 09:00:24.426197: step: 372/533, loss: 0.005121815484017134
2023-01-24 09:00:25.556274: step: 376/533, loss: 0.005897581577301025
2023-01-24 09:00:26.658972: step: 380/533, loss: 0.012193550355732441
2023-01-24 09:00:27.749050: step: 384/533, loss: 0.018895026296377182
2023-01-24 09:00:28.832187: step: 388/533, loss: 0.012992204166948795
2023-01-24 09:00:29.923135: step: 392/533, loss: 0.0010085946414619684
2023-01-24 09:00:31.043888: step: 396/533, loss: 0.0058656916953623295
2023-01-24 09:00:32.139723: step: 400/533, loss: 0.0047399201430380344
2023-01-24 09:00:33.227236: step: 404/533, loss: 0.008662022650241852
2023-01-24 09:00:34.329459: step: 408/533, loss: 0.012488281354308128
2023-01-24 09:00:35.437905: step: 412/533, loss: 0.006589555647224188
2023-01-24 09:00:36.540033: step: 416/533, loss: 0.022495713084936142
2023-01-24 09:00:37.676341: step: 420/533, loss: 0.004260800778865814
2023-01-24 09:00:38.776066: step: 424/533, loss: 0.008518863469362259
2023-01-24 09:00:39.870520: step: 428/533, loss: 5.420642264652997e-05
2023-01-24 09:00:40.964114: step: 432/533, loss: 0.009645206853747368
2023-01-24 09:00:42.041030: step: 436/533, loss: 0.007242233492434025
2023-01-24 09:00:43.141549: step: 440/533, loss: 0.019469348713755608
2023-01-24 09:00:44.228458: step: 444/533, loss: 0.0042952983640134335
2023-01-24 09:00:45.344878: step: 448/533, loss: 0.0061609153635799885
2023-01-24 09:00:46.473525: step: 452/533, loss: 0.0035621810238808393
2023-01-24 09:00:47.579738: step: 456/533, loss: 0.007115418557077646
2023-01-24 09:00:48.684557: step: 460/533, loss: 0.005537300370633602
2023-01-24 09:00:49.773624: step: 464/533, loss: 0.005261151120066643
2023-01-24 09:00:50.870660: step: 468/533, loss: 0.009104584343731403
2023-01-24 09:00:51.986956: step: 472/533, loss: 0.02174200303852558
2023-01-24 09:00:53.080379: step: 476/533, loss: 0.03593664988875389
2023-01-24 09:00:54.180835: step: 480/533, loss: 0.0009834622032940388
2023-01-24 09:00:55.266150: step: 484/533, loss: 0.005103354342281818
2023-01-24 09:00:56.381363: step: 488/533, loss: 0.004258615896105766
2023-01-24 09:00:57.477450: step: 492/533, loss: 0.0014788415282964706
2023-01-24 09:00:58.583114: step: 496/533, loss: 0.03226887062191963
2023-01-24 09:00:59.704147: step: 500/533, loss: 0.0031560983043164015
2023-01-24 09:01:00.801816: step: 504/533, loss: 0.006287951022386551
2023-01-24 09:01:01.909483: step: 508/533, loss: 0.0032772941049188375
2023-01-24 09:01:02.996385: step: 512/533, loss: 0.0022725961171090603
2023-01-24 09:01:04.096023: step: 516/533, loss: 0.006017862819135189
2023-01-24 09:01:05.179498: step: 520/533, loss: 0.009196525439620018
2023-01-24 09:01:06.276919: step: 524/533, loss: 0.003494034754112363
2023-01-24 09:01:07.370336: step: 528/533, loss: 0.003696341533213854
2023-01-24 09:01:08.468573: step: 532/533, loss: 0.0021583011839538813
2023-01-24 09:01:09.579999: step: 536/533, loss: 0.01346699520945549
2023-01-24 09:01:10.670779: step: 540/533, loss: 0.015131239779293537
2023-01-24 09:01:11.749684: step: 544/533, loss: 0.00041760795284062624
2023-01-24 09:01:12.826915: step: 548/533, loss: 0.012783384881913662
2023-01-24 09:01:13.924616: step: 552/533, loss: 0.001055683009326458
2023-01-24 09:01:15.016668: step: 556/533, loss: 0.00038049742579460144
2023-01-24 09:01:16.122387: step: 560/533, loss: 0.006986986845731735
2023-01-24 09:01:17.213566: step: 564/533, loss: 0.005732170306146145
2023-01-24 09:01:18.337626: step: 568/533, loss: 0.005338446702808142
2023-01-24 09:01:19.441726: step: 572/533, loss: 0.027179254218935966
2023-01-24 09:01:20.542017: step: 576/533, loss: 0.009325766004621983
2023-01-24 09:01:21.660534: step: 580/533, loss: 0.0005210209055803716
2023-01-24 09:01:22.768470: step: 584/533, loss: 0.004962848965078592
2023-01-24 09:01:23.861994: step: 588/533, loss: 0.0007578069344162941
2023-01-24 09:01:24.957969: step: 592/533, loss: 0.033471353352069855
2023-01-24 09:01:26.068872: step: 596/533, loss: 0.014184338040649891
2023-01-24 09:01:27.150570: step: 600/533, loss: 0.009448576718568802
2023-01-24 09:01:28.265470: step: 604/533, loss: 0.00559212127700448
2023-01-24 09:01:29.391183: step: 608/533, loss: 0.005263106897473335
2023-01-24 09:01:30.484323: step: 612/533, loss: 0.00047528502182103693
2023-01-24 09:01:31.558027: step: 616/533, loss: 0.0007578724180348217
2023-01-24 09:01:32.665844: step: 620/533, loss: 0.011139397509396076
2023-01-24 09:01:33.773639: step: 624/533, loss: 0.0018729263683781028
2023-01-24 09:01:34.851622: step: 628/533, loss: 0.0009022523881867528
2023-01-24 09:01:35.937320: step: 632/533, loss: 0.005717436317354441
2023-01-24 09:01:37.048402: step: 636/533, loss: 0.03276916220784187
2023-01-24 09:01:38.142645: step: 640/533, loss: 0.02010415494441986
2023-01-24 09:01:39.252755: step: 644/533, loss: 0.008716876618564129
2023-01-24 09:01:40.356813: step: 648/533, loss: 0.0007959402864798903
2023-01-24 09:01:41.447579: step: 652/533, loss: 0.0019232049817219377
2023-01-24 09:01:42.554536: step: 656/533, loss: 0.0028740542475134134
2023-01-24 09:01:43.651082: step: 660/533, loss: 0.0035975698847323656
2023-01-24 09:01:44.758220: step: 664/533, loss: 0.009088591672480106
2023-01-24 09:01:45.850848: step: 668/533, loss: 0.0067664869129657745
2023-01-24 09:01:46.941033: step: 672/533, loss: 0.006937122903764248
2023-01-24 09:01:48.045596: step: 676/533, loss: 0.005613783374428749
2023-01-24 09:01:49.157209: step: 680/533, loss: 0.00951266661286354
2023-01-24 09:01:50.268104: step: 684/533, loss: 0.0009909189539030194
2023-01-24 09:01:51.351712: step: 688/533, loss: 0.007841049693524837
2023-01-24 09:01:52.484505: step: 692/533, loss: 0.0033444741275161505
2023-01-24 09:01:53.560119: step: 696/533, loss: 0.0006371344206854701
2023-01-24 09:01:54.644488: step: 700/533, loss: 0.00484386645257473
2023-01-24 09:01:55.748749: step: 704/533, loss: 0.002261750865727663
2023-01-24 09:01:56.856362: step: 708/533, loss: 0.006516668014228344
2023-01-24 09:01:57.957541: step: 712/533, loss: 0.004148789215832949
2023-01-24 09:01:59.046462: step: 716/533, loss: 0.004781858064234257
2023-01-24 09:02:00.156939: step: 720/533, loss: 0.011675932444632053
2023-01-24 09:02:01.253288: step: 724/533, loss: 0.019003912806510925
2023-01-24 09:02:02.365975: step: 728/533, loss: 0.010627138428390026
2023-01-24 09:02:03.480132: step: 732/533, loss: 0.007367225829511881
2023-01-24 09:02:04.580908: step: 736/533, loss: 0.006052244920283556
2023-01-24 09:02:05.685888: step: 740/533, loss: 0.004270386416465044
2023-01-24 09:02:06.752539: step: 744/533, loss: 9.641897486289963e-05
2023-01-24 09:02:07.841808: step: 748/533, loss: 0.0012979843886569142
2023-01-24 09:02:08.940365: step: 752/533, loss: 0.0007613477646373212
2023-01-24 09:02:10.046082: step: 756/533, loss: 0.0013937755720689893
2023-01-24 09:02:11.142060: step: 760/533, loss: 0.016063367947936058
2023-01-24 09:02:12.265119: step: 764/533, loss: 0.00031983497319743037
2023-01-24 09:02:13.370729: step: 768/533, loss: 0.0024303377140313387
2023-01-24 09:02:14.459459: step: 772/533, loss: 0.004429682157933712
2023-01-24 09:02:15.541857: step: 776/533, loss: 0.0021141243632882833
2023-01-24 09:02:16.625689: step: 780/533, loss: 0.00316550862044096
2023-01-24 09:02:17.719993: step: 784/533, loss: 0.005428397562354803
2023-01-24 09:02:18.804370: step: 788/533, loss: 4.416644151206128e-05
2023-01-24 09:02:19.915594: step: 792/533, loss: 0.0033471626229584217
2023-01-24 09:02:21.046647: step: 796/533, loss: 0.0023251366801559925
2023-01-24 09:02:22.120575: step: 800/533, loss: 0.00935712456703186
2023-01-24 09:02:23.204628: step: 804/533, loss: 0.0036983792670071125
2023-01-24 09:02:24.294392: step: 808/533, loss: 0.021688934415578842
2023-01-24 09:02:25.405691: step: 812/533, loss: 0.004476968199014664
2023-01-24 09:02:26.517642: step: 816/533, loss: 0.022451993077993393
2023-01-24 09:02:27.606891: step: 820/533, loss: 0.007026543840765953
2023-01-24 09:02:28.704377: step: 824/533, loss: 0.008347269147634506
2023-01-24 09:02:29.802471: step: 828/533, loss: 0.006524907425045967
2023-01-24 09:02:30.891829: step: 832/533, loss: 0.0035706658381968737
2023-01-24 09:02:31.979706: step: 836/533, loss: 0.0029529158491641283
2023-01-24 09:02:33.061339: step: 840/533, loss: 0.0005310599808581173
2023-01-24 09:02:34.149840: step: 844/533, loss: 0.003620147006586194
2023-01-24 09:02:35.253143: step: 848/533, loss: 0.011565468274056911
2023-01-24 09:02:36.344724: step: 852/533, loss: 0.007489136885851622
2023-01-24 09:02:37.456366: step: 856/533, loss: 0.0012559877941384912
2023-01-24 09:02:38.565988: step: 860/533, loss: 0.002828342141583562
2023-01-24 09:02:39.651386: step: 864/533, loss: 0.006566721014678478
2023-01-24 09:02:40.742190: step: 868/533, loss: 0.005643533542752266
2023-01-24 09:02:41.818472: step: 872/533, loss: 0.003410474630072713
2023-01-24 09:02:42.895662: step: 876/533, loss: 0.00012380638509057462
2023-01-24 09:02:44.047617: step: 880/533, loss: 0.0054560438729822636
2023-01-24 09:02:45.146444: step: 884/533, loss: 0.0015764596173539758
2023-01-24 09:02:46.223366: step: 888/533, loss: 0.016783492639660835
2023-01-24 09:02:47.336577: step: 892/533, loss: 0.010834753513336182
2023-01-24 09:02:48.424826: step: 896/533, loss: 0.011761211790144444
2023-01-24 09:02:49.517069: step: 900/533, loss: 0.0022041068878024817
2023-01-24 09:02:50.595010: step: 904/533, loss: 0.000344049563864246
2023-01-24 09:02:51.678312: step: 908/533, loss: 0.006451483350247145
2023-01-24 09:02:52.774139: step: 912/533, loss: 0.0005766208632849157
2023-01-24 09:02:53.887486: step: 916/533, loss: 0.019842850044369698
2023-01-24 09:02:55.011472: step: 920/533, loss: 0.0028821825981140137
2023-01-24 09:02:56.090270: step: 924/533, loss: 0.0013883045176044106
2023-01-24 09:02:57.189096: step: 928/533, loss: 0.007064721547067165
2023-01-24 09:02:58.297571: step: 932/533, loss: 0.012484817765653133
2023-01-24 09:02:59.396878: step: 936/533, loss: 0.022461002692580223
2023-01-24 09:03:00.482274: step: 940/533, loss: 0.00036061438731849194
2023-01-24 09:03:01.575611: step: 944/533, loss: 0.03004397079348564
2023-01-24 09:03:02.682042: step: 948/533, loss: 0.002280781278386712
2023-01-24 09:03:03.793606: step: 952/533, loss: 0.039794571697711945
2023-01-24 09:03:04.895255: step: 956/533, loss: 0.0008022491238079965
2023-01-24 09:03:05.985328: step: 960/533, loss: 0.0001259648852283135
2023-01-24 09:03:07.070375: step: 964/533, loss: 0.0008525452576577663
2023-01-24 09:03:08.158589: step: 968/533, loss: 0.035580456256866455
2023-01-24 09:03:09.255476: step: 972/533, loss: 0.0085849454626441
2023-01-24 09:03:10.350584: step: 976/533, loss: 0.0011851713061332703
2023-01-24 09:03:11.438479: step: 980/533, loss: 0.013051035813987255
2023-01-24 09:03:12.526778: step: 984/533, loss: 0.009019398130476475
2023-01-24 09:03:13.629886: step: 988/533, loss: 0.021764354780316353
2023-01-24 09:03:14.719247: step: 992/533, loss: 0.0335749052464962
2023-01-24 09:03:15.840410: step: 996/533, loss: 0.000870225194375962
2023-01-24 09:03:16.930873: step: 1000/533, loss: 0.0011684221681207418
2023-01-24 09:03:18.027588: step: 1004/533, loss: 0.008572004735469818
2023-01-24 09:03:19.125777: step: 1008/533, loss: 0.019943267107009888
2023-01-24 09:03:20.237451: step: 1012/533, loss: 0.003670214442536235
2023-01-24 09:03:21.338353: step: 1016/533, loss: 0.04213007912039757
2023-01-24 09:03:22.425106: step: 1020/533, loss: 0.003625896293669939
2023-01-24 09:03:23.528051: step: 1024/533, loss: 0.003332745749503374
2023-01-24 09:03:24.630874: step: 1028/533, loss: 0.004359920509159565
2023-01-24 09:03:25.720393: step: 1032/533, loss: 0.0026250570081174374
2023-01-24 09:03:26.829297: step: 1036/533, loss: 0.005392670631408691
2023-01-24 09:03:27.955910: step: 1040/533, loss: 0.043840859085321426
2023-01-24 09:03:29.061701: step: 1044/533, loss: 0.0056304726749658585
2023-01-24 09:03:30.181820: step: 1048/533, loss: 0.006523744203150272
2023-01-24 09:03:31.272230: step: 1052/533, loss: 0.01609966903924942
2023-01-24 09:03:32.363450: step: 1056/533, loss: 0.006232260260730982
2023-01-24 09:03:33.454645: step: 1060/533, loss: 0.04302826523780823
2023-01-24 09:03:34.527372: step: 1064/533, loss: 0.008509531617164612
2023-01-24 09:03:35.607591: step: 1068/533, loss: 0.004587607923895121
2023-01-24 09:03:36.709685: step: 1072/533, loss: 0.009234833531081676
2023-01-24 09:03:37.813646: step: 1076/533, loss: 0.0462842732667923
2023-01-24 09:03:38.904306: step: 1080/533, loss: 0.011478964239358902
2023-01-24 09:03:40.009724: step: 1084/533, loss: 0.004419317003339529
2023-01-24 09:03:41.118588: step: 1088/533, loss: 0.001445088884793222
2023-01-24 09:03:42.203191: step: 1092/533, loss: 0.0005062343552708626
2023-01-24 09:03:43.304438: step: 1096/533, loss: 0.0008132986840792
2023-01-24 09:03:44.377151: step: 1100/533, loss: 0.021822763606905937
2023-01-24 09:03:45.472543: step: 1104/533, loss: 0.0030935120303183794
2023-01-24 09:03:46.560423: step: 1108/533, loss: 0.00415413361042738
2023-01-24 09:03:47.659483: step: 1112/533, loss: 0.006080939434468746
2023-01-24 09:03:48.743017: step: 1116/533, loss: 0.006092450115829706
2023-01-24 09:03:49.819625: step: 1120/533, loss: 0.002181618707254529
2023-01-24 09:03:50.940004: step: 1124/533, loss: 0.012036127969622612
2023-01-24 09:03:52.028875: step: 1128/533, loss: 0.011470663361251354
2023-01-24 09:03:53.132723: step: 1132/533, loss: 0.000943235878366977
2023-01-24 09:03:54.237247: step: 1136/533, loss: 0.0021356961224228144
2023-01-24 09:03:55.335918: step: 1140/533, loss: 0.007906238548457623
2023-01-24 09:03:56.443420: step: 1144/533, loss: 0.008875084109604359
2023-01-24 09:03:57.521720: step: 1148/533, loss: 0.0035598059184849262
2023-01-24 09:03:58.654406: step: 1152/533, loss: 0.020732378587126732
2023-01-24 09:03:59.794750: step: 1156/533, loss: 0.012490106746554375
2023-01-24 09:04:00.888396: step: 1160/533, loss: 0.0012431200593709946
2023-01-24 09:04:01.981619: step: 1164/533, loss: 0.014775216579437256
2023-01-24 09:04:03.074931: step: 1168/533, loss: 0.001585128135047853
2023-01-24 09:04:04.168640: step: 1172/533, loss: 0.0015594871947541833
2023-01-24 09:04:05.268676: step: 1176/533, loss: 0.0043412549421191216
2023-01-24 09:04:06.354596: step: 1180/533, loss: 0.007919569499790668
2023-01-24 09:04:07.453557: step: 1184/533, loss: 0.003998902160674334
2023-01-24 09:04:08.591880: step: 1188/533, loss: 0.0037656803615391254
2023-01-24 09:04:09.693287: step: 1192/533, loss: 0.0008864960982464254
2023-01-24 09:04:10.796464: step: 1196/533, loss: 0.005609560292214155
2023-01-24 09:04:11.877110: step: 1200/533, loss: 0.0038855953607708216
2023-01-24 09:04:12.975156: step: 1204/533, loss: 0.005973102990537882
2023-01-24 09:04:14.047524: step: 1208/533, loss: 0.011247203685343266
2023-01-24 09:04:15.160815: step: 1212/533, loss: 0.0059984419494867325
2023-01-24 09:04:16.255197: step: 1216/533, loss: 0.003702316666021943
2023-01-24 09:04:17.338448: step: 1220/533, loss: 0.011450709775090218
2023-01-24 09:04:18.431258: step: 1224/533, loss: 0.0037971094716340303
2023-01-24 09:04:19.561019: step: 1228/533, loss: 0.00387790915556252
2023-01-24 09:04:20.687598: step: 1232/533, loss: 0.0021998838055878878
2023-01-24 09:04:21.801129: step: 1236/533, loss: 0.004519790410995483
2023-01-24 09:04:22.900606: step: 1240/533, loss: 0.0020931214094161987
2023-01-24 09:04:23.978959: step: 1244/533, loss: 0.01853582076728344
2023-01-24 09:04:25.067767: step: 1248/533, loss: 0.013136357069015503
2023-01-24 09:04:26.158301: step: 1252/533, loss: 0.0050955889746546745
2023-01-24 09:04:27.245944: step: 1256/533, loss: 0.0018737257923930883
2023-01-24 09:04:28.333343: step: 1260/533, loss: 0.0009794497163966298
2023-01-24 09:04:29.439964: step: 1264/533, loss: 0.006553822662681341
2023-01-24 09:04:30.517167: step: 1268/533, loss: 0.0024709899444133043
2023-01-24 09:04:31.616581: step: 1272/533, loss: 0.0001154326819232665
2023-01-24 09:04:32.693025: step: 1276/533, loss: 0.006534364074468613
2023-01-24 09:04:33.782132: step: 1280/533, loss: 0.0060380566865205765
2023-01-24 09:04:34.866673: step: 1284/533, loss: 0.001954849809408188
2023-01-24 09:04:35.961458: step: 1288/533, loss: 0.02706380933523178
2023-01-24 09:04:37.047940: step: 1292/533, loss: 0.004703739192336798
2023-01-24 09:04:38.139627: step: 1296/533, loss: 0.0016036543529480696
2023-01-24 09:04:39.228132: step: 1300/533, loss: 0.00036491118953563273
2023-01-24 09:04:40.312656: step: 1304/533, loss: 0.0041574034839868546
2023-01-24 09:04:41.401617: step: 1308/533, loss: 0.0035752567928284407
2023-01-24 09:04:42.505833: step: 1312/533, loss: 0.010087407194077969
2023-01-24 09:04:43.595943: step: 1316/533, loss: 0.0038982012774795294
2023-01-24 09:04:44.690029: step: 1320/533, loss: 0.005025359336286783
2023-01-24 09:04:45.782666: step: 1324/533, loss: 0.004777011927217245
2023-01-24 09:04:46.875791: step: 1328/533, loss: 0.002158521907404065
2023-01-24 09:04:47.958463: step: 1332/533, loss: 0.008118193596601486
2023-01-24 09:04:49.052417: step: 1336/533, loss: 0.011287289671599865
2023-01-24 09:04:50.142309: step: 1340/533, loss: 0.0012641104403883219
2023-01-24 09:04:51.240134: step: 1344/533, loss: 0.009086346253752708
2023-01-24 09:04:52.320813: step: 1348/533, loss: 0.011629522778093815
2023-01-24 09:04:53.424092: step: 1352/533, loss: 0.0013634655624628067
2023-01-24 09:04:54.505609: step: 1356/533, loss: 0.0037193314637988806
2023-01-24 09:04:55.607295: step: 1360/533, loss: 0.008912209421396255
2023-01-24 09:04:56.698923: step: 1364/533, loss: 0.00744472723454237
2023-01-24 09:04:57.767931: step: 1368/533, loss: 0.00037884878111071885
2023-01-24 09:04:58.872624: step: 1372/533, loss: 0.0036030488554388285
2023-01-24 09:04:59.984944: step: 1376/533, loss: 0.008011872880160809
2023-01-24 09:05:01.066345: step: 1380/533, loss: 4.5741158828604966e-05
2023-01-24 09:05:02.171172: step: 1384/533, loss: 0.007109255529940128
2023-01-24 09:05:03.270347: step: 1388/533, loss: 0.0015127689111977816
2023-01-24 09:05:04.383647: step: 1392/533, loss: 0.010235778987407684
2023-01-24 09:05:05.474421: step: 1396/533, loss: 0.007014463189989328
2023-01-24 09:05:06.576607: step: 1400/533, loss: 0.03636828809976578
2023-01-24 09:05:07.671294: step: 1404/533, loss: 0.0023161342833191156
2023-01-24 09:05:08.761725: step: 1408/533, loss: 0.0005792021984234452
2023-01-24 09:05:09.846362: step: 1412/533, loss: 0.011384935118258
2023-01-24 09:05:10.947084: step: 1416/533, loss: 0.00015826501476112753
2023-01-24 09:05:12.040169: step: 1420/533, loss: 8.568159515220941e-09
2023-01-24 09:05:13.149829: step: 1424/533, loss: 0.019405685365200043
2023-01-24 09:05:14.254514: step: 1428/533, loss: 0.0027804686687886715
2023-01-24 09:05:15.352353: step: 1432/533, loss: 0.0041356878355145454
2023-01-24 09:05:16.463500: step: 1436/533, loss: 0.020097017288208008
2023-01-24 09:05:17.544939: step: 1440/533, loss: 0.001824912498705089
2023-01-24 09:05:18.631786: step: 1444/533, loss: 0.007178185041993856
2023-01-24 09:05:19.720740: step: 1448/533, loss: 0.00011396031914046034
2023-01-24 09:05:20.818493: step: 1452/533, loss: 0.003175118938088417
2023-01-24 09:05:21.916316: step: 1456/533, loss: 0.0059076715260744095
2023-01-24 09:05:23.013991: step: 1460/533, loss: 0.0022466976661235094
2023-01-24 09:05:24.120174: step: 1464/533, loss: 0.013666774146258831
2023-01-24 09:05:25.221853: step: 1468/533, loss: 0.0034701297990977764
2023-01-24 09:05:26.336589: step: 1472/533, loss: 0.00907872524112463
2023-01-24 09:05:27.439243: step: 1476/533, loss: 0.004399539437144995
2023-01-24 09:05:28.532228: step: 1480/533, loss: 0.002163391327485442
2023-01-24 09:05:29.636273: step: 1484/533, loss: 0.015848182141780853
2023-01-24 09:05:30.733480: step: 1488/533, loss: 0.016311069950461388
2023-01-24 09:05:31.827099: step: 1492/533, loss: 0.021918749436736107
2023-01-24 09:05:32.897815: step: 1496/533, loss: 0.00019594158220570534
2023-01-24 09:05:33.969814: step: 1500/533, loss: 0.005106988362967968
2023-01-24 09:05:35.072909: step: 1504/533, loss: 0.0039046620950102806
2023-01-24 09:05:36.167660: step: 1508/533, loss: 0.006399724166840315
2023-01-24 09:05:37.254458: step: 1512/533, loss: 0.007941045798361301
2023-01-24 09:05:38.365998: step: 1516/533, loss: 0.0056286221370100975
2023-01-24 09:05:39.456181: step: 1520/533, loss: 0.000892113137524575
2023-01-24 09:05:40.548471: step: 1524/533, loss: 0.00395196070894599
2023-01-24 09:05:41.637940: step: 1528/533, loss: 0.0022757472470402718
2023-01-24 09:05:42.733411: step: 1532/533, loss: 5.351109939510934e-05
2023-01-24 09:05:43.840370: step: 1536/533, loss: 0.004246511496603489
2023-01-24 09:05:44.957787: step: 1540/533, loss: 0.00285726529546082
2023-01-24 09:05:46.049211: step: 1544/533, loss: 0.005288968328386545
2023-01-24 09:05:47.144313: step: 1548/533, loss: 0.003231736831367016
2023-01-24 09:05:48.232856: step: 1552/533, loss: 0.0018369518220424652
2023-01-24 09:05:49.335633: step: 1556/533, loss: 0.00240459106862545
2023-01-24 09:05:50.486379: step: 1560/533, loss: 0.003636219073086977
2023-01-24 09:05:51.585735: step: 1564/533, loss: 0.007195653393864632
2023-01-24 09:05:52.694860: step: 1568/533, loss: 0.0004071895673405379
2023-01-24 09:05:53.782827: step: 1572/533, loss: 0.0019291354110464454
2023-01-24 09:05:54.870933: step: 1576/533, loss: 0.000446243560872972
2023-01-24 09:05:55.958380: step: 1580/533, loss: 0.009022315964102745
2023-01-24 09:05:57.064114: step: 1584/533, loss: 0.0012326148571446538
2023-01-24 09:05:58.164318: step: 1588/533, loss: 0.005875287111848593
2023-01-24 09:05:59.261345: step: 1592/533, loss: 0.003151476848870516
2023-01-24 09:06:00.351814: step: 1596/533, loss: 0.01689518429338932
2023-01-24 09:06:01.453713: step: 1600/533, loss: 0.0013390079839155078
2023-01-24 09:06:02.540863: step: 1604/533, loss: 0.0012116912985220551
2023-01-24 09:06:03.643097: step: 1608/533, loss: 0.012336661107838154
2023-01-24 09:06:04.725369: step: 1612/533, loss: 0.0031413156539201736
2023-01-24 09:06:05.823679: step: 1616/533, loss: 0.0018415426602587104
2023-01-24 09:06:06.902195: step: 1620/533, loss: 0.001934324624016881
2023-01-24 09:06:07.990167: step: 1624/533, loss: 0.00968566257506609
2023-01-24 09:06:09.075428: step: 1628/533, loss: 0.009623591788113117
2023-01-24 09:06:10.171111: step: 1632/533, loss: 0.0001774797565303743
2023-01-24 09:06:11.271956: step: 1636/533, loss: 0.0032672081142663956
2023-01-24 09:06:12.340825: step: 1640/533, loss: 0.0023456565104424953
2023-01-24 09:06:13.457417: step: 1644/533, loss: 0.004192539025098085
2023-01-24 09:06:14.539364: step: 1648/533, loss: 0.004131511319428682
2023-01-24 09:06:15.630438: step: 1652/533, loss: 0.007016743998974562
2023-01-24 09:06:16.733231: step: 1656/533, loss: 0.005280924029648304
2023-01-24 09:06:17.831896: step: 1660/533, loss: 0.001571949222125113
2023-01-24 09:06:18.970987: step: 1664/533, loss: 0.011225712485611439
2023-01-24 09:06:20.059711: step: 1668/533, loss: 0.0017664742190390825
2023-01-24 09:06:21.144230: step: 1672/533, loss: 0.009531441144645214
2023-01-24 09:06:22.241493: step: 1676/533, loss: 0.004623569082468748
2023-01-24 09:06:23.362016: step: 1680/533, loss: 0.004238318186253309
2023-01-24 09:06:24.456692: step: 1684/533, loss: 0.0009229454444721341
2023-01-24 09:06:25.529731: step: 1688/533, loss: 0.005016854032874107
2023-01-24 09:06:26.600145: step: 1692/533, loss: 4.6691235183971e-05
2023-01-24 09:06:27.695139: step: 1696/533, loss: 0.0019515911117196083
2023-01-24 09:06:28.801195: step: 1700/533, loss: 0.00544441444799304
2023-01-24 09:06:29.887723: step: 1704/533, loss: 0.003857135307043791
2023-01-24 09:06:30.993925: step: 1708/533, loss: 0.015606380999088287
2023-01-24 09:06:32.079938: step: 1712/533, loss: 0.0014624831965193152
2023-01-24 09:06:33.162328: step: 1716/533, loss: 0.001651458558626473
2023-01-24 09:06:34.267131: step: 1720/533, loss: 0.015364877879619598
2023-01-24 09:06:35.377406: step: 1724/533, loss: 0.005741654895246029
2023-01-24 09:06:36.473008: step: 1728/533, loss: 0.002814542967826128
2023-01-24 09:06:37.567005: step: 1732/533, loss: 0.008345343172550201
2023-01-24 09:06:38.664171: step: 1736/533, loss: 0.0017145182937383652
2023-01-24 09:06:39.781825: step: 1740/533, loss: 0.00010117284546140581
2023-01-24 09:06:40.881825: step: 1744/533, loss: 0.007945938967168331
2023-01-24 09:06:41.973221: step: 1748/533, loss: 0.005303646437823772
2023-01-24 09:06:43.073669: step: 1752/533, loss: 0.029831521213054657
2023-01-24 09:06:44.166531: step: 1756/533, loss: 0.008714421652257442
2023-01-24 09:06:45.253851: step: 1760/533, loss: 0.003748358925804496
2023-01-24 09:06:46.359189: step: 1764/533, loss: 0.008918979205191135
2023-01-24 09:06:47.448605: step: 1768/533, loss: 0.0024885879829525948
2023-01-24 09:06:48.541428: step: 1772/533, loss: 0.01802513375878334
2023-01-24 09:06:49.632065: step: 1776/533, loss: 0.0011806187685579062
2023-01-24 09:06:50.735471: step: 1780/533, loss: 0.005206563975661993
2023-01-24 09:06:51.843374: step: 1784/533, loss: 0.009615745395421982
2023-01-24 09:06:52.924425: step: 1788/533, loss: 0.0038772104308009148
2023-01-24 09:06:54.016042: step: 1792/533, loss: 0.011932672932744026
2023-01-24 09:06:55.119608: step: 1796/533, loss: 0.0006140652694739401
2023-01-24 09:06:56.217875: step: 1800/533, loss: 0.0026406676042824984
2023-01-24 09:06:57.311223: step: 1804/533, loss: 0.01441273931413889
2023-01-24 09:06:58.407256: step: 1808/533, loss: 0.013970641419291496
2023-01-24 09:06:59.539663: step: 1812/533, loss: 0.004292869009077549
2023-01-24 09:07:00.628228: step: 1816/533, loss: 0.0019625891000032425
2023-01-24 09:07:01.745620: step: 1820/533, loss: 0.008124927058815956
2023-01-24 09:07:02.837135: step: 1824/533, loss: 0.015217330306768417
2023-01-24 09:07:03.943611: step: 1828/533, loss: 0.0331416092813015
2023-01-24 09:07:05.028202: step: 1832/533, loss: 0.0028403685428202152
2023-01-24 09:07:06.124606: step: 1836/533, loss: 0.014229648746550083
2023-01-24 09:07:07.219059: step: 1840/533, loss: 0.004458426497876644
2023-01-24 09:07:08.324465: step: 1844/533, loss: 0.009048285894095898
2023-01-24 09:07:09.431206: step: 1848/533, loss: 0.017690183594822884
2023-01-24 09:07:10.543295: step: 1852/533, loss: 0.00180422468110919
2023-01-24 09:07:11.635657: step: 1856/533, loss: 0.006955134216696024
2023-01-24 09:07:12.709605: step: 1860/533, loss: 0.0009929146617650986
2023-01-24 09:07:13.809423: step: 1864/533, loss: 0.0073118070140480995
2023-01-24 09:07:14.923205: step: 1868/533, loss: 0.02197384461760521
2023-01-24 09:07:16.033614: step: 1872/533, loss: 0.0157154593616724
2023-01-24 09:07:17.128547: step: 1876/533, loss: 0.0014746100641787052
2023-01-24 09:07:18.231702: step: 1880/533, loss: 0.040344059467315674
2023-01-24 09:07:19.335134: step: 1884/533, loss: 4.719916432804894e-06
2023-01-24 09:07:20.443389: step: 1888/533, loss: 0.00455081183463335
2023-01-24 09:07:21.537834: step: 1892/533, loss: 0.0016449985560029745
2023-01-24 09:07:22.613541: step: 1896/533, loss: 0.009950541891157627
2023-01-24 09:07:23.725341: step: 1900/533, loss: 0.03328080102801323
2023-01-24 09:07:24.838627: step: 1904/533, loss: 0.001306359190493822
2023-01-24 09:07:25.915091: step: 1908/533, loss: 0.004956203978508711
2023-01-24 09:07:27.005506: step: 1912/533, loss: 0.0003071356622967869
2023-01-24 09:07:28.081434: step: 1916/533, loss: 0.005287814419716597
2023-01-24 09:07:29.182475: step: 1920/533, loss: 0.003164898604154587
2023-01-24 09:07:30.296598: step: 1924/533, loss: 0.0016971592558547854
2023-01-24 09:07:31.392974: step: 1928/533, loss: 0.0049974615685641766
2023-01-24 09:07:32.468375: step: 1932/533, loss: 0.00825286190956831
2023-01-24 09:07:33.553444: step: 1936/533, loss: 0.002666659653186798
2023-01-24 09:07:34.634065: step: 1940/533, loss: 0.00943884439766407
2023-01-24 09:07:35.750023: step: 1944/533, loss: 0.0036759136710315943
2023-01-24 09:07:36.844215: step: 1948/533, loss: 0.002751452848315239
2023-01-24 09:07:37.934582: step: 1952/533, loss: 0.0025299754925072193
2023-01-24 09:07:39.019516: step: 1956/533, loss: 0.004914052318781614
2023-01-24 09:07:40.135903: step: 1960/533, loss: 0.01810113899409771
2023-01-24 09:07:41.261419: step: 1964/533, loss: 0.003999169450253248
2023-01-24 09:07:42.370180: step: 1968/533, loss: 0.00785564910620451
2023-01-24 09:07:43.476088: step: 1972/533, loss: 0.006371656432747841
2023-01-24 09:07:44.570970: step: 1976/533, loss: 0.0007513090968132019
2023-01-24 09:07:45.674916: step: 1980/533, loss: 0.0018068323843181133
2023-01-24 09:07:46.749931: step: 1984/533, loss: 0.021318498998880386
2023-01-24 09:07:47.849243: step: 1988/533, loss: 0.010066987946629524
2023-01-24 09:07:48.959773: step: 1992/533, loss: 0.008842708542943
2023-01-24 09:07:50.053701: step: 1996/533, loss: 0.000428685249062255
2023-01-24 09:07:51.147441: step: 2000/533, loss: 0.004915186669677496
2023-01-24 09:07:52.239846: step: 2004/533, loss: 0.0022880458272993565
2023-01-24 09:07:53.349777: step: 2008/533, loss: 0.05600258335471153
2023-01-24 09:07:54.427608: step: 2012/533, loss: 0.006157109513878822
2023-01-24 09:07:55.522716: step: 2016/533, loss: 0.008332879282534122
2023-01-24 09:07:56.610049: step: 2020/533, loss: 0.0028868508525192738
2023-01-24 09:07:57.705745: step: 2024/533, loss: 0.00045059891999699175
2023-01-24 09:07:58.790492: step: 2028/533, loss: 0.0010483278892934322
2023-01-24 09:07:59.879019: step: 2032/533, loss: 0.008325236849486828
2023-01-24 09:08:00.990278: step: 2036/533, loss: 0.009828277863562107
2023-01-24 09:08:02.111468: step: 2040/533, loss: 0.005076834931969643
2023-01-24 09:08:03.209174: step: 2044/533, loss: 0.0017634235555306077
2023-01-24 09:08:04.310643: step: 2048/533, loss: 0.004998413380235434
2023-01-24 09:08:05.414021: step: 2052/533, loss: 0.0034961712080985308
2023-01-24 09:08:06.522756: step: 2056/533, loss: 0.0034334484953433275
2023-01-24 09:08:07.612966: step: 2060/533, loss: 0.0024690141435712576
2023-01-24 09:08:08.726365: step: 2064/533, loss: 0.0017764086369425058
2023-01-24 09:08:09.846794: step: 2068/533, loss: 0.012939650565385818
2023-01-24 09:08:10.955777: step: 2072/533, loss: 0.009973276406526566
2023-01-24 09:08:12.045890: step: 2076/533, loss: 0.0033852835185825825
2023-01-24 09:08:13.149764: step: 2080/533, loss: 0.0032529616728425026
2023-01-24 09:08:14.239777: step: 2084/533, loss: 0.0033692303113639355
2023-01-24 09:08:15.367611: step: 2088/533, loss: 0.005619236268103123
2023-01-24 09:08:16.452081: step: 2092/533, loss: 0.0038419319316744804
2023-01-24 09:08:17.567415: step: 2096/533, loss: 0.0026143277063965797
2023-01-24 09:08:18.650537: step: 2100/533, loss: 0.00022001763863954693
2023-01-24 09:08:19.734998: step: 2104/533, loss: 0.0010883540380746126
2023-01-24 09:08:20.814899: step: 2108/533, loss: 0.014261215925216675
2023-01-24 09:08:21.913415: step: 2112/533, loss: 0.0057484302669763565
2023-01-24 09:08:23.004076: step: 2116/533, loss: 0.008537928573787212
2023-01-24 09:08:24.103080: step: 2120/533, loss: 0.007787937764078379
2023-01-24 09:08:25.203799: step: 2124/533, loss: 0.0006057439604774117
2023-01-24 09:08:26.291390: step: 2128/533, loss: 0.0022065499797463417
2023-01-24 09:08:27.378511: step: 2132/533, loss: 0.015993956476449966
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3861080383480826, 'r': 0.33115907653383936, 'f1': 0.35652877085461354}, 'combined': 0.26270541010339943, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3950155107636563, 'r': 0.35779289532631176, 'f1': 0.37548396684093266}, 'combined': 0.2503226445606217, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3624856561786011, 'r': 0.3212159420026693, 'f1': 0.34060523427647227}, 'combined': 0.2509722778879269, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3887157308119644, 'r': 0.30910375902066783, 'f1': 0.34436840855007456}, 'combined': 0.22957893903338297, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34681372549019607, 'r': 0.3139091974550731, 'f1': 0.3295421256151863}, 'combined': 0.2428205136111899, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38548060596144323, 'r': 0.3484151630805352, 'f1': 0.366011888488643}, 'combined': 0.2440079256590953, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 09:10:46.943586: step: 4/533, loss: 8.0966463428922e-05
2023-01-24 09:10:48.030189: step: 8/533, loss: 0.0023015830665826797
2023-01-24 09:10:49.087430: step: 12/533, loss: 0.007734872400760651
2023-01-24 09:10:50.191503: step: 16/533, loss: 0.008311012759804726
2023-01-24 09:10:51.250177: step: 20/533, loss: 0.008611820638179779
2023-01-24 09:10:52.346677: step: 24/533, loss: 0.004204935859888792
2023-01-24 09:10:53.436331: step: 28/533, loss: 0.00651250034570694
2023-01-24 09:10:54.523232: step: 32/533, loss: 0.003072660183534026
2023-01-24 09:10:55.619150: step: 36/533, loss: 0.0051412396132946014
2023-01-24 09:10:56.705745: step: 40/533, loss: 0.002788097131997347
2023-01-24 09:10:57.789148: step: 44/533, loss: 0.001235146657563746
2023-01-24 09:10:58.895007: step: 48/533, loss: 0.0026609066408127546
2023-01-24 09:11:00.003849: step: 52/533, loss: 0.004810952115803957
2023-01-24 09:11:01.075226: step: 56/533, loss: 0.003829183056950569
2023-01-24 09:11:02.145591: step: 60/533, loss: 0.0022024111822247505
2023-01-24 09:11:03.270191: step: 64/533, loss: 0.007290588691830635
2023-01-24 09:11:04.349662: step: 68/533, loss: 0.008113766089081764
2023-01-24 09:11:05.433800: step: 72/533, loss: 0.001202093088068068
2023-01-24 09:11:06.499373: step: 76/533, loss: 7.902102515799925e-05
2023-01-24 09:11:07.587803: step: 80/533, loss: 0.0003823718579951674
2023-01-24 09:11:08.670087: step: 84/533, loss: 0.005102192051708698
2023-01-24 09:11:09.752581: step: 88/533, loss: 0.0023103728890419006
2023-01-24 09:11:10.836302: step: 92/533, loss: 0.0022932332940399647
2023-01-24 09:11:11.918882: step: 96/533, loss: 0.0044368538074195385
2023-01-24 09:11:13.002512: step: 100/533, loss: 5.379260073823389e-06
2023-01-24 09:11:14.089031: step: 104/533, loss: 0.0008365602698177099
2023-01-24 09:11:15.186441: step: 108/533, loss: 0.00042032889905385673
2023-01-24 09:11:16.267446: step: 112/533, loss: 5.788538146589417e-06
2023-01-24 09:11:17.348247: step: 116/533, loss: 0.007583192549645901
2023-01-24 09:11:18.463523: step: 120/533, loss: 0.019036507233977318
2023-01-24 09:11:19.537640: step: 124/533, loss: 0.00979465339332819
2023-01-24 09:11:20.609914: step: 128/533, loss: 0.004084856249392033
2023-01-24 09:11:21.708410: step: 132/533, loss: 0.009691416285932064
2023-01-24 09:11:22.791955: step: 136/533, loss: 0.0003042093594558537
2023-01-24 09:11:23.889766: step: 140/533, loss: 0.0012556682340800762
2023-01-24 09:11:25.003192: step: 144/533, loss: 0.005699270870536566
2023-01-24 09:11:26.079025: step: 148/533, loss: 0.023608962073922157
2023-01-24 09:11:27.185517: step: 152/533, loss: 0.001439716899767518
2023-01-24 09:11:28.280619: step: 156/533, loss: 0.003456997685134411
2023-01-24 09:11:29.366547: step: 160/533, loss: 0.00839202105998993
2023-01-24 09:11:30.470409: step: 164/533, loss: 0.007593044079840183
2023-01-24 09:11:31.562047: step: 168/533, loss: 0.002693352522328496
2023-01-24 09:11:32.662340: step: 172/533, loss: 0.029990993440151215
2023-01-24 09:11:33.765229: step: 176/533, loss: 0.010694582015275955
2023-01-24 09:11:34.842288: step: 180/533, loss: 0.006824728101491928
2023-01-24 09:11:35.925624: step: 184/533, loss: 0.03706947714090347
2023-01-24 09:11:37.028734: step: 188/533, loss: 0.004041747190058231
2023-01-24 09:11:38.137459: step: 192/533, loss: 0.008203216828405857
2023-01-24 09:11:39.206728: step: 196/533, loss: 0.003842031117528677
2023-01-24 09:11:40.327331: step: 200/533, loss: 0.0031862840987741947
2023-01-24 09:11:41.409953: step: 204/533, loss: 0.011993718333542347
2023-01-24 09:11:42.482739: step: 208/533, loss: 0.0007226848974823952
2023-01-24 09:11:43.567139: step: 212/533, loss: 0.00019760234863497317
2023-01-24 09:11:44.632825: step: 216/533, loss: 0.008321443572640419
2023-01-24 09:11:45.756042: step: 220/533, loss: 0.005422838497906923
2023-01-24 09:11:46.833107: step: 224/533, loss: 0.006147393025457859
2023-01-24 09:11:47.943564: step: 228/533, loss: 0.00014510832261294127
2023-01-24 09:11:49.072390: step: 232/533, loss: 0.006330178119242191
2023-01-24 09:11:50.199340: step: 236/533, loss: 0.0068958294577896595
2023-01-24 09:11:51.268450: step: 240/533, loss: 4.675898890127428e-05
2023-01-24 09:11:52.377971: step: 244/533, loss: 0.006600236985832453
2023-01-24 09:11:53.495033: step: 248/533, loss: 0.0005372997839003801
2023-01-24 09:11:54.592172: step: 252/533, loss: 0.004938424564898014
2023-01-24 09:11:55.702399: step: 256/533, loss: 0.0011595961404964328
2023-01-24 09:11:56.800520: step: 260/533, loss: 0.010030509904026985
2023-01-24 09:11:57.882084: step: 264/533, loss: 0.004461414180696011
2023-01-24 09:11:58.983674: step: 268/533, loss: 0.0010695857927203178
2023-01-24 09:12:00.091214: step: 272/533, loss: 0.003885589772835374
2023-01-24 09:12:01.225567: step: 276/533, loss: 0.00439440319314599
2023-01-24 09:12:02.320180: step: 280/533, loss: 0.06642025709152222
2023-01-24 09:12:03.408793: step: 284/533, loss: 0.007028973661363125
2023-01-24 09:12:04.489744: step: 288/533, loss: 0.042385000735521317
2023-01-24 09:12:05.586290: step: 292/533, loss: 0.0009913453832268715
2023-01-24 09:12:06.697374: step: 296/533, loss: 0.015447116456925869
2023-01-24 09:12:07.807885: step: 300/533, loss: 0.0011656328570097685
2023-01-24 09:12:08.894042: step: 304/533, loss: 0.0016296689864248037
2023-01-24 09:12:09.991804: step: 308/533, loss: 0.0032862862572073936
2023-01-24 09:12:11.098488: step: 312/533, loss: 0.004613254684954882
2023-01-24 09:12:12.220619: step: 316/533, loss: 0.010540368035435677
2023-01-24 09:12:13.325008: step: 320/533, loss: 0.002389268483966589
2023-01-24 09:12:14.418836: step: 324/533, loss: 0.0012244494864717126
2023-01-24 09:12:15.509151: step: 328/533, loss: 0.0013210611650720239
2023-01-24 09:12:16.599912: step: 332/533, loss: 0.006205260753631592
2023-01-24 09:12:17.676153: step: 336/533, loss: 0.0016825487837195396
2023-01-24 09:12:18.766335: step: 340/533, loss: 0.005014369264245033
2023-01-24 09:12:19.854536: step: 344/533, loss: 0.0014662459725514054
2023-01-24 09:12:20.956425: step: 348/533, loss: 0.0027540598530322313
2023-01-24 09:12:22.044302: step: 352/533, loss: 0.01924949139356613
2023-01-24 09:12:23.151739: step: 356/533, loss: 0.006817998364567757
2023-01-24 09:12:24.253945: step: 360/533, loss: 0.001510970527306199
2023-01-24 09:12:25.358224: step: 364/533, loss: 0.00747899804264307
2023-01-24 09:12:26.439538: step: 368/533, loss: 0.0017245096387341619
2023-01-24 09:12:27.543130: step: 372/533, loss: 0.018177727237343788
2023-01-24 09:12:28.646062: step: 376/533, loss: 0.021210433915257454
2023-01-24 09:12:29.745884: step: 380/533, loss: 0.007874980568885803
2023-01-24 09:12:30.830910: step: 384/533, loss: 0.011429889127612114
2023-01-24 09:12:31.932181: step: 388/533, loss: 0.013838778249919415
2023-01-24 09:12:33.011505: step: 392/533, loss: 0.012341911904513836
2023-01-24 09:12:34.112684: step: 396/533, loss: 0.002673715353012085
2023-01-24 09:12:35.194206: step: 400/533, loss: 0.0019763547461479902
2023-01-24 09:12:36.305190: step: 404/533, loss: 0.0037041360046714544
2023-01-24 09:12:37.400184: step: 408/533, loss: 0.0035335980355739594
2023-01-24 09:12:38.495947: step: 412/533, loss: 0.016438407823443413
2023-01-24 09:12:39.604414: step: 416/533, loss: 0.0036197821609675884
2023-01-24 09:12:40.720468: step: 420/533, loss: 0.007343341130763292
2023-01-24 09:12:41.854085: step: 424/533, loss: 0.10530548542737961
2023-01-24 09:12:42.945353: step: 428/533, loss: 0.014492571353912354
2023-01-24 09:12:44.025777: step: 432/533, loss: 0.004810307174921036
2023-01-24 09:12:45.119066: step: 436/533, loss: 0.0086522176861763
2023-01-24 09:12:46.203369: step: 440/533, loss: 0.0018515178235247731
2023-01-24 09:12:47.294566: step: 444/533, loss: 0.016669249162077904
2023-01-24 09:12:48.383358: step: 448/533, loss: 0.003930500242859125
2023-01-24 09:12:49.475216: step: 452/533, loss: 0.007133360020816326
2023-01-24 09:12:50.583399: step: 456/533, loss: 0.0031633516773581505
2023-01-24 09:12:51.691917: step: 460/533, loss: 0.01503559947013855
2023-01-24 09:12:52.757727: step: 464/533, loss: 0.00022578668722417206
2023-01-24 09:12:53.841463: step: 468/533, loss: 0.0006520909373648465
2023-01-24 09:12:54.949135: step: 472/533, loss: 0.008549286052584648
2023-01-24 09:12:56.040693: step: 476/533, loss: 0.0004599808598868549
2023-01-24 09:12:57.152891: step: 480/533, loss: 0.002974553732201457
2023-01-24 09:12:58.265482: step: 484/533, loss: 0.000907369249034673
2023-01-24 09:12:59.333450: step: 488/533, loss: 0.0013387913350015879
2023-01-24 09:13:00.411229: step: 492/533, loss: 0.008805065415799618
2023-01-24 09:13:01.503997: step: 496/533, loss: 0.004395386669784784
2023-01-24 09:13:02.616951: step: 500/533, loss: 0.0009569603716954589
2023-01-24 09:13:03.737811: step: 504/533, loss: 0.025318758562207222
2023-01-24 09:13:04.849361: step: 508/533, loss: 0.002299608662724495
2023-01-24 09:13:05.946797: step: 512/533, loss: 0.00240132724866271
2023-01-24 09:13:07.065755: step: 516/533, loss: 0.0029548273887485266
2023-01-24 09:13:08.163277: step: 520/533, loss: 0.0037298905663192272
2023-01-24 09:13:09.248455: step: 524/533, loss: 7.182019180618227e-05
2023-01-24 09:13:10.341753: step: 528/533, loss: 0.006083901505917311
2023-01-24 09:13:11.446836: step: 532/533, loss: 0.0012510297819972038
2023-01-24 09:13:12.544930: step: 536/533, loss: 0.0003578716132324189
2023-01-24 09:13:13.636223: step: 540/533, loss: 0.005109770689159632
2023-01-24 09:13:14.771945: step: 544/533, loss: 0.0036911792121827602
2023-01-24 09:13:15.868897: step: 548/533, loss: 0.0019272980280220509
2023-01-24 09:13:16.952578: step: 552/533, loss: 0.0045945909805595875
2023-01-24 09:13:18.048138: step: 556/533, loss: 0.0002878583036363125
2023-01-24 09:13:19.157170: step: 560/533, loss: 0.002195600653067231
2023-01-24 09:13:20.277855: step: 564/533, loss: 0.0016848500818014145
2023-01-24 09:13:21.388680: step: 568/533, loss: 0.0063800690695643425
2023-01-24 09:13:22.477034: step: 572/533, loss: 0.0106077641248703
2023-01-24 09:13:23.584476: step: 576/533, loss: 0.00907472800463438
2023-01-24 09:13:24.672790: step: 580/533, loss: 0.006805250886827707
2023-01-24 09:13:25.761634: step: 584/533, loss: 0.004331057891249657
2023-01-24 09:13:26.856744: step: 588/533, loss: 0.02009602263569832
2023-01-24 09:13:27.940912: step: 592/533, loss: 0.012161490507423878
2023-01-24 09:13:29.028503: step: 596/533, loss: 0.005830874666571617
2023-01-24 09:13:30.115690: step: 600/533, loss: 0.0002997197734657675
2023-01-24 09:13:31.192353: step: 604/533, loss: 0.00517085799947381
2023-01-24 09:13:32.300920: step: 608/533, loss: 0.0015361672267317772
2023-01-24 09:13:33.385584: step: 612/533, loss: 0.0014342950889840722
2023-01-24 09:13:34.484529: step: 616/533, loss: 0.0038108776789158583
2023-01-24 09:13:35.615077: step: 620/533, loss: 0.005859197583049536
2023-01-24 09:13:36.736414: step: 624/533, loss: 0.0011812959564849734
2023-01-24 09:13:37.804112: step: 628/533, loss: 0.0012199271004647017
2023-01-24 09:13:38.888829: step: 632/533, loss: 0.0022006502840667963
2023-01-24 09:13:39.962802: step: 636/533, loss: 0.0028874878771603107
2023-01-24 09:13:41.078121: step: 640/533, loss: 0.0011738876346498728
2023-01-24 09:13:42.160695: step: 644/533, loss: 0.00014610850485041738
2023-01-24 09:13:43.260268: step: 648/533, loss: 0.00590424844995141
2023-01-24 09:13:44.349628: step: 652/533, loss: 0.00011098058894276619
2023-01-24 09:13:45.443600: step: 656/533, loss: 0.0010168123990297318
2023-01-24 09:13:46.555717: step: 660/533, loss: 0.04462634027004242
2023-01-24 09:13:47.654754: step: 664/533, loss: 0.004974106326699257
2023-01-24 09:13:48.750197: step: 668/533, loss: 0.011911511421203613
2023-01-24 09:13:49.824233: step: 672/533, loss: 0.0002815905027091503
2023-01-24 09:13:50.935918: step: 676/533, loss: 0.037176210433244705
2023-01-24 09:13:52.041742: step: 680/533, loss: 0.0016358168795704842
2023-01-24 09:13:53.151461: step: 684/533, loss: 0.003364528762176633
2023-01-24 09:13:54.272564: step: 688/533, loss: 0.010265462100505829
2023-01-24 09:13:55.372120: step: 692/533, loss: 0.007061947602778673
2023-01-24 09:13:56.453494: step: 696/533, loss: 0.004756347741931677
2023-01-24 09:13:57.561536: step: 700/533, loss: 0.004620659165084362
2023-01-24 09:13:58.658356: step: 704/533, loss: 0.006073028780519962
2023-01-24 09:13:59.789155: step: 708/533, loss: 0.0008409203146584332
2023-01-24 09:14:00.884721: step: 712/533, loss: 0.00740415696054697
2023-01-24 09:14:01.999082: step: 716/533, loss: 0.009619070217013359
2023-01-24 09:14:03.076003: step: 720/533, loss: 2.6077017878378683e-08
2023-01-24 09:14:04.178505: step: 724/533, loss: 0.0033633175771683455
2023-01-24 09:14:05.259627: step: 728/533, loss: 0.008680108934640884
2023-01-24 09:14:06.348196: step: 732/533, loss: 0.003329221624881029
2023-01-24 09:14:07.449103: step: 736/533, loss: 0.002594414632767439
2023-01-24 09:14:08.563380: step: 740/533, loss: 0.006610732991248369
2023-01-24 09:14:09.687067: step: 744/533, loss: 0.012836098670959473
2023-01-24 09:14:10.786913: step: 748/533, loss: 0.0008769871783442795
2023-01-24 09:14:11.879796: step: 752/533, loss: 0.0011432046303525567
2023-01-24 09:14:12.965786: step: 756/533, loss: 0.004250215832144022
2023-01-24 09:14:14.059776: step: 760/533, loss: 0.0012450105277821422
2023-01-24 09:14:15.139867: step: 764/533, loss: 0.018578901886940002
2023-01-24 09:14:16.240463: step: 768/533, loss: 0.04128025472164154
2023-01-24 09:14:17.323925: step: 772/533, loss: 1.8666327378014103e-05
2023-01-24 09:14:18.419248: step: 776/533, loss: 0.0010333489626646042
2023-01-24 09:14:19.498057: step: 780/533, loss: 0.0022955527529120445
2023-01-24 09:14:20.608681: step: 784/533, loss: 0.010634703561663628
2023-01-24 09:14:21.726151: step: 788/533, loss: 0.010546831414103508
2023-01-24 09:14:22.821686: step: 792/533, loss: 0.0013935179449617863
2023-01-24 09:14:23.925572: step: 796/533, loss: 0.002955765463411808
2023-01-24 09:14:25.029037: step: 800/533, loss: 0.008751630783081055
2023-01-24 09:14:26.155914: step: 804/533, loss: 0.006691962946206331
2023-01-24 09:14:27.256169: step: 808/533, loss: 0.005504224915057421
2023-01-24 09:14:28.396058: step: 812/533, loss: 0.0018005338497459888
2023-01-24 09:14:29.493889: step: 816/533, loss: 0.01071806438267231
2023-01-24 09:14:30.564804: step: 820/533, loss: 0.016453931108117104
2023-01-24 09:14:31.661440: step: 824/533, loss: 0.0015953333349898458
2023-01-24 09:14:32.762522: step: 828/533, loss: 0.002123825252056122
2023-01-24 09:14:33.853981: step: 832/533, loss: 0.0013914185110479593
2023-01-24 09:14:34.946144: step: 836/533, loss: 0.002776889596134424
2023-01-24 09:14:36.036685: step: 840/533, loss: 0.011816862970590591
2023-01-24 09:14:37.164170: step: 844/533, loss: 0.01963752880692482
2023-01-24 09:14:38.285377: step: 848/533, loss: 0.008957276120781898
2023-01-24 09:14:39.393661: step: 852/533, loss: 0.005090773105621338
2023-01-24 09:14:40.483871: step: 856/533, loss: 0.0011276418808847666
2023-01-24 09:14:41.590750: step: 860/533, loss: 0.0004038401530124247
2023-01-24 09:14:42.691835: step: 864/533, loss: 0.0009605124942027032
2023-01-24 09:14:43.806889: step: 868/533, loss: 0.030390849336981773
2023-01-24 09:14:44.912332: step: 872/533, loss: 0.02717532031238079
2023-01-24 09:14:45.988899: step: 876/533, loss: 0.0003826993051916361
2023-01-24 09:14:47.093408: step: 880/533, loss: 0.0003548540989868343
2023-01-24 09:14:48.193702: step: 884/533, loss: 0.0004677722754422575
2023-01-24 09:14:49.295412: step: 888/533, loss: 0.003376259934157133
2023-01-24 09:14:50.391921: step: 892/533, loss: 0.00014735809236299247
2023-01-24 09:14:51.498269: step: 896/533, loss: 0.003201836720108986
2023-01-24 09:14:52.605401: step: 900/533, loss: 0.0026509594172239304
2023-01-24 09:14:53.685072: step: 904/533, loss: 0.006282740272581577
2023-01-24 09:14:54.777596: step: 908/533, loss: 0.001313160639256239
2023-01-24 09:14:55.898400: step: 912/533, loss: 0.0035391354467719793
2023-01-24 09:14:56.986330: step: 916/533, loss: 0.00026187949697487056
2023-01-24 09:14:58.073844: step: 920/533, loss: 0.005410416983067989
2023-01-24 09:14:59.173945: step: 924/533, loss: 0.007963521406054497
2023-01-24 09:15:00.277709: step: 928/533, loss: 0.0
2023-01-24 09:15:01.396346: step: 932/533, loss: 7.240815466502681e-05
2023-01-24 09:15:02.517383: step: 936/533, loss: 0.04031747952103615
2023-01-24 09:15:03.623987: step: 940/533, loss: 0.008926824666559696
2023-01-24 09:15:04.721374: step: 944/533, loss: 0.009052708745002747
2023-01-24 09:15:05.824230: step: 948/533, loss: 0.013581193052232265
2023-01-24 09:15:06.928494: step: 952/533, loss: 0.012582150287926197
2023-01-24 09:15:08.027933: step: 956/533, loss: 0.0010705174645408988
2023-01-24 09:15:09.113099: step: 960/533, loss: 0.00017971792840398848
2023-01-24 09:15:10.193715: step: 964/533, loss: 5.8159366744803265e-05
2023-01-24 09:15:11.306000: step: 968/533, loss: 0.005876472219824791
2023-01-24 09:15:12.387583: step: 972/533, loss: 0.005427788943052292
2023-01-24 09:15:13.467012: step: 976/533, loss: 0.0012403104919940233
2023-01-24 09:15:14.543346: step: 980/533, loss: 0.005286113359034061
2023-01-24 09:15:15.647090: step: 984/533, loss: 0.009619809687137604
2023-01-24 09:15:16.726281: step: 988/533, loss: 0.001143975998274982
2023-01-24 09:15:17.818875: step: 992/533, loss: 0.006745561026036739
2023-01-24 09:15:18.920449: step: 996/533, loss: 0.0006419665878638625
2023-01-24 09:15:20.020338: step: 1000/533, loss: 0.00022394077677745372
2023-01-24 09:15:21.128833: step: 1004/533, loss: 0.005287556443363428
2023-01-24 09:15:22.203033: step: 1008/533, loss: 0.0006249186117202044
2023-01-24 09:15:23.299312: step: 1012/533, loss: 0.011068388819694519
2023-01-24 09:15:24.397537: step: 1016/533, loss: 0.0008795336470939219
2023-01-24 09:15:25.497219: step: 1020/533, loss: 0.004379631951451302
2023-01-24 09:15:26.589991: step: 1024/533, loss: 0.0013071621069684625
2023-01-24 09:15:27.699472: step: 1028/533, loss: 0.008616293780505657
2023-01-24 09:15:28.763733: step: 1032/533, loss: 0.0005881609977222979
2023-01-24 09:15:29.881857: step: 1036/533, loss: 0.000978726428002119
2023-01-24 09:15:30.983258: step: 1040/533, loss: 0.008642845787107944
2023-01-24 09:15:32.096295: step: 1044/533, loss: 0.004118085838854313
2023-01-24 09:15:33.227779: step: 1048/533, loss: 0.004312623757869005
2023-01-24 09:15:34.331831: step: 1052/533, loss: 0.020321372896432877
2023-01-24 09:15:35.420161: step: 1056/533, loss: 0.00597147922962904
2023-01-24 09:15:36.507341: step: 1060/533, loss: 0.0028833302203565836
2023-01-24 09:15:37.584443: step: 1064/533, loss: 0.004840112291276455
2023-01-24 09:15:38.666541: step: 1068/533, loss: 0.00096668372862041
2023-01-24 09:15:39.754940: step: 1072/533, loss: 0.006684991996735334
2023-01-24 09:15:40.856864: step: 1076/533, loss: 0.004123821388930082
2023-01-24 09:15:41.952131: step: 1080/533, loss: 0.001617311267182231
2023-01-24 09:15:43.061769: step: 1084/533, loss: 0.00832895003259182
2023-01-24 09:15:44.171427: step: 1088/533, loss: 0.00035457676858641207
2023-01-24 09:15:45.260840: step: 1092/533, loss: 0.014226068742573261
2023-01-24 09:15:46.351573: step: 1096/533, loss: 0.0003300784737803042
2023-01-24 09:15:47.445672: step: 1100/533, loss: 0.0019248822936788201
2023-01-24 09:15:48.524170: step: 1104/533, loss: 0.00998083595186472
2023-01-24 09:15:49.627498: step: 1108/533, loss: 0.004030205775052309
2023-01-24 09:15:50.741500: step: 1112/533, loss: 0.01247142069041729
2023-01-24 09:15:51.844296: step: 1116/533, loss: 0.007295466493815184
2023-01-24 09:15:52.943440: step: 1120/533, loss: 0.005601938813924789
2023-01-24 09:15:54.035283: step: 1124/533, loss: 0.012579820118844509
2023-01-24 09:15:55.128845: step: 1128/533, loss: 0.003381167072802782
2023-01-24 09:15:56.220414: step: 1132/533, loss: 0.008450916968286037
2023-01-24 09:15:57.334795: step: 1136/533, loss: 0.0005160145810805261
2023-01-24 09:15:58.423144: step: 1140/533, loss: 0.0007492847507819533
2023-01-24 09:15:59.499561: step: 1144/533, loss: 0.0038683409802615643
2023-01-24 09:16:00.597790: step: 1148/533, loss: 0.025578802451491356
2023-01-24 09:16:01.711469: step: 1152/533, loss: 0.002691584639251232
2023-01-24 09:16:02.823208: step: 1156/533, loss: 0.002878822386264801
2023-01-24 09:16:03.934060: step: 1160/533, loss: 0.0035332702100276947
2023-01-24 09:16:05.003461: step: 1164/533, loss: 6.705823761876673e-05
2023-01-24 09:16:06.115485: step: 1168/533, loss: 0.0049301632679998875
2023-01-24 09:16:07.202523: step: 1172/533, loss: 0.0071345167234539986
2023-01-24 09:16:08.281674: step: 1176/533, loss: 3.0510947908624075e-05
2023-01-24 09:16:09.380621: step: 1180/533, loss: 0.008081662468612194
2023-01-24 09:16:10.486960: step: 1184/533, loss: 8.293344581034034e-05
2023-01-24 09:16:11.579580: step: 1188/533, loss: 0.009140494279563427
2023-01-24 09:16:12.666397: step: 1192/533, loss: 0.009747833013534546
2023-01-24 09:16:13.742406: step: 1196/533, loss: 0.013418515212833881
2023-01-24 09:16:14.851853: step: 1200/533, loss: 0.027077481150627136
2023-01-24 09:16:15.925173: step: 1204/533, loss: 0.007601981516927481
2023-01-24 09:16:17.017548: step: 1208/533, loss: 0.007521620951592922
2023-01-24 09:16:18.109512: step: 1212/533, loss: 0.009275157935917377
2023-01-24 09:16:19.209229: step: 1216/533, loss: 0.003975642845034599
2023-01-24 09:16:20.280766: step: 1220/533, loss: 0.002060307888314128
2023-01-24 09:16:21.351717: step: 1224/533, loss: 0.004908957984298468
2023-01-24 09:16:22.444360: step: 1228/533, loss: 0.002806080039590597
2023-01-24 09:16:23.534861: step: 1232/533, loss: 0.021672651171684265
2023-01-24 09:16:24.645183: step: 1236/533, loss: 0.005626632831990719
2023-01-24 09:16:25.741050: step: 1240/533, loss: 0.0008402874227613211
2023-01-24 09:16:26.843408: step: 1244/533, loss: 0.010043120011687279
2023-01-24 09:16:27.940763: step: 1248/533, loss: 0.011334897950291634
2023-01-24 09:16:29.019895: step: 1252/533, loss: 0.0024684572126716375
2023-01-24 09:16:30.144428: step: 1256/533, loss: 0.014636797830462456
2023-01-24 09:16:31.230970: step: 1260/533, loss: 0.003371714847162366
2023-01-24 09:16:32.342233: step: 1264/533, loss: 0.005179308354854584
2023-01-24 09:16:33.433452: step: 1268/533, loss: 0.0050382246263325214
2023-01-24 09:16:34.502064: step: 1272/533, loss: 0.00017348206893075258
2023-01-24 09:16:35.604820: step: 1276/533, loss: 0.0007109942962415516
2023-01-24 09:16:36.710075: step: 1280/533, loss: 0.016031760722398758
2023-01-24 09:16:37.796577: step: 1284/533, loss: 0.007176543120294809
2023-01-24 09:16:38.905377: step: 1288/533, loss: 0.003994397819042206
2023-01-24 09:16:40.016017: step: 1292/533, loss: 0.00419353973120451
2023-01-24 09:16:41.118761: step: 1296/533, loss: 0.0008720775367692113
2023-01-24 09:16:42.210754: step: 1300/533, loss: 9.734038030728698e-05
2023-01-24 09:16:43.296762: step: 1304/533, loss: 0.011972995474934578
2023-01-24 09:16:44.382215: step: 1308/533, loss: 0.001484379405155778
2023-01-24 09:16:45.492924: step: 1312/533, loss: 0.0036566522903740406
2023-01-24 09:16:46.586159: step: 1316/533, loss: 0.011528963223099709
2023-01-24 09:16:47.663315: step: 1320/533, loss: 0.0019494763109833002
2023-01-24 09:16:48.757810: step: 1324/533, loss: 0.0023181948345154524
2023-01-24 09:16:49.862713: step: 1328/533, loss: 0.017356323078274727
2023-01-24 09:16:50.974476: step: 1332/533, loss: 0.0021150142420083284
2023-01-24 09:16:52.066428: step: 1336/533, loss: 0.005233916454017162
2023-01-24 09:16:53.163069: step: 1340/533, loss: 0.006132038310170174
2023-01-24 09:16:54.266019: step: 1344/533, loss: 0.0043643261305987835
2023-01-24 09:16:55.352830: step: 1348/533, loss: 0.010574309155344963
2023-01-24 09:16:56.443712: step: 1352/533, loss: 0.00021273769380059093
2023-01-24 09:16:57.542134: step: 1356/533, loss: 0.006159632466733456
2023-01-24 09:16:58.642359: step: 1360/533, loss: 0.0025981205981224775
2023-01-24 09:16:59.739775: step: 1364/533, loss: 0.005347955971956253
2023-01-24 09:17:00.842464: step: 1368/533, loss: 0.015543361194431782
2023-01-24 09:17:01.929032: step: 1372/533, loss: 0.00235842471010983
2023-01-24 09:17:03.039663: step: 1376/533, loss: 0.005971644539386034
2023-01-24 09:17:04.126177: step: 1380/533, loss: 0.003023166675120592
2023-01-24 09:17:05.200637: step: 1384/533, loss: 0.010599070228636265
2023-01-24 09:17:06.268745: step: 1388/533, loss: 0.02626877836883068
2023-01-24 09:17:07.368561: step: 1392/533, loss: 0.008498293347656727
2023-01-24 09:17:08.453992: step: 1396/533, loss: 0.004714000970125198
2023-01-24 09:17:09.536265: step: 1400/533, loss: 0.0011781529756262898
2023-01-24 09:17:10.619208: step: 1404/533, loss: 0.005562079604715109
2023-01-24 09:17:11.687228: step: 1408/533, loss: 0.004478005692362785
2023-01-24 09:17:12.809950: step: 1412/533, loss: 0.007593823596835136
2023-01-24 09:17:13.902758: step: 1416/533, loss: 0.005256038624793291
2023-01-24 09:17:15.035083: step: 1420/533, loss: 0.0037465717177838087
2023-01-24 09:17:16.126931: step: 1424/533, loss: 0.010340599343180656
2023-01-24 09:17:17.254392: step: 1428/533, loss: 0.0024860487319529057
2023-01-24 09:17:18.322961: step: 1432/533, loss: 0.001973186619579792
2023-01-24 09:17:19.406475: step: 1436/533, loss: 0.009253907948732376
2023-01-24 09:17:20.516910: step: 1440/533, loss: 0.0016720121493563056
2023-01-24 09:17:21.608677: step: 1444/533, loss: 0.0007566652493551373
2023-01-24 09:17:22.700665: step: 1448/533, loss: 0.06217731535434723
2023-01-24 09:17:23.789252: step: 1452/533, loss: 0.0010038508335128427
2023-01-24 09:17:24.880377: step: 1456/533, loss: 0.0009154926519840956
2023-01-24 09:17:25.963707: step: 1460/533, loss: 0.0001055522370734252
2023-01-24 09:17:27.072963: step: 1464/533, loss: 0.004042826127260923
2023-01-24 09:17:28.177544: step: 1468/533, loss: 0.011107144877314568
2023-01-24 09:17:29.284606: step: 1472/533, loss: 0.005225350148975849
2023-01-24 09:17:30.364728: step: 1476/533, loss: 0.0020108779426664114
2023-01-24 09:17:31.464982: step: 1480/533, loss: 0.012898258864879608
2023-01-24 09:17:32.562521: step: 1484/533, loss: 0.0023187713231891394
2023-01-24 09:17:33.661583: step: 1488/533, loss: 0.0006290011806413531
2023-01-24 09:17:34.756600: step: 1492/533, loss: 0.010615375824272633
2023-01-24 09:17:35.848492: step: 1496/533, loss: 0.0010315000545233488
2023-01-24 09:17:36.947226: step: 1500/533, loss: 0.0027469953056424856
2023-01-24 09:17:38.030456: step: 1504/533, loss: 0.031639691442251205
2023-01-24 09:17:39.116385: step: 1508/533, loss: 0.0035144477151334286
2023-01-24 09:17:40.209610: step: 1512/533, loss: 0.005127620417624712
2023-01-24 09:17:41.352597: step: 1516/533, loss: 0.01077451091259718
2023-01-24 09:17:42.442150: step: 1520/533, loss: 7.03836340107955e-05
2023-01-24 09:17:43.540655: step: 1524/533, loss: 0.025423603132367134
2023-01-24 09:17:44.634873: step: 1528/533, loss: 0.013142062351107597
2023-01-24 09:17:45.729921: step: 1532/533, loss: 0.008357544429600239
2023-01-24 09:17:46.819231: step: 1536/533, loss: 0.0029497668147087097
2023-01-24 09:17:47.911403: step: 1540/533, loss: 0.0013538310304284096
2023-01-24 09:17:48.997126: step: 1544/533, loss: 0.003522058017551899
2023-01-24 09:17:50.080736: step: 1548/533, loss: 0.008023491129279137
2023-01-24 09:17:51.180226: step: 1552/533, loss: 0.02331327460706234
2023-01-24 09:17:52.254100: step: 1556/533, loss: 0.004861598368734121
2023-01-24 09:17:53.338753: step: 1560/533, loss: 0.006296186242252588
2023-01-24 09:17:54.421643: step: 1564/533, loss: 0.02641856111586094
2023-01-24 09:17:55.519888: step: 1568/533, loss: 0.003513287752866745
2023-01-24 09:17:56.629260: step: 1572/533, loss: 0.0022878029849380255
2023-01-24 09:17:57.726546: step: 1576/533, loss: 0.0005979323177598417
2023-01-24 09:17:58.811140: step: 1580/533, loss: 0.012944917194545269
2023-01-24 09:17:59.894254: step: 1584/533, loss: 0.0014025972923263907
2023-01-24 09:18:01.004216: step: 1588/533, loss: 0.005452245473861694
2023-01-24 09:18:02.101890: step: 1592/533, loss: 0.0007882829522714019
2023-01-24 09:18:03.176297: step: 1596/533, loss: 0.004802216775715351
2023-01-24 09:18:04.262457: step: 1600/533, loss: 0.0024937668349593878
2023-01-24 09:18:05.369799: step: 1604/533, loss: 0.012629855424165726
2023-01-24 09:18:06.463201: step: 1608/533, loss: 0.02552303671836853
2023-01-24 09:18:07.533176: step: 1612/533, loss: 0.0
2023-01-24 09:18:08.633387: step: 1616/533, loss: 0.03368644416332245
2023-01-24 09:18:09.710468: step: 1620/533, loss: 2.6709076337283477e-06
2023-01-24 09:18:10.813261: step: 1624/533, loss: 0.0044256942346692085
2023-01-24 09:18:11.915973: step: 1628/533, loss: 0.005778053775429726
2023-01-24 09:18:12.997889: step: 1632/533, loss: 0.00720041012391448
2023-01-24 09:18:14.100930: step: 1636/533, loss: 0.002086650812998414
2023-01-24 09:18:15.183159: step: 1640/533, loss: 0.0036802776157855988
2023-01-24 09:18:16.292294: step: 1644/533, loss: 0.0027965742629021406
2023-01-24 09:18:17.412650: step: 1648/533, loss: 0.00316993216983974
2023-01-24 09:18:18.508599: step: 1652/533, loss: 0.000600764062255621
2023-01-24 09:18:19.645691: step: 1656/533, loss: 0.04593329504132271
2023-01-24 09:18:20.739629: step: 1660/533, loss: 0.0073166158981621265
2023-01-24 09:18:21.837883: step: 1664/533, loss: 0.0007220246479846537
2023-01-24 09:18:22.954920: step: 1668/533, loss: 0.0014358111657202244
2023-01-24 09:18:24.055722: step: 1672/533, loss: 0.007990172132849693
2023-01-24 09:18:25.159448: step: 1676/533, loss: 0.005699526984244585
2023-01-24 09:18:26.259805: step: 1680/533, loss: 0.007386927958577871
2023-01-24 09:18:27.355153: step: 1684/533, loss: 0.0014043179107829928
2023-01-24 09:18:28.480300: step: 1688/533, loss: 0.005673672072589397
2023-01-24 09:18:29.578804: step: 1692/533, loss: 0.005380718037486076
2023-01-24 09:18:30.697893: step: 1696/533, loss: 0.007314375136047602
2023-01-24 09:18:31.796828: step: 1700/533, loss: 0.015426565892994404
2023-01-24 09:18:32.891656: step: 1704/533, loss: 0.013775831088423729
2023-01-24 09:18:33.981157: step: 1708/533, loss: 0.011842172592878342
2023-01-24 09:18:35.082722: step: 1712/533, loss: 0.003054550150409341
2023-01-24 09:18:36.176932: step: 1716/533, loss: 0.005187804810702801
2023-01-24 09:18:37.265805: step: 1720/533, loss: 0.004457004368305206
2023-01-24 09:18:38.353841: step: 1724/533, loss: 0.0044310675002634525
2023-01-24 09:18:39.464286: step: 1728/533, loss: 0.0025345811154693365
2023-01-24 09:18:40.568222: step: 1732/533, loss: 0.007606471423059702
2023-01-24 09:18:41.653184: step: 1736/533, loss: 0.0017797172768041492
2023-01-24 09:18:42.727113: step: 1740/533, loss: 0.022214870899915695
2023-01-24 09:18:43.804441: step: 1744/533, loss: 0.004739285446703434
2023-01-24 09:18:44.924040: step: 1748/533, loss: 0.0025547968689352274
2023-01-24 09:18:45.993819: step: 1752/533, loss: 0.0024715459439903498
2023-01-24 09:18:47.103532: step: 1756/533, loss: 0.0009939868468791246
2023-01-24 09:18:48.194591: step: 1760/533, loss: 0.001604017917998135
2023-01-24 09:18:49.293256: step: 1764/533, loss: 0.014368787407875061
2023-01-24 09:18:50.437954: step: 1768/533, loss: 0.001777826459147036
2023-01-24 09:18:51.516657: step: 1772/533, loss: 0.00044424482621252537
2023-01-24 09:18:52.599898: step: 1776/533, loss: 0.0009410561178810894
2023-01-24 09:18:53.694321: step: 1780/533, loss: 0.006222167517989874
2023-01-24 09:18:54.806889: step: 1784/533, loss: 0.041235554963350296
2023-01-24 09:18:55.886138: step: 1788/533, loss: 0.004095329903066158
2023-01-24 09:18:56.976209: step: 1792/533, loss: 0.01342339813709259
2023-01-24 09:18:58.063497: step: 1796/533, loss: 0.0025176445487886667
2023-01-24 09:18:59.147685: step: 1800/533, loss: 0.007466341368854046
2023-01-24 09:19:00.253355: step: 1804/533, loss: 0.005234529264271259
2023-01-24 09:19:01.379862: step: 1808/533, loss: 0.0053945803083479404
2023-01-24 09:19:02.479277: step: 1812/533, loss: 0.009437784552574158
2023-01-24 09:19:03.558958: step: 1816/533, loss: 0.007065090350806713
2023-01-24 09:19:04.670608: step: 1820/533, loss: 0.004551362246274948
2023-01-24 09:19:05.765477: step: 1824/533, loss: 0.001542198471724987
2023-01-24 09:19:06.861134: step: 1828/533, loss: 0.006873770151287317
2023-01-24 09:19:07.971561: step: 1832/533, loss: 0.013553147204220295
2023-01-24 09:19:09.066569: step: 1836/533, loss: 0.0014409372815862298
2023-01-24 09:19:10.183408: step: 1840/533, loss: 0.0025044374633580446
2023-01-24 09:19:11.291489: step: 1844/533, loss: 0.003000967437401414
2023-01-24 09:19:12.371816: step: 1848/533, loss: 0.001001311233267188
2023-01-24 09:19:13.452241: step: 1852/533, loss: 0.000604658795055002
2023-01-24 09:19:14.538405: step: 1856/533, loss: 0.001004775520414114
2023-01-24 09:19:15.642686: step: 1860/533, loss: 0.0009725639247335494
2023-01-24 09:19:16.728235: step: 1864/533, loss: 0.0030611499678343534
2023-01-24 09:19:17.859599: step: 1868/533, loss: 0.007213626988232136
2023-01-24 09:19:18.932585: step: 1872/533, loss: 0.003354415763169527
2023-01-24 09:19:20.042017: step: 1876/533, loss: 0.002132953144609928
2023-01-24 09:19:21.140808: step: 1880/533, loss: 0.00421088095754385
2023-01-24 09:19:22.239591: step: 1884/533, loss: 0.013657732866704464
2023-01-24 09:19:23.350244: step: 1888/533, loss: 0.005772585980594158
2023-01-24 09:19:24.456693: step: 1892/533, loss: 0.004002551082521677
2023-01-24 09:19:25.550227: step: 1896/533, loss: 0.002280946122482419
2023-01-24 09:19:26.612673: step: 1900/533, loss: 0.003860623110085726
2023-01-24 09:19:27.711447: step: 1904/533, loss: 0.004499933682382107
2023-01-24 09:19:28.794394: step: 1908/533, loss: 0.0018029565690085292
2023-01-24 09:19:29.887163: step: 1912/533, loss: 0.0004678279801737517
2023-01-24 09:19:30.963549: step: 1916/533, loss: 0.0004288742784410715
2023-01-24 09:19:32.045331: step: 1920/533, loss: 0.003016713075339794
2023-01-24 09:19:33.142026: step: 1924/533, loss: 0.0025895987637341022
2023-01-24 09:19:34.262149: step: 1928/533, loss: 0.002936949487775564
2023-01-24 09:19:35.371143: step: 1932/533, loss: 0.00452790129929781
2023-01-24 09:19:36.462481: step: 1936/533, loss: 0.0012797558447346091
2023-01-24 09:19:37.558757: step: 1940/533, loss: 0.002978884382173419
2023-01-24 09:19:38.648446: step: 1944/533, loss: 0.011260745115578175
2023-01-24 09:19:39.750488: step: 1948/533, loss: 0.0030630971305072308
2023-01-24 09:19:40.835877: step: 1952/533, loss: 0.005661534145474434
2023-01-24 09:19:41.916023: step: 1956/533, loss: 0.004134665708988905
2023-01-24 09:19:42.997726: step: 1960/533, loss: 0.004340717568993568
2023-01-24 09:19:44.097055: step: 1964/533, loss: 0.0031973393633961678
2023-01-24 09:19:45.242729: step: 1968/533, loss: 0.0069664400070905685
2023-01-24 09:19:46.323283: step: 1972/533, loss: 0.0002785075339488685
2023-01-24 09:19:47.430679: step: 1976/533, loss: 0.0012535923160612583
2023-01-24 09:19:48.519942: step: 1980/533, loss: 0.007952805608510971
2023-01-24 09:19:49.613937: step: 1984/533, loss: 0.0018560178577899933
2023-01-24 09:19:50.715106: step: 1988/533, loss: 0.007084692362695932
2023-01-24 09:19:51.812431: step: 1992/533, loss: 0.005869815591722727
2023-01-24 09:19:52.890429: step: 1996/533, loss: 0.03379692882299423
2023-01-24 09:19:53.988822: step: 2000/533, loss: 0.0009799572871997952
2023-01-24 09:19:55.071486: step: 2004/533, loss: 0.0005221671308390796
2023-01-24 09:19:56.177316: step: 2008/533, loss: 0.0002102218713844195
2023-01-24 09:19:57.308079: step: 2012/533, loss: 0.018826931715011597
2023-01-24 09:19:58.401322: step: 2016/533, loss: 0.006814286112785339
2023-01-24 09:19:59.508869: step: 2020/533, loss: 0.0037472564727067947
2023-01-24 09:20:00.610999: step: 2024/533, loss: 0.00011487873416626826
2023-01-24 09:20:01.721825: step: 2028/533, loss: 0.0014433760661631823
2023-01-24 09:20:02.820898: step: 2032/533, loss: 0.0021628933027386665
2023-01-24 09:20:03.915781: step: 2036/533, loss: 0.004525352269411087
2023-01-24 09:20:05.066201: step: 2040/533, loss: 0.036670707166194916
2023-01-24 09:20:06.163364: step: 2044/533, loss: 0.00017026283603627235
2023-01-24 09:20:07.243314: step: 2048/533, loss: 0.0009782097768038511
2023-01-24 09:20:08.333957: step: 2052/533, loss: 0.003879781812429428
2023-01-24 09:20:09.431042: step: 2056/533, loss: 0.0046060518361628056
2023-01-24 09:20:10.527923: step: 2060/533, loss: 0.0029822876676917076
2023-01-24 09:20:11.611130: step: 2064/533, loss: 0.00431935116648674
2023-01-24 09:20:12.717342: step: 2068/533, loss: 0.0007618810050189495
2023-01-24 09:20:13.808381: step: 2072/533, loss: 0.006606304086744785
2023-01-24 09:20:14.900429: step: 2076/533, loss: 0.001267096260562539
2023-01-24 09:20:16.013864: step: 2080/533, loss: 0.00046347794705070555
2023-01-24 09:20:17.124296: step: 2084/533, loss: 0.003910245839506388
2023-01-24 09:20:18.208253: step: 2088/533, loss: 0.0018862136639654636
2023-01-24 09:20:19.279194: step: 2092/533, loss: 0.007703021168708801
2023-01-24 09:20:20.378113: step: 2096/533, loss: 0.0021212627179920673
2023-01-24 09:20:21.493541: step: 2100/533, loss: 0.005067327991127968
2023-01-24 09:20:22.577735: step: 2104/533, loss: 0.01243984792381525
2023-01-24 09:20:23.675188: step: 2108/533, loss: 0.0016194643685594201
2023-01-24 09:20:24.788874: step: 2112/533, loss: 0.034756872802972794
2023-01-24 09:20:25.888251: step: 2116/533, loss: 0.004770620726048946
2023-01-24 09:20:26.981835: step: 2120/533, loss: 0.0060800351202487946
2023-01-24 09:20:28.080898: step: 2124/533, loss: 0.01017078198492527
2023-01-24 09:20:29.189272: step: 2128/533, loss: 0.0001416133891325444
2023-01-24 09:20:30.303086: step: 2132/533, loss: 0.003218707861378789
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3821728801169591, 'r': 0.33068469323213157, 'f1': 0.3545693455408613}, 'combined': 0.2612616230301083, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3976391935184612, 'r': 0.3586399649233814, 'f1': 0.37713403793763056}, 'combined': 0.2514226919584203, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35811610473603117, 'r': 0.3207415587009615, 'f1': 0.3384000028736871}, 'combined': 0.24934737053850628, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38952416187074584, 'r': 0.3086229897898986, 'f1': 0.34438616886426454}, 'combined': 0.22959077924284296, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34334064508156203, 'r': 0.3101141310414109, 'f1': 0.3258826461791097}, 'combined': 0.240124055079344, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38406606374733326, 'r': 0.34529016308053523, 'f1': 0.3636473616240573}, 'combined': 0.24243157441603816, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.7, 'r': 0.45652173913043476, 'f1': 0.5526315789473684}, 'combined': 0.36842105263157887, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 09:22:49.361605: step: 4/533, loss: 0.0006501296884380281
2023-01-24 09:22:50.425879: step: 8/533, loss: 0.002190602943301201
2023-01-24 09:22:51.501231: step: 12/533, loss: 0.004302293062210083
2023-01-24 09:22:52.599883: step: 16/533, loss: 0.0004653643409255892
2023-01-24 09:22:53.686124: step: 20/533, loss: 0.014345088042318821
2023-01-24 09:22:54.772801: step: 24/533, loss: 0.0011216728016734123
2023-01-24 09:22:55.883716: step: 28/533, loss: 0.0018318864749744534
2023-01-24 09:22:56.949975: step: 32/533, loss: 0.007939928211271763
2023-01-24 09:22:58.062251: step: 36/533, loss: 0.011236152611672878
2023-01-24 09:22:59.137727: step: 40/533, loss: 0.0023519028909504414
2023-01-24 09:23:00.237442: step: 44/533, loss: 0.002508342731744051
2023-01-24 09:23:01.348425: step: 48/533, loss: 0.0014312934363260865
2023-01-24 09:23:02.437118: step: 52/533, loss: 0.00020912016043439507
2023-01-24 09:23:03.537124: step: 56/533, loss: 0.0008082762942649424
2023-01-24 09:23:04.655542: step: 60/533, loss: 0.0015428223414346576
2023-01-24 09:23:05.732333: step: 64/533, loss: 0.004537738859653473
2023-01-24 09:23:06.814387: step: 68/533, loss: 0.00030275044264271855
2023-01-24 09:23:07.916214: step: 72/533, loss: 0.0031970907002687454
2023-01-24 09:23:08.996903: step: 76/533, loss: 0.00905806478112936
2023-01-24 09:23:10.115653: step: 80/533, loss: 0.0012434605741873384
2023-01-24 09:23:11.215414: step: 84/533, loss: 0.004967758897691965
2023-01-24 09:23:12.296507: step: 88/533, loss: 0.010319028049707413
2023-01-24 09:23:13.420381: step: 92/533, loss: 0.0055261412635445595
2023-01-24 09:23:14.541977: step: 96/533, loss: 0.004936480429023504
2023-01-24 09:23:15.625742: step: 100/533, loss: 0.0013388030929490924
2023-01-24 09:23:16.717930: step: 104/533, loss: 0.0029529740568250418
2023-01-24 09:23:17.824492: step: 108/533, loss: 0.003228808520361781
2023-01-24 09:23:18.922784: step: 112/533, loss: 0.0020662066526710987
2023-01-24 09:23:20.016005: step: 116/533, loss: 4.312029341235757e-05
2023-01-24 09:23:21.117995: step: 120/533, loss: 0.004829925950616598
2023-01-24 09:23:22.200891: step: 124/533, loss: 0.002030835719779134
2023-01-24 09:23:23.294480: step: 128/533, loss: 0.00015952950343489647
2023-01-24 09:23:24.416336: step: 132/533, loss: 0.0024107845965772867
2023-01-24 09:23:25.516601: step: 136/533, loss: 0.0005700646433979273
2023-01-24 09:23:26.600990: step: 140/533, loss: 0.010682135820388794
2023-01-24 09:23:27.679696: step: 144/533, loss: 0.005115222185850143
2023-01-24 09:23:28.778708: step: 148/533, loss: 0.00872737169265747
2023-01-24 09:23:29.863300: step: 152/533, loss: 0.005015823990106583
2023-01-24 09:23:30.963825: step: 156/533, loss: 0.006994422525167465
2023-01-24 09:23:32.040079: step: 160/533, loss: 0.0020481711253523827
2023-01-24 09:23:33.130012: step: 164/533, loss: 6.594126170966774e-05
2023-01-24 09:23:34.211243: step: 168/533, loss: 0.0100933276116848
2023-01-24 09:23:35.309973: step: 172/533, loss: 0.002921723062172532
2023-01-24 09:23:36.424121: step: 176/533, loss: 0.006975309923291206
2023-01-24 09:23:37.512723: step: 180/533, loss: 0.006142225582152605
2023-01-24 09:23:38.594094: step: 184/533, loss: 0.00019831507233902812
2023-01-24 09:23:39.691423: step: 188/533, loss: 0.004497775807976723
2023-01-24 09:23:40.785097: step: 192/533, loss: 0.0005806366680189967
2023-01-24 09:23:41.880799: step: 196/533, loss: 0.004088614601641893
2023-01-24 09:23:42.976207: step: 200/533, loss: 0.0030789144802838564
2023-01-24 09:23:44.056725: step: 204/533, loss: 0.004177447408437729
2023-01-24 09:23:45.157734: step: 208/533, loss: 0.007904031313955784
2023-01-24 09:23:46.242203: step: 212/533, loss: 0.0008981654536910355
2023-01-24 09:23:47.336995: step: 216/533, loss: 0.0003578485338948667
2023-01-24 09:23:48.443121: step: 220/533, loss: 0.011737420223653316
2023-01-24 09:23:49.541404: step: 224/533, loss: 0.0020441189408302307
2023-01-24 09:23:50.652269: step: 228/533, loss: 0.002955114236101508
2023-01-24 09:23:51.758574: step: 232/533, loss: 0.004687462467700243
2023-01-24 09:23:52.853764: step: 236/533, loss: 0.0006156915333122015
2023-01-24 09:23:53.974508: step: 240/533, loss: 0.001247961656190455
2023-01-24 09:23:55.073622: step: 244/533, loss: 0.00296454643830657
2023-01-24 09:23:56.182715: step: 248/533, loss: 0.007051004562526941
2023-01-24 09:23:57.274715: step: 252/533, loss: 0.0017897036159411073
2023-01-24 09:23:58.363339: step: 256/533, loss: 0.00014883477706462145
2023-01-24 09:23:59.466016: step: 260/533, loss: 0.0010962714441120625
2023-01-24 09:24:00.580832: step: 264/533, loss: 2.6576759410090744e-05
2023-01-24 09:24:01.672192: step: 268/533, loss: 0.00565024558454752
2023-01-24 09:24:02.772953: step: 272/533, loss: 0.0029851016588509083
2023-01-24 09:24:03.852321: step: 276/533, loss: 0.005191290285438299
2023-01-24 09:24:04.944095: step: 280/533, loss: 7.753412501187995e-05
2023-01-24 09:24:06.027274: step: 284/533, loss: 0.0010333094978705049
2023-01-24 09:24:07.120095: step: 288/533, loss: 9.881428923108615e-06
2023-01-24 09:24:08.241771: step: 292/533, loss: 0.0011568479239940643
2023-01-24 09:24:09.331678: step: 296/533, loss: 0.0009962848853319883
2023-01-24 09:24:10.421281: step: 300/533, loss: 0.0005619408329948783
2023-01-24 09:24:11.528086: step: 304/533, loss: 0.0035652536898851395
2023-01-24 09:24:12.647002: step: 308/533, loss: 0.00378275103867054
2023-01-24 09:24:13.744528: step: 312/533, loss: 0.0031830084044486284
2023-01-24 09:24:14.825061: step: 316/533, loss: 0.0002546948380768299
2023-01-24 09:24:15.932738: step: 320/533, loss: 0.005320979747921228
2023-01-24 09:24:17.036564: step: 324/533, loss: 0.003876382252201438
2023-01-24 09:24:18.120746: step: 328/533, loss: 0.012107914313673973
2023-01-24 09:24:19.214797: step: 332/533, loss: 0.007033552974462509
2023-01-24 09:24:20.324650: step: 336/533, loss: 0.0046746619045734406
2023-01-24 09:24:21.407377: step: 340/533, loss: 0.012710971757769585
2023-01-24 09:24:22.475097: step: 344/533, loss: 0.002229569712653756
2023-01-24 09:24:23.594134: step: 348/533, loss: 0.0006239691865630448
2023-01-24 09:24:24.705625: step: 352/533, loss: 0.0041011846624314785
2023-01-24 09:24:25.790258: step: 356/533, loss: 0.0010463137878105044
2023-01-24 09:24:26.901502: step: 360/533, loss: 0.002632411662489176
2023-01-24 09:24:27.979343: step: 364/533, loss: 0.0005020548705942929
2023-01-24 09:24:29.091525: step: 368/533, loss: 0.001526649808511138
2023-01-24 09:24:30.212037: step: 372/533, loss: 0.0021908425260335207
2023-01-24 09:24:31.301775: step: 376/533, loss: 0.001668452750891447
2023-01-24 09:24:32.388769: step: 380/533, loss: 0.007411563768982887
2023-01-24 09:24:33.481930: step: 384/533, loss: 0.003729166928678751
2023-01-24 09:24:34.567211: step: 388/533, loss: 0.0015194836305454373
2023-01-24 09:24:35.659030: step: 392/533, loss: 0.015497555024921894
2023-01-24 09:24:36.781628: step: 396/533, loss: 0.003238741308450699
2023-01-24 09:24:37.860431: step: 400/533, loss: 0.0013868740061298013
2023-01-24 09:24:38.953246: step: 404/533, loss: 0.001599499606527388
2023-01-24 09:24:40.071321: step: 408/533, loss: 0.007825602777302265
2023-01-24 09:24:41.144879: step: 412/533, loss: 0.0009360603289678693
2023-01-24 09:24:42.215354: step: 416/533, loss: 0.00021951772214379162
2023-01-24 09:24:43.330818: step: 420/533, loss: 0.010557690635323524
2023-01-24 09:24:44.424070: step: 424/533, loss: 0.002368317684158683
2023-01-24 09:24:45.506297: step: 428/533, loss: 0.0012696490157395601
2023-01-24 09:24:46.609095: step: 432/533, loss: 0.00219950033351779
2023-01-24 09:24:47.694651: step: 436/533, loss: 0.0049997130408883095
2023-01-24 09:24:48.777052: step: 440/533, loss: 0.006914209574460983
2023-01-24 09:24:49.872394: step: 444/533, loss: 0.004115957301110029
2023-01-24 09:24:50.945967: step: 448/533, loss: 0.0027506703045219183
2023-01-24 09:24:52.019938: step: 452/533, loss: 2.2790513867221307e-06
2023-01-24 09:24:53.141714: step: 456/533, loss: 0.006777388975024223
2023-01-24 09:24:54.259916: step: 460/533, loss: 0.0014950307086110115
2023-01-24 09:24:55.354393: step: 464/533, loss: 0.007269009482115507
2023-01-24 09:24:56.444057: step: 468/533, loss: 0.00042447849409654737
2023-01-24 09:24:57.536621: step: 472/533, loss: 0.006560338661074638
2023-01-24 09:24:58.628309: step: 476/533, loss: 5.6481796491425484e-05
2023-01-24 09:24:59.729548: step: 480/533, loss: 0.009608210995793343
2023-01-24 09:25:00.813303: step: 484/533, loss: 0.0015550085809081793
2023-01-24 09:25:01.925685: step: 488/533, loss: 0.005190815310925245
2023-01-24 09:25:03.020399: step: 492/533, loss: 0.012691410258412361
2023-01-24 09:25:04.135933: step: 496/533, loss: 0.00818686280399561
2023-01-24 09:25:05.252097: step: 500/533, loss: 0.0012181230122223496
2023-01-24 09:25:06.347367: step: 504/533, loss: 0.005986603442579508
2023-01-24 09:25:07.452050: step: 508/533, loss: 0.002621543128043413
2023-01-24 09:25:08.551370: step: 512/533, loss: 0.0013965716352686286
2023-01-24 09:25:09.652521: step: 516/533, loss: 0.010302654467523098
2023-01-24 09:25:10.756275: step: 520/533, loss: 0.0004918037448078394
2023-01-24 09:25:11.832168: step: 524/533, loss: 0.002170099411159754
2023-01-24 09:25:12.935875: step: 528/533, loss: 0.007867131382226944
2023-01-24 09:25:14.042855: step: 532/533, loss: 0.017289938405156136
2023-01-24 09:25:15.171377: step: 536/533, loss: 0.006946890149265528
2023-01-24 09:25:16.261812: step: 540/533, loss: 0.0034974473528563976
2023-01-24 09:25:17.361545: step: 544/533, loss: 0.002057790756225586
2023-01-24 09:25:18.454607: step: 548/533, loss: 0.00261012464761734
2023-01-24 09:25:19.558915: step: 552/533, loss: 0.004431142937391996
2023-01-24 09:25:20.644300: step: 556/533, loss: 0.004948324523866177
2023-01-24 09:25:21.744178: step: 560/533, loss: 0.0027544803451746702
2023-01-24 09:25:22.843495: step: 564/533, loss: 0.000520062749274075
2023-01-24 09:25:23.942777: step: 568/533, loss: 0.002406143583357334
2023-01-24 09:25:25.028379: step: 572/533, loss: 0.007917222566902637
2023-01-24 09:25:26.125750: step: 576/533, loss: 0.0015240604989230633
2023-01-24 09:25:27.215947: step: 580/533, loss: 0.003050352679565549
2023-01-24 09:25:28.296108: step: 584/533, loss: 0.003522532293573022
2023-01-24 09:25:29.380491: step: 588/533, loss: 0.007864906452596188
2023-01-24 09:25:30.452085: step: 592/533, loss: 0.0018257355550304055
2023-01-24 09:25:31.547623: step: 596/533, loss: 0.014875518158078194
2023-01-24 09:25:32.637365: step: 600/533, loss: 0.003860292723402381
2023-01-24 09:25:33.713489: step: 604/533, loss: 0.004587505478411913
2023-01-24 09:25:34.808143: step: 608/533, loss: 0.0005013970658183098
2023-01-24 09:25:35.893981: step: 612/533, loss: 0.0006412919610738754
2023-01-24 09:25:36.991086: step: 616/533, loss: 0.006759547628462315
2023-01-24 09:25:38.071346: step: 620/533, loss: 0.0056808507069945335
2023-01-24 09:25:39.183990: step: 624/533, loss: 7.459612970706075e-05
2023-01-24 09:25:40.314935: step: 628/533, loss: 0.00970338936895132
2023-01-24 09:25:41.415953: step: 632/533, loss: 0.006960647646337748
2023-01-24 09:25:42.502371: step: 636/533, loss: 0.0014457583893090487
2023-01-24 09:25:43.603991: step: 640/533, loss: 0.0019142662640661001
2023-01-24 09:25:44.680141: step: 644/533, loss: 0.0010514409514144063
2023-01-24 09:25:45.782602: step: 648/533, loss: 0.006489334627985954
2023-01-24 09:25:46.883061: step: 652/533, loss: 0.003641535295173526
2023-01-24 09:25:48.001602: step: 656/533, loss: 0.003535536350682378
2023-01-24 09:25:49.119781: step: 660/533, loss: 9.602468344382942e-05
2023-01-24 09:25:50.205144: step: 664/533, loss: 0.0
2023-01-24 09:25:51.324190: step: 668/533, loss: 0.008729162625968456
2023-01-24 09:25:52.433124: step: 672/533, loss: 0.0004638537357095629
2023-01-24 09:25:53.546649: step: 676/533, loss: 0.005191960837692022
2023-01-24 09:25:54.636580: step: 680/533, loss: 0.0045438180677592754
2023-01-24 09:25:55.748633: step: 684/533, loss: 0.0025226487778127193
2023-01-24 09:25:56.844790: step: 688/533, loss: 0.00355205568484962
2023-01-24 09:25:57.934502: step: 692/533, loss: 0.0022972188889980316
2023-01-24 09:25:59.032484: step: 696/533, loss: 0.0017816554754972458
2023-01-24 09:26:00.124567: step: 700/533, loss: 0.008271086029708385
2023-01-24 09:26:01.227817: step: 704/533, loss: 0.004054742399603128
2023-01-24 09:26:02.309790: step: 708/533, loss: 0.00042310968274250627
2023-01-24 09:26:03.439803: step: 712/533, loss: 0.0055381846614181995
2023-01-24 09:26:04.525814: step: 716/533, loss: 0.001348143327049911
2023-01-24 09:26:05.617753: step: 720/533, loss: 0.002024108311161399
2023-01-24 09:26:06.711916: step: 724/533, loss: 0.007094672415405512
2023-01-24 09:26:07.800458: step: 728/533, loss: 0.00422718795016408
2023-01-24 09:26:08.892350: step: 732/533, loss: 0.0015843508299440145
2023-01-24 09:26:09.989084: step: 736/533, loss: 0.0006010166252963245
2023-01-24 09:26:11.079582: step: 740/533, loss: 0.0023305134382098913
2023-01-24 09:26:12.170449: step: 744/533, loss: 0.051366377621889114
2023-01-24 09:26:13.287973: step: 748/533, loss: 0.000556276470888406
2023-01-24 09:26:14.407898: step: 752/533, loss: 0.0009954578708857298
2023-01-24 09:26:15.497149: step: 756/533, loss: 0.0029166049789637327
2023-01-24 09:26:16.592891: step: 760/533, loss: 0.007090398110449314
2023-01-24 09:26:17.679473: step: 764/533, loss: 0.0002295580052305013
2023-01-24 09:26:18.803801: step: 768/533, loss: 0.012037604115903378
2023-01-24 09:26:19.940163: step: 772/533, loss: 0.004565393086522818
2023-01-24 09:26:21.038464: step: 776/533, loss: 0.005963960662484169
2023-01-24 09:26:22.107664: step: 780/533, loss: 0.00016551643784623593
2023-01-24 09:26:23.205151: step: 784/533, loss: 0.02152642048895359
2023-01-24 09:26:24.311128: step: 788/533, loss: 0.001569701242260635
2023-01-24 09:26:25.413381: step: 792/533, loss: 0.00455344095826149
2023-01-24 09:26:26.503196: step: 796/533, loss: 0.0005568175693042576
2023-01-24 09:26:27.599772: step: 800/533, loss: 0.0008045812137424946
2023-01-24 09:26:28.676160: step: 804/533, loss: 0.0007057508919388056
2023-01-24 09:26:29.747831: step: 808/533, loss: 0.0013974476605653763
2023-01-24 09:26:30.853563: step: 812/533, loss: 0.001139280153438449
2023-01-24 09:26:31.948924: step: 816/533, loss: 0.00016154287732206285
2023-01-24 09:26:33.049233: step: 820/533, loss: 0.0009778233943507075
2023-01-24 09:26:34.158371: step: 824/533, loss: 0.0017104103462770581
2023-01-24 09:26:35.245351: step: 828/533, loss: 0.0008396184421144426
2023-01-24 09:26:36.338523: step: 832/533, loss: 0.0011292670387774706
2023-01-24 09:26:37.435441: step: 836/533, loss: 0.002448735060170293
2023-01-24 09:26:38.555577: step: 840/533, loss: 0.002805169904604554
2023-01-24 09:26:39.666619: step: 844/533, loss: 0.003904076525941491
2023-01-24 09:26:40.757260: step: 848/533, loss: 0.006930394098162651
2023-01-24 09:26:41.851753: step: 852/533, loss: 0.001607742509804666
2023-01-24 09:26:42.961695: step: 856/533, loss: 0.0020783268846571445
2023-01-24 09:26:44.082996: step: 860/533, loss: 0.005400207359343767
2023-01-24 09:26:45.174337: step: 864/533, loss: 0.006741140969097614
2023-01-24 09:26:46.275979: step: 868/533, loss: 0.004932500422000885
2023-01-24 09:26:47.366424: step: 872/533, loss: 0.028750095516443253
2023-01-24 09:26:48.467429: step: 876/533, loss: 0.002190527506172657
2023-01-24 09:26:49.574674: step: 880/533, loss: 0.01576266996562481
2023-01-24 09:26:50.688442: step: 884/533, loss: 0.008612928912043571
2023-01-24 09:26:51.756019: step: 888/533, loss: 0.00036077946424484253
2023-01-24 09:26:52.842656: step: 892/533, loss: 0.0018399718683212996
2023-01-24 09:26:53.926846: step: 896/533, loss: 0.0016533154994249344
2023-01-24 09:26:55.020729: step: 900/533, loss: 3.363002906553447e-05
2023-01-24 09:26:56.154345: step: 904/533, loss: 0.00570429302752018
2023-01-24 09:26:57.247840: step: 908/533, loss: 0.0016914685256779194
2023-01-24 09:26:58.367432: step: 912/533, loss: 0.001138660591095686
2023-01-24 09:26:59.456345: step: 916/533, loss: 0.00012700003571808338
2023-01-24 09:27:00.564601: step: 920/533, loss: 0.003015296533703804
2023-01-24 09:27:01.667611: step: 924/533, loss: 0.009538363665342331
2023-01-24 09:27:02.766523: step: 928/533, loss: 0.0034277543891221285
2023-01-24 09:27:03.856317: step: 932/533, loss: 0.02165544033050537
2023-01-24 09:27:04.944294: step: 936/533, loss: 0.0022418485023081303
2023-01-24 09:27:06.041252: step: 940/533, loss: 0.0052300915122032166
2023-01-24 09:27:07.119859: step: 944/533, loss: 0.004846231080591679
2023-01-24 09:27:08.204010: step: 948/533, loss: 0.0006571479607373476
2023-01-24 09:27:09.304018: step: 952/533, loss: 0.00603738147765398
2023-01-24 09:27:10.367801: step: 956/533, loss: 0.0012525409692898393
2023-01-24 09:27:11.461392: step: 960/533, loss: 0.013041223399341106
2023-01-24 09:27:12.551215: step: 964/533, loss: 0.010400550439953804
2023-01-24 09:27:13.668456: step: 968/533, loss: 0.004416936077177525
2023-01-24 09:27:14.766880: step: 972/533, loss: 0.016265306621789932
2023-01-24 09:27:15.888222: step: 976/533, loss: 0.0040619284845888615
2023-01-24 09:27:16.993841: step: 980/533, loss: 0.009430475533008575
2023-01-24 09:27:18.085703: step: 984/533, loss: 0.007596489042043686
2023-01-24 09:27:19.187271: step: 988/533, loss: 0.002648328198119998
2023-01-24 09:27:20.312486: step: 992/533, loss: 0.01574014313519001
2023-01-24 09:27:21.400136: step: 996/533, loss: 0.0037416755221784115
2023-01-24 09:27:22.487662: step: 1000/533, loss: 0.0029143330175429583
2023-01-24 09:27:23.582635: step: 1004/533, loss: 0.000983239384368062
2023-01-24 09:27:24.666430: step: 1008/533, loss: 8.854625775711611e-05
2023-01-24 09:27:25.758080: step: 1012/533, loss: 8.430860907537863e-05
2023-01-24 09:27:26.874443: step: 1016/533, loss: 0.013761716894805431
2023-01-24 09:27:27.974860: step: 1020/533, loss: 0.004193814937025309
2023-01-24 09:27:29.083892: step: 1024/533, loss: 0.006760057061910629
2023-01-24 09:27:30.176070: step: 1028/533, loss: 0.0034508509561419487
2023-01-24 09:27:31.256571: step: 1032/533, loss: 0.038306478410959244
2023-01-24 09:27:32.329483: step: 1036/533, loss: 9.217961633112282e-05
2023-01-24 09:27:33.441316: step: 1040/533, loss: 0.021758737042546272
2023-01-24 09:27:34.545573: step: 1044/533, loss: 0.004345691297203302
2023-01-24 09:27:35.631047: step: 1048/533, loss: 0.0019146119011566043
2023-01-24 09:27:36.732177: step: 1052/533, loss: 0.006257615052163601
2023-01-24 09:27:37.833186: step: 1056/533, loss: 0.0015231543220579624
2023-01-24 09:27:38.932047: step: 1060/533, loss: 0.0010309253120794892
2023-01-24 09:27:40.035195: step: 1064/533, loss: 0.0048611219972372055
2023-01-24 09:27:41.126034: step: 1068/533, loss: 0.004094008821994066
2023-01-24 09:27:42.246371: step: 1072/533, loss: 0.011448785662651062
2023-01-24 09:27:43.314918: step: 1076/533, loss: 0.02828272059559822
2023-01-24 09:27:44.400134: step: 1080/533, loss: 0.010482283309102058
2023-01-24 09:27:45.467836: step: 1084/533, loss: 0.002233669627457857
2023-01-24 09:27:46.576258: step: 1088/533, loss: 0.0003326405421830714
2023-01-24 09:27:47.646600: step: 1092/533, loss: 0.0
2023-01-24 09:27:48.742163: step: 1096/533, loss: 0.0007521243533119559
2023-01-24 09:27:49.827715: step: 1100/533, loss: 0.007818377576768398
2023-01-24 09:27:50.960420: step: 1104/533, loss: 0.006646736059337854
2023-01-24 09:27:52.057397: step: 1108/533, loss: 0.0025155728217214346
2023-01-24 09:27:53.144582: step: 1112/533, loss: 0.0007667778991162777
2023-01-24 09:27:54.257009: step: 1116/533, loss: 0.007607198320329189
2023-01-24 09:27:55.355749: step: 1120/533, loss: 0.001413090736605227
2023-01-24 09:27:56.461138: step: 1124/533, loss: 0.004425590857863426
2023-01-24 09:27:57.554062: step: 1128/533, loss: 0.024587508291006088
2023-01-24 09:27:58.639621: step: 1132/533, loss: 0.0005647339858114719
2023-01-24 09:27:59.721410: step: 1136/533, loss: 0.00023231144587043673
2023-01-24 09:28:00.823492: step: 1140/533, loss: 0.001312870648689568
2023-01-24 09:28:01.910566: step: 1144/533, loss: 0.002822637092322111
2023-01-24 09:28:03.045258: step: 1148/533, loss: 0.006910782773047686
2023-01-24 09:28:04.144388: step: 1152/533, loss: 0.032357800751924515
2023-01-24 09:28:05.249547: step: 1156/533, loss: 0.008506949059665203
2023-01-24 09:28:06.329083: step: 1160/533, loss: 0.005975577048957348
2023-01-24 09:28:07.448993: step: 1164/533, loss: 0.0040647489950060844
2023-01-24 09:28:08.537828: step: 1168/533, loss: 9.351650078315288e-05
2023-01-24 09:28:09.615595: step: 1172/533, loss: 2.4129827579599805e-05
2023-01-24 09:28:10.705261: step: 1176/533, loss: 0.0029558539390563965
2023-01-24 09:28:11.832558: step: 1180/533, loss: 0.0033301329240202904
2023-01-24 09:28:12.930029: step: 1184/533, loss: 0.00240930262953043
2023-01-24 09:28:14.048764: step: 1188/533, loss: 0.002074610674753785
2023-01-24 09:28:15.152855: step: 1192/533, loss: 0.00913869310170412
2023-01-24 09:28:16.268440: step: 1196/533, loss: 0.003307648468762636
2023-01-24 09:28:17.364868: step: 1200/533, loss: 0.0020472630858421326
2023-01-24 09:28:18.484669: step: 1204/533, loss: 0.02072952501475811
2023-01-24 09:28:19.588312: step: 1208/533, loss: 0.007125630974769592
2023-01-24 09:28:20.711567: step: 1212/533, loss: 0.006462289951741695
2023-01-24 09:28:21.785844: step: 1216/533, loss: 0.0009338983800262213
2023-01-24 09:28:22.881721: step: 1220/533, loss: 0.009741331450641155
2023-01-24 09:28:23.964799: step: 1224/533, loss: 0.0018659615889191628
2023-01-24 09:28:25.057672: step: 1228/533, loss: 0.009069742634892464
2023-01-24 09:28:26.212738: step: 1232/533, loss: 0.0040040817111730576
2023-01-24 09:28:27.303640: step: 1236/533, loss: 0.0038919912185519934
2023-01-24 09:28:28.391506: step: 1240/533, loss: 0.0008264913922175765
2023-01-24 09:28:29.479044: step: 1244/533, loss: 0.0011542803840711713
2023-01-24 09:28:30.574456: step: 1248/533, loss: 0.0010688349138945341
2023-01-24 09:28:31.654677: step: 1252/533, loss: 0.006268318276852369
2023-01-24 09:28:32.748324: step: 1256/533, loss: 0.00633086496964097
2023-01-24 09:28:33.861735: step: 1260/533, loss: 0.010848697274923325
2023-01-24 09:28:34.938335: step: 1264/533, loss: 0.011368331499397755
2023-01-24 09:28:36.021174: step: 1268/533, loss: 0.0007532137678936124
2023-01-24 09:28:37.109421: step: 1272/533, loss: 0.004735951311886311
2023-01-24 09:28:38.194405: step: 1276/533, loss: 0.0023842505179345608
2023-01-24 09:28:39.291913: step: 1280/533, loss: 0.00039504875894635916
2023-01-24 09:28:40.373062: step: 1284/533, loss: 0.00026684283511713147
2023-01-24 09:28:41.444410: step: 1288/533, loss: 0.02031594142317772
2023-01-24 09:28:42.562616: step: 1292/533, loss: 0.00393396383151412
2023-01-24 09:28:43.629033: step: 1296/533, loss: 0.00172455795109272
2023-01-24 09:28:44.722198: step: 1300/533, loss: 0.007793080527335405
2023-01-24 09:28:45.817418: step: 1304/533, loss: 0.000899472797755152
2023-01-24 09:28:46.917686: step: 1308/533, loss: 0.006432081572711468
2023-01-24 09:28:48.015412: step: 1312/533, loss: 0.0018834318034350872
2023-01-24 09:28:49.121542: step: 1316/533, loss: 0.0035186363384127617
2023-01-24 09:28:50.217651: step: 1320/533, loss: 0.003377563552930951
2023-01-24 09:28:51.329465: step: 1324/533, loss: 0.005759339313954115
2023-01-24 09:28:52.436227: step: 1328/533, loss: 0.003935147542506456
2023-01-24 09:28:53.526504: step: 1332/533, loss: 5.691684054909274e-05
2023-01-24 09:28:54.631496: step: 1336/533, loss: 0.001335231470875442
2023-01-24 09:28:55.721545: step: 1340/533, loss: 0.013812964782118797
2023-01-24 09:28:56.825166: step: 1344/533, loss: 0.0002194885746575892
2023-01-24 09:28:57.895175: step: 1348/533, loss: 0.015113897621631622
2023-01-24 09:28:58.993000: step: 1352/533, loss: 0.007370117586106062
2023-01-24 09:29:00.092630: step: 1356/533, loss: 0.0036639985628426075
2023-01-24 09:29:01.209750: step: 1360/533, loss: 0.010255895555019379
2023-01-24 09:29:02.314006: step: 1364/533, loss: 0.0061612362042069435
2023-01-24 09:29:03.416628: step: 1368/533, loss: 0.0031834812834858894
2023-01-24 09:29:04.533437: step: 1372/533, loss: 0.0047301664017140865
2023-01-24 09:29:05.629886: step: 1376/533, loss: 0.005385466385632753
2023-01-24 09:29:06.724966: step: 1380/533, loss: 0.0011027802247554064
2023-01-24 09:29:07.821546: step: 1384/533, loss: 0.0026133449282497168
2023-01-24 09:29:08.932108: step: 1388/533, loss: 7.57255038479343e-05
2023-01-24 09:29:10.015743: step: 1392/533, loss: 0.002687153872102499
2023-01-24 09:29:11.110207: step: 1396/533, loss: 0.0008950177580118179
2023-01-24 09:29:12.222099: step: 1400/533, loss: 0.01544934418052435
2023-01-24 09:29:13.309069: step: 1404/533, loss: 0.0014742488274350762
2023-01-24 09:29:14.390354: step: 1408/533, loss: 0.0003378414548933506
2023-01-24 09:29:15.482667: step: 1412/533, loss: 0.0054564871825277805
2023-01-24 09:29:16.582197: step: 1416/533, loss: 0.003070283681154251
2023-01-24 09:29:17.669860: step: 1420/533, loss: 0.005933952517807484
2023-01-24 09:29:18.759604: step: 1424/533, loss: 0.0042821126990020275
2023-01-24 09:29:19.855188: step: 1428/533, loss: 0.004154504276812077
2023-01-24 09:29:20.958579: step: 1432/533, loss: 0.005687218625098467
2023-01-24 09:29:22.048368: step: 1436/533, loss: 0.002307645045220852
2023-01-24 09:29:23.159592: step: 1440/533, loss: 0.0021145811770111322
2023-01-24 09:29:24.252307: step: 1444/533, loss: 0.0020099738612771034
2023-01-24 09:29:25.344276: step: 1448/533, loss: 0.0019690573681145906
2023-01-24 09:29:26.456281: step: 1452/533, loss: 0.004985225386917591
2023-01-24 09:29:27.550429: step: 1456/533, loss: 0.006504940800368786
2023-01-24 09:29:28.650484: step: 1460/533, loss: 0.004415595903992653
2023-01-24 09:29:29.751068: step: 1464/533, loss: 0.005096379667520523
2023-01-24 09:29:30.835531: step: 1468/533, loss: 0.01703072339296341
2023-01-24 09:29:31.951434: step: 1472/533, loss: 0.003552381880581379
2023-01-24 09:29:33.054733: step: 1476/533, loss: 0.011117136105895042
2023-01-24 09:29:34.162897: step: 1480/533, loss: 0.004073269199579954
2023-01-24 09:29:35.246912: step: 1484/533, loss: 0.006368438713252544
2023-01-24 09:29:36.329334: step: 1488/533, loss: 0.00034716667141765356
2023-01-24 09:29:37.412356: step: 1492/533, loss: 0.0016900775954127312
2023-01-24 09:29:38.478645: step: 1496/533, loss: 0.0009560674079693854
2023-01-24 09:29:39.554985: step: 1500/533, loss: 0.0026676487177610397
2023-01-24 09:29:40.658214: step: 1504/533, loss: 0.003847801126539707
2023-01-24 09:29:41.742746: step: 1508/533, loss: 0.0027794581837952137
2023-01-24 09:29:42.854381: step: 1512/533, loss: 0.0020206484477967024
2023-01-24 09:29:43.947371: step: 1516/533, loss: 8.273332059616223e-05
2023-01-24 09:29:45.029926: step: 1520/533, loss: 0.0023907991126179695
2023-01-24 09:29:46.112794: step: 1524/533, loss: 0.007517497055232525
2023-01-24 09:29:47.214156: step: 1528/533, loss: 0.007818466983735561
2023-01-24 09:29:48.282544: step: 1532/533, loss: 0.006928917020559311
2023-01-24 09:29:49.363010: step: 1536/533, loss: 0.001238807337358594
2023-01-24 09:29:50.472857: step: 1540/533, loss: 8.92915268195793e-05
2023-01-24 09:29:51.563606: step: 1544/533, loss: 0.0023208397906273603
2023-01-24 09:29:52.672275: step: 1548/533, loss: 6.048150680726394e-05
2023-01-24 09:29:53.773058: step: 1552/533, loss: 0.010169277898967266
2023-01-24 09:29:54.865928: step: 1556/533, loss: 0.0011578175472095609
2023-01-24 09:29:55.976878: step: 1560/533, loss: 0.003177701961249113
2023-01-24 09:29:57.059940: step: 1564/533, loss: 0.0
2023-01-24 09:29:58.154400: step: 1568/533, loss: 0.009450558573007584
2023-01-24 09:29:59.225446: step: 1572/533, loss: 0.0050566717982292175
2023-01-24 09:30:00.313311: step: 1576/533, loss: 0.008648700080811977
2023-01-24 09:30:01.405566: step: 1580/533, loss: 3.1743478757562116e-05
2023-01-24 09:30:02.536208: step: 1584/533, loss: 0.0009405695600435138
2023-01-24 09:30:03.632998: step: 1588/533, loss: 0.001050574705004692
2023-01-24 09:30:04.759708: step: 1592/533, loss: 6.931226380402222e-05
2023-01-24 09:30:05.833571: step: 1596/533, loss: 0.0007640647818334401
2023-01-24 09:30:06.924488: step: 1600/533, loss: 0.0020976897794753313
2023-01-24 09:30:08.022206: step: 1604/533, loss: 0.0025084493681788445
2023-01-24 09:30:09.116009: step: 1608/533, loss: 0.026036223396658897
2023-01-24 09:30:10.181793: step: 1612/533, loss: 4.1551495087333024e-05
2023-01-24 09:30:11.275743: step: 1616/533, loss: 0.037610672414302826
2023-01-24 09:30:12.383741: step: 1620/533, loss: 0.0006771648768335581
2023-01-24 09:30:13.500830: step: 1624/533, loss: 0.00982343778014183
2023-01-24 09:30:14.591245: step: 1628/533, loss: 0.002046136651188135
2023-01-24 09:30:15.715598: step: 1632/533, loss: 0.006402168422937393
2023-01-24 09:30:16.808210: step: 1636/533, loss: 0.0009214101592078805
2023-01-24 09:30:17.899821: step: 1640/533, loss: 0.0026967863086611032
2023-01-24 09:30:19.001588: step: 1644/533, loss: 0.0015194867737591267
2023-01-24 09:30:20.100909: step: 1648/533, loss: 0.004480686970055103
2023-01-24 09:30:21.169087: step: 1652/533, loss: 0.003578297095373273
2023-01-24 09:30:22.261456: step: 1656/533, loss: 0.002255129162222147
2023-01-24 09:30:23.367460: step: 1660/533, loss: 0.0012768591986969113
2023-01-24 09:30:24.462928: step: 1664/533, loss: 0.008509736508131027
2023-01-24 09:30:25.559432: step: 1668/533, loss: 0.0007901521748863161
2023-01-24 09:30:26.643804: step: 1672/533, loss: 0.007095117587596178
2023-01-24 09:30:27.724208: step: 1676/533, loss: 0.016421185806393623
2023-01-24 09:30:28.815095: step: 1680/533, loss: 0.002755896421149373
2023-01-24 09:30:29.909714: step: 1684/533, loss: 1.956124287971761e-05
2023-01-24 09:30:31.004266: step: 1688/533, loss: 0.007141175214201212
2023-01-24 09:30:32.089454: step: 1692/533, loss: 0.008014900609850883
2023-01-24 09:30:33.180633: step: 1696/533, loss: 0.0056859287433326244
2023-01-24 09:30:34.262840: step: 1700/533, loss: 0.0037238681688904762
2023-01-24 09:30:35.375662: step: 1704/533, loss: 0.0015828241594135761
2023-01-24 09:30:36.508751: step: 1708/533, loss: 0.0380101203918457
2023-01-24 09:30:37.591408: step: 1712/533, loss: 0.007287724409252405
2023-01-24 09:30:38.671879: step: 1716/533, loss: 0.010083246044814587
2023-01-24 09:30:39.771683: step: 1720/533, loss: 0.002094738883897662
2023-01-24 09:30:40.884838: step: 1724/533, loss: 0.0018825379665941
2023-01-24 09:30:41.975778: step: 1728/533, loss: 0.0008677532896399498
2023-01-24 09:30:43.062506: step: 1732/533, loss: 0.0027095761615782976
2023-01-24 09:30:44.198869: step: 1736/533, loss: 0.003608931787312031
2023-01-24 09:30:45.323150: step: 1740/533, loss: 0.004042340908199549
2023-01-24 09:30:46.437736: step: 1744/533, loss: 0.0027598037850111723
2023-01-24 09:30:47.528358: step: 1748/533, loss: 0.0042104572057724
2023-01-24 09:30:48.609928: step: 1752/533, loss: 0.0028036844450980425
2023-01-24 09:30:49.691706: step: 1756/533, loss: 0.003030079649761319
2023-01-24 09:30:50.791463: step: 1760/533, loss: 0.0029320460744202137
2023-01-24 09:30:51.886436: step: 1764/533, loss: 0.013292648829519749
2023-01-24 09:30:52.990629: step: 1768/533, loss: 5.953263462288305e-05
2023-01-24 09:30:54.068078: step: 1772/533, loss: 0.007933138869702816
2023-01-24 09:30:55.185703: step: 1776/533, loss: 0.0028409596998244524
2023-01-24 09:30:56.302898: step: 1780/533, loss: 0.008058097213506699
2023-01-24 09:30:57.385534: step: 1784/533, loss: 0.006203290540724993
2023-01-24 09:30:58.477275: step: 1788/533, loss: 0.00115295744035393
2023-01-24 09:30:59.576572: step: 1792/533, loss: 0.011549800634384155
2023-01-24 09:31:00.678290: step: 1796/533, loss: 0.008960242383182049
2023-01-24 09:31:01.768489: step: 1800/533, loss: 0.005343765020370483
2023-01-24 09:31:02.872402: step: 1804/533, loss: 0.018717829138040543
2023-01-24 09:31:03.978669: step: 1808/533, loss: 0.0016886387020349503
2023-01-24 09:31:05.097472: step: 1812/533, loss: 0.005174985155463219
2023-01-24 09:31:06.174304: step: 1816/533, loss: 0.0006512253312394023
2023-01-24 09:31:07.268315: step: 1820/533, loss: 0.005492731928825378
2023-01-24 09:31:08.347399: step: 1824/533, loss: 0.0028567996341735125
2023-01-24 09:31:09.445314: step: 1828/533, loss: 0.013332575559616089
2023-01-24 09:31:10.551103: step: 1832/533, loss: 0.006778811104595661
2023-01-24 09:31:11.655047: step: 1836/533, loss: 0.0006425138562917709
2023-01-24 09:31:12.772990: step: 1840/533, loss: 0.003846043488010764
2023-01-24 09:31:13.879101: step: 1844/533, loss: 0.01710832118988037
2023-01-24 09:31:14.973493: step: 1848/533, loss: 0.010672998614609241
2023-01-24 09:31:16.076488: step: 1852/533, loss: 0.00018192618153989315
2023-01-24 09:31:17.177001: step: 1856/533, loss: 0.0024727843701839447
2023-01-24 09:31:18.271559: step: 1860/533, loss: 0.003673441708087921
2023-01-24 09:31:19.367145: step: 1864/533, loss: 0.0017342701321467757
2023-01-24 09:31:20.480048: step: 1868/533, loss: 0.006193461362272501
2023-01-24 09:31:21.587087: step: 1872/533, loss: 0.005337781272828579
2023-01-24 09:31:22.661504: step: 1876/533, loss: 0.004181611351668835
2023-01-24 09:31:23.743564: step: 1880/533, loss: 0.00957772321999073
2023-01-24 09:31:24.853607: step: 1884/533, loss: 0.028640875592827797
2023-01-24 09:31:25.933453: step: 1888/533, loss: 0.00015349889872595668
2023-01-24 09:31:27.029718: step: 1892/533, loss: 0.003979808185249567
2023-01-24 09:31:28.119372: step: 1896/533, loss: 0.015256096608936787
2023-01-24 09:31:29.217214: step: 1900/533, loss: 0.008930166251957417
2023-01-24 09:31:30.309657: step: 1904/533, loss: 0.0051594567485153675
2023-01-24 09:31:31.418580: step: 1908/533, loss: 0.04043930768966675
2023-01-24 09:31:32.516714: step: 1912/533, loss: 0.000679764139931649
2023-01-24 09:31:33.641209: step: 1916/533, loss: 0.005395657382905483
2023-01-24 09:31:34.733862: step: 1920/533, loss: 8.152350346790627e-05
2023-01-24 09:31:35.830631: step: 1924/533, loss: 0.0014380929060280323
2023-01-24 09:31:36.937794: step: 1928/533, loss: 0.0002880374959204346
2023-01-24 09:31:38.035132: step: 1932/533, loss: 0.0033575501292943954
2023-01-24 09:31:39.123391: step: 1936/533, loss: 0.017584558576345444
2023-01-24 09:31:40.232453: step: 1940/533, loss: 0.004657108336687088
2023-01-24 09:31:41.313139: step: 1944/533, loss: 9.90028929663822e-05
2023-01-24 09:31:42.421633: step: 1948/533, loss: 0.0515572763979435
2023-01-24 09:31:43.529013: step: 1952/533, loss: 0.0036450207699090242
2023-01-24 09:31:44.611982: step: 1956/533, loss: 0.0013537645572796464
2023-01-24 09:31:45.709203: step: 1960/533, loss: 0.00045936668175272644
2023-01-24 09:31:46.805034: step: 1964/533, loss: 0.01635720394551754
2023-01-24 09:31:47.869187: step: 1968/533, loss: 1.777923353074584e-05
2023-01-24 09:31:48.982043: step: 1972/533, loss: 0.0061915237456560135
2023-01-24 09:31:50.073501: step: 1976/533, loss: 0.005713324993848801
2023-01-24 09:31:51.185724: step: 1980/533, loss: 0.0031912541016936302
2023-01-24 09:31:52.296294: step: 1984/533, loss: 0.006424645893275738
2023-01-24 09:31:53.374120: step: 1988/533, loss: 0.0029513807967305183
2023-01-24 09:31:54.459548: step: 1992/533, loss: 0.0015137136215344071
2023-01-24 09:31:55.557239: step: 1996/533, loss: 0.001914086053147912
2023-01-24 09:31:56.683904: step: 2000/533, loss: 6.89652151777409e-05
2023-01-24 09:31:57.773312: step: 2004/533, loss: 0.00045138286077417433
2023-01-24 09:31:58.875806: step: 2008/533, loss: 0.013276724144816399
2023-01-24 09:31:59.946099: step: 2012/533, loss: 4.931577495881356e-05
2023-01-24 09:32:01.050909: step: 2016/533, loss: 0.009829960763454437
2023-01-24 09:32:02.162925: step: 2020/533, loss: 0.016770359128713608
2023-01-24 09:32:03.267943: step: 2024/533, loss: 0.00013659113028552383
2023-01-24 09:32:04.365822: step: 2028/533, loss: 0.0030190150719136
2023-01-24 09:32:05.471249: step: 2032/533, loss: 0.006036240141838789
2023-01-24 09:32:06.550774: step: 2036/533, loss: 0.00742169376462698
2023-01-24 09:32:07.646368: step: 2040/533, loss: 0.008461099117994308
2023-01-24 09:32:08.748159: step: 2044/533, loss: 0.0014425048138946295
2023-01-24 09:32:09.863219: step: 2048/533, loss: 0.0022387162316590548
2023-01-24 09:32:10.951463: step: 2052/533, loss: 0.004022717475891113
2023-01-24 09:32:12.064210: step: 2056/533, loss: 0.006600686814635992
2023-01-24 09:32:13.175084: step: 2060/533, loss: 0.007146819494664669
2023-01-24 09:32:14.256610: step: 2064/533, loss: 0.000235022118431516
2023-01-24 09:32:15.350868: step: 2068/533, loss: 0.005705125629901886
2023-01-24 09:32:16.452036: step: 2072/533, loss: 0.0027613756246864796
2023-01-24 09:32:17.548596: step: 2076/533, loss: 0.00979827530682087
2023-01-24 09:32:18.640019: step: 2080/533, loss: 0.037205785512924194
2023-01-24 09:32:19.739512: step: 2084/533, loss: 0.0020715428981930017
2023-01-24 09:32:20.833730: step: 2088/533, loss: 0.0072781601920723915
2023-01-24 09:32:21.917303: step: 2092/533, loss: 0.0012629979755729437
2023-01-24 09:32:23.027370: step: 2096/533, loss: 0.008056655526161194
2023-01-24 09:32:24.104920: step: 2100/533, loss: 0.00040651531890034676
2023-01-24 09:32:25.205088: step: 2104/533, loss: 0.004210646264255047
2023-01-24 09:32:26.322563: step: 2108/533, loss: 0.004619951825588942
2023-01-24 09:32:27.416769: step: 2112/533, loss: 0.005438565276563168
2023-01-24 09:32:28.500679: step: 2116/533, loss: 0.008718165569007397
2023-01-24 09:32:29.614247: step: 2120/533, loss: 0.0008997052209451795
2023-01-24 09:32:30.723772: step: 2124/533, loss: 0.003689745208248496
2023-01-24 09:32:31.835581: step: 2128/533, loss: 0.013668321073055267
2023-01-24 09:32:32.954339: step: 2132/533, loss: 0.014092162251472473
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3796954777534646, 'r': 0.32926154332700824, 'f1': 0.352684620596206}, 'combined': 0.2598728783340465, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39581168910760534, 'r': 0.3585140491724656, 'f1': 0.376240778142648}, 'combined': 0.25082718542843196, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3585761732668228, 'r': 0.31979279209754596, 'f1': 0.33807583036189914}, 'combined': 0.24910850658245198, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38643467316605623, 'r': 0.30766145132836015, 'f1': 0.34257806143628966}, 'combined': 0.22838537429085973, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34628961647552103, 'r': 0.3134348141533653, 'f1': 0.3290441176470589}, 'combined': 0.24245356037151705, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.37938223248264596, 'r': 0.34144400923438134, 'f1': 0.35941474656250677}, 'combined': 0.23960983104167113, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 09:34:52.115644: step: 4/533, loss: 0.00024380332615692168
2023-01-24 09:34:53.187674: step: 8/533, loss: 0.003955993335694075
2023-01-24 09:34:54.302098: step: 12/533, loss: 0.003326190635561943
2023-01-24 09:34:55.391185: step: 16/533, loss: 0.005060807801783085
2023-01-24 09:34:56.493909: step: 20/533, loss: 0.002188408514484763
2023-01-24 09:34:57.591857: step: 24/533, loss: 0.003980934154242277
2023-01-24 09:34:58.670916: step: 28/533, loss: 0.0017223694594576955
2023-01-24 09:34:59.762411: step: 32/533, loss: 0.0013290556380525231
2023-01-24 09:35:00.863012: step: 36/533, loss: 0.009844877757132053
2023-01-24 09:35:01.948461: step: 40/533, loss: 0.0006573601858690381
2023-01-24 09:35:03.057653: step: 44/533, loss: 0.0041272882372140884
2023-01-24 09:35:04.170778: step: 48/533, loss: 0.007277172524482012
2023-01-24 09:35:05.265770: step: 52/533, loss: 0.002881270134821534
2023-01-24 09:35:06.354108: step: 56/533, loss: 0.0019101910293102264
2023-01-24 09:35:07.445099: step: 60/533, loss: 0.00014794351591262966
2023-01-24 09:35:08.561064: step: 64/533, loss: 0.0022971120197325945
2023-01-24 09:35:09.643059: step: 68/533, loss: 0.003582217264920473
2023-01-24 09:35:10.734273: step: 72/533, loss: 0.0036140300799161196
2023-01-24 09:35:11.837726: step: 76/533, loss: 0.006046731024980545
2023-01-24 09:35:12.935488: step: 80/533, loss: 0.002812119433656335
2023-01-24 09:35:14.028415: step: 84/533, loss: 0.0029055944178253412
2023-01-24 09:35:15.128805: step: 88/533, loss: 0.0023672168608754873
2023-01-24 09:35:16.224054: step: 92/533, loss: 0.011180892586708069
2023-01-24 09:35:17.300843: step: 96/533, loss: 0.006980047561228275
2023-01-24 09:35:18.395882: step: 100/533, loss: 0.0034669756423681974
2023-01-24 09:35:19.488070: step: 104/533, loss: 0.0006052074022591114
2023-01-24 09:35:20.571662: step: 108/533, loss: 0.00017591372306924313
2023-01-24 09:35:21.652158: step: 112/533, loss: 8.389454887947068e-05
2023-01-24 09:35:22.744684: step: 116/533, loss: 0.00021109484077896923
2023-01-24 09:35:23.850662: step: 120/533, loss: 0.038310859352350235
2023-01-24 09:35:24.962434: step: 124/533, loss: 0.0006225889665074646
2023-01-24 09:35:26.078201: step: 128/533, loss: 0.0015699025243520737
2023-01-24 09:35:27.149255: step: 132/533, loss: 0.00011550921044545248
2023-01-24 09:35:28.222950: step: 136/533, loss: 0.0015041844453662634
2023-01-24 09:35:29.302208: step: 140/533, loss: 0.0006576735177077353
2023-01-24 09:35:30.384643: step: 144/533, loss: 1.673005499469582e-05
2023-01-24 09:35:31.472631: step: 148/533, loss: 0.0006565125077031553
2023-01-24 09:35:32.560705: step: 152/533, loss: 0.0027966173365712166
2023-01-24 09:35:33.674373: step: 156/533, loss: 0.0053399489261209965
2023-01-24 09:35:34.768422: step: 160/533, loss: 0.0031277905218303204
2023-01-24 09:35:35.861039: step: 164/533, loss: 0.002586896764114499
2023-01-24 09:35:36.990808: step: 168/533, loss: 0.02255460061132908
2023-01-24 09:35:38.070562: step: 172/533, loss: 0.017595242708921432
2023-01-24 09:35:39.196624: step: 176/533, loss: 0.02323240227997303
2023-01-24 09:35:40.280888: step: 180/533, loss: 0.004910741001367569
2023-01-24 09:35:41.389119: step: 184/533, loss: 0.00771360145881772
2023-01-24 09:35:42.481661: step: 188/533, loss: 0.001910832361318171
2023-01-24 09:35:43.572807: step: 192/533, loss: 1.7854817997431383e-06
2023-01-24 09:35:44.666264: step: 196/533, loss: 1.8094041251970339e-06
2023-01-24 09:35:45.777164: step: 200/533, loss: 0.008362052030861378
2023-01-24 09:35:46.867982: step: 204/533, loss: 0.004836269188672304
2023-01-24 09:35:47.952618: step: 208/533, loss: 0.0003306365688331425
2023-01-24 09:35:49.048356: step: 212/533, loss: 0.005265132058411837
2023-01-24 09:35:50.133043: step: 216/533, loss: 4.288237323635258e-05
2023-01-24 09:35:51.221305: step: 220/533, loss: 0.007204795256257057
2023-01-24 09:35:52.315342: step: 224/533, loss: 0.0016979341162368655
2023-01-24 09:35:53.414137: step: 228/533, loss: 0.0007142344838939607
2023-01-24 09:35:54.507177: step: 232/533, loss: 0.0012339751701802015
2023-01-24 09:35:55.607986: step: 236/533, loss: 0.0008220844902098179
2023-01-24 09:35:56.682271: step: 240/533, loss: 0.0002474302891641855
2023-01-24 09:35:57.757790: step: 244/533, loss: 0.0001885897945612669
2023-01-24 09:35:58.839630: step: 248/533, loss: 0.0037842588499188423
2023-01-24 09:35:59.927624: step: 252/533, loss: 0.0061601619236171246
2023-01-24 09:36:01.024432: step: 256/533, loss: 0.00022151258599478751
2023-01-24 09:36:02.139737: step: 260/533, loss: 0.0006325804279185832
2023-01-24 09:36:03.244191: step: 264/533, loss: 0.007201085798442364
2023-01-24 09:36:04.339955: step: 268/533, loss: 0.004035120829939842
2023-01-24 09:36:05.433788: step: 272/533, loss: 0.0031111135613173246
2023-01-24 09:36:06.526073: step: 276/533, loss: 0.006573380436748266
2023-01-24 09:36:07.616510: step: 280/533, loss: 0.0007544734980911016
2023-01-24 09:36:08.713863: step: 284/533, loss: 0.007801631931215525
2023-01-24 09:36:09.820459: step: 288/533, loss: 0.0005991553771309555
2023-01-24 09:36:10.906411: step: 292/533, loss: 0.005869938991963863
2023-01-24 09:36:12.026222: step: 296/533, loss: 0.001325715333223343
2023-01-24 09:36:13.131396: step: 300/533, loss: 0.01164182648062706
2023-01-24 09:36:14.218758: step: 304/533, loss: 0.004028564319014549
2023-01-24 09:36:15.315878: step: 308/533, loss: 0.02201184444129467
2023-01-24 09:36:16.435422: step: 312/533, loss: 0.006663999520242214
2023-01-24 09:36:17.518168: step: 316/533, loss: 0.0
2023-01-24 09:36:18.618221: step: 320/533, loss: 0.0017514013452455401
2023-01-24 09:36:19.702564: step: 324/533, loss: 0.007680973969399929
2023-01-24 09:36:20.786523: step: 328/533, loss: 0.0003139690961688757
2023-01-24 09:36:21.879225: step: 332/533, loss: 0.006780778989195824
2023-01-24 09:36:22.973532: step: 336/533, loss: 0.010680127888917923
2023-01-24 09:36:24.072774: step: 340/533, loss: 0.0005427238065749407
2023-01-24 09:36:25.169331: step: 344/533, loss: 4.899458508589305e-05
2023-01-24 09:36:26.260845: step: 348/533, loss: 0.002067571273073554
2023-01-24 09:36:27.345146: step: 352/533, loss: 0.0015440828865393996
2023-01-24 09:36:28.435003: step: 356/533, loss: 0.002634576288983226
2023-01-24 09:36:29.534309: step: 360/533, loss: 0.001910128747113049
2023-01-24 09:36:30.623962: step: 364/533, loss: 0.00604513892903924
2023-01-24 09:36:31.728825: step: 368/533, loss: 0.0012735191266983747
2023-01-24 09:36:32.814195: step: 372/533, loss: 0.0031332552898675203
2023-01-24 09:36:33.911522: step: 376/533, loss: 0.008258722722530365
2023-01-24 09:36:35.031048: step: 380/533, loss: 0.006897420156747103
2023-01-24 09:36:36.125369: step: 384/533, loss: 0.001181826344691217
2023-01-24 09:36:37.215486: step: 388/533, loss: 0.0007202559500001371
2023-01-24 09:36:38.336686: step: 392/533, loss: 0.010487506166100502
2023-01-24 09:36:39.440929: step: 396/533, loss: 0.008188190869987011
2023-01-24 09:36:40.544782: step: 400/533, loss: 0.016469238325953484
2023-01-24 09:36:41.634936: step: 404/533, loss: 0.004093158058822155
2023-01-24 09:36:42.716375: step: 408/533, loss: 0.005338730756193399
2023-01-24 09:36:43.819325: step: 412/533, loss: 0.0007964154938235879
2023-01-24 09:36:44.922092: step: 416/533, loss: 0.008264083415269852
2023-01-24 09:36:46.031630: step: 420/533, loss: 0.007491594646126032
2023-01-24 09:36:47.140347: step: 424/533, loss: 0.003962042275816202
2023-01-24 09:36:48.255161: step: 428/533, loss: 0.012472460977733135
2023-01-24 09:36:49.354213: step: 432/533, loss: 0.007246095687150955
2023-01-24 09:36:50.457027: step: 436/533, loss: 0.004674055147916079
2023-01-24 09:36:51.544022: step: 440/533, loss: 0.0044150082394480705
2023-01-24 09:36:52.650055: step: 444/533, loss: 0.005949612241238356
2023-01-24 09:36:53.731378: step: 448/533, loss: 0.0003912788233719766
2023-01-24 09:36:54.816284: step: 452/533, loss: 0.0033401967957615852
2023-01-24 09:36:55.912088: step: 456/533, loss: 0.005736442282795906
2023-01-24 09:36:57.033762: step: 460/533, loss: 0.0002071027847705409
2023-01-24 09:36:58.122216: step: 464/533, loss: 0.0015715175541117787
2023-01-24 09:36:59.228171: step: 468/533, loss: 0.009783513844013214
2023-01-24 09:37:00.338869: step: 472/533, loss: 0.004917282611131668
2023-01-24 09:37:01.414217: step: 476/533, loss: 0.00026343134231865406
2023-01-24 09:37:02.526372: step: 480/533, loss: 0.0022621476091444492
2023-01-24 09:37:03.605912: step: 484/533, loss: 0.0011048815213143826
2023-01-24 09:37:04.711137: step: 488/533, loss: 0.007635756395757198
2023-01-24 09:37:05.811050: step: 492/533, loss: 0.001483274158090353
2023-01-24 09:37:06.929236: step: 496/533, loss: 0.004503882955759764
2023-01-24 09:37:08.029673: step: 500/533, loss: 0.0013448494719341397
2023-01-24 09:37:09.122915: step: 504/533, loss: 0.0005351643776521087
2023-01-24 09:37:10.195845: step: 508/533, loss: 9.45433639572002e-05
2023-01-24 09:37:11.289170: step: 512/533, loss: 0.002345600165426731
2023-01-24 09:37:12.386022: step: 516/533, loss: 0.007589023560285568
2023-01-24 09:37:13.498092: step: 520/533, loss: 0.0010907112155109644
2023-01-24 09:37:14.584812: step: 524/533, loss: 0.0007260671118274331
2023-01-24 09:37:15.670215: step: 528/533, loss: 0.0002262668131152168
2023-01-24 09:37:16.760722: step: 532/533, loss: 0.00882030837237835
2023-01-24 09:37:17.879766: step: 536/533, loss: 0.023267202079296112
2023-01-24 09:37:18.982799: step: 540/533, loss: 0.0025204813573509455
2023-01-24 09:37:20.068067: step: 544/533, loss: 0.0007892930298112333
2023-01-24 09:37:21.162784: step: 548/533, loss: 0.014902232214808464
2023-01-24 09:37:22.285473: step: 552/533, loss: 0.013179103843867779
2023-01-24 09:37:23.387965: step: 556/533, loss: 0.0015736751956865191
2023-01-24 09:37:24.467332: step: 560/533, loss: 0.004053467884659767
2023-01-24 09:37:25.544288: step: 564/533, loss: 0.005954406224191189
2023-01-24 09:37:26.650651: step: 568/533, loss: 0.010241019539535046
2023-01-24 09:37:27.730836: step: 572/533, loss: 0.00035632564686238766
2023-01-24 09:37:28.838419: step: 576/533, loss: 0.005989603232592344
2023-01-24 09:37:29.936267: step: 580/533, loss: 0.007535836659371853
2023-01-24 09:37:31.036713: step: 584/533, loss: 0.0003997876774519682
2023-01-24 09:37:32.136592: step: 588/533, loss: 0.004788553807884455
2023-01-24 09:37:33.218289: step: 592/533, loss: 0.02515365183353424
2023-01-24 09:37:34.313670: step: 596/533, loss: 0.0037984333466738462
2023-01-24 09:37:35.407358: step: 600/533, loss: 0.0013387073995545506
2023-01-24 09:37:36.485457: step: 604/533, loss: 0.0013091868022456765
2023-01-24 09:37:37.588539: step: 608/533, loss: 0.006706457119435072
2023-01-24 09:37:38.708574: step: 612/533, loss: 0.004410469438880682
2023-01-24 09:37:39.824713: step: 616/533, loss: 0.011268922127783298
2023-01-24 09:37:40.912506: step: 620/533, loss: 0.009302875958383083
2023-01-24 09:37:42.027804: step: 624/533, loss: 0.008498779498040676
2023-01-24 09:37:43.133669: step: 628/533, loss: 0.005212119780480862
2023-01-24 09:37:44.232772: step: 632/533, loss: 0.008831747807562351
2023-01-24 09:37:45.348455: step: 636/533, loss: 0.003631663741543889
2023-01-24 09:37:46.462733: step: 640/533, loss: 0.006467610131949186
2023-01-24 09:37:47.589971: step: 644/533, loss: 0.0019013453274965286
2023-01-24 09:37:48.716738: step: 648/533, loss: 0.0011684150667861104
2023-01-24 09:37:49.814843: step: 652/533, loss: 0.0015550003154203296
2023-01-24 09:37:50.958075: step: 656/533, loss: 0.007062254473567009
2023-01-24 09:37:52.087313: step: 660/533, loss: 0.007503184489905834
2023-01-24 09:37:53.183153: step: 664/533, loss: 0.01888129487633705
2023-01-24 09:37:54.297165: step: 668/533, loss: 0.013670106418430805
2023-01-24 09:37:55.406596: step: 672/533, loss: 0.00027207215316593647
2023-01-24 09:37:56.504875: step: 676/533, loss: 0.002116141375154257
2023-01-24 09:37:57.613782: step: 680/533, loss: 0.003488345770165324
2023-01-24 09:37:58.711457: step: 684/533, loss: 0.0006570327095687389
2023-01-24 09:37:59.784212: step: 688/533, loss: 1.8253621192343417e-07
2023-01-24 09:38:00.877820: step: 692/533, loss: 0.011955947615206242
2023-01-24 09:38:01.975128: step: 696/533, loss: 0.011632067151367664
2023-01-24 09:38:03.093412: step: 700/533, loss: 0.0009934846311807632
2023-01-24 09:38:04.202952: step: 704/533, loss: 0.003704171860590577
2023-01-24 09:38:05.306271: step: 708/533, loss: 0.0033076582476496696
2023-01-24 09:38:06.402653: step: 712/533, loss: 0.008561967872083187
2023-01-24 09:38:07.501905: step: 716/533, loss: 0.0002770892169792205
2023-01-24 09:38:08.601917: step: 720/533, loss: 0.004188166931271553
2023-01-24 09:38:09.685940: step: 724/533, loss: 0.0017923597479239106
2023-01-24 09:38:10.783868: step: 728/533, loss: 0.003247710643336177
2023-01-24 09:38:11.870828: step: 732/533, loss: 0.0005436796927824616
2023-01-24 09:38:12.974457: step: 736/533, loss: 0.0034694457426667213
2023-01-24 09:38:14.082436: step: 740/533, loss: 0.0027144753839820623
2023-01-24 09:38:15.197034: step: 744/533, loss: 0.0031950026750564575
2023-01-24 09:38:16.318403: step: 748/533, loss: 0.018243268132209778
2023-01-24 09:38:17.419038: step: 752/533, loss: 0.0001996125211007893
2023-01-24 09:38:18.511879: step: 756/533, loss: 0.0010231230407953262
2023-01-24 09:38:19.598493: step: 760/533, loss: 0.0005237577715888619
2023-01-24 09:38:20.694598: step: 764/533, loss: 0.007726180832833052
2023-01-24 09:38:21.788870: step: 768/533, loss: 0.007069366984069347
2023-01-24 09:38:22.871537: step: 772/533, loss: 0.006010855082422495
2023-01-24 09:38:23.962411: step: 776/533, loss: 0.006864919327199459
2023-01-24 09:38:25.052202: step: 780/533, loss: 0.00015164277283474803
2023-01-24 09:38:26.158093: step: 784/533, loss: 0.006961608771234751
2023-01-24 09:38:27.248169: step: 788/533, loss: 0.00044897623592987657
2023-01-24 09:38:28.347817: step: 792/533, loss: 0.00024519741418771446
2023-01-24 09:38:29.453285: step: 796/533, loss: 0.0006446785409934819
2023-01-24 09:38:30.531883: step: 800/533, loss: 0.006463160738348961
2023-01-24 09:38:31.644543: step: 804/533, loss: 0.0065233721397817135
2023-01-24 09:38:32.729912: step: 808/533, loss: 0.0007551119779236615
2023-01-24 09:38:33.822028: step: 812/533, loss: 0.0020657062996178865
2023-01-24 09:38:34.923276: step: 816/533, loss: 0.010540065355598927
2023-01-24 09:38:36.017306: step: 820/533, loss: 0.009215413592755795
2023-01-24 09:38:37.157042: step: 824/533, loss: 0.0013883649371564388
2023-01-24 09:38:38.253732: step: 828/533, loss: 0.003951892256736755
2023-01-24 09:38:39.339257: step: 832/533, loss: 7.115535481716506e-06
2023-01-24 09:38:40.426561: step: 836/533, loss: 0.003358010668307543
2023-01-24 09:38:41.523557: step: 840/533, loss: 0.003240708727389574
2023-01-24 09:38:42.600427: step: 844/533, loss: 0.0013265198795124888
2023-01-24 09:38:43.692908: step: 848/533, loss: 0.01142299547791481
2023-01-24 09:38:44.786232: step: 852/533, loss: 0.004683015402406454
2023-01-24 09:38:45.897102: step: 856/533, loss: 0.004316160921007395
2023-01-24 09:38:46.998856: step: 860/533, loss: 0.005709308665245771
2023-01-24 09:38:48.102144: step: 864/533, loss: 0.010167115367949009
2023-01-24 09:38:49.205498: step: 868/533, loss: 0.0039401850663125515
2023-01-24 09:38:50.295978: step: 872/533, loss: 0.007255776319652796
2023-01-24 09:38:51.423294: step: 876/533, loss: 0.0046425024047493935
2023-01-24 09:38:52.525885: step: 880/533, loss: 0.001377429929561913
2023-01-24 09:38:53.615007: step: 884/533, loss: 0.00041201538988389075
2023-01-24 09:38:54.720295: step: 888/533, loss: 0.005787092261016369
2023-01-24 09:38:55.816307: step: 892/533, loss: 0.0022157609928399324
2023-01-24 09:38:56.918075: step: 896/533, loss: 0.01156845036894083
2023-01-24 09:38:58.029431: step: 900/533, loss: 0.00015683486708439887
2023-01-24 09:38:59.135013: step: 904/533, loss: 0.0036759446375072002
2023-01-24 09:39:00.253722: step: 908/533, loss: 0.005686640739440918
2023-01-24 09:39:01.360613: step: 912/533, loss: 0.007341242861002684
2023-01-24 09:39:02.481028: step: 916/533, loss: 0.0032197306863963604
2023-01-24 09:39:03.571960: step: 920/533, loss: 0.002005833899602294
2023-01-24 09:39:04.676621: step: 924/533, loss: 0.0011770750861614943
2023-01-24 09:39:05.793312: step: 928/533, loss: 0.0002941054990515113
2023-01-24 09:39:06.901692: step: 932/533, loss: 0.004846217576414347
2023-01-24 09:39:07.992914: step: 936/533, loss: 0.010311385616660118
2023-01-24 09:39:09.117850: step: 940/533, loss: 0.000298919971100986
2023-01-24 09:39:10.223357: step: 944/533, loss: 0.0021796743385493755
2023-01-24 09:39:11.330800: step: 948/533, loss: 0.0035865418612957
2023-01-24 09:39:12.435638: step: 952/533, loss: 0.0024803848937153816
2023-01-24 09:39:13.526937: step: 956/533, loss: 0.0030769698787480593
2023-01-24 09:39:14.628055: step: 960/533, loss: 0.0017535150982439518
2023-01-24 09:39:15.733766: step: 964/533, loss: 0.004078370984643698
2023-01-24 09:39:16.824711: step: 968/533, loss: 0.006965979468077421
2023-01-24 09:39:17.914678: step: 972/533, loss: 3.4378714190097526e-05
2023-01-24 09:39:19.020097: step: 976/533, loss: 0.008599521592259407
2023-01-24 09:39:20.115199: step: 980/533, loss: 0.002834304003044963
2023-01-24 09:39:21.213286: step: 984/533, loss: 0.006700475700199604
2023-01-24 09:39:22.328492: step: 988/533, loss: 0.03228718042373657
2023-01-24 09:39:23.418225: step: 992/533, loss: 0.004505963530391455
2023-01-24 09:39:24.509582: step: 996/533, loss: 0.0009314006310887635
2023-01-24 09:39:25.600222: step: 1000/533, loss: 0.006904862355440855
2023-01-24 09:39:26.702577: step: 1004/533, loss: 0.0002508819743525237
2023-01-24 09:39:27.816917: step: 1008/533, loss: 0.009192700497806072
2023-01-24 09:39:28.924021: step: 1012/533, loss: 0.004135646857321262
2023-01-24 09:39:29.995901: step: 1016/533, loss: 0.004827674012631178
2023-01-24 09:39:31.102810: step: 1020/533, loss: 0.014663049019873142
2023-01-24 09:39:32.198186: step: 1024/533, loss: 0.0002930742921307683
2023-01-24 09:39:33.315025: step: 1028/533, loss: 0.0031684022396802902
2023-01-24 09:39:34.438597: step: 1032/533, loss: 0.001396894920617342
2023-01-24 09:39:35.547371: step: 1036/533, loss: 0.007224187254905701
2023-01-24 09:39:36.662407: step: 1040/533, loss: 0.0041254740208387375
2023-01-24 09:39:37.774555: step: 1044/533, loss: 0.002199897775426507
2023-01-24 09:39:38.907375: step: 1048/533, loss: 0.003896738402545452
2023-01-24 09:39:40.016606: step: 1052/533, loss: 0.0046297889202833176
2023-01-24 09:39:41.126648: step: 1056/533, loss: 0.0010784213664010167
2023-01-24 09:39:42.241622: step: 1060/533, loss: 0.006227557547390461
2023-01-24 09:39:43.348515: step: 1064/533, loss: 1.1072819688706659e-05
2023-01-24 09:39:44.441600: step: 1068/533, loss: 0.007174093276262283
2023-01-24 09:39:45.564133: step: 1072/533, loss: 0.011392912827432156
2023-01-24 09:39:46.668262: step: 1076/533, loss: 0.003730322001501918
2023-01-24 09:39:47.742407: step: 1080/533, loss: 0.0027966618072241545
2023-01-24 09:39:48.854144: step: 1084/533, loss: 0.004385578911751509
2023-01-24 09:39:49.973121: step: 1088/533, loss: 0.002639094367623329
2023-01-24 09:39:51.074530: step: 1092/533, loss: 0.006054427474737167
2023-01-24 09:39:52.176875: step: 1096/533, loss: 0.0003486870846245438
2023-01-24 09:39:53.264365: step: 1100/533, loss: 5.555916141020134e-05
2023-01-24 09:39:54.351383: step: 1104/533, loss: 0.0017139589181169868
2023-01-24 09:39:55.438192: step: 1108/533, loss: 0.00390937365591526
2023-01-24 09:39:56.561381: step: 1112/533, loss: 0.005678579211235046
2023-01-24 09:39:57.658760: step: 1116/533, loss: 0.0009237974300049245
2023-01-24 09:39:58.765828: step: 1120/533, loss: 0.003694339655339718
2023-01-24 09:39:59.859113: step: 1124/533, loss: 0.0
2023-01-24 09:40:00.963243: step: 1128/533, loss: 0.010245459154248238
2023-01-24 09:40:02.080145: step: 1132/533, loss: 0.006662936415523291
2023-01-24 09:40:03.187624: step: 1136/533, loss: 0.0005061589763499796
2023-01-24 09:40:04.290740: step: 1140/533, loss: 0.00316277495585382
2023-01-24 09:40:05.392022: step: 1144/533, loss: 0.017137102782726288
2023-01-24 09:40:06.492452: step: 1148/533, loss: 0.0038940708618611097
2023-01-24 09:40:07.594153: step: 1152/533, loss: 0.006420553661882877
2023-01-24 09:40:08.694569: step: 1156/533, loss: 0.004238523077219725
2023-01-24 09:40:09.778802: step: 1160/533, loss: 0.00034015989513136446
2023-01-24 09:40:10.893679: step: 1164/533, loss: 0.0032839870546013117
2023-01-24 09:40:11.987368: step: 1168/533, loss: 0.00020586836035363376
2023-01-24 09:40:13.084332: step: 1172/533, loss: 0.003615408670157194
2023-01-24 09:40:14.175944: step: 1176/533, loss: 0.00038195360684767365
2023-01-24 09:40:15.278251: step: 1180/533, loss: 0.0023135992232710123
2023-01-24 09:40:16.369046: step: 1184/533, loss: 0.00861938763409853
2023-01-24 09:40:17.475633: step: 1188/533, loss: 0.001447248738259077
2023-01-24 09:40:18.554332: step: 1192/533, loss: 0.0025778755079954863
2023-01-24 09:40:19.639136: step: 1196/533, loss: 0.0014077917439863086
2023-01-24 09:40:20.732535: step: 1200/533, loss: 0.00871556717902422
2023-01-24 09:40:21.840792: step: 1204/533, loss: 0.004208829253911972
2023-01-24 09:40:22.970821: step: 1208/533, loss: 0.0037526527885347605
2023-01-24 09:40:24.049886: step: 1212/533, loss: 3.2327799999620765e-05
2023-01-24 09:40:25.142679: step: 1216/533, loss: 0.003046599216759205
2023-01-24 09:40:26.218323: step: 1220/533, loss: 0.0011580970603972673
2023-01-24 09:40:27.305905: step: 1224/533, loss: 0.006763590034097433
2023-01-24 09:40:28.406302: step: 1228/533, loss: 6.671099981758744e-05
2023-01-24 09:40:29.500644: step: 1232/533, loss: 0.005372189916670322
2023-01-24 09:40:30.622505: step: 1236/533, loss: 0.0009054936817847192
2023-01-24 09:40:31.694699: step: 1240/533, loss: 0.002070776652544737
2023-01-24 09:40:32.792961: step: 1244/533, loss: 0.007038265932351351
2023-01-24 09:40:33.903872: step: 1248/533, loss: 0.0008507717866450548
2023-01-24 09:40:34.997212: step: 1252/533, loss: 0.006543744821101427
2023-01-24 09:40:36.068567: step: 1256/533, loss: 0.000487605546368286
2023-01-24 09:40:37.181683: step: 1260/533, loss: 0.006190032232552767
2023-01-24 09:40:38.269082: step: 1264/533, loss: 0.022043516859412193
2023-01-24 09:40:39.393452: step: 1268/533, loss: 0.010292374528944492
2023-01-24 09:40:40.482144: step: 1272/533, loss: 0.010886370204389095
2023-01-24 09:40:41.605606: step: 1276/533, loss: 0.00014053921040613204
2023-01-24 09:40:42.723140: step: 1280/533, loss: 0.00033721994259394705
2023-01-24 09:40:43.840223: step: 1284/533, loss: 0.01307658851146698
2023-01-24 09:40:44.931857: step: 1288/533, loss: 0.01231358665972948
2023-01-24 09:40:46.023675: step: 1292/533, loss: 0.0015688561834394932
2023-01-24 09:40:47.121450: step: 1296/533, loss: 0.012670583091676235
2023-01-24 09:40:48.219765: step: 1300/533, loss: 0.006208021193742752
2023-01-24 09:40:49.333843: step: 1304/533, loss: 0.0075460160151124
2023-01-24 09:40:50.432634: step: 1308/533, loss: 0.053645018488168716
2023-01-24 09:40:51.526832: step: 1312/533, loss: 0.002847421681508422
2023-01-24 09:40:52.621680: step: 1316/533, loss: 0.004932621493935585
2023-01-24 09:40:53.723462: step: 1320/533, loss: 2.279802538396325e-05
2023-01-24 09:40:54.801669: step: 1324/533, loss: 0.0014099193504080176
2023-01-24 09:40:55.889182: step: 1328/533, loss: 0.006204068660736084
2023-01-24 09:40:56.982061: step: 1332/533, loss: 0.003845800878480077
2023-01-24 09:40:58.052067: step: 1336/533, loss: 0.0030008405447006226
2023-01-24 09:40:59.143198: step: 1340/533, loss: 0.0001669353077886626
2023-01-24 09:41:00.248110: step: 1344/533, loss: 0.0115022212266922
2023-01-24 09:41:01.362972: step: 1348/533, loss: 0.005369207356125116
2023-01-24 09:41:02.441711: step: 1352/533, loss: 0.0008841327507980168
2023-01-24 09:41:03.567872: step: 1356/533, loss: 0.002631040057167411
2023-01-24 09:41:04.693787: step: 1360/533, loss: 0.004527223762124777
2023-01-24 09:41:05.793857: step: 1364/533, loss: 0.0006656870245933533
2023-01-24 09:41:06.891696: step: 1368/533, loss: 0.005894456058740616
2023-01-24 09:41:08.014387: step: 1372/533, loss: 0.00408930703997612
2023-01-24 09:41:09.119671: step: 1376/533, loss: 0.0004529018478933722
2023-01-24 09:41:10.236184: step: 1380/533, loss: 0.00015447955229319632
2023-01-24 09:41:11.345908: step: 1384/533, loss: 0.002324416534975171
2023-01-24 09:41:12.471912: step: 1388/533, loss: 0.007207160349935293
2023-01-24 09:41:13.572715: step: 1392/533, loss: 0.0023338161408901215
2023-01-24 09:41:14.667581: step: 1396/533, loss: 0.0022198122460395098
2023-01-24 09:41:15.764663: step: 1400/533, loss: 0.015152310952544212
2023-01-24 09:41:16.878896: step: 1404/533, loss: 0.012968926690518856
2023-01-24 09:41:17.963085: step: 1408/533, loss: 0.0016017114976420999
2023-01-24 09:41:19.061250: step: 1412/533, loss: 0.00150458631105721
2023-01-24 09:41:20.190414: step: 1416/533, loss: 0.011056695133447647
2023-01-24 09:41:21.282520: step: 1420/533, loss: 0.0011486548464745283
2023-01-24 09:41:22.383333: step: 1424/533, loss: 0.00684012658894062
2023-01-24 09:41:23.482448: step: 1428/533, loss: 0.0007466397364623845
2023-01-24 09:41:24.573035: step: 1432/533, loss: 0.0006889000069350004
2023-01-24 09:41:25.645453: step: 1436/533, loss: 0.003310261992737651
2023-01-24 09:41:26.760498: step: 1440/533, loss: 0.001864623511210084
2023-01-24 09:41:27.838358: step: 1444/533, loss: 0.001742799300700426
2023-01-24 09:41:28.935589: step: 1448/533, loss: 0.002664618892595172
2023-01-24 09:41:30.019413: step: 1452/533, loss: 0.00414510490372777
2023-01-24 09:41:31.112390: step: 1456/533, loss: 0.004356284625828266
2023-01-24 09:41:32.198080: step: 1460/533, loss: 0.004470780957490206
2023-01-24 09:41:33.276888: step: 1464/533, loss: 0.00013521920482162386
2023-01-24 09:41:34.371878: step: 1468/533, loss: 6.283844413701445e-05
2023-01-24 09:41:35.464390: step: 1472/533, loss: 0.0022413574624806643
2023-01-24 09:41:36.549416: step: 1476/533, loss: 0.02528192661702633
2023-01-24 09:41:37.644526: step: 1480/533, loss: 0.0006621882203035057
2023-01-24 09:41:38.727473: step: 1484/533, loss: 0.005570436827838421
2023-01-24 09:41:39.830495: step: 1488/533, loss: 8.810934377834201e-05
2023-01-24 09:41:40.942795: step: 1492/533, loss: 0.007907001301646233
2023-01-24 09:41:42.020633: step: 1496/533, loss: 0.0014418595237657428
2023-01-24 09:41:43.089853: step: 1500/533, loss: 0.0006302191759459674
2023-01-24 09:41:44.165239: step: 1504/533, loss: 0.0060143256559967995
2023-01-24 09:41:45.274209: step: 1508/533, loss: 0.005798174999654293
2023-01-24 09:41:46.395281: step: 1512/533, loss: 0.004379651974886656
2023-01-24 09:41:47.494954: step: 1516/533, loss: 0.0071278843097388744
2023-01-24 09:41:48.600639: step: 1520/533, loss: 0.0031092732679098845
2023-01-24 09:41:49.702314: step: 1524/533, loss: 0.002311966149136424
2023-01-24 09:41:50.787765: step: 1528/533, loss: 0.003607879625633359
2023-01-24 09:41:51.870985: step: 1532/533, loss: 0.0018328933510929346
2023-01-24 09:41:52.952266: step: 1536/533, loss: 0.0027920452412217855
2023-01-24 09:41:54.033085: step: 1540/533, loss: 0.003821662161499262
2023-01-24 09:41:55.119634: step: 1544/533, loss: 0.000783932046033442
2023-01-24 09:41:56.244247: step: 1548/533, loss: 5.8391848142491654e-05
2023-01-24 09:41:57.373958: step: 1552/533, loss: 7.567866123281419e-05
2023-01-24 09:41:58.476575: step: 1556/533, loss: 0.001544472761452198
2023-01-24 09:41:59.566033: step: 1560/533, loss: 0.0006543706404045224
2023-01-24 09:42:00.676816: step: 1564/533, loss: 0.00010897399624809623
2023-01-24 09:42:01.767476: step: 1568/533, loss: 0.008557301014661789
2023-01-24 09:42:02.842749: step: 1572/533, loss: 0.0030547126661986113
2023-01-24 09:42:03.966743: step: 1576/533, loss: 0.0007383005577139556
2023-01-24 09:42:05.042251: step: 1580/533, loss: 0.008487534709274769
2023-01-24 09:42:06.143081: step: 1584/533, loss: 0.0035957875661551952
2023-01-24 09:42:07.227498: step: 1588/533, loss: 0.0009401571005582809
2023-01-24 09:42:08.319985: step: 1592/533, loss: 0.00032505946001037955
2023-01-24 09:42:09.396595: step: 1596/533, loss: 0.00939187966287136
2023-01-24 09:42:10.493395: step: 1600/533, loss: 0.0008922767592594028
2023-01-24 09:42:11.573239: step: 1604/533, loss: 0.001014544046483934
2023-01-24 09:42:12.655687: step: 1608/533, loss: 9.512832184555009e-05
2023-01-24 09:42:13.752573: step: 1612/533, loss: 0.013762862421572208
2023-01-24 09:42:14.848045: step: 1616/533, loss: 0.016050662845373154
2023-01-24 09:42:15.945771: step: 1620/533, loss: 0.0003404193848837167
2023-01-24 09:42:17.083763: step: 1624/533, loss: 0.007574685849249363
2023-01-24 09:42:18.171582: step: 1628/533, loss: 0.0042413934133946896
2023-01-24 09:42:19.251058: step: 1632/533, loss: 0.006781661882996559
2023-01-24 09:42:20.350257: step: 1636/533, loss: 0.003687092801555991
2023-01-24 09:42:21.432872: step: 1640/533, loss: 0.0020757471211254597
2023-01-24 09:42:22.515896: step: 1644/533, loss: 0.0004461239150259644
2023-01-24 09:42:23.601021: step: 1648/533, loss: 0.0063677155412733555
2023-01-24 09:42:24.730522: step: 1652/533, loss: 0.0013171298196539283
2023-01-24 09:42:25.846343: step: 1656/533, loss: 0.00035640629357658327
2023-01-24 09:42:26.938652: step: 1660/533, loss: 0.002375681884586811
2023-01-24 09:42:28.049876: step: 1664/533, loss: 0.001225990359671414
2023-01-24 09:42:29.158850: step: 1668/533, loss: 0.016268707811832428
2023-01-24 09:42:30.253416: step: 1672/533, loss: 0.0003133040154352784
2023-01-24 09:42:31.368631: step: 1676/533, loss: 0.0035783080384135246
2023-01-24 09:42:32.486462: step: 1680/533, loss: 0.04532569274306297
2023-01-24 09:42:33.568152: step: 1684/533, loss: 0.00013850924733560532
2023-01-24 09:42:34.657099: step: 1688/533, loss: 0.00399570120498538
2023-01-24 09:42:35.748017: step: 1692/533, loss: 0.0012352996272966266
2023-01-24 09:42:36.854750: step: 1696/533, loss: 0.0029057140927761793
2023-01-24 09:42:37.930700: step: 1700/533, loss: 0.002427001018077135
2023-01-24 09:42:39.038895: step: 1704/533, loss: 0.0022146045230329037
2023-01-24 09:42:40.127015: step: 1708/533, loss: 0.001842237077653408
2023-01-24 09:42:41.240584: step: 1712/533, loss: 0.003854658454656601
2023-01-24 09:42:42.349204: step: 1716/533, loss: 0.00448719784617424
2023-01-24 09:42:43.456933: step: 1720/533, loss: 0.0015353142516687512
2023-01-24 09:42:44.557568: step: 1724/533, loss: 0.001036871806718409
2023-01-24 09:42:45.646840: step: 1728/533, loss: 0.0001417698513250798
2023-01-24 09:42:46.753557: step: 1732/533, loss: 0.008033894933760166
2023-01-24 09:42:47.846059: step: 1736/533, loss: 0.0003389666089788079
2023-01-24 09:42:48.949959: step: 1740/533, loss: 0.001652801875025034
2023-01-24 09:42:50.031521: step: 1744/533, loss: 0.013553068973124027
2023-01-24 09:42:51.119387: step: 1748/533, loss: 0.008029614575207233
2023-01-24 09:42:52.234753: step: 1752/533, loss: 0.00036373568582348526
2023-01-24 09:42:53.316862: step: 1756/533, loss: 0.0004161128308624029
2023-01-24 09:42:54.420356: step: 1760/533, loss: 0.005016508512198925
2023-01-24 09:42:55.543799: step: 1764/533, loss: 0.011855932883918285
2023-01-24 09:42:56.639743: step: 1768/533, loss: 0.02886717952787876
2023-01-24 09:42:57.729922: step: 1772/533, loss: 0.00011155694664921612
2023-01-24 09:42:58.825778: step: 1776/533, loss: 0.004687306471168995
2023-01-24 09:42:59.932431: step: 1780/533, loss: 0.0018492075614631176
2023-01-24 09:43:01.030158: step: 1784/533, loss: 0.004652804229408503
2023-01-24 09:43:02.126843: step: 1788/533, loss: 0.0024371095933020115
2023-01-24 09:43:03.218760: step: 1792/533, loss: 0.015656063333153725
2023-01-24 09:43:04.314490: step: 1796/533, loss: 0.01406926941126585
2023-01-24 09:43:05.406255: step: 1800/533, loss: 0.010150215588510036
2023-01-24 09:43:06.527919: step: 1804/533, loss: 0.0032371829729527235
2023-01-24 09:43:07.632568: step: 1808/533, loss: 0.03526343032717705
2023-01-24 09:43:08.757945: step: 1812/533, loss: 0.006122988648712635
2023-01-24 09:43:09.876125: step: 1816/533, loss: 0.0013521341606974602
2023-01-24 09:43:11.001857: step: 1820/533, loss: 0.00546457851305604
2023-01-24 09:43:12.112881: step: 1824/533, loss: 0.0020414988975971937
2023-01-24 09:43:13.220005: step: 1828/533, loss: 0.0032918185461312532
2023-01-24 09:43:14.331564: step: 1832/533, loss: 0.0025139551144093275
2023-01-24 09:43:15.411204: step: 1836/533, loss: 0.001813585520721972
2023-01-24 09:43:16.515203: step: 1840/533, loss: 0.0019647893495857716
2023-01-24 09:43:17.596242: step: 1844/533, loss: 0.0022341220173984766
2023-01-24 09:43:18.671624: step: 1848/533, loss: 0.021449264138936996
2023-01-24 09:43:19.798266: step: 1852/533, loss: 0.0021347154397517443
2023-01-24 09:43:20.857360: step: 1856/533, loss: 3.961675247410312e-06
2023-01-24 09:43:21.968500: step: 1860/533, loss: 0.0011613235110417008
2023-01-24 09:43:23.057514: step: 1864/533, loss: 0.003081898670643568
2023-01-24 09:43:24.143108: step: 1868/533, loss: 0.0019843089394271374
2023-01-24 09:43:25.240669: step: 1872/533, loss: 0.000726963859051466
2023-01-24 09:43:26.326875: step: 1876/533, loss: 0.0002846642746590078
2023-01-24 09:43:27.414062: step: 1880/533, loss: 0.005255353171378374
2023-01-24 09:43:28.502208: step: 1884/533, loss: 0.003103154245764017
2023-01-24 09:43:29.594275: step: 1888/533, loss: 0.0036544990725815296
2023-01-24 09:43:30.678810: step: 1892/533, loss: 0.024762338027358055
2023-01-24 09:43:31.789529: step: 1896/533, loss: 0.00439894013106823
2023-01-24 09:43:32.879709: step: 1900/533, loss: 0.001974341459572315
2023-01-24 09:43:34.000564: step: 1904/533, loss: 0.01946522481739521
2023-01-24 09:43:35.097001: step: 1908/533, loss: 0.000969995919149369
2023-01-24 09:43:36.195378: step: 1912/533, loss: 0.0021651999559253454
2023-01-24 09:43:37.292158: step: 1916/533, loss: 0.00029149636975489557
2023-01-24 09:43:38.375872: step: 1920/533, loss: 0.005681419745087624
2023-01-24 09:43:39.458825: step: 1924/533, loss: 5.650767889164854e-07
2023-01-24 09:43:40.554838: step: 1928/533, loss: 0.0043229954317212105
2023-01-24 09:43:41.655494: step: 1932/533, loss: 0.0030707060359418392
2023-01-24 09:43:42.759531: step: 1936/533, loss: 0.001978139625862241
2023-01-24 09:43:43.836416: step: 1940/533, loss: 0.010794850997626781
2023-01-24 09:43:44.961714: step: 1944/533, loss: 0.0033245037775486708
2023-01-24 09:43:46.088080: step: 1948/533, loss: 0.0039625284262001514
2023-01-24 09:43:47.200408: step: 1952/533, loss: 0.0048455242067575455
2023-01-24 09:43:48.310981: step: 1956/533, loss: 0.001169305294752121
2023-01-24 09:43:49.385424: step: 1960/533, loss: 0.0031322434078902006
2023-01-24 09:43:50.482125: step: 1964/533, loss: 0.00042858414235524833
2023-01-24 09:43:51.580402: step: 1968/533, loss: 2.3189479179563932e-05
2023-01-24 09:43:52.669651: step: 1972/533, loss: 7.164699127315544e-06
2023-01-24 09:43:53.781479: step: 1976/533, loss: 0.00019621619139797986
2023-01-24 09:43:54.897303: step: 1980/533, loss: 0.002533025573939085
2023-01-24 09:43:55.990123: step: 1984/533, loss: 0.008151463232934475
2023-01-24 09:43:57.078957: step: 1988/533, loss: 0.002498792950063944
2023-01-24 09:43:58.153038: step: 1992/533, loss: 0.003166694426909089
2023-01-24 09:43:59.270231: step: 1996/533, loss: 0.0035412039142102003
2023-01-24 09:44:00.386254: step: 2000/533, loss: 0.004534178413450718
2023-01-24 09:44:01.490192: step: 2004/533, loss: 0.004485357087105513
2023-01-24 09:44:02.580173: step: 2008/533, loss: 0.0019477077294141054
2023-01-24 09:44:03.671022: step: 2012/533, loss: 0.0074815209954977036
2023-01-24 09:44:04.766231: step: 2016/533, loss: 0.0007420096662826836
2023-01-24 09:44:05.868213: step: 2020/533, loss: 0.00477526243776083
2023-01-24 09:44:06.957607: step: 2024/533, loss: 0.002847573719918728
2023-01-24 09:44:08.067157: step: 2028/533, loss: 0.006260199937969446
2023-01-24 09:44:09.154258: step: 2032/533, loss: 0.001271393266506493
2023-01-24 09:44:10.236586: step: 2036/533, loss: 0.007010755594819784
2023-01-24 09:44:11.316354: step: 2040/533, loss: 0.0009448737255297601
2023-01-24 09:44:12.418682: step: 2044/533, loss: 0.006298178341239691
2023-01-24 09:44:13.516766: step: 2048/533, loss: 0.0024006739258766174
2023-01-24 09:44:14.632732: step: 2052/533, loss: 0.0005495974910445511
2023-01-24 09:44:15.719494: step: 2056/533, loss: 0.003964740317314863
2023-01-24 09:44:16.834645: step: 2060/533, loss: 0.0018671418074518442
2023-01-24 09:44:17.919667: step: 2064/533, loss: 0.0006631906726397574
2023-01-24 09:44:19.048034: step: 2068/533, loss: 8.174024696927518e-05
2023-01-24 09:44:20.130884: step: 2072/533, loss: 0.0016061882488429546
2023-01-24 09:44:21.213416: step: 2076/533, loss: 0.004092411138117313
2023-01-24 09:44:22.299775: step: 2080/533, loss: 0.006743691861629486
2023-01-24 09:44:23.400831: step: 2084/533, loss: 0.012733488343656063
2023-01-24 09:44:24.497621: step: 2088/533, loss: 0.00735132023692131
2023-01-24 09:44:25.596087: step: 2092/533, loss: 0.006029689684510231
2023-01-24 09:44:26.687307: step: 2096/533, loss: 0.004430215805768967
2023-01-24 09:44:27.766365: step: 2100/533, loss: 0.00036081409780308604
2023-01-24 09:44:28.856740: step: 2104/533, loss: 0.0019843224436044693
2023-01-24 09:44:29.966584: step: 2108/533, loss: 0.0012128649977967143
2023-01-24 09:44:31.089002: step: 2112/533, loss: 0.006904556415975094
2023-01-24 09:44:32.176894: step: 2116/533, loss: 0.0043343654833734035
2023-01-24 09:44:33.277925: step: 2120/533, loss: 0.006374252960085869
2023-01-24 09:44:34.361763: step: 2124/533, loss: 0.009752770885825157
2023-01-24 09:44:35.493228: step: 2128/533, loss: 0.007875858806073666
2023-01-24 09:44:36.595572: step: 2132/533, loss: 0.009636057540774345
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37721920289855077, 'r': 0.32926154332700824, 'f1': 0.35161263086795}, 'combined': 0.2590829911658579, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39515254339595385, 'r': 0.3601967414801579, 'f1': 0.3768658059752155}, 'combined': 0.25124387065014364, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3563019057831009, 'r': 0.31979279209754596, 'f1': 0.3370616028708135}, 'combined': 0.24836118106270466, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38771657788894903, 'r': 0.3105460667129755, 'f1': 0.3448669614324555}, 'combined': 0.22991130762163695, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34237036810566224, 'r': 0.3124860475499498, 'f1': 0.3267463235294118}, 'combined': 0.2407604489164087, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38158917418386945, 'r': 0.3467324707728429, 'f1': 0.363326720003785}, 'combined': 0.24221781333585662, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 09:46:58.257002: step: 4/533, loss: 0.004642787855118513
2023-01-24 09:46:59.337132: step: 8/533, loss: 0.0042380220256745815
2023-01-24 09:47:00.413546: step: 12/533, loss: 0.0013811232056468725
2023-01-24 09:47:01.518470: step: 16/533, loss: 0.00889498833566904
2023-01-24 09:47:02.598896: step: 20/533, loss: 0.0230429507791996
2023-01-24 09:47:03.674524: step: 24/533, loss: 0.0011070636101067066
2023-01-24 09:47:04.758832: step: 28/533, loss: 0.001165607594884932
2023-01-24 09:47:05.825523: step: 32/533, loss: 0.0012389898765832186
2023-01-24 09:47:06.892641: step: 36/533, loss: 0.0002702665515244007
2023-01-24 09:47:07.965167: step: 40/533, loss: 0.0009135964210145175
2023-01-24 09:47:09.029377: step: 44/533, loss: 0.005618186667561531
2023-01-24 09:47:10.142441: step: 48/533, loss: 0.009635942988097668
2023-01-24 09:47:11.237812: step: 52/533, loss: 0.005092759616672993
2023-01-24 09:47:12.332825: step: 56/533, loss: 0.0021004918962717056
2023-01-24 09:47:13.417562: step: 60/533, loss: 0.00017284016939811409
2023-01-24 09:47:14.491248: step: 64/533, loss: 0.007907027378678322
2023-01-24 09:47:15.571490: step: 68/533, loss: 0.007110178470611572
2023-01-24 09:47:16.647805: step: 72/533, loss: 0.0045658741146326065
2023-01-24 09:47:17.733912: step: 76/533, loss: 0.035479068756103516
2023-01-24 09:47:18.842577: step: 80/533, loss: 0.006371338851749897
2023-01-24 09:47:19.914077: step: 84/533, loss: 0.012587880715727806
2023-01-24 09:47:21.030784: step: 88/533, loss: 0.006573655642569065
2023-01-24 09:47:22.106215: step: 92/533, loss: 0.0003099156601820141
2023-01-24 09:47:23.192515: step: 96/533, loss: 9.653872984927148e-05
2023-01-24 09:47:24.294970: step: 100/533, loss: 0.0055318609811365604
2023-01-24 09:47:25.394438: step: 104/533, loss: 0.005305789411067963
2023-01-24 09:47:26.476301: step: 108/533, loss: 0.026445116847753525
2023-01-24 09:47:27.560891: step: 112/533, loss: 0.0017025062115862966
2023-01-24 09:47:28.642783: step: 116/533, loss: 0.0009977588197216392
2023-01-24 09:47:29.758407: step: 120/533, loss: 0.034979868680238724
2023-01-24 09:47:30.840247: step: 124/533, loss: 0.046214617788791656
2023-01-24 09:47:31.899261: step: 128/533, loss: 0.004699335433542728
2023-01-24 09:47:33.008240: step: 132/533, loss: 0.005981661379337311
2023-01-24 09:47:34.103142: step: 136/533, loss: 0.0031148307025432587
2023-01-24 09:47:35.196610: step: 140/533, loss: 0.0003748050075955689
2023-01-24 09:47:36.287636: step: 144/533, loss: 0.003077451605349779
2023-01-24 09:47:37.380216: step: 148/533, loss: 0.001654106075875461
2023-01-24 09:47:38.501576: step: 152/533, loss: 0.01048434991389513
2023-01-24 09:47:39.594755: step: 156/533, loss: 0.004062238615006208
2023-01-24 09:47:40.702175: step: 160/533, loss: 0.0002877771039493382
2023-01-24 09:47:41.787465: step: 164/533, loss: 0.006677479483187199
2023-01-24 09:47:42.914357: step: 168/533, loss: 0.00467509962618351
2023-01-24 09:47:44.036173: step: 172/533, loss: 0.001585502875968814
2023-01-24 09:47:45.145253: step: 176/533, loss: 0.005515960976481438
2023-01-24 09:47:46.239007: step: 180/533, loss: 0.01355141494423151
2023-01-24 09:47:47.333171: step: 184/533, loss: 0.05194706469774246
2023-01-24 09:47:48.411173: step: 188/533, loss: 0.011446144431829453
2023-01-24 09:47:49.503038: step: 192/533, loss: 0.005525769665837288
2023-01-24 09:47:50.605227: step: 196/533, loss: 0.007917615585029125
2023-01-24 09:47:51.694167: step: 200/533, loss: 0.01816740073263645
2023-01-24 09:47:52.766499: step: 204/533, loss: 0.0019241698319092393
2023-01-24 09:47:53.850510: step: 208/533, loss: 0.0003951963735744357
2023-01-24 09:47:54.935575: step: 212/533, loss: 0.0009698979556560516
2023-01-24 09:47:56.024238: step: 216/533, loss: 0.00046733394265174866
2023-01-24 09:47:57.129598: step: 220/533, loss: 0.0023697693832218647
2023-01-24 09:47:58.238048: step: 224/533, loss: 0.00017003829998429865
2023-01-24 09:47:59.357241: step: 228/533, loss: 0.0016359906876459718
2023-01-24 09:48:00.456918: step: 232/533, loss: 0.009897015057504177
2023-01-24 09:48:01.557141: step: 236/533, loss: 0.0020268128719180822
2023-01-24 09:48:02.667395: step: 240/533, loss: 0.006038276478648186
2023-01-24 09:48:03.752322: step: 244/533, loss: 0.0005829042638652027
2023-01-24 09:48:04.834435: step: 248/533, loss: 0.0014180411817505956
2023-01-24 09:48:05.931110: step: 252/533, loss: 0.0023875043261796236
2023-01-24 09:48:07.056765: step: 256/533, loss: 0.03412700071930885
2023-01-24 09:48:08.130228: step: 260/533, loss: 0.005486309062689543
2023-01-24 09:48:09.219571: step: 264/533, loss: 0.0028211153112351894
2023-01-24 09:48:10.327536: step: 268/533, loss: 0.004483514931052923
2023-01-24 09:48:11.436234: step: 272/533, loss: 0.005611533764749765
2023-01-24 09:48:12.532353: step: 276/533, loss: 0.0033813256304711103
2023-01-24 09:48:13.645514: step: 280/533, loss: 0.0011388449929654598
2023-01-24 09:48:14.762711: step: 284/533, loss: 0.0017817965708673
2023-01-24 09:48:15.855257: step: 288/533, loss: 0.00869556050747633
2023-01-24 09:48:16.934950: step: 292/533, loss: 0.0007774020195938647
2023-01-24 09:48:18.025958: step: 296/533, loss: 0.001493919175118208
2023-01-24 09:48:19.107641: step: 300/533, loss: 0.01093620527535677
2023-01-24 09:48:20.208546: step: 304/533, loss: 0.00013686220336239785
2023-01-24 09:48:21.335717: step: 308/533, loss: 0.002293609781190753
2023-01-24 09:48:22.422055: step: 312/533, loss: 0.0017688825028017163
2023-01-24 09:48:23.539259: step: 316/533, loss: 0.00696111936122179
2023-01-24 09:48:24.674742: step: 320/533, loss: 0.007227766327559948
2023-01-24 09:48:25.768705: step: 324/533, loss: 0.015504234470427036
2023-01-24 09:48:26.880190: step: 328/533, loss: 0.006478292401880026
2023-01-24 09:48:27.996353: step: 332/533, loss: 0.001975342631340027
2023-01-24 09:48:29.097373: step: 336/533, loss: 0.0004737675189971924
2023-01-24 09:48:30.213172: step: 340/533, loss: 0.006680705584585667
2023-01-24 09:48:31.316278: step: 344/533, loss: 0.001273679663427174
2023-01-24 09:48:32.390877: step: 348/533, loss: 0.003966344520449638
2023-01-24 09:48:33.489612: step: 352/533, loss: 0.002248354023322463
2023-01-24 09:48:34.585192: step: 356/533, loss: 0.002159616444259882
2023-01-24 09:48:35.682021: step: 360/533, loss: 0.035607729107141495
2023-01-24 09:48:36.769533: step: 364/533, loss: 0.0026232032105326653
2023-01-24 09:48:37.863863: step: 368/533, loss: 0.0003496787394396961
2023-01-24 09:48:38.993091: step: 372/533, loss: 0.0024271984584629536
2023-01-24 09:48:40.073936: step: 376/533, loss: 0.005492524243891239
2023-01-24 09:48:41.171987: step: 380/533, loss: 0.0007889361586421728
2023-01-24 09:48:42.282291: step: 384/533, loss: 0.004286116920411587
2023-01-24 09:48:43.378858: step: 388/533, loss: 0.005535990931093693
2023-01-24 09:48:44.499072: step: 392/533, loss: 0.025218002498149872
2023-01-24 09:48:45.608387: step: 396/533, loss: 0.006231311243027449
2023-01-24 09:48:46.693859: step: 400/533, loss: 0.0027945530600845814
2023-01-24 09:48:47.812838: step: 404/533, loss: 0.01172003336250782
2023-01-24 09:48:48.909668: step: 408/533, loss: 4.976150376023725e-05
2023-01-24 09:48:50.017826: step: 412/533, loss: 0.007846618071198463
2023-01-24 09:48:51.091289: step: 416/533, loss: 0.0031642864923924208
2023-01-24 09:48:52.193105: step: 420/533, loss: 0.0003526798100210726
2023-01-24 09:48:53.294732: step: 424/533, loss: 0.005897599272429943
2023-01-24 09:48:54.373094: step: 428/533, loss: 0.0006018753629177809
2023-01-24 09:48:55.453174: step: 432/533, loss: 0.002098051132634282
2023-01-24 09:48:56.554479: step: 436/533, loss: 0.009074848145246506
2023-01-24 09:48:57.646891: step: 440/533, loss: 0.009605534374713898
2023-01-24 09:48:58.768855: step: 444/533, loss: 0.022999662905931473
2023-01-24 09:48:59.864181: step: 448/533, loss: 0.005497829057276249
2023-01-24 09:49:00.993191: step: 452/533, loss: 8.561968911635631e-07
2023-01-24 09:49:02.058527: step: 456/533, loss: 0.016701187938451767
2023-01-24 09:49:03.144045: step: 460/533, loss: 4.8721369239501655e-05
2023-01-24 09:49:04.228534: step: 464/533, loss: 0.0014615383697673678
2023-01-24 09:49:05.335787: step: 468/533, loss: 0.005763007327914238
2023-01-24 09:49:06.429251: step: 472/533, loss: 8.52637822390534e-05
2023-01-24 09:49:07.529267: step: 476/533, loss: 0.00013467016106005758
2023-01-24 09:49:08.623459: step: 480/533, loss: 0.009257345460355282
2023-01-24 09:49:09.705337: step: 484/533, loss: 0.0002018270461121574
2023-01-24 09:49:10.829478: step: 488/533, loss: 0.001709848758764565
2023-01-24 09:49:11.933972: step: 492/533, loss: 0.0004214384825900197
2023-01-24 09:49:13.019575: step: 496/533, loss: 0.001691313344053924
2023-01-24 09:49:14.098955: step: 500/533, loss: 0.0019610992167145014
2023-01-24 09:49:15.210302: step: 504/533, loss: 0.005715094041079283
2023-01-24 09:49:16.330637: step: 508/533, loss: 0.00523547874763608
2023-01-24 09:49:17.452113: step: 512/533, loss: 0.0018539009615778923
2023-01-24 09:49:18.548322: step: 516/533, loss: 0.004026525653898716
2023-01-24 09:49:19.637416: step: 520/533, loss: 0.0023068436421453953
2023-01-24 09:49:20.749265: step: 524/533, loss: 0.005682474467903376
2023-01-24 09:49:21.844026: step: 528/533, loss: 0.0009728763834573328
2023-01-24 09:49:22.935165: step: 532/533, loss: 0.0008224290795624256
2023-01-24 09:49:24.023675: step: 536/533, loss: 0.004581208806484938
2023-01-24 09:49:25.125964: step: 540/533, loss: 0.002389604225754738
2023-01-24 09:49:26.226169: step: 544/533, loss: 0.003109780140221119
2023-01-24 09:49:27.325974: step: 548/533, loss: 0.0030403900891542435
2023-01-24 09:49:28.430106: step: 552/533, loss: 0.0004706977924797684
2023-01-24 09:49:29.519827: step: 556/533, loss: 0.0001463730732211843
2023-01-24 09:49:30.628182: step: 560/533, loss: 0.0043122307397425175
2023-01-24 09:49:31.753819: step: 564/533, loss: 0.002060150960460305
2023-01-24 09:49:32.864290: step: 568/533, loss: 0.005182350520044565
2023-01-24 09:49:33.971777: step: 572/533, loss: 0.0030952466186136007
2023-01-24 09:49:35.067147: step: 576/533, loss: 0.00015296571655198932
2023-01-24 09:49:36.174114: step: 580/533, loss: 0.0059334333054721355
2023-01-24 09:49:37.280493: step: 584/533, loss: 0.0012150227557867765
2023-01-24 09:49:38.395311: step: 588/533, loss: 0.007207000628113747
2023-01-24 09:49:39.471381: step: 592/533, loss: 6.773974746465683e-05
2023-01-24 09:49:40.565612: step: 596/533, loss: 0.004725846461951733
2023-01-24 09:49:41.628247: step: 600/533, loss: 0.00041605590377002954
2023-01-24 09:49:42.740336: step: 604/533, loss: 0.00012091467942809686
2023-01-24 09:49:43.833410: step: 608/533, loss: 0.007607077714055777
2023-01-24 09:49:44.907528: step: 612/533, loss: 2.6248242193105398e-06
2023-01-24 09:49:46.006639: step: 616/533, loss: 0.0016710207564756274
2023-01-24 09:49:47.158928: step: 620/533, loss: 0.004406934604048729
2023-01-24 09:49:48.256094: step: 624/533, loss: 7.957691559568048e-05
2023-01-24 09:49:49.358129: step: 628/533, loss: 0.006411142647266388
2023-01-24 09:49:50.455739: step: 632/533, loss: 0.0001035914319800213
2023-01-24 09:49:51.549175: step: 636/533, loss: 0.002034962410107255
2023-01-24 09:49:52.621012: step: 640/533, loss: 0.0009061702294275165
2023-01-24 09:49:53.708119: step: 644/533, loss: 0.0040790312923491
2023-01-24 09:49:54.824238: step: 648/533, loss: 0.010422549210488796
2023-01-24 09:49:55.931277: step: 652/533, loss: 0.012470975518226624
2023-01-24 09:49:57.014678: step: 656/533, loss: 0.0001585818245075643
2023-01-24 09:49:58.136717: step: 660/533, loss: 0.0006977925077080727
2023-01-24 09:49:59.231674: step: 664/533, loss: 5.354552195058204e-05
2023-01-24 09:50:00.326513: step: 668/533, loss: 0.0018985543865710497
2023-01-24 09:50:01.432092: step: 672/533, loss: 0.0022382279857993126
2023-01-24 09:50:02.535691: step: 676/533, loss: 0.0029381304048001766
2023-01-24 09:50:03.621129: step: 680/533, loss: 0.007771194912493229
2023-01-24 09:50:04.723308: step: 684/533, loss: 0.007026690058410168
2023-01-24 09:50:05.823435: step: 688/533, loss: 0.002659125253558159
2023-01-24 09:50:06.946954: step: 692/533, loss: 0.02850530296564102
2023-01-24 09:50:08.048665: step: 696/533, loss: 0.004601944237947464
2023-01-24 09:50:09.153940: step: 700/533, loss: 0.006608284078538418
2023-01-24 09:50:10.235164: step: 704/533, loss: 0.009377521462738514
2023-01-24 09:50:11.336605: step: 708/533, loss: 2.0932442566845566e-05
2023-01-24 09:50:12.417435: step: 712/533, loss: 0.0034799673594534397
2023-01-24 09:50:13.516850: step: 716/533, loss: 1.523418632132234e-05
2023-01-24 09:50:14.610726: step: 720/533, loss: 0.00044973997864872217
2023-01-24 09:50:15.699596: step: 724/533, loss: 0.00191646465100348
2023-01-24 09:50:16.788503: step: 728/533, loss: 3.927987199858762e-05
2023-01-24 09:50:17.909157: step: 732/533, loss: 0.0033505030442029238
2023-01-24 09:50:19.000210: step: 736/533, loss: 9.219852654496208e-05
2023-01-24 09:50:20.107152: step: 740/533, loss: 0.00025364416069351137
2023-01-24 09:50:21.201594: step: 744/533, loss: 0.00921058189123869
2023-01-24 09:50:22.289012: step: 748/533, loss: 0.0025928206741809845
2023-01-24 09:50:23.377419: step: 752/533, loss: 0.0004282293375581503
2023-01-24 09:50:24.488188: step: 756/533, loss: 0.0032719469163566828
2023-01-24 09:50:25.576969: step: 760/533, loss: 0.0008936317753978074
2023-01-24 09:50:26.668476: step: 764/533, loss: 0.003091009333729744
2023-01-24 09:50:27.746406: step: 768/533, loss: 0.004709113854914904
2023-01-24 09:50:28.837526: step: 772/533, loss: 0.003572245128452778
2023-01-24 09:50:29.941493: step: 776/533, loss: 0.005256059113889933
2023-01-24 09:50:31.030562: step: 780/533, loss: 0.0003918256261385977
2023-01-24 09:50:32.109468: step: 784/533, loss: 0.002033818745985627
2023-01-24 09:50:33.205622: step: 788/533, loss: 0.0007080455543473363
2023-01-24 09:50:34.335305: step: 792/533, loss: 0.0060540675185620785
2023-01-24 09:50:35.432219: step: 796/533, loss: 0.005387973506003618
2023-01-24 09:50:36.531710: step: 800/533, loss: 0.010785789228975773
2023-01-24 09:50:37.627018: step: 804/533, loss: 0.0011016837088391185
2023-01-24 09:50:38.744280: step: 808/533, loss: 0.0018486685585230589
2023-01-24 09:50:39.823355: step: 812/533, loss: 0.003318076254799962
2023-01-24 09:50:40.911611: step: 816/533, loss: 0.0005521344137378037
2023-01-24 09:50:42.001075: step: 820/533, loss: 0.0033604793716222048
2023-01-24 09:50:43.089686: step: 824/533, loss: 0.0014540957054123282
2023-01-24 09:50:44.204514: step: 828/533, loss: 0.0029252851381897926
2023-01-24 09:50:45.285591: step: 832/533, loss: 6.33293382179545e-08
2023-01-24 09:50:46.373158: step: 836/533, loss: 0.004994706716388464
2023-01-24 09:50:47.459930: step: 840/533, loss: 0.00200504157692194
2023-01-24 09:50:48.549899: step: 844/533, loss: 0.015309522859752178
2023-01-24 09:50:49.670017: step: 848/533, loss: 0.0011504695285111666
2023-01-24 09:50:50.775395: step: 852/533, loss: 0.00023968175810296088
2023-01-24 09:50:51.885887: step: 856/533, loss: 0.009278391487896442
2023-01-24 09:50:53.008563: step: 860/533, loss: 0.0014004065888002515
2023-01-24 09:50:54.124679: step: 864/533, loss: 0.0015874359523877501
2023-01-24 09:50:55.236614: step: 868/533, loss: 0.010510061867535114
2023-01-24 09:50:56.336542: step: 872/533, loss: 0.0002641559694893658
2023-01-24 09:50:57.438693: step: 876/533, loss: 0.016338109970092773
2023-01-24 09:50:58.540600: step: 880/533, loss: 0.004392032045871019
2023-01-24 09:50:59.635722: step: 884/533, loss: 0.0008806161349639297
2023-01-24 09:51:00.740805: step: 888/533, loss: 4.9902071623364463e-05
2023-01-24 09:51:01.824291: step: 892/533, loss: 0.004525795113295317
2023-01-24 09:51:02.924252: step: 896/533, loss: 0.0061322543770074844
2023-01-24 09:51:04.021037: step: 900/533, loss: 0.004464881960302591
2023-01-24 09:51:05.112736: step: 904/533, loss: 0.007263854146003723
2023-01-24 09:51:06.228389: step: 908/533, loss: 0.004065243527293205
2023-01-24 09:51:07.306671: step: 912/533, loss: 0.00021325920533854514
2023-01-24 09:51:08.386363: step: 916/533, loss: 0.0005864838021807373
2023-01-24 09:51:09.481835: step: 920/533, loss: 0.0017816167091950774
2023-01-24 09:51:10.591396: step: 924/533, loss: 0.0068408227525651455
2023-01-24 09:51:11.674375: step: 928/533, loss: 0.0004706044855993241
2023-01-24 09:51:12.789175: step: 932/533, loss: 0.0031339137349277735
2023-01-24 09:51:13.901260: step: 936/533, loss: 0.0066862343810498714
2023-01-24 09:51:14.977895: step: 940/533, loss: 0.0030028591863811016
2023-01-24 09:51:16.071242: step: 944/533, loss: 0.0005082470597699285
2023-01-24 09:51:17.170897: step: 948/533, loss: 0.004333869554102421
2023-01-24 09:51:18.271543: step: 952/533, loss: 0.0003605246602091938
2023-01-24 09:51:19.370338: step: 956/533, loss: 0.004059371072798967
2023-01-24 09:51:20.456423: step: 960/533, loss: 2.1898746126680635e-05
2023-01-24 09:51:21.557909: step: 964/533, loss: 0.003783420892432332
2023-01-24 09:51:22.728291: step: 968/533, loss: 0.005082321353256702
2023-01-24 09:51:23.815344: step: 972/533, loss: 0.004534102510660887
2023-01-24 09:51:24.910914: step: 976/533, loss: 0.005286916624754667
2023-01-24 09:51:25.994106: step: 980/533, loss: 0.005270530469715595
2023-01-24 09:51:27.092005: step: 984/533, loss: 0.0015382500132545829
2023-01-24 09:51:28.180192: step: 988/533, loss: 0.00013809918891638517
2023-01-24 09:51:29.289859: step: 992/533, loss: 0.006540811154991388
2023-01-24 09:51:30.390704: step: 996/533, loss: 0.0030747840646654367
2023-01-24 09:51:31.487952: step: 1000/533, loss: 0.011098472401499748
2023-01-24 09:51:32.608613: step: 1004/533, loss: 0.0008736164891161025
2023-01-24 09:51:33.704769: step: 1008/533, loss: 0.005364149808883667
2023-01-24 09:51:34.800082: step: 1012/533, loss: 0.003826503874734044
2023-01-24 09:51:35.896852: step: 1016/533, loss: 0.0019752352964133024
2023-01-24 09:51:37.012130: step: 1020/533, loss: 0.006751165725290775
2023-01-24 09:51:38.109505: step: 1024/533, loss: 0.0055239503271877766
2023-01-24 09:51:39.186787: step: 1028/533, loss: 0.002385033294558525
2023-01-24 09:51:40.283020: step: 1032/533, loss: 0.00956160482019186
2023-01-24 09:51:41.368056: step: 1036/533, loss: 0.006893908604979515
2023-01-24 09:51:42.483623: step: 1040/533, loss: 0.0020833134185522795
2023-01-24 09:51:43.590747: step: 1044/533, loss: 0.002873441204428673
2023-01-24 09:51:44.689409: step: 1048/533, loss: 0.0068705277517437935
2023-01-24 09:51:45.792595: step: 1052/533, loss: 0.0011864552507176995
2023-01-24 09:51:46.877702: step: 1056/533, loss: 0.004692883230745792
2023-01-24 09:51:47.992073: step: 1060/533, loss: 0.010893517173826694
2023-01-24 09:51:49.097488: step: 1064/533, loss: 0.027625778689980507
2023-01-24 09:51:50.206106: step: 1068/533, loss: 0.0039296699687838554
2023-01-24 09:51:51.298326: step: 1072/533, loss: 0.002559104235842824
2023-01-24 09:51:52.408991: step: 1076/533, loss: 0.0012440828140825033
2023-01-24 09:51:53.506453: step: 1080/533, loss: 0.005678507033735514
2023-01-24 09:51:54.606139: step: 1084/533, loss: 0.005662733688950539
2023-01-24 09:51:55.707766: step: 1088/533, loss: 0.0036698849871754646
2023-01-24 09:51:56.810980: step: 1092/533, loss: 0.013403421267867088
2023-01-24 09:51:57.913114: step: 1096/533, loss: 0.005124801769852638
2023-01-24 09:51:58.987316: step: 1100/533, loss: 0.0005794070311821997
2023-01-24 09:52:00.061453: step: 1104/533, loss: 0.0010334710823372006
2023-01-24 09:52:01.173074: step: 1108/533, loss: 0.010906674899160862
2023-01-24 09:52:02.264771: step: 1112/533, loss: 0.005158464424312115
2023-01-24 09:52:03.340524: step: 1116/533, loss: 0.02488597109913826
2023-01-24 09:52:04.448731: step: 1120/533, loss: 0.010795176029205322
2023-01-24 09:52:05.544728: step: 1124/533, loss: 0.0023812204599380493
2023-01-24 09:52:06.609135: step: 1128/533, loss: 3.275966810178943e-05
2023-01-24 09:52:07.679456: step: 1132/533, loss: 0.0025991995353251696
2023-01-24 09:52:08.775704: step: 1136/533, loss: 0.011424358002841473
2023-01-24 09:52:09.874094: step: 1140/533, loss: 0.0031795594841241837
2023-01-24 09:52:10.979874: step: 1144/533, loss: 0.0023868493735790253
2023-01-24 09:52:12.072233: step: 1148/533, loss: 0.0003129100950900465
2023-01-24 09:52:13.156712: step: 1152/533, loss: 0.005316525232046843
2023-01-24 09:52:14.249296: step: 1156/533, loss: 0.007030473090708256
2023-01-24 09:52:15.331247: step: 1160/533, loss: 0.00494907284155488
2023-01-24 09:52:16.428083: step: 1164/533, loss: 0.015128516592085361
2023-01-24 09:52:17.543668: step: 1168/533, loss: 0.0008103975560516119
2023-01-24 09:52:18.638115: step: 1172/533, loss: 0.009715834632515907
2023-01-24 09:52:19.722094: step: 1176/533, loss: 0.001284303842112422
2023-01-24 09:52:20.809843: step: 1180/533, loss: 0.0003198575577698648
2023-01-24 09:52:21.902431: step: 1184/533, loss: 0.0011189812794327736
2023-01-24 09:52:23.007913: step: 1188/533, loss: 0.004146880470216274
2023-01-24 09:52:24.092512: step: 1192/533, loss: 0.002396579133346677
2023-01-24 09:52:25.183364: step: 1196/533, loss: 0.0034002489410340786
2023-01-24 09:52:26.288321: step: 1200/533, loss: 0.019656045362353325
2023-01-24 09:52:27.390557: step: 1204/533, loss: 0.0026881445664912462
2023-01-24 09:52:28.460129: step: 1208/533, loss: 0.0035737408325076103
2023-01-24 09:52:29.560723: step: 1212/533, loss: 0.0030627609230577946
2023-01-24 09:52:30.647328: step: 1216/533, loss: 0.012841791845858097
2023-01-24 09:52:31.753457: step: 1220/533, loss: 0.0007427922100760043
2023-01-24 09:52:32.827654: step: 1224/533, loss: 0.0021177439484745264
2023-01-24 09:52:33.925035: step: 1228/533, loss: 0.044927194714546204
2023-01-24 09:52:35.052473: step: 1232/533, loss: 0.0034336114767938852
2023-01-24 09:52:36.135229: step: 1236/533, loss: 0.003373584011569619
2023-01-24 09:52:37.239581: step: 1240/533, loss: 0.00398977380245924
2023-01-24 09:52:38.350175: step: 1244/533, loss: 0.009282859042286873
2023-01-24 09:52:39.449713: step: 1248/533, loss: 0.004519219975918531
2023-01-24 09:52:40.554767: step: 1252/533, loss: 0.010294519364833832
2023-01-24 09:52:41.651596: step: 1256/533, loss: 7.957263733260334e-05
2023-01-24 09:52:42.750841: step: 1260/533, loss: 0.0033851086627691984
2023-01-24 09:52:43.839561: step: 1264/533, loss: 0.001120443339459598
2023-01-24 09:52:44.939316: step: 1268/533, loss: 0.004258371889591217
2023-01-24 09:52:46.046933: step: 1272/533, loss: 0.002686034422367811
2023-01-24 09:52:47.144291: step: 1276/533, loss: 0.0004837879096157849
2023-01-24 09:52:48.232774: step: 1280/533, loss: 0.002780620474368334
2023-01-24 09:52:49.325281: step: 1284/533, loss: 0.02618834376335144
2023-01-24 09:52:50.468724: step: 1288/533, loss: 0.00401887996122241
2023-01-24 09:52:51.571341: step: 1292/533, loss: 0.0037556407041847706
2023-01-24 09:52:52.685206: step: 1296/533, loss: 0.0005887798615731299
2023-01-24 09:52:53.771463: step: 1300/533, loss: 0.00069751578848809
2023-01-24 09:52:54.897831: step: 1304/533, loss: 0.02456999383866787
2023-01-24 09:52:56.003843: step: 1308/533, loss: 0.02306412346661091
2023-01-24 09:52:57.086303: step: 1312/533, loss: 0.019248709082603455
2023-01-24 09:52:58.180977: step: 1316/533, loss: 0.002775588072836399
2023-01-24 09:52:59.284854: step: 1320/533, loss: 0.05259313806891441
2023-01-24 09:53:00.363427: step: 1324/533, loss: 2.825314186338801e-05
2023-01-24 09:53:01.439231: step: 1328/533, loss: 0.003156710881739855
2023-01-24 09:53:02.559514: step: 1332/533, loss: 0.001099259010516107
2023-01-24 09:53:03.646710: step: 1336/533, loss: 0.0015544056659564376
2023-01-24 09:53:04.767568: step: 1340/533, loss: 0.006473899353295565
2023-01-24 09:53:05.879467: step: 1344/533, loss: 0.004892932716757059
2023-01-24 09:53:06.971340: step: 1348/533, loss: 0.00035454510361887515
2023-01-24 09:53:08.058718: step: 1352/533, loss: 0.0004919866332784295
2023-01-24 09:53:09.152946: step: 1356/533, loss: 0.002446613973006606
2023-01-24 09:53:10.252825: step: 1360/533, loss: 0.012500490061938763
2023-01-24 09:53:11.372341: step: 1364/533, loss: 0.0039536068215966225
2023-01-24 09:53:12.472039: step: 1368/533, loss: 0.009226319380104542
2023-01-24 09:53:13.562193: step: 1372/533, loss: 0.00010264314187224954
2023-01-24 09:53:14.631195: step: 1376/533, loss: 0.006994308903813362
2023-01-24 09:53:15.727141: step: 1380/533, loss: 3.1108088478504214e-06
2023-01-24 09:53:16.818860: step: 1384/533, loss: 0.004497695714235306
2023-01-24 09:53:17.916311: step: 1388/533, loss: 0.004066984169185162
2023-01-24 09:53:19.007220: step: 1392/533, loss: 9.396802488481626e-05
2023-01-24 09:53:20.116649: step: 1396/533, loss: 0.004798862151801586
2023-01-24 09:53:21.196058: step: 1400/533, loss: 0.0031711184419691563
2023-01-24 09:53:22.300368: step: 1404/533, loss: 0.0031452339608222246
2023-01-24 09:53:23.381755: step: 1408/533, loss: 0.00034043824416585267
2023-01-24 09:53:24.478397: step: 1412/533, loss: 0.004051752854138613
2023-01-24 09:53:25.561732: step: 1416/533, loss: 0.005626460071653128
2023-01-24 09:53:26.656907: step: 1420/533, loss: 0.0008271787082776427
2023-01-24 09:53:27.758734: step: 1424/533, loss: 0.0007798072183504701
2023-01-24 09:53:28.885699: step: 1428/533, loss: 0.02283618599176407
2023-01-24 09:53:29.976293: step: 1432/533, loss: 0.0002016763319261372
2023-01-24 09:53:31.061254: step: 1436/533, loss: 0.0026856083422899246
2023-01-24 09:53:32.172420: step: 1440/533, loss: 0.019176537171006203
2023-01-24 09:53:33.274995: step: 1444/533, loss: 0.0057919807732105255
2023-01-24 09:53:34.376451: step: 1448/533, loss: 0.0029484578408300877
2023-01-24 09:53:35.449530: step: 1452/533, loss: 0.017066285014152527
2023-01-24 09:53:36.527980: step: 1456/533, loss: 0.02423667535185814
2023-01-24 09:53:37.617100: step: 1460/533, loss: 0.0011075719958171248
2023-01-24 09:53:38.721713: step: 1464/533, loss: 0.019958244636654854
2023-01-24 09:53:39.825909: step: 1468/533, loss: 0.01447628065943718
2023-01-24 09:53:40.927599: step: 1472/533, loss: 0.0032117071095854044
2023-01-24 09:53:42.012927: step: 1476/533, loss: 0.0113234743475914
2023-01-24 09:53:43.131470: step: 1480/533, loss: 0.005681568291038275
2023-01-24 09:53:44.245443: step: 1484/533, loss: 0.007408827543258667
2023-01-24 09:53:45.349321: step: 1488/533, loss: 0.00023793835134711117
2023-01-24 09:53:46.446801: step: 1492/533, loss: 0.005543272010982037
2023-01-24 09:53:47.536630: step: 1496/533, loss: 0.0005621587624773383
2023-01-24 09:53:48.642560: step: 1500/533, loss: 0.001052303472533822
2023-01-24 09:53:49.748157: step: 1504/533, loss: 0.005539839155972004
2023-01-24 09:53:50.831870: step: 1508/533, loss: 0.0006021801964379847
2023-01-24 09:53:51.952672: step: 1512/533, loss: 0.002916711615398526
2023-01-24 09:53:53.053122: step: 1516/533, loss: 0.008573983795940876
2023-01-24 09:53:54.129740: step: 1520/533, loss: 0.0009496908751316369
2023-01-24 09:53:55.225495: step: 1524/533, loss: 0.008933279663324356
2023-01-24 09:53:56.341809: step: 1528/533, loss: 0.005476103629916906
2023-01-24 09:53:57.433897: step: 1532/533, loss: 0.006011069752275944
2023-01-24 09:53:58.524578: step: 1536/533, loss: 0.0030837992671877146
2023-01-24 09:53:59.613260: step: 1540/533, loss: 0.0009466426563449204
2023-01-24 09:54:00.717804: step: 1544/533, loss: 0.005486219190061092
2023-01-24 09:54:01.813063: step: 1548/533, loss: 0.005362777970731258
2023-01-24 09:54:02.912461: step: 1552/533, loss: 0.002726495498791337
2023-01-24 09:54:03.987370: step: 1556/533, loss: 0.005116560496389866
2023-01-24 09:54:05.099119: step: 1560/533, loss: 0.0015097804134711623
2023-01-24 09:54:06.184253: step: 1564/533, loss: 0.00042100888094864786
2023-01-24 09:54:07.281451: step: 1568/533, loss: 0.004275943618267775
2023-01-24 09:54:08.393012: step: 1572/533, loss: 0.004444078542292118
2023-01-24 09:54:09.487445: step: 1576/533, loss: 0.003720453940331936
2023-01-24 09:54:10.585291: step: 1580/533, loss: 0.0013273685472086072
2023-01-24 09:54:11.671584: step: 1584/533, loss: 0.00017654901603236794
2023-01-24 09:54:12.758457: step: 1588/533, loss: 0.005267465487122536
2023-01-24 09:54:13.891941: step: 1592/533, loss: 0.005125822499394417
2023-01-24 09:54:15.028171: step: 1596/533, loss: 0.00835886038839817
2023-01-24 09:54:16.127411: step: 1600/533, loss: 0.005547842476516962
2023-01-24 09:54:17.244298: step: 1604/533, loss: 0.012390973046422005
2023-01-24 09:54:18.340469: step: 1608/533, loss: 0.012000452727079391
2023-01-24 09:54:19.448831: step: 1612/533, loss: 0.01474769413471222
2023-01-24 09:54:20.537386: step: 1616/533, loss: 0.012903259135782719
2023-01-24 09:54:21.617231: step: 1620/533, loss: 0.0065773483365774155
2023-01-24 09:54:22.724048: step: 1624/533, loss: 1.2575702385220211e-05
2023-01-24 09:54:23.851020: step: 1628/533, loss: 0.004026269074529409
2023-01-24 09:54:24.954482: step: 1632/533, loss: 0.0026223582681268454
2023-01-24 09:54:26.063235: step: 1636/533, loss: 0.005184705834835768
2023-01-24 09:54:27.175588: step: 1640/533, loss: 0.001111309276893735
2023-01-24 09:54:28.248756: step: 1644/533, loss: 0.0031127226538956165
2023-01-24 09:54:29.354568: step: 1648/533, loss: 0.005620947107672691
2023-01-24 09:54:30.453447: step: 1652/533, loss: 0.00027842592680826783
2023-01-24 09:54:31.560820: step: 1656/533, loss: 0.00011178318527527153
2023-01-24 09:54:32.650938: step: 1660/533, loss: 0.005421430803835392
2023-01-24 09:54:33.732647: step: 1664/533, loss: 0.0010394853306934237
2023-01-24 09:54:34.820879: step: 1668/533, loss: 0.0058592744171619415
2023-01-24 09:54:35.902850: step: 1672/533, loss: 0.0007755936239846051
2023-01-24 09:54:37.005452: step: 1676/533, loss: 0.004990776069462299
2023-01-24 09:54:38.078024: step: 1680/533, loss: 0.005050123203545809
2023-01-24 09:54:39.168838: step: 1684/533, loss: 0.0037893597036600113
2023-01-24 09:54:40.270168: step: 1688/533, loss: 0.0009316328214481473
2023-01-24 09:54:41.370068: step: 1692/533, loss: 0.0007011006237007678
2023-01-24 09:54:42.467010: step: 1696/533, loss: 0.03676219657063484
2023-01-24 09:54:43.569505: step: 1700/533, loss: 0.0007793661789037287
2023-01-24 09:54:44.643530: step: 1704/533, loss: 0.007743233349174261
2023-01-24 09:54:45.750404: step: 1708/533, loss: 0.017983341589570045
2023-01-24 09:54:46.841228: step: 1712/533, loss: 0.005512095056474209
2023-01-24 09:54:47.948017: step: 1716/533, loss: 0.002964372280985117
2023-01-24 09:54:49.040327: step: 1720/533, loss: 0.011980078183114529
2023-01-24 09:54:50.136638: step: 1724/533, loss: 0.0007291572401300073
2023-01-24 09:54:51.232159: step: 1728/533, loss: 0.005544681567698717
2023-01-24 09:54:52.332544: step: 1732/533, loss: 0.00542797427624464
2023-01-24 09:54:53.414159: step: 1736/533, loss: 0.0012486664345487952
2023-01-24 09:54:54.502330: step: 1740/533, loss: 0.0013879829784855247
2023-01-24 09:54:55.609331: step: 1744/533, loss: 0.004642318934202194
2023-01-24 09:54:56.725778: step: 1748/533, loss: 0.041004374623298645
2023-01-24 09:54:57.850728: step: 1752/533, loss: 6.8694404035341e-05
2023-01-24 09:54:58.998844: step: 1756/533, loss: 0.0009901407174766064
2023-01-24 09:55:00.097704: step: 1760/533, loss: 0.032190557569265366
2023-01-24 09:55:01.187686: step: 1764/533, loss: 0.004202557262033224
2023-01-24 09:55:02.278566: step: 1768/533, loss: 0.01192536111921072
2023-01-24 09:55:03.381049: step: 1772/533, loss: 0.004640738479793072
2023-01-24 09:55:04.474921: step: 1776/533, loss: 0.0014679827727377415
2023-01-24 09:55:05.568522: step: 1780/533, loss: 0.0007155884522944689
2023-01-24 09:55:06.656826: step: 1784/533, loss: 0.020500382408499718
2023-01-24 09:55:07.756895: step: 1788/533, loss: 0.020863482728600502
2023-01-24 09:55:08.874547: step: 1792/533, loss: 0.0010502899531275034
2023-01-24 09:55:09.973367: step: 1796/533, loss: 0.009378473274409771
2023-01-24 09:55:11.076547: step: 1800/533, loss: 0.00971035473048687
2023-01-24 09:55:12.170387: step: 1804/533, loss: 0.0023945854045450687
2023-01-24 09:55:13.276050: step: 1808/533, loss: 0.011558703146874905
2023-01-24 09:55:14.401251: step: 1812/533, loss: 0.0020034813787788153
2023-01-24 09:55:15.490384: step: 1816/533, loss: 0.002887313487008214
2023-01-24 09:55:16.588099: step: 1820/533, loss: 0.0028799395076930523
2023-01-24 09:55:17.692157: step: 1824/533, loss: 0.0001772477407939732
2023-01-24 09:55:18.787314: step: 1828/533, loss: 0.0012629746925085783
2023-01-24 09:55:19.901936: step: 1832/533, loss: 7.215770892798901e-06
2023-01-24 09:55:20.985548: step: 1836/533, loss: 0.0006982661434449255
2023-01-24 09:55:22.080982: step: 1840/533, loss: 0.003910706378519535
2023-01-24 09:55:23.162879: step: 1844/533, loss: 0.001769261434674263
2023-01-24 09:55:24.268526: step: 1848/533, loss: 0.015199275687336922
2023-01-24 09:55:25.380923: step: 1852/533, loss: 0.0016406280919909477
2023-01-24 09:55:26.478500: step: 1856/533, loss: 0.0017196130938827991
2023-01-24 09:55:27.577109: step: 1860/533, loss: 0.009553959593176842
2023-01-24 09:55:28.668809: step: 1864/533, loss: 0.0035231998190283775
2023-01-24 09:55:29.739355: step: 1868/533, loss: 0.0034083197824656963
2023-01-24 09:55:30.852509: step: 1872/533, loss: 0.01761735789477825
2023-01-24 09:55:31.961982: step: 1876/533, loss: 0.015242472290992737
2023-01-24 09:55:33.057783: step: 1880/533, loss: 0.003416922874748707
2023-01-24 09:55:34.160611: step: 1884/533, loss: 0.0031704914290457964
2023-01-24 09:55:35.237402: step: 1888/533, loss: 0.009121900424361229
2023-01-24 09:55:36.331336: step: 1892/533, loss: 0.0014389894204214215
2023-01-24 09:55:37.418878: step: 1896/533, loss: 0.0032174671068787575
2023-01-24 09:55:38.531034: step: 1900/533, loss: 0.0013458527391776443
2023-01-24 09:55:39.636708: step: 1904/533, loss: 0.004142499528825283
2023-01-24 09:55:40.721267: step: 1908/533, loss: 0.0007871268317103386
2023-01-24 09:55:41.805377: step: 1912/533, loss: 0.0033629639074206352
2023-01-24 09:55:42.890567: step: 1916/533, loss: 0.000362435239367187
2023-01-24 09:55:43.945229: step: 1920/533, loss: 0.004283709917217493
2023-01-24 09:55:45.038285: step: 1924/533, loss: 0.003644602606073022
2023-01-24 09:55:46.125483: step: 1928/533, loss: 0.0015798425301909447
2023-01-24 09:55:47.247181: step: 1932/533, loss: 0.004316437523812056
2023-01-24 09:55:48.340800: step: 1936/533, loss: 0.006086855195462704
2023-01-24 09:55:49.448958: step: 1940/533, loss: 0.004294418729841709
2023-01-24 09:55:50.543928: step: 1944/533, loss: 0.004562284331768751
2023-01-24 09:55:51.660995: step: 1948/533, loss: 0.012311648577451706
2023-01-24 09:55:52.770819: step: 1952/533, loss: 0.005319316405802965
2023-01-24 09:55:53.865116: step: 1956/533, loss: 0.0031219234224408865
2023-01-24 09:55:54.967721: step: 1960/533, loss: 0.018420642241835594
2023-01-24 09:55:56.063417: step: 1964/533, loss: 0.0013132343301549554
2023-01-24 09:55:57.157565: step: 1968/533, loss: 0.0012210148852318525
2023-01-24 09:55:58.266171: step: 1972/533, loss: 0.003999612294137478
2023-01-24 09:55:59.350569: step: 1976/533, loss: 0.0016251255292445421
2023-01-24 09:56:00.449230: step: 1980/533, loss: 0.006466568913310766
2023-01-24 09:56:01.568831: step: 1984/533, loss: 0.018461178988218307
2023-01-24 09:56:02.676247: step: 1988/533, loss: 0.004555370658636093
2023-01-24 09:56:03.771111: step: 1992/533, loss: 0.0032839414197951555
2023-01-24 09:56:04.864481: step: 1996/533, loss: 0.0015775030478835106
2023-01-24 09:56:05.955818: step: 2000/533, loss: 0.008274293504655361
2023-01-24 09:56:07.031136: step: 2004/533, loss: 0.0060800472274422646
2023-01-24 09:56:08.125587: step: 2008/533, loss: 0.011846175417304039
2023-01-24 09:56:09.222677: step: 2012/533, loss: 0.0027653092984110117
2023-01-24 09:56:10.321435: step: 2016/533, loss: 0.006105853710323572
2023-01-24 09:56:11.416558: step: 2020/533, loss: 0.0009124097414314747
2023-01-24 09:56:12.509832: step: 2024/533, loss: 0.0005457018269225955
2023-01-24 09:56:13.608131: step: 2028/533, loss: 0.002030693693086505
2023-01-24 09:56:14.720354: step: 2032/533, loss: 0.014128362759947777
2023-01-24 09:56:15.816671: step: 2036/533, loss: 0.0001448775437893346
2023-01-24 09:56:16.893846: step: 2040/533, loss: 0.0054580275900661945
2023-01-24 09:56:17.969764: step: 2044/533, loss: 0.0007001154590398073
2023-01-24 09:56:19.083117: step: 2048/533, loss: 0.003718607360497117
2023-01-24 09:56:20.190898: step: 2052/533, loss: 0.005579912103712559
2023-01-24 09:56:21.268109: step: 2056/533, loss: 0.0005695783765986562
2023-01-24 09:56:22.369774: step: 2060/533, loss: 0.003574712434783578
2023-01-24 09:56:23.472084: step: 2064/533, loss: 0.0031878736335784197
2023-01-24 09:56:24.546019: step: 2068/533, loss: 5.609767322312109e-05
2023-01-24 09:56:25.628558: step: 2072/533, loss: 0.002051748801022768
2023-01-24 09:56:26.757011: step: 2076/533, loss: 0.0034125084057450294
2023-01-24 09:56:27.864348: step: 2080/533, loss: 0.002723362296819687
2023-01-24 09:56:28.984754: step: 2084/533, loss: 0.0001749385119182989
2023-01-24 09:56:30.077322: step: 2088/533, loss: 0.003758937818929553
2023-01-24 09:56:31.164817: step: 2092/533, loss: 0.0005058296956121922
2023-01-24 09:56:32.258331: step: 2096/533, loss: 0.012547427788376808
2023-01-24 09:56:33.350512: step: 2100/533, loss: 0.004150098655372858
2023-01-24 09:56:34.423328: step: 2104/533, loss: 0.03857294097542763
2023-01-24 09:56:35.521467: step: 2108/533, loss: 1.843418795033358e-05
2023-01-24 09:56:36.620141: step: 2112/533, loss: 0.014450492337346077
2023-01-24 09:56:37.714814: step: 2116/533, loss: 0.0018523945473134518
2023-01-24 09:56:38.804589: step: 2120/533, loss: 0.00016009835235308856
2023-01-24 09:56:39.912167: step: 2124/533, loss: 0.00266197114251554
2023-01-24 09:56:41.018351: step: 2128/533, loss: 0.002243522321805358
2023-01-24 09:56:42.125258: step: 2132/533, loss: 0.0041077155619859695
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.382049209770115, 'r': 0.33637729285262497, 'f1': 0.35776152034981507}, 'combined': 0.2636137518367058, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39296622642269474, 'r': 0.3623602030186195, 'f1': 0.37704313270571715}, 'combined': 0.25136208847047803, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3543622671601818, 'r': 0.3207415587009615, 'f1': 0.33671474389523254}, 'combined': 0.24810560076490817, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3855147555071279, 'r': 0.3117479897898986, 'f1': 0.3447293029043004}, 'combined': 0.22981953526953355, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34020564077787174, 'r': 0.3143835807567809, 'f1': 0.3267852999187841}, 'combined': 0.2407891683612093, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3808473586678044, 'r': 0.35081900923438136, 'f1': 0.36521698659034696}, 'combined': 0.24347799106023124, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.703125, 'r': 0.4891304347826087, 'f1': 0.576923076923077}, 'combined': 0.38461538461538464, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 09:59:04.655233: step: 4/533, loss: 0.004791678860783577
2023-01-24 09:59:05.754766: step: 8/533, loss: 0.0016097489278763533
2023-01-24 09:59:06.841255: step: 12/533, loss: 0.0023783636279404163
2023-01-24 09:59:07.924385: step: 16/533, loss: 0.0009115452994592488
2023-01-24 09:59:09.025584: step: 20/533, loss: 0.0076829236932098866
2023-01-24 09:59:10.136542: step: 24/533, loss: 0.002348264679312706
2023-01-24 09:59:11.230994: step: 28/533, loss: 0.0011866915738210082
2023-01-24 09:59:12.318886: step: 32/533, loss: 0.0037825542967766523
2023-01-24 09:59:13.415462: step: 36/533, loss: 0.0006914320983923972
2023-01-24 09:59:14.486574: step: 40/533, loss: 0.0013894616859033704
2023-01-24 09:59:15.561860: step: 44/533, loss: 0.003912001848220825
2023-01-24 09:59:16.648899: step: 48/533, loss: 0.00428289920091629
2023-01-24 09:59:17.743062: step: 52/533, loss: 0.004794435575604439
2023-01-24 09:59:18.836799: step: 56/533, loss: 0.000500489491969347
2023-01-24 09:59:19.909370: step: 60/533, loss: 0.0058922357857227325
2023-01-24 09:59:20.998682: step: 64/533, loss: 0.004075516946613789
2023-01-24 09:59:22.086776: step: 68/533, loss: 0.0005638864240609109
2023-01-24 09:59:23.176948: step: 72/533, loss: 0.020583104342222214
2023-01-24 09:59:24.251099: step: 76/533, loss: 0.006968772504478693
2023-01-24 09:59:25.322922: step: 80/533, loss: 0.0022594789043068886
2023-01-24 09:59:26.410148: step: 84/533, loss: 0.0009020747966133058
2023-01-24 09:59:27.505015: step: 88/533, loss: 0.002252426231279969
2023-01-24 09:59:28.601235: step: 92/533, loss: 0.004320651758462191
2023-01-24 09:59:29.691160: step: 96/533, loss: 0.018381061032414436
2023-01-24 09:59:30.770829: step: 100/533, loss: 0.0008703085477463901
2023-01-24 09:59:31.859900: step: 104/533, loss: 0.001956680789589882
2023-01-24 09:59:32.948039: step: 108/533, loss: 0.007869044318795204
2023-01-24 09:59:34.073297: step: 112/533, loss: 0.0006912454846315086
2023-01-24 09:59:35.169106: step: 116/533, loss: 0.006367552559822798
2023-01-24 09:59:36.277916: step: 120/533, loss: 0.0046379962004721165
2023-01-24 09:59:37.377498: step: 124/533, loss: 0.01381286233663559
2023-01-24 09:59:38.489233: step: 128/533, loss: 0.00452254805713892
2023-01-24 09:59:39.555316: step: 132/533, loss: 0.008519639261066914
2023-01-24 09:59:40.654666: step: 136/533, loss: 0.00010123771062353626
2023-01-24 09:59:41.752773: step: 140/533, loss: 0.003423751564696431
2023-01-24 09:59:42.863827: step: 144/533, loss: 0.0009711952297948301
2023-01-24 09:59:43.973842: step: 148/533, loss: 0.0018722357926890254
2023-01-24 09:59:45.055947: step: 152/533, loss: 0.006367494352161884
2023-01-24 09:59:46.150188: step: 156/533, loss: 0.00011249367526033893
2023-01-24 09:59:47.230379: step: 160/533, loss: 0.004675439093261957
2023-01-24 09:59:48.330237: step: 164/533, loss: 0.004556040279567242
2023-01-24 09:59:49.427377: step: 168/533, loss: 0.001875725807622075
2023-01-24 09:59:50.521041: step: 172/533, loss: 0.003925638273358345
2023-01-24 09:59:51.614451: step: 176/533, loss: 0.004376445896923542
2023-01-24 09:59:52.687203: step: 180/533, loss: 0.007494747638702393
2023-01-24 09:59:53.772075: step: 184/533, loss: 0.0026175579987466335
2023-01-24 09:59:54.874708: step: 188/533, loss: 0.0026020866353064775
2023-01-24 09:59:55.969537: step: 192/533, loss: 0.004970707464963198
2023-01-24 09:59:57.049675: step: 196/533, loss: 0.0005093092331662774
2023-01-24 09:59:58.158956: step: 200/533, loss: 0.0011953633511438966
2023-01-24 09:59:59.276978: step: 204/533, loss: 0.003538611112162471
2023-01-24 10:00:00.397581: step: 208/533, loss: 8.99856531759724e-05
2023-01-24 10:00:01.492539: step: 212/533, loss: 0.0001003869911073707
2023-01-24 10:00:02.589401: step: 216/533, loss: 0.004922454711049795
2023-01-24 10:00:03.657991: step: 220/533, loss: 0.008166012354195118
2023-01-24 10:00:04.737181: step: 224/533, loss: 0.00013534915342461318
2023-01-24 10:00:05.845447: step: 228/533, loss: 0.004625893197953701
2023-01-24 10:00:06.964540: step: 232/533, loss: 0.0007884650258347392
2023-01-24 10:00:08.069377: step: 236/533, loss: 0.002195534994825721
2023-01-24 10:00:09.193547: step: 240/533, loss: 0.004068003036081791
2023-01-24 10:00:10.276250: step: 244/533, loss: 0.0025808350183069706
2023-01-24 10:00:11.354146: step: 248/533, loss: 0.0005780967185273767
2023-01-24 10:00:12.450276: step: 252/533, loss: 0.011257696896791458
2023-01-24 10:00:13.530047: step: 256/533, loss: 0.0003197825571987778
2023-01-24 10:00:14.624288: step: 260/533, loss: 0.013132868334650993
2023-01-24 10:00:15.715501: step: 264/533, loss: 0.00022617678041569889
2023-01-24 10:00:16.839162: step: 268/533, loss: 0.0025280825793743134
2023-01-24 10:00:17.916044: step: 272/533, loss: 0.0021800119429826736
2023-01-24 10:00:18.996541: step: 276/533, loss: 0.0019786644261330366
2023-01-24 10:00:20.074864: step: 280/533, loss: 4.528164572548121e-05
2023-01-24 10:00:21.167729: step: 284/533, loss: 0.00933734979480505
2023-01-24 10:00:22.268170: step: 288/533, loss: 0.0029000986833125353
2023-01-24 10:00:23.372640: step: 292/533, loss: 0.022852545604109764
2023-01-24 10:00:24.472016: step: 296/533, loss: 0.0011038176016882062
2023-01-24 10:00:25.564733: step: 300/533, loss: 0.00046507493243552744
2023-01-24 10:00:26.664865: step: 304/533, loss: 0.003011062042787671
2023-01-24 10:00:27.757684: step: 308/533, loss: 0.004074779339134693
2023-01-24 10:00:28.866761: step: 312/533, loss: 0.0032834019511938095
2023-01-24 10:00:29.958837: step: 316/533, loss: 0.0015411429340019822
2023-01-24 10:00:31.055794: step: 320/533, loss: 0.009638076648116112
2023-01-24 10:00:32.164865: step: 324/533, loss: 0.0025848059449344873
2023-01-24 10:00:33.287000: step: 328/533, loss: 0.0005720409099012613
2023-01-24 10:00:34.388141: step: 332/533, loss: 0.0034660398960113525
2023-01-24 10:00:35.487523: step: 336/533, loss: 0.0038483701646327972
2023-01-24 10:00:36.576083: step: 340/533, loss: 0.001415163278579712
2023-01-24 10:00:37.659757: step: 344/533, loss: 0.008363374508917332
2023-01-24 10:00:38.753578: step: 348/533, loss: 0.0029824019875377417
2023-01-24 10:00:39.849232: step: 352/533, loss: 0.005242650397121906
2023-01-24 10:00:40.943560: step: 356/533, loss: 0.00014957234088797122
2023-01-24 10:00:42.027452: step: 360/533, loss: 0.008386089466512203
2023-01-24 10:00:43.118587: step: 364/533, loss: 0.001973103266209364
2023-01-24 10:00:44.242655: step: 368/533, loss: 0.006201819982379675
2023-01-24 10:00:45.340181: step: 372/533, loss: 0.0003292427572887391
2023-01-24 10:00:46.430117: step: 376/533, loss: 0.009948239661753178
2023-01-24 10:00:47.525009: step: 380/533, loss: 0.00012413185322657228
2023-01-24 10:00:48.624599: step: 384/533, loss: 0.0015588094247505069
2023-01-24 10:00:49.725431: step: 388/533, loss: 0.008218183182179928
2023-01-24 10:00:50.833724: step: 392/533, loss: 1.5107117405932513e-06
2023-01-24 10:00:51.906658: step: 396/533, loss: 0.007452758494764566
2023-01-24 10:00:53.002655: step: 400/533, loss: 0.00011211884702788666
2023-01-24 10:00:54.137302: step: 404/533, loss: 0.0005855325143784285
2023-01-24 10:00:55.245931: step: 408/533, loss: 0.0004674453812185675
2023-01-24 10:00:56.355418: step: 412/533, loss: 0.002068473258987069
2023-01-24 10:00:57.464507: step: 416/533, loss: 0.010116081684827805
2023-01-24 10:00:58.550507: step: 420/533, loss: 0.00010878677858272567
2023-01-24 10:00:59.646261: step: 424/533, loss: 3.408937845961191e-05
2023-01-24 10:01:00.762113: step: 428/533, loss: 0.00581952603533864
2023-01-24 10:01:01.867502: step: 432/533, loss: 0.004737149458378553
2023-01-24 10:01:02.933936: step: 436/533, loss: 0.007001113146543503
2023-01-24 10:01:04.022187: step: 440/533, loss: 0.0013192900223657489
2023-01-24 10:01:05.134174: step: 444/533, loss: 0.004117125645279884
2023-01-24 10:01:06.235718: step: 448/533, loss: 0.005541543941944838
2023-01-24 10:01:07.318642: step: 452/533, loss: 0.0004287994815967977
2023-01-24 10:01:08.436268: step: 456/533, loss: 0.0024777858052402735
2023-01-24 10:01:09.555295: step: 460/533, loss: 0.0004489559505600482
2023-01-24 10:01:10.644010: step: 464/533, loss: 5.875227725482546e-05
2023-01-24 10:01:11.740250: step: 468/533, loss: 0.002337637124583125
2023-01-24 10:01:12.826595: step: 472/533, loss: 0.0036645373329520226
2023-01-24 10:01:13.936567: step: 476/533, loss: 0.004678815603256226
2023-01-24 10:01:15.049017: step: 480/533, loss: 0.0020938427187502384
2023-01-24 10:01:16.136247: step: 484/533, loss: 0.00016922756913118064
2023-01-24 10:01:17.249977: step: 488/533, loss: 0.0014465975109487772
2023-01-24 10:01:18.386312: step: 492/533, loss: 0.00307208439335227
2023-01-24 10:01:19.473337: step: 496/533, loss: 0.0026184399612247944
2023-01-24 10:01:20.594493: step: 500/533, loss: 0.008059652522206306
2023-01-24 10:01:21.687289: step: 504/533, loss: 0.0007211562478914857
2023-01-24 10:01:22.769801: step: 508/533, loss: 0.00023141555720940232
2023-01-24 10:01:23.874537: step: 512/533, loss: 0.007552965544164181
2023-01-24 10:01:24.968081: step: 516/533, loss: 0.022168099880218506
2023-01-24 10:01:26.085525: step: 520/533, loss: 0.002785957418382168
2023-01-24 10:01:27.172789: step: 524/533, loss: 0.0002901311090681702
2023-01-24 10:01:28.265117: step: 528/533, loss: 0.00576599407941103
2023-01-24 10:01:29.357900: step: 532/533, loss: 0.004378336947411299
2023-01-24 10:01:30.449252: step: 536/533, loss: 0.005015286151319742
2023-01-24 10:01:31.522946: step: 540/533, loss: 0.00011839955550385639
2023-01-24 10:01:32.621945: step: 544/533, loss: 0.0001740623265504837
2023-01-24 10:01:33.725027: step: 548/533, loss: 0.011382361873984337
2023-01-24 10:01:34.827177: step: 552/533, loss: 0.0017758235335350037
2023-01-24 10:01:35.936088: step: 556/533, loss: 0.004038352984935045
2023-01-24 10:01:37.058980: step: 560/533, loss: 0.0012040920555591583
2023-01-24 10:01:38.167845: step: 564/533, loss: 0.001655370113439858
2023-01-24 10:01:39.283584: step: 568/533, loss: 0.002622924279421568
2023-01-24 10:01:40.403712: step: 572/533, loss: 0.0055399322882294655
2023-01-24 10:01:41.506883: step: 576/533, loss: 0.00023558746033813804
2023-01-24 10:01:42.629292: step: 580/533, loss: 0.0019015519646927714
2023-01-24 10:01:43.725589: step: 584/533, loss: 0.002161797136068344
2023-01-24 10:01:44.821258: step: 588/533, loss: 0.00207718089222908
2023-01-24 10:01:45.902503: step: 592/533, loss: 0.002164623001590371
2023-01-24 10:01:46.989835: step: 596/533, loss: 0.000931211281567812
2023-01-24 10:01:48.093448: step: 600/533, loss: 0.0008028893498703837
2023-01-24 10:01:49.211844: step: 604/533, loss: 0.003130938159301877
2023-01-24 10:01:50.332554: step: 608/533, loss: 0.002810003701597452
2023-01-24 10:01:51.417081: step: 612/533, loss: 0.010163401253521442
2023-01-24 10:01:52.511385: step: 616/533, loss: 0.0005341544165275991
2023-01-24 10:01:53.607208: step: 620/533, loss: 0.004451815038919449
2023-01-24 10:01:54.689758: step: 624/533, loss: 0.0011158691486343741
2023-01-24 10:01:55.789276: step: 628/533, loss: 0.020304614678025246
2023-01-24 10:01:56.901806: step: 632/533, loss: 4.833106231671991e-06
2023-01-24 10:01:57.985781: step: 636/533, loss: 1.5738320144009776e-05
2023-01-24 10:01:59.091209: step: 640/533, loss: 0.0042512016370892525
2023-01-24 10:02:00.183304: step: 644/533, loss: 0.00010924398520728573
2023-01-24 10:02:01.284786: step: 648/533, loss: 0.0003635298926383257
2023-01-24 10:02:02.419279: step: 652/533, loss: 0.0015546871582046151
2023-01-24 10:02:03.501146: step: 656/533, loss: 0.009253461845219135
2023-01-24 10:02:04.603293: step: 660/533, loss: 0.0005400435766205192
2023-01-24 10:02:05.695633: step: 664/533, loss: 0.0018183921929448843
2023-01-24 10:02:06.790575: step: 668/533, loss: 0.0026284726336598396
2023-01-24 10:02:07.910882: step: 672/533, loss: 0.029474690556526184
2023-01-24 10:02:09.008897: step: 676/533, loss: 0.00024645368102937937
2023-01-24 10:02:10.116020: step: 680/533, loss: 0.002937576500698924
2023-01-24 10:02:11.214131: step: 684/533, loss: 1.632708517718129e-05
2023-01-24 10:02:12.340646: step: 688/533, loss: 0.0015157571760937572
2023-01-24 10:02:13.421001: step: 692/533, loss: 0.00010779868171084672
2023-01-24 10:02:14.490002: step: 696/533, loss: 0.0016452742274850607
2023-01-24 10:02:15.585882: step: 700/533, loss: 0.0011109896004199982
2023-01-24 10:02:16.690387: step: 704/533, loss: 0.004375772550702095
2023-01-24 10:02:17.780445: step: 708/533, loss: 0.004025992937386036
2023-01-24 10:02:18.875087: step: 712/533, loss: 0.004299519117921591
2023-01-24 10:02:19.973362: step: 716/533, loss: 0.0022544206585735083
2023-01-24 10:02:21.064586: step: 720/533, loss: 0.0035835104063153267
2023-01-24 10:02:22.163863: step: 724/533, loss: 0.00391499325633049
2023-01-24 10:02:23.257406: step: 728/533, loss: 0.03179148584604263
2023-01-24 10:02:24.376639: step: 732/533, loss: 0.0013152704341337085
2023-01-24 10:02:25.484204: step: 736/533, loss: 0.00010093249147757888
2023-01-24 10:02:26.590166: step: 740/533, loss: 0.002371604321524501
2023-01-24 10:02:27.686348: step: 744/533, loss: 0.006610687356442213
2023-01-24 10:02:28.767456: step: 748/533, loss: 0.0016715957317501307
2023-01-24 10:02:29.857620: step: 752/533, loss: 0.007537439465522766
2023-01-24 10:02:30.962213: step: 756/533, loss: 0.0015496010892093182
2023-01-24 10:02:32.037586: step: 760/533, loss: 0.004527871962636709
2023-01-24 10:02:33.131493: step: 764/533, loss: 0.013858838938176632
2023-01-24 10:02:34.205545: step: 768/533, loss: 0.024072900414466858
2023-01-24 10:02:35.315333: step: 772/533, loss: 0.001850985223427415
2023-01-24 10:02:36.410720: step: 776/533, loss: 0.007340989541262388
2023-01-24 10:02:37.521574: step: 780/533, loss: 0.00011833521421067417
2023-01-24 10:02:38.631477: step: 784/533, loss: 0.0041513508185744286
2023-01-24 10:02:39.726722: step: 788/533, loss: 0.00918998196721077
2023-01-24 10:02:40.818510: step: 792/533, loss: 0.005654564592987299
2023-01-24 10:02:41.901294: step: 796/533, loss: 0.004085469990968704
2023-01-24 10:02:43.006335: step: 800/533, loss: 6.212072185007855e-05
2023-01-24 10:02:44.125736: step: 804/533, loss: 0.003693186677992344
2023-01-24 10:02:45.242656: step: 808/533, loss: 0.03680189326405525
2023-01-24 10:02:46.328835: step: 812/533, loss: 0.0020570133347064257
2023-01-24 10:02:47.436026: step: 816/533, loss: 6.805714747315506e-07
2023-01-24 10:02:48.549370: step: 820/533, loss: 0.017158757895231247
2023-01-24 10:02:49.647584: step: 824/533, loss: 0.00042640327592380345
2023-01-24 10:02:50.757584: step: 828/533, loss: 0.0025178417563438416
2023-01-24 10:02:51.847498: step: 832/533, loss: 0.002081652171909809
2023-01-24 10:02:52.932754: step: 836/533, loss: 0.0006351170595735312
2023-01-24 10:02:54.012651: step: 840/533, loss: 0.0021157553419470787
2023-01-24 10:02:55.106186: step: 844/533, loss: 0.003691704012453556
2023-01-24 10:02:56.195948: step: 848/533, loss: 0.0004564235277939588
2023-01-24 10:02:57.289357: step: 852/533, loss: 0.0033700524363666773
2023-01-24 10:02:58.391247: step: 856/533, loss: 0.0038247695192694664
2023-01-24 10:02:59.489555: step: 860/533, loss: 0.0002343023952562362
2023-01-24 10:03:00.595814: step: 864/533, loss: 0.00860179215669632
2023-01-24 10:03:01.678644: step: 868/533, loss: 0.0028152165468782187
2023-01-24 10:03:02.770498: step: 872/533, loss: 0.0065716225653886795
2023-01-24 10:03:03.872583: step: 876/533, loss: 0.002417056355625391
2023-01-24 10:03:04.988293: step: 880/533, loss: 0.0027183089405298233
2023-01-24 10:03:06.075777: step: 884/533, loss: 0.009205114096403122
2023-01-24 10:03:07.167666: step: 888/533, loss: 0.00038022693479433656
2023-01-24 10:03:08.255296: step: 892/533, loss: 0.000496425200253725
2023-01-24 10:03:09.360168: step: 896/533, loss: 4.4910975702805445e-05
2023-01-24 10:03:10.481363: step: 900/533, loss: 0.014285506680607796
2023-01-24 10:03:11.607474: step: 904/533, loss: 0.001546451123431325
2023-01-24 10:03:12.715531: step: 908/533, loss: 0.0025391022209078074
2023-01-24 10:03:13.828911: step: 912/533, loss: 0.012165246531367302
2023-01-24 10:03:14.919630: step: 916/533, loss: 0.0041103670373559
2023-01-24 10:03:16.025629: step: 920/533, loss: 0.006893141195178032
2023-01-24 10:03:17.116821: step: 924/533, loss: 0.005684357136487961
2023-01-24 10:03:18.202814: step: 928/533, loss: 4.6617437874374446e-06
2023-01-24 10:03:19.296001: step: 932/533, loss: 0.0013610685709863901
2023-01-24 10:03:20.428313: step: 936/533, loss: 0.003538792720064521
2023-01-24 10:03:21.510247: step: 940/533, loss: 0.0013382298639044166
2023-01-24 10:03:22.604818: step: 944/533, loss: 0.0001088837452698499
2023-01-24 10:03:23.696194: step: 948/533, loss: 0.002296646824106574
2023-01-24 10:03:24.826908: step: 952/533, loss: 0.002239560941234231
2023-01-24 10:03:25.914898: step: 956/533, loss: 0.000863869849126786
2023-01-24 10:03:26.989320: step: 960/533, loss: 0.0001274089445360005
2023-01-24 10:03:28.073459: step: 964/533, loss: 0.003186913440003991
2023-01-24 10:03:29.168067: step: 968/533, loss: 0.001150807598605752
2023-01-24 10:03:30.283458: step: 972/533, loss: 0.0026918058283627033
2023-01-24 10:03:31.365025: step: 976/533, loss: 6.168036634335294e-05
2023-01-24 10:03:32.454141: step: 980/533, loss: 0.0010211658664047718
2023-01-24 10:03:33.548142: step: 984/533, loss: 0.0019329055212438107
2023-01-24 10:03:34.644652: step: 988/533, loss: 0.008180102333426476
2023-01-24 10:03:35.731341: step: 992/533, loss: 0.02422501891851425
2023-01-24 10:03:36.830630: step: 996/533, loss: 0.015680918470025063
2023-01-24 10:03:37.952052: step: 1000/533, loss: 0.00044971314491704106
2023-01-24 10:03:39.033092: step: 1004/533, loss: 0.0078738359734416
2023-01-24 10:03:40.123023: step: 1008/533, loss: 0.0003331125481054187
2023-01-24 10:03:41.222903: step: 1012/533, loss: 0.003334991866722703
2023-01-24 10:03:42.312174: step: 1016/533, loss: 0.0009181959321722388
2023-01-24 10:03:43.413666: step: 1020/533, loss: 0.005910418462008238
2023-01-24 10:03:44.508323: step: 1024/533, loss: 0.0034422443713992834
2023-01-24 10:03:45.607912: step: 1028/533, loss: 0.0010012106504291296
2023-01-24 10:03:46.697948: step: 1032/533, loss: 0.00931843277066946
2023-01-24 10:03:47.774712: step: 1036/533, loss: 0.010023634880781174
2023-01-24 10:03:48.860350: step: 1040/533, loss: 0.0001808304659789428
2023-01-24 10:03:49.968495: step: 1044/533, loss: 0.002033291617408395
2023-01-24 10:03:51.047368: step: 1048/533, loss: 0.0015597662422806025
2023-01-24 10:03:52.154748: step: 1052/533, loss: 0.03808736428618431
2023-01-24 10:03:53.241480: step: 1056/533, loss: 0.002030114410445094
2023-01-24 10:03:54.341865: step: 1060/533, loss: 0.0009056462440639734
2023-01-24 10:03:55.456011: step: 1064/533, loss: 0.0013318357523530722
2023-01-24 10:03:56.544039: step: 1068/533, loss: 0.011761617846786976
2023-01-24 10:03:57.641586: step: 1072/533, loss: 0.10574667900800705
2023-01-24 10:03:58.733681: step: 1076/533, loss: 0.0004321039014030248
2023-01-24 10:03:59.851344: step: 1080/533, loss: 0.004517702851444483
2023-01-24 10:04:00.952672: step: 1084/533, loss: 0.0005970491329208016
2023-01-24 10:04:02.044408: step: 1088/533, loss: 0.005085958633571863
2023-01-24 10:04:03.121953: step: 1092/533, loss: 0.003346991492435336
2023-01-24 10:04:04.203914: step: 1096/533, loss: 4.3692471081158146e-05
2023-01-24 10:04:05.283756: step: 1100/533, loss: 0.0022725146263837814
2023-01-24 10:04:06.386597: step: 1104/533, loss: 2.024775767495157e-06
2023-01-24 10:04:07.469269: step: 1108/533, loss: 0.005545760039240122
2023-01-24 10:04:08.571434: step: 1112/533, loss: 0.0001723337481962517
2023-01-24 10:04:09.678376: step: 1116/533, loss: 0.00012271587911527604
2023-01-24 10:04:10.780417: step: 1120/533, loss: 0.00047871939023025334
2023-01-24 10:04:11.868964: step: 1124/533, loss: 0.002539054024964571
2023-01-24 10:04:12.973057: step: 1128/533, loss: 0.00039384292904287577
2023-01-24 10:04:14.064234: step: 1132/533, loss: 0.002441694959998131
2023-01-24 10:04:15.157656: step: 1136/533, loss: 0.007306189276278019
2023-01-24 10:04:16.270539: step: 1140/533, loss: 0.003225123044103384
2023-01-24 10:04:17.352168: step: 1144/533, loss: 0.0003174249141011387
2023-01-24 10:04:18.458632: step: 1148/533, loss: 0.001957499422132969
2023-01-24 10:04:19.547351: step: 1152/533, loss: 0.0021962292958050966
2023-01-24 10:04:20.640721: step: 1156/533, loss: 0.006696137599647045
2023-01-24 10:04:21.716831: step: 1160/533, loss: 0.003397204214707017
2023-01-24 10:04:22.804643: step: 1164/533, loss: 0.00707328412681818
2023-01-24 10:04:23.890051: step: 1168/533, loss: 0.02038923278450966
2023-01-24 10:04:24.989445: step: 1172/533, loss: 0.005347252357751131
2023-01-24 10:04:26.089769: step: 1176/533, loss: 0.000226540447329171
2023-01-24 10:04:27.174445: step: 1180/533, loss: 0.0024090667720884085
2023-01-24 10:04:28.285930: step: 1184/533, loss: 0.003674723207950592
2023-01-24 10:04:29.386539: step: 1188/533, loss: 0.007183699868619442
2023-01-24 10:04:30.473864: step: 1192/533, loss: 0.006848715245723724
2023-01-24 10:04:31.572623: step: 1196/533, loss: 0.004640339873731136
2023-01-24 10:04:32.664910: step: 1200/533, loss: 0.0008892629994079471
2023-01-24 10:04:33.752040: step: 1204/533, loss: 0.004636200610548258
2023-01-24 10:04:34.843670: step: 1208/533, loss: 0.0003389216144569218
2023-01-24 10:04:35.930776: step: 1212/533, loss: 0.005154387094080448
2023-01-24 10:04:37.019354: step: 1216/533, loss: 0.005760980304330587
2023-01-24 10:04:38.090855: step: 1220/533, loss: 0.0011280179023742676
2023-01-24 10:04:39.182183: step: 1224/533, loss: 0.0005039868992753327
2023-01-24 10:04:40.255681: step: 1228/533, loss: 0.0013841758482158184
2023-01-24 10:04:41.337884: step: 1232/533, loss: 0.0014759245095774531
2023-01-24 10:04:42.434598: step: 1236/533, loss: 0.002883825683966279
2023-01-24 10:04:43.528267: step: 1240/533, loss: 0.001058677677065134
2023-01-24 10:04:44.616137: step: 1244/533, loss: 0.00371046201325953
2023-01-24 10:04:45.716547: step: 1248/533, loss: 0.01607479341328144
2023-01-24 10:04:46.817055: step: 1252/533, loss: 8.791509458205837e-07
2023-01-24 10:04:47.923361: step: 1256/533, loss: 0.002676281612366438
2023-01-24 10:04:49.010970: step: 1260/533, loss: 0.0027292342856526375
2023-01-24 10:04:50.089528: step: 1264/533, loss: 0.0074095092713832855
2023-01-24 10:04:51.167739: step: 1268/533, loss: 0.00010627500887494534
2023-01-24 10:04:52.239424: step: 1272/533, loss: 0.0011385750258341432
2023-01-24 10:04:53.322833: step: 1276/533, loss: 0.002621783409267664
2023-01-24 10:04:54.404251: step: 1280/533, loss: 0.0010466104140505195
2023-01-24 10:04:55.528247: step: 1284/533, loss: 0.0024366239085793495
2023-01-24 10:04:56.623640: step: 1288/533, loss: 0.0001901690848171711
2023-01-24 10:04:57.712038: step: 1292/533, loss: 0.0006951289251446724
2023-01-24 10:04:58.824791: step: 1296/533, loss: 0.009983147494494915
2023-01-24 10:04:59.922597: step: 1300/533, loss: 0.0023124453146010637
2023-01-24 10:05:01.024596: step: 1304/533, loss: 0.00013820680032949895
2023-01-24 10:05:02.108670: step: 1308/533, loss: 0.00015362771227955818
2023-01-24 10:05:03.202008: step: 1312/533, loss: 0.0028972814325243235
2023-01-24 10:05:04.292537: step: 1316/533, loss: 0.007112267892807722
2023-01-24 10:05:05.392782: step: 1320/533, loss: 0.000408171268645674
2023-01-24 10:05:06.499741: step: 1324/533, loss: 0.008241366595029831
2023-01-24 10:05:07.610542: step: 1328/533, loss: 0.010457765311002731
2023-01-24 10:05:08.696187: step: 1332/533, loss: 0.002957731718197465
2023-01-24 10:05:09.803533: step: 1336/533, loss: 3.351505802129395e-05
2023-01-24 10:05:10.897882: step: 1340/533, loss: 0.002072863280773163
2023-01-24 10:05:11.980246: step: 1344/533, loss: 4.607054052030435e-06
2023-01-24 10:05:13.066501: step: 1348/533, loss: 8.339130727108568e-05
2023-01-24 10:05:14.173135: step: 1352/533, loss: 0.007553946692496538
2023-01-24 10:05:15.258309: step: 1356/533, loss: 0.0032567777670919895
2023-01-24 10:05:16.356627: step: 1360/533, loss: 0.0015867598121985793
2023-01-24 10:05:17.443487: step: 1364/533, loss: 0.0013543434906750917
2023-01-24 10:05:18.526725: step: 1368/533, loss: 0.0112200528383255
2023-01-24 10:05:19.622581: step: 1372/533, loss: 0.0080289700999856
2023-01-24 10:05:20.708145: step: 1376/533, loss: 0.0010386975482106209
2023-01-24 10:05:21.809866: step: 1380/533, loss: 0.0072889020666480064
2023-01-24 10:05:22.909349: step: 1384/533, loss: 0.0006474694237112999
2023-01-24 10:05:24.005992: step: 1388/533, loss: 0.002143559278920293
2023-01-24 10:05:25.094851: step: 1392/533, loss: 0.0019812132231891155
2023-01-24 10:05:26.177675: step: 1396/533, loss: 0.0005021504475735128
2023-01-24 10:05:27.276716: step: 1400/533, loss: 5.269894245429896e-05
2023-01-24 10:05:28.373852: step: 1404/533, loss: 0.002884772839024663
2023-01-24 10:05:29.461035: step: 1408/533, loss: 0.006081774830818176
2023-01-24 10:05:30.549479: step: 1412/533, loss: 0.005945678800344467
2023-01-24 10:05:31.644943: step: 1416/533, loss: 0.004404555540531874
2023-01-24 10:05:32.776443: step: 1420/533, loss: 0.0013624532148241997
2023-01-24 10:05:33.890798: step: 1424/533, loss: 0.0013212584890425205
2023-01-24 10:05:34.968846: step: 1428/533, loss: 0.0006087392685003579
2023-01-24 10:05:36.063151: step: 1432/533, loss: 0.0015009884955361485
2023-01-24 10:05:37.166916: step: 1436/533, loss: 0.003314326051622629
2023-01-24 10:05:38.241820: step: 1440/533, loss: 0.0038107004947960377
2023-01-24 10:05:39.333436: step: 1444/533, loss: 0.0008374282624572515
2023-01-24 10:05:40.445283: step: 1448/533, loss: 0.0009384050499647856
2023-01-24 10:05:41.535693: step: 1452/533, loss: 0.006657710298895836
2023-01-24 10:05:42.605144: step: 1456/533, loss: 0.00182434543967247
2023-01-24 10:05:43.707880: step: 1460/533, loss: 0.0016635070787742734
2023-01-24 10:05:44.813945: step: 1464/533, loss: 0.002088554436340928
2023-01-24 10:05:45.898833: step: 1468/533, loss: 0.0025557936169207096
2023-01-24 10:05:47.000325: step: 1472/533, loss: 0.007096676155924797
2023-01-24 10:05:48.111236: step: 1476/533, loss: 0.005643774289637804
2023-01-24 10:05:49.218275: step: 1480/533, loss: 0.0023625940084457397
2023-01-24 10:05:50.336221: step: 1484/533, loss: 0.001219236757606268
2023-01-24 10:05:51.455058: step: 1488/533, loss: 0.0017046440625563264
2023-01-24 10:05:52.548066: step: 1492/533, loss: 0.004005202557891607
2023-01-24 10:05:53.638164: step: 1496/533, loss: 0.0009595747105777264
2023-01-24 10:05:54.743783: step: 1500/533, loss: 0.0026299916207790375
2023-01-24 10:05:55.831723: step: 1504/533, loss: 0.0008154292590916157
2023-01-24 10:05:56.919496: step: 1508/533, loss: 5.647083526127972e-05
2023-01-24 10:05:58.029139: step: 1512/533, loss: 0.003915955312550068
2023-01-24 10:05:59.104653: step: 1516/533, loss: 0.010504196397960186
2023-01-24 10:06:00.203591: step: 1520/533, loss: 0.00321620749309659
2023-01-24 10:06:01.297277: step: 1524/533, loss: 0.0035383994691073895
2023-01-24 10:06:02.412887: step: 1528/533, loss: 0.0005014479975216091
2023-01-24 10:06:03.506442: step: 1532/533, loss: 0.00013978366041556
2023-01-24 10:06:04.624625: step: 1536/533, loss: 0.01089765876531601
2023-01-24 10:06:05.728821: step: 1540/533, loss: 0.0011169861536473036
2023-01-24 10:06:06.807296: step: 1544/533, loss: 0.0019830241799354553
2023-01-24 10:06:07.898972: step: 1548/533, loss: 0.0006220468203537166
2023-01-24 10:06:08.974233: step: 1552/533, loss: 0.0010833156993612647
2023-01-24 10:06:10.046147: step: 1556/533, loss: 0.0008142712758854032
2023-01-24 10:06:11.130713: step: 1560/533, loss: 0.002496890025213361
2023-01-24 10:06:12.239972: step: 1564/533, loss: 0.0007081998628564179
2023-01-24 10:06:13.349425: step: 1568/533, loss: 3.1066028896020725e-06
2023-01-24 10:06:14.426481: step: 1572/533, loss: 0.0006730841123498976
2023-01-24 10:06:15.517018: step: 1576/533, loss: 0.00010822821059264243
2023-01-24 10:06:16.601979: step: 1580/533, loss: 0.0005642768810503185
2023-01-24 10:06:17.673966: step: 1584/533, loss: 0.007764765061438084
2023-01-24 10:06:18.759798: step: 1588/533, loss: 0.012040973640978336
2023-01-24 10:06:19.852186: step: 1592/533, loss: 0.002518319757655263
2023-01-24 10:06:20.959941: step: 1596/533, loss: 0.0021240958012640476
2023-01-24 10:06:22.058972: step: 1600/533, loss: 0.0013543047243729234
2023-01-24 10:06:23.147014: step: 1604/533, loss: 0.0002269197575515136
2023-01-24 10:06:24.250060: step: 1608/533, loss: 0.003662078408524394
2023-01-24 10:06:25.374255: step: 1612/533, loss: 0.00496441125869751
2023-01-24 10:06:26.480445: step: 1616/533, loss: 0.000244211609242484
2023-01-24 10:06:27.569487: step: 1620/533, loss: 0.0006543853669427335
2023-01-24 10:06:28.670371: step: 1624/533, loss: 0.006709955167025328
2023-01-24 10:06:29.762241: step: 1628/533, loss: 4.7419620386790484e-05
2023-01-24 10:06:30.859939: step: 1632/533, loss: 0.0016044552903622389
2023-01-24 10:06:31.953167: step: 1636/533, loss: 0.0010231140768155456
2023-01-24 10:06:33.056938: step: 1640/533, loss: 0.0017304434441030025
2023-01-24 10:06:34.152498: step: 1644/533, loss: 0.0018254914321005344
2023-01-24 10:06:35.246743: step: 1648/533, loss: 0.0005161607987247407
2023-01-24 10:06:36.351834: step: 1652/533, loss: 0.0022367946803569794
2023-01-24 10:06:37.433072: step: 1656/533, loss: 0.011122153140604496
2023-01-24 10:06:38.527847: step: 1660/533, loss: 0.009022983722388744
2023-01-24 10:06:39.621465: step: 1664/533, loss: 0.006490306928753853
2023-01-24 10:06:40.716548: step: 1668/533, loss: 0.009089448489248753
2023-01-24 10:06:41.816686: step: 1672/533, loss: 0.0015085141640156507
2023-01-24 10:06:42.909966: step: 1676/533, loss: 0.006277013104408979
2023-01-24 10:06:43.984038: step: 1680/533, loss: 0.0009033732349053025
2023-01-24 10:06:45.081453: step: 1684/533, loss: 0.013625068590044975
2023-01-24 10:06:46.191648: step: 1688/533, loss: 0.00012089319352526218
2023-01-24 10:06:47.288289: step: 1692/533, loss: 4.1483832319499925e-05
2023-01-24 10:06:48.374093: step: 1696/533, loss: 0.006493451539427042
2023-01-24 10:06:49.458272: step: 1700/533, loss: 8.882491329131881e-07
2023-01-24 10:06:50.551345: step: 1704/533, loss: 0.00037963283830322325
2023-01-24 10:06:51.660283: step: 1708/533, loss: 0.04327859356999397
2023-01-24 10:06:52.752557: step: 1712/533, loss: 0.001042308402247727
2023-01-24 10:06:53.847198: step: 1716/533, loss: 0.006917646154761314
2023-01-24 10:06:54.940741: step: 1720/533, loss: 0.0015418570255860686
2023-01-24 10:06:56.051759: step: 1724/533, loss: 0.000326622772263363
2023-01-24 10:06:57.166255: step: 1728/533, loss: 0.00046695308992639184
2023-01-24 10:06:58.231917: step: 1732/533, loss: 0.0020488931331783533
2023-01-24 10:06:59.334793: step: 1736/533, loss: 0.0038257644046097994
2023-01-24 10:07:00.450692: step: 1740/533, loss: 0.00030324351973831654
2023-01-24 10:07:01.546098: step: 1744/533, loss: 2.9237233320600353e-05
2023-01-24 10:07:02.640327: step: 1748/533, loss: 8.505409641657025e-05
2023-01-24 10:07:03.746408: step: 1752/533, loss: 0.0030777985230088234
2023-01-24 10:07:04.827084: step: 1756/533, loss: 0.001473877695389092
2023-01-24 10:07:05.923795: step: 1760/533, loss: 1.5552510376437567e-05
2023-01-24 10:07:07.022858: step: 1764/533, loss: 0.003369821235537529
2023-01-24 10:07:08.139242: step: 1768/533, loss: 0.000476518296636641
2023-01-24 10:07:09.233064: step: 1772/533, loss: 3.455991463852115e-05
2023-01-24 10:07:10.346712: step: 1776/533, loss: 0.00481459591537714
2023-01-24 10:07:11.441814: step: 1780/533, loss: 6.230077269719914e-05
2023-01-24 10:07:12.541243: step: 1784/533, loss: 0.006353878881782293
2023-01-24 10:07:13.633595: step: 1788/533, loss: 0.0023672590032219887
2023-01-24 10:07:14.731385: step: 1792/533, loss: 0.004378738347440958
2023-01-24 10:07:15.831021: step: 1796/533, loss: 0.0017623448511585593
2023-01-24 10:07:16.921897: step: 1800/533, loss: 0.0007162004476413131
2023-01-24 10:07:18.014601: step: 1804/533, loss: 0.00021445433958433568
2023-01-24 10:07:19.097771: step: 1808/533, loss: 0.00011320069461362436
2023-01-24 10:07:20.210335: step: 1812/533, loss: 0.00014227835345081985
2023-01-24 10:07:21.274328: step: 1816/533, loss: 0.0031791345681995153
2023-01-24 10:07:22.366627: step: 1820/533, loss: 0.00034533979487605393
2023-01-24 10:07:23.462339: step: 1824/533, loss: 0.0032124361023306847
2023-01-24 10:07:24.553454: step: 1828/533, loss: 0.0037896335124969482
2023-01-24 10:07:25.652119: step: 1832/533, loss: 0.003190693212673068
2023-01-24 10:07:26.754516: step: 1836/533, loss: 0.0009134127758443356
2023-01-24 10:07:27.853411: step: 1840/533, loss: 0.00036692462163046
2023-01-24 10:07:28.943452: step: 1844/533, loss: 0.00981849990785122
2023-01-24 10:07:30.054588: step: 1848/533, loss: 0.00033018854446709156
2023-01-24 10:07:31.164579: step: 1852/533, loss: 0.00037095247535035014
2023-01-24 10:07:32.268467: step: 1856/533, loss: 2.171502092096489e-05
2023-01-24 10:07:33.366009: step: 1860/533, loss: 0.005235819611698389
2023-01-24 10:07:34.434773: step: 1864/533, loss: 0.00887572392821312
2023-01-24 10:07:35.509276: step: 1868/533, loss: 0.00021273453603498638
2023-01-24 10:07:36.618406: step: 1872/533, loss: 0.005061112344264984
2023-01-24 10:07:37.735032: step: 1876/533, loss: 0.005999962333589792
2023-01-24 10:07:38.827339: step: 1880/533, loss: 0.0004751422966364771
2023-01-24 10:07:39.918348: step: 1884/533, loss: 0.0007621151162311435
2023-01-24 10:07:40.997535: step: 1888/533, loss: 0.008891172707080841
2023-01-24 10:07:42.119029: step: 1892/533, loss: 0.005400713533163071
2023-01-24 10:07:43.229806: step: 1896/533, loss: 0.005122761707752943
2023-01-24 10:07:44.357256: step: 1900/533, loss: 0.0027864929288625717
2023-01-24 10:07:45.451601: step: 1904/533, loss: 0.001181607716716826
2023-01-24 10:07:46.539339: step: 1908/533, loss: 0.0002783705131150782
2023-01-24 10:07:47.644139: step: 1912/533, loss: 0.006172033492475748
2023-01-24 10:07:48.724745: step: 1916/533, loss: 0.0009223615634255111
2023-01-24 10:07:49.817656: step: 1920/533, loss: 0.0030633127316832542
2023-01-24 10:07:50.904297: step: 1924/533, loss: 0.0003782140265684575
2023-01-24 10:07:52.008929: step: 1928/533, loss: 0.021095965057611465
2023-01-24 10:07:53.134433: step: 1932/533, loss: 0.0033337040804326534
2023-01-24 10:07:54.234272: step: 1936/533, loss: 0.006070057861506939
2023-01-24 10:07:55.314613: step: 1940/533, loss: 0.0016271751374006271
2023-01-24 10:07:56.430524: step: 1944/533, loss: 0.00666749058291316
2023-01-24 10:07:57.528370: step: 1948/533, loss: 0.003211100585758686
2023-01-24 10:07:58.619366: step: 1952/533, loss: 0.002255910774692893
2023-01-24 10:07:59.709652: step: 1956/533, loss: 0.002847905270755291
2023-01-24 10:08:00.800038: step: 1960/533, loss: 0.0027622305788099766
2023-01-24 10:08:01.883853: step: 1964/533, loss: 0.00040234680636785924
2023-01-24 10:08:02.983143: step: 1968/533, loss: 0.0009677308844402432
2023-01-24 10:08:04.063970: step: 1972/533, loss: 0.003470547730103135
2023-01-24 10:08:05.172274: step: 1976/533, loss: 0.0024677279870957136
2023-01-24 10:08:06.258000: step: 1980/533, loss: 0.00016482110368087888
2023-01-24 10:08:07.341315: step: 1984/533, loss: 0.0003669261059258133
2023-01-24 10:08:08.432998: step: 1988/533, loss: 0.002825469244271517
2023-01-24 10:08:09.538901: step: 1992/533, loss: 0.005936977919191122
2023-01-24 10:08:10.634776: step: 1996/533, loss: 0.004179216921329498
2023-01-24 10:08:11.742333: step: 2000/533, loss: 0.0009154830477200449
2023-01-24 10:08:12.850173: step: 2004/533, loss: 0.0003210182476323098
2023-01-24 10:08:13.960274: step: 2008/533, loss: 0.00886419415473938
2023-01-24 10:08:15.062414: step: 2012/533, loss: 0.0003335850778967142
2023-01-24 10:08:16.154342: step: 2016/533, loss: 0.004377765581011772
2023-01-24 10:08:17.266043: step: 2020/533, loss: 0.0022071495186537504
2023-01-24 10:08:18.343939: step: 2024/533, loss: 0.005288831423968077
2023-01-24 10:08:19.443055: step: 2028/533, loss: 0.0121331000700593
2023-01-24 10:08:20.527869: step: 2032/533, loss: 0.0007773085962980986
2023-01-24 10:08:21.649585: step: 2036/533, loss: 0.0003222657833248377
2023-01-24 10:08:22.735140: step: 2040/533, loss: 0.0003934453707188368
2023-01-24 10:08:23.853667: step: 2044/533, loss: 0.005265571177005768
2023-01-24 10:08:24.951419: step: 2048/533, loss: 0.0027606028597801924
2023-01-24 10:08:26.025454: step: 2052/533, loss: 0.0011723826173692942
2023-01-24 10:08:27.111437: step: 2056/533, loss: 0.005560764577239752
2023-01-24 10:08:28.235968: step: 2060/533, loss: 0.0007259122794494033
2023-01-24 10:08:29.308667: step: 2064/533, loss: 0.00117867614608258
2023-01-24 10:08:30.403703: step: 2068/533, loss: 0.006736216135323048
2023-01-24 10:08:31.493130: step: 2072/533, loss: 0.002940678270533681
2023-01-24 10:08:32.588191: step: 2076/533, loss: 0.0031734092626720667
2023-01-24 10:08:33.647588: step: 2080/533, loss: 2.103169754263945e-05
2023-01-24 10:08:34.739725: step: 2084/533, loss: 0.00040202116360887885
2023-01-24 10:08:35.841343: step: 2088/533, loss: 0.0003093196137342602
2023-01-24 10:08:36.941068: step: 2092/533, loss: 1.8148060917155817e-05
2023-01-24 10:08:38.025023: step: 2096/533, loss: 0.007537328638136387
2023-01-24 10:08:39.106924: step: 2100/533, loss: 0.0016540357610210776
2023-01-24 10:08:40.220300: step: 2104/533, loss: 0.004886386450380087
2023-01-24 10:08:41.325164: step: 2108/533, loss: 0.02779049426317215
2023-01-24 10:08:42.397623: step: 2112/533, loss: 0.0031590734142810106
2023-01-24 10:08:43.497358: step: 2116/533, loss: 0.004480249714106321
2023-01-24 10:08:44.573472: step: 2120/533, loss: 0.0007080962532199919
2023-01-24 10:08:45.658734: step: 2124/533, loss: 0.0005082221468910575
2023-01-24 10:08:46.754954: step: 2128/533, loss: 0.0019927804823964834
2023-01-24 10:08:47.844634: step: 2132/533, loss: 0.00391067611053586
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38084069168506257, 'r': 0.32736401012017713, 'f1': 0.35208333333333336}, 'combined': 0.2594298245614035, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39505809695677047, 'r': 0.3570717414801579, 'f1': 0.3751056678175396}, 'combined': 0.250070445211693, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3592736647439116, 'r': 0.3183696421924226, 'f1': 0.33758712562456084}, 'combined': 0.24874840835493955, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39281796017276505, 'r': 0.30934414363605245, 'f1': 0.3461193215508279}, 'combined': 0.23074621436721857, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34592387910578243, 'r': 0.3091653644379953, 'f1': 0.3265133207591654}, 'combined': 0.24058876266464818, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38331729774354856, 'r': 0.34240554769591985, 'f1': 0.36170824743906205}, 'combined': 0.2411388316260413, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 10:11:04.955414: step: 4/533, loss: 0.004979346413165331
2023-01-24 10:11:06.036428: step: 8/533, loss: 0.016234993934631348
2023-01-24 10:11:07.152214: step: 12/533, loss: 0.026073280721902847
2023-01-24 10:11:08.237232: step: 16/533, loss: 0.007753645535558462
2023-01-24 10:11:09.343480: step: 20/533, loss: 0.0036886741872876883
2023-01-24 10:11:10.412339: step: 24/533, loss: 4.230743434163742e-05
2023-01-24 10:11:11.488750: step: 28/533, loss: 0.0026576288510113955
2023-01-24 10:11:12.585380: step: 32/533, loss: 0.002769174287095666
2023-01-24 10:11:13.692712: step: 36/533, loss: 0.0047452980652451515
2023-01-24 10:11:14.772762: step: 40/533, loss: 0.0019568651914596558
2023-01-24 10:11:15.857473: step: 44/533, loss: 0.00814677495509386
2023-01-24 10:11:16.952768: step: 48/533, loss: 0.005982976406812668
2023-01-24 10:11:18.064926: step: 52/533, loss: 0.0019655926153063774
2023-01-24 10:11:19.179166: step: 56/533, loss: 0.00010748140630312264
2023-01-24 10:11:20.270485: step: 60/533, loss: 0.010497907176613808
2023-01-24 10:11:21.374888: step: 64/533, loss: 0.000277341459877789
2023-01-24 10:11:22.453240: step: 68/533, loss: 5.4280197218758985e-05
2023-01-24 10:11:23.536753: step: 72/533, loss: 0.005671729799360037
2023-01-24 10:11:24.610452: step: 76/533, loss: 0.036837488412857056
2023-01-24 10:11:25.694446: step: 80/533, loss: 6.50439687888138e-05
2023-01-24 10:11:26.777366: step: 84/533, loss: 0.006655267905443907
2023-01-24 10:11:27.864854: step: 88/533, loss: 0.0020219606813043356
2023-01-24 10:11:28.931431: step: 92/533, loss: 0.0006623697117902339
2023-01-24 10:11:30.025237: step: 96/533, loss: 0.0003033580433111638
2023-01-24 10:11:31.145002: step: 100/533, loss: 0.0018522251630201936
2023-01-24 10:11:32.224350: step: 104/533, loss: 0.0019999907817691565
2023-01-24 10:11:33.315521: step: 108/533, loss: 0.05308543145656586
2023-01-24 10:11:34.402547: step: 112/533, loss: 0.00031855053384788334
2023-01-24 10:11:35.495574: step: 116/533, loss: 0.004399975296109915
2023-01-24 10:11:36.585470: step: 120/533, loss: 0.0
2023-01-24 10:11:37.665766: step: 124/533, loss: 0.0015248819254338741
2023-01-24 10:11:38.786923: step: 128/533, loss: 0.00030701287323608994
2023-01-24 10:11:39.886001: step: 132/533, loss: 0.003585812635719776
2023-01-24 10:11:40.994274: step: 136/533, loss: 0.0011205067858099937
2023-01-24 10:11:42.095694: step: 140/533, loss: 0.006803089287132025
2023-01-24 10:11:43.189501: step: 144/533, loss: 0.00938600953668356
2023-01-24 10:11:44.274379: step: 148/533, loss: 0.00041816162411123514
2023-01-24 10:11:45.391164: step: 152/533, loss: 0.0014268491650000215
2023-01-24 10:11:46.479899: step: 156/533, loss: 0.00042326722177676857
2023-01-24 10:11:47.576323: step: 160/533, loss: 0.000586865353398025
2023-01-24 10:11:48.656222: step: 164/533, loss: 0.00016709577175788581
2023-01-24 10:11:49.763942: step: 168/533, loss: 0.0014539408730342984
2023-01-24 10:11:50.858132: step: 172/533, loss: 0.0026885501574724913
2023-01-24 10:11:51.957398: step: 176/533, loss: 0.00080332369543612
2023-01-24 10:11:53.056802: step: 180/533, loss: 0.0034964228980243206
2023-01-24 10:11:54.169468: step: 184/533, loss: 0.0024426535237580538
2023-01-24 10:11:55.257861: step: 188/533, loss: 0.004360251594334841
2023-01-24 10:11:56.357505: step: 192/533, loss: 0.002630239352583885
2023-01-24 10:11:57.475950: step: 196/533, loss: 0.0005118328263051808
2023-01-24 10:11:58.560957: step: 200/533, loss: 0.0015185795491561294
2023-01-24 10:11:59.682980: step: 204/533, loss: 0.003406007308512926
2023-01-24 10:12:00.784214: step: 208/533, loss: 0.0033942563459277153
2023-01-24 10:12:01.864594: step: 212/533, loss: 0.00863209180533886
2023-01-24 10:12:02.998747: step: 216/533, loss: 0.002844410017132759
2023-01-24 10:12:04.097851: step: 220/533, loss: 0.0005948045873083174
2023-01-24 10:12:05.183256: step: 224/533, loss: 0.00011376216571079567
2023-01-24 10:12:06.275805: step: 228/533, loss: 3.229029243811965e-05
2023-01-24 10:12:07.398072: step: 232/533, loss: 0.004187675658613443
2023-01-24 10:12:08.510258: step: 236/533, loss: 0.0003824588202405721
2023-01-24 10:12:09.628302: step: 240/533, loss: 0.002864314243197441
2023-01-24 10:12:10.726720: step: 244/533, loss: 0.0025325980968773365
2023-01-24 10:12:11.822832: step: 248/533, loss: 4.3057352741016075e-05
2023-01-24 10:12:12.925296: step: 252/533, loss: 0.002598017919808626
2023-01-24 10:12:14.050545: step: 256/533, loss: 0.002938514109700918
2023-01-24 10:12:15.166474: step: 260/533, loss: 0.0006071623647585511
2023-01-24 10:12:16.264396: step: 264/533, loss: 0.010655377991497517
2023-01-24 10:12:17.374611: step: 268/533, loss: 0.0016514412127435207
2023-01-24 10:12:18.494265: step: 272/533, loss: 0.0023842400405555964
2023-01-24 10:12:19.597224: step: 276/533, loss: 0.0037618051283061504
2023-01-24 10:12:20.695955: step: 280/533, loss: 0.004291097167879343
2023-01-24 10:12:21.785402: step: 284/533, loss: 0.0024277563206851482
2023-01-24 10:12:22.878463: step: 288/533, loss: 0.00195493851788342
2023-01-24 10:12:23.993596: step: 292/533, loss: 0.00973235722631216
2023-01-24 10:12:25.081679: step: 296/533, loss: 0.010800465941429138
2023-01-24 10:12:26.203996: step: 300/533, loss: 0.008858682587742805
2023-01-24 10:12:27.295384: step: 304/533, loss: 0.0004983202088624239
2023-01-24 10:12:28.393891: step: 308/533, loss: 0.00154401536565274
2023-01-24 10:12:29.511386: step: 312/533, loss: 0.0026067134458571672
2023-01-24 10:12:30.603231: step: 316/533, loss: 0.001613895408809185
2023-01-24 10:12:31.707233: step: 320/533, loss: 0.008253108710050583
2023-01-24 10:12:32.803697: step: 324/533, loss: 0.0007935107569210231
2023-01-24 10:12:33.924977: step: 328/533, loss: 0.0021176591981202364
2023-01-24 10:12:35.021892: step: 332/533, loss: 0.001713754259981215
2023-01-24 10:12:36.122966: step: 336/533, loss: 0.0009436543332412839
2023-01-24 10:12:37.194311: step: 340/533, loss: 4.803122465091292e-06
2023-01-24 10:12:38.309508: step: 344/533, loss: 0.0021487099584192038
2023-01-24 10:12:39.408297: step: 348/533, loss: 0.0010960092768073082
2023-01-24 10:12:40.502451: step: 352/533, loss: 0.0004138115036766976
2023-01-24 10:12:41.612501: step: 356/533, loss: 0.004991626832634211
2023-01-24 10:12:42.711811: step: 360/533, loss: 0.0019172257743775845
2023-01-24 10:12:43.816475: step: 364/533, loss: 0.004364550579339266
2023-01-24 10:12:44.901737: step: 368/533, loss: 0.0007605582941323519
2023-01-24 10:12:45.998216: step: 372/533, loss: 0.013118796981871128
2023-01-24 10:12:47.113606: step: 376/533, loss: 0.005485953763127327
2023-01-24 10:12:48.203583: step: 380/533, loss: 0.0004640043480321765
2023-01-24 10:12:49.288978: step: 384/533, loss: 0.0029042381793260574
2023-01-24 10:12:50.419713: step: 388/533, loss: 0.02256741374731064
2023-01-24 10:12:51.525263: step: 392/533, loss: 0.005941659212112427
2023-01-24 10:12:52.629536: step: 396/533, loss: 0.0007259793346747756
2023-01-24 10:12:53.699648: step: 400/533, loss: 0.0006852867663837969
2023-01-24 10:12:54.787655: step: 404/533, loss: 0.005045272875577211
2023-01-24 10:12:55.905011: step: 408/533, loss: 0.0019493092549964786
2023-01-24 10:12:57.012595: step: 412/533, loss: 0.0005007777945138514
2023-01-24 10:12:58.105247: step: 416/533, loss: 0.004207795951515436
2023-01-24 10:12:59.197564: step: 420/533, loss: 0.0001733555836835876
2023-01-24 10:13:00.332966: step: 424/533, loss: 0.0010762350866571069
2023-01-24 10:13:01.426545: step: 428/533, loss: 0.00029618735425174236
2023-01-24 10:13:02.517362: step: 432/533, loss: 0.003920475021004677
2023-01-24 10:13:03.609994: step: 436/533, loss: 0.0013512646546587348
2023-01-24 10:13:04.710912: step: 440/533, loss: 0.0035405505914241076
2023-01-24 10:13:05.817215: step: 444/533, loss: 0.0049911849200725555
2023-01-24 10:13:06.921839: step: 448/533, loss: 0.0040571801364421844
2023-01-24 10:13:08.021714: step: 452/533, loss: 0.0005463521229103208
2023-01-24 10:13:09.136639: step: 456/533, loss: 0.00010745752661023289
2023-01-24 10:13:10.252615: step: 460/533, loss: 0.002180763054639101
2023-01-24 10:13:11.376215: step: 464/533, loss: 0.0032978085801005363
2023-01-24 10:13:12.440452: step: 468/533, loss: 0.0010633519850671291
2023-01-24 10:13:13.526650: step: 472/533, loss: 0.0018555995775386691
2023-01-24 10:13:14.628347: step: 476/533, loss: 0.0022688212338835
2023-01-24 10:13:15.716315: step: 480/533, loss: 3.6423148230824154e-06
2023-01-24 10:13:16.807633: step: 484/533, loss: 0.0027841171249747276
2023-01-24 10:13:17.897225: step: 488/533, loss: 1.368441735394299e-05
2023-01-24 10:13:19.010913: step: 492/533, loss: 0.004436892922967672
2023-01-24 10:13:20.120980: step: 496/533, loss: 0.00330473599024117
2023-01-24 10:13:21.203223: step: 500/533, loss: 0.001467104651965201
2023-01-24 10:13:22.276596: step: 504/533, loss: 0.0006060199812054634
2023-01-24 10:13:23.379730: step: 508/533, loss: 2.5414410629309714e-05
2023-01-24 10:13:24.477179: step: 512/533, loss: 0.029414743185043335
2023-01-24 10:13:25.555322: step: 516/533, loss: 0.01221733819693327
2023-01-24 10:13:26.650443: step: 520/533, loss: 0.003477820660918951
2023-01-24 10:13:27.734973: step: 524/533, loss: 0.0026301539037376642
2023-01-24 10:13:28.821115: step: 528/533, loss: 0.0019434090936556458
2023-01-24 10:13:29.911893: step: 532/533, loss: 0.004290147218853235
2023-01-24 10:13:31.004615: step: 536/533, loss: 0.00025236408691853285
2023-01-24 10:13:32.128608: step: 540/533, loss: 0.003763454733416438
2023-01-24 10:13:33.250244: step: 544/533, loss: 0.011676069349050522
2023-01-24 10:13:34.347350: step: 548/533, loss: 0.005779169034212828
2023-01-24 10:13:35.437827: step: 552/533, loss: 0.00594358891248703
2023-01-24 10:13:36.548354: step: 556/533, loss: 0.006297259125858545
2023-01-24 10:13:37.646291: step: 560/533, loss: 0.0003840004210360348
2023-01-24 10:13:38.738050: step: 564/533, loss: 0.0002484287542756647
2023-01-24 10:13:39.842395: step: 568/533, loss: 0.003555877599865198
2023-01-24 10:13:40.946614: step: 572/533, loss: 0.0035104798153042793
2023-01-24 10:13:42.041125: step: 576/533, loss: 0.0002129197819158435
2023-01-24 10:13:43.122376: step: 580/533, loss: 0.0011042358819395304
2023-01-24 10:13:44.229674: step: 584/533, loss: 6.797090463805944e-05
2023-01-24 10:13:45.345882: step: 588/533, loss: 0.002270652446895838
2023-01-24 10:13:46.432568: step: 592/533, loss: 0.00028929763357155025
2023-01-24 10:13:47.525887: step: 596/533, loss: 0.005641954019665718
2023-01-24 10:13:48.627330: step: 600/533, loss: 0.001451905001886189
2023-01-24 10:13:49.704688: step: 604/533, loss: 0.0011659783776849508
2023-01-24 10:13:50.802482: step: 608/533, loss: 6.3449069784837775e-06
2023-01-24 10:13:51.891335: step: 612/533, loss: 0.00014382207882590592
2023-01-24 10:13:52.977123: step: 616/533, loss: 0.0036450496409088373
2023-01-24 10:13:54.066483: step: 620/533, loss: 0.0009822043357416987
2023-01-24 10:13:55.178729: step: 624/533, loss: 0.00510006956756115
2023-01-24 10:13:56.255850: step: 628/533, loss: 0.0008576105465181172
2023-01-24 10:13:57.339379: step: 632/533, loss: 0.004443850833922625
2023-01-24 10:13:58.433679: step: 636/533, loss: 0.007367939222604036
2023-01-24 10:13:59.548249: step: 640/533, loss: 0.00013071924331597984
2023-01-24 10:14:00.623765: step: 644/533, loss: 0.0007797309663146734
2023-01-24 10:14:01.716652: step: 648/533, loss: 0.02259058691561222
2023-01-24 10:14:02.816029: step: 652/533, loss: 0.001063498784787953
2023-01-24 10:14:03.917621: step: 656/533, loss: 0.0006826447788625956
2023-01-24 10:14:05.017847: step: 660/533, loss: 0.002072249073535204
2023-01-24 10:14:06.102277: step: 664/533, loss: 0.005938853602856398
2023-01-24 10:14:07.211304: step: 668/533, loss: 0.002149818232282996
2023-01-24 10:14:08.302255: step: 672/533, loss: 0.0005651297979056835
2023-01-24 10:14:09.397022: step: 676/533, loss: 0.00577884167432785
2023-01-24 10:14:10.497263: step: 680/533, loss: 0.008090972900390625
2023-01-24 10:14:11.600383: step: 684/533, loss: 0.005390999373048544
2023-01-24 10:14:12.740105: step: 688/533, loss: 0.0016074719605967402
2023-01-24 10:14:13.826219: step: 692/533, loss: 0.000481416325783357
2023-01-24 10:14:14.923614: step: 696/533, loss: 0.005768462549895048
2023-01-24 10:14:16.043728: step: 700/533, loss: 0.012341530062258244
2023-01-24 10:14:17.150428: step: 704/533, loss: 0.00028129067504778504
2023-01-24 10:14:18.296979: step: 708/533, loss: 0.004366698674857616
2023-01-24 10:14:19.399095: step: 712/533, loss: 0.0024709715507924557
2023-01-24 10:14:20.493715: step: 716/533, loss: 0.0015704536344856024
2023-01-24 10:14:21.598351: step: 720/533, loss: 0.0043671042658388615
2023-01-24 10:14:22.684184: step: 724/533, loss: 0.003589223138988018
2023-01-24 10:14:23.783664: step: 728/533, loss: 0.0005789348506368697
2023-01-24 10:14:24.863165: step: 732/533, loss: 9.109736129175872e-05
2023-01-24 10:14:25.950195: step: 736/533, loss: 0.0013455174630507827
2023-01-24 10:14:27.051039: step: 740/533, loss: 5.3111416491447017e-05
2023-01-24 10:14:28.136373: step: 744/533, loss: 0.0007297784904949367
2023-01-24 10:14:29.228037: step: 748/533, loss: 1.3447809578792658e-05
2023-01-24 10:14:30.328574: step: 752/533, loss: 0.0002640521270222962
2023-01-24 10:14:31.436847: step: 756/533, loss: 0.006397965829819441
2023-01-24 10:14:32.511881: step: 760/533, loss: 0.004281010944396257
2023-01-24 10:14:33.590059: step: 764/533, loss: 0.00045038986718282104
2023-01-24 10:14:34.667740: step: 768/533, loss: 0.0041498057544231415
2023-01-24 10:14:35.778781: step: 772/533, loss: 0.001196471625007689
2023-01-24 10:14:36.886920: step: 776/533, loss: 0.007737394887953997
2023-01-24 10:14:37.976240: step: 780/533, loss: 0.00019581425294745713
2023-01-24 10:14:39.062336: step: 784/533, loss: 0.004007205367088318
2023-01-24 10:14:40.156366: step: 788/533, loss: 0.0006900871521793306
2023-01-24 10:14:41.254009: step: 792/533, loss: 0.00013120073708705604
2023-01-24 10:14:42.363943: step: 796/533, loss: 0.014397312887012959
2023-01-24 10:14:43.436094: step: 800/533, loss: 0.0018165010260418057
2023-01-24 10:14:44.533016: step: 804/533, loss: 0.0027290789876133204
2023-01-24 10:14:45.651832: step: 808/533, loss: 0.0042579639703035355
2023-01-24 10:14:46.754339: step: 812/533, loss: 0.00011248866212554276
2023-01-24 10:14:47.850971: step: 816/533, loss: 0.0030733945313841105
2023-01-24 10:14:48.950251: step: 820/533, loss: 0.001302038668654859
2023-01-24 10:14:50.044800: step: 824/533, loss: 7.971973445819458e-07
2023-01-24 10:14:51.147411: step: 828/533, loss: 0.0037807938642799854
2023-01-24 10:14:52.256798: step: 832/533, loss: 0.005457732360810041
2023-01-24 10:14:53.351738: step: 836/533, loss: 0.004512487445026636
2023-01-24 10:14:54.440779: step: 840/533, loss: 0.002170076360926032
2023-01-24 10:14:55.527103: step: 844/533, loss: 0.0008860263624228537
2023-01-24 10:14:56.604081: step: 848/533, loss: 0.00019949537818320096
2023-01-24 10:14:57.688526: step: 852/533, loss: 0.0003205246466677636
2023-01-24 10:14:58.818429: step: 856/533, loss: 0.0014557414688169956
2023-01-24 10:14:59.918018: step: 860/533, loss: 0.0042099482379853725
2023-01-24 10:15:01.020340: step: 864/533, loss: 0.004473040346056223
2023-01-24 10:15:02.124737: step: 868/533, loss: 0.0001644704316277057
2023-01-24 10:15:03.236531: step: 872/533, loss: 0.00026523208362050354
2023-01-24 10:15:04.337240: step: 876/533, loss: 0.003267372725531459
2023-01-24 10:15:05.438375: step: 880/533, loss: 0.000174522225279361
2023-01-24 10:15:06.531509: step: 884/533, loss: 0.00925154983997345
2023-01-24 10:15:07.629159: step: 888/533, loss: 0.0008707995293661952
2023-01-24 10:15:08.735346: step: 892/533, loss: 1.11588697109255e-05
2023-01-24 10:15:09.824035: step: 896/533, loss: 0.004479663446545601
2023-01-24 10:15:10.905630: step: 900/533, loss: 0.003360830945894122
2023-01-24 10:15:11.989416: step: 904/533, loss: 0.005443373695015907
2023-01-24 10:15:13.094405: step: 908/533, loss: 0.000150375155499205
2023-01-24 10:15:14.194973: step: 912/533, loss: 0.007922984659671783
2023-01-24 10:15:15.296800: step: 916/533, loss: 7.2155348789237905e-06
2023-01-24 10:15:16.376210: step: 920/533, loss: 0.0025405832566320896
2023-01-24 10:15:17.473530: step: 924/533, loss: 0.007104810327291489
2023-01-24 10:15:18.588367: step: 928/533, loss: 0.003462539054453373
2023-01-24 10:15:19.688174: step: 932/533, loss: 0.0029969196766614914
2023-01-24 10:15:20.791500: step: 936/533, loss: 0.0057390914298594
2023-01-24 10:15:21.904127: step: 940/533, loss: 0.0003970266552641988
2023-01-24 10:15:23.004033: step: 944/533, loss: 0.0009326048893854022
2023-01-24 10:15:24.105610: step: 948/533, loss: 0.005636975634843111
2023-01-24 10:15:25.189881: step: 952/533, loss: 0.0030398883391171694
2023-01-24 10:15:26.299104: step: 956/533, loss: 0.004231573082506657
2023-01-24 10:15:27.372682: step: 960/533, loss: 0.001568461419083178
2023-01-24 10:15:28.491737: step: 964/533, loss: 0.0056822882033884525
2023-01-24 10:15:29.602048: step: 968/533, loss: 0.007191978860646486
2023-01-24 10:15:30.687334: step: 972/533, loss: 0.0030804642010480165
2023-01-24 10:15:31.801183: step: 976/533, loss: 0.0012866631150245667
2023-01-24 10:15:32.896934: step: 980/533, loss: 0.002389132510870695
2023-01-24 10:15:34.009023: step: 984/533, loss: 0.002482391195371747
2023-01-24 10:15:35.089089: step: 988/533, loss: 0.0015236112521961331
2023-01-24 10:15:36.170499: step: 992/533, loss: 0.0036275158636271954
2023-01-24 10:15:37.267386: step: 996/533, loss: 0.0012296775821596384
2023-01-24 10:15:38.373251: step: 1000/533, loss: 6.330913311103359e-05
2023-01-24 10:15:39.466780: step: 1004/533, loss: 0.0002371250739088282
2023-01-24 10:15:40.550254: step: 1008/533, loss: 0.0018764325650408864
2023-01-24 10:15:41.637565: step: 1012/533, loss: 0.005854928866028786
2023-01-24 10:15:42.740913: step: 1016/533, loss: 0.0022538267076015472
2023-01-24 10:15:43.831913: step: 1020/533, loss: 0.0036579640582203865
2023-01-24 10:15:44.952369: step: 1024/533, loss: 0.0040265233255922794
2023-01-24 10:15:46.054955: step: 1028/533, loss: 0.0003079830203205347
2023-01-24 10:15:47.152357: step: 1032/533, loss: 0.00025854873820208013
2023-01-24 10:15:48.276142: step: 1036/533, loss: 0.00033699936466291547
2023-01-24 10:15:49.391961: step: 1040/533, loss: 0.007712732069194317
2023-01-24 10:15:50.478083: step: 1044/533, loss: 0.010020319372415543
2023-01-24 10:15:51.559464: step: 1048/533, loss: 0.002344088861718774
2023-01-24 10:15:52.659342: step: 1052/533, loss: 0.007637407165020704
2023-01-24 10:15:53.753308: step: 1056/533, loss: 0.005171115975826979
2023-01-24 10:15:54.853179: step: 1060/533, loss: 0.0021107362117618322
2023-01-24 10:15:55.952893: step: 1064/533, loss: 0.0001524565159343183
2023-01-24 10:15:57.047906: step: 1068/533, loss: 0.0016333898529410362
2023-01-24 10:15:58.136689: step: 1072/533, loss: 0.004824764560908079
2023-01-24 10:15:59.229689: step: 1076/533, loss: 0.027853094041347504
2023-01-24 10:16:00.316512: step: 1080/533, loss: 0.002095442032441497
2023-01-24 10:16:01.422049: step: 1084/533, loss: 2.3890814190963283e-05
2023-01-24 10:16:02.498775: step: 1088/533, loss: 0.00023271790996659547
2023-01-24 10:16:03.598458: step: 1092/533, loss: 0.002567504532635212
2023-01-24 10:16:04.682453: step: 1096/533, loss: 0.0015531450044363737
2023-01-24 10:16:05.778258: step: 1100/533, loss: 0.0036640088073909283
2023-01-24 10:16:06.885500: step: 1104/533, loss: 0.00021314255718607455
2023-01-24 10:16:07.978259: step: 1108/533, loss: 0.00020403970847837627
2023-01-24 10:16:09.070459: step: 1112/533, loss: 0.00010649573960108683
2023-01-24 10:16:10.197465: step: 1116/533, loss: 0.003856595838442445
2023-01-24 10:16:11.293443: step: 1120/533, loss: 0.0030984317418187857
2023-01-24 10:16:12.379460: step: 1124/533, loss: 0.0008268175879493356
2023-01-24 10:16:13.461851: step: 1128/533, loss: 0.0035364481154829264
2023-01-24 10:16:14.563480: step: 1132/533, loss: 0.0019064474618062377
2023-01-24 10:16:15.690298: step: 1136/533, loss: 0.0001196812663692981
2023-01-24 10:16:16.787491: step: 1140/533, loss: 0.005862274207174778
2023-01-24 10:16:17.866171: step: 1144/533, loss: 0.0012001566356047988
2023-01-24 10:16:18.959181: step: 1148/533, loss: 0.002966964151710272
2023-01-24 10:16:20.062514: step: 1152/533, loss: 0.005717375315725803
2023-01-24 10:16:21.177935: step: 1156/533, loss: 0.005004387814551592
2023-01-24 10:16:22.281160: step: 1160/533, loss: 0.0011654195841401815
2023-01-24 10:16:23.382739: step: 1164/533, loss: 0.009293054230511189
2023-01-24 10:16:24.488298: step: 1168/533, loss: 0.0018414383521303535
2023-01-24 10:16:25.586903: step: 1172/533, loss: 0.0029561121482402086
2023-01-24 10:16:26.673131: step: 1176/533, loss: 0.002001096261665225
2023-01-24 10:16:27.774832: step: 1180/533, loss: 0.009331459179520607
2023-01-24 10:16:28.876548: step: 1184/533, loss: 0.0014758583856746554
2023-01-24 10:16:29.964589: step: 1188/533, loss: 0.004002986941486597
2023-01-24 10:16:31.042189: step: 1192/533, loss: 8.003373295650817e-06
2023-01-24 10:16:32.121189: step: 1196/533, loss: 0.0018830219050869346
2023-01-24 10:16:33.193267: step: 1200/533, loss: 0.0007164053386077285
2023-01-24 10:16:34.299362: step: 1204/533, loss: 0.0019999255891889334
2023-01-24 10:16:35.378040: step: 1208/533, loss: 0.004068983718752861
2023-01-24 10:16:36.473789: step: 1212/533, loss: 0.003109771991148591
2023-01-24 10:16:37.549160: step: 1216/533, loss: 0.002929655136540532
2023-01-24 10:16:38.643845: step: 1220/533, loss: 7.552983151981607e-05
2023-01-24 10:16:39.730024: step: 1224/533, loss: 0.005683601833879948
2023-01-24 10:16:40.820988: step: 1228/533, loss: 0.02499091997742653
2023-01-24 10:16:41.911776: step: 1232/533, loss: 0.002397323725745082
2023-01-24 10:16:43.026887: step: 1236/533, loss: 0.0011376288020983338
2023-01-24 10:16:44.092860: step: 1240/533, loss: 0.008976047858595848
2023-01-24 10:16:45.181909: step: 1244/533, loss: 0.004628659226000309
2023-01-24 10:16:46.279330: step: 1248/533, loss: 0.0007278687553480268
2023-01-24 10:16:47.350962: step: 1252/533, loss: 0.0006860348512418568
2023-01-24 10:16:48.464222: step: 1256/533, loss: 0.001238387543708086
2023-01-24 10:16:49.555821: step: 1260/533, loss: 0.004206634126603603
2023-01-24 10:16:50.656688: step: 1264/533, loss: 1.0646324881236069e-05
2023-01-24 10:16:51.733378: step: 1268/533, loss: 0.004561436362564564
2023-01-24 10:16:52.816143: step: 1272/533, loss: 0.007293396163731813
2023-01-24 10:16:53.911280: step: 1276/533, loss: 0.006394236348569393
2023-01-24 10:16:55.008866: step: 1280/533, loss: 0.0017830673605203629
2023-01-24 10:16:56.089661: step: 1284/533, loss: 0.00016062251233961433
2023-01-24 10:16:57.203080: step: 1288/533, loss: 0.015475285239517689
2023-01-24 10:16:58.283527: step: 1292/533, loss: 0.0009722411632537842
2023-01-24 10:16:59.370268: step: 1296/533, loss: 0.00824839435517788
2023-01-24 10:17:00.459827: step: 1300/533, loss: 0.03792582079768181
2023-01-24 10:17:01.585828: step: 1304/533, loss: 0.0003535341820679605
2023-01-24 10:17:02.680517: step: 1308/533, loss: 0.003059917129576206
2023-01-24 10:17:03.771274: step: 1312/533, loss: 0.003900732845067978
2023-01-24 10:17:04.885879: step: 1316/533, loss: 0.0011576401302590966
2023-01-24 10:17:06.000398: step: 1320/533, loss: 5.309830521582626e-05
2023-01-24 10:17:07.088880: step: 1324/533, loss: 0.005928587634116411
2023-01-24 10:17:08.189580: step: 1328/533, loss: 0.00019149213039781898
2023-01-24 10:17:09.275517: step: 1332/533, loss: 6.822309660492465e-05
2023-01-24 10:17:10.373478: step: 1336/533, loss: 0.002904194872826338
2023-01-24 10:17:11.492489: step: 1340/533, loss: 0.013054164126515388
2023-01-24 10:17:12.617487: step: 1344/533, loss: 0.0024712628219276667
2023-01-24 10:17:13.714905: step: 1348/533, loss: 0.0018989392556250095
2023-01-24 10:17:14.820286: step: 1352/533, loss: 0.004472807515412569
2023-01-24 10:17:15.908777: step: 1356/533, loss: 3.063756230403669e-05
2023-01-24 10:17:16.994809: step: 1360/533, loss: 0.0016155593330040574
2023-01-24 10:17:18.085208: step: 1364/533, loss: 0.0022709271870553493
2023-01-24 10:17:19.195928: step: 1368/533, loss: 0.0004591657198034227
2023-01-24 10:17:20.278990: step: 1372/533, loss: 2.5773617380764335e-05
2023-01-24 10:17:21.359870: step: 1376/533, loss: 0.00016566613339819014
2023-01-24 10:17:22.459087: step: 1380/533, loss: 0.0009378889226354659
2023-01-24 10:17:23.541579: step: 1384/533, loss: 0.0012013090308755636
2023-01-24 10:17:24.631156: step: 1388/533, loss: 0.0026272593531757593
2023-01-24 10:17:25.758372: step: 1392/533, loss: 0.0013985797995701432
2023-01-24 10:17:26.844013: step: 1396/533, loss: 2.5368279921167414e-07
2023-01-24 10:17:27.917361: step: 1400/533, loss: 0.0004161988908890635
2023-01-24 10:17:28.992570: step: 1404/533, loss: 8.664534107083455e-05
2023-01-24 10:17:30.061521: step: 1408/533, loss: 9.645934369473252e-06
2023-01-24 10:17:31.145896: step: 1412/533, loss: 0.0024793611373752356
2023-01-24 10:17:32.237997: step: 1416/533, loss: 0.0004564561531879008
2023-01-24 10:17:33.331688: step: 1420/533, loss: 0.003552953014150262
2023-01-24 10:17:34.437406: step: 1424/533, loss: 0.00015635447925888002
2023-01-24 10:17:35.528848: step: 1428/533, loss: 0.0011051121400669217
2023-01-24 10:17:36.613721: step: 1432/533, loss: 0.0036787448916584253
2023-01-24 10:17:37.707670: step: 1436/533, loss: 0.0007287077605724335
2023-01-24 10:17:38.835000: step: 1440/533, loss: 0.0014277034206315875
2023-01-24 10:17:39.930795: step: 1444/533, loss: 0.0019347977358847857
2023-01-24 10:17:41.046855: step: 1448/533, loss: 0.0008331290446221828
2023-01-24 10:17:42.151265: step: 1452/533, loss: 0.010528255254030228
2023-01-24 10:17:43.243563: step: 1456/533, loss: 0.011107956990599632
2023-01-24 10:17:44.346211: step: 1460/533, loss: 0.001899199327453971
2023-01-24 10:17:45.431564: step: 1464/533, loss: 0.0005653625121340156
2023-01-24 10:17:46.553932: step: 1468/533, loss: 0.0025783120654523373
2023-01-24 10:17:47.635355: step: 1472/533, loss: 0.0001272145746042952
2023-01-24 10:17:48.737595: step: 1476/533, loss: 0.0032576490193605423
2023-01-24 10:17:49.834848: step: 1480/533, loss: 0.001436434919014573
2023-01-24 10:17:50.958343: step: 1484/533, loss: 0.00034526779199950397
2023-01-24 10:17:52.061303: step: 1488/533, loss: 0.008598732762038708
2023-01-24 10:17:53.167848: step: 1492/533, loss: 0.00114924693480134
2023-01-24 10:17:54.256824: step: 1496/533, loss: 0.0002077439712593332
2023-01-24 10:17:55.332791: step: 1500/533, loss: 5.0621638365555555e-05
2023-01-24 10:17:56.435163: step: 1504/533, loss: 0.009059310890734196
2023-01-24 10:17:57.516005: step: 1508/533, loss: 0.00032027362613007426
2023-01-24 10:17:58.598666: step: 1512/533, loss: 0.0003150522825308144
2023-01-24 10:17:59.681606: step: 1516/533, loss: 0.0002183937467634678
2023-01-24 10:18:00.757062: step: 1520/533, loss: 0.0029115304350852966
2023-01-24 10:18:01.830882: step: 1524/533, loss: 0.007359171751886606
2023-01-24 10:18:02.931952: step: 1528/533, loss: 0.00037611546576954424
2023-01-24 10:18:04.039997: step: 1532/533, loss: 0.0031488039530813694
2023-01-24 10:18:05.166520: step: 1536/533, loss: 0.0015551394317299128
2023-01-24 10:18:06.257816: step: 1540/533, loss: 0.0012384300353005528
2023-01-24 10:18:07.347939: step: 1544/533, loss: 9.652330845710821e-06
2023-01-24 10:18:08.435945: step: 1548/533, loss: 0.008549907244741917
2023-01-24 10:18:09.550386: step: 1552/533, loss: 0.00028127123368903995
2023-01-24 10:18:10.661499: step: 1556/533, loss: 0.005977772641927004
2023-01-24 10:18:11.760926: step: 1560/533, loss: 0.0003216448239982128
2023-01-24 10:18:12.877010: step: 1564/533, loss: 3.590633014027844e-06
2023-01-24 10:18:14.005405: step: 1568/533, loss: 0.004501028917729855
2023-01-24 10:18:15.123121: step: 1572/533, loss: 0.0002870613825507462
2023-01-24 10:18:16.201195: step: 1576/533, loss: 0.006521498318761587
2023-01-24 10:18:17.279972: step: 1580/533, loss: 0.012084666639566422
2023-01-24 10:18:18.386989: step: 1584/533, loss: 0.0005747171817347407
2023-01-24 10:18:19.477566: step: 1588/533, loss: 4.944249667460099e-05
2023-01-24 10:18:20.563604: step: 1592/533, loss: 0.0016278194962069392
2023-01-24 10:18:21.661250: step: 1596/533, loss: 0.0014248465886339545
2023-01-24 10:18:22.774433: step: 1600/533, loss: 0.0005522174178622663
2023-01-24 10:18:23.897709: step: 1604/533, loss: 0.0024106460623443127
2023-01-24 10:18:24.984978: step: 1608/533, loss: 1.4888228179188445e-05
2023-01-24 10:18:26.093988: step: 1612/533, loss: 0.0008557833498343825
2023-01-24 10:18:27.181434: step: 1616/533, loss: 0.0067607141099870205
2023-01-24 10:18:28.260539: step: 1620/533, loss: 0.00010413616837467998
2023-01-24 10:18:29.347611: step: 1624/533, loss: 0.004895301070064306
2023-01-24 10:18:30.464081: step: 1628/533, loss: 0.027310524135828018
2023-01-24 10:18:31.539904: step: 1632/533, loss: 0.005383253563195467
2023-01-24 10:18:32.629014: step: 1636/533, loss: 0.012554661370813847
2023-01-24 10:18:33.736123: step: 1640/533, loss: 0.010049236938357353
2023-01-24 10:18:34.819096: step: 1644/533, loss: 0.00012109882663935423
2023-01-24 10:18:35.927963: step: 1648/533, loss: 0.028772370889782906
2023-01-24 10:18:37.010086: step: 1652/533, loss: 0.008093871176242828
2023-01-24 10:18:38.130705: step: 1656/533, loss: 0.008715897798538208
2023-01-24 10:18:39.247903: step: 1660/533, loss: 0.0006298307562246919
2023-01-24 10:18:40.370464: step: 1664/533, loss: 0.025447813794016838
2023-01-24 10:18:41.468807: step: 1668/533, loss: 0.004883204586803913
2023-01-24 10:18:42.542580: step: 1672/533, loss: 0.0031102667562663555
2023-01-24 10:18:43.649902: step: 1676/533, loss: 0.0037120268680155277
2023-01-24 10:18:44.763053: step: 1680/533, loss: 9.486189810559154e-05
2023-01-24 10:18:45.860954: step: 1684/533, loss: 0.0016714378725737333
2023-01-24 10:18:46.960352: step: 1688/533, loss: 0.004674609750509262
2023-01-24 10:18:48.060324: step: 1692/533, loss: 0.004026324488222599
2023-01-24 10:18:49.172391: step: 1696/533, loss: 0.0057922047562897205
2023-01-24 10:18:50.280615: step: 1700/533, loss: 0.021139536052942276
2023-01-24 10:18:51.364380: step: 1704/533, loss: 8.092859206954017e-05
2023-01-24 10:18:52.447424: step: 1708/533, loss: 0.0037019059527665377
2023-01-24 10:18:53.541933: step: 1712/533, loss: 0.0015728414291515946
2023-01-24 10:18:54.627298: step: 1716/533, loss: 0.0064818887040019035
2023-01-24 10:18:55.709173: step: 1720/533, loss: 0.0042629605159163475
2023-01-24 10:18:56.784493: step: 1724/533, loss: 0.01647437922656536
2023-01-24 10:18:57.869423: step: 1728/533, loss: 0.000924134103115648
2023-01-24 10:18:58.978601: step: 1732/533, loss: 0.012348723597824574
2023-01-24 10:19:00.059750: step: 1736/533, loss: 0.002834076527506113
2023-01-24 10:19:01.136931: step: 1740/533, loss: 0.0014643965987488627
2023-01-24 10:19:02.212060: step: 1744/533, loss: 0.002757522277534008
2023-01-24 10:19:03.319908: step: 1748/533, loss: 0.004313614219427109
2023-01-24 10:19:04.405134: step: 1752/533, loss: 0.00013597954239230603
2023-01-24 10:19:05.516743: step: 1756/533, loss: 0.010961191728711128
2023-01-24 10:19:06.620549: step: 1760/533, loss: 0.008589433506131172
2023-01-24 10:19:07.735775: step: 1764/533, loss: 0.0014757303288206458
2023-01-24 10:19:08.840812: step: 1768/533, loss: 6.358225073199719e-05
2023-01-24 10:19:09.946951: step: 1772/533, loss: 0.003339791903272271
2023-01-24 10:19:11.033193: step: 1776/533, loss: 0.004539866931736469
2023-01-24 10:19:12.140254: step: 1780/533, loss: 0.003348962403833866
2023-01-24 10:19:13.227418: step: 1784/533, loss: 0.004149759653955698
2023-01-24 10:19:14.321101: step: 1788/533, loss: 0.008146613836288452
2023-01-24 10:19:15.435859: step: 1792/533, loss: 0.01002760510891676
2023-01-24 10:19:16.520025: step: 1796/533, loss: 0.002688026987016201
2023-01-24 10:19:17.621194: step: 1800/533, loss: 0.005398971494287252
2023-01-24 10:19:18.740610: step: 1804/533, loss: 0.006903204135596752
2023-01-24 10:19:19.849129: step: 1808/533, loss: 0.0028953521978110075
2023-01-24 10:19:20.970864: step: 1812/533, loss: 0.007598459254950285
2023-01-24 10:19:22.049632: step: 1816/533, loss: 0.006448944564908743
2023-01-24 10:19:23.135605: step: 1820/533, loss: 4.770908708451316e-05
2023-01-24 10:19:24.227704: step: 1824/533, loss: 0.0014981756685301661
2023-01-24 10:19:25.319346: step: 1828/533, loss: 0.001831358764320612
2023-01-24 10:19:26.442337: step: 1832/533, loss: 0.0014983119908720255
2023-01-24 10:19:27.537488: step: 1836/533, loss: 0.009631932713091373
2023-01-24 10:19:28.655236: step: 1840/533, loss: 0.007191481534391642
2023-01-24 10:19:29.749119: step: 1844/533, loss: 0.003957523498684168
2023-01-24 10:19:30.851977: step: 1848/533, loss: 0.0010460205376148224
2023-01-24 10:19:31.930788: step: 1852/533, loss: 0.0005718767642974854
2023-01-24 10:19:33.020270: step: 1856/533, loss: 0.0016806506318971515
2023-01-24 10:19:34.104247: step: 1860/533, loss: 0.00473020039498806
2023-01-24 10:19:35.205418: step: 1864/533, loss: 0.0019366309279575944
2023-01-24 10:19:36.285450: step: 1868/533, loss: 0.006527764722704887
2023-01-24 10:19:37.384605: step: 1872/533, loss: 9.721149399410933e-05
2023-01-24 10:19:38.493958: step: 1876/533, loss: 0.007584711071103811
2023-01-24 10:19:39.601708: step: 1880/533, loss: 0.027894994243979454
2023-01-24 10:19:40.710272: step: 1884/533, loss: 0.0058264234103262424
2023-01-24 10:19:41.806289: step: 1888/533, loss: 0.004142390564084053
2023-01-24 10:19:42.942508: step: 1892/533, loss: 0.002360124606639147
2023-01-24 10:19:44.030170: step: 1896/533, loss: 0.0038905201945453882
2023-01-24 10:19:45.131579: step: 1900/533, loss: 0.0056654224172234535
2023-01-24 10:19:46.230915: step: 1904/533, loss: 0.0074616107158362865
2023-01-24 10:19:47.318548: step: 1908/533, loss: 0.009747428819537163
2023-01-24 10:19:48.410791: step: 1912/533, loss: 0.0010841217590495944
2023-01-24 10:19:49.502682: step: 1916/533, loss: 0.0031346846371889114
2023-01-24 10:19:50.628190: step: 1920/533, loss: 0.0023832698352634907
2023-01-24 10:19:51.738208: step: 1924/533, loss: 0.0027656354941427708
2023-01-24 10:19:52.835927: step: 1928/533, loss: 0.0014487991575151682
2023-01-24 10:19:53.927444: step: 1932/533, loss: 0.005521680228412151
2023-01-24 10:19:55.021513: step: 1936/533, loss: 0.007741387002170086
2023-01-24 10:19:56.110849: step: 1940/533, loss: 0.007091823499649763
2023-01-24 10:19:57.201898: step: 1944/533, loss: 0.004733461886644363
2023-01-24 10:19:58.292795: step: 1948/533, loss: 0.008046519011259079
2023-01-24 10:19:59.375677: step: 1952/533, loss: 0.003084833500906825
2023-01-24 10:20:00.482245: step: 1956/533, loss: 0.009081747382879257
2023-01-24 10:20:01.584405: step: 1960/533, loss: 7.242261926876381e-05
2023-01-24 10:20:02.709837: step: 1964/533, loss: 0.0051553514786064625
2023-01-24 10:20:03.788486: step: 1968/533, loss: 2.2728590920451097e-05
2023-01-24 10:20:04.896523: step: 1972/533, loss: 0.005268563982099295
2023-01-24 10:20:05.988130: step: 1976/533, loss: 0.009896432049572468
2023-01-24 10:20:07.070503: step: 1980/533, loss: 0.00475313188508153
2023-01-24 10:20:08.146692: step: 1984/533, loss: 0.0006820019334554672
2023-01-24 10:20:09.254017: step: 1988/533, loss: 0.0014968231553211808
2023-01-24 10:20:10.352436: step: 1992/533, loss: 0.021235883235931396
2023-01-24 10:20:11.441657: step: 1996/533, loss: 0.0021941522136330605
2023-01-24 10:20:12.529988: step: 2000/533, loss: 0.004522593691945076
2023-01-24 10:20:13.619684: step: 2004/533, loss: 0.0012486609630286694
2023-01-24 10:20:14.714436: step: 2008/533, loss: 0.0021793036721646786
2023-01-24 10:20:15.812070: step: 2012/533, loss: 0.00204588589258492
2023-01-24 10:20:16.892647: step: 2016/533, loss: 0.0006610504351556301
2023-01-24 10:20:17.992849: step: 2020/533, loss: 0.006211029831320047
2023-01-24 10:20:19.069800: step: 2024/533, loss: 0.00023648684145882726
2023-01-24 10:20:20.168201: step: 2028/533, loss: 0.0
2023-01-24 10:20:21.252687: step: 2032/533, loss: 0.00960368663072586
2023-01-24 10:20:22.403340: step: 2036/533, loss: 0.003502683714032173
2023-01-24 10:20:23.502747: step: 2040/533, loss: 0.0028324599843472242
2023-01-24 10:20:24.582755: step: 2044/533, loss: 0.0006842349539510906
2023-01-24 10:20:25.669464: step: 2048/533, loss: 0.00021361598919611424
2023-01-24 10:20:26.734225: step: 2052/533, loss: 0.0002972499351017177
2023-01-24 10:20:27.812501: step: 2056/533, loss: 0.0002675220603123307
2023-01-24 10:20:28.900622: step: 2060/533, loss: 0.003177470061928034
2023-01-24 10:20:29.992721: step: 2064/533, loss: 0.00252855964936316
2023-01-24 10:20:31.074344: step: 2068/533, loss: 0.00010808667138917372
2023-01-24 10:20:32.169867: step: 2072/533, loss: 0.01042440626770258
2023-01-24 10:20:33.253778: step: 2076/533, loss: 0.00014456131611950696
2023-01-24 10:20:34.322728: step: 2080/533, loss: 0.013087878003716469
2023-01-24 10:20:35.444297: step: 2084/533, loss: 0.0035043267998844385
2023-01-24 10:20:36.563793: step: 2088/533, loss: 0.00039808297879062593
2023-01-24 10:20:37.658066: step: 2092/533, loss: 0.005782985128462315
2023-01-24 10:20:38.766327: step: 2096/533, loss: 0.0035352257546037436
2023-01-24 10:20:39.863854: step: 2100/533, loss: 0.01574915647506714
2023-01-24 10:20:40.983959: step: 2104/533, loss: 0.0009572178823873401
2023-01-24 10:20:42.051760: step: 2108/533, loss: 7.693147199461237e-05
2023-01-24 10:20:43.134444: step: 2112/533, loss: 0.0012686325935646892
2023-01-24 10:20:44.246819: step: 2116/533, loss: 0.00024097273126244545
2023-01-24 10:20:45.329910: step: 2120/533, loss: 0.0010604930575937033
2023-01-24 10:20:46.423023: step: 2124/533, loss: 0.0003967970551457256
2023-01-24 10:20:47.524991: step: 2128/533, loss: 0.001220724661834538
2023-01-24 10:20:48.633652: step: 2132/533, loss: 0.007710147183388472
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3813366156090445, 'r': 0.33068469323213157, 'f1': 0.3542090108401084}, 'combined': 0.2609961132506062, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3940260435337188, 'r': 0.35803327994169637, 'f1': 0.3751683739439438}, 'combined': 0.2501122492959625, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622453022124075, 'r': 0.3216903253043771, 'f1': 0.340765430020918}, 'combined': 0.25109031685751854, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3882462673689548, 'r': 0.30910375902066783, 'f1': 0.3441840571536344}, 'combined': 0.2294560381024229, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3439326576296481, 'r': 0.30869098113628757, 'f1': 0.3253602941176471}, 'combined': 0.23973916408668733, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38225823051245406, 'r': 0.34697285538822753, 'f1': 0.36376186451991593}, 'combined': 0.2425079096799439, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3467294730392157, 'r': 0.31580673066190423, 'f1': 0.33054646883579647}, 'combined': 0.24356055598427107, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810234081760824, 'r': 0.3407228553882275, 'f1': 0.3597479894454382}, 'combined': 0.2398319929636254, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 1}
******************************
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 10:23:08.046471: step: 4/533, loss: 0.003950439393520355
2023-01-24 10:23:09.110795: step: 8/533, loss: 0.007263805251568556
2023-01-24 10:23:10.174939: step: 12/533, loss: 1.0742717677203473e-05
2023-01-24 10:23:11.261388: step: 16/533, loss: 0.00182864791713655
2023-01-24 10:23:12.348417: step: 20/533, loss: 0.0011350094573572278
2023-01-24 10:23:13.424845: step: 24/533, loss: 0.004684919957071543
2023-01-24 10:23:14.534536: step: 28/533, loss: 0.0016632064944133162
2023-01-24 10:23:15.617185: step: 32/533, loss: 0.0032545903231948614
2023-01-24 10:23:16.714675: step: 36/533, loss: 0.0050168391317129135
2023-01-24 10:23:17.811218: step: 40/533, loss: 0.0005296050803735852
2023-01-24 10:23:18.897195: step: 44/533, loss: 0.0037520411424338818
2023-01-24 10:23:19.997961: step: 48/533, loss: 4.891226490144618e-05
2023-01-24 10:23:21.089461: step: 52/533, loss: 0.0008789235725998878
2023-01-24 10:23:22.164320: step: 56/533, loss: 0.0012338956585153937
2023-01-24 10:23:23.262755: step: 60/533, loss: 0.0019108123378828168
2023-01-24 10:23:24.354909: step: 64/533, loss: 0.014991523697972298
2023-01-24 10:23:25.462506: step: 68/533, loss: 0.0016947853146120906
2023-01-24 10:23:26.550631: step: 72/533, loss: 0.005430115386843681
2023-01-24 10:23:27.639270: step: 76/533, loss: 0.00020558052347041667
2023-01-24 10:23:28.726007: step: 80/533, loss: 9.212242002831772e-05
2023-01-24 10:23:29.796266: step: 84/533, loss: 4.5251170377014205e-05
2023-01-24 10:23:30.875699: step: 88/533, loss: 0.0008485477883368731
2023-01-24 10:23:31.973896: step: 92/533, loss: 0.002646084874868393
2023-01-24 10:23:33.070244: step: 96/533, loss: 0.0027092897798866034
2023-01-24 10:23:34.156306: step: 100/533, loss: 0.002300105756148696
2023-01-24 10:23:35.235994: step: 104/533, loss: 0.0007244906155392528
2023-01-24 10:23:36.334152: step: 108/533, loss: 0.0012139061000198126
2023-01-24 10:23:37.427884: step: 112/533, loss: 0.0064126281067729
2023-01-24 10:23:38.512246: step: 116/533, loss: 0.0012266600970178843
2023-01-24 10:23:39.623826: step: 120/533, loss: 0.015162327326834202
2023-01-24 10:23:40.729216: step: 124/533, loss: 0.01112031564116478
2023-01-24 10:23:41.814574: step: 128/533, loss: 0.0031957104802131653
2023-01-24 10:23:42.899242: step: 132/533, loss: 0.003122711554169655
2023-01-24 10:23:43.982279: step: 136/533, loss: 0.0019189201993867755
2023-01-24 10:23:45.081807: step: 140/533, loss: 0.0057475450448691845
2023-01-24 10:23:46.166203: step: 144/533, loss: 0.0018454153323546052
2023-01-24 10:23:47.256262: step: 148/533, loss: 0.00399413239210844
2023-01-24 10:23:48.345942: step: 152/533, loss: 0.00935183372348547
2023-01-24 10:23:49.422036: step: 156/533, loss: 0.005138451233506203
2023-01-24 10:23:50.515308: step: 160/533, loss: 0.00016625160060357302
2023-01-24 10:23:51.618087: step: 164/533, loss: 0.001949066761881113
2023-01-24 10:23:52.717058: step: 168/533, loss: 0.0047758594155311584
2023-01-24 10:23:53.812662: step: 172/533, loss: 0.0031744944863021374
2023-01-24 10:23:54.909043: step: 176/533, loss: 0.00010407866648165509
2023-01-24 10:23:56.002150: step: 180/533, loss: 0.008021501824259758
2023-01-24 10:23:57.106741: step: 184/533, loss: 0.002023284789174795
2023-01-24 10:23:58.202913: step: 188/533, loss: 0.008799652568995953
2023-01-24 10:23:59.284958: step: 192/533, loss: 0.0011324889492243528
2023-01-24 10:24:00.388024: step: 196/533, loss: 0.004377183970063925
2023-01-24 10:24:01.472656: step: 200/533, loss: 6.617120379814878e-05
2023-01-24 10:24:02.571945: step: 204/533, loss: 0.004759805276989937
2023-01-24 10:24:03.661558: step: 208/533, loss: 0.001278265262953937
2023-01-24 10:24:04.742133: step: 212/533, loss: 0.006741429213434458
2023-01-24 10:24:05.881341: step: 216/533, loss: 0.005145348608493805
2023-01-24 10:24:06.976120: step: 220/533, loss: 0.0037836225237697363
2023-01-24 10:24:08.071192: step: 224/533, loss: 0.0034807457122951746
2023-01-24 10:24:09.180004: step: 228/533, loss: 0.00020054572087246925
2023-01-24 10:24:10.291509: step: 232/533, loss: 0.004516679793596268
2023-01-24 10:24:11.395092: step: 236/533, loss: 0.0001996499195229262
2023-01-24 10:24:12.484871: step: 240/533, loss: 0.00011080123658757657
2023-01-24 10:24:13.599856: step: 244/533, loss: 0.0032462654635310173
2023-01-24 10:24:14.702995: step: 248/533, loss: 0.00114775775000453
2023-01-24 10:24:15.853621: step: 252/533, loss: 0.0020893244072794914
2023-01-24 10:24:16.950114: step: 256/533, loss: 6.446677434723824e-05
2023-01-24 10:24:18.048732: step: 260/533, loss: 0.00018810031178873032
2023-01-24 10:24:19.160850: step: 264/533, loss: 0.0020683433394879103
2023-01-24 10:24:20.270560: step: 268/533, loss: 0.0017390551511198282
2023-01-24 10:24:21.369077: step: 272/533, loss: 0.0003470223746262491
2023-01-24 10:24:22.472896: step: 276/533, loss: 0.005643635056912899
2023-01-24 10:24:23.562062: step: 280/533, loss: 0.0016115170437842607
2023-01-24 10:24:24.648075: step: 284/533, loss: 0.0053515126928687096
2023-01-24 10:24:25.738362: step: 288/533, loss: 0.0017452051397413015
2023-01-24 10:24:26.821576: step: 292/533, loss: 0.0004690744390245527
2023-01-24 10:24:27.910299: step: 296/533, loss: 0.0005994596285745502
2023-01-24 10:24:29.025111: step: 300/533, loss: 0.0021099743898957968
2023-01-24 10:24:30.146812: step: 304/533, loss: 0.003724969457834959
2023-01-24 10:24:31.234684: step: 308/533, loss: 0.0033319289796054363
2023-01-24 10:24:32.326240: step: 312/533, loss: 0.001280790544115007
2023-01-24 10:24:33.415464: step: 316/533, loss: 0.029495850205421448
2023-01-24 10:24:34.506609: step: 320/533, loss: 0.000605663051828742
2023-01-24 10:24:35.619880: step: 324/533, loss: 0.008252566680312157
2023-01-24 10:24:36.727489: step: 328/533, loss: 4.817748504137853e-06
2023-01-24 10:24:37.848069: step: 332/533, loss: 0.0007580813835375011
2023-01-24 10:24:38.940422: step: 336/533, loss: 0.018417859449982643
2023-01-24 10:24:40.049307: step: 340/533, loss: 0.0005041623371653259
2023-01-24 10:24:41.154023: step: 344/533, loss: 0.008928955532610416
2023-01-24 10:24:42.271661: step: 348/533, loss: 0.005696728825569153
2023-01-24 10:24:43.373030: step: 352/533, loss: 0.004768241662532091
2023-01-24 10:24:44.491911: step: 356/533, loss: 0.003773614764213562
2023-01-24 10:24:45.607620: step: 360/533, loss: 0.0018490363145247102
2023-01-24 10:24:46.690220: step: 364/533, loss: 0.006596399936825037
2023-01-24 10:24:47.793277: step: 368/533, loss: 0.005579029209911823
2023-01-24 10:24:48.913002: step: 372/533, loss: 0.11934904754161835
2023-01-24 10:24:50.016733: step: 376/533, loss: 0.0007859505130909383
2023-01-24 10:24:51.111333: step: 380/533, loss: 0.0007357222493737936
2023-01-24 10:24:52.207006: step: 384/533, loss: 0.0007392988190986216
2023-01-24 10:24:53.306388: step: 388/533, loss: 0.0009351771441288292
2023-01-24 10:24:54.393342: step: 392/533, loss: 0.0002917919191531837
2023-01-24 10:24:55.473537: step: 396/533, loss: 0.00919488538056612
2023-01-24 10:24:56.585681: step: 400/533, loss: 0.0041647497564554214
2023-01-24 10:24:57.667820: step: 404/533, loss: 0.004003587644547224
2023-01-24 10:24:58.740616: step: 408/533, loss: 0.0001554991031298414
2023-01-24 10:24:59.837846: step: 412/533, loss: 0.004208484198898077
2023-01-24 10:25:00.933421: step: 416/533, loss: 0.0043732281774282455
2023-01-24 10:25:02.044576: step: 420/533, loss: 5.6903598306234926e-05
2023-01-24 10:25:03.136582: step: 424/533, loss: 0.004765829537063837
2023-01-24 10:25:04.216425: step: 428/533, loss: 0.0009469236247241497
2023-01-24 10:25:05.312307: step: 432/533, loss: 0.011035281233489513
2023-01-24 10:25:06.419651: step: 436/533, loss: 0.0017757733585312963
2023-01-24 10:25:07.513591: step: 440/533, loss: 0.0033795051276683807
2023-01-24 10:25:08.600508: step: 444/533, loss: 0.005347330588847399
2023-01-24 10:25:09.668504: step: 448/533, loss: 0.0011359334457665682
2023-01-24 10:25:10.758662: step: 452/533, loss: 0.0005267669912427664
2023-01-24 10:25:11.839091: step: 456/533, loss: 4.253066435921937e-06
2023-01-24 10:25:12.951514: step: 460/533, loss: 0.027029452845454216
2023-01-24 10:25:14.053935: step: 464/533, loss: 0.0032559623941779137
2023-01-24 10:25:15.152203: step: 468/533, loss: 0.0006213289452716708
2023-01-24 10:25:16.243788: step: 472/533, loss: 0.002729186089709401
2023-01-24 10:25:17.335158: step: 476/533, loss: 0.00944548286497593
2023-01-24 10:25:18.441338: step: 480/533, loss: 0.007011879701167345
2023-01-24 10:25:19.530957: step: 484/533, loss: 0.00022719621483702213
2023-01-24 10:25:20.626944: step: 488/533, loss: 0.0012650199932977557
2023-01-24 10:25:21.722752: step: 492/533, loss: 0.0016651629703119397
2023-01-24 10:25:22.815122: step: 496/533, loss: 0.004619124345481396
2023-01-24 10:25:23.891293: step: 500/533, loss: 0.0012140357866883278
2023-01-24 10:25:24.993915: step: 504/533, loss: 0.001660192501731217
2023-01-24 10:25:26.091039: step: 508/533, loss: 0.0022425048518925905
2023-01-24 10:25:27.164534: step: 512/533, loss: 0.000613369164057076
2023-01-24 10:25:28.273725: step: 516/533, loss: 0.00857542548328638
2023-01-24 10:25:29.380063: step: 520/533, loss: 0.0028465772047638893
2023-01-24 10:25:30.477724: step: 524/533, loss: 3.3556766538822558e-06
2023-01-24 10:25:31.558321: step: 528/533, loss: 0.004257860593497753
2023-01-24 10:25:32.644465: step: 532/533, loss: 0.003311136271804571
2023-01-24 10:25:33.759380: step: 536/533, loss: 0.000415271264500916
2023-01-24 10:25:34.836074: step: 540/533, loss: 0.0
2023-01-24 10:25:35.949949: step: 544/533, loss: 0.00536735262721777
2023-01-24 10:25:37.022968: step: 548/533, loss: 0.014722093939781189
2023-01-24 10:25:38.117603: step: 552/533, loss: 0.009286709129810333
2023-01-24 10:25:39.252138: step: 556/533, loss: 0.002643781481310725
2023-01-24 10:25:40.350238: step: 560/533, loss: 0.0019389259396120906
2023-01-24 10:25:41.446753: step: 564/533, loss: 3.096170985372737e-05
2023-01-24 10:25:42.533165: step: 568/533, loss: 0.006863110698759556
2023-01-24 10:25:43.626972: step: 572/533, loss: 4.757631540996954e-05
2023-01-24 10:25:44.728883: step: 576/533, loss: 0.00039877425297163427
2023-01-24 10:25:45.843335: step: 580/533, loss: 0.0004039833147544414
2023-01-24 10:25:46.953013: step: 584/533, loss: 0.0018151582917198539
2023-01-24 10:25:48.053448: step: 588/533, loss: 0.002156848320737481
2023-01-24 10:25:49.170711: step: 592/533, loss: 0.003955623600631952
2023-01-24 10:25:50.279564: step: 596/533, loss: 0.0009833404328674078
2023-01-24 10:25:51.375306: step: 600/533, loss: 0.0016195853240787983
2023-01-24 10:25:52.474819: step: 604/533, loss: 0.0002722127828747034
2023-01-24 10:25:53.547653: step: 608/533, loss: 0.004795106593519449
2023-01-24 10:25:54.633421: step: 612/533, loss: 0.002460624324157834
2023-01-24 10:25:55.729805: step: 616/533, loss: 0.002307569608092308
2023-01-24 10:25:56.813021: step: 620/533, loss: 8.701105798536446e-06
2023-01-24 10:25:57.911572: step: 624/533, loss: 0.0004655691736843437
2023-01-24 10:25:58.999572: step: 628/533, loss: 0.0008090700139291584
2023-01-24 10:26:00.093012: step: 632/533, loss: 0.003142721252515912
2023-01-24 10:26:01.193106: step: 636/533, loss: 3.8145692087709904e-05
2023-01-24 10:26:02.292189: step: 640/533, loss: 0.005087446887046099
2023-01-24 10:26:03.384773: step: 644/533, loss: 0.0007988712168298662
2023-01-24 10:26:04.475550: step: 648/533, loss: 0.001162784406915307
2023-01-24 10:26:05.587212: step: 652/533, loss: 0.0008605723851360381
2023-01-24 10:26:06.694197: step: 656/533, loss: 0.005452387500554323
2023-01-24 10:26:07.789725: step: 660/533, loss: 0.0002914255310315639
2023-01-24 10:26:08.888548: step: 664/533, loss: 0.0038128977175801992
2023-01-24 10:26:09.988504: step: 668/533, loss: 0.0042551439255476
2023-01-24 10:26:11.067354: step: 672/533, loss: 0.002724230522289872
2023-01-24 10:26:12.150936: step: 676/533, loss: 4.031935895909555e-05
2023-01-24 10:26:13.279884: step: 680/533, loss: 5.5365606385748833e-05
2023-01-24 10:26:14.398231: step: 684/533, loss: 0.0007007706444710493
2023-01-24 10:26:15.496106: step: 688/533, loss: 0.003270220709964633
2023-01-24 10:26:16.601355: step: 692/533, loss: 3.366549572092481e-05
2023-01-24 10:26:17.693828: step: 696/533, loss: 0.002054857788607478
2023-01-24 10:26:18.798399: step: 700/533, loss: 0.009654482826590538
2023-01-24 10:26:19.896749: step: 704/533, loss: 0.0009477714193053544
2023-01-24 10:26:21.001884: step: 708/533, loss: 0.0034496085718274117
2023-01-24 10:26:22.091783: step: 712/533, loss: 0.004538394510746002
2023-01-24 10:26:23.189416: step: 716/533, loss: 0.0035235481336712837
2023-01-24 10:26:24.272930: step: 720/533, loss: 0.0008386040572077036
2023-01-24 10:26:25.358721: step: 724/533, loss: 0.0012919867876917124
2023-01-24 10:26:26.459160: step: 728/533, loss: 0.001081659458577633
2023-01-24 10:26:27.559712: step: 732/533, loss: 0.0046126991510391235
2023-01-24 10:26:28.642468: step: 736/533, loss: 0.003131159348413348
2023-01-24 10:26:29.751577: step: 740/533, loss: 0.03281427547335625
2023-01-24 10:26:30.877098: step: 744/533, loss: 0.0020238033030182123
2023-01-24 10:26:31.982164: step: 748/533, loss: 0.0028214878402650356
2023-01-24 10:26:33.060062: step: 752/533, loss: 0.00035467694397084415
2023-01-24 10:26:34.181336: step: 756/533, loss: 0.007672674488276243
2023-01-24 10:26:35.305409: step: 760/533, loss: 0.0012049440992996097
2023-01-24 10:26:36.387370: step: 764/533, loss: 0.005093137267976999
2023-01-24 10:26:37.487021: step: 768/533, loss: 0.004943084437400103
2023-01-24 10:26:38.584476: step: 772/533, loss: 0.005509162787348032
2023-01-24 10:26:39.697755: step: 776/533, loss: 0.0016891263658180833
2023-01-24 10:26:40.805859: step: 780/533, loss: 0.0062433574348688126
2023-01-24 10:26:41.927327: step: 784/533, loss: 0.0025985052343457937
2023-01-24 10:26:43.026034: step: 788/533, loss: 0.008410242386162281
2023-01-24 10:26:44.126412: step: 792/533, loss: 3.1914463761495426e-05
2023-01-24 10:26:45.222088: step: 796/533, loss: 0.029431438073515892
2023-01-24 10:26:46.304899: step: 800/533, loss: 0.0013381186872720718
2023-01-24 10:26:47.397026: step: 804/533, loss: 0.0021975012496113777
2023-01-24 10:26:48.491034: step: 808/533, loss: 0.000996553455479443
2023-01-24 10:26:49.588517: step: 812/533, loss: 0.0012242257362231612
2023-01-24 10:26:50.717004: step: 816/533, loss: 0.0021587612573057413
2023-01-24 10:26:51.787313: step: 820/533, loss: 1.2793083442375064e-05
2023-01-24 10:26:52.876746: step: 824/533, loss: 0.000508723605889827
2023-01-24 10:26:53.981637: step: 828/533, loss: 0.003261380363255739
2023-01-24 10:26:55.085264: step: 832/533, loss: 0.001979151042178273
2023-01-24 10:26:56.175991: step: 836/533, loss: 0.0021510059013962746
2023-01-24 10:26:57.290811: step: 840/533, loss: 0.0007757382118143141
2023-01-24 10:26:58.405879: step: 844/533, loss: 0.005161563865840435
2023-01-24 10:26:59.494623: step: 848/533, loss: 0.000984849059022963
2023-01-24 10:27:00.591217: step: 852/533, loss: 0.0021363627165555954
2023-01-24 10:27:01.676944: step: 856/533, loss: 0.006650221534073353
2023-01-24 10:27:02.771193: step: 860/533, loss: 0.0030919178389012814
2023-01-24 10:27:03.865987: step: 864/533, loss: 0.0011457346845418215
2023-01-24 10:27:04.952508: step: 868/533, loss: 0.00010148462752113119
2023-01-24 10:27:06.062476: step: 872/533, loss: 0.0019212535116821527
2023-01-24 10:27:07.164976: step: 876/533, loss: 0.0015328327426686883
2023-01-24 10:27:08.276355: step: 880/533, loss: 0.0011701378971338272
2023-01-24 10:27:09.408870: step: 884/533, loss: 0.0041809589602053165
2023-01-24 10:27:10.485047: step: 888/533, loss: 0.002503356197848916
2023-01-24 10:27:11.569442: step: 892/533, loss: 0.009764756076037884
2023-01-24 10:27:12.659123: step: 896/533, loss: 0.002364510903134942
2023-01-24 10:27:13.757624: step: 900/533, loss: 0.004997037351131439
2023-01-24 10:27:14.839208: step: 904/533, loss: 0.0023642457090318203
2023-01-24 10:27:15.931259: step: 908/533, loss: 0.004629787057638168
2023-01-24 10:27:17.016852: step: 912/533, loss: 0.002737612696364522
2023-01-24 10:27:18.101845: step: 916/533, loss: 0.007732829079031944
2023-01-24 10:27:19.206141: step: 920/533, loss: 0.04982207715511322
2023-01-24 10:27:20.308080: step: 924/533, loss: 0.0017023899126797915
2023-01-24 10:27:21.395496: step: 928/533, loss: 0.023883474990725517
2023-01-24 10:27:22.518933: step: 932/533, loss: 0.0026195773389190435
2023-01-24 10:27:23.605322: step: 936/533, loss: 0.0007758325664326549
2023-01-24 10:27:24.704171: step: 940/533, loss: 0.0028161476366221905
2023-01-24 10:27:25.800691: step: 944/533, loss: 0.00541316345334053
2023-01-24 10:27:26.929894: step: 948/533, loss: 0.009918084368109703
2023-01-24 10:27:28.042478: step: 952/533, loss: 0.008299322798848152
2023-01-24 10:27:29.132663: step: 956/533, loss: 0.0010625753784552217
2023-01-24 10:27:30.219510: step: 960/533, loss: 0.0011958582326769829
2023-01-24 10:27:31.336555: step: 964/533, loss: 0.0038207313045859337
2023-01-24 10:27:32.413556: step: 968/533, loss: 0.004113881383091211
2023-01-24 10:27:33.517692: step: 972/533, loss: 0.017333850264549255
2023-01-24 10:27:34.599196: step: 976/533, loss: 0.0027374185156077147
2023-01-24 10:27:35.685455: step: 980/533, loss: 7.42439851819654e-06
2023-01-24 10:27:36.776396: step: 984/533, loss: 0.007241811603307724
2023-01-24 10:27:37.899330: step: 988/533, loss: 3.7286465612851316e-06
2023-01-24 10:27:38.996677: step: 992/533, loss: 0.0006439899443648756
2023-01-24 10:27:40.121195: step: 996/533, loss: 0.009004329331219196
2023-01-24 10:27:41.242137: step: 1000/533, loss: 0.0016703573055565357
2023-01-24 10:27:42.318154: step: 1004/533, loss: 0.02312503755092621
2023-01-24 10:27:43.414778: step: 1008/533, loss: 0.0007298278505913913
2023-01-24 10:27:44.522561: step: 1012/533, loss: 0.0024792482145130634
2023-01-24 10:27:45.611611: step: 1016/533, loss: 8.978568075690418e-05
2023-01-24 10:27:46.709621: step: 1020/533, loss: 6.779774594178889e-06
2023-01-24 10:27:47.795959: step: 1024/533, loss: 0.0032985375728458166
2023-01-24 10:27:48.902123: step: 1028/533, loss: 0.003460162552073598
2023-01-24 10:27:50.014208: step: 1032/533, loss: 0.007902523502707481
2023-01-24 10:27:51.119639: step: 1036/533, loss: 0.004816838074475527
2023-01-24 10:27:52.222622: step: 1040/533, loss: 4.428064858075231e-05
2023-01-24 10:27:53.305596: step: 1044/533, loss: 0.002422850113362074
2023-01-24 10:27:54.398415: step: 1048/533, loss: 0.008805358782410622
2023-01-24 10:27:55.498188: step: 1052/533, loss: 0.004504465032368898
2023-01-24 10:27:56.585097: step: 1056/533, loss: 7.010494300629944e-05
2023-01-24 10:27:57.692977: step: 1060/533, loss: 0.008112751878798008
2023-01-24 10:27:58.810522: step: 1064/533, loss: 0.0050381203182041645
2023-01-24 10:27:59.899711: step: 1068/533, loss: 0.006655182223767042
2023-01-24 10:28:01.001327: step: 1072/533, loss: 2.980115141326678e-07
2023-01-24 10:28:02.096908: step: 1076/533, loss: 4.6215725888032466e-05
2023-01-24 10:28:03.206209: step: 1080/533, loss: 0.00499233603477478
2023-01-24 10:28:04.296540: step: 1084/533, loss: 0.006635240279138088
2023-01-24 10:28:05.418482: step: 1088/533, loss: 0.007479975465685129
2023-01-24 10:28:06.521427: step: 1092/533, loss: 0.00040188556886278093
2023-01-24 10:28:07.617907: step: 1096/533, loss: 4.166658618487418e-05
2023-01-24 10:28:08.727268: step: 1100/533, loss: 0.003907589707523584
2023-01-24 10:28:09.811367: step: 1104/533, loss: 0.0027937546838074923
2023-01-24 10:28:10.887349: step: 1108/533, loss: 0.003118653781712055
2023-01-24 10:28:11.971606: step: 1112/533, loss: 0.0007133159087970853
2023-01-24 10:28:13.067381: step: 1116/533, loss: 0.004976219031959772
2023-01-24 10:28:14.167056: step: 1120/533, loss: 0.005911215674132109
2023-01-24 10:28:15.260033: step: 1124/533, loss: 0.007793016266077757
2023-01-24 10:28:16.354630: step: 1128/533, loss: 0.04246175289154053
2023-01-24 10:28:17.457831: step: 1132/533, loss: 0.0036611580289900303
2023-01-24 10:28:18.551703: step: 1136/533, loss: 0.004508808255195618
2023-01-24 10:28:19.655455: step: 1140/533, loss: 0.0
2023-01-24 10:28:20.782841: step: 1144/533, loss: 0.0030254547018557787
2023-01-24 10:28:21.876058: step: 1148/533, loss: 0.0018608423415571451
2023-01-24 10:28:22.979197: step: 1152/533, loss: 0.002319303108379245
2023-01-24 10:28:24.076878: step: 1156/533, loss: 0.016714319586753845
2023-01-24 10:28:25.181041: step: 1160/533, loss: 0.0007996285567060113
2023-01-24 10:28:26.278496: step: 1164/533, loss: 0.009608916006982327
2023-01-24 10:28:27.356322: step: 1168/533, loss: 0.002236143685877323
2023-01-24 10:28:28.450482: step: 1172/533, loss: 0.004382158629596233
2023-01-24 10:28:29.567687: step: 1176/533, loss: 0.0011994686210528016
2023-01-24 10:28:30.663920: step: 1180/533, loss: 0.00039390899473801255
2023-01-24 10:28:31.761068: step: 1184/533, loss: 0.004637932404875755
2023-01-24 10:28:32.860976: step: 1188/533, loss: 0.0019200496608391404
2023-01-24 10:28:33.962793: step: 1192/533, loss: 0.004840195178985596
2023-01-24 10:28:35.050640: step: 1196/533, loss: 0.004363042768090963
2023-01-24 10:28:36.122807: step: 1200/533, loss: 0.0010614650091156363
2023-01-24 10:28:37.237393: step: 1204/533, loss: 0.0037756827659904957
2023-01-24 10:28:38.340031: step: 1208/533, loss: 0.007881267927587032
2023-01-24 10:28:39.429802: step: 1212/533, loss: 0.0017297463491559029
2023-01-24 10:28:40.520708: step: 1216/533, loss: 6.090212627896108e-05
2023-01-24 10:28:41.614290: step: 1220/533, loss: 0.008364011533558369
2023-01-24 10:28:42.707726: step: 1224/533, loss: 0.0003601594944484532
2023-01-24 10:28:43.803372: step: 1228/533, loss: 0.00013563265383709222
2023-01-24 10:28:44.911967: step: 1232/533, loss: 0.008005182258784771
2023-01-24 10:28:46.032404: step: 1236/533, loss: 0.003764244494959712
2023-01-24 10:28:47.125797: step: 1240/533, loss: 0.012207334861159325
2023-01-24 10:28:48.227900: step: 1244/533, loss: 1.6405472706537694e-05
2023-01-24 10:28:49.323900: step: 1248/533, loss: 0.015221110545098782
2023-01-24 10:28:50.429245: step: 1252/533, loss: 0.00018963123147841543
2023-01-24 10:28:51.497432: step: 1256/533, loss: 6.434150691347895e-06
2023-01-24 10:28:52.590443: step: 1260/533, loss: 6.190939893713221e-05
2023-01-24 10:28:53.717545: step: 1264/533, loss: 2.6381900170235895e-05
2023-01-24 10:28:54.819818: step: 1268/533, loss: 0.012466111220419407
2023-01-24 10:28:55.902946: step: 1272/533, loss: 1.164535092357255e-06
2023-01-24 10:28:56.992447: step: 1276/533, loss: 0.006264992989599705
2023-01-24 10:28:58.076882: step: 1280/533, loss: 0.011524328030645847
2023-01-24 10:28:59.153544: step: 1284/533, loss: 0.0020726914517581463
2023-01-24 10:29:00.267389: step: 1288/533, loss: 0.0031859774608165026
2023-01-24 10:29:01.370563: step: 1292/533, loss: 0.001065863762050867
2023-01-24 10:29:02.466376: step: 1296/533, loss: 0.008210231550037861
2023-01-24 10:29:03.562576: step: 1300/533, loss: 0.008087042719125748
2023-01-24 10:29:04.672040: step: 1304/533, loss: 0.037366922944784164
2023-01-24 10:29:05.753216: step: 1308/533, loss: 0.0035953782498836517
2023-01-24 10:29:06.842401: step: 1312/533, loss: 0.00027975664124824107
2023-01-24 10:29:07.974272: step: 1316/533, loss: 0.003516263095661998
2023-01-24 10:29:09.054013: step: 1320/533, loss: 0.0026487463619560003
2023-01-24 10:29:10.175086: step: 1324/533, loss: 0.0017194319516420364
2023-01-24 10:29:11.270267: step: 1328/533, loss: 0.07317997515201569
2023-01-24 10:29:12.377847: step: 1332/533, loss: 0.0003576835442800075
2023-01-24 10:29:13.469590: step: 1336/533, loss: 0.009329725056886673
2023-01-24 10:29:14.584217: step: 1340/533, loss: 0.005545720923691988
2023-01-24 10:29:15.665399: step: 1344/533, loss: 0.0020436004269868135
2023-01-24 10:29:16.776515: step: 1348/533, loss: 0.002335364231839776
2023-01-24 10:29:17.886885: step: 1352/533, loss: 0.0007064181845635176
2023-01-24 10:29:18.991728: step: 1356/533, loss: 0.0007438739994540811
2023-01-24 10:29:20.081017: step: 1360/533, loss: 0.0037594398017972708
2023-01-24 10:29:21.164220: step: 1364/533, loss: 0.0023862558882683516
2023-01-24 10:29:22.292979: step: 1368/533, loss: 0.0012980845058336854
2023-01-24 10:29:23.387718: step: 1372/533, loss: 0.004830062855035067
2023-01-24 10:29:24.453802: step: 1376/533, loss: 0.002976753981783986
2023-01-24 10:29:25.550129: step: 1380/533, loss: 0.006307583302259445
2023-01-24 10:29:26.638486: step: 1384/533, loss: 0.0035322431940585375
2023-01-24 10:29:27.719750: step: 1388/533, loss: 0.0032803791109472513
2023-01-24 10:29:28.812226: step: 1392/533, loss: 0.005853346548974514
2023-01-24 10:29:29.910954: step: 1396/533, loss: 0.003757394850254059
2023-01-24 10:29:30.983503: step: 1400/533, loss: 0.001062704366631806
2023-01-24 10:29:32.077916: step: 1404/533, loss: 0.001585218938998878
2023-01-24 10:29:33.173795: step: 1408/533, loss: 0.0011668087681755424
2023-01-24 10:29:34.261777: step: 1412/533, loss: 0.0001553358742967248
2023-01-24 10:29:35.365782: step: 1416/533, loss: 0.0020625272300094366
2023-01-24 10:29:36.468413: step: 1420/533, loss: 0.0003636222390923649
2023-01-24 10:29:37.567072: step: 1424/533, loss: 9.30580499698408e-05
2023-01-24 10:29:38.640762: step: 1428/533, loss: 0.006786765996366739
2023-01-24 10:29:39.714858: step: 1432/533, loss: 0.0004674094670917839
2023-01-24 10:29:40.801896: step: 1436/533, loss: 0.0001263003214262426
2023-01-24 10:29:41.882538: step: 1440/533, loss: 0.010980622842907906
2023-01-24 10:29:42.969924: step: 1444/533, loss: 0.003066767007112503
2023-01-24 10:29:44.059659: step: 1448/533, loss: 0.0023029239382594824
2023-01-24 10:29:45.135736: step: 1452/533, loss: 0.012325845658779144
2023-01-24 10:29:46.249134: step: 1456/533, loss: 0.0001607300655450672
2023-01-24 10:29:47.340068: step: 1460/533, loss: 0.0025270869955420494
2023-01-24 10:29:48.414488: step: 1464/533, loss: 0.0024355545174330473
2023-01-24 10:29:49.516862: step: 1468/533, loss: 0.0004332764947321266
2023-01-24 10:29:50.642266: step: 1472/533, loss: 0.005122432950884104
2023-01-24 10:29:51.741414: step: 1476/533, loss: 0.0015055324183776975
2023-01-24 10:29:52.848710: step: 1480/533, loss: 0.0029256746638566256
2023-01-24 10:29:53.948697: step: 1484/533, loss: 0.007653603795915842
2023-01-24 10:29:55.044352: step: 1488/533, loss: 1.7904479818753316e-06
2023-01-24 10:29:56.158293: step: 1492/533, loss: 0.0010488649131730199
2023-01-24 10:29:57.252227: step: 1496/533, loss: 0.0004469682462513447
2023-01-24 10:29:58.342486: step: 1500/533, loss: 0.0011574316304177046
2023-01-24 10:29:59.433398: step: 1504/533, loss: 0.010617057792842388
2023-01-24 10:30:00.547849: step: 1508/533, loss: 0.0055631049908697605
2023-01-24 10:30:01.649319: step: 1512/533, loss: 5.374250031309202e-05
2023-01-24 10:30:02.746859: step: 1516/533, loss: 0.0028244280256330967
2023-01-24 10:30:03.833442: step: 1520/533, loss: 0.0011174314422532916
2023-01-24 10:30:04.935516: step: 1524/533, loss: 0.010671704076230526
2023-01-24 10:30:06.023465: step: 1528/533, loss: 0.02177772857248783
2023-01-24 10:30:07.118333: step: 1532/533, loss: 0.00015799909306224436
2023-01-24 10:30:08.197062: step: 1536/533, loss: 0.0004447957326192409
2023-01-24 10:30:09.318120: step: 1540/533, loss: 0.0028882299084216356
2023-01-24 10:30:10.415217: step: 1544/533, loss: 0.006790920160710812
2023-01-24 10:30:11.545740: step: 1548/533, loss: 0.004153222311288118
2023-01-24 10:30:12.622462: step: 1552/533, loss: 2.6241126761306077e-05
2023-01-24 10:30:13.725140: step: 1556/533, loss: 0.0007858063327148557
2023-01-24 10:30:14.797596: step: 1560/533, loss: 0.0013317828997969627
2023-01-24 10:30:15.894670: step: 1564/533, loss: 0.009271956980228424
2023-01-24 10:30:16.972997: step: 1568/533, loss: 0.0008984762243926525
2023-01-24 10:30:18.087360: step: 1572/533, loss: 9.194939048029482e-05
2023-01-24 10:30:19.172370: step: 1576/533, loss: 0.03466714173555374
2023-01-24 10:30:20.283835: step: 1580/533, loss: 0.0029726240318268538
2023-01-24 10:30:21.358774: step: 1584/533, loss: 0.001832545385695994
2023-01-24 10:30:22.472590: step: 1588/533, loss: 0.005128352902829647
2023-01-24 10:30:23.544015: step: 1592/533, loss: 0.003743568668141961
2023-01-24 10:30:24.649467: step: 1596/533, loss: 0.007251785136759281
2023-01-24 10:30:25.775245: step: 1600/533, loss: 0.02097368612885475
2023-01-24 10:30:26.879420: step: 1604/533, loss: 0.007541379891335964
2023-01-24 10:30:27.987596: step: 1608/533, loss: 0.00790859293192625
2023-01-24 10:30:29.093402: step: 1612/533, loss: 0.006177091971039772
2023-01-24 10:30:30.212522: step: 1616/533, loss: 3.014644971699454e-05
2023-01-24 10:30:31.317478: step: 1620/533, loss: 0.001881403848528862
2023-01-24 10:30:32.416161: step: 1624/533, loss: 0.003910279832780361
2023-01-24 10:30:33.514056: step: 1628/533, loss: 0.022966232150793076
2023-01-24 10:30:34.603919: step: 1632/533, loss: 0.0020921388640999794
2023-01-24 10:30:35.695063: step: 1636/533, loss: 0.0018498116405680776
2023-01-24 10:30:36.778229: step: 1640/533, loss: 0.00023134994262363762
2023-01-24 10:30:37.900705: step: 1644/533, loss: 0.004351253621280193
2023-01-24 10:30:38.999804: step: 1648/533, loss: 0.0005367333651520312
2023-01-24 10:30:40.095373: step: 1652/533, loss: 0.0005475341458804905
2023-01-24 10:30:41.189241: step: 1656/533, loss: 0.0036158906295895576
2023-01-24 10:30:42.282560: step: 1660/533, loss: 0.0027100176084786654
2023-01-24 10:30:43.401509: step: 1664/533, loss: 0.0056711421348154545
2023-01-24 10:30:44.502262: step: 1668/533, loss: 0.00018285939586348832
2023-01-24 10:30:45.598123: step: 1672/533, loss: 0.005945150274783373
2023-01-24 10:30:46.710375: step: 1676/533, loss: 0.03354419767856598
2023-01-24 10:30:47.808585: step: 1680/533, loss: 0.000676512427162379
2023-01-24 10:30:48.903850: step: 1684/533, loss: 0.014503566548228264
2023-01-24 10:30:50.012157: step: 1688/533, loss: 0.0035401247441768646
2023-01-24 10:30:51.114650: step: 1692/533, loss: 0.00039808452129364014
2023-01-24 10:30:52.194043: step: 1696/533, loss: 7.04487820257782e-06
2023-01-24 10:30:53.297342: step: 1700/533, loss: 0.0012783093843609095
2023-01-24 10:30:54.378995: step: 1704/533, loss: 0.00016493360453750938
2023-01-24 10:30:55.476122: step: 1708/533, loss: 0.0037238080985844135
2023-01-24 10:30:56.570834: step: 1712/533, loss: 0.00014258308510761708
2023-01-24 10:30:57.668498: step: 1716/533, loss: 1.234806973116065e-06
2023-01-24 10:30:58.783564: step: 1720/533, loss: 0.002507386961951852
2023-01-24 10:30:59.892160: step: 1724/533, loss: 0.005266042426228523
2023-01-24 10:31:01.008226: step: 1728/533, loss: 7.450580152834618e-10
2023-01-24 10:31:02.087926: step: 1732/533, loss: 0.0009155470761470497
2023-01-24 10:31:03.175103: step: 1736/533, loss: 2.4871662390069105e-05
2023-01-24 10:31:04.256407: step: 1740/533, loss: 0.0033149151131510735
2023-01-24 10:31:05.387148: step: 1744/533, loss: 0.0014335426967591047
2023-01-24 10:31:06.486594: step: 1748/533, loss: 0.004039490129798651
2023-01-24 10:31:07.583710: step: 1752/533, loss: 0.002599750179797411
2023-01-24 10:31:08.685182: step: 1756/533, loss: 0.0027997849974781275
2023-01-24 10:31:09.790958: step: 1760/533, loss: 0.000997508061118424
2023-01-24 10:31:10.901547: step: 1764/533, loss: 0.014272946864366531
2023-01-24 10:31:11.988459: step: 1768/533, loss: 0.0004000952758360654
2023-01-24 10:31:13.129379: step: 1772/533, loss: 0.060677699744701385
2023-01-24 10:31:14.206539: step: 1776/533, loss: 0.0007547039422206581
2023-01-24 10:31:15.303247: step: 1780/533, loss: 0.0021845779847353697
2023-01-24 10:31:16.408487: step: 1784/533, loss: 0.0008199600270017982
2023-01-24 10:31:17.522309: step: 1788/533, loss: 0.003028515260666609
2023-01-24 10:31:18.600668: step: 1792/533, loss: 0.005054660141468048
2023-01-24 10:31:19.697497: step: 1796/533, loss: 0.0024121697060763836
2023-01-24 10:31:20.795944: step: 1800/533, loss: 0.0006518853479065001
2023-01-24 10:31:21.885164: step: 1804/533, loss: 0.0006590721313841641
2023-01-24 10:31:22.974949: step: 1808/533, loss: 0.002677211305126548
2023-01-24 10:31:24.095801: step: 1812/533, loss: 0.004822150804102421
2023-01-24 10:31:25.228959: step: 1816/533, loss: 0.0001353654224658385
2023-01-24 10:31:26.309484: step: 1820/533, loss: 0.0017196391709148884
2023-01-24 10:31:27.421866: step: 1824/533, loss: 0.00293372361920774
2023-01-24 10:31:28.512534: step: 1828/533, loss: 0.004826163407415152
2023-01-24 10:31:29.611737: step: 1832/533, loss: 8.666315261507407e-05
2023-01-24 10:31:30.687823: step: 1836/533, loss: 0.0018977575236931443
2023-01-24 10:31:31.771454: step: 1840/533, loss: 0.0003903876058757305
2023-01-24 10:31:32.867131: step: 1844/533, loss: 0.001976850675418973
2023-01-24 10:31:33.971516: step: 1848/533, loss: 0.0017122164135798812
2023-01-24 10:31:35.046134: step: 1852/533, loss: 0.016763320192694664
2023-01-24 10:31:36.140355: step: 1856/533, loss: 0.0021983019541949034
2023-01-24 10:31:37.237439: step: 1860/533, loss: 0.0014892034232616425
2023-01-24 10:31:38.331389: step: 1864/533, loss: 0.00029917617212049663
2023-01-24 10:31:39.425136: step: 1868/533, loss: 0.003042049240320921
2023-01-24 10:31:40.536057: step: 1872/533, loss: 0.0010834234999492764
2023-01-24 10:31:41.608835: step: 1876/533, loss: 0.000442570453742519
2023-01-24 10:31:42.691035: step: 1880/533, loss: 0.0002725624362938106
2023-01-24 10:31:43.778954: step: 1884/533, loss: 0.0006026945193298161
2023-01-24 10:31:44.870801: step: 1888/533, loss: 0.00351278530433774
2023-01-24 10:31:45.989279: step: 1892/533, loss: 0.0023959530517458916
2023-01-24 10:31:47.077452: step: 1896/533, loss: 0.002761167474091053
2023-01-24 10:31:48.173140: step: 1900/533, loss: 0.00014272166299633682
2023-01-24 10:31:49.277876: step: 1904/533, loss: 0.0017722677439451218
2023-01-24 10:31:50.371822: step: 1908/533, loss: 0.008121934719383717
2023-01-24 10:31:51.478990: step: 1912/533, loss: 3.4458656728020287e-07
2023-01-24 10:31:52.574434: step: 1916/533, loss: 0.0016720143612474203
2023-01-24 10:31:53.687959: step: 1920/533, loss: 0.00048806247650645673
2023-01-24 10:31:54.759280: step: 1924/533, loss: 0.00043989851837977767
2023-01-24 10:31:55.838586: step: 1928/533, loss: 6.942907202756032e-05
2023-01-24 10:31:56.932694: step: 1932/533, loss: 0.004254623781889677
2023-01-24 10:31:58.023313: step: 1936/533, loss: 1.8720873413258232e-05
2023-01-24 10:31:59.122687: step: 1940/533, loss: 0.0024295824114233255
2023-01-24 10:32:00.204469: step: 1944/533, loss: 0.0042814151383936405
2023-01-24 10:32:01.321490: step: 1948/533, loss: 0.00030810933094471693
2023-01-24 10:32:02.398168: step: 1952/533, loss: 0.0018373882630839944
2023-01-24 10:32:03.495931: step: 1956/533, loss: 0.003512292867526412
2023-01-24 10:32:04.579826: step: 1960/533, loss: 0.0002876254147849977
2023-01-24 10:32:05.655679: step: 1964/533, loss: 3.3749662975424144e-07
2023-01-24 10:32:06.751448: step: 1968/533, loss: 8.35411628941074e-05
2023-01-24 10:32:07.860103: step: 1972/533, loss: 0.0058256820775568485
2023-01-24 10:32:08.953372: step: 1976/533, loss: 0.018751733005046844
2023-01-24 10:32:10.065627: step: 1980/533, loss: 0.001113171107135713
2023-01-24 10:32:11.183543: step: 1984/533, loss: 0.0044909995049238205
2023-01-24 10:32:12.318260: step: 1988/533, loss: 0.017932061105966568
2023-01-24 10:32:13.428825: step: 1992/533, loss: 0.008470152504742146
2023-01-24 10:32:14.516568: step: 1996/533, loss: 0.00019297630933579057
2023-01-24 10:32:15.633924: step: 2000/533, loss: 0.0019433964043855667
2023-01-24 10:32:16.714835: step: 2004/533, loss: 0.0008608169737271965
2023-01-24 10:32:17.809457: step: 2008/533, loss: 6.875632971059531e-05
2023-01-24 10:32:18.887621: step: 2012/533, loss: 0.005103981122374535
2023-01-24 10:32:20.003186: step: 2016/533, loss: 0.003713170299306512
2023-01-24 10:32:21.082459: step: 2020/533, loss: 0.00011643425386864692
2023-01-24 10:32:22.164306: step: 2024/533, loss: 1.641404742258601e-05
2023-01-24 10:32:23.260066: step: 2028/533, loss: 0.0007001549238339067
2023-01-24 10:32:24.351587: step: 2032/533, loss: 0.013848381116986275
2023-01-24 10:32:25.431586: step: 2036/533, loss: 0.003956747241318226
2023-01-24 10:32:26.513270: step: 2040/533, loss: 0.0001338177389698103
2023-01-24 10:32:27.596899: step: 2044/533, loss: 0.0041389563120901585
2023-01-24 10:32:28.689224: step: 2048/533, loss: 0.001075610052794218
2023-01-24 10:32:29.766756: step: 2052/533, loss: 6.113169365562499e-05
2023-01-24 10:32:30.873254: step: 2056/533, loss: 2.8129134079790674e-05
2023-01-24 10:32:31.973990: step: 2060/533, loss: 0.0041338000446558
2023-01-24 10:32:33.065439: step: 2064/533, loss: 0.008743975311517715
2023-01-24 10:32:34.147345: step: 2068/533, loss: 0.00016295764362439513
2023-01-24 10:32:35.232700: step: 2072/533, loss: 0.004691815469413996
2023-01-24 10:32:36.342510: step: 2076/533, loss: 0.011975549161434174
2023-01-24 10:32:37.430163: step: 2080/533, loss: 4.649611946661025e-05
2023-01-24 10:32:38.515133: step: 2084/533, loss: 0.002334790537133813
2023-01-24 10:32:39.623266: step: 2088/533, loss: 0.005131153855472803
2023-01-24 10:32:40.697097: step: 2092/533, loss: 0.00825737789273262
2023-01-24 10:32:41.783237: step: 2096/533, loss: 0.004578899592161179
2023-01-24 10:32:42.874132: step: 2100/533, loss: 0.0011325943050906062
2023-01-24 10:32:43.970424: step: 2104/533, loss: 0.0007827337249182165
2023-01-24 10:32:45.084161: step: 2108/533, loss: 0.003066880628466606
2023-01-24 10:32:46.176209: step: 2112/533, loss: 0.0023694857954978943
2023-01-24 10:32:47.261640: step: 2116/533, loss: 0.02227810211479664
2023-01-24 10:32:48.366219: step: 2120/533, loss: 0.0019473910797387362
2023-01-24 10:32:49.478388: step: 2124/533, loss: 0.00012861825234722346
2023-01-24 10:32:50.587079: step: 2128/533, loss: 0.0036670491099357605
2023-01-24 10:32:51.690876: step: 2132/533, loss: 0.009046339429914951
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3791666666666667, 'r': 0.32736401012017713, 'f1': 0.3513662593346912}, 'combined': 0.25890145424661454, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3984656169207688, 'r': 0.36091789532631174, 'f1': 0.3787634824816995}, 'combined': 0.25250898832113294, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3577415808857286, 'r': 0.3183696421924226, 'f1': 0.33690923983013393}, 'combined': 0.24824891355904605, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3909636586733026, 'r': 0.31126722055912937, 'f1': 0.3465930507296516}, 'combined': 0.23106203381976767, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35048248859292147, 'r': 0.31722988056702756, 'f1': 0.33302818139207874}, 'combined': 0.2453891862889001, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38299654503075575, 'r': 0.34432862461899677, 'f1': 0.3626347033962093}, 'combined': 0.24175646893080613, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 16}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35048248859292147, 'r': 0.31722988056702756, 'f1': 0.33302818139207874}, 'combined': 0.2453891862889001, 'stategy': 1, 'epoch': 16}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38299654503075575, 'r': 0.34432862461899677, 'f1': 0.3626347033962093}, 'combined': 0.24175646893080613, 'stategy': 1, 'epoch': 16}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 16}
******************************
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 10:35:21.927145: step: 4/533, loss: 0.0015225373208522797
2023-01-24 10:35:22.993675: step: 8/533, loss: 0.00011265672219451517
2023-01-24 10:35:24.067317: step: 12/533, loss: 0.014336178079247475
2023-01-24 10:35:25.168292: step: 16/533, loss: 0.00015229248674586415
2023-01-24 10:35:26.263384: step: 20/533, loss: 0.0020451059099286795
2023-01-24 10:35:27.341601: step: 24/533, loss: 5.738744584959932e-05
2023-01-24 10:35:28.423789: step: 28/533, loss: 0.00034198423963971436
2023-01-24 10:35:29.512827: step: 32/533, loss: 0.0012501085875555873
2023-01-24 10:35:30.627171: step: 36/533, loss: 0.005224632564932108
2023-01-24 10:35:31.709939: step: 40/533, loss: 0.000294815021334216
2023-01-24 10:35:32.834310: step: 44/533, loss: 8.984184387372807e-05
2023-01-24 10:35:33.910111: step: 48/533, loss: 0.0034656268544495106
2023-01-24 10:35:34.979283: step: 52/533, loss: 0.005528515670448542
2023-01-24 10:35:36.097147: step: 56/533, loss: 0.010681912302970886
2023-01-24 10:35:37.198016: step: 60/533, loss: 0.0065715922974050045
2023-01-24 10:35:38.292789: step: 64/533, loss: 0.00010260730050504208
2023-01-24 10:35:39.370504: step: 68/533, loss: 0.0200312789529562
2023-01-24 10:35:40.452160: step: 72/533, loss: 0.0007554791518487036
2023-01-24 10:35:41.532276: step: 76/533, loss: 0.003003625897690654
2023-01-24 10:35:42.612648: step: 80/533, loss: 0.00017133733490481973
2023-01-24 10:35:43.699835: step: 84/533, loss: 0.0071298498660326
2023-01-24 10:35:44.781049: step: 88/533, loss: 0.0016886970261111856
2023-01-24 10:35:45.855844: step: 92/533, loss: 0.0033416212536394596
2023-01-24 10:35:46.922912: step: 96/533, loss: 0.003547379281371832
2023-01-24 10:35:48.040493: step: 100/533, loss: 0.01667761243879795
2023-01-24 10:35:49.160633: step: 104/533, loss: 0.0010066510876640677
2023-01-24 10:35:50.287920: step: 108/533, loss: 0.007399471942335367
2023-01-24 10:35:51.380728: step: 112/533, loss: 0.01539274025708437
2023-01-24 10:35:52.470399: step: 116/533, loss: 0.0008453050977550447
2023-01-24 10:35:53.583513: step: 120/533, loss: 0.004963121842592955
2023-01-24 10:35:54.691291: step: 124/533, loss: 0.0290669072419405
2023-01-24 10:35:55.785561: step: 128/533, loss: 0.0033694440498948097
2023-01-24 10:35:56.893363: step: 132/533, loss: 5.8194804296363145e-05
2023-01-24 10:35:57.997806: step: 136/533, loss: 0.026346556842327118
2023-01-24 10:35:59.082407: step: 140/533, loss: 0.0034191994927823544
2023-01-24 10:36:00.177071: step: 144/533, loss: 0.0033627666998654604
2023-01-24 10:36:01.272205: step: 148/533, loss: 0.0003960058093070984
2023-01-24 10:36:02.392216: step: 152/533, loss: 0.0016868896782398224
2023-01-24 10:36:03.480620: step: 156/533, loss: 4.3130843550898135e-05
2023-01-24 10:36:04.566114: step: 160/533, loss: 0.0
2023-01-24 10:36:05.662098: step: 164/533, loss: 0.002522764028981328
2023-01-24 10:36:06.741046: step: 168/533, loss: 0.00010279243724653497
2023-01-24 10:36:07.848424: step: 172/533, loss: 0.00010232294880552217
2023-01-24 10:36:08.936723: step: 176/533, loss: 0.015232169069349766
2023-01-24 10:36:10.026285: step: 180/533, loss: 2.031663643720094e-05
2023-01-24 10:36:11.127652: step: 184/533, loss: 0.0027214973233640194
2023-01-24 10:36:12.220806: step: 188/533, loss: 4.9670498825094e-09
2023-01-24 10:36:13.316099: step: 192/533, loss: 0.0018078399589285254
2023-01-24 10:36:14.433700: step: 196/533, loss: 0.0020013859029859304
2023-01-24 10:36:15.533192: step: 200/533, loss: 0.009399987757205963
2023-01-24 10:36:16.640377: step: 204/533, loss: 1.0781712262541987e-05
2023-01-24 10:36:17.732853: step: 208/533, loss: 0.0034557997714728117
2023-01-24 10:36:18.820456: step: 212/533, loss: 0.0021103534381836653
2023-01-24 10:36:19.907729: step: 216/533, loss: 0.0021904490422457457
2023-01-24 10:36:21.026436: step: 220/533, loss: 0.0003784768341574818
2023-01-24 10:36:22.126604: step: 224/533, loss: 0.016775524243712425
2023-01-24 10:36:23.225721: step: 228/533, loss: 0.004216290544718504
2023-01-24 10:36:24.320196: step: 232/533, loss: 0.0022980081848800182
2023-01-24 10:36:25.395762: step: 236/533, loss: 0.0024828072637319565
2023-01-24 10:36:26.484258: step: 240/533, loss: 0.0005352682201191783
2023-01-24 10:36:27.588301: step: 244/533, loss: 0.0013043429935351014
2023-01-24 10:36:28.699952: step: 248/533, loss: 0.0004540742957033217
2023-01-24 10:36:29.800500: step: 252/533, loss: 9.573761781211942e-05
2023-01-24 10:36:30.893330: step: 256/533, loss: 0.004858030471950769
2023-01-24 10:36:31.996911: step: 260/533, loss: 0.0019376103300601244
2023-01-24 10:36:33.095388: step: 264/533, loss: 0.00010007956007029861
2023-01-24 10:36:34.207349: step: 268/533, loss: 0.0010184036800637841
2023-01-24 10:36:35.310278: step: 272/533, loss: 0.0008821519440971315
2023-01-24 10:36:36.418567: step: 276/533, loss: 0.0038966757711023092
2023-01-24 10:36:37.535262: step: 280/533, loss: 0.0007309672073461115
2023-01-24 10:36:38.630390: step: 284/533, loss: 0.002461482537910342
2023-01-24 10:36:39.707604: step: 288/533, loss: 0.004281487315893173
2023-01-24 10:36:40.807579: step: 292/533, loss: 0.0034507557284086943
2023-01-24 10:36:41.905985: step: 296/533, loss: 9.072550165001303e-05
2023-01-24 10:36:43.000561: step: 300/533, loss: 0.003752213204279542
2023-01-24 10:36:44.086855: step: 304/533, loss: 0.0001170730174635537
2023-01-24 10:36:45.193110: step: 308/533, loss: 0.00545499287545681
2023-01-24 10:36:46.309241: step: 312/533, loss: 0.004657335579395294
2023-01-24 10:36:47.410497: step: 316/533, loss: 0.0001654384977882728
2023-01-24 10:36:48.494971: step: 320/533, loss: 7.798781734891236e-05
2023-01-24 10:36:49.601419: step: 324/533, loss: 5.89112751185894e-05
2023-01-24 10:36:50.703227: step: 328/533, loss: 0.0023352617863565683
2023-01-24 10:36:51.789966: step: 332/533, loss: 0.0017495412612333894
2023-01-24 10:36:52.880873: step: 336/533, loss: 0.005081417504698038
2023-01-24 10:36:53.989226: step: 340/533, loss: 0.0003403233422432095
2023-01-24 10:36:55.097257: step: 344/533, loss: 0.0017416315386071801
2023-01-24 10:36:56.171150: step: 348/533, loss: 0.00018589368846733123
2023-01-24 10:36:57.256742: step: 352/533, loss: 0.0026645606849342585
2023-01-24 10:36:58.346150: step: 356/533, loss: 0.007809861097484827
2023-01-24 10:36:59.463644: step: 360/533, loss: 5.088219495519297e-06
2023-01-24 10:37:00.567689: step: 364/533, loss: 0.004602053668349981
2023-01-24 10:37:01.659676: step: 368/533, loss: 0.001314472290687263
2023-01-24 10:37:02.784201: step: 372/533, loss: 0.0006731789908371866
2023-01-24 10:37:03.879033: step: 376/533, loss: 1.452026299375575e-05
2023-01-24 10:37:04.984464: step: 380/533, loss: 0.0009123113704845309
2023-01-24 10:37:06.160950: step: 384/533, loss: 0.0076425219886004925
2023-01-24 10:37:07.267152: step: 388/533, loss: 0.002659332240000367
2023-01-24 10:37:08.366852: step: 392/533, loss: 0.00011222065222682431
2023-01-24 10:37:09.479473: step: 396/533, loss: 0.004741138778626919
2023-01-24 10:37:10.558285: step: 400/533, loss: 0.009844550862908363
2023-01-24 10:37:11.644362: step: 404/533, loss: 0.0015517750289291143
2023-01-24 10:37:12.770279: step: 408/533, loss: 0.0004425237129908055
2023-01-24 10:37:13.863510: step: 412/533, loss: 0.0028256785590201616
2023-01-24 10:37:14.977260: step: 416/533, loss: 1.3418522257779841e-06
2023-01-24 10:37:16.077573: step: 420/533, loss: 3.291319444542751e-05
2023-01-24 10:37:17.162525: step: 424/533, loss: 0.007360241375863552
2023-01-24 10:37:18.267025: step: 428/533, loss: 0.001451636548154056
2023-01-24 10:37:19.369335: step: 432/533, loss: 0.0027591707184910774
2023-01-24 10:37:20.467251: step: 436/533, loss: 0.01920190453529358
2023-01-24 10:37:21.536221: step: 440/533, loss: 0.0024741385132074356
2023-01-24 10:37:22.613135: step: 444/533, loss: 0.0001539332006359473
2023-01-24 10:37:23.709614: step: 448/533, loss: 0.002133090514689684
2023-01-24 10:37:24.809461: step: 452/533, loss: 0.002312898635864258
2023-01-24 10:37:25.886426: step: 456/533, loss: 0.00443243095651269
2023-01-24 10:37:26.957766: step: 460/533, loss: 8.785396494204178e-05
2023-01-24 10:37:28.042145: step: 464/533, loss: 0.001958114095032215
2023-01-24 10:37:29.135304: step: 468/533, loss: 0.007603033445775509
2023-01-24 10:37:30.226752: step: 472/533, loss: 0.00036789727164432406
2023-01-24 10:37:31.326310: step: 476/533, loss: 0.007051269058138132
2023-01-24 10:37:32.443577: step: 480/533, loss: 0.0037809067871421576
2023-01-24 10:37:33.518896: step: 484/533, loss: 0.006364382803440094
2023-01-24 10:37:34.621116: step: 488/533, loss: 0.005731227342039347
2023-01-24 10:37:35.743713: step: 492/533, loss: 0.002364946762099862
2023-01-24 10:37:36.847491: step: 496/533, loss: 0.0002648198278620839
2023-01-24 10:37:37.962736: step: 500/533, loss: 0.003513348288834095
2023-01-24 10:37:39.067547: step: 504/533, loss: 0.011069977656006813
2023-01-24 10:37:40.164432: step: 508/533, loss: 0.004276184365153313
2023-01-24 10:37:41.258071: step: 512/533, loss: 0.0006195905734784901
2023-01-24 10:37:42.347836: step: 516/533, loss: 0.001428889692761004
2023-01-24 10:37:43.425351: step: 520/533, loss: 0.0005092397332191467
2023-01-24 10:37:44.530631: step: 524/533, loss: 0.001745460438542068
2023-01-24 10:37:45.636890: step: 528/533, loss: 0.0036056297831237316
2023-01-24 10:37:46.758324: step: 532/533, loss: 0.0029431325383484364
2023-01-24 10:37:47.861035: step: 536/533, loss: 0.00011205059854546562
2023-01-24 10:37:48.957512: step: 540/533, loss: 7.936687325127423e-05
2023-01-24 10:37:50.065734: step: 544/533, loss: 0.007810648996382952
2023-01-24 10:37:51.156509: step: 548/533, loss: 0.0005484299617819488
2023-01-24 10:37:52.248368: step: 552/533, loss: 0.0014435253106057644
2023-01-24 10:37:53.359065: step: 556/533, loss: 0.0015811665216460824
2023-01-24 10:37:54.487470: step: 560/533, loss: 0.0030019558034837246
2023-01-24 10:37:55.567030: step: 564/533, loss: 2.3640536710445303e-06
2023-01-24 10:37:56.682167: step: 568/533, loss: 0.0037207852583378553
2023-01-24 10:37:57.767757: step: 572/533, loss: 0.0041724699549376965
2023-01-24 10:37:58.846790: step: 576/533, loss: 0.0053480383940041065
2023-01-24 10:37:59.940683: step: 580/533, loss: 0.007379960268735886
2023-01-24 10:38:01.058432: step: 584/533, loss: 0.0020042003598064184
2023-01-24 10:38:02.135006: step: 588/533, loss: 5.97972612013109e-05
2023-01-24 10:38:03.231952: step: 592/533, loss: 0.0017150758067145944
2023-01-24 10:38:04.323813: step: 596/533, loss: 0.00366823747754097
2023-01-24 10:38:05.380368: step: 600/533, loss: 0.0008052396588027477
2023-01-24 10:38:06.456621: step: 604/533, loss: 1.5376497685792856e-05
2023-01-24 10:38:07.535886: step: 608/533, loss: 0.0025619552470743656
2023-01-24 10:38:08.645709: step: 612/533, loss: 0.0016460728365927935
2023-01-24 10:38:09.735438: step: 616/533, loss: 0.00844366755336523
2023-01-24 10:38:10.833724: step: 620/533, loss: 0.006845889147371054
2023-01-24 10:38:11.929000: step: 624/533, loss: 0.00259371567517519
2023-01-24 10:38:13.000505: step: 628/533, loss: 0.005602969788014889
2023-01-24 10:38:14.102873: step: 632/533, loss: 0.00019542254449333996
2023-01-24 10:38:15.191422: step: 636/533, loss: 0.0027839946560561657
2023-01-24 10:38:16.277941: step: 640/533, loss: 0.003391941310837865
2023-01-24 10:38:17.363279: step: 644/533, loss: 0.002799833193421364
2023-01-24 10:38:18.451748: step: 648/533, loss: 0.00871035922318697
2023-01-24 10:38:19.583580: step: 652/533, loss: 0.0016629680758342147
2023-01-24 10:38:20.683114: step: 656/533, loss: 0.01647239737212658
2023-01-24 10:38:21.758912: step: 660/533, loss: 0.003109176643192768
2023-01-24 10:38:22.856840: step: 664/533, loss: 0.006942462641745806
2023-01-24 10:38:23.963567: step: 668/533, loss: 1.3661194770975271e-06
2023-01-24 10:38:25.074627: step: 672/533, loss: 0.006546204909682274
2023-01-24 10:38:26.166469: step: 676/533, loss: 0.00029820582130923867
2023-01-24 10:38:27.311619: step: 680/533, loss: 0.0024209588300436735
2023-01-24 10:38:28.392943: step: 684/533, loss: 0.00010229455074295402
2023-01-24 10:38:29.475891: step: 688/533, loss: 0.00021139762247912586
2023-01-24 10:38:30.585696: step: 692/533, loss: 0.0038101854734122753
2023-01-24 10:38:31.676503: step: 696/533, loss: 0.00010616704821586609
2023-01-24 10:38:32.770096: step: 700/533, loss: 0.001636108965612948
2023-01-24 10:38:33.843076: step: 704/533, loss: 0.005135894753038883
2023-01-24 10:38:34.973454: step: 708/533, loss: 0.0002269493998028338
2023-01-24 10:38:36.083453: step: 712/533, loss: 0.006002513226121664
2023-01-24 10:38:37.187891: step: 716/533, loss: 0.0006663108360953629
2023-01-24 10:38:38.279751: step: 720/533, loss: 0.0018496201373636723
2023-01-24 10:38:39.366387: step: 724/533, loss: 0.00038271211087703705
2023-01-24 10:38:40.472658: step: 728/533, loss: 0.003208843059837818
2023-01-24 10:38:41.560916: step: 732/533, loss: 0.0012256484478712082
2023-01-24 10:38:42.648112: step: 736/533, loss: 0.0022995020262897015
2023-01-24 10:38:43.730844: step: 740/533, loss: 0.0030025106389075518
2023-01-24 10:38:44.825695: step: 744/533, loss: 0.007176817394793034
2023-01-24 10:38:45.923667: step: 748/533, loss: 0.005372742656618357
2023-01-24 10:38:47.020940: step: 752/533, loss: 0.0012175878509879112
2023-01-24 10:38:48.076741: step: 756/533, loss: 0.004096833523362875
2023-01-24 10:38:49.177425: step: 760/533, loss: 0.0016120551154017448
2023-01-24 10:38:50.291344: step: 764/533, loss: 0.00663337018340826
2023-01-24 10:38:51.407697: step: 768/533, loss: 0.006655734498053789
2023-01-24 10:38:52.511309: step: 772/533, loss: 0.0016186066204681993
2023-01-24 10:38:53.613206: step: 776/533, loss: 0.000168942118762061
2023-01-24 10:38:54.741578: step: 780/533, loss: 0.005645799450576305
2023-01-24 10:38:55.839389: step: 784/533, loss: 0.00046792515786364675
2023-01-24 10:38:56.914691: step: 788/533, loss: 0.0022178387735038996
2023-01-24 10:38:58.024218: step: 792/533, loss: 0.002279298147186637
2023-01-24 10:38:59.110375: step: 796/533, loss: 0.002453784691169858
2023-01-24 10:39:00.218599: step: 800/533, loss: 0.0009365553851239383
2023-01-24 10:39:01.330625: step: 804/533, loss: 0.000942423939704895
2023-01-24 10:39:02.430364: step: 808/533, loss: 0.0025986582040786743
2023-01-24 10:39:03.511586: step: 812/533, loss: 0.004537773318588734
2023-01-24 10:39:04.613417: step: 816/533, loss: 0.004808306228369474
2023-01-24 10:39:05.728872: step: 820/533, loss: 0.0012576010776683688
2023-01-24 10:39:06.824058: step: 824/533, loss: 0.0020789995323866606
2023-01-24 10:39:07.914459: step: 828/533, loss: 0.00103310018312186
2023-01-24 10:39:09.015621: step: 832/533, loss: 0.0012139208847656846
2023-01-24 10:39:10.122317: step: 836/533, loss: 0.0032230354845523834
2023-01-24 10:39:11.226141: step: 840/533, loss: 0.015307550318539143
2023-01-24 10:39:12.306574: step: 844/533, loss: 0.0017626653425395489
2023-01-24 10:39:13.392586: step: 848/533, loss: 0.0019507633987814188
2023-01-24 10:39:14.489982: step: 852/533, loss: 0.0017146292375400662
2023-01-24 10:39:15.584375: step: 856/533, loss: 0.0010669626062735915
2023-01-24 10:39:16.673582: step: 860/533, loss: 0.0016031644772738218
2023-01-24 10:39:17.779781: step: 864/533, loss: 0.0005642237374559045
2023-01-24 10:39:18.866672: step: 868/533, loss: 0.002014532685279846
2023-01-24 10:39:19.973292: step: 872/533, loss: 0.004993136506527662
2023-01-24 10:39:21.066602: step: 876/533, loss: 0.0014866860583424568
2023-01-24 10:39:22.227326: step: 880/533, loss: 0.0030124022159725428
2023-01-24 10:39:23.347700: step: 884/533, loss: 0.004391687456518412
2023-01-24 10:39:24.442994: step: 888/533, loss: 0.0008727506501600146
2023-01-24 10:39:25.536642: step: 892/533, loss: 0.0011682618642225862
2023-01-24 10:39:26.644127: step: 896/533, loss: 0.0029143481515347958
2023-01-24 10:39:27.732327: step: 900/533, loss: 0.003210943192243576
2023-01-24 10:39:28.861203: step: 904/533, loss: 0.0065821497701108456
2023-01-24 10:39:29.937892: step: 908/533, loss: 0.0007983128889463842
2023-01-24 10:39:31.044359: step: 912/533, loss: 0.0007535142940469086
2023-01-24 10:39:32.160913: step: 916/533, loss: 0.0013972041197121143
2023-01-24 10:39:33.264675: step: 920/533, loss: 0.002052387921139598
2023-01-24 10:39:34.346883: step: 924/533, loss: 0.0013589616864919662
2023-01-24 10:39:35.452680: step: 928/533, loss: 8.656123100081459e-05
2023-01-24 10:39:36.537691: step: 932/533, loss: 0.0028138230554759502
2023-01-24 10:39:37.645729: step: 936/533, loss: 0.0030169342644512653
2023-01-24 10:39:38.750630: step: 940/533, loss: 0.006691014394164085
2023-01-24 10:39:39.838507: step: 944/533, loss: 0.0038718010764569044
2023-01-24 10:39:40.941130: step: 948/533, loss: 0.0033565890043973923
2023-01-24 10:39:42.024830: step: 952/533, loss: 5.6925440730992705e-05
2023-01-24 10:39:43.105139: step: 956/533, loss: 0.01242921780794859
2023-01-24 10:39:44.207096: step: 960/533, loss: 0.010111834853887558
2023-01-24 10:39:45.306777: step: 964/533, loss: 0.0014661105815321207
2023-01-24 10:39:46.407134: step: 968/533, loss: 0.0039834752678871155
2023-01-24 10:39:47.503228: step: 972/533, loss: 0.007827145978808403
2023-01-24 10:39:48.607506: step: 976/533, loss: 0.000588025082834065
2023-01-24 10:39:49.697492: step: 980/533, loss: 0.0021358884405344725
2023-01-24 10:39:50.782183: step: 984/533, loss: 0.0005323893274180591
2023-01-24 10:39:51.873282: step: 988/533, loss: 0.003796221921220422
2023-01-24 10:39:52.964390: step: 992/533, loss: 0.0018567820079624653
2023-01-24 10:39:54.071452: step: 996/533, loss: 0.0067658983170986176
2023-01-24 10:39:55.164737: step: 1000/533, loss: 0.0009499022271484137
2023-01-24 10:39:56.266229: step: 1004/533, loss: 0.0011140524875372648
2023-01-24 10:39:57.379990: step: 1008/533, loss: 0.007084611337631941
2023-01-24 10:39:58.466202: step: 1012/533, loss: 0.005325814243406057
2023-01-24 10:39:59.557739: step: 1016/533, loss: 0.0022987648844718933
2023-01-24 10:40:00.644239: step: 1020/533, loss: 0.0013770429650321603
2023-01-24 10:40:01.739046: step: 1024/533, loss: 0.0006234582979232073
2023-01-24 10:40:02.821017: step: 1028/533, loss: 0.003225509077310562
2023-01-24 10:40:03.903601: step: 1032/533, loss: 0.0002216475986642763
2023-01-24 10:40:04.992795: step: 1036/533, loss: 0.0013336549745872617
2023-01-24 10:40:06.099485: step: 1040/533, loss: 0.004189975094050169
2023-01-24 10:40:07.189682: step: 1044/533, loss: 0.00040315158548764884
2023-01-24 10:40:08.298903: step: 1048/533, loss: 0.004613040946424007
2023-01-24 10:40:09.366095: step: 1052/533, loss: 0.003209726419299841
2023-01-24 10:40:10.457117: step: 1056/533, loss: 0.00028606096748262644
2023-01-24 10:40:11.538403: step: 1060/533, loss: 0.001666568685323
2023-01-24 10:40:12.622325: step: 1064/533, loss: 0.002614523284137249
2023-01-24 10:40:13.707427: step: 1068/533, loss: 0.000115613205707632
2023-01-24 10:40:14.793612: step: 1072/533, loss: 0.006163819693028927
2023-01-24 10:40:15.873606: step: 1076/533, loss: 0.0001181361367343925
2023-01-24 10:40:16.956447: step: 1080/533, loss: 0.015631308779120445
2023-01-24 10:40:18.064468: step: 1084/533, loss: 0.011310567148029804
2023-01-24 10:40:19.172764: step: 1088/533, loss: 0.0032153711654245853
2023-01-24 10:40:20.270263: step: 1092/533, loss: 0.0001527929853182286
2023-01-24 10:40:21.390698: step: 1096/533, loss: 0.0017432760214433074
2023-01-24 10:40:22.472162: step: 1100/533, loss: 0.0009569507092237473
2023-01-24 10:40:23.578337: step: 1104/533, loss: 0.0015057430136948824
2023-01-24 10:40:24.666846: step: 1108/533, loss: 1.595540925336536e-05
2023-01-24 10:40:25.794734: step: 1112/533, loss: 0.008377277292311192
2023-01-24 10:40:26.874242: step: 1116/533, loss: 0.006671874318271875
2023-01-24 10:40:27.977781: step: 1120/533, loss: 0.00024786757421679795
2023-01-24 10:40:29.060647: step: 1124/533, loss: 0.012387343682348728
2023-01-24 10:40:30.144707: step: 1128/533, loss: 0.0037991127464920282
2023-01-24 10:40:31.238473: step: 1132/533, loss: 0.0019681407138705254
2023-01-24 10:40:32.337159: step: 1136/533, loss: 0.004722165409475565
2023-01-24 10:40:33.425094: step: 1140/533, loss: 0.00540987029671669
2023-01-24 10:40:34.527487: step: 1144/533, loss: 0.01612924225628376
2023-01-24 10:40:35.616241: step: 1148/533, loss: 0.00011862082465086132
2023-01-24 10:40:36.710685: step: 1152/533, loss: 0.0002534756495151669
2023-01-24 10:40:37.798370: step: 1156/533, loss: 0.008664361201226711
2023-01-24 10:40:38.913529: step: 1160/533, loss: 0.0018622050993144512
2023-01-24 10:40:40.010440: step: 1164/533, loss: 0.00708386953920126
2023-01-24 10:40:41.112663: step: 1168/533, loss: 0.010939963161945343
2023-01-24 10:40:42.206935: step: 1172/533, loss: 0.0052548907697200775
2023-01-24 10:40:43.292395: step: 1176/533, loss: 0.0010494234738871455
2023-01-24 10:40:44.381263: step: 1180/533, loss: 6.064847639208892e-06
2023-01-24 10:40:45.472934: step: 1184/533, loss: 0.0026288521476089954
2023-01-24 10:40:46.578939: step: 1188/533, loss: 5.8678451750893146e-05
2023-01-24 10:40:47.681727: step: 1192/533, loss: 0.0005747538525611162
2023-01-24 10:40:48.799947: step: 1196/533, loss: 5.5157281167339534e-05
2023-01-24 10:40:49.879053: step: 1200/533, loss: 6.972187838982791e-05
2023-01-24 10:40:50.953059: step: 1204/533, loss: 1.5445713870576583e-05
2023-01-24 10:40:52.061408: step: 1208/533, loss: 0.004274369683116674
2023-01-24 10:40:53.160807: step: 1212/533, loss: 0.0012518336297944188
2023-01-24 10:40:54.252494: step: 1216/533, loss: 0.002084947656840086
2023-01-24 10:40:55.349099: step: 1220/533, loss: 0.012687657959759235
2023-01-24 10:40:56.443869: step: 1224/533, loss: 0.00016052197315730155
2023-01-24 10:40:57.515000: step: 1228/533, loss: 1.5174869986367412e-05
2023-01-24 10:40:58.587729: step: 1232/533, loss: 0.003119942732155323
2023-01-24 10:40:59.686535: step: 1236/533, loss: 0.002927095163613558
2023-01-24 10:41:00.768302: step: 1240/533, loss: 0.0008320771157741547
2023-01-24 10:41:01.864917: step: 1244/533, loss: 0.003455535275861621
2023-01-24 10:41:02.955749: step: 1248/533, loss: 0.0052369278855621815
2023-01-24 10:41:04.046943: step: 1252/533, loss: 9.038031566888094e-05
2023-01-24 10:41:05.141644: step: 1256/533, loss: 4.2981599108316004e-05
2023-01-24 10:41:06.239626: step: 1260/533, loss: 0.00869517307728529
2023-01-24 10:41:07.333281: step: 1264/533, loss: 0.0004897586186416447
2023-01-24 10:41:08.448915: step: 1268/533, loss: 0.00048360254731960595
2023-01-24 10:41:09.564145: step: 1272/533, loss: 0.0003859882417600602
2023-01-24 10:41:10.663701: step: 1276/533, loss: 0.0014212566893547773
2023-01-24 10:41:11.755997: step: 1280/533, loss: 8.04123828856973e-06
2023-01-24 10:41:12.837077: step: 1284/533, loss: 0.003319635521620512
2023-01-24 10:41:13.956570: step: 1288/533, loss: 0.00011288908717688173
2023-01-24 10:41:15.082292: step: 1292/533, loss: 0.0001500264334026724
2023-01-24 10:41:16.195423: step: 1296/533, loss: 0.0009004746098071337
2023-01-24 10:41:17.296982: step: 1300/533, loss: 0.007022792939096689
2023-01-24 10:41:18.395107: step: 1304/533, loss: 0.0013324968749657273
2023-01-24 10:41:19.507133: step: 1308/533, loss: 0.006250076927244663
2023-01-24 10:41:20.605054: step: 1312/533, loss: 4.1059764043893665e-05
2023-01-24 10:41:21.675760: step: 1316/533, loss: 0.005909195635467768
2023-01-24 10:41:22.769667: step: 1320/533, loss: 3.059494338231161e-05
2023-01-24 10:41:23.869342: step: 1324/533, loss: 0.0016796001000329852
2023-01-24 10:41:24.946000: step: 1328/533, loss: 0.005690047983080149
2023-01-24 10:41:26.036335: step: 1332/533, loss: 0.00046010102960281074
2023-01-24 10:41:27.134243: step: 1336/533, loss: 0.0009190365672111511
2023-01-24 10:41:28.215353: step: 1340/533, loss: 0.02107909880578518
2023-01-24 10:41:29.305044: step: 1344/533, loss: 0.0018169950926676393
2023-01-24 10:41:30.382258: step: 1348/533, loss: 0.0020604627206921577
2023-01-24 10:41:31.481131: step: 1352/533, loss: 0.0042875707149505615
2023-01-24 10:41:32.588600: step: 1356/533, loss: 0.007826408371329308
2023-01-24 10:41:33.653292: step: 1360/533, loss: 0.0033560264855623245
2023-01-24 10:41:34.756070: step: 1364/533, loss: 0.005118506029248238
2023-01-24 10:41:35.855267: step: 1368/533, loss: 0.006081028375774622
2023-01-24 10:41:36.946709: step: 1372/533, loss: 0.0005061220726929605
2023-01-24 10:41:38.071211: step: 1376/533, loss: 0.0017817443003877997
2023-01-24 10:41:39.172998: step: 1380/533, loss: 0.004070763476192951
2023-01-24 10:41:40.256481: step: 1384/533, loss: 0.0013133843895047903
2023-01-24 10:41:41.373123: step: 1388/533, loss: 0.0024674462620168924
2023-01-24 10:41:42.455915: step: 1392/533, loss: 7.460982305929065e-05
2023-01-24 10:41:43.570378: step: 1396/533, loss: 0.002592416014522314
2023-01-24 10:41:44.677651: step: 1400/533, loss: 0.014221341349184513
2023-01-24 10:41:45.763323: step: 1404/533, loss: 0.0009545204811729491
2023-01-24 10:41:46.870209: step: 1408/533, loss: 0.007501746062189341
2023-01-24 10:41:47.979894: step: 1412/533, loss: 0.004466319922357798
2023-01-24 10:41:49.091394: step: 1416/533, loss: 0.0034969865810126066
2023-01-24 10:41:50.195425: step: 1420/533, loss: 5.248958768788725e-05
2023-01-24 10:41:51.286365: step: 1424/533, loss: 0.0003983006172347814
2023-01-24 10:41:52.381346: step: 1428/533, loss: 0.0029391562566161156
2023-01-24 10:41:53.481702: step: 1432/533, loss: 0.009896871633827686
2023-01-24 10:41:54.592119: step: 1436/533, loss: 0.0016631693579256535
2023-01-24 10:41:55.697790: step: 1440/533, loss: 0.00017429159197490662
2023-01-24 10:41:56.806575: step: 1444/533, loss: 0.008947030641138554
2023-01-24 10:41:57.897003: step: 1448/533, loss: 0.003940290305763483
2023-01-24 10:41:58.976923: step: 1452/533, loss: 0.0017901642713695765
2023-01-24 10:42:00.060755: step: 1456/533, loss: 0.00017248079529963434
2023-01-24 10:42:01.159438: step: 1460/533, loss: 0.011474172584712505
2023-01-24 10:42:02.235916: step: 1464/533, loss: 0.004037350881844759
2023-01-24 10:42:03.319228: step: 1468/533, loss: 0.004886717535555363
2023-01-24 10:42:04.419828: step: 1472/533, loss: 0.0021581940818578005
2023-01-24 10:42:05.519892: step: 1476/533, loss: 0.0038235746324062347
2023-01-24 10:42:06.643372: step: 1480/533, loss: 0.004473594948649406
2023-01-24 10:42:07.733953: step: 1484/533, loss: 0.00046075211139395833
2023-01-24 10:42:08.814399: step: 1488/533, loss: 2.647105611686129e-05
2023-01-24 10:42:09.922343: step: 1492/533, loss: 0.0127689428627491
2023-01-24 10:42:11.017398: step: 1496/533, loss: 0.002868526615202427
2023-01-24 10:42:12.118939: step: 1500/533, loss: 0.0033692873548716307
2023-01-24 10:42:13.230200: step: 1504/533, loss: 2.8439835659810342e-05
2023-01-24 10:42:14.330789: step: 1508/533, loss: 2.4384138669120148e-05
2023-01-24 10:42:15.455657: step: 1512/533, loss: 0.0018239350756630301
2023-01-24 10:42:16.552085: step: 1516/533, loss: 0.007801080588251352
2023-01-24 10:42:17.635134: step: 1520/533, loss: 0.00037450564559549093
2023-01-24 10:42:18.705368: step: 1524/533, loss: 0.021633770316839218
2023-01-24 10:42:19.820759: step: 1528/533, loss: 0.0077534327283501625
2023-01-24 10:42:20.974759: step: 1532/533, loss: 0.0006354067591018975
2023-01-24 10:42:22.056764: step: 1536/533, loss: 0.0033184823114424944
2023-01-24 10:42:23.150485: step: 1540/533, loss: 0.0022576290648430586
2023-01-24 10:42:24.242480: step: 1544/533, loss: 5.574202532443451e-06
2023-01-24 10:42:25.326270: step: 1548/533, loss: 0.00017976808885578066
2023-01-24 10:42:26.425143: step: 1552/533, loss: 0.020325370132923126
2023-01-24 10:42:27.511934: step: 1556/533, loss: 0.00034587705158628523
2023-01-24 10:42:28.596642: step: 1560/533, loss: 0.0013800077140331268
2023-01-24 10:42:29.698044: step: 1564/533, loss: 0.006364561151713133
2023-01-24 10:42:30.784859: step: 1568/533, loss: 0.001842388533987105
2023-01-24 10:42:31.863737: step: 1572/533, loss: 0.0008123943116515875
2023-01-24 10:42:32.965007: step: 1576/533, loss: 0.005211479961872101
2023-01-24 10:42:34.057854: step: 1580/533, loss: 8.881805115379393e-06
2023-01-24 10:42:35.137566: step: 1584/533, loss: 0.0032975429203361273
2023-01-24 10:42:36.226090: step: 1588/533, loss: 0.0031447771470993757
2023-01-24 10:42:37.354761: step: 1592/533, loss: 0.041540492326021194
2023-01-24 10:42:38.450427: step: 1596/533, loss: 0.0015757762594148517
2023-01-24 10:42:39.550809: step: 1600/533, loss: 0.0019704510923475027
2023-01-24 10:42:40.640545: step: 1604/533, loss: 0.00015862021245993674
2023-01-24 10:42:41.734845: step: 1608/533, loss: 0.0013390674721449614
2023-01-24 10:42:42.834187: step: 1612/533, loss: 0.005046529695391655
2023-01-24 10:42:43.927247: step: 1616/533, loss: 0.0006613946170546114
2023-01-24 10:42:45.037315: step: 1620/533, loss: 0.0007267061155289412
2023-01-24 10:42:46.121007: step: 1624/533, loss: 0.00017341694911010563
2023-01-24 10:42:47.201130: step: 1628/533, loss: 0.00011128465121146291
2023-01-24 10:42:48.306993: step: 1632/533, loss: 0.010883492417633533
2023-01-24 10:42:49.413661: step: 1636/533, loss: 0.0018650345737114549
2023-01-24 10:42:50.515643: step: 1640/533, loss: 6.60491205053404e-05
2023-01-24 10:42:51.614179: step: 1644/533, loss: 0.0025949866976588964
2023-01-24 10:42:52.689142: step: 1648/533, loss: 0.0006640476058237255
2023-01-24 10:42:53.770645: step: 1652/533, loss: 0.0026031839661300182
2023-01-24 10:42:54.840413: step: 1656/533, loss: 0.009180408902466297
2023-01-24 10:42:55.925244: step: 1660/533, loss: 0.005370055325329304
2023-01-24 10:42:57.022331: step: 1664/533, loss: 0.014299515634775162
2023-01-24 10:42:58.124431: step: 1668/533, loss: 0.0014423374086618423
2023-01-24 10:42:59.241071: step: 1672/533, loss: 0.043578293174505234
2023-01-24 10:43:00.314169: step: 1676/533, loss: 0.0021850289776921272
2023-01-24 10:43:01.412478: step: 1680/533, loss: 0.0030041311401873827
2023-01-24 10:43:02.492904: step: 1684/533, loss: 0.000998139032162726
2023-01-24 10:43:03.589109: step: 1688/533, loss: 5.8946981880581006e-05
2023-01-24 10:43:04.703898: step: 1692/533, loss: 0.0032190654892474413
2023-01-24 10:43:05.819518: step: 1696/533, loss: 0.00610214052721858
2023-01-24 10:43:06.913015: step: 1700/533, loss: 0.0018859332194551826
2023-01-24 10:43:08.013890: step: 1704/533, loss: 0.007525980472564697
2023-01-24 10:43:09.090647: step: 1708/533, loss: 0.002822878770530224
2023-01-24 10:43:10.185749: step: 1712/533, loss: 0.001391697209328413
2023-01-24 10:43:11.272354: step: 1716/533, loss: 0.003079632529988885
2023-01-24 10:43:12.380410: step: 1720/533, loss: 0.0029867570847272873
2023-01-24 10:43:13.460251: step: 1724/533, loss: 1.0082648259412963e-05
2023-01-24 10:43:14.551239: step: 1728/533, loss: 0.003066820092499256
2023-01-24 10:43:15.640760: step: 1732/533, loss: 0.009043503552675247
2023-01-24 10:43:16.730705: step: 1736/533, loss: 0.005965122953057289
2023-01-24 10:43:17.815620: step: 1740/533, loss: 0.0012175337178632617
2023-01-24 10:43:18.895237: step: 1744/533, loss: 0.003957536071538925
2023-01-24 10:43:19.974825: step: 1748/533, loss: 0.001041304087266326
2023-01-24 10:43:21.089867: step: 1752/533, loss: 0.005643005482852459
2023-01-24 10:43:22.195877: step: 1756/533, loss: 0.008474212139844894
2023-01-24 10:43:23.284422: step: 1760/533, loss: 0.0006694925832562149
2023-01-24 10:43:24.390320: step: 1764/533, loss: 5.3829637181479484e-05
2023-01-24 10:43:25.460934: step: 1768/533, loss: 0.006600833963602781
2023-01-24 10:43:26.539274: step: 1772/533, loss: 0.00011529691255418584
2023-01-24 10:43:27.636188: step: 1776/533, loss: 0.0026294745039194822
2023-01-24 10:43:28.754546: step: 1780/533, loss: 0.004196548834443092
2023-01-24 10:43:29.850666: step: 1784/533, loss: 0.002364157699048519
2023-01-24 10:43:30.929137: step: 1788/533, loss: 7.332391396630555e-05
2023-01-24 10:43:32.057140: step: 1792/533, loss: 0.0019309991039335728
2023-01-24 10:43:33.133680: step: 1796/533, loss: 0.0014684053603559732
2023-01-24 10:43:34.210381: step: 1800/533, loss: 0.0016879334580153227
2023-01-24 10:43:35.305392: step: 1804/533, loss: 0.06574810296297073
2023-01-24 10:43:36.408752: step: 1808/533, loss: 0.007456582505255938
2023-01-24 10:43:37.514084: step: 1812/533, loss: 0.007528172805905342
2023-01-24 10:43:38.612156: step: 1816/533, loss: 6.815748929511756e-05
2023-01-24 10:43:39.710198: step: 1820/533, loss: 0.007705535739660263
2023-01-24 10:43:40.823231: step: 1824/533, loss: 0.006849327124655247
2023-01-24 10:43:41.904404: step: 1828/533, loss: 0.007550984621047974
2023-01-24 10:43:42.988142: step: 1832/533, loss: 9.112316183745861e-05
2023-01-24 10:43:44.070263: step: 1836/533, loss: 0.0014395969919860363
2023-01-24 10:43:45.156234: step: 1840/533, loss: 0.0020976944360882044
2023-01-24 10:43:46.252792: step: 1844/533, loss: 0.0002585102920420468
2023-01-24 10:43:47.362257: step: 1848/533, loss: 0.007740733679383993
2023-01-24 10:43:48.453032: step: 1852/533, loss: 0.03051679953932762
2023-01-24 10:43:49.550854: step: 1856/533, loss: 0.0029383471701294184
2023-01-24 10:43:50.652342: step: 1860/533, loss: 0.0013876514276489615
2023-01-24 10:43:51.763487: step: 1864/533, loss: 0.00042652667616494
2023-01-24 10:43:52.852961: step: 1868/533, loss: 0.004762750118970871
2023-01-24 10:43:53.963156: step: 1872/533, loss: 0.0026988808531314135
2023-01-24 10:43:55.058627: step: 1876/533, loss: 0.00013081508222967386
2023-01-24 10:43:56.142292: step: 1880/533, loss: 0.0019252138445153832
2023-01-24 10:43:57.263455: step: 1884/533, loss: 0.004507293459028006
2023-01-24 10:43:58.344560: step: 1888/533, loss: 0.0007141348905861378
2023-01-24 10:43:59.439562: step: 1892/533, loss: 0.006849430967122316
2023-01-24 10:44:00.537850: step: 1896/533, loss: 0.0031171541195362806
2023-01-24 10:44:01.651404: step: 1900/533, loss: 4.955739768774947e-06
2023-01-24 10:44:02.745229: step: 1904/533, loss: 0.0017322179628536105
2023-01-24 10:44:03.848704: step: 1908/533, loss: 0.0002128157502738759
2023-01-24 10:44:04.945104: step: 1912/533, loss: 0.002660390455275774
2023-01-24 10:44:06.045220: step: 1916/533, loss: 0.003699501510709524
2023-01-24 10:44:07.147642: step: 1920/533, loss: 0.014841990545392036
2023-01-24 10:44:08.253254: step: 1924/533, loss: 0.0009250234579667449
2023-01-24 10:44:09.348252: step: 1928/533, loss: 0.002279134001582861
2023-01-24 10:44:10.447510: step: 1932/533, loss: 0.007421928457915783
2023-01-24 10:44:11.552886: step: 1936/533, loss: 0.000745499215554446
2023-01-24 10:44:12.643041: step: 1940/533, loss: 0.0027754546608775854
2023-01-24 10:44:13.742223: step: 1944/533, loss: 0.02478289045393467
2023-01-24 10:44:14.832809: step: 1948/533, loss: 9.963645197785809e-07
2023-01-24 10:44:15.934511: step: 1952/533, loss: 0.00018304065451957285
2023-01-24 10:44:17.057673: step: 1956/533, loss: 0.005622530356049538
2023-01-24 10:44:18.160936: step: 1960/533, loss: 0.00016430276446044445
2023-01-24 10:44:19.255213: step: 1964/533, loss: 0.002509491750970483
2023-01-24 10:44:20.335101: step: 1968/533, loss: 0.003993680234998465
2023-01-24 10:44:21.432195: step: 1972/533, loss: 0.0023097216617316008
2023-01-24 10:44:22.542417: step: 1976/533, loss: 0.003144592512398958
2023-01-24 10:44:23.618498: step: 1980/533, loss: 3.673838364193216e-05
2023-01-24 10:44:24.706415: step: 1984/533, loss: 0.0010960212675854564
2023-01-24 10:44:25.813713: step: 1988/533, loss: 0.010138210840523243
2023-01-24 10:44:26.897839: step: 1992/533, loss: 0.006285564042627811
2023-01-24 10:44:27.995647: step: 1996/533, loss: 0.0018664976814761758
2023-01-24 10:44:29.088209: step: 2000/533, loss: 0.0
2023-01-24 10:44:30.205145: step: 2004/533, loss: 0.0049706436693668365
2023-01-24 10:44:31.315209: step: 2008/533, loss: 0.007012594025582075
2023-01-24 10:44:32.411536: step: 2012/533, loss: 0.004583301953971386
2023-01-24 10:44:33.518422: step: 2016/533, loss: 0.002588975941762328
2023-01-24 10:44:34.612452: step: 2020/533, loss: 0.0029606830794364214
2023-01-24 10:44:35.692422: step: 2024/533, loss: 0.003285836661234498
2023-01-24 10:44:36.799567: step: 2028/533, loss: 0.00846436433494091
2023-01-24 10:44:37.882759: step: 2032/533, loss: 0.00017492401821073145
2023-01-24 10:44:39.004094: step: 2036/533, loss: 0.002809682860970497
2023-01-24 10:44:40.085984: step: 2040/533, loss: 0.002871294040232897
2023-01-24 10:44:41.193498: step: 2044/533, loss: 0.0009610694251023233
2023-01-24 10:44:42.278688: step: 2048/533, loss: 0.0023990455083549023
2023-01-24 10:44:43.394269: step: 2052/533, loss: 0.003915017936378717
2023-01-24 10:44:44.497987: step: 2056/533, loss: 0.0024210214614868164
2023-01-24 10:44:45.593685: step: 2060/533, loss: 0.0021397913806140423
2023-01-24 10:44:46.689454: step: 2064/533, loss: 0.005917406640946865
2023-01-24 10:44:47.776556: step: 2068/533, loss: 2.322784894204233e-05
2023-01-24 10:44:48.872599: step: 2072/533, loss: 0.001241489197127521
2023-01-24 10:44:49.983098: step: 2076/533, loss: 0.0032497572246938944
2023-01-24 10:44:51.078372: step: 2080/533, loss: 0.00013577584468293935
2023-01-24 10:44:52.148925: step: 2084/533, loss: 0.017105886712670326
2023-01-24 10:44:53.244921: step: 2088/533, loss: 0.019909784197807312
2023-01-24 10:44:54.335485: step: 2092/533, loss: 0.0020719622261822224
2023-01-24 10:44:55.431185: step: 2096/533, loss: 0.008762981742620468
2023-01-24 10:44:56.531065: step: 2100/533, loss: 0.00015584642824251205
2023-01-24 10:44:57.627154: step: 2104/533, loss: 0.001080223941244185
2023-01-24 10:44:58.732774: step: 2108/533, loss: 0.0004094424657523632
2023-01-24 10:44:59.845254: step: 2112/533, loss: 0.0005582819576375186
2023-01-24 10:45:00.954986: step: 2116/533, loss: 0.009994668886065483
2023-01-24 10:45:02.052310: step: 2120/533, loss: 9.148784556600731e-06
2023-01-24 10:45:03.170538: step: 2124/533, loss: 0.0014986387686803937
2023-01-24 10:45:04.259603: step: 2128/533, loss: 1.8456688849255443e-05
2023-01-24 10:45:05.359050: step: 2132/533, loss: 0.0036223598290234804
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38084069168506257, 'r': 0.32736401012017713, 'f1': 0.35208333333333336}, 'combined': 0.2594298245614035, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39829915899719004, 'r': 0.35923520301861944, 'f1': 0.37775997081836626}, 'combined': 0.25183998054557744, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36087966046125636, 'r': 0.31979279209754596, 'f1': 0.3390961799505165}, 'combined': 0.24986034312143318, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3922967267414776, 'r': 0.3100652974822063, 'f1': 0.3463672496041832}, 'combined': 0.23091149973612207, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34486230798051704, 'r': 0.3082165978345798, 'f1': 0.32551131675114936}, 'combined': 0.23985044392189953, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3810104824074642, 'r': 0.34144400923438134, 'f1': 0.36014378255959084}, 'combined': 0.24009585503972716, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35048248859292147, 'r': 0.31722988056702756, 'f1': 0.33302818139207874}, 'combined': 0.2453891862889001, 'stategy': 1, 'epoch': 16}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38299654503075575, 'r': 0.34432862461899677, 'f1': 0.3626347033962093}, 'combined': 0.24175646893080613, 'stategy': 1, 'epoch': 16}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 16}
******************************
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 10:47:23.438261: step: 4/533, loss: 0.005062687676399946
2023-01-24 10:47:24.488815: step: 8/533, loss: 0.002071927534416318
2023-01-24 10:47:25.588889: step: 12/533, loss: 0.0021633196156471968
2023-01-24 10:47:26.672230: step: 16/533, loss: 0.009308838285505772
2023-01-24 10:47:27.768687: step: 20/533, loss: 0.0015118271112442017
2023-01-24 10:47:28.856640: step: 24/533, loss: 0.0017828185809776187
2023-01-24 10:47:29.954797: step: 28/533, loss: 0.07316688448190689
2023-01-24 10:47:31.035530: step: 32/533, loss: 0.0034202723763883114
2023-01-24 10:47:32.135219: step: 36/533, loss: 0.007765723392367363
2023-01-24 10:47:33.221179: step: 40/533, loss: 0.0006457660347223282
2023-01-24 10:47:34.301472: step: 44/533, loss: 0.0025299901608377695
2023-01-24 10:47:35.364646: step: 48/533, loss: 0.0013185723219066858
2023-01-24 10:47:36.446607: step: 52/533, loss: 0.0008052604971453547
2023-01-24 10:47:37.527126: step: 56/533, loss: 0.00024710578145459294
2023-01-24 10:47:38.628940: step: 60/533, loss: 0.0011958400718867779
2023-01-24 10:47:39.718499: step: 64/533, loss: 0.0016897801542654634
2023-01-24 10:47:40.804975: step: 68/533, loss: 1.0083678716910072e-05
2023-01-24 10:47:41.878647: step: 72/533, loss: 0.00021768581063952297
2023-01-24 10:47:42.973883: step: 76/533, loss: 0.0006256516207940876
2023-01-24 10:47:44.069446: step: 80/533, loss: 2.1401288904598914e-05
2023-01-24 10:47:45.166571: step: 84/533, loss: 3.06406436720863e-05
2023-01-24 10:47:46.256626: step: 88/533, loss: 0.0010649897158145905
2023-01-24 10:47:47.336724: step: 92/533, loss: 0.0008405293338000774
2023-01-24 10:47:48.411600: step: 96/533, loss: 0.00019941054051741958
2023-01-24 10:47:49.491594: step: 100/533, loss: 0.0034869294613599777
2023-01-24 10:47:50.572355: step: 104/533, loss: 7.810726856405381e-06
2023-01-24 10:47:51.679003: step: 108/533, loss: 0.01118532381951809
2023-01-24 10:47:52.762345: step: 112/533, loss: 0.01056651957333088
2023-01-24 10:47:53.875281: step: 116/533, loss: 3.306894359411672e-05
2023-01-24 10:47:54.999106: step: 120/533, loss: 0.002993333851918578
2023-01-24 10:47:56.094447: step: 124/533, loss: 0.005563503131270409
2023-01-24 10:47:57.186293: step: 128/533, loss: 9.25996428122744e-05
2023-01-24 10:47:58.294007: step: 132/533, loss: 0.0010568808065727353
2023-01-24 10:47:59.367952: step: 136/533, loss: 0.0009048984502442181
2023-01-24 10:48:00.453699: step: 140/533, loss: 0.0008401935338042676
2023-01-24 10:48:01.564286: step: 144/533, loss: 2.6847361368709244e-05
2023-01-24 10:48:02.662134: step: 148/533, loss: 0.0022782294545322657
2023-01-24 10:48:03.754052: step: 152/533, loss: 0.005917553324252367
2023-01-24 10:48:04.849709: step: 156/533, loss: 0.0020961356349289417
2023-01-24 10:48:05.948534: step: 160/533, loss: 0.0300761666148901
2023-01-24 10:48:07.036495: step: 164/533, loss: 0.001063434174284339
2023-01-24 10:48:08.129836: step: 168/533, loss: 0.004255944397300482
2023-01-24 10:48:09.196793: step: 172/533, loss: 0.0
2023-01-24 10:48:10.305155: step: 176/533, loss: 0.00041442649671807885
2023-01-24 10:48:11.400255: step: 180/533, loss: 1.9534902094164863e-05
2023-01-24 10:48:12.485291: step: 184/533, loss: 0.015576104633510113
2023-01-24 10:48:13.607094: step: 188/533, loss: 0.0026228029746562243
2023-01-24 10:48:14.703023: step: 192/533, loss: 0.003384827869012952
2023-01-24 10:48:15.794267: step: 196/533, loss: 0.00015783528215251863
2023-01-24 10:48:16.894521: step: 200/533, loss: 0.0014213575050234795
2023-01-24 10:48:17.970939: step: 204/533, loss: 0.0060867490246891975
2023-01-24 10:48:19.061013: step: 208/533, loss: 0.002389300614595413
2023-01-24 10:48:20.153168: step: 212/533, loss: 4.454513145901728e-06
2023-01-24 10:48:21.260281: step: 216/533, loss: 0.003102466929703951
2023-01-24 10:48:22.363874: step: 220/533, loss: 0.0034140944480895996
2023-01-24 10:48:23.458345: step: 224/533, loss: 0.0021139224991202354
2023-01-24 10:48:24.560001: step: 228/533, loss: 0.010329709388315678
2023-01-24 10:48:25.646007: step: 232/533, loss: 0.00010708403715398163
2023-01-24 10:48:26.730063: step: 236/533, loss: 0.0018410123884677887
2023-01-24 10:48:27.821644: step: 240/533, loss: 0.005139097571372986
2023-01-24 10:48:28.922094: step: 244/533, loss: 0.00016105952090583742
2023-01-24 10:48:30.021380: step: 248/533, loss: 0.008179176598787308
2023-01-24 10:48:31.110700: step: 252/533, loss: 0.00610836036503315
2023-01-24 10:48:32.216411: step: 256/533, loss: 0.00027326808776706457
2023-01-24 10:48:33.333043: step: 260/533, loss: 0.0010019134497269988
2023-01-24 10:48:34.424329: step: 264/533, loss: 0.007852811366319656
2023-01-24 10:48:35.525594: step: 268/533, loss: 0.0021419445984065533
2023-01-24 10:48:36.607013: step: 272/533, loss: 8.590459037804976e-05
2023-01-24 10:48:37.697886: step: 276/533, loss: 0.0002794333850033581
2023-01-24 10:48:38.786182: step: 280/533, loss: 3.471372838248499e-05
2023-01-24 10:48:39.918729: step: 284/533, loss: 0.009511951357126236
2023-01-24 10:48:41.008505: step: 288/533, loss: 0.0013632086338475347
2023-01-24 10:48:42.133848: step: 292/533, loss: 0.0014141640858724713
2023-01-24 10:48:43.239247: step: 296/533, loss: 0.04954986274242401
2023-01-24 10:48:44.332067: step: 300/533, loss: 0.001771342707797885
2023-01-24 10:48:45.425696: step: 304/533, loss: 0.0012996740406379104
2023-01-24 10:48:46.512668: step: 308/533, loss: 2.1290923541528173e-05
2023-01-24 10:48:47.602524: step: 312/533, loss: 7.077970849422854e-07
2023-01-24 10:48:48.707346: step: 316/533, loss: 0.004388987086713314
2023-01-24 10:48:49.796449: step: 320/533, loss: 6.923225737409666e-05
2023-01-24 10:48:50.877182: step: 324/533, loss: 0.0017223019385710359
2023-01-24 10:48:51.987242: step: 328/533, loss: 0.007034540642052889
2023-01-24 10:48:53.067604: step: 332/533, loss: 0.0013285073218867183
2023-01-24 10:48:54.161922: step: 336/533, loss: 0.00172691629268229
2023-01-24 10:48:55.256862: step: 340/533, loss: 0.0006792946951463819
2023-01-24 10:48:56.338795: step: 344/533, loss: 3.979965640610317e-06
2023-01-24 10:48:57.427980: step: 348/533, loss: 0.008409262634813786
2023-01-24 10:48:58.542842: step: 352/533, loss: 0.005284180399030447
2023-01-24 10:48:59.646370: step: 356/533, loss: 0.002504500327631831
2023-01-24 10:49:00.749854: step: 360/533, loss: 0.0003335425863042474
2023-01-24 10:49:01.836942: step: 364/533, loss: 0.0015229147393256426
2023-01-24 10:49:02.930276: step: 368/533, loss: 0.028152285143733025
2023-01-24 10:49:04.033087: step: 372/533, loss: 0.0010969177819788456
2023-01-24 10:49:05.113534: step: 376/533, loss: 0.0014910788740962744
2023-01-24 10:49:06.201193: step: 380/533, loss: 0.0028997359331697226
2023-01-24 10:49:07.315175: step: 384/533, loss: 2.3441934899892658e-05
2023-01-24 10:49:08.422490: step: 388/533, loss: 0.00019604586123023182
2023-01-24 10:49:09.511882: step: 392/533, loss: 0.0019105934770777822
2023-01-24 10:49:10.615219: step: 396/533, loss: 1.7485339412814938e-05
2023-01-24 10:49:11.708651: step: 400/533, loss: 1.2313786101003643e-05
2023-01-24 10:49:12.848699: step: 404/533, loss: 0.0016934183659031987
2023-01-24 10:49:13.960231: step: 408/533, loss: 0.0024167040828615427
2023-01-24 10:49:15.060285: step: 412/533, loss: 8.922498091123998e-05
2023-01-24 10:49:16.174729: step: 416/533, loss: 0.001391711295582354
2023-01-24 10:49:17.267764: step: 420/533, loss: 0.007077332586050034
2023-01-24 10:49:18.367444: step: 424/533, loss: 6.138377648312598e-05
2023-01-24 10:49:19.457971: step: 428/533, loss: 6.373259384417906e-05
2023-01-24 10:49:20.578095: step: 432/533, loss: 8.907536539481953e-05
2023-01-24 10:49:21.666382: step: 436/533, loss: 0.0022983362432569265
2023-01-24 10:49:22.744518: step: 440/533, loss: 0.006345545873045921
2023-01-24 10:49:23.827873: step: 444/533, loss: 1.8150205505662598e-05
2023-01-24 10:49:24.936653: step: 448/533, loss: 0.0037839829456061125
2023-01-24 10:49:26.016074: step: 452/533, loss: 0.00024723756359890103
2023-01-24 10:49:27.135619: step: 456/533, loss: 0.0015087121864780784
2023-01-24 10:49:28.253124: step: 460/533, loss: 0.0074209910817444324
2023-01-24 10:49:29.370679: step: 464/533, loss: 0.002466948237270117
2023-01-24 10:49:30.473923: step: 468/533, loss: 0.00043910546810366213
2023-01-24 10:49:31.569483: step: 472/533, loss: 0.00017136854876298457
2023-01-24 10:49:32.664756: step: 476/533, loss: 0.002746874000877142
2023-01-24 10:49:33.777229: step: 480/533, loss: 0.00022558360069524497
2023-01-24 10:49:34.872455: step: 484/533, loss: 0.0016314767999574542
2023-01-24 10:49:35.961101: step: 488/533, loss: 0.0001262743171537295
2023-01-24 10:49:37.067122: step: 492/533, loss: 0.0006094829295761883
2023-01-24 10:49:38.169844: step: 496/533, loss: 0.0013159788213670254
2023-01-24 10:49:39.263225: step: 500/533, loss: 0.00145278952550143
2023-01-24 10:49:40.354848: step: 504/533, loss: 0.0025376188568770885
2023-01-24 10:49:41.449933: step: 508/533, loss: 0.0011324470397084951
2023-01-24 10:49:42.529206: step: 512/533, loss: 0.0020807001274079084
2023-01-24 10:49:43.626579: step: 516/533, loss: 0.0010600340319797397
2023-01-24 10:49:44.740749: step: 520/533, loss: 0.00034821746521629393
2023-01-24 10:49:45.841950: step: 524/533, loss: 0.003926863428205252
2023-01-24 10:49:46.958508: step: 528/533, loss: 0.001203176099807024
2023-01-24 10:49:48.052729: step: 532/533, loss: 0.0019781410228461027
2023-01-24 10:49:49.140704: step: 536/533, loss: 0.0035326352808624506
2023-01-24 10:49:50.256139: step: 540/533, loss: 0.00019127369159832597
2023-01-24 10:49:51.350310: step: 544/533, loss: 0.00021687190746888518
2023-01-24 10:49:52.447145: step: 548/533, loss: 0.0014056521467864513
2023-01-24 10:49:53.526278: step: 552/533, loss: 0.0010903450893238187
2023-01-24 10:49:54.611966: step: 556/533, loss: 0.003912372048944235
2023-01-24 10:49:55.714672: step: 560/533, loss: 5.2034670261491556e-06
2023-01-24 10:49:56.823505: step: 564/533, loss: 0.007030379958450794
2023-01-24 10:49:57.908785: step: 568/533, loss: 0.0006009471835568547
2023-01-24 10:49:59.001200: step: 572/533, loss: 0.007528329733759165
2023-01-24 10:50:00.087448: step: 576/533, loss: 4.1869108827086166e-05
2023-01-24 10:50:01.170717: step: 580/533, loss: 0.002129929605871439
2023-01-24 10:50:02.270983: step: 584/533, loss: 0.002345738233998418
2023-01-24 10:50:03.351090: step: 588/533, loss: 0.003923907410353422
2023-01-24 10:50:04.450360: step: 592/533, loss: 2.9581187845906243e-05
2023-01-24 10:50:05.549403: step: 596/533, loss: 0.0029439181089401245
2023-01-24 10:50:06.647635: step: 600/533, loss: 0.0022498061880469322
2023-01-24 10:50:07.740623: step: 604/533, loss: 0.0010034615406766534
2023-01-24 10:50:08.824529: step: 608/533, loss: 1.0550620572757907e-05
2023-01-24 10:50:09.915156: step: 612/533, loss: 0.0010239691473543644
2023-01-24 10:50:11.006274: step: 616/533, loss: 0.0005933732027187943
2023-01-24 10:50:12.098022: step: 620/533, loss: 0.0016130880685523152
2023-01-24 10:50:13.210175: step: 624/533, loss: 0.02947252057492733
2023-01-24 10:50:14.337169: step: 628/533, loss: 0.0004867848474532366
2023-01-24 10:50:15.435339: step: 632/533, loss: 0.005298789124935865
2023-01-24 10:50:16.547077: step: 636/533, loss: 0.0027617153245955706
2023-01-24 10:50:17.627622: step: 640/533, loss: 0.00047647804603911936
2023-01-24 10:50:18.707035: step: 644/533, loss: 0.0004277276457287371
2023-01-24 10:50:19.801422: step: 648/533, loss: 4.961851800544537e-07
2023-01-24 10:50:20.916930: step: 652/533, loss: 5.7546687457943335e-05
2023-01-24 10:50:22.026014: step: 656/533, loss: 0.0032567204907536507
2023-01-24 10:50:23.137394: step: 660/533, loss: 0.00972148310393095
2023-01-24 10:50:24.226138: step: 664/533, loss: 0.004412045702338219
2023-01-24 10:50:25.318620: step: 668/533, loss: 0.00021108902001287788
2023-01-24 10:50:26.415793: step: 672/533, loss: 0.0005678031593561172
2023-01-24 10:50:27.532999: step: 676/533, loss: 0.005597666371613741
2023-01-24 10:50:28.630379: step: 680/533, loss: 0.0004098345525562763
2023-01-24 10:50:29.719841: step: 684/533, loss: 0.002693260321393609
2023-01-24 10:50:30.829394: step: 688/533, loss: 1.7247059531655395e-06
2023-01-24 10:50:31.938497: step: 692/533, loss: 0.00027592063997872174
2023-01-24 10:50:33.022683: step: 696/533, loss: 2.4172972956648664e-08
2023-01-24 10:50:34.167786: step: 700/533, loss: 0.002742467215284705
2023-01-24 10:50:35.262879: step: 704/533, loss: 0.0005073018255643547
2023-01-24 10:50:36.366015: step: 708/533, loss: 0.0010964280227199197
2023-01-24 10:50:37.452537: step: 712/533, loss: 0.0005595646798610687
2023-01-24 10:50:38.542774: step: 716/533, loss: 0.00459898728877306
2023-01-24 10:50:39.646378: step: 720/533, loss: 0.00899939239025116
2023-01-24 10:50:40.733896: step: 724/533, loss: 0.00441969046369195
2023-01-24 10:50:41.826635: step: 728/533, loss: 0.004464415367692709
2023-01-24 10:50:42.919776: step: 732/533, loss: 0.00035249462234787643
2023-01-24 10:50:44.048267: step: 736/533, loss: 0.0011351987486705184
2023-01-24 10:50:45.166251: step: 740/533, loss: 0.0002315524616278708
2023-01-24 10:50:46.246393: step: 744/533, loss: 0.0012131952680647373
2023-01-24 10:50:47.335537: step: 748/533, loss: 0.001361105008982122
2023-01-24 10:50:48.424300: step: 752/533, loss: 0.00026753259589895606
2023-01-24 10:50:49.520843: step: 756/533, loss: 0.004599571228027344
2023-01-24 10:50:50.634995: step: 760/533, loss: 0.0031680359970778227
2023-01-24 10:50:51.732102: step: 764/533, loss: 0.001587109174579382
2023-01-24 10:50:52.816348: step: 768/533, loss: 0.012213991023600101
2023-01-24 10:50:53.915108: step: 772/533, loss: 0.0040910872630774975
2023-01-24 10:50:55.019167: step: 776/533, loss: 0.002911878051236272
2023-01-24 10:50:56.114055: step: 780/533, loss: 4.328940485720523e-05
2023-01-24 10:50:57.208524: step: 784/533, loss: 0.003189524170011282
2023-01-24 10:50:58.292101: step: 788/533, loss: 0.003933151718229055
2023-01-24 10:50:59.388432: step: 792/533, loss: 0.001032230444252491
2023-01-24 10:51:00.489513: step: 796/533, loss: 0.007065333891659975
2023-01-24 10:51:01.572581: step: 800/533, loss: 6.38542915112339e-05
2023-01-24 10:51:02.676091: step: 804/533, loss: 0.0007325523183681071
2023-01-24 10:51:03.784020: step: 808/533, loss: 0.001641602604649961
2023-01-24 10:51:04.892186: step: 812/533, loss: 0.0023623628076165915
2023-01-24 10:51:05.983846: step: 816/533, loss: 0.0007221190608106554
2023-01-24 10:51:07.086844: step: 820/533, loss: 0.001587066799402237
2023-01-24 10:51:08.169557: step: 824/533, loss: 0.000197272005607374
2023-01-24 10:51:09.254365: step: 828/533, loss: 0.0041940659284591675
2023-01-24 10:51:10.345978: step: 832/533, loss: 1.1467683407317963e-06
2023-01-24 10:51:11.449451: step: 836/533, loss: 0.0001621201663510874
2023-01-24 10:51:12.564188: step: 840/533, loss: 0.003171137999743223
2023-01-24 10:51:13.664311: step: 844/533, loss: 0.0005936245433986187
2023-01-24 10:51:14.771861: step: 848/533, loss: 0.0006542549817822874
2023-01-24 10:51:15.864368: step: 852/533, loss: 0.0021065331529825926
2023-01-24 10:51:16.966234: step: 856/533, loss: 0.009932667016983032
2023-01-24 10:51:18.061819: step: 860/533, loss: 0.0035304855555295944
2023-01-24 10:51:19.168686: step: 864/533, loss: 0.0012791685294359922
2023-01-24 10:51:20.295806: step: 868/533, loss: 0.012057403102517128
2023-01-24 10:51:21.372455: step: 872/533, loss: 0.04011140391230583
2023-01-24 10:51:22.451454: step: 876/533, loss: 0.0022768480703234673
2023-01-24 10:51:23.539558: step: 880/533, loss: 0.004990806337445974
2023-01-24 10:51:24.619016: step: 884/533, loss: 0.0006911258678883314
2023-01-24 10:51:25.697292: step: 888/533, loss: 0.007871109060943127
2023-01-24 10:51:26.782986: step: 892/533, loss: 0.0009174428414553404
2023-01-24 10:51:27.879431: step: 896/533, loss: 0.00461563840508461
2023-01-24 10:51:28.960132: step: 900/533, loss: 0.001600267249159515
2023-01-24 10:51:30.024111: step: 904/533, loss: 0.0009192511788569391
2023-01-24 10:51:31.117543: step: 908/533, loss: 0.0024864135775715113
2023-01-24 10:51:32.191259: step: 912/533, loss: 0.00032204954186454415
2023-01-24 10:51:33.294471: step: 916/533, loss: 0.0017368741100654006
2023-01-24 10:51:34.401425: step: 920/533, loss: 0.0017457371577620506
2023-01-24 10:51:35.501060: step: 924/533, loss: 0.005843042396008968
2023-01-24 10:51:36.617338: step: 928/533, loss: 0.0024925353936851025
2023-01-24 10:51:37.702388: step: 932/533, loss: 0.0010597469517961144
2023-01-24 10:51:38.804260: step: 936/533, loss: 0.00013138589565642178
2023-01-24 10:51:39.913598: step: 940/533, loss: 0.0002890757459681481
2023-01-24 10:51:40.984928: step: 944/533, loss: 0.0027274745516479015
2023-01-24 10:51:42.090296: step: 948/533, loss: 6.31653965683654e-05
2023-01-24 10:51:43.198614: step: 952/533, loss: 0.005652320571243763
2023-01-24 10:51:44.281780: step: 956/533, loss: 0.0036472135689109564
2023-01-24 10:51:45.385694: step: 960/533, loss: 0.0033288937993347645
2023-01-24 10:51:46.498759: step: 964/533, loss: 0.0010028932010754943
2023-01-24 10:51:47.583742: step: 968/533, loss: 0.018029915168881416
2023-01-24 10:51:48.677412: step: 972/533, loss: 0.00010169000597670674
2023-01-24 10:51:49.782521: step: 976/533, loss: 0.0011550599010661244
2023-01-24 10:51:50.901532: step: 980/533, loss: 0.00015045150939840823
2023-01-24 10:51:51.993739: step: 984/533, loss: 3.463180473772809e-05
2023-01-24 10:51:53.069629: step: 988/533, loss: 0.005396848078817129
2023-01-24 10:51:54.147214: step: 992/533, loss: 0.0033563473261892796
2023-01-24 10:51:55.251655: step: 996/533, loss: 0.0002540129062253982
2023-01-24 10:51:56.344086: step: 1000/533, loss: 0.0010461205383762717
2023-01-24 10:51:57.454512: step: 1004/533, loss: 0.0032819253392517567
2023-01-24 10:51:58.562571: step: 1008/533, loss: 0.007797548081725836
2023-01-24 10:51:59.663974: step: 1012/533, loss: 0.0011754160514101386
2023-01-24 10:52:00.748487: step: 1016/533, loss: 2.1594318241113797e-05
2023-01-24 10:52:01.849676: step: 1020/533, loss: 5.174911711947061e-05
2023-01-24 10:52:02.938722: step: 1024/533, loss: 1.6054269508458674e-05
2023-01-24 10:52:04.071122: step: 1028/533, loss: 0.003761495929211378
2023-01-24 10:52:05.151932: step: 1032/533, loss: 0.020900920033454895
2023-01-24 10:52:06.281626: step: 1036/533, loss: 0.005128931254148483
2023-01-24 10:52:07.403724: step: 1040/533, loss: 0.007899763062596321
2023-01-24 10:52:08.506068: step: 1044/533, loss: 0.007491723634302616
2023-01-24 10:52:09.579400: step: 1048/533, loss: 0.0010906659299507737
2023-01-24 10:52:10.702027: step: 1052/533, loss: 0.0003814274678006768
2023-01-24 10:52:11.786382: step: 1056/533, loss: 0.005165406968444586
2023-01-24 10:52:12.881575: step: 1060/533, loss: 0.004386221989989281
2023-01-24 10:52:13.968188: step: 1064/533, loss: 0.00038891626172699034
2023-01-24 10:52:15.059973: step: 1068/533, loss: 0.0023489822633564472
2023-01-24 10:52:16.168783: step: 1072/533, loss: 9.631858119973913e-06
2023-01-24 10:52:17.286149: step: 1076/533, loss: 0.0034737419337034225
2023-01-24 10:52:18.363059: step: 1080/533, loss: 0.0036069643683731556
2023-01-24 10:52:19.454415: step: 1084/533, loss: 0.0018586234655231237
2023-01-24 10:52:20.553145: step: 1088/533, loss: 2.141439836123027e-05
2023-01-24 10:52:21.667981: step: 1092/533, loss: 0.003410555189475417
2023-01-24 10:52:22.748157: step: 1096/533, loss: 4.231475031701848e-05
2023-01-24 10:52:23.869621: step: 1100/533, loss: 0.0028217125218361616
2023-01-24 10:52:24.954176: step: 1104/533, loss: 0.0002759444760158658
2023-01-24 10:52:26.055712: step: 1108/533, loss: 0.00478389160707593
2023-01-24 10:52:27.148982: step: 1112/533, loss: 0.002534197410568595
2023-01-24 10:52:28.235301: step: 1116/533, loss: 0.003971835598349571
2023-01-24 10:52:29.330988: step: 1120/533, loss: 0.0001030934217851609
2023-01-24 10:52:30.411386: step: 1124/533, loss: 0.000196712018805556
2023-01-24 10:52:31.494454: step: 1128/533, loss: 0.0008303156355395913
2023-01-24 10:52:32.575430: step: 1132/533, loss: 0.004952205810695887
2023-01-24 10:52:33.674009: step: 1136/533, loss: 0.0005496282828971744
2023-01-24 10:52:34.778423: step: 1140/533, loss: 0.006099950056523085
2023-01-24 10:52:35.879099: step: 1144/533, loss: 0.0030288659036159515
2023-01-24 10:52:36.959101: step: 1148/533, loss: 0.04400619864463806
2023-01-24 10:52:38.068692: step: 1152/533, loss: 0.0007646779413335025
2023-01-24 10:52:39.161533: step: 1156/533, loss: 0.0013779893051832914
2023-01-24 10:52:40.253016: step: 1160/533, loss: 0.000208981815376319
2023-01-24 10:52:41.358908: step: 1164/533, loss: 0.0008088971953839064
2023-01-24 10:52:42.471659: step: 1168/533, loss: 0.0004956267075613141
2023-01-24 10:52:43.547461: step: 1172/533, loss: 0.0026861457154154778
2023-01-24 10:52:44.641575: step: 1176/533, loss: 5.8311201428296044e-05
2023-01-24 10:52:45.743622: step: 1180/533, loss: 0.0005833582254126668
2023-01-24 10:52:46.814515: step: 1184/533, loss: 0.0004759877629112452
2023-01-24 10:52:47.892541: step: 1188/533, loss: 0.0026328396052122116
2023-01-24 10:52:48.991310: step: 1192/533, loss: 0.004736026749014854
2023-01-24 10:52:50.065671: step: 1196/533, loss: 0.0005450062453746796
2023-01-24 10:52:51.179588: step: 1200/533, loss: 0.008725064806640148
2023-01-24 10:52:52.270299: step: 1204/533, loss: 0.00011126544268336147
2023-01-24 10:52:53.343592: step: 1208/533, loss: 0.004628079943358898
2023-01-24 10:52:54.437668: step: 1212/533, loss: 0.0007206516456790268
2023-01-24 10:52:55.561128: step: 1216/533, loss: 0.0076291607692837715
2023-01-24 10:52:56.647678: step: 1220/533, loss: 0.0004630462790373713
2023-01-24 10:52:57.735549: step: 1224/533, loss: 0.0004548488650470972
2023-01-24 10:52:58.819958: step: 1228/533, loss: 0.0005756756290793419
2023-01-24 10:52:59.926455: step: 1232/533, loss: 0.002830867189913988
2023-01-24 10:53:01.029992: step: 1236/533, loss: 0.004472828470170498
2023-01-24 10:53:02.145154: step: 1240/533, loss: 0.002643321407958865
2023-01-24 10:53:03.247662: step: 1244/533, loss: 0.025015173479914665
2023-01-24 10:53:04.342533: step: 1248/533, loss: 3.300476964795962e-05
2023-01-24 10:53:05.443143: step: 1252/533, loss: 0.001250859466381371
2023-01-24 10:53:06.532073: step: 1256/533, loss: 5.5232383601833135e-05
2023-01-24 10:53:07.622265: step: 1260/533, loss: 0.007153133396059275
2023-01-24 10:53:08.714304: step: 1264/533, loss: 6.333937199087813e-05
2023-01-24 10:53:09.825629: step: 1268/533, loss: 0.003836860880255699
2023-01-24 10:53:10.918426: step: 1272/533, loss: 0.0022705935407429934
2023-01-24 10:53:11.991185: step: 1276/533, loss: 0.0008195606642402709
2023-01-24 10:53:13.083518: step: 1280/533, loss: 0.0005800870712846518
2023-01-24 10:53:14.174690: step: 1284/533, loss: 0.001996290171518922
2023-01-24 10:53:15.256904: step: 1288/533, loss: 0.000997242983430624
2023-01-24 10:53:16.371175: step: 1292/533, loss: 0.0012965997448191047
2023-01-24 10:53:17.445583: step: 1296/533, loss: 0.00012825689918827266
2023-01-24 10:53:18.557618: step: 1300/533, loss: 0.003438497195020318
2023-01-24 10:53:19.647045: step: 1304/533, loss: 0.00017847702838480473
2023-01-24 10:53:20.799712: step: 1308/533, loss: 9.299517842009664e-05
2023-01-24 10:53:21.875973: step: 1312/533, loss: 8.696688746567816e-05
2023-01-24 10:53:22.974548: step: 1316/533, loss: 0.011722828261554241
2023-01-24 10:53:24.078730: step: 1320/533, loss: 0.00097181141609326
2023-01-24 10:53:25.176261: step: 1324/533, loss: 1.90558403119212e-05
2023-01-24 10:53:26.300928: step: 1328/533, loss: 0.007603359408676624
2023-01-24 10:53:27.373166: step: 1332/533, loss: 2.0499857782851905e-05
2023-01-24 10:53:28.479453: step: 1336/533, loss: 3.999216278316453e-05
2023-01-24 10:53:29.604471: step: 1340/533, loss: 0.004352320916950703
2023-01-24 10:53:30.732606: step: 1344/533, loss: 0.0024543299805372953
2023-01-24 10:53:31.831275: step: 1348/533, loss: 0.003961043432354927
2023-01-24 10:53:32.949331: step: 1352/533, loss: 0.0018002977594733238
2023-01-24 10:53:34.042162: step: 1356/533, loss: 0.003702238667756319
2023-01-24 10:53:35.149136: step: 1360/533, loss: 0.005150108132511377
2023-01-24 10:53:36.252758: step: 1364/533, loss: 0.0070759630762040615
2023-01-24 10:53:37.372689: step: 1368/533, loss: 0.0027163720224052668
2023-01-24 10:53:38.469046: step: 1372/533, loss: 0.003405302297323942
2023-01-24 10:53:39.585218: step: 1376/533, loss: 0.0043831863440573215
2023-01-24 10:53:40.693468: step: 1380/533, loss: 0.006287361029535532
2023-01-24 10:53:41.798212: step: 1384/533, loss: 0.00473616411909461
2023-01-24 10:53:42.895306: step: 1388/533, loss: 0.001443610293790698
2023-01-24 10:53:43.989208: step: 1392/533, loss: 0.008686110377311707
2023-01-24 10:53:45.082040: step: 1396/533, loss: 2.3614778910996392e-05
2023-01-24 10:53:46.171218: step: 1400/533, loss: 0.0016586016863584518
2023-01-24 10:53:47.275889: step: 1404/533, loss: 0.0004601578984875232
2023-01-24 10:53:48.383142: step: 1408/533, loss: 0.011283429339528084
2023-01-24 10:53:49.492991: step: 1412/533, loss: 0.00015859873383305967
2023-01-24 10:53:50.590667: step: 1416/533, loss: 1.0244678378512617e-05
2023-01-24 10:53:51.689692: step: 1420/533, loss: 7.495797035517171e-05
2023-01-24 10:53:52.813538: step: 1424/533, loss: 0.04375913366675377
2023-01-24 10:53:53.909241: step: 1428/533, loss: 0.0015629951376467943
2023-01-24 10:53:55.002556: step: 1432/533, loss: 0.001613187720067799
2023-01-24 10:53:56.089022: step: 1436/533, loss: 0.012827831320464611
2023-01-24 10:53:57.198093: step: 1440/533, loss: 0.0007839933387003839
2023-01-24 10:53:58.302980: step: 1444/533, loss: 0.008048146963119507
2023-01-24 10:53:59.407454: step: 1448/533, loss: 0.0004323936009313911
2023-01-24 10:54:00.505530: step: 1452/533, loss: 7.696387910982594e-05
2023-01-24 10:54:01.613792: step: 1456/533, loss: 0.043119389563798904
2023-01-24 10:54:02.712356: step: 1460/533, loss: 0.001726892194710672
2023-01-24 10:54:03.832299: step: 1464/533, loss: 0.0013748126802965999
2023-01-24 10:54:04.937845: step: 1468/533, loss: 0.0017935099313035607
2023-01-24 10:54:06.078095: step: 1472/533, loss: 0.0008053779602050781
2023-01-24 10:54:07.173713: step: 1476/533, loss: 2.3890390366432257e-05
2023-01-24 10:54:08.264776: step: 1480/533, loss: 0.0002525101008359343
2023-01-24 10:54:09.354891: step: 1484/533, loss: 0.003070581704378128
2023-01-24 10:54:10.453643: step: 1488/533, loss: 0.0014215834671631455
2023-01-24 10:54:11.548421: step: 1492/533, loss: 0.0007127938442863524
2023-01-24 10:54:12.642789: step: 1496/533, loss: 0.00897926464676857
2023-01-24 10:54:13.749661: step: 1500/533, loss: 0.005227182526141405
2023-01-24 10:54:14.870081: step: 1504/533, loss: 0.00036330221337266266
2023-01-24 10:54:16.001660: step: 1508/533, loss: 0.0016407282091677189
2023-01-24 10:54:17.106275: step: 1512/533, loss: 0.006567827891558409
2023-01-24 10:54:18.229514: step: 1516/533, loss: 0.0010122137609869242
2023-01-24 10:54:19.318488: step: 1520/533, loss: 0.002790943719446659
2023-01-24 10:54:20.449069: step: 1524/533, loss: 0.0019421306205913424
2023-01-24 10:54:21.579434: step: 1528/533, loss: 0.002191857434809208
2023-01-24 10:54:22.686427: step: 1532/533, loss: 0.0058403038419783115
2023-01-24 10:54:23.761816: step: 1536/533, loss: 0.0012100166641175747
2023-01-24 10:54:24.875981: step: 1540/533, loss: 0.0019768911879509687
2023-01-24 10:54:25.995470: step: 1544/533, loss: 0.001768930465914309
2023-01-24 10:54:27.104868: step: 1548/533, loss: 6.682453386019915e-05
2023-01-24 10:54:28.188629: step: 1552/533, loss: 0.00013836866128258407
2023-01-24 10:54:29.265459: step: 1556/533, loss: 0.002378632314503193
2023-01-24 10:54:30.381611: step: 1560/533, loss: 0.050406623631715775
2023-01-24 10:54:31.493307: step: 1564/533, loss: 0.005390016827732325
2023-01-24 10:54:32.583561: step: 1568/533, loss: 0.0015913870884105563
2023-01-24 10:54:33.680471: step: 1572/533, loss: 0.003808403154835105
2023-01-24 10:54:34.793242: step: 1576/533, loss: 0.0010783681645989418
2023-01-24 10:54:35.873560: step: 1580/533, loss: 0.001029927865602076
2023-01-24 10:54:36.977813: step: 1584/533, loss: 0.00486422423273325
2023-01-24 10:54:38.065862: step: 1588/533, loss: 0.0001924679963849485
2023-01-24 10:54:39.176745: step: 1592/533, loss: 0.006622611079365015
2023-01-24 10:54:40.262568: step: 1596/533, loss: 0.004170107189565897
2023-01-24 10:54:41.374160: step: 1600/533, loss: 0.001412565354257822
2023-01-24 10:54:42.455499: step: 1604/533, loss: 0.0007441662019118667
2023-01-24 10:54:43.584467: step: 1608/533, loss: 0.002658234443515539
2023-01-24 10:54:44.677879: step: 1612/533, loss: 0.003151416778564453
2023-01-24 10:54:45.772864: step: 1616/533, loss: 0.0028475960716605186
2023-01-24 10:54:46.870610: step: 1620/533, loss: 0.004588868468999863
2023-01-24 10:54:47.973159: step: 1624/533, loss: 0.0018904457101598382
2023-01-24 10:54:49.061824: step: 1628/533, loss: 0.0012989871902391315
2023-01-24 10:54:50.196606: step: 1632/533, loss: 0.002785335760563612
2023-01-24 10:54:51.323025: step: 1636/533, loss: 0.0004646194283850491
2023-01-24 10:54:52.413702: step: 1640/533, loss: 0.005113999359309673
2023-01-24 10:54:53.522910: step: 1644/533, loss: 0.002171002561226487
2023-01-24 10:54:54.630079: step: 1648/533, loss: 0.0058752126060426235
2023-01-24 10:54:55.767587: step: 1652/533, loss: 0.008050262928009033
2023-01-24 10:54:56.882848: step: 1656/533, loss: 0.00022795688710175455
2023-01-24 10:54:57.965882: step: 1660/533, loss: 0.00047123702825047076
2023-01-24 10:54:59.076266: step: 1664/533, loss: 0.00011222408647881821
2023-01-24 10:55:00.157178: step: 1668/533, loss: 0.020215149968862534
2023-01-24 10:55:01.281478: step: 1672/533, loss: 0.013169074431061745
2023-01-24 10:55:02.366096: step: 1676/533, loss: 0.0018502718303352594
2023-01-24 10:55:03.473787: step: 1680/533, loss: 0.003890259424224496
2023-01-24 10:55:04.582304: step: 1684/533, loss: 0.0007880213088355958
2023-01-24 10:55:05.699674: step: 1688/533, loss: 0.010074465535581112
2023-01-24 10:55:06.819867: step: 1692/533, loss: 0.0012769254390150309
2023-01-24 10:55:07.907949: step: 1696/533, loss: 0.00012946815695613623
2023-01-24 10:55:09.013758: step: 1700/533, loss: 0.0030732653103768826
2023-01-24 10:55:10.115290: step: 1704/533, loss: 0.008508858270943165
2023-01-24 10:55:11.233531: step: 1708/533, loss: 0.0004671087663155049
2023-01-24 10:55:12.357886: step: 1712/533, loss: 8.763720870774705e-06
2023-01-24 10:55:13.442335: step: 1716/533, loss: 4.5352880988502875e-05
2023-01-24 10:55:14.529069: step: 1720/533, loss: 0.0035408767871558666
2023-01-24 10:55:15.640048: step: 1724/533, loss: 0.0009131893166340888
2023-01-24 10:55:16.749990: step: 1728/533, loss: 0.010847645811736584
2023-01-24 10:55:17.878233: step: 1732/533, loss: 0.008226634003221989
2023-01-24 10:55:18.955744: step: 1736/533, loss: 0.0012527883518487215
2023-01-24 10:55:20.041484: step: 1740/533, loss: 4.8085450544022024e-05
2023-01-24 10:55:21.162117: step: 1744/533, loss: 0.0009326632134616375
2023-01-24 10:55:22.247135: step: 1748/533, loss: 1.4391749573405832e-05
2023-01-24 10:55:23.353202: step: 1752/533, loss: 9.399873670190573e-05
2023-01-24 10:55:24.444701: step: 1756/533, loss: 0.003978671971708536
2023-01-24 10:55:25.533693: step: 1760/533, loss: 0.0017634208779782057
2023-01-24 10:55:26.669670: step: 1764/533, loss: 0.0012975907884538174
2023-01-24 10:55:27.758179: step: 1768/533, loss: 0.0017308234237134457
2023-01-24 10:55:28.871180: step: 1772/533, loss: 0.0007692330982536077
2023-01-24 10:55:29.980011: step: 1776/533, loss: 0.0008965295273810625
2023-01-24 10:55:31.073437: step: 1780/533, loss: 0.0007986239506863058
2023-01-24 10:55:32.174196: step: 1784/533, loss: 0.0006854113889858127
2023-01-24 10:55:33.263289: step: 1788/533, loss: 8.186270133592188e-05
2023-01-24 10:55:34.354139: step: 1792/533, loss: 0.0015493525424972177
2023-01-24 10:55:35.447022: step: 1796/533, loss: 0.0010045107919722795
2023-01-24 10:55:36.539892: step: 1800/533, loss: 3.8751401007175446e-05
2023-01-24 10:55:37.610652: step: 1804/533, loss: 0.0022434222046285868
2023-01-24 10:55:38.712772: step: 1808/533, loss: 0.001383899012580514
2023-01-24 10:55:39.796540: step: 1812/533, loss: 1.0308566743333358e-05
2023-01-24 10:55:40.904781: step: 1816/533, loss: 2.3818872705305694e-06
2023-01-24 10:55:41.995037: step: 1820/533, loss: 0.000916070188395679
2023-01-24 10:55:43.085602: step: 1824/533, loss: 0.00024853902868926525
2023-01-24 10:55:44.189727: step: 1828/533, loss: 0.00017823936650529504
2023-01-24 10:55:45.289847: step: 1832/533, loss: 4.967044878867455e-05
2023-01-24 10:55:46.368043: step: 1836/533, loss: 0.0017026015557348728
2023-01-24 10:55:47.493980: step: 1840/533, loss: 0.005879640579223633
2023-01-24 10:55:48.597329: step: 1844/533, loss: 0.010877669788897038
2023-01-24 10:55:49.694736: step: 1848/533, loss: 0.00182923988904804
2023-01-24 10:55:50.805639: step: 1852/533, loss: 0.006797377951443195
2023-01-24 10:55:51.893676: step: 1856/533, loss: 0.003226029686629772
2023-01-24 10:55:52.982457: step: 1860/533, loss: 0.0002482278214301914
2023-01-24 10:55:54.083799: step: 1864/533, loss: 0.0009223408997058868
2023-01-24 10:55:55.247571: step: 1868/533, loss: 0.008654667064547539
2023-01-24 10:55:56.319773: step: 1872/533, loss: 0.00031653931364417076
2023-01-24 10:55:57.381530: step: 1876/533, loss: 7.122893293853849e-06
2023-01-24 10:55:58.484557: step: 1880/533, loss: 0.00029793381690979004
2023-01-24 10:55:59.601414: step: 1884/533, loss: 0.004804526921361685
2023-01-24 10:56:00.683522: step: 1888/533, loss: 0.001668571843765676
2023-01-24 10:56:01.785001: step: 1892/533, loss: 0.006242298521101475
2023-01-24 10:56:02.909651: step: 1896/533, loss: 2.578546991571784e-05
2023-01-24 10:56:04.025032: step: 1900/533, loss: 0.08139161020517349
2023-01-24 10:56:05.111557: step: 1904/533, loss: 3.7393834645627066e-05
2023-01-24 10:56:06.189827: step: 1908/533, loss: 0.02611294761300087
2023-01-24 10:56:07.282903: step: 1912/533, loss: 0.00029313730192370713
2023-01-24 10:56:08.384666: step: 1916/533, loss: 6.064640547265299e-05
2023-01-24 10:56:09.504464: step: 1920/533, loss: 0.0023711074609309435
2023-01-24 10:56:10.602022: step: 1924/533, loss: 0.0008752704015932977
2023-01-24 10:56:11.694546: step: 1928/533, loss: 0.00015882252773735672
2023-01-24 10:56:12.784873: step: 1932/533, loss: 0.002547198673710227
2023-01-24 10:56:13.877778: step: 1936/533, loss: 0.0001221850689034909
2023-01-24 10:56:14.961710: step: 1940/533, loss: 0.004997347015887499
2023-01-24 10:56:16.050480: step: 1944/533, loss: 0.0016544545069336891
2023-01-24 10:56:17.150786: step: 1948/533, loss: 0.001664850628003478
2023-01-24 10:56:18.250909: step: 1952/533, loss: 0.0008806188125163317
2023-01-24 10:56:19.399809: step: 1956/533, loss: 0.0012162365019321442
2023-01-24 10:56:20.510927: step: 1960/533, loss: 0.017666444182395935
2023-01-24 10:56:21.616654: step: 1964/533, loss: 0.0008225405472330749
2023-01-24 10:56:22.725807: step: 1968/533, loss: 0.01176410261541605
2023-01-24 10:56:23.811977: step: 1972/533, loss: 9.950343127229644e-08
2023-01-24 10:56:24.903063: step: 1976/533, loss: 0.0023595797829329967
2023-01-24 10:56:25.995384: step: 1980/533, loss: 0.0009438741253688931
2023-01-24 10:56:27.089420: step: 1984/533, loss: 0.0004937687190249562
2023-01-24 10:56:28.180050: step: 1988/533, loss: 0.0030970671214163303
2023-01-24 10:56:29.303284: step: 1992/533, loss: 0.003202456748113036
2023-01-24 10:56:30.436094: step: 1996/533, loss: 0.011219280771911144
2023-01-24 10:56:31.532575: step: 2000/533, loss: 0.00263996166177094
2023-01-24 10:56:32.635043: step: 2004/533, loss: 0.0012446005130186677
2023-01-24 10:56:33.715611: step: 2008/533, loss: 0.00224428903311491
2023-01-24 10:56:34.814911: step: 2012/533, loss: 0.004114397335797548
2023-01-24 10:56:35.885312: step: 2016/533, loss: 8.818650530884042e-05
2023-01-24 10:56:36.997880: step: 2020/533, loss: 0.0018202557694166899
2023-01-24 10:56:38.108516: step: 2024/533, loss: 1.923138916026801e-05
2023-01-24 10:56:39.183311: step: 2028/533, loss: 0.0013667086604982615
2023-01-24 10:56:40.281713: step: 2032/533, loss: 0.00043558748438954353
2023-01-24 10:56:41.360350: step: 2036/533, loss: 8.64706962602213e-05
2023-01-24 10:56:42.455389: step: 2040/533, loss: 0.00039210394606925547
2023-01-24 10:56:43.556042: step: 2044/533, loss: 0.010561991482973099
2023-01-24 10:56:44.652194: step: 2048/533, loss: 2.062778548861388e-05
2023-01-24 10:56:45.764771: step: 2052/533, loss: 8.36115887636879e-08
2023-01-24 10:56:46.845375: step: 2056/533, loss: 0.00262275873683393
2023-01-24 10:56:47.937289: step: 2060/533, loss: 0.010614222846925259
2023-01-24 10:56:49.027230: step: 2064/533, loss: 3.211184207430051e-07
2023-01-24 10:56:50.121112: step: 2068/533, loss: 0.0002933823561761528
2023-01-24 10:56:51.222309: step: 2072/533, loss: 0.002105648862197995
2023-01-24 10:56:52.330081: step: 2076/533, loss: 0.005264936480671167
2023-01-24 10:56:53.440336: step: 2080/533, loss: 0.005022134631872177
2023-01-24 10:56:54.554591: step: 2084/533, loss: 0.0010705323657020926
2023-01-24 10:56:55.643413: step: 2088/533, loss: 0.0008448737789876759
2023-01-24 10:56:56.725455: step: 2092/533, loss: 4.9371836212230846e-05
2023-01-24 10:56:57.838593: step: 2096/533, loss: 0.005214858800172806
2023-01-24 10:56:58.930410: step: 2100/533, loss: 3.888430728693493e-05
2023-01-24 10:57:00.013364: step: 2104/533, loss: 0.0011194488033652306
2023-01-24 10:57:01.103045: step: 2108/533, loss: 0.005270752124488354
2023-01-24 10:57:02.165404: step: 2112/533, loss: 0.0012955316342413425
2023-01-24 10:57:03.253987: step: 2116/533, loss: 0.0011213688412681222
2023-01-24 10:57:04.339547: step: 2120/533, loss: 0.0051189144141972065
2023-01-24 10:57:05.429879: step: 2124/533, loss: 0.0066608102060854435
2023-01-24 10:57:06.508884: step: 2128/533, loss: 1.573308873048518e-05
2023-01-24 10:57:07.628696: step: 2132/533, loss: 0.009856920689344406
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38055249632892807, 'r': 0.3278383934218849, 'f1': 0.3522341148487938}, 'combined': 0.2595409267306902, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39437259419698645, 'r': 0.3568313568647733, 'f1': 0.37466391836382057}, 'combined': 0.24977594557588031, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36064273810984343, 'r': 0.32026717539925376, 'f1': 0.3392578923324758}, 'combined': 0.24997949961340318, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.3904719092232294, 'r': 0.3086229897898986, 'f1': 0.34475607882008}, 'combined': 0.22983738588005329, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3441316674975075, 'r': 0.3082165978345798, 'f1': 0.3251854795972443}, 'combined': 0.23961035338744316, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38208344378085474, 'r': 0.34240554769591985, 'f1': 0.36115798134255234}, 'combined': 0.2407719875617015, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35048248859292147, 'r': 0.31722988056702756, 'f1': 0.33302818139207874}, 'combined': 0.2453891862889001, 'stategy': 1, 'epoch': 16}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38299654503075575, 'r': 0.34432862461899677, 'f1': 0.3626347033962093}, 'combined': 0.24175646893080613, 'stategy': 1, 'epoch': 16}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 16}
******************************
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 10:59:26.302370: step: 4/533, loss: 0.0009410997154191136
2023-01-24 10:59:27.385152: step: 8/533, loss: 0.004544538911432028
2023-01-24 10:59:28.468060: step: 12/533, loss: 0.00014766598178539425
2023-01-24 10:59:29.561835: step: 16/533, loss: 0.0032116647344082594
2023-01-24 10:59:30.641481: step: 20/533, loss: 0.0007585564162582159
2023-01-24 10:59:31.742054: step: 24/533, loss: 0.0018707580165937543
2023-01-24 10:59:32.837695: step: 28/533, loss: 0.00477310037240386
2023-01-24 10:59:33.925873: step: 32/533, loss: 0.0004972910974174738
2023-01-24 10:59:35.039546: step: 36/533, loss: 0.0025345359463244677
2023-01-24 10:59:36.138868: step: 40/533, loss: 0.0006242909003049135
2023-01-24 10:59:37.199098: step: 44/533, loss: 0.0026144462171941996
2023-01-24 10:59:38.289279: step: 48/533, loss: 0.018481917679309845
2023-01-24 10:59:39.397913: step: 52/533, loss: 0.008312263526022434
2023-01-24 10:59:40.488522: step: 56/533, loss: 0.0030477873515337706
2023-01-24 10:59:41.580830: step: 60/533, loss: 0.0005004052654840052
2023-01-24 10:59:42.666345: step: 64/533, loss: 0.0010010869009420276
2023-01-24 10:59:43.761331: step: 68/533, loss: 3.291551911388524e-05
2023-01-24 10:59:44.840431: step: 72/533, loss: 0.0006430524517782032
2023-01-24 10:59:45.924604: step: 76/533, loss: 0.0001362840848742053
2023-01-24 10:59:47.011198: step: 80/533, loss: 0.011455376632511616
2023-01-24 10:59:48.088261: step: 84/533, loss: 0.002231361111626029
2023-01-24 10:59:49.168732: step: 88/533, loss: 8.15136227174662e-05
2023-01-24 10:59:50.268888: step: 92/533, loss: 0.005096331238746643
2023-01-24 10:59:51.337184: step: 96/533, loss: 0.003994058817625046
2023-01-24 10:59:52.426900: step: 100/533, loss: 0.005634046159684658
2023-01-24 10:59:53.508429: step: 104/533, loss: 0.00023996341042220592
2023-01-24 10:59:54.617746: step: 108/533, loss: 3.0274832170107402e-05
2023-01-24 10:59:55.702557: step: 112/533, loss: 0.0008117935503832996
2023-01-24 10:59:56.827727: step: 116/533, loss: 0.014688802883028984
2023-01-24 10:59:57.921274: step: 120/533, loss: 0.0013207090087234974
2023-01-24 10:59:58.992118: step: 124/533, loss: 7.648661267012358e-06
2023-01-24 11:00:00.113548: step: 128/533, loss: 0.00235088262706995
2023-01-24 11:00:01.200397: step: 132/533, loss: 3.178406359438668e-06
2023-01-24 11:00:02.295836: step: 136/533, loss: 0.00012720597442239523
2023-01-24 11:00:03.392106: step: 140/533, loss: 0.005689735524356365
2023-01-24 11:00:04.482024: step: 144/533, loss: 8.553644875064492e-05
2023-01-24 11:00:05.569601: step: 148/533, loss: 0.00014960342377889901
2023-01-24 11:00:06.662110: step: 152/533, loss: 0.00296128005720675
2023-01-24 11:00:07.768864: step: 156/533, loss: 0.0002694720169529319
2023-01-24 11:00:08.847009: step: 160/533, loss: 0.003163629909977317
2023-01-24 11:00:09.929168: step: 164/533, loss: 8.168125350493938e-05
2023-01-24 11:00:11.050842: step: 168/533, loss: 0.0001671270001679659
2023-01-24 11:00:12.126206: step: 172/533, loss: 0.00022432493278756738
2023-01-24 11:00:13.211369: step: 176/533, loss: 0.00034793821396306157
2023-01-24 11:00:14.300590: step: 180/533, loss: 0.0008499118266627192
2023-01-24 11:00:15.395587: step: 184/533, loss: 0.0011228359071537852
2023-01-24 11:00:16.499223: step: 188/533, loss: 0.0028448740486055613
2023-01-24 11:00:17.603634: step: 192/533, loss: 0.0015078689903020859
2023-01-24 11:00:18.709083: step: 196/533, loss: 2.002663677558303e-05
2023-01-24 11:00:19.824972: step: 200/533, loss: 0.0007816139841452241
2023-01-24 11:00:20.964463: step: 204/533, loss: 0.0038217687979340553
2023-01-24 11:00:22.065296: step: 208/533, loss: 0.00010062997898785397
2023-01-24 11:00:23.174596: step: 212/533, loss: 0.0006479599978774786
2023-01-24 11:00:24.279286: step: 216/533, loss: 0.0025840559974312782
2023-01-24 11:00:25.356130: step: 220/533, loss: 0.0020715463906526566
2023-01-24 11:00:26.444281: step: 224/533, loss: 0.008057761006057262
2023-01-24 11:00:27.556724: step: 228/533, loss: 0.003530653892084956
2023-01-24 11:00:28.655437: step: 232/533, loss: 0.003127600299194455
2023-01-24 11:00:29.747493: step: 236/533, loss: 6.221603689482436e-05
2023-01-24 11:00:30.823657: step: 240/533, loss: 0.0011535790981724858
2023-01-24 11:00:31.931509: step: 244/533, loss: 0.004111037589609623
2023-01-24 11:00:33.021730: step: 248/533, loss: 4.778734364663251e-05
2023-01-24 11:00:34.119110: step: 252/533, loss: 0.0012513729743659496
2023-01-24 11:00:35.214974: step: 256/533, loss: 3.756900696316734e-05
2023-01-24 11:00:36.306582: step: 260/533, loss: 0.0005659213638864458
2023-01-24 11:00:37.424651: step: 264/533, loss: 0.00012557154695969075
2023-01-24 11:00:38.553105: step: 268/533, loss: 0.004475293215364218
2023-01-24 11:00:39.642227: step: 272/533, loss: 0.01278272457420826
2023-01-24 11:00:40.740040: step: 276/533, loss: 0.002034920733422041
2023-01-24 11:00:41.830525: step: 280/533, loss: 0.02859220653772354
2023-01-24 11:00:42.925396: step: 284/533, loss: 0.0007397309527732432
2023-01-24 11:00:44.012540: step: 288/533, loss: 0.0004514993343036622
2023-01-24 11:00:45.114031: step: 292/533, loss: 0.008027608506381512
2023-01-24 11:00:46.207578: step: 296/533, loss: 0.0006040503503754735
2023-01-24 11:00:47.310173: step: 300/533, loss: 0.0074706366285681725
2023-01-24 11:00:48.419782: step: 304/533, loss: 4.985829582437873e-05
2023-01-24 11:00:49.516341: step: 308/533, loss: 0.00015615238226018846
2023-01-24 11:00:50.626372: step: 312/533, loss: 0.001273818896152079
2023-01-24 11:00:51.704617: step: 316/533, loss: 0.0004028705006930977
2023-01-24 11:00:52.792588: step: 320/533, loss: 1.0262932846671902e-05
2023-01-24 11:00:53.877733: step: 324/533, loss: 0.0012719040969386697
2023-01-24 11:00:54.967499: step: 328/533, loss: 2.4759396183071658e-05
2023-01-24 11:00:56.073558: step: 332/533, loss: 0.008302816189825535
2023-01-24 11:00:57.165511: step: 336/533, loss: 7.615966296725674e-06
2023-01-24 11:00:58.268215: step: 340/533, loss: 0.0003245500847697258
2023-01-24 11:00:59.392739: step: 344/533, loss: 0.0021601023618131876
2023-01-24 11:01:00.510012: step: 348/533, loss: 0.0007495186291635036
2023-01-24 11:01:01.625928: step: 352/533, loss: 0.00011829469440272078
2023-01-24 11:01:02.723606: step: 356/533, loss: 0.033508606255054474
2023-01-24 11:01:03.801846: step: 360/533, loss: 0.0033848241437226534
2023-01-24 11:01:04.918716: step: 364/533, loss: 0.007248087786138058
2023-01-24 11:01:06.010263: step: 368/533, loss: 0.00013414357090368867
2023-01-24 11:01:07.120698: step: 372/533, loss: 0.0005971805658191442
2023-01-24 11:01:08.218257: step: 376/533, loss: 0.000559271895326674
2023-01-24 11:01:09.314558: step: 380/533, loss: 0.0008905145805329084
2023-01-24 11:01:10.393270: step: 384/533, loss: 0.0020530810579657555
2023-01-24 11:01:11.509141: step: 388/533, loss: 0.0013265254674479365
2023-01-24 11:01:12.593124: step: 392/533, loss: 0.00403763959184289
2023-01-24 11:01:13.682205: step: 396/533, loss: 0.004882507491856813
2023-01-24 11:01:14.775590: step: 400/533, loss: 0.0019314475357532501
2023-01-24 11:01:15.860254: step: 404/533, loss: 0.0018873877124860883
2023-01-24 11:01:16.959054: step: 408/533, loss: 0.002649756846949458
2023-01-24 11:01:18.050417: step: 412/533, loss: 0.0012787866871804
2023-01-24 11:01:19.157527: step: 416/533, loss: 9.592829155735672e-05
2023-01-24 11:01:20.269337: step: 420/533, loss: 0.005875616334378719
2023-01-24 11:01:21.365676: step: 424/533, loss: 0.0015758858062326908
2023-01-24 11:01:22.455108: step: 428/533, loss: 0.0011062219273298979
2023-01-24 11:01:23.555828: step: 432/533, loss: 0.0011775217717513442
2023-01-24 11:01:24.650811: step: 436/533, loss: 0.0010463586077094078
2023-01-24 11:01:25.726142: step: 440/533, loss: 0.0003136684244964272
2023-01-24 11:01:26.818846: step: 444/533, loss: 0.0030972128733992577
2023-01-24 11:01:27.914465: step: 448/533, loss: 0.0008704753709025681
2023-01-24 11:01:29.012670: step: 452/533, loss: 0.0012429322814568877
2023-01-24 11:01:30.099018: step: 456/533, loss: 0.00013093469897285104
2023-01-24 11:01:31.216631: step: 460/533, loss: 0.0006693479954265058
2023-01-24 11:01:32.337078: step: 464/533, loss: 0.00021879600535612553
2023-01-24 11:01:33.463273: step: 468/533, loss: 0.006657117512077093
2023-01-24 11:01:34.561376: step: 472/533, loss: 0.0027828379534184933
2023-01-24 11:01:35.656200: step: 476/533, loss: 0.002961687743663788
2023-01-24 11:01:36.756629: step: 480/533, loss: 0.0006207011174410582
2023-01-24 11:01:37.830328: step: 484/533, loss: 0.0010571738239377737
2023-01-24 11:01:38.922380: step: 488/533, loss: 0.0128471152856946
2023-01-24 11:01:40.029206: step: 492/533, loss: 0.0006803200813010335
2023-01-24 11:01:41.141813: step: 496/533, loss: 0.006354971788823605
2023-01-24 11:01:42.261179: step: 500/533, loss: 0.0009280457743443549
2023-01-24 11:01:43.368275: step: 504/533, loss: 0.0010501743527129292
2023-01-24 11:01:44.451499: step: 508/533, loss: 0.0008813183521851897
2023-01-24 11:01:45.561492: step: 512/533, loss: 2.2383943587556132e-07
2023-01-24 11:01:46.640603: step: 516/533, loss: 0.00012182912905700505
2023-01-24 11:01:47.749474: step: 520/533, loss: 0.008588865399360657
2023-01-24 11:01:48.860043: step: 524/533, loss: 0.0031527497339993715
2023-01-24 11:01:50.011443: step: 528/533, loss: 0.0008142708684317768
2023-01-24 11:01:51.135676: step: 532/533, loss: 0.00018249577260576189
2023-01-24 11:01:52.215944: step: 536/533, loss: 2.9758633900200948e-05
2023-01-24 11:01:53.321926: step: 540/533, loss: 2.3460373995476402e-05
2023-01-24 11:01:54.449892: step: 544/533, loss: 0.00025031346012838185
2023-01-24 11:01:55.551682: step: 548/533, loss: 0.0006601669010706246
2023-01-24 11:01:56.634233: step: 552/533, loss: 0.004290645942091942
2023-01-24 11:01:57.757207: step: 556/533, loss: 0.004969021305441856
2023-01-24 11:01:58.841153: step: 560/533, loss: 0.0
2023-01-24 11:01:59.930804: step: 564/533, loss: 3.285400816821493e-05
2023-01-24 11:02:01.050818: step: 568/533, loss: 0.00014929662575013936
2023-01-24 11:02:02.138746: step: 572/533, loss: 0.004276810213923454
2023-01-24 11:02:03.247681: step: 576/533, loss: 4.902975888398942e-06
2023-01-24 11:02:04.341984: step: 580/533, loss: 9.88425836112583e-06
2023-01-24 11:02:05.449190: step: 584/533, loss: 0.014389281161129475
2023-01-24 11:02:06.529990: step: 588/533, loss: 0.002177980961278081
2023-01-24 11:02:07.638235: step: 592/533, loss: 0.002431486966088414
2023-01-24 11:02:08.726265: step: 596/533, loss: 0.006396268494427204
2023-01-24 11:02:09.824357: step: 600/533, loss: 0.0009460755391046405
2023-01-24 11:02:10.906513: step: 604/533, loss: 0.00437344191595912
2023-01-24 11:02:12.014108: step: 608/533, loss: 0.00015456235269084573
2023-01-24 11:02:13.114104: step: 612/533, loss: 0.0005404619150795043
2023-01-24 11:02:14.215423: step: 616/533, loss: 0.0002562321606092155
2023-01-24 11:02:15.335391: step: 620/533, loss: 0.00023938783851917833
2023-01-24 11:02:16.418852: step: 624/533, loss: 0.003401353256776929
2023-01-24 11:02:17.547412: step: 628/533, loss: 0.0008854721090756357
2023-01-24 11:02:18.636862: step: 632/533, loss: 0.00017004599794745445
2023-01-24 11:02:19.729106: step: 636/533, loss: 0.004521358758211136
2023-01-24 11:02:20.842789: step: 640/533, loss: 0.0011133769294247031
2023-01-24 11:02:21.922845: step: 644/533, loss: 0.0002037424419540912
2023-01-24 11:02:23.030947: step: 648/533, loss: 0.00016876845620572567
2023-01-24 11:02:24.146448: step: 652/533, loss: 0.006316011305898428
2023-01-24 11:02:25.245720: step: 656/533, loss: 0.004135015420615673
2023-01-24 11:02:26.366962: step: 660/533, loss: 0.003328001359477639
2023-01-24 11:02:27.454127: step: 664/533, loss: 9.925581252900884e-05
2023-01-24 11:02:28.584332: step: 668/533, loss: 0.0017004447290673852
2023-01-24 11:02:29.699990: step: 672/533, loss: 0.00192838569637388
2023-01-24 11:02:30.797125: step: 676/533, loss: 0.00013095399481244385
2023-01-24 11:02:31.913965: step: 680/533, loss: 0.006728821899741888
2023-01-24 11:02:33.010155: step: 684/533, loss: 0.0002471611660439521
2023-01-24 11:02:34.082353: step: 688/533, loss: 0.0008719475590623915
2023-01-24 11:02:35.167780: step: 692/533, loss: 0.0002958431432489306
2023-01-24 11:02:36.262326: step: 696/533, loss: 0.00048827784485183656
2023-01-24 11:02:37.354235: step: 700/533, loss: 0.00010954685421893373
2023-01-24 11:02:38.472270: step: 704/533, loss: 0.0018404489383101463
2023-01-24 11:02:39.591727: step: 708/533, loss: 0.00620208540931344
2023-01-24 11:02:40.701334: step: 712/533, loss: 0.003818746656179428
2023-01-24 11:02:41.783925: step: 716/533, loss: 7.970898877829313e-06
2023-01-24 11:02:42.890845: step: 720/533, loss: 0.005827288143336773
2023-01-24 11:02:43.986298: step: 724/533, loss: 0.005920866504311562
2023-01-24 11:02:45.105716: step: 728/533, loss: 0.002132477005943656
2023-01-24 11:02:46.232193: step: 732/533, loss: 4.9393791414331645e-05
2023-01-24 11:02:47.323655: step: 736/533, loss: 0.005247549153864384
2023-01-24 11:02:48.421608: step: 740/533, loss: 0.00017103868594858795
2023-01-24 11:02:49.543725: step: 744/533, loss: 0.001853362307883799
2023-01-24 11:02:50.656117: step: 748/533, loss: 0.0003467810165602714
2023-01-24 11:02:51.756661: step: 752/533, loss: 0.01039961725473404
2023-01-24 11:02:52.866188: step: 756/533, loss: 0.004007407929748297
2023-01-24 11:02:53.943859: step: 760/533, loss: 0.0033764869440346956
2023-01-24 11:02:55.052543: step: 764/533, loss: 0.007050534710288048
2023-01-24 11:02:56.164728: step: 768/533, loss: 0.0016474276781082153
2023-01-24 11:02:57.296597: step: 772/533, loss: 0.0008581114234402776
2023-01-24 11:02:58.400669: step: 776/533, loss: 0.001249748282134533
2023-01-24 11:02:59.511759: step: 780/533, loss: 0.0019852209370583296
2023-01-24 11:03:00.614127: step: 784/533, loss: 0.0012333453632891178
2023-01-24 11:03:01.721375: step: 788/533, loss: 0.0005126133328303695
2023-01-24 11:03:02.823114: step: 792/533, loss: 0.004307086113840342
2023-01-24 11:03:03.914845: step: 796/533, loss: 0.000629466783721
2023-01-24 11:03:05.016184: step: 800/533, loss: 0.0028676805086433887
2023-01-24 11:03:06.098827: step: 804/533, loss: 0.0038517401553690434
2023-01-24 11:03:07.190103: step: 808/533, loss: 0.0034845122136175632
2023-01-24 11:03:08.313526: step: 812/533, loss: 0.0003340121766086668
2023-01-24 11:03:09.420961: step: 816/533, loss: 3.618074697442353e-05
2023-01-24 11:03:10.515116: step: 820/533, loss: 0.0
2023-01-24 11:03:11.614671: step: 824/533, loss: 1.691860416030977e-05
2023-01-24 11:03:12.704886: step: 828/533, loss: 3.1914965802570805e-05
2023-01-24 11:03:13.794540: step: 832/533, loss: 0.00186781189404428
2023-01-24 11:03:14.882084: step: 836/533, loss: 2.2351738238057806e-09
2023-01-24 11:03:15.970126: step: 840/533, loss: 0.002450590254738927
2023-01-24 11:03:17.064232: step: 844/533, loss: 0.002585506532341242
2023-01-24 11:03:18.171075: step: 848/533, loss: 0.006543491501361132
2023-01-24 11:03:19.247789: step: 852/533, loss: 0.0026102301198989153
2023-01-24 11:03:20.354702: step: 856/533, loss: 0.04224894195795059
2023-01-24 11:03:21.461411: step: 860/533, loss: 0.0001547687134006992
2023-01-24 11:03:22.558171: step: 864/533, loss: 0.0029676384292542934
2023-01-24 11:03:23.642545: step: 868/533, loss: 4.7041270590852946e-05
2023-01-24 11:03:24.739959: step: 872/533, loss: 0.00987533200532198
2023-01-24 11:03:25.822620: step: 876/533, loss: 0.00026769126998260617
2023-01-24 11:03:26.920861: step: 880/533, loss: 0.0066827088594436646
2023-01-24 11:03:28.043488: step: 884/533, loss: 0.006484674289822578
2023-01-24 11:03:29.160377: step: 888/533, loss: 0.0024081282317638397
2023-01-24 11:03:30.245858: step: 892/533, loss: 3.737882025234285e-06
2023-01-24 11:03:31.348082: step: 896/533, loss: 0.023483604192733765
2023-01-24 11:03:32.453522: step: 900/533, loss: 7.834248390281573e-05
2023-01-24 11:03:33.535235: step: 904/533, loss: 3.6972998884721164e-08
2023-01-24 11:03:34.650336: step: 908/533, loss: 0.0011235163547098637
2023-01-24 11:03:35.756194: step: 912/533, loss: 0.006713624577969313
2023-01-24 11:03:36.845538: step: 916/533, loss: 4.0923005144577473e-05
2023-01-24 11:03:37.942289: step: 920/533, loss: 0.005303933285176754
2023-01-24 11:03:39.033766: step: 924/533, loss: 0.0007445853552781045
2023-01-24 11:03:40.149039: step: 928/533, loss: 0.0001638050889596343
2023-01-24 11:03:41.246824: step: 932/533, loss: 6.871539517305791e-05
2023-01-24 11:03:42.350926: step: 936/533, loss: 2.3939759557833895e-05
2023-01-24 11:03:43.434022: step: 940/533, loss: 0.002262422349303961
2023-01-24 11:03:44.535642: step: 944/533, loss: 9.918155228660908e-06
2023-01-24 11:03:45.638105: step: 948/533, loss: 0.0009859208948910236
2023-01-24 11:03:46.739647: step: 952/533, loss: 0.0011032314505428076
2023-01-24 11:03:47.825130: step: 956/533, loss: 0.00390942208468914
2023-01-24 11:03:48.947109: step: 960/533, loss: 0.003303768578916788
2023-01-24 11:03:50.043074: step: 964/533, loss: 0.0003487922949716449
2023-01-24 11:03:51.156607: step: 968/533, loss: 0.001552112866193056
2023-01-24 11:03:52.264380: step: 972/533, loss: 0.004904949571937323
2023-01-24 11:03:53.347108: step: 976/533, loss: 0.0007106948178261518
2023-01-24 11:03:54.460486: step: 980/533, loss: 4.2599316657288e-05
2023-01-24 11:03:55.583664: step: 984/533, loss: 0.00020213874813634902
2023-01-24 11:03:56.690500: step: 988/533, loss: 9.471744306210894e-06
2023-01-24 11:03:57.789890: step: 992/533, loss: 0.0019799175206571817
2023-01-24 11:03:58.877891: step: 996/533, loss: 0.00039909881888888776
2023-01-24 11:03:59.978413: step: 1000/533, loss: 8.929453906603158e-05
2023-01-24 11:04:01.063892: step: 1004/533, loss: 0.0011780296918004751
2023-01-24 11:04:02.148346: step: 1008/533, loss: 0.00014696019934490323
2023-01-24 11:04:03.262608: step: 1012/533, loss: 0.0007049570558592677
2023-01-24 11:04:04.368882: step: 1016/533, loss: 0.00411481037735939
2023-01-24 11:04:05.452186: step: 1020/533, loss: 0.005990826524794102
2023-01-24 11:04:06.569408: step: 1024/533, loss: 0.01649569161236286
2023-01-24 11:04:07.660986: step: 1028/533, loss: 0.0027267285622656345
2023-01-24 11:04:08.757226: step: 1032/533, loss: 0.00034516272717155516
2023-01-24 11:04:09.865943: step: 1036/533, loss: 0.0005622964818030596
2023-01-24 11:04:10.955489: step: 1040/533, loss: 0.0007611809996888041
2023-01-24 11:04:12.067539: step: 1044/533, loss: 0.0033290560822933912
2023-01-24 11:04:13.152348: step: 1048/533, loss: 0.010709947906434536
2023-01-24 11:04:14.232607: step: 1052/533, loss: 2.005822716455441e-05
2023-01-24 11:04:15.308692: step: 1056/533, loss: 0.0019236274529248476
2023-01-24 11:04:16.401673: step: 1060/533, loss: 2.1614694560412318e-05
2023-01-24 11:04:17.493974: step: 1064/533, loss: 3.375996675458737e-05
2023-01-24 11:04:18.613654: step: 1068/533, loss: 1.6838119336171076e-05
2023-01-24 11:04:19.696972: step: 1072/533, loss: 0.001674283412285149
2023-01-24 11:04:20.819826: step: 1076/533, loss: 0.001022015349008143
2023-01-24 11:04:21.904469: step: 1080/533, loss: 0.0018856620881706476
2023-01-24 11:04:23.012286: step: 1084/533, loss: 6.316120561677963e-05
2023-01-24 11:04:24.113459: step: 1088/533, loss: 0.00014221749734133482
2023-01-24 11:04:25.222534: step: 1092/533, loss: 0.0003054407425224781
2023-01-24 11:04:26.338631: step: 1096/533, loss: 0.005386364180594683
2023-01-24 11:04:27.451278: step: 1100/533, loss: 0.0015728367725387216
2023-01-24 11:04:28.540155: step: 1104/533, loss: 0.001880164723843336
2023-01-24 11:04:29.633661: step: 1108/533, loss: 0.0028171283192932606
2023-01-24 11:04:30.732238: step: 1112/533, loss: 0.009833925403654575
2023-01-24 11:04:31.830809: step: 1116/533, loss: 4.441916098585352e-05
2023-01-24 11:04:32.938827: step: 1120/533, loss: 0.0036951119545847178
2023-01-24 11:04:34.032899: step: 1124/533, loss: 0.004377064295113087
2023-01-24 11:04:35.145583: step: 1128/533, loss: 0.0030492397490888834
2023-01-24 11:04:36.260076: step: 1132/533, loss: 0.001302488730289042
2023-01-24 11:04:37.360192: step: 1136/533, loss: 0.0002320230269106105
2023-01-24 11:04:38.439450: step: 1140/533, loss: 0.0012285909615457058
2023-01-24 11:04:39.547154: step: 1144/533, loss: 0.002024136483669281
2023-01-24 11:04:40.648511: step: 1148/533, loss: 0.009654855355620384
2023-01-24 11:04:41.756364: step: 1152/533, loss: 0.0031709547620266676
2023-01-24 11:04:42.866160: step: 1156/533, loss: 0.006433273199945688
2023-01-24 11:04:43.974837: step: 1160/533, loss: 0.003206901950761676
2023-01-24 11:04:45.081377: step: 1164/533, loss: 0.004692808724939823
2023-01-24 11:04:46.216526: step: 1168/533, loss: 0.0006139763281680644
2023-01-24 11:04:47.293235: step: 1172/533, loss: 0.0013034525327384472
2023-01-24 11:04:48.383688: step: 1176/533, loss: 0.0006517119472846389
2023-01-24 11:04:49.512660: step: 1180/533, loss: 0.004368583206087351
2023-01-24 11:04:50.636642: step: 1184/533, loss: 0.014883970841765404
2023-01-24 11:04:51.735474: step: 1188/533, loss: 0.0075720855966210365
2023-01-24 11:04:52.850915: step: 1192/533, loss: 0.0028379475697875023
2023-01-24 11:04:53.950641: step: 1196/533, loss: 0.006841960363090038
2023-01-24 11:04:55.081204: step: 1200/533, loss: 0.009573064744472504
2023-01-24 11:04:56.158729: step: 1204/533, loss: 0.0005734837613999844
2023-01-24 11:04:57.256825: step: 1208/533, loss: 0.0028042292688041925
2023-01-24 11:04:58.356437: step: 1212/533, loss: 0.011271877214312553
2023-01-24 11:04:59.451935: step: 1216/533, loss: 0.0005306096863932908
2023-01-24 11:05:00.564638: step: 1220/533, loss: 0.0006685850094072521
2023-01-24 11:05:01.667909: step: 1224/533, loss: 5.8392670325702056e-05
2023-01-24 11:05:02.758863: step: 1228/533, loss: 0.0004614060162566602
2023-01-24 11:05:03.834199: step: 1232/533, loss: 0.0001951318554347381
2023-01-24 11:05:04.944559: step: 1236/533, loss: 0.00031871741521172225
2023-01-24 11:05:06.054194: step: 1240/533, loss: 0.010656261816620827
2023-01-24 11:05:07.129672: step: 1244/533, loss: 0.005999983288347721
2023-01-24 11:05:08.220633: step: 1248/533, loss: 0.0009773006895557046
2023-01-24 11:05:09.321576: step: 1252/533, loss: 0.0024451487697660923
2023-01-24 11:05:10.445397: step: 1256/533, loss: 0.004688398912549019
2023-01-24 11:05:11.562046: step: 1260/533, loss: 0.004382180515676737
2023-01-24 11:05:12.674280: step: 1264/533, loss: 0.05971986800432205
2023-01-24 11:05:13.774854: step: 1268/533, loss: 7.362897304119542e-05
2023-01-24 11:05:14.850517: step: 1272/533, loss: 0.0002789305872283876
2023-01-24 11:05:15.926327: step: 1276/533, loss: 0.00254845037125051
2023-01-24 11:05:17.028034: step: 1280/533, loss: 0.00651832390576601
2023-01-24 11:05:18.124176: step: 1284/533, loss: 0.0008583285380154848
2023-01-24 11:05:19.212270: step: 1288/533, loss: 0.0031015416607260704
2023-01-24 11:05:20.312568: step: 1292/533, loss: 6.418740667868406e-05
2023-01-24 11:05:21.411635: step: 1296/533, loss: 0.010359569452702999
2023-01-24 11:05:22.500280: step: 1300/533, loss: 0.02182219922542572
2023-01-24 11:05:23.567957: step: 1304/533, loss: 0.0
2023-01-24 11:05:24.691285: step: 1308/533, loss: 0.0008588824421167374
2023-01-24 11:05:25.822259: step: 1312/533, loss: 5.2004783356096596e-05
2023-01-24 11:05:26.927410: step: 1316/533, loss: 4.120226003578864e-05
2023-01-24 11:05:28.000155: step: 1320/533, loss: 0.0010942269582301378
2023-01-24 11:05:29.099391: step: 1324/533, loss: 0.0021572564728558064
2023-01-24 11:05:30.193741: step: 1328/533, loss: 0.0023706378415226936
2023-01-24 11:05:31.294706: step: 1332/533, loss: 0.0015674227615818381
2023-01-24 11:05:32.397913: step: 1336/533, loss: 0.003993717487901449
2023-01-24 11:05:33.490531: step: 1340/533, loss: 0.0002113636874128133
2023-01-24 11:05:34.574776: step: 1344/533, loss: 0.0013669751351699233
2023-01-24 11:05:35.681626: step: 1348/533, loss: 0.0037322824355214834
2023-01-24 11:05:36.764168: step: 1352/533, loss: 0.0009304008563049138
2023-01-24 11:05:37.845051: step: 1356/533, loss: 0.005382231902331114
2023-01-24 11:05:38.935194: step: 1360/533, loss: 0.0023384117521345615
2023-01-24 11:05:40.038900: step: 1364/533, loss: 0.0005794452736154199
2023-01-24 11:05:41.135062: step: 1368/533, loss: 0.0079593351110816
2023-01-24 11:05:42.246094: step: 1372/533, loss: 0.003727107774466276
2023-01-24 11:05:43.337445: step: 1376/533, loss: 0.0052826558239758015
2023-01-24 11:05:44.424639: step: 1380/533, loss: 4.365444056020351e-06
2023-01-24 11:05:45.519418: step: 1384/533, loss: 0.0031508812680840492
2023-01-24 11:05:46.615843: step: 1388/533, loss: 0.0007854063296690583
2023-01-24 11:05:47.721449: step: 1392/533, loss: 0.002851440804079175
2023-01-24 11:05:48.830477: step: 1396/533, loss: 1.6273172150249593e-05
2023-01-24 11:05:49.914995: step: 1400/533, loss: 0.00039028949686326087
2023-01-24 11:05:51.056923: step: 1404/533, loss: 0.008089164271950722
2023-01-24 11:05:52.136434: step: 1408/533, loss: 0.002891525160521269
2023-01-24 11:05:53.221388: step: 1412/533, loss: 0.007293758448213339
2023-01-24 11:05:54.316736: step: 1416/533, loss: 0.00438268668949604
2023-01-24 11:05:55.428141: step: 1420/533, loss: 0.0030430308543145657
2023-01-24 11:05:56.540943: step: 1424/533, loss: 0.0009497086284682155
2023-01-24 11:05:57.643391: step: 1428/533, loss: 0.0022427497897297144
2023-01-24 11:05:58.739386: step: 1432/533, loss: 0.00012148274254286662
2023-01-24 11:05:59.842060: step: 1436/533, loss: 0.000617994403000921
2023-01-24 11:06:00.943859: step: 1440/533, loss: 0.002512829378247261
2023-01-24 11:06:02.057641: step: 1444/533, loss: 0.0034312389325350523
2023-01-24 11:06:03.139075: step: 1448/533, loss: 0.0034534542355686426
2023-01-24 11:06:04.232103: step: 1452/533, loss: 0.002732381224632263
2023-01-24 11:06:05.327213: step: 1456/533, loss: 7.135634859878337e-06
2023-01-24 11:06:06.428538: step: 1460/533, loss: 0.0032151222694665194
2023-01-24 11:06:07.523656: step: 1464/533, loss: 0.0019357663113623857
2023-01-24 11:06:08.615812: step: 1468/533, loss: 0.0003057916765101254
2023-01-24 11:06:09.684866: step: 1472/533, loss: 0.0005933460779488087
2023-01-24 11:06:10.757437: step: 1476/533, loss: 0.0024123084731400013
2023-01-24 11:06:11.852119: step: 1480/533, loss: 1.3655290786118712e-05
2023-01-24 11:06:12.943255: step: 1484/533, loss: 1.7892021787702106e-05
2023-01-24 11:06:14.050643: step: 1488/533, loss: 4.831738260691054e-05
2023-01-24 11:06:15.138343: step: 1492/533, loss: 6.638347986154258e-05
2023-01-24 11:06:16.225834: step: 1496/533, loss: 0.018753638491034508
2023-01-24 11:06:17.324444: step: 1500/533, loss: 0.0020794819574803114
2023-01-24 11:06:18.432295: step: 1504/533, loss: 0.00012263053213246167
2023-01-24 11:06:19.556390: step: 1508/533, loss: 0.0005290747503750026
2023-01-24 11:06:20.653470: step: 1512/533, loss: 0.0012176078744232655
2023-01-24 11:06:21.767638: step: 1516/533, loss: 0.001087386510334909
2023-01-24 11:06:22.861922: step: 1520/533, loss: 0.0015819676918908954
2023-01-24 11:06:23.976786: step: 1524/533, loss: 0.008475600741803646
2023-01-24 11:06:25.081263: step: 1528/533, loss: 0.02004097029566765
2023-01-24 11:06:26.177799: step: 1532/533, loss: 8.594460814492777e-05
2023-01-24 11:06:27.284342: step: 1536/533, loss: 0.005688393488526344
2023-01-24 11:06:28.391545: step: 1540/533, loss: 0.0027153342962265015
2023-01-24 11:06:29.499227: step: 1544/533, loss: 0.002307295799255371
2023-01-24 11:06:30.581606: step: 1548/533, loss: 0.00024789926828816533
2023-01-24 11:06:31.694673: step: 1552/533, loss: 0.0014466815628111362
2023-01-24 11:06:32.793761: step: 1556/533, loss: 0.0037533852737396955
2023-01-24 11:06:33.907932: step: 1560/533, loss: 0.0006833667866885662
2023-01-24 11:06:35.006437: step: 1564/533, loss: 2.1916464902460575e-05
2023-01-24 11:06:36.110229: step: 1568/533, loss: 0.00241021323017776
2023-01-24 11:06:37.191996: step: 1572/533, loss: 0.00027759786462411284
2023-01-24 11:06:38.270019: step: 1576/533, loss: 2.7420817332313163e-06
2023-01-24 11:06:39.356804: step: 1580/533, loss: 0.00017048879817593843
2023-01-24 11:06:40.436733: step: 1584/533, loss: 0.004882603883743286
2023-01-24 11:06:41.544556: step: 1588/533, loss: 0.004991601221263409
2023-01-24 11:06:42.650756: step: 1592/533, loss: 6.55549592920579e-05
2023-01-24 11:06:43.738575: step: 1596/533, loss: 9.808763570617884e-05
2023-01-24 11:06:44.878600: step: 1600/533, loss: 0.0008361959480680525
2023-01-24 11:06:45.987453: step: 1604/533, loss: 0.002129750791937113
2023-01-24 11:06:47.080488: step: 1608/533, loss: 0.0001057552799466066
2023-01-24 11:06:48.198588: step: 1612/533, loss: 0.0066966712474823
2023-01-24 11:06:49.289464: step: 1616/533, loss: 0.001488488749600947
2023-01-24 11:06:50.386673: step: 1620/533, loss: 0.0023336259182542562
2023-01-24 11:06:51.477023: step: 1624/533, loss: 0.004367019049823284
2023-01-24 11:06:52.571865: step: 1628/533, loss: 0.00048620314919389784
2023-01-24 11:06:53.662100: step: 1632/533, loss: 3.3007727324729785e-05
2023-01-24 11:06:54.758951: step: 1636/533, loss: 0.00065714301308617
2023-01-24 11:06:55.860342: step: 1640/533, loss: 0.001794257084839046
2023-01-24 11:06:56.957294: step: 1644/533, loss: 0.004419530741870403
2023-01-24 11:06:58.055460: step: 1648/533, loss: 0.0005958147230558097
2023-01-24 11:06:59.125616: step: 1652/533, loss: 1.628181962587405e-06
2023-01-24 11:07:00.218583: step: 1656/533, loss: 0.0006447355845011771
2023-01-24 11:07:01.292349: step: 1660/533, loss: 9.899061979012913e-07
2023-01-24 11:07:02.374797: step: 1664/533, loss: 0.003182790009304881
2023-01-24 11:07:03.462987: step: 1668/533, loss: 0.0003024760808330029
2023-01-24 11:07:04.533903: step: 1672/533, loss: 0.0004480490169953555
2023-01-24 11:07:05.627469: step: 1676/533, loss: 0.0002015163190662861
2023-01-24 11:07:06.715904: step: 1680/533, loss: 0.0002091509522870183
2023-01-24 11:07:07.811226: step: 1684/533, loss: 0.015574702993035316
2023-01-24 11:07:08.936574: step: 1688/533, loss: 0.001094275969080627
2023-01-24 11:07:10.030062: step: 1692/533, loss: 3.002250196004752e-05
2023-01-24 11:07:11.126265: step: 1696/533, loss: 0.000414376292610541
2023-01-24 11:07:12.207716: step: 1700/533, loss: 0.009045393206179142
2023-01-24 11:07:13.292481: step: 1704/533, loss: 0.000743130745831877
2023-01-24 11:07:14.386154: step: 1708/533, loss: 0.001196467550471425
2023-01-24 11:07:15.494687: step: 1712/533, loss: 0.0024691226426512003
2023-01-24 11:07:16.600677: step: 1716/533, loss: 0.00574424909427762
2023-01-24 11:07:17.684583: step: 1720/533, loss: 0.0007722361478954554
2023-01-24 11:07:18.775890: step: 1724/533, loss: 0.005464841611683369
2023-01-24 11:07:19.865193: step: 1728/533, loss: 2.3082266125129536e-06
2023-01-24 11:07:20.945181: step: 1732/533, loss: 0.0009892795933410525
2023-01-24 11:07:22.033887: step: 1736/533, loss: 0.00418660556897521
2023-01-24 11:07:23.127462: step: 1740/533, loss: 0.0005477951490320265
2023-01-24 11:07:24.209457: step: 1744/533, loss: 0.0034859757870435715
2023-01-24 11:07:25.307169: step: 1748/533, loss: 0.0002277175517519936
2023-01-24 11:07:26.395379: step: 1752/533, loss: 0.0006597511237487197
2023-01-24 11:07:27.488398: step: 1756/533, loss: 0.0010649014730006456
2023-01-24 11:07:28.575839: step: 1760/533, loss: 6.695041065540863e-06
2023-01-24 11:07:29.664959: step: 1764/533, loss: 0.001699916087090969
2023-01-24 11:07:30.754215: step: 1768/533, loss: 2.969097113236785e-05
2023-01-24 11:07:31.839840: step: 1772/533, loss: 0.0032967152073979378
2023-01-24 11:07:32.942356: step: 1776/533, loss: 0.002681987127289176
2023-01-24 11:07:34.012927: step: 1780/533, loss: 0.0028065908700227737
2023-01-24 11:07:35.128074: step: 1784/533, loss: 0.0006567779346369207
2023-01-24 11:07:36.227127: step: 1788/533, loss: 0.0028243050910532475
2023-01-24 11:07:37.332930: step: 1792/533, loss: 0.005447614472359419
2023-01-24 11:07:38.421116: step: 1796/533, loss: 0.017580104991793633
2023-01-24 11:07:39.501235: step: 1800/533, loss: 0.02638031169772148
2023-01-24 11:07:40.612166: step: 1804/533, loss: 0.000991424429230392
2023-01-24 11:07:41.710782: step: 1808/533, loss: 0.0034624021500349045
2023-01-24 11:07:42.823958: step: 1812/533, loss: 0.004007275681942701
2023-01-24 11:07:43.932080: step: 1816/533, loss: 0.0014018678339198232
2023-01-24 11:07:45.028287: step: 1820/533, loss: 0.00010253865184495226
2023-01-24 11:07:46.124600: step: 1824/533, loss: 0.0008420667727477849
2023-01-24 11:07:47.247176: step: 1828/533, loss: 0.0020046657882630825
2023-01-24 11:07:48.336563: step: 1832/533, loss: 1.3327510714589152e-05
2023-01-24 11:07:49.460682: step: 1836/533, loss: 0.0039538051933050156
2023-01-24 11:07:50.569561: step: 1840/533, loss: 0.010382239706814289
2023-01-24 11:07:51.658229: step: 1844/533, loss: 0.0003220579819753766
2023-01-24 11:07:52.754796: step: 1848/533, loss: 5.9047895774710923e-05
2023-01-24 11:07:53.839034: step: 1852/533, loss: 0.013473790138959885
2023-01-24 11:07:54.948300: step: 1856/533, loss: 0.0008254739223048091
2023-01-24 11:07:56.028371: step: 1860/533, loss: 2.2900270778336562e-05
2023-01-24 11:07:57.120545: step: 1864/533, loss: 0.00048197247087955475
2023-01-24 11:07:58.192626: step: 1868/533, loss: 2.8974426413697074e-08
2023-01-24 11:07:59.298843: step: 1872/533, loss: 0.00024738535284996033
2023-01-24 11:08:00.447496: step: 1876/533, loss: 1.7155516616185196e-05
2023-01-24 11:08:01.527271: step: 1880/533, loss: 0.0013291644863784313
2023-01-24 11:08:02.627093: step: 1884/533, loss: 0.010741009376943111
2023-01-24 11:08:03.729239: step: 1888/533, loss: 0.004338882863521576
2023-01-24 11:08:04.818228: step: 1892/533, loss: 0.0
2023-01-24 11:08:05.925845: step: 1896/533, loss: 6.663255771854892e-05
2023-01-24 11:08:07.026614: step: 1900/533, loss: 0.005636206828057766
2023-01-24 11:08:08.120350: step: 1904/533, loss: 0.00020264896738808602
2023-01-24 11:08:09.222937: step: 1908/533, loss: 5.6227338063763455e-05
2023-01-24 11:08:10.338267: step: 1912/533, loss: 0.010780072771012783
2023-01-24 11:08:11.419534: step: 1916/533, loss: 0.0010127476416528225
2023-01-24 11:08:12.502000: step: 1920/533, loss: 0.00031271445914171636
2023-01-24 11:08:13.613025: step: 1924/533, loss: 0.004049594048410654
2023-01-24 11:08:14.695940: step: 1928/533, loss: 1.3771966678177705e-06
2023-01-24 11:08:15.803626: step: 1932/533, loss: 0.0007767128408886492
2023-01-24 11:08:16.918724: step: 1936/533, loss: 0.01138350274413824
2023-01-24 11:08:18.013980: step: 1940/533, loss: 0.0029184913728386164
2023-01-24 11:08:19.080603: step: 1944/533, loss: 2.8658714654739015e-05
2023-01-24 11:08:20.205406: step: 1948/533, loss: 0.0029728123918175697
2023-01-24 11:08:21.286653: step: 1952/533, loss: 0.00012695933401118964
2023-01-24 11:08:22.418496: step: 1956/533, loss: 0.0025797307025641203
2023-01-24 11:08:23.515720: step: 1960/533, loss: 5.357843747333391e-06
2023-01-24 11:08:24.591738: step: 1964/533, loss: 1.665156196395401e-05
2023-01-24 11:08:25.695875: step: 1968/533, loss: 0.0020268098451197147
2023-01-24 11:08:26.819912: step: 1972/533, loss: 0.0027595118153840303
2023-01-24 11:08:27.932391: step: 1976/533, loss: 0.0019997854251414537
2023-01-24 11:08:29.029945: step: 1980/533, loss: 0.00260147824883461
2023-01-24 11:08:30.142003: step: 1984/533, loss: 0.0014527341118082404
2023-01-24 11:08:31.245830: step: 1988/533, loss: 0.0036564692854881287
2023-01-24 11:08:32.349234: step: 1992/533, loss: 0.003292633220553398
2023-01-24 11:08:33.464835: step: 1996/533, loss: 0.005945717915892601
2023-01-24 11:08:34.560099: step: 2000/533, loss: 0.0002162624878110364
2023-01-24 11:08:35.648981: step: 2004/533, loss: 0.000398698408389464
2023-01-24 11:08:36.753053: step: 2008/533, loss: 0.00036622743937186897
2023-01-24 11:08:37.857057: step: 2012/533, loss: 0.0052780769765377045
2023-01-24 11:08:38.952955: step: 2016/533, loss: 0.000446510937763378
2023-01-24 11:08:40.061933: step: 2020/533, loss: 0.0014261852484196424
2023-01-24 11:08:41.161139: step: 2024/533, loss: 0.00015211921709124
2023-01-24 11:08:42.275480: step: 2028/533, loss: 0.007753189653158188
2023-01-24 11:08:43.381170: step: 2032/533, loss: 2.3495354980695993e-05
2023-01-24 11:08:44.465013: step: 2036/533, loss: 2.7041593853027734e-07
2023-01-24 11:08:45.556611: step: 2040/533, loss: 0.0005524296429939568
2023-01-24 11:08:46.667187: step: 2044/533, loss: 0.00249215099029243
2023-01-24 11:08:47.756458: step: 2048/533, loss: 5.967829201836139e-05
2023-01-24 11:08:48.861717: step: 2052/533, loss: 0.00015757069922983646
2023-01-24 11:08:49.982971: step: 2056/533, loss: 8.028579759411514e-05
2023-01-24 11:08:51.090736: step: 2060/533, loss: 0.0005603015306405723
2023-01-24 11:08:52.201212: step: 2064/533, loss: 0.009193070232868195
2023-01-24 11:08:53.293054: step: 2068/533, loss: 0.0001603877462912351
2023-01-24 11:08:54.397601: step: 2072/533, loss: 0.003062947653234005
2023-01-24 11:08:55.493859: step: 2076/533, loss: 0.005343954544514418
2023-01-24 11:08:56.560573: step: 2080/533, loss: 5.159346073924098e-06
2023-01-24 11:08:57.657506: step: 2084/533, loss: 0.001257540425285697
2023-01-24 11:08:58.745168: step: 2088/533, loss: 0.0067181335762143135
2023-01-24 11:08:59.849003: step: 2092/533, loss: 0.00029405279201455414
2023-01-24 11:09:00.970831: step: 2096/533, loss: 0.001057903398759663
2023-01-24 11:09:02.085212: step: 2100/533, loss: 0.0001481717627029866
2023-01-24 11:09:03.186370: step: 2104/533, loss: 0.001032595755532384
2023-01-24 11:09:04.289389: step: 2108/533, loss: 1.1622406645983574e-06
2023-01-24 11:09:05.381240: step: 2112/533, loss: 0.00018516559794079512
2023-01-24 11:09:06.493554: step: 2116/533, loss: 0.005244530271738768
2023-01-24 11:09:07.597303: step: 2120/533, loss: 0.002081845421344042
2023-01-24 11:09:08.724969: step: 2124/533, loss: 0.006011663936078548
2023-01-24 11:09:09.825213: step: 2128/533, loss: 0.006045818794518709
2023-01-24 11:09:10.943283: step: 2132/533, loss: 0.00037411859375424683
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3835622710622711, 'r': 0.33115907653383936, 'f1': 0.35543957909029195}, 'combined': 0.2619028477507414, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39751284320187086, 'r': 0.3604371260955425, 'f1': 0.37806819076083126}, 'combined': 0.25204546050722076, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35864576575298035, 'r': 0.3212159420026693, 'f1': 0.3389005033741876}, 'combined': 0.24971616038098032, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39066172630615287, 'r': 0.31102683594374475, 'f1': 0.3463253847767608}, 'combined': 0.2308835898511738, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3465753637607263, 'r': 0.3110628976448264, 'f1': 0.32786029411764706}, 'combined': 0.2415812693498452, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38455992503062475, 'r': 0.34721324000361214, 'f1': 0.3649335721109213}, 'combined': 0.2432890480739475, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.45652173913043476, 'f1': 0.5675675675675675}, 'combined': 0.37837837837837834, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3859148550724638, 'r': 0.3368516761543327, 'f1': 0.35971800067544746}, 'combined': 0.26505536891875076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.39543910536932264, 'r': 0.3555149649233814, 'f1': 0.37441576052690295}, 'combined': 0.24961050701793525, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2936046511627907, 'r': 0.3607142857142857, 'f1': 0.32371794871794873}, 'combined': 0.21581196581196582, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3621905610201861, 'r': 0.32026717539925376, 'f1': 0.3399411912092784}, 'combined': 0.2504829829963104, 'stategy': 1, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38557998711346425, 'r': 0.3054979897898986, 'f1': 0.34089904440074525}, 'combined': 0.2272660296004968, 'stategy': 1, 'epoch': 7}
Korean: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.75, 'r': 0.4891304347826087, 'f1': 0.5921052631578948}, 'combined': 0.39473684210526316, 'stategy': 1, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35048248859292147, 'r': 0.31722988056702756, 'f1': 0.33302818139207874}, 'combined': 0.2453891862889001, 'stategy': 1, 'epoch': 16}
Test for Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5196850393700787, 'f1': 0.6666666666666665}, 'slot': {'p': 0.38299654503075575, 'r': 0.34432862461899677, 'f1': 0.3626347033962093}, 'combined': 0.24175646893080613, 'stategy': 1, 'epoch': 16}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.27586206896551724, 'f1': 0.3902439024390244}, 'combined': 0.26016260162601623, 'stategy': 1, 'epoch': 16}